Computer Access

In order to best accommodate all users in an equitable fashion, we've devised the following computer access policy. Please address questions or comments on our policy to StephenFisher.

• VNC: should only be run on kimclust11.
• Mathematica: is only licensed to run on kimclust50.

• kimclust9: file server - not to be used for user jobs.
• kimclust10: file server - not to be used for user jobs.
• kimclust11: file server, NIS server, ftp server, VNC server - not to be used for user jobs.
• kimclust12: file server - not to be used for user jobs.
• kimclust50: Mathematica server - avoid using both CPU for non-Mathematica jobs.

• kimclust[36 - 38]: 64bit workstation - use these machines if your jobs would benefit from 64bit processors.
• kimclust39: 64bit workstation with 8 GB RAM - use this machine if your jobs require large amounts of RAM or would benefit from 64bit processors.
• kimclust[40 - 54]: workstations - use these machines for all other jobs.

We currently have 4 machines set up for 64bit computing (36 to 39). These machines are capable of running 32bit or 64bit applications. So any application compiled on another cluster machine should work fine on these machines. However, it will be run as a 32bit application. To make use of the 64bit processors you need to recompile the jobs using a 64bit compiler, which are the default compilers on these machines. In order to facilitate the use of the 64bit processors /usr/local has been changed on these machines. The 32bit version of /usr/local (the version accessible on all other workstations) is located at /usr/local32. In order to access these 32bit programs on the 64bit machines, you must reference them via /usr/local32/bin/<...>. On these machines /usr/local/bin contains only 64bit applications. Thus applications you're used to finding in /usr/local/bin throughout the cluster are in /usr/local32/bin on the 64bit machines. Programs are only compiled as 64bit applications as they are needed. So if you don't find something in /usr/local/bin that you need, let StephenFisher know.

Currently the best way to run jobs across the cluster is to ConfiguringSSH to allow passwordless logins and then to use ssh to remotely launch jobs. Since this will not balance the loads across the cluster, you can view the machine loads with the "cuptime.pl" or "cup.pl" commands as described in CurrentUsage.

In the following example, the user is logged into kimclust11 and uses ssh to launch the command 'date' on kimclust38. The output from the command will be displayed in the current terminal window.

[fisher@kimclust11]$ ssh kimclust38 date

The 'nice' command can be used to change the priority of a command while it is running. With larger nice levels, fewer the CPU cycles are allocated to the job, thus giving more priority to other jobs with lower nice levels. 19 is the maximum nice level. The syntax of the nice command is as follows.

[fisher@kimclust11]$ nice -n 19 "your command here"

The following example uses the nice command to run 'date' on kimclust38 with a nice level of 19.

[fisher@kimclust11]$ ssh kimclust38 nice -n 19 date