From: Carel Si <beibei.si@intel.com>
To: lkp@lists.01.org
Subject: Re: [x86/mm/tlb] 2f4305b19f: will-it-scale.per_thread_ops 23.3% improvement
Date: Mon, 29 Nov 2021 11:59:45 +0800 [thread overview]
Message-ID: <20211129035943.GA7092@linux.intel.com> (raw)
In-Reply-To: <20211125050221.GA26741@linux.intel.com>
[-- Attachment #1: Type: text/plain, Size: 6904 bytes --]
Hi Amit,
On Thu, Nov 25, 2021 at 01:02:22PM +0800, Carel Si wrote:
> Hi Amit,
>
> On Sun, Nov 07, 2021 at 09:47:46PM +0000, Nadav Amit wrote:
> >
> >
> > > On Nov 7, 2021, at 6:28 AM, kernel test robot <oliver.sang@intel.com> wrote:
> > >
> > >
> > >
> > > Greeting,
> > >
> > > FYI, we noticed a 23.3% improvement of will-it-scale.per_thread_ops due to commit:
> > >
> > >
> > > commit: 2f4305b19fe6a2a261d76c21856c5598f7d878fe ("x86/mm/tlb: Privatize cpu_tlbstate")
> > > https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgit.kernel.org%2Fcgit%2Flinux%2Fkernel%2Fgit%2Ftorvalds%2Flinux.git&data=04%7C01%7Cnamit%40vmware.com%7Cfb2bd9a47e794ec3898508d9a1faf794%7Cb39138ca3cee4b4aa4d6cd83d9dd62f0%7C0%7C0%7C637718921590793957%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=cw6sFeT6qAQSSaG7nCIWm19Yi9RPZqyr2bQPwSBuzzs%3D&reserved=0 master
> > >
> > > will-it-scale.per_thread_ops
> > >
> > > 4000 +--------------------------------------------------------------------+
> > > | |
> > > 3500 |-O O O O O O O O O O O O O O OO O O O O O O O O O O O O O O O O |
> > > 3000 |-+ .+. .+. |
> > > |.+.+.+.+.+.+ +.+.+.+.+.+.+.+ ++ +.+.+.+.+.+.+.+.+.+.+.+ |
> > > 2500 |-+ : : |
> > > | : : |
> > > 2000 |-+ : : |
> > > | : : |
> > > 1500 |-+ : : |
> > > 1000 |-+ : : |
> > > | : : |
> > > 500 |-+ : |
> > > | : |
> > > 0 +--------------------------------------------------------------------+
> >
> > Am I to understand that the following commit somehow reverted the performance
> > improvement of this patch? The graph shows it as a “spike”, no?
After more tests, we think this performance improvement was not reverted in its
following commit, the improvement was partly reverted (from +23% improvement to
+4.3% improvement) in 2ad32cf09b ("ceph: fix memory leak on decode error in
ceph_handle_caps"), which was merged in v5.15-rc1. Thanks.
=========================================================================================
compiler/cpufreq_governor/kconfig/mode/nr_task/rootfs/tbox_group/test/testcase/ucode:
gcc-9/performance/x86_64-rhel-8.3/thread/100%/debian-10.4-x86_64-20200603.cgz/lkp-hsw-4ex1/tlb_flush3/will-it-scale/0x16
commit:
4ce94eabac ("x86/mm/tlb: Flush remote and local TLBs concurrently")
2f4305b19f ("x86/mm/tlb: Privatize cpu_tlbstate")
v5.13-rc1
v5.14 >>> 2ad32cf09b's parent
2ad32cf09b ("ceph: fix memory leak on decode error in ceph_handle_caps")
4ce94eabac16b1d2 2f4305b19fe6a2a261d76c21856 v5.13-rc1 v5.14 2ad32cf09bd28a21e6ad1595355
---------------- --------------------------- --------------------------- --------------------------- ---------------------------
%stddev %change %stddev %change %stddev %change %stddev %change %stddev
\ | \ | \ | \ | \
2793 +23.4% 3448 +21.6% 3398 +20.5% 3366 +4.3% 2913 will-it-scale.per_thread_ops
>
> The performance improvement is exists in 635de956a7 ("Merge tag
> 'x86-mm-2021-04-29' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip"),
> in which the fbc has been merged, and v5.13-rc1, in which the fbc has been
> merged in mainline, and v5.14.
>
> We found the improvement has reverted between v5.15-rc5 and v5.14, has triggered
> bisection for it. Thanks.
>
> =========================================================================================
> compiler/cpufreq_governor/kconfig/mode/nr_task/rootfs/tbox_group/test/testcase/ucode:
> gcc-9/performance/x86_64-rhel-8.3/thread/100%/debian-10.4-x86_64-20200603.cgz/lkp-hsw-4ex1/tlb_flush3/will-it-scale/0x16
>
> commit:
> 4ce94eabac ("x86/mm/tlb: Flush remote and local TLBs concurrently") >> parent
> 2f4305b19f ("x86/mm/tlb: Privatize cpu_tlbstate") >> fbc
> 635de956a7 >> fbc merged
> v5.13-rc1 >> fbc merged to mainline
> v5.14
> v5.15-rc5
>
> 4ce94eabac16b1d2 2f4305b19fe6a2a261d76c21856 635de956a7f5a6ffcb04f29d706 v5.13-rc1 v5.14 v5.15-rc5
> ---------------- --------------------------- --------------------------- --------------------------- --------------------------- ---------------------------
> %stddev %change %stddev %change %stddev %change %stddev %change %stddev %change %stddev
> \ | \ | \ | \ | \ | \
> 2796 +23.3% 3448 +21.0% 3382 +21.4% 3393 +20.4% 3366 +10.0% 3075 ± 9% will-it-scale.per_thread_ops
>
>
> * 635de956a7f5a6 Merge tag 'x86-mm-2021-04-29' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
> |\
> | * a500fc918f7b8d Merge branch 'locking/core' into x86/mm, to resolve conflict
> | |\
> | * | d43f17a1da2537 smp: Micro-optimize smp_call_function_many_cond()
> | * | a5aa5ce3005972 smp: Inline on_each_cpu_cond() and on_each_cpu()
> | * | 1608e4cf31b88c x86/mm/tlb: Remove unnecessary uses of the inline keyword
> | * | 291c4011dd7ac0 cpumask: Mark functions as pure
> | * | 09c5272e48614a x86/mm/tlb: Do not make is_lazy dirty for no reason
> | * | 2f4305b19fe6a2 x86/mm/tlb: Privatize cpu_tlbstate >>> fbc
> | * | 4ce94eabac16b1 x86/mm/tlb: Flush remote and local TLBs concurrently
>
> >
> >
> > _______________________________________________
> > LKP mailing list -- lkp(a)lists.01.org
> > To unsubscribe send an email to lkp-leave(a)lists.01.org
next prev parent reply other threads:[~2021-11-29 3:59 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-11-07 14:28 [x86/mm/tlb] 2f4305b19f: will-it-scale.per_thread_ops 23.3% improvement kernel test robot
2021-11-07 21:47 ` Nadav Amit
2021-11-25 5:02 ` Carel Si
2021-11-29 3:59 ` Carel Si [this message]
2021-11-29 17:34 ` Nadav Amit
2021-12-06 13:45 ` Carel Si
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=20211129035943.GA7092@linux.intel.com \
--to=beibei.si@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.