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

[Jens Axboe]

On 9/24/22 5:56 AM, Pankaj Raghav wrote:
>>>> 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.
>>
> 
> Do you want me send a separate patch for this change or you will fold it in
> the existing series?

Probably cleaner as a separate patch, would be great if you could
send one.

-- 
Jens Axboe