Abstract
We consider a parallel-server system with K homogeneous servers where incoming tasks, arriving at rate λ, are dispatched by n dispatchers. Servers are FCFS queues and dispatchers implement a size-based policy such that the servers are equally loaded. We compare the performance of a system with n> 1 dispatchers and of a system with a single dispatcher. Every dispatcher handles a fraction 1/n of the incoming traffic and balances the load to K/n servers. We show that the performance of a system with n dispatchers, K servers and arrival rate λ coincides with that of a system with one dispatcher, K/n servers and arrival rate λ/n. Therefore, the performance comparison can be interpreted as the economies of scale in a system with one dispatcher when we scale up the number of servers and the arrival rate proportionately. We consider two continuous service time distributions: uniform and Bounded Pareto that have increasing and decreasing failure rates, respectively; and a discrete distribution with two values, which is the distribution that maximizes the variance for a given mean. We show that the performance degradation is small for uniformly distributed job sizes, but that for Bounded Pareto and two points distributions it can be unbounded.
Original language | English |
---|---|
Title of host publication | IEEE Conference on Computer Communications |
Subtitle of host publication | Proceedings : IEEE INFOCOM |
Publisher | IEEE |
Pages | 1350-1358 |
Number of pages | 9 |
ISBN (Electronic) | 978-1-5090-5336-0 |
DOIs | |
Publication status | Published - 2017 |
MoE publication type | A4 Conference publication |
Event | IEEE Conference on Computer Communications - Atlanta, United States Duration: 1 May 2017 → 4 May 2017 http://infocom2017.ieee-infocom.org/ |
Publication series
Name | IEEE Conference on Computer Communications |
---|---|
ISSN (Print) | 0743-166X |
Conference
Conference | IEEE Conference on Computer Communications |
---|---|
Abbreviated title | INFOCOM |
Country/Territory | United States |
City | Atlanta |
Period | 01/05/2017 → 04/05/2017 |
Internet address |