All of lore.kernel.org
 help / color / mirror / Atom feed
From: Dave Chinner <david@fromorbit.com>
To: Alex Elder <aelder@sgi.com>
Cc: xfs@oss.sgi.com
Subject: Re: [PATCH 4/8] xfs: limit extent length for allocation to AG size
Date: Thu, 27 Jan 2011 11:38:52 +1100	[thread overview]
Message-ID: <20110127003851.GC21311@dastard> (raw)
In-Reply-To: <1296076968.1980.941.camel@doink>

On Wed, Jan 26, 2011 at 03:22:48PM -0600, Alex Elder wrote:
> On Tue, 2011-01-25 at 19:50 +1100, Dave Chinner wrote:
> > From: Dave Chinner <dchinner@redhat.com>
> > 
> > Delayed allocation extents can be larger than AGs, so when trying to
> > convert a large range we may scan every AG inside
> > xfs_bmap_alloc_nullfb() trying to find an AG with a size larger than
> > an AG. We should stop when we find the first AG with a maximum
> > possible allocation size. This causes excessive CPU usage when there
> > are lots of AGs.
> > 
> > The same problem occurs when doing preallocation of a range larger
> > than an AG.
> > 
> > Fix the problem by limiting real allocation lengths to the maximum
> > that an AG can support. This means if we have empty AGs, we'll stop
> > the search at the first of them. If there are no empty AGs, we'll
> > still scan them all, but that is a different problem....
> 
> Maybe I'm wrong but I think you need to change a "+"
> to a "-" (shown below).

Good catch. That's what I get for cleaning up code ;)

> 
> And I have a few really minor suggestions:
> - You should update a comment (which I point
>   out below) to match your change.

Will fix.

> - Maybe make use of a local variable, at least
>   in xfs_bmap_btalloc_nullfb(), such as:
>     xfs_extlen_t requested = args->maxlen;

All the allocation code is coded that way to avoid putting local
variables on the stack. The allocation-in-writeback path is the
critical stack usage path in XFS, so I'd prefer to keep using
args->maxlen here....

Cheers,

Dave.
-- 
Dave Chinner
david@fromorbit.com

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs

  reply	other threads:[~2011-01-27  0:36 UTC|newest]

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-01-25  8:50 [PATCH 0/8] xfs: 2.6.38-rc candidate fixes V2 Dave Chinner
2011-01-25  8:50 ` [PATCH 1/8] xfs: fix log ticket leak on forced shutdown Dave Chinner
2011-01-26 21:22   ` Alex Elder
2011-01-25  8:50 ` [PATCH 2/8] xfs: fix efi item " Dave Chinner
2011-01-25 23:53   ` Christoph Hellwig
2011-01-27  0:35     ` Dave Chinner
2011-01-26 21:22   ` Alex Elder
2011-01-25  8:50 ` [PATCH 3/8] xfs: speculative delayed allocation uses rounddown_power_of_2 badly Dave Chinner
2011-01-26 21:22   ` Alex Elder
2011-01-25  8:50 ` [PATCH 4/8] xfs: limit extent length for allocation to AG size Dave Chinner
2011-01-26 21:22   ` Alex Elder
2011-01-27  0:38     ` Dave Chinner [this message]
2011-01-25  8:50 ` [PATCH 5/8] xfs: prevent extsize alignment from exceeding maximum extent size Dave Chinner
2011-01-25  9:49   ` Christoph Hellwig
2011-01-26 21:22   ` Alex Elder
2011-01-27  0:50     ` Dave Chinner
2011-01-25  8:50 ` [PATCH 6/8] xfs: limit extsize to size of AGs and/or MAXEXTLEN Dave Chinner
2011-01-26 21:23   ` Alex Elder
2011-01-25  8:50 ` [PATCH 7/8] xfs: handle CIl transaction commit failures correctly Dave Chinner
2011-01-25  9:53   ` Christoph Hellwig
2011-01-26 21:23   ` Alex Elder
2011-01-25  8:50 ` [PATCH 8/8] xfs: fix dquot shaker deadlock Dave Chinner
2011-01-25  9:52   ` Christoph Hellwig
2011-01-27  1:54     ` Dave Chinner
2011-01-27  2:24       ` Dave Chinner
2011-01-26 21:23   ` Alex Elder
2011-01-25  9:20 ` [PATCH 0/8] xfs: 2.6.38-rc candidate fixes V2 Christoph Hellwig
2011-01-26 21:23 ` Alex Elder
2011-01-27  3:53 [PATCH 0/8] xfs: candidate 2.6.38-rc fixes V3 Dave Chinner
2011-01-27  3:53 ` [PATCH 4/8] xfs: limit extent length for allocation to AG size Dave Chinner

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=20110127003851.GC21311@dastard \
    --to=david@fromorbit.com \
    --cc=aelder@sgi.com \
    --cc=xfs@oss.sgi.com \
    /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.