2013/01/08 by Bernat Gastón, Gastón, Bernat, Jaume Pujol +3 · 3 citations
Computer Science · #Advanced Data Storage Technologies #Caching and Content Delivery #Distributed #Distributed and Parallel Computing Systems #Distributed systems and fault tolerance #FOS: Computer and information sciences #Information Theory (cs.IT) #Parallel #Peer-to-Peer Network Technologies #and Cluster Computing (cs.DC)
paper · pdf · doi:10.48550/arxiv.1301.1549
openalex publication_date 2013/01/08 · openalex created_date 2022/10/02 · openalex updated_date 2026/07/28
In a realistic distributed storage environment, storage nodes are usually\nplaced in racks, a metallic support designed to accommodate electronic\nequipment. It is known that the communication (bandwidth) cost between nodes\nwithin a rack is much lower than the communication (bandwidth) cost between\nnodes within different racks.\n In this paper, a new model, where the storage nodes are placed in two racks,\nis proposed and analyzed. In this model, the storage nodes have different\nrepair costs to repair a node depending on the rack where they are placed. A\nthreshold function, which minimizes the amount of stored data per node and the\nbandwidth needed to regenerate a failed node, is shown. This threshold function\ngeneralizes the threshold function from previous distributed storage models.\nThe tradeoff curve obtained from this threshold function is compared with the\nones obtained from the previous models, and it is shown that this new model\noutperforms the previous ones in terms of repair cost.\n