File server system providing direct data sharing between clients with a server acting as an arbiter and coordinator

• US 6,973,455 B1
• Filed: 03/03/1999
• Issued: 12/06/2005
• Est. Priority Date: 03/03/1999
• Status: Expired due to Term

• Current Assignee: Emc IP Holding Company LLC (Dell Technologies Inc.)
• Original Assignee: EMC Corporation (Dell Technologies Inc.)
• Inventors: Vahalia, Uresh K., Tzelnic, Percy
• Primary Examiner(s): Follansbee, John
• Assistant Examiner(s): Nguyen, Dustin
• Application Number:
  US09/261,621
• Time in Patent Office: 2,470 Days
• Field of Search: 707/202, 707/203, 707/1, 707/8, 707/102, 707/205, 707/103, 707/10, 709/201, 709/219, 709/223, 709/226, 711/118, 711/162, 711/152, 711/203, 714/63, 714/38, 712/28, 710/200, 718/104
• US Class Current: 1/1
• CPC Class Codes: G06F 16/1774 Locking methods, e.g. locking methods for file systems allowing shared and concurrent access to files
• CPC Class Codes: Y10S 707/99936 Pattern matching access
• CPC Class Codes: Y10S 707/99938 Concurrency, e.g. lock management in shared database

Abstract

A client is permitted to send data access commands directly to network data storage of a network file server after obtaining a lock on at least a portion of the file and obtaining metadata indicating storage locations for the data in the data storage. For example, the client sends to the file server at least one request for access to a file. In response, the file server grants a lock to the client, and returns to the client metadata of the file including information specifying data storage locations in the network data storage for storing data of the file. The client receives the metadata, and uses the metadata to produce at least one data access command for accessing the data storage locations in the network storage. The client sends the data access command to the network data storage to read or write data to the file. For a write operation, the client may modify the metadata. When the client is finished writing to the file, the client returns any modified metadata to the file server.

Claims

1. A method of operating a file server and a client in a data network, said method comprising:

(a) the client sending to the file server at least one request for access to a file;

(b) the file server receiving said at least one request for access to the file, granting to the client a lock on at least a portion of the file, and sending to the client metadata of the file including information specifying data storage locations in the file server for storing data of the file;

(c) the client receiving from the file server the metadata of the file, using the metadata of the file to produce at least one data access command for accessing the data storage locations in the file server, and sending the data access command to the file server to access the data storage locations in the file server; and

(d) the file server responding to the data access command by accessing the data storage locations in the file server;

wherein the file server includes a data storage device including the data storage locations, and a data mover computer for managing locks on files having data stored in said data storage device, and wherein the client sends to the data mover computer said at least one request for access to the file, the data mover computer responds to said at least one request for access to the file by returning to the client the metadata of the file, and wherein the client sends the data access command to the data storage device over a data transmission path that bypasses the data mover computer.

2. The method as claimed in claim 1, wherein the data storage device stores metadata of a plurality of files having file data stored in the data storage device, the data mover computer is coupled to the data storage device for transfer of the metadata between the data storage device and the data mover computer, the data mover computer has a random access memory, and the method includes the data mover computer maintaining a metadata cache in the random access memory, and the method includes the data mover computer accessing the metadata cache for obtaining the metadata that is sent to the client.

3. A file server comprising:

at least one data storage device for storing a file system; and

a data mover computer coupled to the data storage device for exchange of metadata of files in the file system, the data mover computer having at least one network port for exchange of control information and metadata of files in the file system with data processing devices in the data network, the control information including metadata requests;

wherein the data storage device has at least one network port for exchange of data with the data processing devices in the data network over at least one data path that bypasses the data mover computer; and

wherein the data mover computer is programmed for responding to each metadata request for metadata of a file from each data processing device by granting to said each data processing device a lock on at least a portion of the file, and returning to said each data processing device metadata of the file including information specifying data storage locations in the data storage device for storing data of the file.

4. The file server as claimed in claim 3, wherein the data mover computer is programmed to receive modified metadata from said each data processing device, and write the modified metadata to the data storage device.

5. The file server as claimed in claim 3, wherein the data mover computer has a random access memory, and the data mover computer is programmed for maintaining a metadata cache in the random access memory, and the data mover computer is programmed for accessing the metadata cache for obtaining the metadata that is returned to said each data processing device.

6. The file server as claimed in claim 5, wherein the data mover computer is programmed for receiving modified metadata from said each data processing device, and writing the modified metadata to the metadata cache in the random access memory.

7. The file server as claimed in claim 3, wherein the data mover computer is programmed for receiving a metadata version identifier in said each metadata request, for comparing the metadata version identifier in said each metadata request to a version identifier of a most recent version of the metadata of the file, and for returning the most recent version of the metadata of the file to said each data processing device when the comparison indicates that the metadata version identifier in said each metadata request fails to identify the most recent version of the metadata of the file.

8. The file server as claimed in claim 7, wherein the version identifier is a number, and the data mover computer is programmed to increment the version identifier when the metadata of the file is modified.

9. A data processing system comprising, in combination;

a file server; and

a plurality of clients linked by a data network to the file server;

wherein the file server is programmed for receiving from each client at least one request for access to a file, for granting to said each client a lock on at least a portion of the file, and for sending to said each client metadata of the file including information specifying data storage locations in the file server for storing data of the file;

wherein said each client is programmed for using the metadata of the file to produce at least one data access command for accessing data of the file; and

wherein the file server is programmed for receiving from said each client said at least one data access command for accessing data of the file by accessing the data storage locations in the file server;

wherein the file server includes a data storage device including the data storage locations, and a data mover computer programmed for managing locks on files having data stored in said data storage device, wherein the data mover computer has a network port for receipt of file access requests from clients, and wherein the data storage device has a network port for receipt of data access commands from said clients over at least one data transmission path that bypasses the data mover computer.

10. The data processing system as claimed in claim 9, wherein the data storage device stores metadata of a plurality of files having file data stored in the data storage device, the data mover computer is coupled to the data storage device for the transfer of the metadata between the data storage device and the data mover computer, the data mover computer has a random access memory, and the data mover computer is programmed for maintaining a metadata cache in the random access memory, and for accessing the metadata cache for obtaining the metadata that is sent to said each client.

11. A method of operating a file server and a client in a data network, the file server having a cached disk array including data storage locations, and a data mover computer for managing locks on files having data stored in the cached disk array, said method comprising:

(a) the client sending to the data mover computer at least one request for write access to a file;

(b) the data mover computer receiving said at least one request for write access to the file, granting to the client a lock on at least a portion of the file, and sending to the client metadata of the file including information specifying data storage locations in the cached disk array for storing data of the file;

(c) the client receiving from the data mover computer the metadata of the file, using the metadata of the file to produce at least one data access command for writing data to the data storage locations in the cached disk array for storing data of the file, the data access command including the data to be written to the data storage locations in the cached disk array for storing data of the file and specifying the data storage locations in the cached disk array for storing the data to be written, and sending the data access command over a data path that bypasses the data mover computer to access the data storage locations in the cached disk array for storing the data to be written;

(d) the file server responding to the data access command by writing the data to be written to the data storage locations in the cached disk array for storing the data to be written;

(e) the client modifying the metadata from the data mover computer in accordance with the writing of the data to be written to the data storage locations in the cached disk array for storing the data to be written; and

(f) the client sending the modified metadata to the data mover computer after the data has been written to the data storage locations in the cached disk array for storing the data to be written.