Messages in this thread | | | Subject | Re: [sched/fair] ddb3b1126f: hackbench.throughput -25.9% regression | From | Tim Chen <> | Date | Wed, 30 Mar 2022 16:48:05 -0700 |
| |
On Wed, 2022-03-30 at 17:46 +0800, kernel test robot wrote: > > Greeting, > > FYI, we noticed a -25.9% regression of hackbench.throughput due to commit: >
Will try to check the regression seen.
Thanks.
Tim
> > > commit: > d9ad181b93 ("sched/fair: Don't rely on ->exec_start for migration") > ddb3b1126f ("sched/fair: Simple runqueue order on migrate") > > d9ad181b93f83b36 ddb3b1126fe93e8d6e059600488 > ---------------- --------------------------- > %stddev %change %stddev > \ | \ > 92566 -25.9% 68598 ± 2% hackbench.throughput > 85.50 +40.8% 120.35 ± 2% hackbench.time.elapsed_time > 85.50 +40.8% 120.35 ± 2% hackbench.time.elapsed_time.max > 9674391 ± 2% +466.2% 54780205 ± 2% hackbench.time.involuntary_context_switches > 1240 +42.6% 1768 ± 3% hackbench.time.system_time > 89.58 +20.4% 107.85 hackbench.time.user_time > 36626407 +270.2% 1.356e+08 ± 2% hackbench.time.voluntary_context_switches > 2500490 ± 3% +78.2% 4456808 ± 3% cpuidle..usage > 118.45 ± 2% +29.2% 153.02 ± 2% uptime.boot >
| |