Received-SPF: pass (google.com: domain of linux-kernel+bounces-11499-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45e3:2400::1 as permitted sender) client-ip=2604:1380:45e3:2400::1;
Precedence: bulk
MIME-Version: 1.0
References: <20231207043118.118158-1-fengli@smartx.com> <20231225092010-mutt-send-email-mst@kernel.org>
 <AB23804D-FF38-47B8-ADC6-C0A19B7083CC@smartx.com> <20231226040342-mutt-send-email-mst@kernel.org>
In-Reply-To: <20231226040342-mutt-send-email-mst@kernel.org>
From: Li Feng <fengli@smartx.com>
Date: Tue, 26 Dec 2023 20:14:13 +0800
Message-ID: <CAHckoCyBxHd6Lc8UPh_3urSHz_eDj6jrm+c80+wKBmypzjvz+A@mail.gmail.com>
Subject: Re: [PATCH] virtio_blk: set the default scheduler to none
To: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Jens Axboe <axboe@kernel.dk>, Jason Wang <jasowang@redhat.com>, 
	Paolo Bonzini <pbonzini@redhat.com>, Stefan Hajnoczi <stefanha@redhat.com>, 
	Xuan Zhuo <xuanzhuo@linux.alibaba.com>, 
	"open list:BLOCK LAYER" <linux-block@vger.kernel.org>, linux-kernel <linux-kernel@vger.kernel.org>, 
	"open list:VIRTIO BLOCK AND SCSI DRIVERS" <virtualization@lists.linux.dev>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

On Tue, Dec 26, 2023 at 5:05=E2=80=AFPM Michael S. Tsirkin <mst@redhat.com>=
 wrote:
>
> On Tue, Dec 26, 2023 at 05:01:40PM +0800, Li Feng wrote:
> > Hi MST and paolo,
> >
> > mq-deadline is good for slow media, and none is good for high-speed med=
ia.
> > It depends on how the community views this issue. When virtio-blk adopt=
s
> > multi-queue,it automatically changes from deadline to none, which is no=
t
> > uniform here.
>
> It's not virtio-blk changing though, it's linux doing that, right?
> Is virtio-blk special somehow?
>
Yes, it=E2=80=99s the common code path.

Each block driver has a chance to set the default none scheduler, like loop=
,
it has set the none as the default scheduler.

https://lkml.kernel.org/stable/20230809103647.895397540@linuxfoundation.org=
/

> > I don't have ideas right now to answer Christoph/Paolo's question.
> >
> > Thanks,
> > Li
>
> --
> MST
>