15-440 - Distributed Systems

Home Syllabus Schedule Lectures Assignments Projects Exams Resources

Project 4: Maximizing Data Locality in Hadoop Clusters via Controlled Reduce Task Scheduling

Interim Design Report: Not Required

Final Project Due Date: 13 Dec 2011, by 11:59pm

• Project description can be found in Project 4 Handout.
• All required code and scripts will be integrated into your VM clusters.

Useful References:

• Apache Hadoop
• Hadoop 0.20 API documentation