> >>>>> "Pete" == Pete Wyckoff <wyckoff@ca.sandia.gov> writes:
>
> Pete> davem@redhat.com said:
> >> This is the whole point of "zero-copy" TCP, or did I miss something
> >> in the changes you did?
>
> Pete> Right you are. I only avoided the checksum calculation, which
> Pete> is hardly worth it for modern processors even though the NIC
> Pete> will do it for you.
>
> Pete> One could further argue that TCP is not the protocol of choice
> Pete> if you're looking to minimize transfer latency. There's still
> Pete> the receive path to worry about, for instance.
>
> Latency? zero-copy TCP is not going to do anything to the latency,
> since a NIC that does TCP checksumming on TX will have to do it as
> 'store and forward' since the checksum is in the header. The world is
> about bulk data transfers ;-)
Or you could use XTP with tailer checksums ;);)
Of course implementing all the complexity of XTP is another thing.
-Andi
-- This is like TV. I don't like TV.- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/