2006 27th IEEE International Real-Time Systems Symposium (RTSS'06) 2006
DOI: 10.1109/rtss.2006.20
|View full text |Cite
|
Sign up to set email alerts
|

Distributed Utilization Control for Real-Time Clusters with Load Balancing

Abstract: Recent years have seen rapid growth of online services that rely on large-scale server clusters to handle high volume of requests. Such clusters must adaptively control the CPU utilizations of many processors in order to maintain desired soft real-time performance and prevent system overload in face of unpredictable workloads. This paper presents DUC-LB, a novel distributed utilization control algorithm for cluster-based soft real-time applications. Compared to earlier works on utilization control, a distingui… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
18
0

Year Published

2008
2008
2016
2016

Publication Types

Select...
9

Relationship

1
8

Authors

Journals

citations
Cited by 30 publications
(18 citation statements)
references
References 32 publications
0
18
0
Order By: Relevance
“…Wang et al in [67] developed a real-time utilization control middleware, which adopts task rate adaptation to handle variations in application workload and system resources. Fu et al in [22] focused on clusterbased soft real-time applications, and developed a utilization control algorithm DUC-LB for large-scale server clusters. Koutsoukos et al in [38] considered a scenario where control variables are discrete.…”
Section: Other Control and Optimization Approaches In Real-time Embedmentioning
confidence: 99%
“…Wang et al in [67] developed a real-time utilization control middleware, which adopts task rate adaptation to handle variations in application workload and system resources. Fu et al in [22] focused on clusterbased soft real-time applications, and developed a utilization control algorithm DUC-LB for large-scale server clusters. Koutsoukos et al in [38] considered a scenario where control variables are discrete.…”
Section: Other Control and Optimization Approaches In Real-time Embedmentioning
confidence: 99%
“… Supposing free flow, besides S=1, E=1, u=1, α=1, β=1, Δt=1 the equation regarding to the transmitted vehicle length will be constructed, in such way the vehicle lengths regarding to 1 sec will be determined.  The velocity-density function will be selected, in this case it is the linear function (but it can be other function, if required)  The equation (11) will be solved with (12).  Fig.…”
Section: E 5 ]mentioning
confidence: 99%
“…These models are used to describe the multitude in different systems, for example, in traffic systems, that manage the flow of cars on the road, or the flow of aircrafts in the airspace in that the control is performed with groups of computers Fu, Y. et al, (2006).…”
Section: Introductionmentioning
confidence: 99%
“…To the best of our knowledge there is no prior control theoretic work that deals with balancing the execution of partitioned query tasks in volatile settings; however an interesting approach to enforcing desired utilization set points under a range of dynamic workloads with the help of a controller appears in [Fu et al 2006], where the methodology adopted is based on diffusive load balancing. In a different setting, cost-aware load balancing has been investigated in [Birdwell et al 2006], as well.…”
Section: ·mentioning
confidence: 99%