RAL Tier1 weekly operations castor 05/08/2016
Contents
Minutes from the previous meeting
Operation problems
gdss678 failed went out production
Operation news
All 9 new Dell tape-backed disk servers have been deployed into CASTOR
Long-term projects
Good progress has been made with the CASTOR 2.1.15 upgrade. The gridFTP transfer problem was fixed and a configuration check bug was isolated. Stress, functional, xroot tests will be scheduled
George will liaise with Bruno so that he can understand better the technical requirements of the SL7 upgrade on the tape servers
Stafing
RA on call
Alison away
Actions
RA disks servers requiring RAID update - locate servers and plan for update with fabric
RA decide what to do with persistent data (for daily test) is still on GenScratch
RA to update the doc for xroot certificates
GP to present the stress test results of gdss596 configured with the WAN tuning parameters
Operation problems
gdss634 (atlasTape) and gdss651, gdss763 (preprod) failed and went out of prod. gdss634 had all Hard drives replaced and currently is under acceptance testing.
A large number of GridFTP transfers on a 2011 lhcb server resulting in reduction of performance. Solution: Global tightening of transfermanager weightings. For details see here
Operation news
CERN OPN link now running on 2*10Gbit
The workload on DBs is normal
The name server dump script for ATLAS appears to work and it was successfully cronified. See RT 154144
Correction of double putStarts in ATLAS. See here
The 2014 disk servers from Ceph are in the last stage of conversion to CASTOR RT 173922
Long-term projects
Stress test the 2.1.15 upgrade on preprod
George will liaise with Bruno so that he can understand better the technical requirements of the SL7 upgrade on the tape servers
Staffing
RA on call
Chris, Andrey away
Actions
RA disks servers requiring RAID update - locate servers and plan for update with fabric
RA decide what to do with persistent data (for daily test) is still on GenScratch
RA to update the doc for xroot certificates
GP to present the stress test results of gdss596 configured with the WAN tuning parameters