From: Minchan Kim <minchan.kim@gmail.com>
To: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: LKML <linux-kernel@vger.kernel.org>,
linux-mm <linux-mm@kvack.org>,
Andrew Morton <akpm@linux-foundation.org>,
Johannes Weiner <hannes@cmpxchg.org>, Mel Gorman <mel@csn.ul.ie>,
Wu Fengguang <fengguang.wu@intel.com>,
Rik van Riel <riel@redhat.com>
Subject: Re: [PATCH 2/7] vmscan: synchronous lumpy reclaim don't call congestion_wait()
Date: Thu, 5 Aug 2010 22:55:04 +0900 [thread overview]
Message-ID: <20100805135504.GA2985@barrios-desktop> (raw)
In-Reply-To: <20100805151229.31BD.A69D9226@jp.fujitsu.com>
On Thu, Aug 05, 2010 at 03:13:03PM +0900, KOSAKI Motohiro wrote:
> congestion_wait() mean "waiting quueue congestion is cleared".
> That said, if the system have plenty dirty pages and flusher thread push
> new request to IO queue conteniously, IO queue are not cleared
> congestion status for long time. thus, congestion_wait(HZ/10) become
> almostly equivalent schedule_timeout(HZ/10).
>
> However, synchronous lumpy reclaim donesn't need this
> congestion_wait() at all. shrink_page_list(PAGEOUT_IO_SYNC) are
> using wait_on_page_writeback() and it provide sufficient waiting.
>
> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
--
Kind regards,
Minchan Kim
WARNING: multiple messages have this Message-ID (diff)
From: Minchan Kim <minchan.kim@gmail.com>
To: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: LKML <linux-kernel@vger.kernel.org>,
linux-mm <linux-mm@kvack.org>,
Andrew Morton <akpm@linux-foundation.org>,
Johannes Weiner <hannes@cmpxchg.org>, Mel Gorman <mel@csn.ul.ie>,
Wu Fengguang <fengguang.wu@intel.com>,
Rik van Riel <riel@redhat.com>
Subject: Re: [PATCH 2/7] vmscan: synchronous lumpy reclaim don't call congestion_wait()
Date: Thu, 5 Aug 2010 22:55:04 +0900 [thread overview]
Message-ID: <20100805135504.GA2985@barrios-desktop> (raw)
In-Reply-To: <20100805151229.31BD.A69D9226@jp.fujitsu.com>
On Thu, Aug 05, 2010 at 03:13:03PM +0900, KOSAKI Motohiro wrote:
> congestion_wait() mean "waiting quueue congestion is cleared".
> That said, if the system have plenty dirty pages and flusher thread push
> new request to IO queue conteniously, IO queue are not cleared
> congestion status for long time. thus, congestion_wait(HZ/10) become
> almostly equivalent schedule_timeout(HZ/10).
>
> However, synchronous lumpy reclaim donesn't need this
> congestion_wait() at all. shrink_page_list(PAGEOUT_IO_SYNC) are
> using wait_on_page_writeback() and it provide sufficient waiting.
>
> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
--
Kind regards,
Minchan Kim
--
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>
next prev parent reply other threads:[~2010-08-05 13:55 UTC|newest]
Thread overview: 66+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-08-05 6:11 [RFC][PATCH 0/7] low latency synchrounous lumpy reclaim KOSAKI Motohiro
2010-08-05 6:11 ` KOSAKI Motohiro
2010-08-05 6:12 ` [PATCH 1/7] vmscan: raise the bar to PAGEOUT_IO_SYNC stalls KOSAKI Motohiro
2010-08-05 6:12 ` KOSAKI Motohiro
2010-08-05 15:02 ` Mel Gorman
2010-08-05 15:02 ` Mel Gorman
2010-08-08 6:42 ` KOSAKI Motohiro
2010-08-08 6:42 ` KOSAKI Motohiro
2010-08-05 15:19 ` Rik van Riel
2010-08-05 15:19 ` Rik van Riel
2010-08-05 6:13 ` [PATCH 2/7] vmscan: synchronous lumpy reclaim don't call congestion_wait() KOSAKI Motohiro
2010-08-05 6:13 ` KOSAKI Motohiro
2010-08-05 13:55 ` Minchan Kim [this message]
2010-08-05 13:55 ` Minchan Kim
2010-08-05 15:05 ` Rik van Riel
2010-08-05 15:05 ` Rik van Riel
2010-08-05 15:06 ` Mel Gorman
2010-08-05 15:06 ` Mel Gorman
2010-08-05 6:13 ` [PATCH 3/7] vmscan: synchrounous lumpy reclaim use lock_page() instead trylock_page() KOSAKI Motohiro
2010-08-05 6:13 ` KOSAKI Motohiro
2010-08-05 14:17 ` Minchan Kim
2010-08-05 14:17 ` Minchan Kim
2010-08-06 0:52 ` Minchan Kim
2010-08-06 0:52 ` Minchan Kim
2010-08-05 15:12 ` Mel Gorman
2010-08-05 15:12 ` Mel Gorman
2010-08-05 15:26 ` Rik van Riel
2010-08-05 15:26 ` Rik van Riel
2010-08-05 6:14 ` [PATCH 4/7] vmscan: narrowing synchrounous lumply reclaim condition KOSAKI Motohiro
2010-08-05 6:14 ` KOSAKI Motohiro
2010-08-05 14:59 ` Minchan Kim
2010-08-05 14:59 ` Minchan Kim
2010-10-27 16:41 ` Andrea Arcangeli
2010-10-27 16:41 ` Andrea Arcangeli
2010-10-27 17:16 ` Mel Gorman
2010-10-27 17:16 ` Mel Gorman
2010-10-27 18:03 ` Andrea Arcangeli
2010-10-27 18:03 ` Andrea Arcangeli
2010-10-28 8:00 ` KOSAKI Motohiro
2010-10-28 8:00 ` KOSAKI Motohiro
2010-10-28 15:12 ` Andrea Arcangeli
2010-10-28 15:12 ` Andrea Arcangeli
2010-10-29 2:23 ` KOSAKI Motohiro
2010-10-29 2:23 ` KOSAKI Motohiro
2010-10-28 10:20 ` Mel Gorman
2010-10-28 10:20 ` Mel Gorman
2010-11-02 2:04 ` Wu Fengguang
2010-11-02 2:04 ` Wu Fengguang
2010-10-28 2:31 ` Ed Tomlinson
2010-10-28 2:31 ` Ed Tomlinson
2010-10-28 15:22 ` Andrea Arcangeli
2010-10-28 15:22 ` Andrea Arcangeli
2010-08-05 6:14 ` [PATCH 5/7] vmscan: kill dead code in shrink_inactive_list() KOSAKI Motohiro
2010-08-05 6:14 ` KOSAKI Motohiro
2010-08-05 15:08 ` Minchan Kim
2010-08-05 15:08 ` Minchan Kim
2010-08-05 15:14 ` Mel Gorman
2010-08-05 15:14 ` Mel Gorman
2010-08-05 6:15 ` [PATCH 6/7] vmscan: remove PF_SWAPWRITE from __zone_reclaim() KOSAKI Motohiro
2010-08-05 6:15 ` KOSAKI Motohiro
2010-08-05 6:16 ` [PATCH 7/7] vmscan: isolated_lru_pages() stop neighbor search if neighbor can't be isolated KOSAKI Motohiro
2010-08-05 6:16 ` KOSAKI Motohiro
2010-08-05 15:25 ` Mel Gorman
2010-08-05 15:25 ` Mel Gorman
2010-08-05 15:40 ` Minchan Kim
2010-08-05 15:40 ` 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=20100805135504.GA2985@barrios-desktop \
--to=minchan.kim@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=fengguang.wu@intel.com \
--cc=hannes@cmpxchg.org \
--cc=kosaki.motohiro@jp.fujitsu.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mel@csn.ul.ie \
--cc=riel@redhat.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 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.