Skip to content

fix(parquet/file): restore goroutine safety for reader #343

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
zeroshade merged 1 commit into from
Apr 11, 2025
Merged

fix(parquet/file): restore goroutine safety for reader #343

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
5 changes: 5 additions & 0 deletions parquet/file/file_reader.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -322,6 +322,11 @@ func (f *Reader) RowGroup(i int) *RowGroupReader {
fileDecryptor: f.fileDecryptor,
bufferPool: &f.bufferPool,
pageIndexReader: f.pageIndexReader,
// don't pre-emptively initialize the row group page index reader
// do it on demand, but ensure that it is goroutine safe.
rgPageIndexReader: sync.OnceValues(func() (*metadata.RowGroupPageIndexReader, error) {
return f.pageIndexReader.RowGroup(i)
}),
}
}

Expand Down
17 changes: 7 additions & 10 deletions parquet/file/row_group_reader.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,7 +42,7 @@ type RowGroupReader struct {
fileDecryptor encryption.FileDecryptor

pageIndexReader *metadata.PageIndexReader
rgPageIndexReader *metadata.RowGroupPageIndexReader
rgPageIndexReader func() (*metadata.RowGroupPageIndexReader, error)
bufferPool *sync.Pool
}

Expand Down Expand Up @@ -86,12 +86,9 @@ func (r *RowGroupReader) GetColumnPageReader(i int) (PageReader, error) {
return nil, err
}

if r.rgPageIndexReader == nil {
rgIdx, err := r.pageIndexReader.RowGroup(int(r.rgMetadata.Ordinal()))
if err != nil {
return nil, err
}
r.rgPageIndexReader = rgIdx
rgIdxRdr, err := r.rgPageIndexReader()
if err != nil {
return nil, err
}

colStart := col.DataPageOffset()
Expand Down Expand Up @@ -128,7 +125,7 @@ func (r *RowGroupReader) GetColumnPageReader(i int) (PageReader, error) {
r: stream,
chunk: col,
colIdx: i,
pgIndexReader: r.rgPageIndexReader,
pgIndexReader: rgIdxRdr,
maxPageHeaderSize: defaultMaxPageHeaderSize,
nrows: col.NumValues(),
mem: r.props.Allocator(),
Expand Down Expand Up @@ -157,7 +154,7 @@ func (r *RowGroupReader) GetColumnPageReader(i int) (PageReader, error) {
r: stream,
chunk: col,
colIdx: i,
pgIndexReader: r.rgPageIndexReader,
pgIndexReader: rgIdxRdr,
maxPageHeaderSize: defaultMaxPageHeaderSize,
nrows: col.NumValues(),
mem: r.props.Allocator(),
Expand All @@ -181,7 +178,7 @@ func (r *RowGroupReader) GetColumnPageReader(i int) (PageReader, error) {
r: stream,
chunk: col,
colIdx: i,
pgIndexReader: r.rgPageIndexReader,
pgIndexReader: rgIdxRdr,
maxPageHeaderSize: defaultMaxPageHeaderSize,
nrows: col.NumValues(),
mem: r.props.Allocator(),
Expand Down
Loading