Nagios监控nginx服务具体过程
2017-06-26 20:24
267 查看
1在nginx 服务器上安装nrpe客户端：
Nginx的服务须要监控起来。不然万一down了而不及时修复，会影响web应用。例如以下web应用上面启动的nginx后台进程
[root@lb-net-2 ~]# ps aux|grep nginx
nobody 15294 0.0 0.0 22432 3464 ? S Jul03 0:05 nginx: worker process
nobody 15295 0.0 0.0 22432 3480 ? S Jul03 0:05 nginx: worker process
......
nobody 15316 0.0 0.0 22432 3468 ?
S Jul03 0:05 nginx: worker process
nobody 15317 0.0 0.0 22432 3480 ? S Jul03 0:05 nginx: worker process
root 16260 0.0 0.0 20584 1684 ? Ss Jun18 0:00 nginx: master process /usr/local/nginx/sbin/nginx
root 21211 0.0 0.0 103252 860 pts/1 S+ 17:50 0:00 grep nginx
1.1，rpm方式安装nrpe客户端
下载地址：http://download.csdn.net/detail/mchdba/7493875
[root@localhost nagios]# ll
总计 768
-rw-r--r-- 1 root root 713389 12-16 12:08 nagios-plugins-1.4.11-1.x86_64.rpm
-rw-r--r-- 1 root root 32706 12-16 12:09 nrpe-2.12-1.x86_64.rpm
-rw-r--r-- 1 root root 18997 12-16 12:08 nrpe-plugin-2.12-1.x86_64.rpm
[root@localhost nagios]# rpm -ivh *.rpm --nodeps --force
1.2 在配置文件最末尾，加入配置信息以及监控主机服务器ip地址
[root@ localhost nagios]# vim /etc/nagios/nrpe.cfg
# add by tim on 2014-06-11
command[check_users]=/usr/local/nagios/libexec/check_users -w 8 -c 15
command[check_load]=/usr/local/nagios/libexec/check_load -w 15,10,5 -c 30,25,20
command[check_sda1]=/usr/local/nagios/libexec/check_disk -w 20% -c 10% -p /dev/sda
command[check_zombie_procs]=/usr/local/nagios/libexec/check_procs -w 5 -c 10 -s Z
#command[check_total_procs]=/usr/local/nagios/libexec/check_procs -w 50 -c 80
command[check_total_procs]=/usr/local/nagios/libexec/check_procs -w 750 -c 800
command[check-host-alive]=/usr/local/nagios/libexec/check_ping -H 10.xx.3.29 -w 3000.0,80% -c 5000.0,100% -p 5
allowed_hosts = 127.0.0.1,10.xx.3.41
check下命令是否生效：
[root@web-9 nrpe-2.15]# /usr/local/nagios/libexec/check_users -w 8 -c 15
USERS OK - 2 users currently logged in |users=2;8;15;0
[root@web-9 nrpe-2.15]#
看到已经USERS OK -….命令已经生效。
1.3 启动nrpe报错例如以下：
[root@web-9 ~]# service nrpe restart
Shutting down nrpe: [失败]
Starting nrpe: /usr/sbin/nrpe: error while loading shared libraries: libssl.so.6: cannot open shared object file: No such file or directory
[失败]
[root@web-9 ~]#
[root@db-m2-slave-1 nagios_client]# service nrpe start
Starting nrpe: /usr/sbin/nrpe: error while loading shared libraries: libssl.so.6: cannot open shared object file: No such file or directory
[失败]
[root@db-m2-slave-1 nagios_client]#
建立连接
[root@db-m2-slave-1 nagios_client]# ln -s /usr/lib64/libssl.so /usr/lib64/libssl.so.6
(假设没有libssl.so，就採用别的libssl.so.10来做软连接，ln -s /usr/lib64/libssl.so.10 /usr/lib64/libssl.so.6)
[root@db-m2-slave-1 nagios_client]#
再又一次启动例如以下：
[root@db-m2-slave-1 nagios_client]# service nrpe start
Starting nrpe: /usr/sbin/nrpe: error while loading shared libraries: libcrypto.so.6: cannot open shared object file: No such file or directory
[失败]
[root@web-10 ~]# ll /usr/lib64/libcrypto.so
lrwxrwxrwx. 1 root root 18 10月 13 2013 /usr/lib64/libcrypto.so -> libcrypto.so.1.0.0
[root@db-m2-slave-1 nagios_client]#
再建链接：
[root@db-m2-slave-1 nagios_client]# ln -s /usr/lib64/libcrypto.so /usr/lib64/libcrypto.so.6
(或者假设没有libcrypto.so，就採用libcrypto.so.10做软连接， ln -s /usr/lib64/libcrypto.so.10 /usr/lib64/libcrypto.so.6)
[root@db-m2-slave-1 nagios_client]# service nrpe start
Starting nrpe: [确定]
[root@db-m2-slave-1 nagios_client]#
1.4 检測下nrpe是否正常执行：
去nagios服务器端check下
[root@cache-2 ~]# /usr/local/nagios/libexec/check_nrpe -H 10.xx.3.xx
NRPE v2.12
[root@cache-2 ~]#
看到返回NRPE v2.15表示已经连接成功，客户端的nrpe服务已经监控完毕。
2，比較简单的通过check_http的方式监控
能够在/etc/nagios/nrpe.cfg里面採用check_http的方式来获取nginx是否执行：
(1) 编辑nrpe.cfg
Vim /etc/nagios/nrpe.cfg
command[check_nginx_status]=/usr/lib/nagios/plugins/check_http -I localhost -p 80 -u /nginx_status -e 200 -w 3 -c 10
(2) 重新启动nrpe服务
[root@lb-net-2 ~]# service nrpe restart
Shutting down nrpe: [确定]
Starting nrpe: [确定]
[root@lb-net-2 ~]#
(3) 在nagios服务器端check。成功。
[root@cache-2 ~]# /usr/local/nagios/libexec/check_nrpe -H10.xx.1.22 -c check_nginx_status
HTTP OK HTTP/1.1 200 OK - 254 bytes in 0.002 seconds |time=0.002031s;3.000000;10.000000;0.000000 size=254B;;;0
(4) 在services.cfg里面加入check_nginx_status服务
define service{
host_name lb-net-2
service_description check_nginx_status
check_command check_nrpe!check_nginx_status
max_check_attempts 5
normal_check_interval 3
retry_check_interval 2
check_period 24x7
notification_interval 10
notification_period 24x7
notification_options w,u,c,r
contact_groups opsweb
}
(5) 在command.cfg加入check_nginx_status服务
define command{
command_name check_nginx_status
command_line $USER1$/check_nginx_status -I $HOSTADDRESS$ -w $Warning$ -c $Cri$
}
(6) 又一次载入nagios
[root@cache-2 objects]# service nagios reload
Running configuration check...
Reloading nagios configuration...
done
[root@cache-2 objects]#
(7) 查看界面的nginx监控服务。例如以下所看到的：
3 编写脚本来监控nginx服务
3.1 调试具体经过
[root@lb-net-2 run]# find / -name nginx.pid
/usr/local/nginx/logs/nginx.pid
[root@lb-net-2 run]# /usr/lib/nagios/plugins/check_nginxstatus -H localhost -P 80 -p /usr/local/nginx/logs/ -n /usr/local/nginx/logs/nginx.pid -s nginx_status -o /tmp/ -w 1500 -c 2000
expr: 參数数目错误
expr: 语法错误
(standard_in) 1: syntax error
/usr/lib/nagios/plugins/check_nginxstatus: line 258: [: : integer expression expected
/usr/lib/nagios/plugins/check_nginxstatus: line 262: [: : integer expression expected
OK - nginx is running. requests per second, connections per second ( requests per connection) | 'reqpsec'= 'conpsec'= 'conpreq'= ]
去查看262行。将逻辑运算符 "-a" 改成 "&&"
[root@lb-net-2 run]# vim /usr/lib/nagios/plugins/check_nginxstatus
[root@lb-net-2 run]# /usr/lib/nagios/plugins/check_nginxstatus -H localhost -P 80 -p /usr/local/nginx/logs/ -n /usr/local/nginx/logs/nginx.pid -s nginx_status -o /tmp/ -w 1500 -c 2000
expr: 參数数目错误
expr: 语法错误
(standard_in) 1: syntax error
/usr/lib/nagios/plugins/check_nginxstatus: line 258: [: missing `]'
/usr/lib/nagios/plugins/check_nginxstatus: line 262: [: : integer expression expected
OK - nginx is running. requests per second, connections per second ( requests per connection) | 'reqpsec'= 'conpsec'= 'conpreq'= ]
[root@lb-net-2 run]#
看到已经OK了。再改动文件。
[root@lb-net-2 run]# vim /usr/lib/nagios/plugins/check_nginxstatus
[root@lb-net-2 run]#
[root@lb-net-2 run]# /usr/lib/nagios/plugins/check_nginxstatus -H localhost -P 80 -p /usr/local/nginx/logs/ -n /usr/local/nginx/logs/nginx.pid -s nginx_status -o /tmp/ -w 1500 -c 2000
expr: 參数数目错误
expr: 语法错误
(standard_in) 1: syntax error
/usr/lib/nagios/plugins/check_nginxstatus: line 258: [: missing `]'
OK - nginx is running. requests per second, connections per second ( requests per connection) | 'reqpsec'= 'conpsec'= 'conpreq'= ]
[root@lb-net-2 run]#
将[]改成使用"[[]]"。 就可以！
[root@lb-net-2 run]# vim /usr/lib/nagios/plugins/check_nginxstatus
[root@lb-net-2 run]#
[root@lb-net-2 run]#
[root@lb-net-2 run]# /usr/lib/nagios/plugins/check_nginxstatus -H localhost -P 80 -p /usr/local/nginx/logs/ -n /usr/local/nginx/logs/nginx.pid -s nginx_status -o /tmp/ -w 1500 -c 2000
expr: 參数数目错误
expr: 语法错误
(standard_in) 1: syntax error
OK - nginx is running. requests per second, connections per second ( requests per connection) | 'reqpsec'= 'conpsec'= 'conpreq'= ]
[root@lb-net-2 run]#
凝视掉#reqpcon=`echo "scale=2; $reqpsec / $conpsec" | bc -l`之后。就不会报(standard_in) 1: syntax error错误，例如以下所看到的：
[root@lb-net-2 run]# /usr/lib/nagios/plugins/check_nginxstatus -H localhost -P 80 -p /usr/local/nginx/logs/ -s nginx_status -n nginx.pid -w 15000 -c 20000
expr: 參数数目错误
expr: 语法错误
OK - nginx is running. requests per second, connections per second ( requests per connection) | 'reqpsec'= 'conpsec'= 'conpreq'= ]
[root@lb-net-2 run]#
凝视掉# reqpsec=`expr $tmp2_reqpsec - $tmp1_reqpsec` 就不会再报 expr: 參数数目错误，例如以下所看到的：
报错：
[root@lb-net-2 run]# /usr/lib/nagios/plugins/check_nginxstatus -H localhost -P 80 -p /usr/local/nginx/logs/ -s nginx_status -n nginx.pid -w 15000 -c 20000
expr: 语法错误
OK - nginx is running. requests per second, connections per second ( requests per connection) | 'reqpsec'= 'conpsec'= 'conpreq'= ]
再次凝视掉 #reqpcon=`echo "scale=2; $reqpsec / $conpsec" | bc -l` 后。执行不会报expr: 语法错误。例如以下所看到的：
[root@lb-net-2 run]# /usr/lib/nagios/plugins/check_nginxstatus -H localhost -P 80 -p /usr/local/nginx/logs/ -s nginx_status -n nginx.pid -w 15000 -c 20000
OK - nginx is running. requests per second, connections per second ( requests per connection) | 'reqpsec'= 'conpsec'= 'conpreq'= ]
[root@lb-net-2 run]#
看到这里发现'reqpsec'= 'conpsec'= 'conpreq'=都没有值，可是nginx又是在启动执行着，问题出在哪里？经过排查，原来是nginx_status服务没有启动。须要在/usr/local/nginx/conf/nginx.conf配置文件中面加入例如以下配置：
# 加入pid參数
pid logs/nginx.pid;
#charset koi8-r;
access_log logs/host.access.log main;
location /nginx_status {
stub_status on;
access_log off;
deny all;
}
然后又一次载入nginx，看到新的nginx-status文件是生成了。可是文件内容为空，例如以下所看到的：
[root@lb-net-2 logs]# ll /tmp/nginx*
-rw-r--r--. 1 root root 0 7月 3 15:06 /tmp/nginx-status.1
[root@lb-net-2 logs]#
去查看ngins后台日志
[root@lb-net-2 logs]# cd /usr/local/nginx/
[root@lb-net-2 logs]# tail -n 300 error.log
……
2014/07/03 15:05:47 [error] 4285#0: *1851293 access forbidden by rule, client: 127.0.0.1, server: localhost, request: "GET /nginx_status HTTP/1.0", host: "localhost"
2014/07/03 15:05:48 [error] 4285#0: *1851294 access forbidden by rule, client: 127.0.0.1, server: localhost, request: "GET /nginx_status HTTP/1.0", host: "localhost"
2014/07/03 15:06:12 [error] 4282#0: *1851362 access forbidden by rule, client: 127.0.0.1, server: localhost, request: "GET /nginx_status HTTP/1.0", host: "localhost"
2014/07/03 15:06:13 [error] 4282#0: *1851363 access forbidden by rule, client: 127.0.0.1, server: localhost, request: "GET /nginx_status HTTP/1.0", host: "localhost"
2014/07/03 15:06:55 [error] 4285#0: *1851509 access forbidden by rule, client: 127.0.0.1, server: localhost, request: "GET /nginx_status HTTP/1.0", host: "localhost"
2014/07/03 15:06:56 [error] 4285#0: *1851519 access forbidden by rule, client: 127.0.0.1, server: localhost, request: "GET /nginx_status HTTP/1.0", host: "localhost"
查看nginx编译參数
[root@lb-net-2 logs]# /usr/local/nginx/sbin/nginx -V
nginx version: nginx/1.4.2
built by gcc 4.4.7 20120313 (Red Hat 4.4.7-3) (GCC)
configure arguments: --prefix=/usr/local/nginx --with-http_stub_status_module --with-http_realip_module
证明白实是载入了stub_status插件，之后去改动配置文件。凝视掉deny all;又一次载入nginx。
[root@lb-net-2 logs]# vim /usr/local/nginx/conf/nginx.conf
#deny all;
[root@lb-net-2 logs]# service nginx reload
reload nginx
[root@lb-net-2 logs]#
[root@lb-net-2 logs]# ll /tmp/nginx*
ls: 无法訪问/tmp/nginx*: 没有那个文件或文件夹
[root@lb-net-2 logs]#
还是没有看到/tmp/nginx-status.1状态文件生成。因为nagios下监控nginx的脚本是从nginx-status.1获取数据，假设没有这个文件，没有办法获取数据。
继续google，”nginx stub_status没有生成nginx-status.1”文件。看到有人说仅仅要配置好了这个状态文件有没有无所谓，我就试着直接执行脚本看看是否能生效。
[root@lb-net-2 logs]# ll /tmp/nginx*
ls: 无法訪问/tmp/nginx*: 没有那个文件或文件夹
[root@lb-net-2 logs]# /root/check_nginx2.sh -H localhost -P 80 -p /usr/local/nginx/logs/ -n nginx.pid -s nginx_status -w 15000 -c 20000
OK - nginx is running. 1 requests per second, 2 connections per second (.50 requests per connection) | 'reqpsec'=1 'conpsec'=2 'conpreq'=.50 ]
[root@lb-net-2 logs]#
看到'reqpsec'=1 'conpsec'=2 'conpreq'=.50里面有数据了，再去check下文件有没有生成，例如以下所看到的：
[root@lb-net-2 logs]# ll /tmp/nginx*
ls: 无法訪问/tmp/nginx*: 没有那个文件或文件夹
[root@lb-net-2 logs]#
还是没有文件生成，可是check已经有数据了，证明不一定要拘泥于是否在/tmp/文件夹下是否有nginx-status.1文件。
通过脚本分析例如以下：
[root@lb-net-2 logs]# vim /usr/lib/nagios/plugins/check_nginxstatus
180 get_status() {
181 if [ "$secure" = 1 ]
182 then
183 wget_opts="-O- -q -t 3 -T 3 --no-check-certificate"
184 out1=`wget ${wget_opts} http://${hostname}:${port}/${status_page}`
185 sleep 1
186 out2=`wget ${wget_opts} http://${hostname}:${port}/${status_page}`
187 else
188 wget_opts="-O- -q -t 3 -T 3"
189 out1=`wget ${wget_opts} http://${hostname}:${port}/${status_page}`
190 sleep 1
191 out2=`wget ${wget_opts} http://${hostname}:${port}/${status_page}`
192 fi
193
194 if [ -z "$out1" -o -z "$out2" ]
195 then
196 echo "UNKNOWN - Local copy/copies of $status_page is empty."
197 exit $ST_UK
198 fi
199 }
是通过訪问`wget -O- -q -t 3 -T 3 --no-check-certificate http://10.xx.xx.xx:80/nginx_status`这个链接来获取status的数据记录的，而不是去载入/tmp/nginx-status.1文件来获取数据的。
直接訪问 http://10.xx.xx.xx:80/nginx_status 地址就能获取nginx执行数据，例如以下图所看到的：
在nagios服务器上check下。报错：
[root@cache-2 ~]# /usr/local/nagios/libexec/check_nrpe -H10.xx.xx.xx -c check_nginx_status
UNKNOWN - Local copy/copies of nginx_status is empty.
[root@cache-2 ~]#
检查监控脚本，搜索 ‘Local copy/copies of nginx_status is empty.’在第197行，有例如以下代码：
195 if [ -z "$out1" -o -z "$out2" ]
196 then
197 echo "UNKNOWN - Local copy/copies of $status_page is empty."
198 exit $ST_UK
199 fi
看出是因为if [ -z "$out1" -o -z "$out2" ]这个推断生效。导致监控脚本执行到这里就exit了。继续调试。发现用nagios服务器调用脚本的时候。执行到下面第190行到第192行
out1=`/usr/bin/wget ${wget_opts} http://${hostname}:${port}/${status_page}`
sleep 1
out2=`/usr/bin/wget ${wget_opts} http://${hostname}:${port}/${status_page}`
的时候。out1为空，out2也为空，所以在后面的if [ -z "$out1" -o -z "$out2" ]推断通过报出信息为：UNKNOWN - Local copy/copies of $status_page is empty. 然后直接exit。
说明：因为nginx是要调用wget命令来获取nginx_status状态的，而wget命令是仅仅能以root用户来执行的, 所以须要将nagios用户设置成能够无需password直接su成root，这样就能以nagios用户执行命令sudo /usr/lib/nagios/plugins/check_nginxstatus 。在centos系统中。无法直接调用sudo命令，须要改动/etc/sudoers, 找到 #Defaults requiretty 并取消凝视，另外新增一行。表示nagios用户不须要登陆终端就能够调用命令。例如以下所看到的：
Defaults requiretty
Defaults:nagios !requiretty
#加入nagios 请求sudo，同意特定指令时（可跟參数），不须要password（如）。
nagios ALL=(ALL) NOPASSWD: ALL
改动完后。再check，数据出来了：
[root@cache-2 ~]# /usr/local/nagios/libexec/check_nrpe -H10.xx.xx.xx -c check_nginx_status
OK - nginx is running. 1 requests per second, 1 connections per second (1.00 requests per connection) | 'reqpsec'=1 'conpsec'=1 'conpreq'=1.00 ]
[root@cache-2 ~]#
3.2 share下check_nginxstatus脚本
#!/bin/sh
PROGNAME=`basename $0`
VERSION=\\\"Version 1.1,\\\"
AUTHOR=\\\"tim man\\\"
ST_OK=0
ST_WR=1
ST_CR=2
ST_UK=3
hostname=\\\"localhost\\\"
port=80
path_pid=/var/run
name_pid=\\\"nginx.pid\\\"
status_page=\\\"nginx_status\\\"
pid_check=1
secure=0
print_version() {
echo \\\"$VERSION $AUTHOR\\\"
}
print_help() {
print_version $PROGNAME $VERSION
echo \\\"\\\"
echo \\\"$PROGNAME is a Nagios plugin to check whether nginx is running.\\\"
echo \\\"It also parses the nginx\\\'s status page to get requests and\\\"
echo \\\"connections per second as well as requests per connection. You\\\"
echo \\\"may have to alter your nginx configuration so that the plugin\\\"
echo \\\"can access the server\\\'s status page.\\\"
echo \\\"The plugin is highly configurable for this reason. See below for\\\"
echo \\\"available options.\\\"
echo \\\"\\\"
echo \\\"$PROGNAME -H localhost -P 80 -p /var/run -n nginx.pid \\\"
echo \\\" -s nginx_statut -o /tmp [-w INT] [-c INT] [-S] [-N]\\\"
echo \\\"\\\"
echo \\\"Options:\\\"
echo \\\" -H/--hostname)\\\"
echo \\\" Defines the hostname. Default is: localhost\\\"
echo \\\" -P/--port)\\\"
echo \\\" Defines the port. Default is: 80\\\"
echo \\\" -p/--path-pid)\\\"
echo \\\" Path where nginx\\\'s pid file is being stored. You might need\\\"
echo \\\" to alter this path according to your distribution. Default\\\"
echo \\\" is: /var/run\\\"
echo \\\" -n/--name_pid)\\\"
echo \\\" Name of the pid file. Default is: nginx.pid\\\"
echo \\\" -N/--no-pid-check)\\\"
echo \\\" Turn this on, if you don\\\'t want to check for a pid file\\\"
echo \\\" whether nginx is running, e.g. when you\\\'re checking a\\\"
echo \\\" remote server. Default is: off\\\"
echo \\\" -s/--status-page)\\\"
echo \\\" Name of the server\\\'s status page defined in the location\\\"
echo \\\" directive of your nginx configuration. Default is:\\\"
echo \\\" nginx_status\\\"
echo \\\" -S/--secure)\\\"
echo \\\" In case your server is only reachable via SSL, use this\\\"
echo \\\" this switch to use HTTPS instead of HTTP. Default is: off\\\"
echo \\\" -w/--warning)\\\"
echo \\\" Sets a warning level for requests per second. Default is: off\\\"
echo \\\" -c/--critical)\\\"
echo \\\" Sets a critical level for requests per second. Default is:\\\"
echo \\\" off\\\"
exit $ST_UK
}
while test -n \\\"$1\\\"; do
case \\\"$1\\\" in
-help|-h)
print_help
exit $ST_UK
;;
--version|-v)
print_version $PROGNAME $VERSION
exit $ST_UK
;;
--hostname|-H)
hostname=$2
shift
;;
--port|-P)
port=$2
shift
;;
--path-pid|-p)
path_pid=$2
shift
;;
--name-pid|-n)
name_pid=$2
shift
;;
--no-pid-check|-N)
pid_check=0
;;
--status-page|-s)
status_page=$2
shift
;;
--secure|-S)
secure=1
;;
--warning|-w)
warning=$2
shift
;;
--critical|-c)
critical=$2
shift
;;
*)
echo \\\"Unknown argument: $1\\\"
print_help
exit $ST_UK
;;
esac
shift
done
get_wcdiff() {
if [ ! -z \\\"$warning\\\" -a ! -z \\\"$critical\\\" ]
then
wclvls=1
if [ ${warning} -ge ${critical} ]
then
wcdiff=1
fi
elif [ ! -z \\\"$warning\\\" -a -z \\\"$critical\\\" ]
then
wcdiff=2
elif [ -z \\\"$warning\\\" -a ! -z \\\"$critical\\\" ]
then
wcdiff=3
fi
}
val_wcdiff() {
if [ \\\"$wcdiff\\\" = 1 ]
then
echo \\\"Please adjust your warning/critical thresholds. The warning \\\\
must be lower than the critical level!\\\"
exit $ST_UK
elif [ \\\"$wcdiff\\\" = 2 ]
then
echo \\\"Please also set a critical value when you want to use \\\\
warning/critical thresholds!\\\"
exit $ST_UK
elif [ \\\"$wcdiff\\\" = 3 ]
then
echo \\\"Please also set a warning value when you want to use \\\\
warning/critical thresholds!\\\"
exit $ST_UK
fi
}
check_pid() {
if [ -f \\\"$path_pid/$name_pid\\\" ]
then
retval=0
else
retval=1
fi
}
get_status() {
if [ \\\"$secure\\\" = 1 ]
then
wget_opts=\\\"-O- -q -t 3 -T 3 --no-check-certificate\\\"
#out1=`/usr/bin/wget ${wget_opts} http://${hostname}:${port}/${status_page}`
out1=`/usr/bin/wget -O- -q -t 3 -T 3 http://localhost:80/nginx_status`
sleep 1
out2=`/usr/bin/wget -O- -q -t 3 -T 3 http://localhost:80/nginx_status`
else
wget_opts=\\\"-O- -q -t 3 -T 3\\\"
out1=`/usr/bin/wget -O- -q -t 3 -T 3 http://localhost:80/nginx_status`
sleep 1
out2=`/usr/bin/wget -O- -q -t 3 -T 3 http://localhost:80/nginx_status`
fi
if [ -z \\\"$out1\\\" -o -z \\\"$out2\\\" ]
then
echo \\\"out1:$out1 out2:$out2, UNKNOWN - Local copy/copies of $status_page is empty.\\\"
exit $ST_UK
fi
}
get_vals() {
tmp1_reqpsec=`echo ${out1}|awk \\\'{print $10}\\\'`
tmp2_reqpsec=`echo ${out2}|awk \\\'{print $10}\\\'`
reqpsec=`expr $tmp2_reqpsec - $tmp1_reqpsec`
tmp1_conpsec=`echo ${out1}|awk \\\'{print $9}\\\'`
tmp2_conpsec=`echo ${out2}|awk \\\'{print $9}\\\'`
conpsec=`expr $tmp2_conpsec - $tmp1_conpsec`
reqpcon=`echo \\\"scale=2; $reqpsec / $conpsec\\\" | bc -l`
if [ \\\"$reqpcon\\\" = \\\".99\\\" ]
then
reqpcon=\\\"1.00\\\"
fi
}
do_output() {
output=\\\"nginx is running. $reqpsec requests per second, $conpsec connections per second ($reqpcon requests per connection)\\\"
}
do_perfdata() {
perfdata=\\\"\\\'reqpsec\\\'=$reqpsec \\\'conpsec\\\'=$conpsec \\\'conpreq\\\'=$reqpcon\\\"
}
# Here we
get_wcdiff
val_wcdiff
if [ ${pid_check} = 1 ]
then
check_pid
if [ \\\"$retval\\\" = 1 ]
then
echo \\\"There\\\'s no pid file for nginx. Is nginx running? Please also make sure whether your pid path and name is correct.\\\"
exit $ST_CR
fi
fi
get_status
get_vals
do_output
do_perfdata
if [[ -n \\\"$warning\\\" ]] && [[ -n \\\"$critical\\\" ]]
then
if [[ \\\"$reqpsec\\\" -ge \\\"$warning\\\" ]] && [[ \\\"$reqpsec\\\" -lt \\\"$critical\\\" ]]
then
echo \\\"WARNING - ${output} | ${perfdata}\\\"
exit $ST_WR
elif [ \\\"$reqpsec\\\" -ge \\\"$critical\\\" ]
then
echo \\\"CRITICAL - ${output} | ${perfdata}\\\"
exit $ST_CR
else
echo \\\"OK - ${output} | ${perfdata} ]\\\"
exit $ST_OK
fi
else
echo \\\"OK - ${output} | ${perfdata}\\\"
exit $ST_OK
fi
Nginx的服务须要监控起来。不然万一down了而不及时修复，会影响web应用。例如以下web应用上面启动的nginx后台进程
[root@lb-net-2 ~]# ps aux|grep nginx
nobody 15294 0.0 0.0 22432 3464 ? S Jul03 0:05 nginx: worker process
nobody 15295 0.0 0.0 22432 3480 ? S Jul03 0:05 nginx: worker process
......
nobody 15316 0.0 0.0 22432 3468 ?
S Jul03 0:05 nginx: worker process
nobody 15317 0.0 0.0 22432 3480 ? S Jul03 0:05 nginx: worker process
root 16260 0.0 0.0 20584 1684 ? Ss Jun18 0:00 nginx: master process /usr/local/nginx/sbin/nginx
root 21211 0.0 0.0 103252 860 pts/1 S+ 17:50 0:00 grep nginx
1.1，rpm方式安装nrpe客户端
下载地址：http://download.csdn.net/detail/mchdba/7493875
[root@localhost nagios]# ll
总计 768
-rw-r--r-- 1 root root 713389 12-16 12:08 nagios-plugins-1.4.11-1.x86_64.rpm
-rw-r--r-- 1 root root 32706 12-16 12:09 nrpe-2.12-1.x86_64.rpm
-rw-r--r-- 1 root root 18997 12-16 12:08 nrpe-plugin-2.12-1.x86_64.rpm
[root@localhost nagios]# rpm -ivh *.rpm --nodeps --force
1.2 在配置文件最末尾，加入配置信息以及监控主机服务器ip地址
[root@ localhost nagios]# vim /etc/nagios/nrpe.cfg
# add by tim on 2014-06-11
command[check_users]=/usr/local/nagios/libexec/check_users -w 8 -c 15
command[check_load]=/usr/local/nagios/libexec/check_load -w 15,10,5 -c 30,25,20
command[check_sda1]=/usr/local/nagios/libexec/check_disk -w 20% -c 10% -p /dev/sda
command[check_zombie_procs]=/usr/local/nagios/libexec/check_procs -w 5 -c 10 -s Z
#command[check_total_procs]=/usr/local/nagios/libexec/check_procs -w 50 -c 80
command[check_total_procs]=/usr/local/nagios/libexec/check_procs -w 750 -c 800
command[check-host-alive]=/usr/local/nagios/libexec/check_ping -H 10.xx.3.29 -w 3000.0,80% -c 5000.0,100% -p 5
allowed_hosts = 127.0.0.1,10.xx.3.41
check下命令是否生效：
[root@web-9 nrpe-2.15]# /usr/local/nagios/libexec/check_users -w 8 -c 15
USERS OK - 2 users currently logged in |users=2;8;15;0
[root@web-9 nrpe-2.15]#
看到已经USERS OK -….命令已经生效。
1.3 启动nrpe报错例如以下：
[root@web-9 ~]# service nrpe restart
Shutting down nrpe: [失败]
Starting nrpe: /usr/sbin/nrpe: error while loading shared libraries: libssl.so.6: cannot open shared object file: No such file or directory
[失败]
[root@web-9 ~]#
[root@db-m2-slave-1 nagios_client]# service nrpe start
Starting nrpe: /usr/sbin/nrpe: error while loading shared libraries: libssl.so.6: cannot open shared object file: No such file or directory
[失败]
[root@db-m2-slave-1 nagios_client]#
建立连接
[root@db-m2-slave-1 nagios_client]# ln -s /usr/lib64/libssl.so /usr/lib64/libssl.so.6
(假设没有libssl.so，就採用别的libssl.so.10来做软连接，ln -s /usr/lib64/libssl.so.10 /usr/lib64/libssl.so.6)
[root@db-m2-slave-1 nagios_client]#
再又一次启动例如以下：
[root@db-m2-slave-1 nagios_client]# service nrpe start
Starting nrpe: /usr/sbin/nrpe: error while loading shared libraries: libcrypto.so.6: cannot open shared object file: No such file or directory
[失败]
[root@web-10 ~]# ll /usr/lib64/libcrypto.so
lrwxrwxrwx. 1 root root 18 10月 13 2013 /usr/lib64/libcrypto.so -> libcrypto.so.1.0.0
[root@db-m2-slave-1 nagios_client]#
再建链接：
[root@db-m2-slave-1 nagios_client]# ln -s /usr/lib64/libcrypto.so /usr/lib64/libcrypto.so.6
(或者假设没有libcrypto.so，就採用libcrypto.so.10做软连接， ln -s /usr/lib64/libcrypto.so.10 /usr/lib64/libcrypto.so.6)
[root@db-m2-slave-1 nagios_client]# service nrpe start
Starting nrpe: [确定]
[root@db-m2-slave-1 nagios_client]#
1.4 检測下nrpe是否正常执行：
去nagios服务器端check下
[root@cache-2 ~]# /usr/local/nagios/libexec/check_nrpe -H 10.xx.3.xx
NRPE v2.12
[root@cache-2 ~]#
看到返回NRPE v2.15表示已经连接成功，客户端的nrpe服务已经监控完毕。
2，比較简单的通过check_http的方式监控
能够在/etc/nagios/nrpe.cfg里面採用check_http的方式来获取nginx是否执行：
(1) 编辑nrpe.cfg
Vim /etc/nagios/nrpe.cfg
command[check_nginx_status]=/usr/lib/nagios/plugins/check_http -I localhost -p 80 -u /nginx_status -e 200 -w 3 -c 10
(2) 重新启动nrpe服务
[root@lb-net-2 ~]# service nrpe restart
Shutting down nrpe: [确定]
Starting nrpe: [确定]
[root@lb-net-2 ~]#
(3) 在nagios服务器端check。成功。
[root@cache-2 ~]# /usr/local/nagios/libexec/check_nrpe -H10.xx.1.22 -c check_nginx_status
HTTP OK HTTP/1.1 200 OK - 254 bytes in 0.002 seconds |time=0.002031s;3.000000;10.000000;0.000000 size=254B;;;0
(4) 在services.cfg里面加入check_nginx_status服务
define service{
host_name lb-net-2
service_description check_nginx_status
check_command check_nrpe!check_nginx_status
max_check_attempts 5
normal_check_interval 3
retry_check_interval 2
check_period 24x7
notification_interval 10
notification_period 24x7
notification_options w,u,c,r
contact_groups opsweb
}
(5) 在command.cfg加入check_nginx_status服务
define command{
command_name check_nginx_status
command_line $USER1$/check_nginx_status -I $HOSTADDRESS$ -w $Warning$ -c $Cri$
}
(6) 又一次载入nagios
[root@cache-2 objects]# service nagios reload
Running configuration check...
Reloading nagios configuration...
done
[root@cache-2 objects]#
(7) 查看界面的nginx监控服务。例如以下所看到的：
3 编写脚本来监控nginx服务
3.1 调试具体经过
[root@lb-net-2 run]# find / -name nginx.pid
/usr/local/nginx/logs/nginx.pid
[root@lb-net-2 run]# /usr/lib/nagios/plugins/check_nginxstatus -H localhost -P 80 -p /usr/local/nginx/logs/ -n /usr/local/nginx/logs/nginx.pid -s nginx_status -o /tmp/ -w 1500 -c 2000
expr: 參数数目错误
expr: 语法错误
(standard_in) 1: syntax error
/usr/lib/nagios/plugins/check_nginxstatus: line 258: [: : integer expression expected
/usr/lib/nagios/plugins/check_nginxstatus: line 262: [: : integer expression expected
OK - nginx is running. requests per second, connections per second ( requests per connection) | 'reqpsec'= 'conpsec'= 'conpreq'= ]
去查看262行。将逻辑运算符 "-a" 改成 "&&"
[root@lb-net-2 run]# vim /usr/lib/nagios/plugins/check_nginxstatus
[root@lb-net-2 run]# /usr/lib/nagios/plugins/check_nginxstatus -H localhost -P 80 -p /usr/local/nginx/logs/ -n /usr/local/nginx/logs/nginx.pid -s nginx_status -o /tmp/ -w 1500 -c 2000
expr: 參数数目错误
expr: 语法错误
(standard_in) 1: syntax error
/usr/lib/nagios/plugins/check_nginxstatus: line 258: [: missing `]'
/usr/lib/nagios/plugins/check_nginxstatus: line 262: [: : integer expression expected
OK - nginx is running. requests per second, connections per second ( requests per connection) | 'reqpsec'= 'conpsec'= 'conpreq'= ]
[root@lb-net-2 run]#
看到已经OK了。再改动文件。
[root@lb-net-2 run]# vim /usr/lib/nagios/plugins/check_nginxstatus
[root@lb-net-2 run]#
[root@lb-net-2 run]# /usr/lib/nagios/plugins/check_nginxstatus -H localhost -P 80 -p /usr/local/nginx/logs/ -n /usr/local/nginx/logs/nginx.pid -s nginx_status -o /tmp/ -w 1500 -c 2000
expr: 參数数目错误
expr: 语法错误
(standard_in) 1: syntax error
/usr/lib/nagios/plugins/check_nginxstatus: line 258: [: missing `]'
OK - nginx is running. requests per second, connections per second ( requests per connection) | 'reqpsec'= 'conpsec'= 'conpreq'= ]
[root@lb-net-2 run]#
将[]改成使用"[[]]"。 就可以！
[root@lb-net-2 run]# vim /usr/lib/nagios/plugins/check_nginxstatus
[root@lb-net-2 run]#
[root@lb-net-2 run]#
[root@lb-net-2 run]# /usr/lib/nagios/plugins/check_nginxstatus -H localhost -P 80 -p /usr/local/nginx/logs/ -n /usr/local/nginx/logs/nginx.pid -s nginx_status -o /tmp/ -w 1500 -c 2000
expr: 參数数目错误
expr: 语法错误
(standard_in) 1: syntax error
OK - nginx is running. requests per second, connections per second ( requests per connection) | 'reqpsec'= 'conpsec'= 'conpreq'= ]
[root@lb-net-2 run]#
凝视掉#reqpcon=`echo "scale=2; $reqpsec / $conpsec" | bc -l`之后。就不会报(standard_in) 1: syntax error错误，例如以下所看到的：
[root@lb-net-2 run]# /usr/lib/nagios/plugins/check_nginxstatus -H localhost -P 80 -p /usr/local/nginx/logs/ -s nginx_status -n nginx.pid -w 15000 -c 20000
expr: 參数数目错误
expr: 语法错误
OK - nginx is running. requests per second, connections per second ( requests per connection) | 'reqpsec'= 'conpsec'= 'conpreq'= ]
[root@lb-net-2 run]#
凝视掉# reqpsec=`expr $tmp2_reqpsec - $tmp1_reqpsec` 就不会再报 expr: 參数数目错误，例如以下所看到的：
报错：
[root@lb-net-2 run]# /usr/lib/nagios/plugins/check_nginxstatus -H localhost -P 80 -p /usr/local/nginx/logs/ -s nginx_status -n nginx.pid -w 15000 -c 20000
expr: 语法错误
OK - nginx is running. requests per second, connections per second ( requests per connection) | 'reqpsec'= 'conpsec'= 'conpreq'= ]
再次凝视掉 #reqpcon=`echo "scale=2; $reqpsec / $conpsec" | bc -l` 后。执行不会报expr: 语法错误。例如以下所看到的：
[root@lb-net-2 run]# /usr/lib/nagios/plugins/check_nginxstatus -H localhost -P 80 -p /usr/local/nginx/logs/ -s nginx_status -n nginx.pid -w 15000 -c 20000
OK - nginx is running. requests per second, connections per second ( requests per connection) | 'reqpsec'= 'conpsec'= 'conpreq'= ]
[root@lb-net-2 run]#
看到这里发现'reqpsec'= 'conpsec'= 'conpreq'=都没有值，可是nginx又是在启动执行着，问题出在哪里？经过排查，原来是nginx_status服务没有启动。须要在/usr/local/nginx/conf/nginx.conf配置文件中面加入例如以下配置：
# 加入pid參数
pid logs/nginx.pid;
#charset koi8-r;
access_log logs/host.access.log main;
location /nginx_status {
stub_status on;
access_log off;
deny all;
}
然后又一次载入nginx，看到新的nginx-status文件是生成了。可是文件内容为空，例如以下所看到的：
[root@lb-net-2 logs]# ll /tmp/nginx*
-rw-r--r--. 1 root root 0 7月 3 15:06 /tmp/nginx-status.1
[root@lb-net-2 logs]#
去查看ngins后台日志
[root@lb-net-2 logs]# cd /usr/local/nginx/
[root@lb-net-2 logs]# tail -n 300 error.log
……
2014/07/03 15:05:47 [error] 4285#0: *1851293 access forbidden by rule, client: 127.0.0.1, server: localhost, request: "GET /nginx_status HTTP/1.0", host: "localhost"
2014/07/03 15:05:48 [error] 4285#0: *1851294 access forbidden by rule, client: 127.0.0.1, server: localhost, request: "GET /nginx_status HTTP/1.0", host: "localhost"
2014/07/03 15:06:12 [error] 4282#0: *1851362 access forbidden by rule, client: 127.0.0.1, server: localhost, request: "GET /nginx_status HTTP/1.0", host: "localhost"
2014/07/03 15:06:13 [error] 4282#0: *1851363 access forbidden by rule, client: 127.0.0.1, server: localhost, request: "GET /nginx_status HTTP/1.0", host: "localhost"
2014/07/03 15:06:55 [error] 4285#0: *1851509 access forbidden by rule, client: 127.0.0.1, server: localhost, request: "GET /nginx_status HTTP/1.0", host: "localhost"
2014/07/03 15:06:56 [error] 4285#0: *1851519 access forbidden by rule, client: 127.0.0.1, server: localhost, request: "GET /nginx_status HTTP/1.0", host: "localhost"
查看nginx编译參数
[root@lb-net-2 logs]# /usr/local/nginx/sbin/nginx -V
nginx version: nginx/1.4.2
built by gcc 4.4.7 20120313 (Red Hat 4.4.7-3) (GCC)
configure arguments: --prefix=/usr/local/nginx --with-http_stub_status_module --with-http_realip_module
证明白实是载入了stub_status插件，之后去改动配置文件。凝视掉deny all;又一次载入nginx。
[root@lb-net-2 logs]# vim /usr/local/nginx/conf/nginx.conf
#deny all;
[root@lb-net-2 logs]# service nginx reload
reload nginx
[root@lb-net-2 logs]#
[root@lb-net-2 logs]# ll /tmp/nginx*
ls: 无法訪问/tmp/nginx*: 没有那个文件或文件夹
[root@lb-net-2 logs]#
还是没有看到/tmp/nginx-status.1状态文件生成。因为nagios下监控nginx的脚本是从nginx-status.1获取数据，假设没有这个文件，没有办法获取数据。
继续google，”nginx stub_status没有生成nginx-status.1”文件。看到有人说仅仅要配置好了这个状态文件有没有无所谓，我就试着直接执行脚本看看是否能生效。
[root@lb-net-2 logs]# ll /tmp/nginx*
ls: 无法訪问/tmp/nginx*: 没有那个文件或文件夹
[root@lb-net-2 logs]# /root/check_nginx2.sh -H localhost -P 80 -p /usr/local/nginx/logs/ -n nginx.pid -s nginx_status -w 15000 -c 20000
OK - nginx is running. 1 requests per second, 2 connections per second (.50 requests per connection) | 'reqpsec'=1 'conpsec'=2 'conpreq'=.50 ]
[root@lb-net-2 logs]#
看到'reqpsec'=1 'conpsec'=2 'conpreq'=.50里面有数据了，再去check下文件有没有生成，例如以下所看到的：
[root@lb-net-2 logs]# ll /tmp/nginx*
ls: 无法訪问/tmp/nginx*: 没有那个文件或文件夹
[root@lb-net-2 logs]#
还是没有文件生成，可是check已经有数据了，证明不一定要拘泥于是否在/tmp/文件夹下是否有nginx-status.1文件。
通过脚本分析例如以下：
[root@lb-net-2 logs]# vim /usr/lib/nagios/plugins/check_nginxstatus
180 get_status() {
181 if [ "$secure" = 1 ]
182 then
183 wget_opts="-O- -q -t 3 -T 3 --no-check-certificate"
184 out1=`wget ${wget_opts} http://${hostname}:${port}/${status_page}`
185 sleep 1
186 out2=`wget ${wget_opts} http://${hostname}:${port}/${status_page}`
187 else
188 wget_opts="-O- -q -t 3 -T 3"
189 out1=`wget ${wget_opts} http://${hostname}:${port}/${status_page}`
190 sleep 1
191 out2=`wget ${wget_opts} http://${hostname}:${port}/${status_page}`
192 fi
193
194 if [ -z "$out1" -o -z "$out2" ]
195 then
196 echo "UNKNOWN - Local copy/copies of $status_page is empty."
197 exit $ST_UK
198 fi
199 }
是通过訪问`wget -O- -q -t 3 -T 3 --no-check-certificate http://10.xx.xx.xx:80/nginx_status`这个链接来获取status的数据记录的，而不是去载入/tmp/nginx-status.1文件来获取数据的。
直接訪问 http://10.xx.xx.xx:80/nginx_status 地址就能获取nginx执行数据，例如以下图所看到的：
在nagios服务器上check下。报错：
[root@cache-2 ~]# /usr/local/nagios/libexec/check_nrpe -H10.xx.xx.xx -c check_nginx_status
UNKNOWN - Local copy/copies of nginx_status is empty.
[root@cache-2 ~]#
检查监控脚本，搜索 ‘Local copy/copies of nginx_status is empty.’在第197行，有例如以下代码：
195 if [ -z "$out1" -o -z "$out2" ]
196 then
197 echo "UNKNOWN - Local copy/copies of $status_page is empty."
198 exit $ST_UK
199 fi
看出是因为if [ -z "$out1" -o -z "$out2" ]这个推断生效。导致监控脚本执行到这里就exit了。继续调试。发现用nagios服务器调用脚本的时候。执行到下面第190行到第192行
out1=`/usr/bin/wget ${wget_opts} http://${hostname}:${port}/${status_page}`
sleep 1
out2=`/usr/bin/wget ${wget_opts} http://${hostname}:${port}/${status_page}`
的时候。out1为空，out2也为空，所以在后面的if [ -z "$out1" -o -z "$out2" ]推断通过报出信息为：UNKNOWN - Local copy/copies of $status_page is empty. 然后直接exit。
说明：因为nginx是要调用wget命令来获取nginx_status状态的，而wget命令是仅仅能以root用户来执行的, 所以须要将nagios用户设置成能够无需password直接su成root，这样就能以nagios用户执行命令sudo /usr/lib/nagios/plugins/check_nginxstatus 。在centos系统中。无法直接调用sudo命令，须要改动/etc/sudoers, 找到 #Defaults requiretty 并取消凝视，另外新增一行。表示nagios用户不须要登陆终端就能够调用命令。例如以下所看到的：
Defaults requiretty
Defaults:nagios !requiretty
#加入nagios 请求sudo，同意特定指令时（可跟參数），不须要password（如）。
nagios ALL=(ALL) NOPASSWD: ALL
改动完后。再check，数据出来了：
[root@cache-2 ~]# /usr/local/nagios/libexec/check_nrpe -H10.xx.xx.xx -c check_nginx_status
OK - nginx is running. 1 requests per second, 1 connections per second (1.00 requests per connection) | 'reqpsec'=1 'conpsec'=1 'conpreq'=1.00 ]
[root@cache-2 ~]#
3.2 share下check_nginxstatus脚本
#!/bin/sh
PROGNAME=`basename $0`
VERSION=\\\"Version 1.1,\\\"
AUTHOR=\\\"tim man\\\"
ST_OK=0
ST_WR=1
ST_CR=2
ST_UK=3
hostname=\\\"localhost\\\"
port=80
path_pid=/var/run
name_pid=\\\"nginx.pid\\\"
status_page=\\\"nginx_status\\\"
pid_check=1
secure=0
print_version() {
echo \\\"$VERSION $AUTHOR\\\"
}
print_help() {
print_version $PROGNAME $VERSION
echo \\\"\\\"
echo \\\"$PROGNAME is a Nagios plugin to check whether nginx is running.\\\"
echo \\\"It also parses the nginx\\\'s status page to get requests and\\\"
echo \\\"connections per second as well as requests per connection. You\\\"
echo \\\"may have to alter your nginx configuration so that the plugin\\\"
echo \\\"can access the server\\\'s status page.\\\"
echo \\\"The plugin is highly configurable for this reason. See below for\\\"
echo \\\"available options.\\\"
echo \\\"\\\"
echo \\\"$PROGNAME -H localhost -P 80 -p /var/run -n nginx.pid \\\"
echo \\\" -s nginx_statut -o /tmp [-w INT] [-c INT] [-S] [-N]\\\"
echo \\\"\\\"
echo \\\"Options:\\\"
echo \\\" -H/--hostname)\\\"
echo \\\" Defines the hostname. Default is: localhost\\\"
echo \\\" -P/--port)\\\"
echo \\\" Defines the port. Default is: 80\\\"
echo \\\" -p/--path-pid)\\\"
echo \\\" Path where nginx\\\'s pid file is being stored. You might need\\\"
echo \\\" to alter this path according to your distribution. Default\\\"
echo \\\" is: /var/run\\\"
echo \\\" -n/--name_pid)\\\"
echo \\\" Name of the pid file. Default is: nginx.pid\\\"
echo \\\" -N/--no-pid-check)\\\"
echo \\\" Turn this on, if you don\\\'t want to check for a pid file\\\"
echo \\\" whether nginx is running, e.g. when you\\\'re checking a\\\"
echo \\\" remote server. Default is: off\\\"
echo \\\" -s/--status-page)\\\"
echo \\\" Name of the server\\\'s status page defined in the location\\\"
echo \\\" directive of your nginx configuration. Default is:\\\"
echo \\\" nginx_status\\\"
echo \\\" -S/--secure)\\\"
echo \\\" In case your server is only reachable via SSL, use this\\\"
echo \\\" this switch to use HTTPS instead of HTTP. Default is: off\\\"
echo \\\" -w/--warning)\\\"
echo \\\" Sets a warning level for requests per second. Default is: off\\\"
echo \\\" -c/--critical)\\\"
echo \\\" Sets a critical level for requests per second. Default is:\\\"
echo \\\" off\\\"
exit $ST_UK
}
while test -n \\\"$1\\\"; do
case \\\"$1\\\" in
-help|-h)
print_help
exit $ST_UK
;;
--version|-v)
print_version $PROGNAME $VERSION
exit $ST_UK
;;
--hostname|-H)
hostname=$2
shift
;;
--port|-P)
port=$2
shift
;;
--path-pid|-p)
path_pid=$2
shift
;;
--name-pid|-n)
name_pid=$2
shift
;;
--no-pid-check|-N)
pid_check=0
;;
--status-page|-s)
status_page=$2
shift
;;
--secure|-S)
secure=1
;;
--warning|-w)
warning=$2
shift
;;
--critical|-c)
critical=$2
shift
;;
*)
echo \\\"Unknown argument: $1\\\"
print_help
exit $ST_UK
;;
esac
shift
done
get_wcdiff() {
if [ ! -z \\\"$warning\\\" -a ! -z \\\"$critical\\\" ]
then
wclvls=1
if [ ${warning} -ge ${critical} ]
then
wcdiff=1
fi
elif [ ! -z \\\"$warning\\\" -a -z \\\"$critical\\\" ]
then
wcdiff=2
elif [ -z \\\"$warning\\\" -a ! -z \\\"$critical\\\" ]
then
wcdiff=3
fi
}
val_wcdiff() {
if [ \\\"$wcdiff\\\" = 1 ]
then
echo \\\"Please adjust your warning/critical thresholds. The warning \\\\
must be lower than the critical level!\\\"
exit $ST_UK
elif [ \\\"$wcdiff\\\" = 2 ]
then
echo \\\"Please also set a critical value when you want to use \\\\
warning/critical thresholds!\\\"
exit $ST_UK
elif [ \\\"$wcdiff\\\" = 3 ]
then
echo \\\"Please also set a warning value when you want to use \\\\
warning/critical thresholds!\\\"
exit $ST_UK
fi
}
check_pid() {
if [ -f \\\"$path_pid/$name_pid\\\" ]
then
retval=0
else
retval=1
fi
}
get_status() {
if [ \\\"$secure\\\" = 1 ]
then
wget_opts=\\\"-O- -q -t 3 -T 3 --no-check-certificate\\\"
#out1=`/usr/bin/wget ${wget_opts} http://${hostname}:${port}/${status_page}`
out1=`/usr/bin/wget -O- -q -t 3 -T 3 http://localhost:80/nginx_status`
sleep 1
out2=`/usr/bin/wget -O- -q -t 3 -T 3 http://localhost:80/nginx_status`
else
wget_opts=\\\"-O- -q -t 3 -T 3\\\"
out1=`/usr/bin/wget -O- -q -t 3 -T 3 http://localhost:80/nginx_status`
sleep 1
out2=`/usr/bin/wget -O- -q -t 3 -T 3 http://localhost:80/nginx_status`
fi
if [ -z \\\"$out1\\\" -o -z \\\"$out2\\\" ]
then
echo \\\"out1:$out1 out2:$out2, UNKNOWN - Local copy/copies of $status_page is empty.\\\"
exit $ST_UK
fi
}
get_vals() {
tmp1_reqpsec=`echo ${out1}|awk \\\'{print $10}\\\'`
tmp2_reqpsec=`echo ${out2}|awk \\\'{print $10}\\\'`
reqpsec=`expr $tmp2_reqpsec - $tmp1_reqpsec`
tmp1_conpsec=`echo ${out1}|awk \\\'{print $9}\\\'`
tmp2_conpsec=`echo ${out2}|awk \\\'{print $9}\\\'`
conpsec=`expr $tmp2_conpsec - $tmp1_conpsec`
reqpcon=`echo \\\"scale=2; $reqpsec / $conpsec\\\" | bc -l`
if [ \\\"$reqpcon\\\" = \\\".99\\\" ]
then
reqpcon=\\\"1.00\\\"
fi
}
do_output() {
output=\\\"nginx is running. $reqpsec requests per second, $conpsec connections per second ($reqpcon requests per connection)\\\"
}
do_perfdata() {
perfdata=\\\"\\\'reqpsec\\\'=$reqpsec \\\'conpsec\\\'=$conpsec \\\'conpreq\\\'=$reqpcon\\\"
}
# Here we
get_wcdiff
val_wcdiff
if [ ${pid_check} = 1 ]
then
check_pid
if [ \\\"$retval\\\" = 1 ]
then
echo \\\"There\\\'s no pid file for nginx. Is nginx running? Please also make sure whether your pid path and name is correct.\\\"
exit $ST_CR
fi
fi
get_status
get_vals
do_output
do_perfdata
if [[ -n \\\"$warning\\\" ]] && [[ -n \\\"$critical\\\" ]]
then
if [[ \\\"$reqpsec\\\" -ge \\\"$warning\\\" ]] && [[ \\\"$reqpsec\\\" -lt \\\"$critical\\\" ]]
then
echo \\\"WARNING - ${output} | ${perfdata}\\\"
exit $ST_WR
elif [ \\\"$reqpsec\\\" -ge \\\"$critical\\\" ]
then
echo \\\"CRITICAL - ${output} | ${perfdata}\\\"
exit $ST_CR
else
echo \\\"OK - ${output} | ${perfdata} ]\\\"
exit $ST_OK
fi
else
echo \\\"OK - ${output} | ${perfdata}\\\"
exit $ST_OK
fi
内容来自用户分享和网络整理，不保证内容的准确性，如有侵权内容，可联系管理员处理 
相关文章推荐
- Nagios监控nginx服务详细过程
- nagios监控私有服务过程
- Nagios监控Memcached、Nginx服务 推荐
- Nginx平台安装Nagios监控服务(0608更新) 推荐
- Nagios 监控mysqlserver具体实现过程
- nagios监控mysql服务示例
- nginx平台架设nagios监控
- Nagios监控系统配置过程2
- 关于nagios监控系统添加主机和服务脚本
- Nagios3.0 NRPE 安装 监控远程Linux服务
- Nagios+Nconf 监控主机和服务
- 安装nagios 图形添加监控主机和服务的软件nconf
- 使用nagios监控oracle服务 推荐
- nagios监控linux主机和主机上的web服务
- 在nagios里面添加要监控的主机和要监控的服务以及系统参数
- nagios监控mysql主机,nginx,cpu,网卡流量
- Nagios监控系统配置过程1
- nagios监控系统配置过程
- LINUX开源监控平台Nagios(服务监控配置)