Installing Scyld: some questions

[Bruno Barberi Gnecco]

Jag wrote:

> You can't telnet or ftp to them because a) you shouldn't have to, and b)
> there are no binaries on the slave nodes, so there's no way for them to
> run the daemons, or the shells.

	Isn't the lack of binaries a drawback? It would be nice for us to
have binaries, and specially data, in the local disks. The reason is simple:
we will deal with very large databases, and it's kind of stupid (not to
mention slow) to read them, copy over the network, save locally, etc. 

> > d) I intend to run X on the slaves. Is it a problem?
> Hrm.. is there a particular reason you want to run X on the slave nodes?
> I'm not sure if its possible or not, but if it is, it will be a /LOT/ of
> work to setup.

	Yes, there is. The primary goal of this cluster is to control a
CAVE system (each machine will be responsible for a projector).

> Running X on the slaves doesn't make a whole lot of sense to me.  With
> the beowulf setup, you want to just log into the head node and not have
> to worry about logging into the slave nodes.  This is even more
> prevelent with the Scyld setup, where the slave nodes don't have any
> binaries on them, instead you run processes on them by using BProc to
> propagate the process from the head node to the slave nodes.

	We need to run X because we are interested in graphic output.
We'll be primarily using OpenGL, which (AFAIK) can only be used under X,
but other libraries (Performer, OpenInventor, GGI, even things like GTK)
will also be used. X also is sure to provide drivers for our video boards.
I don't need (and don't want) people logging in the slaves. My idea was to
run X by a dummy user.

	Would you advise against Scyld in this case? I like it, and it
fits very well for our purposes. Would it be too difficult to install
X in the hard disk and run in remotely?

> > e) Is there a way to bypass the requirement of 2 net boards on the
> > master? I've been fooling it by using an onboard ethernet (that will
> > not be used) as eth0, and disabling it by ifconfig. But eth1 only allows
> > access to the slave nodes. The reason to do it is lack of ports in our
> > switches.
> I really wouldn't advise that.  I'd like to point you to
> http://bproc.sourceforge.net/bproc_3.html#SEC13, the Security section in
> particular.  Scyld is based on BProc, and this section gives a very
> brief overview of why you would never want to use BProc on anything
> except its own private network.
> Compared to the cost of the machines in your cluster, a dedicated switch
> for your cluster is really inexpensive.  I highly recommend you get a
> dedicated switch for your cluster.  This is for security as well as for
> keeping things like broadcasts from slowing down your cluster.  The way
> Scyld is designed to work is to have eth0 on the head node connect to
> the outside world (or private company network, etc), and to have eth1
> connect to a switch that has all of your slave nodes on it, and no other
> machines.

	There's a switch used exclusively for the cluster. The problem
is with the rest of the network; we need one extra connectors which are
not currently available. Another switch will eventually arrive, but I'd
like to be able to run the cluster and the rest of the network meanwhile.
Currently I can telnet to the master, but not access the rest of the 
network from it.

	Thanks a lot for your reply, 

-- 
Bruno Barberi Gnecco <brunobg at geocities.com>
http://www.geocities.com/RodeoDrive/1980/
Quoth the Raven, "Nevermore". - Poe