● Outstanding tickets
- GGUS# 145614 and #145931 (Manchester): look like same issue, so could be combined
- GGUS #145688 (Manchester): no progress
- GGUS #145971 (Manchester) seems to be an SKA ticket, maybe added "Concerned VO: atlas" by accident
- GGUS #145510 (RAL): stage-out issues similar to other sites. stage-in: see a broad range of rates into WN. Could be due to lots of jobs running on WNs and blocking HDD. SSD on new WNs might alleviate. James will test on a single node.
- GGUS #144759 (Glasgow): no progress
● CPU
- Manchester has ramped down today. No ideas.
- RHUL stopped running Monday-Tuesday: Vip thinks one of the pool nodes had problems. Now fixed.
- Cambridge not running since Friday. Peter said it wasn't receiving Pilots, so probably ATLAS problem. We no longer have local support, so Matt suggested if it is a site issue, we could email site contact.
- Durham is wobbly. It should be more stable now fully DPM-DOMEd.
- ECDF-RDF is going away.
● CentOS7 - Sussex
No news
● Glasgow Ceph storage
Now running Nautilus with newly recompiled XRootD 4.11.2. Sam will configure XRootD in the next couple of days.
Will start a new pool with final EC setup, and move test data to new pool.
● Grand Unified queues
Peter: Nicolo reported on Monday that they will grand-unify UK next week. James will ping Nicolo.
● News round-table
- Elena: leaving ATLAS Cloud Support to work more for LZ. Need someone to take over ATLAS report to GridPP Ops meeting.
- James: NETR
- Matt: some disk servers at risk, but hopefully OK.
- Peter: NETR
- Sam: Discussion in storage meeting about Coronavirus. Mostly people can work from home, but VPN infrastructure may be overloaded.
- Stewart: NETR
- Tim: NETR
- Vip: NETR
There are minutes attached to this event.
Show them.