Sergei Poljanski
0cc3e1dece
datacenterbingo gets a public page showing whether each datacenter's network answers. The probing lives here, next to the schema and the admin, since the public site only has a read-only role. bin/monitor runs as a second container from the same image. Once a minute it opens one TCP connection to every active target (a handshake or a refusal both count as answered) and folds the results into 5-minute rows per datacenter, plus a per-bucket row for control hosts in Russia, so a lost vantage point isn't mistaken for dark sites. Rows are kept 30 days. Targets are managed at /admin/bingo/monitor; only hosts a public source ties to that one site belong there. Migration 017 also grants the new tables to the bingo role, so the public site can read them without a storage redeploy. Assisted-by: Claude:opus-5-5
45 lines
1.4 KiB
YAML
45 lines
1.4 KiB
YAML
services:
|
|
asxpio:
|
|
# Image will be dynamically updated during deployment
|
|
# Format: registry.example.com/user/asxpio:sha_tag
|
|
build: .
|
|
image: asxpio:latest
|
|
container_name: asxpio
|
|
restart: unless-stopped
|
|
env_file: .env
|
|
networks:
|
|
- traefik
|
|
- storage
|
|
labels:
|
|
- "traefik.enable=true"
|
|
- "traefik.http.routers.asxpio.rule=Host(`asxp.io`) || Host(`www.asxp.io`)"
|
|
- "traefik.http.routers.asxpio.entrypoints=websecure"
|
|
- "traefik.http.routers.asxpio.tls=true"
|
|
- "traefik.http.routers.asxpio.tls.certresolver=letsencrypt"
|
|
- "traefik.http.routers.asxpio.service=asxpio"
|
|
- "traefik.http.services.asxpio.loadbalancer.server.port=3000"
|
|
|
|
# Reachability worker for datacenterbingo's status page (bin/monitor).
|
|
# Same image; the deploy's sed sets both image lines.
|
|
asxpio-monitor:
|
|
image: asxpio:latest
|
|
container_name: asxpio-monitor
|
|
restart: unless-stopped
|
|
env_file: .env
|
|
command: ["ruby", "bin/monitor"]
|
|
networks:
|
|
- storage # postgres; not internal, so probes reach the internet
|
|
mem_limit: 256m
|
|
healthcheck:
|
|
# The worker touches its heartbeat after every round (60 s).
|
|
test: ["CMD", "ruby", "-e", "exit(Time.now - File.mtime('/tmp/monitor.heartbeat') < 300 ? 0 : 1)"]
|
|
interval: 60s
|
|
timeout: 10s
|
|
start_period: 120s
|
|
retries: 3
|
|
|
|
networks:
|
|
traefik:
|
|
external: true
|
|
storage:
|
|
external: true
|