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 <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

2 files changed, 14 insertions, 2 deletions

diff --git a/block/Kconfig b/block/Kconfig
index 8b5f8e560eb4..1b62ad6d0e12 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -26,6 +26,9 @@ menuconfig BLOCK
 
 if BLOCK
 
+config BLK_RQ_ALLOC_TIME
+        bool
+
 config BLK_SCSI_REQUEST
         bool
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index cf768d0c2950..004411236034 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 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) {