An-I Andy Wang

The Conquest file system: Better performance through a disk/persistent-RAM hybrid design

Modern file systems assume the use of disk, a system-wide performance bottleneck for over a decade. Current disk caching and RAM file systems either impose high overhead to access memory content or fail to provide mechanisms to achieve data persistence across reboots.The Conquest file system is based on the observation that memory is becoming inexpensive, which enables all file system services to be delivered from memory, except for providing large storage capacity. Unlike caching, Conquest uses memory with battery backup as persistent storage, and provides specialized and separate data paths to memory and disk. Therefore, the memory data path contains no disk-related complexity. The disk data path consists of optimizations only for the specialized disk usage pattern.Compared to a memory-based file system, Conquest incurs little performance overhead. Compared to several disk-based file systems, Conquest achieves 1.3x to 19x faster memory performance, and 1.4x to 2.0x faster performance when exercising both memory and disk.Conquest realizes most of the benefits of persistent RAM at a fraction of the cost of a RAM-only solution. It also demonstrates that disk-related optimizations impose high overheads for accessing memory content in a memory-rich environment.

A survey of confidential data storage and deletion methods

As the amount of digital data grows, so does the theft of sensitive data through the loss or misplacement of laptops, thumb drives, external hard drives, and other electronic storage media. Sensitive data may also be leaked accidentally due to improper disposal or resale of storage media. To protect the secrecy of the entire data lifetime, we must have confidential ways to store and delete data. This survey summarizes and compares existing methods of providing confidential storage and deletion of data in personal computing environments.

PARAID: A gear-shifting power-aware RAID

Reducing power consumption for server-class computers is important, since increased energy usage causes more heat dissipation, greater cooling requirements, reduced computational density, and higher operating costs. For a typical data center, storage accounts for 27% of energy consumption. Conventional server-class RAIDs cannot easily reduce power because loads are balanced to use all disks, even for light loads. We have built the power-aware RAID (PARAID), which reduces energy use of commodity server-class disks without specialized hardware. PARAID uses a skewed striping pattern to adapt to the system load by varying the number of powered disks. By spinning disks down during light loads, PARAID can reduce power consumption, while still meeting performance demands, by matching the number of powered disks to the system load. Reliability is achieved by limiting disk power cycles and using different RAID encoding schemes. Based on our five-disk prototype, PARAID uses up to 34% less power than conventional RAIDs while achieving similar performance and reliability.

Modeling vanet deployment in urban settings

The growing interest in wireless Vehicular Ad Hoc Networks (VANETs) has prompted greater research into simulation models that better reflect urban VANET deployments. Still, we lack a systematic understanding of the required level of simulation details in modeling various real-world urban constraints. In this work, we developed a series of simulation models that account for street layout, traffic rules, multilane roads, acceleration-deceleration, and RF attenuation due to obstacles. Using real and controlled synthetic maps, we evaluated the sensitivity of the simulation results toward these details. Our results indicate that the delivery ratio and packet delays in VANETs are more sensitive to the clustering effect of vehicles at intersections and their acceleration/deceleration. The VANET performance appears to be only marginally affected by the simulation of multiple lanes and careful synchronization at traffic signals. We also found that the performance in dense VANETs improves significantly when routing decisions are limited to a wireless backbone of mesh nodes, whereas in sparse VANETs, performance improves when vehicles also participate in ad hoc routing. Finally, through measurement and analysis of signal strengths around urban city blocks, we show that the effect of signal attenuation due to physical obstacles can potentially be parameterized in simulations. Our work provides a starting point for further understanding and development of more accurate VANET simulation model.

Electric-field-based routing: a reliable framework for routing in MANETs

Constructing multipath routes in MANETs is important for providing reliable delivery, load balancing, and bandwidth aggregation. However, popular multipath routing approaches fail to produce spatially disjoint routes in a simple and cost-effective manner, and existing single-path approaches cannot be easily modified to produce multiple disjoint routes. In this paper we propose Electric-Field-Based Routing (EFR) as a reliable framework for routing in MANETs by applying the concept of electric field lines. Our location-based protocol naturally provides spatially disjoint routes based on the shapes of these lines. The computation is highly localized and requires no explicit coordination among routes. EFR can also be easily extended to offer load-balancing, bandwidth aggregation, and power management. Through simulation, EFR shows a higher delivery ratio and lower overhead under high mobility, high network loads, and network failures compared to popular multipath and location-based schemes. EFR also demonstrates high resiliency to DoS attacks.

ContextProvider: Context awareness for medical monitoring applications

Smartphones are sensor-rich and Internet-enabled. With their on-board sensors, web services, social media, and external biosensors, smartphones can provide contextual information about the device, user, and environment, thereby enabling the creation of rich, biologically driven applications. We introduce ContextProvider, a framework that offers a unified, query-able interface to contextual data on the device. Unlike other context-based frameworks, ContextProvider offers interactive user feedback, self-adaptive sensor polling, and minimal reliance on third-party infrastructure. ContextProvider also allows for rapid development of new context and bio-aware applications. Evaluation of ContextProvider shows the incorporation of an additional monitoring sensor into the framework with fewer than 100 lines of Java code. With adaptive sensor monitoring, power consumption per sensor can be reduced down to 1% overhead. Finally, through the use of context, accuracy of data interpretation can be improved by up to 80%.

Modeling Device Driver Effects in Real-Time Schedulability Analysis: Study of a Network Driver

Device drivers are integral components of operating systems. The computational workloads imposed by device drivers tend to be aperiodic and unpredictable because they are triggered in response to events that occur in the device, and may arbitrarily block or preempt other time-critical tasks. This characteristic poses significant challenges in real-time systems, where schedulability analysis is essential to guarantee system-wide timing constraints. At the same time, device driver workloads cannot be ignored. Demand-based schedulability analysis is a technique that has been successful in validating the timing constraints in both single and multiprocessor systems. In this paper we present two approaches to demand-based schedulability analysis of systems that include device drivers. First, we derive load-bound functions using empirical measurement techniques. Second, we modify the scheduling of network device driver tasks in Linux to implement an algorithm for which a load-bound function can be derived analytically. We demonstrate the practicality of our approach through detailed experiments with a network device under Linux. Our results show that, even though the network device driver does not conform to conventional periodic or sporadic task models, it can be successfully modeled using hyperbolic load-bound functions that are fitted to empirical performance measurements

TrueErase: per-file secure deletion for the storage data path

The ability to securely delete sensitive data from electronic storage is becoming important. However, current per-file deletion solutions tend to be limited to a segment of the operating systems storage data path or specific to particular file systems or storage media. This paper introduces TrueErase, a holistic secure-deletion framework. Through its design, implementation, verification, and evaluation, TrueErase shows that it is possible to build a legacy-compatible full-storage-data-path framework that performs per-file secure deletion and works with common file systems and solid-state storage, while handling common system failures. In addition, this framework can serve as a building block for encryption- and tainting-based secure-deletion systems.

BEAT: Bio-Environmental Android Tracking

We introduce BEAT (Bio-Environmental Android Tracking), which provides methods for collecting, processing, and archiving ones daily vital and spatiotemporal statistics using off-the-shelf wireless devices and biologic and environmental sensors. BEAT can operate in a self-contained manner on a mobile device and analyze vital information in real time. It uses statistics such as heartbeat variance and range thresholds to issue alerts. Alerts are propagated in a tiered fashion, so that the end user and his/her social contacts have a chance to detect false alerts before contacting medical professionals. BEAT is built on the open Android platform to support a diverse class of mobile devices. The framework can be extended to a full-fledged personal health monitoring system by incorporating additional biosensor data such as blood pressure, glucose, and weight.

When cryptography meets storage

Confidential data storage through encryption is becoming increasingly important. Designers and implementers of encryption methods of storage media must be aware that storage has different usage patterns and properties compared to securing other information media such as networks. In this paper, we empirically demonstrate two-time pad vulnerabilities in storage that are exposed via shifting file contents, in-place file updates, storage mechanisms hidden by layers of abstractions, inconsistencies between memory and disk content, and backups. We also demonstrate how a simple application of Bloom filters can automatically extract plaintexts from two-time pads. Further, our experience sheds light on system research directions to better support cryptographic assumptions and guarantees.