DATE: Thursday, September 1, 2011
TIME: 12:00 pm - 1:00 pm
PLACE: Gates 8102

SPEAKER: Anshul Gandhi, CMU

TITLE: AutoScale: Dynamic Power Management for Multi-Tier Data Centers

ABSTRACT:
Energy costs for data centers continue to double every 5 years, already exceeding $15 billion yearly. Sadly much of this power is wasted. Servers are only busy 10-30%, but they are often left on, while idle, utilizing 60% or more of peak power when in the idle state.

We introduce a power management algorithm, AutoScale, that greatly reduces power costs in data centers driven by unpredictable, time- varying load, while meeting response time SLAs. AutoScale scales the data center capacity, turning servers on and off as needed.

We evaluate our power-management approach via implementation on a 38- server multi-tier data center, serving a web site of the type seen in Facebook or Amazon, with a key-value store workload. We find that AutoScale improves upon the current static power management used in data centers by up to 50% with respect to power, and furthermore, vastly improves upon existing dynamic power management policies with respect to meeting SLAs and robustness.

BIO:
Anshul Gandhi is a Ph.D. student in the Computer Science Department at Carnegie Mellon University, under the direction of Mor Harchol-Balter. His research involves designing and implementing power management policies for datacenters as well as general performance modeling of computer systems.

SDI / ISTC Seminar Questions?
Karen Lindenfelser, 86716, or visit www.pdl.cmu.edu/SDI/