diff options
author | Sebastian Andrzej Siewior <bigeasy@linutronix.de> | 2025-06-30 17:50:34 +0300 |
---|---|---|
committer | Peter Zijlstra <peterz@infradead.org> | 2025-07-01 16:02:05 +0300 |
commit | 9a57c3773152a3ff2c35cc8325e088d011c9f83b (patch) | |
tree | 8d8142ce34bc9355fe9aab42e4179390df261e53 /scripts/lib/kdoc/kdoc_files.py | |
parent | d0b3b7b22dfa1f4b515fd3a295b3fd958f9e81af (diff) | |
download | linux-9a57c3773152a3ff2c35cc8325e088d011c9f83b.tar.xz |
futex: Temporary disable FUTEX_PRIVATE_HASH
Chris Mason reported a performance regression on big iron. Reports of
this kind were usually reported as part of a micro benchmark but Chris'
test did mimic his real workload. This makes it a real regression.
The root cause is rcuref_get() which is invoked during each futex
operation. If all threads of an application do this simultaneously then
it leads to cache line bouncing and the performance drops.
Disable FUTEX_PRIVATE_HASH entirely for this cycle. The performance
regression will be addressed in the following cycle enabling the option
again.
Closes: https://lore.kernel.org/all/3ad05298-351e-4d61-9972-ca45a0a50e33@meta.com/
Reported-by: Chris Mason <clm@meta.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20250630145034.8JnINEaS@linutronix.de
Diffstat (limited to 'scripts/lib/kdoc/kdoc_files.py')
0 files changed, 0 insertions, 0 deletions