Automatic and scalable data replication manager in distributed computation and storage infrastructure of Cyber-Physical Systems

Abstract

Cyber-Physical System (CPS) is a rising technology that utilizes computation and storage resources for sensing, processing, analysis, predicting, understanding of field-data, and then uses communication resources for interaction, intervene, and interface management, and finally provides control for systems so that they can inter-operate, evolve, and run in a stable evidence-based environment. There are two major demands when building the storage infrastructure for a CPS cluster to support above-mentioned functionalities: (1) high I/O and network throughput requirements during runtime, and (2) low latency demand for disaster recovery. To address challenges brought by these demands, in this paper, we propose a complete solution called "AutoReplica" - an automatic and scalable data replication manager in distributed computation and storage infrastructure of cyber-physical systems, using tiering storage with SSD (solid state disk) and HDD (hard disk drive). Specifically, AutoReplica uses SSD to absorb hot data and to maximize I/Os, and its intelligent replication scheme further helps to recovery from disaster. To effectively balance the trade-off between I/O performance and fault tolerance, AutoReplica utilizes the SSDs of remote CPS server nodes (which are connected by high speed fibers) to replicate hot datasets cached in the SSD tier of the local CPS server node. AutoReplica has three approaches to build the replica cluster in order to support multiple SLAs. AutoReplica automatically balances loads among nodes, and can conduct seamlessly online migration operation (i.e., migrate-on-write scheme), instead of pausing the subsystem and copying the entire dataset from one node to the other. Lastly, AutoReplica supports parallel prefetching from both primary node and replica node(s) with a new dynamic optimizing streaming technique to improve I/O performance. We implemented AutoReplica on a real CPS infrastructure, and experimental results show that AutoReplica can significantly reduce the total recovery time with slight overhead compared to the no replication cluster and traditional replication clusters.