All of lore.kernel.org
 help / color / mirror / Atom feed
From: Nathan Chancellor <nathan@kernel.org>
To: Rik van Riel <riel@surriel.com>
Cc: Thorsten Leemhuis <regressions@leemhuis.info>,
	Andrew Morton <akpm@linux-foundation.org>,
	Yang Shi <shy828301@gmail.com>,
	"Huang, Ying" <ying.huang@intel.com>,
	kernel test robot <yujie.liu@intel.com>,
	lkp@lists.01.org, lkp@intel.com,
	Matthew Wilcox <willy@infradead.org>,
	linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	feng.tang@intel.com, zhengjun.xing@linux.intel.com,
	fengwei.yin@intel.com
Subject: Re: [mm] f35b5d7d67: will-it-scale.per_process_ops -95.5% regression
Date: Thu, 1 Dec 2022 14:35:31 -0700	[thread overview]
Message-ID: <Y4keIyIK6OA3nOwT@dev-arch.thelio-3990X> (raw)
In-Reply-To: <07adee081a70c2b4b44d9bf93a0ad3142e091086.camel@surriel.com>

On Thu, Dec 01, 2022 at 03:29:41PM -0500, Rik van Riel wrote:
> On Thu, 2022-12-01 at 19:33 +0100, Thorsten Leemhuis wrote:
> > Hi, this is your Linux kernel regression tracker.
> > 
> > On 28.11.22 07:40, Nathan Chancellor wrote:
> > > Hi Rik,
> > 
> > I wonder what we should do about below performance regression. Is
> > reverting the culprit now and reapplying it later together with a fix
> > a
> > viable option? Or was anything done/is anybody doing something
> > already
> > to address the problem and I just missed it?
> 
> The changeset in question speeds up kernel compiles with
> GCC, as well as the runtime speed of other programs, due
> to being able to use THPs more. However, it slows down kernel
> compiles with clang, due to ... something clang does.
> 
> I have not figured out what that something is yet.
> 
> I don't know if I have the wrong version of clang here,
> but I have not seen any smoking gun at all when tracing
> clang system calls. I see predominantly small mmap and
> unmap calls, and nothing that even triggers 2MB alignment.

Sorry about that :/ What version of clang are you trying to reproduce
with? I was able to see this with 14.x and 16.x, it is possible that
older versions do not do the thing that is causing this.

I cannot really be testing much on my main workstation but I will see if
I can reproduce this behavior on one of my other test systems or a
virtual machine. Once I do that, if you are still unable to reproduce
it, I can potentially try and help you debug this, although I will
likely need some hand holding.

Cheers,
Nathan

> > Yang Shi, Andrew, what's your option on this? I ask you directly,
> > because it looks like Rik hasn't posted anything to lists archived on
> > lore during the last few weeks. :-/
> > 
> > Ciao, Thorsten (wearing his 'the Linux kernel's regression tracker'
> > hat)
> > 
> > P.S.: As the Linux kernel's regression tracker I deal with a lot of
> > reports and sometimes miss something important when writing mails
> > like
> > this. If that's the case here, don't hesitate to tell me in a public
> > reply, it's in everyone's interest to set the public record straight.
> > 
> > > On Thu, Oct 20, 2022 at 10:16:20AM -0700, Nathan Chancellor wrote:
> > > > On Thu, Oct 20, 2022 at 11:28:16AM -0400, Rik van Riel wrote:
> > > > > On Thu, 2022-10-20 at 13:07 +0800, Huang, Ying wrote:
> > > > > > Nathan Chancellor <nathan@kernel.org> writes:
> > > > > > > 
> > > > > > > For what it's worth, I just bisected a massive and visible
> > > > > > > performance
> > > > > > > regression on my Threadripper 3990X workstation to commit
> > > > > > > f35b5d7d676e
> > > > > > > ("mm: align larger anonymous mappings on THP boundaries"),
> > > > > > > which
> > > > > > > seems
> > > > > > > directly related to this report/analysis. I initially
> > > > > > > noticed this
> > > > > > > because my full set of kernel builds against mainline went
> > > > > > > from 2
> > > > > > > hours
> > > > > > > and 20 minutes or so to over 3 hours. Zeroing in on x86_64
> > > > > > > allmodconfig,
> > > > > > > which I used for the bisect:
> > > > > > > 
> > > > > > > @ 7b5a0b664ebe ("mm/page_ext: remove unused variable in
> > > > > > > offline_page_ext"):
> > > > > > > 
> > > > > > > Benchmark 1: make -skj128 LLVM=1 allmodconfig all
> > > > > > >   Time (mean ± σ):     318.172 s ±  0.730 s    [User:
> > > > > > > 31750.902 s,
> > > > > > > System: 4564.246 s]
> > > > > > >   Range (min … max):   317.332 s … 318.662 s    3 runs
> > > > > > > 
> > > > > > > @ f35b5d7d676e ("mm: align larger anonymous mappings on THP
> > > > > > > boundaries"):
> > > > > > > 
> > > > > > > Benchmark 1: make -skj128 LLVM=1 allmodconfig all
> > > > > > >   Time (mean ± σ):     406.688 s ±  0.676 s    [User:
> > > > > > > 31819.526 s,
> > > > > System: 16327.022 s]
> > > > > > >   Range (min … max):   405.954 s … 407.284 s    3 run
> > > > > > 
> > > > > > Have you tried to build with gcc?  Want to check whether is
> > > > > > this
> > > > > > clang
> > > > > > specific issue or not.
> > > > > 
> > > > > This may indeed be something LLVM specific. In previous tests,
> > > > > GCC has generally seen a benefit from increased THP usage.
> > > > > Many other applications also benefit from getting more THPs.
> > > > 
> > > > Indeed, GCC builds actually appear to be slightly faster on my
> > > > system now,
> > > > apologies for not trying that before reporting :/
> > > > 
> > > > 7b5a0b664ebe:
> > > > 
> > > > Benchmark 1: make -skj128 allmodconfig all
> > > >   Time (mean ± σ):     355.294 s ±  0.931 s    [User: 33620.469
> > > > s, System: 6390.064 s]
> > > >   Range (min … max):   354.571 s … 356.344 s    3 runs
> > > > 
> > > > f35b5d7d676e:
> > > > 
> > > > Benchmark 1: make -skj128 allmodconfig all
> > > >   Time (mean ± σ):     347.400 s ±  2.029 s    [User: 34389.724
> > > > s, System: 4603.175 s]
> > > >   Range (min … max):   345.815 s … 349.686 s    3 runs
> > > > 
> > > > > LLVM showing 10% system time before this change, and a whopping
> > > > > 30% system time after that change, suggests that LLVM is
> > > > > behaving
> > > > > quite differently from GCC in some ways.
> > > > 
> > > > The above tests were done with GCC 12.2.0 from Arch Linux. The
> > > > previous LLVM
> > > > tests were done with a self-compiled version of LLVM from the
> > > > main branch
> > > > (16.0.0), optimized with BOLT [1]. To eliminate that as a source
> > > > of issues, I
> > > > used my distribution's version of clang (14.0.6) and saw similar
> > > > results as
> > > > before:
> > > > 
> > > > 7b5a0b664ebe:
> > > > 
> > > > Benchmark 1: make -skj128 LLVM=/usr/bin/ allmodconfig all
> > > >   Time (mean ± σ):     462.517 s ±  1.214 s    [User: 48544.240
> > > > s, System: 5586.212 s]
> > > >   Range (min … max):   461.115 s … 463.245 s    3 runs
> > > > 
> > > > f35b5d7d676e:
> > > > 
> > > > Benchmark 1: make -skj128 LLVM=/usr/bin/ allmodconfig all
> > > >   Time (mean ± σ):     547.927 s ±  0.862 s    [User: 47913.709
> > > > s, System: 17682.514 s]
> > > >   Range (min … max):   547.429 s … 548.922 s    3 runs
> > > > 
> > > > > If we can figure out what these differences are, maybe we can
> > > > > just fine tune the code to avoid this issue.
> > > > > 
> > > > > I'll try to play around with LLVM compilation a little bit next
> > > > > week, to see if I can figure out what might be going on. I
> > > > > wonder
> > > > > if LLVM is doing lots of mremap calls or something...
> > > > 
> > > > If there is any further information I can provide or patches I
> > > > can test,
> > > > I am more than happy to do so.
> > > > 
> > > > [1]:
> > > > https://github.com/llvm/llvm-project/tree/96552e73900176d65ee6650facae8d669d6f9498/bolt
> > > 
> > > Was there ever a follow up to this report that I missed? I just
> > > noticed that I am still reverting f35b5d7d676e in my mainline
> > > kernel.
> > > 
> > > Cheers,
> > > Nathan
> > > 
> > 
> > #regzbot ignore-activity
> > 
> 
> -- 
> All Rights Reversed.



  parent reply	other threads:[~2022-12-01 21:35 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-10-18  8:44 [mm] f35b5d7d67: will-it-scale.per_process_ops -95.5% regression kernel test robot
2022-10-18  8:44 ` kernel test robot
2022-10-19  2:05 ` Huang, Ying
2022-10-19  2:05   ` Huang, Ying
2022-10-20  4:23   ` Nathan Chancellor
2022-10-20  4:23     ` Nathan Chancellor
2022-10-20  5:07     ` Huang, Ying
2022-10-20  5:07       ` Huang, Ying
2022-10-20 15:28       ` Rik van Riel
2022-10-20 15:28         ` Rik van Riel
2022-10-20 17:16         ` Nathan Chancellor
2022-10-20 17:16           ` Nathan Chancellor
2022-11-28  6:40           ` Nathan Chancellor
2022-12-01 18:33             ` Thorsten Leemhuis
2022-12-01 20:29               ` Rik van Riel
2022-12-01 21:22                 ` Andrew Morton
2022-12-01 21:44                   ` Yang Shi
2022-12-02  8:46                   ` Thorsten Leemhuis
2022-12-02 18:44                     ` Andrew Morton
2022-12-02 19:37                       ` Thorsten Leemhuis
2022-12-01 21:35                 ` Nathan Chancellor [this message]
2022-12-16 11:48                 ` Yin, Fengwei
2022-10-20 16:40       ` Yujie Liu
2022-10-20 16:40         ` Yujie Liu
2022-11-29  8:59     ` [mm] f35b5d7d67: will-it-scale.per_process_ops -95.5% regression #forregzbot Thorsten Leemhuis
2022-12-02  6:43       ` Thorsten Leemhuis

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=Y4keIyIK6OA3nOwT@dev-arch.thelio-3990X \
    --to=nathan@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=feng.tang@intel.com \
    --cc=fengwei.yin@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=lkp@intel.com \
    --cc=lkp@lists.01.org \
    --cc=regressions@leemhuis.info \
    --cc=riel@surriel.com \
    --cc=shy828301@gmail.com \
    --cc=willy@infradead.org \
    --cc=ying.huang@intel.com \
    --cc=yujie.liu@intel.com \
    --cc=zhengjun.xing@linux.intel.com \
    /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.