Add service health monitoring: postgres, node, cAdvisor exporters + dashboard

Exporters:
- postgres_exporter: DB connections, transactions, cache hit ratio, query stats
- node_exporter: host CPU, memory, disk, network
- cAdvisor: per-container CPU and memory usage

PostgreSQL:
- Enable pg_stat_statements for query-level performance tracking
- Track index scans vs sequential scans, cache hit ratio

Dashboard (service-health.json):
- DB: connections, size, transactions/s, slow queries, cache hit ratio, index usage
- Host: disk gauge, CPU, memory, network I/O, disk I/O
- BRouter: request latency p50/p95/p99, container CPU + memory
- All containers: CPU and memory comparison

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Ullrich Schäfer 2026-03-27 18:44:14 +01:00
parent f87aca6188
commit 424e692ee0
No known key found for this signature in database
GPG key ID: A32FF691A0F752D9
14 changed files with 326 additions and 12 deletions

View file

@ -78,12 +78,52 @@ services:
POSTGRES_DB: trails
volumes:
- pgdata:/var/lib/postgresql/data
command:
- "postgres"
- "-c"
- "shared_preload_libraries=pg_stat_statements"
- "-c"
- "pg_stat_statements.track=all"
healthcheck:
test: ["CMD-SHELL", "pg_isready -U trails"]
interval: 5s
timeout: 5s
retries: 5
postgres-exporter:
image: prometheuscommunity/postgres-exporter:latest
restart: unless-stopped
environment:
DATA_SOURCE_NAME: postgresql://trails:${POSTGRES_PASSWORD:-trails}@postgres:5432/trails?sslmode=disable
depends_on:
postgres:
condition: service_healthy
node-exporter:
image: prom/node-exporter:latest
restart: unless-stopped
pid: host
volumes:
- /proc:/host/proc:ro
- /sys:/host/sys:ro
- /:/rootfs:ro
command:
- "--path.procfs=/host/proc"
- "--path.sysfs=/host/sys"
- "--path.rootfs=/rootfs"
- "--collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc)($$|/)"
cadvisor:
image: gcr.io/cadvisor/cadvisor:latest
restart: unless-stopped
privileged: true
volumes:
- /:/rootfs:ro
- /var/run:/var/run:ro
- /sys:/sys:ro
- /var/lib/docker/:/var/lib/docker:ro
- /dev/disk/:/dev/disk:ro
prometheus:
image: prom/prometheus:latest
restart: unless-stopped