This paper describes and evaluates new techniques for network-originated retransmissions for end-to-end transport connections, yielding performance benefits for encrypted transport protocols in lossy settings. We use set-reconciliation techniques based on the Rateless IBLT to let receivers efficiently acknowledge encrypted packets to a middlebox, without modifying the sender or the underlying wire format. The scheme integrates awareness of in-network retransmissions within transport receivers, which delay some selective-acknowledgment ranges to reduce spurious end-to-end retransmissions. With these tools, transport receivers can receive protocol-agnostic, network-originated retransmissions for encrypted transport connections.

We describe a system for serverless computing where users, programs, and the underlying platform share a common representation of a computation: a deterministic procedure, run in an environment of well-specified data or the outputs of other computations. This representation externalizes I/O: data movement over the network is performed exclusively by the platform. Applications can describe the precise data needed at each stage, helping the provider schedule tasks and network transfers to reduce starvation. The design suggests an end-to-end argument for outsourced computing, shifting the service model from ``pay-for-effort'' to ``pay-for-results.''

In the 1990s, many networks deployed performanceenhancing proxies (PEPs) that transparently split TCP connections to aid performance, especially over lossy, long-delay paths. Two recent developments have cast doubts on their relevance: the BBR congestion-control algorithm, which deemphasizes loss as a congestion signal, and the QUIC transport protocol, which prevents transparent connection-splitting yet empirically matches or exceeds TCP's performance in wide deployment, using the same congestion control. In light of this, are PEPs obsolete? This paper presents a range of emulation measurements indicating: "probably not." While BBR's original 2016 version didn't benefit markedly from connection-splitting, more recent versions of BBR do and, in some cases, even more so than earlier "loss-based" congestion-control algorithms. We also find that QUIC implementations of the "same" congestion-control algorithms vary dramatically and further differ from those of Linux TCP-frustrating head-to-head comparisons. Notwithstanding their controversial nature, our results suggest that PEPs remain relevant to Internet performance for the foreseeable future.

In response to concerns about protocol ossification and privacy, post-TCP transport protocols such as QUIC and Web-RTC include end-to-end encryption and authentication at the transport layer. This makes their packets opaque to middleboxes, freeing the transport protocol to evolve but preventing some in-network innovations and performance improvements. This paper describes sidekick protocols: an approach to innetwork assistance for opaque transport protocols where innetwork intermediaries help endpoints by sending information adjacent to the underlying connection, which remains opaque and unmodified on the wire. A key technical challenge is how the sidekick connection can efficiently refer to ranges of packets of the underlying connection without the ability to observe cleartext sequence numbers. We present a mathematical tool called a quACK that concisely represents a selective acknowledgment of opaque packets, without access to cleartext sequence numbers. In real-world and emulation-based evaluations, the sidekick improved performance in several scenarios: early retransmission over lossy Wi-Fi paths, proxy acknowledgments to save energy, and a path-aware congestion-control mechanism we call PACUBIC that emulates a "split" connection.

In fields like data mining and natural language processing, design contests have been successfully used to advance the state of the art. Such contests offer an opportunity to bring the excitement and challenges of protocol design—one of the core intellectual elements of research and practice in networked systems—to a broader group of potential contributors, whose ideas may prove important. More-over, it may lead to an increase in the number of students, especially undergraduates or those learning via online courses, interested in pursuing a career in the field. We describe the creation of the infrastructure and our experience with a protocol design contest conducted in MIT’s graduate Computer Networks class. This contest involved the design and evaluation of a congestion-control protocol for paths traversing cellular wireless networks. One key to the success of a design contest is an unambiguous, measurable objective to compare protocols. In practice, protocol design is the art of trading off conflicting goals with each other, but in this contest, we specified that the goal was to maximize log ( throughput / delay ) . This goal is a good match for applications such as video streaming or videoconferencing that care about high throughput and low interactive delays. Some students produced protocols whose performance was better than published protocols tackling similar goals. Furthermore, the convex hull of the set of all student protocols traced out a trade-off curve in the throughput-delay space, providing useful insights into the entire space of possible protocols. We found that student protocols diverged in performance between the training and testing traces, indicating that some students had overtrained (“overfitted”) their protocols to the training trace. Our conclusion is that, if designed properly, such contests could benefit networking research by making new proposals more easily reproducible and amenable to such “gamification,”

In response to ossification and privacy concerns, post-TCP transport protocols such as QUIC are designed to be "paranoid"---opaque to meddling middleboxes by encrypting and authenticating the header and payload---making it impossible for Performance-Enhancing Proxies (PEPs) to provide the same assistance as before. We propose a research agenda towards an alternate approach to PEPs, creating a sidecar protocol that is loosely-coupled to the unchanged and opaque, underlying transport protocol. The key technical challenge to sidecar protocols is how to usefully refer to the packets of the underlying connection without ossification. We have made progress on this problem by creating a tool we call a quACK (quick ACK), a concise representation of a multiset of numbers that can be used to efficiently decode the randomly-encrypted packet contents a sidecar has received. We implement the quACK and discuss how to achieve several applications with this approach: alternate congestion control, ACK reduction, and PEP-to-PEP retransmission across a lossy subpath.

Virtual reality systems today cannot yet stream immersive, retina-quality virtual reality video over a network. One of the greatest challenges to this goal is the sheer data rates required to transmit retina-quality video frames at high resolutions and frame rates. Recent work has leveraged the decay of visual acuity in human perception in novel gaze-contingent video compression techniques. In this paper, we show that reducing the motion-to-photon latency of a system itself is a key method for improving the compression ratio of gaze-contingent compression. Our key finding is that a client and streaming server system with sub-15ms latency can achieve 5x better compression than traditional techniques while also using simpler software algorithms than previous work.

In this paper we explore the viability of path tracing massive scenes using a "supercomputer" constructed on-the-fly from thousands of small, serverless cloud computing nodes. We present R2E2 (Really Elastic Ray Engine) a scene decomposition-based parallel renderer that rapidly acquires thousands of cloud CPU cores, loads scene geometry from a pre-built scene BVH into the aggregate memory of these nodes in parallel, and performs full path traced global illumination using an inter-node messaging service designed for communicating ray data. To balance ray tracing work across many nodes, R2E2 adopts a service-oriented design that statically replicates geometry and texture data from frequently traversed scene regions onto multiple nodes based on estimates of load, and dynamically assigns ray tracing work to lightly loaded nodes holding the required data. We port pbrt's ray-scene intersection components to the R2E2 architecture, and demonstrate that scenes with up to a terabyte of geometry and texture data (where as little as 1/250th of the scene can fit on any one node) can be path traced at 4K resolution, in tens of seconds using thousands of tiny serverless nodes on the AWS Lambda platform.

Vegetation water stress is a key control on wildfire risk, tree mortality, and ecosystem water and carbon fluxes. Although active microwave remote sensing methods have been used to estimate vegetation water, they remain poorly validated because of the immense mismatch between the scale of radar pixel resolutions (100 m to 25 km) and field measurements (individual trees). In this study, we present a new plot-scale vegetation water measurement technique using a side-facing bistatic radar. Using field experiments and a matched filtering technique to isolate the radar signal from noise, we show that radar amplitude is sensitive to xylem water potential (a measure of tree water status). However, our results are affected by periodic noise (period of~12 hours), which may be due to radio frequency interference. We discuss potential pathways to isolate the signal and the implications of the new tree water status measurement system for global validation of microwave remote sensing.

In response to ossification and privacy concerns, post-TCP transport protocols such as QUIC are designed to be "paranoid"---opaque to meddling middleboxes by encrypting and authenticating the header and payload---making it impossible for Performance-Enhancing Proxies (PEPs) to provide the same assistance as before. We propose a research agenda towards an alternate approach to PEPs, creating a sidecar protocol that is loosely-coupled to the unchanged and opaque, underlying transport protocol. The key technical challenge to sidecar protocols is how to usefully refer to the packets of the underlying connection without ossification. We have made progress on this problem by creating a tool we call a quACK (quick ACK) , a concise representation of a multiset of numbers that can be used to efficiently decode the randomly-encrypted packet contents a sidecar has received. We implement the quACK and discuss how to achieve several applications with this approach: alternate congestion control, ACK reduction, and PEP-to-PEP retransmission across a lossy subpath.

Virtual reality systems today cannot yet stream immersive, retina-quality virtual reality video over a network. One of the greatest challenges to this goal is the sheer data rates required to transmit retina-quality video frames at high resolutions and frame rates. Recent work has leveraged the decay of visual acuity in human perception in novel gaze-contingent video compression techniques. In this paper, we show that reducing the motion-to-photon latency of a system itself is a key method for improving the compression ratio of gaze-contingent compression. Our key finding is that a client and streaming server system with sub-15ms latency can achieve 5x better compression than traditional techniques while also using simpler software algorithms than previous work.

In this paper we explore the viability of path tracing massive scenes using a "supercomputer" constructed on-the-fly from thousands of small, serverless cloud computing nodes. We present R2E2 (Really Elastic Ray Engine) a scene decomposition-based parallel renderer that rapidly acquires thousands of cloud CPU cores, loads scene geometry from a pre-built scene BVH into the aggregate memory of these nodes in parallel, and performs full path traced global illumination using an inter-node messaging service designed for communicating ray data. To balance ray tracing work across many nodes, R2E2 adopts a service-oriented design that statically replicates geometry and texture data from frequently traversed scene regions onto multiple nodes based on estimates of load, and dynamically assigns ray tracing work to lightly loaded nodes holding the required data. We port pbrt's ray-scene intersection components to the R2E2 architecture, and demonstrate that scenes with up to a terabyte of geometry and texture data (where as little as 1/250th of the scene can fit on any one node) can be path traced at 4K resolution, in tens of seconds using thousands of tiny serverless nodes on the AWS Lambda platform.

We propose putting computation at the center of what networked computers and cloud services do for their users. We envision a shared representation of a computation: a deterministic procedure, run in an environment of well-specified dependencies. This suggests an end-to-end argument for serverless computing, shifting the service model from "renting CPUs by the second" to "providing the unambiguously correct result of a computation." Accountability to these higher-level abstractions could permit agility and innovation on other axes.

The shared nature of the wireless medium induces contention between data transport and backward signaling, such as acknowledgment. The current way of TCP acknowledgment induces control overhead which is counter-productive for TCP performance especially in wireless local area network (WLAN) scenarios. In this paper, we present a new acknowledgment called TACK (“Tame ACK”), as well as its TCP implementation TCP-TACK. TACK seeks to minimize ACK frequency, which is exactly what is required by transport. TCP-TACK works on top of commodity WLAN, delivering high wireless transport goodput with minimal control overhead in the form of ACKs, without any hardware modification. Evaluation results show that TCP-TACK achieves significant advantages over legacy TCP in WLAN scenarios due to less contention between data packets and ACKs. Specifically, TCP-TACK reduces over 90% of ACKs and also obtains an improvement of up to 28% on goodput. A TACK-based protocol is a good replacement of the legacy TCP to compensate for scenarios where the acknowledgment overhead is non-negligible.

We describe the results of a randomized controlled trial of video-streaming algorithms for bitrate selection and network prediction. Over the last eight months, we have streamed 14.2 years of video to 56,000 users across the Internet. Sessions are randomized in blinded fashion among algorithms, and client telemetry is recorded for analysis. We found that in this real-world setting, it is difficult for sophisticated or machine-learned control schemes to outperform a simple scheme (buffer-based control), notwithstanding good performance in network emulators or simulators. We performed a statistical analysis and found that the variability and heavy-tailed nature of network and algorithm behavior create hurdles for robust learned algorithms in this area. We developed an ABR algorithm that robustly outperforms other schemes in practice, by combining classical control with a learned network predictor, trained with supervised learning in situ on data from the real deployment environment. To support further investigation, we are publishing an archive of traces and results each day, and will open our ongoing study to the community. We welcome other researchers to use this platform to develop and validate new algorithms for bitrate selection, network prediction, and congestion control.

This paper presents a system called NetKernel that decouples the network stack from the guest virtual machine and offers it as an independent module. NetKernel represents a new paradigm where network stack can be managed as part of the virtualized infrastructure. It provides important efficiency benefits: By gaining control and visibility of the network stack, operators can perform network management more directly and flexibly, such as multiplexing VMs running different applications to the same network stack module to save CPU cores, and enforcing fair bandwidth sharing. Users also benefit from the simplified stack deployment and better performance: For example mTCP can be deployed without API change to support nginx natively, and shared memory networking can be readily enabled to improve performance of colocated VMs. Testbed evaluation using 100G NICs shows that NetKernel preserves the performance and scalability of both kernel and userspace network stacks, and provides the same isolation as the current architecture.

We present a sensing system that determines soil moisture via RF using backscatter tags paired with a commodity ultra-wideband RF transceiver. Despite decades of research confirming the benefits, soil moisture sensors are still not widely adopted on working farms for three key reasons: the high cost of sensors, the difficulty of deploying and maintaining these sensors, and the lack of reliable internet access in rural areas. We seek to address these obstacles by designing a low-cost soil moisture sensing system that uses a hybrid approach of pairing completely wireless backscatter tags with a mobile reader. We designed and built two backscatter tag prototypes and tested our system both in laboratory and \emph{in situ} at an organic farm field. Our backscatter tags have a projected battery lifetime of up to 15 years on $4\times$AA batteries, and can operate at a depth of at least 30cm and up to 75cm. We achieve an average accuracy within 0.01-0.03$cm^3/cm^3$ of the ground truth with a 90th percentile of $0.034cm^3/cm^3$, which is comparable to state-of-the-art commercial soil sensors, at an order of magnitude lower cost.

The shared nature of the wireless medium induces contention between data transport and backward signaling, such as acknowledgement. The current way of TCP acknowledgment induces control overhead which is counter-productive for TCP performance especially in wireless local area network (WLAN) scenarios. In this paper, we present a new acknowledgement called TACK ("Tame ACK"), as well as its TCP implementation TCP-TACK. TCP-TACK works on top of commodity WLAN, delivering high wireless transport goodput with minimal control overhead in the form of ACKs, without any hardware modification. To minimize ACK frequency, TACK abandons the legacy received-packet-driven ACK. Instead, it balances byte-counting ACK and periodic ACK so as to achieve a controlled ACK frequency. Evaluation results show that TCP-TACK achieves significant advantages over legacy TCP in WLAN scenarios due to less contention between data packets and ACKs. Specifically, TCP-TACK reduces over 90% of ACKs and also obtains an improvement of similar to 28% on goodput. We further find it performs equally well as high-speed TCP variants in wide area network (WAN) scenarios, this is attributed to the advancements of the TACK-based protocol design in loss recovery, round-trip timing, and send rate control.

One ABR algorithm implemented on Puffer is BOLA-BASIC, the simplest variant of BOLA. BOLA finds wide use in industry, notably in the MPEG-DASH reference player used as the basis for video players at Akamai, BBC, Orange, and CBS. The overall goal of BOLA is to maximize each encoded chunk's video quality while minimizing rebuffering. To measure video quality, Puffer uses the structural similarity metric SSIM, whereas BOLA and other ABR algorithms like BBA, MPC, and Pensieve are more commonly implemented using bitrate (or a variant of bitrate). While bitrate is frequently used, BOLA allows the video provider to define its own proxy of video quality as the algorithm's "utility" function. However, using SSIM as utility proved surprisingly complex for BOLA-BASIC, despite the algorithm's simplicity. Given the rising popularity of SSIM and related quality metrics, we anticipate that a growing number of Puffer-like systems will face similar challenges. We hope developers of such systems find our experiences informative as they implement algorithms designed with bitrate-based utility in mind.