Release 2.0.2 (#1851)

* bump version
* update release notes
* implement missing unit-test

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,48 @@
+---
+name: Bug report
+about: Create a report to help us improve
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+**Describe the bug**
+A clear and concise description of what the bug is.
+
+**To Reproduce**
+Steps to reproduce the behavior:
+
+**Expected behavior**
+A clear and concise description of what you expected to happen.
+
+**Screenshots**
+If applicable, add screenshots to help explain your problem.
+
+**Environment**
+- Patroni version:
+- PostgreSQL version:
+- DCS (and its version):
+
+**Patroni configuration file**
+```
+Please copy&paste your Patroni configuration file here
+```
+
+**patronictl show-config**
+```
+Please copy&paste the output of "patronictl show-config" command here
+```
+
+**Have you checked Patroni logs?**
+Please provide a snippet of Patroni log files here
+
+**Have you checked PostgreSQL logs?**
+Please provide a snippet here
+
+**Have you tried to use GitHub issue search?**
+Maybe there is already a similar issue solved.
+
+
+**Additional context**
+Add any other context about the problem here.

.github/workflows/install_deps.py

@@ -0,0 +1,182 @@
+import inspect
+import os
+import shutil
+import subprocess
+import stat
+import sys
+import tarfile
+import time
+import zipfile
+
+
+def install_requirements(what):
+    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)))
+    try:
+        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 += ['psycopg2-binary', 'coverage']
+    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 r.startswith(v[0])}
+            if not extras or what == 'all' or what in extras:
+                requirements.append(r)
+
+    subprocess.call([sys.executable, '-m', 'pip', 'install', '--upgrade', 'pip'])
+    r = subprocess.call([sys.executable, '-m', 'pip', 'install'] + requirements)
+    s = subprocess.call([sys.executable, '-m', 'pip', 'install', '--upgrade', 'setuptools'])
+    return s | r
+
+
+def install_packages(what):
+    packages = {
+        'zookeeper': ['zookeeper', 'zookeeper-bin', 'zookeeperd'],
+        'consul': ['consul'],
+    }
+    packages['exhibitor'] = packages['zookeeper']
+    packages = packages.get(what, [])
+    ver = str({'etcd': '9.6', 'etcd3': '9.6', 'consul': 10, 'exhibitor': 11, 'kubernetes': 12, 'raft': 13}.get(what))
+    subprocess.call(['sudo', 'apt-get', 'update', '-y'])
+    return subprocess.call(['sudo', 'apt-get', 'install', '-y', 'postgresql-' + ver, 'expect-dev', 'wget'] + packages)
+
+
+def get_file(url, name):
+    try:
+        from urllib.request import urlretrieve
+    except ImportError:
+        from urllib import urlretrieve
+
+    print('Downloading ' + url)
+    urlretrieve(url, name)
+
+
+def untar(archive, name):
+    with tarfile.open(archive) as tar:
+        f = tar.extractfile(name)
+        dest = os.path.basename(name)
+        with open(dest, 'wb') as d:
+            shutil.copyfileobj(f, d)
+            return dest
+
+
+def unzip(archive, name):
+    with zipfile.ZipFile(archive, 'r') as z:
+        name = z.extract(name)
+        dest = os.path.basename(name)
+        shutil.move(name, dest)
+        return dest
+
+
+def unzip_all(archive):
+    print('Extracting ' + archive)
+    with zipfile.ZipFile(archive, 'r') as z:
+        z.extractall()
+
+
+def chmod_755(name):
+    os.chmod(name, stat.S_IRUSR | stat.S_IWUSR | stat.S_IXUSR |
+             stat.S_IRGRP | stat.S_IXGRP | stat.S_IROTH | stat.S_IXOTH)
+
+
+def unpack(archive, name):
+    print('Extracting {0} from {1}'.format(name, archive))
+    func = unzip if archive.endswith('.zip') else untar
+    name = func(archive, name)
+    chmod_755(name)
+    return name
+
+
+def install_etcd():
+    version = os.environ.get('ETCDVERSION', '3.3.13')
+    platform = {'linux2': 'linux', 'win32': 'windows', 'cygwin': 'windows'}.get(sys.platform, sys.platform)
+    dirname = 'etcd-v{0}-{1}-amd64'.format(version, platform)
+    ext = 'tar.gz' if platform == 'linux' else 'zip'
+    name = '{0}.{1}'.format(dirname, ext)
+    url = 'https://github.com/etcd-io/etcd/releases/download/v{0}/{1}'.format(version, name)
+    get_file(url, name)
+    ext = '.exe' if platform == 'windows' else ''
+    return int(unpack(name, '{0}/etcd{1}'.format(dirname, ext)) is None)
+
+
+def install_postgres():
+    version = os.environ.get('PGVERSION', '12.1-1')
+    platform = {'darwin': 'osx', 'win32': 'windows-x64', 'cygwin': 'windows-x64'}[sys.platform]
+    name = 'postgresql-{0}-{1}-binaries.zip'.format(version, platform)
+    get_file('http://get.enterprisedb.com/postgresql/' + name, name)
+    unzip_all(name)
+    bin_dir = os.path.join('pgsql', 'bin')
+    for f in os.listdir(bin_dir):
+        chmod_755(os.path.join(bin_dir, f))
+    subprocess.call(['pgsql/bin/postgres', '-V'])
+    return 0
+
+
+def setup_kubernetes():
+    get_file('https://storage.googleapis.com/minikube/k8sReleases/v1.7.0/localkube-linux-amd64', 'localkube')
+    chmod_755('localkube')
+
+    devnull = open(os.devnull, 'w')
+    subprocess.Popen(['sudo', 'nohup', './localkube', '--logtostderr=true', '--enable-dns=false'],
+                     stdout=devnull, stderr=devnull)
+    for _ in range(0, 120):
+        if subprocess.call(['wget', '-qO', '-', 'http://127.0.0.1:8080/'], stdout=devnull, stderr=devnull) == 0:
+            break
+        time.sleep(1)
+    else:
+        print('localkube did not start')
+        return 1
+
+    subprocess.call('sudo chmod 644 /var/lib/localkube/certs/*', shell=True)
+    print('Set up .kube/config')
+    kube = os.path.join(os.path.expanduser('~'), '.kube')
+    os.makedirs(kube)
+    with open(os.path.join(kube, 'config'), 'w') as f:
+        f.write("""apiVersion: v1
+clusters:
+- cluster:
+    certificate-authority: /var/lib/localkube/certs/ca.crt
+    server: https://127.0.0.1:8443
+  name: local
+contexts:
+- context:
+    cluster: local
+    user: myself
+  name: local
+current-context: local
+kind: Config
+preferences: {}
+users:
+- name: myself
+  user:
+    client-certificate: /var/lib/localkube/certs/apiserver.crt
+    client-key: /var/lib/localkube/certs/apiserver.key
+""")
+    return 0
+
+
+def main():
+    what = os.environ.get('DCS', sys.argv[1] if len(sys.argv) > 1 else 'all')
+
+    if what != 'all':
+        if sys.platform.startswith('linux'):
+            r = install_packages(what)
+            if r == 0 and what == 'kubernetes':
+                r = setup_kubernetes()
+        else:
+            r = install_postgres()
+
+        if r == 0 and what.startswith('etcd'):
+            r = install_etcd()
+
+        if r != 0:
+            return r
+
+    return install_requirements(what)
+
+
+if __name__ == '__main__':
+    sys.exit(main())

.github/workflows/run_tests.py

@@ -0,0 +1,47 @@
+import os
+import shutil
+import subprocess
+import sys
+import tempfile
+
+
+def main():
+    what = os.environ.get('DCS', sys.argv[1] if len(sys.argv) > 1 else 'all')
+
+    if what == 'all':
+        flake8 = subprocess.call([sys.executable, 'setup.py', 'flake8'])
+        test = subprocess.call([sys.executable, 'setup.py', 'test'])
+        version = '.'.join(map(str, sys.version_info[:2]))
+        shutil.move('.coverage', os.path.join(tempfile.gettempdir(), '.coverage.' + version))
+        return flake8 | test
+    elif what == 'combine':
+        tmp = tempfile.gettempdir()
+        for name in os.listdir(tmp):
+            if name.startswith('.coverage.'):
+                shutil.move(os.path.join(tmp, name), name)
+        return subprocess.call([sys.executable, '-m', 'coverage', 'combine'])
+
+    env = os.environ.copy()
+    if sys.platform.startswith('linux'):
+        version = {'etcd': '9.6', 'etcd3': '9.6', 'consul': 10, 'exhibitor': 11, 'kubernetes': 12, 'raft': 13}.get(what)
+        path = '/usr/lib/postgresql/{0}/bin:.'.format(version)
+        unbuffer = ['timeout', '600', 'unbuffer']
+    else:
+        path = os.path.abspath(os.path.join('pgsql', 'bin'))
+        if sys.platform == 'darwin':
+            path += ':.'
+        unbuffer = []
+    env['PATH'] = path + os.pathsep + env['PATH']
+    env['DCS'] = what
+
+    ret = subprocess.call(unbuffer + [sys.executable, '-m', 'behave'], env=env)
+
+    if ret != 0:
+        if subprocess.call('grep . features/output/*_failed/*postgres?.*', shell=True) != 0:
+            subprocess.call('grep . features/output/*/*postgres?.*', shell=True)
+        return 1
+    return 0
+
+
+if __name__ == '__main__':
+    sys.exit(main())

.github/workflows/tests.yaml

@@ -0,0 +1,175 @@
+name: Tests
+
+on:
+  pull_request:
+  push:
+    branches:
+    - master
+    tags:
+    - v.*
+
+jobs:
+  unit:
+    runs-on: ${{ matrix.os }}-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu, windows, macos]
+
+    steps:
+    - uses: actions/checkout@v1
+    - name: Set up Python 2.7
+      uses: actions/setup-python@v2
+      with:
+        python-version: 2.7
+      if: matrix.os != 'windows'
+    - name: Install dependencies
+      run: python .github/workflows/install_deps.py
+      if: matrix.os != 'windows'
+    - name: Run tests and flake8
+      run: python .github/workflows/run_tests.py
+      if: matrix.os != 'windows'
+
+    - name: Set up Python 3.5
+      uses: actions/setup-python@v2
+      with:
+        python-version: 3.5
+    - 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 3.6
+      uses: actions/setup-python@v2
+      with:
+        python-version: 3.6
+    - 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 3.7
+      uses: actions/setup-python@v2
+      with:
+        python-version: 3.7
+    - 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 3.8
+      uses: actions/setup-python@v2
+      with:
+        python-version: 3.8
+    - 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 3.9
+      uses: actions/setup-python@v2
+      with:
+        python-version: 3.9
+    - name: Install dependencies
+      run: python .github/workflows/install_deps.py
+    - name: Run tests and flake8
+      run: python .github/workflows/run_tests.py
+
+    - name: Combine coverage
+      run: python .github/workflows/run_tests.py combine
+
+    - name: Install coveralls
+      run: python -m pip install coveralls
+
+    - name: Upload Coverage
+      env:
+        COVERALLS_FLAG_NAME: unit-${{ matrix.os }}
+        COVERALLS_PARALLEL: 'true'
+        GITHUB_TOKEN: ${{ secrets.github_token }}
+      run: python -m coveralls --service=github
+
+    - name: Run codacy-coverage-reporter
+      uses: codacy/codacy-coverage-reporter-action@master
+      env:
+        SECRETS_AVAILABLE: ${{ secrets.CODACY_PROJECT_TOKEN != '' }}
+      with:
+        project-token: ${{ secrets.CODACY_PROJECT_TOKEN }}
+        coverage-reports: coverage.xml
+      if: ${{ matrix.os == 'ubuntu' && env.SECRETS_AVAILABLE == 'true' }}
+
+  behave:
+    runs-on: ${{ matrix.os }}-latest
+    env:
+      DCS: ${{ matrix.dcs }}
+      ETCDVERSION: 3.3.13
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu]
+        python-version: [2.7, 3.5, 3.8]
+        dcs: [etcd, etcd3, consul, exhibitor, kubernetes, raft]
+
+    steps:
+    - uses: actions/checkout@v1
+    - name: Set up Python
+      uses: actions/setup-python@v2
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install dependencies
+      run: python .github/workflows/install_deps.py
+    - name: Run behave tests
+      run: python .github/workflows/run_tests.py
+    - uses: actions/setup-python@v2
+      with:
+        python-version: 3.9
+    - name: Install coveralls
+      run: python -m pip install coveralls
+    - name: Upload Coverage
+      env:
+        COVERALLS_FLAG_NAME: behave-${{ matrix.os }}-${{ matrix.dcs }}-${{ matrix.python-version }}
+        COVERALLS_PARALLEL: 'true'
+        GITHUB_TOKEN: ${{ secrets.github_token }}
+      run: python -m coveralls --service=github
+
+  behavem:
+    runs-on: ${{ matrix.os }}-latest
+    env:
+      DCS: ${{ matrix.dcs }}
+      ETCDVERSION: 3.3.13
+      PGVERSION: 12.1-1  # for windows and macos
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [macos]  #, windows]
+        python-version: [3.7]
+        dcs: [etcd, etcd3, raft]
+
+    steps:
+    - uses: actions/checkout@v1
+    - name: Set up Python
+      uses: actions/setup-python@v2
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install dependencies
+      run: python .github/workflows/install_deps.py
+    - name: Run behave tests
+      run: python .github/workflows/run_tests.py
+    - name: Install coveralls
+      run: python -m pip install coveralls
+    - name: Upload Coverage
+      env:
+        COVERALLS_FLAG_NAME: behave-${{ matrix.os }}-${{ matrix.dcs }}-${{ matrix.python-version }}
+        COVERALLS_PARALLEL: 'true'
+        GITHUB_TOKEN: ${{ secrets.github_token }}
+      run: python -m coveralls --service=github
+
+  coveralls-finish:
+    name: Finalize coveralls.io
+    needs: [unit, behave, behavem]
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/setup-python@v2
+    - run: python -m pip install coveralls
+    - run: python -m coveralls --service=github --finish
+      env:
+        GITHUB_TOKEN: ${{ secrets.github_token }}

.travis.yml

@@ -1,164 +0,0 @@
-sudo: true
-dist: trusty
-language: python
-addons:
-  apt:
-    packages:
-      - expect-dev # for unbuffer
-env:
-  global:
-  - ETCDVERSION=3.3.13 ZKVERSION=3.4.14 CONSULVERSION=0.7.4
-  - PYVERSIONS="2.7 3.6"
-  - BOTO_CONFIG=/doesnotexist
-matrix:
-  include:
-  - python: "3.5"
-    env: PYVERSIONS="2.7 3.5 3.6" TEST_SUITE="python setup.py"
-  - python: "3.6"
-    env: DCS="etcd" TEST_SUITE="behave"
-  - python: "3.6"
-    env: DCS="etcd3" TEST_SUITE="behave"
-  - python: "3.6"
-    env: DCS="exhibitor" TEST_SUITE="behave"
-  - python: "3.6"
-    env: DCS="consul" TEST_SUITE="behave"
-  - python: "3.6"
-    env: DCS="raft" TEST_SUITE="behave"
-  - python: "3.6"
-    env: DCS="kubernetes" TEST_SUITE="behave"
-branches:
-  only:
-  - master
-  - /^v\d+\.\d+(\.\d+)?$/
-cache:
-  directories:
-  - $HOME/mycache
-before_cache:
-- |
-  rm -fr $HOME/mycache/python*
-  for pv in $PYVERSIONS; do
-      fpv=$(basename $(readlink $HOME/virtualenv/python${pv}))
-      mv $HOME/virtualenv/${fpv} $HOME/mycache/${fpv}
-  done
-install:
-  - |
-    set -e
-
-    if [[ $TEST_SUITE == "behave" ]]; then
-        function get_consul() {
-            CC=~/mycache/consul_${CONSULVERSION}
-            if [[ ! -x $CC ]]; then
-                curl -L https://releases.hashicorp.com/consul/${CONSULVERSION}/consul_${CONSULVERSION}_linux_amd64.zip \
-                    | gunzip > $CC
-                [[ ${PIPESTATUS[0]} == 0 ]] || return 1
-                chmod +x $CC
-            fi
-            ln -s $CC consul
-        }
-
-        function get_etcd() {
-            EC=~/mycache/etcd_${ETCDVERSION}
-            if [[ ! -x $EC ]]; then
-                rm -rf ~/mycache/etcd_*
-                curl -L https://github.com/coreos/etcd/releases/download/v${ETCDVERSION}/etcd-v${ETCDVERSION}-linux-amd64.tar.gz \
-                    | tar xz -C . --strip=1 --wildcards --no-anchored etcd
-                [[ ${PIPESTATUS[0]} == 0 ]] || return 1
-                mv etcd $EC
-            fi
-            ln -s $EC etcd
-        }
-
-        function get_etcd3() {
-            get_etcd
-        }
-
-        function get_kubernetes() {
-            wget -O localkube "https://storage.googleapis.com/minikube/k8sReleases/v1.7.0/localkube-linux-amd64"
-            chmod +x localkube
-            sudo nohup ./localkube --logtostderr=true --enable-dns=false > localkube.log 2>&1 &
-
-            echo "Waiting for localkube to start..."
-            if ! timeout 120 sh -c "while ! curl -ks http://127.0.0.1:8080/ >/dev/null; do sleep 1; done"; then
-                sudo cat localkube.log
-                echo "localkube did not start"
-                exit 1
-            fi
-            echo "Check certificate permissions"
-            sudo chmod 644 /var/lib/localkube/certs/*
-            sudo ls -altr /var/lib/localkube/certs/
-
-            echo "Set up .kube/config"
-            mkdir ~/.kube
-            echo -e "apiVersion: v1\nclusters:\n- cluster:\n    certificate-authority: /var/lib/localkube/certs/ca.crt\n    server: https://127.0.0.1:8443\n  name: local\ncontexts:\n- context:\n    cluster: local\n    user: myself\n  name: local\ncurrent-context: local\nkind: Config\npreferences: {}\nusers:\n- name: myself\n  user:\n    client-certificate: /var/lib/localkube/certs/apiserver.crt\n    client-key: /var/lib/localkube/certs/apiserver.key\n" > ~/.kube/config
-        }
-
-        function get_exhibitor() {
-            ZC=~/mycache/zookeeper-${ZKVERSION}
-            if [[ ! -d $ZC ]]; then
-                curl -L http://www.apache.org/dist/zookeeper/zookeeper-${ZKVERSION}/zookeeper-${ZKVERSION}.tar.gz | tar xz
-                [[ ${PIPESTATUS[0]} == 0 ]] || return 1
-                mv zookeeper-${ZKVERSION}/conf/zoo_sample.cfg zookeeper-${ZKVERSION}/conf/zoo.cfg
-                mv zookeeper-${ZKVERSION} $ZC
-            fi
-            $ZC/bin/zkServer.sh start
-            # following lines are 'emulating' exhibitor REST API
-            while true; do
-                echo -e 'HTTP/1.0 200 OK\nContent-Type: application/json\n\n{"servers":["127.0.0.1"],"port":2181}' \
-                    | nc -l 8181 &> /dev/null
-            done&
-        }
-
-        function get_raft() {
-            return 0
-        }
-
-        attempt_num=1
-        until get_${DCS}; do
-            [[ $attempt_num -ge 3 ]] && exit 1
-            echo "Attempt $attempt_num failed! Trying again in $attempt_num seconds..."
-            sleep $(( attempt_num++ ))
-        done
-    fi
-
-    for pv in $PYVERSIONS; do
-        fpv=$(basename $(readlink $HOME/virtualenv/python$pv))
-        if [[ -d ~/mycache/${fpv} ]]; then
-            mv ~/virtualenv/${fpv} ~/virtualenv/${fpv}.bckp
-            mv ~/mycache/${fpv} ~/virtualenv/${fpv}
-        fi
-        source ~/virtualenv/python${pv}/bin/activate
-        # explicitly install all needed python modules to cache them
-        for p in '-r requirements.txt' 'psycopg2-binary behave codacy-coverage coverage coveralls flake8 mock pytest-cov pytest setuptools'; do
-            pip install $p --upgrade
-        done
-    done
-script:
-  - |
-    for pv in $PYVERSIONS; do
-        source ~/virtualenv/python${pv}/bin/activate
-
-        if [[ $TEST_SUITE = "behave" ]]; then
-            echo Running integration tests using python${pv}
-            if ! PATH=.:/usr/lib/postgresql/9.6/bin:$PATH unbuffer $TEST_SUITE; then
-                # output all log files when tests are failing
-                grep . features/output/*_failed/*postgres?.*
-                exit 1
-            fi
-        else
-            echo Running unit tests using python${pv}
-            unbuffer $TEST_SUITE test
-            $TEST_SUITE flake8
-        fi
-        mv .coverage /tmp/.coverage.$pv
-    done
-    mv /tmp/.coverage.* .
-    python -m coverage combine
-
-    set +e
-after_success:
-  # before_cache is executed earlier than after_success, so we need to restore one of virtualenv directories
-  - fpv=$(basename $(readlink $HOME/virtualenv/python3.6)) && mv $HOME/mycache/${fpv} $HOME/virtualenv/${fpv}
-  - coveralls
-  - if [[ $TEST_SUITE != "behave" ]]; then python-codacy-coverage -r coverage.xml; fi
-  - if [[ $DCS == "exhibitor" ]]; then ~/mycache/zookeeper-${ZKVERSION}/bin/zkServer.sh stop; fi
-  - sudo kill $(jobs -p)

README.rst

@@ -12,6 +12,8 @@ Patroni is a template for you to create your own customized, high-availability s
 
 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 13.
+
 **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.
 
 .. contents::

docs/CONTRIBUTING.rst

@@ -10,6 +10,39 @@ Chatting
 
 Just want to chat with other Patroni users?  Looking for interactive troubleshooting help? Join us on channel #patroni in the `PostgreSQL Slack <https://postgres-slack.herokuapp.com/>`__.
 
+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`.
+
+ Install dependencies:
+
+.. code-block:: bash
+
+    # You may want to use Virtualenv or specify pip3.
+    pip install -r requirements.txt
+    pip install -r requirements.dev.txt
+
+After you have all dependencies installed, you can run the various test suites:
+
+.. code-block:: bash
+
+    # You may want to use Virtualenv or specify python3.
+
+    # Run flake8 to check syntax and formatting:
+    python setup.py flake8
+
+    # Run the pytest suite in tests/:
+    python setup.py test
+
+    # 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
+
 Reporting issues
 ----------------
 

docs/ENVIRONMENT.rst

@@ -109,9 +109,11 @@ Kubernetes
 Raft
 ----
 
--  **PATRONI\_RAFT\_SELF\_ADDR**: ``ip:port`` to listen on for Raft connections. If not set, the node will not participate in consensus.
+-  **PATRONI\_RAFT\_SELF\_ADDR**: ``ip:port`` to listen on for Raft connections. The ``self_addr`` must be accessible from other nodes of the cluster. If not set, the node will not participate in consensus.
+-  **PATRONI\_RAFT\_BIND\_ADDR**: (optional) ``ip:port`` to listen on for Raft connections. If not specified the ``self_addr`` will be used.
 -  **PATRONI\_RAFT\_PARTNER\_ADDRS**: list of other Patroni nodes in the cluster in format ``"'ip1:port1','ip2:port2'"``. It is important to quote every single entity!
 -  **PATRONI\_RAFT\_DATA\_DIR**: directory where to store Raft log and snapshot. If not specified the current working directory is used.
+-  **PATRONI\_RAFT\_PASSWORD**: (optional) Encrypt Raft traffic with a specified password, requires ``cryptography`` python module.
 
 PostgreSQL
 ----------
@@ -125,6 +127,7 @@ PostgreSQL
 -  **PATRONI\_REPLICATION\_PASSWORD**: replication password; the user will be created during initialization.
 -  **PATRONI\_REPLICATION\_SSLMODE**: (optional) maps to the `sslmode <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLMODE>`__ connection parameter, which allows a client to specify the type of TLS negotiation mode with the server. For more information on how each mode works, please visit the `PostgreSQL documentation <https://www.postgresql.org/docs/current/libpq-ssl.html#LIBPQ-SSL-SSLMODE-STATEMENTS>`__. The default mode is ``prefer``.
 -  **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\_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.
@@ -134,6 +137,7 @@ PostgreSQL
 -  **PATRONI\_SUPERUSER\_PASSWORD**: password for the superuser, set during initialization (initdb).
 -  **PATRONI\_SUPERUSER\_SSLMODE**: (optional) maps to the `sslmode <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLMODE>`__ connection parameter, which allows a client to specify the type of TLS negotiation mode with the server. For more information on how each mode works, please visit the `PostgreSQL documentation <https://www.postgresql.org/docs/current/libpq-ssl.html#LIBPQ-SSL-SSLMODE-STATEMENTS>`__. The default mode is ``prefer``.
 -  **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\_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.
@@ -143,6 +147,7 @@ PostgreSQL
 -  **PATRONI\_REWIND\_PASSWORD**: password for the user for ``pg_rewind``; the user will be created during initialization.
 -  **PATRONI\_REWIND\_SSLMODE**: (optional) maps to the `sslmode <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLMODE>`__ connection parameter, which allows a client to specify the type of TLS negotiation mode with the server. For more information on how each mode works, please visit the `PostgreSQL documentation <https://www.postgresql.org/docs/current/libpq-ssl.html#LIBPQ-SSL-SSLMODE-STATEMENTS>`__. The default mode is ``prefer``.
 -  **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\_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.
@@ -157,7 +162,9 @@ REST API
 -  **PATRONI\_RESTAPI\_PASSWORD**: Basic-auth password to protect unsafe REST API endpoints.
 -  **PATRONI\_RESTAPI\_CERTFILE**: Specifies the file with the certificate in the PEM format. If the certfile is not specified or is left empty, the API server will work without SSL.
 -  **PATRONI\_RESTAPI\_KEYFILE**: Specifies the file with the secret key in the PEM format.
+-  **PATRONI\_RESTAPI\_KEYFILE\_PASSWORD**: Specifies a password for decrypting the keyfile.
 -  **PATRONI\_RESTAPI\_CAFILE**: Specifies the file with the CA_BUNDLE with certificates of trusted CAs to use while verifying client certs.
+-  **PATRONI\_RESTAPI\_CIPHERS**: (optional) Specifies the permitted cipher suites (e.g. "ECDHE-RSA-AES256-GCM-SHA384:DHE-RSA-AES256-GCM-SHA384:ECDHE-RSA-AES128-GCM-SHA256:DHE-RSA-AES128-GCM-SHA256:!SSLv1:!SSLv2:!SSLv3:!TLSv1:!TLSv1.1")
 -  **PATRONI\_RESTAPI\_VERIFY\_CLIENT**: ``none`` (default), ``optional`` or ``required``. When ``none`` REST API will not check client certificates. When ``required`` client certificates are required for all REST API calls. When ``optional`` client certificates are required for all unsafe REST API endpoints. When ``required`` is used, then client authentication succeeds, if the certificate signature verification succeeds. For ``optional`` the client cert will only be checked for ``PUT``, ``POST``, ``PATCH``, and ``DELETE`` requests.
 -  **PATRONI\_RESTAPI\_HTTP\_EXTRA\_HEADERS**: (optional) HTTP headers let the REST API server pass additional information with an HTTP response.
 -  **PATRONI\_RESTAPI\_HTTPS\_EXTRA\_HEADERS**: (optional) HTTPS headers let the REST API server pass additional information with an HTTP response when TLS is enabled. This will also pass additional information set in ``http_extra_headers``.

docs/README.rst

@@ -163,3 +163,20 @@ When connecting from an application, always use a non-superuser. Patroni require
    :target: https://travis-ci.org/zalando/patroni
 .. |Coverage Status| image:: https://coveralls.io/repos/zalando/patroni/badge.svg?branch=master
    :target: https://coveralls.io/r/zalando/patroni?branch=master
+
+Testing Your HA Solution
+--------------------------------------
+Testing an HA solution is a time consuming process, with many variables. This is particularly true considering a cross-platform application. You need a trained system administrator or a consultant to do this work. It is not something we can cover in depth in the documentaiton.
+
+That said, here are some pieces of your infrastructure you should be sure to test:
+
+* Network (the network in front of your system as well as the NICs [physical or virtual] themselves)
+* Disk IO 
+* file limits (nofile in Linux)
+* RAM. Even if you have oomkiller turned off as suggested, the unavailability of RAM could cause issues.
+* CPU
+* Virtualization Contention (overcommitting the hypervisor)
+* Any cgroup limitation (likely to be related to the above)
+* ``kill -9`` of any postgres process (except postmaster!). This is a decent simulation of a segfault.
+
+One thing that you should not do is run ``kill -9`` on a postmaster process. This is because doing so does not mimic any real life scenario. If you are concerned your infrastructure is insecure and an attacker could run ``kill -9``, no amount of HA process is going to fix that. The attacker will simply kill the process again, or cause chaos in another way.

docs/SETTINGS.rst

@@ -15,6 +15,7 @@ Dynamic configuration is stored in the DCS (Distributed Configuration Store) and
 -  **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.
 -  **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.
 -  **master\_start\_timeout**: the amount of time a master 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 master failure is: loop\_wait + master\_start\_timeout + loop\_wait, unless master\_start\_timeout is zero, in which case it's just loop\_wait. Set the value according to your durability/availability tradeoff.
 - **master\_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 master_stop_timeout. Set the value according to your durability/availability tradeoff. If the parameter is not set or set <= 0, master_stop_timeout does not apply.
@@ -38,6 +39,32 @@ Dynamic configuration is stored in the DCS (Distributed Configuration Store) and
         -  **type**: slot type. Could be ``physical`` or ``logical``. If the slot is logical, you have to additionally define ``database`` and ``plugin``.
         -  **database**: the database name where logical slots should be created.
         -  **plugin**: the plugin name for the logical slot.
+-  **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.
+    -  **name**: the name of the replication slot.
+    -  **type**: slot type. Can be ``physical`` or ``logical``. If the slot is logical, you may additionally define ``database`` and/or ``plugin``.
+    -  **database**: the database name (when matching a ``logical`` slot).
+    -  **plugin**: the logical decoding plugin (when matching a ``logical`` slot).
+
+Note: **slots** is a hashmap while **ignore_slots** is an array. For example:
+
+.. code:: YAML
+
+        slots:
+          permanent_logical_slot_name:
+            type: logical
+            database: my_db
+            plugin: test_decoding
+          permanent_physical_slot_name:
+            type: physical
+          ...
+        ignore_slots:
+          - name: ignored_logical_slot_name
+            type: logical
+            database: my_db
+            plugin: test_decoding
+          - name: ignored_physical_slot_name
+            type: physical
+          ...
 
 Global/Universal
 ----------------
@@ -183,9 +210,11 @@ Kubernetes
 
 Raft
 ----
--  **self\_addr**: ``ip:port`` to listen on for Raft connections. If not set, the node will not participate in consensus.
+-  **self\_addr**: ``ip:port`` to listen on for Raft connections. The ``self_addr`` must be accessible from other nodes of the cluster. If not set, the node will not participate in consensus.
+-  **bind\_addr**: (optional) ``ip:port`` to listen on for Raft connections. If not specified the ``self_addr`` will be used.
 -  **partner\_addrs**: list of other Patroni nodes in the cluster in format: ['ip1:port', 'ip2:port', 'etc...']
 -  **data\_dir**: directory where to store Raft log and snapshot. If not specified the current working directory is used.
+-  **password**: (optional) Encrypt Raft traffic with a specified password, requires ``cryptography`` python module.
 
   Short FAQ about Raft implementation
 
@@ -207,7 +236,7 @@ Raft
 
   - Q: It is possible to run Patroni and PostgreSQL only on two nodes?
 
-    A: Yes, on the third node you can run ``patroni_raft_controller`` (without Patroni and PostgreSQL). In such setup one can temporary loose one node without affecting the primary.
+    A: Yes, on the third node you can run ``patroni_raft_controller`` (without Patroni and PostgreSQL). In such a setup, one can temporarily lose one node without affecting the primary.
 
 
 .. _postgresql_settings:
@@ -221,6 +250,7 @@ PostgreSQL
             -  **password**: password for the superuser, set during initialization (initdb).
             -  **sslmode**: (optional) maps to the `sslmode <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLMODE>`__ connection parameter, which allows a client to specify the type of TLS negotiation mode with the server. For more information on how each mode works, please visit the `PostgreSQL documentation <https://www.postgresql.org/docs/current/libpq-ssl.html#LIBPQ-SSL-SSLMODE-STATEMENTS>`__. The default mode is ``prefer``.
             -  **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.
             -  **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.
@@ -231,6 +261,7 @@ PostgreSQL
             -  **password**: replication password; the user will be created during initialization.
             -  **sslmode**: (optional) maps to the `sslmode <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLMODE>`__ connection parameter, which allows a client to specify the type of TLS negotiation mode with the server. For more information on how each mode works, please visit the `PostgreSQL documentation <https://www.postgresql.org/docs/current/libpq-ssl.html#LIBPQ-SSL-SSLMODE-STATEMENTS>`__. The default mode is ``prefer``.
             -  **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.
             -  **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.
@@ -241,6 +272,7 @@ PostgreSQL
             -  **password**: password for the user for ``pg_rewind``; the user will be created during initialization.
             -  **sslmode**: (optional) maps to the `sslmode <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLMODE>`__ connection parameter, which allows a client to specify the type of TLS negotiation mode with the server. For more information on how each mode works, please visit the `PostgreSQL documentation <https://www.postgresql.org/docs/current/libpq-ssl.html#LIBPQ-SSL-SSLMODE-STATEMENTS>`__. The default mode is ``prefer``.
             -  **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.
             -  **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.
@@ -290,7 +322,9 @@ REST API
             -  **password**: Basic-auth password to protect unsafe REST API endpoints.
         -  **certfile**: (optional): Specifies the file with the certificate in the PEM format. If the certfile is not specified or is left empty, the API server will work without SSL.
         -  **keyfile**: (optional): Specifies the file with the secret key in the PEM format.
+        -  **keyfile_password**: (optional): Specifies a password for decrypting the keyfile.
         -  **cafile**: (optional): Specifies the file with the CA_BUNDLE with certificates of trusted CAs to use while verifying client certs.
+        -  **ciphers**: (optional): Specifies the permitted cipher suites (e.g. "ECDHE-RSA-AES256-GCM-SHA384:DHE-RSA-AES256-GCM-SHA384:ECDHE-RSA-AES128-GCM-SHA256:DHE-RSA-AES128-GCM-SHA256:!SSLv1:!SSLv2:!SSLv3:!TLSv1:!TLSv1.1")
         -  **verify\_client**: (optional): ``none`` (default), ``optional`` or ``required``. When ``none`` REST API will not check client certificates. When ``required`` client certificates are required for all REST API calls. When ``optional`` client certificates are required for all unsafe REST API endpoints. When ``required`` is used, then client authentication succeeds, if the certificate signature verification succeeds.  For ``optional`` the client cert will only be checked for ``PUT``, ``POST``, ``PATCH``, and ``DELETE`` requests.
         -  **http\_extra\_headers**: (optional): HTTP headers let the REST API server pass additional information with an HTTP response.
         -  **https\_extra\_headers**: (optional): HTTPS headers let the REST API server pass additional information with an HTTP response when TLS is enabled. This will also pass additional information set in ``http_extra_headers``.

docs/index.rst

@@ -10,6 +10,8 @@ Patroni is a template for you to create your own customized, high-availability s
 
 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 13.
+
 **Note to Kubernetes users**: Patroni can run natively on top of Kubernetes. Take a look at the :ref:`Kubernetes <kubernetes>` chapter of the Patroni documentation.
 
 
@@ -20,6 +22,7 @@ We call Patroni a "template" because it is far from being a one-size-fits-all or
    README
    dynamic_configuration
    rest_api
+   existing_data
    ENVIRONMENT
    SETTINGS
    security

docs/releases.rst

@@ -3,6 +3,150 @@
 Release notes
 =============
 
+Version 2.0.2
+-------------
+
+**New features**
+
+- Ability to ignore externally managed replication slots (James Coleman)
+
+  Patroni is trying to remove any replication slot which is unknown to it, but there are certainly cases when replication slots should be managed externally. From now on it is possible to configure slots that should not be removed.
+
+- Added support for cipher suite limitation for REST API (Gunnar "Nick" Bluth)
+
+  It could be configured via ``restapi.ciphers`` or the ``PATRONI_RESTAPI_CIPHERS`` environment variable.
+
+- Added support for encrypted TLS keys for REST API (Jonathan S. Katz)
+
+  It could be configured via ``restapi.keyfile_password`` or the ``PATRONI_RESTAPI_KEYFILE_PASSWORD`` environment variable.
+
+- Constant time comparison of REST API authentication credentials (Alex Brasetvik)
+
+  Use ``hmac.compare_digest()`` instead of ``==``, which is vulnerable to timing attack.
+
+- Choose synchronous nodes based on replication lag (Krishna Sarabu)
+
+  If the replication lag on the synchronous node starts exceeding the configured threshold it could be demoted to asynchronous and/or replaced by the other node. Behaviour is controlled with ``maximum_lag_on_syncnode``.
+
+
+**Stability improvements**
+
+- Start postgres with ``hot_standby = off`` when doing custom bootstrap (Igor Yanchenko)
+
+  During custom bootstrap Patroni is restoring the basebackup, starting Postgres up, and waiting until recovery finishes. Some PostgreSQL parameters on the standby can't be smaller than on the primary and if the new value (restored from WAL) is higher than the configured one, Postgres panics and stops. In order to avoid such behavior we will do custom bootstrap without ``hot_standby`` mode.
+
+- Warn the user if the required watchdog is not healthy (Nicolas Thauvin)
+
+  When the watchdog device is not writable or missing in required mode, the member cannot be promoted. Added a warning to show the user where to search for this misconfiguration.
+
+- Better verbosity for single-user mode recovery (Alexander Kukushkin)
+
+  If Patroni notices that PostgreSQL wasn't shutdown clearly, in certain cases the crash-recovery is executed by starting Postgres in single-user mode. It could happen that the recovery failed (for example due to the lack of space on disk) but errors were swallowed.
+
+- Added compatibility with ``python-consul2`` module (Alexander, Wilfried Roset)
+
+  The good old ``python-consul`` is not maintained since a few years, therefore someone created a fork with new features and bug-fixes.
+
+- Don't use ``bypass_api_service`` when running ``patronictl`` (Alexander)
+
+  When a K8s pod is running in a non-``default`` namespace it does not necessarily have enough permissions to query the ``kubernetes`` endpoint. In this case Patroni shows the warning and ignores the ``bypass_api_service`` setting. In case of ``patronictl`` the warning was a bit annoying.
+
+- Create ``raft.data_dir`` if it doesn't exists or make sure that it is writable (Mark Mercado)
+
+  Improves user-friendliness and usability.
+
+
+**Bugfixes**
+
+- Don't interrupt restart or promote if lost leader lock in pause (Alexander)
+
+  In pause it is allowed to run postgres as primary without lock.
+
+- Fixed issue with ``shutdown_request()`` in the REST API (Nicolas Limage)
+
+  In order to improve handling of SSL connections and delay the handshake until thread is started Patroni overrides a few methods in the ``HTTPServer``. The ``shutdown_request()`` method was forgotten.
+
+- Fixed issue with sleep time when using Zookeeper (Alexander)
+
+  There were chances that Patroni was sleeping up to twice longer between running HA code.
+
+- Fixed invalid ``os.symlink()`` calls when moving data directory after failed bootstrap (Andrew L'Ecuyer)
+
+  If the bootstrap failed Patroni is renaming data directory, pg_wal, and all tablespaces. After that it updates symlinks so filesystem remains consistent. The symlink creation was failing due to the ``src`` and ``dst`` arguments being swapped.
+
+- Fixed bug in the post_bootstrap() method (Alexander)
+
+  If the superuser password wasn't configured Patroni was failing to call the ``post_init`` script and therefore the whole bootstrap was failing.
+
+- Fixed an issues with pg_rewind in the standby cluster (Alexander)
+
+  If the superuser name is different from Postgres, the ``pg_rewind`` in the standby cluster was failing because the connection string didn't contain the database name.
+
+- Exit only if authentication with Etcd v3 explicitly failed (Alexander)
+
+  On start Patroni performs discovery of Etcd cluster topology and authenticates if it is necessarily. It could happen that one of etcd servers is not accessible, Patroni was trying to perform authentication on this server and failing instead of retrying with the next node.
+
+- Handle case with psutil cmdline() returning empty list (Alexander)
+
+  Zombie processes are still postmasters children, but they don't have cmdline()
+
+- Treat ``PATRONI_KUBERNETES_USE_ENDPOINTS`` environment variable as boolean (Alexander)
+
+  Not doing so was making impossible disabling ``kubernetes.use_endpoints`` via environment.
+
+- Improve handling of concurrent endpoint update errors (Alexander)
+
+  Patroni will explicitly query the current endpoint object, verify that the current pod still holds the leader lock and repeat the update.
+
+
+Version 2.0.1
+-------------
+
+**New features**
+
+- Use ``more`` as pager in ``patronictl edit-config`` if ``less`` is not available (Pavel Golub)
+
+  On Windows it would be the ``more.com``. In addition to that, ``cdiff`` was changed to ``ydiff`` in ``requirements.txt``, but ``patronictl`` still supports both for compatibility.
+
+- Added support of ``raft`` ``bind_addr`` and ``password`` (Alexander Kukushkin)
+
+  ``raft.bind_addr`` might be useful when running behind NAT. ``raft.password`` enables traffic encryption (requires the ``cryptography`` module).
+
+- Added ``sslpassword`` connection parameter support (Kostiantyn Nemchenko)
+
+  The connection parameter was introduced in PostgreSQL 13.
+
+**Stability improvements**
+
+- Changed the behavior in pause (Alexander)
+
+  1. Patroni will not call the ``bootstrap`` method if the ``PGDATA`` directory is missing/empty.
+  2. Patroni will not exit on sysid mismatch in pause, only log a warning.
+  3. The node will not try to grab the leader key in pause mode if Postgres is running not in recovery (accepting writes) but the sysid doesn't match with the initialize key.
+
+- Apply ``master_start_timeout`` when executing crash recovery (Alexander)
+
+  If Postgres crashed on the leader node, Patroni does a crash-recovery by starting Postgres in single-user mode. During the crash-recovery the leader lock is being updated. If the crash-recovery didn't finish in ``master_start_timeout`` seconds, Patroni will stop it forcefully and release the leader lock.
+
+- Removed the ``secure`` extra from the ``urllib3`` requirements (Alexander)
+
+  The only reason for adding it there was the ``ipaddress`` dependency for python 2.7.
+
+**Bugfixes**
+
+- Fixed a bug in the ``Kubernetes.update_leader()`` (Alexander)
+
+  An unhandled exception was preventing demoting the primary when the update of the leader object failed.
+
+- Fixed hanging ``patronictl`` when RAFT is being used (Alexander)
+
+  When using ``patronictl`` with Patroni config, ``self_addr`` should be added to the ``partner_addrs``.
+
+- Fixed bug in ``get_guc_value()`` (Alexander)
+
+  Patroni was failing to get the value of ``restore_command`` on PostgreSQL 12, therefore fetching missing WALs for ``pg_rewind`` didn't work.
+
+
 Version 2.0.0
 -------------
 

docs/replica_bootstrap.rst

@@ -143,6 +143,10 @@ possible to specify a ``basebackup`` configuration section. Same rules as with t
 namely, only long (with --) options should be specified there. Not all parameters make sense, if you override a connection
 string or provide an option to created tar-ed or compressed base backups, patroni won't be able to make a replica out
 of it. There is no validation performed on the names or values of the parameters passed to the ``basebackup`` section.
+Also note that in case symlinks are used for the WAL folder it is up to the user to specify the correct ``--waldir``
+path as an option, so that after replica buildup or re-initialization the symlink would persist. This option is supported
+only since v10 though.
+
 You can specify basebackup parameters as either a map (key-value pairs) or a list of elements, where each element
 could be either a key-value pair or a single key (for options that does not receive any values, for instance, ``--verbose``).
 Consider those 2 examples:
@@ -162,6 +166,7 @@ and
         basebackup:
             - verbose
             - max-rate: '100M'
+            - 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.
 

extras/startup-scripts/patroni.service

@@ -14,7 +14,8 @@ Group=postgres
 # Read in configuration file if it exists, otherwise proceed
 EnvironmentFile=-/etc/patroni_env.conf
 
-WorkingDirectory=~
+# the default is the user's home directory, and if you want to change it, you must provide an absolute path.
+# WorkingDirectory=/home/sameuser
 
 # Where to send early-startup messages from the server
 # This is normally controlled by the global default set by systemd

features/basic_replication.feature

@@ -28,6 +28,25 @@ Feature: basic replication
     When I issue a GET request to http://127.0.0.1:8009/async
     Then I receive a response code 200
 
+  Scenario: check stuck sync replica
+    Given I issue a PATCH request to http://127.0.0.1:8008/config with {"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 sleep for 2 seconds
+    And I issue a GET request to http://127.0.0.1:8009/sync
+    Then I receive a response code 200
+    When I issue a GET request to http://127.0.0.1:8010/async
+    Then I receive a response code 200
+    When I issue a PATCH request to http://127.0.0.1:8008/config with {"maximum_lag_on_syncnode": -1, "postgresql": {"parameters": {"synchronous_commit": "on"}}}
+    Then I receive a response code 200
+    And I drop table on postgres0
+
   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

features/environment.py

@@ -13,6 +13,8 @@ import threading
 import time
 import yaml
 
+from six.moves.BaseHTTPServer import BaseHTTPRequestHandler, HTTPServer
+
 
 @six.add_metaclass(abc.ABCMeta)
 class AbstractController(object):
@@ -176,6 +178,7 @@ class PatroniController(AbstractController):
 
         config['name'] = name
         config['postgresql']['data_dir'] = self._data_dir
+        config['postgresql']['basebackup'] = [{'checkpoint': 'fast'}]
         config['postgresql']['use_unix_socket'] = os.name != 'nt'  # windows doesn't yet support unix-domain sockets
         config['postgresql']['pgpass'] = os.path.join(tempfile.gettempdir(), 'pgpass_' + name)
         config['postgresql']['parameters'].update({
@@ -191,6 +194,8 @@ class PatroniController(AbstractController):
         if custom_config is not None:
             self.recursive_update(config, custom_config)
 
+        self.recursive_update(config, {
+            'bootstrap': {'dcs': {'postgresql': {'parameters': {'wal_keep_segments': 100}}}}})
         if config['postgresql'].get('callbacks', {}).get('on_role_change'):
             config['postgresql']['callbacks']['on_role_change'] += ' ' + str(self.__PORT)
 
@@ -558,11 +563,28 @@ class ZooKeeperController(AbstractDcsController):
             return False
 
 
+class MockExhibitor(BaseHTTPRequestHandler):
+
+    def do_GET(self):
+        self.send_response(200)
+        self.end_headers()
+        self.wfile.write(b'{"servers":["127.0.0.1"],"port":2181}')
+
+    def log_message(self, fmt, *args):
+        pass
+
+
 class ExhibitorController(ZooKeeperController):
 
     def __init__(self, context):
         super(ExhibitorController, self).__init__(context, False)
-        os.environ.update({'PATRONI_EXHIBITOR_HOSTS': 'localhost', 'PATRONI_EXHIBITOR_PORT': '8181'})
+        port = 8181
+        exhibitor = HTTPServer(('', port), MockExhibitor)
+        exhibitor.daemon_thread = True
+        exhibitor_thread = threading.Thread(target=exhibitor.serve_forever)
+        exhibitor_thread.daemon = True
+        exhibitor_thread.start()
+        os.environ.update({'PATRONI_EXHIBITOR_HOSTS': 'localhost', 'PATRONI_EXHIBITOR_PORT': str(port)})
 
 
 class RaftController(AbstractDcsController):
@@ -849,8 +871,8 @@ class WatchdogMonitor(object):
 # actions to execute on start/stop of the tests and before running invidual features
 def before_all(context):
     os.environ.update({'PATRONI_RESTAPI_USERNAME': 'username', 'PATRONI_RESTAPI_PASSWORD': 'password'})
-    context.ci = 'TRAVIS_BUILD_NUMBER' in os.environ or 'BUILD_NUMBER' in os.environ
-    context.timeout_multiplier = 2 if context.ci else 1
+    context.ci = any(a in os.environ for a in ('TRAVIS_BUILD_NUMBER', 'BUILD_NUMBER', 'GITHUB_ACTIONS'))
+    context.timeout_multiplier = 5 if context.ci else 1  # MacOS sometimes is VERY slow
     context.pctl = PatroniPoolController(context)
     context.dcs_ctl = context.pctl.known_dcs[context.pctl.dcs](context)
     context.dcs_ctl.start()

features/ignored_slots.feature

@@ -0,0 +1,61 @@
+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
+    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 {"loop_wait": 2, "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
+    # 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 3 seconds
+    # Make sure Patroni has finished telling Postgres it should be accepting writes.
+    And postgres1 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
+    # 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
+
+    When I start postgres0
+    Then "members/postgres0" key in DCS has role=replica after 3 seconds
+    And postgres0 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 3 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 3 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
+
+    # 3. After a failover the server (now a master) still has the slot.
+    When I shut down postgres0
+    Then "members/postgres1" key in DCS has role=master after 3 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

features/patroni_api.feature

@@ -61,9 +61,15 @@ Scenario: check the scheduled restart
 		And postgres0 role is the primary after 10 seconds
 
 Scenario: check API requests for the primary-replica pair in the pause mode
-	Given I run patronictl.py pause batman
+	Given I start postgres1
+	Then replication works from postgres0 to postgres1 after 20 seconds
+	When I run patronictl.py pause batman
+	Then I receive a response returncode 0
+	When I kill postmaster on postgres1
+	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
 	Then I receive a response returncode 0
-	When I start postgres1
 	Then replication works from postgres0 to postgres1 after 20 seconds
 	When I issue a GET request to http://127.0.0.1:8009/replica
 	Then I receive a response code 200

features/steps/basic_replication.py

@@ -33,6 +33,37 @@ def add_table(context, table_name, pg_name):
         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}')
+def toggle_wal_replay(context, action, pg_name):
+    # pause or resume the wal replay process
+    try:
+       version = context.pctl.query(pg_name, "select pg_catalog.pg_read_file('PG_VERSION', 0, 2)").fetchone()
+       wal = version and version[0] and int(version[0].split('.')[0]) < 10 and "xlog" or "wal"
+       context.pctl.query(pg_name, "SELECT pg_{0}_replay_{1}()".format(wal, 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}')
+def crdr_mytest(context, action, pg_name):
+    try:
+       if (action == "create"):
+           context.pctl.query(pg_name, "create table if not exists mytest(id Numeric)")
+       else:
+           context.pctl.query(pg_name, "drop table if exists mytest")
+    except pg.Error as e:
+        assert False, "Error {0} table mytest on {1}: {2}".format(action, pg_name, e)
+
+
+@step('I load data on {pg_name:w}')
+def initiate_load(context, pg_name):
+    # perform dummy load
+    try:
+       context.pctl.query(pg_name, "begin; insert into mytest select r::numeric from generate_series(1, 350000) r; commit;")
+    except pg.Error as e:
+        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')
 def table_is_present_on(context, table_name, pg_name, max_replication_delay):
     max_replication_delay *= context.timeout_multiplier

features/steps/cascading_replication.py

@@ -12,8 +12,10 @@ def start_patroni_with_a_name_value_tag(context, name, tag_name, tag_value):
 @then('There is a {label} with "{content}" in {name:w} data directory')
 def check_label(context, label, content, name):
     label = context.pctl.read_label(name, label)
+    if label is None:
+        label = ""
     label = label.replace('\n', '\\n')
-    assert content in label, "{0} doesn't contain {1}".format(label, content)
+    assert content in label, "\"{0}\" doesn't contain {1}".format(label, content)
 
 
 @step('I create label with "{content:w}" in {name:w} data directory')
@@ -25,15 +27,18 @@ def write_label(context, content, name):
 def check_member(context, name, 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(name))
-            if response.get(key) == value:
+            dcs_value = response.get(key)
+            if dcs_value == value:
                 return
         except Exception:
             pass
         time.sleep(1)
-    assert False, "{0} does not have {1}={2} in dcs after {3} seconds".format(name, key, value, time_limit)
+    assert False, "{0} does not have {1}={2} (found {3}) in dcs after {4} seconds".format(name, key, value,
+                                                                                          dcs_value, time_limit)
 
 
 @step('there is a non empty {key:w} key in DCS after {time_limit:d} seconds')

features/steps/slots.py

@@ -0,0 +1,36 @@
+from behave import step, then
+import psycopg2 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):
+    try:
+        output = context.pctl.query(pg_name, ("SELECT pg_create_logical_replication_slot('{0}', '{1}'),"
+                                              " current_database()").format(slot_name, plugin))
+        print(output.fetchone())
+    except pg.Error as e:
+        print(e)
+        assert False, "Error creating slot {0} on {1} with plugin {2}".format(slot_name, pg_name, plugin)
+
+
+@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)
+
+
+@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):
+    try:
+        row = context.pctl.query(pg_name, ("SELECT 1 FROM pg_replication_slots"
+                                           " WHERE slot_name = '{0}'").format(slot_name)).fetchone()
+        assert not row, "Found unexpected replication slot named {0}".format(slot_name)
+    except pg.Error:
+        assert False, "Error looking for slot {0} on {1}".format(slot_name, pg_name)

patroni/api.py

@@ -1,4 +1,5 @@
 import base64
+import hmac
 import json
 import logging
 import psycopg2
@@ -197,7 +198,7 @@ class RestApiHandler(BaseHTTPRequestHandler):
     def do_PATCH_config(self):
         request = self._read_json_content()
         if request:
-            cluster = self.server.patroni.dcs.get_cluster()
+            cluster = self.server.patroni.dcs.get_cluster(True)
             if not (cluster.config and cluster.config.modify_index):
                 return self.send_error(503)
             data = cluster.config.data.copy()
@@ -558,7 +559,7 @@ class RestApiServer(ThreadingMixIn, HTTPServer, Thread):
             fcntl.fcntl(fd, fcntl.F_SETFD, flags | fcntl.FD_CLOEXEC)
 
     def check_basic_auth_key(self, key):
-        return self.__auth_key == key
+        return hmac.compare_digest(self.__auth_key, key.encode('utf-8'))
 
     def check_auth_header(self, auth_header):
         if self.__auth_key:
@@ -634,7 +635,10 @@ class RestApiServer(ThreadingMixIn, HTTPServer, Thread):
         if self.__protocol == 'https':
             import ssl
             ctx = ssl.create_default_context(ssl.Purpose.CLIENT_AUTH, cafile=ssl_options.get('cafile'))
-            ctx.load_cert_chain(certfile=ssl_options['certfile'], keyfile=ssl_options.get('keyfile'))
+            if ssl_options.get('ciphers'):
+                ctx.set_ciphers(ssl_options['ciphers'])
+            ctx.load_cert_chain(certfile=ssl_options['certfile'], keyfile=ssl_options.get('keyfile'),
+                                password=ssl_options.get('keyfile_password'))
             verify_client = ssl_options.get('verify_client')
             if verify_client:
                 modes = {'none': ssl.CERT_NONE, 'optional': ssl.CERT_OPTIONAL, 'required': ssl.CERT_REQUIRED}
@@ -664,11 +668,17 @@ class RestApiServer(ThreadingMixIn, HTTPServer, Thread):
             newsock = (sock, newsock)
         return newsock, addr
 
+    def shutdown_request(self, request):
+        if isinstance(request, tuple):
+            _, request = request  # SSLSocket
+        return super(RestApiServer, self).shutdown_request(request)
+
     def reload_config(self, config):
         if 'listen' not in config:  # changing config in runtime
             raise ValueError('Can not find "restapi.listen" config')
 
-        ssl_options = {n: config[n] for n in ('certfile', 'keyfile', 'cafile') if n in config}
+        ssl_options = {n: config[n] for n in ('certfile', 'keyfile', 'keyfile_password',
+                                              'cafile', 'ciphers') if n in config}
 
         self.http_extra_headers = config.get('http_extra_headers') or {}
         self.http_extra_headers.update((config.get('https_extra_headers') or {}) if ssl_options.get('certfile') else {})
@@ -679,7 +689,7 @@ class RestApiServer(ThreadingMixIn, HTTPServer, Thread):
         if self.__listen != config['listen'] or self.__ssl_options != ssl_options:
             self.__initialize(config['listen'], ssl_options)
 
-        self.__auth_key = base64.b64encode(config['auth'].encode('utf-8')).decode('utf-8') if 'auth' in config else None
+        self.__auth_key = base64.b64encode(config['auth'].encode('utf-8')) if 'auth' in config else None
         self.connection_string = uri(self.__protocol, config.get('connect_address') or self.__listen, 'patroni')
 
     @staticmethod

patroni/config.py

@@ -21,6 +21,7 @@ _AUTH_ALLOWED_PARAMETERS = (
     'sslmode',
     'sslcert',
     'sslkey',
+    'sslpassword',
     'sslrootcert',
     'sslcrl',
     'gssencmode',
@@ -59,6 +60,7 @@ class Config(object):
     __DEFAULT_CONFIG = {
         'ttl': 30, 'loop_wait': 10, 'retry_timeout': 10,
         'maximum_lag_on_failover': 1048576,
+        'maximum_lag_on_syncnode': -1,
         'check_timeline': False,
         'master_start_timeout': 300,
         'master_stop_timeout': 0,
@@ -264,8 +266,9 @@ class Config(object):
                 if value:
                     ret[section][param] = value
 
-        _set_section_values('restapi', ['listen', 'connect_address', 'certfile', 'keyfile', 'cafile', 'verify_client',
-                                        'http_extra_headers', 'https_extra_headers'])
+        _set_section_values('restapi', ['listen', 'connect_address', 'certfile', 'keyfile', 'keyfile_password',
+                                        'cafile', 'ciphers', 'verify_client', 'http_extra_headers',
+                                        'https_extra_headers'])
         _set_section_values('ctl', ['insecure', 'cacert', 'certfile', 'keyfile'])
         _set_section_values('postgresql', ['listen', 'connect_address', 'config_dir', 'data_dir', 'pgpass', 'bin_dir'])
         _set_section_values('log', ['level', 'traceback_level', 'format', 'dateformat', 'max_queue_size',
@@ -316,7 +319,7 @@ class Config(object):
                 logger.exception('Exception when parsing list %s', value)
                 return None
 
-        _set_section_values('raft', ['data_dir', 'self_addr', 'partner_addrs'])
+        _set_section_values('raft', ['data_dir', 'self_addr', 'partner_addrs', 'password', 'bind_addr'])
         if 'raft' in ret and 'partner_addrs' in ret['raft']:
             ret['raft']['partner_addrs'] = _parse_list(ret['raft']['partner_addrs'])
 
@@ -336,7 +339,7 @@ class Config(object):
                         value = value and _parse_list(value)
                     elif suffix == 'LABELS':
                         value = _parse_dict(value)
-                    elif suffix in ('USE_PROXIES', 'REGISTER_SERVICE', 'BYPASS_API_SERVICE'):
+                    elif suffix in ('USE_PROXIES', 'REGISTER_SERVICE', 'USE_ENDPOINTS', 'BYPASS_API_SERVICE'):
                         value = parse_bool(value)
                     if value:
                         ret[name.lower()][suffix.lower()] = value
@@ -411,6 +414,7 @@ class Config(object):
             'synchronous_mode',
             'synchronous_mode_strict',
             'synchronous_node_count',
+            'maximum_lag_on_syncnode'
         )
 
         pg_config.update({p: config[p] for p in updated_fields if p in config})

patroni/ctl.py

@@ -7,7 +7,6 @@ import codecs
 import datetime
 import dateutil.parser
 import dateutil.tz
-import cdiff
 import copy
 import difflib
 import io
@@ -25,16 +24,22 @@ import yaml
 from click import ClickException
 from collections import defaultdict
 from contextlib import contextmanager
-from patroni.dcs import get_dcs as _get_dcs
-from patroni.exceptions import PatroniException
-from patroni.postgresql import Postgresql
-from patroni.postgresql.misc import postgres_version_to_int
-from patroni.utils import cluster_as_json, patch_config, polling_loop
-from patroni.request import PatroniRequest
-from patroni.version import __version__
 from prettytable import ALL, FRAME, PrettyTable
 from six.moves.urllib_parse import urlparse
 
+try:
+    from ydiff import markup_to_pager, PatchStream
+except ImportError:  # pragma: no cover
+    from cdiff import markup_to_pager, PatchStream
+
+from .dcs import get_dcs as _get_dcs
+from .exceptions import PatroniException
+from .postgresql import Postgresql
+from .postgresql.misc import postgres_version_to_int
+from .utils import cluster_as_json, find_executable, patch_config, polling_loop
+from .request import PatroniRequest
+from .version import __version__
+
 CONFIG_DIR_PATH = click.get_app_dir('patroni')
 CONFIG_FILE_PATH = os.path.join(CONFIG_DIR_PATH, 'patronictl.yaml')
 DCS_DEFAULTS = {'zookeeper': {'port': 2181, 'template': "zookeeper:\n hosts: ['{host}:{port}']"},
@@ -1086,7 +1091,14 @@ def show_diff(before_editing, after_editing):
             side_by_side = False
             width = 80
             tab_width = 8
-        cdiff.markup_to_pager(cdiff.PatchStream(buf), opts)
+            wrap = True
+            if find_executable('less'):
+                pager = None
+            else:
+                pager = 'more.com' if sys.platform == 'win32' else 'more'
+            pager_options = None
+
+        markup_to_pager(PatchStream(buf), opts)
     else:
         for line in unified_diff:
             click.echo(line.rstrip('\n'))
@@ -1161,24 +1173,6 @@ def apply_yaml_file(data, filename):
     return format_config_for_editing(changed_data), changed_data
 
 
-def find_executable(executable, path=None):
-    _, ext = os.path.splitext(executable)
-
-    if (sys.platform == 'win32') and (ext != '.exe'):
-        executable = executable + '.exe'
-
-    if os.path.isfile(executable):
-        return executable
-
-    if path is None:
-        path = os.environ.get('PATH', os.defpath)
-
-    for p in path.split(os.pathsep):
-        f = os.path.join(p, executable)
-        if os.path.isfile(f):
-            return f
-
-
 def invoke_editor(before_editing, cluster_name):
     """Starts editor command to edit configuration in human readable format
 

patroni/dcs/__init__.py

@@ -341,6 +341,10 @@ class ClusterConfig(namedtuple('ClusterConfig', 'index,data,modify_index')):
                 self.data.get('permanent_slots') or self.data.get('slots')
         ) or {}
 
+    @property
+    def ignore_slots_matchers(self):
+        return isinstance(self.data, dict) and self.data.get('ignore_slots') or []
+
     @property
     def max_timelines_history(self):
         return self.data.get('max_timelines_history', 0)

patroni/dcs/consul.py

@@ -8,6 +8,7 @@ import ssl
 import time
 import urllib3
 
+from collections import namedtuple
 from consul import ConsulException, NotFound, base
 from urllib3.exceptions import HTTPError
 from six.moves.urllib.parse import urlencode, urlparse, quote
@@ -36,6 +37,9 @@ class InvalidSession(ConsulException):
     """invalid session"""
 
 
+Response = namedtuple('Response', 'code,headers,body,content')
+
+
 class HTTPClient(object):
 
     def __init__(self, host='127.0.0.1', port=8500, token=None, scheme='http', verify=True, cert=None, ca_cert=None):
@@ -71,16 +75,17 @@ class HTTPClient(object):
 
     @staticmethod
     def response(response):
-        data = response.data.decode('utf-8')
+        content = response.data
+        body = content.decode('utf-8')
         if response.status == 500:
-            msg = '{0} {1}'.format(response.status, data)
-            if data.startswith('Invalid Session TTL'):
+            msg = '{0} {1}'.format(response.status, body)
+            if body.startswith('Invalid Session TTL'):
                 raise InvalidSessionTTL(msg)
-            elif data.startswith('invalid session'):
+            elif body.startswith('invalid session'):
                 raise InvalidSession(msg)
             else:
                 raise ConsulInternalError(msg)
-        return base.Response(response.status, response.headers, data)
+        return Response(response.status, response.headers, body, content)
 
     def uri(self, path, params=None):
         return '{0}{1}{2}'.format(self.base_uri, path, params and '?' + urlencode(params) or '')
@@ -89,7 +94,7 @@ class HTTPClient(object):
         if method not in ('get', 'post', 'put', 'delete'):
             raise AttributeError("HTTPClient instance has no attribute '{0}'".format(method))
 
-        def wrapper(callback, path, params=None, data=''):
+        def wrapper(callback, path, params=None, data='', headers=None):
             # python-consul doesn't allow to specify ttl smaller then 10 seconds
             # because session_ttl_min defaults to 10s, so we have to do this ugly dirty hack...
             if method == 'put' and path == '/v1/session/create':
@@ -110,8 +115,9 @@ class HTTPClient(object):
                 kwargs['timeout'] = timeout + max(timeout/15.0, 1)
             else:
                 kwargs['timeout'] = self._read_timeout
+            kwargs['headers'] = (headers or {}).copy()
+            kwargs['headers'].update(urllib3.make_headers(user_agent=USER_AGENT))
             token = params.pop('token', self.token) if isinstance(params, dict) else self.token
-            kwargs['headers'] = urllib3.make_headers(user_agent=USER_AGENT)
             if token:
                 kwargs['headers']['X-Consul-Token'] = token
             return callback(self.response(self.http.request(method.upper(), self.uri(path, params), **kwargs)))
@@ -126,7 +132,7 @@ class ConsulClient(base.Consul):
         self.token = kwargs.get('token')
         super(ConsulClient, self).__init__(*args, **kwargs)
 
-    def connect(self, *args, **kwargs):
+    def http_connect(self, *args, **kwargs):
         kwargs.update(dict(zip(['host', 'port', 'scheme', 'verify'], args)))
         if self._cert:
             kwargs['cert'] = self._cert
@@ -136,6 +142,9 @@ class ConsulClient(base.Consul):
             kwargs['token'] = self.token
         return HTTPClient(**kwargs)
 
+    def connect(self, *args, **kwargs):
+        return self.http_connect(*args, **kwargs)
+
     def reload_config(self, config):
         self.http.token = self.token = config.get('token')
         self.consistency = config.get('consistency', 'default')

patroni/dcs/etcd.py

@@ -404,7 +404,7 @@ class EtcdClient(AbstractEtcdClientWithFailover):
         if self.http is not None:
             try:
                 self.http.clear()
-            except (ReferenceError, TypeError):
+            except (ReferenceError, TypeError, AttributeError):
                 pass
 
     def _prepare_get_members(self, etcd_nodes):

patroni/dcs/etcd3.py

@@ -98,6 +98,10 @@ class UserEmpty(InvalidArgument):
     error = "etcdserver: user name is empty"
 
 
+class AuthFailed(InvalidArgument):
+    error = "etcdserver: authentication failed, invalid user ID or password"
+
+
 class PermissionDenied(Etcd3ClientError):
     code = GRPCCode.PermissionDenied
     error = "etcdserver: permission denied"
@@ -186,7 +190,7 @@ class Etcd3Client(AbstractEtcdClientWithFailover):
 
         try:
             self.authenticate()
-        except Exception as e:
+        except AuthFailed as e:
             logger.fatal('Etcd3 authentication failed: %r', e)
             sys.exit(1)
 

patroni/dcs/kubernetes.py

@@ -631,7 +631,8 @@ class Kubernetes(AbstractDCS):
             port.update({n: p[n] for n in ('name', 'protocol') if p.get(n)})
             self.__ports.append(k8s_client.V1EndpointPort(**port))
 
-        self._api = CoreV1ApiProxy(config.get('use_endpoints'), config.get('bypass_api_service'))
+        bypass_api_service = not config.get('patronictl') and config.get('bypass_api_service')
+        self._api = CoreV1ApiProxy(config.get('use_endpoints'), bypass_api_service)
         self._should_create_config_service = self._api.use_endpoints
         self.reload_config(config)
         # leader_observed_record, leader_resource_version, and leader_observed_time are used only for leader race!
@@ -901,16 +902,26 @@ class Kubernetes(AbstractDCS):
             else:
                 logger.exception('Permission denied' if e.status == 403 else 'Unexpected error from Kubernetes API')
                 return False
-        except RetryFailedError:
+        except (RetryFailedError, K8sException):
             return False
 
-        deadline = retry.stoptime - time.time()
-        if deadline < 2:
+        retry.deadline = retry.stoptime - time.time()
+        if retry.deadline < 1:
             return False
 
-        retry.sleep_func(1)  # Give a chance for ObjectCache to receive the latest version
+        # Try to get the latest version directly from K8s API instead of relying on async cache
+        try:
+            kind = retry(self._api.read_namespaced_kind, self.leader_path, self._namespace)
+        except Exception as e:
+            logger.error('Failed to get the leader object "%s": %r', self.leader_path, e)
+            return False
+
+        self._kinds.set(self.leader_path, kind)
+
+        retry.deadline = retry.stoptime - time.time()
+        if retry.deadline < 0.5:
+            return False
 
-        kind = self._kinds.get(self.leader_path)
         kind_annotations = kind and kind.metadata.annotations or {}
         kind_resource_version = kind and kind.metadata.resource_version
 
@@ -918,7 +929,6 @@ class Kubernetes(AbstractDCS):
         if kind and (kind_annotations.get(self._LEADER) != self._name or kind_resource_version == resource_version):
             return False
 
-        retry.deadline = deadline - 1  # Update deadline and retry
         return self.patch_or_create(self.leader_path, annotations, kind_resource_version, ips=ips, retry=_retry)
 
     def update_leader(self, last_operation, access_is_restricted=False):

patroni/dcs/raft.py

@@ -5,6 +5,7 @@ import threading
 import time
 
 from patroni.dcs import AbstractDCS, ClusterConfig, Cluster, Failover, Leader, Member, SyncState, TimelineHistory
+from ..utils import validate_directory
 from pysyncobj import SyncObj, SyncObjConf, replicated, FAIL_REASON
 from pysyncobj.transport import Node, TCPTransport, CONNECTION_STATE
 
@@ -87,15 +88,14 @@ class DynMemberSyncObj(SyncObj):
 
     def __init__(self, selfAddress, partnerAddrs, conf):
         add_self = False
-        if selfAddress:
-            utility = SyncObjUtility(partnerAddrs, conf)
-            for node in utility._SyncObj__otherNodes:
-                utility.setPartnerNode(node)
-                response = utility.sendMessage(['members'])
-                if response:
-                    partnerAddrs = [member['addr'] for member in response if member['addr'] != selfAddress]
-                    add_self = len(partnerAddrs) == len(response)
-                    break
+        utility = SyncObjUtility(partnerAddrs, conf)
+        for node in utility._SyncObj__otherNodes:
+            utility.setPartnerNode(node)
+            response = utility.sendMessage(['members'])
+            if response:
+                partnerAddrs = [member['addr'] for member in response if member['addr'] != selfAddress]
+                add_self = selfAddress and len(partnerAddrs) == len(response)
+                break
 
         super(DynMemberSyncObj, self).__init__(selfAddress, partnerAddrs, conf, transportClass=MyTCPTransport)
         if add_self:
@@ -269,14 +269,27 @@ class Raft(AbstractDCS):
         super(Raft, self).__init__(config)
         self._ttl = int(config.get('ttl') or 30)
 
-        self_addr = None if self._ctl else config.get('self_addr')
-        template = os.path.join(config.get('data_dir', ''), self_addr or '')
-        files = {'journalFile': template + '.journal', 'fullDumpFile': template + '.dump'} if self_addr else {}
+        self_addr = config.get('self_addr')
+        partner_addrs = config.get('partner_addrs', [])
+        if self._ctl:
+            if self_addr:
+                partner_addrs.append(self_addr)
+            self_addr = None
+
+        # Create raft data_dir if necessary
+        raft_data_dir = config.get('data_dir', '')
+        if raft_data_dir != '':
+            validate_directory(raft_data_dir)
 
         ready_event = threading.Event()
-        conf = SyncObjConf(commandsWaitLeader=False, appendEntriesUseBatch=False, onReady=ready_event.set,
-                           dynamicMembershipChange=True, **files)
-        self._sync_obj = KVStoreTTL(self_addr, config.get('partner_addrs', []), conf, self._on_set, self._on_delete)
+        file_template = os.path.join(config.get('data_dir', ''), (self_addr or ''))
+        conf = SyncObjConf(password=config.get('password'), appendEntriesUseBatch=False,
+                           bindAddress=config.get('bind_addr'), commandsWaitLeader=False,
+                           fullDumpFile=(file_template + '.dump' if self_addr else None),
+                           journalFile=(file_template + '.journal' if self_addr else None),
+                           onReady=ready_event.set, dynamicMembershipChange=True)
+
+        self._sync_obj = KVStoreTTL(self_addr, partner_addrs, conf, self._on_set, self._on_delete)
         while True:
             ready_event.wait(5)
             if ready_event.isSet() or self._sync_obj.applied_local_log:

patroni/dcs/zookeeper.py

@@ -123,13 +123,14 @@ class ZooKeeper(AbstractDCS):
         # the same time, set_ttl method will reestablish connection and return
         # `!True`, otherwise we will close existing connection and let kazoo
         # open the new one.
-        if not self.set_ttl(int(config['ttl'] * 1000)) and loop_wait_changed:
+        if not self.set_ttl(config['ttl']) and loop_wait_changed:
             self._client._connection._socket.close()
 
     def set_ttl(self, ttl):
         """It is not possible to change ttl (session_timeout) in zookeeper without
         destroying old session and creating the new one. This method returns `!True`
         if session_timeout has been changed (`restart()` has been called)."""
+        ttl = int(ttl * 1000)
         if self._client._session_timeout != ttl:
             self._client._session_timeout = ttl
             self._client.restart()
@@ -137,7 +138,7 @@ class ZooKeeper(AbstractDCS):
 
     @property
     def ttl(self):
-        return self._client._session_timeout
+        return self._client._session_timeout / 1000.0
 
     def set_retry_timeout(self, retry_timeout):
         retry = self._client.retry if isinstance(self._client.retry, KazooRetry) else self._client._retry
@@ -372,6 +373,7 @@ class ZooKeeper(AbstractDCS):
         return self.set_sync_state_value("{}", index)
 
     def watch(self, leader_index, timeout):
-        if super(ZooKeeper, self).watch(leader_index, timeout) and not self._fetch_optime:
+        ret = super(ZooKeeper, self).watch(leader_index, timeout)
+        if ret and not self._fetch_optime:
             self._fetch_cluster = True
-        return self._fetch_cluster
+        return ret or self._fetch_cluster

patroni/ha.py

@@ -72,6 +72,7 @@ class Ha(object):
         self.recovering = False
         self._async_response = CriticalTask()
         self._crash_recovery_executed = False
+        self._crash_recovery_started = None
         self._start_timeout = None
         self._async_executor = AsyncExecutor(self.state_handler.cancellable, self.wakeup)
         self.watchdog = patroni.watchdog
@@ -156,7 +157,11 @@ class Ha(object):
                 last_operation = self.state_handler.last_operation()
             except Exception:
                 logger.exception('Exception when called state_handler.last_operation()')
-        ret = self.dcs.update_leader(last_operation, self._leader_access_is_restricted)
+        try:
+            ret = self.dcs.update_leader(last_operation, self._leader_access_is_restricted)
+        except Exception:
+            logger.exception('Unexpected exception raised from update_leader, please report it as a BUG')
+            ret = False
         self.set_is_leader(ret)
         if ret:
             self.watchdog.keepalive()
@@ -329,6 +334,7 @@ class Ha(object):
                 and not self._crash_recovery_executed and \
                 (self.cluster.is_unlocked() or self._rewind.can_rewind):
             self._crash_recovery_executed = True
+            self._crash_recovery_started = time.time()
             msg = 'doing crash recovery in a single user mode'
             return self._async_executor.try_run_async(msg, self._rewind.ensure_clean_shutdown) or msg
 
@@ -454,7 +460,9 @@ class Ha(object):
         if self.is_synchronous_mode():
             sync_node_count = self.patroni.config['synchronous_node_count']
             current = self.cluster.sync.leader and self.cluster.sync.members or []
-            picked, allow_promote = self.state_handler.pick_synchronous_standby(self.cluster, sync_node_count)
+            picked, allow_promote = self.state_handler.pick_synchronous_standby(self.cluster, sync_node_count,
+                                                                                self.patroni.config[
+                                                                                    'maximum_lag_on_syncnode'])
             if set(picked) != set(current):
                 # update synchronous standby list in dcs temporarily to point to common nodes in current and picked
                 sync_common = list(set(current).intersection(set(allow_promote)))
@@ -478,7 +486,9 @@ class Ha(object):
                     # Wait for PostgreSQL to enable synchronous mode and see if we can immediately set sync_standby
                     time.sleep(2)
                     _, allow_promote = self.state_handler.pick_synchronous_standby(self.cluster,
-                                                                                   sync_node_count)
+                                                                                   sync_node_count,
+                                                                                   self.patroni.config[
+                                                                                       'maximum_lag_on_syncnode'])
                 if allow_promote and set(allow_promote) != set(sync_common):
                     try:
                         cluster = self.dcs.get_cluster()
@@ -761,8 +771,10 @@ class Ha(object):
         if self.state_handler.is_starting():  # postgresql still starting up is unhealthy
             return False
 
-        if self.state_handler.is_leader():  # leader is always the healthiest
-            return True
+        if self.state_handler.is_leader():
+            # in pause leader is the healthiest only when no initialize or sysid matches with initialize!
+            return not self.is_paused() or not self.cluster.initialize\
+                    or self.state_handler.sysid == self.cluster.initialize
 
         if self.is_paused():
             return False
@@ -774,6 +786,7 @@ class Ha(object):
             return self.manual_failover_process_no_leader()
 
         if not self.watchdog.is_healthy:
+            logger.warning('Watchdog device is not usable')
             return False
 
         # When in sync mode, only last known master and sync standby are allowed to promote automatically.
@@ -1165,8 +1178,16 @@ class Ha(object):
         Figure out what to do with the task AsyncExecutor is performing.
         """
         if self.has_lock() and self.update_lock():
+            if self._async_executor.scheduled_action == 'doing crash recovery in a single user mode':
+                time_left = self.patroni.config['master_start_timeout'] - (time.time() - self._crash_recovery_started)
+                if time_left <= 0 and self.is_failover_possible(self.cluster.members):
+                    logger.info("Demoting self because crash recovery is taking too long")
+                    self.state_handler.cancellable.cancel(True)
+                    self.demote('immediate')
+                    return 'terminated crash recovery because of startup timeout'
+
             return 'updated leader lock during ' + self._async_executor.scheduled_action
-        elif not self.state_handler.bootstrapping:
+        elif not self.state_handler.bootstrapping and not self.is_paused():
             # Don't have lock, make sure we are not promoting or starting up a master in the background
             if self._async_executor.scheduled_action == 'promote':
                 with self._async_response:
@@ -1348,6 +1369,8 @@ class Ha(object):
                     self.release_leader_key_voluntarily()
                     return 'released leader key voluntarily as data dir empty and currently leader'
 
+                if self.is_paused():
+                    return 'running with empty data directory'
                 return self.bootstrap()  # new node
             else:
                 # check if we are allowed to join
@@ -1359,9 +1382,16 @@ class Ha(object):
 
                 if self.sysid_valid(self.cluster.initialize):
                     if self.cluster.initialize != data_sysid:
-                        logger.fatal("system ID mismatch, node %s belongs to a different cluster: %s != %s",
-                                     self.state_handler.name, self.cluster.initialize, data_sysid)
-                        sys.exit(1)
+                        if self.is_paused():
+                            logger.warning('system ID has changed while in paused mode. Patroni will exit when resuming'
+                                           ' unless system ID is reset: %s != %s', self.cluster.initialize, data_sysid)
+                            if self.has_lock():
+                                self.release_leader_key_voluntarily()
+                                return 'released leader key voluntarily due to the system ID mismatch'
+                        else:
+                            logger.fatal('system ID mismatch, node %s belongs to a different cluster: %s != %s',
+                                         self.state_handler.name, self.cluster.initialize, data_sysid)
+                            sys.exit(1)
                 elif self.cluster.is_unlocked() and not self.is_paused():
                     # "bootstrap", but data directory is not empty
                     if not self.state_handler.cb_called and self.state_handler.is_running() \

patroni/postgresql/__init__.py

@@ -459,6 +459,8 @@ class Postgresql(object):
         self._pending_restart = False
 
         try:
+            if not self._major_version:
+                self.configure_server_parameters()
             configuration = self.config.effective_configuration
         except Exception:
             return None
@@ -698,7 +700,7 @@ class Postgresql(object):
         return True
 
     def get_guc_value(self, name):
-        cmd = [self.pgcommand('postgres'), self._data_dir, '-C', name]
+        cmd = [self.pgcommand('postgres'), '-D', self._data_dir, '-C', name]
         try:
             data = subprocess.check_output(cmd)
             if data:
@@ -913,7 +915,7 @@ class Postgresql(object):
                     new_name = '{0}_{1}'.format(pg_wal_realpath, postfix)
                     os.rename(pg_wal_realpath, new_name)
                     os.unlink(source)
-                    os.symlink(source, new_name)
+                    os.symlink(new_name, source)
 
                 # Move user defined tablespace directory
                 for (source, pg_tsp_rpath) in self.pg_tblspc_realpaths().items():
@@ -921,7 +923,7 @@ class Postgresql(object):
                     new_name = '{0}_{1}'.format(pg_tsp_rpath, postfix)
                     os.rename(pg_tsp_rpath, new_name)
                     os.unlink(source)
-                    os.symlink(source, new_name)
+                    os.symlink(new_name, source)
 
                 new_name = '{0}_{1}'.format(self._data_dir, postfix)
                 logger.info('renaming data directory to %s', new_name)
@@ -960,11 +962,15 @@ class Postgresql(object):
     def _get_synchronous_commit_param(self):
         return self.query("SHOW synchronous_commit").fetchone()[0]
 
-    def pick_synchronous_standby(self, cluster, sync_node_count=1):
+    def pick_synchronous_standby(self, cluster, sync_node_count=1, sync_node_maxlag=-1):
         """Finds the best candidate to be the synchronous standby.
 
         Current synchronous standby is always preferred, unless it has disconnected or does not want to be a
         synchronous standby any longer.
+        Parameter sync_node_maxlag(maximum_lag_on_syncnode) would help swapping unhealthy sync replica incase
+        if it stops responding (or hung). Please set the value high enough so it won't unncessarily swap sync
+        standbys during high loads. Any less or equal of 0 value keep the behavior backward compatible and
+        will not swap. Please note that it will not also swap sync standbys in case where all replicas are hung.
 
         :returns tuple of candidates list and synchronous standby list.
         """
@@ -973,6 +979,7 @@ class Postgresql(object):
         members = {m.name.lower(): m for m in cluster.members}
         candidates = []
         sync_nodes = []
+        replica_list = []
         # Pick candidates based on who has higher replay/remote_write/flush lsn.
         sync_commit_par = self._get_synchronous_commit_param()
         sort_col = {'remote_apply': 'replay', 'remote_write': 'write'}.get(sync_commit_par, 'flush')
@@ -982,17 +989,22 @@ class Postgresql(object):
         # receiving changes faster than the sync member (very rare but possible). Such cases would
         # trigger sync standby member swapping frequently and the sort on sync_state desc should
         # help in keeping the query result consistent.
-        for app_name, state, sync_state in self.query(
-                "SELECT pg_catalog.lower(application_name), state, sync_state"
+        for app_name, sync_state, replica_lsn in self.query(
+                "SELECT pg_catalog.lower(application_name), sync_state, pg_{2}_{1}_diff({0}_{1}, '0/0')::bigint"
                 " FROM pg_catalog.pg_stat_replication"
                 " WHERE state = 'streaming'"
-                " ORDER BY sync_state DESC, {0}_{1} DESC".format(sort_col, self.lsn_name)):
+                " ORDER BY sync_state DESC, {0}_{1} DESC".format(sort_col, self.lsn_name, self.wal_name)):
             member = members.get(app_name)
-            if not member or member.tags.get('nosync', False):
-                continue
-            candidates.append(member.name)
-            if sync_state == 'sync':
-                sync_nodes.append(member.name)
+            if member and not member.tags.get('nosync', False):
+                replica_list.append((member.name, sync_state, replica_lsn))
+
+        max_lsn = max(replica_list, key=lambda x: x[2])[2] if len(replica_list) > 1 else int(str(self.last_operation()))
+
+        for app_name, sync_state, replica_lsn in replica_list:
+            if sync_node_maxlag <= 0 or max_lsn - replica_lsn <= sync_node_maxlag:
+                candidates.append(app_name)
+                if sync_state == 'sync':
+                    sync_nodes.append(app_name)
             if len(candidates) >= sync_node_count:
                 break
 
@@ -1001,8 +1013,11 @@ class Postgresql(object):
     def schedule_sanity_checks_after_pause(self):
         """
             After coming out of pause we have to:
-            1. sync replication slots, because it might happen that slots were removed
-            2. get new 'Database system identifier' to make sure that it wasn't changed
+            1. configure server parameters if necessary
+            2. sync replication slots, because it might happen that slots were removed
+            3. get new 'Database system identifier' to make sure that it wasn't changed
         """
+        if not self._major_version:
+            self.configure_server_parameters()
         self.slots_handler.schedule()
         self._sysid = None

patroni/postgresql/bootstrap.py

@@ -130,7 +130,7 @@ class Bootstrap(object):
                 # (pghost empty or the default socket directory) connections coming from the local machine.
                 r['host'] = 'localhost'  # set it to localhost to write into pgpass
 
-            env = self._postgresql.config.write_pgpass(r) if 'password' in r else None
+            env = self._postgresql.config.write_pgpass(r)
             env['PGOPTIONS'] = '-c synchronous_commit=local'
 
             try:

patroni/postgresql/cancellable.py

@@ -114,7 +114,7 @@ class CancellableSubprocess(CancellableExecutor):
         with self._lock:
             return self._is_cancelled
 
-    def cancel(self):
+    def cancel(self, kill=False):
         with self._lock:
             self._is_cancelled = True
             if self._process is None or not self._process.is_running():
@@ -127,5 +127,7 @@ class CancellableSubprocess(CancellableExecutor):
             with self._lock:
                 if self._process is None or not self._process.is_running():
                     return
+            if kill:
+                break
 
         self._kill_process()

patroni/postgresql/config.py

@@ -387,6 +387,11 @@ class ConfigHandler(object):
         if 'custom_conf' not in self._config and not os.path.exists(self._postgresql_base_conf):
             os.rename(self._postgresql_conf, self._postgresql_base_conf)
 
+        # In case we are using custom bootstrap from spilo image with PITR it fails if it contains increasing
+        # values like Max_connections. We disable hot_standby so it will accept increasing values.
+        if self._postgresql.bootstrap.running_custom_bootstrap:
+            configuration['hot_standby'] = 'off'
+
         with ConfigWriter(self._postgresql_conf) as f:
             include = self._config.get('custom_conf') or self._postgresql_base_conf_name
             f.writeline("include '{0}'\n".format(ConfigWriter.escape(include)))
@@ -478,7 +483,7 @@ class ConfigHandler(object):
     def format_dsn(self, params, include_dbname=False):
         # A list of keywords that can be found in a conninfo string. Follows what is acceptable by libpq
         keywords = ('dbname', 'user', 'passfile' if params.get('passfile') else 'password', 'host', 'port',
-                    'sslmode', 'sslcompression', 'sslcert', 'sslkey', 'sslrootcert', 'sslcrl',
+                    'sslmode', 'sslcompression', 'sslcert', 'sslkey', 'sslpassword', 'sslrootcert', 'sslcrl',
                     'application_name', 'krbsrvname', 'gssencmode', 'channel_binding')
         if include_dbname:
             params = params.copy()

patroni/postgresql/postmaster.py

@@ -187,10 +187,10 @@ class PostmasterProcess(psutil.Process):
         user_backends_cmdlines = []
         for child in children:
             try:
-                cmdline = child.cmdline()[0]
-                if not aux_proc_re.match(cmdline):
+                cmdline = child.cmdline()
+                if cmdline and not aux_proc_re.match(cmdline[0]):
                     user_backends.append(child)
-                    user_backends_cmdlines.append(cmdline)
+                    user_backends_cmdlines.append(cmdline[0])
             except psutil.NoSuchProcess:
                 pass
         if user_backends:

patroni/postgresql/rewind.py

@@ -1,5 +1,6 @@
 import logging
 import os
+import shlex
 import six
 import subprocess
 
@@ -58,11 +59,10 @@ class Rewind(object):
         if self.can_rewind_or_reinitialize_allowed and self._state != REWIND_STATUS.NEED:
             self._state = REWIND_STATUS.CHECK
 
-    def check_leader_is_not_in_recovery(self, **kwargs):
-        if not kwargs.get('database'):
-            kwargs['database'] = self._postgresql.database
+    @staticmethod
+    def check_leader_is_not_in_recovery(conn_kwargs):
         try:
-            with get_connection_cursor(connect_timeout=3, options='-c statement_timeout=2000', **kwargs) as cur:
+            with get_connection_cursor(connect_timeout=3, options='-c statement_timeout=2000', **conn_kwargs) as cur:
                 cur.execute('SELECT pg_catalog.pg_is_in_recovery()')
                 if not cur.fetchone()[0]:
                     return True
@@ -164,6 +164,12 @@ class Rewind(object):
 
         logger.info('master: history=%s', '\n'.join(history_show))
 
+    def _conn_kwargs(self, member, auth):
+        ret = member.conn_kwargs(auth)
+        if not ret.get('database'):
+            ret['database'] = self._postgresql.database
+        return ret
+
     def _check_timeline_and_lsn(self, leader):
         in_recovery, local_timeline, local_lsn = self._get_local_timeline_lsn()
         if local_timeline is None or local_lsn is None:
@@ -173,7 +179,7 @@ class Rewind(object):
             if leader.member.data.get('role') != 'master':
                 return
         # standby cluster
-        elif not self.check_leader_is_not_in_recovery(**leader.conn_kwargs(self._postgresql.config.replication)):
+        elif not self.check_leader_is_not_in_recovery(self._conn_kwargs(leader, self._postgresql.config.replication)):
             return
 
         history = need_rewind = None
@@ -273,7 +279,7 @@ class Rewind(object):
             i += 1
 
         logger.info('Trying to fetch the missing wal: %s', cmd)
-        return self._postgresql.cancellable.call(cmd, shell=True) == 0
+        return self._postgresql.cancellable.call(shlex.split(cmd)) == 0
 
     def _find_missing_wal(self, data):
         # could not open file "$PGDATA/pg_wal/0000000A00006AA100000068": No such file or directory
@@ -332,7 +338,7 @@ class Rewind(object):
             return logger.warning('Can not run pg_rewind because postgres is still running')
 
         # prepare pg_rewind connection
-        r = leader.conn_kwargs(self._postgresql.config.rewind_credentials)
+        r = self._conn_kwargs(leader, self._postgresql.config.rewind_credentials)
 
         # 1. make sure that we are really trying to rewind from the master
         # 2. make sure that pg_control contains the new timeline by:
@@ -340,17 +346,17 @@ class Rewind(object):
         #   waiting until Patroni on the master will expose checkpoint_after_promote=True
         checkpoint_status = leader.checkpoint_after_promote if isinstance(leader, Leader) else None
         if checkpoint_status is None:  # master still runs the old Patroni
-            leader_status = self._postgresql.checkpoint(leader.conn_kwargs(self._postgresql.config.superuser))
+            leader_status = self._postgresql.checkpoint(self._conn_kwargs(leader, self._postgresql.config.superuser))
             if leader_status:
                 return logger.warning('Can not use %s for rewind: %s', leader.name, leader_status)
         elif not checkpoint_status:
             return logger.info('Waiting for checkpoint on %s before rewind', leader.name)
-        elif not self.check_leader_is_not_in_recovery(**r):
+        elif not self.check_leader_is_not_in_recovery(r):
             return
 
         if self.pg_rewind(r):
             self._state = REWIND_STATUS.SUCCESS
-        elif not self.check_leader_is_not_in_recovery(**r):
+        elif not self.check_leader_is_not_in_recovery(r):
             logger.warning('Failed to rewind because master %s become unreachable', leader.name)
         else:
             logger.error('Failed to rewind from healty master: %s', leader.name)
@@ -427,4 +433,10 @@ class Rewind(object):
         opts = self.read_postmaster_opts()
         opts.update({'archive_mode': 'on', 'archive_command': 'false'})
         self._postgresql.config.remove_recovery_conf()
-        return self.single_user_mode(options=opts) == 0 or None
+        output = {}
+        ret = self.single_user_mode(communicate=output, options=opts)
+        if ret != 0:
+            logger.error('Crash recovery finished with code=%s', ret)
+            logger.info(' stdout=%s', output['stdout'].decode('utf-8'))
+            logger.info(' stderr=%s', output['stderr'].decode('utf-8'))
+        return ret == 0 or None

patroni/postgresql/slots.py

@@ -33,6 +33,14 @@ class SlotsHandler(object):
             self._replication_slots = replication_slots
             self._schedule_load_slots = False
 
+    def ignore_replication_slot(self, cluster, name):
+        slot = self._replication_slots[name]
+        for matcher in cluster.config.ignore_slots_matchers:
+            if ((matcher.get("name") is None or matcher["name"] == name)
+               and all(not matcher.get(a) or matcher[a] == slot.get(a) for a in ('database', 'plugin', 'type'))):
+                return True
+        return False
+
     def drop_replication_slot(self, name):
         cursor = self._query(('SELECT pg_catalog.pg_drop_replication_slot(%s) WHERE EXISTS (SELECT 1 ' +
                               'FROM pg_catalog.pg_replication_slots WHERE slot_name = %s AND NOT active)'), name, name)
@@ -40,7 +48,7 @@ class SlotsHandler(object):
         return cursor.rowcount == 1
 
     def sync_replication_slots(self, cluster):
-        if self._postgresql.major_version >= 90400:
+        if self._postgresql.major_version >= 90400 and cluster.config:
             try:
                 self.load_replication_slots()
 
@@ -48,7 +56,7 @@ class SlotsHandler(object):
 
                 # drop old replication slots which are not presented in desired slots
                 for name in set(self._replication_slots) - set(slots):
-                    if not self.drop_replication_slot(name):
+                    if not self.ignore_replication_slot(cluster, name) and not self.drop_replication_slot(name):
                         logger.error("Failed to drop replication slot '%s'", name)
                         self._schedule_load_slots = True
 

patroni/postgresql/validator.py

@@ -484,7 +484,7 @@ recovery_parameters = CaseInsensitiveDict({
     'promote_trigger_file': String(120000, None),
     'recovery_end_command': String(90300, None),
     'recovery_min_apply_delay': Integer(90400, None, 0, 2147483647, 'ms'),
-    'recovery_target': Enum(90400, None, ('immediate',)),
+    'recovery_target': Enum(90400, None, ('immediate', '')),
     'recovery_target_action': Enum(90500, None, ('pause', 'promote', 'shutdown')),
     'recovery_target_inclusive': Bool(90300, None),
     'recovery_target_lsn': String(100000, None),

patroni/utils.py

@@ -1,3 +1,4 @@
+import errno
 import json.decoder as json_decoder
 import logging
 import os
@@ -461,7 +462,8 @@ def validate_directory(d, msg="{} {}"):
             os.makedirs(d)
         except OSError as e:
             logger.error(e)
-            raise PatroniException(msg.format(d, "couldn't create the directory"))
+            if e.errno != errno.EEXIST:
+                raise PatroniException(msg.format(d, "couldn't create the directory"))
     elif os.path.isdir(d):
         try:
             fd, tmpfile = tempfile.mkstemp(dir=d)
@@ -512,3 +514,21 @@ def enable_keepalive(sock, timeout, idle, cnt=3):
 
     for opt in keepalive_socket_options(timeout, idle, cnt):
         sock.setsockopt(*opt)
+
+
+def find_executable(executable, path=None):
+    _, ext = os.path.splitext(executable)
+
+    if (sys.platform == 'win32') and (ext != '.exe'):
+        executable = executable + '.exe'
+
+    if os.path.isfile(executable):
+        return executable
+
+    if path is None:
+        path = os.environ.get('PATH', os.defpath)
+
+    for p in path.split(os.pathsep):
+        f = os.path.join(p, executable)
+        if os.path.isfile(f):
+            return f

patroni/validator.py

@@ -4,12 +4,12 @@ import socket
 import re
 import subprocess
 
-from patroni.utils import split_host_port, data_directory_is_empty
-from patroni.ctl import find_executable
-from patroni.dcs import dcs_modules
-from patroni.exceptions import ConfigParseError
 from six import string_types
 
+from .utils import find_executable, split_host_port, data_directory_is_empty
+from .dcs import dcs_modules
+from .exceptions import ConfigParseError
+
 
 def data_directory_empty(data_dir):
     if os.path.isfile(os.path.join(data_dir, "global", "pg_control")):
@@ -53,11 +53,15 @@ def validate_host_port(host_port, listen=False, multiple_hosts=False):
     return True
 
 
-def comma_separated_host_port(string):
-    assert all([validate_host_port(s.strip()) for s in string.split(",")]), "didn't pass the validation"
+def validate_host_port_list(value):
+    assert all([validate_host_port(v) for v in value]), "didn't pass the validation"
     return True
 
 
+def comma_separated_host_port(string):
+    return validate_host_port_list([s.strip() for s in string.split(",")])
+
+
 def validate_host_port_listen(host_port):
     return validate_host_port(host_port, listen=True)
 
@@ -291,11 +295,20 @@ def assert_(condition, message="Wrong value"):
 
 userattributes = {"username": "", Optional("password"): ""}
 available_dcs = [m.split(".")[-1] for m in dcs_modules()]
+validate_host_port_list.expected_type = list
 comma_separated_host_port.expected_type = string_types
 validate_connect_address.expected_type = string_types
 validate_host_port_listen.expected_type = string_types
 validate_host_port_listen_multiple_hosts.expected_type = string_types
 validate_data_dir.expected_type = string_types
+validate_etcd = {
+    Or("host", "hosts", "srv", "url", "proxy"): Case({
+        "host": validate_host_port,
+        "hosts": Or(comma_separated_host_port, [validate_host_port]),
+        "srv": str,
+        "url": str,
+        "proxy": str})
+}
 
 schema = Schema({
   "name": str,
@@ -320,19 +333,20 @@ schema = Schema({
               "host": validate_host_port,
               "url": str})
           },
-      "etcd": {
-          Or("host", "hosts", "srv", "url", "proxy"): Case({
-              "host": validate_host_port,
-              "hosts": Or(comma_separated_host_port, [validate_host_port]),
-              "srv": str,
-              "url": str,
-              "proxy": str})
-         },
+      "etcd": validate_etcd,
+      "etcd3": validate_etcd,
       "exhibitor": {
           "hosts": [str],
           "port": lambda i: assert_(int(i) <= 65535),
           Optional("pool_interval"): int
           },
+      "raft": {
+          "self_addr": validate_connect_address,
+          Optional("bind_addr"): validate_host_port_listen,
+          "partner_addrs": validate_host_port_list,
+          Optional("data_dir"): str,
+          Optional("password"): str
+          },
       "zookeeper": {
           "hosts": Or(comma_separated_host_port, [validate_host_port]),
           },

patroni/version.py

@@ -1 +1 @@
-__version__ = '2.0.0'
+__version__ = '2.0.2'

postgres1.yml

@@ -112,6 +112,7 @@ postgresql:
   basebackup:
       - verbose
       - max-rate: 100M
+#      - waldir: /pg-wal-mount/external-waldir # only needed in case pg_wal is symlinked outside of data_dir
   # Additional fencing script executed after acquiring the leader lock but before promoting the replica
   #pre_promote: /path/to/pre_promote.sh
 

requirements.dev.txt

@@ -0,0 +1,8 @@
+psycopg2-binary
+behave
+coverage
+flake8
+mock
+pytest-cov
+pytest
+setuptools

requirements.txt

@@ -1,4 +1,5 @@
-urllib3[secure]>=1.19.1,!=1.21
+urllib3>=1.19.1,!=1.21
+ipaddress; python_version=="2.7"
 boto
 PyYAML
 six >= 1.7
@@ -8,6 +9,6 @@ python-consul>=0.7.1
 click>=4.1
 prettytable>=0.7
 python-dateutil
-pysyncobj>=0.3.5
+pysyncobj>=0.3.7
 psutil>=2.0.0
-cdiff
+ydiff>=1.2.0

setup.py

@@ -23,7 +23,7 @@ KEYWORDS = 'etcd governor patroni postgresql postgres ha haproxy confd' +\
     ' zookeeper exhibitor consul streaming replication kubernetes k8s'
 
 EXTRAS_REQUIRE = {'aws': ['boto'], 'etcd': ['python-etcd'], 'etcd3': ['python-etcd'], 'consul': ['python-consul'],
-                  'exhibitor': ['kazoo'], 'zookeeper': ['kazoo'], 'kubernetes': [], 'raft': ['pysyncobj']}
+                  'exhibitor': ['kazoo'], 'zookeeper': ['kazoo'], 'kubernetes': ['ipaddress'], 'raft': ['pysyncobj']}
 COVERAGE_XML = True
 COVERAGE_HTML = False
 
@@ -46,6 +46,8 @@ CLASSIFIERS = [
     'Programming Language :: Python :: 3.5',
     'Programming Language :: Python :: 3.6',
     'Programming Language :: Python :: 3.7',
+    'Programming Language :: Python :: 3.8',
+    'Programming Language :: Python :: 3.9',
     'Programming Language :: Python :: Implementation :: CPython',
 ]
 
@@ -143,9 +145,13 @@ class PyTest(Command):
 
     def run(self):
         from pkg_resources import evaluate_marker
-        requirements = self.distribution.install_requires + ['mock>=2.0.0', 'pytest-cov', 'pytest'] +\
-            [v for k, v in self.distribution.extras_require.items() if not k.startswith(':') or evaluate_marker(k[1:])]
-        self.distribution.fetch_build_eggs(requirements)
+
+        requirements = set(self.distribution.install_requires + ['mock>=2.0.0', 'pytest-cov', 'pytest'])
+        for k, v in self.distribution.extras_require.items():
+            if not k.startswith(':') or evaluate_marker(k[1:]):
+                requirements.update(v)
+
+        self.distribution.fetch_build_eggs(list(requirements))
         self.run_tests()
 
 
@@ -167,7 +173,7 @@ def setup_package(version):
         extra = False
         for e, v in EXTRAS_REQUIRE.items():
             if v and r.startswith(v[0]):
-                EXTRAS_REQUIRE[e] = [r]
+                EXTRAS_REQUIRE[e] = [r] if e != 'kubernetes' or sys.version_info < (3, 0, 0) else []
                 extra = True
         if not extra:
             install_requires.append(r)

tests/test_api.py

@@ -446,10 +446,12 @@ class TestRestApiHandler(unittest.TestCase):
 class TestRestApiServer(unittest.TestCase):
 
     @patch('ssl.SSLContext.load_cert_chain', Mock())
+    @patch('ssl.SSLContext.set_ciphers', Mock())
     @patch('ssl.SSLContext.wrap_socket', Mock(return_value=0))
     @patch.object(BaseHTTPServer.HTTPServer, '__init__', Mock())
     def setUp(self):
-        self.srv = MockRestApiServer(Mock(), '', {'listen': '*:8008', 'certfile': 'a', 'verify_client': 'required'})
+        self.srv = MockRestApiServer(Mock(), '', {'listen': '*:8008', 'certfile': 'a', 'verify_client': 'required',
+                                                  'ciphers': '!SSLv1:!SSLv2:!SSLv3:!TLSv1:!TLSv1.1'})
 
     @patch.object(BaseHTTPServer.HTTPServer, '__init__', Mock())
     def test_reload_config(self):
@@ -488,3 +490,16 @@ class TestRestApiServer(unittest.TestCase):
         mock_accept.return_value = (newsock, '2')
         self.srv.socket = Mock()
         self.assertEqual(self.srv.get_request(), ((self.srv.socket, newsock), '2'))
+
+    @patch.object(MockRestApiServer, 'process_request', Mock(side_effect=RuntimeError))
+    def test_process_request_error(self):
+        mock_address = ('127.0.0.1', 55555)
+        mock_socket = Mock()
+        mock_ssl_socket = (Mock(), Mock())
+        for mock_request in (mock_socket, mock_ssl_socket):
+            with patch.object(
+                MockRestApiServer,
+                'get_request',
+                Mock(return_value=(mock_request, mock_address))
+            ):
+                self.srv._handle_request_noblock()

tests/test_callback_executor.py

@@ -14,6 +14,7 @@ class TestCallbackExecutor(unittest.TestCase):
 
         ce = CallbackExecutor()
         ce._kill_children = Mock(side_effect=Exception)
+        ce._invoke_excepthook = Mock()
         self.assertIsNone(ce.call([]))
         ce.join()
 
@@ -30,5 +31,6 @@ class TestCallbackExecutor(unittest.TestCase):
         mock_popen.side_effect = Exception
         ce = CallbackExecutor()
         ce._condition.wait = Mock(side_effect=[None, Exception])
+        ce._invoke_excepthook = Mock()
         self.assertIsNone(ce.call([]))
         ce.join()

tests/test_consul.py

@@ -4,7 +4,7 @@ import unittest
 from consul import ConsulException, NotFound
 from mock import Mock, patch
 from patroni.dcs.consul import AbstractDCS, Cluster, Consul, ConsulInternalError, \
-                                ConsulError, HTTPClient, InvalidSessionTTL, InvalidSession
+                                ConsulError, ConsulClient, HTTPClient, InvalidSessionTTL, InvalidSession
 from . import SleepException
 
 
@@ -41,7 +41,8 @@ def kv_get(self, key, **kwargs):
 class TestHTTPClient(unittest.TestCase):
 
     def setUp(self):
-        self.client = HTTPClient('127.0.0.1', '8500', 'http', False)
+        c = ConsulClient()
+        self.client = c.http
         self.client.http.request = Mock()
 
     def test_get(self):

tests/test_ctl.py

@@ -7,7 +7,7 @@ from datetime import datetime, timedelta
 from mock import patch, Mock
 from patroni.ctl import ctl, store_config, load_config, output_members, get_dcs, parse_dcs, \
     get_all_members, get_any_member, get_cursor, query_member, configure, PatroniCtlException, apply_config_changes, \
-    format_config_for_editing, show_diff, invoke_editor, format_pg_version, find_executable, CONFIG_FILE_PATH
+    format_config_for_editing, show_diff, invoke_editor, format_pg_version, CONFIG_FILE_PATH
 from patroni.dcs.etcd import AbstractEtcdClientWithFailover, Failover
 from patroni.utils import tzutc
 from psycopg2 import OperationalError
@@ -561,7 +561,7 @@ class TestCtl(unittest.TestCase):
         self.assertRaises(PatroniCtlException, apply_config_changes, before_editing, config, ['a'])
 
     @patch('sys.stdout.isatty', return_value=False)
-    @patch('cdiff.markup_to_pager')
+    @patch('patroni.ctl.markup_to_pager')
     def test_show_diff(self, mock_markup_to_pager, mock_isatty):
         show_diff("foo:\n  bar: 1\n", "foo:\n  bar: 2\n")
         mock_markup_to_pager.assert_not_called()
@@ -570,6 +570,9 @@ class TestCtl(unittest.TestCase):
         show_diff("foo:\n  bar: 1\n", "foo:\n  bar: 2\n")
         mock_markup_to_pager.assert_called_once()
 
+        with patch('patroni.ctl.find_executable', Mock(return_value=None)):
+            show_diff("foo:\n  bar: 1\n", "foo:\n  bar: 2\n")
+
         # Test that unicode handling doesn't fail with an exception
         show_diff(b"foo:\n  bar: \xc3\xb6\xc3\xb6\n".decode('utf-8'),
                   b"foo:\n  bar: \xc3\xbc\xc3\xbc\n".decode('utf-8'))
@@ -626,15 +629,6 @@ class TestCtl(unittest.TestCase):
         self.assertEqual(format_pg_version(100001), '10.1')
         self.assertEqual(format_pg_version(90605), '9.6.5')
 
-    @patch('sys.platform', 'win32')
-    def test_find_executable(self):
-        with patch('os.path.isfile', Mock(return_value=True)):
-            self.assertEqual(find_executable('vim'), 'vim.exe')
-        with patch('os.path.isfile', Mock(return_value=False)):
-            self.assertIsNone(find_executable('vim'))
-        with patch('os.path.isfile', Mock(side_effect=[False, True])):
-            self.assertEqual(find_executable('vim', '/'), '/vim.exe')
-
     @patch('patroni.ctl.get_dcs')
     def test_get_members(self, mock_get_dcs):
         mock_get_dcs.return_value = self.e

tests/test_etcd.py

@@ -110,6 +110,7 @@ class TestDnsCachingResolver(unittest.TestCase):
     @patch('socket.getaddrinfo', Mock(side_effect=socket.gaierror))
     def test_run(self):
         r = DnsCachingResolver()
+        r._invoke_excepthook = Mock()
         self.assertIsNone(r.resolve_async('', 0))
         r.join()
 

tests/test_etcd3.py

@@ -5,7 +5,7 @@ import urllib3
 
 from mock import Mock, patch
 from patroni.dcs.etcd3 import PatroniEtcd3Client, Cluster, Etcd3, Etcd3Error, Etcd3ClientError, RetryFailedError,\
-        InvalidAuthToken, Unavailable, Unknown, UnsupportedEtcdVersion, UserEmpty, base64_encode
+        InvalidAuthToken, Unavailable, Unknown, UnsupportedEtcdVersion, UserEmpty, AuthFailed, base64_encode
 from threading import Thread
 
 from . import SleepException, MockResponse
@@ -90,7 +90,7 @@ class TestKVCache(BaseTestEtcd3):
 
 class TestPatroniEtcd3Client(BaseTestEtcd3):
 
-    @patch('patroni.dcs.etcd3.Etcd3Client.authenticate', Mock(side_effect=Exception))
+    @patch('patroni.dcs.etcd3.Etcd3Client.authenticate', Mock(side_effect=AuthFailed))
     def test__init__(self):
         self.assertRaises(SystemExit, self.setUp)
 

tests/test_ha.py

@@ -3,7 +3,7 @@ import etcd
 import os
 import sys
 
-from mock import call, Mock, MagicMock, PropertyMock, patch, mock_open
+from mock import Mock, MagicMock, PropertyMock, patch, mock_open
 from patroni.config import Config
 from patroni.dcs import Cluster, ClusterConfig, Failover, Leader, Member, get_dcs, SyncState, TimelineHistory
 from patroni.dcs.etcd import AbstractEtcdClientWithFailover
@@ -200,7 +200,8 @@ class TestHa(PostgresInit):
 
     def test_update_lock(self):
         self.p.last_operation = Mock(side_effect=PostgresConnectionException(''))
-        self.assertTrue(self.ha.update_lock(True))
+        self.ha.dcs.update_leader = Mock(side_effect=Exception)
+        self.assertFalse(self.ha.update_lock(True))
 
     @patch.object(Postgresql, 'received_timeline', Mock(return_value=None))
     def test_touch_member(self):
@@ -260,9 +261,17 @@ class TestHa(PostgresInit):
 
     @patch.object(Rewind, 'ensure_clean_shutdown', Mock())
     def test_crash_recovery(self):
+        self.ha.has_lock = true
         self.p.is_running = false
         self.p.controldata = lambda: {'Database cluster state': 'in production', 'Database system identifier': SYSID}
         self.assertEqual(self.ha.run_cycle(), 'doing crash recovery in a single user mode')
+        with patch('patroni.async_executor.AsyncExecutor.busy', PropertyMock(return_value=True)),\
+                patch.object(Ha, 'check_timeline', Mock(return_value=False)):
+            self.ha._async_executor.schedule('doing crash recovery in a single user mode')
+            self.ha.state_handler.cancellable._process = Mock()
+            self.ha._crash_recovery_started -= 600
+            self.ha.patroni.config.set_dynamic_configuration({'maximum_lag_on_failover': 10})
+            self.assertEqual(self.ha.run_cycle(), 'terminated crash recovery because of startup timeout')
 
     @patch.object(Rewind, 'rewind_or_reinitialize_needed_and_possible', Mock(return_value=True))
     @patch.object(Rewind, 'can_rewind', PropertyMock(return_value=True))
@@ -492,6 +501,9 @@ class TestHa(PostgresInit):
                     self.assertEqual(self.ha.run_cycle(), 'lost leader lock during restart')
                     mock_terminate.assert_called()
 
+            self.ha.is_paused = true
+            self.assertEqual(self.ha.run_cycle(), 'PAUSE: restart in progress')
+
     def test_manual_failover_from_leader(self):
         self.ha.fetch_node_status = get_node_status()
         self.ha.has_lock = true
@@ -901,9 +913,8 @@ class TestHa(PostgresInit):
         self.p.pick_synchronous_standby = Mock(return_value=(['other2', 'other3'], ['other2']))
         self.ha.dcs.write_sync_state = Mock(return_value=True)
         self.ha.run_cycle()
-        # mock_set_sync.assert_called_once_with(['other2'])
-        calls = [call(['other2']), call(['other2', 'other3'])]
-        mock_set_sync.assert_has_calls(calls)
+        self.assertEqual(mock_set_sync.call_args_list[0][0], (['other2'],))
+        self.assertEqual(mock_set_sync.call_args_list[1][0], (['other2', 'other3'],))
 
         mock_set_sync.reset_mock()
         # Test sync standby is not disabled when updating dcs fails
@@ -1111,3 +1122,18 @@ class TestHa(PostgresInit):
         self.assertEqual(self.ha.run_cycle(), 'Unexpected exception raised, please report it as a BUG')
         self.ha.dcs.touch_member = Mock(side_effect=PatroniFatalException('foo'))
         self.assertRaises(PatroniFatalException, self.ha.run_cycle)
+
+    def test_empty_directory_in_pause(self):
+        self.ha.is_paused = true
+        self.p.data_directory_empty = true
+        self.assertEqual(self.ha.run_cycle(), 'PAUSE: running with empty data directory')
+        self.assertEqual(self.p.role, 'uninitialized')
+
+    @patch('patroni.ha.Ha.sysid_valid', MagicMock(return_value=True))
+    def test_sysid_no_match_in_pause(self):
+        self.ha.is_paused = true
+        self.p.controldata = lambda: {'Database cluster state': 'in recovery', 'Database system identifier': '123'}
+        self.assertEqual(self.ha.run_cycle(), 'PAUSE: continue to run as master without lock')
+
+        self.ha.has_lock = true
+        self.assertEqual(self.ha.run_cycle(), 'PAUSE: released leader key voluntarily due to the system ID mismatch')

tests/test_kubernetes.py

@@ -26,7 +26,7 @@ def mock_list_namespaced_config_map(*args, **kwargs):
     return k8s_client.V1ConfigMapList(metadata=metadata, items=items, kind='ConfigMapList')
 
 
-def mock_list_namespaced_endpoints(*args, **kwargs):
+def mock_read_namespaced_endpoints(*args, **kwargs):
     target_ref = k8s_client.V1ObjectReference(kind='Pod', resource_version='10', name='p-0',
                                               namespace='default', uid='964dfeae-e79b-4476-8a5a-1920b5c2a69d')
     address0 = k8s_client.V1EndpointAddress(ip='10.0.0.0', target_ref=target_ref)
@@ -35,9 +35,12 @@ def mock_list_namespaced_endpoints(*args, **kwargs):
     subset = k8s_client.V1EndpointSubset(addresses=[address1, address0], ports=[port])
     metadata = k8s_client.V1ObjectMeta(resource_version='1', labels={'f': 'b'}, name='test',
                                        annotations={'optime': '1234', 'leader': 'p-0', 'ttl': '30s'})
-    endpoint = k8s_client.V1Endpoints(subsets=[subset], metadata=metadata)
-    metadata = k8s_client.V1ObjectMeta(resource_version='1')
-    return k8s_client.V1EndpointsList(metadata=metadata, items=[endpoint], kind='V1EndpointsList')
+    return k8s_client.V1Endpoints(subsets=[subset], metadata=metadata)
+
+
+def mock_list_namespaced_endpoints(*args, **kwargs):
+    return k8s_client.V1EndpointsList(metadata=k8s_client.V1ObjectMeta(resource_version='1'),
+                                      items=[mock_read_namespaced_endpoints()], kind='V1EndpointsList')
 
 
 def mock_list_namespaced_pod(*args, **kwargs):
@@ -261,20 +264,25 @@ class TestKubernetesEndpoints(BaseTestKubernetes):
     def test_update_leader_with_restricted_access(self):
         self.assertIsNotNone(self.k.update_leader('123', True))
 
+    @patch.object(k8s_client.CoreV1Api, 'read_namespaced_endpoints', create=True)
     @patch.object(k8s_client.CoreV1Api, 'patch_namespaced_endpoints', create=True)
-    def test__update_leader_with_retry(self, mock_patch):
+    def test__update_leader_with_retry(self, mock_patch, mock_read):
+        mock_read.return_value = mock_read_namespaced_endpoints()
         mock_patch.side_effect = k8s_client.rest.ApiException(502, '')
         self.assertFalse(self.k.update_leader('123'))
         mock_patch.side_effect = RetryFailedError('')
         self.assertFalse(self.k.update_leader('123'))
         mock_patch.side_effect = k8s_client.rest.ApiException(409, '')
-        with patch('time.time', Mock(side_effect=[0, 100, 200])):
+        with patch('time.time', Mock(side_effect=[0, 100, 200, 0, 0, 0, 0, 100, 200])):
             self.assertFalse(self.k.update_leader('123'))
-        with patch('time.sleep', Mock()):
             self.assertFalse(self.k.update_leader('123'))
-            mock_patch.side_effect = [k8s_client.rest.ApiException(409, ''), mock_namespaced_kind()]
-            self.k._kinds._object_cache['test'].metadata.resource_version = '2'
-            self.assertIsNotNone(self.k._update_leader_with_retry({}, '1', []))
+        self.assertFalse(self.k.update_leader('123'))
+        mock_patch.side_effect = [k8s_client.rest.ApiException(409, ''), mock_namespaced_kind()]
+        mock_read.return_value.metadata.resource_version = '2'
+        self.assertIsNotNone(self.k._update_leader_with_retry({}, '1', []))
+        mock_patch.side_effect = k8s_client.rest.ApiException(409, '')
+        mock_read.side_effect = Exception
+        self.assertFalse(self.k.update_leader('123'))
 
     @patch.object(k8s_client.CoreV1Api, 'create_namespaced_endpoints',
                   Mock(side_effect=[k8s_client.rest.ApiException(500, ''),

tests/test_postgresql.py

@@ -306,7 +306,8 @@ class TestPostgresql(BaseTestPostgresql):
     def test_sync_replication_slots(self):
         self.p.start()
         config = ClusterConfig(1, {'slots': {'test_3': {'database': 'a', 'plugin': 'b'},
-                                             'A': 0, 'ls': 0, 'b': {'type': 'logical', 'plugin': '1'}}}, 1)
+                                             'A': 0, 'ls': 0, 'b': {'type': 'logical', 'plugin': '1'}},
+                                   'ignore_slots': [{'name': 'blabla'}]}, 1)
         cluster = Cluster(True, config, self.leader, 0, [self.me, self.other, self.leadermem], None, None, None)
         with mock.patch('patroni.postgresql.Postgresql._query', Mock(side_effect=psycopg2.OperationalError)):
             self.p.slots_handler.sync_replication_slots(cluster)
@@ -614,32 +615,32 @@ class TestPostgresql(BaseTestPostgresql):
 
         with patch.object(Postgresql, "query", side_effect=[
                     mock_cursor,
-                    [(self.leadermem.name, 'streaming', 'sync'),
-                     (self.me.name, 'streaming', 'async'),
-                     (self.other.name, 'streaming', 'async')]
+                    [(self.leadermem.name, 'sync', 1),
+                     (self.me.name, 'async', 2),
+                     (self.other.name, 'async', 2)]
                 ]):
             self.assertEqual(self.p.pick_synchronous_standby(cluster), ([self.leadermem.name], [self.leadermem.name]))
 
         with patch.object(Postgresql, "query", side_effect=[
                     mock_cursor,
-                    [(self.leadermem.name, 'streaming', 'potential'),
-                     (self.me.name, 'streaming', 'async'),
-                     (self.other.name, 'streaming', 'async')]
+                    [(self.leadermem.name, 'potential', 1),
+                     (self.me.name, 'async', 2),
+                     (self.other.name, 'async', 2)]
                 ]):
             self.assertEqual(self.p.pick_synchronous_standby(cluster), ([self.leadermem.name], []))
 
         with patch.object(Postgresql, "query", side_effect=[
                     mock_cursor,
-                    [(self.me.name, 'streaming', 'async'),
-                     (self.other.name, 'streaming', 'async')]
+                    [(self.me.name, 'async', 1),
+                     (self.other.name, 'async', 2)]
                 ]):
             self.assertEqual(self.p.pick_synchronous_standby(cluster), ([self.me.name], []))
 
         with patch.object(Postgresql, "query", side_effect=[
                     mock_cursor,
-                    [('missing', 'streaming', 'sync'),
-                     (self.me.name, 'streaming', 'async'),
-                     (self.other.name, 'streaming', 'async')]
+                    [('missing', 'sync', 1),
+                     (self.me.name, 'async', 2),
+                     (self.other.name, 'async', 3)]
                 ]):
             self.assertEqual(self.p.pick_synchronous_standby(cluster), ([self.me.name], []))
 

tests/test_raft.py

@@ -1,5 +1,6 @@
 import os
 import unittest
+import tempfile
 import time
 
 from mock import Mock, patch
@@ -86,8 +87,6 @@ class TestKVStoreTTL(unittest.TestCase):
         self.so.set('foo', 'bar')
         self.so.set('fooo', 'bar')
         self.assertFalse(self.so.delete('foo', prevValue='buz'))
-        self.assertFalse(self.so.delete('foo', prevValue='bar', timeout=0.00001))
-        self.assertFalse(self.so.delete('foo', prevValue='bar'))
         self.assertTrue(self.so.delete('foo', recursive=True))
         self.assertFalse(self.so.retry(self.so._delete, 'foo', prevValue=''))
 
@@ -99,10 +98,14 @@ class TestKVStoreTTL(unittest.TestCase):
 
     @patch('time.sleep', Mock())
     def test_retry(self):
-        return_values = [FAIL_REASON.QUEUE_FULL, FAIL_REASON.SUCCESS, FAIL_REASON.REQUEST_DENIED]
+        return_values = [FAIL_REASON.QUEUE_FULL] * 2 + [FAIL_REASON.SUCCESS, FAIL_REASON.REQUEST_DENIED]
 
         def test(callback):
             callback(True, return_values.pop(0))
+
+        with patch('time.time', Mock(side_effect=[1, 100])):
+            self.assertFalse(self.so.retry(test))
+
         self.assertTrue(self.so.retry(test))
         self.assertFalse(self.so.retry(test))
 
@@ -119,8 +122,11 @@ class TestKVStoreTTL(unittest.TestCase):
 
 class TestRaft(unittest.TestCase):
 
+    _TMP = tempfile.gettempdir()
+
     def test_raft(self):
-        raft = Raft({'ttl': 30, 'scope': 'test', 'name': 'pg', 'self_addr': '127.0.0.1:1234', 'retry_timeout': 10})
+        raft = Raft({'ttl': 30, 'scope': 'test', 'name': 'pg', 'self_addr': '127.0.0.1:1234',
+                     'retry_timeout': 10, 'data_dir': self._TMP})
         raft.set_retry_timeout(20)
         raft.set_ttl(60)
         self.assertTrue(raft.touch_member(''))
@@ -142,7 +148,7 @@ class TestRaft(unittest.TestCase):
         raft._sync_obj._SyncObj__thread.join()
 
     def tearDown(self):
-        remove_files('127.0.0.1:1234.')
+        remove_files(os.path.join(self._TMP, '127.0.0.1:1234.'))
 
     def setUp(self):
         self.tearDown()
@@ -152,4 +158,5 @@ class TestRaft(unittest.TestCase):
     def test_init(self, mock_event, mock_kvstore):
         mock_kvstore.return_value.applied_local_log = False
         mock_event.return_value.isSet.side_effect = [False, True]
-        self.assertIsNotNone(Raft({'ttl': 30, 'scope': 'test', 'name': 'pg', 'patronictl': True}))
+        self.assertIsNotNone(Raft({'ttl': 30, 'scope': 'test', 'name': 'pg', 'patronictl': True,
+                                   'self_addr': '1', 'data_dir': self._TMP}))

tests/test_rewind.py

@@ -40,6 +40,12 @@ def mock_cancellable_call1(*args, **kwargs):
     return 1
 
 
+def mock_single_user_mode(self, communicate, options):
+    communicate['stdout'] = b'foo'
+    communicate['stderr'] = b'bar'
+    return 1
+
+
 @patch('subprocess.call', Mock(return_value=0))
 @patch('psycopg2.connect', psycopg2_connect)
 class TestRewind(BaseTestPostgresql):
@@ -170,8 +176,8 @@ class TestRewind(BaseTestPostgresql):
 
     @patch.object(MockCursor, 'fetchone', Mock(side_effect=[(True,), Exception]))
     def test_check_leader_is_not_in_recovery(self):
-        self.r.check_leader_is_not_in_recovery()
-        self.r.check_leader_is_not_in_recovery()
+        self.r.check_leader_is_not_in_recovery({})
+        self.r.check_leader_is_not_in_recovery({})
 
     def test_read_postmaster_opts(self):
         m = mock_open(read_data='/usr/lib/postgres/9.6/bin/postgres "-D" "data/postgresql0" \
@@ -206,9 +212,9 @@ class TestRewind(BaseTestPostgresql):
     @patch('os.listdir', Mock(return_value=[]))
     @patch('os.path.isfile', Mock(return_value=True))
     @patch.object(Rewind, 'read_postmaster_opts', Mock(return_value={}))
-    @patch.object(Rewind, 'single_user_mode', Mock(return_value=0))
+    @patch.object(Rewind, 'single_user_mode', mock_single_user_mode)
     def test_ensure_clean_shutdown(self):
-        self.assertTrue(self.r.ensure_clean_shutdown())
+        self.assertIsNone(self.r.ensure_clean_shutdown())
 
     @patch('patroni.postgresql.rewind.Thread', MockThread)
     @patch.object(Postgresql, 'controldata')

tests/test_utils.py

@@ -2,7 +2,7 @@ import unittest
 
 from mock import Mock, patch
 from patroni.exceptions import PatroniException
-from patroni.utils import Retry, RetryFailedError, enable_keepalive, polling_loop, validate_directory
+from patroni.utils import Retry, RetryFailedError, enable_keepalive, find_executable, polling_loop, validate_directory
 
 
 class TestUtils(unittest.TestCase):
@@ -41,6 +41,15 @@ class TestUtils(unittest.TestCase):
                 with patch('sys.platform', platform):
                     self.assertIsNone(enable_keepalive(Mock(), 10, 5))
 
+    @patch('sys.platform', 'win32')
+    def test_find_executable(self):
+        with patch('os.path.isfile', Mock(return_value=True)):
+            self.assertEqual(find_executable('vim'), 'vim.exe')
+        with patch('os.path.isfile', Mock(return_value=False)):
+            self.assertIsNone(find_executable('vim'))
+        with patch('os.path.isfile', Mock(side_effect=[False, True])):
+            self.assertEqual(find_executable('vim', '/'), '/vim.exe')
+
 
 @patch('time.sleep', Mock())
 class TestRetrySleeper(unittest.TestCase):

tests/test_validator.py

@@ -33,11 +33,21 @@ config = {
     "etcd": {
         "hosts": "127.0.0.1:2379,127.0.0.1:2380"
     },
+    "etcd3": {
+        "url": "https://127.0.0.1:2379"
+    },
     "exhibitor": {
         "hosts": ["string"],
         "port": 4000,
         "pool_interval": 1000
     },
+    "raft": {
+        "self_addr": "127.0.0.1:2222",
+        "bind_addr": "0.0.0.0:2222",
+        "partner_addrs": ["127.0.0.1:2223", "127.0.0.1:2224"],
+        "data_dir": "/",
+        "password": "12345"
+    },
     "zookeeper": {
         "hosts":  "127.0.0.1:3379,127.0.0.1:3380"
     },
@@ -139,7 +149,7 @@ class TestValidator(unittest.TestCase):
     def test_complete_config(self, mock_out, mock_err):
         schema(config)
         output = mock_out.getvalue()
-        self.assertEqual(['postgresql.bin_dir'], parse_output(output))
+        self.assertEqual(['postgresql.bin_dir', 'raft.bind_addr', 'raft.self_addr'], parse_output(output))
 
     def test_bin_dir_is_file(self, mock_out, mock_err):
         files.append(config["postgresql"]["data_dir"])
@@ -151,7 +161,8 @@ class TestValidator(unittest.TestCase):
         schema(c)
         output = mock_out.getvalue()
         self.assertEqual(['etcd.hosts.1', 'etcd.hosts.2', 'kubernetes.pod_ip', 'postgresql.bin_dir',
-                          'postgresql.data_dir', 'restapi.connect_address'], parse_output(output))
+                          'postgresql.data_dir', 'raft.bind_addr', 'raft.self_addr',
+                          'restapi.connect_address'], parse_output(output))
 
     @patch('socket.inet_pton', Mock(), create=True)
     def test_bin_dir_is_empty(self, mock_out, mock_err):
@@ -167,8 +178,8 @@ class TestValidator(unittest.TestCase):
         with patch('patroni.validator.open', mock_open(read_data='9')):
             schema(c)
         output = mock_out.getvalue()
-        self.assertEqual(['consul.host', 'etcd.host', 'postgresql.bin_dir', 'postgresql.data_dir',
-                          'postgresql.listen', 'restapi.connect_address'], parse_output(output))
+        self.assertEqual(['consul.host', 'etcd.host', 'postgresql.bin_dir', 'postgresql.data_dir', 'postgresql.listen',
+                          'raft.bind_addr', 'raft.self_addr', 'restapi.connect_address'], parse_output(output))
 
     @patch('subprocess.check_output', Mock(return_value=b"postgres (PostgreSQL) 12.1"))
     def test_data_dir_contains_pg_version(self, mock_out, mock_err):
@@ -186,7 +197,7 @@ class TestValidator(unittest.TestCase):
         with patch('patroni.validator.open', mock_open(read_data='12')):
             schema(config)
         output = mock_out.getvalue()
-        self.assertEqual([], parse_output(output))
+        self.assertEqual(['raft.bind_addr', 'raft.self_addr'], parse_output(output))
 
     @patch('subprocess.check_output', Mock(return_value=b"postgres (PostgreSQL) 12.1"))
     def test_pg_version_missmatch(self, mock_out, mock_err):
@@ -201,7 +212,8 @@ class TestValidator(unittest.TestCase):
         with patch('patroni.validator.open', mock_open(read_data='11')):
             schema(c)
         output = mock_out.getvalue()
-        self.assertEqual(['etcd.hosts', 'postgresql.data_dir'], parse_output(output))
+        self.assertEqual(['etcd.hosts', 'postgresql.data_dir',
+                          'raft.bind_addr', 'raft.self_addr'], parse_output(output))
 
     @patch('subprocess.check_output', Mock(return_value=b"postgres (PostgreSQL) 12.1"))
     def test_pg_wal_doesnt_exist(self, mock_out, mock_err):
@@ -214,7 +226,7 @@ class TestValidator(unittest.TestCase):
         with patch('patroni.validator.open', mock_open(read_data='11')):
             schema(c)
         output = mock_out.getvalue()
-        self.assertEqual(['postgresql.data_dir'], parse_output(output))
+        self.assertEqual(['postgresql.data_dir', 'raft.bind_addr', 'raft.self_addr'], parse_output(output))
 
     def test_data_dir_is_empty_string(self, mock_out, mock_err):
         directories.append(config["postgresql"]["data_dir"])
@@ -226,5 +238,5 @@ class TestValidator(unittest.TestCase):
         c["postgresql"]["bin_dir"] = ""
         schema(c)
         output = mock_out.getvalue()
-        self.assertEqual(['kubernetes', 'postgresql.bin_dir',
-                          'postgresql.data_dir', 'postgresql.pg_hba'], parse_output(output))
+        self.assertEqual(['kubernetes', 'postgresql.bin_dir', 'postgresql.data_dir',
+                          'postgresql.pg_hba', 'raft.bind_addr', 'raft.self_addr'], parse_output(output))

tests/test_zookeeper.py

@@ -17,7 +17,7 @@ class MockKazooClient(Mock):
 
     def __init__(self, *args, **kwargs):
         super(MockKazooClient, self).__init__()
-        self._session_timeout = 30
+        self._session_timeout = 30000
 
     @property
     def client_id(self):