From: Rik van Riel <riel@redhat.com>
To: Ying Han <yinghan@google.com>
Cc: linux-mm@kvack.org, Hugh Dickins <hughd@google.com>,
Minchan Kim <minchan.kim@gmail.com>,
KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>,
Andrew Morton <akpm@linux-foundation.org>
Subject: Re: [PATCH] mm: don't flush TLB when propagate PTE access bit to struct page.
Date: Thu, 28 Oct 2010 07:53:41 -0400 [thread overview]
Message-ID: <4CC96445.9040408@redhat.com> (raw)
In-Reply-To: <AANLkTim9ENR7dFvkNW_h2-Bfg6GHCbOgr6Bd=W34z7s0@mail.gmail.com>
On 10/27/2010 04:19 PM, Ying Han wrote:
>
>
> On Wed, Oct 27, 2010 at 11:05 AM, Rik van Riel <riel@redhat.com
> <mailto:riel@redhat.com>> wrote:
>
> On 10/27/2010 01:21 PM, Ying Han wrote:
>
> kswapd's use case of hardware PTE accessed bit is to approximate
> page LRU. The
> ActiveLRU demotion to InactiveLRU are not base on accessed bit,
> while it is only
> used to promote when a page is on inactive LRU list. All of the
> state transitions
> are triggered by memory pressure and thus has weak relationship
> with respect to
> time. In addition, hardware already transparently flush tlb
> whenever CPU context
> switch processes and given limited hardware TLB resource, the
> time period in
> which a page is accessed but not yet propagated to struct page
> is very small
> in practice. With the nature of approximation, kernel really
> don't need to flush TLB
> for changing PTE's access bit. This commit removes the flush
> operation from it.
>
> Signed-off-by: Ying Han<yinghan@google.com
> <mailto:yinghan@google.com>>
> Singed-off-by: Ken Chen<kenchen@google.com
> <mailto:kenchen@google.com>>
>
>
> The reasoning behind the patch makes sense.
>
> However, have you measured any improvements in run time with
> this patch? The VM is already tweaked to minimize the number
> of pages that get aged, so it would be interesting to know
> where you saw issues.
>
>
> Rik, the workload we were running are some MapReduce jobs.
Well, what kind of performance improvement did you measure?
--
All rights reversed
--
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>
prev parent reply other threads:[~2010-10-28 11:53 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-10-27 17:21 [PATCH] mm: don't flush TLB when propagate PTE access bit to struct page Ying Han
2010-10-27 18:05 ` Rik van Riel
2010-10-27 18:22 ` Nick Piggin
2010-10-27 18:37 ` Nick Piggin
2010-10-27 19:13 ` Hugh Dickins
2010-10-27 20:35 ` Ying Han
2010-10-28 0:11 ` KAMEZAWA Hiroyuki
2010-10-29 1:30 ` Ken Chen
2010-10-29 2:45 ` KAMEZAWA Hiroyuki
2010-10-29 3:43 ` Rik van Riel
2010-10-29 4:27 ` Minchan Kim
2010-10-29 12:31 ` Rik van Riel
2010-10-29 13:03 ` Minchan Kim
2010-10-29 13:15 ` Rik van Riel
2010-10-30 0:20 ` Minchan Kim
2010-10-27 20:19 ` Ying Han
2010-10-28 11:53 ` Rik van Riel [this message]
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=4CC96445.9040408@redhat.com \
--to=riel@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=hughd@google.com \
--cc=kamezawa.hiroyu@jp.fujitsu.com \
--cc=linux-mm@kvack.org \
--cc=minchan.kim@gmail.com \
--cc=yinghan@google.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).