diff mbox series

[1/4] block, bfq: update inject limit only after injection occurred

Message ID 20190822152037.15413-2-paolo.valente@linaro.org
State Accepted
Commit 23ed570accc94cf9de9036b71102aa7c0e0e8dc6
Headers show
Series block, bfq: series of improvements and small fixes of the injection mechanism | expand

Commit Message

Paolo Valente Aug. 22, 2019, 3:20 p.m. UTC 
BFQ updates the injection limit of each bfq_queue as a function of how
much the limit inflates the service times experienced by the I/O
requests of the queue. So only service times affected by injection
must be taken into account. Unfortunately, in the current
implementation of this update scheme, the service time of an I/O
request rq not affected by injection may happen to be considered in
the following case: there is no I/O request in service when rq
arrives.

This commit fixes this issue by making sure that only service times
affected by injection are considered for updating the injection
limit. In particular, the service time of an I/O request rq is now
considered only if at least one of the following two conditions holds:
- the destination bfq_queue for rq underwent injection before rq
arrival, and there is still I/O in service in the drive on rq arrival
(the service of such unfinished I/O may delay the service of rq);
- injection occurs between the arrival and the completion time of rq.

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>

---
 block/bfq-iosched.c | 19 +++++++++++++++++--
 1 file changed, 17 insertions(+), 2 deletions(-)

-- 
2.20.1
diff mbox series

Patch

diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index b33be928d164..5a2bbd8613a8 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -2025,7 +2025,21 @@  static void bfq_add_request(struct request *rq)
 			 * be set when rq will be dispatched.
 			 */
 			bfqd->wait_dispatch = true;
-			bfqd->rqs_injected = false;
+			/*
+			 * If there is no I/O in service in the drive,
+			 * then possible injection occurred before the
+			 * arrival of rq will not affect the total
+			 * service time of rq. So the injection limit
+			 * must not be updated as a function of such
+			 * total service time, unless new injection
+			 * occurs before rq is completed. To have the
+			 * injection limit updated only in the latter
+			 * case, reset rqs_injected here (rqs_injected
+			 * will be set in case injection is performed
+			 * on bfqq before rq is completed).
+			 */
+			if (bfqd->rq_in_driver == 0)
+				bfqd->rqs_injected = false;
 		}
 	}
 
@@ -5784,7 +5798,7 @@  static void bfq_update_inject_limit(struct bfq_data *bfqd,
 	u64 tot_time_ns = ktime_get_ns() - bfqd->last_empty_occupied_ns;
 	unsigned int old_limit = bfqq->inject_limit;
 
-	if (bfqq->last_serv_time_ns > 0) {
+	if (bfqq->last_serv_time_ns > 0 && bfqd->rqs_injected) {
 		u64 threshold = (bfqq->last_serv_time_ns * 3)>>1;
 
 		if (tot_time_ns >= threshold && old_limit > 0) {
@@ -5830,6 +5844,7 @@  static void bfq_update_inject_limit(struct bfq_data *bfqd,
 
 	/* update complete, not waiting for any request completion any longer */
 	bfqd->waited_rq = NULL;
+	bfqd->rqs_injected = false;
 }
 
 /*