All of lore.kernel.org
 help / color / mirror / Atom feed
From: Wu Fengguang <fengguang.wu@intel.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: 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>,
	Peter Zijlstra <a.p.zijlstra@chello.nl>,
	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 12/13] writeback: add trace event for balance_dirty_pages()
Date: Wed, 17 Nov 2010 12:41:29 +0800	[thread overview]
Message-ID: <20101117044129.GA16203@localhost> (raw)
In-Reply-To: <20101117042850.725694164@intel.com>

Sorry, there are some lags in the document.

On Wed, Nov 17, 2010 at 12:27:32PM +0800, Wu, Fengguang wrote:
> Here is an interesting test to verify the theory with balance_dirty_pages()
> tracing. On a partition that can do ~60MB/s, a sparse file is created and
> 4 rsync tasks with different write bandwidth started:
> 
> 	dd if=/dev/zero of=/mnt/1T bs=1M count=1 seek=1024000
> 	echo 1 > /debug/tracing/events/writeback/balance_dirty_pages/enable
> 
> 	rsync localhost:/mnt/1T /mnt/a --bwlimit 10000&
> 	rsync localhost:/mnt/1T /mnt/A --bwlimit 10000&
> 	rsync localhost:/mnt/1T /mnt/b --bwlimit 20000&
> 	rsync localhost:/mnt/1T /mnt/c --bwlimit 30000&
> 
> Trace outputs within 0.1 second, grouped by tasks:
> 
> rsync-3824  [004] 15002.076447: balance_dirty_pages: bdi=btrfs-2 weight=15% limit=130876 gap=5340 dirtied=192 pause=20
> 
> rsync-3822  [003] 15002.091701: balance_dirty_pages: bdi=btrfs-2 weight=15% limit=130777 gap=5113 dirtied=192 pause=20
> 
> rsync-3821  [006] 15002.004667: balance_dirty_pages: bdi=btrfs-2 weight=30% limit=129570 gap=3714 dirtied=64 pause=8
> rsync-3821  [006] 15002.012654: balance_dirty_pages: bdi=btrfs-2 weight=30% limit=129589 gap=3733 dirtied=64 pause=8
> rsync-3821  [006] 15002.021838: balance_dirty_pages: bdi=btrfs-2 weight=30% limit=129604 gap=3748 dirtied=64 pause=8
> rsync-3821  [004] 15002.091193: balance_dirty_pages: bdi=btrfs-2 weight=29% limit=129583 gap=3983 dirtied=64 pause=8
> rsync-3821  [004] 15002.102729: balance_dirty_pages: bdi=btrfs-2 weight=29% limit=129594 gap=3802 dirtied=64 pause=8
> rsync-3821  [000] 15002.109252: balance_dirty_pages: bdi=btrfs-2 weight=29% limit=129619 gap=3827 dirtied=64 pause=8
> 
> rsync-3823  [002] 15002.009029: balance_dirty_pages: bdi=btrfs-2 weight=39% limit=128762 gap=2842 dirtied=64 pause=12
> rsync-3823  [002] 15002.021598: balance_dirty_pages: bdi=btrfs-2 weight=39% limit=128813 gap=3021 dirtied=64 pause=12
> rsync-3823  [003] 15002.032973: balance_dirty_pages: bdi=btrfs-2 weight=39% limit=128805 gap=2885 dirtied=64 pause=12
> rsync-3823  [003] 15002.048800: balance_dirty_pages: bdi=btrfs-2 weight=39% limit=128823 gap=2967 dirtied=64 pause=12
> rsync-3823  [003] 15002.060728: balance_dirty_pages: bdi=btrfs-2 weight=39% limit=128821 gap=3221 dirtied=64 pause=12
> rsync-3823  [000] 15002.073152: balance_dirty_pages: bdi=btrfs-2 weight=39% limit=128825 gap=3225 dirtied=64 pause=12
> rsync-3823  [005] 15002.090111: balance_dirty_pages: bdi=btrfs-2 weight=39% limit=128782 gap=3214 dirtied=64 pause=12
> rsync-3823  [004] 15002.102520: balance_dirty_pages: bdi=btrfs-2 weight=39% limit=128764 gap=3036 dirtied=64 pause=12

The above lines are in the old output format, but you get the idea..

> +	/*
> +	 *           [..................soft throttling range.........]
> +	 *           ^                |<=========== bdi_gap =========>|
> +	 * background_thresh          |<== task_gap ==>|

That background_thresh should be global (background+dirty)/2.

> +	 * -------------------|-------+----------------|--------------|
> +	 *   (bdi_limit * 7/8)^       ^bdi_dirty       ^task_limit    ^bdi_limit
> +	 *
> +	 * Reasonable large gaps help produce smooth pause times.
> +	 */
> +	TP_printk("bdi=%s bdi_dirty=%lu bdi_limit=%lu task_limit=%lu "
> +		  "task_weight=%ld%% task_gap=%ld%% bdi_gap=%ld%% "
> +		  "pages_dirtied=%lu pause=%lu",
> +		  __entry->bdi,
> +		  __entry->bdi_dirty,
> +		  __entry->bdi_limit,
> +		  __entry->task_limit,
> +		  /* task weight: proportion of recent dirtied pages */
> +		  BDP_PERCENT(bdi_limit, task_limit, TASK_SOFT_DIRTY_LIMIT),
> +		  BDP_PERCENT(task_limit, bdi_dirty, TASK_SOFT_DIRTY_LIMIT),
> +		  BDP_PERCENT(bdi_limit, bdi_dirty, BDI_SOFT_DIRTY_LIMIT),
> +		  __entry->pages_dirtied,
> +		  __entry->pause
> +		  )
> +);

Thanks,
Fengguang

WARNING: multiple messages have this Message-ID (diff)
From: Wu Fengguang <fengguang.wu@intel.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: 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>,
	Peter Zijlstra <a.p.zijlstra@chello.nl>,
	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 12/13] writeback: add trace event for balance_dirty_pages()
Date: Wed, 17 Nov 2010 12:41:29 +0800	[thread overview]
Message-ID: <20101117044129.GA16203@localhost> (raw)
In-Reply-To: <20101117042850.725694164@intel.com>

Sorry, there are some lags in the document.

On Wed, Nov 17, 2010 at 12:27:32PM +0800, Wu, Fengguang wrote:
> Here is an interesting test to verify the theory with balance_dirty_pages()
> tracing. On a partition that can do ~60MB/s, a sparse file is created and
> 4 rsync tasks with different write bandwidth started:
> 
> 	dd if=/dev/zero of=/mnt/1T bs=1M count=1 seek=1024000
> 	echo 1 > /debug/tracing/events/writeback/balance_dirty_pages/enable
> 
> 	rsync localhost:/mnt/1T /mnt/a --bwlimit 10000&
> 	rsync localhost:/mnt/1T /mnt/A --bwlimit 10000&
> 	rsync localhost:/mnt/1T /mnt/b --bwlimit 20000&
> 	rsync localhost:/mnt/1T /mnt/c --bwlimit 30000&
> 
> Trace outputs within 0.1 second, grouped by tasks:
> 
> rsync-3824  [004] 15002.076447: balance_dirty_pages: bdi=btrfs-2 weight=15% limit=130876 gap=5340 dirtied=192 pause=20
> 
> rsync-3822  [003] 15002.091701: balance_dirty_pages: bdi=btrfs-2 weight=15% limit=130777 gap=5113 dirtied=192 pause=20
> 
> rsync-3821  [006] 15002.004667: balance_dirty_pages: bdi=btrfs-2 weight=30% limit=129570 gap=3714 dirtied=64 pause=8
> rsync-3821  [006] 15002.012654: balance_dirty_pages: bdi=btrfs-2 weight=30% limit=129589 gap=3733 dirtied=64 pause=8
> rsync-3821  [006] 15002.021838: balance_dirty_pages: bdi=btrfs-2 weight=30% limit=129604 gap=3748 dirtied=64 pause=8
> rsync-3821  [004] 15002.091193: balance_dirty_pages: bdi=btrfs-2 weight=29% limit=129583 gap=3983 dirtied=64 pause=8
> rsync-3821  [004] 15002.102729: balance_dirty_pages: bdi=btrfs-2 weight=29% limit=129594 gap=3802 dirtied=64 pause=8
> rsync-3821  [000] 15002.109252: balance_dirty_pages: bdi=btrfs-2 weight=29% limit=129619 gap=3827 dirtied=64 pause=8
> 
> rsync-3823  [002] 15002.009029: balance_dirty_pages: bdi=btrfs-2 weight=39% limit=128762 gap=2842 dirtied=64 pause=12
> rsync-3823  [002] 15002.021598: balance_dirty_pages: bdi=btrfs-2 weight=39% limit=128813 gap=3021 dirtied=64 pause=12
> rsync-3823  [003] 15002.032973: balance_dirty_pages: bdi=btrfs-2 weight=39% limit=128805 gap=2885 dirtied=64 pause=12
> rsync-3823  [003] 15002.048800: balance_dirty_pages: bdi=btrfs-2 weight=39% limit=128823 gap=2967 dirtied=64 pause=12
> rsync-3823  [003] 15002.060728: balance_dirty_pages: bdi=btrfs-2 weight=39% limit=128821 gap=3221 dirtied=64 pause=12
> rsync-3823  [000] 15002.073152: balance_dirty_pages: bdi=btrfs-2 weight=39% limit=128825 gap=3225 dirtied=64 pause=12
> rsync-3823  [005] 15002.090111: balance_dirty_pages: bdi=btrfs-2 weight=39% limit=128782 gap=3214 dirtied=64 pause=12
> rsync-3823  [004] 15002.102520: balance_dirty_pages: bdi=btrfs-2 weight=39% limit=128764 gap=3036 dirtied=64 pause=12

The above lines are in the old output format, but you get the idea..

> +	/*
> +	 *           [..................soft throttling range.........]
> +	 *           ^                |<=========== bdi_gap =========>|
> +	 * background_thresh          |<== task_gap ==>|

That background_thresh should be global (background+dirty)/2.

> +	 * -------------------|-------+----------------|--------------|
> +	 *   (bdi_limit * 7/8)^       ^bdi_dirty       ^task_limit    ^bdi_limit
> +	 *
> +	 * Reasonable large gaps help produce smooth pause times.
> +	 */
> +	TP_printk("bdi=%s bdi_dirty=%lu bdi_limit=%lu task_limit=%lu "
> +		  "task_weight=%ld%% task_gap=%ld%% bdi_gap=%ld%% "
> +		  "pages_dirtied=%lu pause=%lu",
> +		  __entry->bdi,
> +		  __entry->bdi_dirty,
> +		  __entry->bdi_limit,
> +		  __entry->task_limit,
> +		  /* task weight: proportion of recent dirtied pages */
> +		  BDP_PERCENT(bdi_limit, task_limit, TASK_SOFT_DIRTY_LIMIT),
> +		  BDP_PERCENT(task_limit, bdi_dirty, TASK_SOFT_DIRTY_LIMIT),
> +		  BDP_PERCENT(bdi_limit, bdi_dirty, BDI_SOFT_DIRTY_LIMIT),
> +		  __entry->pages_dirtied,
> +		  __entry->pause
> +		  )
> +);

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>

  reply	other threads:[~2010-11-17  4:41 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
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 [this message]
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 12/13] writeback: add trace event for balance_dirty_pages() 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=20101117044129.GA16203@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.