Obtaining high performance for storage outsourcing

Ng, Wee Teck; Hillyer, Bruce K.

doi:10.1145/378420.378813

Cited by 18 publications

(29 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further, we are interested in pushing the boundaries of traditional distributed file systems, such as NFS, by using them across the wide area. Two papers have addressed the effect of high latencies on file system traffic [14,15], but neither of them considered QoS or costs. We expect Internet block-storage services to become widespread in the future, as protocols such as iSCSI become more popular.…”

Section: Related Workmentioning

confidence: 99%

“…We study a set of three nodes because they provide a sufficiently rich space to understand the behaviors of the two algorithms, yet is not overly complicated to explain. [5,14,15] base [5,10,15] optWait [5,10,15] base [5,6,15] optWait [5,6,15] Table 2 lists the optimized costs and request distributions for Base and OptWait for costs [5,10,15].…”

Section: Base Vs Optwaitmentioning

confidence: 99%

“…For example, consider the costs achieved by Base and OptWait for cost [5,10,15] at latency guarantees of 500ms and 600ms. At 500ms, Base achieves lower cost than OptWait because it is able to use the medium-cost service 17% of the time, whereas OptWait cannot yet use the medium-cost service (see Table 2).…”

Section: Base Vs Optwaitmentioning

confidence: 99%

“…However, eventually, OptWait can use the lower-cost service more aggressively because it can avoid the tail of the CDF by re-sending requests to the more expensive services as needed. Table 3 the distributions computed for L f within the interval [1200ms, 1400ms] for costs [5,6,15] vs. [5,10,15]. For [5,10,15], OptWait chooses to use either the low-and medium-cost or low-and high-cost services.…”

Section: Base Vs Optwaitmentioning

confidence: 99%

“…Table 3 the distributions computed for L f within the interval [1200ms, 1400ms] for costs [5,6,15] vs. [5,10,15]. For [5,10,15], OptWait chooses to use either the low-and medium-cost or low-and high-cost services. For [5,6,15], OptWait only chooses to use the mediumcost service.…”

Section: Base Vs Optwaitmentioning

confidence: 99%

See 4 more Smart Citations

A Cost-Effective Distributed File Service with QoS Guarantees

Bianchini

Nguyen

2007

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Large-scale, value-added Internet services composed of independent cooperating or competing services will soon become common place. Several groups have addressed the performance, communication, discovery, and description aspects of these services. However, little work has been done on effectively composing paid services and the quality-of-service (QoS) guarantees that they provide. We address these issues in the context of distributed file storage in this paper. In particular, we propose, implement, and evaluate a cost-effective, QoSaware distributed file service comprising a front-end file service and back-end (third-party) storage services. Our front-end service uses mathematical modeling and optimization to provide performance and availability guarantees at low cost by carefully orchestrating the accesses to the back-end services. Experimental results from our prototype implementation validate our modeling and optimization. We conclude that our approach for providing QoS at low cost should be useful to future composite Internet services.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Base Vs Optwaitmentioning

confidence: 99%

Section: Base Vs Optwaitmentioning

confidence: 99%

Section: Base Vs Optwaitmentioning

confidence: 99%

Section: Base Vs Optwaitmentioning

confidence: 99%

See 3 more Smart Citations

A Cost-Effective Distributed File Service with QoS Guarantees

Bianchini

Nguyen

2007

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

iSCSI analysis system and performance improvement of sequential access in a long‐latency environment

Yamaguchi

Oguchi

2005

Electron Comm Jpn Pt III

View full text Add to dashboard Cite

SUMMARYThe iSCSI protocol, approved by the IETF in February 2003, is used by data centers to offer storage outsourcing and remote backup services. A key issue when accessing remote storage over iSCSI is minimizing the performance degradation caused by network distance. Because iSCSI's performance is dictated by the iSCSI protocol, the SCSI protocol, the network, network devices, and so on, there is a need for a capable analysis system that comprehends all these layers. This paper discusses the functions of an iSCSI analysis system developed by the authors. With existing iSCSI equipment, if the system is not optimized for the conditions on the network, then increasing distance will cause a dramatic decrease in performance. With the proposed iSCSI analysis system, the authors have been able to elucidate the root causes of this performance degradation, and bring performance nearly to the level of the network substrate's limit.

show abstract

STICS: SCSI-to-IP cache for storage area networks

Zhang

Yang

2004

Journal of Parallel and Distributed Computing

View full text Add to dashboard Cite

7Data storage plays an essential role in today's fast-growing data-intensive network services. New standards and products emerge very rapidly for networked data storage. Given the mature Internet infrastructure, the overwhelming preference among the IT community 9 recently is using IP for storage networking because of economy and convenience. iSCSI is one of the most recent standards that allow SCSI protocols to be carried out over IP networks. However, there are many disparities between SCSI and IP in terms of protocols, speeds, 11 bandwidths, data unit sizes, and design considerations that prevent fast and efficient deployment of storage area network (SAN) over IP. This paper introduces SCSI-to-IP cache storage (STICS), a novel storage architecture that couples reliable and high-speed data caching 13 with low-overhead conversion between SCSI and IP protocols. A STICS block consists of one or several storage devices and an intelligent processing unit with CPU and RAM. The storage devices are used to cache and store data while the intelligent processing unit carries 15 out the caching algorithm, protocol conversion, and self-management functions. Through the efficient caching algorithm and localization of certain unnecessary protocol overheads, STICS can significantly improve performance, reliability, and scalability over current iSCSI 17 systems. Furthermore, STICS can be used as a basic plug-and-play building block for data storage over IP. Analogous to "cache memory" invented several decades ago for bridging the speed gap between CPU and memory, STICS is the first-ever "cache storage" for bridging 19 the gap between SCSI and IP making it possible to build an efficient SAN over IP. We have implemented software STICS prototype on Linux operating system. Numerical results using popular benchmarks such as vxbench, IOzone, PostMark, and EMC's trace have shown 21 a dramatic performance gain over the current iSCSI implementation.

show abstract

Obtaining high performance for storage outsourcing

Cited by 18 publications

References 1 publication

A Cost-Effective Distributed File Service with QoS Guarantees

A Cost-Effective Distributed File Service with QoS Guarantees

iSCSI analysis system and performance improvement of sequential access in a long‐latency environment

STICS: SCSI-to-IP cache for storage area networks

Contact Info

Product

Resources

About