From: rick.jones2@hp.com   
      
   glen herrmannsfeldt  wrote:   
   > Rick Jones  wrote:   
   > (snip on IPv4 vs IPv6 and UDP checksum)   
   >   
   > > That might be more accurately put as IPv6 does not include an IP   
   > > *header* checksum - someone reading "packet checksum" might mistakenly   
   > > conclude the IPv4 header checksum includes the data of the IP   
   > > datagram.  The checksum in IPv4 only covers the IPv4 header, to verify   
   > > that there were no bit errors in the header.   
      
   > I remember the discussions some years ago on Sun running NFS with   
   > UDP checksum turned off.  The suggestion was that ethernet checksum   
   > would apply, and verify that the data was correct.  NFS was, and   
   > probably still is, mostly used on LANs, and rarely WANs.  Most often   
   > with no router in between, maybe at most one, and ethernet all the   
   > way.  At that time (68020 Sun3) the time to calculate and verify the   
   > checksum might have been significant, but should be much less   
   > significant today.   
      
   It was a very interesting juxtaposition - the NFS writes have to be to   
   "stable storage" before the replies were sent, but it was OK to eschew   
   the UDP checksum... :)   
      
   Back then there were vendors offering "NFS offload" cards - of course   
   the then-commodity/embedded CPUs on the NFS cards didn't keep-up with   
   the pace at which host CPUs were advancing and so the NFS offload   
   cards died-out.  I wonder if we will see the same thing with TOE (TCP   
   Offload Engine) cards :)   
      
   rick jones   
   --   
   Process shall set you free from the need for rational thought.   
   these opinions are mine, all mine; HP might not want them anyway... :)   
   feel free to post, OR email to rick.jones2 in hp.com but NOT BOTH...   
      
   --- SoupGate-Win32 v1.05   
    * Origin: you cannot sedate... all the things you hate (1:229/2)