Merge branch 'main' into iceberg_10

FelixYBW · web-flow · commit 078cf47a1045 · 2025-11-19T01:21:26.000-08:00
diff --git a/.github/workflows/docker_image.yml b/.github/workflows/docker_image.yml
@@ -159,7 +159,7 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [ ubuntu-latest ] #TODO: adding arm back
+        os: [ ubuntu-latest, ubuntu-24.04-arm ]
 
     steps:
       - name: Checkout repository
@@ -385,10 +385,9 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        digests: [ vcpkg-centos-8, vcpkg-centos-8-gcc13, vcpkg-centos-9, centos-8-jdk8, centos-8-jdk11, centos-8-jdk17, centos-9-jdk8, centos-9-jdk11, centos-9-jdk17 ]
+        digests: [ vcpkg-centos-8, vcpkg-centos-9, centos-8-jdk8, centos-8-jdk11, centos-8-jdk17, centos-9-jdk8, centos-9-jdk11, centos-9-jdk17 ]
     needs:
       - build-vcpkg-centos-8
-      - build-vcpkg-centos-8-gcc13
       - build-vcpkg-centos-9
       - build-centos-8
       - build-centos-9
@@ -397,7 +396,7 @@ jobs:
         uses: actions/download-artifact@v4
         with:
           path: ${{ runner.temp }}/digests
-          pattern: digests-${{ matrix.digests }}-*
+          pattern: digests-${{ matrix.digests }}-ubuntu*
           merge-multiple: true
 
       - name: Login to Docker Hub
@@ -425,4 +424,45 @@ jobs:
       - name: Inspect image
         run: |
           docker buildx imagetools inspect ${{ env.DOCKERHUB_REPO }}:${{ steps.meta.outputs.version }}
+  
+  merge-gcc13:
+    if: ${{ startsWith(github.repository, 'apache/') }}
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        digests: [ vcpkg-centos-8-gcc13 ]
+    needs:
+      - build-vcpkg-centos-8-gcc13
+    steps:
+      - name: Download digests
+        uses: actions/download-artifact@v4
+        with:
+          path: ${{ runner.temp }}/digests
+          pattern: digests-${{ matrix.digests }}-*
+          merge-multiple: true
 
+      - name: Login to Docker Hub
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKERHUB_USER }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Docker meta
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.DOCKERHUB_REPO }}
+          tags: ${{ matrix.digests }}
+
+      - name: Create manifest list and push
+        working-directory: ${{ runner.temp }}/digests
+        run: |
+          docker buildx imagetools create $(jq -cr '.tags | map("-t " + .) | join(" ")' <<< "$DOCKER_METADATA_OUTPUT_JSON") \
+            $(printf '${{ env.DOCKERHUB_REPO }}@sha256:%s ' *)
+
+      - name: Inspect image
+        run: |
+          docker buildx imagetools inspect ${{ env.DOCKERHUB_REPO }}:${{ steps.meta.outputs.version }}
diff --git a/.github/workflows/velox_backend_x86.yml b/.github/workflows/velox_backend_x86.yml
@@ -555,7 +555,8 @@ jobs:
       fail-fast: false
       matrix:
         spark: [ "spark-3.2" ]
-        celeborn: [ "celeborn-0.6.1", "celeborn-0.5.4", "celeborn-0.4.3"]
+        celeborn: [ "celeborn-0.6.1", "celeborn-0.5.4"]
+        writer: [ "sort", "hash"]
     runs-on: ubuntu-22.04
     container: apache/gluten:centos-8-jdk8
     steps:
@@ -577,9 +578,7 @@ jobs:
       - name: TPC-H SF1.0 && TPC-DS SF1.0 Parquet local spark3.2 with ${{ matrix.celeborn }}
         run: |
           EXTRA_PROFILE=""
-          if [ "${{ matrix.celeborn }}" = "celeborn-0.4.3" ]; then
-            EXTRA_PROFILE="-Pceleborn-0.4"
-          elif [ "${{ matrix.celeborn }}" = "celeborn-0.5.4" ]; then
+          if [ "${{ matrix.celeborn }}" = "celeborn-0.5.4" ]; then
             EXTRA_PROFILE="-Pceleborn-0.5"
           elif [ "${{ matrix.celeborn }}" = "celeborn-0.6.1" ]; then
             EXTRA_PROFILE="-Pceleborn-0.6"
@@ -592,23 +591,31 @@ jobs:
           cd /opt && mkdir -p celeborn && \
           tar xzf apache-${{ matrix.celeborn }}-bin.tgz -C /opt/celeborn --strip-components=1 && cd celeborn && \
           mv ./conf/celeborn-env.sh.template ./conf/celeborn-env.sh && \
-          bash -c "echo -e 'CELEBORN_MASTER_MEMORY=4g\nCELEBORN_WORKER_MEMORY=4g\nCELEBORN_WORKER_OFFHEAP_MEMORY=8g' > ./conf/celeborn-env.sh" && \
-          bash -c "echo -e 'celeborn.worker.commitFiles.threads 128\nceleborn.worker.sortPartition.threads 64' > ./conf/celeborn-defaults.conf" && \
+          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 ${EXTRA_PROFILE} && \
-          GLUTEN_IT_JVM_ARGS=-Xmx10G sbin/gluten-it.sh queries-compare \
-            --local --preset=velox-with-celeborn --benchmark-type=h --error-on-memleak --off-heap-size=10g -s=1.0 --threads=8 --iterations=1 && \
-          GLUTEN_IT_JVM_ARGS=-Xmx10G sbin/gluten-it.sh queries-compare \
-            --local --preset=velox-with-celeborn --benchmark-type=ds --error-on-memleak --off-heap-size=10g -s=1.0 --threads=8 --iterations=1 && \
-          GLUTEN_IT_JVM_ARGS=-Xmx10G sbin/gluten-it.sh queries-compare \
-            --local --preset=velox-with-celeborn --extra-conf=spark.celeborn.client.spark.shuffle.writer=sort \
-            --extra-conf=spark.celeborn.push.sortMemory.threshold=8m --benchmark-type=ds --error-on-memleak \
-            --off-heap-size=10g -s=1.0 --threads=8 --iterations=1
-          GLUTEN_IT_JVM_ARGS=-Xmx10G sbin/gluten-it.sh queries-compare \
-            --local --preset=velox-with-celeborn --extra-conf=spark.celeborn.client.spark.shuffle.writer=sort \
-            --extra-conf=spark.gluten.sql.columnar.shuffle.celeborn.useRssSort=false \
-            --extra-conf=spark.celeborn.push.sortMemory.threshold=8m --benchmark-type=ds --error-on-memleak \
-            --off-heap-size=10g -s=1.0 --threads=8 --iterations=1
+          GLUTEN_IT_JVM_ARGS=-Xmx16G sbin/gluten-it.sh queries-compare \
+            --extra-conf=spark.celeborn.client.spark.shuffle.writer=${{ matrix.writer }} \
+            --extra-conf=spark.sql.shuffle.partitions=16 \
+            --extra-conf=spark.celeborn.client.eagerlyCreateInputStream.threads=4 \
+            --local --preset=velox-with-celeborn --benchmark-type=h --error-on-memleak --off-heap-size=16g -s=1.0 --threads=16 --iterations=1 && \
+          GLUTEN_IT_JVM_ARGS=-Xmx16G sbin/gluten-it.sh queries-compare \
+            --local --preset=velox-with-celeborn --extra-conf=spark.celeborn.client.spark.shuffle.writer=${{ matrix.writer }} \
+            --extra-conf=spark.gluten.sql.columnar.shuffle.celeborn.useRssSort=true \
+            --extra-conf=spark.sql.shuffle.partitions=16 \
+            --extra-conf=spark.celeborn.client.eagerlyCreateInputStream.threads=4 \
+            --benchmark-type=ds --error-on-memleak \
+            --off-heap-size=16g -s=1.0 --threads=16 --iterations=1
+          if [ "${{ matrix.writer }}" = "sort" ]; then
+            GLUTEN_IT_JVM_ARGS=-Xmx16G sbin/gluten-it.sh queries-compare \
+              --local --preset=velox-with-celeborn --extra-conf=spark.celeborn.client.spark.shuffle.writer=${{ matrix.writer }} \
+              --extra-conf=spark.gluten.sql.columnar.shuffle.celeborn.useRssSort=false \
+              --extra-conf=spark.celeborn.client.eagerlyCreateInputStream.threads=4 \
+              --extra-conf=spark.sql.shuffle.partitions=16 \
+              --benchmark-type=ds --error-on-memleak \
+              --off-heap-size=16g -s=1.0 --threads=16 --iterations=1
+          fi
 
   spark-test-spark32:
     needs: build-native-lib-centos-7
diff --git a/cpp/velox/jni/VeloxJniWrapper.cc b/cpp/velox/jni/VeloxJniWrapper.cc
@@ -559,8 +559,13 @@ Java_org_apache_gluten_datasource_VeloxDataSourceJniWrapper_splitBlockByPartitio
   const auto inputRowVector = veloxBatch->getRowVector();
   const auto numRows = inputRowVector->size();
 
-  connector::hive::PartitionIdGenerator idGen{
-      asRowType(inputRowVector->type()), partitionColIndicesVec, 128, pool.get(), true};
+  connector::hive::PartitionIdGenerator idGen(
+      asRowType(inputRowVector->type()), partitionColIndicesVec, 128, pool.get()
+#ifdef GLUTEN_ENABLE_ENHANCED_FEATURES
+      ,
+      true
+#endif    
+    );
   raw_vector<uint64_t> partitionIds{};
   idGen.run(inputRowVector, partitionIds);
   GLUTEN_CHECK(partitionIds.size() == numRows, "Mismatched number of partition ids");
diff --git a/dev/docker/Dockerfile.centos8-dynamic-build b/dev/docker/Dockerfile.centos8-dynamic-build
@@ -40,7 +40,6 @@ RUN set -ex; \
     tar -xvf ${local_binary}; \
     mv apache-maven-${maven_version} /usr/lib/maven; \
     rm -rf ${local_binary}; \
-    wget -nv https://archive.apache.org/dist/celeborn/celeborn-0.4.3/apache-celeborn-0.4.3-bin.tgz -P /opt/; \
     wget -nv https://archive.apache.org/dist/celeborn/celeborn-0.5.4/apache-celeborn-0.5.4-bin.tgz -P /opt/; \
     wget -nv https://archive.apache.org/dist/celeborn/celeborn-0.6.1/apache-celeborn-0.6.1-bin.tgz -P /opt/; \
     wget -nv https://archive.apache.org/dist/incubator/uniffle/0.9.2/apache-uniffle-0.9.2-incubating-bin.tar.gz -P /opt/; \
diff --git a/dev/docker/Dockerfile.centos8-gcc13 b/dev/docker/Dockerfile.centos8-gcc13
@@ -16,11 +16,19 @@
 # copied from https://github.com/jeromerobert/centos7-gcc13
 FROM centos:8 as base0
 
-FROM base0 as base
+FROM base0 as base1
 RUN /usr/bin/sed -i -e "s|mirrorlist=|#mirrorlist=|g" /etc/yum.repos.d/CentOS-*; sed -i -e "s|#baseurl=http://mirror.centos.org|baseurl=http://vault.centos.org|g" /etc/yum.repos.d/CentOS-*;
 RUN yum update -y && yum install epel-release wget perl -y
-RUN yum -y install ftp://ftp.icm.edu.pl/vol/rzm5/linux-centos-vault/8.0.1905/PowerTools/aarch64/kickstart/Packages/perl-Unicode-EastAsianWidth-1.33-13.el8.noarch.rpm ftp://ftp.icm.edu.pl/vol/rzm5/linux-centos-vault/8.2.2004/PowerTools/x86_64/kickstart/Packages/texinfo-6.5-6.el8.x86_64.rpm
 
+# texinfo
+FROM base1 as base
+RUN curl -kLO https://ftp.gnu.org/gnu/texinfo/texinfo-6.8.tar.xz
+RUN tar xf texinfo*.tar.*
+WORKDIR build-texinfo
+RUN yum -y install gcc make m4
+RUN ../texinfo*/configure
+RUN make -j$(nproc)
+RUN make install
 
 # Git
 FROM base as git
diff --git a/dev/docker/Dockerfile.centos8-gcc13-static-build b/dev/docker/Dockerfile.centos8-gcc13-static-build
@@ -13,7 +13,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-FROM inteldpo/gluten:centos8_gcc13
+FROM inteldpo/gluten-ci-images:centos-8_gcc13
 
 
 ENV JAVA_HOME=/usr/lib/jvm/java-1.8.0-openjdk
@@ -27,15 +27,16 @@ ENV VCPKG_BINARY_SOURCES=clear;files,${VCPKG_PATH},readwrite
 
 RUN set -ex; \
     yum update -y && yum install -y epel-release sudo dnf && yum install -y ccache; \
-    dnf install -y --setopt=install_weak_deps=False gcc-toolset-11; \
     echo "check_certificate = off" >> ~/.wgetrc; \
-    yum install -y java-1.8.0-openjdk-devel patch wget git perl; \
+    yum install -y java-1.8.0-openjdk-devel patch wget git perl python3 automake libtool flex; \
+    dnf -y --enablerepo=powertools install autoconf-archive ninja-build; \
+    pip3 install --upgrade pip; \
+    pip3 install cmake; \
     rpm -qa | grep tzdata; \
     dnf clean all; \
     git clone --depth=1 https://github.com/apache/incubator-gluten /opt/gluten; \
-    cd /opt/gluten && bash ./dev/vcpkg/setup-build-depends.sh; \
-    yum remove gcc -y && yum clean all; \
-    yes | cp -rf /usr/share/aclocal/* /usr/local/share/aclocal/; \
+    cd /opt/gluten; bash .github/workflows/util/setup-helper.sh install_maven; \
+    export PATH=/usr/lib/maven/bin:$PATH; \
     mkdir -p ${VCPKG_PATH}; \
     echo "Build arrow, then install the native libs to system paths and jar package to .m2/ directory."; \
     if [ "$(uname -m)" = "aarch64" ]; then \
diff --git a/dev/docker/Dockerfile.centos9-dynamic-build b/dev/docker/Dockerfile.centos9-dynamic-build
@@ -38,7 +38,6 @@ RUN set -ex; \
     tar -xvf ${local_binary}; \
     mv apache-maven-${maven_version} /usr/lib/maven; \
     rm -rf ${local_binary}; \
-    wget -nv https://archive.apache.org/dist/celeborn/celeborn-0.4.3/apache-celeborn-0.4.3-bin.tgz -P /opt/; \
     wget -nv https://archive.apache.org/dist/celeborn/celeborn-0.5.4/apache-celeborn-0.5.4-bin.tgz -P /opt/; \
     wget -nv https://archive.apache.org/dist/celeborn/celeborn-0.6.1/apache-celeborn-0.6.1-bin.tgz -P /opt/; \
     wget -nv https://archive.apache.org/dist/incubator/uniffle/0.9.2/apache-uniffle-0.9.2-incubating-bin.tar.gz -P /opt/; \
diff --git a/dev/vcpkg/CONTRIBUTING.md b/dev/vcpkg/CONTRIBUTING.md
@@ -13,7 +13,7 @@ Please init vcpkg env first:
 
 Vcpkg already maintains a lot of libraries.
 You can find them by vcpkg cli.
-(NOTE: Please always use cli because [packages on vcpkg.io](https://vcpkg.io/en/packages.html) is outdate).
+(NOTE: Please always use cli because [packages on vcpkg.io](https://vcpkg.io/en/packages.html) is outdated).
 
 ```
 $ ./.vcpkg/vcpkg search folly
@@ -65,37 +65,11 @@ See also [Versioning](https://learn.microsoft.com/en-us/vcpkg/users/versioning).
 
 Otherwise, you must create a new port in `./ports/$package` to override the vcpkg's original version.
 
-**If a new ports has been merged in vcpkg main branch**.
-You can find git tree-ish and checkout it.
-For example, arrow 12.0.0 has been merged but not include in last release (2023.04.15).
-
-``` patch
-# https://patch-diff.githubusercontent.com/raw/microsoft/vcpkg/pull/31321.patch
-
-diff --git a/versions/a-/arrow.json b/versions/a-/arrow.json
-index 07c7ef67cb27c..f7bbe94b4f914 100644
---- a/versions/a-/arrow.json
-+++ b/versions/a-/arrow.json
-@@ -1,5 +1,10 @@
- {
-   "versions": [
-+    {
-+      "git-tree": "881bfaaab349dae46929b36e5b84e7036a009ad3",
-+      "version": "12.0.0",
-+      "port-version": 0
-+    },
-     {
-       "git-tree": "21fea47a1e9c7bf68e6c088ad5a6b7b6e33c2fcb",
-       "version": "11.0.0",
-```
-
-Git tree-ish is `21fea47a1e9c7bf68e6c088ad5a6b7b6e33c2fcb`. Then fetch and checkout it.
-
-``` sh
-cd .vcpkg
-git fetch origin master
-git archive 21fea47a1e9c7bf68e6c088ad5a6b7b6e33c2fcb | tar -x -C ../ports/arrow
-```
+**If a newer version of a library is supported in a later version of vcpkg**.
+Developers can configure `vcpkg-configuration.json` to allow importing a new port, overriding the
+corresponding port specified in the `builtin-baseline`. This approach also applies to libraries
+that have been removed from vcpkg at the `builtin-baseline`; by setting a historical vcpkg version,
+you can import such ports.
 
 **If you want to modify port based on vcpkg version**.
 Copy port directory from `./.vcpkg/ports/$package` to `./ports/$package`.
diff --git a/dev/vcpkg/README.md b/dev/vcpkg/README.md
@@ -1,8 +1,18 @@
 # Build Gluten + Velox in Vcpkg Environment
 
-## Build in Docker
+## Overview
+
+Currently, the `builtin-baseline` set in `vcpkg.json` is the commit hash for the `2025.09.17` tag of vcpkg.
+The versions of all dependency libraries are determined by their respective ports at this vcpkg version,
+except for those overridden in `vcpkg.json`, `vcpkg-configuration.json`, and overlay ports.
+
+## Build in docker
+
+For main branch code, you can follow the commands below.
+- Pull the docker image: `docker pull apache/gluten:vcpkg-centos-7`
+- Build native code: `bash dev/ci-velox-buildstatic-centos-7.sh`
+- Build JVM code: `mvn clean install -Pbackends-velox -Pspark-3.5 -DskipTests`
 
-Please install make and docker on your system, then `make`.
 The gluten packages will be placed in `$GLUTEN_REPO/package/target/gluten-velox-bundle-*.jar`.
 
 ## Setup build environment manually
@@ -15,7 +25,7 @@ Please install build depends on your system to compile all libraries:
 sudo $GLUTEN_REPO/dev/vcpkg/setup-build-depends.sh
 ```
 
-GCC-11 is the minimum required compiler. It needs to be enabled beforehand. Take Centos-7/8 as example:
+GCC 11 is the minimum required compiler. It needs to be enabled beforehand. Take Centos 7/8 as example:
 
 ``` sh
 # CentOS 8
@@ -32,7 +42,7 @@ For unsupported linux distro, you can install the following packages from packag
 * wget
 * curl
 * git >= 2.7.4
-* gcc >= 9
+* gcc >= 11
 * pkg-config
 * autotools
 * flex >= 2.6.0
@@ -48,4 +58,4 @@ You can configure [binary cache](https://learn.microsoft.com/en-us/vcpkg/users/b
 
 ``` sh
 $GLUTEN_REPO/dev/buildbundle-veloxbe.sh --enable_vcpkg=ON --build_tests=ON --build_benchmarks=ON --enable_s3=ON  --enable_hdfs=ON
-```
+```
diff --git a/dev/vcpkg/init.sh b/dev/vcpkg/init.sh
@@ -68,13 +68,12 @@ SCRIPT_ROOT="$(realpath "$(dirname "$0")")"
 cd "$SCRIPT_ROOT"
 
 if [ ! -d "$VCPKG_ROOT" ] || [ -z "$(ls "$VCPKG_ROOT")" ]; then
-    git clone https://github.com/microsoft/vcpkg.git --branch 2023.10.19 "$VCPKG_ROOT"
+    # The builtin-baseline (commit hash) specified in vcpkg.json should exist in this branch.
+    # Therefore, upgrading the builtin-baseline may require updating the branch.
+    git clone https://github.com/microsoft/vcpkg.git --branch 2025.09.17 "$VCPKG_ROOT"
 fi
 [ -f "$VCPKG" ] || "$VCPKG_ROOT/bootstrap-vcpkg.sh" -disableMetrics
 
-sed -i "s/3.27.1/3.28.3/g" $VCPKG_ROOT/scripts/vcpkgTools.xml
-sed -i "s/192374a68e2971f04974a194645726196d9b8ee7abd650d1e6f65f7aa2ccc9b186c3edb473bb4958c764532edcdd42f4182ee1fcb86b17d78b0bcd6305ce3df1/bd311ca835ef0914952f21d70d1753564d58de2ede02e80ede96e78cd2f40b4189e006007643ebb37792e13edd97eb4a33810bc8aca1eab6dd428eaffe1d2e38/g" $VCPKG_ROOT/scripts/vcpkgTools.xml
-
 EXTRA_FEATURES=""
 if [ "$BUILD_TESTS" = "ON" ]; then
   EXTRA_FEATURES+="--x-feature=duckdb "
diff --git a/dev/vcpkg/ports/aws-sdk-cpp/portfile.cmake b/dev/vcpkg/ports/aws-sdk-cpp/portfile.cmake
@@ -45,7 +45,7 @@ vcpkg_cmake_configure(
         "-DBUILD_SHARED_LIBS=OFF"
         "-DAWS_SDK_WARNINGS_ARE_ERRORS=OFF"
         "-DCMAKE_INSTALL_RPATH=${rpath}"
-        "-DCMAKE_MODULE_PATH=${CURRENT_INSTALLED_DIR}/share/aws-c-common" # use extra cmake files
+        "-DCMAKE_MODULE_PATH=${CURRENT_INSTALLED_DIR}/share/aws-c-common/modules" # use extra cmake files
 )
 vcpkg_cmake_install()
 
diff --git a/dev/vcpkg/vcpkg-configuration.json b/dev/vcpkg/vcpkg-configuration.json
@@ -14,6 +14,12 @@
       "repository": "https://github.com/Microsoft/vcpkg",
       "baseline": "f82160a747b1b529daad7ce2f75a0d6c6a0d285d",
       "packages": [ "google-cloud-cpp"]
+    },
+    {
+      "kind": "git",
+      "repository": "https://github.com/Microsoft/vcpkg",
+      "baseline": "a7b6122f6b6504d16d96117336a0562693579933",
+      "packages": [ "upb"]
     }
 
   ]
diff --git a/dev/vcpkg/vcpkg.json b/dev/vcpkg/vcpkg.json
@@ -1,6 +1,6 @@
 {
   "$schema": "https://raw.githubusercontent.com/microsoft/vcpkg-tool/main/docs/vcpkg.schema.json",
-  "builtin-baseline": "a7b6122f6b6504d16d96117336a0562693579933",
+  "builtin-baseline": "4334d8b4c8916018600212ab4dd4bbdc343065d1",
   "default-features": ["velox"],
   "features": {
     "velox": {
@@ -108,6 +108,13 @@
   "overrides": [
     { "name": "fmt", "version": "10.1.1" },
     { "name": "liblzma", "version": "5.6.2" },
-    { "name": "xsimd", "version": "10.0.0" }
+    { "name": "xsimd", "version": "10.0.0" },
+    { "name": "snappy", "version": "1.1.8"},
+    { "name": "protobuf", "version": "3.21.8"},
+    { "name": "abseil", "version": "20230802.1"},
+    { "name": "re2", "version": "2023-07-01"},
+    { "name": "glog", "version": "0.6.0"},
+    { "name": "gflags", "version": "2.2.2"},
+    { "name": "azure-identity-cpp", "version": "1.11.0"}
   ]
 }
diff --git a/ep/build-velox/src/get-velox.sh b/ep/build-velox/src/get-velox.sh
diff --git a/gluten-ut/spark40/src/test/scala/org/apache/gluten/utils/velox/VeloxTestSettings.scala b/gluten-ut/spark40/src/test/scala/org/apache/gluten/utils/velox/VeloxTestSettings.scala
diff --git a/tools/gluten-it/pom.xml b/tools/gluten-it/pom.xml
