Shall we worry about Packet Reordering?

Przybylski, Michal; Belter, Bartosz; Binczewski, Artur

doi:10.12921/cmst.2005.11.02.141-146

Cited by 26 publications

(26 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Bennett et al [30] refuted the widely held belief that packet reordering in the Internet is an uncommon behavior caused by incorrect or malfunctioning network components. Przybylski et al [31] discussed the factors affecting ordered packet delivery and revealed that the main protocols of modern gigabit networks cannot cope well with reordering.…”

Section: Related Workmentioning

confidence: 99%

A Case Study of IPv6 Network Performance: Packet Delay, Loss, and Reordering

Wang

Pan

et al. 2017

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Internet Protocol (IP) is used to identify and locate computers on the Internet. Currently, IPv4 still routes most Internet traffic. However, with the exhausting of IPv4 addresses, the transition to IPv6 is imminent, because, as the successor of IPv4, IPv6 can provide a larger available address space. Existing studies have addressed the notion that IPv6-centric next generation networks are widely deployed and applied. In order to gain a deep understanding of IPv6, this paper revisits several critical IPv6 performance metrics. Our extensive measurement shows that packet delay and loss rate of IPv6 are similar to IPv4 when the AS-level paths are roughly the same. Specifically, when the link utilization exceeds a threshold, for example, 0.83 in our study, variation of packet delay presents a similar pattern with the variation of link utilization. If packet delay of a path is large, packet-loss rate of that path is more likely to fluctuate. In addition, we conduct a first-ever analysis of packet reordering in IPv6 world. Few IPv6 probe packets are out-of-order and the reordering rate is 2.3 * 10 −6 , which is much lower than that of 0.79% in IPv4 world. Our analysis consolidates an experimental basis for operators and researchers of IPv6 networks.

show abstract

Section: Related Workmentioning

confidence: 99%

A Case Study of IPv6 Network Performance: Packet Delay, Loss, and Reordering

Wang

Pan

et al. 2017

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…Also should a larger GOF rate be utilised, then SD will provide data equality for all frames within the GOF. In [11], the authors highlight that datagrams of dissimilar processing times, produce dissimilar transmission times. Such that by maintaining such datagram byte-size equality, the order of packet delivery is improved.…”

Section: Section Distributionmentioning

confidence: 99%

ALD: adaptive layer distribution for scalable video

2014

View full text Add to dashboard Cite

“…In Juniper M160, with four parallel processors, each with a capacity of 2.5 Gbps to serve a single 10Gbps interface, reordering was a concern [13,14]. Corrective action was taken in the design of the subsequent generations of high-end Juniper routers, e.g., T640, to avoid this problem.…”

Section: A Routersmentioning

confidence: 99%

“…Corrective action was taken in the design of the subsequent generations of high-end Juniper routers, e.g., T640, to avoid this problem. Other notable instances of reordering include that in BD6808/6816 [14]. The recent high-end routers attempt to reduce or avoid reordering by either a) input buffering, i.e., tracking the packets at the input to identify the individual streams, and forwarding the packets of the same stream to the same queue, thus preventing reordering, or b) output buffering, i.e., buffering packets at the output of the router to ensure that the packets belonging to the same stream are released in the order of their entry into the node [15].…”

Section: A Routersmentioning

confidence: 99%

On Growth of Parallelism within Routers and Its Impact on Packet Reordering

Bare

Jayasumana

Piratla

2007

2007 15th IEEE Workshop on Local &Amp; Metropolitan Area Networks

View full text Add to dashboard Cite

Abstract-The network link speeds increase at a higher rate compared to processing speeds. This coupled with the increase in size of router tables demand higher levels of parallelism within router hardware. However, such parallelism introduces unintended consequences that potentially may negate some of the performance gains provided by the improved technology. The growth trends of computing speeds, link speeds, and routing table sizes are used to evaluate one such consequence, packet reordering within routers. Results presented show the trends related to the degree of hardware parallelism and packet reordering I. INTRODUCTIONAs the speed of physical links and networks increase beyond gigabit per second, and the end-to-end latency to packet transmission time ratio increases by orders of magnitude, certain phenomena that were insignificant and safely ignored assume substantial importance. In fact some of these second order effects, unless countered, can negate to a significant degree the gains provided by faster physical links and routing/switching hardware, and will have an adverse impact on the end-to-end performance seen by the applications. These unavoidable phenomena include, among others, delay jitter and packet reordering. Jitter has received attention only with respect to real-time applications such as VoIP, and effects of reordering were safely ignored.According to Moore's law, the CPU computing speed approximately doubles every 18 months [1, 2], while recent trends indicate that network link speed approximately doubles every nine months [3,4]. Thus, the network link speeds increase at a faster rate than the computing speed. The Internet itself is growing in size, resulting in the increase of routing tables sizes in backbone routers [5]. Consequently, the amount of processing to be performed by the routers will increase at a faster rate than the rate of increase in the computing power. Routers will rely on architectures that use an increasing number of processors working in parallel to counter the additional computation requirements. However, processing packets from the same stream in parallel processors deteriorates the problem of reordering. The two

show abstract

Shall we worry about Packet Reordering?

Abstract: The article describes the recent standardisation initiatives for packet reordering metrics in IP networks, the methods of measuring it and also provides a discussion of the common factors affecting ordered packet delivery, based on real examples.

Cited by 26 publications

References 3 publications

A Case Study of IPv6 Network Performance: Packet Delay, Loss, and Reordering

A Case Study of IPv6 Network Performance: Packet Delay, Loss, and Reordering

ALD: adaptive layer distribution for scalable video

On Growth of Parallelism within Routers and Its Impact on Packet Reordering

Contact Info

Product

Resources

About