Weekly SubMIT project team meeting

→ America/New_York
ZOOM

ZOOM

David Walter (Massachusetts Institute of Technology), Mariarosaria D'Alfonso (Massachusetts Institute of Technology)
    • 1
      Discussion
      Speakers: David Walter (Massachusetts Institute of Technology), Luca Lavezzo (MIT), Mariarosaria D'Alfonso (Massachusetts Institute of Technology), Matthew Heine (Massachusetts Institute of Technology)

      Next users meeting will be on 6 October. There will be a project team talk, first of the new school year and a report from Florian that is using OpenMPI

      alarms:

      1. certificates xrtood expires in 5 weeks website (last time restarted website) (Maria will fix)
      2. archi was off, restarted last saturday (restarted on saturday)
      3. some outliers
          1. Details: backup_incremental_age_hours = 37.0; lower limit = 0; upper limit = 36  (node=submit07.mit.edu; metric=
          2. backup_incremental_age_hours)
      4.  Power in Building 24 exceeded "Near Overload" (thursday 10th)

       

      tickets: no major to follow up 

      login nodes well behaving

      1. Slurm: updated version update from David following security email from OSG
        1. (updated all the nodes, cleanup misconfiguration, demaon on submit30)
      2. David IS&T contacted us to close one a2rchi-graffana port
        1. https://cleo.mit.edu/issues/6275
        2. immediate: restrict the port to MIT network(David):
        3. longer time scale (Maria): Put all these ports (both users and admins) beyond the MIT touchstone (as backup use the ssh proxy or VPN)
      3. Jupiterhub (Matt) configuration backup on git https://github.com/mit-submit/submit-admin/pull/5
        1. (it also contains the latest update of Mathematica on all nodes)