mirror of
https://github.com/torvalds/linux
synced 2024-09-30 00:10:51 +00:00
d97e594c51
The tags used for an IO scheduler are currently per hctx. As such, when q->nr_hw_queues grows, so does the request queue total IO scheduler tag depth. This may cause problems for SCSI MQ HBAs whose total driver depth is fixed. Ming and Yanhui report higher CPU usage and lower throughput in scenarios where the fixed total driver tag depth is appreciably lower than the total scheduler tag depth: https://lore.kernel.org/linux-block/440dfcfc-1a2c-bd98-1161-cec4d78c6dfc@huawei.com/T/#mc0d6d4f95275a2743d1c8c3e4dc9ff6c9aa3a76b In that scenario, since the scheduler tag is got first, much contention is introduced since a driver tag may not be available after we have got the sched tag. Improve this scenario by introducing request queue-wide tags for when a tagset-wide sbitmap is used. The static sched requests are still allocated per hctx, as requests are initialised per hctx, as in blk_mq_init_request(..., hctx_idx, ...) -> set->ops->init_request(.., hctx_idx, ...). For simplicity of resizing the request queue sbitmap when updating the request queue depth, just init at the max possible size, so we don't need to deal with the possibly with swapping out a new sbitmap for old if we need to grow. Signed-off-by: John Garry <john.garry@huawei.com> Reviewed-by: Ming Lei <ming.lei@redhat.com> Link: https://lore.kernel.org/r/1620907258-30910-3-git-send-email-john.garry@huawei.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
87 lines
2.4 KiB
C
87 lines
2.4 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef BLK_MQ_SCHED_H
|
|
#define BLK_MQ_SCHED_H
|
|
|
|
#include "blk-mq.h"
|
|
#include "blk-mq-tag.h"
|
|
|
|
#define MAX_SCHED_RQ (16 * BLKDEV_MAX_RQ)
|
|
|
|
void blk_mq_sched_assign_ioc(struct request *rq);
|
|
|
|
bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio,
|
|
unsigned int nr_segs, struct request **merged_request);
|
|
bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio,
|
|
unsigned int nr_segs);
|
|
bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq);
|
|
void blk_mq_sched_mark_restart_hctx(struct blk_mq_hw_ctx *hctx);
|
|
void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx);
|
|
|
|
void blk_mq_sched_insert_request(struct request *rq, bool at_head,
|
|
bool run_queue, bool async);
|
|
void blk_mq_sched_insert_requests(struct blk_mq_hw_ctx *hctx,
|
|
struct blk_mq_ctx *ctx,
|
|
struct list_head *list, bool run_queue_async);
|
|
|
|
void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx);
|
|
|
|
int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e);
|
|
void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e);
|
|
void blk_mq_sched_free_requests(struct request_queue *q);
|
|
|
|
static inline bool
|
|
blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio,
|
|
unsigned int nr_segs)
|
|
{
|
|
if (blk_queue_nomerges(q) || !bio_mergeable(bio))
|
|
return false;
|
|
|
|
return __blk_mq_sched_bio_merge(q, bio, nr_segs);
|
|
}
|
|
|
|
static inline bool
|
|
blk_mq_sched_allow_merge(struct request_queue *q, struct request *rq,
|
|
struct bio *bio)
|
|
{
|
|
struct elevator_queue *e = q->elevator;
|
|
|
|
if (e && e->type->ops.allow_merge)
|
|
return e->type->ops.allow_merge(q, rq, bio);
|
|
|
|
return true;
|
|
}
|
|
|
|
static inline void blk_mq_sched_completed_request(struct request *rq, u64 now)
|
|
{
|
|
struct elevator_queue *e = rq->q->elevator;
|
|
|
|
if (e && e->type->ops.completed_request)
|
|
e->type->ops.completed_request(rq, now);
|
|
}
|
|
|
|
static inline void blk_mq_sched_requeue_request(struct request *rq)
|
|
{
|
|
struct request_queue *q = rq->q;
|
|
struct elevator_queue *e = q->elevator;
|
|
|
|
if ((rq->rq_flags & RQF_ELVPRIV) && e && e->type->ops.requeue_request)
|
|
e->type->ops.requeue_request(rq);
|
|
}
|
|
|
|
static inline bool blk_mq_sched_has_work(struct blk_mq_hw_ctx *hctx)
|
|
{
|
|
struct elevator_queue *e = hctx->queue->elevator;
|
|
|
|
if (e && e->type->ops.has_work)
|
|
return e->type->ops.has_work(hctx);
|
|
|
|
return false;
|
|
}
|
|
|
|
static inline bool blk_mq_sched_needs_restart(struct blk_mq_hw_ctx *hctx)
|
|
{
|
|
return test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
|
|
}
|
|
|
|
#endif
|