CloudProphet: towards application performance prediction in cloud

Authors:
Ang Li;Xuanran Zong;Srikanth Kandula;Xiaowei Yang;Ming Zhang
Affiliations:
Duke University, Durham, NC, USA;Duke University, Durham, NC, USA;Microsoft Research, Redmond, WA, USA;Duke University, Durham, NC, USA;Microsoft Research, Redmond, WA, USA
Venue:
Proceedings of the ACM SIGCOMM 2011 conference
Year:
2011

Citing 4
Cited 5

The SPLASH-2 programs: characterization and methodological considerations

ISCA '95 Proceedings of the 22nd annual international symposium on Computer architecture
Deterministic replay of Java multithreaded applications

SPDT '98 Proceedings of the SIGMETRICS symposium on Parallel and distributed tools
Trace: parallel trace replay with approximate causal events

FAST '07 Proceedings of the 5th USENIX conference on File and Storage Technologies
CloudCmp: comparing public cloud providers

IMC '10 Proceedings of the 10th ACM SIGCOMM conference on Internet measurement

Bridging the tenant-provider gap in cloud services

Proceedings of the Third ACM Symposium on Cloud Computing
Next stop, the cloud: understanding modern web service deployment in EC2 and azure

Proceedings of the 2013 conference on Internet measurement conference
Proceedings of the Twenty-Fourth ACM Symposium on Operating Systems Principles

ACM SIGOPS 24th Symposium on Operating Systems Principles
ROOT: replaying multithreaded traces with resource-oriented ordering

Proceedings of the Twenty-Fourth ACM Symposium on Operating Systems Principles
Google hostload prediction based on Bayesian model with optimized feature combination

Journal of Parallel and Distributed Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Choosing the best-performing cloud for one's application is a critical problem for potential cloud customers. We propose CloudProphet, a trace-and-replay tool to predict a legacy application's performance if migrated to a cloud infrastructure. CloudProphet traces the workload of the application when running locally, and replays the same workload in the cloud for prediction. We discuss two key technical challenges in designing CloudProphet, and some preliminary results using a prototype implementation.