VSOCK: support mergeable rx buffer in vhost-vsock

From the test results, the performance is improved obviously, and guest

Now vsock only support send/receive small packet, it can't achieve high performance. As previous discussed with Jason Wang, I revisit the idea of vhost-net about mergeable rx buffer and implement the mergeable rx buffer in vhost-vsock, it can allow big packet to be scattered in into different buffers and improve performance obviously.

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.

---

Yiwen Jiang (5):
VSOCK: support fill mergeable rx buffer in guest
VSOCK: support fill data to mergeable rx buffer in host
VSOCK: support receive mergeable rx buffer in guest
VSOCK: modify default rx buf size to improve performance
VSOCK: batch sending rx buffer to increase bandwidth

  drivers/vhost/vsock.c                   | 135 +++++++++++++++++++++++------
  include/linux/virtio_vsock.h            |  15 +++-
  include/uapi/linux/virtio_vsock.h       |   5 ++
  net/vmw_vsock/virtio_transport.c        | 147 ++++++++++++++++++++++++++------
  net/vmw_vsock/virtio_transport_common.c |  59 +++++++++++--
  5 files changed, 300 insertions(+), 61 deletions(-)

Quoted 15 lines · jiangyiwen

Now vsock only support send/receive small packet, it can't achieve high performance. As previous discussed with Jason Wang, I revisit the idea of vhost-net about mergeable rx buffer and implement the mergeable rx buffer in vhost-vsock, it can allow big packet to be scattered in into different buffers and improve performance obviously.

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

Quoted 7 lines

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.

Hi:

Thanks for the patches and the numbers are really impressive.

But instead of duplicating codes between sock and net. I was considering to use virtio-net as a transport of vsock. Then we may have all existed features likes batching, mergeable rx buffers and multiqueue. Want to consider this idea? Thoughts?

Quoted 10 lines

---

Yiwen Jiang (5):
VSOCK: support fill mergeable rx buffer in guest
VSOCK: support fill data to mergeable rx buffer in host
VSOCK: support receive mergeable rx buffer in guest
VSOCK: modify default rx buf size to improve performance
VSOCK: batch sending rx buffer to increase bandwidth

Quoted 7 lines

  drivers/vhost/vsock.c                   | 135 +++++++++++++++++++++++------
  include/linux/virtio_vsock.h            |  15 +++-
  include/uapi/linux/virtio_vsock.h       |   5 ++
  net/vmw_vsock/virtio_transport.c        | 147 ++++++++++++++++++++++++++------
  net/vmw_vsock/virtio_transport_common.c |  59 +++++++++++--
  5 files changed, 300 insertions(+), 61 deletions(-)

.

Quoted 21 lines · Jason Wang

Quoted 20 lines · jiangyiwen

Now vsock only support send/receive small packet, it can't achieve high performance. As previous discussed with Jason Wang, I revisit the idea of vhost-net about mergeable rx buffer and implement the mergeable rx buffer in vhost-vsock, it can allow big packet to be scattered in into different buffers and improve performance obviously.

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

Quoted 9 lines

Quoted 2 lines

From the test results, the performance is improved obviously, and guest
memory will not be wasted.

Hi:

Thanks for the patches and the numbers are really impressive.

But instead of duplicating codes between sock and net. I was considering to use virtio-net as a transport of vsock. Then we may have all existed features likes batching, mergeable rx buffers and multiqueue. Want to consider this idea? Thoughts?

Hi Jason,

I am not very familiar with virtio-net, so I am afraid I can't give too much effective advice. Then I have several problems:

1. If use virtio-net as a transport, guest should see a virtio-net device instead of virtio-vsock device, right? Is vsock only as a transport between socket and net_device? User should still use AF_VSOCK type to create socket, right?

2. I want to know if this idea has already started, and how is the current progress?

3. And what is stefan's idea?

Thanks,
Yiwen.

Quoted 33 lines · jiangyiwen

Quoted 21 lines · Jason Wang

Quoted 20 lines · jiangyiwen

Now vsock only support send/receive small packet, it can't achieve high performance. As previous discussed with Jason Wang, I revisit the idea of vhost-net about mergeable rx buffer and implement the mergeable rx buffer in vhost-vsock, it can allow big packet to be scattered in into different buffers and improve performance obviously.

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

Quoted 9 lines

Quoted 2 lines

From the test results, the performance is improved obviously, and guest
memory will not be wasted.

Hi:

Thanks for the patches and the numbers are really impressive.

But instead of duplicating codes between sock and net. I was considering to use virtio-net as a transport of vsock. Then we may have all existed features likes batching, mergeable rx buffers and multiqueue. Want to consider this idea? Thoughts?

Hi Jason,

Quoted 7 lines

I am not very familiar with virtio-net, so I am afraid I can't give too much effective advice. Then I have several problems:

1. If use virtio-net as a transport, guest should see a virtio-net device instead of virtio-vsock device, right? Is vsock only as a transport between socket and net_device? User should still use AF_VSOCK type to create socket, right?

Well, there're many choices. What you need is just to keep the socket API and hide the implementation. For example, you can keep the vosck device in guest and switch to use vhost-net in host. We probably need a new feature bit or header to let vhost know we are passing vsock packet. And vhost-net could forward the packet to vsock core on host.

Quoted 3 lines

2. I want to know if this idea has already started, and how is the current progress?

Not yet started. Just want to listen from the community. If this sounds good, do you have interest in implementing this?

Quoted 1 line

Quoted 1 line

3. And what is stefan's idea?

Talk with Stefan a little on this during KVM Forum. I think he tends to agree on this idea. Anyway, let's wait for his reply.

Thanks

Quoted 4 lines

Thanks,
Yiwen.

.

Quoted 56 lines · Jason Wang

Quoted 33 lines · jiangyiwen

Quoted 21 lines · Jason Wang

Quoted 20 lines · jiangyiwen

Now vsock only support send/receive small packet, it can't achieve high performance. As previous discussed with Jason Wang, I revisit the idea of vhost-net about mergeable rx buffer and implement the mergeable rx buffer in vhost-vsock, it can allow big packet to be scattered in into different buffers and improve performance obviously.

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

Quoted 9 lines

Quoted 2 lines

From the test results, the performance is improved obviously, and guest
memory will not be wasted.

Hi:

Thanks for the patches and the numbers are really impressive.

But instead of duplicating codes between sock and net. I was considering to use virtio-net as a transport of vsock. Then we may have all existed features likes batching, mergeable rx buffers and multiqueue. Want to consider this idea? Thoughts?

Hi Jason,

Quoted 7 lines

I am not very familiar with virtio-net, so I am afraid I can't give too much effective advice. Then I have several problems:

1. If use virtio-net as a transport, guest should see a virtio-net device instead of virtio-vsock device, right? Is vsock only as a transport between socket and net_device? User should still use AF_VSOCK type to create socket, right?

Well, there're many choices. What you need is just to keep the socket API and hide the implementation. For example, you can keep the vosck device in guest and switch to use vhost-net in host. We probably need a new feature bit or header to let vhost know we are passing vsock packet. And vhost-net could forward the packet to vsock core on host.

Quoted 2 lines

2. I want to know if this idea has already started, and how is the current progress?

Not yet started. Just want to listen from the community. If this sounds good, do you have interest in implementing this?

Quoted 1 line

3. And what is stefan's idea?

Talk with Stefan a little on this during KVM Forum. I think he tends to agree on this idea. Anyway, let's wait for his reply.

Quoted 3 lines

Thanks

Hi Jason,

Thanks your reply, what you want is try to avoid duplicate code, and still use the existed features with virtio-net.

Yes, if this sounds good and most people can recognize this idea, I am very happy to implement this.

In addition, I hope you can review these patches before the new idea is implemented, after all the performance can be improved. :-)

Thanks,
Yiwen.

Quoted 5 lines

Quoted 3 lines

Thanks,
Yiwen.

.

Quoted 57 lines · jiangyiwen

Quoted 56 lines · Jason Wang

Quoted 33 lines · jiangyiwen

Quoted 21 lines · Jason Wang

Quoted 20 lines · jiangyiwen

Now vsock only support send/receive small packet, it can't achieve high performance. As previous discussed with Jason Wang, I revisit the idea of vhost-net about mergeable rx buffer and implement the mergeable rx buffer in vhost-vsock, it can allow big packet to be scattered in into different buffers and improve performance obviously.

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

Quoted 9 lines

Quoted 2 lines

From the test results, the performance is improved obviously, and guest
memory will not be wasted.

Hi:

Thanks for the patches and the numbers are really impressive.

But instead of duplicating codes between sock and net. I was considering to use virtio-net as a transport of vsock. Then we may have all existed features likes batching, mergeable rx buffers and multiqueue. Want to consider this idea? Thoughts?

Hi Jason,

Quoted 7 lines

I am not very familiar with virtio-net, so I am afraid I can't give too much effective advice. Then I have several problems:

1. If use virtio-net as a transport, guest should see a virtio-net device instead of virtio-vsock device, right? Is vsock only as a transport between socket and net_device? User should still use AF_VSOCK type to create socket, right?

Well, there're many choices. What you need is just to keep the socket API and hide the implementation. For example, you can keep the vosck device in guest and switch to use vhost-net in host. We probably need a new feature bit or header to let vhost know we are passing vsock packet. And vhost-net could forward the packet to vsock core on host.

Quoted 2 lines

2. I want to know if this idea has already started, and how is the current progress?

Not yet started. Just want to listen from the community. If this sounds good, do you have interest in implementing this?

Quoted 1 line

3. And what is stefan's idea?

Talk with Stefan a little on this during KVM Forum. I think he tends to agree on this idea. Anyway, let's wait for his reply.

Quoted 7 lines

Quoted 3 lines

Thanks

Hi Jason,

Thanks your reply, what you want is try to avoid duplicate code, and still use the existed features with virtio-net.

Yes, technically we can use virtio-net driver is guest as well but we could do it step by step.

Quoted 2 lines

Yes, if this sounds good and most people can recognize this idea, I am very happy to implement this.

Cool, thanks.

Quoted 3 lines

In addition, I hope you can review these patches before the new idea is implemented, after all the performance can be improved. :-)

Ok.

So the patch actually did three things:

- mergeable buffer implementation

- increase the default rx buffer size

- add used and signal guest in a batch

It would be helpful if you can measure the performance improvement independently. This can give reviewer a better understanding on how much did each part help.

Thanks

Quoted 4 lines

Thanks,
Yiwen.

Quoted 6 lines

Quoted 5 lines

Quoted 3 lines

Thanks,
Yiwen.

.

.

Quoted 94 lines · Jason Wang

Quoted 57 lines · jiangyiwen

Quoted 56 lines · Jason Wang

Quoted 33 lines · jiangyiwen

Quoted 21 lines · Jason Wang

Quoted 20 lines · jiangyiwen

Now vsock only support send/receive small packet, it can't achieve high performance. As previous discussed with Jason Wang, I revisit the idea of vhost-net about mergeable rx buffer and implement the mergeable rx buffer in vhost-vsock, it can allow big packet to be scattered in into different buffers and improve performance obviously.

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

Quoted 9 lines

Quoted 2 lines

From the test results, the performance is improved obviously, and guest
memory will not be wasted.

Hi:

Thanks for the patches and the numbers are really impressive.

But instead of duplicating codes between sock and net. I was considering to use virtio-net as a transport of vsock. Then we may have all existed features likes batching, mergeable rx buffers and multiqueue. Want to consider this idea? Thoughts?

Hi Jason,

Quoted 7 lines

I am not very familiar with virtio-net, so I am afraid I can't give too much effective advice. Then I have several problems:

1. If use virtio-net as a transport, guest should see a virtio-net device instead of virtio-vsock device, right? Is vsock only as a transport between socket and net_device? User should still use AF_VSOCK type to create socket, right?

Well, there're many choices. What you need is just to keep the socket API and hide the implementation. For example, you can keep the vosck device in guest and switch to use vhost-net in host. We probably need a new feature bit or header to let vhost know we are passing vsock packet. And vhost-net could forward the packet to vsock core on host.

Quoted 2 lines

2. I want to know if this idea has already started, and how is the current progress?

Not yet started. Just want to listen from the community. If this sounds good, do you have interest in implementing this?

Quoted 1 line

3. And what is stefan's idea?

Talk with Stefan a little on this during KVM Forum. I think he tends to agree on this idea. Anyway, let's wait for his reply.

Quoted 7 lines

Quoted 3 lines

Thanks

Hi Jason,

Thanks your reply, what you want is try to avoid duplicate code, and still use the existed features with virtio-net.

Yes, technically we can use virtio-net driver is guest as well but we could do it step by step.

Quoted 2 lines

Yes, if this sounds good and most people can recognize this idea, I am very happy to implement this.

Cool, thanks.

Quoted 3 lines

In addition, I hope you can review these patches before the new idea is implemented, after all the performance can be improved. :-)

Ok.

So the patch actually did three things:

- mergeable buffer implementation

- increase the default rx buffer size

- add used and signal guest in a batch

Quoted 5 lines

It would be helpful if you can measure the performance improvement independently. This can give reviewer a better understanding on how much did each part help.

Thanks

Great, I will test the performance independently in the later version.

Quoted 92 lines · jiangyiwen

Quoted 91 lines · Jason Wang

Quoted 54 lines · jiangyiwen

Quoted 53 lines · Jason Wang

Quoted 33 lines · jiangyiwen

Quoted 21 lines · Jason Wang

Quoted 20 lines · jiangyiwen

Now vsock only support send/receive small packet, it can't achieve high performance. As previous discussed with Jason Wang, I revisit the idea of vhost-net about mergeable rx buffer and implement the mergeable rx buffer in vhost-vsock, it can allow big packet to be scattered in into different buffers and improve performance obviously.

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

Quoted 9 lines

Quoted 2 lines

From the test results, the performance is improved obviously, and guest
memory will not be wasted.

Hi:

Thanks for the patches and the numbers are really impressive.

But instead of duplicating codes between sock and net. I was considering to use virtio-net as a transport of vsock. Then we may have all existed features likes batching, mergeable rx buffers and multiqueue. Want to consider this idea? Thoughts?

Hi Jason,

Quoted 7 lines

I am not very familiar with virtio-net, so I am afraid I can't give too much effective advice. Then I have several problems:

1. If use virtio-net as a transport, guest should see a virtio-net device instead of virtio-vsock device, right? Is vsock only as a transport between socket and net_device? User should still use AF_VSOCK type to create socket, right?

Well, there're many choices. What you need is just to keep the socket API and hide the implementation. For example, you can keep the vosck device in guest and switch to use vhost-net in host. We probably need a new feature bit or header to let vhost know we are passing vsock packet. And vhost-net could forward the packet to vsock core on host.

Quoted 2 lines

2. I want to know if this idea has already started, and how is the current progress?

Not yet started. Just want to listen from the community. If this sounds good, do you have interest in implementing this?

Quoted 1 line

3. And what is stefan's idea?

Talk with Stefan a little on this during KVM Forum. I think he tends to agree on this idea. Anyway, let's wait for his reply.

Quoted 7 lines

Quoted 3 lines

Thanks

Hi Jason,

Thanks your reply, what you want is try to avoid duplicate code, and still use the existed features with virtio-net.

Yes, technically we can use virtio-net driver is guest as well but we could do it step by step.

Quoted 2 lines

Yes, if this sounds good and most people can recognize this idea, I am very happy to implement this.

Cool, thanks.

Quoted 2 lines

In addition, I hope you can review these patches before the new idea is implemented, after all the performance can be improved. :-)

Ok.

So the patch actually did three things:

- mergeable buffer implementation

- increase the default rx buffer size

- add used and signal guest in a batch

It would be helpful if you can measure the performance improvement independently. This can give reviewer a better understanding on how much did each part help.

Thanks

Quoted 1 line

Great, I will test the performance independently in the later version.

I'm catching up on email so maybe you've already discussed this, but a key design point in virtio-vsock is reliable in-order delivery. When using virtio-net code it's important to keep those properties so that AF_VSOCK SOCK_STREAM sockets work as expected. Packets must not be reordered or dropped.

In addition, there's the virtio-vsock flow control scheme that allows multiple sockets to share a ring without starvation or denial-of-service problems. The guest knows how much socket buffer space is available on the host (and vice versa). A well-behaved guest only sends up to the available buffer space so that the host can copy the data into the socket buffer and free up ring space for other sockets. This scheme is how virtio-vsock achieves guaranteed delivery while avoiding starvation or denial-of-service.

So you'll need to use some kind of framing (protocol) that preserves these properties on top of virtio-net. This framing could be based on virtio-vsock's packet headers.

Stefan

Quoted 92 lines · jiangyiwen

Quoted 91 lines · Jason Wang

Quoted 54 lines · jiangyiwen

Quoted 53 lines · Jason Wang

Quoted 33 lines · jiangyiwen

Quoted 21 lines · Jason Wang

Quoted 20 lines · jiangyiwen

Now vsock only support send/receive small packet, it can't achieve high performance. As previous discussed with Jason Wang, I revisit the idea of vhost-net about mergeable rx buffer and implement the mergeable rx buffer in vhost-vsock, it can allow big packet to be scattered in into different buffers and improve performance obviously.

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

Quoted 9 lines

Quoted 2 lines

From the test results, the performance is improved obviously, and guest
memory will not be wasted.

Hi:

Thanks for the patches and the numbers are really impressive.

But instead of duplicating codes between sock and net. I was considering to use virtio-net as a transport of vsock. Then we may have all existed features likes batching, mergeable rx buffers and multiqueue. Want to consider this idea? Thoughts?

Hi Jason,

Quoted 7 lines

I am not very familiar with virtio-net, so I am afraid I can't give too much effective advice. Then I have several problems:

1. If use virtio-net as a transport, guest should see a virtio-net device instead of virtio-vsock device, right? Is vsock only as a transport between socket and net_device? User should still use AF_VSOCK type to create socket, right?

Well, there're many choices. What you need is just to keep the socket API and hide the implementation. For example, you can keep the vosck device in guest and switch to use vhost-net in host. We probably need a new feature bit or header to let vhost know we are passing vsock packet. And vhost-net could forward the packet to vsock core on host.

Quoted 2 lines

2. I want to know if this idea has already started, and how is the current progress?

Not yet started. Just want to listen from the community. If this sounds good, do you have interest in implementing this?

Quoted 1 line

3. And what is stefan's idea?

Talk with Stefan a little on this during KVM Forum. I think he tends to agree on this idea. Anyway, let's wait for his reply.

Quoted 7 lines

Quoted 3 lines

Thanks

Hi Jason,

Thanks your reply, what you want is try to avoid duplicate code, and still use the existed features with virtio-net.

Yes, technically we can use virtio-net driver is guest as well but we could do it step by step.

Quoted 2 lines

Yes, if this sounds good and most people can recognize this idea, I am very happy to implement this.

Cool, thanks.

Quoted 2 lines

In addition, I hope you can review these patches before the new idea is implemented, after all the performance can be improved. :-)

Ok.

So the patch actually did three things:

- mergeable buffer implementation

- increase the default rx buffer size

- add used and signal guest in a batch

It would be helpful if you can measure the performance improvement independently. This can give reviewer a better understanding on how much did each part help.

Thanks

Quoted 1 line

Great, I will test the performance independently in the later version.

I'm catching up on email so maybe you've already discussed this, but a key design point in virtio-vsock is reliable in-order delivery. When using virtio-net code it's important to keep those properties so that AF_VSOCK SOCK_STREAM sockets work as expected. Packets must not be reordered or dropped.

In addition, there's the virtio-vsock flow control scheme that allows multiple sockets to share a ring without starvation or denial-of-service problems. The guest knows how much socket buffer space is available on the host (and vice versa). A well-behaved guest only sends up to the available buffer space so that the host can copy the data into the socket buffer and free up ring space for other sockets. This scheme is how virtio-vsock achieves guaranteed delivery while avoiding starvation or denial-of-service.

So you'll need to use some kind of framing (protocol) that preserves these properties on top of virtio-net. This framing could be based on virtio-vsock's packet headers.

Stefan

Quoted 95 lines · jiangyiwen

Quoted 94 lines · Jason Wang

Quoted 57 lines · jiangyiwen

Quoted 56 lines · Jason Wang

Quoted 33 lines · jiangyiwen

Quoted 21 lines · Jason Wang

Quoted 20 lines · jiangyiwen

Now vsock only support send/receive small packet, it can't achieve high performance. As previous discussed with Jason Wang, I revisit the idea of vhost-net about mergeable rx buffer and implement the mergeable rx buffer in vhost-vsock, it can allow big packet to be scattered in into different buffers and improve performance obviously.

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

Quoted 9 lines

Quoted 2 lines

From the test results, the performance is improved obviously, and guest
memory will not be wasted.

Hi:

Thanks for the patches and the numbers are really impressive.

But instead of duplicating codes between sock and net. I was considering to use virtio-net as a transport of vsock. Then we may have all existed features likes batching, mergeable rx buffers and multiqueue. Want to consider this idea? Thoughts?

Hi Jason,

Quoted 7 lines

I am not very familiar with virtio-net, so I am afraid I can't give too much effective advice. Then I have several problems:

1. If use virtio-net as a transport, guest should see a virtio-net device instead of virtio-vsock device, right? Is vsock only as a transport between socket and net_device? User should still use AF_VSOCK type to create socket, right?

Well, there're many choices. What you need is just to keep the socket API and hide the implementation. For example, you can keep the vosck device in guest and switch to use vhost-net in host. We probably need a new feature bit or header to let vhost know we are passing vsock packet. And vhost-net could forward the packet to vsock core on host.

Quoted 2 lines

2. I want to know if this idea has already started, and how is the current progress?

Not yet started. Just want to listen from the community. If this sounds good, do you have interest in implementing this?

Quoted 1 line

3. And what is stefan's idea?

Talk with Stefan a little on this during KVM Forum. I think he tends to agree on this idea. Anyway, let's wait for his reply.

Quoted 7 lines

Quoted 3 lines

Thanks

Hi Jason,

Thanks your reply, what you want is try to avoid duplicate code, and still use the existed features with virtio-net.

Yes, technically we can use virtio-net driver is guest as well but we could do it step by step.

Quoted 2 lines

Yes, if this sounds good and most people can recognize this idea, I am very happy to implement this.

Cool, thanks.

Quoted 3 lines

In addition, I hope you can review these patches before the new idea is implemented, after all the performance can be improved. :-)

Ok.

So the patch actually did three things:

- mergeable buffer implementation

- increase the default rx buffer size

- add used and signal guest in a batch

Quoted 7 lines

Quoted 5 lines

It would be helpful if you can measure the performance improvement independently. This can give reviewer a better understanding on how much did each part help.

Thanks

Great, I will test the performance independently in the later version.

I'm catching up on email so maybe you've already discussed this, but a key design point in virtio-vsock is reliable in-order delivery. When using virtio-net code it's important to keep those properties so that AF_VSOCK SOCK_STREAM sockets work as expected. Packets must not be reordered or dropped.

In addition, there's the virtio-vsock flow control scheme that allows multiple sockets to share a ring without starvation or denial-of-service problems. The guest knows how much socket buffer space is available on the host (and vice versa). A well-behaved guest only sends up to the available buffer space so that the host can copy the data into the socket buffer and free up ring space for other sockets. This scheme is how virtio-vsock achieves guaranteed delivery while avoiding starvation or denial-of-service.

So you'll need to use some kind of framing (protocol) that preserves these properties on top of virtio-net. This framing could be based on virtio-vsock's packet headers.

Stefan

Quoted 56 lines · Jason Wang

Quoted 33 lines · jiangyiwen

Quoted 21 lines · Jason Wang

Quoted 20 lines · jiangyiwen

Now vsock only support send/receive small packet, it can't achieve high performance. As previous discussed with Jason Wang, I revisit the idea of vhost-net about mergeable rx buffer and implement the mergeable rx buffer in vhost-vsock, it can allow big packet to be scattered in into different buffers and improve performance obviously.

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

Quoted 9 lines

Quoted 2 lines

From the test results, the performance is improved obviously, and guest
memory will not be wasted.

Hi:

Thanks for the patches and the numbers are really impressive.

But instead of duplicating codes between sock and net. I was considering to use virtio-net as a transport of vsock. Then we may have all existed features likes batching, mergeable rx buffers and multiqueue. Want to consider this idea? Thoughts?

Hi Jason,

Quoted 7 lines

I am not very familiar with virtio-net, so I am afraid I can't give too much effective advice. Then I have several problems:

1. If use virtio-net as a transport, guest should see a virtio-net device instead of virtio-vsock device, right? Is vsock only as a transport between socket and net_device? User should still use AF_VSOCK type to create socket, right?

Well, there're many choices. What you need is just to keep the socket API and hide the implementation. For example, you can keep the vosck device in guest and switch to use vhost-net in host. We probably need a new feature bit or header to let vhost know we are passing vsock packet. And vhost-net could forward the packet to vsock core on host.

Quoted 2 lines

2. I want to know if this idea has already started, and how is the current progress?

Not yet started. Just want to listen from the community. If this sounds good, do you have interest in implementing this?

Quoted 1 line

3. And what is stefan's idea?

Talk with Stefan a little on this during KVM Forum. I think he tends to agree on this idea. Anyway, let's wait for his reply.

Quoted 3 lines

Thanks

Hi Jason,

Thanks your reply, what you want is try to avoid duplicate code, and still use the existed features with virtio-net.

Yes, if this sounds good and most people can recognize this idea, I am very happy to implement this.

In addition, I hope you can review these patches before the new idea is implemented, after all the performance can be improved. :-)

Thanks,
Yiwen.

Quoted 5 lines

Quoted 3 lines

Thanks,
Yiwen.

.

Quoted 21 lines · Jason Wang

Quoted 20 lines · jiangyiwen

Now vsock only support send/receive small packet, it can't achieve high performance. As previous discussed with Jason Wang, I revisit the idea of vhost-net about mergeable rx buffer and implement the mergeable rx buffer in vhost-vsock, it can allow big packet to be scattered in into different buffers and improve performance obviously.

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

Quoted 9 lines

Quoted 2 lines

From the test results, the performance is improved obviously, and guest
memory will not be wasted.

Hi:

Thanks for the patches and the numbers are really impressive.

But instead of duplicating codes between sock and net. I was considering to use virtio-net as a transport of vsock. Then we may have all existed features likes batching, mergeable rx buffers and multiqueue. Want to consider this idea? Thoughts?

Hi Jason,

I am not very familiar with virtio-net, so I am afraid I can't give too much effective advice. Then I have several problems:

1. If use virtio-net as a transport, guest should see a virtio-net device instead of virtio-vsock device, right? Is vsock only as a transport between socket and net_device? User should still use AF_VSOCK type to create socket, right?

2. I want to know if this idea has already started, and how is the current progress?

3. And what is stefan's idea?

Thanks,
Yiwen.

Quoted 15 lines · jiangyiwen

Now vsock only support send/receive small packet, it can't achieve high performance. As previous discussed with Jason Wang, I revisit the idea of vhost-net about mergeable rx buffer and implement the mergeable rx buffer in vhost-vsock, it can allow big packet to be scattered in into different buffers and improve performance obviously.

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

Quoted 7 lines

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.

Hi:

Thanks for the patches and the numbers are really impressive.

But instead of duplicating codes between sock and net. I was considering to use virtio-net as a transport of vsock. Then we may have all existed features likes batching, mergeable rx buffers and multiqueue. Want to consider this idea? Thoughts?

Quoted 10 lines

---

Yiwen Jiang (5):
VSOCK: support fill mergeable rx buffer in guest
VSOCK: support fill data to mergeable rx buffer in host
VSOCK: support receive mergeable rx buffer in guest
VSOCK: modify default rx buf size to improve performance
VSOCK: batch sending rx buffer to increase bandwidth

Quoted 7 lines

  drivers/vhost/vsock.c                   | 135 +++++++++++++++++++++++------
  include/linux/virtio_vsock.h            |  15 +++-
  include/uapi/linux/virtio_vsock.h       |   5 ++
  net/vmw_vsock/virtio_transport.c        | 147 ++++++++++++++++++++++++++------
  net/vmw_vsock/virtio_transport_common.c |  59 +++++++++++--
  5 files changed, 300 insertions(+), 61 deletions(-)

.

Now vsock only support send/receive small packet, it can't achieve high performance. As previous discussed with Jason Wang, I revisit the idea of vhost-net about mergeable rx buffer and implement the mergeable rx buffer in vhost-vsock, it can allow big packet to be scattered in into different buffers and improve performance obviously.

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.

---

Yiwen Jiang (5):
VSOCK: support fill mergeable rx buffer in guest
VSOCK: support fill data to mergeable rx buffer in host
VSOCK: support receive mergeable rx buffer in guest
VSOCK: modify default rx buf size to improve performance
VSOCK: batch sending rx buffer to increase bandwidth

  drivers/vhost/vsock.c                   | 135 +++++++++++++++++++++++------
  include/linux/virtio_vsock.h            |  15 +++-
  include/uapi/linux/virtio_vsock.h       |   5 ++
  net/vmw_vsock/virtio_transport.c        | 147 ++++++++++++++++++++++++++------
  net/vmw_vsock/virtio_transport_common.c |  59 +++++++++++--
  5 files changed, 300 insertions(+), 61 deletions(-)