From 1ece1fac9f1375ca64327a171b99aad5647808c4 Mon Sep 17 00:00:00 2001
From: Tian Gao <gaogaotiantian@hotmail.com>
Date: Tue, 30 Jun 2026 15:50:16 -0700
Subject: [PATCH] [SPARK-57791][4.0][INFRA] Backport CI precompile artifact
 sharing, Coursier cache unification, and zstd in CI images

This backports the CI build-time optimization series to branch-4.0,
combining the work that landed on branch-4.1 as #56798 (precompile
artifact sharing + unified Coursier cache) and #56911 (install zstd in
the CI container images).

build_and_test.yml: a precompile job builds Spark once with SBT and
publishes the compile output (target/ dirs, zstd-compressed) as an
artifact. The build, pyspark, sparkr, tpcds-1g, docker-integration-tests
and k8s-integration-tests jobs download and extract it, falling back to a
local SBT build when the precompile job is absent or fails. The
run-tests-driven jobs export SKIP_SCALA_BUILD to skip the local build.
Per-job Coursier caches are unified under a single ${{ runner.os }}-coursier
key, with the precompile job as the sole writer and all consumers
restore-only.

maven_test.yml: a precompile-maven job runs `clean install` once and
publishes target/ plus ~/.m2/.../spark as an artifact for the matrix
entries. Adapted for branch-4.0, which has no SPARK-51628 assembly-wipe:
the full target/ is shipped (including assembly), so the reuse path simply
skips the local `clean install` and needs no assembly rebuild for connect.
No macOS cache guards are added since SPARK-54466 is not on branch-4.0 and
the existing build job caches unconditionally.

python_macos_test.yml: branch-4.0's analog of branch-4.1's
python_hosted_runner_test.yml. A precompile job builds Spark with SBT on
macOS and publishes a macOS-distinct artifact that the matrix consumes.

dev/run-tests.py: guard build_apache_spark and build_spark_assembly_sbt
behind SKIP_SCALA_BUILD so the test run reuses the precompiled output.

Dockerfiles: install zstd in dev/infra/Dockerfile and the docs, lint,
sparkr, python-311 and pypy-310 images under dev/spark-test-image/, the
set the branch-4.0 scheduler builds. Without zstd the precompiled
artifact's `zstd -dc` extraction fails in the container jobs, and
actions/cache silently falls back to gzip and never restores
zstd-saved caches.

CI-only; no user-facing change.

Co-authored-by: Isaac
---
 .github/workflows/build_and_test.yml       | 263 +++++++++++++++++----
 .github/workflows/maven_test.yml           | 101 +++++++-
 .github/workflows/python_macos_test.yml    |  97 +++++++-
 dev/infra/Dockerfile                       |   1 +
 dev/run-tests.py                           |   6 +-
 dev/spark-test-image/docs/Dockerfile       |   1 +
 dev/spark-test-image/lint/Dockerfile       |   1 +
 dev/spark-test-image/pypy-310/Dockerfile   |   1 +
 dev/spark-test-image/python-311/Dockerfile |   3 +-
 dev/spark-test-image/sparkr/Dockerfile     |   1 +
 10 files changed, 424 insertions(+), 51 deletions(-)

diff --git a/.github/workflows/build_and_test.yml b/.github/workflows/build_and_test.yml
index cdd76673eb095..05aa487c7b847 100644
--- a/.github/workflows/build_and_test.yml
+++ b/.github/workflows/build_and_test.yml
@@ -223,8 +223,8 @@ jobs:
   # Build: build Spark and run the tests for specified modules.
   build:
     name: "Build modules: ${{ matrix.modules }} ${{ matrix.comment }}"
-    needs: precondition
-    if: fromJson(needs.precondition.outputs.required).build == 'true'
+    needs: [precondition, precompile]
+    if: (!cancelled()) && fromJson(needs.precondition.outputs.required).build == 'true'
     runs-on: ubuntu-latest
     timeout-minutes: 120
     strategy:
@@ -331,13 +331,14 @@ jobs:
         key: build-${{ 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@v4
+    - name: Restore Coursier local repository
+      uses: actions/cache/restore@v4
       with:
         path: ~/.cache/coursier
-        key: ${{ matrix.java }}-${{ matrix.hadoop }}-coursier-${{ hashFiles('**/pom.xml', '**/plugins.sbt') }}
+        key: ${{ runner.os }}-${{ matrix.java }}-${{ matrix.hadoop }}-coursier-${{ hashFiles('**/pom.xml', '**/plugins.sbt') }}
         restore-keys: |
-          ${{ matrix.java }}-${{ matrix.hadoop }}-coursier-
+          ${{ runner.os }}-${{ matrix.java }}-${{ matrix.hadoop }}-coursier-
+          ${{ runner.os }}-coursier-
     - name: Free up disk space
       run: |
         if [ -f ./dev/free_disk_space ]; then
@@ -362,6 +363,20 @@ jobs:
       run: |
         python3.11 -m pip install 'numpy>=1.20.0' pyarrow 'pandas==2.3.3' scipy unittest-xml-reporting 'lxml==4.9.4' 'grpcio==1.67.0' 'grpcio-status==1.67.0' 'protobuf==5.29.1'
         python3.11 -m pip list
+    - name: Download precompiled artifact
+      id: download-precompiled
+      if: needs.precompile.result == 'success'
+      continue-on-error: true
+      uses: actions/download-artifact@v4
+      with:
+        name: spark-compile-${{ inputs.branch }}-${{ github.run_id }}
+    - name: Extract precompiled artifact
+      id: extract-precompiled
+      if: steps.download-precompiled.outcome == 'success'
+      continue-on-error: true
+      run: |
+        zstd -dc compile-artifact.tar.zst | tar -xf -
+        rm compile-artifact.tar.zst
     # Run the tests.
     - name: Run tests
       env: ${{ fromJSON(inputs.envs) }}
@@ -372,9 +387,13 @@ jobs:
         # Hive "other tests" test needs larger metaspace size based on experiment.
         if [[ "$MODULES_TO_TEST" == "hive" ]] && [[ "$EXCLUDED_TAGS" == "org.apache.spark.tags.SlowHiveTest" ]]; then export METASPACE_SIZE=2g; fi
         # SPARK-46283: should delete the following env replacement after SPARK 3.x EOL
-        if [[ "$MODULES_TO_TEST" == *"streaming-kinesis-asl"* ]] && [[ "${{ inputs.branch }}" =~ ^branch-3 ]]; then 
+        if [[ "$MODULES_TO_TEST" == *"streaming-kinesis-asl"* ]] && [[ "${{ inputs.branch }}" =~ ^branch-3 ]]; then
           MODULES_TO_TEST=${MODULES_TO_TEST//streaming-kinesis-asl, /}
         fi
+        if [ "${{ steps.extract-precompiled.outcome }}" = "success" ]; then
+          export SKIP_SCALA_BUILD=true
+          echo "Reusing precompiled artifact, skipping local SBT build."
+        fi
         export SERIAL_SBT_TESTS=1
         ./dev/run-tests --parallelism 1 --modules "$MODULES_TO_TEST" --included-tags "$INCLUDED_TAGS" --excluded-tags "$EXCLUDED_TAGS"
     - name: Upload test results to report
@@ -485,8 +504,84 @@ jobs:
           cache-from: type=registry,ref=ghcr.io/apache/spark/apache-spark-github-action-image-pyspark-${{ env.PYSPARK_IMAGE_TO_TEST }}-cache:${{ inputs.branch }}
 
 
+  precompile:
+    needs: precondition
+    if: >-
+      (!cancelled()) && (
+        fromJson(needs.precondition.outputs.required).build == 'true' ||
+        fromJson(needs.precondition.outputs.required).pyspark == 'true' ||
+        fromJson(needs.precondition.outputs.required).pyspark-pandas == 'true' ||
+        fromJson(needs.precondition.outputs.required).sparkr == 'true' ||
+        fromJson(needs.precondition.outputs.required).docker-integration-tests == 'true' ||
+        fromJson(needs.precondition.outputs.required).k8s-integration-tests == 'true' ||
+        fromJson(needs.precondition.outputs.required).tpcds-1g == 'true')
+    name: "Precompile Spark"
+    runs-on: ubuntu-latest
+    timeout-minutes: 60
+    # Optional optimization: if this job fails or is cancelled, the pyspark
+    # matrix entries fall back to running the SBT build locally as before.
+    continue-on-error: true
+    env:
+      HADOOP_PROFILE: ${{ inputs.hadoop }}
+      HIVE_PROFILE: hive2.3
+      GITHUB_PREV_SHA: ${{ github.event.before }}
+    steps:
+    - name: Checkout Spark repository
+      uses: actions/checkout@v4
+      with:
+        fetch-depth: 0
+        repository: apache/spark
+        ref: ${{ inputs.branch }}
+    - name: Sync the current branch with the latest in Apache Spark
+      if: github.repository != 'apache/spark'
+      run: |
+        echo "APACHE_SPARK_REF=$(git rev-parse HEAD)" >> $GITHUB_ENV
+        git fetch https://github.com/$GITHUB_REPOSITORY.git ${GITHUB_REF#refs/heads/}
+        git -c user.name='Apache Spark Test Account' -c user.email='sparktestacc@gmail.com' merge --no-commit --progress --squash FETCH_HEAD
+        git -c user.name='Apache Spark Test Account' -c user.email='sparktestacc@gmail.com' commit -m "Merged commit" --allow-empty
+    - name: Cache SBT and Maven
+      uses: actions/cache@v4
+      with:
+        path: |
+          build/apache-maven-*
+          build/*.jar
+          ~/.sbt
+        key: build-${{ 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@v4
+      with:
+        path: ~/.cache/coursier
+        key: ${{ runner.os }}-coursier-${{ hashFiles('**/pom.xml', '**/plugins.sbt') }}
+        restore-keys: |
+          ${{ runner.os }}-coursier-
+    - name: Install Java ${{ inputs.java }}
+      uses: actions/setup-java@v4
+      with:
+        distribution: zulu
+        java-version: ${{ inputs.java }}
+    - name: Build Spark
+      run: |
+        ./build/sbt -Phadoop-3 -Pyarn -Pspark-ganglia-lgpl -Phadoop-cloud -Phive \
+          -Pkubernetes -Pjvm-profiler -Pkinesis-asl -Phive-thriftserver \
+          -Pdocker-integration-tests -Pkubernetes-integration-tests -Pvolcano \
+          Test/package streaming-kinesis-asl-assembly/assembly connect/assembly assembly/package
+    - name: Package compile output
+      run: |
+        find . -type d -name target -not -path './build/*' -not -path './.git/*' -print0 \
+          | tar --null -cf - -T - | zstd -c -T0 > compile-artifact.tar.zst
+        ls -lh compile-artifact.tar.zst
+    - name: Upload compile artifact
+      uses: actions/upload-artifact@v4
+      with:
+        name: spark-compile-${{ inputs.branch }}-${{ github.run_id }}
+        path: compile-artifact.tar.zst
+        retention-days: 1
+        if-no-files-found: error
+
   pyspark:
-    needs: [precondition, infra-image]
+    needs: [precondition, infra-image, precompile]
     # always run if pyspark == 'true', even infra-image is skip (such as non-master job)
     if: (!cancelled()) && (fromJson(needs.precondition.outputs.required).pyspark == 'true' || fromJson(needs.precondition.outputs.required).pyspark-pandas == 'true')
     name: "Build modules: ${{ matrix.modules }}"
@@ -573,13 +668,13 @@ jobs:
         key: build-${{ 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@v4
+    - name: Restore Coursier local repository
+      uses: actions/cache/restore@v4
       with:
         path: ~/.cache/coursier
-        key: pyspark-coursier-${{ hashFiles('**/pom.xml', '**/plugins.sbt') }}
+        key: ${{ runner.os }}-coursier-${{ hashFiles('**/pom.xml', '**/plugins.sbt') }}
         restore-keys: |
-          pyspark-coursier-
+          ${{ runner.os }}-coursier-
     - name: Free up disk space
       shell: 'script -q -e -c "bash {0}"'
       run: ./dev/free_disk_space_container
@@ -603,11 +698,29 @@ jobs:
       uses: conda-incubator/setup-miniconda@v3
       with:
         miniforge-version: latest
+    - name: Download precompiled artifact
+      id: download-precompiled
+      if: needs.precompile.result == 'success'
+      continue-on-error: true
+      uses: actions/download-artifact@v4
+      with:
+        name: spark-compile-${{ inputs.branch }}-${{ github.run_id }}
+    - name: Extract precompiled artifact
+      id: extract-precompiled
+      if: steps.download-precompiled.outcome == 'success'
+      continue-on-error: true
+      run: |
+        zstd -dc compile-artifact.tar.zst | tar -xf -
+        rm compile-artifact.tar.zst
     # Run the tests.
     - name: Run tests
       env: ${{ fromJSON(inputs.envs) }}
       shell: 'script -q -e -c "bash {0}"'
       run: |
+        if [ "${{ steps.extract-precompiled.outcome }}" = "success" ]; then
+          export SKIP_SCALA_BUILD=true
+          echo "Reusing precompiled artifact, skipping local SBT build."
+        fi
         if [[ "$MODULES_TO_TEST" == *"pyspark-errors"* ]]; then
           export PATH=$CONDA/bin:$PATH
           export SKIP_PACKAGING=false
@@ -645,7 +758,7 @@ jobs:
         path: "**/target/unit-tests.log"
 
   sparkr:
-    needs: [precondition, infra-image]
+    needs: [precondition, infra-image, precompile]
     # always run if sparkr == 'true', even infra-image is skip (such as non-master job)
     if: (!cancelled()) && fromJson(needs.precondition.outputs.required).sparkr == 'true'
     name: "Build modules: sparkr"
@@ -690,13 +803,13 @@ jobs:
         key: build-${{ hashFiles('**/pom.xml', 'project/build.properties', 'build/mvn', 'build/sbt', 'build/sbt-launch-lib.bash', 'build/spark-build-info') }}
         restore-keys: |
           build-
-    - name: Cache Coursier local repository
-      uses: actions/cache@v4
+    - name: Restore Coursier local repository
+      uses: actions/cache/restore@v4
       with:
         path: ~/.cache/coursier
-        key: sparkr-coursier-${{ hashFiles('**/pom.xml', '**/plugins.sbt') }}
+        key: ${{ runner.os }}-coursier-${{ hashFiles('**/pom.xml', '**/plugins.sbt') }}
         restore-keys: |
-          sparkr-coursier-
+          ${{ runner.os }}-coursier-
     - name: Free up disk space
       run: ./dev/free_disk_space_container
     - name: Install Java ${{ inputs.java }}
@@ -704,6 +817,20 @@ jobs:
       with:
         distribution: zulu
         java-version: ${{ inputs.java }}
+    - name: Download precompiled artifact
+      id: download-precompiled
+      if: needs.precompile.result == 'success'
+      continue-on-error: true
+      uses: actions/download-artifact@v4
+      with:
+        name: spark-compile-${{ inputs.branch }}-${{ github.run_id }}
+    - name: Extract precompiled artifact
+      id: extract-precompiled
+      if: steps.download-precompiled.outcome == 'success'
+      continue-on-error: true
+      run: |
+        zstd -dc compile-artifact.tar.zst | tar -xf -
+        rm compile-artifact.tar.zst
     - name: Run tests
       env: ${{ fromJSON(inputs.envs) }}
       run: |
@@ -711,6 +838,10 @@ jobs:
         # R issues at docker environment
         export TZ=UTC
         export _R_CHECK_SYSTEM_CLOCK_=FALSE
+        if [ "${{ steps.extract-precompiled.outcome }}" = "success" ]; then
+          export SKIP_SCALA_BUILD=true
+          echo "Reusing precompiled artifact, skipping local SBT build."
+        fi
         ./dev/run-tests --parallelism 1 --modules sparkr
     - name: Upload test results to report
       if: always()
@@ -811,13 +942,13 @@ jobs:
         key: build-${{ hashFiles('**/pom.xml', 'project/build.properties', 'build/mvn', 'build/sbt', 'build/sbt-launch-lib.bash', 'build/spark-build-info') }}
         restore-keys: |
           build-
-    - name: Cache Coursier local repository
-      uses: actions/cache@v4
+    - name: Restore Coursier local repository
+      uses: actions/cache/restore@v4
       with:
         path: ~/.cache/coursier
-        key: docs-coursier-${{ hashFiles('**/pom.xml', '**/plugins.sbt') }}
+        key: ${{ runner.os }}-coursier-${{ hashFiles('**/pom.xml', '**/plugins.sbt') }}
         restore-keys: |
-          docs-coursier-
+          ${{ runner.os }}-coursier-
     - name: Cache Maven local repository
       uses: actions/cache@v4
       with:
@@ -942,13 +1073,13 @@ jobs:
         key: build-${{ 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@v4
+    - name: Restore Coursier local repository
+      uses: actions/cache/restore@v4
       with:
         path: ~/.cache/coursier
-        key: docs-coursier-${{ hashFiles('**/pom.xml', '**/plugins.sbt') }}
+        key: ${{ runner.os }}-coursier-${{ hashFiles('**/pom.xml', '**/plugins.sbt') }}
         restore-keys: |
-          docs-coursier-
+          ${{ runner.os }}-coursier-
     - name: Cache Maven local repository
       uses: actions/cache@v4
       with:
@@ -1022,8 +1153,8 @@ jobs:
 
   # Any TPC-DS related updates on this job need to be applied to tpcds-1g-gen job of benchmark.yml as well
   tpcds-1g:
-    needs: precondition
-    if: fromJson(needs.precondition.outputs.required).tpcds-1g == 'true'
+    needs: [precondition, precompile]
+    if: (!cancelled()) && fromJson(needs.precondition.outputs.required).tpcds-1g == 'true'
     name: Run TPC-DS queries with SF=1
     runs-on: ubuntu-latest
     timeout-minutes: 120
@@ -1052,18 +1183,32 @@ jobs:
         key: build-${{ hashFiles('**/pom.xml', 'project/build.properties', 'build/mvn', 'build/sbt', 'build/sbt-launch-lib.bash', 'build/spark-build-info') }}
         restore-keys: |
           build-
-    - name: Cache Coursier local repository
-      uses: actions/cache@v4
+    - name: Restore Coursier local repository
+      uses: actions/cache/restore@v4
       with:
         path: ~/.cache/coursier
-        key: tpcds-coursier-${{ hashFiles('**/pom.xml', '**/plugins.sbt') }}
+        key: ${{ runner.os }}-coursier-${{ hashFiles('**/pom.xml', '**/plugins.sbt') }}
         restore-keys: |
-          tpcds-coursier-
+          ${{ runner.os }}-coursier-
     - name: Install Java ${{ inputs.java }}
       uses: actions/setup-java@v4
       with:
         distribution: zulu
         java-version: ${{ inputs.java }}
+    - name: Download precompiled artifact
+      id: download-precompiled
+      if: needs.precompile.result == 'success'
+      continue-on-error: true
+      uses: actions/download-artifact@v4
+      with:
+        name: spark-compile-${{ inputs.branch }}-${{ github.run_id }}
+    - name: Extract precompiled artifact
+      id: extract-precompiled
+      if: steps.download-precompiled.outcome == 'success'
+      continue-on-error: true
+      run: |
+        zstd -dc compile-artifact.tar.zst | tar -xf -
+        rm compile-artifact.tar.zst
     - name: Cache TPC-DS generated data
       id: cache-tpcds-sf-1
       uses: actions/cache@v4
@@ -1124,8 +1269,8 @@ jobs:
         path: "**/target/unit-tests.log"
 
   docker-integration-tests:
-    needs: precondition
-    if: fromJson(needs.precondition.outputs.required).docker-integration-tests == 'true'
+    needs: [precondition, precompile]
+    if: (!cancelled()) && fromJson(needs.precondition.outputs.required).docker-integration-tests == 'true'
     name: Run Docker integration tests
     runs-on: ubuntu-latest
     timeout-minutes: 120
@@ -1161,21 +1306,39 @@ jobs:
         key: build-${{ hashFiles('**/pom.xml', 'project/build.properties', 'build/mvn', 'build/sbt', 'build/sbt-launch-lib.bash', 'build/spark-build-info') }}
         restore-keys: |
           build-
-    - name: Cache Coursier local repository
-      uses: actions/cache@v4
+    - name: Restore Coursier local repository
+      uses: actions/cache/restore@v4
       with:
         path: ~/.cache/coursier
-        key: docker-integration-coursier-${{ hashFiles('**/pom.xml', '**/plugins.sbt') }}
+        key: ${{ runner.os }}-coursier-${{ hashFiles('**/pom.xml', '**/plugins.sbt') }}
         restore-keys: |
-          docker-integration-coursier-
+          ${{ runner.os }}-coursier-
     - name: Install Java ${{ inputs.java }}
       uses: actions/setup-java@v4
       with:
         distribution: zulu
         java-version: ${{ inputs.java }}
+    - name: Download precompiled artifact
+      id: download-precompiled
+      if: needs.precompile.result == 'success'
+      continue-on-error: true
+      uses: actions/download-artifact@v4
+      with:
+        name: spark-compile-${{ inputs.branch }}-${{ github.run_id }}
+    - name: Extract precompiled artifact
+      id: extract-precompiled
+      if: steps.download-precompiled.outcome == 'success'
+      continue-on-error: true
+      run: |
+        zstd -dc compile-artifact.tar.zst | tar -xf -
+        rm compile-artifact.tar.zst
     - name: Run tests
       env: ${{ fromJSON(inputs.envs) }}
       run: |
+        if [ "${{ steps.extract-precompiled.outcome }}" = "success" ]; then
+          export SKIP_SCALA_BUILD=true
+          echo "Reusing precompiled artifact, skipping local SBT build."
+        fi
         ./dev/run-tests --parallelism 1 --modules docker-integration-tests --included-tags org.apache.spark.tags.DockerTest
     - name: Upload test results to report
       if: always()
@@ -1191,8 +1354,8 @@ jobs:
         path: "**/target/unit-tests.log"
 
   k8s-integration-tests:
-    needs: precondition
-    if: fromJson(needs.precondition.outputs.required).k8s-integration-tests == 'true'
+    needs: [precondition, precompile]
+    if: (!cancelled()) && fromJson(needs.precondition.outputs.required).k8s-integration-tests == 'true'
     name: Run Spark on Kubernetes Integration test
     runs-on: ubuntu-latest
     timeout-minutes: 120
@@ -1220,13 +1383,13 @@ jobs:
           key: build-${{ hashFiles('**/pom.xml', 'project/build.properties', 'build/mvn', 'build/sbt', 'build/sbt-launch-lib.bash', 'build/spark-build-info') }}
           restore-keys: |
             build-
-      - name: Cache Coursier local repository
-        uses: actions/cache@v4
+      - name: Restore Coursier local repository
+        uses: actions/cache/restore@v4
         with:
           path: ~/.cache/coursier
-          key: k8s-integration-coursier-${{ hashFiles('**/pom.xml', '**/plugins.sbt') }}
+          key: ${{ runner.os }}-coursier-${{ hashFiles('**/pom.xml', '**/plugins.sbt') }}
           restore-keys: |
-            k8s-integration-coursier-
+            ${{ runner.os }}-coursier-
       - name: Free up disk space
         run: |
           if [ -f ./dev/free_disk_space ]; then
@@ -1237,6 +1400,20 @@ jobs:
         with:
           distribution: zulu
           java-version: ${{ inputs.java }}
+      - name: Download precompiled artifact
+        id: download-precompiled
+        if: needs.precompile.result == 'success'
+        continue-on-error: true
+        uses: actions/download-artifact@v4
+        with:
+          name: spark-compile-${{ inputs.branch }}-${{ github.run_id }}
+      - name: Extract precompiled artifact
+        id: extract-precompiled
+        if: steps.download-precompiled.outcome == 'success'
+        continue-on-error: true
+        run: |
+          zstd -dc compile-artifact.tar.zst | tar -xf -
+          rm compile-artifact.tar.zst
       - name: Install R
         run: |
           sudo apt update
diff --git a/.github/workflows/maven_test.yml b/.github/workflows/maven_test.yml
index 67813815d43b7..1fabe6c3e9cb1 100644
--- a/.github/workflows/maven_test.yml
+++ b/.github/workflows/maven_test.yml
@@ -47,9 +47,85 @@ on:
         type: string
         default: '{}'
 jobs:
+  # Precompile Spark with Maven once and publish target/ + ~/.m2/.../spark as
+  # an artifact for the matrix entries below to consume. Optional: any failure
+  # here degrades the matrix to its original local `clean install` path.
+  precompile-maven:
+    name: "Precompile Spark with Maven"
+    runs-on: ${{ inputs.os }}
+    # If this job fails or is cancelled, the matrix entries fall back to
+    # running `mvn clean install` locally as before.
+    continue-on-error: true
+    env:
+      HADOOP_PROFILE: ${{ inputs.hadoop }}
+      HIVE_PROFILE: hive2.3
+      SPARK_LOCAL_IP: localhost
+      GITHUB_PREV_SHA: ${{ github.event.before }}
+    steps:
+      - name: Checkout Spark repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          repository: apache/spark
+          ref: ${{ inputs.branch }}
+      - name: Sync the current branch with the latest in Apache Spark
+        if: github.repository != 'apache/spark'
+        run: |
+          echo "APACHE_SPARK_REF=$(git rev-parse HEAD)" >> $GITHUB_ENV
+          git fetch https://github.com/$GITHUB_REPOSITORY.git ${GITHUB_REF#refs/heads/}
+          git -c user.name='Apache Spark Test Account' -c user.email='sparktestacc@gmail.com' merge --no-commit --progress --squash FETCH_HEAD
+          git -c user.name='Apache Spark Test Account' -c user.email='sparktestacc@gmail.com' commit -m "Merged commit" --allow-empty
+      - name: Cache SBT and Maven
+        uses: actions/cache@v4
+        with:
+          path: |
+            build/apache-maven-*
+            build/*.jar
+            ~/.sbt
+          key: build-${{ hashFiles('**/pom.xml', 'project/build.properties', 'build/mvn', 'build/sbt', 'build/sbt-launch-lib.bash', 'build/spark-build-info') }}
+          restore-keys: |
+            build-
+      - name: Cache Maven local repository
+        uses: actions/cache@v4
+        with:
+          path: ~/.m2/repository
+          key: java${{ inputs.java }}-maven-${{ hashFiles('**/pom.xml') }}
+          restore-keys: |
+            java${{ inputs.java }}-maven-
+      - name: Install Java ${{ inputs.java }}
+        uses: actions/setup-java@v4
+        with:
+          distribution: zulu
+          java-version: ${{ inputs.java }}
+      - name: Build Spark with Maven
+        run: |
+          export MAVEN_OPTS="-Xss64m -Xmx4g -Xms4g -XX:ReservedCodeCacheSize=128m -Dorg.slf4j.simpleLogger.defaultLogLevel=WARN"
+          export MAVEN_CLI_OPTS="--no-transfer-progress"
+          export JAVA_VERSION=${{ inputs.java }}
+          ./build/mvn $MAVEN_CLI_OPTS -DskipTests -Pyarn -Pkubernetes -Pvolcano -Phive -Phive-thriftserver -Phadoop-cloud -Pjvm-profiler -Pspark-ganglia-lgpl -Pkinesis-asl -Djava.version=${JAVA_VERSION/-ea} clean install
+      - name: Package compile output
+        run: |
+          find . -type d -name target -not -path './build/*' -not -path './.git/*' -print0 \
+            | tar --null -cf - -T - | zstd -c -T0 > compile-target.tar.zst
+          if [ -d "$HOME/.m2/repository/org/apache/spark" ]; then
+            tar -C "$HOME/.m2/repository/org/apache" -cf - spark | zstd -c -T0 > compile-m2-spark.tar.zst
+          fi
+          ls -lh compile-target.tar.zst compile-m2-spark.tar.zst
+      - name: Upload compile artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: spark-maven-compile-${{ inputs.branch }}-java${{ inputs.java }}-${{ github.run_id }}
+          path: |
+            compile-target.tar.zst
+            compile-m2-spark.tar.zst
+          retention-days: 1
+          if-no-files-found: error
+
   # Build: build Spark and run the tests for specified modules using maven
   build:
     name: "Build modules using Maven: ${{ matrix.modules }} ${{ matrix.comment }}"
+    needs: precompile-maven
+    if: (!cancelled())
     runs-on: ${{ inputs.os }}
     timeout-minutes: 150
     strategy:
@@ -182,6 +258,25 @@ jobs:
         run: |
           python3.11 -m pip install 'numpy>=1.20.0' pyarrow 'pandas==2.3.3' scipy unittest-xml-reporting 'grpcio==1.67.0' 'grpcio-status==1.67.0' 'protobuf==5.29.1'
           python3.11 -m pip list
+      - name: Download precompiled artifact
+        id: download-precompiled
+        if: needs.precompile-maven.result == 'success'
+        continue-on-error: true
+        uses: actions/download-artifact@v4
+        with:
+          name: spark-maven-compile-${{ inputs.branch }}-java${{ matrix.java }}-${{ github.run_id }}
+      - name: Extract precompiled artifact
+        id: extract-precompiled
+        if: steps.download-precompiled.outcome == 'success'
+        continue-on-error: true
+        run: |
+          zstd -dc compile-target.tar.zst | tar -xf -
+          rm compile-target.tar.zst
+          if [ -f compile-m2-spark.tar.zst ]; then
+            mkdir -p "$HOME/.m2/repository/org/apache"
+            zstd -dc compile-m2-spark.tar.zst | tar -C "$HOME/.m2/repository/org/apache" -xf -
+            rm compile-m2-spark.tar.zst
+          fi
       # Run the tests.
       - name: Run tests
         env: ${{ fromJSON(inputs.envs) }}
@@ -192,7 +287,11 @@ jobs:
           export ENABLE_KINESIS_TESTS=0
           # Replace with the real module name, for example, connector#kafka-0-10 -> connector/kafka-0-10
           export TEST_MODULES=`echo "$MODULES_TO_TEST" | sed -e "s%#%/%g"`
-          ./build/mvn $MAVEN_CLI_OPTS -DskipTests -Pyarn -Pkubernetes -Pvolcano -Phive -Phive-thriftserver -Phadoop-cloud -Pjvm-profiler -Pspark-ganglia-lgpl -Pkinesis-asl -Djava.version=${JAVA_VERSION/-ea} clean install
+          if [ "${{ steps.extract-precompiled.outcome }}" = "success" ]; then
+            echo "Reusing precompiled artifact, skipping local Maven clean install."
+          else
+            ./build/mvn $MAVEN_CLI_OPTS -DskipTests -Pyarn -Pkubernetes -Pvolcano -Phive -Phive-thriftserver -Phadoop-cloud -Pjvm-profiler -Pspark-ganglia-lgpl -Pkinesis-asl -Djava.version=${JAVA_VERSION/-ea} clean install
+          fi
           if [[ "$INCLUDED_TAGS" != "" ]]; then
             ./build/mvn $MAVEN_CLI_OPTS -pl "$TEST_MODULES" -Pyarn -Pkubernetes -Pvolcano -Phive -Phive-thriftserver -Phadoop-cloud -Pjvm-profiler -Pspark-ganglia-lgpl -Pkinesis-asl -Djava.version=${JAVA_VERSION/-ea} -Dtest.include.tags="$INCLUDED_TAGS" test -fae
           elif [[ "$MODULES_TO_TEST" == "connect" ]]; then
diff --git a/.github/workflows/python_macos_test.yml b/.github/workflows/python_macos_test.yml
index bce464fe08260..de682ee36e53c 100644
--- a/.github/workflows/python_macos_test.yml
+++ b/.github/workflows/python_macos_test.yml
@@ -46,8 +46,79 @@ on:
         type: string
         default: '{}'
 jobs:
+  # Precompile Spark with SBT once and publish target/ as an artifact for the
+  # matrix entries below to consume. Optional: any failure here degrades the
+  # matrix to its original local SBT build path.
+  precompile:
+    name: "Precompile Spark"
+    runs-on: macos-15
+    # If this job fails or is cancelled, the matrix entries fall back to
+    # running the SBT build locally as before.
+    continue-on-error: true
+    env:
+      HADOOP_PROFILE: ${{ inputs.hadoop }}
+      HIVE_PROFILE: hive2.3
+      SPARK_LOCAL_IP: localhost
+      GITHUB_PREV_SHA: ${{ github.event.before }}
+    steps:
+      - name: Checkout Spark repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          repository: apache/spark
+          ref: ${{ inputs.branch }}
+      - name: Sync the current branch with the latest in Apache Spark
+        if: github.repository != 'apache/spark'
+        run: |
+          echo "APACHE_SPARK_REF=$(git rev-parse HEAD)" >> $GITHUB_ENV
+          git fetch https://github.com/$GITHUB_REPOSITORY.git ${GITHUB_REF#refs/heads/}
+          git -c user.name='Apache Spark Test Account' -c user.email='sparktestacc@gmail.com' merge --no-commit --progress --squash FETCH_HEAD
+          git -c user.name='Apache Spark Test Account' -c user.email='sparktestacc@gmail.com' commit -m "Merged commit" --allow-empty
+      - name: Cache SBT and Maven
+        uses: actions/cache@v4
+        with:
+          path: |
+            build/apache-maven-*
+            build/*.jar
+            ~/.sbt
+          key: build-${{ 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@v4
+        with:
+          path: ~/.cache/coursier
+          key: ${{ runner.os }}-coursier-${{ hashFiles('**/pom.xml', '**/plugins.sbt') }}
+          restore-keys: |
+            ${{ runner.os }}-coursier-
+      - name: Install Java ${{ inputs.java }}
+        uses: actions/setup-java@v4
+        with:
+          distribution: zulu
+          java-version: ${{ inputs.java }}
+      - name: Build Spark
+        run: |
+          ./build/sbt -Phadoop-3 -Pyarn -Pspark-ganglia-lgpl -Phadoop-cloud -Phive \
+            -Pkubernetes -Pjvm-profiler -Pkinesis-asl -Phive-thriftserver \
+            -Pdocker-integration-tests -Pvolcano \
+            Test/package streaming-kinesis-asl-assembly/assembly connect/assembly assembly/package
+      - name: Package compile output
+        run: |
+          find . -type d -name target -not -path './build/*' -not -path './.git/*' -print0 \
+            | tar --null -cf - -T - | zstd -c -T0 > compile-artifact.tar.zst
+          ls -lh compile-artifact.tar.zst
+      - name: Upload compile artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: spark-compile-macos-${{ inputs.branch }}-${{ github.run_id }}
+          path: compile-artifact.tar.zst
+          retention-days: 1
+          if-no-files-found: error
+
   build:
     name: "PySpark test on macos: ${{ matrix.modules }}"
+    needs: precompile
+    if: (!cancelled())
     runs-on: macos-15
     strategy:
       fail-fast: false
@@ -114,13 +185,13 @@ jobs:
           key: build-${{ 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@v4
+      - name: Restore Coursier local repository
+        uses: actions/cache/restore@v4
         with:
           path: ~/.cache/coursier
-          key: pyspark-coursier-${{ hashFiles('**/pom.xml', '**/plugins.sbt') }}
+          key: ${{ runner.os }}-coursier-${{ hashFiles('**/pom.xml', '**/plugins.sbt') }}
           restore-keys: |
-            pyspark-coursier-
+            ${{ runner.os }}-coursier-
       - name: Install Java ${{ matrix.java }}
         uses: actions/setup-java@v4
         with:
@@ -135,10 +206,28 @@ jobs:
           python${{matrix.python}} -m pip cache purge
       - name: List Python packages
         run: python${{matrix.python}} -m pip list
+      - name: Download precompiled artifact
+        id: download-precompiled
+        if: needs.precompile.result == 'success'
+        continue-on-error: true
+        uses: actions/download-artifact@v4
+        with:
+          name: spark-compile-macos-${{ inputs.branch }}-${{ github.run_id }}
+      - name: Extract precompiled artifact
+        id: extract-precompiled
+        if: steps.download-precompiled.outcome == 'success'
+        continue-on-error: true
+        run: |
+          zstd -dc compile-artifact.tar.zst | tar -xf -
+          rm compile-artifact.tar.zst
       # Run the tests.
       - name: Run tests
         env: ${{ fromJSON(inputs.envs) }}
         run: |
+          if [ "${{ steps.extract-precompiled.outcome }}" = "success" ]; then
+            export SKIP_SCALA_BUILD=true
+            echo "Reusing precompiled artifact, skipping local SBT build."
+          fi
           if [[ "$MODULES_TO_TEST" == *"pyspark-errors"* ]]; then
             export SKIP_PACKAGING=false
             echo "Python Packaging Tests Enabled!"
diff --git a/dev/infra/Dockerfile b/dev/infra/Dockerfile
index 8965802fcb75e..548389c2c437e 100644
--- a/dev/infra/Dockerfile
+++ b/dev/infra/Dockerfile
@@ -66,6 +66,7 @@ RUN apt-get update && apt-get install -y \
     software-properties-common \
     wget \
     zlib1g-dev \
+    zstd \
     && rm -rf /var/lib/apt/lists/*
 
 
diff --git a/dev/run-tests.py b/dev/run-tests.py
index eb760139f9b68..5425ccec2072e 100755
--- a/dev/run-tests.py
+++ b/dev/run-tests.py
@@ -642,7 +642,8 @@ def main():
         run_build_tests()
 
     # spark build
-    build_apache_spark(build_tool, extra_profiles)
+    if os.environ.get("SKIP_SCALA_BUILD", "false") != "true":
+        build_apache_spark(build_tool, extra_profiles)
 
     # backwards compatibility checks
     if build_tool == "sbt":
@@ -651,7 +652,8 @@ def main():
             detect_binary_inop_with_mima(extra_profiles)
         # Since we did not build assembly/package before running dev/mima, we need to
         # do it here because the tests still rely on it; see SPARK-13294 for details.
-        build_spark_assembly_sbt(extra_profiles, should_run_java_style_checks)
+        if os.environ.get("SKIP_SCALA_BUILD", "false") != "true":
+            build_spark_assembly_sbt(extra_profiles, should_run_java_style_checks)
 
     # run the test suites
     run_scala_tests(build_tool, extra_profiles, test_modules, excluded_tags, included_tags)
diff --git a/dev/spark-test-image/docs/Dockerfile b/dev/spark-test-image/docs/Dockerfile
index 6735795adef44..4e35a36f5095a 100644
--- a/dev/spark-test-image/docs/Dockerfile
+++ b/dev/spark-test-image/docs/Dockerfile
@@ -65,6 +65,7 @@ RUN apt-get update && apt-get install -y \
     software-properties-common \
     wget \
     zlib1g-dev \
+    zstd \
     && rm -rf /var/lib/apt/lists/*
 
 
diff --git a/dev/spark-test-image/lint/Dockerfile b/dev/spark-test-image/lint/Dockerfile
index 5c2157fc7258b..e25fdde691b55 100644
--- a/dev/spark-test-image/lint/Dockerfile
+++ b/dev/spark-test-image/lint/Dockerfile
@@ -58,6 +58,7 @@ RUN apt-get update && apt-get install -y \
     software-properties-common \
     wget \
     zlib1g-dev \
+    zstd \
     && rm -rf /var/lib/apt/lists/*
 
 RUN Rscript -e "install.packages(c('remotes', 'knitr', 'markdown', 'rmarkdown', 'testthat'), repos='https://cloud.r-project.org/')" \
diff --git a/dev/spark-test-image/pypy-310/Dockerfile b/dev/spark-test-image/pypy-310/Dockerfile
index 8461ed5bd4c9e..2a9f6538d50f7 100644
--- a/dev/spark-test-image/pypy-310/Dockerfile
+++ b/dev/spark-test-image/pypy-310/Dockerfile
@@ -58,6 +58,7 @@ RUN apt-get update && apt-get install -y \
     software-properties-common \
     wget \
     zlib1g-dev \
+    zstd \
     && apt-get autoremove --purge -y \
     && apt-get clean \
     && rm -rf /var/lib/apt/lists/*
diff --git a/dev/spark-test-image/python-311/Dockerfile b/dev/spark-test-image/python-311/Dockerfile
index 047e91077b71d..257ce34bcddc5 100644
--- a/dev/spark-test-image/python-311/Dockerfile
+++ b/dev/spark-test-image/python-311/Dockerfile
@@ -57,7 +57,8 @@ RUN apt-get update && apt-get install -y \
     tzdata \
     software-properties-common \
     wget \
-    zlib1g-dev
+    zlib1g-dev \
+    zstd
 
 # Install Python 3.11
 RUN add-apt-repository ppa:deadsnakes/ppa
diff --git a/dev/spark-test-image/sparkr/Dockerfile b/dev/spark-test-image/sparkr/Dockerfile
index 9b2d702fc2d63..26554d693a9c7 100644
--- a/dev/spark-test-image/sparkr/Dockerfile
+++ b/dev/spark-test-image/sparkr/Dockerfile
@@ -60,6 +60,7 @@ RUN apt-get update && apt-get install -y \
     software-properties-common \
     wget \
     zlib1g-dev \
+    zstd \
     && rm -rf /var/lib/apt/lists/*
 
 RUN echo 'deb https://cloud.r-project.org/bin/linux/ubuntu jammy-cran40/' >> /etc/apt/sources.list