Computational Cluster Programs
Computing on the CNSI Cluster
The preferred way to access the CNSI Cluster is through the UCLA Grid Portal at http://grid.ucla.edu. The grid portal makes the CNSI Cluster accessible from any web browser. You can submit batch jobs, run interactive GUI applications and get an xterm from the UCLA Grid Portal. If you are going to use the CNSI Cluster from the UCLA Grid Portal, to use batch or interactive services (except for xterm) you will not need to know the information presented here.
Role of the Head Node
Use the CNSI head node for logging into the CNSI Cluster.
You may do the following when logged onto the CNSI Cluster head node:
- File management
- Editing
- Compile programs (from source code)
Do not Compute on the Head Node
Do not run applications on the head node. The load average on the head node is continously monitored and any user processes that is contributing significantly to the load average is terminated without notice.
Run Interactive Programs on the Interactive Nodes
There are 2 interactive nodes that are provided for software development, debugging and the running of interactive applications. They are named n3 and n4. and can be accessed from the head node using the commands:
ssh n3and
ssh n4
Do debug your programs and run interactive applications on the interactive nodes. However note that, any program that requires more than 1 hour to complete and which does not require considerable human interaction must be submitted to a batch job queue.
Batch Jobs
Most of the nodes on the CNSI Cluster are dedicated to running batch jobs. All non-interactive programs that require more than 1 hour to complete must be submitted as batch jobs.
The CNSI Cluster has 46 compute nodes named n5, n6, ... n50. You can run at most a 92 processor job as each node has 2 CPUs and 2 GB of memory per processor.
There are two high-memory comput nodes. You can request up to 6 GB per processor for a high-memory job. High-memory jobs are limited to 4 processors.
home
Disability Resources