linux-fsdevel.vger.kernel.org archive mirror
 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>, Wu Fengguang <fengguang.wu@intel.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: Chris Mason <chris.mason@oracle.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Rik van Riel <riel@redhat.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: linux-mm <linux-mm@kvack.org>
Cc: <linux-fsdevel@vger.kernel.org>
Cc: LKML <linux-kernel@vger.kernel.org>
Subject: [PATCH 32/47] writeback: extend balance_dirty_pages() trace event
Date: Mon, 13 Dec 2010 14:43:21 +0800	[thread overview]
Message-ID: <20101213064840.918401954@intel.com> (raw)
In-Reply-To: 20101213064249.648862451@intel.com

[-- Attachment #1: writeback-trace-add-fields.patch --]
[-- Type: text/plain, Size: 5047 bytes --]

Make it more useful for analyzing the dynamics of the throttling
algorithms, and helpful for debugging user reported problems.

Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
---
 include/trace/events/writeback.h |   52 +++++++++++++++++++++--------
 mm/page-writeback.c              |   14 +++++++
 2 files changed, 53 insertions(+), 13 deletions(-)

--- linux-next.orig/include/trace/events/writeback.h	2010-12-09 12:21:04.000000000 +0800
+++ linux-next/include/trace/events/writeback.h	2010-12-09 12:24:49.000000000 +0800
@@ -149,35 +149,53 @@ DEFINE_WBC_EVENT(wbc_writeback_written);
 DEFINE_WBC_EVENT(wbc_writeback_wait);
 DEFINE_WBC_EVENT(wbc_writepage);
 
+#define KBps(x)			((x) << (PAGE_SHIFT - 10))
 #define BDP_PERCENT(a, b, c)	((__entry->a - __entry->b) * 100 * c + \
 				  __entry->bdi_limit/2) / (__entry->bdi_limit|1)
+
 TRACE_EVENT(balance_dirty_pages,
 
 	TP_PROTO(struct backing_dev_info *bdi,
 		 long bdi_dirty,
+		 long avg_dirty,
 		 long bdi_limit,
 		 long task_limit,
-		 long pages_dirtied,
+		 long dirtied,
+		 long task_bw,
+		 long period,
 		 long pause),
 
-	TP_ARGS(bdi, bdi_dirty, bdi_limit, task_limit,
-		pages_dirtied, pause),
+	TP_ARGS(bdi, bdi_dirty, avg_dirty, bdi_limit, task_limit,
+		dirtied, task_bw, period, pause),
 
 	TP_STRUCT__entry(
 		__array(char,	bdi, 32)
 		__field(long,	bdi_dirty)
+		__field(long,	avg_dirty)
 		__field(long,	bdi_limit)
 		__field(long,	task_limit)
-		__field(long,	pages_dirtied)
+		__field(long,	dirtied)
+		__field(long,	bdi_bw)
+		__field(long,	base_bw)
+		__field(long,	task_bw)
+		__field(long,	period)
+		__field(long,	think)
 		__field(long,	pause)
 	),
 
 	TP_fast_assign(
 		strlcpy(__entry->bdi, dev_name(bdi->dev), 32);
 		__entry->bdi_dirty	= bdi_dirty;
+		__entry->avg_dirty	= avg_dirty;
 		__entry->bdi_limit	= bdi_limit;
 		__entry->task_limit	= task_limit;
-		__entry->pages_dirtied	= pages_dirtied;
+		__entry->dirtied	= dirtied;
+		__entry->bdi_bw		= KBps(bdi->write_bandwidth);
+		__entry->base_bw	= KBps(bdi->throttle_bandwidth);
+		__entry->task_bw	= KBps(task_bw);
+		__entry->think		= current->paused_when == 0 ? 0 :
+			 (long)(jiffies - current->paused_when) * 1000 / HZ;
+		__entry->period		= period * 1000 / HZ;
 		__entry->pause		= pause * 1000 / HZ;
 	),
 
@@ -191,19 +209,27 @@ TRACE_EVENT(balance_dirty_pages,
 	 *
 	 * 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",
+	TP_printk("bdi %s: "
+		  "bdi_limit=%lu task_limit=%lu bdi_dirty=%lu avg_dirty=%lu "
+		  "bdi_gap=%ld%% task_gap=%ld%% task_weight=%ld%% "
+		  "bdi_bw=%lu base_bw=%lu task_bw=%lu "
+		  "dirtied=%lu period=%lu think=%ld pause=%ld",
 		  __entry->bdi,
-		  __entry->bdi_dirty,
 		  __entry->bdi_limit,
 		  __entry->task_limit,
+		  __entry->bdi_dirty,
+		  __entry->avg_dirty,
+		  BDP_PERCENT(bdi_limit, bdi_dirty, BDI_SOFT_DIRTY_LIMIT),
+		  BDP_PERCENT(task_limit, avg_dirty, TASK_SOFT_DIRTY_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
+		  __entry->bdi_bw,	/* bdi write bandwidth */
+		  __entry->base_bw,	/* bdi base throttle bandwidth */
+		  __entry->task_bw,	/* task throttle bandwidth */
+		  __entry->dirtied,
+		  __entry->period,	/* ms */
+		  __entry->think,	/* ms */
+		  __entry->pause	/* ms */
 		  )
 );
 
--- linux-next.orig/mm/page-writeback.c	2010-12-09 12:24:47.000000000 +0800
+++ linux-next/mm/page-writeback.c	2010-12-09 12:24:49.000000000 +0800
@@ -785,6 +785,8 @@ static void balance_dirty_pages(struct a
 		pause_max = max_pause(bdi_thresh);
 
 		if (avg_dirty >= task_thresh || nr_dirty > dirty_thresh) {
+			bw = 0;
+			period = 0;
 			pause = pause_max;
 			goto pause;
 		}
@@ -812,6 +814,15 @@ static void balance_dirty_pages(struct a
 		 * it may be a light dirtier.
 		 */
 		if (unlikely(-pause < HZ*10)) {
+			trace_balance_dirty_pages(bdi,
+						  bdi_dirty,
+						  avg_dirty,
+						  bdi_thresh,
+						  task_thresh,
+						  pages_dirtied,
+						  bw,
+						  period,
+						  pause);
 			if (-pause <= HZ/10)
 				current->paused_when += period;
 			else
@@ -824,9 +835,12 @@ static void balance_dirty_pages(struct a
 pause:
 		trace_balance_dirty_pages(bdi,
 					  bdi_dirty,
+					  avg_dirty,
 					  bdi_thresh,
 					  task_thresh,
 					  pages_dirtied,
+					  bw,
+					  period,
 					  pause);
 		current->paused_when = jiffies;
 		__set_current_state(TASK_UNINTERRUPTIBLE);


--
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>

  parent reply	other threads:[~2010-12-13  6:43 UTC|newest]

Thread overview: 51+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-12-13  6:42 [PATCH 00/47] IO-less dirty throttling v3 Wu Fengguang
2010-12-13  6:42 ` [PATCH 01/47] writeback: enabling gate limit for light dirtied bdi Wu Fengguang
2010-12-13  6:42 ` [PATCH 02/47] writeback: safety margin for bdi stat error Wu Fengguang
2010-12-13  6:42 ` [PATCH 03/47] writeback: IO-less balance_dirty_pages() Wu Fengguang
2010-12-13  6:42 ` [PATCH 04/47] writeback: consolidate variable names in balance_dirty_pages() Wu Fengguang
2010-12-13  6:42 ` [PATCH 05/47] writeback: per-task rate limit on balance_dirty_pages() Wu Fengguang
2010-12-13  6:42 ` [PATCH 06/47] writeback: prevent duplicate balance_dirty_pages_ratelimited() calls Wu Fengguang
2010-12-13  6:42 ` [PATCH 07/47] writeback: account per-bdi accumulated written pages Wu Fengguang
2010-12-13  6:42 ` [PATCH 08/47] writeback: bdi write bandwidth estimation Wu Fengguang
2010-12-13  6:42 ` [PATCH 09/47] writeback: show bdi write bandwidth in debugfs Wu Fengguang
2010-12-13  6:42 ` [PATCH 10/47] writeback: quit throttling when bdi dirty pages dropped low Wu Fengguang
2010-12-13  6:43 ` [PATCH 11/47] writeback: reduce per-bdi dirty threshold ramp up time Wu Fengguang
2010-12-13  6:43 ` [PATCH 12/47] writeback: make reasonable gap between the dirty/background thresholds Wu Fengguang
2010-12-13  6:43 ` [PATCH 13/47] writeback: scale down max throttle bandwidth on concurrent dirtiers Wu Fengguang
2010-12-13  6:43 ` [PATCH 14/47] writeback: add trace event for balance_dirty_pages() Wu Fengguang
2010-12-13  6:43 ` [PATCH 15/47] writeback: make nr_to_write a per-file limit Wu Fengguang
2010-12-13  6:43 ` [PATCH 16/47] writeback: make-nr_to_write-a-per-file-limit fix Wu Fengguang
2010-12-13  6:43 ` [PATCH 17/47] writeback: do uninterruptible sleep in balance_dirty_pages() Wu Fengguang
2010-12-13  6:43 ` [PATCH 18/47] writeback: move BDI_WRITTEN accounting into __bdi_writeout_inc() Wu Fengguang
2010-12-13  6:43 ` [PATCH 19/47] writeback: fix increasement of nr_dirtied_pause Wu Fengguang
2010-12-13  6:43 ` [PATCH 20/47] writeback: use do_div in bw calculation Wu Fengguang
2010-12-13  6:43 ` [PATCH 21/47] writeback: prevent divide error on tiny HZ Wu Fengguang
2010-12-13  6:43 ` [PATCH 22/47] writeback: prevent bandwidth calculation overflow Wu Fengguang
2010-12-13  6:43 ` [PATCH 23/47] writeback: spinlock protected bdi bandwidth update Wu Fengguang
2010-12-13  6:43 ` [PATCH 24/47] writeback: increase pause time on concurrent dirtiers Wu Fengguang
2010-12-13  6:43 ` [PATCH 25/47] writeback: make it easier to break from a dirty exceeded bdi Wu Fengguang
2010-12-13  6:43 ` [PATCH 26/47] writeback: start background writeback earlier Wu Fengguang
2010-12-13  6:43 ` [PATCH 27/47] writeback: user space think time compensation Wu Fengguang
2010-12-13  6:43 ` [PATCH 28/47] writeback: bdi base throttle bandwidth Wu Fengguang
2010-12-13  6:43 ` [PATCH 29/47] writeback: smoothed bdi dirty pages Wu Fengguang
2010-12-13  6:43 ` [PATCH 30/47] writeback: adapt max balance pause time to memory size Wu Fengguang
2010-12-13  6:43 ` [PATCH 31/47] writeback: increase min pause time on concurrent dirtiers Wu Fengguang
2010-12-13  6:43 ` Wu Fengguang [this message]
2010-12-13  6:43 ` [PATCH 33/47] writeback: trace global dirty page states Wu Fengguang
2010-12-13  6:43 ` [PATCH 34/47] writeback: trace writeback_single_inode() Wu Fengguang
2010-12-13  6:43 ` [PATCH 35/47] writeback: scale IO chunk size up to device bandwidth Wu Fengguang
2010-12-13  6:43 ` [PATCH 36/47] btrfs: dont call balance_dirty_pages_ratelimited() on already dirty pages Wu Fengguang
2010-12-13  6:43 ` [PATCH 37/47] btrfs: lower the dirty balacing rate limit Wu Fengguang
2010-12-13  6:43 ` [PATCH 38/47] btrfs: wait on too many nr_async_bios Wu Fengguang
2010-12-13  6:43 ` [PATCH 39/47] nfs: livelock prevention is now done in VFS Wu Fengguang
2010-12-13  6:43 ` [PATCH 40/47] nfs: writeback pages wait queue Wu Fengguang
2010-12-13  6:43 ` [PATCH 41/47] nfs: in-commit pages accounting and " Wu Fengguang
2010-12-13  6:43 ` [PATCH 42/47] nfs: heuristics to avoid commit Wu Fengguang
2010-12-13  6:43 ` [PATCH 43/47] nfs: dont change wbc->nr_to_write in write_inode() Wu Fengguang
2010-12-13  6:43 ` [PATCH 44/47] nfs: limit the range of commits Wu Fengguang
2010-12-13  6:43 ` [PATCH 45/47] nfs: adapt congestion threshold to dirty threshold Wu Fengguang
2010-12-13  6:43 ` [PATCH 46/47] nfs: trace nfs_commit_unstable_pages() Wu Fengguang
2010-12-13  6:43 ` [PATCH 47/47] nfs: trace nfs_commit_release() Wu Fengguang
2010-12-13 11:27 ` [PATCH 00/47] IO-less dirty throttling v3 Peter Zijlstra
2010-12-13 11:49   ` Wu Fengguang
2010-12-13 12:38     ` Peter Zijlstra

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=20101213064840.918401954@intel.com \
    --to=fengguang.wu@intel.com \
    --cc=akpm@linux-foundation.org \
    --cc=jack@suse.cz \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).