linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Shaohua Li <shli@kernel.org>
To: Daniel Micay <danielmicay@gmail.com>
Cc: Andy Lutomirski <luto@amacapital.net>,
	Minchan Kim <minchan@kernel.org>, Hugh Dickins <hughd@google.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Michael Kerrisk <mtk.manpages@gmail.com>,
	Michal Hocko <mhocko@suse.cz>,
	"linux-mm@kvack.org" <linux-mm@kvack.org>,
	KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>,
	"Kirill A. Shutemov" <kirill@shutemov.name>,
	Rik van Riel <riel@redhat.com>,
	Johannes Weiner <hannes@cmpxchg.org>,
	Linux API <linux-api@vger.kernel.org>, Jason Evans <je@fb.com>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	yalin wang <yalin.wang2010@gmail.com>,
	Mel Gorman <mgorman@suse.de>
Subject: Re: [PATCH v2 01/13] mm: support madvise(MADV_FREE)
Date: Thu, 5 Nov 2015 10:17:26 -0800	[thread overview]
Message-ID: <20151105181726.GA63566@kernel.org> (raw)
In-Reply-To: <563A813B.9080903@gmail.com>

On Wed, Nov 04, 2015 at 05:05:47PM -0500, Daniel Micay wrote:
> > With enough pages at once, though, munmap would be fine, too.
> 
> That implies lots of page faults and zeroing though. The zeroing alone
> is a major performance issue.
> 
> There are separate issues with munmap since it ends up resulting in a
> lot more virtual memory fragmentation. It would help if the kernel used
> first-best-fit for mmap instead of the current naive algorithm (bonus:
> O(log n) worst-case, not O(n)). Since allocators like jemalloc and
> PartitionAlloc want 2M aligned spans, mixing them with other allocators
> can also accelerate the VM fragmentation caused by the dumb mmap
> algorithm (i.e. they make a 2M aligned mapping, some other mmap user
> does 4k, now there's a nearly 2M gap when the next 2M region is made and
> the kernel keeps going rather than reusing it). Anyway, that's a totally
> separate issue from this. Just felt like complaining :).
> 
> > Maybe what's really needed is a MADV_FREE variant that takes an iovec.
> > On an all-cores multithreaded mm, the TLB shootdown broadcast takes
> > thousands of cycles on each core more or less regardless of how much
> > of the TLB gets zapped.
> 
> That would work very well. The allocator ends up having a sequence of
> dirty spans that it needs to purge in one go. As long as purging is
> fairly spread out, the cost of a single TLB shootdown isn't that bad. It
> is extremely bad if it needs to do it over and over to purge a bunch of
> ranges, which can happen if the memory has ended up being very, very
> fragmentated despite the efforts to compact it (depends on what the
> application ends up doing).

I posted a patch doing exactly iovec madvise. Doesn't support MADV_FREE yet
though, but should be easy to do it.

http://marc.info/?l=linux-mm&m=144615663522661&w=2

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  reply	other threads:[~2015-11-05 18:17 UTC|newest]

Thread overview: 42+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-11-04  1:25 [PATCH v2 00/13] MADV_FREE support Minchan Kim
2015-11-04  1:25 ` [PATCH v2 01/13] mm: support madvise(MADV_FREE) Minchan Kim
2015-11-04  2:16   ` Sergey Senozhatsky
2015-11-04 23:39     ` Minchan Kim
2015-11-05  3:41       ` Sergey Senozhatsky
2015-11-04  2:29   ` Sergey Senozhatsky
2015-11-04 23:40     ` Minchan Kim
2015-11-04  3:41   ` Andy Lutomirski
2015-11-04  5:50     ` Daniel Micay
2015-11-04  5:53       ` Daniel Micay
2015-11-04  6:04         ` Daniel Micay
2015-11-04 18:23       ` Andy Lutomirski
2015-11-04 22:05         ` Daniel Micay
2015-11-05 18:17           ` Shaohua Li [this message]
2015-11-05 20:13             ` Daniel Micay
2015-11-05 20:14               ` Daniel Micay
2015-11-05  0:13     ` Minchan Kim
2015-11-05  0:42       ` Andy Lutomirski
2015-11-05  0:56         ` Minchan Kim
2015-11-05  1:29           ` Andy Lutomirski
2015-11-05  1:48             ` Minchan Kim
2015-11-04 20:00   ` Shaohua Li
2015-11-04 21:16     ` Daniel Micay
2015-11-04 21:29       ` Daniel Micay
2015-11-04 21:43     ` Andy Lutomirski
2015-11-05  1:33     ` Minchan Kim
2015-11-05  1:37       ` Minchan Kim
2015-12-01 22:30     ` John Stultz
2015-11-04  1:25 ` [PATCH v2 02/13] mm: define MADV_FREE for some arches Minchan Kim
2015-11-04  1:25 ` [PATCH v2 03/13] arch: uapi: asm: mman.h: Let MADV_FREE have same value for all architectures Minchan Kim
2015-11-04  1:25 ` [PATCH v2 04/13] mm: free swp_entry in madvise_free Minchan Kim
2015-11-04  1:25 ` [PATCH v2 05/13] mm: move lazily freed pages to inactive list Minchan Kim
2015-11-04  1:26 ` [PATCH v2 06/13] mm: clear PG_dirty to mark page freeable Minchan Kim
2015-11-04  1:26 ` [PATCH v2 07/13] mm: mark stable page dirty in KSM Minchan Kim
2015-11-04  1:26 ` [PATCH v2 08/13] x86: add pmd_[dirty|mkclean] for THP Minchan Kim
2015-11-04  1:26 ` [PATCH v2 09/13] sparc: " Minchan Kim
2015-11-04  1:26 ` [PATCH v2 10/13] powerpc: " Minchan Kim
2015-11-04  1:26 ` [PATCH v2 11/13] arm: add pmd_mkclean " Minchan Kim
2015-11-04  1:26 ` [PATCH v2 12/13] arm64: " Minchan Kim
2015-11-04  1:26 ` [PATCH v2 13/13] mm: don't split THP page when syscall is called Minchan Kim
2015-12-05 11:10 ` [PATCH v2 00/13] MADV_FREE support Pavel Machek
2015-12-05 15:51   ` Daniel Micay

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=20151105181726.GA63566@kernel.org \
    --to=shli@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=danielmicay@gmail.com \
    --cc=hannes@cmpxchg.org \
    --cc=hughd@google.com \
    --cc=je@fb.com \
    --cc=kirill@shutemov.name \
    --cc=kosaki.motohiro@jp.fujitsu.com \
    --cc=linux-api@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=luto@amacapital.net \
    --cc=mgorman@suse.de \
    --cc=mhocko@suse.cz \
    --cc=minchan@kernel.org \
    --cc=mtk.manpages@gmail.com \
    --cc=riel@redhat.com \
    --cc=yalin.wang2010@gmail.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 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).