Peer to peer ownership negotiation

• US 10,031,933 B2
• Filed: 03/02/2015
• Issued: 07/24/2018
• Est. Priority Date: 03/02/2014
• Status: Active Grant

• Current Assignee: NetApp, Inc.
• Original Assignee: NetApp, Inc.
• Inventors: Golander, Amit
• Primary Examiner(s): Vostal, O. C.
• Application Number:
  US14/635,236
• Publication Number:
  US 20150249618A1
• Time in Patent Office: 1,240 Days
• Field of Search: 709224
• CPC Class Codes: G06F 16/182 Distributed file systems
• CPC Class Codes: G06F 16/185 Hierarchical storage management [HSM] systems, e.g. file migration or policies thereof details of archiving G06F16/11
• CPC Class Codes: G06F 16/22 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/2455 Query execution
• CPC Class Codes: H04L 47/70 Admission control; Resource allocation
• CPC Class Codes: H04L 67/104 Peer-to-peer [P2P] networks
• 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 method of negotiating memory record ownership between network nodes, comprising: storing in a memory of a first network node a subset of a plurality of memory records and one of a plurality of file system segments of a file system mapping the memory records; receiving a request from a second network node to access a memory record of the memory records subset; identifying the memory record by using the file system segment; deciding, by a placement algorithm, whether to relocate the memory record, from the memory records subset to a second subset of the plurality of memory records stored in a memory of the second network node; when a relocation is not decided, providing remote access of the memory record via a network to the second network node; and when a relocation is decided, relocating the memory record via the network for management by the second network node.

Claims

1. A method, comprising:

storing in a memory of a first network node a subset of a plurality of memory records and one of a plurality of file system segments of a shared file system executed by a plurality of network nodes;

wherein the one file system segment executed by the first network node maps to said subset of the plurality of memory records, and wherein said subset of the plurality of memory records is owned by said first network node such that only said first network node is allowed to commit any changes to said subset of memory records stored at the memory of the first network node;

receiving a request from a second network node to access a memory record of said memory records subset owned by said first network node;

identifying said memory record by using said file system segment of the first network node;

deciding, by a placement algorithm executed by the first network node that owns the memory record requested by the second network node, whether to relocate said memory record, from said memory records subset to a second subset of said plurality of memory records stored in a memory of said second network node based on making the memory record requested by the second network node local to the second network node and a frequency of previous relocations, if any, of said memory record;

when a relocation is not decided, providing remote access to said memory record stored at the first network node via a network to said second network node; and

when a relocation is decided, relocating said memory record via said network to the memory of the second network node such that said memory record becomes local to the second network node after relocation, for management by said second network node using a segment of the shared file system stored at the memory of the second network node.

2. The method of claim 1, wherein said deciding is done according to an open action for said memory record by said second network node.

3. The method of claim 1, wherein said deciding is done according to use of said memory record by other network nodes.

4. The method of claim 1, wherein said deciding is done according to traffic load on said network based on connections to said network node.

5. The method of claim 1, further comprising:

monitoring previous relocations of said memory record between the plurality of network nodes in previous ownership negotiation processes;

wherein said deciding is done according to said monitoring.

6. The method of claim 1, further comprising:

when receiving requests from multiple network nodes for read only access to said memory record, creating cached copies of said memory record in storage units of said multiple network nodes to decrease network load.

7. The method of claim 6, further comprising:

when said memory record is updated, invalidating said cached copies of said memory record.

8. The method of claim 1, wherein said relocation is delayed due to lack of vacant capacity on a memory of said second network node as indicated by said second network node.

9. The method of claim 1, wherein said relocation is delayed due to network traffic load on said network based on connections to said network node.

10. The method of claim 1, wherein said relocation is done by prioritizing relocation of data units of said memory record that are requested by said second network node.

11. The method of claim 1, further comprising:

relocating a memory record of a directory containing said memory record.

12. A non-transitory machine-readable storage medium having stored thereon instructions for performing a method, comprising machine executable code which when executed by at least one machine, causes the machine to:

store in a memory of a first network node a subset of a plurality of memory records and one of a plurality of file system segments of a shared file system executed by a plurality of network nodes;

wherein the one file system segment executed by the first network node maps to said subset of the plurality of memory records, and wherein said subset of the plurality of memory records is owned by said first network node such that only said first network node is allowed to commit any changes to said subset of memory records stored at the memory of the first network node;

receive a request from a second network node to access a memory record of said memory records subset owned by said first network node;

identify said memory record by using said file system segment of the first network node;

decide, by a placement algorithm executed by the first network node that owns the memory record requested by the second network node, whether to relocate said memory record, from said memory records subset to a second subset of said plurality of memory records stored in a memory of said second network node based on making the memory record requested by the second network node local to the second network node and a frequency of previous relocations, if any, of said memory record;

when a relocation is not decided, provide remote access to said memory record stored at the first network node via a network to said second network node; and

when a relocation is decided, relocate said memory record via said network to the memory of the second network node such that said memory record becomes local to the second network node after relocation, for management by said second network node using a segment of the shared file system stored at the memory of the second network node.

13. The non-transitory storage medium of claim 12, wherein decision to relocate is further based on an open action for said memory record by said second network node.

14. The non-transitory storage medium of claim 12, wherein decision to relocate is further based on use of said memory record by other network nodes.

15. The non-transitory storage medium of claim 12, wherein decision to relocate is further based on traffic load on said network based on connections to said second network node.

16. The non-transitory storage medium of claim 12, wherein relocation to the second network node is delayed due to lack of capacity at the memory of said second network node as indicated by said second network node.

17. A system, comprising:

a memory containing machine readable medium comprising machine executable code having stored thereon instructions; and

a processor coupled to the memory to execute the machine executable code to;

store in a memory of a first network node a subset of a plurality of memory records and one of a plurality of file system segments of a shared file system executed by a plurality of network nodes;

wherein the one file system segment executed by the first network node maps to said subset of the plurality of memory records, and wherein said subset of the plurality of memory records is owned by said first network node such that only said first network node is allowed to commit any changes to said subset of memory records stored at the memory of the first network node;

receive a request from a second network node to access a memory record of said memory records subset owned by said first network node;

identify said memory record by using said file system segment of the first network node;

decide, by a placement algorithm executed by the first network node that owns the memory record requested by the second network node, whether to relocate said memory record, from said memory records subset to a second subset of said plurality of memory records stored in a memory of said second network node, based on making the memory record requested by the second network node local to the second network node and a frequency of previous relocations, if any, of said memory record;

when a relocation is not decided, provide remote access to said memory record stored at the first network node via a network to said second network node; and

when a relocation is decided, relocate said memory record via said network to the memory of the second network node such that said memory record becomes local to the second network node after relocation, for management by said second network node using a segment of the shared file system stored at the memory of the second network node.

18. The system of claim 17, wherein decision to relocate is further based on an open action for said memory record by said second network node.

19. The system of claim 17, wherein decision to relocate is further based on use of said memory record by other network nodes.

20. The system of claim 17, wherein decision to relocate is further based on traffic load on said network based on connections to said second network node.