xfs
[Top] [All Lists]

Re: [PATCH 3/4] xfs: exact busy extent tracking

To: Christoph Hellwig <hch@xxxxxxxxxxxxx>
Subject: Re: [PATCH 3/4] xfs: exact busy extent tracking
From: Dave Chinner <david@xxxxxxxxxxxxx>
Date: Fri, 29 Apr 2011 11:10:35 +1000
Cc: xfs@xxxxxxxxxxx
In-reply-to: <20110424190657.064969622@xxxxxxxxxxxxxxxxxxxxxx>
References: <20110424190613.404786382@xxxxxxxxxxxxxxxxxxxxxx> <20110424190657.064969622@xxxxxxxxxxxxxxxxxxxxxx>
User-agent: Mutt/1.5.20 (2009-06-14)
On Sun, Apr 24, 2011 at 03:06:16PM -0400, Christoph Hellwig wrote:
> Update the extent tree in case we have to reuse a busy extent, so that it
> always is kept uptodate.  This is done by replacing the busy list searches
> with a new xfs_alloc_busy_reuse helper, which updates the busy extent tree
> in case of a reuse.  This allows us to allow reusing metadata extents
> unconditionally, and thus avoid log forces especially for allocation btree
> blocks.

I'd add one comment to this - that this returns to the old way of
clearing busy extents by issuing a sync log force with the AGF
locked. This can cause additional allocation latency, but should be
rare given the occurrence of of metadata->data reallocation.

> Signed-off-by: Christoph Hellwig <hch@xxxxxx>
> Reviewed-by: Alex Elder <aelder@xxxxxxx>

Otherwise,

Reviewed-by: Dave Chinner <dchinner@xxxxxxxxxx>

-- 
Dave Chinner
david@xxxxxxxxxxxxx

<Prev in Thread] Current Thread [Next in Thread>