Production Team Report 2011-04-04

From GridPP Wiki
Jump to: navigation, search

RAL Tier1 Production Team Report for 4th April 2011.

AoD This Week

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

Last week

  • Gareth: AoD 1 day; GridPP - 2 days;
  • John: GridPP - 2 days; Checking batch worker nodes;
  • Tiju: AoD (4 days - including over GridPP);

Changes to Operating procedures

  • None

Declared Outages in GOC DB

  • None

Advanced Warning

  • Power outage in Atlas building Saturday 9th April.

Other Changes

  • Fabric:
    • Upgrade to networking for tape servers to enable sufficient bandwidth for T10KC tapes.
  • 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
    • SRM 2.10 upgrade.
    • 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)