Re: [PATCH] thp: reduce usage of huge zero page's atomic counter

From	Andrew Morton <akpm@linux-foundation.org>
Newsgroups	linux.kernel
Subject	Re: [PATCH] thp: reduce usage of huge zero page's atomic counter
Date	2016-08-30 07:00 +0200
Message-ID	<sbJjs-9c-5@gated-at.bofh.it> (permalink)
References	<sbooF-3Ql-21@gated-at.bofh.it> <sbDH4-4VF-9@gated-at.bofh.it> <sbHAZ-7ES-1@gated-at.bofh.it> <sbI41-7Oi-3@gated-at.bofh.it> <sbJ9L-5O-11@gated-at.bofh.it>
Organization	linux.* mail to news gateway

Show all headers | View raw

On Tue, 30 Aug 2016 10:14:25 +0530 Anshuman Khandual <khandual@linux.vnet.ibm.com> wrote:

> On 08/30/2016 09:09 AM, Andrew Morton wrote:
> > On Tue, 30 Aug 2016 11:09:15 +0800 Aaron Lu <aaron.lu@intel.com> wrote:
> > 
> >>>> Case used for test on Haswell EP:
> >>>> usemem -n 72 --readonly -j 0x200000 100G
> >>>> Which spawns 72 processes and each will mmap 100G anonymous space and
> >>>> then do read only access to that space sequentially with a step of 2MB.
> >>>>
> >>>> perf report for base commit:
> >>>>     54.03%  usemem   [kernel.kallsyms]   [k] get_huge_zero_page
> >>>> perf report for this commit:
> >>>>      0.11%  usemem   [kernel.kallsyms]   [k] mm_get_huge_zero_page
> >>>
> >>> Does this mean that overall usemem runtime halved?
> >>
> >> Sorry for the confusion, the above line is extracted from perf report.
> >> It shows the percent of CPU cycles executed in a specific function.
> >>
> >> The above two perf lines are used to show get_huge_zero_page doesn't
> >> consume that much CPU cycles after applying the patch.
> >>
> >>>
> >>> Do we have any numbers for something which is more real-wordly?
> >>
> >> Unfortunately, no real world numbers.
> >>
> >> We think the global atomic counter could be an issue for performance
> >> so I'm trying to solve the problem.
> > 
> > So, umm, we don't actually know if the patch is useful to anyone?
> 
> On a POWER system it improves the CPU consumption of the above mentioned
> function a little bit. Dont think its going to improve actual throughput
> of the workload substantially.
> 
> 0.07%  usemem  [kernel.vmlinux]  [k] mm_get_huge_zero_page
> 
> to
> 
> 0.01%  usemem  [kernel.vmlinux]  [k] mm_get_huge_zero_page

I can't say I'm surprised really.  A huge page is, ahem, huge.  The
computational cost of actually writing stuff into that page will swamp
the cost of the locking to acquire it.

Is the patch really worth the additional complexity?

Thread

[PATCH] thp: reduce usage of huge zero page's atomic counter Aaron Lu <aaron.lu@intel.com> - 2016-08-29 08:40 +0200
  Re: [PATCH] thp: reduce usage of huge zero page's atomic counter Aaron Lu <aaron.lu@intel.com> - 2016-08-29 11:00 +0200
    Re: [PATCH] thp: reduce usage of huge zero page's atomic counter Anshuman Khandual <khandual@linux.vnet.ibm.com> - 2016-08-29 15:50 +0200
      Re: [PATCH] thp: reduce usage of huge zero page's atomic counter Aaron Lu <aaron.lu@intel.com> - 2016-08-29 16:20 +0200
  Re: [PATCH] thp: reduce usage of huge zero page's atomic counter Anshuman Khandual <khandual@linux.vnet.ibm.com> - 2016-08-29 11:00 +0200
  Re: [PATCH] thp: reduce usage of huge zero page's atomic counter Andrew Morton <akpm@linux-foundation.org> - 2016-08-30 01:00 +0200
    Re: [PATCH] thp: reduce usage of huge zero page's atomic counter Aaron Lu <aaron.lu@intel.com> - 2016-08-30 05:10 +0200
      Re: [PATCH] thp: reduce usage of huge zero page's atomic counter Andrew Morton <akpm@linux-foundation.org> - 2016-08-30 05:40 +0200
        Re: [PATCH] thp: reduce usage of huge zero page's atomic counter Anshuman Khandual <khandual@linux.vnet.ibm.com> - 2016-08-30 06:50 +0200
          Re: [PATCH] thp: reduce usage of huge zero page's atomic counter Andrew Morton <akpm@linux-foundation.org> - 2016-08-30 07:00 +0200
          Re: [PATCH] thp: reduce usage of huge zero page's atomic counter Aaron Lu <aaron.lu@intel.com> - 2016-08-30 08:00 +0200
            Re: [PATCH] thp: reduce usage of huge zero page's atomic counter Anshuman Khandual <khandual@linux.vnet.ibm.com> - 2016-08-30 08:50 +0200
        Re: [PATCH] thp: reduce usage of huge zero page's atomic counter Aaron Lu <aaron.lu@intel.com> - 2016-08-30 08:00 +0200
    Re: [PATCH] thp: reduce usage of huge zero page's atomic counter Anshuman Khandual <khandual@linux.vnet.ibm.com> - 2016-08-30 07:20 +0200
      Re: [PATCH] thp: reduce usage of huge zero page's atomic counter Andrew Morton <akpm@linux-foundation.org> - 2016-08-30 07:20 +0200
  Re: [PATCH] thp: reduce usage of huge zero page's atomic counter Sergey Senozhatsky <sergey.senozhatsky@gmail.com> - 2016-08-30 18:10 +0200
    [PATCH v2] thp: reduce usage of huge zero page's atomic counter Aaron Lu <aaron.lu@intel.com> - 2016-08-31 04:10 +0200

csiph-web