From: Bart Van Assche <bart.vanassche@sandisk.com>
To: Jens Axboe <axboe@kernel.dk>
Cc: <linux-block@vger.kernel.org>, <linux-scsi@vger.kernel.org>,
"Bart Van Assche" <bart.vanassche@sandisk.com>,
Christoph Hellwig <hch@lst.de>, "Hannes Reinecke" <hare@suse.com>
Subject: [PATCH v4 2/6] blk-mq: Restart a single queue if tag sets are shared
Date: Fri, 7 Apr 2017 11:16:50 -0700 [thread overview]
Message-ID: <20170407181654.27836-3-bart.vanassche@sandisk.com> (raw)
In-Reply-To: <20170407181654.27836-1-bart.vanassche@sandisk.com>
To improve scalability, if hardware queues are shared, restart
a single hardware queue in round-robin fashion. Rename
blk_mq_sched_restart_queues() to reflect the new semantics.
Remove blk_mq_sched_mark_restart_queue() because this function
has no callers. Remove flag QUEUE_FLAG_RESTART because this
patch removes the code that uses this flag.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.com>
---
block/blk-mq-sched.c | 63 ++++++++++++++++++++++++++++++++++++++++++--------
block/blk-mq-sched.h | 16 +------------
block/blk-mq.c | 2 +-
include/linux/blkdev.h | 1 -
4 files changed, 55 insertions(+), 27 deletions(-)
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 09af8ff18719..a5c683a6429c 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -317,25 +317,68 @@ static bool blk_mq_sched_bypass_insert(struct blk_mq_hw_ctx *hctx,
return true;
}
-static void blk_mq_sched_restart_hctx(struct blk_mq_hw_ctx *hctx)
+static bool blk_mq_sched_restart_hctx(struct blk_mq_hw_ctx *hctx)
{
if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state)) {
clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
- if (blk_mq_hctx_has_pending(hctx))
+ if (blk_mq_hctx_has_pending(hctx)) {
blk_mq_run_hw_queue(hctx, true);
+ return true;
+ }
}
+ return false;
}
-void blk_mq_sched_restart_queues(struct blk_mq_hw_ctx *hctx)
-{
- struct request_queue *q = hctx->queue;
- unsigned int i;
+/**
+ * list_for_each_entry_rcu_rr - iterate in a round-robin fashion over rcu list
+ * @pos: loop cursor.
+ * @skip: the list element that will not be examined. Iteration starts at
+ * @skip->next.
+ * @head: head of the list to examine. This list must have at least one
+ * element, namely @skip.
+ * @member: name of the list_head structure within typeof(*pos).
+ */
+#define list_for_each_entry_rcu_rr(pos, skip, head, member) \
+ for ((pos) = (skip); \
+ (pos = (pos)->member.next != (head) ? list_entry_rcu( \
+ (pos)->member.next, typeof(*pos), member) : \
+ list_entry_rcu((pos)->member.next->next, typeof(*pos), member)), \
+ (pos) != (skip); )
- if (test_bit(QUEUE_FLAG_RESTART, &q->queue_flags)) {
- if (test_and_clear_bit(QUEUE_FLAG_RESTART, &q->queue_flags)) {
- queue_for_each_hw_ctx(q, hctx, i)
- blk_mq_sched_restart_hctx(hctx);
+/*
+ * Called after a driver tag has been freed to check whether a hctx needs to
+ * be restarted. Restarts @hctx if its tag set is not shared. Restarts hardware
+ * queues in a round-robin fashion if the tag set of @hctx is shared with other
+ * hardware queues.
+ */
+void blk_mq_sched_restart(struct blk_mq_hw_ctx *const hctx)
+{
+ struct blk_mq_tags *const tags = hctx->tags;
+ struct blk_mq_tag_set *const set = hctx->queue->tag_set;
+ struct request_queue *const queue = hctx->queue, *q;
+ struct blk_mq_hw_ctx *hctx2;
+ unsigned int i, j;
+
+ if (set->flags & BLK_MQ_F_TAG_SHARED) {
+ rcu_read_lock();
+ list_for_each_entry_rcu_rr(q, queue, &set->tag_list,
+ tag_set_list) {
+ queue_for_each_hw_ctx(q, hctx2, i)
+ if (hctx2->tags == tags &&
+ blk_mq_sched_restart_hctx(hctx2))
+ goto done;
+ }
+ j = hctx->queue_num + 1;
+ for (i = 0; i < queue->nr_hw_queues; i++, j++) {
+ if (j == queue->nr_hw_queues)
+ j = 0;
+ hctx2 = queue->queue_hw_ctx[j];
+ if (hctx2->tags == tags &&
+ blk_mq_sched_restart_hctx(hctx2))
+ break;
}
+done:
+ rcu_read_unlock();
} else {
blk_mq_sched_restart_hctx(hctx);
}
diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h
index a75b16b123f7..4e3fc2a40207 100644
--- a/block/blk-mq-sched.h
+++ b/block/blk-mq-sched.h
@@ -19,7 +19,7 @@ bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio,
struct request **merged_request);
bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio);
bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq);
-void blk_mq_sched_restart_queues(struct blk_mq_hw_ctx *hctx);
+void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx);
void blk_mq_sched_insert_request(struct request *rq, bool at_head,
bool run_queue, bool async, bool can_block);
@@ -131,20 +131,6 @@ static inline void blk_mq_sched_mark_restart_hctx(struct blk_mq_hw_ctx *hctx)
set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
}
-/*
- * Mark a hardware queue and the request queue it belongs to as needing a
- * restart.
- */
-static inline void blk_mq_sched_mark_restart_queue(struct blk_mq_hw_ctx *hctx)
-{
- struct request_queue *q = hctx->queue;
-
- if (!test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
- set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
- if (!test_bit(QUEUE_FLAG_RESTART, &q->queue_flags))
- set_bit(QUEUE_FLAG_RESTART, &q->queue_flags);
-}
-
static inline bool blk_mq_sched_needs_restart(struct blk_mq_hw_ctx *hctx)
{
return test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index c26464f9649a..dba34eb79a08 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -351,7 +351,7 @@ void __blk_mq_finish_request(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
blk_mq_put_tag(hctx, hctx->tags, ctx, rq->tag);
if (sched_tag != -1)
blk_mq_sched_completed_request(hctx, rq);
- blk_mq_sched_restart_queues(hctx);
+ blk_mq_sched_restart(hctx);
blk_queue_exit(q);
}
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 3cf241b0814d..dc6c8d39d462 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -615,7 +615,6 @@ struct request_queue {
#define QUEUE_FLAG_FLUSH_NQ 25 /* flush not queueuable */
#define QUEUE_FLAG_DAX 26 /* device supports DAX */
#define QUEUE_FLAG_STATS 27 /* track rq completion times */
-#define QUEUE_FLAG_RESTART 28 /* queue needs restart at completion */
#define QUEUE_FLAG_POLL_STATS 29 /* collecting stats for hybrid polling */
#define QUEUE_FLAG_REGISTERED 30 /* queue has been registered to a disk */
--
2.12.0
next prev parent reply other threads:[~2017-04-07 18:16 UTC|newest]
Thread overview: 33+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-04-07 18:16 [PATCH v4 0/6] Avoid that scsi-mq and dm-mq queue processing stalls sporadically Bart Van Assche
2017-04-07 18:16 ` [PATCH v4 1/6] blk-mq: Make it safe to use RCU to iterate over blk_mq_tag_set.tag_list Bart Van Assche
2017-04-10 7:10 ` Christoph Hellwig
2017-04-07 18:16 ` Bart Van Assche [this message]
2017-04-10 7:11 ` [PATCH v4 2/6] blk-mq: Restart a single queue if tag sets are shared Christoph Hellwig
2017-04-07 18:16 ` [PATCH v4 3/6] blk-mq: Clarify comments in blk_mq_dispatch_rq_list() Bart Van Assche
2017-04-10 7:11 ` Christoph Hellwig
2017-04-07 18:16 ` [PATCH v4 4/6] blk-mq: Introduce blk_mq_delay_run_hw_queue() Bart Van Assche
2017-04-10 7:12 ` Christoph Hellwig
2017-04-10 15:02 ` Jens Axboe
2017-04-07 18:16 ` [PATCH v4 5/6] scsi: Avoid that SCSI queues get stuck Bart Van Assche
2017-04-10 7:12 ` Christoph Hellwig
2017-04-07 18:16 ` [PATCH v4 6/6] dm rq: Avoid that request processing stalls sporadically Bart Van Assche
2017-04-11 16:09 ` Mike Snitzer
2017-04-11 16:26 ` Bart Van Assche
2017-04-11 17:47 ` Mike Snitzer
2017-04-11 17:51 ` Bart Van Assche
2017-04-11 18:03 ` Mike Snitzer
2017-04-11 18:18 ` Bart Van Assche
2017-04-12 3:42 ` Ming Lei
2017-04-12 18:38 ` Bart Van Assche
2017-04-13 2:20 ` Ming Lei
2017-04-13 16:59 ` Bart Van Assche
2017-04-14 1:13 ` Ming Lei
2017-04-14 17:12 ` Bart Van Assche
2017-04-16 10:21 ` Ming Lei
2017-04-07 18:23 ` [PATCH v4 0/6] Avoid that scsi-mq and dm-mq queue " Jens Axboe
2017-04-07 18:33 ` Bart Van Assche
2017-04-07 18:39 ` Bart Van Assche
2017-04-07 18:51 ` Jens Axboe
2017-04-12 10:55 ` Benjamin Block
2017-04-12 18:11 ` Bart Van Assche
2017-04-13 12:23 ` Benjamin Block
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=20170407181654.27836-3-bart.vanassche@sandisk.com \
--to=bart.vanassche@sandisk.com \
--cc=axboe@kernel.dk \
--cc=hare@suse.com \
--cc=hch@lst.de \
--cc=linux-block@vger.kernel.org \
--cc=linux-scsi@vger.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