Title
DTS: Using Dynamic Time-Slice Scaling to Address the OS Problem Incurred by DVFS
Abstract
Dynamic voltage and frequency scaling (DVFS) has been the most useful technology to reduce power consumption, but it causes unpredictable program performance decreasing and unfair performance sharing among threads, which may render performance analysis, optimization, and isolation extremely difficult and lead to thread starvation and priority inversion. This paper firstly proposes an OS scheduler based on dynamic time-slice scaling (DTS) to address the OS problem incurred by DVFS. The DTS scheduler dynamically allocates each thread with a time-slice according to threads' behavior characteristic and processor's frequency. There are two main contributions: 1) this paper is the first work to analyze and address the OS problems incurred by DVFS, 2) we firstly allocate threads' time-slice according to threads' behavior characteristic and processor's frequency. Experimental results demonstrate our DTS scheduler can well solve most OS problems incurred by DVFS with little cost, and at the same time DTS improves system performance.
Year
DOI
Venue
2012
10.1109/ClusterW.2012.12
CLUSTER Workshops
Keywords
Field
DocType
optimisation,time dts,power aware computing,unpredictable program performance,scheduling,power consumption,dynamic voltage and frequency scaling,microprocessor chips,threads' behavior characteristic,dts scheduler dynamically,dts scheduler,system performance,os problem,unfair sharing,unfair performance sharing,unpredictable performance decreasing,optimization,os scheduler,dvfs,behavior characteristic,performance evaluation,dynamic time-slice scaling,performance analysis,dynamic time-slice
Preemption,Scheduling (computing),Computer science,Voltage,Parallel computing,Thread (computing),Real-time computing,Priority inversion,Frequency scaling,Scaling,Power consumption,Embedded system
Conference
ISBN
Citations 
PageRank 
978-1-4673-2893-7
1
0.36
References 
Authors
0
5
Name
Order
Citations
PageRank
Gangyong Jia115024.20
Xuhong Gao220.74
Xi Li320236.61
Chao Wang4352.86
Xuehai Zhou555177.54