Messages in this thread | | | Date | Fri, 03 Apr 2009 14:54:02 +0300 | From | Avi Kivity <> | Subject | Re: [RFC PATCH 00/17] virtual-bus |
| |
Herbert Xu wrote: > On Fri, Apr 03, 2009 at 02:46:04PM +0300, Avi Kivity wrote: > >> The host writes the packet to tap, at which point it is consumed from >> its point of view. The host would like to mention that if there was an >> API to notify it when the packet was actually consumed, then it would >> gladly use it. Bonus points if this involves not copying the packet. >> > > We're using write(2) for this, no?
Yes.
> That should invoke netif_rx_ni > which blocks until the packet is "processed", which usually means > that it's placed on the NIC's hardware queue. >
It doesn't copy and queue the packet? We use O_NONBLOCK and poll() so we can tell when we can queue without blocking.
-- I have a truly marvellous patch that fixes the bug which this signature is too narrow to contain.
| |