Sunday, November 4, 2012

Google Search Architecture

Google search architecture is mind blowing. It is like watching nerve breaking movie independence day or
Jurassic-park movies

If you are the software developer, you would know "look table implementation" method. When the user searches, we search in the table, with the particular keyword. And we will get the required output.  I am talking about molecule level of Google amazing architecture". 

If you have the heart problem, you could stop reading the below stuff. This is phenomenal work, Google has done while your sleeping/and working other stuff.
The extensible parallel process, state-of-the-art clustering servers are being used here.

To build an infrastructure capable of executing thousands of queries per second, where each query in itself consumes billions of CPU cycles is really challenging.

A single query on Google reads hundreds of megabytes of data and consumes tens of billions of CPU cycles.

Google Architecture 
Google architecture features clusters of more than 15,000 commodity-class PCs with fault-tolerant software to achieve superior performance.

Combining 15000 commodity-class PCs, with fault-tolerant software, gives higher performance than a smaller group of high-end servers.

Google Web server and high-level block diagram
The search is  invoked by the user are processed by using the index services, document servers, spell checker.Document servers hold data which was crawled earlier. And within fractions of secs the above process is done. User gets the results for the "search". 

In the above process, Google uses innovations, software abstraction like MapReduce or GFS or Colossus, SStable, and others.

Google Architecture 

In the above process, rock-star developers were involved. Jeff dean, Sanjay Ghemawat, Luiz Barroso, Yrs Holzle.

Colossus Picture 

The contents mentioned are here are the property of respective owners. I have documented based on my understanding.

Hope u enjoyed. Will write more on this area. Please feedback


No comments: