Routing in multihop packet switching networks: Gb/s challenge

Baransel, Cesur; Dobosiewicz, W.; Gburzyński, Paweł

doi:10.1109/65.386051

Cited by 76 publications

(30 citation statements)

References 75 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…De Bruijn graphs [5], [19], [22], [38] are nearly optimal, fixed-degree digraphs of diameter log k N , where k is the fixed degree of each node and N is the total number of nodes. Note that de Bruijn graphs are directed graphs with k outgoing and k incoming edges at each node, which also holds for many other protocols [35], [40], [43].…”

Section: Structure Of De Bruijn Graphsmentioning

confidence: 99%

Graph-theoretic analysis of structured peer-to-peer systems: routing distances and fault resilience

Loguinov

Casas²,

Wang

2005

IEEE/ACM Trans. Networking

171

223

View full text Add to dashboard Cite

This paper examines graph-theoretic properties of existing peer-to-peer architectures and proposes a new infrastructure based on optimal-diameter de Bruijn graphs. Since generalized de Bruijn graphs possess very short average routing distances and high resilience to node failure, they are well suited for structured peer-to-peer networks. Using the example of Chord, CAN, and de Bruijn, we first study routing performance, graph expansion, and clustering properties of each graph. We then examine bisection width, path overlap, and several other properties that affect routing and resilience of peer-to-peer networks. Having confirmed that de Bruijn graphs offer the best diameter and highest connectivity among the existing peer-to-peer structures, we offer a very simple incremental building process that preserves optimal properties of de Bruijn graphs under uniform user joins/departures. We call the combined peer-to-peer architecture ODRI -Optimal Diameter Routing Infrastructure.

show abstract

Section: Structure Of De Bruijn Graphsmentioning

confidence: 99%

Graph-theoretic analysis of structured peer-to-peer systems: routing distances and fault resilience

Loguinov

Casas²,

Wang

2005

IEEE/ACM Trans. Networking

171

223

View full text Add to dashboard Cite

show abstract

“…Finally, we note that "deflection" and "dispersion" routing schemes that forward packets along varying or multiple paths have many of the characteristics of fluttering paths [BDG95,GK97]. While these schemes can offer benefits in terms of simplified routing decisions, enhanced throughput, and resilience, they bring with them the difficulties discussed above.…”

Section: Significance Of Flutteringmentioning

confidence: 99%

“…In addition to the books cited above, see, for example, McQuillan et al's discussion of the initial ARPANET routing algorithm [MFR78] and the algorithms that replaced it [MRR80,KZ89]; the Exterior Gateway Protocol used in the NSFNET [Ro82,Re89], and the Border Gateway Protocol that replaced it [RL95,RG95,Tr95a,Tr95b]; the related work by Estrin et al on routing between administrative domains [BE90, ERH92]; Awerbuch's technique of reducing asynchronous networks to synchronous ones to simplify routing algorithms [Aw90]; Perlman and Varghese's discussion of difficulties in designing routing algorithms [PV88]; Deering and Cheriton's seminal work on multicast routing [DC90]; Perlman's comparison of the popular OSPF and IS-IS protocols [Pe91]; and Baransel et al's survey of routing techniques for very high speed networks [BDG95].…”

Section: Studies Of Routing Protocolsmentioning

confidence: 99%

Measurements and analysis of end-to-end Internet dynamics

Paxson

1997

405

298

View full text Add to dashboard Cite

Measurements and Analysis of End-to-End Internet Dynamics by Vern Edward Paxson Doctor of Philosophy in Computer ScienceUniversity of California at Berkeley Prof. Domenico Ferrari, ChairAccurately characterizing end-to-end Internet dynamics-the performance that a user actually obtains from the lengthy series of network links that comprise a path through the Internet-is exceptionally difficult, due to the network's immense heterogeneity. It can be impossible to gauge the generality of findings based on measurements of a handful of paths, yet logistically it has proven very difficult to obtain end-to-end measurements on larger scales.At the heart of our work is a "measurement framework" we devised in which a number of sites around the Internet host a specialized measurement service. By coordinating "probes" between pairs of these sites we can measure end-to-end behavior along ON 2 paths for a framework consisting of N sites. Consequently, we obtain a superlinear scaling that allows us to measure a rich cross-section of Internet behavior without requiring huge numbers of observation points. 37 sites participated in our study, allowing us to measure more than 1,000 distinct Internet paths.The first part of our work looks at the behavior of end-to-end routing: the series of routers over which a connection's packets travel. Based on 40,000 measurements made using our framework, we analyze: routing "pathologies" such as loops, outages, and flutter; the stability of routes over time; and the symmetry of routing along the two directions of an end-to-end path. We find that pathologies increased significantly over the course of 1995, indicating that, by one metric, routing degraded over the year; that Internet paths are heavily dominated by a single route, but that routing lifetimes range from seconds to many days, with most lasting for days; and that, at the end of 1995, about half of all Internet paths included a major routing asymmetry.The second part of our work studies end-to-end Internet packet dynamics. We analyze 20,000 TCP transfers of 100 Kbyte each to investigate the performance of both the TCP endpoints and the Internet paths. The measurements used for this part of our study are much richer than those for the first part, but require a great degree of attention to issues of calibration, which we address by applying self-consistency checks to the measurements whenever possible. We find that packet filters are capable of a wide range of measurement errors, some of which, if undetected, can significantly taint subsequent analysis. We further find that network clocks exhibit adjustments and skews relative to other clocks frequently enough that a failure to detect and remove these effects will likewise pollute subsequent packet timing analysis.Using TCP transfers for our network path "measurement probes" gains a number of advantages, the chief of which is the ability to probe fine time scales without unduly loading the network. However, using TCP also requires us to accurately distinguish between connection ...

show abstract

“…Previously McQuillan has discussed about the initial ARPANET routing algorithm [l] and the algorithms that replaced it [2]; the Exterior Gateway Protocol used in the NSFNET [3] and the Border Gateway Protocol that replaced it [4]; the related work by Estrin et aI., on routing between administrative domains [5]; Perlman and Verghese's discussion of difficulties in designing routing algorithms [6]; Perlman's comparison of the popular OSPF and IS-IS protocols [7]; Barasel et aI's survey of routing techniques for very high speed networks [8].…”

Section: State Of the Artmentioning

confidence: 99%

Internet Routing—The State of the Art

Ramasamy

Arokiasamy

Balakrishnan

2002

Communication Systems

View full text Add to dashboard Cite

Abstract:The Internet protocols are the world's most popular open-system (nonproprietary) protocol suite because they can be used to communicate across any set of interconnected networks. In this paper an overview on some internet routing is analyzed. The routing protocols used in the internet are ARPANET protocol, Routing Information Protocol (RIP), Open Shortest Path First protocol (OSPF), Interior Routing Protocol (lRP), Exterior Routing Protocol (ERP), Interior Gateway Protocol (lGP), Exterior Gateway Protocol (EGP), Transfer Control Protocol (TCP) and Internet Protocol (IP). The routing protocols are used based on reliability, scalability and security. The OSPF protocol has been given the status of being the standard routing protocol for IP internetworks. The routing protocol, which is currently in use, is Transmission Control ProtocoVInternet Protocol (TCP/IP), which is providing to be a great success for transmission of data. TCP provides a reliable connection for the transfer of data between applications. The Internet Protocol (IP) is a network-layer protocol that contains addressing information and source control information that enables packets to be routed. It has two primary responsibilities: providing connectionless, best effort delivery datagrams through an internetwork and providing fragmentation and ressembly of datagrams to support data links with different maximumtransmission unit (MTU) sizes. In addition to the TCP, there is another transport level protocol, the UserDatagram Protocol (UDP) which provides connectionless service for applicationlevel procedures. UDP is useful when TCP would be too complex, too slow or just unnecessary. UDP address is the combination of 32-bit IP address and 16-bit port number. Unlike IP,it does checksum its data,ensuring data integrity.lPv6 is a new version of the Internet protocol based on IPv4.1t increases the IP address size from 32 bits to 128 bits to support more levels of addressing hierarchy, much greater number of addressable modes and simpler auto-configuration of address. Scalability of multicast address is introduced.A new type of address called an anycast address is also defined to send a packet to anyone of a group of nodes.L. Chapin (ed.), Communication Systems

show abstract

Routing in multihop packet switching networks: Gb/s challenge

Cited by 76 publications

References 75 publications

Graph-theoretic analysis of structured peer-to-peer systems: routing distances and fault resilience

Graph-theoretic analysis of structured peer-to-peer systems: routing distances and fault resilience

Measurements and analysis of end-to-end Internet dynamics

Internet Routing—The State of the Art

Contact Info

Product

Resources

About