RAL Tier1 weekly operations castor 25/11/2013
From GridPP Wiki
- Have decreased CASTOR overhead to 1% on 5 production disk servers. We will wait until they fill up and monitor them closely before rolling out the change to everything.
- Testing started on 2.1.14-3. Some problems with xroot testing. Now 2.1.14-4 (which includes some xroot bug fixes) is out, we'll use that instead
- Some tape-backed LHCb inconsistent files were discovered due to a race condition that happens under certain conditions between the stager and GC: https://savannah.cern.ch/bugs/index.php?103235. We have increased the GC limit in the meantime which should reduce chance of repetitition.
- (Mon) Problems switching to backup link at CERN caused all SUM tests to fail between 0900-1200CET.
Planned, Scheduled and Cancelled Interventions
Entries in/planned to go to GOCDB
- CASTOR 2.1.14 + SL5/6 testing
- Castor on Call person
- Staff absence/out of the office:
- Mostly in.