Re: [Qemu-devel] [PATCH v5] vhost-user: add multi queue support

[Xu, Qian Q]

+ Jingguo, and he will be working on the vhost multi-queue support functional 
tests. 

Marcel, 
What you try to is to run dpdk-vhost sample and the dpdk-virtio(virtio-pmd) 
case? Attached the step-by-step guide of running it with one queue, you can 
update the multiple queue commands in it. 

Thanks
Qian

-----Original Message-----
From: Ouyang, Changchun 
Sent: Monday, August 31, 2015 1:29 PM
To: address@hidden; address@hidden; address@hidden; Xu, Qian Q
Cc: address@hidden; address@hidden; address@hidden; Long, Thomas; Liu, Yuanhan; 
Ouyang, Changchun
Subject: RE: [Qemu-devel] [PATCH v5] vhost-user: add multi queue support


> -----Original Message-----
> From: Marcel Apfelbaum [mailto:address@hidden
> Sent: Sunday, August 30, 2015 11:28 PM
> To: Ouyang, Changchun; address@hidden; address@hidden
> Cc: address@hidden; address@hidden;
> address@hidden; Long, Thomas
> Subject: Re: [Qemu-devel] [PATCH v5] vhost-user: add multi queue 
> support
> 
> On 05/28/2015 04:23 AM, Ouyang Changchun wrote:
> > Based on patch by Nikolay Nikolaev:
> > Vhost-user will implement the multi queue support in a similar way 
> > to what vhost already has - a separate thread for each queue.
> > To enable the multi queue functionality - a new command line 
> > parameter "queues" is introduced for the vhost-user netdev.
> >
> > Signed-off-by: Nikolay Nikolaev <address@hidden>
> > Signed-off-by: Changchun Ouyang <address@hidden>
> Hi,
> 
> Can you please share how you did you test it?
> Was it the DPDK vhost-user example? (after the MQ patches, of course) 
> I ask because I tried to test it with no success so far.
> Any pointers would be appreciated.
> 

Yes, I use DPDK vhost-user example to test it.
Hope the following link help you a bit.
http://article.gmane.org/gmane.comp.networking.dpdk.devel/22758/match=vhost+multiple

Qian and Yuanhan, maybe you can have more try and share more information here. 

Thanks
Changchun

> Thanks,
> Marcel
> 
> 
> > ---
> > Changes since v4:
> >   - remove the unnecessary trailing '\n'
> >
> > Changes since v3:
> >   - fix one typo and wrap one long line
> >
> > Changes since v2:
> >   - fix vq index issue for set_vring_call
> >     When it is the case of VHOST_SET_VRING_CALL, The vq_index is not
> initialized before it is used,
> >     thus it could be a random value. The random value leads to crash 
> > in vhost
> after passing down
> >     to vhost, as vhost use this random value to index an array index.
> >   - fix the typo in the doc and description
> >   - address vq index for reset_owner
> >
> > Changes since v1:
> >   - use s->nc.info_str when bringing up/down the backend
> >
> >   docs/specs/vhost-user.txt |  5 +++++
> >   hw/net/vhost_net.c        |  3 ++-
> >   hw/virtio/vhost-user.c    | 11 ++++++++++-
> >   net/vhost-user.c          | 37 ++++++++++++++++++++++++-------------
> >   qapi-schema.json          |  6 +++++-
> >   qemu-options.hx           |  5 +++--
> >   6 files changed, 49 insertions(+), 18 deletions(-)
> >
> > diff --git a/docs/specs/vhost-user.txt b/docs/specs/vhost-user.txt 
> > index 650bb18..2c8e934 100644
> > --- a/docs/specs/vhost-user.txt
> > +++ b/docs/specs/vhost-user.txt
> > @@ -127,6 +127,11 @@ in the ancillary data:
> >   If Master is unable to send the full message or receives a wrong 
> > reply it
> will
> >   close the connection. An optional reconnection mechanism can be
> implemented.
> >
> > +Multi queue support
> > +-------------------
> > +The protocol supports multiple queues by setting all index fields 
> > +in the sent messages to a properly calculated value.
> > +
> >   Message types
> >   -------------
> >
> > diff --git a/hw/net/vhost_net.c b/hw/net/vhost_net.c index 
> > 47f8b89..426b23e 100644
> > --- a/hw/net/vhost_net.c
> > +++ b/hw/net/vhost_net.c
> > @@ -157,6 +157,7 @@ struct vhost_net *vhost_net_init(VhostNetOptions
> > *options)
> >
> >       net->dev.nvqs = 2;
> >       net->dev.vqs = net->vqs;
> > +    net->dev.vq_index = net->nc->queue_index;
> >
> >       r = vhost_dev_init(&net->dev, options->opaque,
> >                          options->backend_type, options->force); @@
> > -267,7 +268,7 @@ static void vhost_net_stop_one(struct vhost_net *net,
> >           for (file.index = 0; file.index < net->dev.nvqs; ++file.index) {
> >               const VhostOps *vhost_ops = net->dev.vhost_ops;
> >               int r = vhost_ops->vhost_call(&net->dev, VHOST_RESET_OWNER,
> > -                                          NULL);
> > +                                          &file);
> >               assert(r >= 0);
> >           }
> >       }
> > diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c index
> > e7ab829..d6f2163 100644
> > --- a/hw/virtio/vhost-user.c
> > +++ b/hw/virtio/vhost-user.c
> > @@ -210,7 +210,12 @@ static int vhost_user_call(struct vhost_dev 
> > *dev,
> unsigned long int request,
> >           break;
> >
> >       case VHOST_SET_OWNER:
> > +        break;
> > +
> >       case VHOST_RESET_OWNER:
> > +        memcpy(&msg.state, arg, sizeof(struct vhost_vring_state));
> > +        msg.state.index += dev->vq_index;
> > +        msg.size = sizeof(m.state);
> >           break;
> >
> >       case VHOST_SET_MEM_TABLE:
> > @@ -253,17 +258,20 @@ static int vhost_user_call(struct vhost_dev 
> > *dev,
> unsigned long int request,
> >       case VHOST_SET_VRING_NUM:
> >       case VHOST_SET_VRING_BASE:
> >           memcpy(&msg.state, arg, sizeof(struct vhost_vring_state));
> > +        msg.state.index += dev->vq_index;
> >           msg.size = sizeof(m.state);
> >           break;
> >
> >       case VHOST_GET_VRING_BASE:
> >           memcpy(&msg.state, arg, sizeof(struct vhost_vring_state));
> > +        msg.state.index += dev->vq_index;
> >           msg.size = sizeof(m.state);
> >           need_reply = 1;
> >           break;
> >
> >       case VHOST_SET_VRING_ADDR:
> >           memcpy(&msg.addr, arg, sizeof(struct vhost_vring_addr));
> > +        msg.addr.index += dev->vq_index;
> >           msg.size = sizeof(m.addr);
> >           break;
> >
> > @@ -271,7 +279,7 @@ static int vhost_user_call(struct vhost_dev 
> > *dev,
> unsigned long int request,
> >       case VHOST_SET_VRING_CALL:
> >       case VHOST_SET_VRING_ERR:
> >           file = arg;
> > -        msg.u64 = file->index & VHOST_USER_VRING_IDX_MASK;
> > +        msg.u64 = (file->index + dev->vq_index) & 
> > + VHOST_USER_VRING_IDX_MASK;
> >           msg.size = sizeof(m.u64);
> >           if (ioeventfd_enabled() && file->fd > 0) {
> >               fds[fd_num++] = file->fd; @@ -313,6 +321,7 @@ static 
> > int vhost_user_call(struct vhost_dev *dev, unsigned long int request,
> >                   error_report("Received bad msg size.");
> >                   return -1;
> >               }
> > +            msg.state.index -= dev->vq_index;
> >               memcpy(arg, &msg.state, sizeof(struct vhost_vring_state));
> >               break;
> >           default:
> > diff --git a/net/vhost-user.c b/net/vhost-user.c index 
> > 1d86a2b..904d8af 100644
> > --- a/net/vhost-user.c
> > +++ b/net/vhost-user.c
> > @@ -121,35 +121,39 @@ static void net_vhost_user_event(void *opaque,
> int event)
> >       case CHR_EVENT_OPENED:
> >           vhost_user_start(s);
> >           net_vhost_link_down(s, false);
> > -        error_report("chardev \"%s\" went up", s->chr->label);
> > +        error_report("chardev \"%s\" went up", s->nc.info_str);
> >           break;
> >       case CHR_EVENT_CLOSED:
> >           net_vhost_link_down(s, true);
> >           vhost_user_stop(s);
> > -        error_report("chardev \"%s\" went down", s->chr->label);
> > +        error_report("chardev \"%s\" went down", s->nc.info_str);
> >           break;
> >       }
> >   }
> >
> >   static int net_vhost_user_init(NetClientState *peer, const char *device,
> > -                               const char *name, CharDriverState *chr)
> > +                               const char *name, CharDriverState *chr,
> > +                               uint32_t queues)
> >   {
> >       NetClientState *nc;
> >       VhostUserState *s;
> > +    int i;
> >
> > -    nc = qemu_new_net_client(&net_vhost_user_info, peer, device,
> name);
> > +    for (i = 0; i < queues; i++) {
> > +        nc = qemu_new_net_client(&net_vhost_user_info, peer, 
> > + device, name);
> >
> > -    snprintf(nc->info_str, sizeof(nc->info_str), "vhost-user to %s",
> > -             chr->label);
> > +        snprintf(nc->info_str, sizeof(nc->info_str), "vhost-user%d to %s",
> > +                 i, chr->label);
> >
> > -    s = DO_UPCAST(VhostUserState, nc, nc);
> > +        s = DO_UPCAST(VhostUserState, nc, nc);
> >
> > -    /* We don't provide a receive callback */
> > -    s->nc.receive_disabled = 1;
> > -    s->chr = chr;
> > -
> > -    qemu_chr_add_handlers(s->chr, NULL, NULL, net_vhost_user_event,
> s);
> > +        /* We don't provide a receive callback */
> > +        s->nc.receive_disabled = 1;
> > +        s->chr = chr;
> > +        s->nc.queue_index = i;
> >
> > +        qemu_chr_add_handlers(s->chr, NULL, NULL, 
> > + net_vhost_user_event,
> s);
> > +    }
> >       return 0;
> >   }
> >
> > @@ -225,6 +229,7 @@ static int net_vhost_check_net(QemuOpts *opts,
> void *opaque)
> >   int net_init_vhost_user(const NetClientOptions *opts, const char *name,
> >                           NetClientState *peer)
> >   {
> > +    uint32_t queues;
> >       const NetdevVhostUserOptions *vhost_user_opts;
> >       CharDriverState *chr;
> >
> > @@ -243,6 +248,12 @@ int net_init_vhost_user(const NetClientOptions
> *opts, const char *name,
> >           return -1;
> >       }
> >
> > +    /* number of queues for multiqueue */
> > +    if (vhost_user_opts->has_queues) {
> > +        queues = vhost_user_opts->queues;
> > +    } else {
> > +        queues = 1;
> > +    }
> >
> > -    return net_vhost_user_init(peer, "vhost_user", name, chr);
> > +    return net_vhost_user_init(peer, "vhost_user", name, chr, 
> > + queues);
> >   }
> > diff --git a/qapi-schema.json b/qapi-schema.json index 
> > f97ffa1..00791dd 100644
> > --- a/qapi-schema.json
> > +++ b/qapi-schema.json
> > @@ -2444,12 +2444,16 @@
> >   #
> >   # @vhostforce: #optional vhost on for non-MSIX virtio guests (default:
> false).
> >   #
> > +# @queues: #optional number of queues to be created for multiqueue
> vhost-user
> > +#          (default: 1) (Since 2.4)
> > +#
> >   # Since 2.1
> >   ##
> >   { 'struct': 'NetdevVhostUserOptions',
> >     'data': {
> >       'chardev':        'str',
> > -    '*vhostforce':    'bool' } }
> > +    '*vhostforce':    'bool',
> > +    '*queues':        'uint32' } }
> >
> >   ##
> >   # @NetClientOptions
> > diff --git a/qemu-options.hx b/qemu-options.hx index 
> > ec356f6..dad035e
> > 100644
> > --- a/qemu-options.hx
> > +++ b/qemu-options.hx
> > @@ -1942,13 +1942,14 @@ The hubport netdev lets you connect a NIC to 
> > a
> QEMU "vlan" instead of a single
> >   netdev.  @code{-net} and @code{-device} with parameter 
> > @option{vlan}
> create the
> >   required hub automatically.
> >
> > address@hidden -netdev vhost-user,address@hidden,vhostforce=on|off]
> > address@hidden -netdev
> > +vhost-user,address@hidden,vhostforce=on|off][,queues=n]
> >
> >   Establish a vhost-user netdev, backed by a chardev @var{id}. The 
> > chardev
> should
> >   be a unix domain socket backed one. The vhost-user uses a 
> > specifically
> defined
> >   protocol to pass vhost ioctl replacement messages to an 
> > application on the
> other
> >   end of the socket. On non-MSIX guests, the feature can be forced 
> > with address@hidden
> > address@hidden Use 'address@hidden' to specify the number of 
> > +queues to be created for multiqueue vhost-user.
> >
> >   Example:
> >   @example
> >

Vhost-GSG.docx
Description: Vhost-GSG.docx