From: Yu Kuai <yukuai3@huawei.com>
Date: Mon, 29 May 2023 13:11:06 +0000 (+0800)
Subject: md/raid1-10: limit the number of plugged bio
X-Git-Url: http://git.maquefel.me/?a=commitdiff_plain;h=460af1f9d9e62acce4a21f9bd00b5bcd5963bcd4;p=linux.git
md/raid1-10: limit the number of plugged bio
bio can be added to plug infinitely, and following writeback test can
trigger huge amount of plugged bio:
Test script:
modprobe brd rd_nr=4 rd_size=10485760
mdadm -CR /dev/md0 -l10 -n4 /dev/ram[0123] --assume-clean --bitmap=internal
echo 0 > /proc/sys/vm/dirty_background_ratio
fio -filename=/dev/md0 -ioengine=libaio -rw=write -bs=4k -numjobs=1 -iodepth=128 -name=test
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 plugged bio based on the number
of copies for original bio.
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20230529131106.2123367-8-yukuai1@huaweicloud.com
---
diff --git a/drivers/md/raid1-10.c b/drivers/md/raid1-10.c
index c62bcb17c67bb..169ebe296f2d0 100644
--- a/drivers/md/raid1-10.c
+++ b/drivers/md/raid1-10.c
@@ -21,6 +21,7 @@
#define IO_MADE_GOOD ((struct bio *)2)
#define BIO_SPECIAL(bio) ((unsigned long)bio <= 2)
+#define MAX_PLUG_BIO 32
/* for managing resync I/O pages */
struct resync_pages {
@@ -31,6 +32,7 @@ struct resync_pages {
struct raid1_plug_cb {
struct blk_plug_cb cb;
struct bio_list pending;
+ unsigned int count;
};
static void rbio_pool_free(void *rbio, void *data)
@@ -129,7 +131,7 @@ static inline void raid1_submit_write(struct bio *bio)
}
static inline bool raid1_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;
@@ -149,6 +151,11 @@ static inline bool raid1_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 334ed76d3c5ab..dd25832eb0452 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1565,7 +1565,7 @@ 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 (!raid1_add_bio_to_plug(mddev, mbio, raid1_unplug)) {
+ if (!raid1_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 f890f549086ba..d0de8c9fb3cfb 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1314,7 +1314,7 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
atomic_inc(&r10_bio->remaining);
- if (!raid1_add_bio_to_plug(mddev, mbio, raid10_unplug)) {
+ if (!raid1_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);