[Pacemaker] Resources are not started
Andreas Kurz
andreas.kurz at gmail.com
Fri Nov 4 13:57:00 UTC 2011
On 11/04/2011 01:52 PM, Matti Linnanvuori wrote:
>
> On Nov 4, 2011, at 2:37 PM, Andreas Kurz wrote:
>
>> On 11/04/2011 01:01 PM, Matti Linnanvuori wrote:
>>> I think I have found a bug. Resources are not started and I don't see a reason why not. All resources except PSQL-slave should be started. There is only one node. The operating system is SuSE Linux Enterprise Server 11 SP1.
>>>
>>> crm_mon -1 -rfo
>>> ============
>>> Last updated: Fri Nov 4 13:08:28 2011
>>> Stack: openais
>>> Current DC: iac-pgis - partition WITHOUT quorum
>>
>> *polishingcrystalball* .... hmm ... nothing, as quorum-policy already is
>> "ignore" ... don't hesitate to share your complete config if you want to
>> get help on a mailing-list ;-)
>
>
> All right, configuration follows:
hmm ... config looks ok, though it's not the freshest pacemaker version
so it might be a bug ... IIRC there were som bugs fixed regarding
resource_sets post release 1.1.2. ... try to explicitly set a score of
INFINITY for your order constraint.
Regards,
Andreas
--
Need 24/7 help with Pacemaker?
http://www.hastexo.com/now
>
> cibadmin -Q
> <cib epoch="94" num_updates="30" admin_epoch="0" validate-with="pacemaker-1.2" crm_feature_set="3.0.2" have-quorum="0" cib-last-written="Thu Nov 3 13:11:52 2011" dc-uuid="iac-pgis">
> <configuration>
> <crm_config>
> <cluster_property_set id="cib-bootstrap-options">
> <nvpair id="cib-bootstrap-options-dc-version" name="dc-version" value="1.1.2-2e096a41a5f9e184a1c1537c82c6da1093698eb5"/>
> <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-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-last-lrm-refresh" name="last-lrm-refresh" value="1320397737"/>
> </cluster_property_set>
> </crm_config>
> <nodes>
> <node id="iac-pgis" type="normal" uname="iac-pgis"/>
> </nodes>
> <resources>
> <!-- ================================================================== -->
> <!-- Resources expected in ACTIVE configuration -->
> <primitive id="PSQL-master" class="ocf" type="pgsql" provider="heartbeat">
> <instance_attributes id="psql-master-atts">
> <nvpair id="psql-master-config" name="config_file" value="/var/lib/pgsql/data/postgresql.conf"/>
> </instance_attributes>
> <operations>
> <op id="psql-master-alive" name="monitor" interval="10s"/>
> </operations>
> </primitive>
> <primitive id="rabbitmq" class="ocf" type="rabbitmq-server" provider="rabbitmq">
> <instance_attributes id="rabbit-attributes">
> <!-- Replace "localhost" with real node name -->
> <nvpair id="rabbit-nodename" name="nodename" value="rabbit at iac-pgis"/>
> </instance_attributes>
> <operations>
> <op id="rabbit-alive" name="monitor" interval="10s"/>
> </operations>
> </primitive>
> <primitive id="DB-daemon" class="ocf" type="db" provider="portalify">
> <instance_attributes id="DB-attributes">
> <nvpair id="db-binary" name="db_binary" value="/etc/init.d/iac-db"/>
> </instance_attributes>
> <operations>
> <op id="db-alive" name="monitor" interval="5s"/>
> </operations>
> </primitive>
> <primitive id="PGIS-daemon" class="ocf" type="pgis" provider="portalify">
> <instance_attributes id="PGIS-attributes">
> <nvpair id="pgis-binary" name="pgis_binary" value="/etc/init.d/iac-pgis"/>
> </instance_attributes>
> <operations>
> <op id="pgis-alive" name="monitor" interval="5s"/>
> </operations>
> </primitive>
> <primitive id="LF-daemon" class="ocf" type="lf" provider="portalify">
> <instance_attributes id="LF-attributes">
> <nvpair id="lf-binary" name="lf_binary" value="/etc/init.d/iac-location-facade"/>
> <!-- Replace "localhost" with real node name -->
> <nvpair id="lf-rabbitmq-observer-node" name="node_name" value="rabbit at iac-pgis"/>
> <nvpair id="lf-queue" name="lf_queue" value="queue.lf.location"/>
> <nvpair id="lf-observation-rounds" name="lf_obs_round" value="10"/>
> <nvpair id="lf-queue-observer-binary" name="queue_observer_binary" value="/opt/iac/openais-current/bin/check_rabbit_queue_lf.sh"/>
> <nvpair id="lf-temporary-directory" name="lf_temp_dir" value="/opt/iac/var/tmp"/>
> </instance_attributes>
> <operations>
> <op id="lf-alive" name="monitor" interval="5s"/>
> </operations>
> </primitive>
> <primitive id="audit-daemon" class="ocf" type="audit" provider="portalify">
> <instance_attributes id="audit-attributes">
> <nvpair id="audit-binary" name="audit_binary" value="/etc/init.d/iac-audit"/>
> </instance_attributes>
> <operations>
> <op id="audit-alive" name="monitor" interval="5s"/>
> </operations>
> </primitive>
> <primitive id="statusmgr-daemon" class="ocf" type="statusmgr" provider="portalify">
> <instance_attributes id="statusmgr-attributes">
> <nvpair id="statusmgr-binary" name="statusmgr_binary" value="/etc/init.d/iac-statusmgr"/>
> </instance_attributes>
> <operations>
> <op id="statusmgr-alive" name="monitor" interval="5s"/>
> </operations>
> </primitive>
> <primitive id="taskmgr-daemon" class="ocf" type="taskmgr" provider="portalify">
> <instance_attributes id="taskmgr-attributes">
> <nvpair id="taskmgr-binary" name="taskmgr_binary" value="/etc/init.d/iac-taskmgr"/>
> </instance_attributes>
> <operations>
> <op id="taskmgr-alive" name="monitor" interval="5s"/>
> </operations>
> </primitive>
> <primitive id="rm-daemon" class="ocf" type="rman" provider="portalify">
> <instance_attributes id="rm-attributes">
> <nvpair id="rm-binary" name="rm_binary" value="/etc/init.d/iac-routing"/>
> <!-- Replace "localhost" with real node name -->
> <nvpair id="rm-node" name="node_name" value="rabbit at iac-pgis"/>
> </instance_attributes>
> <operations>
> <op id="rm-alive" name="monitor" interval="5s"/>
> </operations>
> </primitive>
> <!-- ================================================================== -->
> <!-- Resources expected in STAND-BY configuration -->
> <primitive id="PSQL-slave" class="ocf" type="pgsql" provider="heartbeat">
> <instance_attributes id="psql-slave-atts">
> <!-- TODO: this should be pointing to a PostgreSQL slave configuration -->
> <nvpair id="psql-slave-config" name="config_file" value="/var/lib/pgsql/data/postgresql.conf"/>
> </instance_attributes>
> <operations>
> <op id="psql-slave-alive" name="monitor" interval="10s"/>
> </operations>
> </primitive>
> <!-- ================================================================== -->
> <!-- Resources that report system state -->
> <primitive id="rabbitmq-queue-length" class="ocf" type="rabbit-observer" provider="portalify">
> <instance_attributes id="queue-len-params">
> <nvpair id="rabbitmq-observer-limit" name="max_queue_length" value="10000"/>
> <nvpair id="rabbitmq-observer-pidfile" name="pidfile" value="/var/run/ocf-rabbitmq-observer"/>
> <nvpair id="rabbitmq-observer-binary" name="rabbit_observer_binary" value="/opt/iac/openais-current/bin/check_rabbit_queue_length.sh"/>
> <!-- Replace "localhost" with real node name -->
> <nvpair id="rabbitmq-observer-node" name="node_name" value="rabbit at iac-pgis"/>
> </instance_attributes>
> <operations>
> <op id="rabbit-limit-check" name="monitor" interval="10s"/>
> </operations>
> <meta_attributes id="meta-rabbitmq-length">
> <nvpair id="queue-length-management" name="is-managed" value="true"/>
> <nvpair id="queue-length-target" name="target-role" value="started"/>
> <nvpair id="queue-length-threshold" name="migration-threshold" value="10"/>
> </meta_attributes>
> </primitive>
> </resources>
> <constraints>
> <rsc_order id="active-order">
> <resource_set sequential="true" id="active-controls">
> <resource_ref id="PSQL-master"/>
> <resource_ref id="rabbitmq"/>
> <resource_ref id="DB-daemon"/>
> <resource_ref id="PGIS-daemon"/>
> <resource_ref id="audit-daemon"/>
> <resource_ref id="rm-daemon"/>
> <resource_ref id="statusmgr-daemon"/>
> <resource_ref id="taskmgr-daemon"/>
> </resource_set>
> <resource_set sequential="false" id="active-monitors">
> <resource_ref id="rabbitmq-queue-length"/>
> <resource_ref id="LF-daemon"/>
> </resource_set>
> </rsc_order>
> <!-- Define active and passive setups as mutually exclusive -->
> <rsc_colocation id="psql-exclusion" rsc="PSQL-slave" with-rsc="PSQL-master" score="-INFINITY"/>
> <!-- Other collocation settings are not defined: unnecessary while the system is reduced to a single node -->
> </constraints>
> <op_defaults/>
> <rsc_defaults/>
> </configuration>
> <status>
> <node_state id="iac-pgis" uname="iac-pgis" ha="active" in_ccm="true" crmd="online" join="member" expected="member" crm-debug-origin="do_update_resource" shutdown="0">
> <lrm id="iac-pgis">
> <lrm_resources>
> <lrm_resource id="PSQL-master" type="pgsql" class="ocf" provider="heartbeat">
> <lrm_rsc_op id="PSQL-master_monitor_0" operation="monitor" crm-debug-origin="do_update_resource" crm_feature_set="3.0.2" transition-key="12:1:7:05fea70b-673a-4bf9-94fe-20525ff55ea5" transition-magic="0:7;12:1:7:05fea70b-673a-4bf9-94fe-20525ff55ea5" call-id="2" rc-code="7" op-status="0" interval="0" last-run="1320319593" last-rc-change="1320319593" exec-time="320" queue-time="0" op-digest="2eee2c15d44c592a22a3c5c91d02b50b"/>
> <lrm_rsc_op id="PSQL-master_start_0" operation="start" crm-debug-origin="do_update_resource" crm_feature_set="3.0.2" transition-key="23:1:0:05fea70b-673a-4bf9-94fe-20525ff55ea5" transition-magic="0:0;23:1:0:05fea70b-673a-4bf9-94fe-20525ff55ea5" call-id="13" rc-code="0" op-status="0" interval="0" last-run="1320319596" last-rc-change="1320319596" exec-time="1610" queue-time="0" op-digest="2eee2c15d44c592a22a3c5c91d02b50b"/>
> <lrm_rsc_op id="PSQL-master_monitor_10000" operation="monitor" crm-debug-origin="do_update_resource" crm_feature_set="3.0.2" transition-key="14:2:0:05fea70b-673a-4bf9-94fe-20525ff55ea5" transition-magic="0:0;14:2:0:05fea70b-673a-4bf9-94fe-20525ff55ea5" call-id="14" rc-code="0" op-status="0" interval="10000" last-run="1320319597" last-rc-change="1320319597" exec-time="320" queue-time="0" op-digest="48e67e862a9d5260f14241e5eba3f817"/>
> </lrm_resource>
> <lrm_resource id="statusmgr-daemon" type="statusmgr" class="ocf" provider="portalify">
> <lrm_rsc_op id="statusmgr-daemon_monitor_0" operation="monitor" crm-debug-origin="do_update_resource" crm_feature_set="3.0.2" transition-key="18:1:7:05fea70b-673a-4bf9-94fe-20525ff55ea5" transition-magic="0:7;18:1:7:05fea70b-673a-4bf9-94fe-20525ff55ea5" call-id="8" rc-code="7" op-status="0" interval="0" last-run="1320319594" last-rc-change="1320319594" exec-time="190" queue-time="1010" op-digest="3c203aa468b3f34bf445200594da55da"/>
> <lrm_rsc_op id="statusmgr-daemon_start_0" operation="start" crm-debug-origin="do_update_resource" crm_feature_set="3.0.2" transition-key="29:2844:0:05fea70b-673a-4bf9-94fe-20525ff55ea5" transition-magic="0:0;29:2844:0:05fea70b-673a-4bf9-94fe-20525ff55ea5" call-id="4773" rc-code="0" op-status="0" interval="0" last-run="1320389761" last-rc-change="1320389761" exec-time="790" queue-time="0" op-digest="3c203aa468b3f34bf445200594da55da"/>
> <lrm_rsc_op id="statusmgr-daemon_monitor_5000" operation="monitor" crm-debug-origin="do_update_resource" crm_feature_set="3.0.2" transition-key="30:166:0:05fea70b-673a-4bf9-94fe-20525ff55ea5" transition-magic="0:0;30:166:0:05fea70b-673a-4bf9-94fe-20525ff55ea5" call-id="1424" rc-code="0" op-status="0" interval="5000" last-run="1320402325" last-rc-change="1320402325" exec-time="340" queue-time="0" op-digest="928b5b49dc502aa14ac0c84fc17bd8fc"/>
> <lrm_rsc_op id="statusmgr-daemon_stop_0" operation="stop" crm-debug-origin="do_update_resource" crm_feature_set="3.0.2" transition-key="32:2864:0:05fea70b-673a-4bf9-94fe-20525ff55ea5" transition-magic="0:0;32:2864:0:05fea70b-673a-4bf9-94fe-20525ff55ea5" call-id="4791" rc-code="0" op-status="0" interval="0" last-run="1320390318" last-rc-change="1320390318" exec-time="760" queue-time="310" op-digest="3c203aa468b3f34bf445200594da55da"/>
> </lrm_resource>
> <lrm_resource id="PSQL-slave" type="pgsql" class="ocf" provider="heartbeat">
> <lrm_rsc_op id="PSQL-slave_monitor_0" operation="monitor" crm-debug-origin="do_update_resource" crm_feature_set="3.0.2" transition-key="21:1:7:05fea70b-673a-4bf9-94fe-20525ff55ea5" transition-magic="0:7;21:1:7:05fea70b-673a-4bf9-94fe-20525ff55ea5" call-id="11" rc-code="7" op-status="0" interval="0" last-run="1320319595" last-rc-change="1320319595" exec-time="200" queue-time="2010" op-digest="2eee2c15d44c592a22a3c5c91d02b50b"/>
> </lrm_resource>
> <lrm_resource id="DB-daemon" type="db" class="ocf" provider="portalify">
> <lrm_rsc_op id="DB-daemon_monitor_0" operation="monitor" crm-debug-origin="do_update_resource" crm_feature_set="3.0.2" transition-key="13:2790:7:05fea70b-673a-4bf9-94fe-20525ff55ea5" transition-magic="0:0;13:2790:7:05fea70b-673a-4bf9-94fe-20525ff55ea5" call-id="4674" rc-code="0" op-status="0" interval="0" last-run="1320388096" last-rc-change="1320388096" exec-time="340" queue-time="0" op-digest="7312afa9a61f27995180efb451d71ca3"/>
> <lrm_rsc_op id="DB-daemon_monitor_5000" operation="monitor" crm-debug-origin="do_update_resource" crm_feature_set="3.0.2" transition-key="20:2791:0:05fea70b-673a-4bf9-94fe-20525ff55ea5" transition-magic="0:0;20:2791:0:05fea70b-673a-4bf9-94fe-20525ff55ea5" call-id="4675" rc-code="0" op-status="0" interval="5000" last-run="1320397718" last-rc-change="1320397718" exec-time="690" queue-time="630" op-digest="727f4d0604b62bc8c19b4159c3cfe116"/>
> <lrm_rsc_op id="DB-daemon_stop_0" operation="stop" crm-debug-origin="do_update_resource" crm_feature_set="3.0.2" transition-key="4:2913:0:05fea70b-673a-4bf9-94fe-20525ff55ea5" transition-magic="0:0;4:2913:0:05fea70b-673a-4bf9-94fe-20525ff55ea5" call-id="4818" rc-code="0" op-status="0" interval="0" last-run="1320391150" last-rc-change="1320391150" exec-time="160" queue-time="0" op-digest="7312afa9a61f27995180efb451d71ca3"/>
> <lrm_rsc_op id="DB-daemon_start_0" operation="start" crm-debug-origin="do_update_resource" crm_feature_set="3.0.2" transition-key="22:2913:0:05fea70b-673a-4bf9-94fe-20525ff55ea5" transition-magic="0:0;22:2913:0:05fea70b-673a-4bf9-94fe-20525ff55ea5" call-id="4819" rc-code="0" op-status="0" interval="0" last-run="1320391151" last-rc-change="1320391151" exec-time="280" queue-time="0" op-digest="7312afa9a61f27995180efb451d71ca3"/>
> </lrm_resource>
> <lrm_resource id="rabbitmq-queue-length" type="rabbit-observer" class="ocf" provider="portalify">
> <lrm_rsc_op id="rabbitmq-queue-length_monitor_0" operation="monitor" crm-debug-origin="do_update_resource" crm_feature_set="3.0.2" transition-key="16:2804:7:05fea70b-673a-4bf9-94fe-20525ff55ea5" transition-magic="0:7;16:2804:7:05fea70b-673a-4bf9-94fe-20525ff55ea5" call-id="4683" rc-code="7" op-status="0" interval="0" last-run="1320388838" last-rc-change="1320388838" exec-time="50" queue-time="0" op-digest="a7bad9b6c47b94452c9d645db13cb53d"/>
> <lrm_rsc_op id="rabbitmq-queue-length_start_0" operation="start" crm-debug-origin="do_update_resource" crm_feature_set="3.0.2" transition-key="38:2848:0:05fea70b-673a-4bf9-94fe-20525ff55ea5" transition-magic="0:0;38:2848:0:05fea70b-673a-4bf9-94fe-20525ff55ea5" call-id="4779" rc-code="0" op-status="0" interval="0" last-run="1320389764" last-rc-change="1320389764" exec-time="230" queue-time="0" op-digest="a7bad9b6c47b94452c9d645db13cb53d"/>
> <lrm_rsc_op id="rabbitmq-queue-length_monitor_10000" operation="monitor" crm-debug-origin="do_update_resource" crm_feature_set="3.0.2" transition-key="41:2849:0:05fea70b-673a-4bf9-94fe-20525ff55ea5" transition-magic="0:0;41:2849:0:05fea70b-673a-4bf9-94fe-20525ff55ea5" call-id="4781" rc-code="0" op-status="0" interval="10000" last-run="1320389773" last-rc-change="1320389773" exec-time="3290" queue-time="7010" op-digest="52bc73dbb39890b2e95bae24a2854fb4"/>
> <lrm_rsc_op id="rabbitmq-queue-length_stop_0" operation="stop" crm-debug-origin="do_update_resource" crm_feature_set="3.0.2" transition-key="40:2861:0:05fea70b-673a-4bf9-94fe-20525ff55ea5" transition-magic="0:0;40:2861:0:05fea70b-673a-4bf9-94fe-20525ff55ea5" call-id="4790" rc-code="0" op-status="0" interval="0" last-run="1320390316" last-rc-change="1320390316" exec-time="50" queue-time="1000" op-digest="a7bad9b6c47b94452c9d645db13cb53d"/>
> </lrm_resource>
> <lrm_resource id="audit-daemon" type="audit" class="ocf" provider="portalify">
> <lrm_rsc_op id="audit-daemon_monitor_0" operation="monitor" crm-debug-origin="do_update_resource" crm_feature_set="3.0.2" transition-key="16:2806:7:05fea70b-673a-4bf9-94fe-20525ff55ea5" transition-magic="0:0;16:2806:7:05fea70b-673a-4bf9-94fe-20525ff55ea5" call-id="4684" rc-code="0" op-status="0" interval="0" last-run="1320388858" last-rc-change="1320388858" exec-time="70" queue-time="10" op-digest="3bb0ec352fdd89523059dbf7a0d3bfb1"/>
> <lrm_rsc_op id="audit-daemon_monitor_5000" operation="monitor" crm-debug-origin="do_update_resource" crm_feature_set="3.0.2" transition-key="28:2827:0:05fea70b-673a-4bf9-94fe-20525ff55ea5" transition-magic="0:0;28:2827:0:05fea70b-673a-4bf9-94fe-20525ff55ea5" call-id="4732" rc-code="0" op-status="0" interval="5000" last-run="1320402318" last-rc-change="1320402318" exec-time="540" queue-time="0" op-digest="c7dedd75b8d5276dad877a7724401657"/>
> <lrm_rsc_op id="audit-daemon_stop_0" operation="stop" crm-debug-origin="do_update_resource" crm_feature_set="3.0.2" transition-key="26:2920:0:05fea70b-673a-4bf9-94fe-20525ff55ea5" transition-magic="0:0;26:2920:0:05fea70b-673a-4bf9-94fe-20525ff55ea5" call-id="4831" rc-code="0" op-status="0" interval="0" last-run="1320391188" last-rc-change="1320391188" exec-time="730" queue-time="0" op-digest="3bb0ec352fdd89523059dbf7a0d3bfb1"/>
> <lrm_rsc_op id="audit-daemon_start_0" operation="start" crm-debug-origin="do_update_resource" crm_feature_set="3.0.2" transition-key="25:2919:0:05fea70b-673a-4bf9-94fe-20525ff55ea5" transition-magic="0:0;25:2919:0:05fea70b-673a-4bf9-94fe-20525ff55ea5" call-id="4830" rc-code="0" op-status="0" interval="0" last-run="1320391187" last-rc-change="1320391187" exec-time="890" queue-time="10" op-digest="3bb0ec352fdd89523059dbf7a0d3bfb1"/>
> </lrm_resource>
> </lrm_resources>
> </lrm>
> <transient_attributes id="iac-pgis">
> <instance_attributes id="status-iac-pgis">
> <nvpair id="status-iac-pgis-probe_complete" name="probe_complete" value="true"/>
> <nvpair id="status-iac-pgis-last-failure-rm-daemon" name="last-failure-rm-daemon" value="1320397081"/>
> <nvpair id="status-iac-pgis-fail-count-statusmgr-daemon" name="fail-count-statusmgr-daemon" value="78"/>
> <nvpair id="status-iac-pgis-last-failure-statusmgr-daemon" name="last-failure-statusmgr-daemon" value="1320396102"/>
> <nvpair id="status-iac-pgis-last-failure-audit-daemon" name="last-failure-audit-daemon" value="1320396326"/>
> <nvpair id="status-iac-pgis-last-failure-PGIS-daemon" name="last-failure-PGIS-daemon" value="1320391209"/>
> <nvpair id="status-iac-pgis-last-failure-taskmgr-daemon" name="last-failure-taskmgr-daemon" value="1320395877"/>
> <nvpair id="status-iac-pgis-last-failure-LF-daemon" name="last-failure-LF-daemon" value="1320397121"/>
> <nvpair id="status-iac-pgis-last-failure-DB-daemon" name="last-failure-DB-daemon" value="1320397115"/>
> <nvpair id="status-iac-pgis-last-failure-rabbitmq" name="last-failure-rabbitmq" value="1320397126"/>
> <nvpair id="status-iac-pgis-last-failure-rabbitmq-queue-length" name="last-failure-rabbitmq-queue-length" value="1320331350"/>
> <nvpair id="status-iac-pgis-fail-count-DB-daemon" name="fail-count-DB-daemon" value="13"/>
> <nvpair id="status-iac-pgis-fail-count-audit-daemon" name="fail-count-audit-daemon" value="20"/>
> </instance_attributes>
> </transient_attributes>
> </node_state>
> </status>
> </cib>
>
> Matti Linnanvuori
>
>
> _______________________________________________
> Pacemaker mailing list: Pacemaker at 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
--
Need help with Pacemaker?
http://www.hastexo.com/now
More information about the Pacemaker
mailing list