From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:42297) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1ZWKrw-0003eg-1h for qemu-devel@nongnu.org; Mon, 31 Aug 2015 04:55:13 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1ZWKrs-0008SU-4L for qemu-devel@nongnu.org; Mon, 31 Aug 2015 04:55:11 -0400 Received: from mx1.redhat.com ([209.132.183.28]:41174) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1ZWKrr-0008Om-Sh for qemu-devel@nongnu.org; Mon, 31 Aug 2015 04:55:08 -0400 References: <1432776186-24515-1-git-send-email-changchun.ouyang@intel.com> <55E32100.7020705@gmail.com> <82F45D86ADE5454A95A89742C8D1410E01DC7D42@shsmsx102.ccr.corp.intel.com> From: Marcel Apfelbaum Message-ID: <55E41665.8060407@redhat.com> Date: Mon, 31 Aug 2015 11:55:01 +0300 MIME-Version: 1.0 In-Reply-To: <82F45D86ADE5454A95A89742C8D1410E01DC7D42@shsmsx102.ccr.corp.intel.com> Content-Type: text/plain; charset=windows-1252; format=flowed Content-Transfer-Encoding: 7bit Subject: Re: [Qemu-devel] [PATCH v5] vhost-user: add multi queue support List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: "Xu, Qian Q" , "Ouyang, Changchun" , "qemu-devel@nongnu.org" , "mst@redhat.com" Cc: "snabb-devel@googlegroups.com" , "Liu, Yuanhan" , "n.nikolaev@virtualopensystems.com" , "luke@snabb.co" , "Long, Thomas" , "Fu, JingguoX" On 08/31/2015 08:42 AM, Xu, Qian Q wrote: > + 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. > Yes. Thanks a lot for the information! I'll give it a try, Marcel > Thanks > Qian > > -----Original Message----- > From: Ouyang, Changchun > Sent: Monday, August 31, 2015 1:29 PM > To: marcel@redhat.com; qemu-devel@nongnu.org; mst@redhat.com; Xu, Qian Q > Cc: snabb-devel@googlegroups.com; n.nikolaev@virtualopensystems.com; luke@snabb.co; Long, Thomas; Liu, Yuanhan; Ouyang, Changchun > Subject: RE: [Qemu-devel] [PATCH v5] vhost-user: add multi queue support > > >> -----Original Message----- >> From: Marcel Apfelbaum [mailto:marcel.apfelbaum@gmail.com] >> Sent: Sunday, August 30, 2015 11:28 PM >> To: Ouyang, Changchun; qemu-devel@nongnu.org; mst@redhat.com >> Cc: snabb-devel@googlegroups.com; n.nikolaev@virtualopensystems.com; >> luke@snabb.co; 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 >>> Signed-off-by: Changchun Ouyang >> 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. >>> >>> -@item -netdev vhost-user,chardev=@var{id}[,vhostforce=on|off] >>> +@item -netdev >>> +vhost-user,chardev=@var{id}[,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 -@var{vhostforce}. >>> +@var{vhostforce}. Use 'queues=@var{n}' to specify the number of >>> +queues to be created for multiqueue vhost-user. >>> >>> Example: >>> @example >>> >