登录到远程服务器，安装monit. ubuntu安装monit很简单 sudo apt-get install monit . 安装好之后，就可以配置monit去监控应用了．
############################################################################### ## Monit control file ############################################################################### ## ## Comments begin with a '#' and extend through the end of the line. Keywords ## are case insensitive. All path's MUST BE FULLY QUALIFIED, starting with '/'. ## ## Below you will find examples of some frequently used statements. For ## information about the control file and a complete list of statements and ## options, please have a look in the Monit manual. ## ## ############################################################################### ## Global section ############################################################################### ## ## Start Monit in the background (run as a daemon): # set daemon 30 # check services at 2-minute intervals, current is 30 second # with start delay 240 # optional: delay the first check by 4-minutes (by # # default Monit check immediately after Monit start) # # ## Set syslog logging with the 'daemon' facility. If the FACILITY option is ## omitted, Monit will use 'user' facility by default. If you want to log to ## a standalone log file instead, specify the full path to the log file # # set logfile syslog facility log_daemon set logfile /var/log/monit.log # 下面的是163的邮箱服务器,请注意端口是ssl或者非ssl情况. # set mailserver smtp.163.com username "name@163.com" password "pwd" using sslv3 # 下面的这个是万网的邮箱服务器 set mailserver smtp.mxhichina.com username "name@domain.com" password "pwd" using sslv3 with timeout 30 seconds # 这个是邮件接收者 set alert receive@mail.com # 这个是邮件格式，可以自己定义. set mail-format { from: name@domain.com subject: monit alert -- $EVENT $SERVICE message: $EVENT Service $SERVICE Date: $DATE Action: $ACTION Host: $HOST Description: $DESCRIPTION Your faithful employee, Monit } ## Set the location of the Monit id file which stores the unique id for the ## Monit instance. The id is generated and stored on first Monit start. By ## default the file is placed in $HOME/.monit.id. # # set idfile /var/.monit.id set idfile /var/lib/monit/id # ## Set the location of the Monit state file which saves monitoring states ## on each cycle. By default the file is placed in $HOME/.monit.state. If ## the state file is stored on a persistent filesystem, Monit will recover ## the monitoring state across reboots. If it is on temporary filesystem, the ## state will be lost on reboot which may be convenient in some situations. # set statefile /var/lib/monit/state # ## Set the list of mail servers for alert delivery. Multiple servers may be ## specified using a comma separator. If the first mail server fails, Monit # will use the second mail server in the list and so on. By default Monit uses # port 25 - it is possible to override this with the PORT option. ## By default Monit will drop alert events if no mail servers are available. ## If you want to keep the alerts for later delivery retry, you can use the ## EVENTQUEUE statement. The base directory where undelivered alerts will be ## stored is specified by the BASEDIR option. You can limit the maximal queue ## size using the SLOTS option (if omitted, the queue is limited by space ## available in the back end filesystem). # set eventqueue basedir /var/lib/monit/events # set the base directory where events will be stored slots 100 # optionally limit the queue size # ## Monit by default uses the following format for alerts if the the mail-format ## statement is missing:: ## --8<-- ## --8<-- ## ## You can override this message format or parts of it, such as subject ## or sender using the MAIL-FORMAT statement. Macros such as $DATE, etc. ## are expanded at runtime. For example, to override the sender, use: # # set mail-format { from: monit@foo.bar } # 监控网页应用 check system domain.com if loadavg (1min) > 4 then alert if loadavg (5min) > 2 then alert if memory usage > 75% then alert if swap usage > 25% then alert if cpu usage (user) > 70% then alert if cpu usage (system) > 30% then alert if cpu usage (wait) > 20% then alert # ## You can set alert recipients whom will receive alerts if/when a ## service defined in this file has errors. Alerts may be restricted on ## events by using a filter as in the second example below. # # set alert didmehh@163.com # receive all alerts ## Do not alert when Monit start,stop or perform a user initiated action # set alert manager@foo.bar not on { instance, action } # # ## Monit has an embedded web server which can be used to view status of ## services monitored and manage services from a web interface. See the ## Monit Wiki if you want to enable SSL for the web server. # 监控情况在网页上可视 set httpd port 2812 and # use address localhost # only accept connection from localhost # allow localhost # allow localhost to connect to the server and # allow admin:monit # require user 'admin' with password 'monit' allow admin:monit # allow users of group 'monit' to connect (rw) # allow @users readonly # allow users of group 'users' to connect readonly # # monit postgresql check process web_postgresql with pidfile /var/run/postgresql/9.3-main.pid start program = "/etc/init.d/postgresql start" with timeout 60 seconds stop program = "/etc/init.d/postgresql stop" # monit nginx check process web_nginx with pidfile /run/nginx.pid start program = "/etc/init.d/nginx start" with timeout 60 seconds stop program = "/etc/init.d/nginx stop" # monit redis check process web_redis with pidfile /var/run/redis_server.pid start program = "/etc/init.d/redis_server start" with timeout 60 seconds stop program = "/etc/init.d/redis_server stop" # monit puma check process web_puma with pidfile /home/user/www/app/shared/tmp/pids/puma.pid start program = "/bin/su - ubuntu -c 'cd /home/user/www/app/current && bundle exec puma -C config/puma.rb'" stop program = "/bin/su - ubuntu -c 'kill `cat /home/user/www/app/shared/tmp/pids/puma.pid`'" # monit sidekiq check process web_sidekiq with pidfile /home/user/www/app/shared/tmp/pids/sidekiq.pid # 监控硬盘 check filesystem datafs with path /dev/xvda1 start program = "/bin/mount /data" stop program = "/bin/umount /data" if failed permission 660 then unmonitor if failed uid root then unmonitor if failed gid disk then unmonitor if space usage > 80% for 5 times within 15 cycles then alert if space usage > 99% then stop if inode usage > 30000 then alert if inode usage > 99% then stop group server # 监控home空间 #check device home with path /home/user # if SPACE usage > 0% then alert ############################################################################### ## Services ############################################################################### ## ## Check general system resources such as load average, cpu and memory ## usage. Each test specifies a resource, conditions and the action to be ## performed should a test fail. # # check system myhost.mydomain.tld # if loadavg (1min) > 4 then alert # if loadavg (5min) > 2 then alert # if memory usage > 75% then alert # if swap usage > 25% then alert # if cpu usage (user) > 70% then alert # if cpu usage (system) > 30% then alert # if cpu usage (wait) > 20% then alert # # ## Check if a file exists, checksum, permissions, uid and gid. In addition ## to alert recipients in the global section, customized alert can be sent to ## additional recipients by specifying a local alert handler. The service may ## be grouped using the GROUP option. More than one group can be specified by ## repeating the 'group name' statement. # # check file apache_bin with path /usr/local/apache/bin/httpd # if failed checksum and # expect the sum 8f7f419955cefa0b33a2ba316cba3659 then unmonitor # if failed permission 755 then unmonitor # if failed uid root then unmonitor # if failed gid root then unmonitor # alert security@foo.bar on { # checksum, permission, uid, gid, unmonitor # } with the mail-format { subject: Alarm! } # group server # # ## Check that a process is running, in this case Apache, and that it respond ## to HTTP and HTTPS requests. Check its resource usage such as cpu and memory, ## and number of children. If the process is not running, Monit will restart ## it by default. In case the service is restarted very often and the ## problem remains, it is possible to disable monitoring using the TIMEOUT ## statement. This service depends on another service (apache_bin) which ## is defined above. # # check process apache with pidfile /usr/local/apache/logs/httpd.pid # start program = "/etc/init.d/httpd start" with timeout 60 seconds # stop program = "/etc/init.d/httpd stop" # if cpu > 60% for 2 cycles then alert # if cpu > 80% for 5 cycles then restart # if totalmem > 200.0 MB for 5 cycles then restart # if children > 250 then restart # if loadavg(5min) greater than 10 for 8 cycles then stop # if failed host www.tildeslash.com port 80 protocol http # and request "/somefile.html" # then restart # if failed port 443 type tcpssl protocol http # with timeout 15 seconds # then restart # if 3 restarts within 5 cycles then timeout # depends on apache_bin # group server # # ## Check filesystem permissions, uid, gid, space and inode usage. Other services, ## such as databases, may depend on this resource and an automatically graceful ## stop may be cascaded to them before the filesystem will become full and data ## lost. # # check filesystem datafs with path /dev/sdb1 # start program = "/bin/mount /data" # stop program = "/bin/umount /data" # if failed permission 660 then unmonitor # if failed uid root then unmonitor # if failed gid disk then unmonitor # if space usage > 80% for 5 times within 15 cycles then alert # if space usage > 99% then stop # if inode usage > 30000 then alert # if inode usage > 99% then stop # group server # # ## Check a file's timestamp. In this example, we test if a file is older ## than 15 minutes and assume something is wrong if its not updated. Also, ## if the file size exceed a given limit, execute a script # # check file database with path /data/mydatabase.db # if failed permission 700 then alert # if failed uid data then alert # if failed gid data then alert # if timestamp > 15 minutes then alert # if size > 100 MB then exec "/my/cleanup/script" as uid dba and gid dba # # ## Check directory permission, uid and gid. An event is triggered if the ## directory does not belong to the user with uid 0 and gid 0. In addition, ## the permissions have to match the octal description of 755 (see chmod(1)). # ## Check a remote host availability by issuing a ping test and check the ## content of a response from a web server. Up to three pings are sent and ## connection to a port and an application level network check is performed. # # check host myserver with address 192.168.1.1 # if failed icmp type echo count 3 with timeout 3 seconds then alert # if failed port 3306 protocol mysql with timeout 15 seconds then alert # if failed url http://user:password@www.foo.bar:8080/?querystring # and content == 'action="j_security_check"' # then alert # # ############################################################################### ## Includes ############################################################################### ## ## It is possible to include additional configuration parts from other files or ## directories. # include /etc/monit/conf.d/* #这里我们保存好之后，重新加载配置文件．
sudo service monit reload然后再重新启动
sudo service monit restartPs: Puma也可以不那么玩,可以搞个文件在/etc/init.d下. 配置文件是这里
