Distributed storage network data revision control

• US 10,142,115 B2
• Filed: 07/16/2010
• Issued: 11/27/2018
• Est. Priority Date: 03/31/2008
• Status: Active Grant

• Current Assignee: Pure Storage, Inc.
• Original Assignee: International Business Machines Corporation
• Inventors: Resch, Jason K., Dhuse, Greg, Volvovski, Ilya, Baptist, Andrew
• Primary Examiner(s): Shaw, Yin Chen
• Assistant Examiner(s): Amorin, Carlos E
• Application Number:
  US12/837,961
• Publication Number:
  US 20110107113A1
• Time in Patent Office: 3,056 Days
• CPC Class Codes: G06F 11/1076 Parity data used in redundant arrays of independent storages, e.g. in RAID systems
• CPC Class Codes: G06F 11/1469 Backup restoration techniques
• CPC Class Codes: G06F 2211/1028 Distributed, i.e. distributed RAID systems with parity
• CPC Class Codes: H04L 12/00 Data switching networks interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units G06F13/00
• 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 9/3247 involving digital signatures

Abstract

Multiple revisions of an encoded data slice are generated, with each revision having the same slice name. Each of the data slices represents the same original data portion, but each is encoded so that no single data slice can be used to reconstruct the original data portion. Appropriate revision numbers are associated with each encoded data slice, and the encoded data slices and associated revision numbers are transmitted for storage in selected storage units of a distributed storage network. If write confirmations are received from at least a write threshold number of storage units, a commit command is transmitted so that the most recently written data slices will be available for access. After a commit command is issued, a current directory used to access the encoded data slices can be sliced, encoded, and stored in the same way as the data slices.

Claims

1. A method for execution by a computing device that includes a computing core, the method comprising:

encoding a first data segment using an error coding dispersal storage function to produce a first set of encoded data slices;

determining a first revision number regarding a version of the first data segment;

associating the first revision number to each encoded data slice of the first set of encoded data slices to produce a first set of appended encoded data slices;

transmitting, by the computing device via an output interface, write commands regarding the first set of appended encoded data slices to storage units of a distributed storage network (DSN), wherein the write commands include the first set of appended encoded data slices for storage in the storage units;

receiving write confirmation messages from at least some of the storage units;

verifying the first revision number within the write confirmation messages;

when a write threshold number of write confirmation messages have been received and the first revision number has been verified within each of the write threshold number of write confirmation messages, sending write commit messages to the storage units; and

slicing, encoding and storing a current directory used to access the encoded data slices in the same way as the first data segment.

2. The method of claim 1, wherein the first revision number is appended to each encoded data slice of the first set of encoded data slices.

3. The method of claim 1 further comprising:

determining whether write commit responses have been received from at least some of the storage units, wherein a write commit response indicates that a storage unit has made a corresponding encoded data slice visible.

4. The method of claim 1 further comprising:

when the write confirmations for the at least the write threshold number of each of the first set of appended encoded data slices have not been received, retransmitting at least some of the write commands to different storage units.

5. The method of claim 1, further comprising:

determining the first revision numbers based on at least one of a timestamp, a random number, a user vault identifier, a user identifier, a data object identifier, a hash of the first data segment, and a hash of a data segment identifier.

6. A method for execution by a computing device that includes a computing core, the method comprising:

retrieving, via an input interface of the computing device, a first set of appended encoded data slices from storage units of a distributed storage network (DSN);

processing, by the computing device, the first set of appended encoded data slices to produce a set of first revision numbers and a first set of encoded data slices;

comparing the set of first revisions numbers; and

when each of the first revision numbers of the set of first revision numbers has the same value and the first set of appended encoded data slices includes a read threshold number of appended encoded data slices, decoding, by the computing device, the first set of encoded data slices using an error coding dispersal storage function to reconstruct a first data segment.

7. The method of claim 6, further comprising:

when each of the first revision numbers of the set of first revision numbers does not include the same number, retrieving an encoded data slice of a plurality of encoded data slices from another storage unit, wherein the first data segment was encoded into the plurality of encoded data slices and a threshold number of encoded data slices is required to reproduce the first data segment.

8. The method of claim 6, further comprising:

the first set of encoded data slices including a threshold number of encoded data slices of a plurality of encoded data slices, wherein the first data segment was encoded into the plurality of encoded data slices, wherein the threshold number of encoded data slices is required to reproduce the first data segment.

9. A distributed storage computing device comprising:

an interface;

memory; and

a processing system, including a processor and operably coupled to the interface and to the memory, wherein the processing system is operable to;

encode a first data segment using an error coding dispersal storage function to produce a first set of encoded data slices;

determine a first revision number regarding a version of the first data segment;

associate the first revision number to each encoded data slice[H] of the first set of encoded data slices to produce a first set of appended encoded data slices;

transmit, via the interface, write commands regarding the first set of appended encoded data slices to storage units of a distributed storage network (DSN);

receive write confirmation messages from at least some of the storage units;

verify the first revision number within the write confirmation messages;

when a write threshold number of write confirmation messages have been received and the first revision number has been verified within each of the write threshold number of write confirmation messages, send write commit messages to the storage units; and

slice, encode and store a current directory used to access the encoded data slices in the same way as the first data segment.

10. The distributed storage computing device of claim 9, wherein the first revision number is appended to each encoded data slice of the first set of encoded data slices.

11. The distributed storage computing device of claim 9, wherein the processing system is further operable to:

determine whether write commit responses have been received from at least some of the storage units, wherein a write commit response indicates that a storage unit has made a corresponding encoded data slice visible.

12. A distributed storage computing device comprising:

an interface;

memory; and

a processing system that includes a processor and is operably coupled to the interface and to the memory, wherein the processing system is operable to;

retrieve a first set of appended encoded data slices from storage units of a distributed storage network (DSN);

process the first set of appended encoded data slices to produce a set of first revision numbers and a first set of encoded data slices;

compare the set of first revision numbers; and

when each of the first revision numbers of the set of first revision numbers has the same value and the first set of appended encoded data slices includes a read threshold number of appended encoded data slices, decode the first set of encoded data slices using an error coding dispersal storage function to reconstruct a first data segment.

13. The distributed storage computing device of claim 12, wherein the processing system is further operable to:

when each of the first revision numbers of the set of first revision numbers does not include the same number, retrieve an encoded data slice of a plurality of encoded data slices from another storage unit, wherein the first data segment was encoded into the plurality of encoded data slices and a threshold number of encoded data slices is required to reproduce the first data segment.

14. The distributed storage computing device of claim 12 further comprising:

the first set of encoded data slices including a threshold number of encoded data slices of a plurality of encoded data slices, wherein the first data segment was encoded into the plurality of encoded data slices, wherein the threshold number of encoded data slices is required to reproduce the first data segment.