Real-Time In-Memory Checkpointing for Future Hybrid Memory Systems

In this paper, we study real-time in-memory checkpointing as an effective means to improve the reliability of future large-scale parallel processing systems. Under this context, the checkpoint overhead can become a significant perfor-mance bottleneck. Novel memory system designs with upcoming non-volatile random access memory (NVRAM) technologies are emerging to address this performance is-sue. However, we find that those designs can still have prohibitively high checkpoint overhead and system down-time, especially when checkpoints are taken frequently to implement a reliable system. In this paper, we propose a novel in-memory checkpointing system, named Mona, for reducing the checkpoint overhead of hybrid memory systems with NVRAM and DRAM. To minimize the in-memory checkpoint overhead, Mona dynamically writes par-tial checkpoints from DRAM to NVRAM during application execution. To reduce the interference of partial check-pointing, Mona utilizes runtime idle periods and leverages a cost model to guide partial checkpointing decisions for individual DRAM ranks. We further develop load-balancing mechanisms to balance checkpoint overheads across different DRAM ranks. Simulation results demonstrate the efficiency and effectiveness of Mona in reducing the checkpoint over-head, downtime and restarting time