Merge branch 'apache:master' into master

.github/PULL_REQUEST_TEMPLATE

@@ -9,7 +9,7 @@ Thanks for sending a pull request!  Here are some tips for you:
   7. If you want to add a new configuration, please read the guideline first for naming configurations in
      'core/src/main/scala/org/apache/spark/internal/config/ConfigEntry.scala'.
   8. If you want to add or modify an error type or message, please read the guideline first in
-     'core/src/main/resources/error/README.md'.
+     'common/utils/src/main/resources/error/README.md'.
 -->
 
 ### What changes were proposed in this pull request?

.github/labeler.yml

@@ -21,7 +21,6 @@ INFRA:
   - changed-files:
     - any-glob-to-any-file: [
      '.github/**/*',
-     'appveyor.yml',
      'tools/**/*',
      'dev/create-release/**/*',
      '.asf.yaml',
@@ -102,6 +101,8 @@ SQL:
     ]
     - any-glob-to-any-file: [
      'common/unsafe/**/*',
+     'common/sketch/**/*',
+     'common/variant/**/*',
      'bin/spark-sql*',
      'bin/beeline*',
      'sbin/*thriftserver*.sh',
@@ -128,8 +129,11 @@ DSTREAM:
     - any-glob-to-any-file: [
      'streaming/**/*',
      'data/streaming/**/*',
-     'connector/kinesis*',
-     'connector/kafka*',
+     'connector/kinesis-asl/**/*',
+     'connector/kinesis-asl-assembly/**/*',
+     'connector/kafka-0-10/**/*',
+     'connector/kafka-0-10-assembly/**/*',
+     'connector/kafka-0-10-token-provider/**/*',
      'python/pyspark/streaming/**/*'
     ]
 

.github/workflows/benchmark.yml

@@ -46,7 +46,7 @@ on:
 jobs:
   matrix-gen:
     name: Generate matrix for job splits
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-latest
     outputs:
       matrix: ${{ steps.set-matrix.outputs.matrix }}
     env:
@@ -69,27 +69,26 @@ jobs:
         # In order to get diff files
         with:
           fetch-depth: 0
-      - name: Cache Scala, SBT and Maven
-        uses: actions/cache@v3
+      - name: Cache SBT and Maven
+        uses: actions/cache@v4
         with:
           path: |
             build/apache-maven-*
-            build/scala-*
             build/*.jar
             ~/.sbt
           key: build-${{ hashFiles('**/pom.xml', 'project/build.properties', 'build/mvn', 'build/sbt', 'build/sbt-launch-lib.bash', 'build/spark-build-info') }}
           restore-keys: |
             build-
       - name: Cache Coursier local repository
-        uses: actions/cache@v3
+        uses: actions/cache@v4
         with:
           path: ~/.cache/coursier
           key: benchmark-coursier-${{ github.event.inputs.jdk }}-${{ hashFiles('**/pom.xml', '**/plugins.sbt') }}
           restore-keys: |
             benchmark-coursier-${{ github.event.inputs.jdk }}
       - name: Cache TPC-DS generated data
         id: cache-tpcds-sf-1
-        uses: actions/cache@v3
+        uses: actions/cache@v4
         with:
           path: ./tpcds-sf-1
           key: tpcds-${{ hashFiles('.github/workflows/benchmark.yml', 'sql/core/src/test/scala/org/apache/spark/sql/TPCDSSchema.scala') }}
@@ -117,8 +116,7 @@ jobs:
     name: "Run benchmarks: ${{ github.event.inputs.class }} (JDK ${{ github.event.inputs.jdk }}, Scala ${{ github.event.inputs.scala }}, ${{ matrix.split }} out of ${{ github.event.inputs.num-splits }} splits)"
     if: always()
     needs: [matrix-gen, tpcds-1g-gen]
-    # Ubuntu 20.04 is the latest LTS. The next LTS is 22.04.
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-latest
     strategy:
       fail-fast: false
       matrix:
@@ -138,19 +136,18 @@ jobs:
       # In order to get diff files
       with:
         fetch-depth: 0
-    - name: Cache Scala, SBT and Maven
-      uses: actions/cache@v3
+    - name: Cache SBT and Maven
+      uses: actions/cache@v4
       with:
         path: |
           build/apache-maven-*
-          build/scala-*
           build/*.jar
           ~/.sbt
         key: build-${{ hashFiles('**/pom.xml', 'project/build.properties', 'build/mvn', 'build/sbt', 'build/sbt-launch-lib.bash', 'build/spark-build-info') }}
         restore-keys: |
           build-
     - name: Cache Coursier local repository
-      uses: actions/cache@v3
+      uses: actions/cache@v4
       with:
         path: ~/.cache/coursier
         key: benchmark-coursier-${{ github.event.inputs.jdk }}-${{ hashFiles('**/pom.xml', '**/plugins.sbt') }}
@@ -164,7 +161,7 @@ jobs:
     - name: Cache TPC-DS generated data
       if: contains(github.event.inputs.class, 'TPCDSQueryBenchmark') || contains(github.event.inputs.class, '*')
       id: cache-tpcds-sf-1
-      uses: actions/cache@v3
+      uses: actions/cache@v4
       with:
         path: ./tpcds-sf-1
         key: tpcds-${{ hashFiles('.github/workflows/benchmark.yml', 'sql/core/src/test/scala/org/apache/spark/sql/TPCDSSchema.scala') }}