core/benches: Add benchmark for apply_inbound #95
Conversation
This file contains 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
This commit adds a small benchmark test for the `apply_inbound` method. This allows benchmarking the usage of `Vec` or `SmallVec` in the `InboundUpgradeApplyState` state machine. The benchmark executes a minimal multistream-select listener upgrade on an in-memory connection and then runs the `Ready` upgrade on top of the negotiated in-memory connection. The protocol negotiated in the first step is either stored in a `Vec` or a `SmallVec`. I am unable to optimize the benchmark such that `SmallVec` has a significant performance benefit over `Vec`. I would love to be proven wrong, i.e. I would love for someone to find a benchmark that does show a significant difference. You can replicate these results by running: ``` cd core cargo bench --bench upgrade -- --save-baseline vec cargo bench --bench upgrade -- --save-baseline small-vec ➜ critcmp small-vec vec group small-vec vec ----- --------- --- inbound_upgrade 1.00 342.6±1.43ns ? ?/sec 1.02 348.0±1.66ns ? ?/sec ``` (Note on the protocol name, I was initially testing the failure case.)
4 tasks
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Outdated suggestions cannot be applied.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.
This commit adds a small benchmark test for the
apply_inboundmethod. This allows benchmarking the usage ofVecorSmallVecin theInboundUpgradeApplyStatestate machine.The benchmark executes a minimal multistream-select listener upgrade on an in-memory connection and then runs the
Readyupgrade on top of the negotiated in-memory connection. The protocol negotiated in the first step is either stored in aVecor aSmallVec.I am unable to optimize the benchmark such that
SmallVechas a significant performance benefit overVec. I would love to be proven wrong, i.e. I would love for someone to find a benchmark that does show a significant difference.You can replicate these results by running:
(Note on the protocol name, I was initially testing the failure case.)