perf(sqlite-native): avoid cloning cached read chunks

[NathanFlurry]

Description

Please include a summary of the changes and the related issue. Please also include relevant motivation and context.

Type of change

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• This change requires a documentation update

How Has This Been Tested?

Please describe the tests that you ran to verify your changes.

Checklist:

• My code follows the style guidelines of this project
• I have performed a self-review of my code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes

[NathanFlurry]

Warning

This pull request is not mergeable via GitHub because a downstack PR is open. Once all requirements are satisfied, merge this PR as a stack on Graphite.
Learn more

• fix(rivetkit): surface native sqlite kv errors to callers #4645
• fix(rivetkit): prevent sleep races during disconnect and db work #4644
• fix(rivetkit): isolate engine envoys and propagate startup failures #4643
• test(rivetkit): remove wasm sqlite-only fixtures and coverage #4642
• chore(sqlite-vfs): remove wasm sqlite packages and workspace wiring #4641
• chore(rivetkit): remove wasm sqlite runtime #4614
• fix(sqlite-native): restore native startup kv preload #4639
• fix(sqlite-native): delete metadata before chunk range #4638
• fix(sqlite-native): keep truncate cache coherent #4637
• fix(sqlite-vfs): use delete range for truncate cleanup #4636
• fix(sqlite-native): restore kv error hook #4635
• perf(sqlite-native): avoid cloning cached read chunks #4634 👈 (View in Graphite)
• perf(sqlite-native): gate kv operation labels #4633
• perf(sqlite-native): reuse read cache for partial writes #4632
• perf(sqlite-native): remove delete file existence probe #4631
• fix(sqlite-native): gate native read cache behind env var #4630
• fix(pegboard): isolate runner config dc lookup failures #4625 : 1 other dependent PR (#4626 )
• docs(pegboard): note runner config upsert split write risk #4624
• fix(pegboard): unpack global runner config keys correctly #4623
• fix(pegboard-gateway): enforce tunnel message state #4622
• fix(pegboard-runner): clear terminal tunnel routes #4621
• fix(pegboard): skip protocol version keys in runner pool backfill #4620
• fix(pegboard): create missing normal runner configs #4619
• fix(epoxy): reuse cached optimistic value #4618
• main

This stack of pull requests is managed by Graphite. Learn more about stacking.

[claude]

Review: perf(sqlite-native): avoid cloning cached read chunks\n\nThe optimization is correct and well-targeted.\n\n### What the change does\n\n1. Eliminates buffered.clone() and cached.clone() for dirty-buffer and read-cache hits by storing &[u8] slices instead of owned Vec<u8> copies.\n2. Defers the read-cache population until after the chunk-copy loop, decoupling it from the KV response handling.\n3. Cleans up comment organization and restructures the lookup chain.\n\n### Correctness\n\nThe code is correct. Two invariants make it safe:\n\n- Disjoint key sets: buffered_chunks stores slices from read_cache for chunks that were cache hits. The subsequent read_cache.insert loop only writes newly fetched chunks (cache misses). No key overlap means no existing Vec is dropped while buffered_chunks slices are still live.\n- Vec heap stability: HashMap<Vec<u8>, Vec<u8>> stores values inline as Vec<u8> structs. On HashMap resize the struct is moved but the heap buffer it points to is not. So as_slice() survives a HashMap grow.\n\nThese invariants hold but are non-obvious. A brief comment near the buffered_chunks declaration explaining why the slices remain valid through the later read_cache.as_mut() call would help future readers.\n\n### Minor: double BTreeMap lookup for dirty-buffer chunks\n\nThe new code does contains_key in the prep loop then get in the retrieval loop: two O(log n) lookups. This could be collapsed by storing the borrow directly:\n\nrust\nif state.batch_mode {\n if let Some(buffered) = state.dirty_buffer.get(&(chunk_idx as u32)) {\n buffered_chunks.insert(chunk_idx, buffered.as_slice()); // no clone\n continue;\n }\n}\n\n\nThis eliminates the if state.batch_mode branch in the retrieval loop too. Not a blocker.\n\n### Nit: shadowed variable name\n\nread_start is declared twice in kv_io_read (line 376 as Instant::now(), line 442 as a chunk byte offset). Predates this PR but worth a follow-up.\n\n---\n\nOverall: Sound optimization with cleaner structure. Main ask is a comment near buffered_chunks documenting the slice-lifetime safety invariant.