Adjusting dispersed storage error encoding parameters

• US 9,176,822 B2
• Filed: 07/17/2013
• Issued: 11/03/2015
• Est. Priority Date: 08/31/2012
• Status: Active Grant

• Current Assignee: Pure Storage, Inc.
• Original Assignee: Cleversafe Incorporated (International Business Machines Corporation)
• Inventors: Vedpathak, Yogesh Ramesh, Rouzbeh, Ramin, Resch, Jason K.
• Primary Examiner(s): KUDIRKA, JOSEPH R
• Application Number:
  US13/944,342
• Publication Number:
  US 20140068320A1
• Time in Patent Office: 839 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 11/0712 in a virtual computing platform, e.g. logically partitioned systems
• CPC Class Codes: G06F 11/0784 Routing of error reports, e.g. with a specific transmission path or data flow
• CPC Class Codes: G06F 11/0787 Storage of error reports, e.g. persistent data storage, storage using memory protection
• CPC Class Codes: G06F 11/1004 to protect a block of data words, e.g. CRC or checksum G06F11/1076 takes precedence; security arrangements for protecting computers or computer systems against unauthorized activity G06F21/00
• CPC Class Codes: G06F 11/1044 with specific ECC/EDC distribution
• CPC Class Codes: G06F 11/1076 Parity data used in redundant arrays of independent storages, e.g. in RAID systems
• CPC Class Codes: G06F 11/1092 Rebuilding, e.g. when physically replacing a failing disk
• CPC Class Codes: G06F 11/142 Reconfiguring to eliminate the error group management mechanisms in a peer-to-peer network H04L67/1044
• CPC Class Codes: G06F 11/2094 Redundant storage or storage space G06F11/2056 takes precedence
• CPC Class Codes: G06F 21/10 Protecting distributed programs or content, e.g. vending or licensing of copyrighted material protection in video systems or pay television H04N7/16 ; Digital rights management [DRM]
• CPC Class Codes: G06F 21/60 Protecting data
• CPC Class Codes: G06F 21/6272 by registering files or documents with a third party
• CPC Class Codes: H03M 13/611 Specific encoding aspects, e.g. encoding by means of decoding
• CPC Class Codes: H03M 13/616 Matrix operations, especially for generator matrices or check matrices, e.g. column or row permutations
• CPC Class Codes: H04L 2209/34 Encoding or coding, e.g. Huffman coding or error correction
• 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 9/0861 Generation of secret information including derivation or calculation of cryptographic keys or passwords
• CPC Class Codes: H04L 9/0894 Escrow, recovery or storing of secret information, e.g. secret key escrow or cryptographic key storage

Abstract

A method begins by a processing module receiving a large data file for storage in a dispersed storage network (DSN) and determining initial dispersed storage error encoding parameters. The method continues with the processing module encoding, during a first time interval of receiving the large data file, first data segments of the large data file using the initial dispersed storage error encoding parameters to produce a first plurality of sets of encoded data slices. The method continues with the processing module writing the first plurality of sets of encoded data slices to the DSN and monitoring processing of the writing to produce first write processing performance information. When the first write processing performance information compares unfavorably to a desired write performance range, the method continues with the processing module adjusting, for a second time interval, the initial dispersed storage error encoding parameters to produce adjusted dispersed storage error encoding parameters.

Claims

1. A method for execution by one or more processing modules of one or more computing devices, the method comprising:

receiving, over time, a large data file for storage in a dispersed storage network (DSN);

determining initial dispersed storage error encoding parameters for storing the large data file, wherein the initial dispersed storage error encoding parameters indicate an error coding number and a decode threshold number, wherein the error coding number indicates a number of encoded data slices that results when a data segment of the large data file is encoded using a dispersed storage error encoding function, and the decode threshold number indicates a minimum number of the encoded data slices that are needed to recover the data segment;

encoding, using the dispersed storage error encoding function and during a first time interval of receiving the large data file, a first plurality of data segments of a first portion of the large data file using the initial dispersed storage error encoding parameters to produce a first plurality of sets of encoded data slices;

writing, during the first time interval, the first plurality of sets of encoded data slices to storage units of the DSN;

monitoring processing of the writing of the first plurality of sets of encoded data slices to produce first write processing performance information; and

when the first write processing performance information compares unfavorably to a desired write performance range, adjusting, for a second time interval of receiving the large data file, at least one of the error coding number and the decode threshold number to produce adjusted dispersed storage error encoding parameters.

2. The method of claim 1 further comprising:

writing the first plurality of sets of encoded data slices by;

for each group of a plurality of groups of encoded data slices of the first plurality of sets of encoded data slices, wherein a group of the plurality of groups of encoded data slices includes one or more sets of encoded data slices of the first plurality of sets of encoded data slices;

generating a set of write requests;

sending the set of write requests to the storage units; and

receiving write acknowledgements from at least some of the storage units; and

the monitoring the processing of the writing including;

monitoring the write acknowledgements to determine one or more of;

a number of storage units sending a write acknowledgment, response time for the at least some of the storage units sending the write acknowledgements, resending of a write request to one or more storage units, a write acknowledgement indicating a storage failure, and storage performance information embedded in the write acknowledgement; and

interpreting the monitoring to create the first write processing performance information.

3. The method of claim 1 further comprising:

obtaining storage performance history data regarding the storage units; and

including the storage performance history data in the first write processing performance information.

4. The method of claim 1 further comprising:

determining that the first write processing performance information compares unfavorably to the desired write performance range by one or more of;

when a number of storage units acknowledging storage of encoded data slices of at least some of the first plurality of sets of encoded data slices is at or below a minimum desired storage response number;

when the number of storage units acknowledging storage of encoded data slices of at least some of the first plurality of sets of encoded data slices is at or above a maximum desired storage response number;

when response time for at least some of the storage units acknowledging storage of the at least some of the first plurality of sets of encoded data slices is at or below a minimum desired response time;

when the response time for the at least some of the storage units acknowledging storage of the at least some of the first plurality of sets of encoded data slices is at or above a maximum desired response time;

when at least an acceptable maximum resend tolerance number of resend write requests is received from one or more of the storage units;

when less than a minimum resend tolerance number of resend write requests is received from the storage units;

when at least an acceptable maximum failure tolerance number of storage failure messages is received from the one or more of the storage units;

when less than a minimum failure tolerance number of storage failure messages is received from the storage units;

when write response messages from the one or more of the storage units include storage performance information indicative of at least one of declined storage performance and declined storage reliability; and

when the write response messages from the one or more of the storage units include storage performance information indicative of at least one of increased storage performance and increased storage reliability.

5. The method of claim 1, wherein the adjusting the at least one of the error coding number and the decode threshold number comprises one of:

increasing the error coding number and maintaining the decode threshold number when the unfavorable comparison of the first write processing performance information with the desired write performance range indicates a declined storage performance;

decreasing the error coding number and maintaining the decode threshold number when the unfavorable comparison of the first write processing performance information with the desired write performance range indicates an increased storage performance; and

increasing the error coding number and increasing the decode threshold number when the unfavorable comparison of the first write processing performance information with the desired write performance range indicates a declined storage reliability.

6. The method of claim 1 further comprising:

encoding, using the dispersed storage error encoding function and during the second time interval, a second plurality of data segments of a second portion of the large data file using the adjusted dispersed storage error encoding parameters to produce a second plurality of sets of encoded data slices;

writing, during the second time interval, the second plurality of sets of encoded data slices to the storage units of the DSN;

monitoring processing of the writing of the second plurality of sets of encoded data slices to produce second write processing performance information; and

when the second write processing performance information compares unfavorably to the desired write performance range, adjusting, for a third time interval of receiving the large data file, the adjusted dispersed storage error encoding parameters to produce readjusted dispersed storage error encoding parameters.

7. The method of claim 1 further comprising:

when the large data file is stored, determining whether to normalize the first and adjusted dispersed storage error encoding parameters;

when the first and adjusted dispersed storage error encoding parameters are to be normalized, normalizing the first and adjusted dispersed storage error encoding parameters to produce normalized dispersed storage error encoding parameters; and

updating dispersed storage error encoding storage of the large data file in accordance with the normalized dispersed storage error encoding parameters.

8. The method of claim 1 further comprising:

after the large data file is stored as multiple pluralities of sets of encoded data slices, wherein at least two of the pluralities of sets of encoded data slices were encoded using different dispersed storage error encoding parameters, reading at least a portion of the large data file from the storage units;

monitoring read performance of the reading of at least some of the multiple pluralities of sets of encoded data slices to produce read processing performance information;

when the read processing performance information compares unfavorably to a desired read performance range, determining whether to adjust the dispersed storage error encoding parameters for at least one of the multiple pluralities of sets of encoded data slices; and

when the dispersed storage error encoding parameters for the at least one of the multiple pluralities of sets of encoded data slices are to be adjusted;

adjusting the dispersed storage error encoding parameters for the at least one of the multiple pluralities of sets of encoded data slices to produce read-based adjusted dispersed storage error encoding parameters; and

updating storage of the at least one of the multiple pluralities of sets of encoded data slices in accordance with the read-based adjusted dispersed storage error encoding parameters.

9. The method of claim 8, wherein the monitoring the read performance comprises:

monitoring read responses to determine one or more of;

a number of storage units sending a read response, read response time for the at least some of the storage units sending the read responses, resending of a read request to one or more storage units, a read response indicating a storage failure, and read performance information embedded in the read response; and

interpreting the monitoring to create the read processing performance information.

10. The method of claim 8, wherein the updating storage comprises one of:

when the read-based adjusted dispersed storage error encoding parameters include a decreased error coding number, deleting one or more redundancy encoded data slices from each set of encoded data slices of the at least one of the multiple pluralities of sets of encoded data slices;

when the read-based adjusted dispersed storage error encoding parameters include an increased error coding number, creating, in accordance with the dispersed storage error encoding function, one or more new redundancy encoded data slices for each set of encoded data slices of the at least one of the multiple pluralities of sets of encoded data slices; and

when the read-based adjusted dispersed storage error encoding parameters include a changed error coding number and a changed decode threshold number, re-encoding a plurality of data segments for each of the at least one of the multiple pluralities of sets of encoded data slices using the dispersed storage error encoding function in accordance with the read-based adjusted dispersed storage error encoding parameters to produce a plurality of sets of re-encoded data slices.

11. The method of claim 1 further comprising:

establishing a beginning of the second time interval to correspond to when the first write processing performance information compares unfavorably to the desired write performance range.

12. A dispersed storage (DS) module comprising:

an ingesting module, when operable within a computing device, causing the computing device to;

receive, over time, a large data file for storage in a dispersed storage network (DSN); and

determine initial dispersed storage error encoding parameters for storing the large data file, wherein the initial dispersed storage error encoding parameters indicate an error coding number and a decode threshold number, wherein the error coding number indicates a number of encoded data slices that results when a data segment of the large data file is encoded using a dispersed storage error encoding function, and the decode threshold number indicates a minimum number of the encoded data slices that are needed to recover the data segment;

a storing module, when operable within the computing device, causing the computing device to;

encode, using the dispersed storage error encoding function and during a first time interval of receiving the large data file, a first plurality of data segments of a first portion of the large data file using the initial dispersed storage error encoding parameters to produce a first plurality of sets of encoded data slices; and

write, during the first time interval, the first plurality of sets of encoded data slices to storage units of the DSN; and

an adjusting module, when operable within the computing device, causing the computing device to;

monitor processing of the writing of the first plurality of sets of encoded data slices to produce first write processing performance information; and

when the first write processing performance information compares unfavorably to a desired write performance range, adjust, for a second time interval of receiving the large data file, at least one of the error coding number and the decode threshold number to produce adjusted dispersed storage error encoding parameters.

13. The DS module of claim 12 further comprising:

the storing module functions to write the first plurality of sets of encoded data slices by;

for each group of a plurality of groups of encoded data slices of the first plurality of sets of encoded data slices, wherein a group of the plurality of groups of encoded data slices includes one or more sets of encoded data slices of the first plurality of sets of encoded data slices;

generating a set of write requests;

sending the set of write requests to the storage units; and

receiving write acknowledgements from at least some of the storage units; and

the adjusting module functions to monitor the processing of the writing by;

monitoring the write acknowledgements to determine one or more of;

a number of storage units sending a write acknowledgment, response time for the at least some of the storage units sending the write acknowledgements, resending of a write request to one or more storage units, a write acknowledgement indicating a storage failure, and storage performance information embedded in the write acknowledgement; and

interpreting the monitoring to create the first write processing performance information.

14. The DS module of claim 12 further comprising:

the adjusting module further functions to;

obtain storage performance history data regarding the storage units; and

include the storage performance history data in the first write processing performance information.

15. The DS module of claim 12 further comprising:

the adjusting module further functions to determine that the first write processing performance information compares unfavorably to the desired write performance range by one or more of;

when a number of storage units acknowledging storage of encoded data slices of at least some of the first plurality of sets of encoded data slices is at or below a minimum desired storage response number;

when the number of storage units acknowledging storage of encoded data slices of at least some of the first plurality of sets of encoded data slices is at or above a maximum desired storage response number;

when response time for at least some of the storage units acknowledging storage of the at least some of the first plurality of sets of encoded data slices is at or below a minimum desired response time;

when the response time for the at least some of the storage units acknowledging storage of the at least some of the first plurality of sets of encoded data slices is at or above a maximum desired response time;

when at least an acceptable maximum resend tolerance number of resend write requests is received from one or more of the storage units;

when less than a minimum resend tolerance number of resend write requests is received from the storage units;

when at least an acceptable maximum failure tolerance number of storage failure messages is received from the one or more of the storage units;

when less than a minimum failure tolerance number of storage failure messages is received from the storage units;

when write response messages from the one or more of the storage units include storage performance information indicative of at least one of declined storage performance and declined storage reliability; and

when the write response messages from the one or more of the storage units include storage performance information indicative of at least one of increased storage performance and increased storage reliability.

16. The DS module of claim 12, wherein the adjusting module functions to adjust the at least one of the error coding number and the decode threshold number by one of:

increasing the error coding number and maintaining the decode threshold number when the unfavorable comparison of the first write processing performance information with the desired write performance range indicates a declined storage performance;

decreasing the error coding number and maintaining the decode threshold number when the unfavorable comparison of the first write processing performance information with the desired write performance range indicates an increased storage performance; and

increasing the error coding number and increasing the decode threshold number when the unfavorable comparison of the first write processing performance information with the desired write performance range indicates a declined storage reliability.

17. The DS module of claim 12 further comprising:

the storing module further functions to;

encode, using the dispersed storage error encoding function and during the second time interval, a second plurality of data segments of a second portion of the large data file using the adjusted dispersed storage error encoding parameters to produce a second plurality of sets of encoded data slices; and

write, during the second time interval, the second plurality of sets of encoded data slices to the storage units of the DSN; and

the adjusting module further functions to;

monitor processing of the writing of the second plurality of sets of encoded data slices to produce second write processing performance information; and

when the second write processing performance information compares unfavorably to the desired write performance range, adjust, for a third time interval of receiving the large data file, the adjusted dispersed storage error encoding parameters to produce readjusted dispersed storage error encoding parameters.

18. The DS module of claim 12 further comprising:

the adjusting module further functions to;

when the large data file is stored, determine whether to normalize the first and adjusted dispersed storage error encoding parameters;

when the first and adjusted dispersed storage error encoding parameters are to be normalized, normalize the first and adjusted dispersed storage error encoding parameters to produce normalized dispersed storage error encoding parameters; and

update dispersed storage error encoding storage of the large data file in accordance with the normalized dispersed storage error encoding parameters.

19. The DS module of claim 12 further comprising:

a reading module, when operable within the computing device, causing the computing device to;

after the large data file is stored as multiple pluralities of sets of encoded data slices, wherein at least two of the pluralities of sets of encoded data slices were encoded using different dispersed storage error encoding parameters, read at least a portion of the large data file from the storage units;

monitor read performance of the reading of at least some of the multiple pluralities of sets of encoded data slices to produce read processing performance information;

when the read processing performance information compares unfavorably to a desired read performance range, determine whether to adjust the dispersed storage error encoding parameters for at least one of the multiple pluralities of sets of encoded data slices; and

when the dispersed storage error encoding parameters for the at least one of the multiple pluralities of sets of encoded data slices are to be adjusted;

adjust the dispersed storage error encoding parameters for the at least one of the multiple pluralities of sets of encoded data slices to produce read-based adjusted dispersed storage error encoding parameters; and

update storage of the at least one of the multiple pluralities of sets of encoded data slices in accordance with the read-based adjusted dispersed storage error encoding parameters.

20. The DS module of claim 19, wherein the reading module functions to monitor the read performance by:

monitoring read responses to determine one or more of;

a number of storage units sending a read response, read response time for the at least some of the storage units sending the read responses, resending of a read request to one or more storage units, a read response indicating a storage failure, and read performance information embedded in the read response; and

interpreting the monitoring to create the read processing performance information.

21. The DS module of claim 19, wherein the reading module functions to update storage by one of:

when the read-based adjusted dispersed storage error encoding parameters include a decreased error coding number, deleting one or more redundancy encoded data slices from each set of encoded data slices of the at least one of the multiple pluralities of sets of encoded data slices;

when the read-based adjusted dispersed storage error encoding parameters include an increased error coding number, creating, in accordance with the dispersed storage error encoding function, one or more new redundancy encoded data slices for each set of encoded data slices of the at least one of the multiple pluralities of sets of encoded data slices; and

when the read-based adjusted dispersed storage error encoding parameters include a changed error coding number and a changed decode threshold number, re-encoding a plurality of data segments for each of the at least one of the multiple pluralities of sets of encoded data slices using the dispersed storage error encoding function in accordance with the read-based adjusted dispersed storage error encoding parameters to produce a plurality of sets of re-encoded data slices.

22. The DS module of claim 12 further comprising:

the adjusting module further functions to establish a beginning of the second time interval to correspond to when the first write processing performance information compares unfavorably to the desired write performance range.