FILE LOAD BALANCING IN AN N-LEVEL DIRECTORY TREE OF A DATA STORAGE SYSTEM

摘要

Implementations of the present disclosure involve a system and/or method for storing one or more data files in an n-level directory tree of a data storage system. In general, the system and/or method computes an n-byte value from a data file name which is used to create a directory path in the data storage system, where parts of the n-byte value are used to form each directory name in the directory path. Storage and retrieval of a data file is performed by storing in or retrieving data files from the computed directory. In one embodiment, the calculated n-byte value is obtained by computing the value with a cyclic redundancy check (CRC) algorithm. Use of the CRC algorithm to compute the directory path provides a balanced set of directories and number of data files that is repeatable such that location and retrieval of the data file is accomplished without the need to search through each directory of the system.

主权项

1. A data storage system comprising:
a computer-readable medium configured to store a plurality of directories and a plurality of data files; at least one input/output (I/O) port configured to receive a data file and a data file identifier; and at least one processor configured to execute one or more computer-readable instructions to perform the operations of:
receiving the data file and the data file identifier corresponding to the data file;obtaining a directory address from the file identifier by converting the file identifier into at least a one byte value; andstoring the data file in a first directory of the plurality of directories, the first directory corresponding to the directory address.