All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Michael S. Tsirkin" <mst@redhat.com>
To: Raphael Norwitz <raphael.s.norwitz@gmail.com>
Cc: Kevin Wolf <kwolf@redhat.com>,
	Pankaj Gupta <pankaj.gupta.linux@gmail.com>,
	Eduardo Habkost <ehabkost@redhat.com>,
	qemu-block@nongnu.org, cohuck@redhat.com,
	QEMU <qemu-devel@nongnu.org>, Max Reitz <mreitz@redhat.com>,
	Stefan Hajnoczi <stefanha@redhat.com>,
	Paolo Bonzini <pbonzini@redhat.com>, Fam Zheng <fam@euphon.net>,
	Raphael Norwitz <raphael.norwitz@nutanix.com>
Subject: Re: [PATCH v4 5/5] vhost-user-blk: default num_queues to -smp N
Date: Tue, 9 Jun 2020 11:36:31 -0400	[thread overview]
Message-ID: <20200609113523-mutt-send-email-mst@kernel.org> (raw)
In-Reply-To: <CAFubqFuCk42dRtKvC=V-A288y7JC398-fWSDPx7YsU97O8foGg@mail.gmail.com>

On Sat, May 30, 2020 at 10:42:05PM -0400, Raphael Norwitz wrote:
> I'm happy with the code but as David pointed out with virtio-scsi, we
> should probably add a comment about virtio_pci_optimal_num_queues()
> capping the number of VQs here too.

Stefan could you add this tweak and repost pls? Thanks!


> 
> On Wed, May 27, 2020 at 6:34 AM Stefan Hajnoczi <stefanha@redhat.com> wrote:
> >
> > Automatically size the number of request virtqueues to match the number
> > of vCPUs.  This ensures that completion interrupts are handled on the
> > same vCPU that submitted the request.  No IPI is necessary to complete
> > an I/O request and performance is improved.
> >
> > Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
> > Reviewed-by: Cornelia Huck <cohuck@redhat.com>
> > ---
> >  include/hw/virtio/vhost-user-blk.h | 2 ++
> >  hw/block/vhost-user-blk.c          | 6 +++++-
> >  hw/core/machine.c                  | 1 +
> >  hw/virtio/vhost-user-blk-pci.c     | 4 ++++
> >  4 files changed, 12 insertions(+), 1 deletion(-)
> >
> > diff --git a/include/hw/virtio/vhost-user-blk.h b/include/hw/virtio/vhost-user-blk.h
> > index 34ad6f0c0e..292d17147c 100644
> > --- a/include/hw/virtio/vhost-user-blk.h
> > +++ b/include/hw/virtio/vhost-user-blk.h
> > @@ -25,6 +25,8 @@
> >  #define VHOST_USER_BLK(obj) \
> >          OBJECT_CHECK(VHostUserBlk, (obj), TYPE_VHOST_USER_BLK)
> >
> > +#define VHOST_USER_BLK_AUTO_NUM_QUEUES UINT16_MAX
> > +
> >  typedef struct VHostUserBlk {
> >      VirtIODevice parent_obj;
> >      CharBackend chardev;
> > diff --git a/hw/block/vhost-user-blk.c b/hw/block/vhost-user-blk.c
> > index 9d8c0b3909..7a8639516f 100644
> > --- a/hw/block/vhost-user-blk.c
> > +++ b/hw/block/vhost-user-blk.c
> > @@ -385,6 +385,9 @@ static void vhost_user_blk_device_realize(DeviceState *dev, Error **errp)
> >          return;
> >      }
> >
> > +    if (s->num_queues == VHOST_USER_BLK_AUTO_NUM_QUEUES) {
> > +        s->num_queues = 1;
> > +    }
> >      if (!s->num_queues || s->num_queues > VIRTIO_QUEUE_MAX) {
> >          error_setg(errp, "vhost-user-blk: invalid number of IO queues");
> >          return;
> > @@ -496,7 +499,8 @@ static const VMStateDescription vmstate_vhost_user_blk = {
> >
> >  static Property vhost_user_blk_properties[] = {
> >      DEFINE_PROP_CHR("chardev", VHostUserBlk, chardev),
> > -    DEFINE_PROP_UINT16("num-queues", VHostUserBlk, num_queues, 1),
> > +    DEFINE_PROP_UINT16("num-queues", VHostUserBlk, num_queues,
> > +                       VHOST_USER_BLK_AUTO_NUM_QUEUES),
> >      DEFINE_PROP_UINT32("queue-size", VHostUserBlk, queue_size, 128),
> >      DEFINE_PROP_BIT("config-wce", VHostUserBlk, config_wce, 0, true),
> >      DEFINE_PROP_END_OF_LIST(),
> > diff --git a/hw/core/machine.c b/hw/core/machine.c
> > index 4aba3bdd3c..8cc4b54eec 100644
> > --- a/hw/core/machine.c
> > +++ b/hw/core/machine.c
> > @@ -32,6 +32,7 @@ GlobalProperty hw_compat_5_0[] = {
> >      { "virtio-blk-device", "num-queues", "1"},
> >      { "virtio-scsi-device", "num_queues", "1"},
> >      { "vhost-scsi", "num_queues", "1"},
> > +    { "vhost-user-blk", "num-queues", "1"},
> >      { "vhost-user-scsi", "num_queues", "1"},
> >  };
> >  const size_t hw_compat_5_0_len = G_N_ELEMENTS(hw_compat_5_0);
> > diff --git a/hw/virtio/vhost-user-blk-pci.c b/hw/virtio/vhost-user-blk-pci.c
> > index 58d7c31735..1c8ab7f5e6 100644
> > --- a/hw/virtio/vhost-user-blk-pci.c
> > +++ b/hw/virtio/vhost-user-blk-pci.c
> > @@ -54,6 +54,10 @@ static void vhost_user_blk_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp)
> >      VHostUserBlkPCI *dev = VHOST_USER_BLK_PCI(vpci_dev);
> >      DeviceState *vdev = DEVICE(&dev->vdev);
> >
> > +    if (dev->vdev.num_queues == VHOST_USER_BLK_AUTO_NUM_QUEUES) {
> > +        dev->vdev.num_queues = virtio_pci_optimal_num_queues(0);
> > +    }
> > +
> >      if (vpci_dev->nvectors == DEV_NVECTORS_UNSPECIFIED) {
> >          vpci_dev->nvectors = dev->vdev.num_queues + 1;
> >      }
> > --
> > 2.25.4
> >



      reply	other threads:[~2020-06-09 15:37 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-05-27 10:29 [PATCH v4 0/5] virtio-pci: enable blk and scsi multi-queue by default Stefan Hajnoczi
2020-05-27 10:29 ` [PATCH v4 1/5] virtio-pci: add virtio_pci_optimal_num_queues() helper Stefan Hajnoczi
2020-05-28 15:35   ` Cornelia Huck
2020-06-09 15:37     ` Michael S. Tsirkin
2020-07-06 13:25     ` Stefan Hajnoczi
2020-07-06 14:14       ` Cornelia Huck
2020-05-27 10:29 ` [PATCH v4 2/5] virtio-scsi: introduce a constant for fixed virtqueues Stefan Hajnoczi
2020-05-28 14:18   ` Pankaj Gupta
2020-05-28 15:22   ` Philippe Mathieu-Daudé
2020-05-31  2:43   ` Raphael Norwitz
2020-05-27 10:29 ` [PATCH v4 3/5] virtio-scsi: default num_queues to -smp N Stefan Hajnoczi
2020-05-27 10:38   ` Daniel P. Berrangé
2020-05-28  8:50     ` Stefan Hajnoczi
2020-05-27 10:29 ` [PATCH v4 4/5] virtio-blk: " Stefan Hajnoczi
2020-05-28 14:45   ` Pankaj Gupta
2020-05-27 10:29 ` [PATCH v4 5/5] vhost-user-blk: " Stefan Hajnoczi
2020-05-31  2:42   ` Raphael Norwitz
2020-06-09 15:36     ` Michael S. Tsirkin [this message]

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=20200609113523-mutt-send-email-mst@kernel.org \
    --to=mst@redhat.com \
    --cc=cohuck@redhat.com \
    --cc=ehabkost@redhat.com \
    --cc=fam@euphon.net \
    --cc=kwolf@redhat.com \
    --cc=mreitz@redhat.com \
    --cc=pankaj.gupta.linux@gmail.com \
    --cc=pbonzini@redhat.com \
    --cc=qemu-block@nongnu.org \
    --cc=qemu-devel@nongnu.org \
    --cc=raphael.norwitz@nutanix.com \
    --cc=raphael.s.norwitz@gmail.com \
    --cc=stefanha@redhat.com \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.