[VL] Replace std::cerr/cout with LOG and remove GLUTEN_PRINT_DEBUG macro

cpp/CMakeLists.txt

@@ -74,13 +74,7 @@ include(ResolveDependency)
 # Compiler flags
 #
 
-if (${CMAKE_BUILD_TYPE} STREQUAL "RelWithDebInfo")
-# keep this original logic
-  add_definitions(-DGLUTEN_PRINT_DEBUG)
-  message(STATUS "Add definition GLUTEN_PRINT_DEBUG")
-elseif (${CMAKE_BUILD_TYPE} STREQUAL "Debug")
-  add_definitions(-DGLUTEN_PRINT_DEBUG)
-  message(STATUS "Add definition GLUTEN_PRINT_DEBUG")
+if (${CMAKE_BUILD_TYPE} STREQUAL "Debug")
   set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -ggdb -O0")
   message(STATUS "CMAKE_CXX_FLAGS_DEBUG=${CMAKE_CXX_FLAGS_DEBUG}")
 else ()
@@ -165,7 +159,7 @@ function(ADD_TEST_CASE TEST_NAME)
   endif()
 
   add_executable(${TEST_NAME} ${SOURCES})
-  target_link_libraries(${TEST_NAME} gluten GTest::gtest GTest::gtest_main Threads::Threads)
+  target_link_libraries(${TEST_NAME} gluten google::glog GTest::gtest GTest::gtest_main Threads::Threads)
   target_include_directories(${TEST_NAME} PRIVATE ${CMAKE_SOURCE_DIR}/core)
 
   if(ARG_EXTRA_LINK_LIBS)

cpp/core/CMakeLists.txt

@@ -209,7 +209,6 @@ set(SPARK_COLUMNAR_PLUGIN_SRCS
         shuffle/rss/CelebornPartitionWriter.cc
         shuffle/Utils.cc
         utils/Compression.cc
-        utils/DebugOut.cc
         utils/StringUtil.cc
         utils/ObjectStore.cc
         jni/JniError.cc

cpp/core/benchmarks/CMakeLists.txt

@@ -31,7 +31,7 @@
 
 macro(package_add_gbenchmark TESTNAME)
   add_executable(${TESTNAME} ${ARGN})
-  target_link_libraries(${TESTNAME} benchmark::benchmark gluten ${CMAKE_THREAD_LIBS_INIT})
+  target_link_libraries(${TESTNAME} benchmark::benchmark gluten google::glog ${CMAKE_THREAD_LIBS_INIT})
   target_include_directories(${TESTNAME} PUBLIC ${source_root_directory})
   set_target_properties(${TESTNAME} PROPERTIES FOLDER tests)
 endmacro()

cpp/core/benchmarks/CompressionBenchmark.cc

@@ -25,6 +25,7 @@
 #include <arrow/type_fwd.h>
 #include <benchmark/benchmark.h>
 #include <execinfo.h>
+#include <glog/logging.h>
 #include <parquet/arrow/reader.h>
 #include <parquet/file_reader.h>
 #include <sched.h>
@@ -126,7 +127,7 @@ class BenchmarkCompression {
       }
       case gluten::kQatZstd: {
         ipcWriteOptions.codec = createArrowIpcCodec(arrow::Compression::ZSTD, CodecBackend::QAT);
-        std::cout << "load qatzstd" << std::endl;
+        LOG(INFO) << "load qatzstd";
         break;
       }
 #endif
@@ -163,7 +164,7 @@ class BenchmarkCompression {
         state);
     auto endTime = std::chrono::steady_clock::now();
     auto totalTime = (endTime - startTime).count();
-    std::cout << "Thread " << state.thread_index() << " took " << (1.0 * totalTime / 1e9) << "s" << std::endl;
+    LOG(INFO) << "Thread " << state.thread_index() << " took " << (1.0 * totalTime / 1e9) << "s";
 
     state.counters["rowgroups"] =
         benchmark::Counter(rowGroupIndices_.size(), benchmark::Counter::kAvgThreads, benchmark::Counter::OneK::kIs1000);
@@ -301,8 +302,8 @@ class BenchmarkCompressionCacheScanBenchmark final : public BenchmarkCompression
       }
     } while (recordBatch);
 
-    std::cout << "parquet parse done elapsed time " << elapseRead / 1e6 << " ms " << std::endl;
-    std::cout << "batches = " << numBatches << " rows = " << numRows << std::endl;
+    LOG(INFO) << "parquet parse done elapsed time " << elapseRead / 1e6 << " ms ";
+    LOG(INFO) << "batches = " << numBatches << " rows = " << numRows;
 
     std::vector<std::shared_ptr<arrow::ipc::IpcPayload>> payloads(batches.size());
     std::vector<std::vector<int64_t>> uncompressedBufferSize(batches.size());
@@ -418,26 +419,26 @@ int main(int argc, char** argv) {
     } else if (strcmp(argv[i], "--file") == 0) {
       datafile = argv[i + 1];
     } else if (strcmp(argv[i], "--qat-gzip") == 0) {
-      std::cout << "QAT gzip is used as codec" << std::endl;
+      LOG(INFO) << "QAT gzip is used as codec";
       codec = gluten::kQatGzip;
     } else if (strcmp(argv[i], "--qat-zstd") == 0) {
-      std::cout << "QAT zstd is used as codec" << std::endl;
+      LOG(INFO) << "QAT zstd is used as codec";
       codec = gluten::kQatZstd;
     } else if (strcmp(argv[i], "--qpl-gzip") == 0) {
-      std::cout << "QPL gzip is used as codec" << std::endl;
+      LOG(INFO) << "QPL gzip is used as codec";
       codec = gluten::kQplGzip;
     } else if (strcmp(argv[i], "--zstd") == 0) {
-      std::cout << "CPU zstd is used as codec" << std::endl;
+      LOG(INFO) << "CPU zstd is used as codec";
       codec = gluten::kZstd;
     } else if (strcmp(argv[i], "--buffer-size") == 0) {
       compressBufferSize = atol(argv[i + 1]);
     } else if (strcmp(argv[i], "--cpu-offset") == 0) {
       cpuOffset = atol(argv[i + 1]);
     }
   }
-  std::cout << "iterations = " << iterations << std::endl;
-  std::cout << "threads = " << threads << std::endl;
-  std::cout << "datafile = " << datafile << std::endl;
+  LOG(INFO) << "iterations = " << iterations;
+  LOG(INFO) << "threads = " << threads;
+  LOG(INFO) << "datafile = " << datafile;
 
   gluten::BenchmarkCompressionIterateScanBenchmark bmIterateScan(datafile, compressBufferSize);
   gluten::BenchmarkCompressionCacheScanBenchmark bmCacheScan(datafile, compressBufferSize);

cpp/core/compute/Runtime.h

@@ -17,6 +17,8 @@
 
 #pragma once
 
+#include <glog/logging.h>
+
 #include "compute/ProtobufUtils.h"
 #include "compute/ResultIterator.h"
 #include "memory/ArrowMemoryPool.h"
@@ -29,7 +31,6 @@
 #include "shuffle/ShuffleReader.h"
 #include "shuffle/ShuffleWriter.h"
 #include "substrait/plan.pb.h"
-#include "utils/DebugOut.h"
 #include "utils/ObjectStore.h"
 
 namespace gluten {

cpp/core/jni/JniCommon.h

@@ -28,7 +28,6 @@
 #include "memory/AllocationListener.h"
 #include "shuffle/rss/RssClient.h"
 #include "utils/Compression.h"
-#include "utils/DebugOut.h"
 #include "utils/exception.h"
 
 static jint jniVersion = JNI_VERSION_1_8;
@@ -52,7 +51,7 @@ static inline void checkException(JNIEnv* env) {
     std::string description =
         jStringToCString(env, (jstring)env->CallStaticObjectMethod(describerClass, describeMethod, t));
     if (env->ExceptionCheck()) {
-      std::cerr << "Fatal: Uncaught Java exception during calling the Java exception describer method! " << std::endl;
+      LOG(WARNING) << "Fatal: Uncaught Java exception during calling the Java exception describer method! ";
     }
     throw gluten::GlutenException("Error during calling Java code from native code: " + description);
   }
@@ -106,13 +105,13 @@ static inline jmethodID getStaticMethodIdOrError(JNIEnv* env, jclass thisClass,
 static inline void attachCurrentThreadAsDaemonOrThrow(JavaVM* vm, JNIEnv** out) {
   int getEnvStat = vm->GetEnv(reinterpret_cast<void**>(out), jniVersion);
   if (getEnvStat == JNI_EDETACHED) {
-    DEBUG_OUT << "JNIEnv was not attached to current thread." << std::endl;
+    DLOG(INFO) << "JNIEnv was not attached to current thread.";
     // Reattach current thread to JVM
     getEnvStat = vm->AttachCurrentThreadAsDaemon(reinterpret_cast<void**>(out), NULL);
     if (getEnvStat != JNI_OK) {
       throw gluten::GlutenException("Failed to reattach current thread to JVM.");
     }
-    DEBUG_OUT << "Succeeded attaching current thread." << std::endl;
+    DLOG(INFO) << "Succeeded attaching current thread.";
     return;
   }
   if (getEnvStat != JNI_OK) {
@@ -161,7 +160,7 @@ static inline void backtrace() {
   auto size = backtrace(array, 1024);
   char** strings = backtrace_symbols(array, size);
   for (size_t i = 0; i < size; ++i) {
-    std::cout << strings[i] << std::endl;
+    LOG(INFO) << strings[i];
   }
   free(strings);
 }
@@ -229,8 +228,8 @@ class SparkAllocationListener final : public gluten::AllocationListener {
   ~SparkAllocationListener() override {
     JNIEnv* env;
     if (vm_->GetEnv(reinterpret_cast<void**>(&env), jniVersion) != JNI_OK) {
-      std::cerr << "SparkAllocationListener#~SparkAllocationListener(): "
-                << "JNIEnv was not attached to current thread" << std::endl;
+      LOG(WARNING) << "SparkAllocationListener#~SparkAllocationListener(): "
+                   << "JNIEnv was not attached to current thread";
       return;
     }
     env->DeleteGlobalRef(jListenerGlobalRef_);
@@ -329,8 +328,8 @@ class CelebornClient : public RssClient {
   ~CelebornClient() {
     JNIEnv* env;
     if (vm_->GetEnv(reinterpret_cast<void**>(&env), jniVersion) != JNI_OK) {
-      std::cerr << "CelebornClient#~CelebornClient(): "
-                << "JNIEnv was not attached to current thread" << std::endl;
+      LOG(WARNING) << "CelebornClient#~CelebornClient(): "
+                   << "JNIEnv was not attached to current thread";
       return;
     }
     env->DeleteGlobalRef(javaCelebornShuffleWriter_);

cpp/core/jni/JniWrapper.cc

@@ -18,7 +18,6 @@
 #include <jni.h>
 #include <filesystem>
 
-#include <glog/logging.h>
 #include "compute/ProtobufUtils.h"
 #include "compute/Runtime.h"
 #include "config/GlutenConfig.h"
@@ -92,11 +91,10 @@ class JavaInputStreamAdaptor final : public arrow::io::InputStream {
     try {
       auto status = JavaInputStreamAdaptor::Close();
       if (!status.ok()) {
-        DEBUG_OUT << __func__ << " call JavaInputStreamAdaptor::Close() failed, status:" << status.ToString()
-                  << std::endl;
+        LOG(WARNING) << __func__ << " call JavaInputStreamAdaptor::Close() failed, status:" << status.ToString();
       }
     } catch (std::exception& e) {
-      DEBUG_OUT << __func__ << " call JavaInputStreamAdaptor::Close() got exception:" << e.what() << std::endl;
+      LOG(WARNING) << __func__ << " call JavaInputStreamAdaptor::Close() got exception:" << e.what();
     }
   }
 
@@ -836,7 +834,7 @@ JNIEXPORT jlong JNICALL Java_io_glutenproject_vectorized_ShuffleWriterJniWrapper
   jobject thread = env->CallStaticObjectMethod(cls, mid);
   checkException(env);
   if (thread == NULL) {
-    std::cerr << "Thread.currentThread() return NULL" << std::endl;
+    LOG(WARNING) << "Thread.currentThread() return NULL";
   } else {
     jmethodID midGetid = getMethodIdOrError(env, cls, "getId", "()J");
     jlong sid = env->CallLongMethod(thread, midGetid);

cpp/core/shuffle/LocalPartitionWriter.cc

@@ -19,7 +19,6 @@
 #include <random>
 #include <thread>
 #include "shuffle/Utils.h"
-#include "utils/DebugOut.h"
 #include "utils/StringUtil.h"
 #include "utils/Timer.h"
 
@@ -129,7 +128,7 @@ class FlushOnSpillEvictHandle final : public LocalPartitionWriter::LocalEvictHan
     ARROW_ASSIGN_OR_RAISE(auto start, os_->Tell());
     RETURN_NOT_OK(arrow::ipc::WriteIpcPayload(*payload, options_, os_.get(), &metadataLength));
     ARROW_ASSIGN_OR_RAISE(auto end, os_->Tell());
-    DEBUG_OUT << "Spilled partition " << partitionId << " file start: " << start << ", file end: " << end << std::endl;
+    DLOG(INFO) << "Spilled partition " << partitionId << " file start: " << start << ", file end: " << end;
     spillInfo_->partitionSpillInfos.push_back({partitionId, end - start});
     return arrow::Status::OK();
   }

cpp/core/tests/RoundRobinPartitionerTest.cc

@@ -15,6 +15,7 @@
  * limitations under the License.
  */
 #include "shuffle/RoundRobinPartitioner.h"
+#include <glog/logging.h>
 #include <gtest/gtest.h>
 #include <numeric>
 
@@ -46,10 +47,11 @@ class RoundRobinPartitionerTest : public ::testing::Test {
 
   template <typename T>
   void toString(const std::vector<T>& vec, const std::string& name) const {
-    std::cout << name << " = [";
-    std::copy(vec.cbegin(), vec.cend(), std::ostream_iterator<T>(std::cout, ","));
-    std::cout << " ]";
-    std::cout << std::endl;
+    std::stringstream ss;
+    ss << name << " = [";
+    std::copy(vec.cbegin(), vec.cend(), std::ostream_iterator<T>(ss, ","));
+    ss << " ]";
+    LOG(INFO) << ss.str();
   }
 
   int32_t getPidSelection() const {

cpp/core/utils/ObjectStore.cc

@@ -16,6 +16,7 @@
  */
 
 #include "ObjectStore.h"
+#include <glog/logging.h>
 #include <iostream>
 
 gluten::ObjectStore::~ObjectStore() {
@@ -24,7 +25,7 @@ gluten::ObjectStore::~ObjectStore() {
   for (auto itr = aliveObjectHandles_.rbegin(); itr != aliveObjectHandles_.rend(); itr++) {
     ResourceHandle handle = *itr;
     if (store_.lookup(handle) == nullptr) {
-      std::cerr << "Fatal: resource handle " + std::to_string(handle) + " not found in store." << std::endl;
+      LOG(WARNING) << "Fatal: resource handle " + std::to_string(handle) + " not found in store.";
     }
     store_.erase(handle);
   }