Re: [PATCH 1/5] block: enable batched allocation for blk_mq_alloc_request()

From: Jens Axboe <axboe@kernel.dk>
To: Pankaj Raghav <p.raghav@samsung.com>,
	Damien Le Moal <damien.lemoal@opensource.wdc.com>
Cc: linux-block@vger.kernel.org, linux-scsi@vger.kernel.org,
	linux-nvme@lists.infradead.org, joshi.k@samsung.com,
	Pankaj Raghav <pankydev8@gmail.com>,
	Bart Van Assche <bvanassche@acm.org>
Subject: Re: [PATCH 1/5] block: enable batched allocation for blk_mq_alloc_request()
Date: Fri, 23 Sep 2022 14:54:11 -0600	[thread overview]
Message-ID: <2e484ccb-b65b-2991-e259-d3f7be6ad1a6@kernel.dk> (raw)
In-Reply-To: <c7b76fa1-f7e3-3ac6-c92d-35baa0d9a40a@samsung.com>

On 9/23/22 9:13 AM, Pankaj Raghav wrote:
> On 2022-09-23 16:52, Pankaj Raghav wrote:
>> On Thu, Sep 22, 2022 at 12:28:01PM -0600, Jens Axboe wrote:
>>> The filesystem IO path can take advantage of allocating batches of
>>> requests, if the underlying submitter tells the block layer about it
>>> through the blk_plug. For passthrough IO, the exported API is the
>>> blk_mq_alloc_request() helper, and that one does not allow for
>>> request caching.
>>>
>>> Wire up request caching for blk_mq_alloc_request(), which is generally
>>> done without having a bio available upfront.
>>>
>>> Signed-off-by: Jens Axboe <axboe@kernel.dk>
>>> ---
>>>  block/blk-mq.c | 80 ++++++++++++++++++++++++++++++++++++++++++++------
>>>  1 file changed, 71 insertions(+), 9 deletions(-)
>>>
>> I think we need this patch to ensure correct behaviour for passthrough:
>>
>> diff --git a/block/blk-mq.c b/block/blk-mq.c
>> index c11949d66163..840541c1ab40 100644
>> --- a/block/blk-mq.c
>> +++ b/block/blk-mq.c
>> @@ -1213,7 +1213,7 @@ void blk_execute_rq_nowait(struct request *rq, bool at_head)
>>         WARN_ON(!blk_rq_is_passthrough(rq));
>>  
>>         blk_account_io_start(rq);
>> -       if (current->plug)
>> +       if (blk_mq_plug(rq->bio))
>>                 blk_add_rq_to_plug(current->plug, rq);
>>         else
>>                 blk_mq_sched_insert_request(rq, at_head, true, false);
>>
>> As the passthrough path can now support request caching via blk_mq_alloc_request(),
>> and it uses blk_execute_rq_nowait(), bad things can happen at least for zoned
>> devices:
>>
>> static inline struct blk_plug *blk_mq_plug( struct bio *bio)
>> {
>> 	/* Zoned block device write operation case: do not plug the BIO */
>> 	if (bdev_is_zoned(bio->bi_bdev) && op_is_write(bio_op(bio)))
>> 		return NULL;
>> ..
> 
> Thinking more about it, even this will not fix it because op is
> REQ_OP_DRV_OUT if it is a NVMe write for passthrough requests.
> 
> @Damien Should the condition in blk_mq_plug() be changed to:
> 
> static inline struct blk_plug *blk_mq_plug( struct bio *bio)
> {
> 	/* Zoned block device write operation case: do not plug the BIO */
> 	if (bdev_is_zoned(bio->bi_bdev) && !op_is_read(bio_op(bio)))
> 		return NULL;

That looks reasonable to me. It'll prevent plug optimizations even
for passthrough on zoned devices, but that's probably fine.

-- 
Jens Axboe