So far this week, we've had duplicate tickets from GGUS about a failure with dcache01 (affect the ce01 SAM tests), all transfers were stalling, I couldn't debug this as my certificate expired the day i returned from a week off and my dteam membership still hasn't been updated. Restarting the dcache headnode fixed this.
And this morning I discovered that a number of our Worker Nodes had full /scratch partitions, the problem has been tracked to a phenogrid user, and we're working with him on attempting to isolate the issue.
No comments:
Post a Comment