ceph/src/upstart/ceph-mon.conf
Sage Weil eaff6cb24e upstart: limit respawn to 3 in 30 mins (instead of 5 in 30s)
It may take tens of seconds to restart each time, so 5 in 30s does not stop
the crash on startup respawn loop in many cases.  In particular, we'd like
to catch the case where the internal heartbeats fail.

This should be enough for all but the most sluggish of OSDs and capture
many cases of failure shortly after startup.

Fixes: #11798
Signed-off-by: Sage Weil <sage@redhat.com>
2015-06-03 14:57:34 -04:00

32 lines
690 B
Plaintext

description "Ceph MON"
start on ceph-mon
stop on runlevel [!2345] or stopping ceph-mon-all
respawn
respawn limit 3 1800
limit nofile 16384 16384
pre-start script
set -e
test -x /usr/bin/ceph-mon || { stop; exit 0; }
test -d "/var/lib/ceph/mon/${cluster:-ceph}-$id" || { stop; exit 0; }
install -d -m0755 /var/run/ceph
end script
instance ${cluster:-ceph}/$id
export cluster
export id
# this breaks oneiric
#usage "cluster = name of cluster (defaults to 'ceph'); id = monitor instance id"
exec /usr/bin/ceph-mon --cluster="${cluster:-ceph}" -i "$id" -f
post-stop script
# Cleanup socket in case of segfault
rm -f "/var/run/ceph/ceph-mon.$id.asok"
end script