blk-mq: use the I/O scheduler for writes from the flush state machine

Send write requests issued by the flush state machine through the normal
I/O submission path including the I/O scheduler (if present) so that I/O
scheduler policies are applied to writes with the FUA flag set.

Separate the I/O scheduler members from the flush members in struct
request since now a request may pass through both an I/O scheduler
and the flush machinery.

Note that the actual flush requests, which have no bio attached to the
request still bypass the I/O schedulers.

Signed-off-by: Bart Van Assche <bvanassche@acm.org>
[hch: rebased]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Link: https://lore.kernel.org/r/20230519044050.107790-5-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This commit is contained in:
Bart Van Assche 2023-05-19 06:40:47 +02:00 коммит произвёл Jens Axboe
Родитель 360f264834
Коммит be4c427809
2 изменённых файлов: 12 добавлений и 17 удалений

Просмотреть файл

@ -458,7 +458,7 @@ static struct request *__blk_mq_alloc_requests(struct blk_mq_alloc_data *data)
* Flush/passthrough requests are special and go directly to the
* dispatch list.
*/
if (!op_is_flush(data->cmd_flags) &&
if ((data->cmd_flags & REQ_OP_MASK) != REQ_OP_FLUSH &&
!blk_op_is_passthrough(data->cmd_flags)) {
struct elevator_mq_ops *ops = &q->elevator->type->ops;
@ -2497,7 +2497,7 @@ static void blk_mq_insert_request(struct request *rq, blk_insert_t flags)
* dispatch it given we prioritize requests in hctx->dispatch.
*/
blk_mq_request_bypass_insert(rq, flags);
} else if (rq->rq_flags & RQF_FLUSH_SEQ) {
} else if (req_op(rq) == REQ_OP_FLUSH) {
/*
* Firstly normal IO request is inserted to scheduler queue or
* sw queue, meantime we add flush request to dispatch queue(

Просмотреть файл

@ -169,25 +169,20 @@ struct request {
void *completion_data;
};
/*
* Three pointers are available for the IO schedulers, if they need
* more they have to dynamically allocate it. Flush requests are
* never put on the IO scheduler. So let the flush fields share
* space with the elevator data.
* more they have to dynamically allocate it.
*/
union {
struct {
struct io_cq *icq;
void *priv[2];
} elv;
struct {
struct io_cq *icq;
void *priv[2];
} elv;
struct {
unsigned int seq;
struct list_head list;
rq_end_io_fn *saved_end_io;
} flush;
};
struct {
unsigned int seq;
struct list_head list;
rq_end_io_fn *saved_end_io;
} flush;
union {
struct __call_single_data csd;