There are currently two start time timestamps - start_time_ns and io_start_time_ns. The former marks the request allocation and and the second issue-to-device time. The planned io.weight controller needs to measure the total time bios take to execute after it leaves rq_qos including the time spent waiting for request to become available, which can easily dominate on saturated devices. This patch adds request->pre_start_time_ns which records when the request allocation attempt started. As it isn't used for the usual stats, make it optional behind QUEUE_FLAG_REC_PRESTART. Signed-off-by: Tejun Heo <tj@xxxxxxxxxx> --- block/blk-mq.c | 11 +++++++++-- include/linux/blkdev.h | 7 ++++++- 2 files changed, 15 insertions(+), 3 deletions(-) diff --git a/block/blk-mq.c b/block/blk-mq.c index e5ef40c603ca..90b46988cc02 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -291,7 +291,7 @@ static inline bool blk_mq_need_time_stamp(struct request *rq) } static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, - unsigned int tag, unsigned int op) + unsigned int tag, unsigned int op, u64 pre_start_time_ns) { struct blk_mq_tags *tags = blk_mq_tags_from_data(data); struct request *rq = tags->static_rqs[tag]; @@ -325,6 +325,7 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, RB_CLEAR_NODE(&rq->rb_node); rq->rq_disk = NULL; rq->part = NULL; + rq->pre_start_time_ns = pre_start_time_ns; if (blk_mq_need_time_stamp(rq)) rq->start_time_ns = ktime_get_ns(); else @@ -356,8 +357,14 @@ static struct request *blk_mq_get_request(struct request_queue *q, struct request *rq; unsigned int tag; bool clear_ctx_on_error = false; + u64 pre_start_time_ns = 0; blk_queue_enter_live(q); + + /* pre_start_time includes depth and tag waits */ + if (blk_queue_rec_prestart(q)) + pre_start_time_ns = ktime_get_ns(); + data->q = q; if (likely(!data->ctx)) { data->ctx = blk_mq_get_ctx(q); @@ -393,7 +400,7 @@ static struct request *blk_mq_get_request(struct request_queue *q, return NULL; } - rq = blk_mq_rq_ctx_init(data, tag, data->cmd_flags); + rq = blk_mq_rq_ctx_init(data, tag, data->cmd_flags, pre_start_time_ns); if (!op_is_flush(data->cmd_flags)) { rq->elv.icq = NULL; if (e && e->type->ops.prepare_request) { diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 259bd7ad8312..4247a9bc44b7 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -194,7 +194,9 @@ struct request { struct gendisk *rq_disk; struct hd_struct *part; - /* Time that I/O was submitted to the kernel. */ + /* Time that the first bio started allocating this request. */ + u64 pre_start_time_ns; + /* Time that this request was allocated for this IO. */ u64 start_time_ns; /* Time that I/O was submitted to the device. */ u64 io_start_time_ns; @@ -606,6 +608,7 @@ struct request_queue { #define QUEUE_FLAG_SCSI_PASSTHROUGH 23 /* queue supports SCSI commands */ #define QUEUE_FLAG_QUIESCED 24 /* queue has been quiesced */ #define QUEUE_FLAG_PCI_P2PDMA 25 /* device supports PCI p2p requests */ +#define QUEUE_FLAG_REC_PRESTART 26 /* record pre_start_time_ns */ #define QUEUE_FLAG_MQ_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_SAME_COMP)) @@ -632,6 +635,8 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); test_bit(QUEUE_FLAG_SCSI_PASSTHROUGH, &(q)->queue_flags) #define blk_queue_pci_p2pdma(q) \ test_bit(QUEUE_FLAG_PCI_P2PDMA, &(q)->queue_flags) +#define blk_queue_rec_prestart(q) \ + test_bit(QUEUE_FLAG_REC_PRESTART, &(q)->queue_flags) #define blk_noretry_request(rq) \ ((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \ -- 2.17.1