From 20ad17d271fb443f6c40591e205e880b5014a4f3 Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Wed, 3 Jun 2015 14:57:34 -0400 Subject: [PATCH] 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 (cherry picked from commit eaff6cb24ef052c54dfa2131811758e335f19939) --- src/upstart/ceph-mds.conf | 2 +- src/upstart/ceph-mon.conf | 2 +- src/upstart/ceph-osd.conf | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/src/upstart/ceph-mds.conf b/src/upstart/ceph-mds.conf index 77841cdccd7..4063d9116eb 100644 --- a/src/upstart/ceph-mds.conf +++ b/src/upstart/ceph-mds.conf @@ -4,7 +4,7 @@ start on ceph-mds stop on runlevel [!2345] or stopping ceph-mds-all respawn -respawn limit 5 30 +respawn limit 3 1800 limit nofile 16384 16384 diff --git a/src/upstart/ceph-mon.conf b/src/upstart/ceph-mon.conf index 0279f15c5a8..83c98583c5d 100644 --- a/src/upstart/ceph-mon.conf +++ b/src/upstart/ceph-mon.conf @@ -4,7 +4,7 @@ start on ceph-mon stop on runlevel [!2345] or stopping ceph-mon-all respawn -respawn limit 5 30 +respawn limit 3 1800 limit nofile 16384 16384 diff --git a/src/upstart/ceph-osd.conf b/src/upstart/ceph-osd.conf index 7175c2d9300..6fa97ed1d23 100644 --- a/src/upstart/ceph-osd.conf +++ b/src/upstart/ceph-osd.conf @@ -4,7 +4,7 @@ start on ceph-osd stop on runlevel [!2345] or stopping ceph-osd-all respawn -respawn limit 5 30 +respawn limit 3 1800 limit nofile 32768 32768 -- 2.47.3