This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision Next revision Both sides next revision | ||
cluster:93 [2011/01/08 23:11] hmeij |
cluster:93 [2011/01/09 20:37] hmeij |
||
---|---|---|---|
Line 18: | Line 18: | ||
The purchase of the HP hardware followed a fierce bidding round in which certain design aspects had to met. | The purchase of the HP hardware followed a fierce bidding round in which certain design aspects had to met. | ||
- | * We continually run of disk space for our home directories. | + | * We continually run out of disk space for our home directories. |
* We wanted more nodes, in fewer queues, with a decent memory footprint. | * We wanted more nodes, in fewer queues, with a decent memory footprint. | ||
* All nodes should be on an Infiniband switch. | * All nodes should be on an Infiniband switch. | ||
Line 24: | Line 24: | ||
* Data (NFS) was to be served up via a secondary gigabit ethernet switch, hence not compete with administrative traffic. | * Data (NFS) was to be served up via a secondary gigabit ethernet switch, hence not compete with administrative traffic. | ||
* (With the HP solution we will actually route data (NFS) traffic over the infiniband switch using OFED/MPI, a practice called [[http:// | * (With the HP solution we will actually route data (NFS) traffic over the infiniband switch using OFED/MPI, a practice called [[http:// | ||
- | * Linux or CentOS as operating system. | + | * Linux (Redhat |
* Flexible on scheduler (options: Lava, LSF, Sun Grid Engine) | * Flexible on scheduler (options: Lava, LSF, Sun Grid Engine) | ||
* The disk array, switches and login node should be backed by some form of UPS (not the compute nodes) | * The disk array, switches and login node should be backed by some form of UPS (not the compute nodes) | ||
Line 35: | Line 35: | ||
In short using linpack (More about [[http:// | In short using linpack (More about [[http:// | ||
- | * greentail' | + | * greentail' |
- | * petaltail/ | + | * petaltail/ |
- | * petaltail/ | + | * petaltail/ |
* so the total is 570 gigaflops, but you'd never want to run across both switches simultaneously | * so the total is 570 gigaflops, but you'd never want to run across both switches simultaneously | ||
- | * sharptail' | + | * sharptail' |
* never got quite all the nodes working together, not sure why | * never got quite all the nodes working together, not sure why | ||
===== Home Dirs ===== | ===== Home Dirs ===== | ||
+ | |||
+ | ===== Passwords ===== | ||
+ | |||
+ | The password, shadow and group files of host petaltail were used to populate greentail' | ||
+ | |||
+ | If you change your password, do it on all four hosts (petaltail, swallowtail, | ||
+ | |||
+ | I know, a pain. | ||
+ | |||
===== SSH Keys ===== | ===== SSH Keys ===== | ||
Line 55: | Line 64: | ||
* log into a host, then issue the command '' | * log into a host, then issue the command '' | ||
* supply an empty passphrase (just hit return) | * supply an empty passphrase (just hit return) | ||
- | * then copy the contents of / | + | * then copy the contents of / |
- | * yoiu can have multiple public ssh key entries in this file | + | * you can have multiple public ssh key entries in this file |
- | Note: the software stack on host petaltail/ | + | Note: the software stack on host petaltail/ |
To test if your keys are set up right, simply ssh around the hosts petaltail, swallowtail and greentail. | To test if your keys are set up right, simply ssh around the hosts petaltail, swallowtail and greentail. |