February 11, 2008
Cellnet+Hunt, an Atlanta-based utility metering and energy efficiency services company, recently made the move to grid computing by transforming its one-box-per-customer siloed architecture into a four-node Oracle RAC set-up that powers the databases for all 21 of the company’s customers.
Cellnet+Hunt services upward of 20 million customer endpoints, and the move to a grid architecture was spurred by not only a demand to pull in more data from the meters, but also from the already rapid growth in data volume. “The amount of information we’re needing to process as we move forward is sometimes 10 times as much,” said Letha McLaren, services general manager at Cellnet+Hunt. “That’s why it’s really important for us, first of all, to be really scalable, and secondly, [to be reliable].”
With such an increase in data, the need for scalability is no surprise, but with Cellnet+Hunt’s customers demanding 24 by 7 access to metering data – especially when it comes to Cellnet’s service providing real-time views into power outage data – reliability become tantamount. According to Nigam Desai, PMP systems services manager for network operations at Cellnet+Hunt. “Before we went into grid, if one particular instance went down, then that customer was completely down. Given the grid, now we can have things fail over, and that keeps everything running 24 by 7.”
Balaji Subramanian, DBA supervisor at Cellnet+Hunt, said that the Oracle grid is currently managing between 7 and 8TB of data, and running at a 50 percent utilization rate, but with daily data quantities expected to multiply five or six times in the near future, Cellnet+Hunt could be adding a fifth Sun Fire V890 node relatively soon.
McLaren says that while her company holds its IT infrastructure to higher standards because Cellnet+Hunt, as a service provider that gathers, processes and delivers data back to the utilities, handles much more data than its competitors, which generally just sell systems to utilities, grid computing is nonetheless “catching on” in the utility space. Scalability and reliability are big issues not just with Cellnet+Hunt, but with everyone, she said.
And, thus far, Cellnet+Hunt’s Oracle grid environment had paid off in terms of reliability and availability. Since making the switch, the company’s database environment has not experienced any unplanned downtime.
10/30/2013 | Cray, DDN, Mellanox, NetApp, ScaleMP, Supermicro, Xyratex | Creating data is easy… the challenge is getting it to the right place to make use of it. This paper discusses fresh solutions that can directly increase I/O efficiency, and the applications of these solutions to current, and new technology infrastructures.
10/01/2013 | IBM | A new trend is developing in the HPC space that is also affecting enterprise computing productivity with the arrival of “ultra-dense” hyper-scale servers.
Ken Claffey, SVP and General Manager at Xyratex, presents ClusterStor at the Vendor Showdown at ISC13 in Leipzig, Germany.
Join HPCwire Editor Nicole Hemsoth and Dr. David Bader from Georgia Tech as they take center stage on opening night at Atlanta's first Big Data Kick Off Week, filmed in front of a live audience. Nicole and David look at the evolution of HPC, today's big data challenges, discuss real world solutions, and reveal their predictions. Exactly what does the future holds for HPC?