Optimizing Distributed Computer Networks

• US 20120089664A1
• Filed: 10/12/2010
• Published: 04/12/2012
• Est. Priority Date: 10/12/2010
• Status: Active Grant

• Current Assignee: SAP SE
• Original Assignee: Sap Portals Israel Ltd (SAP SE)
• Inventors: Igelka, Or
• Granted Patent: US 8,838,830 B2
• Time in Patent Office: Days
• US Class Current: 709/203
• CPC Class Codes: G06F 9/5083 Techniques for rebalancing the load in a distributed system
• CPC Class Codes: H04L 41/0883 Semiautomatic configuration, e.g. proposals from system
• CPC Class Codes: H04L 45/22 Alternate routing
• CPC Class Codes: H04L 67/1031 Controlling of the operation of servers by a load balancer, e.g. adding or removing servers that serve requests

Abstract

In one general embodiment, a computer-implemented method for managing a distributed computer network performed by one or more processors includes the steps of: receiving a request from a client in the distributed computer network for a network service; optimizing a delivery of the requested network service to the client from a server in the distributed computer network; and monitoring an execution of the delivery of the network service.

Claims

1. A computer-implemented method for managing a distributed computer network, the method comprising the following steps performed by one or more processors:

receiving a request from a client in the distributed computer network for a network service;

optimizing a delivery of the requested network service to the client from a server in the distributed computer network; and

monitoring an execution of the delivery of the network service.

2. The computer-implemented method of claim 1, wherein optimizing a delivery of the requested network service to the client from the server comprises at least one of:

balancing a load between the client and the server in the distributed computer network;

bypassing a first communication pathway between the client and the server to deliver the requested network service via a second communication pathway between the client and the server;

providing a suggested adjustment of at least one attribute of the distributed computer network to an administrator of the network; and

automatically applying a dynamic adjustment to the distributed computer system.

3. The computer-implemented method of claim 2, wherein providing a suggested adjustment of at least one attribute of the distributed computer network to an administrator of the network comprises:

monitoring the at least one attribute of the distributed computer network;

comparing the monitored attribute to at least one predefined objective; and

based on the comparison, providing the suggested adjustment of the distributed computer network to the administrator of the network

4. The computer-implemented method of claim 3, wherein the at least one attribute is a measurement of the delivery of the requested network service.

5. The computer-implemented method of claim 3, wherein the suggested adjustment comprises at least one of:

a suggestion to add a node to the distributed computer network;

a suggestion to add a new communication pathway between at least two existing nodes in the distributed computer network; and

a suggestion to add a new network service available on the distributed computer network;

a suggestion to modify an existing network service available on the distributed computer network;

a suggestion to adjust a variable related to the first communication pathway;

a suggestion to remove one or more nodes from the distributed computer network;

a suggestion to remove one or more communication pathways from the distributed computer network; and

a suggestion to remove one or more network services from the distributed computing network.

6. The computer-implemented method of claim 3, wherein comparing the monitored attribute to at least one predefined objective comprises:

defining an objective function comprising at least one variable representative of the distributed computer network;

defining at least one constraint on the variable; and

solving the objective function to determine a value of the variable within the constraint.

7. The computer-implemented method of claim 6, wherein solving the objective function to determine a value of the variable within the constraint comprises:

solving one of a minimization or a maximization of the objective function to determine the value of the variable within the constraint.

8. The computer-implemented method of claim 6, wherein solving the objective function to determine a value of the variable within the constraint comprises:

solving the objective function to determine a value of the variable within the constraint using at least one of a linear programming algorithm and an integer programming algorithm.

9. The computer-implemented method of claim 2, wherein bypassing a first communication pathway between the client and the server to deliver the requested network service via a second communication pathway between the client and the server comprises:

determining that the requested network service stored on the server cannot be delivered through the first communication pathway;

identifying the second communication pathway between the client and the server; and

delivering the requested network service from the server to the client via the second communication pathway.

10. The computer-implemented method of claim 9, further comprising:

identifying an event in the distributed computer network on the first communication pathway, the event communicably decoupling the client and the server within the first communication pathway;

determining the second communication pathway between the client and the server that does not include the event; and

establishing the second communication pathway between the client and the server.

11. The computer-implemented method of claim 10, further comprising:

determining that the identified event is within a predefined class of events;

identifying a predefined responsive action associated with the predefined class of events; and

initiating the predefined responsive action.

12. The computer-implemented method of claim 11, wherein the responsive action comprises at least one of:

establishing the second communication pathway between the client and the server;

notifying an administrator of the distributed computer network of the identified event;

establishing a third communication pathway between the client and a second server; and

providing a suggestion to the administrator to add a fourth communication pathway.

13. The computer-implemented method of claim 12, further comprising:

in response to the provided suggestion, receiving a command to establish the fourth communication pathway; and

establishing the fourth communication pathway between the client and the server in the distributed computer network.

14. The computer-implemented method of claim 10, further comprising:

subsequent to establishing the second communication pathway between the client and the server, determining that the event is completed such that the client and the server are communicably coupled within the first communication pathway;

receiving a second request from the client in the distributed computer network for the network service; and

delivering the requested network service to the client from the server via the first communication pathway.

15. The computer-implemented method of claim 2, wherein balancing a load between the client and the server in the distributed computer network comprises:

monitoring the load on a first node in the distributed computer network between the client and the server, the load associated with delivery of network services through the first node;

determining that the load exceeds a predetermined threshold; and

delivering the requested network service from the server to the client through a second node distinct from the first node.

16. The computer-implemented method of claim 2, wherein balancing a load between the client and the server in the distributed computer network comprises:

balancing a load between two or more communication pathways in the distributed computer network.

17. The computer-implemented method of claim 16, wherein balancing a load between two or more communication pathways in the distributed computer network comprises:

monitoring a first load on a first communication pathway between the client and the server;

monitoring a second load on a second communication pathway between the client and the server, the first and second loads associated with delivery of network services on the respective first and second communication pathways;

determining that the first load exceeds the second load; and

based on the determination, delivering the requested network service from the server to the client via the second communication pathway.

18. The computer-implemented method of claim 17, wherein the first communication pathway comprises a first server communicably coupled to a first server front end that is communicably coupled to the client;

and

the second communication pathway comprises the first server communicably coupled to a second server front end that is communicably coupled to the client, and

wherein delivering the requested network service from the server to the client via the second communication pathway comprises delivering at least a portion of the requested network service from the first server to the client through the second server front end.

19. The computer-implemented method of claim 18, further comprising:

delivering another portion of the requested network service from the first server to the client through the first server front end substantially simultaneous to delivering the portion of the requested network service from the first server to the client through the second server front end.

20. The computer-implemented method of claim 17, wherein the first communication pathway comprises a first server communicably coupled to a first server front end that is communicably coupled to the client;

and

the second communication pathway comprises a second server communicably coupled to the first server front end that is communicably coupled to the client, and

wherein delivering the requested network service from the server to the client via the second communication pathway comprises delivering at least a portion of the requested network service from the second server to the client through the first server front end.

21. The computer-implemented method of claim 20, further comprising:

delivering another portion of the requested network service from the first server to the client through the first server front end substantially simultaneous to delivering the portion of the requested network service from the second server to the client through the first server front end.

22. The computer-implemented method of claim 1, wherein monitoring an execution of the delivery of the network service comprises:

monitoring, in real-time, a plurality of attributes associated with the execution of the delivery of the network service; and

graphically presenting at least one of the plurality of monitored attributes to an administrator of the distributed computing network.

23. The computer-implemented method of claim 1, wherein monitoring an execution of the delivery of the network service comprises:

routing the request to a first node in the distributed computer network, the first node comprising a first optimizing engine operable to monitor delivery and execution of the requested network service and display a first group of data associated with the delivery and execution of the requested network service through a first user interface;

routing the request to a second node in the distributed computer network, the second node comprising a second optimizing engine operable to monitor delivery and execution of the requested network service and display a second group of data associated with the delivery and execution of the requested network service through a second user interface. the second group of data different than the first group of data; and

synchronizing the first optimizing engine with the second optimizing engine such that data displayed on the first user interface matches data displayed on the second user interface.

24. The computer-implemented method of claim 23, further comprising:

identifying a first configuration of the first node;

identifying a second first configuration of the second node; and

synchronizing the first optimizing engine with the second optimizing engine such that the first and second configurations are substantially identical.

25. The computer-implemented method of claim 2, wherein the dynamic adjustment to the distributed computer system comprises at least one of:

adding a node to the distributed computer network;

adding a new communication pathway between at least two existing nodes in the distributed computer network; and

adding a new network service available on the distributed computer network;

modifying an existing network service available on the distributed computer network;

adjusting a variable related to the first communication pathway;

removing one or more nodes from the distributed computer network;

removing one or more communication pathways from the distributed computer network; and

removing one or more network services from the distributed computing network.

26. The computer-implemented method of claim 2, further comprising:

notifying an administrator of the distributed computing system of the dynamic adjustment.

27. An apparatus comprising at least one non-transitory, computer-readable storage medium storing instructions operable, when executed by at least one processor, to perform operations for managing a distributed computer network, the operations comprising:

receiving a request from a client in the distributed computer network for a network service;

optimizing a delivery of the requested network service to the client from a server in the distributed computer network; and

monitoring an execution of the delivery of the network service.

28. The apparatus of claim 27, wherein optimizing a delivery of the requested network service to the client from the server comprises at least one of:

balancing a load between the client and the server in the distributed computer network;

bypassing a first communication pathway between the client and the server to deliver the requested network service via a second communication pathway between the client and the server;

providing a suggested adjustment of at least one attribute of the distributed computer network to an administrator of the network; and

automatically applying a dynamic adjustment to the distributed computer system.

29. The apparatus of claim 28, wherein providing a suggested adjustment of at least one attribute of the distributed computer network to an administrator of the network comprises:

monitoring the at least one attribute of the distributed computer network;

comparing the monitored attribute to at least one predefined objective; and

based on the comparison, providing the suggested adjustment of the distributed computer network to the administrator of the network

30. The apparatus of claim 28, wherein bypassing a first communication pathway between the client and the server to deliver the requested network service via a second communication pathway between the client and the server comprises:

determining that the requested network service stored on the server cannot be delivered through the first communication pathway;

identifying the second communication pathway between the client and the server; and

delivering the requested network service from the server to the client via the second communication pathway.

31. The apparatus of claim 28, wherein balancing a load between the client and the server in the distributed computer network comprises:

monitoring the load on a first node in the distributed computer network between the client and the server, the load associated with delivery of network services through the first node;

determining that the load exceeds a predetermined threshold;

delivering the requested network service from the server to the client through a second node distinct from the first node.

32. The apparatus of claim 28, balancing a load between the client and the server in the distributed computer network comprises:

balancing a load between two or more communication pathways in the distributed computer network.

33. The apparatus of claim 32, wherein balancing a load between two or more communication pathways in the distributed computer network comprises:

monitoring a first load on a first communication pathway between the client and the server;

monitoring a second load on a second communication pathway between the client and the server, the first and second loads associated with delivery of network services on the respective first and second communication pathways;

determining that the first load exceeds the second load; and

based on the determination, delivering the requested network service from the server to the client via the second communication pathway.

34. The apparatus of claim 27, wherein monitoring an execution of the delivery of the network service comprises:

monitoring, in real-time, a plurality of attributes associated with the execution of the delivery of the network service; and

graphically presenting at least one of the plurality of monitored attributes to an administrator of the distributed computing network.

35. The apparatus of claim 27, wherein monitoring an execution of the delivery of the network service comprises:

routing the request to a first node in the distributed computer network, the first node comprising a first optimizing engine operable to monitor delivery and execution of the requested network service and display a first group of data associated with the delivery and execution of the requested network service through a first user interface;

routing the request to a second node in the distributed computer network, the second node comprising a second optimizing engine operable to monitor delivery and execution of the requested network service and display a second group of data associated with the delivery and execution of the requested network service through a second user interface. the second group of data different than the first group of data; and

synchronizing the first optimizing engine with the second optimizing engine such that data displayed on the first user interface matches data displayed on the second user interface.

36. The apparatus of claim 35, the operations further comprising:

identifying a first configuration of the first node;

identifying a second first configuration of the second node; and

synchronizing the first optimizing engine with the second optimizing engine such that the first and second configurations are substantially identical.

37. The apparatus of claim 28, wherein the dynamic adjustment to the distributed computer system comprises at least one of:

adding a node to the distributed computer network;

adding a new communication pathway between at least two existing nodes in the distributed computer network; and

adding a new network service available on the distributed computer network;

modifying an existing network service available on the distributed computer network;

adjusting a variable related to the first communication pathway;

removing one or more nodes from the distributed computer network;

removing one or more communication pathways from the distributed computer network; and

removing one or more network services from the distributed computing network.

38. The apparatus of claim 28, the operations further comprising:

notifying an administrator of the distributed computing system of the dynamic adjustment.