blk-mq: add optional request->alloc_time_ns

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->alloc_time_ns which records when the request
allocation attempt started.  As it isn't used for the usual stats,
make it optional behind CONFIG_BLK_RQ_ALLOC_TIME and
QUEUE_FLAG_RQ_ALLOC_TIME so that it can be compiled out when there are
no users and it's active only on queues which need it even when
compiled in.

v2: s/pre_start_time/alloc_time/ and add CONFIG_BLK_RQ_ALLOC_TIME
    gating as suggested by Jens.

Signed-off-by: Tejun Heo <[email protected]>
Signed-off-by: Jens Axboe <[email protected]>

block/Kconfig

@@ -26,6 +26,9 @@ menuconfig BLOCK
 
 if BLOCK
 
+config BLK_RQ_ALLOC_TIME
+	bool
+
 config BLK_SCSI_REQUEST
 	bool
 

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 alloc_time_ns)
 {
 	struct blk_mq_tags *tags = blk_mq_tags_from_data(data);
 	struct request *rq = tags->static_rqs[tag];
@@ -325,6 +325,9 @@ 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;
+#ifdef CONFIG_BLK_RQ_ALLOC_TIME
+	rq->alloc_time_ns = alloc_time_ns;
+#endif
 	if (blk_mq_need_time_stamp(rq))
 		rq->start_time_ns = ktime_get_ns();
 	else
@@ -356,8 +359,14 @@ static struct request *blk_mq_get_request(struct request_queue *q,
 	struct request *rq;
 	unsigned int tag;
 	bool clear_ctx_on_error = false;
+	u64 alloc_time_ns = 0;
 
 	blk_queue_enter_live(q);
+
+	/* alloc_time includes depth and tag waits */
+	if (blk_queue_rq_alloc_time(q))
+		alloc_time_ns = ktime_get_ns();
+
 	data->q = q;
 	if (likely(!data->ctx)) {
 		data->ctx = blk_mq_get_ctx(q);
@@ -393,7 +402,7 @@ 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, alloc_time_ns);
 	if (!op_is_flush(data->cmd_flags)) {
 		rq->elv.icq = NULL;
 		if (e && e->type->ops.prepare_request) {

include/linux/blkdev.h

@@ -194,7 +194,11 @@ struct request {
 
 	struct gendisk *rq_disk;
 	struct hd_struct *part;
-	/* Time that I/O was submitted to the kernel. */
+#ifdef CONFIG_BLK_RQ_ALLOC_TIME
+	/* Time that the first bio started allocating this request. */
+	u64 alloc_time_ns;
+#endif
+	/* 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;
@@ -609,6 +613,7 @@ struct request_queue {
 #define QUEUE_FLAG_QUIESCED	24	/* queue has been quiesced */
 #define QUEUE_FLAG_PCI_P2PDMA	25	/* device supports PCI p2p requests */
 #define QUEUE_FLAG_ZONE_RESETALL 26	/* supports Zone Reset All */
+#define QUEUE_FLAG_RQ_ALLOC_TIME 27	/* record rq->alloc_time_ns */
 
 #define QUEUE_FLAG_MQ_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
 				 (1 << QUEUE_FLAG_SAME_COMP))
@@ -637,6 +642,12 @@ 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)
+#ifdef CONFIG_BLK_RQ_ALLOC_TIME
+#define blk_queue_rq_alloc_time(q)	\
+	test_bit(QUEUE_FLAG_RQ_ALLOC_TIME, &(q)->queue_flags)
+#else
+#define blk_queue_rq_alloc_time(q)	false
+#endif
 
 #define blk_noretry_request(rq) \
 	((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \