Difference between revisions of "Development and Testing"
m (Lthibert moved page Test Nodes to Test Servers) |
|||
Line 18: | Line 18: | ||
* 64 cores | * 64 cores | ||
* 256 GB RAM | * 256 GB RAM | ||
+ | ==HiPerGator 2.0== | ||
+ | Instructions for accessing HiPerGator 2.0 development nodes will be forthcoming soon. | ||
+ | |||
+ | The development node service will be handled via the SLURM scheduler and direct SSH access to the development nodes will not be available. This will allow Research Computing resources to be moved around as needed in order to facilitate development more thoroughly. |
Revision as of 18:51, 2 May 2016
Overview
The test servers are available for software development and testing. If you need to develop code (i.e., the standard edit, build, test cycle) or test your workflows and scripts before submitting batch jobs, you should use these machines. The software environment on the test servers is kept consistent with that of the compute servers so you can run jobs and get an accurate idea of what resources are used.
Please remember that you are not allowed to run user applications on the login servers. Interactive work of any kind must be performed on a test machine. We ask that you limit the runtime of jobs on the test servers to thirty minutes or less. Note that violation of this policy may result in suspension of your UFRC account.
Access
Connect to the cluster (gator.rc.ufl.edu) and use the ssh command to access either of the test servers.
ssh dev1
or
ssh dev2
Test Queue
There is a test queue you can use to test your job submission scripts. Please visit the Queues page for more information.
Technical specifications
Both dev1 and dev2 have the same technical specifications, as follows:
- Opteron 6378
- 2.4 GHz
- 64 cores
- 256 GB RAM
HiPerGator 2.0
Instructions for accessing HiPerGator 2.0 development nodes will be forthcoming soon.
The development node service will be handled via the SLURM scheduler and direct SSH access to the development nodes will not be available. This will allow Research Computing resources to be moved around as needed in order to facilitate development more thoroughly.