Google's secret of success? Dealing with failure

TalkBack 7 of 10:

Next »

« Previous

• Thread View
• Flat View

Using Cheap Equipment, aka massively parallel computers

Google's approach works because the nature of the process which Google is executing is inherently parallel, e.g. many-to-many transactions. Not only this, but the data Google handles is relatively static and is relatively insensitive to update issues. Most importantly, the multiple copies of the data (e.g. the web pages)do not need to be identical, they can be out of sync with each other.

Googles approach would work well with any situation which matches theirs a many-to-many transaction relationship. Unfortunately, these tend to be less common than the more usual one-to-many data relationship which obtains with most commercial situations.

Posted by: smfriedland   Posted on: 03/06/05 You are currently: a Guest | Members login | Terms of Use

Alert moderator to an offensive message

Subscribe to this discussion via Email or RSS

SponsoredWhite Papers, Webcasts, and Downloads

• Evaluating Price/Performance of VMware ESX Server on Dell PowerEdge Servers Dell This paper examines the price/performance advantage that enterprises can ... Download Now
• INNOV8 2.0: A Business Process Management Simulator IBM Innovate your business' process model, play against the market, compete ... Download Now
• Designing a Balanced Architecture With Oracle RAC and VERITAS Software for Linux Dell Introducing Oracle RAC into an IT infrastructure and using Linux as the ... Download Now