| To: | Christoph Hellwig <hch@xxxxxxxxxxxxx> |
|---|---|
| Subject: | Re: [PATCH 5/5] xfs: use shared ilock mode for direct IO writes by default |
| From: | Mark Tinguely <tinguely@xxxxxxx> |
| Date: | Tue, 03 Apr 2012 12:01:20 -0500 |
| Cc: | xfs@xxxxxxxxxxx |
| In-reply-to: | <20120327143826.969369776@xxxxxxxxxxxxxxxxxxxxxx> |
| References: | <20120327143445.196524266@xxxxxxxxxxxxxxxxxxxxxx> <20120327143826.969369776@xxxxxxxxxxxxxxxxxxxxxx> |
| User-agent: | Mozilla/5.0 (X11; FreeBSD amd64; rv:9.0) Gecko/20120122 Thunderbird/9.0 |
On 03/27/12 09:34, Christoph Hellwig wrote: From: Dave Chinner<dchinner@xxxxxxxxxx> For the direct IO write path, we only really need the ilock to be taken in exclusive mode during IO submission if we need to do extent allocation instaled of all the time. Change the block mapping code to take the ilock in shared mode for the initial block mapping, and only retake it exclusively when we actually have to perform extent allocations. We were already dropping the ilock for the transaction allocation, so this doesn't introduce new race windows. Based on an earlier patch from Dave Chinner. Signed-off-by: Christoph Hellwig<hch@xxxxxx> Looks good. Reviewed-by: Mark Tinguely <tinguely@xxxxxxx> |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Re: [ANNOUNCE] XFS Developers meeting in San Francisco, April 3rd, Christoph Hellwig |
|---|---|
| Next by Date: | Re: Corrupt xfs on USB HDD : sub-optimal xfs_repair, Eric Sandeen |
| Previous by Thread: | The Wall Streert Journal Asia Newspaper " Discount 74% /For New Member 2012, Nunoun, Noppawan |
| Next by Thread: | Re: XFS: Assertion failed: bp->b_bn != XFS_BUF_DADDR_NULL, file: fs/xfs/xfs_buf.c, line: 598, RafaÅ Kupka |
| Indexes: | [Date] [Thread] [Top] [All Lists] |