All of lore.kernel.org
 help / color / mirror / Atom feed
From: Wu Fengguang <fengguang.wu@intel.com>
To: <linux-fsdevel@vger.kernel.org>
Cc: Jan Kara <jack@suse.cz>, Peter Zijlstra <a.p.zijlstra@chello.nl>,
	Wu Fengguang <fengguang.wu@intel.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: LKML <linux-kernel@vger.kernel.org>
Subject: [PATCH 3/7] writeback: fix dirtied pages accounting on sub-page writes
Date: Mon, 28 Nov 2011 21:53:41 +0800	[thread overview]
Message-ID: <20111128140513.275099009@intel.com> (raw)
In-Reply-To: 20111128135338.249672012@intel.com

[-- Attachment #1: writeback-accurate-task-dirtied.patch --]
[-- Type: text/plain, Size: 1640 bytes --]

When dd in 512bytes, generic_perform_write() calls
balance_dirty_pages_ratelimited() 8 times for the same page, but
obviously the page is only dirtied once.

Fix it by accounting tsk->nr_dirtied and bdp_ratelimits at page dirty time.

Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
---
 mm/page-writeback.c |   13 +++++--------
 1 file changed, 5 insertions(+), 8 deletions(-)

--- linux-next.orig/mm/page-writeback.c	2011-11-28 21:23:20.000000000 +0800
+++ linux-next/mm/page-writeback.c	2011-11-28 21:23:23.000000000 +0800
@@ -1239,8 +1239,6 @@ void balance_dirty_pages_ratelimited_nr(
 	if (bdi->dirty_exceeded)
 		ratelimit = min(ratelimit, 32 >> (PAGE_SHIFT - 10));
 
-	current->nr_dirtied += nr_pages_dirtied;
-
 	preempt_disable();
 	/*
 	 * This prevents one CPU to accumulate too many dirtied pages without
@@ -1251,12 +1249,9 @@ void balance_dirty_pages_ratelimited_nr(
 	p =  &__get_cpu_var(bdp_ratelimits);
 	if (unlikely(current->nr_dirtied >= ratelimit))
 		*p = 0;
-	else {
-		*p += nr_pages_dirtied;
-		if (unlikely(*p >= ratelimit_pages)) {
-			*p = 0;
-			ratelimit = 0;
-		}
+	else if (unlikely(*p >= ratelimit_pages)) {
+		*p = 0;
+		ratelimit = 0;
 	}
 	/*
 	 * Pick up the dirtied pages by the exited tasks. This avoids lots of
@@ -1749,6 +1744,8 @@ void account_page_dirtied(struct page *p
 		__inc_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE);
 		__inc_bdi_stat(mapping->backing_dev_info, BDI_DIRTIED);
 		task_io_account_write(PAGE_CACHE_SIZE);
+		current->nr_dirtied++;
+		this_cpu_inc(bdp_ratelimits);
 	}
 }
 EXPORT_SYMBOL(account_page_dirtied);



  parent reply	other threads:[~2011-11-28 14:09 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-11-28 13:53 [PATCH 0/7] dirty throttling bits for 3.3 (v2) Wu Fengguang
2011-11-28 13:53 ` [PATCH 1/7] writeback: balanced_rate cannot exceed write bandwidth Wu Fengguang
2011-12-07 10:21   ` Jan Kara
2011-11-28 13:53 ` [PATCH 2/7] writeback: charge leaked page dirties to active tasks Wu Fengguang
2011-12-07 10:23   ` Jan Kara
2011-11-28 13:53 ` Wu Fengguang [this message]
2011-12-07 10:53   ` [PATCH 3/7] writeback: fix dirtied pages accounting on sub-page writes Jan Kara
2011-12-07 12:08     ` Wu Fengguang
2011-12-07 16:07       ` Jan Kara
2011-12-08  2:44         ` Wu Fengguang
2011-11-28 13:53 ` [PATCH 4/7] writeback: fix dirtied pages accounting on redirty Wu Fengguang
2011-12-07 16:09   ` Jan Kara
2011-11-28 13:53 ` [PATCH 5/7] btrfs: fix dirtied pages accounting on sub-page writes Wu Fengguang
2011-11-28 14:16   ` Wu Fengguang
2011-11-28 13:53 ` [PATCH 6/7] writeback: dirty ratelimit - think time compensation Wu Fengguang
2011-12-07 16:14   ` Jan Kara
2011-11-28 13:53 ` [PATCH 7/7] writeback: comment on the bdi dirty threshold Wu Fengguang
2011-12-07 10:57   ` Jan Kara

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=20111128140513.275099009@intel.com \
    --to=fengguang.wu@intel.com \
    --cc=a.p.zijlstra@chello.nl \
    --cc=jack@suse.cz \
    --cc=linux-fsdevel@vger.kernel.org \
    /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.