Did you also increase MMAX_REQ_PER_JOB as well? -- Steven DuChene -----Original Message----- From: Michel Béland [mailto:[email protected]] Sent: Tuesday, November 29, 2011 11:08 AM To: DuChene, StevenX A Cc: [email protected] Subject: Re: [Mauiusers] maui segfaults trying to schedule a job
Steven DuChene wrote: > No, the systems in this cluster only have 4 cores per node. > > BTW, in case this has some bearing on the problem here are the things I have > set in my maui.cfg file: > > > The job the user is submitting requests the following: > > #PBS -l > nodes=39:SeaMicro:diskgrp1+39:SeaMicro:diskgrp2+39:SeaMicro:diskgrp3+39:SeaMicro:diskgrp4+16:SeaMicro:diskgrp6 > That's it, you have five node requests with properties and the maximum is four. In your later message you wrote that you changed MAX_MREQ_PER_JOB from 4 to 8. This is what solved the problem. On our cluster, I bumped MAX_MREQ_PER_JOB to 64, but still I think that anybody with malicious intentions could write a dummy job that would kill Maui all the time. -- Michel Béland, analyste en calcul scientifique [email protected] bureau S-250, pavillon Roger-Gaudry (principal), Université de Montréal téléphone : 514 343-6111 poste 3892 télécopieur : 514 343-2155 Calcul Québec (www.calculquebec.ca) Calcul Canada (calculcanada.org) _______________________________________________ mauiusers mailing list [email protected] http://www.supercluster.org/mailman/listinfo/mauiusers
