Re: [PATCH V7 4/6] blk-mq: introduce .get_budget and .put_budget in blk_mq_ops

[Jens Axboe <axboe@kernel.dk>]

On 10/13/2017 10:22 AM, Ming Lei wrote:
> On Fri, Oct 13, 2017 at 10:20:01AM -0600, Jens Axboe wrote:
>> On 10/13/2017 10:17 AM, Ming Lei wrote:
>>> On Fri, Oct 13, 2017 at 08:44:23AM -0600, Jens Axboe wrote:
>>>> On 10/12/2017 06:19 PM, Ming Lei wrote:
>>>>> On Thu, Oct 12, 2017 at 12:46:24PM -0600, Jens Axboe wrote:
>>>>>> On 10/12/2017 12:37 PM, Ming Lei wrote:
>>>>>>> For SCSI devices, there is often per-request-queue depth, which need
>>>>>>> to be respected before queuing one request.
>>>>>>>
>>>>>>> The current blk-mq always dequeues one request first, then calls .queue_rq()
>>>>>>> to dispatch the request to lld. One obvious issue of this way is that I/O
>>>>>>> merge may not be good, because when the per-request-queue depth can't be
>>>>>>> respected,  .queue_rq() has to return BLK_STS_RESOURCE, then this request
>>>>>>> has to staty in hctx->dispatch list, and never got chance to participate
>>>>>>> into I/O merge.
>>>>>>>
>>>>>>> This patch introduces .get_budget and .put_budget callback in blk_mq_ops,
>>>>>>> then we can try to get reserved budget first before dequeuing request.
>>>>>>> Once we can't get budget for queueing I/O, we don't need to dequeue request
>>>>>>> at all, then I/O merge can get improved a lot.
>>>>>>
>>>>>> I can't help but think that it would be cleaner to just be able to
>>>>>> reinsert the request into the scheduler properly, if we fail to
>>>>>> dispatch it. Bart hinted at that earlier as well.
>>>>>
>>>>> Actually when I start to investigate the issue, the 1st thing I tried
>>>>> is to reinsert, but that way is even worse on qla2xxx.
>>>>>
>>>>> Once request is dequeued, the IO merge chance is decreased a lot.
>>>>> With none scheduler, it becomes not possible to merge because
>>>>> we only try to merge over the last 8 requests. With mq-deadline,
>>>>> when one request is reinserted, another request may be dequeued
>>>>> at the same time.
>>>>
>>>> I don't care too much about 'none'. If perfect merging is crucial for
>>>> getting to the performance level you want on the hardware you are using,
>>>> you should not be using 'none'. 'none' will work perfectly fine for NVMe
>>>> etc style devices, where we are not dependent on merging to the same
>>>> extent that we are on other devices.
>>>
>>> We still have some SCSI device, such as qla2xxx, which is 1:1 multi-queue
>>> device, like NVMe, in my test, the big lock of mq-deadline has been
>>> an issue for this kind of device, and none actually is better than
>>> mq-deadline, even though its merge isn't good.
>>
>> Kyber should be able to fill that hole, hopefully.
> 
> Yeah, kyber still uses same IO merge with none, :-)

Doesn't mean it can't be changed... 'none' has to remain with very low
overhead, any extra smarts or logic should be a scheduler thing.

-- 
Jens Axboe