improved container restart alert

Add cAdvisor container to the monitoring stack for container-level
metrics. Configure Alloy to scrape cAdvisor. Expand the README
Recommended Alerts section with exact PromQL/LogQL queries, thresholds,
and Grafana alert rule configuration for all five alerts.

README.md

@@ -46,7 +46,7 @@ graph TB
 
 ## Prerequisites
 
-- A VPS with SSH access
+- A VPS with SSH access (minimum 1 core, 3 GB RAM)
 - Domain `t-gstone.de` with DNS control
 - Git installed locally
 
@@ -56,6 +56,24 @@ Check your VPS OS:
 cat /etc/os-release
 ```
 
+### Swap (recommended)
+
+Check current memory and swap:
+
+```bash
+free -h
+```
+
+If swap shows `0B`, add a 2 GB swapfile to prevent OOM kills:
+
+```bash
+sudo fallocate -l 2G /swapfile
+sudo chmod 600 /swapfile
+sudo mkswap /swapfile
+sudo swapon /swapfile
+echo '/swapfile none swap sw 0 0' | sudo tee -a /etc/fstab
+```
+
 ## DNS Setup
 
 Create these A records pointing to your VPS IP:
@@ -312,15 +330,91 @@ or low cost, and Restic handles encryption + deduplication automatically. A cron
 
 ### Recommended Alerts
 
-Set these up in Grafana Cloud UI (**Alerting** -> **Alert rules**):
+Set these up in Grafana Cloud UI (**Alerting** -> **Alert rules** -> **New alert rule**). Choose **Grafana-managed rule**
+and select the appropriate data source (Prometheus or Loki).
 
-| Alert                | Condition                                                             | Severity |
+| Alert                | Condition                            | Severity |
-|----------------------|-----------------------------------------------------------------------|----------|
+|----------------------|--------------------------------------|----------|
-| Disk usage high      | `node_filesystem_avail_bytes` / `node_filesystem_size_bytes` < 0.2    | Critical |
+| Disk usage high      | Available disk < 20%                 | Critical |
-| Container restarting | Container restart count > 3 in 10 min                                 | Warning  |
+| Container restarting | Restart count > 3 in 10 min          | Warning  |
-| High memory usage    | `node_memory_MemAvailable_bytes` / `node_memory_MemTotal_bytes` < 0.1 | Warning  |
+| High memory usage    | Available memory < 10%               | Warning  |
-| High CPU usage       | `node_cpu_seconds_total` idle < 10% sustained 5 min                   | Warning  |
+| High CPU usage       | CPU usage > 90% sustained 5 min      | Warning  |
-| Nextcloud cron stale | No log line from `nextcloud-cron` in 15 min                           | Warning  |
+| Nextcloud cron stale | No cron log lines in 15 min          | Warning  |
+
+#### Disk usage high
+
+Fires when any filesystem drops below 20% free space.
+
+- **Data source:** Prometheus
+- **Query (A):**
+  ```promql
+  node_filesystem_avail_bytes{mountpoint="/"} / node_filesystem_size_bytes{mountpoint="/"} * 100
+  ```
+- **Expression (B):** Threshold — `A IS BELOW 20`
+- **Evaluate every:** `1m`
+- **Pending period (For):** `5m`
+- **Labels:** `severity: critical`
+
+#### Container restarting
+
+Fires when any container restarts more than 3 times in 10 minutes, indicating a crash loop.
+Detects both in-place restarts (`docker restart`) and ID-changing restarts (`docker compose down/up`).
+Requires cAdvisor (included in the monitoring stack).
+
+- **Data source:** Prometheus
+- **Query (A):**
+  ```promql
+  sum by (name) (changes(container_start_time_seconds{name!=""}[10m]))
+  +
+  count by (name) (count_over_time(container_start_time_seconds{name!=""}[10m])) - 1
+  ```
+- **Expression (B):** Threshold — `A IS ABOVE 3`
+- **Evaluate every:** `1m`
+- **Pending period (For):** `0s`
+- **Labels:** `severity: warning`
+
+#### High memory usage
+
+Fires when available memory drops below 10% of total.
+
+- **Data source:** Prometheus
+- **Query (A):**
+  ```promql
+  node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100
+  ```
+- **Expression (B):** Threshold — `A IS BELOW 10`
+- **Evaluate every:** `1m`
+- **Pending period (For):** `5m`
+- **Labels:** `severity: warning`
+
+#### High CPU usage
+
+Fires when average CPU usage exceeds 90% for 5 minutes.
+
+- **Data source:** Prometheus
+- **Query (A):**
+  ```promql
+  avg by (instance) (rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100
+  ```
+- **Expression (B):** Threshold — `A IS BELOW 10`
+- **Evaluate every:** `1m`
+- **Pending period (For):** `5m`
+- **Labels:** `severity: warning`
+
+#### Nextcloud cron stale
+
+Fires when no log output from the `nextcloud-cron` container appears for 15 minutes, indicating background jobs have stopped.
+
+- **Data source:** Loki
+- **Query (A):**
+  ```logql
+  count_over_time({container="/nextcloud-cron"}[15m])
+  ```
+- **Expression (B):** Threshold — `A IS BELOW 1`
+- **Alert condition:** also trigger on **No Data**
+- **Evaluate every:** `5m`
+- **Pending period (For):** `0s`
+- **Labels:** `severity: warning`
 
 ### Recommended Dashboards
 

caddy/Caddyfile

@@ -12,6 +12,11 @@ nextcloud.t-gstone.de {
 	reverse_proxy nextcloud-nginx:80
 
 	header Strict-Transport-Security "max-age=31536000; includeSubDomains; preload"
+	header Referrer-Policy "no-referrer"
+	header X-Content-Type-Options "nosniff"
+	header X-Frame-Options "SAMEORIGIN"
+	header X-Permitted-Cross-Domain-Policies "none"
+	header X-Robots-Tag "noindex, nofollow"
 
 	request_body {
 		max_size 10G

caddy/docker-compose.yml

@@ -3,6 +3,8 @@ services:
     image: caddy:2-alpine
     container_name: caddy
     restart: unless-stopped
+    depends_on:
+      - alloy
     ports:
       - "80:80"
       - "443:443"

gitea/docker-compose.yml

@@ -3,6 +3,8 @@ services:
     image: gitea/gitea:1.25.5-rootless
     container_name: gitea
     restart: unless-stopped
+    depends_on:
+      - alloy
     env_file: .env
     volumes:
       - ${DATA_ROOT}/gitea/data:/var/lib/gitea

monitoring/config.alloy

@@ -54,6 +54,18 @@ prometheus.scrape "node" {
   scrape_interval = "60s"
 }
 
+// ============================================================
+// cAdvisor container metrics -> Grafana Cloud Prometheus
+// ============================================================
+
+prometheus.scrape "cadvisor" {
+  targets    = [{"__address__" = "cadvisor:8080"}]
+  forward_to = [prometheus.remote_write.grafana_cloud.receiver]
+
+  scrape_interval = "60s"
+  metrics_path    = "/metrics"
+}
+
 prometheus.remote_write "grafana_cloud" {
   endpoint {
     url = env("GRAFANA_CLOUD_PROMETHEUS_URL")

monitoring/docker-compose.yml

@@ -16,7 +16,7 @@ services:
       - EXEC=0
       - IMAGES=0
       - INFO=0
-      - NETWORKS=0
+      - NETWORKS=1
       - NODES=0
       - PLUGINS=0
       - SERVICES=0
@@ -33,6 +33,29 @@ services:
         max-size: "10m"
         max-file: "3"
 
+  cadvisor:
+    image: gcr.io/cadvisor/cadvisor:v0.54.1
+    container_name: cadvisor
+    restart: unless-stopped
+    privileged: true
+    volumes:
+      - /var/run/docker.sock:/var/run/docker.sock:ro
+      - /run/containerd/containerd.sock:/run/containerd/containerd.sock:ro
+      - /sys:/sys:ro
+      - /var/lib/docker/:/var/lib/docker:ro
+    command:
+      - --docker_only=true
+      - --housekeeping_interval=30s
+      - --containerd=/run/containerd/containerd.sock
+      - --disable_metrics=cpu_topology,disk,diskIO,hugetlb,memory_numa,network,oom_event,percpu,perf_event,process,referenced_memory,resctrl,sched,tcp,udp
+    networks:
+      - monitoring
+    logging:
+      driver: json-file
+      options:
+        max-size: "10m"
+        max-file: "3"
+
   alloy:
     image: grafana/alloy:v1.14.1
     container_name: alloy

nextcloud/docker-compose.yml

@@ -20,6 +20,7 @@ services:
       - ./hooks/post-installation.sh:/docker-entrypoint-hooks.d/post-installation/post-installation.sh:ro
       - ./hooks/post-upgrade.sh:/docker-entrypoint-hooks.d/post-upgrade/post-upgrade.sh:ro
       - ./fpm-tuning.conf:/usr/local/etc/php-fpm.d/zz-tuning.conf:ro
+      - ./php-tuning.ini:/usr/local/etc/php/conf.d/zz-tuning.ini:ro
     networks:
       - nextcloud-internal
     logging:
@@ -56,6 +57,8 @@ services:
     image: postgres:17-alpine
     container_name: nextcloud-postgres
     restart: unless-stopped
+    depends_on:
+      - alloy
     env_file: .env
     volumes:
       - ${DATA_ROOT}/nextcloud/db:/var/lib/postgresql/data
@@ -76,6 +79,8 @@ services:
     image: redis:8-alpine
     container_name: nextcloud-redis
     restart: unless-stopped
+    depends_on:
+      - alloy
     command: redis-server --requirepass ${REDIS_PASSWORD}
     env_file: .env
     networks:

nextcloud/fpm-tuning.conf

@@ -1,7 +1,7 @@
 [www]
 pm = dynamic
-pm.max_children = 12
+pm.max_children = 5
-pm.start_servers = 4
+pm.start_servers = 2
-pm.min_spare_servers = 2
+pm.min_spare_servers = 1
-pm.max_spare_servers = 6
+pm.max_spare_servers = 3
 pm.max_requests = 500

nextcloud/nginx.conf

@@ -6,19 +6,30 @@ map $uri $nonce_uri {
     default "";
 }
 
+map $arg_v $asset_immutable {
+    "" "";
+    default ", immutable";
+}
+
 server {
     listen 80;
     server_name _;
 
-    client_max_body_size 10G;
+    include mime.types;
-    client_body_timeout 300s;
+    types {
-    fastcgi_buffers 64 4K;
+        application/javascript mjs;
+    }
 
     gzip on;
     gzip_vary on;
     gzip_comp_level 4;
     gzip_min_length 256;
-    gzip_types application/javascript application/json text/css text/plain text/xml application/xml image/svg+xml;
+    gzip_proxied any;
+    gzip_types text/plain text/css application/json application/javascript text/xml application/xml image/svg+xml;
+
+    client_max_body_size 10G;
+    client_body_timeout 300s;
+    fastcgi_buffers 64 4K;
 
     root /var/www/html;
     index index.php index.html /index.php$request_uri;
@@ -27,27 +38,18 @@ server {
     location ^~ /.well-known {
         location = /.well-known/carddav { return 301 /remote.php/dav/; }
         location = /.well-known/caldav  { return 301 /remote.php/dav/; }
-        location ^~ /.well-known        { return 301 /index.php$uri; }
+        location /.well-known/acme-challenge { try_files $uri $uri/ =404; }
+        location /.well-known/pki-validation { try_files $uri $uri/ =404; }
+        return 301 /index.php$request_uri;
     }
 
     # Deny access to internal paths
     location ~ ^/(?:build|tests|config|lib|3rdparty|templates|data)(?:$|/) { return 404; }
     location ~ ^/(?:\.|autotest|occ|issue|indie|db_|console)              { return 404; }
 
-    # Serve static files directly — only if file exists on disk
+    # PHP handling (must be before static file locations so that internal
-    location ~ \.(?:css|js|mjs|svg|gif|png|jpg|ico|wasm|tflite|map|ogg|flac)$ {
+    # redirects like /index.php/apps/theming/theme/dark.css match here
-        try_files $uri =404;
+    # instead of cycling back into the static file try_files)
-        expires 6M;
-        access_log off;
-    }
-
-    location ~ \.woff2?$ {
-        try_files $uri =404;
-        expires 7d;
-        access_log off;
-    }
-
-    # PHP handling
     location ~ \.php(?:$|/) {
         fastcgi_split_path_info ^(.+?\.php)(/.*)$;
         set $path_info $fastcgi_path_info;
@@ -60,10 +62,24 @@ server {
         fastcgi_param front_controller_active true;
         fastcgi_pass php-handler;
         fastcgi_intercept_errors on;
+        fastcgi_hide_header X-Powered-By;
         fastcgi_request_buffering off;
         fastcgi_max_temp_file_size 0;
     }
 
+    # Serve static files directly, fall through to PHP for dynamic assets (e.g. theming)
+    location ~ \.(?:css|js|mjs|svg|gif|ico|jpg|png|webp|wasm|tflite|map|ogg|flac|mp4|webm)$ {
+        try_files $uri /index.php$request_uri;
+        add_header Cache-Control "public, max-age=15778463$asset_immutable";
+        access_log off;
+    }
+
+    location ~ \.woff2?$ {
+        try_files $uri /index.php$request_uri;
+        expires 7d;
+        access_log off;
+    }
+
     # Default handler — route everything else through PHP front controller
     location / {
         rewrite ^ /index.php$request_uri last;

nextcloud/php-tuning.ini

@@ -0,0 +1,10 @@
+; OPcache tuning for Nextcloud
+opcache.interned_strings_buffer=16
+opcache.max_accelerated_files=10000
+opcache.revalidate_freq=60
+opcache.save_comments=1
+opcache.enable_file_override=1
+
+; APCu local cache
+apc.shm_size=64M
+apc.enable_cli=1