<<< Date Index >>>     <<< Thread Index >>>

[IP] more on on Google? Vital statistics




Delivered-To: dfarber+@xxxxxxxxxxxxxxxxxx
Date: Sun, 02 May 2004 07:42:41 -0700 (PDT)
From: Joseph Lorenzo Hall <jhall@xxxxxxxxxxxxxxxxx>
Subject: Re: [IP] What can't you find on Google? Vital statistics
To: Dave Farber <dave@xxxxxxxxxx>


Here's a great back-of-the-envelope calculation by Tristan Louis of
just how many servers are in the Google farm using their hardware
expenditures from Google's S-1 filing:

----
http://www.tnl.net/blog/entry/How_many_Google_machines

# How many Google machines

## April 30, 2004

An interesting tidbit coming out of the [Google S-1 filing][1] is that
they have spent about $250 million on hardware equipment. From there,
we can get a few guesses at the magnitude of the Google system. Based
on quick back of the envelope calculations, it looks like Google is
managing between 45,000 and 80,000 servers. Here's how I arrived at
this conclusion:

According to calculations by the IEE, in [a paper about the Google
cluster][2], a rack with 88 dual-CPU machines used to cost about
$278,000. If you divide the $250 million figure from the S-1 filing by
$278,000, you end up with a bit over 899 racks. Assuming that each
rack holds 88 machines, you end up with 79,000 machines.

However, one must recognize that equipment is not all CPUs. As a
result, you must discount the figure of $250 million to account for
routers, firewalls, machines for employees, etc... So let's assume for
a minute that only about $200 million is going to the CPUs. That still
leaves us with 719 racks or a bit over 63,000 machines.

Even if we discount other equipment to be costing $100 million, we end
up with a bit over 47,000 machines on 539 racks.

So how much processing power is that? Well, once again, the Google
cluster document provides some interesting tidbits. Per the document,
the racks that were used were

> 88 dual-CPU 2Ghz Intel Xeon servers with 2 Gbytes of RAM and an
  80-Gbyte hard disk.

That means that, on the low end, the Google cluster has the following stats:

  * 539 racks
  * 47,432 machines
  * 94,864 CPUs
  * 189,728 Ghz of processing power
  * 94,864 Gb of RAM
  * 3,705 Tb of Hard Drive space


In the middle range of my estimates, the cluster would have:

  * 719 racks
  * 63,262 machines
  * 126,544 CPUs
  * 253,088 Ghz of processing power
  * 126,544 Gb of RAM
  * 4,943 Tb of Hard Drive space


And on the high end of my estimates:

  * 899 racks
  * 79,112 machines
  * 158,224 CPUs
  * 316,448 Ghz of processing power
  * 158,224 Gb of RAM
  * 6,180 Tb of Hard Drive space

Assuming that the 1Ghz chip is going at about a third the gigaflops of
a 2Ghz processor ([3.3Gflops][3]), we can then guess at the size of
the Google supercomputer. Just for the sake of argument, let's go with
1 Gigaflop per processor. This means that the Google supercomputer has
about 189 teraflops of power on the low end of my estimates, 253
teraflops on the middle end, and 316 teraflops on the high end. This
would easily put it on top of [the list of fastest computers in the
world][4].

Any way you slice it, that's a lot of power.

[1]: http://www.tnl.net/blog/entry/Google_files_S-1 (TNL.net: Google Files S-1) [2]: http://www.computer.org/micro/mi2003/m2022.pdf (Web Search for a planet - the google cluster architecture) [3]: http://softwareforums.intel.com/ids/board/message?board.id=IPP&&amp;message.id=31&&amp;jump=true (Intel Forums: poor performance of intel microcode) [4]: http://seattlepi.nwsource.com/local/136634_computer26.html (Seattle PI: 11.8-teraflop computer powers up)


------------------------------------------------------------------------
Joseph Lorenzo Hall,                      SIMS PhD Student; UC Berkeley.
[web:<http://pobox.com/~joehall/>, blog:<http://pobox.com/~joehall/nqb>]

"Always put 'property' in quotes... never give it to them."
--Rick Prelinger, Archivist. <http://www.archive.org/movies/>

This email is formatted for [Markdown][].
[markdown]: http://daringfireball.net/projects/markdown

-------------------------------------
You are subscribed as roessler@xxxxxxxxxxxxxxxxxx
To manage your subscription, go to
 http://v2.listbox.com/member/?listname=ip

Archives at: http://www.interesting-people.org/archives/interesting-people/