Fix lwAFTR trace performance issues (for release Alpina) #1488
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Outdated suggestions cannot be applied.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.
Running CI for the Alpina release showed a performance regression in the lwaftr benchmark.
I’ve triaged this to not be due a specific code change, but an existing condition where the previous code generated traces that unnecessarily invoked the GC.
These two commits eliminate some casts that could set off the GC and some side traces to make perf more predictable:
push
(I had increased the queue size for this, but it should be fine with the defaultengine.pull_npackets
and there is a new assertion to check the currently hardcoded queue size is sufficient.)make_multi_hash
method to not generate side traces. Also removed casts (caller has to ensure arguments are of the right types, all current callers already do this).