Re: TCP Checksum offload in 2.4.19

From: David S. Miller (davem@redhat.com)
Date: Fri Sep 06 2002 - 18:30:54 EST


   From: Bernd Eckenfels <ecki@lina.inka.de>
   Date: Sat, 7 Sep 2002 01:35:27 +0200

   On Fri, Sep 06, 2002 at 04:16:36PM -0700, David S. Miller wrote:
> You don't understand. Because it is too complicated to zerocopy
> arbitrary anonymous user pages, we have to copy it into a stable
> kernel buffer. Because we have to copy, we checksum at the
> same time.
   
   well, which does not make the claim false.

Yes it does, the overhead to flip the users pages
outweighs the benefit of the zerocopy.

But I've even described how to use sendfile() to get all
of the effect of a zerocopy() sendmsg. So it doesn't even
matter if we provide the facility via sendmsg() or not.

I think you're just being difficult for the sake of being
difficult.
-
To unsubscribe from this list: send the line "unsubscribe linux-net" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html



This archive was generated by hypermail 2b29 : Sat Sep 07 2002 - 22:00:02 EST