Sergei Poljanski
2359370e24
All checks were successful
deploy / ansible (push) Successful in 7m59s
Each SSH login from Ansible and CI deploys creates its own session-N.scope unit. As a journal label that made 3400+ streams and Loki rejected new ones with 429, dropping container logs. Map them all to session.scope. cAdvisor's image healthcheck probes localhost:8080, but it listens on the VPC address on 9180, so both containers showed unhealthy. Assisted-by: Claude:opus-5-5
72 lines
2.3 KiB
Django/Jinja
72 lines
2.3 KiB
Django/Jinja
# Managed by Ansible (role monitoring_agent).
|
|
services:
|
|
node-exporter:
|
|
image: prom/node-exporter:{{ monitoring_node_exporter_version }}
|
|
container_name: node-exporter
|
|
command:
|
|
- --path.rootfs=/host
|
|
- --web.listen-address={{ vpc_ip }}:{{ monitoring_node_exporter_port }}
|
|
- --collector.textfile.directory=/textfile
|
|
- --collector.filesystem.mount-points-exclude=^/(dev|proc|run|sys|var/lib/docker/.+)($|/)
|
|
network_mode: host
|
|
pid: host
|
|
volumes:
|
|
- /:/host:ro,rslave
|
|
- {{ monitoring_textfile_dir }}:/textfile:ro
|
|
restart: unless-stopped
|
|
mem_limit: 64m
|
|
|
|
cadvisor:
|
|
image: ghcr.io/google/cadvisor:{{ monitoring_cadvisor_version }}
|
|
container_name: cadvisor
|
|
command:
|
|
- --listen_ip={{ vpc_ip }}
|
|
- --port={{ monitoring_cadvisor_port }}
|
|
- --docker_only=true
|
|
- --housekeeping_interval=30s
|
|
- --store_container_labels=false
|
|
- --whitelisted_container_labels=com.docker.compose.project,com.docker.compose.service
|
|
- --disable_metrics=percpu,sched,tcp,udp,hugetlb,referenced_memory,cpu_topology,resctrl,advtcp,process
|
|
network_mode: host
|
|
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
|
|
healthcheck:
|
|
# The image probes localhost:8080; we listen on the VPC address only.
|
|
test: ["CMD", "wget", "-q", "--tries=1", "--spider", "http://{{ vpc_ip }}:{{ monitoring_cadvisor_port }}/healthz"]
|
|
interval: 30s
|
|
timeout: 3s
|
|
retries: 3
|
|
restart: unless-stopped
|
|
mem_limit: 192m
|
|
|
|
alloy:
|
|
image: grafana/alloy:{{ monitoring_alloy_version }}
|
|
container_name: alloy
|
|
command:
|
|
- run
|
|
- --server.http.listen-addr={{ vpc_ip }}:12345
|
|
- --storage.path=/var/lib/alloy/data
|
|
- /etc/alloy/config.alloy
|
|
network_mode: host
|
|
volumes:
|
|
- ./config.alloy:/etc/alloy/config.alloy:ro
|
|
- /var/run/docker.sock:/var/run/docker.sock:ro
|
|
- /var/log/journal:/var/log/journal:ro
|
|
- /run/log/journal:/run/log/journal:ro
|
|
- /etc/machine-id:/etc/machine-id:ro
|
|
{% if inventory_hostname == 'asxpio-ops' %}
|
|
- /opt/traefik/logs:/traefik-logs:ro
|
|
{% endif %}
|
|
- alloy-data:/var/lib/alloy/data
|
|
restart: unless-stopped
|
|
mem_limit: 256m
|
|
|
|
volumes:
|
|
alloy-data:
|