Write a Blog >>
Tue 10 Nov 2020 17:05 - 17:06 at Virtual room 1 - Configuration

Approximation is a technique that optimizes the balance between application outcome quality and its resource usage. Trading quality for performance has been investigated for single application scenarios, but not for environments where multiple approximate applications may run concurrently on the same machine, interfering with each other by sharing machine resources. Applying existing, single application techniques to this multi-programming environment may lead to configuration space size explosion, or result in poor overall application quality outcomes.

Our new RAPID-M system is the first cross-application con-figuration management framework. It reduces the problem size by clustering configurations of individual applications into local"similarity buckets". The global cross-applications configuration selection is based on these local bucket spaces. RAPID-M dynamically assigns buckets to applications such that overall quality is maximized while respecting individual application cost budgets.Once assigned a bucket, reconfigurations within buckets may be performed locally with minimal impact on global selections. Experimental results using six configurable applications show that even large configuration spaces of complex applications can be clustered into a small number of buckets, resulting in search space size reductions of up to 9 orders of magnitude for our six applications. RAPID-M constructs performance cost models with an average prediction error of ≤3%. For our application execution traces, RAPID-M dynamically selects configurations that lower the budget violation rate by 33.9% with an average budget exceeding rate of 6.6% as compared to other possible approaches. RAPID-M successfully finishes 22.75% more executions which translates to a 1.52X global output quality increase under high system loads. Theo verhead ofRAPID-Mis within≤1% of application execution times.

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

17:00 - 17:02
Talk
Configuration Smells in Continuous Delivery Pipelines: A Linter and a Six-Month Study on GitLab
Research Papers
Carmine VassalloUniversity of Zurich, Switzerland, Sebastian ProkschDelft University of Technology, Netherlands, Anna JancsoUniversity of Zurich, Switzerland, Harald GallUniversity of Zurich, Switzerland, Massimiliano Di PentaUniversity of Sannio, Italy
DOI Pre-print
17:03 - 17:04
Talk
Dimensions of Software Configuration: On the Configuration Context in Modern Software Development
Research Papers
Norbert SiegmundLeipzig University, Nicolai RuckelBauhaus-University Weimar, Janet SiegmundTU Chemnitz, Germany
DOI
17:05 - 17:06
Talk
Global Cost/Quality Management across Multiple Applications
Research Papers
Liu LiuRutgers University, USA, Sibren IsaacmanLoyola University Maryland, USA, Uli KremerRutgers University, USA
DOI
17:07 - 17:08
Talk
Inferring and Securing Software Configurations using Automated Reasoning
Visions and Reflections
Paul GazzilloUniversity of Central Florida
DOI
17:09 - 17:10
Talk
Understanding and Discovering Software Configuration Dependencies in Cloud and Datacenter Systems
Research Papers
Qingrong ChenUniversity of Illinois at Urbana-Champaign, USA, Teng WangNational University of Defense Technology, China, Owolabi LegunsenCornell University, Shanshan LiNational University of Defense Technology, China, Tianyin XuUniversity of Illinois at Urbana-Champaign, USA
DOI
17:11 - 17:30
Talk
Conversations on Configuration
Paper Presentations
Carmine VassalloUniversity of Zurich, Switzerland, Liu LiuRutgers University, Nicolai RuckelBauhaus-University Weimar, Paul GazzilloUniversity of Central Florida, Qingrong ChenUniversity of Illinois at Urbana-Champaign, USA, M: Sarah NadiUniversity of Alberta