Page tree

Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

...

  • There are currently two compute nodes, each with 64 cores and 256GB of memory set aside for interactive use,
  • qrsh wil log you on one of them, to use one CPU (core or slot) and 8GB of mem,
    • to increase these values use qrsh -pe mthread N, where N is between 2 and 32, to use 2 to 32 slots or 16 to 256 GB of memory.
  • The limit of CPU you can use is  12h per requested CPU (core or slot), while the limit of elapsed time is set to 24 hour.
  • A single user can't use more than 32 1 job and 16 slots in the interactive queue and can't keep it for longer than 24 hour.
    (lightbulb) By default, the variable NSLOTS is not set by qrsh. If you want/need it to be set to the value of N passed to -pe mthread N, use either
    • qrsh -pe mthread N -pty y bash
      or
    • qrsh -pe mthread N -pty y csh
    depending on which shell you want to launch (more details available here). 
    (warning) I you forgot the "-pty y" you won't get a prompt, simply type exit.
  • Since we have not installed X11 on the compute nodes, qsh will always fail - if you need X on the interactive nodes, contact us.
  • (warning) Since Hydra is a shared resource, do not "waste" interactive slots by keeping your qrsh session idle.

...