[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [HTCondor-users] Help on FLOCK and CCB

Thanks for the input.

I was thinking if it is at all possible to offer the user a virtual machine like what Amazon does by using the idle desktop/laptops.

The user will get a virtual machine, which have some computation capacity, in addition it ( the virtual machine ) can send jobs to pool A or B of idle desktops/laptops.  Both the virtual machine and pools will be created from idle desktop/laptops.

Do you think this is kind of infrastructure is already is in place?

This may be off topic for this list , but still any suggestion/pointer how to proceed is most welcome.

Batsayan Das
Tata Consultancy Services
Mailto: batsayan.das@xxxxxxx
Experience certainty.        IT Services
                       Business Solutions

From: Ben Cotton <ben.cotton@xxxxxxxxxxxxxxxxxx>
To: HTCondor-Users Mail List <htcondor-users@xxxxxxxxxxx>
Date: 03/06/2014 07:07 PM
Subject: Re: [HTCondor-users] Help on FLOCK and CCB
Sent by: "HTCondor-users" <htcondor-users-bounces@xxxxxxxxxxx>

On Thu, Mar 6, 2014 at 5:38 AM, Batsayan Das <batsayan.das@xxxxxxx> wrote:

> Is there and simple guide on  how  " we had flocking set up with several
> other institutions" ? The manuals are too exhaustive!!

The basics were to set FLOCK_TO on the schedds to include the central
managers of the other pools and to set FLOCK_FROM on the central
managers and execute nodes to include the schedulers of the other

In practice, we had to tweak some of our security settings in order to
work with the configuration at one of the other sites, but since
you're (probably) similarly-configured across the two pools, you
probably won't have to worry about that.

> How can I test the flocking setup configuration between pool A and B, before
> actual deployment?

You can't, really. Setting FLOCK_FROM won't do much if nothings
flocking *to* a pool, so you can do that first. Then you can set up a
test schedd that has FLOCK_TO set. Set your test jobs requirements
such that nothing in pool A matches and machines in pool B match. If
your job runs, flocking is successfully configured.


Ben Cotton
main: 888.292.5320

Cycle Computing
Leader in Utility HPC Software

twitter: @cyclecomputing
HTCondor-users mailing list
To unsubscribe, send a message to htcondor-users-request@xxxxxxxxxxx with a
subject: Unsubscribe
You can also unsubscribe by visiting

The archives can be found at:

Notice: The information contained in this e-mail
message and/or attachments to it may contain
confidential or privileged information. If you are
not the intended recipient, any dissemination, use,
review, distribution, printing or copying of the
information contained in this e-mail message
and/or attachments to it are strictly prohibited. If
you have received this communication in error,
please notify us by reply e-mail or telephone and
immediately and permanently delete the message
and any attachments. Thank you