Monit — это легковесная система мониторинга серверов, имеющая открытый исходный код. Monit устанавливается на сервер и обеспечивает возможность отправки уведомлений в случае обнаружения проблем. Кроме того, Monit может автономно выполнять определенное действие в качестве реакции на заданные события.

$ sudo yum install monit

Расскоментируем такие строки:

$ sudo nano /etc/monitrc
set mailserver localhost
set mail-format { from: monit@domen.com }
set alert admin@domen.com
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'
include /etc/monit.d/*.conf

Проверяем синтаксис:

$ sudo monit -t

Запускаем:

$ sudo systemctl start monit
$ sudo systemctl status monit
$ sudo systemctl enable monit
$ monit status

Создаем конфигурации мониторинга

cd /etc/monit.d/

$ sudo nano filesystem.conf
check device root with path /dev/mapper/centos-home
    if space usage > 85% for 5 times within 15 cycles then alert
    if inode usage > 85% then alert
    check device home with path /dev/sdb
    if space usage > 85% for 5 times within 15 cycles then alert
    if inode usage > 85% then alert

$ sudo nano mariadb.conf
# Monitor MariaDB
check process mysql with pidfile /var/run/mariadb/mariadb.pid
    group database
    start program = "/usr/bin/systemctl start mariadb"
    stop program = "/usr/bin/systemctl stop mariadb"
    #if failed host 127.0.0.1 port 3306 then restart
    #if 5 restarts within 5 cycles then timeout

$ sudo nano system.conf
check system host.domen.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

$ sudo nano nginx.conf
check process nginx with pidfile /var/run/nginx.pid
    start program = "/usr/sbin/nginx start"
    stop program = "/usr/sbin/nginx stop"

$ sudo nano postfix.conf
# Monitor postfix mailserver
check process postfix with pidfile /var/spool/postfix/pid/master.pid
    group mail
    start program = "/usr/bin/systemctl start postfix"
    stop program = "/usr/bin/systemctl stop postfix"
    if failed port 25 protocol smtp then restart
    if 5 restarts within 5 cycles then timeout

$ sudo nano proftpd.conf
# Monitor the Proftpd service
check process proftpd with pidfile /var/run/proftpd/proftpd.pid
    start program = "/usr/bin/systemctl start proftpd"
    stop program = "/usr/bin/systemctl stop proftpd"
    #if failed port 21 protocol ftp then restart
    #if 5 restarts within 5 cycles then timeout