LSO and HW TX Checksum Link Properties [PSARC/2009/345 FastTrack timeout 06/15/2009]

[James Carlson]

Dale Ghent writes:
> Take a driver such as bge or e1000g for example. These two drivers  
> support a ton of silicon parts that have quite varied feature sets  
> among. Some do jumbo, some don't. Some have various levels of off- 
> loading and checksumming, some none at all. It would be useful, I  
> would think, for an admin to know if a particular (offload) feature is  
> present on a particular chipset without trying to dig up the chipset's  
> docs, make sense of source code, or guess. Right now this area is sort  
> of like mystery meat.

That does sound useful, but I don't think it sounds like a
configuration parameter.  Perhaps a set of common kstats could be
developed to 'advertise' certain internal but non-trivial features.
(Almost by definition, these would likely be things that happen to be
complicated enough that they're usually infested with bugs.  :-/)

> Extrapolating this into the future, who knows what other features lay  
> in wait when it comes to ethernet chipset one-upmanship... iscsi crap,  
> RDMA, and so on. All I'm saying is that info is good, even in read- 
> only form. It can take the sleuthing out of wondering what you've got  
> when you put in a new Intel PRO card or are wondering what exactly  
> your Nvidia chip is capable of.

The fine line here would be between exporting administratively useful
information versus exporting meaningless marketing trash.  I think
it'll be hard to avoid having this mechanism (whatever it might be)
become a sewer main.

-- 
James Carlson, Solaris Networking              <james.d.carlson at sun.com>
Sun Microsystems / 35 Network Drive        71.232W   Vox +1 781 442 2084
MS UBUR02-212 / Burlington MA 01803-2757   42.496N   Fax +1 781 442 1677