bash中的Nagios事件处理程序脚本,用于重新启动服务,如果服务未启动,则在满足条件之前不要重新启动下一个服务

所有注释均为代码。仔细检查StopService函数,因为您没有提到如何停止服务,所以我做了类似的操作。

#!/bin/bash

SERVICESTATE=$1;      #Common Check State (OK,WARNING,CRITICAL or UNKNOWN)
Host=$2;              #HostName or IP
SERVICESTATETYPE=$3;  #Hard or Soft service type

TimeOut=3;            #Time (seconds) to wait service start/stop 
                      #before next service processing
                      #You could not make infinite TimeOut, because 
                      #nagios process will kill this handler if it 
                      #will run too long


#Services is array with service names
Services=(DecisionEngine_1 DecisionEngine_2 DecisionEngine_3 DecisionEngine_4)

#add path to nagios plugins dir
PATH=$PATH:/usr/local/nagios/libexec

RestartService() {
   #function restarts services via NRPE.
   #Usage:  RestartService ServiceName
   echo -n " Restarting $1;"
   check_nrpe -H "${Host}" -p 5666 -c restart_service -a "$1" >/dev/null 2>&1
   return $?
}

StopService() {
   #function stops services via NRPE.
   #Usage: StopService ServiceName
   echo -n " Stopping $1;"
   check_nrpe -H "${Host}" -p 5666 -c stop_service -a "$1" >/dev/null 2>&1
   return $?
}

ServiceWait() {
   #function do continious checks service via NRPE, until success,
   #unsuccess check or TimeOut 
   #Usage:  ServiceWait ServiceName {start|stop}
   #start optin waits for success check
   #stop option waits for unsuccess check
   Logic="";
   [ "$2" == "start" ] && Logic="-eq"; #RC for start check should be 0
   [ "$2" == "stop" ] && Logic="-ne" ; #RC for stop check should NOT be 0
   [ -z "$Logic" ] && { echo "ServiceWait function usage error"; exit 19; }
   t=${TimeOut}
   while [ "$t" -ge 0 ]; do
      check_nrpe -H "${Host}" -p 5666 -t 30 \
                 -c check_service -a "$1" 'crit=not state_is_ok()' >/dev/null 2>&1
      RC=$?
      [ "$RC" $Logic 0 ] && { echo -n "CheckRC=$RC;"; return $RC; }      
                              #success check, no need to wait anymore
      let t--
      sleep 1
   done
   echo -n "TimeOut; " 
   return 3
}

#check if script received zero params in $1, $2 and $3
[ -z "${SERVICESTATE}" -o -z "${Host}" -o -z "${SERVICESTATETYPE}" ] && { 
    echo "Usage: $0 {OK|WARNING|UNKNOWN|CRITICAL} Hostname {SOFT|HARD}"; 
    exit 1; 
  }

case "${SERVICESTATE}" in
   OK)
   ;;
   WARNING)
   ;;
   UNKNOWN)
   ;;
   CRITICAL) ## DECISION ENGINE RESTART
     #uncomment if you need @mail
     #cat /usr/local/nagios/libexec/mail/DeServiceRestart.txt | \
     # mail -s "Restarting DE services" email@someteam.com -r Nagios@ATL-NM-01
     RC=0

     if [ "$SERVICESTATETYPE" == "SOFT" ] ; then
        for (( i=0; i<${#Services[*]}; i++ )); do
           RestartService ${Services[$i]}
           ServiceWait ${Services[$i]} start
           RC=$?
           #if previous check failed, then do not try to do any restarts anymore
           [ "$RC" -ne 0 ] && break;         
           SuccessRestart+=(${Services[$i]})
        done
        echo "Restart is complete. ${SuccessRestart[*]} Return Code is ${RC}"
     elif [ "$SERVICESTATETYPE" == "HARD" ] ; then
        #Stop all services sequentially.
        for (( i=0; i<${#Services[*]}; i++ )); do
           StopService ${Services[$i]}
           #Here you need to experiment what to wait
           #May be it will be better to stay here for N seconds while
           #service is been stopped
           #rather then try to check service state
           ServiceWait ${Services[$i]} stop
           #sleep $TimeOut
        done
        #Start all services sequentially.
        for (( i=0; i<${#Services[*]}; i++ )); do
           RestartService ${Services[$i]}
           ServiceWait ${Services[$i]} start
           RC=$?
           #if previous check failed, then do not try to do any restarts anymore
           [ "$RC" -ne 0 ] && break;      
           SuccessRestart+=(${Services[$i]})
        done
     else
         echo "Unknown SERVICESTATETYPE $SERVICESTATETYPE option" 
         exit 20
     fi
   ;;
esac
exit 0