blumeops/mise-tasks/services-check

216 lines
7.6 KiB
Text
Raw Normal View History

#!/usr/bin/env bash
#MISE description="Check that all services are online and responding"
set -euo pipefail
# Colors for output
RED='\033[0;31m'
GREEN='\033[0;32m'
YELLOW='\033[0;33m'
NC='\033[0m' # No Color
FAILED=0
check_service() {
local name="$1"
local check_cmd="$2"
Migrate observability stack to Kubernetes (#42) Note: the name of this branch was chosen before the scope widened to encompass the entire observability stack. Summary - Fix Grafana data source URLs (docker driver uses host.minikube.internal, not host.containers.internal) - Migrate Prometheus and Loki from indri to Kubernetes with Tailscale Ingresses - Expose CNPG PostgreSQL metrics via Tailscale and update dashboard to use cnpg_* metrics - Update Alloy to push metrics/logs to k8s endpoints (prometheus.tail8d86e.ts.net, loki.tail8d86e.ts.net) - Add ACL rule for port 9187 (CNPG metrics) - Delete obsolete ansible roles for prometheus and loki Changes - argocd/manifests/prometheus/ - New Prometheus StatefulSet with 20Gi PVC and Tailscale Ingress - argocd/manifests/loki/ - New Loki StatefulSet with 20Gi PVC and Tailscale Ingress - argocd/apps/prometheus.yaml, argocd/apps/loki.yaml - ArgoCD Applications - argocd/manifests/grafana/values.yaml - Data sources now use k8s internal DNS - argocd/manifests/databases/service-metrics-tailscale.yaml - CNPG metrics endpoint - argocd/manifests/grafana-config/dashboards/configmap-postgresql.yaml - Updated to cnpg_* metrics - ansible/roles/alloy/defaults/main.yml - Push to k8s Tailscale endpoints - pulumi/policy.hujson - ACL for port 9187 - Deleted ansible/roles/prometheus/ and ansible/roles/loki/ Deployment and Testing - Stop prometheus and loki on indri - Sync ArgoCD apps (apps, prometheus, loki, grafana) - Run mise run provision-indri -- --tags alloy - Verify Grafana dashboards show data 🤖 Generated with https://claude.ai/claude-code Reviewed-on: https://forge.tail8d86e.ts.net/eblume/blumeops/pulls/42
2026-01-22 12:06:02 -08:00
printf "%-24s " "$name..."
if eval "$check_cmd" > /dev/null 2>&1; then
echo -e "${GREEN}OK${NC}"
else
echo -e "${RED}FAILED${NC}"
FAILED=1
fi
}
check_http() {
local name="$1"
local url="$2"
Migrate observability stack to Kubernetes (#42) Note: the name of this branch was chosen before the scope widened to encompass the entire observability stack. Summary - Fix Grafana data source URLs (docker driver uses host.minikube.internal, not host.containers.internal) - Migrate Prometheus and Loki from indri to Kubernetes with Tailscale Ingresses - Expose CNPG PostgreSQL metrics via Tailscale and update dashboard to use cnpg_* metrics - Update Alloy to push metrics/logs to k8s endpoints (prometheus.tail8d86e.ts.net, loki.tail8d86e.ts.net) - Add ACL rule for port 9187 (CNPG metrics) - Delete obsolete ansible roles for prometheus and loki Changes - argocd/manifests/prometheus/ - New Prometheus StatefulSet with 20Gi PVC and Tailscale Ingress - argocd/manifests/loki/ - New Loki StatefulSet with 20Gi PVC and Tailscale Ingress - argocd/apps/prometheus.yaml, argocd/apps/loki.yaml - ArgoCD Applications - argocd/manifests/grafana/values.yaml - Data sources now use k8s internal DNS - argocd/manifests/databases/service-metrics-tailscale.yaml - CNPG metrics endpoint - argocd/manifests/grafana-config/dashboards/configmap-postgresql.yaml - Updated to cnpg_* metrics - ansible/roles/alloy/defaults/main.yml - Push to k8s Tailscale endpoints - pulumi/policy.hujson - ACL for port 9187 - Deleted ansible/roles/prometheus/ and ansible/roles/loki/ Deployment and Testing - Stop prometheus and loki on indri - Sync ArgoCD apps (apps, prometheus, loki, grafana) - Run mise run provision-indri -- --tags alloy - Verify Grafana dashboards show data 🤖 Generated with https://claude.ai/claude-code Reviewed-on: https://forge.tail8d86e.ts.net/eblume/blumeops/pulls/42
2026-01-22 12:06:02 -08:00
printf "%-24s " "$name..."
if curl -sf --max-time 5 "$url" > /dev/null 2>&1; then
echo -e "${GREEN}OK${NC}"
else
echo -e "${RED}FAILED${NC}"
FAILED=1
fi
}
# ============== Grafana Alerting API ==============
GRAFANA_URL="https://grafana.ops.eblu.me"
GRAFANA_CREDS=""
fetch_alerts() {
if [ -z "$GRAFANA_CREDS" ]; then
local pass
pass=$(op read 'op://vg6xf6vvfmoh5hqjjhlhbeoaie/oxkcr3xtxnewy7noep2izvyr6y/password' 2>/dev/null) || true
if [ -n "$pass" ]; then
GRAFANA_CREDS=$(echo -n "admin:$pass" | base64)
fi
fi
if [ -z "$GRAFANA_CREDS" ]; then
echo ""
return
fi
curl -sf --max-time 10 \
-H "Authorization: Basic $GRAFANA_CREDS" \
"$GRAFANA_URL/api/prometheus/grafana/api/v1/alerts" 2>/dev/null || echo ""
}
# Fetch all alerts once
ALERTS_JSON=$(fetch_alerts)
check_alert() {
local name="$1"
local alertname="$2"
# Optional: filter by a label key=value
local filter_key="${3:-}"
local filter_value="${4:-}"
printf "%-24s " "$name..."
if [ -z "$ALERTS_JSON" ]; then
echo -e "${YELLOW}NO DATA${NC} (can't reach Grafana alerting API)"
return
fi
local firing
firing=$(echo "$ALERTS_JSON" | python3 -c "
import json, sys
try:
data = json.load(sys.stdin)
except:
sys.exit(1)
alerts = data.get('data', {}).get('alerts', [])
for a in alerts:
if a['labels'].get('alertname') != '$alertname':
continue
if '$filter_key' and a['labels'].get('$filter_key') != '$filter_value':
continue
if a['state'] in ('Alerting', 'Pending') or a['state'].startswith('Alerting'):
url = a.get('annotations', {}).get('runbook_url', '')
summary = a.get('annotations', {}).get('summary', '')
print(f'{summary}|{url}')
" 2>/dev/null)
if [ -z "$firing" ]; then
echo -e "${GREEN}OK${NC}"
else
local summary runbook
summary=$(echo "$firing" | head -1 | cut -d'|' -f1)
runbook=$(echo "$firing" | head -1 | cut -d'|' -f2)
echo -e "${RED}FIRING${NC}"
if [ -n "$summary" ]; then
echo -e " $summary"
fi
if [ -n "$runbook" ]; then
echo -e " Runbook: $runbook"
fi
FAILED=1
fi
}
echo "Checking services..."
echo "===================="
echo ""
# Local services on indri (not yet covered by alerting)
Migrate observability stack to Kubernetes (#42) Note: the name of this branch was chosen before the scope widened to encompass the entire observability stack. Summary - Fix Grafana data source URLs (docker driver uses host.minikube.internal, not host.containers.internal) - Migrate Prometheus and Loki from indri to Kubernetes with Tailscale Ingresses - Expose CNPG PostgreSQL metrics via Tailscale and update dashboard to use cnpg_* metrics - Update Alloy to push metrics/logs to k8s endpoints (prometheus.tail8d86e.ts.net, loki.tail8d86e.ts.net) - Add ACL rule for port 9187 (CNPG metrics) - Delete obsolete ansible roles for prometheus and loki Changes - argocd/manifests/prometheus/ - New Prometheus StatefulSet with 20Gi PVC and Tailscale Ingress - argocd/manifests/loki/ - New Loki StatefulSet with 20Gi PVC and Tailscale Ingress - argocd/apps/prometheus.yaml, argocd/apps/loki.yaml - ArgoCD Applications - argocd/manifests/grafana/values.yaml - Data sources now use k8s internal DNS - argocd/manifests/databases/service-metrics-tailscale.yaml - CNPG metrics endpoint - argocd/manifests/grafana-config/dashboards/configmap-postgresql.yaml - Updated to cnpg_* metrics - ansible/roles/alloy/defaults/main.yml - Push to k8s Tailscale endpoints - pulumi/policy.hujson - ACL for port 9187 - Deleted ansible/roles/prometheus/ and ansible/roles/loki/ Deployment and Testing - Stop prometheus and loki on indri - Sync ArgoCD apps (apps, prometheus, loki, grafana) - Run mise run provision-indri -- --tags alloy - Verify Grafana dashboards show data 🤖 Generated with https://claude.ai/claude-code Reviewed-on: https://forge.tail8d86e.ts.net/eblume/blumeops/pulls/42
2026-01-22 12:06:02 -08:00
echo "Local services on indri:"
check_service "forgejo" "ssh indri 'launchctl list mcquack.eblume.forgejo | grep -v \"^-\"'"
Migrate observability stack to Kubernetes (#42) Note: the name of this branch was chosen before the scope widened to encompass the entire observability stack. Summary - Fix Grafana data source URLs (docker driver uses host.minikube.internal, not host.containers.internal) - Migrate Prometheus and Loki from indri to Kubernetes with Tailscale Ingresses - Expose CNPG PostgreSQL metrics via Tailscale and update dashboard to use cnpg_* metrics - Update Alloy to push metrics/logs to k8s endpoints (prometheus.tail8d86e.ts.net, loki.tail8d86e.ts.net) - Add ACL rule for port 9187 (CNPG metrics) - Delete obsolete ansible roles for prometheus and loki Changes - argocd/manifests/prometheus/ - New Prometheus StatefulSet with 20Gi PVC and Tailscale Ingress - argocd/manifests/loki/ - New Loki StatefulSet with 20Gi PVC and Tailscale Ingress - argocd/apps/prometheus.yaml, argocd/apps/loki.yaml - ArgoCD Applications - argocd/manifests/grafana/values.yaml - Data sources now use k8s internal DNS - argocd/manifests/databases/service-metrics-tailscale.yaml - CNPG metrics endpoint - argocd/manifests/grafana-config/dashboards/configmap-postgresql.yaml - Updated to cnpg_* metrics - ansible/roles/alloy/defaults/main.yml - Push to k8s Tailscale endpoints - pulumi/policy.hujson - ACL for port 9187 - Deleted ansible/roles/prometheus/ and ansible/roles/loki/ Deployment and Testing - Stop prometheus and loki on indri - Sync ArgoCD apps (apps, prometheus, loki, grafana) - Run mise run provision-indri -- --tags alloy - Verify Grafana dashboards show data 🤖 Generated with https://claude.ai/claude-code Reviewed-on: https://forge.tail8d86e.ts.net/eblume/blumeops/pulls/42
2026-01-22 12:06:02 -08:00
check_service "alloy" "ssh indri 'launchctl list mcquack.eblume.alloy | grep -v \"^-\"'"
check_service "borgmatic" "ssh indri 'launchctl list mcquack.eblume.borgmatic | grep -v \"^-\"'"
check_service "borgmatic-metrics" "ssh indri 'launchctl list mcquack.borgmatic-metrics | grep -v \"^-\"'"
check_service "zot" "ssh indri 'launchctl list mcquack.eblume.zot | grep -v \"^-\"'"
check_service "zot-metrics" "ssh indri 'launchctl list mcquack.zot-metrics | grep -v \"^-\"'"
check_service "minikube-metrics" "ssh indri 'launchctl list mcquack.minikube-metrics | grep -v \"^-\"'"
check_service "jellyfin-metrics" "ssh indri 'launchctl list mcquack.eblume.jellyfin-metrics | grep -v \"^-\"'"
echo ""
echo "Metrics textfiles (via alerting):"
check_alert "textfile-freshness" "TextfileStale"
echo ""
echo "Kubernetes cluster (not yet covered by alerting):"
check_service "minikube" "ssh indri 'minikube status --format={{.Host}} | grep -q Running'"
check_service "k8s-apiserver (indri)" "ssh indri 'kubectl get --raw /healthz'"
check_service "k8s-apiserver (remote)" "kubectl --kubeconfig=$HOME/.kube/minikube-indri/config.yml --context=minikube-indri get --raw /healthz"
echo ""
echo "HTTP endpoints (via alerting):"
check_alert "Prometheus" "ServiceProbeFailure" "service" "prometheus"
check_alert "Loki" "ServiceProbeFailure" "service" "loki"
check_alert "Grafana" "ServiceProbeFailure" "service" "grafana"
check_alert "ArgoCD" "ServiceProbeFailure" "service" "argocd"
check_alert "Kiwix" "ServiceProbeFailure" "service" "kiwix"
check_alert "Miniflux" "ServiceProbeFailure" "service" "miniflux"
check_alert "TeslaMate" "ServiceProbeFailure" "service" "teslamate"
check_alert "Devpi" "ServiceProbeFailure" "service" "devpi"
check_alert "Transmission" "ServiceProbeFailure" "service" "transmission"
check_alert "Immich" "ServiceProbeFailure" "service" "immich"
check_alert "Navidrome" "ServiceProbeFailure" "service" "navidrome"
echo ""
echo "HTTP endpoints (not yet covered by alerting):"
Expose Forgejo publicly at forge.eblu.me (#278) ## Summary Expose Forgejo publicly at `forge.eblu.me` via the Fly.io reverse proxy — the first dynamic, authenticated public-facing service. - **Forgejo hardening:** Domain changed to forge.eblu.me, SSH stays on forge.ops.eblu.me, reverse proxy trust headers configured, local registration locked to external-only (Authentik SSO) - **Tailscale Ingress:** ExternalName Service + Ingress in tailscale-operator creates forge.tail8d86e.ts.net endpoint - **Fly.io proxy:** nginx server block with rate-limited auth endpoints (3r/s), fail2ban with custom nginx-deny action, security headers, /swagger blocked, WebSocket support, 512m body limit - **Authentik:** OAuth callback updated to forge.eblu.me - **DNS/TLS:** CNAME record in Pulumi, cert in fly-setup - **Rename:** ~29 files updated from forge.ops.eblu.me to forge.eblu.me (HTTPS refs only; SSH, container builds, and Caddy table kept as-is) ## Deployment Order 1. `mise run provision-indri -- --tags forgejo` (config changes) 2. Verify forge.ops.eblu.me still works 3. `argocd app set tailscale-operator --revision feature/forge-public && argocd app sync tailscale-operator` 4. Verify `curl https://forge.tail8d86e.ts.net` 5. `cd fly && fly deploy` 6. Verify pre-DNS: `curl -H "Host: forge.eblu.me" https://blumeops-proxy.fly.dev/` 7. `fly certs add forge.eblu.me -a blumeops-proxy` 8. `argocd app set authentik --revision feature/forge-public && argocd app sync authentik` 9. `mise run dns-preview && mise run dns-up` 10. Full verification (see below) 11. Rehearse `mise run fly-shutoff` 12. After merge: reset ArgoCD revisions to main, re-sync ## Verification Checklist - [ ] forge.eblu.me loads, shows public repos - [ ] forge.ops.eblu.me still works from tailnet - [ ] SSH clone via forge.ops.eblu.me:2222 works - [ ] HTTPS clone via forge.eblu.me works - [ ] UI shows forge.eblu.me for HTTPS clone, forge.ops.eblu.me for SSH - [ ] /swagger returns 403 - [ ] Rapid login attempts trigger 429 rate limit - [ ] fail2ban bans after 5 failed logins in 10 minutes - [ ] ArgoCD can still sync (SSH unaffected) - [ ] `mise run fly-shutoff` stops all public traffic - [ ] `mise run services-check` passes Reviewed-on: https://forge.eblu.me/eblume/blumeops/pulls/278
2026-03-03 08:40:41 -08:00
check_http "Forgejo" "https://forge.eblu.me/"
check_http "Zot Registry" "https://registry.ops.eblu.me/v2/_catalog"
check_http "CV" "https://cv.ops.eblu.me/"
Deploy Frigate NVR stack with Mosquitto, Ntfy, and frigate-notify (#190) ## Summary Deploy a cloud-free NVR stack for the GableCam (ReoLink Elite Floodlight at 192.168.1.159): - **Mosquitto** — shared MQTT broker in `mqtt` namespace (cluster-internal, no auth) - **Ntfy** — self-hosted push notifications in `ntfy` namespace, exposed at `ntfy.tail8d86e.ts.net` / `ntfy.ops.eblu.me` - **Frigate** — NVR with GableCam via HTTP-FLV, ONNX CPU detection, NFS recordings on sifaka, exposed at `nvr.tail8d86e.ts.net` / `nvr.ops.eblu.me` - **frigate-notify** — bridges Frigate detection events (person, car, dog, cat) to Ntfy alerts via MQTT Also includes: - Prometheus scrape target for Frigate metrics - Grafana dashboard for Frigate (status, inference speed, FPS, CPU/memory, storage) - Caddy reverse proxy entries for `nvr.ops.eblu.me` and `ntfy.ops.eblu.me` ## Prerequisites - [ ] Create NFS share `frigate` on sifaka (`/volume1/frigate`, RW for indri) - [ ] Create 1Password item "Reolink Floodlight Camera" in `blumeops` vault with `username` and `password` fields ## Deployment (after merge) ```bash argocd app sync apps argocd app sync mosquitto argocd app sync ntfy argocd app sync frigate argocd app sync grafana-config argocd app sync prometheus mise run provision-indri -- --tags caddy mise run services-check ``` ## Verification - [ ] Mosquitto pod running, accepting connections on 1883 - [ ] Ntfy web UI accessible at `ntfy.ops.eblu.me` - [ ] Frigate web UI at `nvr.ops.eblu.me` showing GableCam live feed - [ ] Object detection working (ONNX, person/car/dog/cat) - [ ] Recordings appearing in NFS share on sifaka - [ ] frigate-notify sending detection alerts to Ntfy - [ ] Prometheus scraping Frigate metrics - [ ] Grafana dashboard showing Frigate data Reviewed-on: https://forge.ops.eblu.me/eblume/blumeops/pulls/190
2026-02-14 21:27:44 -08:00
check_http "Ntfy" "https://ntfy.ops.eblu.me/v1/health"
check_http "Authentik" "https://authentik.ops.eblu.me/-/health/live/"
Deploy Frigate NVR stack with Mosquitto, Ntfy, and frigate-notify (#190) ## Summary Deploy a cloud-free NVR stack for the GableCam (ReoLink Elite Floodlight at 192.168.1.159): - **Mosquitto** — shared MQTT broker in `mqtt` namespace (cluster-internal, no auth) - **Ntfy** — self-hosted push notifications in `ntfy` namespace, exposed at `ntfy.tail8d86e.ts.net` / `ntfy.ops.eblu.me` - **Frigate** — NVR with GableCam via HTTP-FLV, ONNX CPU detection, NFS recordings on sifaka, exposed at `nvr.tail8d86e.ts.net` / `nvr.ops.eblu.me` - **frigate-notify** — bridges Frigate detection events (person, car, dog, cat) to Ntfy alerts via MQTT Also includes: - Prometheus scrape target for Frigate metrics - Grafana dashboard for Frigate (status, inference speed, FPS, CPU/memory, storage) - Caddy reverse proxy entries for `nvr.ops.eblu.me` and `ntfy.ops.eblu.me` ## Prerequisites - [ ] Create NFS share `frigate` on sifaka (`/volume1/frigate`, RW for indri) - [ ] Create 1Password item "Reolink Floodlight Camera" in `blumeops` vault with `username` and `password` fields ## Deployment (after merge) ```bash argocd app sync apps argocd app sync mosquitto argocd app sync ntfy argocd app sync frigate argocd app sync grafana-config argocd app sync prometheus mise run provision-indri -- --tags caddy mise run services-check ``` ## Verification - [ ] Mosquitto pod running, accepting connections on 1883 - [ ] Ntfy web UI accessible at `ntfy.ops.eblu.me` - [ ] Frigate web UI at `nvr.ops.eblu.me` showing GableCam live feed - [ ] Object detection working (ONNX, person/car/dog/cat) - [ ] Recordings appearing in NFS share on sifaka - [ ] frigate-notify sending detection alerts to Ntfy - [ ] Prometheus scraping Frigate metrics - [ ] Grafana dashboard showing Frigate data Reviewed-on: https://forge.ops.eblu.me/eblume/blumeops/pulls/190
2026-02-14 21:27:44 -08:00
check_http "Frigate" "https://nvr.ops.eblu.me/api/version"
Migrate observability stack to Kubernetes (#42) Note: the name of this branch was chosen before the scope widened to encompass the entire observability stack. Summary - Fix Grafana data source URLs (docker driver uses host.minikube.internal, not host.containers.internal) - Migrate Prometheus and Loki from indri to Kubernetes with Tailscale Ingresses - Expose CNPG PostgreSQL metrics via Tailscale and update dashboard to use cnpg_* metrics - Update Alloy to push metrics/logs to k8s endpoints (prometheus.tail8d86e.ts.net, loki.tail8d86e.ts.net) - Add ACL rule for port 9187 (CNPG metrics) - Delete obsolete ansible roles for prometheus and loki Changes - argocd/manifests/prometheus/ - New Prometheus StatefulSet with 20Gi PVC and Tailscale Ingress - argocd/manifests/loki/ - New Loki StatefulSet with 20Gi PVC and Tailscale Ingress - argocd/apps/prometheus.yaml, argocd/apps/loki.yaml - ArgoCD Applications - argocd/manifests/grafana/values.yaml - Data sources now use k8s internal DNS - argocd/manifests/databases/service-metrics-tailscale.yaml - CNPG metrics endpoint - argocd/manifests/grafana-config/dashboards/configmap-postgresql.yaml - Updated to cnpg_* metrics - ansible/roles/alloy/defaults/main.yml - Push to k8s Tailscale endpoints - pulumi/policy.hujson - ACL for port 9187 - Deleted ansible/roles/prometheus/ and ansible/roles/loki/ Deployment and Testing - Stop prometheus and loki on indri - Sync ArgoCD apps (apps, prometheus, loki, grafana) - Run mise run provision-indri -- --tags alloy - Verify Grafana dashboards show data 🤖 Generated with https://claude.ai/claude-code Reviewed-on: https://forge.tail8d86e.ts.net/eblume/blumeops/pulls/42
2026-01-22 12:06:02 -08:00
echo ""
echo "Frigate (via alerting):"
check_alert "camera-fps" "FrigateCameraDown"
echo "Frigate (not yet covered by alerting):"
check_service "frigate-storage" "curl -sf --max-time 5 https://nvr.ops.eblu.me/api/stats | jq -e '.service.storage | to_entries | map(select(.key | startswith(\"/media\"))) | length > 0 and all(.[]; .value.free > 0)'"
echo ""
echo "Ringtail (not yet covered by alerting):"
check_service "ssh" "ssh -o ConnectTimeout=5 ringtail true"
check_service "tailscale" "ssh ringtail 'tailscale status --self --json' | jq -e '.Self.Online' > /dev/null"
check_service "k3s" "ssh ringtail 'KUBECONFIG=/etc/rancher/k3s/k3s.yaml k3s kubectl get nodes --no-headers | grep -q Ready'"
Add k3s, 1Password Connect, and systemd nix-container-builder to ringtail (#209) ## Summary Extends ringtail from a desktop/gaming NixOS box into an infrastructure node with a k3s cluster, secrets management, and a Forgejo Actions runner for building containers with Nix. ### K3s cluster - Single-node k3s with Traefik/ServiceLB/metrics-server disabled (minimal footprint) - TLS SAN set to `ringtail.tail8d86e.ts.net` so ArgoCD on indri can manage it via Tailscale - Containerd registry mirrors pull through Zot on indri (`k3s-registries.yaml`) - Tailscale interface added to `trustedInterfaces` for cross-node ArgoCD access - `kubectl` added to system packages ### 1Password Connect + External Secrets Operator - Four new ArgoCD apps targeting `k3s-ringtail`: `1password-connect-ringtail`, `external-secrets-crds-ringtail`, `external-secrets-ringtail`, `external-secrets-config-ringtail` - Reuses the same Helm charts/values as indri, just pointed at ringtail's k3s API server - Bootstrap secrets (`op-credentials`, `onepassword-token`) provisioned by Ansible pre_tasks via `op read`, then applied to the `1password` namespace in post_tasks ### Systemd Forgejo Actions runner - Native `services.gitea-actions-runner` with `forgejo-runner` package — no DinD, no k8s pod, runs directly on the NixOS host - Label `nix-container-builder:host` — jobs execute on the host with `nix`, `skopeo`, `nodejs`, etc. in PATH - Registration token fetched from 1Password (`Forgejo Secrets/runner_reg`) by Ansible and written to `/etc/forgejo-runner/token.env` - Runner's dynamic user (`gitea-runner`) added to `nix.settings.trusted-users` for nix daemon access ### Nix container build workflow - New `.forgejo/workflows/build-container-nix.yaml` triggers on `*-nix-v[0-9]*` tags (e.g. `nettest-nix-v1.0.0`) - Builds with `nix build -f containers/<name>/default.nix`, pushes to Zot via `skopeo copy` - Existing Dockerfile workflow guarded with `if: !contains(github.ref_name, '-nix-v')` to avoid double-triggering ### Mise task updates - `container-tag-and-release` auto-detects `default.nix` vs `Dockerfile` and uses the appropriate tag format (`-nix-v` vs `-v`) - `container-list` shows build type indicator (`[nix]` / `[dockerfile]`) ## Post-merge 1. `mise run provision-ringtail` — deploys k3s token, runner token, NixOS rebuild 2. Register k3s cluster in ArgoCD (first time only): ```fish ssh ringtail 'sudo cat /etc/rancher/k3s/k3s.yaml' | \ sed 's|127.0.0.1|ringtail.tail8d86e.ts.net|' > /tmp/k3s-ringtail.yaml set -x KUBECONFIG /tmp/k3s-ringtail.yaml argocd cluster add default --name k3s-ringtail 3. Sync ArgoCD apps in order: 1password-connect-ringtail -> external-secrets-crds-ringtail -> external-secrets-ringtail -> external-secrets-config-ringtail 4. Verify runner: ssh ringtail 'systemctl status gitea-runner-nix-container-builder' 5. Check Forgejo admin panel for ringtail-nix-builder runner online 6. Test: create containers/<name>/default.nix, tag with <name>-nix-v0.1.0 Reviewed-on: https://forge.ops.eblu.me/eblume/blumeops/pulls/209
2026-02-18 21:15:30 -08:00
check_service "k3s-apiserver (remote)" "kubectl --context=k3s-ringtail get --raw /healthz"
check_service "forgejo-runner" "ssh ringtail 'systemctl is-active gitea-runner-nix_container_builder.service'"
echo ""
echo "Pod health (via alerting):"
check_alert "pod-readiness" "PodNotReady"
echo ""
echo "Database (via alerting):"
check_alert "PostgreSQL" "PostgresClusterUnhealthy"
echo ""
echo "Public services (not yet covered by alerting):"
check_http "Docs (public)" "https://docs.eblu.me/"
check_http "CV (public)" "https://cv.eblu.me/"
check_http "Forge (public)" "https://forge.eblu.me/"
check_http "Fly.io healthz" "https://blumeops-proxy.fly.dev/healthz"
Migrate observability stack to Kubernetes (#42) Note: the name of this branch was chosen before the scope widened to encompass the entire observability stack. Summary - Fix Grafana data source URLs (docker driver uses host.minikube.internal, not host.containers.internal) - Migrate Prometheus and Loki from indri to Kubernetes with Tailscale Ingresses - Expose CNPG PostgreSQL metrics via Tailscale and update dashboard to use cnpg_* metrics - Update Alloy to push metrics/logs to k8s endpoints (prometheus.tail8d86e.ts.net, loki.tail8d86e.ts.net) - Add ACL rule for port 9187 (CNPG metrics) - Delete obsolete ansible roles for prometheus and loki Changes - argocd/manifests/prometheus/ - New Prometheus StatefulSet with 20Gi PVC and Tailscale Ingress - argocd/manifests/loki/ - New Loki StatefulSet with 20Gi PVC and Tailscale Ingress - argocd/apps/prometheus.yaml, argocd/apps/loki.yaml - ArgoCD Applications - argocd/manifests/grafana/values.yaml - Data sources now use k8s internal DNS - argocd/manifests/databases/service-metrics-tailscale.yaml - CNPG metrics endpoint - argocd/manifests/grafana-config/dashboards/configmap-postgresql.yaml - Updated to cnpg_* metrics - ansible/roles/alloy/defaults/main.yml - Push to k8s Tailscale endpoints - pulumi/policy.hujson - ACL for port 9187 - Deleted ansible/roles/prometheus/ and ansible/roles/loki/ Deployment and Testing - Stop prometheus and loki on indri - Sync ArgoCD apps (apps, prometheus, loki, grafana) - Run mise run provision-indri -- --tags alloy - Verify Grafana dashboards show data 🤖 Generated with https://claude.ai/claude-code Reviewed-on: https://forge.tail8d86e.ts.net/eblume/blumeops/pulls/42
2026-01-22 12:06:02 -08:00
echo ""
echo "ArgoCD app sync status (via alerting):"
check_alert "argocd-sync" "ArgoCDAppOutOfSync"
# Keep the detailed table as a summary view
Migrate observability stack to Kubernetes (#42) Note: the name of this branch was chosen before the scope widened to encompass the entire observability stack. Summary - Fix Grafana data source URLs (docker driver uses host.minikube.internal, not host.containers.internal) - Migrate Prometheus and Loki from indri to Kubernetes with Tailscale Ingresses - Expose CNPG PostgreSQL metrics via Tailscale and update dashboard to use cnpg_* metrics - Update Alloy to push metrics/logs to k8s endpoints (prometheus.tail8d86e.ts.net, loki.tail8d86e.ts.net) - Add ACL rule for port 9187 (CNPG metrics) - Delete obsolete ansible roles for prometheus and loki Changes - argocd/manifests/prometheus/ - New Prometheus StatefulSet with 20Gi PVC and Tailscale Ingress - argocd/manifests/loki/ - New Loki StatefulSet with 20Gi PVC and Tailscale Ingress - argocd/apps/prometheus.yaml, argocd/apps/loki.yaml - ArgoCD Applications - argocd/manifests/grafana/values.yaml - Data sources now use k8s internal DNS - argocd/manifests/databases/service-metrics-tailscale.yaml - CNPG metrics endpoint - argocd/manifests/grafana-config/dashboards/configmap-postgresql.yaml - Updated to cnpg_* metrics - ansible/roles/alloy/defaults/main.yml - Push to k8s Tailscale endpoints - pulumi/policy.hujson - ACL for port 9187 - Deleted ansible/roles/prometheus/ and ansible/roles/loki/ Deployment and Testing - Stop prometheus and loki on indri - Sync ArgoCD apps (apps, prometheus, loki, grafana) - Run mise run provision-indri -- --tags alloy - Verify Grafana dashboards show data 🤖 Generated with https://claude.ai/claude-code Reviewed-on: https://forge.tail8d86e.ts.net/eblume/blumeops/pulls/42
2026-01-22 12:06:02 -08:00
printf "%-20s %-12s %-12s %s\n" "NAME" "SYNC" "HEALTH" "TARGET"
while read -r name sync health target; do
if [[ "$sync" == "Synced" ]]; then
printf "%-20s ${GREEN}%-12s${NC} %-12s %s\n" "$name" "$sync" "$health" "$target"
elif [[ "$sync" == "OutOfSync" ]]; then
printf "%-20s ${RED}%-12s${NC} %-12s %s\n" "$name" "$sync" "$health" "$target"
else
printf "%-20s %-12s %-12s %s\n" "$name" "$sync" "$health" "$target"
fi
done < <(kubectl --context=minikube-indri get applications -n argocd --no-headers -o custom-columns='NAME:.metadata.name,SYNC:.status.sync.status,HEALTH:.status.health.status,TARGET:.spec.source.targetRevision' 2>/dev/null)
echo ""
if [ $FAILED -eq 0 ]; then
echo -e "${GREEN}All services healthy!${NC}"
exit 0
else
echo -e "${RED}Some services failed health check${NC}"
exit 1
fi