update citus images and hosts, to generate helm charts

During the network split some Etcd nodes could become stale, however they are still available for read requests. It is not a problem for the old primary, because such etcd nodes are not writable and primary demotes when fails to update the leader lock.

When the network split resolves and Etcd node connects back to the cluster, it may trigger the leader election (in Etcd), what typically results in some failures of client requests. Such state quickly resolves, and client requests could be retried. but it takes some time for the disconnected node to catch up. During this time it shows stale data for read requests without quorum requirement.

It could happen that the current Patroni primary is impacted by failed client requests while Etcd cluster is doing leader elections and there is a chance that it may switch to the stale Etcd node, discover that someone else is a leader, and demote.

To protect from this situation we will memorize the last known "term" of the Etcd cluster and when executing client requests we will compare the "term" reported by Etcd node with the term we memorized. It allows to detect stale Etcd nodes and temporary ignore them by switching to some other available Etcd nodes.

An alternative approach to solve this problem would be using quorum/serializable reads for read requests, but it will increase resource usage on Etcd nodes.

Close #3314

.github/workflows/install_deps.py

@@ -9,6 +9,11 @@ import zipfile
 
 
 def install_requirements(what):
+    subprocess.call([sys.executable, '-m', 'pip', 'install', '--upgrade', 'pip'])
+    s = subprocess.call([sys.executable, '-m', 'pip', 'install', '--upgrade', 'wheel', 'setuptools'])
+    if s != 0:
+        return s
+
     old_path = sys.path[:]
     w = os.path.join(os.getcwd(), os.path.dirname(inspect.getfile(inspect.currentframe())))
     sys.path.insert(0, os.path.dirname(os.path.dirname(w)))
@@ -16,23 +21,25 @@ def install_requirements(what):
         from setup import EXTRAS_REQUIRE, read
     finally:
         sys.path = old_path
-    requirements = ['mock>=2.0.0', 'flake8', 'pytest', 'pytest-cov'] if what == 'all' else ['behave']
+    requirements = ['flake8', 'pytest', 'pytest-cov'] if what == 'all' else ['behave']
     requirements += ['coverage']
     # try to split tests between psycopg2 and psycopg3
     requirements += ['psycopg[binary]'] if sys.version_info >= (3, 8, 0) and\
-        (sys.platform != 'darwin' or what == 'etcd3') else ['psycopg2-binary']
-    for r in read('requirements.txt').split('\n'):
-        r = r.strip()
-        if r != '':
-            extras = {e for e, v in EXTRAS_REQUIRE.items() if v and any(r.startswith(x) for x in v)}
-            if not extras or what == 'all' or what in extras:
-                requirements.append(r)
+        (sys.platform != 'darwin' or what == 'etcd3') else ['psycopg2-binary==2.9.9' 
+                                                            if sys.platform == 'darwin' else 'psycopg2-binary']
 
-    subprocess.call([sys.executable, '-m', 'pip', 'install', '--upgrade', 'pip'])
-    subprocess.call([sys.executable, '-m', 'pip', 'install', '--upgrade', 'wheel'])
-    r = subprocess.call([sys.executable, '-m', 'pip', 'install'] + requirements)
-    s = subprocess.call([sys.executable, '-m', 'pip', 'install', '--upgrade', 'setuptools'])
-    return s | r
+    from pip._vendor.distlib.markers import evaluator, DEFAULT_CONTEXT
+    from pip._vendor.distlib.util import parse_requirement
+
+    for r in read('requirements.txt').split('\n'):
+        r = parse_requirement(r)
+        if not r or r.marker and not evaluator.evaluate(r.marker, DEFAULT_CONTEXT):
+            continue
+        extras = {e for e, v in EXTRAS_REQUIRE.items() if v and any(r.requirement.startswith(x) for x in v)}
+        if not extras or what == 'all' or what in extras:
+            requirements.append(r.requirement)
+
+    return subprocess.call([sys.executable, '-m', 'pip', 'install'] + requirements)
 
 
 def install_packages(what):
@@ -45,8 +52,8 @@ def install_packages(what):
     packages['exhibitor'] = packages['zookeeper']
     packages = packages.get(what, [])
     ver = versions.get(what)
-    if float(ver) >= 15:
-        packages += ['postgresql-{0}-citus-11.2'.format(ver)]
+    if 15 <= float(ver) < 18:
+        packages += ['postgresql-{0}-citus-13.0'.format(ver)]
     subprocess.call(['sudo', 'apt-get', 'update', '-y'])
     return subprocess.call(['sudo', 'apt-get', 'install', '-y', 'postgresql-' + ver, 'expect-dev'] + packages)
 
@@ -110,7 +117,7 @@ def install_etcd():
 
 
 def install_postgres():
-    version = os.environ.get('PGVERSION', '15.1-1')
+    version = os.environ.get('PGVERSION', '16.1-1')
     platform = {'darwin': 'osx', 'win32': 'windows-x64', 'cygwin': 'windows-x64'}[sys.platform]
     if platform == 'osx':
         return subprocess.call(['brew', 'install', 'expect', 'postgresql@{0}'.format(version.split('.')[0])])

.github/workflows/mapping.py

@@ -1 +1 @@
-versions = {'etcd': '9.6', 'etcd3': '14', 'consul': '13', 'exhibitor': '12', 'raft': '11', 'kubernetes': '15'}
+versions = {'etcd': '9.6', 'etcd3': '16', 'consul': '17', 'exhibitor': '12', 'raft': '14', 'kubernetes': '15'}

.github/workflows/release.yaml

@@ -10,13 +10,15 @@ jobs:
   build-n-publish:
     name: Build and publish Patroni distributions to PyPI and TestPyPI
     runs-on: ubuntu-latest
+    permissions:
+      id-token: write
     steps:
-    - uses: actions/checkout@master
+    - uses: actions/checkout@v4
 
-    - name: Set up Python 3.9
-      uses: actions/setup-python@v4
+    - name: Set up Python 3.11
+      uses: actions/setup-python@v5
       with:
-        python-version: 3.9
+        python-version: 3.11
 
     - name: Install dependencies
       run: python .github/workflows/install_deps.py
@@ -24,18 +26,18 @@ jobs:
     - name: Run tests and flake8
       run: python .github/workflows/run_tests.py
 
+    - name: Install Python packaging build frontend
+      run: python -m pip install build
+
     - name: Build a binary wheel and a source tarball
-      run: python setup.py sdist bdist_wheel
+      run: python -m build
 
     - name: Publish distribution to Test PyPI
       if: github.event_name == 'push'
-      uses: pypa/gh-action-pypi-publish@v1.5.1
+      uses: pypa/gh-action-pypi-publish@v1.9.0
       with:
-        password: ${{ secrets.TEST_PYPI_API_TOKEN }}
         repository_url: https://test.pypi.org/legacy/
 
     - name: Publish distribution to PyPI
       if: github.event_name == 'release'
-      uses: pypa/gh-action-pypi-publish@v1.5.1
-      with:
-        password: ${{ secrets.PYPI_API_TOKEN }}
+      uses: pypa/gh-action-pypi-publish@v1.9.0

.github/workflows/run_tests.py

@@ -27,11 +27,11 @@ def main():
 
         version = versions.get(what)
         path = '/usr/lib/postgresql/{0}/bin:.'.format(version)
-        unbuffer = ['timeout', '900', 'unbuffer']
+        unbuffer = ['timeout', '1200', 'unbuffer']
     else:
         if sys.platform == 'darwin':
-            version = os.environ.get('PGVERSION', '15.1-1')
-            path = '/usr/local/opt/postgresql@{0}/bin:.'.format(version.split('.')[0])
+            version = os.environ.get('PGVERSION', '16.1-1')
+            path = '/opt/homebrew/opt/postgresql@{0}/bin:.'.format(version.split('.')[0])
             unbuffer = ['unbuffer']
         else:
             path = os.path.abspath(os.path.join('pgsql', 'bin'))

.github/workflows/tests.yaml

@@ -5,6 +5,7 @@ on:
   push:
     branches:
     - master
+    - 'REL_[0-9]+_[0-9]+'
 
 env:
   CODACY_PROJECT_TOKEN: ${{ secrets.CODACY_PROJECT_TOKEN }}
@@ -12,26 +13,29 @@ env:
 
 jobs:
   unit:
-    runs-on: ${{ matrix.os }}-latest
+    runs-on: ${{ fromJson('{"ubuntu":"ubuntu-22.04","windows":"windows-latest","macos":"macos-latest"}')[matrix.os] }}
     strategy:
       fail-fast: false
       matrix:
         os: [ubuntu, windows, macos]
 
     steps:
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v4
 
     - name: Set up Python 3.7
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v5
       with:
         python-version: 3.7
+      if: matrix.os != 'macos'
     - name: Install dependencies
       run: python .github/workflows/install_deps.py
+      if: matrix.os != 'macos'
     - name: Run tests and flake8
       run: python .github/workflows/run_tests.py
+      if: matrix.os != 'macos'
 
     - name: Set up Python 3.8
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v5
       with:
         python-version: 3.8
     - name: Install dependencies
@@ -40,7 +44,7 @@ jobs:
       run: python .github/workflows/run_tests.py
 
     - name: Set up Python 3.9
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v5
       with:
         python-version: 3.9
     - name: Install dependencies
@@ -49,7 +53,7 @@ jobs:
       run: python .github/workflows/run_tests.py
 
     - name: Set up Python 3.10
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v5
       with:
         python-version: '3.10'
     - name: Install dependencies
@@ -58,7 +62,7 @@ jobs:
       run: python .github/workflows/run_tests.py
 
     - name: Set up Python 3.11
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v5
       with:
         python-version: 3.11
     - name: Install dependencies
@@ -66,6 +70,27 @@ jobs:
     - name: Run tests and flake8
       run: python .github/workflows/run_tests.py
 
+    - name: Set up Python 3.12
+      uses: actions/setup-python@v5
+      with:
+        python-version: 3.12
+    - name: Install dependencies
+      run: python .github/workflows/install_deps.py
+    - name: Run tests and flake8
+      run: python .github/workflows/run_tests.py
+
+    - name: Set up Python 3.13
+      uses: actions/setup-python@v5
+      with:
+        python-version: 3.13
+      if: matrix.os != 'macos'
+    - name: Install dependencies
+      run: python .github/workflows/install_deps.py
+      if: matrix.os != 'macos'
+    - name: Run tests and flake8
+      run: python .github/workflows/run_tests.py
+      if: matrix.os != 'macos'
+
     - name: Combine coverage
       run: python .github/workflows/run_tests.py combine
 
@@ -80,16 +105,16 @@ jobs:
       run: python -m coveralls --service=github
 
   behave:
-    runs-on: ${{ matrix.os }}-latest
+    runs-on: ${{ fromJson('{"ubuntu":"ubuntu-22.04","windows":"windows-latest","macos":"macos-latest"}')[matrix.os] }}
     env:
       DCS: ${{ matrix.dcs }}
       ETCDVERSION: 3.4.23
-      PGVERSION: 15.1-1  # for windows and macos
+      PGVERSION: 16.1-1  # for windows and macos
     strategy:
       fail-fast: false
       matrix:
         os: [ubuntu]
-        python-version: [3.7, '3.10']
+        python-version: [3.7, 3.13]
         dcs: [etcd, etcd3, consul, exhibitor, kubernetes, raft]
         include:
         - os: macos
@@ -103,9 +128,9 @@ jobs:
           dcs: etcd3
 
     steps:
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v4
     - name: Set up Python
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v5
       with:
         python-version: ${{ matrix.python-version }}
     - uses: nolar/setup-k3d-k3s@v1
@@ -124,12 +149,12 @@ jobs:
     - name: Run behave tests
       run: python .github/workflows/run_tests.py
     - name: Upload logs if behave failed
-      uses: actions/upload-artifact@v3
+      uses: actions/upload-artifact@v4
       if: failure()
       with:
         name: behave-${{ matrix.os }}-${{ matrix.dcs }}-${{ matrix.python-version }}-logs
         path: |
-          features/output/*_failed/*postgres?.*
+          features/output/*_failed/*postgres-?.*
           features/output/*.log
         if-no-files-found: error
         retention-days: 5
@@ -144,7 +169,7 @@ jobs:
     needs: unit
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/setup-python@v4
+    - uses: actions/setup-python@v5
     - run: python -m pip install coveralls
     - run: python -m coveralls --service=github --finish
       env:
@@ -161,27 +186,44 @@ jobs:
   pyright:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v4
 
-    - name: Set up Python 3.11
-      uses: actions/setup-python@v4
+    - name: Set up Python 3.13
+      uses: actions/setup-python@v5
       with:
-        python-version: 3.11
+        python-version: 3.13
 
     - name: Install dependencies
       run: python -m pip install -r requirements.txt psycopg2-binary psycopg
 
-    - uses: jakebailey/pyright-action@v1
+    - uses: jakebailey/pyright-action@v2
       with:
-        version: 1.1.320
+        version: 1.1.394
+
+  ydiff:
+    name: Test compatibility with the latest version of ydiff
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+
+    - name: Set up Python 3.13
+      uses: actions/setup-python@v5
+      with:
+        python-version: 3.13
+    - name: Install dependencies
+      run: python .github/workflows/install_deps.py
+    - name: Update ydiff
+      run: python -m pip install -U ydiff
+    - name: Run tests
+      run: python -m pytest tests/test_ctl.py -v
 
   docs:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v4
 
     - name: Set up Python 3.11
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v5
       with:
         python-version: 3.11
         cache: pip
@@ -198,3 +240,20 @@ jobs:
 
     - name: Generate documentation
       run: tox -m docs
+
+  isort:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+
+    - name: Set up Python 3.12
+      uses: actions/setup-python@v5
+      with:
+        python-version: 3.12
+        cache: pip
+
+    - name: isort
+      uses: isort/isort-action@master
+      with:
+        requirementsFiles: "requirements.txt requirements.dev.txt requirements.docs.txt"
+        sort-paths: "patroni tests features setup.py"

.gitignore

@@ -27,14 +27,15 @@ lib64
 pip-log.txt
 
 # Unit test / coverage reports
-.coverage
+.coverage*
 .tox
 nosetests.xml
 coverage.xml
 htmlcov
 junit.xml
-features/output
+features/output*
 dummy
+result.json
 
 # Translations
 *.mo
@@ -48,10 +49,12 @@ pgpass
 scm-source.json
 
 # Sphinx-generated documentation
+docs/_build/
 docs/build/
 docs/source/_static/
 docs/source/_templates/
 docs/modules/
+docs/pdf/
 
 # Pycharm IDE
 .idea/

Dockerfile

@@ -1,6 +1,6 @@
 ## This Dockerfile is meant to aid in the building and debugging patroni whilst developing on your local machine
 ## It has all the necessary components to play/debug with a single node appliance, running etcd
-ARG PG_MAJOR=15
+ARG PG_MAJOR=16
 ARG COMPRESS=false
 ARG PGHOME=/home/postgres
 ARG PGDATA=$PGHOME/data
@@ -94,9 +94,9 @@ RUN set -ex \
         /usr/share/locale/??_?? \
         /usr/share/postgresql/*/man \
         /usr/share/postgresql-common/pg_wrapper \
-        /usr/share/vim/vim80/doc \
-        /usr/share/vim/vim80/lang \
-        /usr/share/vim/vim80/tutor \
+        /usr/share/vim/vim*/doc \
+        /usr/share/vim/vim*/lang \
+        /usr/share/vim/vim*/tutor \
 #        /var/lib/dpkg/info/* \
     && find /usr/bin -xtype l -delete \
     && find /var/log -type f -exec truncate --size 0 {} \; \
@@ -125,6 +125,8 @@ RUN if [ "$COMPRESS" = "true" ]; then \
         && /bin/busybox sh -c "(find $save_dirs -not -type d && cat /exclude /exclude && echo exclude) | sort | uniq -u | xargs /bin/busybox rm" \
         && /bin/busybox --install -s \
         && /bin/busybox sh -c "find $save_dirs -type d -depth -exec rmdir -p {} \; 2> /dev/null"; \
+    else \
+        /bin/busybox --install -s; \
     fi
 
 FROM scratch
@@ -143,6 +145,7 @@ ARG PGBIN=/usr/lib/postgresql/$PG_MAJOR/bin
 
 ENV LC_ALL=$LC_ALL LANG=$LANG EDITOR=/usr/bin/editor
 ENV PGDATA=$PGDATA PATH=$PATH:$PGBIN
+ENV ETCDCTL_API=3
 
 COPY patroni /patroni/
 COPY extras/confd/conf.d/haproxy.toml /etc/confd/conf.d/

Dockerfile.citus

@@ -1,13 +1,13 @@
 ## This Dockerfile is meant to aid in the building and debugging patroni whilst developing on your local machine
 ## It has all the necessary components to play/debug with a single node appliance, running etcd
-ARG PG_MAJOR=15
+ARG PG_MAJOR=16
 ARG COMPRESS=false
 ARG PGHOME=/home/postgres
 ARG PGDATA=$PGHOME/data
 ARG LC_ALL=C.UTF-8
 ARG LANG=C.UTF-8
 
-FROM postgres:$PG_MAJOR as builder
+FROM postgres:$PG_MAJOR AS builder
 
 ARG PGHOME
 ARG PGDATA
@@ -40,7 +40,7 @@ RUN set -ex \
         echo "deb [signed-by=/etc/apt/trusted.gpg.d/citusdata_community.gpg] https://packagecloud.io/citusdata/community/debian/ $(lsb_release -cs) main" > /etc/apt/sources.list.d/citusdata_community.list \
         && curl -sL https://packagecloud.io/citusdata/community/gpgkey | gpg --dearmor > /etc/apt/trusted.gpg.d/citusdata_community.gpg \
         && apt-get update -y \
-        && apt-get -y install postgresql-$PG_MAJOR-citus-11.3; \
+        && apt-get -y install postgresql-$PG_MAJOR-citus-12.1; \
     fi \
 \
     # Cleanup all locales but en_US.UTF-8
@@ -113,9 +113,9 @@ RUN set -ex \
         /usr/share/locale/??_?? \
         /usr/share/postgresql/*/man \
         /usr/share/postgresql-common/pg_wrapper \
-        /usr/share/vim/vim80/doc \
-        /usr/share/vim/vim80/lang \
-        /usr/share/vim/vim80/tutor \
+        /usr/share/vim/vim*/doc \
+        /usr/share/vim/vim*/lang \
+        /usr/share/vim/vim*/tutor \
 #        /var/lib/dpkg/info/* \
     && find /usr/bin -xtype l -delete \
     && find /var/log -type f -exec truncate --size 0 {} \; \
@@ -164,6 +164,7 @@ ARG PGBIN=/usr/lib/postgresql/$PG_MAJOR/bin
 
 ENV LC_ALL=$LC_ALL LANG=$LANG EDITOR=/usr/bin/editor
 ENV PGDATA=$PGDATA PATH=$PATH:$PGBIN
+ENV ETCDCTL_API=3
 
 COPY patroni /patroni/
 COPY extras/confd/conf.d/haproxy.toml /etc/confd/conf.d/
@@ -179,7 +180,7 @@ RUN sed -i 's/env python/&3/' /patroni*.py \
     && sed -i "s|^\(  data_dir: \).*|\1$PGDATA|" postgres?.yml \
     && sed -i "s|^#\(  bin_dir: \).*|\1$PGBIN|" postgres?.yml \
     && sed -i 's/^  - encoding: UTF8/  - locale: en_US.UTF-8\n&/' postgres?.yml \
-    && sed -i 's/^scope:/log:\n  loggers:\n    patroni.postgresql.citus: DEBUG\n#&/' postgres?.yml \
+    && sed -i 's/^scope:/log:\n  loggers:\n    patroni.postgresql.mpp.citus: DEBUG\n#&/' postgres?.yml \
     && sed -i 's/^\(name\|etcd\|  host\|  authentication\|  connect_address\|  parameters\):/#&/' postgres?.yml \
     && sed -i 's/^    \(replication\|superuser\|rewind\|unix_socket_directories\|\(\(  \)\{0,1\}\(username\|password\)\)\):/#&/' postgres?.yml \
     && sed -i 's/^postgresql:/&\n  basebackup:\n    checkpoint: fast/' postgres?.yml \

LICENSE

@@ -1,6 +1,6 @@
 The MIT License (MIT)
 
-Copyright (c) 2015 Compose, Zalando SE
+Copyright (c) 2025 Compose, Zalando SE, Patroni Contributors
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

README.rst

@@ -12,11 +12,11 @@ Patroni is a template for high availability (HA) PostgreSQL solutions using Pyth
 
 We call Patroni a "template" because it is far from being a one-size-fits-all or plug-and-play replication system. It will have its own caveats. Use wisely.
 
-Currently supported PostgreSQL versions: 9.3 to 15.
+Currently supported PostgreSQL versions: 9.3 to 17.
 
-**Note to Citus users**: Starting from 3.0 Patroni nicely integrates with the `Citus <https://github.com/citusdata/citus>`__ database extension to Postgres. Please check the `Citus support page <https://github.com/zalando/patroni/blob/master/docs/citus.rst>`__ in the Patroni documentation for more info about how to use Patroni high availability together with a Citus distributed cluster.
+**Note to Citus users**: Starting from 3.0 Patroni nicely integrates with the `Citus <https://github.com/citusdata/citus>`__ database extension to Postgres. Please check the `Citus support page <https://github.com/patroni/patroni/blob/master/docs/citus.rst>`__ in the Patroni documentation for more info about how to use Patroni high availability together with a Citus distributed cluster.
 
-**Note to Kubernetes users**: Patroni can run natively on top of Kubernetes. Take a look at the `Kubernetes <https://github.com/zalando/patroni/blob/master/docs/kubernetes.rst>`__ chapter of the Patroni documentation.
+**Note to Kubernetes users**: Patroni can run natively on top of Kubernetes. Take a look at the `Kubernetes <https://github.com/patroni/patroni/blob/master/docs/kubernetes.rst>`__ chapter of the Patroni documentation.
 
 .. contents::
     :local:
@@ -27,29 +27,27 @@ Currently supported PostgreSQL versions: 9.3 to 15.
 How Patroni Works
 =================
 
-Patroni originated as a fork of `Governor <https://github.com/compose/governor>`__, the project from Compose. It includes plenty of new features.
-
-For an example of a Docker-based deployment with Patroni, see `Spilo <https://github.com/zalando/spilo>`__, currently in use at Zalando.
+Patroni (formerly known as Zalando's Patroni) originated as a fork of `Governor <https://github.com/compose/governor>`__, the project from Compose. It includes plenty of new features.
 
 For additional background info, see:
 
 * `Elephants on Automatic: HA Clustered PostgreSQL with Helm <https://www.youtube.com/watch?v=CftcVhFMGSY>`_, talk by Josh Berkus and Oleksii Kliukin at KubeCon Berlin 2017
 * `PostgreSQL HA with Kubernetes and Patroni <https://www.youtube.com/watch?v=iruaCgeG7qs>`__, talk by Josh Berkus at KubeCon 2016 (video)
-* `Feb. 2016 Zalando Tech blog post <https://tech.zalando.de/blog/zalandos-patroni-a-template-for-high-availability-postgresql/>`__
+* `Feb. 2016 Zalando Tech blog post <https://engineering.zalando.com/posts/2016/02/zalandos-patroni-a-template-for-high-availability-postgresql.html>`__
 
 ==================
 Development Status
 ==================
 
-Patroni is in active development and accepts contributions. See our `Contributing <https://github.com/zalando/patroni/blob/master/docs/CONTRIBUTING.rst>`__ section below for more details.
+Patroni is in active development and accepts contributions. See our `Contributing <https://github.com/patroni/patroni/blob/master/docs/contributing_guidelines.rst>`__ section below for more details.
 
-We report new releases information `here <https://github.com/zalando/patroni/releases>`__.
+We report new releases information `here <https://github.com/patroni/patroni/releases>`__.
 
 =========
 Community
 =========
 
-There are two places to connect with the Patroni community: `on github <https://github.com/zalando/patroni>`__, via Issues and PRs, and on channel `#patroni <https://postgresteam.slack.com/archives/C9XPYG92A>`__ in the `PostgreSQL Slack <https://pgtreats.info/slack-invite>`__.  If you're using Patroni, or just interested, please join us.
+There are two places to connect with the Patroni community: `on github <https://github.com/patroni/patroni>`__, via Issues and PRs, and on channel `#patroni <https://postgresteam.slack.com/archives/C9XPYG92A>`__ in the `PostgreSQL Slack <https://pgtreats.info/slack-invite>`__.  If you're using Patroni, or just interested, please join us.
 
 ===================================
 Technical Requirements/Installation
@@ -77,23 +75,8 @@ There are a few options available:
     sudo apt-get install python3-psycopg2  # install psycopg2 module on Debian/Ubuntu
     sudo yum install python3-psycopg2      # install psycopg2 on RedHat/Fedora/CentOS
 
-2. Install psycopg2 from the binary package
+2. Specify one of `psycopg`, `psycopg2`, or `psycopg2-binary` in the list of dependencies when installing Patroni with pip (see below).
 
-::
-
-    pip install psycopg2-binary
-
-3. Install psycopg2 from source
-
-::
-
-    pip install psycopg2>=2.5.4
-
-4. Use psycopg 3.0 instead of psycopg2
-
-::
-
-    pip install psycopg[binary]>=3.0.0
 
 **General installation for pip**
 
@@ -108,7 +91,7 @@ where dependencies can be either empty, or consist of one or more of the followi
 etcd or etcd3
     `python-etcd` module in order to use Etcd as DCS
 consul
-    `python-consul` module in order to use Consul as DCS
+    `py-consul` module in order to use Consul as DCS
 zookeeper
     `kazoo` module in order to use Zookeeper as DCS
 exhibitor
@@ -119,12 +102,22 @@ raft
     `pysyncobj` module in order to use python Raft implementation as DCS
 aws
     `boto3` in order to use AWS callbacks
+systemd
+    `systemd-python` in order to use sd_notify integration
+all
+    all of the above (except psycopg family)
+psycopg3
+    `psycopg[binary]>=3.0.0` module
+psycopg2
+    `psycopg2>=2.5.4` module
+psycopg2-binary
+    `psycopg2-binary` module
 
-For example, the command in order to install Patroni together with dependencies for Etcd as a DCS and AWS callbacks is:
+For example, the command in order to install Patroni together with psycopg3, dependencies for Etcd as a DCS, and AWS callbacks is:
 
 ::
 
-    pip install patroni[etcd,aws]
+    pip install patroni[psycopg3,etcd3,aws]
 
 Note that external tools to call in the replica creation or custom bootstrap scripts (i.e. WAL-E) should be installed independently of Patroni.
 
@@ -158,19 +151,19 @@ run:
 YAML Configuration
 ==================
 
-Go `here <https://github.com/zalando/patroni/blob/master/docs/SETTINGS.rst>`__ for comprehensive information about settings for etcd, consul, and ZooKeeper. And for an example, see `postgres0.yml <https://github.com/zalando/patroni/blob/master/postgres0.yml>`__.
+Go `here <https://github.com/patroni/patroni/blob/master/docs/dynamic_configuration.rst>`__ for comprehensive information about settings for etcd, consul, and ZooKeeper. And for an example, see `postgres0.yml <https://github.com/patroni/patroni/blob/master/postgres0.yml>`__.
 
 =========================
 Environment Configuration
 =========================
 
-Go `here <https://github.com/zalando/patroni/blob/master/docs/ENVIRONMENT.rst>`__ for comprehensive information about configuring(overriding) settings via environment variables.
+Go `here <https://github.com/patroni/patroni/blob/master/docs/ENVIRONMENT.rst>`__ for comprehensive information about configuring(overriding) settings via environment variables.
 
 ===================
 Replication Choices
 ===================
 
-Patroni uses Postgres' streaming replication, which is asynchronous by default. Patroni's asynchronous replication configuration allows for ``maximum_lag_on_failover`` settings. This setting ensures failover will not occur if a follower is more than a certain number of bytes behind the leader. This setting should be increased or decreased based on business requirements. It's also possible to use synchronous replication for better durability guarantees. See `replication modes documentation <https://github.com/zalando/patroni/blob/master/docs/replication_modes.rst>`__ for details.
+Patroni uses Postgres' streaming replication, which is asynchronous by default. Patroni's asynchronous replication configuration allows for ``maximum_lag_on_failover`` settings. This setting ensures failover will not occur if a follower is more than a certain number of bytes behind the leader. This setting should be increased or decreased based on business requirements. It's also possible to use synchronous replication for better durability guarantees. See `replication modes documentation <https://github.com/patroni/patroni/blob/master/docs/replication_modes.rst>`__ for details.
 
 ======================================
 Applications Should Not Use Superusers
@@ -178,7 +171,7 @@ Applications Should Not Use Superusers
 
 When connecting from an application, always use a non-superuser. Patroni requires access to the database to function properly. By using a superuser from an application, you can potentially use the entire connection pool, including the connections reserved for superusers, with the ``superuser_reserved_connections`` setting. If Patroni cannot access the Primary because the connection pool is full, behavior will be undesirable.
 
-.. |Tests Status| image:: https://github.com/zalando/patroni/actions/workflows/tests.yaml/badge.svg
-   :target: https://github.com/zalando/patroni/actions/workflows/tests.yaml?query=branch%3Amaster
-.. |Coverage Status| image:: https://coveralls.io/repos/zalando/patroni/badge.svg?branch=master
-   :target: https://coveralls.io/github/zalando/patroni?branch=master
+.. |Tests Status| image:: https://github.com/patroni/patroni/actions/workflows/tests.yaml/badge.svg
+   :target: https://github.com/patroni/patroni/actions/workflows/tests.yaml?query=branch%3Amaster
+.. |Coverage Status| image:: https://coveralls.io/repos/patroni/patroni/badge.svg?branch=master
+   :target: https://coveralls.io/github/patroni/patroni?branch=master

docker-compose-citus.yml

@@ -9,17 +9,19 @@
 # $ docker-compose -f docker-compose-citus.yml up -d
 # You can read more about it in the:
 # https://github.com/zalando/patroni/blob/master/docker/README.md#citus-cluster
-version: "2"
+version: "3"
 
 networks:
     demo:
 
 services:
     etcd1: &etcd
-        image: ${PATRONI_TEST_IMAGE:-patroni-citus}
+        image: harbor.optimcloud.com/library/optim/patroni-citus:latest
         networks: [ demo ]
+        ports:
+            - 2379
+            - 2380
         environment:
-            ETCDCTL_API: 3
             ETCD_LISTEN_PEER_URLS: http://0.0.0.0:2380
             ETCD_LISTEN_CLIENT_URLS: http://0.0.0.0:2379
             ETCD_INITIAL_CLUSTER: etcd1=http://etcd1:2380,etcd2=http://etcd2:2380,etcd3=http://etcd3:2380
@@ -28,22 +30,28 @@ services:
             ETCD_UNSUPPORTED_ARCH: arm64
         container_name: demo-etcd1
         hostname: etcd1
-        command: etcd -name etcd1 -initial-advertise-peer-urls http://etcd1:2380
+        command: etcd --name etcd1 --initial-advertise-peer-urls http://etcd1:2380
 
     etcd2:
         <<: *etcd
         container_name: demo-etcd2
+        ports:
+            - 2379
+            - 2380        
         hostname: etcd2
-        command: etcd -name etcd2 -initial-advertise-peer-urls http://etcd2:2380
+        command: etcd --name etcd2 --initial-advertise-peer-urls http://etcd2:2380
 
     etcd3:
         <<: *etcd
         container_name: demo-etcd3
+        ports:
+            - 2379
+            - 2380        
         hostname: etcd3
-        command: etcd -name etcd3 -initial-advertise-peer-urls http://etcd3:2380
+        command: etcd --name etcd3 --initial-advertise-peer-urls http://etcd3:2380
 
     haproxy:
-        image: ${PATRONI_TEST_IMAGE:-patroni-citus}
+        image: harbor.optimcloud.com/library/optim/patroni-citus:latest
         networks: [ demo ]
         env_file: docker/patroni.env
         hostname: haproxy
@@ -53,7 +61,6 @@ services:
             - "5001:5001"  # Load-balancing across workers primaries
         command: haproxy
         environment: &haproxy_env
-            ETCDCTL_API: 3
             ETCDCTL_ENDPOINTS: http://etcd1:2379,http://etcd2:2379,http://etcd3:2379
             PATRONI_ETCD3_HOSTS: "'etcd1:2379','etcd2:2379','etcd3:2379'"
             PATRONI_SCOPE: demo
@@ -65,8 +72,10 @@ services:
             PGSSLROOTCERT: /etc/ssl/certs/ssl-cert-snakeoil.pem
 
     coord1:
-        image: ${PATRONI_TEST_IMAGE:-patroni-citus}
+        image: harbor.optimcloud.com/library/optim/patroni-citus:latest
         networks: [ demo ]
+        ports:
+            - "5432"
         env_file: docker/patroni.env
         hostname: coord1
         container_name: demo-coord1
@@ -76,8 +85,10 @@ services:
             PATRONI_CITUS_GROUP: 0
 
     coord2:
-        image: ${PATRONI_TEST_IMAGE:-patroni-citus}
+        image: harbor.optimcloud.com/library/optim/patroni-citus:latest
         networks: [ demo ]
+        ports:
+            - "5432"
         env_file: docker/patroni.env
         hostname: coord2
         container_name: demo-coord2
@@ -86,8 +97,10 @@ services:
             PATRONI_NAME: coord2
 
     coord3:
-        image: ${PATRONI_TEST_IMAGE:-patroni-citus}
+        image: harbor.optimcloud.com/library/optim/patroni-citus:latest
         networks: [ demo ]
+        ports:
+            - "5432"
         env_file: docker/patroni.env
         hostname: coord3
         container_name: demo-coord3
@@ -97,8 +110,10 @@ services:
 
 
     work1-1:
-        image: ${PATRONI_TEST_IMAGE:-patroni-citus}
+        image: harbor.optimcloud.com/library/optim/patroni-citus:latest
         networks: [ demo ]
+        ports:
+            - "5432"
         env_file: docker/patroni.env
         hostname: work1-1
         container_name: demo-work1-1
@@ -108,8 +123,10 @@ services:
             PATRONI_CITUS_GROUP: 1
 
     work1-2:
-        image: ${PATRONI_TEST_IMAGE:-patroni-citus}
+        image: harbor.optimcloud.com/library/optim/patroni-citus:latest
         networks: [ demo ]
+        ports:
+            - "5432"
         env_file: docker/patroni.env
         hostname: work1-2
         container_name: demo-work1-2
@@ -119,8 +136,10 @@ services:
 
 
     work2-1:
-        image: ${PATRONI_TEST_IMAGE:-patroni-citus}
+        image: harbor.optimcloud.com/library/optim/patroni-citus:latest
         networks: [ demo ]
+        ports:
+            - "5432"
         env_file: docker/patroni.env
         hostname: work2-1
         container_name: demo-work2-1
@@ -130,8 +149,10 @@ services:
             PATRONI_CITUS_GROUP: 2
 
     work2-2:
-        image: ${PATRONI_TEST_IMAGE:-patroni-citus}
+        image: harbor.optimcloud.com/library/optim/patroni-citus:latest
         networks: [ demo ]
+        ports:
+            - "5432"
         env_file: docker/patroni.env
         hostname: work2-2
         container_name: demo-work2-2

docker-compose.yml

@@ -6,7 +6,7 @@
 # The cluster could be started as:
 # $ docker-compose up -d
 # You can read more about it in the:
-# https://github.com/zalando/patroni/blob/master/docker/README.md
+# https://github.com/patroni/patroni/blob/master/docker/README.md
 version: "2"
 
 networks:
@@ -25,19 +25,19 @@ services:
             ETCD_UNSUPPORTED_ARCH: arm64
         container_name: demo-etcd1
         hostname: etcd1
-        command: etcd -name etcd1 -initial-advertise-peer-urls http://etcd1:2380
+        command: etcd --name etcd1 --initial-advertise-peer-urls http://etcd1:2380
 
     etcd2:
         <<: *etcd
         container_name: demo-etcd2
         hostname: etcd2
-        command: etcd -name etcd2 -initial-advertise-peer-urls http://etcd2:2380
+        command: etcd --name etcd2 --initial-advertise-peer-urls http://etcd2:2380
 
     etcd3:
         <<: *etcd
         container_name: demo-etcd3
         hostname: etcd3
-        command: etcd -name etcd3 -initial-advertise-peer-urls http://etcd3:2380
+        command: etcd --name etcd3 --initial-advertise-peer-urls http://etcd3:2380
 
     haproxy:
         image: ${PATRONI_TEST_IMAGE:-patroni}

docker/README.md

@@ -19,102 +19,96 @@ The haproxy listens on ports 5000 (connects to the primary) and 5001 (does load-
 
 Example session:
 
-    $ docker-compose up -d
-    Creating demo-haproxy ...
-    Creating demo-patroni2 ...
-    Creating demo-patroni1 ...
-    Creating demo-patroni3 ...
-    Creating demo-etcd2 ...
-    Creating demo-etcd1 ...
-    Creating demo-etcd3 ...
-    Creating demo-haproxy
-    Creating demo-patroni2
-    Creating demo-patroni1
-    Creating demo-patroni3
-    Creating demo-etcd1
-    Creating demo-etcd2
-    Creating demo-etcd2 ... done
+    $ docker compose up -d
+    ✔ Network patroni_demo     Created
+    ✔ Container demo-etcd1     Started
+    ✔ Container demo-haproxy   Started
+    ✔ Container demo-patroni1  Started
+    ✔ Container demo-patroni2  Started
+    ✔ Container demo-patroni3  Started
+    ✔ Container demo-etcd2     Started
+    ✔ Container demo-etcd3     Started
 
     $ docker ps
-    CONTAINER ID        IMAGE               COMMAND                  CREATED             STATUS              PORTS                              NAMES
-    5b7a90b4cfbf        patroni             "/bin/sh /entrypoint…"   29 seconds ago      Up 27 seconds                                          demo-etcd2
-    e30eea5222f2        patroni             "/bin/sh /entrypoint…"   29 seconds ago      Up 27 seconds                                          demo-etcd1
-    83bcf3cb208f        patroni             "/bin/sh /entrypoint…"   29 seconds ago      Up 27 seconds                                          demo-etcd3
-    922532c56e7d        patroni             "/bin/sh /entrypoint…"   29 seconds ago      Up 28 seconds                                          demo-patroni3
-    14f875e445f3        patroni             "/bin/sh /entrypoint…"   29 seconds ago      Up 28 seconds                                          demo-patroni2
-    110d1073b383        patroni             "/bin/sh /entrypoint…"   29 seconds ago      Up 28 seconds                                          demo-patroni1
-    5af5e6e36028        patroni             "/bin/sh /entrypoint…"   29 seconds ago      Up 28 seconds       0.0.0.0:5000-5001->5000-5001/tcp   demo-haproxy
+    CONTAINER ID   IMAGE     COMMAND                  CREATED          STATUS          PORTS                                                           NAMES
+    a37bcec56726   patroni   "/bin/sh /entrypoint…"   15 minutes ago   Up 15 minutes                                                                   demo-etcd3
+    034ab73868a8   patroni   "/bin/sh /entrypoint…"   15 minutes ago   Up 15 minutes                                                                   demo-patroni2
+    03837736f710   patroni   "/bin/sh /entrypoint…"   15 minutes ago   Up 15 minutes                                                                   demo-patroni3
+    22815c3d85b3   patroni   "/bin/sh /entrypoint…"   15 minutes ago   Up 15 minutes                                                                   demo-etcd2
+    814b4304d132   patroni   "/bin/sh /entrypoint…"   15 minutes ago   Up 15 minutes   0.0.0.0:5000-5001->5000-5001/tcp, :::5000-5001->5000-5001/tcp   demo-haproxy
+    6375b0ba2d0a   patroni   "/bin/sh /entrypoint…"   15 minutes ago   Up 15 minutes                                                                   demo-patroni1
+    aef8bf3ee91f   patroni   "/bin/sh /entrypoint…"   15 minutes ago   Up 15 minutes                                                                   demo-etcd1
 
     $ docker logs demo-patroni1
-    2019-02-20 08:19:32,714 INFO: Failed to import patroni.dcs.consul
-    2019-02-20 08:19:32,737 INFO: Selected new etcd server http://etcd3:2379
-    2019-02-20 08:19:35,140 INFO: Lock owner: None; I am patroni1
-    2019-02-20 08:19:35,174 INFO: trying to bootstrap a new cluster
+    2024-08-26 09:04:33,547 INFO: Selected new etcd server http://172.29.0.3:2379
+    2024-08-26 09:04:33,605 INFO: Lock owner: None; I am patroni1
+    2024-08-26 09:04:33,693 INFO: trying to bootstrap a new cluster
     ...
-    2019-02-20 08:19:39,310 INFO: postmaster pid=37
-    2019-02-20 08:19:39.314 UTC [37] LOG:  listening on IPv4 address "0.0.0.0", port 5432
-    2019-02-20 08:19:39.321 UTC [37] LOG:  listening on Unix socket "/var/run/postgresql/.s.PGSQL.5432"
-    2019-02-20 08:19:39.353 UTC [39] LOG:  database system was shut down at 2019-02-20 08:19:36 UTC
-    2019-02-20 08:19:39.354 UTC [40] FATAL:  the database system is starting up
-    localhost:5432 - rejecting connections
-    2019-02-20 08:19:39.369 UTC [37] LOG:  database system is ready to accept connections
+    2024-08-26 09:04:34.920 UTC [43] LOG:  starting PostgreSQL 16.4 (Debian 16.4-1.pgdg120+1) on x86_64-pc-linux-gnu, compiled by gcc (Debian 12.2.0-14) 12.2.0, 64-bit
+    2024-08-26 09:04:34.921 UTC [43] LOG:  listening on IPv4 address "0.0.0.0", port 5432
+    2024-08-26 09:04:34,922 INFO: postmaster pid=43
+    2024-08-26 09:04:34.922 UTC [43] LOG:  listening on Unix socket "/var/run/postgresql/.s.PGSQL.5432"
+    2024-08-26 09:04:34.925 UTC [47] LOG:  database system was shut down at 2024-08-26 09:04:34 UTC
+    2024-08-26 09:04:34.928 UTC [43] LOG:  database system is ready to accept connections
     localhost:5432 - accepting connections
-    2019-02-20 08:19:39,383 INFO: establishing a new patroni connection to the postgres cluster
-    2019-02-20 08:19:39,408 INFO: running post_bootstrap
-    2019-02-20 08:19:39,432 WARNING: Could not activate Linux watchdog device: "Can't open watchdog device: [Errno 2] No such file or directory: '/dev/watchdog'"
-    2019-02-20 08:19:39,515 INFO: initialized a new cluster
-    2019-02-20 08:19:49,424 INFO: Lock owner: patroni1; I am patroni1
-    2019-02-20 08:19:49,447 INFO: Lock owner: patroni1; I am patroni1
-    2019-02-20 08:19:49,480 INFO: no action.  i am the leader with the lock
-    2019-02-20 08:19:59,422 INFO: Lock owner: patroni1; I am patroni1
+    localhost:5432 - accepting connections
+    2024-08-26 09:04:34,938 INFO: establishing a new patroni heartbeat connection to postgres
+    2024-08-26 09:04:34,992 INFO: running post_bootstrap
+    2024-08-26 09:04:35,004 WARNING: User creation via "bootstrap.users" will be removed in v4.0.0
+    2024-08-26 09:04:35,189 INFO: initialized a new cluster
+    2024-08-26 09:04:35,328 INFO: no action. I am (patroni1), the leader with the lock
+    2024-08-26 09:04:43,824 INFO: establishing a new patroni restapi connection to postgres
+    2024-08-26 09:04:45,322 INFO: no action. I am (patroni1), the leader with the lock
+    2024-08-26 09:04:55,320 INFO: no action. I am (patroni1), the leader with the lock
+    ...
 
     $ docker exec -ti demo-patroni1 bash
     postgres@patroni1:~$ patronictl list
-    +---------+----------+------------+--------+---------+----+-----------+
-    | Cluster |  Member  |    Host    |  Role  |  State  | TL | Lag in MB |
-    +---------+----------+------------+--------+---------+----+-----------+
-    |   demo  | patroni1 | 172.22.0.3 | Leader | running |  1 |         0 |
-    |   demo  | patroni2 | 172.22.0.7 |        | running |  1 |         0 |
-    |   demo  | patroni3 | 172.22.0.4 |        | running |  1 |         0 |
-    +---------+----------+------------+--------+---------+----+-----------+
+    + Cluster: demo (7303838734793224214) --------+----+-----------+
+    | Member   | Host       | Role    | State     | TL | Lag in MB |
+    +----------+------------+---------+-----------+----+-----------+
+    | patroni1 | 172.29.0.2 | Leader  | running   |  1 |           |
+    | patroni2 | 172.29.0.6 | Replica | streaming |  1 |         0 |
+    | patroni3 | 172.29.0.5 | Replica | streaming |  1 |         0 |
+    +----------+------------+---------+-----------+----+-----------+
 
-    postgres@patroni1:~$ etcdctl ls --recursive --sort -p /service/demo
+    postgres@patroni1:~$ etcdctl get --keys-only --prefix /service/demo
     /service/demo/config
     /service/demo/initialize
     /service/demo/leader
-    /service/demo/members/
     /service/demo/members/patroni1
     /service/demo/members/patroni2
     /service/demo/members/patroni3
-    /service/demo/optime/
-    /service/demo/optime/leader
+    /service/demo/status
 
     postgres@patroni1:~$ etcdctl member list
-    1bab629f01fa9065: name=etcd3 peerURLs=http://etcd3:2380 clientURLs=http://etcd3:2379 isLeader=false
-    8ecb6af518d241cc: name=etcd2 peerURLs=http://etcd2:2380 clientURLs=http://etcd2:2379 isLeader=true
-    b2e169fcb8a34028: name=etcd1 peerURLs=http://etcd1:2380 clientURLs=http://etcd1:2379 isLeader=false
+    2bf3e2ceda5d5960, started, etcd2, http://etcd2:2380, http://172.29.0.3:2379
+    55b3264e129c7005, started, etcd3, http://etcd3:2380, http://172.29.0.7:2379
+    acce7233f8ec127e, started, etcd1, http://etcd1:2380, http://172.29.0.8:2379
+
+
     postgres@patroni1:~$ exit
 
     $ docker exec -ti demo-haproxy bash
     postgres@haproxy:~$ psql -h localhost -p 5000 -U postgres -W
     Password: postgres
-    psql (11.2 (Ubuntu 11.2-1.pgdg18.04+1), server 10.7 (Debian 10.7-1.pgdg90+1))
+    psql (16.4 (Debian 16.4-1.pgdg120+1))
     Type "help" for help.
 
-    localhost/postgres=# select pg_is_in_recovery();
+    postgres=# SELECT pg_is_in_recovery();
      pg_is_in_recovery
     ───────────────────
      f
     (1 row)
 
-    localhost/postgres=# \q
+    postgres=# \q
 
-    $postgres@haproxy:~ psql -h localhost -p 5001 -U postgres -W
+    postgres@haproxy:~$ psql -h localhost -p 5001 -U postgres -W
     Password: postgres
-    psql (11.2 (Ubuntu 11.2-1.pgdg18.04+1), server 10.7 (Debian 10.7-1.pgdg90+1))
+    psql (16.4 (Debian 16.4-1.pgdg120+1))
     Type "help" for help.
 
-    localhost/postgres=# select pg_is_in_recovery();
+    postgres=# SELECT pg_is_in_recovery();
      pg_is_in_recovery
     ───────────────────
      t
@@ -128,80 +122,99 @@ The haproxy listens on ports 5000 (connects to the coordinator primary) and 5001
 Example session:
 
     $ docker-compose -f docker-compose-citus.yml up -d
-    Creating demo-work2-1 ... done
-    Creating demo-work1-1 ... done
-    Creating demo-etcd2   ... done
-    Creating demo-etcd1   ... done
-    Creating demo-coord3  ... done
-    Creating demo-etcd3   ... done
-    Creating demo-coord1  ... done
-    Creating demo-haproxy ... done
-    Creating demo-work2-2 ... done
-    Creating demo-coord2  ... done
-    Creating demo-work1-2 ... done
+    ✔ Network patroni_demo    Created
+    ✔ Container demo-coord2   Started
+    ✔ Container demo-work2-2  Started
+    ✔ Container demo-etcd1    Started
+    ✔ Container demo-haproxy  Started
+    ✔ Container demo-work1-1  Started
+    ✔ Container demo-work2-1  Started
+    ✔ Container demo-work1-2  Started
+    ✔ Container demo-coord1   Started
+    ✔ Container demo-etcd3    Started
+    ✔ Container demo-coord3   Started
+    ✔ Container demo-etcd2    Started
+
 
     $ docker ps
-    CONTAINER ID   IMAGE                  COMMAND                  CREATED         STATUS         PORTS                              NAMES
-    852d8885a612   patroni-citus          "/bin/sh /entrypoint…"   6 seconds ago   Up 3 seconds                                      demo-coord3
-    cdd692f947ab   patroni-citus          "/bin/sh /entrypoint…"   6 seconds ago   Up 3 seconds                                      demo-work1-2
-    9f4e340b36da   patroni-citus          "/bin/sh /entrypoint…"   6 seconds ago   Up 3 seconds                                      demo-etcd3
-    d69c129a960a   patroni-citus          "/bin/sh /entrypoint…"   6 seconds ago   Up 4 seconds                                      demo-etcd1
-    c5849689b8cd   patroni-citus          "/bin/sh /entrypoint…"   6 seconds ago   Up 4 seconds                                      demo-coord1
-    c9d72bd6217d   patroni-citus          "/bin/sh /entrypoint…"   6 seconds ago   Up 3 seconds                                      demo-work2-1
-    24b1b43efa05   patroni-citus          "/bin/sh /entrypoint…"   6 seconds ago   Up 4 seconds                                      demo-coord2
-    cb0cc2b4ca0a   patroni-citus          "/bin/sh /entrypoint…"   6 seconds ago   Up 3 seconds                                      demo-work2-2
-    9796c6b8aad5   patroni-citus          "/bin/sh /entrypoint…"   6 seconds ago   Up 5 seconds                                      demo-work1-1
-    8baccd74dcae   patroni-citus          "/bin/sh /entrypoint…"   6 seconds ago   Up 4 seconds                                      demo-etcd2
-    353ec62a0187   patroni-citus          "/bin/sh /entrypoint…"   6 seconds ago   Up 4 seconds   0.0.0.0:5000-5001->5000-5001/tcp   demo-haproxy
+    CONTAINER ID   IMAGE           COMMAND                  CREATED          STATUS          PORTS                                                           NAMES
+    79c95492fac9   patroni-citus   "/bin/sh /entrypoint…"   11 minutes ago   Up 11 minutes                                                                   demo-etcd3
+    77eb82d0f0c1   patroni-citus   "/bin/sh /entrypoint…"   11 minutes ago   Up 11 minutes                                                                   demo-work2-1
+    03dacd7267ef   patroni-citus   "/bin/sh /entrypoint…"   11 minutes ago   Up 11 minutes                                                                   demo-etcd1
+    db9206c66f85   patroni-citus   "/bin/sh /entrypoint…"   11 minutes ago   Up 11 minutes                                                                   demo-etcd2
+    9a0fef7b7dd4   patroni-citus   "/bin/sh /entrypoint…"   11 minutes ago   Up 11 minutes                                                                   demo-work1-2
+    f06b031d99dc   patroni-citus   "/bin/sh /entrypoint…"   11 minutes ago   Up 11 minutes                                                                   demo-work2-2
+    f7c58545f314   patroni-citus   "/bin/sh /entrypoint…"   11 minutes ago   Up 11 minutes                                                                   demo-coord2
+    383f9e7e188a   patroni-citus   "/bin/sh /entrypoint…"   11 minutes ago   Up 11 minutes                                                                   demo-work1-1
+    f02e96dcc9d6   patroni-citus   "/bin/sh /entrypoint…"   11 minutes ago   Up 11 minutes                                                                   demo-coord3
+    6945834b7056   patroni-citus   "/bin/sh /entrypoint…"   11 minutes ago   Up 11 minutes                                                                   demo-coord1
+    b96ca42f785d   patroni-citus   "/bin/sh /entrypoint…"   11 minutes ago   Up 11 minutes   0.0.0.0:5000-5001->5000-5001/tcp, :::5000-5001->5000-5001/tcp   demo-haproxy
+
 
     $ docker logs demo-coord1
-    2023-01-05 15:09:31,295 INFO: Selected new etcd server http://172.27.0.4:2379
-    2023-01-05 15:09:31,388 INFO: Lock owner: None; I am coord1
-    2023-01-05 15:09:31,501 INFO: trying to bootstrap a new cluster
+    2024-08-26 08:21:05,323 INFO: Selected new etcd server http://172.19.0.5:2379
+    2024-08-26 08:21:05,339 INFO: No PostgreSQL configuration items changed, nothing to reload.
+    2024-08-26 08:21:05,388 INFO: Lock owner: None; I am coord1
+    2024-08-26 08:21:05,480 INFO: trying to bootstrap a new cluster
     ...
-    2023-01-05 15:09:45,096 INFO: postmaster pid=39
+    2024-08-26 08:21:17,115 INFO: postmaster pid=35
     localhost:5432 - no response
-    2023-01-05 15:09:45.137 UTC [39] LOG:  starting PostgreSQL 15.1 (Debian 15.1-1.pgdg110+1) on x86_64-pc-linux-gnu, compiled by gcc (Debian 10.2.1-6) 10.2.1 20210110, 64-bit
-    2023-01-05 15:09:45.137 UTC [39] LOG:  listening on IPv4 address "0.0.0.0", port 5432
-    2023-01-05 15:09:45.152 UTC [39] LOG:  listening on Unix socket "/var/run/postgresql/.s.PGSQL.5432"
-    2023-01-05 15:09:45.177 UTC [43] LOG:  database system was shut down at 2023-01-05 15:09:32 UTC
-    2023-01-05 15:09:45.193 UTC [39] LOG:  database system is ready to accept connections
+    2024-08-26 08:21:17.127 UTC [35] LOG:  starting PostgreSQL 16.4 (Debian 16.4-1.pgdg120+1) on x86_64-pc-linux-gnu, compiled by gcc (Debian 12.2.0-14) 12.2.0, 64-bit
+    2024-08-26 08:21:17.127 UTC [35] LOG:  listening on IPv4 address "0.0.0.0", port 5432
+    2024-08-26 08:21:17.141 UTC [35] LOG:  listening on Unix socket "/var/run/postgresql/.s.PGSQL.5432"
+    2024-08-26 08:21:17.155 UTC [39] LOG:  database system was shut down at 2024-08-26 08:21:05 UTC
+    2024-08-26 08:21:17.182 UTC [35] LOG:  database system is ready to accept connections
+    2024-08-26 08:21:17,683 INFO: establishing a new patroni heartbeat connection to postgres
+    2024-08-26 08:21:17,704 INFO: establishing a new patroni restapi connection to postgres
     localhost:5432 - accepting connections
     localhost:5432 - accepting connections
-    2023-01-05 15:09:46,139 INFO: establishing a new patroni connection to the postgres cluster
-    2023-01-05 15:09:46,208 INFO: running post_bootstrap
-    2023-01-05 15:09:47.209 UTC [55] LOG:  starting maintenance daemon on database 16386 user 10
-    2023-01-05 15:09:47.209 UTC [55] CONTEXT:  Citus maintenance daemon for database 16386 user 10
-    2023-01-05 15:09:47,215 WARNING: Could not activate Linux watchdog device: "Can't open watchdog device: [Errno 2] No such file or directory: '/dev/watchdog'"
-    2023-01-05 15:09:47.446 UTC [41] LOG:  checkpoint starting: immediate force wait
-    2023-01-05 15:09:47,466 INFO: initialized a new cluster
-    2023-01-05 15:09:47,594 DEBUG: query(SELECT nodeid, groupid, nodename, nodeport, noderole FROM pg_catalog.pg_dist_node WHERE noderole = 'primary', ())
-    2023-01-05 15:09:47,594 INFO: establishing a new patroni connection to the postgres cluster
-    2023-01-05 15:09:47,467 INFO: Lock owner: coord1; I am coord1
-    2023-01-05 15:09:47,613 DEBUG: query(SELECT pg_catalog.citus_set_coordinator_host(%s, %s, 'primary', 'default'), ('172.27.0.6', 5432))
-    2023-01-05 15:09:47,924 INFO: no action. I am (coord1), the leader with the lock
-    2023-01-05 15:09:51.282 UTC [41] LOG:  checkpoint complete: wrote 1086 buffers (53.0%); 0 WAL file(s) added, 0 removed, 0 recycled; write=0.029 s, sync=3.746 s, total=3.837 s; sync files=280, longest=0.028 s, average=0.014 s; distance=8965 kB, estimate=8965 kB
-    2023-01-05 15:09:51.283 UTC [41] LOG:  checkpoint starting: immediate force wait
-    2023-01-05 15:09:51.495 UTC [41] LOG:  checkpoint complete: wrote 18 buffers (0.9%); 0 WAL file(s) added, 0 removed, 0 recycled; write=0.044 s, sync=0.091 s, total=0.212 s; sync files=15, longest=0.015 s, average=0.007 s; distance=67 kB, estimate=8076 kB
-    2023-01-05 15:09:57,467 INFO: Lock owner: coord1; I am coord1
-    2023-01-05 15:09:57,569 INFO: Assigning synchronous standby status to ['coord3']
+    2024-08-26 08:21:18,202 INFO: running post_bootstrap
+    2024-08-26 08:21:19.048 UTC [53] LOG:  starting maintenance daemon on database 16385 user 10
+    2024-08-26 08:21:19.048 UTC [53] CONTEXT:  Citus maintenance daemon for database 16385 user 10
+    2024-08-26 08:21:19,058 DEBUG: Could not activate Linux watchdog device: Can't open watchdog device: [Errno 2] No such file or directory: '/dev/watchdog'
+    2024-08-26 08:21:19.250 UTC [37] LOG:  checkpoint starting: immediate force wait
+    2024-08-26 08:21:19,275 INFO: initialized a new cluster
+    2024-08-26 08:21:22.946 UTC [37] LOG:  checkpoint starting: immediate force wait
+    2024-08-26 08:21:29,059 INFO: Lock owner: coord1; I am coord1
+    2024-08-26 08:21:29,205 INFO: Enabled synchronous replication
+    2024-08-26 08:21:29,206 DEBUG: query(SELECT groupid, nodename, nodeport, noderole, nodeid FROM pg_catalog.pg_dist_node, ())
+    2024-08-26 08:21:29,206 INFO: establishing a new patroni citus connection to postgres
+    2024-08-26 08:21:29,206 DEBUG: Adding the new task: PgDistTask({PgDistNode(nodeid=None,host=172.19.0.8,port=5432,role=primary)})
+    2024-08-26 08:21:29,206 DEBUG: Adding the new task: PgDistTask({PgDistNode(nodeid=None,host=172.19.0.2,port=5432,role=primary)})
+    2024-08-26 08:21:29,206 DEBUG: Adding the new task: PgDistTask({PgDistNode(nodeid=None,host=172.19.0.9,port=5432,role=primary)})
+    2024-08-26 08:21:29,219 DEBUG: query(SELECT pg_catalog.citus_add_node(%s, %s, %s, %s, 'default'), ('172.19.0.2', 5432, 1, 'primary'))
+    2024-08-26 08:21:29,256 DEBUG: query(SELECT pg_catalog.citus_add_node(%s, %s, %s, %s, 'default'), ('172.19.0.9', 5432, 2, 'primary'))
+    2024-08-26 08:21:29,474 INFO: no action. I am (coord1), the leader with the lock
+    2024-08-26 08:21:39,060 INFO: Lock owner: coord1; I am coord1
+    2024-08-26 08:21:39,159 DEBUG: Adding the new task: PgDistTask({PgDistNode(nodeid=None,host=172.19.0.8,port=5432,role=primary), PgDistNode(nodeid=None,host=172.19.0.11,port=5432,role=secondary), PgDistNode(nodeid=None,host=172.19.0.7,port=5432,role=secondary)})
+    2024-08-26 08:21:39,159 DEBUG: Adding the new task: PgDistTask({PgDistNode(nodeid=None,host=172.19.0.2,port=5432,role=primary), PgDistNode(nodeid=None,host=172.19.0.12,port=5432,role=secondary)})
+    2024-08-26 08:21:39,159 DEBUG: Adding the new task: PgDistTask({PgDistNode(nodeid=None,host=172.19.0.6,port=5432,role=secondary), PgDistNode(nodeid=None,host=172.19.0.9,port=5432,role=primary)})
+    2024-08-26 08:21:39,160 DEBUG: query(BEGIN, ())
+    2024-08-26 08:21:39,160 DEBUG: query(SELECT pg_catalog.citus_add_node(%s, %s, %s, %s, 'default'), ('172.19.0.11', 5432, 0, 'secondary'))
+    2024-08-26 08:21:39,164 DEBUG: query(SELECT pg_catalog.citus_add_node(%s, %s, %s, %s, 'default'), ('172.19.0.7', 5432, 0, 'secondary'))
+    2024-08-26 08:21:39,166 DEBUG: query(COMMIT, ())
+    2024-08-26 08:21:39,176 DEBUG: query(SELECT pg_catalog.citus_add_node(%s, %s, %s, %s, 'default'), ('172.19.0.12', 5432, 1, 'secondary'))
+    2024-08-26 08:21:39,191 DEBUG: query(SELECT pg_catalog.citus_add_node(%s, %s, %s, %s, 'default'), ('172.19.0.6', 5432, 2, 'secondary'))
+    2024-08-26 08:21:39,211 INFO: no action. I am (coord1), the leader with the lock
+    2024-08-26 08:21:49,060 INFO: Lock owner: coord1; I am coord1
+    2024-08-26 08:21:49,166 INFO: Setting synchronous replication to 1 of 2 (coord2, coord3)
     server signaled
-    2023-01-05 15:09:57.574 UTC [39] LOG:  received SIGHUP, reloading configuration files
-    2023-01-05 15:09:57.580 UTC [39] LOG:  parameter "synchronous_standby_names" changed to "coord3"
-    2023-01-05 15:09:59,637 INFO: Synchronous standby status assigned to ['coord3']
-    2023-01-05 15:09:59,638 DEBUG: query(SELECT pg_catalog.citus_add_node(%s, %s, %s, 'primary', 'default'), ('172.27.0.2', 5432, 1))
-    2023-01-05 15:09:59.690 UTC [67] LOG:  standby "coord3" is now a synchronous standby with priority 1
-    2023-01-05 15:09:59.690 UTC [67] STATEMENT:  START_REPLICATION SLOT "coord3" 0/3000000 TIMELINE 1
-    2023-01-05 15:09:59,694 INFO: no action. I am (coord1), the leader with the lock
-    2023-01-05 15:09:59,704 DEBUG: query(SELECT pg_catalog.citus_add_node(%s, %s, %s, 'primary', 'default'), ('172.27.0.8', 5432, 2))
-    2023-01-05 15:10:07,625 INFO: no action. I am (coord1), the leader with the lock
-    2023-01-05 15:10:17,579 INFO: no action. I am (coord1), the leader with the lock
+    2024-08-26 08:21:49.170 UTC [35] LOG:  received SIGHUP, reloading configuration files
+    2024-08-26 08:21:49.171 UTC [35] LOG:  parameter "synchronous_standby_names" changed to "ANY 1 (coord2,coord3)"
+    2024-08-26 08:21:49.377 UTC [68] LOG:  standby "coord2" is now a candidate for quorum synchronous standby
+    2024-08-26 08:21:49.377 UTC [68] STATEMENT:  START_REPLICATION SLOT "coord2" 0/3000000 TIMELINE 1
+    2024-08-26 08:21:49.377 UTC [69] LOG:  standby "coord3" is now a candidate for quorum synchronous standby
+    2024-08-26 08:21:49.377 UTC [69] STATEMENT:  START_REPLICATION SLOT "coord3" 0/4000000 TIMELINE 1
+    2024-08-26 08:21:50,278 INFO: Setting leader to coord1, quorum to 1 of 2 (coord2, coord3)
+    2024-08-26 08:21:50,390 INFO: no action. I am (coord1), the leader with the lock
+    2024-08-26 08:21:59,159 INFO: no action. I am (coord1), the leader with the lock
+    ...
 
     $ docker exec -ti demo-haproxy bash
     postgres@haproxy:~$ etcdctl member list
-    1bab629f01fa9065, started, etcd3, http://etcd3:2380, http://172.27.0.10:2379
-    8ecb6af518d241cc, started, etcd2, http://etcd2:2380, http://172.27.0.4:2379
-    b2e169fcb8a34028, started, etcd1, http://etcd1:2380, http://172.27.0.7:2379
+    2b28411e74c0c281, started, etcd3, http://etcd3:2380, http://172.30.0.4:2379
+    6c70137d27cfa6c1, started, etcd2, http://etcd2:2380, http://172.30.0.5:2379
+    a28f9a70ebf21304, started, etcd1, http://etcd1:2380, http://172.30.0.6:2379
 
     postgres@haproxy:~$ etcdctl get --keys-only --prefix /service/demo
     /service/demo/0/config
@@ -229,7 +242,7 @@ Example session:
 
     postgres@haproxy:~$ psql -h localhost -p 5000 -U postgres -d citus
     Password for user postgres: postgres
-    psql (15.1 (Debian 15.1-1.pgdg110+1))
+    psql (16.4 (Debian 16.4-1.pgdg120+1))
     SSL connection (protocol: TLSv1.3, cipher: TLS_AES_256_GCM_SHA384, compression: off)
     Type "help" for help.
 
@@ -240,67 +253,76 @@ Example session:
     (1 row)
 
     citus=# table pg_dist_node;
-     nodeid | groupid |  nodename  | nodeport | noderack | hasmetadata | isactive | noderole | nodecluster | metadatasynced | shouldhaveshards
-    --------+---------+------------+----------+----------+-------------+----------+----------+-------------+----------------+------------------
-          1 |       0 | 172.27.0.6 |     5432 | default  | t           | t        | primary  | default     | t              | f
-          2 |       1 | 172.27.0.2 |     5432 | default  | t           | t        | primary  | default     | t              | t
-          3 |       2 | 172.27.0.8 |     5432 | default  | t           | t        | primary  | default     | t              | t
-    (3 rows)
+     nodeid | groupid |  nodename   | nodeport | noderack | hasmetadata | isactive | noderole  | nodecluster | metadatasynced | shouldhaveshards
+    --------+---------+-------------+----------+----------+-------------+----------+-----------+-------------+----------------+------------------
+          1 |       0 | 172.19.0.8  |     5432 | default  | t           | t        | primary   | default     | t              | f
+          2 |       1 | 172.19.0.2  |     5432 | default  | t           | t        | primary   | default     | t              | t
+          3 |       2 | 172.19.0.9  |     5432 | default  | t           | t        | primary   | default     | t              | t
+          4 |       0 | 172.19.0.11 |     5432 | default  | t           | t        | secondary | default     | t              | f
+          5 |       0 | 172.19.0.7  |     5432 | default  | t           | t        | secondary | default     | t              | f
+          6 |       1 | 172.19.0.12 |     5432 | default  | f           | t        | secondary | default     | f              | t
+          7 |       2 | 172.19.0.6  |     5432 | default  | f           | t        | secondary | default     | f              | t
+    (7 rows)
 
     citus=# \q
 
     postgres@haproxy:~$ patronictl list
-    + Citus cluster: demo ----------+--------------+---------+----+-----------+
-    | Group | Member  | Host        | Role         | State   | TL | Lag in MB |
-    +-------+---------+-------------+--------------+---------+----+-----------+
-    |     0 | coord1  | 172.27.0.6  | Leader       | running |  1 |           |
-    |     0 | coord2  | 172.27.0.5  | Replica      | running |  1 |         0 |
-    |     0 | coord3  | 172.27.0.9  | Sync Standby | running |  1 |         0 |
-    |     1 | work1-1 | 172.27.0.2  | Leader       | running |  1 |           |
-    |     1 | work1-2 | 172.27.0.12 | Sync Standby | running |  1 |         0 |
-    |     2 | work2-1 | 172.27.0.11 | Sync Standby | running |  1 |         0 |
-    |     2 | work2-2 | 172.27.0.8  | Leader       | running |  1 |           |
-    +-------+---------+-------------+--------------+---------+----+-----------+
+    + Citus cluster: demo ----------+----------------+-----------+----+-----------+
+    | Group | Member  | Host        | Role           | State     | TL | Lag in MB |
+    +-------+---------+-------------+----------------+-----------+----+-----------+
+    |     0 | coord1  | 172.19.0.8  | Leader         | running   |  1 |           |
+    |     0 | coord2  | 172.19.0.7  | Quorum Standby | streaming |  1 |         0 |
+    |     0 | coord3  | 172.19.0.11 | Quorum Standby | streaming |  1 |         0 |
+    |     1 | work1-1 | 172.19.0.12 | Quorum Standby | streaming |  1 |         0 |
+    |     1 | work1-2 | 172.19.0.2  | Leader         | running   |  1 |           |
+    |     2 | work2-1 | 172.19.0.6  | Quorum Standby | streaming |  1 |         0 |
+    |     2 | work2-2 | 172.19.0.9  | Leader         | running   |  1 |           |
+    +-------+---------+-------------+----------------+-----------+----+-----------+
+
 
     postgres@haproxy:~$ patronictl switchover --group 2 --force
     Current cluster topology
-    + Citus cluster: demo (group: 2, 7185185529556963355) +-----------+
-    | Member  | Host        | Role         | State   | TL | Lag in MB |
-    +---------+-------------+--------------+---------+----+-----------+
-    | work2-1 | 172.27.0.11 | Sync Standby | running |  1 |         0 |
-    | work2-2 | 172.27.0.8  | Leader       | running |  1 |           |
-    +---------+-------------+--------------+---------+----+-----------+
-    2023-01-05 15:29:29.54204 Successfully switched over to "work2-1"
-    + Citus cluster: demo (group: 2, 7185185529556963355) -------+
-    | Member  | Host        | Role    | State   | TL | Lag in MB |
-    +---------+-------------+---------+---------+----+-----------+
-    | work2-1 | 172.27.0.11 | Leader  | running |  1 |           |
-    | work2-2 | 172.27.0.8  | Replica | stopped |    |   unknown |
-    +---------+-------------+---------+---------+----+-----------+
+    + Citus cluster: demo (group: 2, 7407360296219029527) ---+-----------+
+    | Member  | Host       | Role           | State     | TL | Lag in MB |
+    +---------+------------+----------------+-----------+----+-----------+
+    | work2-1 | 172.19.0.6 | Quorum Standby | streaming |  1 |         0 |
+    | work2-2 | 172.19.0.9 | Leader         | running   |  1 |           |
+    +---------+------------+----------------+-----------+----+-----------+
+    2024-08-26 08:31:45.92277 Successfully switched over to "work2-1"
+    + Citus cluster: demo (group: 2, 7407360296219029527) ------+
+    | Member  | Host       | Role    | State   | TL | Lag in MB |
+    +---------+------------+---------+---------+----+-----------+
+    | work2-1 | 172.19.0.6 | Leader  | running |  1 |           |
+    | work2-2 | 172.19.0.9 | Replica | stopped |    |   unknown |
+    +---------+------------+---------+---------+----+-----------+
 
     postgres@haproxy:~$ patronictl list
-    + Citus cluster: demo ----------+--------------+---------+----+-----------+
-    | Group | Member  | Host        | Role         | State   | TL | Lag in MB |
-    +-------+---------+-------------+--------------+---------+----+-----------+
-    |     0 | coord1  | 172.27.0.6  | Leader       | running |  1 |           |
-    |     0 | coord2  | 172.27.0.5  | Replica      | running |  1 |         0 |
-    |     0 | coord3  | 172.27.0.9  | Sync Standby | running |  1 |         0 |
-    |     1 | work1-1 | 172.27.0.2  | Leader       | running |  1 |           |
-    |     1 | work1-2 | 172.27.0.12 | Sync Standby | running |  1 |         0 |
-    |     2 | work2-1 | 172.27.0.11 | Leader       | running |  2 |           |
-    |     2 | work2-2 | 172.27.0.8  | Sync Standby | running |  2 |         0 |
-    +-------+---------+-------------+--------------+---------+----+-----------+
+    + Citus cluster: demo ----------+----------------+-----------+----+-----------+
+    | Group | Member  | Host        | Role           | State     | TL | Lag in MB |
+    +-------+---------+-------------+----------------+-----------+----+-----------+
+    |     0 | coord1  | 172.19.0.8  | Leader         | running   |  1 |           |
+    |     0 | coord2  | 172.19.0.7  | Quorum Standby | streaming |  1 |         0 |
+    |     0 | coord3  | 172.19.0.11 | Quorum Standby | streaming |  1 |         0 |
+    |     1 | work1-1 | 172.19.0.12 | Quorum Standby | streaming |  1 |         0 |
+    |     1 | work1-2 | 172.19.0.2  | Leader         | running   |  1 |           |
+    |     2 | work2-1 | 172.19.0.6  | Leader         | running   |  2 |           |
+    |     2 | work2-2 | 172.19.0.9  | Quorum Standby | streaming |  2 |         0 |
+    +-------+---------+-------------+----------------+-----------+----+-----------+
 
     postgres@haproxy:~$ psql -h localhost -p 5000 -U postgres -d citus
     Password for user postgres: postgres
-    psql (15.1 (Debian 15.1-1.pgdg110+1))
+    psql (16.4 (Debian 16.4-1.pgdg120+1))
     SSL connection (protocol: TLSv1.3, cipher: TLS_AES_256_GCM_SHA384, compression: off)
     Type "help" for help.
 
     citus=# table pg_dist_node;
-     nodeid | groupid |  nodename   | nodeport | noderack | hasmetadata | isactive | noderole | nodecluster | metadatasynced | shouldhaveshards
-    --------+---------+-------------+----------+----------+-------------+----------+----------+-------------+----------------+------------------
-          1 |       0 | 172.27.0.6  |     5432 | default  | t           | t        | primary  | default     | t              | f
-          3 |       2 | 172.27.0.11 |     5432 | default  | t           | t        | primary  | default     | t              | t
-          2 |       1 | 172.27.0.2  |     5432 | default  | t           | t        | primary  | default     | t              | t
-    (3 rows)
+     nodeid | groupid |  nodename   | nodeport | noderack | hasmetadata | isactive | noderole  | nodecluster | metadatasynced | shouldhaveshards
+    --------+---------+-------------+----------+----------+-------------+----------+-----------+-------------+----------------+------------------
+          1 |       0 | 172.19.0.8  |     5432 | default  | t           | t        | primary   | default     | t              | f
+          4 |       0 | 172.19.0.11 |     5432 | default  | t           | t        | secondary | default     | t              | f
+          5 |       0 | 172.19.0.7  |     5432 | default  | t           | t        | secondary | default     | t              | f
+          6 |       1 | 172.19.0.12 |     5432 | default  | f           | t        | secondary | default     | f              | t
+          3 |       2 | 172.19.0.6  |     5432 | default  | t           | t        | primary   | default     | t              | t
+          2 |       1 | 172.19.0.2  |     5432 | default  | t           | t        | primary   | default     | t              | t
+          8 |       2 | 172.19.0.9  |     5432 | default  | f           | t        | secondary | default     | f              | t
+    (7 rows)

docker/entrypoint.sh

@@ -13,6 +13,8 @@ readonly PATRONI_NAMESPACE="${PATRONI_NAMESPACE%/}"
 DOCKER_IP=$(hostname --ip-address)
 readonly DOCKER_IP
 
+export DUMB_INIT_SETSID=0
+
 case "$1" in
     haproxy)
         haproxy -f /etc/haproxy/haproxy.cfg -p /var/run/haproxy.pid -D
@@ -36,7 +38,7 @@ EOT
         exec dumb-init "$@"
         ;;
     etcd)
-        exec "$@" -advertise-client-urls "http://$DOCKER_IP:2379"
+        exec "$@" --auto-compaction-retention=1 -advertise-client-urls "http://$DOCKER_IP:2379"
         ;;
     zookeeper)
         exec /usr/share/zookeeper/bin/zkServer.sh start-foreground
@@ -72,4 +74,4 @@ export PATRONI_SUPERUSER_SSLKEY="${PATRONI_SUPERUSER_SSLKEY:-$PGSSLKEY}"
 export PATRONI_SUPERUSER_SSLCERT="${PATRONI_SUPERUSER_SSLCERT:-$PGSSLCERT}"
 export PATRONI_SUPERUSER_SSLROOTCERT="${PATRONI_SUPERUSER_SSLROOTCERT:-$PGSSLROOTCERT}"
 
-exec python3 /patroni.py postgres0.yml
+exec dumb-init python3 /patroni.py postgres0.yml

docs/ENVIRONMENT.rst

@@ -14,24 +14,28 @@ Global/Universal
 
 Log
 ---
+-  **PATRONI\_LOG\_TYPE**: sets the format of logs. Can be either **plain** or **json**. To use **json** format, you must have the :ref:`jsonlogger <extras>` installed. The default value is **plain**.
 -  **PATRONI\_LOG\_LEVEL**: sets the general logging level. Default value is **INFO** (see `the docs for Python logging <https://docs.python.org/3.6/library/logging.html#levels>`_)
 -  **PATRONI\_LOG\_TRACEBACK\_LEVEL**: sets the level where tracebacks will be visible. Default value is **ERROR**. Set it to **DEBUG** if you want to see tracebacks only if you enable **PATRONI\_LOG\_LEVEL=DEBUG**.
--  **PATRONI\_LOG\_FORMAT**: sets the log formatting string. Default value is **%(asctime)s %(levelname)s: %(message)s** (see `the LogRecord attributes <https://docs.python.org/3.6/library/logging.html#logrecord-attributes>`_)
+-  **PATRONI\_LOG\_FORMAT**: sets the log formatting string. If the log type is **plain**, the log format should be a string.
+   Refer to `the LogRecord attributes <https://docs.python.org/3.6/library/logging.html#logrecord-attributes>`_ for
+   available attributes. If the log type is **json**, the log format can be a list in addition to a string. Each list
+   item should correspond to LogRecord attributes. Be cautious that only the field name is required, and the **%(**
+   and **)** should be omitted. If you wish to print a log field with a different key name, use a dictionary where
+   the dictionary key is the log field, and the value is the name of the field you want to be printed in the log.
+   Default value is **%(asctime)s %(levelname)s: %(message)s**
 -  **PATRONI\_LOG\_DATEFORMAT**: sets the datetime formatting string. (see the `formatTime() documentation <https://docs.python.org/3.6/library/logging.html#logging.Formatter.formatTime>`_)
+-  **PATRONI\_LOG\_STATIC\_FIELDS**: add additional fields to the log. This option is only available when the log type is set to **json**. Example ``PATRONI_LOG_STATIC_FIELDS="{app: patroni}"``
 -  **PATRONI\_LOG\_MAX\_QUEUE\_SIZE**: Patroni is using two-step logging. Log records are written into the in-memory queue and there is a separate thread which pulls them from the queue and writes to stderr or file. The maximum size of the internal queue is limited by default by **1000** records, which is enough to keep logs for the past 1h20m.
 -  **PATRONI\_LOG\_DIR**: Directory to write application logs to. The directory must exist and be writable by the user executing Patroni. If you set this env variable, the application will retain 4 25MB logs by default. You can tune those retention values with `PATRONI_LOG_FILE_NUM` and `PATRONI_LOG_FILE_SIZE` (see below).
+-  **PATRONI\_LOG\_MODE**: Permissions for log files (for example, ``0644``). If not specified, permissions will be set based on the current umask value.
 -  **PATRONI\_LOG\_FILE\_NUM**: The number of application logs to retain.
 -  **PATRONI\_LOG\_FILE\_SIZE**: Size of patroni.log file (in bytes) that triggers a log rolling.
 -  **PATRONI\_LOG\_LOGGERS**: Redefine logging level per python module. Example ``PATRONI_LOG_LOGGERS="{patroni.postmaster: WARNING, urllib3: DEBUG}"``
+-  **PATRONI\_LOG\_DEDUPLICATE\_HEARTBEAT\_LOGS**: If set to ``true``, successive heartbeat logs that are identical shall not be output. Default value is ``false``.
 
-Bootstrap configuration
------------------------
-It is possible to create new database users right after the successful initialization of a new cluster. This process is defined by the following variables:
-
--  **PATRONI\_<username>\_PASSWORD='<password>'**
--  **PATRONI\_<username>\_OPTIONS='list,of,options'**
-
-Example: defining ``PATRONI_admin_PASSWORD=strongpasswd`` and ``PATRONI_admin_OPTIONS='createrole,createdb'`` will cause creation of the user **admin** with the password **strongpasswd** that is allowed to create other users and databases.
+.. warning::
+   The time the HA loop executes at can be very valuable information in diagnosing failovers due to resource exhaustion and similar problems. When ``PATRONI_LOG_DEDUPLICATE_HEARTBEAT_LOGS`` is set to ``true`` there will be no log generated for the HA loop execution (unless the leader changes) and hence this potentially useful information will not be available from the logs.
 
 Citus
 -----
@@ -55,9 +59,9 @@ Consul
 -  **PATRONI\_CONSUL\_CONSISTENCY**: (optional) Select consul consistency mode. Possible values are ``default``, ``consistent``, or ``stale`` (more details in `consul API reference <https://www.consul.io/api/features/consistency.html/>`__)
 -  **PATRONI\_CONSUL\_CHECKS**: (optional) list of Consul health checks used for the session. By default an empty list is used.
 -  **PATRONI\_CONSUL\_REGISTER\_SERVICE**: (optional) whether or not to register a service with the name defined by the scope parameter and the tag master, primary, replica, or standby-leader depending on the node's role. Defaults to **false**
--  **PATRONI\_CONSUL\_SERVICE\_TAGS**: (optional) additional static tags to add to the Consul service apart from the role (``master``/``primary``/``replica``/``standby-leader``). By default an empty list is used.
+-  **PATRONI\_CONSUL\_SERVICE\_TAGS**: (optional) additional static tags to add to the Consul service apart from the role (``primary``/``replica``/``standby-leader``). By default an empty list is used.
 -  **PATRONI\_CONSUL\_SERVICE\_CHECK\_INTERVAL**: (optional) how often to perform health check against registered url
--  **PATRONI\_CONSUL\_SERVICE\_CHECK\_TLS\_SERVER\_NAME**: (optional) overide SNI host when connecting via TLS, see also `consul agent check API reference <https://www.consul.io/api-docs/agent/check#tlsservername>`__.
+-  **PATRONI\_CONSUL\_SERVICE\_CHECK\_TLS\_SERVER\_NAME**: (optional) override SNI host when connecting via TLS, see also `consul agent check API reference <https://www.consul.io/api-docs/agent/check#tlsservername>`__.
 
 Etcd
 ----
@@ -81,7 +85,7 @@ Etcdv3
 Environment names for Etcdv3 are similar as for Etcd, you just need to use ``ETCD3`` instead of ``ETCD`` in the variable name. Example: ``PATRONI_ETCD3_HOST``, ``PATRONI_ETCD3_CACERT``, and so on.
 
 .. warning::
-    Keys created with protocol version 2 are not visible with protocol version 3 and the other way around, therefore it is not possible to switch from Etcd to Etcdv3 just by updating Patroni configuration.
+    Keys created with protocol version 2 are not visible with protocol version 3 and the other way around, therefore it is not possible to switch from Etcd to Etcdv3 just by updating Patroni configuration. In addition, Patroni uses Etcd's gRPC-gateway (proxy) to communicate with the V3 API, which means that TLS common name authentication is not possible.
 
 
 ZooKeeper
@@ -94,6 +98,7 @@ ZooKeeper
 -  **PATRONI\_ZOOKEEPER\_KEY\_PASSWORD**: (optional) The client key password.
 -  **PATRONI\_ZOOKEEPER\_VERIFY**: (optional) Whether to verify certificate or not. Defaults to ``true``.
 -  **PATRONI\_ZOOKEEPER\_SET\_ACLS**: (optional) If set, configure Kazoo to apply a default ACL to each ZNode that it creates. ACLs will assume 'x509' schema and should be specified as a dictionary with the principal as the key and one or more permissions as a list in the value.  Permissions may be one of ``CREATE``, ``READ``, ``WRITE``, ``DELETE`` or ``ADMIN``.  For example, ``set_acls: {CN=principal1: [CREATE, READ], CN=principal2: [ALL]}``.
+-  **PATRONI\_ZOOKEEPER\_AUTH\_DATA**: (optional) Authentication credentials to use for the connection. Should be a dictionary in the form that `scheme` is the key and `credential` is the value. Defaults to empty dictionary.
 
 .. note::
     It is required to install ``kazoo>=2.6.0`` to support SSL.
@@ -112,11 +117,12 @@ Kubernetes
 -  **PATRONI\_KUBERNETES\_NAMESPACE**: (optional) Kubernetes namespace where the Patroni pod is running. Default value is `default`.
 -  **PATRONI\_KUBERNETES\_LABELS**: Labels in format ``{label1: value1, label2: value2}``. These labels will be used to find existing objects (Pods and either Endpoints or ConfigMaps) associated with the current cluster. Also Patroni will set them on every object (Endpoint or ConfigMap) it creates.
 -  **PATRONI\_KUBERNETES\_SCOPE\_LABEL**: (optional) name of the label containing cluster name. Default value is `cluster-name`.
--  **PATRONI\_KUBERNETES\_ROLE\_LABEL**: (optional) name of the label containing role (master or replica or other custom value). Patroni will set this label on the pod it runs in. Default value is ``role``.
--  **PATRONI\_KUBERNETES\_LEADER\_LABEL\_VALUE**: (optional) value of the pod label when Postgres role is `master`. Default value is `master`.
+-  **PATRONI\_KUBERNETES\_BOOTSTRAP\_LABELS**: (optional) Labels in format ``{label1: value1, label2: value2}``. These labels will be assigned to a Patroni pod when its state is either ``initializing new cluster``, ``running custom bootstrap script``, ``starting after custom bootstrap`` or ``creating replica``.
+-  **PATRONI\_KUBERNETES\_ROLE\_LABEL**: (optional) name of the label containing role (`primary`, `replica` or other custom value). Patroni will set this label on the pod it runs in. Default value is ``role``.
+-  **PATRONI\_KUBERNETES\_LEADER\_LABEL\_VALUE**: (optional) value of the pod label when Postgres role is `primary`. Default value is `primary`.
 -  **PATRONI\_KUBERNETES\_FOLLOWER\_LABEL\_VALUE**: (optional) value of the pod label when Postgres role is `replica`. Default value is `replica`.
--  **PATRONI\_KUBERNETES\_STANDBY\_LEADER\_LABEL\_VALUE**: (optional) value of the pod label when Postgres role is ``standby-leader``. Default value is ``standby-leader``.
--  **PATRONI\_KUBERNETES\_TMP\_ROLE\_LABEL**: (optional) name of the temporary label containing role (master or replica). Value of this label will always use the default of corresponding role. Set only when necessary.
+-  **PATRONI\_KUBERNETES\_STANDBY\_LEADER\_LABEL\_VALUE**: (optional) value of the pod label when Postgres role is ``standby_leader``. Default value is ``primary``.
+-  **PATRONI\_KUBERNETES\_TMP\_ROLE\_LABEL**: (optional) name of the temporary label containing role (`primary` or `replica`). Value of this label will always use the default of corresponding role. Set only when necessary.
 -  **PATRONI\_KUBERNETES\_USE\_ENDPOINTS**: (optional) if set to true, Patroni will use Endpoints instead of ConfigMaps to run leader elections and keep cluster state.
 -  **PATRONI\_KUBERNETES\_POD\_IP**: (optional) IP address of the pod Patroni is running in. This value is required when `PATRONI_KUBERNETES_USE_ENDPOINTS` is enabled and is used to populate the leader endpoint subsets when the pod's PostgreSQL is promoted.
 -  **PATRONI\_KUBERNETES\_PORTS**: (optional) if the Service object has the name for the port, the same name must appear in the Endpoint object, otherwise service won't work. For example, if your service is defined as ``{Kind: Service, spec: {ports: [{name: postgresql, port: 5432, targetPort: 5432}]}}``, then you have to set ``PATRONI_KUBERNETES_PORTS='[{"name": "postgresql", "port": 5432}]'`` and Patroni will use it for updating subsets of the leader Endpoint. This parameter is used only if `PATRONI_KUBERNETES_USE_ENDPOINTS` is set.
@@ -154,9 +160,10 @@ PostgreSQL
 -  **PATRONI\_REPLICATION\_SSLKEY**: (optional) maps to the `sslkey <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLKEY>`__ connection parameter, which specifies the location of the secret key used with the client's certificate.
 -  **PATRONI\_REPLICATION\_SSLPASSWORD**: (optional) maps to the `sslpassword <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLPASSWORD>`__ connection parameter, which specifies the password for the secret key specified in ``PATRONI_REPLICATION_SSLKEY``.
 -  **PATRONI\_REPLICATION\_SSLCERT**: (optional) maps to the `sslcert <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLCERT>`__ connection parameter, which specifies the location of the client certificate.
--  **PATRONI\_REPLICATION\_SSLROOTCERT**: (optional) maps to the `sslrootcert <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLROOTCERT>`__ connection parameter, which specifies the location of a file containing one ore more certificate authorities (CA) certificates that the client will use to verify a server's certificate.
+-  **PATRONI\_REPLICATION\_SSLROOTCERT**: (optional) maps to the `sslrootcert <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLROOTCERT>`__ connection parameter, which specifies the location of a file containing one or more certificate authorities (CA) certificates that the client will use to verify a server's certificate.
 -  **PATRONI\_REPLICATION\_SSLCRL**: (optional) maps to the `sslcrl <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLCRL>`__ connection parameter, which specifies the location of a file containing a certificate revocation list. A client will reject connecting to any server that has a certificate present in this list.
 -  **PATRONI\_REPLICATION\_SSLCRLDIR**: (optional) maps to the `sslcrldir <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLCRLDIR>`__ connection parameter, which specifies the location of a directory with files containing a certificate revocation list. A client will reject connecting to any server that has a certificate present in this list.
+-  **PATRONI\_REPLICATION\_SSLNEGOTIATION**: (optional) maps to the `sslnegotiation <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLNEGOTIATION>`__ connection parameter, which controls how SSL encryption is negotiated with the server, if SSL is used.
 -  **PATRONI\_REPLICATION\_GSSENCMODE**: (optional) maps to the `gssencmode <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-GSSENCMODE>`__ connection parameter, which determines whether or with what priority a secure GSS TCP/IP connection will be negotiated with the server
 -  **PATRONI\_REPLICATION\_CHANNEL\_BINDING**: (optional) maps to the `channel_binding <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-CHANNEL-BINDING>`__ connection parameter, which controls the client's use of channel binding.
 -  **PATRONI\_SUPERUSER\_USERNAME**: name for the superuser, set during initialization (initdb) and later used by Patroni to connect to the postgres. Also this user is used by pg_rewind.
@@ -165,9 +172,10 @@ PostgreSQL
 -  **PATRONI\_SUPERUSER\_SSLKEY**: (optional) maps to the `sslkey <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLKEY>`__ connection parameter, which specifies the location of the secret key used with the client's certificate.
 -  **PATRONI\_SUPERUSER\_SSLPASSWORD**: (optional) maps to the `sslpassword <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLPASSWORD>`__ connection parameter, which specifies the password for the secret key specified in ``PATRONI_SUPERUSER_SSLKEY``.
 -  **PATRONI\_SUPERUSER\_SSLCERT**: (optional) maps to the `sslcert <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLCERT>`__ connection parameter, which specifies the location of the client certificate.
--  **PATRONI\_SUPERUSER\_SSLROOTCERT**: (optional) maps to the `sslrootcert <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLROOTCERT>`__ connection parameter, which specifies the location of a file containing one ore more certificate authorities (CA) certificates that the client will use to verify a server's certificate.
+-  **PATRONI\_SUPERUSER\_SSLROOTCERT**: (optional) maps to the `sslrootcert <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLROOTCERT>`__ connection parameter, which specifies the location of a file containing one or more certificate authorities (CA) certificates that the client will use to verify a server's certificate.
 -  **PATRONI\_SUPERUSER\_SSLCRL**: (optional) maps to the `sslcrl <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLCRL>`__ connection parameter, which specifies the location of a file containing a certificate revocation list. A client will reject connecting to any server that has a certificate present in this list.
 -  **PATRONI\_SUPERUSER\_SSLCRLDIR**: (optional) maps to the `sslcrldir <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLCRLDIR>`__ connection parameter, which specifies the location of a directory with files containing a certificate revocation list. A client will reject connecting to any server that has a certificate present in this list.
+-  **PATRONI\_SUPERUSER\_SSLNEGOTIATION**: (optional) maps to the `sslnegotiation <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLNEGOTIATION>`__ connection parameter, which controls how SSL encryption is negotiated with the server, if SSL is used.
 -  **PATRONI\_SUPERUSER\_GSSENCMODE**: (optional) maps to the `gssencmode <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-GSSENCMODE>`__ connection parameter, which determines whether or with what priority a secure GSS TCP/IP connection will be negotiated with the server
 -  **PATRONI\_SUPERUSER\_CHANNEL\_BINDING**: (optional) maps to the `channel_binding <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-CHANNEL-BINDING>`__ connection parameter, which controls the client's use of channel binding.
 -  **PATRONI\_REWIND\_USERNAME**: (optional) name for the user for ``pg_rewind``; the user will be created during initialization of postgres 11+ and all necessary `permissions <https://www.postgresql.org/docs/11/app-pgrewind.html#id-1.9.5.8.8>`__ will be granted.
@@ -176,9 +184,10 @@ PostgreSQL
 -  **PATRONI\_REWIND\_SSLKEY**: (optional) maps to the `sslkey <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLKEY>`__ connection parameter, which specifies the location of the secret key used with the client's certificate.
 -  **PATRONI\_REWIND\_SSLPASSWORD**: (optional) maps to the `sslpassword <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLPASSWORD>`__ connection parameter, which specifies the password for the secret key specified in ``PATRONI_REWIND_SSLKEY``.
 -  **PATRONI\_REWIND\_SSLCERT**: (optional) maps to the `sslcert <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLCERT>`__ connection parameter, which specifies the location of the client certificate.
--  **PATRONI\_REWIND\_SSLROOTCERT**: (optional) maps to the `sslrootcert <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLROOTCERT>`__ connection parameter, which specifies the location of a file containing one ore more certificate authorities (CA) certificates that the client will use to verify a server's certificate.
+-  **PATRONI\_REWIND\_SSLROOTCERT**: (optional) maps to the `sslrootcert <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLROOTCERT>`__ connection parameter, which specifies the location of a file containing one or more certificate authorities (CA) certificates that the client will use to verify a server's certificate.
 -  **PATRONI\_REWIND\_SSLCRL**: (optional) maps to the `sslcrl <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLCRL>`__ connection parameter, which specifies the location of a file containing a certificate revocation list. A client will reject connecting to any server that has a certificate present in this list.
 -  **PATRONI\_REWIND\_SSLCRLDIR**: (optional) maps to the `sslcrldir <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLCRLDIR>`__ connection parameter, which specifies the location of a directory with files containing a certificate revocation list. A client will reject connecting to any server that has a certificate present in this list.
+-  **PATRONI\_REWIND\_SSLNEGOTIATION**: (optional) maps to the `sslnegotiation <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLNEGOTIATION>`__ connection parameter, which controls how SSL encryption is negotiated with the server, if SSL is used.
 -  **PATRONI\_REWIND\_GSSENCMODE**: (optional) maps to the `gssencmode <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-GSSENCMODE>`__ connection parameter, which determines whether or with what priority a secure GSS TCP/IP connection will be negotiated with the server
 -  **PATRONI\_REWIND\_CHANNEL\_BINDING**: (optional) maps to the `channel_binding <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-CHANNEL-BINDING>`__ connection parameter, which controls the client's use of channel binding.
 
@@ -209,10 +218,10 @@ REST API
 CTL
 ---
 -  **PATRONICTL\_CONFIG\_FILE**: (optional) location of the configuration file.
--  **PATRONI\_CTL\_USERNAME**: (optional) Basic-auth username for accessing protected REST API endpoints. If not provided patronictl will use the value provided for REST API "username" parameter.
--  **PATRONI\_CTL\_PASSWORD**: (optional) Basic-auth password for accessing protected REST API endpoints. If not provided patronictl will use the value provided for REST API "password" parameter.
+-  **PATRONI\_CTL\_USERNAME**: (optional) Basic-auth username for accessing protected REST API endpoints. If not provided :ref:`patronictl` will use the value provided for REST API "username" parameter.
+-  **PATRONI\_CTL\_PASSWORD**: (optional) Basic-auth password for accessing protected REST API endpoints. If not provided :ref:`patronictl` will use the value provided for REST API "password" parameter.
 -  **PATRONI\_CTL\_INSECURE**: (optional) Allow connections to REST API without verifying SSL certs.
--  **PATRONI\_CTL\_CACERT**: (optional) Specifies the file with the CA_BUNDLE file or directory with certificates of trusted CAs to use while verifying REST API SSL certs. If not provided patronictl will use the value provided for REST API "cafile" parameter.
+-  **PATRONI\_CTL\_CACERT**: (optional) Specifies the file with the CA_BUNDLE file or directory with certificates of trusted CAs to use while verifying REST API SSL certs. If not provided :ref:`patronictl` will use the value provided for REST API "cafile" parameter.
 -  **PATRONI\_CTL\_CERTFILE**: (optional) Specifies the file with the client certificate in the PEM format.
 -  **PATRONI\_CTL\_KEYFILE**: (optional) Specifies the file with the client secret key in the PEM format.
 -  **PATRONI\_CTL\_KEYFILE\_PASSWORD**: (optional) Specifies a password for decrypting the client keyfile.

docs/README.rst

@@ -6,12 +6,10 @@ Introduction
 
 Patroni is a template for high availability (HA) PostgreSQL solutions using Python. Patroni originated as a fork of `Governor <https://github.com/compose/governor>`__, the project from Compose. It includes plenty of new features.
 
-For an example of a Docker-based deployment with Patroni, see `Spilo <https://github.com/zalando/spilo>`__, currently in use at Zalando.
-
 For additional background info, see:
 
 * `PostgreSQL HA with Kubernetes and Patroni <https://www.youtube.com/watch?v=iruaCgeG7qs>`__, talk by Josh Berkus at KubeCon 2016 (video)
-* `Feb. 2016 Zalando Tech blog post <https://tech.zalando.de/blog/zalandos-patroni-a-template-for-high-availability-postgresql/>`__
+* `Feb. 2016 Zalando Tech blog post <https://engineering.zalando.com/posts/2016/02/zalandos-patroni-a-template-for-high-availability-postgresql.html>`__
 
 
 Development Status
@@ -25,82 +23,7 @@ We report new releases information :ref:`here <releases>`.
 Technical Requirements/Installation
 -----------------------------------
 
-**Pre-requirements for Mac OS**
-
-To install requirements on a Mac, run the following:
-
-::
-
-    brew install postgresql etcd haproxy libyaml python
-
-.. _psycopg2_install_options:
-
-**Psycopg**
-
-Starting from `psycopg2-2.8 <http://initd.org/psycopg/articles/2019/04/04/psycopg-28-released/>`__ the binary version of psycopg2 will no longer be installed by default. Installing it from the source code requires C compiler and postgres+python dev packages.
-Since in the python world it is not possible to specify dependency as ``psycopg2 OR psycopg2-binary`` you will have to decide how to install it.
-
-There are a few options available:
-
-1. Use the package manager from your distro
-
-::
-
-    sudo apt-get install python3-psycopg2  # install psycopg2 module on Debian/Ubuntu
-    sudo yum install python3-psycopg2      # install psycopg2 on RedHat/Fedora/CentOS
-
-2. Install psycopg2 from the binary package
-
-::
-
-    pip install psycopg2-binary
-
-3. Install psycopg2 from source
-
-::
-
-    pip install psycopg2>=2.5.4
-
-4. Use psycopg 3.0 instead of psycopg2
-
-::
-
-    pip install psycopg[binary]>=3.0.0
-
-**General installation for pip**
-
-Patroni can be installed with pip:
-
-::
-
-    pip install patroni[dependencies]
-
-where dependencies can be either empty, or consist of one or more of the following:
-
-etcd or etcd3
-    `python-etcd` module in order to use Etcd as Distributed Configuration Store (DCS)
-consul
-    `python-consul` module in order to use Consul as DCS
-zookeeper
-    `kazoo` module in order to use Zookeeper as DCS
-exhibitor
-    `kazoo` module in order to use Exhibitor as DCS (same dependencies as for Zookeeper)
-kubernetes
-    `kubernetes` module in order to use Kubernetes as DCS in Patroni
-raft
-    `pysyncobj` module in order to use python Raft implementation as DCS
-aws
-    `boto3` in order to use AWS callbacks
-
-For example, the command in order to install Patroni together with dependencies for Etcd as a DCS and AWS callbacks is:
-
-::
-
-    pip install patroni[etcd,aws]
-
-Note that external tools to call in the replica creation or custom bootstrap scripts (i.e. WAL-E) should be installed
-independently of Patroni.
-
+Go :ref:`here <installation>` for guidance on installing and upgrading Patroni on various platforms.
 
 .. _running_configuring:
 
@@ -114,7 +37,7 @@ perfectly fine. You can add more standby nodes later.
 Running and Configuring
 -----------------------
 
-The following section assumes Patroni repository as being cloned from https://github.com/zalando/patroni. Namely, you
+The following section assumes Patroni repository as being cloned from https://github.com/patroni/patroni. Namely, you
 will need example configuration files `postgres0.yml` and `postgres1.yml`. If you installed Patroni with pip, you can
 obtain those files from the git repository and replace `./patroni.py` below with `patroni` command.
 
@@ -144,7 +67,7 @@ run:
 YAML Configuration
 ------------------
 
-Go :ref:`here <yaml_configuration>` for comprehensive information about settings for etcd, consul, and ZooKeeper. And for an example, see `postgres0.yml <https://github.com/zalando/patroni/blob/master/postgres0.yml>`__.
+Go :ref:`here <yaml_configuration>` for comprehensive information about settings for etcd, consul, and ZooKeeper. And for an example, see `postgres0.yml <https://github.com/patroni/patroni/blob/master/postgres0.yml>`__.
 
 
 Environment Configuration

docs/citus.rst

@@ -34,30 +34,36 @@ There are only a few simple rules you need to follow:
 
 After that you just need to start Patroni and it will handle the rest:
 
+0. Patroni will set ``bootstrap.dcs.synchronous_mode`` to :ref:`quorum <quorum_mode>`
+   if it is not explicitly set to any other value.
 1. ``citus`` extension will be automatically added to ``shared_preload_libraries``.
 2. If ``max_prepared_transactions`` isn't explicitly set in the global
    :ref:`dynamic configuration <dynamic_configuration>` Patroni will
    automatically set it to ``2*max_connections``.
-3. The ``citus.database`` will be automatically created followed by ``CREATE EXTENSION citus``.
-4. Current superuser :ref:`credentials <postgresql_settings>` will be added to the ``pg_dist_authinfo``
+3. The ``citus.local_hostname`` GUC value will be adjusted from ``localhost`` to the
+   value that Patroni is using in order to connect to the local PostgreSQL
+   instance. The value sometimes should be different from the ``localhost``
+   because PostgreSQL might be not listening on it.
+4. The ``citus.database`` will be automatically created followed by ``CREATE EXTENSION citus``.
+5. Current superuser :ref:`credentials <postgresql_settings>` will be added to the ``pg_dist_authinfo``
    table to allow cross-node communication. Don't forget to update them if
    later you decide to change superuser username/password/sslcert/sslkey!
-5. The coordinator primary node will automatically discover worker primary
+6. The coordinator primary node will automatically discover worker primary
    nodes and add them to the ``pg_dist_node`` table using the
    ``citus_add_node()`` function.
-6. Patroni will also maintain ``pg_dist_node`` in case failover/switchover
+7. Patroni will also maintain ``pg_dist_node`` in case failover/switchover
    on the coordinator or worker clusters occurs.
 
 patronictl
 ----------
 
 Coordinator and worker clusters are physically different PostgreSQL/Patroni
-clusters that are just logically groupped together using the
+clusters that are just logically grouped together using the
 `Citus <https://github.com/citusdata/citus>`__ database extension to
 PostgreSQL. Therefore in most cases it is not possible to manage them as a
 single entity.
 
-It results in two major differences in ``patronictl`` behaviour when
+It results in two major differences in :ref:`patronictl` behaviour when
 ``patroni.yaml`` has the ``citus`` section comparing with the usual:
 
 1. The ``list`` and the ``topology`` by default output all members of the Citus
@@ -65,44 +71,44 @@ It results in two major differences in ``patronictl`` behaviour when
    which Citus group they belong to.
 2. For all ``patronictl`` commands the new option is introduced, named
    ``--group``. For some commands the default value for the group might be
-   taken from the ``patroni.yaml``. For example, ``patronictl pause`` will
+   taken from the ``patroni.yaml``. For example, :ref:`patronictl_pause` will
    enable the maintenance mode by default for the ``group`` that is set in the
-   ``citus`` section, but for example for ``patronictl  switchover`` or
-   ``patronictl remove`` the group must be explicitly specified.
+   ``citus`` section, but for example for :ref:`patronictl_switchover` or
+   :ref:`patronictl_remove` the group must be explicitly specified.
 
-An example of ``patronictl list`` output for the Citus cluster::
+An example of :ref:`patronictl_list` output for the Citus cluster::
 
     postgres@coord1:~$ patronictl list demo
-    + Citus cluster: demo ----------+--------------+---------+----+-----------+
-    | Group | Member  | Host        | Role         | State   | TL | Lag in MB |
-    +-------+---------+-------------+--------------+---------+----+-----------+
-    |     0 | coord1  | 172.27.0.10 | Replica      | running |  1 |         0 |
-    |     0 | coord2  | 172.27.0.6  | Sync Standby | running |  1 |         0 |
-    |     0 | coord3  | 172.27.0.4  | Leader       | running |  1 |           |
-    |     1 | work1-1 | 172.27.0.8  | Sync Standby | running |  1 |         0 |
-    |     1 | work1-2 | 172.27.0.2  | Leader       | running |  1 |           |
-    |     2 | work2-1 | 172.27.0.5  | Sync Standby | running |  1 |         0 |
-    |     2 | work2-2 | 172.27.0.7  | Leader       | running |  1 |           |
-    +-------+---------+-------------+--------------+---------+----+-----------+
+    + Citus cluster: demo ----------+----------------+---------+----+-----------+
+    | Group | Member  | Host        | Role           | State   | TL | Lag in MB |
+    +-------+---------+-------------+----------------+---------+----+-----------+
+    |     0 | coord1  | 172.27.0.10 | Replica        | running |  1 |         0 |
+    |     0 | coord2  | 172.27.0.6  | Quorum Standby | running |  1 |         0 |
+    |     0 | coord3  | 172.27.0.4  | Leader         | running |  1 |           |
+    |     1 | work1-1 | 172.27.0.8  | Quorum Standby | running |  1 |         0 |
+    |     1 | work1-2 | 172.27.0.2  | Leader         | running |  1 |           |
+    |     2 | work2-1 | 172.27.0.5  | Quorum Standby | running |  1 |         0 |
+    |     2 | work2-2 | 172.27.0.7  | Leader         | running |  1 |           |
+    +-------+---------+-------------+----------------+---------+----+-----------+
 
 If we add the ``--group`` option, the output will change to::
 
     postgres@coord1:~$ patronictl list demo --group 0
-    + Citus cluster: demo (group: 0, 7179854923829112860) -----------+
-    | Member | Host        | Role         | State   | TL | Lag in MB |
-    +--------+-------------+--------------+---------+----+-----------+
-    | coord1 | 172.27.0.10 | Replica      | running |  1 |         0 |
-    | coord2 | 172.27.0.6  | Sync Standby | running |  1 |         0 |
-    | coord3 | 172.27.0.4  | Leader       | running |  1 |           |
-    +--------+-------------+--------------+---------+----+-----------+
+    + Citus cluster: demo (group: 0, 7179854923829112860) -+-----------+
+    | Member | Host        | Role           | State   | TL | Lag in MB |
+    +--------+-------------+----------------+---------+----+-----------+
+    | coord1 | 172.27.0.10 | Replica        | running |  1 |         0 |
+    | coord2 | 172.27.0.6  | Quorum Standby | running |  1 |         0 |
+    | coord3 | 172.27.0.4  | Leader         | running |  1 |           |
+    +--------+-------------+----------------+---------+----+-----------+
 
     postgres@coord1:~$ patronictl list demo --group 1
-    + Citus cluster: demo (group: 1, 7179854923881963547) -----------+
-    | Member  | Host       | Role         | State   | TL | Lag in MB |
-    +---------+------------+--------------+---------+----+-----------+
-    | work1-1 | 172.27.0.8 | Sync Standby | running |  1 |         0 |
-    | work1-2 | 172.27.0.2 | Leader       | running |  1 |           |
-    +---------+------------+--------------+---------+----+-----------+
+    + Citus cluster: demo (group: 1, 7179854923881963547) -+-----------+
+    | Member  | Host       | Role           | State   | TL | Lag in MB |
+    +---------+------------+----------------+---------+----+-----------+
+    | work1-1 | 172.27.0.8 | Quorum Standby | running |  1 |         0 |
+    | work1-2 | 172.27.0.2 | Leader         | running |  1 |           |
+    +---------+------------+----------------+---------+----+-----------+
 
 Citus worker switchover
 -----------------------
@@ -115,33 +121,33 @@ the coordinator for the shards hosted on a worker node. The switchover then
 happens while the traffic is kept on the coordinator, and resumes as soon as a
 new primary worker node is ready to accept read-write queries.
 
-An example of ``patronictl switchover`` on the worker cluster::
+An example of :ref:`patronictl_switchover` on the worker cluster::
 
     postgres@coord1:~$ patronictl switchover demo
-    + Citus cluster: demo ----------+--------------+---------+----+-----------+
-    | Group | Member  | Host        | Role         | State   | TL | Lag in MB |
-    +-------+---------+-------------+--------------+---------+----+-----------+
-    |     0 | coord1  | 172.27.0.10 | Replica      | running |  1 |         0 |
-    |     0 | coord2  | 172.27.0.6  | Sync Standby | running |  1 |         0 |
-    |     0 | coord3  | 172.27.0.4  | Leader       | running |  1 |           |
-    |     1 | work1-1 | 172.27.0.8  | Leader       | running |  1 |           |
-    |     1 | work1-2 | 172.27.0.2  | Sync Standby | running |  1 |         0 |
-    |     2 | work2-1 | 172.27.0.5  | Sync Standby | running |  1 |         0 |
-    |     2 | work2-2 | 172.27.0.7  | Leader       | running |  1 |           |
-    +-------+---------+-------------+--------------+---------+----+-----------+
+    + Citus cluster: demo ----------+----------------+---------+----+-----------+
+    | Group | Member  | Host        | Role           | State   | TL | Lag in MB |
+    +-------+---------+-------------+----------------+---------+----+-----------+
+    |     0 | coord1  | 172.27.0.10 | Replica        | running |  1 |         0 |
+    |     0 | coord2  | 172.27.0.6  | Quorum Standby | running |  1 |         0 |
+    |     0 | coord3  | 172.27.0.4  | Leader         | running |  1 |           |
+    |     1 | work1-1 | 172.27.0.8  | Leader         | running |  1 |           |
+    |     1 | work1-2 | 172.27.0.2  | Quorum Standby | running |  1 |         0 |
+    |     2 | work2-1 | 172.27.0.5  | Quorum Standby | running |  1 |         0 |
+    |     2 | work2-2 | 172.27.0.7  | Leader         | running |  1 |           |
+    +-------+---------+-------------+----------------+---------+----+-----------+
     Citus group: 2
     Primary [work2-2]:
     Candidate ['work2-1'] []:
-    When should the switchover take place (e.g. 2022-12-22T08:02 )  [now]:
+    When should the switchover take place (e.g. 2024-08-26T08:02 )  [now]:
     Current cluster topology
-    + Citus cluster: demo (group: 2, 7179854924063375386) -----------+
-    | Member  | Host       | Role         | State   | TL | Lag in MB |
-    +---------+------------+--------------+---------+----+-----------+
-    | work2-1 | 172.27.0.5 | Sync Standby | running |  1 |         0 |
-    | work2-2 | 172.27.0.7 | Leader       | running |  1 |           |
-    +---------+------------+--------------+---------+----+-----------+
+    + Citus cluster: demo (group: 2, 7179854924063375386) -+-----------+
+    | Member  | Host       | Role           | State   | TL | Lag in MB |
+    +---------+------------+----------------+---------+----+-----------+
+    | work2-1 | 172.27.0.5 | Quorum Standby | running |  1 |         0 |
+    | work2-2 | 172.27.0.7 | Leader         | running |  1 |           |
+    +---------+------------+----------------+---------+----+-----------+
     Are you sure you want to switchover cluster demo, demoting current primary work2-2? [y/N]: y
-    2022-12-22 07:02:40.33003 Successfully switched over to "work2-1"
+    2024-08-26 07:02:40.33003 Successfully switched over to "work2-1"
     + Citus cluster: demo (group: 2, 7179854924063375386) ------+
     | Member  | Host       | Role    | State   | TL | Lag in MB |
     +---------+------------+---------+---------+----+-----------+
@@ -150,32 +156,41 @@ An example of ``patronictl switchover`` on the worker cluster::
     +---------+------------+---------+---------+----+-----------+
 
     postgres@coord1:~$ patronictl list demo
-    + Citus cluster: demo ----------+--------------+---------+----+-----------+
-    | Group | Member  | Host        | Role         | State   | TL | Lag in MB |
-    +-------+---------+-------------+--------------+---------+----+-----------+
-    |     0 | coord1  | 172.27.0.10 | Replica      | running |  1 |         0 |
-    |     0 | coord2  | 172.27.0.6  | Sync Standby | running |  1 |         0 |
-    |     0 | coord3  | 172.27.0.4  | Leader       | running |  1 |           |
-    |     1 | work1-1 | 172.27.0.8  | Leader       | running |  1 |           |
-    |     1 | work1-2 | 172.27.0.2  | Sync Standby | running |  1 |         0 |
-    |     2 | work2-1 | 172.27.0.5  | Leader       | running |  2 |           |
-    |     2 | work2-2 | 172.27.0.7  | Sync Standby | running |  2 |         0 |
-    +-------+---------+-------------+--------------+---------+----+-----------+
+    + Citus cluster: demo ----------+----------------+---------+----+-----------+
+    | Group | Member  | Host        | Role           | State   | TL | Lag in MB |
+    +-------+---------+-------------+----------------+---------+----+-----------+
+    |     0 | coord1  | 172.27.0.10 | Replica        | running |  1 |         0 |
+    |     0 | coord2  | 172.27.0.6  | Quorum Standby | running |  1 |         0 |
+    |     0 | coord3  | 172.27.0.4  | Leader         | running |  1 |           |
+    |     1 | work1-1 | 172.27.0.8  | Leader         | running |  1 |           |
+    |     1 | work1-2 | 172.27.0.2  | Quorum Standby | running |  1 |         0 |
+    |     2 | work2-1 | 172.27.0.5  | Leader         | running |  2 |           |
+    |     2 | work2-2 | 172.27.0.7  | Quorum Standby | running |  2 |         0 |
+    +-------+---------+-------------+----------------+---------+----+-----------+
 
 And this is how it looks on the coordinator side::
 
     # The worker primary notifies the coordinator that it is going to execute "pg_ctl stop".
-    2022-12-22 07:02:38,636 DEBUG: query("BEGIN")
-    2022-12-22 07:02:38,636 DEBUG: query("SELECT pg_catalog.citus_update_node(3, '172.27.0.7-demoted', 5432, true, 10000)")
+    2024-08-26 07:02:38,636 DEBUG: query(BEGIN, ())
+    2024-08-26 07:02:38,636 DEBUG: query(SELECT pg_catalog.citus_update_node(%s, %s, %s, true, %s), (3, '172.19.0.7-demoted', 5432, 10000))
     # From this moment all application traffic on the coordinator to the worker group 2 is paused.
 
+    # The old worker primary is assigned as a secondary. 
+    2024-08-26 07:02:40,084 DEBUG: query(SELECT pg_catalog.citus_update_node(%s, %s, %s, true, %s), (7, '172.19.0.7', 5432, 10000))
+
     # The future worker primary notifies the coordinator that it acquired the leader lock in DCS and about to run "pg_ctl promote".
-    2022-12-22 07:02:40,085 DEBUG: query("SELECT pg_catalog.citus_update_node(3, '172.27.0.5', 5432)")
+    2024-08-26 07:02:40,085 DEBUG: query(SELECT pg_catalog.citus_update_node(%s, %s, %s, true, %s), (3, '172.19.0.5', 5432, 10000))
 
     # The new worker primary just finished promote and notifies coordinator that it is ready to accept read-write traffic.
-    2022-12-22 07:02:41,485 DEBUG: query("COMMIT")
+    2024-08-26 07:02:41,485 DEBUG: query(COMMIT, ())
     # From this moment the application traffic on the coordinator to the worker group 2 is unblocked.
 
+Secondary nodes
+---------------
+
+Starting from Patroni v4.0.0 Citus secondary nodes without ``noloadbalance`` :ref:`tag <tags_settings>` are also registered in ``pg_dist_node``.
+However, to use secondary nodes for read-only queries applications need to change `citus.use_secondary_nodes <https://docs.citusdata.com/en/latest/develop/api_guc.html#citus-use-secondary-nodes-enum>`__ GUC.
+
 Peek into DCS
 -------------
 
@@ -331,7 +346,7 @@ new Kubernetes objects ConfigMaps or Endpoints, it automatically puts the
 You can find a complete example of Patroni deployment on Kubernetes with Citus
 support in the `kubernetes`__ folder of the Patroni repository.
 
-__ https://github.com/zalando/patroni/tree/master/kubernetes
+__ https://github.com/patroni/patroni/tree/master/kubernetes
 
 There are two important files for you:
 
@@ -343,7 +358,7 @@ Citus upgrades and PostgreSQL major upgrades
 
 First, please read about upgrading Citus version in the `documentation`__.
 There is one minor change in the process. When executing upgrade, you have to
-use ``patronictl restart`` instead of ``systemctl restart`` to restart
+use :ref:`patronictl_restart` instead of ``systemctl restart`` to restart
 PostgreSQL.
 
 __ https://docs.citusdata.com/en/latest/admin_guide/upgrading_citus.html

docs/conf.py

@@ -21,6 +21,8 @@ import os
 
 import sys
 
+from sphinx.application import ENV_PICKLE_FILENAME
+
 sys.path.insert(0, os.path.abspath('..'))
 
 from patroni.version import __version__
@@ -54,6 +56,13 @@ apidoc_output_dir = 'modules'
 apidoc_excluded_paths = excludes
 apidoc_separate_modules = True
 
+# Include autodoc for all members, including private ones and the ones that are missing a docstring.
+autodoc_default_options = {
+    "members": True,
+    "undoc-members": True,
+    "private-members": True,
+}
+
 # Add any paths that contain templates here, relative to this directory.
 templates_path = ['_templates']
 
@@ -68,8 +77,8 @@ master_doc = 'index'
 
 # General information about the project.
 project = 'Patroni'
-copyright = '2015 Compose, Zalando SE'
-author = 'Zalando SE'
+copyright = '2025 Compose, Zalando SE, Patroni Contributors'
+author = 'Patroni Contributors'
 
 # The version info for the project you're documenting, acts as replacement for
 # |version| and |release|, also used in various other places throughout the
@@ -105,11 +114,8 @@ todo_include_todos = True
 # a list of builtin themes.
 #
 
+html_theme = 'sphinx_rtd_theme'
 on_rtd = os.environ.get('READTHEDOCS', None) == 'True'
-if not on_rtd:  # only import and set the theme if we're building docs locally
-    import sphinx_rtd_theme
-    html_theme = 'sphinx_rtd_theme'
-    html_theme_path = [sphinx_rtd_theme.get_html_theme_path()]
 
 # Theme options are theme-specific and customize the look and feel of a theme
 # further.  For a list of options available for each theme, see the
@@ -125,7 +131,7 @@ html_static_path = ['_static']
 # Replace "source" links with "edit on GitHub" when using rtd theme
 html_context = {
     'display_github': True,
-    'github_user': 'zalando',
+    'github_user': 'patroni',
     'github_repo': 'patroni',
     'github_version': 'master',
     'conf_py_path': '/docs/',
@@ -182,7 +188,7 @@ latex_elements = {
 #  author, documentclass [howto, manual, or own class]).
 latex_documents = [
     (master_doc, 'Patroni.tex', 'Patroni Documentation',
-     'Zalando SE', 'manual'),
+     'Patroni Contributors', 'manual'),
 ]
 
 
@@ -236,13 +242,24 @@ intersphinx_mapping = {'python': ('https://docs.python.org/', None)}
 # Remove these pages from index, references, toc trees, etc.
 # If the builder is not 'html' then add the API docs modules index to pages to be removed.
 exclude_from_builder = {
-    'latex': ['modules/modules'],
-    'epub': ['modules/modules'],
+    'latex': ['modules/'],
+    'epub': ['modules/'],
 }
 # Internal holding list, anything added here will always be excluded
 _docs_to_remove = []
 
 
+def config_inited(app, config):
+    """Run during Sphinx `config-inited` phase.
+
+    rtd reuses the environment, and there is no way to customize this behavior.
+    Thus we remove the saved env.
+    """
+    pickle_file = os.path.join(app.doctreedir, ENV_PICKLE_FILENAME)
+    if on_rtd and os.path.exists(pickle_file):
+        os.remove(pickle_file)
+
+
 def builder_inited(app):
     """Run during Sphinx `builder-inited` phase.
 
@@ -256,14 +273,28 @@ def builder_inited(app):
         _docs_to_remove.extend(exclude_from_builder[app.builder.name])
 
 
+def _to_be_removed(doc):
+    for remove in _docs_to_remove:
+        if doc.startswith(remove):
+            return True
+    return False
+
+
 def env_get_outdated(app, env, added, changed, removed):
     """Run during Sphinx `env-get-outdated` phase.
 
     Remove the items listed in `docs_to_remove` from known pages.
     """
-    added.difference_update(_docs_to_remove)
-    changed.difference_update(_docs_to_remove)
-    removed.update(_docs_to_remove)
+    to_remove = set()
+    if hasattr(env, 'found_docs'):
+        for doc in env.found_docs:
+            if _to_be_removed(doc):
+                to_remove.add(doc)
+    added.difference_update(to_remove)
+    changed.difference_update(to_remove)
+    removed.update(to_remove)
+    if hasattr(env, 'project'):
+        env.project.docnames.difference_update(to_remove)
     return []
 
 
@@ -275,11 +306,18 @@ def doctree_read(app, doctree):
     from sphinx import addnodes
     for toc_tree_node in doctree.traverse(addnodes.toctree):
         for e in toc_tree_node['entries']:
-            ref = str(e[1])
-            if ref in _docs_to_remove:
+            if _to_be_removed(str(e[1])):
                 toc_tree_node['entries'].remove(e)
 
 
+def autodoc_skip(app, what, name, obj, would_skip, options):
+    """Include autodoc of ``__init__`` methods, which are skipped by default."""
+    if name == "__init__":
+        return False
+    return would_skip
+
+
+
 # A possibility to have an own stylesheet, to add new rules or override existing ones
 # For the latter case, the CSS specificity of the rules should be higher than the default ones
 def setup(app):
@@ -289,6 +327,8 @@ def setup(app):
         app.add_stylesheet('custom.css')
 
     # Run extra steps to remove module docs when running with a non-html builder
+    app.connect('config-inited', config_inited)
     app.connect('builder-inited', builder_inited)
     app.connect('env-get-outdated', env_get_outdated)
     app.connect('doctree-read', doctree_read)
+    app.connect("autodoc-skip-member", autodoc_skip)

docs/contributing_guidelines.rst

@@ -3,21 +3,29 @@
 Contributing guidelines
 =======================
 
-Wanna contribute to Patroni? Yay - here is how!
+.. _chatting:
 
 Chatting
 --------
 
-Just want to chat with other Patroni users?  Looking for interactive troubleshooting help? Join us on channel `#patroni <https://postgresteam.slack.com/archives/C9XPYG92A>`__ in the `PostgreSQL Slack <https://pgtreats.info/slack-invite>`__.
+If you have a question, looking for an interactive troubleshooting help or want to chat with other Patroni users, join us on channel `#patroni <https://postgresteam.slack.com/archives/C9XPYG92A>`__ in the `PostgreSQL Slack <https://pgtreats.info/slack-invite>`__.
+
+.. _reporting_bugs:
+
+Reporting bugs
+--------------
+
+Before reporting a bug please make sure to **reproduce it with the latest Patroni version**!
+Also please double check if the issue already exists in our `Issues Tracker <https://github.com/patroni/patroni/issues>`__.
 
 Running tests
 -------------
 
 Requirements for running behave tests:
 
-1. PostgreSQL packages need to be installed.
-2. PostgreSQL binaries must be available in your `PATH`. You may need to add them to the path with something like `PATH=/usr/lib/postgresql/11/bin:$PATH python -m behave`.
-3. If you'd like to test with external DCSs (e.g., Etcd, Consul, and Zookeeper) you'll need the packages installed and respective services running and accepting unencrypted/unprotected connections on localhost and default port. In the case of Etcd or Consul, the behave test suite could start them up if binaries are available in the `PATH`.
+#. PostgreSQL packages including `contrib <https://www.postgresql.org/docs/current/contrib.html>`__ modules need to be installed.
+#. PostgreSQL binaries must be available in your `PATH`. You may need to add them to the path with something like `PATH=/usr/lib/postgresql/11/bin:$PATH python -m behave`.
+#. If you'd like to test with external DCSs (e.g., Etcd, Consul, and Zookeeper) you'll need the packages installed and respective services running and accepting unencrypted/unprotected connections on localhost and default port. In the case of Etcd or Consul, the behave test suite could start them up if binaries are available in the `PATH`.
 
 Install dependencies:
 
@@ -39,6 +47,13 @@ After you have all dependencies installed, you can run the various test suites:
     # Run the pytest suite in tests/:
     python setup.py test
 
+    # Moreover, you may want to run tests in different scopes for debugging purposes,
+    # the -s option include print output during test execution.
+    # Tests in pytest typically follow the pattern: FILEPATH::CLASSNAME::TESTNAME.
+    pytest -s tests/test_api.py
+    pytest -s tests/test_api.py::TestRestApiHandler
+    pytest -s tests/test_api.py::TestRestApiHandler::test_do_GET
+
     # Run the behave (https://behave.readthedocs.io/en/latest/) test suite in features/;
     # modify DCS as desired (raft has no dependencies so is the easiest to start with):
     DCS=raft python -m behave
@@ -143,12 +158,12 @@ If you want to disable this facility set the env var `OPEN_CMD` to the `:` no-op
 Behave tests
 ^^^^^^^^^^^^
 
-Behave tests with `-m behave` will build docker images based on PG_MAJOR version 11 through 15 and then run all
+Behave tests with `-m behave` will build docker images based on PG_MAJOR version 11 through 16 and then run all
 behave tests. This can take quite a long time to run so you might want to limit the scope to a select version of
 Postgres or to a specific feature set or steps.
 
 To specify the version of postgres include the full name of the dependent image build env that you want and then the
-behave env name. For instance if you want Postgres 15 use:
+behave env name. For instance if you want Postgres 14 use:
 
 .. code-block:: bash
 
@@ -163,19 +178,12 @@ the watchdog behave feature test scenario with all versions of Postgres.
 
 Of course you can combine the two.
 
-Reporting issues
-----------------
-
-If you have a question about patroni or have a problem using it, please read the :ref:`README <readme>` before filing an issue.
-Also double check with the current issues on our `Issues Tracker <https://github.com/zalando/patroni/issues>`__.
-
 Contributing a pull request
 ---------------------------
 
-1) Submit a comment to the relevant issue or create a new issue describing your proposed change.
-2) Do a fork, develop and test your code changes.
-3) Include documentation
-4) Submit a pull request.
+#. Fork the repository, develop and test your code changes.
+#. Reflect changes in the user documentation.
+#. Submit a pull request with a clear description of the changes objective. Link an existing issue if necessary.
 
 You'll get feedback about your pull request as soon as possible.
 

docs/dcs_failsafe_mode.rst

@@ -60,4 +60,4 @@ F.A.Q.
 
 - How to enable the Failsafe Mode?
 
-  Before enabling the ``failsafe_mode`` please make sure that Patroni version on all members is up-to-date. After that, you can use either the ``PATCH /config`` :ref:`REST API <rest_api>` or ``patronictl edit-config -s failsafe_mode=true``
+  Before enabling the ``failsafe_mode`` please make sure that Patroni version on all members is up-to-date. After that, you can use either the ``PATCH /config`` :ref:`REST API <rest_api>` or :ref:`patronictl edit-config -s failsafe_mode=true <patronictl_edit_config_parameters>`

docs/dynamic_configuration.rst

@@ -6,25 +6,35 @@ Dynamic Configuration Settings
 
 Dynamic configuration is stored in the DCS (Distributed Configuration Store) and applied on all cluster nodes.
 
-In order to change the dynamic configuration you can use either ``patronictl edit-config`` tool or Patroni :ref:`REST API <rest_api>`.
+In order to change the dynamic configuration you can use either :ref:`patronictl_edit_config` tool or Patroni :ref:`REST API <rest_api>`.
+
+-  **loop\_wait**: the number of seconds the loop will sleep. Default value: 10, minimum possible value: 1
+-  **ttl**: the TTL to acquire the leader lock (in seconds). Think of it as the length of time before initiation of the automatic failover process. Default value: 30, minimum possible value: 20
+-  **retry\_timeout**: timeout for DCS and PostgreSQL operation retries (in seconds). DCS or network issues shorter than this will not cause Patroni to demote the leader. Default value: 10, minimum possible value: 3
+
+.. warning::
+    when changing values of **loop_wait**, **retry_timeout**, or **ttl** you have to follow the rule:
+
+    .. code-block:: python
+
+        loop_wait + 2 * retry_timeout <= ttl
+
 
--  **loop\_wait**: the number of seconds the loop will sleep. Default value: 10
--  **ttl**: the TTL to acquire the leader lock (in seconds). Think of it as the length of time before initiation of the automatic failover process. Default value: 30
--  **retry\_timeout**: timeout for DCS and PostgreSQL operation retries (in seconds). DCS or network issues shorter than this will not cause Patroni to demote the leader. Default value: 10
 -  **maximum\_lag\_on\_failover**: the maximum bytes a follower may lag to be able to participate in leader election.
--  **maximum\_lag\_on\_syncnode**: the maximum bytes a synchronous follower may lag before it is considered as an unhealthy candidate and swapped by healthy asynchronous follower. Patroni utilize the max replica lsn if there is more than one follower, otherwise it will use leader's current wal lsn. Default is -1, Patroni will not take action to swap synchronous unhealthy follower when the value is set to 0 or below. Please set the value high enough so Patroni won't swap synchrounous follower fequently during high transaction volume.
+-  **maximum\_lag\_on\_syncnode**: the maximum bytes a synchronous follower may lag before it is considered as an unhealthy candidate and swapped by healthy asynchronous follower. Patroni utilize the max replica lsn if there is more than one follower, otherwise it will use leader's current wal lsn. Default is -1, Patroni will not take action to swap synchronous unhealthy follower when the value is set to 0 or below. Please set the value high enough so Patroni won't swap synchrounous follower frequently during high transaction volume.
 -  **max\_timelines\_history**: maximum number of timeline history items kept in DCS.  Default value: 0. When set to 0, it keeps the full history in DCS.
 -  **primary\_start\_timeout**: the amount of time a primary is allowed to recover from failures before failover is triggered (in seconds). Default is 300 seconds. When set to 0 failover is done immediately after a crash is detected if possible. When using asynchronous replication a failover can cause lost transactions. Worst case failover time for primary failure is: loop\_wait + primary\_start\_timeout + loop\_wait, unless primary\_start\_timeout is zero, in which case it's just loop\_wait. Set the value according to your durability/availability tradeoff.
 -  **primary\_stop\_timeout**: The number of seconds Patroni is allowed to wait when stopping Postgres and effective only when synchronous_mode is enabled. When set to > 0 and the synchronous_mode is enabled, Patroni sends SIGKILL to the postmaster if the stop operation is running for more than the value set by primary\_stop\_timeout. Set the value according to your durability/availability tradeoff. If the parameter is not set or set <= 0, primary\_stop\_timeout does not apply.
--  **synchronous\_mode**: turns on synchronous replication mode. In this mode a replica will be chosen as synchronous and only the latest leader and synchronous replica are able to participate in leader election. Synchronous mode makes sure that successfully committed transactions will not be lost at failover, at the cost of losing availability for writes when Patroni cannot ensure transaction durability. See :ref:`replication modes documentation <replication_modes>` for details.
+-  **synchronous\_mode**: turns on synchronous replication mode. Possible values: ``off``, ``on``, ``quorum``. In this mode the leader takes care of management of ``synchronous_standby_names``, and only the last known leader, or one of synchronous replicas, are allowed to participate in leader race. Synchronous mode makes sure that successfully committed transactions will not be lost at failover, at the cost of losing availability for writes when Patroni cannot ensure transaction durability. See :ref:`replication modes documentation <replication_modes>` for details.
 -  **synchronous\_mode\_strict**: prevents disabling synchronous replication if no synchronous replicas are available, blocking all client writes to the primary. See :ref:`replication modes documentation <replication_modes>` for details.
+-  **synchronous\_node\_count**: if ``synchronous_mode`` is enabled, this parameter is used by Patroni to manage the precise number of synchronous standby instances and adjusts the state in DCS and the ``synchronous_standby_names`` parameter in PostgreSQL as members join and leave. If the parameter is set to a value higher than the number of eligible nodes, it will be automatically adjusted. Defaults to ``1``.
 -  **failsafe\_mode**: Enables :ref:`DCS Failsafe Mode <dcs_failsafe_mode>`. Defaults to `false`.
 -  **postgresql**:
 
-   -  **use\_pg\_rewind**: whether or not to use pg_rewind. Defaults to `false`.
+   -  **use\_pg\_rewind**: whether or not to use pg_rewind. Defaults to `false`. Note that either the cluster must be initialized with ``data page checksums`` (``--data-checksums`` option for ``initdb``) and/or ``wal_log_hints`` must be set to ``on``, or ``pg_rewind`` will not work.
    -  **use\_slots**: whether or not to use replication slots. Defaults to `true` on PostgreSQL 9.4+.
    -  **recovery\_conf**: additional configuration settings written to recovery.conf when configuring follower. There is no recovery.conf anymore in PostgreSQL 12, but you may continue using this section, because Patroni handles it transparently.
-   -  **parameters**: list of configuration settings for Postgres.
+   -  **parameters**: configuration parameters (GUCs) for Postgres in format ``{max_connections: 100, wal_level: "replica", max_wal_senders: 10, wal_log_hints: "on"}``. Many of these are required for replication to work.
 
    -  **pg\_hba**: list of lines that Patroni will use to generate ``pg_hba.conf``. Patroni ignores this parameter if ``hba_file`` PostgreSQL parameter is set to a non-default value.
 
@@ -46,13 +56,15 @@ In order to change the dynamic configuration you can use either ``patronictl edi
    -  **archive\_cleanup\_command**: cleanup command for standby leader
    -  **recovery\_min\_apply\_delay**: how long to wait before actually apply WAL records on a standby leader
 
--  **slots**: define permanent replication slots. These slots will be preserved during switchover/failover. Permanent slots that don't exist will be created by Patroni. The physical slots are maintained only in the current primary. The logical slots are copied from the primary to a standby with restart, and after that their position advanced every **loop_wait** seconds (if necessary). Copying logical slot files performed via ``libpq`` connection and using either rewind or superuser credentials (see **postgresql.authentication** section). There is always a chance that the logical slot position on the replica is a bit behind the former primary, therefore application should be prepared that some messages could be received the second time after the failover. The easiest way of doing so - tracking ``confirmed_flush_lsn``. Enabling permanent logical replication slots requires **postgresql.use_slots** to be set and will also automatically enable the ``hot_standby_feedback``. Since the failover of logical replication slots is unsafe on PostgreSQL 9.6 and older and PostgreSQL version 10 is missing some important functions, the feature only works with PostgreSQL 11+.
+-  **member_slots_ttl**: retention time of physical replication slots for replicas when they are shut down. Default value: `30min`. Set it to `0` if you want to keep the old behavior (when the member key expires from DCS, the slot is immediately removed). The feature works only starting from PostgreSQL 11.
+-  **slots**: define permanent replication slots. These slots will be preserved during switchover/failover. Permanent slots that don't exist will be created by Patroni. With PostgreSQL 11 onwards permanent physical slots are created on all nodes and their position is advanced every **loop_wait** seconds. For PostgreSQL versions older than 11 permanent physical replication slots are maintained only on the current primary. The logical slots are copied from the primary to a standby with restart, and after that their position advanced every **loop_wait** seconds (if necessary). Copying logical slot files performed via ``libpq`` connection and using either rewind or superuser credentials (see **postgresql.authentication** section). There is always a chance that the logical slot position on the replica is a bit behind the former primary, therefore application should be prepared that some messages could be received the second time after the failover. The easiest way of doing so - tracking ``confirmed_flush_lsn``. Enabling permanent replication slots requires **postgresql.use_slots** to be set to ``true``. If there are permanent logical replication slots defined Patroni will automatically enable the ``hot_standby_feedback``. Since the failover of logical replication slots is unsafe on PostgreSQL 9.6 and older and PostgreSQL version 10 is missing some important functions, the feature only works with PostgreSQL 11+.
 
-   -  **my\_slot\_name**: the name of the permanent replication slot. If the permanent slot name matches with the name of the current leader it will not be created. Please note that Patroni does not make checks for permanent slot names added to this configuration matching those that Patroni creates automatically for members. If those names are added, Patroni will ensure that any slots that were created are not removed even if the member becomes unresponsive, situation which would normally result in the slot's removal by Patroni. Although this can be useful in some situations, such as when importing existing members to a new Patroni cluster (see :ref:`Convert a Standalone to a Patroni Cluster <existing_data>` for details), caution should be exercised by the operator that these clashes in names are not persisted in the DCS due to its effect on normal functioning of Patroni.
+   -  **my\_slot\_name**: the name of the permanent replication slot. If the permanent slot name matches with the name of the current node it will not be created on this node. If you add a permanent physical replication slot which name matches the name of a Patroni member, Patroni will ensure that the slot that was created is not removed even if the corresponding member becomes unresponsive, situation which would normally result in the slot's removal by Patroni. Although this can be useful in some situations, such as when you want replication slots used by members to persist during temporary failures or when importing existing members to a new Patroni cluster (see :ref:`Convert a Standalone to a Patroni Cluster <existing_data>` for details), caution should be exercised by the operator that these clashes in names are not persisted in the DCS, when the slot is no longer required, due to its effect on normal functioning of Patroni.
 
-      -  **type**: slot type. Could be ``physical`` or ``logical``. If the slot is logical, you have to additionally define ``database`` and ``plugin``.
+      -  **type**: slot type. Could be ``physical`` or ``logical``. If the slot is logical, you have to additionally define ``database`` and ``plugin``. If the slot is physical, you can optionally define ``cluster_type``.
       -  **database**: the database name where logical slots should be created.
       -  **plugin**: the plugin name for the logical slot.
+      -  **cluster_type**: the type of cluster (``primary`` or ``standby``) the slot should only be created on, otherwise it will not be created or an already existing slot will be dropped.
 
 -  **ignore\_slots**: list of sets of replication slot properties for which Patroni should ignore matching slots. This configuration/feature/etc. is useful when some replication slots are managed outside of Patroni. Any subset of matching properties will cause a slot to be ignored.
 
@@ -80,4 +92,26 @@ Note: **slots** is a hashmap while **ignore_slots** is an array. For example:
             plugin: test_decoding
           - name: ignored_physical_slot_name
             type: physical
-          ...
+          ...
+
+Note: When running PostgreSQL v11 or newer Patroni maintains physical replication slots on all nodes that could potentially become a leader, so that replica nodes keep WAL segments reserved if they are potentially required by other nodes. In case the node is absent and its member key in DCS gets expired, the corresponding replication slot is dropped after ``member_slots_ttl`` (default value is `30min`). You can increase or decrease retention based on your needs. Alternatively, if your cluster topology is static (fixed number of nodes that never change their names) you can configure permanent physical replication slots with names corresponding to the names of the nodes to avoid slots removal and recycling of WAL files while replica is temporarily down:
+
+.. code:: YAML
+
+        slots:
+          node_name1:
+            type: physical
+          node_name2:
+            type: physical
+          node_name3:
+            type: physical
+          ...
+
+
+.. warning::
+   Permanent replication slots are synchronized only from the ``primary``/``standby_leader`` to replica nodes. That means, applications are supposed to be using them only from the leader node. Using them on replica nodes will cause indefinite growth of ``pg_wal`` on all other nodes in the cluster.
+   An exception to that rule are physical slots that match the Patroni member names (created and maintained by Patroni). Those will be synchronized among all nodes as they are used for replication among them.
+
+
+.. warning::
+   Setting ``nostream`` tag on standby disables copying and synchronization of permanent logical replication slots on the node itself and all its cascading replicas if any.

docs/existing_data.rst

@@ -36,18 +36,18 @@ You can find below an overview of steps for converting an existing Postgres clus
 
    #. If you are running Postgres through systemd, then disable the Postgres systemd unit. This is performed as Patroni manages starting and stopping the Postgres daemon.
 
-   #. Create a YAML configuration file for Patroni.
+   #. Create a YAML configuration file for Patroni. You can use :ref:`Patroni configuration generation and validation tooling <validate_generate_config>` for that.
 
       * **Note (specific for the primary node):** If you have replication slots being used for replication between cluster members, then it is recommended that you enable ``use_slots`` and configure the existing replication slots as permanent via the ``slots`` configuration item. Be aware that Patroni automatically creates replication slots for replication between members, and drops replication slots that it does not recognize, when ``use_slots`` is enabled. The idea of using permanent slots here is to allow your existing slots to persist while the migration to Patroni is in progress. See :ref:`YAML Configuration Settings <yaml_configuration>` for details.
 
    #. Start Patroni using the ``patroni`` systemd service unit. It automatically detects that Postgres is already running and starts monitoring the instance.
 
-#. Hand over Postgres "start up procedure" to Patroni. In order to do that you need to restart the cluster members through ``patronictl restart cluster-name member-name`` command. For minimal downtime you might want to split this step into:
+#. Hand over Postgres "start up procedure" to Patroni. In order to do that you need to restart the cluster members through :ref:`patronictl restart cluster-name member-name <patronictl_restart_parameters>` command. For minimal downtime you might want to split this step into:
 
    #. Immediate restart of the standby nodes.
    #. Scheduled restart of the primary node within a maintenance window.
 
-#. If you configured permanent slots in step ``1.2.``, then you should remove them from ``slots`` configuration through ``patronictl edit-config cluster-name member-name`` command once the ``restart_lsn`` of the slots created by Patroni is able to catch up with the ``restart_lsn`` of the original slots for the corresponding members. By removing the slots from ``slots`` configuration you will allow Patroni to drop the original slots from your cluster once they are not needed anymore. You can find below an example query to check the ``restart_lsn`` of a couple slots, so you can compare them:
+#. If you configured permanent slots in step ``1.2.``, then you should remove them from ``slots`` configuration through :ref:`patronictl edit-config cluster-name member-name <patronictl_edit_config_parameters>` command once the ``restart_lsn`` of the slots created by Patroni is able to catch up with the ``restart_lsn`` of the original slots for the corresponding members. By removing the slots from ``slots`` configuration you will allow Patroni to drop the original slots from your cluster once they are not needed anymore. You can find below an example query to check the ``restart_lsn`` of a couple slots, so you can compare them:
 
    .. code-block:: sql
 
@@ -73,7 +73,7 @@ The only possible way to do a major upgrade currently is:
 #. Stop Patroni
 #. Upgrade PostgreSQL binaries and perform `pg_upgrade <https://www.postgresql.org/docs/current/pgupgrade.html>`_ on the primary node
 #. Update patroni.yml
-#. Remove the initialize key from DCS or wipe complete cluster state from DCS. The second one could be achieved by running ``patronictl remove <cluster-name>``. It is necessary because pg_upgrade runs initdb which actually creates a new database with a new PostgreSQL system identifier.
+#. Remove the initialize key from DCS or wipe complete cluster state from DCS. The second one could be achieved by running :ref:`patronictl remove cluster-name <patronictl_remove_parameters>` . It is necessary because pg_upgrade runs initdb which actually creates a new database with a new PostgreSQL system identifier.
 #. If you wiped the cluster state in the previous step, you may wish to copy patroni.dynamic.json from old data dir to the new one.  It will help you to retain some PostgreSQL parameters you had set before.
 #. Start Patroni on the primary node.
 #. Upgrade PostgreSQL binaries, update patroni.yml and wipe the data_dir on standby nodes.

docs/faq.rst

@@ -0,0 +1,332 @@
+.. _faq:
+
+FAQ
+===
+
+In this section you will find answers for the most frequently asked questions about Patroni.
+Each sub-section attempts to focus on different kinds of questions.
+
+We hope that this helps you to clarify most of your questions.
+If you still have further concerns or find yourself facing an unexpected issue, please refer to :ref:`chatting` and :ref:`reporting_bugs` for instructions on how to get help or report issues.
+
+Comparison with other HA solutions
+----------------------------------
+
+Why does Patroni require a separate cluster of DCS nodes while other solutions like ``repmgr`` do not?
+    There are different ways of implementing HA solutions, each of them with their pros and cons.
+
+    Software like ``repmgr`` performs communication among the nodes to decide when actions should be taken.
+
+    Patroni on the other hand relies on the state stored in the DCS. The DCS acts as a source of truth for Patroni to decide what it should do.
+
+    While having a separate DCS cluster can make you bloat your architecture, this approach also makes it less likely for split-brain scenarios to happen in your Postgres cluster.
+
+What is the difference between Patroni and other HA solutions in regards to Postgres management?
+    Patroni does not just manage the high availability of the Postgres cluster but also manages Postgres itself.
+
+    If Postgres nodes do not exist yet, it takes care of bootstrapping the primary and the standby nodes, and also manages Postgres configuration of the nodes. If the Postgres nodes already exist, Patroni will take over management of the cluster.
+
+    Besides the above, Patroni also has self-healing capabilities. In other words, if a primary node fails, Patroni will not only fail over to a replica, but also attempt to rejoin the former primary as a replica of the new primary. Similarly, if a replica fails, Patroni will attempt to rejoin that replica.
+
+    That is way we call Patroni as a "template for HA solutions". It goes further than just managing physical replication: it manages Postgres as a whole.
+
+DCS
+---
+
+Can I use the same ``etcd`` cluster to store data from two or more Patroni clusters?
+    Yes, you can!
+
+    Information about a Patroni cluster is stored in the DCS under a path prefixed with the ``namespace`` and ``scope`` Patroni settings.
+
+    As long as you do not have conflicting namespace and scope across different Patroni clusters, you should be able to use the same DCS cluster to store information from multiple Patroni clusters.
+
+What occurs if I attempt to use the same combination of ``namespace`` and ``scope`` for different Patroni clusters that point to the same DCS cluster?
+    The second Patroni cluster that attempts to use the same ``namespace`` and ``scope`` will not be able to manage Postgres because it will find information related with that same combination in the DCS, but with an incompatible Postgres system identifier.
+    The mismatch on the system identifier causes Patroni to abort the management of the second cluster, as it assumes that refers to a different cluster and that the user has misconfigured Patroni.
+
+    Make sure to use different ``namespace`` / ``scope`` when dealing with different Patroni clusters that share the same DCS cluster.
+
+What occurs if I lose my DCS cluster?
+    The DCS is used to store basically status and the dynamic configuration of the Patroni cluster.
+
+    They very first consequence is that all the Patroni clusters that rely on that DCS will go to read-only mode -- unless :ref:`dcs_failsafe_mode` is enabled.
+
+What should I do if I lose my DCS cluster?
+    There are three possible outcomes upon losing your DCS cluster:
+
+    1. The DCS cluster is fully recovered: this requires no action from the Patroni side. Once the DCS cluster is recovered, Patroni should be able to recover too;
+    2. The DCS cluster is re-created in place, and the endpoints remain the same. No changes are required on the Patroni side;
+    3. A new DCS cluster is created with different endpoints. You will need to update the DCS endpoints in the Patroni configuration of each Patroni node.
+
+    If you face scenario ``2.`` or ``3.`` Patroni will take care of creating the status information again based on the current status of the cluster, and recreate the dynamic configuration on the DCS based on a backup file named ``patroni.dynamic.json`` which is stored inside the Postgres data directory of each member of the Patroni cluster.
+
+What occurs if I lose majority in my DCS cluster?
+    The DCS will become unresponsive, which will cause Patroni to demote the current read/write Postgres node.
+
+    Remember: Patroni relies on the state of the DCS to take actions on the cluster.
+
+    You can use the :ref:`dcs_failsafe_mode` to alleviate that situation.
+
+patronictl
+----------
+
+Do I need to run :ref:`patronictl` in the Patroni host?
+    No, you do not need to do that.
+
+    Running :ref:`patronictl` in the Patroni host is handy if you have access to the Patroni host because you can use the very same configuration file from the ``patroni`` agent for the :ref:`patronictl` application.
+
+    However, :ref:`patronictl` is basically a client and it can be executed from remote machines. You just need to provide it with enough configuration so it can reach the DCS and the REST API of the Patroni member(s).
+
+Why did the information from one of my Patroni members disappear from the output of :ref:`patronictl_list` command?
+    Information shown by :ref:`patronictl_list` is based on the contents of the DCS.
+
+    If information about a member disappeared from the DCS it is very likely that the Patroni agent on that node is not running anymore, or it is not able to communicate with the DCS.
+
+    As the member is not able to update the information, the information eventually expires from the DCS, and consequently the member is not shown anymore in the output of :ref:`patronictl_list`.
+
+Why is the information about one of my Patroni members not up-to-date in the output of :ref:`patronictl_list` command?
+    Information shown by :ref:`patronictl_list` is based on the contents of the DCS.
+
+    By default, that information is updated by Patroni roughly every ``loop_wait`` seconds.
+    In other words, even if everything is normally functional you may still see a "delay" of up to ``loop_wait`` seconds in the information stored in the DCS.
+
+    Be aware that that is not a rule, though. Some operations performed by Patroni cause it to immediately update the DCS information.
+
+Configuration
+-------------
+
+What is the difference between dynamic configuration and local configuration?
+    Dynamic configuration (or global configuration) is the configuration stored in the DCS, and which is applied to all members of the Patroni cluster.
+    This is primarily where you should store your configuration.
+
+    Settings that are specific to a node, or settings that you would like to overwrite the global configuration with, you should set only on the desired Patroni member as a local configuration.
+    That local configuration can be specified either through the configuration file or through environment variables.
+
+    See more in :ref:`patroni_configuration`.
+
+What are the types of configuration in Patroni, and what is the precedence?
+    The types are:
+
+    * Dynamic configuration: applied to all members;
+    * Local configuration: applied to the local member, overrides dynamic configuration;
+    * Environment configuration: applied to the local member, overrides both dynamic and local configuration.
+
+    **Note:** some Postgres GUCs can only be set globally, i.e., through dynamic configuration. Besides that, there are GUCs which Patroni enforces a hard-coded value.
+
+    See more in :ref:`patroni_configuration`.
+
+Is there any facility to help me create my Patroni configuration file?
+    Yes, there is.
+
+    You can use ``patroni --generate-sample-config`` or ``patroni --generate-config`` commands to generate a sample Patroni configuration or a Patroni configuration based on an existing Postgres instance, respectively.
+
+    Please refer to :ref:`generate_sample_config` and :ref:`generate_config` for more details.
+
+I changed my parameters under ``bootstrap.dcs`` configuration but Patroni is not applying the changes to the cluster members. What is wrong?
+    The values configured under ``bootstrap.dcs`` are only used when bootstrapping a fresh cluster. Those values will be written to the DCS during the bootstrap.
+
+    After the bootstrap phase finishes, you will only be able to change the dynamic configuration through the DCS.
+
+    Refer to the next question for more details.
+
+How can I change my dynamic configuration?
+    You need to change the configuration in the DCS. That is accomplished either through:
+
+    * :ref:`patronictl_edit_config`; or
+    * A ``PATCH`` request to :ref:`config_endpoint`.
+
+How can I change my local configuration?
+    You need to change the configuration file of the corresponding Patroni member and signal the Patroni agent with ``SIHGUP``. You can do that using either of these approaches:
+
+    * Send a ``POST`` request to the REST API :ref:`reload_endpoint`; or
+    * Run :ref:`patronictl_reload`; or
+    * Locally signal the Patroni process with ``SIGHUP``:
+
+        * If you started Patroni through systemd, you can use the command ``systemctl reload PATRONI_UNIT.service``, ``PATRONI_UNIT`` being the name of the Patroni service; or
+        * If you started Patroni through other means, you will need to identify the ``patroni`` process and run ``kill -s HUP PID``, ``PID`` being the process ID of the ``patroni`` process.
+
+    **Note:** there are cases where a reload through the :ref:`patronictl_reload` may not work:
+
+    * Expired REST API certificates: you can mitigate that by using the ``-k`` option of the :ref:`patronictl`;
+    * Wrong credentials: for example when changing ``restapi`` or ``ctl`` credentials in the configuration file, and using that same configuration file for Patroni and :ref:`patronictl`.
+
+How can I change my environment configuration?
+    The environment configuration is only read by Patroni during startup.
+
+    With that in mind, if you change the environment configuration you will need to restart the corresponding Patroni agent.
+
+    Take care to not cause a failover in the cluster! You might be interested in checking :ref:`patronictl_pause`.
+
+What occurs if I change a Postgres GUC that requires a reload?
+    When you change the dynamic or the local configuration as explained in the previous questions, Patroni will take care of reloading the Postgres configuration for you.
+
+What occurs if I change a Postgres GUC that requires a restart?
+    Patroni will mark the affected members with a flag of ``pending restart``.
+
+    It is up to you to determine when and how to restart the members. That can be accomplished either through:
+
+    * :ref:`patronictl_restart`; or
+    * A ``POST`` request to :ref:`restart_endpoint`.
+
+    **Note:** some Postgres GUCs require a special management in terms of the order for restarting the Postgres nodes. Refer to :ref:`shared_memory_gucs` for more details.
+
+What is the difference between ``etcd`` and ``etcd3`` in Patroni configuration?
+    ``etcd`` uses the API version 2 of ``etcd``, while ``etcd3`` uses the API version 3 of ``etcd``.
+
+    Be aware that information stored by the API version 2 is not manageable by API version 3 and vice-versa.
+
+    We recommend that you configure ``etcd3`` instead of ``etcd`` because:
+
+    * API version 2 is disabled by default from Etcd v3.4 onward;
+    * API version 2 will be completely removed on Etcd v3.6.
+
+I have ``use_slots`` enabled in my Patroni configuration, but when a cluster member goes offline for some time, the replication slot used by that member is dropped on the upstream node. What can I do to avoid that issue?
+    There are two options:
+
+    1. You can tune ``member_slots_ttl`` (default value ``30min``, available since Patroni ``4.0.0`` and PostgreSQL 11 onwards) and replication slots for absent members will not be removed when the members downtime is shorter than the configured threshold.
+    2. You can configure permanent physical replication slots for the members.
+
+    Since Patroni ``3.2.0`` it is now possible to have member slots as permanent slots managed by Patroni.
+
+    Patroni will create the permanent physical slots on all nodes, and make sure to not remove the slots, as well as to advance the slots' LSN on all nodes according to the LSN that has been consumed by the member.
+
+    Later, if you decide to remove the corresponding member, it's **your responsibility** to adjust the permanent slots configuration, otherwise Patroni will keep the slots around forever.
+
+    **Note:** on Patroni older than ``3.2.0`` you could still have member slots configured as permanent physical slots, however they would be managed only on the current leader. That is, in case of failover/switchover these slots would be created on the new leader, but that wouldn't guarantee that it had all WAL segments for the absent node.
+
+    **Note:** even with Patroni ``3.2.0`` there might be a small race condition. In the very beginning, when the slot is created on the replica it could be ahead of the same slot on the leader and in case if nobody is consuming the slot there is still a chance that some files could be missing after failover. With that in mind, it is recommended that you configure continuous archiving, which makes it possible to restore required WALs or perform PITR.
+
+What is the difference between ``loop_wait``, ``retry_timeout`` and ``ttl``?
+    Patroni performs what we call a HA cycle from time to time. On each HA cycle it takes care of performing a series of checks on the cluster to determine its healthiness, and depending on the status it may take actions, like failing over to a standby.
+
+    ``loop_wait`` determines for how long, in seconds, Patroni should sleep before performing a new cycle of HA checks.
+
+    ``retry_timeout`` sets the timeout for retry operations on the DCS and on Postgres. For example: if the DCS is unresponsive for more than ``retry_timeout`` seconds, Patroni might demote the primary node as a security action.
+
+    ``ttl`` sets the lease time on the ``leader`` lock in the DCS. If the current leader of the cluster is not able to renew the lease during its HA cycles for longer than ``ttl``, then the lease will expire and that will trigger a ``leader race`` in the cluster.
+
+    **Note:** when modifying these settings, please keep in mind that Patroni enforces the rule and minimal values described in :ref:`dynamic_configuration` section of the docs.
+
+Postgres management
+-------------------
+
+Can I change Postgres GUCs directly in Postgres configuration?
+    You can, but you should avoid that.
+
+    Postgres configuration is managed by Patroni, and attempts to edit the configuration files may end up being frustrated by Patroni as it may eventually overwrite them.
+
+    There are a few options available to overcome the management performed by Patroni:
+
+    * Change Postgres GUCs through ``$PGDATA/postgresql.base.conf``; or
+    * Define a ``postgresql.custom_conf`` which will be used instead of ``postgresql.base.conf`` so you can manage that externally; or
+    * Change GUCs using ``ALTER SYSTEM`` / ``ALTER DATABASE`` / ``ALTER USER``.
+
+    You can find more information about that in the section :ref:`important_configuration_rules`.
+
+    In any case we recommend that you manage all the Postgres configuration through Patroni. That will centralize the management and make it easier to debug Patroni when needed.
+
+Can I restart Postgres nodes directly?
+    No, you should **not** attempt to manage Postgres directly!
+
+    Any attempt of bouncing the Postgres server without Patroni can lead your cluster to face failovers.
+
+    If you need to manage the Postgres server, do that through the ways exposed by Patroni.
+
+Is Patroni able to take over management of an already existing Postgres cluster?
+    Yes, it can!
+
+    Please refer to :ref:`existing_data` for detailed instructions.
+
+How does Patroni manage Postgres?
+    Patroni takes care of bringing Postgres up and down by running the Postgres binaries, like ``pg_ctl`` and ``postgres``.
+
+    With that in mind you **MUST** disable any other sources that could manage the Postgres clusters, like the systemd units, e.g. ``postgresql.service``. Only Patroni should be able to start, stop and promote Postgres instances in the cluster. Not doing so may result in split-brain scenarios. For example: if the node running as a primary failed and the unit ``postgresql.service`` is enabled, it may bring Postgres back up and cause a split-brain.
+
+Concepts and requirements
+-------------------------
+
+Which are the applications that make part of Patroni?
+    Patroni basically ships a couple applications:
+
+    * ``patroni``: This is the Patroni agent, which takes care of managing a Postgres node;
+    * ``patronictl``: This is a command-line utility used to interact with a Patroni cluster (perform switchovers, restarts, changes in the configuration, etc.). Please find more information in :ref:`patronictl`.
+
+What is a ``standby cluster`` in Patroni?
+    It is a cluster that does not have any primary Postgres node running, i.e., there is no read/write member in the cluster.
+
+    These kinds of clusters exist to replicate data from another cluster and are usually useful when you want to replicate data across data centers.
+
+    There will be a leader in the cluster which will be a standby in charge of replicating changes from a remote Postgres node.
+    Then, there will be a set of standbys configured with cascading replication from such leader member.
+
+    **Note:** the standby cluster doesn't know anything about the source cluster which it is replicating from -- it can even use ``restore_command`` instead of WAL streaming, and may use an absolutely independent DCS cluster.
+
+    Refer to :ref:`standby_cluster` for more details.
+
+What is a ``leader`` in Patroni?
+    A ``leader`` in Patroni is like a coordinator of the cluster.
+
+    In a regular Patroni cluster, the ``leader`` will be the read/write node.
+
+    In a standby Patroni cluster, the ``leader`` (AKA ``standby leader``) will be in charge of replicating from a remote Postgres node, and cascading those changes to the other members of the standby cluster.
+
+Does Patroni require a minimum number of Postgres nodes in the cluster?
+    No, you can run Patroni with any number of Postgres nodes.
+
+    Remember: Patroni is decoupled from the DCS.
+
+What does ``pause`` mean in Patroni?
+    Pause is an operation exposed by Patroni so the user can ask Patroni to step back in regards to Postgres management.
+
+    That is mainly useful when you want to perform maintenance on the cluster, and would like to avoid that Patroni takes decisions related with HA, like failing over to a standby when you stop the primary.
+
+    You can find more information about that in :ref:`pause`.
+
+Automatic failover
+------------------
+
+How does the automatic failover mechanism of Patroni work?
+    Patroni automatic failover is based on what we call ``leader race``.
+
+    Patroni stores the cluster's status in the DCS, among them a ``leader`` lock which holds the name of the Patroni member which is the current ``leader`` of the cluster.
+
+    That ``leader`` lock has a time-to-live associated with it. If the leader node fails to update the lease of the ``leader`` lock in time, the key will eventually expire from the DCS.
+
+    When the ``leader`` lock expires, it triggers what Patroni calls a ``leader race``: all nodes start performing checks to determine if they are the best candidates for taking over the ``leader`` role.
+    Some of these checks include calls to the REST API of all other Patroni members.
+
+    All Patroni members that find themselves as the best candidate for taking over the ``leader`` lock will attempt to do so.
+    The first Patroni member that is able to take the ``leader`` lock will promote itself to a read/write node (or ``standby leader``), and the others will be configured to follow it.
+
+Can I temporarily disable automatic failover in the Patroni cluster?
+    Yes, you can!
+
+    You can achieve that by temporarily pausing the cluster.
+    This is typically useful for performing maintenance.
+
+    When you want to resume the automatic failover of the cluster, you just need to unpause it.
+
+    You can find more information about that in :ref:`pause`.
+
+Bootstrapping and standbys creation
+-----------------------------------
+
+How does Patroni create a primary Postgres node? What about a standby Postgres node?
+    By default Patroni will use ``initdb`` to bootstrap a fresh cluster, and ``pg_basebackup`` to create standby nodes from a copy of the ``leader`` member.
+
+    You can customize that behavior by writing your custom bootstrap methods, and your custom replica creation methods.
+
+    Custom methods are usually useful when you want to restore backups created by backup tools like pgBackRest or Barman, for example.
+
+    For detailed information please refer to :ref:`custom_bootstrap` and :ref:`custom_replica_creation`.
+
+Monitoring
+----------
+
+How can I monitor my Patroni cluster?
+    Patroni exposes a couple handy endpoints in its :ref:`rest_api`:
+
+    * ``/metrics``: exposes monitoring metrics in a format that can be consumed by Prometheus;
+    * ``/patroni``: exposes the status of the cluster in a JSON format. The information shown here is very similar to what is shown by the ``/metrics`` endpoint.
+
+    You can use those endpoints to implement monitoring checks.

docs/ha_loop_diagram.dot

@@ -109,7 +109,7 @@ digraph G {
   subgraph cluster_process_healthy_cluster {
     label = "process_healthy_cluster"
     "healthy_has_lock" [label="Am I the owner of the leader lock?", shape=diamond]
-    "healthy_is_leader" [label="Is Postgres running as master?", shape=diamond]
+    "healthy_is_leader" [label="Is Postgres running as primary?", shape=diamond]
     "healthy_no_lock" [label="Follow the leader (async,\ncreate/update recovery.conf and restart if necessary)"]
     "healthy_has_lock" -> "healthy_no_lock" [label="no" color="red"]
     "healthy_has_lock" -> "healthy_update_leader_lock" [label="yes" color="green"]
@@ -119,7 +119,7 @@ digraph G {
     "healthy_update_success" -> "healthy_is_leader" [label="yes" color="green"]
     "healthy_update_success" -> "healthy_demote" [label="no" color="red"]
     "healthy_demote" [label="Demote (async,\nrestart in read-only)"]
-    "healthy_failover" [label="Promote Postgres to master"]
+    "healthy_failover" [label="Promote Postgres to primary"]
     "healthy_is_leader" -> "healthy_failover" [label="no" color="red"]
   }
   "healthy_demote" -> "update_member"
@@ -134,10 +134,10 @@ digraph G {
     "unhealthy_leader_race" [label="Try to create leader key"]
     "unhealthy_leader_race" -> "unhealthy_acquire_lock"
     "unhealthy_acquire_lock" [label="Was I able to get the lock?", shape="diamond"]
-    "unhealthy_is_leader" [label="Is Postgres running as master?", shape=diamond]
+    "unhealthy_is_leader" [label="Is Postgres running as primary?", shape=diamond]
     "unhealthy_acquire_lock" -> "unhealthy_is_leader" [label="yes" color="green"]
     "unhealthy_is_leader" -> "unhealthy_promote" [label="no" color="red"]
-    "unhealthy_promote" [label="Promote to master"]
+    "unhealthy_promote" [label="Promote to primary"]
     "unhealthy_is_healthiest" -> "unhealthy_follow" [label="no" color="red"]
     "unhealthy_follow" [label="try to follow somebody else()"]
     "unhealthy_acquire_lock" -> "unhealthy_follow" [label="no" color="red"]

docs/ha_multi_dc.rst

@@ -44,7 +44,7 @@ You should not use ``pg_ctl promote`` in this scenario, you need "manually promo
 
 In case you want to return to the "initial" state, there are only two ways of resolving it:
 
-- Add the standby_cluster section back and it will trigger pg_rewind, but there are chances that pg_rewind will fail.
+- Add the standby_cluster section back and it will trigger ``pg_rewind``; however, for ``pg_rewind`` to function properly, either the cluster must be initialized with ``data page checksums`` (``--data-checksums`` option for ``initdb``) and/or ``wal_log_hints`` must be set to ``on``, but there are still chances that ``pg_rewind`` might fail due to other factors.
 - Rebuild the standby cluster from scratch.
 
 Before promoting standby cluster one have to manually ensure that the source cluster is down (STONITH). When DC1 recovers, the cluster has to be converted to a standby cluster.

docs/index.rst

@@ -10,7 +10,7 @@ Patroni is a template for high availability (HA) PostgreSQL solutions using Pyth
 
 We call Patroni a "template" because it is far from being a one-size-fits-all or plug-and-play replication system. It will have its own caveats. Use wisely. There are many ways to run high availability with PostgreSQL; for a list, see the `PostgreSQL Documentation <https://wiki.postgresql.org/wiki/Replication,_Clustering,_and_Connection_Pooling>`__.
 
-Currently supported PostgreSQL versions: 9.3 to 15.
+Currently supported PostgreSQL versions: 9.3 to 17.
 
 **Note to Citus users**: Starting from 3.0 Patroni nicely integrates with the `Citus <https://github.com/citusdata/citus>`__ database extension to Postgres. Please check the :ref:`Citus support page <citus>` in the Patroni documentation for more info about how to use Patroni high availability together with a Citus distributed cluster.
 
@@ -22,18 +22,23 @@ Currently supported PostgreSQL versions: 9.3 to 15.
    :caption: Contents:
 
    README
+   installation
    patroni_configuration
    rest_api
+   patronictl
    replica_bootstrap
    replication_modes
+   standby_cluster
    watchdog
    pause
    dcs_failsafe_mode
    kubernetes
    citus
    existing_data
+   tools_integration
    security
    ha_multi_dc
+   faq
    releases
    CONTRIBUTING
 

docs/installation.rst

@@ -0,0 +1,200 @@
+.. _installation:
+
+Installation
+============
+
+Pre-requirements for Mac OS
+---------------------------
+
+To install requirements on a Mac, run the following:
+
+.. code-block:: shell
+
+    brew install postgresql etcd haproxy libyaml python
+
+.. _psycopg2_install_options:
+
+Psycopg
+-------
+
+Starting from `psycopg2-2.8`_ the binary version of psycopg2 will no longer be installed by default. Installing it from
+the source code requires C compiler and postgres+python dev packages. Since in the python world it is not possible to
+specify dependency as ``psycopg2 OR psycopg2-binary`` you will have to decide how to install it.
+
+There are a few options available:
+
+1. Use the package manager from your distro
+
+.. code-block:: shell
+
+    sudo apt-get install python3-psycopg2  # install psycopg2 module on Debian/Ubuntu
+    sudo yum install python3-psycopg2      # install psycopg2 on RedHat/Fedora/CentOS
+
+2. Specify one of `psycopg`, `psycopg2`, or `psycopg2-binary` in the :ref:`list of dependencies <extras>` when installing Patroni with pip.
+
+
+.. _extras:
+
+General installation for pip
+----------------------------
+
+Patroni can be installed with pip:
+
+.. code-block:: shell
+
+    pip install patroni[dependencies]
+
+where ``dependencies`` can be either empty, or consist of one or more of the following:
+
+etcd or etcd3
+    `python-etcd` module in order to use Etcd as Distributed Configuration Store (DCS)
+consul
+    `py-consul` module in order to use Consul as DCS
+zookeeper
+    `kazoo` module in order to use Zookeeper as DCS
+exhibitor
+    `kazoo` module in order to use Exhibitor as DCS (same dependencies as for Zookeeper)
+kubernetes
+    `kubernetes` module in order to use Kubernetes as DCS in Patroni
+raft
+    `pysyncobj` module in order to use python Raft implementation as DCS
+aws
+    `boto3` in order to use AWS callbacks
+jsonlogger
+    `python-json-logger` module in order to enable :ref:`logging <log_settings>` in json format
+systemd
+    `systemd-python` in order to use sd_notify integration
+all
+    all of the above (except psycopg family)
+psycopg
+    `psycopg[binary]>=3.0.0` module
+psycopg2
+    `psycopg2>=2.5.4` module
+psycopg2-binary
+    `psycopg2-binary` module
+
+For example, the command in order to install Patroni together with psycopg3, dependencies for Etcd as a DCS, and AWS callbacks is:
+
+.. code-block:: shell
+
+    pip install patroni[psycopg3,etcd3,aws]
+
+Note that external tools to call in the replica creation or custom bootstrap scripts (i.e. WAL-E) should be installed
+independently of Patroni.
+
+.. _package_installation:
+
+Package installation on Linux
+-----------------------------
+
+Patroni packages may be available for your operating system, produced by the Postgres community for:
+
+* RHEL, RockyLinux, AlmaLinux;
+* Debian and Ubuntu;
+* SUSE Enterprise Linux.
+
+You can also find packages for direct dependencies of Patroni, like python modules that might not be available in
+the official operating system repositories.
+
+For more information see the `PGDG repository`_ documentation.
+
+If you are on a RedHat Enterprise Linux derivative operating system you may also require packages from EPEL, see
+`EPEL repository`_ documentation.
+
+Once you have installed the PGDG repository for your OS you can install patroni.
+
+.. note::
+
+    Patroni packages are not maintained by the Patroni developers, but rather by the Postgres community. If you
+    require support please first try connecting on `Postgres slack`_.
+
+Installing on Debian derivatives
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+With PGDG repo installed, see :ref:`above <package_installation>`, install Patroni via apt run:
+
+.. code-block:: shell
+
+    apt-get install patroni
+
+Installing on RedHat derivatives
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+With PGDG repo installed, see :ref:`above <package_installation>`, install patroni with an etcd DCS via dnf on RHEL 9
+(and derivatives) run:
+
+.. code-block:: shell
+
+    dnf install patroni patroni-etcd
+
+You can install etcd from PGDG if your RedHat derivative distribution does not provide packages. On the nodes that will
+host the DCS run:
+
+.. code-block:: shell
+
+    dnf install 'dnf-command(config-manager)'
+    dnf config-manager --enable pgdg-rhel9-extras
+    dnf install etcd
+
+You can replace the version of RHEL with `8` in the repo to make `pgdg-rhel8-extras` if needed. The repo name is still
+`pgdg-rhelN-extras` on RockyLinux, AlmaLinux, Oracle Linux, etc...
+
+Installing on SUSE Enterprise Linux
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+You might need to enable the SUSE PackageHub repositories for some dependencies. see `SUSE PackageHub`_ documentation.
+
+For SLES 15 with PGDG repo installed, see :ref:`above <package_installation>`, you can install patroni using:
+
+.. code-block:: shell
+
+    zypper install patroni patroni-etcd
+
+With the SUSE PackageHub repo enabled you can also install etcd:
+
+.. code-block:: shell
+
+    SUSEConnect -p PackageHub/15.5/x86_64
+    zypper install etcd
+
+Upgrading
+---------
+
+Upgrading patroni is a very simple process, just update the software installation and restart the Patroni daemon on
+each node in the cluster.
+
+However, restarting the Patroni daemon will result in a Postgres database restart. In some situations this may cause
+a failover of the primary node in your cluster, therefore it is recommended to put the cluster into maintenance mode
+until the Patroni daemon restart has been completed.
+
+To put the cluster in maintenance mode, run the following command on one of the patroni nodes:
+
+.. code-block:: shell
+
+    patronictl pause --wait
+
+Then on each node in the cluster, perform the package upgrade required for your OS:
+
+.. code-block:: shell
+
+    apt-get update && apt-get install patroni patroni-etcd
+
+Restart the patroni daemon process on each node:
+
+.. code-block:: shell
+
+    systemctl restart patroni
+
+Then finally resume monitoring of Postgres with patroni to take it out of maintenance mode:
+
+.. code-block:: shell
+
+    patronictl resume --wait
+
+The cluster will now be full operational with the new version of Patroni.
+
+.. _psycopg2-2.8: http://initd.org/psycopg/articles/2019/04/04/psycopg-28-released/
+.. _PGDG repository: https://www.postgresql.org/download/linux/
+.. _EPEL repository: https://docs.fedoraproject.org/en-US/epel/
+.. _SUSE PackageHub: https://packagehub.suse.com/how-to-use/
+.. _Postgres slack: http://pgtreats.info/slack-invite

docs/kubernetes.rst

@@ -37,7 +37,7 @@ Patroni Kubernetes :ref:`settings <kubernetes_settings>` and :ref:`environment v
 Customize role label
 ^^^^^^^^^^^^^^^^^^^^
 
-By default, Patroni will set corresponding labels on the pod it runs in based on node's role, such as ``role=master``.
+By default, Patroni will set corresponding labels on the pod it runs in based on node's role, such as ``role=primary``.
 The key and value of label can be customized by `kubernetes.role_label`, `kubernetes.leader_label_value`, `kubernetes.follower_label_value` and `kubernetes.standby_leader_label_value`.
 
 Note that if you migrate from default role labels to custom ones, you can reduce downtime by following migration steps:
@@ -48,8 +48,8 @@ Note that if you migrate from default role labels to custom ones, you can reduce
 
     labels:
       cluster-name: foo
-      role: master
-      tmp_role: master
+      role: primary
+      tmp_role: primary
 
 2. After all pods have been updated, modify the service selector to select the temporary label.
 
@@ -57,7 +57,7 @@ Note that if you migrate from default role labels to custom ones, you can reduce
 
     selector:
       cluster-name: foo
-      tmp_role: master
+      tmp_role: primary
 
 3. Add your custom role label (e.g., set `kubernetes.leader_label_value=primary`). Once pods are restarted they will get following new labels set by Patroni:
 
@@ -66,7 +66,7 @@ Note that if you migrate from default role labels to custom ones, you can reduce
     labels:
       cluster-name: foo
       role: primary
-      tmp_role: master
+      tmp_role: primary
 
 4. After all pods have been updated again, modify the service selector to use new role value.
 
@@ -87,7 +87,7 @@ Note that if you migrate from default role labels to custom ones, you can reduce
 Examples
 --------
 
-- The `kubernetes <https://github.com/zalando/patroni/tree/master/kubernetes>`__ folder of the Patroni repository contains
+- The `kubernetes <https://github.com/patroni/patroni/tree/master/kubernetes>`__ folder of the Patroni repository contains
   examples of the Docker image, and the Kubernetes manifest to test Patroni Kubernetes setup.
   Note that in the current state it will not be able to use PersistentVolumes because of permission issues.
 
@@ -98,5 +98,5 @@ Examples
   to deploy the Spilo image configured with Patroni running using Kubernetes.
 
 - In order to run your database clusters at scale using Patroni and Spilo, take a look at the
-  `postgres-operator <https://github.com/zalando-incubator/postgres-operator>`_ project. It implements the operator pattern
+  `postgres-operator <https://github.com/zalando/postgres-operator>`_ project. It implements the operator pattern
   to manage Spilo clusters.

docs/patroni_configuration.rst

@@ -15,7 +15,7 @@ There are 3 types of Patroni configuration:
 
 - Global :ref:`dynamic configuration <dynamic_configuration>`.
 	These options are stored in the DCS (Distributed Configuration Store) and applied on all cluster nodes.
-	Dynamic configuration can be set at any time using ``patronictl edit-config`` tool or Patroni :ref:`REST API <rest_api>`.
+	Dynamic configuration can be set at any time using :ref:`patronictl_edit_config` tool or Patroni :ref:`REST API <rest_api>`.
 	If the options changed are not part of the startup configuration, they are applied asynchronously (upon the next wake up cycle)
 	to every node, which gets subsequently reloaded.
 	If the node requires a restart to apply the configuration (for `PostgreSQL parameters <https://www.postgresql.org/docs/current/view-pg-settings.html>`__ with context postmaster, if their values
@@ -24,12 +24,13 @@ There are 3 types of Patroni configuration:
 
 - Local :ref:`configuration file <yaml_configuration>` (patroni.yml).
 	These options are defined in the configuration file and take precedence over dynamic configuration.
-	``patroni.yml`` can be changed and reloaded at runtime (without restart of Patroni) by sending SIGHUP to the Patroni process, performing ``POST /reload`` REST-API request or executing ``patronictl reload``. Local configuration can be either a single YAML file or a directory. When it is a directory, all YAML files in that directory are loaded one by one in sorted order. In case a key is defined in multiple files, the occurrence in the last file takes precedence.
+	``patroni.yml`` can be changed and reloaded at runtime (without restart of Patroni) by sending SIGHUP to the Patroni process, performing ``POST /reload`` REST-API request or executing :ref:`patronictl_reload`. Local configuration can be either a single YAML file or a directory. When it is a directory, all YAML files in that directory are loaded one by one in sorted order. In case a key is defined in multiple files, the occurrence in the last file takes precedence.
 
 - :ref:`Environment configuration <environment>`.
 	It is possible to set/override some of the "Local" configuration parameters with environment variables.
 	Environment configuration is very useful when you are running in a dynamic environment and you don't know some of the parameters in advance (for example it's not possible to know your external IP address when you are running inside ``docker``).
 
+.. _important_configuration_rules:
 
 Important rules
 ---------------
@@ -48,10 +49,11 @@ Some of the PostgreSQL parameters **must hold the same values on the primary and
 
 For the parameters below, PostgreSQL does not require equal values among the primary and all the replicas. However, considering the possibility of a replica to become the primary at any time, it doesn't really make sense to set them differently; therefore, **Patroni restricts setting their values to the** :ref:`dynamic configuration <dynamic_configuration>`.
 
-- **max_wal_senders**: 5
-- **max_replication_slots**: 5
+- **max_wal_senders**: 10
+- **max_replication_slots**: 10
 - **wal_keep_segments**: 8
 - **wal_keep_size**: 128MB
+- **wal_log_hints**: on
 
 These parameters are validated to ensure they are sane, or meet a minimum value.
 
@@ -61,24 +63,24 @@ There are some other Postgres parameters controlled by Patroni:
 - **port** - is set either from ``postgresql.listen`` or from ``PATRONI_POSTGRESQL_LISTEN`` environment variable
 - **cluster_name** - is set either from ``scope`` or from ``PATRONI_SCOPE`` environment variable
 - **hot_standby: on**
-- **wal_log_hints: on** - for Postgres 9.4 and newer.
 
-To be on the safe side parameters from the above lists are not written into ``postgresql.conf``, but passed as a list of arguments to the ``pg_ctl start`` which gives them the highest precedence, even above `ALTER SYSTEM <https://www.postgresql.org/docs/current/static/sql-altersystem.html>`__
+To be on the safe side parameters from the above lists are written into ``postgresql.conf``, and passed as a list of arguments to the ``postgres`` which gives them the highest precedence (except ``wal_keep_segments`` and ``wal_keep_size``), even above `ALTER SYSTEM <https://www.postgresql.org/docs/current/static/sql-altersystem.html>`__
 
 There also are some parameters like **postgresql.listen**, **postgresql.data_dir** that **can be set only locally**, i.e. in the Patroni :ref:`config file <yaml_configuration>` or via :ref:`configuration <environment>` variable. In most cases the local configuration will override the dynamic configuration.
 
 
 When applying the local or dynamic configuration options, the following actions are taken:
 
-- The node first checks if there is a `postgresql.base.conf` or if the ``custom_conf`` parameter is set.
-- If the ``custom_conf`` parameter is set, it will take the file specified on it as a base configuration, ignoring `postgresql.base.conf` and `postgresql.conf`.
-- If the ``custom_conf`` parameter is not set and `postgresql.base.conf` exists, it contains the renamed "original" configuration and it will be used as a base configuration.
-- If there is no ``custom_conf``` nor `postgresql.base.conf`, the original `postgresql.conf`` is taken and renamed to postgresql.base.conf.
-- The dynamic options (with the exceptions above) are dumped into the `postgresql.conf`` and an include is set in
-  postgresql.conf to the used base configuration (either `postgresql.base.conf` or what is on ``custom_conf``). Therefore, we would be able to apply new options without re-reading the configuration file to check if the include is present not.
+- The node first checks if there is a `postgresql.base.conf` file or if the ``custom_conf`` parameter is set.
+- If the ``custom_conf`` parameter is set, the file it specifies is used as the base configuration, ignoring `postgresql.base.conf` and `postgresql.conf`.
+- If the ``custom_conf`` parameter is not set and `postgresql.base.conf` exists, it contains the renamed "original" configuration and is used as the base configuration.
+- If there is no ``custom_conf`` nor `postgresql.base.conf`, the original `postgresql.conf` is renamed to `postgresql.base.conf` and used as the base configuration.
+- The dynamic options (with the exceptions above) are dumped into the `postgresql.conf` and an include is set in
+  `postgresql.conf` to the base configuration (either `postgresql.base.conf` or the file at ``custom_conf``).
+  Therefore, we would be able to apply new options without re-reading the configuration file to check if the include is present or not.
 - Some parameters that are essential for Patroni to manage the cluster are overridden using the command line.
-- If some of the options that require restart are changed (we should look at the context in pg_settings and at the actual
-  values of those options), a pending_restart flag of a given node is set. This flag is reset on any restart.
+- If an option that requires restart is changed (we should look at the context in pg_settings and at the actual
+  values of those options), a pending_restart flag is set on that node. This flag is reset on any restart.
 
 The parameters would be applied in the following order (run-time are given the highest priority):
 
@@ -89,6 +91,43 @@ The parameters would be applied in the following order (run-time are given the h
 
 This allows configuration for all the nodes (2), configuration for a specific node using ``ALTER SYSTEM`` (3) and ensures that parameters essential to the running of Patroni are enforced (4), as well as leaves room for configuration tools that manage `postgresql.conf` directly without involving Patroni (1).
 
+.. _shared_memory_gucs:
+
+PostgreSQL parameters that touch shared memory
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+PostgreSQL has some parameters that determine the size of the shared memory used by them:
+
+- **max_connections**
+- **max_prepared_transactions**
+- **max_locks_per_transaction**
+- **max_wal_senders**
+- **max_worker_processes**
+
+Changing these parameters require a PostgreSQL restart to take effect, and their shared memory structures cannot be smaller on the standby nodes than on the primary node.
+
+As explained before, Patroni restrict changing their values through :ref:`dynamic configuration <dynamic_configuration>`, which usually consists of:
+
+1. Applying changes through :ref:`patronictl_edit_config` (or via REST API ``/config`` endpoint)
+2. Restarting nodes through :ref:`patronictl_restart` (or via REST API ``/restart`` endpoint)
+
+**Note:** please keep in mind that you should perform a restart of the PostgreSQL nodes through :ref:`patronictl_restart` command, or via REST API ``/restart`` endpoint. An attempt to restart PostgreSQL by restarting the Patroni daemon, e.g. by executing ``systemctl restart patroni``, can cause a failover to occur in the cluster, if you are restarting the primary node.
+
+However, as those settings manage shared memory, some extra care should be taken when restarting the nodes:
+
+* If you want to **increase** the value of any of those settings:
+
+   1. Restart all standbys first
+   2. Restart the primary after that
+
+* If you want to **decrease** the value of any of those settings:
+
+   1. Restart the primary first
+   2. Restart all standbys after that
+
+**Note:** if you attempt to restart all nodes in one go after **decreasing** the value of any of those settings, Patroni will ignore the change and restart the standby with the original setting value, thus requiring that you restart the standbys again later. Patroni does that to prevent the standby to enter in an infinite crash loop, because PostgreSQL quits with a `FATAL` message if you attempt to set any of those parameters to a value lower than what is visible in ``pg_controldata`` on the Standby node. In other words, we can only decrease the setting on the standby once its ``pg_controldata`` is up-to-date with the primary in regards to these changes on the primary.
+
+More information about that can be found at `PostgreSQL Administrator's Overview <https://www.postgresql.org/docs/current/hot-standby.html#HOT-STANDBY-ADMIN>`__.
 
 Patroni configuration parameters
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
@@ -106,3 +145,115 @@ Also the following Patroni configuration options **can be changed only dynamical
 Upon changing these options, Patroni will read the relevant section of the configuration stored in DCS and change its run-time values.
 
 Patroni nodes are dumping the state of the DCS options to disk upon for every change of the configuration into the file ``patroni.dynamic.json`` located in the Postgres data directory. Only the leader is allowed to restore these options from the on-disk dump if these are completely absent from the DCS or if they are invalid.
+
+
+.. _validate_generate_config:
+
+Configuration generation and validation
+---------------------------------------
+
+Patroni provides command-line interfaces for a Patroni :ref:`local configuration <yaml_configuration>` generation and validation. Using the ``patroni`` executable you can:
+
+- Create a sample local Patroni configuration;
+- Create a Patroni configuration file for the locally running PostgreSQL instance (e.g. as a preparation step for the :ref:`Patroni integration <existing_data>`);
+- Validate a given Patroni configuration file.
+
+.. _generate_sample_config:
+
+Sample Patroni configuration
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+.. code:: text
+
+   patroni --generate-sample-config [configfile]
+
+Description
+"""""""""""
+
+Generate a sample Patroni configuration file in ``yaml`` format.
+Parameter values are defined using the :ref:`Environment configuration <environment>`, otherwise, if not set, the defaults used in Patroni or the ``#FIXME`` string for the values that should be later defined by the user.
+
+Some default values are defined based on the local setup:
+
+   -  **postgresql.listen**: the IP address returned by ``gethostname`` call for the current machine's hostname and the standard ``5432`` port.
+   -  **postgresql.connect_address**: the IP address returned by ``gethostname`` call for the current machine's hostname and the standard ``5432`` port.
+   -  **postgresql.authentication.rewind**: is only defined if the PostgreSQL version can be defined from the binary and the version is 11 or later.
+   -  **restapi.listen**: IP address returned by ``gethostname`` call for the current machine's hostname and the standard ``8008`` port.
+   -  **restapi.connect_address**: IP address returned by ``gethostname`` call for the current machine's hostname and the standard ``8008`` port.
+
+Parameters
+""""""""""
+
+``configfile`` - full path to the configuration file used to store the result. If not provided, the result is sent to ``stdout``.
+
+.. _generate_config:
+
+Patroni configuration for a running instance
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+.. code:: text
+
+   patroni --generate-config [--dsn DSN] [configfile]
+
+Description
+"""""""""""
+
+Generate a Patroni configuration in ``yaml`` format for the locally running PostgreSQL instance. 
+Either the provided DSN (takes precedence) or PostgreSQL `environment variables <https://www.postgresql.org/docs/current/libpq-envars.html>`__ will be used for the PostgreSQL connection. If the password is not provided, it should be entered via prompt.
+
+All the non-internal GUCs defined in the source Postgres instance, independently if they were set through a configuration file, through the postmaster command-line, or through environment variables, will be used as the source for the following Patroni configuration parameters:
+
+   -  **scope**: ``cluster_name`` GUC value;
+   -  **postgresql.listen**: ``listen_addresses`` and ``port`` GUC values;
+   -  **postgresql.datadir**: ``data_directory`` GUC value;
+   -  **postgresql.parameters**: ``archive_command``, ``restore_command``, ``archive_cleanup_command``, ``recovery_end_command``, ``ssl_passphrase_command``, ``hba_file``, ``ident_file``, ``config_file`` GUC values;
+   -  **bootstrap.dcs**: all other gathered PostgreSQL GUCs.
+
+If ``scope``, ``postgresql.listen`` or ``postgresql.datadir`` is not set from the Postgres GUCs, the respective :ref:`Environment configuration <environment>` value is used.
+
+Other rules applied for the values definition:
+
+   -  **name**: ``PATRONI_NAME`` environment variable value if set, otherwise the current machine's hostname.
+   -  **postgresql.bin_dir**: path to the Postgres binaries gathered from the running instance.
+   -  **postgresql.connect_address**: the IP address returned by ``gethostname`` call for the current machine's hostname and the port used for the instance connection or the ``port`` GUC value.
+   -  **postgresql.authentication.superuser**: the configuration used for the instance connection;
+   -  **postgresql.pg_hba**: the lines gathered from the source instance's ``hba_file``.
+   -  **postgresql.pg_ident**: the lines gathered from the source instance's ``ident_file``.
+   -  **restapi.listen**: IP address returned by ``gethostname`` call for the current machine's hostname and the standard ``8008`` port.
+   -  **restapi.connect_address**: IP address returned by ``gethostname`` call for the current machine's hostname and the standard ``8008`` port.
+
+Other parameters defined using :ref:`Environment configuration <environment>` are also included into the configuration.
+
+Parameters
+""""""""""
+
+``configfile``
+    Full path to the configuration file used to store the result. If not provided, result is sent to ``stdout``.
+
+``dsn``
+    Optional DSN string for the local PostgreSQL instance to get GUC values from.
+
+
+Validate Patroni configuration
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+.. code:: text
+
+   patroni --validate-config [configfile] [--ignore-listen-port | -i]
+
+Description
+"""""""""""
+
+Validate the given Patroni configuration and print the information about the failed checks.
+
+Parameters
+""""""""""
+
+``configfile``
+    Full path to the configuration file to check. If not given or file does not exist, will try to read from the ``PATRONI_CONFIG_VARIABLE`` environment variable or, if not set, from the :ref:`Patroni environment variables <environment>`.
+
+``--ignore-listen-port | -i``
+    Optional flag to ignore bind failures for ``listen`` ports that are already in use when validating the ``configfile``.
+
+``--print | -p``
+    Optional flag to print out local configuration (including environment configuration overrides) after it has been successfully validated.

docs/pause.rst

@@ -19,7 +19,7 @@ When Patroni runs in a paused mode, it does not change the state of PostgreSQL,
 
 - For the Postgres primary with the leader lock Patroni updates the lock. If the node with the leader lock stops being the primary (i.e. is demoted manually), Patroni will release the lock instead of promoting the node back.
 
-- Manual unscheduled restart, reinitialize and manual failover are allowed. Manual failover is only allowed if the node to failover to is specified. In the paused mode, manual failover does not require a running primary node.
+- Manual unscheduled restart, manual unscheduled failover/switchover and reinitialize are allowed. No scheduled action is allowed. Manual switchover is only allowed if the node to switch over to is specified.
 
 - If 'parallel' primaries are detected by Patroni, it emits a warning, but does not demote the primary without the leader lock.
 
@@ -32,6 +32,6 @@ When Patroni runs in a paused mode, it does not change the state of PostgreSQL,
 User guide
 ----------
 
-``patronictl`` supports ``pause`` and ``resume`` commands.
+``patronictl`` supports :ref:`pause <patronictl_pause>` and :ref:`resume <patronictl_resume>` commands.
 
 One can also issue a ``PATCH`` request to the ``{namespace}/{cluster}/config`` key with ``{"pause": true/false/null}``

docs/replica_bootstrap.rst

@@ -1,3 +1,5 @@
+.. _replica_imaging_and_bootstrap:
+
 Replica imaging and bootstrap
 =============================
 
@@ -43,19 +45,49 @@ in the configuration files, Patroni supplies two cluster-specific ones:
 
 Passing these two additional flags can be disabled by setting a special ``no_params`` parameter to ``True``.
 
-If the bootstrap script returns 0, Patroni tries to configure and start the PostgreSQL instance produced by it. If any
+If the bootstrap script returns ``0``, Patroni tries to configure and start the PostgreSQL instance produced by it. If any
 of the intermediate steps fail, or the script returns a non-zero value, Patroni assumes that the bootstrap has failed,
 cleans up after itself and releases the initialize lock to give another node the opportunity to bootstrap.
 
 If a ``recovery_conf`` block is defined in the same section as the custom bootstrap method, Patroni will generate a
-``recovery.conf`` before starting the newly bootstrapped instance. Typically, such recovery.conf should contain at least
-one of the ``recovery_target_*`` parameters, together with the ``recovery_target_timeline`` set to ``promote``.
+``recovery.conf`` before starting the newly bootstrapped instance (or set the recovery settings on Postgres configuration if
+running PostgreSQL >= 12).
+Typically, such recovery configuration should contain at least one of the ``recovery_target_*`` parameters, together with the ``recovery_target_action`` set to ``promote``.
 
-If ``keep_existing_recovery_conf`` is defined and set to ``True``, Patroni will not remove the existing ``recovery.conf`` file if it exists.
-This is useful when bootstrapping from a backup with tools like pgBackRest that generate the appropriate ``recovery.conf`` for you.
+If ``keep_existing_recovery_conf`` is defined and set to ``True``, Patroni will not remove the existing ``recovery.conf`` file if it exists (PostgreSQL <= 11).
+Similarly, in that case Patroni will not remove the existing ``recovery.signal`` or ``standby.signal`` if either exists, nor will it override the configured recovery settings (PostgreSQL >= 12).
+This is useful when bootstrapping from a backup with tools like pgBackRest that generate the appropriate recovery configuration for you.
+
+Besides that, any additional key/value pairs informed in the custom bootstrap method configuration will be passed as arguments to ``command`` in the format ``--name=value``. For example:
+
+.. code:: YAML
+
+    bootstrap:
+        method: <custom_bootstrap_method_name>
+        <custom_bootstrap_method_name>:
+            command: <path_to_custom_bootstrap_script>
+            arg1: value1
+            arg2: value2
+
+Makes the configured ``command`` to be called additionally with ``--arg1=value1 --arg2=value2`` command-line arguments.
 
  .. note:: Bootstrap methods are neither chained, nor fallen-back to the default one in case the primary one fails
 
+As an example, you are able to bootstrap a fresh Patroni cluster from a Barman backup with a configuration like this:
+
+.. code:: YAML
+
+    bootstrap:
+        method: barman
+        barman:
+            keep_existing_recovery_conf: true
+            command: patroni_barman --api-url https://barman-host:7480 recover
+            barman-server: my_server
+            ssh-command: ssh postgres@patroni-host
+
+.. note::
+    ``patroni_barman recover`` requires that you have both Barman and ``pg-backup-api`` configured in the Barman host, so it can execute a remote ``barman recover`` through the backup API.
+    The above example uses a subset of the available parameters. You can get more information running ``patroni_barman recover --help``.
 
 .. _custom_replica_creation:
 
@@ -110,6 +142,24 @@ example: pgbackrest
         basebackup:
             max-rate: '100M'
 
+example: Barman
+
+.. code:: YAML
+
+    postgresql:
+        create_replica_methods:
+            - barman
+            - basebackup
+        barman:
+            command: patroni_barman --api-url https://barman-host:7480 recover
+            barman-server: my_server
+            ssh-command: ssh postgres@patroni-host
+        basebackup:
+            max-rate: '100M'
+
+.. note::
+    ``patroni_barman recover`` requires that you have both Barman and ``pg-backup-api`` configured in the Barman host, so it can execute a remote ``barman recover`` through the backup API.
+    The above example uses a subset of the available parameters. You can get more information running ``patroni_barman recover --help``.
 
 The ``create_replica_methods`` defines available replica creation methods and the order of executing them. Patroni will
 stop on the first one that returns 0. Each method should define a separate section in the configuration file, listing the command
@@ -169,59 +219,3 @@ and
             - waldir: /pg-wal-mount/external-waldir
 
 If all replica creation methods fail, Patroni will try again all methods in order during the next event loop cycle.
-
-.. _standby_cluster:
-
-Standby cluster
----------------
-
-Another available option is to run a "standby cluster", that contains only of
-standby nodes replicating from some remote node. This type of clusters has:
-
-* "standby leader", that behaves pretty much like a regular cluster leader,
-  except it replicates from a remote node.
-
-* cascade replicas, that are replicating from standby leader.
-
-Standby leader holds and updates a leader lock in DCS. If the leader lock
-expires, cascade replicas will perform an election to choose another leader
-from the standbys.
-
-There is no further relationship between the standby cluster and the primary
-cluster it replicates from, in particular, they must not share the same DCS
-scope if they use the same DCS. They do not know anything else from each other
-apart from replication information. Also, the standby cluster is not being
-displayed in ``patronictl list`` or ``patronictl topology`` output on the
-primary cluster.
-
-For the sake of flexibility, you can specify methods of creating a replica and
-recovery WAL records when a cluster is in the "standby mode" by providing
-`create_replica_methods` key in `standby_cluster` section. It is distinct from
-creating replicas, when cluster is detached and functions as a normal cluster,
-which is controlled by `create_replica_methods` in `postgresql` section. Both
-"standby" and "normal" `create_replica_methods` reference  keys in `postgresql`
-section.
-
-To configure such cluster you need to specify the section ``standby_cluster``
-in a patroni configuration:
-
-.. code:: YAML
-
-    bootstrap:
-        dcs:
-            standby_cluster:
-                host: 1.2.3.4
-                port: 5432
-                primary_slot_name: patroni
-                create_replica_methods:
-                - basebackup
-
-Note, that these options will be applied only once during cluster bootstrap,
-and the only way to change them afterwards is through DCS.
-
-Patroni expects to find `postgresql.conf` or `postgresql.conf.backup` in PGDATA
-of the remote primary and will not start if it does not find it after a
-basebackup. If the remote primary keeps its `postgresql.conf` elsewhere, it is
-your responsibility to copy it to PGDATA.
-
-If you use replication slots on the standby cluster, you must also create the corresponding replication slot on the primary cluster.  It will not be done automatically by the standby cluster implementation.  You can use Patroni's permanent replication slots feature on the primary cluster to maintain a replication slot with the same name as ``primary_slot_name``, or its default value if ``primary_slot_name`` is not provided.

docs/replication_modes.rst

@@ -6,8 +6,9 @@ Replication modes
 
 Patroni uses PostgreSQL streaming replication. For more information about streaming replication, see the `Postgres documentation <http://www.postgresql.org/docs/current/static/warm-standby.html#STREAMING-REPLICATION>`__. By default Patroni configures PostgreSQL for asynchronous replication. Choosing your replication schema is dependent on your business considerations. Investigate both async and sync replication, as well as other HA solutions, to determine which solution is best for you.
 
+
 Asynchronous mode durability
-----------------------------
+============================
 
 In asynchronous mode the cluster is allowed to lose some committed transactions to ensure availability. When the primary server fails or becomes unavailable for any other reason Patroni will automatically promote a sufficiently healthy standby to primary. Any transactions that have not been replicated to that standby remain in a "forked timeline" on the primary, and are effectively unrecoverable [1]_.
 
@@ -15,10 +16,11 @@ The amount of transactions that can be lost is controlled via ``maximum_lag_on_f
 
 By default, when running leader elections, Patroni does not take into account the current timeline of replicas, what in some cases could be undesirable behavior. You can prevent the node not having the same timeline as a former primary become the new leader by changing the value of ``check_timeline`` parameter to ``true``.
 
-PostgreSQL synchronous replication
-----------------------------------
 
-You can use Postgres's `synchronous replication <http://www.postgresql.org/docs/current/static/warm-standby.html#SYNCHRONOUS-REPLICATION>`__ with Patroni. Synchronous replication ensures consistency across a cluster by confirming that writes are written to a secondary before returning to the connecting client with a success. The cost of synchronous replication: reduced throughput on writes. This throughput will be entirely based on network performance.
+PostgreSQL synchronous replication
+==================================
+
+You can use Postgres's `synchronous replication <http://www.postgresql.org/docs/current/static/warm-standby.html#SYNCHRONOUS-REPLICATION>`__ with Patroni. Synchronous replication ensures consistency across a cluster by confirming that writes are written to a secondary before returning to the connecting client with a success. The cost of synchronous replication: increased latency and reduced throughput on writes. This throughput will be entirely based on network performance.
 
 In hosted datacenter environments (like AWS, Rackspace, or any network you do not control), synchronous replication significantly increases the variability of write performance. If followers become inaccessible from the leader, the leader effectively becomes read-only.
 
@@ -33,10 +35,11 @@ When using PostgreSQL synchronous replication, use at least three Postgres data
 
 Using PostgreSQL synchronous replication does not guarantee zero lost transactions under all circumstances. When the primary and the secondary that is currently acting as a synchronous replica fail simultaneously a third node that might not contain all transactions will be promoted.
 
+
 .. _synchronous_mode:
 
 Synchronous mode
-----------------
+================
 
 For use cases where losing committed transactions is not permissible you can turn on Patroni's ``synchronous_mode``. When ``synchronous_mode`` is turned on Patroni will not promote a standby unless it is certain that the standby contains all transactions that may have returned a successful commit status to client [2]_. This means that the system may be unavailable for writes even though some servers are available. System administrators can still use manual failover commands to promote a standby even if it results in transaction loss.
 
@@ -53,32 +56,126 @@ are available. As a downside, the primary is not be available for writes
 blocking all client write requests until at least one synchronous replica comes
 up.
 
-You can ensure that a standby never becomes the synchronous standby by setting ``nosync`` tag to true. This is recommended to set for standbys that are behind slow network connections and would cause performance degradation when becoming a synchronous standby.
+You can ensure that a standby never becomes the synchronous standby by setting ``nosync`` tag to true. This is recommended to set for standbys that are behind slow network connections and would cause performance degradation when becoming a synchronous standby. Setting tag ``nostream`` to true will also have the same effect.
 
-Synchronous mode can be switched on and off via Patroni REST interface. See :ref:`dynamic configuration <dynamic_configuration>` for instructions.
+Synchronous mode can be switched on and off using ``patronictl edit-config`` command or via Patroni REST interface. See :ref:`dynamic configuration <dynamic_configuration>` for instructions.
 
 Note: Because of the way synchronous replication is implemented in PostgreSQL it is still possible to lose transactions even when using ``synchronous_mode_strict``. If the PostgreSQL backend is cancelled while waiting to acknowledge replication (as a result of packet cancellation due to client timeout or backend failure) transaction changes become visible for other backends. Such changes are not yet replicated and may be lost in case of standby promotion.
 
+
 Synchronous Replication Factor
-------------------------------
-The parameter ``synchronous_node_count`` is used by Patroni to manage number of synchronous standby databases. It is set to 1 by default. It has no effect when ``synchronous_mode`` is set to off. When enabled, Patroni manages precise number of synchronous standby databases based on parameter ``synchronous_node_count`` and adjusts the state in DCS & synchronous_standby_names as members join and leave.
+==============================
+
+The parameter ``synchronous_node_count`` is used by Patroni to manage the number of synchronous standby databases. It is set to ``1`` by default. It has no effect when ``synchronous_mode`` is set to ``off``. When enabled, Patroni manages the precise number of synchronous standby databases based on parameter ``synchronous_node_count`` and adjusts the state in DCS & ``synchronous_standby_names`` in PostgreSQL as members join and leave. If the parameter is set to a value higher than the number of eligible nodes it will be automatically reduced by Patroni.
+
+
+Maximum lag on synchronous node
+===============================
+
+By default Patroni sticks to nodes that are declared as ``synchronous``, according to the ``pg_stat_replication`` view, even when there are other nodes ahead of it. This is done to minimize the number of changes of ``synchronous_standby_names``. To change this behavior one may use ``maximum_lag_on_syncnode`` parameter. It controls how much lag the replica can have to still be considered as "synchronous".
+
+Patroni utilizes the max replica LSN if there is more than one standby, otherwise it will use leader's current wal LSN. The default is ``-1``, and Patroni will not take action to swap a synchronous unhealthy standby when the value is set to ``0`` or less. Please set the value high enough so that Patroni won't swap synchronous standbys frequently during high transaction volume.
+
 
 Synchronous mode implementation
--------------------------------
+===============================
 
-When in synchronous mode Patroni maintains synchronization state in the DCS, containing the latest primary and current synchronous standby databases. This state is updated with strict ordering constraints to ensure the following invariants:
+When in synchronous mode Patroni maintains synchronization state in the DCS (``/sync`` key), containing the latest primary and current synchronous standby databases. This state is updated with strict ordering constraints to ensure the following invariants:
 
 - A node must be marked as the latest leader whenever it can accept write transactions. Patroni crashing or PostgreSQL not shutting down can cause violations of this invariant.
 
-- A node must be set as the synchronous standby in PostgreSQL as long as it is published as the synchronous standby.
+- A node must be set as the synchronous standby in PostgreSQL as long as it is published as the synchronous standby in the ``/sync`` key in DCS..
 
 - A node that is not the leader or current synchronous standby is not allowed to promote itself automatically.
 
 Patroni will only assign one or more synchronous standby nodes based on ``synchronous_node_count`` parameter to ``synchronous_standby_names``.
 
-On each HA loop iteration Patroni re-evaluates synchronous standby nodes choice. If the current list of synchronous standby nodes are connected and has not requested its synchronous status to be removed it remains picked. Otherwise the cluster member available for sync that is furthest ahead in replication is picked.
+On each HA loop iteration Patroni re-evaluates synchronous standby nodes choice. If the current list of synchronous standby nodes are connected and has not requested its synchronous status to be removed it remains picked. Otherwise the cluster members available for sync that are furthest ahead in replication are picked.
+
+Example:
+---------
+
+``/config`` key in DCS
+^^^^^^^^^^^^^^^^^^^^^^
+
+.. code-block:: YAML
+
+    synchronous_mode: on
+    synchronous_node_count: 2
+    ...
+
+``/sync`` key in DCS
+^^^^^^^^^^^^^^^^^^^^
+
+.. code-block:: JSON
+
+    {
+        "leader": "node0",
+        "sync_standby": "node1,node2"
+    }
+
+postgresql.conf
+^^^^^^^^^^^^^^^
+
+.. code-block:: INI
+
+    synchronous_standby_names = 'FIRST 2 (node1,node2)'
 
 
-.. [1] The data is still there, but recovering it requires a manual recovery effort by data recovery specialists. When Patroni is allowed to rewind with ``use_pg_rewind`` the forked timeline will be automatically erased to rejoin the failed primary with the cluster.
+In the above examples only nodes ``node1`` and ``node2`` are known to be synchronous and allowed to be automatically promoted if the primary (``node0``) fails.
+
+
+.. _quorum_mode:
+
+Quorum commit mode
+==================
+
+Starting from PostgreSQL v10 Patroni supports quorum-based synchronous replication.
+
+In this mode, Patroni maintains synchronization state in the DCS, containing the latest known primary, the number of nodes required for quorum, and the nodes currently eligible to vote on quorum. In steady state, the nodes voting on quorum are the leader and all synchronous standbys. This state is updated with strict ordering constraints, with regards to node promotion and ``synchronous_standby_names``, to ensure that at all times any subset of voters that can achieve quorum includes at least one node with the latest successful commit.
+
+On each iteration of HA loop, Patroni re-evaluates synchronous standby choices and quorum, based on node availability and requested cluster configuration. In PostgreSQL versions above 9.6 all eligible nodes are added as synchronous standbys as soon as their replication catches up to leader.
+
+Quorum commit helps to reduce worst case latencies, even during normal operation, as a higher latency of replicating to one standby can be compensated by other standbys.
+
+The quorum-based synchronous mode could be enabled by setting ``synchronous_mode`` to ``quorum`` using ``patronictl edit-config`` command or via Patroni REST interface. See :ref:`dynamic configuration <dynamic_configuration>` for instructions.
+
+Other parameters, like ``synchronous_node_count``, ``maximum_lag_on_syncnode``, and ``synchronous_mode_strict`` continue to work the same way as with ``synchronous_mode=on``.
+
+Example:
+---------
+
+``/config`` key in DCS
+^^^^^^^^^^^^^^^^^^^^^^
+
+.. code-block:: YAML
+
+    synchronous_mode: quorum
+    synchronous_node_count: 2
+    ...
+
+``/sync`` key in DCS
+^^^^^^^^^^^^^^^^^^^^
+
+.. code-block:: JSON
+
+    {
+        "leader": "node0",
+        "sync_standby": "node1,node2,node3",
+        "quorum": 1
+    }
+
+postgresql.conf
+^^^^^^^^^^^^^^^
+
+.. code-block:: INI
+
+    synchronous_standby_names = 'ANY 2 (node1,node2,node3)'
+
+
+If the primary (``node0``) failed, in the above example two of the ``node1``, ``node2``, ``node3`` will have the latest transaction received, but we don't know which ones. To figure out whether the node ``node1`` has received the latest transaction, we need to compare its LSN with the LSN on **at least** one node (``quorum=1`` in the ``/sync`` key) among ``node2`` and ``node3``. If ``node1`` isn't behind of at least one of them, we can guarantee that there will be no user visible data loss if ``node1`` is promoted.
+
+
+.. [1] The data is still there, but recovering it requires a manual recovery effort by data recovery specialists. When Patroni is allowed to rewind with ``use_pg_rewind`` the forked timeline will be automatically erased to rejoin the failed primary with the cluster. However, for ``use_pg_rewind`` to function properly, either the cluster must be initialized with ``data page checksums`` (``--data-checksums`` option for ``initdb``) and/or ``wal_log_hints`` must be set to ``on``.
 
 .. [2] Clients can change the behavior per transaction using PostgreSQL's ``synchronous_commit`` setting. Transactions with ``synchronous_commit`` values of ``off`` and ``local`` may be lost on fail over, but will not be blocked by replication delays.

docs/rest_api.rst

@@ -3,7 +3,7 @@
 Patroni REST API
 ================
 
-Patroni has a rich REST API, which is used by Patroni itself during the leader race, by the ``patronictl`` tool in order to perform failovers/switchovers/reinitialize/restarts/reloads, by HAProxy or any other kind of load balancer to perform HTTP health checks, and of course could also be used for monitoring. Below you will find the list of Patroni REST API endpoints.
+Patroni has a rich REST API, which is used by Patroni itself during the leader race, by the :ref:`patronictl` tool in order to perform failovers/switchovers/reinitialize/restarts/reloads, by HAProxy or any other kind of load balancer to perform HTTP health checks, and of course could also be used for monitoring. Below you will find the list of Patroni REST API endpoints.
 
 Health check endpoints
 ----------------------
@@ -45,6 +45,10 @@ For all health check ``GET`` requests Patroni returns a JSON document with the s
 
 - ``GET /read-only-sync``: like the above endpoint, but also includes the primary.
 
+- ``GET /quorum``: returns HTTP status code **200** only when this Patroni node is listed as a quorum node in ``synchronous_standby_names`` on the primary.
+
+- ``GET /read-only-quorum``: like the above endpoint, but also includes the primary.
+
 - ``GET /asynchronous`` or ``GET /async``: returns HTTP status code **200** only when the Patroni node is running as an asynchronous standby.
 
 
@@ -99,9 +103,9 @@ The ``GET /patroni`` is used by Patroni during the leader race. It also could be
     $ curl -s http://localhost:8008/patroni | jq .
     {
       "state": "running",
-      "postmaster_start_time": "2023-08-18 11:03:37.966359+00:00",
-      "role": "master",
-      "server_version": 150004,
+      "postmaster_start_time": "2024-08-28 19:39:26.352526+00:00",
+      "role": "primary",
+      "server_version": 160004,
       "xlog": {
         "location": 67395656
       },
@@ -130,8 +134,9 @@ The ``GET /patroni`` is used by Patroni during the leader race. It also could be
       },
       "database_system_identifier": "7268616322854375442",
       "patroni": {
-        "version": "3.1.0",
-        "scope": "demo"
+        "version": "4.0.0",
+        "scope": "demo",
+        "name": "patroni1"
       }
     }
 
@@ -142,9 +147,9 @@ The ``GET /patroni`` is used by Patroni during the leader race. It also could be
     $ curl -s http://localhost:8008/patroni  | jq .
     {
       "state": "running",
-      "postmaster_start_time": "2023-08-18 11:09:08.615242+00:00",
+      "postmaster_start_time": "2024-08-28 19:39:26.352526+00:00",
       "role": "replica",
-      "server_version": 150004,
+      "server_version": 160004,
       "xlog": {
         "received_location": 67419744,
         "replayed_location": 67419744,
@@ -177,8 +182,9 @@ The ``GET /patroni`` is used by Patroni during the leader race. It also could be
       },
       "database_system_identifier": "7268616322854375442",
       "patroni": {
-        "version": "3.1.0",
-        "scope": "demo"
+        "version": "4.0.0",
+        "scope": "demo",
+        "name": "patroni1"
       }
     }
 
@@ -189,9 +195,9 @@ The ``GET /patroni`` is used by Patroni during the leader race. It also could be
     $ curl -s http://localhost:8008/patroni  | jq .
     {
       "state": "running",
-      "postmaster_start_time": "2023-08-18 11:09:08.615242+00:00",
+      "postmaster_start_time": "2024-08-28 19:39:26.352526+00:00",
       "role": "replica",
-      "server_version": 150004,
+      "server_version": 160004,
       "xlog": {
         "location": 67420024
       },
@@ -222,8 +228,9 @@ The ``GET /patroni`` is used by Patroni during the leader race. It also could be
       },
       "database_system_identifier": "7268616322854375442",
       "patroni": {
-        "version": "3.1.0",
-        "scope": "demo"
+        "version": "4.0.0",
+        "scope": "demo",
+        "name": "patroni1"
       }
     }
 
@@ -234,9 +241,9 @@ The ``GET /patroni`` is used by Patroni during the leader race. It also could be
     $ curl -s http://localhost:8008/patroni  | jq .
     {
       "state": "running",
-      "postmaster_start_time": "2023-08-18 11:09:08.615242+00:00",
+      "postmaster_start_time": "2024-08-28 19:39:26.352526+00:00",
       "role": "replica",
-      "server_version": 150004,
+      "server_version": 160004,
       "xlog": {
         "location": 67420024
       },
@@ -260,14 +267,15 @@ The ``GET /patroni`` is used by Patroni during the leader race. It also could be
         }
       ],
       "pause": true,
-      "dcs_last_seen": 1692356928,
+      "dcs_last_seen": 1724874295,
       "tags": {
         "clonefrom": true
       },
       "database_system_identifier": "7268616322854375442",
       "patroni": {
-        "version": "3.1.0",
-        "scope": "demo"
+        "version": "4.0.0",
+        "scope": "demo",
+        "name": "patroni1"
       }
     }
 
@@ -279,70 +287,70 @@ Retrieve the Patroni metrics in Prometheus format through the ``GET /metrics`` e
 	
 	# HELP patroni_version Patroni semver without periods. \
 	# TYPE patroni_version gauge
-	patroni_version{scope="batman"} 020103
+	patroni_version{scope="batman",name="patroni1"} 040000
 	# HELP patroni_postgres_running Value is 1 if Postgres is running, 0 otherwise.
 	# TYPE patroni_postgres_running gauge
-	patroni_postgres_running{scope="batman"} 1
+	patroni_postgres_running{scope="batman",name="patroni1"} 1
 	# HELP patroni_postmaster_start_time Epoch seconds since Postgres started.
 	# TYPE patroni_postmaster_start_time gauge
-	patroni_postmaster_start_time{scope="batman"} 1657656955.179243
-	# HELP patroni_master Value is 1 if this node is the leader, 0 otherwise.
-	# TYPE patroni_master gauge
-	patroni_master{scope="batman"} 1
+	patroni_postmaster_start_time{scope="batman",name="patroni1"} 1724873966.352526
 	# HELP patroni_primary Value is 1 if this node is the leader, 0 otherwise.
 	# TYPE patroni_primary gauge
-	patroni_primary{scope="batman"} 1
+	patroni_primary{scope="batman",name="patroni1"} 1
 	# HELP patroni_xlog_location Current location of the Postgres transaction log, 0 if this node is not the leader.
 	# TYPE patroni_xlog_location counter
-	patroni_xlog_location{scope="batman"} 22320573386952
+	patroni_xlog_location{scope="batman",name="patroni1"} 22320573386952
 	# HELP patroni_standby_leader Value is 1 if this node is the standby_leader, 0 otherwise.
 	# TYPE patroni_standby_leader gauge
-	patroni_standby_leader{scope="batman"} 0
+	patroni_standby_leader{scope="batman",name="patroni1"} 0
 	# HELP patroni_replica Value is 1 if this node is a replica, 0 otherwise.
 	# TYPE patroni_replica gauge
-	patroni_replica{scope="batman"} 0
+	patroni_replica{scope="batman",name="patroni1"} 0
 	# HELP patroni_sync_standby Value is 1 if this node is a sync standby replica, 0 otherwise.
 	# TYPE patroni_sync_standby gauge
-	patroni_sync_standby{scope="batman"} 0
+	patroni_sync_standby{scope="batman",name="patroni1"} 0
+	# HELP patroni_quorum_standby Value is 1 if this node is a quorum standby replica, 0 otherwise.
+	# TYPE patroni_quorum_standby gauge
+	patroni_quorum_standby{scope="batman",name="patroni1"} 0
 	# HELP patroni_xlog_received_location Current location of the received Postgres transaction log, 0 if this node is not a replica.
 	# TYPE patroni_xlog_received_location counter
-	patroni_xlog_received_location{scope="batman"} 0
+	patroni_xlog_received_location{scope="batman",name="patroni1"} 0
 	# HELP patroni_xlog_replayed_location Current location of the replayed Postgres transaction log, 0 if this node is not a replica.
 	# TYPE patroni_xlog_replayed_location counter
-	patroni_xlog_replayed_location{scope="batman"} 0
+	patroni_xlog_replayed_location{scope="batman",name="patroni1"} 0
 	# HELP patroni_xlog_replayed_timestamp Current timestamp of the replayed Postgres transaction log, 0 if null.
 	# TYPE patroni_xlog_replayed_timestamp gauge
-	patroni_xlog_replayed_timestamp{scope="batman"} 0
+	patroni_xlog_replayed_timestamp{scope="batman",name="patroni1"} 0
 	# HELP patroni_xlog_paused Value is 1 if the Postgres xlog is paused, 0 otherwise.
 	# TYPE patroni_xlog_paused gauge
-	patroni_xlog_paused{scope="batman"} 0
+	patroni_xlog_paused{scope="batman",name="patroni1"} 0
 	# HELP patroni_postgres_streaming Value is 1 if Postgres is streaming, 0 otherwise.
 	# TYPE patroni_postgres_streaming gauge
-	patroni_postgres_streaming{scope="batman"} 1
+	patroni_postgres_streaming{scope="batman",name="patroni1"} 1
 	# HELP patroni_postgres_in_archive_recovery Value is 1 if Postgres is replicating from archive, 0 otherwise.
 	# TYPE patroni_postgres_in_archive_recovery gauge
-	patroni_postgres_in_archive_recovery{scope="batman"} 0
+	patroni_postgres_in_archive_recovery{scope="batman",name="patroni1"} 0
 	# HELP patroni_postgres_server_version Version of Postgres (if running), 0 otherwise.
 	# TYPE patroni_postgres_server_version gauge
-	patroni_postgres_server_version {scope="batman"} 140004
+	patroni_postgres_server_version{scope="batman",name="patroni1"} 160004
 	# HELP patroni_cluster_unlocked Value is 1 if the cluster is unlocked, 0 if locked.
 	# TYPE patroni_cluster_unlocked gauge
-	patroni_cluster_unlocked{scope="batman"} 0
+	patroni_cluster_unlocked{scope="batman",name="patroni1"} 0
 	# HELP patroni_postgres_timeline Postgres timeline of this node (if running), 0 otherwise.
 	# TYPE patroni_postgres_timeline counter
-	patroni_failsafe_mode_is_active{scope="batman"} 0
+	patroni_failsafe_mode_is_active{scope="batman",name="patroni1"} 0
 	# HELP patroni_postgres_timeline Postgres timeline of this node (if running), 0 otherwise.
 	# TYPE patroni_postgres_timeline counter
-	patroni_postgres_timeline{scope="batman"} 24
+	patroni_postgres_timeline{scope="batman",name="patroni1"} 24
 	# HELP patroni_dcs_last_seen Epoch timestamp when DCS was last contacted successfully by Patroni.
 	# TYPE patroni_dcs_last_seen gauge
-	patroni_dcs_last_seen{scope="batman"} 1677658321
+	patroni_dcs_last_seen{scope="batman",name="patroni1"} 1724874235
 	# HELP patroni_pending_restart Value is 1 if the node needs a restart, 0 otherwise.
 	# TYPE patroni_pending_restart gauge
-	patroni_pending_restart{scope="batman"} 1
+	patroni_pending_restart{scope="batman",name="patroni1"} 1
 	# HELP patroni_is_paused Value is 1 if auto failover is disabled, 0 otherwise.
 	# TYPE patroni_is_paused gauge
-	patroni_is_paused{scope="batman"} 1
+	patroni_is_paused{scope="batman",name="patroni1"} 1
 
 
 Cluster status endpoints
@@ -381,6 +389,7 @@ Cluster status endpoints
           "lag": 0
         }
       ],
+      "scope": "demo",
       "scheduled_switchover": {
         "at": "2023-09-24T10:36:00+02:00",
         "from": "patroni1",
@@ -421,6 +430,7 @@ Cluster status endpoints
       ]
     ]
 
+.. _config_endpoint:
 
 Config endpoint
 ---------------
@@ -482,19 +492,29 @@ Let's check that the node processed this configuration. First of all it should s
 
 	$ curl -s http://localhost:8008/patroni | jq .
 	{
-	  "pending_restart": true,
 	  "database_system_identifier": "6287881213849985952",
-	  "postmaster_start_time": "2016-06-13 13:13:05.211 CEST",
+	  "postmaster_start_time": "2024-08-28 19:39:26.352526+00:00",
 	  "xlog": {
 	    "location": 2197818976
 	  },
+	  "timeline": 1,
+	  "dcs_last_seen": 1724874545,
+	  "database_system_identifier": "7408277255830290455",
+	  "pending_restart": true,
+	  "pending_restart_reason": {
+	    "max_connections": {
+	      "old_value": "100",
+	      "new_value": "101"
+	    }
+	  },
 	  "patroni": {
+	    "version": "4.0.0",
 	    "scope": "batman",
-	    "version": "1.0"
+	    "name": "patroni1"
 	  },
 	  "state": "running",
-	  "role": "master",
-	  "server_version": 90503
+	  "role": "primary",
+	  "server_version": 160004
 	}
 
 Removing parameters:
@@ -554,41 +574,114 @@ The above call removes ``postgresql.parameters.max_connections`` from the dynami
 Switchover and failover endpoints
 ---------------------------------
 
-``POST /switchover`` or ``POST /failover``. These endpoints are very similar to each other. There are a couple of minor differences though:
+.. _switchover_api:
 
-1. The failover endpoint allows to perform a manual failover when there are no healthy nodes, but at the same time it will not allow you to schedule a switchover.
+Switchover
+^^^^^^^^^^
 
-2. The switchover endpoint is the opposite. It works only when the cluster is healthy (there is a leader) and allows to schedule a switchover at a given time.
+``/switchover`` endpoint only works when the cluster is healthy (there is a leader). It also allows to schedule a switchover at a given time.
 
+When calling ``/switchover`` endpoint a candidate can be specified but is not required, in contrast to ``/failover`` endpoint. If a candidate is not provided, all the eligible nodes of the cluster will participate in the leader race after the leader stepped down.
 
-In the JSON body of the ``POST`` request you must specify at least the ``leader`` or ``candidate`` fields and optionally the ``scheduled_at`` field if you want to schedule a switchover at a specific time.
+In the JSON body of the ``POST`` request you must specify the ``leader`` field. The ``candidate`` and the ``scheduled_at`` fields are optional and can be used to schedule a switchover at a specific time.
 
+Depending on the situation, requests might return different HTTP status codes and bodies. Status code **200** is returned when the switchover or failover successfully completed. If the switchover was successfully scheduled, Patroni will return HTTP status code **202**. In case something went wrong, the error status code (one of **400**, **412**, or **503**) will be returned with some details in the response body.
 
-Example: perform a failover to the specific node:
+``DELETE /switchover`` can be used to delete the currently scheduled switchover.
+
+**Example:** perform a switchover to any healthy standby
 
 .. code-block:: bash
 
-    $ curl -s http://localhost:8009/failover -XPOST -d '{"candidate":"postgresql1"}'
-    Successfully failed over to "postgresql1"
+	$ curl -s http://localhost:8008/switchover -XPOST -d '{"leader":"postgresql1"}'
+	Successfully switched over to "postgresql2"
 
 
-Example: schedule a switchover from the leader to any other healthy replica in the cluster at a specific time:
+**Example:** perform a switchover to a specific node
 
 .. code-block:: bash
 
-    $ curl -s http://localhost:8008/switchover -XPOST -d \
-	    '{"leader":"postgresql0","scheduled_at":"2019-09-24T12:00+00"}'
-    Switchover scheduled
+	$ curl -s http://localhost:8008/switchover -XPOST -d \
+		'{"leader":"postgresql1","candidate":"postgresql2"}'
+	Successfully switched over to "postgresql2"
 
 
-Depending on the situation the request might finish with a different HTTP status code and body. The status code **200** is returned when the switchover or failover successfully completed. If the switchover was successfully scheduled, Patroni will return HTTP status code **202**. In case something went wrong, the error status code (one of **400**, **412** or **503**) will be returned with some details in the response body. For more information please check the source code of ``patroni/api.py:do_POST_failover()`` method.
+**Example:** schedule a switchover from the leader to any other healthy standby in the cluster at a specific time.
 
-- ``DELETE /switchover``: delete the scheduled switchover
+.. code-block:: bash
 
-The ``POST /switchover`` and ``POST failover`` endpoints are used by ``patronictl switchover`` and ``patronictl failover``, respectively.
-The ``DELETE /switchover`` is used by ``patronictl flush <cluster-name> switchover``.
+	$ curl -s http://localhost:8008/switchover -XPOST -d \
+		'{"leader":"postgresql0","scheduled_at":"2019-09-24T12:00+00"}'
+	Switchover scheduled
 
 
+Failover
+^^^^^^^^
+
+``/failover`` endpoint can be used to perform a manual failover when there are no healthy nodes (e.g. to an asynchronous standby if all synchronous standbys are not healthy enough to promote). However there is no requirement for a cluster not to have leader - failover can also be run on a healthy cluster.
+
+In the JSON body of the ``POST`` request you must specify the ``candidate`` field. If the ``leader`` field is specified, a switchover is triggered instead.
+
+**Example:**
+
+.. code-block:: bash
+
+	$ curl -s http://localhost:8008/failover -XPOST -d '{"candidate":"postgresql1"}'
+	Successfully failed over to "postgresql1"
+
+.. warning::
+	:ref:`Be very careful <failover_healthcheck>` when using this endpoint, as this can cause data loss in certain situations. In most cases, :ref:`the switchover endpoint <switchover_api>` satisfies the administrator's needs. 
+
+
+``POST /switchover`` and ``POST /failover`` endpoints are used by :ref:`patronictl_switchover` and :ref:`patronictl_failover`, respectively.
+
+``DELETE /switchover`` is used by :ref:`patronictl flush cluster-name switchover <patronictl_flush_parameters>`.
+
+.. list-table:: Failover/Switchover comparison
+   :widths: 25 25 25
+   :header-rows: 1
+
+   * -
+     - Failover
+     - Switchover
+   * - Requires leader specified
+     - no
+     - yes
+   * - Requires candidate specified
+     - yes
+     - no
+   * - Can be run in pause
+     - yes
+     - yes (only to a specific candidate)
+   * - Can be scheduled
+     - no
+     - yes (if not in pause)
+
+.. _failover_healthcheck:
+
+Healthy standby
+^^^^^^^^^^^^^^^
+
+There are a couple of checks that a member of a cluster should pass to be able to participate in the leader race during a switchover or to become a leader as a failover/switchover candidate:
+
+- be reachable via Patroni API;
+- not have ``nofailover`` tag set to ``true``;
+- have watchdog fully functional (if required by the configuration);
+- in case of a switchover in a healthy cluster or an automatic failover, not exceed maximum replication lag (``maximum_lag_on_failover`` :ref:`configuration parameter <dynamic_configuration>`);
+- in case of a switchover in a healthy cluster or an automatic failover, not have a timeline number smaller than the cluster timeline if ``check_timeline`` :ref:`configuration parameter <dynamic_configuration>` is set to ``true``;
+- in :ref:`synchronous mode <synchronous_mode>`:
+
+  - In case of a switchover (both with and without a candidate): be listed in the ``/sync`` key members;
+  - For a failover in both healthy and unhealthy clusters, this check is omitted.
+
+.. warning::
+    In case of a manual failover in a cluster without a leader, a candidate will be allowed to promote even if:
+	- it is not in the ``/sync`` key members when synchronous mode is enabled;
+	- its lag exceeds the maximum replication lag allowed;
+	- it has the timeline number smaller than the last known cluster timeline.
+
+.. _restart_endpoint:
+
 Restart endpoint
 ----------------
 
@@ -602,15 +695,16 @@ Restart endpoint
 
 - ``DELETE /restart``: delete the scheduled restart
 
-``POST /restart`` and ``DELETE /restart`` endpoints are used by ``patronictl restart`` and ``patronictl flush <cluster-name> restart`` respectively.
+``POST /restart`` and ``DELETE /restart`` endpoints are used by :ref:`patronictl_restart` and :ref:`patronictl flush cluster-name restart <patronictl_flush_parameters>` respectively.
 
+.. _reload_endpoint:
 
 Reload endpoint
 ---------------
 
-The ``POST /reload`` call will order Patroni to re-read and apply the configuration file. This is the equivalent of sending the ``SIGHUP`` signal to the Patroni process. In case you changed some of the Postgres parameters which require a restart (like **shared_buffers**), you still have to explicitly do the restart of Postgres by either calling the ``POST /restart`` endpoint or with the help of ``patronictl restart``.
+The ``POST /reload`` call will order Patroni to re-read and apply the configuration file. This is the equivalent of sending the ``SIGHUP`` signal to the Patroni process. In case you changed some of the Postgres parameters which require a restart (like **shared_buffers**), you still have to explicitly do the restart of Postgres by either calling the ``POST /restart`` endpoint or with the help of :ref:`patronictl_restart`.
 
-The reload endpoint is used by ``patronictl reload``.
+The reload endpoint is used by :ref:`patronictl_reload`.
 
 
 Reinitialize endpoint
@@ -620,4 +714,4 @@ Reinitialize endpoint
 
 The call might fail if Patroni is in a loop trying to recover (restart) a failed Postgres. In order to overcome this problem one can specify ``{"force":true}`` in the request body.
 
-The reinitialize endpoint is used by ``patronictl reinit``.
+The reinitialize endpoint is used by :ref:`patronictl_reinit`.

docs/security.rst

@@ -9,7 +9,7 @@ A Patroni cluster has two interfaces to be protected from unauthorized access: t
 Protecting DCS
 ==============
 
-Patroni and patronictl both store and retrieve data to/from the DCS.
+Patroni and :ref:`patronictl` both store and retrieve data to/from the DCS.
 
 Despite DCS doesn't contain any sensitive information, it allows changing some of Patroni/Postgres configuration. Therefore the very first thing that should be protected is DCS itself.
 
@@ -22,7 +22,7 @@ Protecting the REST API
 
 Protecting the REST API is a more complicated task.
 
-The Patroni REST API is used by Patroni itself during the leader race, by the ``patronictl`` tool in order to perform failovers/switchovers/reinitialize/restarts/reloads, by HAProxy or any other kind of load balancer to perform HTTP health checks, and of course could also be used for monitoring.
+The Patroni REST API is used by Patroni itself during the leader race, by the :ref:`patronictl` tool in order to perform failovers/switchovers/reinitialize/restarts/reloads, by HAProxy or any other kind of load balancer to perform HTTP health checks, and of course could also be used for monitoring.
 
 From the point of view of security, REST API contains safe (``GET`` requests, only retrieve information) and unsafe (``PUT``, ``POST``, ``PATCH`` and ``DELETE`` requests, change the state of nodes) endpoints.
 
@@ -32,6 +32,6 @@ When TLS for the REST API is enabled and a PKI is established, mutual authentica
 
 The ``restapi`` section parameters enable TLS client authentication to the server. Depending on the value of the ``verify_client`` parameter, the API server requires a successful client certificate verification for both safe and unsafe API calls (``verify_client: required``), or only for unsafe API calls (``verify_client: optional``), or for no API calls (``verify_client: none``).
 
-The ``ctl`` section parameters enable TLS server authentication to the client (the ``patronictl`` tool which uses the same config as patroni). Set ``insecure: true`` to disable the server certificate verification by the client. See :ref:`settings <patronictl_settings>` for a detailed description of the TLS client parameters.
+The ``ctl`` section parameters enable TLS server authentication to the client (the :ref:`patronictl` tool which uses the same config as patroni). Set ``insecure: true`` to disable the server certificate verification by the client. See :ref:`settings <patronictl_settings>` for a detailed description of the TLS client parameters.
 
 Protecting the PostgreSQL database proper from unauthorized access is beyond the scope of this document and is covered in https://www.postgresql.org/docs/current/client-authentication.html

docs/standby_cluster.rst

@@ -0,0 +1,82 @@
+.. _standby_cluster:
+
+Standby cluster
+---------------
+
+Patroni also support running cascading replication to a remote datacenter
+(region) using a feature that is called "standby cluster". This type of
+clusters has:
+
+* "standby leader", that behaves pretty much like a regular cluster leader,
+  except it replicates from a remote node.
+
+* cascade replicas, that are replicating from standby leader.
+
+Standby leader holds and updates a leader lock in DCS. If the leader lock
+expires, cascade replicas will perform an election to choose another leader
+from the standbys.
+
+There is no further relationship between the standby cluster and the primary
+cluster it replicates from, in particular, they must not share the same DCS
+scope if they use the same DCS. They do not know anything else from each other
+apart from replication information. Also, the standby cluster is not being
+displayed in :ref:`patronictl_list` or :ref:`patronictl_topology` output on the
+primary cluster.
+
+For the sake of flexibility, you can specify methods of creating a replica and
+recovery WAL records when a cluster is in the "standby mode" by providing
+:ref:`create_replica_methods <custom_replica_creation>` key in
+`standby_cluster` section. It is distinct from creating replicas, when cluster
+is detached and functions as a normal cluster, which is controlled by
+`create_replica_methods` in `postgresql` section. Both "standby" and "normal"
+`create_replica_methods` reference  keys in `postgresql` section.
+
+To configure such cluster you need to specify the section ``standby_cluster``
+in a patroni configuration:
+
+.. code:: YAML
+
+    bootstrap:
+        dcs:
+            standby_cluster:
+                host: 1.2.3.4
+                port: 5432
+                primary_slot_name: patroni
+                create_replica_methods:
+                - basebackup
+
+Note, that these options will be applied only once during cluster bootstrap,
+and the only way to change them afterwards is through DCS.
+
+Patroni expects to find `postgresql.conf` or `postgresql.conf.backup` in PGDATA
+of the remote primary and will not start if it does not find it after a
+basebackup. If the remote primary keeps its `postgresql.conf` elsewhere, it is
+your responsibility to copy it to PGDATA.
+
+If you use replication slots on the standby cluster, you must also create the
+corresponding replication slot on the primary cluster.  It will not be done
+automatically by the standby cluster implementation.  You can use Patroni's
+permanent replication slots feature on the primary cluster to maintain a
+replication slot with the same name as ``primary_slot_name``, or its default
+value if ``primary_slot_name`` is not provided.
+
+In case the remote site doesn't provide a single endpoint that connects to a
+primary, one could list all hosts of the source cluster in the
+``standby_cluster.host`` section.  When ``standby_cluster.host`` contains
+multiple hosts separated by commas, Patroni will:
+
+* add ``target_session_attrs=read-write`` to the ``primary_conninfo`` on the
+  standby leader node.
+* use ``target_session_attrs=read-write`` when trying to determine whether we
+  need to run ``pg_rewind`` or when executing ``pg_rewind`` on all nodes of the
+  standby cluster.
+* It is important to note that for ``pg_rewind`` to operate successfully, 
+  either the cluster must be initialized with ``data page checksums`` 
+  (``--data-checksums`` option for ``initdb``) and/or ``wal_log_hints`` must be set to ``on``.
+  Otherwise, ``pg_rewind`` will not function properly.
+  
+There is also a possibility to replicate the standby cluster from another
+standby cluster or from a standby member of the primary cluster: for that, you
+need to define a single host in the ``standby_cluster.host`` section. However,
+you need to beware that in this case ``pg_rewind`` will fail to execute on the
+standby cluster.

docs/tools_integration.rst

@@ -0,0 +1,64 @@
+.. _tools_integration:
+
+Integration with other tools
+============================
+
+Patroni is able to integrate with other tools in your stack. In this section you
+will find a list of examples, which although not an exhaustive list, might
+provide you with ideas on how Patroni can integrate with other tools.
+
+Barman
+------
+
+Patroni delivers an application named ``patroni_barman`` which has logic to
+communicate with ``pg-backup-api``, so you are able to perform Barman operations
+remotely.
+
+This application currently has a couple of sub-commands: ``recover`` and
+``config-switch``.
+
+patroni_barman recover
+^^^^^^^^^^^^^^^^^^^^^^
+
+The ``recover`` sub-command can be used as a custom bootstrap or custom replica
+creation method. You can find more information about that in
+:ref:`replica_imaging_and_bootstrap`.
+
+patroni_barman config-switch
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+The ``config-switch`` sub-command is designed to be used as an ``on_role_change``
+callback in Patroni. As an example, assume you are streaming WALs from your
+current primary to your Barman host. In the event of a failover in the cluster
+you might want to start streaming WALs from the new primary. You can accomplish
+this by using ``patroni_barman config-switch`` as the ``on_role_change`` callback.
+
+.. note::
+    That sub-command relies on the ``barman config-switch`` command, which is in
+    charge of overriding the configuration of a Barman server by applying a
+    pre-defined model on top of it. This command is available since Barman 3.10.
+    Please consult the Barman documentation for more details.
+
+This is an example of how you can configure Patroni to apply a configuration
+model in case this Patroni node is promoted to primary:
+
+.. code:: YAML
+
+    postgresql:
+        callbacks:
+            on_role_change: >
+                patroni_barman
+                    --api-url YOUR_API_URL
+                    config-switch
+                    --barman-server YOUR_BARMAN_SERVER_NAME
+                    --barman-model YOUR_BARMAN_MODEL_NAME
+                    --switch-when promoted
+
+.. note::
+    ``patroni_barman config-switch`` requires that you have both Barman and
+    ``pg-backup-api`` configured in the Barman host, so it can execute a remote
+    ``barman config-switch`` through the backup API. Also, it requires that you
+    have pre-configured Barman models to be applied. The above example uses a
+    subset of the available parameters. You can get more information running
+    ``patroni_barman config-switch --help``, and by consulting the Barman
+    documentation.

docs/yaml_configuration.rst

@@ -11,20 +11,49 @@ Global/Universal
 -  **namespace**: path within the configuration store where Patroni will keep information about the cluster. Default value: "/service"
 -  **scope**: cluster name
 
+.. _log_settings:
+
 Log
 ---
+-  **type**: sets the format of logs. Can be either **plain** or **json**. To use **json** format, you must have the :ref:`jsonlogger <extras>` installed. The default value is **plain**.
 -  **level**: sets the general logging level. Default value is **INFO** (see `the docs for Python logging <https://docs.python.org/3.6/library/logging.html#levels>`_)
 -  **traceback\_level**: sets the level where tracebacks will be visible. Default value is **ERROR**. Set it to **DEBUG** if you want to see tracebacks only if you enable **log.level=DEBUG**.
--  **format**: sets the log formatting string. Default value is **%(asctime)s %(levelname)s: %(message)s** (see `the LogRecord attributes <https://docs.python.org/3.6/library/logging.html#logrecord-attributes>`_)
+-  **format**: sets the log formatting string. If the log type is **plain**, the log format should be a string. Refer to
+   `the LogRecord attributes <https://docs.python.org/3.6/library/logging.html#logrecord-attributes>`_ for
+   available attributes. If the log type is **json**, the log format can be a list in addition to a string. Each list
+   item should correspond to LogRecord attributes. Be cautious that only the field name is required, and the **%(**
+   and **)** should be omitted. If you wish to print a log field with a different key name, use a dictionary where
+   the dictionary key is the log field, and the value is the name of the field you want to be printed in the log.
+   Default value is **%(asctime)s %(levelname)s: %(message)s**
 -  **dateformat**: sets the datetime formatting string. (see the `formatTime() documentation <https://docs.python.org/3.6/library/logging.html#logging.Formatter.formatTime>`_)
+-  **static_fields**: add additional fields to the log. This option is only available when the log type is set to **json**.
 -  **max\_queue\_size**: Patroni is using two-step logging. Log records are written into the in-memory queue and there is a separate thread which pulls them from the queue and writes to stderr or file. The maximum size of the internal queue is limited by default by **1000** records, which is enough to keep logs for the past 1h20m.
 -  **dir**: Directory to write application logs to. The directory must exist and be writable by the user executing Patroni. If you set this value, the application will retain 4 25MB logs by default. You can tune those retention values with `file_num` and `file_size` (see below).
+-  **mode**: Permissions for log files (for example, ``0644``). If not specified, permissions will be set based on the current umask value.
 -  **file\_num**: The number of application logs to retain.
 -  **file\_size**: Size of patroni.log file (in bytes) that triggers a log rolling.
 -  **loggers**: This section allows redefining logging level per python module
 
    -  **patroni.postmaster: WARNING**
    -  **urllib3: DEBUG**
+-  **deduplicate_heartbeat_logs**: If set to ``true``, successive heartbeat logs that are identical shall not be output. Default value is ``false``.
+
+.. warning::
+   The time the HA loop executes at can be very valuable information in diagnosing failovers due to resource exhaustion and similar problems. When ``deduplicate_heartbeat_logs`` is set to ``true`` there will be no log generated for the HA loop execution (unless the leader changes) and hence this potentially useful information will not be available from the logs.
+
+Here is an example of how to config patroni to log in json format.
+
+.. code:: YAML
+
+   log:
+      type: json
+      format:
+         - message
+         - module
+         - asctime: '@timestamp'
+         - levelname: level
+      static_fields:
+         app: patroni
 
 .. _bootstrap_settings:
 
@@ -34,7 +63,7 @@ Bootstrap configuration
 .. note::
     Once Patroni has initialized the cluster for the first time and settings have been stored in the DCS, all future
     changes to the ``bootstrap.dcs`` section of the YAML configuration will not take any effect! If you want to change
-    them please use either ``patronictl edit-config`` or the Patroni :ref:`REST API <rest_api>`.
+    them please use either :ref:`patronictl_edit_config` or the Patroni :ref:`REST API <rest_api>`.
 
 -  **bootstrap**:
 
@@ -49,24 +78,8 @@ Bootstrap configuration
       -  **- data-checksums**: Must be enabled when pg_rewind is needed on 9.3.
       -  **- encoding: UTF8**: default encoding for new databases.
       -  **- locale: UTF8**: default locale for new databases.
-   -  **users**: Some additional users which need to be created after initializing new cluster, see :ref:`Bootstrap users configuration <bootstrap_users_configuration>` below.
    -  **post\_bootstrap** or **post\_init**: An additional script that will be executed after initializing the cluster. The script receives a connection string URL (with the cluster superuser as a user name). The PGPASSFILE variable is set to the location of pgpass file.
 
-.. _bootstrap_users_configuration:
-
-Bootstrap users configuration
-=============================
-
-Users which need to be created after initializing the cluster:
-
--  **admin**: the name of user
-
-  -  **password**: (optional) password for the user
-  -  **options**: list of options for CREATE USER statement
-
-    -  **- createrole**
-    -  **- createdb**
-
 .. _citus_settings:
 
 Citus
@@ -95,9 +108,9 @@ Most of the parameters are optional, but you have to specify one of the **host**
 -  **consistency**: (optional) Select consul consistency mode. Possible values are ``default``, ``consistent``, or ``stale`` (more details in `consul API reference <https://www.consul.io/api/features/consistency.html/>`__)
 -  **checks**: (optional) list of Consul health checks used for the session. By default an empty list is used.
 -  **register\_service**: (optional) whether or not to register a service with the name defined by the scope parameter and the tag master, primary, replica, or standby-leader depending on the node's role. Defaults to **false**.
--  **service\_tags**: (optional) additional static tags to add to the Consul service apart from the role (``master``/``primary``/``replica``/``standby-leader``). By default an empty list is used.
+-  **service\_tags**: (optional) additional static tags to add to the Consul service apart from the role (``primary``/``replica``/``standby-leader``). By default an empty list is used.
 -  **service\_check\_interval**: (optional) how often to perform health check against registered url. Defaults to '5s'.
--  **service\_check\_tls\_server\_name**: (optional) overide SNI host when connecting via TLS, see also `consul agent check API reference <https://www.consul.io/api-docs/agent/check#tlsservername>`__.
+-  **service\_check\_tls\_server\_name**: (optional) override SNI host when connecting via TLS, see also `consul agent check API reference <https://www.consul.io/api-docs/agent/check#tlsservername>`__.
 
 The ``token`` needs to have the following ACL permissions:
 
@@ -136,7 +149,7 @@ Etcdv3
 If you want that Patroni works with Etcd cluster via protocol version 3, you need to use the ``etcd3`` section in the Patroni configuration file. All configuration parameters are the same as for ``etcd``.
 
 .. warning::
-    Keys created with protocol version 2 are not visible with protocol version 3 and the other way around, therefore it is not possible to switch from ``etcd`` to ``etcd3`` just by updating Patroni config file.
+    Keys created with protocol version 2 are not visible with protocol version 3 and the other way around, therefore it is not possible to switch from ``etcd`` to ``etcd3`` just by updating Patroni config file. In addition, Patroni uses Etcd's gRPC-gateway (proxy) to communicate with the V3 API, which means that TLS common name authentication is not possible.
 
 
 ZooKeeper
@@ -149,6 +162,7 @@ ZooKeeper
 -  **key_password**: (optional) The client key password.
 -  **verify**: (optional) Whether to verify certificate or not. Defaults to ``true``.
 -  **set_acls**: (optional) If set, configure Kazoo to apply a default ACL to each ZNode that it creates. ACLs will assume 'x509' schema and should be specified as a dictionary with the principal as the key and one or more permissions as a list in the value.  Permissions may be one of ``CREATE``, ``READ``, ``WRITE``, ``DELETE`` or ``ADMIN``.  For example, ``set_acls: {CN=principal1: [CREATE, READ], CN=principal2: [ALL]}``.
+-  **auth_data**: (optional) Authentication credentials to use for the connection. Should be a dictionary in the form that `scheme` is the key and `credential` is the value. Defaults to empty dictionary.
 
 .. note::
     It is required to install ``kazoo>=2.6.0`` to support SSL.
@@ -168,11 +182,12 @@ Kubernetes
 -  **namespace**: (optional) Kubernetes namespace where Patroni pod is running. Default value is `default`.
 -  **labels**: Labels in format ``{label1: value1, label2: value2}``. These labels will be used to find existing objects (Pods and either Endpoints or ConfigMaps) associated with the current cluster. Also Patroni will set them on every object (Endpoint or ConfigMap) it creates.
 -  **scope\_label**: (optional) name of the label containing cluster name. Default value is `cluster-name`.
--  **role\_label**: (optional) name of the label containing role (master or replica or other custom value). Patroni will set this label on the pod it runs in. Default value is ``role``.
--  **leader\_label\_value**: (optional) value of the pod label when Postgres role is ``master``. Default value is ``master``.
+-  **bootstrap\_labels**: (optional) Labels in format ``{label1: value1, label2: value2}``. These labels will be assigned to a Patroni pod when its state is either ``initializing new cluster``, ``running custom bootstrap script``, ``starting after custom bootstrap`` or ``creating replica``.
+-  **role\_label**: (optional) name of the label containing role (`primary`, `replica`, or other custom value). Patroni will set this label on the pod it runs in. Default value is ``role``.
+-  **leader\_label\_value**: (optional) value of the pod label when Postgres role is ``primary``. Default value is ``primary``.
 -  **follower\_label\_value**: (optional) value of the pod label when Postgres role is ``replica``. Default value is ``replica``.
--  **standby\_leader\_label\_value**: (optional) value of the pod label when Postgres role is ``standby-leader``. Default value is ``standby-leader``.
--  **tmp_\role\_label**: (optional) name of the temporary label containing role (master or replica). Value of this label will always use the default of corresponding role. Set only when necessary.
+-  **standby\_leader\_label\_value**: (optional) value of the pod label when Postgres role is ``standby_leader``. Default value is ``primary``.
+-  **tmp\_role\_label**: (optional) name of the temporary label containing role (`primary` or `replica`). Value of this label will always use the default of corresponding role. Set only when necessary.
 -  **use\_endpoints**: (optional) if set to true, Patroni will use Endpoints instead of ConfigMaps to run leader elections and keep cluster state.
 -  **pod\_ip**: (optional) IP address of the pod Patroni is running in. This value is required when `use_endpoints` is enabled and is used to populate the leader endpoint subsets when the pod's PostgreSQL is promoted.
 -  **ports**: (optional) if the Service object has the name for the port, the same name must appear in the Endpoint object, otherwise service won't work. For example, if your service is defined as ``{Kind: Service, spec: {ports: [{name: postgresql, port: 5432, targetPort: 5432}]}}``, then you have to set ``kubernetes.ports: [{"name": "postgresql", "port": 5432}]`` and Patroni will use it for updating subsets of the leader Endpoint. This parameter is used only if `kubernetes.use_endpoints` is set.
@@ -229,9 +244,10 @@ PostgreSQL
          -  **sslkey**: (optional) maps to the `sslkey <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLKEY>`__ connection parameter, which specifies the location of the secret key used with the client's certificate.
          -  **sslpassword**: (optional) maps to the `sslpassword <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLPASSWORD>`__ connection parameter, which specifies the password for the secret key specified in ``sslkey``.
          -  **sslcert**: (optional) maps to the `sslcert <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLCERT>`__ connection parameter, which specifies the location of the client certificate.
-         -  **sslrootcert**: (optional) maps to the `sslrootcert <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLROOTCERT>`__ connection parameter, which specifies the location of a file containing one ore more certificate authorities (CA) certificates that the client will use to verify a server's certificate.
+         -  **sslrootcert**: (optional) maps to the `sslrootcert <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLROOTCERT>`__ connection parameter, which specifies the location of a file containing one or more certificate authorities (CA) certificates that the client will use to verify a server's certificate.
          -  **sslcrl**: (optional) maps to the `sslcrl <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLCRL>`__ connection parameter, which specifies the location of a file containing a certificate revocation list. A client will reject connecting to any server that has a certificate present in this list.
          -  **sslcrldir**: (optional) maps to the `sslcrldir <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLCRLDIR>`__ connection parameter, which specifies the location of a directory with files containing a certificate revocation list. A client will reject connecting to any server that has a certificate present in this list.
+         -  **sslnegotiation**: (optional) maps to the `sslnegotiation <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLNEGOTIATION>`__ connection parameter, which controls how SSL encryption is negotiated with the server, if SSL is used.
          -  **gssencmode**: (optional) maps to the `gssencmode <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-GSSENCMODE>`__ connection parameter, which determines whether or with what priority a secure GSS TCP/IP connection will be negotiated with the server
          -  **channel_binding**: (optional) maps to the `channel_binding <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-CHANNEL-BINDING>`__ connection parameter, which controls the client's use of channel binding.
       -  **replication**:
@@ -242,9 +258,10 @@ PostgreSQL
          -  **sslkey**: (optional) maps to the `sslkey <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLKEY>`__ connection parameter, which specifies the location of the secret key used with the client's certificate.
          -  **sslpassword**: (optional) maps to the `sslpassword <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLPASSWORD>`__ connection parameter, which specifies the password for the secret key specified in ``sslkey``.
          -  **sslcert**: (optional) maps to the `sslcert <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLCERT>`__ connection parameter, which specifies the location of the client certificate.
-         -  **sslrootcert**: (optional) maps to the `sslrootcert <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLROOTCERT>`__ connection parameter, which specifies the location of a file containing one ore more certificate authorities (CA) certificates that the client will use to verify a server's certificate.
+         -  **sslrootcert**: (optional) maps to the `sslrootcert <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLROOTCERT>`__ connection parameter, which specifies the location of a file containing one or more certificate authorities (CA) certificates that the client will use to verify a server's certificate.
          -  **sslcrl**: (optional) maps to the `sslcrl <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLCRL>`__ connection parameter, which specifies the location of a file containing a certificate revocation list. A client will reject connecting to any server that has a certificate present in this list.
          -  **sslcrldir**: (optional) maps to the `sslcrldir <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLCRLDIR>`__ connection parameter, which specifies the location of a directory with files containing a certificate revocation list. A client will reject connecting to any server that has a certificate present in this list.
+         -  **sslnegotiation**: (optional) maps to the `sslnegotiation <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLNEGOTIATION>`__ connection parameter, which controls how SSL encryption is negotiated with the server, if SSL is used.
          -  **gssencmode**: (optional) maps to the `gssencmode <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-GSSENCMODE>`__ connection parameter, which determines whether or with what priority a secure GSS TCP/IP connection will be negotiated with the server
          -  **channel_binding**: (optional) maps to the `channel_binding <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-CHANNEL-BINDING>`__ connection parameter, which controls the client's use of channel binding.
       -  **rewind**:
@@ -255,9 +272,10 @@ PostgreSQL
          -  **sslkey**: (optional) maps to the `sslkey <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLKEY>`__ connection parameter, which specifies the location of the secret key used with the client's certificate.
          -  **sslpassword**: (optional) maps to the `sslpassword <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLPASSWORD>`__ connection parameter, which specifies the password for the secret key specified in ``sslkey``.
          -  **sslcert**: (optional) maps to the `sslcert <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLCERT>`__ connection parameter, which specifies the location of the client certificate.
-         -  **sslrootcert**: (optional) maps to the `sslrootcert <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLROOTCERT>`__ connection parameter, which specifies the location of a file containing one ore more certificate authorities (CA) certificates that the client will use to verify a server's certificate.
+         -  **sslrootcert**: (optional) maps to the `sslrootcert <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLROOTCERT>`__ connection parameter, which specifies the location of a file containing one or more certificate authorities (CA) certificates that the client will use to verify a server's certificate.
          -  **sslcrl**: (optional) maps to the `sslcrl <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLCRL>`__ connection parameter, which specifies the location of a file containing a certificate revocation list. A client will reject connecting to any server that has a certificate present in this list.
          -  **sslcrldir**: (optional) maps to the `sslcrldir <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLCRLDIR>`__ connection parameter, which specifies the location of a directory with files containing a certificate revocation list. A client will reject connecting to any server that has a certificate present in this list.
+         -  **sslnegotiation**: (optional) maps to the `sslnegotiation <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLNEGOTIATION>`__ connection parameter, which controls how SSL encryption is negotiated with the server, if SSL is used.
          -  **gssencmode**: (optional) maps to the `gssencmode <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-GSSENCMODE>`__ connection parameter, which determines whether or with what priority a secure GSS TCP/IP connection will be negotiated with the server
          -  **channel_binding**: (optional) maps to the `channel_binding <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-CHANNEL-BINDING>`__ connection parameter, which controls the client's use of channel binding.
 
@@ -291,7 +309,7 @@ PostgreSQL
    -  **pgpass**: path to the `.pgpass <https://www.postgresql.org/docs/current/static/libpq-pgpass.html>`__ password file. Patroni creates this file before executing pg\_basebackup, the post_init script and under some other circumstances. The location must be writable by Patroni.
    -  **recovery\_conf**: additional configuration settings written to recovery.conf when configuring follower.
    -  **custom\_conf** : path to an optional custom ``postgresql.conf`` file, that will be used in place of ``postgresql.base.conf``. The file must exist on all cluster nodes, be readable by PostgreSQL and will be included from its location on the real ``postgresql.conf``. Note that Patroni will not monitor this file for changes, nor backup it. However, its settings can still be overridden by Patroni's own configuration facilities - see :ref:`dynamic configuration <patroni_configuration>` for details.
-   -  **parameters**: list of configuration settings for Postgres. Many of these are required for replication to work.
+   -  **parameters**: configuration parameters (GUCs) for Postgres in format ``{ssl: "on", ssl_cert_file: "cert_file"}``.
    -  **pg\_hba**: list of lines that Patroni will use to generate ``pg_hba.conf``. Patroni ignores this parameter if ``hba_file`` PostgreSQL parameter is set to a non-default value. Together with :ref:`dynamic configuration <dynamic_configuration>` this parameter simplifies management of ``pg_hba.conf``.
 
       -  **- host all all 0.0.0.0/0 md5**
@@ -301,7 +319,7 @@ PostgreSQL
       -  **- mapname1 systemname1 pguser1**
       -  **- mapname1 systemname2 pguser2**
    -  **pg\_ctl\_timeout**: How long should pg_ctl wait when doing ``start``, ``stop`` or ``restart``. Default value is 60 seconds.
-   -  **use\_pg\_rewind**: try to use pg\_rewind on the former leader when it joins cluster as a replica.
+   -  **use\_pg\_rewind**: try to use pg\_rewind on the former leader when it joins cluster as a replica. Either the cluster must be initialized with ``data page checksums`` (``--data-checksums`` option for ``initdb``) and/or ``wal_log_hints`` must be set to ``on``, or ``pg_rewind`` will not work.
    -  **remove\_data\_directory\_on\_rewind\_failure**: If this option is enabled, Patroni will remove the PostgreSQL data directory and recreate the replica. Otherwise it will try to follow the new leader. Default value is **false**.
    -  **remove\_data\_directory\_on\_diverged\_timelines**: Patroni will remove the PostgreSQL data directory and recreate the replica if it notices that timelines are diverging and the former primary can not start streaming from the new primary. This option is useful when ``pg_rewind`` can not be used. While performing timelines divergence check on PostgreSQL v10 and older Patroni will try to connect with replication credential to the "postgres" database. Hence, such access should be allowed in the pg_hba.conf. Default value is **false**.
    -  **replica\_method**: for each create_replica_methods other than basebackup, you would add a configuration section of the same name. At a minimum, this should include "command" with a full path to the actual script to be executed. Other configuration parameters will be passed along to the script in the form "parameter=value".
@@ -366,10 +384,10 @@ CTL
 
    -  **authentication**:
 
-      -  **username**: Basic-auth username for accessing protected REST API endpoints. If not provided patronictl will use the value provided for REST API "username" parameter.
-      -  **password**: Basic-auth password for accessing protected REST API endpoints. If not provided patronictl will use the value provided for REST API "password" parameter.
+      -  **username**: Basic-auth username for accessing protected REST API endpoints. If not provided :ref:`patronictl` will use the value provided for REST API "username" parameter.
+      -  **password**: Basic-auth password for accessing protected REST API endpoints. If not provided :ref:`patronictl` will use the value provided for REST API "password" parameter.
    -  **insecure**: Allow connections to REST API without verifying SSL certs.
-   -  **cacert**: Specifies the file with the CA_BUNDLE file or directory with certificates of trusted CAs to use while verifying REST API SSL certs. If not provided patronictl will use the value provided for REST API "cafile" parameter.
+   -  **cacert**: Specifies the file with the CA_BUNDLE file or directory with certificates of trusted CAs to use while verifying REST API SSL certs. If not provided :ref:`patronictl` will use the value provided for REST API "cafile" parameter.
    -  **certfile**: Specifies the file with the client certificate in the PEM format.
    -  **keyfile**: Specifies the file with the client secret key in the PEM format.
    -  **keyfile\_password**: Specifies a password for decrypting the client keyfile.
@@ -384,11 +402,17 @@ Watchdog
 
 Tags
 ----
--  **nofailover**: ``true`` or ``false``, controls whether this node is allowed to participate in the leader race and become a leader. Defaults to ``false``
 -  **clonefrom**: ``true`` or ``false``. If set to ``true`` other nodes might prefer to use this node for bootstrap (take ``pg_basebackup`` from). If there are several nodes with ``clonefrom`` tag set to ``true`` the node to bootstrap from will be chosen randomly. The default value is ``false``.
 -  **noloadbalance**: ``true`` or ``false``. If set to ``true`` the node will return HTTP Status Code 503 for the ``GET /replica`` REST API health-check and therefore will be excluded from the load-balancing. Defaults to ``false``.
--  **replicatefrom**: The IP address/hostname of another replica. Used to support cascading replication.
+-  **replicatefrom**: The name of another replica to replicate from. Used to support cascading replication.
 -  **nosync**: ``true`` or ``false``. If set to ``true`` the node will never be selected as a synchronous replica.
+-  **sync_priority**: integer, controls the priority this node should have during synchronous replica selection when ``synchronous_mode`` is set to ``on``. Nodes with higher priority will be preferred over lower-priority nodes. If the ``sync_priority`` is 0 or negative - such node is not allowed to be written to ``synchronous_standby_names`` PostgreSQL parameter (similar to ``nosync: true``). Keep in mind, that this parameter has the opposite meaning to ``sync_priority`` value reported in ``pg_stat_replication`` view.
+-  **nofailover**: ``true`` or ``false``, controls whether this node is allowed to participate in the leader race and become a leader. Defaults to ``false``, meaning this node _can_ participate in leader races. 
+-  **failover_priority**: integer, controls the priority this node should have during failover. Nodes with higher priority will be preferred over lower-priority nodes if they received/replayed the same amount of WAL. However, nodes with higher values of receive/replay LSN are preferred regardless of their priority. If the ``failover_priority`` is 0 or negative - such node is not allowed to participate in the leader race and to become a leader (similar to ``nofailover: true``).
+-  **nostream**: ``true`` or ``false``. If set to ``true`` the node will not use replication protocol to stream WAL. It will rely instead on archive recovery (if ``restore_command`` is configured) and ``pg_wal``/``pg_xlog`` polling. It also disables copying and synchronization of permanent logical replication slots on the node itself and all its cascading replicas. Setting this tag on primary node has no effect.
+
+.. warning::
+   Provide only one of ``nofailover`` or ``failover_priority``. Providing ``nofailover: true`` is the same as ``failover_priority: 0``, and providing ``nofailover: false`` will give the node priority 1. 
 
 In addition to these predefined tags, you can also add your own ones:
 
@@ -397,4 +421,4 @@ In addition to these predefined tags, you can also add your own ones:
 -  **key3**: ``1.4``
 -  **key4**: ``"RandomString"``
 
-Tags are visible in the :ref:`REST API <rest_api>` and ``patronictl list`` You can also check for an instance health using these tags. If the tag isn't defined for an instance, or if the respective value doesn't match the querying value, it will return HTTP Status Code 503.
+Tags are visible in the :ref:`REST API <rest_api>` and :ref:`patronictl_list` You can also check for an instance health using these tags. If the tag isn't defined for an instance, or if the respective value doesn't match the querying value, it will return HTTP Status Code 503.

extras/startup-scripts/patroni.service

@@ -6,7 +6,7 @@ Description=Runners to orchestrate a high-availability PostgreSQL
 After=syslog.target network.target
 
 [Service]
-Type=simple
+Type=notify
 
 User=postgres
 Group=postgres

features/Dockerfile

@@ -27,8 +27,8 @@ RUN set -ex \
     && apt-get update \
     && apt-get reinstall init-system-helpers \
     && apt-get install -y \
-      python3-pip \
       python3-dev \
+      python3-venv \
       rsync \
       curl \
       gcc \
@@ -40,7 +40,9 @@ RUN set -ex \
       net-tools \
       iputils-ping \
     && rm -rf /var/cache/apt \
-    && python3 -m pip install --no-cache-dir tox \
+    \
+    && python3 -m venv /tox \
+    && /tox/bin/pip install --no-cache-dir tox>=4 \
     \
     && mkdir -p "$PGHOME" \
     && sed -i "s|/var/lib/postgresql.*|$PGHOME:/bin/bash|" /etc/passwd \
@@ -50,6 +52,7 @@ RUN set -ex \
     && curl -sL "$ETCDURL/etcd-v$ETCDVERSION-linux-$(dpkg --print-architecture).tar.gz" \
        | tar xz -C /usr/local/bin --strip=1 --wildcards --no-anchored etcd etcdctl
 
+ENV PATH="/tox/bin:$PATH"
 
 # This Dockerfile syntax only works with docker buildx and the syntax
 # line at the top of this file.

features/archive-restore.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python
-import os
 import argparse
+import os
 import shutil
 
 if __name__ == "__main__":

features/backup_create.py

@@ -3,12 +3,18 @@ import argparse
 import subprocess
 import sys
 
+from time import sleep
+
 if __name__ == "__main__":
     parser = argparse.ArgumentParser()
     parser.add_argument("--datadir", required=True)
     parser.add_argument("--dbname", required=True)
     parser.add_argument("--walmethod", required=True, choices=("fetch", "stream", "none"))
+    parser.add_argument("--sleep", required=False, type=int)
     args, _ = parser.parse_known_args()
 
+    if args.sleep:
+        sleep(args.sleep)
+
     walmethod = ["-X", args.walmethod] if args.walmethod != "none" else []
     sys.exit(subprocess.call(["pg_basebackup", "-D", args.datadir, "-c", "fast", "-d", args.dbname] + walmethod))

features/backup_restore.py

@@ -2,10 +2,17 @@
 import argparse
 import shutil
 
+from time import sleep
+
 if __name__ == "__main__":
     parser = argparse.ArgumentParser()
     parser.add_argument("--datadir", required=True)
     parser.add_argument("--sourcedir", required=True)
+    parser.add_argument("--test-argument", required=True)
+    parser.add_argument("--sleep", required=False, type=int)
     args, _ = parser.parse_known_args()
 
+    if args.sleep:
+        sleep(args.sleep)
+
     shutil.copytree(args.sourcedir, args.datadir)

features/basic_replication.feature

@@ -2,57 +2,57 @@ Feature: basic replication
   We should check that the basic bootstrapping, replication and failover works.
 
   Scenario: check replication of a single table
-    Given I start postgres0
-    Then postgres0 is a leader after 10 seconds
+    Given I start postgres-0
+    Then postgres-0 is a leader after 10 seconds
     And there is a non empty initialize key in DCS after 15 seconds
     When I issue a PATCH request to http://127.0.0.1:8008/config with {"ttl": 20, "synchronous_mode": true}
     Then I receive a response code 200
-    When I start postgres1
-    And I configure and start postgres2 with a tag replicatefrom postgres0
-    And "sync" key in DCS has leader=postgres0 after 20 seconds
-    And I add the table foo to postgres0
-    Then table foo is present on postgres1 after 20 seconds
-    Then table foo is present on postgres2 after 20 seconds
+    When I start postgres-1
+    And I configure and start postgres-2 with a tag replicatefrom postgres-0
+    And "sync" key in DCS has leader=postgres-0 after 20 seconds
+    And I add the table foo to postgres-0
+    Then table foo is present on postgres-1 after 20 seconds
+    Then table foo is present on postgres-2 after 20 seconds
 
   Scenario: check restart of sync replica
-    Given I shut down postgres2
-    Then "sync" key in DCS has sync_standby=postgres1 after 5 seconds
-    When I start postgres2
-    And I shut down postgres1
-    Then "sync" key in DCS has sync_standby=postgres2 after 10 seconds
-    When I start postgres1
-    Then "members/postgres1" key in DCS has state=running after 10 seconds
+    Given I shut down postgres-2
+    Then "sync" key in DCS has sync_standby=postgres-1 after 5 seconds
+    When I start postgres-2
+    And I shut down postgres-1
+    Then "sync" key in DCS has sync_standby=postgres-2 after 10 seconds
+    When I start postgres-1
+    Then "members/postgres-1" key in DCS has state=running after 10 seconds
     And Status code on GET http://127.0.0.1:8010/sync is 200 after 3 seconds
     And Status code on GET http://127.0.0.1:8009/async is 200 after 3 seconds
 
   Scenario: check stuck sync replica
     Given I issue a PATCH request to http://127.0.0.1:8008/config with {"pause": true, "maximum_lag_on_syncnode": 15000000, "postgresql": {"parameters": {"synchronous_commit": "remote_apply"}}}
     Then I receive a response code 200
-    And I create table on postgres0
-    And table mytest is present on postgres1 after 2 seconds
-    And table mytest is present on postgres2 after 2 seconds
-    When I pause wal replay on postgres2
-    And I load data on postgres0
-    Then "sync" key in DCS has sync_standby=postgres1 after 15 seconds
-    And I resume wal replay on postgres2
+    And I create table on postgres-0
+    And table mytest is present on postgres-1 after 2 seconds
+    And table mytest is present on postgres-2 after 2 seconds
+    When I pause wal replay on postgres-2
+    And I load data on postgres-0
+    Then "sync" key in DCS has sync_standby=postgres-1 after 15 seconds
+    And I resume wal replay on postgres-2
     And Status code on GET http://127.0.0.1:8009/sync is 200 after 3 seconds
     And Status code on GET http://127.0.0.1:8010/async is 200 after 3 seconds
     When I issue a PATCH request to http://127.0.0.1:8008/config with {"pause": null, "maximum_lag_on_syncnode": -1, "postgresql": {"parameters": {"synchronous_commit": "on"}}}
     Then I receive a response code 200
-    And I drop table on postgres0
+    And I drop table on postgres-0
 
   Scenario: check multi sync replication
     Given I issue a PATCH request to http://127.0.0.1:8008/config with {"synchronous_node_count": 2}
     Then I receive a response code 200
-    Then "sync" key in DCS has sync_standby=postgres1,postgres2 after 10 seconds
+    Then "sync" key in DCS has sync_standby=postgres-1,postgres-2 after 10 seconds
     And Status code on GET http://127.0.0.1:8010/sync is 200 after 3 seconds
     And Status code on GET http://127.0.0.1:8009/sync is 200 after 3 seconds
     When I issue a PATCH request to http://127.0.0.1:8008/config with {"synchronous_node_count": 1}
     Then I receive a response code 200
-    And I shut down postgres1
-    Then "sync" key in DCS has sync_standby=postgres2 after 10 seconds
-    When I start postgres1
-    Then "members/postgres1" key in DCS has state=running after 10 seconds
+    And I shut down postgres-1
+    Then "sync" key in DCS has sync_standby=postgres-2 after 10 seconds
+    When I start postgres-1
+    Then "members/postgres-1" key in DCS has state=running after 10 seconds
     And Status code on GET http://127.0.0.1:8010/sync is 200 after 3 seconds
     And Status code on GET http://127.0.0.1:8009/async is 200 after 3 seconds
 
@@ -60,26 +60,26 @@ Feature: basic replication
     Given I run patronictl.py pause batman
     Then I receive a response returncode 0
     When I sleep for 2 seconds
-    And I shut down postgres0
+    And I shut down postgres-0
     And I run patronictl.py resume batman
     Then I receive a response returncode 0
-    And postgres2 role is the primary after 24 seconds
+    And postgres-2 role is the primary after 24 seconds
     And Response on GET http://127.0.0.1:8010/history contains recovery after 10 seconds
-    And there is a postgres2_cb.log with "on_role_change master batman" in postgres2 data directory
+    And there is a postgres-2_cb.log with "on_role_change primary batman" in postgres-2 data directory
     When I issue a PATCH request to http://127.0.0.1:8010/config with {"synchronous_mode": null, "master_start_timeout": 0}
     Then I receive a response code 200
-    When I add the table bar to postgres2
-    Then table bar is present on postgres1 after 20 seconds
+    When I add the table bar to postgres-2
+    Then table bar is present on postgres-1 after 20 seconds
     And Response on GET http://127.0.0.1:8010/config contains master_start_timeout after 10 seconds
 
   Scenario: check rejoin of the former primary with pg_rewind
-    Given I add the table splitbrain to postgres0
-    And I start postgres0
-    Then postgres0 role is the secondary after 20 seconds
-    When I add the table buz to postgres2
-    Then table buz is present on postgres0 after 20 seconds
+    Given I add the table splitbrain to postgres-0
+    And I start postgres-0
+    Then postgres-0 role is the secondary after 20 seconds
+    When I add the table buz to postgres-2
+    Then table buz is present on postgres-0 after 20 seconds
 
   @reject-duplicate-name
   Scenario: check graceful rejection when two nodes have the same name
-    Given I start duplicate postgres0 on port 8011
-    Then there is a "Can't start; there is already a node named 'postgres0' running" CRITICAL in the dup-postgres0 patroni log
+    Given I start duplicate postgres-0 on port 8011
+    Then there is one of ["Can't start; there is already a node named 'postgres-0' running"] CRITICAL in the dup-postgres-0 patroni log after 5 seconds

features/bootstrap_labels.feature

@@ -0,0 +1,22 @@
+Feature: bootstrap labels
+  Check that user-configurable bootstrap labels are set and removed with state change
+
+Scenario: check label for cluster bootstrap
+    When I start postgres-0
+    Then postgres-0 is a leader after 10 seconds
+    When I start postgres-1 in a cluster batman1 as a long-running clone of postgres-0
+    Then "members/postgres-1" key in DCS has state=running custom bootstrap script after 20 seconds
+    And postgres-1 is labeled with "foo"
+    And postgres-1 is a leader of batman1 after 20 seconds
+
+Scenario: check label for replica bootstrap
+    When I do a backup of postgres-1
+    And I start postgres-2 in cluster batman1 using long-running backup_restore
+    Then "members/postgres-2" key in DCS has state=creating replica after 20 seconds
+    And postgres-2 is labeled with "foo"
+
+Scenario: check bootstrap label is removed
+    Given "members/postgres-1" key in DCS has state=running after 2 seconds
+    And  "members/postgres-2" key in DCS has state=running after 20 seconds
+    Then postgres-1 is not labeled with "foo"
+    And postgres-2 is not labeled with "foo"

features/callback2.py

@@ -1,5 +1,6 @@
 #!/usr/bin/env python
 
 import sys
+
 with open("data/{0}/{0}_cb.log".format(sys.argv[1]), "a+") as log:
     log.write(" ".join(sys.argv[-3:]) + "\n")

features/cascading_replication.feature

@@ -2,13 +2,13 @@ Feature: cascading replication
 	We should check that patroni can do base backup and streaming from the replica
 
 Scenario: check a base backup and streaming replication from a replica
-	Given I start postgres0
-	And postgres0 is a leader after 10 seconds
-	And I configure and start postgres1 with a tag clonefrom true
-	And replication works from postgres0 to postgres1 after 20 seconds
-	And I create label with "postgres0" in postgres0 data directory
-	And I create label with "postgres1" in postgres1 data directory
-	And "members/postgres1" key in DCS has state=running after 12 seconds
-	And I configure and start postgres2 with a tag replicatefrom postgres1
-	Then replication works from postgres0 to postgres2 after 30 seconds
-	And there is a label with "postgres1" in postgres2 data directory
+	Given I start postgres-0
+	And postgres-0 is a leader after 10 seconds
+	And I configure and start postgres-1 with a tag clonefrom true
+	And replication works from postgres-0 to postgres-1 after 20 seconds
+	And I create label with "postgres-0" in postgres-0 data directory
+	And I create label with "postgres-1" in postgres-1 data directory
+	And "members/postgres-1" key in DCS has state=running after 12 seconds
+	And I configure and start postgres-2 with a tag replicatefrom postgres-1
+	Then replication works from postgres-0 to postgres-2 after 30 seconds
+	And there is a label with "postgres-1" in postgres-2 data directory

features/citus.feature

@@ -2,72 +2,79 @@ Feature: citus
   We should check that coordinator discovers and registers workers and clients don't have errors when worker cluster switches over
 
   Scenario: check that worker cluster is registered in the coordinator
-    Given I start postgres0 in citus group 0
-    And I start postgres2 in citus group 1
-    Then postgres0 is a leader in a group 0 after 10 seconds
-    And postgres2 is a leader in a group 1 after 10 seconds
-    When I start postgres1 in citus group 0
-    And I start postgres3 in citus group 1
-    Then replication works from postgres0 to postgres1 after 15 seconds
-    Then replication works from postgres2 to postgres3 after 15 seconds
-    And postgres0 is registered in the postgres0 as the primary in group 0 after 5 seconds
-    And postgres2 is registered in the postgres0 as the primary in group 1 after 5 seconds
+    Given I start postgres-0 in citus group 0
+    And I start postgres-2 in citus group 1
+    Then postgres-0 is a leader in a group 0 after 10 seconds
+    And postgres-2 is a leader in a group 1 after 10 seconds
+    When I start postgres-1 in citus group 0
+    And I start postgres-3 in citus group 1
+    Then replication works from postgres-0 to postgres-1 after 15 seconds
+    Then replication works from postgres-2 to postgres-3 after 15 seconds
+    And postgres-0 is registered in the postgres-0 as the primary in group 0 after 5 seconds
+    And postgres-1 is registered in the postgres-0 as the secondary in group 0 after 5 seconds
+    And postgres-2 is registered in the postgres-0 as the primary in group 1 after 5 seconds
+    And postgres-3 is registered in the postgres-0 as the secondary in group 1 after 5 seconds
 
   Scenario: coordinator failover updates pg_dist_node
-    Given I run patronictl.py failover batman --group 0 --candidate postgres1 --force
-    Then postgres1 role is the primary after 10 seconds
-    And "members/postgres0" key in a group 0 in DCS has state=running after 15 seconds
-    And replication works from postgres1 to postgres0 after 15 seconds
-    And postgres1 is registered in the postgres2 as the primary in group 0 after 5 seconds
-    And "sync" key in a group 0 in DCS has sync_standby=postgres0 after 15 seconds
-    When I run patronictl.py switchover batman --group 0 --candidate postgres0 --force
-    Then postgres0 role is the primary after 10 seconds
-    And replication works from postgres0 to postgres1 after 15 seconds
-    And postgres0 is registered in the postgres2 as the primary in group 0 after 5 seconds
-    And "sync" key in a group 0 in DCS has sync_standby=postgres1 after 15 seconds
+    Given I run patronictl.py failover batman --group 0 --candidate postgres-1 --force
+    Then postgres-1 role is the primary after 10 seconds
+    And "members/postgres-0" key in a group 0 in DCS has state=running after 15 seconds
+    And replication works from postgres-1 to postgres-0 after 15 seconds
+    And postgres-1 is registered in the postgres-2 as the primary in group 0 after 5 seconds
+    And postgres-0 is registered in the postgres-2 as the secondary in group 0 after 15 seconds
+    And "sync" key in a group 0 in DCS has sync_standby=postgres-0 after 15 seconds
+    When I run patronictl.py switchover batman --group 0 --candidate postgres-0 --force
+    Then postgres-0 role is the primary after 10 seconds
+    And replication works from postgres-0 to postgres-1 after 15 seconds
+    And postgres-0 is registered in the postgres-2 as the primary in group 0 after 5 seconds
+    And postgres-1 is registered in the postgres-2 as the secondary in group 0 after 15 seconds
+    And "sync" key in a group 0 in DCS has sync_standby=postgres-1 after 15 seconds
 
   Scenario: worker switchover doesn't break client queries on the coordinator
-    Given I create a distributed table on postgres0
-    And I start a thread inserting data on postgres0
+    Given I create a distributed table on postgres-0
+    And I start a thread inserting data on postgres-0
     When I run patronictl.py switchover batman --group 1 --force
     Then I receive a response returncode 0
-    And postgres3 role is the primary after 10 seconds
-    And "members/postgres2" key in a group 1 in DCS has state=running after 15 seconds
-    And replication works from postgres3 to postgres2 after 15 seconds
-    And postgres3 is registered in the postgres0 as the primary in group 1 after 5 seconds
-    And "sync" key in a group 1 in DCS has sync_standby=postgres2 after 15 seconds
+    And postgres-3 role is the primary after 10 seconds
+    And "members/postgres-2" key in a group 1 in DCS has state=running after 15 seconds
+    And replication works from postgres-3 to postgres-2 after 15 seconds
+    And postgres-3 is registered in the postgres-0 as the primary in group 1 after 5 seconds
+    And postgres-2 is registered in the postgres-0 as the secondary in group 1 after 15 seconds
+    And "sync" key in a group 1 in DCS has sync_standby=postgres-2 after 15 seconds
     And a thread is still alive
     When I run patronictl.py switchover batman --group 1 --force
     Then I receive a response returncode 0
-    And postgres2 role is the primary after 10 seconds
-    And replication works from postgres2 to postgres3 after 15 seconds
-    And postgres2 is registered in the postgres0 as the primary in group 1 after 5 seconds
-    And "sync" key in a group 1 in DCS has sync_standby=postgres3 after 15 seconds
+    And postgres-2 role is the primary after 10 seconds
+    And replication works from postgres-2 to postgres-3 after 15 seconds
+    And postgres-2 is registered in the postgres-0 as the primary in group 1 after 5 seconds
+    And postgres-3 is registered in the postgres-0 as the secondary in group 1 after 15 seconds
+    And "sync" key in a group 1 in DCS has sync_standby=postgres-3 after 15 seconds
     And a thread is still alive
     When I stop a thread
-    Then a distributed table on postgres0 has expected rows
+    Then a distributed table on postgres-0 has expected rows
 
   Scenario: worker primary restart doesn't break client queries on the coordinator
-    Given I cleanup a distributed table on postgres0
-    And I start a thread inserting data on postgres0
-    When I run patronictl.py restart batman postgres2 --group 1 --force
+    Given I cleanup a distributed table on postgres-0
+    And I start a thread inserting data on postgres-0
+    When I run patronictl.py restart batman postgres-2 --group 1 --force
     Then I receive a response returncode 0
-    And postgres2 role is the primary after 10 seconds
-    And replication works from postgres2 to postgres3 after 15 seconds
-    And postgres2 is registered in the postgres0 as the primary in group 1 after 5 seconds
+    And postgres-2 role is the primary after 10 seconds
+    And replication works from postgres-2 to postgres-3 after 15 seconds
+    And postgres-2 is registered in the postgres-0 as the primary in group 1 after 5 seconds
+    And postgres-3 is registered in the postgres-0 as the secondary in group 1 after 15 seconds
     And a thread is still alive
     When I stop a thread
-    Then a distributed table on postgres0 has expected rows
+    Then a distributed table on postgres-0 has expected rows
 
   Scenario: check that in-flight transaction is rolled back after timeout when other workers need to change pg_dist_node
-    Given I start postgres4 in citus group 2
-    Then postgres4 is a leader in a group 2 after 10 seconds
-    And "members/postgres4" key in a group 2 in DCS has role=master after 3 seconds
+    Given I start postgres-4 in citus group 2
+    Then postgres-4 is a leader in a group 2 after 10 seconds
+    And "members/postgres-4" key in a group 2 in DCS has role=primary after 3 seconds
     When I run patronictl.py edit-config batman --group 2 -s ttl=20 --force
     Then I receive a response returncode 0
     And I receive a response output "+ttl: 20"
-    Then postgres4 is registered in the postgres2 as the primary in group 2 after 5 seconds
-    When I shut down postgres4
-    Then There is a transaction in progress on postgres0 changing pg_dist_node
-    When I run patronictl.py restart batman postgres2 --group 1 --force
+    Then postgres-4 is registered in the postgres-2 as the primary in group 2 after 5 seconds
+    When I shut down postgres-4
+    Then there is a transaction in progress on postgres-0 changing pg_dist_node after 5 seconds
+    When I run patronictl.py restart batman postgres-2 --group 1 --force
     Then a transaction finishes in 20 seconds

features/custom_bootstrap.feature

@@ -2,16 +2,16 @@ Feature: custom bootstrap
     We should check that patroni can bootstrap a new cluster from a backup
 
 Scenario: clone existing cluster using pg_basebackup
-    Given I start postgres0
-    Then postgres0 is a leader after 10 seconds
-    When I add the table foo to postgres0
-    And I start postgres1 in a cluster batman1 as a clone of postgres0
-    Then postgres1 is a leader of batman1 after 10 seconds
-    Then table foo is present on postgres1 after 10 seconds
+    Given I start postgres-0
+    Then postgres-0 is a leader after 10 seconds
+    When I add the table foo to postgres-0
+    And I start postgres-1 in a cluster batman1 as a clone of postgres-0
+    Then postgres-1 is a leader of batman1 after 10 seconds
+    Then table foo is present on postgres-1 after 10 seconds
 
 Scenario: make a backup and do a restore into a new cluster
-    Given I add the table bar to postgres1
-    And I do a backup of postgres1
-    When I start postgres2 in a cluster batman2 from backup
-    Then postgres2 is a leader of batman2 after 30 seconds
-    And table bar is present on postgres2 after 10 seconds
+    Given I add the table bar to postgres-1
+    And I do a backup of postgres-1
+    When I start postgres-2 in a cluster batman2 from backup
+    Then postgres-2 is a leader of batman2 after 30 seconds
+    And table bar is present on postgres-2 after 10 seconds

features/dcs_failsafe_mode.feature

@@ -2,16 +2,16 @@ Feature: dcs failsafe mode
   We should check the basic dcs failsafe mode functioning
 
   Scenario: check failsafe mode can be successfully enabled
-    Given I start postgres0
-    And postgres0 is a leader after 10 seconds
-    And I sleep for 3 seconds
-    When I issue a PATCH request to http://127.0.0.1:8008/config with {"loop_wait": 2, "ttl": 20, "retry_timeout": 5, "failsafe_mode": true}
+    Given I start postgres-0
+    And postgres-0 is a leader after 10 seconds
+    Then "config" key in DCS has ttl=30 after 10 seconds
+    When I issue a PATCH request to http://127.0.0.1:8008/config with {"loop_wait": 2, "ttl": 20, "retry_timeout": 3, "failsafe_mode": true}
     Then I receive a response code 200
-    And Response on GET http://127.0.0.1:8008/failsafe contains postgres0 after 10 seconds
+    And Response on GET http://127.0.0.1:8008/failsafe contains postgres-0 after 10 seconds
     When I issue a GET request to http://127.0.0.1:8008/failsafe
     Then I receive a response code 200
-    And I receive a response postgres0 http://127.0.0.1:8008/patroni
-    When I issue a PATCH request to http://127.0.0.1:8008/config with {"postgresql": {"parameters": {"wal_level": "logical"}}}
+    And I receive a response postgres-0 http://127.0.0.1:8008/patroni
+    When I issue a PATCH request to http://127.0.0.1:8008/config with {"postgresql": {"parameters": {"wal_level": "logical"}},"slots":{"dcs_slot_1": null,"postgres_0":null}}
     Then I receive a response code 200
     When I issue a PATCH request to http://127.0.0.1:8008/config with {"slots": {"dcs_slot_0": {"type": "logical", "database": "postgres", "plugin": "test_decoding"}}}
     Then I receive a response code 200
@@ -20,66 +20,99 @@ Feature: dcs failsafe mode
   Scenario: check one-node cluster is functioning while DCS is down
     Given DCS is down
     Then Response on GET http://127.0.0.1:8008/primary contains failsafe_mode_is_active after 12 seconds
-    And postgres0 role is the primary after 10 seconds
+    And postgres-0 role is the primary after 10 seconds
 
   @dcs-failsafe
   Scenario: check new replica isn't promoted when leader is down and DCS is up
     Given DCS is up
-    When I do a backup of postgres0
-    And I shut down postgres0
-    When I start postgres1 in a cluster batman from backup with no_leader
-    And I sleep for 2 seconds
-    Then postgres1 role is the replica after 12 seconds
+    When I do a backup of postgres-0
+    And I shut down postgres-0
+    When I start postgres-1 in a cluster batman from backup with no_leader
+    Then postgres-1 role is the replica after 12 seconds
 
   Scenario: check leader and replica are both in /failsafe key after leader is back
-    Given I start postgres0
-    And I start postgres1
-    Then "members/postgres0" key in DCS has state=running after 10 seconds
-    And "members/postgres1" key in DCS has state=running after 2 seconds
-    And Response on GET http://127.0.0.1:8009/failsafe contains postgres1 after 10 seconds
+    Given I start postgres-0
+    And I start postgres-1
+    Then "members/postgres-0" key in DCS has state=running after 10 seconds
+    And "members/postgres-1" key in DCS has state=running after 2 seconds
+    And Response on GET http://127.0.0.1:8009/failsafe contains postgres-1 after 10 seconds
     When I issue a GET request to http://127.0.0.1:8009/failsafe
     Then I receive a response code 200
-    And I receive a response postgres0 http://127.0.0.1:8008/patroni
-    And I receive a response postgres1 http://127.0.0.1:8009/patroni
+    And I receive a response postgres-0 http://127.0.0.1:8008/patroni
+    And I receive a response postgres-1 http://127.0.0.1:8009/patroni
 
   @dcs-failsafe
-  @slot-advance
+  @pg110000
   Scenario: check leader and replica are functioning while DCS is down
-    Given logical slot dcs_slot_0 is in sync between postgres0 and postgres1 after 10 seconds
+    Given I get all changes from physical slot dcs_slot_1 on postgres-0
+    Then physical slot dcs_slot_1 is in sync between postgres-0 and postgres-1 after 10 seconds
+    And logical slot dcs_slot_0 is in sync between postgres-0 and postgres-1 after 10 seconds
     And DCS is down
     Then Response on GET http://127.0.0.1:8008/primary contains failsafe_mode_is_active after 12 seconds
-    Then postgres0 role is the primary after 10 seconds
-    And postgres1 role is the replica after 2 seconds
-    And replication works from postgres0 to postgres1 after 10 seconds
-    And I get all changes from logical slot dcs_slot_0 on postgres0
-    And logical slot dcs_slot_0 is in sync between postgres0 and postgres1 after 20 seconds
+    Then postgres-0 role is the primary after 10 seconds
+    And postgres-1 role is the replica after 2 seconds
+    And replication works from postgres-0 to postgres-1 after 10 seconds
+    When I get all changes from logical slot dcs_slot_0 on postgres-0
+    And I get all changes from physical slot dcs_slot_1 on postgres-0
+    Then logical slot dcs_slot_0 is in sync between postgres-0 and postgres-1 after 20 seconds
+    And physical slot dcs_slot_1 is in sync between postgres-0 and postgres-1 after 10 seconds
 
   @dcs-failsafe
   Scenario: check primary is demoted when one replica is shut down and DCS is down
     Given DCS is down
-    And I kill postgres1
-    And I kill postmaster on postgres1
-    And I sleep for 2 seconds
-    Then postgres0 role is the replica after 12 seconds
+    And I kill postgres-1
+    And I kill postmaster on postgres-1
+    Then postgres-0 role is the replica after 12 seconds
 
   @dcs-failsafe
   Scenario: check known replica is promoted when leader is down and DCS is up
-    Given I shut down postgres0
+    Given I kill postgres-0
+    And I shut down postmaster on postgres-0
     And DCS is up
-    When I start postgres1
-    Then "members/postgres1" key in DCS has state=running after 10 seconds
-    And postgres1 role is the primary after 25 seconds
+    When I start postgres-1
+    Then "members/postgres-1" key in DCS has state=running after 10 seconds
+    And postgres-1 role is the primary after 25 seconds
+
+  @dcs-failsafe
+  Scenario: scale to three-node cluster
+    Given I start postgres-0
+    And I configure and start postgres-2 with a tag replicatefrom postgres-0
+    Then "members/postgres-2" key in DCS has state=running after 10 seconds
+    And "members/postgres-0" key in DCS has state=running after 20 seconds
+    And Response on GET http://127.0.0.1:8008/failsafe contains postgres-2 after 10 seconds
+    And replication works from postgres-1 to postgres-0 after 10 seconds
+    And replication works from postgres-1 to postgres-2 after 10 seconds
+
+  @dcs-failsafe
+  @pg110000
+  Scenario: make sure permanent slots exist on replicas
+    Given I issue a PATCH request to http://127.0.0.1:8009/config with {"slots":{"dcs_slot_0":null,"dcs_slot_2":{"type":"logical","database":"postgres","plugin":"test_decoding"}}}
+    Then logical slot dcs_slot_2 is in sync between postgres-1 and postgres-0 after 20 seconds
+    And logical slot dcs_slot_2 is in sync between postgres-1 and postgres-2 after 20 seconds
+    When I get all changes from physical slot dcs_slot_1 on postgres-1
+    Then physical slot dcs_slot_1 is in sync between postgres-1 and postgres-0 after 10 seconds
+    And physical slot dcs_slot_1 is in sync between postgres-1 and postgres-2 after 10 seconds
+    And physical slot postgres_0 is in sync between postgres-1 and postgres-2 after 10 seconds
+    And physical slot postgres_2 is in sync between postgres-0 and postgres-1 after 10 seconds
 
   @dcs-failsafe
   Scenario: check three-node cluster is functioning while DCS is down
-    Given I start postgres0
-    And I start postgres2
-    Then "members/postgres2" key in DCS has state=running after 10 seconds
-    And "members/postgres0" key in DCS has state=running after 20 seconds
-    And Response on GET http://127.0.0.1:8008/failsafe contains postgres2 after 10 seconds
-    And replication works from postgres1 to postgres0 after 10 seconds
     Given DCS is down
-    Then Response on GET http://127.0.0.1:8008/primary contains failsafe_mode_is_active after 12 seconds
-    Then postgres1 role is the primary after 10 seconds
-    And postgres0 role is the replica after 2 seconds
-    And postgres2 role is the replica after 2 seconds
+    Then Response on GET http://127.0.0.1:8009/primary contains failsafe_mode_is_active after 12 seconds
+    Then postgres-1 role is the primary after 10 seconds
+    And postgres-0 role is the replica after 2 seconds
+    And postgres-2 role is the replica after 2 seconds
+
+  @dcs-failsafe
+  @pg110000
+  Scenario: check that permanent slots are in sync between nodes while DCS is down
+    Given replication works from postgres-1 to postgres-0 after 10 seconds
+    And replication works from postgres-1 to postgres-2 after 10 seconds
+    When I get all changes from logical slot dcs_slot_2 on postgres-1
+    And I get all changes from physical slot dcs_slot_1 on postgres-1
+    Then logical slot dcs_slot_2 is in sync between postgres-1 and postgres-0 after 20 seconds
+    And logical slot dcs_slot_2 is in sync between postgres-1 and postgres-2 after 20 seconds
+    And physical slot dcs_slot_1 is in sync between postgres-1 and postgres-0 after 10 seconds
+    And physical slot dcs_slot_1 is in sync between postgres-1 and postgres-2 after 10 seconds
+    And physical slot postgres_0 is in sync between postgres-1 and postgres-2 after 10 seconds
+    And physical slot postgres_2 is in sync between postgres-0 and postgres-1 after 10 seconds

features/environment.py

@@ -1,9 +1,8 @@
 import abc
 import datetime
 import glob
-import os
 import json
-import psutil
+import os
 import re
 import shutil
 import signal
@@ -13,11 +12,14 @@ import sys
 import tempfile
 import threading
 import time
+
+from http.server import BaseHTTPRequestHandler, HTTPServer
+
+import psutil
 import yaml
 
 import patroni.psycopg as psycopg
 
-from http.server import BaseHTTPRequestHandler, HTTPServer
 from patroni.request import PatroniRequest
 
 
@@ -52,6 +54,8 @@ class AbstractController(abc.ABC):
         self._log = open(os.path.join(self._output_dir, self._name + '.log'), 'a')
         self._handle = self._start()
 
+        if max_wait_limit < 0:
+            return
         max_wait_limit *= self._context.timeout_multiplier
         for _ in range(max_wait_limit):
             assert self._has_started(), "Process {0} is not running after being started".format(self._name)
@@ -162,9 +166,10 @@ class PatroniController(AbstractController):
 
     def stop(self, kill=False, timeout=15, postgres=False):
         if postgres:
-            return subprocess.call(['pg_ctl', '-D', self._data_dir, 'stop', '-mi', '-w'])
+            mode = 'i' if kill else 'f'
+            return subprocess.call(['pg_ctl', '-D', self._data_dir, 'stop', '-m' + mode, '-w'])
         super(PatroniController, self).stop(kill, timeout)
-        if isinstance(self._context.dcs_ctl, KubernetesController):
+        if isinstance(self._context.dcs_ctl, KubernetesController) and not kill:
             self._context.dcs_ctl.delete_pod(self._name[8:])
         if self.watchdog:
             self.watchdog.stop()
@@ -215,6 +220,8 @@ class PatroniController(AbstractController):
             'host replication replicator all md5',
             'host all all all md5'
         ]
+        if isinstance(self._context.dcs_ctl, KubernetesController):
+            config['kubernetes'] = {'bootstrap_labels': {'foo': 'bar'}}
 
         if self._context.postgres_supports_ssl and self._context.certfile:
             config['postgresql']['parameters'].update({
@@ -244,6 +251,10 @@ class PatroniController(AbstractController):
             self.recursive_update(config, custom_config)
 
         self.recursive_update(config, {
+            'log': {
+                'format': '%(asctime)s %(levelname)s [%(pathname)s:%(lineno)d - %(funcName)s]: %(message)s',
+                'loggers': {'patroni.postgresql.callback_executor': 'DEBUG'}
+            },
             'bootstrap': {
                 'dcs': {
                     'loop_wait': 2,
@@ -251,10 +262,18 @@ class PatroniController(AbstractController):
                         'parameters': {
                             'wal_keep_segments': 100,
                             'archive_mode': 'on',
-                            'archive_command': (PatroniPoolController.ARCHIVE_RESTORE_SCRIPT
-                                                + ' --mode archive '
-                                                + '--dirname {} --filename %f --pathname %p').format(
-                                                    os.path.join(self._work_directory, 'data', 'wal_archive'))
+                            'archive_command':
+                                (PatroniPoolController.ARCHIVE_RESTORE_SCRIPT
+                                 + ' --mode archive '
+                                 + '--dirname {} --filename %f --pathname %p').format(
+                                     os.path.join(self._work_directory, 'data',
+                                                  f'wal_archive{str(self._citus_group or "")}')).replace('\\', '/'),
+                            'restore_command':
+                                (PatroniPoolController.ARCHIVE_RESTORE_SCRIPT
+                                 + ' --mode restore '
+                                 + '--dirname {} --filename %f --pathname %p').format(
+                                     os.path.join(self._work_directory, 'data',
+                                                  f'wal_archive{str(self._citus_group or "")}')).replace('\\', '/')
                         }
                     }
                 }
@@ -485,6 +504,7 @@ class AbstractEtcdController(AbstractDcsController):
 
     def _is_running(self):
         from patroni.dcs.etcd import DnsCachingResolver
+
         # if etcd is running, but we didn't start it
         try:
             self._client = self._client_cls({'host': 'localhost', 'port': 2379, 'retry_timeout': 30,
@@ -641,6 +661,10 @@ class KubernetesController(AbstractExternalDcsController):
             except Exception:
                 break
 
+    def pod_labels(self, name):
+        pod = self._api.read_namespaced_pod(name, self._namespace)
+        return pod.metadata.labels or {}
+
     def query(self, key, scope='batman', group=None):
         if key.startswith('members/'):
             pod = self._api.read_namespaced_pod(key[8:], self._namespace)
@@ -649,9 +673,10 @@ class KubernetesController(AbstractExternalDcsController):
             try:
                 if group is not None:
                     scope = '{0}-{1}'.format(scope, group)
-                ep = scope + {'leader': '', 'history': '-config', 'initialize': '-config'}.get(key, '-' + key)
+                rkey = 'leader' if key in ('status', 'failsafe') else key
+                ep = scope + {'leader': '', 'history': '-config', 'initialize': '-config'}.get(rkey, '-' + rkey)
                 e = self._api.read_namespaced_endpoints(ep, self._namespace)
-                if key != 'sync':
+                if key not in ('sync', 'status', 'failsafe'):
                     return e.metadata.annotations[key]
                 else:
                     return json.dumps(e.metadata.annotations)
@@ -687,7 +712,7 @@ class ZooKeeperController(AbstractExternalDcsController):
         self._client = kazoo.client.KazooClient()
 
     def process_name(self):
-        return "zookeeper"
+        return "java .*zookeeper"
 
     def query(self, key, scope='batman', group=None):
         import kazoo.exceptions
@@ -853,7 +878,7 @@ class PatroniPoolController(object):
         os.makedirs(feature_dir)
         self._output_dir = feature_dir
 
-    def clone(self, from_name, cluster_name, to_name):
+    def clone(self, from_name, cluster_name, to_name, long_running=False):
         f = self._processes[from_name]
         custom_config = {
             'scope': cluster_name,
@@ -861,7 +886,8 @@ class PatroniPoolController(object):
                 'method': 'pg_basebackup',
                 'pg_basebackup': {
                     'command': " ".join(self.BACKUP_SCRIPT
-                                        + ['--walmethod=stream', '--dbname="{0}"'.format(f.backup_source)])
+                                        + ['--walmethod=stream', f'--dbname="{f.backup_source}"',
+                                           f'--sleep {5 if long_running else 0}'])
                 },
                 'dcs': {
                     'postgresql': {
@@ -879,33 +905,43 @@ class PatroniPoolController(object):
                     .format(os.path.join(self.patroni_path, 'data', 'wal_archive_clone').replace('\\', '/'))
                 },
                 'authentication': {
-                    'superuser': {'password': 'zalando1'},
+                    'superuser': {'password': 'patroni1'},
                     'replication': {'password': 'rep-pass1'}
                 }
             }
         }
-        self.start(to_name, custom_config=custom_config)
+        kwargs = {'custom_config': custom_config}
+        if long_running:
+            kwargs['max_wait_limit'] = -1
+        self.start(to_name, **kwargs)
+
+    def backup_restore_config(self, params=None, long_running=False):
+        return {
+            'command': (self.BACKUP_RESTORE_SCRIPT
+                        + ' --sourcedir=' + os.path.join(self.patroni_path, 'data', 'basebackup')
+                        + f' --sleep {5 if long_running else 0}').replace('\\', '/'),
+            'test-argument': 'test-value',  # test config mapping approach on custom bootstrap/replica creation
+            **(params or {}),
+        }
 
     def bootstrap_from_backup(self, name, cluster_name):
         custom_config = {
             'scope': cluster_name,
             'bootstrap': {
                 'method': 'backup_restore',
-                'backup_restore': {
-                    'command': (self.BACKUP_RESTORE_SCRIPT + ' --sourcedir='
-                                + os.path.join(self.patroni_path, 'data', 'basebackup').replace('\\', '/')),
+                'backup_restore': self.backup_restore_config({
                     'recovery_conf': {
                         'recovery_target_action': 'promote',
                         'recovery_target_timeline': 'latest',
                         'restore_command': (self.ARCHIVE_RESTORE_SCRIPT + ' --mode restore '
                                             + '--dirname {} --filename %f --pathname %p').format(
                             os.path.join(self.patroni_path, 'data', 'wal_archive_clone').replace('\\', '/'))
-                    }
-                }
+                    },
+                })
             },
             'postgresql': {
                 'authentication': {
-                    'superuser': {'password': 'zalando2'},
+                    'superuser': {'password': 'patroni2'},
                     'replication': {'password': 'rep-pass2'}
                 }
             }
@@ -916,17 +952,8 @@ class PatroniPoolController(object):
         custom_config = {
             'scope': cluster_name,
             'postgresql': {
-                'recovery_conf': {
-                    'restore_command': (self.ARCHIVE_RESTORE_SCRIPT + ' --mode restore '
-                                        + '--dirname {} --filename %f --pathname %p')
-                    .format(os.path.join(self.patroni_path, 'data', 'wal_archive').replace('\\', '/'))
-                },
                 'create_replica_methods': ['no_leader_bootstrap'],
-                'no_leader_bootstrap': {
-                    'command': (self.BACKUP_RESTORE_SCRIPT + ' --sourcedir='
-                                + os.path.join(self.patroni_path, 'data', 'basebackup').replace('\\', '/')),
-                    'no_leader': '1'
-                }
+                'no_leader_bootstrap': self.backup_restore_config({'no_leader': '1'})
             }
         }
         self.start(name, custom_config=custom_config)
@@ -1109,12 +1136,14 @@ def before_feature(context, feature):
     elif feature.name == 'citus':
         lib = subprocess.check_output(['pg_config', '--pkglibdir']).decode('utf-8').strip()
         if not os.path.exists(os.path.join(lib, 'citus.so')):
-            return feature.skip("Citus extenstion isn't available")
+            return feature.skip("Citus extension isn't available")
+    elif feature.name == 'bootstrap labels' and context.dcs_ctl.name() != 'kubernetes':
+        feature.skip("Tested only on Kubernetes")
     context.pctl.create_and_set_output_directory(feature.name)
 
 
 def after_feature(context, feature):
-    """ send SIGCONT to a dcs if neccessary,
+    """ send SIGCONT to a dcs if necessary,
     stop all Patronis remove their data directory and cleanup the keys in etcd """
     context.dcs_ctl.stop_outage()
     context.pctl.stop_all()
@@ -1139,11 +1168,18 @@ def after_feature(context, feature):
 
 
 def before_scenario(context, scenario):
-    if 'slot-advance' in scenario.effective_tags:
-        for p in context.pctl._processes.values():
-            if p._conn and p._conn.server_version < 110000:
-                scenario.skip('pg_replication_slot_advance() is not supported on {0}'.format(p._conn.server_version))
-                break
+    for tag in scenario.effective_tags:
+        if tag.startswith('pg') and 6 < len(tag) < 9:
+            try:
+                ver = int(tag[2:])
+            except Exception:
+                ver = 0
+            if not ver:
+                continue
+            for p in context.pctl._processes.values():
+                if p._conn and p._conn.server_version < ver:
+                    scenario.skip('not supported on {0}'.format(p._conn.server_version))
+                    break
     if 'dcs-failsafe' in scenario.effective_tags and not context.dcs_ctl._handle:
         scenario.skip('it is not possible to control state of {0} from tests'.format(context.dcs_ctl.name()))
     if 'reject-duplicate-name' in scenario.effective_tags and context.dcs_ctl.name() == 'raft':

features/ignored_slots.feature

@@ -1,61 +1,66 @@
 Feature: ignored slots
   Scenario: check ignored slots aren't removed on failover/switchover
-    Given I start postgres1
-    Then postgres1 is a leader after 10 seconds
+    Given I start postgres-1
+    Then postgres-1 is a leader after 10 seconds
     And there is a non empty initialize key in DCS after 15 seconds
     When I issue a PATCH request to http://127.0.0.1:8009/config with {"ignore_slots": [{"name": "unmanaged_slot_0", "database": "postgres", "plugin": "test_decoding", "type": "logical"}, {"name": "unmanaged_slot_1", "database": "postgres", "plugin": "test_decoding"}, {"name": "unmanaged_slot_2", "database": "postgres"}, {"name": "unmanaged_slot_3"}], "postgresql": {"parameters": {"wal_level": "logical"}}}
     Then I receive a response code 200
     And Response on GET http://127.0.0.1:8009/config contains ignore_slots after 10 seconds
+    And Response on GET http://127.0.0.1:8009/patroni contains pending_restart after 10 seconds
     # Make sure the wal_level has been changed.
-    When I shut down postgres1
-    And I start postgres1
-    Then postgres1 is a leader after 10 seconds
-    And "members/postgres1" key in DCS has role=master after 10 seconds
+    When I run patronictl.py restart batman postgres-1 --force
+    Then "members/postgres-1" key in DCS has role=primary after 10 seconds
     # Make sure Patroni has finished telling Postgres it should be accepting writes.
-    And postgres1 role is the primary after 20 seconds
+    And postgres-1 role is the primary after 20 seconds
     # 1. Create our test logical replication slot.
     # Test that ny subset of attributes in the ignore slots matcher is enough to match a slot
     # by using 3 different slots.
-    When I create a logical replication slot unmanaged_slot_0 on postgres1 with the test_decoding plugin
-    And I create a logical replication slot unmanaged_slot_1 on postgres1 with the test_decoding plugin
-    And I create a logical replication slot unmanaged_slot_2 on postgres1 with the test_decoding plugin
-    And I create a logical replication slot unmanaged_slot_3 on postgres1 with the test_decoding plugin
-    And I create a logical replication slot dummy_slot on postgres1 with the test_decoding plugin
+    When I create a logical replication slot unmanaged_slot_0 on postgres-1 with the test_decoding plugin
+    And I create a logical replication slot unmanaged_slot_1 on postgres-1 with the test_decoding plugin
+    And I create a logical replication slot unmanaged_slot_2 on postgres-1 with the test_decoding plugin
+    And I create a logical replication slot unmanaged_slot_3 on postgres-1 with the test_decoding plugin
+    And I create a logical replication slot dummy_slot on postgres-1 with the test_decoding plugin
     # It seems like it'd be obvious that these slots exist since we just created them,
     # but Patroni can actually end up dropping them almost immediately, so it's helpful
     # to verify they exist before we begin testing whether they persist through failover
     # cycles.
-    Then postgres1 has a logical replication slot named unmanaged_slot_0 with the test_decoding plugin
-    And postgres1 has a logical replication slot named unmanaged_slot_1 with the test_decoding plugin
-    And postgres1 has a logical replication slot named unmanaged_slot_2 with the test_decoding plugin
-    And postgres1 has a logical replication slot named unmanaged_slot_3 with the test_decoding plugin
+    Then postgres-1 has a logical replication slot named unmanaged_slot_0 with the test_decoding plugin after 2 seconds
+    And postgres-1 has a logical replication slot named unmanaged_slot_1 with the test_decoding plugin after 2 seconds
+    And postgres-1 has a logical replication slot named unmanaged_slot_2 with the test_decoding plugin after 2 seconds
+    And postgres-1 has a logical replication slot named unmanaged_slot_3 with the test_decoding plugin after 2 seconds
 
-    When I start postgres0
-    Then "members/postgres0" key in DCS has role=replica after 10 seconds
-    And postgres0 role is the secondary after 20 seconds
+    When I start postgres-0
+    Then "members/postgres-0" key in DCS has role=replica after 10 seconds
+    And postgres-0 role is the secondary after 20 seconds
     # Verify that the replica has advanced beyond the point in the WAL
     # where we created the replication slot so that on the next failover
     # cycle we don't accidentally rewind to before the slot creation.
-    And replication works from postgres1 to postgres0 after 20 seconds
-    When I shut down postgres1
-    Then "members/postgres0" key in DCS has role=master after 10 seconds
+    And replication works from postgres-1 to postgres-0 after 20 seconds
+    When I shut down postgres-1
+    Then "members/postgres-0" key in DCS has role=primary after 10 seconds
 
     # 2. After a failover the server (now a replica) still has the slot.
-    When I start postgres1
-    Then postgres1 role is the secondary after 20 seconds
-    And "members/postgres1" key in DCS has role=replica after 10 seconds
+    When I start postgres-1
+    Then postgres-1 role is the secondary after 20 seconds
+    And "members/postgres-1" key in DCS has role=replica after 10 seconds
     # give Patroni time to sync replication slots
     And I sleep for 2 seconds
-    And postgres1 has a logical replication slot named unmanaged_slot_0 with the test_decoding plugin
-    And postgres1 has a logical replication slot named unmanaged_slot_1 with the test_decoding plugin
-    And postgres1 has a logical replication slot named unmanaged_slot_2 with the test_decoding plugin
-    And postgres1 has a logical replication slot named unmanaged_slot_3 with the test_decoding plugin
-    And postgres1 does not have a logical replication slot named dummy_slot
+    And postgres-1 has a logical replication slot named unmanaged_slot_0 with the test_decoding plugin after 2 seconds
+    And postgres-1 has a logical replication slot named unmanaged_slot_1 with the test_decoding plugin after 2 seconds
+    And postgres-1 has a logical replication slot named unmanaged_slot_2 with the test_decoding plugin after 2 seconds
+    And postgres-1 has a logical replication slot named unmanaged_slot_3 with the test_decoding plugin after 2 seconds
+    And postgres-1 does not have a replication slot named dummy_slot
 
     # 3. After a failover the server (now a primary) still has the slot.
-    When I shut down postgres0
-    Then "members/postgres1" key in DCS has role=master after 10 seconds
-    And postgres1 has a logical replication slot named unmanaged_slot_0 with the test_decoding plugin
-    And postgres1 has a logical replication slot named unmanaged_slot_1 with the test_decoding plugin
-    And postgres1 has a logical replication slot named unmanaged_slot_2 with the test_decoding plugin
-    And postgres1 has a logical replication slot named unmanaged_slot_3 with the test_decoding plugin
+    When I shut down postgres-0
+    Then "members/postgres-1" key in DCS has role=primary after 10 seconds
+    And postgres-1 has a logical replication slot named unmanaged_slot_0 with the test_decoding plugin after 2 seconds
+    And postgres-1 has a logical replication slot named unmanaged_slot_1 with the test_decoding plugin after 2 seconds
+    And postgres-1 has a logical replication slot named unmanaged_slot_2 with the test_decoding plugin after 2 seconds
+    And postgres-1 has a logical replication slot named unmanaged_slot_3 with the test_decoding plugin after 2 seconds
+
+  @pg170000
+  Scenario: check that logical slots with failover are not removed by Patroni
+    Given I create a logical failover slot test17 on postgres-1 with the pgoutput plugin
+    When I run patronictl.py restart batman postgres-1 --force
+    Then postgres-1 has a logical replication slot named test17 with the pgoutput plugin after 2 seconds

features/nostream_node.feature

@@ -0,0 +1,26 @@
+Feature: nostream node
+
+Scenario: check nostream node is recovering from archive
+    When I start postgres-0
+    And I configure and start postgres-1 with a tag nostream true
+    Then "members/postgres-1" key in DCS has replication_state=in archive recovery after 10 seconds
+    And replication works from postgres-0 to postgres-1 after 30 seconds
+
+@pg110000
+Scenario: check permanent logical replication slots are not copied
+    When I issue a PATCH request to http://127.0.0.1:8008/config with {"postgresql": {"parameters": {"wal_level": "logical"}}, "slots":{"test_logical":{"type":"logical","database":"postgres","plugin":"test_decoding"}}}
+    Then I receive a response code 200
+    When I run patronictl.py restart batman postgres-0 --force
+    Then postgres-0 has a logical replication slot named test_logical with the test_decoding plugin after 10 seconds
+    When I configure and start postgres-2 with a tag replicatefrom postgres-1
+    Then "members/postgres-2" key in DCS has replication_state=streaming after 10 seconds 
+    And postgres-1 does not have a replication slot named test_logical
+    And postgres-2 does not have a replication slot named test_logical
+
+@pg110000
+Scenario: check that slots are written to the /status key
+    Given "status" key in DCS has postgres_0 in slots
+    And "status" key in DCS has postgres_2 in slots
+    And "status" key in DCS has test_logical in slots
+    And "status" key in DCS has test_logical in slots
+    And "status" key in DCS does not have postgres_1 in slots

features/patroni_api.feature

@@ -2,12 +2,12 @@ Feature: patroni api
 	We should check that patroni correctly responds to valid and not-valid API requests.
 
 Scenario: check API requests on a stand-alone server
-	Given I start postgres0
-	And postgres0 is a leader after 10 seconds
+	Given I start postgres-0
+	And postgres-0 is a leader after 10 seconds
 	When I issue a GET request to http://127.0.0.1:8008/
 	Then I receive a response code 200
 	And I receive a response state running
-	And I receive a response role master
+	And I receive a response role primary
 	When I issue a GET request to http://127.0.0.1:8008/standby_leader
 	Then I receive a response code 503
 	When I issue a GET request to http://127.0.0.1:8008/health
@@ -17,10 +17,10 @@ Scenario: check API requests on a stand-alone server
 	When I issue a POST request to http://127.0.0.1:8008/reinitialize with {"force": true}
 	Then I receive a response code 503
 	And I receive a response text I am the leader, can not reinitialize
-	When I run patronictl.py switchover batman --master postgres0 --force
+	When I run patronictl.py switchover batman --primary postgres-0 --force
 	Then I receive a response returncode 1
 	And I receive a response output "Error: No candidates found to switchover to"
-	When I issue a POST request to http://127.0.0.1:8008/switchover with {"leader": "postgres0"}
+	When I issue a POST request to http://127.0.0.1:8008/switchover with {"leader": "postgres-0"}
 	Then I receive a response code 412
 	And I receive a response text switchover is not possible: cluster does not have members except leader
 	When I issue an empty POST request to http://127.0.0.1:8008/failover
@@ -30,7 +30,7 @@ Scenario: check API requests on a stand-alone server
 	And I receive a response text "Failover could be performed only to a specific candidate"
 
 Scenario: check local configuration reload
-	Given I add tag new_tag new_value to postgres0 config
+	Given I add tag new_tag new_value to postgres-0 config
 	And I issue an empty POST request to http://127.0.0.1:8008/reload
 	Then I receive a response code 202
 
@@ -58,42 +58,43 @@ Scenario: check the scheduled restart
 	Given I issue a scheduled restart at http://127.0.0.1:8008 in 5 seconds with {"restart_pending": "True"}
 	Then I receive a response code 202
 	And Response on GET http://127.0.0.1:8008/patroni does not contain pending_restart after 10 seconds
-	And postgres0 role is the primary after 10 seconds
+	And postgres-0 role is the primary after 10 seconds
 
 Scenario: check API requests for the primary-replica pair in the pause mode
-	Given I start postgres1
-	Then replication works from postgres0 to postgres1 after 20 seconds
+	Given I start postgres-1
+	Then replication works from postgres-0 to postgres-1 after 20 seconds
 	When I run patronictl.py pause batman
 	Then I receive a response returncode 0
-	When I kill postmaster on postgres1
+	When I kill postmaster on postgres-1
 	And I issue a GET request to http://127.0.0.1:8009/replica
 	Then I receive a response code 503
-	When I run patronictl.py restart batman postgres1 --force
+	And "members/postgres-1" key in DCS has state=stopped after 10 seconds
+	When I run patronictl.py restart batman postgres-1 --force
 	Then I receive a response returncode 0
-	Then replication works from postgres0 to postgres1 after 20 seconds
+	Then replication works from postgres-0 to postgres-1 after 20 seconds
 	And I sleep for 2 seconds
 	When I issue a GET request to http://127.0.0.1:8009/replica
 	Then I receive a response code 200
 	And I receive a response state running
 	And I receive a response role replica
-	When I run patronictl.py reinit batman postgres1 --force
+	When I run patronictl.py reinit batman postgres-1 --force --wait
 	Then I receive a response returncode 0
-	And I receive a response output "Success: reinitialize for member postgres1"
-	And postgres1 role is the secondary after 30 seconds
-	And replication works from postgres0 to postgres1 after 20 seconds
-	When I run patronictl.py restart batman postgres0 --force
+	And I receive a response output "Success: reinitialize for member postgres-1"
+	And postgres-1 role is the secondary after 30 seconds
+	And replication works from postgres-0 to postgres-1 after 20 seconds
+	When I run patronictl.py restart batman postgres-0 --force
 	Then I receive a response returncode 0
-	And I receive a response output "Success: restart on member postgres0"
-	And postgres0 role is the primary after 5 seconds
+	And I receive a response output "Success: restart on member postgres-0"
+	And postgres-0 role is the primary after 5 seconds
 
 Scenario: check the switchover via the API in the pause mode
-	Given I issue a POST request to http://127.0.0.1:8008/switchover with {"leader": "postgres0", "candidate": "postgres1"}
+	Given I issue a POST request to http://127.0.0.1:8008/switchover with {"leader": "postgres-0", "candidate": "postgres-1"}
 	Then I receive a response code 200
-	And postgres1 is a leader after 5 seconds
-	And postgres1 role is the primary after 10 seconds
-	And postgres0 role is the secondary after 10 seconds
-	And replication works from postgres1 to postgres0 after 20 seconds
-	And "members/postgres0" key in DCS has state=running after 10 seconds
+	And postgres-1 is a leader after 5 seconds
+	And postgres-1 role is the primary after 10 seconds
+	And postgres-0 role is the secondary after 10 seconds
+	And replication works from postgres-1 to postgres-0 after 20 seconds
+	And "members/postgres-0" key in DCS has state=running after 10 seconds
 	When I issue a GET request to http://127.0.0.1:8008/primary
 	Then I receive a response code 503
 	When I issue a GET request to http://127.0.0.1:8008/replica
@@ -104,18 +105,18 @@ Scenario: check the switchover via the API in the pause mode
 	Then I receive a response code 503
 
 Scenario: check the scheduled switchover
-	Given I issue a scheduled switchover from postgres1 to postgres0 in 10 seconds
+	Given I issue a scheduled switchover from postgres-1 to postgres-0 in 10 seconds
 	Then I receive a response returncode 1
 	And I receive a response output "Can't schedule switchover in the paused state"
 	When I run patronictl.py resume batman
 	Then I receive a response returncode 0
-	Given I issue a scheduled switchover from postgres1 to postgres0 in 10 seconds
+	Given I issue a scheduled switchover from postgres-1 to postgres-0 in 10 seconds
 	Then I receive a response returncode 0
-	And postgres0 is a leader after 20 seconds
-	And postgres0 role is the primary after 10 seconds
-	And postgres1 role is the secondary after 10 seconds
-	And replication works from postgres0 to postgres1 after 25 seconds
-	And "members/postgres1" key in DCS has state=running after 10 seconds
+	And postgres-0 is a leader after 20 seconds
+	And postgres-0 role is the primary after 10 seconds
+	And postgres-1 role is the secondary after 10 seconds
+	And replication works from postgres-0 to postgres-1 after 25 seconds
+	And "members/postgres-1" key in DCS has state=running after 10 seconds
 	When I issue a GET request to http://127.0.0.1:8008/primary
 	Then I receive a response code 200
 	When I issue a GET request to http://127.0.0.1:8008/replica

features/permanent_slots.feature

@@ -0,0 +1,86 @@
+Feature: permanent slots
+  Scenario: check that physical permanent slots are created
+    Given I start postgres-0
+    Then postgres-0 is a leader after 10 seconds
+    And there is a non empty initialize key in DCS after 15 seconds
+    When I issue a PATCH request to http://127.0.0.1:8008/config with {"slots":{"test_physical":0,"postgres_3":0},"postgresql":{"parameters":{"wal_level":"logical"}}}
+    Then I receive a response code 200
+    And Response on GET http://127.0.0.1:8008/config contains slots after 10 seconds
+    When I start postgres-1
+    And I configure and start postgres-2 with a tag nofailover true
+    And I configure and start postgres-3 with a tag replicatefrom postgres-2
+    Then postgres-0 has a physical replication slot named test_physical after 10 seconds
+    And postgres-0 has a physical replication slot named postgres_1 after 10 seconds
+    And postgres-0 has a physical replication slot named postgres_2 after 10 seconds
+    And postgres-2 has a physical replication slot named postgres_3 after 10 seconds
+    And postgres-2 does not have a replication slot named test_physical
+
+  @pg110000
+  Scenario: check that logical permanent slots are created
+    Given I run patronictl.py restart batman postgres-0 --force
+    And I issue a PATCH request to http://127.0.0.1:8008/config with {"slots":{"test_logical":{"type":"logical","database":"postgres","plugin":"test_decoding"}}}
+    Then postgres-0 has a logical replication slot named test_logical with the test_decoding plugin after 10 seconds
+
+  @pg110000
+  Scenario: check that permanent slots are created on replicas
+    Given postgres-1 has a logical replication slot named test_logical with the test_decoding plugin after 10 seconds
+    Then Logical slot test_logical is in sync between postgres-0 and postgres-1 after 10 seconds
+    And Logical slot test_logical is in sync between postgres-0 and postgres-3 after 10 seconds
+    And postgres-1 has a physical replication slot named test_physical after 2 seconds
+    And postgres-2 does not have a replication slot named test_logical
+    And postgres-3 has a physical replication slot named test_physical after 2 seconds
+
+  @pg110000
+  Scenario: check permanent physical slots that match with member names
+    Given postgres-0 has a physical replication slot named postgres_3 after 2 seconds
+    And postgres-1 has a physical replication slot named postgres_0 after 2 seconds
+    And postgres-1 has a physical replication slot named postgres_2 after 2 seconds
+    And postgres-1 has a physical replication slot named postgres_3 after 2 seconds
+    And postgres-2 does not have a replication slot named postgres_0
+    And postgres-2 does not have a replication slot named postgres_1
+    And postgres-2 has a physical replication slot named postgres_3 after 2 seconds
+    And postgres-3 has a physical replication slot named postgres_0 after 2 seconds
+    And postgres-3 has a physical replication slot named postgres_1 after 2 seconds
+    And postgres-3 has a physical replication slot named postgres_2 after 2 seconds
+
+  @pg110000
+  Scenario: check that permanent slots are advanced on replicas
+    Given I add the table replicate_me to postgres-0
+    When I get all changes from logical slot test_logical on postgres-0
+    And I get all changes from physical slot test_physical on postgres-0
+    Then Logical slot test_logical is in sync between postgres-0 and postgres-1 after 10 seconds
+    And Physical slot test_physical is in sync between postgres-0 and postgres-1 after 10 seconds
+    And Logical slot test_logical is in sync between postgres-0 and postgres-3 after 10 seconds
+    And Physical slot test_physical is in sync between postgres-0 and postgres-3 after 10 seconds
+    And Physical slot postgres_1 is in sync between postgres-0 and postgres-3 after 10 seconds
+    And Physical slot postgres_3 is in sync between postgres-2 and postgres-0 after 20 seconds
+    And Physical slot postgres_3 is in sync between postgres-2 and postgres-1 after 10 seconds
+
+  @pg110000
+  Scenario: check that permanent slots and member slots are written to the /status key
+    Given "status" key in DCS has test_physical in slots
+    And "status" key in DCS has postgres_0 in slots
+    And "status" key in DCS has postgres_1 in slots
+    And "status" key in DCS has postgres_2 in slots
+    And "status" key in DCS has postgres_3 in slots
+
+  @pg110000
+  Scenario: check that only non-permanent member slots are written to the retain_slots in /status key
+    Given "status" key in DCS has postgres_0 in retain_slots
+    And "status" key in DCS has postgres_1 in retain_slots
+    And "status" key in DCS has postgres_2 in retain_slots
+    And "status" key in DCS does not have postgres_3 in retain_slots
+
+  Scenario: check permanent physical replication slot after failover
+    Given I shut down postgres-3
+    And I shut down postgres-2
+    And I shut down postgres-0
+    Then postgres-1 has a physical replication slot named test_physical after 10 seconds
+    And postgres-1 has a physical replication slot named postgres_0 after 10 seconds
+    And postgres-1 has a physical replication slot named postgres_3 after 10 seconds
+    When I start postgres-0
+    Then postgres-0 role is the replica after 20 seconds
+    And physical replication slot named postgres_1 on postgres-0 has no xmin value after 10 seconds
+    # postgres_2 and postgres_3 slots are retained, but postgres_2 will still have xmin value :(
+    And postgres-0 has a physical replication slot named postgres_2 after 10 seconds
+    And postgres-0 has a physical replication slot named postgres_3 after 10 seconds

features/priority_failover.feature

@@ -0,0 +1,39 @@
+Feature: priority replication
+  We should check that we can give nodes priority during failover
+
+  Scenario: check failover priority 0 prevents leaderships
+    Given I configure and start postgres-0 with a tag failover_priority 1
+    And I configure and start postgres-1 with a tag failover_priority 0
+    Then replication works from postgres-0 to postgres-1 after 20 seconds
+    When I shut down postgres-0
+    And there is one of ["following a different leader because I am not allowed to promote"] INFO in the postgres-1 patroni log after 5 seconds
+    Then postgres-1 role is the secondary after 10 seconds
+    When I start postgres-0
+    Then postgres-0 role is the primary after 10 seconds
+
+  Scenario: check higher failover priority is respected
+    Given I configure and start postgres-2 with a tag failover_priority 1
+    And I configure and start postgres-3 with a tag failover_priority 2
+    Then replication works from postgres-0 to postgres-2 after 20 seconds
+    And replication works from postgres-0 to postgres-3 after 20 seconds
+    When I shut down postgres-0
+    Then postgres-3 role is the primary after 10 seconds
+    And there is one of ["postgres-3 has equally tolerable WAL position and priority 2, while this node has priority 1","Wal position of postgres-3 is ahead of my wal position"] INFO in the postgres-2 patroni log after 5 seconds
+
+ Scenario: check conflicting configuration handling
+    When I set nofailover tag in postgres-2 config
+    And I issue an empty POST request to http://127.0.0.1:8010/reload
+    Then I receive a response code 202
+    And there is one of ["Conflicting configuration between nofailover: True and failover_priority: 1. Defaulting to nofailover: True"] WARNING in the postgres-2 patroni log after 5 seconds
+    And "members/postgres-2" key in DCS has tags={'failover_priority': '1', 'nofailover': True} after 10 seconds
+    When I issue a POST request to http://127.0.0.1:8010/failover with {"candidate": "postgres-2"}
+    Then I receive a response code 412
+    And I receive a response text "failover is not possible: no good candidates have been found"
+    When I reset nofailover tag in postgres-1 config
+    And I issue an empty POST request to http://127.0.0.1:8009/reload
+    Then I receive a response code 202
+    And there is one of ["Conflicting configuration between nofailover: False and failover_priority: 0. Defaulting to nofailover: False"] WARNING in the postgres-1 patroni log after 5 seconds
+    And "members/postgres-1" key in DCS has tags={'failover_priority': '0', 'nofailover': False} after 10 seconds
+    And I issue a POST request to http://127.0.0.1:8009/failover with {"candidate": "postgres-1"}
+    Then I receive a response code 200
+    And postgres-1 role is the primary after 10 seconds

features/priority_sync.feature

@@ -0,0 +1,38 @@
+Feature: synchronous replicas priority
+    We should check that we can give nodes priority for becoming synchronous replicas
+
+  Scenario: check replica with sync_priority=0 does not become a synchronous replica
+     Given I start postgres-0
+     Then postgres-0 is a leader after 10 seconds
+     And there is a non empty initialize key in DCS after 15 seconds
+     When I issue a PATCH request to http://127.0.0.1:8008/config with {"ttl": 20, "synchronous_mode": true}
+     Then I receive a response code 200
+     When I configure and start postgres-1 with a tag sync_priority 0
+     Then sync key in DCS has leader=postgres-0 after 20 seconds
+     And sync key in DCS has sync_standby=None after 5 seconds
+
+  Scenario: check higher synchronous replicas priority is respected
+    Given I configure and start postgres-2 with a tag sync_priority 1
+    And I configure and start postgres-3 with a tag sync_priority 2
+    Then replication works from postgres-0 to postgres-2 after 20 seconds
+    And replication works from postgres-0 to postgres-3 after 20 seconds
+    When I issue a PATCH request to http://127.0.0.1:8008/config with {"synchronous_node_count": 1}
+    Then I receive a response code 200
+    And sync key in DCS has sync_standby=postgres-3 after 10 seconds
+
+
+ Scenario: check conflicting configuration handling
+    When I set nosync tag in postgres-3 config
+    And I issue an empty POST request to http://127.0.0.1:8011/reload
+    Then I receive a response code 202
+    And there is one of ["Conflicting configuration between nosync: True and sync_priority: 2. Defaulting to nosync: True"] WARNING in the postgres-3 patroni log after 5 seconds
+    And "members/postgres-3" key in DCS has tags={'nosync': True, 'sync_priority': '2'} after 10 seconds
+    And "sync" key in DCS has sync_standby=postgres-2 after 10 seconds
+    When I reset nosync tag in postgres-1 config
+    And I issue an empty POST request to http://127.0.0.1:8009/reload
+    Then I receive a response code 202
+    And there is one of ["Conflicting configuration between nosync: False and sync_priority: 0. Defaulting to nosync: False"] WARNING in the postgres-1 patroni log after 5 seconds
+    And "members/postgres-1" key in DCS has tags={'nosync': False, 'sync_priority': '0'} after 10 seconds
+    When I shut down postgres-2
+    And "sync" key in DCS has sync_standby=postgres-1 after 3 seconds
+

features/quorum_commit.feature

@@ -0,0 +1,68 @@
+Feature: quorum commit
+  Check basic workfrlows when quorum commit is enabled
+
+  Scenario: check enable quorum commit and that the only leader promotes after restart
+    Given I start postgres-0
+    Then postgres-0 is a leader after 10 seconds
+    And there is a non empty initialize key in DCS after 15 seconds
+    When I issue a PATCH request to http://127.0.0.1:8008/config with {"ttl": 20, "synchronous_mode": "quorum"}
+    Then I receive a response code 200
+    And sync key in DCS has leader=postgres-0 after 20 seconds
+    And sync key in DCS has quorum=0 after 2 seconds
+    And synchronous_standby_names on postgres-0 is set to '_empty_str_' after 2 seconds
+    When I shut down postgres-0
+    And sync key in DCS has leader=postgres-0 after 2 seconds
+    When I start postgres-0
+    Then postgres-0 role is the primary after 10 seconds
+    When I issue a PATCH request to http://127.0.0.1:8008/config with {"synchronous_mode_strict": true}
+    Then synchronous_standby_names on postgres-0 is set to 'ANY 1 (*)' after 10 seconds
+
+  Scenario: check failover with one quorum standby
+    Given I start postgres-1
+    Then sync key in DCS has sync_standby=postgres-1 after 10 seconds
+    And synchronous_standby_names on postgres-0 is set to 'ANY 1 ("postgres-1")' after 2 seconds
+    When I shut down postgres-0
+    Then postgres-1 role is the primary after 10 seconds
+    And sync key in DCS has quorum=0 after 10 seconds
+    Then synchronous_standby_names on postgres-1 is set to 'ANY 1 (*)' after 10 seconds
+    When I start postgres-0
+    Then sync key in DCS has leader=postgres-1 after 10 seconds
+    Then sync key in DCS has sync_standby=postgres-0 after 10 seconds
+    And synchronous_standby_names on postgres-1 is set to 'ANY 1 ("postgres-0")' after 2 seconds
+
+  Scenario: check behavior with three nodes and different replication factor
+    Given I start postgres-2
+    Then sync key in DCS has sync_standby=postgres-0,postgres-2 after 10 seconds
+    And sync key in DCS has quorum=1 after 2 seconds
+    And synchronous_standby_names on postgres-1 is set to 'ANY 1 ("postgres-0","postgres-2")' after 2 seconds
+    When I issue a PATCH request to http://127.0.0.1:8009/config with {"synchronous_node_count": 2}
+    Then sync key in DCS has quorum=0 after 10 seconds
+    And synchronous_standby_names on postgres-1 is set to 'ANY 2 ("postgres-0","postgres-2")' after 2 seconds
+
+  Scenario: switch from quorum replication to good old multisync and back
+    Given I issue a PATCH request to http://127.0.0.1:8009/config with {"synchronous_mode": true, "synchronous_node_count": 1}
+    And I shut down postgres-0
+    Then synchronous_standby_names on postgres-1 is set to '"postgres-2"' after 10 seconds
+    And sync key in DCS has sync_standby=postgres-2 after 10 seconds
+    Then sync key in DCS has quorum=0 after 2 seconds
+    When I issue a PATCH request to http://127.0.0.1:8009/config with {"synchronous_mode": "quorum"}
+    And I start postgres-0
+    Then synchronous_standby_names on postgres-1 is set to 'ANY 1 ("postgres-0","postgres-2")' after 10 seconds
+    And sync key in DCS has sync_standby=postgres-0,postgres-2 after 10 seconds
+    Then sync key in DCS has quorum=1 after 2 seconds
+
+  Scenario: REST API and patronictl
+    Given I run patronictl.py list batman
+    Then I receive a response returncode 0
+    And I receive a response output "Quorum Standby"
+    And Status code on GET http://127.0.0.1:8008/quorum is 200 after 3 seconds
+    And Status code on GET http://127.0.0.1:8010/quorum is 200 after 3 seconds
+
+  Scenario: nosync node is removed from voters and synchronous_standby_names
+    Given I add tag nosync true to postgres-2 config
+    When I issue an empty POST request to http://127.0.0.1:8010/reload
+    Then I receive a response code 202
+    And sync key in DCS has quorum=0 after 10 seconds
+    And sync key in DCS has sync_standby=postgres-0 after 10 seconds
+    And synchronous_standby_names on postgres-1 is set to 'ANY 1 ("postgres-0")' after 2 seconds
+    And Status code on GET http://127.0.0.1:8010/quorum is 503 after 10 seconds

features/recovery.feature

@@ -2,23 +2,34 @@ Feature: recovery
   We want to check that crashed postgres is started back
 
   Scenario: check that timeline is not incremented when primary is started after crash
-    Given I start postgres0
-    Then postgres0 is a leader after 10 seconds
+    Given I start postgres-0
+    Then postgres-0 is a leader after 10 seconds
     And there is a non empty initialize key in DCS after 15 seconds
-    When I start postgres1
-    And I add the table foo to postgres0
-    Then table foo is present on postgres1 after 20 seconds
-    When I kill postmaster on postgres0
-    Then postgres0 role is the primary after 10 seconds
+    When I start postgres-1
+    And I add the table foo to postgres-0
+    Then table foo is present on postgres-1 after 20 seconds
+    When I kill postmaster on postgres-0
+    Then postgres-0 role is the primary after 10 seconds
     When I issue a GET request to http://127.0.0.1:8008/
     Then I receive a response code 200
-    And I receive a response role master
+    And I receive a response role primary
     And I receive a response timeline 1
+    And "members/postgres-0" key in DCS has state=running after 12 seconds
+    And replication works from postgres-0 to postgres-1 after 15 seconds
 
   Scenario: check immediate failover when master_start_timeout=0
     Given I issue a PATCH request to http://127.0.0.1:8008/config with {"master_start_timeout": 0}
     Then I receive a response code 200
     And Response on GET http://127.0.0.1:8008/config contains master_start_timeout after 10 seconds
-    When I kill postmaster on postgres0
-    Then postgres1 is a leader after 10 seconds
-    And postgres1 role is the primary after 10 seconds
+    When I kill postmaster on postgres-0
+    Then postgres-1 is a leader after 10 seconds
+    And postgres-1 role is the primary after 10 seconds
+
+  Scenario: check crashed primary demotes after failed attempt to start
+    Given I issue a PATCH request to http://127.0.0.1:8009/config with {"master_start_timeout": null}
+    Then I receive a response code 200
+    And postgres-0 role is the replica after 10 seconds
+    When I ensure postgres-1 fails to start after a failure
+    When I kill postmaster on postgres-1
+    Then postgres-0 is a leader after 10 seconds
+    And there is a postgres-1_cb.log with "on_role_change demoted batman" in postgres-1 data directory

features/standby_cluster.feature

@@ -1,7 +1,7 @@
 Feature: standby cluster
   Scenario: prepare the cluster with logical slots
-    Given I start postgres1
-    Then postgres1 is a leader after 10 seconds
+    Given I start postgres-1
+    Then postgres-1 is a leader after 10 seconds
     And there is a non empty initialize key in DCS after 15 seconds
     When I issue a PATCH request to http://127.0.0.1:8009/config with {"slots": {"pm_1": {"type": "physical"}}, "postgresql": {"parameters": {"wal_level": "logical"}}}
     Then I receive a response code 200
@@ -9,62 +9,58 @@ Feature: standby cluster
     And I sleep for 3 seconds
     When I issue a PATCH request to http://127.0.0.1:8009/config with {"slots": {"test_logical": {"type": "logical", "database": "postgres", "plugin": "test_decoding"}}}
     Then I receive a response code 200
-    And I do a backup of postgres1
-    When I start postgres0
-    Then "members/postgres0" key in DCS has state=running after 10 seconds
-    And replication works from postgres1 to postgres0 after 15 seconds
-    When I issue a GET request to http://127.0.0.1:8008/patroni
-    Then I receive a response code 200
-    And I receive a response replication_state streaming
-    And "members/postgres0" key in DCS has replication_state=streaming after 10 seconds
+    And I do a backup of postgres-1
+    When I start postgres-0
+    Then "members/postgres-0" key in DCS has state=running after 10 seconds
+    And replication works from postgres-1 to postgres-0 after 15 seconds
+    And Response on GET http://127.0.0.1:8008/patroni contains replication_state=streaming after 10 seconds
+    And "members/postgres-0" key in DCS has replication_state=streaming after 10 seconds
 
-  @slot-advance
+  @pg110000
   Scenario: check permanent logical slots are synced to the replica
-    Given I run patronictl.py restart batman postgres1 --force
-    Then Logical slot test_logical is in sync between postgres0 and postgres1 after 10 seconds
-    When I add the table replicate_me to postgres1
-    And I get all changes from logical slot test_logical on postgres1
-    Then Logical slot test_logical is in sync between postgres0 and postgres1 after 10 seconds
+    Given I run patronictl.py restart batman postgres-1 --force
+    Then Logical slot test_logical is in sync between postgres-0 and postgres-1 after 10 seconds
 
   Scenario: Detach exiting node from the cluster
-    When I shut down postgres1
-    Then postgres0 is a leader after 10 seconds
-    And "members/postgres0" key in DCS has role=master after 3 seconds
+    When I shut down postgres-1
+    Then postgres-0 is a leader after 10 seconds
+    And "members/postgres-0" key in DCS has role=primary after 5 seconds
     When I issue a GET request to http://127.0.0.1:8008/
     Then I receive a response code 200
 
   Scenario: check replication of a single table in a standby cluster
-    Given I start postgres1 in a standby cluster batman1 as a clone of postgres0
-    Then postgres1 is a leader of batman1 after 10 seconds
-    When I add the table foo to postgres0
-    Then table foo is present on postgres1 after 20 seconds
-    When I issue a GET request to http://127.0.0.1:8009/patroni
-    Then I receive a response code 200
-    And I receive a response replication_state streaming
+    Given I start postgres-1 in a standby cluster batman1 as a clone of postgres-0
+    Then postgres-1 is a leader of batman1 after 10 seconds
+    When I add the table foo to postgres-0
+    Then table foo is present on postgres-1 after 20 seconds
+    And Response on GET http://127.0.0.1:8009/patroni contains replication_state=streaming after 10 seconds
     And I sleep for 3 seconds
     When I issue a GET request to http://127.0.0.1:8009/primary
     Then I receive a response code 503
     When I issue a GET request to http://127.0.0.1:8009/standby_leader
     Then I receive a response code 200
     And I receive a response role standby_leader
-    And there is a postgres1_cb.log with "on_role_change standby_leader batman1" in postgres1 data directory
-    When I start postgres2 in a cluster batman1
-    Then postgres2 role is the replica after 24 seconds
-    And table foo is present on postgres2 after 20 seconds
-    When I issue a GET request to http://127.0.0.1:8010/patroni
-    Then I receive a response code 200
-    And I receive a response replication_state streaming
-    And postgres1 does not have a logical replication slot named test_logical
+    And there is a postgres-1_cb.log with "on_role_change standby_leader batman1" in postgres-1 data directory
+    When I start postgres-2 in a cluster batman1
+    Then postgres-2 role is the replica after 24 seconds
+    And postgres-2 is replicating from postgres-1 after 10 seconds
+    And table foo is present on postgres-2 after 20 seconds
+    And Response on GET http://127.0.0.1:8010/patroni contains replication_state=streaming after 10 seconds
+    And postgres-1 does not have a replication slot named test_logical
+
+  Scenario: check switchover
+    Given I run patronictl.py switchover batman1 --force
+    Then Status code on GET http://127.0.0.1:8010/standby_leader is 200 after 10 seconds
+    And postgres-1 is replicating from postgres-2 after 32 seconds
+    And there is a postgres-2_cb.log with "on_start replica batman1\non_role_change standby_leader batman1" in postgres-2 data directory
 
   Scenario: check failover
-    When I kill postgres1
-    And I kill postmaster on postgres1
-    Then postgres2 is replicating from postgres0 after 32 seconds
-    When I issue a GET request to http://127.0.0.1:8010/primary
+    When I kill postgres-2
+    And I kill postmaster on postgres-2
+    Then postgres-1 is replicating from postgres-0 after 32 seconds
+    And Status code on GET http://127.0.0.1:8009/standby_leader is 200 after 10 seconds
+    When I issue a GET request to http://127.0.0.1:8009/primary
     Then I receive a response code 503
-    And I sleep for 3 seconds
-    When I issue a GET request to http://127.0.0.1:8010/standby_leader
-    Then I receive a response code 200
     And I receive a response role standby_leader
-    And replication works from postgres0 to postgres2 after 15 seconds
-    And there is a postgres2_cb.log with "on_start replica batman1\non_role_change standby_leader batman1" in postgres2 data directory
+    And replication works from postgres-0 to postgres-1 after 15 seconds
+    And there is a postgres-1_cb.log with "on_role_change replica batman1\non_role_change standby_leader batman1" in postgres-1 data directory

features/steps/basic_replication.py

@@ -1,15 +1,28 @@
-import patroni.psycopg as pg
+import json
 
-from behave import step, then
 from time import sleep, time
 
+import parse
 
-@step('I start {name:w}')
+from behave import register_type, step, then
+
+import patroni.psycopg as pg
+
+
+@parse.with_pattern(r'[a-z][a-z0-9_\-]*[a-z0-9]')
+def parse_name(text):
+    return text
+
+
+register_type(name=parse_name)
+
+
+@step('I start {name:name}')
 def start_patroni(context, name):
     return context.pctl.start(name)
 
 
-@step('I start duplicate {name:w} on port {port:d}')
+@step('I start duplicate {name:name} on port {port:d}')
 def start_duplicate_patroni(context, name, port):
     config = {
         "name": name,
@@ -25,42 +38,51 @@ def start_duplicate_patroni(context, name, port):
             "No error was raised by duplicate start of {0} ".format(name)
 
 
-@step('I shut down {name:w}')
+@step('I shut down {name:name}')
 def stop_patroni(context, name):
     return context.pctl.stop(name, timeout=60)
 
 
-@step('I kill {name:w}')
+@step('I kill {name:name}')
 def kill_patroni(context, name):
     return context.pctl.stop(name, kill=True)
 
 
-@step('I kill postmaster on {name:w}')
+@step('I shut down postmaster on {name:name}')
 def stop_postgres(context, name):
     return context.pctl.stop(name, postgres=True)
 
 
-@step('I add the table {table_name:w} to {pg_name:w}')
+@step('I kill postmaster on {name:name}')
+def kill_postgres(context, name):
+    return context.pctl.stop(name, kill=True, postgres=True)
+
+
+def get_wal_name(context, pg_name):
+    version = context.pctl.query(pg_name, "SHOW server_version_num").fetchone()[0]
+    return 'xlog' if int(version) / 10000 < 10 else 'wal'
+
+
+@step('I add the table {table_name:w} to {pg_name:name}')
 def add_table(context, table_name, pg_name):
     # parse the configuration file and get the port
     try:
         context.pctl.query(pg_name, "CREATE TABLE public.{0}()".format(table_name))
+        context.pctl.query(pg_name, "SELECT pg_switch_{0}()".format(get_wal_name(context, pg_name)))
     except pg.Error as e:
         assert False, "Error creating table {0} on {1}: {2}".format(table_name, pg_name, e)
 
 
-@step('I {action:w} wal replay on {pg_name:w}')
+@step('I {action:w} wal replay on {pg_name:name}')
 def toggle_wal_replay(context, action, pg_name):
     # pause or resume the wal replay process
     try:
-        version = context.pctl.query(pg_name, "SHOW server_version_num").fetchone()[0]
-        wal_name = 'xlog' if int(version) / 10000 < 10 else 'wal'
-        context.pctl.query(pg_name, "SELECT pg_{0}_replay_{1}()".format(wal_name, action))
+        context.pctl.query(pg_name, "SELECT pg_{0}_replay_{1}()".format(get_wal_name(context, pg_name), action))
     except pg.Error as e:
         assert False, "Error during {0} wal recovery on {1}: {2}".format(action, pg_name, e)
 
 
-@step('I {action:w} table on {pg_name:w}')
+@step('I {action:w} table on {pg_name:name}')
 def crdr_mytest(context, action, pg_name):
     try:
         if (action == "create"):
@@ -71,7 +93,7 @@ def crdr_mytest(context, action, pg_name):
         assert False, "Error {0} table mytest on {1}: {2}".format(action, pg_name, e)
 
 
-@step('I load data on {pg_name:w}')
+@step('I load data on {pg_name:name}')
 def initiate_load(context, pg_name):
     # perform dummy load
     try:
@@ -80,7 +102,7 @@ def initiate_load(context, pg_name):
         assert False, "Error loading test data on {0}: {1}".format(pg_name, e)
 
 
-@then('Table {table_name:w} is present on {pg_name:w} after {max_replication_delay:d} seconds')
+@then('Table {table_name:w} is present on {pg_name:name} after {max_replication_delay:d} seconds')
 def table_is_present_on(context, table_name, pg_name, max_replication_delay):
     max_replication_delay *= context.timeout_multiplier
     for _ in range(int(max_replication_delay)):
@@ -92,24 +114,31 @@ def table_is_present_on(context, table_name, pg_name, max_replication_delay):
             "Table {0} is not present on {1} after {2} seconds".format(table_name, pg_name, max_replication_delay)
 
 
-@then('{pg_name:w} role is the {pg_role:w} after {max_promotion_timeout:d} seconds')
+@then('{pg_name:name} role is the {pg_role:w} after {max_promotion_timeout:d} seconds')
 def check_role(context, pg_name, pg_role, max_promotion_timeout):
     max_promotion_timeout *= context.timeout_multiplier
     assert context.pctl.check_role_has_changed_to(pg_name, pg_role, timeout=int(max_promotion_timeout)), \
         "{0} role didn't change to {1} after {2} seconds".format(pg_name, pg_role, max_promotion_timeout)
 
 
-@step('replication works from {primary:w} to {replica:w} after {time_limit:d} seconds')
-@then('replication works from {primary:w} to {replica:w} after {time_limit:d} seconds')
+@step('replication works from {primary:name} to {replica:name} after {time_limit:d} seconds')
+@then('replication works from {primary:name} to {replica:name} after {time_limit:d} seconds')
 def replication_works(context, primary, replica, time_limit):
     context.execute_steps(u"""
         When I add the table test_{0} to {1}
         Then table test_{0} is present on {2} after {3} seconds
-    """.format(int(time()), primary, replica, time_limit))
+    """.format(str(time()).replace('.', '_').replace(',', '_'), primary, replica, time_limit))
 
 
-@then('there is a "{message}" {level:w} in the {node} patroni log')
-def check_patroni_log(context, message, level, node):
-    messsages_of_level = context.pctl.read_patroni_log(node, level)
-    assert any(message in line for line in messsages_of_level), \
-        "There was no {0} {1} in the {2} patroni log".format(message, level, node)
+@step('there is one of {message_list} {level:w} in the {node} patroni log after {timeout:d} seconds')
+def check_patroni_log(context, message_list, level, node, timeout):
+    timeout *= context.timeout_multiplier
+    message_list = json.loads(message_list)
+
+    for _ in range(int(timeout)):
+        messages_of_level = context.pctl.read_patroni_log(node, level)
+        if any(any(message in line for line in messages_of_level) for message in message_list):
+            break
+        sleep(1)
+    else:
+        assert False, f"There were none of {message_list} {level} in the {node} patroni log after {timeout} seconds"

features/steps/bootstrap_labels.py

@@ -0,0 +1,31 @@
+from behave import step, then
+
+
+@step('I start {name:name} in a cluster {cluster_name:w} as a long-running clone of {name2:name}')
+def start_cluster_clone(context, name, cluster_name, name2):
+    context.pctl.clone(name2, cluster_name, name, True)
+
+
+@step('I start {name:name} in cluster {cluster_name:w} using long-running backup_restore')
+def start_patroni(context, name, cluster_name):
+    return context.pctl.start(name, custom_config={
+        "scope": cluster_name,
+        "postgresql": {
+            'create_replica_methods': ['backup_restore'],
+            "backup_restore": context.pctl.backup_restore_config(long_running=True),
+            'authentication': {
+                'superuser': {'password': 'patroni1'},
+                'replication': {'password': 'rep-pass1'}
+            }
+        }
+    }, max_wait_limit=-1)
+
+
+@then('{name:name} is labeled with "{label:w}"')
+def pod_labeled(context, name, label):
+    assert label in context.dcs_ctl.pod_labels(name), f'pod {name} is not labeled with {label}'
+
+
+@then('{name:name} is not labeled with "{label:w}"')
+def pod_not_labeled(context, name, label):
+    assert label not in context.dcs_ctl.pod_labels(name), f'pod {name} is still labeled with {label}'

features/steps/cascading_replication.py

@@ -4,18 +4,18 @@ import time
 from behave import step, then
 
 
-@step('I configure and start {name:w} with a tag {tag_name:w} {tag_value:w}')
+@step('I configure and start {name:name} with a tag {tag_name:w} {tag_value}')
 def start_patroni_with_a_name_value_tag(context, name, tag_name, tag_value):
     return context.pctl.start(name, custom_config={'tags': {tag_name: tag_value}})
 
 
-@then('There is a {label} with "{content}" in {name:w} data directory')
+@then('There is a {label} with "{content}" in {name:name} data directory')
 def check_label(context, label, content, name):
     value = (context.pctl.read_label(name, label) or '').replace('\n', '\\n')
     assert content in value, "\"{0}\" in {1} doesn't contain {2}".format(value, label, content)
 
 
-@step('I create label with "{content:w}" in {name:w} data directory')
+@step('I create label with "{content}" in {name:name} data directory')
 def write_label(context, content, name):
     context.pctl.write_label(name, content)
 
@@ -28,7 +28,7 @@ def check_member(context, name, key, value, time_limit):
     while time.time() < max_time:
         try:
             response = json.loads(context.dcs_ctl.query(name))
-            dcs_value = response.get(key)
+            dcs_value = str(response.get(key))
             if dcs_value == value:
                 return
         except Exception:

features/steps/citus.py

@@ -1,17 +1,18 @@
 import json
 import time
 
-from behave import step, then
-from dateutil import tz
 from datetime import datetime
 from functools import partial
-from threading import Thread, Event
+from threading import Event, Thread
+
+from behave import step, then
+from dateutil import tz
 
 tzutc = tz.tzutc()
 
 
-@step('{name:w} is a leader in a group {group:d} after {time_limit:d} seconds')
-@then('{name:w} is a leader in a group {group:d} after {time_limit:d} seconds')
+@step('{name:name} is a leader in a group {group:d} after {time_limit:d} seconds')
+@then('{name:name} is a leader in a group {group:d} after {time_limit:d} seconds')
 def is_a_group_leader(context, name, group, time_limit):
     time_limit *= context.timeout_multiplier
     max_time = time.time() + int(time_limit)
@@ -39,12 +40,12 @@ def check_group_member(context, name, group, key, value, time_limit):
                    " after {5} seconds").format(name, group, key, value, response, time_limit)
 
 
-@step('I start {name:w} in citus group {group:d}')
+@step('I start {name:name} in citus group {group:d}')
 def start_citus(context, name, group):
     return context.pctl.start(name, custom_config={"citus": {"database": "postgres", "group": int(group)}})
 
 
-@step('{name1:w} is registered in the {name2:w} as the {role:w} in group {group:d} after {time_limit:d} seconds')
+@step('{name1:name} is registered in the {name2:name} as the {role:w} in group {group:d} after {time_limit:d} seconds')
 def check_registration(context, name1, name2, role, group, time_limit):
     time_limit *= context.timeout_multiplier
     max_time = time.time() + int(time_limit)
@@ -64,13 +65,13 @@ def check_registration(context, name1, name2, role, group, time_limit):
     assert False, "Node {0} is not registered in pg_dist_node on the node {1}".format(name1, name2)
 
 
-@step('I create a distributed table on {name:w}')
+@step('I create a distributed table on {name:name}')
 def create_distributed_table(context, name):
     context.pctl.query(name, 'CREATE TABLE public.d(id int not null)')
     context.pctl.query(name, "SELECT create_distributed_table('public.d', 'id')")
 
 
-@step('I cleanup a distributed table on {name:w}')
+@step('I cleanup a distributed table on {name:name}')
 def cleanup_distributed_table(context, name):
     context.pctl.query(name, 'TRUNCATE public.d')
 
@@ -86,7 +87,7 @@ def insert_thread(query_func, context):
         context.thread_stop_event.wait(0.01)
 
 
-@step('I start a thread inserting data on {name:w}')
+@step('I start a thread inserting data on {name:name}')
 def start_insert_thread(context, name):
     context.thread_stop_event = Event()
     context.insert_counter = 0
@@ -109,21 +110,27 @@ def stop_insert_thread(context):
     assert not context.thread.is_alive(), "Thread is still alive"
 
 
-@step("a distributed table on {name:w} has expected rows")
+@step("a distributed table on {name:name} has expected rows")
 def count_rows(context, name):
     rows = context.pctl.query(name, "SELECT COUNT(*) FROM public.d").fetchone()[0]
     assert rows == context.insert_counter, "Distributed table doesn't have expected amount of rows"
 
 
-@step("There is a transaction in progress on {name:w} changing pg_dist_node")
-def check_transaction(context, name):
-    cur = context.pctl.query(name, "SELECT xact_start FROM pg_stat_activity WHERE pid <> pg_backend_pid()"
-                                   " AND state = 'idle in transaction' AND query ~ 'citus_update_node'")
-    assert cur.rowcount == 1, "There is no idle in transaction updating pg_dist_node"
-    context.xact_start = cur.fetchone()[0]
+@step("there is a transaction in progress on {name:name} changing pg_dist_node after {time_limit:d} seconds")
+def check_transaction(context, name, time_limit):
+    time_limit *= context.timeout_multiplier
+    max_time = time.time() + int(time_limit)
+    while time.time() < max_time:
+        cur = context.pctl.query(name, "SELECT xact_start FROM pg_stat_activity WHERE pid <> pg_backend_pid()"
+                                       " AND state = 'idle in transaction' AND query ~ 'citus_update_node'")
+        if cur.rowcount == 1:
+            context.xact_start = cur.fetchone()[0]
+            return
+        time.sleep(1)
+    assert False, f"There is no idle in transaction on {name} updating pg_dist_node after {time_limit} seconds"
 
 
 @step("a transaction finishes in {timeout:d} seconds")
 def check_transaction_timeout(context, timeout):
-    assert (datetime.now(tzutc) - context.xact_start).seconds > timeout, \
+    assert (datetime.now(tzutc) - context.xact_start).seconds >= timeout, \
         "a transaction finished earlier than in {0} seconds".format(timeout)

features/steps/custom_bootstrap.py

@@ -3,17 +3,17 @@ import time
 from behave import step, then
 
 
-@step('I start {name:w} in a cluster {cluster_name:w} as a clone of {name2:w}')
+@step('I start {name:name} in a cluster {cluster_name:w} as a clone of {name2:name}')
 def start_cluster_clone(context, name, cluster_name, name2):
     context.pctl.clone(name2, cluster_name, name)
 
 
-@step('I start {name:w} in a cluster {cluster_name:w} from backup')
+@step('I start {name:name} in a cluster {cluster_name:w} from backup')
 def start_cluster_from_backup(context, name, cluster_name):
     context.pctl.bootstrap_from_backup(name, cluster_name)
 
 
-@then('{name:w} is a leader of {cluster_name:w} after {time_limit:d} seconds')
+@then('{name:name} is a leader of {cluster_name:w} after {time_limit:d} seconds')
 def is_a_leader(context, name, cluster_name, time_limit):
     time_limit *= context.timeout_multiplier
     max_time = time.time() + int(time_limit)
@@ -22,6 +22,6 @@ def is_a_leader(context, name, cluster_name, time_limit):
         assert time.time() < max_time, "{0} is not a leader in dcs after {1} seconds".format(name, time_limit)
 
 
-@step('I do a backup of {name:w}')
+@step('I do a backup of {name:name}')
 def do_backup(context, name):
     context.pctl.backup(name)

features/steps/dcs_failsafe_mode.py

@@ -11,6 +11,6 @@ def stop_dcs_outage(context):
     context.dcs_ctl.stop_outage()
 
 
-@step('I start {name:w} in a cluster {cluster_name:w} from backup with no_leader')
+@step('I start {name:name} in a cluster {cluster_name:w} from backup with no_leader')
 def start_cluster_from_backup_no_leader(context, name, cluster_name):
     context.pctl.bootstrap_from_backup_no_leader(name, cluster_name)

features/steps/patroni_api.py

@@ -1,14 +1,16 @@
 import json
-import parse
 import shlex
 import subprocess
 import sys
 import time
+
+from datetime import datetime, timedelta
+
+import parse
 import yaml
 
 from behave import register_type, step, then
 from dateutil import tz
-from datetime import datetime, timedelta
 
 tzutc = tz.tzutc()
 
@@ -26,8 +28,8 @@ register_type(url=parse_url)
 # just rely on the database availability, since there is
 # a short gap between the time PostgreSQL becomes available
 # and Patroni assuming the leader role.
-@step('{name:w} is a leader after {time_limit:d} seconds')
-@then('{name:w} is a leader after {time_limit:d} seconds')
+@step('{name:name} is a leader after {time_limit:d} seconds')
+@then('{name:name} is a leader after {time_limit:d} seconds')
 def is_a_leader(context, name, time_limit):
     time_limit *= context.timeout_multiplier
     max_time = time.time() + int(time_limit)
@@ -95,7 +97,7 @@ def do_run(context, cmd):
     context.response = response.decode('utf-8').strip()
 
 
-@then('I receive a response {component:w} {data}')
+@then('I receive a response {component:name} {data}')
 def check_response(context, component, data):
     if component == 'code':
         assert context.status_code == int(data), \
@@ -114,10 +116,10 @@ def check_response(context, component, data):
         assert str(context.response[component]) == str(data), "{0} does not contain {1}".format(component, data)
 
 
-@step('I issue a scheduled switchover from {from_host:w} to {to_host:w} in {in_seconds:d} seconds')
+@step('I issue a scheduled switchover from {from_host:name} to {to_host:name} in {in_seconds:d} seconds')
 def scheduled_switchover(context, from_host, to_host, in_seconds):
     context.execute_steps(u"""
-        Given I run patronictl.py switchover batman --master {0} --candidate {1} --scheduled "{2}" --force
+        Given I run patronictl.py switchover batman --primary {0} --candidate {1} --scheduled "{2}" --force
     """.format(from_host, to_host, datetime.now(tzutc) + timedelta(seconds=int(in_seconds))))
 
 
@@ -128,7 +130,13 @@ def scheduled_restart(context, url, in_seconds, data):
     context.execute_steps(u"""Given I issue a POST request to {0}/restart with {1}""".format(url, json.dumps(data)))
 
 
-@step('I add tag {tag:w} {value:w} to {pg_name:w} config')
+@step('I {action:w} {tag:w} tag in {pg_name:name} config')
+def add_bool_tag_to_config(context, action, tag, pg_name):
+    value = action == 'set'
+    context.pctl.add_tag_to_config(pg_name, tag, value)
+
+
+@step('I add tag {tag:w} {value:w} to {pg_name:name} config')
 def add_tag_to_config(context, tag, value, pg_name):
     context.pctl.add_tag_to_config(pg_name, tag, value)
 
@@ -152,9 +160,24 @@ def check_http_response(context, url, value, timeout, negate=False):
     if context.certfile:
         url = url.replace('http://', 'https://')
     timeout *= context.timeout_multiplier
+    if '=' in value:
+        key, val = value.split('=', 1)
+    else:
+        key, val = value, None
     for _ in range(int(timeout)):
         r = context.request_executor.request('GET', url)
-        if (value in r.data.decode('utf-8')) != negate:
+        data = r.data.decode('utf-8')
+        if val is not None:
+            try:
+                data = json.loads(data)
+                if negate:
+                    if key not in data or data[key] != val:
+                        break
+                elif key in data and data[key] == val:
+                    break
+            except Exception:
+                pass
+        elif (value in r.data.decode('utf-8')) != negate:
             break
         time.sleep(1)
     else:

features/steps/quorum_commit.py

@@ -0,0 +1,60 @@
+import json
+import re
+import time
+
+from behave import step, then
+
+
+@step('sync key in DCS has {key:w}={value} after {time_limit:d} seconds')
+def check_sync(context, key, value, time_limit):
+    time_limit *= context.timeout_multiplier
+    max_time = time.time() + int(time_limit)
+    dcs_value = None
+    while time.time() < max_time:
+        try:
+            response = json.loads(context.dcs_ctl.query('sync'))
+            dcs_value = response.get(key)
+            if key == 'sync_standby' and set((dcs_value or '').split(',')) == set(value.split(',')):
+                return
+            elif str(dcs_value) == value:
+                return
+        except Exception:
+            pass
+        time.sleep(1)
+    assert False, "sync does not have {0}={1} (found {2}) in dcs after {3} seconds".format(key, value,
+                                                                                           dcs_value, time_limit)
+
+
+def _parse_synchronous_standby_names(value):
+    if '(' in value:
+        m = re.match(r'.*(\d+) \(([^)]+)\)', value)
+        expected_value = set(m.group(2).split())
+        expected_num = m.group(1)
+    else:
+        expected_value = set([value])
+        expected_num = '1'
+    return expected_num, expected_value
+
+
+@then("synchronous_standby_names on {name:2} is set to '{value}' after {time_limit:d} seconds")
+def check_synchronous_standby_names(context, name, value, time_limit):
+    time_limit *= context.timeout_multiplier
+    max_time = time.time() + int(time_limit)
+
+    if value == '_empty_str_':
+        value = ''
+
+    expected_num, expected_value = _parse_synchronous_standby_names(value)
+
+    ssn = None
+    while time.time() < max_time:
+        try:
+            ssn = context.pctl.query(name, "SHOW synchronous_standby_names").fetchone()[0]
+            db_num, db_value = _parse_synchronous_standby_names(ssn)
+            if expected_value == db_value and expected_num == db_num:
+                return
+        except Exception:
+            pass
+        time.sleep(1)
+    assert False, "synchronous_standby_names is not set to '{0}' (found '{1}') after {2} seconds".format(value, ssn,
+                                                                                                         time_limit)

features/steps/recovery.py

@@ -0,0 +1,9 @@
+import os
+
+from behave import step
+
+
+@step('I ensure {name:name} fails to start after a failure')
+def spoil_autoconf(context, name):
+    with open(os.path.join(context.pctl._processes[name]._data_dir, 'postgresql.auto.conf'), 'w') as f:
+        f.write('foo=bar')

features/steps/slots.py

@@ -1,35 +1,44 @@
+import json
 import time
 
 from behave import step, then
+
 import patroni.psycopg as pg
 
 
-@step('I create a logical replication slot {slot_name} on {pg_name:w} with the {plugin:w} plugin')
-def create_logical_replication_slot(context, slot_name, pg_name, plugin):
+@step('I create a logical {slot_type} slot {slot_name} on {pg_name:name} with the {plugin:w} plugin')
+def create_logical_replication_slot(context, slot_type, slot_name, pg_name, plugin):
+    failover = ', failover=>true' if slot_type == 'failover' else ''
     try:
-        output = context.pctl.query(pg_name, ("SELECT pg_create_logical_replication_slot('{0}', '{1}'),"
-                                              " current_database()").format(slot_name, plugin))
-        print(output.fetchone())
+        context.pctl.query(pg_name, f"SELECT pg_create_logical_replication_slot('{slot_name}', '{plugin}'{failover})")
     except pg.Error as e:
-        print(e)
-        assert False, "Error creating slot {0} on {1} with plugin {2}".format(slot_name, pg_name, plugin)
+        assert False, "Error creating slot {0} on {1} with plugin {2}: {3}".format(slot_name, pg_name, plugin, e)
 
 
-@then('{pg_name:w} has a logical replication slot named {slot_name} with the {plugin:w} plugin')
-def has_logical_replication_slot(context, pg_name, slot_name, plugin):
-    try:
-        row = context.pctl.query(pg_name, ("SELECT slot_type, plugin FROM pg_replication_slots"
-                                           " WHERE slot_name = '{0}'").format(slot_name)).fetchone()
-        assert row, "Couldn't find replication slot named {0}".format(slot_name)
-        assert row[0] == "logical", "Found replication slot named {0} but wasn't a logical slot".format(slot_name)
-        assert row[1] == plugin, ("Found replication slot named {0} but was using plugin "
-                                  "{1} rather than {2}").format(slot_name, row[1], plugin)
-    except pg.Error:
-        assert False, "Error looking for slot {0} on {1} with plugin {2}".format(slot_name, pg_name, plugin)
+@step('{pg_name:name} has a logical replication slot named {slot_name}'
+      ' with the {plugin:w} plugin after {time_limit:d} seconds')
+@then('{pg_name:name} has a logical replication slot named {slot_name}'
+      ' with the {plugin:w} plugin after {time_limit:d} seconds')
+def has_logical_replication_slot(context, pg_name, slot_name, plugin, time_limit):
+    time_limit *= context.timeout_multiplier
+    max_time = time.time() + int(time_limit)
+    while time.time() < max_time:
+        try:
+            row = context.pctl.query(pg_name, ("SELECT slot_type, plugin FROM pg_replication_slots"
+                                               f" WHERE slot_name = '{slot_name}'")).fetchone()
+            if row:
+                assert row[0] == "logical", f"Replication slot {slot_name} isn't a logical but {row[0]}"
+                assert row[1] == plugin, f"Replication slot {slot_name} using plugin {row[1]} rather than {plugin}"
+                return
+        except Exception:
+            pass
+        time.sleep(1)
+    assert False, f"Error looking for slot {slot_name} on {pg_name} with plugin {plugin}"
 
 
-@then('{pg_name:w} does not have a logical replication slot named {slot_name}')
-def does_not_have_logical_replication_slot(context, pg_name, slot_name):
+@step('{pg_name:name} does not have a replication slot named {slot_name:w}')
+@then('{pg_name:name} does not have a replication slot named {slot_name:w}')
+def does_not_have_replication_slot(context, pg_name, slot_name):
     try:
         row = context.pctl.query(pg_name, ("SELECT 1 FROM pg_replication_slots"
                                            " WHERE slot_name = '{0}'").format(slot_name)).fetchone()
@@ -38,13 +47,15 @@ def does_not_have_logical_replication_slot(context, pg_name, slot_name):
         assert False, "Error looking for slot {0} on {1}".format(slot_name, pg_name)
 
 
-@step('Logical slot {slot_name:w} is in sync between {pg_name1:w} and {pg_name2:w} after {time_limit:d} seconds')
-def logical_slots_in_sync(context, slot_name, pg_name1, pg_name2, time_limit):
+@step('{slot_type:w} slot {slot_name:w} is in sync between '
+      '{pg_name1:name} and {pg_name2:name} after {time_limit:d} seconds')
+def slots_in_sync(context, slot_type, slot_name, pg_name1, pg_name2, time_limit):
     time_limit *= context.timeout_multiplier
     max_time = time.time() + int(time_limit)
+    column = 'confirmed_flush_lsn' if slot_type.lower() == 'logical' else 'restart_lsn'
+    query = f"SELECT {column} FROM pg_replication_slots WHERE slot_name = '{slot_name}'"
     while time.time() < max_time:
         try:
-            query = "SELECT confirmed_flush_lsn FROM pg_replication_slots WHERE slot_name = '{0}'".format(slot_name)
             slot1 = context.pctl.query(pg_name1, query).fetchone()
             slot2 = context.pctl.query(pg_name2, query).fetchone()
             if slot1[0] == slot2[0]:
@@ -52,9 +63,63 @@ def logical_slots_in_sync(context, slot_name, pg_name1, pg_name2, time_limit):
         except Exception:
             pass
         time.sleep(1)
-    assert False, "Logical slot {0} is not in sync between {1} and {2}".format(slot_name, pg_name1, pg_name2)
+    assert False, \
+        f"{slot_type} slot {slot_name} is not in sync between {pg_name1} and {pg_name2} after {time_limit} seconds"
 
 
-@step('I get all changes from logical slot {slot_name:w} on {pg_name:w}')
+@step('I get all changes from logical slot {slot_name:w} on {pg_name:name}')
 def logical_slot_get_changes(context, slot_name, pg_name):
     context.pctl.query(pg_name, "SELECT * FROM pg_logical_slot_get_changes('{0}', NULL, NULL)".format(slot_name))
+
+
+@step('I get all changes from physical slot {slot_name:w} on {pg_name:name}')
+def physical_slot_get_changes(context, slot_name, pg_name):
+    context.pctl.query(pg_name, f"SELECT * FROM pg_replication_slot_advance('{slot_name}', pg_current_wal_lsn())")
+
+
+@step('{pg_name:name} has a physical replication slot named {slot_name} after {time_limit:d} seconds')
+def has_physical_replication_slot(context, pg_name, slot_name, time_limit):
+    time_limit *= context.timeout_multiplier
+    max_time = time.time() + int(time_limit)
+    query = f"SELECT * FROM pg_catalog.pg_replication_slots WHERE slot_type = 'physical' AND slot_name = '{slot_name}'"
+    while time.time() < max_time:
+        try:
+            row = context.pctl.query(pg_name, query).fetchone()
+            if row:
+                return
+        except Exception:
+            pass
+        time.sleep(1)
+    assert False, f"Physical slot {slot_name} doesn't exist after {time_limit} seconds"
+
+
+@step('physical replication slot named {slot_name} on {pg_name:name} has no xmin value after {time_limit:d} seconds')
+def physical_slot_no_xmin(context, pg_name, slot_name, time_limit):
+    time_limit *= context.timeout_multiplier
+    max_time = time.time() + int(time_limit)
+    query = "SELECT xmin FROM pg_catalog.pg_replication_slots WHERE slot_type = 'physical'" +\
+        f" AND slot_name = '{slot_name}'"
+    exists = False
+    while time.time() < max_time:
+        try:
+            row = context.pctl.query(pg_name, query).fetchone()
+            exists = bool(row)
+            if exists and row[0] is None:
+                return
+        except Exception:
+            pass
+        time.sleep(1)
+    assert False, f"Physical slot {slot_name} doesn't exist after {time_limit} seconds" if not exists \
+        else f"Physical slot {slot_name} has xmin value after {time_limit} seconds"
+
+
+@step('"{name}" key in DCS has {subkey} in {key:w}')
+def dcs_key_contains(context, name, subkey, key):
+    response = json.loads(context.dcs_ctl.query(name))
+    assert key in response and subkey in response[key], f"{name} key in DCS doesn't have {subkey} in {key}"
+
+
+@step('"{name}" key in DCS does not have {subkey} in {key:w}')
+def dcs_key_does_not_contain(context, name, subkey, key):
+    response = json.loads(context.dcs_ctl.query(name))
+    assert key not in response or subkey not in response[key], f"{name} key in DCS has {subkey} in {key}"

features/steps/standby_cluster.py

@@ -9,20 +9,18 @@ def callbacks(context, name):
             for c in ('on_start', 'on_stop', 'on_restart', 'on_role_change')}
 
 
-@step('I start {name:w} in a cluster {cluster_name:w}')
+@step('I start {name:name} in a cluster {cluster_name:w}')
 def start_patroni(context, name, cluster_name):
     return context.pctl.start(name, custom_config={
         "scope": cluster_name,
         "postgresql": {
             "callbacks": callbacks(context, name),
-            "backup_restore": {
-                "command": (context.pctl.PYTHON + " features/backup_restore.py --sourcedir="
-                            + os.path.join(context.pctl.patroni_path, 'data', 'basebackup').replace('\\', '/'))}
+            "backup_restore": context.pctl.backup_restore_config()
         }
     })
 
 
-@step('I start {name:w} in a standby cluster {cluster_name:w} as a clone of {name2:w}')
+@step('I start {name:name} in a standby cluster {cluster_name:w} as a clone of {name2:name}')
 def start_patroni_standby_cluster(context, name, cluster_name, name2):
     # we need to remove patroni.dynamic.json in order to "bootstrap" standby cluster with existing PGDATA
     os.unlink(os.path.join(context.pctl._processes[name]._data_dir, 'patroni.dynamic.json'))
@@ -34,6 +32,7 @@ def start_patroni_standby_cluster(context, name, cluster_name, name2):
                 "ttl": 20,
                 "loop_wait": 2,
                 "retry_timeout": 5,
+                "synchronous_mode": True,  # should be completely ignored
                 "standby_cluster": {
                     "host": "localhost",
                     "port": port,
@@ -50,7 +49,7 @@ def start_patroni_standby_cluster(context, name, cluster_name, name2):
     return context.pctl.start(name)
 
 
-@step('{pg_name1:w} is replicating from {pg_name2:w} after {timeout:d} seconds')
+@step('{pg_name1:name} is replicating from {pg_name2:name} after {timeout:d} seconds')
 def check_replication_status(context, pg_name1, pg_name2, timeout):
     bound_time = time.time() + timeout * context.timeout_multiplier
 

features/steps/watchdog.py

@@ -1,6 +1,7 @@
-from behave import step, then
 import time
 
+from behave import step, then
+
 
 def polling_loop(timeout, interval=1):
     """Returns an iterator that returns values until timeout has passed. Timeout is measured from start of iteration."""
@@ -13,12 +14,12 @@ def polling_loop(timeout, interval=1):
         time.sleep(interval)
 
 
-@step('I start {name:w} with watchdog')
+@step('I start {name:name} with watchdog')
 def start_patroni_with_watchdog(context, name):
     return context.pctl.start(name, custom_config={'watchdog': True, 'bootstrap': {'dcs': {'ttl': 20}}})
 
 
-@step('{name:w} watchdog has been pinged after {timeout:d} seconds')
+@step('{name:name} watchdog has been pinged after {timeout:d} seconds')
 def watchdog_was_pinged(context, name, timeout):
     for _ in polling_loop(timeout):
         if context.pctl.get_watchdog(name).was_pinged:
@@ -26,22 +27,22 @@ def watchdog_was_pinged(context, name, timeout):
     return False
 
 
-@then('{name:w} watchdog has been closed')
+@then('{name:name} watchdog has been closed')
 def watchdog_was_closed(context, name):
     assert context.pctl.get_watchdog(name).was_closed
 
 
-@step('{name:w} watchdog has a {timeout:d} second timeout')
+@step('{name:name} watchdog has a {timeout:d} second timeout')
 def watchdog_has_timeout(context, name, timeout):
     assert context.pctl.get_watchdog(name).timeout == timeout
 
 
-@step('I reset {name:w} watchdog state')
+@step('I reset {name:name} watchdog state')
 def watchdog_reset_pinged(context, name):
     context.pctl.get_watchdog(name).reset()
 
 
-@then('{name:w} watchdog is triggered after {timeout:d} seconds')
+@then('{name:name} watchdog is triggered after {timeout:d} seconds')
 def watchdog_was_triggered(context, name, timeout):
     for _ in polling_loop(timeout):
         if context.pctl.get_watchdog(name).was_triggered:
@@ -49,6 +50,6 @@ def watchdog_was_triggered(context, name, timeout):
     assert False
 
 
-@step('{name:w} hangs for {timeout:d} seconds')
+@step('{name:name} hangs for {timeout:d} seconds')
 def patroni_hang(context, name, timeout):
     return context.pctl.patroni_hang(name, timeout)

features/watchdog.feature

@@ -2,38 +2,38 @@ Feature: watchdog
   Verify that watchdog gets pinged and triggered under appropriate circumstances.
 
   Scenario: watchdog is opened and pinged
-    Given I start postgres0 with watchdog
-    Then postgres0 is a leader after 10 seconds
-    And postgres0 role is the primary after 10 seconds
-    And postgres0 watchdog has been pinged after 10 seconds
-    And postgres0 watchdog has a 15 second timeout
+    Given I start postgres-0 with watchdog
+    Then postgres-0 is a leader after 10 seconds
+    And postgres-0 role is the primary after 10 seconds
+    And postgres-0 watchdog has been pinged after 10 seconds
+    And postgres-0 watchdog has a 15 second timeout
 
   Scenario: watchdog is reconfigured after global ttl changed
     Given I run patronictl.py edit-config batman -s ttl=30 --force
     Then I receive a response returncode 0
     And I receive a response output "+ttl: 30"
     When I sleep for 4 seconds
-    Then postgres0 watchdog has a 25 second timeout
+    Then postgres-0 watchdog has a 25 second timeout
 
   Scenario: watchdog is disabled during pause
     Given I run patronictl.py pause batman
     Then I receive a response returncode 0
     When I sleep for 2 seconds
-    Then postgres0 watchdog has been closed
+    Then postgres-0 watchdog has been closed
 
   Scenario: watchdog is opened and pinged after resume
-    Given I reset postgres0 watchdog state
+    Given I reset postgres-0 watchdog state
     And I run patronictl.py resume batman
     Then I receive a response returncode 0
-    And postgres0 watchdog has been pinged after 10 seconds
+    And postgres-0 watchdog has been pinged after 10 seconds
 
   Scenario: watchdog is disabled when shutting down
-    Given I shut down postgres0
-    Then postgres0 watchdog has been closed
+    Given I shut down postgres-0
+    Then postgres-0 watchdog has been closed
 
   Scenario: watchdog is triggered if patroni stops responding
-    Given I reset postgres0 watchdog state
-    And I start postgres0 with watchdog
-    Then postgres0 role is the primary after 10 seconds
-    When postgres0 hangs for 30 seconds
-    Then postgres0 watchdog is triggered after 30 seconds
+    Given I reset postgres-0 watchdog state
+    And I start postgres-0 with watchdog
+    Then postgres-0 role is the primary after 10 seconds
+    When postgres-0 hangs for 30 seconds
+    Then postgres-0 watchdog is triggered after 30 seconds

kubernetes/Dockerfile

@@ -1,4 +1,4 @@
-FROM postgres:15
+FROM postgres:16
 LABEL maintainer="Alexander Kukushkin <[email protected]>"
 
 RUN export DEBIAN_FRONTEND=noninteractive \
@@ -9,8 +9,8 @@ RUN export DEBIAN_FRONTEND=noninteractive \
             | xargs apt-get install -y vim-tiny curl jq locales git python3-pip python3-wheel \
     ## Make sure we have a en_US.UTF-8 locale available
     && localedef -i en_US -c -f UTF-8 -A /usr/share/locale/locale.alias en_US.UTF-8 \
-    && pip3 install setuptools \
-    && pip3 install 'git+https://github.com/zalando/patroni.git#egg=patroni[kubernetes]' \
+    && pip3 install --break-system-packages setuptools \
+    && pip3 install --break-system-packages 'git+https://github.com/patroni/patroni.git#egg=patroni[kubernetes]' \
     && PGHOME=/home/postgres \
     && mkdir -p $PGHOME \
     && chown postgres $PGHOME \

kubernetes/Dockerfile.citus

@@ -1,4 +1,4 @@
-FROM postgres:15
+FROM postgres:16
 LABEL maintainer="Alexander Kukushkin <[email protected]>"
 
 RUN export DEBIAN_FRONTEND=noninteractive \
@@ -10,12 +10,24 @@ RUN export DEBIAN_FRONTEND=noninteractive \
             | xargs apt-get install -y busybox vim-tiny curl jq less locales git python3-pip python3-wheel lsb-release \
     ## Make sure we have a en_US.UTF-8 locale available
     && localedef -i en_US -c -f UTF-8 -A /usr/share/locale/locale.alias en_US.UTF-8 \
-    && echo "deb [signed-by=/etc/apt/trusted.gpg.d/citusdata_community.gpg] https://packagecloud.io/citusdata/community/debian/ $(lsb_release -cs) main" > /etc/apt/sources.list.d/citusdata_community.list \
-    && curl -sL https://packagecloud.io/citusdata/community/gpgkey | gpg --dearmor > /etc/apt/trusted.gpg.d/citusdata_community.gpg \
-    && apt-get update -y \
-    && apt-get -y install postgresql-$PG_MAJOR-citus-11.3 \
-    && pip3 install setuptools \
-    && pip3 install 'git+https://github.com/zalando/patroni.git#egg=patroni[kubernetes]' \
+    && if [ $(dpkg --print-architecture) = 'arm64' ]; then \
+        apt-get install -y postgresql-server-dev-16 \
+                           gcc make autoconf \
+                           libc6-dev flex libcurl4-gnutls-dev \
+                           libicu-dev libkrb5-dev liblz4-dev \
+                           libpam0g-dev libreadline-dev libselinux1-dev\
+                           libssl-dev libxslt1-dev libzstd-dev uuid-dev \
+        && git clone -b "main" https://github.com/citusdata/citus.git \
+        && MAKEFLAGS="-j $(grep -c ^processor /proc/cpuinfo)" \
+        && cd citus && ./configure && make install && cd ../ && rm -rf /citus; \
+    else \
+        echo "deb [signed-by=/etc/apt/trusted.gpg.d/citusdata_community.gpg] https://packagecloud.io/citusdata/community/debian/ $(lsb_release -cs) main" > /etc/apt/sources.list.d/citusdata_community.list \
+        && curl -sL https://packagecloud.io/citusdata/community/gpgkey | gpg --dearmor > /etc/apt/trusted.gpg.d/citusdata_community.gpg \
+        && apt-get update -y \
+        && apt-get -y install postgresql-16-citus-12.1; \
+    fi \
+    && pip3 install --break-system-packages setuptools \
+    && pip3 install --break-system-packages 'git+https://github.com/patroni/patroni.git#egg=patroni[kubernetes]' \
     && PGHOME=/home/postgres \
     && mkdir -p $PGHOME \
     && chown postgres $PGHOME \
@@ -26,6 +38,9 @@ RUN export DEBIAN_FRONTEND=noninteractive \
     && chmod 664 /etc/passwd \
     # Clean up
     && apt-get remove -y git python3-pip python3-wheel \
+               postgresql-server-dev-16 gcc make autoconf \
+               libc6-dev flex libicu-dev libkrb5-dev liblz4-dev \
+               libpam0g-dev libreadline-dev libselinux1-dev libssl-dev libxslt1-dev libzstd-dev uuid-dev \
     && apt-get autoremove -y \
     && apt-get clean -y \
     && rm -rf /var/lib/apt/lists/* /root/.cache

kubernetes/README.md

@@ -23,7 +23,7 @@ Example session:
 
     $ docker build -t patroni .
     Sending build context to Docker daemon  138.8kB
-    Step 1/9 : FROM postgres:15
+    Step 1/9 : FROM postgres:16
     ...
     Successfully built e9bfe69c5d2b
     Successfully tagged patroni:latest
@@ -46,7 +46,7 @@ Example session:
 
     $ kubectl get pods -L role
     NAME            READY   STATUS    RESTARTS   AGE   ROLE
-    patronidemo-0   1/1     Running   0          34s   master
+    patronidemo-0   1/1     Running   0          34s   primary
     patronidemo-1   1/1     Running   0          30s   replica
     patronidemo-2   1/1     Running   0          26s   replica
 
@@ -82,7 +82,7 @@ Example session:
 
     demo@localhost:~/git/patroni/kubernetes$ docker build -f Dockerfile.citus -t patroni-citus-k8s .
     Sending build context to Docker daemon  138.8kB
-    Step 1/11 : FROM postgres:15
+    Step 1/11 : FROM postgres:16
     ...
     Successfully built 8cd73e325028
     Successfully tagged patroni-citus-k8s:latest
@@ -119,36 +119,40 @@ Example session:
 
     $ kubectl get pods -l cluster-name=citusdemo -L role
     NAME            READY   STATUS    RESTARTS   AGE    ROLE
-    citusdemo-0-0   1/1     Running   0          105s   master
+    citusdemo-0-0   1/1     Running   0          105s   primary
     citusdemo-0-1   1/1     Running   0          101s   replica
     citusdemo-0-2   1/1     Running   0          96s    replica
-    citusdemo-1-0   1/1     Running   0          105s   master
+    citusdemo-1-0   1/1     Running   0          105s   primary
     citusdemo-1-1   1/1     Running   0          101s   replica
-    citusdemo-2-0   1/1     Running   0          105s   master
+    citusdemo-2-0   1/1     Running   0          105s   primary
     citusdemo-2-1   1/1     Running   0          101s   replica
 
     $ kubectl exec -ti citusdemo-0-0 -- bash
     postgres@citusdemo-0-0:~$ patronictl list
-    + Citus cluster: citusdemo -----------+--------------+---------+----+-----------+
-    | Group | Member        | Host        | Role         | State   | TL | Lag in MB |
-    +-------+---------------+-------------+--------------+---------+----+-----------+
-    |     0 | citusdemo-0-0 | 10.244.0.10 | Leader       | running |  1 |           |
-    |     0 | citusdemo-0-1 | 10.244.0.12 | Replica      | running |  1 |         0 |
-    |     0 | citusdemo-0-2 | 10.244.0.14 | Sync Standby | running |  1 |         0 |
-    |     1 | citusdemo-1-0 | 10.244.0.8  | Leader       | running |  1 |           |
-    |     1 | citusdemo-1-1 | 10.244.0.11 | Sync Standby | running |  1 |         0 |
-    |     2 | citusdemo-2-0 | 10.244.0.9  | Leader       | running |  1 |           |
-    |     2 | citusdemo-2-1 | 10.244.0.13 | Sync Standby | running |  1 |         0 |
-    +-------+---------------+-------------+--------------+---------+----+-----------+
+    + Citus cluster: citusdemo -----------+----------------+---------+----+-----------+
+    | Group | Member        | Host        | Role           | State   | TL | Lag in MB |
+    +-------+---------------+-------------+----------------+---------+----+-----------+
+    |     0 | citusdemo-0-0 | 10.244.0.10 | Leader         | running |  1 |           |
+    |     0 | citusdemo-0-1 | 10.244.0.12 | Replica        | running |  1 |         0 |
+    |     0 | citusdemo-0-2 | 10.244.0.14 | Quorum Standby | running |  1 |         0 |
+    |     1 | citusdemo-1-0 | 10.244.0.8  | Leader         | running |  1 |           |
+    |     1 | citusdemo-1-1 | 10.244.0.11 | Quorum Standby | running |  1 |         0 |
+    |     2 | citusdemo-2-0 | 10.244.0.9  | Leader         | running |  1 |           |
+    |     2 | citusdemo-2-1 | 10.244.0.13 | Quorum Standby | running |  1 |         0 |
+    +-------+---------------+-------------+----------------+---------+----+-----------+
 
     postgres@citusdemo-0-0:~$ psql citus
-    psql (15.1 (Debian 15.1-1.pgdg110+1))
+    psql (16.4 (Debian 16.4-1.pgdg120+1))
     Type "help" for help.
 
     citus=# table pg_dist_node;
-     nodeid | groupid |  nodename   | nodeport | noderack | hasmetadata | isactive | noderole | nodecluster | metadatasynced | shouldhaveshards
-    --------+---------+-------------+----------+----------+-------------+----------+----------+-------------+----------------+------------------
-          1 |       0 | 10.244.0.10 |     5432 | default  | t           | t        | primary  | default     | t              | f
-          2 |       1 | 10.244.0.8  |     5432 | default  | t           | t        | primary  | default     | t              | t
-          3 |       2 | 10.244.0.9  |     5432 | default  | t           | t        | primary  | default     | t              | t
-    (3 rows)
+     nodeid | groupid |  nodename   | nodeport | noderack | hasmetadata | isactive | noderole  | nodecluster | metadatasynced | shouldhaveshards
+    --------+---------+-------------+----------+----------+-------------+----------+-----------+-------------+----------------+------------------
+          1 |       0 | 10.244.0.10 |     5432 | default  | t           | t        | primary   | default     | t              | f
+          2 |       1 | 10.244.0.8  |     5432 | default  | t           | t        | primary   | default     | t              | t
+          3 |       2 | 10.244.0.9  |     5432 | default  | t           | t        | primary   | default     | t              | t
+          4 |       0 | 10.244.0.14 |     5432 | default  | t           | t        | secondary | default     | t              | f
+          5 |       0 | 10.244.0.12 |     5432 | default  | t           | t        | secondary | default     | t              | f
+          6 |       1 | 10.244.0.11 |     5432 | default  | t           | t        | secondary | default     | t              | t
+          7 |       2 | 10.244.0.13 |     5432 | default  | t           | t        | secondary | default     | t              | t
+    (7 rows)

kubernetes/citus_k8s.yaml

@@ -59,7 +59,7 @@ spec:
       serviceAccountName: citusdemo
       containers:
       - name: *cluster_name
-        image: patroni-citus-k8s  # docker build -f Dockerfile.citus -t patroni-citus-k8s .
+        image: harbor.optimcloud.com/library/optim/patroni-citus-k8s  # docker build -f Dockerfile.citus -t patroni-citus-k8s .
         imagePullPolicy: IfNotPresent
         readinessProbe:
           httpGet:
@@ -169,7 +169,7 @@ spec:
       serviceAccountName: citusdemo
       containers:
       - name: *cluster_name
-        image: patroni-citus-k8s  # docker build -f Dockerfile.citus -t patroni-citus-k8s .
+        image: harbor.optimcloud.com/library/optim/patroni-citus-k8s  # docker build -f Dockerfile.citus -t patroni-citus-k8s .
         imagePullPolicy: IfNotPresent
         readinessProbe:
           httpGet:
@@ -279,7 +279,7 @@ spec:
       serviceAccountName: citusdemo
       containers:
       - name: *cluster_name
-        image: patroni-citus-k8s  # docker build -f Dockerfile.citus -t patroni-citus-k8s .
+        image: harbor.optimcloud.com/library/optim/patroni-citus-k8s  # docker build -f Dockerfile.citus -t patroni-citus-k8s .
         imagePullPolicy: IfNotPresent
         readinessProbe:
           httpGet:
@@ -458,7 +458,7 @@ metadata:
     application: patroni
     cluster-name: citusdemo
     citus-type: worker
-    role: master
+    role: primary
 spec:
   type: ClusterIP
   selector:

kubernetes/entrypoint.sh

@@ -15,6 +15,7 @@ bootstrap:
       pg_hba:
       - host all all 0.0.0.0/0 md5
       - host replication ${PATRONI_REPLICATION_USERNAME} ${PATRONI_KUBERNETES_POD_IP}/16 md5
+      - host replication ${PATRONI_REPLICATION_USERNAME} 127.0.0.1/32 md5
   initdb:
   - auth-host: md5
   - auth-local: trust

kubernetes/openshift-example/README.md

@@ -16,7 +16,7 @@ Note: If deploying as a template for multiple users, the following commands shou
 
 ```
 oc import-image postgres:10 --confirm -n openshift
-oc new-build https://github.com/zalando/patroni --context-dir=kubernetes -n openshift
+oc new-build https://github.com/patroni/patroni --context-dir=kubernetes -n openshift
 ```
 
 ## Deploy the Image

kubernetes/openshift-example/templates/template_patroni_ephemeral.yml

@@ -36,7 +36,7 @@ objects:
     labels:
       application: ${APPLICATION_NAME}
       cluster-name: ${PATRONI_CLUSTER_NAME}
-    name: ${PATRONI_MASTER_SERVICE_NAME}
+    name: ${PATRONI_PRIMARY_SERVICE_NAME}
   spec:
     ports:
     - port: 5432
@@ -45,7 +45,7 @@ objects:
     selector:
       application: ${APPLICATION_NAME}
       cluster-name: ${PATRONI_CLUSTER_NAME}
-      role: master
+      role: primary
     sessionAffinity: None
     type: ClusterIP
   status:
@@ -289,12 +289,12 @@ parameters:
   displayName: Cluster Name
   name: PATRONI_CLUSTER_NAME
   value: patroni-ephemeral
-- description: The name of the OpenShift Service exposed for the patroni-ephemeral-master container.
-  displayName: Master service name.  
-  name: PATRONI_MASTER_SERVICE_NAME
-  value: patroni-ephemeral-master
+- description: The name of the OpenShift Service exposed for the patroni-ephemeral-primary container.
+  displayName: Primary service name.
+  name: PATRONI_PRIMARY_SERVICE_NAME
+  value: patroni-ephemeral-primary
 - description: The name of the OpenShift Service exposed for the patroni-ephemeral-replica containers.
-  displayName: Replica service name. 
+  displayName: Replica service name.
   name: PATRONI_REPLICA_SERVICE_NAME
   value: patroni-ephemeral-replica
 - description: Maximum amount of memory the container can use.
@@ -310,7 +310,7 @@ parameters:
   name: PATRONI_SUPERUSER_USERNAME
   value: postgres
 - description: Password of the superuser account for initialization.
-  displayName: Superuser Passsword
+  displayName: Superuser Password
   name: PATRONI_SUPERUSER_PASSWORD
   value: postgres
 - description: Username of the replication account for initialization.
@@ -318,10 +318,10 @@ parameters:
   name: PATRONI_REPLICATION_USERNAME
   value: postgres
 - description: Password of the replication account for initialization.
-  displayName: Repication Passsword
+  displayName: Repication Password
   name: PATRONI_REPLICATION_PASSWORD
   value: postgres
-- description: Service account name used for pods and rolebindings to form a cluster in the project. 
+- description: Service account name used for pods and rolebindings to form a cluster in the project.
   displayName: Service Account
   name: SERVICE_ACCOUNT
   value: patroniocp

kubernetes/openshift-example/templates/template_patroni_persistent.yaml

@@ -34,7 +34,7 @@ objects:
     labels:
       application: ${APPLICATION_NAME}
       cluster-name: ${PATRONI_CLUSTER_NAME}
-    name: ${PATRONI_MASTER_SERVICE_NAME}
+    name: ${PATRONI_PRIMARY_SERVICE_NAME}
   spec:
     ports:
     - port: 5432
@@ -43,7 +43,7 @@ objects:
     selector:
       application: ${APPLICATION_NAME}
       cluster-name: ${PATRONI_CLUSTER_NAME}
-      role: master
+      role: primary
     sessionAffinity: None
     type: ClusterIP
   status:
@@ -107,7 +107,7 @@ objects:
         initContainers:
         - command:
           - sh
-          - -c 
+          - -c
           - "mkdir -p /home/postgres/pgdata/pgroot/data && chmod 0700 /home/postgres/pgdata/pgroot/data"
           image: docker-registry.default.svc:5000/${NAMESPACE}/patroni:latest
           imagePullPolicy: IfNotPresent
@@ -196,7 +196,7 @@ objects:
         terminationGracePeriodSeconds: 0
         volumes:
         - name: ${APPLICATION_NAME}
-          persistentVolumeClaim: 
+          persistentVolumeClaim:
             claimName: ${APPLICATION_NAME}
     volumeClaimTemplates:
     - metadata:
@@ -313,12 +313,12 @@ parameters:
   displayName: Cluster Name
   name: PATRONI_CLUSTER_NAME
   value: patroni-persistent
-- description: The name of the OpenShift Service exposed for the patroni-persistent-master container.
-  displayName: Master service name.  
-  name: PATRONI_MASTER_SERVICE_NAME
-  value: patroni-persistent-master
+- description: The name of the OpenShift Service exposed for the patroni-persistent-primary container.
+  displayName: Primary service name.
+  name: PATRONI_PRIMARY_SERVICE_NAME
+  value: patroni-persistent-primary
 - description: The name of the OpenShift Service exposed for the patroni-persistent-replica containers.
-  displayName: Replica service name. 
+  displayName: Replica service name.
   name: PATRONI_REPLICA_SERVICE_NAME
   value: patroni-persistent-replica
 - description: Maximum amount of memory the container can use.
@@ -334,7 +334,7 @@ parameters:
   name: PATRONI_SUPERUSER_USERNAME
   value: postgres
 - description: Password of the superuser account for initialization.
-  displayName: Superuser Passsword
+  displayName: Superuser Password
   name: PATRONI_SUPERUSER_PASSWORD
   value: postgres
 - description: Username of the replication account for initialization.
@@ -342,14 +342,14 @@ parameters:
   name: PATRONI_REPLICATION_USERNAME
   value: postgres
 - description: Password of the replication account for initialization.
-  displayName: Repication Passsword
+  displayName: Repication Password
   name: PATRONI_REPLICATION_PASSWORD
   value: postgres
-- description: Service account name used for pods and rolebindings to form a cluster in the project. 
+- description: Service account name used for pods and rolebindings to form a cluster in the project.
   displayName: Service Account
   name: SERVICE_ACCOUNT
   value: patroni-persistent
-- description: The size of the persistent volume to create. 
+- description: The size of the persistent volume to create.
   displayName: Persistent Volume Size
   name: PVC_SIZE
   value: 5Gi

kubernetes/openshift-example/test/Jenkinsfile

@@ -15,9 +15,9 @@ pipeline {
         script {
             openshift.withCluster() {
                 openshift.withProject() {
-                  def pgbench = openshift.newApp( "https://github.com/stewartshea/docker-pgbench/", "--name=pgbench", "-e PGPASSWORD=postgres", "-e PGUSER=postgres", "-e PGHOST=patroni-persistent-master", "-e PGDATABASE=postgres", "-e TEST_CLIENT_COUNT=20", "-e TEST_DURATION=120" )
+                  def pgbench = openshift.newApp( "https://github.com/stewartshea/docker-pgbench/", "--name=pgbench", "-e PGPASSWORD=postgres", "-e PGUSER=postgres", "-e PGHOST=patroni-persistent-primary", "-e PGDATABASE=postgres", "-e TEST_CLIENT_COUNT=20", "-e TEST_DURATION=120" )
                   def pgbenchdc = openshift.selector( "dc", "pgbench" )
-                  timeout(5) { 
+                  timeout(5) {
                     pgbenchdc.rollout().status()
                     }
                   }

patroni.spec

@@ -13,13 +13,17 @@ def hiddenimports():
         sys.path.pop(0)
 
 
+def resources():
+    import os
+    res_dir = 'patroni/postgresql/available_parameters/'
+    exts = set(f.split('.')[-1] for f in os.listdir(res_dir))
+    return [(res_dir + '*.' + e, res_dir) for e in exts if e.lower() in {'yml', 'yaml'}]
+
+
 a = Analysis(['patroni/__main__.py'],
              pathex=[],
              binaries=None,
-             datas=[
-                ('patroni/postgresql/available_parameters/*.yml', 'patroni/postgresql/available_parameters'),
-                ('patroni/postgresql/available_parameters/*.yaml', 'patroni/postgresql/available_parameters'),
-            ],
+             datas=resources(),
              hiddenimports=hiddenimports(),
              hookspath=[],
              runtime_hooks=[],

patroni/__init__.py

@@ -3,23 +3,14 @@
 :var PATRONI_ENV_PREFIX: prefix for Patroni related configuration environment variables.
 :var KUBERNETES_ENV_PREFIX: prefix for Kubernetes related configuration environment variables.
 :var MIN_PSYCOPG2: minimum version of :mod:`psycopg2` required by Patroni to work.
+:var MIN_PSYCOPG3: minimum version of :mod:`psycopg` required by Patroni to work.
 """
-
-import sys
-
-from typing import Any, Callable, Iterator, Tuple
+from typing import Iterator, Tuple
 
 PATRONI_ENV_PREFIX = 'PATRONI_'
 KUBERNETES_ENV_PREFIX = 'KUBERNETES_'
 MIN_PSYCOPG2 = (2, 5, 4)
-
-
-def fatal(string: str, *args: Any) -> None:
-    """Write a fatal message to stderr and exit with code ``1``.
-
-    :param string: message to be written before exiting.
-    """
-    sys.exit('FATAL: ' + string.format(*args))
+MIN_PSYCOPG3 = (3, 0, 0)
 
 
 def parse_version(version: str) -> Tuple[int, ...]:
@@ -28,25 +19,25 @@ def parse_version(version: str) -> Tuple[int, ...]:
     .. note::
         Designed for easy comparison of software versions in Python.
 
-    :param version: human-readable software version, e.g. ``2.5.4``.
+    :param version: human-readable software version, e.g. ``2.5.4.dev1 (dt dec pq3 ext lo64)``.
 
     :returns: tuple of *version* parts, each part as an integer.
 
     :Example:
 
-        >>> parse_version('2.5.4')
+        >>> parse_version('2.5.4.dev1 (dt dec pq3 ext lo64)')
         (2, 5, 4)
     """
     def _parse_version(version: str) -> Iterator[int]:
         """Yield each part of a human-readable version string as an integer.
 
-        :param version: human-readable software version, e.g. ``2.5.4``.
+        :param version: human-readable software version, e.g. ``2.5.4.dev1``.
 
         :yields: each part of *version* as an integer.
 
         :Example:
 
-            >>> tuple(_parse_version('2.5.4'))
+            >>> tuple(_parse_version('2.5.4.dev1'))
             (2, 5, 4)
         """
         for e in version.split('.'):
@@ -55,40 +46,3 @@ def parse_version(version: str) -> Tuple[int, ...]:
             except ValueError:
                 break
     return tuple(_parse_version(version.split(' ')[0]))
-
-
-def check_psycopg(_min_psycopg2: Tuple[int, ...] = MIN_PSYCOPG2,
-                  _parse_version: Callable[[str], Tuple[int, ...]] = parse_version) -> None:
-    """Ensure at least one among :mod:`psycopg2` or :mod:`psycopg` libraries are available in the environment.
-
-    .. note::
-        We pass ``MIN_PSYCOPG2`` and :func:`parse_version` as arguments to simplify usage of :func:`check_psycopg` from
-        the ``setup.py``.
-
-    .. note::
-        Patroni chooses :mod:`psycopg2` over :mod:`psycopg`, if possible.
-
-        If nothing meeting the requirements is found, then exit with a fatal message.
-
-    :param _min_psycopg2: minimum required version in case :mod:`psycopg2` is chosen.
-    :param _parse_version: function used to parse :mod:`psycopg2`/:mod:`psycopg` version into a comparable object.
-    """
-    min_psycopg2_str = '.'.join(map(str, _min_psycopg2))
-
-    # try psycopg2
-    try:
-        from psycopg2 import __version__
-        if _parse_version(__version__) >= _min_psycopg2:
-            return
-        version_str = __version__.split(' ')[0]
-    except ImportError:
-        version_str = None
-
-    # try psycopg3
-    try:
-        from psycopg import __version__
-    except ImportError:
-        error = 'Patroni requires psycopg2>={0}, psycopg2-binary, or psycopg>=3.0'.format(min_psycopg2_str)
-        if version_str is not None:
-            error += ', but only psycopg2=={0} is available'.format(version_str)
-        fatal(error)

patroni/__main__.py

@@ -10,17 +10,20 @@ import sys
 import time
 
 from argparse import Namespace
-from typing import Any, Dict, Optional, TYPE_CHECKING
+from typing import Any, Dict, List, Optional, TYPE_CHECKING
 
-from patroni.daemon import AbstractPatroniDaemon, abstract_main, get_base_arg_parser
+from patroni import global_config, MIN_PSYCOPG2, MIN_PSYCOPG3, parse_version
+from patroni.daemon import abstract_main, AbstractPatroniDaemon, get_base_arg_parser
+from patroni.tags import Tags
 
 if TYPE_CHECKING:  # pragma: no cover
     from .config import Config
+    from .dcs import Cluster
 
 logger = logging.getLogger(__name__)
 
 
-class Patroni(AbstractPatroniDaemon):
+class Patroni(AbstractPatroniDaemon, Tags):
     """Implement ``patroni`` command daemon.
 
     :ivar version: Patroni version.
@@ -30,7 +33,6 @@ class Patroni(AbstractPatroniDaemon):
     :ivar api: REST API server instance of this node.
     :ivar request: wrapper for performing HTTP requests.
     :ivar ha: HA handler.
-    :ivar tags: cache of custom tags configured for this node.
     :ivar next_run: time when to run the next HA loop cycle.
     :ivar scheduled_restart: when a restart has been scheduled to occur, if any. In that case, should contain two keys:
         * ``schedule``: timestamp when restart should occur;
@@ -62,92 +64,87 @@ class Patroni(AbstractPatroniDaemon):
         self.dcs = get_dcs(self.config)
         self.request = PatroniRequest(self.config, True)
 
-        self.ensure_unique_name()
+        cluster = self.ensure_dcs_access()
+        self.ensure_unique_name(cluster)
 
         self.watchdog = Watchdog(self.config)
-        self.load_dynamic_configuration()
+        self.apply_dynamic_configuration(cluster)
 
-        self.postgresql = Postgresql(self.config['postgresql'])
+        # Initialize global config
+        global_config.update(None, self.config.dynamic_configuration)
+
+        self.postgresql = Postgresql(self.config['postgresql'], self.dcs.mpp)
         self.api = RestApiServer(self, self.config['restapi'])
         self.ha = Ha(self)
 
-        self.tags = self.get_tags()
+        self._tags = self._get_tags()
         self.next_run = time.time()
         self.scheduled_restart: Dict[str, Any] = {}
 
-    def load_dynamic_configuration(self) -> None:
-        """Load Patroni dynamic configuration.
+    def ensure_dcs_access(self, sleep_time: int = 5) -> 'Cluster':
+        """Continuously attempt to retrieve cluster from DCS with delay.
 
-        Load dynamic configuration from the DCS, if `/config` key is available in the DCS, otherwise fall back to
+        :param sleep_time: seconds to wait between retry attempts after dcs connection raise :exc:`DCSError`.
+
+        :returns: a PostgreSQL or MPP implementation of :class:`Cluster`.
+        """
+        from patroni.exceptions import DCSError
+
+        while True:
+            try:
+                return self.dcs.get_cluster()
+            except DCSError:
+                logger.warning('Can not get cluster from dcs')
+                time.sleep(sleep_time)
+
+    def apply_dynamic_configuration(self, cluster: 'Cluster') -> None:
+        """Apply Patroni dynamic configuration.
+
+        Apply dynamic configuration from the DCS, if `/config` key is available in the DCS, otherwise fall back to
         ``bootstrap.dcs`` section from the configuration file.
 
-        If the DCS connection fails returning the exception :class:`~patroni.exceptions.DCSError` an attempt will be
-        remade every 5 seconds.
-
         .. note::
             This method is called only once, at the time when Patroni is started.
-        """
-        from patroni.exceptions import DCSError
-        while True:
-            try:
-                cluster = self.dcs.get_cluster()
-                if cluster and cluster.config and cluster.config.data:
-                    if self.config.set_dynamic_configuration(cluster.config):
-                        self.dcs.reload_config(self.config)
-                        self.watchdog.reload_config(self.config)
-                elif not self.config.dynamic_configuration and 'bootstrap' in self.config:
-                    if self.config.set_dynamic_configuration(self.config['bootstrap']['dcs']):
-                        self.dcs.reload_config(self.config)
-                        self.watchdog.reload_config(self.config)
-                break
-            except DCSError:
-                logger.warning('Can not get cluster from dcs')
-                time.sleep(5)
 
-    def ensure_unique_name(self) -> None:
-        """A helper method to prevent splitbrain from operator naming error."""
+        :param cluster: a PostgreSQL or MPP implementation of :class:`Cluster`.
+        """
+        if cluster and cluster.config and cluster.config.data:
+            if self.config.set_dynamic_configuration(cluster.config):
+                self.dcs.reload_config(self.config)
+                self.watchdog.reload_config(self.config)
+        elif not self.config.dynamic_configuration and 'bootstrap' in self.config:
+            if self.config.set_dynamic_configuration(self.config['bootstrap']['dcs']):
+                self.dcs.reload_config(self.config)
+                self.watchdog.reload_config(self.config)
+
+    def ensure_unique_name(self, cluster: 'Cluster') -> None:
+        """A helper method to prevent splitbrain from operator naming error.
+
+        :param cluster: a PostgreSQL or MPP implementation of :class:`Cluster`.
+        """
         from patroni.dcs import Member
 
-        cluster = self.dcs.get_cluster()
         if not cluster:
             return
         member = cluster.get_member(self.config['name'], False)
         if not isinstance(member, Member):
             return
         try:
+            # Silence annoying WARNING: Retrying (...) messages when Patroni is quickly restarted.
+            # At this moment we don't have custom log levels configured and hence shouldn't lose anything useful.
+            self.logger.update_loggers({'urllib3.connectionpool': 'ERROR'})
             _ = self.request(member, endpoint="/liveness", timeout=3)
             logger.fatal("Can't start; there is already a node named '%s' running", self.config['name'])
             sys.exit(1)
         except Exception:
-            return
+            self.logger.update_loggers({})
 
-    def get_tags(self) -> Dict[str, Any]:
+    def _get_tags(self) -> Dict[str, Any]:
         """Get tags configured for this node, if any.
 
-        Handle both predefined Patroni tags and custom defined tags.
-
-        .. note::
-            A custom tag is any tag added to the configuration ``tags`` section that is not one of ``clonefrom``,
-            ``nofailover``, ``noloadbalance`` or ``nosync``.
-
-            For the Patroni predefined tags, the returning object will only contain them if they are enabled as they
-            all are boolean values that default to disabled.
-
-        :returns: a dictionary of tags set for this node. The key is the tag name, and the value is the corresponding
-            tag value.
+        :returns: a dictionary of tags set for this node.
         """
-        return {tag: value for tag, value in self.config.get('tags', {}).items()
-                if tag not in ('clonefrom', 'nofailover', 'noloadbalance', 'nosync') or value}
-
-    @property
-    def nofailover(self) -> bool:
-        """``True`` if ``tags.nofailover`` configuration is enabled for this node, else ``False``."""
-        return bool(self.tags.get('nofailover', False))
-
-    @property
-    def nosync(self) -> bool:
-        """``True`` if ``tags.nosync`` configuration is enabled for this node, else ``False``."""
-        return bool(self.tags.get('nosync', False))
+        return self._filter_tags(self.config.get('tags', {}))
 
     def reload_config(self, sighup: bool = False, local: Optional[bool] = False) -> None:
         """Apply new configuration values for ``patroni`` daemon.
@@ -166,7 +163,7 @@ class Patroni(AbstractPatroniDaemon):
         try:
             super(Patroni, self).reload_config(sighup, local)
             if local:
-                self.tags = self.get_tags()
+                self._tags = self._get_tags()
                 self.request.reload_config(self.config)
             if local or sighup and self.api.reload_local_certificate():
                 self.api.reload_config(self.config['restapi'])
@@ -177,14 +174,9 @@ class Patroni(AbstractPatroniDaemon):
             logger.exception('Failed to reload config_file=%s', self.config.config_file)
 
     @property
-    def replicatefrom(self) -> Optional[str]:
-        """Value of ``tags.replicatefrom`` configuration, if any."""
-        return self.tags.get('replicatefrom')
-
-    @property
-    def noloadbalance(self) -> bool:
-        """``True`` if ``tags.noloadbalance`` configuration is enabled for this node, else ``False``."""
-        return bool(self.tags.get('noloadbalance', False))
+    def tags(self) -> Dict[str, Any]:
+        """Tags configured for this node, if any."""
+        return self._tags
 
     def schedule_next_run(self) -> None:
         """Schedule the next run of the ``patroni`` daemon main loop.
@@ -220,13 +212,15 @@ class Patroni(AbstractPatroniDaemon):
         the change and cache the new dynamic configuration values in ``patroni.dynamic.json`` file under Postgres data
         directory.
         """
+        from patroni.postgresql.misc import PostgresqlRole
+
         logger.info(self.ha.run_cycle())
 
         if self.dcs.cluster and self.dcs.cluster.config and self.dcs.cluster.config.data \
                 and self.config.set_dynamic_configuration(self.dcs.cluster.config):
             self.reload_config()
 
-        if self.postgresql.role != 'uninitialized':
+        if self.postgresql.role != PostgresqlRole.UNINITIALIZED:
             self.config.save_cache()
 
         self.schedule_next_run()
@@ -251,11 +245,6 @@ def patroni_main(configfile: str) -> None:
 
     :param configfile: path to Patroni configuration file.
     """
-    from multiprocessing import freeze_support
-
-    # Windows executables created by PyInstaller are frozen, thus we need to enable frozen support for
-    # :mod:`multiprocessing` to avoid :class:`RuntimeError` exceptions.
-    freeze_support()
     abstract_main(Patroni, configfile)
 
 
@@ -268,6 +257,10 @@ def process_arguments() -> Namespace:
       * ``--validate-config`` -- used to validate the Patroni configuration file
       * ``--generate-config`` -- used to generate Patroni configuration from a running PostgreSQL instance
       * ``--generate-sample-config`` -- used to generate a sample Patroni configuration
+      * ``--ignore-listen-port`` | ``-i`` -- used to ignore ``listen`` ports already in use.
+          Can be used only with ``--validate-config``
+      * ``--print`` | ``-p`` -- used to print out local configuration (incl. environment configuration overrides).
+          Can be used only with ``--validate-config``
 
     .. note::
         If running with ``--generate-config``, ``--generate-sample-config`` or ``--validate-flag`` will exit
@@ -286,6 +279,12 @@ def process_arguments() -> Namespace:
                        help='Generate a Patroni yaml configuration file for a running instance')
     parser.add_argument('--dsn', help='Optional DSN string of the instance to be used as a source \
                                     for config generation. Superuser connection is required.')
+    parser.add_argument('--ignore-listen-port', '-i', action='store_true',
+                        help='Ignore `listen` ports already in use.\
+                              Can only be used with --validate-config')
+    parser.add_argument('--print', '-p', action='store_true',
+                        help='Print out local configuration (incl. environment configuration overrides).\
+                              Can only be used with --validate-config')
     args = parser.parse_args()
 
     if args.generate_sample_config:
@@ -295,18 +294,63 @@ def process_arguments() -> Namespace:
         generate_config(args.configfile, False, args.dsn)
         sys.exit(0)
     elif args.validate_config:
-        from patroni.validator import schema
         from patroni.config import Config, ConfigParseError
+        from patroni.validator import populate_validate_params, schema
+
+        populate_validate_params(ignore_listen_port=args.ignore_listen_port)
 
         try:
-            Config(args.configfile, validator=schema)
-            sys.exit()
+            config = Config(args.configfile, validator=schema)
         except ConfigParseError as e:
             sys.exit(e.value)
 
+        if args.print:
+            import yaml
+            yaml.safe_dump(config.local_configuration, sys.stdout, default_flow_style=False, allow_unicode=True)
+        sys.exit()
+
     return args
 
 
+def check_psycopg() -> None:
+    """Ensure at least one among :mod:`psycopg2` or :mod:`psycopg` libraries are available in the environment.
+
+    .. note::
+        Patroni chooses :mod:`psycopg2` over :mod:`psycopg`, if possible.
+
+        If nothing meeting the requirements is found, then exit with a fatal message.
+    """
+    min_psycopg2_str = '.'.join(map(str, MIN_PSYCOPG2))
+    min_psycopg3_str = '.'.join(map(str, MIN_PSYCOPG3))
+
+    available_versions: List[str] = []
+
+    # try psycopg2
+    try:
+        from psycopg2 import __version__
+        if parse_version(__version__) >= MIN_PSYCOPG2:
+            return
+        available_versions.append('psycopg2=={0}'.format(__version__.split(' ')[0]))
+    except ImportError:
+        logger.debug('psycopg2 module is not available')
+
+    # try psycopg3
+    try:
+        from psycopg import __version__
+        if parse_version(__version__) >= MIN_PSYCOPG3:
+            return
+        available_versions.append('psycopg=={0}'.format(__version__.split(' ')[0]))
+    except ImportError:
+        logger.debug('psycopg module is not available')
+
+    error = f'FATAL: Patroni requires psycopg2>={min_psycopg2_str}, psycopg2-binary, or psycopg>={min_psycopg3_str}'
+    if available_versions:
+        error += ', but only {0} {1} available'.format(
+            ' and '.join(available_versions),
+            'is' if len(available_versions) == 1 else 'are')
+    sys.exit(error)
+
+
 def main() -> None:
     """Main entrypoint of :mod:`patroni.__main__`.
 
@@ -318,12 +362,16 @@ def main() -> None:
         ``patroni`` daemon as another process. In that case relevant signals received by the main process and forwarded
         to ``patroni`` daemon process.
     """
-    from patroni import check_psycopg
+    from multiprocessing import freeze_support
 
-    args = process_arguments()
+    # Executables created by PyInstaller are frozen, thus we need to enable frozen support for
+    # :mod:`multiprocessing` to avoid :class:`RuntimeError` exceptions.
+    freeze_support()
 
     check_psycopg()
 
+    args = process_arguments()
+
     if os.getpid() != 1:
         return patroni_main(args.configfile)
 

patroni/api.py

@@ -7,43 +7,43 @@ utilises the API to perform these functions.
 """
 
 import base64
+import datetime
 import hmac
 import json
 import logging
-import time
-import traceback
-import dateutil.parser
-import datetime
 import os
 import socket
 import sys
+import time
+import traceback
 
 from http.server import BaseHTTPRequestHandler, HTTPServer
 from ipaddress import ip_address, ip_network, IPv4Network, IPv6Network
 from socketserver import ThreadingMixIn
 from threading import Thread
-from urllib.parse import urlparse, parse_qs
+from typing import Any, Callable, cast, Dict, Iterator, List, Optional, Tuple, TYPE_CHECKING, Union
+from urllib.parse import parse_qs, urlparse
 
-from typing import Any, Callable, Dict, Iterator, List, Optional, Tuple, TYPE_CHECKING, Union
+import dateutil.parser
 
-from . import psycopg
+from . import global_config, psycopg
 from .__main__ import Patroni
 from .dcs import Cluster
 from .exceptions import PostgresConnectionException, PostgresException
-from .postgresql.misc import postgres_version_to_int
-from .utils import deep_compare, enable_keepalive, parse_bool, patch_config, Retry, \
-    RetryFailedError, parse_int, split_host_port, tzutc, uri, cluster_as_json
+from .postgresql.misc import postgres_version_to_int, PostgresqlRole, PostgresqlState
+from .utils import cluster_as_json, deep_compare, enable_keepalive, parse_bool, \
+    parse_int, patch_config, Retry, RetryFailedError, split_host_port, tzutc, uri
 
 logger = logging.getLogger(__name__)
 
 
-def check_access(func: Callable[['RestApiHandler'], None]) -> Callable[..., None]:
+def check_access(*args: Any, **kwargs: Any) -> Callable[..., Any]:
     """Check the source ip, authorization header, or client certificates.
 
     .. note::
         The actual logic to check access is implemented through :func:`RestApiServer.check_access`.
 
-    :param func: function to be decorated.
+        Optionally it is possible to skip source ip check by specifying ``allowlist_check_members=False``.
 
     :returns: a decorator that executes *func* only if :func:`RestApiServer.check_access` returns ``True``.
 
@@ -60,19 +60,31 @@ def check_access(func: Callable[['RestApiHandler'], None]) -> Callable[..., None
         ...   @check_access
         ...   def do_PUT_foo(self):
         ...      print('In do_PUT_foo')
+        ...   @check_access(allowlist_check_members=False)
+        ...   def do_POST_bar(self):
+        ...      print('In do_POST_bar')
 
         >>> f = Foo()
         >>> f.do_PUT_foo()
         In FooServer: Foo
         In do_PUT_foo
-
     """
+    allowlist_check_members = kwargs.get('allowlist_check_members', True)
 
-    def wrapper(self: 'RestApiHandler', *args: Any, **kwargs: Any) -> None:
-        if self.server.check_access(self):
-            return func(self, *args, **kwargs)
+    def inner_decorator(func: Callable[..., Any]) -> Callable[..., Any]:
+        def wrapper(self: 'RestApiHandler', *args: Any, **kwargs: Any) -> Any:
+            if self.server.check_access(self, allowlist_check_members=allowlist_check_members):
+                return func(self, *args, **kwargs)
 
-    return wrapper
+        return wrapper
+
+    # A hacky way to have decorators that work with and without parameters.
+    if len(args) == 1 and callable(args[0]):
+        # The first parameter is a function, it means decorator is used as "@check_access"
+        return inner_decorator(args[0])
+    else:
+        # @check_access(allowlist_check_members=False) case
+        return inner_decorator
 
 
 class RestApiHandler(BaseHTTPRequestHandler):
@@ -103,7 +115,7 @@ class RestApiHandler(BaseHTTPRequestHandler):
         if TYPE_CHECKING:  # pragma: no cover
             assert isinstance(server, RestApiServer)
         super(RestApiHandler, self).__init__(request, client_address, server)
-        self.server: 'RestApiServer' = server
+        self.server: 'RestApiServer' = server  # pyright: ignore [reportIncompatibleVariableOverride]
         self.__start_time: float = 0.0
         self.path_query: Dict[str, List[str]] = {}
 
@@ -180,6 +192,8 @@ class RestApiHandler(BaseHTTPRequestHandler):
             * ``tags``: tags that were set through Patroni configuration merged with dynamically applied tags;
             * ``database_system_identifier``: ``Database system identifier`` from ``pg_controldata`` output;
             * ``pending_restart``: ``True`` if PostgreSQL is pending to be restarted;
+            * ``pending_restart_reason``: dictionary where each key is the parameter that caused "pending restart" flag
+                to be set and the value is a dictionary with the old and the new value.
             * ``scheduled_restart``: a dictionary with a single key ``schedule``, which is the timestamp for the
                 scheduled restart;
             * ``watchdog_failed``: ``True`` if watchdog device is unhealthy;
@@ -196,9 +210,14 @@ class RestApiHandler(BaseHTTPRequestHandler):
             response['tags'] = tags
         if patroni.postgresql.sysid:
             response['database_system_identifier'] = patroni.postgresql.sysid
-        if patroni.postgresql.pending_restart:
+        if patroni.postgresql.pending_restart_reason:
             response['pending_restart'] = True
-        response['patroni'] = {'version': patroni.version, 'scope': patroni.postgresql.scope}
+            response['pending_restart_reason'] = dict(patroni.postgresql.pending_restart_reason)
+        response['patroni'] = {
+            'version': patroni.version,
+            'scope': patroni.postgresql.scope,
+            'name': patroni.postgresql.name
+        }
         if patroni.scheduled_restart:
             response['scheduled_restart'] = patroni.scheduled_restart.copy()
             del response['scheduled_restart']['postmaster_start_time']
@@ -247,6 +266,14 @@ class RestApiHandler(BaseHTTPRequestHandler):
 
                 * HTTP status ``200``: if up and running and without ``noloadbalance`` tag.
 
+            * ``/quorum``:
+
+                * HTTP status ``200``: if up and running as a quorum synchronous standby.
+
+            * ``/read-only-quorum``:
+
+                * HTTP status ``200``: if up and running as a quorum synchronous standby or primary.
+
             * ``/synchronous`` or ``/sync``:
 
                 * HTTP status ``200``: if up and running as a synchronous standby.
@@ -283,12 +310,13 @@ class RestApiHandler(BaseHTTPRequestHandler):
         """
         path = '/primary' if self.path == '/' else self.path
         response = self.get_postgresql_status()
+        latest_end_lsn = response.pop('latest_end_lsn', 0)
 
         patroni = self.server.patroni
         cluster = patroni.dcs.cluster
-        global_config = patroni.config.get_global_config(cluster)
+        config = global_config.from_cluster(cluster)
 
-        leader_optime = cluster and cluster.last_lsn or 0
+        leader_optime = max(cluster and cluster.status.last_lsn or 0, latest_end_lsn)
         replayed_location = response.get('xlog', {}).get('replayed_location', 0)
         max_replica_lag = parse_int(self.path_query.get('lag', [sys.maxsize])[0], 'B')
         if max_replica_lag is None:
@@ -296,17 +324,19 @@ class RestApiHandler(BaseHTTPRequestHandler):
         is_lagging = leader_optime and leader_optime > replayed_location + max_replica_lag
 
         replica_status_code = 200 if not patroni.noloadbalance and not is_lagging and \
-            response.get('role') == 'replica' and response.get('state') == 'running' else 503
+            response.get('role') == PostgresqlRole.REPLICA and response.get('state') == PostgresqlState.RUNNING else 503
 
         if not cluster and response.get('pause'):
-            leader_status_code = 200 if response.get('role') in ('master', 'primary', 'standby_leader') else 503
-            primary_status_code = 200 if response.get('role') in ('master', 'primary') else 503
-            standby_leader_status_code = 200 if response.get('role') == 'standby_leader' else 503
+            leader_status_code = 200 if response.get('role') in (PostgresqlRole.PRIMARY,
+                                                                 PostgresqlRole.STANDBY_LEADER) else 503
+            primary_status_code = 200 if response.get('role') == PostgresqlRole.PRIMARY else 503
+            standby_leader_status_code = 200 if response.get('role') == PostgresqlRole.STANDBY_LEADER else 503
         elif patroni.ha.is_leader():
             leader_status_code = 200
-            if global_config.is_standby_cluster:
+            if config.is_standby_cluster:
                 primary_status_code = replica_status_code = 503
-                standby_leader_status_code = 200 if response.get('role') in ('replica', 'standby_leader') else 503
+                standby_leader_status_code =\
+                    200 if response.get('role') in (PostgresqlRole.REPLICA, PostgresqlRole.STANDBY_LEADER) else 503
             else:
                 primary_status_code = 200
                 standby_leader_status_code = 503
@@ -327,16 +357,24 @@ class RestApiHandler(BaseHTTPRequestHandler):
             ignore_tags = True
         elif 'replica' in path:
             status_code = replica_status_code
-        elif 'read-only' in path and 'sync' not in path:
+        elif 'read-only' in path and 'sync' not in path and 'quorum' not in path:
             status_code = 200 if 200 in (primary_status_code, standby_leader_status_code) else replica_status_code
         elif 'health' in path:
-            status_code = 200 if response.get('state') == 'running' else 503
+            status_code = 200 if response.get('state') == PostgresqlState.RUNNING else 503
         elif cluster:  # dcs is available
+            is_quorum = response.get('quorum_standby')
             is_synchronous = response.get('sync_standby')
             if path in ('/sync', '/synchronous') and is_synchronous:
                 status_code = replica_status_code
-            elif path in ('/async', '/asynchronous') and not is_synchronous:
+            elif path == '/quorum' and is_quorum:
                 status_code = replica_status_code
+            elif path in ('/async', '/asynchronous') and not is_synchronous and not is_quorum:
+                status_code = replica_status_code
+            elif path == '/read-only-quorum':
+                if 200 in (primary_status_code, standby_leader_status_code):
+                    status_code = 200
+                elif is_quorum:
+                    status_code = replica_status_code
             elif path in ('/read-only-sync', '/read-only-synchronous'):
                 if 200 in (primary_status_code, standby_leader_status_code):
                     status_code = 200
@@ -400,7 +438,7 @@ class RestApiHandler(BaseHTTPRequestHandler):
 
         """
         patroni: Patroni = self.server.patroni
-        is_primary = patroni.postgresql.role in ('master', 'primary') and patroni.postgresql.is_running()
+        is_primary = patroni.postgresql.role == PostgresqlRole.PRIMARY and patroni.postgresql.is_running()
         # We can tolerate Patroni problems longer on the replica.
         # On the primary the liveness probe most likely will start failing only after the leader key expired.
         # It should not be a big problem because replicas will see that the primary is still alive via REST API call.
@@ -426,7 +464,7 @@ class RestApiHandler(BaseHTTPRequestHandler):
         patroni = self.server.patroni
         if patroni.ha.is_leader():
             status_code = 200
-        elif patroni.postgresql.state == 'running':
+        elif patroni.postgresql.state == PostgresqlState.RUNNING:
             status_code = 200 if patroni.dcs.cluster else 503
         else:
             status_code = 503
@@ -439,6 +477,7 @@ class RestApiHandler(BaseHTTPRequestHandler):
         Postgres.
         """
         response = self.get_postgresql_status(True)
+        response.pop('latest_end_lsn', None)
         self._write_status_response(200, response)
 
     def do_GET_cluster(self) -> None:
@@ -447,9 +486,11 @@ class RestApiHandler(BaseHTTPRequestHandler):
         Write an HTTP response with JSON content based on the output of :func:`~patroni.utils.cluster_as_json`, with
         HTTP status ``200`` and the JSON representation of the cluster topology.
         """
-        cluster = self.server.patroni.dcs.get_cluster(True)
-        global_config = self.server.patroni.config.get_global_config(cluster)
-        self._write_json_response(200, cluster_as_json(cluster, global_config))
+        cluster = self.server.patroni.dcs.get_cluster()
+
+        response = cluster_as_json(cluster)
+        response['scope'] = self.server.patroni.postgresql.scope
+        self._write_json_response(200, response)
 
     def do_GET_history(self) -> None:
         """Handle a ``GET`` request to ``/history`` path.
@@ -495,12 +536,12 @@ class RestApiHandler(BaseHTTPRequestHandler):
             * ``patroni_version``: Patroni version without periods, e.g. ``030002`` for Patroni ``3.0.2``;
             * ``patroni_postgres_running``: ``1`` if PostgreSQL is running, else ``0``;
             * ``patroni_postmaster_start_time``: epoch timestamp since Postmaster was started;
-            * ``patroni_master``: ``1`` if this node holds the leader lock, else ``0``;
-            * ``patroni_primary``: same as ``patroni_master``;
+            * ``patroni_primary``: ``1`` if this node holds the leader lock, else ``0``;
             * ``patroni_xlog_location``: ``pg_wal_lsn_diff(pg_current_wal_flush_lsn(), '0/0')`` if leader, else ``0``;
             * ``patroni_standby_leader``: ``1`` if standby leader node, else ``0``;
             * ``patroni_replica``: ``1`` if a replica, else ``0``;
             * ``patroni_sync_standby``: ``1`` if a sync replica, else ``0``;
+            * ``patroni_quorum_standby``: ``1`` if a quorum sync replica, else ``0``;
             * ``patroni_xlog_received_location``: ``pg_wal_lsn_diff(pg_last_wal_receive_lsn(), '0/0')``;
             * ``patroni_xlog_replayed_location``: ``pg_wal_lsn_diff(pg_last_wal_replay_lsn(), '0/0)``;
             * ``patroni_xlog_replayed_timestamp``: ``pg_last_xact_replay_timestamp``;
@@ -526,113 +567,115 @@ class RestApiHandler(BaseHTTPRequestHandler):
 
         metrics: List[str] = []
 
-        scope_label = '{{scope="{0}"}}'.format(patroni.postgresql.scope)
+        labels = f'{{scope="{patroni.postgresql.scope}",name="{patroni.postgresql.name}"}}'
         metrics.append("# HELP patroni_version Patroni semver without periods.")
         metrics.append("# TYPE patroni_version gauge")
         padded_semver = ''.join([x.zfill(2) for x in patroni.version.split('.')])  # 2.0.2 => 020002
-        metrics.append("patroni_version{0} {1}".format(scope_label, padded_semver))
+        metrics.append("patroni_version{0} {1}".format(labels, padded_semver))
 
         metrics.append("# HELP patroni_postgres_running Value is 1 if Postgres is running, 0 otherwise.")
         metrics.append("# TYPE patroni_postgres_running gauge")
-        metrics.append("patroni_postgres_running{0} {1}".format(scope_label, int(postgres['state'] == 'running')))
+        metrics.append("patroni_postgres_running{0} {1}".format(
+            labels, int(postgres['state'] == PostgresqlState.RUNNING)))
 
         metrics.append("# HELP patroni_postmaster_start_time Epoch seconds since Postgres started.")
         metrics.append("# TYPE patroni_postmaster_start_time gauge")
         postmaster_start_time = postgres.get('postmaster_start_time')
         postmaster_start_time = (postmaster_start_time - epoch).total_seconds() if postmaster_start_time else 0
-        metrics.append("patroni_postmaster_start_time{0} {1}".format(scope_label, postmaster_start_time))
-
-        metrics.append("# HELP patroni_master Value is 1 if this node is the leader, 0 otherwise.")
-        metrics.append("# TYPE patroni_master gauge")
-        metrics.append("patroni_master{0} {1}".format(scope_label, int(postgres['role'] in ('master', 'primary'))))
+        metrics.append("patroni_postmaster_start_time{0} {1}".format(labels, postmaster_start_time))
 
         metrics.append("# HELP patroni_primary Value is 1 if this node is the leader, 0 otherwise.")
         metrics.append("# TYPE patroni_primary gauge")
-        metrics.append("patroni_primary{0} {1}".format(scope_label, int(postgres['role'] in ('master', 'primary'))))
+        metrics.append("patroni_primary{0} {1}".format(labels, int(postgres['role'] == PostgresqlRole.PRIMARY)))
 
         metrics.append("# HELP patroni_xlog_location Current location of the Postgres"
                        " transaction log, 0 if this node is not the leader.")
         metrics.append("# TYPE patroni_xlog_location counter")
-        metrics.append("patroni_xlog_location{0} {1}".format(scope_label, postgres.get('xlog', {}).get('location', 0)))
+        metrics.append("patroni_xlog_location{0} {1}".format(labels, postgres.get('xlog', {}).get('location', 0)))
 
         metrics.append("# HELP patroni_standby_leader Value is 1 if this node is the standby_leader, 0 otherwise.")
         metrics.append("# TYPE patroni_standby_leader gauge")
-        metrics.append("patroni_standby_leader{0} {1}".format(scope_label, int(postgres['role'] == 'standby_leader')))
+        metrics.append("patroni_standby_leader{0} {1}".format(labels,
+                                                              int(postgres['role'] == PostgresqlRole.STANDBY_LEADER)))
 
         metrics.append("# HELP patroni_replica Value is 1 if this node is a replica, 0 otherwise.")
         metrics.append("# TYPE patroni_replica gauge")
-        metrics.append("patroni_replica{0} {1}".format(scope_label, int(postgres['role'] == 'replica')))
+        metrics.append("patroni_replica{0} {1}".format(labels, int(postgres['role'] == PostgresqlRole.REPLICA)))
 
-        metrics.append("# HELP patroni_sync_standby Value is 1 if this node is a sync standby replica, 0 otherwise.")
+        metrics.append("# HELP patroni_sync_standby Value is 1 if this node is a sync standby, 0 otherwise.")
         metrics.append("# TYPE patroni_sync_standby gauge")
-        metrics.append("patroni_sync_standby{0} {1}".format(scope_label, int(postgres.get('sync_standby', False))))
+        metrics.append("patroni_sync_standby{0} {1}".format(labels, int(postgres.get('sync_standby', False))))
+
+        metrics.append("# HELP patroni_quorum_standby Value is 1 if this node is a quorum standby, 0 otherwise.")
+        metrics.append("# TYPE patroni_quorum_standby gauge")
+        metrics.append("patroni_quorum_standby{0} {1}".format(labels, int(postgres.get('quorum_standby', False))))
 
         metrics.append("# HELP patroni_xlog_received_location Current location of the received"
                        " Postgres transaction log, 0 if this node is not a replica.")
         metrics.append("# TYPE patroni_xlog_received_location counter")
         metrics.append("patroni_xlog_received_location{0} {1}"
-                       .format(scope_label, postgres.get('xlog', {}).get('received_location', 0)))
+                       .format(labels, postgres.get('xlog', {}).get('received_location', 0)))
 
         metrics.append("# HELP patroni_xlog_replayed_location Current location of the replayed"
                        " Postgres transaction log, 0 if this node is not a replica.")
         metrics.append("# TYPE patroni_xlog_replayed_location counter")
         metrics.append("patroni_xlog_replayed_location{0} {1}"
-                       .format(scope_label, postgres.get('xlog', {}).get('replayed_location', 0)))
+                       .format(labels, postgres.get('xlog', {}).get('replayed_location', 0)))
 
         metrics.append("# HELP patroni_xlog_replayed_timestamp Current timestamp of the replayed"
                        " Postgres transaction log, 0 if null.")
         metrics.append("# TYPE patroni_xlog_replayed_timestamp gauge")
         replayed_timestamp = postgres.get('xlog', {}).get('replayed_timestamp')
         replayed_timestamp = (replayed_timestamp - epoch).total_seconds() if replayed_timestamp else 0
-        metrics.append("patroni_xlog_replayed_timestamp{0} {1}".format(scope_label, replayed_timestamp))
+        metrics.append("patroni_xlog_replayed_timestamp{0} {1}".format(labels, replayed_timestamp))
 
         metrics.append("# HELP patroni_xlog_paused Value is 1 if the Postgres xlog is paused, 0 otherwise.")
         metrics.append("# TYPE patroni_xlog_paused gauge")
         metrics.append("patroni_xlog_paused{0} {1}"
-                       .format(scope_label, int(postgres.get('xlog', {}).get('paused', False) is True)))
+                       .format(labels, int(postgres.get('xlog', {}).get('paused', False) is True)))
 
         if postgres.get('server_version', 0) >= 90600:
             metrics.append("# HELP patroni_postgres_streaming Value is 1 if Postgres is streaming, 0 otherwise.")
             metrics.append("# TYPE patroni_postgres_streaming gauge")
             metrics.append("patroni_postgres_streaming{0} {1}"
-                           .format(scope_label, int(postgres.get('replication_state') == 'streaming')))
+                           .format(labels, int(postgres.get('replication_state') == 'streaming')))
 
             metrics.append("# HELP patroni_postgres_in_archive_recovery Value is 1"
                            " if Postgres is replicating from archive, 0 otherwise.")
             metrics.append("# TYPE patroni_postgres_in_archive_recovery gauge")
             metrics.append("patroni_postgres_in_archive_recovery{0} {1}"
-                           .format(scope_label, int(postgres.get('replication_state') == 'in archive recovery')))
+                           .format(labels, int(postgres.get('replication_state') == 'in archive recovery')))
 
         metrics.append("# HELP patroni_postgres_server_version Version of Postgres (if running), 0 otherwise.")
         metrics.append("# TYPE patroni_postgres_server_version gauge")
-        metrics.append("patroni_postgres_server_version {0} {1}".format(scope_label, postgres.get('server_version', 0)))
+        metrics.append("patroni_postgres_server_version {0} {1}".format(labels, postgres.get('server_version', 0)))
 
         metrics.append("# HELP patroni_cluster_unlocked Value is 1 if the cluster is unlocked, 0 if locked.")
         metrics.append("# TYPE patroni_cluster_unlocked gauge")
-        metrics.append("patroni_cluster_unlocked{0} {1}".format(scope_label, int(postgres.get('cluster_unlocked', 0))))
+        metrics.append("patroni_cluster_unlocked{0} {1}".format(labels, int(postgres.get('cluster_unlocked', 0))))
 
         metrics.append("# HELP patroni_failsafe_mode_is_active Value is 1 if failsafe mode is active, 0 if inactive.")
         metrics.append("# TYPE patroni_failsafe_mode_is_active gauge")
         metrics.append("patroni_failsafe_mode_is_active{0} {1}"
-                       .format(scope_label, int(postgres.get('failsafe_mode_is_active', 0))))
+                       .format(labels, int(postgres.get('failsafe_mode_is_active', 0))))
 
         metrics.append("# HELP patroni_postgres_timeline Postgres timeline of this node (if running), 0 otherwise.")
         metrics.append("# TYPE patroni_postgres_timeline counter")
-        metrics.append("patroni_postgres_timeline{0} {1}".format(scope_label, postgres.get('timeline', 0)))
+        metrics.append("patroni_postgres_timeline{0} {1}".format(labels, postgres.get('timeline') or 0))
 
         metrics.append("# HELP patroni_dcs_last_seen Epoch timestamp when DCS was last contacted successfully"
                        " by Patroni.")
         metrics.append("# TYPE patroni_dcs_last_seen gauge")
-        metrics.append("patroni_dcs_last_seen{0} {1}".format(scope_label, postgres.get('dcs_last_seen', 0)))
+        metrics.append("patroni_dcs_last_seen{0} {1}".format(labels, postgres.get('dcs_last_seen', 0)))
 
         metrics.append("# HELP patroni_pending_restart Value is 1 if the node needs a restart, 0 otherwise.")
         metrics.append("# TYPE patroni_pending_restart gauge")
         metrics.append("patroni_pending_restart{0} {1}"
-                       .format(scope_label, int(patroni.postgresql.pending_restart)))
+                       .format(labels, int(bool(patroni.postgresql.pending_restart_reason))))
 
         metrics.append("# HELP patroni_is_paused Value is 1 if auto failover is disabled, 0 otherwise.")
         metrics.append("# TYPE patroni_is_paused gauge")
-        metrics.append("patroni_is_paused{0} {1}".format(scope_label, int(postgres.get('pause', 0))))
+        metrics.append("patroni_is_paused{0} {1}".format(labels, int(postgres.get('pause', 0))))
 
         self.write_response(200, '\n'.join(metrics) + '\n', content_type='text/plain')
 
@@ -661,9 +704,9 @@ class RestApiHandler(BaseHTTPRequestHandler):
             content_length = int(self.headers.get('content-length') or 0)
             if content_length == 0 and body_is_optional:
                 return {}
-            request: Union[Dict[str, Any], Any] = json.loads(self.rfile.read(content_length).decode('utf-8'))
+            request = json.loads(self.rfile.read(content_length).decode('utf-8'))
             if isinstance(request, dict) and (request or body_is_optional):
-                return request
+                return cast(Dict[str, Any], request)
         except Exception:
             logger.exception('Bad request')
         self.send_error(400)
@@ -683,7 +726,7 @@ class RestApiHandler(BaseHTTPRequestHandler):
         """
         request = self._read_json_content()
         if request:
-            cluster = self.server.patroni.dcs.get_cluster(True)
+            cluster = self.server.patroni.dcs.get_cluster()
             if not (cluster.config and cluster.config.modify_version):
                 return self.send_error(503)
             data = cluster.config.data.copy()
@@ -738,12 +781,12 @@ class RestApiHandler(BaseHTTPRequestHandler):
         else:
             self.send_error(502)
 
-    @check_access
+    @check_access(allowlist_check_members=False)
     def do_POST_failsafe(self) -> None:
         """Handle a ``POST`` request to ``/failsafe`` path.
 
         Writes a response with HTTP status ``200`` if this node is a Standby, or with HTTP status ``500`` if this is
-        the primary.
+        the primary. In addition to that it returns absolute value of received/replayed LSN in the ``lsn`` header.
 
         .. note::
             If ``failsafe_mode`` is not enabled, then write a response with HTTP status ``502``.
@@ -751,9 +794,11 @@ class RestApiHandler(BaseHTTPRequestHandler):
         if self.server.patroni.ha.is_failsafe_mode():
             request = self._read_json_content()
             if request:
-                message = self.server.patroni.ha.update_failsafe(request) or 'Accepted'
+                ret = self.server.patroni.ha.update_failsafe(request)
+                headers = {'lsn': str(ret)} if isinstance(ret, int) else {}
+                message = ret if isinstance(ret, str) else 'Accepted'
                 code = 200 if message == 'Accepted' else 500
-                self.write_response(code, message)
+                self.write_response(code, message, headers=headers)
         else:
             self.send_error(502)
 
@@ -819,7 +864,7 @@ class RestApiHandler(BaseHTTPRequestHandler):
             * ``schedule``: timestamp at which the restart should occur;
             * ``role``: restart only nodes which role is ``role``. Can be either:
 
-                * ``primary`` (or ``master``); or
+                * ``primary`; or
                 * ``replica``.
 
             * ``postgres_version``: restart only nodes which PostgreSQL version is less than ``postgres_version``, e.g.
@@ -848,7 +893,7 @@ class RestApiHandler(BaseHTTPRequestHandler):
             If it's not able to parse the request body, then the request is silently discarded.
         """
         status_code = 500
-        data = 'restart failed'
+        data = PostgresqlState.RESTART_FAILED
         request = self._read_json_content(body_is_optional=True)
         cluster = self.server.patroni.dcs.get_cluster()
         if request is None:
@@ -857,7 +902,7 @@ class RestApiHandler(BaseHTTPRequestHandler):
         if request:
             logger.debug("received restart request: {0}".format(request))
 
-        if self.server.patroni.config.get_global_config(cluster).is_paused and 'schedule' in request:
+        if global_config.from_cluster(cluster).is_paused and 'schedule' in request:
             self.write_response(status_code, "Can't schedule restart in the paused state")
             return
 
@@ -868,9 +913,9 @@ class RestApiHandler(BaseHTTPRequestHandler):
                     status_code = _
                     break
             elif k == 'role':
-                if request[k] not in ('master', 'primary', 'replica'):
+                if request[k] not in (PostgresqlRole.PRIMARY, PostgresqlRole.STANDBY_LEADER, PostgresqlRole.REPLICA):
                     status_code = 400
-                    data = "PostgreSQL role should be either primary or replica"
+                    data = "PostgreSQL role should be either primary, standby_leader, or replica"
                     break
             elif k == 'postgres_version':
                 try:
@@ -1026,16 +1071,17 @@ class RestApiHandler(BaseHTTPRequestHandler):
 
         :returns: a string with the error message or ``None`` if good nodes are found.
         """
-        is_synchronous_mode = self.server.patroni.config.get_global_config(cluster).is_synchronous_mode
+        config = global_config.from_cluster(cluster)
         if leader and (not cluster.leader or cluster.leader.name != leader):
             return 'leader name does not match'
         if candidate:
-            if action == 'switchover' and is_synchronous_mode and not cluster.sync.matches(candidate):
+            if action == 'switchover' and config.is_synchronous_mode\
+                    and not config.is_quorum_commit_mode and not cluster.sync.matches(candidate):
                 return 'candidate name does not match with sync_standby'
             members = [m for m in cluster.members if m.name == candidate]
             if not members:
                 return 'candidate does not exists'
-        elif is_synchronous_mode:
+        elif config.is_synchronous_mode and not config.is_quorum_commit_mode:
             members = [m for m in cluster.members if cluster.sync.matches(m.name)]
             if not members:
                 return action + ' is not possible: can not find sync_standby'
@@ -1067,7 +1113,8 @@ class RestApiHandler(BaseHTTPRequestHandler):
             * ``412``: if operation is not possible;
             * ``503``: if unable to register the operation to the DCS;
             * HTTP status returned by :func:`parse_schedule`, if any error was observed while parsing the schedule;
-            * HTTP status returned by :func:`poll_failover_result` if the operation has been processed immediately.
+            * HTTP status returned by :func:`poll_failover_result` if the operation has been processed immediately;
+            * ``400``: if none of the above applies.
 
         .. note::
             If unable to parse the request body, then the request is silently discarded.
@@ -1083,7 +1130,7 @@ class RestApiHandler(BaseHTTPRequestHandler):
         candidate = request.get('candidate') or request.get('member')
         scheduled_at = request.get('scheduled_at')
         cluster = self.server.patroni.dcs.get_cluster()
-        global_config = self.server.patroni.config.get_global_config(cluster)
+        config = global_config.from_cluster(cluster)
 
         logger.info("received %s request with leader=%s candidate=%s scheduled_at=%s",
                     action, leader, candidate, scheduled_at)
@@ -1094,15 +1141,22 @@ class RestApiHandler(BaseHTTPRequestHandler):
             data = 'Switchover could be performed only from a specific leader'
 
         if not data and scheduled_at:
-            if not leader:
-                data = 'Scheduled {0} is possible only from a specific leader'.format(action)
-            if not data and global_config.is_paused:
-                data = "Can't schedule {0} in the paused state".format(action)
-            if not data:
+            if action == 'failover':
+                data = "Failover can't be scheduled"
+            elif config.is_paused:
+                data = "Can't schedule switchover in the paused state"
+            else:
                 (status_code, data, scheduled_at) = self.parse_schedule(scheduled_at, action)
 
-        if not data and global_config.is_paused and not candidate:
-            data = action.title() + ' is possible only to a specific candidate in a paused state'
+        if not data and config.is_paused and not candidate:
+            data = 'Switchover is possible only to a specific candidate in a paused state'
+
+        if action == 'failover' and leader:
+            logger.warning('received failover request with leader specified - performing switchover instead')
+            action = 'switchover'
+
+        if not data and leader == candidate:
+            data = 'Switchover target and source are the same'
 
         if not data and not scheduled_at:
             data = self.is_failover_possible(cluster, leader, candidate, action)
@@ -1119,7 +1173,7 @@ class RestApiHandler(BaseHTTPRequestHandler):
                     status_code, data = self.poll_failover_result(cluster.leader and cluster.leader.name,
                                                                   candidate, action)
             else:
-                data = 'failed to write {0} key into DCS'.format(action)
+                data = 'failed to write failover key into DCS'
                 status_code = 503
         # pyright thinks ``status_code`` can be ``None`` because ``parse_schedule`` call may return ``None``. However,
         # if that's the case, ``status_code`` will be overwritten somewhere between ``parse_schedule`` and
@@ -1139,8 +1193,16 @@ class RestApiHandler(BaseHTTPRequestHandler):
     def do_POST_citus(self) -> None:
         """Handle a ``POST`` request to ``/citus`` path.
 
-        Call :func:`~patroni.postgresql.CitusHandler.handle_event` to handle the request, then write a response with
-        HTTP status code ``200``.
+        .. note::
+            We keep this entrypoint for backward compatibility and simply dispatch the request to :meth:`do_POST_mpp`.
+        """
+        self.do_POST_mpp()
+
+    def do_POST_mpp(self) -> None:
+        """Handle a ``POST`` request to ``/mpp`` path.
+
+        Call :func:`~patroni.postgresql.mpp.AbstractMPPHandler.handle_event` to handle the request,
+        then write a response with HTTP status code ``200``.
 
         .. note::
             If unable to parse the request body, then the request is silently discarded.
@@ -1150,9 +1212,9 @@ class RestApiHandler(BaseHTTPRequestHandler):
             return
 
         patroni = self.server.patroni
-        if patroni.postgresql.citus_handler.is_coordinator() and patroni.ha.is_leader():
-            cluster = patroni.dcs.get_cluster(True)
-            patroni.postgresql.citus_handler.handle_event(cluster, request)
+        if patroni.postgresql.mpp_handler.is_coordinator() and patroni.ha.is_leader():
+            cluster = patroni.dcs.get_cluster()
+            patroni.postgresql.mpp_handler.handle_event(cluster, request)
         self.write_response(200, 'OK')
 
     def parse_request(self) -> bool:
@@ -1205,20 +1267,19 @@ class RestApiHandler(BaseHTTPRequestHandler):
 
         :returns: a dict with the status of Postgres/Patroni. The keys are:
 
-            * ``state``: Postgres state among ``stopping``, ``stopped``, ``stop failed``, ``crashed``, ``running``,
-              ``starting``, ``start failed``, ``restarting``, ``restart failed``, ``initializing new cluster``,
-              ``initdb failed``, ``running custom bootstrap script``, ``custom bootstrap failed``,
-              ``creating replica``, or ``unknown``;
+            * ``state``: one of :class:`~patroni.postgresql.misc.PostgresqlState` or ``unknown``;
             * ``postmaster_start_time``: ``pg_postmaster_start_time()``;
-            * ``role``: ``replica`` or ``master`` based on ``pg_is_in_recovery()`` output;
+            * ``role``: :class:`~patroni.postgresql.misc.PostgresqlRole.REPLICA` or
+                :class:`~patroni.postgresql.misc.PostgresqlRole.PRIMARY` based on ``pg_is_in_recovery()`` output;
             * ``server_version``: Postgres version without periods, e.g. ``150002`` for Postgres ``15.2``;
+            * ``latest_end_lsn``: latest_end_lsn value from ``pg_stat_get_wal_receiver()``, only on replica nodes;
             * ``xlog``: dictionary. Its structure depends on ``role``:
 
-                * If ``master``:
+                * If :class:`~patroni.postgresql.misc.PostgresqlRole.PRIMARY`:
 
                     * ``location``: ``pg_current_wal_flush_lsn()``
 
-                * If ``replica``:
+                * If :class:`~patroni.postgresql.misc.PostgresqlRole.REPLICA`:
 
                     * ``received_location``: ``pg_wal_lsn_diff(pg_last_wal_receive_lsn(), '0/0')``;
                     * ``replayed_location``: ``pg_wal_lsn_diff(pg_last_wal_replay_lsn(), '0/0)``;
@@ -1226,6 +1287,7 @@ class RestApiHandler(BaseHTTPRequestHandler):
                     * ``paused``: ``pg_is_wal_replay_paused()``;
 
             * ``sync_standby``: ``True`` if replication mode is synchronous and this is a sync standby;
+            * ``quorum_standby``: ``True`` if replication mode is quorum and this is a quorum standby;
             * ``timeline``: PostgreSQL primary node timeline;
             * ``replication``: :class:`list` of :class:`dict` entries, one for each replication connection. Each entry
                 contains the following keys:
@@ -1245,30 +1307,34 @@ class RestApiHandler(BaseHTTPRequestHandler):
         """
         postgresql = self.server.patroni.postgresql
         cluster = self.server.patroni.dcs.cluster
-        global_config = self.server.patroni.config.get_global_config(cluster)
+        config = global_config.from_cluster(cluster)
         try:
 
-            if postgresql.state not in ('running', 'restarting', 'starting'):
+            if postgresql.state not in (PostgresqlState.RUNNING, PostgresqlState.RESTARTING,
+                                        PostgresqlState.STARTING):
                 raise RetryFailedError('')
-            replication_state = ('(pg_catalog.pg_stat_get_wal_receiver()).status'
-                                 if postgresql.major_version >= 90600 else 'NULL') + ", " +\
-                ("pg_catalog.current_setting('restore_command')" if postgresql.major_version >= 120000 else "NULL")
+            replication_state = ("pg_catalog.pg_{0}_{1}_diff(wr.latest_end_lsn, '0/0')::bigint, wr.status"
+                                 if postgresql.major_version >= 90600 else "NULL, NULL") + ", " +\
+                ("pg_catalog.current_setting('restore_command')" if postgresql.major_version >= 120000 else "NULL") +\
+                ", " + ("pg_catalog.pg_wal_lsn_diff(wr.written_lsn, '0/0')::bigint"
+                        if postgresql.major_version >= 130000 else "NULL")
             stmt = ("SELECT " + postgresql.POSTMASTER_START_TIME + ", " + postgresql.TL_LSN + ","
                     " pg_catalog.pg_last_xact_replay_timestamp(), " + replication_state + ","
-                    " pg_catalog.array_to_json(pg_catalog.array_agg(pg_catalog.row_to_json(ri))) "
+                    " (SELECT pg_catalog.array_to_json(pg_catalog.array_agg(pg_catalog.row_to_json(ri))) "
                     "FROM (SELECT (SELECT rolname FROM pg_catalog.pg_authid WHERE oid = usesysid) AS usename,"
                     " application_name, client_addr, w.state, sync_state, sync_priority"
-                    " FROM pg_catalog.pg_stat_get_wal_senders() w, pg_catalog.pg_stat_get_activity(pid)) AS ri")
+                    " FROM pg_catalog.pg_stat_get_wal_senders() w, pg_catalog.pg_stat_get_activity(pid)) AS ri)") +\
+                (" FROM pg_catalog.pg_stat_get_wal_receiver() AS wr" if postgresql.major_version >= 90600 else "")
 
             row = self.query(stmt.format(postgresql.wal_name, postgresql.lsn_name,
                                          postgresql.wal_flush), retry=retry)[0]
             result = {
                 'state': postgresql.state,
                 'postmaster_start_time': row[0],
-                'role': 'replica' if row[1] == 0 else 'master',
+                'role': PostgresqlRole.REPLICA if row[1] == 0 else PostgresqlRole.PRIMARY,
                 'server_version': postgresql.server_version,
                 'xlog': ({
-                    'received_location': row[4] or row[3],
+                    'received_location': row[10] or row[4] or row[3],
                     'replayed_location': row[3],
                     'replayed_timestamp': row[6],
                     'paused': row[5]} if row[1] == 0 else {
@@ -1276,12 +1342,12 @@ class RestApiHandler(BaseHTTPRequestHandler):
                 })
             }
 
-            if result['role'] == 'replica' and global_config.is_standby_cluster:
+            if result['role'] == PostgresqlRole.REPLICA and config.is_standby_cluster:
                 result['role'] = postgresql.role
 
-            if result['role'] == 'replica' and global_config.is_synchronous_mode\
+            if result['role'] == PostgresqlRole.REPLICA and config.is_synchronous_mode\
                     and cluster and cluster.sync.matches(postgresql.name):
-                result['sync_standby'] = True
+                result['quorum_standby' if global_config.is_quorum_commit_mode else 'sync_standby'] = True
 
             if row[1] > 0:
                 result['timeline'] = row[1]
@@ -1290,21 +1356,24 @@ class RestApiHandler(BaseHTTPRequestHandler):
                     if not cluster or cluster.is_unlocked() or not cluster.leader else cluster.leader.timeline
                 result['timeline'] = postgresql.replica_cached_timeline(leader_timeline)
 
-            replication_state = postgresql.replication_state_from_parameters(row[1] > 0, row[7], row[8])
+            if row[7]:
+                result['latest_end_lsn'] = row[7]
+
+            replication_state = postgresql.replication_state_from_parameters(row[1] > 0, row[8], row[9])
             if replication_state:
                 result['replication_state'] = replication_state
 
-            if row[9]:
-                result['replication'] = row[9]
+            if row[11]:
+                result['replication'] = row[11]
 
         except (psycopg.Error, RetryFailedError, PostgresConnectionException):
             state = postgresql.state
-            if state == 'running':
+            if state == PostgresqlState.RUNNING:
                 logger.exception('get_postgresql_status')
                 state = 'unknown'
             result: Dict[str, Any] = {'state': state, 'role': postgresql.role}
 
-        if global_config.is_paused:
+        if config.is_paused:
             result['pause'] = True
         if not cluster or cluster.is_unlocked():
             result['cluster_unlocked'] = True
@@ -1368,6 +1437,9 @@ class RestApiServer(ThreadingMixIn, HTTPServer, Thread):
     def query(self, sql: str, *params: Any) -> List[Tuple[Any, ...]]:
         """Execute *sql* query with *params* and optionally return results.
 
+        .. note::
+            Prefer to use own connection to postgres and fallback to ``heartbeat`` when own isn't available.
+
         :param sql: the SQL statement to be run.
         :param params: positional arguments to be used as parameters for *sql*.
 
@@ -1377,10 +1449,21 @@ class RestApiServer(ThreadingMixIn, HTTPServer, Thread):
             :class:`psycopg.Error`: if had issues while executing *sql*.
             :class:`~patroni.exceptions.PostgresConnectionException`: if had issues while connecting to the database.
         """
+        # We first try to get a heartbeat connection because it is always required for the main thread.
         try:
-            return self.patroni.postgresql.query(sql, *params, retry=False)
-        except RetryFailedError as e:
-            raise PostgresConnectionException(str(e))
+            heartbeat_connection = self.patroni.postgresql.connection_pool.get('heartbeat')
+            heartbeat_connection.get()  # try to open psycopg connection to postgres
+        except psycopg.Error as exc:
+            raise PostgresConnectionException('connection problems') from exc
+
+        try:
+            connection = self.patroni.postgresql.connection_pool.get('restapi')
+            connection.get()  # try to open psycopg connection to postgres
+        except psycopg.Error:
+            logger.debug('restapi connection to postgres is not available')
+            connection = heartbeat_connection
+
+        return connection.query(sql, *params)
 
     @staticmethod
     def _set_fd_cloexec(fd: socket.socket) -> None:
@@ -1460,7 +1543,7 @@ class RestApiServer(ThreadingMixIn, HTTPServer, Thread):
                         except Exception as e:
                             logger.debug('Failed to parse url %s: %r', member.api_url, e)
 
-    def check_access(self, rh: RestApiHandler) -> Optional[bool]:
+    def check_access(self, rh: RestApiHandler, allowlist_check_members: bool = True) -> Optional[bool]:
         """Ensure client has enough privileges to perform a given request.
 
         Write a response back to the client if any issue is observed, and the HTTP status may be:
@@ -1473,12 +1556,17 @@ class RestApiServer(ThreadingMixIn, HTTPServer, Thread):
                 * a client certificate is expected by the server, but is missing in the request.
 
         :param rh: the request which access should be checked.
+        :param allowlist_check_members: whether we should check the source ip against existing cluster members.
 
         :returns: ``True`` if client access verification succeeded, otherwise ``None``.
         """
-        if self.__allowlist or self.__allowlist_include_members:
+        allowlist_check_members = allowlist_check_members and bool(self.__allowlist_include_members)
+        if self.__allowlist or allowlist_check_members:
             incoming_ip = ip_address(rh.client_address[0])
-            if not any(incoming_ip in net for net in self.__allowlist + tuple(self.__members_ips())):
+
+            members_ips = tuple(self.__members_ips()) if allowlist_check_members else ()
+
+            if not any(incoming_ip in net for net in self.__allowlist + members_ips):
                 return rh.write_response(403, 'Access is denied')
 
         if not hasattr(rh.request, 'getpeercert') or not rh.request.getpeercert():  # valid client cert isn't present
@@ -1524,13 +1612,16 @@ class RestApiServer(ThreadingMixIn, HTTPServer, Thread):
         if hostname in ('', '*'):
             hostname = None
 
-        info = socket.getaddrinfo(hostname, port, socket.AF_UNSPEC, socket.SOCK_STREAM, 0, socket.AI_PASSIVE)
+        # Filter out unexpected results when python is compiled with --disable-ipv6 and running on IPv6 system.
+        info = [(a[0], a[4][0], a[4][1])
+                for a in socket.getaddrinfo(hostname, port, socket.AF_UNSPEC, socket.SOCK_STREAM, 0, socket.AI_PASSIVE)
+                if isinstance(a[4][0], str) and isinstance(a[4][1], int)]
         # in case dual stack is not supported we want IPv4 to be preferred over IPv6
         info.sort(key=lambda x: x[0] == socket.AF_INET, reverse=not dual_stack)
 
         self.address_family = info[0][0]
         try:
-            HTTPServer.__init__(self, info[0][-1][:2], RestApiHandler)
+            HTTPServer.__init__(self, (info[0][1], info[0][2]), RestApiHandler)
         except socket.error:
             logger.error(
                 "Couldn't start a service on '%s:%s', please check your `restapi.listen` configuration", hostname, port)
@@ -1546,7 +1637,7 @@ class RestApiServer(ThreadingMixIn, HTTPServer, Thread):
         :param listen: IP and port to bind REST API to. It should be a string in the format ``host:port``, where
             ``host`` can be a hostname or IP address. It is the value of ``restapi.listen`` setting.
         :param ssl_options: dictionary that may contain the following keys, depending on what has been configured in
-            ``restapi` section:
+            ``restapi`` section:
 
             * ``certfile``: path to PEM certificate. If given, will start in HTTPS mode;
             * ``keyfile``: path to key of ``certfile``;
@@ -1647,12 +1738,11 @@ class RestApiServer(ThreadingMixIn, HTTPServer, Thread):
 
         :returns: serial number of the certificate configured through ``restapi.certfile`` setting.
         """
-        if self.__ssl_options.get('certfile'):
+        certfile: Optional[str] = self.__ssl_options.get('certfile')
+        if certfile:
             import ssl
             try:
-                crt: Dict[str, Any] = ssl._ssl._test_decode_cert(self.__ssl_options['certfile'])  # pyright: ignore
-                if TYPE_CHECKING:  # pragma: no cover
-                    assert isinstance(crt, dict)
+                crt = cast(Dict[str, Any], ssl._ssl._test_decode_cert(certfile))  # pyright: ignore
                 return crt.get('serialNumber')
             except ssl.SSLError as e:
                 logger.error('Failed to get serial number from certificate %s: %r', self.__ssl_options['certfile'], e)

patroni/collections.py

@@ -1,9 +1,10 @@
 """Patroni custom object types somewhat like :mod:`collections` module.
 
-Provides a case insensitive :class:`dict` and :class:`set` object types.
+Provides a case insensitive :class:`dict` and :class:`set` object types, and `EMPTY_DICT` frozen dictionary object.
 """
 from collections import OrderedDict
-from typing import Any, Collection, Dict, Iterator, KeysView, MutableMapping, MutableSet, Optional
+from copy import deepcopy
+from typing import Any, Collection, Dict, Iterator, KeysView, Mapping, MutableMapping, MutableSet, Optional
 
 
 class CaseInsensitiveSet(MutableSet[str]):
@@ -48,7 +49,7 @@ class CaseInsensitiveSet(MutableSet[str]):
         """
         return str(set(self._values.values()))
 
-    def __contains__(self, value: str) -> bool:
+    def __contains__(self, value: object) -> bool:
         """Check if set contains *value*.
 
         The check is performed case-insensitively.
@@ -57,7 +58,7 @@ class CaseInsensitiveSet(MutableSet[str]):
 
         :returns: ``True`` if *value* is already in the set, ``False`` otherwise.
         """
-        return value.lower() in self._values
+        return isinstance(value, str) and value.lower() in self._values
 
     def __iter__(self) -> Iterator[str]:
         """Iterate over the values in this set.
@@ -207,3 +208,47 @@ class CaseInsensitiveDict(MutableMapping[str, Any]):
             "<CaseInsensitiveDict{'A': 'B', 'c': 'd'} at ..."
         """
         return '<{0}{1} at {2:x}>'.format(type(self).__name__, dict(self.items()), id(self))
+
+
+class _FrozenDict(Mapping[str, Any]):
+    """Frozen dictionary object."""
+
+    def __init__(self, *args: Any, **kwargs: Any) -> None:
+        """Create a new instance of :class:`_FrozenDict` with given data."""
+        self.__values: Dict[str, Any] = dict(*args, **kwargs)
+
+    def __iter__(self) -> Iterator[str]:
+        """Iterate over keys of this dict.
+
+        :yields: each key present in the dict. Yields each key with its last case that has been stored.
+        """
+        return iter(self.__values)
+
+    def __len__(self) -> int:
+        """Get the length of this dict.
+
+        :returns: number of keys in the dict.
+
+        :Example:
+
+        >>> len(_FrozenDict())
+        0
+        """
+        return len(self.__values)
+
+    def __getitem__(self, key: str) -> Any:
+        """Get the value corresponding to *key*.
+
+        :returns: value corresponding to *key*.
+        """
+        return self.__values[key]
+
+    def copy(self) -> Dict[str, Any]:
+        """Create a copy of this dict.
+
+        :return: a new dict object with the same keys and values of this dict.
+        """
+        return deepcopy(self.__values)
+
+
+EMPTY_DICT = _FrozenDict()

patroni/config.py

@@ -2,21 +2,24 @@
 import json
 import logging
 import os
+import re
 import shutil
 import tempfile
-import yaml
 
 from collections import defaultdict
 from copy import deepcopy
-from typing import Any, Callable, Collection, Dict, List, Optional, Union, TYPE_CHECKING
+from typing import Any, Callable, cast, Collection, Dict, List, Optional, TYPE_CHECKING, Union
+
+import yaml
 
 from . import PATRONI_ENV_PREFIX
-from .collections import CaseInsensitiveDict
-from .dcs import ClusterConfig, Cluster
+from .collections import CaseInsensitiveDict, EMPTY_DICT
+from .dcs import ClusterConfig
 from .exceptions import ConfigParseError
 from .file_perm import pg_perm
 from .postgresql.config import ConfigHandler
 from .utils import deep_compare, parse_bool, parse_int, patch_config
+from .validator import IntValidator
 
 logger = logging.getLogger(__name__)
 
@@ -31,7 +34,8 @@ _AUTH_ALLOWED_PARAMETERS = (
     'sslcrl',
     'sslcrldir',
     'gssencmode',
-    'channel_binding'
+    'channel_binding',
+    'sslnegotiation'
 )
 
 
@@ -53,154 +57,6 @@ def default_validator(conf: Dict[str, Any]) -> List[str]:
     return []
 
 
-class GlobalConfig(object):
-    """A class that wraps global configuration and provides convenient methods to access/check values.
-
-    It is instantiated either by calling :func:`get_global_config` or :meth:`Config.get_global_config`, which picks
-    either a configuration from provided :class:`Cluster` object (the most up-to-date) or from the
-    local cache if :class:`ClusterConfig` is not initialized or doesn't have a valid config.
-    """
-
-    def __init__(self, config: Dict[str, Any]) -> None:
-        """Initialize :class:`GlobalConfig` object with given *config*.
-
-        :param config: current configuration either from
-                       :class:`ClusterConfig` or from :func:`Config.dynamic_configuration`.
-        """
-        self.__config = config
-
-    def get(self, name: str) -> Any:
-        """Gets global configuration value by *name*.
-
-        :param name: parameter name.
-
-        :returns: configuration value or ``None`` if it is missing.
-        """
-        return self.__config.get(name)
-
-    def check_mode(self, mode: str) -> bool:
-        """Checks whether the certain parameter is enabled.
-
-        :param mode: parameter name, e.g. ``synchronous_mode``, ``failsafe_mode``, ``pause``, ``check_timeline``, and
-            so on.
-
-        :returns: ``True`` if parameter *mode* is enabled in the global configuration.
-        """
-        return bool(parse_bool(self.__config.get(mode)))
-
-    @property
-    def is_paused(self) -> bool:
-        """``True`` if cluster is in maintenance mode."""
-        return self.check_mode('pause')
-
-    @property
-    def is_synchronous_mode(self) -> bool:
-        """``True`` if synchronous replication is requested."""
-        return self.check_mode('synchronous_mode')
-
-    @property
-    def is_synchronous_mode_strict(self) -> bool:
-        """``True`` if at least one synchronous node is required."""
-        return self.check_mode('synchronous_mode_strict')
-
-    def get_standby_cluster_config(self) -> Union[Dict[str, Any], Any]:
-        """Get ``standby_cluster`` configuration.
-
-        :returns: a copy of ``standby_cluster`` configuration.
-        """
-        return deepcopy(self.get('standby_cluster'))
-
-    @property
-    def is_standby_cluster(self) -> bool:
-        """``True`` if global configuration has a valid ``standby_cluster`` section."""
-        config = self.get_standby_cluster_config()
-        return isinstance(config, dict) and\
-            bool(config.get('host') or config.get('port') or config.get('restore_command'))
-
-    def get_int(self, name: str, default: int = 0) -> int:
-        """Gets current value of *name* from the global configuration and try to return it as :class:`int`.
-
-        :param name: name of the parameter.
-        :param default: default value if *name* is not in the configuration or invalid.
-
-        :returns: currently configured value of *name* from the global configuration or *default* if it is not set or
-            invalid.
-        """
-        ret = parse_int(self.get(name))
-        return default if ret is None else ret
-
-    @property
-    def min_synchronous_nodes(self) -> int:
-        """The minimal number of synchronous nodes based on whether ``synchronous_mode_strict`` is enabled or not."""
-        return 1 if self.is_synchronous_mode_strict else 0
-
-    @property
-    def synchronous_node_count(self) -> int:
-        """Currently configured value of ``synchronous_node_count`` from the global configuration.
-
-        Assume ``1`` if it is not set or invalid.
-        """
-        return max(self.get_int('synchronous_node_count', 1), self.min_synchronous_nodes)
-
-    @property
-    def maximum_lag_on_failover(self) -> int:
-        """Currently configured value of ``maximum_lag_on_failover`` from the global configuration.
-
-        Assume ``1048576`` if it is not set or invalid.
-        """
-        return self.get_int('maximum_lag_on_failover', 1048576)
-
-    @property
-    def maximum_lag_on_syncnode(self) -> int:
-        """Currently configured value of ``maximum_lag_on_syncnode`` from the global configuration.
-
-        Assume ``-1`` if it is not set or invalid.
-        """
-        return self.get_int('maximum_lag_on_syncnode', -1)
-
-    @property
-    def primary_start_timeout(self) -> int:
-        """Currently configured value of ``primary_start_timeout`` from the global configuration.
-
-        Assume ``300`` if it is not set or invalid.
-
-        .. note::
-            ``master_start_timeout`` is still supported to keep backward compatibility.
-        """
-        default = 300
-        return self.get_int('primary_start_timeout', default)\
-            if 'primary_start_timeout' in self.__config else self.get_int('master_start_timeout', default)
-
-    @property
-    def primary_stop_timeout(self) -> int:
-        """Currently configured value of ``primary_stop_timeout`` from the global configuration.
-
-        Assume ``0`` if it is not set or invalid.
-
-        .. note::
-            ``master_stop_timeout`` is still supported to keep backward compatibility.
-        """
-        default = 0
-        return self.get_int('primary_stop_timeout', default)\
-            if 'primary_stop_timeout' in self.__config else self.get_int('master_stop_timeout', default)
-
-
-def get_global_config(cluster: Optional[Cluster], default: Optional[Dict[str, Any]] = None) -> GlobalConfig:
-    """Instantiates :class:`GlobalConfig` based on the input.
-
-    :param cluster: the currently known cluster state from DCS.
-    :param default: default configuration, which will be used if there is no valid *cluster.config*.
-
-    :returns: :class:`GlobalConfig` object.
-    """
-    # Try to protect from the case when DCS was wiped out
-    if cluster and cluster.config and cluster.config.modify_version:
-        config = cluster.config.data
-    else:
-        config = default or {}
-    return GlobalConfig(deepcopy(config))
-
-
 class Config(object):
     """Handle Patroni configuration.
 
@@ -257,7 +113,7 @@ class Config(object):
 
               * file or directory path passed as command-line argument (*configfile*), if it exists and the file or
                 files found in the directory can be parsed (see :meth:`~Config._load_config_path`), otherwise
-              * YAML file passed via the environment variable (see :cvar:`PATRONI_CONFIG_VARIABLE`), if the referenced
+              * YAML file passed via the environment variable (see :attr:`PATRONI_CONFIG_VARIABLE`), if the referenced
                 file exists and can be parsed, otherwise
               * from configuration values defined as environment variables, see
                 :meth:`~Config._build_environment_configuration`.
@@ -289,8 +145,9 @@ class Config(object):
         self.__effective_configuration = self._build_effective_configuration({}, self._local_configuration)
         self._data_dir = self.__effective_configuration.get('postgresql', {}).get('data_dir', "")
         self._cache_file = os.path.join(self._data_dir, self.__CACHE_FILENAME)
-        if validator:  # patronictl uses validator=None and we don't want to load anything from local cache in this case
-            self._load_cache()
+        if validator:  # patronictl uses validator=None
+            self._load_cache()  # we don't want to load anything from local cache for ctl
+            self._validate_contradictory_tags()  # irrelevant for ctl
         self._cache_needs_saving = False
 
     @property
@@ -331,6 +188,7 @@ class Config(object):
 
         :raises:
             :class:`ConfigParseError`: if *path* is invalid.
+            :class:`ConfigParseError`: if *path* does not contain dict (empty file or no mapping values).
         """
         if os.path.isfile(path):
             files = [path]
@@ -345,7 +203,10 @@ class Config(object):
         for fname in files:
             with open(fname) as f:
                 config = yaml.safe_load(f)
-                patch_config(overall_config, config)
+                if not isinstance(config, dict):
+                    logger.error('%s does not contain a dict', fname)
+                    raise ConfigParseError(f'invalid config file {fname}')
+                patch_config(overall_config, cast(Dict[Any, Any], config))
         return overall_config
 
     def _load_config_file(self) -> Dict[str, Any]:
@@ -399,6 +260,66 @@ class Config(object):
                     except Exception:
                         logger.error('Can not remove temporary file %s', tmpfile)
 
+    def __get_and_maybe_adjust_int_value(self, config: Dict[str, Any], param: str, min_value: int) -> int:
+        """Get, validate and maybe adjust a *param* integer value from the *config* :class:`dict`.
+
+        .. note:
+            If the value is smaller than provided *min_value* we update the *config*.
+
+            This method may raise an exception if value isn't :class:`int` or cannot be casted to :class:`int`.
+
+        :param config: :class:`dict` object with new global configuration.
+        :param param: name of the configuration parameter we want to read/validate/adjust.
+        :param min_value: the minimum possible value that a given *param* could have.
+
+        :returns: an integer value which corresponds to a provided *param*.
+        """
+        value = int(config.get(param, self.__DEFAULT_CONFIG[param]))
+        if value < min_value:
+            logger.warning("%s=%d can't be smaller than %d, adjusting...", param, value, min_value)
+            value = config[param] = min_value
+        return value
+
+    def _validate_and_adjust_timeouts(self, config: Dict[str, Any]) -> None:
+        """Validate and adjust ``loop_wait``, ``retry_timeout``, and ``ttl`` values if necessary.
+
+        Minimum values:
+
+            * ``loop_wait``: 1 second;
+            * ``retry_timeout``: 3 seconds.
+            * ``ttl``: 20 seconds;
+
+        Maximum values:
+        In case if values don't fulfill the following rule, ``retry_timeout`` and ``loop_wait``
+        are reduced so that the rule is fulfilled:
+
+            .. code-block:: python
+
+                loop_wait + 2 * retry_timeout <= ttl
+
+        .. note:
+            We prefer to reduce ``loop_wait`` and will reduce ``retry_timeout`` only if ``loop_wait``
+            is already set to a minimal possible value.
+
+        :param config: :class:`dict` object with new global configuration.
+        """
+
+        min_loop_wait = 1
+        loop_wait = self. __get_and_maybe_adjust_int_value(config, 'loop_wait', min_loop_wait)
+        retry_timeout = self. __get_and_maybe_adjust_int_value(config, 'retry_timeout', 3)
+        ttl = self. __get_and_maybe_adjust_int_value(config, 'ttl', 20)
+
+        if min_loop_wait + 2 * retry_timeout > ttl:
+            config['loop_wait'] = min_loop_wait
+            config['retry_timeout'] = (ttl - min_loop_wait) // 2
+            logger.warning('Violated the rule "loop_wait + 2*retry_timeout <= ttl", where ttl=%d. '
+                           'Adjusting loop_wait from %d to %d and retry_timeout from %d to %d',
+                           ttl, loop_wait, min_loop_wait, retry_timeout, config['retry_timeout'])
+        elif loop_wait + 2 * retry_timeout > ttl:
+            config['loop_wait'] = ttl - 2 * retry_timeout
+            logger.warning('Violated the rule "loop_wait + 2*retry_timeout <= ttl", where ttl=%d and retry_timeout=%d.'
+                           ' Adjusting loop_wait from %d to %d', ttl, retry_timeout, loop_wait, config['loop_wait'])
+
     # configuration could be either ClusterConfig or dict
     def set_dynamic_configuration(self, configuration: Union[ClusterConfig, Dict[str, Any]]) -> bool:
         """Set dynamic configuration values with given *configuration*.
@@ -416,6 +337,7 @@ class Config(object):
 
         if not deep_compare(self._dynamic_configuration, configuration):
             try:
+                self._validate_and_adjust_timeouts(configuration)
                 self.__effective_configuration = self._build_effective_configuration(configuration,
                                                                                      self._local_configuration)
                 self._dynamic_configuration = configuration
@@ -441,6 +363,7 @@ class Config(object):
                     new_configuration = self._build_effective_configuration(self._dynamic_configuration, configuration)
                     self._local_configuration = configuration
                     self.__effective_configuration = new_configuration
+                    self._validate_contradictory_tags()
                     return True
                 else:
                     logger.info('No local configuration items changed.')
@@ -471,7 +394,6 @@ class Config(object):
                 * ``cluster_name``: set through ``scope`` local configuration or through ``PATRONI_SCOPE`` environment
                     variable;
                 * ``hot_standby``: always enabled;
-                * ``wal_log_hints``: always enabled.
 
         :param parameters: Postgres parameters to be processed. Should be the parsed YAML value of
             ``postgresql.parameters`` configuration, either from local or from dynamic configuration.
@@ -487,8 +409,10 @@ class Config(object):
             if name not in ConfigHandler.CMDLINE_OPTIONS:
                 pg_params[name] = value
             elif not is_local:
-                if ConfigHandler.CMDLINE_OPTIONS[name][1](value):
-                    pg_params[name] = value
+                validator = ConfigHandler.CMDLINE_OPTIONS[name][1]
+                if validator(value):
+                    int_val = parse_int(value) if isinstance(validator, IntValidator) else None
+                    pg_params[name] = int_val if isinstance(int_val, int) else value
                 else:
                     logger.warning("postgresql parameter %s=%s failed validation, defaulting to %s",
                                    name, value, ConfigHandler.CMDLINE_OPTIONS[name][0])
@@ -526,14 +450,14 @@ class Config(object):
 
         for name, value in dynamic_configuration.items():
             if name == 'postgresql':
-                for name, value in (value or {}).items():
+                for name, value in (value or EMPTY_DICT).items():
                     if name == 'parameters':
                         config['postgresql'][name].update(self._process_postgresql_parameters(value))
                     elif name not in ('connect_address', 'proxy_address', 'listen',
                                       'config_dir', 'data_dir', 'pgpass', 'authentication'):
                         config['postgresql'][name] = deepcopy(value)
             elif name == 'standby_cluster':
-                for name, value in (value or {}).items():
+                for name, value in (value or EMPTY_DICT).items():
                     if name in self.__DEFAULT_CONFIG['standby_cluster']:
                         config['standby_cluster'][name] = deepcopy(value)
             elif name in config:  # only variables present in __DEFAULT_CONFIG allowed to be overridden from DCS
@@ -616,8 +540,9 @@ class Config(object):
         _set_section_values('ctl', ['insecure', 'cacert', 'certfile', 'keyfile', 'keyfile_password'])
         _set_section_values('postgresql', ['listen', 'connect_address', 'proxy_address',
                                            'config_dir', 'data_dir', 'pgpass', 'bin_dir'])
-        _set_section_values('log', ['level', 'traceback_level', 'format', 'dateformat', 'max_queue_size',
-                                    'dir', 'file_size', 'file_num', 'loggers'])
+        _set_section_values('log', ['type', 'level', 'traceback_level', 'format', 'dateformat', 'static_fields',
+                                    'max_queue_size', 'dir', 'mode', 'file_size', 'file_num', 'loggers',
+                                    'deduplicate_heartbeat_logs'])
         _set_section_values('raft', ['data_dir', 'self_addr', 'partner_addrs', 'password', 'bind_addr'])
 
         for binary in ('pg_ctl', 'initdb', 'pg_controldata', 'pg_basebackup', 'postgres', 'pg_isready', 'pg_rewind'):
@@ -626,7 +551,8 @@ class Config(object):
                 ret['postgresql'].setdefault('bin_name', {})[binary] = value
 
         # parse all values retrieved from the environment as Python objects, according to the expected type
-        for first, second in (('restapi', 'allowlist_include_members'), ('ctl', 'insecure')):
+        for first, second in (('restapi', 'allowlist_include_members'), ('ctl', 'insecure'),
+                              ('log', 'deduplicate_heartbeat_logs')):
             value = ret.get(first, {}).pop(second, None)
             if value:
                 value = parse_bool(value)
@@ -634,7 +560,7 @@ class Config(object):
                     ret[first][second] = value
 
         for first, params in (('restapi', ('request_queue_size',)),
-                              ('log', ('max_queue_size', 'file_size', 'file_num'))):
+                              ('log', ('max_queue_size', 'file_size', 'file_num', 'mode'))):
             for second in params:
                 value = ret.get(first, {}).pop(second, None)
                 if value:
@@ -664,6 +590,12 @@ class Config(object):
                 if value:
                     ret[first][second] = value
 
+        logformat = ret.get('log', {}).get('format')
+        if logformat and not re.search(r'%\(\w+\)', logformat):
+            logformat = _parse_list(logformat)
+            if logformat:
+                ret['log']['format'] = logformat
+
         def _parse_dict(value: str) -> Optional[Dict[str, Any]]:
             """Parse an YAML dictionary *value* as a :class:`dict`.
 
@@ -679,7 +611,12 @@ class Config(object):
                 logger.exception('Exception when parsing dict %s', value)
                 return None
 
-        for first, params in (('restapi', ('http_extra_headers', 'https_extra_headers')), ('log', ('loggers',))):
+        dict_configs = (
+            ('restapi', ('http_extra_headers', 'https_extra_headers')),
+            ('log', ('static_fields', 'loggers'))
+        )
+
+        for first, params in dict_configs:
             for second in params:
                 value = ret.get(first, {}).pop(second, None)
                 if value:
@@ -726,7 +663,7 @@ class Config(object):
                               'SERVICE_TAGS', 'NAMESPACE', 'CONTEXT', 'USE_ENDPOINTS', 'SCOPE_LABEL', 'ROLE_LABEL',
                               'POD_IP', 'PORTS', 'LABELS', 'BYPASS_API_SERVICE', 'RETRIABLE_HTTP_CODES', 'KEY_PASSWORD',
                               'USE_SSL', 'SET_ACLS', 'GROUP', 'DATABASE', 'LEADER_LABEL_VALUE', 'FOLLOWER_LABEL_VALUE',
-                              'STANDBY_LEADER_LABEL_VALUE', 'TMP_ROLE_LABEL') and name:
+                              'STANDBY_LEADER_LABEL_VALUE', 'TMP_ROLE_LABEL', 'AUTH_DATA', 'BOOTSTRAP_LABELS') and name:
                     value = os.environ.pop(param)
                     if name == 'CITUS':
                         if suffix == 'GROUP':
@@ -737,7 +674,7 @@ class Config(object):
                         value = value and parse_int(value)
                     elif suffix in ('HOSTS', 'PORTS', 'CHECKS', 'SERVICE_TAGS', 'RETRIABLE_HTTP_CODES'):
                         value = value and _parse_list(value)
-                    elif suffix in ('LABELS', 'SET_ACLS'):
+                    elif suffix in ('LABELS', 'SET_ACLS', 'AUTH_DATA', 'BOOTSTRAP_LABELS'):
                         value = _parse_dict(value)
                     elif suffix in ('USE_PROXIES', 'REGISTER_SERVICE', 'USE_ENDPOINTS', 'BYPASS_API_SERVICE', 'VERIFY'):
                         value = parse_bool(value)
@@ -747,23 +684,6 @@ class Config(object):
             if dcs in ret:
                 ret[dcs].update(_get_auth(dcs))
 
-        users = {}
-        for param in list(os.environ.keys()):
-            if param.startswith(PATRONI_ENV_PREFIX):
-                name, suffix = (param[len(PATRONI_ENV_PREFIX):].rsplit('_', 1) + [''])[:2]
-                # PATRONI_<username>_PASSWORD=<password>, PATRONI_<username>_OPTIONS=<option1,option2,...>
-                # CREATE USER "<username>" WITH <OPTIONS> PASSWORD '<password>'
-                if name and suffix == 'PASSWORD':
-                    password = os.environ.pop(param)
-                    if password:
-                        users[name] = {'password': password}
-                        options = os.environ.pop(param[:-9] + '_OPTIONS', None)  # replace "_PASSWORD" with "_OPTIONS"
-                        options = options and _parse_list(options)
-                        if options:
-                            users[name]['options'] = options
-        if users:
-            ret['bootstrap']['users'] = users
-
         return ret
 
     def _build_effective_configuration(self, dynamic_configuration: Dict[str, Any],
@@ -781,8 +701,8 @@ class Config(object):
         config = self._safe_copy_dynamic_configuration(dynamic_configuration)
         for name, value in local_configuration.items():
             if name == 'citus':  # remove invalid citus configuration
-                if isinstance(value, dict) and isinstance(value.get('group'), int)\
-                        and isinstance(value.get('database'), str):
+                if isinstance(value, dict) and isinstance(cast(Dict[str, Any], value).get('group'), int) \
+                        and isinstance(cast(Dict[str, Any], value).get('database'), str):
                     config[name] = value
             elif name == 'postgresql':
                 for name, value in (value or {}).items():
@@ -827,7 +747,7 @@ class Config(object):
         if 'citus' in config:
             bootstrap = config.setdefault('bootstrap', {})
             dcs = bootstrap.setdefault('dcs', {})
-            dcs.setdefault('synchronous_mode', True)
+            dcs.setdefault('synchronous_mode', 'quorum')
 
         updated_fields = (
             'name',
@@ -884,14 +804,31 @@ class Config(object):
         """
         return deepcopy(self.__effective_configuration)
 
-    def get_global_config(self, cluster: Optional[Cluster]) -> GlobalConfig:
-        """Instantiate :class:`GlobalConfig` based on input.
+    def _validate_contradictory_tags(self) -> None:
+        """Check boolean/priority tags' config and warn user if it's contradictory.
 
-        Use the configuration from provided *cluster* (the most up-to-date) or from the
-        local cache if *cluster.config* is not initialized or doesn't have a valid config.
-
-        :param cluster: the currently known cluster state from DCS.
-
-        :returns: :class:`GlobalConfig` object.
+        .. note::
+          To preserve sanity (and backwards compatibility) the ``nofailover``/``nosync`` tag will still exist.
+          A contradictory configuration is one where ``nofailover``/``nosync`` is ``True`` but
+          ``failover_priority > 0``/``sync_priority > 0``, or where ``nofailover``/``nosync`` is ``False``,
+          but ``failover_priority <= 0``/``sync_priority <= 0``. Essentially, ``nofailover``/``nosync`` and
+          ``failover_priority``/``sync_priority`` are communicating different things.
+          This checks for this edge case (which is a misconfiguration on the part of the user) and warns them.
+          The behaviour is as if ``failover_priority``/``sync_priority`` were not provided
+          (i.e ``nofailover``/``nosync`` is the bedrock source of truth).
         """
-        return get_global_config(cluster, self._dynamic_configuration)
+        tags = self.get('tags', {})
+
+        def validate_tag(bool_name: str, priority_name: str) -> None:
+            if bool_name not in tags:
+                return
+            bool_tag = tags.get(bool_name)
+            priority_tag = parse_int(tags.get(priority_name))
+            if priority_tag is not None \
+                    and (bool(bool_tag) is True and priority_tag > 0
+                         or bool(bool_tag) is False and priority_tag <= 0):
+                logger.warning('Conflicting configuration between %s: %s and %s: %s. Defaulting to %s: %s',
+                               bool_name, bool_tag, priority_name, priority_tag, bool_name, bool_tag)
+
+        validate_tag('nofailover', 'failover_priority')
+        validate_tag('nosync', 'sync_priority')

patroni/config_generator.py

@@ -2,26 +2,29 @@
 import abc
 import logging
 import os
-import psutil
 import socket
 import sys
+
+from contextlib import contextmanager
+from getpass import getpass, getuser
+from typing import Any, Dict, Iterator, List, Optional, TextIO, Tuple, TYPE_CHECKING, Union
+
+import psutil
 import yaml
 
-from getpass import getuser, getpass
-from contextlib import contextmanager
-from typing import Any, Dict, Iterator, List, Optional, Tuple, TYPE_CHECKING, Union
 if TYPE_CHECKING:  # pragma: no cover
     from psycopg import Cursor
     from psycopg2 import cursor
 
 from . import psycopg
+from .collections import EMPTY_DICT
 from .config import Config
 from .exceptions import PatroniException
+from .log import PatroniLogger
 from .postgresql.config import ConfigHandler, parse_dsn
 from .postgresql.misc import postgres_major_version_to_int
 from .utils import get_major_version, parse_bool, patch_config, read_stripped
 
-
 # Mapping between the libpq connection parameters and the environment variables.
 # This dict should be kept in sync with `patroni.utils._AUTH_ALLOWED_PARAMETERS`
 # (we use "username" in the Patroni config for some reason, other parameter names are the same).
@@ -36,9 +39,10 @@ _AUTH_ALLOWED_PARAMETERS_MAPPING = {
     'sslcrl': 'PGSSLCRL',
     'sslcrldir': 'PGSSLCRLDIR',
     'gssencmode': 'PGGSSENCMODE',
-    'channel_binding': 'PGCHANNELBINDING'
+    'channel_binding': 'PGCHANNELBINDING',
+    'sslnegotiation': 'PGSSLNEGOTIATION'
 }
-_NO_VALUE_MSG = '#FIXME'
+NO_VALUE_MSG = '#FIXME'
 
 
 def get_address() -> Tuple[str, str]:
@@ -50,16 +54,18 @@ def get_address() -> Tuple[str, str]:
     :returns: tuple consisting of the hostname returned by :func:`~socket.gethostname`
         and the first element in the sorted list of the addresses returned by :func:`~socket.getaddrinfo`.
         Sorting guarantees it will prefer IPv4.
-        If an exception occured, hostname and ip values are equal to :data:`~patroni.config_generator._NO_VALUE_MSG`.
+        If an exception occurred, hostname and ip values are equal to :data:`~patroni.config_generator.NO_VALUE_MSG`.
     """
     hostname = None
     try:
         hostname = socket.gethostname()
-        return hostname, sorted(socket.getaddrinfo(hostname, 0, socket.AF_UNSPEC, socket.SOCK_STREAM, 0),
-                                key=lambda x: x[0])[0][4][0]
+        # Filter out unexpected results when python is compiled with --disable-ipv6 and running on IPv6 system.
+        addrs = [(a[0], a[4][0]) for a in socket.getaddrinfo(hostname, 0, socket.AF_UNSPEC, socket.SOCK_STREAM, 0)
+                 if isinstance(a[4][0], str)]
+        return hostname, sorted(addrs, key=lambda x: x[0])[0][1]
     except Exception as err:
         logging.warning('Failed to obtain address: %r', err)
-        return _NO_VALUE_MSG, _NO_VALUE_MSG
+        return NO_VALUE_MSG, NO_VALUE_MSG
 
 
 class AbstractConfigGenerator(abc.ABC):
@@ -70,8 +76,6 @@ class AbstractConfigGenerator(abc.ABC):
     :ivar config: dictionary used for the generated configuration storage.
     """
 
-    _HOSTNAME, _IP = get_address()
-
     def __init__(self, output_file: Optional[str]) -> None:
         """Set up the output file (if passed), helper vars and the minimal config structure.
 
@@ -88,30 +92,47 @@ class AbstractConfigGenerator(abc.ABC):
         """Generate a template config for further extension (e.g. in the inherited classes).
 
         :returns: dictionary with the values gathered from Patroni env, hopefully defined hostname and ip address
-                  (otherwise set to :data:`~patroni.config_generator._NO_VALUE_MSG`), and some sane defaults.
+                  (otherwise set to :data:`~patroni.config_generator.NO_VALUE_MSG`), and some sane defaults.
         """
+        _HOSTNAME, _IP = get_address()
+
         template_config: Dict[str, Any] = {
-            'scope': _NO_VALUE_MSG,
-            'name': cls._HOSTNAME,
+            'scope': NO_VALUE_MSG,
+            'name': _HOSTNAME,
+            'restapi': {
+                'connect_address': _IP + ':8008',
+                'listen': _IP + ':8008'
+            },
+            'log': {
+                'type': PatroniLogger.DEFAULT_TYPE,
+                'level': PatroniLogger.DEFAULT_LEVEL,
+                'traceback_level': PatroniLogger.DEFAULT_TRACEBACK_LEVEL,
+                'format': PatroniLogger.DEFAULT_FORMAT,
+                'max_queue_size': PatroniLogger.DEFAULT_MAX_QUEUE_SIZE
+            },
             'postgresql': {
-                'data_dir': _NO_VALUE_MSG,
-                'connect_address': _NO_VALUE_MSG + ':5432',
-                'listen': _NO_VALUE_MSG + ':5432',
+                'data_dir': NO_VALUE_MSG,
+                'connect_address': _IP + ':5432',
+                'listen': _IP + ':5432',
                 'bin_dir': '',
                 'authentication': {
                     'superuser': {
                         'username': 'postgres',
-                        'password': _NO_VALUE_MSG
+                        'password': NO_VALUE_MSG
                     },
                     'replication': {
                         'username': 'replicator',
-                        'password': _NO_VALUE_MSG
+                        'password': NO_VALUE_MSG
                     }
                 }
             },
-            'restapi': {
-                'connect_address': cls._IP + ':8008',
-                'listen': cls._IP + ':8008'
+            'tags': {
+                'failover_priority': 1,
+                'sync_priority': 1,
+                'noloadbalance': False,
+                'clonefrom': True,
+                'nosync': False,
+                'nostream': False,
             }
         }
 
@@ -130,6 +151,72 @@ class AbstractConfigGenerator(abc.ABC):
     def generate(self) -> None:
         """Generate config and store in :attr:`~AbstractConfigGenerator.config`."""
 
+    @staticmethod
+    def _format_block(block: Any, line_prefix: str = '') -> str:
+        """Format a single YAML block.
+
+        .. note::
+            Optionally the formatted block could be indented with the *line_prefix*
+
+        :param block: the object that should be formatted to YAML.
+        :param line_prefix: is used for indentation.
+
+        :returns: a formatted and indented *block*.
+        """
+        return line_prefix + yaml.safe_dump(block, default_flow_style=False, line_break='\n',
+                                            allow_unicode=True, indent=2).strip().replace('\n', '\n' + line_prefix)
+
+    def _format_config_section(self, section_name: str) -> Iterator[str]:
+        """Format and yield as single section of the current :attr:`~AbstractConfigGenerator.config`.
+
+        .. note::
+            If the section is a :class:`dict` object we put an empty line before it.
+
+        :param section_name: a section name in the :attr:`~AbstractConfigGenerator.config`.
+
+        :yields: a formatted section in case if it exists in the :attr:`~AbstractConfigGenerator.config`.
+        """
+        if section_name in self.config:
+            if isinstance(self.config[section_name], dict):
+                yield ''
+            yield self._format_block({section_name: self.config[section_name]})
+
+    def _format_config(self) -> Iterator[str]:
+        """Format current :attr:`~AbstractConfigGenerator.config` and enrich it with some comments.
+
+        :yields: formatted lines or blocks that represent a text output of the YAML document.
+        """
+        for name in ('scope', 'namespace', 'name', 'log', 'restapi', 'ctl', 'citus',
+                     'consul', 'etcd', 'etcd3', 'exhibitor', 'kubernetes', 'raft', 'zookeeper'):
+            yield from self._format_config_section(name)
+
+        if 'bootstrap' in self.config:
+            yield '\n# The bootstrap configuration. Works only when the cluster is not yet initialized.'
+            yield '# If the cluster is already initialized, all changes in the `bootstrap` section are ignored!'
+            yield 'bootstrap:'
+            if 'dcs' in self.config['bootstrap']:
+                yield '  # This section will be written into <dcs>:/<namespace>/<scope>/config after initializing'
+                yield '  # new cluster and all other cluster members will use it as a `global configuration`.'
+                yield '  # WARNING! If you want to change any of the parameters that were set up'
+                yield '  # via `bootstrap.dcs` section, please use `patronictl edit-config`!'
+                yield '  dcs:'
+                for name in ('loop_wait', 'retry_timeout', 'ttl'):
+                    if name in self.config['bootstrap']['dcs']:
+                        yield self._format_block({name: self.config['bootstrap']['dcs'].pop(name)}, '    ')
+
+                for name, value in self.config['bootstrap']['dcs'].items():
+                    yield self._format_block({name: value}, '    ')
+
+        for name in ('postgresql', 'watchdog', 'tags'):
+            yield from self._format_config_section(name)
+
+    def _write_config_to_fd(self, fd: TextIO) -> None:
+        """Format and write current :attr:`~AbstractConfigGenerator.config` to provided file descriptor.
+
+        :param fd: where to write the config file. Could be ``sys.stdout`` or the real file.
+        """
+        fd.write('\n'.join(self._format_config()))
+
     def write_config(self) -> None:
         """Write current :attr:`~AbstractConfigGenerator.config` to the output file if provided, to stdout otherwise."""
         if self.output_file:
@@ -137,15 +224,15 @@ class AbstractConfigGenerator(abc.ABC):
             if dir_path and not os.path.isdir(dir_path):
                 os.makedirs(dir_path)
             with open(self.output_file, 'w', encoding='UTF-8') as output_file:
-                yaml.safe_dump(self.config, output_file, default_flow_style=False, allow_unicode=True)
+                self._write_config_to_fd(output_file)
         else:
-            yaml.safe_dump(self.config, sys.stdout, default_flow_style=False, allow_unicode=True)
+            self._write_config_to_fd(sys.stdout)
 
 
 class SampleConfigGenerator(AbstractConfigGenerator):
     """Object representing the generated sample Patroni config.
 
-    Sane defults are used based on the gathered PG version.
+    Sane defaults are used based on the gathered PG version.
     """
 
     @property
@@ -163,7 +250,8 @@ class SampleConfigGenerator(AbstractConfigGenerator):
                   See :func:`~patroni.postgresql.misc.postgres_major_version_to_int` and
                   :func:`~patroni.utils.get_major_version`.
         """
-        postgres_bin = ((self.config.get('postgresql') or {}).get('bin_name') or {}).get('postgres', 'postgres')
+        postgres_bin = ((self.config.get('postgresql')
+                         or EMPTY_DICT).get('bin_name') or EMPTY_DICT).get('postgres', 'postgres')
         return postgres_major_version_to_int(get_major_version(self.config['postgresql'].get('bin_dir'), postgres_bin))
 
     def generate(self) -> None:
@@ -182,10 +270,14 @@ class SampleConfigGenerator(AbstractConfigGenerator):
         self.config['bootstrap']['dcs']['postgresql']['parameters'][wal_keep_param] = \
             ConfigHandler.CMDLINE_OPTIONS[wal_keep_param][0]
 
-        self.config['bootstrap']['dcs']['postgresql']['use_pg_rewind'] = True
+        wal_level = 'hot_standby' if self.pg_major < 90600 else 'replica'
+        self.config['bootstrap']['dcs']['postgresql']['parameters']['wal_level'] = wal_level
+
+        self.config['bootstrap']['dcs']['postgresql']['use_pg_rewind'] = \
+            parse_bool(self.config['bootstrap']['dcs']['postgresql']['parameters']['wal_log_hints']) is True
         if self.pg_major >= 110000:
             self.config['postgresql']['authentication'].setdefault(
-                'rewind', {'username': 'rewind_user'}).setdefault('password', _NO_VALUE_MSG)
+                'rewind', {'username': 'rewind_user'}).setdefault('password', NO_VALUE_MSG)
 
 
 class RunningClusterConfigGenerator(AbstractConfigGenerator):
@@ -225,7 +317,7 @@ class RunningClusterConfigGenerator(AbstractConfigGenerator):
 
     @property
     def _required_pg_params(self) -> List[str]:
-        """PG configuration prameters that have to be always present in the generated config.
+        """PG configuration parameters that have to be always present in the generated config.
 
         :returns: list of the parameter names.
         """
@@ -241,7 +333,7 @@ class RunningClusterConfigGenerator(AbstractConfigGenerator):
             :exc:`~patroni.exceptions.PatroniException`: if:
 
                 * pid could not be obtained from the ``postmaster.pid`` file; or
-                * :exc:`OSError` occured during ``postmaster.pid`` file handling; or
+                * :exc:`OSError` occurred during ``postmaster.pid`` file handling; or
                 * the obtained postmaster pid doesn't exist.
         """
         postmaster_pid = None
@@ -264,7 +356,7 @@ class RunningClusterConfigGenerator(AbstractConfigGenerator):
         """Get cursor for the PG connection established based on the stored information.
 
         :raises:
-            :exc:`~patroni.exceptions.PatroniException`: if :exc:`psycopg.Error` occured.
+            :exc:`~patroni.exceptions.PatroniException`: if :exc:`psycopg.Error` occurred.
         """
         try:
             conn = psycopg.connect(dsn=self.dsn,
@@ -287,7 +379,7 @@ class RunningClusterConfigGenerator(AbstractConfigGenerator):
 
         :param cur: connection cursor to use.
         """
-        cur.execute("SELECT name, current_setting(name) FROM pg_settings "
+        cur.execute("SELECT name, pg_catalog.current_setting(name) FROM pg_catalog.pg_settings "
                     "WHERE context <> 'internal' "
                     "AND source IN ('configuration file', 'command line', 'environment variable') "
                     "AND category <> 'Write-Ahead Log / Recovery Target' "
@@ -313,8 +405,9 @@ class RunningClusterConfigGenerator(AbstractConfigGenerator):
             else:
                 self.config['bootstrap']['dcs']['postgresql']['parameters'][param] = value
 
+        connect_ip = self.config['postgresql']['connect_address'].rsplit(':')[0]
         connect_port = self.parsed_dsn.get('port', os.getenv('PGPORT', helper_dict['port']))
-        self.config['postgresql']['connect_address'] = f'{self._IP}:{connect_port}'
+        self.config['postgresql']['connect_address'] = f'{connect_ip}:{connect_port}'
         self.config['postgresql']['listen'] = f'{helper_dict["listen_addresses"]}:{helper_dict["port"]}'
 
     def _set_su_params(self) -> None:
@@ -327,15 +420,17 @@ class RunningClusterConfigGenerator(AbstractConfigGenerator):
             val = self.parsed_dsn.get(conn_param, os.getenv(env_var))
             if val:
                 su_params[conn_param] = val
-        patroni_env_su_username = ((self.config.get('authentication') or {}).get('superuser') or {}).get('username')
-        patroni_env_su_pwd = ((self.config.get('authentication') or {}).get('superuser') or {}).get('password')
+        patroni_env_su_username = ((self.config.get('authentication')
+                                    or EMPTY_DICT).get('superuser') or EMPTY_DICT).get('username')
+        patroni_env_su_pwd = ((self.config.get('authentication')
+                               or EMPTY_DICT).get('superuser') or EMPTY_DICT).get('password')
         # because we use "username" in the config for some reason
         su_params['username'] = su_params.pop('user', patroni_env_su_username) or getuser()
         su_params['password'] = su_params.get('password', patroni_env_su_pwd) or \
             getpass('Please enter the user password:')
         self.config['postgresql']['authentication'] = {
             'superuser': su_params,
-            'replication': {'username': _NO_VALUE_MSG, 'password': _NO_VALUE_MSG}
+            'replication': {'username': NO_VALUE_MSG, 'password': NO_VALUE_MSG}
         }
 
     def _set_conf_files(self) -> None:
@@ -347,7 +442,7 @@ class RunningClusterConfigGenerator(AbstractConfigGenerator):
             are located outside of ``PGDATA`` and Patroni doesn't have write permissions for them.
 
         :raises:
-            :exc:`~patroni.exceptions.PatroniException`: if :exc:`OSError` occured during the conf files handling.
+            :exc:`~patroni.exceptions.PatroniException`: if :exc:`OSError` occurred during the conf files handling.
         """
         default_hba_path = os.path.join(self.config['postgresql']['data_dir'], 'pg_hba.conf')
         if self.config['postgresql']['parameters']['hba_file'] == default_hba_path:
@@ -387,7 +482,7 @@ class RunningClusterConfigGenerator(AbstractConfigGenerator):
         with self._get_connection_cursor() as cur:
             self.pg_major = getattr(cur.connection, 'server_version', 0)
 
-            if not parse_bool(cur.connection.info.parameter_status('is_superuser')):
+            if not parse_bool(getattr(cur.connection, 'get_parameter_status')('is_superuser')):
                 raise PatroniException('The provided user does not have superuser privilege')
 
             self._set_pg_params(cur)
@@ -411,41 +506,6 @@ class RunningClusterConfigGenerator(AbstractConfigGenerator):
 def generate_config(output_file: str, sample: bool, dsn: Optional[str]) -> None:
     """Generate Patroni configuration file.
 
-    Gather all the available non-internal GUC values having configuration file, postmaster command line or environment
-    variable as a source and store them in the appropriate part of Patroni configuration (``postgresql.parameters`` or
-    ``bootstrap.dcs.postgresql.parameters``). Either the provided DSN (takes precedence) or PG ENV vars will be used
-    for the connection. If password is not provided, it should be entered via prompt.
-
-    The created configuration contains:
-    * ``scope``: ``cluster_name`` GUC value or ``PATRONI_SCOPE ENV`` variable value if available.
-    * ``name``: ``PATRONI_NAME`` ENV variable value if set, otherwise hostname.
-
-    * ``bootstrap.dcs``: section with all the parameters (incl. the majority of PG GUCs) set to their default values
-      defined by Patroni and adjusted by the source instances's configuration values.
-
-    * ``postgresql.parameters``: the source instance's ``archive_command``, ``restore_command``,
-      ``archive_cleanup_command``, ``recovery_end_command``, ``ssl_passphrase_command``, ``hba_file``, ``ident_file``,
-      ``config_file`` GUC values.
-
-    * ``postgresql.bin_dir``: path to Postgres binaries gathered from the running instance or, if not available,
-      the value of ``PATRONI_POSTGRESQL_BIN_DIR`` ENV variable. Otherwise, an empty string.
-
-    * ``postgresql.datadir``: the value gathered from the corresponding PG GUC.
-    * ``postgresql.listen``: source instance's ``listen_addresses`` and port GUC values.
-    * ``postgresql.connect_address``: if possible, generated from the connection params.
-    * ``postgresql.authentication``:
-
-        * superuser and replication users defined (if possible, usernames are set from the respective Patroni ENV vars,
-          otherwise the default ``postgres`` and ``replicator`` values are used).
-          If not a sample config, either DSN or PG ENV vars are used to define superuser authentication parameters.
-
-        * rewind user is defined only for sample config, if PG version can be defined and PG version is >=11
-          (if possible, username is set from the respective Patroni ENV var).
-
-    * ``bootstrap.dcs.postgresql.use_pg_rewind`` set to ``True`` for a sample config only.
-    * ``postgresql.pg_hba`` defaults or the lines gathered from the source instance's ``hba_file``.
-    * ``postgresql.pg_ident`` the lines gathered from the source instance's ``ident_file``.
-
     :param output_file: Full path to the configuration file to be used. If not provided, result is sent to ``stdout``.
     :param sample: Optional flag. If set, no source instance will be used - generate config with some sane defaults.
     :param dsn: Optional DSN string for the local instance to get GUC values from.

patroni/daemon.py

@@ -7,6 +7,7 @@ from __future__ import print_function
 
 import abc
 import argparse
+import logging
 import os
 import signal
 import sys
@@ -17,6 +18,8 @@ from typing import Any, Optional, Type, TYPE_CHECKING
 if TYPE_CHECKING:  # pragma: no cover
     from .config import Config
 
+logger = logging.getLogger(__name__)
+
 
 def get_base_arg_parser() -> argparse.ArgumentParser:
     """Create a basic argument parser with the arguments used for both patroni and raft controller daemon.
@@ -132,8 +135,13 @@ class AbstractPatroniDaemon(abc.ABC):
         """Run the daemon process.
 
         Start the logger thread and keep running execution cycles until a SIGTERM is eventually received. Also reload
-        configuration uppon receiving SIGHUP.
+        configuration upon receiving SIGHUP.
         """
+        try:  # pragma: no cover
+            from systemd import daemon  # pyright: ignore
+            daemon.notify("READY=1")  # pyright: ignore
+        except ImportError:  # pragma: no cover
+            logger.info("Systemd integration is not supported")
         self.logger.start()
         while not self.received_sigterm:
             if self._received_sighup:

patroni/dcs/consul.py

@@ -1,4 +1,5 @@
 from __future__ import absolute_import
+
 import json
 import logging
 import os
@@ -6,19 +7,24 @@ import re
 import socket
 import ssl
 import time
-import urllib3
 
 from collections import defaultdict
-from consul import ConsulException, NotFound, base
 from http.client import HTTPException
+from typing import Any, Callable, Dict, List, Mapping, NamedTuple, Optional, Tuple, TYPE_CHECKING, Union
+from urllib.parse import quote, urlencode, urlparse
+
+import urllib3
+
+from consul import base, Check, ConsulException, NotFound
 from urllib3.exceptions import HTTPError
-from urllib.parse import urlencode, urlparse, quote
-from typing import Any, Callable, Dict, List, Mapping, NamedTuple, Optional, Union, Tuple, TYPE_CHECKING
 
-from . import AbstractDCS, Cluster, ClusterConfig, Failover, Leader, Member, SyncState, \
-    TimelineHistory, ReturnFalseException, catch_return_false_exception, citus_group_re
 from ..exceptions import DCSError
+from ..postgresql.misc import PostgresqlRole, PostgresqlState
+from ..postgresql.mpp import AbstractMPP
 from ..utils import deep_compare, parse_bool, Retry, RetryFailedError, split_host_port, uri, USER_AGENT
+from . import AbstractDCS, catch_return_false_exception, Cluster, ClusterConfig, \
+    Failover, Leader, Member, ReturnFalseException, Status, SyncState, TimelineHistory
+
 if TYPE_CHECKING:  # pragma: no cover
     from ..config import Config
 
@@ -141,6 +147,36 @@ class HTTPClient(object):
 class ConsulClient(base.Consul):
 
     def __init__(self, *args: Any, **kwargs: Any) -> None:
+        """
+        Consul client with Patroni customisations.
+
+        .. note::
+
+            Parameters, *token*, *cert* and *ca_cert* are not passed to the parent class :class:`consul.base.Consul`.
+
+        Original class documentation,
+
+            *token* is an optional ``ACL token``. If supplied it will be used by
+            default for all requests made with this client session. It's still
+            possible to override this token by passing a token explicitly for a
+            request.
+
+            *consistency* sets the consistency mode to use by default for all reads
+            that support the consistency option. It's still possible to override
+            this by passing explicitly for a given request. *consistency* can be
+            either 'default', 'consistent' or 'stale'.
+
+            *dc* is the datacenter that this agent will communicate with.
+            By default, the datacenter of the host is used.
+
+            *verify* is whether to verify the SSL certificate for HTTPS requests
+
+            *cert* client side certificates for HTTPS requests
+
+        :param args: positional arguments to pass to :class:`consul.base.Consul`
+        :param kwargs: keyword arguments, with *cert*, *ca_cert* and *token* removed, passed to
+                       :class:`consul.base.Consul`
+        """
         self._cert = kwargs.pop('cert', None)
         self._ca_cert = kwargs.pop('ca_cert', None)
         self.token = kwargs.get('token')
@@ -157,7 +193,7 @@ class ConsulClient(base.Consul):
         return HTTPClient(**kwargs)
 
     def connect(self, *args: Any, **kwargs: Any) -> HTTPClient:
-        return self.http_connect(*args, **kwargs)
+        return self.http_connect(*args, **kwargs)  # pragma: no cover
 
     def reload_config(self, config: Dict[str, Any]) -> None:
         self.http.token = self.token = config.get('token')
@@ -202,8 +238,8 @@ def service_name_from_scope_name(scope_name: str) -> str:
 
 class Consul(AbstractDCS):
 
-    def __init__(self, config: Dict[str, Any]) -> None:
-        super(Consul, self).__init__(config)
+    def __init__(self, config: Dict[str, Any], mpp: AbstractMPP) -> None:
+        super(Consul, self).__init__(config, mpp)
         self._base_path = self._base_path[1:]
         self._scope = config['scope']
         self._session = None
@@ -353,23 +389,8 @@ class Consul(AbstractDCS):
         history = history and TimelineHistory.from_node(history['ModifyIndex'], history['Value'])
 
         # get last known leader lsn and slots
-        status = nodes.get(self._STATUS)
-        if status:
-            try:
-                status = json.loads(status['Value'])
-                last_lsn = status.get(self._OPTIME)
-                slots = status.get('slots')
-            except Exception:
-                slots = last_lsn = None
-        else:
-            last_lsn = nodes.get(self._LEADER_OPTIME)
-            last_lsn = last_lsn and last_lsn['Value']
-            slots = None
-
-        try:
-            last_lsn = int(last_lsn or '')
-        except Exception:
-            last_lsn = 0
+        status = nodes.get(self._STATUS) or nodes.get(self._LEADER_OPTIME)
+        status = Status.from_node(status and status['Value'])
 
         # get list of members
         members = [self.member(n) for k, n in nodes.items() if k.startswith(self._MEMBERS) and k.count('/') == 1]
@@ -398,29 +419,42 @@ class Consul(AbstractDCS):
         except Exception:
             failsafe = None
 
-        return Cluster(initialize, config, leader, last_lsn, members, failover, sync, history, slots, failsafe)
+        return Cluster(initialize, config, leader, status, members, failover, sync, history, failsafe)
 
     @property
     def _consistency(self) -> str:
         return 'consistent' if self._ctl else self._client.consistency
 
-    def _cluster_loader(self, path: str) -> Cluster:
+    def _postgresql_cluster_loader(self, path: str) -> Cluster:
+        """Load and build the :class:`Cluster` object from DCS, which represents a single PostgreSQL cluster.
+
+        :param path: the path in DCS where to load :class:`Cluster` from.
+
+        :returns: :class:`Cluster` instance.
+        """
         _, results = self.retry(self._client.kv.get, path, recurse=True, consistency=self._consistency)
         if results is None:
-            raise NotFound
-        nodes = {}
+            return Cluster.empty()
+        nodes: Dict[str, Dict[str, Any]] = {}
         for node in results:
             node['Value'] = (node['Value'] or b'').decode('utf-8')
             nodes[node['Key'][len(path):]] = node
 
         return self._cluster_from_nodes(nodes)
 
-    def _citus_cluster_loader(self, path: str) -> Dict[int, Cluster]:
+    def _mpp_cluster_loader(self, path: str) -> Dict[int, Cluster]:
+        """Load and build all PostgreSQL clusters from a single MPP cluster.
+
+        :param path: the path in DCS where to load Cluster(s) from.
+
+        :returns: all MPP groups as :class:`dict`, with group IDs as keys and :class:`Cluster` objects as values.
+        """
+        results: Optional[List[Dict[str, Any]]]
         _, results = self.retry(self._client.kv.get, path, recurse=True, consistency=self._consistency)
-        clusters: Dict[int, Dict[str, Cluster]] = defaultdict(dict)
+        clusters: Dict[int, Dict[str, Dict[str, Any]]] = defaultdict(dict)
         for node in results or []:
             key = node['Key'][len(path):].split('/', 1)
-            if len(key) == 2 and citus_group_re.match(key[0]):
+            if len(key) == 2 and self._mpp.group_re.match(key[0]):
                 node['Value'] = (node['Value'] or b'').decode('utf-8')
                 clusters[int(key[0])][key[1]] = node
         return {group: self._cluster_from_nodes(nodes) for group, nodes in clusters.items()}
@@ -430,8 +464,6 @@ class Consul(AbstractDCS):
     ) -> Union[Cluster, Dict[int, Cluster]]:
         try:
             return loader(path)
-        except NotFound:
-            return Cluster.empty()
         except Exception:
             logger.exception('get_cluster')
             raise ConsulError('Consul is not responding properly')
@@ -495,16 +527,14 @@ class Consul(AbstractDCS):
         api_parts = api_parts._replace(path='/{0}'.format(role))
         conn_url: str = data['conn_url']
         conn_parts = urlparse(conn_url)
-        check = base.Check.http(api_parts.geturl(), self._service_check_interval,
-                                deregister='{0}s'.format(self._client.http.ttl * 10))
+        check = Check.http(api_parts.geturl(), self._service_check_interval,
+                           deregister='{0}s'.format(self._client.http.ttl * 10))
         if self._service_check_tls_server_name is not None:
             check['TLSServerName'] = self._service_check_tls_server_name
         tags = self._service_tags[:]
         tags.append(role)
-        if role == 'master':
-            tags.append('primary')
-        elif role == 'primary':
-            tags.append('master')
+        if data['role'] == PostgresqlRole.PRIMARY:
+            tags.append(PostgresqlRole.MASTER)
         self._previous_loop_service_tags = self._service_tags
         self._previous_loop_token = self._client.token
 
@@ -517,13 +547,13 @@ class Consul(AbstractDCS):
             'enable_tag_override': True,
         }
 
-        if state == 'stopped' or (not self._register_service and self._previous_loop_register_service):
+        if state == PostgresqlState.STOPPED or (not self._register_service and self._previous_loop_register_service):
             self._previous_loop_register_service = self._register_service
             return self.deregister_service(params['service_id'])
 
         self._previous_loop_register_service = self._register_service
-        if role in ['master', 'primary', 'replica', 'standby-leader']:
-            if state != 'running':
+        if data['role'] in [PostgresqlRole.PRIMARY, PostgresqlRole.REPLICA, PostgresqlRole.STANDBY_LEADER]:
+            if state != PostgresqlState.RUNNING:
                 return
             return self.register_service(service_name, **params)
 
@@ -551,14 +581,17 @@ class Consul(AbstractDCS):
         try:
             return retry(self._client.kv.put, self.leader_path, self._name, acquire=self._session)
         except InvalidSession:
-            logger.error('Our session disappeared from Consul. Will try to get a new one and retry attempt')
             self._session = None
-            retry.ensure_deadline(0)
+
+            if not retry.ensure_deadline(0):
+                logger.error('Our session disappeared from Consul. Deadline exceeded, giving up')
+                return False
+
+            logger.error('Our session disappeared from Consul. Will try to get a new one and retry attempt')
 
             retry(self._do_refresh_session)
 
             retry.ensure_deadline(1, ConsulError('_do_attempt_to_acquire_leader timeout'))
-
             return retry(self._client.kv.put, self.leader_path, self._name, acquire=self._session)
 
     @catch_return_false_exception
@@ -650,10 +683,10 @@ class Consul(AbstractDCS):
     def set_sync_state_value(self, value: str, version: Optional[int] = None) -> Union[int, bool]:
         retry = self._retry.copy()
         ret = retry(self._client.kv.put, self.sync_path, value, cas=version)
-        if ret:  # We have no other choise, only read after write :(
+        if ret:  # We have no other choice, only read after write :(
             if not retry.ensure_deadline(0.5):
                 return False
-            _, ret = self.retry(self._client.kv.get, self.sync_path)
+            _, ret = self.retry(self._client.kv.get, self.sync_path, consistency='consistent')
             if ret and (ret.get('Value') or b'').decode('utf-8') == value:
                 return ret['ModifyIndex']
         return False

patroni/dcs/etcd.py

@@ -1,31 +1,36 @@
 from __future__ import absolute_import
+
 import abc
-import etcd
 import json
 import logging
 import os
-import urllib3.util.connection
 import random
 import socket
 import time
 
 from collections import defaultdict
 from copy import deepcopy
-from dns.exception import DNSException
-from dns import resolver
 from http.client import HTTPException
 from queue import Queue
 from threading import Thread
-from typing import Any, Callable, Collection, Dict, List, Optional, Union, Tuple, Type, TYPE_CHECKING
+from typing import Any, Callable, Collection, Dict, List, Optional, Tuple, Type, TYPE_CHECKING, Union
 from urllib.parse import urlparse
-from urllib3 import Timeout
-from urllib3.exceptions import HTTPError, ReadTimeoutError, ProtocolError
 
-from . import AbstractDCS, Cluster, ClusterConfig, Failover, Leader, Member, SyncState, \
-    TimelineHistory, ReturnFalseException, catch_return_false_exception, citus_group_re
+import etcd
+import urllib3.util.connection
+
+from dns import resolver
+from dns.exception import DNSException
+from urllib3 import Timeout
+from urllib3.exceptions import HTTPError, ProtocolError, ReadTimeoutError
+
 from ..exceptions import DCSError
+from ..postgresql.mpp import AbstractMPP
 from ..request import get as requests_get
 from ..utils import Retry, RetryFailedError, split_host_port, uri, USER_AGENT
+from . import AbstractDCS, catch_return_false_exception, Cluster, ClusterConfig, \
+    Failover, Leader, Member, ReturnFalseException, Status, SyncState, TimelineHistory
+
 if TYPE_CHECKING:  # pragma: no cover
     from ..config import Config
 
@@ -36,11 +41,16 @@ class EtcdRaftInternal(etcd.EtcdException):
     """Raft Internal Error"""
 
 
+class StaleEtcdNode(Exception):
+    """Node is stale (raft term is older than previous known)."""
+
+
 class EtcdError(DCSError):
     pass
 
 
-_AddrInfo = Tuple[socket.AddressFamily, socket.SocketKind, int, str, Union[Tuple[str, int], Tuple[str, int, int, int]]]
+_AddrInfo = Tuple[socket.AddressFamily, socket.SocketKind, int, str,
+                  Union[Tuple[str, int], Tuple[str, int, int, int], Tuple[int, bytes]]]
 
 
 class DnsCachingResolver(Thread):
@@ -96,6 +106,8 @@ class AbstractEtcdClientWithFailover(abc.ABC, etcd.Client):
     ERROR_CLS: Type[Exception]
 
     def __init__(self, config: Dict[str, Any], dns_resolver: DnsCachingResolver, cache_ttl: int = 300) -> None:
+        self._cluster_id = None
+        self._raft_term = 0
         self._dns_resolver = dns_resolver
         self.set_machines_cache_ttl(cache_ttl)
         self._machines_cache_updated = 0
@@ -113,6 +125,32 @@ class AbstractEtcdClientWithFailover(abc.ABC, etcd.Client):
         self._read_options.add('retry')
         self._del_conditions.add('retry')
 
+    def _check_cluster_raft_term(self, cluster_id: Optional[str], value: Union[None, str, int]) -> None:
+        """Check that observed Raft Term in Etcd cluster is increasing.
+
+        If we observe that the new value is smaller than the previously known one, it could be an
+        indicator that we connected to a stale node and should switch to some other node.
+        However, we need to reset the memorized value when we notice that Cluster ID changed.
+        """
+        if not (cluster_id and value):
+            return
+
+        if self._cluster_id and self._cluster_id != cluster_id:
+            logger.warning('Etcd Cluster ID changed from %s to %s', self._cluster_id, cluster_id)
+            self._raft_term = 0
+        self._cluster_id = cluster_id
+
+        try:
+            raft_term = int(value)
+        except Exception:
+            return
+
+        if raft_term < self._raft_term:
+            logger.warning('Connected to Etcd node with term %d. Old known term %d. Switching to another node.',
+                           raft_term, self._raft_term)
+            raise StaleEtcdNode
+        self._raft_term = raft_term
+
     def _calculate_timeouts(self, etcd_nodes: int, timeout: Optional[float] = None) -> Tuple[int, float, int]:
         """Calculate a request timeout and number of retries per single etcd node.
         In case if the timeout per node is too small (less than one second) we will reduce the number of nodes.
@@ -221,7 +259,7 @@ class AbstractEtcdClientWithFailover(abc.ABC, etcd.Client):
     def _do_http_request(self, retry: Optional[Retry], machines_cache: List[str],
                          request_executor: Callable[..., urllib3.response.HTTPResponse],
                          method: str, path: str, fields: Optional[Dict[str, Any]] = None,
-                         **kwargs: Any) -> urllib3.response.HTTPResponse:
+                         **kwargs: Any) -> Any:
         is_watch_request = isinstance(fields, dict) and fields.get('wait') == 'true'
         if fields is not None:
             kwargs['fields'] = fields
@@ -235,8 +273,8 @@ class AbstractEtcdClientWithFailover(abc.ABC, etcd.Client):
                 if some_request_failed:
                     self.set_base_uri(base_uri)
                     self._refresh_machines_cache()
-                return response
-            except (HTTPError, HTTPException, socket.error, socket.timeout) as e:
+                return self._handle_server_response(response)
+            except (HTTPError, HTTPException, socket.error, socket.timeout, StaleEtcdNode) as e:
                 self.http.clear()
                 if not retry:
                     if len(machines_cache) == 1:
@@ -279,8 +317,7 @@ class AbstractEtcdClientWithFailover(abc.ABC, etcd.Client):
 
         while True:
             try:
-                response = self._do_http_request(retry, machines_cache, request_executor, method, path, **kwargs)
-                return self._handle_server_response(response)
+                return self._do_http_request(retry, machines_cache, request_executor, method, path, **kwargs)
             except etcd.EtcdWatchTimedOut:
                 raise
             except etcd.EtcdConnectionFailed as ex:
@@ -345,7 +382,9 @@ class AbstractEtcdClientWithFailover(abc.ABC, etcd.Client):
     def _get_machines_cache_from_dns(self, host: str, port: int) -> List[str]:
         """One host might be resolved into multiple ip addresses. We will make list out of it"""
         if self.protocol == 'http':
-            ret = [uri(self.protocol, res[-1][:2]) for res in self._dns_resolver.resolve(host, port)]
+            # Filter out unexpected results when python is compiled with --disable-ipv6 and running on IPv6 system.
+            ret = [uri(self.protocol, (res[4][0], res[4][1])) for res in self._dns_resolver.resolve(host, port)
+                   if isinstance(res[4][0], str) and isinstance(res[4][1], int)]
             if ret:
                 return list(set(ret))
         return [uri(self.protocol, (host, port))]
@@ -455,6 +494,10 @@ class EtcdClient(AbstractEtcdClientWithFailover):
     def _prepare_get_members(self, etcd_nodes: int) -> Dict[str, Any]:
         return self._prepare_common_parameters(etcd_nodes)
 
+    def _handle_server_response(self, response: urllib3.response.HTTPResponse) -> Any:
+        self._check_cluster_raft_term(response.headers.get('x-etcd-cluster-id'), response.headers.get('x-raft-term'))
+        return super(EtcdClient, self)._handle_server_response(response)
+
     def _get_members(self, base_uri: str, **kwargs: Any) -> List[str]:
         response = self.http.request(self._MGET, base_uri + self.version_prefix + '/machines', **kwargs)
         data = self._handle_server_response(response).data.decode('utf-8')
@@ -470,9 +513,9 @@ class EtcdClient(AbstractEtcdClientWithFailover):
 
 class AbstractEtcd(AbstractDCS):
 
-    def __init__(self, config: Dict[str, Any], client_cls: Type[AbstractEtcdClientWithFailover],
+    def __init__(self, config: Dict[str, Any], mpp: AbstractMPP, client_cls: Type[AbstractEtcdClientWithFailover],
                  retry_errors_cls: Union[Type[Exception], Tuple[Type[Exception], ...]]) -> None:
-        super(AbstractEtcd, self).__init__(config)
+        super(AbstractEtcd, self).__init__(config, mpp)
         self._retry = Retry(deadline=config['retry_timeout'], max_delay=1, max_tries=-1,
                             retry_exceptions=retry_errors_cls)
         self._ttl = int(config.get('ttl') or 30)
@@ -645,8 +688,8 @@ def catch_etcd_errors(func: Callable[..., Any]) -> Any:
 
 class Etcd(AbstractEtcd):
 
-    def __init__(self, config: Dict[str, Any]) -> None:
-        super(Etcd, self).__init__(config, EtcdClient, (etcd.EtcdLeaderElectionInProgress, EtcdRaftInternal))
+    def __init__(self, config: Dict[str, Any], mpp: AbstractMPP) -> None:
+        super(Etcd, self).__init__(config, mpp, EtcdClient, (etcd.EtcdLeaderElectionInProgress, EtcdRaftInternal))
         self.__do_not_watch = False
 
     @property
@@ -677,23 +720,8 @@ class Etcd(AbstractEtcd):
         history = history and TimelineHistory.from_node(history.modifiedIndex, history.value)
 
         # get last know leader lsn and slots
-        status = nodes.get(self._STATUS)
-        if status:
-            try:
-                status = json.loads(status.value)
-                last_lsn = status.get(self._OPTIME)
-                slots = status.get('slots')
-            except Exception:
-                slots = last_lsn = None
-        else:
-            last_lsn = nodes.get(self._LEADER_OPTIME)
-            last_lsn = last_lsn and last_lsn.value
-            slots = None
-
-        try:
-            last_lsn = int(last_lsn or '')
-        except Exception:
-            last_lsn = 0
+        status = nodes.get(self._STATUS) or nodes.get(self._LEADER_OPTIME)
+        status = Status.from_node(status and status.value)
 
         # get list of members
         members = [self.member(n) for k, n in nodes.items() if k.startswith(self._MEMBERS) and k.count('/') == 1]
@@ -722,19 +750,38 @@ class Etcd(AbstractEtcd):
         except Exception:
             failsafe = None
 
-        return Cluster(initialize, config, leader, last_lsn, members, failover, sync, history, slots, failsafe)
+        return Cluster(initialize, config, leader, status, members, failover, sync, history, failsafe)
 
-    def _cluster_loader(self, path: str) -> Cluster:
-        result = self.retry(self._client.read, path, recursive=True, quorum=self._ctl)
+    def _postgresql_cluster_loader(self, path: str) -> Cluster:
+        """Load and build the :class:`Cluster` object from DCS, which represents a single PostgreSQL cluster.
+
+        :param path: the path in DCS where to load :class:`Cluster` from.
+
+        :returns: :class:`Cluster` instance.
+        """
+        try:
+            result = self.retry(self._client.read, path, recursive=True, quorum=self._ctl)
+        except etcd.EtcdKeyNotFound:
+            return Cluster.empty()
         nodes = {node.key[len(result.key):].lstrip('/'): node for node in result.leaves}
         return self._cluster_from_nodes(result.etcd_index, nodes)
 
-    def _citus_cluster_loader(self, path: str) -> Dict[int, Cluster]:
+    def _mpp_cluster_loader(self, path: str) -> Dict[int, Cluster]:
+        """Load and build all PostgreSQL clusters from a single MPP cluster.
+
+        :param path: the path in DCS where to load Cluster(s) from.
+
+        :returns: all MPP groups as :class:`dict`, with group IDs as keys and :class:`Cluster` objects as values.
+        """
+        try:
+            result = self.retry(self._client.read, path, recursive=True, quorum=self._ctl)
+        except etcd.EtcdKeyNotFound:
+            return {}
+
         clusters: Dict[int, Dict[str, etcd.EtcdResult]] = defaultdict(dict)
-        result = self.retry(self._client.read, path, recursive=True, quorum=self._ctl)
         for node in result.leaves:
             key = node.key[len(result.key):].lstrip('/').split('/', 1)
-            if len(key) == 2 and citus_group_re.match(key[0]):
+            if len(key) == 2 and self._mpp.group_re.match(key[0]):
                 clusters[int(key[0])][key[1]] = node
         return {group: self._cluster_from_nodes(result.etcd_index, nodes) for group, nodes in clusters.items()}
 
@@ -744,8 +791,6 @@ class Etcd(AbstractEtcd):
         cluster = None
         try:
             cluster = loader(path)
-        except etcd.EtcdKeyNotFound:
-            cluster = Cluster.empty()
         except Exception as e:
             self._handle_exception(e, 'get_cluster', raise_ex=EtcdError('Etcd is not responding properly'))
         self._has_failed = False

patroni/dcs/etcd3.py

@@ -1,25 +1,30 @@
 from __future__ import absolute_import
+
 import base64
-import etcd
 import json
 import logging
 import os
 import socket
 import sys
 import time
-import urllib3
 
 from collections import defaultdict
 from enum import IntEnum
-from urllib3.exceptions import ReadTimeoutError, ProtocolError
 from threading import Condition, Lock, Thread
 from typing import Any, Callable, Collection, Dict, Iterator, List, Optional, Tuple, Type, TYPE_CHECKING, Union
 
-from . import ClusterConfig, Cluster, Failover, Leader, Member, SyncState, \
-    TimelineHistory, catch_return_false_exception, citus_group_re
-from .etcd import AbstractEtcdClientWithFailover, AbstractEtcd, catch_etcd_errors, DnsCachingResolver, Retry
+import etcd
+import urllib3
+
+from urllib3.exceptions import ProtocolError, ReadTimeoutError
+
+from ..collections import EMPTY_DICT
 from ..exceptions import DCSError, PatroniException
+from ..postgresql.mpp import AbstractMPP
 from ..utils import deep_compare, enable_keepalive, iter_response_objects, RetryFailedError, USER_AGENT
+from . import catch_return_false_exception, Cluster, ClusterConfig, \
+    Failover, Leader, Member, Status, SyncState, TimelineHistory
+from .etcd import AbstractEtcd, AbstractEtcdClientWithFailover, catch_etcd_errors, DnsCachingResolver, Retry
 
 logger = logging.getLogger(__name__)
 
@@ -124,6 +129,10 @@ class AuthFailed(InvalidArgument):
     error = "etcdserver: authentication failed, invalid user ID or password"
 
 
+class AuthOldRevision(InvalidArgument):
+    error = "etcdserver: revision of auth store is old"
+
+
 class PermissionDenied(Etcd3ClientError):
     code = GRPCCode.PermissionDenied
     error = "etcdserver: permission denied"
@@ -142,8 +151,7 @@ errStringToClientError = {getattr(s, 'error'): s for s in Etcd3ClientError.get_s
 errCodeToClientError = {getattr(s, 'code'): s for s in Etcd3ClientError.__subclasses__()}
 
 
-def _raise_for_data(data: Union[bytes, str, Dict[str, Union[Any, Dict[str, Any]]]],
-                    status_code: Optional[int] = None) -> Etcd3ClientError:
+def _raise_for_data(data: Union[bytes, str, Dict[str, Any]], status_code: Optional[int] = None) -> Etcd3ClientError:
     try:
         if TYPE_CHECKING:  # pragma: no cover
             assert isinstance(data, dict)
@@ -204,8 +212,9 @@ class Etcd3Client(AbstractEtcdClientWithFailover):
     ERROR_CLS = Etcd3Error
 
     def __init__(self, config: Dict[str, Any], dns_resolver: DnsCachingResolver, cache_ttl: int = 300) -> None:
+        self._reauthenticate = False
         self._token = None
-        self._cluster_version: Tuple[int] = tuple()
+        self._cluster_version: Tuple[int, ...] = tuple()
         super(Etcd3Client, self).__init__({**config, 'version_prefix': '/v3beta'}, dns_resolver, cache_ttl)
 
         try:
@@ -232,6 +241,10 @@ class Etcd3Client(AbstractEtcdClientWithFailover):
         try:
             data = data.decode('utf-8')
             ret: Dict[str, Any] = json.loads(data)
+
+            header = ret.get('header', EMPTY_DICT)
+            self._check_cluster_raft_term(header.get('cluster_id'), header.get('raft_term'))
+
             if response.status < 400:
                 return ret
         except (TypeError, ValueError, UnicodeError) as e:
@@ -282,7 +295,7 @@ class Etcd3Client(AbstractEtcdClientWithFailover):
         fields['retry'] = retry
         return self.api_execute(self.version_prefix + method, self._MPOST, fields)
 
-    def authenticate(self) -> bool:
+    def authenticate(self, *, retry: Optional[Retry] = None) -> bool:
         if self._use_proxies and not self._cluster_version:
             kwargs = self._prepare_common_parameters(1)
             self._ensure_version_prefix(self._base_uri, **kwargs)
@@ -291,7 +304,7 @@ class Etcd3Client(AbstractEtcdClientWithFailover):
         logger.info('Trying to authenticate on Etcd...')
         old_token, self._token = self._token, None
         try:
-            response = self.call_rpc('/auth/authenticate', {'name': self.username, 'password': self.password})
+            response = self.call_rpc('/auth/authenticate', {'name': self.username, 'password': self.password}, retry)
         except AuthNotEnabled:
             logger.info('Etcd authentication is not enabled')
             self._token = None
@@ -302,48 +315,64 @@ class Etcd3Client(AbstractEtcdClientWithFailover):
             self._token = response.get('token')
         return old_token != self._token
 
-    def handle_auth_errors(self: 'Etcd3Client', func: Callable[..., Any], *args: Any, **kwargs: Any) -> Any:
-        def retry(ex: Exception) -> Any:
-            if self.username and self.password:
-                self.authenticate()
-                return func(self, *args, **kwargs)
-            else:
-                logger.fatal('Username or password not set, authentication is not possible')
-                raise ex
+    def handle_auth_errors(self: 'Etcd3Client', func: Callable[..., Any], *args: Any,
+                           retry: Optional[Retry] = None, **kwargs: Any) -> Any:
+        reauthenticated = False
+        exc = None
+        while True:
+            if self._reauthenticate:
+                if self.username and self.password:
+                    self.authenticate(retry=retry)
+                    self._reauthenticate = False
+                else:
+                    msg = 'Username or password not set, authentication is not possible'
+                    logger.fatal(msg)
+                    raise exc or Etcd3Exception(msg)
+                reauthenticated = True
 
-        try:
-            return func(self, *args, **kwargs)
-        except (UserEmpty, PermissionDenied) as e:  # no token provided
-            # PermissionDenied is raised on 3.0 and 3.1
-            if self._cluster_version < (3, 3) and (not isinstance(e, PermissionDenied)
-                                                   or self._cluster_version < (3, 2)):
-                raise UnsupportedEtcdVersion('Authentication is required by Etcd cluster but not '
-                                             'supported on version lower than 3.3.0. Cluster version: '
-                                             '{0}'.format('.'.join(map(str, self._cluster_version))))
-            return retry(e)
-        except InvalidAuthToken as e:
-            logger.error('Invalid auth token: %s', self._token)
-            return retry(e)
+            try:
+                return func(self, *args, retry=retry, **kwargs)
+            except (UserEmpty, PermissionDenied) as e:  # no token provided
+                # PermissionDenied is raised on 3.0 and 3.1
+                if self._cluster_version < (3, 3) and (not isinstance(e, PermissionDenied)
+                                                       or self._cluster_version < (3, 2)):
+                    raise UnsupportedEtcdVersion('Authentication is required by Etcd cluster but not '
+                                                 'supported on version lower than 3.3.0. Cluster version: '
+                                                 '{0}'.format('.'.join(map(str, self._cluster_version))))
+                exc = e
+            except InvalidAuthToken as e:
+                logger.error('Invalid auth token: %s', self._token)
+                exc = e
+            except AuthOldRevision as e:
+                logger.error('Auth token is for old revision of auth store')
+                exc = e
+            self._reauthenticate = True
+            if retry:
+                logger.error('retry = %s', retry)
+                retry.ensure_deadline(0.5, exc)
+            elif reauthenticated:
+                raise exc
 
     @_handle_auth_errors
     def range(self, key: str, range_end: Union[bytes, str, None] = None, serializable: bool = True,
-              retry: Optional[Retry] = None) -> Dict[str, Any]:
+              *, retry: Optional[Retry] = None) -> Dict[str, Any]:
         params = build_range_request(key, range_end)
         params['serializable'] = serializable  # For better performance. We can tolerate stale reads
         return self.call_rpc('/kv/range', params, retry)
 
-    def prefix(self, key: str, serializable: bool = True, retry: Optional[Retry] = None) -> Dict[str, Any]:
-        return self.range(key, prefix_range_end(key), serializable, retry)
+    def prefix(self, key: str, serializable: bool = True, *, retry: Optional[Retry] = None) -> Dict[str, Any]:
+        return self.range(key, prefix_range_end(key), serializable, retry=retry)
 
     @_handle_auth_errors
-    def lease_grant(self, ttl: int, retry: Optional[Retry] = None) -> str:
+    def lease_grant(self, ttl: int, *, retry: Optional[Retry] = None) -> str:
         return self.call_rpc('/lease/grant', {'TTL': ttl}, retry)['ID']
 
-    def lease_keepalive(self, ID: str, retry: Optional[Retry] = None) -> Optional[str]:
+    def lease_keepalive(self, ID: str, *, retry: Optional[Retry] = None) -> Optional[str]:
         return self.call_rpc('/lease/keepalive', {'ID': ID}, retry).get('result', {}).get('TTL')
 
+    @_handle_auth_errors
     def txn(self, compare: Dict[str, Any], success: Dict[str, Any],
-            failure: Optional[Dict[str, Any]] = None, retry: Optional[Retry] = None) -> Dict[str, Any]:
+            failure: Optional[Dict[str, Any]] = None, *, retry: Optional[Retry] = None) -> Dict[str, Any]:
         fields = {'compare': [compare], 'success': [success]}
         if failure:
             fields['failure'] = [failure]
@@ -352,7 +381,7 @@ class Etcd3Client(AbstractEtcdClientWithFailover):
 
     @_handle_auth_errors
     def put(self, key: str, value: str, lease: Optional[str] = None, create_revision: Optional[str] = None,
-            mod_revision: Optional[str] = None, retry: Optional[Retry] = None) -> Dict[str, Any]:
+            mod_revision: Optional[str] = None, *, retry: Optional[Retry] = None) -> Dict[str, Any]:
         fields = {'key': base64_encode(key), 'value': base64_encode(value)}
         if lease:
             fields['lease'] = lease
@@ -367,14 +396,14 @@ class Etcd3Client(AbstractEtcdClientWithFailover):
 
     @_handle_auth_errors
     def deleterange(self, key: str, range_end: Union[bytes, str, None] = None,
-                    mod_revision: Optional[str] = None, retry: Optional[Retry] = None) -> Dict[str, Any]:
+                    mod_revision: Optional[str] = None, *, retry: Optional[Retry] = None) -> Dict[str, Any]:
         fields = build_range_request(key, range_end)
         if mod_revision is None:
             return self.call_rpc('/kv/deleterange', fields, retry)
         compare = {'target': 'MOD', 'mod_revision': mod_revision, 'key': fields['key']}
         return self.txn(compare, {'request_delete_range': fields}, retry=retry)
 
-    def deleteprefix(self, key: str, retry: Optional[Retry] = None) -> Dict[str, Any]:
+    def deleteprefix(self, key: str, *, retry: Optional[Retry] = None) -> Dict[str, Any]:
         return self.deleterange(key, prefix_range_end(key), retry=retry)
 
     def watchrange(self, key: str, range_end: Union[bytes, str, None] = None,
@@ -574,12 +603,6 @@ class PatroniEtcd3Client(Etcd3Client):
         super(PatroniEtcd3Client, self).set_base_uri(value)
         self._restart_watcher()
 
-    def authenticate(self) -> bool:
-        ret = super(PatroniEtcd3Client, self).authenticate()
-        if ret:
-            self._restart_watcher()
-        return ret
-
     def _wait_cache(self, timeout: float) -> None:
         stop_time = time.time() + timeout
         while self._kv_cache and not self._kv_cache.is_ready():
@@ -631,8 +654,8 @@ class PatroniEtcd3Client(Etcd3Client):
         return ret
 
     def txn(self, compare: Dict[str, Any], success: Dict[str, Any],
-            failure: Optional[Dict[str, Any]] = None, retry: Optional[Retry] = None) -> Dict[str, Any]:
-        ret = super(PatroniEtcd3Client, self).txn(compare, success, failure, retry)
+            failure: Optional[Dict[str, Any]] = None, *, retry: Optional[Retry] = None) -> Dict[str, Any]:
+        ret = super(PatroniEtcd3Client, self).txn(compare, success, failure, retry=retry)
         # Here we abuse the fact that the `failure` is only set in the call from update_leader().
         # In all other cases the txn() call failure may be an indicator of a stale cache,
         # and therefore we want to restart watcher.
@@ -643,8 +666,9 @@ class PatroniEtcd3Client(Etcd3Client):
 
 class Etcd3(AbstractEtcd):
 
-    def __init__(self, config: Dict[str, Any]) -> None:
-        super(Etcd3, self).__init__(config, PatroniEtcd3Client, (DeadlineExceeded, Unavailable, FailedPrecondition))
+    def __init__(self, config: Dict[str, Any], mpp: AbstractMPP) -> None:
+        super(Etcd3, self).__init__(config, mpp, PatroniEtcd3Client,
+                                    (DeadlineExceeded, Unavailable, FailedPrecondition))
         self.__do_not_watch = False
         self._lease = None
         self._last_lease_refresh = 0
@@ -676,12 +700,12 @@ class Etcd3(AbstractEtcd):
         if not force and self._lease and self._last_lease_refresh + self._loop_wait > time.time():
             return False
 
-        if self._lease and not self._client.lease_keepalive(self._lease, retry):
+        if self._lease and not self._client.lease_keepalive(self._lease, retry=retry):
             self._lease = None
 
         ret = not self._lease
         if ret:
-            self._lease = self._client.lease_grant(self._ttl, retry)
+            self._lease = self._client.lease_grant(self._ttl, retry=retry)
 
         self._last_lease_refresh = time.time()
         return ret
@@ -703,7 +727,11 @@ class Etcd3(AbstractEtcd):
 
     @property
     def cluster_prefix(self) -> str:
-        return self._base_path + '/' if self.is_citus_coordinator() else self.client_path('')
+        """Construct the cluster prefix for the cluster.
+
+        :returns: path in the DCS under which we store information about this Patroni cluster.
+        """
+        return self._base_path + '/' if self.is_mpp_coordinator() else self.client_path('')
 
     @staticmethod
     def member(node: Dict[str, str]) -> Member:
@@ -723,23 +751,8 @@ class Etcd3(AbstractEtcd):
         history = history and TimelineHistory.from_node(history['mod_revision'], history['value'])
 
         # get last know leader lsn and slots
-        status = nodes.get(self._STATUS)
-        if status:
-            try:
-                status = json.loads(status['value'])
-                last_lsn = status.get(self._OPTIME)
-                slots = status.get('slots')
-            except Exception:
-                slots = last_lsn = None
-        else:
-            last_lsn = nodes.get(self._LEADER_OPTIME)
-            last_lsn = last_lsn and last_lsn['value']
-            slots = None
-
-        try:
-            last_lsn = int(last_lsn or '')
-        except Exception:
-            last_lsn = 0
+        status = nodes.get(self._STATUS) or nodes.get(self._LEADER_OPTIME)
+        status = Status.from_node(status and status['value'])
 
         # get list of members
         members = [self.member(n) for k, n in nodes.items() if k.startswith(self._MEMBERS) and k.count('/') == 1]
@@ -770,20 +783,32 @@ class Etcd3(AbstractEtcd):
         except Exception:
             failsafe = None
 
-        return Cluster(initialize, config, leader, last_lsn, members, failover, sync, history, slots, failsafe)
+        return Cluster(initialize, config, leader, status, members, failover, sync, history, failsafe)
 
-    def _cluster_loader(self, path: str) -> Cluster:
+    def _postgresql_cluster_loader(self, path: str) -> Cluster:
+        """Load and build the :class:`Cluster` object from DCS, which represents a single PostgreSQL cluster.
+
+        :param path: the path in DCS where to load :class:`Cluster` from.
+
+        :returns: :class:`Cluster` instance.
+        """
         nodes = {node['key'][len(path):]: node
                  for node in self._client.get_cluster(path)
                  if node['key'].startswith(path)}
         return self._cluster_from_nodes(nodes)
 
-    def _citus_cluster_loader(self, path: str) -> Dict[int, Cluster]:
+    def _mpp_cluster_loader(self, path: str) -> Dict[int, Cluster]:
+        """Load and build all PostgreSQL clusters from a single MPP cluster.
+
+        :param path: the path in DCS where to load Cluster(s) from.
+
+        :returns: all MPP groups as :class:`dict`, with group IDs as keys and :class:`Cluster` objects as values.
+        """
         clusters: Dict[int, Dict[str, Dict[str, Any]]] = defaultdict(dict)
         path = self._base_path + '/'
         for node in self._client.get_cluster(path):
             key = node['key'][len(path):].split('/', 1)
-            if len(key) == 2 and citus_group_re.match(key[0]):
+            if len(key) == 2 and self._mpp.group_re.match(key[0]):
                 clusters[int(key[0])][key[1]] = node
         return {group: self._cluster_from_nodes(nodes) for group, nodes in clusters.items()}
 
@@ -835,14 +860,16 @@ class Etcd3(AbstractEtcd):
         try:
             return _retry(self._client.put, self.leader_path, self._name, self._lease, create_revision='0')
         except LeaseNotFound:
-            logger.error('Our lease disappeared from Etcd. Will try to get a new one and retry attempt')
             self._lease = None
-            retry.ensure_deadline(0)
+            if not retry.ensure_deadline(0):
+                logger.error('Our lease disappeared from Etcd. Deadline exceeded, giving up')
+                return False
+
+            logger.error('Our lease disappeared from Etcd. Will try to get a new one and retry attempt')
 
             _retry(self._do_refresh_lease)
 
             retry.ensure_deadline(1, Etcd3Error('_do_attempt_to_acquire_leader timeout'))
-
             return _retry(self._client.put, self.leader_path, self._name, self._lease, create_revision='0')
 
     @catch_return_false_exception

patroni/dcs/exhibitor.py

@@ -3,12 +3,13 @@ import logging
 import random
 import time
 
-from typing import Any, Callable, Dict, List, Union
+from typing import Any, Callable, cast, Dict, List, Union
 
-from . import Cluster
-from .zookeeper import ZooKeeper
+from ..postgresql.mpp import AbstractMPP
 from ..request import get as requests_get
 from ..utils import uri
+from . import Cluster
+from .zookeeper import ZooKeeper
 
 logger = logging.getLogger(__name__)
 
@@ -40,8 +41,9 @@ class ExhibitorEnsembleProvider(object):
 
         if isinstance(json, dict) and 'servers' in json and 'port' in json:
             self._next_poll = time.time() + self._poll_interval
-            servers: List[str] = json['servers']
-            zookeeper_hosts = ','.join([h + ':' + str(json['port']) for h in sorted(servers)])
+            servers: List[str] = cast(Dict[str, Any], json)['servers']
+            port = str(cast(Dict[str, Any], json)['port'])
+            zookeeper_hosts = ','.join([h + ':' + port for h in sorted(servers)])
             if self._zookeeper_hosts != zookeeper_hosts:
                 logger.info('ZooKeeper connection string has changed: %s => %s', self._zookeeper_hosts, zookeeper_hosts)
                 self._zookeeper_hosts = zookeeper_hosts
@@ -49,7 +51,7 @@ class ExhibitorEnsembleProvider(object):
                 return True
         return False
 
-    def _query_exhibitors(self, exhibitors: List[str]) -> Union[Dict[str, Any], Any]:
+    def _query_exhibitors(self, exhibitors: List[str]) -> Any:
         random.shuffle(exhibitors)
         for host in exhibitors:
             try:
@@ -66,10 +68,10 @@ class ExhibitorEnsembleProvider(object):
 
 class Exhibitor(ZooKeeper):
 
-    def __init__(self, config: Dict[str, Any]) -> None:
+    def __init__(self, config: Dict[str, Any], mpp: AbstractMPP) -> None:
         interval = config.get('poll_interval', 300)
         self._ensemble_provider = ExhibitorEnsembleProvider(config['hosts'], config['port'], poll_interval=interval)
-        super(Exhibitor, self).__init__({**config, 'hosts': self._ensemble_provider.zookeeper_hosts})
+        super(Exhibitor, self).__init__({**config, 'hosts': self._ensemble_provider.zookeeper_hosts}, mpp)
 
     def _load_cluster(
             self, path: str, loader: Callable[[str], Union[Cluster, Dict[int, Cluster]]]

patroni/dcs/kubernetes.py

@@ -9,21 +9,26 @@ import random
 import socket
 import tempfile
 import time
-import urllib3
-import yaml
 
 from collections import defaultdict
 from copy import deepcopy
 from http.client import HTTPException
-from urllib3.exceptions import HTTPError
 from threading import Condition, Lock, Thread
-from typing import Any, Callable, Collection, Dict, List, Optional, Tuple, Type, Union, TYPE_CHECKING
+from typing import Any, Callable, Collection, Dict, List, Optional, Tuple, Type, TYPE_CHECKING, Union
 
-from . import AbstractDCS, Cluster, ClusterConfig, Failover, Leader, Member, SyncState, \
-    TimelineHistory, CITUS_COORDINATOR_GROUP_ID, citus_group_re
+import urllib3
+import yaml
+
+from urllib3.exceptions import HTTPError
+
+from ..collections import EMPTY_DICT
 from ..exceptions import DCSError
-from ..utils import deep_compare, iter_response_objects, keepalive_socket_options, \
-    Retry, RetryFailedError, tzutc, uri, USER_AGENT
+from ..postgresql.misc import PostgresqlRole, PostgresqlState
+from ..postgresql.mpp import AbstractMPP
+from ..utils import deep_compare, iter_response_objects, \
+    keepalive_socket_options, Retry, RetryFailedError, tzutc, uri, USER_AGENT
+from . import AbstractDCS, Cluster, ClusterConfig, Failover, Leader, Member, Status, SyncState, TimelineHistory
+
 if TYPE_CHECKING:  # pragma: no cover
     from ..config import Config
 
@@ -470,7 +475,7 @@ class K8sClient(object):
                 if len(args) == 3:  # name, namespace, body
                     body = args[2]
                 elif action == 'create':  # namespace, body
-                    body = args[1]
+                    body = args[1]  # pyright: ignore [reportGeneralTypeIssues]
                 elif action == 'delete':  # name, namespace
                     body = kwargs.pop('body', None)
                 else:
@@ -509,7 +514,7 @@ class KubernetesRetriableException(k8s_client.rest.ApiException):
     @property
     def sleeptime(self) -> Optional[int]:
         try:
-            return int((self.headers or {}).get('retry-after', ''))
+            return int((self.headers or EMPTY_DICT).get('retry-after', ''))
         except Exception:
             return None
 
@@ -644,7 +649,7 @@ class ObjectCache(Thread):
         with self._object_cache_lock:
             return self._object_cache.get(name)
 
-    def _process_event(self, event: Dict[str, Union[Any, Dict[str, Union[Any, Dict[str, Any]]]]]) -> None:
+    def _process_event(self, event: Dict[str, Any]) -> None:
         ev_type = event['type']
         obj = event['object']
         name = obj['metadata']['name']
@@ -654,7 +659,7 @@ class ObjectCache(Thread):
             obj = K8sObject(obj)
             success, old_value = self.set(name, obj)
             if success:
-                new_value = (obj.metadata.annotations or {}).get(self._annotations_map.get(name))
+                new_value = (obj.metadata.annotations or EMPTY_DICT).get(self._annotations_map.get(name, ''))
         elif ev_type == 'DELETED':
             success, old_value = self.delete(name, obj['metadata']['resourceVersion'])
         else:
@@ -662,7 +667,7 @@ class ObjectCache(Thread):
 
         if success and obj.get('kind') != 'Pod':
             if old_value:
-                old_value = (old_value.metadata.annotations or {}).get(self._annotations_map.get(name))
+                old_value = (old_value.metadata.annotations or EMPTY_DICT).get(self._annotations_map.get(name, ''))
 
             value_changed = old_value != new_value and \
                 (name != self._dcs.config_path or old_value is not None and new_value is not None)
@@ -746,22 +751,22 @@ class ObjectCache(Thread):
 
 class Kubernetes(AbstractDCS):
 
-    _CITUS_LABEL = 'citus-group'
-
-    def __init__(self, config: Dict[str, Any]) -> None:
+    def __init__(self, config: Dict[str, Any], mpp: AbstractMPP) -> None:
         self._labels = deepcopy(config['labels'])
         self._labels[config.get('scope_label', 'cluster-name')] = config['scope']
         self._label_selector = ','.join('{0}={1}'.format(k, v) for k, v in self._labels.items())
         self._namespace = config.get('namespace') or 'default'
         self._role_label = config.get('role_label', 'role')
-        self._leader_label_value = config.get('leader_label_value', 'master')
+        self._leader_label_value = config.get('leader_label_value', 'primary')
         self._follower_label_value = config.get('follower_label_value', 'replica')
-        self._standby_leader_label_value = config.get('standby_leader_label_value', 'standby-leader')
+        self._standby_leader_label_value = config.get('standby_leader_label_value', 'primary')
         self._tmp_role_label = config.get('tmp_role_label')
+        self._bootstrap_labels: Dict[str, str] = {str(k): str(v)
+                                                  for k, v in (config.get('bootstrap_labels') or EMPTY_DICT).items()}
         self._ca_certs = os.environ.get('PATRONI_KUBERNETES_CACERT', config.get('cacert')) or SERVICE_CERT_FILENAME
-        super(Kubernetes, self).__init__({**config, 'namespace': ''})
-        if self._citus_group:
-            self._labels[self._CITUS_LABEL] = self._citus_group
+        super(Kubernetes, self).__init__({**config, 'namespace': ''}, mpp)
+        if self._mpp.is_enabled():
+            self._labels[self._mpp.k8s_group_label] = str(self._mpp.group)
 
         self._retry = Retry(deadline=config['retry_timeout'], max_delay=1, max_tries=-1,
                             retry_exceptions=KubernetesRetriableException)
@@ -771,8 +776,7 @@ class Kubernetes(AbstractDCS):
         except k8s_config.ConfigException:
             k8s_config.load_kube_config(context=config.get('context', 'kind-kind'))
 
-        pod_ip = config.get('pod_ip')
-        self.__ips: List[str] = [] if self._ctl or not isinstance(pod_ip, str) else [pod_ip]
+        self.__ips: List[str] = [] if self._ctl else [config.get('pod_ip', '')]
         self.__ports: List[K8sObject] = []
         ports: List[Dict[str, Any]] = config.get('ports', [{}])
         for p in ports:
@@ -836,7 +840,7 @@ class Kubernetes(AbstractDCS):
         self._api.configure_timeouts(self.loop_wait, self._retry.deadline, self.ttl)
 
         # retriable_http_codes supposed to be either int, list of integers or comma-separated string with integers.
-        retriable_http_codes = config.get('retriable_http_codes', [])
+        retriable_http_codes: Union[str, List[Union[str, int]]] = config.get('retriable_http_codes', [])
         if not isinstance(retriable_http_codes, list):
             retriable_http_codes = [c.strip() for c in str(retriable_http_codes).split(',')]
 
@@ -847,7 +851,7 @@ class Kubernetes(AbstractDCS):
 
     @staticmethod
     def member(pod: K8sObject) -> Member:
-        annotations = pod.metadata.annotations or {}
+        annotations = pod.metadata.annotations or EMPTY_DICT
         member = Member.from_node(pod.metadata.resource_version, pod.metadata.name, None, annotations.get('status', ''))
         member.data['pod_labels'] = pod.metadata.labels
         return member
@@ -888,18 +892,8 @@ class Kubernetes(AbstractDCS):
             self._leader_resource_version = metadata.resource_version if metadata else None
         annotations: Dict[str, str] = metadata and metadata.annotations or {}
 
-        # get last known leader lsn
-        try:
-            last_lsn = int(annotations.get(self._OPTIME, ''))
-        except Exception:
-            last_lsn = 0
-
-        # get permanent slots state (confirmed_flush_lsn)
-        slots = annotations.get('slots')
-        try:
-            slots = json.loads(annotations.get('slots', ''))
-        except Exception:
-            slots = None
+        # get last known leader lsn and slots
+        status = Status.from_node(annotations)
 
         # get failsafe topology
         try:
@@ -938,29 +932,41 @@ class Kubernetes(AbstractDCS):
         failover = nodes.get(path + self._FAILOVER)
         metadata = failover and failover.metadata
         failover = metadata and Failover.from_node(metadata.resource_version,
-                                                   (metadata.annotations or {}).copy())
+                                                   (metadata.annotations or EMPTY_DICT).copy())
 
         # get synchronization state
         sync = nodes.get(path + self._SYNC)
         metadata = sync and sync.metadata
         sync = SyncState.from_node(metadata and metadata.resource_version, metadata and metadata.annotations)
 
-        return Cluster(initialize, config, leader, last_lsn, members, failover, sync, history, slots, failsafe)
+        return Cluster(initialize, config, leader, status, members, failover, sync, history, failsafe)
 
-    def _cluster_loader(self, path: Dict[str, Any]) -> Cluster:
+    def _postgresql_cluster_loader(self, path: Dict[str, Any]) -> Cluster:
+        """Load and build the :class:`Cluster` object from DCS, which represents a single PostgreSQL cluster.
+
+        :param path: the path in DCS where to load :class:`Cluster` from.
+
+        :returns: :class:`Cluster` instance.
+        """
         return self._cluster_from_nodes(path['group'], path['nodes'], path['pods'].values())
 
-    def _citus_cluster_loader(self, path: Dict[str, Any]) -> Dict[int, Cluster]:
+    def _mpp_cluster_loader(self, path: Dict[str, Any]) -> Dict[int, Cluster]:
+        """Load and build all PostgreSQL clusters from a single MPP cluster.
+
+        :param path: the path in DCS where to load Cluster(s) from.
+
+        :returns: all MPP groups as :class:`dict`, with group IDs as keys and :class:`Cluster` objects as values.
+        """
         clusters: Dict[str, Dict[str, Dict[str, K8sObject]]] = defaultdict(lambda: defaultdict(dict))
 
         for name, pod in path['pods'].items():
-            group = pod.metadata.labels.get(self._CITUS_LABEL)
-            if group and citus_group_re.match(group):
+            group = pod.metadata.labels.get(self._mpp.k8s_group_label)
+            if group and self._mpp.group_re.match(group):
                 clusters[group]['pods'][name] = pod
 
         for name, kind in path['nodes'].items():
-            group = kind.metadata.labels.get(self._CITUS_LABEL)
-            if group and citus_group_re.match(group):
+            group = kind.metadata.labels.get(self._mpp.k8s_group_label)
+            if group and self._mpp.group_re.match(group):
                 clusters[group]['nodes'][name] = kind
         return {int(group): self._cluster_from_nodes(group, value['nodes'], value['pods'].values())
                 for group, value in clusters.items()}
@@ -976,9 +982,9 @@ class Kubernetes(AbstractDCS):
             with self._condition:
                 self._wait_caches(stop_time)
                 pods = {name: pod for name, pod in self._pods.copy().items()
-                        if not group or pod.metadata.labels.get(self._CITUS_LABEL) == group}
+                        if not group or pod.metadata.labels.get(self._mpp.k8s_group_label) == group}
                 nodes = {name: kind for name, kind in self._kinds.copy().items()
-                         if not group or kind.metadata.labels.get(self._CITUS_LABEL) == group}
+                         if not group or kind.metadata.labels.get(self._mpp.k8s_group_label) == group}
             return loader({'group': group, 'pods': pods, 'nodes': nodes})
         except Exception:
             logger.exception('get_cluster')
@@ -987,17 +993,24 @@ class Kubernetes(AbstractDCS):
     def _load_cluster(
             self, path: str, loader: Callable[[Any], Union[Cluster, Dict[int, Cluster]]]
     ) -> Union[Cluster, Dict[int, Cluster]]:
-        group = self._citus_group if path == self.client_path('') else None
+        group = str(self._mpp.group) if self._mpp.is_enabled() and path == self.client_path('') else None
         return self.__load_cluster(group, loader)
 
-    def get_citus_coordinator(self) -> Optional[Cluster]:
+    def get_mpp_coordinator(self) -> Optional[Cluster]:
+        """Load the PostgreSQL cluster for the MPP Coordinator.
+
+        .. note::
+            This method is only executed on the worker nodes to find the coordinator.
+
+        :returns: Select :class:`Cluster` instance associated with the MPP Coordinator group ID.
+        """
         try:
-            ret = self.__load_cluster(str(CITUS_COORDINATOR_GROUP_ID), self._cluster_loader)
+            ret = self.__load_cluster(str(self._mpp.coordinator_group_id), self._postgresql_cluster_loader)
             if TYPE_CHECKING:  # pragma: no cover
                 assert isinstance(ret, Cluster)
             return ret
         except Exception as e:
-            logger.error('Failed to load Citus coordinator cluster from Kubernetes: %r', e)
+            logger.error('Failed to load %s coordinator cluster from Kubernetes: %r', self._mpp.type, e)
 
     @staticmethod
     def compare_ports(p1: K8sObject, p2: K8sObject) -> bool:
@@ -1040,9 +1053,10 @@ class Kubernetes(AbstractDCS):
         return False
 
     def __target_ref(self, leader_ip: str, latest_subsets: List[K8sObject], pod: K8sObject) -> K8sObject:
-        # we want to re-use existing target_ref if possible
+        # we want to reuse existing target_ref if possible
+        empty_addresses: List[K8sObject] = []
         for subset in latest_subsets:
-            for address in subset.addresses or []:
+            for address in subset.addresses or empty_addresses:
                 if address.ip == leader_ip and address.target_ref and address.target_ref.name == self._name:
                     return address.target_ref
         return k8s_client.V1ObjectReference(kind='Pod', uid=pod.metadata.uid, namespace=self._namespace,
@@ -1050,7 +1064,8 @@ class Kubernetes(AbstractDCS):
 
     def _map_subsets(self, endpoints: Dict[str, Any], ips: List[str]) -> None:
         leader = self._kinds.get(self.leader_path)
-        latest_subsets = leader and leader.subsets or []
+        empty_addresses: List[K8sObject] = []
+        latest_subsets = leader and leader.subsets or empty_addresses
         if not ips:
             # We want to have subsets empty
             if latest_subsets:
@@ -1069,6 +1084,27 @@ class Kubernetes(AbstractDCS):
     def _patch_or_create(self, name: str, annotations: Dict[str, Any],
                          resource_version: Optional[str] = None, patch: bool = False,
                          retry: Optional[Callable[..., Any]] = None, ips: Optional[List[str]] = None) -> K8sObject:
+        """Patch or create K8s object, Endpoint or ConfigMap.
+
+        :param name: the name of the object.
+        :param annotations: mapping of annotations that we want to create/update.
+        :param resource_version: object should be updated only if the ``resource_version`` matches provided value.
+        :param patch: ``True`` if we know in advance that the object already exists and we should patch it.
+        :param retry: a callable that will take care of retries
+        :param ips: IP address that we want to put to the subsets of the endpoint. Could have following values:
+
+                    * ``None`` - when we don't need to touch subset;
+                    * ``[]`` - to set subsets to the empty list, when :meth:`delete_leader` method is called;
+
+                    * ``['ip.add.re.ss']`` - when we want to make sure that the subsets of the leader endpoint
+                      contains the IP address of the leader, that we get from the ``kubernetes.pod_ip``;
+
+                    * ``['']`` - when we want to make sure that the subsets of the leader endpoint contains the IP
+                      address of the leader, but ``kubernetes.pod_ip`` configuration is missing. In this case we will
+                      try to take the IP address of the Pod which name matches ``name`` from the config file.
+
+        :returns: the new :class:`V1Endpoints` or :class:`V1ConfigMap` object, that was created or updated.
+        """
         metadata = {'namespace': self._namespace, 'name': name, 'labels': self._labels, 'annotations': annotations}
         if patch or resource_version:
             if resource_version is not None:
@@ -1081,9 +1117,10 @@ class Kubernetes(AbstractDCS):
             metadata['annotations'] = {k: v for k, v in annotations.items() if v is not None}
 
         metadata = k8s_client.V1ObjectMeta(**metadata)
-        if ips is not None and self._api.use_endpoints:
+        if self._api.use_endpoints:
             endpoints = {'metadata': metadata}
-            self._map_subsets(endpoints, ips)
+            if ips is not None:
+                self._map_subsets(endpoints, ips)
             body = k8s_client.V1Endpoints(**endpoints)
         else:
             body = k8s_client.V1ConfigMap(metadata=metadata)
@@ -1140,6 +1177,13 @@ class Kubernetes(AbstractDCS):
         """Unused"""
         raise NotImplementedError  # pragma: no cover
 
+    def write_leader_optime(self, last_lsn: int) -> None:
+        """Write value for WAL LSN to ``optime`` annotation of the leader object.
+
+        :param last_lsn: absolute WAL LSN in bytes.
+        """
+        self.patch_or_create(self.leader_path, {self._OPTIME: str(last_lsn)}, patch=True, retry=False)
+
     def _update_leader_with_retry(self, annotations: Dict[str, Any],
                                   resource_version: Optional[str], ips: List[str]) -> bool:
         retry = self._retry.copy()
@@ -1174,23 +1218,28 @@ class Kubernetes(AbstractDCS):
 
         self._kinds.set(self.leader_path, kind)
 
-        if not retry.ensure_deadline(0.5):
-            return False
-
-        kind_annotations = kind and kind.metadata.annotations or {}
+        kind_annotations = kind and kind.metadata.annotations or EMPTY_DICT
         kind_resource_version = kind and kind.metadata.resource_version
 
         # There is different leader or resource_version in cache didn't change
         if kind and (kind_annotations.get(self._LEADER) != self._name or kind_resource_version == resource_version):
             return False
 
+        # We can get 409 because we do at least one retry, and the first update might have succeeded,
+        # therefore we will check if annotations on the read object match expectations.
+        if all(kind_annotations.get(k) == v for k, v in annotations.items()):
+            return True
+
+        if not retry.ensure_deadline(0.5):
+            return False
+
         return bool(_run_and_handle_exceptions(self._patch_or_create, self.leader_path, annotations,
                                                kind_resource_version, ips=ips, retry=_retry))
 
-    def update_leader(self, leader: Leader, last_lsn: Optional[int],
+    def update_leader(self, cluster: Cluster, last_lsn: Optional[int],
                       slots: Optional[Dict[str, int]] = None, failsafe: Optional[Dict[str, str]] = None) -> bool:
         kind = self._kinds.get(self.leader_path)
-        kind_annotations = kind and kind.metadata.annotations or {}
+        kind_annotations = kind and kind.metadata.annotations or EMPTY_DICT
 
         if kind and kind_annotations.get(self._LEADER) != self._name:
             return False
@@ -1203,6 +1252,8 @@ class Kubernetes(AbstractDCS):
         if last_lsn:
             annotations[self._OPTIME] = str(last_lsn)
             annotations['slots'] = json.dumps(slots, separators=(',', ':')) if slots else None
+            retain_slots = self._build_retain_slots(cluster, slots)
+            annotations['retain_slots'] = json.dumps(retain_slots) if retain_slots else None
 
         if failsafe is not None:
             annotations[self._FAILSAFE] = json.dumps(failsafe, separators=(',', ':')) if failsafe else None
@@ -1225,11 +1276,10 @@ class Kubernetes(AbstractDCS):
             else:
                 annotations['acquireTime'] = self._leader_observed_record.get('acquireTime') or now
             annotations['transitions'] = str(transitions)
-        ips: Optional[List[str]] = [] if self._api.use_endpoints else None
 
         try:
             ret = bool(self._patch_or_create(self.leader_path, annotations,
-                                             self._leader_resource_version, retry=self.retry, ips=ips))
+                                             self._leader_resource_version, retry=self.retry, ips=self.__ips))
         except k8s_client.rest.ApiException as e:
             if e.status == 409 and self._leader_resource_version:  # Conflict in resource_version
                 # Terminate watchers, it could be a sign that K8s API is in a failed state
@@ -1269,31 +1319,36 @@ class Kubernetes(AbstractDCS):
     def touch_member(self, data: Dict[str, Any]) -> bool:
         cluster = self.cluster
         if cluster and cluster.leader and cluster.leader.name == self._name:
-            role = self._leader_label_value
-            tmp_role = 'master'
-        elif data['state'] == 'running' and data['role'] not in ('master', 'primary'):
-            role = {
-                'replica': self._follower_label_value,
-                'standby-leader': self._standby_leader_label_value,
-            }.get(data['role'], data['role'])
+            role = self._standby_leader_label_value \
+                if data['role'] == PostgresqlRole.STANDBY_LEADER else self._leader_label_value
+            tmp_role = 'primary'
+        elif data['state'] == PostgresqlState.RUNNING and data['role'] != PostgresqlRole.PRIMARY:
+            role = {'replica': self._follower_label_value}.get(data['role'], data['role'])
             tmp_role = data['role']
         else:
             role = None
             tmp_role = None
 
-        role_labels = {self._role_label: role}
+        updated_labels = {self._role_label: role}
         if self._tmp_role_label:
-            role_labels[self._tmp_role_label] = tmp_role
+            updated_labels[self._tmp_role_label] = tmp_role
+
+        if self._bootstrap_labels:
+            if data['state'] in (PostgresqlState.INITDB, PostgresqlState.CUSTOM_BOOTSTRAP,
+                                 PostgresqlState.BOOTSTRAP_STARTING, PostgresqlState.CREATING_REPLICA):
+                updated_labels.update(self._bootstrap_labels)
+            else:
+                updated_labels.update({k: None for k, _ in self._bootstrap_labels.items()})
 
         member = cluster and cluster.get_member(self._name, fallback_to_leader=False)
         pod_labels = member and member.data.pop('pod_labels', None)
         ret = member and pod_labels is not None\
-            and all(pod_labels.get(k) == v for k, v in role_labels.items())\
+            and all(pod_labels.get(k) == v for k, v in updated_labels.items())\
             and deep_compare(data, member.data)
 
         if not ret:
-            metadata = {'namespace': self._namespace, 'name': self._name, 'labels': role_labels,
-                        'annotations': {'status': json.dumps(data, separators=(',', ':'))}}
+            metadata: Dict[str, Any] = {'namespace': self._namespace, 'name': self._name, 'labels': updated_labels,
+                                        'annotations': {'status': json.dumps(data, separators=(',', ':'))}}
             body = k8s_client.V1Pod(metadata=k8s_client.V1ObjectMeta(**metadata))
             ret = self._api.patch_namespaced_pod(self._name, self._namespace, body)
             if ret:
@@ -1315,7 +1370,7 @@ class Kubernetes(AbstractDCS):
     def delete_leader(self, leader: Optional[Leader], last_lsn: Optional[int] = None) -> bool:
         ret = False
         kind = self._kinds.get(self.leader_path)
-        if kind and (kind.metadata.annotations or {}).get(self._LEADER) == self._name:
+        if kind and (kind.metadata.annotations or EMPTY_DICT).get(self._LEADER) == self._name:
             annotations: Dict[str, Optional[str]] = {self._LEADER: None}
             if last_lsn:
                 annotations[self._OPTIME] = str(last_lsn)
@@ -1339,15 +1394,18 @@ class Kubernetes(AbstractDCS):
         raise NotImplementedError  # pragma: no cover
 
     def write_sync_state(self, leader: Optional[str], sync_standby: Optional[Collection[str]],
-                         version: Optional[str] = None) -> Optional[SyncState]:
+                         quorum: Optional[int], version: Optional[str] = None) -> Optional[SyncState]:
         """Prepare and write annotations to $SCOPE-sync Endpoint or ConfigMap.
 
         :param leader: name of the leader node that manages /sync key
         :param sync_standby: collection of currently known synchronous standby node names
+        :param quorum: if the node from sync_standby list is doing a leader race it should
+                       see at least quorum other nodes from the sync_standby + leader list
         :param version: last known `resource_version` for conditional update of the object
         :returns: the new :class:`SyncState` object or None
         """
-        sync_state = self.sync_state(leader, sync_standby)
+        sync_state = self.sync_state(leader, sync_standby, quorum)
+        sync_state['quorum'] = str(sync_state['quorum']) if sync_state['quorum'] is not None else None
         ret = self.patch_or_create(self.sync_path, sync_state, version, False)
         if not isinstance(ret, bool):
             return SyncState.from_node(ret.metadata.resource_version, sync_state)
@@ -1359,7 +1417,7 @@ class Kubernetes(AbstractDCS):
         :param version: last known `resource_version` for conditional update of the object
         :returns: `True` if "delete" was successful
         """
-        return self.write_sync_state(None, None, version=version) is not None
+        return self.write_sync_state(None, None, None, version=version) is not None
 
     def watch(self, leader_version: Optional[str], timeout: float) -> bool:
         if self.__do_not_watch:

patroni/dcs/raft.py

@@ -5,16 +5,19 @@ import threading
 import time
 
 from collections import defaultdict
-from pysyncobj import SyncObj, SyncObjConf, replicated, FAIL_REASON
+from typing import Any, Callable, Collection, Dict, List, Optional, Set, TYPE_CHECKING, Union
+
+from pysyncobj import FAIL_REASON, replicated, SyncObj, SyncObjConf
 from pysyncobj.dns_resolver import globalDnsResolver
 from pysyncobj.node import TCPNode
-from pysyncobj.transport import TCPTransport, CONNECTION_STATE
+from pysyncobj.transport import CONNECTION_STATE, TCPTransport
 from pysyncobj.utility import TcpUtility
-from typing import Any, Callable, Collection, Dict, List, Optional, Set, Union, TYPE_CHECKING
 
-from . import AbstractDCS, ClusterConfig, Cluster, Failover, Leader, Member, SyncState, TimelineHistory, citus_group_re
 from ..exceptions import DCSError
+from ..postgresql.mpp import AbstractMPP
 from ..utils import validate_directory
+from . import AbstractDCS, Cluster, ClusterConfig, Failover, Leader, Member, Status, SyncState, TimelineHistory
+
 if TYPE_CHECKING:  # pragma: no cover
     from ..config import Config
 
@@ -252,7 +255,7 @@ class KVStoreTTL(DynMemberSyncObj):
                         self.__limb.pop(key)
                 self._expire(key, value, callback=callback)
 
-    def get(self, key: str, recursive: bool = False) -> Union[None, Dict[str, Any], Dict[str, Dict[str, Any]]]:
+    def get(self, key: str, recursive: bool = False) -> Optional[Dict[str, Any]]:
         if not recursive:
             return self.__data.get(key)
         return {k: v for k, v in self.__data.items() if k.startswith(key)}
@@ -284,8 +287,8 @@ class KVStoreTTL(DynMemberSyncObj):
 
 class Raft(AbstractDCS):
 
-    def __init__(self, config: Dict[str, Any]) -> None:
-        super(Raft, self).__init__(config)
+    def __init__(self, config: Dict[str, Any], mpp: AbstractMPP) -> None:
+        super(Raft, self).__init__(config, mpp)
         self._ttl = int(config.get('ttl') or 30)
 
         ready_event = threading.Event()
@@ -343,23 +346,8 @@ class Raft(AbstractDCS):
         history = history and TimelineHistory.from_node(history['index'], history['value'])
 
         # get last know leader lsn and slots
-        status = nodes.get(self._STATUS)
-        if status:
-            try:
-                status = json.loads(status['value'])
-                last_lsn = status.get(self._OPTIME)
-                slots = status.get('slots')
-            except Exception:
-                slots = last_lsn = None
-        else:
-            last_lsn = nodes.get(self._LEADER_OPTIME)
-            last_lsn = last_lsn and last_lsn['value']
-            slots = None
-
-        try:
-            last_lsn = int(last_lsn or '')
-        except Exception:
-            last_lsn = 0
+        status = nodes.get(self._STATUS) or nodes.get(self._LEADER_OPTIME)
+        status = Status.from_node(status and status['value'])
 
         # get list of members
         members = [self.member(k, n) for k, n in nodes.items() if k.startswith(self._MEMBERS) and k.count('/') == 1]
@@ -387,21 +375,33 @@ class Raft(AbstractDCS):
         except Exception:
             failsafe = None
 
-        return Cluster(initialize, config, leader, last_lsn, members, failover, sync, history, slots, failsafe)
+        return Cluster(initialize, config, leader, status, members, failover, sync, history, failsafe)
 
-    def _cluster_loader(self, path: str) -> Cluster:
+    def _postgresql_cluster_loader(self, path: str) -> Cluster:
+        """Load and build the :class:`Cluster` object from DCS, which represents a single PostgreSQL cluster.
+
+        :param path: the path in DCS where to load :class:`Cluster` from.
+
+        :returns: :class:`Cluster` instance.
+        """
         response = self._sync_obj.get(path, recursive=True)
         if not response:
             return Cluster.empty()
         nodes = {key[len(path):]: value for key, value in response.items()}
         return self._cluster_from_nodes(nodes)
 
-    def _citus_cluster_loader(self, path: str) -> Dict[int, Cluster]:
+    def _mpp_cluster_loader(self, path: str) -> Dict[int, Cluster]:
+        """Load and build all PostgreSQL clusters from a single MPP cluster.
+
+        :param path: the path in DCS where to load Cluster(s) from.
+
+        :returns: all MPP groups as :class:`dict`, with group IDs as keys and :class:`Cluster` objects as values.
+        """
         clusters: Dict[int, Dict[str, Any]] = defaultdict(dict)
         response = self._sync_obj.get(path, recursive=True)
         for key, value in (response or {}).items():
             key = key[len(path):].split('/', 1)
-            if len(key) == 2 and citus_group_re.match(key[0]):
+            if len(key) == 2 and self._mpp.group_re.match(key[0]):
                 clusters[int(key[0])][key[1]] = value
         return {group: self._cluster_from_nodes(nodes) for group, nodes in clusters.items()}