JISCMail - LCG-ROLLOUT Archives

Hi Stephen, Jeff, David, all

We are using the same approach to scale the CPU in the ARC-CE that Stephen commented on. As it happens with other systems such as Torque, the cputime and walltime are multiplied by the cputmult depending on the kind of CPU.

The problem, in fact, is comparing the value of the "wallclock" that in account-egi.next.egi.eu, if I'm not wrong, means walltime*cores. On the other hand, the wallclock work is walltime*cores*benchmark-value-site. My problem is that the wallclock from EGI accounting and the wallclock from our local accounting is not the same (the cputime yes, it is!) and we are directly taking the value from WallDuration in the usagerecordCAR files and multiplying it by the number of cores.

I'll continue to investigate what I'm doing wrong in our local accounting.

Thank you very much.

Cheers,

Carles

On Mon, 3 Feb 2020 at 14:40, Stephen Jones <[log in to unmask]> wrote:

Hi Jeff,

On 03/02/2020 13:28, Jeff Templon wrote:
> We have our own script that knows what the cpu power is for each WN,
> this populates a local job database, and periodically another script
> pushes recent records on to the EGI accounting database.
>

Yes - thanks; VAC likewise uses the raw times and the specific slot
power of the actual node, as you do. It's right.

> The schema makes it possible to Do The Right Thing, if desired.

The spirit is willing but the flesh is weak. As much as I may wish to Do
The Right Thing, the difficulties of change are daunting. But perhaps we
should work on it ...

Cheers,

Ste

--
Steve Jones [log in to unmask]
Grid System Administrator office: 220
High Energy Physics Division tel (int): 43396
Oliver Lodge Laboratory tel (ext): +44 (0)151 794 3396
University of Liverpool http://www.liv.ac.uk/physics/hep/

########################################################################

To unsubscribe from the LCG-ROLLOUT list, click the following link:
https://www.jiscmail.ac.uk/cgi-bin/webadmin?SUBED1=LCG-ROLLOUT&A=1

Carles Acosta i Silva

PIC (Port d'Informació Científica)

Campus UAB, Edifici D

E-08193 Bellaterra, Barcelona

Tel: +34 93 581 33 08

Fax: +34 93 581 41 10

http://www.pic.es

Avís - Aviso - Legal Notice: http://www.ifae.es/legal.html