定义故障监视器

# Set up a temporary file for the nslookup replies.
DNSPROBEFILE=/tmp/.$RESOURCE_NAME.probe
probefail=0
retries=0

while :
do
   # The interval at which the probe needs to run is specified in the
   # property THOROUGH_PROBE_INTERVAL. Therefore, set the probe to sleep
   # for a duration of THOROUGH_PROBE_INTERVAL.
   sleep $PROBE_INTERVAL

   # Run an nslookup command of the IP address on which DNS is serving.
   hatimerun -t $PROBE_TIMEOUT /usr/sbin/nslookup $DNS_HOST $DNS_HOST \
          > $DNSPROBEFILE 2>&1

      retcode=$?
      if [ $retcode -ne 0 ]; then
            probefail=1
      fi

   # Make sure that the reply to nslookup comes from the HA-DNS
   # server and not from another nameserver mentioned in the 
   # /etc/resolv.conf file.
   if [ $probefail -eq 0 ]; then
# Get the name of the server that replied to the nslookup query.
   SERVER=` awk ' $1=="Server:" { print $2 }' \
   $DNSPROBEFILE | awk -F. ' { print $1 } ' `
   if [ -z "$SERVER" ]; then
      probefail=1
      else
         if [ $SERVER != $DNS_HOST ]; then
            probefail=1
         fi
   fi
fi

   if [ $probefail -ne 0 ]; then
         decide_restart_or_failover
   else
         logger -p ${SYSLOG_FACILITY}.err\
         -t [$SYSLOG_TAG]\
         "${ARGV0} Probe for resource HA-DNS successful"
   fi

function restart_service
{

        # To restart the data service, first verify that the 
        # data service itself is still registered under PMF.
        pmfadm -q $PMF_TAG
        if [[ $? -eq 0 ]]; then
                # Since the TAG for the data service is still registered under
                # PMF, first stop the data service and start it back up again.

                # Obtain the Stop method name and the STOP_TIMEOUT value for
                # this resource.
                STOP_TIMEOUT=`scha_resource_get -O STOP_TIMEOUT \
                        -R $RESOURCE_NAME -G $RESOURCEGROUP_NAM?
                STOP_METHOD=`scha_resource_get -O STOP \
                        -R $RESOURCE_NAME -G $RESOURCEGROUP_NAM?
                hatimerun -t $STOP_TIMEOUT $RT_BASEDIR/$STOP_METHOD \
                        -R $RESOURCE_NAME -G $RESOURCEGROUP_NAME \
                        -T $RESOURCETYPE_NAME

                if [[ $? -ne 0 ]]; then
                        logger-p ${SYSLOG_FACILITY}.err -t [$SYSLOG_TAG] \
                                “${ARGV0} Stop method failed.”
                        return 1
                fi

                # Obtain the START method name and the START_TIMEOUT value for
                # this resource.
                START_TIMEOUT=`scha_resource_get -O START_TIMEOUT \
                        -R $RESOURCE_NAME -G $RESOURCEGROUP_NAM?
                START_METHOD=`scha_resource_get -O START \
                        -R $RESOURCE_NAME -G $RESOURCEGROUP_NAM?
                hatimerun -t $START_TIMEOUT $RT_BASEDIR/$START_METHOD \
                        -R $RESOURCE_NAME -G $RESOURCEGROUP_NAME \
                        -T $RESOURCETYPE_NAME

                if [[ $? -ne 0 ]]; then
                        logger-p ${SYSLOG_FACILITY}.err -t [$SYSLOG_TAG] \
                                “${ARGV0} Start method failed.”
                        return 1
                fi


        else
                # The absence of the TAG for the dataservice 
                # implies that the data service has already
                # exceeded the maximum retries allowed under PMF. 
                # Therefore, do not attempt to restart the
                # data service again, but try to failover
                # to another node in the cluster.
                scha_control -O GIVEOVER -G $RESOURCEGROUP_NAME \
                        -R $RESOURCE_NAME
        fi

        return 0
}

# Find where the probe program resides by obtaining the value of the
# RT_BASEDIR property of the resource.
RT_BASEDIR=`scha_resource_get -O RT_BASEDIR -R $RESOURCE_NAME -G \
$RESOURCEGROUP_NAME`

# Start the probe for the data service under PMF. Use the infinite retries 
# option to start the probe. Pass the resource name, type, and group to the 
# probe program. 
pmfadm -c $RESOURCE_NAME.monitor -n -1 -t -1 \
   $RT_BASEDIR/dns_probe -R $RESOURCE_NAME -G $RESOURCEGROUP_NAME \
   -T $RESOURCETYPE_NAME

# See if the monitor is running, and if so, kill it. 
if pmfadm -q $PMF_TAG; then 
   pmfadm -s $PMF_TAG KILL
   if [ $? -ne 0 ]; then 
         logger -p ${SYSLOG_FACILITY}.err \
            -t [$SYSLOG_TAG] \
            "${ARGV0} Could not stop monitor for resource " \
            $RESOURCE_NAME
           exit 1
   else
         # could successfully stop the monitor. Log a message.
         logger -p ${SYSLOG_FACILITY}.err \
            -t [$SYSLOG_TAG] \
            "${ARGV0} Monitor for resource " $RESOURCE_NAME \
            " successfully stopped"
   fi
fi
exit 0

# Obtain the full path for the Validate method from
# the RT_BASEDIR property of the resource type.
RT_BASEDIR=`scha_resource_get -O RT_BASEDIR -R $RESOURCE_NAME \
   -G $RESOURCEGROUP_NAM?

# Obtain the name of the Validate method for this resource.
VALIDATE_METHOD=`scha_resource_get -O VALIDATE \
   -R $RESOURCE_NAME -G $RESOURCEGROUP_NAM?

# Obtain the value of the Confdir property in order to start the
# data service. Use the resource name and the resource group entered to
# obtain the Confdir value set at the time of adding the resource.
config_info=`scha_resource_get -O Extension -R $RESOURCE_NAME \
 -G $RESOURCEGROUP_NAME Confdir`

# scha_resource_get returns the type as well as the value for extension
# properties. Use awk to get only the value of the extension property.
CONFIG_DIR=`echo $config_info | awk `{print $2}'`

# Call the validate method so that the dataservice can be failed over 
# successfully to the new node.
$RT_BASEDIR/$VALIDATE_METHOD -R $RESOURCE_NAME -G $RESOURCEGROUP_NAME \
   -T $RESOURCETYPE_NAME -x Confdir=$CONFIG_DIR