On Mon, Nov 23, 2009 at 11:23:18AM +1030, Rusty Russell wrote:
On Fri, 20 Nov 2009 04:39:19 pm Shirley Ma wrote:
Guest virtio_net receives packets from its pre-allocated vring
buffers, then it delivers these packets to upper layer protocols
as skb buffs. So it's not necessary to
On Mon, 2009-11-23 at 11:23 +1030, Rusty Russell wrote:
I'd like to drop big packet support from our driver, but I don't know
how many kvm hosts will not offer mergable rx bufs yet. Anthony?
Mergeable rx bufs were first added in kvm-80 and qemu-0.10.0
So e.g., it's in Fedora since Fedora 11
On Fri, 20 Nov 2009 04:39:19 pm Shirley Ma wrote:
Guest virtio_net receives packets from its pre-allocated vring
buffers, then it delivers these packets to upper layer protocols
as skb buffs. So it's not necessary to pre-allocate skb for each
mergable buffer, then frees it when it's useless.
Guest virtio_net receives packets from its pre-allocated vring
buffers, then it delivers these packets to upper layer protocols
as skb buffs. So it's not necessary to pre-allocate skb for each
mergable buffer, then frees it when it's useless.
This patch has deferred skb allocation when