You are here
|Post date||System Status:||Update Notes|
|2013-07-31 - 11:51 PDT||Conditions||
Filesystem problems are affecting Parallel, Lattice and Breezy.
The systems are available but performance can very poor. Systems staff are working with the hardware vendor to resolve the problem. Normal service will be resumed as soon as is possible, and we apologise for the inconvenience caused.
|2013-07-11 - 07:20 PDT||Online||
2013-07-13 Job scheduling restarted on Parallel
Job scheduling was restarted on Parallel on Wednesday, July 10, after power and cooling problems were corrected.
|2013-07-09 - 17:33 PDT||Conditions||
2013-07-08/09 Power and cooling failures affect Parallel
Monday evening (2013-07-08) a power failure at the University of Calgary affected WestGrid systems there, including Parallel. Job scheduling was paused while the situation was being assessed. After the power was restored, it was found that cold water cooling to the machines was not available. Running jobs were lost, as the compute nodes had to be shut down. Please check output carefully to see what needs to be resubmitted.
Status as of 1830 Tuesday (2013-07-09): Cooling was restored Tuesday afternoon but job scheduling will not be restarted until Wednesday morning in order to make sure that the situation is stable. Sorry for the inconvenience. In the meantime, the login server and file systems (/home, /global/scratch, /global/software) are available.
|2013-07-08 - 20:44 PDT||Offline||
2013-07-08 Power failure affects Parallel
Monday evening (2013-07-08) a power failure at the University of Calgary has affected WestGrid systems there, including Parallel. Job scheduling has been paused while the situation is being assessed.
July 9, 2013: 13:30: waiting for cold water flow to be restored.
|2013-05-29 - 12:30 PDT||Online||
Lattice/Parallel systems fully operational
Update 1330 MDT 2013-5-29:
We are back online and jobs are being scheduled once again.
|2013-05-29 - 00:22 PDT||Conditions||
Lattice/Parallel system scheduling update
Update 0025 MDT 2013-05-29:
File systems are back online. Scheduling of jobs will remain paused overnight.
|2013-05-28 - 14:07 PDT||Offline||
May 28 - File System Issue on Lattice and Parallel
1530 MDT 2013-05-28:
We are having file system issues on Parallel and Lattice. This system notice will be updated as new information is available. Sorry for the inconvenience.