SNMP shell script for process monitor

一个临时解决办法，为了监测进程的健康状态，首先必须在被控机上安装 net-snmp，然后配置 /etc/snmp/snmpd.conf 如下：

syscontact  sysadm@sample.com
proc vsftpd 100 1
proc httpd 3000 1
proc mysqld 3000 1
disk  /data 100G
com2sec mynet    192.168.0.0/24  process-mon
group   mynet    v1              mynet
group   mynet    v2c             mynet
view    system       included       .1.3.6.1.2.1
view    system       included       .1.3.6.1.4.1.2021.2
access  mynet "" any  noauth  exact  system  none  none

接着编辑脚本：

#!/bin/sh

PATH=$PATH:/usr/bin
PROGRAM=`basename $0`

community='demo'
host='localhost'
mailto=''
items=''
ilist='tmp'

args=`getopt -l help,item:items-list: c:h:m:i:I: $*`
if [ $? -gt 0 ]; then
    strerr="Invalid options"
    echo "$strerr" >&2
    logger -it "$strerr"
    exit 1
fi

for i in $args; do
    case $i in
    -c) shift; community=$1; shift;;
    -h) shift; host=$1; shift;;
    -m) shift; mailto=$1; shift;;
    -i|--item)
        shift
        if [ -n "$items" ]; then
            items=`echo -e "$items\n$1"`
        else
            items="$1"
        fi
        shift
        ;;
    -I|--items-list)
        shift; ilist=$1; shift;;
    --help)
        shift
        echo "useage: $PROGRAM [-c|-h|-m] [--item|--help]
    -c community
    -h host
    -m mailto
    -i|--item item_map, 'community host' map
    --help, print this message"
        exit 0
        ;;
    esac
done

if [ -z "$items" ]; then
    items="$community $host"
fi

STRERR=""
if [ "$ilist" == "tmp" ]; then echo "$items" >$ilist; fi
while read community host; do
# echo "$items" | while read community host; do
# for item in "$items"; do
#   community=`echo $item | awk '{print $1}'`
#   host=`echo $item | awk '{print $2}'`
    if [ -z "$community" -o -z "$host" ]; then
        strerr="Invalid 'community host' item"
        echo strerr >&2
        logger -it $PROGRAM "$strerr"
        continue
    fi

    snmp_result=`snmpwalk -v2c -c $community $host UCD-SNMP-MIB::prNames`
    if [ $? -gt 0 ];then
        strerr="$host: SNMP ERROR, maybe system is down"
        echo "$strerr" >&2
        logger -it "$PROGRAM" $strerr
        STRERR="$STRERR\n$strerr"
    fi
    num=`echo "$snmp_result" | wc -l` && \
    for i in `seq 1 $num`; do
        status=$(snmpget -v2c -c $community $host UCD-SNMP-MIB::prErrorFlag.$i | awk -F' = ' '{print $2}') && \
        process=$(echo "$snmp_result" | sed -n "$i{s/^UCD-SNMP-MIB::prNames.$i = STRING: \(.*\)$/\1/p}") && \
        if [ "$status" == "INTEGER: error(1)" -o "$status" == "INTEGER: 1" ]; then
            message=$(snmpget -v2c -c $community $host UCD-SNMP-MIB::prErrMessage.$i | sed "s/UCD-SNMP-MIB::prErrMessage.$i = STRING: \(.*\)$/\1/")
            strerr="$host: $message"
            echo "$strerr" >&2
            logger -it $PROGRAM "$strerr"
            STRERR="$STRERR\n$strerr"
        fi
    done
done <$ilist
# rm -f tmp

if [ -n "$mailto" ] && [ -n "$STRERR" ]; then
    STRERR="*** CRITICAL ERRORs ***\n$STRERR"
    echo -e "$STRERR" | mail -s "*** CRITICAL: process monitor ERRORs reporting ***" $mailto
fi

这个脚本可以这样运行：

sh$ process-mon -c demo -h 192.168.0.98
sh$ process-mon -i 'demo 192.168.0.98' -i 'mon 192.168.0.99' -m chowroc@sample.com
检查两台主机并在有问题时发送邮件到(mailto)指定的的地址
sh$ process-mon -I process-mon.list -m roc@sample.com
sh$ cat process-mon
demo 192.168.0.98
mon 192.168.0.99
...