Cold data eviction using node congestion probability for HDFS based on Hybrid SSD

Data exist in various persistent-storage formats, and Hadoop distributed file system (HDFS) has been recognized to be effective for distributed storage and processing. Recently, the research of Hybrid NAND flash-based solid state drives (SSD) is rapidly expanding into the storage areas including Hybrid ReRAM/MLC NAND SSD. Most existing researches of Hybrid SSD are based on a single storage, while the management of multiple nodes like HDFS is still immature. In this paper a new efficient cold data eviction scheme is proposed which is based on the state of node congestion of Hybrid SSD for HDFS. It computer simulation reveals that the proposed scheme significantly reduces average recovery and execution time in comparison to the existing replication schemes.