Monitoring server Ubuntu

[wiss]

Hy.

Im installed Perfect Ubuntu server 10.04 with ispconfig 3.03, and works fine.

I would like to monitor all services and logs and receive emails when anithyng works bad.

Im too have a postgresql server running in this machine and clustering with bucardo.


What recommend me?

thank you in advance.

[itsnedkeren]

Try this:

http://www.howtoforge.com/server-mon...n-debian-lenny

Should work also for Ubuntu.

[wiss]

Thx itsnedkeren.

But this is only monitoring, not sen mail when anything fails... no?

Y read for nagios, what do you think?

Thx in advance.

[itsnedkeren]

Monit will send mails if the configured service fails. I'm using it my self, and it's very effective.

NagiOS is enterprise scale monitoring, which you would require a standalone server to run.

[wiss]

Txh.

Monit works with postgre?

Thx.

[itsnedkeren]

Originally Posted by wiss

Txh.

Monit works with postgre?

Thx.

http://mmonit.com/wiki/Monit/PostgreSQL

[wiss]

Thx so much.

I've try it now.

[wiss]

Hy!!!!

I follow the tutorial and it works very well.

Here is my monitrc.

Machine: OpenVZ ubuntu server 10.04 PERFECT SERVER ISPCONFIG 3.

set daemon  60
set logfile syslog facility log_daemon
set mailserver smtp.gmail.com port 587 username "xxx@gmail.com" password "xxxx" using tlsv1 with timeout 30 seconds
set mail-format {
   from: xxxxxx@gmail.com
   subject: $SERVICE el $DATE
   message:
 
            Monit: $ACTION $SERVICE
	    Fecha: $DATE
	    Descripción: $DESCRIPTION.

           	SERVIDOR $HOST
           Powered by: monit
}
set alert xxxx@gmail.com only on { action
                      checksum
                      content
                      data
                      exec
                      gid
                      icmp
                      invalid
                      fsflags
                      nonexist
                      permission
                      size
                      timeout
                      timestamp }



check process sshd with pidfile /var/run/sshd.pid
   start program  "/etc/init.d/ssh start"
   stop program  "/etc/init.d/ssh stop"
   if failed port 22 protocol ssh then restart
   if 5 restarts within 5 cycles then timeout

check process postfix with pidfile /var/spool/postfix/pid/master.pid
   group mail
   start program = "/etc/init.d/postfix start"
   stop  program = "/etc/init.d/postfix stop"
   if failed port 25 protocol smtp then restart
   if 5 restarts within 5 cycles then timeout


# amavis
check process amavisd with pidfile /var/run/amavis/amavisd.pid
   group mail
   start program = "/etc/init.d/amavis start"
   stop  program = "/etc/init.d/amavis stop"
   if failed port 10024 protocol smtp then restart
   if 5 restarts within 5 cycles then timeout
   depends on amavisd_bin
   depends on amavisd_rc

check file amavisd_bin with path  /usr/sbin/amavisd-new
   group mail
   if failed checksum then unmonitor
   if failed permission 755 then unmonitor
   if failed uid root then unmonitor
   if failed gid root then unmonitor

check file amavisd_rc with path /etc/init.d/amavis
   group mail
   if failed checksum then unmonitor
   if failed permission 755 then unmonitor
   if failed uid root then unmonitor
   if failed gid root then unmonitor

# Apache2
check process apache with pidfile /var/run/apache2.pid
   group www
   start program = "/etc/init.d/apache2 start"
   stop program  = "/etc/init.d/apache2 stop"
   if failed port 80 protocol http then restart
   if cpu is greater than 60% for 2 cycles then alert
   if cpu > 80% for 5 cycles then restart
   if totalmem > 1500 MB for 5 cycles then restart
   if children > 512 then restart
   if loadavg(5min) greater than 10 for 8 cycles then stop
   if 3 restarts within 5 cycles then timeout

# Courier_authdaemon
check process authdaemon with pidfile /var/run/courier/authdaemon/pid
   group services
   start program = "/etc/init.d/courier-authdaemon start"
   stop  program = "/etc/init.d/courier-authdaemon stop"
   if 5 restarts within 5 cycles then timeout

# Cron
check process cron with pidfile /var/run/crond.pid
   start program = "/etc/init.d/cron start"
   stop  program = "/etc/init.d/cron stop"
   group system
   depends cron_init, cron_bin

check file cron_init with path /etc/init.d/cron
   group system

check file cron_bin with path /usr/sbin/cron
   group system

# fail2ban
check process fail2ban with pidfile /var/run/fail2ban/fail2ban.pid
   group services
   start program = "/etc/init.d/fail2ban start"
   stop  program = "/etc/init.d/fail2ban stop"
   if 5 restarts within 5 cycles then timeout

# Courier_imapd
check process imap with pidfile /var/run/courier/imapd.pid
   group mail
   start program = "/etc/init.d/courier-imap start"
   stop  program = "/etc/init.d/courier-imap stop"
   if failed port 143 then restart
   if 5 restarts within 5 cycles then timeout

# Courier_immapd-ssl
check process imapd-ssl with pidfile /var/run/courier/imapd-ssl.pid
   group mail
   start program = "/etc/init.d/courier-imap-ssl start"
   stop  program = "/etc/init.d/courier-imap-ssl stop"
   if failed port 143 then restart
   if 5 restarts within 5 cycles then timeout

# Munin-node
check process munin-node with pidfile /var/run/munin/munin-node.pid
   group services
   start program = "/etc/init.d/munin-node start"
   stop  program = "/etc/init.d/munin-node stop"
   if 5 restarts within 5 cycles then timeout

# Courier_pop3d
check process pop3 with pidfile /var/run/courier/pop3d.pid
   group mail
   start program = "/etc/init.d/courier-pop start"
   stop  program = "/etc/init.d/courier-pop stop"
   if failed port 110 then restart
   if 5 restarts within 5 cycles then timeout

# Courier_pop3-ssl
check process pop3-ssl with pidfile /var/run/courier/pop3d-ssl.pid
   group mail
   start program = "/etc/init.d/courier-pop-ssl start"
   stop  program = "/etc/init.d/courier-pop-ssl stop"
   if failed port 995 then restart
   if 5 restarts within 5 cycles then timeout

#PureFTPd
check process pure-ftpd with pidfile /var/run/pure-ftpd/pure-ftpd.pid
   start program  "/etc/init.d/pure-ftpd-mysql start"
   stop program  "/etc/init.d/pure-ftpd-mysql stop"
   if failed host 127.0.0.1 port 21 then restart
   if 5 restarts within 5 cycles then timeout

# Spamassassin
check process spamd with pidfile /var/run/spamd.pid
   group mail
   start program = "/etc/init.d/spamassassin start"
   stop  program = "/etc/init.d/spamassassin stop"
   if 5 restarts within 5 cycles then timeout
   if cpu usage > 99% for 5 cycles then alert
   if mem usage > 99% for 5 cycles then alert

check file spamd_bin with path /usr/sbin/spamd
   group mail
   if failed checksum then unmonitor
   if failed permission 755 then unmonitor
   if failed uid root then unmonitor
   if failed gid root then unmonitor

 check file spamd_rc with path /etc/init.d/spamassassin
   group mail
   if failed checksum then unmonitor
   if failed permission 755 then unmonitor
   if failed uid root then unmonitor
   if failed gid root then unmonitor

# Syslog-ng
check process syslogd with pidfile /var/run/syslog-ng.pid
   start program = "/etc/init.d/syslog-ng  start"
   stop program = "/etc/init.d/syslog-ng  stop"
   if 5 restarts within 5 cycles then timeout
   check file syslogd_file with path /var/log/syslog

check process postgresql with pidfile /var/run/postgresql/8.4-main.pid
    group database
    start program = "/etc/init.d/postgresql start"
    stop  program = "/etc/init.d/postgresql stop"
 if failed host localhost port 5432 protocol pgsql then restart
 if failed host localhost port 5432 protocol pgsql then alert
 if 5 restarts within 5 cycles then timeout


check process mysql with pidfile /var/lib/mysql/virt318.pid
   group database
   start program = "/etc/init.d/mysql start"
   stop program = "/etc/init.d/mysql stop"
   if failed host 127.0.0.1 port 3306 protocol mysql then restart
   if 5 restarts within 5 cycles then timeout

# Clamd
check process clamd with pidfile /var/run/clamav/clamd.pid
   group virus
   start program = "/etc/init.d/clamav-daemon start"
   stop  program = "/etc/init.d/clamav-daemon stop"
   if failed unixsocket /var/run/clamav/clamd.ctl then restart
   if 5 restarts within 5 cycles then timeout
   depends on clamavd_bin
   depends on clamavd_rc

check file clamavd_bin with path /usr/sbin/clamd
   group virus
   if failed checksum then unmonitor
   if failed permission 755 then unmonitor
   if failed uid root then unmonitor
   if failed gid root then unmonitor

check file clamavd_rc with path /etc/init.d/clamav-daemon
   group virus
   if failed checksum then unmonitor
   if failed permission 755 then unmonitor
   if failed uid root then unmonitor
   if failed gid root then unmonitor

Thats perfect!!!!