Separating computation and storage with storage virtualization

Zhang, Yaoxue; Zhou, Yuezhi

doi:10.1016/j.comcom.2010.06.024

Cited by 17 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1 Therefore, in such a system, the data requests become two-stage jobs, consisting of the disk-read and the network-transmission operations, while each server becomes a two-stage flowshop, consisting of the disk-read and networktransmission processors (note that the disk-read and network-transmission can run in parallel in the same server), and scheduling a given set of such requests in a multiple-server center becomes an instance of the scheduling model we have formulated. We should remark that the time for disk-read and the time for network-transmission in a typical server are in general comparable, and, due to the impact of cache systems, they need not to have a linear relation [22]. Therefore, neither can be simply ignored if we want to maintain good performance for the cloud system.…”

Section: Motivationsmentioning

confidence: 99%

“…Consider the situation in data centers as we described in Section 1. In order to improve the process of data-read/networktransformation, severs in the center may keep certain commonly used software codes in the main memory so that the time-consuming process of data-read can be avoided (see, for example, [22]). Thus, client requests for the code will become two-stage jobs J i = (r i , t i ) with r i = 0.…”

Section: Dual Jobs and Dual Schedulesmentioning

confidence: 99%

See 1 more Smart Citation

Scheduling two-stage jobs on multiple flowshops

Chen

2019

Theoretical Computer Science

View full text Add to dashboard Cite

Section: Motivationsmentioning

confidence: 99%

Section: Dual Jobs and Dual Schedulesmentioning

confidence: 99%

Scheduling two-stage jobs on multiple flowshops

Chen

2019

Theoretical Computer Science

View full text Add to dashboard Cite

“…Transparent Computing paradigm [7][8][9] aims at the vision advocated by pervasive computing in which users can demand computing services in a hassle-free way. Fig.…”

Section: Preliminariesmentioning

confidence: 99%

A Holistic Approach for Distributed Dimensionality Reduction of Big Data

Kuang

Yang

Chen

et al. 2018

IEEE Trans. Cloud Comput.

View full text Add to dashboard Cite

With the exponential growth of data volume, big data have placed an unprecedented burden on current computing infrastructure. Dimensionality reduction of big data attracts a great deal of attention in recent years as an efficient method to extract the core data which is smaller to store and faster to process. This paper aims at addressing the three fundamental problems closely related to distributed dimensionality reduction of big data, i.e. big data fusion, dimensionality reduction algorithm and construction of distributed computing platform. A chunk tensor method is presented to fuse the unstructured, semi-structured and structured data as a unified model in which all characteristics of the heterogeneous data are appropriately arranged along the tensor orders. A Lanczos based High Order Singular Value Decomposition algorithm is proposed to reduce dimensionality of the unified model. Theoretical analyses of the algorithm are provided in terms of storage scheme, convergence property and computation cost. To execute the dimensionality reduction task, this paper employs the Transparent Computing paradigm to construct a distributed computing platform as well as utilizes the linear predictive model to partition the data blocks. Experimental results demonstrate that the proposed holistic approach is efficient for distributed dimensionality reduction of big data.

show abstract

“…The TCP takes charge of the management and allocation of OS resources, application resources and users' private resources, by providing data storage and access services for the terminal users through the transparent network. All the requests that come from terminals are redirected to the Vdisks in the TCP [21].…”

Section: Preliminarymentioning

confidence: 99%

A Caching Strategy for Transparent Computing Server Side Based on Data Block Relevance

et al. 2018

View full text Add to dashboard Cite

The performance bottleneck of transparent computing (TC) is on the server side. Caching is one of the key factors of the server-side performance. The count of disk input/output (I/O) can be reduced if multiple data blocks that are correlated with the data block currently accessed are prefetched in advance. As a result, the service performance and user experience quality in TC can be improved. In this study, we propose a caching strategy for the TC server side based on data block relevance, which is called the correlation pattern-based caching strategy (CPCS). In this method, we adjust a model that is based on a frequent pattern tree (FP-tree) for mining frequent patterns from data streams (FP-stream) to the characteristics of data access in TC, and we devise a cache structure in accordance with the storage model of TC. Finally, the access process in TC with real access traces in different caching strategies. Simulation results show that the cache hit rate under the CPCS is higher than that using other algorithms under conditions in which the parameters are coordinated properly.

show abstract

Separating computation and storage with storage virtualization

Cited by 17 publications

References 15 publications

Scheduling two-stage jobs on multiple flowshops

Scheduling two-stage jobs on multiple flowshops

A Holistic Approach for Distributed Dimensionality Reduction of Big Data

A Caching Strategy for Transparent Computing Server Side Based on Data Block Relevance

Contact Info

Product

Resources

About