[Pacemaker] Monitor of LVM resources problem

[Claude.Durocher at mcccf.gouv.qc.ca]

I have a 3 node cluster running Xen resources on SLES11sp1 with HAE. The
nodes are connected to a SAN and Pacemaker controls the start of the shared
disk. From time to time, monitor of LVM volume groups or ocfs2 file system
fails : this triggers a stopping of the shared disk resource but this can't
be completed as Xen resources are running using the shared disk (I don't
know why monitor fails as the resource seems to be running fine) :

Log patterns:
Aug 13 21:27:49 qcpvms09 crmd: [9677]: ERROR: process_lrm_event: LRM
operation xen_configstore_volume1:1_monitor_120000 (32) Timed Out
(timeout=50000ms)
Aug 13 21:28:09 qcpvms09 crmd: [9677]: ERROR: process_lrm_event: LRM
operation xen_configstore_volume1:1_stop_0 (55) Timed Out (timeout=20000ms)
Aug 13 21:28:29 qcpvms09 crmd: [9677]: ERROR: process_lrm_event: LRM
operation qcdtypo01_monitor_120000 (54) Timed Out (timeout=90000ms)

Is there a way to have the monitor operation to retry x times before
declaring the resource failed? Or should the monitor part of the LVM
resource or OCFS2 resource be changed?

My running config :

node qcpvms07 \
	attributes standby="off"
node qcpvms08 \
	attributes standby="off"
node qcpvms09 \
	attributes standby="off"
primitive clvm ocf:lvm2:clvmd \
	operations $id="clvm-operations" \
	op monitor interval="120" timeout="20" start-delay="10" \
	op start interval="0" timeout="30" \
	params daemon_timeout="30" daemon_options="-d0"
primitive dlm ocf:pacemaker:controld \
	operations $id="dlm-operations" \
	op monitor interval="120" timeout="20" start-delay="10"
primitive o2cb ocf:ocfs2:o2cb \
	operations $id="o2cb-operations" \
	op monitor interval="120" timeout="20" start-delay="10"
primitive ping-net1 ocf:pacemaker:ping \
	operations $id="ping-net1-operations" \
	op monitor interval="120" timeout="20" on-fail="restart"
start-delay="0" \
	params name="ping-net1" host_list="192.168.88.1 192.168.88.43"
interval="15" timeout="5" attempts="5" \
	meta target-role="started"
primitive qcddom01 ocf:heartbeat:Xen \
	meta target-role="started" \
	operations $id="qcddom01-operations" \
	op monitor interval="120" timeout="30" on-fail="restart"
start-delay="60" \
	op start interval="0" timeout="120" start-delay="0" \
	op stop interval="0" timeout="120" \
	op migrate_from interval="0" timeout="240" \
	op migrate_to interval="0" timeout="240" \
	params xmfile="/etc/xen/vm/qcddom01" allow-migrate="true"
primitive qcdtypo01 ocf:heartbeat:Xen \
	meta target-role="started" \
	operations $id="qcdtypo01-operations" \
	op monitor interval="120" timeout="30" on-fail="restart"
start-delay="60" \
	op start interval="0" timeout="120" start-delay="0" \
	op stop interval="0" timeout="120" \
	op migrate_from interval="0" timeout="240" \
	op migrate_to interval="0" timeout="240" \
	params xmfile="/etc/xen/vm/qcdtypo01" allow-migrate="true"
primitive stonith-sbd stonith:external/sbd \
	meta target-role="started" \
	operations $id="stonith-sbd-operations" \
	op monitor interval="30" timeout="15" start-delay="30" \
	params sbd_device="/dev/mapper/mpathc"
primitive xen_configstore_volume1 ocf:heartbeat:Filesystem \
	operations $id="xen_configstore_volume1-operations" \
	op monitor interval="120" timeout="40" start-delay="10" \
	params device="/dev/xen_volume1_group/xen_configstore_volume1"
directory="/etc/xen/vm" fstype="ocfs2"
primitive xen_volume1_group ocf:heartbeat:LVM \
	operations $id="xen_volume1_group-operations" \
	op monitor interval="120" timeout="30" start-delay="10" \
	params volgrpname="xen_volume1_group"
primitive xen_volume2_group ocf:heartbeat:LVM \
	operations $id="xen_volume2_group-operations" \
	op monitor interval="120" timeout="30" start-delay="10" \
	params volgrpname="xen_volume2_group"
group shared-disk-group dlm clvm o2cb xen_volume1_group xen_volume2_group
xen_configstore_volume1 \
	meta target-role="started"
clone ping-clone ping-net1 \
	meta target-role="started" interleave="true" ordered="true"
clone shared-disk-clone shared-disk-group \
	meta target-role="stopped"
location qcddom01-on-ping-net1 qcddom01 \
	rule $id="qcddom01-on-ping-net1-rule" -inf: not_defined ping-net1 or
ping-net1 lte 0
location qcddom01-prefer-qcpvms08 qcddom01 500: qcpvms08
location qcdtypo01-on-ping-net1 qcdtypo01 \
	rule $id="qcdtypo01-on-ping-net1-rule" -inf: not_defined ping-net1 or
ping-net1 lte 0
location qcdtypo01-prefer-qcpvms07 qcdtypo01 500: qcpvms07
colocation colocation-qcddom01-shared-disk-clone inf: qcddom01
shared-disk-clone
colocation colocation-qcdtypo01-shared-disk-clone inf: qcdtypo01
shared-disk-clone
order order-qcddom01 inf: shared-disk-clone qcddom01
order order-qcdtypo01 inf: shared-disk-clone qcdtypo01
property $id="cib-bootstrap-options" \
	dc-version="1.1.2-2e096a41a5f9e184a1c1537c82c6da1093698eb5" \
	cluster-infrastructure="openais" \
	no-quorum-policy="freeze" \
	default-resource-stickiness="500" \
	last-lrm-refresh="1281552641" \
	expected-quorum-votes="3" \
	stonith-timeout="240s"
op_defaults $id="op_defaults-options" \
	record-pending="false"

Claude
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.clusterlabs.org/pipermail/pacemaker/attachments/20100817/5bf63597/attachment-0001.htm>