Multi-cloud storage can provide better features such as availability and scalability. Current works use multiple cloud storage providers with erasure coding to achieve certain benefits including fault-tolerance improv...
详细信息
Multi-cloud storage can provide better features such as availability and scalability. Current works use multiple cloud storage providers with erasure coding to achieve certain benefits including fault-tolerance improving or vendor lock-in avoiding. However, these works only use the multi-cloud storage in ad-hoc ways, and none of them considers the optimization issue in general. In fact, the key to optimize the multi-cloud storage is to effectively choose providers and erasure coding parameters. Meanwhile, the dataplacement should satisfy system or application developers' requirements. As developers often demand various objectives to be optimized simultaneously, such complex requirement optimization cannot be easily fulfilled by ad-hoc ways. This paper presents Triones, a systematic model to formally formulate dataplacement in multi-cloud storage by using erasure coding. Firstly, Triones addresses the problem of data placement optimization by applying non-linear programming and geometric space abstraction. It could satisfy complex requirements involving multi-objective optimization. Secondly, Triones can effectively balance among different objectives in optimization and is scalable to incorporate new ones. The effectiveness of the model is proved by extensive experiments on multiple cloud storage providers in the real world. For simple requirements, Triones can achieve 50 percent access latency reduction, compared with the model in mu LibCloud. For complex requirements, Triones can improve fault-tolerance level by 2x and reduce access latency and vendor lock-in level by 30 similar to 70 percent and 49.85 percent respectively with about 19.19 percent more cost, compared with the model only optimizing cost in Scalia.
With the steady increase of offered cloud storage services, they became a popular alternative to local storage systems. Beside several benefits, the usage of cloud storage services can offer, they have also some downs...
详细信息
ISBN:
(纸本)9781538613269
With the steady increase of offered cloud storage services, they became a popular alternative to local storage systems. Beside several benefits, the usage of cloud storage services can offer, they have also some downsides like potential vendor lock-in or unavailability. Different pricing models, storage technologies and changing storage requirements are further complicating the selection of the best fitting storage solution. In this work, we present a heuristic optimization approach that optimizes the placement of data on cloud-based storage services in a redundant, cost- and latency-efficient way while considering user-defined Quality of Service requirements. The presented approach uses monitored data access patterns to find the best fitting storage solution. Through extensive evaluations, we show that our approach saves up to 30% of the storage cost and reduces the upload and download times by up to 48% and 69% in comparison to a baseline that follows a state-of-the-art approach.
This paper provides a data placement optimization approach for Coarse-Grained Reconfigurable Architecture (CGRA) based computing platform in order to simultaneously optimize the performance of CGRA execution and data ...
详细信息
ISBN:
(纸本)9783981926309
This paper provides a data placement optimization approach for Coarse-Grained Reconfigurable Architecture (CGRA) based computing platform in order to simultaneously optimize the performance of CGRA execution and data transformation between main memory and multi-bank memory. To achieve this goal, we have developed a performance model to evaluate the efficiency of data transformation and CGRA execution. This model is used for comparing the performances difference when using different dataplacement strategies. We search for the optimal dataplacement method by firstly choosing the method which generates the best CGRA execution efficiency front the candidates who can generate the optimal data transformation efficiency. Then we choose the best dataplacement strategy by comparing the performance of the selected strategy with the one generated through existing multi-bank optimization algorithm. Evaluation shows our approach is capable of optimizing the performance to 2.76x of state-of-the-art method when considering both data-transformation and CGRA execution efficiency.
暂无评论