diff --git a/.github/workflows/velox_docker.yml b/.github/workflows/velox_docker.yml index c310d5298f12..644fe62b932e 100644 --- a/.github/workflows/velox_docker.yml +++ b/.github/workflows/velox_docker.yml @@ -68,17 +68,16 @@ jobs: if: ${{ steps.cache.outputs.cache-hit != 'true' }} run: | df -a + cd $GITHUB_WORKSPACE/ bash dev/ci-velox-buildstatic-centos-7.sh - - name: Upload Artifact Native - uses: actions/upload-artifact@v2 + - uses: actions/upload-artifact@v2 with: - path: ./cpp/build/releases/ name: velox-native-lib-centos-7-${{github.sha}} - - name: Upload Artifact Arrow Jar - uses: actions/upload-artifact@v2 + path: ./cpp/build/releases/ + - uses: actions/upload-artifact@v2 with: + name: arrow-jars-centos-7-${{github.sha}} path: /root/.m2/repository/org/apache/arrow/ - name: velox-arrow-jar-centos-7-${{github.sha}} run-tpc-test-ubuntu: needs: build-native-lib-centos-7 @@ -118,7 +117,7 @@ jobs: - name: Download All Arrow Jar Artifacts uses: actions/download-artifact@v2 with: - name: velox-arrow-jar-centos-7-${{github.sha}} + name: arrow-jars-centos-7-${{github.sha}} path: /root/.m2/repository/org/apache/arrow/ - name: Setup tzdata run: | @@ -189,7 +188,7 @@ jobs: - name: Download All Arrow Jar Artifacts uses: actions/download-artifact@v2 with: - name: velox-arrow-jar-centos-7-${{github.sha}} + name: arrow-jars-centos-7-${{github.sha}} path: /root/.m2/repository/org/apache/arrow/ - name: Update mirror list run: | @@ -274,7 +273,7 @@ jobs: - name: Download All Arrow Jar Artifacts uses: actions/download-artifact@v2 with: - name: velox-arrow-jar-centos-7-${{github.sha}} + name: arrow-jars-centos-7-${{github.sha}} path: /home/runner/.m2/repository/org/apache/arrow/ - name: Setup java and maven run: | @@ -386,7 +385,7 @@ jobs: - name: Download All Arrow Jar Artifacts uses: actions/download-artifact@v2 with: - name: velox-arrow-jar-centos-7-${{github.sha}} + name: arrow-jars-centos-7-${{github.sha}} path: /home/runner/.m2/repository/org/apache/arrow/ - name: Setup java and maven run: | @@ -479,7 +478,7 @@ jobs: - name: Download All Arrow Jar Artifacts uses: actions/download-artifact@v2 with: - name: velox-arrow-jar-centos-7-${{github.sha}} + name: arrow-jars-centos-7-${{github.sha}} path: /root/.m2/repository/org/apache/arrow/ - name: Update mirror list run: | @@ -546,7 +545,7 @@ jobs: - name: Download All Arrow Jar Artifacts uses: actions/download-artifact@v2 with: - name: velox-arrow-jar-centos-7-${{github.sha}} + name: arrow-jars-centos-7-${{github.sha}} path: /root/.m2/repository/org/apache/arrow/ - name: Setup tzdata run: | @@ -583,7 +582,7 @@ jobs: GLUTEN_IT_JVM_ARGS=-Xmx5G sbin/gluten-it.sh queries-compare \ --local --preset=velox-with-celeborn --benchmark-type=ds --error-on-memleak --off-heap-size=10g -s=1.0 --threads=8 --iterations=1 - build-native-lib-centos-8: + run-CPP-test-UDF-test: runs-on: ubuntu-20.04 container: ghcr.io/facebookincubator/velox-dev:centos8 steps: @@ -606,50 +605,37 @@ jobs: run: | df -a bash dev/ci-velox-buildshared-centos-8.sh - - uses: actions/upload-artifact@v2 - with: - name: velox-native-lib-centos-8-${{github.sha}} - path: ./cpp/build/releases/ - - uses: actions/upload-artifact@v2 - with: - name: udf-example-lib-centos-8-${{github.sha}} - path: ./cpp/build/velox/udf/examples/ - - uses: actions/upload-artifact@v2 - with: - name: benchmark-centos-8-${{github.sha}} - path: ./cpp/build/velox/benchmarks/ - - uses: actions/upload-artifact@v2 - with: - name: arrow-jars-centos-8-${{github.sha}} - path: /root/.m2/repository/org/apache/arrow/ + - name: Run CPP unit test + run: | + cd ./cpp/build && ctest -V + - name: Run CPP benchmark test + run: | + $MVN_CMD test -Pspark-3.5 -Pbackends-velox -pl backends-velox -am \ + -DtagsToInclude="org.apache.gluten.tags.GenerateExample" -Dtest=none -DfailIfNoTests=false -Dexec.skip + # This test depends on example.json generated by the above mvn test. + cd cpp/build/velox/benchmarks && sudo chmod +x ./generic_benchmark + ./generic_benchmark --run-example --with-shuffle --threads 1 --iterations 1 + - name: Run UDF test + run: | + # Depends on --build_example=ON. + $MVN_CMD test -Pspark-3.5 -Pbackends-velox -Piceberg -Pdelta -DtagsToExclude=None \ + -DtagsToInclude=org.apache.gluten.tags.UDFTest run-spark-test-spark32: - needs: build-native-lib-centos-8 + needs: build-native-lib-centos-7 runs-on: ubuntu-20.04 container: ghcr.io/facebookincubator/velox-dev:centos8 env: CCACHE_DIR: "${{ github.workspace }}/.ccache" steps: - uses: actions/checkout@v2 - - name: Download All Artifacts - uses: actions/download-artifact@v2 + - uses: actions/download-artifact@v2 with: - name: velox-native-lib-centos-8-${{github.sha}} + name: velox-native-lib-centos-7-${{github.sha}} path: ./cpp/build/releases - - name: Download UDF Example Lib - uses: actions/download-artifact@v2 + - uses: actions/download-artifact@v2 with: - name: udf-example-lib-centos-8-${{github.sha}} - path: ./cpp/build/velox/udf/examples/ - - name: Download Benchmark - uses: actions/download-artifact@v2 - with: - name: benchmark-centos-8-${{github.sha}} - path: ./cpp/build/velox/benchmarks/ - - name: Download Arrow Jars - uses: actions/download-artifact@v2 - with: - name: arrow-jars-centos-8-${{github.sha}} + name: arrow-jars-centos-7-${{github.sha}} path: /root/.m2/repository/org/apache/arrow/ - name: Update mirror list run: | @@ -693,23 +679,18 @@ jobs: run: | cd $GITHUB_WORKSPACE/ export SPARK_SCALA_VERSION=2.12 - $MVN_CMD clean install -Pspark-3.2 -Pspark-ut -Pbackends-velox -Pceleborn -Piceberg -Pdelta -DargLine="-Dspark.test.home=$GITHUB_WORKSPACE//shims/spark32/spark_home/" -DtagsToExclude=org.apache.spark.tags.ExtendedSQLTest,org.apache.gluten.tags.UDFTest,org.apache.gluten.tags.SkipTestTags && \ - $MVN_CMD test -Pspark-3.2 -Pbackends-velox -Piceberg -Pdelta -DtagsToExclude=None -DtagsToInclude=org.apache.gluten.tags.UDFTest + $MVN_CMD clean install -Pspark-3.2 -Pspark-ut -Pbackends-velox -Pceleborn -Piceberg \ + -Pdelta -DargLine="-Dspark.test.home=$GITHUB_WORKSPACE//shims/spark32/spark_home/" \ + -DtagsToExclude=org.apache.spark.tags.ExtendedSQLTest,org.apache.gluten.tags.UDFTest,org.apache.gluten.tags.SkipTestTags - name: Upload golden files if: failure() uses: actions/upload-artifact@v4 with: name: golden-files-spark32 path: /tmp/tpch-approved-plan/** - - name: Gluten CPP Benchmark Test - run: | - # This test depends on example.json generated by the above mvn test. - cd $GITHUB_WORKSPACE/cpp/build/velox/benchmarks && \ - sudo chmod +x ./generic_benchmark && \ - ./generic_benchmark --run-example --with-shuffle --threads 1 --iterations 1 run-spark-test-spark32-slow: - needs: build-native-lib-centos-8 + needs: build-native-lib-centos-7 runs-on: ubuntu-20.04 container: ghcr.io/facebookincubator/velox-dev:centos8 env: @@ -719,12 +700,12 @@ jobs: - name: Download All Artifacts uses: actions/download-artifact@v2 with: - name: velox-native-lib-centos-8-${{github.sha}} + name: velox-native-lib-centos-7-${{github.sha}} path: ./cpp/build/releases - name: Download Arrow Jars uses: actions/download-artifact@v2 with: - name: arrow-jars-centos-8-${{github.sha}} + name: arrow-jars-centos-7-${{github.sha}} path: /root/.m2/repository/org/apache/arrow/ - name: Update mirror list run: | @@ -759,7 +740,7 @@ jobs: $MVN_CMD clean install -Pspark-3.2 -Pspark-ut -Pbackends-velox -Pceleborn -Piceberg -Pdelta -DargLine="-Dspark.test.home=$GITHUB_WORKSPACE//shims/spark32/spark_home/" -DtagsToInclude=org.apache.spark.tags.ExtendedSQLTest run-spark-test-spark33: - needs: build-native-lib-centos-8 + needs: build-native-lib-centos-7 runs-on: ubuntu-20.04 container: ghcr.io/facebookincubator/velox-dev:centos8 env: @@ -769,17 +750,12 @@ jobs: - name: Download All Artifacts uses: actions/download-artifact@v2 with: - name: velox-native-lib-centos-8-${{github.sha}} + name: velox-native-lib-centos-7-${{github.sha}} path: ./cpp/build/releases - - name: Download UDF Example Lib - uses: actions/download-artifact@v2 - with: - name: udf-example-lib-centos-8-${{github.sha}} - path: ./cpp/build/velox/udf/examples/ - name: Download Arrow Jars uses: actions/download-artifact@v2 with: - name: arrow-jars-centos-8-${{github.sha}} + name: arrow-jars-centos-7-${{github.sha}} path: /root/.m2/repository/org/apache/arrow/ - name: Update mirror list run: | @@ -823,8 +799,9 @@ jobs: run: | cd $GITHUB_WORKSPACE/ export SPARK_SCALA_VERSION=2.12 - $MVN_CMD clean install -Pspark-3.3 -Pbackends-velox -Pceleborn -Piceberg -Pdelta -Pspark-ut -DargLine="-Dspark.test.home=$GITHUB_WORKSPACE//shims/spark33/spark_home/" -DtagsToExclude=org.apache.spark.tags.ExtendedSQLTest,org.apache.gluten.tags.UDFTest,org.apache.gluten.tags.SkipTestTags && \ - $MVN_CMD test -Pspark-3.3 -Pbackends-velox -Piceberg -Pdelta -DtagsToExclude=None -DtagsToInclude=org.apache.gluten.tags.UDFTest + $MVN_CMD clean install -Pspark-3.3 -Pbackends-velox -Pceleborn -Piceberg -Pdelta -Pspark-ut \ + -DargLine="-Dspark.test.home=$GITHUB_WORKSPACE//shims/spark33/spark_home/" \ + -DtagsToExclude=org.apache.spark.tags.ExtendedSQLTest,org.apache.gluten.tags.UDFTest,org.apache.gluten.tags.SkipTestTags - name: Upload golden files if: failure() uses: actions/upload-artifact@v4 @@ -834,7 +811,7 @@ jobs: run-spark-test-spark33-slow: - needs: build-native-lib-centos-8 + needs: build-native-lib-centos-7 runs-on: ubuntu-20.04 container: ghcr.io/facebookincubator/velox-dev:centos8 env: @@ -844,12 +821,12 @@ jobs: - name: Download All Artifacts uses: actions/download-artifact@v2 with: - name: velox-native-lib-centos-8-${{github.sha}} + name: velox-native-lib-centos-7-${{github.sha}} path: ./cpp/build/releases - name: Download Arrow Jars uses: actions/download-artifact@v2 with: - name: arrow-jars-centos-8-${{github.sha}} + name: arrow-jars-centos-7-${{github.sha}} path: /root/.m2/repository/org/apache/arrow/ - name: Update mirror list run: | @@ -881,10 +858,12 @@ jobs: - name: Build and Run unit test for Spark 3.3.1 (slow tests) run: | cd $GITHUB_WORKSPACE/ - $MVN_CMD clean install -Pspark-3.3 -Pbackends-velox -Pceleborn -Piceberg -Pdelta -Pspark-ut -DargLine="-Dspark.test.home=$GITHUB_WORKSPACE//shims/spark33/spark_home/" -DtagsToInclude=org.apache.spark.tags.ExtendedSQLTest + $MVN_CMD clean install -Pspark-3.3 -Pbackends-velox -Pceleborn -Piceberg -Pdelta -Pspark-ut \ + -DargLine="-Dspark.test.home=$GITHUB_WORKSPACE//shims/spark33/spark_home/" \ + -DtagsToInclude=org.apache.spark.tags.ExtendedSQLTest run-spark-test-spark34: - needs: build-native-lib-centos-8 + needs: build-native-lib-centos-7 runs-on: ubuntu-20.04 container: ghcr.io/facebookincubator/velox-dev:centos8 env: @@ -894,17 +873,12 @@ jobs: - name: Download All Artifacts uses: actions/download-artifact@v2 with: - name: velox-native-lib-centos-8-${{github.sha}} + name: velox-native-lib-centos-7-${{github.sha}} path: ./cpp/build/releases - - name: Download UDF Example Lib - uses: actions/download-artifact@v2 - with: - name: udf-example-lib-centos-8-${{github.sha}} - path: ./cpp/build/velox/udf/examples/ - name: Download Arrow Jars uses: actions/download-artifact@v2 with: - name: arrow-jars-centos-8-${{github.sha}} + name: arrow-jars-centos-7-${{github.sha}} path: /root/.m2/repository/org/apache/arrow/ - name: Update mirror list run: | @@ -948,8 +922,9 @@ jobs: run: | cd $GITHUB_WORKSPACE/ export SPARK_SCALA_VERSION=2.12 - $MVN_CMD clean install -Pspark-3.4 -Pbackends-velox -Pceleborn -Piceberg -Pdelta -Pspark-ut -DargLine="-Dspark.test.home=$GITHUB_WORKSPACE//shims/spark34/spark_home/" -DtagsToExclude=org.apache.spark.tags.ExtendedSQLTest,org.apache.gluten.tags.UDFTest,org.apache.gluten.tags.SkipTestTags && \ - $MVN_CMD test -Pspark-3.4 -Pbackends-velox -Piceberg -Pdelta -DtagsToExclude=None -DtagsToInclude=org.apache.gluten.tags.UDFTest + $MVN_CMD clean install -Pspark-3.4 -Pbackends-velox -Pceleborn -Piceberg -Pdelta -Pspark-ut \ + -DargLine="-Dspark.test.home=$GITHUB_WORKSPACE//shims/spark34/spark_home/" \ + -DtagsToExclude=org.apache.spark.tags.ExtendedSQLTest,org.apache.gluten.tags.UDFTest,org.apache.gluten.tags.SkipTestTags - name: Upload golden files if: failure() uses: actions/upload-artifact@v4 @@ -959,7 +934,7 @@ jobs: run-spark-test-spark34-slow: - needs: build-native-lib-centos-8 + needs: build-native-lib-centos-7 runs-on: ubuntu-20.04 container: ghcr.io/facebookincubator/velox-dev:centos8 env: @@ -969,12 +944,12 @@ jobs: - name: Download All Artifacts uses: actions/download-artifact@v2 with: - name: velox-native-lib-centos-8-${{github.sha}} + name: velox-native-lib-centos-7-${{github.sha}} path: ./cpp/build/releases - name: Download Arrow Jars uses: actions/download-artifact@v2 with: - name: arrow-jars-centos-8-${{github.sha}} + name: arrow-jars-centos-7-${{github.sha}} path: /root/.m2/repository/org/apache/arrow/ - name: Update mirror list run: | @@ -1006,10 +981,12 @@ jobs: - name: Build and Run unit test for Spark 3.4.2 (slow tests) run: | cd $GITHUB_WORKSPACE/ - $MVN_CMD clean install -Pspark-3.4 -Pbackends-velox -Pceleborn -Piceberg -Pdelta -Pspark-ut -DargLine="-Dspark.test.home=$GITHUB_WORKSPACE//shims/spark34/spark_home/" -DtagsToInclude=org.apache.spark.tags.ExtendedSQLTest + $MVN_CMD clean install -Pspark-3.4 -Pbackends-velox -Pceleborn -Piceberg -Pdelta -Pspark-ut \ + -DargLine="-Dspark.test.home=$GITHUB_WORKSPACE//shims/spark34/spark_home/" \ + -DtagsToInclude=org.apache.spark.tags.ExtendedSQLTest run-spark-test-spark35: - needs: build-native-lib-centos-8 + needs: build-native-lib-centos-7 runs-on: ubuntu-20.04 container: ghcr.io/facebookincubator/velox-dev:centos8 env: @@ -1019,17 +996,12 @@ jobs: - name: Download All Artifacts uses: actions/download-artifact@v2 with: - name: velox-native-lib-centos-8-${{github.sha}} + name: velox-native-lib-centos-7-${{github.sha}} path: ./cpp/build/releases - - name: Download UDF Example Lib - uses: actions/download-artifact@v2 - with: - name: udf-example-lib-centos-8-${{github.sha}} - path: ./cpp/build/velox/udf/examples/ - name: Download Arrow Jars uses: actions/download-artifact@v2 with: - name: arrow-jars-centos-8-${{github.sha}} + name: arrow-jars-centos-7-${{github.sha}} path: /root/.m2/repository/org/apache/arrow/ - name: Update mirror list run: | @@ -1073,8 +1045,9 @@ jobs: run: | cd $GITHUB_WORKSPACE/ export SPARK_SCALA_VERSION=2.12 - $MVN_CMD clean install -Pspark-3.5 -Pbackends-velox -Pceleborn -Piceberg -Pdelta -Pspark-ut -DargLine="-Dspark.test.home=$GITHUB_WORKSPACE//shims/spark35/spark_home/" -DtagsToExclude=org.apache.spark.tags.ExtendedSQLTest,org.apache.gluten.tags.UDFTest,org.apache.gluten.tags.SkipTestTags && \ - $MVN_CMD test -Pspark-3.5 -Pbackends-velox -Piceberg -Pdelta -DtagsToExclude=None -DtagsToInclude=org.apache.gluten.tags.UDFTest + $MVN_CMD clean install -Pspark-3.5 -Pbackends-velox -Pceleborn -Piceberg -Pdelta -Pspark-ut \ + -DargLine="-Dspark.test.home=$GITHUB_WORKSPACE//shims/spark35/spark_home/" \ + -DtagsToExclude=org.apache.spark.tags.ExtendedSQLTest,org.apache.gluten.tags.UDFTest,org.apache.gluten.tags.SkipTestTags - name: Upload golden files if: failure() uses: actions/upload-artifact@v4 @@ -1083,7 +1056,7 @@ jobs: path: /tmp/tpch-approved-plan/** run-spark-test-spark35-scala213: - needs: build-native-lib-centos-8 + needs: build-native-lib-centos-7 runs-on: ubuntu-20.04 container: ghcr.io/facebookincubator/velox-dev:centos8 env: @@ -1093,17 +1066,12 @@ jobs: - name: Download All Artifacts uses: actions/download-artifact@v2 with: - name: velox-native-lib-centos-8-${{github.sha}} + name: velox-native-lib-centos-7-${{github.sha}} path: ./cpp/build/releases - - name: Download UDF Example Lib - uses: actions/download-artifact@v2 - with: - name: udf-example-lib-centos-8-${{github.sha}} - path: ./cpp/build/velox/udf/examples/ - name: Download Arrow Jars uses: actions/download-artifact@v2 with: - name: arrow-jars-centos-8-${{github.sha}} + name: arrow-jars-centos-7-${{github.sha}} path: /root/.m2/repository/org/apache/arrow/ - name: Update mirror list run: | @@ -1147,11 +1115,12 @@ jobs: run: | cd $GITHUB_WORKSPACE/ export SPARK_SCALA_VERSION=2.13 - $MVN_CMD clean install -Pspark-3.5 -Pscala-2.13 -Pbackends-velox -Pceleborn -Piceberg -Pdelta -Pspark-ut -DargLine="-Dspark.test.home=$GITHUB_WORKSPACE//shims/spark35/spark_home/" -DtagsToExclude=org.apache.spark.tags.ExtendedSQLTest,org.apache.gluten.tags.UDFTest,org.apache.gluten.tags.SkipTestTags && \ - $MVN_CMD test -Pspark-3.5 -Pscala-2.13 -Pbackends-velox -Piceberg -Pdelta -DtagsToExclude=None -DtagsToInclude=org.apache.gluten.tags.UDFTest + $MVN_CMD clean install -Pspark-3.5 -Pscala-2.13 -Pbackends-velox -Pceleborn -Piceberg \ + -Pdelta -Pspark-ut -DargLine="-Dspark.test.home=$GITHUB_WORKSPACE//shims/spark35/spark_home/" \ + -DtagsToExclude=org.apache.spark.tags.ExtendedSQLTest,org.apache.gluten.tags.UDFTest,org.apache.gluten.tags.SkipTestTags run-spark-test-spark35-slow: - needs: build-native-lib-centos-8 + needs: build-native-lib-centos-7 runs-on: ubuntu-20.04 container: ghcr.io/facebookincubator/velox-dev:centos8 env: @@ -1161,12 +1130,12 @@ jobs: - name: Download All Artifacts uses: actions/download-artifact@v2 with: - name: velox-native-lib-centos-8-${{github.sha}} + name: velox-native-lib-centos-7-${{github.sha}} path: ./cpp/build/releases - name: Download Arrow Jars uses: actions/download-artifact@v2 with: - name: arrow-jars-centos-8-${{github.sha}} + name: arrow-jars-centos-7-${{github.sha}} path: /root/.m2/repository/org/apache/arrow/ - name: Update mirror list run: | @@ -1204,4 +1173,6 @@ jobs: - name: Build and Run unit test for Spark 3.5.1 (slow tests) run: | cd $GITHUB_WORKSPACE/ - $MVN_CMD clean install -Pspark-3.5 -Pbackends-velox -Pceleborn -Piceberg -Pdelta -Pspark-ut -DargLine="-Dspark.test.home=$GITHUB_WORKSPACE//shims/spark35/spark_home/" -DtagsToInclude=org.apache.spark.tags.ExtendedSQLTest + $MVN_CMD clean install -Pspark-3.5 -Pbackends-velox -Pceleborn -Piceberg -Pdelta -Pspark-ut \ + -DargLine="-Dspark.test.home=$GITHUB_WORKSPACE//shims/spark35/spark_home/" \ + -DtagsToInclude=org.apache.spark.tags.ExtendedSQLTest diff --git a/dev/ci-velox-buildshared-centos-8.sh b/dev/ci-velox-buildshared-centos-8.sh index 362900bd009a..f337185de379 100755 --- a/dev/ci-velox-buildshared-centos-8.sh +++ b/dev/ci-velox-buildshared-centos-8.sh @@ -10,9 +10,8 @@ yum install sudo patch java-1.8.0-openjdk-devel wget -y wget https://downloads.apache.org/maven/maven-3/3.8.8/binaries/apache-maven-3.8.8-bin.tar.gz tar -xvf apache-maven-3.8.8-bin.tar.gz && mv apache-maven-3.8.8 /usr/lib/maven export PATH="${PATH}:/usr/lib/maven/bin" +echo "PATH=${PATH}:/usr/lib/maven/bin" >> $GITHUB_ENV source /opt/rh/gcc-toolset-9/enable ./dev/builddeps-veloxbe.sh --run_setup_script=OFF --enable_ep_cache=OFF --build_tests=ON \ --build_examples=ON --build_benchmarks=ON --build_protobuf=ON - -cd ./cpp/build && ctest -V diff --git a/dev/ci-velox-buildstatic-centos-7.sh b/dev/ci-velox-buildstatic-centos-7.sh index d83d443fc489..3272de95d910 100755 --- a/dev/ci-velox-buildstatic-centos-7.sh +++ b/dev/ci-velox-buildstatic-centos-7.sh @@ -3,8 +3,6 @@ set -e source /opt/rh/devtoolset-9/enable -cd $GITHUB_WORKSPACE/ -source ./dev/vcpkg/env.sh export NUM_THREADS=4 -./dev/builddeps-veloxbe.sh --build_tests=OFF --build_benchmarks=OFF --build_arrow=OFF --enable_s3=ON \ - --enable_gcs=ON --enable_hdfs=ON --enable_abfs=ON +./dev/builddeps-veloxbe.sh --enable_vcpkg=ON --build_arrow=OFF --build_tests=OFF --build_benchmarks=OFF \ + --build_examples=OFF --enable_s3=ON --enable_gcs=ON --enable_hdfs=ON --enable_abfs=ON diff --git a/dev/vcpkg/ports/simdjson/vcpkg.json b/dev/vcpkg/ports/simdjson/vcpkg.json index 6e46382e42f8..2b74be554cfc 100644 --- a/dev/vcpkg/ports/simdjson/vcpkg.json +++ b/dev/vcpkg/ports/simdjson/vcpkg.json @@ -17,8 +17,7 @@ "default-features": [ "deprecated", "exceptions", - "threads", - "utf8-validation" + "threads" ], "features": { "deprecated": { diff --git a/docs/developers/UsingGperftoolsInCH.md b/docs/developers/UsingGperftoolsInCH.md index f0d5c720b30b..5a4bbea3fbbc 100644 --- a/docs/developers/UsingGperftoolsInCH.md +++ b/docs/developers/UsingGperftoolsInCH.md @@ -1,3 +1,10 @@ +--- +layout: page +title: Debug for CH Backend with gpertools Tool +nav_order: 11 +has_children: true +parent: /developer-overview/ +--- We need using gpertools to find the memory or CPU issue. That's what this document is about. ## Install gperftools diff --git a/docs/developers/UsingJemallocWithCH.md b/docs/developers/UsingJemallocWithCH.md index 626f7522d7c8..365a35dd39fe 100644 --- a/docs/developers/UsingJemallocWithCH.md +++ b/docs/developers/UsingJemallocWithCH.md @@ -1,3 +1,10 @@ +--- +layout: page +title: Use Jemalloc for CH Backend +nav_order: 12 +has_children: true +parent: /developer-overview/ +--- We need using jemalloc to find the memory issue. That's what this document is about. ## Change code of jemalloc diff --git a/docs/developers/VeloxUDF.md b/docs/developers/VeloxUDF.md index 25b896929a43..6872f2d0c841 100644 --- a/docs/developers/VeloxUDF.md +++ b/docs/developers/VeloxUDF.md @@ -1,3 +1,10 @@ +--- +layout: page +title: Velox UDF and UDAF +nav_order: 13 +has_children: true +parent: /developer-overview/ +--- # Velox User-Defined Functions (UDF) and User-Defined Aggregate Functions (UDAF) ## Introduction diff --git a/docs/developers/velox-backend-CI.md b/docs/developers/velox-backend-CI.md new file mode 100644 index 000000000000..e4dceffdf72e --- /dev/null +++ b/docs/developers/velox-backend-CI.md @@ -0,0 +1,24 @@ +--- +layout: page +title: Velox Backend CI +nav_order: 14 +parent: Developer Overview +--- +# Velox Backend CI + +GHA workflows are defined under `.github/workflows/`. + +## Docker Build +We have a weekly job to build a docker based on `Dockerfile.gha` for CI verification, defined in `docker_image.yml`. + +## Vcpkg Caching +Gluten main branch is pulled down during docker build. And vcpkg will cache binary data of all dependencies defined under dev/vcpkg. +These binary data is cached into `/var/cache/vcpkg` and CI job can re-use them in new build. By setting `VCPKG_BINARY_SOURCES=clear` in env., +reusing vcpkg cache can be disabled. + +## Arrow Libs Pre-installation +Arrow libs are pre-installed in docker, assuming they are not actively changed, then not necessarily to be re-built every time. + +## Updating Docker Image +Two GitHub secrets `DOCKERHUB_USER` & `DOCKERHUB_TOKEN` can be used to push docker image to docker hub: https://hub.docker.com/r/apache/gluten/tags. +Note GitHub secrets are not retrievable in PR from forked repo. \ No newline at end of file