What to do with pledges? 

For CMS:

CPU : 62800 -> 72767 (9967)

Echo: 7686 -> 9394 (1708)

Antares: 24528 -> 29438 (4910)

Another period of low efficiency CMS jobs coinciding with long read-times (for small amounts of data). Many T1s see the same. Job failure rate was again fine. CMS CompOps investigated and there is some issue with remote reads. Remote reads were turned off (not sure how the data is then accessed..?). There is also a lot of discussion over the number of cores being used by the jobs.

As discussed previously on the subject of reading data from Echo using AAA. Reading jobs were timing out because they couldn't get hold of data at RAL. Increasing  the throttling level to allow more connections - IOPS went up higher than we are comfortable with. There is an associated ticket. https://helpdesk.ggus.eu/#ticket/zoom/2837