[wasm] mmap/lock free allocator optimizations#102265
Merged
kg merged 1 commit intodotnet:mainfrom May 23, 2024
Merged
Conversation
…enabled Request non-zeroed pages from custom mmap in lock free allocator, since all of its callers memset their allocations anyway
ghost
added
the
needs-area-label
Contributor
|
Tagging subscribers to 'arch-wasm': @lewing |
Member
Author
|
According to the profiler this also makes sgen meaningfully faster at scanning roots, but I'm not sure why. Maybe it always scans complete pages so by more efficiently using pages there are less bytes for it to scan? |
BrzVlad
approved these changes
May 15, 2024
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 subscribe to this conversation on GitHub.
Already have an account?
Sign in.
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Right now on WASM we ask mmap for 16KB pages in the lock-free allocator, and mmap hands us 64KB pages that we end up wasting 3/4 of.
We also ask for zeroed pages, but we don't need zeroed pages because all of the lock-free allocator's callers memset or fully initialize their allocations anyway.
Partially fixes dotnet/perf-autofiling-issues#34303 and fixes dotnet/perf-autofiling-issues#34274