Date & time of incident:
Saturday, June 25, 2011 - 18:20
Post date:
Sunday, June 26, 2011 - 13:13
Incident Description:
On 25-06-11posted by CC Operators:
xrdcp processes stuck on lxbatch copying files from Castor Around 700 "xrdcp" processes were found stuck (for many hours or days) on the Batch Service while attempting to copy files from Castor - with the associated jobs stalled. The stuck xrdcp processes have been killed ( the jobs themselves have been left running to allow them to process the file copy failure appropriately ).
More news on Monday morning.
Workaround:
The problem has been resolved. Sorry for the inconvenience.
Service Element Affected:
Under Investigation
Impact:
Service is degraded
Status:
Resolved
Resolution date:
Tue, Jun 28, 10:00
Posted by:
IT-PES
Unit responsible for resolution:
IT Department