Derek Rayside

Object ownership profiling: a technique for finding and fixing memory leaks

We introduce object ownership profiling, a technique forfinding and fixing memory leaks in object-oriented programs. Object ownership profiling is the first memory profiling technique that reports both a hierarchy of allocated objects along with size and time information aggregated up that hierarchy. In addition, it reveals the cross-hierarchy interactions that areessential to pinpointing the source of the leak. We identify five memory management anti-patterns, including two that involve rich heap structure and object interactions, and are novel contributions of this work. We apply object ownership profiling to find and fix memory leaks in the Alloy IDE v3 that users had complained about for years, and that had eluded detection by code reviews and type-based commercial memory profilers.

Unifying execution of imperative and declarative code

We present a unified environment for running declarative specifications in the context of an imperative object-Oriented programming language. Specifications are Alloy-like, written in first-order relational logic with transitive closure, and the imperative language is Java. By being able to mix imperative code with executable declarative specifications, the user can easily express constraint problems in place, i.e., in terms of the existing data structures and objects on the heap. After a solution is found, the heap is updated to reflect the solution, so the user can continue to manipulate the program heap in the usual imperative way. We show that this approach is not only convenient, but, for certain problems can also outperform a standard imperative implementation. We also present an optimization technique that allowed us to run our tool on heaps with almost 2000 objects.

Visualization and exploration of optimal variants in product line engineering

The decision-making process in Product Line Engineering (PLE) is often concerned with variant qualities such as cost, battery life, or security. Pareto-optimal variants, with respect to a set of objectives such as minimizing a variants cost while maximizing battery life and security, are variants in which no single quality can be improved without sacrificing other qualities. We propose a novel method and a tool for visualization and exploration of a multi-dimensional space of optimal variants (i.e., a Pareto front). The visualization method is an integrated, interactive, and synchronized set of complementary views onto a Pareto front specifically designed to support PLE scenarios, including: understanding differences among variants and their positioning with respect to quality dimensions; solving trade-offs; selecting the most desirable variants; and understanding the impact of changes during product line evolution on a variants qualities. We present an initial experimental evaluation showing that the visualization method is a good basis for supporting these PLE scenarios.

Comparison of exact and approximate multi-objective optimization for software product lines

Software product lines (SPLs) allow stakeholders to manage product variants in a systematical way and derive variants by selecting features. Finding a desirable variant is often difficult, due to the huge configuration space and usually conflicting objectives (e.g., lower cost and higher performance). This scenario can be characterized as a multi-objective optimization problem applied to SPLs. We address the problem using an exact and an approximate algorithm and compare their accuracy, time consumption, scalability, parameter setting requirements on five case studies with increasing complexity. Our empirical results show that (1) it is feasible to use exact techniques for small SPL multi-objective optimization problems, and (2) approximate methods can be used for large problems but require substantial effort to find the best parameter setting for acceptable approximation which can be ameliorated with known good parameter ranges. Finally, we discuss the tradeoff between accuracy and time consumption when using exact and approximate techniques for SPL multi-objective optimization and guide stakeholders to choose one or the other in practice.

Extracting Java library subsets for deployment on embedded systems

Embedded systems provide means for enhancing the functionality delivered by small-sized electronic devices such as hand-held computers and cellular phones. Java is a programming language which incorporates a number of features that are useful for developing such embedded systems. However the size and the complexity of the Java language and its libraries have slowed its adoption for embedded systems, due to the processing power and storage space limitations found in these systems. A common approach to address storage space limitations is for the vendor to offer special versions of the libraries with reduced functionality and size to meet the constraints of embedded systems. This paper presents a technique that is used for dynamically selecting, on an as needed basis, the subset of library entities that is exactly required for a given Java application to run. This subset can then be down-loaded to the device for execution. The advantage of this approach is that the developer can use arbitrary libraries, instead of being restricted to those which have been adapted for embedded systems by the vendors. A prototype system, that dynamically builds library subsets on an as needed per application basis, has been built and tested on several mid-size Java applications with positive results.

Modelling and multi-objective optimization of quality attributes in variability-rich software

Variability-rich software, such as software product lines, offers optional and alternative features to accommodate varying needs of users. Designers of variability-rich software face the challenge of reasoning about the impact of selecting such features on the quality attributes of the resulting software variant. Attributed feature models have been proposed to model such features and their impact on quality attributes, but existing variability modelling languages and tools have limited or no support for such models and the complex multi-objective optimization problem that arises. This paper presents ClaferMoo, a language and tool that addresses these shortcomings. ClaferMoo uses type inheritance to modularize the attribution of features in feature models and allows specifying multiple optimization goals. We evaluate an implementation of the language on a set of attributed feature models from the literature, showing that the optimization infrastructure can handle small-scale feature models with about a dozen features within seconds.

A dynamic analysis for revealing object ownership and sharing

We present a dynamic analysis for inferring object ownership and sharing, defined in terms of the write control graph. We render the results in an interactive hierarchical matrix visualizer.The purpose of the analysis and visualization is to reveal object ownership and sharing relations in the program, to facilitate program understanding and modification tasks.

Automating commutativity analysis at the design level

Two operations commute if executing them serially in either order results in the same change of state. In a system in which commands may be issued simultaneously by different users, lack of commutativity can result in unpredictable behaviour, even if the commands are serialized, because one users command may be preempted by anothers, and thus executed in an unanticipated state. This paper describes an automated approach to analyzing commutativity. The operations are expressed as constraints in a declarative modelling language such as Alloy, and a constraint solver is used to find violating scenarios. A case study application to the beam scheduling component of a proton therapy machine (originally specified in OCL) revealed several violations of commutativity in which requests from medical technicians in treatment rooms could conflict with the actions of a beam operator in a master control room. Some of the issues involved in automating the analysis for OCL itself are also discussed.

Comparing software architecture recovery techniques using accurate dependencies

Many techniques have been proposed to automatically recover software architectures from software implementations. A thorough comparison among the recovery techniques is needed to understand their effectiveness and applicability. This study improves on previous studies in two ways. First, we study the impact of leveraging more accurate symbol dependencies on the accuracy of architecture recovery techniques. Previous studies have not seriously considered how the quality of the input might affect the quality of the output for architecture recovery techniques. Second, we study a system (Chromium) that is substantially larger (9.7 million lines of code) than those included in previous studies. Obtaining the ground-truth architecture of Chromium involved two years of collaboration with its developers. As part of this work we developed a new sub module-based technique to recover preliminary versions of ground-truth architectures. The other systems that we study have been examined previously. In some cases, we have updated the ground-truth architectures to newer versions, and in other cases we have corrected newly discovered inconsistencies. Our evaluation of nine variants of six state-of-the-art architecture recovery techniques shows that symbol dependencies generally produce architectures with higher accuracies than include dependencies. Despite this improvement, the overall accuracy is low for all recovery techniques. The results suggest that (1) in addition to architecture recovery techniques, the accuracy of dependencies used as their inputs is another factor to consider for high recovery accuracy, and (2) more accurate recovery techniques are needed. Our results show that some of the studied architecture recovery techniques scale to the 10M lines-of-code range (the size of Chromium), whereas others do not.

Scaling exact multi-objective combinatorial optimization by parallelization

Multi-Objective Combinatorial Optimization (MOCO) is fundamental to the development and optimization of software systems. We propose five novel parallel algorithms for solving MOCO problems exactly and efficiently. Our algorithms rely on off-the-shelf solvers to search for exact Pareto-optimal solutions, and they parallelize the search via collaborative communication, divide-and-conquer, or both. We demonstrate the feasibility and performance of our algorithms by experiments on three case studies of software-system designs. A key finding is that one algorithm, which we call FS-GIA, achieves substantial (even super-linear) speedups that scale well up to 64 cores. Furthermore, we analyze the performance bottlenecks and opportunities of our parallel algorithms, which facilitates further research on exact, parallel MOCO.