摘要：Mark Cavage and David Pacheco, Joyent While the term big data is vague enough to have lost much of its meaning, today's storage systems are growing more quickly and managing more data than ever before. Consumer devices generate large numbers of photos, videos, and other large digital assets. Machines are rapidly catching up to humans in data generation through extensive recording of system logs and metrics, as well as applications such as video capture and genome sequencing. Large data sets are now commonplace, and people increasingly want to run sophisticated analyses on the data. In this article, big data refers to a corpus of data large enough to benefit significantly from parallel computation across a fleet of systems, where the efficient orchestration of the computation is itself a considerable challenge. The first problem with operating on big data is maintaining the infrastructure to store it durably and ensure its availability for computation, which may range from analytic query access to direct access over HTTP. While there is no universal solution to the storage problem, managing a storage system of record (that is, one hosting the primary copy of data that must never be lost) typically falls to enterprise storage solutions such as SANs (storage area networks). These solutions do not typically offer WAN (wide area network) access, however, and they often require extra infrastructure to ingest data from and export data to arbitrary clients; this is hard to scale with the data footprint.
