[PATCH] Skip benchmarking of non-best xor_syndrome functions
From: Dirk Müller <hidden>
Date: 2021-12-29 22:34:20
Subsystem:
library code, the rest · Maintainers:
Andrew Morton, Linus Torvalds
In commit fe5cbc6e06c7 ("md/raid6 algorithms: delta syndrome functions")
a xor_syndrome() has been added for optimized syndrome calculation and
being added also to to the raid6_choose_gen() function. However, the
result of the xor_syndrome() benchmarking was intentionally discarded
and did not influence the choice.
We can optimize raid6_choose_gen() without changing its behavior by
only benchmarking the chosen xor_syndrome() variant and printing it
output, rather than benchmarking also the ones that are discarded and
never influence the outcome.
For x86_64, this removes 8 out of 18 benchmark loops which each take
16 jiffies, so up to 160 jiffies saved on module load (640ms on a 250HZ
kernel).
Signed-off-by: Dirk Müller <redacted>
---
lib/raid6/algos.c | 76 +++++++++++++++++++++++------------------------
1 file changed, 37 insertions(+), 39 deletions(-)
diff --git a/lib/raid6/algos.c b/lib/raid6/algos.c
index 6d5e5000fdd7..889033b7fc0d 100644
--- a/lib/raid6/algos.c
+++ b/lib/raid6/algos.c@@ -145,12 +145,12 @@ static inline const struct raid6_recov_calls *raid6_choose_recov(void) static inline const struct raid6_calls *raid6_choose_gen( void *(*const dptrs)[RAID6_TEST_DISKS], const int disks) { - unsigned long perf, bestgenperf, bestxorperf, j0, j1; + unsigned long perf, bestgenperf, j0, j1; int start = (disks>>1)-1, stop = disks-3; /* work on the second half of the disks */ const struct raid6_calls *const *algo; const struct raid6_calls *best; - for (bestgenperf = 0, bestxorperf = 0, best = NULL, algo = raid6_algos; *algo; algo++) { + for (bestgenperf = 0, best = NULL, algo = raid6_algos; *algo; algo++) { if (!best || (*algo)->prefer >= best->prefer) { if ((*algo)->valid && !(*algo)->valid()) continue;
@@ -180,50 +180,48 @@ static inline const struct raid6_calls *raid6_choose_gen( pr_info("raid6: %-8s gen() %5ld MB/s\n", (*algo)->name, (perf * HZ * (disks-2)) >> (20 - PAGE_SHIFT + RAID6_TIME_JIFFIES_LG2)); + } + } - if (!(*algo)->xor_syndrome) - continue; + if (best == NULL) { + pr_err("raid6: Yikes! No algorithm found!\n"); + goto out; + } - perf = 0; + raid6_call = *best; - preempt_disable(); - j0 = jiffies; - while ((j1 = jiffies) == j0) - cpu_relax(); - while (time_before(jiffies, - j1 + (1<<RAID6_TIME_JIFFIES_LG2))) { - (*algo)->xor_syndrome(disks, start, stop, - PAGE_SIZE, *dptrs); - perf++; - } - preempt_enable(); - - if (best == *algo) - bestxorperf = perf; + if (!IS_ENABLED(CONFIG_RAID6_PQ_BENCHMARK)) { + pr_info("raid6: skipped pq benchmark and selected %s\n", + best->name); + goto out; + } - pr_info("raid6: %-8s xor() %5ld MB/s\n", (*algo)->name, - (perf * HZ * (disks-2)) >> - (20 - PAGE_SHIFT + RAID6_TIME_JIFFIES_LG2 + 1)); + pr_info("raid6: using algorithm %s gen() %ld MB/s\n", + best->name, + (bestgenperf * HZ * (disks-2)) >> + (20 - PAGE_SHIFT+RAID6_TIME_JIFFIES_LG2)); + + if (best->xor_syndrome) { + perf = 0; + + preempt_disable(); + j0 = jiffies; + while ((j1 = jiffies) == j0) + cpu_relax(); + while (time_before(jiffies, + j1 + (1 << RAID6_TIME_JIFFIES_LG2))) { + best->xor_syndrome(disks, start, stop, + PAGE_SIZE, *dptrs); + perf++; } - } + preempt_enable(); - if (best) { - if (IS_ENABLED(CONFIG_RAID6_PQ_BENCHMARK)) { - pr_info("raid6: using algorithm %s gen() %ld MB/s\n", - best->name, - (bestgenperf * HZ * (disks-2)) >> - (20 - PAGE_SHIFT+RAID6_TIME_JIFFIES_LG2)); - if (best->xor_syndrome) - pr_info("raid6: .... xor() %ld MB/s, rmw enabled\n", - (bestxorperf * HZ * (disks-2)) >> - (20 - PAGE_SHIFT + RAID6_TIME_JIFFIES_LG2 + 1)); - } else - pr_info("raid6: skip pq benchmark and using algorithm %s\n", - best->name); - raid6_call = *best; - } else - pr_err("raid6: Yikes! No algorithm found!\n"); + pr_info("raid6: .... xor() %ld MB/s, rmw enabled\n", + (perf * HZ * (disks-2)) >> + (20 - PAGE_SHIFT + RAID6_TIME_JIFFIES_LG2 + 1)); + } +out: return best; }
--
2.34.1