[Xen-devel] Re: RX_COPY_THRESHOLD in netfront

[Keir Fraser <Keir.Fraser@xxxxxxxxxxxx>]

On 12/8/06 1:29 am, "Herbert Xu" <herbert@xxxxxxxxxxxxxxxxxxx> wrote:

> I do concede that we're wasting effort in repeatedly initialising skb's
> that we throw away in the case of jumbo packets.  We can remove that
> waste by maintaining our own list of unused skb's that we can simply
> put back on the ring in network_alloc_rx_buffers without going through
> alloc_skb again.

If we're successfully allocating *whole pages* in
network_alloc_rx_buffers(), I'd be surprised if we couldn't allocate a
256-byte skbuff in netif_poll(). On the other hand, just putting the skbuffs
on the rx_batch queue is an easier change to make.

 -- Keir



_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel