Yu Chao e76eebee70 f2fs: optimize fs_lock for better performance
There is a performance problem: when all sbi->fs_lock are holded, then
all the following threads may get the same next_lock value from sbi->next_lock_num
in function mutex_lock_op, and wait for the same lock(fs_lock[next_lock]),
it may cause performance reduce.
So we move the sbi->next_lock_num++ before getting lock, this will average the
following threads if all sbi->fs_lock are holded.

v1-->v2:
	Drop the needless spin_lock as Jaegeuk suggested.

Suggested-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
Signed-off-by: Yu Chao <chao2.yu@samsung.com>
Signed-off-by: Gu Zheng <guz.fnst@cn.fujitsu.com>
Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2013-09-24 17:45:48 +09:00
..
2013-06-29 12:56:55 +04:00
2013-07-05 18:59:33 +04:00
2013-06-29 12:56:46 +04:00
2013-08-12 15:22:43 -05:00
2013-06-29 12:56:53 +04:00
2013-09-16 19:17:24 -04:00
2013-09-07 10:38:29 +02:00
2013-06-29 12:56:47 +04:00
2013-09-16 19:17:24 -04:00
2013-06-29 12:56:32 +04:00
2013-06-29 12:56:38 +04:00
2013-06-29 12:56:39 +04:00
2013-06-29 12:56:29 +04:00
2013-09-12 16:13:41 -07:00
2013-06-29 12:57:04 +04:00
2013-07-10 18:11:34 -07:00
2013-07-10 18:11:34 -07:00
2013-04-29 15:40:23 -04:00
2013-09-13 23:06:40 -04:00
2013-06-29 12:57:05 +04:00
2013-03-03 23:00:23 -05:00
2013-09-10 18:56:31 -04:00
2013-09-13 23:06:40 -04:00
2013-02-22 23:31:31 -05:00
2013-04-17 13:25:09 +01:00
2013-05-07 20:16:25 -07:00
2013-05-31 15:16:33 -04:00
2013-07-30 11:53:12 -04:00
2013-06-29 12:57:05 +04:00
2013-09-10 18:56:32 -04:00
2013-05-29 12:57:34 -07:00