Lessons and challenges in automating data dependability
Proceedings of the 11th workshop on ACM SIGOPS European workshop
On building next generation data centers: energy flow in the information technology stack
COMPUTE '08 Proceedings of the 1st Bangalore Annual Compute Conference
Don't settle for less than the best: use optimization to make decisions
HOTOS'07 Proceedings of the 11th USENIX workshop on Hot topics in operating systems
| Hi-index | 0.00 |
Large-scale systems experience frequent failures whichcan result in unacceptably high service downtime or applicationexecution time. To meet performance and availabilityrequirements, the user must perform a complex design task includingthe selection and configuration of hardware and softwarecomponents and mechanisms for handling failures. Webelieve users should be relieved of this burden by automatingthe design process in order to generate cost-effective solutionsfrom high-level application requirements. In this paper,we present Aved, a proof of concept design automation enginewhich is a first step toward this goal. We describe how infrastructurechoices, application models, and user requirementsare represented with Aved to automate design space searchand reason about design alternatives. We additionally presentexamples to illustrate how Aved can generate a complete pictureof the cost-availability and cost-performance tradeoffsfor the infrastructure design.