Analysis of checkpointing for schedulability of real-time systems

Checkpointing is a relatively cost effective method for achieving fault tolerance in real-time systems. Since checkpointing schemes depend on time redundancy, they could affect the correctness of the system by causing deadlines to be missed. This paper provides exact schedulability tests for fault tolerant task sets under specified failure hypothesis and employing checkpointing to assist in fault recovery. The effects of checkpointing strategies on task response time are analysed and some insights for optimal checkpointing are provided. The emphasis here is on utilizing this analysis as an off-line design support tool. Key words— Real-time systems, Checkpointing, realtime scheduling, schedulability analysis, fault-tolerant systems, fault-tolerant scheduling, real-time system design. Predictable performance in the event of failures is of paramount importance in most safety critical real-time systems. Among various hardware as well as software techniques employed for achieving fault-tolerance, checkpointing is a relatively cost-effective scheme. One needs to checkpoint only those variables whose values have changed since the last checkpoint operation. Bowen and Pradhan [1] give a detailed discussion on different types of processor as well as memory based checkpointing schemes. These schemes allow checkpoints to be performed like atomic operations with negligible overhead using ‘copyback’ cache and atomic-update feature of stable transaction memory(STM). However, since checkpointing schemes depend on time redundancy, it can affect the correctness of the system by causing deadlines to be missed.