Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > linux.kernel > #1326069

Re: [PATCH 4/4] thp: rewrite freeze_page()/unfreeze_page() with generic rmap walkers

From Andrew Morton <akpm@linux-foundation.org>
Newsgroups linux.kernel
Subject Re: [PATCH 4/4] thp: rewrite freeze_page()/unfreeze_page() with generic rmap walkers
Date 2016-02-03 23:50 +0100
Message-ID <qYepl-8ec-47@gated-at.bofh.it> (permalink)
References <qY7nP-3C1-3@gated-at.bofh.it> <qY7nR-3C1-29@gated-at.bofh.it> <qY7QS-3Om-17@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw


On Wed, 3 Feb 2016 07:42:01 -0800 Dave Hansen <dave.hansen@intel.com> wrote:

> On 02/03/2016 07:14 AM, Kirill A. Shutemov wrote:
> > But the new variant is somewhat slower. Current helpers iterates over
> > VMAs the compound page is mapped to, and then over ptes within this VMA.
> > New helpers iterates over small page, then over VMA the small page
> > mapped to, and only then find relevant pte.
> 
> The code simplification here is really attractive.  Can you quantify
> what the slowdown is?  Is it noticeable, or would it be in the noise
> during all the other stuff that happens under memory pressure?

yup.  And the "more testing is required" is a bit worrisome.  Is this
code really ready for getting pounded upon in -next?

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


Thread

[PATCH 0/4] thp: simplify freeze_page() and unfreeze_page() "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> - 2016-02-03 16:20 +0100
  [PATCH 1/4] rmap: introduce rmap_walk_locked() "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> - 2016-02-03 16:20 +0100
    Re: [PATCH 1/4] rmap: introduce rmap_walk_locked() Andrew Morton <akpm@linux-foundation.org> - 2016-02-03 23:50 +0100
      Re: [PATCH 1/4] rmap: introduce rmap_walk_locked() "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> - 2016-02-03 23:50 +0100
        Re: [PATCH 1/4] rmap: introduce rmap_walk_locked() Andrew Morton <akpm@linux-foundation.org> - 2016-02-04 00:00 +0100
          Re: [PATCH 1/4] rmap: introduce rmap_walk_locked() "Kirill A. Shutemov" <kirill@shutemov.name> - 2016-02-04 15:40 +0100
  [PATCH 3/4] mm: make remove_migration_ptes() beyond mm/migration.c "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> - 2016-02-03 16:20 +0100
  [PATCH 4/4] thp: rewrite freeze_page()/unfreeze_page() with generic rmap walkers "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> - 2016-02-03 16:20 +0100
    Re: [PATCH 4/4] thp: rewrite freeze_page()/unfreeze_page() with  generic rmap walkers Dave Hansen <dave.hansen@intel.com> - 2016-02-03 16:50 +0100
      Re: [PATCH 4/4] thp: rewrite freeze_page()/unfreeze_page() with  generic rmap walkers Andrew Morton <akpm@linux-foundation.org> - 2016-02-03 23:50 +0100
        Re: [PATCH 4/4] thp: rewrite freeze_page()/unfreeze_page() with  generic rmap walkers "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> - 2016-02-04 00:00 +0100
      Re: [PATCH 4/4] thp: rewrite freeze_page()/unfreeze_page() with  generic rmap walkers "Kirill A. Shutemov" <kirill@shutemov.name> - 2016-02-04 15:40 +0100
      Re: [PATCH 4/4] thp: rewrite freeze_page()/unfreeze_page() with  generic rmap walkers "Kirill A. Shutemov" <kirill@shutemov.name> - 2016-02-05 01:00 +0100

csiph-web