diff options
| author | Dirk Müller <dmueller@suse.de> | 2022-01-05 17:38:47 +0100 |
|---|---|---|
| committer | Song Liu <song@kernel.org> | 2022-01-06 08:37:03 -0800 |
| commit | 36dacddbf0bdba86cd00f066b4d724157eeb63f1 (patch) | |
| tree | 3875efa25f6b1115f386c5d9d2805e0f732ce7a0 /lib/raid6/algos.c | |
| parent | 38640c480939d56cc8b03d58642fc5261761a697 (diff) | |
lib/raid6: Use strict priority ranking for pq gen() benchmarking
On x86_64, currently 3 variants of AVX512, 3 variants of AVX2
and 3 variants of SSE2 are benchmarked on initialization, taking
between 144-153 jiffies. Testing across a hardware pool of
various generations of intel cpus I could not find a single
case where SSE2 won over AVX2 or AVX512. There are cases where
AVX2 wins over AVX512 however.
Change "prefer" into an integer priority field (similar to
how recov selection works) to have more than one ranking level
available, which is backwards compatible with existing behavior.
Give AVX2/512 variants higher priority over SSE2 in order to skip
SSE testing when AVX is available. in a AVX2/x86_64/HZ=250 case this
saves in the order of 200ms of initialization time.
Signed-off-by: Dirk Müller <dmueller@suse.de>
Acked-by: Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: Song Liu <song@kernel.org>
Diffstat (limited to 'lib/raid6/algos.c')
| -rw-r--r-- | lib/raid6/algos.c | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/lib/raid6/algos.c b/lib/raid6/algos.c index 9b7e8a837b27..39b74221f4a7 100644 --- a/lib/raid6/algos.c +++ b/lib/raid6/algos.c @@ -151,7 +151,7 @@ static inline const struct raid6_calls *raid6_choose_gen( const struct raid6_calls *best; for (bestgenperf = 0, best = NULL, algo = raid6_algos; *algo; algo++) { - if (!best || (*algo)->prefer >= best->prefer) { + if (!best || (*algo)->priority >= best->priority) { if ((*algo)->valid && !(*algo)->valid()) continue; |