JIRIAF Meeting Apr. 4 2024

From epsciwiki
Revision as of 17:47, 4 April 2024 by Gurjyan (talk | contribs) (Created page with " === Connection Info: === <div class="toccolours mw-collapsible mw-collapsed"> You can connect using [https://jlab-org.zoomgov.com/j/1601266529?pwd=ZkZKL0tjeWFpbmxDeWZob0Vmbz...")
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search


Connection Info:

You can connect using the following link (Meeting ID: 160 126 6529). (Click "Expand" to the right for details -->):

One tap mobile: US: +16692545252,,1608518798# or +16468287666,,1608518798#
Meeting URL: https://jlab-org.zoomgov.com/j/1601266529?pwd=ZkZKL0tjeWFpbmxDeWZob0VmbzNOUT09&from=addon
Meeting ID: 160 126 6529
Passcode: 292304

Join by Telephone
For higher quality, dial a number based on your current location.
Dial:
US: +1 669 254 5252 or +1 646 828 7666 or +1 551 285 1373 or +1 669 216 1590 or 833 568 8864 (Toll Free)
Meeting ID: 160 126 6529

International numbers
Join by SIP
1616903130@sip.zoomgov.com
Join by H.323
161.199.138.10 (US West)
161.199.136.10 (US East)
Meeting ID: 160 851 8798
Passcode: 292304


Agenda:

  • Announcements
  • JFE
    • Code base
      • Current status (demo)
        • CIlogon authentication, database, etc.
      • Deployment on jiriaf2301
        • Job request queue
        • List of pending and active JRMs
      • Public-facing website
        • Grafana deployment metrics visualization
        • K8S visualization?
  • JRM
    • Tables and their physical location.
    • Metric server
    • Horizontal autoscaling support
  • JCS and JMS
    • No proactivity support
      • Do we need access SWIF2 DB?
      • Resource Acquisition
        • Time, cpu, and memory requests to steer deployment: SLURM -> JRM
        • Check the job request queue and decide if we need to run more JRMs
      • Remove JRM if the job is completed.
    • Fabric deployment and testing the proactive resource acquisition and utilization.
      • JRMs with larger wall time as k8s nodes within the JIRAF k8s cluster
  • ML and digital twin
    • ML model trained on the historical data to help with the resource acquisition
    • Bayesian network-based agent model for a site/workflow.
      • Queueing theory-based mathematical model for predicting wait time for a streaming event in a queue before processing.
  • Documentation and code
    • Centralize the code base in Github.
  • Demo and presentations for the joint ALS-JIRIAF meeting
  • Start preparing a paper for NIM (e.g.)
  • Start working on CHEP24 abstract and presentation
* AOT

Useful References



Minutes: