* [RFC] Discuss about an new idea "Vsock over Virtio-net"
@ 2018-11-15 3:56 jiangyiwen
2018-11-15 4:19 ` Jason Wang
` (2 more replies)
0 siblings, 3 replies; 29+ messages in thread
From: jiangyiwen @ 2018-11-15 3:56 UTC (permalink / raw)
To: stefanha, stefanha, Jason Wang, mst; +Cc: netdev, kvm, virtualization
Hi Stefan, Michael, Jason and everyone,
Several days ago, I discussed with jason about "Vsock over Virtio-net".
This idea has two advantages:
First, it can use many great features of virtio-net, like batching,
mergeable rx buffer and multiqueue, etc.
Second, it can reduce many duplicate codes and make it easy to be
maintained.
Before the implement, I want to discuss with everyone again, and
want to know everyone's suggestions.
After the discussion, based on this point I will try to implement
this idea, but I am not familiar with the virtio-net, that is a
pity. :(
-------------------------Simple idea------------------------------
1. The packet layout will become as follows:
+---------------------------------+
| Virtio-net header |
|(struct virtio_net_hdr_mrg_rxbuf)|
+---------------------------------+
| Vsock header |
| (struct virtio_vsock_hdr) |
+---------------------------------+
| payload |
| (until end of packet) |
+---------------------------------+
2. The Guest->Host basic code flow as follow:
+------------+
| Client |
+------------+
|
|
+------------------------------------------------------------------+
|VSOCK Core Module |
|ops->sendmsg; (vsock_stream_sendmsg) |
| -> alloc_skb; /* it will packet a skb buffer, and include vsock |
| * hdr and payload */ |
| -> dev_queue_xmit(); /* it will call start_xmit(virtio-net.c) */|
|vsock hdr and payload, and then call |
+------------------------------------------------------------------+
|
|
+------------------------------------------------------------------+
|Virtio-net Module |
|start_xmit |
| -> add virtio_net_hdr and pack sg in ring desc, notify Host |
+------------------------------------------------------------------+
|
|
+------------------------------------------------------------------+
|Vhost-net Module |
|handle_tx |
| -> get tx buffer, skip virtio_net_hdr and call Vsock function. |
| /* This point has some differences, vhost-net use ->sendmsg to |
| * forward information, however vsock only need to notify server |
| * that data ready. */ |
+------------------------------------------------------------------+
|
|
+------------------------------------------------------------------+
|VSOCK Core Module |
|alloc_pkt, copy skb data to pkt. |
|add pkt to rx_queue and notify server to get data. |
+------------------------------------------------------------------+
3. To Host->Guest
I have a problem and difficult, mainly I know about virtio-net a little),
because I have been doing work related with storage and file system.
The problem as follows:
we should monitor all of socket of vsock in handle_rx, when there are
data coming, and copy data to vq desc. Vhost-net use ->recvmsg to
get data, it is different with socket. To vsock, I think host will
not call ->recvmsg when it need to send message to guest. To net,
vhost-net only as forwarding layer.
^ permalink raw reply [flat|nested] 29+ messages in thread
* Re: [RFC] Discuss about an new idea "Vsock over Virtio-net"
2018-11-15 3:56 [RFC] Discuss about an new idea "Vsock over Virtio-net" jiangyiwen
@ 2018-11-15 4:19 ` Jason Wang
2018-11-15 6:46 ` jiangyiwen
2018-11-15 7:04 ` Michael S. Tsirkin
2018-11-15 9:36 ` Yan Vugenfirer
2 siblings, 1 reply; 29+ messages in thread
From: Jason Wang @ 2018-11-15 4:19 UTC (permalink / raw)
To: jiangyiwen, stefanha, stefanha, mst; +Cc: netdev, kvm, virtualization
On 2018/11/15 上午11:56, jiangyiwen wrote:
> Hi Stefan, Michael, Jason and everyone,
>
> Several days ago, I discussed with jason about "Vsock over Virtio-net".
> This idea has two advantages:
> First, it can use many great features of virtio-net, like batching,
> mergeable rx buffer and multiqueue, etc.
> Second, it can reduce many duplicate codes and make it easy to be
> maintained.
>
> Before the implement, I want to discuss with everyone again, and
> want to know everyone's suggestions.
>
> After the discussion, based on this point I will try to implement
> this idea, but I am not familiar with the virtio-net, that is a
> pity. :(
I think we should have a new feature flag for this. E.g
VIRTIO_NET_F_VSOCK. And host should fail the negotiation if guest
doesn't support this to avoid confusion. When this feature is
negotiated, we will use it only for VOSCK transport. This can simplify
things somehow.
> -------------------------Simple idea------------------------------
>
> 1. The packet layout will become as follows:
>
> +---------------------------------+
> | Virtio-net header |
> |(struct virtio_net_hdr_mrg_rxbuf)|
> +---------------------------------+
> | Vsock header |
> | (struct virtio_vsock_hdr) |
> +---------------------------------+
> | payload |
> | (until end of packet) |
> +---------------------------------+
>
> 2. The Guest->Host basic code flow as follow:
> +------------+
> | Client |
> +------------+
> |
> |
> +------------------------------------------------------------------+
> |VSOCK Core Module |
> |ops->sendmsg; (vsock_stream_sendmsg) |
> | -> alloc_skb; /* it will packet a skb buffer, and include vsock |
> | * hdr and payload */ |
> | -> dev_queue_xmit(); /* it will call start_xmit(virtio-net.c) */|
> |vsock hdr and payload, and then call |
> +------------------------------------------------------------------+
Note, if we've negotiated the feature, virtio-net driver must not use
register_netdev to register it to network core. This can avoid lots of
confusion.
> |
> |
> +------------------------------------------------------------------+
> |Virtio-net Module |
> |start_xmit |
> | -> add virtio_net_hdr and pack sg in ring desc, notify Host |
> +------------------------------------------------------------------+
> |
> |
> +------------------------------------------------------------------+
> |Vhost-net Module |
> |handle_tx |
> | -> get tx buffer, skip virtio_net_hdr and call Vsock function. |
> | /* This point has some differences, vhost-net use ->sendmsg to |
> | * forward information, however vsock only need to notify server |
> | * that data ready. */ |
> +------------------------------------------------------------------+
When VIRTIO_NET_F_VOSCK is negotiated, we know that it's a vsock
transport, we can then forward it to vsock core.
> |
> |
> +------------------------------------------------------------------+
> |VSOCK Core Module |
> |alloc_pkt, copy skb data to pkt. |
> |add pkt to rx_queue and notify server to get data. |
> +------------------------------------------------------------------+
>
> 3. To Host->Guest
> I have a problem and difficult, mainly I know about virtio-net a little),
> because I have been doing work related with storage and file system.
>
> The problem as follows:
> we should monitor all of socket of vsock in handle_rx, when there are
> data coming, and copy data to vq desc. Vhost-net use ->recvmsg to
> get data, it is different with socket. To vsock, I think host will
> not call ->recvmsg when it need to send message to guest. To net,
> vhost-net only as forwarding layer.
Know not much here, but is it possible to have a vsock(tap) to be passed
to vhost_net and let vhost call its recvmgs()? Bascially it was a socket
on host as well I believe?
If this doesn't work, we can have vsock specific receiving routine in
vhost_net if VIRTIO_NET_F_VOSCK is negotiated.
Generally, I think we should try out best to keep the exist
sendmsg()/recvmsg() interfaces and only consider the alternatives if we
meet some real blocker.
Thanks
>
^ permalink raw reply [flat|nested] 29+ messages in thread
* Re: [RFC] Discuss about an new idea "Vsock over Virtio-net"
2018-11-15 4:19 ` Jason Wang
@ 2018-11-15 6:46 ` jiangyiwen
2018-11-15 6:49 ` jiangyiwen
2018-11-15 8:19 ` Jason Wang
0 siblings, 2 replies; 29+ messages in thread
From: jiangyiwen @ 2018-11-15 6:46 UTC (permalink / raw)
To: Jason Wang, stefanha, stefanha, mst; +Cc: netdev, kvm, virtualization
On 2018/11/15 12:19, Jason Wang wrote:
>
> On 2018/11/15 上午11:56, jiangyiwen wrote:
>> Hi Stefan, Michael, Jason and everyone,
>>
>> Several days ago, I discussed with jason about "Vsock over Virtio-net".
>> This idea has two advantages:
>> First, it can use many great features of virtio-net, like batching,
>> mergeable rx buffer and multiqueue, etc.
>> Second, it can reduce many duplicate codes and make it easy to be
>> maintained.
>>
>> Before the implement, I want to discuss with everyone again, and
>> want to know everyone's suggestions.
>>
>> After the discussion, based on this point I will try to implement
>> this idea, but I am not familiar with the virtio-net, that is a
>> pity. :(
>
>
> I think we should have a new feature flag for this. E.g VIRTIO_NET_F_VSOCK. And host should fail the negotiation if guest doesn't support this to avoid confusion. When this feature is negotiated, we will use it only for VOSCK transport. This can simplify things somehow.
>
>
>> -------------------------Simple idea------------------------------
>>
>> 1. The packet layout will become as follows:
>>
>> +---------------------------------+
>> | Virtio-net header |
>> |(struct virtio_net_hdr_mrg_rxbuf)|
>> +---------------------------------+
>> | Vsock header |
>> | (struct virtio_vsock_hdr) |
>> +---------------------------------+
>> | payload |
>> | (until end of packet) |
>> +---------------------------------+
>>
>> 2. The Guest->Host basic code flow as follow:
>> +------------+
>> | Client |
>> +------------+
>> |
>> |
>> +------------------------------------------------------------------+
>> |VSOCK Core Module |
>> |ops->sendmsg; (vsock_stream_sendmsg) |
>> | -> alloc_skb; /* it will packet a skb buffer, and include vsock |
>> | * hdr and payload */ |
>> | -> dev_queue_xmit(); /* it will call start_xmit(virtio-net.c) */|
>> |vsock hdr and payload, and then call |
>> +------------------------------------------------------------------+
>
>
> Note, if we've negotiated the feature, virtio-net driver must not use register_netdev to register it to network core. This can avoid lots of confusion.
Hi Jason,
You mean we should not register netdev if use vsock, and in order to
avoid confusion, then I think whether we should keep vsock and export
some virtio-net's functions that can be shared. In this way, first, vsock
may keep existing architecture and will not affect virtio-net. In addition,
vsock doesn't need to use virtio_net header too, then it don't need to pack
skb structure.
Thanks,
Yiwen.
>
>
>> |
>> |
>> +------------------------------------------------------------------+
>> |Virtio-net Module |
>> |start_xmit |
>> | -> add virtio_net_hdr and pack sg in ring desc, notify Host |
>> +------------------------------------------------------------------+
>> |
>> |
>> +------------------------------------------------------------------+
>> |Vhost-net Module |
>> |handle_tx |
>> | -> get tx buffer, skip virtio_net_hdr and call Vsock function. |
>> | /* This point has some differences, vhost-net use ->sendmsg to |
>> | * forward information, however vsock only need to notify server |
>> | * that data ready. */ |
>> +------------------------------------------------------------------+
>
>
> When VIRTIO_NET_F_VOSCK is negotiated, we know that it's a vsock transport, we can then forward it to vsock core.
>
>
>> |
>> |
>> +------------------------------------------------------------------+
>> |VSOCK Core Module |
>> |alloc_pkt, copy skb data to pkt. |
>> |add pkt to rx_queue and notify server to get data. |
>> +------------------------------------------------------------------+
>>
>> 3. To Host->Guest
>> I have a problem and difficult, mainly I know about virtio-net a little),
>> because I have been doing work related with storage and file system.
>>
>> The problem as follows:
>> we should monitor all of socket of vsock in handle_rx, when there are
>> data coming, and copy data to vq desc. Vhost-net use ->recvmsg to
>> get data, it is different with socket. To vsock, I think host will
>> not call ->recvmsg when it need to send message to guest. To net,
>> vhost-net only as forwarding layer.
>
> Know not much here, but is it possible to have a vsock(tap) to be passed to vhost_net and let vhost call its recvmgs()? Bascially it was a socket on host as well I believe?
For vsock, Host->Guest, it's code flow as follows:
Server call send()
-> sendmsg(); (vsock_stream_sendmsg)
-> virtio_trasnport_send_pkt_info
-> alloc pkt, add pkt to send_pkt_list, wake up vhost_worker
Vhost_worker
-> vhost_transport_send_pkt_work
-> get pkt from send_pkt_list
-> get vq input desc and then fill data to desc addr
-> update used ring and then signal guest
In the whole process, host don't call recvmsg() because it is a net device, and
it also receives any messages.
For vhost-net, I understand it is a tap device, so it can receive messages
from other net device.
This is my understanding, it may have some errors.
Thanks.
>
> If this doesn't work, we can have vsock specific receiving routine in vhost_net if VIRTIO_NET_F_VOSCK is negotiated.
>
> Generally, I think we should try out best to keep the exist sendmsg()/recvmsg() interfaces and only consider the alternatives if we meet some real blocker.
>
> Thanks
>
>
>>
>
> .
>
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
^ permalink raw reply [flat|nested] 29+ messages in thread
* Re: [RFC] Discuss about an new idea "Vsock over Virtio-net"
2018-11-15 6:46 ` jiangyiwen
@ 2018-11-15 6:49 ` jiangyiwen
2018-11-15 8:19 ` Jason Wang
1 sibling, 0 replies; 29+ messages in thread
From: jiangyiwen @ 2018-11-15 6:49 UTC (permalink / raw)
To: Jason Wang, stefanha, stefanha, mst; +Cc: netdev, kvm, virtualization
On 2018/11/15 14:46, jiangyiwen wrote:
> On 2018/11/15 12:19, Jason Wang wrote:
>>
>> On 2018/11/15 上午11:56, jiangyiwen wrote:
>>> Hi Stefan, Michael, Jason and everyone,
>>>
>>> Several days ago, I discussed with jason about "Vsock over Virtio-net".
>>> This idea has two advantages:
>>> First, it can use many great features of virtio-net, like batching,
>>> mergeable rx buffer and multiqueue, etc.
>>> Second, it can reduce many duplicate codes and make it easy to be
>>> maintained.
>>>
>>> Before the implement, I want to discuss with everyone again, and
>>> want to know everyone's suggestions.
>>>
>>> After the discussion, based on this point I will try to implement
>>> this idea, but I am not familiar with the virtio-net, that is a
>>> pity. :(
>>
>>
>> I think we should have a new feature flag for this. E.g VIRTIO_NET_F_VSOCK. And host should fail the negotiation if guest doesn't support this to avoid confusion. When this feature is negotiated, we will use it only for VOSCK transport. This can simplify things somehow.
>>
>>
>>> -------------------------Simple idea------------------------------
>>>
>>> 1. The packet layout will become as follows:
>>>
>>> +---------------------------------+
>>> | Virtio-net header |
>>> |(struct virtio_net_hdr_mrg_rxbuf)|
>>> +---------------------------------+
>>> | Vsock header |
>>> | (struct virtio_vsock_hdr) |
>>> +---------------------------------+
>>> | payload |
>>> | (until end of packet) |
>>> +---------------------------------+
>>>
>>> 2. The Guest->Host basic code flow as follow:
>>> +------------+
>>> | Client |
>>> +------------+
>>> |
>>> |
>>> +------------------------------------------------------------------+
>>> |VSOCK Core Module |
>>> |ops->sendmsg; (vsock_stream_sendmsg) |
>>> | -> alloc_skb; /* it will packet a skb buffer, and include vsock |
>>> | * hdr and payload */ |
>>> | -> dev_queue_xmit(); /* it will call start_xmit(virtio-net.c) */|
>>> |vsock hdr and payload, and then call |
>>> +------------------------------------------------------------------+
>>
>>
>> Note, if we've negotiated the feature, virtio-net driver must not use register_netdev to register it to network core. This can avoid lots of confusion.
>
> Hi Jason,
>
> You mean we should not register netdev if use vsock, and in order to
> avoid confusion, then I think whether we should keep vsock and export
> some virtio-net's functions that can be shared. In this way, first, vsock
> may keep existing architecture and will not affect virtio-net. In addition,
> vsock doesn't need to use virtio_net header too, then it don't need to pack
> skb structure.
>
> Thanks,
> Yiwen.
>
>>
>>
>>> |
>>> |
>>> +------------------------------------------------------------------+
>>> |Virtio-net Module |
>>> |start_xmit |
>>> | -> add virtio_net_hdr and pack sg in ring desc, notify Host |
>>> +------------------------------------------------------------------+
>>> |
>>> |
>>> +------------------------------------------------------------------+
>>> |Vhost-net Module |
>>> |handle_tx |
>>> | -> get tx buffer, skip virtio_net_hdr and call Vsock function. |
>>> | /* This point has some differences, vhost-net use ->sendmsg to |
>>> | * forward information, however vsock only need to notify server |
>>> | * that data ready. */ |
>>> +------------------------------------------------------------------+
>>
>>
>> When VIRTIO_NET_F_VOSCK is negotiated, we know that it's a vsock transport, we can then forward it to vsock core.
>>
>>
>>> |
>>> |
>>> +------------------------------------------------------------------+
>>> |VSOCK Core Module |
>>> |alloc_pkt, copy skb data to pkt. |
>>> |add pkt to rx_queue and notify server to get data. |
>>> +------------------------------------------------------------------+
>>>
>>> 3. To Host->Guest
>>> I have a problem and difficult, mainly I know about virtio-net a little),
>>> because I have been doing work related with storage and file system.
>>>
>>> The problem as follows:
>>> we should monitor all of socket of vsock in handle_rx, when there are
>>> data coming, and copy data to vq desc. Vhost-net use ->recvmsg to
>>> get data, it is different with socket. To vsock, I think host will
>>> not call ->recvmsg when it need to send message to guest. To net,
>>> vhost-net only as forwarding layer.
>>
>> Know not much here, but is it possible to have a vsock(tap) to be passed to vhost_net and let vhost call its recvmgs()? Bascially it was a socket on host as well I believe?
>
> For vsock, Host->Guest, it's code flow as follows:
> Server call send()
> -> sendmsg(); (vsock_stream_sendmsg)
> -> virtio_trasnport_send_pkt_info
> -> alloc pkt, add pkt to send_pkt_list, wake up vhost_worker
>
> Vhost_worker
> -> vhost_transport_send_pkt_work
> -> get pkt from send_pkt_list
> -> get vq input desc and then fill data to desc addr
> -> update used ring and then signal guest
>
> In the whole process, host don't call recvmsg() because it is a net device, and
> it also receives any messages.
Sorry, it is *not* a net device, it *does not* receive any messages.
Thanks.
>
> For vhost-net, I understand it is a tap device, so it can receive messages
> from other net device.
>
> This is my understanding, it may have some errors.
>
> Thanks.
>
>>
>> If this doesn't work, we can have vsock specific receiving routine in vhost_net if VIRTIO_NET_F_VOSCK is negotiated.
>>
>> Generally, I think we should try out best to keep the exist sendmsg()/recvmsg() interfaces and only consider the alternatives if we meet some real blocker.
>>
>> Thanks
>>
>>
>>>
>>
>> .
>>
>
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
^ permalink raw reply [flat|nested] 29+ messages in thread
* Re: [RFC] Discuss about an new idea "Vsock over Virtio-net"
2018-11-15 3:56 [RFC] Discuss about an new idea "Vsock over Virtio-net" jiangyiwen
2018-11-15 4:19 ` Jason Wang
@ 2018-11-15 7:04 ` Michael S. Tsirkin
2018-11-15 7:38 ` jiangyiwen
2018-11-15 8:24 ` Jason Wang
2018-11-15 9:36 ` Yan Vugenfirer
2 siblings, 2 replies; 29+ messages in thread
From: Michael S. Tsirkin @ 2018-11-15 7:04 UTC (permalink / raw)
To: jiangyiwen; +Cc: stefanha, stefanha, Jason Wang, netdev, kvm, virtualization
On Thu, Nov 15, 2018 at 11:56:03AM +0800, jiangyiwen wrote:
> Hi Stefan, Michael, Jason and everyone,
>
> Several days ago, I discussed with jason about "Vsock over Virtio-net".
> This idea has two advantages:
> First, it can use many great features of virtio-net, like batching,
> mergeable rx buffer and multiqueue, etc.
> Second, it can reduce many duplicate codes and make it easy to be
> maintained.
I'm not sure I get the motivation. Which features of
virtio net are relevant to vsock? The ones that you mention
all seem to be mostly of use to the networking stack.
> Before the implement, I want to discuss with everyone again, and
> want to know everyone's suggestions.
>
> After the discussion, based on this point I will try to implement
> this idea, but I am not familiar with the virtio-net, that is a
> pity. :(
>
> -------------------------Simple idea------------------------------
>
> 1. The packet layout will become as follows:
>
> +---------------------------------+
> | Virtio-net header |
> |(struct virtio_net_hdr_mrg_rxbuf)|
Which fields in virtio_net_hdr_mrg_rxbuf are of interest to vsock?
> +---------------------------------+
> | Vsock header |
> | (struct virtio_vsock_hdr) |
> +---------------------------------+
> | payload |
> | (until end of packet) |
> +---------------------------------+
Thanks,
--
MST
^ permalink raw reply [flat|nested] 29+ messages in thread
* Re: [RFC] Discuss about an new idea "Vsock over Virtio-net"
2018-11-15 7:04 ` Michael S. Tsirkin
@ 2018-11-15 7:38 ` jiangyiwen
2018-11-15 8:10 ` Michael S. Tsirkin
2018-11-15 8:24 ` Jason Wang
1 sibling, 1 reply; 29+ messages in thread
From: jiangyiwen @ 2018-11-15 7:38 UTC (permalink / raw)
To: Michael S. Tsirkin; +Cc: kvm, virtualization, stefanha, netdev
On 2018/11/15 15:04, Michael S. Tsirkin wrote:
> On Thu, Nov 15, 2018 at 11:56:03AM +0800, jiangyiwen wrote:
>> Hi Stefan, Michael, Jason and everyone,
>>
>> Several days ago, I discussed with jason about "Vsock over Virtio-net".
>> This idea has two advantages:
>> First, it can use many great features of virtio-net, like batching,
>> mergeable rx buffer and multiqueue, etc.
>> Second, it can reduce many duplicate codes and make it easy to be
>> maintained.
>
> I'm not sure I get the motivation. Which features of
> virtio net are relevant to vsock? The ones that you mention
> all seem to be mostly of use to the networking stack.
>
>
>> Before the implement, I want to discuss with everyone again, and
>> want to know everyone's suggestions.
>>
>> After the discussion, based on this point I will try to implement
>> this idea, but I am not familiar with the virtio-net, that is a
>> pity. :(
>>
>> -------------------------Simple idea------------------------------
>>
>> 1. The packet layout will become as follows:
>>
>> +---------------------------------+
>> | Virtio-net header |
>> |(struct virtio_net_hdr_mrg_rxbuf)|
>
> Which fields in virtio_net_hdr_mrg_rxbuf are of interest to vsock?
>
Hi Michael,
Yes, currently vsock has poor performance, first, it only support transport
small packet, in order to make the balance between performance and guest memory.
In order to solve this problem, there are two features vsock can used,
mergeable rx buffer and multiqueue. Based on this, there are some shared
codes vsock can use.
Thanks,
Yiwen.
>> +---------------------------------+
>> | Vsock header |
>> | (struct virtio_vsock_hdr) |
>> +---------------------------------+
>> | payload |
>> | (until end of packet) |
>> +---------------------------------+
>
> Thanks,
>
^ permalink raw reply [flat|nested] 29+ messages in thread
* Re: [RFC] Discuss about an new idea "Vsock over Virtio-net"
2018-11-15 7:38 ` jiangyiwen
@ 2018-11-15 8:10 ` Michael S. Tsirkin
2018-11-15 8:27 ` Jason Wang
2018-11-15 8:38 ` jiangyiwen
0 siblings, 2 replies; 29+ messages in thread
From: Michael S. Tsirkin @ 2018-11-15 8:10 UTC (permalink / raw)
To: jiangyiwen; +Cc: kvm, virtualization, stefanha, netdev
On Thu, Nov 15, 2018 at 03:38:15PM +0800, jiangyiwen wrote:
> On 2018/11/15 15:04, Michael S. Tsirkin wrote:
> > On Thu, Nov 15, 2018 at 11:56:03AM +0800, jiangyiwen wrote:
> >> Hi Stefan, Michael, Jason and everyone,
> >>
> >> Several days ago, I discussed with jason about "Vsock over Virtio-net".
> >> This idea has two advantages:
> >> First, it can use many great features of virtio-net, like batching,
> >> mergeable rx buffer and multiqueue, etc.
> >> Second, it can reduce many duplicate codes and make it easy to be
> >> maintained.
> >
> > I'm not sure I get the motivation. Which features of
> > virtio net are relevant to vsock? The ones that you mention
> > all seem to be mostly of use to the networking stack.
> >
> >
> >> Before the implement, I want to discuss with everyone again, and
> >> want to know everyone's suggestions.
> >>
> >> After the discussion, based on this point I will try to implement
> >> this idea, but I am not familiar with the virtio-net, that is a
> >> pity. :(
> >>
> >> -------------------------Simple idea------------------------------
> >>
> >> 1. The packet layout will become as follows:
> >>
> >> +---------------------------------+
> >> | Virtio-net header |
> >> |(struct virtio_net_hdr_mrg_rxbuf)|
> >
> > Which fields in virtio_net_hdr_mrg_rxbuf are of interest to vsock?
> >
>
> Hi Michael,
>
> Yes, currently vsock has poor performance, first, it only support transport
> small packet, in order to make the balance between performance and guest memory.
>
> In order to solve this problem, there are two features vsock can used,
> mergeable rx buffer and multiqueue. Based on this, there are some shared
> codes vsock can use.
>
> Thanks,
> Yiwen.
Supporting more queues with vsock is probably significantly
less work than a completely new interface.
For mergeable, as buffers are split arbitrarily, why can't you combine
them within guest driver before sending them up the stack?
Probably better than relying on host to do it.
> >> +---------------------------------+
> >> | Vsock header |
> >> | (struct virtio_vsock_hdr) |
> >> +---------------------------------+
> >> | payload |
> >> | (until end of packet) |
> >> +---------------------------------+
> >
> > Thanks,
> >
>
^ permalink raw reply [flat|nested] 29+ messages in thread
* Re: [RFC] Discuss about an new idea "Vsock over Virtio-net"
2018-11-15 6:46 ` jiangyiwen
2018-11-15 6:49 ` jiangyiwen
@ 2018-11-15 8:19 ` Jason Wang
2018-11-15 9:02 ` jiangyiwen
1 sibling, 1 reply; 29+ messages in thread
From: Jason Wang @ 2018-11-15 8:19 UTC (permalink / raw)
To: jiangyiwen, stefanha, stefanha, mst; +Cc: netdev, kvm, virtualization
On 2018/11/15 下午2:46, jiangyiwen wrote:
> On 2018/11/15 12:19, Jason Wang wrote:
>> On 2018/11/15 上午11:56, jiangyiwen wrote:
>>> Hi Stefan, Michael, Jason and everyone,
>>>
>>> Several days ago, I discussed with jason about "Vsock over Virtio-net".
>>> This idea has two advantages:
>>> First, it can use many great features of virtio-net, like batching,
>>> mergeable rx buffer and multiqueue, etc.
>>> Second, it can reduce many duplicate codes and make it easy to be
>>> maintained.
>>>
>>> Before the implement, I want to discuss with everyone again, and
>>> want to know everyone's suggestions.
>>>
>>> After the discussion, based on this point I will try to implement
>>> this idea, but I am not familiar with the virtio-net, that is a
>>> pity. :(
>>
>> I think we should have a new feature flag for this. E.g VIRTIO_NET_F_VSOCK. And host should fail the negotiation if guest doesn't support this to avoid confusion. When this feature is negotiated, we will use it only for VOSCK transport. This can simplify things somehow.
>>
>>
>>> -------------------------Simple idea------------------------------
>>>
>>> 1. The packet layout will become as follows:
>>>
>>> +---------------------------------+
>>> | Virtio-net header |
>>> |(struct virtio_net_hdr_mrg_rxbuf)|
>>> +---------------------------------+
>>> | Vsock header |
>>> | (struct virtio_vsock_hdr) |
>>> +---------------------------------+
>>> | payload |
>>> | (until end of packet) |
>>> +---------------------------------+
>>>
>>> 2. The Guest->Host basic code flow as follow:
>>> +------------+
>>> | Client |
>>> +------------+
>>> |
>>> |
>>> +------------------------------------------------------------------+
>>> |VSOCK Core Module |
>>> |ops->sendmsg; (vsock_stream_sendmsg) |
>>> | -> alloc_skb; /* it will packet a skb buffer, and include vsock |
>>> | * hdr and payload */ |
>>> | -> dev_queue_xmit(); /* it will call start_xmit(virtio-net.c) */|
>>> |vsock hdr and payload, and then call |
>>> +------------------------------------------------------------------+
>>
>> Note, if we've negotiated the feature, virtio-net driver must not use register_netdev to register it to network core. This can avoid lots of confusion.
> Hi Jason,
>
> You mean we should not register netdev if use vsock, and in order to
> avoid confusion, then I think whether we should keep vsock and export
> some virtio-net's functions that can be shared. In this way, first, vsock
> may keep existing architecture and will not affect virtio-net.
At least it needs new feature bits which will be a functional
duplication of virtio-net (e.g mrg_rxbuf).
> In addition,
> vsock doesn't need to use virtio_net header too, then it don't need to pack
> skb structure.
For mergeable rx buffer it need I think?
>
> Thanks,
> Yiwen.
>
>>
>>> |
>>> |
>>> +------------------------------------------------------------------+
>>> |Virtio-net Module |
>>> |start_xmit |
>>> | -> add virtio_net_hdr and pack sg in ring desc, notify Host |
>>> +------------------------------------------------------------------+
>>> |
>>> |
>>> +------------------------------------------------------------------+
>>> |Vhost-net Module |
>>> |handle_tx |
>>> | -> get tx buffer, skip virtio_net_hdr and call Vsock function. |
>>> | /* This point has some differences, vhost-net use ->sendmsg to |
>>> | * forward information, however vsock only need to notify server |
>>> | * that data ready. */ |
>>> +------------------------------------------------------------------+
>>
>> When VIRTIO_NET_F_VOSCK is negotiated, we know that it's a vsock transport, we can then forward it to vsock core.
>>
>>
>>> |
>>> |
>>> +------------------------------------------------------------------+
>>> |VSOCK Core Module |
>>> |alloc_pkt, copy skb data to pkt. |
>>> |add pkt to rx_queue and notify server to get data. |
>>> +------------------------------------------------------------------+
>>>
>>> 3. To Host->Guest
>>> I have a problem and difficult, mainly I know about virtio-net a little),
>>> because I have been doing work related with storage and file system.
>>>
>>> The problem as follows:
>>> we should monitor all of socket of vsock in handle_rx, when there are
>>> data coming, and copy data to vq desc. Vhost-net use ->recvmsg to
>>> get data, it is different with socket. To vsock, I think host will
>>> not call ->recvmsg when it need to send message to guest. To net,
>>> vhost-net only as forwarding layer.
>> Know not much here, but is it possible to have a vsock(tap) to be passed to vhost_net and let vhost call its recvmgs()? Bascially it was a socket on host as well I believe?
> For vsock, Host->Guest, it's code flow as follows:
> Server call send()
> -> sendmsg(); (vsock_stream_sendmsg)
> -> virtio_trasnport_send_pkt_info
> -> alloc pkt, add pkt to send_pkt_list, wake up vhost_worker
>
> Vhost_worker
> -> vhost_transport_send_pkt_work
> -> get pkt from send_pkt_list
> -> get vq input desc and then fill data to desc addr
> -> update used ring and then signal guest
>
> In the whole process, host don't call recvmsg() because it is a net device, and
> it also receives any messages.
If I understand this correctly, there's no a socket object on host that
represent vosck in guest? If yes, maybe we can invent one.
Thanks
>
> For vhost-net, I understand it is a tap device, so it can receive messages
> from other net device.
>
> This is my understanding, it may have some errors.
>
> Thanks.
>
>> If this doesn't work, we can have vsock specific receiving routine in vhost_net if VIRTIO_NET_F_VOSCK is negotiated.
>>
>> Generally, I think we should try out best to keep the exist sendmsg()/recvmsg() interfaces and only consider the alternatives if we meet some real blocker.
>>
>> Thanks
>>
>>
>> .
>>
>
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
^ permalink raw reply [flat|nested] 29+ messages in thread
* Re: [RFC] Discuss about an new idea "Vsock over Virtio-net"
2018-11-15 7:04 ` Michael S. Tsirkin
2018-11-15 7:38 ` jiangyiwen
@ 2018-11-15 8:24 ` Jason Wang
2018-11-29 14:00 ` Michael S. Tsirkin
1 sibling, 1 reply; 29+ messages in thread
From: Jason Wang @ 2018-11-15 8:24 UTC (permalink / raw)
To: Michael S. Tsirkin, jiangyiwen; +Cc: virtualization, kvm, stefanha, netdev
On 2018/11/15 下午3:04, Michael S. Tsirkin wrote:
> On Thu, Nov 15, 2018 at 11:56:03AM +0800, jiangyiwen wrote:
>> Hi Stefan, Michael, Jason and everyone,
>>
>> Several days ago, I discussed with jason about "Vsock over Virtio-net".
>> This idea has two advantages:
>> First, it can use many great features of virtio-net, like batching,
>> mergeable rx buffer and multiqueue, etc.
>> Second, it can reduce many duplicate codes and make it easy to be
>> maintained.
> I'm not sure I get the motivation. Which features of
> virtio net are relevant to vsock?
Vsock is just a L2 (and above) protocol from the view of the device. So
I think we should answer the question why we need two different paths
for networking traffic? Or what is the fundamental reason that makes
vsock does not go for virtio-net?
I agree they could be different type of devices but codes could be
shared in both guest and host (or even qemu) for not duplicating
features(bugs).
Thanks
> The ones that you mention
> all seem to be mostly of use to the networking stack.
>
>
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
^ permalink raw reply [flat|nested] 29+ messages in thread
* Re: [RFC] Discuss about an new idea "Vsock over Virtio-net"
2018-11-15 8:10 ` Michael S. Tsirkin
@ 2018-11-15 8:27 ` Jason Wang
2018-11-15 8:38 ` jiangyiwen
1 sibling, 0 replies; 29+ messages in thread
From: Jason Wang @ 2018-11-15 8:27 UTC (permalink / raw)
To: Michael S. Tsirkin, jiangyiwen
Cc: stefanha, stefanha, netdev, kvm, virtualization
On 2018/11/15 下午4:10, Michael S. Tsirkin wrote:
> On Thu, Nov 15, 2018 at 03:38:15PM +0800, jiangyiwen wrote:
>> On 2018/11/15 15:04, Michael S. Tsirkin wrote:
>>> On Thu, Nov 15, 2018 at 11:56:03AM +0800, jiangyiwen wrote:
>>>> Hi Stefan, Michael, Jason and everyone,
>>>>
>>>> Several days ago, I discussed with jason about "Vsock over Virtio-net".
>>>> This idea has two advantages:
>>>> First, it can use many great features of virtio-net, like batching,
>>>> mergeable rx buffer and multiqueue, etc.
>>>> Second, it can reduce many duplicate codes and make it easy to be
>>>> maintained.
>>> I'm not sure I get the motivation. Which features of
>>> virtio net are relevant to vsock? The ones that you mention
>>> all seem to be mostly of use to the networking stack.
>>>
>>>
>>>> Before the implement, I want to discuss with everyone again, and
>>>> want to know everyone's suggestions.
>>>>
>>>> After the discussion, based on this point I will try to implement
>>>> this idea, but I am not familiar with the virtio-net, that is a
>>>> pity.:(
>>>>
>>>> -------------------------Simple idea------------------------------
>>>>
>>>> 1. The packet layout will become as follows:
>>>>
>>>> +---------------------------------+
>>>> | Virtio-net header |
>>>> |(struct virtio_net_hdr_mrg_rxbuf)|
>>> Which fields in virtio_net_hdr_mrg_rxbuf are of interest to vsock?
>>>
>> Hi Michael,
>>
>> Yes, currently vsock has poor performance, first, it only support transport
>> small packet, in order to make the balance between performance and guest memory.
>>
>> In order to solve this problem, there are two features vsock can used,
>> mergeable rx buffer and multiqueue. Based on this, there are some shared
>> codes vsock can use.
>>
>> Thanks,
>> Yiwen.
> Supporting more queues with vsock is probably significantly
> less work than a completely new interface.
> For mergeable, as buffers are split arbitrarily, why can't you combine
> them within guest driver before sending them up the stack?
I don't get this question. But I think the fact that we use mergeable
buffer by default for virtio-net answer the question. Or anything
special in vsock?
Thanks
> Probably better than relying on host to do it.
>
^ permalink raw reply [flat|nested] 29+ messages in thread
* Re: [RFC] Discuss about an new idea "Vsock over Virtio-net"
2018-11-15 8:10 ` Michael S. Tsirkin
2018-11-15 8:27 ` Jason Wang
@ 2018-11-15 8:38 ` jiangyiwen
1 sibling, 0 replies; 29+ messages in thread
From: jiangyiwen @ 2018-11-15 8:38 UTC (permalink / raw)
To: Michael S. Tsirkin; +Cc: kvm, virtualization, stefanha, netdev
On 2018/11/15 16:10, Michael S. Tsirkin wrote:
> On Thu, Nov 15, 2018 at 03:38:15PM +0800, jiangyiwen wrote:
>> On 2018/11/15 15:04, Michael S. Tsirkin wrote:
>>> On Thu, Nov 15, 2018 at 11:56:03AM +0800, jiangyiwen wrote:
>>>> Hi Stefan, Michael, Jason and everyone,
>>>>
>>>> Several days ago, I discussed with jason about "Vsock over Virtio-net".
>>>> This idea has two advantages:
>>>> First, it can use many great features of virtio-net, like batching,
>>>> mergeable rx buffer and multiqueue, etc.
>>>> Second, it can reduce many duplicate codes and make it easy to be
>>>> maintained.
>>>
>>> I'm not sure I get the motivation. Which features of
>>> virtio net are relevant to vsock? The ones that you mention
>>> all seem to be mostly of use to the networking stack.
>>>
>>>
>>>> Before the implement, I want to discuss with everyone again, and
>>>> want to know everyone's suggestions.
>>>>
>>>> After the discussion, based on this point I will try to implement
>>>> this idea, but I am not familiar with the virtio-net, that is a
>>>> pity. :(
>>>>
>>>> -------------------------Simple idea------------------------------
>>>>
>>>> 1. The packet layout will become as follows:
>>>>
>>>> +---------------------------------+
>>>> | Virtio-net header |
>>>> |(struct virtio_net_hdr_mrg_rxbuf)|
>>>
>>> Which fields in virtio_net_hdr_mrg_rxbuf are of interest to vsock?
>>>
>>
>> Hi Michael,
>>
>> Yes, currently vsock has poor performance, first, it only support transport
>> small packet, in order to make the balance between performance and guest memory.
>>
>> In order to solve this problem, there are two features vsock can used,
>> mergeable rx buffer and multiqueue. Based on this, there are some shared
>> codes vsock can use.
>>
>> Thanks,
>> Yiwen.
>
> Supporting more queues with vsock is probably significantly
> less work than a completely new interface.
> For mergeable, as buffers are split arbitrarily, why can't you combine
> them within guest driver before sending them up the stack?
> Probably better than relying on host to do it.
>
Actually, I want to said the mergeable *rx* buffer, it cause the
default packet size of vsock is set to 4k. For tx buffer, it is
actually can be scattered in tx vq only need to modify very few codes.
In addition, I has already first version about vsock support mergeable
rx buffer and send patch to the VSOCK community, these codes are
revisited from virtio-net, and some codes are duplicated. Based on
this, we want to use virtio-net as transport of vsock. It can make
the vsock code easy to maintained.
Thanks.
>>>> +---------------------------------+
>>>> | Vsock header |
>>>> | (struct virtio_vsock_hdr) |
>>>> +---------------------------------+
>>>> | payload |
>>>> | (until end of packet) |
>>>> +---------------------------------+
>>>
>>> Thanks,
>>>
>>
>
> .
>
^ permalink raw reply [flat|nested] 29+ messages in thread
* Re: [RFC] Discuss about an new idea "Vsock over Virtio-net"
2018-11-15 8:19 ` Jason Wang
@ 2018-11-15 9:02 ` jiangyiwen
2018-11-15 9:21 ` Jason Wang
0 siblings, 1 reply; 29+ messages in thread
From: jiangyiwen @ 2018-11-15 9:02 UTC (permalink / raw)
To: Jason Wang, stefanha, stefanha, mst; +Cc: netdev, kvm, virtualization
On 2018/11/15 16:19, Jason Wang wrote:
>
> On 2018/11/15 下午2:46, jiangyiwen wrote:
>> On 2018/11/15 12:19, Jason Wang wrote:
>>> On 2018/11/15 上午11:56, jiangyiwen wrote:
>>>> Hi Stefan, Michael, Jason and everyone,
>>>>
>>>> Several days ago, I discussed with jason about "Vsock over Virtio-net".
>>>> This idea has two advantages:
>>>> First, it can use many great features of virtio-net, like batching,
>>>> mergeable rx buffer and multiqueue, etc.
>>>> Second, it can reduce many duplicate codes and make it easy to be
>>>> maintained.
>>>>
>>>> Before the implement, I want to discuss with everyone again, and
>>>> want to know everyone's suggestions.
>>>>
>>>> After the discussion, based on this point I will try to implement
>>>> this idea, but I am not familiar with the virtio-net, that is a
>>>> pity. :(
>>>
>>> I think we should have a new feature flag for this. E.g VIRTIO_NET_F_VSOCK. And host should fail the negotiation if guest doesn't support this to avoid confusion. When this feature is negotiated, we will use it only for VOSCK transport. This can simplify things somehow.
>>>
>>>
>>>> -------------------------Simple idea------------------------------
>>>>
>>>> 1. The packet layout will become as follows:
>>>>
>>>> +---------------------------------+
>>>> | Virtio-net header |
>>>> |(struct virtio_net_hdr_mrg_rxbuf)|
>>>> +---------------------------------+
>>>> | Vsock header |
>>>> | (struct virtio_vsock_hdr) |
>>>> +---------------------------------+
>>>> | payload |
>>>> | (until end of packet) |
>>>> +---------------------------------+
>>>>
>>>> 2. The Guest->Host basic code flow as follow:
>>>> +------------+
>>>> | Client |
>>>> +------------+
>>>> |
>>>> |
>>>> +------------------------------------------------------------------+
>>>> |VSOCK Core Module |
>>>> |ops->sendmsg; (vsock_stream_sendmsg) |
>>>> | -> alloc_skb; /* it will packet a skb buffer, and include vsock |
>>>> | * hdr and payload */ |
>>>> | -> dev_queue_xmit(); /* it will call start_xmit(virtio-net.c) */|
>>>> |vsock hdr and payload, and then call |
>>>> +------------------------------------------------------------------+
>>>
>>> Note, if we've negotiated the feature, virtio-net driver must not use register_netdev to register it to network core. This can avoid lots of confusion.
>> Hi Jason,
>>
>> You mean we should not register netdev if use vsock, and in order to
>> avoid confusion, then I think whether we should keep vsock and export
>> some virtio-net's functions that can be shared. In this way, first, vsock
>> may keep existing architecture and will not affect virtio-net.
>
>
> At least it needs new feature bits which will be a functional duplication of virtio-net (e.g mrg_rxbuf).
Hi Jason,
Actually I mean only use some shared function to make vsock support these
features, in that way, guest see the device is still vsock device instead of
virtio-net device, in addition, it can have less codes and easier to be
compatible with old vsock version.
Thanks,
Yiwen.
>
>
>> In addition,
>> vsock doesn't need to use virtio_net header too, then it don't need to pack
>> skb structure.
>
>
> For mergeable rx buffer it need I think?
As said above, I will define the related structure in the virtio-vsock module.
>
>
>>
>> Thanks,
>> Yiwen.
>>
>>>
>>>> |
>>>> |
>>>> +------------------------------------------------------------------+
>>>> |Virtio-net Module |
>>>> |start_xmit |
>>>> | -> add virtio_net_hdr and pack sg in ring desc, notify Host |
>>>> +------------------------------------------------------------------+
>>>> |
>>>> |
>>>> +------------------------------------------------------------------+
>>>> |Vhost-net Module |
>>>> |handle_tx |
>>>> | -> get tx buffer, skip virtio_net_hdr and call Vsock function. |
>>>> | /* This point has some differences, vhost-net use ->sendmsg to |
>>>> | * forward information, however vsock only need to notify server |
>>>> | * that data ready. */ |
>>>> +------------------------------------------------------------------+
>>>
>>> When VIRTIO_NET_F_VOSCK is negotiated, we know that it's a vsock transport, we can then forward it to vsock core.
>>>
>>>
>>>> |
>>>> |
>>>> +------------------------------------------------------------------+
>>>> |VSOCK Core Module |
>>>> |alloc_pkt, copy skb data to pkt. |
>>>> |add pkt to rx_queue and notify server to get data. |
>>>> +------------------------------------------------------------------+
>>>>
>>>> 3. To Host->Guest
>>>> I have a problem and difficult, mainly I know about virtio-net a little),
>>>> because I have been doing work related with storage and file system.
>>>>
>>>> The problem as follows:
>>>> we should monitor all of socket of vsock in handle_rx, when there are
>>>> data coming, and copy data to vq desc. Vhost-net use ->recvmsg to
>>>> get data, it is different with socket. To vsock, I think host will
>>>> not call ->recvmsg when it need to send message to guest. To net,
>>>> vhost-net only as forwarding layer.
>>> Know not much here, but is it possible to have a vsock(tap) to be passed to vhost_net and let vhost call its recvmgs()? Bascially it was a socket on host as well I believe?
>> For vsock, Host->Guest, it's code flow as follows:
>> Server call send()
>> -> sendmsg(); (vsock_stream_sendmsg)
>> -> virtio_trasnport_send_pkt_info
>> -> alloc pkt, add pkt to send_pkt_list, wake up vhost_worker
>>
>> Vhost_worker
>> -> vhost_transport_send_pkt_work
>> -> get pkt from send_pkt_list
>> -> get vq input desc and then fill data to desc addr
>> -> update used ring and then signal guest
>>
>> In the whole process, host don't call recvmsg() because it is a net device, and
>> it also receives any messages.
>
>
> If I understand this correctly, there's no a socket object on host that represent vosck in guest? If yes, maybe we can invent one.
>
> Thanks
>
Sorry, I am not understanding you very much, vsock only a socket
channel, it does not have a network device entity, so it only
transmit the data between server and client, the data is only
saved in server and client. Instead of vhost-net, I feel it
has a network device that can saved the data, so when host
send message to guest, it can use recvmsg() from the
network device(tap). For Vsock, recvmsg() interface will
read message from tx vq.
>
>>
>> For vhost-net, I understand it is a tap device, so it can receive messages
>> from other net device.
>>
>> This is my understanding, it may have some errors.
>>
>> Thanks.
>>
>>> If this doesn't work, we can have vsock specific receiving routine in vhost_net if VIRTIO_NET_F_VOSCK is negotiated.
>>>
>>> Generally, I think we should try out best to keep the exist sendmsg()/recvmsg() interfaces and only consider the alternatives if we meet some real blocker.
>>>
>>> Thanks
>>>
>>>
>>> .
>>>
>>
>
> .
>
^ permalink raw reply [flat|nested] 29+ messages in thread
* Re: [RFC] Discuss about an new idea "Vsock over Virtio-net"
2018-11-15 9:02 ` jiangyiwen
@ 2018-11-15 9:21 ` Jason Wang
2018-11-16 2:32 ` jiangyiwen
0 siblings, 1 reply; 29+ messages in thread
From: Jason Wang @ 2018-11-15 9:21 UTC (permalink / raw)
To: jiangyiwen, stefanha, stefanha, mst; +Cc: netdev, kvm, virtualization
On 2018/11/15 下午5:02, jiangyiwen wrote:
> On 2018/11/15 16:19, Jason Wang wrote:
>> On 2018/11/15 下午2:46, jiangyiwen wrote:
>>> On 2018/11/15 12:19, Jason Wang wrote:
>>>> On 2018/11/15 上午11:56, jiangyiwen wrote:
>>>>> Hi Stefan, Michael, Jason and everyone,
>>>>>
>>>>> Several days ago, I discussed with jason about "Vsock over Virtio-net".
>>>>> This idea has two advantages:
>>>>> First, it can use many great features of virtio-net, like batching,
>>>>> mergeable rx buffer and multiqueue, etc.
>>>>> Second, it can reduce many duplicate codes and make it easy to be
>>>>> maintained.
>>>>>
>>>>> Before the implement, I want to discuss with everyone again, and
>>>>> want to know everyone's suggestions.
>>>>>
>>>>> After the discussion, based on this point I will try to implement
>>>>> this idea, but I am not familiar with the virtio-net, that is a
>>>>> pity. :(
>>>> I think we should have a new feature flag for this. E.g VIRTIO_NET_F_VSOCK. And host should fail the negotiation if guest doesn't support this to avoid confusion. When this feature is negotiated, we will use it only for VOSCK transport. This can simplify things somehow.
>>>>
>>>>
>>>>> -------------------------Simple idea------------------------------
>>>>>
>>>>> 1. The packet layout will become as follows:
>>>>>
>>>>> +---------------------------------+
>>>>> | Virtio-net header |
>>>>> |(struct virtio_net_hdr_mrg_rxbuf)|
>>>>> +---------------------------------+
>>>>> | Vsock header |
>>>>> | (struct virtio_vsock_hdr) |
>>>>> +---------------------------------+
>>>>> | payload |
>>>>> | (until end of packet) |
>>>>> +---------------------------------+
>>>>>
>>>>> 2. The Guest->Host basic code flow as follow:
>>>>> +------------+
>>>>> | Client |
>>>>> +------------+
>>>>> |
>>>>> |
>>>>> +------------------------------------------------------------------+
>>>>> |VSOCK Core Module |
>>>>> |ops->sendmsg; (vsock_stream_sendmsg) |
>>>>> | -> alloc_skb; /* it will packet a skb buffer, and include vsock |
>>>>> | * hdr and payload */ |
>>>>> | -> dev_queue_xmit(); /* it will call start_xmit(virtio-net.c) */|
>>>>> |vsock hdr and payload, and then call |
>>>>> +------------------------------------------------------------------+
>>>> Note, if we've negotiated the feature, virtio-net driver must not use register_netdev to register it to network core. This can avoid lots of confusion.
>>> Hi Jason,
>>>
>>> You mean we should not register netdev if use vsock, and in order to
>>> avoid confusion, then I think whether we should keep vsock and export
>>> some virtio-net's functions that can be shared. In this way, first, vsock
>>> may keep existing architecture and will not affect virtio-net.
>>
>> At least it needs new feature bits which will be a functional duplication of virtio-net (e.g mrg_rxbuf).
> Hi Jason,
>
> Actually I mean only use some shared function to make vsock support these
> features, in that way, guest see the device is still vsock device instead of
> virtio-net device, in addition, it can have less codes and easier to be
> compatible with old vsock version.
Yes, I think we're talking about same thing. Both of us want to share
codes. What you want is to export and share some common helpers between
virtio-net and vsock. What I meant is to e.g probe vsock device and
merge vsock specific codes into virtio-net driver. I agree it's not a
small project. We can start from e.g patches that try to share the
codes. This could also give us inspiration for how to unify them.
>
> Thanks,
> Yiwen.
>
>>
>>> In addition,
>>> vsock doesn't need to use virtio_net header too, then it don't need to pack
>>> skb structure.
>>
>> For mergeable rx buffer it need I think?
> As said above, I will define the related structure in the virtio-vsock module.
>
>>
>>> Thanks,
>>> Yiwen.
>>>
>>>>> |
>>>>> |
>>>>> +------------------------------------------------------------------+
>>>>> |Virtio-net Module |
>>>>> |start_xmit |
>>>>> | -> add virtio_net_hdr and pack sg in ring desc, notify Host |
>>>>> +------------------------------------------------------------------+
>>>>> |
>>>>> |
>>>>> +------------------------------------------------------------------+
>>>>> |Vhost-net Module |
>>>>> |handle_tx |
>>>>> | -> get tx buffer, skip virtio_net_hdr and call Vsock function. |
>>>>> | /* This point has some differences, vhost-net use ->sendmsg to |
>>>>> | * forward information, however vsock only need to notify server |
>>>>> | * that data ready. */ |
>>>>> +------------------------------------------------------------------+
>>>> When VIRTIO_NET_F_VOSCK is negotiated, we know that it's a vsock transport, we can then forward it to vsock core.
>>>>
>>>>
>>>>> |
>>>>> |
>>>>> +------------------------------------------------------------------+
>>>>> |VSOCK Core Module |
>>>>> |alloc_pkt, copy skb data to pkt. |
>>>>> |add pkt to rx_queue and notify server to get data. |
>>>>> +------------------------------------------------------------------+
>>>>>
>>>>> 3. To Host->Guest
>>>>> I have a problem and difficult, mainly I know about virtio-net a little),
>>>>> because I have been doing work related with storage and file system.
>>>>>
>>>>> The problem as follows:
>>>>> we should monitor all of socket of vsock in handle_rx, when there are
>>>>> data coming, and copy data to vq desc. Vhost-net use ->recvmsg to
>>>>> get data, it is different with socket. To vsock, I think host will
>>>>> not call ->recvmsg when it need to send message to guest. To net,
>>>>> vhost-net only as forwarding layer.
>>>> Know not much here, but is it possible to have a vsock(tap) to be passed to vhost_net and let vhost call its recvmgs()? Bascially it was a socket on host as well I believe?
>>> For vsock, Host->Guest, it's code flow as follows:
>>> Server call send()
>>> -> sendmsg(); (vsock_stream_sendmsg)
>>> -> virtio_trasnport_send_pkt_info
>>> -> alloc pkt, add pkt to send_pkt_list, wake up vhost_worker
>>>
>>> Vhost_worker
>>> -> vhost_transport_send_pkt_work
>>> -> get pkt from send_pkt_list
>>> -> get vq input desc and then fill data to desc addr
>>> -> update used ring and then signal guest
>>>
>>> In the whole process, host don't call recvmsg() because it is a net device, and
>>> it also receives any messages.
>>
>> If I understand this correctly, there's no a socket object on host that represent vosck in guest? If yes, maybe we can invent one.
>>
>> Thanks
>>
> Sorry, I am not understanding you very much, vsock only a socket
> channel, it does not have a network device entity, so it only
> transmit the data between server and client, the data is only
> saved in server and client. Instead of vhost-net, I feel it
> has a network device that can saved the data, so when host
> send message to guest, it can use recvmsg() from the
> network device(tap). For Vsock, recvmsg() interface will
> read message from tx vq.
So I understand the model is not a real socket pair on host which
AF_UNIX did. Maybe it's better to have one. What I meant is, have a
socket that represent for each guest vsock device on host (guest
socket). Then when you transfer packets from host to guest, you can
queue the packets into the receive queue of the guest socket and wake up
vhost-net and it will call recvmsg() for the guest socket. And when you
want to transfer packets form guest to host, vhost_net will call
sendmsg() to the guest socket on host then it can search the correct
destination and queue packet on the receive of host socket. This can
make vsock much more easier to be integrated with vhost_net.
Thanks
>
>>> For vhost-net, I understand it is a tap device, so it can receive messages
>>> from other net device.
>>>
>>> This is my understanding, it may have some errors.
>>>
>>> Thanks.
>>>
>>>> If this doesn't work, we can have vsock specific receiving routine in vhost_net if VIRTIO_NET_F_VOSCK is negotiated.
>>>>
>>>> Generally, I think we should try out best to keep the exist sendmsg()/recvmsg() interfaces and only consider the alternatives if we meet some real blocker.
>>>>
>>>> Thanks
>>>>
>>>>
>>>> .
>>>>
>> .
>>
>
^ permalink raw reply [flat|nested] 29+ messages in thread
* Re: [RFC] Discuss about an new idea "Vsock over Virtio-net"
2018-11-15 3:56 [RFC] Discuss about an new idea "Vsock over Virtio-net" jiangyiwen
2018-11-15 4:19 ` Jason Wang
2018-11-15 7:04 ` Michael S. Tsirkin
@ 2018-11-15 9:36 ` Yan Vugenfirer
2018-11-16 2:37 ` jiangyiwen
2 siblings, 1 reply; 29+ messages in thread
From: Yan Vugenfirer @ 2018-11-15 9:36 UTC (permalink / raw)
To: jiangyiwen
Cc: stefanha, stefanha, Jason Wang, mst, netdev, kvm, virtualization
> On 15 Nov 2018, at 05:56, jiangyiwen <jiangyiwen@huawei.com> wrote:
>
> Hi Stefan, Michael, Jason and everyone,
>
> Several days ago, I discussed with jason about "Vsock over Virtio-net".
> This idea has two advantages:
> First, it can use many great features of virtio-net, like batching,
> mergeable rx buffer and multiqueue, etc.
> Second, it can reduce many duplicate codes and make it easy to be
> maintained.
I would like to add that from Windows guest support perspective it makes more sense.
To support vsock we most probably need NDIS protocol driver and if it will be binded to NDIS miniport driver (the driver that currently handles virtio-net in Windows) it will make our life much easier. Otherwise we need to “plug” into NIDS on one hand, and handle transport outside of NDIS on other hand or in some strange way by creating mini port driver that is not really NIC miniport driver.
Best regards,
Yan.
>
> Before the implement, I want to discuss with everyone again, and
> want to know everyone's suggestions.
>
> After the discussion, based on this point I will try to implement
> this idea, but I am not familiar with the virtio-net, that is a
> pity. :(
>
> -------------------------Simple idea------------------------------
>
> 1. The packet layout will become as follows:
>
> +---------------------------------+
> | Virtio-net header |
> |(struct virtio_net_hdr_mrg_rxbuf)|
> +---------------------------------+
> | Vsock header |
> | (struct virtio_vsock_hdr) |
> +---------------------------------+
> | payload |
> | (until end of packet) |
> +---------------------------------+
>
> 2. The Guest->Host basic code flow as follow:
> +------------+
> | Client |
> +------------+
> |
> |
> +------------------------------------------------------------------+
> |VSOCK Core Module |
> |ops->sendmsg; (vsock_stream_sendmsg) |
> | -> alloc_skb; /* it will packet a skb buffer, and include vsock |
> | * hdr and payload */ |
> | -> dev_queue_xmit(); /* it will call start_xmit(virtio-net.c) */|
> |vsock hdr and payload, and then call |
> +------------------------------------------------------------------+
> |
> |
> +------------------------------------------------------------------+
> |Virtio-net Module |
> |start_xmit |
> | -> add virtio_net_hdr and pack sg in ring desc, notify Host |
> +------------------------------------------------------------------+
> |
> |
> +------------------------------------------------------------------+
> |Vhost-net Module |
> |handle_tx |
> | -> get tx buffer, skip virtio_net_hdr and call Vsock function. |
> | /* This point has some differences, vhost-net use ->sendmsg to |
> | * forward information, however vsock only need to notify server |
> | * that data ready. */ |
> +------------------------------------------------------------------+
> |
> |
> +------------------------------------------------------------------+
> |VSOCK Core Module |
> |alloc_pkt, copy skb data to pkt. |
> |add pkt to rx_queue and notify server to get data. |
> +------------------------------------------------------------------+
>
> 3. To Host->Guest
> I have a problem and difficult, mainly I know about virtio-net a little),
> because I have been doing work related with storage and file system.
>
> The problem as follows:
> we should monitor all of socket of vsock in handle_rx, when there are
> data coming, and copy data to vq desc. Vhost-net use ->recvmsg to
> get data, it is different with socket. To vsock, I think host will
> not call ->recvmsg when it need to send message to guest. To net,
> vhost-net only as forwarding layer.
>
^ permalink raw reply [flat|nested] 29+ messages in thread
* Re: [RFC] Discuss about an new idea "Vsock over Virtio-net"
2018-11-15 9:21 ` Jason Wang
@ 2018-11-16 2:32 ` jiangyiwen
2018-11-16 6:35 ` Jason Wang
0 siblings, 1 reply; 29+ messages in thread
From: jiangyiwen @ 2018-11-16 2:32 UTC (permalink / raw)
To: Jason Wang, stefanha, stefanha, mst; +Cc: netdev, kvm, virtualization
On 2018/11/15 17:21, Jason Wang wrote:
>
> On 2018/11/15 下午5:02, jiangyiwen wrote:
>> On 2018/11/15 16:19, Jason Wang wrote:
>>> On 2018/11/15 下午2:46, jiangyiwen wrote:
>>>> On 2018/11/15 12:19, Jason Wang wrote:
>>>>> On 2018/11/15 上午11:56, jiangyiwen wrote:
>>>>>> Hi Stefan, Michael, Jason and everyone,
>>>>>>
>>>>>> Several days ago, I discussed with jason about "Vsock over Virtio-net".
>>>>>> This idea has two advantages:
>>>>>> First, it can use many great features of virtio-net, like batching,
>>>>>> mergeable rx buffer and multiqueue, etc.
>>>>>> Second, it can reduce many duplicate codes and make it easy to be
>>>>>> maintained.
>>>>>>
>>>>>> Before the implement, I want to discuss with everyone again, and
>>>>>> want to know everyone's suggestions.
>>>>>>
>>>>>> After the discussion, based on this point I will try to implement
>>>>>> this idea, but I am not familiar with the virtio-net, that is a
>>>>>> pity. :(
>>>>> I think we should have a new feature flag for this. E.g VIRTIO_NET_F_VSOCK. And host should fail the negotiation if guest doesn't support this to avoid confusion. When this feature is negotiated, we will use it only for VOSCK transport. This can simplify things somehow.
>>>>>
>>>>>
>>>>>> -------------------------Simple idea------------------------------
>>>>>>
>>>>>> 1. The packet layout will become as follows:
>>>>>>
>>>>>> +---------------------------------+
>>>>>> | Virtio-net header |
>>>>>> |(struct virtio_net_hdr_mrg_rxbuf)|
>>>>>> +---------------------------------+
>>>>>> | Vsock header |
>>>>>> | (struct virtio_vsock_hdr) |
>>>>>> +---------------------------------+
>>>>>> | payload |
>>>>>> | (until end of packet) |
>>>>>> +---------------------------------+
>>>>>>
>>>>>> 2. The Guest->Host basic code flow as follow:
>>>>>> +------------+
>>>>>> | Client |
>>>>>> +------------+
>>>>>> |
>>>>>> |
>>>>>> +------------------------------------------------------------------+
>>>>>> |VSOCK Core Module |
>>>>>> |ops->sendmsg; (vsock_stream_sendmsg) |
>>>>>> | -> alloc_skb; /* it will packet a skb buffer, and include vsock |
>>>>>> | * hdr and payload */ |
>>>>>> | -> dev_queue_xmit(); /* it will call start_xmit(virtio-net.c) */|
>>>>>> |vsock hdr and payload, and then call |
>>>>>> +------------------------------------------------------------------+
>>>>> Note, if we've negotiated the feature, virtio-net driver must not use register_netdev to register it to network core. This can avoid lots of confusion.
>>>> Hi Jason,
>>>>
>>>> You mean we should not register netdev if use vsock, and in order to
>>>> avoid confusion, then I think whether we should keep vsock and export
>>>> some virtio-net's functions that can be shared. In this way, first, vsock
>>>> may keep existing architecture and will not affect virtio-net.
>>>
>>> At least it needs new feature bits which will be a functional duplication of virtio-net (e.g mrg_rxbuf).
>> Hi Jason,
>>
>> Actually I mean only use some shared function to make vsock support these
>> features, in that way, guest see the device is still vsock device instead of
>> virtio-net device, in addition, it can have less codes and easier to be
>> compatible with old vsock version.
>
>
> Yes, I think we're talking about same thing. Both of us want to share codes. What you want is to export and share some common helpers between virtio-net and vsock. What I meant is to e.g probe vsock device and merge vsock specific codes into virtio-net driver. I agree it's not a small project. We can start from e.g patches that try to share the codes. This could also give us inspiration for how to unify them.
>
>
Then we have two ways to implement it.
1. For Guest, it is a virtio-net device(VIRTIO_ID_NET),
use a feature bit(e.g VIRTIO_NET_F_VSOCK) to distinguish
vsock special device and other virtio-net device. For old
vsock device, it still use old driver to drive it.
2. For Guest, it is a virtio-vsock device(VIRTIO_ID_VSOCK),
use virtio device id to distinguish them, it will integrate
old driver, but it may be more complicated, because it needs
to consider the compatibility with old vsock device.
>>
>> Thanks,
>> Yiwen.
>>
>>>
>>>> In addition,
>>>> vsock doesn't need to use virtio_net header too, then it don't need to pack
>>>> skb structure.
>>>
>>> For mergeable rx buffer it need I think?
>> As said above, I will define the related structure in the virtio-vsock module.
>>
>>>
>>>> Thanks,
>>>> Yiwen.
>>>>
>>>>>> |
>>>>>> |
>>>>>> +------------------------------------------------------------------+
>>>>>> |Virtio-net Module |
>>>>>> |start_xmit |
>>>>>> | -> add virtio_net_hdr and pack sg in ring desc, notify Host |
>>>>>> +------------------------------------------------------------------+
>>>>>> |
>>>>>> |
>>>>>> +------------------------------------------------------------------+
>>>>>> |Vhost-net Module |
>>>>>> |handle_tx |
>>>>>> | -> get tx buffer, skip virtio_net_hdr and call Vsock function. |
>>>>>> | /* This point has some differences, vhost-net use ->sendmsg to |
>>>>>> | * forward information, however vsock only need to notify server |
>>>>>> | * that data ready. */ |
>>>>>> +------------------------------------------------------------------+
>>>>> When VIRTIO_NET_F_VOSCK is negotiated, we know that it's a vsock transport, we can then forward it to vsock core.
>>>>>
>>>>>
>>>>>> |
>>>>>> |
>>>>>> +------------------------------------------------------------------+
>>>>>> |VSOCK Core Module |
>>>>>> |alloc_pkt, copy skb data to pkt. |
>>>>>> |add pkt to rx_queue and notify server to get data. |
>>>>>> +------------------------------------------------------------------+
>>>>>>
>>>>>> 3. To Host->Guest
>>>>>> I have a problem and difficult, mainly I know about virtio-net a little),
>>>>>> because I have been doing work related with storage and file system.
>>>>>>
>>>>>> The problem as follows:
>>>>>> we should monitor all of socket of vsock in handle_rx, when there are
>>>>>> data coming, and copy data to vq desc. Vhost-net use ->recvmsg to
>>>>>> get data, it is different with socket. To vsock, I think host will
>>>>>> not call ->recvmsg when it need to send message to guest. To net,
>>>>>> vhost-net only as forwarding layer.
>>>>> Know not much here, but is it possible to have a vsock(tap) to be passed to vhost_net and let vhost call its recvmgs()? Bascially it was a socket on host as well I believe?
>>>> For vsock, Host->Guest, it's code flow as follows:
>>>> Server call send()
>>>> -> sendmsg(); (vsock_stream_sendmsg)
>>>> -> virtio_trasnport_send_pkt_info
>>>> -> alloc pkt, add pkt to send_pkt_list, wake up vhost_worker
>>>>
>>>> Vhost_worker
>>>> -> vhost_transport_send_pkt_work
>>>> -> get pkt from send_pkt_list
>>>> -> get vq input desc and then fill data to desc addr
>>>> -> update used ring and then signal guest
>>>>
>>>> In the whole process, host don't call recvmsg() because it is a net device, and
>>>> it also receives any messages.
>>>
>>> If I understand this correctly, there's no a socket object on host that represent vosck in guest? If yes, maybe we can invent one.
>>>
>>> Thanks
>>>
>> Sorry, I am not understanding you very much, vsock only a socket
>> channel, it does not have a network device entity, so it only
>> transmit the data between server and client, the data is only
>> saved in server and client. Instead of vhost-net, I feel it
>> has a network device that can saved the data, so when host
>> send message to guest, it can use recvmsg() from the
>> network device(tap). For Vsock, recvmsg() interface will
>> read message from tx vq.
>
>
> So I understand the model is not a real socket pair on host which AF_UNIX did. Maybe it's better to have one. What I meant is, have a socket that represent for each guest vsock device on host (guest socket). Then when you transfer packets from host to guest, you can queue the packets into the receive queue of the guest socket and wake up vhost-net and it will call recvmsg() for the guest socket. And when you want to transfer packets form guest to host, vhost_net will call sendmsg() to the guest socket on host then it can search the correct destination and queue packet on the receive of host socket. This can make vsock much more easier to be integrated with vhost_net.
>
> Thanks
>
>>
>>>> For vhost-net, I understand it is a tap device, so it can receive messages
>>>> from other net device.
>>>>
>>>> This is my understanding, it may have some errors.
>>>>
>>>> Thanks.
>>>>
>>>>> If this doesn't work, we can have vsock specific receiving routine in vhost_net if VIRTIO_NET_F_VOSCK is negotiated.
>>>>>
>>>>> Generally, I think we should try out best to keep the exist sendmsg()/recvmsg() interfaces and only consider the alternatives if we meet some real blocker.
>>>>>
>>>>> Thanks
>>>>>
>>>>>
>>>>> .
>>>>>
>>> .
>>>
>>
>
> .
>
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
^ permalink raw reply [flat|nested] 29+ messages in thread
* Re: [RFC] Discuss about an new idea "Vsock over Virtio-net"
2018-11-15 9:36 ` Yan Vugenfirer
@ 2018-11-16 2:37 ` jiangyiwen
0 siblings, 0 replies; 29+ messages in thread
From: jiangyiwen @ 2018-11-16 2:37 UTC (permalink / raw)
To: Yan Vugenfirer
Cc: stefanha, stefanha, Jason Wang, mst, netdev, kvm, virtualization
On 2018/11/15 17:36, Yan Vugenfirer wrote:
>
>
>> On 15 Nov 2018, at 05:56, jiangyiwen <jiangyiwen@huawei.com> wrote:
>>
>> Hi Stefan, Michael, Jason and everyone,
>>
>> Several days ago, I discussed with jason about "Vsock over Virtio-net".
>> This idea has two advantages:
>> First, it can use many great features of virtio-net, like batching,
>> mergeable rx buffer and multiqueue, etc.
>> Second, it can reduce many duplicate codes and make it easy to be
>> maintained.
>
> I would like to add that from Windows guest support perspective it makes more sense.
> To support vsock we most probably need NDIS protocol driver and if it will be binded to NDIS miniport driver (the driver that currently handles virtio-net in Windows) it will make our life much easier. Otherwise we need to “plug” into NIDS on one hand, and handle transport outside of NDIS on other hand or in some strange way by creating mini port driver that is not really NIC miniport driver.
>
> Best regards,
> Yan.
Sorry, I am not familiar with windows vsock driver, if vsock
is integrated in virtio-net, it can make windows vsock more
easier, then it should be a more suitable solution.
Thanks.
>>
>> Before the implement, I want to discuss with everyone again, and
>> want to know everyone's suggestions.
>>
>> After the discussion, based on this point I will try to implement
>> this idea, but I am not familiar with the virtio-net, that is a
>> pity. :(
>>
>> -------------------------Simple idea------------------------------
>>
>> 1. The packet layout will become as follows:
>>
>> +---------------------------------+
>> | Virtio-net header |
>> |(struct virtio_net_hdr_mrg_rxbuf)|
>> +---------------------------------+
>> | Vsock header |
>> | (struct virtio_vsock_hdr) |
>> +---------------------------------+
>> | payload |
>> | (until end of packet) |
>> +---------------------------------+
>>
>> 2. The Guest->Host basic code flow as follow:
>> +------------+
>> | Client |
>> +------------+
>> |
>> |
>> +------------------------------------------------------------------+
>> |VSOCK Core Module |
>> |ops->sendmsg; (vsock_stream_sendmsg) |
>> | -> alloc_skb; /* it will packet a skb buffer, and include vsock |
>> | * hdr and payload */ |
>> | -> dev_queue_xmit(); /* it will call start_xmit(virtio-net.c) */|
>> |vsock hdr and payload, and then call |
>> +------------------------------------------------------------------+
>> |
>> |
>> +------------------------------------------------------------------+
>> |Virtio-net Module |
>> |start_xmit |
>> | -> add virtio_net_hdr and pack sg in ring desc, notify Host |
>> +------------------------------------------------------------------+
>> |
>> |
>> +------------------------------------------------------------------+
>> |Vhost-net Module |
>> |handle_tx |
>> | -> get tx buffer, skip virtio_net_hdr and call Vsock function. |
>> | /* This point has some differences, vhost-net use ->sendmsg to |
>> | * forward information, however vsock only need to notify server |
>> | * that data ready. */ |
>> +------------------------------------------------------------------+
>> |
>> |
>> +------------------------------------------------------------------+
>> |VSOCK Core Module |
>> |alloc_pkt, copy skb data to pkt. |
>> |add pkt to rx_queue and notify server to get data. |
>> +------------------------------------------------------------------+
>>
>> 3. To Host->Guest
>> I have a problem and difficult, mainly I know about virtio-net a little),
>> because I have been doing work related with storage and file system.
>>
>> The problem as follows:
>> we should monitor all of socket of vsock in handle_rx, when there are
>> data coming, and copy data to vq desc. Vhost-net use ->recvmsg to
>> get data, it is different with socket. To vsock, I think host will
>> not call ->recvmsg when it need to send message to guest. To net,
>> vhost-net only as forwarding layer.
>>
>
>
> .
>
^ permalink raw reply [flat|nested] 29+ messages in thread
* Re: [RFC] Discuss about an new idea "Vsock over Virtio-net"
2018-11-16 2:32 ` jiangyiwen
@ 2018-11-16 6:35 ` Jason Wang
0 siblings, 0 replies; 29+ messages in thread
From: Jason Wang @ 2018-11-16 6:35 UTC (permalink / raw)
To: jiangyiwen, stefanha, stefanha, mst; +Cc: netdev, kvm, virtualization
On 2018/11/16 上午10:32, jiangyiwen wrote:
>>>>>> Note, if we've negotiated the feature, virtio-net driver must not use register_netdev to register it to network core. This can avoid lots of confusion.
>>>>> Hi Jason,
>>>>>
>>>>> You mean we should not register netdev if use vsock, and in order to
>>>>> avoid confusion, then I think whether we should keep vsock and export
>>>>> some virtio-net's functions that can be shared. In this way, first, vsock
>>>>> may keep existing architecture and will not affect virtio-net.
>>>> At least it needs new feature bits which will be a functional duplication of virtio-net (e.g mrg_rxbuf).
>>> Hi Jason,
>>>
>>> Actually I mean only use some shared function to make vsock support these
>>> features, in that way, guest see the device is still vsock device instead of
>>> virtio-net device, in addition, it can have less codes and easier to be
>>> compatible with old vsock version.
>> Yes, I think we're talking about same thing. Both of us want to share codes. What you want is to export and share some common helpers between virtio-net and vsock. What I meant is to e.g probe vsock device and merge vsock specific codes into virtio-net driver. I agree it's not a small project. We can start from e.g patches that try to share the codes. This could also give us inspiration for how to unify them.
>>
>>
> Then we have two ways to implement it.
> 1. For Guest, it is a virtio-net device(VIRTIO_ID_NET),
> use a feature bit(e.g VIRTIO_NET_F_VSOCK) to distinguish
> vsock special device and other virtio-net device. For old
> vsock device, it still use old driver to drive it.
>
> 2. For Guest, it is a virtio-vsock device(VIRTIO_ID_VSOCK),
> use virtio device id to distinguish them, it will integrate
> old driver, but it may be more complicated, because it needs
> to consider the compatibility with old vsock device.
This looks even better, btw what compatibility do you mean here? Looking
at vsock driver, it does not have vosck specific feature.
Thanks
^ permalink raw reply [flat|nested] 29+ messages in thread
* Re: [RFC] Discuss about an new idea "Vsock over Virtio-net"
2018-11-15 8:24 ` Jason Wang
@ 2018-11-29 14:00 ` Michael S. Tsirkin
2018-11-30 12:45 ` Jason Wang
0 siblings, 1 reply; 29+ messages in thread
From: Michael S. Tsirkin @ 2018-11-29 14:00 UTC (permalink / raw)
To: Jason Wang; +Cc: jiangyiwen, stefanha, stefanha, netdev, kvm, virtualization
On Thu, Nov 15, 2018 at 04:24:38PM +0800, Jason Wang wrote:
>
> On 2018/11/15 下午3:04, Michael S. Tsirkin wrote:
> > On Thu, Nov 15, 2018 at 11:56:03AM +0800, jiangyiwen wrote:
> > > Hi Stefan, Michael, Jason and everyone,
> > >
> > > Several days ago, I discussed with jason about "Vsock over Virtio-net".
> > > This idea has two advantages:
> > > First, it can use many great features of virtio-net, like batching,
> > > mergeable rx buffer and multiqueue, etc.
> > > Second, it can reduce many duplicate codes and make it easy to be
> > > maintained.
> > I'm not sure I get the motivation. Which features of
> > virtio net are relevant to vsock?
>
>
> Vsock is just a L2 (and above) protocol from the view of the device.
I don't believe so. I think virtio-vsock operates at a transport level.
There is in theory a bit of network level but we don't really implement
it as it's only host to guest. I am not aware of any data link
functionality n virtio-vsock. virtio-vsock provides services such as
connection-oriented communication, reliability, flow control and
multiplexing.
> So I
> think we should answer the question why we need two different paths for
> networking traffic? Or what is the fundamental reason that makes vsock does
> not go for virtio-net?
So virtio-vsock ensures reliability. If you want to compare it with
something that would be TCP or QUIC. The fundamental difference between
virtio-vsock and e.g. TCP is that TCP operates in a packet loss environment.
So they are using timers for reliability, and receiver is always free to
discard any unacked data.
> I agree they could be different type of devices but codes could be shared in
> both guest and host (or even qemu) for not duplicating features(bugs).
>
> Thanks
>
>
> > The ones that you mention
> > all seem to be mostly of use to the networking stack.
> >
> >
^ permalink raw reply [flat|nested] 29+ messages in thread
* Re: [RFC] Discuss about an new idea "Vsock over Virtio-net"
2018-11-29 14:00 ` Michael S. Tsirkin
@ 2018-11-30 12:45 ` Jason Wang
2018-11-30 12:52 ` Michael S. Tsirkin
0 siblings, 1 reply; 29+ messages in thread
From: Jason Wang @ 2018-11-30 12:45 UTC (permalink / raw)
To: Michael S. Tsirkin
Cc: jiangyiwen, stefanha, stefanha, netdev, kvm, virtualization
On 2018/11/29 下午10:00, Michael S. Tsirkin wrote:
> On Thu, Nov 15, 2018 at 04:24:38PM +0800, Jason Wang wrote:
>> On 2018/11/15 下午3:04, Michael S. Tsirkin wrote:
>>> On Thu, Nov 15, 2018 at 11:56:03AM +0800, jiangyiwen wrote:
>>>> Hi Stefan, Michael, Jason and everyone,
>>>>
>>>> Several days ago, I discussed with jason about "Vsock over Virtio-net".
>>>> This idea has two advantages:
>>>> First, it can use many great features of virtio-net, like batching,
>>>> mergeable rx buffer and multiqueue, etc.
>>>> Second, it can reduce many duplicate codes and make it easy to be
>>>> maintained.
>>> I'm not sure I get the motivation. Which features of
>>> virtio net are relevant to vsock?
>>
>> Vsock is just a L2 (and above) protocol from the view of the device.
> I don't believe so. I think virtio-vsock operates at a transport level.
> There is in theory a bit of network level but we don't really implement
> it as it's only host to guest. I am not aware of any data link
> functionality n virtio-vsock. virtio-vsock provides services such as
> connection-oriented communication, reliability, flow control and
> multiplexing.
Ok, consider it doesn't implement L2, it's pretty fit for virtio-net I
believe?
>
>> So I
>> think we should answer the question why we need two different paths for
>> networking traffic? Or what is the fundamental reason that makes vsock does
>> not go for virtio-net?
> So virtio-vsock ensures reliability.
It's done at the level of protocol instead of virtio transport or virtio
device.
> If you want to compare it with
> something that would be TCP or QUIC. The fundamental difference between
> virtio-vsock and e.g. TCP is that TCP operates in a packet loss environment.
> So they are using timers for reliability, and receiver is always free to
> discard any unacked data.
Virtio-net knows nothing above L2, so they are totally transparent to
device itself. I still don't get why not using virtio-net instead.
Thanks
>
>
>> I agree they could be different type of devices but codes could be shared in
>> both guest and host (or even qemu) for not duplicating features(bugs).
>>
>> Thanks
>>
>>
>>> The ones that you mention
>>> all seem to be mostly of use to the networking stack.
>>>
>>>
^ permalink raw reply [flat|nested] 29+ messages in thread
* Re: [RFC] Discuss about an new idea "Vsock over Virtio-net"
2018-11-30 12:45 ` Jason Wang
@ 2018-11-30 12:52 ` Michael S. Tsirkin
2018-11-30 12:55 ` Jason Wang
0 siblings, 1 reply; 29+ messages in thread
From: Michael S. Tsirkin @ 2018-11-30 12:52 UTC (permalink / raw)
To: Jason Wang; +Cc: jiangyiwen, stefanha, stefanha, netdev, kvm, virtualization
On Fri, Nov 30, 2018 at 08:45:39PM +0800, Jason Wang wrote:
>
> On 2018/11/29 下午10:00, Michael S. Tsirkin wrote:
> > On Thu, Nov 15, 2018 at 04:24:38PM +0800, Jason Wang wrote:
> > > On 2018/11/15 下午3:04, Michael S. Tsirkin wrote:
> > > > On Thu, Nov 15, 2018 at 11:56:03AM +0800, jiangyiwen wrote:
> > > > > Hi Stefan, Michael, Jason and everyone,
> > > > >
> > > > > Several days ago, I discussed with jason about "Vsock over Virtio-net".
> > > > > This idea has two advantages:
> > > > > First, it can use many great features of virtio-net, like batching,
> > > > > mergeable rx buffer and multiqueue, etc.
> > > > > Second, it can reduce many duplicate codes and make it easy to be
> > > > > maintained.
> > > > I'm not sure I get the motivation. Which features of
> > > > virtio net are relevant to vsock?
> > >
> > > Vsock is just a L2 (and above) protocol from the view of the device.
> > I don't believe so. I think virtio-vsock operates at a transport level.
> > There is in theory a bit of network level but we don't really implement
> > it as it's only host to guest. I am not aware of any data link
> > functionality n virtio-vsock. virtio-vsock provides services such as
> > connection-oriented communication, reliability, flow control and
> > multiplexing.
>
>
> Ok, consider it doesn't implement L2, it's pretty fit for virtio-net I
> believe?
>
>
> >
> > > So I
> > > think we should answer the question why we need two different paths for
> > > networking traffic? Or what is the fundamental reason that makes vsock does
> > > not go for virtio-net?
> > So virtio-vsock ensures reliability.
>
>
> It's done at the level of protocol instead of virtio transport or virtio
> device.
>
>
> > If you want to compare it with
> > something that would be TCP or QUIC. The fundamental difference between
> > virtio-vsock and e.g. TCP is that TCP operates in a packet loss environment.
> > So they are using timers for reliability, and receiver is always free to
> > discard any unacked data.
>
>
> Virtio-net knows nothing above L2, so they are totally transparent to device
> itself. I still don't get why not using virtio-net instead.
>
>
> Thanks
Is your question why is virtio-vsock used instead of TCP on top of IP
on top of virtio-net?
>
> >
> >
> > > I agree they could be different type of devices but codes could be shared in
> > > both guest and host (or even qemu) for not duplicating features(bugs).
> > >
> > > Thanks
> > >
> > >
> > > > The ones that you mention
> > > > all seem to be mostly of use to the networking stack.
> > > >
> > > >
^ permalink raw reply [flat|nested] 29+ messages in thread
* Re: [RFC] Discuss about an new idea "Vsock over Virtio-net"
2018-11-30 12:52 ` Michael S. Tsirkin
@ 2018-11-30 12:55 ` Jason Wang
2018-11-30 13:10 ` Jason Wang
2018-11-30 13:34 ` Michael S. Tsirkin
0 siblings, 2 replies; 29+ messages in thread
From: Jason Wang @ 2018-11-30 12:55 UTC (permalink / raw)
To: Michael S. Tsirkin
Cc: jiangyiwen, stefanha, stefanha, netdev, kvm, virtualization
On 2018/11/30 下午8:52, Michael S. Tsirkin wrote:
>>> If you want to compare it with
>>> something that would be TCP or QUIC. The fundamental difference between
>>> virtio-vsock and e.g. TCP is that TCP operates in a packet loss environment.
>>> So they are using timers for reliability, and receiver is always free to
>>> discard any unacked data.
>> Virtio-net knows nothing above L2, so they are totally transparent to device
>> itself. I still don't get why not using virtio-net instead.
>>
>>
>> Thanks
> Is your question why is virtio-vsock used instead of TCP on top of IP
> on top of virtio-net?
>
>
No, my question is why not do vsock through virtio-net.
Thanks
^ permalink raw reply [flat|nested] 29+ messages in thread
* Re: [RFC] Discuss about an new idea "Vsock over Virtio-net"
2018-11-30 12:55 ` Jason Wang
@ 2018-11-30 13:10 ` Jason Wang
2018-11-30 13:40 ` Michael S. Tsirkin
2018-11-30 13:34 ` Michael S. Tsirkin
1 sibling, 1 reply; 29+ messages in thread
From: Jason Wang @ 2018-11-30 13:10 UTC (permalink / raw)
To: Michael S. Tsirkin
Cc: jiangyiwen, stefanha, stefanha, netdev, kvm, virtualization
On 2018/11/30 下午8:55, Jason Wang wrote:
>
> On 2018/11/30 下午8:52, Michael S. Tsirkin wrote:
>>>> If you want to compare it with
>>>> something that would be TCP or QUIC. The fundamental difference
>>>> between
>>>> virtio-vsock and e.g. TCP is that TCP operates in a packet loss
>>>> environment.
>>>> So they are using timers for reliability, and receiver is always
>>>> free to
>>>> discard any unacked data.
>>> Virtio-net knows nothing above L2, so they are totally transparent
>>> to device
>>> itself. I still don't get why not using virtio-net instead.
>>>
>>>
>>> Thanks
>> Is your question why is virtio-vsock used instead of TCP on top of IP
>> on top of virtio-net?
>>
>>
>
> No, my question is why not do vsock through virtio-net.
>
> Thanks
>
Just to clarify, it's not about vosck over ethernet, and it's not about
inventing new features or APIs. It's probably something like:
- Let virtio-net driver probe vsock device and do vosck specific things
if needed to share as much codes.
- A new kind of sockfd (which is vsock based) for vhost-net for it to do
vsock specific things (hopefully it can be transparent).
The change should be totally transparent to userspace applications.
Thanks
^ permalink raw reply [flat|nested] 29+ messages in thread
* Re: [RFC] Discuss about an new idea "Vsock over Virtio-net"
2018-11-30 12:55 ` Jason Wang
2018-11-30 13:10 ` Jason Wang
@ 2018-11-30 13:34 ` Michael S. Tsirkin
1 sibling, 0 replies; 29+ messages in thread
From: Michael S. Tsirkin @ 2018-11-30 13:34 UTC (permalink / raw)
To: Jason Wang; +Cc: jiangyiwen, stefanha, stefanha, netdev, kvm, virtualization
On Fri, Nov 30, 2018 at 08:55:17PM +0800, Jason Wang wrote:
>
> On 2018/11/30 下午8:52, Michael S. Tsirkin wrote:
> > > > If you want to compare it with
> > > > something that would be TCP or QUIC. The fundamental difference between
> > > > virtio-vsock and e.g. TCP is that TCP operates in a packet loss environment.
> > > > So they are using timers for reliability, and receiver is always free to
> > > > discard any unacked data.
> > > Virtio-net knows nothing above L2, so they are totally transparent to device
> > > itself. I still don't get why not using virtio-net instead.
> > >
> > >
> > > Thanks
> > Is your question why is virtio-vsock used instead of TCP on top of IP
> > on top of virtio-net?
> >
> >
>
> No, my question is why not do vsock through virtio-net.
>
> Thanks
Because apps need reliability, multiplexing and flow control and
virtio-net does not provide it.
--
MST
^ permalink raw reply [flat|nested] 29+ messages in thread
* Re: [RFC] Discuss about an new idea "Vsock over Virtio-net"
2018-11-30 13:10 ` Jason Wang
@ 2018-11-30 13:40 ` Michael S. Tsirkin
2018-12-03 3:10 ` jiangyiwen
0 siblings, 1 reply; 29+ messages in thread
From: Michael S. Tsirkin @ 2018-11-30 13:40 UTC (permalink / raw)
To: Jason Wang; +Cc: jiangyiwen, stefanha, stefanha, netdev, kvm, virtualization
On Fri, Nov 30, 2018 at 09:10:03PM +0800, Jason Wang wrote:
>
> On 2018/11/30 下午8:55, Jason Wang wrote:
> >
> > On 2018/11/30 下午8:52, Michael S. Tsirkin wrote:
> > > > > If you want to compare it with
> > > > > something that would be TCP or QUIC. The fundamental
> > > > > difference between
> > > > > virtio-vsock and e.g. TCP is that TCP operates in a packet
> > > > > loss environment.
> > > > > So they are using timers for reliability, and receiver is
> > > > > always free to
> > > > > discard any unacked data.
> > > > Virtio-net knows nothing above L2, so they are totally
> > > > transparent to device
> > > > itself. I still don't get why not using virtio-net instead.
> > > >
> > > >
> > > > Thanks
> > > Is your question why is virtio-vsock used instead of TCP on top of IP
> > > on top of virtio-net?
> > >
> > >
> >
> > No, my question is why not do vsock through virtio-net.
> >
> > Thanks
> >
>
> Just to clarify, it's not about vosck over ethernet, and it's not about
> inventing new features or APIs. It's probably something like:
>
> - Let virtio-net driver probe vsock device and do vosck specific things if
> needed to share as much codes.
>
> - A new kind of sockfd (which is vsock based) for vhost-net for it to do
> vsock specific things (hopefully it can be transparent).
>
> The change should be totally transparent to userspace applications.
>
> Thanks
Which code is duplicated between virtio vsock and virtio net right now?
--
MST
^ permalink raw reply [flat|nested] 29+ messages in thread
* Re: [RFC] Discuss about an new idea "Vsock over Virtio-net"
2018-11-30 13:40 ` Michael S. Tsirkin
@ 2018-12-03 3:10 ` jiangyiwen
2018-12-04 1:31 ` Michael S. Tsirkin
0 siblings, 1 reply; 29+ messages in thread
From: jiangyiwen @ 2018-12-03 3:10 UTC (permalink / raw)
To: Michael S. Tsirkin, Jason Wang
Cc: stefanha, stefanha, netdev, kvm, virtualization
On 2018/11/30 21:40, Michael S. Tsirkin wrote:
> On Fri, Nov 30, 2018 at 09:10:03PM +0800, Jason Wang wrote:
>>
>> On 2018/11/30 下午8:55, Jason Wang wrote:
>>>
>>> On 2018/11/30 下午8:52, Michael S. Tsirkin wrote:
>>>>>> If you want to compare it with
>>>>>> something that would be TCP or QUIC. The fundamental
>>>>>> difference between
>>>>>> virtio-vsock and e.g. TCP is that TCP operates in a packet
>>>>>> loss environment.
>>>>>> So they are using timers for reliability, and receiver is
>>>>>> always free to
>>>>>> discard any unacked data.
>>>>> Virtio-net knows nothing above L2, so they are totally
>>>>> transparent to device
>>>>> itself. I still don't get why not using virtio-net instead.
>>>>>
>>>>>
>>>>> Thanks
>>>> Is your question why is virtio-vsock used instead of TCP on top of IP
>>>> on top of virtio-net?
>>>>
>>>>
>>>
>>> No, my question is why not do vsock through virtio-net.
>>>
>>> Thanks
>>>
>>
>> Just to clarify, it's not about vosck over ethernet, and it's not about
>> inventing new features or APIs. It's probably something like:
>>
>> - Let virtio-net driver probe vsock device and do vosck specific things if
>> needed to share as much codes.
>>
>> - A new kind of sockfd (which is vsock based) for vhost-net for it to do
>> vsock specific things (hopefully it can be transparent).
>>
>> The change should be totally transparent to userspace applications.
>>
>> Thanks
>
> Which code is duplicated between virtio vsock and virtio net right now?
>
Hi Michael,
AFAIK, there is almost no duplicate code between virtio vsock and virtio net now.
But, if virtio vsock wants to support mergeable rx buffer and multiqueue feature,
it has some duplicate codes from virtio net. Based on it, we both think vsock
may use virtio net as a transport channel, in this way, vsock can use some of
virtio net great features.
Thanks,
Yiwen.
^ permalink raw reply [flat|nested] 29+ messages in thread
* Re: [RFC] Discuss about an new idea "Vsock over Virtio-net"
2018-12-03 3:10 ` jiangyiwen
@ 2018-12-04 1:31 ` Michael S. Tsirkin
2018-12-04 2:21 ` jiangyiwen
0 siblings, 1 reply; 29+ messages in thread
From: Michael S. Tsirkin @ 2018-12-04 1:31 UTC (permalink / raw)
To: jiangyiwen; +Cc: Jason Wang, stefanha, stefanha, netdev, kvm, virtualization
On Mon, Dec 03, 2018 at 11:10:58AM +0800, jiangyiwen wrote:
> On 2018/11/30 21:40, Michael S. Tsirkin wrote:
> > On Fri, Nov 30, 2018 at 09:10:03PM +0800, Jason Wang wrote:
> >>
> >> On 2018/11/30 下午8:55, Jason Wang wrote:
> >>>
> >>> On 2018/11/30 下午8:52, Michael S. Tsirkin wrote:
> >>>>>> If you want to compare it with
> >>>>>> something that would be TCP or QUIC. The fundamental
> >>>>>> difference between
> >>>>>> virtio-vsock and e.g. TCP is that TCP operates in a packet
> >>>>>> loss environment.
> >>>>>> So they are using timers for reliability, and receiver is
> >>>>>> always free to
> >>>>>> discard any unacked data.
> >>>>> Virtio-net knows nothing above L2, so they are totally
> >>>>> transparent to device
> >>>>> itself. I still don't get why not using virtio-net instead.
> >>>>>
> >>>>>
> >>>>> Thanks
> >>>> Is your question why is virtio-vsock used instead of TCP on top of IP
> >>>> on top of virtio-net?
> >>>>
> >>>>
> >>>
> >>> No, my question is why not do vsock through virtio-net.
> >>>
> >>> Thanks
> >>>
> >>
> >> Just to clarify, it's not about vosck over ethernet, and it's not about
> >> inventing new features or APIs. It's probably something like:
> >>
> >> - Let virtio-net driver probe vsock device and do vosck specific things if
> >> needed to share as much codes.
> >>
> >> - A new kind of sockfd (which is vsock based) for vhost-net for it to do
> >> vsock specific things (hopefully it can be transparent).
> >>
> >> The change should be totally transparent to userspace applications.
> >>
> >> Thanks
> >
> > Which code is duplicated between virtio vsock and virtio net right now?
> >
>
> Hi Michael,
>
> AFAIK, there is almost no duplicate code between virtio vsock and virtio net now.
>
> But, if virtio vsock wants to support mergeable rx buffer and multiqueue feature,
> it has some duplicate codes from virtio net. Based on it, we both think vsock
> may use virtio net as a transport channel, in this way, vsock can use some of
> virtio net great features.
>
> Thanks,
> Yiwen.
What I would do is just copy some code and show a performance
benefit. If that works out it will be clearer which code
should be shared.
--
MST
^ permalink raw reply [flat|nested] 29+ messages in thread
* Re: [RFC] Discuss about an new idea "Vsock over Virtio-net"
2018-12-04 1:31 ` Michael S. Tsirkin
@ 2018-12-04 2:21 ` jiangyiwen
2018-12-04 4:08 ` Michael S. Tsirkin
0 siblings, 1 reply; 29+ messages in thread
From: jiangyiwen @ 2018-12-04 2:21 UTC (permalink / raw)
To: Michael S. Tsirkin
Cc: Jason Wang, stefanha, stefanha, netdev, kvm, virtualization
On 2018/12/4 9:31, Michael S. Tsirkin wrote:
> On Mon, Dec 03, 2018 at 11:10:58AM +0800, jiangyiwen wrote:
>> On 2018/11/30 21:40, Michael S. Tsirkin wrote:
>>> On Fri, Nov 30, 2018 at 09:10:03PM +0800, Jason Wang wrote:
>>>>
>>>> On 2018/11/30 下午8:55, Jason Wang wrote:
>>>>>
>>>>> On 2018/11/30 下午8:52, Michael S. Tsirkin wrote:
>>>>>>>> If you want to compare it with
>>>>>>>> something that would be TCP or QUIC. The fundamental
>>>>>>>> difference between
>>>>>>>> virtio-vsock and e.g. TCP is that TCP operates in a packet
>>>>>>>> loss environment.
>>>>>>>> So they are using timers for reliability, and receiver is
>>>>>>>> always free to
>>>>>>>> discard any unacked data.
>>>>>>> Virtio-net knows nothing above L2, so they are totally
>>>>>>> transparent to device
>>>>>>> itself. I still don't get why not using virtio-net instead.
>>>>>>>
>>>>>>>
>>>>>>> Thanks
>>>>>> Is your question why is virtio-vsock used instead of TCP on top of IP
>>>>>> on top of virtio-net?
>>>>>>
>>>>>>
>>>>>
>>>>> No, my question is why not do vsock through virtio-net.
>>>>>
>>>>> Thanks
>>>>>
>>>>
>>>> Just to clarify, it's not about vosck over ethernet, and it's not about
>>>> inventing new features or APIs. It's probably something like:
>>>>
>>>> - Let virtio-net driver probe vsock device and do vosck specific things if
>>>> needed to share as much codes.
>>>>
>>>> - A new kind of sockfd (which is vsock based) for vhost-net for it to do
>>>> vsock specific things (hopefully it can be transparent).
>>>>
>>>> The change should be totally transparent to userspace applications.
>>>>
>>>> Thanks
>>>
>>> Which code is duplicated between virtio vsock and virtio net right now?
>>>
>>
>> Hi Michael,
>>
>> AFAIK, there is almost no duplicate code between virtio vsock and virtio net now.
>>
>> But, if virtio vsock wants to support mergeable rx buffer and multiqueue feature,
>> it has some duplicate codes from virtio net. Based on it, we both think vsock
>> may use virtio net as a transport channel, in this way, vsock can use some of
>> virtio net great features.
>>
>> Thanks,
>> Yiwen.
>
> What I would do is just copy some code and show a performance
> benefit. If that works out it will be clearer which code
> should be shared.
>
Hi Michael,
I have already sent a series of patches (VSOCK: support mergeable rx buffer in vhost-vsock)
a month ago, and the performance as follows:
I write a tool to test the vhost-vsock performance, mainly send big
packet(64K) included guest->Host and Host->Guest. The result as
follows:
Before performance:
Single socket Multiple sockets(Max Bandwidth)
Guest->Host ~400MB/s ~480MB/s
Host->Guest ~1450MB/s ~1600MB/s
After performance:
Single socket Multiple sockets(Max Bandwidth)
Guest->Host ~1700MB/s ~2900MB/s
Host->Guest ~1700MB/s ~2900MB/s
>From the test results, the performance is improved obviously, and guest
memory will not be wasted.
In addition, multiqueue feature I have not implemented it yet.
Thanks,
Yiwen.
^ permalink raw reply [flat|nested] 29+ messages in thread
* Re: [RFC] Discuss about an new idea "Vsock over Virtio-net"
2018-12-04 2:21 ` jiangyiwen
@ 2018-12-04 4:08 ` Michael S. Tsirkin
2018-12-04 6:01 ` jiangyiwen
0 siblings, 1 reply; 29+ messages in thread
From: Michael S. Tsirkin @ 2018-12-04 4:08 UTC (permalink / raw)
To: jiangyiwen; +Cc: Jason Wang, stefanha, stefanha, netdev, kvm, virtualization
On Tue, Dec 04, 2018 at 10:21:40AM +0800, jiangyiwen wrote:
> On 2018/12/4 9:31, Michael S. Tsirkin wrote:
> > On Mon, Dec 03, 2018 at 11:10:58AM +0800, jiangyiwen wrote:
> >> On 2018/11/30 21:40, Michael S. Tsirkin wrote:
> >>> On Fri, Nov 30, 2018 at 09:10:03PM +0800, Jason Wang wrote:
> >>>>
> >>>> On 2018/11/30 下午8:55, Jason Wang wrote:
> >>>>>
> >>>>> On 2018/11/30 下午8:52, Michael S. Tsirkin wrote:
> >>>>>>>> If you want to compare it with
> >>>>>>>> something that would be TCP or QUIC. The fundamental
> >>>>>>>> difference between
> >>>>>>>> virtio-vsock and e.g. TCP is that TCP operates in a packet
> >>>>>>>> loss environment.
> >>>>>>>> So they are using timers for reliability, and receiver is
> >>>>>>>> always free to
> >>>>>>>> discard any unacked data.
> >>>>>>> Virtio-net knows nothing above L2, so they are totally
> >>>>>>> transparent to device
> >>>>>>> itself. I still don't get why not using virtio-net instead.
> >>>>>>>
> >>>>>>>
> >>>>>>> Thanks
> >>>>>> Is your question why is virtio-vsock used instead of TCP on top of IP
> >>>>>> on top of virtio-net?
> >>>>>>
> >>>>>>
> >>>>>
> >>>>> No, my question is why not do vsock through virtio-net.
> >>>>>
> >>>>> Thanks
> >>>>>
> >>>>
> >>>> Just to clarify, it's not about vosck over ethernet, and it's not about
> >>>> inventing new features or APIs. It's probably something like:
> >>>>
> >>>> - Let virtio-net driver probe vsock device and do vosck specific things if
> >>>> needed to share as much codes.
> >>>>
> >>>> - A new kind of sockfd (which is vsock based) for vhost-net for it to do
> >>>> vsock specific things (hopefully it can be transparent).
> >>>>
> >>>> The change should be totally transparent to userspace applications.
> >>>>
> >>>> Thanks
> >>>
> >>> Which code is duplicated between virtio vsock and virtio net right now?
> >>>
> >>
> >> Hi Michael,
> >>
> >> AFAIK, there is almost no duplicate code between virtio vsock and virtio net now.
> >>
> >> But, if virtio vsock wants to support mergeable rx buffer and multiqueue feature,
> >> it has some duplicate codes from virtio net. Based on it, we both think vsock
> >> may use virtio net as a transport channel, in this way, vsock can use some of
> >> virtio net great features.
> >>
> >> Thanks,
> >> Yiwen.
> >
> > What I would do is just copy some code and show a performance
> > benefit. If that works out it will be clearer which code
> > should be shared.
> >
>
> Hi Michael,
>
> I have already sent a series of patches (VSOCK: support mergeable rx buffer in vhost-vsock)
> a month ago, and the performance as follows:
>
> I write a tool to test the vhost-vsock performance, mainly send big
> packet(64K) included guest->Host and Host->Guest. The result as
> follows:
>
> Before performance:
> Single socket Multiple sockets(Max Bandwidth)
> Guest->Host ~400MB/s ~480MB/s
> Host->Guest ~1450MB/s ~1600MB/s
>
> After performance:
> Single socket Multiple sockets(Max Bandwidth)
> Guest->Host ~1700MB/s ~2900MB/s
> Host->Guest ~1700MB/s ~2900MB/s
>
> >From the test results, the performance is improved obviously, and guest
> memory will not be wasted.
Oh I didn't see that one. Pls CC me in the future.
Looking at it I agree zero page allocation looks like an issue
but besides that, I think we can merge something similar
and look at refactoring and future extensions later.
However, any interface change (e.g. a new feature) must be CC'd to one of
virtio lists (subscriber-only).
> In addition, multiqueue feature I have not implemented it yet.
>
> Thanks,
> Yiwen.
>
^ permalink raw reply [flat|nested] 29+ messages in thread
* Re: [RFC] Discuss about an new idea "Vsock over Virtio-net"
2018-12-04 4:08 ` Michael S. Tsirkin
@ 2018-12-04 6:01 ` jiangyiwen
0 siblings, 0 replies; 29+ messages in thread
From: jiangyiwen @ 2018-12-04 6:01 UTC (permalink / raw)
To: Michael S. Tsirkin; +Cc: kvm, virtualization, stefanha, netdev
On 2018/12/4 12:08, Michael S. Tsirkin wrote:
> On Tue, Dec 04, 2018 at 10:21:40AM +0800, jiangyiwen wrote:
>> On 2018/12/4 9:31, Michael S. Tsirkin wrote:
>>> On Mon, Dec 03, 2018 at 11:10:58AM +0800, jiangyiwen wrote:
>>>> On 2018/11/30 21:40, Michael S. Tsirkin wrote:
>>>>> On Fri, Nov 30, 2018 at 09:10:03PM +0800, Jason Wang wrote:
>>>>>>
>>>>>> On 2018/11/30 下午8:55, Jason Wang wrote:
>>>>>>>
>>>>>>> On 2018/11/30 下午8:52, Michael S. Tsirkin wrote:
>>>>>>>>>> If you want to compare it with
>>>>>>>>>> something that would be TCP or QUIC. The fundamental
>>>>>>>>>> difference between
>>>>>>>>>> virtio-vsock and e.g. TCP is that TCP operates in a packet
>>>>>>>>>> loss environment.
>>>>>>>>>> So they are using timers for reliability, and receiver is
>>>>>>>>>> always free to
>>>>>>>>>> discard any unacked data.
>>>>>>>>> Virtio-net knows nothing above L2, so they are totally
>>>>>>>>> transparent to device
>>>>>>>>> itself. I still don't get why not using virtio-net instead.
>>>>>>>>>
>>>>>>>>>
>>>>>>>>> Thanks
>>>>>>>> Is your question why is virtio-vsock used instead of TCP on top of IP
>>>>>>>> on top of virtio-net?
>>>>>>>>
>>>>>>>>
>>>>>>>
>>>>>>> No, my question is why not do vsock through virtio-net.
>>>>>>>
>>>>>>> Thanks
>>>>>>>
>>>>>>
>>>>>> Just to clarify, it's not about vosck over ethernet, and it's not about
>>>>>> inventing new features or APIs. It's probably something like:
>>>>>>
>>>>>> - Let virtio-net driver probe vsock device and do vosck specific things if
>>>>>> needed to share as much codes.
>>>>>>
>>>>>> - A new kind of sockfd (which is vsock based) for vhost-net for it to do
>>>>>> vsock specific things (hopefully it can be transparent).
>>>>>>
>>>>>> The change should be totally transparent to userspace applications.
>>>>>>
>>>>>> Thanks
>>>>>
>>>>> Which code is duplicated between virtio vsock and virtio net right now?
>>>>>
>>>>
>>>> Hi Michael,
>>>>
>>>> AFAIK, there is almost no duplicate code between virtio vsock and virtio net now.
>>>>
>>>> But, if virtio vsock wants to support mergeable rx buffer and multiqueue feature,
>>>> it has some duplicate codes from virtio net. Based on it, we both think vsock
>>>> may use virtio net as a transport channel, in this way, vsock can use some of
>>>> virtio net great features.
>>>>
>>>> Thanks,
>>>> Yiwen.
>>>
>>> What I would do is just copy some code and show a performance
>>> benefit. If that works out it will be clearer which code
>>> should be shared.
>>>
>>
>> Hi Michael,
>>
>> I have already sent a series of patches (VSOCK: support mergeable rx buffer in vhost-vsock)
>> a month ago, and the performance as follows:
>>
>> I write a tool to test the vhost-vsock performance, mainly send big
>> packet(64K) included guest->Host and Host->Guest. The result as
>> follows:
>>
>> Before performance:
>> Single socket Multiple sockets(Max Bandwidth)
>> Guest->Host ~400MB/s ~480MB/s
>> Host->Guest ~1450MB/s ~1600MB/s
>>
>> After performance:
>> Single socket Multiple sockets(Max Bandwidth)
>> Guest->Host ~1700MB/s ~2900MB/s
>> Host->Guest ~1700MB/s ~2900MB/s
>>
>> >From the test results, the performance is improved obviously, and guest
>> memory will not be wasted.
>
> Oh I didn't see that one. Pls CC me in the future.
>
> Looking at it I agree zero page allocation looks like an issue
> but besides that, I think we can merge something similar
> and look at refactoring and future extensions later.
>
> However, any interface change (e.g. a new feature) must be CC'd to one of
> virtio lists (subscriber-only).
>
>
Okay, previously I send Virtio-vsock patch only CC stefan and mailing lists
based on MAINTAINERS, because it only be related to Virtio-vsock.
Then, first I send v2 patch based on Jason's suggestions, and then let's
see how to combine with virtio-vsock and virtio-net. What do you think?
Thanks,
Yiwen.
>
>> In addition, multiqueue feature I have not implemented it yet.
>>
>> Thanks,
>> Yiwen.
>>
>
>
>
>
> .
>
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
^ permalink raw reply [flat|nested] 29+ messages in thread
end of thread, other threads:[~2018-12-04 6:01 UTC | newest]
Thread overview: 29+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2018-11-15 3:56 [RFC] Discuss about an new idea "Vsock over Virtio-net" jiangyiwen
2018-11-15 4:19 ` Jason Wang
2018-11-15 6:46 ` jiangyiwen
2018-11-15 6:49 ` jiangyiwen
2018-11-15 8:19 ` Jason Wang
2018-11-15 9:02 ` jiangyiwen
2018-11-15 9:21 ` Jason Wang
2018-11-16 2:32 ` jiangyiwen
2018-11-16 6:35 ` Jason Wang
2018-11-15 7:04 ` Michael S. Tsirkin
2018-11-15 7:38 ` jiangyiwen
2018-11-15 8:10 ` Michael S. Tsirkin
2018-11-15 8:27 ` Jason Wang
2018-11-15 8:38 ` jiangyiwen
2018-11-15 8:24 ` Jason Wang
2018-11-29 14:00 ` Michael S. Tsirkin
2018-11-30 12:45 ` Jason Wang
2018-11-30 12:52 ` Michael S. Tsirkin
2018-11-30 12:55 ` Jason Wang
2018-11-30 13:10 ` Jason Wang
2018-11-30 13:40 ` Michael S. Tsirkin
2018-12-03 3:10 ` jiangyiwen
2018-12-04 1:31 ` Michael S. Tsirkin
2018-12-04 2:21 ` jiangyiwen
2018-12-04 4:08 ` Michael S. Tsirkin
2018-12-04 6:01 ` jiangyiwen
2018-11-30 13:34 ` Michael S. Tsirkin
2018-11-15 9:36 ` Yan Vugenfirer
2018-11-16 2:37 ` jiangyiwen
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).