[Pacemaker] resources are restarted without obvious reasons

[Pavlos Parissis]

Hi
Could be related to a possible bug mentioned here[1]?

BTW here is the conf of pacemaker
node $id="b8ad13a6-8a6e-4304-a4a1-8f69fa735100" node-02
node $id="d5557037-cf8f-49b7-95f5-c264927a0c76" node-01
node $id="e5195d6b-ed14-4bb3-92d3-9105543f9251" node-03
primitive drbd_01 ocf:linbit:drbd \
        params drbd_resource="drbd_pbx_service_1" \
        op monitor interval="30s" \
        op start interval="0" timeout="240s" \
        op stop interval="0" timeout="120s"
primitive drbd_02 ocf:linbit:drbd \
        params drbd_resource="drbd_pbx_service_2" \
        op monitor interval="30s" \
        op start interval="0" timeout="240s" \
        op stop interval="0" timeout="120s"
primitive fs_01 ocf:heartbeat:Filesystem \
        params device="/dev/drbd1" directory="/pbx_service_01" fstype="ext3"
\
        meta migration-threshold="3" failure-timeout="60" \
        op monitor interval="20s" timeout="40s" OCF_CHECK_LEVEL="20" \
        op start interval="0" timeout="60s" \
        op stop interval="0" timeout="60s"
primitive fs_02 ocf:heartbeat:Filesystem \
        params device="/dev/drbd2" directory="/pbx_service_02" fstype="ext3"
\
        meta migration-threshold="3" failure-timeout="60" \
        op monitor interval="20s" timeout="40s" OCF_CHECK_LEVEL="20" \
        op start interval="0" timeout="60s" \
        op stop interval="0" timeout="60s"
primitive ip_01 ocf:heartbeat:IPaddr2 \
        params ip="192.168.78.10" cidr_netmask="24"
broadcast="192.168.78.255" \
        meta failure-timeout="120" migration-threshold="3" \
        op monitor interval="5s"
primitive ip_02 ocf:heartbeat:IPaddr2 \
        params ip="192.168.78.20" cidr_netmask="24"
broadcast="192.168.78.255" \
        op monitor interval="5s"
primitive pbx_01 lsb:test-01 \
        meta failure-timeout="60" migration-threshold="3"
target-role="Started" \
        op monitor interval="20s" \
        op start interval="0" timeout="60s" \
        op stop interval="0" timeout="60s"
primitive pbx_02 lsb:test-02 \
        meta failure-timeout="60" migration-threshold="3"
target-role="Started" \
        op monitor interval="20s" \
        op start interval="0" timeout="60s" \
        op stop interval="0" timeout="60s"
group pbx_service_01 ip_01 fs_01 pbx_01 \
        meta target-role="Started"
group pbx_service_02 ip_02 fs_02 pbx_02 \
        meta target-role="Started"
ms ms-drbd_01 drbd_01 \
        meta master-max="1" master-node-max="1" clone-max="2"
clone-node-max="1" notify="true" target-role="Started"
ms ms-drbd_02 drbd_02 \
        meta master-max="1" master-node-max="1" clone-max="2"
clone-node-max="1" notify="true" target-role="Started"
location PrimaryNode-drbd_01 ms-drbd_01 100: node-01
location PrimaryNode-drbd_02 ms-drbd_02 100: node-02
location PrimaryNode-pbx_service_01 pbx_service_01 200: node-01
location PrimaryNode-pbx_service_02 pbx_service_02 200: node-02
location SecondaryNode-drbd_01 ms-drbd_01 0: node-03
location SecondaryNode-drbd_02 ms-drbd_02 0: node-03
location SecondaryNode-pbx_service_01 pbx_service_01 10: node-03
location SecondaryNode-pbx_service_02 pbx_service_02 10: node-03
colocation fs_01-on-drbd_01 inf: fs_01 ms-drbd_01:Master
colocation fs_02-on-drbd_02 inf: fs_02 ms-drbd_02:Master
order pbx_service_01-after-drbd_01 inf: ms-drbd_01:promote
pbx_service_01:start
order pbx_service_02-after-drbd_02 inf: ms-drbd_02:promote
pbx_service_02:start
property $id="cib-bootstrap-options" \
        dc-version="1.0.9-89bd754939df5150de7cd76835f98fe90851b677" \
        cluster-infrastructure="Heartbeat" \
        stonith-enabled="false" \
        symmetric-cluster="false" \
        last-lrm-refresh="1285323745"
rsc_defaults $id="rsc-options" \

Cheers,
Pavlos




[1]
http://oss.clusterlabs.org/pipermail/pacemaker/2010-September/007624.html
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.clusterlabs.org/pipermail/pacemaker/attachments/20101001/1d48c4d1/attachment-0002.htm>