Gitweb: http://git.fedorahosted.org/git/cluster.git?p=cluster.git;a=commitdiff;h=64f... Commit: 64f54ec761a16143c28fe414aa4fefef308bdc43 Parent: 93e33cb09d2567e9523a7098247c6c9df324c16b Author: Lon Hohberger lhh@redhat.com AuthorDate: Wed Jan 4 23:01:07 2012 -0500 Committer: Lon Hohberger lhh@redhat.com CommitterDate: Thu Jan 5 10:56:32 2012 -0500
rgmanager: Avoid duplicate restart of service
If B depends on A and both A and B are running on node 1 and node 1 fails, the stop events generated will inadvertently cause B to be restarted after the initial failover.
This patch resolves this issue by comparing the start times in central_processing mode.
A known limitation to this patch is that in order for this patch to work correctly, the cluster nodes' time must be approximately in sync.
Resolves: rhbz#743214
Signed-off-by: Lon Hohberger lhh@redhat.com --- rgmanager/src/resources/default_event_script.sl | 19 ++++++++++++++++++- 1 files changed, 18 insertions(+), 1 deletions(-)
diff --git a/rgmanager/src/resources/default_event_script.sl b/rgmanager/src/resources/default_event_script.sl index cdde066..2d5503f 100644 --- a/rgmanager/src/resources/default_event_script.sl +++ b/rgmanager/src/resources/default_event_script.sl @@ -444,6 +444,8 @@ define default_service_event_handler() variable tmp; variable owner; variable state; + variable d_trans, s_trans; + variable s_state;
debug("Executing default service event handler");
@@ -498,17 +500,32 @@ define default_service_event_handler() continue; }
- (,,, owner, state) = service_status(services[x]); + (d_trans,,,, owner, state) = service_status(services[x], 1); if ((service_state == "started") and (owner < 0) and (state == "stopped")) { info("Dependency met; starting ", services[x]); nodes = allowed_nodes(services[x]); ()=move_or_start(services[x], nodes); + continue; }
% service died - stop service(s) that depend on the dead if ((service_owner < 0) and (owner >= 0) and (depend_mode != "soft")) { + + % grab the -current- state of the service here + % If the service is running, and its dependent service + % as above is running and the dependent service was + % started at or after the service, then stopping it + % will result in unwanted service outage. + (s_trans,,,, s_state) = service_status(service_name); + if ((s_state == "started") and (state == "started") and + (d_trans >= s_trans)) { + debug("Skipping ", services[x], + "; restart not needed"); + continue; + } + info("Dependency lost; stopping ", services[x]); ()=service_stop(services[x]); }
cluster-commits@lists.fedorahosted.org