Bound analysis of closed queueing networks with workload burstiness

Casale, Giuliano; Mi, Ningfang; Smirni, Evgenia

doi:10.1145/1384529.1375460

Cited by 12 publications

(5 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The CTMC state is a tuple (n, k), where n is the population 2 Notice that a closed PH queueing network might be seen as a specialization of the recently proposed MAP queueing networks [7], which additionally offer the ability to consider service times that are correlated as described by a Markovian arrival process (MAP). However, such models are harder to solve and thus are less appealing for run-time applications.…”

Section: Matrix Geometric Methodsmentioning

confidence: 99%

“…A general methodology based on approximation to G/G/1-queues leads to the queueing network analysis proposed by Whitt [26]. More recently, work has been done in approximating networks in which arrival-or service-processes are represented by correlated Markov-modulated processes [13,25,7,9,8]. Such methods are able to evaluate more expressive models than are studied here, but typically their computational requirements are much larger than the ones we propose 1 .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A class of tractable models for run-time performance evaluation

Casale

Harrison

2012

Proceedings of the 3rd ACM/SPEC International Conference on Performance Engineering

Self Cite

View full text Add to dashboard Cite

Run-time resource allocation requires the availability of system performance models that are both accurate and inexpensive to solve. We here propose a new methodology for run-time performance evaluation based on a class of closed queueing networks. Compared to exponential product-form models, the proposed queueing networks also support the inclusion of resources having first-come first-served scheduling under non-exponential service times. Motivated by the lack of an exact solution for these networks, we propose a fixedpoint algorithm that approximates performance indexes in linear time and linear space with respect to the number of requests considered in the model. Numerical evaluation shows that, compared to simulation, the proposed models solved by fixed-point iteration have errors of about 1% − 6%, while, on the same test cases, exponential product-form models suffer errors even in excess of 100%. Execution times on commodity hardware are of the order of a few seconds or less, making the proposed methodology practical for runtime decision-making.

show abstract

Section: Matrix Geometric Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A class of tractable models for run-time performance evaluation

Casale

Harrison

2012

Proceedings of the 3rd ACM/SPEC International Conference on Performance Engineering

Self Cite

View full text Add to dashboard Cite

show abstract

“…In contrast, service demand burstiness can be seen as the result of serially correlated service demands placed by consecutive requests on a hardware or software system [26,23,21], rather than a feature of the interarrival times between requests. It is much harder to model and predict system performance for workloads with service demand burstiness than for traditional workloads [7]. This stresses the need for benchmarking tools that support analytic and simulation techniques to study the performance impact of service demand burstiness.…”

Section: Related Workmentioning

confidence: 99%

Bap

Rolia

Krishnamurthy

Casale³

et al. 2010

Proceedings of the First Joint WOSP/SIPEW International Conference on Performance Engineering

Self Cite

View full text Add to dashboard Cite

This paper describes our joint research on performance engineering methods for services in shared resource utilities. The techniques support the automated sizing of a customized service instance and the automated creation of performance validation tests for the instance. The performance tests permit fine-grained control over inter-arrival time and service time burstiness to validate sizing and facilitate the development and validation of adaptation policies. Our novel research on sizing also takes into account the impact of workload factors that contribute to such burstiness. The methods are automated, integrated, and exploit an algebraic approach to workload modelling that relies on per-service benchmark suites with benchmarks that can be automatically executed within utilities. The benchmarks and their performance results are reused to support a Benchmarkdriven Algebraic method for the Performance (BAP) engineering of customized services.

show abstract

“…Specifically, we use a new linear programming approach that remains computationally efficient also on models with large populations and large number of servers. An extended version of the work presented here can be found in [1].…”

Section: Introductionmentioning

confidence: 99%

Versatile models of systems using map queueing networks

Casale

Smirni

2008

2008 IEEE International Symposium on Parallel and Distributed Processing

Self Cite

View full text Add to dashboard Cite

Analyzing the performance impact of temporal dependent workloads on hardware and software systems is a challenging task that yet must be addressed to enhance performance of real applications. For instance, existing matrixanalytic queueing models can capture temporal dependence only in systems that can be described by one or two queues, but the capacity planning of real multi-tier architectures requires larger models with arbitrary topology.To address the lack of a proper modeling technique for systems subject to temporal dependent workloads, we introduce a class of closed queueing networks where service times can have non-exponential distribution and accurately approximate temporal dependent features such as short or long range dependence. We describe these service processes using Markovian Arrival Processes (MAPs), which include the popular Markov-Modulated Poisson Processes (MMPPs) as special cases. Using a linear programming approach, we obtain for MAP closed networks tight upper and lower bounds for arbitrary performance indexes (e.g., throughput, response time, utilization). Numerical experiments indicate that our bounds achieve a mean accuracy error of 2% and promote our modeling approach for the accurate performance analysis of real multi-tier architectures.

show abstract

Bound analysis of closed queueing networks with workload burstiness

Cited by 12 publications

References 27 publications

A class of tractable models for run-time performance evaluation

A class of tractable models for run-time performance evaluation

Bap

Versatile models of systems using map queueing networks

Contact Info

Product

Resources

About