Routing Scalability: An Operator's View

Zhao, Xiaoliang; Pacella, Dante; Schiller, Jason

doi:10.1109/jsac.2010.101004

Cited by 36 publications

(36 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, the lower bound remains firm as long as we do not have control over the allocation of node ids and thereby the order of symbols in s v is essentially random 3 . The entropy bound is computable for any graph at least empirically: we just need to obtain the forwarding functions and then evaluate the entropy over the port id distribution, which can certainly be done with enough computing power at hand; the results are verifiable as we can easily evaluate the entropy on real forwarding table traces from production routers (see later); and the model is also implementable in actual router hardware, even though current wavelet tree implementations' performance might lag behind a bit (but see [10] on how to overcome this issue).…”

Section: The Modelmentioning

confidence: 99%

“…Yet, it seems very likely that we can cope in the long term, by leveraging Moore's Law or, say, moving BGP entirely to the cloud [2]. In reality it is the data plane, with its custom line card ASICs and SRAM modules and stringent real-time performance requirements, where Internet scalability issues manifest themselves most markedly [3,4]. And even though subject to concentrated research efforts [5] and heated debates [6,7], there is still no clear answer to the question as to whether the Internet routing architecture will scale to the foreseeable future.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An Information-Theoretic Approach to Routing Scalability

Rétvári

Szabó

Gulyás

et al. 2014

Proceedings of the 13th ACM Workshop on Hot Topics in Networks

View full text Add to dashboard Cite

Many of our computer networks, not the least of which the Internet, are built upon hop-by-hop routing. At the moment, it is not clear whether we will be able to scale these networks into the future economically. In this paper, we propose a new information-theoretic model to study routing scalability, we present preliminary analysis suggesting that hop-by-hop routing tolerates network growth surprisingly efficiently, and we sketch the scalability map of the Internet which we then use to make some bold predictions.

show abstract

Section: The Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

An Information-Theoretic Approach to Routing Scalability

Rétvári

Szabó

Gulyás

et al. 2014

Proceedings of the 13th ACM Workshop on Hot Topics in Networks

View full text Add to dashboard Cite

show abstract

“…Handling the initial traffic is a major concern for deploying cache mechanisms [17]. To address this issue effectively, we fill up the initial empty cache with a set of leaf prefixes from the FIB that cover the most IP addresses.…”

Section: Cache Operationsmentioning

confidence: 99%

“…One of the biggest concerns for ISPs is how to handle the initial traffic when the cache starts with an empty set [17]. Instead of a cold start, we fill the initial empty cache completely with the shortest non-overlapping prefixes if there is no history of popular prefixes available.…”

Section: Initial Traffic Handlingmentioning

confidence: 99%

“…possibilities to mitigate the routing scalability issue, and concluded that FIB size reduction would be the most promising solution from an operator's view [17]. One approach to reducing the impact of large FIBs is to use highspeed memory as a cache to store the most popular routes [2,6,8,15], while storing the full FIB in lower-cost memory.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Efficient FIB caching using minimal non-overlapping prefixes

Liu

Amin

Wang

2013

SIGCOMM Comput. Commun. Rev.

View full text Add to dashboard Cite

The size of the global Routing Information Base (RIB) has been increasing at an alarming rate. This directly leads to the rapid growth of the global Forwarding Information Base (FIB) size, which raises serious concerns for ISPs as the FIB memory in line cards is much more expensive than regular memory modules and it is very costly to increase this memory capacity frequently for all the routers in an ISP. One potential solution is to install only the most popular FIB entries into the fast memory (i.e., a FIB cache), while storing the complete FIB in slow memory. In this paper, we propose an effective FIB caching scheme that achieves a considerably higher hit ratio than previous approaches while preventing the cache-hiding problem. Our experimental results show that with only 20K prefixes in the cache (5.36% of the actual FIB size), the hit ratio of our scheme is higher than 99.95%. Our scheme can also handle cache misses, cache replacement and routing updates efficiently.

show abstract

A mapping forwarding approach for supporting mobility in networks with identifier/locator separation

Qiu

Luo

et al. 2011

Int J Communication

View full text Add to dashboard Cite

SUMMARYThe identifier/locator separation has been widely recognized as a feasible solution for addressing the current Internet's routing scaling problem. Moreover, such a separation solution in terms of mobility can keep connection survivability and support global seamless roaming. A critical challenge in supporting efficient mobility is how to update the identifier‐to‐locator mappings of mobile nodes (MNs). In this paper, we propose a mapping forwarding (MF) scheme for location management in the identifier/locator separation architecture. In the MF scheme, a tunnel router (xTR) is selected as an agent of an MN and keeps the MN's identifier‐to‐locator mapping invariable by setting up an MF chain. As long as the MN is managed by the same xTR, the MN's mapping stored in the xTR of each correspondent node of the MN does not need to be updated, thus reducing the location update signaling cost. Meanwhile, the unchanged mapping assures the correct forwarding of packets, which reduces mobility‐related disruption and enhances the location management's reliability. In addition, for the handoff in two MF chains, we propose a data‐triggered update scheme that can achieve route optimization. To evaluate the proposed MF scheme, we establish two analytical models and formulate the blocking probability and the total protocol cost. The performance results show how the blocking probability changes under various parameters and how the MF scheme can effectively reduce the blocking probability compared with the location management scheme without the MF strategy. Meanwhile, our analysis demonstrates that the MF scheme has a lower overhead when the mobility rate is high. Copyright © 2011 John Wiley & Sons, Ltd.

show abstract

Routing Scalability: An Operator's View

Cited by 36 publications

References 3 publications

An Information-Theoretic Approach to Routing Scalability

An Information-Theoretic Approach to Routing Scalability

Efficient FIB caching using minimal non-overlapping prefixes

A mapping forwarding approach for supporting mobility in networks with identifier/locator separation

Contact Info

Product

Resources

About