Authors:
Michel Albonico
and
Paulo Varela
Affiliation:
Federal Technological University - Paraná, Francisco Beltrão and Brazil
Keyword(s):
Cloud Computing, Elasticity, Combinatorial Testing, Small Test Sequences, Performance Testing.
Abstract:
Elasticity is one of the main features of cloud-based systems (CBS), helping them to meet performance requirements under a varying workload. Given the great number of combinations among workload and elastic adaptation parameters, assessing their effect on CBS performance may be prohibitive. Existing systematic combinatorial testing approaches can help to reduce such combinations, though most of them only consider conventional software architectures. In the literature, we only find a single work on elastic CBS combinatorial testing, presented by some of the authors. However, the paper only presents experimental results on 2-wise elasticity parameter interactions and shallowly explores the performance issue causes. In this paper, we lead a further experiment by using our previous approach to generate performance test cases that cover three elasticity parameter interactions (i. e., 3-wise), one interaction longer than on the previous paper. Despite the significant increase in execution
time and cost, new experimental results do not reveal any new critical performance issue by 3-wise, which enforces the acceptance of 2-wise elasticity parameter interactions.
(More)