Conventionally, a Real-time Operating System (RTOS) is built without knowing which specific applications will be executed upon it. The RTOS is built for the general case, rather than to meet the specific requirements of an application. This paper proposes a generic module-based reflective framework to implement an RTOS that allows applications to dynamically adapt the policies within the RTOS to better meet applicationspecific requirements.The specific approach taken is to augment a conventional µkernel with a module-based reflective mechanism that allows applications to dynamically change the behaviour of themselves, and the policies of the underlying RTOS. Reflection is used to allow applications and system modules to access key OS data structures to obtain information pertaining to the current system performance and resource management policies (eg. scheduling). An application is then able to modify or introduce new policies into the RTOS to satisfy its demands. Evaluation of our approach shows a considerable performance gain.

Embedded system applications are becoming more complex, requiring increased memory. However, additional physical memory increases system cost and power consumption. Virtual memory techniques such as paging, can make use of low-power auxiliary memory, allowing applications increased memory for execution. Currently paging yields poor performance due to page swapping overheads. This paper presents a combined approach of using application hints along with an efficient page lock/release mechanism in the OS to reduce paging overheads. This makes paging a viable solution to support out-of-core embedded real-time applications. The Co-operative Application Specific Paging (CASP) mechanism presented works in conjunction with most existing page replacement policies, providing explicit support for applications via insertion of paging hints in the application source code. Both automatic and manual methods of inserting hints are described and evaluated. The benchmark results of a CASP implementation in the Linux 2.6.16 kernel have shown significant reduction in the number of page-faults (22.3%) and a considerable improvement in application execution times (12.5%).

No abstract

Application level interoperability between ubiquitous networked communication devices (e.g. Mobile phones, PDA, CCD camera, etc.) poses many problems. In this paper we consider the issue of efficient application level access to resources on remote devices whilst achieving both network and distribution transparency. Provision of such transparency is difficult as lowresource devices are usually limited to one or two standard communication mediums (e.g. WiFi, Bluetooth, ZigBee). Thus, it is unlikely that an application node can communicate directly with all other nodes, with the requirement for some to act as intermediaries. Also, direct control of remote devices (potentially via some intermediary) in the same manner as local devices is not usually provided by conventional OSs. In this paper we consider the Styx protocol (from the Inferno OS) as a solution to these problems. Styx is defined to provide a file based interface to devices, within a namespace that provides distribution transparency (coping with intermediary devices). However, Styx currently is only available as software, requiring a OS (and CPU). We define and implement a (hardware) Styx IP-core Module 1 to provide both network and distribution transparency for applications that control physically remote devices. For lowresource devices, such an approach removes the need for a CPU (to execute a software OS and Styx implementation). The implementation of the hardware Styx IP-core (and subsequent demonstration) presented within the paper show the efficacy of this hardware Styx approach.

No abstract