update

apache · Nov 18, 2024 · 2203599 · 2203599
1 parent 8eea3c7
commit 2203599
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 6 deletions.
diff --git a/cpp/core/shuffle/Utils.cc b/cpp/core/shuffle/Utils.cc
@@ -227,11 +227,7 @@ arrow::Result<std::shared_ptr<MmapFileStream>> MmapFileStream::open(const std::s
     return arrow::Status::IOError("Memory mapping file failed: ", ::arrow::internal::ErrnoMessage(errno));
   }
 
-  auto fstream = std::shared_ptr<MmapFileStream>(new MmapFileStream());
-  fstream->fd_ = std::move(fd);
-  fstream->data_ = static_cast<uint8_t*>(result);
-  fstream->size_ = size;
-  return fstream;
+  return std::make_shared<MmapFileStream>(std::move(fd), static_cast<uint8_t*>(result), size);
 }
 
 void MmapFileStream::advance(int64_t length) {

diff --git a/cpp/core/shuffle/Utils.h b/cpp/core/shuffle/Utils.h
@@ -72,8 +72,12 @@ arrow::Result<std::shared_ptr<arrow::RecordBatch>> makeUncompressedRecordBatch(
 
 std::shared_ptr<arrow::Buffer> zeroLengthNullBuffer();
 
+// MmapFileStream is used to optimize sequential file reading. It uses madvise
+// to prefetch and release memory timely.
 class MmapFileStream : public arrow::io::InputStream {
  public:
+  MmapFileStream(arrow::internal::FileDescriptor fd, uint8_t* data, int64_t size)
+      : fd_(std::move(fd)), data_(data), size_(size){};
   static arrow::Result<std::shared_ptr<MmapFileStream>> open(const std::string& path);
   arrow::Result<int64_t> Tell() const override;
   arrow::Status Close() override;
@@ -99,7 +103,6 @@ class MmapFileStream : public arrow::io::InputStream {
   int64_t size_;
   int64_t pos_ = 0;
   int64_t posRetain_ = 0;
-  MmapFileStream() = default;
 };
 
 } // namespace gluten