linux/block
Jens Axboe a993800655 cfq-iosched: fix sequential write regression
We have a 10-15% performance regression for sequential writes on TCQ/NCQ
enabled drives in 2.6.21-rcX after the CFQ update went in.  It has been
reported by Valerie Clement <valerie.clement@bull.net> and the Intel
testing folks.  The regression is because of CFQ's now more aggressive
queue control, limiting the depth available to the device.

This patches fixes that regression by allowing a greater depth when only
one queue is busy.  It has been tested to not impact sync-vs-async
workloads too much - we still do a lot better than 2.6.20.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-04-20 22:56:29 -07:00
..
as-iosched.c [PATCH] Allow as-iosched to be unloaded 2006-12-13 13:25:18 +01:00
blktrace.c [PATCH] mark struct file_operations const 3 2007-02-12 09:48:45 -08:00
cfq-iosched.c cfq-iosched: fix sequential write regression 2007-04-20 22:56:29 -07:00
deadline-iosched.c [BLOCK] Cleanup unused variable passing 2006-12-01 10:42:33 +01:00
elevator.c make elv_register() output atomic 2007-03-27 08:53:04 +02:00
genhd.c [PATCH] remove protection of LANANA-reserved majors 2007-04-04 21:12:47 -07:00
ioctl.c [PATCH] lockdep: annotate BLKPG_DEL_PARTITION 2007-02-20 17:10:16 -08:00
Kconfig [PATCH] Centralise definitions of sector_t and blkcnt_t 2006-12-04 19:41:15 -08:00
Kconfig.iosched update I/O sched Kconfig help texts - CFQ is now default, not AS. 2007-02-17 20:08:22 +01:00
ll_rw_blk.c block: blk_max_pfn is somtimes wrong 2007-03-27 08:52:47 +02:00
Makefile [PATCH] BLOCK: Make it possible to disable the block layer [try #6] 2006-09-30 20:52:31 +02:00
noop-iosched.c [BLOCK] Cleanup unused variable passing 2006-12-01 10:42:33 +01:00
scsi_ioctl.c [PATCH] Fix SG_IO timeout jiffy conversion 2007-01-29 20:32:03 -08:00