 |
 |
Hi Jean-michel, we have the same problem at DESY-HH: 5 CREAM-CEs are serving 1 batch server. In order to avoid double counting we set on 1 CE for yaim (siteinfo.def): CE_PHYSCPU=_the_real_number_ CE_LOGCPU=_the_real_number_ and on all others CEs: CE_PHYSCPU=0 CE_LOGCPU=0 Cheers Andreas On Wed, 12 Feb 2014, Jean-Michel Barbet wrote: > Hello all, > > We are running two CREAM-CE submitting jobs to the same (separate) > Torque batch server. I splitted the number of slots in the cluster > on the 2 CEs to avoid double-counting the resources. > > Now as I prepare to replace one of the EMI2 CREAM by a new EMI3 CREAM, > I started to read about glite-CLUSTER and I am wondering if it is > a good idea to use it. It is supposed to fit with our situation but > is it still maintained, widely used, and is it worth it if declaring > half of the resources on each CE does the trick ? > > Thanks > > JM > > -- > ------------------------------------------------------------------------ > Jean-michel BARBET | Tel: +33 (0)2 51 85 84 86 > Laboratoire SUBATECH Nantes France | Fax: +33 (0)2 51 85 84 79 > CNRS-IN2P3/Ecole des Mines/Universite | E-Mail: [log in to unmask] > ------------------------------------------------------------------------ > > # Andreas Gellrich # DESY IT / Grid Computing # 2b/317, Notkestr. 85, D-22607 Hamburg, +49 40 8998 2732