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

Re: [Condor-users] Getting cpuinfo in standard universe jobs

There is not detailed information in the SlotAd until it is
checkpointed, even then it is limited.

If you're looking for matching requirements, there are benchmarks which
you can use:


To see the slog of information presented by your slots you can type:

condor_status -long <- gives you everything
condor_status -long slotXYZ <- gives you detailed info about a slot.

If your request goes beyond *this you may want to append to:

Hope this helps,

On Thu, 2011-08-11 at 15:13 -0400, Ka-Hei Law wrote:
> Dear all,
> How can I get the CPU information (model and speed) on the nodes where
> my standard universe jobs are executed? They are x86-64 Linux nodes.
> I tried reading "/proc/cpuinfo" using stdio functions in C, but the
> "file" seems to be empty for standard universe jobs. Perhaps reading
> the proc fs isn't supported in the standard universe.
> I found that the CPUID opcode (http://en.wikipedia.org/wiki/CPUID) may
> give me what I need. Do you think it will work in my case? If yes, do
> you think it's the way to go? Or would you suggest other alternatives?
> Thanks,
> Ka-Hei Law
> _______________________________________________
> Condor-users mailing list
> To unsubscribe, send a message to condor-users-request@xxxxxxxxxxx with a
> subject: Unsubscribe
> You can also unsubscribe by visiting
> https://lists.cs.wisc.edu/mailman/listinfo/condor-users
> The archives can be found at:
> https://lists.cs.wisc.edu/archive/condor-users/