Christoph Hellwig 474fce0675 xfs: replace i_flock with a sleeping bitlock
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 that uses
a bit waitqueue for the rare sleeping path.  This primarily is a
tradeoff between a much smaller inode and a faster non-blocking
path vs faster wakeups, and we are much better off with the former.

A small downside is that we will lose lockdep checking for i_flock, but
given that it's always taken inside the ilock that should be acceptable.

Note that for example the inode writeback locking is implemented in a
very similar way.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Alex Elder <aelder@sgi.com>
Signed-off-by: Ben Myers <bpm@sgi.com>
2012-01-17 15:06:45 -06:00
..
2012-01-03 22:55:04 -05:00
2012-01-03 22:54:53 -05:00
2012-01-03 22:54:53 -05:00
2012-01-03 22:54:07 -05:00
2012-01-09 16:36:12 -05:00
2012-01-03 22:54:57 -05:00
2012-01-03 22:55:10 -05:00
2012-01-03 22:54:54 -05:00
2012-01-09 10:48:11 -05:00
2012-01-10 13:45:22 -08:00
2012-01-10 13:45:22 -08:00
2012-01-03 22:55:01 -05:00
2012-01-03 22:55:07 -05:00
2012-01-10 13:45:22 -08:00
2012-01-03 22:55:03 -05:00
2012-01-03 22:55:11 -05:00
2012-01-03 22:54:54 -05:00
2012-01-03 22:54:07 -05:00
2012-01-10 13:06:32 -05:00
2012-01-12 20:13:04 -08:00
2012-01-03 22:52:39 -05:00
2012-01-05 15:40:12 -08:00
2012-01-03 22:54:07 -05:00
2012-01-03 22:52:40 -05:00
2012-01-03 22:54:07 -05:00
2012-01-03 22:53:07 -05:00
2012-01-03 22:54:07 -05:00
2012-01-03 22:52:40 -05:00