Hi,
I use heartbeat 2.1.1 in an active/passive configuration.
I'am testing differents failover and how stonith reacts ?
When my active node is down (hardware failure or simply kill -9 PID(hb
master)), Stonith with apcmastersnmp from my standby node shoot the active node
and resources are failover on the standby node. GOOD...
Now my problem:
1- If I unplug the network card, pingd reacts and failover the resources on the
other node BUT stonith doesn't shoot the active node before.
2- Same problem whith resource's failure, at the end of the sixth failure
(depends of my configuration stickiness), the resources are failover on the
standby node BUT again, stonith doesn't shoot the node.
Do i miss sommething ? how to obtain the anticipated result ?
I attach my cib.xml for information.
Thanks
Fabrice
<cib admin_epoch="6" have_quorum="false" ignore_dtd="false" num_peers="2" cib_feature_revision="1.3" generated="false" epoch="39" num_updates="1" cib-last-written="Wed Sep 19 14:49:41 2007">
<configuration>
<crm_config>
<cluster_property_set id="cib-bootstrap-options">
<attributes>
<nvpair id="cib-bootstrap-options-symmetric-cluster" name="symmetric-cluster" value="true"/>
<nvpair id="cib-bootstrap-options-no-quorum-policy" name="no-quorum-policy" value="stop"/>
<nvpair id="cib-bootstrap-options-default-resource-stickiness" name="default-resource-stickiness" value="200"/>
<nvpair id="cib-bootstrap-options-default-resource-failure-stickiness" name="default-resource-failure-stickiness" value="-200"/>
<nvpair id="cib-bootstrap-options-stonith-enabled" name="stonith-enabled" value="true"/>
<nvpair id="cib-bootstrap-options-stonith-action" name="stonith-action" value="reboot"/>
<nvpair id="cib-bootstrap-options-stop-orphan-resources" name="stop-orphan-resources" value="true"/>
<nvpair id="cib-bootstrap-options-stop-orphan-actions" name="stop-orphan-actions" value="true"/>
<nvpair id="cib-bootstrap-options-remove-after-stop" name="remove-after-stop" value="false"/>
<nvpair id="cib-bootstrap-options-short-resource-names" name="short-resource-names" value="true"/>
<nvpair id="cib-bootstrap-options-transition-idle-timeout" name="transition-idle-timeout" value="60s"/>
<nvpair id="cib-bootstrap-options-default-action-timeout" name="default-action-timeout" value="15s"/>
<nvpair id="cib-bootstrap-options-is-managed-default" name="is-managed-default" value="true"/>
<nvpair name="last-lrm-refresh" id="cib-bootstrap-options-last-lrm-refresh" value="1190203977"/>
</attributes>
</cluster_property_set>
</crm_config>
<nodes>
<node id="47cb4e3e-7c8f-4dc0-9da8-d9744815ed53" uname="castor" type="normal"/>
<node id="6bf7fba5-aa0e-40c8-b9d0-fcff43e6c066" uname="pollux" type="normal"/>
</nodes>
<resources>
<group id="group_1">
<primitive class="ocf" id="IPaddr_147_210_36_7" provider="heartbeat" type="IPaddr">
<operations>
<op id="IPaddr_147_210_36_7_mon" interval="5s" name="monitor" timeout="5s"/>
</operations>
<instance_attributes id="IPaddr_147_210_36_7_inst_attr">
<attributes>
<nvpair id="IPaddr_147_210_36_7_attr_0" name="ip" value="147.210.36.7"/>
<nvpair id="IPaddr_147_210_36_7_attr_1" name="netmask" value="255.255.255.0"/>
<nvpair id="IPaddr_147_210_36_7_attr_2" name="nic" value="eth0"/>
</attributes>
</instance_attributes>
</primitive>
<primitive class="ocf" id="Filesystem_2" provider="heartbeat" type="Filesystem">
<operations>
<op id="Filesystem_2_mon" interval="60s" name="monitor" timeout="60s"/>
</operations>
<instance_attributes id="Filesystem_2_inst_attr">
<attributes>
<nvpair id="Filesystem_2_attr_0" name="device" value="/dev/VolGroup01/maillv"/>
<nvpair id="Filesystem_2_attr_1" name="directory" value="/mailsan"/>
<nvpair id="Filesystem_2_attr_2" name="fstype" value="ext3"/>
<nvpair id="Filesystem_2_attr_3" name="options" value="noatime"/>
</attributes>
</instance_attributes>
</primitive>
<primitive class="lsb" id="cyrus-imapd_3" provider="heartbeat" type="cyrus-imapd">
<operations>
<op id="cyrus-imapd_3_mon" interval="60s" name="monitor" timeout="45s"/>
</operations>
</primitive>
<primitive class="lsb" id="saslauthd_4" provider="heartbeat" type="saslauthd">
<operations>
<op id="saslauthd_4_mon" interval="60s" name="monitor" timeout="45s"/>
</operations>
</primitive>
</group>
<clone id="pingd">
<instance_attributes id="pingd">
<attributes>
<nvpair id="pingd-clone_node_max" name="clone_node_max" value="1"/>
</attributes>
</instance_attributes>
<primitive id="pingd-child" provider="heartbeat" class="ocf" type="pingd">
<operations>
<op id="pingd-child-monitor" name="monitor" interval="20s" timeout="40s" prereq="nothing"/>
<op id="pingd-child-start" name="start" prereq="nothing"/>
</operations>
<instance_attributes id="pingd_inst_attr">
<attributes>
<nvpair id="pingd-dampen" name="dampen" value="5s"/>
<nvpair id="pingd-multiplier" name="multiplier" value="100"/>
</attributes>
</instance_attributes>
</primitive>
</clone>
<clone id="DoFencing">
<instance_attributes id="DoFencing_inst_attr">
<attributes>
<nvpair id="DoFencing_attr_1" name="clone_max" value="2"/>
<nvpair id="DoFencing_attr_2" name="clone_node_max" value="1"/>
</attributes>
</instance_attributes>
<primitive class="stonith" id="child_DoFencing" provider="heartbeat" type="apcmastersnmp">
<operations>
<op id="stonith_mon" interval="10s" name="monitor" prereq="nothing" timeout="60s"/>
<op id="stonith_start" name="start" prereq="nothing" timeout="60s"/>
</operations>
<instance_attributes id="stonith_inst_attr">
<attributes>
<nvpair id="stonith_attr_2" name="ipaddr" value="192.168.100.254"/>
<nvpair id="stonith_attr_3" name="port" value="161"/>
<nvpair id="stonith_attr_4" name="community" value="private"/>
</attributes>
</instance_attributes>
</primitive>
</clone>
</resources>
<constraints>
<rsc_location rsc="group_1" id="rsc_location_group_1">
<rule id="prefered_location_group_1" score="200">
<expression attribute="#uname" id="prefered_location_group_1_expr" operation="eq" value="castor"/>
</rule>
<rule id="group_1:connected:rule" score="-INFINITY" boolean_op="and">
<expression id="my_resource:connected:expr:zero" attribute="pingd" operation="lte" value="0"/>
</rule>
</rsc_location>
</constraints>
</configuration>
</cib>
_______________________________________________
Linux-HA mailing list
[email protected]
http://lists.linux-ha.org/mailman/listinfo/linux-ha
See also: http://linux-ha.org/ReportingProblems
