*  ATLAS needs to run more single-core analysis jobs
- https://helpdesk.gridpp.rl.ac.uk/Ticket/Display.html?id=397775

* ATLAS hostname env for WN containers
- https://helpdesk.gridpp.rl.ac.uk/Ticket/Display.html?id=398494 

* Oxford Xcache; Done on RAL side
- https://helpdesk.gridpp.rl.ac.uk/Ticket/Display.html?id=397191 

Discrepancy between Vande 100% CPU (for ATLAS)  and  ATLAS Monitoring (cf. Vande * 11.7/10). 
 - to be understood

ATLAS slowly increasing Single-core running jobs (to ~ 3k).

Vector Reads:
   CMS Sam test code can run on gw683 and gw691:
- See at what frequency problem can be triggered;
- In parallel try some lower-level tests