RAL Tier1 weekly operations castor 20/12/2010
From GridPP Wiki
- Remaining SRMs (LHCb, Gen) upgraded to 2.8-6
- Wrong checksums were found to be given to ~30 LHCb files, leading to errors in the rtcopyd log. This was due to a bug (fixed in 2.1.9-9) affecting incompletely transferred files. Since the transfer error was originally sent back to the user, this is not considered as data corruption due to us.
- Jobmanager stopped working for LHCb for ~45 minutes. Secondary job managers will be enabled for remaining instances (LHCb, Gen)
- aliceTape GC limits were found to be wrong, leading to a lack of spare capacity. These were corrected.
- On Friday, the ATLAS instance became very busy. The 6 SRMs coped, but a backlog was created in LSF. The FTS was throttled to prevent further congestion.
- Lack of production-class hardware running ORACLE 10g needs to be resolved prior to CASTOR for Facilities going into full production
Planned, Scheduled and Cancelled Interventions
Entries in/planned to go to GOCDB
|Description||Start||End||Type||Affected VO(s)||Lead by|
|Update ATLAS disk servers to SL5 64bit (TBC)||17/01/2011 08:00||18/12/2011 16:00||Downtime||ATLAS||MV|
- CASTOR for Facilities instance in production by end of 2010
- Upgrade ATLAS, CMS, Gen disk servers to SL5 64bit and Quattorize the non-Quattorized disk servers
- CASTOR certification and upgrade to 2.1.9-10 which incorporates the fix for gridftp-internal to support multiple service classes, enabling checksums for Gen
- CASTOR upgrade to 2.1.9-10 and SRM upgrade to 2.10 to fix the unavailable status being reported to FTS with draining disk servers
- Castor on Call person: Chris
- Staff absence/out of the office:
- Shaun out all week
- Jens out from Wednesday