● Outstanding tickets

• GGUS #146538 Glasgow deletion errors. Rod has the important files he wanted off the bad disk. Sam is draining the disk. Is there a tool to say which are the unique files? Sam will discuss with Rod, CC with atlas-support-cloud-uk@cern.ch.
• GGUS #146525 Sheffield. James will follow up on TB-SUPPORT@JISCMAIL.AC.UK.
• GGUS #146523 Manchester. Two issues: usual timeouts and file existence check failed. Wait for Alessandra to check.
• GGUS #146374 Sheffield. No news.
• GGUS #146280 Lancaster. Matt restarted and it looks better now. Seeing DAVS transfers, but would be surprised if this is production.
• GGUS #146159 Glasgow. nothing to add
• GGUS #145688 Manchester. no update from Alessandra.
• GGUS #145510 RAL now have new WNs with SSD. Seem to be performing much better with IO. Maybe can close this ticket soon.
• GGUS #144759 Glasgow. no change
• GGUS #142329 Sussex. Peter applied AGIS updates, but they didn't help. Last email from Patrick to Peter on 13 April. Global setting larger memory fixes jobs, but can't get this set for ATLAS jobs.

● CPU

• RAL new machines installed, giving a bump in running slots.
• A few planned interventions at some T2s.
• Gareth: HammerCloud excluded Glasgow due to some missing files. Need to understand.

● Glasgow Ceph storage

• Dimitrios and Sam discussed putting new endpoint online. Will try to bring up this week.
• Sam thought the AGIS changes looked fine.
• Naming scheme for the servers: c=cache, s=server; .beowulf.cluster=internal interface, .gla.scotgrid.ac.uk=external interface, but on the same machines.

● Grand Unified queues

No changes. Everything should be done now.

● News round-table

Dan: NTR
Gareth: NTR
James; NTR
Matt: NTR
Sam: NTR
Tim: NTR
Vip: [earlier in the meeting] Discussed making Oxford storageless. Will talk with Pete next week to decide when can go ahead. ATLAS has a well-defined procedure.