Google Spanner Achieves the Impossible
December 27, 2012
Wired has posted a thorough article about a recent Google tech breakthrough in its “Exclusive: Inside Google Spanner, the Largest Single Database on Earth.” This database, like many other Googley projects, grew out of the company’s solution to an internal problem—collaborating between their scattered offices without being slowed down by the delay that usually plagues global communications and data sharing.
“Spanner is a creation so large, some have trouble wrapping their heads around it. But the end result is easily explained: With Spanner, Google can offer a web service to a worldwide audience, but still ensure that something happening on the service in one part of the world doesn’t contradict what’s happening in another. . . .
“Before Spanner was revealed, many didn’t even think it was possible. Yes, we had ‘NoSQL’ databases capable of storing information across multiple data centers, but they couldn’t do so while keeping that information ‘consistent’ — meaning that someone looking at the data on one side of the world sees the same thing as someone on the other side. The assumption was that consistency was barred by the inherent delays that come when sending information between data centers.”
Google’s engineers have found a way, though, one that involved creating its own time-keeping mechanism and ended up reducing costs in the bargain. It is well worth reading the article for the details.
What caught our eye most, though, is the hostility toward Google in some of the comments. I won’t reproduce them here, but we wonder: why the chip on the community’s shoulder?
We officially love Google.
Cynthia Murrell, December 27, 2012
Sponsored by ArnoldIT.com, developer of Augmentext
Comments
-
- Subscribe to Beyond Search
Feature archive
News archive
-
