Образовательный проект «SnakeProject» Михаила Козлова

⇒ FreeBSD and Nix ⇐

CISCO

Voice(Asterisk\Cisco)

Microsoft

Powershell

Python

SQL\T-SQL

1С

Общая

WEB Разработка

ORACLE SQL \ JAVA

Мото

Стрельба, пневматика, оружие

Саморазвитие и психология

Prometheus + alertmanager

Prometheus + alertmanager

Пример установки и простенькой настройки оповещения по почте через alertmanager

Правила, интересующие для алертов

prometheus_rules.yml:
groups: - name: custom_rules rules: - record: Mem_Free_Percent expr: 100 - (100 * node_memory_MemFree_bytes / node_memory_MemTotal_bytes) - record: Disk_Free_Percent expr: 100 * node_filesystem_free_bytes{mountpoint="/"} / node_filesystem_size_bytes{mountpoint="/"} - name: alert_rules rules: - alert: InstanceDown expr: up == 0 for: 1m labels: severity: critical annotations: summary: 'Instance {{ $labels.instance }} down' description: '{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 1 minute.' - alert: MemSpaceFree10Percent expr: Mem_Free_Percent <= 10 labels: severity: warning annotations: summary: 'Instance {{ $labels.instance }} has 10% or less Free memory space' description: '{{ $labels.instance }} has only {{ $value }}% or less free.' - alert: DiskSpaceFree10Percent expr: Disk_Free_Percent <= 10 labels: severity: warning annotations: summary: 'Instance {{ $labels.instance }} has 10% or less Free disk space' description: '{{ $labels.instance }} has only {{ $value }}% or less free.'

Впишем связь в основной конф. файл

prometheus.yml:
... rule_files: - "prometheus_rules.yml" ... scrape_configs: ... - job_name: 'alertmanager' static_configs: - targets: [localhost:9093] ...

./promtool check rules prometheus_rules.yml
systemctl daemon-reload
service prometheus restart
service prometheus status

Установим сам alertmanager

https://prometheus.io/download/#alertmanager

wget https://github.com/prometheus/alertmanager/releases/download/v0.27.0/alertmanager-0.27.0.linux-amd64.tar.gz
tar -xvf alertmanager-0.27.0.linux-amd64.tar.gz
cd alertmanager-0.27.0.linux-amd64

mkdir -p /usr/local/bin/alertmanager
cp -r . /usr/local/bin/alertmanager

/usr/local/bin/alertmanager/alertmanager.yml:
route: group_by: ['Alertname'] receiver: 'email' repeat_interval: 4h receivers: - name: 'email' email_configs: - send_resolved: true to: 'user_name@gmail.com' from: 'user_name@gmail.com' smarthost: smtp.gmail.com:587 auth_username: 'user_name@gmail.com' auth_identity: 'user_name@gmail.com' auth_password: 'user_name_password'

/usr/local/bin/alertmanager/amtool check-config /usr/local/bin/alertmanager/alertmanager.yml

/etc/systemd/system/alertmanager.service:
[Unit] Description=Alertmanager Service After=network.target [Service] Type=simple ExecStart=/usr/local/bin/alertmanager/alertmanager \ --config.file=/usr/local/bin/alertmanager/alertmanager.yml [Install] WantedBy=multi-user.target

systemctl daemon-reload
systemctl enable alertmanager
service alertmanager restart
service alertmanager status

Указываем связь

/usr/local/bin/prometheus/prometheus.yml:
... alerting: alertmanagers: - static_configs: - targets: # alertmanager:9093 - localhost:9093 ...

/usr/local/bin/prometheus/promtool check config /usr/local/bin/prometheus/prometheus.yml
service prometheus restart
service prometheus status

Комментарии пользователей