shell实战之Linux主机系统监控

1、系统监控概述

采集的监控信息主要有内存占用率，CPU占用率，当前在线用户，磁盘挂载及磁盘空间使用率，平均每秒写入流量，平均每秒流出流量。磁盘IO：平均每秒从磁盘读入内存的速率，平均每秒从内存写入磁盘的速率。

2、监控原理

2.1、CPU占用率

监控原理：

CPU相关信息记录在文件 /proc/stat中。详情请查看博文：https://blog.csdn.net/ustclu/article/details/1721673

stephen@stephen-K55VD:~/shell$ cat  /proc/stat
cpu
cpu0
cpu1
cpu2
cpu3
intr
ctxt
btime
processes
procs_running
procs_blocked
softirq           

代码实现：

 #获取CPU的总量与使用量
     cpuTotalStart=`awk 'BEGIN{total=0} /cpu / {for(i=2;i<=NF;i++);total+=i}END{print $total}' /proc/stat`
     cpuUsedStart=`awk 'BEGIN{used=0} /cpu / { used=$2+$3+$4+$7+$8 }END{print used}' /proc/stat`
     #隔30s再获取一次CPU总量与使用量并计算差值
     sleep
     cpuTotalEnd=`awk 'BEGIN{total=0} /cpu / {for(i=2;i<=NF;i++);total+=i}END{print $total}' /proc/stat`
     cpuUsedEnd=`awk 'BEGIN{used=0} /cpu / { used=$2+$3+$4+$7+$8 }END{print used}' /proc/stat`
     usedCPU=`expr ${cpuUsedEnd} - ${cpuUsedStart}`
     totalCPU=`expr ${cpuTotalEnd} - ${cpuTotalStart}`

2.2、内存占用率

监控原理：

内存相关的信息记录在/proc/meminfo文件中，MemTotal为内存总量，单位为kb，MemFree为空闲内存。内存占用率=（总内存-空闲内存）/ 总内存。

stephen@stephen-K55VD:~/shell$ cat /proc/meminfo
MemTotal:         kB
MemFree:           kB
MemAvailable:      kB
Buffers:            kB
Cached:            kB
SwapCached:         kB
Active:           kB

代码实现：

 #获取内存使用率
 function memUsage(){
     logInfo "Begin to get mem usage of Host [${ip}]"
     #获取总内存
     totalMem=`awk '/MemTotal/{print $2}' /proc/meminfo`
     #获取空闲内存
     freeMem=`awk '/MemFree/{print $2}' /proc/meminfo`
     usedMem=`expr ${totalMem} - ${freeMem}`
     #echo $(usagePercent ${usedMem} ${totalMem})
     #echo $(kbToGb ${totalMem})
     logInfo "Host [${ip}] total mem is :  $(kbToGb ${totalMem}) GB"
     #计算内存使用率并打印到日志中
     logInfo "Host [${ip}] mem usage is :  $(usagePercent ${usedMem} ${totalMem}) %"
     logInfo "End to get mem usage of Host [${ip}]"
 }

2.3、流量监控

监控原理：

Linux机器流量信息记录在/proc/net/dev文件中。通过计算一段时间段内接收和发送的字节数来计算速率。第一列为网卡信息，第二列为接收的字节数，第10列为发送的字节数。

stephen@stephen-K55VD:~/shell/sysMonitor$ cat /proc/net/dev
Inter-|   Receive                                                |  Transmit
 face |bytes    packets errs drop fifo frame compressed multicast|bytes    packets errs drop fifo colls carrier compressed
wlp3s0:
enp4s0f2:
docker0:
    lo:                                                                                   

代码实现：

 #ethName为网卡名称
 receiveByteStart=`cat  /proc/net/dev  |grep  -E "${ethName}"|awk '{print $2}'`
 sendByteStart=`cat  /proc/net/dev  |grep  -E "${ethName}"|awk '{print $10}'`

2.4、磁盘IO

监控原理：

磁盘IO相关的信息记录在/proc/vmstat文件中，pgpgin对应的为输入方向的数据量。pgpgout对应的为输出方向的数据量。采集一段时间的数据量，除以时间来计算速率。

代码实现：

 #disk IO in
 function diskIOIn(){
     #获取磁盘入方向IO
     inIoStart=`awk '/pgpgin/{print $2}' /proc/vmstat`
     sleep
     inIoEnd=`awk '/pgpgin/{print $2}' /proc/vmstat`
     inIo=$(((inIoEnd-inIoStart)/(*)))
     logInfo "Host [${ip}] in IO is :  ${inIo} MB / s"

 }

3、脚本代码

• hostLists:监控主机的IP集合。

• sysMonitor.sh*：获取各项监控信息的脚本。

 #!/bin/bash
 #监控linux主机系统信息
 #导入工具模块
 source utils

 #获取CPU占用率
 function cpuUsage()
 {
     #物理CPU个数
     phyCPUNums=`cat /proc/cpuinfo |grep "physical id"|sort |uniq|wc -l`
     #逻辑CPU个数
     lgCPUNums=`cat /proc/cpuinfo |grep "processor"|wc -l`
         #core
     cores=`cat /proc/cpuinfo |grep "cores"|uniq|awk '{print $4}'`
     logInfo "Host [${ip}] physical CPU nums is :  ${phyCPUNums}"
     logInfo "Host [${ip}] logic CPU nums is :  ${lgCPUNums}"
     logInfo "Host [${ip}] core nums is :  ${cores}"
     #CPU占用率
     #获取CPU的总量与使用量
     cpuTotalStart=`awk 'BEGIN{total=0} /cpu / {for(i=2;i<=NF;i++);total+=i}END{print $total}' /proc/stat`
         cpuUsedStart=`awk 'BEGIN{used=0} /cpu / { used=$2+$3+$4+$7+$8 }END{print used}' /proc/stat`
     #隔30s再获取一次CPU总量与使用量并计算差值
     sleep
     cpuTotalEnd=`awk 'BEGIN{total=0} /cpu / {for(i=2;i<=NF;i++);total+=i}END{print $total}' /proc/stat`
     cpuUsedEnd=`awk 'BEGIN{used=0} /cpu / { used=$2+$3+$4+$7+$8 }END{print used}' /proc/stat`
     usedCPU=`expr ${cpuUsedEnd} - ${cpuUsedStart}`
     totalCPU=`expr ${cpuTotalEnd} - ${cpuTotalStart}`
     logInfo "Host [${ip}] CPU usage is :  $(usagePercent ${usedCPU} ${totalCPU}) %"

 }

 #获取内存使用率
 function memUsage(){
     logInfo "Begin to get mem usage of Host [${ip}]"
     #获取总内存
     totalMem=`awk '/MemTotal/{print $2}' /proc/meminfo`
     #获取空闲内存
     freeMem=`awk '/MemFree/{print $2}' /proc/meminfo`
     usedMem=`expr ${totalMem} - ${freeMem}`
     #echo $(usagePercent ${usedMem} ${totalMem})
     #echo $(kbToGb ${totalMem})
     logInfo "Host [${ip}] total mem is :  $(kbToGb ${totalMem}) GB"
     #计算内存使用率并打印到日志中
     logInfo "Host [${ip}] mem usage is :  $(usagePercent ${usedMem} ${totalMem}) %"
     logInfo "End to get mem usage of Host [${ip}]"
 }

 #网卡平均每秒流量
 function netData(){
     logInfo "Begin to get  net data of Host [${ip}]"
     ethName=$
     receiveByteStart=`cat  /proc/net/dev  |grep  -E "${ethName}"|awk '{print $2}'`
     sendByteStart=`cat  /proc/net/dev  |grep  -E "${ethName}"|awk '{print $10}'`
     sleep
     receiveByteSEnd=`cat  /proc/net/dev  |grep  -E "${ethName}"|awk '{print $2}'`
     sendBytesEnd=`cat  /proc/net/dev  |grep  -E "${ethName}"|awk '{print $10}'`
     inDataRate=$(echo "scale=2;(${receiveByteSEnd}-${receiveByteStart})/10" | bc)
     outDataRate=$(echo "scale=2;(${sendBytesEnd}-${sendByteStart})/10" | bc)
     logInfo "Host [${ip}] in data is :  ${inDataRate} kb / s"
     logInfo "Host [${ip}] out data is :  ${outDataRate} kb / s"
     logInfo "End to get  net data of Host [${ip}]"
 }

 #磁盘空间使用情况
 function diskUsage(){
     logInfo "Begin to get disk usage of Host [${ip}]"
     noTimeLogInfo "`df -h`"
     logInfo "End to get disk usage of Host [${ip}]"
 }

 #disk IO in
 function diskIOIn(){
     #获取磁盘入方向IO
     inIoStart=`awk '/pgpgin/{print $2}' /proc/vmstat`
     sleep
     inIoEnd=`awk '/pgpgin/{print $2}' /proc/vmstat`
     inIo=$(((inIoEnd-inIoStart)/(*)))
     logInfo "Host [${ip}] in IO is :  ${inIo} MB / s"

 }

 #disk IO out
 function diskIOout(){
     #获取磁盘出方向的IO
     outIoStart=`awk '/pgpgout/{print $2}' /proc/vmstat`
     sleep
     outIoEnd=`awk '/pgpgout/{print $2}' /proc/vmstat`
     outIo=$(((outIoEnd-outIoStart)/(*)))
     logInfo "Host [${ip}] out IO is :  ${outIo} MB / s"
 }

 #当前在线用户
 function onlineUser(){
     user=`w |awk  'NR>1'|awk '{print $1 "\t" "\t" $4}'`
     userCount=`w |awk  'NR>1'|wc -l`
         #loginAt=`w |awk  'NR>1'|awk '{print $4 }'`
         logInfo "There are [${userCount}] users online now."
     noTimeLogInfo "UserName        loginAt"
         noTimeLogInfo "${user}"
 }

 #判断主机网络连通性
 function isAlive(){
         for ip in `cat hostLists`
     do
     ping ${ip} -c  >/dev/null
         if [ $? -eq  ];then
         logInfo "${ip} is reachable"
         #查看在线用户
             onlineUser
         #获取CPU相关信息
         cpuUsage
         #获取mem相关信息
         memUsage
         #获取磁盘IO
         diskIOIn
         diskIOout
         #磁盘使用率
         diskUsage
         #平均每秒流接收或输出流量
         netData wlp3s0
     else
         logInfo "ERROR ${ip} is unreachable,try login in see more details.."
     fi
     done
 }

 while [  ]
     do
     isAlive
     sleep
     done

• utils：打印日志的函数等。

 #!/bin/bash
 #日志打印
 curr_path=`pwd`
 function logInfo()
 {
 local curr_time=`date "+%Y-%m-%d %H:%M:%S"`
 log_file=${curr_path}/system_status.log
 #判断日志文件是否存在
 if [ -e ${log_file} ]
    then
    #检测文件是否可写
    if [ -w ${log_file} ]
    then
        #若文件无写权限则使用chmod命令赋予权限
        chmod  ${log_file}
    fi
 else
    #若日志文件不存在则创建
    touch ${log_file}
 fi
 #写日志
 local info=$
 echo "${curr_time}  `whoami` [Info] ${info}">>${log_file}
 }
 function noTimeLogInfo(){
     msg=$
     echo  "${msg}">>${log_file}
 }

 #把kb转换成gb，精度为3。expr只支持整数计算
 function kbToGb(){
     kbVal=$
     gbVal=$(echo "scale=3;${kbVal}/1024/1024"| bc)
     echo $gbVal
 }
 #使用率以百分比的形式
 #第一个参数为已使用量，第二个参数为总量
 function usagePercent(){
     used=$
     total=$
     usedPercent=$(echo "scale=2;${used}*100/${total}"| bc)
     echo ${usedPercent}
 }

脚本结构：

 -rw-r--r--  stephen stephen    4月    : hostLists
 -rwxrwxr-x  stephen stephen  4月    : sysMonitor.sh*
 -rw-r--r--  stephen stephen   4月    : utils

4、运行结果

监控信息记录在日志system_status.log中。运行结果如下：

-- ::  stephen [Info] 192.168.1.109 is reachable
-- ::  stephen [Info] There are [] users online now.
UserName        loginAt
USER        LOGIN@
stephen        :
-- ::  stephen [Info] Host [192.168.1.109] physical CPU nums is :
-- ::  stephen [Info] Host [192.168.1.109] logic CPU nums is :
-- ::  stephen [Info] Host [192.168.1.109] core nums is :
-- ::  stephen [Info] Host [192.168.1.109] CPU usage is :  10.12 %
-- ::  stephen [Info] Begin to get mem usage of Host [192.168.1.109]
-- ::  stephen [Info] Host [192.168.1.109] total mem is :  3.741 GB
-- ::  stephen [Info] Host [192.168.1.109] mem usage is :  95.83 %
-- ::  stephen [Info] End to get mem usage of Host [192.168.1.109]
-- ::  stephen [Info] Host [192.168.1.109] in IO is :   MB / s
-- ::  stephen [Info] Host [192.168.1.109] out IO is :   MB / s
-- ::  stephen [Info] Begin to get disk usage of Host [192.168.1.109]
文件系统        容量  已用  可用 已用% 挂载点
udev            .9G       .9G    % /dev
tmpfs           384M  2.0M  382M    % /run
/dev/sda10       42G   20G   20G   % /
tmpfs           .9G   20M  .9G    % /dev/shm
tmpfs           5.0M  .0K  5.0M    % /run/lock
tmpfs           .9G       .9G    % /sys/fs/cgroup
/dev/loop0      3.8M  3.8M       % /snap/notepad-plus-plus/
/dev/loop2       54M   54M       % /snap/core18/
/dev/loop4      441M  441M       % /snap/wine-platform/
/dev/loop5      441M  441M       % /snap/wine-platform/
/dev/loop7      3.8M  3.8M       % /snap/notepad-plus-plus/
/dev/loop3       90M   90M       % /snap/core/
/dev/loop1      274M  274M       % /snap/wps-office-multilang/
/dev/loop6       91M   91M       % /snap/core/
/dev/loop8       92M   92M       % /snap/core/
/dev/loop9       36M   36M       % /snap/gtk-common-themes/
/dev/loop10     3.8M  3.8M       % /snap/notepad-plus-plus/
/dev/loop11     441M  441M       % /snap/wine-platform/
tmpfs           384M   16K  384M    % /run/user/
tmpfs           384M   52K  384M    % /run/user/
-- ::  stephen [Info] End to get disk usage of Host [192.168.1.109]
-- ::  stephen [Info] Begin to get  net data of Host [192.168.1.109]
-- ::  stephen [Info] Host [192.168.1.109] in data is :  42.90 kb / s
-- ::  stephen [Info] Host [192.168.1.109] out data is :  7.00 kb / s
-- ::  stephen [Info] End to get  net data of Host [192.168.1.109]
-- ::  stephen [Info] ERROR 255.255.255.254 is unreachable,try login in see more details..

5、参考文档

5.1、ifstat网络流量监控之/proc/net/dev文件

https://blog.csdn.net/kongshuai19900505/article/details/80676607

5.2、awk命令

http://man.linuxde.net/awk

5.3、使用shell脚本采集系统cpu、内存、磁盘、网络等信息

https://www.jb51.net/article/50436.htm