Production Team Report 2011-04-11

RAL Tier1 Production Team Report for 11th April 2011.

AoD This Week

Mon - Tue: Tiju Wed - Thu: Gareth Fri: Tiju

Last week

• Gareth: AoD (1 day); A/L (1 day); Investigating network packet loss.
• John: AoD (3 days)
• Tiju: AoD (1 day); CVMFS Nagios tests,

Changes to Operating procedures

• CVMFS considered a production service.

Declared Outages in GOC DB

• Tuesday 12th April: LHCb - SRM 2.10-2 upgrade.

Advanced Warning

• Wednesday 12th April: Atlas - SRM 2.10-2 upgrade.
• Thursday 12th April: CMS - SRM 2.10-2 upgrade.
• Friday 12th April: GEN - SRM 2.10-2 upgrade.

Other Changes

• Fabric:
  • Upgrade to networking for tape servers to enable sufficient bandwidth for T10KC tapes.
  • Microcode update on tape robots.
• Database:
  • Switch Castor databases to array in R26 (3-4 hour outage of Castor)
  • Switch Castor databases back to array in R89 (3-4 hour outage of Castor)
  • Switch non-Castor databases to new array. (~1 hour outage of LFC, FTS, 3D)
• Grid Services:
  • None
• Castor:
  • Change ATLAS castor permissions to prevent users deleting data
  • Castor 2.1.10 client upgrade on WNs
  • xroot client upgrade on WNs
  • Castor update to obtain functionality for T10KC tapes.
  • Updates to new hardware for castor head nodes.
• Networks:
  • Firmware updates for central networking components (likely to have some short network breaks - maybe in March)