Joseph L. Hellerstein - Integrating Job Management and Machine Management in Google Data Centers

13:00

Thursday

Jan

2012

Keynote Speech

Place:

Campus - ENSIMAG - Amphi E

Organized by:

L’équipe "Keynotes" du LIG

Speaker:

Joseph L. Hellerstein

Keywords:

Calcul pour les sciences et technologies Systèmes répartis
Algorithmique répartie
Evaluation de performances

- Biography of Joseph L. Hellerstein, Google, USA

Joseph L Hellerstein received his undergraduate degree from the University of Michigan in Ann Arbor, and his M.S. and Ph.D. in Computer Science from the University of California at Los Angeles.

From 1984 through 2006, he was Researcher and Senior Manager at the IBM Thomas J. Watson Research Center in Hawthorne, New York, where he founded the Adaptive Systems Department, and received an Outstanding Technical Achievement Award for contributing feedback control technologies to IBM products.

From 2006 to 2008, he was Principal Architect at Microsoft Developer Division where he developed scheduling optimizations for .NET.

Since 2008, he has been with Google, Inc. leading projects that optimize Google’s distributed operating system and storage infrastructure. Dr. Hellerstein has published over 100 peer-reviewed publications, and has taught at Columbia University and the University of Washington. He received the IEEE/IFIP Stokesberry Award for outstanding contributions to the network management community (2007), and is a Fellow of the IEEE.

- See also
— His web site
— All the LIG Keynotes

In cloud based services, many jobs run for months. This is a time frame that is on the order of machine lifetimes. As a result, scheduling the administration of machines (e.g., repairs, adding new machines, draining machines) must be integrated with scheduling jobs. At Google, we approach this problem by using an abstraction called shapes to describe both machines and jobs. I will discuss the shapes abstraction, and I will also describe optimization problems that we solve using shapes.