gilfanovrandClaude Opus 5.5
d1269162e7
- servers/rpi.md: новая домашняя Raspberry Pi 4 (Trixie, cloud-init), HDD 4 ТБ, грабли с питанием двух HDD от USB - stacks/rpi-backup: rclone sync с вечным архивом версий, еженедельная сверка хэшей, smartd, пуш SMART и статуса бэкапов - fr1: pushgateway (127.0.0.1:9091), приём по SSH через forced command ~/bin/pushgw-ingest, алерты группы rpi Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
120 lines
4.0 KiB
YAML
120 lines
4.0 KiB
YAML
name: monitoring
|
|
|
|
services:
|
|
prometheus:
|
|
image: prom/prometheus:latest
|
|
container_name: prometheus
|
|
restart: unless-stopped
|
|
command:
|
|
- '--config.file=/etc/prometheus/prometheus.yml'
|
|
- '--storage.tsdb.path=/prometheus'
|
|
- '--storage.tsdb.retention.time=90d'
|
|
- '--web.enable-lifecycle'
|
|
volumes:
|
|
- ./prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
|
|
- ./prometheus/targets:/etc/prometheus/targets:ro
|
|
- ./prometheus/rules:/etc/prometheus/rules:ro
|
|
- prometheus_data:/prometheus
|
|
extra_hosts:
|
|
- "host.docker.internal:host-gateway"
|
|
ports:
|
|
- '127.0.0.1:9090:9090'
|
|
networks: [monitoring]
|
|
|
|
alertmanager:
|
|
image: prom/alertmanager:latest
|
|
container_name: alertmanager
|
|
restart: unless-stopped
|
|
volumes:
|
|
- ./alertmanager/alertmanager.yml:/etc/alertmanager/alertmanager.yml:ro
|
|
- ./alertmanager/telegram_token:/etc/alertmanager/telegram_token:ro
|
|
- alertmanager_data:/alertmanager
|
|
ports:
|
|
- '127.0.0.1:9093:9093'
|
|
networks: [monitoring]
|
|
|
|
# pushgateway: метрики от хостов за NAT (rpi), которые не скрейпнуть.
|
|
# Порт только на 127.0.0.1 — пуш идёт по SSH через forced command ~/bin/pushgw-ingest
|
|
# (см. servers/fr1.md), наружу не торчит. Персистентность — чтобы рестарт не обнулял алерты.
|
|
pushgateway:
|
|
image: prom/pushgateway:latest
|
|
container_name: pushgateway
|
|
restart: unless-stopped
|
|
command:
|
|
- '--persistence.file=/data/metrics'
|
|
- '--persistence.interval=1m'
|
|
volumes:
|
|
- pushgateway_data:/data
|
|
ports:
|
|
- '127.0.0.1:9091:9091'
|
|
networks: [monitoring]
|
|
|
|
grafana:
|
|
image: grafana/grafana:latest
|
|
container_name: grafana
|
|
restart: unless-stopped
|
|
environment:
|
|
GF_SECURITY_ADMIN_USER: admin
|
|
GF_SECURITY_ADMIN_PASSWORD: ${GF_ADMIN_PASSWORD:-admin}
|
|
GF_USERS_ALLOW_SIGN_UP: 'false'
|
|
GF_SERVER_ROOT_URL: https://mon.ruzzy.dev
|
|
volumes:
|
|
- grafana_data:/var/lib/grafana
|
|
- ./grafana/provisioning:/etc/grafana/provisioning:ro
|
|
ports:
|
|
- '127.0.0.1:3000:3000'
|
|
networks: [monitoring]
|
|
depends_on: [prometheus]
|
|
|
|
# node-exporter в host-network: видит реальные интерфейсы хоста (eth0, wg0, tun…).
|
|
# Слушает host:9100; доступ ограничен ufw (только docker-сети). Скрейпится через host.docker.internal.
|
|
node-exporter:
|
|
image: prom/node-exporter:latest
|
|
container_name: node-exporter
|
|
network_mode: host
|
|
pid: host
|
|
restart: unless-stopped
|
|
command:
|
|
- '--path.procfs=/host/proc'
|
|
- '--path.sysfs=/host/sys'
|
|
- '--path.rootfs=/rootfs'
|
|
- '--collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc)($$|/)'
|
|
volumes:
|
|
- /proc:/host/proc:ro
|
|
- /sys:/host/sys:ro
|
|
- /:/rootfs:ro
|
|
|
|
cadvisor:
|
|
image: gcr.io/cadvisor/cadvisor:latest
|
|
container_name: cadvisor
|
|
restart: unless-stopped
|
|
# init: true — pid1-reaper, иначе healthcheck-wget копятся зомбями (образ без init)
|
|
init: true
|
|
# Дефолт cadvisor: housekeeping 1s + все метрики → ~2 ядра на 8-ядерном хабе.
|
|
# Реже опрос + только docker-контейнеры + отключены дорогие/ненужные метрики.
|
|
command:
|
|
- '--housekeeping_interval=30s'
|
|
- '--docker_only=true'
|
|
- '--store_container_labels=false'
|
|
- '--disable_metrics=percpu,disk,diskIO,tcp,udp,advtcp,sched,process,hugetlb,referenced_memory,cpu_topology,resctrl'
|
|
privileged: true
|
|
devices:
|
|
- /dev/kmsg
|
|
volumes:
|
|
- /:/rootfs:ro
|
|
- /var/run:/var/run:ro
|
|
- /sys:/sys:ro
|
|
- /var/lib/docker/:/var/lib/docker:ro
|
|
- /dev/disk/:/dev/disk:ro
|
|
networks: [monitoring]
|
|
|
|
volumes:
|
|
pushgateway_data:
|
|
prometheus_data:
|
|
grafana_data:
|
|
alertmanager_data:
|
|
|
|
networks:
|
|
monitoring:
|
|
driver: bridge
|