Re: [HTCondor-users] Job Scheduling

[Brian Candler <b.candler@xxxxxxxxx>]

On 03/06/2013 12:57, Muak rules wrote:

I run condor_q on workers node and that queue was empty... All i understood is that the worker will not know if job is executing on its machine......

Workers don't have queues. Workers run startd which in turn executes job(s). The machine reports back to the master what resources (slots) it has, and how many are in use; the match-making process uses this information to work out where to hand out jobs to execute.

If you want to view this information, type "condor_status" on the master node.

> If I were you, I'd start simple. One master node, a number of execute
> nodes, everyone logs into the master node to submit jobs.

will you please explain this who this will happened "everyone logs into the master node to submit jobs."

I'm sorry, but I think you are not taking the trouble to read what I have written, nor what has been written in the plentiful documentation.

Here is my final attempt:

* User X logs into the master node, using ssh
* User X creates a job submission file
* User X types "condor_submit myjob.sub"
* The job goes into the queue on the master node
* The job is matched up with a free worker node
* The job is executed on that worker node
* Any results from the job are copied back to the master node

I cannot make it any simpler than this.

Regards,

Brian.