[GLUTEN-6887][VL] Daily Update Velox Version (2026_06_12)

.github/workflows/velox_backend_arm.yml

@@ -66,6 +66,7 @@ jobs:
       - name: Build Gluten native libraries
         run: |
           df -a
+          pip install cmake==3.31.4
           bash dev/ci-velox-buildstatic-centos-9.sh
           ccache -s
       - name: "Save ccache"

.github/workflows/velox_backend_x86.yml

@@ -1178,7 +1178,7 @@ jobs:
           mkdir -p /work/.ccache
 
           cd /work
-          bash dev/builddeps-veloxbe.sh --run_setup_script=OFF --build_arrow=OFF --build_tests=ON --build_benchmarks=ON --enable_gpu=ON
+          bash dev/builddeps-veloxbe.sh --run_setup_script=ON --build_arrow=OFF --build_tests=ON --build_benchmarks=ON --enable_gpu=ON
           rm -rf ep/build-velox/build/velox_ep
           build/mvn clean package -Pbackends-velox -Pspark-3.4 -DskipTests
           ccache -s

cpp/velox/CMakeLists.txt

@@ -375,6 +375,51 @@ else()
 endif()
 target_link_libraries(velox PUBLIC external::geos)
 
+find_package(veloxthrift CONFIG)
+if(veloxthrift_FOUND AND TARGET veloxthrift::veloxthrift)
+  add_library(external::veloxthrift ALIAS veloxthrift::veloxthrift)
+else()
+  message(STATUS "import Velox bundled veloxthrift")
+  import_library(external::veloxthrift ${VELOX_BUILD_PATH}/velox/dwio/parquet/thrift/libvelox_dwio_parquet_thrift_raw.a)
+endif()
+target_link_libraries(velox PUBLIC external::veloxthrift)
+
+# Link thrift libraries - check vcpkg first, then fall back to system libraries
+# Determine vcpkg triplet directory based on architecture
+if(CMAKE_SYSTEM_PROCESSOR MATCHES "(x86)|(X86)|(amd64)|(AMD64)")
+  set(VCPKG_TRIPLET_DIR "x64-linux-avx")
+elseif(CMAKE_SYSTEM_PROCESSOR MATCHES "(aarch64)|(arm64)")
+  set(VCPKG_TRIPLET_DIR "arm64-linux-neon")
+else()
+  message(WARNING "Unknown processor type for vcpkg: ${CMAKE_SYSTEM_PROCESSOR}, defaulting to x64-linux-avx")
+  set(VCPKG_TRIPLET_DIR "x64-linux-avx")
+endif()
+
+if(DEFINED VCPKG_INSTALLED_DIR AND EXISTS "${VCPKG_INSTALLED_DIR}/${VCPKG_TRIPLET_DIR}/lib/libthriftcpp2.a")
+  message(STATUS "Using vcpkg thrift libraries from ${VCPKG_INSTALLED_DIR}/${VCPKG_TRIPLET_DIR}")
+  target_link_libraries(
+    velox
+    PRIVATE
+      ${VCPKG_INSTALLED_DIR}/${VCPKG_TRIPLET_DIR}/lib/libthriftcpp2.a
+      ${VCPKG_INSTALLED_DIR}/${VCPKG_TRIPLET_DIR}/lib/libthriftprotocol.a
+  )
+else()
+  message(STATUS "Using system thrift libraries from /usr/local/lib")
+  find_library(THRIFTCPP2_LIB NAMES thriftcpp2 PATHS /usr/local/lib NO_DEFAULT_PATH)
+  find_library(THRIFTPROTOCOL_LIB NAMES thriftprotocol PATHS /usr/local/lib NO_DEFAULT_PATH)
+
+  if(THRIFTCPP2_LIB AND THRIFTPROTOCOL_LIB)
+    target_link_libraries(
+      velox
+      PRIVATE
+        ${THRIFTCPP2_LIB}
+        ${THRIFTPROTOCOL_LIB}
+    )
+  else()
+    message(FATAL_ERROR "Could not find thrift libraries. Please install them or use vcpkg.")
+  endif()
+endif()
+
 find_package(simdjson CONFIG)
 if(simdjson_FOUND AND TARGET simdjson::simdjson)
   target_link_libraries(velox PUBLIC simdjson::simdjson)

cpp/velox/utils/ConfigExtractor.cc

@@ -233,8 +233,6 @@ std::shared_ptr<facebook::velox::config::ConfigBase> createHiveConnectorSessionC
   configs[facebook::velox::connector::hive::HiveConfig::kReadTimestampUnitSession] = std::string("6");
   configs[facebook::velox::connector::hive::HiveConfig::kMaxPartitionsPerWritersSession] =
       conf->get<std::string>(kMaxPartitions, "10000");
-  configs[facebook::velox::connector::hive::HiveConfig::kMaxTargetFileSize] =
-      conf->get<std::string>(kMaxTargetFileSize, "0B"); // 0 means no limit on target file size
   configs[facebook::velox::connector::hive::HiveConfig::kIgnoreMissingFilesSession] =
       conf->get<bool>(kIgnoreMissingFiles, false) ? "true" : "false";
   configs[facebook::velox::connector::hive::HiveConfig::kParquetUseColumnNamesSession] =

dev/build-arrow.sh

@@ -53,11 +53,11 @@ function build_arrow_cpp() {
        -DARROW_PROTOBUF_USE_SHARED=OFF \
        -DARROW_DEPENDENCY_USE_SHARED=OFF \
        -DARROW_DEPENDENCY_SOURCE=BUNDLED \
-       -DARROW_WITH_THRIFT=ON \
        -DARROW_WITH_LZ4=ON \
        -DARROW_WITH_SNAPPY=ON \
        -DARROW_WITH_ZLIB=${ARROW_WITH_ZLIB} \
        -DARROW_WITH_ZSTD=ON \
+       -DBoost_NO_BOOST_CMAKE=TRUE \
        -DARROW_JEMALLOC=OFF \
        -DARROW_SIMD_LEVEL=NONE \
        -DARROW_RUNTIME_SIMD_LEVEL=NONE \
@@ -68,10 +68,6 @@ function build_arrow_cpp() {
        -DARROW_BUILD_SHARED=OFF \
        -DARROW_BUILD_STATIC=ON
 
- # Install thrift.
- cd _build/thrift_ep-prefix/src/thrift_ep-build
- ${SUDO} cmake --install ./ --prefix "${INSTALL_PREFIX}"/
- popd
 }
 
 function build_arrow_java() {

dev/ci-velox-buildshared-centos-9.sh

@@ -24,5 +24,5 @@ if [ "$(uname -m)" = "aarch64" ]; then
     export VCPKG_FORCE_SYSTEM_BINARIES=1;
 fi
 
-./dev/builddeps-veloxbe.sh --run_setup_script=OFF --build_arrow=OFF --build_tests=ON \
+./dev/builddeps-veloxbe.sh --run_setup_script=ON --build_arrow=ON --build_tests=ON \
     --build_examples=ON --build_benchmarks=ON

dev/ci-velox-buildstatic-centos-7.sh

@@ -17,6 +17,6 @@
 
 set -e
 
-export NUM_THREADS=4
+cp ep/build-velox/src/socket.h /usr/include/asm-generic/socket.h 
 ./dev/builddeps-veloxbe.sh --enable_vcpkg=ON --build_arrow=OFF --build_tests=OFF --build_benchmarks=OFF \
                            --build_examples=OFF --enable_s3=ON --enable_gcs=ON --enable_hdfs=ON --enable_abfs=ON

dev/vcpkg/init.sh

@@ -70,7 +70,7 @@ cd "$SCRIPT_ROOT"
 if [ ! -d "$VCPKG_ROOT" ] || [ -z "$(ls "$VCPKG_ROOT")" ]; then
     # 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 "$VCPKG_ROOT"
+    git clone https://github.com/microsoft/vcpkg.git --branch 2026.03.18 "$VCPKG_ROOT"
 fi
 [ -f "$VCPKG" ] || "$VCPKG_ROOT/bootstrap-vcpkg.sh" -disableMetrics
 
@@ -92,7 +92,7 @@ if [ "${VCPKG_DYNAMIC_OPENSSL:-OFF}" = "ON" ]; then
 fi
 
 
-$VCPKG install --no-print-usage \
+$VCPKG install --no-print-usage --allow-unsupported \
     --triplet="${VCPKG_TRIPLET}" --host-triplet="${VCPKG_TRIPLET}" ${EXTRA_FEATURES}
 
 # For fixing a build error like below when gluten's build type is Debug:

dev/vcpkg/ports/fbthrift/compactv1-protocol-refiller.patch

@@ -0,0 +1,23 @@
+--- a/thrift/lib/cpp2/protocol/ProtocolReaderWithRefill.h
++++ b/thrift/lib/cpp2/protocol/ProtocolReaderWithRefill.h
+@@ -172,6 +172,20 @@
+     protocol_.skipBytes(bytes);
+   }
+
++ protected:
++  /**
++   * Allow derived refill readers to use this helper where they cannot access
++   * CompactProtocolReader::in_ directly (due to not having a friend
++   * declaration).
++   * Allows users to implement refill readers for CompactV1ProtocolReader if
++   * necessary, without supporting it in the Thrift codebase or having to patch
++   * in a friend declaration.
++   */
++  template <typename T>
++  T readLEFromBuffer() {
++    return protocol_.in_.template readLE<T>();
++  }
++
+  private:
+   /**
+    * Make sure a varint can be read from the current buffer after idx bytes.

dev/vcpkg/ports/fbthrift/fix-deps.patch

@@ -0,0 +1,47 @@
+diff --git a/CMakeLists.txt b/CMakeLists.txt
+index 2f214f5..b45f528 100644
+--- a/CMakeLists.txt
++++ b/CMakeLists.txt
+@@ -118,12 +118,15 @@ endif ()
+
+ # Find required dependencies for thrift/lib
+ if (THRIFT_LIB_ONLY OR build_all)
+-  find_package(Gflags REQUIRED)
+-  find_package(Glog REQUIRED)
++  find_package(gflags CONFIG REQUIRED)
++  set(LIBGFLAGS_LIBRARY gflags::gflags)
++  find_package(glog CONFIG REQUIRED)
++  set(GLOG_LIBRARIES glog::glog)
+   find_package(fizz CONFIG REQUIRED)
+   find_package(wangle CONFIG REQUIRED)
+   find_package(ZLIB REQUIRED)
+-  find_package(Zstd REQUIRED)
++  find_package(zstd CONFIG REQUIRED)
++  set(ZSTD_LIBRARIES zstd::libzstd)
+   find_package(Xxhash REQUIRED)
+   find_package(mvfst CONFIG REQUIRED)
+   # https://cmake.org/cmake/help/v3.9/module/FindThreads.html
+diff --git a/thrift/cmake/FBThriftConfig.cmake.in b/thrift/cmake/FBThriftConfig.cmake.in
+index e279485..4dd8bd1 100644
+--- a/thrift/cmake/FBThriftConfig.cmake.in
++++ b/thrift/cmake/FBThriftConfig.cmake.in
+@@ -29,9 +29,16 @@ else()
+   set_and_check(FBTHRIFT_COMPILER "@PACKAGE_BIN_INSTALL_DIR@/thrift1")
+ endif()
+
+-find_dependency(Xxhash REQUIRED)
+-find_dependency(ZLIB REQUIRED)
+-find_package(mvfst CONFIG REQUIRED)
++find_dependency(xxHash CONFIG)
++find_dependency(ZLIB)
++find_dependency(mvfst CONFIG)
++find_dependency(fizz CONFIG)
++find_dependency(fmt CONFIG)
++find_dependency(folly CONFIG)
++find_dependency(gflags CONFIG)
++find_dependency(glog CONFIG)
++find_dependency(wangle CONFIG)
++find_dependency(zstd CONFIG)
+
+ if (NOT TARGET FBThrift::thriftcpp2)
+   include("${FBTHRIFT_CMAKE_DIR}/FBThriftTargets.cmake")

dev/vcpkg/ports/fbthrift/fix-fmt-include.patch

@@ -0,0 +1,13 @@
+diff --git a/thrift/lib/cpp2/server/RoundRobinRequestPile.h b/thrift/lib/cpp2/server/RoundRobinRequestPile.h
+index 3a06c5b..bae9387 100644
+--- a/thrift/lib/cpp2/server/RoundRobinRequestPile.h
++++ b/thrift/lib/cpp2/server/RoundRobinRequestPile.h
+@@ -21,6 +21,8 @@
+ #include <limits>
+ #include <memory>
+
++#include <fmt/ranges.h>
++
+ #include <folly/Executor.h>
+ #include <folly/concurrency/UnboundedQueue.h>
+ #include <folly/io/async/AtomicNotificationQueue.h>

dev/vcpkg/ports/fbthrift/fix-test.patch

@@ -0,0 +1,16 @@
+diff --git a/thrift/lib/cpp2/CMakeLists.txt b/thrift/lib/cpp2/CMakeLists.txt
+index 439f0814..3374dd34 100644
+--- a/thrift/lib/cpp2/CMakeLists.txt
++++ b/thrift/lib/cpp2/CMakeLists.txt
+@@ -15,11 +15,6 @@
+ # Set the cpp2 directory
+ set(LIB_CPP2_HOME ${CMAKE_CURRENT_SOURCE_DIR})
+
+-if (enable_tests)
+-  add_subdirectory(protocol/test)
+-endif ()
+-add_subdirectory(test)
+-
+ #######
+ # CMAKE variables only have local/subdirectory scope
+ # So even though this is defined in ../thrift/CMakeLists.txt as a variable

dev/vcpkg/ports/fbthrift/folly-has-liburing.diff

@@ -0,0 +1,13 @@
+diff --git a/thrift/lib/cpp2/security/SSLUtil.cpp b/thrift/lib/cpp2/security/SSLUtil.cpp
+index 571ffef..8803f37 100644
+--- a/thrift/lib/cpp2/security/SSLUtil.cpp
++++ b/thrift/lib/cpp2/security/SSLUtil.cpp
+@@ -144,7 +144,7 @@ folly::AsyncSocketTransport::UniquePtr toFDSocket(
+
+   auto sock = fizzSock->template getUnderlyingTransport<folly::AsyncSocket>();
+   folly::AsyncSocketTransport::UniquePtr ret;
+-#if defined(__linux__) && __has_include(<liburing.h>)
++#if defined(__linux__) && FOLLY_HAS_LIBURING
+   if (!sock &&
+       fizzSock->template getUnderlyingTransport<folly::AsyncIoUringSocket>()) {
+     // `AsyncFdSocket` currently lacks uring support, so hardcode `AsyncSocket`

dev/vcpkg/ports/fbthrift/portfile.cmake

@@ -0,0 +1,102 @@
+vcpkg_from_github(
+    OUT_SOURCE_PATH SOURCE_PATH
+    REPO facebook/fbthrift
+    REF "v${VERSION}"
+    SHA512 32f2a648496a321b6aaf55197c2dc1412d030ca82f8d8a5ca0516379379a0f71dc17e2edcb2be3972f76603935c7dcae29769c067caa1ec8a33e7f4efb251581
+    HEAD_REF main
+    PATCHES
+        fix-deps.patch
+        folly-has-liburing.diff
+        fix-fmt-include.patch
+        compactv1-protocol-refiller.patch
+)
+
+file(REMOVE "${SOURCE_PATH}/thrift/cmake/FindGMock.cmake")
+file(REMOVE "${SOURCE_PATH}/thrift/cmake/FindOpenSSL.cmake")
+file(REMOVE "${SOURCE_PATH}/thrift/cmake/FindZstd.cmake")
+file(REMOVE "${SOURCE_PATH}/build/fbcode_builder/CMake/FindGflags.cmake")
+file(REMOVE "${SOURCE_PATH}/build/fbcode_builder/CMake/FindGlog.cmake")
+file(REMOVE "${SOURCE_PATH}/build/fbcode_builder/CMake/FindGMock.cmake")
+file(REMOVE "${SOURCE_PATH}/build/fbcode_builder/CMake/FindLibEvent.cmake")
+file(REMOVE "${SOURCE_PATH}/build/fbcode_builder/CMake/FindSodium.cmake")
+file(REMOVE "${SOURCE_PATH}/build/fbcode_builder/CMake/FindZstd.cmake")
+
+vcpkg_cmake_configure(
+    SOURCE_PATH "${SOURCE_PATH}"
+    OPTIONS
+        "-Dthriftpy=OFF"
+        "-Denable_tests=OFF"
+)
+vcpkg_cmake_install()
+vcpkg_cmake_config_fixup(CONFIG_PATH lib/cmake/fbthrift)
+
+file(REMOVE_RECURSE "${CURRENT_PACKAGES_DIR}/debug/include")
+
+# There should be no empty directories in vcpkg/packages/fbthrift_x64-linux
+file(REMOVE_RECURSE
+    "${CURRENT_PACKAGES_DIR}/include/thrift/common/test"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/cpp/test"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/cpp/transport/test"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/cpp/util/test"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/cpp2/async/metadata/test"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/cpp2/debug_thrift_data_difference/test"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/cpp2/detail/test"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/cpp2/dynamic/test"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/cpp2/folly_dynamic/test"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/cpp2/frozen/test"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/cpp2/patch/test"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/cpp2/protocol/detail/test"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/cpp2/protocol/test"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/cpp2/protocol/tool"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/cpp2/reflection/demo"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/cpp2/reflection/docs"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/cpp2/runtime/test"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/cpp2/schema/test"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/cpp2/security/extensions/test"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/cpp2/security/test"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/cpp2/server/test"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/cpp2/test"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/cpp2/transport/core/test"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/cpp2/transport/http2/common/test"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/cpp2/transport/http2/server/test"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/cpp2/transport/http2/test"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/cpp2/transport/inmemory/test"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/cpp2/transport/rocket/client/test"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/cpp2/transport/rocket/compression/test"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/cpp2/transport/rocket/core/test"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/cpp2/transport/rocket/framing/parser/test"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/cpp2/transport/rocket/payload/test"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/cpp2/transport/rocket/server/test"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/cpp2/util/gtest/test"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/cpp2/util/test"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/cpp2/visitation/test"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/py3/benchmark"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/py3/test"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/python/any/test"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/python/benchmark"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/python/capi/benchmark"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/python/conformance"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/python/conformance/test"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/python/server/interceptor/test"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/python/server/test"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/python/test/adapters"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/python/test/cpp_conversion"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/python/test/request_context_extractor"
+    "${CURRENT_PACKAGES_DIR}/include/thrift/lib/thrift/annotation"
+)
+vcpkg_copy_tools(TOOL_NAMES thrift1 AUTO_CLEAN)
+vcpkg_copy_pdbs()
+
+if(EXISTS "${CURRENT_PACKAGES_DIR}/share/fbthrift/FBThriftConfig.cmake")
+    vcpkg_replace_string("${CURRENT_PACKAGES_DIR}/share/fbthrift/FBThriftConfig.cmake" 
+        "${PACKAGE_PREFIX_DIR}/lib/cmake/fbthrift" "${PACKAGE_PREFIX_DIR}/share/fbthrift")
+    vcpkg_replace_string("${CURRENT_PACKAGES_DIR}/share/fbthrift/FBThriftConfig.cmake" 
+        "${PACKAGE_PREFIX_DIR}/bin/thrift1.exe" "${PACKAGE_PREFIX_DIR}/tools/fbthrift/thrift1.exe")
+    vcpkg_replace_string("${CURRENT_PACKAGES_DIR}/share/fbthrift/FBThriftConfig.cmake" 
+        "${PACKAGE_PREFIX_DIR}/bin/thrift1" "${PACKAGE_PREFIX_DIR}/tools/fbthrift/thrift1")
+endif()
+
+# Only used internally and removed in master
+vcpkg_replace_string("${CURRENT_PACKAGES_DIR}/share/fbthrift/FBThriftTargets.cmake" "LOCATION_HH=\\\"${CURRENT_BUILDTREES_DIR}/${TARGET_TRIPLET}-rel/thrift/compiler/location.hh\\\"" "" IGNORE_UNCHANGED)
+
+vcpkg_install_copyright(FILE_LIST "${SOURCE_PATH}/LICENSE")

dev/vcpkg/ports/fbthrift/vcpkg.json

@@ -0,0 +1,35 @@
+{
+  "name": "fbthrift",
+  "version-string": "2026.02.23.00",
+  "description": "Facebook's branch of Apache Thrift, including a new C++ server.",
+  "homepage": "https://github.com/facebook/fbthrift",
+  "license": "Apache-2.0",
+  "supports": "x64 & static",
+  "dependencies": [
+    "boost-context",
+    "boost-filesystem",
+    "boost-program-options",
+    "boost-regex",
+    "boost-system",
+    "boost-thread",
+    "fizz",
+    "fmt",
+    "folly",
+    "gflags",
+    "glog",
+    "mvfst",
+    "openssl",
+    {
+      "name": "vcpkg-cmake",
+      "host": true
+    },
+    {
+      "name": "vcpkg-cmake-config",
+      "host": true
+    },
+    "wangle",
+    "xxhash",
+    "zlib",
+    "zstd"
+  ]
+}