Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Yu Kuai <yukuai1@huaweicloud.com>
To:     song@kernel.org, neilb@suse.de, akpm@osdl.org
Cc:     linux-raid@vger.kernel.org, linux-kernel@vger.kernel.org,
        yukuai3@huawei.com, yukuai1@huaweicloud.com, yi.zhang@huawei.com,
        yangerkun@huawei.com
Subject: [PATCH -next 8/8] md/raid1-10: limit the number of plugged bio
Date:   Thu, 20 Apr 2023 19:29:46 +0800
Message-Id: <20230420112946.2869956-9-yukuai1@huaweicloud.com>
In-Reply-To: <20230420112946.2869956-1-yukuai1@huaweicloud.com>
References: <20230420112946.2869956-1-yukuai1@huaweicloud.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: Yu Kuai <yukuai3@huawei.com>

bio can be added to plug infinitely, and following writeback test can
trigger huge amount of pluged bio:

Test script:
modprobe brd rd_nr=4 rd_size=10485760
mdadm -CR /dev/md0 -l10 -n4 /dev/ram[0123] --assume-clean
echo 0 > /proc/sys/vm/dirty_background_ratio
echo 60 > /proc/sys/vm/dirty_ratio
fio -filename=/dev/md0 -ioengine=libaio -rw=write -thread -bs=1k-8k -numjobs=1 -iodepth=128 -name=xxx

Test result:
Monitor /sys/block/md0/inflight will found that inflight keep increasing
until fio finish writing, after running for about 2 minutes:

[root@fedora ~]# cat /sys/block/md0/inflight
       0  4474191

Fix the problem by limiting the number of pluged bio based on the number
of copies for orininal bio.

Signed-off-by: Yu Kuai <yukuai3@huawei.com>
---
 drivers/md/raid1-10.h | 9 ++++++++-
 drivers/md/raid1.c    | 2 +-
 drivers/md/raid10.c   | 2 +-
 3 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/md/raid1-10.h b/drivers/md/raid1-10.h
index 95b2fb4dd9aa..2785ae805953 100644
--- a/drivers/md/raid1-10.h
+++ b/drivers/md/raid1-10.h
@@ -33,9 +33,12 @@ struct resync_pages {
 	struct page	*pages[RESYNC_PAGES];
 };
 
+#define MAX_PLUG_BIO 32
+
 struct raid1_plug_cb {
 	struct blk_plug_cb	cb;
 	struct bio_list		pending;
+	unsigned int		count;
 };
 
 static inline void rbio_pool_free(void *rbio, void *data)
@@ -132,7 +135,7 @@ static inline void md_submit_write(struct bio *bio)
 }
 
 static inline bool md_add_bio_to_plug(struct mddev *mddev, struct bio *bio,
-				      blk_plug_cb_fn unplug)
+				      blk_plug_cb_fn unplug, int copies)
 {
 	struct raid1_plug_cb *plug = NULL;
 	struct blk_plug_cb *cb;
@@ -152,6 +155,10 @@ static inline bool md_add_bio_to_plug(struct mddev *mddev, struct bio *bio,
 
 	plug = container_of(cb, struct raid1_plug_cb, cb);
 	bio_list_add(&plug->pending, bio);
+	if (++plug->count / MAX_PLUG_BIO >= copies) {
+		list_del(&cb->list);
+		cb->callback(cb, false);
+	}
 
 	return true;
 }
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 91e1dbc48228..6a38104a7b89 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1561,7 +1561,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 					      r1_bio->sector);
 		/* flush_pending_writes() needs access to the rdev so...*/
 		mbio->bi_bdev = (void *)rdev;
-		if (!md_add_bio_to_plug(mddev, mbio, raid1_unplug)) {
+		if (!md_add_bio_to_plug(mddev, mbio, raid1_unplug, disks)) {
 			spin_lock_irqsave(&conf->device_lock, flags);
 			bio_list_add(&conf->pending_bio_list, mbio);
 			spin_unlock_irqrestore(&conf->device_lock, flags);
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index d92b1efe9eee..721d50646043 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1300,7 +1300,7 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
 
 	atomic_inc(&r10_bio->remaining);
 
-	if (!md_add_bio_to_plug(mddev, mbio, raid10_unplug)) {
+	if (!md_add_bio_to_plug(mddev, mbio, raid10_unplug, conf->copies)) {
 		spin_lock_irqsave(&conf->device_lock, flags);
 		bio_list_add(&conf->pending_bio_list, mbio);
 		spin_unlock_irqrestore(&conf->device_lock, flags);
-- 
2.39.2