linux-block.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Ming Lei <ming.lei@redhat.com>
To: Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org, Ming Lei <ming.lei@redhat.com>,
	John Garry <john.garry@huawei.com>,
	Bart Van Assche <bvanassche@acm.org>,
	Hannes Reinecke <hare@suse.com>, Christoph Hellwig <hch@lst.de>,
	Thomas Gleixner <tglx@linutronix.de>
Subject: [PATCH V8 10/11] blk-mq: re-submit IO in case that hctx is inactive
Date: Fri, 24 Apr 2020 18:23:50 +0800	[thread overview]
Message-ID: <20200424102351.475641-11-ming.lei@redhat.com> (raw)
In-Reply-To: <20200424102351.475641-1-ming.lei@redhat.com>

When all CPUs in one hctx are offline and this hctx becomes inactive, we
shouldn't run this hw queue for completing request any more.

So allocate request from one live hctx, and clone & resubmit the request,
either it is from sw queue or scheduler queue.

Cc: John Garry <john.garry@huawei.com>
Cc: Bart Van Assche <bvanassche@acm.org>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
---
 block/blk-mq.c | 102 +++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 98 insertions(+), 4 deletions(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 0759e0d606b3..a4a26bb23533 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2370,6 +2370,98 @@ static int blk_mq_hctx_notify_online(unsigned int cpu, struct hlist_node *node)
 	return 0;
 }
 
+static void blk_mq_resubmit_end_rq(struct request *rq, blk_status_t error)
+{
+	struct request *orig_rq = rq->end_io_data;
+
+	blk_mq_cleanup_rq(orig_rq);
+	blk_mq_end_request(orig_rq, error);
+
+	blk_put_request(rq);
+}
+
+static void blk_mq_resubmit_rq(struct request *rq)
+{
+	struct request *nrq;
+	unsigned int flags = 0;
+	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
+	struct blk_mq_tags *tags = rq->q->elevator ? hctx->sched_tags :
+		hctx->tags;
+	bool reserved = blk_mq_tag_is_reserved(tags, rq->internal_tag);
+
+	if (rq->rq_flags & RQF_PREEMPT)
+		flags |= BLK_MQ_REQ_PREEMPT;
+	if (reserved)
+		flags |= BLK_MQ_REQ_RESERVED;
+
+	/* avoid allocation failure by clearing NOWAIT */
+	nrq = blk_get_request(rq->q, rq->cmd_flags & ~REQ_NOWAIT, flags);
+	if (!nrq)
+		return;
+
+	blk_rq_copy_request(nrq, rq);
+
+	nrq->timeout = rq->timeout;
+	nrq->rq_disk = rq->rq_disk;
+	nrq->part = rq->part;
+
+	memcpy(blk_mq_rq_to_pdu(nrq), blk_mq_rq_to_pdu(rq),
+			rq->q->tag_set->cmd_size);
+
+	nrq->end_io = blk_mq_resubmit_end_rq;
+	nrq->end_io_data = rq;
+	nrq->bio = rq->bio;
+	nrq->biotail = rq->biotail;
+
+	if (blk_insert_cloned_request(nrq->q, nrq) != BLK_STS_OK)
+		blk_mq_request_bypass_insert(nrq, false, true);
+}
+
+static void blk_mq_hctx_deactivate(struct blk_mq_hw_ctx *hctx)
+{
+	LIST_HEAD(sched);
+	LIST_HEAD(re_submit);
+	LIST_HEAD(flush_in);
+	LIST_HEAD(flush_out);
+	struct request *rq, *nxt;
+	struct elevator_queue *e = hctx->queue->elevator;
+
+	if (!e) {
+		blk_mq_flush_busy_ctxs(hctx, &re_submit);
+	} else {
+		while ((rq = e->type->ops.dispatch_request(hctx))) {
+			if (rq->mq_hctx != hctx)
+				list_add(&rq->queuelist, &sched);
+			else
+				list_add(&rq->queuelist, &re_submit);
+		}
+	}
+	while (!list_empty(&sched)) {
+		rq = list_first_entry(&sched, struct request, queuelist);
+		list_del_init(&rq->queuelist);
+		blk_mq_sched_insert_request(rq, true, true, true);
+	}
+
+	/* requests in dispatch list have to be re-submitted too */
+	spin_lock(&hctx->lock);
+	list_splice_tail_init(&hctx->dispatch, &re_submit);
+	spin_unlock(&hctx->lock);
+
+	/* blk_end_flush_machinery will cover flush request */
+	list_for_each_entry_safe(rq, nxt, &re_submit, queuelist) {
+		if (rq->rq_flags & RQF_FLUSH_SEQ)
+			list_move(&rq->queuelist, &flush_in);
+	}
+	blk_end_flush_machinery(hctx, &flush_in, &flush_out);
+	list_splice_tail(&flush_out, &re_submit);
+
+	while (!list_empty(&re_submit)) {
+		rq = list_first_entry(&re_submit, struct request, queuelist);
+		list_del_init(&rq->queuelist);
+		blk_mq_resubmit_rq(rq);
+	}
+}
+
 static void blk_mq_hctx_handle_dead_cpu(struct blk_mq_hw_ctx *hctx,
 		unsigned int cpu)
 {
@@ -2398,9 +2490,8 @@ static void blk_mq_hctx_handle_dead_cpu(struct blk_mq_hw_ctx *hctx,
 }
 
 /*
- * 'cpu' is going away. splice any existing rq_list entries from this
- * software queue to the hw queue dispatch list, and ensure that it
- * gets run.
+ * @cpu has gone away. If this hctx is inactive, we can't dispatch request
+ * to the hctx any more, so clone and re-submit requests from this hctx
  */
 static int blk_mq_hctx_notify_dead(unsigned int cpu, struct hlist_node *node)
 {
@@ -2410,7 +2501,10 @@ static int blk_mq_hctx_notify_dead(unsigned int cpu, struct hlist_node *node)
 	if (!cpumask_test_cpu(cpu, hctx->cpumask))
 		return 0;
 
-	blk_mq_hctx_handle_dead_cpu(hctx, cpu);
+	if (test_bit(BLK_MQ_S_INACTIVE, &hctx->state))
+		blk_mq_hctx_deactivate(hctx);
+	else
+		blk_mq_hctx_handle_dead_cpu(hctx, cpu);
 	return 0;
 }
 
-- 
2.25.2


  parent reply	other threads:[~2020-04-24 10:25 UTC|newest]

Thread overview: 80+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-04-24 10:23 [PATCH V8 00/11] blk-mq: improvement CPU hotplug Ming Lei
2020-04-24 10:23 ` [PATCH V8 01/11] block: clone nr_integrity_segments and write_hint in blk_rq_prep_clone Ming Lei
2020-04-24 10:32   ` Christoph Hellwig
2020-04-24 12:43   ` Hannes Reinecke
2020-04-24 16:11   ` Martin K. Petersen
2020-04-24 10:23 ` [PATCH V8 02/11] block: add helper for copying request Ming Lei
2020-04-24 10:35   ` Christoph Hellwig
2020-04-24 12:43   ` Hannes Reinecke
2020-04-24 16:12   ` Martin K. Petersen
2020-04-24 10:23 ` [PATCH V8 03/11] blk-mq: mark blk_mq_get_driver_tag as static Ming Lei
2020-04-24 12:44   ` Hannes Reinecke
2020-04-24 16:13   ` Martin K. Petersen
2020-04-24 10:23 ` [PATCH V8 04/11] blk-mq: assign rq->tag in blk_mq_get_driver_tag Ming Lei
2020-04-24 10:35   ` Christoph Hellwig
2020-04-24 13:02   ` Hannes Reinecke
2020-04-25  2:54     ` Ming Lei
2020-04-25 18:26       ` Hannes Reinecke
2020-04-24 10:23 ` [PATCH V8 05/11] blk-mq: support rq filter callback when iterating rqs Ming Lei
2020-04-24 13:17   ` Hannes Reinecke
2020-04-25  3:04     ` Ming Lei
2020-04-24 10:23 ` [PATCH V8 06/11] blk-mq: prepare for draining IO when hctx's all CPUs are offline Ming Lei
2020-04-24 13:23   ` Hannes Reinecke
2020-04-25  3:24     ` Ming Lei
2020-04-24 10:23 ` [PATCH V8 07/11] blk-mq: stop to handle IO and drain IO before hctx becomes inactive Ming Lei
2020-04-24 10:38   ` Christoph Hellwig
2020-04-25  3:17     ` Ming Lei
2020-04-25  8:32       ` Christoph Hellwig
2020-04-25  9:34         ` Ming Lei
2020-04-25  9:53           ` Ming Lei
2020-04-25 15:48             ` Christoph Hellwig
2020-04-26  2:06               ` Ming Lei
2020-04-26  8:19                 ` John Garry
2020-04-27 15:36                 ` Christoph Hellwig
2020-04-28  1:10                   ` Ming Lei
2020-04-27 19:03               ` Paul E. McKenney
2020-04-28  6:54                 ` Christoph Hellwig
2020-04-28 15:58               ` Peter Zijlstra
2020-04-29  2:16                 ` Ming Lei
2020-04-29  8:07                   ` Will Deacon
2020-04-29  9:46                     ` Ming Lei
2020-04-29 12:27                       ` Will Deacon
2020-04-29 13:43                         ` Ming Lei
2020-04-29 17:34                           ` Will Deacon
2020-04-30  0:39                             ` Ming Lei
2020-04-30 11:04                               ` Will Deacon
2020-04-30 14:02                                 ` Ming Lei
2020-05-05 15:46                                   ` Christoph Hellwig
2020-05-06  1:24                                     ` Ming Lei
2020-05-06  7:28                                       ` Will Deacon
2020-05-06  8:07                                         ` Ming Lei
2020-05-06  9:56                                           ` Will Deacon
2020-05-06 10:22                                             ` Ming Lei
2020-04-29 17:46                           ` Paul E. McKenney
2020-04-30  0:43                             ` Ming Lei
2020-04-24 13:27   ` Hannes Reinecke
2020-04-25  3:30     ` Ming Lei
2020-04-24 13:42   ` John Garry
2020-04-25  3:41     ` Ming Lei
2020-04-24 10:23 ` [PATCH V8 08/11] block: add blk_end_flush_machinery Ming Lei
2020-04-24 10:41   ` Christoph Hellwig
2020-04-25  3:44     ` Ming Lei
2020-04-25  8:11       ` Christoph Hellwig
2020-04-25  9:51         ` Ming Lei
2020-04-24 13:47   ` Hannes Reinecke
2020-04-25  3:47     ` Ming Lei
2020-04-24 10:23 ` [PATCH V8 09/11] blk-mq: add blk_mq_hctx_handle_dead_cpu for handling cpu dead Ming Lei
2020-04-24 10:42   ` Christoph Hellwig
2020-04-25  3:48     ` Ming Lei
2020-04-24 13:48   ` Hannes Reinecke
2020-04-24 10:23 ` Ming Lei [this message]
2020-04-24 10:44   ` [PATCH V8 10/11] blk-mq: re-submit IO in case that hctx is inactive Christoph Hellwig
2020-04-25  3:52     ` Ming Lei
2020-04-24 13:55   ` Hannes Reinecke
2020-04-25  3:59     ` Ming Lei
2020-04-24 10:23 ` [PATCH V8 11/11] block: deactivate hctx when the hctx is actually inactive Ming Lei
2020-04-24 10:43   ` Christoph Hellwig
2020-04-24 13:56   ` Hannes Reinecke
2020-04-24 15:23 ` [PATCH V8 00/11] blk-mq: improvement CPU hotplug Jens Axboe
2020-04-24 15:40   ` Christoph Hellwig
2020-04-24 15:41     ` Jens Axboe

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=20200424102351.475641-11-ming.lei@redhat.com \
    --to=ming.lei@redhat.com \
    --cc=axboe@kernel.dk \
    --cc=bvanassche@acm.org \
    --cc=hare@suse.com \
    --cc=hch@lst.de \
    --cc=john.garry@huawei.com \
    --cc=linux-block@vger.kernel.org \
    --cc=tglx@linutronix.de \
    /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).