add sleep, allow errno '3' (ESRCH) on the open of /proc/pid/cmdline

The sleep is added here simply to not completely spin cpu on waiting
for the parent pid to die.

the allowing of errno 3 is because I was getting this.  I dont have
a perfect explanation, but I suspect that the 'open' was actually
getting this back from the /proc filesystem after the pid had died.
Possibly in the window between when the 'open' was done and the 'read()'
was done.

1 files changed, 6 insertions, 2 deletions

diff --git a/cloudinit/config/cc_power_state_change.py b/cloudinit/config/cc_power_state_change.py
index 22f1aade..02434322 100644
--- a/cloudinit/config/cc_power_state_change.py
+++ b/cloudinit/config/cc_power_state_change.py
@@ -121,6 +121,8 @@ def run_after_pid_gone(pid, pidcmdline, timeout, log, func, args):
             log.warn(msg)
         doexit(EXIT_FAIL)
 
+    known_errnos = (errno.ENOENT, errno.ESRCH)
+
     while True:
         if time.time() > end_time:
             msg = "timeout reached before %s ended" % pid
@@ -135,8 +137,8 @@ def run_after_pid_gone(pid, pidcmdline, timeout, log, func, args):
                 break
 
         except IOError as ioerr:
-            if ioerr.errno == errno.ENOENT:
-                msg = "pidfile '%s' gone" % cmdline_f
+            if ioerr.errno in known_errnos:
+                msg = "pidfile '%s' gone [%d]" % (cmdline_f, ioerr.errno)
             else:
                 fatal("IOError during wait: %s" % ioerr)
             break
@@ -144,6 +146,8 @@ def run_after_pid_gone(pid, pidcmdline, timeout, log, func, args):
         except Exception as e:
             fatal("Unexpected Exception: %s" % e)
 
+        time.sleep(.25)
+
     if not msg:
         fatal("Unexpected error in run_after_pid_gone")