ci: refactor Spark workflow for DRY and robustness

1. Add explicit permissions (least privilege):
   - contents: read
   - checks: write (for test reports)
   - pull-requests: write (for PR comments)

2. Extract duplicate build steps into shared 'build-deps' job:
   - Eliminates duplication between spark-tests and spark-example
   - Build artifacts are uploaded and reused by dependent jobs
   - Reduces CI time and ensures consistency

3. Fix spark-example service startup verification:
   - Match robust approach from spark-tests job
   - Add explicit timeout and failure handling
   - Verify all services (master, volume, filer)
   - Include diagnostic logging on failure
   - Prevents silent failures and obscure errors

These changes improve maintainability, security, and reliability
of the Spark integration test workflow.

.github/workflows/spark-integration-tests.yml

@@ -19,11 +19,16 @@ on:
       - '.github/workflows/spark-integration-tests.yml'
   workflow_dispatch:
 
+permissions:
+  contents: read
+  checks: write
+  pull-requests: write
+
 jobs:
-  spark-tests:
-    name: Spark Integration Tests
+  build-deps:
+    name: Build SeaweedFS Dependencies
     runs-on: ubuntu-latest
-    timeout-minutes: 30
+    timeout-minutes: 15
     
     steps:
     - name: Checkout code
@@ -70,6 +75,37 @@ jobs:
         mvn clean install -DskipTests -Dgpg.skip=true
         echo "✓ HDFS3 client built"
 
+    - name: Upload build artifacts
+      uses: actions/upload-artifact@v4
+      with:
+        name: seaweedfs-build
+        path: |
+          docker/weed
+          ~/.m2/repository/com/seaweedfs
+        retention-days: 1
+
+  spark-tests:
+    name: Spark Integration Tests
+    runs-on: ubuntu-latest
+    needs: build-deps
+    timeout-minutes: 30
+    
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v4
+
+    - name: Set up JDK 11
+      uses: actions/setup-java@v4
+      with:
+        java-version: '11'
+        distribution: 'temurin'
+
+    - name: Download build artifacts
+      uses: actions/download-artifact@v4
+      with:
+        name: seaweedfs-build
+        path: .
+
     - name: Start SeaweedFS services
       working-directory: test/java/spark
       run: |
@@ -157,7 +193,7 @@ jobs:
   spark-example:
     name: Run Spark Example Application
     runs-on: ubuntu-latest
-    needs: spark-tests
+    needs: [build-deps, spark-tests]
     timeout-minutes: 20
     if: github.event_name == 'push' || github.event_name == 'workflow_dispatch'
     
@@ -170,38 +206,12 @@ jobs:
       with:
         java-version: '11'
         distribution: 'temurin'
-        cache: maven
 
-    - name: Set up Go
-      uses: actions/setup-go@v5
+    - name: Download build artifacts
+      uses: actions/download-artifact@v4
       with:
-        go-version: '1.24'
-
-    - name: Build SeaweedFS binary
-      run: |
-        echo "Building SeaweedFS binary..."
-        cd weed
-        go build -o ../docker/weed
-        cd ../docker
-        ls -la weed filer.toml entrypoint.sh
-        echo "✓ SeaweedFS binary built and ready for Docker build"
-
-    - name: Build SeaweedFS Java dependencies
-      run: |
-        echo "Building Java client..."
-        cd other/java/client
-        mvn clean install -DskipTests -Dgpg.skip=true
-        cd ../../..
-        
-        echo "Building HDFS2 client..."
-        cd other/java/hdfs2
-        mvn clean install -DskipTests -Dgpg.skip=true
-        cd ../../..
-        
-        echo "Building HDFS3 client..."
-        cd other/java/hdfs3
-        mvn clean install -DskipTests -Dgpg.skip=true
-        echo "✓ All Java dependencies built"
+        name: seaweedfs-build
+        path: .
 
     - name: Cache Apache Spark
       id: cache-spark
@@ -226,17 +236,29 @@ jobs:
     - name: Start SeaweedFS services
       working-directory: test/java/spark
       run: |
-        docker compose up -d
-        sleep 10
+        echo "Starting SeaweedFS with Docker Compose..."
+        docker compose up -d seaweedfs-master seaweedfs-volume seaweedfs-filer
         
-        # Wait for filer to be ready
-        for i in {1..20}; do
+        echo "Waiting for SeaweedFS filer to be ready..."
+        for i in {1..30}; do
           if curl -f http://localhost:8888/ > /dev/null 2>&1; then
-            echo "✓ SeaweedFS is ready"
+            echo "✓ SeaweedFS filer is ready!"
             break
           fi
+          if [ $i -eq 30 ]; then
+            echo "✗ SeaweedFS failed to start after 60 seconds"
+            docker compose logs
+            exit 1
+          fi
+          echo "Waiting... ($i/30)"
           sleep 2
         done
+        
+        # Verify all services
+        echo "Verifying SeaweedFS services..."
+        curl -f http://localhost:9333/cluster/status || exit 1
+        curl -f http://localhost:8888/ || exit 1
+        echo "✓ All SeaweedFS services are healthy"
 
     - name: Build project
       working-directory: test/java/spark