Search

With the proliferation of sensor and personal devices, our physical spaces are now awash in potential data sources. In principle this data could serve a wide range of applications and services. However, leveraging these data sources is challenging with today's systems because they are not typically designed to consume data opportunistically, from a new device that happens to arrive in the vicinity. In this paper, we present the design and implementation of Jut, a system designed for "Just-in-Time" data access - in which an application is able to discover and consume data from any available source, even ones not known at development or installation time. Jut combines two novel design choices: modularizing data processing systems to better reflect the physical world, and a new form of application-data integration that equips data processing pipelines with the information they need to process new and evolving data formats and schemas. We show that these choices greatly simplify the development and use of smart-space and IoT applications. For a representative set of devices and application scenarios, we show that Jut can implement use-cases not easily supported today, or can do so with 3.2-14.8x less development effort and 3-12x lower query complexity than current systems.

We introduce the Internet of Data Apps (IoDA), representing the next natural progression of the Internet, Big Data, AI, and the Internet of Things. Despite advancements in these fields, the full potential of universal data access - the capability to seamlessly consume and contribute data via data applications - remains stifled by organizational and technological silos. To address these constraints, we propose the designs of an IoDA layer borrowing inspirations from the standard Internet protocols. This layer facilitates the interconnection of data applications across different devices and domains. This short paper serves as an invitation to dialogue over this proposal., Comment: 5 pages, 2 figures

Microservices are increasingly used in modern applications, leading to a growing need for effective service composition solutions. However, we argue that traditional API-centric composition mechanisms (e.g., RPC, REST, and Pub/Sub) hamper the modularity of microservices. These mechanisms introduce rigid code-level coupling, scatter composition logic, and hinder visibility into cross-service data exchanges. Ultimately, these limitations complicate the maintenance and evolution of microservice-based applications. In response, we propose a rethinking of service composition and present Knactor, a new data-centric composition framework to restore the modularity that microservices were intended to offer. Knactor decouples service composition from service development, allowing composition to be implemented as explicit data exchanges among multiple services. Our initial case study suggests that Knactor simplifies service composition and creates new opportunities for optimizations., Comment: Corrected terms

We present DBNet, a data-driven network automation framework built on top of a DBMS. DBNet utilizes key primitives of a DBMS including tables, procedures, transactions, logging, and access control to serve the functions of a data-centric network control plane. DBNet accomplishes this functionality by storing mirrored network device states, executing automation programs on these mirror states within the DBMS, and proxying state updates out to the physical devices upon changes to mirror/local state. The framework also stores network telemetry data, performs analytics on the data, uses the analytics to motivate control plane actions, and provides provenance logging features on the actions taken. We apply DBNet to motivating cloud network infrastructure examples and show how developers can use DBNet's interface to express rich user-defined policies. Our preliminary case studies show that the overhead to run DBNet is trivial in the timescales generally relevant for network automation., Comment: 6 pages

Communities, ranging from homes to cities, are a ubiquitous part of our lives. However, there is a lack of adequate support for applications built around these communities. As a result, current applications each need to implement their own notion of communities, making it difficult for both the app developers and the app users (\ie the community admins and members) to create and use these community apps. In this paper, we argue that communities should be supported at the infrastructure-level rather than at the app-level. We refer to this approach as the Platform-Managed Community (PMC). We propose Comverse, a platform designed to this end. Comverse is predicated on the principle of federation, allowing autonomous nodes representing community members to voluntarily associate and share data while maintaining control over their data and participation. Through Comverse, we explore the vision of community computing by showcasing its applicability with real-world community apps., Comment: 6 pages, 3 figures

In the era where personal devices and applications are pervasive, individuals are continuously generating and interacting with a vast amount of data. Despite this, access to and control over such data remains challenging due to its scattering across various app providers and formats. This paper presents Human-Scale Computing, a vision and an approach where every individual has straightforward, unified access to their data across all devices, apps, and services. Key to this solution is the Human Scale Portal, a progressively designed intermediary that integrates different applications and service providers. This design adopts a transitional development and deployment strategy, involving an initial bootstrapping phase to engage application providers, an acceleration phase to enhance the convenience of access, and an eventual solution. We believe that this progressive "narrow waist" design can bridge the gap between the current state of data access and our envisioned future of human-scale access., Comment: 6 pages, 1 figure

Using memory located on remote machines, or far memory, as a swap space is a promising approach to meet the increasing memory demands of modern datacenter applications. Operating systems have long relied on prefetchers to mask the increased latency of fetching pages from swap space to main memory. Unfortunately, with traditional prefetching heuristics, performance still degrades when applications use far memory. In this paper we propose a new prefetching technique for far-memory applications. We focus our efforts on memory-intensive, oblivious applications whose memory access patterns are independent of their inputs, such as matrix multiplication. For this class of applications we observe that we can perfectly prefetch pages without relying on heuristics. However, prefetching perfectly without requiring significant application modifications is challenging. In this paper we describe the design and implementation of 3PO, a system that provides pre-planned prefetching for general oblivious applications. We demonstrate that 3PO can accelerate applications, e.g., running them 30-150% faster than with Linux's prefetcher with 20% local memory. We also use 3PO to understand the fundamental software overheads of prefetching in a paging-based system, and the minimum performance penalty that they impose when we run applications under constrained local memory., Comment: 14 pages

A growing number of devices and services collect detailed time series data that is stored in the cloud. Protecting the confidentiality of this vast and continuously generated data is an acute need for many applications in this space. At the same time, we must preserve the utility of this data by enabling authorized services to securely and selectively access and run analytics. This paper presents TimeCrypt, a system that provides scalable and real-time analytics over large volumes of encrypted time series data. TimeCrypt allows users to define expressive data access and privacy policies and enforces it cryptographically via encryption. In TimeCrypt, data is encrypted end-to-end, and authorized parties can only decrypt and verify queries within their authorized access scope. Our evaluation of TimeCrypt shows that its memory overhead and performance are competitive and close to operating on data in the clear.

The advent of RoCE (RDMA over Converged Ethernet) has led to a significant increase in the use of RDMA in datacenter networks. To achieve good performance, RoCE requires a lossless network which is in turn achieved by enabling Priority Flow Control (PFC) within the network. However, PFC brings with it a host of problems such as head-of-the-line blocking, congestion spreading, and occasional deadlocks. Rather than seek to fix these issues, we instead ask: is PFC fundamentally required to support RDMA over Ethernet? We show that the need for PFC is an artifact of current RoCE NIC designs rather than a fundamental requirement. We propose an improved RoCE NIC (IRN) design that makes a few simple changes to the RoCE NIC for better handling of packet losses. We show that IRN (without PFC) outperforms RoCE (with PFC) by 6-83% for typical network scenarios. Thus not only does IRN eliminate the need for PFC, it improves performance in the process! We further show that the changes that IRN introduces can be implemented with modest overheads of about 3-10% to NIC resources. Based on our results, we argue that research and industry should rethink the current trajectory of network support for RDMA., Comment: Extended version of the paper appearing in ACM SIGCOMM 2018

This paper presents Droplet, a decentralized data access control service. Droplet enables data owners to securely and selectively share their encrypted data while guaranteeing data confidentiality in the presence of unauthorized parties and compromised data servers. Droplet's contribution lies in coupling two key ideas: (i) a cryptographically-enforced access control construction for encrypted data streams which enables users to define fine-grained stream-specific access policies, and (ii) a decentralized authorization service that serves user-defined access policies. In this paper, we present Droplet's design, the reference implementation of Droplet, and the experimental results of three case-study applications deployed with Droplet: Fitbit activity tracker, Ava health tracker, and ECOviz smart meter dashboard, demonstrating Droplet's applicability for secure sharing of IoT streams.

In this paper we address a seemingly simple question: Is there a universal packet scheduling algorithm? More precisely, we analyze (both theoretically and empirically) whether there is a single packet scheduling algorithm that, at a network-wide level, can match the results of any given scheduling algorithm. We find that in general the answer is "no". However, we show theoretically that the classical Least Slack Time First (LSTF) scheduling algorithm comes closest to being universal and demonstrate empirically that LSTF can closely, though not perfectly, replay a wide range of scheduling algorithms in realistic network settings. We then evaluate whether LSTF can be used {\em in practice} to meet various network-wide objectives by looking at three popular performance metrics (mean FCT, tail packet delays, and fairness); we find that LSTF performs comparable to the state-of-the-art for each of them., Comment: This is the same as our ACM HotNets 2015 paper, extended to include proofs for our theoretical results

Low latency is critical for interactive networked applications. But while we know how to scale systems to increase capacity, reducing latency --- especially the tail of the latency distribution --- can be much more difficult. In this paper, we argue that the use of redundancy is an effective way to convert extra capacity into reduced latency. By initiating redundant operations across diverse resources and using the first result which completes, redundancy improves a system's latency even under exceptional conditions. We study the tradeoff with added system utilization, characterizing the situations in which replicating all tasks reduces mean latency. We then demonstrate empirically that replicating all operations can result in significant mean and tail latency reduction in real-world systems including DNS queries, database servers, and packet forwarding within networks.

We introduce a protocol which routes on flat, location-independent identifiers with guaranteed scalability and low stretch. Our design builds on theoretical advances in the area of compact routing, and is the first to realize these guarantees in a dynamic distributed setting., Comment: 13 pages