Abstract
Many service providers distribute various kinds of content over the Internet. They often use replica servers to provide stable service. To position them appropriately, service providers must predict the demands for their services and provide computing capacity sufficient for servicing the demands. Unfortunately, predicting demands is difficult because demand for a service usually fluctuates. Our research group is developing ExaPeer, an infrastructure that apportions computing capacity to services running on hundreds or thousands of trusted machines all over the Internet. In this paper, we describe ExaPeer's approach to dynamically selecting candidate spots for replica servers. The runtime system in ExaPeer detects fluctuations in demand and then dynamically selects candidate spots on which replica servers should be placed to best meet the demand. Experimental results demonstrate that the candidate spots selected by ExaPeer work better than manually selected ones even if the scale of demand changes rapidly.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS |
| Volume | 1 |
| DOIs | |
| Publication status | Published - 2007 |
| Event | 13th International Conference on Parallel and Distributed Systems, ICPADS - Hsinchu, Taiwan, Province of China Duration: 2007 Dec 5 → 2007 Dec 7 |
Other
| Other | 13th International Conference on Parallel and Distributed Systems, ICPADS |
|---|---|
| Country | Taiwan, Province of China |
| City | Hsinchu |
| Period | 07/12/5 → 07/12/7 |
Fingerprint
ASJC Scopus subject areas
- Engineering(all)
Cite this
Finding candidate spots for replica servers based on demand fluctuation. / Asahara, Masato; Shimada, Akio; Yamada, Hiroshi; Kono, Kenji.
Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS. Vol. 1 2007. 4447737.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Finding candidate spots for replica servers based on demand fluctuation
AU - Asahara, Masato
AU - Shimada, Akio
AU - Yamada, Hiroshi
AU - Kono, Kenji
PY - 2007
Y1 - 2007
N2 - Many service providers distribute various kinds of content over the Internet. They often use replica servers to provide stable service. To position them appropriately, service providers must predict the demands for their services and provide computing capacity sufficient for servicing the demands. Unfortunately, predicting demands is difficult because demand for a service usually fluctuates. Our research group is developing ExaPeer, an infrastructure that apportions computing capacity to services running on hundreds or thousands of trusted machines all over the Internet. In this paper, we describe ExaPeer's approach to dynamically selecting candidate spots for replica servers. The runtime system in ExaPeer detects fluctuations in demand and then dynamically selects candidate spots on which replica servers should be placed to best meet the demand. Experimental results demonstrate that the candidate spots selected by ExaPeer work better than manually selected ones even if the scale of demand changes rapidly.
AB - Many service providers distribute various kinds of content over the Internet. They often use replica servers to provide stable service. To position them appropriately, service providers must predict the demands for their services and provide computing capacity sufficient for servicing the demands. Unfortunately, predicting demands is difficult because demand for a service usually fluctuates. Our research group is developing ExaPeer, an infrastructure that apportions computing capacity to services running on hundreds or thousands of trusted machines all over the Internet. In this paper, we describe ExaPeer's approach to dynamically selecting candidate spots for replica servers. The runtime system in ExaPeer detects fluctuations in demand and then dynamically selects candidate spots on which replica servers should be placed to best meet the demand. Experimental results demonstrate that the candidate spots selected by ExaPeer work better than manually selected ones even if the scale of demand changes rapidly.
UR - http://www.scopus.com/inward/record.url?scp=48049100570&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=48049100570&partnerID=8YFLogxK
U2 - 10.1109/ICPADS.2007.4447737
DO - 10.1109/ICPADS.2007.4447737
M3 - Conference contribution
AN - SCOPUS:48049100570
SN - 9781424418909
VL - 1
BT - Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS
ER -