netdev
[Top] [All Lists]

Re: [PATCH 2.6] iptables CLUSTERIP target

To: Harald Welte <laforge@xxxxxxxxxxxxx>, bert hubert <ahu@xxxxxxx>, Christoph Hellwig <hch@xxxxxxxxxxxxx>, Linux Netdev List <netdev@xxxxxxxxxxx>
Subject: Re: [PATCH 2.6] iptables CLUSTERIP target
From: Lars Marowsky-Bree <lmb@xxxxxxx>
Date: Thu, 21 Oct 2004 15:33:46 +0200
In-reply-to: <20041021130327.GD3551@xxxxxxxxxxxxxxxxxxxxxxx>
References: <20041020223828.GP19899@xxxxxxxxxxxxxxxxxxxxxxx> <20041021075530.GA1278@xxxxxxxxxxxxx> <20041021091229.GA3551@xxxxxxxxxxxxxxxxxxxxxxx> <20041021110513.GA21579@xxxxxxxxxxxxxxx> <20041021130327.GD3551@xxxxxxxxxxxxxxxxxxxxxxx>
Sender: netdev-bounce@xxxxxxxxxxx
User-agent: Mutt/1.5.6i
On 2004-10-21T15:03:27, Harald Welte <laforge@xxxxxxxxxxxxx> wrote:

> > 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.

Yeah, I learned about it from Fabio, thought it would be a cool idea,
and eventually we sponsored Harald to make it happen. It's shipping in
SLES9, and we're adding full support for it in the 2.0 heartbeat cluster
resource manager. 

It's meant to complement the LVS / mod_backhand based approaches.

If the proc file IO for communicating with the module goes away in
favour of a commandline based add/list/remove/etc interface, that would
just help to tidy up our code, so it's OK with me.

> > 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.

Yeah, but with this they get a whole lot more ;-)


Sincerely,
    Lars Marowsky-Brée <lmb@xxxxxxx>

-- 
High Availability & Clustering
SUSE Labs, Research and Development
SUSE LINUX AG - A Novell company


<Prev in Thread] Current Thread [Next in Thread>