Re: [Condor-users] hawkeye on dual-processor nodes

[Junjun Mao <jmao@xxxxxxxxxxxxxxxxx>]

Hi Nick,

You explained it very well, and I could get rid of the extra node by 
setting NUM_CPUS = 2. The problem is these vms are changing unclaimed 
to owner too often.

I am running collector daemon on central manager only and I didn't 
install hawkeye on the central manager. Can you be more specific on 
"start a second collector, and point all of the hawkeye startds at it."?

My understanding is to run two Collectors on the central manager, but 
how do I ask execute nodes to report to one Collector daemon, and how 
will this help?

Junjun

> In general, you want to have your hawkeye startds reporting to their
> own separate collector.  This prevents the hawkeye startd ad from
> clobbering the condor machine ad.  In your case, because you're
> running on an MP machine, the hawkeye configuration has a default
> "NUM_CPUS = 1", so that's why you see the "node74" and the
> "vmx@node74" side by side.  On a single CPU machine, you'd only see
> the "node74" ads, but they'd sometimes be from the condor startd,
> and, at other times, from the hawkeye startd -- this is most
> certainly not what you want.
>
> So, bottom line, start a second collector, and point all of the
> hawkeye startds at it.