METHOD AND APPARATUS FOR DISTRIBUTED CONFIGURATION MANAGEMENT

• US 20160371354A1
• Filed: 08/29/2016
• Published: 12/22/2016
• Est. Priority Date: 06/23/2011
• Status: Active Grant

• Current Assignee: Hewlett Packard Enterprise Development LP (Hewlett-Packard Enterprise Company)
• Original Assignee: SimpliVity Corporation (Hewlett-Packard Enterprise Company)
• Inventors: Stack, Michael T., Beaverson, Arthur J., Bagby, Steven, King, James E. III
• Granted Patent: US 10,255,340 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/128 Details of file system snapshots on the file-level, e.g. snapshot creation, administration, deletion use of snapshots for error detection or correction G06F11/14, G06F11/16
• CPC Class Codes: G06F 16/1834 implemented based on peer-to-peer networks, e.g. gnutella p2p communication protocols H04L67/104
• CPC Class Codes: G06F 16/2329 using versioning
• 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 16/278 Data partitioning, e.g. horizontal or vertical partitioning
• CPC Class Codes: H04L 67/1095 Replication or mirroring of data, e.g. scheduling or transport for data synchronisation between network nodes

Abstract

Method and apparatus for replicating data structures over a network in which each data structure is assigned an owner node among a plurality of networked peer nodes. Preferably that owner can be ascertained through information in the data structure. When an update to the data structure is desired by a non-owner, a request to modify the data structure is sent out on the network and when received by the owner, the owner performs the modification. The owner node can then notify the other nodes regarding the update. The method, implemented through a single-writer, multiple-reader paradigm, insures availability, partition tolerance and eventual consistency; it avoids the high overhead costs and single point of failure drawbacks of the prior art centralized management and locking protocols. Administrators can connect to any peer node in the network to manage, monitor and request modifications to a data structure.

Claims

1. A computer-readable medium containing executable program instructions for a method of replicating data structures, the method comprising:

on a network of peer nodes, wherein data structures are replicated to all nodes on the network;

designating a single peer node as owner of a data structure;

permitting only the designated owner node to modify the data structure; and

when one peer node desires to modify the data structure and determines it is not the owner node, the one peer node initiates a request to modify the data structure, the request comprises one of the data structures and is owned by the one peer node, and the request is transmitted to all nodes on the network; and

the owner node receives and executes the request to modify the data structure.

2. The medium of claim 1, wherein the method includes:

the owner node initiates a response regarding the modified data structure, the response is one of the data structures and is owned by the owner node, and the response is transmitted to all nodes on the network.

3. The medium of claim 2, wherein the method includes:

when the response is received by a non-owner node, the receiving node determines whether it has already received the response and if so, drops the response, and if not, it processes the response.

4. The medium of claim 2, wherein the response includes an identifier for the modified data structure.

5. The medium of claim 1, wherein the request includes a tag uniquely identifying the request.

6. The medium of claim 1, wherein the method includes:

when one peer node desires to modify the data structure and determines it is the owner node, the one peer node modifies the data structure.

7. The medium of claim 1, wherein when a partition divides the network into multiple network partitions, the replication on each network partition remains operable.

8. The medium of claim 7, wherein when the partition ends, the replication across the partition resumes.

9. The medium of claim 1, wherein the network is a network in which all nodes are not directly connected.

10. The medium of claim 1, wherein the data structure includes an identifier of the owner node.

11. The medium of claim 1, wherein the data structure contains an identifier which is globally unique across all of the nodes.

12. The medium of claim 1, wherein the data structure is stored in a database.

13. The medium of claim 1, wherein the method implements a relational database.

14. The medium of claim 1, wherein the data structure is a row in a database table.

15. The medium of claim 1, wherein the data structure describes a network interface, a file system, or a file system snapshot.

16. The medium of claim 2, wherein the data structure, request and response are replicated by propagation to all nodes on the network.

17. A method implemented by a computer network, the method comprising:

obtaining information in a replica of a data structure that is replicated on multiple peer nodes, the information indicating one of the peer nodes as an owner node that has exclusive rights to update the data structure;

determining if a peer node is the owner node via the information;

if the peer node is not the owner node, performing actions comprising;

sending a request to update the data structure to all directly connected peer nodes to propagate the request;

the owner node receiving the request, updating the data structure after receiving the request and sending an update regarding the updated data structure to all directly connected peer nodes to propagate the update.

18. In a computing environment, an apparatus on each of a plurality of peer nodes in a network comprising:

a replication manager operable to participate in replicating a data structure across the peer nodes;

an update manager operable to update the replica of the data structure on the peer node; and

a configuration manager operable to;

determine whether a peer node is an owner node of the data structure based on information included in the data structure;

initiate a request to modify the data structure if the peer node is not the owner node; and

process a response to the request regarding the modified data structure, wherein the owner node has exclusive rights to update the data structure and the request and response are also data structures replicated across the peer nodes.