LOAD BALANCING AND FAULT TOLERANT SERVICE IN A DISTRIBUTED DATA SYSTEM

• US 20160239350A1
• Filed: 02/12/2015
• Published: 08/18/2016
• Est. Priority Date: 02/12/2015
• Status: Active Grant

• Current Assignee: NetApp, Inc.
• Original Assignee: NetApp, Inc.
• Inventors: Kamawat, Rakshit, TS, Veena, Marappa, Ganesh
• Granted Patent: US 9,785,480 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 11/1425 by reconfiguration of node membership
• CPC Class Codes: G06F 11/1484 involving virtual machines
• CPC Class Codes: G06F 11/203 using migration
• CPC Class Codes: G06F 11/2035 without idle spare hardware
• CPC Class Codes: G06F 11/3433 for load management allocation of a server based on load conditions G06F9/505; load rebalancing G06F9/5083; redistributing the load in a network by a load balancer H04L67/1029
• CPC Class Codes: G06F 2201/805 Real-time
• CPC Class Codes: G06F 9/5088 involving task migration

Abstract

Techniques for load balancing and fault tolerant service are described. An apparatus may comprise load balancing and fault tolerant component operative to execute a load balancing and fault tolerant service in a distributed data system. The load balancing and fault tolerant service distributes a load of a task to a first node in a cluster of nodes using a routing table. The load balancing and fault tolerant service stores information to indicate the first node from the cluster of nodes is assigned to perform the task. The load balancing and fault tolerant service detects a failure condition for the first node. The load balancing and fault tolerant service moves the task to a second node from the cluster of nodes to perform the task for the first node upon occurrence of the failure condition.

Claims

1. A computer-implemented method, comprising:

distributing a load of a task to a first node in a cluster of nodes using a routing table;

storing information to indicate the first node from the cluster of nodes is assigned to perform the task;

detecting a failure condition for the first node; and

moving the task to a second node from the cluster of nodes to perform the task for the first node upon occurrence of the failure condition.

2. The method of claim 1, comprising:

creating a relationship between the first node and the second node in the cluster of nodes;

delegating the relationship from the first node to the second node for load balancing the second node in the cluster of nodes upon detection of the failure condition of the first node;

detecting a return of the first node to an active status; and

returning the relationship to the first node upon the first node returning to the active status following the failure condition.

3. The method of claim 2, comprising:

replicating the routing table to the first node in the cluster of nodes using a replicated database (RDB) service;

saving similar information in a structured format in the first node in the cluster of nodes by the RDB service;

maintaining quorums of the cluster of nodes; and

providing a notification upon a node joining or leaving one of the quorums of the cluster of nodes.

4. The method of claim 1, comprising:

restarting the task by the second node upon movement from the first node; and

restoring to the first node the load of the task upon the first node becoming active after the failure condition.

5. The method of claim 1, comprising joining a new node that is capable of receiving the load to the cluster of nodes, wherein the new node is the second node.

6. The method of claim 1, comprising maintaining in the routing table an ownership list indicating which node in the cluster of nodes is a most recent owner responsible for the task.

7. The method of claim 1, comprising determining a performance state for the first node in the cluster of nodes.

8. The method of claim 1, comprising maintaining user space processes on each node for distributing the load of the task.

9. An apparatus, comprising:

a processor circuit on a device; and

a load balancing and fault tolerant component operative on the processor circuit to execute a load balancing and fault tolerant service in a distributed data system, the load balancing and fault tolerant component operative to;

distribute a load of a task to a first node in a cluster of nodes using a routing table;

store information to indicate the first node from the cluster of nodes is assigned to perform the task;

detect a failure condition for the first node; and

move the task to a second node from the cluster of nodes to perform the task for the first node upon occurrence of the failure condition.

10. The apparatus of claim 9, the load balancing and fault tolerant component operative to:

create a relationship between the first node and the second node in the cluster of nodes;

delegate the relationship from the first node to the second node for load balancing the second node in the cluster of nodes upon detection of the failure condition of the first node;

detect a return of the first node to an active status; and

return the relationship to the first node upon the first node returning to the active status following the failure condition.

11. The apparatus of claim 10, the load balancing and fault tolerant component operative to:

replicate the routing table to the first node in the cluster of nodes using a replicated database (RDB) service;

save similar information in a structured format in the first node in the cluster of nodes;

maintain quorums of the cluster of nodes; and

provide a notification upon a node joining or leaving one of the quorums of the cluster of nodes.

12. The apparatus of claim 9, the load balancing and fault tolerant component operative to:

restart the task by the second node upon occurrence of the failure condition; and

restore to the first node the load to perform the task upon the first node becoming active after the failure condition.

13. The apparatus of claim 9, the load balancing and fault tolerant component operative to join a new node that is capable of receiving the load to the cluster of nodes, wherein the new node is the second node.

14. The apparatus of claim 9, the load balancing and fault tolerant component operative to:

maintain in the routing table an ownership list indicating which node in the cluster of nodes is a most recent owner responsible for the task;

determine a performance state for the first node in the cluster of nodes; and

maintain user space processes on each node for distributing the load of the task.

15. At least one non-transitory computer-readable storage medium comprising instructions that, when executed, cause a system to:

distribute a load of a task to a first node in a cluster of nodes using a routing table;

store information to indicate the first node from the cluster of nodes is assigned to perform the task;

detect a failure condition for the first node; and

move the task to a second node from the cluster of nodes to perform the task for the first node upon occurrence of the failure condition.

16. The computer-readable storage medium of claim 15, comprising further instructions that, when executed, cause a system to:

create a relationship between the first node and the second node in the cluster of nodes;

delegate the relationship from the first node to the second node for load balancing the second node in the cluster of nodes upon detection of the failure condition of the first node;

detect a return of the first node to an active status; and

return the relationship to the first node upon the first node returning to the active status following the failure condition.

17. The computer-readable storage medium of claim 16, comprising further instructions that, when executed, cause a system to:

replicate the routing table to the first node in the cluster of nodes using a replicated database (RDB) service;

save similar information in a structured format in the first node in the cluster of nodes;

maintain quorums of the cluster of nodes; and

provide a notification upon a node joining or leaving one of the quorums of the cluster of nodes.

18. The computer-readable storage medium of claim 15, comprising further instructions that, when executed, cause a system to:

restart the task by the second node upon occurrence of the failure condition; and

restore to the first node the load to perform the task upon the first node becoming active after the failure condition.

19. The computer-readable storage medium of claim 15, comprising further instructions that, when executed, cause a system to join a new node that is capable of receiving the load to the cluster of nodes, wherein the new node is the second node.

20. The computer-readable storage medium of claim 15, comprising further instructions that, when executed, cause a system to:

maintain in the routing table an ownership list indicating which node in the cluster of nodes is a most recent owner responsible for the task;

determine a performance state for the first node in the cluster of nodes; and

maintain user space processes on each node for distributing the load of the task.