Hello --
We've experienced a weird problem 3 times in the last month on different
clusters.
Environment:
- Pacemaker 1.0.9.1-1
- Corosync 1.2.5-1
- RHEL5.4
- 2 nodes
We run a simple configuration with a master/slave resource, appended below.
Three times we have found different clusters in a state where both instances
are slaves and Pacemaker seems perfectly happy with this. Looking at the
configuration (cib.xml) reveals that the target-role attribute for the
master/slave resource has changed from Master to Started. Changing the value
of this attribute back to Master fixes the problem immediately.
Any ideas what might be causing this? Nobody is doing it manually.
I'll hold off on logs until asked, this stuff can get voluminous.
Thanks, Rick Kint
<configuration>
<crm_config>
<cluster_property_set id="cib-bootstrap-options">
<nvpair id="cib-bootstrap-options-stonith-enabled" name="stonith-enabled"
value="false"/>
<nvpair id="cib-bootstrap-options-no-quorum-policy"
name="no-quorum-policy" value="ignore"/>
<nvpair id="cib-bootstrap-options-dc-version" name="dc-version"
value="1.0.9-89bd754939df5150de7cd76835f98fe90851b677"/>
<nvpair id="cib-bootstrap-options-cluster-infrastructure"
name="cluster-infrastructure" value="openais"/>
<nvpair id="cib-bootstrap-options-expected-quorum-votes"
name="expected-quorum-votes" value="2"/>
<nvpair id="cib-bootstrap-options-last-lrm-refresh"
name="last-lrm-refresh" value="1289857566"/>
</cluster_property_set>
</crm_config>
<nodes>
<node id="fnord004" type="normal" uname="fnord004"/>
<node id="fnord005" type="normal" uname="fnord005"/>
</nodes>
<resources>
<master id="Bar">
<meta_attributes id="Bar-meta_attributes">
<nvpair id="Bar-meta_attributes-clone-max" name="clone-max" value="2"/>
<nvpair id="Bar-meta_attributes-clone-node-max" name="clone-node-max"
value="1"/>
<nvpair id="Bar-meta_attributes-master-max" name="master-max"
value="1"/>
<nvpair id="Bar-meta_attributes-notify" name="notify" value="false"/>
<nvpair id="Bar-meta_attributes-target-role" name="target-role"
value="Master"/>
<nvpair id="Bar-meta_attributes-is-managed" name="is-managed"
value="true"/>
</meta_attributes>
<primitive class="ocf" id="Foo" provider="fnord" type="foo">
<operations>
<op id="Foo-start-0s" interval="0s" name="start" timeout="300s"/>
<op id="Foo-monitor-2s" interval="2s" name="monitor" role="Master"
timeout="20s"/>
<op id="Foo-monitor-3s" interval="3s" name="monitor" role="Slave"
timeout="20s"/>
</operations>
</primitive>
</master>
</resources>
<constraints/>
<op_defaults/>
<rsc_defaults>
<meta_attributes id="rsc-options">
<nvpair id="rsc-options-resource-stickiness" name="resource-stickiness"
value="100"/>
</meta_attributes>
</rsc_defaults>
</configuration>
_______________________________________________
Pacemaker mailing list: Pacemaker@oss.clusterlabs.org
http://oss.clusterlabs.org/mailman/listinfo/pacemaker
Project Home: http://www.clusterlabs.org
Getting started: http://www.clusterlabs.org/doc/Cluster_from_Scratch.pdf
Bugs: http://developerbugs.linux-foundation.org/enter_bug.cgi?product=Pacemaker
