From 98b85d3620cf4271a56c574e3e191ff045bd780e Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Wed, 26 Feb 2020 13:45:25 -0600 Subject: [PATCH] qa/tasks/ceph_manager: increase CLI command timeout There is a problem with mimic releases where pg_creates can stall for a long time doing the build_pg_history while holding osd_lock. That lock is also used by the tell command processing queue, which means that commands like 'flush_pg_stats' can block for long periods...and time out. This is currently happening with mimic->nautilus upgrades. Note that the problem is mostly fixed in nautilus and totally fixed in octopus, so this is just a matter of tolerating slow behavior in old releases for the purposes of the upgrade tests. Work around this by increasing the timeout from 120s -> 900s. Fixes: https://tracker.ceph.com/issues/43914 Signed-off-by: Sage Weil --- qa/tasks/ceph_manager.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/qa/tasks/ceph_manager.py b/qa/tasks/ceph_manager.py index f4cbbf6e08d2..ae3bc56b4ecc 100644 --- a/qa/tasks/ceph_manager.py +++ b/qa/tasks/ceph_manager.py @@ -1146,7 +1146,7 @@ class CephManager: 'ceph-coverage', '{tdir}/archive/coverage'.format(tdir=testdir), 'timeout', - '120', + '900', 'ceph', '--cluster', self.cluster, @@ -1169,7 +1169,7 @@ class CephManager: 'ceph-coverage', '{tdir}/archive/coverage'.format(tdir=testdir), 'timeout', - '120', + '900', 'ceph', '--cluster', self.cluster, -- 2.47.3