Integrated distributed file system with variable parity groups

A method for storing data in a computer network, comprising:

• loading a first portion of file system metadata on a first file server operably connected to a network fabric;
• loading a second portion of file system metadata on a second file server connected to said network fabric, said file system metadata comprising information to allow finding a desired file in a directory structure that aggregates at least a portion of one or more files stored by said first file server or said second file server;
• organizing data in a first file stored on said first file server into at least one distributed parity group, said at least one distributed parity group comprising one or more data blocks and a parity block;
• storing each of said data blocks of said at least one distributed parity group on a different disk drive;
• storing said parity block of said at least one distributed parity group on a disk drive different from the disk drives used to store said data blocks of said at least one distributed parity group;
• and
• updating said first portion of said file system metadata to specify storage locations of each of said data blocks of said at least one distributed parity group and a storage location of said parity block of said at least one distributed parity group.

A computer network file system, comprising:

• a first file server operably connected to a network fabric;
• a second file server operably connected to the network fabric;
• means for locating a distributed parity group of a file stored by said first file server and files stored by said second file server by traversing a directory structure that spans at least a said first file server and said second file server.
• means for a computing parity block for said distributed parity group and for storing said distributed parity group and said parity block.