Integrated client for use with a dispersed data storage network

• US 8,965,956 B2
• Filed: 12/29/2009
• Issued: 02/24/2015
• Est. Priority Date: 10/09/2007
• Status: Expired due to Fees

• Current Assignee: Pure Storage, Inc.
• Original Assignee: Cleversafe Incorporated (International Business Machines Corporation)
• Inventors: Palthepu, Srinivas, Thornton, Vance T., Young, Jesse Louis, Quigley, John, Baptist, Andrew, Dhuse, Greg
• Primary Examiner(s): Tiv, Backhean
• Application Number:
  US12/649,099
• Publication Number:
  US 20100217796A1
• Time in Patent Office: 1,883 Days
• Field of Search: 709/203, 709/214, 709/217, 709/246
• US Class Current: 709/203
• CPC Class Codes: G06F 16/182 Distributed file systems
• CPC Class Codes: H04L 67/1097 for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]

Abstract

An integrated client computer for accessing a dispersed data storage network is disclosed. A client program operating on the client computer accepts commands from a user and in response, issues network messages to a plurality of slice servers implementing a dispersed data storage network. Data slices can be read, written or modified using the disclosed integrated client computer.

Claims

1. A method for execution by a computer to access a file in a dispersed storage network (DSN), the method comprises:

receiving a read request to read data;

retrieving, in response to the read request, at least a minimum number of root directory slices from the DSN, wherein a root directory was encoded using an information dispersal algorithm to produce a plurality of root directory slices that is stored in the DSN and wherein the minimum number of root directory slices is less than the plurality of root directory slices;

applying the information dispersal algorithm on at least the minimum number of root directory slices to reconstruct the root directory;

identifying one or more intervening directories including a home directory of the data, from the reconstructed root directory based on the read request;

retrieving a minimum number of intervening directory slices from the one or more intervening directories from the DSN, wherein the one or more intervening directories was encoded using the information dispersal algorithm to produce a plurality of intervening directory slices that is stored in the DSN and wherein the minimum number of intervening directory slices is less than the plurality of intervening directory slices;

applying the information dispersal algorithm on the minimum number of intervening directory slices to reconstruct the one or more intervening directories;

identifying the home directory from the reconstructed one or more intervening directories;

identifying file object metadata from the home directory, wherein the file object metadata identifies data slices and wherein the data is encoded using the information dispersal algorithm to produce the data slices;

issuing commands to retrieve at least a minimum number of data slices to reconstruct the data; and

when at least the minimum number of data slices have been received, applying the information dispersal algorithm on at least the minimum number of data slices to reconstruct the data.

2. The method of claim 1 further comprises:

prior to retrieving at least the minimum number of root directory slices, determining whether the root directory is stored in cache memory of the computer; and

when the root directory is stored in the cache memory, accessing the root directory from the cache memory.

3. The method of claim 1, wherein the retrieving at least the minimum number of root directory slices comprises:

accessing root metadata associated with the root directory, wherein the root metadata includes information regarding DSN addressing of at least the minimum number of root directory slices.

4. The method of claim 1 further comprises:

determining a vault in which the data is stored based on a data source identifier of the data that includes a data source root identifier of the vault, wherein the data source identifier for the root directory is fixed within the vault; and

identifying DSN addressing of at least the minimum number of root directory slices based on the data source root directory.

5. The method of claim 1, wherein the identifying the one or more intervening directories comprises:

accessing directory metadata associated with the one or more intervening directories, wherein the directory metadata includes DSN addressing information regarding the one or more intervening directories.

6. The method of claim 1, wherein the identifying the one or more intervening directories comprises:

determining whether the one or more intervening directories is stored in cache memory of the computer;

when the one or more intervening directories is not stored in the cache memory, loading the one or more intervening directories into the cache memory; and

when the one or more intervening directories is stored in the cache memory, accessing the one or more intervening directories from the cache memory.

7. A computer comprising:

a network port adaptively coupled to a network in communication with slice servers of a distributed storage network (DSN); and

a client program operating on said computer, said client program adapted to;

receive, via the network port, a read request to read data;

retrieve, in response to the read request and via the network port, at least a minimum number of root directory slices from the DSN, wherein a root directory was encoded using an information dispersal algorithm to produce a plurality of root directory slices that is stored in the DSN and wherein the minimum number of root directory slices is less than the plurality of root directory slices;

apply the information dispersal algorithm on at least the minimum number of root directory slices to reconstruct a root directory;

identify one or more intervening directories including a home directory of the data from the reconstructed root directory based on the read request;

retrieve, via the network port, a minimum number of intervening directory slices from the DSN, wherein the one or more intervening directories was encoded using the information dispersal algorithm to produce a plurality of intervening directory slices that is stored in the DSN and wherein the minimum number of intervening directory slices is less than the plurality of intervening directory slices;

apply the information dispersal algorithm on the minimum number of intervening directory slices to reconstruct the intervening directory;

identify file object metadata from the home directory, wherein the file object metadata identifies data slices and wherein the data is encoded using an information dispersal algorithm to produce the data slices;

issue, via the network port, commands to retrieve at least a minimum number of data slices to reconstruct the data; and

when at least the minimum number of data slices have been received, applying the information dispersal algorithm on at least the minimum number of data slices to reconstruct the data.

8. The computer of claim 7 wherein the client program is further adapted to:

prior to retrieving at least the minimum number of root directory slices, determining whether the root directory is stored in cache memory of the computer; and

when the root directory is stored in the cache memory, accessing the root directory from the cache memory.

9. The computer of claim 7 wherein the client program is further adapted to:

access root metadata associated with the root directory, wherein the root metadata includes information regarding DSN addressing of the at least a minimum number of root directory slices.

10. The computer of claim 7 wherein the client program is further adapted to:

determine a vault in which the data of the file is stored based on a data source identifier of the data that includes a data source root identifier of the vault; and

identify DSN addressing of the at least a minimum number of root directory slices based on the data source root directory.

11. The computer of claim 7 wherein the client program is further adapted to:

access directory metadata associated with the one or more intervening directories, wherein the directory metadata includes information regarding the one or more intervening directories.

12. The computer of claim 7 wherein the client program is further adapted to identify the intervening directory by:

determining whether the one or more intervening directories is stored in cache memory of the computer;

when the one or more intervening directories is not stored in the cache memory, loading the one or more intervening directories into the cache memory; and

when the one or more intervening directories is stored in the cache memory, accessing the one or more intervening directories from the cache memory.