AI_INFN Technical Meeting

Monday 20 Jan 2025, 16:00 → 17:10 Europe/Rome

Virtual meeting room (zoom): https://l.infn.it/ai-infn-meeting

AI_INFN Technical meeting – Minutes and actions

Date: 2025-01-20

Operations

• NTR

Tracked developments:

 Automation of RKE2 deployments in INFN Cloud

• The image prepared by Gioacchino is now the default in the platform. Snakemake 8 seems unavailable, though. The old version 6 is installed.
• Graphics to be followed with DataCloud.

 Develop monitoring and accounting infrastructure (R. Petrini)

• Created a new storage cluster for practicing with monitoring

 Environment setup (S. Giagu, S. Bordoni, L. Cappelli)

• Issue with GPUs reported by Luca Clissa last week was due to missing information on the platform docs, leading to installing the kernel with the wrong command. The docs have been updated accordingly.

 Offloading tests with virtual kubelets (G. Bianchini, D. Ciangottini)

• Scalability tests with Postgres as meta-engine for JuiceFS failed. The memory footprint of connections to Postgres is very large. Moved back to Redis trying to improve persistence settings.

 Acquisto FPGA

• Diego collected information from Enrico and others and tried to contact an AMD engineer. The main problem is RHEL8.3 is needed to run the board, but OpenStack requires RHEL9.

Status legend

 Active
 Priority
 Problems
 Postponed or Blocked by others
 Completed

16:00 → 16:15 News and setup

Speaker: Lucio Anderlini (Istituto Nazionale di Fisica Nucleare)

16:15 → 16:50 Updates on development activities

16:50 → 17:00 Any other business