Hi,
today one DomU running mainly Apache, Typo3, MySQL went unusable.
Last message from Nagios:
Ram : 98%, Swap : 100% : 99, 90 : CRITICAL
Logging in with xm console I saw oom-killer messages and did an xm
destroy.
Is there any solution to automatically destroy and restart a DomU in
such a case?
The current crm config is as follows (only the relevant part of one
DomU):
xen11:/# crm configure show
node $id="xxx" xen11
node $id="yyy" xen10
primitive xen_drbd2_1 ocf:linbit:drbd \
params drbd_resource="drbd2_1" \
op monitor interval="15s" \
op start interval="0" timeout="240s" \
op stop interval="0" timeout="100s"
primitive xen_drbd2_2 ocf:linbit:drbd \
params drbd_resource="drbd2_2" \
op monitor interval="15s" \
op start interval="0" timeout="240s" \
op stop interval="0" timeout="100s"
primitive xen_typo3 ocf:heartbeat:Xen \
params xmfile="/etc/xen/typo3.cfg" \
op monitor interval="3s" timeout="30s" \
op start interval="0" timeout="60s" \
op stop interval="0" timeout="40s" \
meta target-role="Started" allow-migrate="false" is-managed="true"
group group_drbd2 xen_drbd2_1 xen_drbd2_2
ms DrbdClone2 group_drbd2 \
meta master_max="1" master-mode-max="1" clone-max="2" clone-node-
max="1" notify="true"
location cli-prefer-xen_typo3 xen_typo3 \
rule $id="cli-prefer-rule-xen_typo3" inf: #uname eq xen10
colocation xen_typo3_and_drbd inf: xen_typo3 DrbdClone2:Master
order xen_typo3_after_drbd inf: DrbdClone2:promote xen_typo3:start
property $id="cib-bootstrap-options" \
dc-version="1.0.9-74392a28b7f31d7ddc86689598bd23114f58978b" \
cluster-infrastructure="Heartbeat" \
stonith-enabled="false" \
no-quorum-policy="ignore" \
last-lrm-refresh="1331211005" \
maintenance-mode="false"
rsc_defaults $id="rsc-options" \
resource-stickiness="100"
TIA
Helmut Wollmersdorfer
_______________________________________________
Linux-HA mailing list
[email protected]
http://lists.linux-ha.org/mailman/listinfo/linux-ha
See also: http://linux-ha.org/ReportingProblems
