On Thu, Oct 21, 2004 at 01:05:13PM +0200, bert hubert wrote:
> Is the CLUSTERIP target going anywhere after the (needlessly harsh) rebukes
> posted here?
Yes, I think so. I'm in the process of investigating why I didn't use
seq_file at the time I implemented it (some 1.5 years ago, IIRC).
Unfortunately I don't really remember all the issues involved :( If I'm
not mistaken, I even posted some questions in this regard to lkml.
> I note with glee that CLUSTERIP implements (and improves) the evil ideas of
> http://lartc.org/autoloadbalance.php3
I didn't know about that page, but yes, indeed. I first was informed
about this approach by Fabio Olive Leite, who was one of my colleagues
at Conectiva (where I was 2001). He presented this approach at the
Linux Kongress 2002:
http://www.linux-kongress.org/2002/papers/lk2002-leite.html
Later SuSE approached me if I was interested in implementing that idea,
and that's how CLUSTERIP happened. If I'm not mistaken SuSE is already
shipping this (at least in some beta version?) - I don't really know but
maybe lmb can shed some light on this issue.
> And yes, I've received hate mail over this from switch engineers :-)
Why is that? They have to deal with multicast traffic, too... and I
don't really see how this is any different.
> Good luck!
Thanks ;)
--
- Harald Welte <laforge@xxxxxxxxxxxxx> http://www.netfilter.org/
============================================================================
"Fragmentation is like classful addressing -- an interesting early
architectural error that shows how much experimentation was going
on while IP was being designed." -- Paul Vixie
signature.asc
Description: Digital signature
|