RAL Tier1 weekly operations castor 3/11/2014
From GridPP Wiki
Contents
Operations News
- xrootd security advisory with FAX component within xrootd
- SL6 Headnode work - tested in vcert, next test in prepord including stress testing
- Draining going well - 40TB in a week, ETA finish in c15 weeks for draining of 1Gb systems
Operations Problems
- gdss720 / gdss763 are both drained, out of production and currently being worked on by Fabric team
- gdss659 had been previously drained and is currently undergoing final tests before returning to production
- A few SUM test failures this week across a number of VOs
- Non LHC Nagios /Sam tests failing due to Kashif ( @Oxford) DN being used by all , and failing due to SRM not being voms aware.
Blocking Issues
- grid ftp bug in SL6 - stops any globus copy if a client is using a particular library. This is a show stopper for SL6 on disk server.
- webdav access for LHCb requires firewall changes by Fabric
Planned, Scheduled and Cancelled Interventions
- A Tier 1 Database cleanup is planned so as to eliminate a number of excess tables and other entities left over from previous CASTOR versions. This will be change-controlled in the near future.
Advanced Planning
Tasks
- Plan to ensure PreProd represents production in terms of hardware generation are underway
- Possible future upgrade to CASTOR 2.1.14-15 post christmas
- Switch from admin machines: lcgccvm02 to lcgcadm05
- New VM configured to run against the standby CASTOR database will be created as a front-end for dark data etc queries.
- Correct partitioning alignment issue (3rd CASTOR partition) on new castor disk servers
Interventions
Actions
- Brian to talk to atlas re periods of stress and if these are reflected in poor service at atlas. If not then possibly just leave xroot weighting as it is.
- Brian - check atlas disk pledge with 720 / 763 out ..
- Rob - document findings of investigations relating to high wait IO on atlas
- Rob - to document preprod SL6 upgrade on wiki as he goes
- Bruno to present changes to castor quattor / doc
- CIP into instructions for castor failover
Staffing
- Castor on Call person
- Chris
- Staff absence/out of the office:
- Bruno all week
- Chris Thurs (poss half day TBC)
- Matt Monday
- Juan Friday
