Hi!
I configured my nodes *not* to auto failback after a defective node comes back
online. This worked nicely for a while, but now it doesn't (and, honestly, I do
not know what was changed in the meantime).
What we do: We disconnect the two (virtual) interfaces of our node mgmt01
(running on vmware esxi) by means of the vsphere client. Node mgmt02 takes over
the services as it should. When node mgmt01's interfaces are switched on again,
everything looks alright for a minute or two, but then mgmt01 takes over the
resources again. Which it should not. Here's the relevant sniplet of the
configuration (full config below):
location nag_loc nag_grp 100: ipfuie-mgmt01
property default-resource-stickiness="100"
I thought, that because the resource-stickiness has the same value as the
location constrain, the resources would stick to the node they are started on.
Am I wrong?
Is there any other way to let resources by default start on mgmt01 (make mgmt01
the default preferred node), but don't allow resources to migrate back after
the cluster is complete again after a split brain?
Thanks for your input,
Andreas
PS: Full config below:
node ipfuie-mgmt01
node ipfuie-mgmt02
primitive ajaxterm lsb:ajaxterm \
op monitor interval="15s" \
op start interval="0" timeout="30s" \
op stop interval="0" timeout="30s"
primitive drbd_r0 ocf:linbit:drbd \
params drbd_resource="r0" \
op monitor interval="15s" \
op start interval="0" timeout="240s" \
op stop interval="0" timeout="100s"
primitive fs_r0 ocf:heartbeat:Filesystem \
params device="/dev/drbd0" directory="/drbd" fstype="ext4" \
op start interval="0" timeout="60s" \
op stop interval="0" timeout="60s"
primitive nagios_res lsb:nagios \
op monitor interval="1min" \
op start interval="0" timeout="1min" \
op stop interval="0" timeout="1min"
primitive pingy_res ocf:pacemaker:ping \
params dampen="5s" multiplier="1000" host_list="10.10.10.205
10.10.10.206 10.10.10.254" \
op monitor interval="60s" timeout="60s" \
op start interval="0" timeout="60s"
primitive sharedIP ocf:heartbeat:IPaddr2 \
params ip="10.10.10.204" cidr_netmask="255.255.252.0" nic="eth0:0"
primitive web_res ocf:heartbeat:apache \
params configfile="/etc/apache2/httpd.conf" \
params httpd="/usr/sbin/httpd2-prefork" \
params testregex="body" statusurl="http://localhost/server-status"; \
op start interval="0" timeout="40s" \
op stop interval="0" timeout="60s" \
op monitor interval="1min"
group nag_grp fs_r0 sharedIP web_res nagios_res ajaxterm \
meta target-role="Started"
ms ms_drbd_r0 drbd_r0 \
meta master-max="1" master-node-max="1" clone-max="2"
clone-node-max="1" notify="true" target-role="Started"
clone pingy_clone pingy_res \
meta target-role="Started"
location cli-prefer-nag_grp nag_grp \
rule $id="cli-prefer-rule-nag_grp" inf: #uname eq ipfuie-mgmt01 and
#uname eq ipfuie-mgmt01
location nag_loc nag_grp 100: ipfuie-mgmt01
location only-if-connected nag_grp \
rule $id="only-if-connected-rule" -inf: not_defined pingd or pingd lte
1500
colocation nag_grp-only-on-master inf: nag_grp ms_drbd_r0:Master
order apache-after-ip inf: sharedIP web_res
order nag_grp-after-drbd inf: ms_drbd_r0:promote nag_grp:start
order nagios-after-apache inf: web_res nagios_res
property $id="cib-bootstrap-options" \
stonith-enabled="false" \
no-quorum-policy="ignore" \
stonith-action="poweroff" \
default-resource-stickiness="100" \
dc-version="1.1.2-8b9ec9ccc5060457ac761dce1de719af86895b10" \
cluster-infrastructure="openais" \
expected-quorum-votes="2" \
stop-all-resources="false" \
last-lrm-refresh="1303825164"
------------------------
CONET Solutions GmbH, Theodor-Heuss-Allee 19, 53773 Hennef.
Registergericht/Registration Court: Amtsgericht Siegburg (HRB Nr. 9136)
Gesch?ftsf?hrer/Managing Directors: J?rgen Zender (Sprecher/Chairman), Anke
H?fer
_______________________________________________
Linux-HA mailing list
Linux-HA@lists.linux-ha.org
http://lists.linux-ha.org/mailman/listinfo/linux-ha
See also: http://linux-ha.org/ReportingProblems
