Author Archives: Steve Uhlig

The October 2021 issue

This October 2021 issue contains two technical papers, two educational contributions, and one editorial note.

The first technical paper, When Latency Matters: Measurements and Lessons Learned, by Marco Iorio and colleagues, evaluates the “latency argument” for edge computing, i.e., that placing elastic computing and storage platforms in close proximity to end-users makes sense for latency-critical applications. The paper evaluates several sources of latency, including latency induced by core network routing inefficiencies, wired and wireless access network, transport protocol and application protocol. The paper concludes that moving data-centers close to the users is only a small part of the latency problems, and that solving it requires a more careful coordination of efforts across the network stack.

The second technical paper, REDACT: Refraction Networking from the Data Center, by Arjun Devraj and colleagues, extends the concept of refraction networking by assigning the edge router of a cloud datacenter the role of a decoy router.

The first educational contribution, Machine learning-based Analysis of COVID-19 Pandemic Impact on US Research Networks, by Mariam Kiran and colleagues, sheds light on the performance of a large network throughout the COVID-19 pandemic. Extensive traces are studied and analyzed, with a number of interesting findings using various statistical techniques.

The second educational contribution, An educational toolkit for teaching cloud computing, by Cosimo Anglano and colleagues, proposes the creation of a software layer to hide the specifics of the underlying cloud platforms from students, enabling them to perform their assignments atop a general API. The proposed approach is an innovative idea to improve the educational experience of students on cloud platforms.

Finally, we have an editorial note. Data-driven Networking Research: models for academic collaboration with industry (a Google point of view), by Jeffrey C. Mogul and his colleagues, describes collaboration models aimed at stimulating data-driven networking research. The authors describe specific areas where they would welcome proposals to work within those models.

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

When latency matters: measurements and lessons learned

Marco Iorio, Fulvio Risso, Claudio Casetti

Abstract

Several emerging classes of interactive applications are demanding for extremely low-latency to be fully unleashed, with edge computing generally regarded as a key enabler thanks to reduced delays. This paper presents the outcome of a large-scale end-to-end measurement campaign focusing on task-offloading scenarios, showing that moving the computation closer to the end-users, alone, may turn out not to be enough. Indeed, the complexity associated with modern networks, both at the access and in the core, the behavior of the protocols at different levels of the stack, as well as the orchestration platforms used in data-centers hide a set of pitfalls potentially reverting the benefits introduced by low propagation delays. In short, we highlight how ensuring good QoS to latency-sensitive applications is definitely a multi-dimensional problem, requiring to cope with a great deal of customization and cooperation to get the best from the underlying network.

Download from ACM

A square law revisited

Brian Carpenter

Abstract

An earlier study observed that until 2008, the size of the BGP4 system for IPv4 appeared to have grown approximately in proportion to the square root of the host count of the globally addressable Internet. This article revisits this study by including IPv4 data until 2020 and adding IPv6 data. The results indicate that BGP4 for IPv4 is continuing to scale steadily even as IPv4 approaches its end of life, and that it is working as it should for IPv6, except for a slight concern that the number of announced routes is trending upwards faster as time goes on.

Download from ACM

Workshop on Overcoming Measurement Barriers to Internet Research (WOMBIR 2021) final report

KC Claffy, David Clark, John Heidemann, Fabian Bustamante, Mattijs Jonker, Aaron Schulman, Ellen Zegura

Abstract

In January and April 2021 we held the Workshop on Overcoming Measurement Barriers to Internet Research (WOMBIR) with the goal of understanding challenges in network and security data set collection and sharing. Most workshop attendees provided white papers describing their perspectives, and many participated in short-talks and discussion in two virtual workshops over five days. That discussion produced consensus around several points. First, many aspects of the Internet are characterized by decreasing visibility of important network properties, which is in tension with the Internet’s role as critical infrastructure. We discussed three specific research areas that illustrate this tension: security, Internet access; and mobile networking. We discussed visibility challenges at all layers of the networking stack, and the challenge of gathering data and validating inferences. Important data sets require longitudinal (long-term, ongoing) data collection and sharing, support for which is more challenging for Internet research than other fields. We discussed why a combination of technical and policy methods are necessary to safeguard privacy when using or sharing measurement data. Workshop participants proposed several opportunities to accelerate progress, some of which require coordination across government, industry, and academia.

Download from ACM

Collaboration in the IETF: an initial analysis of two decades in email discussions

Michael Welzl, Stephan Oepen, Cezary Jaskula, Carsten Griwodz, Safiqul Islam

Abstract

RFC 9000, published in May 2021, marks an important milestone for the Internet’s standardization body, the Internet Engineering Task Force (IETF): finally, the specification of the QUIC protocol is available. QUIC is the result of a five-year effort – and it is also the second of two major protocols (the first being SPDY, which later became HTTP/2) that Google LLC first deployed, and then brought to the IETF for standardization. This begs the question: when big players follow such a “shoot first, discuss later” approach, is IETF collaboration still “real”, or is the IETF now being (mis-)used to approve protocols for standardization when they are already practically established, without really actively involving anyone but the main proponents?

Download from ACM

Limited domains considered useful

Brian Carpenter, Jon Crowcroft, Dirk Trossen

Abstract

Limited domains were defined conceptually in RFC 8799 to cater to requirements and behaviours that extend the dominant view of IP packet delivery in the Internet. This paper argues not only that limited domains have been with us from the very beginning of the Internet but also that they have been shaping innovation of Internet technologies ever since, and will continue to do so. In order to build limited domains that successfully interoperate with the existing Internet, we propose an architectural framework as a blueprint. We discuss the role of the IETF in ensuring continued innovation in Internet technologies by embracing the wider research community’s work on limited domain technology, leading to our key insight that Limited Domains are not only considered useful but a must to sustain innovation.

Download from ACM

P4Pi: P4 on Raspberry Pi for networking education

Sándor Laki, Radostin Stoyanov, Dávid Kis, Robert Soulé, Péter Vörös, Noa Zilberman

Abstract

High level, network programming languages, like P4, enable students to gain hands-on experience in the structure of a switch or router. Students can implement the packet processing pipeline themselves, without prior knowledge of circuit design. However, when choosing a P4 programmable target for use in the classroom, instructors face a lack of options. On the one hand, software solutions, such as the behavioral model (BMv2) switch, are overly simplified and offer low performance. On the other hand, existing hardware solutions are closed source and expensive.

In this paper, we present P4Pi, a new, low-cost, open-source hardware platform intended for networking education. P4Pi allows students to design and deploy P4-based network devices using the Raspberry Pi board, which has a price tag of less than many academic textbooks. We describe the high-level design of the P4Pi platform, offer some suggestions for how P4Pi could be used in the classroom, and present some additional use-cases for applications and functionality that could be developed using P4Pi.

Download from ACM

The graph neural networking challenge: a worldwide competition for education in AI/ML for networks

José Suárez-Varela, Miquel Ferriol-Galmés, Albert López, Paul Almasan, Guillermo Bernárdez, David Pujol-Perich, Krzysztof Rusek, Loïck Bonniot, Christoph Neumann, François Schnitzler, François Taïani, Martin Happ, Christian Maier, Jia Lei Du, Matthias Herlich, Peter Dorfinger, Nick Vincent Hainke, Stefan Venz, Johannes Wegener, Henrike Wissing, Bo Wu, Shihan Xiao, Pere Barlet-Ros, Albert Cabellos-Aparicio

Abstract

During the last decade, Machine Learning (ML) has increasingly become a hot topic in the field of Computer Networks and is expected to be gradually adopted for a plethora of control, monitoring and management tasks in real-world deployments. This poses the need to count on new generations of students, researchers and practitioners with a solid background in ML applied to networks. During 2020, the International Telecommunication Union (ITU) has organized the “ITU AI/ML in 5G challenge”, an open global competition that has introduced to a broad audience some of the current main challenges in ML for networks. This large-scale initiative has gathered 23 different challenges proposed by network operators, equipment manufacturers and academia, and has attracted a total of 1300+ participants from 60+ countries. This paper narrates our experience organizing one of the proposed challenges: the “Graph Neural Networking Challenge 2020”. We describe the problem presented to participants, the tools and resources provided, some organization aspects and participation statistics, an outline of the top-3 awarded solutions, and a summary with some lessons learned during all this journey. As a result, this challenge leaves a curated set of educational resources openly available to anyone interested in the topic.

Download from ACM

NemFi: record-and-replay to emulate WiFi

Abhishek kumar Mishra, Sara Ayoubi, Giulio Grassi, Renata Teixeira

Abstract

This paper presents NemFi: a trace-driven WiFi emulator. NemFi is a record-and-replay emulator that captures traces representing real WiFi conditions, and later replay these traces to reproduce the same conditions. In this paper, we demonstrate that the state-of-the-art emulator that was developed for cellular links cannot emulate WiFi conditions. We identify the three key differences that must be addressed to enable accurate WiFi record-and-replay: WiFi packet losses, medium-access control, and frame aggregation. We then extend the existing cellular network emulator to support WiFi record-and-replay. We evaluate the performance of NemFi via repeated experimentation across different WiFi conditions and for three different types of applications: speed-test, file download, and video streaming. Our experimental results demonstrate that average application performance over NemFi and real WiFi links is similar (with less than 3 percent difference).

Download from ACM

The July 2021 issue

This July 2021 issue contains one technical paper, two educational contributions, as well as four editorial notes.

The technical paper, NemFi: Record-and-replay to emulate WiFi, by Abhishek kumar Mishra and colleagues, proposes a trace-driven WiFi emulator called NemFi, that allows modeling of transmission opportunities of uplink and downlink directions, packet loss, frame aggregation, and media access control behavior. The latter two concepts are unique for WiFi when compared with other similar tools that have been built for cellular networks.

The first educational contribution, The Graph Neural Networking Challenge: A Worldwide Competition for Education in AI/ML for Networks, by Jose Suarez-Varela and colleagues, proposes a ”challenge” to teach students about applications of AI/MLin computer networks. The authors describe a process to select a dataset, and a competition-based approach where participants must design a neural-network-based approach to infer properties of the dataset with as much accuracy as possible.

The second educational contribution, P4Pi: P4 on Raspberry Pi for Networking Education, by Sandor Laki and colleagues, presents a novel platform for networking education based on a Raspberry Pi, allowing students to program P4.

Then, we have four editorial notes. The first one, Limited Domains Considered Useful, by Brian Carpenter and his colleagues, argues not only that limited domains have been with us from the very beginning of the Internet but also that they have been shaping innovation of Internet technologies ever since, and will continue to do so.

The second editorial note, Collaboration in the IETF: An Initial Analysis of Two Decades in Email Discussions, by Michael Welzl and his colleagues, discusses the following question: when big players follow such a “shoot first, discuss later” approach, is IETF collaboration still “real”, or is the IETF now being (mis-)used to approve protocols for standardization when they are already practically established, without really actively involving anyone but the main proponents?

The third editorial note, Workshop on Overcoming Measurement Barriers to Internet Research (WOMBIR 2021) Final Report, by kc claffy and her colleagues, reports on the Workshop on Overcoming Measurement Barriers to Internet Research (WOMBIR), held earlier in 2021.

The fourth and last editorial note, A Square Law Revisited, by Brian Carpenter, revisits the approximate apparent growth of the globally addressable Internet in proportion to the square root of the host count.

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