Welcome to CA&ES Computing Cluster Center

Network connectivity restored — by Adam Getchell — last modified Sep 28, 2010 10:52 AM

Dropped connections issue with Ganglia and external network configurations resolved

Farm restored — by Adam Getchell — last modified Aug 27, 2010 12:54 PM

Farm was restored to full functionality Friday, August 20, and has been running for the past week without issue.

Head node failure — by Adam Getchell — last modified Aug 17, 2010 02:36 PM

A head node failure has brought the cluster down. Bill Broadley has pulled spare head node and is working to bring back up. Details follow. We'll let you know when Farm is available again. Sorry for the inconvenience.

I/O problems — by Scott Beardsley — last modified Jan 14, 2010 12:31 PM

We had a problem this morning that forced a reboot and raid rebuild

Welcome to Farm — by Scott Beardsley — last modified Nov 25, 2009 03:39 PM

A short welcome message to the people that have been waiting for this resource to come online.

Rack installed — by Adam Getchell — last modified Nov 02, 2009 03:30 PM

Rack was delivered and carried up stairs and is now in Watershed. Now awaiting being bolted to the floor, and installation of power whips on Friday, 11/6/2009.

Rack installation scheduled for Monday, Nov. 2, 2009 — by Adam Getchell — last modified Oct 28, 2009 05:29 PM

Special Services will be out at 8:30AM on Monday, November 2nd, to pickup the server rack from the Data Center and move it to the second floor of Watershed.

Cluster arrived at Watershed — by Adam Getchell — last modified Oct 27, 2009 06:01 PM

Thanks to heroic efforts from Bill & Scott in CSE, equipment delivery was received in Watershed.

Cluster in transit to UC Davis — by Adam Getchell — last modified Oct 23, 2009 12:06 PM

All nodes passed final checks from CSE, and the cluster hardware has been packaged and shipped from Chicago, IL to Davis via AIT trucking, ETA 10/29/09.

New heatsinks ordered — by Adam Getchell — last modified Oct 15, 2009 12:58 PM

Vendor has ordered new heatsinks to resolve cooling issues on second processor of each node

First burn-in test — by Adam Getchell — last modified Oct 15, 2009 12:37 PM

The CSE group has logged into the cluster as built on the vendor premises and conducted the first round of burn-in by running sample code. Results indicate anomalously high temperatures on second CPU core of each node. Vendor working on resolution.

Cluster build status 9.18.2009 — by Adam Getchell — last modified Sep 18, 2009 01:14 PM

Build pending arrival of Supermicro motherboards, delayed due to Defense Department priority order. Full text from Ace Computers in notice.

Cluster build ETA 9.15.09 — by Adam Getchell — last modified Sep 18, 2009 01:13 PM

John Samborski, PE from Ace computers has given a two-week build time estimate and one week shipping estimate. We expect to do cluster burn-in at Ace Computer's facilities to make initial parts replacement easier. If you are a founder and have jobs you wish to submit as part of the burn-in, please contact us.

CAES Cluster contract awarded — by Adam Getchell — last modified Aug 20, 2009 08:42 AM

The CAES cluster contract has been awarded to Ace Computers. The winning bid has been posted.

Re-bids and new specifications — by Adam Getchell — last modified Aug 13, 2009 06:54 AM

Due to an error in the technical specifications included with the previous RFQ, a new RFQ has been submitted with updated specifications. Vendor bids are due August 18.

Specifications & Bid — by Adam Getchell — last modified Aug 11, 2009 05:34 PM

The cluster hardware is at Purchasing (PR #013933091) for bidding, acceptance and delivery. The cluster specifications and a vendor bid are available for review.

Vendor bids due August 4, 2009 — by Adam Getchell — last modified Jul 30, 2009 05:38 PM