Re: [PATCH RESEND v5 3/7] blk-mq: add a new queue sysfs attribute async_depth

[Bart Van Assche]

On 11/15/25 7:52 PM, Yu Kuai wrote:
> +static void blk_mq_limit_depth(struct blk_mq_alloc_data *data)
> +{
> +	struct elevator_mq_ops *ops;
> +
> +	/* If elevator is none, don't limit requests */

Nobody calls an I/O scheduler an elevator anymore. So I propose to
change "elevator is none" into "no I/O scheduler has been configured".

> +	/*
> +	 * Flush/passthrough requests are special and go directly to the
> +	 * dispatch list, they don't have limit.
> +	 */
"they don't have a limit" -> "are not subject to the async_depth limit".

> +	/*
> +	 * By default, sync requests have no limit, and async requests is
> +	 * limited to async_depth.
> +	 */

"is" -> "are"

> -		/*
> -		 * All requests use scheduler tags when an I/O scheduler is
> -		 * enabled for the queue.
> -		 */
> -		data->rq_flags |= RQF_SCHED_TAGS;

Why has the above comment been removed? I think that it is useful.

Additionally, please split this patch into two patches: a first patch
that introduces the function blk_mq_limit_depth() and a second patch
with the remaining changes from this patch.

Thanks,

Bart.