Re: [PATCH] scsi: core: only re-run queue in scsi_end_request() if device queue is busy

[Jens Axboe <axboe@kernel.dk>]

On 11/17/19 5:18 PM, Damien Le Moal wrote:
> On 2019/11/17 17:08, Ming Lei wrote:
>> Now the requeue queue is run in scsi_end_request() unconditionally if both
>> target queue and host queue is ready. We should have re-run request queue
>> only after this device queue becomes busy for restarting this LUN only.
>>
>> Recently Long Li reported that cost of run queue may be very heavy in
>> case of high queue depth. So improve this situation by only running
>> requesut queue when this LUN is busy.
> 
> s/requesut/request
> 
> Also, shouldn't this patch have the tag:
> 
> Reported-by: Long Li <longli@microsoft.com>
> 
> ?
> 
> Another remark is that Long's approach is generic to the block layer
> while your patch here is scsi specific. I wonder if the same problem
> cannot happen with other drivers too ?

The block layer is just doing what it's told, and I doubt many drivers
would have the crazy kind of re-run logic that the SCSI midlayer does.
As far as I'm concerned, the fix belongs on the SCSI side of things
instead of being papered over on the block side.

-- 
Jens Axboe