To facilitate various Machine Learning (ML) training and inference tasks, enterprises tend to build large and expensive clusters and share them among different teams for diverse ML workloads. Virtualized platforms (containers/VMs) and schedulers are typically deployed to allow such access, manage heterogeneous resources and schedule ML jobs in these clusters. However, allocating resource budgets for different ML jobs to achieve best performance and cluster resource efficiency remains a significant challenge. This work proposes Nearchus to accelerate distributed ML training while ensuring high resource efficiency by using adaptive resource allocation. Nearchus automatically identifies potential performance bottlenecks for running jobs and re-allocates resources to provide optimized run-time performance with high resource efficiency. Nearchus’s resource configuration significantly improves the training speed of individual jobs up to 71.4%–129.1% against state-of-the-art resource schedulers, and reduces job completion and queuing time by 35.6% and 67.8%, respectively.

Today, video cameras are ubiquitously deployed. These cameras collect, stream, store, and analyze video footage for a variety of use cases, ranging from surveillance, retail analytics, architectural engineering, and more. At the same time, many citizens are becoming weary of the amount of personal data captured, along with the algorithms and datasets used to process video pipelines. This work investigates how users can opt-out of such pipelines by explicitly providing consent to be recorded. An ideal system should obfuscate or otherwise cleanse non-consenting user data, ideally before a user even enters the video processing pipeline itself. We present a system, called Consent-Box, that enables obfuscation of users without using complex or personally-identifying vision techniques. Instead, a user's location on a video frame is estimated via Wi-Fi localization of a user's mobile device. This estimation allows us to remove individuals from frames before those frames enter complex vision pipelines.

In the past, researchers designed, deployed, and evaluated Wi-Fi based localization techniques in order to locate users and devices without adding extra or costly infrastructure. However, as infrastructure deployments change, one must reexamine the role of Wi-Fi localization. Today, cameras are becoming increasingly deployed, and therefore this work examines how contextual and vision data obtained from cameras can be integrated with Wi-Fi localization techniques. We present an approach called CALM that works on commodity APs and cameras. Our approach contains several contributions: a camera line fitting technique to restrict the search space of candidate locations, single AP and camera localization via a deprojection scheme inspired from 3D cameras, simple and robust AP weighting that analyzes the context of users via the camera, and a new virtual camera methodology to scale analysis. We motivate our scheme by analyzing real camera and AP topologies from a major vendor. Our evaluation over 9 rooms and 102,300 wireless readings shows CALM can obtain decimeter-level accuracy, improving performance over previous Wi-Fi techniques like FTM by $2.7\times$ and SpotFi by $2.3\times$.

This paper pushes the limits of automated resource allocation in container environments. Recent works set container CPU and memory limits by automatically scaling containers based on past resource usage. However, these systems are heavy- weight and run on coarse-grained time scales, resulting in poor performance when predictions are incorrect. We propose Escra, a container orchestrator that enables fine-grained, event- based resource allocation for a single container and distributed resource allocation to manage a collection of containers. Escra performs resource allocation on sub-second intervals within and across hosts, allowing operators to cost-effectively scale resources without performance penalty. We evaluate Escra on two types of containerized applications: microservices and serverless functions. In microservice environments, fine-grained and event- based resource allocation can reduce application latency by up to 96.9% and increase throughput by up to 3.2x when compared against the current state-of-the-art. Escra can increase performance while simultaneously reducing 50th and 99th%ile CPU waste by over 10x and 3.2x, respectively. In serverless environments, Escra can reduce CPU reservations by over 2.1x and memory reservations by more than 2x while maintaining similar end-to-end performance.

Serverless computing is a rapidly growing paradigm that easily harnesses the power of the cloud. With serverless computing, developers simply provide an event-driven function to cloud providers, and the provider seamlessly scales function invocations to meet demands as event-triggers occur. As current and future serverless offerings support a wide variety of serverless applications, effective techniques to manage serverless workloads becomes an important issue. This work examines current management and scheduling practices in cloud providers, uncovering many issues including inflated application run times, function drops, inefficient allocations, and other undocumented and unexpected behavior. To fix these issues, a new quality-of-service function scheduling and allocation framework, called Sequoia, is designed. Sequoia allows developers or administrators to easily def ne how serverless functions and applications should be deployed, capped, prioritized, or altered based on easily configured, flexible policies. Results with controlled and realistic workloads show Sequoia seamlessly adapts to policies, eliminates mid-chain drops, reduces queuing times by up to 6.4X, enforces tight chain-level fairness, and improves run-time performance up to 25X.

This paper presents a new approach to memory disaggregation called FluidMem that leverages the userfault mechanism in Linux to achieve full memory disaggregation in software. FluidMem enables dynamic and transparent resizing of an unmodified Virtual Machine’s (VM’s) memory footprint in the cloud. As a result, a VM’s memory footprint can seamlessly scale over multiple machines or even be downsized to a near-zero footprint on a given server. FluidMem’s architecture provides flexibility to cloud operators to manage remote memory without requiring guest intervention, while also supporting paging out the entirety of a VM’s pages within its address space. FluidMem integrates with a remote memory backend in a modular way, easily supporting systems such as RAMCloud to harness remote memory. We demonstrate FluidMem outperforms an existing memory disaggregation approach based on network swap. Microbenchmarks are evaluated to characterize the latency of different components of the FluidMem architecture, and two memory-intensive applications are demonstrated using FluidMem, the Graph500 benchmark, and MongoDB. Additionally, we show FluidMem can flexibly and efficiently grow and shrink the memory footprint of a VM as defined by a cloud provider.

Efficient resource management in cloud computing research is a crucial problem because resource over-provisioning increases costs for cloud providers and cloud customers; resource under-provisioning increases the application latency, and it may violate service level agreements, which eventually makes cloud providers lose their customers and income. As a result, researchers have been striving to develop optimal resource management in cloud computing environments in different ways, such as container placement, job scheduling and multi-resource scheduling. Machine learning techniques are extensively used in this area. In this paper, we present a comprehensive survey on the projects that leveraged machine learning techniques for resource management solutions in the cloud computing environment. At the end, we provide a comparison between these projects. Furthermore, we propose some future directions that will guide researchers to advance this field.

As personal interactive devices become more ingrained into our daily lives, it becomes more important to understand how seamless interaction with those devices can be fostered. A typical mechanism to interface with a personal device is via a touch screen, in which users use their fingertip or stylus to scroll, type, select, or otherwise control device usage. Touch-based techniques, however, can become restrictive or inconvenient under a variety of scenarios. For example, personal devices such as phones or tablets are continuously increasing in size, making one-handed interaction difficult because one cannot easily hold the phone and touch the screen (with the thumb) at the same time with one hand. Therefore, in this demo, we present a new technique to interact with personal devices in which the screen and touch screen interactions can adapt to a user's grip or current touch constraints.

In serverless computing, developers define a function to handle an event, and the serverless framework horizontally scales the application as needed. The downside of this function-based abstraction is it limits the type of application supported and places a bound on the function to be within the physical resource limitations of the server the function executes on. In this paper we propose a new abstraction for serverless computing: a developer supplies a process and the serverless framework seamlessly scales out the process's resource usage across the datacenter. This abstraction enables processing to not only be more general purpose, but also allows a process to break out of the limitations of a single server – making serverless computing more serverless. To realize this abstraction, we propose ServerlessOS, comprised of three key components: (i) a new disaggregation model, which leverages disaggregation for abstraction, but enables resources to move fluidly between servers for performance; (ii) a cloud orchestration layer which manages fine-grained resource allocation and placement throughout the application's lifetime via local and global decision making; and (iii) an isolation capability that enforces data and resource isolation across disaggregation, effectively extending Linux cgroup functionality to span servers.

Driven to create intuitive computing interfaces throughout our everyday space, various state-of-the-art technologies have been proposed for near-surface localization of a user's finger input such as hover or touch. However, these works require specialized hardware not commonly available, limiting the adoption of such technologies. We present SymmetriSense, a technology enabling near-surface 3-dimensional fingertip localization above arbitrary glossy surfaces using a single commodity camera device such as a smartphone. SymmetriSense addresses the localization challenges in using a single regular camera by a novel technique utilizing the principle of reflection symmetry and the fingertip's natural reflection casted upon surfaces like mirrors, granite countertops, or televisions. SymmetriSense achieves typical accuracies at sub-centimeter levels in our localization tests with dozens of volunteers and remains accurate under various environmental conditions. We hope SymmetriSense provides a technical foundation on which various everyday near-surface interactivity can be designed.

Multi-tenant datacenters are successful because tenants can seamlessly port their applications and services to the cloud. Virtual Machine (VM) technology plays an integral role in this success by enabling a diverse set of software to be run on a unified underlying framework. This flexibility, however, comes at the cost of dealing with out-dated, inefficient, or misconfigured TCP stacks implemented in the VMs. This paper investigates if administrators can take control of a VM's TCP congestion control algorithm without making changes to the VM or network hardware. We propose AC/DC TCP, a scheme that exerts fine-grained control over arbitrary tenant TCP stacks by enforcing per-flow congestion control in the virtual switch (vSwitch). Our scheme is light-weight, flexible, scalable and can police non-conforming flows. In our evaluation the computational overhead of AC/DC TCP is less than one percentage point and we show implementing an administrator-defined congestion control algorithm in the vSwitch (i.e., DCTCP) closely tracks its native performance, regardless of the VM's TCP stack.

Datacenter networks deal with a variety of workloads, ranging from latency-sensitive small flows to bandwidth-hungry large flows. Load balancing schemes based on flow hashing, e.g., ECMP, cause congestion when hash collisions occur and can perform poorly in asymmetric topologies. Recent proposals to load balance the network require centralized traffic engineering, multipath-aware transport, or expensive specialized hardware. We propose a mechanism that avoids these limitations by (i) pushing load-balancing functionality into the soft network edge (e.g., virtual switches) such that no changes are required in the transport layer, customer VMs, or networking hardware, and (ii) load balancing on fine-grained, near-uniform units of data (flowcells) that fit within end-host segment offload optimizations used to support fast networking speeds. We design and implement such a soft-edge load balancing scheme, called Presto, and evaluate it on a 10 Gbps physical testbed. We demonstrate the computational impact of packet reordering on receivers and propose a mechanism to handle reordering in the TCP receive offload functionality. Presto's performance closely tracks that of a single, non-blocking switch over many workloads and is adaptive to failures and topology asymmetry.

Software-defined networking introduces the possibility of building self-tuning networks that constantly monitor network conditions and react rapidly to important events such as congestion. Unfortunately, state-of-the-art monitoring mechanisms for conventional networks require hundreds of milliseconds to seconds to extract global network state, like link utilization or the identity of "elephant" flows. Such latencies are adequate for responding to persistent issues, e.g., link failures or long-lasting congestion, but are inadequate for responding to transient problems, e.g., congestion induced by bursty workloads sharing a link. In this paper, we present Planck, a novel network measurement architecture that employs oversubscribed port mirroring to extract network information at 280 µs--7 ms timescales on a 1 Gbps commodity switch and 275 µs--4 ms timescales on a 10 Gbps commodity switch,over 11x and 18x faster than recent approaches, respectively (and up to 291x if switch firmware allowed buffering to be disabled on some ports). To demonstrate the value of Planck's speed and accuracy, we use it to drive a traffic engineering application that can reroute congested flows in milliseconds. On a 10 Gbps commodity switch, Planck-driven traffic engineering achieves aggregate throughput within 1--4% of optimal for most workloads we evaluated, even with flows as small as 50 MiB, an improvement of up to 53% over previous schemes.

Wireless systems are getting deployed in many new environments with different antenna heights, frequency bands and multipath conditions. This has led to an increasing demand for more channel measurements to understand wireless propagation in specific environments and assist deployment engineering. We design and implement a rapid wireless channel sounding system, using the Universal Software Radio Peripheral (USRP) and GNU Radio software, to address these demands. Our design measures channel propagation characteristics simultaneously from multiple transmitter locations. The system consists of multiple battery-powered transmitters and receivers. Therefore, we can set-up the channel sounder rapidly at a field location and measure expeditiously by analyzing different transmitters' signals during a single walk or drive through the environment. Our design can be used for both indoor and outdoor channel measurements in the frequency range of 1 MHz to 6 GHz. We expect that the proposed approach, with a few further refinements, can transform the task of propagation measurement as a routine part of day-to-day wireless network engineering.

Opportunistic routing aims to improve wireless performance by exploiting communication opportunities arising by chance. A key challenge in opportunistic routing is how to achieve good, predictable performance despite the incidental nature of such communication opportunities and the complicated effects of wireless interference in IEEE 802.11 networks. To address the challenge, we develop a model-driven optimization framework to jointly optimize opportunistic routes and rate limits for both unicast and multicast traffic. A distinctive feature of our framework is that the performance derived from optimization can be achieved in a real IEEE 802.11 network. Our framework consists of three key components: 1) a model for capturing the interference among IEEE 802.11 broadcast transmissions; 2) a novel algorithm for accurately optimizing different performance objectives; and 3) effective techniques for mapping the resulting solutions to practical routing configurations. Extensive simulations and testbed experiments show that our approach significantly outperforms state-of-the-art shortest-path routing and opportunistic routing protocols. Moreover, the difference between the achieved performance and our model estimation is typically within 20%. Evaluation in dynamic and uncontrolled environments further shows that our approach is robust against inaccuracy introduced by a dynamic network and it also consistently outperforms the existing schemes. These results clearly demonstrate the effectiveness and accuracy of our approach.

Efficiently sharing spectrum among multiple users is critical to wireless network performance. In this paper, we propose a novel spectrum sharing protocol called Collision-Resistant Multiple Access (CRMA) to achieve high efficiency. In CRMA, each transmitter views the OFDM physical layer as multiple orthogonal but sharable channels, and independently selects a few channels for transmission. The transmissions that share the same channel naturally add up in the air. The receiver extracts the received signals from all the channels and efficiently decodes the transmissions by solving a simple linear system. We implement our approach in the Qualnet simulator and show that it yields significant improvement over existing spectrum sharing schemes. We also demonstrate the feasibility of our approach using implementation and experiments on GNU Radios.

Opportunistic routing achieves significant performance gain under lossy wireless links. In this paper, we develop a novel approach that exploits inter-flow network coding in opportunistic routing. A unique feature of our design is that it systematically optimizes end-to-end performance (e.g., total throughput). A key challenge to achieve this goal is a strong tension between opportunistic routing and inter-flow network coding: to achieve high reliability, opportunistic routing uses intra-flow coding to spread information across multiple nodes; this reduces the information reaching an individual node, which in turn reduces inter-flow coding opportunity. To address this challenge, we decouple opportunistic routing and inter-flow network coding by proposing a novel framework where an overlay network performs overlay routing and inter-flow coding without worrying about packet losses, while an underlay network uses optimized opportunistic routing and rate limiting to provide efficient and reliable overlay links for the overlay network to take advantage of. Based on this framework, we develop the first optimization algorithm to jointly optimize opportunistic routes, rate limits, inter-flow and intra-flow coding. We then develop a practical opportunistic routing protocol (O3) based on the optimization results. Using Qualnet simulation, we study the individual and aggregate benefits of opportunistic routing, inter-flow coding, and rate limits. Our results show that (i) rate limiting significantly improves the performance of all routing protocols, (ii) opportunistic routing is beneficial under high loss rates, whereas inter-flow coding is more effective under low loss rates, and (iii) O3 significantly out-performs state-of-the-art routing protocols by simultaneously leveraging optimized opportunistic routing, inter-flow coding, and rate limits.

Opportunistic routing aims to improve wireless performance by exploiting communication opportunities arising by chance. A key challenge in opportunistic routing is how to achieve good, predictable performance despite the incidental nature of such communication opportunities and the complicated effects of wireless interference in IEEE 802.11 networks. To address the challenge, we develop a model-driven optimization framework to jointly optimize opportunistic routes and rate limits for both unicast and multicast traffic. A distinctive feature of our framework is that the performance derived from optimization can be achieved in a real IEEE 802.11 network. Our framework consists of three key components: (i) a model for capturing the interference among IEEE 802.11 broadcast transmissions, (ii) a novel algorithm for accurately optimizing different performance objectives, and (iii) effective techniques for mapping the resulting solutions to practical routing configurations. Extensive simulations and testbed experiments show that our approach significantly outperforms state-of-the-art shortest path routing and opportunistic routing protocols. Moreover, the difference between the achieved performance and our model estimation is typically within 20%. Evaluation in dynamic and uncontrolled environments further shows that our approach is robust against inaccuracy introduced by a dynamic network and it also consistently out-performs the existing schemes. These results clearly demonstrate the effectiveness and accuracy of our approach.

WiFi radios in smart-phones consume a significant amount of power when active. The 802.11 standard allows these devices to save power through an energy-conserving Power Save Mode (PSM). However, depending on the PSM implementation strategies used by the clients/Access Points (APs), we find competing background traffic results in one or more of the following negative consequences: a significant increase, up to 300%, in a client's energy consumption, a decrease in wireless network capacity due to unnecessary retransmissions, and unfairness.

With the phenomenal growth of wireless networks and applications, it is increasingly important to deliver content efficiently and reliably over wireless links. However, wireless performance is still far from satisfactory due to limited wireless spectrum, inherent lossy wireless medium, and imperfect packet scheduling. While significant research has been done to improve wireless performance, much of the existing work focuses on individual design space. We take a holistic approach to optimizing wireless performance and resilience. We propose Fast Resilient Jumbo frames (FRJ), which exploit the synergy between three important design spaces: (i) frame size selection, (ii) partial packet recovery, and (iii) rate adaptation. While these design spaces are seemingly unrelated, we show that there are strong interactions between them and effectively leveraging these techniques can provide increased robustness and performance benefits in wireless LANs. FRJ uses jumbo frames to boost network throughput under good channel conditions and uses partial packet recovery to efficiently recover packet losses under bad channel conditions. FRJ also utilizes partial recovery aware rate adaptation to maximize throughput under partial recovery. Using real implementation and testbed experiments, we show that FRJ out-performs existing approaches in a wide range of scenarios.

Multihop wireless mesh networks are becoming a new attractive communication paradigm owing to their low cost and ease of deployment. Routing protocols are critical to the performance and reliability of wireless mesh networks. Traditional routing protocols send traffic along predetermined paths and face difficulties in coping with unreliable and unpredictable wireless medium. In this paper, we propose a simple opportunistic adaptive routing protocol (SOAR) to explicitly support multiple simultaneous flows in wireless mesh networks. SOAR incorporates the following four major components to achieve high throughput and fairness: 1) adaptive forwarding path selection to leverage path diversity while minimizing duplicate transmissions, 2) priority timer-based forwarding to let only the best forwarding node forward the packet, 3) local loss recovery to efficiently detect and retransmit lost packets, and 4) adaptive rate control to determine an appropriate sending rate according to the current network conditions. We implement SOAR in both NS-2 simulation and an 18-node wireless mesh testbed. Our extensive evaluation shows that SOAR significantly outperforms traditional routing and a seminal opportunistic routing protocol, ExOR, under a wide range of scenarios.

Wireless LANs (WLANs) have been deployed at a remarkable rate at university campuses, office buildings, airports, hotels, and malls. Providing efficient and reliable wireless communications is challenging due to inherent lossy wireless medium and imperfect packet scheduling that results in packet collisions. In this paper, we develop an efficient retransmission scheme (ER) for wirless LANs. Instead of retransmitting the lost packets in their original forms, ER codes packets lost at different destinations and uses a single retransmission to potentially recover multiple packet losses. We develop a simple and practical protocol to realize the idea and implement it in both simulation and testbed, and our results demonstrate the effectiveness of this approach.

Campus and enterprise wireless networks are increasingly characterized by ubiquitous coverage and rising traffic demands. Efficiently assigning channels to access points (APs) in these networks can significantly affect the performance and capacity of the WLANs. The state-of-the-art approaches assign channels statically, without considering prevailing traffic demands. In this paper, we show that the quality of a channel assignment can be improved significantly by incorporating observed traffic demands at APs and clients into the assignment process. We refer to this astraffic-aware channel assignment. We conduct extensive trace-driven and synthetic simulations and identify deployment scenarios where traffic-awareness is likely to be of great help, and scenarios where the benefit is minimal. We address key practical issues in using traffic-awareness, including measuring an interference graph, handling non-binary interference, collecting traffic demands, and predicting future demands based on historical information. We present an implementation of our assignment scheme for a 25-node WLAN testbed. Our testbed experiments show that traffic-aware assignment offers superior network performance under a wide range of real network configurations. On the whole, our approach is simple yet effective. It can be incorporated into existing WLANs with little modification to existing wireless nodes and infrastructure.