01. 概括
1.0 脚本更新地址Git更新地址：shell_monitor_script.sh文章原文地址：使用shell脚本监控少量服务器并发送微信告警信息
1.1 前提：平台系统：linux系统下接收信息：微信企业号
1.2 脚本说明需要修改微信接口脚本对应参数的修改：包括IP，告警阈值等
1.3 脚本使用该脚本监控包括Disk、CPU、MEM、LOAD等主机资源，以及docker服务和docker容器。将该脚本附件假定放于：/home/mai/.check_host.sh。那么在定时任务上可以增加定时任务：$ echo "## 每分钟执行监控脚本一次" | sudo tee -a /etc/crontab$ echo "*/1 * * * * mai bash /home/mai/.check_host.sh" | sudo tee -a /etc/crontab
02. 脚本附件
#!/bin/bash
#!/bin/bash
# Create for mai # Copyright http://www.mairoot.com # Create date 2018-07-21 # Using check host source # Noting delete content # Shell Option [email protected]
# 01.获取主机资源function sys_info(){ # 系统信息 Date=`date +%Y-%m-%d` Date_time=`date "+%Y-%m-%d__%H:%M:%S"` Host_name=`hostname` IP_net_dev="ens33" IP_addr=`ifconfig $IP_net_dev|grep "inet addr"|awk -F":" '{print $2}'|awk -F" " '{print $1}'` # 主机资源 Disk_rate_sys=`df -h|grep \/\$|awk -F" " '{ print $5 }'` Disk_rate_sys2=${Disk_rate_sys%%%} Disk_rate_data=`df -h|grep \/boot\$|awk -F" " '{ print $5 }'` Disk_rate_data2=${Disk_rate_data%%%} CPU_free=`vmstat |tail -1|awk -F" " '{print $15}'` Load_ave15=`uptime |awk '{ print $NF }'|awk -F" " '{ print $1 }'` Load_ave15_1=`expr $Load_ave15` Mem_Total_kb=`cat /proc/meminfo | grep "MemTotal"|awk -F":" '{print $2}'|awk '{print $1}'` Mem_Free_kb=`cat /proc/meminfo | grep "MemFree"|awk -F":" '{print $2}'|awk '{print $1}'` Mem_Total=`expr $Mem_Total_kb / 1024` Mem_Free=`expr $Mem_Free_kb / 1024` # 微信接口 CropID='ww4730ead71a1818a6' Secret='1Nu6vcloj8SGzs6XqsIhuZVk1lO3khVS1j_GY6XEbFo' GURL="https://qyapi.weixin.qq.com/cgi-bin/gettoken?corpid=$CropID&corpsecret=$Secret" Gtoken=$(/usr/bin/curl -s -G $GURL | awk -F\" '{print $10}') PURL="https://qyapi.weixin.qq.com/cgi-bin/message/send?access_token=$Gtoken" To_User="mairoot" To_Party="1" Agent_ID="1000001" # 日志目录 if [ ! -d "/tmp/logs_check" ]; then mkdir /tmp/logs_check; fi Logs_file='/tmp/logs_check' # 远程地址 SSH_addr="192.168.3.12:22" # 运行业务 Project_mode="测试机"}
# 02.主机资源磁盘、CPU、MEM、LOAD# 2.1 判断根磁盘使用率超额 #系统盘使用率function sys_disk(){if [ $Disk_rate_sys2 -gt 80 ] then echo "$Date_time 磁盘使用率超额" >> $Logs_file/disk_rate.$Date.log /usr/bin/curl --data-ascii '{ "touser": "'${To_User}'", "toparty": "'${To_Party}'","msgtype": "text","agentid": "'${Agent_ID}'","text": {"content": "'获取时间：${Date_time}'\n'运行业务：${Project_mode}'\n'远程地址：${SSH_addr}'\n'内网地址：${IP_addr}'\n'主机名称：${Host_name}'\n'磁盘使用：目录/为${Disk_rate_sys}'"},"safe":"0"}' $PURL else echo "$Date_time 磁盘使用率良好：$Disk_rate_sys" >> $Logs_file/disk_rate.$Date.log fi
#数据盘使用率if [ $Disk_rate_data2 -gt 80 ] then echo "$Date_time 磁盘使用率超额" >> $Logs_file/disk_rate.$Date.log /usr/bin/curl --data-ascii '{ "touser": "'${To_User}'", "toparty": "'${To_Party}'","msgtype": "text","agentid": "'${Agent_ID}'","text": {"content": "'获取时间：${Date_time}'\n'运行业务：${Project_mode}'\n'远程地址：${SSH_addr}'\n'内网地址：${IP_addr}'\n'主机名称：${Host_name}'\n'磁盘使用：目录/data为${Disk_rate_data}'"},"safe":"0"}' $PURL else echo "$Date_time 磁盘使用率良好：$Disk_rate_data" >> $Logs_file/disk_rate.$Date.log fi}
# 2.2 判断MEM使用function sys_mem(){ if [ $Mem_Free_kb -lt 102400 ] then echo "$Date_time MEM空闲少于100M" >> $Logs_file/MEM_free.$Date.log /usr/bin/curl --data-ascii '{ "touser": "'${To_User}'", "toparty": "'${To_Party}'","msgtype": "text","agentid": "'${Agent_ID}'","text": {"content": "'获取时间：${Date_time}'\n'运行业务：${Project_mode}'\n'远程地址：${SSH_addr}'\n'内网地址：${IP_addr}'\n'主机名称：${Host_name}'\n'内存总共：${Mem_Total}MB'\n'内存剩余：${Mem_Free}MB'"},"safe":"0"}' $PURL else echo "$Date_time MEM空闲良好：$Mem_Free" >> $Logs_file/MEM_free.$Date.log fi}
# 2.3 判断CPU空闲值过低function sys_cpu(){ if [ $CPU_free -lt 10 ] then echo "$Date_time CPU空闲率少于10%" >> $Logs_file/CPU_free.$Date.log /usr/bin/curl --data-ascii '{ "touser": "'${To_User}'", "toparty": "'${To_Party}'","msgtype": "text","agentid": "'${Agent_ID}'","text": {"content": "'获取时间：${Date_time}'\n'运行业务：${Project_mode}'\n'远程地址：${SSH_addr}'\n'内网地址：${IP_addr}'\n'主机名称：${Host_name}'\n'CPU空闲：${CPU_free}%'"},"safe":"0"}' $PURL else echo "$Date_time CPU空闲率良好：$CPU_free%" >> $Logs_file/CPU_free.$Date.log fi}
# 2.4 判断服务器15分钟负载过高function sys_load(){ if [ `expr $Load_ave15_1 \> 0` -gt 1 ] then echo "$Date_time 服务器15分钟负载过高：$Load_ave15%" >> $Logs_file/Load_ave15.$Date.log /usr/bin/curl --data-ascii '{ "touser": "'${To_User}'", "toparty": "'${To_Party}'","msgtype": "text","agentid": "'${Agent_ID}'","text": {"content": "'获取时间：${Date_time}'\n'运行业务：${Project_mode}'\n'远程地址：${SSH_addr}'\n'内网地址：${IP_addr}'\n'主机名称：${Host_name}'\n'主机负载：${Load_ave15}%'"},"safe":"0"}' $PURL else echo "$Date_time 服务器15分钟负载良好：$Load_ave15%" >> $Logs_file/Load_ave15.$Date.log fi}
# 03.检查服务# 3.1 检查docker服务存活function docker_status(){ps -ef|grep docker |grep -v grepif [ $? -eq 0 ]then Date_time311=`date "+%Y-%m-%d__%H:%M:%S"` echo "$Date_time311:docker is up" >> $Logs_file/Docker_pro.$Date.log else Date_time312=`date "+%Y-%m-%d__%H:%M:%S"` echo "$Date_time312:Docker服务第一次停止" >> $Logs_file/docker.$Date.log /usr/bin/curl --data-ascii '{ "touser": "'${To_User}'", "toparty": "'${To_Party}'","msgtype": "text","agentid": "'${Agent_ID}'","text": {"content": "'获取时间：${Date_time312}'\n'运行业务：${Project_mode}'\n'远程地址：${SSH_addr}'\n'内网地址：${IP_addr}'\n'主机名称：${Host_name}'\n'发生事件：Docker第一次停止'"},"safe":"0"}' $PURL service docker start Os_code=$? if [ $Os_code -eq 0 ] then Date_time313=`date "+%Y-%m-%d__%H:%M:%S"` echo "$Date_time313:Docker_rec is up" >> $Logs_file/docker.$Date.log /usr/bin/curl --data-ascii '{ "touser": "'${To_User}'", "toparty": "'${To_Party}'","msgtype": "text","agentid": "'${Agent_ID}'","text": {"content": "'获取时间：${Date_time313}'\n'运行业务：${Project_mode}'\n'远程地址：${SSH_addr}'\n'内网地址：${IP_addr}'\n'主机名称：${Host_name}'\n'发生事件：Docker服务恢复'"},"safe":"0"}' $PURL elif [ $Os_code -ne 0 ] then Date_time314=`date "+%Y-%m-%d__%H:%M:%S"` echo "$Date_time314:Docker重启失败" >> $Logs_file/docker.$Date.log /usr/bin/curl --data-ascii '{ "touser": "'${To_User}'", "toparty": "'${To_Party}'","msgtype": "text","agentid": "'${Agent_ID}'","text": {"content": "'获取时间：${Date_time314}'\n'运行业务：${Project_mode}'\n'远程地址：${SSH_addr}'\n'内网地址：${IP_addr}'\n'主机名称：${Host_name}'\n'发生事件：Docker服务停止'"},"safe":"0"}' $PURL fifi}
# 3.2 检查docker容器存活 # docker Container_ID 自下向上function docker_container(){#Container_ID_ALL=("2ac5dfa2cd4e" "36c6485bf415" "a2a46bfde7bb" "3ad69c74ef9c")#Container_ID_ALL="`docker ps -aq`"Container_ID_ALL="`docker ps -q`"for Container_ID in ${Container_ID_ALL[@]}do Container_Name=`docker inspect -f='{{.Name}}' $(docker ps -a -q|grep $Container_ID)|awk -F"/" '{print $2}'` docker ps |grep $Container_ID if [ $? -eq 0 ] then Date_time321=`date "+%Y-%m-%d__%H:%M:%S"` echo "$Date_time321:$Container_Name is up" >> $Logs_file/Docker_Container.$Date.log else docker start $Container_ID Os_code=$? if [ $Os_code -eq 0 ] then Date_time322=`date "+%Y-%m-%d__%H:%M:%S"` echo "$Date_time322:$Container_Name is up" >> $Logs_file/Docker_Container.$Date.log /usr/bin/curl --data-ascii '{ "touser": "'${To_User}'", "toparty": "'${To_Party}'","msgtype": "text","agentid": "'${Agent_ID}'","text": {"content": "'获取时间：${Date_time322}'\n'运行业务：${Project_mode}'\n'远程地址：${SSH_addr}'\n'内网地址：${IP_addr}'\n'主机名称：${Host_name}'\n'发生事件：${Container_Name}服务恢复'"},"safe":"0"}' $PURL elif [ $Os_code -ne 0 ] then Date_time323=`date "+%Y-%m-%d__%H:%M:%S"` echo "$Date_time323:$Container_Name重启失败" >> $Logs_file/Docker_Container.$Date.log /usr/bin/curl --data-ascii '{ "touser": "'${To_User}'", "toparty": "'${To_Party}'","msgtype": "text","agentid": "'${Agent_ID}'","text": {"content": "'获取时间：${Date_time323}'\n'运行业务：${Project_mode}'\n'远程地址：${SSH_addr}'\n'内网地址：${IP_addr}'\n'主机名称：${Host_name}'\n'发生事件：${Container_Name}服务停止'"},"safe":"0"}' $PURL fi fidone}
# 10 调用函数sys_infosys_disksys_cpusys_memsys_loaddocker_statusdocker_container03. 微信接收信息
原文地址：http://blog.51cto.com/11564577/2158456
时间： 2024-10-20 22:59:21