Past Details

Self-Tuning Hadoop for Big Data Analytics

Date / Time:
24/02/2014 Download ICS File
Location:
Carnegie Mellon Qatar, room 1202
Category:
Lectures and Activities
QCRI-Logo-new-2016.jpg Dr. Ashraf Aboulnaga is a Principal Scientist in the Qatar Computing Research Institute, where he heads the Distributed Systems group. His current research interests are in the area of data intensive cloud computing, with a current focus on platforms for Big Data, distributed storage systems, and data integration on the web. Dr. Aboulnaga obtained M.S. and Ph.D. degrees from the University of Wisconsin - Madison, and B.S. and M.S. degrees from Alexandria University, Egypt. He holds an Associate Professor position at the University of Waterloo in Canada, where he has worked since 2004.


Hadoop has become one of the most popular platforms for Big Data analytics, enabling flexible and powerful analysis of massive data sets on commodity computing clusters. However, tuning and administering Hadoop clusters is still not a well-studied area. In this talk, I will present two projects that aim to make Hadoop more self-tuning. The first is ReStore, a system for reusing MapReduce results. ReStore focuses on queries that are expressed in high-level query languages such as Pig Latin or Hive. The compilers of these languages translate queries into workflows of MapReduce jobs. Each job in these workflows reads its input from the Hadoop file system (HDFS) and produces output that is stored in HDFS.  The current practice is to delete all intermediate results from HDFS at the end of executing the workflow. ReStore keeps these intermediate results and reuses them for future queries, resulting in significant performance improvement. I will also present PStorM, a system for tuning Hadoop configuration parameters based on the history of previously observed MapReduce jobs. The two projects presented in the talk share the goal of automatically improving the performance of Hadoop based on workload characteristics.

Follow Us

  • YouTube
  • Twitter
  • Facebook
  • RSS Feed
  • Linkedin
  • github-web.png
Back to Top

In the Media

BBC newshack pic.jpg

QCRI team wins SUMMA BBC #NewsHack 'Best Audience Experience' prize

13/12/2017

Congratulations to Ahmed Ali, Yifan Zhang and Fahim Dalvi for winning the prize of the “Best Audience Experience” category at the news hack hosted by SUMMA and BBC in London on 21-22 November with ...

Read More

Neural networks MIT.jpg

Reading a neural network’s mind

12/12/2017

Neural networks, which learn to perform computational tasks by analyzing huge sets of training data, have been responsible for the most impressive recent advances in artificial intelligence, ...

Read More

CSAIl image october 2017 story.JPG

CSAIL hosts annual meeting highlighting innovative collaboration with QCRI

10/10/2017

This year CSAIL celebrates five years of collaboration with the Qatar Computing Research Institute (QCRI), an esteemed research institute that’s part of Hamad Bin Khalifa University in Doha. This ...

Read More

Events

2017

after school pic.JPG

QCRI's Creative Space launches free after-school computing courses for teenagers

Download ICS File 01/11/2017  - 20/12/2018 ,

We offer an App Inventor Course in Arabic for students aged 13-15 and an Arduino Programming Course in English for students aged 14-18. Courses are free. Please register quickly as places are limited.

Read More

Past Events

Summer Camp 2.jpg

QCRI conducts first summer computing camps for kids

Download ICS File 16/07/2017  - 27/07/2017 ,

Children and teenagers have been given a rare chance to develop their computing skills with world-class computing scientists at the first summer computing camp conducted by the Qatar Computing ...

Read More

CS 1.jpg

QCRI’s Creative Space holds Open House event for kids

Download ICS File 20/05/2017 ,

The Qatar Computing Research Institute’s new Creative Space, which conducts fun activities to teach children computing skills, has successfully held its first Open House event. About 100 children ...

Read More

News

Jim Jansen pic preferred.jpg

Research by QCRI's Jim Jansen among most influential of decade: top journals

13/12/2017

QCRI Social Computing group's principal scientist achieves rare honor.

Read More

yelena pic.JPG

#Halal now a lifestyle definition on Instagram

29/11/2017

The word “halal” is no longer being defined only in a religious context but is becoming a lifestyle term associated with health and fashion around the globe, a new study of Instagram posts led by ...

Read More

Dr. Mokbel.jpg

QCRI’s Mohamed Mokbel named Distinguished Scientist by world’s largest computing society ACM

21/11/2017

Chief scientist among only 43 scientists globally - and the only one from the Middle East - to be selected for the honor in 2017.

Read More