35,000 Core Ubuntu Server Farm at Weta Digital

By | 2010/01/20

I just read an article over at Dustin Kirkland’s blog regarding the enormous server farm that Weta Digital has setup to render blockbuster movies. Apparently the latest Blockbuster, Avatar, had scenes rendered using a 35,000 core Ubuntu-based server farm. 35,000! That is hard to imagine! They’ve also rendered a few other films you may have heard of:

  • Avatar
  • District 9
  • The Day the Earth Stood Still
  • King Kong
  • Jumper
  • Lord of the Rings
  • Fantastic Four
  • i-Robot
  • X-Men
  • Eragon

It is amazing to think that in just a few short years Ubuntu has gained such a reputation that it would be used for such high-end commercial services.

A few years ago I did a talk at a local conference regarding Ubuntu in the Enterprise. Sadly, at the time, it was very hard to find any real solid documentation regarding large businesses using Ubuntu day-to-day. Sure it had crept onto some corporate desktops, but it was very hard to find it elsewhere. Now, we have stories like this and I’m sure this is just the tip of the iceberg!

What other companies do you know that run Ubuntu in production? I’m sure many of us would be interested to find out where else it is being used.

(Note: more details and links regarding Weta Digital and the source of this data at Dustin’s blog.)

2 thoughts on “35,000 Core Ubuntu Server Farm at Weta Digital

  1. Pete Lundin

    ith that amount of server power running, I hope the studios consider energy saving and environmental issues a top priority. Siting is definitely one of the most important factors that affect the energy consumption and environmental effects of a server farm. There are places with cooler climates than in the continental US and with more green electricity available. I would recommend anybody considering siting a datacenter to take a look at the Finnish website on these issues: http://www.fincloud.freehostingcloud.com/

    Reply

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.