以下shell/ target=_blank class=infotextkey>shell脚本分为两种情况，第一种情况是nginx作为最前端的负载均衡器，其集群架构为Nginx+Keepalived时。
1，shell文件log-nginx.sh
#!/bin/bash
# www.jb200.com
if [$# -eq 0 ]; then
echo "Error: please specify logfile."
exit 0
else
LOG=￥1
fi
if [ ! -f $1 ]; then
echo "Sorry， sir， I can""t find this apache log file， pls try again!"
exit 0
fi
################################
echo "Most of the ip:"
echo "-------------------------------------------"
linuxjishu/13830.html target=_blank class=infotextkey>awk ""{ print $1 }""$LOG| sort| uniq -c| sort -nr| head -10
echo
echo
###################
echo "Most of the time:"
echo "--------------------------------------------"
awk ""{ print $4 }""$LOG| cut -c 14-18| sort| uniq -c| sort -nr| head -10
echo
echo
#######################
echo "Most of the page:"
echo "--------------------------------------------"
awk ""{print $11}""$LOG| sed ""s/^.*（.cn*）"/1/g""| sort| uniq -c| sort -rn| head -10
echo
echo
#####################3
echo "Most of the time / Most of the ip:"
echo "--------------------------------------------"
awk ""{ print $4 }""$LOG| cut -c 14-18| sort -n| uniq -c| sort -nr| head -10 > timelog
for i in ""awk ""{ print $2 }"" timelog""
do
num=""grep $i timelog| awk ""{ print $1 }""""
echo "$i $num"
ip=""grep $i $LOG| awk ""{ print $1}""| sort -n| uniq -c| sort -nr| head -10""
echo "$ip"
echo
done
rm -f timelog
第二种情况是以Nginx作为Web端，置于LVS后面，这时要剔除掉LVS的IP地址，比如LVS服务器的公网IP地址(像203.93.236.141、203.93.236.145等)。
这样可以将第一种情况的脚本略微调整下：
#!/bin/bash
# www.jb200.com
if ［$# -eq 0 ］; then
echo "Error: please specify logfile."
exit 0
else
cat$1| egrep -v '203.93.236.141|145' > LOG
fi
if ［ ! -f$1 ］; then
echo "Sorry, sir, I can't find this apache log file, pls try again!"
exit 0
fi
###################################################
echo "Most of the ip:"
echo "-------------------------------------------"
awk '{ print$1 }' LOG| sort| uniq -c| sort -nr| head -10
echo
echo
####################################################
echo "Most of the time:"
echo "--------------------------------------------"
awk '{ print$4 }' LOG| cut -c 14-18| sort| uniq -c| sort -nr| head -10
echo
echo
####################################################
echo "Most of the page:"
echo "--------------------------------------------"
awk '{print$11}' LOG| sed 's/^.*(.cn*)"/1/g'| sort| uniq -c| sort -rn| head -10
echo
echo
####################################################
echo "Most of the time / Most of the ip:"
echo "--------------------------------------------"
awk '{ print$4 }' LOG| cut -c 14-18| sort -n| uniq -c| sort -nr| head -10 > timelog
for i in 'awk '{ print$2 }' timelog'
do
num='grep$i timelog| awk '{ print$1 }''
echo "$i$num"
ip='grep$i LOG| awk '{ print$1}'| sort -n| uniq -c| sort -nr| head -10'
echo "$ip"
echo
done
rm -f timelog
#!/bin/bash
if ［$# -eq 0 ］; then
echo "Error: please specify logfile."
exit 0
else
cat$1| egrep -v '203.93.236.141|145' > LOG
fi
if ［ ! -f$1 ］; then
echo "Sorry, sir, I can't find this apache log file, pls try again!"
exit 0
fi
###################################################
echo "Most of the ip:"
echo "-------------------------------------------"
awk '{ print$1 }' LOG| sort| uniq -c| sort -nr| head -10
echo
echo
####################################################
echo "Most of the time:"
echo "--------------------------------------------"
awk '{ print$4 }' LOG| cut -c 14-18| sort| uniq -c| sort -nr| head -10
echo
echo
####################################################
echo "Most of the page:"
echo "--------------------------------------------"
awk '{print$11}' LOG| sed 's/^.*(.cn*)"/1/g'| sort| uniq -c| sort -rn| head -10
echo
echo
####################################################
echo "Most of the time / Most of the ip:"
echo "--------------------------------------------"
awk '{ print$4 }' LOG| cut -c 14-18| sort -n| uniq -c| sort -nr| head -10 > timelog
for i in 'awk '{ print$2 }' timelog'
do
num='grep$i timelog| awk '{ print$1 }''
echo "$i$num"
ip='grep$i LOG| awk '{ print$1}'| sort -n| uniq -c| sort -nr| head -10'
echo "$ip"
echo
done
rm -f timelog
可以用此脚本分析文件名为www_tomcat_20110331.log的文件。[root@localhost 03]# sh counter_nginx.sh www_tomcat_20110331.log，大家可能比较关注脚本运行后的第一项和第二项结果，即访问网站最多的IP和哪个时间段IP访问比较多，如下所示：
如果对日志的要求不高，可以直接通过awk命令和sed命令来分析linux日志(如果对perl熟练也可以用它来操作)，还可以通过awstats来进行详细分析，后者尤其适合web服务器和邮件服务器。
另外，如果对日志有特殊需求的话，还可以架设专用的日志服务器来收集linux服务器日志。