linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Dave Chinner <david@fromorbit.com>
To: Wu Fengguang <fengguang.wu@intel.com>
Cc: Jan Kara <jack@suse.cz>,
	"linux-fsdevel@vger.kernel.org" <linux-fsdevel@vger.kernel.org>,
	"linux-mm@kvack.org" <linux-mm@kvack.org>,
	Peter Zijlstra <a.p.zijlstra@chello.nl>,
	Andrew Morton <akpm@linux-foundation.org>
Subject: Re: [PATCH RFC 0/5] IO-less balance_dirty_pages() v2 (simple approach)
Date: Tue, 29 Mar 2011 13:14:58 +1100	[thread overview]
Message-ID: <20110329021458.GF3008@dastard> (raw)
In-Reply-To: <20110328024445.GA11816@localhost>

On Mon, Mar 28, 2011 at 10:44:45AM +0800, Wu Fengguang wrote:
> On Sat, Mar 26, 2011 at 07:05:44AM +0800, Jan Kara wrote:
> > And actually the NFS traces you pointed to originally seem to be different
> > problem, in fact not directly related to what balance_dirty_pages() does...
> > And with local filesystem the results seem to be reasonable (although there
> > are some longer sleeps in your JBOD measurements I don't understand yet).
> 
> Yeah the NFS case can be improved on the FS side (for now you may just
> reuse my NFS patches and focus on other generic improvements).
> 
> The JBOD issue is also beyond my understanding.
> 
> Note that XFS will also see one big IO completion per 0.5-1 seconds,
> when we are to increase the write chunk size from the current 4MB to
> near the bdi's write bandwidth. As illustrated by this graph:
> 
> http://www.kernel.org/pub/linux/kernel/people/wfg/writeback/dirty-throttling-v6/4G/xfs-1dd-1M-8p-3927M-20%25-2.6.38-rc6-dt6+-2011-02-27-22-58/global_dirtied_written-500.png

Which is _bad_.

Increasing the writeback chunk size simply causes dirty queue
starvation issues when there are lots of dirty files and lots more
memory than there is writeback bandwidth. Think of a machine with
1TB of RAM (that's a 200GB dirty limit) and 1GB/s of disk
throughput. Thats 3 minutes worth of writeback and increasing the
chunk size to ~1s worth of throughput means that the 200th dirty
file won't get serviced for 3 minutes....

We used to have behaviour similar to this this (prior to 2.6.16, IIRC),
and it caused all sorts of problems where people were losing 10-15
minute old data when the system crashed because writeback didn't
process the dirty inode list fast enough in the presence of lots of
large files....

A small writeback chunk size has no adverse impact on XFS as long as
the elevator does it's job of merging IOs (which in 99.9% of cases
it does) so I'm wondering what the reason for making this change
is.

Cheers,

Dave.
-- 
Dave Chinner
david@fromorbit.com

--
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>

  parent reply	other threads:[~2011-03-29  2:15 UTC|newest]

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-03-08 22:31 [PATCH RFC 0/5] IO-less balance_dirty_pages() v2 (simple approach) Jan Kara
2011-03-08 22:31 ` [PATCH 1/5] writeback: account per-bdi accumulated written pages Jan Kara
2011-03-08 22:31 ` [PATCH 2/5] mm: Properly reflect task dirty limits in dirty_exceeded logic Jan Kara
2011-03-09 21:02   ` Vivek Goyal
2011-03-14 20:44     ` Jan Kara
2011-03-15 15:21       ` Vivek Goyal
2011-03-08 22:31 ` [PATCH 3/5] mm: Implement IO-less balance_dirty_pages() Jan Kara
2011-03-10  0:07   ` Vivek Goyal
2011-03-14 20:48     ` Jan Kara
2011-03-15 15:23       ` Vivek Goyal
2011-03-16 21:26         ` Curt Wohlgemuth
2011-03-16 22:53           ` Curt Wohlgemuth
2011-03-16 16:53   ` Vivek Goyal
2011-03-16 19:10     ` Jan Kara
2011-03-16 19:31       ` Vivek Goyal
2011-03-16 19:58         ` Jan Kara
2011-03-16 20:22           ` Vivek Goyal
2011-03-08 22:31 ` [PATCH 4/5] mm: Remove low limit from sync_writeback_pages() Jan Kara
2011-03-08 22:31 ` [PATCH 5/5] mm: Autotune interval between distribution of page completions Jan Kara
2011-03-17 15:46 ` [PATCH RFC 0/5] IO-less balance_dirty_pages() v2 (simple approach) Curt Wohlgemuth
2011-03-17 15:51   ` Christoph Hellwig
2011-03-17 16:24     ` Curt Wohlgemuth
2011-03-17 16:43       ` Christoph Hellwig
2011-03-17 17:32   ` Jan Kara
2011-03-17 18:55     ` Curt Wohlgemuth
2011-03-17 22:56       ` Vivek Goyal
2011-03-18 14:30 ` Wu Fengguang
2011-03-22 21:43   ` Jan Kara
2011-03-23  4:41     ` Dave Chinner
2011-03-25 12:59       ` Wu Fengguang
2011-03-25 13:44     ` Wu Fengguang
2011-03-25 23:05       ` Jan Kara
2011-03-28  2:44         ` Wu Fengguang
2011-03-28 15:08           ` Jan Kara
2011-03-29  1:44             ` Wu Fengguang
2011-03-29  2:14           ` Dave Chinner [this message]
2011-03-29  2:41             ` Wu Fengguang
2011-03-29  5:59               ` Dave Chinner
2011-03-29  7:31                 ` Wu Fengguang
2011-03-29  7:52                   ` 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=20110329021458.GF3008@dastard \
    --to=david@fromorbit.com \
    --cc=a.p.zijlstra@chello.nl \
    --cc=akpm@linux-foundation.org \
    --cc=fengguang.wu@intel.com \
    --cc=jack@suse.cz \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-mm@kvack.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 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).