Performance profiling consists of monitoring a software system during execution and then analyzing the obtained data. There are two ways to collect profiling data: event tracing through code instrumentation and statistical sampling. These two approaches have different advantages and drawbacks. This paper proposes a hybrid approach to data collection that combines the completeness of event tracing with the low cost of statistical sampling. We propose to maximize the weighted amount of information obtained during data collection, show that such maximization can be performed in linear time or is NPhard depending on the data collected and the collection implementation. We propose an approximation algorithm for NP-hard case. Our paper also presents an application of the formal approach to an example use case.

Abstract. The validation of modern software systems on mobile devices needs to incorporate both functional and non-functional requirements. While some progress has been made in validating performance (including power consumption) on current mobile devices, future mobile devices will incorporate multiple processing units, more complex software and hardware that will raise additional challenges. This paper outlines ideas for future directions in performance validation on multicore devices, based on the current work in model-based validation, application state monitoring and performance assertions.

No abstract

No abstract

Assertions have long been used to validate the functionality of software systems. Researchers and practitioners have extended them for validation of non-functional requirements, such as performance. This paper presents the implementation and application of the performance assertions in mobile device software. When applying performance assertions for such systems, we have discovered and resolved a number of issues in assertion specification, matching, and evaluation that were unresolved in previous research. The paper describes a simple, but effective framework geared towards mobile devices that allows specification and validation of real world performance requirements.