Marjory Blumenthal, Ramesh Govindan, Ethan Katz-Bassett, Arvind Krishnamurthy, James McCauley, Nick Merrill, Tejas Narechania, Aurojit Panda, Scott Shenker

Abstract

The goal of this short document is to explain why recent developments in the Internet’s infrastructure are problematic. As context, we note that the Internet was originally designed to provide a simple universal service – global end-to-end packet delivery – on which a wide variety of end-user applications could be built. The early Internet supported this packet-delivery service via an interconnected collection of commercial Internet Service Providers (ISPs) that we will refer to collectively as the “public Internet.” The Internet has fulfilled its packet-delivery mission far beyond all expectations and is now the dominant global communications infrastructure. By providing a level playing field on which new applications could be deployed, the Internet has enabled a degree of innovation that no one could have foreseen. To improve performance for some common applications, “enhancements” such as caching (as in content-delivery networks) have been gradually added to the Internet. The resulting performance improvements are so significant that such enhancements are now effectively necessary to meet current content delivery demands. Despite these tangible benefits, this document argues that the way these enhancements are currently deployed seriously undermines the sustainability of the public Internet and could lead to an Internet infrastructure that reaches fewer people and is largely concentrated among only a few large-scale providers. We wrote this document because we fear that these developments are now decidedly tipping the Internet’s playing field towards those who can deploy these enhancements at massive scale, which in turn will limit the degree to which the future Internet can support unfettered innovation. This document begins by explaining our concerns but goes on to articulate how this unfortunate fate can be avoided. To provide more depth for those who seek it, we provide a separate addendum with further detail.

Download from ACM

Justine Sherry

Abstract

Many researchers are turning to SmartNIC offloads to improve the performance of high-performance networked systems. In this editorial, I discuss why SmartNICs are an especially powerful form factor for improving I/O intensive applications, and how their position in the dataplane enables them to take on central role in managing I/O. Rather than focusing on the benefits of individual offloads, this paper aims to explore the position of SmartNICs in the overall system integration of datacenter servers at the hardware and software level. I argue that SmartNICs should be viewed as ‘data movement controllers’ (NIC-DMCs) which are responsible for tasks involved in moving data between network, CPU, accelerators, and other endpoints: multiplexing/steering, interfacing between protocols, and enforcing I/O policies. I then enumerate open questions in how the hardware and software systems of the future will evolve to accommodate a dedicated NIC-DMC which is independent of the CPU complex.

Download from ACM

Quentin De Coninck, Louis Navarre, Nicolas Rybowski

Abstract

eBPF is a popular technology originating from the Linux kernel that enables safely running user-provided programs in a kernel-context. This technology opened the door for efficient programming in the operating system, especially in its network stack. However, its applicability is not limited to the Linux kernel. Various efforts leveraged the eBPF Instruction Set Architecture (ISA) as the basis of other networking related use cases outside of the Linux kernel. This paper focuses on the pluginized protocols’ use case such as PQUIC and xBGP where the eBPF ISA serves as the basis to execute plugins providing per-session protocol behavior. It first quickly describes how the Linux kernel builds around this eBPF ISA to provide enhanced in-kernel network programmability. Then, the paper considers the case of pluginized protocols. Leveraging eBPF outside of the Linux kernel environment requires complementing the eBPF ISA to meet the pluginized protocols’ requirements. This paper details these integration efforts. Based on the lessons learned from these, it finally concludes by an applicability discussion of the eBPF ISA to other use cases.

Download from ACM

This October 2023 issue contains three editorial notes.

The observing reader of CCR will have noticed that there is no July 2023 issue. There are three main factors at play here. Given the timing of our SIGCOMM conferences, summer is a low period for submissions to CCR. Then, as CCR is selective and its scope limited to timely works relevant to our community, few technical papers make it above our bar. Finally, I have witnessed a healthy shift away from technical papers towards more thought-provoking editorials over the last few years. We have enough conference and journals for technical papers to find an appropriate venue. On the other hand, our conferences and journals, due to their selective nature and the overly critical nature of the reviewing process, do not lend themselves to welcome thought-provoking and contentious contributions. Let CCR be their home.

The first editorial note, On Integrating eBPF into Pluginized Protocols, by Quentin De Coninck, Louis Navarre, and Nicolas Rybowski, considers the case of pluginized protocols, by leveraging eBPF outside of the Linux kernel environment. The second editorial note, The I/O Driven Server: From SmartNICs to Data Movement Controllers, by Justine Sherry, explores the position of SmartNICs in the overall system integration of datacenter servers at the hardware and software level. The third editorial note, Can We Save The Public Internet?, by Marjory Blumenthal, Ramesh Govindan, Ethan Katz-Bassett, Arvind Krishnamurthy, James McCauley, Nick Merrill, Tejas Narechania, Aurojit Panda, and Scott Shenker, explains why recent developments in the Internet’s infrastructure are problematic, and how we could prevent an evolution of the Internet that impedes on its original design principles and goals.

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.