From: Minchan Kim <minchan.kim@gmail.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-mm <linux-mm@kvack.org>,
LKML <linux-kernel@vger.kernel.org>,
Ben Gamari <bgamari.foss@gmail.com>,
Minchan Kim <minchan.kim@gmail.com>
Subject: [PATCH v3 0/3] f/madivse(DONTNEED) support
Date: Tue, 30 Nov 2010 00:23:18 +0900 [thread overview]
Message-ID: <cover.1291043273.git.minchan.kim@gmail.com> (raw)
Recently there is a report about working set page eviction due to rsync
workload. application programmers want to use fadvise but it's not easy.
You could see detailed description on [1/3].
- [1/3] is to move invalidated page which is dirty/writeback on active list
into inactive list's head.
- [2/3] is for moving invalidated page into inactive list's tail when the
page's writeout is completed.
- [3/3] is to not calling mark_page_accessed in case of madvise(DONTNEED).
Minchan Kim (3):
deactivate invalidated pages
Reclaim invalidated page ASAP
Prevent activation of page in madvise_dontneed
include/linux/mm.h | 4 +-
include/linux/swap.h | 1 +
mm/madvise.c | 4 +-
mm/memory.c | 38 +++++++++++-------
mm/mmap.c | 4 +-
mm/page-writeback.c | 12 +++++-
mm/swap.c | 102 ++++++++++++++++++++++++++++++++++++++++++++++++++
mm/truncate.c | 16 ++++++--
8 files changed, 155 insertions(+), 26 deletions(-)
WARNING: multiple messages have this Message-ID (diff)
From: Minchan Kim <minchan.kim@gmail.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-mm <linux-mm@kvack.org>,
LKML <linux-kernel@vger.kernel.org>,
Ben Gamari <bgamari.foss@gmail.com>,
Minchan Kim <minchan.kim@gmail.com>
Subject: [PATCH v3 0/3] f/madivse(DONTNEED) support
Date: Tue, 30 Nov 2010 00:23:18 +0900 [thread overview]
Message-ID: <cover.1291043273.git.minchan.kim@gmail.com> (raw)
Recently there is a report about working set page eviction due to rsync
workload. application programmers want to use fadvise but it's not easy.
You could see detailed description on [1/3].
- [1/3] is to move invalidated page which is dirty/writeback on active list
into inactive list's head.
- [2/3] is for moving invalidated page into inactive list's tail when the
page's writeout is completed.
- [3/3] is to not calling mark_page_accessed in case of madvise(DONTNEED).
Minchan Kim (3):
deactivate invalidated pages
Reclaim invalidated page ASAP
Prevent activation of page in madvise_dontneed
include/linux/mm.h | 4 +-
include/linux/swap.h | 1 +
mm/madvise.c | 4 +-
mm/memory.c | 38 +++++++++++-------
mm/mmap.c | 4 +-
mm/page-writeback.c | 12 +++++-
mm/swap.c | 102 ++++++++++++++++++++++++++++++++++++++++++++++++++
mm/truncate.c | 16 ++++++--
8 files changed, 155 insertions(+), 26 deletions(-)
--
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/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next reply other threads:[~2010-11-29 15:23 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-11-29 15:23 Minchan Kim [this message]
2010-11-29 15:23 ` [PATCH v3 0/3] f/madivse(DONTNEED) support Minchan Kim
2010-11-29 15:23 ` [PATCH v3 1/3] deactivate invalidated pages Minchan Kim
2010-11-29 15:23 ` Minchan Kim
2010-11-30 1:01 ` KOSAKI Motohiro
2010-11-30 1:01 ` KOSAKI Motohiro
2010-11-30 5:22 ` Johannes Weiner
2010-11-30 5:22 ` Johannes Weiner
2010-11-30 6:18 ` Minchan Kim
2010-11-30 6:18 ` Minchan Kim
2010-11-29 15:23 ` [PATCH 2/3] Reclaim invalidated page ASAP Minchan Kim
2010-11-29 15:23 ` Minchan Kim
2010-11-29 16:57 ` Mel Gorman
2010-11-29 16:57 ` Mel Gorman
2010-11-29 22:41 ` Minchan Kim
2010-11-29 22:41 ` Minchan Kim
2010-11-30 9:16 ` Mel Gorman
2010-11-30 9:16 ` Mel Gorman
2010-11-30 14:04 ` Minchan Kim
2010-11-30 14:04 ` Minchan Kim
2010-11-30 11:20 ` Johannes Weiner
2010-11-30 11:20 ` Johannes Weiner
2010-11-30 14:03 ` Minchan Kim
2010-11-30 14:03 ` Minchan Kim
2010-11-30 1:10 ` KOSAKI Motohiro
2010-11-30 1:10 ` KOSAKI Motohiro
2010-11-30 9:18 ` Mel Gorman
2010-11-30 9:18 ` Mel Gorman
2010-11-30 14:01 ` Minchan Kim
2010-11-30 14:01 ` Minchan Kim
2010-11-30 14:11 ` Ben Gamari
2010-11-30 14:11 ` Ben Gamari
2010-11-29 15:23 ` [PATCH v3 3/3] Prevent activation of page in madvise_dontneed Minchan Kim
2010-11-29 15:23 ` Minchan Kim
2010-11-30 1:08 ` KOSAKI Motohiro
2010-11-30 1:08 ` KOSAKI Motohiro
2010-11-30 11:35 ` Johannes Weiner
2010-11-30 11:35 ` Johannes Weiner
2010-12-01 0:50 ` Minchan Kim
2010-12-01 0:50 ` Minchan Kim
2010-11-30 18:34 ` Hugh Dickins
2010-11-30 18:34 ` Hugh Dickins
2010-12-01 0:49 ` Minchan Kim
2010-12-01 0:49 ` Minchan Kim
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=cover.1291043273.git.minchan.kim@gmail.com \
--to=minchan.kim@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=bgamari.foss@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.