Skip to content

Parquet Reader: avoid caching the compressed buffer in the ColumnReader #16263

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Mytherin merged 1 commit into from
Feb 17, 2025
Merged

Parquet Reader: avoid caching the compressed buffer in the ColumnReader #16263

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 4 additions & 6 deletions extension/parquet/column_reader.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -319,7 +319,8 @@ void ColumnReader::PreparePageV2(PageHeader &page_hdr) {

auto compressed_bytes = page_hdr.compressed_page_size - uncompressed_bytes;

AllocateCompressed(compressed_bytes);
ResizeableBuffer compressed_buffer;
compressed_buffer.resize(GetAllocator(), compressed_bytes);
reader.ReadData(*protocol, compressed_buffer.ptr, compressed_bytes);

DecompressInternal(chunk->meta_data.codec, compressed_buffer.ptr, compressed_bytes, block->ptr + uncompressed_bytes,
Expand All @@ -334,10 +335,6 @@ void ColumnReader::AllocateBlock(idx_t size) {
}
}

void ColumnReader::AllocateCompressed(idx_t size) {
compressed_buffer.resize(GetAllocator(), size);
}

void ColumnReader::PreparePage(PageHeader &page_hdr) {
AllocateBlock(page_hdr.uncompressed_page_size + 1);
if (chunk->meta_data.codec == CompressionCodec::UNCOMPRESSED) {
Expand All @@ -348,7 +345,8 @@ void ColumnReader::PreparePage(PageHeader &page_hdr) {
return;
}

AllocateCompressed(page_hdr.compressed_page_size + 1);
ResizeableBuffer compressed_buffer;
compressed_buffer.resize(GetAllocator(), page_hdr.compressed_page_size + 1);
reader.ReadData(*protocol, compressed_buffer.ptr, page_hdr.compressed_page_size);

DecompressInternal(chunk->meta_data.codec, compressed_buffer.ptr, page_hdr.compressed_page_size, block->ptr,
Expand Down
2 changes: 0 additions & 2 deletions extension/parquet/include/column_reader.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -160,7 +160,6 @@ class ColumnReader {

private:
void AllocateBlock(idx_t size);
void AllocateCompressed(idx_t size);
void PrepareRead(parquet_filter_t &filter);
void PreparePage(PageHeader &page_hdr);
void PrepareDataPage(PageHeader &page_hdr);
Expand All @@ -178,7 +177,6 @@ class ColumnReader {

shared_ptr<ResizeableBuffer> block;

ResizeableBuffer compressed_buffer;
ResizeableBuffer offset_buffer;

unique_ptr<RleBpDecoder> dict_decoder;
Expand Down
Loading