Multi-core Partitioning for Mixed Criticality Software Isolation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The high cost of certifying flight critical software due to the need for all software to be certified at the highest safety or security level when mixed criticality systems lack guaranteed separation, and existing methods fail to leverage multi-core systems and hardware virtualization for efficient partitioning.
Innovation Solution
A method and apparatus for partitioning a data processing system with multiple cores, where a configuration profile is used to assign partitions to cores, allocate resources, and release control until the next system startup, enabling independent operation of each partition and reducing certification costs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If all software is certified at the highest safety or security level to ensure system safety and security, then system reliability is improved, but certification cost increases significantly
Solution Approach 1:
The patent divides the system into multiple isolated partitions, each containing software at different safety or security levels. This segmentation allows each partition to be certified at its appropriate level rather than requiring all software to be certified at the highest level, thereby reducing overall certification costs while maintaining system reliability through enforced isolation between partitions.
2Reliability
If hardware and software partitions are used to guarantee safety and security of mixed criticality systems, then system reliability is improved, but software size and system complexity increase
Solution Approach 1:
The patent implements self-service mechanisms where each partition automatically manages its own resources and operations within its isolated environment. The partitioning infrastructure provides automatic isolation and resource management, reducing the need for complex inter-partition communication software and minimizing the overall partitioning software size while still guaranteeing safety and security.
Data Source
AI summary
The different advantageous embodiments provide a system for partitioning a data processing system comprising a number of cores and a partitioning process. The partitioning process is configured to assign a number of partitions to the number of cores. Each partition in the number of partitions is assigned to a separate number of cores from the number of cores.