настройка простейшего failover-а (Pacemaker + Corosync)

crm_mon --inactive --failcount

-inf: not_defined custom_primitive or custom_primitive lte 0

============
Last updated: Mon May 13 15:09:20 2013
Stack: openais
Current DC: srv01 - partition with quorum
Version: 1.0.12-unknown
2 Nodes configured, 2 expected votes
4 Resources configured.
============

Online: [ srv01 srv02 ]

 ClusterIP	(ocf::heartbeat:IPaddr2):	Started srv01

drbd_resource=«r0» device=«/dev/drbd1»

# Setting the resource:
  RESOURCE="custom_primitive"

# Initialization:

: ${OCF_FUNCTIONS_DIR=${OCF_ROOT}/lib/heartbeat}
. ${OCF_FUNCTIONS_DIR}/ocf-shellfuncs

#######################################################################

meta_data() {
        cat <<END
<?xml version="1.0"?>
<!DOCTYPE resource-agent SYSTEM "ra-api-1.dtd">
<resource-agent name="custom_resource_failover" version="0.9">
<version>1.0</version>

<longdesc lang="en">
This is a custom_resource_failover Resource Agent. It does absolutely nothing except 
keep track of whether its running or not.
Its purpose in life is for testing and to serve as a template for RA writers.

<shortdesc lang="en">Example stateless resource agent</shortdesc>
<parameters>
<parameter name="state" unique="1">
<longdesc lang="en">
Location to store the resource state in.
</longdesc>
<shortdesc lang="en">State file</shortdesc>
<content type="string" default="${HA_RSCTMP}/custom_resource_failover-${OCF_RESOURCE_INSTANCE}.state" />
</parameter>

<parameter name="fake" unique="0">
<longdesc lang="en">
Fake attribute that can be changed to cause a reload
</longdesc>
<shortdesc lang="en">Fake attribute that can be changed to cause a reload</shortdesc>
<content type="string" default="custom_resource_failover" />
</parameter>

</parameters>

<actions>
<action name="start"        timeout="20" />
<action name="promote"      timeout="90" />
<action name="demote"       timeout="90" />
<action name="notify"       timeout="90" />
<action name="stop"         timeout="20" />
<action name="monitor" depth="0"  timeout="10" interval="10" />
<action name="reload"       timeout="20" />
<action name="migrate_to"   timeout="20" />
<action name="migrate_from" timeout="20" />
<action name="meta-data"    timeout="5" />
<action name="validate-all"   timeout="20" />
</actions>
</resource-agent>
END
}

#######################################################################

custom_resource_usage() {
        cat <<END
usage: $0 {start|stop|monitor|migrate_to|migrate_from|validate-all|meta-data}

Expects to have a fully populated OCF RA-compliant environment set.
END
}

custom_resource_start() {
    echo "custom_resource: in the start function" >> /tmp/custom.log

    custom_resource_monitor
    if [ $? =  $OCF_SUCCESS ]; then
        echo "custom_resource: in the start function when monitor is okay" >> /tmp/custom.log
        return $OCF_SUCCESS
    else
        echo "custom_resource: in the start function when monitor is failured" >> /tmp/custom.log
        return $?
    fi
}

custom_resource_stop() {
    echo "custom_resource: in the stop function" >> /tmp/custom.log

    return $OCF_SUCCESS
}

custom_resource_status() {
    #get response from custom software by sending query to it
    return $some_response
}

custom_resource_good_response='is okay'

custom_resource_monitor() {
	custom_resource_status
	real_custom_resource_answer = ?$
        if [[ "$real_custom_resource_answer" != "$custom_resource_good_response" ]]
        then
                echo "custom resource is not running and error code to return is $OCF_ERR_UNIMPLEMENTED" >> /tmp/custom.log
                return $OCF_ERR_UNIMPLEMENTED
        else
                echo "custom resource is running and error code to return is $OCF_SUCCESS"  >> /tmp/custom.log
                return $OCF_SUCCESS
        fi
}

custom_resource_validate() {
    echo "custom_resource: in the validate function" >> /tmp/custom.log

    return $OCF_SUCCESS
}

: ${OCF_RESKEY_state=${HA_RSCTMP}/custom_resource_failover-${OCF_RESOURCE_INSTANCE}.state}
: ${OCF_RESKEY_fake="custom_resource_failover"}

case $__OCF_ACTION in
meta-data)      meta_data
                exit $OCF_SUCCESS
                ;;
start)          custom_resource_start;;
stop)           custom_resource_stop;;
monitor)        custom_resource_monitor;;
migrate_to)     ocf_log info "Migrating ${OCF_RESOURCE_INSTANCE} to ${OCF_RESKEY_CRM_meta_migrate_target}."
                custom_resource_stop
                ;;
migrate_from)   ocf_log info "Migrating ${OCF_RESOURCE_INSTANCE} from ${OCF_RESKEY_CRM_meta_migrate_source}."
                custom_resource_start
                ;;
reload)         ocf_log info "Reloading ${OCF_RESOURCE_INSTANCE} ..."
                ;;
validate-all)   custom_resource_validate;;
usage|help)     custom_resource_usage
                exit $OCF_SUCCESS
                ;;
*)              custom_resource_usage
                exit $OCF_ERR_UNIMPLEMENTED
                ;;
esac
rc=$?
ocf_log debug "${OCF_RESOURCE_INSTANCE} $__OCF_ACTION : $rc"
exit $rc

node srv01 \
	attributes standby="off"
node srv02 \
	attributes standby="off"
primitive custom_script ocf:heartbeat:custom_script_failover \
	op monitor interval="5s" \
	meta migration-threshold="0" failure-timeout="5s" target-role="Started"
primitive ClusterDRBD ocf:linbit:drbd \
	params drbd_resource="r0" \
	op monitor interval="4s" \
	meta target-role="Stopped"
primitive ClusterIP ocf:heartbeat:IPaddr2 \
	params ip="192.168.100.57" cidr_netmask="27" \
	op monitor interval="5s" \
	meta target-role="Started"
primitive fs_ClusterDRBD ocf:heartbeat:Filesystem \
	params device="/dev/drbd1" directory="/mnt/drbd0" fstype="ext3" \
	meta target-role="Started"
ms ms_ClusterDRBD ClusterDRBD \
	meta master-max="1" master-node-max="1" clone-max="2" clone-node-max="1" notify="true" target-role="Started" is-managed="true"
property $id="cib-bootstrap-options" \
	dc-version="1.0.12-unknown" \
	cluster-infrastructure="openais" \
	expected-quorum-votes="2" \
	stonith-enabled="false" \
	no-quorum-policy="ignore" \
	default-resource-stickiness="1"