On Mon, Apr 24, 2017 at 01:49:30PM -0400, Willem de Bruijn wrote: > From: Willem de Bruijn <will...@google.com> > > Tx napi mode increases the rate of transmit interrupts. Suppress some > by masking interrupts while more packets are expected. The interrupts > will be reenabled before the last packet is sent. > > This optimization reduces the througput drop with tx napi for > unidirectional flows such as UDP_STREAM that do not benefit from > cleaning tx completions in the the receive napi handler. > > Signed-off-by: Willem de Bruijn <will...@google.com> > --- > drivers/net/virtio_net.c | 3 +++ > 1 file changed, 3 insertions(+) > > diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c > index 9dd978f34c1f..003143835766 100644 > --- a/drivers/net/virtio_net.c > +++ b/drivers/net/virtio_net.c > @@ -1200,6 +1200,9 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, > struct net_device *dev) > /* Free up any pending old buffers before queueing new ones. */ > free_old_xmit_skbs(sq); > > + if (use_napi && kick) > + virtqueue_enable_cb_delayed(sq->vq); > + > /* timestamp packet in software */ > skb_tx_timestamp(skb);
I have been poking at this code today and I noticed that is actually does enable cb where the commit log says masking interrupts. I think the reason is that with even index previously disable cb actually did nothing while virtqueue_enable_cb_delayed pushed the event index out some more. And this likely explains why it does not work well for packed, where virtqueue_enable_cb_delayed is same as virtqueue_enable_cb. Right? Or did I miss something? > -- > 2.12.2.816.g2cccc81164-goog _______________________________________________ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
