Using latency to evaluate interactive system performance
OSDI '96 Proceedings of the second USENIX symposium on Operating systems design and implementation
The interactive performance of SLIM: a stateless, thin-client architecture
Proceedings of the seventeenth ACM symposium on Operating systems principles
Improving interactive performance using TIPME
Proceedings of the 2000 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
IEEE Internet Computing
Measuring Thin-Client Performance Using Slow-Motion Benchmarking
Proceedings of the General Track: 2002 USENIX Annual Technical Conference
Optimizing the migration of virtual computers
OSDI '02 Proceedings of the 5th symposium on Operating systems design and implementationCopyright restrictions prevent ACM from being able to make the PDFs for this conference available for downloading
The collective: a cache-based system management architecture
NSDI'05 Proceedings of the 2nd conference on Symposium on Networked Systems Design & Implementation - Volume 2
Ensemble-level Power Management for Dense Blade Servers
Proceedings of the 33rd annual international symposium on Computer Architecture
The collective: a cache-based system management architecture
NSDI'05 Proceedings of the 2nd conference on Symposium on Networked Systems Design & Implementation - Volume 2
The potential of speculative class-loading
Proceedings of the 5th international symposium on Principles and practice of programming in Java
Measuring the performance of interactive applications with listener latency profiling
Proceedings of the 6th international symposium on Principles and practice of programming in Java
Interactive resource-intensive applications made easy
Proceedings of the ACM/IFIP/USENIX 2007 International Conference on Middleware
DeskBench: flexible virtual desktop benchmarking toolkit
IM'09 Proceedings of the 11th IFIP/IEEE international conference on Symposium on Integrated Network Management
Modeling remote desktop systems in utility environment with application to QoS management
IM'09 Proceedings of the 11th IFIP/IEEE international conference on Symposium on Integrated Network Management
Performance-aware thermal management via task scheduling
ACM Transactions on Architecture and Code Optimization (TACO)
Interactive resource-intensive applications made easy
MIDDLEWARE2007 Proceedings of the 8th ACM/IFIP/USENIX international conference on Middleware
Reliable preservation of interactive environments and workflows
ECDL'10 Proceedings of the 14th European conference on Research and advanced technology for digital libraries
Listener latency profiling: Measuring the perceptible performance of interactive Java applications
Science of Computer Programming
Catch me if you can: performance bug detection in the wild
Proceedings of the 2011 ACM international conference on Object oriented programming systems languages and applications
Utility-directed resource allocation in virtual desktop clouds
Computer Networks: The International Journal of Computer and Telecommunications Networking
Bulk synchronous visualization
Proceedings of the 2013 International Workshop on Programming Models and Applications for Multicores and Manycores
Cloudlet-screen computing: a client-server architecture with top graphics performance
International Journal of Ad Hoc and Ubiquitous Computing
Virtual asymmetric multiprocessor for interactive performance of consolidated desktops
Proceedings of the 10th ACM SIGPLAN/SIGOPS international conference on Virtual execution environments
Hi-index | 0.00 |
Today many system benchmarks use throughput as a measure of performance. While throughput is appropriate for benchmarking server environments, response time is a better metric for evaluating desktop performance. Currently, there is a lack of good tools to measure interactive performance; although several commercial GUI testing tools exist, they are not designed for performance measurement. This paper presents VNCplay, a cross-platform tool for measuring interactive performance of GUI-based systems. VNCplay records a user's interactive session with a system and replays it multiple times under different system configurations; interactive response time is evaluated by comparing the times at which similar screen updates occur in each of the replayed sessions. Using VNCplay we studied the effect of processor speed and disk load on interactive performance of Microsoft Windows and Linux. These experiments show that the same user session can have widely varying interactive response times in different environments while maintaining the same total running time, illustrating that response time is a better measure of interactive performance than throughput. The experimental results make a case for a response time measurement tool like VNCplay.