Method for Improving Mean Time to Data Loss (MTDL) in a Fixed Content Distributed Data Storage

摘要

An archival storage cluster of preferably symmetric nodes includes a data protection management system that periodically organizes the then-available nodes into one or more protection sets, with each set comprising a set of n nodes, where “n” refers to a configurable “data protection level” (DPL). At the time of its creation, a given protection set is closed in the sense that each then available node is a member of one, and only one, protection set. When an object is to be stored within the archive, the data protection management system stores the object in a given node of a given protection set and then constrains the distribution of copies of that object to other nodes within the given protection set. As a consequence, all DPL copies of an object are all stored within the same protection set, and only that protection set. This scheme significantly improves MTDL for the cluster as a whole, as the data can only be lost if multiple failures occur within nodes of a given protection set. This is far more unlikely than failures occurring across any random distribution of nodes within the cluster.

主权项

1. A system comprising:
a plurality of servers configured to be grouped, for a data protection level which defines a number of servers to be able to store a copy of content data, into one of a plurality of protection sets being associated with the data protection level; and a network that couples the plurality of servers; and wherein the system is configured to, upon receipt of first content data that has the protection level, store copies of the first content data to each server in a first protection set which is associated with the protection level, and prevent distribution of the copies of the first content data to any other servers in any other protection sets which are associated with the protection level.