Storage area network extension solutions and their performance assessment

Telikepalli, R.; Drwiega, T.; Yan, James

doi:10.1109/mcom.2004.1284930

Cited by 37 publications

(6 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Data storage capabilities rely on hardware infrastructure, database and management and programming models (Hu et al, 2014). To store larger data sets, hardware infrastructure have advanced to networking architecture, such as direct attached storage (DAS), network attached storage (NAS) and storage area network (SAN) (e.g., Chen et al, 2014;Shiroishi et al, 2009;Gibson & van Meter, 2000;Reed et al, 2000;Barker & Massiglia, 2002;Telikepalli et al, 2004). These storage facilities connect to each other or link to a network, which gives easier access to other storage space.…”

Section: Big Data Storagementioning

confidence: 99%

Technology in the 21st century: New challenges and opportunities

Sheng

Amankwah‐Amoah

Wang

2019

Technological Forecasting and Social Change

View full text Add to dashboard Cite

Although big data, big data analytics (BDA) and business intelligence have attracted growing attention of both academics and practitioners, a lack of clarity persists about how BDA has been applied in business and management domains. In reflecting on Professor Ayre's contributions, we want to extend his ideas on technological change by incorporating the discourses around big data, BDA and business intelligence. With this in mind, we integrate the burgeoning but disjointed streams of research on big data, BDA and business intelligence to develop unified frameworks. Our review takes on both technical and managerial perspectives to explore the complex nature of big data, techniques in big data analytics and utilisation of big data in business and management community. The advanced analytics techniques appear pivotal in bridging big data and business intelligence. The study of advanced analytics techniques and their applications in big data analytics led to identification of promising avenues for future research.

show abstract

Section: Big Data Storagementioning

confidence: 99%

Technology in the 21st century: New challenges and opportunities

Sheng

Amankwah‐Amoah

Wang

2019

Technological Forecasting and Social Change

View full text Add to dashboard Cite

show abstract

“…In addition, installing FC networks requires separate physical infrastructure and new network management skills. To remedy the distance limitation two extensions of the FCP were developed --FC over TCP/IP (FCIP) and Internet [3]. FCIP is a tunneled solution that interconnects FC SAN islands by encapsulating FC block data and subsequently transporting it over a TCP socket.…”

Section: Storage Area Network (Sans)mentioning

confidence: 99%

“…IP based extension solutions encapsulate data units of SAN traffic into standard IP frames to be transported over core networks. In [3], models were developed to compare the reliability of SONET-based extensions with IP-based extensions. It was found that SONET-based solutions are more able to satisfy customers while IP-based solutions have service interruptions due to hardware/software failure.…”

Section: Introductionmentioning

confidence: 99%

Storage and Mirroring in Single and Dual Section Metro WDM Rings under Different Traffic Scenarios

El-Gorashi¹,

Elmirghani²

2010

JNW

View full text Add to dashboard Cite

This paper introduces a novel data mirroring technique for storage area networks (SANs) in a metropolitan wavelength division multiplexing (WDM) ring scenario. Sectioning links are introduced to the ring to help deal with the hot node (SAN node on ring) scenarios created by the SANs and their mirrors. Two network architectures are studied: The first architecture accommodates conventional access nodes and a single SAN and its mirror, the latter connected through a sectioning link. The other architecture accommodates conventional access nodes and two pairs of SANs and their mirrors with a sectioning link connecting each pair. Simulation is carried out to evaluate the performance of both architectures under the proposed mirroring technique for a 24 node architecture with 1 Gb/s access node rate and 5 Gb/s SAN node rate and under two different traffic models– Poisson and selfsimilar. In addition to the fixed-size (FS) slot scheme, performance is evaluated under two different slot schemes accommodating variable size packet traffic — variable-size (VS) and super-size (SS) slot schemes. Simulation Results of average node throughput and queuing delay are presented and analyzed.

show abstract

“…However, such network architectures are still widely prevalent in several other contexts such as storage area networks [34], interconnection networks for parallel computing [13], etc. In this paper, we study the throughput performance of such flow-controlled lossless networks.…”

Section: Introductionmentioning

confidence: 99%

On the maximal throughput of networks with finite buffers and its application to buffered crossbars

Giaccone

Leonardi

Shah

Proceedings IEEE 24th Annual Joint Conference of the IEEE Computer and Communications Societies.

View full text Add to dashboard Cite

Abstract-The advent of packet networks has motivated many researchers to study the performance of networks of queues in the last decade or two. However, most of the previous work assumes the availability of infinite queue-size. Instead, in this paper, we study the maximal achievable throughput in a flow-controlled lossless network with finite-queue size. In such networks, throughput depends on the packet scheduling policy utilized. As the main of this paper, we obtain a dynamic scheduling policy that achieves the maximal throughput (equal to the maximal throughput in the presence of infinite queuesize) with a minimal finite queue-size at the internal nodes of the network. Though the performance of the policy is ideal, it is quite complex and hence difficult to implement. This leads us to a design of simpler and possibly implementable policy. We obtain a natural trade-off between throughput and queue-size for this policy.We apply our results to the packet switches with buffered crossbar architecture. We propose a simple, implementable, distributed scheduling policy which provides high throughput in the presence of minimal internal buffer. We also obtain a natural trade-off between throughput, internal speedup and buffer-size providing a switch designer with a gamut of designs.To the best of authors' knowledge, this is one of the first attempts to study the throughput for general networks with finite queue-size. We believe that our methods are general and can be useful in other contexts.

show abstract

Storage area network extension solutions and their performance assessment

Cited by 37 publications

References 8 publications

Technology in the 21st century: New challenges and opportunities

Technology in the 21st century: New challenges and opportunities

Storage and Mirroring in Single and Dual Section Metro WDM Rings under Different Traffic Scenarios

On the maximal throughput of networks with finite buffers and its application to buffered crossbars

Contact Info

Product

Resources

About