Mail Archive Search: <+subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*\[PATCH\s+2\/4\]\s+xfs\:\s+replace\s+i_flock\s+with\s+a\s+sleeping\s+bitlock\s*$/>

Results:

References: [ +subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*\[PATCH\s+2\/4\]\s+xfs\:\s+replace\s+i_flock\s+with\s+a\s+sleeping\s+bitlock\s*$/: 5 ]

Total 5 documents matching your query.

1. [PATCH 2/4] xfs: replace i_flock with a sleeping bitlock (score: 1): Author: Christoph Hellwig <hch@xxxxxxxxxxxxx>; Date: Tue, 18 Oct 2011 16:13:06 -0400; We almost never block on i_flock, the exception is synchronous inode flushing. Instead of bloating the inode with a 16/24-byte completion that we abuse as a semaphore just implement it as a bitlock t; /archives/xfs/2011-10/msg00362.html (16,811 bytes)
2. Re: [PATCH 2/4] xfs: replace i_flock with a sleeping bitlock (score: 1): Author: Dave Chinner <david@xxxxxxxxxxxxx>; Date: Wed, 19 Oct 2011 11:42:06 +1100; ..... Given that the only way that the inode will become unlocked is for IO to complete, that makes this an IO wait, right? Perhaps this should call io_schedule() in that case? Any reason for leaving; /archives/xfs/2011-10/msg00369.html (11,026 bytes)
3. Re: [PATCH 2/4] xfs: replace i_flock with a sleeping bitlock (score: 1): Author: Christoph Hellwig <hch@xxxxxxxxxxxxx>; Date: Wed, 19 Oct 2011 05:01:06 -0400; It probably should, and would help a bit with our %iowait accounting. The biggie for that is the buffer lock, though. Either we'll need a variant of the semaphore that does io_schedule, which is prob; /archives/xfs/2011-10/msg00373.html (11,303 bytes)
4. [PATCH 2/4] xfs: replace i_flock with a sleeping bitlock (score: 1): Author: Christoph Hellwig <hch@xxxxxxxxxxxxx>; Date: Wed, 19 Oct 2011 14:23:45 -0400; We almost never block on i_flock, the exception is synchronous inode flushing. Instead of bloating the inode with a 16/24-byte completion that we abuse as a semaphore just implement it as a bitlock t; /archives/xfs/2011-10/msg00398.html (17,098 bytes)
5. Re: [PATCH 2/4] xfs: replace i_flock with a sleeping bitlock (score: 1): Author: Alex Elder <aelder@xxxxxxx>; Date: Wed, 26 Oct 2011 16:07:21 -0500; vs faster wakeups Substitute "beeing" -> "being" throughout. There's also one thing I'd like you to check and likely fix, below. Otherwise looks good. Reviewed-by: Alex Elder <aelder@xxxxxxx> . . . i; /archives/xfs/2011-10/msg00467.html (10,818 bytes)

Current List: 1 - 5
Page: [1]