svn commit: r268837 - head/sys/netinet

[Peter Grehan]

Hi Adrian,

> Hah! I wonder why the key from the T3 NIC that Robert committed was so
> .. terrible then.
>
> Are you saying that the actual byte order is totally reversed, or just endian?

  The 32-bit word order of your array is reversed. The last 4 bytes 
should be the first, etc. Have a look at the values in the Microsoft spec.

> I think that was Roberts main concern with using a randomised key at
> startup. It sounds Netapp have already done a lot of the work that I
> was thinking about in the back of my mind - I'll add that to my TODO
> list so we can write a random key generation function at boot time.

  It's still useful to select the Microsoft value e.g. with a tunable, 
since it allows easy verification when folk are implementing RSS.

later,

Peter.