Better SIGCHLD handling, use correct user name.

- Defer SIGCHLD processing until the later stage in order to allow
  subprocess to run its own reaping of children and return the correct
  exit code from the process called.

- When changing the password at startup, do not assume the user postgres.

helpers/postgresql.py

@@ -354,7 +354,7 @@ primary_conninfo = '{}'
                 self.query('CREATE ROLE "{0}" WITH LOGIN SUPERUSER PASSWORD %s'.format(
                     self.superuser['username']), self.superuser['password'])
             else:
-                self.query('ALTER ROLE postgres WITH PASSWORD %s', self.superuser['password'])
+                self.query('ALTER ROLE "{0}" WITH PASSWORD %s'.format(os.environ['USER']), self.superuser['password'])
         if self.admin:
             self.query('CREATE ROLE "{0}" WITH LOGIN CREATEDB CREATEROLE PASSWORD %s'.format(
                 self.admin['username']), self.admin['password'])

helpers/utils.py

@@ -5,7 +5,8 @@ import signal
 import sys
 import time
 
-received_sigchld = False
+interrupted_sleep = False
+reap_children = False
 
 _DATE_TIME_RE = re.compile(r'''^
 (?P<year>\d{4})\-(?P<month>\d{2})\-(?P<day>\d{2})  # date
@@ -72,30 +73,38 @@ def sigterm_handler(signo, stack_frame):
 
 
 def sigchld_handler(signo, stack_frame):
-    global received_sigchld
-    received_sigchld = True
-    try:
-        while True:
-            ret = os.waitpid(-1, os.WNOHANG)
-            if ret == (0, 0):
-                break
-    except OSError:
-        pass
+    global interrupted_sleep, reap_children
+    reap_children = interrupted_sleep = True
 
 
 def sleep(interval):
-    global received_sigchld
+    global interrupted_sleep
     current_time = time.time()
     end_time = current_time + interval
     while current_time < end_time:
-        received_sigchld = False
+        interrupted_sleep = False
         time.sleep(end_time - current_time)
-        if not received_sigchld:  # we will ignore only sigchld
+        if not interrupted_sleep:  # we will ignore only sigchld
             break
         current_time = time.time()
-    received_sigchld = False
+    interrupted_sleep = False
 
 
 def setup_signal_handlers():
     signal.signal(signal.SIGTERM, sigterm_handler)
     signal.signal(signal.SIGCHLD, sigchld_handler)
+
+
+def reap_children():
+    global reap_children
+    if reap_children:
+        try:
+            while True:
+                ret = os.waitpid(-1, os.WNOHANG)
+                print ret
+                if ret == (0, 0):
+                    break
+        except OSError:
+            pass
+        finally:
+            reap_children = False

patroni.py

@@ -9,7 +9,7 @@ from helpers.api import RestApiServer
 from helpers.etcd import Etcd
 from helpers.ha import Ha
 from helpers.postgresql import Postgresql
-from helpers.utils import setup_signal_handlers, sleep
+from helpers.utils import setup_signal_handlers, sleep, reap_children
 from helpers.zookeeper import ZooKeeper
 
 logger = logging.getLogger(__name__)
@@ -93,6 +93,7 @@ class Patroni:
             except:
                 logger.exception('Exception when changing replication slots')
             self.schedule_next_run()
+            reap_children()
 
 
 def main():