Pretty Cool – Sorting/Processing PB of Data
Google has been working on parallel processing (no surprise there; they have one of the msot well-known parallel processing environments going…) – to the point where they’re processing Petabytes (1000 TB) of data, in record time. The whole parallel processing approach holds great promise, especially as things start to share environments and processing power with the cloud.
Why does Googles work impact us with SQL Server? They’re reportedly working with SQL Server to do some of these tests and development work. The impact, testing, systems and solutions could have a very substantial impact on the long-term scaling options for SQL Server.
The whole idea of having the ability to reliably add commodity servers to a system of servers and increase processing power (parallel processing) is one of the big challenges – yes, there are some solutions out there, but built-in capabilities for SQL Server in this area are still something largely on the horizon.
It’ll be really interesting to see how these features make it into the product over time, and how it impacts more mainstream use of and functionality for SQL Server.
Featured White Paper(s)
Building High-Performance Database Systems with EMC Storage Technology and Microsoft SQL Server 2005
In this white paper, you’ll read about Microsoft SQL Server 2005 Enterprise Edition, which incorporates powerful data managem… (read more)
The Shortcut Guide to SQL Server Infrastructure Optimization
In The Shortcut Guide to SQL Server Infrastructure Optimization, the new eBook from Realtime Publishers, leading IT author Do… (read more)