Nagios

# Arquitectura de Nagios:
#
# ┌─────────────────────────────────────────────────┐
# │              NAGIOS CORE                        │
# │  Scheduler ──► Plugins ──► Estado ──► Alerta   │
# └─────────────────────────────────────────────────┘
#         │                         │
#   ┌─────▼──────┐         ┌────────▼────────┐
#   │  Chequeos  │         │  Notificaciones  │
#   │  Locales   │         │  Email/Slack/SMS │
#   └────────────┘         └─────────────────┘
#         │
#   ┌─────▼──────┐
#   │    NRPE    │  ◄── Plugin daemon en hosts remotos
#   │  (remoto)  │
#   └────────────┘

# Flujo de un chequeo:
# 1. Scheduler decide cuándo chequear
# 2. Ejecuta el plugin correspondiente
# 3. Plugin devuelve 0(OK), 1(WARN), 2(CRIT), 3(UNKNOWN)
# 4. Nagios actualiza estado en BD
# 5. Si cambió a estado problemático → envía notificación
# 6. Si se recupera → notificación de recuperación

# Ver plugins instalados:
ls /usr/local/nagios/libexec/
# check_http  check_ping  check_ssh  check_disk  check_load...

# ── DEPENDENCIAS ──────────────────────────────────────
sudo apt update && sudo apt upgrade -y
sudo apt install -y autoconf gcc libc6 make wget unzip apache2 \
  php libapache2-mod-php libgd-dev openssl libssl-dev \
  build-essential checkinstall libperl-dev libnet-snmp-perl

# ── USUARIO Y GRUPO ────────────────────────────────────
sudo useradd nagios
sudo groupadd nagcmd
sudo usermod -aG nagcmd nagios
sudo usermod -aG nagcmd www-data

# ── DESCARGAR Y COMPILAR NAGIOS CORE ──────────────────
cd /tmp
wget -O nagios.tar.gz \
  https://github.com/NagiosEnterprises/nagioscore/archive/nagios-4.4.14.tar.gz
tar xzf nagios.tar.gz && cd nagioscore-nagios-4.4.14/

sudo ./configure --with-command-group=nagcmd
sudo make all
sudo make install           # Binarios
sudo make install-init      # Scripts systemd
sudo make install-config    # Configs por defecto
sudo make install-commandmode
sudo make install-webconf   # Config Apache

# ── USUARIO WEB ────────────────────────────────────────
sudo htpasswd -c /usr/local/nagios/etc/htpasswd.users nagiosadmin

# ── APACHE ─────────────────────────────────────────────
sudo a2enmod rewrite cgi
sudo systemctl restart apache2

# ── INSTALAR PLUGINS ───────────────────────────────────
cd /tmp
wget -O plugins.tar.gz \
  https://github.com/nagios-plugins/nagios-plugins/archive/release-2.4.6.tar.gz
tar xzf plugins.tar.gz && cd nagios-plugins-release-2.4.6/
sudo ./tools/setup
sudo ./configure --with-nagios-user=nagios --with-nagios-group=nagios
sudo make && sudo make install

# ── INICIAR NAGIOS ─────────────────────────────────────
sudo systemctl enable nagios
sudo systemctl start nagios

# Verificar configuración (debe decir 0 Errors):
sudo /usr/local/nagios/bin/nagios -v /usr/local/nagios/etc/nagios.cfg

# Acceder: http://TU_IP/nagios  |  Usuario: nagiosadmin

# ── EN EL SERVIDOR REMOTO: Instalar NRPE ─────────────
sudo apt install nagios-nrpe-server nagios-plugins-basic nagios-plugins-standard

sudo nano /etc/nagios/nrpe.cfg
# Cambiar: allowed_hosts=127.0.0.1,192.168.1.10  (IP de tu Nagios server)

# Comandos disponibles en NRPE:
command[check_users]=/usr/lib/nagios/plugins/check_users -w 5 -c 10
command[check_load]=/usr/lib/nagios/plugins/check_load -w 15,10,5 -c 30,25,20
command[check_disk]=/usr/lib/nagios/plugins/check_disk -w 20% -c 10% -p /
command[check_mem]=/usr/lib/nagios/plugins/check_memory -w 80 -c 95
command[check_procs]=/usr/lib/nagios/plugins/check_procs -w 150 -c 200

sudo systemctl restart nagios-nrpe-server

# ── EN EL SERVIDOR NAGIOS: Configurar el host ─────────
sudo nano /usr/local/nagios/etc/objects/servers/web01.cfg

define host {
    use                 linux-server
    host_name           web-server-01
    alias               Servidor Web Principal
    address             192.168.1.100
    max_check_attempts  3
    check_period        24x7
    notification_interval 60
    notification_period 24x7
    contacts            nagiosadmin
}

define service {
    use                 generic-service
    host_name           web-server-01
    service_description HTTP
    check_command       check_http
    check_interval      5
    notifications_enabled 1
}

define service {
    use                 generic-service
    host_name           web-server-01
    service_description Carga CPU
    check_command       check_nrpe!check_load
}

define service {
    use                 generic-service
    host_name           web-server-01
    service_description Disco /
    check_command       check_nrpe!check_disk
}

# Verificar sin errores y recargar:
sudo /usr/local/nagios/bin/nagios -v /usr/local/nagios/etc/nagios.cfg
sudo systemctl reload nagios

# ── CONTACTO CON EMAIL ────────────────────────────────
sudo nano /usr/local/nagios/etc/objects/contacts.cfg

define contact {
    contact_name            nagiosadmin
    use                     generic-contact
    alias                   Administrador Nagios
    email                   admin@tuempresa.com
    service_notification_options    w,u,c,r,f,s
    host_notification_options       d,u,r,f,s
    service_notification_commands   notify-service-by-email
    host_notification_commands      notify-host-by-email
    service_notification_period     24x7
    host_notification_period        24x7
}

define contactgroup {
    contactgroup_name   sysadmins
    alias               Administradores de Sistema
    members             nagiosadmin,admin2,oncall
}

# ── NOTIFICACIÓN POR SLACK ─────────────────────────────
cat > /usr/local/nagios/libexec/notify-slack.sh << 'SCRIPT'
#!/bin/bash
WEBHOOK="https://hooks.slack.com/services/TU/WEBHOOK/AQUI"
COLOR="danger"
[ "$NAGIOS_SERVICESTATE" = "OK" ] && COLOR="good"
[ "$NAGIOS_SERVICESTATE" = "WARNING" ] && COLOR="warning"
curl -s -X POST $WEBHOOK -H 'Content-type: application/json' -d "{
  "attachments": [{"color":"$COLOR",
  "title":"$NAGIOS_SERVICESTATE - $NAGIOS_HOSTNAME",
  "text":"Servicio: $NAGIOS_SERVICEDESC\n$NAGIOS_SERVICEOUTPUT"}]}"
SCRIPT
chmod +x /usr/local/nagios/libexec/notify-slack.sh

# Añadir en commands.cfg:
define command {
    command_name    notify-service-by-slack
    command_line    /usr/local/nagios/libexec/notify-slack.sh
}

# ── ESCALADO DE ALERTAS ────────────────────────────────
# Si problema persiste 60+ min → escalar al gerente
define serviceescalation {
    host_name               web-server-01
    service_description     HTTP
    first_notification      4       # 4ta notificación en adelante
    last_notification       0       # 0 = sin límite
    notification_interval   30
    contact_groups          management
}

# ── MANTENIMIENTO PROGRAMADO ───────────────────────────
# Evitar alertas durante actualizaciones:
echo "[$(date +%s)] SCHEDULE_HOST_DOWNTIME;web-server-01;$(date +%s);$(date -d '+2 hours' +%s);1;0;7200;nagiosadmin;Mantenimiento" \
  > /usr/local/nagios/var/rw/nagios.cmd