This is an automated email from the ASF dual-hosted git repository.
nicholasjiang pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/auron.git
The following commit(s) were added to refs/heads/master by this push:
new f90e23e8 [AURON-1281][INFRA] Make workflow flexible with dynamic Spark
version (#1282)
f90e23e8 is described below
commit f90e23e8b68ec1cad897df722eeaaf83afa9fd88
Author: Ruilei Ma <merril...@gmail.com>
AuthorDate: Tue Sep 16 10:16:25 2025 +0800
[AURON-1281][INFRA] Make workflow flexible with dynamic Spark version
(#1282)
* [AURON-1281][INFRA] Make workflow flexible with dynamic Spark version
* nit fix
* bug fix
---
.github/workflows/celeborn.yml | 2 +-
.github/workflows/tpcds-reusable.yml | 101 +++++++++++++++++++++++++----------
.github/workflows/tpcds.yml | 12 ++---
.github/workflows/uniffle.yml | 8 +--
4 files changed, 84 insertions(+), 39 deletions(-)
diff --git a/.github/workflows/celeborn.yml b/.github/workflows/celeborn.yml
index 194f5fa3..c9e171d6 100644
--- a/.github/workflows/celeborn.yml
+++ b/.github/workflows/celeborn.yml
@@ -50,7 +50,7 @@ jobs:
extrabuildopt: -P${{ matrix.celebornprofile }} -DcelebornVersion=${{
matrix.celebornver }}
extraidentifier: celeborn-${{ matrix.celebornver }}
sparkver: "spark-3.5"
- sparkurl:
"https://archive.apache.org/dist/spark/spark-3.5.6/spark-3.5.6-bin-hadoop3.tgz";
+ hadoop-profile: 'hadoop3'
scalaver: "2.12"
extrasparkconf: >-
--conf
spark.shuffle.manager=org.apache.spark.sql.execution.auron.shuffle.celeborn.AuronCelebornShuffleManager
diff --git a/.github/workflows/tpcds-reusable.yml
b/.github/workflows/tpcds-reusable.yml
index d252be8b..90a93477 100644
--- a/.github/workflows/tpcds-reusable.yml
+++ b/.github/workflows/tpcds-reusable.yml
@@ -21,56 +21,71 @@ on:
workflow_call:
inputs:
sparkver:
+ description: 'Maven profile id to resolve sparkVersion (e.g.,
spark-3.5)'
required: true
type: string
- sparkurl:
+ hadoop-profile:
+ description: 'Hadoop profile (e.g., hadoop2.7, hadoop3)'
required: true
type: string
+ default: ''
javaver:
+ description: 'Optional Java version'
required: false
type: string
default: '8'
scalaver:
+ description: 'Optional Scala version'
required: false
type: string
default: '2.12'
celebornver:
+ description: 'Optional Celeborn version'
required: false
type: string
default: ''
celebornurl:
+ description: 'Optional Celeborn URL'
required: false
type: string
default: ''
unifflever:
+ description: 'Optional Uniffle version'
required: false
type: string
default: ''
uniffleurl:
+ description: 'Optional Uniffle URL'
required: false
type: string
default: ''
hadoopver:
+ description: 'Optional Hadoop version'
required: false
type: string
default: ''
hadoopurl:
+ description: 'Optional Hadoop URL'
required: false
type: string
default: ''
extrabuildopt:
+ description: 'Optional extra build options for Maven'
required: false
type: string
default: ''
extraidentifier:
+ description: 'Optional extra identifier for artifact names'
required: false
type: string
default: ''
extrasparkconf:
+ description: 'Optional extra Spark conf to pass'
required: false
type: string
default: ''
queries:
+ description: 'Optional list of queries to run'
required: false
type: string
default: |
@@ -89,32 +104,35 @@ on:
jobs:
build-validator:
- name: Build Validator
+ name: Build TPC-DS Validator
runs-on: ubuntu-latest
steps:
- - uses: actions/cache@v4
+ - name: Cache TPC-DS Validator
+ uses: actions/cache@v4
id: cache-tpcds-validator
with:
key: tpcds-validator_${{ inputs.scalaver }}
path: target/tpcds-validator_${{ inputs.scalaver
}}-0.1.0-SNAPSHOT-with-dependencies.jar
- - uses: actions/checkout@v4
+ - name: Checkout TPC-DS Validator
+ uses: actions/checkout@v4
if: steps.cache-tpcds-validator.outputs.cache-hit != 'true'
with:
repository: auron-project/tpcds-validator
- - uses: actions/setup-java@v4
+ - name: Setup Java and Maven cache
+ uses: actions/setup-java@v4
if: steps.cache-tpcds-validator.outputs.cache-hit != 'true'
with:
distribution: 'adopt-hotspot'
java-version: ${{ inputs.javaver }}
cache: 'maven'
- - name: Build
+ - name: Build TPC-DS Validator
if: steps.cache-tpcds-validator.outputs.cache-hit != 'true'
run: ./build/mvn package -DskipTests -Pscala-${{ inputs.scalaver }}
- - name: Upload Artifact
+ - name: Upload TPC-DS Validator
uses: actions/upload-artifact@v4
with:
name: tpcds-validator-${{ inputs.sparkver }}_${{ inputs.scalaver
}}-jdk-${{ inputs.javaver }}${{ inputs.extraidentifier }}
@@ -125,21 +143,26 @@ jobs:
name: Build Auron JAR
runs-on: ubuntu-latest
steps:
- - uses: actions/checkout@v4
+ - name: Checkout Auron
+ uses: actions/checkout@v4
with:
submodules: recursive
- - uses: actions/setup-java@v4
+
+ - name: Setup Java and Maven cache
+ uses: actions/setup-java@v4
with:
distribution: 'adopt-hotspot'
java-version: ${{ inputs.javaver }}
cache: 'maven'
- - uses: arduino/setup-protoc@v2
+ - name: Setup protoc
+ uses: arduino/setup-protoc@v2
with:
version: "21.7"
repo-token: ${{ secrets.GITHUB_TOKEN }}
- - uses: ./.github/actions/setup-rust-toolchain
+ - name: Setup Rust toolchain
+ uses: ./.github/actions/setup-rust-toolchain
with:
rustflags: --allow warnings -C target-feature=+aes
components:
@@ -151,13 +174,13 @@ jobs:
cargo --version
cargo test --workspace --all-features
- - name: Build ${{ inputs.sparkver }}_${{ inputs.scalaver }} jdk-${{
inputs.javaver }}
+ - name: Build auron (Spark ${{ inputs.sparkver }}, Scala ${{
inputs.scalaver }}, JDK ${{ inputs.javaver }})
run: |
sed -i 's/opt-level = 1/opt-level = 0/g' Cargo.toml # use opt-level 0
rm -f .build-checksum_*.cache
./build/mvn package -Ppre -P${{ inputs.sparkver }} -Pscala-${{
inputs.scalaver }} -Pjdk-${{ inputs.javaver }} ${{ inputs.extrabuildopt }}
- - name: Upload ${{ inputs.sparkver }}_${{ inputs.scalaver }} jdk-${{
inputs.javaver }}
+ - name: Upload auron (Spark ${{ inputs.sparkver }}, Scala ${{
inputs.scalaver }}, JDK ${{ inputs.javaver }})
uses: actions/upload-artifact@v4
with:
name: auron-${{ inputs.sparkver }}_${{ inputs.scalaver }}-jdk-${{
inputs.javaver }}${{ inputs.extraidentifier }}
@@ -173,27 +196,44 @@ jobs:
matrix:
query: ${{ fromJson(inputs.queries) }}
steps:
- - uses: actions/checkout@v4
+ - name: Checkout Auron
+ uses: actions/checkout@v4
- - uses: actions/cache@v4
+ - name: Get Spark actual version from pom
+ id: get-spark-version
+ run: |
+ SPARK_VERSION=$(./build/mvn help:evaluate -N
-Dexpression=sparkVersion -P ${{ inputs.sparkver }} -q -DforceStdout)
+ if [ ${{inputs.scalaver}} = "2.13" ]; then
+
SPARK_URL="https://archive.apache.org/dist/spark/spark-${SPARK_VERSION}/spark-${SPARK_VERSION}-bin-${{
inputs.hadoop-profile }}-scala${{inputs.scalaver}}.tgz"
+ else
+
SPARK_URL="https://archive.apache.org/dist/spark/spark-${SPARK_VERSION}/spark-${SPARK_VERSION}-bin-${{
inputs.hadoop-profile }}.tgz"
+ fi
+ echo "Detected Spark VERSION: $SPARK_VERSION"
+ echo "Detected SPARK URL: $SPARK_URL"
+ echo "sparkurl=$SPARK_URL" >> $GITHUB_OUTPUT
+
+ - name: Cache Spark (Spark ${{ inputs.sparkver }}, Scala ${{
inputs.scalaver }})
+ uses: actions/cache@v4
id: cache-spark-bin
with:
path: spark-bin-${{ inputs.sparkver }}_${{ inputs.scalaver }}
key: spark-bin-${{ inputs.sparkver }}_${{ inputs.scalaver }}
- - name: Setup ${{ inputs.sparkver }}
+ - name: Setup Spark (Spark ${{ inputs.sparkver }}, Scala ${{
inputs.scalaver }})
id: setup-spark-bin
if: steps.cache-spark-bin.outputs.cache-hit != 'true'
run: |
- wget -c ${{ inputs.sparkurl }}
+ wget -c ${{ steps.get-spark-version.outputs.sparkurl }}
mkdir -p spark-bin-${{ inputs.sparkver }}_${{ inputs.scalaver }}
cd spark-bin-${{ inputs.sparkver }}_${{ inputs.scalaver }} && tar
-xf ../spark-*.tgz --strip-component=1
- - uses: actions/download-artifact@v4
+ - name: Download Auron JAR
+ uses: actions/download-artifact@v4
with:
name: auron-${{ inputs.sparkver }}_${{ inputs.scalaver }}-jdk-${{
inputs.javaver }}${{ inputs.extraidentifier }}
- - uses: actions/download-artifact@v4
+ - name: Download TPC-DS Validator JAR
+ uses: actions/download-artifact@v4
with:
name: tpcds-validator-${{ inputs.sparkver }}_${{ inputs.scalaver
}}-jdk-${{ inputs.javaver }}${{ inputs.extraidentifier }}
@@ -208,13 +248,15 @@ jobs:
ls -la
cp auron-*${{ inputs.sparkver }}_${{ inputs.scalaver }}*.jar
spark-bin-${{ inputs.sparkver }}_${{ inputs.scalaver }}/jars/
- - uses: actions/setup-java@v4
+ - name: Setup Java and Maven cache
+ uses: actions/setup-java@v4
with:
distribution: 'adopt-hotspot'
java-version: ${{ inputs.javaver }}
cache: 'maven'
- - uses: actions/cache@v4
+ - name: Cache Celeborn-${{ inputs.celebornver }}
+ uses: actions/cache@v4
if: ${{ inputs.celebornver != '' && inputs.celebornurl != '' }}
id: cache-celeborn-bin
with:
@@ -223,7 +265,7 @@ jobs:
- name: Setup Celeborn-${{ inputs.celebornver }}
id: setup-celeborn-bin
- if: ${{ inputs.celebornver != '' && inputs.celebornurl != '' &&
steps.cache-celeborn-bin.outputs.cache-hit != 'true' }}
+ if: ${{ inputs.celebornver != '' && inputs.celebornurl != '' &&
steps.cache-celeborn-bin.outputs.cache-hit != 'true' }}
run: |
wget -c ${{ inputs.celebornurl }} && \
mkdir -p celeborn-bin-${{ inputs.celebornver }} && \
@@ -245,7 +287,8 @@ jobs:
ls -la celeborn-bin-${{ inputs.celebornver }}/spark
cp celeborn-bin-${{ inputs.celebornver
}}/spark/celeborn-client-spark-*_${{ inputs.scalaver }}-*.jar spark-bin-${{
inputs.sparkver }}_${{ inputs.scalaver }}/jars/
- - uses: actions/cache@v4
+ - name: Cache Uniffle-${{ inputs.unifflever }}
+ uses: actions/cache@v4
if: ${{ inputs.unifflever != '' && inputs.uniffleurl != '' }}
id: cache-uniffle-bin
with:
@@ -254,13 +297,14 @@ jobs:
- name: Setup Uniffle-${{ inputs.unifflever }}
id: setup-uniffle-bin
- if: ${{ inputs.unifflever != '' && inputs.uniffleurl != '' &&
steps.cache-uniffle-bin.outputs.cache-hit != 'true' }}
+ if: ${{ inputs.unifflever != '' && inputs.uniffleurl != '' &&
steps.cache-uniffle-bin.outputs.cache-hit != 'true' }}
run: |
wget -c ${{ inputs.uniffleurl }} && \
mkdir -p uniffle-bin-${{ inputs.unifflever }} && \
tar -xf ./apache-uniffle-${{ inputs.unifflever
}}-incubating-bin.tar.gz -C uniffle-bin-${{ inputs.unifflever }}
--strip-component=1
- - uses: actions/cache@v4
+ - name: Cache hadoop-${{ inputs.hadoopver }}
+ uses: actions/cache@v4
if: ${{ inputs.hadoopver != '' && inputs.hadoopurl != '' }}
id: cache-hadoop-bin
with:
@@ -269,7 +313,7 @@ jobs:
- name: Setup hadoop-${{ inputs.hadoopver }}
id: setup-hadoop-bin
- if: ${{ inputs.hadoopver != '' && inputs.hadoopurl != '' &&
steps.cache-hadoop-bin.outputs.cache-hit != 'true' }}
+ if: ${{ inputs.hadoopver != '' && inputs.hadoopurl != '' &&
steps.cache-hadoop-bin.outputs.cache-hit != 'true' }}
run: |
wget -c ${{ inputs.hadoopurl }} && \
mkdir -p hadoop-bin-${{ inputs.hadoopver }} && \
@@ -292,13 +336,14 @@ jobs:
ls -la uniffle-bin-${{ inputs.unifflever }}/jars/client/spark3/
cp uniffle-bin-${{ inputs.unifflever }}/jars/client/spark3/*.jar
spark-bin-${{ inputs.sparkver }}_${{ inputs.scalaver }}/jars/
- - name: Run
+ - name: Run TPC-DS Query ${{ matrix.query }}
run: |
ls -la
export RUST_LOG=ERROR
export RUST_BACKTRACE=1
export SCALA_VERSION=${{ inputs.scalaver }}
- SPARK_HOME=spark-bin-${{ inputs.sparkver }}_${{ inputs.scalaver }}
dev/run-tpcds-test \
+ export SPARK_HOME=spark-bin-${{ inputs.sparkver }}_${{
inputs.scalaver }}
+ dev/run-tpcds-test \
${{ inputs.extrasparkconf }} \
--data-location dev/tpcds_1g \
--query-filter ${{ matrix.query }}
diff --git a/.github/workflows/tpcds.yml b/.github/workflows/tpcds.yml
index 7d2fca79..6da9dfbd 100644
--- a/.github/workflows/tpcds.yml
+++ b/.github/workflows/tpcds.yml
@@ -38,42 +38,42 @@ jobs:
uses: ./.github/workflows/tpcds-reusable.yml
with:
sparkver: spark-3.0
- sparkurl:
https://archive.apache.org/dist/spark/spark-3.0.3/spark-3.0.3-bin-hadoop2.7.tgz
+ hadoop-profile: 'hadoop2.7'
test-spark-31:
name: Test spark-3.1
uses: ./.github/workflows/tpcds-reusable.yml
with:
sparkver: spark-3.1
- sparkurl:
https://archive.apache.org/dist/spark/spark-3.1.3/spark-3.1.3-bin-hadoop2.7.tgz
+ hadoop-profile: 'hadoop2.7'
test-spark-32:
name: Test spark-3.2
uses: ./.github/workflows/tpcds-reusable.yml
with:
sparkver: spark-3.2
- sparkurl:
https://archive.apache.org/dist/spark/spark-3.2.4/spark-3.2.4-bin-hadoop2.7.tgz
+ hadoop-profile: 'hadoop2.7'
test-spark-33:
name: Test spark-3.3
uses: ./.github/workflows/tpcds-reusable.yml
with:
sparkver: spark-3.3
- sparkurl:
https://archive.apache.org/dist/spark/spark-3.3.4/spark-3.3.4-bin-hadoop3.tgz
+ hadoop-profile: 'hadoop3'
test-spark-34-jdk11:
name: Test spark-3.4
uses: ./.github/workflows/tpcds-reusable.yml
with:
sparkver: spark-3.4
- sparkurl:
https://archive.apache.org/dist/spark/spark-3.4.3/spark-3.4.3-bin-hadoop3.tgz
javaver: '11'
+ hadoop-profile: 'hadoop3'
test-spark-35-jdk17-scala-2-13:
name: Test spark-3.5 JDK17 Scala-2.13
uses: ./.github/workflows/tpcds-reusable.yml
with:
sparkver: spark-3.5
- sparkurl:
https://archive.apache.org/dist/spark/spark-3.5.5/spark-3.5.5-bin-hadoop3-scala2.13.tgz
javaver: '17'
scalaver: '2.13'
+ hadoop-profile: 'hadoop3'
diff --git a/.github/workflows/uniffle.yml b/.github/workflows/uniffle.yml
index 2367705e..373a5071 100644
--- a/.github/workflows/uniffle.yml
+++ b/.github/workflows/uniffle.yml
@@ -44,15 +44,15 @@ jobs:
uses: ./.github/workflows/tpcds-reusable.yml
name: Test Uniffle ${{ matrix.unifflever }}
with:
+ sparkver: "spark-3.5"
+ hadoop-profile: 'hadoop3'
+ scalaver: "2.12"
+ hadoopver: ${{ matrix.hadoopver }}
unifflever: ${{ matrix.unifflever }}
uniffleurl: https://archive.apache.org/dist/uniffle/${{
matrix.unifflever }}/apache-uniffle-${{ matrix.unifflever
}}-incubating-bin.tar.gz
- hadoopver: ${{ matrix.hadoopver }}
hadoopurl: https://archive.apache.org/dist/hadoop/common/hadoop-${{
matrix.hadoopver }}/hadoop-${{ matrix.hadoopver }}.tar.gz
extrabuildopt: -P${{ matrix.uniffleprofile }} -DuniffleVersion=${{
matrix.unifflever }}
extraidentifier: uniffle-${{ matrix.unifflever }}
- sparkver: "spark-3.5"
- sparkurl:
"https://archive.apache.org/dist/spark/spark-3.5.6/spark-3.5.6-bin-hadoop3.tgz";
- scalaver: "2.12"
extrasparkconf: >-
--conf
spark.shuffle.manager=org.apache.spark.sql.execution.auron.shuffle.uniffle.AuronUniffleShuffleManager
--conf spark.serializer=org.apache.spark.serializer.KryoSerializer
