Re: zero-copy TCP fileserving

Jes Sorensen (Jes.Sorensen@cern.ch)
24 Sep 1999 20:01:30 +0200


>>>>> "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 ;-)

I am still looking forward to the day when we will have zero-copy TX
support, it should give us even more performance on the Linux boxes
running our tape silos.

Jes

-
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/