Flexible network load balancing

• US 7,590,736 B2
• Filed: 06/30/2003
• Issued: 09/15/2009
• Est. Priority Date: 06/30/2003
• Status: Expired due to Fees

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Joy, Joseph M., Welland, Robert V., Hydrie, Aamer
• Primary Examiner(s): Caldwell; Andrew
• Assistant Examiner(s): MacIlwinen; John M
• Application Number:
  US10/610,506
• Publication Number:
  US 20040267920A1
• Time in Patent Office: 2,269 Days
• Field of Search: 710/223, 710/203, 710/226, 710/229, 709/223, 709/203, 709/226, 709/229
• US Class Current: 709/226
• CPC Class Codes: H04L 67/1001 for accessing one among a plurality of replicated servers
• CPC Class Codes: H04L 67/1008 based on parameters of servers, e.g. available memory or workload monitoring of computer activity G06F11/30
• CPC Class Codes: H04L 67/101 based on network conditions
• CPC Class Codes: H04L 67/1017 based on a round robin mechanism
• CPC Class Codes: H04L 9/40 Network security protocols

Abstract

In an exemplary media implementation, one or more processor-accessible media include processor-executable instructions that, when executed, enable a system to facilitate actions including: operating network load balancing infrastructure in a first configuration; scaling out the network load balancing infrastructure; and operating the scaled-out network load balancing infrastructure in at least one other configuration. In another exemplary media implementation, one or more processor-accessible media include processor-executable instructions that, when executed, enable a system to be configured such that different percentages of system resources may be allocated to different network-load-balancing functions. In one embodiment, the scaling out includes moving at least a portion of network-load-balancing functionality from a device that executes host functionality to another device, that does not execute host functionality and routing network traffic from the other device to the host functionality executing on the device.

Claims

1. A method for flexible network load balancing, the method comprising:

operating network load balancing infrastructure in a first configuration that includes forwarding functionality, classifying functionality, and session tracking functionality at a first resource distribution allocation;

the first resource distribution allocation to allocate first, second, and third percentages of load balancing resources to the forwarding functionality, the classifying functionality, and the session tracking functionality, respectively;

wherein the first configuration comprises, at least in part, a device that executes host functionality;

scaling out the network load balancing infrastructure by adjusting from the first configuration at the first resource distribution allocation to a second configuration at a second resource distribution allocation; and

operating the scaled-out network load balancing infrastructure in the second configuration that includes the forwarding functionality, the classifying functionality, and the session tracking functionality at the second resource distribution allocation;

the second resource distribution allocation to allocate fourth, fifth, and sixth percentages of the load balancing resources to the forwarding functionality, the classifying functionality, and the session tracking functionality, respectively;

wherein the second configuration comprises, at least in part, another device that does not execute host functionality;

wherein;

the scaling out comprises moving at least a portion of network-load-balancing functionality from the device that executes host functionality to the other device, that does not execute host functionality;

the operating network load balancing infrastructure comprises routing network traffic internally within the device to the host functionality executing thereon; and

the operating the scaled-out network load balancing infrastructure comprises routing network traffic from the other device to the host functionality executing on the device.

2. The method as recited in claim 1, wherein the scaling out comprises at least one of:

moving an individual network load balancing functionality to a new device, adding a component to which an individual network load balancing functionality is directed, or increasing allocated resources that are devoted to an individual network load balancing functionality.

3. The method as recited in claim 1, wherein the first and second resource distribution allocations each comprise a set of resources that include one or more of:

(i) a device, (ii) a plurality of devices, (iii) a number of processor cycles on at least one device, (iv) an amount of memory available for consumption, and (v) a level of available network bandwidth.

4. The method as recited in claim 1, wherein the first resource distribution allocation and the second resource distribution allocation are to allocate load balancing resources to one or more load balancing functionalities selected from the group comprising:

request routing, health and/or load handling, and connection migrating.

5. One or more processor-accessible storage media comprising processor-executable instructions that, when executed, direct a system to perform the method as recited in claim 1.

6. The method as recited in claim 1, wherein the scaling out comprises:

adding at least one network-load-balancing functional component to the network load balancing infrastructure to produce the scaled-out network load balancing infrastructure.

7. The method as recited in claim 6, wherein the scaling out further comprises:

adding at least two network-load-balancing functional components to the network load balancing infrastructure to produce the scaled-out network load balancing infrastructure.

8. The method as recited in claim 7, wherein the adding at least two network-load-balancing functional components comprises:

adding the at least two network-load-balancing functional components of a single network-load-balancing functional type.

9. The method as recited in claim 7, wherein the adding at least two network-load-balancing functional components comprises:

adding the at least two network-load-balancing functional components of different network-load-balancing functional types.

10. The method as recited in claim 6, wherein the adding comprises:

adding the at least one network-load-balancing functional component, wherein the added at least one network-load-balancing functional component comprises at least part of one or more devices.

11. The method as recited in claim 6, wherein the adding comprises:

adding the at least one network-load-balancing functional component, wherein the added at least one network-load-balancing functional component is selected from the group comprising;

a request router, a health and/or load handler, and a connection migrator.

12. The method as recited in claim 6, wherein:

the operating network load balancing infrastructure comprises routing network traffic utilizing a plurality of network-load-balancing functional components that do not include the added at least one network-load-balancing functional component; and

the operating the scaled-out network load balancing infrastructure comprises routing network traffic utilizing the plurality of network-load-balancing functional components and the added at least one network-load-balancing functional component.

13. The method as recited in claim 1, wherein the moving comprises:

moving the at least a portion of network-load-balancing functionality by transferring software from the device that executes host functionality to the other device that does not execute host functionality.

14. The method as recited in claim 1, wherein the scaling out further comprises:

moving at least one network-load-balancing functional component from the device that executes host functionality to the other device that does not execute host functionality.

15. The method as recited in claim 14, wherein the moving at least one network-load-balancing functional component comprises:

moving a forwarder and a classifier from the device that executes host functionality to the other device that does not execute host functionality.

16. The method as recited in claim 1, wherein the scaling out comprises:

adding a device to the network load balancing infrastructure to produce the scaled-out network load balancing infrastructure; and

distributing network-load-balancing functionality onto the added device.

17. The method as recited in claim 16, wherein:

the operating network load balancing infrastructure comprises load balancing network traffic using a plurality of devices that does not include the added device; and

the operating the scaled-out network load balancing infrastructure comprises load balancing network traffic using the plurality of devices and the added device.

18. One or more processor-accessible storage media comprising processor-executable instructions that, when executed, enable a system to facilitate actions comprising:

operating network load balancing infrastructure in a first configuration that includes forwarding functionality, classifying functionality, and session tracking functionality at a first resource distribution allocation;

the first resource distribution allocation to allocate first, second, and third percentages of load balancing resources to the forwarding functionality, the classifying functionality, and the session tracking functionality, respectively;

wherein the first configuration comprises, at least in part, a device that executes host functionality, wherein the operating network load balancing infrastructure comprises routing, at least occasionally, network traffic internally within the device to the host functionality executing thereon;

scaling out the network load balancing infrastructure by adjusting from the first configuration at the first resource distribution allocation to a second configuration at a second resource distribution allocation, wherein the scaling out comprises moving at least a portion of network-load-balancing functionality from the device that executes host functionality to another device that does not execute host functionality; and

operating the scaled-out network load balancing infrastructure in the second configuration that includes the forwarding functionality, the classifying functionality, and the session tracking functionality at the second resource distribution allocation;

the second resource distribution allocation to allocate fourth, fifth, and sixth percentages of the load balancing resources to the forwarding functionality, the classifying functionality, and the session tracking functionality, respectively;

wherein the second configuration comprises, at least in part, the other device that does not execute host functionality, wherein the operating the scaled-out network load balancing infrastructure comprises routing, at least occasionally, network traffic from the other device to the host functionality executing on the device.

19. The one or more processor-accessible storage media as recited in claim 18, wherein the action of scaling out comprises at least one action of:

moving an individual network load balancing functionality to a new device, adding a component to which an individual network load balancing functionality is directed, or increasing allocated resources that are devoted to an individual network load balancing functionality.

20. The one or more processor-accessible storage media as recited in claim 18, wherein the first and second resource distribution allocations each comprise a set of resources that include one or more of:

(i) a device, (ii) a plurality of devices, (iii) a number of processor cycles on at least one device, (iv) an amount of memory available for consumption, and (v) a level of available network bandwidth.

21. The one or more processor-accessible storage media as recited in claim 18, wherein the first resource distribution allocation and the second resource distribution allocation are to allocate load balancing resources to one or more load balancing functionalities selected from the group comprising:

request routing, health and/or load handling, and connection migrating.

22. The one or more processor-accessible storage media as recited in claim 18, wherein at least a portion of the processor-executable instructions comprise at least part of network load balancing software.

23. The one or more processor-accessible storage media as recited in claim 18, wherein the action of scaling out comprises an action of:

adding at least one network-load-balancing functional component to the network load balancing infrastructure to produce the scaled-out network load balancing infrastructure.

24. The one or more processor-accessible storage media as recited in claim 23, wherein the action of scaling out further comprises an action of:

adding at least two network-load-balancing functional components to the network load balancing infrastructure to produce the scaled-out network load balancing infrastructure.

25. The one or more processor-accessible storage media as recited in claim 24, wherein the action of adding at least two network-load-balancing functional components comprises an action of:

adding the at least two network-load-balancing functional components of a single network-load-balancing functional type.

26. The one or more processor-accessible storage media as recited in claim 24, wherein the action of adding at least two network-load-balancing functional components comprises an action of:

adding the at least two network-load-balancing functional components of different network-load-balancing functional types.

27. The one or more processor-accessible storage media as recited in claim 23, wherein the action of adding comprises an action of:

adding the at least one network-load-balancing functional component, wherein the added at least one network-load-balancing functional component comprises at least part of one or more devices.

28. The one or more processor-accessible storage media as recited in claim 23, wherein the action of adding comprises an action of:

adding the at least one network-load-balancing functional component, wherein the added at least one network-load-balancing functional component is selected from the group comprising;

a request router, a health and/or load handler, and a connection migrator.

29. The one or more processor-accessible storage media as recited in claim 23, wherein:

the action of operating network load balancing infrastructure comprises an action of routing network traffic utilizing a plurality of network-load-balancing functional components that do not include the added at least one network-load-balancing functional component; and

the action of operating the scaled-out network load balancing infrastructure comprises an action of routing network traffic utilizing the plurality of network-load-balancing functional components and the added at least one network-load-balancing functional component.

30. The one or more processor-accessible storage media as recited in claim 18, wherein the action of moving comprises an action of:

moving the at least a portion of network-load-balancing functionality by transferring processor-executable instructions from the device that executes host functionality to the other device that does not execute host functionality.

31. The one or more processor-accessible storage media as recited in claim 18, wherein the action of scaling out further comprises an action of:

moving at least one network-load-balancing functional component from the device that executes host functionality to the other device that does not execute host functionality.

32. The one or more processor-accessible storage media as recited in claim 31, wherein the action of moving at least one network-load-balancing functional component comprises an action of:

moving a forwarder and a classifier from the device that executes host functionality to the other device that does not execute host functionality.

33. The one or more processor-accessible storage media as recited in claim 18, wherein the action of scaling out comprises actions of:

adding a device to the network load balancing infrastructure to produce the scaled-out network load balancing infrastructure; and

distributing network-load-balancing functionality onto the added device.

34. The one or more processor-accessible storage media as recited in claim 33, wherein:

the action of operating network load balancing infrastructure comprises an action of load balancing network traffic using a plurality of devices that does not include the added device; and

the action of operating the scaled-out network load balancing infrastructure comprises an action of load balancing network traffic using the plurality of devices and the added device.

35. The one or more processor-accessible storage media as recited in claim 18 comprising the processor-executable instructions that, when executed, enable the system to be configured such that different percentages of system resources may be allocated to different ones of the load balancing resources that are used to implement network-load-balancing functionality of the network load balancing infrastructure.

36. The one or more processor-accessible storage media as recited in claim 35, wherein the processor-executable instructions, when executed, further enable system resource allocations to the different network-load-balancing functionality to be changed from time to time.

37. The one or more processor-accessible storage media as recited in claim 36, wherein the processor-executable instructions, when executed, further enable changes to the system resource allocations to be performed while network load balancing is occurring.

38. The one or more processor-accessible storage media as recited in claim 18 comprising the processor-executable instructions that, when executed, enable the system to gradually increase a percentage of total computing resources that is devoted to the network load balancing infrastructure.

39. The one or more processor-accessible storage media as recited in claim 38, wherein the system comprises at least part of the device in the first configuration and at least part of the other device in the second configuration.

40. The one or more processor-accessible storage media as recited in claim 38, wherein at least a portion of the total computing resources that is not devoted to the network load balancing infrastructure is devoted to application hosting.

41. A system comprising:

a processor;

a memory coupled to the processor, the memory comprising instructions configured to direct the processor to implement network-load-balancing functionality;

a plurality of network-load-balancing functional components that form at least part of a network load balancing infrastructure using load balancing resources;

the plurality of network-load-balancing functional components including forwarding functionality, classifying functionality, and session tracking functionality; and

wherein;

the network load balancing infrastructure is capable of being scaled out by adjusting from a first configuration at a first resource distribution allocation of the plurality of network-load-balancing functional components to a second configuration at a second resource distribution allocation of the plurality of network-load-balancing functional components;

to operate the network load balancing infrastructure in the first configuration includes the forwarding functionality, the classifying functionality, and the session tracking functionality at the first resource distribution allocation;

the first resource distribution allocation to allocate first, second, and third percentages of the load balancing resources to the forwarding functionality, the classifying functionality, and the session tracking functionality, respectively;

to operate the scaled-out network load balancing infrastructure in the second configuration includes the forwarding functionality, the classifying functionality, and the session tracking functionality at the second resource distribution allocation;

the second resource distribution allocation to allocate fourth, fifth, and sixth percentages of the load balancing resources to the forwarding functionality, the classifying functionality, and the session tracking functionality, respectively;

the first configuration comprises, at least in part, a device that executes host functionality; and

the second configuration comprises, at least in part, another device that does not execute host functionality;

the scaled-out network moves at least a portion of network-load-balancing functionality from the device that executes host functionality to the other device that does not execute host functionality;

the network load balancing infrastructure routes, at least occasionally, network traffic internally within the device to the host functionality executing thereon; and

the scaled-out network load balancing infrastructure routes at least occasionally, network traffic from the other device to the host functionality executing on the device.

42. The system as recited in claim 41, wherein the scaling out of the network load balancing infrastructure comprises at least one of:

moving an individual network load balancing functionality to a new device, adding a component to which an individual network load balancing functionality is directed, or increasing allocated resources that are devoted to an individual network load balancing functionality.

43. The system as recited in claim 41, wherein the load balancing resources of the system comprise one or more of device resources, processor resources, memory resources, and network resources.

44. The system as recited in claim 41, wherein the first resource distribution allocation and the second resource distribution allocation are to allocate the load balancing resources to one or more other network-load-balancing functional components selected from the group comprising:

request routing, health and/or load handling, and connection migrating.

45. The system as recited in claim 41, wherein the network load balancing infrastructure is adapted to move at least one network-load-balancing functional component of the plurality of network-load-balancing functional components from a device that executes host functionality to another device that does not execute host functionality.

46. The system as recited in claim 41, wherein the system comprises the device and the other device with network load balancing code executing on both the device and the other device.

47. The system as recited in claim 41, wherein the system comprises a plurality of devices and network load balancing code, the network load balancing code executing on the plurality of devices in a distributed fashion.

48. The system as recited in claim 41, wherein the network load balancing infrastructure is adapted (i) to enable adding the other device to the network load balancing infrastructure to produce the second configuration from the first configuration and (ii) to distribute network-load-balancing functionality that is selected from the plurality of network-load-balancing functional components onto the added other device.

49. An arrangement for flexible network load balancing that includes one or more processor-accessible storage media, the arrangement comprising:

means for configuring network load balancing infrastructure into a first configuration that includes forwarding functionality, classifying functionality, and session tracking functionality at a first resource distribution allocation;

the first resource distribution allocation to allocate first, second, and third percentages of load balancing resources to the forwarding functionality, the classifying functionality, and the session tracking functionality, respectively;

wherein the first configuration comprises, at least in part, a device that executes host functionality, wherein the means for configuring the network load balancing infrastructure comprises a means for routing, at least occasionally, network traffic internally within the device to the host functionality executing thereon;

means for scaling out the network load balancing infrastructure by adjusting from the first configuration at the first resource distribution allocation to a second configuration at a second resource distribution allocation, wherein the means for scaling out comprises a means for moving at least a portion of network-load-balancing functionality from the device that executes host functionality to another device that does not execute host functionality; and

means for configuring the scaled-out network load balancing infrastructure into the second configuration that includes the forwarding functionality, the classifying functionality, and the session tracking functionality at the second resource distribution allocation;

the second resource distribution allocation to allocate fourth, fifth, and sixth percentages of the load balancing resources to the forwarding functionality, the classifying functionality, and the session tracking functionality, respectively;

wherein the second configuration comprises, at least in part, the other device that does not execute host functionality, wherein the means for configuring the scaled-out network load balancing infrastructure comprises a means for routing, at least occasionally, network traffic from the other device to the host functionality executing on the device.

50. The arrangement as recited in claim 49, wherein the means for scaling out comprises at least one of:

means for moving an individual network load balancing functionality to a new device, means for adding a component to which an individual network load balancing functionality is directed, or means for increasing allocated resources that are devoted to an individual network load balancing functionality.

51. The arrangement as recited in claim 49, wherein the means for scaling out comprises:

means for adding at least one network-load-balancing functional component to the network load balancing infrastructure to produce the scaled-out network load balancing infrastructure;

the at least one network-load-balancing functional component selected from the group comprising;

request routing, health and/or load handling, and connection migrating.

52. The arrangement as recited in claim 49, wherein the first and second resource distribution allocations each comprise a set of resources that include one or more of:

(i) a device, (ii) a plurality of devices, (iii) a number of processor cycles on at least one device, (iv) an amount of memory available for consumption, and (v) a level of available network bandwidth.

53. The arrangement as recited in claim 49, wherein the means for scaling out comprises:

means for adding the other device to the network load balancing infrastructure to produce the scaled-out network load balancing infrastructure; and

means for distributing network-load-balancing functionality onto the added other device.

54. The arrangement as recited in claim 49, wherein the arrangement comprises the device and the other device.

55. The arrangement as recited in claim 49, wherein the arrangement comprises the one or more processor-accessible storage media.