Data availability is perilous in distributed storing systems, especially when node failures are prevalent in real life. A key requirement is to minimize the amount of data transferred among nodes when recovering the lost or unavailable data of failed nodes. The retrieval solutions for proposed system based on regenerating codes, which are shown to provide fault-tolerant storage and minimum recovery bandwidth. Existing optimal regenerating codes are designed for single node failures. The failures in distributed storing systems, which supplements existing optimal regenerating codes to support a general number of failures including single and concurrent failures. The distributed storage system achieves single and concurrent failures having minimum possible recovery bandwidth for most cases. The proposed system implements single and concurrent failures in distributed storage systems and evaluate our prototype atop a Hadoop HDFS cluster tested with up to 2 storage nodes. The experimental result shows the single and concurrent failures in distributed storage systems prototype conforms to our theoretical findings and achieves recovery bandwidth and stores the lost data.
Keywords: Single and Concurrent failures, Erasure coded System, Recovery bandwidth, Mapreduce .