Feeds

Yahoo! invites world of boffins into 4,000-node Hadoop cluster

Hello! Yahoo! is! a! tech! company!

Choosing a cloud hosting partner with confidence

Yahoo! has opened up its Hadoop research cluster to computer science boffins at four additional US universities, including Stanford, the University of Washington, the University of Michigan, and Purdue.

The company's M45 cluster — a Hadoop setup spanning 4,000 processors and 1.5-petabyte of disk space inside a data center at Yahoo!'s Sunnyvale headquarters —– was originally launched in 2007, and is now available for Big Data research at eight universities across the country. Other participants include founding member Carnegie Mellon, plus the The University of California at Berkeley, Cornell University, and the University of Massachusetts at Amherst.

Speaking with The Reg, Thomas Kwan, director of research operations for Yahoo! Research, reaffirmed the company's commitment to Hadoop research, saying that the M45 continues not only to drive development of the open source distributed number-crunching platform, but to serve as a means of educating future Yahoo! employees.

Though the M45 is a godsend for Big Data boffins, it's a rather large inconvenience for the mainstream media, which insists on telling the world that Yahoo! is not a tech company. It can be difficult to explain why a non-tech company is funding a 4,000-processor and 1.5-petabyte data cluster that crunches epic amounts of data using an open source distributed-computing platform that now underpins everything from Facebook to Twitter to a portion of Microsoft Bing.

Hadoop — whose development was largely driven by Yahoo! — is based on the GFS and MapReduce distributed-computing platforms developed at Google. In 2004, Mountain View published a pair of papers on these technologies, and soon, Doug Cutting — known previously for developing Lucene, the open-source retrieval library — used them to start an open source shadow project. He called it Hadoop after his son's stuffed elephant.

Today, the M45 drives such projects as the Carnegie Mellon natural language–processing system known as NELL (Never Ending Language Learning System) and the University of Washington's sweeping knowledge database project KnowItAll. The cluster is only available to universities. ®

Security for virtualized datacentres

More from The Register

next story
It's Big, it's Blue... it's simply FABLESS! IBM's chip-free future
Or why the reversal of globalisation ain't gonna 'appen
'Hmm, why CAN'T I run a water pipe through that rack of media servers?'
Leaving Las Vegas for Armenia kludging and Dubai dune bashing
Bitcasa bins $10-a-month Infinite storage offer
Firm cites 'low demand' plus 'abusers'
Facebook slurps 'paste sites' for STOLEN passwords, sprinkles on hash and salt
Zuck's ad empire DOESN'T see details in plain text. Phew!
CAGE MATCH: Microsoft, Dell open co-located bit barns in Oz
Whole new species of XaaS spawning in the antipodes
Microsoft and Dell’s cloud in a box: Instant Azure for the data centre
A less painful way to run Microsoft’s private cloud
AWS pulls desktop-as-a-service from the PC
Support for PCoIP protocol means zero clients can run cloudy desktops
prev story

Whitepapers

Why cloud backup?
Combining the latest advancements in disk-based backup with secure, integrated, cloud technologies offer organizations fast and assured recovery of their critical enterprise data.
A strategic approach to identity relationship management
ForgeRock commissioned Forrester to evaluate companies’ IAM practices and requirements when it comes to customer-facing scenarios versus employee-facing ones.
Security for virtualized datacentres
Legacy security solutions are inefficient due to the architectural differences between physical and virtual environments.
Reg Reader Research: SaaS based Email and Office Productivity Tools
Read this Reg reader report which provides advice and guidance for SMBs towards the use of SaaS based email and Office productivity tools.
New hybrid storage solutions
Tackling data challenges through emerging hybrid storage solutions that enable optimum database performance whilst managing costs and increasingly large data stores.