From: Wu Fengguang <fengguang.wu@intel.com>
To: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Jan Kara <jack@suse.cz>, Christoph Hellwig <hch@lst.de>,
Dave Chinner <david@fromorbit.com>,
"Theodore Ts'o" <tytso@mit.edu>,
Chris Mason <chris.mason@oracle.com>, Mel Gorman <mel@csn.ul.ie>,
Rik van Riel <riel@redhat.com>,
KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>,
linux-mm <linux-mm@kvack.org>,
"linux-fsdevel@vger.kernel.org" <linux-fsdevel@vger.kernel.org>,
LKML <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 08/13] writeback: quit throttling when bdi dirty pages dropped low
Date: Wed, 24 Nov 2010 20:59:01 +0800 [thread overview]
Message-ID: <20101124125901.GD10413@localhost> (raw)
In-Reply-To: <1290602811.2072.462.camel@laptop>
On Wed, Nov 24, 2010 at 08:46:51PM +0800, Peter Zijlstra wrote:
> On Wed, 2010-11-24 at 20:30 +0800, Wu Fengguang wrote:
> >
> > For the 1-dd case, it looks better to lower the break threshold to
> > 125ms. After all, it's not easy for the dirty pages to drop by 250ms
> > worth of data when you only slept 200ms (note: the max pause time has
> > been doubled mainly for servers).
> >
> > - if (nr_dirty < dirty_thresh &&
> > - bdi_prev_dirty - bdi_dirty > (long)bdi->write_bandwidth / 4)
> > + if (nr_dirty <= dirty_thresh &&
> > + bdi_prev_dirty - bdi_dirty > (long)bdi->write_bandwidth / 8)
> > break;
>
> Hrm, but 125ms worth in 200ms is rather easy, you'd want to keep that
> limit above what the pause should give you, right?
Yeah, I exactly mean to quit the loop after sleeping 200ms.
200ms pause already seem large..
I'll leave the safeguard to the "nr_dirty <= dirty_thresh" test :)
This trace shows the problem it tries to solve. Here on fresh boot,
bdi_dirty=106600 which is much larger than bdi_limit=13525.
The same situation may happen if some task quickly eats lots of
anonymous memory, then the global/bdi limits will be knock down
suddenly and it takes time to bring down bdi_dirty.
# TASK-PID CPU# TIMESTAMP FUNCTION
# | | | | |
<...>-2722 [005] 39.623216: balance_dirty_pages: bdi=8:0 bdi_dirty=106600 bdi_limit=13525 task_limit=13423 task_weight=12% task_gap=-11022% bdi_gap=-5504% dirtied=268 bw=0 ratelimit=0 period=0 think=0 pause=200
<...>-2720 [004] 39.623222: balance_dirty_pages: bdi=8:0 bdi_dirty=106600 bdi_limit=13513 task_limit=13441 task_weight=9% task_gap=-11029% bdi_gap=-5510% dirtied=267 bw=0 ratelimit=0 period=0 think=0 pause=200
<...>-2717 [003] 39.623666: balance_dirty_pages: bdi=8:0 bdi_dirty=106560 bdi_limit=13742 task_limit=13659 task_weight=10% task_gap=-10815% bdi_gap=-5402% dirtied=268 bw=0 ratelimit=0 period=0 think=0 pause=200
<...>-2718 [004] 39.623990: balance_dirty_pages: bdi=8:0 bdi_dirty=106560 bdi_limit=13979 task_limit=13913 task_weight=8% task_gap=-10603% bdi_gap=-5297% dirtied=272 bw=0 ratelimit=0 period=0 think=0 pause=200
<...>-2715 [007] 39.626472: balance_dirty_pages: bdi=8:0 bdi_dirty=106360 bdi_limit=15312 task_limit=15211 task_weight=11% task_gap=-9523% bdi_gap=-4756% dirtied=268 bw=0 ratelimit=0 period=0 think=0 pause=200
<...>-2723 [001] 39.628951: balance_dirty_pages: bdi=8:0 bdi_dirty=106560 bdi_limit=15749 task_limit=15640 task_weight=11% task_gap=-9236% bdi_gap=-4612% dirtied=269 bw=0 ratelimit=0 period=0 think=0 pause=200
Thanks,
Fengguang
WARNING: multiple messages have this Message-ID (diff)
From: Wu Fengguang <fengguang.wu@intel.com>
To: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Jan Kara <jack@suse.cz>, Christoph Hellwig <hch@lst.de>,
Dave Chinner <david@fromorbit.com>, Theodore Ts'o <tytso@mit.edu>,
Chris Mason <chris.mason@oracle.com>, Mel Gorman <mel@csn.ul.ie>,
Rik van Riel <riel@redhat.com>,
KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>,
linux-mm <linux-mm@kvack.org>,
"linux-fsdevel@vger.kernel.org" <linux-fsdevel@vger.kernel.org>,
LKML <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 08/13] writeback: quit throttling when bdi dirty pages dropped low
Date: Wed, 24 Nov 2010 20:59:01 +0800 [thread overview]
Message-ID: <20101124125901.GD10413@localhost> (raw)
In-Reply-To: <1290602811.2072.462.camel@laptop>
On Wed, Nov 24, 2010 at 08:46:51PM +0800, Peter Zijlstra wrote:
> On Wed, 2010-11-24 at 20:30 +0800, Wu Fengguang wrote:
> >
> > For the 1-dd case, it looks better to lower the break threshold to
> > 125ms. After all, it's not easy for the dirty pages to drop by 250ms
> > worth of data when you only slept 200ms (note: the max pause time has
> > been doubled mainly for servers).
> >
> > - if (nr_dirty < dirty_thresh &&
> > - bdi_prev_dirty - bdi_dirty > (long)bdi->write_bandwidth / 4)
> > + if (nr_dirty <= dirty_thresh &&
> > + bdi_prev_dirty - bdi_dirty > (long)bdi->write_bandwidth / 8)
> > break;
>
> Hrm, but 125ms worth in 200ms is rather easy, you'd want to keep that
> limit above what the pause should give you, right?
Yeah, I exactly mean to quit the loop after sleeping 200ms.
200ms pause already seem large..
I'll leave the safeguard to the "nr_dirty <= dirty_thresh" test :)
This trace shows the problem it tries to solve. Here on fresh boot,
bdi_dirty=106600 which is much larger than bdi_limit=13525.
The same situation may happen if some task quickly eats lots of
anonymous memory, then the global/bdi limits will be knock down
suddenly and it takes time to bring down bdi_dirty.
# TASK-PID CPU# TIMESTAMP FUNCTION
# | | | | |
<...>-2722 [005] 39.623216: balance_dirty_pages: bdi=8:0 bdi_dirty=106600 bdi_limit=13525 task_limit=13423 task_weight=12% task_gap=-11022% bdi_gap=-5504% dirtied=268 bw=0 ratelimit=0 period=0 think=0 pause=200
<...>-2720 [004] 39.623222: balance_dirty_pages: bdi=8:0 bdi_dirty=106600 bdi_limit=13513 task_limit=13441 task_weight=9% task_gap=-11029% bdi_gap=-5510% dirtied=267 bw=0 ratelimit=0 period=0 think=0 pause=200
<...>-2717 [003] 39.623666: balance_dirty_pages: bdi=8:0 bdi_dirty=106560 bdi_limit=13742 task_limit=13659 task_weight=10% task_gap=-10815% bdi_gap=-5402% dirtied=268 bw=0 ratelimit=0 period=0 think=0 pause=200
<...>-2718 [004] 39.623990: balance_dirty_pages: bdi=8:0 bdi_dirty=106560 bdi_limit=13979 task_limit=13913 task_weight=8% task_gap=-10603% bdi_gap=-5297% dirtied=272 bw=0 ratelimit=0 period=0 think=0 pause=200
<...>-2715 [007] 39.626472: balance_dirty_pages: bdi=8:0 bdi_dirty=106360 bdi_limit=15312 task_limit=15211 task_weight=11% task_gap=-9523% bdi_gap=-4756% dirtied=268 bw=0 ratelimit=0 period=0 think=0 pause=200
<...>-2723 [001] 39.628951: balance_dirty_pages: bdi=8:0 bdi_dirty=106560 bdi_limit=15749 task_limit=15640 task_weight=11% task_gap=-9236% bdi_gap=-4612% dirtied=269 bw=0 ratelimit=0 period=0 think=0 pause=200
Thanks,
Fengguang
--
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 prev parent reply other threads:[~2010-11-24 12:59 UTC|newest]
Thread overview: 162+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-11-17 4:27 [PATCH 00/13] IO-less dirty throttling v2 Wu Fengguang
2010-11-17 4:27 ` Wu Fengguang
2010-11-17 4:27 ` Wu Fengguang
2010-11-17 4:27 ` [PATCH 01/13] writeback: IO-less balance_dirty_pages() Wu Fengguang
2010-11-17 4:27 ` Wu Fengguang
2010-11-17 4:27 ` Wu Fengguang
2010-11-17 10:34 ` Minchan Kim
2010-11-17 10:34 ` Minchan Kim
2010-11-22 2:01 ` Wu Fengguang
2010-11-22 2:01 ` Wu Fengguang
2010-11-22 2:01 ` Wu Fengguang
2010-11-17 23:08 ` Andrew Morton
2010-11-17 23:08 ` Andrew Morton
2010-11-17 23:08 ` Andrew Morton
2010-11-18 13:04 ` Peter Zijlstra
2010-11-18 13:04 ` Peter Zijlstra
2010-11-18 13:26 ` Wu Fengguang
2010-11-18 13:26 ` Wu Fengguang
2010-11-18 13:40 ` Peter Zijlstra
2010-11-18 13:40 ` Peter Zijlstra
2010-11-18 14:02 ` Wu Fengguang
2010-11-18 14:02 ` Wu Fengguang
[not found] ` <20101129151719.GA30590@localhost>
[not found] ` <1291064013.32004.393.camel@laptop>
[not found] ` <20101130043735.GA22947@localhost>
[not found] ` <1291156522.32004.1359.camel@laptop>
[not found] ` <1291156765.32004.1365.camel@laptop>
[not found] ` <20101201133818.GA13377@localhost>
2010-12-01 23:03 ` Andrew Morton
2010-12-01 23:03 ` Andrew Morton
2010-12-02 1:56 ` Wu Fengguang
2010-12-02 1:56 ` Wu Fengguang
2010-12-05 16:14 ` Wu Fengguang
2010-12-06 2:42 ` Ted Ts'o
2010-12-06 2:42 ` Ted Ts'o
2010-12-06 9:52 ` Dmitry
2010-12-06 9:52 ` Dmitry
2010-12-06 9:52 ` Dmitry
2010-12-06 12:34 ` Ted Ts'o
2010-12-06 12:34 ` Ted Ts'o
2010-11-17 4:27 ` [PATCH 02/13] writeback: consolidate variable names in balance_dirty_pages() Wu Fengguang
2010-11-17 4:27 ` Wu Fengguang
2010-11-17 4:27 ` [PATCH 03/13] writeback: per-task rate limit on balance_dirty_pages() Wu Fengguang
2010-11-17 4:27 ` Wu Fengguang
2010-11-17 4:27 ` Wu Fengguang
2010-11-17 14:39 ` Wu Fengguang
2010-11-17 14:39 ` Wu Fengguang
2010-11-24 10:23 ` Peter Zijlstra
2010-11-24 10:23 ` Peter Zijlstra
2010-11-24 10:43 ` Wu Fengguang
2010-11-24 10:43 ` Wu Fengguang
2010-11-24 10:49 ` Peter Zijlstra
2010-11-24 10:49 ` Peter Zijlstra
2010-11-17 4:27 ` [PATCH 04/13] writeback: prevent duplicate balance_dirty_pages_ratelimited() calls Wu Fengguang
2010-11-17 4:27 ` Wu Fengguang
2010-11-17 4:27 ` Wu Fengguang
2010-11-17 4:27 ` [PATCH 05/13] writeback: account per-bdi accumulated written pages Wu Fengguang
2010-11-17 4:27 ` Wu Fengguang
2010-11-17 4:27 ` Wu Fengguang
2010-11-24 10:26 ` Peter Zijlstra
2010-11-24 10:26 ` Peter Zijlstra
2010-11-24 10:44 ` Wu Fengguang
2010-11-24 10:44 ` Wu Fengguang
2010-11-17 4:27 ` [PATCH 06/13] writeback: bdi write bandwidth estimation Wu Fengguang
2010-11-17 4:27 ` Wu Fengguang
2010-11-17 4:27 ` Wu Fengguang
2010-11-17 23:08 ` Andrew Morton
2010-11-17 23:08 ` Andrew Morton
2010-11-17 23:08 ` Andrew Morton
2010-11-17 23:24 ` Peter Zijlstra
2010-11-17 23:24 ` Peter Zijlstra
2010-11-17 23:38 ` Andrew Morton
2010-11-17 23:38 ` Andrew Morton
2010-11-17 23:43 ` Peter Zijlstra
2010-11-17 23:43 ` Peter Zijlstra
2010-11-18 6:51 ` Wu Fengguang
2010-11-18 6:51 ` Wu Fengguang
2010-11-24 10:58 ` Peter Zijlstra
2010-11-24 10:58 ` Peter Zijlstra
2010-11-24 14:06 ` Wu Fengguang
2010-11-24 14:06 ` Wu Fengguang
2010-11-24 11:05 ` Peter Zijlstra
2010-11-24 11:05 ` Peter Zijlstra
2010-11-24 12:10 ` Wu Fengguang
2010-11-24 12:10 ` Wu Fengguang
2010-11-24 12:50 ` Peter Zijlstra
2010-11-24 12:50 ` Peter Zijlstra
2010-11-24 13:14 ` Wu Fengguang
2010-11-24 13:14 ` Wu Fengguang
2010-11-24 13:20 ` Wu Fengguang
2010-11-24 13:20 ` Wu Fengguang
2010-11-24 13:42 ` Peter Zijlstra
2010-11-24 13:42 ` Peter Zijlstra
2010-11-24 13:46 ` Wu Fengguang
2010-11-24 13:46 ` Wu Fengguang
2010-11-24 14:12 ` Peter Zijlstra
2010-11-24 14:12 ` Peter Zijlstra
2010-11-24 14:21 ` Wu Fengguang
2010-11-24 14:21 ` Wu Fengguang
2010-11-24 14:31 ` Peter Zijlstra
2010-11-24 14:31 ` Peter Zijlstra
2010-11-24 14:38 ` Wu Fengguang
2010-11-24 14:38 ` Wu Fengguang
2010-11-24 14:34 ` Wu Fengguang
2010-11-24 14:34 ` Wu Fengguang
2010-11-17 4:27 ` [PATCH 07/13] writeback: show bdi write bandwidth in debugfs Wu Fengguang
2010-11-17 4:27 ` Wu Fengguang
2010-11-17 4:27 ` Wu Fengguang
2010-11-17 4:27 ` [PATCH 08/13] writeback: quit throttling when bdi dirty pages dropped low Wu Fengguang
2010-11-17 4:27 ` Wu Fengguang
2010-11-17 4:27 ` Wu Fengguang
2010-11-24 11:13 ` Peter Zijlstra
2010-11-24 11:13 ` Peter Zijlstra
2010-11-24 12:30 ` Wu Fengguang
2010-11-24 12:30 ` Wu Fengguang
2010-11-24 12:46 ` Peter Zijlstra
2010-11-24 12:46 ` Peter Zijlstra
2010-11-24 12:59 ` Wu Fengguang [this message]
2010-11-24 12:59 ` Wu Fengguang
2010-11-17 4:27 ` [PATCH 09/13] writeback: reduce per-bdi dirty threshold ramp up time Wu Fengguang
2010-11-17 4:27 ` Wu Fengguang
2010-11-17 4:27 ` Wu Fengguang
2010-11-24 11:15 ` Peter Zijlstra
2010-11-24 11:15 ` Peter Zijlstra
2010-11-24 12:39 ` Wu Fengguang
2010-11-24 12:39 ` Wu Fengguang
2010-11-24 12:56 ` Peter Zijlstra
2010-11-24 12:56 ` Peter Zijlstra
2010-11-17 4:27 ` [PATCH 10/13] writeback: make reasonable gap between the dirty/background thresholds Wu Fengguang
2010-11-17 4:27 ` Wu Fengguang
2010-11-17 4:27 ` Wu Fengguang
2010-11-24 11:18 ` Peter Zijlstra
2010-11-24 11:18 ` Peter Zijlstra
2010-11-24 12:48 ` Wu Fengguang
2010-11-24 12:48 ` Wu Fengguang
2010-11-17 4:27 ` [PATCH 11/13] writeback: scale down max throttle bandwidth on concurrent dirtiers Wu Fengguang
2010-11-17 4:27 ` Wu Fengguang
2010-11-17 4:27 ` Wu Fengguang
2010-11-17 4:27 ` [PATCH 12/13] writeback: add trace event for balance_dirty_pages() Wu Fengguang
2010-11-17 4:27 ` Wu Fengguang
2010-11-17 4:27 ` Wu Fengguang
2010-11-17 4:41 ` Wu Fengguang
2010-11-17 4:41 ` Wu Fengguang
2010-11-17 4:27 ` [PATCH 13/13] writeback: make nr_to_write a per-file limit Wu Fengguang
2010-11-17 4:27 ` Wu Fengguang
2010-11-17 4:27 ` Wu Fengguang
2010-11-17 23:03 ` [PATCH 00/13] IO-less dirty throttling v2 Andrew Morton
2010-11-17 23:03 ` Andrew Morton
2010-11-17 23:03 ` Andrew Morton
2010-11-18 2:06 ` Dave Chinner
2010-11-18 2:06 ` Dave Chinner
2010-11-18 2:09 ` Andrew Morton
2010-11-18 2:09 ` Andrew Morton
2010-11-18 3:21 ` Dave Chinner
2010-11-18 3:21 ` Dave Chinner
2010-11-18 3:34 ` Andrew Morton
2010-11-18 3:34 ` Andrew Morton
2010-11-18 7:27 ` Dave Chinner
2010-11-18 7:27 ` Dave Chinner
2010-11-18 7:33 ` Andrew Morton
2010-11-18 7:33 ` Andrew Morton
2010-11-19 3:11 ` Dave Chinner
2010-11-19 3:11 ` Dave Chinner
2010-11-24 11:12 ` Avi Kivity
2010-11-24 11:12 ` Avi Kivity
-- strict thread matches above, loose matches on Subject: below --
2010-11-17 3:58 [PATCH 08/13] writeback: quit throttling when bdi dirty pages dropped low Wu Fengguang
2010-11-17 3:58 ` Wu Fengguang
2010-11-17 3:58 ` Wu Fengguang
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=20101124125901.GD10413@localhost \
--to=fengguang.wu@intel.com \
--cc=a.p.zijlstra@chello.nl \
--cc=akpm@linux-foundation.org \
--cc=chris.mason@oracle.com \
--cc=david@fromorbit.com \
--cc=hch@lst.de \
--cc=jack@suse.cz \
--cc=kosaki.motohiro@jp.fujitsu.com \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mel@csn.ul.ie \
--cc=riel@redhat.com \
--cc=tytso@mit.edu \
/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.