[Sorry for the partial message I sent earlier.  Here's the full one.]

I am attempting to write my own resource agent to support postgres WAL log
shipping.  My PostgreSQL primitive is currently stuck in a FAILED state due
to a bug in the resource agent script that I have fixed, and I can't figure
out how to get the primitive working again.

I tried moving it to another node:
root@trustcentric2:~# crm resource move PostgreSQL trustcentric1

This does not give an error, but the primitive is still on trustcentric2:

root@trustcentric1:~# crm_mon -1
============
Last updated: Fri Feb 18 07:49:13 2011
Stack: Heartbeat
Current DC: trustcentric2 (28ebee49-31c7-419e-a29a-c939c3a241bd) - partition
with quorum
Version: 1.0.8-042548a451fce8400660f6031f4da6f0223dd5dd
2 Nodes configured, unknown expected votes
2 Resources configured.
============

Online: [ trustcentric1 trustcentric2 ]

 ClusterIP      (ocf::heartbeat:IPaddr2) Started [      trustcentric1
trustcentric2 ]
 PostgreSQL     (ocf::trustcentric:postgresql): Started trustcentric2
(unmanaged) FAILED

Failed actions:
    PostgreSQL_start_0 (node=trustcentric2, call=10, rc=-2, status=Timed
Out): unknown exec error
    PostgreSQL_stop_0 (node=trustcentric2, call=11, rc=1, status=complete):
unknown error

How do I get PostgreSQL running again?  I have attached an XML dump.

Thanks,
Jody
<cib validate-with="pacemaker-1.0" crm_feature_set="3.0.1" have-quorum="1" dc-uuid="28ebee49-31c7-419e-a29a-c939c3a241bd" admin_epoch="0" epoch="44" num_updates="7" cib-last-written="Thu Feb 17 19:21:07 2011">
  <configuration>
    <crm_config>
      <cluster_property_set id="cib-bootstrap-options">
        <nvpair id="cib-bootstrap-options-dc-version" name="dc-version" value="1.0.8-042548a451fce8400660f6031f4da6f0223dd5dd"/>
        <nvpair id="cib-bootstrap-options-cluster-infrastructure" name="cluster-infrastructure" value="Heartbeat"/>
        <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"/>
      </cluster_property_set>
    </crm_config>
    <nodes>
      <node id="7afb9c87-2252-4c07-879b-4eaccfc9bd5b" uname="trustcentric1" type="normal"/>
      <node id="28ebee49-31c7-419e-a29a-c939c3a241bd" uname="trustcentric2" type="normal"/>
    </nodes>
    <resources>
      <primitive class="ocf" id="ClusterIP" provider="heartbeat" type="IPaddr2">
        <instance_attributes id="ClusterIP-instance_attributes">
          <nvpair id="ClusterIP-instance_attributes-ip" name="ip" value="172.16.46.99"/>
          <nvpair id="ClusterIP-instance_attributes-cidr_netmask" name="cidr_netmask" value="24"/>
        </instance_attributes>
        <operations>
          <op id="ClusterIP-monitor-30s" interval="30s" name="monitor"/>
        </operations>
      </primitive>
      <primitive class="ocf" id="PostgreSQL" provider="trustcentric" type="postgresql"/>
    </resources>
    <constraints>
      <rsc_colocation id="postgresql-with-ip" rsc="PostgreSQL" score="INFINITY" with-rsc="ClusterIP"/>
      <rsc_order first="ClusterIP" id="postgresql-after-ip" score="INFINITY" then="PostgreSQL"/>
      <rsc_location id="cli-prefer-PostgreSQL" rsc="PostgreSQL">
        <rule id="cli-prefer-rule-PostgreSQL" score="INFINITY" boolean-op="and">
          <expression id="cli-prefer-expr-PostgreSQL" attribute="#uname" operation="eq" value="trustcentric1" type="string"/>
        </rule>
      </rsc_location>
      <rsc_location id="cli-prefer-ClusterIP" rsc="ClusterIP">
        <rule id="cli-prefer-rule-ClusterIP" score="INFINITY" boolean-op="and">
          <expression id="cli-prefer-expr-ClusterIP" attribute="#uname" operation="eq" value="trustcentric1" type="string"/>
        </rule>
      </rsc_location>
    </constraints>
    <rsc_defaults>
      <meta_attributes id="rsc-options">
        <nvpair id="rsc-options-resource-stickiness" name="resource-stickiness" value="100"/>
      </meta_attributes>
    </rsc_defaults>
    <op_defaults/>
  </configuration>
  <status>
    <node_state uname="trustcentric1" ha="active" in_ccm="true" crmd="online" shutdown="0" join="member" id="7afb9c87-2252-4c07-879b-4eaccfc9bd5b" expected="member" crm-debug-origin="do_state_transition">
      <transient_attributes id="7afb9c87-2252-4c07-879b-4eaccfc9bd5b">
        <instance_attributes id="status-7afb9c87-2252-4c07-879b-4eaccfc9bd5b">
          <nvpair id="status-7afb9c87-2252-4c07-879b-4eaccfc9bd5b-fail-count-ClusterIP" name="fail-count-ClusterIP" value="1"/>
          <nvpair id="status-7afb9c87-2252-4c07-879b-4eaccfc9bd5b-last-failure-ClusterIP" name="last-failure-ClusterIP" value="1297961272"/>
          <nvpair id="status-7afb9c87-2252-4c07-879b-4eaccfc9bd5b-probe_complete" name="probe_complete" value="true"/>
        </instance_attributes>
      </transient_attributes>
      <lrm id="7afb9c87-2252-4c07-879b-4eaccfc9bd5b">
        <lrm_resources>
          <lrm_resource id="ClusterIP" type="IPaddr2" class="ocf" provider="heartbeat">
            <lrm_rsc_op id="ClusterIP_monitor_0" operation="monitor" crm-debug-origin="build_active_RAs" crm_feature_set="3.0.1" transition-key="5:0:7:87c27c7a-6a36-4ff7-a324-e601fbbd4a8a" transition-magic="0:7;5:0:7:87c27c7a-6a36-4ff7-a324-e601fbbd4a8a" call-id="2" rc-code="7" op-status="0" interval="0" last-run="1297894810" last-rc-change="1297894810" exec-time="30" queue-time="0" op-digest="0e7882c4c01ea5e641399e6aaf1e0265"/>
            <lrm_rsc_op id="ClusterIP_stop_0" operation="stop" crm-debug-origin="build_active_RAs" crm_feature_set="3.0.1" transition-key="7:39:0:87c27c7a-6a36-4ff7-a324-e601fbbd4a8a" transition-magic="0:0;7:39:0:87c27c7a-6a36-4ff7-a324-e601fbbd4a8a" call-id="8" rc-code="0" op-status="0" interval="0" last-run="1297982262" last-rc-change="1297982262" exec-time="80" queue-time="0" op-digest="0e7882c4c01ea5e641399e6aaf1e0265"/>
            <lrm_rsc_op id="ClusterIP_start_0" operation="start" crm-debug-origin="build_active_RAs" crm_feature_set="3.0.1" transition-key="9:39:0:87c27c7a-6a36-4ff7-a324-e601fbbd4a8a" transition-magic="0:0;9:39:0:87c27c7a-6a36-4ff7-a324-e601fbbd4a8a" call-id="9" rc-code="0" op-status="0" interval="0" last-run="1297982263" last-rc-change="1297982263" exec-time="40" queue-time="0" op-digest="0e7882c4c01ea5e641399e6aaf1e0265"/>
            <lrm_rsc_op id="ClusterIP_monitor_30000" operation="monitor" crm-debug-origin="build_active_RAs" crm_feature_set="3.0.1" transition-key="1:39:0:87c27c7a-6a36-4ff7-a324-e601fbbd4a8a" transition-magic="0:0;1:39:0:87c27c7a-6a36-4ff7-a324-e601fbbd4a8a" call-id="10" rc-code="0" op-status="0" interval="30000" last-run="1298029385" last-rc-change="1297982266" exec-time="10" queue-time="0" op-digest="8e6968ccf21d8107aaf5a58888656b7d"/>
          </lrm_resource>
          <lrm_resource id="PostgreSQL" type="postgresql" class="ocf" provider="trustcentric">
            <lrm_rsc_op id="PostgreSQL_monitor_0" operation="monitor" crm-debug-origin="build_active_RAs" crm_feature_set="3.0.1" transition-key="5:46:7:87c27c7a-6a36-4ff7-a324-e601fbbd4a8a" transition-magic="0:7;5:46:7:87c27c7a-6a36-4ff7-a324-e601fbbd4a8a" call-id="11" rc-code="7" op-status="0" interval="0" last-run="1297988151" last-rc-change="1297988151" exec-time="20" queue-time="0" op-digest="f2317cad3d54cec5d7d7aa7d0bf35cf8"/>
          </lrm_resource>
        </lrm_resources>
      </lrm>
    </node_state>
    <node_state uname="trustcentric2" ha="active" in_ccm="true" crmd="online" join="member" shutdown="0" id="28ebee49-31c7-419e-a29a-c939c3a241bd" expected="member" crm-debug-origin="do_state_transition">
      <transient_attributes id="28ebee49-31c7-419e-a29a-c939c3a241bd">
        <instance_attributes id="status-28ebee49-31c7-419e-a29a-c939c3a241bd">
          <nvpair id="status-28ebee49-31c7-419e-a29a-c939c3a241bd-probe_complete" name="probe_complete" value="true"/>
          <nvpair id="status-28ebee49-31c7-419e-a29a-c939c3a241bd-fail-count-PostgreSQL" name="fail-count-PostgreSQL" value="INFINITY"/>
          <nvpair id="status-28ebee49-31c7-419e-a29a-c939c3a241bd-last-failure-PostgreSQL" name="last-failure-PostgreSQL" value="1297988174"/>
        </instance_attributes>
      </transient_attributes>
      <lrm id="28ebee49-31c7-419e-a29a-c939c3a241bd">
        <lrm_resources>
          <lrm_resource id="ClusterIP" type="IPaddr2" class="ocf" provider="heartbeat">
            <lrm_rsc_op id="ClusterIP_monitor_0" operation="monitor" crm-debug-origin="build_active_RAs" crm_feature_set="3.0.1" transition-key="6:0:7:50d637b9-b30f-4d9f-b289-16dee69a649b" transition-magic="0:7;6:0:7:50d637b9-b30f-4d9f-b289-16dee69a649b" call-id="2" rc-code="7" op-status="0" interval="0" last-run="1297894774" last-rc-change="1297894774" exec-time="40" queue-time="0" op-digest="0e7882c4c01ea5e641399e6aaf1e0265"/>
            <lrm_rsc_op id="ClusterIP_stop_0" operation="stop" crm-debug-origin="build_active_RAs" crm_feature_set="3.0.1" transition-key="8:39:0:87c27c7a-6a36-4ff7-a324-e601fbbd4a8a" transition-magic="0:0;8:39:0:87c27c7a-6a36-4ff7-a324-e601fbbd4a8a" call-id="8" rc-code="0" op-status="0" interval="0" last-run="1297982261" last-rc-change="1297982261" exec-time="30" queue-time="0" op-digest="0e7882c4c01ea5e641399e6aaf1e0265"/>
            <lrm_rsc_op id="ClusterIP_start_0" operation="start" crm-debug-origin="build_active_RAs" crm_feature_set="3.0.1" transition-key="4:99:0:87c27c7a-6a36-4ff7-a324-e601fbbd4a8a" transition-magic="0:0;4:99:0:87c27c7a-6a36-4ff7-a324-e601fbbd4a8a" call-id="12" rc-code="0" op-status="0" interval="0" last-run="1298028581" last-rc-change="1298028581" exec-time="1490" queue-time="0" op-digest="0e7882c4c01ea5e641399e6aaf1e0265"/>
            <lrm_rsc_op id="ClusterIP_monitor_30000" operation="monitor" crm-debug-origin="build_active_RAs" crm_feature_set="3.0.1" transition-key="5:99:0:87c27c7a-6a36-4ff7-a324-e601fbbd4a8a" transition-magic="0:0;5:99:0:87c27c7a-6a36-4ff7-a324-e601fbbd4a8a" call-id="13" rc-code="0" op-status="0" interval="30000" last-run="1298029392" last-rc-change="1298028582" exec-time="20" queue-time="0" op-digest="8e6968ccf21d8107aaf5a58888656b7d"/>
          </lrm_resource>
          <lrm_resource id="PostgreSQL" type="postgresql" class="ocf" provider="trustcentric">
            <lrm_rsc_op id="PostgreSQL_monitor_0" operation="monitor" crm-debug-origin="build_active_RAs" crm_feature_set="3.0.1" transition-key="7:46:7:87c27c7a-6a36-4ff7-a324-e601fbbd4a8a" transition-magic="0:7;7:46:7:87c27c7a-6a36-4ff7-a324-e601fbbd4a8a" call-id="9" rc-code="7" op-status="0" interval="0" last-run="1297988151" last-rc-change="1297988151" exec-time="30" queue-time="0" op-digest="f2317cad3d54cec5d7d7aa7d0bf35cf8"/>
            <lrm_rsc_op id="PostgreSQL_start_0" operation="start" crm-debug-origin="build_active_RAs" crm_feature_set="3.0.1" transition-key="10:46:0:87c27c7a-6a36-4ff7-a324-e601fbbd4a8a" transition-magic="2:-2;10:46:0:87c27c7a-6a36-4ff7-a324-e601fbbd4a8a" call-id="10" rc-code="-2" op-status="2" interval="0" last-run="1297988153" last-rc-change="1297988173" exec-time="20000" queue-time="0" op-digest="f2317cad3d54cec5d7d7aa7d0bf35cf8"/>
            <lrm_rsc_op id="PostgreSQL_stop_0" operation="stop" crm-debug-origin="build_active_RAs" crm_feature_set="3.0.1" transition-key="2:49:0:87c27c7a-6a36-4ff7-a324-e601fbbd4a8a" transition-magic="0:1;2:49:0:87c27c7a-6a36-4ff7-a324-e601fbbd4a8a" call-id="11" rc-code="1" op-status="0" interval="0" last-run="1297988173" last-rc-change="1297988173" exec-time="20" queue-time="0" op-digest="f2317cad3d54cec5d7d7aa7d0bf35cf8"/>
          </lrm_resource>
        </lrm_resources>
      </lrm>
    </node_state>
  </status>
</cib>
_______________________________________________
Pacemaker mailing list: [email protected]
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

Reply via email to