Method for updating data in a distributed data storage system

• US 8,997,124 B2
• Filed: 09/02/2011
• Issued: 03/31/2015
• Est. Priority Date: 09/02/2011
• Status: Active Grant

• Current Assignee: Compuverde AB (Pure Storage, Inc.)
• Original Assignee: Compuverde AB (Pure Storage, Inc.)
• Inventors: Melander, Christian, Petersson, Gustav, Bernbo, Stefan, Persson, Roger
• Primary Examiner(s): Sough, H S
• Assistant Examiner(s): Onat, Umut
• Application Number:
  US13/224,446
• Publication Number:
  US 20130061253A1
• Time in Patent Office: 1,306 Days
• Field of Search: None
• US Class Current: 719/328
• CPC Class Codes: G06F 16/184 implemented as replicated file system
• CPC Class Codes: G06F 3/061 Improving I/O performance
• CPC Class Codes: G06F 3/0643 Management of files
• CPC Class Codes: G06F 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]

Abstract

There is provided a method implemented in a data storage system including a plurality of storage nodes connected to each other via a communications network. At least one storage node of the plurality of storage nodes may store a first data item. The data item may be arranged to include a reference to a second data item stored in the data storage system. The method may include providing an identifier of the second data item. The method may also include providing status information about the first data item. The identifier may be used to update the first data item, for example based on the status information. The first data item may be stored at the at least one storage node.

Claims

1. A method for updating data stored in a data storage system, the data storage system including a plurality of storage nodes, the method comprising:

determining status information regarding a first data item, wherein the status information comprises an indication of identities of one or more data storage nodes that store the first data item, the first data item comprises a collection object that references one or more other data items in the data storage system, and the one or more other data items comprise at least one other collection object;

determining an identifier for a second data item stored on a second storage node, wherein the identifier uniquely identifies the second data item within the data storage system;

sending an update message for the first data item to a first storage node based on the status information indicating that the first storage node is one of the one or more data storage nodes that store the first data item, wherein the update message indicates that the identifier for the second data item is to be included in a reference to the second data item within in the collection object of the first data item;

determining that at least one data storage node that stores a version of the first data item is storing a version of the first data item with different contents than are included in a version of the first data item stored at the first data storage node; and

determining which version of the first data item should be stored in the data storage system by selecting an instance of the first data item that is stored at a largest number of data storage nodes as the version of the first data item that is to be distributed in the data storage system.

2. The method according to claim 1, wherein the update message is sent using an application programming interface (API).

3. The method according to claim 2, wherein the API is implemented on a server in communication with said first and second storage nodes.

4. The method according to claim 2, wherein the API is implemented in a storage node included in the data storage system.

5. The method according to claim 1, wherein said status information is cached from a previous access to said first data item.

6. The method according to claim 1, wherein said identifier is received prior to receiving the status information, the method further comprising saving the identifier in a memory cache.

7. The method according to claim 1, further comprising sending a subsequent update message to append data to an existing data file included in said first data item or to overwrite an existing data file included in said first data item.

8. The method according to claim 1, wherein said status information comprises a key for the first data item and one or more Internet Protocol (IP) addresses for the data storage nodes that store the first data item.

9. The method according to claim 1, wherein said status information comprises information about an amount of free storage space at said first storage node.

10. The method according to claim 1, wherein said status information comprises information about a load condition at said first storage node.

11. The method according to claim 1, wherein the update message is sent on condition that the size of said second data item is less than a predetermined value.

12. The method according to claim 1, wherein said status information about said first data item is provided at regular time intervals.

13. The method according to claim 1, further comprising receiving an acknowledgement from the first storage node, wherein said acknowledgement comprises information regarding the first storage node.

14. The method according to claim 13, wherein said acknowledgment is a negative acknowledgement, and the method further comprises re-sending the update message for the first data item.

15. The method according to claim 1, wherein the update message is sent as a unicast message.

16. A server comprising a processor and memory, the processor being configured to:

determine status information regarding a first data item, wherein the status information comprises an indication of identities of one or more data storage nodes that store the first data item, the first data item comprises a collection object that references one or more other data items in the data storage system, and the one or more other data items comprise at least one other collection object;

determine an identifier for a second data item stored on a second storage node, wherein the identifier uniquely identifies the second data item within the data storage system;

send an update message for the first data item to a first storage node based on the status information indicating that the first storage node is one of the one or more data storage nodes that store the first data item, wherein the update message indicates that the identifier for the second data item is to be included in a reference to the second data item within in the collection object of the first data item;

determine that at least one data storage node that stores a version of the first data item is storing a version of the first data item with different contents than are included in a version of the first data item stored at the first data storage node;

determine which version of the first data item should be stored in the data storage system by selecting an instance of the first data item that is stored at a largest number of data storage nodes as the version of the first data item that should be stored in the data storage system; and

send a message indicating the version of the first data item to be stored to at least one storage node that stores a different version of the first data item.

17. The server according to claim 16, wherein the server comprises an Application Program Interface (API).

18. A storage node comprising a processor and memory, the processor being configured to:

send status information to a server regarding a first data item, wherein the status information comprises an indication of identities of one or more data storage nodes that store the first data item, the status information indicates that the storage node is one of the one or more storage nodes that store the first data item, the first data item comprises a collection object that references one or more other data items in the data storage system, and the one or more other data items comprise at least one other collection object;

receive an update message for the first data item from the server, wherein the update message indicates an identifier for a second data item stored on a second data storage node and the identifier uniquely identifies the second data item within the data storage system;

update the first data item to include a reference to the second data item based on the received update message, the reference comprising the identifier; and

send a local version of the data of the first data item to another data storage node that stores a different version of the first data item, wherein the local version of the first data item is sent to the another storage node based on the local version of the first data item being stored on a greater number of data storage nodes than store the different version of the first data item.