2d1e4aa98f
An offline trivy install crash-looped (server FATALs when it can't fetch the vuln DB), and on rootless docker the restart storm churned the shared network's port-forwarder until the WebUI's own published host port was torn down — the WebUI stayed healthy INSIDE its container but was unreachable from the host, with nothing detecting or healing it. Three fixes, in the house self-healing style (mirrors the network-drift trio): 1. Control-plane health checker wired into the existing task-processor idle poll (maybeRegenPoll), no new daemon. dockerHealthScan (read-only) detects daemon down, a WebUI running-but-host-port-unreachable (the port-forward corruption), and crash-looping containers. webuiSystemHealthCheck writes frontend/data/system/health_status.json + self-dispatches a heal — the user can't click a button on a dead WebUI, so the poll drives the fix. Frontend health-notifier surfaces a topbar badge + dashboard banner + details panel. 2. Failure cap, enforced centrally by dockerHealthHeal (task-gated): stops crash-loopers (removing the churn), restarts the WebUI to re-publish a lost port forward, and — only if that fails — recycles the rootless daemon and restarts the core container. Caps every app immediately, no template churn. 3. Trivy no longer crash-loops offline: the server runs in a shell retry-loop so the container stays Up and quietly retries on a backoff instead of exiting FATAL. Verified: container stays Up across repeated DB-download failures. Core WebUI compose gains restart: unless-stopped so it self-recovers after a reboot / daemon recycle instead of staying down. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Signed-off-by: librelad <librelad@digitalangels.vip>
60 lines
3.2 KiB
YAML
60 lines
3.2 KiB
YAML
|
|
|
|
networks:
|
|
DOCKER_NETWORK_DATA: #LIBREPORTAL|DOCKER_NETWORK_TAG|DOCKER_NETWORK_DATA
|
|
external: true
|
|
|
|
services:
|
|
libreportal-service: #LIBREPORTAL|SERVICE_TAG_1|libreportal-service
|
|
container_name: libreportal-service
|
|
build:
|
|
context: .
|
|
image: libreportal-service:latest
|
|
# The control plane self-recovers after a host reboot or a rootless-daemon
|
|
# recycle (the health-heal path). "no" would leave the WebUI down until
|
|
# someone started it by hand — exactly the outage this policy prevents.
|
|
restart: unless-stopped
|
|
user: "USER_DATA" #LIBREPORTAL|USER_TAG|USER_DATA
|
|
group_add:
|
|
- SOCKET_GID_DATA #LIBREPORTAL|SOCKET_GID_TAG|SOCKET_GID_DATA
|
|
ports:
|
|
- "PORTS_DATA_1" #LIBREPORTAL|PORTS_TAG_1|PORTS_DATA_1
|
|
volumes:
|
|
- ./frontend:/app/frontend
|
|
- ./backend/routes:/app/backend/routes
|
|
- ./backend/utils:/app/backend/utils
|
|
- ./backend/server.js:/app/backend/server.js
|
|
- ./libreportal.config:/app/libreportal.config:ro
|
|
# Absolute (filled at generation) — the containers root is now separate from
|
|
# the system tree, so the old relative ../../configs no longer reaches it.
|
|
- CONFIGS_DIR_DATA/webui/webui_logins:/app/webui_logins:ro #LIBREPORTAL|CONFIGS_DIR_TAG|CONFIGS_DIR_DATA
|
|
- CONFIGS_DIR_DATA/webui/webui_logs:/app/webui_logs:ro #LIBREPORTAL|CONFIGS_DIR_TAG|CONFIGS_DIR_DATA
|
|
# >>> crowdsec-host-logs >>>
|
|
#- /var/log/crowdsec.log:/host/var/log/crowdsec.log:ro
|
|
#- /var/log/crowdsec-firewall-bouncer.log:/host/var/log/crowdsec-firewall-bouncer.log:ro
|
|
# <<< crowdsec-host-logs <<<
|
|
- SOCKET_DATA #LIBREPORTAL|SOCKET_TAG|SOCKET_DATA
|
|
environment:
|
|
FRONTEND_PATH: /data/frontend
|
|
LIBREPORTAL_CONFIG_PATH: /app/libreportal.config
|
|
LP_CONTAINERS_DIR: CONTAINERS_DIR_DATA #LIBREPORTAL|CONTAINERS_DIR_TAG|CONTAINERS_DIR_DATA
|
|
TZ: TIMEZONE_DATA #LIBREPORTAL|TIMEZONE_TAG|TIMEZONE_DATA
|
|
labels:
|
|
libreportal.category: "CATEGORY_DATA" #LIBREPORTAL|CATEGORY_TAG|CATEGORY_DATA
|
|
libreportal.title: "TITLE_DATA" #LIBREPORTAL|TITLE_TAG|TITLE_DATA
|
|
traefik.enable: TRAEFIK_ENABLE_DATA #LIBREPORTAL|TRAEFIK_ENABLE_TAG|TRAEFIK_ENABLE_DATA
|
|
# TRAEFIK_PORT_1_BEGIN
|
|
traefik.http.routers.libreportal-service.entrypoints: web,websecure
|
|
traefik.http.routers.libreportal-service.rule: Host(`DOMAINSUBNAME_DATA_1`) #LIBREPORTAL|DOMAINSUBNAME_TAG_1|DOMAINSUBNAME_DATA_1
|
|
traefik.http.routers.libreportal-service.tls: true
|
|
traefik.http.routers.libreportal-service.tls.certresolver: production
|
|
traefik.http.services.libreportal-service.loadbalancer.server.port: PORT_INTERNAL_DATA_1 #LIBREPORTAL|PORT_INTERNAL_TAG_1|PORT_INTERNAL_DATA_1
|
|
traefik.http.routers.libreportal-service.middlewares: MIDDLEWARE_DATA_1 #LIBREPORTAL|MIDDLEWARE_TAG_1|MIDDLEWARE_DATA_1
|
|
# TRAEFIK_PORT_1_END
|
|
traefik.docker.network: DOCKER_NETWORK_DATA #LIBREPORTAL|DOCKER_NETWORK_TAG|DOCKER_NETWORK_DATA
|
|
healthcheck:
|
|
disable: HEALTHCHECK_DATA #LIBREPORTAL|HEALTHCHECK_TAG|HEALTHCHECK_DATA
|
|
networks:
|
|
DOCKER_NETWORK_DATA: #LIBREPORTAL|DOCKER_NETWORK_TAG|DOCKER_NETWORK_DATA
|
|
ipv4_address: IP_DATA_1 #LIBREPORTAL|IP_TAG_1|IP_DATA_1
|