Thursday, 14 December 2017

Session 2: Performance Modeling and Evaluation of Adaptive Systems:

A Class of Tractable Models for Run-Time Performance Evaluation

Authors:

Giuliano Casale (Imperial College London)
Peter Harrison (Imperial College London)

Abstract:

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.

DOI: 10.1145/2188286.2188299

Full text: PDF

[#][]

Analysis of Bursty Workload-aware Self-adaptive Systems

Authors:

Diego Perez-Palacin (Universidad de Zaragoza)
José Merseguer (Universidad de Zaragoza)
Raffaela Mirandola (Politecnico di Milano)

Abstract:

Software is often embedded in dynamic contexts where it is subjected to high variable, non-stable, and usually bursty workloads. A key requirement for a software system is to be able to self-react to workload changes by adapting its behavior dynamically, to ensure both the correct functionalities and the required performance. Research on fitting variable workload traces into formal models has been carried out using Markovian Modulated Poisson Processes (MMPP). These works concentrate on modeling stable workload states, but accurate modeling of transient times still deserves attention since they are critical moments for the self-adaptation. In this work, we build on research in the area of MMPP trace fitting and we propose a Petri net fine-grained model for highly variable workloads that also accounts for transient times. We analyze differences between models of adaptive software that accurately represent workload state changes and models that do not. We evaluate their performance and availability and compare the results.

DOI: 10.1145/2188286.2188300

Full text: PDF

[#][]

How a Consumer Can Measure Elasticity for Cloud Platforms

Authors:

Sadeka Islam (University of New South Wales)
Kevin Lee (University of New South Wales)
Alan Fekete (University of New Sydney)
Anna Liu (University of New South Wales)

Abstract:

One major benefit claimed for cloud computing is elasticity: the cost to a consumer of computation can grow or shrink with the workload. This paper offers improved ways to quantify the elasticity concept, using data available to the consumer. We define a measure that reflects the financial penalty to a particular consumer, from under-provisioning (leading to unacceptable latency or unmet demand) or overprovisioning (paying more than necessary for the resources needed to support a workload). We have applied several workloads to a public cloud; from our experiments we extract insights into the characteristics of a platform that influence its elasticity. We explore the impact of the rules used to increase or decrease capacity.

DOI: 10.1145/2188286.2188301

Full text: PDF

[#][]

Statistical Detection of QoS Violations Based on CUSUM Control Charts

Authors:

Ayman Amin (Swinburne University of Technology)
Alan Colman (Swinburne University of Technology)
Lars Grunske (University of Kaiserslautern)

Abstract:

Currently software systems operate in highly dynamic contexts, and consequently they have to adapt their behavior in response to changes in their contexts or/and requirements. Existing approaches trigger adaptations after detecting violations in quality of service (QoS) requirements by just comparing observed QoS values to predefined thresholds without any statistical confidence or certainty. These threshold-based adaptation approaches may perform unnecessary adaptations, which can lead to severe shortcomings such as follow-up failures or increased costs. In this paper we introduce a statistical approach based on CUSUM control charts called AuDeQAV - Automated Detection of QoS Attributes Violations. This approach estimates at runtime a current status of the running system, and monitors its QoS attributes and provides early detection of violations in its requirements with a defined level of confidence. This enables timely intervention preventing undesired consequences from the violation or from inappropriate remediation. We validated our approach using a series of experiments and response time datasets from real-world web services.

DOI: 10.1145/2188286.2188302

Full text: PDF

[#][]