Nagios Monitoring

Nagios, IT altyapısının 7/24 izlenmesini sağlayan açık kaynak monitoring platformudur.

Nagios Kurulumu

# Bağımlılıklar
sudo dnf install -y httpd php php-cli gcc glibc glibc-common gd gd-devel net-snmp

Nagios kullanıcısı
sudo useradd nagios
sudo groupadd nagcmd
sudo usermod -a -G nagcmd nagios
sudo usermod -a -G nagcmd apache
Nagios Core indirme ve kurulum
cd /tmp
wget https://assets.nagios.com/downloads/nagioscore/releases/nagios-4.4.13.tar.gz
tar xzf nagios-4.4.13.tar.gz
cd nagios-4.4.13
./configure --with-command-group=nagcmd
make all
sudo make install
sudo make install-init
sudo make install-commandmode
sudo make install-config
sudo make install-webconf
Admin kullanıcısı
sudo htpasswd -c /usr/local/nagios/etc/htpasswd.users nagiosadmin
Servisleri başlat
sudo systemctl enable --now nagios
sudo systemctl enable --now httpd

Nagios Plugins

# Plugin kurulumu
cd /tmp
wget https://nagios-plugins.org/download/nagios-plugins-2.4.6.tar.gz
tar xzf nagios-plugins-2.4.6.tar.gz
cd nagios-plugins-2.4.6

./configure --with-nagios-user=nagios --with-nagios-group=nagios
make
sudo make install

Host Tanımı

# /usr/local/nagios/etc/objects/hosts.cfg

define host {
    use                     linux-server
    host_name               webserver01
    alias                   Web Server 01
    address                 192.168.1.10
    max_check_attempts      5
    check_period            24x7
    notification_interval   30
    notification_period     24x7
}
define hostgroup {
    hostgroup_name  linux-servers
    alias           Linux Servers
    members         webserver01, webserver02
}

Service Tanımları

define service {
    use                     generic-service
    host_name               webserver01
    service_description     SSH
    check_command           check_ssh
}

define service {
    use                     generic-service
    host_name               webserver01
    service_description     HTTP
    check_command           check_http
}
define service {
    use                     generic-service
    host_name               webserver01
    service_description     Disk Usage
    check_command           check_nrpe!check_disk
}
define service {
    use                     generic-service
    host_name               webserver01
    service_description     CPU Load
    check_command           check_nrpe!check_load
}

NRPE Agent Kurulumu (Client)

# Client sunucuda
sudo dnf install -y nrpe nagios-plugins-all

/etc/nagios/nrpe.cfg
allowed_hosts=127.0.0.1,192.168.1.5
command[check_load]=/usr/lib64/nagios/plugins/check_load -w 15,10,5 -c 30,25,20
command[check_disk]=/usr/lib64/nagios/plugins/check_disk -w 20% -c 10% -p /
command[check_mem]=/usr/lib64/nagios/plugins/check_mem -w 80 -c 90
sudo systemctl enable --now nrpe

Sonuç

Nagios ile proaktif monitoring yapılarak sorunlar önceden tespit edilebilir. Email/SMS alarm entegrasyonu kritiktir.