Hello, I started a small test cluster using heartbeat 2.1.1. The cluster contains one simple master/slave resource.
While playing around with this cluster, I've noticed that whenever the resource
is promoted to be the master on a machine, Heartbeat stops calling its monitor
operation on this node. A quick look on the ha-debug log reveals that the
monitor op is stopped intentionally, because of the resource promotion.
However, there is no restarting of this op once the node becomes the master.
When a second node starts and its resource takes the master role, our demoted
resource starts to be monitored again.
I'm attaching my cib.xml, ha-debug and the resource agent script. Do I have a
configuration error, or have I encountered a bug?
Thanks,
Assaf
____________________________________________________________________________________
Check out the hottest 2008 models today at Yahoo! Autos.
http://autos.yahoo.com/new_cars.html <cib admin_epoch="0" have_quorum="true" ignore_dtd="false" num_peers="0" cib_feature_revision="1.3" generated="false" epoch="1380" num_updates="6" cib-last-written="Mon Oct 1 16:01:45 2007" ccm_transition="1">
<configuration>
<crm_config>
<cluster_property_set id="cluster_properties">
<attributes>
<nvpair id="default-resource-stickiness" name="default-resource-stickiness" value="70"/>
<nvpair id="default-resource-failure-stickiness" name="default-resource-failure-stickiness" value="-100"/>
</attributes>
</cluster_property_set>
<cluster_property_set id="cib-bootstrap-options">
<attributes>
<nvpair name="last-lrm-refresh" id="cib-bootstrap-options-last-lrm-refresh" value="1191164402"/>
</attributes>
</cluster_property_set>
</crm_config>
<nodes>
<node id="0441b161-2421-4218-8b03-0c044937e197" uname="rh4vm1" type="normal">
<instance_attributes id="master-0441b161-2421-4218-8b03-0c044937e197">
<attributes>
<nvpair id="nodes-master-rsc_smith:1-0441b161-2421-4218-8b03-0c044937e197" name="master-rsc_smith:1" value="20"/>
<nvpair id="nodes-master-rsc_smith:0-0441b161-2421-4218-8b03-0c044937e197" name="master-rsc_smith:0" value="20"/>
</attributes>
</instance_attributes>
</node>
<node uname="rh4vm2" type="normal" id="f55d8a1b-6931-4a84-989c-7f241ce2897e">
<instance_attributes id="master-f55d8a1b-6931-4a84-989c-7f241ce2897e">
<attributes>
<nvpair name="master-rsc_smith:0" id="nodes-master-rsc_smith:0-f55d8a1b-6931-4a84-989c-7f241ce2897e" value="30"/>
<nvpair name="master-rsc_smith:1" id="nodes-master-rsc_smith:1-f55d8a1b-6931-4a84-989c-7f241ce2897e" value="20"/>
</attributes>
</instance_attributes>
</node>
</nodes>
<resources>
<master_slave id="master_slave_mvap" ordered="false" interleave="false" notify="false">
<instance_attributes id="ia_clone_ip">
<attributes>
<nvpair id="nvpair_ms_grp_mvap_clone_max" name="clone_max" value="2"/>
<nvpair id="nvpair_ms_grp_mvap_clone_node_max" name="clone_node_max" value="1"/>
<nvpair id="nvpair_ms_grp_mvap_master_max" name="master_max" value="1"/>
<nvpair id="nvpair_ms_grp_mvap_master_node_max" name="master_node_max" value="1"/>
</attributes>
</instance_attributes>
<primitive id="rsc_smith" class="ocf" type="smith2_agent" provider="ML">
<operations>
<op id="op_smith_monitor_special" name="monitor" timeout="3s" interval="3000ms">
<instance_attributes id="ia_smith_monitor_special">
<attributes>
<nvpair id="nvpair_smith_monitor_special_action" name="monitor_action" value="BIT1"/>
</attributes>
</instance_attributes>
</op>
</operations>
</primitive>
</master_slave>
</resources>
<constraints/>
</configuration>
</cib>
ha-debug
Description: Binary data
smith2_agent
Description: Binary data
_______________________________________________ Linux-HA mailing list [email protected] http://lists.linux-ha.org/mailman/listinfo/linux-ha See also: http://linux-ha.org/ReportingProblems
