[Pacemaker] Question: 2 node cluster in two datacenters - how to avoid split brain

[Senftleben, Stefan (itsc)]

Hello,

first of all I want to say hello all recipients of the pacemaker mailinglist!

I manage a two node active-passive cluster with an ms-drbd-resource and a depending resource.
Each node is located in a separate datacenter, connected by a single dwdm-connection, a second network connection is not available.
In case of a network interuption between the datacenters a split brain situation is created and a manual intervention of the admin is needed.

What are your recommendations for me to avoid the split brain situation?



Thanks in advance!

Best regards,

Stefan



Following the configuration:

     node lxds05 \
             attributes standby="off"
     node lxds07 \
             attributes standby="off"
     primitive apache2 ocf:heartbeat:apache \
             params configfile="/etc/apache2/apache2.conf" httpd="/usr/sbin/apache2" \
             operations $id="apache2-operations" \
             op start interval="0" timeout="240" \
             op stop interval="0" timeout="240" \
             op monitor interval="15" timeout="20" start-delay="0" \
             meta target-role="started" failure-timeout="60"
     primitive omd_site_main ocf:omd:omdnagios \
             params site="main" \
             op monitor interval="30s" timeout="30s" \
             op start interval="0s" timeout="240s" \
             op stop interval="0s" timeout="240s" \
             meta target-role="Started" failure-timeout="60"
     primitive pri_drbd_omd ocf:linbit:drbd \
             params drbd_resource="nagios" \
             operations $id="drbd_disk-operations" \
             op monitor interval="10" timeout="240" \
             meta failure-timeout="60"
     primitive pri_fs_omd ocf:heartbeat:Filesystem \
             params device="/dev/drbd0" directory="/opt/omd/" fstype="ext4" \
             operations $id="pri_fs_omd-operations" \
             op start interval="0" timeout="240" \
             op stop interval="0" timeout="360" \
             op monitor interval="15" timeout="20" start-delay="0" \
             op notify interval="0" timeout="20" \
             meta target-role="started" failure-timeout="60"
     primitive pri_nagiosIP ocf:heartbeat:IPaddr2 \
             params ip="192.168.12.21" cidr_netmask="24" iflabel="NagiosIP" \
             operations $id="pri_nagiosIP-operations" \
             op start interval="0" timeout="20" \
             op stop interval="0" timeout="20" \
             op monitor interval="10" timeout="20" start-delay="0" \
             meta target-role="started" failure-timeout="60"
     primitive res_MailTo_1 ocf:heartbeat:MailTo \
             params email="stefan.senftleben at itsc.de" subject="nagios-group" \
             operations $id="res_MailTo_1-operations" \
             op start interval="0" timeout="10" \
             op stop interval="0" timeout="10" \
             op monitor interval="10" timeout="10" start-delay="0" \
             meta failure-timeout="60"
     primitive res_MailTo_2 ocf:heartbeat:MailTo \
             params email="stefan.senftleben at itsc.de" subject="omd_site_main" \
             operations $id="res_MailTo_2-operations" \
             op start interval="0" timeout="10" \
             op stop interval="0" timeout="10" \
             op monitor interval="10" timeout="10" start-delay="0" \
             meta failure-timeout="60"
     primitive res_ping_1 ocf:pacemaker:ping \
             params multiplier="1000" host_list="192.168.12.1 192.168.12.2 192.168.12.13" \
             operations $id="res_ping_1-operations" \
             op start interval="0" timeout="60" \
             op stop interval="0" timeout="20" \
             op monitor interval="10" timeout="60" start-delay="0" \
             op reload interval="0" timeout="100"
     group nagios-group pri_fs_omd pri_nagiosIP apache2 \
             meta target-role="started" failure-timeout="60"
     ms ms_drbd_omd pri_drbd_omd \
             meta clone-max="2" notify="true"
     clone cl_ping_1 res_ping_1 \
             meta clone-max="2" notify="true"
     location loc_drbdmaster_ping ms_drbd_omd \
             rule $id="loc_drbdmaster_ping-rule" $role="Master" pingd: defined pingd
     colocation col_omd_follows_drbd inf: nagios-group ms_drbd_omd:Master
     colocation col_omd_site_main_nagios-group inf: omd_site_main nagios-group
     colocation col_res_MailTo_1_nagios-group inf: res_MailTo_1 nagios-group
     colocation col_res_MailTo_2_omd_site_main inf: res_MailTo_2 omd_site_main
     order ord_drbd_before_omd inf: ms_drbd_omd:promote nagios-group:start
     order ord_nagios-group_omd_site_main inf: nagios-group omd_site_main
     order ord_nagios-group_res_MailTo_1 inf: nagios-group res_MailTo_1
     order ord_omd_site_main_res_MailTo_2 inf: omd_site_main res_MailTo_2
     property $id="cib-bootstrap-options" \
             expected-quorum-votes="2" \
             stonith-enabled="false" \
             dc-version="1.0.8-042548a451fce8400660f6031f4da6f0223dd5dd" \
             no-quorum-policy="ignore" \
             cluster-infrastructure="openais" \
             last-lrm-refresh="1320683212"
     rsc_defaults $id="rsc-options" \
             resource-stickiness="100"





-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://oss.clusterlabs.org/pipermail/pacemaker/attachments/20111110/6cf0a35e/attachment-0001.html>