[root@usvr-210 libexec]# cat check_heartbeat.sh
#!/bin/bash
# Author: Emmanuel Bretelle
# Date: 12/03/2010
# Description: Retrieve
linux HA cluster status using cl_status
# Ba
sed on http://www.randombugs.com/linux/howto-monitor-linux-heartbeat-snmp.html
#
# Autor: Stanila Constantin Adrian
# Date: 20/03/2009
# Description: Check the number of active heartbeats
# http://www.randombugs.com
# Get program path
REVISION=1.3
PROGNAME=`/bin/basename $0`
PROGPATH=`echo $0 | /bin/sed -e 's,[/][^/][^/]*$,,'`
NODE_NAME=`uname -n`
CL_ST='/usr/bin/cl_status'
#nagios error codes
#. $PROGPATH/utils.sh
OK=0
WARNING=1
CRITICAL=2
UNKNOWN=3
usage () {
echo "
Nagios plugin to heartbeat.
Usage:
$PROGNAME
$PROGNAME [--help | -h]
$PROGNAME [--version | -v]
Options:
--help -l Print this help information
--version -v Print version of plugin
"
}
help () {
print_revision $PROGNAME $REVISION
echo; usage; echo; support
}
while test -n "$1"
do
case "$1" in
--help | -h)
help
exit $STATE_OK;;
--version | -v)
print_revision $PROGNAME $REVISION
exit $STATE_OK;;
# -H)
# shift
# HOST=$1;;
# -C)
# shift
# COMMUNITY=$1;;
*)
echo "Heartbeat UNKNOWN: Wrong command usage"; exit $UNKNOWN;;
esac
shift
done
$CL_ST hbstatus > /dev/null
res=$?
if [ $res -ne 0 ]
then
echo "Heartbeat CRITICAL: Heartbeat is not running on this node"
exit $CRITICAL
fi
declare -i I=0
declare -i A=0
NODES=`$CL_ST listnodes`
for node in $NODES
do
status=`$CL_ST nodestatus $node`
let I=$I+1
# if [ $status == "active" ] 默认情况下检测active状态的个数，但是ping状态也为正常状态，因此改成如下条件。
if [ $status == "active" -o $status == "ping" ]
then
let A=$A+1
fi
done
if [ $A -eq 0 ]
then
echo "Heartbeat CRITICAL: $A/$I"
exit $CRITICAL
elif [ $A -ne $I ]
then
echo "Heartbeat WARNING: $A/$I"
exit $WARNING
else
echo "Heartbeat OK: $A/$I"
exit $OK
fi
