Anil Madhavapeddy

Unikernels: library operating systems for the cloud

We present unikernels, a new approach to deploying cloud services via applications written in high-level source code. Unikernels are single-purpose appliances that are compile-time specialised into standalone kernels, and sealed against modification when deployed to a cloud platform. In return they offer significant reduction in image sizes, improved efficiency and security, and should reduce operational costs. Our Mirage prototype compiles OCaml code into unikernels that run on commodity clouds and offer an order of magnitude reduction in code size without significant performance penalty. The architecture combines static type-safety with a single address-space layout that can be made immutable via a hypervisor extension. Mirage contributes a suite of type-safe protocol libraries, and our results demonstrate that the hypervisor is a platform that overcomes the hardware compatibility issues that have made past library operating systems impractical to deploy in the real-world.

Using visual tags to bypass Bluetooth device discovery

One factor that has limited the use of Bluetooth as a networking technology for publicly accessible mobile services is the way in which it handles Device Discovery. Establishing a Bluetooth connection between two devices that have not seen each other before is slow and, from a usability perspective, often awkward. In this paper we present the implementation of an end-to-end Bluetooth-based mobile service framework designed specifically to address this issue. Rather than using the standard Bluetooth Device Discovery model to detect nearby mobile services, our system relies on machine-readable visual tags for out-of-band device and service selection. Our work is motivated by the recent proliferation of cameraphones and PDAs with built-in cameras. We have implemented the described framework completely for Nokia Series 60 cameraphones and demonstrated that our tag-based connection-establishment technique (i) offers order of magnitude time improvements over the standard Bluetooth Device Discovery model; and (ii) is significantly easier to use in a variety of realistic scenarios. Our implementation is available for free download.

A study of bluetooth propagation using accurate indoor location mapping

The ubiquitous computing community has widely researched the use of 802.11 for the purpose of location inference. Meanwhile, Bluetooth is increasingly widely deployed due to its low power consumption and cost. This paper describes a study of Bluetooth radio propagation using an accurate indoor location system to conduct fine-grained signal strength surveys. We discuss practical problems and requirements encountered setting up the infrastructure using the ultrasonic Active Bat indoor location system, and limitations of the commodity Bluetooth devices used. We conclude that Bluetooth is poorly suited to the purpose of fine-grained, low latency location inference due to specification and hardware limitations, and note that the movement speed of mobile devices is an important factor in calculating available bandwidth. We publish our data sets of signal strength samples for the community to freely use in future research.

Unikernels: the rise of the virtual library operating system

What if all the software layers in a virtual appliance were compiled within the same safe, high-level language framework?

Context-Aware Computing with Sound

We propose audio networking: using ubiquitously available sound hardware (i.e. speakers, sound-cards and microphones) for low-bandwidth, wireless networking. A variety of location- and context-aware applications that use audio networking are presented including a location system, a pick-and-drop interface and a framework for embedding digital attachments in voice notes or telephone conversations. Audio networking has a number of interesting characteristics that differentiate it from existing wireless networking technologies: (i) it offers fine-grained control over the range of transmission (since audio APIs allow fine-grained volume adjustment); (ii) walls of buildings are typically designed specifically to attenuate sound waves so one can easily contain transmission to a single room; (iii) it allows existing devices that record or play audio to be brought into the user interface; and (iv) it offers the potential to unify device-to-device and device-to-human communication.

Melange: creating a "functional" internet

Most implementations of critical Internet protocols are written in type-unsafe languages such as C or C++ and are regularly vulnerable to serious security and reliability problems. Type-safe languages eliminate many errors but are not used to due to the perceived performance overheads. We combine two techniques to eliminate this performance penalty in a practical fashion: strong static typing and generative meta-programming. Static typing eliminates run-time type information by checking safety at compile-time and minimises dynamic checks. Meta-programming uses a single specification to abstract the low-level code required to transmit and receive packets. Our domain-specific language, MPL, describes Internet packet protocols and compiles into fast, zero-copy code for both parsing and creating these packets. MPL is designed for implementing quirky Internet protocols ranging from the low-level: Ethernet, IPv4, ICMP and TCP; to the complex application-level: SSH, DNS and BGP; and even file-system protocols such as 9P. We report on fully-featured SSH and DNS servers constructed using MPL and our OCaml framework Melange, and measure greater throughput, lower latency, better flexibility and more succinct source code than their C equivalents OpenSSH and BIND. Our quantitative analysis shows that the benefits of MPL-generated code overcomes the additional overheads of automatic garbage collection and dynamic bounds checking. Qualitatively, the flexibility of our approach shows that dramatic optimisations are easily possible.

Reconfigurable Data Processing for Clouds

Reconfigurable computing in the cloud helps to solve many practical problems relating to scaling out data-centers where computation is limited by energy consumption or latency. However, for reconfigurable computing in the cloud to become practical several research challenges have to be addressed. This paper identifies some of the perquisites for reconfigurable computing systems in the cloud and picks out several scenarios made possible with immense cloud-based computing capability.

Feedback, latency, accuracy: exploring tradeoffs in location-aware gaming

We are witnessing the development of large-scale location systems and a corresponding rise in the popularity of location-aware applications, especially games. Traditional computer games have pushed the limits of CPU and graphics card performance for many years and experience suggests that location-aware games will place similar demands upon location systems. Unlike traditional gaming platforms however, the mobile devices that interact with location systems are heavily constrained especially in the number of ways that feedback can be provided.In this paper we describe a location-aware, fast-paced, close quarters action game and use it to experiment with three key components of future location-aware gaming platforms: (i) the location system, (ii) the network to connect the mobile devices, and (iii) the feedback and computational capabilities of the mobile devices themselves.We investigate the tradeoffs that are possible between these components, the effect of the feedback channel and the suitability of Bluetooth as a network for mobile game devices.

SibylFS: formal specification and oracle-based testing for POSIX and real-world file systems

Systems depend critically on the behaviour of file systems, but that behaviour differs in many details, both between implementations and between each implementation and the POSIX (and other) prose specifications. Building robust and portable software requires understanding these details and differences, but there is currently no good way to systematically describe, investigate, or test file system behaviour across this complex multi-platform interface. In this paper we show how to characterise the envelope of allowed behaviour of file systems in a form that enables practical and highly discriminating testing. We give a mathematically rigorous model of file system behaviour, SibylFS, that specifies the range of allowed behaviours of a file system for any sequence of the system calls within our scope, and that can be used as a test oracle to decide whether an observed trace is allowed by the model, both for validating the model and for testing file systems against it. SibylFS is modular enough to not only describe POSIX, but also specific Linux, OS X and FreeBSD behaviours. We complement the model with an extensive test suite of over 21 000 tests; this can be run on a target file system and checked in less than 5 minutes, making it usable in practice. Finally, we report experimental results for around 40 configurations of many file systems, identifying many differences and some serious flaws.

Cost, performance & flexibility in OpenFlow: Pick three

OS virtualization and cloud computing have radically changed the way Internet services are deployed: enterprises share third-party datacenters, deploying existing applications with minimal changes. Recent measurements reveal a lack of traffic isolation capabilities within the datacenter with network performance exhibiting high variability. We advocate addressing this problem by allowing applications to express their own forwarding logic using OpenFlow to achieve application specific optimal performance. We present an OpenFlow implementation within the Mirage application synthesis framework, in the form of library implementations of a modular controller and an extensible OpenFlow-enabled switch, able to expose the underlying network infrastructure to cloud applications. By linking into the application, this provides a safe yet highly extensible framework for programming network control that, although unoptimised, still provides reasonable performance when compared with existing controllers.