A practical approach to dynamic load balancing

Watts, Jerrell; Taylor, Stephen

doi:10.1109/71.674316

Cited by 150 publications

(79 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, this paper uses io q to denote the probability of the task that finishes it services at web server i and leaves the web cluster. From [5], [8], [9], [10], [11], and [12], the traffic equation for the network is given by:…”

Section: This Paper Usesmentioning

confidence: 99%

“…The information theoretic heuristic is analyzed at each decision level thus, decreasing the lower bound for the sub problem. In 1948, a measure of uncertainty of a discrete stochastic system known as entropy was introduced [8], [9], and [14]. For a probability distribution p define on a finite set   n n ,..., 1 ] [  the Shannon entropy of p is defined by with the convention that…”

Section: July 2013mentioning

confidence: 99%

See 1 more Smart Citation

An Analytical Model of Web Server Load Distribution by Applying a Minimum Entropy Strategy

Nandhakwang¹,

Malisuwan²,

Sivaraks³

et al. 2013

IJCCE

View full text Add to dashboard Cite

Abstract-This paper presents an analytical model and the way of simulation for distributing workload on a distributed web server system. The increase in the Internet traffic has also necessitated the conventional Domain Naming Service (DNS) to operate at a much lower efficiency. Among a number of problems associated with the DNS, a key problem has to do with the authoritative DNS not being able to process complete knowledge of the proximity. This makes the authoritative DNS less effective in monitoring server availability and routing incoming requests around failed servers. The workload distribution strategy on the other hand, keeps track of the state and health of the web server. This avoids connection delay due to, for example, a failed server, which can be temporarily by passed by workload distribution. From a modeling standpoint, the conventional DNS assumes equal queue size for each web server in a round-robin setting. Under load balancing, the queue size for each web server differs based on the probability of accessing that server. This probability is based on such factors as the geography, server health, server response, server threshold, session capacities, and the round trip time. In this paper, both conventional and global workload distribution strategies are developed and compared based on a finite set of practical traffic scenarios.Index Terms-Domain name server, entropy, workload distribution strategy, round-robin setting.

show abstract

Section: This Paper Usesmentioning

confidence: 99%

Section: July 2013mentioning

confidence: 99%

An Analytical Model of Web Server Load Distribution by Applying a Minimum Entropy Strategy

Nandhakwang¹,

Malisuwan²,

Sivaraks³

et al. 2013

IJCCE

View full text Add to dashboard Cite

show abstract

“…To construct a fully functional metacomputer, core modules that provide fault tolerance [7,28,35], load balancing, scheduling [9,68], compute engine, security and communications have to be installed, Figure 6. Each of these modules are plugins to a core module called the Backplane.…”

Section: Webcom Architecturementioning

confidence: 99%

WebCom-G: middleware to hide the Grid

Morrison¹,

Power²,

Clayton³

et al. 2006

Grid Technologies

View full text Add to dashboard Cite

Current Grid enabling technologies consist of stand-alone architectures. A typical architecture provides middleware access to various services at different hierarchical levels. Services exposed at these levels may be leveraged by the application programmer. However, the level at which the service appears in the hierarchy determines both its richness and the complexity of its use. Thus, benefits gained by using these services are defined by the manner in which they are accessed. Generally, choosing to use a particular service inclines the application programmer to use the associated middleware suite as it is difficult to cherry-pick services across middlewares. Interoperability and independent service access are not easily facilitated in current middlewares.If it is accepted that Grid computing will be an important technology in the near to long term (indeed it can be credibly argued that it is already a very important technology to a select few), then wide spread acceptance will depend on making that technology easily accessible to general exploitation. In practice, this will not only involve interoperability and inclusiveness of key features, but, most importantly, it will require that non specialists be facilitated in constructing grid independent applications that run efficiently on the dynamic architecture that constitutes the Grid. The original problems of programming parallel and distributed systems still hold true: they are notoriously hard to program, since programmers usually have responsibility for synchronizing processes and for resource management. Solutions must be developed to free programmers from the low level details whose consideration gives rise to these problems. In effect, grid programming environments must evolve to a point where grid (and, in general, parallel) programs are freed from architecture details such as data locality, machine availability, inter-task synchronisation, communication topologies, task load-balancing, and fault tolerance -in the same manner as present day sequential programmers are freed from explicit memory management, disk access protocols and process scheduling. At that point in the evolution of the Grid, the grid middleware will adopt the character of a grid operating system and many, if not all, of the issues that make grid programming difficult will migrate out of grid application programs. When this is achieved, the vision of hiding the Grid will have been realised and exploitation of the technology can begin in earnest.

show abstract

“…There were also studies on dynamic remapping with an objective of lessening the penalty due to synchronization and load imbalances [4], [7], [10], [11], [17], [22], [24], [25], [26], [29]. Dynamic remapping strategies were demonstrated effective when they were applied to solutionadaptive CFD [11], [26], multistage image understanding systems [4], and Monte Carlo dynamical simulations [10], [25].…”

mentioning

confidence: 99%

“…Dynamic remapping strategies were demonstrated effective when they were applied to solutionadaptive CFD [11], [26], multistage image understanding systems [4], and Monte Carlo dynamical simulations [10], [25]. Dynamic remapping was shown to be important for applications that have no inherent synchronization requirements as well [18].…”

mentioning

confidence: 99%

Optimal remapping in dynamic bulk synchronous computations via a stochastic control approach

Yin

Wang

2002

Proceedings 16th International Parallel and Distributed Processing Symposium

View full text Add to dashboard Cite

Abstract-A bulk synchronous computation proceeds in phases that are separated by barrier synchronization. For dynamic bulk synchronous computations that exhibit varying phase-wise computational requirements, remapping at runtime is an effective approach to ensure parallel efficiency. This paper introduces a novel remapping strategy for computations whose workload changes can be modeled as a Markov chain. The use of Markovian model allows us to treat statistical dependence and more complex structure than the usual independent identically distributed random variable assumptions. Our models are quite general and we do not need to impose conditions on the dynamics of the underlying process other than the transition probability matrix. It is shown that optimal remapping can be formulated as a binary decision process: remap or not at a given synchronizing instant. The optimal strategy is then developed for long lasted computations by employing optimal stopping rules in a stochastic control framework. The existence of optimal controls is established. Necessary and sufficient conditions for the optimality are obtained. Furthermore, a policy iteration algorithm is devised to reduce computational complexity and enhance fast convergence to the desired optimal control.

show abstract

A practical approach to dynamic load balancing

Cited by 150 publications

References 27 publications

An Analytical Model of Web Server Load Distribution by Applying a Minimum Entropy Strategy

An Analytical Model of Web Server Load Distribution by Applying a Minimum Entropy Strategy

WebCom-G: middleware to hide the Grid

Optimal remapping in dynamic bulk synchronous computations via a stochastic control approach

Contact Info

Product

Resources

About