Richard Anthony

Emergence: a paradigm for robust and scalable distributed applications

Natural distributed systems are adaptive, scalable and fault-tolerant. Emergence science describes how higher-level self-regulatory behaviour arises in natural systems from many participants following simple rule-sets. Emergence advocates simple communication models, autonomy and independence, enhancing robustness and self-stabilization. High-quality distributed applications such as autonomic systems must satisfy the appropriate nonfunctional requirements which include scalability, efficiency, robustness, low-latency and stability. However the traditional design of distributed applications, especially in terms of the communication strategies employed, can introduce compromises between these characteristics. This paper discusses ways in which emergence science can be applied to distributed computing, avoiding some of the compromises associated with traditionally-designed applications. To demonstrate the effectiveness of this paradigm, an emergent election algorithm is described and its performance evaluated. The design incorporates nondeterministic behaviour. The resulting algorithm has very low communication complexity, and is simultaneously very stable, scalable and robust.

Policy-Centric Integration and Dynamic Composition of Autonomic Computing Techniques

This paper presents innovative work in the development of policy-based autonomic computing. The core of the work is a powerful and flexible policy-expression language AGILE, which facilitates run-time adaptable policy configuration of autonomic systems. AGILE also serves as an integrating platform for other self-management technologies including signal processing, automated trend analysis and utility functions. Each of these technologies has specific advantages and applicability to different types of dynamic adaptation. The AGILE platform enables seamless interoperability of the different technologies to each perform various aspects of self-management within a single application. The various technologies are implemented as object components. Self-management behaviour is specified using the policy language semantics to bind the various components together as required. Since the policy semantics support run-time re-configuration, the self-management architecture is dynamically composable. Additional benefits include the standardisation of the application programmer interface, terminology and semantics, and only a single point of embedding is required.

A Policy-Definition Language and Prototype Implementation Library for Policy-based Autonomic Systems

This paper presents work towards generic policy toolkit support for autonomic computing systems in which the policies themselves can be adapted dynamically and automatically. The work is motivated by three needs: the need for longer-term policy-based adaptation where the policy itself is dynamically adapted to continually maintain or improve its effectiveness despite changing environmental conditions; the need to enable non autonomics-expert practitioners to embed self-managing behaviours with low cost and risk; and the need for adaptive policy mechanisms that are easy to deploy into legacy code. A policy definition language is presented; designed to permit powerful expression of self-managing behaviours. The language is very flexible through the use of simple yet expressive syntax and semantics and facilitates a very diverse policy behaviour space through both hierarchical and recursive uses of language elements. A prototype library implementation of the policy support mechanisms is described. The library reads and writes policies in well-formed XML script. The implementation extends the state of the art in policy-based autonomics through innovations which include support for multiple policy versions of a given policy type, multiple configuration templates and meta-policies to dynamically select between policy instances and templates. Most significantly, the scheme supports hot-swapping between policy instances. To illustrate the feasibility and generalised applicability of these tools, two dissimilar example deployment scenarios are examined. The first is taken from an exploratory implementation of self-managing parallel processing and is used to demonstrate the simple and efficient use of the tools.

Embedding Dynamic Behaviour into a Self-configuring Software System

This paper describes a methodology for embedding dynamic behaviour into software components. The implications and system architecture requirements to support this adaptivity are discussed. This work is part of a European Commission funded and industry supported project to produce a reconfigurable middleware for use in automotive systems. Such systems must be trustable against illegal internal behaviour and activity with external origins, additional devices for example. Policy-based computing is used here as an example of embedded logic. A key contribution of this work is the way in which static and dynamic aspects of the system are interfaced, such that the behaviour can be changed very flexibly (even during run-time), without modification, recompilation or redeployment of the embedded application code. An implementation of these concepts is presented, focussing on achieving trust in the use of dynamic behaviour.

Deadline Aware Virtual Machine Scheduler for Grid and Cloud Computing

Virtualization technology has enabled applications to be decoupled from the underlying hardware providing the benefits of portability, better control over execution environment and isolation. It has been widely adopted in scientific grids and commercial clouds. Since virtualization, despite its benefits incurs a performance penalty, which could be significant for systems dealing with uncertainty such as High Performance Computing (HPC) applications where jobs have tight deadlines and have dependencies on other jobs before they could run. The major obstacle lies in bridging the gap between performance requirements of a job and performance offered by the virtualization technology if the jobs were to be executed in virtual machines. In this paper, we present a novel approach to optimize job deadlines when run in virtual machines by developing a deadline-aware algorithm that responds to job execution delays in real time, and dynamically optimizes jobs to meet their deadline obligations. Our approaches borrowed concepts both from signal processing and statistical techniques, and their comparative performance results are presented later in the paper including the impact on utilization rate of the hardware resources.

A Run-Time Configurable Software Architecture for Self-Managing Systems

This paper describes a highly flexible component architecture, primarily designed for automotive control systems, that supports distributed dynamically- configurable context-aware behaviour. The architecture enforces a separation of design-time and run-time concerns, enabling almost all decisions concerning runtime composition and adaptation to be deferred beyond deployment. Dynamic context management contributes to flexibility. The architecture is extensible, and can embed potentially many different self-management decision technologies simultaneously. The mechanism that implements the run-time configuration has been designed to be very robust, automatically and silently handling problems arising from the evaluation of self- management logic and ensuring that in the worst case the dynamic aspects of the system collapse down to static behavior in totally predictable ways.

Enabling and optimizing pilot jobs using xen based virtual machines for the HPC grid applications

The primary motivation for uptake of virtualization have been resource isolation, capacity management and resource customization: isolation and capacity management allow providers to isolate users from the site and control their resources usage while customization allows end-users to easily project the required environment onto a variety of sites. Various approaches have been taken to integrate virtualization with Grid technologies. In this paper, we propose an approach that combines virtualization on the existing software infrastructure such as Pilot Jobs with minimum change on the part of resource providers. We also present a standard API to enable a wider set of applications including Batch systems to deploy virtual machines on-demand as isolated job sandboxes. To illustrate the usefulness of this approach, we also evaluate the impact of Xen virtualization on memory and compute intensive tasks, and present our results that how memory and scheduling parameters could be tweaked to optimize job performance.

Policy-based autonomic computing with integral support for self-stabilisation

This paper describes the AGILE technology for building self-managing systems. AGILE serves as both a policy expression language and a framework that facilitates the integration and dynamic composition of several autonomic computing techniques within a single deployment technology and supports run-time self-reconfiguration. The paper also discusses the need for self-stabilisation mechanisms for autonomic systems in order to reduce the reliance of autonomic components on external supervision and extend their behavioural scope and trustability. The self-stabilisation approach taken and the initial support mechanisms in this regard that have been integrated into AGILE are examined. A demonstration application illustrates the powerful dynamic adaptation capabilities of the technology. The self-stabilisation theme is prominent, but other aspects are also demonstrated, including dynamic reconfiguration at the policy level, automated built-in signal processing and trend analysis, the integration of policies and utility functions and the ease with which such advanced self-managing behaviour can be configured using AGILE.

Context-Aware Adaptation in DySCAS

DySCAS is a dynamically self-configuring middleware for automotive control systems. The addition of autonomic, context-aware dynamic configuration to automotive control systems brings a potential for a wide range of benefits in terms of robustness, flexibility, upgrading etc. However, the automotive systems represent a particularly challenging domain for the deployment of autonomics concepts, hav- ing a combination of real-time performance constraints, severe resource limitations, safety-critical aspects and cost pressures. For these reasons current systems are stat- ically configured. This paper describes the dynamic run-time configuration aspects of DySCAS and focuses on the extent to which context-aware adaptation has been achieved in DySCAS, and the ways in which the various design and implementation challenges are met.

Autonomic Middleware for Automotive Embedded Systems

This chapter describes DySCAS: an advanced autonomic platform-independent middleware framework for automotive embedded systems. The concepts and architecture are motivated and described in detail, focusing on the need for, and achievement of, high flexibility and automatic run-time reconfiguration. The design of the middleware is positioned with respect to the way it overcomes the specific technical, environmental, and performance challenges of the automotive domain. Self-management is achieved in terms of automatic configuration for context-aware behavior, resource-use efficiency, and self-healing to handle run-time detected faults. The self-management is governed by the use of policies distributed throughout the middleware components. The simulation techniques that have been used for extensive validation are described and some key results presented. A reference implementation is presented, illustrating the way in which the various concepts and mechanisms can be realized and orchestrated.