Oracle and HP Partner to Deliver Data Warehouse Appliance
HP Oracle Database Machine takes on Teradata and Netezza in a bid to defend Oracle's database dominance.
The story from this week's Oracle Open World — and perhaps for the year for the company — was last night’s announcement (by no less than CEO Larry Ellison) of the HP Oracle Database Machine and HP Oracle Exadata Storage Server. With this joint software/hardware release with HP, Oracle is not just joining the data warehouse appliance movement, it's going right after segment leaders Teradata and Netezza, claiming better performance and scalability than either competitor.
Oracle is also entering the market running with a shipping product, so it's way ahead of Microsoft and its DATAllegro acquisition earlier this year, which may not yield a shipping product for months.
Ellison took the stage last night at Oracle Open World in San Francisco kidding that his "day job" is now racing sailboats, but he quickly drew parallels between his "game changing" Americas Cup racing yacht and the HP Oracle Database Machine and Exadata Storage Server. Tapping "radical new thinking to deliver high performance," Ellison said the pairing eliminates the data bandwidth problems encountered by large disk storage systems in two ways. First, it reduces the amount of data moving into Database Machine by putting compute power in the Exadata Storage Server on each disk — an approach that sounds much like Netezza's architecture. Second, it relies on wider, faster pipes, in this case, two InfiniBand connections between the Database Machine and Exadata Storage Server capable of moving 1 gigabyte of data per second.
While many appliance vendors target 100-terabyte-plus deployments, Ellison made it clear that Oracle is going after the full range of deployments starting in the single digits. "You don't have to have a 200-terabyte database to experience slow downs," he explained. "At 1 terabyte you start to slow down, and even the fastest disk arrays start to fall apart when you get to 10 terabytes."
Each Exadata Storage Server runs on two Intel processors with four cores each and has up to 12 terabytes of raw storage capacity. To scale up, customers add more devices to a grid; a grid of 14 Exadata Storage Servers would deliver up to 168 terabytes of raw storage and 14 GB/sec data bandwidth to the database servers.
HP CEO Mark Hurd, who appeared along with Ellison via video link, stressed that the hardware is built completely on open technologies. "It's the traditional Proliant servers that you would use as an app server or a Web server, it's integrating standard storage technologies and we're bringing it through our standard manufacturing and supply chain," Hurd said. Ellison added that the choice of standard technologies will mean more cores, higher disk capacities, faster connectivity speeds and ever-improving performance in future releases.
Ellison said pricing is $4,000 per terabyte, which he described as "closer to a disk array than a database machine," but that figure did not include the database license and it wasn't clear whether pricing included the Database Machine part of the total appliance.
News of the joint Oracle-HP offering had clearly leaked out ahead of the announcement as reporters were flooded with statements from competitors, yet none of those statements addressed the details of the announcements. Ellison claimed a 2X performance advantage over Netezza and speed and cost advantages over Teradata offerings.
As details of the Exadata Storage Server emerge, Intelligent Enterprise will bring you informed comments from competitors, analysts and contributors in the days ahead.
The Agile ArchiveWhen it comes to managing data, donít look at backup and archiving systems as burdens and cost centers. A well-designed archive can enhance data protection and restores, ease search and e-discovery efforts, and save money by intelligently moving data from expensive primary storage systems.
2014 Analytics, BI, and Information Management SurveyITís tried for years to simplify data analytics and business intelligence efforts. Have visual analysis tools and Hadoop and NoSQL databases helped? Respondents to our 2014 InformationWeek Analytics, Business Intelligence, and Information Management Survey have a mixed outlook.
InformationWeek Must Reads Oct. 21, 2014InformationWeek's new Must Reads is a compendium of our best recent coverage of digital strategy. Learn why you should learn to embrace DevOps, how to avoid roadblocks for digital projects, what the five steps to API management are, and more.