Re: Who wants SACK? (Re: was My planned work on networking stack)

On Mon, Mar 08, 2004 at 03:32:37PM -0800, Jeffrey Hsu wrote:
>   >> I know that our organization would love to see SACK. Much of the
>   >> high-performance network development that used to be on FreeBSD has
>   >> moved to Linux simply because SACK is essential. You can't run
>   >> trans-oceanic TCP streams of gigabit or more throughput without it.
>   >
>   > Whenever i hear these comments, i am very annoyed at one thing
>   > (which in a smaller scale repeats all over the place):
>   > people are more than happy to spend big money for things like
>   > routers or bandwidth or any kind of "commercial" stuff, but when
>   > it comes to open source it must be free or nothing.
>   >
>   > I hope it is clear to everyone that an investment in the 50K$
>   > range would provide a professional-grade implementation of SACK
>   > for FreeBSD, and this money is in the noise for any organization
>   > that uses trans-oceanic gigabit links.
>   > The fact that nobody seems to care about funding such a work
>   > either means that whatever is available already fits their
> 
> What Luigi says is absolutely correct.  It doesn't take a lot to
> get this done.  I've talked to a number of companies about implementing
> SACK for them and while there was interest, no one wanted to fund
> it all themselves, potentially for the benefit of their competitors.
> I know of two that went and did it themselves for FreeBSD --- one
> of which did it wrong and saw zero benefit from SACK and another
> that did it right, but are keeping it proprietary as an edge.  Given
> that Linux and Windows already have it, these and the multiple past
> efforts collectively seem like an unnecessary duplication of work.
> Perhaps if we could pool enough interest, we can raise enough to
> put this issue to rest once and for all.

An angle to try for might be similar to how SoftUpdates was licensed:
distribute the code for a period of time under a suitably restrictive
license, with a provision that after a certain time (e.g. 12 months)
it becomes BSD-licensed.  This allowed Kirk to get commercial funding
for the SU work while also being able to contribute it to end-users
who don't mind the license terms, and eventually for other commercial
users.

Kris