Add benchmark search tracing - #1362
Draft
Roman Schejbal (romanschejbal) wants to merge 1 commit into
Draft
Conversation
Expose coarse disk-search spans and aggregate traversal metrics behind a disabled-by-default diagnostic feature. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> Copilot-Session: cc3dbcbb-b4a9-41a7-93ad-26379768d4fb
|
Roman Schejbal (@romanschejbal) please read the following Contributor License Agreement(CLA). If you agree with the CLA, please reply with the following information.
Contributor License AgreementContribution License AgreementThis Contribution License Agreement (“Agreement”) is agreed to by the party signing below (“You”),
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Reference Issues/PRs
N/A
What does this implement/fix? Briefly explain your changes.
Adds opt-in diagnostic tracing for disk search under the
benchmark-search-tracingfeature.The instrumentation records coarse spans for query preparation, graph search, and reranking, plus aggregate fields for comparisons, hops, beam expansions, neighbors considered, traversal I/O, vertex read/materialization time, PQ computation time, and success/error outcome. The feature is disabled by default and compiles to no-op metric storage when not enabled.
The tracing wrapper is integrated with the current indexed-vector search path and is intended for controlled diagnostic benchmarks.
Any other comments?
This is a draft to gather feedback on span names, aggregation boundaries, and disabled-path overhead before considering broader use.
Validation:
cargo fmt --all -- --checkcargo check -p diskann-disk --features benchmark-search-tracingcargo test -p diskann-disk --lib --features benchmark-search-tracing(252 passed)cargo clippy -p diskann-disk --features benchmark-search-tracing -- -D warnings