Refresh HiveGrid Cloud reference snapshot
This commit is contained in:
1 parent
5e99e14772
commit
7f88026f79
5955 files changed
+1177325
-188362
No files matched your search
@@ -1,10 +1,12 @@
|
||||
# Prometheus — HiveGrid
|
||||
|
||||
Scrapes `/metrics` from the three HiveGrid apps every 15s.
|
||||
Scrapes the HiveGrid runtime metrics every 15s. The web core/admin process and
|
||||
the separately deployed portal process each have their own process-local
|
||||
registry and therefore their own scrape target.
|
||||
|
||||
## Files
|
||||
|
||||
- `prometheus.yml` — scrape jobs (api / worker / web)
|
||||
- `prometheus.yml` — scrape jobs (api / worker / web-core / web-portal)
|
||||
- `docker-compose.yml` — Coolify-friendly compose stack
|
||||
- `secrets/metrics_token` — bearer token (chmod 600, do NOT commit)
|
||||
|
||||
@@ -23,19 +25,27 @@ docker network create hivegrid-observability
|
||||
docker compose up -d
|
||||
```
|
||||
|
||||
Then expose `prometheus.saas-ctrl.com` via Coolify's proxy with
|
||||
**basic-auth or Cloudflare-Access** in front — Prometheus has no
|
||||
built-in auth and ships internal state.
|
||||
Prometheus is deliberately reachable only as `prometheus:9090` on the
|
||||
`hivegrid-observability` Docker network. It has no host-port binding and no
|
||||
lifecycle HTTP endpoint. Use Grafana for dashboards; temporary operator access
|
||||
must use an authenticated tunnel rather than public ingress.
|
||||
|
||||
## Verifying scrape targets
|
||||
|
||||
```sh
|
||||
curl -s -H "Authorization: Bearer $(cat secrets/metrics_token)" \
|
||||
https://api.hivegrid.de/metrics | head -20
|
||||
|
||||
curl -s -H "Authorization: Bearer $(cat secrets/metrics_token)" \
|
||||
https://app.hivegrid.de/api/metrics | head -20
|
||||
|
||||
curl -s -H "Authorization: Bearer $(cat secrets/metrics_token)" \
|
||||
https://portal.hivegrid.de/api/metrics | head -20
|
||||
```
|
||||
|
||||
The Prometheus UI at `https://prometheus.saas-ctrl.com/targets`
|
||||
should list all three jobs as **UP**.
|
||||
Through an authenticated operator tunnel, the Prometheus `/targets` view should
|
||||
list all four jobs as **UP**. Do not also scrape `admin.hivegrid.de`: admin and
|
||||
core share the same process-local registry, so doing so would double-count.
|
||||
|
||||
## Cardinality budget
|
||||
|
||||
|
||||
@@ -14,7 +14,7 @@
|
||||
|
||||
services:
|
||||
prometheus:
|
||||
image: prom/prometheus:v3.6.0
|
||||
image: prom/prometheus:v3.6.0@sha256:76947e7ef22f8a698fc638f706685909be425dbe09bd7a2cd7aca849f79b5f64
|
||||
container_name: hivegrid-prometheus
|
||||
restart: unless-stopped
|
||||
user: "65534:65534"
|
||||
@@ -24,14 +24,12 @@ services:
|
||||
- --storage.tsdb.retention.time=30d
|
||||
- --web.console.libraries=/usr/share/prometheus/console_libraries
|
||||
- --web.console.templates=/usr/share/prometheus/consoles
|
||||
- --web.enable-lifecycle
|
||||
- --web.external-url=https://prometheus.saas-ctrl.com
|
||||
volumes:
|
||||
- ./prometheus.yml:/etc/prometheus/prometheus.yml:ro
|
||||
- ./secrets:/etc/prometheus/secrets:ro
|
||||
- prometheus-data:/prometheus
|
||||
ports:
|
||||
- "9090:9090"
|
||||
expose:
|
||||
- "9090"
|
||||
networks:
|
||||
- observability
|
||||
|
||||
|
||||
@@ -8,7 +8,8 @@
|
||||
# Targets:
|
||||
# * api — apps/api admin metrics surface (port 3201 default)
|
||||
# * worker — apps/worker admin server (port 9101 default; 9100 is health-probe)
|
||||
# * web — apps/web SSR resource route on /api/metrics
|
||||
# * web-core — apps/web core SSR resource route on /api/metrics
|
||||
# * web-portal — apps/web portal SSR resource route on /api/metrics
|
||||
#
|
||||
# Operator deploys this on the Hetzner staging server alongside Sentry.
|
||||
|
||||
@@ -62,20 +63,32 @@ scrape_configs:
|
||||
labels:
|
||||
service: worker
|
||||
|
||||
- job_name: hivegrid-web
|
||||
- job_name: hivegrid-web-core
|
||||
metrics_path: /api/metrics
|
||||
scheme: https
|
||||
authorization:
|
||||
type: Bearer
|
||||
credentials_file: /etc/prometheus/secrets/metrics_token
|
||||
static_configs:
|
||||
# /api/metrics is admin-only — the resource route is mounted on
|
||||
# the admin host. Scraping the tenant-facing host returns 404 by
|
||||
# design. Use admin.<domain> for staging; in prod set to
|
||||
# admin.<prod-domain>.
|
||||
- targets: ["admin.hivegrid.de"]
|
||||
# Core and admin share one process-local registry. Scrape exactly one
|
||||
# host so counters are not duplicated.
|
||||
- targets: ["app.hivegrid.de"]
|
||||
labels:
|
||||
service: web
|
||||
runtime_surface: core
|
||||
|
||||
- job_name: hivegrid-web-portal
|
||||
metrics_path: /api/metrics
|
||||
scheme: https
|
||||
authorization:
|
||||
type: Bearer
|
||||
credentials_file: /etc/prometheus/secrets/metrics_token
|
||||
static_configs:
|
||||
# Portal runs in its own process and therefore has a separate registry.
|
||||
- targets: ["portal.hivegrid.de"]
|
||||
labels:
|
||||
service: web
|
||||
runtime_surface: portal
|
||||
|
||||
# When promoting to production, also scrape the production targets behind
|
||||
# their own bearer-token. Add scrape_configs entries with environment=production.
|
||||
Reference in new issue
Block a user