On evaluating request-distribution schemes for saving energy in server clusters

被引:61
作者
Rajamani, K
Lefurgy, C
机构
来源
ISPASS: 2003 IEEE INTERNATIONAL SYMPOSIUM ON PERFORMANCE ANALYSIS OF SYSTEMS AND SOFTWARE | 2003年
关键词
D O I
10.1109/ISPASS.2003.1190238
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Power-performance optimization is a relatively new problem area particularly in the context of server clusters. Power-aware request distribution is a method of scheduling service requests among servers in a cluster so that energy consumption is minimized, while maintaining a particular level of performance. Energy efficiency is obtained by powering down some servers when the desired quality of service can be met with fewer servers. We have found that it is critical to take into account the system and workload factors during both the design and the evaluation of such request distribution schemes. We identify the key system and workload factors that impact such policies and their effectiveness in saving energy. We measure a web cluster running an industry-standard commercial web workload to demonstrate that understanding this system-workload context is critical to performing valid evaluations and even for improving the energy-saving schemes.
引用
收藏
页码:111 / 122
页数:12
相关论文
共 25 条
[1]  
AMZA C, 2002, 5 ANN IEEE INT WORKS
[2]  
[Anonymous], P 18 S OP SYST PRINC
[3]  
[Anonymous], 2001, WORKSH COMP OP SYST
[4]  
*AP SOFT FDN, AP HTTP SERV
[5]  
*APC COMM CONN, APC ALT PHP CACH
[6]  
APPLEBY K, 2001, P 7 IFIP IEEE INT S
[7]  
BOHRER P, 2002, POWER AWARE COMPUTIN
[8]  
BUYUKTOSUNOGLU A, 2001, LECT NOTES COMPUTER, V2008
[9]  
CREDLE R, 2002, CUTTING EDGE IBM ESE
[10]  
DHODAPKAR A, 2002, P 29 INT S COMP ARCH