Skip to content

Don't recalculate chunk offsets for ChunkedReader #8231

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
myrrc merged 1 commit into from
Jun 3, 2026
Merged

Don't recalculate chunk offsets for ChunkedReader #8231

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
12 changes: 5 additions & 7 deletions vortex-layout/src/layouts/chunked/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -103,10 +103,9 @@ impl VTable for Chunked {
let new_children = OwnedLayoutChildren::layout_children(children);

// Recalculate chunk offsets based on new children
let mut chunk_offsets = Vec::with_capacity(new_children.nchildren() + 1);
chunk_offsets.push(0);
let mut chunk_offsets = vec![0; new_children.nchildren() + 1];
for i in 0..new_children.nchildren() {
chunk_offsets.push(chunk_offsets[i] + new_children.child_row_count(i));
chunk_offsets[i + 1] = chunk_offsets[i] + new_children.child_row_count(i);
}

layout.children = new_children;
Expand All @@ -132,12 +131,11 @@ pub struct ChunkedLayout {

impl ChunkedLayout {
pub fn new(row_count: u64, dtype: DType, children: Arc<dyn LayoutChildren>) -> Self {
let mut chunk_offsets = Vec::with_capacity(children.nchildren() + 1);

chunk_offsets.push(0);
let mut chunk_offsets = vec![0; children.nchildren() + 1];
for i in 0..children.nchildren() {
chunk_offsets.push(chunk_offsets[i] + children.child_row_count(i));
chunk_offsets[i + 1] = chunk_offsets[i] + children.child_row_count(i);
}

assert_eq!(
chunk_offsets[children.nchildren()],
Comment on lines 105 to 140

@joseph-isaacs joseph-isaacs Jun 3, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

revert or use mut iter if you want perf

row_count,
Expand Down
19 changes: 6 additions & 13 deletions vortex-layout/src/layouts/chunked/reader.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,8 +39,6 @@ pub struct ChunkedReader {
layout: ChunkedLayout,
name: Arc<str>,
lazy_children: LazyReaderChildren,
/// Row offset for each chunk
chunk_offsets: Vec<u64>,
}

static UNKNOWN: LazyLock<Arc<str>> = LazyLock::new(|| Arc::from("chunked-child"));
Expand All @@ -53,13 +51,6 @@ impl ChunkedReader {
session: &VortexSession,
) -> Self {
let nchildren = layout.nchildren();

let mut chunk_offsets = vec![0; nchildren + 1];
for i in 1..nchildren {
chunk_offsets[i] = chunk_offsets[i - 1] + layout.children.child_row_count(i - 1);
}
chunk_offsets[nchildren] = layout.row_count();

let dtypes = vec![layout.dtype.clone(); nchildren];

// format!() has non-marginal overhead for short queries like random
Expand All @@ -84,7 +75,6 @@ impl ChunkedReader {
layout,
name,
lazy_children,
chunk_offsets,
}
}

Expand All @@ -94,22 +84,25 @@ impl ChunkedReader {
}

fn chunk_offset(&self, idx: usize) -> u64 {
self.chunk_offsets.get(idx).copied().unwrap_or_else(|| {
if idx >= self.layout.chunk_offsets.len() {
vortex_panic!(
"Internal error: Chunk offset {idx} out of bounds (num_children: {}, num_offsets: {}). \
This indicates a bug in ChunkedReader initialization or chunk_range calculation.",
self.layout.nchildren(),
self.chunk_offsets.len()
self.layout.chunk_offsets.len()
)
})
}
self.layout.chunk_offsets[idx]
}

fn chunk_range(&self, row_range: &Range<u64>) -> Range<usize> {
let start_chunk = self
.layout
.chunk_offsets
.binary_search(&row_range.start)
.unwrap_or_else(|x| x.saturating_sub(1));
let end_chunk = self
.layout
.chunk_offsets
.binary_search(&row_range.end)
.unwrap_or_else(|x| x);
Expand Down
Loading