The Google empire has come a long way, but with thousands of queries per second, Google requires a powerful and well designed architecture to make it all come together. When a search is sent through the Google website, the browser matches an IP to google.com and a request is sent to a Google Web Server (GNS). The query consists of two phases. First, each query word is compared and matched up with a huge list of documents, where a relevance score is assigned to each document. This search is huge, but by using maximal parallelization, the index is divided and looked at by a large pool of machines. This relevancy-ordered list of web document identifiers are used to get the URL and a small summary. This is also a huge task, but by having documents divided up, and using multiple servers and load balancers, Google exponentially decreases the system resources it requires to process a query. Finally, an output page is produced and displayed to the user.
This is the end of the preview.
access the rest of the document.