From: Mel Gorman <mgorman@suse.de>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>, Jan Kara <jack@suse.cz>,
LKML <linux-kernel@vger.kernel.org>, XFS <xfs@oss.sgi.com>,
Christoph Hellwig <hch@infradead.org>,
Linux-MM <linux-mm@kvack.org>,
Minchan Kim <minchan.kim@gmail.com>,
Wu Fengguang <fengguang.wu@intel.com>,
Johannes Weiner <jweiner@redhat.com>
Subject: Re: [PATCH 8/8] mm: vmscan: Do not writeback filesystem pages from kswapd
Date: Fri, 22 Jul 2011 14:31:38 +0100 [thread overview]
Message-ID: <20110722133138.GY5349@suse.de> (raw)
In-Reply-To: <1311339432.27400.36.camel@twins>
On Fri, Jul 22, 2011 at 02:57:12PM +0200, Peter Zijlstra wrote:
> On Thu, 2011-07-21 at 17:28 +0100, Mel Gorman wrote:
> > Assuming that flusher threads will always write back dirty pages promptly
> > then it is always faster for reclaimers to wait for flushers. This patch
> > prevents kswapd writing back any filesystem pages.
>
> That is a somewhat sort changelog for such a big assumption ;-)
>
That is an understatement but the impact of the patch is discussed in
detail in the leader. On NUMA, this patch has a negative impact so
I put no effort into the changelog. The patch is part of the series
because it was specifically asked for.
> I think it can use a few extra words to explain the need to clean pages
> from @zone vs writeback picks whatever fits best on disk and how that
> works out wrt the assumption.
>
At the time of writing the changelog, I knew that flushers were
not finding pages from the correct zones quickly enough in the NUMA
usecase. The changelog documents the assumptions testing shows them to
be false.
> What requirements does this place on writeback and how does it meet
> them.
It places a requirement on writeback to prioritise pages from zones
under memory pressure. It doesn't meet them. I mention in the leader
that I think patch 8 should be dropped which is why the changelog
sucks.
--
Mel Gorman
SUSE Labs
_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs
WARNING: multiple messages have this Message-ID (diff)
From: Mel Gorman <mgorman@suse.de>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Linux-MM <linux-mm@kvack.org>,
LKML <linux-kernel@vger.kernel.org>, XFS <xfs@oss.sgi.com>,
Dave Chinner <david@fromorbit.com>,
Christoph Hellwig <hch@infradead.org>,
Johannes Weiner <jweiner@redhat.com>,
Wu Fengguang <fengguang.wu@intel.com>, Jan Kara <jack@suse.cz>,
Rik van Riel <riel@redhat.com>,
Minchan Kim <minchan.kim@gmail.com>
Subject: Re: [PATCH 8/8] mm: vmscan: Do not writeback filesystem pages from kswapd
Date: Fri, 22 Jul 2011 14:31:38 +0100 [thread overview]
Message-ID: <20110722133138.GY5349@suse.de> (raw)
In-Reply-To: <1311339432.27400.36.camel@twins>
On Fri, Jul 22, 2011 at 02:57:12PM +0200, Peter Zijlstra wrote:
> On Thu, 2011-07-21 at 17:28 +0100, Mel Gorman wrote:
> > Assuming that flusher threads will always write back dirty pages promptly
> > then it is always faster for reclaimers to wait for flushers. This patch
> > prevents kswapd writing back any filesystem pages.
>
> That is a somewhat sort changelog for such a big assumption ;-)
>
That is an understatement but the impact of the patch is discussed in
detail in the leader. On NUMA, this patch has a negative impact so
I put no effort into the changelog. The patch is part of the series
because it was specifically asked for.
> I think it can use a few extra words to explain the need to clean pages
> from @zone vs writeback picks whatever fits best on disk and how that
> works out wrt the assumption.
>
At the time of writing the changelog, I knew that flushers were
not finding pages from the correct zones quickly enough in the NUMA
usecase. The changelog documents the assumptions testing shows them to
be false.
> What requirements does this place on writeback and how does it meet
> them.
It places a requirement on writeback to prioritise pages from zones
under memory pressure. It doesn't meet them. I mention in the leader
that I think patch 8 should be dropped which is why the changelog
sucks.
--
Mel Gorman
SUSE Labs
WARNING: multiple messages have this Message-ID (diff)
From: Mel Gorman <mgorman@suse.de>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Linux-MM <linux-mm@kvack.org>,
LKML <linux-kernel@vger.kernel.org>, XFS <xfs@oss.sgi.com>,
Dave Chinner <david@fromorbit.com>,
Christoph Hellwig <hch@infradead.org>,
Johannes Weiner <jweiner@redhat.com>,
Wu Fengguang <fengguang.wu@intel.com>, Jan Kara <jack@suse.cz>,
Rik van Riel <riel@redhat.com>,
Minchan Kim <minchan.kim@gmail.com>
Subject: Re: [PATCH 8/8] mm: vmscan: Do not writeback filesystem pages from kswapd
Date: Fri, 22 Jul 2011 14:31:38 +0100 [thread overview]
Message-ID: <20110722133138.GY5349@suse.de> (raw)
In-Reply-To: <1311339432.27400.36.camel@twins>
On Fri, Jul 22, 2011 at 02:57:12PM +0200, Peter Zijlstra wrote:
> On Thu, 2011-07-21 at 17:28 +0100, Mel Gorman wrote:
> > Assuming that flusher threads will always write back dirty pages promptly
> > then it is always faster for reclaimers to wait for flushers. This patch
> > prevents kswapd writing back any filesystem pages.
>
> That is a somewhat sort changelog for such a big assumption ;-)
>
That is an understatement but the impact of the patch is discussed in
detail in the leader. On NUMA, this patch has a negative impact so
I put no effort into the changelog. The patch is part of the series
because it was specifically asked for.
> I think it can use a few extra words to explain the need to clean pages
> from @zone vs writeback picks whatever fits best on disk and how that
> works out wrt the assumption.
>
At the time of writing the changelog, I knew that flushers were
not finding pages from the correct zones quickly enough in the NUMA
usecase. The changelog documents the assumptions testing shows them to
be false.
> What requirements does this place on writeback and how does it meet
> them.
It places a requirement on writeback to prioritise pages from zones
under memory pressure. It doesn't meet them. I mention in the leader
that I think patch 8 should be dropped which is why the changelog
sucks.
--
Mel Gorman
SUSE Labs
--
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 internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2011-07-22 13:31 UTC|newest]
Thread overview: 129+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-07-21 16:28 [RFC PATCH 0/8] Reduce filesystem writeback from page reclaim v2 Mel Gorman
2011-07-21 16:28 ` Mel Gorman
2011-07-21 16:28 ` Mel Gorman
2011-07-21 16:28 ` [PATCH 1/8] mm: vmscan: Do not writeback filesystem pages in direct reclaim Mel Gorman
2011-07-21 16:28 ` Mel Gorman
2011-07-21 16:28 ` Mel Gorman
2011-07-31 15:06 ` Minchan Kim
2011-07-31 15:06 ` Minchan Kim
2011-07-31 15:06 ` Minchan Kim
2011-08-02 11:21 ` Mel Gorman
2011-08-02 11:21 ` Mel Gorman
2011-08-02 11:21 ` Mel Gorman
2011-07-21 16:28 ` [PATCH 2/8] xfs: Warn if direct reclaim tries to writeback pages Mel Gorman
2011-07-21 16:28 ` Mel Gorman
2011-07-21 16:28 ` Mel Gorman
2011-07-24 11:32 ` Christoph Hellwig
2011-07-24 11:32 ` Christoph Hellwig
2011-07-24 11:32 ` Christoph Hellwig
2011-07-25 8:19 ` Mel Gorman
2011-07-25 8:19 ` Mel Gorman
2011-07-25 8:19 ` Mel Gorman
2011-07-21 16:28 ` [PATCH 3/8] ext4: " Mel Gorman
2011-07-21 16:28 ` Mel Gorman
2011-07-21 16:28 ` Mel Gorman
2011-08-03 10:58 ` Johannes Weiner
2011-08-03 10:58 ` Johannes Weiner
2011-08-03 10:58 ` Johannes Weiner
2011-08-03 11:06 ` Johannes Weiner
2011-08-03 11:06 ` Johannes Weiner
2011-08-03 11:06 ` Johannes Weiner
2011-08-03 13:44 ` Mel Gorman
2011-08-03 13:44 ` Mel Gorman
2011-08-03 13:44 ` Mel Gorman
2011-08-03 14:00 ` Johannes Weiner
2011-08-03 14:00 ` Johannes Weiner
2011-08-03 14:00 ` Johannes Weiner
2011-08-03 14:18 ` Christoph Hellwig
2011-08-03 14:18 ` Christoph Hellwig
2011-08-03 14:18 ` Christoph Hellwig
2011-08-03 14:35 ` Mel Gorman
2011-08-03 14:35 ` Mel Gorman
2011-08-03 14:35 ` Mel Gorman
2011-07-21 16:28 ` [PATCH 4/8] btrfs: " Mel Gorman
2011-07-21 16:28 ` Mel Gorman
2011-07-21 16:28 ` Mel Gorman
2011-08-03 11:10 ` Johannes Weiner
2011-08-03 11:10 ` Johannes Weiner
2011-08-03 11:10 ` Johannes Weiner
2011-08-03 13:45 ` Mel Gorman
2011-08-03 13:45 ` Mel Gorman
2011-08-03 13:45 ` Mel Gorman
2011-07-21 16:28 ` [PATCH 5/8] mm: vmscan: Do not writeback filesystem pages in kswapd except in high priority Mel Gorman
2011-07-21 16:28 ` Mel Gorman
2011-07-21 16:28 ` Mel Gorman
2011-07-31 15:11 ` Minchan Kim
2011-07-31 15:11 ` Minchan Kim
2011-07-31 15:11 ` Minchan Kim
2011-07-21 16:28 ` [PATCH 6/8] mm: vmscan: Throttle reclaim if encountering too many dirty pages under writeback Mel Gorman
2011-07-21 16:28 ` Mel Gorman
2011-07-21 16:28 ` Mel Gorman
2011-07-31 15:17 ` Minchan Kim
2011-07-31 15:17 ` Minchan Kim
2011-07-31 15:17 ` Minchan Kim
2011-08-03 11:19 ` Johannes Weiner
2011-08-03 11:19 ` Johannes Weiner
2011-08-03 11:19 ` Johannes Weiner
2011-08-03 13:56 ` Mel Gorman
2011-08-03 13:56 ` Mel Gorman
2011-08-03 13:56 ` Mel Gorman
2011-07-21 16:28 ` [PATCH 7/8] mm: vmscan: Immediately reclaim end-of-LRU dirty pages when writeback completes Mel Gorman
2011-07-21 16:28 ` Mel Gorman
2011-07-21 16:28 ` Mel Gorman
2011-07-22 12:53 ` Peter Zijlstra
2011-07-22 12:53 ` Peter Zijlstra
2011-07-22 12:53 ` Peter Zijlstra
2011-07-22 13:23 ` Mel Gorman
2011-07-22 13:23 ` Mel Gorman
2011-07-22 13:23 ` Mel Gorman
2011-07-31 15:24 ` Minchan Kim
2011-07-31 15:24 ` Minchan Kim
2011-07-31 15:24 ` Minchan Kim
2011-08-02 11:25 ` Mel Gorman
2011-08-02 11:25 ` Mel Gorman
2011-08-02 11:25 ` Mel Gorman
2011-08-03 11:26 ` Johannes Weiner
2011-08-03 11:26 ` Johannes Weiner
2011-08-03 11:26 ` Johannes Weiner
2011-08-03 13:57 ` Mel Gorman
2011-08-03 13:57 ` Mel Gorman
2011-08-03 13:57 ` Mel Gorman
2011-07-21 16:28 ` [PATCH 8/8] mm: vmscan: Do not writeback filesystem pages from kswapd Mel Gorman
2011-07-21 16:28 ` Mel Gorman
2011-07-21 16:28 ` Mel Gorman
2011-07-22 12:57 ` Peter Zijlstra
2011-07-22 12:57 ` Peter Zijlstra
2011-07-22 12:57 ` Peter Zijlstra
2011-07-22 13:31 ` Mel Gorman [this message]
2011-07-22 13:31 ` Mel Gorman
2011-07-22 13:31 ` Mel Gorman
2011-08-03 11:37 ` Johannes Weiner
2011-08-03 11:37 ` Johannes Weiner
2011-08-03 11:37 ` Johannes Weiner
2011-08-03 13:58 ` Mel Gorman
2011-08-03 13:58 ` Mel Gorman
2011-08-03 13:58 ` Mel Gorman
2011-07-26 11:20 ` [RFC PATCH 0/8] Reduce filesystem writeback from page reclaim v2 Dave Chinner
2011-07-26 11:20 ` Dave Chinner
2011-07-26 11:20 ` Dave Chinner
2011-07-27 4:32 ` Minchan Kim
2011-07-27 4:32 ` Minchan Kim
2011-07-27 4:32 ` Minchan Kim
2011-07-27 7:37 ` Mel Gorman
2011-07-27 7:37 ` Mel Gorman
2011-07-27 7:37 ` Mel Gorman
2011-07-27 16:18 ` Minchan Kim
2011-07-27 16:18 ` Minchan Kim
2011-07-27 16:18 ` Minchan Kim
2011-07-28 11:38 ` Mel Gorman
2011-07-28 11:38 ` Mel Gorman
2011-07-28 11:38 ` Mel Gorman
2011-07-29 9:48 ` Minchan Kim
2011-07-29 9:48 ` Minchan Kim
2011-07-29 9:48 ` Minchan Kim
2011-07-29 9:50 ` Minchan Kim
2011-07-29 9:50 ` Minchan Kim
2011-07-29 9:50 ` Minchan Kim
2011-07-29 13:41 ` Andrew Lutomirski
2011-07-29 13:41 ` Andrew Lutomirski
2011-07-29 13:41 ` Andrew Lutomirski
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=20110722133138.GY5349@suse.de \
--to=mgorman@suse.de \
--cc=fengguang.wu@intel.com \
--cc=hch@infradead.org \
--cc=jack@suse.cz \
--cc=jweiner@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=minchan.kim@gmail.com \
--cc=peterz@infradead.org \
--cc=riel@redhat.com \
--cc=xfs@oss.sgi.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.