Hi All, I am running heartbeat 2 with CRM enabled and have either a bug in my config or a general understanding problem.
What I want to do: * Application: OpenSER SIP Proxy * Active/Passive with ServiceIP * Node Migration controlled by monitoring script What actually works: * Starting heartbeat raises the shared IP and starts openser Proxy * When the NODE fails (heartbeat unresponsive) the service is migrated as expected * Monitoring with "sipsak" recognized service interruption * Heartbeat starts interrupted Openser service What does NOT work. If I "break" the openser service (broken config), the former active node indefinitely tries to restart the service. In the logs I see: * the service is started * service dies due to the broken config * monitor recognizes the breakdown * the servive is restarted -> loops Below is the used config, I'd be glad if someone can shed some light here. The Openser Script and the Config is taken with slight modificatin from http://www.anders.com/cms/259/Linux.Tutorial/OpenSer/Linux-HA/Heartbeat.v2.0 regards Oliver <cib generated="false" admin_epoch="0" have_quorum="false" ignore_dtd="false" num_peers="2" cib_feature_revision="2.0" epoch="5" num_updates="2" cib-last-written="Wed Oct 8 16:50:48 2008"> <configuration> <crm_config> <cluster_property_set id="cluster-property-set"> <attributes> <nvpair id="short_resource_names" name="short_resource_names" value="true"/> <nvpair id="pe-input-series-max" name="pe-input-series-max" value="-1"/> <nvpair id="default-resource-stickiness" name="default-resource-stickiness" value="10"/> <nvpair id="default-resource-failure-stickiness" name="default-resource-failure-stickiness" value="-10"/> <nvpair id="start-failure-is-fatal" name="start-failure-is-fatal" value="false"/> </attributes> </cluster_property_set> <cluster_property_set id="cib-bootstrap-options"> <attributes> <nvpair id="cib-bootstrap-options-last-lrm-refresh" name="last-lrm-refresh" value="1194982799"/> <nvpair id="cib-bootstrap-options-dc-version" name="dc-version" value="2.1.3-node: 552305612591183b1628baa5bc6e903e0f1e26a3"/> </attributes> </cluster_property_set> </crm_config> <nodes> <node id="69be8c91-7ae1-4483-b9b3-eae000a64990" uname="demuc1yc03" type="normal"/> <node id="ef5804f7-407c-42d1-9a57-431c7e153610" uname="demuc5yc01" type="normal"/> </nodes> <resources> <group id="IPaddr2_OpenSer_group"> <primitive id="IPaddr2-10.122.95.199" class="ocf" type="IPaddr2" provider="heartbeat"> <operations> <op id="ipaddr2-10.122.95.199-monitor" name="monitor" interval="5s" timeout="3s"/> </operations> <instance_attributes id="IPaddr2-10.122.95.199-attributes"> <attributes> <nvpair id="ipaddr2-10.122.95.199-ip" name="ip" value="10.122.95.199"/> <nvpair id="ipaddr2-10.122.95.199-broadcast" name="broadcast" value="10.122.95.255"/> <nvpair id="ipaddr2-10.122.95.199-cidr_netmask" name="cidr_netmask" value="24"/> </attributes> </instance_attributes> </primitive> <primitive id="OpenSer" class="ocf" type="OpenSer" provider="convx"> <operations> <op id="openser-start" name="start" timeout="10s"/> <op id="openser-stop" name="stop" timeout="10s"/> <op id="openser-monitor" name="monitor" interval="10s" timeout="3s"> <instance_attributes id="monitor_10s"> <attributes> <nvpair id="openser-monitor-ip" name="ip" value="10.122.95.199"/> </attributes> </instance_attributes> </op> </operations> </primitive> </group> </resources> <constraints> <rsc_location rsc="OpenSer" id="OpenSer_resource_location"> <rule id="prefered_sip_muc1" score="10"> <expression attribute="#uname" operation="eq" value="demuc1yc03" id="4730c62e-eb2e-474e-a7d9-eec3164e0044"/> </rule> <rule id="prefered_sip_muc5" score="20"> <expression attribute="#uname" operation="eq" value="demuc5yc01" id="f841d96a-c5d4-425e-a5fb-ed3483d8ab09"/> </rule> </rsc_location> </constraints> </configuration> </cib> -- Protect your environment - close windows and adopt a penguin! PGP-Key: 3B2C 8095 A7DF 8BB5 2CFF 8168 CAB7 B0DD 3985 1721 _______________________________________________ Linux-HA mailing list [email protected] http://lists.linux-ha.org/mailman/listinfo/linux-ha See also: http://linux-ha.org/ReportingProblems
