fix: increase deploy health check timeout and reduce start_period

.github/workflows/deploy.yml

@@ -134,17 +134,17 @@ jobs:
         run: |
           DEPLOY_COLOR=$(ssh -i ~/.ssh/deploy_key root@"${{ steps.vps.outputs.ip }}" \
             "cat /opt/rustyip/.active_color")
-          for i in $(seq 1 15); do
+          for i in $(seq 1 30); do
             status=$(ssh -i ~/.ssh/deploy_key root@"${{ steps.vps.outputs.ip }}" \
               "docker inspect --format='{{ '{{' }}.State.Health.Status{{ '}}' }}' rustyip-app-${DEPLOY_COLOR}" 2>/dev/null)
             if [ "$status" = "healthy" ]; then
               echo "Deployment verified: app-${DEPLOY_COLOR} is healthy"
               exit 0
             fi
-            echo "Waiting for health check... (attempt $i/15)"
+            echo "Waiting for health check... (attempt $i/30)"
             sleep 4
           done
-          echo "Health check failed after 60 seconds"
+          echo "Health check failed after 120 seconds"
           exit 1
 
       # ---- Cleanup ----

deploy/ansible/roles/app/tasks/main.yml

@@ -110,7 +110,7 @@
 
 - name: Wait for target container health check (first deploy)
   ansible.builtin.shell: |
-    for i in $(seq 1 30); do
+    for i in $(seq 1 60); do
       status=$(docker inspect --format='{% raw %}{{.State.Health.Status}}{% endraw %}' "rustyip-app-{{ deploy_target }}" 2>/dev/null)
       if [ "$status" = "healthy" ]; then
         echo "healthy"
@@ -152,7 +152,7 @@
 
     - name: Wait for standby container health check
       ansible.builtin.shell: |
-        for i in $(seq 1 30); do
+        for i in $(seq 1 60); do
           status=$(docker inspect --format='{% raw %}{{.State.Health.Status}}{% endraw %}' "rustyip-app-{{ deploy_target }}" 2>/dev/null)
           if [ "$status" = "healthy" ]; then
             echo "healthy"

deploy/ansible/roles/app/templates/docker-compose.yml.j2

@@ -29,7 +29,7 @@ services:
       interval: 5s
       timeout: 3s
       retries: 3
-      start_period: 15s
+      start_period: 5s
     restart: unless-stopped
     ulimits:
       nofile:
@@ -49,7 +49,7 @@ services:
       interval: 5s
       timeout: 3s
       retries: 3
-      start_period: 15s
+      start_period: 5s
     restart: unless-stopped
     ulimits:
       nofile: