Computing Reviews
Today's Issue Hot Topics Search Browse Recommended My Account Log In
Review Help
Search
STACEE: enhancing storage clouds using edge devices
Neumann D., Bodenstein C., Rana O., Krishnaswamy R.  ACE 2011 (Proceedings of the 1st ACM/IEEE Workshop on Autonomic Computing in Economics, Karlsruhe, Germany, Jun 14, 2011)19-26.2011.Type:Proceedings
Date Reviewed: Aug 1 2012

In this day and age, lots of bandwidth is consumed by the delivery of Web content, such as file sharing via peer-to-peer (P2P) applications and video streaming. Internet service providers are feeling the pressure to deliver such multimedia content to the consumer more quickly, while reducing costs. This paper discusses the creation of a storage cloud using edge devices based on P2P resource provisioning.

This paper presents a vague design, implementation, and evaluation of a storage cloud using the STACEE edge devices concept. The term “edge devices” originated in telecommunications and refers to routers, routing switches, and multiplexers. Mobile phones, personal computers and media centers, set-top boxes, modems, and networked storage devices also fall under this category. The authors explore the issue of quality of service (QoS) and QoS-aware scheduling in a P2P storage cloud. The technique is noble in the sense that it is fully transparent and does not require any modifications to Internet protocols. Hence, it can be readily deployed. A more formal definition of edge device could have been helpful.

The paper does not offer details of a working example. Some concerns that need to be addressed further include the possibility of a single point of failure at one of the edge devices and how such a failure would affect data retrieval. Another concern is clustering the devices to achieve high availability. Can these edge devices belong to different vendors? Can one manage all the edge devices centrally? In addition to these questions, there are security issues, such as the need for patching devices such as cable modems and wireless routers.

This could be a revolutionary idea, provided one could design a system that could guarantee an uptime of five nines (that is, one that is available 99.999 percent of the time, which translates to 5.26 minutes of downtime per year, 25.9 seconds of downtime per month, or 6.05 seconds of downtime per week). This is a revolutionary idea because right now we have different edge devices made by various manufacturers; integrating them is not only a challenge, but one that requires cooperation among the stakeholders for the common good.

Overall, I found this paper on a method for storing data using edge devices to be an interesting read.

Reviewer:  Rajat Ravinder Review #: CR140452 (1212-1259)
Bookmark and Share
 
Information Storage (H.3.2 )
 
 
Cloud Computing (C.2.4 ... )
 
Would you recommend this review?
yes
no
Other reviews under "Information Storage": Date
Principles of delay-sensitive multimedia data storage retrieval
Gemmell J., Christodoulakis S. (ed) ACM Transactions on Information Systems 10(1): 51-90, 1992. Type: Article
May 1 1993
Partial match retrieval in implicit data structures
Alt H., Mehlhorn K., Munro J. Information Processing Letters 19(2): 61-65, 1984. Type: Article
May 1 1985
Performance of two-disk partition data allocations
Chang C., Chen C. BIT 27(3): 306-314, 1987. Type: Article
Mar 1 1988
more...

E-Mail This Printer-Friendly
Send Your Comments
Contact Us
Reproduction in whole or in part without permission is prohibited.   Copyright 1999-2024 ThinkLoud®
Terms of Use
| Privacy Policy