Tomcat日志分析

  1 #!/bin/bash
  2 #Shell      statistics.sh
  3 #Author 　　 lipc
  4 #Date     　20200818
  5 #Ps    　　 tomcat接入日志分析,需要tomcat日志开启访问时间记录
  6 
  7 time1=$(date "+%Y-%m-%d %H:%M:%S")
  8 time2=$(date "+%Y-%m-%d-%H")
  9 echo "请输入日志路径,例如:/tmp/localhost_access_log.2020-12-19.txt"
 10 read name
 11 echo "请输入日志存放路径,例如:/tmp/test/"
 12 read dir
 13 echo "请输入模块名称,例如:pbs"
 14 read module
 15 log="$dir""$module"$time2.log
 16 statistics="$dir""$module"statistics$time2.log
 17 IFS=$'
'
 18 
 19 function check() {
 20     if [ -f $name ]; then
 21         echo $name'文件目录检测成功'
 22         echo ""
 23         echo "程序开始时间："$time1 >>$statistics
 24         echo "正在收集URL接口信息，预计一分钟，请等待......"
 25         meta=$(cat $name | awk '{print $7}' | awk -F 'sig' '{print $1}' | sort | uniq | grep -v -w '/' | grep -v 400)
 26         amount=$(echo "$meta" | wc -l)
 27         echo "URL接口信息收集完成,即将开始下一步操作......"
 28         echo ""
 29     else
 30         echo $name'文件目录检测失败，请重新检查文件路径'
 31         exit 1
 32     fi
 33 }
 34 
 35 function metadata() {
 36     echo "正在收集日志元数据，用于后续统计分析操作,日志存放于$log......"
 37     i=0
 38     for url in $meta; do
 39         w=$(expr $i * 100 / $amount)
 40         echo "当前进度$w%"
 41         for time in $(seq -w 07 16); do
 42             num=$(cat $name | grep 2020:$time | grep $url | wc -l)
 43             echo $num $url 2020:$time >>$log
 44         done
 45         i=$(expr $i + 1)
 46     done
 47     echo "日志元数据收集完毕，存放于$log"
 48     echo ""
 49 }
 50 
 51 function concurrent() {
 52     echo "正在分析日志元数据，用于获取接口并发信息,日志存放于$statistics......"
 53     echo "每个接口的5个最高并发时段" >>$statistics
 54     for url in $meta; do
 55         cat $log | grep $url | sort -nr | head -n 5 >>$statistics
 56         echo "" >>$statistics
 57     done
 58 
 59     echo "全天最高并发的5个接口" >>$statistics
 60     for url in $meta; do
 61         a=$(cat $name | grep $url | wc -l)
 62         echo $a $url >>"$dir"a.log
 63     done
 64     cat "$dir"a.log | sort -nr | head -n 5 >>$statistics
 65 }
 66 
 67 function speed() {
 68     echo "正在分析接口耗时信息......"
 69     echo "" >>$statistics
 70     echo "全天10个最高耗时请求:" >>$statistics
 71     echo "" >>$statistics
 72     for url in $meta; do
 73         cat $name | grep $url | sort -nr -k 11 | head -n 1 >>"$dir"b.log
 74     done
 75 
 76     cat "$dir"b.log | sort -nr -k 11 | head -n 10 >>$statistics
 77     echo " " >>$statistics
 78     meta1=$(cat "$dir"b.log | sort -nr -k 11 | head -n 10 | awk '{print $7}' | awk -F 'sig' '{print $1}' | grep -v -w '/' | grep -v 400)
 79 
 80     echo "分析每个接口3个最高耗请求和3个最低耗请求，及其时间:" >>$statistics
 81     echo "" >>$statistics
 82     for url in $meta1; do
 83         echo "$url接口3个最高耗请求，及其时间:" >>$statistics
 84         cat $name | grep $url | sort -nr -k 11 | head -n 3 >>$statistics
 85         echo "$url接口3个最低耗请求，及其时间:" >>$statistics
 86         cat $name | grep $url | sort -nr -k 11 | tail -n 3 >>$statistics
 87         num2=$(cat $name | grep $url | awk '{print $11}' | awk '{sum+=$1} END {print "Average = ", sum/NR}')
 88         echo "$url接口平均耗时:"$num2 ms >>$statistics
 89         echo " " >>$statistics
 90     done
 91     echo "接口耗时信息分析已结束......"
 92 }
 93 
 94 function peak() {
 95     echo "正在分析接口高峰时段信息......"
 96     echo "本次日志分析，接口高峰时段时间" >>$statistics
 97     cat $statistics | awk '{print $3}' | grep 2020 | sort | uniq -c | sort -nr | head -n 6 >>$statistics
 98 }
 99 
100 check
101 metadata
102 concurrent
103 speed
104 
105 time3=$(date "+%Y-%m-%d %H:%M:%S")
106 echo "程序结束时间："$time3 >>$statistics
107 echo "本次分析结束"