This is an automated email from the ASF dual-hosted git repository.
yao pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-gluten.git
The following commit(s) were added to refs/heads/main by this push:
new b8feed90a4 Use build/mvn wrapper in velox_backend_x86 workflow (#11332)
b8feed90a4 is described below
commit b8feed90a43a900418612f62dc52985b29e44d5d
Author: Kent Yao <[email protected]>
AuthorDate: Mon Jan 5 20:06:50 2026 +0800
Use build/mvn wrapper in velox_backend_x86 workflow (#11332)
* Use build/mvn wrapper in velox_backend_x86 workflow
* Install wget in ubuntu jobs for Maven wrapper compatibility
* Use absolute path for build/mvn in Docker container
* Build gluten-it from project root using -pl option
* Build gluten-it from root in celeborn test job
* Build gluten-it from root in tpc-test-ubuntu job
* Revert to separate gluten-it builds - not in main reactor
* Use absolute path for MVN_CMD in gluten-it builds
* use repo.mvn
* cd
---
.github/workflows/velox_backend_x86.yml | 52 ++++++++++++++++-----------------
build/mvn | 49 ++++++++++---------------------
2 files changed, 40 insertions(+), 61 deletions(-)
diff --git a/.github/workflows/velox_backend_x86.yml
b/.github/workflows/velox_backend_x86.yml
index 1f3df3eaa8..9adde6c5ce 100644
--- a/.github/workflows/velox_backend_x86.yml
+++ b/.github/workflows/velox_backend_x86.yml
@@ -39,12 +39,12 @@ on:
- 'ep/build-velox/**'
- 'cpp/**'
- 'dev/**'
+ - 'build/mvn'
env:
ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION: true
- MVN_CMD: 'mvn -ntp'
+ MVN_CMD: 'build/mvn -ntp'
WGET_CMD: 'wget -nv'
- SETUP: 'source .github/workflows/util/setup-helper.sh'
CCACHE_DIR: "${{ github.workspace }}/.ccache"
# spark.sql.ansi.enabled defaults to false.
SPARK_ANSI_SQL_MODE: false
@@ -163,17 +163,17 @@ jobs:
apt-get update
TZ="Etc/GMT" DEBIAN_FRONTEND=noninteractive apt-get install -y
tzdata
fi
- - name: Setup java and maven
+ - name: Setup java
run: |
if [ "${{ matrix.java }}" = "java-17" ]; then
- apt-get update && apt-get install -y openjdk-17-jdk maven
+ apt-get update && apt-get install -y openjdk-17-jdk wget
apt remove openjdk-11* -y
elif [ "${{ matrix.java }}" = "java-21" ]; then
- apt-get update && apt-get install -y openjdk-21-jdk maven
+ apt-get update && apt-get install -y openjdk-21-jdk wget
elif [ "${{ matrix.java }}" = "java-11" ]; then
- apt-get update && apt-get install -y openjdk-11-jdk maven
+ apt-get update && apt-get install -y openjdk-11-jdk wget
else
- apt-get update && apt-get install -y openjdk-8-jdk maven
+ apt-get update && apt-get install -y openjdk-8-jdk wget
apt remove openjdk-11* -y
fi
ls -l
/root/.m2/repository/org/apache/arrow/arrow-dataset/15.0.0-gluten/
@@ -188,8 +188,8 @@ jobs:
$MVN_CMD clean install -P${{ matrix.spark }} -P${{ matrix.java }}
-Pbackends-velox -DskipTests
fi
cd $GITHUB_WORKSPACE/tools/gluten-it
- $MVN_CMD clean install -P${{ matrix.spark }} -P${{ matrix.java }} \
- && GLUTEN_IT_JVM_ARGS=-Xmx5G sbin/gluten-it.sh queries-compare \
+ $GITHUB_WORKSPACE/$MVN_CMD clean install -P${{ matrix.spark }} -P${{
matrix.java }}
+ GLUTEN_IT_JVM_ARGS=-Xmx5G sbin/gluten-it.sh queries-compare \
--local --preset=velox --benchmark-type=h --error-on-memleak
--off-heap-size=10g -s=1.0 --threads=16 --iterations=1 \
&& GLUTEN_IT_JVM_ARGS=-Xmx6G sbin/gluten-it.sh queries-compare \
--local --preset=velox --benchmark-type=ds --error-on-memleak
--off-heap-size=10g -s=1.0 --threads=16 --iterations=1
@@ -241,7 +241,7 @@ jobs:
sed -i -e "s|mirrorlist=|#mirrorlist=|g" /etc/yum.repos.d/CentOS-*
|| true
sed -i -e
"s|#baseurl=http://mirror.centos.org|baseurl=http://vault.centos.org|g"
/etc/yum.repos.d/CentOS-* || true
fi
- - name: Setup java and maven
+ - name: Setup java
run: |
if [ "${{ matrix.java }}" = "java-17" ]; then
yum update -y && yum install -y java-17-openjdk-devel wget
@@ -250,7 +250,6 @@ jobs:
else
yum update -y && yum install -y java-1.8.0-openjdk-devel wget
fi
- $SETUP install_maven
- name: Set environment variables
run: |
if [ "${{ matrix.java }}" = "java-17" ]; then
@@ -270,7 +269,7 @@ jobs:
$MVN_CMD clean install -P${{ matrix.spark }} -P${{ matrix.java }}
-Pbackends-velox -DskipTests
fi
cd $GITHUB_WORKSPACE/tools/gluten-it
- $MVN_CMD clean install -P${{ matrix.spark }} -P${{ matrix.java }}
+ $GITHUB_WORKSPACE/build/mvn clean install -P${{ matrix.spark }}
-P${{ matrix.java }}
- name: Run TPC-H / TPC-DS
run: |
echo "JAVA_HOME: $JAVA_HOME"
@@ -320,16 +319,15 @@ jobs:
sed -i -e 's|mirrorlist=|#mirrorlist=|g' /etc/yum.repos.d/CentOS-*
|| true
sed -i -e
's|#baseurl=http://mirror.centos.org|baseurl=http://vault.centos.org|g'
/etc/yum.repos.d/CentOS-* || true
- # Setup java and maven
yum update -y && yum install -y java-1.8.0-openjdk-devel wget
tzdata python3-pip
- $SETUP install_maven
# Set environment variables
export JAVA_HOME=/usr/lib/jvm/java-1.8.0-openjdk
+ # Build gluten
+ build/mvn -ntp clean install -P${{ matrix.spark }} -P${{
matrix.java }} -Pbackends-velox -DskipTests
# Build gluten-it
- mvn -ntp clean install -P${{ matrix.spark }} -P${{ matrix.java }}
-Pbackends-velox -DskipTests
cd /work/tools/gluten-it
- mvn -ntp clean install -P${{ matrix.spark }} -P${{ matrix.java }}
+ /work/build/mvn -ntp clean install -P${{ matrix.spark }} -P${{
matrix.java }}
# Run TPC-H / TPC-DS
GLUTEN_IT_JVM_ARGS=-Xmx5G sbin/gluten-it.sh queries-compare \
@@ -378,10 +376,10 @@ jobs:
with:
name: arrow-jars-centos-7-${{github.sha}}
path: /home/runner/.m2/repository/org/apache/arrow/
- - name: Setup java and maven
+ - name: Setup java
run: |
sudo apt-get update
- sudo apt-get install -y openjdk-8-jdk maven
+ sudo apt-get install -y openjdk-8-jdk wget
- name: Set environment variables
run: |
echo "JAVA_HOME=/usr/lib/jvm/java-8-openjdk-amd64" >> $GITHUB_ENV
@@ -390,7 +388,7 @@ jobs:
cd $GITHUB_WORKSPACE/
$MVN_CMD clean install -P${{ matrix.spark }} -Pbackends-velox
-DskipTests
cd $GITHUB_WORKSPACE/tools/gluten-it
- $MVN_CMD clean install -P${{ matrix.spark }}
+ $GITHUB_WORKSPACE/build/mvn clean install -P${{ matrix.spark }}
GLUTEN_IT_JVM_ARGS=-Xmx6G sbin/gluten-it.sh data-gen-only --local
--benchmark-type=ds -s=30.0 --threads=12
- name: TPC-DS SF30.0 Parquet local spark3.2 Q67/Q95 low memory, memory
isolation off
run: |
@@ -493,10 +491,10 @@ jobs:
with:
name: arrow-jars-centos-7-${{github.sha}}
path: /home/runner/.m2/repository/org/apache/arrow/
- - name: Setup java and maven
+ - name: Setup java
run: |
sudo apt-get update
- sudo apt-get install -y openjdk-8-jdk maven
+ sudo apt-get install -y openjdk-8-jdk wget
- name: Set environment variables
run: |
echo "JAVA_HOME=/usr/lib/jvm/java-8-openjdk-amd64" >> $GITHUB_ENV
@@ -505,7 +503,7 @@ jobs:
cd $GITHUB_WORKSPACE/
$MVN_CMD clean install -P${{ matrix.spark }} -Pbackends-velox
-DskipTests
cd $GITHUB_WORKSPACE/tools/gluten-it
- $MVN_CMD clean install -P${{ matrix.spark }}
+ $GITHUB_WORKSPACE/build/mvn clean install -P${{ matrix.spark }}
GLUTEN_IT_JVM_ARGS=-Xmx6G sbin/gluten-it.sh data-gen-only --local
--benchmark-type=ds -s=30.0 --threads=12
- name: TPC-DS SF30.0 Parquet local spark3.2 random kill tasks
run: |
@@ -561,7 +559,7 @@ jobs:
run: |
export JAVA_HOME=/usr/lib/jvm/java-1.8.0-openjdk && \
cd $GITHUB_WORKSPACE/tools/gluten-it && \
- $MVN_CMD clean install -P${{ matrix.spark }} -Puniffle && \
+ $GITHUB_WORKSPACE/build/mvn clean install -P${{ matrix.spark }}
-Puniffle && \
GLUTEN_IT_JVM_ARGS=-Xmx5G sbin/gluten-it.sh queries-compare \
--local --preset=velox-with-uniffle --benchmark-type=h
--error-on-memleak --off-heap-size=10g -s=1.0 --threads=16 --iterations=1
@@ -591,10 +589,9 @@ jobs:
run: |
sed -i -e "s|mirrorlist=|#mirrorlist=|g" /etc/yum.repos.d/CentOS-*
|| true
sed -i -e
"s|#baseurl=http://mirror.centos.org|baseurl=http://vault.centos.org|g"
/etc/yum.repos.d/CentOS-* || true
- - name: Setup java and maven
+ - name: Setup java
run: |
yum update -y && yum install -y java-1.8.0-openjdk-devel wget
- $SETUP install_maven
- name: Set environment variables
run: |
echo "JAVA_HOME=/usr/lib/jvm/java-1.8.0-openjdk" >> $GITHUB_ENV
@@ -621,7 +618,8 @@ jobs:
bash -c "echo -e
'CELEBORN_MASTER_MEMORY=8g\nCELEBORN_WORKER_MEMORY=8g\nCELEBORN_WORKER_OFFHEAP_MEMORY=16g'
> ./conf/celeborn-env.sh" && \
bash -c "echo -e 'celeborn.worker.commitFiles.threads
32\nceleborn.worker.sortPartition.threads 16' > ./conf/celeborn-defaults.conf"
&& \
bash ./sbin/start-master.sh && bash ./sbin/start-worker.sh && \
- cd $GITHUB_WORKSPACE/tools/gluten-it && $MVN_CMD clean install
-Pspark-3.2 -Pceleborn ${EXTRA_PROFILE} && \
+ cd $GITHUB_WORKSPACE && $MVN_CMD clean install -Pspark-3.2
-Pceleborn ${EXTRA_PROFILE} -Pbackends-velox -DskipTests && \
+ cd $GITHUB_WORKSPACE/tools/gluten-it && $GITHUB_WORKSPACE/$MVN_CMD
clean install -Pspark-3.2 -Pceleborn ${EXTRA_PROFILE} && \
GLUTEN_IT_JVM_ARGS=-Xmx16G sbin/gluten-it.sh queries-compare \
--extra-conf=spark.celeborn.client.spark.shuffle.writer=${{
matrix.writer }} \
--extra-conf=spark.sql.shuffle.partitions=16 \
@@ -1374,7 +1372,7 @@ jobs:
cd /work
bash dev/builddeps-veloxbe.sh --run_setup_script=OFF
--build_arrow=OFF --build_tests=ON --build_benchmarks=ON --enable_gpu=ON #
TODO: re-enable tests with more disk space
rm -rf ep/build-velox/build/velox_ep
- mvn clean package -Pbackends-velox -Pspark-3.4 -DskipTests
+ build/mvn clean package -Pbackends-velox -Pspark-3.4 -DskipTests
ccache -s
"
diff --git a/build/mvn b/build/mvn
index 2c6e27ca76..f20ea7f7b8 100755
--- a/build/mvn
+++ b/build/mvn
@@ -62,47 +62,28 @@ install_mvn() {
local MVN_TAR="${MVN_DOWNLOAD_DIR}/apache-maven-${VERSION}-bin.tar.gz"
if [ ! -f "${MVN_TAR}" ]; then
- # Construct download URL using Apache closer.lua for better mirror
selection
- local
APACHE_MIRROR="${APACHE_MIRROR:-https://www.apache.org/dyn/closer.lua}"
- local
MVN_DOWNLOAD_PATH="maven/maven-3/${VERSION}/binaries/apache-maven-${VERSION}-bin.tar.gz"
+ # Use Maven Central repository for download
+ local
DOWNLOAD_URL="https://repo1.maven.org/maven2/org/apache/maven/apache-maven/${VERSION}/apache-maven-${VERSION}-bin.tar.gz"
- # Try Apache closer.lua first (redirects to nearest mirror)
- local
DOWNLOAD_URL="${APACHE_MIRROR}?action=download&filename=${MVN_DOWNLOAD_PATH}"
-
- echo "Downloading Maven ${VERSION} from Apache mirror service..."
>&2
+ echo "Downloading Maven ${VERSION} from Maven Central..." >&2
echo "URL: ${DOWNLOAD_URL}" >&2
if command -v curl > /dev/null 2>&1; then
- # Use -L to follow redirects from closer.lua
- if ! curl -f -L --retry 3 --retry-delay 3 \
+ curl -f -L --retry 3 --retry-delay 3 \
--connect-timeout 30 --max-time 600 \
- -o "${MVN_TAR}" "${DOWNLOAD_URL}"; then
- echo "Download failed via closer.lua, trying
archive.apache.org..." >&2
- # Fallback to archive if closer.lua fails
- local
FALLBACK_URL="https://archive.apache.org/dist/${MVN_DOWNLOAD_PATH}"
- curl -f -L --retry 3 --retry-delay 3 \
- --connect-timeout 30 --max-time 600 \
- -o "${MVN_TAR}" "${FALLBACK_URL}" || {
- echo "ERROR: Failed to download Maven from
${FALLBACK_URL}" >&2
- rm -f "${MVN_TAR}"
- exit 1
- }
- fi
+ -o "${MVN_TAR}" "${DOWNLOAD_URL}" || {
+ echo "ERROR: Failed to download Maven from
${DOWNLOAD_URL}" >&2
+ rm -f "${MVN_TAR}"
+ exit 1
+ }
elif command -v wget > /dev/null 2>&1; then
- # wget follows redirects by default
- if ! wget --tries=3 --waitretry=3 \
+ wget --tries=3 --waitretry=3 \
--connect-timeout=30 --read-timeout=600 \
- -O "${MVN_TAR}" "${DOWNLOAD_URL}"; then
- echo "Download failed via closer.lua, trying
archive.apache.org..." >&2
- local
FALLBACK_URL="https://archive.apache.org/dist/${MVN_DOWNLOAD_PATH}"
- wget --tries=3 --waitretry=3 \
- --connect-timeout=30 --read-timeout=600 \
- -O "${MVN_TAR}" "${FALLBACK_URL}" || {
- echo "ERROR: Failed to download Maven from
${FALLBACK_URL}" >&2
- rm -f "${MVN_TAR}"
- exit 1
- }
- fi
+ -O "${MVN_TAR}" "${DOWNLOAD_URL}" || {
+ echo "ERROR: Failed to download Maven from
${DOWNLOAD_URL}" >&2
+ rm -f "${MVN_TAR}"
+ exit 1
+ }
else
echo "ERROR: Neither curl nor wget found. Please install one
of them or install Maven manually." >&2
exit 1
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]