[RFC,v2,04/11] bfq: limit the IO depth of idle_class to 1

Commit Message

brookxu.cn March 12, 2021, 11:08 a.m. UTC

From: Chunguang Xu <[e-mail]>

The IO depth of queues belong to CLASS_IDLE  is limited to 1,
so that it can avoid introducing a larger tail latency under
a device with a larger IO depth. Although limiting the IO
depth may reduce the performance of idle_class, it is
generally not a big problem, because idle_class usually does
not have strict performance requirements.

Signed-off-by: Chunguang Xu <[e-mail]>
---
 block/bfq-iosched.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

Patch

diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index f0f53d6f1f6e..91e903f1e550 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -4808,6 +4808,17 @@  static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
 	if (!bfqq)
 		goto exit;
 
+	/*
+	 * Here, the IO depth of queues belong to CLASS_IDLE is limited
+	 * to 1, so that it can avoid introducing a larger tail latency
+	 * under a device with a larger IO depth. Although limiting the
+	 * IO depth may reduce the performance of idle_class, it is
+	 * generally not a big problem, because idle_class usually
+	 * does not have strict performance requirements.
+	 */
+	if (bfq_class_idle(bfqq) && bfqq->dispatched)
+		goto exit;
+
 	rq = bfq_dispatch_rq_from_bfqq(bfqd, bfqq);
 
 	if (rq) {