Messages in this thread | | | Date | Wed, 1 Apr 2020 16:10:46 +0530 | From | Viresh Kumar <> | Subject | Re: [sched/fair] 3c29e651e1: hackbench.throughput -15.2% regression |
| |
Hi,
Sorry for getting back to this after a long time :(
On 05-02-20, 20:29, kernel test robot wrote: > Greeting, > > FYI, we noticed a -15.2% regression of hackbench.throughput due to commit: > > > commit: 3c29e651e16dd3b3179cfb2d055ee9538e37515c ("sched/fair: Fall back to sched-idle CPU if idle CPU isn't found") > https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master > > in testcase: hackbench > on test machine: 16 threads Intel(R) Xeon(R) E-2278G CPU @ 3.40GHz with 32G memory > with following parameters: > > nr_threads: 100% > mode: threads > ipc: pipe > cpufreq_governor: performance > ucode: 0xca
I tried following command on my x86 box, skylake, 8 CPUs
"/usr/bin/hackbench" "-g" "8" "--threads" "--pipe" "-l" "30000" "-s" "100"
And hackbench mostly reports values from 29.4 to 30.7, with and without my patches. I used intel_pstate=passive in command line and chose performance governor by default.
I don't see any issues here in hackbench numbers because of my patches.
-- viresh
| |