Skip to content

fix prefetch of page index #6999

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
merged 6 commits into from
Jan 22, 2025
Merged

fix prefetch of page index #6999

Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
2648dd1
fix prefetch of page index
adriangb Jan 20, 2025
feb6650
move to assertion
adriangb Jan 20, 2025
dfe74d1
fmt
adriangb Jan 20, 2025
02619ec
less invasive version
adriangb Jan 20, 2025
c45551e
typo
adriangb Jan 20, 2025
ec36a6f
fmt
adriangb Jan 20, 2025
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
40 changes: 39 additions & 1 deletion parquet/src/file/metadata/reader.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -412,7 +412,9 @@ impl ParquetMetaDataReader {
let bytes = match &remainder {
Some((remainder_start, remainder)) if *remainder_start <= range.start => {
let offset = range.start - *remainder_start;
remainder.slice(offset..range.end - *remainder_start + offset)
let end = offset + range.end - range.start;
assert!(end <= remainder.len());
remainder.slice(offset..end)
}
// Note: this will potentially fetch data already in remainder, this keeps things simple
_ => fetch.fetch(range.start..range.end).await?,
Expand Down Expand Up @@ -1052,5 +1054,41 @@ mod async_tests {
.unwrap();
assert_eq!(fetch_count.load(Ordering::SeqCst), 1);
assert!(metadata.offset_index().is_some() && metadata.column_index().is_some());

// Prefetch more than enough but less than the entire file
fetch_count.store(0, Ordering::SeqCst);
let f = MetadataFetchFn(&mut fetch);
let metadata = ParquetMetaDataReader::new()
.with_page_indexes(true)
.with_prefetch_hint(Some(len - 1000)) // prefetch entire file
.load_and_finish(f, len)
.await
.unwrap();
assert_eq!(fetch_count.load(Ordering::SeqCst), 1);
assert!(metadata.offset_index().is_some() && metadata.column_index().is_some());

// Prefetch the entire file
fetch_count.store(0, Ordering::SeqCst);
let f = MetadataFetchFn(&mut fetch);
let metadata = ParquetMetaDataReader::new()
.with_page_indexes(true)
.with_prefetch_hint(Some(len)) // prefetch entire file
.load_and_finish(f, len)
.await
.unwrap();
assert_eq!(fetch_count.load(Ordering::SeqCst), 1);
assert!(metadata.offset_index().is_some() && metadata.column_index().is_some());

// Prefetch more than the entire file
fetch_count.store(0, Ordering::SeqCst);
let f = MetadataFetchFn(&mut fetch);
let metadata = ParquetMetaDataReader::new()
.with_page_indexes(true)
.with_prefetch_hint(Some(len + 1000)) // prefetch entire file
.load_and_finish(f, len)
.await
.unwrap();
assert_eq!(fetch_count.load(Ordering::SeqCst), 1);
assert!(metadata.offset_index().is_some() && metadata.column_index().is_some());
}
}
Loading