An experimental analysis of BGP convergence time

Griffin, Timothy G.; Premore, Brian J.

doi:10.1109/icnp.2001.992760

Cited by 129 publications

(151 citation statements)

References 19 publications

Supporting

Mentioning

139

Contrasting

Order By: Relevance

“…However, measurements from a BGP/MPLS VPN environment [17] have revealed a long BGP convergence time and network instability after the failure of an EP. Several proposals [18,19] have been made to reduce the convergence time by reducing the number of BGP messages that must be exchanged after a failure. However, as they rely on the exchange of messages, the achieved convergence time does not typically meet the stringent requirements of real time services.…”

Section: Solution Implementationmentioning

confidence: 99%

A Closed-Loop Control Traffic Engineering System for the Dynamic Load Balancing of Inter-AS Traffic

Amin

Pavlou

et al. 2009

J Netw Syst Manage

View full text Add to dashboard Cite

Inter-AS outbound traffic engineering (TE) is a set of techniques for controlling inter-AS traffic exiting an autonomous system (AS) by assigning the traffic to the best egress points (i.e. routers or links) from which the traffic is forwarded to adjacent ASes towards the destinations. In practice, changing network conditions such as inter-AS traffic demand variation, link failures and inter-AS routing changes occur dynamically. These changes can make fixed outbound TE solutions inadequate and may subsequently cause inter-AS links to become congested. In order to overcome this problem, we propose the deployment of a closed loop control traffic engineering system that makes outbound traffic robust to inter-AS link failures and adaptive to changing network conditions. The objective is to keep the inter-AS link utilization balanced under unexpected events while reducing service disruption and reconfiguration overheads. Our evaluation results show that the proposed system can successfully achieve better load balancing with less service disruption and re-configuration overhead in comparison to alternative approaches.

show abstract

Section: Solution Implementationmentioning

confidence: 99%

A Closed-Loop Control Traffic Engineering System for the Dynamic Load Balancing of Inter-AS Traffic

Amin

Pavlou

et al. 2009

J Netw Syst Manage

View full text Add to dashboard Cite

show abstract

“…We believe that the behavior observed by Griffin and Premore [6] can be explained in terms of processing overhead of BGP updates. Let's assume that a node A sends an update to a neighbor B at time t. Then, if the MRAI is set to the optimal value, then there is a high probability that A has processed all the update messages in its queue by the time t+Optimal MRAI.…”

Section: Bgp Convergence Delaymentioning

confidence: 92%

“…Griffin and Premore [6] studied the effect of MRAI on the convergence time after a fault was initiated in simple BGP networks. They found that as the MRAI is increased, the convergence time first goes down to a minimum and then increases linearly .…”

Section: Bgp Convergence Delaymentioning

confidence: 99%

“…In particular, it was shown by Labovitz et al [5] that the convergence delay for isolated route withdrawals can be > 3 min in 30% of the cases, and could be as high as 15 minutes. Models [6], [7] have been developed to estimate the BGP convergence delay, but the complexity of analysis has meant that simplifying assumptions need to be made, and most of the work in this field has been concentrated on single failures and simple networks.…”

Section: Introductionmentioning

confidence: 99%

“…Numerous studies [4], [5], [6], [7], [8], [9] have been carried out to study the fault tolerance and recovery characteristics of BGP. In particular, it was shown by Labovitz et al [5] that the convergence delay for isolated route withdrawals can be > 3 min in 30% of the cases, and could be as high as 15 minutes.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Improving BGP Convergence Delay for Large-Scale Failures

Sahoo

Kant

Mohapatra

International Conference on Dependable Systems and Networks (DSN'06)

View full text Add to dashboard Cite

Border Gateway Protocol(BGP) is the standard routing protocol used in the Internet for routing packets between the Autonomous Systems(AS'es). It is known that BGP can take hundreds of seconds to converge after isolated failures. We have also observed that the convergence delay can be even greater for large-scale failures. In this study, we first investigate some of the factors affecting the convergence delay and their relative impacts. We observe that the Minimum Route Advertisement Interval (MRAI) and the processing overhead at the routers during the re-convergence have a significant impact on the BGP recovery time. We propose a novel batching scheme to reduce the number of BGP updates, and thereby decrease route update flapping. We show that this batching scheme and the tuning of the MRAI value decrease the BGP convergence delay significantly, and can thus limit the impact of large scale failures in the Internet.

show abstract

Impact of Routing Lags on Internet Routing Failures

Wang

Gao

2005

NETWORKING 2005. Networking Technologies, Services, and Protocols; Performance of Computer and Communication Networks; Mobile A

View full text Add to dashboard Cite

Abstract. Studies have shown that the Internet has experienced the widespread failures such as router crash, fiber cut, or scheduled maintenance. Ideally, routing protocols should be able to quickly find alternate paths to reroute around failures. In this paper, we consider one important factor that prevents routing protocols from achieving this goal: the delay of finding and obtaining alternate paths, defined as routing lag. We show that a significant number of routing failures in the Internet are caused by routing lags, and they can last for a significant period of time.

show abstract

An experimental analysis of BGP convergence time

Abstract: The Border Gateway Protocol (BGP)

Cited by 129 publications

References 19 publications

A Closed-Loop Control Traffic Engineering System for the Dynamic Load Balancing of Inter-AS Traffic

A Closed-Loop Control Traffic Engineering System for the Dynamic Load Balancing of Inter-AS Traffic

Improving BGP Convergence Delay for Large-Scale Failures

Impact of Routing Lags on Internet Routing Failures

Contact Info

Product

Resources

About