prometheus-monitoring/docker-compose.yml

160 lines
4.0 KiB
YAML

networks:
grafana-network:
driver: bridge
ipam:
config:
- subnet: 192.168.100.0/24
volumes:
prometheus_data: {}
grafana_data: {}
services:
grafana:
image: grafana/grafana:11.2.0
container_name: grafana
volumes:
- grafana_data:/var/lib/grafana
- ./grafana/provisioning:/etc/grafana/provisioning
environment:
- GF_SECURITY_ADMIN_USER=${ADMIN_USER}
- GF_SECURITY_ADMIN_PASSWORD=${ADMIN_PASSWORD}
- GF_USERS_ALLOW_SIGN_UP=false
restart: unless-stopped
ports:
- 3000:3000
networks:
grafana-network:
ipv4_address: 192.168.100.10
labels:
org.label-schema.group: "monitoring"
healthcheck:
test: ["CMD", "curl", "-f", "http://localhost:3000/api/health"]
interval: 30s
timeout: 5s
retries: 3
prometheus:
image: prom/prometheus:v2.54.1
container_name: prometheus
volumes:
- ./prometheus:/etc/prometheus
- prometheus_data:/prometheus
command:
- '--config.file=/etc/prometheus/prometheus.yml'
- '--storage.tsdb.path=/prometheus'
- '--web.console.libraries=/etc/prometheus/console_libraries'
- '--web.console.templates=/etc/prometheus/consoles'
- '--storage.tsdb.retention.time=200h'
- '--web.enable-lifecycle'
restart: unless-stopped
expose:
- 9090
networks:
- grafana-network
labels:
org.label-schema.group: "monitoring"
healthcheck:
test: ["CMD", "wget", "http://localhost:9090"]
interval: 10s
timeout: 15s
retries: 10
start_period: 40s
nodeexporter:
image: prom/node-exporter:v1.8.2
container_name: nodeexporter
volumes:
- /proc:/host/proc:ro
- /sys:/host/sys:ro
- /:/rootfs:ro
command:
- '--path.procfs=/host/proc'
- '--path.rootfs=/rootfs'
- '--path.sysfs=/host/sys'
- '--collector.filesystem.ignored-mount-points=^/(sys|proc|dev|host|etc)($$|/)'
restart: unless-stopped
expose:
- 9100
networks:
- grafana-network
labels:
org.label-schema.group: "monitoring"
cadvisor:
image: gcr.io/cadvisor/cadvisor
container_name: cadvisor
volumes:
- /:/rootfs:ro
- /var/run:/var/run:rw
- /sys:/sys:ro
- /var/lib/docker:/var/lib/docker:ro
- /cgroup:/cgroup:ro #doesn't work on MacOS only for Linux
restart: unless-stopped
expose:
- 8080
networks:
- grafana-network
labels:
org.label-schema.group: "monitoring"
loki:
image: grafana/loki:latest
container_name: loki
ports:
- '3100:3100'
volumes:
- ./loki/config:/etc/loki
- ./loki/cert:/etc/loki/cert
- /etc/localtime:/etc/localtime:ro
- /etc/timezone:/etc/timezone:ro
command: -config.file=/etc/loki/config.yml -config.expand-env=true
networks:
- grafana-network
healthcheck:
test: wget --quiet --tries=1 --output-document=- http://localhost:3100/ready | grep -q -w ready || exit 1
start_period: 20s
interval: 10s
timeout: 1s
retries: 12 # try for 2 minutes
alertmanager:
image: prom/alertmanager:v0.20.0
container_name: alertmanager
volumes:
- ./alertmanager:/etc/alertmanager
command:
- '--config.file=/etc/alertmanager/alertmanager.yml'
- '--storage.path=/alertmanager'
restart: unless-stopped
expose:
- 9093
networks:
- grafana-network
labels:
org.label-schema.group: "monitoring"
healthcheck:
test: ["CMD", "curl", "-f", "http://localhost:9093/-/ready"]
interval: 30s
timeout: 5s
retries: 3
pushgateway:
image: prom/pushgateway:v1.2.0
container_name: pushgateway
restart: unless-stopped
expose:
- 9091
networks:
- grafana-network
labels:
org.label-schema.group: "monitoring"
healthcheck:
test: ["CMD", "curl", "-f", "http://localhost:9091/metrics"]
interval: 30s
timeout: 5s
retries: 3