METHOD AND SYSTEM FOR MANAGING LOAD IN A NETWORK

• US 20100042723A1
• Filed: 08/12/2009
• Published: 02/18/2010
• Est. Priority Date: 08/12/2008
• Status: Abandoned Application

• Current Assignee: Infosys Limited
• Original Assignee: Infosys Limited
• Inventors: Nellitheertha, Hariprasad, Sundarrajan, Srikanth
• Application Number:
  US12/539,699
• Publication Number:
  US 20100042723A1
• Time in Patent Office: Days
• US Class Current: 709/226
• CPC Class Codes: G06F 9/505 considering the load
• CPC Class Codes: H04L 43/0876 Network utilisation, e.g. volume of load or congestion level
• CPC Class Codes: H04L 67/1001 for accessing one among a plurality of replicated servers

Abstract

A method for managing load in a network comprising a first set of hosts, a second set of hosts and a centralized server is provided. A virtual machine runs on each of the first set of hosts. The centralized server receives resource donation information from each of the second set of hosts that are underutilized. Further, a load surge indicating additional tasks to be performed by the first set of hosts and the second set of hosts is identified. Next, the centralized server negotiates with the second set of hosts for modification of the resource donation information. Thereafter, one or more hosts are determined, based on the resource donation information and the load surge. These hosts create a virtual machine, based on the resource donation information, and become a part of the first set of hosts. The centralized server delegates the additional tasks among the first set of hosts.

Claims

1. A method for managing load in a network, the network comprising a first set of hosts, a second set of hosts that are under-utilized and a centralized server, a virtual machine running on each of the first set of hosts, the method at the centralized server comprising:

a. receiving resource donation information from each of the second set of hosts, wherein the host registers the resource donation information with the centralized server;

b. identifying a load surge in the network, wherein the load surge indicates additional tasks to be performed by the first set of hosts and the second set of hosts;

c. negotiating with the second set of hosts when the load surge is identified, wherein the centralized sever negotiates with the second set of hosts for modification of the resource donation information;

d. determining one or more hosts from the second set of hosts, based on the resource donation information received from each of the second set of hosts and the identified load surge, wherein each of the one or more hosts creates a virtual machine based on the resource donation information, wherein the one or more hosts become a part of the first set of hosts; and

e. delegating the additional tasks among the first set of hosts.

2. The method according to claim 1, wherein the resource donation information comprises the information regarding the resources the host is capable of contributing.

3. The method according to claim 2, wherein the resource donation information is determined by the host.

4. The method according to claim 1, wherein the resource donation information is stored by the centralized server in a database.

5. The method according to claim 1 further comprising identifying the decrease in the load in the network, wherein the decrease in the load indicates decrease in the number of tasks to be performed.

6. The method according to claim 5 further comprising:

a. terminating the virtual machine present on at least one host from the first set of hosts, wherein the at least one host releases the resources associated with the terminated virtual machine, further wherein the at least one host becomes a part of the second set of hosts; and

b. receiving modified resource donation information from the at least one host, wherein modified resource donation information is re-registered with the centralized server.

7. A centralized server for managing load in a network, the network comprising a first set of hosts and a second set of hosts, a virtual machine running on each of the first set of hosts, the second set of hosts being underutilized, the centralized server comprising:

a. a resource donation agent configured for receiving resource donation information from each of the second set of hosts, wherein the host registers the resource donation information with a database;

b. a load balancer configured for identifying a load surge in the network, wherein the load surge indicates additional tasks to be performed by the first set of hosts and the second set of hosts; and

c. a scheduling manager communicatively coupled to the load balancer wherein the scheduler manager is configured for;

i. negotiating with the second set of hosts when the load surge is identified, wherein the scheduling manager negotiates for the modification the resource donation information;

ii. determining one or more hosts from the second set of hosts, based on the resource donation information and the identified load surge, wherein each of the one or more hosts creates a virtual machine based on the resource donation information associated with each of the second set of hosts, further wherein the one or more hosts become a part of the first set of hosts; and

iii. delegating the additional tasks among the first set of hosts.

8. The centralized server according to claim 7, wherein the resource donation information comprises the information regarding the resources the host capable of contributing.

9. The centralized server according to claim 8, wherein the resource donation information is determined by the host.

10. The centralized server according to claim 7, wherein the load balancer is further configured for identifying the decrease in the load in the network, wherein the decrease in the load indicates decrease in the number of tasks to be performed.

11. The centralized server according to claim 7, wherein the load balancer is an external network component communicatively coupled to the centralized server.

12. The centralized server according to claim 7, wherein the scheduling manager is further configured for terminating the virtual machine present on at least one host from the first set of hosts when decrease in the load in the network is identified, wherein the at least one host releases the resources associated with the terminated virtual machine, further wherein the at least one host becomes a part of the second set of hosts.

13. The centralized server according to claim 7, wherein the resource donation agent is further configured for receiving modified resource donation information from the host, wherein modified resource donation information is re-registered with the resource donation agent, further wherein the host modifies the resource donation information when a virtual machine on the host is terminated.

14. A host connected in a network, the host comprising:

a. a resource agent configured for;

i. computing resource donation information, wherein the resource donation information indicates the resources the host is ready to contribute; and

ii. registering the resource donation information with a centralized server; and

b. an operation agent configured for creating a virtual machine on the host based on the resource donation information, wherein the operation agent creates the virtual machine based on instructions received from the centralized server.

15. The host according to claim 14, wherein the resource donation information is registered with the centralized server at a predefined time interval.

16. The host according to claim 14, wherein the operation agent is further configured for terminating the virtual machine.

17. The host according to claim 14, wherein the resource agent is further configured for:

a. modifying the resource donation information when the virtual machine is terminated; and

b. re-registering the modified resource donation information with the centralized server.

18. The host according to claim 14, wherein the resource agent is further configured for releasing the resources associated with resource donation information of the host.

19. A computer program product for use with a stored program computer, the computer program product comprising a computer usable medium having a computer readable program code embodied therein for managing load in a network, the network comprising a first set of hosts, a second set of hosts that are under-utilized, and a centralized server, a virtual machine running on each of the first set of hosts, the computer readable program code performing the steps of:

a. receiving resource donation information from each of the second set of hosts, wherein the host registers the resource donation information with the centralized server;

b. identifying a load surge in the network, wherein the load surge indicates additional tasks to be performed by the first set of hosts and the second set of hosts;

c. negotiating with the second set of hosts when the load surge is identified, wherein the centralized sever negotiates with the second set of hosts for modification of the resource donation information;

d. determining one or more hosts from the second set of hosts, based on the resource donation information received from each of the second set of hosts and the identified load surge, wherein each of the one or more hosts creates a virtual machine based on the resource donation information, wherein the one or more hosts become a part of the first set of hosts; and

e. delegating the additional tasks among the first set of hosts.

20. The computer readable program code according to claim 19 further performing the step of identifying the decrease in the load in the network, wherein the decrease in the load indicates decrease in the number to tasks to be performed.

21. The computer readable program code according to claim 19 further performing the steps of:

a. terminating the virtual machine present on at least one host from the first set of hosts, wherein the at least one host releases the resources associated with the terminated virtual machine, further wherein the at least one host becomes a part of the second set of hosts; and

b. receiving modified resource donation information from the at least one host, wherein the modified resource donation information is re-registered with the centralized server.