scispace - formally typeset
Search or ask a question
Topic

Packet loss

About: Packet loss is a research topic. Over the lifetime, 21235 publications have been published within this topic receiving 302453 citations.


Papers
More filters
Proceedings Article
02 Apr 2013
TL;DR: This work creates an engineered network and routing protocol that can almost instantaneously reestablish connectivity and load balance, even in the presence of multiple failures, and shows that following network link and switch failures, F10 has less than 1/7th the packet loss of current schemes.
Abstract: The data center network is increasingly a cost, reliability and performance bottleneck for cloud computing. Although multi-tree topologies can provide scalable bandwidth and traditional routing algorithms can provide eventual fault tolerance, we argue that recovery speed can be dramatically improved through the co-design of the network topology, routing algorithm and failure detector. We create an engineered network and routing protocol that directly address the failure characteristics observed in data centers. At the core of our proposal is a novel network topology that has many of the same desirable properties as FatTrees, but with much better fault recovery properties. We then create a series of failover protocols that benefit from this topology and are designed to cascade and complement each other. The resulting system, F10, can almost instantaneously reestablish connectivity and load balance, even in the presence of multiple failures. Our results show that following network link and switch failures, F10 has less than 1/7th the packet loss of current schemes. A trace-driven evaluation of MapReduce performance shows that F10's lower packet loss yields a median application-level 30% speedup.

208 citations

Proceedings ArticleDOI
21 Mar 1999
TL;DR: The network routing messages exchanged between core Internet backbone routers are examined to show that as a result of specific router vendor software changes suggested by earlier analysis, the volume of Internet routing updates has decreased by an order of magnitude.
Abstract: This paper examines the network routing messages exchanged between core Internet backbone routers. Internet routing instability, or the rapid fluctuation of network reachability information, is an important problem currently facing the Internet engineering community. High levels of network instability can lead to packet loss, increased network latency and time to convergence. At the extreme, high levels of routing instability have led to the loss of internal connectivity in wide-area, national networks. In an earlier study of inter-domain routing, we described widespread, significant pathological behaviour in the routing information exchanged between backbone service providers at the major US public Internet exchange points. These pathologies included several orders of magnitude more routing updates in the Internet core than anticipated, large numbers of duplicate routing messages, and unexpected frequency components between routing instability events. The work described in this paper extends our earlier analysis by identifying the origins of several of these observed pathological Internet routing behaviour. We show that as a result of specific router vendor software changes suggested by our earlier analysis, the volume of Internet routing updates has decreased by an order of magnitude. We also describe additional router software changes that can decrease the volume of routing updates exchanged in the Internet core by an additional 30 percent or more. We conclude with a discussion of trends in the evolution of Internet architecture and policy that may lead to a rise in Internet routing instability.

207 citations

Journal ArticleDOI
TL;DR: In this paper, an architectural concept is discussed and justified mathematically that relies on cascading many small switches to form a bigger switch with a larger buffer depth, providing an economical and feasible hardware solution.
Abstract: Recently, optical packet switch architectures, composed of devices such as optical switches, fiber delay lines, and passive couplers, have been proposed to overcome the electromagnetic interference (EMI), pinout and interconnection problems that would be encountered in future large electronic switch cores. However, attaining the buffer size (buffer depth) in optical packet switches required in practice is a major problem; in this paper, a new solution is presented. An architectural concept is discussed and justified mathematically that relies on cascading many small switches to form a bigger switch with a larger buffer depth. The number of cascaded switches is proportional to the logarithm of the buffer depth, providing an economical and feasible hardware solution. Packet loss performance, control and buffer dimensioning are considered. The optical performance is also modeled, demonstrating the feasibility of buffer depths of several thousand, as required for bursty traffic.

207 citations

Patent
18 Dec 1987
TL;DR: In this article, a packet dropping algorithm is used to determine when to drop a marked packet whenever the network is congested at any point along the path being traversed by the marked packet.
Abstract: A method for controlling congestion in a packet switching network uses a packet dropping algorithm to determine when to drop a marked packet wherever the network is congested at any point along the path being traversed by the marked packet.

206 citations

Proceedings ArticleDOI
08 Nov 1996
TL;DR: This paper describes an effort to characterize the loss behavior of the AT&T WaveLAN, a popular in-building wireless interface, using a trace-based approach and derives another model based on the distributions of the error and error-free length of the packet streams.
Abstract: The loss behavior of wireless networks has become the focus of many recent research efforts. Although it is generally agreed that wireless communications experience higher error rates than wireline, the nature of these lossy links is not fully understood. This paper describes an effort to characterize the loss behavior of the AT&T WaveLAN, a popular in-building wireless interface. Using a trace-based approach, packet loss information is recorded, analyzed, and validated. Our results indicate that WaveLAN experiences an average packet error rate of 2 to 3 percent. Further analysis reveals that these errors are not independent, making it hard to model them with a simple two-state Markov chain. We derive another model based on the distributions of the error and error-free length of the packet streams. For validation, we modulate both the error models and the traces in a simulator. Trace-driven simulations yield an average TCP throughput of about 5 percent less than simulations using our best error model.

205 citations


Network Information
Related Topics (5)
Network packet
159.7K papers, 2.2M citations
96% related
Wireless ad hoc network
49K papers, 1.1M citations
96% related
Wireless network
122.5K papers, 2.1M citations
95% related
Wireless sensor network
142K papers, 2.4M citations
94% related
Key distribution in wireless sensor networks
59.2K papers, 1.2M citations
93% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
2023133
2022325
2021694
2020846
20191,033
2018993