监控脚本路径:
[root@fk-databus01 ~]#cd /opt/log_error_script/
[root@fk-databus01 log_error_script]#ll
total 20
-rw-r--r-- 1 root root 3782 Jun 29 12:13DEJ_0001_error.log-rwxr-xr-x 1 root root 4274 Jun 29 11:38prcc_log_error.sh-rwxr-xr-x 1 root root 1142 Feb 13 10:51sendemail.sh
监控脚本内容
[root@fk-databus01 log_error_script]#cat prcc_log_error.sh#!/bin/sh
ERROR_LOG=`/bin/ls /data/log/sedsb/$(date +%Y%m%d)/DEJ_0001_error*`
ERROR_NEW_LOG=/opt/log_error_script/DEJ_0001_error.log
DATE=`date +%Y年%m月%d日%H时%M分%S秒`
HOST=`/bin/hostname`
IP=`/sbin/ifconfig|grep "inet addr"|grep "Bcast"|cut -d":" -f2|awk -F" " '{print $1}'`
ERROR_MESSAGE=$(/bin/grep -A20 "$(grep"ERROR"$ERROR_LOG|tail -1|awk '{print $1,$2,$3,$4}')"$ERROR_LOG)
DIR=/data/log/sedsb/$(date +%Y%m%d)
FILE=/data/log/sedsb/$(date +%Y%m%d)/DEJ_0001_error_$(date +%Y%m%d).0.logif [ ! -d $DIR ];then/bin/mkdir $DIR
fiif [ ! -f $FILE ];then/bin/touch $FILE
fi/bin/chown -R zquser.zquser $DIR
sleep3
if [ ! -f $ERROR_NEW_LOG ];then/bin/touch $ERROR_NEW_LOG
fi
NUM1=$(/bin/cat $ERROR_LOG|wc -l)
NUM2=$(/bin/cat $ERROR_NEW_LOG|wc -l)if [ -f $ERROR_LOG ] && [ $NUM1 -ne 0 ] && [ $NUM2 -eq 0 ];then/bin/bash /opt/log_error_script/sendemail.sh wangshibo@kevin.com "风控系统${HOSTNAME}机器prcc服务日志的error监控" "告警主机:${HOSTNAME} \n告警IP:${IP} \n告警时间:${DATE} \n告警等级:严重,抓紧解决啊! \n告警人员:王士博 \n告警详情:prcc服务日志中出现error了! \n告警日志文件:${ERROR_LOG} \n当前状态: PROBLEM \n \nerror信息:\n$ERROR_MESSAGE"
/bin/cat $ERROR_LOG >$ERROR_NEW_LOG
fi/usr/bin/cmp $ERROR_LOG $ERROR_NEW_LOG >/dev/null 2>&1
if [ $? -ne 0 ];then/bin/bash /opt/log_error_script/sendemail.sh wangshibo@kevin.com "风控系统${HOSTNAME}机器prcc服务日志的error监控" "告警主机:${HOSTNAME} \n告警IP:${IP} \n告警时间:${DATE} \n告警等级:严重,抓紧解决啊! \n告警人员:王士博 \n告警详情:prcc服务日志中出现error了! \n告警日志文件:${ERROR_LOG} \n当前状态: PROBLEM \n \nerror信息:\n$ERROR_MESSAGE"
/bin/cat $ERROR_LOG >$ERROR_NEW_LOG
fi
结合crontab进行定时监控(每15秒执行一次)
[root@fk-databus01 ~]#crontab -l#监控pcrr日志的error
* * * * * /bin/bash -x /opt/log_error_script/prcc_log_error.sh >/dev/null 2>&1
* * * * * sleep 15;/bin/bash -x /opt/log_error_script/prcc_log_error.sh >/dev/null 2>&1
* * * * * sleep 30;/bin/bash -x /opt/log_error_script/prcc_log_error.sh >/dev/null 2>&1
* * * * * sleep 45;/bin/bash -x /opt/log_error_script/prcc_log_error.sh >/dev/null 2>&1
==================================================================================针对上面脚本中的某些变量说明
[root@fk-databus01 ~]#/bin/ls /data/log/sedsb/$(date +%Y%m%d)/DEJ_0001_error*
/data/log/sedsb/20180629/DEJ_0001_error_20180629.0.log
[root@fk-databus01 ~]#grep "ERROR" /data/log/sedsb/20180629/DEJ_0001_error_20180629.0.log
ERROR DEJ 2018-06-29 12:13:29.191 [pool-4-thread-10] n.s.p.r.thread.OuterCheThdInterface -cx201806291213288440016车300接口异常!
ERROR DEJ2018-06-29 12:13:29.196 [nioEventLoopGroup-3-12] n.s.p.r.c.MessageControllerImpl -cx201806291213288440016:
[root@fk-databus01 ~]#grep "ERROR" /data/log/sedsb/20180629/DEJ_0001_error_20180629.0.log |tail -1|awk '{print $1,$2,$3,$4}'
ERROR DEJ 2018-06-29 12:13:29.196[root@fk-databus01 ~]#/bin/grep -A20 "$(grep "ERROR" /data/log/sedsb/20180629/DEJ_0001_error_20180629.0.log |tail -1|awk '{print $1,$2,$3,$4}')" /data/log/sedsb/20180629/DEJ_0001_error_20180629.0.log
ERROR DEJ 2018-06-29 12:13:29.196 [nioEventLoopGroup-3-12] n.s.p.r.c.MessageControllerImpl -cx201806291213288440016:
net.sinocredit.pre.rcc.utils.exception.OuterDataException: 外部数据:cheFixPrice:mile里程isnull;
at net.sinocredit.pre.rcc.datafactory.OuterDataProcess.execute(OuterDataProcess.java:51)
at net.sinocredit.pre.rcc.datafactory.OuterDataProcess.execute(OuterDataProcess.java:23)
at net.sinocredit.pre.rcc.service.getOtherDataService.MessageServiceImpl.getOrderData(MessageServiceImpl.java:34)
at net.sinocredit.pre.rcc.controller.MessageControllerImpl.divMessage(MessageControllerImpl.java:110)
at net.sinocredit.pre.rcc.handler.ServerHandler.channelRead(ServerHandler.java:28)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:373)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:359)
at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:351)
at io.netty.handler.codec.MessageToMessageDecoder.channelRead(MessageToMessageDecoder.java:102)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:373)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:359)
at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:351)
at io.netty.handler.codec.ByteToMessageDecoder.fireChannelRead(ByteToMessageDecoder.java:293)
at io.netty.handler.codec.ByteToMessageDecoder.channelRead(ByteToMessageDecoder.java:267)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:373)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:359)
at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:351)
at io.netty.channel.DefaultChannelPipeline$HeadContext.channelRead(DefaultChannelPipeline.java:1334)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:373)