Re: [PATCH RFC 2/3] virtio_net: fix tx capacity checks using new API

2011-06-02 Thread Michael S. Tsirkin
On Thu, Jun 02, 2011 at 11:40:26AM +0930, Rusty Russell wrote: > On Wed, 1 Jun 2011 12:49:54 +0300, "Michael S. Tsirkin" > wrote: > > In the (rare) case where new descriptors are used > > while virtio_net enables vq callback for the TX vq, > > virtio_net uses the number of sg entries in the skb i

Re: [PATCH RFC 2/3] virtio_net: fix tx capacity checks using new API

2011-06-01 Thread Rusty Russell
On Wed, 1 Jun 2011 12:49:54 +0300, "Michael S. Tsirkin" wrote: > In the (rare) case where new descriptors are used > while virtio_net enables vq callback for the TX vq, > virtio_net uses the number of sg entries in the skb it frees to > calculate how many descriptors in the ring have just been mad

[PATCH RFC 2/3] virtio_net: fix tx capacity checks using new API

2011-06-01 Thread Michael S. Tsirkin
In the (rare) case where new descriptors are used while virtio_net enables vq callback for the TX vq, virtio_net uses the number of sg entries in the skb it frees to calculate how many descriptors in the ring have just been made available. But this value is an overestimate: with indirect buffers e