All of lore.kernel.org
 help / color / mirror / Atom feed
From: Feng Tang <feng.tang@intel.com>
To: lkp@lists.01.org
Subject: Re: [x86/asm] 0507503671: will-it-scale.per_process_ops -4.9% regression
Date: Tue, 16 Nov 2021 09:41:28 +0800	[thread overview]
Message-ID: <20211116014128.GD34844@shbuild999.sh.intel.com> (raw)
In-Reply-To: <20211115214653.GR174703@worktop.programming.kicks-ass.net>

[-- Attachment #1: Type: text/plain, Size: 1491 bytes --]

On Mon, Nov 15, 2021 at 10:46:53PM +0100, Peter Zijlstra wrote:
> On Mon, Nov 15, 2021 at 01:15:49PM -0800, H. Peter Anvin wrote:
> > It is perhaps a bit hard for gcc to know what S's are C so they can be E'd, since all it sees is assembly.
> 
> Well, if we were able to declare it pure, then it would know that the
> output only depends on the inputs and thus it can merge all
> static_call_{,un}likely() branches that take the same key argument. But
> alas.
> 
> Funnily, everything I try to make that function 'better' actually makes
> it longer, so I'm suspecting it does something clever with
> static_cpu_has() nevertheless.
> 
> > It also doesn't explain how this code
> > could possibly have this kind of impact; of anything, it should make this change more beneficial, not less; certainly not make it consume 5% more CPU.
> 
> Yeah, no idea there. We've had wild 0day reports before due to either
> code or data layout changes that otherwise make no sense at all. They've
> tried to eliminate a bunch of that by increasing function alignment or
> somesuch (there was a talk at LPC? on that). But it remains a bit of a
> mystery.

Yes, we gave a talk at LPC:
https://linuxplumbersconf.org/event/11/contributions/895/attachments/770/1603/Strange_kernel_performance_changes_lpc_2021.pdf

And as you said, for many strange performance impact cases, we still
don't know the exact root cause. And Fengwei is still working on
chasing this down. 

Thanks,
Feng

  reply	other threads:[~2021-11-16  1:41 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-11-15  7:37 [x86/asm] 0507503671: will-it-scale.per_process_ops -4.9% regression kernel test robot
2021-11-15  9:53 ` Yin Fengwei
2021-11-15 19:20   ` H. Peter Anvin
2021-11-15 20:39     ` Peter Zijlstra
2021-11-15 21:15       ` H. Peter Anvin
2021-11-15 21:46         ` Peter Zijlstra
2021-11-16  1:41           ` Feng Tang [this message]
2021-11-16  1:57         ` Yin Fengwei
2021-11-16  1:40     ` Yin Fengwei
2021-11-16  9:33       ` Yin Fengwei
2021-11-17  2:44         ` Oliver Sang
2021-11-17  1:00       ` H. Peter Anvin
2021-11-17  1:27         ` Yin Fengwei

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20211116014128.GD34844@shbuild999.sh.intel.com \
    --to=feng.tang@intel.com \
    --cc=lkp@lists.01.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.