RAL Tier1 weekly operations Fabric 20110124

Editing RAL Tier1 weekly operations Fabric 20110110

Developments

• All:

• Martin:

• Ian:

• Tim:

• James A:
  • Atlas power off completed with no issues.
  • Bulk of ClusterVision WN issues now sorted, now trying to push through acceptance.
  • Continued benchmarking.

• James T
  • ATLAS SL5 x86_64 upgrade
  • End of acceptance tests on Viglen and Streamline 2010 disks
  • AFS documentation
  • First aid course Wednesday and Thursday

• Cheney
  • Atlas power shutdown
  • backups performance testing
  • huge backups testing
  • generate solarb stats
  • dmf disaster recovery

• Kash:
  • Drive replacement.
  • Fixing broken WNs.
  • Decommissioning old batch systems.(R 27)
  • gdss380 add new mac address in dhcp and re-install.
  • gdss189 read-only filesystem.(Scsi errors)
  • gdss496 Scsi errors. Reported to Streamline with logs.(Intervention)
  • gdss451 replaced 4x2gb memory. (Back into production same day)
  • Fabric Hardware failure metrics.
  • Jetstor systems multiple drive failures.
  • gdss576 and gdss577 getting logs to send to Streamline.
  • gdss496 post-mortem.
  • lcgwms03 replaced drive with hotswap method.
  • gdss283 crashed with File system problem.(Intervention)
  • Quattor01 wend down. No problem found.
  • SL 2010 and Viglen 2010 disk servers in testing.
  • SL 2009 Auto rebuild on hotspare fails.

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:

• Cheney
  • DMF dr

• James T:
  • Disk checks in Kash's Absence
  • Review testing of Streamline and Viglen 2010 disks
  • Preparation for CMS SL5 x86_64 upgrade
  • Streamline 2008 testing
  • Project management training Thursday and Friday

• James A:
  • Pushing ClusterVision WNs through acceptance testing.
  • Hardware support while Kash on leave.

• Kash:
  • Drive replacement.
  • Fixing broken WNs.
  • SL 2009 Auto rebuild on hotspare fails.
  • Hardware failure metrics continue.
  • SL08 testing.
  • Continuous decommissioning old batch systems.(R 27)

Absences

• Kash out Monday (Annual Leave)
• JRHA out Wednesday (Annual Leave)
• James T out Thursday and Friday (project management training)

Fabric On-Call

• Monday - Sunday

Services Issues

---

RAL Tier1 weekly operations fabric

Category:RAL_Tier1