Author Archives: Olivier Bonaventure

Wi-Stitch: Content Delivery in Converged Edge Networks

Aravindh Raman, Nishanth Sastry, Arjuna Sathiaseelan, Jigna Chandaria, Andrew Secker
Abstract

Wi-Fi, the most commonly used access technology at the very edge, supports download speeds that are orders of magnitude faster than the average home broadband or cellular data connection. Furthermore, it is extremely common for users to be within reach of their neighbours’ Wi-Fi access points. Given the skewed nature of interest in content items, it is likely that some of these neighbours are interested in the same items as the users. We sketch the design of Wi-Stitch, an architecture that exploits these observations to construct a highly efficient content sharing infrastructure at the very edge and show through analysis of a real workload that it can deliver substantial (up to 70%) savings in network traffic. The Wi-Stitch approach can be used both by clients of fixed-line broadband, as well as mobile devices obtaining indoors access in converged networks.

Download the full article DOI: 10.1145/3155055.3155067

DICE: Dynamic Multi-RAT Selection in the ICN-enabled Wireless Edge

Gaurav Panwar, Reza Tournai, Travis Mick, Abderrahmen Mtibaa, Satyajayant Misra
Abstract

Coupled with the rapid increase in mobile device users and the bandwidth and latency demands are the continuous increase of devices’ processing capabilities, storage, and wireless connectivity options. The multiple radio access technology (multi-RAT) is proposed to satisfy mobile users’ increasing needs. The Information-Centric Networking (ICN) paradigm is better tuned (than the current Internet Protocol approach) to support multi-RAT communications. ICN eschews the connection-based content retrieval model used today and has desirable features such as data naming, in-network caching, and device mobility–a paradigm ripe for exploration.

We propose DICE, an ICN forwarding strategy that helps a device dynamically select a subset of its multi-RAT interfaces for communication. DICE assesses the state of edge links and network congestion to determine the minimum number of interfaces required to perform data delivery. We perform simulations to compare DICE’s performance with bestroute2 and multicast strategies (part of the named data networking simulator, ndnSIM). We show that DICE is the best of both worlds: providing a higher delivery ratio (0.2–2 times) and much lower overhead (by 2–8 times) for different packet rates.

Download the full article DOI: 10.1145/3155055.3155066

 

Report on Networking and Programming Languages 2017

Nikolaj Bjorne, Marco Canini, Nik Sultana
Abstract

The third workshop on Networking and Programming Languages, NetPL 2017, was held in conjunction with SIGCOMM 2017. The workshop series attracts invited speakers from academia and industry and a selection of contributed abstracts for short presentations. NetPL brings together researchers from the networking community and researchers from the programming languages and verification communities. The workshop series is a timely forum for exciting trends, technological and scientific advances in the intersection of these communities.

We describe some of the highlights from the invited talks through the lens of three trends: Advances in network machine architectures, network programming abstractions, and network verification.

NetPL included five invited speakers, four from academia, and one from industry. The program contained six contributed papers out of eight submitted for presentation. The workshop organizers reviewed the abstracts for quality and scope. A total of 42 registrations were received and the attendance occupied the lecture room to the brink.

Slides and abstracts from all talks are available from the workshop home page: http://conferences.sigcomm.org/sigcomm/2017/workshop-netpl.html. Videos of the presentations are available in the NetPL YouTube channel: https://www.youtube.com/channel/UCqU8E2n4MHthZUVb1xK2nRQ.

Download the full article DOI: 10.1145/3155055.3155061

[Community Feedback] A Scalable VPN Gateway for Multi-Tenant Cloud Services

This paper has been submitted to CCR. This is a draft version of the paper that has not been peer-reviewed. Comments on the paper or the supplementary material are encouraged through the comment facility at the bottom of this page.
M. Arashloo, P. Shirshov, R. Gandhi, G. Lu, L. Yuan, J. Rexford
Abstract

Major cloud providers offer networks of virtual machines with private IP addresses as a service on the cloud. To isolate the address space of different customers, customers are required to tunnel their traffic to a Virtual Private Network (VPN) gateway, which is typically a middlebox inside the cloud that internally tunnels each packet to the correct destination. To improve performance, an increasing number of enterprises connect directly to the cloud provider’s network at the edge, to a device that we call the provider’s edge (PE). PE is a chokepoint for customer’s traffic to the cloud, and therefore a natural candidate for implementing network functions concerning customers’ virtual networks, including the VPN gateway, to avoid a detour to middleboxes inside the cloud.

At the scale of today’s cloud providers, VPN gateways need to maintain information for around a million internal tunnels. We argue that no single commodity device can handle these many tunnels while providing a high enough port density to connect to hundreds of cloud customers at the edge. Thus, in this paper, we propose a hybrid architecture for the PE, consisting of a commodity switch, connected to a commodity server which uses Data-Plane Development Kit (DPDK) for fast packet processing. This architecture enables a variety of network functions at the edge by offering the benefits of both hardware and software data planes. We implement a scalable VPN gateway on our proposed PE and show that it matches the scale requirements of today’s cloud providers while processing packets close to line rate.

Draft article

 

[Community Feedback] A Longitudinal Study of Utilization at Internet Interconnection Points

This paper has been submitted to CCR. This is a draft version of the paper that has not been peer-reviewed. Comments on the paper or the supplementary material are encouraged through the comment facility at the bottom of this page.
N. Feamster
Abstract

The increase in high-volume traffic flows due to applications such as video streaming draw new attention on utilization at the interconnections between the Internet’s independently operated networks. This paper surveys the findings from nearly two years of Internet utilization data provided by seven participating ISPs—Bright House Networks, Comcast, Cox, Mediacom, Midco, Suddenlink, and Time Warner Cable—whose access networks represent about 50% of all U.S. broadband subscribers. The dataset spans 18 months and includes about 97% of the paid peering, settlement-free peering, and ISP- paid transit links of each of the participating ISPs. Analysis of the data—which comprises more than 1,000 link groups, representing the diverse and substitutable available routes— suggests that many interconnects have significant spare capacity, that this spare capacity exists both across ISPs in each region and in aggregate for any individual ISP, and that the aggregate utilization across interconnects is roughly 50% during peak periods.

Draft article

Supplementary material

[Community Feedback] Towards a Rigorous Methodology for Measuring Adoption of RPKI Route Validation and Filtering

This paper has been submitted to CCR. This is a draft version of the paper that has not been peer-reviewed. Comments on the paper or the supplementary material are encouraged through the comment facility at the bottom of this page.
A. Reuter, R. Bush, I. Cunha, E. Katz-Bassett, T. Schmidt, M. Wählisch
Abstract

A proposal to improve routing security – Route Origin Authorization (ROA) – has been standardized. A ROA specifies which network is allowed to announce a set of Internet destinations. While some networks now specify ROAs, little is known about whether other networks check routes they receive against these ROAs, a process known as Route Origin Validation (ROV). Which networks blindly accept invalid routes? Which reject them outright? Which de-preference them if alternatives exist? Recent analysis attempts to use uncontrolled experiments to characterize ROV adoption by comparing valid routes and invalid routes. However, we argue that gaining a solid understanding of ROV adoption is impossible using currently available data sets and techniques. Our measurements suggest that, although some ISPs are not observed using invalid routes in uncontrolled experiments, they are actually using different routes for (non-security) traffic engineering purposes, without performing ROV. We conclude with a description of a controlled, verifiable methodology for measuring ROV and present three ASes that do implement ROV, confirmed by operators.

Draft article

 

[Community Feedback] A Hypergiant’s View of the Internet

This paper has been submitted to CCR. This is a draft version of the paper that has not been peer-reviewed. Comments on the paper or the supplementary material are encouraged through the comment facility at the bottom of this page.
T. Better, F. Cuadrado, G. Tyson, I. Castro, S. Uhlig
Abstract

The importance of IXPs to interconnect different networks and exchange traffic locally has been well studied over the last few years. However, far less is known about the role IXPs play as a platform to enable large-scale content delivery and to reach a world-wide customer base. In this paper, we study the infrastructure deployment of a content hypergiant, Netflix, and show that the combined worldwide IXP substrate is the major corner stone of its Content Delivery Network. This highlights the additional role that IXPs play in the Internet ecosystem, not just in terms of interconnection, but also allowing players such as Netflix to deliver significant amounts of traffic.

Draft article

 

[Community Feedback] A longitudinal study of IP Anycast

This paper has been submitted to CCR. This is a draft version of the paper that has not been peer-reviewed. Comments on the paper or the supplementary material are encouraged through the comment facility at the bottom of this page.
D. Cicalese, D. Rossi
Abstract

IP anycast is a commonly used technique to share the load of a variety of global services. For more than one year, leveraging a lightweight technique for IP anycast detection, enumeration and geolocation, we perform regular IP monthly censuses. While this paper provides a brief longitudinal study of the anycast ecosystem, we make all our datasets (raw measurement from PlanetLab and RIPE Atlas), results (monthly geolocated anycast replicas for all IP/24) and code available to the community.

Draft article

[Community Feedback] Looking for Hypergiants in PeeringDB

This paper has been submitted to CCR. This is a draft version of the paper that has not been peer-reviewed. Comments on the paper or the supplementary material are encouraged through the comment facility at the bottom of this page.
T. Bottger, F. Cuadrado, S. Uhlig
Abstract

Hypergiants, such as Google or Netflix, are important organ- isations in the Internet ecosystem, due to their sheer impact in terms of traffic volume exchanged. However, the research community still lacks a sufficiently crisp definition for them, beyond naming specific instances of them. In this paper we analyse PeeringDB data and derive a set of defining char- acteristics for hypergiants. To this end, we first character- ise the organisations present in PeeringDB, allowing us to identify discriminating properties of the these organisations. We then show that these properties differentiate hypergiants well from other organisations. We conclude this paper by investigating how hypergiants exploit the IXP ecosystem to reach the global IPv4 space.

Draft article

Supplementary material

The July 2017 Issue

Computer Communication Review (CCR) continues to evolve. As announced earlier, we now accept technical articles that are longer than six pages provided that the authors release software or datasets to help readers to repeat or reproduce the main results described in the paper. These articles are reviewed on the basis of their technical merits and the supplied artifacts are also peer-reviewed. The summary of those two reviews are attached to each accepted paper. All the technical papers that appear in this issue provide artifacts.

The CCR Online website, https:// ccronline.sigcomm.org has been enhanced with a comments section to encourage inter- actions between readers and authors. We have also launched the Community Com- ments section on CCR Online. This section contains preprints of submitted papers while they are being reviewed. Readers are en- couraged to provide constructive comments to these papers. Authors have to opt-in to have their papers listed in this section.

In 2003, David Clark and his colleagues proposed a vision of a knowledge plane for the Internet. In our first technical paper, Albert Mestres and his colleagues revisit this vision and propose Knowledge-Defined Networking. This paper argues that Software-Defined Networking (SDN) and Network Analytics (NA) are two subdomains where in- teractions between Artificial Intelligence and networking would bring many benefits. The provide both use cases and simple experi- mental results. The available software and datasets could serve as a starting point for researchers willing to explore this emerging field.

Our second technical paper tackles a different topic. Ivan Voitalov and his colleagues propose a new routing scheme in Geohyperbolic Routing and Addressing Schemes. A key concern when designing a routing scheme is the scalability of the solution and the size of the forwarding tables. The solution proposed in this paper couples network topology design with a specific addressing scheme so that forwarding tables and update messages are minimised. The proposed solution is evaluated by simulations and the authors release their software and datasets.

In our third technical paper, On the Evolution of ndnSIM: an Open-Source Simulator for NDN Experimentation, Spyridon Mastorakis et al. describe the ndnSIM network simulator. The first version of this simulator was released in 2012 and it has continuously evolved since. The paper describes the evolution of the simulator, some results and the lessons learned by the authors that would probably apply to other open source projects.

Two editorials also appear in this issue. The first one, co-authored by kc Claffy and David Clark summarises the 7th interdisciplinary Workshop on Internet Economics (WIE) that was held in December 2016. In our second editorial, Using Networks to Teach About Networks (Report on Dagstuhl Seminar #17112), Jurgen Schonwalder and his colleagues summarise a recent Dagsthul seminar that was entirely devoted to network education.

I hope that you will enjoy reading this new issue and welcome comments and suggestions on CCR Online or by email at ccr-editor at sigcomm.org.