add restart tolerance

web/docker-compose.prod.yaml

@@ -20,6 +20,8 @@ services:
       timeout: 5s
       retries: 12
       start_period: 30s
+    restart: unless-stopped
+    stop_grace_period: 60s
     networks:
       - prodnet
 
@@ -54,7 +56,7 @@ services:
       database.migrations:
         condition: service_completed_successfully
       seaweedfs:
-        condition: service_started
+        condition: service_healthy
     build:
       context: ./backend
       dockerfile: API/API.Core/Dockerfile
@@ -79,6 +81,20 @@ services:
       SEAWEEDFS_ACCESS_KEY_ID: "${SEAWEEDFS_ACCESS_KEY_ID}"
       SEAWEEDFS_SECRET_ACCESS_KEY: "${SEAWEEDFS_SECRET_ACCESS_KEY}"
       SEAWEEDFS_BUCKET: "${SEAWEEDFS_BUCKET}"
+    healthcheck:
+      # The .NET runtime image carries bash but no HTTP client, so the probe speaks
+      # HTTP to /health over bash's /dev/tcp rather than adding curl to the image.
+      test:
+        [
+          "CMD",
+          "bash",
+          "-c",
+          'exec 3<>/dev/tcp/127.0.0.1/8080; printf "GET /health HTTP/1.1\r\nHost: localhost\r\nConnection: close\r\n\r\n" >&3; head -1 <&3 | grep -q " 200 "',
+        ]
+      interval: 15s
+      timeout: 5s
+      retries: 5
+      start_period: 30s
     restart: unless-stopped
     networks:
       - prodnet
@@ -97,6 +113,14 @@ services:
       S3_BUCKET: "${SEAWEEDFS_BUCKET}"
     volumes:
       - seaweedfsdata-prod:/data
+    healthcheck:
+      # Probes the S3 gateway, the one component api.core talks to; it comes up
+      # last, after the master, volume and filer servers are serving.
+      test: ["CMD", "curl", "-fsS", "-o", "/dev/null", "http://localhost:8333/status"]
+      interval: 15s
+      timeout: 5s
+      retries: 5
+      start_period: 20s
     restart: unless-stopped
     networks:
       - prodnet
@@ -107,7 +131,7 @@ services:
     container_name: prod-env-frontend
     depends_on:
       api.core:
-        condition: service_started
+        condition: service_healthy
     build:
       context: ./frontend
       dockerfile: Dockerfile
@@ -118,6 +142,14 @@ services:
       PORT: "5656"
       API_BASE_URL: "http://api.core:8080"
       SESSION_SECRET: "${SESSION_SECRET}"
+    healthcheck:
+      # /healthz answers from the Express server alone, so the frontend stays
+      # healthy while api.core is still starting and serves its own error states.
+      test: ["CMD", "wget", "--quiet", "--spider", "--tries=1", "http://127.0.0.1:5656/healthz"]
+      interval: 15s
+      timeout: 5s
+      retries: 5
+      start_period: 15s
     restart: unless-stopped
     networks:
       - prodnet

web/frontend/server.js

@@ -6,6 +6,12 @@ const app = express();
 app.use('/assets', express.static('build/client/assets', { immutable: true, maxAge: '1y' }));
 app.use(express.static('build/client', { maxAge: '1h' }));
 
+// Answers from Express alone so the container health check reports on this
+// process only, independent of whether the API is reachable yet.
+app.get('/healthz', (_req, res) => {
+    res.status(200).type('text/plain').send('ok');
+});
+
 const requestHandler = createRequestHandler({
     build: () => import('./build/server/index.js'),
 });