Search String: Display: Description: Sort:

Results:

References: [ +subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*\[PATCH\]\s+xfs\:\s+Non\-blocking\s+inode\s+locking\s+in\s+IO\s+completion\s*$/: 5 ]

Total 5 documents matching your query.

1. [PATCH] xfs: Non-blocking inode locking in IO completion (score: 1)
Author: Dave Chinner <david@xxxxxxxxxxxxx>
Date: Wed, 17 Feb 2010 16:36:29 +1100
The introduction of barriers to DM loop devices (e.g. dm-crypt) has created a new IO order completion dependency that XFS does not handle. That is, the completion of log IOs (which have barriers) in
/archives/xfs/2010-02/msg00280.html (11,898 bytes)

2. Re: [PATCH] xfs: Non-blocking inode locking in IO completion (score: 1)
Author: Christoph Hellwig <hch@xxxxxxxxxxxxx>
Date: Wed, 17 Feb 2010 14:29:38 -0500
I don't think dm belongs into the picture here at all. The problem is simply with the loop device, which sits below dm-crypt in the bugzilla reports. The loop device in SuSE (and for a short time in
/archives/xfs/2010-02/msg00286.html (8,567 bytes)

3. Re: [PATCH] xfs: Non-blocking inode locking in IO completion (score: 1)
Author: Dave Chinner <david@xxxxxxxxxxxxx>
Date: Thu, 18 Feb 2010 08:13:12 +1100
Fair point. I'll change the description to be more accurate. I thought about using queue_delayed_work(), but then the change became much bigger and has other side effects like increasing the size of
/archives/xfs/2010-02/msg00297.html (9,179 bytes)

4. Re: [PATCH] xfs: Non-blocking inode locking in IO completion (score: 1)
Author: Christoph Hellwig <hch@xxxxxxxxxxxxx>
Date: Thu, 18 Feb 2010 07:35:13 -0500
Yes, now that the normal work struct and the delayed work struct are different it would be a pain, agreed.
/archives/xfs/2010-02/msg00308.html (8,536 bytes)

5. Re: [PATCH] xfs: Non-blocking inode locking in IO completion (score: 1)
Author: Alex Elder <aelder@xxxxxxx>
Date: Thu, 25 Feb 2010 14:06:46 -0600
One comment, below . . . It's not a problem now (and may never be), but it's conceivable error could have been set to the return value from xfs_iomap_write_unwritten() to have value EAGAIN. It might
/archives/xfs/2010-02/msg00337.html (9,540 bytes)


This search system is powered by Namazu