Testbed Support for GridPP member institutes [mailto:TB-
> [log in to unmask]] On Behalf Of Matt Doidge said:
> However they're both seeing a similar amount of jobs done, so it looks
> like the APEL hours are being scaled down by a factor of 2, We're not
> sure what's causing this
Do you use scaling in PBS, and if so what's the factor? For fal-pygrid you publish a scaled SI00 of 3100 and a HEPSPEC of 10.6, so there seems to be a bit of scaling there but not a factor 2 (10.6*250=2650). For the abbadon cluster you have 12.5 and 3200 which looks more like rounding.
Stephen
|