Vicente Esteve UPVLC viesllo@disca.upv.es Ismael Ripoll UPVLC iripoll@disca.upv.es 2003 OCERA Consortium This component can be used outside of the OCERA framework. RTLinux Porting Stand-Alone RTLinux will be a Linux independent implementation of RTLinux. Stand-Alone RTLinux will be a bootable executive with the following main features: a) Low memory overhead. The core systems contains only following modules: the code of RTLinux, the minimum code needed to boot the system and basic virtual memory management. b) Scalability. Users will be able to customize RTLinux funcionalities to reduce kernel memory usage. c) Porting will be possible to systems without hardware for virtual memory support. Therefore, Stand-Alone RTLinux could be ported to a wider range of architectures. d) Less TLB and memory cache misses (or none at all, if paging is not activated) since only real-time applications are being executed. e) We are not longer limited by the Linux memory manager. Standard RTLinux memory management relays completely on the Linux so it is not possible to implement custom virtual memory management algorithms. Stand-Alone RTLinux has full control of the MMU. Current implementation provides three different memory schemes: 1.- Non protected memory. RTLinux executive and application can read and write at any memory location. 2.- Simple memory protection. The application can not write into the RTLinux executive memory space, and null pointers are catched. 3.- Context memory protection: Several applications (each application can run one or more threads) are executed in a protected memory space. Each aplication can read and write its own data but only read system and other applications code and data.