System and method for risk-aware server load balancing

• US 10,334,036 B2
• Filed: 04/03/2018
• Issued: 06/25/2019
• Est. Priority Date: 10/09/2015
• Status: Active Grant

• Current Assignee: Capital One Services LLC (Capital One Financial Corporation)
• Original Assignee: Capital One Services LLC (Capital One Financial Corporation)
• Inventors: Tao, Tao, Bardwaj, Santosh, Yoo, Ii Sun, Tang, Yihui, Gerstle, Jeremy
• Primary Examiner(s): Meky, Moustafa M
• Assistant Examiner(s): Kassa, Elizabeth
• Application Number:
  US15/943,898
• Publication Number:
  US 20180227361A1
• Time in Patent Office: 448 Days
• Field of Search: 709226
• CPC Class Codes: H04L 67/1029 using data related to the state of servers by a load balancer

Abstract

Systems and methods are provided for managing server loads that accounts for various measures of risk associated with different workloads assigned to servers. The systems and methods may include a memory storing instructions for server load management operations, and a processor configured to execute the stored instructions. The processor may receive a workload, determine a value associated with the workload indicating a predetermined importance of the workload, receive information for a plurality of active servers in a server cluster associated with the processor, determine risk levels associated with the active servers based on the received information, and assign the received workload to one of the active servers based on the determined value and the determined risk levels.

Claims

1. A server included within a server cluster managed by a load balancer, the server comprising:

a memory storing instructions for server load management operations; and

a processor configured to execute the stored instructions, to;

receive a query from the load balancer;

provide, to the load balancer, a real-time cumulative resource load, a real-time cumulative workload value status, and a failure rate, the failure rate being associated with a frequency of server failures;

receive a workload assigned by the load balancer to the server based on the real-time cumulative resource load, the real-time cumulative workload value status, the failure rate, and a workload value associated with the workload;

process the assigned workload;

provide, to the load balancer, a workload value status updated based on the processed workload; and

provide an updated real-time cumulative resource load, an updated real-time cumulative value status, and an updated failure rate to the load balancer.

2. The server of claim 1, wherein the workload value status is calculated based on the cumulative workload value of all workloads in-progress at the server.

3. The server of claim 1, wherein the workload value status comprises a report of individual workload values for each workload assigned to the server.

4. The server of claim 1, wherein the processor is configured to process the assigned workload by:

parsing the assigned workload into one or more tasks;

executing the parsed tasks;

storing task results; and

providing workload results to a remote location.

5. The server of claim 1, wherein the failure rate increases proportionally or exponentially with additional server failures.

6. The server of claim 1, wherein, upon detection of a server failure, the processor is further configured to:

determine if the server failure is recoverable;

reset the server by one of the server, an external machine, or an individual responsive to a determination that the server failure is recoverable; and

provide an updated server failure rate to the load balancer.

7. The server of claim 1, wherein, upon detection of a server failure, the processor is further configured to:

determine if the server failure is recoverable; and

remove the server from the server cluster responsive to a determination that the server failure is not recoverable.

8. A method for operating a server included within a server cluster managed by a load balancer, the method comprising:

receiving, at a server in a server cluster, a query from a load balancer;

providing, from the server to the load balancer, a real-time cumulative resource load, a real-time cumulative workload value status, and a failure rate, the failure rate being associated with a frequency of server failures;

receiving, at the server, a workload assigned by the load balancer to the real-time cumulative resource load, the real-time cumulative workload value status, the failure rate, and a workload value associated with the workload;

processing, by the server, the assigned workload;

providing, by the server to the load balancer, a workload value status updated based on the processed workload; and

providing, by the server to the load balancer, an updated real-time cumulative resource load, an updated real-time cumulative value status, and an updated failure rate to the load balancer.

9. The method of claim 8, wherein the workload value status is calculated based on the cumulative workload value of all workloads in-progress at the server.

10. The method of claim 8, wherein the workload value status comprises a report of individual workload values for each workload assigned to the server.

11. The method of claim 8, wherein processing the assigned workload comprises:

parsing the assigned workload into one or more tasks;

executing the parsed tasks;

storing task results; and

providing workload results to a remote location.

12. The method of claim 8, wherein the failure rate increases proportionally or exponentially with additional server failures.

13. The method of claim 8, further comprising, upon detection of a server failure:

determining if the server failure is recoverable;

resetting the server by one of the server, an external machine, or an individual responsive to a determination that the server failure is recoverable; and

providing an updated server failure rate to the load balancer.

14. The method of claim 8, further comprising, upon detection of a server failure:

determining if the server failure is recoverable; and

removing, by the server, the server from the server cluster responsive to a determination that the server failure is not recoverable.

15. A non-transitory computer readable medium having stored instructions, which when executed, cause at least one processor to perform operations for controlling a server included within a server cluster managed by a load balancer, the operations comprising:

receiving, at a server in a server cluster, a query from a load balancer;

providing, from the server to the load balancer, a real-time cumulative resource load, a real-time cumulative workload value status, and a failure rate, the failure rate being associated with a frequency of server failures;

receiving, at the server, a workload assigned by the load balancer to the server based on the real-time cumulative resource load, the cumulative workload value status, the failure rate, and a workload value associated with the workload;

processing, by the server, the assigned workload;

providing, by the server to the load balancer, an updated workload value status updated based on the processed workload; and

providing, by the server to the load balancer, an updated real-time cumulative resource load, an updated real-time cumulative value status, and an updated failure rate to the load balancer.

16. The non-transitory computer readable medium of claim 15, where the operations further comprise, based on the determining a server failure:

determining, upon detection of a server failure, whether the server failure is recoverable;

resetting the server by one of the server, an external machine, or an individual responsive to a determination that the server failure is recoverable; and

providing an updated server failure rate to the load balancer.

17. The non-transitory computer readable medium of claim 15, where the operations further comprise:

determining, upon detection of a server failure, whether the server failure is recoverable; and

removing the server from the server cluster responsive to a determination that the server failure is not recoverable.