[Beowulf] What services do you run on your cluster nodes?

[Greg Lindahl]

On Thu, Sep 25, 2008 at 02:53:14PM -0400, Robert G. Brown wrote:

> The liveness issue is most definitely a problem with xmlsysd/wulfstat,
> because frankly TCP sucks for this specific purpose.  I'd love to have
> what amounts to ping built into the UI, but it is a restricted socket
> command and I don't want to make the UI suid root.

If you have an open stream, pass PING messages and send PONG
replies. That will discover your round-trip time, and you can notice
timeouts.

Or, if you don't have an open socket, open one. That's what the perl
ping module does for non-root processes, it opens a short-lived
socket.

-- greg