Re: [PATCH for-next 2/2] nvme: optimise io_uring passthrough completion

[Pavel Begunkov <asml.silence@gmail.com>]

On 5/17/23 08:23, Christoph Hellwig wrote:
> On Mon, May 15, 2023 at 01:54:43PM +0100, Pavel Begunkov wrote:
>> Use IOU_F_TWQ_LAZY_WAKE via iou_cmd_exec_in_task_lazy() for passthrough
>> commands completion. It further delays the execution of task_work for
>> DEFER_TASKRUN until there are enough of task_work items queued to meet
>> the waiting criteria, which reduces the number of wake ups we issue.
> 
> Why wouldn't you just do that unconditionally for
> io_uring_cmd_complete_in_task?

1) ublk does secondary batching and so may produce multiple cqes,
that's not supported. I believe Ming sent patches removing it,
but I'd rather not deal with conflicts for now.

2) Some users may have dependencies b/w requests, i.e. a request
will only complete when another request's task_work is executed.

3) There might be use cases when you don't wont it to be delayed,
IO retries would be a good example. I wouldn't also use it for
control paths like ublk_ctrl_uring_cmd.

Let's better keep io_uring_cmd_complete_in_task() as the default
option for the interface.

-- 
Pavel Begunkov