allegro Migration In may 2015, the upgraded allegro cluster is set online. The list of new features includes * OS Upgrade Debian Jessie * new scheduler ( ...
Cluster Queue Management The cluster queue is managed by the Slurm Workload Manager. The system knows the following client commands (besides others): sbatch : Su...
Cook Book: Job Arrays Job arrays allow you to create many jobs from one qsub command. You generate them by calling qsub with the t parameter to which you can pas...
Selecting Nodes Classes Node Features Nodes can be selected by adding requirements to your job scripts. Such requirements might be a number of processors per nod...
Selecting Nodes Classes Node Properties Nodes can be selected by adding requirements to your job scripts. Such requirements might be a number of processors per n...
Cook Book: Selecting Queues Available Partitions You can get a list of available partitions by typing scontrol show partitions. Then you can select the partition...
Cook Book: Selecting Queues Using the default queue batch Jobs of a length up to 2 hours can be added to the batch queue. No special action is required, but you ...
Stdout / Stderr Munging Unix applications use the standard output and standard error stream for presenting messages to the user and logging. In the batch processi...
Stdout / Stderr Munging Unix applications use the standard output and standard error stream for presenting messages to the user and logging. In the batch processi...
For the impatient 1 login to adagio or allegro 1 copy your data, if necessary (allegro home) 1 submit job 1 check job $ ssh allegro # or ssh adagio ...
The allegro cluster consists of different node types interconnected with InfiniBand. See the following list for details. NodeName Sockets:Threads:Cores Logi...
Infiniband Every compute node and also the storage nodes are equipped with Mellanox MT26428 QuadDataRate InfiniBand controllers guaranteeing high bandwidth and l...
MPI In a few cases users experienced random like application crashes. In these cases usage of the extra parameter " mca orte_base_help_aggregate 0 verbose" for...
Compute und Remote Login Server Der Rechnerbetrieb stellt seinen Benutzern Rechenleistung in Form von Compute Servern zur Verfügung. Diese Server sind auf dieser...
Kurzzusammenfassung Inhaltsverzeichnis IT Dienste Generell teilen sich die IT Dienste am Fachbereich in mehrere Gruppen auf: * ZEDAT Dienste vormals am Fac...
SlurmNodeStatusTable Clusterknoten Status boot Anleitung Befehle sind auf allegro oder allegro ctrl01 abzusetzen. Einfach nur Rebooten (Nach Updates etc.) Der ...