RocketMQ服务健康监控

1、依赖组件安装
# yum -y install nmap

2、nameserver监控

# vim /data/scripts/check_nameserver_health.sh

#!/bin/sh
PATH=/sbin:/bin:/usr/sbin:/usr/bin:/usr/local/bin:/usr/local/sbin
  
SRV_PORT="9876"                    ## 端口号
SRV_PROT="tcp"                     ## 协议类型
SRV_NAME="rocketmq_nameserver"     ## 服务名
  
## 是否已正确扫描
SCAN_FLAG=0

for ETH_NAME in `/sbin/ifconfig | grep eth0 | awk '{print $1}'`
do	
	#取本机IP
       ETH1_ADDR=`/sbin/ifconfig ${ETH_NAME} | awk -F ':' '/inet addr/{print $2}' | sed 's/[a-zA-Z ]//g'`
       [[ -z "${ETH1_ADDR}" ]] && continue || break
done
  
TMP_SRV_PROT=`echo ${SRV_PROT} | tr '[A-Z]' '[a-z]'`
  
if [[ "${TMP_SRV_PROT}" == "tcp" ]]; then
       PROT_OPT="S"
elif [[ "${TMP_SRV_PROT}" == "udp" ]]; then
       PROT_OPT="U"
else
       echo "未知的协议类型！" && exit1
fi
  
## 最多扫描3次，成功一次即可，以避免网络抖动而导致误判
for ((i=0; i<3; i++)); do
       RETVAL=`/usr/bin/nmap -n -s${PROT_OPT} -p ${SRV_PORT} ${ETH1_ADDR} | grep open`
       [[ -n "${RETVAL}" ]] && SCAN_FLAG=1;break || sleep 10
done
  
if [[ ${SCAN_FLAG} -ne 1 ]]; then
	#重启服务
       [[ -n `ps aux | grep java | grep namesrv` ]] && kill -9 `ps aux | grep java | awk '/namesrv/{print $2}'`
       cd /usr/local/rocketmq/bin && nohup sh mqnamesrv &
fi

3、brokerserver监控

# vim /data/scripts/check_brokerserver_health.sh

#!/bin/sh
PATH=/sbin:/bin:/usr/sbin:/usr/bin:/usr/local/bin:/usr/local/sbin
  
SRV_PORT="10911"                      ## 端口号
SRV_PROT="tcp"                        ## 协议类型
SRV_NAME="rocketmq_brokerserver"      ## 服务名
  
## 是否已正确扫描
SCAN_FLAG=0
  
for ETH_NAME in `/sbin/ifconfig | grep eth0 | awk '{print $1}'`
do
	#取本机IP
       ETH1_ADDR=`/sbin/ifconfig ${ETH_NAME} | awk -F ':' '/inet addr/{print $2}' | sed 's/[a-zA-Z ]//g'`
       [[ -z "${ETH1_ADDR}" ]] && continue || break
done
  
TMP_SRV_PROT=`echo ${SRV_PROT} | tr '[A-Z]' '[a-z]'`
  
if [[ "${TMP_SRV_PROT}" == "tcp" ]]; then
       PROT_OPT="S"
elif [[ "${TMP_SRV_PROT}" == "udp" ]]; then
       PROT_OPT="U"
else
       echo "未知的协议类型！" && exit1
fi
  
## 最多扫描3次，成功一次即可，以避免网络抖动而导致误判
for ((i=0; i<3; i++)); do
       RETVAL=`/usr/bin/nmap -n -s${PROT_OPT} -p ${SRV_PORT} ${ETH1_ADDR} | grep open`
       [[ -n "${RETVAL}" ]] && SCAN_FLAG=1;break || sleep 10
done
  
if [[ ${SCAN_FLAG} -ne 1 ]]; then
	#重启服务
       [[ -n `ps aux | grep java | grep broker` ]] && kill -9 `ps aux | grep java | awk '/broker/{print $2}'`
       cd /usr/local/rocketmq/bin && nohup sh mqbroker -c ../conf/2m-noslave/broker-a.properties &
fi

4、添加crontab信息

# touch /var/run/check_rocketmq_nameserver.lock
# touch /var/run/check_rocketmq_brokerserver.lock

# echo 'touch /var/run/check_rocketmq_nameserver.lock' >> /etc/rc.d/rc.local
# echo 'touch /var/run/check_rocketmq_brokerserver.lock' >> /etc/rc.d/rc.local

# crontab -e
*/2 * * * * (flock --timeout=0 /var/run/check_rocketmq_nameserver.lock /data/scripts/check_nameserver_health.sh >/dev/null 2>&1)
*/2 * * * * (flock --timeout=0 /var/run/check_rocketmq_brokerserver.lock /data/scripts/check_brokerserver_health.sh >/dev/null 2>&1)

flock --timeout=0 /var/run/check_rocketmq_nameserver.lock 设置锁，防止多次运行。

转至：http://sofar.blog.51cto.com/353572/1540874