loop: improve loop aio perf by IOCB

From:		Ming Lei <ming.lei-AT-redhat.com>
To:		Jens Axboe <axboe-AT-kernel.dk>, linux-block-AT-vger.kernel.org
Subject:		[PATCH V2 0/5] loop: improve loop aio perf by IOCB_NOWAIT
Date:		Fri, 14 Mar 2025 10:11:40 +0800
Message-ID:		<20250314021148.3081954-1-ming.lei@redhat.com>
Cc:		Christoph Hellwig <hch-AT-lst.de>, Jooyung Han <jooyung-AT-google.com>, Mike Snitzer <snitzer-AT-kernel.org>, zkabelac-AT-redhat.com, dm-devel-AT-lists.linux.dev, Alasdair Kergon <agk-AT-redhat.com>, Ming Lei <ming.lei-AT-redhat.com>
Archive-link:		Article

Hello Jens,

This patchset improves loop aio perf by using IOCB_NOWAIT for avoiding to queue aio
command to workqueue context, meantime refactor lo_rw_aio() a bit.

In my test VM, loop disk perf becomes very close to perf of the backing block
device(nvme/mq virtio-scsi).

And Mikulas verified that this way can improve 12jobs sequential rw io by
~5X, and basically solve the reported problem together with loop MQ change.

https://lore.kernel.org/linux-block/a8e5c76a-231f-07d1-a3...

The loop MQ change will be posted as standalone patch, because it needs
losetup change.


Thanks,
Ming

V2:
	- patch style fix & cleanup (Christoph)
	- fix randwrite perf regression on sparse backing file
	- drop MQ change

Ming Lei (5):
  loop: simplify do_req_filebacked()
  loop: cleanup lo_rw_aio()
  loop: move command blkcg/memcg initialization into loop_queue_work
  loop: try to handle loop aio command via NOWAIT IO first
  loop: add hint for handling aio via IOCB_NOWAIT

 drivers/block/loop.c | 232 ++++++++++++++++++++++++++++++++++---------
 1 file changed, 186 insertions(+), 46 deletions(-)

-- 
2.47.0

loop: improve loop aio perf by IOCB_NOWAIT