jumbograms (& em) & nfs a no go

[Terry Lambert]

Barney Wolff wrote:
> > Implies the sending host is not honoring the MTU restriction when
> > deciding whether or not to frag packets.
> 
> 67582 looks awfully bogus even as a pre-frag length.  How could that come
> over the wire?

The sending host is not honoring the MTU restriction?

8-) 8-).

Most likely, a direct call to ether_output, or a code path that
results in fragmentation not being implemented; see my other post:
it could be that he's using NFS over UDP, and that's doing it.

-- Terry