Re: [LKP] [lkp] [x86/platform/UV] 71854cb812: will-it-scale.per_thread_ops -2.3% regression

From	Thomas Gleixner <tglx@linutronix.de>
Newsgroups	linux.kernel
Subject	Re: [LKP] [lkp] [x86/platform/UV] 71854cb812: will-it-scale.per_thread_ops -2.3% regression
Date	2016-10-31 19:30 +0100
Message-ID	<sypvk-62L-31@gated-at.bofh.it> (permalink)
References	<sw3IB-1ZK-9@gated-at.bofh.it> <sw7Cx-4uH-9@gated-at.bofh.it> <swI93-3vr-3@gated-at.bofh.it> <sx1Y6-8mn-17@gated-at.bofh.it> <sydDP-6BQ-1@gated-at.bofh.it>
Organization	linux.* mail to news gateway

Show all headers | View raw

On Mon, 31 Oct 2016, Fengguang Wu wrote:
> On Fri, Oct 28, 2016 at 12:37:45AM +0200, Thomas Gleixner wrote:
> > I have no explanation for this either, but you really should try to figure
> > out what's going on here.
> 
> Xiaolong, how about doing a small debug patch (a WARN_ONCE() line may
> be enough) to verify whether the code path is executed?
> 
> It'd also help to compare vmlinux according to Thomas' reasoning:
> 
> > The only difference between plain rc1 and rc + this patch is the resulting
> > text size and therefor some other unrelated stuff moving to different
> > places in memory which has some yet to figure out side effects.

So one other thing you might try is using rc3 as a base line and then
revert the patch in question on top of rc3 and see whether that weird
behaviour persists.
 
> > From bisect POV, the below graphs show the user_time and system_time
> are clearly and consistently different before/after commit 71854cb812.
> So this commit must impacted something.

I agree. I just have no idea what happens.

Thanks,

	tglx

Back to linux.kernel | Previous | Next — Previous in thread | Find similar | Unroll thread

Thread

Re: [lkp] [x86/platform/UV] 71854cb812: will-it-scale.per_thread_ops  -2.3% regression Ye Xiaolong <xiaolong.ye@intel.com> - 2016-10-27 04:00 +0200
  Re: [lkp] [x86/platform/UV] 71854cb812: will-it-scale.per_thread_ops  -2.3% regression Thomas Gleixner <tglx@linutronix.de> - 2016-10-28 01:10 +0200
    Re: [LKP] [lkp] [x86/platform/UV] 71854cb812:  will-it-scale.per_thread_ops -2.3% regression Fengguang Wu <fengguang.wu@intel.com> - 2016-10-31 06:50 +0100
      Re: [LKP] [lkp] [x86/platform/UV] 71854cb812: will-it-scale.per_thread_ops  -2.3% regression Thomas Gleixner <tglx@linutronix.de> - 2016-10-31 19:30 +0100

csiph-web