ACCESSING DATA IN MULTIPLE DISPERSED STORAGE NETWORKS

• US 20110289378A1
• Filed: 05/11/2011
• Published: 11/24/2011
• Est. Priority Date: 05/19/2010
• Status: Active Grant

• Current Assignee: Pure Storage, Inc.
• Original Assignee: Cleversafe Incorporated (International Business Machines Corporation)
• Inventors: Markison, Timothy W., Grube, Gary W.
• Granted Patent: US 8,683,259 B2
• Time in Patent Office: Days
• US Class Current: 714/760
• CPC Class Codes: G06F 11/1092 Rebuilding, e.g. when physically replacing a failing disk
• CPC Class Codes: G06F 11/2094 Redundant storage or storage space G06F11/2056 takes precedence
• CPC Class Codes: G06F 2211/1028 Distributed, i.e. distributed RAID systems with parity
• 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]
• CPC Class Codes: H04L 67/52 specially adapted for the location of the user terminal

Abstract

A method begins by a processing module identifying sets of dispersed storage (DS) units for each of a plurality of dispersed storage networks (DSNs) in a computing system network, wherein a set of the sets of DS unit stores an error coded data file. The method continues with the processing module identifying a reference entity within the computing system network. The method continues with the processing module determining first data access performance information between the reference entity and a first one of the sets of DS units and determining second data access performance information between the reference entity and a second one of the sets of DS units for each of the plurality of DSNs. The method continues with the processing module storing the first and second data access performance information for each of the plurality of DSNs to produce system data access performance information.

Claims

1. A method comprises:

for each of a plurality of dispersed storage networks (DSNs) in a computing system network, identifying sets of dispersed storage (DS) units, wherein a set of the sets of DS unit stores an error coded data file;

identifying a reference entity within the computing system network;

for each of the plurality of DSNs;

determining first data access performance information between the reference entity and a first one of the sets of DS units; and

determining second data access performance information between the reference entity and a second one of the sets of DS units; and

storing the first and second data access performance information for each of the plurality of DSNs to produce system data access performance information.

2. The method of claim 1 further comprises:

identifying a second reference entity within the computing system network;

for each of the plurality of DSNs;

determining third data access performance information between the second reference entity and the first one of the sets of DS units; and

determining fourth data access performance information between the second reference entity and the second one of the sets of DS units; and

storing the third and fourth data access performance information for each of the plurality of DSNs as part of the system data access performance information.

3. The method of claim 1, wherein determining the data access performance information comprises:

determining a likelihood of retrieving a decode threshold number of encoded data slices of at least a portion of the error coded data file;

determining data retrieval access latency for retrieving the decode threshold number of encoded data slices; and

generating the data access performance information based on the likelihood of retrieving the decode threshold number of encoded data slices and the data retrieval access latency.

4. The method of claim 1, wherein determining the data access performance information comprises:

determining a likelihood of storing a write threshold number of encoded data slices of the at least a portion of the error coded data file;

determining data write access latency for storing the write threshold number of encoded data slices; and

generating the data access performance information based on the likelihood of storing the write threshold number of encoded data slices and the data write access latency.

5. The method of claim 1 further comprises:

updating previous data access performance information with current data access performance information to produce the data access performance information.

6. The method of claim 1 further comprises:

outputting the data access performance information to an accessing device such that the accessing device determines specific data access performance information based on the reference entity'"'"'s data access performance information.

7. A method for use in a computing system network that includes a plurality of dispersed storage networks (DSNs), wherein each of the plurality of DSNs includes sets of dispersed storage (DS) units, and wherein a set of the sets of DS unit stores an error coded data file, the method comprises:

obtaining a reference entity'"'"'s data access performance information, wherein the reference entity'"'"'s data access performance information includes, for each of the plurality of DSNs;

first data access performance information between the reference entity and a first one of the sets of DS units; and

second data access performance information between the reference entity and a second one of the sets of DS units;

interpreting the first and second data access performance information of at least one of the plurality of DSNs to identify a desired set of DS units within one of the plurality of DSNs; and

accessing the desired set of DS units regarding the error coded data file.

8. The method of claim 7 further comprises:

determining to read the error coded data file;

identifying one or more of the plurality of DSNs that store a copy of the error coded data file; and

obtaining the reference entity'"'"'s data access performance information for the one or more of the plurality of DSNs.

9. The method of claim 7 further comprises:

determining to write the error coded data file; and

obtaining the reference entity'"'"'s data access performance information for each of the plurality of DSNs.

10. The method of claim 7, wherein the obtaining the reference entity'"'"'s data access performance information comprises at least one of:

outputting a data access performance information request message that identifies the reference entity;

receiving the reference entity'"'"'s data access performance information; and

retrieving the reference entity'"'"'s data access performance information from one of the plurality of DSNs or a publishing authority.

11. A computer comprises:

an interface;

a memory; and

a processing module operable to;

for each of a plurality of dispersed storage networks (DSNs) in a computing system network, identify sets of dispersed storage (DS) units, wherein a set of the sets of DS unit stores an error coded data file;

identify a reference entity within the computing system network;

for each of the plurality of DSNs;

determine first data access performance information between the reference entity and a first one of the sets of DS units; and

determine second data access performance information between the reference entity and a second one of the sets of DS units; and

store, in the memory, the first and second data access performance information for each of the plurality of DSNs to produce system data access performance information.

12. The computer of claim 11, wherein the processing module further functions to:

identify a second reference entity within the computing system network;

for each of the plurality of DSNs;

determine third data access performance information between the second reference entity and the first one of the sets of DS units; and

determine fourth data access performance information between the second reference entity and the second one of the sets of DS units; and

store, in the memory, the third and fourth data access performance information for each of the plurality of DSNs as part of the system data access performance information.

13. The computer of claim 11, wherein the processing module further functions to determine the data access performance information by:

determining a likelihood of retrieving a decode threshold number of encoded data slices of at least a portion of the error coded data file;

determining data retrieval access latency for retrieving the decode threshold number of encoded data slices; and

generating the data access performance information based on the likelihood of retrieving the decode threshold number of encoded data slices and the data retrieval access latency.

14. The computer of claim 11, wherein the processing module further functions to determine the data access performance information by:

determining a likelihood of storing a write threshold number of encoded data slices of the at least a portion of the error coded data file;

determining data write access latency for storing the write threshold number of encoded data slices; and

generating the data access performance information based on the likelihood of storing the write threshold number of encoded data slices and the data write access latency.

15. The computer of claim 11, wherein the processing module further functions to:

update, in the memory, previous data access performance information with current data access performance information to produce the data access performance information.

16. The computer of claim 11, wherein the processing module further functions to:

output, via the interface, the data access performance information to an accessing device such that the accessing device determines specific data access performance information based on the reference entity'"'"'s data access performance information.

17. A computing system network that includes a plurality of dispersed storage networks (DSNs), wherein each of the plurality of DSNs includes sets of dispersed storage (DS) units, and wherein a set of the sets of DS unit stores an error coded data file, a computer comprises:

an interface;

a memory; and

a processing module operable to;

obtain, via the interface, a reference entity'"'"'s data access performance information, wherein the reference entity'"'"'s data access performance information includes, for each of the plurality of DSNs;

first data access performance information between the reference entity and a first one of the sets of DS units; and

second data access performance information between the reference entity and a second one of the sets of DS units;

interpret the first and second data access performance information of at least one of the plurality of DSNs to identify a desired set of DS units within one of the plurality of DSNs; and

access, via the interface, the desired set of DS units regarding the error coded data file.

18. The computer of claim 17, wherein the processing module further functions to:

determine to read the error coded data file;

identify one or more of the plurality of DSNs that store a copy of the error coded data file; and

obtain, via the interface, the reference entity'"'"'s data access performance information for the one or more of the plurality of DSNs.

19. The computer of claim 17, wherein the processing module further functions to:

determine to write the error coded data file; and

obtain, via the interface, the reference entity'"'"'s data access performance information for each of the plurality of DSNs.

20. The computer of claim 17, wherein the processing module further functions to obtain the reference entity'"'"'s data access performance information by at least one of:

outputting, via the interface, a data access performance information request message that identifies the reference entity;

receiving, via the interface, the reference entity'"'"'s data access performance information; and

retrieving, via the interface, the reference entity'"'"'s data access performance information from one of the plurality of DSNs or a publishing authority.