Erich Blume
f1620abb17
Replace single aggregate camera_fps check with per-camera FPS validation and NFS storage accessibility check. Motivated by an outage where Frigate API responded OK but NFS mount was inaccessible, causing "no frames" in UI. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
148 lines
7.4 KiB
Bash
Executable file
148 lines
7.4 KiB
Bash
Executable file
#!/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'
|
|
NC='\033[0m' # No Color
|
|
|
|
FAILED=0
|
|
|
|
check_service() {
|
|
local name="$1"
|
|
local check_cmd="$2"
|
|
|
|
printf "%-24s " "$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="$2"
|
|
|
|
printf "%-24s " "$name..."
|
|
if curl -sf --max-time 5 "$url" > /dev/null 2>&1; then
|
|
echo -e "${GREEN}OK${NC}"
|
|
else
|
|
echo -e "${RED}FAILED${NC}"
|
|
FAILED=1
|
|
fi
|
|
}
|
|
|
|
echo "Checking services..."
|
|
echo "===================="
|
|
echo ""
|
|
|
|
# Local services on indri
|
|
echo "Local services on indri:"
|
|
check_service "forgejo (brew)" "ssh indri 'brew services list | grep forgejo | grep started'"
|
|
check_service "alloy" "ssh indri 'launchctl list mcquack.eblume.alloy | grep -v \"^-\"'"
|
|
check_service "borgmatic" "ssh indri 'launchctl list mcquack.eblume.borgmatic | grep -v \"^-\"'"
|
|
check_service "borgmatic-metrics" "ssh indri 'launchctl list mcquack.borgmatic-metrics | grep -v \"^-\"'"
|
|
check_service "zot" "ssh indri 'launchctl list mcquack.eblume.zot | grep -v \"^-\"'"
|
|
check_service "zot-metrics" "ssh indri 'launchctl list mcquack.zot-metrics | grep -v \"^-\"'"
|
|
check_service "minikube-metrics" "ssh indri 'launchctl list mcquack.minikube-metrics | grep -v \"^-\"'"
|
|
check_service "jellyfin-metrics" "ssh indri 'launchctl list mcquack.eblume.jellyfin-metrics | grep -v \"^-\"'"
|
|
|
|
echo ""
|
|
echo "Metrics textfiles:"
|
|
check_service "borgmatic.prom" "ssh indri 'test -f /opt/homebrew/var/node_exporter/textfile/borgmatic.prom'"
|
|
check_service "zot.prom" "ssh indri 'test -f /opt/homebrew/var/node_exporter/textfile/zot.prom'"
|
|
check_service "minikube.prom" "ssh indri 'test -f /opt/homebrew/var/node_exporter/textfile/minikube.prom'"
|
|
check_service "jellyfin.prom" "ssh indri 'test -f /opt/homebrew/var/node_exporter/textfile/jellyfin.prom'"
|
|
|
|
echo ""
|
|
echo "Kubernetes cluster:"
|
|
check_service "minikube" "ssh indri 'minikube status --format={{.Host}} | grep -q Running'"
|
|
check_service "k8s-apiserver (indri)" "ssh indri 'kubectl get --raw /healthz'"
|
|
check_service "k8s-apiserver (remote)" "kubectl --kubeconfig=$HOME/.kube/minikube-indri/config.yml --context=minikube-indri get --raw /healthz"
|
|
|
|
echo ""
|
|
echo "HTTP endpoints (via Caddy):"
|
|
check_http "Prometheus" "https://prometheus.ops.eblu.me/-/healthy"
|
|
check_http "Loki" "https://loki.ops.eblu.me/ready"
|
|
check_http "Grafana" "https://grafana.ops.eblu.me/api/health"
|
|
check_http "ArgoCD" "https://argocd.ops.eblu.me/healthz"
|
|
check_http "Forgejo" "https://forge.eblu.me/"
|
|
check_http "Zot Registry" "https://registry.ops.eblu.me/v2/_catalog"
|
|
check_http "Kiwix" "https://kiwix.ops.eblu.me/"
|
|
check_http "Miniflux" "https://feed.ops.eblu.me/healthcheck"
|
|
check_http "TeslaMate" "https://tesla.ops.eblu.me/"
|
|
check_http "Devpi" "https://pypi.ops.eblu.me/+api"
|
|
check_http "Transmission" "https://torrent.ops.eblu.me/"
|
|
check_http "Immich" "https://photos.ops.eblu.me/"
|
|
check_http "Navidrome" "https://dj.ops.eblu.me/"
|
|
check_http "CV" "https://cv.ops.eblu.me/"
|
|
check_http "Ntfy" "https://ntfy.ops.eblu.me/v1/health"
|
|
check_http "Authentik" "https://authentik.ops.eblu.me/-/health/live/"
|
|
check_http "Frigate" "https://nvr.ops.eblu.me/api/version"
|
|
check_service "frigate-camera-fps" "curl -sf --max-time 5 https://nvr.ops.eblu.me/api/stats | jq -e '.cameras | to_entries | all(.value.camera_fps > 0)'"
|
|
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)'"
|
|
check_http "JobSync" "https://jobsync.ops.eblu.me/"
|
|
|
|
echo ""
|
|
echo "Ringtail (NixOS):"
|
|
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'"
|
|
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 "Ringtail k3s pods:"
|
|
check_service "ntfy" "kubectl --context=k3s-ringtail -n ntfy get pods -l app=ntfy -o jsonpath='{.items[0].status.phase}' | grep -q Running"
|
|
check_service "authentik" "kubectl --context=k3s-ringtail -n authentik get pods -l component=server -o jsonpath='{.items[0].status.phase}' | grep -q Running"
|
|
check_service "frigate" "kubectl --context=k3s-ringtail -n frigate get pods -l app=frigate -o jsonpath='{.items[0].status.phase}' | grep -q Running"
|
|
check_service "frigate-notify" "kubectl --context=k3s-ringtail -n frigate get pods -l app=frigate-notify -o jsonpath='{.items[0].status.phase}' | grep -q Running"
|
|
check_service "nvidia-device-plugin" "kubectl --context=k3s-ringtail -n nvidia-device-plugin get pods -l app=nvidia-device-plugin -o jsonpath='{.items[0].status.phase}' | grep -q Running"
|
|
check_service "jobsync" "kubectl --context=k3s-ringtail -n jobsync get pods -l app=jobsync -o jsonpath='{.items[0].status.phase}' | grep -q Running"
|
|
|
|
echo ""
|
|
echo "Public services (via Fly.io):"
|
|
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"
|
|
|
|
echo ""
|
|
echo "Database:"
|
|
check_service "PostgreSQL (k8s)" "pg_isready -h pg.ops.eblu.me -p 5432"
|
|
|
|
echo ""
|
|
echo "Indri minikube pods:"
|
|
check_service "prometheus-0" "kubectl --context=minikube-indri -n monitoring get pod prometheus-0 -o jsonpath='{.status.phase}' | grep -q Running"
|
|
check_service "loki-0" "kubectl --context=minikube-indri -n monitoring get pod loki-0 -o jsonpath='{.status.phase}' | grep -q Running"
|
|
check_service "grafana" "kubectl --context=minikube-indri -n monitoring get pods -l app.kubernetes.io/name=grafana -o jsonpath='{.items[0].status.phase}' | grep -q Running"
|
|
check_service "miniflux" "kubectl --context=minikube-indri -n miniflux get pods -l app=miniflux -o jsonpath='{.items[0].status.phase}' | grep -q Running"
|
|
check_service "teslamate" "kubectl --context=minikube-indri -n teslamate get pods -l app=teslamate -o jsonpath='{.items[0].status.phase}' | grep -q Running"
|
|
check_service "blumeops-pg" "kubectl --context=minikube-indri -n databases get pods -l cnpg.io/cluster=blumeops-pg -o jsonpath='{.items[0].status.phase}' | grep -q Running"
|
|
|
|
echo ""
|
|
echo "ArgoCD app sync status:"
|
|
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"
|
|
FAILED=1
|
|
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
|