Dongsu Han

ATLAS: A scalable and high-performance scheduling algorithm for multiple memory controllers

Modern chip multiprocessor (CMP) systems employ multiple memory controllers to control access to main memory. The scheduling algorithm employed by these memory controllers has a significant effect on system throughput, so choosing an efficient scheduling algorithm is important. The scheduling algorithm also needs to be scalable — as the number of cores increases, the number of memory controllers shared by the cores should also increase to provide sufficient bandwidth to feed the cores. Unfortunately, previous memory scheduling algorithms are inefficient with respect to system throughput and/or are designed for a single memory controller and do not scale well to multiple memory controllers, requiring significant finegrained coordination among controllers. This paper proposes ATLAS (Adaptive per-Thread Least-Attained-Service memory scheduling), a fundamentally new memory scheduling technique that improves system throughput without requiring significant coordination among memory controllers. The key idea is to periodically order threads based on the service they have attained from the memory controllers so far, and prioritize those threads that have attained the least service over others in each period. The idea of favoring threads with least-attained-service is borrowed from the queueing theory literature, where, in the context of a single-server queue it is known that least-attained-service optimally schedules jobs, assuming a Pareto (or any decreasing hazard rate) workload distribution. After verifying that our workloads have this characteristic, we show that our implementation of least-attained-service thread prioritization reduces the time the cores spend stalling and significantly improves system throughput. Furthermore, since the periods over which we accumulate the attained service are long, the controllers coordinate very infrequently to form the ordering of threads, thereby making ATLAS scalable to many controllers. We evaluate ATLAS on a wide variety of multiprogrammed SPEC 2006 workloads and systems with 4–32 cores and 1–16 memory controllers, and compare its performance to five previously proposed scheduling algorithms. Averaged over 32 workloads on a 24-core system with 4 controllers, ATLAS improves instruction throughput by 10.8%, and system throughput by 8.4%, compared to PAR-BS, the best previous CMP memory scheduling algorithm. ATLASs performance benefit increases as the number of cores increases.

Access Point Localization Using Local Signal Strength Gradient

Many previous studies have examined the placement of access points (APs) to improve the communitys understanding of the deployment and behavioral characteristics of wireless networks. A key implicit assumption in these studies is that one can estimate the AP location accurately from wardriving-like measurements. However, existing localization algorithms exhibit high error because they over-simplify the complex nature of signal propagation. In this work, we propose a novel approach that localizes APs using directional information derived from local signal strength variations. Our algorithm only uses signal strength information, and improves localization accuracy over existing techniques. Furthermore, the algorithm is robust to the sampling biases and non-uniform shadowing, which are common in wardriving measurements.

Mark-and-sweep: getting the "inside" scoop on neighborhood networks

Residential Internet connectivity is growing at a phenomenal rate. A number of recent studies have attempted to characterize this connectivity - measuring coverage and performance of last-mile broadband links - from a various vantage points on the Internet, via wireless APs, and even with user cooperation. These studies, however, sacrifice accuracy or require substantial human time. In this work, we present a novel two-pass method to characterize neighborhood networks. We demonstrate that the two pass method dramatically reduces the time spent in active measurement while retaining accuracy. A case study on two neighborhoods in Pittsburgh provide new and accurate insights into broadband connectivity, including throughput, broadband coverage (DSL vs. cable vs. fiber), NAT configurations, DHCP, DNS usage. The results further characterize 802.11 connectivity in the neighborhood.

A First Step Towards Leveraging Commodity Trusted Execution Environments for Network Applications

Network applications and protocols are increasingly adopting security and privacy features, as they are becoming one of the primary requirements. The wide-spread use of transport layer security (TLS) and the growing popularity of anonymity networks, such as Tor, exemplify this trend. Motivated by the recent movement towards commoditization of trusted execution environments (TEEs), this paper explores alternative design choices that application and protocol designers should consider. In particular, we explore the possibility of using Intel SGX to provide security and privacy in a wide range of network applications. We show that leveraging hardware protection of TEEs opens up new possibilities, often at the benefit of a much simplified application/protocol design. We demonstrate its practical implications by exploring the design space for SGX-enabled software-defined inter-domain routing, peer-to-peer anonymity networks (Tor), and middleboxes. Finally, we quantify the potential overheads of the SGX-enabled design by implementing it on top of OpenSGX, an open source SGX emulator.

Guaranteeing deadlines for inter-datacenter transfers

Inter-datacenter wide area networks (inter-DC WAN) carry a significant amount of data transfers that require to be completed within certain time periods, or deadlines. However, very little work has been done to guarantee such deadlines. The crux is that the current inter-DC WAN lacks an interface for users to specify their transfer deadlines and a mechanism for provider to ensure the completion while maintaining high WAN utilization. This paper addresses the problem by introducing a Deadline-based Network Abstraction (DNA) for inter-DC WANs. DNA allows users to explicitly specify the amount of data to be delivered and the deadline by which it has to be completed. The malleability of DNA provides flexibility in resource allocation. Based on this, we develop a system called Amoeba that implements DNA. Our simulations and testbed experiments show that Amoeba, by harnessing DNAs malleability, accommodates 15% more user requests with deadlines, while achieving 60% higher WAN utilization than prior solutions.

PIAS: Practical Information-Agnostic Flow Scheduling for Data Center Networks

Many existing data center network (DCN) flow scheduling schemes minimize flow completion times (FCT) based on prior knowledge of flows and custom switch designs, making them hard to use in practice. This paper introduces, Pias, a practical flow scheduling approach that minimizes FCT with no prior knowledge using commodity switches. At its heart, Pias leverages multiple priority queues available in commodity switches to implement a Multiple Level Feedback Queue (MLFQ), in which a PIAS flow gradually demotes from higher-priority queues to lower-priority queues based on the bytes it has sent. In this way, short flows are prioritized over long flows, which enables Pias to emulate Shortest Job First (SJF) scheduling without knowing the flow sizes beforehand. Our preliminary evaluation shows that Pias significantly outperforms all existing information-agnostic solutions. It improves average FCT for short flows by up to 50% and 40% over DCTCP [3] and L2DCT [16]. Compared to an ideal information-aware DCN transport, p-Fabric [5], it only shows 4.9% performance degradation for short flows in a production datacenter workload.

Predicting handoffs in 3G networks

Consumers all over the world are increasingly using their smartphones on the go and expect consistent, high quality connectivity at all times. A key network primitive that enables continuous connectivity in cellular networks is handoff. Although handoffs are necessary for mobile devices to maintain connectivity, they can also cause short-term disruptions in application performance. Thus, applications could benefit from the ability to predict impending handoffs with reasonable accuracy, and modify their behavior to counter the performance degradation that accompanies handoffs. In this paper, we study whether attributes relating to the cellular network conditions measured at handsets can accurately predict handoffs. In particular, we develop a machine learning framework to predict handoffs in the near future. An evaluation on handoff traces from a large US cellular carrier shows that our approach can achieve 80% accuracy -- 27% better than a naive predictor.

Breaking and Fixing VoLTE: Exploiting Hidden Data Channels and Mis-implementations

Long Term Evolution (LTE) is becoming the dominant cellular networking technology, shifting the cellular network away from its circuit-switched legacy towards a packet-switched network that resembles the Internet. To support voice calls over the LTE network, operators have introduced Voice-over-LTE (VoLTE), which dramatically changes how voice calls are handled, both from user equipment and infrastructure perspectives. We find that this dramatic shift opens up a number of new attack surfaces that have not been previously explored. To call attention to this matter, this paper presents a systematic security analysis. Unlike the traditional call setup, the VoLTE call setup is controlled and performed at the Application Processor (AP), using the SIP over IP. A legitimate user who has control over the AP can potentially control and exploit the call setup process to establish a VoLTE channel. This combined with the legacy accounting policy (e.g., unlimited voice and the separation of data and voice) leads to a number of free data channels. In the process of unveiling the free data channels, we identify a number of additional vulnerabilities of early VoLTE implementations, which lead to serious exploits, such as caller spoofing, over-billing, and denial-of-service attacks. We identify the nature of these vulnerabilities and concrete exploits that directly result from the adoption of VoLTE. We also propose immediate countermeasures that can be employed to alleviate the problems. However, we believe that the nature of the problem calls for a more comprehensive solution that eliminates the root causes at mobile devices, mobile platforms, and the core network.

FCP: a flexible transport framework for accommodating diversity

Transport protocols must accommodate diverse application and network requirements. As a result, TCP has evolved over time with new congestion control algorithms such as support for generalized AIMD, background flows, and multipath. On the other hand, explicit congestion control algorithms have been shown to be more efficient. However, they are inherently more rigid because they rely on in-network components. Therefore, it is not clear whether they can be made flexible enough to support diverse application requirements. This paper presents a flexible framework for network resource allocation, called FCP, that accommodates diversity by exposing a simple abstraction for resource allocation. FCP incorporates novel primitives for end-point flexibility (aggregation and preloading) into a single framework and makes economics-based congestion control practical by explicitly handling load variations and by decoupling it from actual billing. We show that FCP allows evolution by accommodating diversity and ensuring coexistence, while being as efficient as existing explicit congestion control algorithms.

Hulu in the neighborhood

Internet Service Providers (ISPs) are in a constant race to meet the bandwidth demands of their subscribers. Access link upgrades, however, are expensive and take years to deploy. Many ISPs are looking for alternative solutions to reduce the need for continuous and expensive infrastructure expansion. This paper shows that there are many forms of local connectivity and storage in residential environments, and that these resources can be used to relieve the access network load. Making effective use of this local connectivity, however, introduces several challenges that require careful application and protocol design.We present a new system for a neighborhood-assisted video-on-demand service that reduces access link traffic by carefully placing VoD data across the neighborhood. We demonstrate that this approach can reduce the access network traffic that ISPs must provision for by up to 45% while still providing high-quality service.