linux-kernel - Re: [sched/fair] 3c29e651e1: hackbench.throughput -15.2% regression

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Date:   Wed, 1 Apr 2020 16:10:46 +0530
From:   Viresh Kumar <viresh.kumar@...aro.org>
To:     kernel test robot <rong.a.chen@...el.com>
Cc:     Ingo Molnar <mingo@...nel.org>,
        Peter Zijlstra <peterz@...radead.org>,
        Daniel Lezcano <daniel.lezcano@...aro.org>,
        Linus Torvalds <torvalds@...ux-foundation.org>,
        Thomas Gleixner <tglx@...utronix.de>,
        Vincent Guittot <vincent.guittot@...aro.org>,
        LKML <linux-kernel@...r.kernel.org>, lkp@...ts.01.org
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