Capacity of clustered distributed storage
Capacity of clustered distributed storage
复制标题
DOI：
10.1109/icc.2017.7997392
复制
发表时间：
2016-10
期刊：
影响因子：
--
通讯作者：
Jy-yong Sohn;Beongjun Choi;Sung Whan Yoon;J. Moon
中科院分区：
文献类型：
--
作者：
Jy-yong Sohn;Beongjun Choi;Sung Whan Yoon;J. Moon
建议采用反映分布式存储集群结构的新系统模型来研究修复故障存储节点的带宽需求。具有多个机架/磁盘或本地存储设备网络（例如传感器网络）的大型数据中心是建议的基于集群的模型的良好应用。在涉及集群存储结构的实际场景中，使用驻留在其他集群中的完整节点修复存储节点比基于集群内节点的信息恢复节点更消耗带宽。因此，在分布式存储建模中区分集群内修复带宽和跨集群修复带宽非常重要。建议模型的容量是作为分布式存储系统的基本资源的函数而获得的，即存储容量、集群内修复带宽和跨集群修复带宽。基于容量表达式，分析了实现可靠存储的可行的所需资源集。结果表明，根据封闭形式中指定的法则，通过允许存储容量和集群内修复带宽上的额外资源，可以将跨集群流量最小化至零（即，集群内的本地修复成为可能）。此外，为了获得足够大的存储容量，需要在跨集群流量和集群内流量之间进行权衡。
A new system model reflecting the clustered structure of distributed storage is suggested to investigate bandwidth requirements for repairing failed storage nodes. Large data centers with multiple racks/disks or local networks of storage devices (e.g. sensor network) are good applications of the suggested cluster-based model. In realistic scenarios involving clustered storage structures, repairing storage nodes using intact nodes residing in other clusters is more bandwidth-consuming than restoring nodes based on information from intra-cluster nodes. Therefore, it is important to differentiate between intra-cluster repair bandwidth and cross-cluster repair bandwidth in modeling distributed storage. Capacity of the suggested model is obtained as a function of fundamental resources of distributed storage systems, namely, storage capacity, intra-cluster repair bandwidth and cross-cluster repair bandwidth. Based on the capacity expression, feasible sets of required resources which enable reliable storage are analyzed. It is shown that the cross-cluster traffic can be minimized to zero (i.e., local repair within a cluster becomes possible) by allowing extra resources on storage capacity and intra-cluster repair bandwidth, according to a law specified in a closed-form. Moreover, trade-off between cross-cluster traffic and intra-cluster traffic is observed for sufficiently large storage capacity.