Distributed transactions with token-associated execution

• US 10,007,457 B2
• Filed: 12/22/2015
• Issued: 06/26/2018
• Est. Priority Date: 12/22/2015
• Status: Active Grant

• Current Assignee: Pure Storage, Inc.
• Original Assignee: Pure Storage, Inc.
• Inventors: Hayes, John, Lee, Robert, Ostrovsky, Igor, Vajgel, Peter
• Primary Examiner(s): YU, JAE UN
• Application Number:
  US14/978,073
• Publication Number:
  US 20170177253A1
• Time in Patent Office: 917 Days
• Field of Search: 711103
• CPC Class Codes: G06F 3/0622 in relation to access
• CPC Class Codes: G06F 3/0637 Permissions
• CPC Class Codes: G06F 3/0659 Command handling arrangements, e.g. command buffers, queues, command scheduling
• CPC Class Codes: G06F 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
• CPC Class Codes: G06F 3/0688 Non-volatile semiconductor memory arrays

Abstract

A method of processing transactions associated with a command in a storage system is provided. The method includes receiving, at a first authority of the storage system, a command relating to user data. The method includes sending a transaction of the command, from the first authority to a second authority of the storage system, wherein a token accompanies the transaction and writing data in accordance with the transaction as permitted by the token into a partition that is allocated to the second authority in a storage device of the storage system.

Claims

1. A method of processing transactions associated with a command in a storage system, comprising:

receiving, at a first authority of the storage system, a command relating to user data;

sending a transaction of the command, from the first authority to a second authority of the storage system, wherein a token is associated with the transaction; and

writing data in accordance with the transaction as permitted by the token into a partition that is allocated to the second authority in a storage device of the storage system, wherein command processing and transaction processing is performed without a global lock on the storage system.

2. The method of claim 1, further comprising:

allocating, to each of a plurality of authorities of the storage system, a partition in each of at least a subset of a plurality of storage devices, for writing data.

3. The method of claim 1, wherein each of a plurality of authorities of the storage system can receive commands and can act as a transaction authority for any authority receiving commands.

4. The method of claim 1, wherein:

each token is time-based; and

presence of a time-based token in one of a plurality of storage nodes of the storage system indicates permission to perform the associated transaction within a time span.

5. The method of claim 1, further comprising:

processing multiple commands, each having multiple transactions, through multiple authorities in parallel, wherein the writing data associated with each of the multiple transactions for one of the multiple commands indicates the one of the multiple commands is committed.

6. The method of claim 1, wherein:

neither completion of a transaction nor completion of a command is broadcast throughout the storage system.

7. The method of claim 1, further comprising:

committing the command once each transaction of the command is written into an allocated partition of the storage device.

8. A tangible, non-transitory, computer-readable media having instructions thereupon which, when executed by a processor, cause the processor to perform a method comprising:

receiving, at a first authority of the storage system, a command relating to user data;

sending a transaction of the command, from the first authority to a second authority of the storage system, wherein a token is associated with the transaction; and

writing data in accordance with the transaction as permitted by the token into a partition that is allocated to the second authority in a storage device of the storage system, wherein command processing and transaction processing is performed without a global lock on the storage system.

9. The computer-readable media of claim 8, wherein the method further comprises:

allocating, to each of a plurality of authorities of the storage system, a partition in each of at least a subset of a plurality of storage devices, for writing data.

10. The computer-readable media of claim 8, wherein each of a plurality of authorities of the storage system can receive commands and can act as a transaction authority for any authority receiving commands.

11. The computer-readable media of claim 8, wherein:

each token is time-based; and

presence of a time-based token in one of a plurality of storage nodes indicates permission to perform the associated transaction within a time span.

12. The computer-readable media of claim 8, wherein the method further comprises:

processing multiple commands, each having multiple transactions, through multiple authorities in parallel, wherein the writing data associated with each of the multiple transactions for one of the multiple commands indicates the one of the multiple commands is committed.

13. The computer-readable media of claim 8, wherein:

neither completion of a transaction nor completion of a command is broadcast throughout the storage system.

14. The computer-readable media of claim 8, wherein the method further comprises:

committing the command once each transaction of the command is written into an allocated partition of the storage device.

15. A storage system comprising:

a memory; and

a processing unit having a processor configured to execute actions, the actions comprising;

receiving, at a first authority of the storage system, a command relating to user data;

sending a transaction of the command, from the first authority to a second authority of the storage system, wherein a token is associated with the transaction; and

writing data in accordance with the transaction as permitted by the token into a partition that is allocated to the second authority in a storage device of the storage system,

wherein command processing and transaction processing is performed without a global lock on the storage system.

16. The storage system of claim 15, wherein the actions further comprise:

allocating, to each of a plurality of authorities of the storage system, a partition in each of at least a subset of a plurality of storage devices, for writing data.

17. The storage system of claim 15, wherein each of a plurality of authorities of the storage system can receive commands and can act as a transaction authority for any authority receiving commands.

18. The storage system of claim 15, wherein:

each token is time-based; and

presence of a time-based token in one of a plurality of storage nodes indicates permission to perform the associated transaction within a time span.

19. The storage system of claim 15, wherein the actions further comprise:

processing multiple commands, each having multiple transactions, through multiple authorities in parallel, wherein the writing data associated with each of the multiple transactions for one of the multiple commands indicates the one of the multiple commands is committed.

20. The storage system of claim 15, wherein:

neither completion of a transaction nor completion of a command is broadcast throughout the storage system.