linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: brookxu <brookxu.cn@gmail.com>
To: paolo.valente@linaro.org, axboe@kernel.dk, tj@kernel.org
Cc: linux-block@vger.kernel.org, cgroups@vger.kernel.org,
	linux-kernel@vger.kernel.org
Subject: [RFC PATCH 4/8] bfq: expire bfqq if a higher priority class is waiting
Date: Mon,  8 Mar 2021 20:00:17 +0800	[thread overview]
Message-ID: <055c82a8f016a0e918e69ac6700a5839a7f4bfaf.1615203034.git.brookxu@tencent.com> (raw)
In-Reply-To: <cover.1615203034.git.brookxu@tencent.com>
In-Reply-To: <cover.1615203034.git.brookxu@tencent.com>

From: Chunguang Xu <brookxu@tencent.com>

From: Chunguang Xu <brookxu@tencent.com>

Expire bfqq If a higher priority class is waiting to be served, we
can further guarantee the delay of the higher priority class.

Signed-off-by: Chunguang Xu <brookxu@tencent.com>
---
 block/bfq-iosched.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index b639cdbb4192..223affaa7c92 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -4677,7 +4677,10 @@ static struct request *bfq_dispatch_rq_from_bfqq(struct bfq_data *bfqd,
 						 struct bfq_queue *bfqq)
 {
 	struct request *rq = bfqq->next_rq;
+	struct bfq_sched_data *sd = bfqq->entity.sched_data;
+	struct bfq_service_tree *st = sd->service_tree;
 	unsigned long service_to_charge;
+	int idx;
 
 	service_to_charge = bfq_serv_to_charge(rq, bfqq);
 
@@ -4714,6 +4717,17 @@ static struct request *bfq_dispatch_rq_from_bfqq(struct bfq_data *bfqd,
 	if (!(bfq_tot_busy_queues(bfqd) > 1 && bfq_class_idle(bfqq)))
 		goto return_rq;
 
+	/*
+	 * Expire bfqq, if other queues belong to higher priority
+	 * class are waiting for service.
+	 */
+	for (idx = bfqq->ioprio_class - 2; idx >= 0; idx--) {
+		if (!RB_EMPTY_ROOT(&(st + idx)->active))
+			break;
+	}
+	if (idx < 0)
+		goto return_rq;
+
 	bfq_bfqq_expire(bfqd, bfqq, false, BFQQE_BUDGET_EXHAUSTED);
 
 return_rq:
-- 
2.30.0


  parent reply	other threads:[~2021-03-08 12:01 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-03-08 12:00 [RFC PATCH 0/8] bfq: introduce bfq.ioprio for cgroup brookxu
2021-03-08 12:00 ` [RFC PATCH 1/8] bfq: introduce bfq_entity_to_bfqg helper method brookxu
2021-03-08 12:00 ` [RFC PATCH 2/8] bfq: limit the IO depth of idle_class to 1 brookxu
2021-03-08 12:00 ` [RFC PATCH 3/8] bfq: keep the minimun bandwidth for be_class brookxu
2021-03-08 12:00 ` brookxu [this message]
2021-03-08 12:00 ` [RFC PATCH 5/8] bfq: introduce bfq.ioprio for cgroup brookxu
2021-03-08 12:00 ` [RFC PATCH 6/8] bfq: convert the type of bfq_group.bfqd to bfq_data* brookxu
2021-03-08 12:00 ` [RFC PATCH 7/8] bfq: remove unnecessary initialization logic brookxu
2021-03-08 12:00 ` [RFC PATCH 8/8] bfq: optimize the calculation of bfq_weight_to_ioprio() brookxu

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=055c82a8f016a0e918e69ac6700a5839a7f4bfaf.1615203034.git.brookxu@tencent.com \
    --to=brookxu.cn@gmail.com \
    --cc=axboe@kernel.dk \
    --cc=cgroups@vger.kernel.org \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=paolo.valente@linaro.org \
    --cc=tj@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).