Increase corosync token timeout

This might prevent dropping members from corosync cluster on high load
environments. Symptoms of this problem happening can sometimes be found
in corosync log:

dub 05 17:23:45 overcloud-controller-0 corosync[14152]: [MAIN ] Corosync
main process was not scheduled for 3691.8391 ms (threshold is 1320.0000
ms). Consider token timeout increase.

The default in the Puppet manifest is 1 second, which matches the
corosync default, and we override it with hiera to 10 seconds.

Change-Id: I5ea850ada657e5eecafa3e8b28613a0ac48e78f3

diff --git a/puppet/hieradata/controller.yaml b/puppet/hieradata/controller.yaml
index 5e87793..8766263 100644 (file)
--- a/puppet/hieradata/controller.yaml
+++ b/puppet/hieradata/controller.yaml
@@ -122,6 +122,7 @@ pacemaker::corosync::cluster_name: 'tripleo_cluster'
 pacemaker::corosync::manage_fw: false
 pacemaker::resource_defaults::defaults:
   resource-stickiness: { value: INFINITY }
+corosync_token_timeout: 10000
 
 # horizon
 horizon::cache_backend: django.core.cache.backends.memcached.MemcachedCache

diff --git a/puppet/manifests/overcloud_controller_pacemaker.pp b/puppet/manifests/overcloud_controller_pacemaker.pp
index f109232..5417623 100644 (file)
--- a/puppet/manifests/overcloud_controller_pacemaker.pp
+++ b/puppet/manifests/overcloud_controller_pacemaker.pp
@@ -82,9 +82,9 @@ if hiera('step') >= 1 {
   $pacemaker_cluster_members = downcase(regsubst(hiera('controller_node_names'), ',', ' ', 'G'))
   $corosync_ipv6 = str2bool(hiera('corosync_ipv6', false))
   if $corosync_ipv6 {
-    $cluster_setup_extras = { '--ipv6' => '' }
+    $cluster_setup_extras = { '--token' => hiera('corosync_token_timeout', 1000), '--ipv6' => '' }
   } else {
-    $cluster_setup_extras = {}
+    $cluster_setup_extras = { '--token' => hiera('corosync_token_timeout', 1000) }
   }
   class { '::pacemaker':
     hacluster_pwd => hiera('hacluster_pwd'),