Method and system for performing load balancing across control planes in a data center

• US 7,933,983 B2
• Filed: 12/17/2002
• Issued: 04/26/2011
• Est. Priority Date: 12/17/2002
• Status: Active Grant

• Current Assignee: Hewlett Packard Enterprise Development LP (Hewlett-Packard Enterprise Company)
• Original Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Inventors: Hogan, Katherine, Schloss, Rheid, Steele, Doug
• Primary Examiner(s): Follansbee; John
• Assistant Examiner(s): Daftuar; Saket K
• Application Number:
  US10/320,461
• Publication Number:
  US 20040117476A1
• Time in Patent Office: 3,052 Days
• Field of Search: 709220-221, 709223-226, 709/230, 709/235, 709/239, 370/252, 370/254, 370/256, 370/392, 370/230, 370/236, 370/396, 370/401, 370/402, 370/443, 370/468
• US Class Current: 709/224
• CPC Class Codes: G06F 9/5083 Techniques for rebalancing the load in a distributed system

Abstract

A system and method analyzes resource usage within a utility data center (UDC) and recommends options to maximize efficient usage of these resources. Information is gathered about the current resources allocated to control planes within the UDC, including resource loads and threshold limits within each plane. Criteria used to analyze efficiency includes customer size and prioritization within the UDC, as well as, historical and trending information, and peak resource usage.

Claims

1. A system for load balancing network resources in a data center, comprising:

a plurality of virtual local area networks (VLANs) including first and second VLANs, wherein each VLAN comprises an independent network of components associated with its respective enterprise;

a control plane coupled to the first and second VLANs, wherein the control plane initially allocates a first set of network resources to the first VLAN and allocates a second set of network resources to the second VLAN based on enterprise requirements;

means for collecting performance metrics from the first set of network resources and second set of network resources, wherein the collected performance metrics comprise one or more of CPU usage, memory usage and throughput; and

means for performing load analysis using the collected performance metrics and corresponding pre-determined performance thresholds for load balancing the first and second set of network resources, wherein the control plane automatically reallocates a network resource from the first set of network resources to the second set of network resources if the collected performance metric associated with the network resource is less than its corresponding pre-determined performance threshold and if the network resource is required by the second VLAN.

2. The system as recited in claims 1, wherein the first and second set of resources comprise one or more of:

data processing resources, memory resources, printing resources, and data communication resources.

3. The system as recited in claims 1, wherein the control plane does not reallocate the network resource from the first set of network resources to the second set of network resources if the collected performance metric associated with the network resource is at or more than its corresponding pre-determined performance threshold or if the network resource is not required by the second VLAN.

4. The system as recited in claims 1, wherein the control plane reallocates a network resource from the second set of network resources to the first set of network resources if the collected performance metric associated with the network resource from the first set of network resources is at or more than its corresponding pre-determined performance threshold and if the network resource from the second set of network resources not required by the second VLAN.

5. The system as recited in claims 1, wherein the control plane automatically reallocates the network resource from the first set of network resources to the second set of network resources only if such reallocation is authorized.

6. The system as recited in claim 1, further comprising:

a monitoring tool to measure performance metrics associated with each resource from the first and second set of resources, wherein the monitoring tool provides the performance metrics to the means for collecting performance metrics.

7. The system as recited in claim 6, wherein the monitoring tool includes at least one tool selected from the group consisting of:

CPU usage monitor, disk usage monitor, throughput monitor, Input/output (I/O) monitor, and network traffic monitor.

8. The system as recited in claim 1, further comprising:

a network operations center (NOC) coupled to a plurality of control planes, wherein the NOC communicates with the plurality of control planes through one or more firewalls and wherein the NOC allocates resources between the plurality of control planes.

9. The system as recited in claim 8, further comprising:

a control plane management system associated with the control plane, wherein the NOC communicates with first and second set of resources using the control plane management system and wherein the NOC comprises;

means for collecting network performance metrics from the plurality of control planes; and

means for load analysis across the plurality of control planes using the collected network performance metrics from the resources and corresponding pre-determined performance thresholds; and

means for allocating resources across the plurality of control planes.

10. The system as recited in claim 9, wherein an operator reallocates resources across the plurality of control planes based on the collected network performance metrics.

11. The system as recited in claim 1, wherein an enterprise is notified before the control plane reallocates the network resource.

12. The system as recited in claim 1, wherein the pre-determined performance thresholds are selected in a service level agreement between an enterprise and the data center.

13. A non-transitory machine-readable storage medium having stored thereon a plurality of executable instructions to implement a method for load balancing resources among virtual local area networks (VLANs), the method comprising:

allocating a first set of network resources to a first VLAN;

allocating a second set of network resources to a second VLAN, wherein the first set of network resources and the second set of network resources are allocated based on enterprise requirements;

collecting performance metrics from the first set of network resources and the second set of network resources, wherein the collected performance metrics comprise CPU usage, memory usage and throughput;

performing load analysis using the collected performance metrics and corresponding pre-determined performance thresholds for load balancing the first and second set of network resources; and

reallocating automatically a network resource from the first set of network resources to the second set of network resources if the collected performance metric associated with the network resource is less than its corresponding pre-determined performance threshold and if the network resource is required by the second VLAN.

14. The non-transitory machine-readable storage medium of claim 13, the method further comprising:

terminating the reallocating step if the collected performance metric associated with the network resource is at or more than its corresponding pre-determined performance threshold or if the network resource is not required by the second VLAN.

15. The non-transitory machine-readable storage medium of claim 13, the method further comprising:

reallocating a network resource from the second set of network resources to the first set of network resources if the collected performance metric associated with the network resource from the first set of network resources is more than its corresponding pre-determined performance threshold and if the network resource from the second set of network resources not required by the second VLAN.

16. The non-transitory machine-readable storage medium of claim 13, the method further comprising:

reallocating automatically the network resource from the first set of network resources to the second set of network resources only if such reallocation is authorized.

17. The non-transitory machine-readable storage medium of claim 13, the method further comprising:

measuring performance metrics associated with each network resource from the first and second set of network resources.

18. The non-transitory machine-readable storage medium of claim 13, the method further comprising:

allocating network resources between a plurality of control planes by a network operations center (NOC).

19. The non-transitory machine-readable storage medium of claim 18, the method further comprising:

communicating by the NOC with the plurality of control planes through one or more firewalls.

20. The non-transitory machine-readable storage medium of claim 18, the method further comprising:

collecting network performance metrics from the plurality of control planes; and

, performing load analysis across control planes using the collected network performance metrics from the network resources and corresponding pre-determined performance thresholds; and

allocating network resources across control planes.

21. The non-transitory machine-readable storage medium of claim 18, the method further comprising:

reallocating resources by an operator across the plurality of control planes based on the collected network performance metrics.

22. The non-transitory machine-readable storage medium of claim 13, the method further comprising:

notifying an enterprise before the control plane reallocates the network resource.

23. A system for load balancing network resources in a data center, comprising:

a plurality of virtual local area networks (VLANs) including first and second VLANs, wherein each VLAN comprises an independent network of components associated with its respective enterprise;

a control plane coupled to the first and second VLANs, wherein the control plane initially allocates a first set of network resources to the first VLAN and allocates a second set of network resources to the second VLAN based on enterprise requirements and wherein the first and second set of resources comprise one or more of data processing resources, memory resources, printing resources, and data communication resources;

a load balancer, wherein the load balancer collects performance metrics from the first set of network resources and second set of network resources and wherein the collected performance metrics comprise one or more of CPU usage, memory usage and throughput; and

an analysis engine, wherein the analysis engine performs load analysis using the collected performance metrics and corresponding pre-determined performance thresholds for load balancing the first and second set of network resources and wherein the control plane automatically reallocates a network resource from the first set of network resources to the second set of network resources if the collected performance metric associated with the network resource is less than its corresponding pre-determined performance threshold and if the network resource is required by the second VLAN.

24. The system as recited in claims 23, wherein the control plane does not reallocate the network resource from the first set of network resources to the second set of network resources if the collected performance metric associated with the network resource is at or more than its corresponding pre-determined performance threshold or if the network resource is not required by the second VLAN.

25. The system as recited in claims 23, wherein the control plane reallocates a network resource from the second set of network resources to the first set of network resources if the collected performance metric associated with the network resource from the first set of network resources is at or more than its corresponding pre-determined performance threshold and if the network resource from the second set of network resources not required by the second VLAN.