Directory information for managing data in network file system

Abstract

A computer network file system is described. The computer network file system includes first metadata, which is managed primarily by a first file server that is operably connected to a network fabric. The first metadata includes first file location information, and the first file location information includes at least one server id. The computer network file system also includes second metadata, which is managed primarily by a second file server that is operably connected to a network fabric. The second metadata includes second file location information, and the second file location information includes at least one server id. The first metadata and the second metadata are configured to allow a requestor to locate files that are stored by the first file server and files that are stored by the second file server in a directory structure that spans the first file server and the second file server.

1 . A computer network file system comprising: 
 a first file server operably connected to a network fabric;    means for creating files stored on the first file server or a second file server connected to the network fabric; and    means for locating files stored by the first file server and files stored by the second file server by traversing a directory structure that spans at least the first file server and the second file server.    
   
   
       2 . The computer network file system of  claim 1 , further comprising means for describing parity groups.  
   
   
       3 . The computer network file system of  claim 1 , wherein the directory structure comprises a hierarchical directory structure having a common root directory.  
   
   
       4 . The computer network file system of  claim 1 , wherein the directory structure is further configured to allow a requestor to find a location of a first file catalogued in the directory structure without prior knowledge as to a server location of the first file.  
   
   
       5 . The computer network file system of  claim 1 , further comprising file system metadata that describes at least one portion of the directory structure.  
   
   
       6 . The computer network file system of  claim 5 , wherein the at least one portion of the directory structure relates to directories stored on the first file server.  
   
   
       7 . The computer network file system of  claim 5 , wherein the file system metadata comprises at least one Gnid-string.  
   
   
       8 . The computer network file system of  claim 7 , wherein the file system metadata further comprises: 
 first file system metadata on the first file server; and    second file system metadata on the second file server.    
   
   
       9 . The computer network file system of  claim 8 , wherein the second file system metadata describes directories stored on the first file server.  
   
   
       10 . The computer network file system of  claim 1 , wherein the network fabric comprises a first Fibre channel network, and wherein the first file server communicates with one or more disk drives using a second Fibre channel network.  
   
   
       11 . A method for locating data in a computer network, the method comprising: 
 storing first files on a first file server operably connected to a network fabric;    storing second files on a second file server operably connected to the network fabric; and    locating the first files stored by the first file server and the second files stored by the second file server by traversing directory information that spans at least the first file server and the second file server.    
   
   
       12 . The method of  claim 11 , additionally comprising: 
 creating first file system metadata on the first file server; and    creating second file system metadata on the second file server.    
   
   
       13 . The method of  claim 12 , wherein the first file system metadata describes at least the first files stored by the first file server, and wherein the second file system metadata describes at least the second files stored by the second file server.  
   
   
       14 . The method of  claim 12 , wherein the first file system metadata comprises at least one Gnid-string.  
   
   
       15 . The method of  claim 14 , wherein a correspondence exists between the Gnid-string and a directory of the first file server.  
   
   
       16 . The method of  claim 11 , additionally comprising defining at least one parity group having a first parity group size, the at least one parity group comprising a parity block and one or more data blocks.  
   
   
       17 . The method of  claim 11 , wherein said locating is performed in response to a request for at least one of the first files, wherein the request does not include information as to a server location of the at least one of the first files.  
   
   
       18 . A file system for managing data in a computer network, the file system comprising: 
 first data managed primarily by a first file server operably connected to a network fabric, wherein the first data comprises at least one Gnid-string and describes at least first files and first directories stored by the first file server; and    second data managed primarily by a second file server operably connected to the network fabric, wherein the second data describes at least second files and second directories stored by the second file server, the first and second data configured to allow a requestor to locate at least one first file stored by the first server in a directory structure that spans the first server and the second server.    
   
   
       19 . The file system of  claim 18 , wherein the first data further comprises first file location information comprising a disk identifier.  
   
   
       20 . The file system of  claim 18 , wherein the directory structure is further configured to allow a requestor to find a location of the at least one first file without prior knowledge as to a server location of the at least one first file.