Systems and methods providing metadata for tracking of information on a distributed file system of storage devices

摘要

The invention relates to a distributed file system for storing data files among a plurality of modular storage units, the file system comprising a plurality of storage units (114) configured to store data blocks; receive a data file read request (C); retrieve location data information corresponding the requested data file, wherein the location data information includes storage location information about data blocks that correspond to the requested data file; retrieve locally stored data blocks; request remotely stored data blocks from the plurality of storage units (114); receive a copy of the remotely stored data blocks from the plurality of storage units (114); and return the requested data file. The invention also relates to a method for enabling actions for a distributed file system (110) to operate over a network, comprising: enabling communication between a switch (125) and a plurality of storage units (114); enabling the distributed file system (110) to include different levels of replication for different files; storing a file on at least one of the plurality of storage units (114) and a replicated copy of the file on at least one of the other storage units (114); -enabling a read request (C) for the at least one file to be provided by the switch (125) to one of the storage units (114), wherein each of the plurality of storage units (114) is operable to monitor access to the file, such that a block cache module (333) is operable to perform a scaled amount of packet read aheads, and wherein the scaled amount is based on at least a current read rate and a current latency of a link to access the file; and determining a number of copies of the file to be replicated and determining at least a portion of the plurality of storage units (114) to store each replicated copy of the file.