System and method for risk-aware server load balancing

Patent metadata

Field	Value
Publication number	US-2018227361-A1
Application number	US-201815943898-A
Country	US
Kind code	A1
Filing date	Apr 3, 2018
Priority date	Oct 9, 2015
Publication date	Aug 9, 2018
Grant date	—

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.

First claim

1 - 20 . (canceled)

21 . A server included within a server duster 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 resource load and a failure rate, the failure rate being associated with a frequency of server failures since being added to the server cluster;
receive a workload assigned by the load balancer;
process the assigned workload; and
provide, to the load balancer, a workload value status updated based on the processed workload.

22 . The server of claim 21 , wherein the processor is further configured to:
provide an updated real-time resource load value and an updated real-time failure rate to the load balancer.

23 . The server of claim 21 , wherein the workload value status is calculated based on the cumulative workload value of all workloads in-progress at the server.

24 . The server of claim 21 , wherein the workload value status comprises a report of individual workload values for each workload assigned to the server.

25 . The server of claim 21 , 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.

26 . The server of claim 21 , wherein the failure rate increases proportionally or exponentially with additional server failures.

27 . The server of claim 21 , 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.

28 . The server of claim 21 , 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.

29 . 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 resource load and a failure rate, the failure rate being associated with a frequency of server failures since being added to the server cluster; receiving, at the server, a workload assigned by the load balancer; processing, by the server, the assigned workload; and providing, by the server to the load balancer, a workload value status updated based on the processed workload.

30 . The method of claim 29 , further comprising:
providing, by the server, an updated real-time resource load value and updated real-time failure rate to the load balancer.

31 . The method of claim 29 , wherein the workload value status is calculated based on the cumulative workload value of all workloads in-progress at the server.

32 . The method of claim 29 , wherein the workload value status comprises a report of individual workload values for each workload assigned to the server.

33 . The method of claim 29 , 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.

34 . The method of claim 29 , wherein the failure rate increases proportionally or exponentially with additional server failures.

35 . The method of claim 29 , 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.

36 . The method of claim 29 , 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.

37 . 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 resource load and a failure rate, the failure rate being associated with a frequency of server failures since being added to the server duster; receiving, at the server, a workload assigned by the load balancer; processing, by the server, the assigned workload; and providing, by the server to the load balancer, an updated workload value status updated based on the processed workload.

38 . The non-transitory computer readable medium of claim 37 , where the operations further comprise:
providing, by the server, an updated real-time resource load value and updated real-time failure rate to the load balancer.

39 . The non-transitory computer readable medium of claim 37 , 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.

40 . The non-transitory computer readable medium of claim 37 , 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.

Assignees

• Capital One Services Llc

Inventors

• Tao Tao
• Bardwaj Santosh
• Yoo Ii Sun
• Tang Yihui
• GERSTLE Jeremy

Classifications

• H04L67/1029 Primary

  using data related to the state of servers by a load balancer · CPC title

• H04L67/322

  Electricity · mapped topic

• H04L67/1002 Primary

  Electricity · mapped topic

• H04L67/16

  Electricity · mapped topic