Weekly SubMIT project team meeting

Monday 26 Oct 2026, 10:00 → 11:00 America/New_York

ZOOM

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

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

10:00 → 10:20 Discussion

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

T3-slurm-firstWeek.png

Paul:

• Moira groups: https://cleo.mit.edu/issues/6322 and https://cleo.mit.edu/issues/6339
• new DNS request  https://cleo.mit.edu/issues/6336

 

certificates roots depth (David):

       requested and update now with alias so that goes over submit

       TO DO: update the document for next time and Paul need to update the DNS

Hardware failure (David): 

• submit75.cern.ch: needed to reboot
• ceph : one disk failed, restarted

 

Linux PHP vulnerability, needed update

Dima requested submit80 for IO test:

• long time to drain it, i.e. done on Friday only on Sunday was free; a long queue of slurm jobs piled up

 

New nodes from T3: 

already in use see the ganglia report from the 1st week attached in the indico agenda 

Maria added to dashboard http://submit08.mit.edu/~mariadlf/SUBMIT/submitnodes-dashboard.html

mainly those in green are worth:

1. 1. other nodes are alive but not connect on slurs and run old Tier3 stuff, slums ...
   2. those in brown are old centos7 can be removed.

 

Possible future re-organization:

1. 1.         take the extra 1080 GPU ( extra 10ish are around) and put together with submit60 to 73. Since no enough power on the submit racks,  can possibly 95,96 since are old and 1gb can go in the Tier3 room
   2.         include disks 1TB vs 6TB as storage, maybe for some backup (i.e. old users)
   3. more servers from Tier2 will be available O(40), they are supposed to be newer