System Notices

Friday January 27 - Matrix Booked

The Matrix System is being used this weekend in partial fulfilment of a request to RAC. The group making the request RAC requires the system for a 24 hour period and will use all processors. ---------

Friday January 27 - Matrix Filesystems Problems

The Matrix System was unavailable 7.50 a.m. Friday January 27th. due to problems with the SFS Disk System. ---------

Monday 16 January WestGrid storage facility reboot

The WestGrid storage facility (gridstore) will be rebooted on Monday, Jan. 16, between 8am and 9am (PST) and filesystems will be unavailable for about 20 min. on robson, tantalus, and blackhole. Due to unexpected file system problems on gridstore all running jobs were lost. ---------

Tuesday 10 January WestGrid network downtime

The network maintenance work originally scheduled for 21 Dec has been rescheduled and will take place on Tuesday, January 10th, between 07:00 and 08:00 PST. (see below for details) Note: only one of the two Triumf - CERN lightpaths will be affected, not both. ---------

Monday 23 and Tuesday 24 January WestGrid storage facility upgrade

The WestGrid storage facility (gridstore) will be completely rebuilt: the file server (gridstore) will be upgraded from a Power4 server to a Power5 server and the operating system will be upgraded to AIX 5.3. We expect that the upgrade will take about two days. Over that period gridstore, robson, tantalus, blackhole and other WestGrid systems housed at SFU will be unavailable. All these systems will have to be rebooted in the process, thus all running jobs on robson and tantalus will be terminated on Monday morning. We expect that all systems will be available again on Wednesday 25.

Wednesday 4th. January 2006 - Matrix Problem

Starting at 06:35 a.m. this morning matrix had filesystem problems. This issue has been resolved, but all running jobs were lost with the cluster re-boot. ---------

Wednesday 21 December WestGrid network downtime

CANCELLED -- WILL BE RESCHEDULED TO EARLY JANUARY Subject: Maintenance two Vancouver - Calgary OC192 circuits Category: Scheduled maintenance Start Time: 2005-12-21 08:30 PST (2005-12-21 16:30 UTC) End Time: 2005-12-21 13:30 PST (2005-12-21 21:30 UTC) Two Vancouver–Calgary OC192 circuits will down to switch equipment. This is part of the network redesign. All light paths provisioned on those two circuits will be affected. The downtime could last as long as the maintenance window.

Friday December 16, 7:00pm (PST) Glacier

We are in the final stages of our upgrade, waiting for the remainder of /global/home to restore from tape. To be on the safe side, we estimate that Glacier will be open sometime during the next 24 to 48 hours. Thanks very much for your patience so far. ---------

Friday December 9, 7:00pm (PST) Glacier

Please note that UBC WestGrid is down for scheduled maintenance beginning at 7:00PM Dec 9 until approximately late Dec 16. We will try to minimize the downtime so that we might return at an earlier date. Please contact WestGrid support (support@westgrid.ca), if you have any questions or concerns. ---------

Thursday December 8, 12:33pm - 2:30pm (MST)(CXFS) - 12:33pm - 4:00pm (MST)(Dendrite, Synapse) - UofA site power outage

The power outage affected all our SAN switches, global (CXFS) filesystems. All running jobs at the time were lost. Dendrite and Synapse lost power during this outage. ---------

Syndicate content