SMART ACCESS TO A DISPERSED DATA STORAGE NETWORK

• US 20100115063A1
• Filed: 01/07/2010
• Published: 05/06/2010
• Est. Priority Date: 10/09/2007
• Status: Active Grant

• Current Assignee: Pure Storage, Inc.
• Original Assignee: Cleversafe Incorporated (International Business Machines Corporation)
• Inventors: VOLVOVSKI, ILYA, DHUSE, GREG, GLADWIN, S. CHRISTOPHER, BELLANCA, JAMIE, THORNTON, VANCE
• Granted Patent: US 8,171,102 B2
• Time in Patent Office: Days
• US Class Current: 709/219
• CPC Class Codes: G06F 11/1076 Parity data used in redundant arrays of independent storages, e.g. in RAID systems
• CPC Class Codes: H04L 67/1001 for accessing one among a plurality of replicated servers
• CPC Class Codes: H04L 67/1008 based on parameters of servers, e.g. available memory or workload monitoring of computer activity G06F11/30
• CPC Class Codes: H04L 67/101 based on network conditions
• CPC Class Codes: H04L 67/1021 based on client or server locations
• CPC Class Codes: H04L 67/1025 Dynamic adaptation of the criteria on which the server selection is based
• 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

A method for reading data from a dispersed data storage network that includes a plurality of slice servers. The method begins by accessing a list of slice servers of the plurality of slice servers, wherein each slice server on the list stores at least one data slice associated with a data segment of the data. The method continues by transmitting read requests to at least some of the slice servers on the list. The method continues by receiving a data slice from a slice server on the list. The method continues by determining whether a threshold number of data slices has been received. The method continues, when the threshold number of data slices has been received, assembling the data segment from at least the threshold number of data slices.

Claims

1. A method for reading data from a dispersed data storage network that includes a plurality of slice servers, the method operating on at least one computer and comprising the steps of:

accessing a list of slice servers of the plurality of slice servers, wherein each slice server on the list stores at least one data slice associated with a data segment of the data;

transmitting read requests to at least some of the slice servers on the list;

receiving a data slice from a slice server on the list;

determining whether a threshold number of data slices has been received; and

when the threshold number of data slices has been received, assembling the data segment from at least the threshold number of data slices.

2. The method of claim 1, wherein the determining whether the threshold number of data slices further comprises:

for each receipt of a data slice of the threshold number of data slices, updating a received data slice count to produce an updated data slide count;

comparing the updated data slice count with the threshold number; and

when the comparing the updated data slice count with the threshold number is favorable, indicating that the threshold number of data slices has been received.

3. The method of claim 1, wherein the assembling the data segment from at least the threshold number of data slices further comprises:

data transforming each data slice of the at least the threshold number of data slices to produce data transformed data slices, wherein the data transforming includes one or more of decryption, decompression, and integrity checking.

4. The method of claim 3 further comprises:

determining whether the data transforming of each the at least the threshold number of data slices is successful;

when the data transforming of a data slice of the at least the threshold number of data slices was unsuccessful, receiving at least one more data slice from at least one more slice server on the list;

data transforming the at least one more data slice to produce at least one more data transformed data slice;

determining whether the data transforming of the at least one more data slice is successful;

when the data transforming of the at least one more data slice is successful, determining whether the at least the threshold number of data slices have been successfully data transformed; and

when the at least the threshold number of data slices have been successfully data transformed, assembling the data segment from the data transformed data slices.

5. The method of claim 1, wherein the assembling the data segment from at least the threshold number of data slices further comprises:

performing an information dispersal algorithm on the at least the threshold number of data slices to produce the data segment.

6. The method of claim 1, wherein the assembling the data segment from at least the threshold number of data slices further comprises:

for each data slice of the at least the threshold number of data slices, reading a version field to produce version data;

comparing the version data of the at least the threshold number of data slices;

when the version data of the at least the threshold number of data slices substantially match, indicating a current version of the at least the threshold number of data slices for assembling the data segment; and

when the version data for the at least the threshold number of data slices does not substantially match, receiving at least one more data slice from at least one more slice server on the list, wherein the at least one more data slice has the version data corresponding to the current version.

7. A method for reading data from a dispersed data storage network that includes a plurality of slice servers, the method operating on at least one computer and comprising the steps of:

accessing a list of slice servers of the plurality of slice servers, wherein each slice server on the list stores at least one data slice associated with a data segment of the data;

determining whether one or more of the slice servers on the list are affected by a network outage;

when one or more of the slice servers on the list are affected by the network outage, determining whether at least a threshold number of slice servers on the list is not affected by the network outage;

when the at least the threshold number of slice servers on the list is not affected by the network outage, transmitting read requests to the at least the threshold number of the slice servers on the list;

receiving a data slice from a slice server on the list;

determining whether a threshold number of data slices has been received; and

when the threshold number of data slices has been received, assembling the data segment from at least the threshold number of data slices.

8. The method of claim 7 further comprises:

when a number of slice servers on the list affected by the network outage is greater than a total number of slice servers on the list minus the threshold number of slice servers, generating a read error message.

9. The method of claim 7, wherein the determining whether the threshold number of data slices further comprises:

for each receipt of a data slice of the threshold number of data slices, updating a received data slice count to produce an updated data slide count;

comparing the updated data slice count with the threshold number; and

when the comparing the updated data slice count with the threshold number is favorable, indicating that the threshold number of data slices has been received.

10. The method of claim 7, wherein the assembling the data segment from at least the threshold number of data slices further comprises:

data transforming each data slice of the at least the threshold number of data slices to produce data transformed data slices, wherein the data transforming includes one or more of decryption, decompression, and integrity checking.

11. The method of claim 10 further comprises:

determining whether the data transforming of each the at least the threshold number of data slices is successful;

when the data transforming of a data slice of the at least the threshold number of data slices was unsuccessful, receiving at least one more data slice from at least one more slice server on the list;

data transforming the at least one more data slice to produce at least one more data transformed data slice;

determining whether the data transforming of the at least one more data slice is successful;

when the data transforming of the at least one more data slice is successful, determining whether the at least the threshold number of data slices have been successfully data transformed; and

when the at least the threshold number of data slices have been successfully data transformed, assembling the data segment from the data transformed data slices.

12. The method of claim 7, wherein the assembling the data segment from at least the threshold number of data slices further comprises:

performing an information dispersal algorithm on the at least the threshold number of data slices to produce the data segment.

13. The method of claim 7, wherein the assembling the data segment from at least the threshold number of data slices further comprises:

for each data slice of the at least the threshold number of data slices, reading a version field to produce version data;

comparing the version data of the at least the threshold number of data slices;

when the version data of the at least the threshold number of data slices substantially match, indicating a current version of the at least the threshold number of data slices for assembling the data segment; and

when the version data for the at least the threshold number of data slices does not substantially match, receiving at least one more data slice from at least one more slice server on the list, wherein the at least one more data slice has the version data corresponding to the current version.

14. A computer for use with a dispersed data storage network, the computer comprising:

a network port coupled to a data network, wherein the data network is coupled to a plurality of slice servers for storing and retrieving a plurality of data slices; and

a central processing unit operable to;

access a list of slice servers of the plurality of slice servers, wherein each slice server on the list stores at least one data slice associated with a data segment of the data;

transmit read requests to at least some of the slice servers on the list;

receive a data slice from a slice server on the list;

determine whether a threshold number of data slices has been received; and

when the threshold number of data slices has been received, assemble the data segment from at least the threshold number of data slices.

15. The computer of claim 14, wherein the central processing unit further functions to determine whether the threshold number of data slices by:

for each receipt of a data slice of the threshold number of data slices, updating a received data slice count to produce an updated data slide count;

comparing the updated data slice count with the threshold number; and

when the comparing the updated data slice count with the threshold number is favorable, indicating that the threshold number of data slices has been received.

16. The computer of claim 14, wherein the central processing unit further functions to assemble the data segment from at least the threshold number of data slices by:

data transforming each data slice of the at least the threshold number of data slices to produce data transformed data slices, wherein the data transforming includes one or more of decryption, decompression, and integrity checking.

17. The computer of claim 16, wherein the central processing unit further functions to:

determining whether the data transforming of each the at least the threshold number of data slices is successful;

when the data transforming of a data slice of the at least the threshold number of data slices was unsuccessful, receiving at least one more data slice from at least one more slice server on the list;

data transforming the at least one more data slice to produce at least one more data transformed data slice;

determining whether the data transforming of the at least one more data slice is successful;

when the data transforming of the at least one more data slice is successful, determining whether the at least the threshold number of data slices have been successfully data transformed; and

when the at least the threshold number of data slices have been successfully data transformed, assembling the data segment from the data transformed data slices.

18. The computer of claim 14, wherein the central processing unit further functions to assemble the data segment from at least the threshold number of data slices by:

performing an information dispersal algorithm on the at least the threshold number of data slices to produce the data segment.

19. The computer of claim 14, wherein the central processing unit further functions to assemble the data segment from at least the threshold number of data slices by:

for each data slice of the at least the threshold number of data slices, reading a version field to produce version data;

comparing the version data of the at least the threshold number of data slices;

when the version data of the at least the threshold number of data slices substantially match, indicating a current version of the at least the threshold number of data slices for assembling the data segment; and

when the version data for the at least the threshold number of data slices does not substantially match, receiving at least one more data slice from at least one more slice server on the list, wherein the at least one more data slice has the version data corresponding to the current version.

20. A computer for use with a dispersed data storage network, the computer comprising:

a network port coupled to a data network, wherein the data network is coupled to a plurality of slice servers for storing and retrieving a plurality of data slices; and

a central processing unit operable to;

access a list of slice servers of the plurality of slice servers, wherein each slice server on the list stores at least one data slice associated with a data segment of the data;

determine whether one or more of the slice servers on the list are affected by a network outage;

when one or more of the slice servers on the list are affected by the network outage, determine whether at least a threshold number of slice servers on the list is not affected by the network outage;

when the at least the threshold number of slice servers on the list is not affected by the network outage, transmit read requests to the at least the threshold number of the slice servers on the list;

receive a data slice from a slice server on the list;

determine whether a threshold number of data slices has been received; and

when the threshold number of data slices has been received, assemble the data segment from at least the threshold number of data slices.

21. The computer of claim 20, wherein the central processing unit further functions to:

when a number of slice servers on the list affected by the network outage is greater than a total number of slice servers on the list minus the threshold number of slice servers, generate a read error message.

22. The computer of claim 20, wherein the central processing unit further functions to determine whether the threshold number of data slices by:

for each receipt of a data slice of the threshold number of data slices, updating a received data slice count to produce an updated data slide count;

comparing the updated data slice count with the threshold number; and

when the comparing the updated data slice count with the threshold number is favorable, indicating that the threshold number of data slices has been received.

23. The computer of claim 20, wherein the central processing unit further functions to assemble the data segment from at least the threshold number of data slices by:

data transforming each data slice of the at least the threshold number of data slices to produce data transformed data slices, wherein the data transforming includes one or more of decryption, decompression, and integrity checking.

24. The computer of claim 20, wherein the central processing unit further functions to:

determining whether the data transforming of each the at least the threshold number of data slices is successful;

when the data transforming of a data slice of the at least the threshold number of data slices was unsuccessful, receiving at least one more data slice from at least one more slice server on the list;

data transforming the at least one more data slice to produce at least one more data transformed data slice;

determining whether the data transforming of the at least one more data slice is successful;

when the data transforming of the at least one more data slice is successful, determining whether the at least the threshold number of data slices have been successfully data transformed; and

when the at least the threshold number of data slices have been successfully data transformed, assembling the data segment from the data transformed data slices.

25. The computer of claim 20, wherein the central processing unit further functions to assemble the data segment from at least the threshold number of data slices by:

performing an information dispersal algorithm on the at least the threshold number of data slices to produce the data segment.

26. The computer of claim 20, wherein the central processing unit further functions to assemble the data segment from at least the threshold number of data slices by:

for each data slice of the at least the threshold number of data slices, reading a version field to produce version data;

comparing the version data of the at least the threshold number of data slices;

when the version data of the at least the threshold number of data slices substantially match, indicating a current version of the at least the threshold number of data slices for assembling the data segment; and

when the version data for the at least the threshold number of data slices does not substantially match, receiving at least one more data slice from at least one more slice server on the list, wherein the at least one more data slice has the version data corresponding to the current version.