Optimal Server Allocation and Frequency Modulation on Multi-Core Based Server Clusters

Optimal Server Allocation and Frequency Modulation on Multi-Core Based Server Clusters

Xinying Zheng (Michigan Technological University, USA) and Yu Cai (Michigan Technological University, USA)
Copyright: © 2013 |Pages: 13
DOI: 10.4018/978-1-4666-2646-1.ch021
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

Multi-core processing has been widely used in high-performance computing systems. Power reduction and energy conservation are important in these systems to minimize operating cost. Two main strategies exist for power management: Dynamic Voltage/Frequency Scaling (DV/FS) and server number controlling: Vary-On Vary-Off (VOVF). In this paper, the authors explore the benefits of DV/FS and VOVF and apply them in a multi-core based server cluster. An optimization problem is formulated to get the optimal resource scheduling strategy given a parallel workload. The presented optimization model provides controllable and quantitative power consumption with theoretically guaranteed service performance. The authors further study the overhead of the proposed scheme and provide a Double Control Periods (DCP) method to compensate the transition overhead. The power optimization model is evaluated via extensive simulations. It is also justified by the real workload data trace. The results prove the effectiveness and efficiency of the proposed model.
Chapter Preview
Top

In recent years, power management has become one of the most important concerns on server clusters. Many previous work achieves energy saving by dynamically adjust processors’ frequency and voltage. Researchers have developed various DV/FS scheduling algorithms to save energy under timing deadlines (Vasic et al., 2008; Pinheiro et al., 2001). VOVF is a major policy applied in server clusters (Fan et al., 2007; Guerra et al., 2008; Sharma et al., 2005). In (Niyato, Chaisiri, & Sung, 2009), researchers constructed a constraint Markov model to adjust server numbers according to transition probability. In (Nedevschi et al., 2008), the authors proposed a method to reduce network energy consumption via sleeping and rate adaptation via combining VOVF and DV/FS. Combining DV/FS and VOVF potentially provide higher energy saving.

Complete Chapter List

Search this Book:
Reset