Skip to content

Commit

Permalink
[GLUTEN-4903][CELEBORN] Support multiple versions of Celeborn
Browse files Browse the repository at this point in the history
  • Loading branch information
kerwin-zk committed Mar 11, 2024
1 parent 3ad58ce commit d7ad6f7
Show file tree
Hide file tree
Showing 26 changed files with 845 additions and 384 deletions.
46 changes: 31 additions & 15 deletions .github/workflows/velox_be.yml
Original file line number Diff line number Diff line change
Expand Up @@ -84,7 +84,7 @@ jobs:
run: |
$PATH_TO_GLUTEN_TE/$OS_IMAGE_NAME/gha/gha-checkout/exec.sh '
cd /opt/gluten && \
mvn clean install -Pspark-3.2 -Pspark-ut -Pbackends-velox -Prss -DargLine="-Dspark.test.home=/opt/spark322" -DtagsToExclude=org.apache.spark.tags.ExtendedSQLTest,io.glutenproject.tags.UDFTest,io.glutenproject.tags.SkipTestTags && \
mvn clean install -Pspark-3.2 -Pspark-ut -Pbackends-velox -Pceleborn-0.3 -DargLine="-Dspark.test.home=/opt/spark322" -DtagsToExclude=org.apache.spark.tags.ExtendedSQLTest,io.glutenproject.tags.UDFTest,io.glutenproject.tags.SkipTestTags && \
mvn test -Pspark-3.2 -Pbackends-velox -DtagsToExclude=None -DtagsToInclude=io.glutenproject.tags.UDFTest'
# Cpp micro benchmarks will use generated files from unit test in backends-velox module.
- name: Run micro benchmarks
Expand Down Expand Up @@ -136,7 +136,7 @@ jobs:
run: |
$PATH_TO_GLUTEN_TE/$OS_IMAGE_NAME/gha/gha-checkout/exec.sh '
cd /opt/gluten && \
mvn clean install -Pspark-3.2 -Pspark-ut -Pbackends-velox -Prss -Piceberg -Pdelta -DargLine="-Dspark.test.home=/opt/spark322" -DtagsToInclude=org.apache.spark.tags.ExtendedSQLTest'
mvn clean install -Pspark-3.2 -Pspark-ut -Pbackends-velox -Pceleborn-0.3 -Piceberg -Pdelta -DargLine="-Dspark.test.home=/opt/spark322" -DtagsToInclude=org.apache.spark.tags.ExtendedSQLTest'
- name: TPC-H SF1.0 && TPC-DS SF1.0 Parquet local spark3.2
run: |
$PATH_TO_GLUTEN_TE/$OS_IMAGE_NAME/gha/gha-checkout/exec.sh 'cd /opt/gluten/tools/gluten-it && \
Expand Down Expand Up @@ -174,7 +174,7 @@ jobs:
- name: Build and Run unit test for Spark 3.3.1 (slow tests)
run: |
$PATH_TO_GLUTEN_TE/$OS_IMAGE_NAME/gha/gha-checkout/exec.sh 'cd /opt/gluten && \
mvn clean install -Pspark-3.3 -Pbackends-velox -Prss -Piceberg -Pdelta -Pspark-ut -DargLine="-Dspark.test.home=/opt/spark331" -DtagsToInclude=org.apache.spark.tags.ExtendedSQLTest'
mvn clean install -Pspark-3.3 -Pbackends-velox -Pceleborn-0.3 -Piceberg -Pdelta -Pspark-ut -DargLine="-Dspark.test.home=/opt/spark331" -DtagsToInclude=org.apache.spark.tags.ExtendedSQLTest'
- name: TPC-H SF1.0 && TPC-DS SF1.0 Parquet local spark3.3
run: |
$PATH_TO_GLUTEN_TE/$OS_IMAGE_NAME/gha/gha-checkout/exec.sh 'cd /opt/gluten/tools/gluten-it && \
Expand Down Expand Up @@ -222,7 +222,7 @@ jobs:
- name: Build and Run unit test for Spark 3.3.1 (other tests)
run: |
$PATH_TO_GLUTEN_TE/$OS_IMAGE_NAME/gha/gha-checkout/exec.sh 'cd /opt/gluten && \
mvn clean install -Pspark-3.3 -Pbackends-velox -Prss -Piceberg -Pdelta -Pspark-ut -DargLine="-Dspark.test.home=/opt/spark331" -DtagsToExclude=org.apache.spark.tags.ExtendedSQLTest,io.glutenproject.tags.UDFTest,io.glutenproject.tags.SkipTestTags && \
mvn clean install -Pspark-3.3 -Pbackends-velox -Pceleborn-0.3 -Piceberg -Pdelta -Pspark-ut -DargLine="-Dspark.test.home=/opt/spark331" -DtagsToExclude=org.apache.spark.tags.ExtendedSQLTest,io.glutenproject.tags.UDFTest,io.glutenproject.tags.SkipTestTags && \
mvn test -Pspark-3.3 -Pbackends-velox -DtagsToExclude=None -DtagsToInclude=io.glutenproject.tags.UDFTest'
- name: Copy golden files from container to host
if: failure()
Expand Down Expand Up @@ -268,7 +268,7 @@ jobs:
- name: Build and Run unit test for Spark 3.4.2 (slow tests)
run: |
$PATH_TO_GLUTEN_TE/$OS_IMAGE_NAME/gha/gha-checkout/exec.sh 'cd /opt/gluten && \
mvn clean install -Pspark-3.4 -Pbackends-velox -Prss -Piceberg -Pdelta -Pspark-ut -DargLine="-Dspark.test.home=/opt/spark342" -DtagsToInclude=org.apache.spark.tags.ExtendedSQLTest'
mvn clean install -Pspark-3.4 -Pbackends-velox -Pceleborn-0.3 -Piceberg -Pdelta -Pspark-ut -DargLine="-Dspark.test.home=/opt/spark342" -DtagsToInclude=org.apache.spark.tags.ExtendedSQLTest'
- name: TPC-H SF1.0 && TPC-DS SF1.0 Parquet local spark3.4
run: |
$PATH_TO_GLUTEN_TE/$OS_IMAGE_NAME/gha/gha-checkout/exec.sh 'cd /opt/gluten/tools/gluten-it && \
Expand Down Expand Up @@ -306,7 +306,7 @@ jobs:
- name: Build and Run unit test for Spark 3.4.2 (other tests)
run: |
$PATH_TO_GLUTEN_TE/$OS_IMAGE_NAME/gha/gha-checkout/exec.sh 'cd /opt/gluten && \
mvn clean install -Pspark-3.4 -Pbackends-velox -Prss -Piceberg -Pdelta -Pspark-ut -DargLine="-Dspark.test.home=/opt/spark342" -DtagsToExclude=org.apache.spark.tags.ExtendedSQLTest,io.glutenproject.tags.UDFTest,io.glutenproject.tags.SkipTestTags && \
mvn clean install -Pspark-3.4 -Pbackends-velox -Pceleborn-0.3 -Piceberg -Pdelta -Pspark-ut -DargLine="-Dspark.test.home=/opt/spark342" -DtagsToExclude=org.apache.spark.tags.ExtendedSQLTest,io.glutenproject.tags.UDFTest,io.glutenproject.tags.SkipTestTags && \
mvn test -Pspark-3.4 -Pbackends-velox -DtagsToExclude=None -DtagsToInclude=io.glutenproject.tags.UDFTest'
- name: Exit docker container
if: ${{ always() }}
Expand Down Expand Up @@ -338,7 +338,7 @@ jobs:
run: |
$PATH_TO_GLUTEN_TE/$OS_IMAGE_NAME/gha/gha-checkout/exec.sh '
cd /opt/gluten && \
mvn clean install -Pspark-3.5 -Pbackends-velox -Prss -DskipTests'
mvn clean install -Pspark-3.5 -Pbackends-velox -Pceleborn-0.3 -DskipTests'
- name: TPC-H SF1.0 && TPC-DS SF1.0 Parquet local spark3.5
run: |
$PATH_TO_GLUTEN_TE/$OS_IMAGE_NAME/gha/gha-checkout/exec.sh 'cd /opt/gluten/tools/gluten-it && \
Expand Down Expand Up @@ -377,7 +377,7 @@ jobs:
run: |
$PATH_TO_GLUTEN_TE/$OS_IMAGE_NAME/gha/gha-checkout/exec.sh '
cd /opt/gluten && \
mvn clean install -Pspark-3.3 -Pbackends-velox -Prss -Piceberg -Pdelta -DskipTests'
mvn clean install -Pspark-3.3 -Pbackends-velox -Pceleborn-0.3 -Piceberg -Pdelta -DskipTests'
- name: TPC-H SF1.0 && TPC-DS SF10.0 Parquet local spark3.3
run: |
$PATH_TO_GLUTEN_TE/$OS_IMAGE_NAME/gha/gha-checkout/exec.sh 'cd /opt/gluten/tools/gluten-it && \
Expand All @@ -390,7 +390,7 @@ jobs:
run: |
$PATH_TO_GLUTEN_TE/$OS_IMAGE_NAME/gha/gha-checkout/exec.sh '
cd /opt/gluten && \
mvn clean install -Pspark-3.4 -Pbackends-velox -Prss -Piceberg -Pdelta -DskipTests'
mvn clean install -Pspark-3.4 -Pbackends-velox -Pceleborn-0.3 -Piceberg -Pdelta -DskipTests'
- name: TPC-H SF1.0 && TPC-DS SF10.0 Parquet local spark3.4
run: |
$PATH_TO_GLUTEN_TE/$OS_IMAGE_NAME/gha/gha-checkout/exec.sh 'cd /opt/gluten/tools/gluten-it && \
Expand Down Expand Up @@ -429,7 +429,7 @@ jobs:
run: |
$PATH_TO_GLUTEN_TE/$OS_IMAGE_NAME/gha/gha-checkout/exec.sh '
cd /opt/gluten && \
mvn clean install -Pspark-3.2 -Pbackends-velox -Prss -Piceberg -Pdelta -DskipTests'
mvn clean install -Pspark-3.2 -Pbackends-velox -Pceleborn-0.3 -Piceberg -Pdelta -DskipTests'
- name: TPC-H SF1.0 && TPC-DS SF10.0 Parquet local spark3.2
run: |
$PATH_TO_GLUTEN_TE/$OS_IMAGE_NAME/gha/gha-checkout/exec.sh 'cd /opt/gluten/tools/gluten-it && \
Expand All @@ -438,7 +438,7 @@ jobs:
--local --preset=velox --benchmark-type=h --error-on-memleak --off-heap-size=10g -s=1.0 --threads=16 --iterations=1 \
&& GLUTEN_IT_JVM_ARGS=-Xmx20G sbin/gluten-it.sh queries-compare \
--local --preset=velox --benchmark-type=ds --error-on-memleak --off-heap-size=40g -s=10.0 --threads=32 --iterations=1'
- name: TPC-H SF1.0 && TPC-DS SF10.0 Parquet local spark3.2 with Celeborn
- name: TPC-H SF1.0 && TPC-DS SF10.0 Parquet local spark3.2 with Celeborn 0.3.0
run: |
$PATH_TO_GLUTEN_TE/$OS_IMAGE_NAME/gha/gha-checkout/exec.sh \
'wget https://archive.apache.org/dist/incubator/celeborn/celeborn-0.3.0-incubating/apache-celeborn-0.3.0-incubating-bin.tgz && \
Expand All @@ -447,7 +447,23 @@ jobs:
echo -e "CELEBORN_MASTER_MEMORY=4g\nCELEBORN_WORKER_MEMORY=4g\nCELEBORN_WORKER_OFFHEAP_MEMORY=8g" > ./conf/celeborn-env.sh && \
echo -e "celeborn.worker.commitFiles.threads 128\nceleborn.worker.sortPartition.threads 64" > ./conf/celeborn-defaults.conf \
&& bash ./sbin/start-master.sh && bash ./sbin/start-worker.sh && \
cd /opt/gluten/tools/gluten-it && mvn clean install -Pspark-3.2,rss \
cd /opt/gluten/tools/gluten-it && mvn clean install -Pspark-3.2,celeborn-0.3 \
&& GLUTEN_IT_JVM_ARGS=-Xmx5G sbin/gluten-it.sh queries-compare \
--local --preset=velox-with-celeborn --benchmark-type=h --error-on-memleak --off-heap-size=10g -s=1.0 --threads=16 --iterations=1 \
&& 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=16 --iterations=1 && \
bash /opt/celeborn/sbin/stop-worker.sh \
&& bash /opt/celeborn/sbin/stop-master.sh && rm -rf /opt/celeborn'
- name: TPC-H SF1.0 && TPC-DS SF10.0 Parquet local spark3.2 with Celeborn 0.4.0
run: |
$PATH_TO_GLUTEN_TE/$OS_IMAGE_NAME/gha/gha-checkout/exec.sh \
'wget https://archive.apache.org/dist/incubator/celeborn/celeborn-0.4.0-incubating/apache-celeborn-0.4.0-incubating-bin.tgz && \
tar xzf apache-celeborn-0.4.0-incubating-bin.tgz -C /opt/ && mv /opt/apache-celeborn-0.4.0-incubating-bin /opt/celeborn && cd /opt/celeborn && \
mv ./conf/celeborn-env.sh.template ./conf/celeborn-env.sh && \
echo -e "CELEBORN_MASTER_MEMORY=4g\nCELEBORN_WORKER_MEMORY=4g\nCELEBORN_WORKER_OFFHEAP_MEMORY=8g" > ./conf/celeborn-env.sh && \
echo -e "celeborn.worker.commitFiles.threads 128\nceleborn.worker.sortPartition.threads 64" > ./conf/celeborn-defaults.conf \
&& bash ./sbin/start-master.sh && bash ./sbin/start-worker.sh && \
cd /opt/gluten/tools/gluten-it && mvn clean install -Pspark-3.2,celeborn-0.4 \
&& GLUTEN_IT_JVM_ARGS=-Xmx5G sbin/gluten-it.sh queries-compare \
--local --preset=velox-with-celeborn --benchmark-type=h --error-on-memleak --off-heap-size=10g -s=1.0 --threads=16 --iterations=1 \
&& GLUTEN_IT_JVM_ARGS=-Xmx5G sbin/gluten-it.sh queries-compare \
Expand Down Expand Up @@ -487,7 +503,7 @@ jobs:
run: |
$PATH_TO_GLUTEN_TE/$OS_IMAGE_NAME/gha/gha-checkout/exec.sh '
cd /opt/gluten && \
mvn clean install -Pspark-3.2 -Pbackends-velox -Prss -Piceberg -Pdelta -DskipTests'
mvn clean install -Pspark-3.2 -Pbackends-velox -Pceleborn-0.3 -Piceberg -Pdelta -DskipTests'
- name: TPC-H SF1.0 && TPC-DS SF30.0 Parquet local spark3.2
run: |
$PATH_TO_GLUTEN_TE/$OS_IMAGE_NAME/gha/gha-checkout/exec.sh 'cd /opt/gluten/tools/gluten-it && \
Expand Down Expand Up @@ -537,7 +553,7 @@ jobs:
run: |
$PATH_TO_GLUTEN_TE/$OS_IMAGE_NAME/gha/gha-checkout/exec.sh '
cd /opt/gluten && \
mvn clean install -Pspark-3.2 -Pbackends-velox -Prss -Piceberg -Pdelta -DskipTests'
mvn clean install -Pspark-3.2 -Pbackends-velox -Pceleborn-0.3 -Piceberg -Pdelta -DskipTests'
- name: TPC-H SF1.0 && TPC-DS SF30.0 Parquet local spark3.2
run: |
$PATH_TO_GLUTEN_TE/$OS_IMAGE_NAME/gha/gha-checkout/exec.sh 'cd /opt/gluten/tools/gluten-it && \
Expand Down Expand Up @@ -621,7 +637,7 @@ jobs:
run: |
docker exec static-build-test-$GITHUB_RUN_ID bash -c '
cd /opt/gluten && \
mvn clean install -Pspark-3.2 -Pbackends-velox -Prss -Piceberg -Pdelta -DskipTests && \
mvn clean install -Pspark-3.2 -Pbackends-velox -Pceleborn-0.3 -Piceberg -Pdelta -DskipTests && \
cd /opt/gluten/tools/gluten-it && \
mvn clean install -Pspark-3.2'
- name: TPC-H SF1.0 && TPC-DS SF1.0 Parquet local spark3.2 (ubuntu 20.04)
Expand Down
8 changes: 4 additions & 4 deletions dev/buildbundle-veloxbe.sh
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@ BASEDIR=$(dirname $0)
source "$BASEDIR/builddeps-veloxbe.sh"

cd $GLUTEN_DIR
mvn clean package -Pbackends-velox -Prss -Pspark-3.2 -DskipTests
mvn clean package -Pbackends-velox -Prss -Pspark-3.3 -DskipTests
mvn clean package -Pbackends-velox -Prss -Pspark-3.4 -DskipTests
mvn clean package -Pbackends-velox -Prss -Pspark-3.5 -DskipTests
mvn clean package -Pbackends-velox -Pceleborn-0.3 -Pspark-3.2 -DskipTests
mvn clean package -Pbackends-velox -Pceleborn-0.3 -Pspark-3.3 -DskipTests
mvn clean package -Pbackends-velox -Pceleborn-0.3 -Pspark-3.4 -DskipTests
mvn clean package -Pbackends-velox -Pceleborn-0.3 -Pspark-3.5 -DskipTests
8 changes: 4 additions & 4 deletions dev/package.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,10 +11,10 @@ ARCH=`uname -m`

# compile gluten jar
$GLUTEN_DIR/dev/builddeps-veloxbe.sh --build_tests=ON --build_benchmarks=ON --enable_s3=ON --enable_hdfs=ON
mvn clean package -Pbackends-velox -Prss -Pspark-3.2 -DskipTests
mvn clean package -Pbackends-velox -Prss -Pspark-3.3 -DskipTests
mvn clean package -Pbackends-velox -Prss -Pspark-3.4 -DskipTests
mvn clean package -Pbackends-velox -Prss -Pspark-3.5 -DskipTests
mvn clean package -Pbackends-velox -Pceleborn-0.3 -Pspark-3.2 -DskipTests
mvn clean package -Pbackends-velox -Pceleborn-0.3 -Pspark-3.3 -DskipTests
mvn clean package -Pbackends-velox -Pceleborn-0.3 -Pspark-3.4 -DskipTests
mvn clean package -Pbackends-velox -Pceleborn-0.3 -Pspark-3.5 -DskipTests

mkdir -p $THIRDPARTY_LIB
function process_setup_ubuntu_2004 {
Expand Down
4 changes: 2 additions & 2 deletions docs/developers/HowTo.md
Original file line number Diff line number Diff line change
Expand Up @@ -51,8 +51,8 @@ gluten_home/dev/builddeps-veloxbe.sh --build_tests=ON --build_benchmarks=ON --bu
2. build Gluten and generate the example files
```
cd gluten_home
mvn clean package -Pspark-3.2 -Pbackends-velox -Prss
mvn test -Pspark-3.2 -Pbackends-velox -Prss -pl backends-velox -am -DtagsToInclude="io.glutenproject.tags.GenerateExample" -Dtest=none -DfailIfNoTests=false -Darrow.version=11.0.0-gluten -Dexec.skip
mvn clean package -Pspark-3.2 -Pbackends-velox -Pceleborn-0.3
mvn test -Pspark-3.2 -Pbackends-velox -Pceleborn-0.3 -pl backends-velox -am -DtagsToInclude="io.glutenproject.tags.GenerateExample" -Dtest=none -DfailIfNoTests=false -Darrow.version=11.0.0-gluten -Dexec.skip
```
- After the above operations, the examples files are generated under `gluten_home/backends-velox`
- You can check it by the command `tree gluten_home/backends-velox/generated-native-benchmark/`
Expand Down
2 changes: 1 addition & 1 deletion docs/developers/MicroBenchmarks.md
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ cd /path/to/gluten/
./dev/buildbundle-veloxbe.sh --build_tests=ON --build_benchmarks=ON

# Run test to generate input data files. If you are using spark 3.3, replace -Pspark-3.2 with -Pspark-3.3
mvn test -Pspark-3.2 -Pbackends-velox -Prss -pl backends-velox -am \
mvn test -Pspark-3.2 -Pbackends-velox -Pceleborn-0.3 -pl backends-velox -am \
-DtagsToInclude="io.glutenproject.tags.GenerateExample" -Dtest=none -DfailIfNoTests=false -Darrow.version=11.0.0-gluten -Dexec.skip
```

Expand Down
4 changes: 2 additions & 2 deletions docs/developers/NewToGluten.md
Original file line number Diff line number Diff line change
Expand Up @@ -108,8 +108,8 @@ To generate a fix for Java/Scala code style, you can run one or more of the belo

For Velox backend:
```
mvn spotless:apply -Pbackends-velox -Prss -Pspark-3.2 -Pspark-ut -DskipTests
mvn spotless:apply -Pbackends-velox -Prss -Pspark-3.3 -Pspark-ut -DskipTests
mvn spotless:apply -Pbackends-velox -Pceleborn-0.3 -Pspark-3.2 -Pspark-ut -DskipTests
mvn spotless:apply -Pbackends-velox -Pceleborn-0.3 -Pspark-3.3 -Pspark-ut -DskipTests
```
For Clickhouse backend:
```
Expand Down
1 change: 1 addition & 0 deletions docs/get-started/ClickHouse.md
Original file line number Diff line number Diff line change
Expand Up @@ -671,6 +671,7 @@ spark.dynamicAllocation.enabled false
```

#### Celeborn Columnar Shuffle Support
Currently, the supported Celeborn versions are `0.3.x` and `0.4.x`.
The native Celeborn support can be enabled by the following configuration
```
spark.shuffle.manager=org.apache.spark.shuffle.gluten.celeborn.CelebornShuffleManager
Expand Down
10 changes: 6 additions & 4 deletions docs/get-started/Velox.md
Original file line number Diff line number Diff line change
Expand Up @@ -104,9 +104,9 @@ cd /path/to/gluten/cpp
## compile Gluten java module and create package jar
cd /path/to/gluten
# For spark3.2.x
mvn clean package -Pbackends-velox -Prss -Pspark-3.2 -DskipTests
mvn clean package -Pbackends-velox -Pceleborn-0.3 -Pspark-3.2 -DskipTests
# For spark3.3.x
mvn clean package -Pbackends-velox -Prss -Pspark-3.3 -DskipTests
mvn clean package -Pbackends-velox -Pceleborn-0.3 -Pspark-3.3 -DskipTests
```

notes:The compilation of `Velox` using the script of `build_velox.sh` may fail caused by `oom`, you can prevent this failure by using the user command of `export NUM_THREADS=4` before executing the above scripts.
Expand Down Expand Up @@ -207,14 +207,16 @@ Currently there are several ways to asscess S3 in Spark. Please refer [Velox S3]

## Celeborn support

Gluten with velox backend supports [Celeborn](https://github.com/apache/incubator-celeborn) as remote shuffle service. Below introduction is used to enable this feature
Gluten with velox backend supports [Celeborn](https://github.com/apache/incubator-celeborn) as remote shuffle service. Currently, the supported Celeborn versions are `0.3.x` and `0.4.x`.

Below introduction is used to enable this feature

First refer to this URL(https://github.com/apache/incubator-celeborn) to setup a celeborn cluster.

When compiling the Gluten Java module, it's required to enable `rss` profile, as follows:

```
mvn clean package -Pbackends-velox -Pspark-3.3 -Prss -DskipTests
mvn clean package -Pbackends-velox -Pspark-3.3 -Pceleborn-0.3 -DskipTests
```

Then add the Gluten and Spark Celeborn Client packages to your Spark application's classpath(usually add them into `$SPARK_HOME/jars`).
Expand Down
4 changes: 2 additions & 2 deletions ep/build-clickhouse/src/package.sh
Original file line number Diff line number Diff line change
Expand Up @@ -78,15 +78,15 @@ cp "${GLUTEN_SOURCE}"/LICENSE "${GLUTEN_SOURCE}"/dist/"${PACKAGE_NAME}"
cp "${GLUTEN_SOURCE}"/README.md "${GLUTEN_SOURCE}"/dist/"${PACKAGE_NAME}"

# build gluten with spark32
mvn clean install -Pbackends-clickhouse -Pspark-3.2 -Prss -DskipTests -Dcheckstyle.skip
mvn clean install -Pbackends-clickhouse -Pspark-3.2 -Pceleborn-0.3 -DskipTests -Dcheckstyle.skip
cp "${GLUTEN_SOURCE}"/backends-clickhouse/target/gluten-*-spark-3.2-jar-with-dependencies.jar "${PACKAGE_DIR_PATH}"/jars/spark32/gluten.jar
cp "${GLUTEN_SOURCE}"/gluten-celeborn/clickhouse/target/gluten-celeborn-clickhouse-${PROJECT_VERSION}-jar-with-dependencies.jar "${PACKAGE_DIR_PATH}"/jars/spark32
delta_version_32=$(mvn -q -Dexec.executable="echo" -Dexec.args='${delta.version}' -Pspark-3.2 --non-recursive exec:exec)
wget https://repo1.maven.org/maven2/io/delta/delta-core_2.12/${delta_version_32}/delta-core_2.12-${delta_version_32}.jar -P "${PACKAGE_DIR_PATH}"/jars/spark32
wget https://repo1.maven.org/maven2/io/delta/delta-storage/${delta_version_32}/delta-storage-${delta_version_32}.jar -P "${PACKAGE_DIR_PATH}"/jars/spark32

# build gluten with spark33
mvn clean install -Pbackends-clickhouse -Pspark-3.3 -Prss -DskipTests -Dcheckstyle.skip
mvn clean install -Pbackends-clickhouse -Pspark-3.3 -Pceleborn-0.3 -DskipTests -Dcheckstyle.skip
cp "${GLUTEN_SOURCE}"/backends-clickhouse/target/gluten-*-spark-3.3-jar-with-dependencies.jar "${PACKAGE_DIR_PATH}"/jars/spark33/gluten.jar
cp "${GLUTEN_SOURCE}"/gluten-celeborn/clickhouse/target/gluten-celeborn-clickhouse-${PROJECT_VERSION}-jar-with-dependencies.jar "${PACKAGE_DIR_PATH}"/jars/spark33
delta_version_33=$(mvn -q -Dexec.executable="echo" -Dexec.args='${delta.version}' -Pspark-3.3 --non-recursive exec:exec)
Expand Down
Loading

0 comments on commit d7ad6f7

Please sign in to comment.