feat(engine): expose ReorderBuffer stall-duration and queue-depth metrics (#1885)#4195
Merged
Merged
Conversation
Adds a public `Metrics` snapshot returned by `ReorderBuffer::metrics()` exposing the cumulative stall duration (time spent waiting for the next expected sequence while items are buffered ahead), the instantaneous queue depth, and the high-water mark since construction. `Instant::now` is only sampled on stall edges, keeping the hot path allocation- and syscall-free for in-order inserts. Bypass mode reports depth only, since it never reorders. Includes unit tests covering single and multi-stall windows, force_insert / take interactions, and the in-flight snapshot behaviour. Closes #1885.
3 tasks
oferchen
added a commit
that referenced
this pull request
May 18, 2026
Adds a public `Metrics` snapshot returned by `ReorderBuffer::metrics()` exposing the cumulative stall duration (time spent waiting for the next expected sequence while items are buffered ahead), the instantaneous queue depth, and the high-water mark since construction. `Instant::now` is only sampled on stall edges, keeping the hot path allocation- and syscall-free for in-order inserts. Bypass mode reports depth only, since it never reorders. Includes unit tests covering single and multi-stall windows, force_insert / take interactions, and the in-flight snapshot behaviour. Closes #1885.
oferchen
added a commit
that referenced
this pull request
May 18, 2026
Adds a public `Metrics` snapshot returned by `ReorderBuffer::metrics()` exposing the cumulative stall duration (time spent waiting for the next expected sequence while items are buffered ahead), the instantaneous queue depth, and the high-water mark since construction. `Instant::now` is only sampled on stall edges, keeping the hot path allocation- and syscall-free for in-order inserts. Bypass mode reports depth only, since it never reorders. Includes unit tests covering single and multi-stall windows, force_insert / take interactions, and the in-flight snapshot behaviour. Closes #1885.
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
1 participant
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.
Summary
ReorderBuffer::metrics()returning aMetrics { stall_duration, current_depth, max_depth }snapshot so operators can diagnose pipeline stalls without ad hoc instrumentation. Feeds the spill-to-tempfile diagnostics tracked in Ensure release workflow uploads architecture-specific assets #1884.Instant::nowis sampled only on stall edges (gap opens, gap closes); steady-state in-order inserts pay no extra syscall.insert,next_in_order,force_insert, andtake. Bypass / passthrough mode reports depth only since it does not reorder.ReorderMetricsfromengine::concurrent_deltaalongside the existingReorderBufferre-export.Test plan
command cargo fmt --all -- --checkcommand cargo clippy -p engine --all-features --all-targets --no-deps -- -D warningscommand cargo nextest run -p engine --all-features -E 'test(concurrent_delta::reorder)'(68 tests, including the 9 newmetrics_testscases)Closes #1885