> > > It does not exist today AFAIK. The hope of such a solution will prevent > > the inclusion of TOE technology that exists today? > > > TOE has a solid track record of being a point-in-time solution with > decreased features and increased maintenance headaches. > > That's what prevents its inclusion. > > Jeff > I think to a large degree what is happening here is some arguing at cross purposes.
I myself, would prefer that everything is done in software. However I respect the rights that people have to implement something in hardware/firmware if they have something they need to get done that they cannot achieve in software easily or cost effectively (e.g. buying a $20K server instead of a $500 card). If a vendor wants to sell a solution then they can. If their code is not accepted into the kernel they are free to offer the code themselves (that is what being free is about). Let the user decide. I for one would rather have a device with an out of kernel driver based on source code rather than a device with no source code support for high performance (e.g. Nvidia binary drivers). What would be even better in my opinion is if the TOE cards were running on an open firmware so that they don't just become a point in time solution. If Chelsio's code does work (and doesn't cause problems) then over time it may well become part of the kernel (or may not). As always though I think the debate is healthy and let the best ideas win rather than the best dollars... - To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html
