5. W-1-W
•WebMap : Graph processing for WWW
•Dreadnaught: Infrastructure for WebMap
•W-1-W:WebMap In One Week
•Juggernaut: Infrastructure for W-1-W
•JFS, JMR, Condor:Abandoned for Hadoop
8. Hadoop Future in 2006:
Hadoop will helpYahoo!
win Search Engine Wars
9. Lessons Learned
•Multi-Tenancy from ground-up
•Agility in lieu of Performance
•Provisioning vs Procurement
•“Weird” use cases as learning experience
•Academic collaboration
20. IAAS: New Hardware
•Public:AWS, Google Cloud,Azure
•Private: vSphere, OpenStack
•Easy Provisioning
•Scalable, Elastic, Ubiquitous
•Bundled with Data & Analytics as Services
21. Cloud Data Fabric
•Store massive & diverse data sets
economically
•Integrate and Ingest from legacy & disparate
sources
•Ability to rapidly analyze massive data sets
•Control,Auditing, Manageability, Self-Service
•Object Stores
27. So,“Big” Data is Still
Important in AI World,
So why *NOT*
Hadoop?
28. Back to the Future 2018:
What is Hadoop?
Hadoop is the OSS
Reference Implementation
of APIs for managing
distributed AI workloads
and their access to large
datasets.