Hi,<br><br>Here is a situation from which I want either automatic (by the cluster) or manually (by the admin) to recover from.<br><br>DRBD resource runs on node 1<br>shutdown all nodes in a such order which will not cause a failover of the resources<br>
start the node 2 which was secondary prior the shutdown.<br><br>As we know DRBD wont let the cluster to start up the drbd resource because is marked outdated.<br>what would be the correct way to recover from this situation?<br>
<br>confs are at the bottom.<br><br>Regards,<br>Pavlos<br><br>node $id="b8ad13a6-8a6e-4304-a4a1-8f69fa735100" node-02<br>node $id="d5557037-cf8f-49b7-95f5-c264927a0c76" node-01<br>node $id="e5195d6b-ed14-4bb3-92d3-9105543f9251" node-03<br>
primitive drbd_01 ocf:linbit:drbd \<br> params drbd_resource="drbd_pbx_service_1" \<br> op monitor interval="30s"<br>primitive drbd_02 ocf:linbit:drbd \<br> params drbd_resource="drbd_pbx_service_2" \<br>
op monitor interval="30s"<br>primitive fs_01 ocf:heartbeat:Filesystem \<br> params device="/dev/drbd1" directory="/pbx_service_01" fstype="ext3" \<br> meta migration-threshold="3" failure-timeout="60" \<br>
op monitor interval="20s" timeout="40s" OCF_CHECK_LEVEL="20" \<br> op start interval="0" timeout="60s" \<br> op stop interval="0" timeout="60s"<br>
primitive fs_02 ocf:heartbeat:Filesystem \<br> params device="/dev/drbd2" directory="/pbx_service_02" fstype="ext3" \<br> meta migration-threshold="3" failure-timeout="60" \<br>
op monitor interval="20s" timeout="40s" OCF_CHECK_LEVEL="20" \<br> op start interval="0" timeout="60s" \<br> op stop interval="0" timeout="60s"<br>
primitive ip_01 ocf:heartbeat:IPaddr2 \<br> params ip="10.10.10.10" cidr_netmask="25" broadcast="10.10.10.127" \<br> meta failure-timeout="120" migration-threshold="3" \<br>
op monitor interval="5s"<br>primitive ip_02 ocf:heartbeat:IPaddr2 \<br> params ip="10.10.10.11" cidr_netmask="25" broadcast="10.10.10.127" \<br> op monitor interval="5s"<br>
primitive pbx_01 ocf:heartbeat:Dummy \<br> params state="/pbx_service_01/Dummy.state" \<br> meta failure-timeout="60" migration-threshold="3" \<br> op monitor interval="20s" timeout="40s"<br>
primitive pbx_02 ocf:heartbeat:Dummy \<br> params state="/pbx_service_02/Dummy.state" \<br> meta failure-timeout="60" migration-threshold="3"<br>group pbx_service_01 ip_01 fs_01 pbx_01 \<br>
meta target-role="Started"<br>group pbx_service_02 ip_02 fs_02 pbx_02 \<br> meta target-role="Started"<br>ms ms-drbd_01 drbd_01 \<br> meta master-max="1" master-node-max="1" clone-max="2" clone-node-max="1" notify="true"<br>
ms ms-drbd_02 drbd_02 \<br> meta master-max="1" master-node-max="1" clone-max="2" clone-node-max="1" notify="true" target-role="Started"<br>location PrimaryNode-drbd_01 ms-drbd_01 100: node-01<br>
location PrimaryNode-drbd_02 ms-drbd_02 100: node-02<br>location PrimaryNode-pbx_service_01 pbx_service_01 200: node-01<br>location PrimaryNode-pbx_service_02 pbx_service_02 200: node-02<br>location SecondaryNode-drbd_01 ms-drbd_01 0: node-03<br>
location SecondaryNode-drbd_02 ms-drbd_02 0: node-03<br>location SecondaryNode-pbx_service_01 pbx_service_01 10: node-03<br>location SecondaryNode-pbx_service_02 pbx_service_02 10: node-03<br>colocation fs_01-on-drbd_01 inf: fs_01 ms-drbd_01:Master<br>
colocation fs_02-on-drbd_02 inf: fs_02 ms-drbd_02:Master<br>colocation pbx_01-with-fs_01 inf: pbx_01 fs_01<br>colocation pbx_01-with-ip_01 inf: pbx_01 ip_01<br>colocation pbx_02-with-fs_02 inf: pbx_02 fs_02<br>colocation pbx_02-with-ip_02 inf: pbx_02 ip_02<br>
order fs_01-after-drbd_01 inf: ms-drbd_01:promote fs_01:start<br>order fs_02-after-drbd_02 inf: ms-drbd_02:promote fs_02:start<br>order pbx_01-after-fs_01 inf: fs_01 pbx_01<br>order pbx_01-after-ip_01 inf: ip_01 pbx_01<br>
order pbx_02-after-fs_02 inf: fs_02 pbx_02<br>order pbx_02-after-ip_02 inf: ip_02 pbx_02<br>property $id="cib-bootstrap-options" \<br> dc-version="1.0.9-89bd754939df5150de7cd76835f98fe90851b677" \<br>
cluster-infrastructure="Heartbeat" \<br> stonith-enabled="false" \<br> symmetric-cluster="false" \<br> last-lrm-refresh="1285323745"<br>rsc_defaults $id="rsc-options" \<br>
resource-stickiness="1000"<br>[root@node-02 ~]# cat /etc/drbd.conf<br>#<br># please have a a look at the example configuration file in<br># /usr/share/doc/drbd83/drbd.conf<br>#<br><br>global {<br> usage-count yes;<br>
}<br>common {<br> protocol C;<br><br> syncer {<br> csums-alg sha1;<br> verify-alg sha1;<br> rate 10M;<br> }<br><br> net {<br> data-integrity-alg sha1;<br> max-buffers 20480;<br> max-epoch-size 16384;<br>
}<br><br> disk {<br> on-io-error detach;<br>### Only when DRBD is under cluster ###<br> fencing resource-only;<br>### --- ###<br> }<br><br> startup {<br> wfc-timeout 60;<br> degr-wfc-timeout 30;<br> outdated-wfc-timeout 15;<br>
}<br><br>### Only when DRBD is under cluster ###<br> handlers {<br> split-brain "/usr/lib/drbd/notify-split-brain.sh root";<br> fence-peer "/usr/lib/drbd/crm-fence-peer.sh";<br> after-resync-target "/usr/lib/drbd/crm-unfence-peer.sh";<br>
}<br>### --- ###<br>}<br><br>resource drbd_pbx_service_1 {<br><br> on node-01 {<br> device /dev/drbd1;<br> disk /dev/sdd1;<br> address <a href="http://10.10.10.129:7789">10.10.10.129:7789</a>;<br> meta-disk internal;<br>
}<br> on node-03 {<br> device /dev/drbd1;<br> disk /dev/sdd1;<br> address <a href="http://10.10.10.131:7789">10.10.10.131:7789</a>;<br> meta-disk internal;<br> }<br>}<br><br>resource drbd_pbx_service_2 {<br>
<br> on node-02 {<br> device /dev/drbd2;<br> disk /dev/sdb1;<br> address <a href="http://10.10.10.130:7790">10.10.10.130:7790</a>;<br> meta-disk internal;<br> }<br> on node-03 {<br> device /dev/drbd2;<br>
disk /dev/sdc1;<br> address <a href="http://10.10.10.131:7790">10.10.10.131:7790</a>;<br> meta-disk internal;<br> }<br>}<br><br>