public inbox for linux-xfs@vger.kernel.org
 help / color / mirror / Atom feed
From: Dave Chinner <david@fromorbit.com>
To: Christoph Hellwig <hch@infradead.org>
Cc: xfs@oss.sgi.com
Subject: Re: [PATCH 10/14] xfs: convert grant head manipulations to lockless algorithm
Date: Thu, 2 Dec 2010 13:11:30 +1100	[thread overview]
Message-ID: <20101202021130.GU16922@dastard> (raw)
In-Reply-To: <20101201131513.GB22455@infradead.org>

On Wed, Dec 01, 2010 at 08:15:13AM -0500, Christoph Hellwig wrote:
> On Mon, Nov 29, 2010 at 12:38:28PM +1100, Dave Chinner wrote:
> > From: Dave Chinner <dchinner@redhat.com>
> > 
> > The only thing that the grant lock remains to protect is the grant head
> > manipulations when adding or removing space from the log. These calculations
> > are already based on atomic variables, so we can already update them safely
> > without locks. However, the grant head manpulations require atomic multi-step
> > calculations to be executed, which the algorithms currently don't allow.
> > 
> > To make these multi-step calculations atomic, convert the algorithms to
> > compare-and-exchange loops on the atomic variables. That is, we sample the old
> > value, perform the calculation and use atomic64_cmpxchg() to attempt to update
> > the head with the new value. If the head has not changed since we sampled it,
> > it will succeed and we are done. Otherwise, we rerun the calculation again from
> > a new sample of the head.
> > 
> > This allows us to remove the grant lock from around all the grant head space
> > manipulations, and that effectively removes the grant lock from the log
> > completely.
> > 
> > Signed-off-by: Dave Chinner <dchinner@redhat.com>
....
> > @@ -3478,11 +3485,18 @@ xlog_verify_dest_ptr(
> >  		xlog_panic("xlog_verify_dest_ptr: invalid ptr");
> >  }
> >  
> > +/*
> > + * XXX: because we cannot atomically sample both the reserve and write heads,
> > + * we cannot verify them reliably as they may be sampled in the middle of
> > + * racing modifications. Hence just taking snapshots of the heads can give an
> > + * incorrect view of the state of log. Hence just disable this check for now.
> > + */
> >  STATIC void
> >  xlog_verify_grant_head(
> 
> I can't see any way to keep this check with the atomic reserve/write
> heads, so we might as well remove it entirely.

Ok, will do.

Cheers,

Dave.
-- 
Dave Chinner
david@fromorbit.com

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

  reply	other threads:[~2010-12-02  2:09 UTC|newest]

Thread overview: 42+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-11-29  1:38 [PATCH 0/14] xfs: grant lock scaling and removal V2 Dave Chinner
2010-11-29  1:38 ` [PATCH 01/14] xfs: convert log grant ticket queues to list heads Dave Chinner
2010-11-30 22:59   ` Christoph Hellwig
2010-11-29  1:38 ` [PATCH 02/14] xfs: clean up log space grant functions Dave Chinner
2010-12-01 12:30   ` Christoph Hellwig
2010-12-02  1:48     ` Dave Chinner
2010-12-02 11:40       ` Christoph Hellwig
2010-12-03  6:45         ` Dave Chinner
2010-11-29  1:38 ` [PATCH 03/14] xfs: convert log grant heads to LSN notation Dave Chinner
2010-12-01 12:42   ` Christoph Hellwig
2010-12-02  1:49     ` Dave Chinner
2010-12-01 13:05   ` Christoph Hellwig
2010-12-02  2:01     ` Dave Chinner
2010-12-02 11:47       ` Christoph Hellwig
2010-11-29  1:38 ` [PATCH 04/14] xfs: use wait queues directly for log grant queues Dave Chinner
2010-12-01 12:34   ` Christoph Hellwig
2010-12-02  2:02     ` Dave Chinner
2010-11-29  1:38 ` [PATCH 05/14] xfs: make AIL tail pushing independent of the grant lock Dave Chinner
2010-12-01 12:45   ` Christoph Hellwig
2010-12-02  2:04     ` Dave Chinner
2010-11-29  1:38 ` [PATCH 06/14] xfs: convert l_last_sync_lsn to an atomic variable Dave Chinner
2010-12-01 12:54   ` Christoph Hellwig
2010-11-29  1:38 ` [PATCH 07/14] xfs: convert l_tail_lsn " Dave Chinner
2010-12-01 12:56   ` Christoph Hellwig
2010-11-29  1:38 ` [PATCH 08/14] xfs: convert log grant heads to atomic variables Dave Chinner
2010-12-01 12:59   ` Christoph Hellwig
2010-12-02  2:04     ` Dave Chinner
2010-11-29  1:38 ` [PATCH 09/14] xfs: introduce new locks for the log grant ticket wait queues Dave Chinner
2010-12-01 13:12   ` Christoph Hellwig
2010-12-02  2:10     ` Dave Chinner
2010-12-02 11:48       ` Christoph Hellwig
2010-11-29  1:38 ` [PATCH 10/14] xfs: convert grant head manipulations to lockless algorithm Dave Chinner
2010-12-01 13:15   ` Christoph Hellwig
2010-12-02  2:11     ` Dave Chinner [this message]
2010-11-29  1:38 ` [PATCH 11/14] xfs: remove log grant lock Dave Chinner
2010-12-01 13:15   ` Christoph Hellwig
2010-11-29  1:38 ` [PATCH 12/14] xfs: kill useless spinlock_destroy macro Dave Chinner
2010-12-01 13:19   ` Christoph Hellwig
2010-11-29  1:38 ` [PATCH 13/14] xfs: replace use of sv_t with waitqueues in the log Dave Chinner
2010-12-01 13:20   ` Christoph Hellwig
2010-11-29  1:38 ` [PATCH 14/14] xfs: remove sv wrappers Dave Chinner
2010-12-01 13:20   ` Christoph Hellwig

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=20101202021130.GU16922@dastard \
    --to=david@fromorbit.com \
    --cc=hch@infradead.org \
    --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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox