RAL Tier1 weekly operations castor 03/03/2014

Operations News

• We have started stress testing the two new 2014 disk server generations now in preprod (gdss726,727)
• Final testing will br ongoing for 2.1.14 - including draining under stress. Our target minor release (-11) will be installed on preprod
• ATLAS has requested that we reduce the number of replicas in HOTDISK from 5 to 1

Operations Problems

• Number of out of thread errors is now back to background levels. The increased thread number on ATLAS stager is being rolled out to all stagers this week.
• ATLASDATADISK and ATLASSCRATCHDISK is full. The VO is aware.
• Admin machine lcgccvm02 has crashed ~5 times over the last 5 days. We believe this is related to HyperV instability.
• Elastic Logging instability continues and needs to be fixed prior to being production ready.

Blocking Issues

• none

Planned, Scheduled and Cancelled Interventions

Entries in/planned to go to GOCDB

Advanced Planning

Tasks

• CASTOR 2.1.14 + SL5/6 testing. The change control has gone through today with few problems.
• iptables to be installed on lcgcviewer01 to harden the logging system against the injection of junk data by security scans.
• Quattor cleanup process is ongoing.
• Installation of new Preprod headnodes

Interventions

• none

Staffing

• Castor on Call person
  • Rob
• Staff absence/out of the office:
  • Chris SDB User Meeting (Mon-Wed)
  • Matt EGI DP workshop (Tue-Thu)