linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Dave Hansen <dave.hansen@intel.com>
To: Matthew Wilcox <willy@infradead.org>,
	Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Cc: linux-kernel@vger.kernel.org,
	Christoph Hellwig <hch@infradead.org>,
	linux-mm@kvack.org, Andy Lutomirski <luto@kernel.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	"Kirill A. Shutemov" <kirill@shutemov.name>
Subject: Re: Use higher-order pages in vmalloc
Date: Wed, 21 Feb 2018 08:16:22 -0800	[thread overview]
Message-ID: <fff58819-d39d-3a8a-f314-690bcb2f95d7@intel.com> (raw)
In-Reply-To: <20180221154214.GA4167@bombadil.infradead.org>

On 02/21/2018 07:42 AM, Matthew Wilcox wrote:
> On Tue, Jan 23, 2018 at 01:55:32PM +0300, Konstantin Khlebnikov wrote:
>> Virtually mapped stack have two bonuses: it eats order-0 pages and
>> adds guard page at the end. But it slightly slower if system have
>> plenty free high-order pages.
>>
>> This patch adds option to use virtually bapped stack as fallback for
>> atomic allocation of traditional high-order page.
> This prompted me to write a patch I've been meaning to do for a while,
> allocating large pages if they're available to satisfy vmalloc.  I thought
> it would save on touching multiple struct pages, but it turns out that
> the checking code we currently have in the free_pages path requires you
> to have initialised all of the tail pages (maybe we can make that code
> conditional ...)

What the concept here?  If we can use high-order pages for vmalloc() at
the moment, we *should* use them?

One of the coolest things about vmalloc() is that it can do large
allocations without consuming large (high-order) pages, so it has very
few side-effects compared to doing a bunch of order-0 allocations.  This
patch seems to propose removing that cool thing.  Even trying the
high-order allocation could kick off a bunch of reclaim and compaction
that was not there previously.

If you could take this an only _opportunistically_ allocate large pages,
it could be a more universal win.  You could try to make sure that no
compaction or reclaim is done for the large allocation.  Or, maybe you
only try it if there are *only* high-order pages in the allocator that
would have been broken down into order-0 *anyway*.

I'm not sure it's worth it, though.  I don't see a lot of folks
complaining about vmalloc()'s speed or TLB impact.

  parent reply	other threads:[~2018-02-21 16:17 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-01-23 10:55 [PATCH 1/4] vmalloc: add vm_flags argument to internal __vmalloc_node() Konstantin Khlebnikov
2018-01-23 10:55 ` [PATCH 2/4] vmalloc: add __vmalloc_area() Konstantin Khlebnikov
2018-01-23 10:55 ` [PATCH 3/4] kernel/fork: switch vmapped stack callation to __vmalloc_area() Konstantin Khlebnikov
2018-01-23 13:57   ` Konstantin Khlebnikov
2018-02-21  0:16     ` Andrew Morton
2018-02-21  7:23       ` Konstantin Khlebnikov
2018-02-21 16:35         ` Andy Lutomirski
2018-01-23 10:55 ` [PATCH 4/4] kernel/fork: add option to use virtually mapped stacks as fallback Konstantin Khlebnikov
2018-02-21 15:42   ` Use higher-order pages in vmalloc Matthew Wilcox
2018-02-21 16:11     ` Andy Lutomirski
2018-02-21 16:50       ` Matthew Wilcox
2018-02-21 16:16     ` Dave Hansen [this message]
2018-02-21 17:01       ` Matthew Wilcox
2018-02-22  6:59         ` Michal Hocko
2018-02-22 12:22           ` Matthew Wilcox
2018-02-22 13:36             ` Michal Hocko
2018-02-22 19:01               ` Andy Lutomirski
2018-02-22 19:19                 ` Dave Hansen
2018-02-22 19:27                   ` Andy Lutomirski
2018-02-22 19:36                     ` Dave Hansen
2018-02-23 12:13                 ` Michal Hocko
2018-03-01 18:16                   ` Eric Dumazet
2018-02-21 12:24 ` [PATCH 1/4] vmalloc: add vm_flags argument to internal __vmalloc_node() Matthew Wilcox
2018-02-21 12:39   ` Andrey Ryabinin

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=fff58819-d39d-3a8a-f314-690bcb2f95d7@intel.com \
    --to=dave.hansen@intel.com \
    --cc=akpm@linux-foundation.org \
    --cc=hch@infradead.org \
    --cc=khlebnikov@yandex-team.ru \
    --cc=kirill@shutemov.name \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=luto@kernel.org \
    --cc=willy@infradead.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).