Skip to content
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

Remove superfluous use of std::vector for std::future #16829

Merged
merged 4 commits into from
Sep 27, 2024
Merged

Remove superfluous use of std::vector for std::future #16829

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
ee20656
Simplify future-related code and enable concurrency
kingcrimsontianyu Sep 18, 2024
2fcd213
Revert some changes
kingcrimsontianyu Sep 24, 2024
4d60803
Merge branch 'branch-24.10' into simplify-io
vuule Sep 24, 2024
335f922
Merge branch 'branch-24.12' into simplify-io
vyasr Sep 26, 2024
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
4 changes: 2 additions & 2 deletions cpp/src/io/parquet/reader_impl.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -188,10 +188,10 @@ class reader::impl {
*
* Does not decompress the chunk data.
*
* @return pair of boolean indicating if compressed chunks were found and a vector of futures for
* @return pair of boolean indicating if compressed chunks were found and a future for
* read completion
*/
std::pair<bool, std::vector<std::future<void>>> read_column_chunks();
std::pair<bool, std::future<void>> read_column_chunks();

/**
* @brief Read compressed data and page information for the current pass.
Expand Down
26 changes: 11 additions & 15 deletions cpp/src/io/parquet/reader_impl_preprocess.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -964,7 +964,7 @@ void reader::impl::allocate_level_decode_space()
}
}

std::pair<bool, std::vector<std::future<void>>> reader::impl::read_column_chunks()
std::pair<bool, std::future<void>> reader::impl::read_column_chunks()
{
auto const& row_groups_info = _pass_itm_data->row_groups;

Expand All @@ -989,7 +989,6 @@ std::pair<bool, std::vector<std::future<void>>> reader::impl::read_column_chunks
// TODO: make this respect the pass-wide skip_rows/num_rows instead of the file-wide
// skip_rows/num_rows
// auto remaining_rows = num_rows;
std::vector<std::future<void>> read_chunk_tasks;
size_type chunk_count = 0;
for (auto const& rg : row_groups_info) {
auto const& row_group = _metadata->get_row_group(rg.index, rg.source_index);
Expand Down Expand Up @@ -1018,16 +1017,15 @@ std::pair<bool, std::vector<std::future<void>>> reader::impl::read_column_chunks
}

// Read compressed chunk data to device memory
read_chunk_tasks.push_back(read_column_chunks_async(_sources,
raw_page_data,
chunks,
0,
chunks.size(),
column_chunk_offsets,
chunk_source_map,
_stream));

return {total_decompressed_size > 0, std::move(read_chunk_tasks)};
return {total_decompressed_size > 0,
read_column_chunks_async(_sources,
raw_page_data,
chunks,
0,
chunks.size(),
column_chunk_offsets,
chunk_source_map,
_stream)};
}

void reader::impl::read_compressed_data()
Expand All @@ -1042,9 +1040,7 @@ void reader::impl::read_compressed_data()
auto const [has_compressed_data, read_chunks_tasks] = read_column_chunks();
pass.has_compressed_data = has_compressed_data;

for (auto& task : read_chunks_tasks) {
task.wait();
}
read_chunks_tasks.wait();

// Process dataset chunk pages into output columns
auto const total_pages = _has_page_index ? count_page_headers_with_pgidx(chunks, _stream)
Expand Down
Loading