perf: O(1) chunk cache lookup with shared Arc buffers instead of O(n) scan+clone

The decompressed-chunk LRU cache was the hottest path in the read pipeline
(every chunked-dataset read goes through it) but did a linear scan through
up to 521 slots on every get/put, and a full buffer copy on every cache hit
(to_vec()/clone() of the whole decompressed chunk). chunked_read.rs then
cloned the buffer a second time just to insert it into the cache after
already having it in hand.

- Added a HashMap<ChunkCoord, usize> index alongside the LRU slots for O(1)
  lookup. Eviction uses swap_remove, so the swapped-in slot's index entry is
  fixed up on every eviction (covered by a dedicated test).
- CachedChunk.data is now Arc<CacheAlignedBuffer> — a cache hit is a
  refcount bump, not a copy. CacheAlignedBuffer gained a Sync impl (same
  soundness argument as its existing Send impl: access is only ever through
  borrow-checked &/&mut, like Vec<u8>) so Arc<CacheAlignedBuffer> is itself
  Send/Sync.
- put_decompressed/put_decompressed_aligned now return the Arc they just
  inserted (or the existing cached copy), so callers can reuse that
  allocation instead of holding a separate clone — eliminates the second
  copy in chunked_read.rs's three call sites, which now consume the
  Arc<CacheAlignedBuffer> (Deref's to &[u8], so downstream indexing/copy
  code is unchanged).
- prefetch_hint's doc comment now leads with "bookkeeping only, does not
  prefetch" instead of describing behavior it doesn't have.

Co-Authored-By: Claude Sonnet 5 <[email protected]>
This commit is contained in:
Omar Sobh
2026-08-05 07:46:05 -07:00
co-authored by Claude Sonnet 5
parent b9898c2a9c
commit b70d594c4f
2 changed files with 128 additions and 57 deletions
+9 -9
View File
@@ -9,6 +9,8 @@ use alloc::{format, vec, vec::Vec};
use crate::chunk_cache::CacheAlignedBuffer;
#[cfg(feature = "std")]
use crate::chunk_cache::ChunkCache;
#[cfg(feature = "std")]
use std::sync::Arc;
use crate::data_layout::DataLayout;
use crate::dataspace::Dataspace;
use crate::datatype::Datatype;
@@ -689,7 +691,7 @@ pub fn read_chunked_data_cached(
let coord: Vec<u64> = chunk_info.offsets.iter().take(rank).copied().collect();
// Try decompressed cache first
let decompressed = if let Some(cached) = cache.get_decompressed(&coord) {
let decompressed = if let Some(cached) = cache.get_decompressed_aligned(&coord) {
cached
} else {
// Decompress from file
@@ -711,8 +713,7 @@ pub fn read_chunked_data_cached(
} else {
raw_chunk.to_vec()
};
cache.put_decompressed(coord, dec.clone());
dec
cache.put_decompressed(coord, dec)
};
let chunk_offsets: Vec<usize> = chunk_info
@@ -1055,7 +1056,7 @@ pub fn read_chunked_data_sweep(
}
// Try decompressed cache first
let decompressed = if let Some(cached) = cache.get_decompressed(&coord) {
let decompressed = if let Some(cached) = cache.get_decompressed_aligned(&coord) {
cached
} else {
// Decompress from file
@@ -1077,8 +1078,7 @@ pub fn read_chunked_data_sweep(
} else {
raw_chunk.to_vec()
};
cache.put_decompressed(coord, dec.clone());
dec
cache.put_decompressed(coord, dec)
};
let chunk_offsets: Vec<usize> = chunk_info
@@ -1271,7 +1271,7 @@ pub fn read_chunked_data_indexed(
.ok_or_else(|| FormatError::ChunkedReadError("chunk layout not available".into()))?;
// Decompress chunks (using LRU cache where possible)
let mut chunk_buffers: Vec<CacheAlignedBuffer> = Vec::with_capacity(mappings_info.len());
let mut chunk_buffers: Vec<Arc<CacheAlignedBuffer>> = Vec::with_capacity(mappings_info.len());
for (coord, file_offset, file_size, filter_mask) in &mappings_info {
if let Some(cached) = cache.get_decompressed_aligned(coord) {
chunk_buffers.push(cached);
@@ -1295,8 +1295,8 @@ pub fn read_chunked_data_indexed(
raw_chunk.to_vec()
};
let aligned = CacheAlignedBuffer::from_vec(decompressed);
cache.put_decompressed_aligned(coord.clone(), aligned.clone());
chunk_buffers.push(aligned);
let arc = cache.put_decompressed_aligned(coord.clone(), aligned);
chunk_buffers.push(arc);
}
}