Operation method and apparatus for data storage system

• US 9,639,588 B2
• Filed: 11/29/2013
• Issued: 05/02/2017
• Est. Priority Date: 06/01/2011
• Status: Active Grant

• Current Assignee: Huawei Technologies Co., Ltd. (Huawei Investment & Holding Co., Ltd.)
• Original Assignee: Huawei Technologies Co., Ltd. (Huawei Investment & Holding Co., Ltd.)
• Inventors: Cheng, Shi
• Primary Examiner(s): Burke, Jeffrey A
• Application Number:
  US14/093,124
• Publication Number:
  US 20140089259A1
• Time in Patent Office: 1,250 Days
• CPC Class Codes: G06F 16/27 Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
• CPC Class Codes: G06F 3/061 Improving I/O performance
• 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]

Abstract

An operation method and apparatus for a data storage system are provided, which relate to the field of data storage and enhance efficiency of a read operation on distributed stored data. The method includes: receiving, by a data node, a data operation message, where the data operation message carries a data operation type and a data object of an operation; querying a state parameter of the data object, where the state parameter is allocated to the data node by a management node, and is used to indicate an update state of the data object, and the update state includes a synchronous state, a semi-synchronous state and an asynchronous state; and if the state parameter is the synchronous state and the operation type is a read operation, reading the data object stored by the data node. Embodiments of the invention are used to operate data in a distributed data storage system.

Claims

1. An operation method for a data storage system including a management node and a plurality of data nodes, comprising:

receiving, by a first data node of the plurality of data nodes, a data operation message, wherein the data operation message carries a data operation type and information of a data object;

querying, by the first data node, a state parameter of the data object, wherein the state parameter is allocated to the first data node by the management node, the state parameter is used to indicate whether the data object is updated to a latest version;

acquiring, by the first data node, information of a second data node storing the data object with a state parameter indicating that the data object is updated to the latest version from a node state table saved by the first data node when the state parameter indicates the data object in the first node is not updated to the latest version, wherein the node state table records data saved by each data node and a state parameter corresponding to the saved data; and

sending, by the first data node, a read operation message to the second data node to read the data object from the second data node when the operation type is a read operation, wherein the read operation message comprises the information of the data object.

2. The method according to claim 1, after the first data node sends the read operation message to the second data node, further comprising:

sending, by the first data node, the read operation message to a third data node storing the data object with a state parameter indicating that the data object is updated to the latest version when a management state exception message returned by the second data node is received within a preset first waiting time period, wherein the management state exception message indicates the second data node is in a connection interruption state.

3. The method according to claim 2, further comprising:

sending, by the first data node, the timeout record table of the first data node to the management node to update a management node state table, wherein state parameters of all data objects reaching a timeout threshold in the first data node is updated in the updated management node state table to indicate the data objects is not updated to a latest version;

receiving, by the first data node, the updated management node state table sent by the management node; and

updating, by the first data node, the node state table of the first data node according to the updated management node state table.

4. The method according to claim 3, after the updating the node state table of the first data node, further comprising:

when a state parameter of another data object of the first data node is changed to indicate the another data object is not updated to a latest version, copying, by the first data node, the another data object from a fourth data node which stores the another data object, wherein the state parameter of the another data object in the fourth data node is updated to a latest version; and

sending, by the first data node, a synchronization completion message to the management node to change the state parameter of the another data object of the first data node to indicate the another data object in the first data node is updated to the latest version in the management node state table.

5. The method according to claim 3, further comprising:

when the number of consecutive connection failures of a management connection request initiated by the first data node to the management node reaches a preset connection failure counting threshold, setting, by the first data node, a management state parameter of the first data node itself to a connection interruption state.

6. The method according to claim 1, further comprising:

sending, by the first data node, a first write operation message to a fifth data node storing the data object with a state parameter indicating that the data object in the fifth data node is updated to the latest version to write the data object in the fifth data node when the operation type is a write operation, wherein the first write operation message comprises the data object.

7. The method according to claim 6, further comprising:

sending, by the fifth data node, a second write operation message to all other data nodes which save the data object to write the data object after the fifth data node completes writing of the data object.

8. The method according to claim 1, after the first data node sends the read operation message to the second data node, further comprising:

updating, by the first data node, a state parameter of the data object of the second data node recorded in the node state table of the first data node when an update state exception message returned by the second data node is received within a preset first waiting time period, wherein the update state exception message indicates the data object in the second data node is not updated to the latest version; and

sending the operation message to a third data node storing the data object with a state parameter indicating that the data object is updated to the latest version.

9. The method according to claim 8, wherein the updating the state parameter of the data object of the second data node recorded in the node state table of the first data node comprises:

acquiring, by the first data node, a new state parameter of the data object of the second data node from the update state exception message returned by the second data node, wherein the update state exception message indicates the data object in the second data node is not updated to the latest version; and

changing, by the first data node, the state parameter of the data object of the second data node recorded in the node state table to the new state parameter of the data object.

10. The method according to claim 1, after the first data node sends the read operation message to the second data node, further comprising:

increasing the number of timeouts of the second data node by 1 in a timeout record table stored by the first data node when a response of the second data node is not received within a first waiting time period.

11. A first data node included in a data storage system, comprising:

a processor; and

a non-transitory computer-readable storage medium coupled to the processor and storing programming instructions for execution by the processor, the programming instructions instruct the processor to;

receive a data operation message, wherein the data operation message carries a data operation type and information of a data object;

query a state parameter of the data object, wherein the data parameter is allocated to the first data node by a management node in the data storage system, the state parameter is used to indicate whether the data object is updated to a latest version

acquire information of a second data node storing the data object with a state parameter indicating that the data object is updated to the latest version from a node state table saved by the first data node when the state parameter indicates the data object in the first node is not updated to the latest version, wherein the data storage system comprises a plurality of data nodes, and wherein the node state table records data saved by each data node and a state parameter corresponding to the saved data; and

send a read operation message to the second data node to read the data object from the second data node when the operation type is a read operation, wherein the read operation message comprises the information of the data object.

12. The first data node according to claim 11, after sends the read operation message to the second data node, the programming instructions instruct the processor further to:

send the read operation message to a third data node storing the data object with a state parameter indicating that the data object is updated to the latest version when a management state exception message returned by the second data node is received within a preset first waiting time period, wherein the management state exception message indicates the second data node is in a connection interruption state.

13. The first data node according to claim 11, wherein the programming instructions instruct the processor further to:

acquire a new state parameter of the data object of the second data node from an update state exception message returned by the second data node, wherein the update state exception message indicates the data object in the second data node is not updated to the latest version;

change the state parameter of the data object of the second data node recorded in the node state table to the new state parameter of the data object; and

sending the operation message to a third data node storing the data object with a state parameter indicating that the data object is updated to the latest version.

14. The first data node according to claim 13, the programming instructions instruct the processor further to:

when the number of consecutive connection failures of a management connection request initiated by the first data node to the management node reaches a preset connection failure counting threshold, set the management state parameter of the first data node itself to a connection interruption state.

15. The first data node according to claim 11, the programming instructions instruct the processor further to:

send a first write operation message to a fifth data node storing the data object with a state parameter indicating that the data object in the fifth data node is updated to the latest version to write the data object in the fifth data node when the operation type is a write operation, wherein the first write operation message comprises the data object.

16. The first data node according to claim 15, the programming instructions instruct the processor further to:

after fifth data node completes writing of the data object, send a second write operation message to all other data nodes which save the data object to write the data object.

17. The first data node according to claim 11, after sends the read operation message to the second data node, the programming instructions instruct the processor further to:

increasing the number of timeouts of the second data node by 1 in a timeout record table stored by the first data node when a response of the second data node is not received within a first waiting time period.

18. The first data node according to claim 17, the programming instructions instruct the processor further to:

send the timeout record table of the first data node to the management node to update a management node state table, wherein state parameters of all data reaching a timeout threshold in the first data node is updated in the updated management node state table to indicate the data object is not updated to a latest version;

receive the updated management node state table sent by the management node; and

update the node state table of the first data node according to the updated management node state table.

19. The first data node according to claim 18, after updating the node state table of the first data node, the programming instructions instruct the processor further to:

when a state parameter of another data object of the first data node is changed to indicate the another data object is not updated to a latest version, copy the another data object from a fourth data node which stores the another data object, wherein the state parameter of the another data object in the fourth data node indicates the another data object in the fourth data node is updated to a latest version; and

send a synchronization completion message to the management node to change the state parameter of the another data object of the first data node to indicate the another data object in the first data node is updated to the latest version in the management node state table.

20. A computer program product, comprising computer executable instructions stored on a non-transitory computer-readable medium, wherein when the instructions are executed by a processor of a first data node in a data storage system including a management node and a plurality of data nodes, causes the processor to:

receive a data operation message, wherein the data operation message carries a data operation type and information of a data object;

query a state parameter of the data object, wherein the data parameter is allocated to the first data node by the management node, the state parameter is used to indicate whether the data object is updated to a latest version;

acquire information of a second data node storing the data object with a state parameter indicating that the data object is updated to the latest version from a node state table saved by the first data node when the state parameter indicates the data object in the first node is not updated to the latest version, wherein the node state table records data saved by each data node and a state parameter corresponding to the saved data; and

send a read operation message to the second data node to read the data object from the second data node when the operation type is a read operation, wherein the read operation message comprises the information of the data object.

21. The computer program product according to claim 20, after the first data node sends the read operation message to the second data node, when the instructions are executed by a processor, causes the processor to:

send the read operation message to a third data node storing the data object with a state parameter indicating that the data object is updated to the latest version when a management state exception message returned by the second data node is received within a preset first waiting time period, wherein the management state exception message indicates the second data node is in a connection interruption state.

22. The computer program product according to claim 21, when the instructions are executed by a processor, causes the processor to:

send a timeout record table of the first data node to the management node to update a management node state table, wherein state parameters of all data objects reaching a timeout threshold in the first data node is updated in the updated management node state table to indicate the data objects is not updated to a latest version;

receive the updated management node state table sent by the management node; and

update the node state table of the first data node according to the updated management node state table.

23. The computer program product according to claim 22, after updating the node state table of the data node according to the management node state table, when the instructions are executed by a processor, causes the processor to:

when a state parameter of another data object of the first data node is changed to indicate the another data object is not updated to a latest version, copy the another data object from a fourth data node which stores the another data object, wherein the state parameter of the another data object in the fourth data node indicates the another data object in the fourth data node is updated to a latest version; and

send a synchronization completion message to the management node to change the state parameter of the another data object of the first data node to indicate the another data object in the first data node is updated to the latest version in the management node state table.

24. The computer program product according to claim 22, when the instructions are executed by a processor, causes the processor to:

when the number of consecutive connection failures of a management connection request initiated by the first data node to the management node reaches a preset connection failure counting threshold, set the management state parameter of the first data node itself to a connection interruption state.

25. The computer program product according to claim 20, when the instructions are executed by a processor, causes the processor to:

send a first write operation message to a fifth data node storing the data object with a state parameter indicating that the data object in the fifth data node is updated to the latest version to write the data object in the fifth data node when the operation type is a write operation, wherein the first write operation message comprises the data object.

26. The computer program product according to claim 25, when the instructions are executed by a processor, further causes the processor to:

send a second write operation message to all other data nodes which save the data object to write the data object after the fifth data node completes writing of the data object.

27. The computer program product according to claim 20, after the first data node sends the read operation message to the second data node, when the instructions are executed by a processor, causes the processor to:

update a state parameter of the data object of the second data node recorded in the node state table of the first data node when an update state exception message returned by the second data node is received within a preset first waiting time period, wherein the update state exception message indicates the data object in the second data node is not updated to the latest version; and

send the read operation message to a third data node storing the data object with a state parameter indicating that the data object is updated to the latest version.

28. The computer program product according to claim 20, after the first data node sends the read operation message to the second data node, when the instructions are executed by a processor, further causes the processor to:

increase the number of timeouts of the second data node by 1 in a timeout record table stored by the first data node when a response of the second data node is not received within a first waiting time period.