lkml.org 
[lkml]   [2019]   [May]   [14]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [PATCH v2 1/8] vsock/virtio: limit the memory used per-socket
On Tue, May 14, 2019 at 11:25:34AM +0800, Jason Wang wrote:
>
> On 2019/5/14 上午1:23, Stefano Garzarella wrote:
> > On Mon, May 13, 2019 at 05:58:53PM +0800, Jason Wang wrote:
> > > On 2019/5/10 下午8:58, Stefano Garzarella wrote:
> > > > Since virtio-vsock was introduced, the buffers filled by the host
> > > > and pushed to the guest using the vring, are directly queued in
> > > > a per-socket list avoiding to copy it.
> > > > These buffers are preallocated by the guest with a fixed
> > > > size (4 KB).
> > > >
> > > > The maximum amount of memory used by each socket should be
> > > > controlled by the credit mechanism.
> > > > The default credit available per-socket is 256 KB, but if we use
> > > > only 1 byte per packet, the guest can queue up to 262144 of 4 KB
> > > > buffers, using up to 1 GB of memory per-socket. In addition, the
> > > > guest will continue to fill the vring with new 4 KB free buffers
> > > > to avoid starvation of her sockets.
> > > >
> > > > This patch solves this issue copying the payload in a new buffer.
> > > > Then it is queued in the per-socket list, and the 4KB buffer used
> > > > by the host is freed.
> > > >
> > > > In this way, the memory used by each socket respects the credit
> > > > available, and we still avoid starvation, paying the cost of an
> > > > extra memory copy. When the buffer is completely full we do a
> > > > "zero-copy", moving the buffer directly in the per-socket list.
> > >
> > > I wonder in the long run we should use generic socket accouting mechanism
> > > provided by kernel (e.g socket, skb, sndbuf, recvbug, truesize) instead of
> > > vsock specific thing to avoid duplicating efforts.
> > I agree, the idea is to switch to sk_buff but this should require an huge
> > change. If we will use the virtio-net datapath, it will become simpler.
>
>
> Yes, unix domain socket is one example that uses general skb and socket
> structure. And we probably need some kind of socket pair on host. Using
> socket can also simplify the unification with vhost-net which depends on the
> socket proto_ops to work. I admit it's a huge change probably, we can do it
> gradually.
>

Yes, I also prefer to do this change gradually :)

>
> > >
> > > > Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
> > > > ---
> > > > drivers/vhost/vsock.c | 2 +
> > > > include/linux/virtio_vsock.h | 8 +++
> > > > net/vmw_vsock/virtio_transport.c | 1 +
> > > > net/vmw_vsock/virtio_transport_common.c | 95 ++++++++++++++++++-------
> > > > 4 files changed, 81 insertions(+), 25 deletions(-)
> > > >
> > > > diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
> > > > index bb5fc0e9fbc2..7964e2daee09 100644
> > > > --- a/drivers/vhost/vsock.c
> > > > +++ b/drivers/vhost/vsock.c
> > > > @@ -320,6 +320,8 @@ vhost_vsock_alloc_pkt(struct vhost_virtqueue *vq,
> > > > return NULL;
> > > > }
> > > > + pkt->buf_len = pkt->len;
> > > > +
> > > > nbytes = copy_from_iter(pkt->buf, pkt->len, &iov_iter);
> > > > if (nbytes != pkt->len) {
> > > > vq_err(vq, "Expected %u byte payload, got %zu bytes\n",
> > > > diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
> > > > index e223e2632edd..345f04ee9193 100644
> > > > --- a/include/linux/virtio_vsock.h
> > > > +++ b/include/linux/virtio_vsock.h
> > > > @@ -54,9 +54,17 @@ struct virtio_vsock_pkt {
> > > > void *buf;
> > > > u32 len;
> > > > u32 off;
> > > > + u32 buf_len;
> > > > bool reply;
> > > > };
> > > > +struct virtio_vsock_buf {
> > > > + struct list_head list;
> > > > + void *addr;
> > > > + u32 len;
> > > > + u32 off;
> > > > +};
> > > > +
> > > > struct virtio_vsock_pkt_info {
> > > > u32 remote_cid, remote_port;
> > > > struct vsock_sock *vsk;
> > > > diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
> > > > index 15eb5d3d4750..af1d2ce12f54 100644
> > > > --- a/net/vmw_vsock/virtio_transport.c
> > > > +++ b/net/vmw_vsock/virtio_transport.c
> > > > @@ -280,6 +280,7 @@ static void virtio_vsock_rx_fill(struct virtio_vsock *vsock)
> > > > break;
> > > > }
> > > > + pkt->buf_len = buf_len;
> > > > pkt->len = buf_len;
> > > > sg_init_one(&hdr, &pkt->hdr, sizeof(pkt->hdr));
> > > > diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
> > > > index 602715fc9a75..0248d6808755 100644
> > > > --- a/net/vmw_vsock/virtio_transport_common.c
> > > > +++ b/net/vmw_vsock/virtio_transport_common.c
> > > > @@ -65,6 +65,9 @@ virtio_transport_alloc_pkt(struct virtio_vsock_pkt_info *info,
> > > > pkt->buf = kmalloc(len, GFP_KERNEL);
> > > > if (!pkt->buf)
> > > > goto out_pkt;
> > > > +
> > > > + pkt->buf_len = len;
> > > > +
> > > > err = memcpy_from_msg(pkt->buf, info->msg, len);
> > > > if (err)
> > > > goto out;
> > > > @@ -86,6 +89,46 @@ virtio_transport_alloc_pkt(struct virtio_vsock_pkt_info *info,
> > > > return NULL;
> > > > }
> > > > +static struct virtio_vsock_buf *
> > > > +virtio_transport_alloc_buf(struct virtio_vsock_pkt *pkt, bool zero_copy)
> > > > +{
> > > > + struct virtio_vsock_buf *buf;
> > > > +
> > > > + if (pkt->len == 0)
> > > > + return NULL;
> > > > +
> > > > + buf = kzalloc(sizeof(*buf), GFP_KERNEL);
> > > > + if (!buf)
> > > > + return NULL;
> > > > +
> > > > + /* If the buffer in the virtio_vsock_pkt is full, we can move it to
> > > > + * the new virtio_vsock_buf avoiding the copy, because we are sure that
> > > > + * we are not use more memory than that counted by the credit mechanism.
> > > > + */
> > > > + if (zero_copy && pkt->len == pkt->buf_len) {
> > > > + buf->addr = pkt->buf;
> > > > + pkt->buf = NULL;
> > > > + } else {
> > >
> > > Is the copy still needed if we're just few bytes less? We meet similar issue
> > > for virito-net, and virtio-net solve this by always copy first 128bytes for
> > > big packets.
> > >
> > > See receive_big()
> > I'm seeing, It is more sophisticated.
> > IIUC, virtio-net allocates a sk_buff with 128 bytes of buffer, then copies the
> > first 128 bytes, then adds the buffer used to receive the packet as a frag to
> > the skb.
>
>
> Yes and the point is if the packet is smaller than 128 bytes the pages will
> be recycled.
>
>

So it's avoid the overhead of allocation of a large buffer. I got it.

Just a curiosity, why the threshold is 128 bytes?

> >
> > Do you suggest to implement something similar, or for now we can use my
> > approach and if we will merge the datapath we can reuse the virtio-net
> > approach?
>
>
> I think we need a better threshold. If I understand the patch correctly, we
> will do copy unless the packet is 64K when guest is doing receiving. 1 byte
> packet is indeed a problem, but we need to solve it without losing too much
> performance.

It is correct. I'll try to figure out a better threshold and the usage of
order 0 page.

Thanks again for your advices,
Stefano

\
 
 \ /
  Last update: 2019-05-14 18:35    [W:0.088 / U:0.148 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site