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;
MIME-Version: 1.0
References: <20230529131106.2123367-1-yukuai1@huaweicloud.com> <20230529131106.2123367-8-yukuai1@huaweicloud.com>
In-Reply-To: <20230529131106.2123367-8-yukuai1@huaweicloud.com>
From:   Xiao Ni <xni@redhat.com>
Date:   Wed, 31 May 2023 23:42:50 +0800
Message-ID: <CALTww29JCfgQivaEqi3dAvTrfxT9bhN6Rj04fyXRRJF2DfNHyg@mail.gmail.com>
Subject: Re: [PATCH -next v3 7/7] md/raid1-10: limit the number of plugged bio
To:     Yu Kuai <yukuai1@huaweicloud.com>
Cc:     song@kernel.org, neilb@suse.de, akpm@osdl.org,
        linux-raid@vger.kernel.org, linux-kernel@vger.kernel.org,
        yukuai3@huawei.com, yi.zhang@huawei.com, yangerkun@huawei.com
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
Precedence: bulk

On Mon, May 29, 2023 at 9:14=E2=80=AFPM Yu Kuai <yukuai1@huaweicloud.com> w=
rote:
>
> From: Yu Kuai <yukuai3@huawei.com>
>
> bio can be added to plug infinitely, and following writeback test can
> trigger huge amount of plugged bio:
>
> Test script:
> modprobe brd rd_nr=3D4 rd_size=3D10485760
> mdadm -CR /dev/md0 -l10 -n4 /dev/ram[0123] --assume-clean --bitmap=3Dinte=
rnal
> echo 0 > /proc/sys/vm/dirty_background_ratio
> fio -filename=3D/dev/md0 -ioengine=3Dlibaio -rw=3Dwrite -bs=3D4k -numjobs=
=3D1 -iodepth=3D128 -name=3Dtest
>
> 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>
> ---
>  drivers/md/raid1-10.c | 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.c b/drivers/md/raid1-10.c
> index 17e55c1fd5a1..bb1e23b66c45 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 <=3D 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)
> @@ -128,7 +130,7 @@ 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 =3D NULL;
>         struct blk_plug_cb *cb;
> @@ -148,6 +150,11 @@ static inline bool raid1_add_bio_to_plug(struct mdde=
v *mddev, struct bio *bio,
>
>         plug =3D container_of(cb, struct raid1_plug_cb, cb);
>         bio_list_add(&plug->pending, bio);
> +       if (++plug->count / MAX_PLUG_BIO >=3D copies) {
> +               list_del(&cb->list);
> +               cb->callback(cb, false);
> +       }
> +
It doesn't need this line here.

Have you done some performance tests with this patch set?

Regards
Xiao
>
>         return true;
>  }
> diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
> index 006620fed595..dc89a1c4b1f1 100644
> --- a/drivers/md/raid1.c
> +++ b/drivers/md/raid1.c
> @@ -1562,7 +1562,7 @@ 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 =3D (void *)rdev;
> -               if (!raid1_add_bio_to_plug(mddev, mbio, raid1_unplug)) {
> +               if (!raid1_add_bio_to_plug(mddev, mbio, raid1_unplug, dis=
ks)) {
>                         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 fb22cfe94d32..9237dbeb07ba 100644
> --- a/drivers/md/raid10.c
> +++ b/drivers/md/raid10.c
> @@ -1306,7 +1306,7 @@ static void raid10_write_one_disk(struct mddev *mdd=
ev, 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->copi=
es)) {
>                 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
>