Files
linux/fs
Jens Axboe 8c052fb300 iomap: support IOCB_DIO_CALLER_COMP
If IOCB_DIO_CALLER_COMP is set, utilize that to set kiocb->dio_complete
handler and data for that callback. Rather than punt the completion to a
workqueue, we pass back the handler and data to the issuer and will get
a callback from a safe task context.

Using the following fio job to randomly dio write 4k blocks at
queue depths of 1..16:

fio --name=dio-write --filename=/data1/file --time_based=1 \
--runtime=10 --bs=4096 --rw=randwrite --norandommap --buffered=0 \
--cpus_allowed=4 --ioengine=io_uring --iodepth=$depth

shows the following results before and after this patch:

	Stock	Patched		Diff
=======================================
QD1	155K	162K		+ 4.5%
QD2	290K	313K		+ 7.9%
QD4	533K	597K		+12.0%
QD8	604K	827K		+36.9%
QD16	615K	845K		+37.4%

which shows nice wins all around. If we factored in per-IOP efficiency,
the wins look even nicer. This becomes apparent as queue depth rises,
as the offloaded workqueue completions runs out of steam.

Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2023-08-01 17:32:49 -06:00
..
2023-05-24 08:42:16 -06:00
2023-05-24 08:42:16 -06:00
2023-08-01 17:32:49 -06:00
2023-03-14 12:56:30 -06:00
2023-06-05 16:50:30 +02:00
2023-06-15 13:37:53 +02:00
2023-03-30 08:51:48 +02:00
2023-06-28 20:35:21 -07:00
2023-05-17 09:16:59 +02:00
2023-01-19 09:24:30 +01:00
2023-07-04 10:20:29 +02:00
2023-05-19 04:30:22 +02:00
2023-05-19 04:30:22 +02:00
2023-03-06 09:59:20 +01:00