diff --git a/.github/workflows/velox_be.yml b/.github/workflows/velox_be.yml index c12596f047efe..5ee6b7ea1e956 100644 --- a/.github/workflows/velox_be.yml +++ b/.github/workflows/velox_be.yml @@ -51,29 +51,29 @@ jobs: - name: Setup docker container run: | docker run --rm --init --privileged --ulimit nofile=65536:65536 --ulimit core=-1 --security-opt seccomp=unconfined \ - -v $PWD:/opt/gluten_gha --name centos7-test-$GITHUB_RUN_ID -e NUM_THREADS=30 -detach 10.0.2.4:5000/gluten-dev-dec/centos:7 \ - bash -c 'cd /opt/gluten_gha && sleep 14400' + -v $PWD:/opt/gluten/ --name centos7-test-$GITHUB_RUN_ID -e NUM_THREADS=30 -detach 10.0.2.4:5000/gluten-dev-dec/centos:7 \ + bash -c 'cd /opt/gluten/ && sleep 14400' - name: Build Gluten velox third party run: | docker exec centos7-test-$GITHUB_RUN_ID bash -c ' source /env.sh && \ - cd /opt/gluten_gha/ep/build-velox/src && \ - ./get_velox.sh --velox_home=/opt/velox --enable_hdfs=ON --enable_s3=ON --enable_gcs=ON && \ - ./build_velox.sh --run_setup_script=OFF --velox_home=/opt/velox --enable_ep_cache=ON --enable_s3=ON --enable_gcs=ON --enable_hdfs=ON' + cd /opt/gluten//ep/build-velox/src && \ + ./get_velox.sh --enable_hdfs=ON --enable_s3=ON --enable_gcs=ON && \ + ./build_velox.sh --run_setup_script=OFF --enable_ep_cache=ON --enable_s3=ON --enable_gcs=ON --enable_hdfs=ON' - name: Build Gluten CPP library run: | docker exec centos7-test-$GITHUB_RUN_ID bash -c ' source /env.sh && \ - cd /opt/gluten_gha/cpp && \ - ./compile.sh --build_velox_backend=ON --velox_home=/opt/velox --enable_hdfs=ON --enable_s3=ON --enable_gcs=ON' + cd /opt/gluten//cpp && \ + ./compile.sh --build_velox_backend=ON --enable_hdfs=ON --enable_s3=ON --enable_gcs=ON' - name: Build for Spark 3.2.2 run: | docker exec centos7-test-$GITHUB_RUN_ID bash -c ' - cd /opt/gluten_gha && \ + cd /opt/gluten/ && \ mvn clean install -Pspark-3.2 -Pbackends-velox -Prss -Piceberg -DskipTests' - name: TPC-H SF1.0 && TPC-DS SF30.0 Parquet local spark3.2 run: | - docker exec centos7-test-$GITHUB_RUN_ID bash -c 'cd /opt/gluten_gha/tools/gluten-it && \ + docker exec centos7-test-$GITHUB_RUN_ID bash -c 'cd /opt/gluten//tools/gluten-it && \ mvn clean install -Pspark-3.2 \ && GLUTEN_IT_JVM_ARGS=-Xmx5G sbin/gluten-it.sh queries-compare \ --local --preset=velox --benchmark-type=h --error-on-memleak --disable-aqe --off-heap-size=10g -s=1.0 --threads=16 --iterations=1 \ @@ -81,7 +81,7 @@ jobs: --local --preset=velox --benchmark-type=ds --error-on-memleak --off-heap-size=50g -s=30.0 --threads=32 --iterations=1' - name: TPC-DS SF30.0 Parquet local spark3.2 Q67/Q95 low memory, memory isolation off run: | - docker exec centos7-test-$GITHUB_RUN_ID bash -c 'cd /opt/gluten_gha/tools/gluten-it && \ + docker exec centos7-test-$GITHUB_RUN_ID bash -c 'cd /opt/gluten//tools/gluten-it && \ mvn clean install -Pspark-3.2 \ && GLUTEN_IT_JVM_ARGS=-Xmx50G sbin/gluten-it.sh parameterized \ --local --preset=velox --benchmark-type=ds --error-on-memleak --queries=q67,q95 -s=30.0 --threads=12 --shuffle-partitions=72 --iterations=1 \ @@ -93,7 +93,7 @@ jobs: -d=OVER_ACQUIRE:0.5,spark.gluten.memory.overAcquiredMemoryRatio=0.5' - name: (To be fixed) TPC-DS SF30.0 Parquet local spark3.2 Q67/Q95 low memory, memory isolation on run: | - docker exec centos7-test-$GITHUB_RUN_ID bash -c 'cd /opt/gluten_gha/tools/gluten-it && \ + docker exec centos7-test-$GITHUB_RUN_ID bash -c 'cd /opt/gluten//tools/gluten-it && \ mvn clean install -Pspark-3.2 \ && GLUTEN_IT_JVM_ARGS=-Xmx50G sbin/gluten-it.sh parameterized \ --local --preset=velox --benchmark-type=ds --error-on-memleak --queries=q67,q95 -s=30.0 --threads=12 --shuffle-partitions=72 --iterations=1 \ @@ -105,7 +105,7 @@ jobs: -d=OVER_ACQUIRE:0.5,spark.gluten.memory.overAcquiredMemoryRatio=0.5' || true - name: TPC-DS SF30.0 Parquet local spark3.2 Q23A/Q23B low memory run: | - docker exec centos7-test-$GITHUB_RUN_ID bash -c 'cd /opt/gluten_gha/tools/gluten-it && \ + docker exec centos7-test-$GITHUB_RUN_ID bash -c 'cd /opt/gluten//tools/gluten-it && \ GLUTEN_IT_JVM_ARGS=-Xmx50G sbin/gluten-it.sh parameterized \ --local --preset=velox --benchmark-type=ds --error-on-memleak --queries=q23a,q23b -s=30.0 --threads=12 --shuffle-partitions=72 --iterations=1 \ --skip-data-gen -m=OffHeapExecutionMemory \ @@ -117,7 +117,7 @@ jobs: -d=PARTIAL_MODE:FLUSHED,spark.gluten.sql.columnar.backend.velox.maxPartialAggregationMemoryRatio=0.05,spark.gluten.sql.columnar.backend.velox.maxExtendedPartialAggregationMemoryRatio=0.1,spark.gluten.sql.columnar.backend.velox.abandonPartialAggregationMinPct=100,spark.gluten.sql.columnar.backend.velox.abandonPartialAggregationMinRows=0' - name: (To be fixed) TPC-DS SF30.0 Parquet local spark3.2 Q97 low memory # The case currently causes crash with "free: invalid size". run: | - docker exec centos7-test-$GITHUB_RUN_ID bash -c 'cd /opt/gluten_gha/tools/gluten-it && \ + docker exec centos7-test-$GITHUB_RUN_ID bash -c 'cd /opt/gluten//tools/gluten-it && \ GLUTEN_IT_JVM_ARGS=-Xmx50G sbin/gluten-it.sh parameterized \ --local --preset=velox --benchmark-type=ds --error-on-memleak --queries=q97 -s=30.0 --threads=12 --shuffle-partitions=72 --iterations=1 \ --skip-data-gen -m=OffHeapExecutionMemory \ @@ -129,59 +129,3 @@ jobs: if: ${{ always() }} run: | docker stop centos7-test-$GITHUB_RUN_ID || true - - static-build-test: - runs-on: velox-self-hosted - steps: - - uses: actions/checkout@v4 - - name: Setup docker container - run: | - docker run --rm --init --privileged --ulimit nofile=65536:65536 --ulimit core=-1 --security-opt seccomp=unconfined \ - -v $PWD:/opt/gluten_gha --name static-build-test-$GITHUB_RUN_ID -e NUM_THREADS=30 -detach 10.0.2.4:5000/gluten-dev/centos:7 \ - bash -c 'cd /opt/gluten_gha && sleep 14400' - - name: Build Gluten CPP library - run: | - docker exec -i static-build-test-$GITHUB_RUN_ID bash -c ' - source /env.sh && \ - sudo yum -y install patch && \ - cd /opt/gluten_gha && \ - source ./dev/vcpkg/env.sh && \ - ./dev/builddeps-veloxbe.sh --run_setup_script=OFF --build_tests=ON --build_benchmarks=ON --enable_s3=ON --enable_gcs=ON --enable_hdfs=ON' - - name: Build for Spark 3.2.2 - run: | - docker exec static-build-test-$GITHUB_RUN_ID bash -c ' - cd /opt/gluten_gha && \ - mvn clean install -Pspark-3.2 -Pbackends-velox -Prss -Piceberg -DskipTests && \ - cd /opt/gluten_gha/tools/gluten-it && \ - mvn clean install -Pspark-3.2' - - name: TPC-H SF1.0 && TPC-DS SF1.0 Parquet local spark3.2 (centos 8) - run: | - docker run --rm --init --privileged --ulimit nofile=65536:65536 --ulimit core=-1 --security-opt seccomp=unconfined \ - -v $PWD:/opt/gluten_gha --name static-build-test-$GITHUB_RUN_ID-tpc -e NUM_THREADS=30 10.0.2.4:5000/gluten-dev-dec/centos:8 \ - bash -c 'cd /opt/gluten_gha/tools/gluten-it \ - && GLUTEN_IT_JVM_ARGS=-Xmx5G sbin/gluten-it.sh queries-compare \ - --local --preset=velox --benchmark-type=h --error-on-memleak --disable-aqe --off-heap-size=10g -s=1.0 --threads=16 --iterations=1 \ - && GLUTEN_IT_JVM_ARGS=-Xmx10G sbin/gluten-it.sh queries-compare \ - --local --preset=velox --benchmark-type=ds --error-on-memleak --off-heap-size=20g -s=1.0 --threads=32 --iterations=1' - - name: TPC-H SF1.0 && TPC-DS SF1.0 Parquet local spark3.2 (ubuntu 20.04) - run: | - docker run --rm --init --privileged --ulimit nofile=65536:65536 --ulimit core=-1 --security-opt seccomp=unconfined \ - -v $PWD:/opt/gluten_gha --name static-build-test-$GITHUB_RUN_ID-tpc -e NUM_THREADS=30 10.0.2.4:5000/gluten-dev/ubuntu:20.04 \ - 'cd /opt/gluten_gha/tools/gluten-it \ - && GLUTEN_IT_JVM_ARGS=-Xmx5G sbin/gluten-it.sh queries-compare \ - --local --preset=velox --benchmark-type=h --error-on-memleak --disable-aqe --off-heap-size=10g -s=1.0 --threads=16 --iterations=1 \ - && GLUTEN_IT_JVM_ARGS=-Xmx10G sbin/gluten-it.sh queries-compare \ - --local --preset=velox --benchmark-type=ds --error-on-memleak --off-heap-size=20g -s=1.0 --threads=32 --iterations=1' - - name: TPC-H SF1.0 && TPC-DS SF1.0 Parquet local spark3.2 (ubuntu 22.04) - run: | - docker run --rm --init --privileged --ulimit nofile=65536:65536 --ulimit core=-1 --security-opt seccomp=unconfined \ - -v $PWD:/opt/gluten_gha --name static-build-test-$GITHUB_RUN_ID-tpc -e NUM_THREADS=30 10.0.2.4:5000/gluten-dev/ubuntu:22.04 \ - 'cd /opt/gluten_gha/tools/gluten-it \ - && GLUTEN_IT_JVM_ARGS=-Xmx5G sbin/gluten-it.sh queries-compare \ - --local --preset=velox --benchmark-type=h --error-on-memleak --disable-aqe --off-heap-size=10g -s=1.0 --threads=16 --iterations=1 \ - && GLUTEN_IT_JVM_ARGS=-Xmx10G sbin/gluten-it.sh queries-compare \ - --local --preset=velox --benchmark-type=ds --error-on-memleak --off-heap-size=20g -s=1.0 --threads=32 --iterations=1' - - name: Exit docker container - if: ${{ always() }} - run: | - docker stop static-build-test-$GITHUB_RUN_ID || true