S. Zhou, J. Wang, X. Zheng and P. Delisle. UTOPIA: a load-sharing facility for large heterogenous distributed computing systems. Software-Practive and Experience, 23(2):1305-1336, 1993.  Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
EquiLoad: a load balancing policy for clustered web servers - Ciardo, Riska, Smirni (2001) (1 citation) (Correct)
....with probability 1=N . We also compare EquiLoad with the Shortest Remaining Processing Time (SRPT) policy, which has been shown to handle well both highly variable workload and heavy overall system load, and the Join Shortest Queue (JSQ) policy, which handles the load of the system reasonably well [29, 30]. We demonstrate that EquiLoad is, by its nature, a good choice to maximize cache hits at the back end servers and compare its performance with LARD [23] a locality aware load balancing policy in clustered web servers. We conclude this section by commenting on the sensitivity of EquiLoad to the ....
....request in all servers of the cluster. JSQ assigns each incoming request to the server with the shortest queue. In this policy, the front end dispatcher must know only the size of the waiting queue for each server in the cluster. In a distributed environment, this policy handles system load well [29, 30]. For presentation clarity, the x axis of Figure 8(b) shows only the value of the b parameter of the lognormal distribution for the workload but we remind the reader that a di erent value of b implies also a di erent value of a, to keep the same mean task size across all workloads. highest ....
S. Zhou, J. Wang, X. Zheng and P. Delisle. UTOPIA: a load-sharing facility for large heterogenous distributed computing systems. Software-Practive and Experience, 23(2):1305-1336, 1993.
EquiLoad: a load balancing policy for clustered web servers - Ciardo, Riska, Smirni (2001) (1 citation) (Correct)
....with probability 1=N . We also compare EquiLoad with the Shortest Remaining Processing Time (SRPT) policy, which has been shown to handle well both highly variable workload and heavy overall system load, and the Join Shortest Queue (JSQ) policy, which handles the load of the system reasonably well [29, 30]. We demonstrate that EquiLoad is, by its nature, a good choice to maximize cache hits at the back end servers and compare its performance with LARD [23] a locality aware load balancing policy in clustered web servers. We conclude this section by commenting on the sensitivity of EquiLoad to the ....
....request in all servers of the cluster. JSQ assigns each incoming request to the server with the shortest queue. In this policy, the front end dispatcher must know only the size of the waiting queue for each server in the cluster. In a distributed environment, this policy handles system load well [29, 30]. 4 For presentation clarity, the x axis of Figure 8(b) shows only the value of the b parameter of the lognormal distribution for the workload but we remind the reader that a di erent value of b implies also a di erent value of a, to keep the same mean task size across all workloads. 16 ....
S. Zhou, J. Wang, X. Zheng and P. Delisle. UTOPIA: a load-sharing facility for large heterogenous distributed computing systems. Software-Practive and Experience, 23(2):1305-1336, 1993. 25
A Case for NOW (Networks of Workstations) - Anderson, Culler, Patterson, team (1994) (65 citations) (Correct)
No context found.
S. Zhou, J. Wang, X. Zheng, and P. Delisle, "Utopia: A Load Sharing Facility for Large, Heterogenous Distributed Computing Systems," Technical Report CSRI-257, University of Toronto, 1992.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC