Login

Weekly SubMIT project team meeting

→ America/New_York
ZOOM

ZOOM
David Walter (Massachusetts Institute of Technology), Mariarosaria D'Alfonso (Massachusetts Institute of Technology)
Description

https://mit.zoom.us/j/95048716850

    • 10:00 → 10:20
      Discussion 20m
      Speakers: David Walter (Massachusetts Institute of Technology), Luca Lavezzo (MIT), Mariarosaria D'Alfonso (Massachusetts Institute of Technology), Matthew Heine (Massachusetts Institute of Technology)

      Review of slides for Tomorrow Users meeting:

      see linked here SubMIT-usersMeeting-Oct6

      URGENT:

      need to contact Paul: we cannot create new Moira groups 

      Operations:

      Some machine didn't come back from the sw installation:

      • submit60 (Luca rebooted), submit 81 (David manual action)
      • Matt will re-organize the alarms and move the slurm normal Drain in the testing channels so that only the important one are there

       

      Review of scratch use:

      https://cleo.mit.edu/issues/6306

      monitoring in please for files by last access time

      possible actions to:

      A) when user leave need to archive the space /scratch

      B) automatic remove of file stale more than 1y

      C) can contact the users with more than 1y

      Initial discussion of security/privacy findings:

      https://cleo.mit.edu/issues/6313

      Initial set of actions:

      A) remove the /ceph/submit/data/prometheus/ (David)

      B) fix permission of the /work/submit/sysadmin/config/submit.mit.edu/slurm/munge.key (David)

      C) contact users to restricts access file with certificates, keys, secrets  (Maria)

      D) add something on permission of those certificates, keys, secrets files in the User Guide (Maria)

      E) Archi related: postgres instances and Ollama (LLM inference)  bound to all interfaces without auth (Maria)

       

      AOB:

      next monday 12 Oct is Columbus day, no meeting