RAL Tier1 weekly operations Fabric 20100419

Developments

• All:

• Martin:

• Ian:

• Tim:
  • Installing new ADS servers (3 down one to go)
  • Configuring new disk on DMF service.
  • New enlarged DMF area put into production to improve stability of system
  • Investigating CMS migration problems

• Cheney:
  • racked up the infortrends
  • wrote some docco on castor
  • started on docco for DR
  • wrote up next years job plan
  • planned a new backups server for db
  • wrote change control docco
• James T:
  • GridPP storage workshop Monday and Tuesday
  • GridPP 24 Wednesday and Thursday
  • Worked on SL5 disk server build with Ian
  • Played with Hadoop Distributed File System

• Jonathan:
  • On leave

• James A:
  • Swapped RAM in gdss370 and 405 to expedite 405's return to service.
  • Updated ARTEMIS room images.
  • Ran HEPSPEC2006 ten times on all new Viglen 2009 WNs to verify performance.
  • Generated Weathermap video for Gareth.
  • Wrote a Nagios plugin to check for web connectivity.
  • Prepared QUATTOR for Streamline 2009 WNs.
  • Switched ARTEMIS to xml feed monitoring of temperatures for 100x precision increase.

• Kash:
  • Drive replacement.
  • Fixing broken WNs.
  • Decommissioning old batch systems.(R 27)
  • gdss405 kernel panic .(Faulty memory) Fixed by James A.
  • propod1 reported single psu failure. (Transtec)
  • lcg1235/1236 bios settings updated by Streamline engineer.
  • ccse03 faulty PSU reported.(Intervention)

Absences

• Jonathan on leave all week
• Kashif A/L (Tuesday)
• James T at GridPP until Thursday
• Tim working at home Monday

Operational Issues and Incidents

Index	Description	Start	End	Severity	Affected VO(s)

Summary of plans for week ahead

Scheduled and Cancelled Down Times

Type=Down/At Risk/Cancelled entries in/planned to go to GOCDB

Component	Description	Start	End	Affected VO(s)	Type

Development priorities

• All

• Martin:

• Ian:

• Tim:
  • Finish installing ADS servers.
  • Finish configuring new ADS servers (Nagios/Ganglia etc)
  • Continue investigating CMS migtration problems
  • Investigate Atlas recall problems
  • APR/Job plans
  • DB Backup procedures
  • SSC finance training Thursday

• Cheney:
  • Last year APR/job plan
  • Evaluate mgt utilities for SRB guys
  • Write more docco
  • install nagios on new ads servers

• James T:
  • Fix disk server kickstart issues
  • Quattor disk server build tweaks
  • Follow up problems with new disk servers with the vendor
  • APR and job plan
  • SSC finance training Tuesday morning

• Jonathan:
  • Catch up after being away
  • APR and job plan
  • SSC finance training Tuesday morning

• James A:
  • Sort out flaky ARTEMIS base unit in LPD room.
  • Begin acceptance testing Streamline 2009 WNs when handed over.
  • Establish Viglen 2009 WN compatibility with SL4.
  • Reclaim Nortel 5510 from CASTOR rack.
  • Put Viglen 2009 WNs into production.
  • Investigate cool-sounding PBS idle WN control.

• Kash:
  • Drive replacement.
  • Fixing broken WNs.
  • Continuous decommissioning old batch systems.(R 27)

Absences

• Jonathan on partial retirement (not in on Monday and Friday)

Services Issues

---

RAL Tier1 weekly operations fabric

Category:RAL_Tier1