| To: | Alex Elder <aelder@xxxxxxx> |
|---|---|
| Subject: | Re: [PATCH 2/6] xfs: do not immediately reuse busy extent ranges |
| From: | Christoph Hellwig <hch@xxxxxxxxxxxxx> |
| Date: | Mon, 28 Mar 2011 08:07:57 -0400 |
| Cc: | Christoph Hellwig <hch@xxxxxxxxxxxxx>, xfs@xxxxxxxxxxx |
| In-reply-to: | <1301086999.2537.688.camel@doink> |
| References: | <20110322195550.260682574@xxxxxxxxxxxxxxxxxxxxxx> <20110322200137.474878707@xxxxxxxxxxxxxxxxxxxxxx> <1301086999.2537.688.camel@doink> |
| User-agent: | Mutt/1.5.21 (2010-09-15) |
On Fri, Mar 25, 2011 at 04:03:19PM -0500, Alex Elder wrote: > > + * Can be trimmed to: > > + * +-------+ OR +-------+ > > + * fbno fend fbno fend > > + * > > + * We prefer the lower bno extent because the next > > + * allocation for this inode will use "end" as the > > + * target for first block. If the busy segment has > > ...will use the updated value of fend as the target... I've replaced all these comments based on the text you replied to the last round (finally..) |
| Previous by Date: | Re: [PATCH 1/6] xfs: optimize AGFL refills, Christoph Hellwig |
|---|---|
| Next by Date: | Re: [PATCH 3/6] xfs: exact busy extent tracking, Christoph Hellwig |
| Previous by Thread: | Re: [PATCH 2/6] xfs: do not immediately reuse busy extent ranges, Alex Elder |
| Next by Thread: | [PATCH 3/6] xfs: exact busy extent tracking, Christoph Hellwig |
| Indexes: | [Date] [Thread] [Top] [All Lists] |