UVic Computing  |  UVic Home
  

The Llaima Cluster

Llaima is a Linux Cluster for use by the Astronomy Department. It's powered by 38 AMD Opteron   dual-core compute nodes and 19 quad-core compute nodes running at 2 Ghz per CPU. The cluster is installed with Scientific Linux 4.2 based on the 2.6 series kernel.

Cluster Storage

The cluster's head node is configured to attach to the Research SAN with two MPIO load balanced HBAs. The SAN volumes are currently being presented to the compute nodes via NFS. All cluster user's home directories are mounted on the SAN.

Cluster Scheduling and Management

Llaima uses two open-source software packages: the Portable Batch System, and the Maui Scheduler. An additional package, the Extreme Cluster Administration Toolkit (xCAT), aids in the management of software on the blades.

PBS manages Llaima's job queues, tracks jobs, and retains information on resources available on each node and the node's availability.

The Maui scheduler coordinates when and where jobs are run. It examines jobs in the various queues, applies various factors and algorithms to determine their priority, and requests for PBS to dispatch the jobs accordingly.

xCAT, to manage the nodes within the cluster.

MPI

Llaima is configured with Message Passing Interface (MPI) libraries (LAM and MPICH) to allow for parallel distribution of jobs across the cluster.