Repository navigation
Conversation
rbstress fails for ff on ubuntu after 4 seconds: ruby 3.2 asks for
posix_memalign(32 KB, 32 MB) while it starts up, and ffmalloc answered
EINVAL for every request above page alignment that reaches its jumbo
path ("until that's fixed"). ruby reads the NULL as out of memory and
aborts in ruby_setup, so both rbstress tests die before the benchmark
begins. Fedora's ruby 4 makes no such request, which is why only ubuntu
is red.
Ask for the alignment in excess in the shared jumbo path and return an
aligned address inside the pool. A pointer inside a jumbo pool is valid
to free because free(), realloc() and malloc_usable_size() resolve the
pool that contains the pointer, so this needs no bookkeeping and the
three refusals in posix_memalign, memalign and aligned_alloc go away.
derSteFfi
marked this pull request as draft
November 12, 2026 16:59
derSteFfi
marked this pull request as ready for review
November 12, 2026 17:13
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
rbstressfails for ff on ubuntu after 4 seconds: ruby 3.2 asks forposix_memalign(32 KB, 32 MB)while it starts up, and ffmalloc answered EINVAL for every request above page alignment that reaches its jumbo path ("until that's fixed"). ruby reads the NULL as out of memory and aborts in ruby_setup, so both rbstress tests die before the benchmark begins. Fedora's ruby 4 makes no such request, which is why only ubuntu is red.Ask for the alignment in excess in the shared jumbo path and return an aligned address inside the pool. A pointer inside a jumbo pool is valid to free because
free(),realloc()andmalloc_usable_size()resolve the pool that contains the pointer, so this needs no bookkeeping and the three refusals in posix_memalign, memalign and aligned_alloc go away.While working on this I discovered what seems to be a race-condition for at least
xmalloc, but I'll look into that separately.