chore(observability): externalize stack from root compose files
Manage now connects to existing Grafana/Prometheus/Alertmanager instances and never deploys its own stack. - docker-compose.yml / docker-compose.dev.yml: removed prometheus, loki, alloy, grafana, alertmanager, node-exporter services, the monitoring network, and observability named volumes; they now ship only backend + frontend. Dev frontend now joins the web network so the Vite dev proxy can reach the backend. - backend: alertmanager_url default is now empty; /api/monitoring/alerts and /alertmanager-status return graceful "not configured" responses when ALERTMANAGER_URL is unset. Added not-configured tests. - docker-compose.observability.yml: kept as the optional standalone example; header clarifies Manage does not deploy it. - Removed orphaned combined monitoring/prometheus/prometheus.yml (standalone stack uses prometheus.standalone.yml). - Docs (README, REQUIREMENTS decision log, monitoring-logging-design, observability-runbooks, context.md, MIGRATION_PLAN, frontend/README, CHANGELOG) updated to the connect-to-existing model. VITE_GRAFANA_URL / VITE_PROMETHEUS_URL remain as optional frontend deep-link overrides. .env.example still needs a manual update (safety policy blocks assistant edits): set ALERTMANAGER_URL empty/optional and move standalone-only vars out of the root file.
This commit is contained in:
Developer
+11
-215
@@ -1,3 +1,12 @@
|
||||
# Manage production stack — backend + frontend only.
|
||||
#
|
||||
# Manage does NOT deploy its own Grafana/Prometheus/Loki/Alertmanager stack.
|
||||
# It exposes a /metrics endpoint and optional Alertmanager proxy endpoints so
|
||||
# an *existing* observability deployment can scrape/consume them.
|
||||
#
|
||||
# For a ready-to-use example observability stack, see
|
||||
# docker-compose.observability.yml and docs/observability-runbooks.md.
|
||||
|
||||
services:
|
||||
backend:
|
||||
build:
|
||||
@@ -26,7 +35,7 @@ services:
|
||||
SMTP_TIMEOUT: ${SMTP_TIMEOUT:-30}
|
||||
SSH_KNOWN_HOSTS_PATH: /app/backend/.cache/known_hosts
|
||||
PROMETHEUS_FILE_SD_DIR: ${PROMETHEUS_FILE_SD_DIR:-/app/backend/.cache/prometheus-file-sd}
|
||||
ALERTMANAGER_URL: ${ALERTMANAGER_URL:-http://alertmanager:9093}
|
||||
ALERTMANAGER_URL: ${ALERTMANAGER_URL:-}
|
||||
ALERTMANAGER_WEBHOOK_URL: ${ALERTMANAGER_WEBHOOK_URL:-}
|
||||
MANAGE_ENCRYPTION_KEY: ${MANAGE_ENCRYPTION_KEY:?generate one with python -c "from cryptography.fernet import Fernet; print(Fernet.generate_key().decode())"}
|
||||
volumes:
|
||||
@@ -34,7 +43,6 @@ services:
|
||||
restart: unless-stopped
|
||||
networks:
|
||||
- web
|
||||
- monitoring
|
||||
expose:
|
||||
- "8000"
|
||||
labels:
|
||||
@@ -71,7 +79,7 @@ services:
|
||||
VITE_OIDC_POST_LOGOUT_REDIRECT_URI: ${VITE_OIDC_POST_LOGOUT_REDIRECT_URI:?set VITE_OIDC_POST_LOGOUT_REDIRECT_URI}
|
||||
VITE_DEV_API_PROXY_TARGET: ${VITE_DEV_API_PROXY_TARGET:-http://backend:8000}
|
||||
VITE_GRAFANA_URL: ${VITE_GRAFANA_URL:-https://grafana.example.com}
|
||||
VITE_PROMETHEUS_URL: ${VITE_PROMETHEUS_URL:-http://localhost:9090}
|
||||
VITE_PROMETHEUS_URL: ${VITE_PROMETHEUS_URL:-http://prometheus.example.com}
|
||||
VITE_APP_VERSION: ${APP_VERSION:-0.1.0}
|
||||
VITE_APP_BUILD_INFO: ${APP_BUILD_INFO:-dev}
|
||||
depends_on:
|
||||
@@ -89,218 +97,6 @@ services:
|
||||
- "8080:80"
|
||||
restart: unless-stopped
|
||||
|
||||
prometheus:
|
||||
image: prom/prometheus:v2.55.1
|
||||
container_name: prometheus
|
||||
command:
|
||||
- "--config.file=/etc/prometheus/prometheus.yml"
|
||||
- "--storage.tsdb.path=/prometheus"
|
||||
- "--storage.tsdb.retention.time=30d"
|
||||
- "--web.console.libraries=/usr/share/prometheus/console_libraries"
|
||||
- "--web.console.templates=/usr/share/prometheus/consoles"
|
||||
- "--web.enable-lifecycle"
|
||||
volumes:
|
||||
- ./monitoring/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
|
||||
- ./monitoring/prometheus/rules:/etc/prometheus/rules:ro
|
||||
- ${BACKEND_CACHE_DIR:-./backend-cache}/prometheus-file-sd:/etc/prometheus/file-sd:ro
|
||||
- prometheus_data:/prometheus
|
||||
expose:
|
||||
- "9090"
|
||||
networks:
|
||||
- web
|
||||
- monitoring
|
||||
restart: unless-stopped
|
||||
healthcheck:
|
||||
test: ["CMD", "wget", "-qO-", "http://127.0.0.1:9090/-/healthy"]
|
||||
interval: 30s
|
||||
timeout: 5s
|
||||
retries: 3
|
||||
start_period: 30s
|
||||
deploy:
|
||||
resources:
|
||||
limits:
|
||||
cpus: "1.00"
|
||||
memory: 1G
|
||||
reservations:
|
||||
cpus: "0.25"
|
||||
memory: 256M
|
||||
|
||||
loki:
|
||||
image: grafana/loki:3.1.1
|
||||
container_name: loki
|
||||
command: -config.file=/etc/loki/loki.yml
|
||||
volumes:
|
||||
- ./monitoring/loki/loki.yml:/etc/loki/loki.yml:ro
|
||||
- loki_data:/loki
|
||||
expose:
|
||||
- "3100"
|
||||
networks:
|
||||
- monitoring
|
||||
restart: unless-stopped
|
||||
healthcheck:
|
||||
test: ["CMD", "wget", "-qO-", "http://127.0.0.1:3100/ready"]
|
||||
interval: 30s
|
||||
timeout: 5s
|
||||
retries: 3
|
||||
start_period: 30s
|
||||
deploy:
|
||||
resources:
|
||||
limits:
|
||||
cpus: "1.00"
|
||||
memory: 1G
|
||||
reservations:
|
||||
cpus: "0.25"
|
||||
memory: 256M
|
||||
|
||||
alloy:
|
||||
image: grafana/alloy:v1.5.0
|
||||
container_name: alloy
|
||||
command:
|
||||
- run
|
||||
- /etc/alloy/config.alloy
|
||||
- --storage.path=/var/lib/alloy
|
||||
volumes:
|
||||
- ./monitoring/alloy/config.alloy:/etc/alloy/config.alloy:ro
|
||||
- /var/run/docker.sock:/var/run/docker.sock:ro
|
||||
- /var/lib/docker/containers:/var/lib/docker/containers:ro
|
||||
networks:
|
||||
- monitoring
|
||||
depends_on:
|
||||
loki:
|
||||
condition: service_healthy
|
||||
restart: unless-stopped
|
||||
user: root
|
||||
healthcheck:
|
||||
test: ["CMD", "wget", "-qO-", "http://127.0.0.1:12345/-/healthy"]
|
||||
interval: 30s
|
||||
timeout: 5s
|
||||
retries: 3
|
||||
start_period: 30s
|
||||
deploy:
|
||||
resources:
|
||||
limits:
|
||||
cpus: "0.50"
|
||||
memory: 512M
|
||||
reservations:
|
||||
cpus: "0.10"
|
||||
memory: 128M
|
||||
|
||||
grafana:
|
||||
image: grafana/grafana:11.3.1
|
||||
container_name: grafana
|
||||
environment:
|
||||
GF_SECURITY_ADMIN_USER: ${GRAFANA_ADMIN_USER:-admin}
|
||||
GF_SECURITY_ADMIN_PASSWORD: ${GRAFANA_ADMIN_PASSWORD:-admin}
|
||||
GF_AUTH_GENERIC_OAUTH_CLIENT_ID: ${GF_AUTH_GENERIC_OAUTH_CLIENT_ID:-}
|
||||
GF_AUTH_GENERIC_OAUTH_CLIENT_SECRET: ${GF_AUTH_GENERIC_OAUTH_CLIENT_SECRET:-}
|
||||
GF_AUTH_GENERIC_OAUTH_AUTH_URL: ${GF_AUTH_GENERIC_OAUTH_AUTH_URL:-}
|
||||
GF_AUTH_GENERIC_OAUTH_TOKEN_URL: ${GF_AUTH_GENERIC_OAUTH_TOKEN_URL:-}
|
||||
GF_AUTH_GENERIC_OAUTH_API_URL: ${GF_AUTH_GENERIC_OAUTH_API_URL:-}
|
||||
LOG_LEVEL: ${LOG_LEVEL:-INFO}
|
||||
volumes:
|
||||
- ./monitoring/grafana/grafana.ini:/etc/grafana/grafana.ini:ro
|
||||
- ./monitoring/grafana/provisioning:/etc/grafana/provisioning:ro
|
||||
- grafana_data:/var/lib/grafana
|
||||
expose:
|
||||
- "3000"
|
||||
networks:
|
||||
- web
|
||||
- monitoring
|
||||
depends_on:
|
||||
prometheus:
|
||||
condition: service_healthy
|
||||
loki:
|
||||
condition: service_healthy
|
||||
restart: unless-stopped
|
||||
healthcheck:
|
||||
test: ["CMD", "wget", "-qO-", "http://127.0.0.1:3000/api/health"]
|
||||
interval: 30s
|
||||
timeout: 5s
|
||||
retries: 3
|
||||
start_period: 30s
|
||||
labels:
|
||||
- "traefik.enable=true"
|
||||
- "traefik.http.routers.${GRAFANA_APP_NAME:-grafana}.rule=Host(`${GRAFANA_APP_HOST:?set GRAFANA_APP_HOST}`)"
|
||||
- "traefik.http.routers.${GRAFANA_APP_NAME:-grafana}.entrypoints=websecure"
|
||||
- "traefik.http.routers.${GRAFANA_APP_NAME:-grafana}.tls.certresolver=${CERT_RESOLVER:?set CERT_RESOLVER}"
|
||||
- "traefik.http.services.${GRAFANA_APP_NAME:-grafana}.loadbalancer.server.port=${GRAFANA_APP_PORT:-3000}"
|
||||
deploy:
|
||||
resources:
|
||||
limits:
|
||||
cpus: "1.00"
|
||||
memory: 512M
|
||||
reservations:
|
||||
cpus: "0.25"
|
||||
memory: 128M
|
||||
|
||||
alertmanager:
|
||||
image: prom/alertmanager:v0.27.0
|
||||
container_name: alertmanager
|
||||
command:
|
||||
- "--config.file=/etc/alertmanager/alertmanager.yml"
|
||||
- "--storage.path=/alertmanager"
|
||||
environment:
|
||||
SMTP_HOST: ${SMTP_HOST:-smtp.example.com}
|
||||
SMTP_PORT: ${SMTP_PORT:-587}
|
||||
SMTP_USERNAME: ${SMTP_USERNAME:-}
|
||||
SMTP_PASSWORD: ${SMTP_PASSWORD:-}
|
||||
SMTP_FROM_ADDRESS: ${SMTP_FROM_ADDRESS:-no-reply@example.com}
|
||||
ALERT_EMAIL_TO: ${ALERT_EMAIL_TO:-admin@example.com}
|
||||
volumes:
|
||||
- ./monitoring/alertmanager/alertmanager.yml:/etc/alertmanager/alertmanager.yml:ro
|
||||
- alertmanager_data:/alertmanager
|
||||
expose:
|
||||
- "9093"
|
||||
networks:
|
||||
- monitoring
|
||||
restart: unless-stopped
|
||||
healthcheck:
|
||||
test: ["CMD", "wget", "-qO-", "http://127.0.0.1:9093/-/healthy"]
|
||||
interval: 30s
|
||||
timeout: 5s
|
||||
retries: 3
|
||||
start_period: 30s
|
||||
deploy:
|
||||
resources:
|
||||
limits:
|
||||
cpus: "0.50"
|
||||
memory: 256M
|
||||
reservations:
|
||||
cpus: "0.10"
|
||||
memory: 64M
|
||||
|
||||
node-exporter:
|
||||
image: prom/node-exporter:v1.8.2
|
||||
container_name: node-exporter
|
||||
command:
|
||||
- "--path.rootfs=/host"
|
||||
volumes:
|
||||
- /:/host:ro,rslave
|
||||
networks:
|
||||
- monitoring
|
||||
restart: unless-stopped
|
||||
healthcheck:
|
||||
test: ["CMD", "wget", "-qO-", "http://127.0.0.1:9100/"]
|
||||
interval: 30s
|
||||
timeout: 5s
|
||||
retries: 3
|
||||
start_period: 10s
|
||||
deploy:
|
||||
resources:
|
||||
limits:
|
||||
cpus: "0.25"
|
||||
memory: 128M
|
||||
reservations:
|
||||
cpus: "0.05"
|
||||
memory: 32M
|
||||
|
||||
networks:
|
||||
web:
|
||||
external: true
|
||||
monitoring:
|
||||
|
||||
volumes:
|
||||
prometheus_data:
|
||||
loki_data:
|
||||
grafana_data:
|
||||
alertmanager_data:
|
||||
|
||||
Reference in New Issue
Block a user