Abstract

Here, we propose a weighted checkpointing approach for Mobile Distributed Computing Systems (MDCSs) that significantly reduces checkpointing overheads on mobile nodes. Checkpointing protocols can be coordinated, log-based or quasi-synchronous. Coordinated checkpointing requires extra synchronisation messages and may block the underlying computation. In quasi-synchronous approach, processes have limited autonomy in checkpointing but all nodes need not checkpoint concurrently. Such protocols guarantee consistent global state but results in dynamic checkpointing overheads. To minimise these overheads, we propose a weighted checkpointing protocol that requires no synchronisation messages, reduces the checkpointing overheads at mobile nodes but requires logging for mobile nodes. Simulation results show that the new approach is better than quasi-synchronous approach.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call