Write a Blog >>
Tue 10 Nov 2020 17:30 - 17:32 at Virtual room 1 - Performance / QoS

Performance issues compromise the response time and resource consumption of a software system. Modern software systems use issue tracking systems to manage all kinds of issue reports, including performance issues.
The problem is that performance issues are often not explicitly tagged. The tagging mechanism, if exists, is completely voluntary, depending on the project's convention and on submitters' discipline. For example, the performance tag rate in Apache's Jira system is below 1%. This paper contributes a hybrid classification approach that combines linguistic patterns and machine/deep learning techniques to automatically detect performance issue reports. We manually analyzed 980 real-life performance issue reports and derived 80 project-agnostic linguistic patterns that recur in the reports. Our approach uses these linguistic patterns to construct the sentence-level and issue-level learning features for training effective machine/deep learning classifiers. We test our approach on two separate datasets, each consisting of 980 unclassified issue reports, and compare the results with 31 baseline methods. Our approach can reach up to 83% precision and up to 59% recall. The only comparable baseline method is BERT, which is still 25% lower in the F1-score.

Tue 10 Nov
Times are displayed in time zone: (UTC) Coordinated Universal Time change

17:30 - 18:00: Performance / QoSPaper Presentations / Research Papers / Journal First at Virtual room 1
17:30 - 17:32
Automatically Identifying Performance Issue Reports with Heuristic Linguistic Patterns
Research Papers
Yutong ZhaoStevens Institute of Technology, USA, Lu XiaoStevens Institute of Technology, USA, Pouria BabveyStevens Institute of Technology, USA, Lei SunStevens Institute of Technology, USA, Sunny WongAnalytical Graphics, USA, Angel A. MartinezAnalytical Graphics, USA, Xiao WangStevens Institute of Technology, USA
17:33 - 17:34
Calm Energy Accounting for Multithreaded Java Applications
Research Papers
Timur BabakolSUNY Binghamton, USA, Anthony CaninoUniversity of Pennsylvania, USA, Khaled MahmoudSUNY Binghamton, USA, Rachit SaxenaSUNY Binghamton, USA, Yu David LiuSUNY Binghamton, USA
17:35 - 17:36
Dynamically Reconfiguring Software Microbenchmarks: Reducing Execution Time without Sacrificing Result Quality
Research Papers
Christoph LaaberUniversity of Zurich, Switzerland, Stefan WürstenUniversity of Zurich, Switzerland, Harald GallUniversity of Zurich, Switzerland, Philipp LeitnerChalmers University of Technology, Sweden / University of Gothenburg, Sweden
DOI Pre-print Media Attached
17:37 - 17:38
Investigating types and survivability of performance bugs in mobile apps
Journal First
Alejandro Mazuera RozoUniversità della Svizzera italiana & Universidad de los Andes, Catia TrubianiGran Sasso Science Institute, Mario Linares-VásquezUniversidad de los Andes, Gabriele BavotaUSI Lugano, Switzerland
17:39 - 17:40
Testing Self-Adaptive Software with Probabilistic Guarantees on Performance MetricsACM SIGSOFT Distinguished Paper Award
Research Papers
Claudio MandrioliLund University, Sweden, Martina MaggioSaarland University, Germany / Lund University, Sweden
DOI Pre-print
17:41 - 18:00
Conversations on Performance / QoS
Paper Presentations
Alejandro Mazuera RozoUniversità della Svizzera italiana & Universidad de los Andes, Christoph LaaberUniversity of Zurich, Switzerland, Claudio MandrioliLund University, Sweden, Timur BabakolSUNY Binghamton, USA, M: Mei NagappanUniversity of Waterloo