Re: [PATCH] dm: Change the default value of rq_affinity from 0 into 1

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 




On Mon, 15 Apr 2024, Bart Van Assche wrote:

> The following behavior is inconsistent:
> * For request-based dm queues the default value of rq_affinity is 1.
> * For bio-based dm queues the default value of rq_affinity is 0.
> 
> The default value for request-based dm queues is 1 because of the following
> code in blk_mq_init_allocated_queue():
> 
>     q->queue_flags |= QUEUE_FLAG_MQ_DEFAULT;
> 
> >From <linux/blkdev.h>:
> 
>     #define QUEUE_FLAG_MQ_DEFAULT ((1UL << QUEUE_FLAG_IO_STAT) |	\
> 				   (1UL << QUEUE_FLAG_SAME_COMP) |	\
> 				   (1UL << QUEUE_FLAG_NOWAIT))
> 
> The default value of rq_affinity for bio-based dm queues is 0 because the
> dm alloc_dev() function does not set any of the QUEUE_FLAG_SAME_* flags. I
> think the different default values are the result of an oversight when
> blk-mq support was added in the device mapper code. Hence this patch that
> changes the default value of rq_affinity from 0 to 1 for bio-based dm
> queues.
> 
> This patch reduces the boot time from 12.23 to 12.20 seconds on my test

Are you sure that this is not jitter?

I am wondering how should QUEUE_FLAG_SAME_COMP work for bio-based
devices.

I grepped the kernel for QUEUE_FLAG_SAME_COMP and it is tested in 
block/blk-mq.c in blk_mq_complete_need_ipi (this code path is taken only 
for request-based devices) and in block/blk-sysfs.c in 
queue_rq_affinity_show (this just displays the value in sysfs). There are 
no other places where QUEUE_FLAG_SAME_COMP is tested, so I don't see what 
effect is it supposed to have.

Mikulas


> setup, a Pixel 2023 development board. The storage controller on that test
> setup supports a single completion interrupt and hence benefits from
> redirecting I/O completions to a CPU core that is closer to the submitter.
> 
> Cc: Mikulas Patocka <mpatocka@xxxxxxxxxx>
> Cc: Eric Biggers <ebiggers@xxxxxxxxxx>
> Cc: Jaegeuk Kim <jaegeuk@xxxxxxxxxx>
> Cc: Daniel Lee <chullee@xxxxxxxxxx>
> Cc: stable@xxxxxxxxxxxxxxx
> Fixes: bfebd1cdb497 ("dm: add full blk-mq support to request-based DM")
> Signed-off-by: Bart Van Assche <bvanassche@xxxxxxx>
> ---
>  drivers/md/dm.c | 1 +
>  1 file changed, 1 insertion(+)
> 
> diff --git a/drivers/md/dm.c b/drivers/md/dm.c
> index 56aa2a8b9d71..9af216c11cf7 100644
> --- a/drivers/md/dm.c
> +++ b/drivers/md/dm.c
> @@ -2106,6 +2106,7 @@ static struct mapped_device *alloc_dev(int minor)
>  	if (IS_ERR(md->disk))
>  		goto bad;
>  	md->queue = md->disk->queue;
> +	blk_queue_flag_set(QUEUE_FLAG_SAME_COMP, md->queue);
>  
>  	init_waitqueue_head(&md->wait);
>  	INIT_WORK(&md->work, dm_wq_work);
> 





[Index of Archives]     [Linux Kernel]     [Kernel Development Newbies]     [Linux USB Devel]     [Video for Linux]     [Linux Audio Users]     [Yosemite Hiking]     [Linux Kernel]     [Linux SCSI]

  Powered by Linux