skip to content
 

Elvis is a cluster of 20 dual-processor quad core Intel based servers. Each machine has eight cores and 16Gb of RAM. They all run Linux.

Elvis can only be accessed by sshing into the head node, whose external name is elvis.ch.private.cam.ac.uk. All work is done from there; there is normally no need to log into compute nodes. Elvis uses the local Admitto service, so you log in with the same password as on the workstations or VPN.

Homespace is on a disk array attached to the head node. IT IS NOT BACKED UP. /home is shared to all nodes on the cluster's internal network, so your job sees the same home directory wherever it is on the machine. It's important to remember that from a compute job's point of view accessing this directory is extremely slow, especially if all the nodes are trying at once. Compute jobs should always write data to a local disk if possible, and copy it back to /home at the end.

Each node also has a local /scratch filesystem on which the queueing system will create you a directory when you use the node. These filesystems are about 200Gb in size with no quota restriction and are the most appropriate place for your jobs to write temporary files during a run. They are local to each node and so considerably faster than the NFS-mounted /home. Please clean up files on /scratch when you are done with them; see the queueing documentation for how to find out which node's /scratch to look at. All of the node /scratch directories are accessible under /nodescratch on the head node. The system uses an automounter so the directories only appear when you try to access them. For example to see the /scratch from node node007 you need to type something like 'ls /nodescratch/node007'.

The following software is installed: Intel Fortran, Intel C, Intel Math Kernel Library, Portland Group Fortran and C compilers, GNU compilers, FFTW library, MPI-CH, OpenMPI. The head node also has other software, including popular editors, as it is intended for interactive work. If there is a package missing from the head node that you would like to use then please ask; it will probably be possible to install it provided it is a sensible size.

Like most local clusters elvis has the modules environment to allow you to switch between different compilers and libraries. The default environment is set up with all the available 64-bit compilers and OpenMPI. If you need to change this then use the module avail command to see what the other options are, and edit the version you want into your ~/.bashrc file.

All compute jobs should be run through the queueing system as users cannot log directly into the nodes. The queueing system will run each job on a set of free compute nodes, copying the output back to a user-specified file at the end of the job. The queueing system is Torque/Maui. Read the generic instructions for instructions on how to use Torque if you need a guide. There are only two queues, short_eth and long_eth and they both have a limit of 24 hours. To run parallel jobs you will need to use the appropriate job launcher; see Elvis's parallel documentation for details.

Can't find what you're looking for?

Then you might find our A-Z site index useful. Or, you can search the site using the box at the top of the page, or by clicking here.