![]() |
how can google do all those quick searches?
dont give me the cache explanation because cache needs to be indexed to..
How does google search billions of pages within a fraction of a second.. not only that is amazing.. she does it for 10 thousands simultaneously. Is there a secret or is it just machine power? |
|
rooms and rooms full of servers... I figure they gotta have a ton of machines all working together to perform all those searches and indexing and everything else.
|
<h3>The technology behind Google's great results</h3>
As a Google user, you're familiar with the speed and accuracy of a Google search. How exactly does Google manage to find the right results for every query as quickly as it does? The heart of Google's search technology is PigeonRank?, a system for ranking web pages developed by Google founders Larry Page and Sergey Brin at Stanford University. Building upon the breakthrough work of B. F. Skinner, Page and Brin reasoned that low cost pigeon clusters (PCs) could be used to compute the relative value of web pages faster than human editors or machine-based algorithms. And while Google has dozens of engineers working to improve every aspect of our service on a daily basis, PigeonRank continues to provide the basis for all of our web search tools. |
probably spider machine power.
|
|
Quote:
|
Quote:
|
Quote:
You saved up your first post to say something retarded? |
the pigeon idea really works
|
interesting read there
|
i always though they just had a ton of horsepower
|
Quote:
|
They got tens of thousands of servers.
|
Quote:
:1orglaugh :1orglaugh :1orglaugh |
wow! google was created by Russian programmist :))
|
Quote:
Crazy you learn shit everyday |
Quote:
|
Quote:
----------------- http://google.com/bsd |
google is one of thise things that as long as it works I dont care how it works
|
Quote:
|
Writing Powerful Programs in C and C++
Using Technologies to avoid slow Hard disk Operations (Big Files) Using Stuff like Lexicon, Word IDs, etc .. Every word found in the document is turned into an integer number (wordID) When somebody searches for "gay seals" it's turned for example into 123 and 653. Then Google looks for all documents matching this two Word IDs. This way they get around SLOW string comparisons .... To rank the site Google uses a Hitlist. For every document found it calculates the IR. If "seals" is for example in Hn tags it's a greater Hit as if it would be in normal P tag ... Then it uses factors like PR, IBLs, anchor text, proximity of keywords and a lots of stuff we do not know to give it the final touch :glugglug This powerful piece of software is than run on 1000 of cheap servers ... :thumbsup Full Paper |
The staff at google are extremely smart. They have more Phd's per square foot there than any institution I can think of.
|
Quote:
|
it's magic
|
Quote:
http://www.cs.rochester.edu/sosp2003...5-ghemawat.pdf If you want to find the others, try searching on Google. |
One of the prime time news magazines showed the Google servers awhile back. They were huge, went down a corridor and were behind chain-link fence.
|
thank you all for the explanation. it makes sense now :thumbsup
|
There servers also use a properiatary filesystem known as GFS which is capable of searching and indexing multiple terabytes of data very effeciently, also developed by the magnificient bastards at google!
|
none the less, its pretty fuckin crazy how then can do that..
|
All times are GMT -7. The time now is 06:56 PM. |
Powered by vBulletin® Version 3.8.8
Copyright ©2000 - 2025, vBulletin Solutions, Inc.
©2000-, AI Media Network Inc123