Storing data in a dispersed storage network

• US 10,015,255 B2
• Filed: 08/10/2017
• Issued: 07/03/2018
• Est. Priority Date: 09/30/2005
• Status: Active Grant

• Current Assignee: Pure Storage, Inc.
• Original Assignee: International Business Machines Corporation
• Inventors: Dhuse, Greg R.
• Primary Examiner(s): BRADLEY, MATTHEW A
• Application Number:
  US15/673,978
• Publication Number:
  US 20170366613A1
• Time in Patent Office: 327 Days
• CPC Class Codes: G06F 11/1092 Rebuilding, e.g. when physically replacing a failing disk
• 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]

Abstract

A computing device includes a processing module operable to generate a set of write requests regarding a set of encoded data slices. The processing module is further operable to send the set of write requests to a set of storage units, where each of at least some of the storage units of the set of storage units generates a write response. The processing module is further operable to receiving the write responses where the write responses includes at least a decode threshold number of write responses. The processing module is further operable to determine a most current revision level regarding the set of encoded data slices based on the lists of revision levels from the at least some of the storage units, and generate a set of write commit messages.

Claims

1. A computing device of a dispersed storage network (DSN), the computing device comprises:

an interface;

memory; and

a processing module operably coupled to the memory and the interface, wherein the processing module is operable to;

generate a set of write requests regarding a set of encoded data slices, wherein a write request of the set of write requests includes an encoded data slice of the set of encoded data slices, a corresponding slice name, and a transaction number corresponding to the set of write requests;

send the set of write requests to a set of storage units, wherein each of at least some of the storage units of the set of storage units generate a write response that includes the transaction number and a list of revision levels corresponding to the slice name;

receiving the write responses from the at least some of the storage units, wherein the write responses includes at least a decode threshold number of write responses;

determining a most current revision level regarding the set of encoded data slices based on the lists of revision levels from the at least some of the storage units; and

generating a set of write commit messages, wherein a write commit message of the set of write commit messages includes the transaction number and a new revision level for the set of encoded data slices.

2. The computing device of claim 1, wherein the write response further comprises:

a particular slice name corresponding to a particular encoded data slice of the set of encoded data slices.

3. The computing device of claim 1, wherein the processing module is operable to generate the write response by:

identifying stored encoded data slices having the slice name;

determining revision values for each of the stored encoded data slices; and

generating the list of revision levels based on the revision values.

4. The computing device of claim 1, wherein the processing module is operable to determine the most current revision level by:

reviewing the lists of revision levels from the at least some of the storage units to determine a highest revision value, wherein the lists of revision levels includes a list of revision values for the corresponding slice name; and

utilizing the highest revision value as the most current revision level.

5. The computing device of claim 1, wherein the processing module is operable to determine the most current revision level by:

reviewing the lists of revision levels from the at least some of the storage units to determine a highest revision value in a threshold number of lists of revision levels, wherein the lists of revision levels includes a list of revision values for the corresponding slice name; and

utilizing the highest revision value in the threshold number of lists of revision levels as the most current revision level.

6. The computing device of claim 1, wherein the processing module is operable to generate the set of write commit messages by at least one of:

determining the new revision level by incrementing the most current revision level; and

determining the new revision level by performing a mathematical function on the most current revision level.

7. The computing device of claim 1, wherein the processing module is further operable to send the set of write requests to the set of storage units, wherein each of the at least some of the storage units generate a write response by:

storing the encoded data slice corresponding to the slice name;

restricting access to the encoded data slice pending the write commit message; and

maintaining access to a previous revision level of the encoded data slice pending the write commit message.

8. The computing device of claim 1, wherein the processing module is further operable to:

send the set of write commit messages to the set of storage units.