NETWORK DEVICE LOAD BALANCING IN A VIRTUALIZED COMPUTING ENVIRONMENT

• US 20150006705A1
• Filed: 06/26/2013
• Published: 01/01/2015
• Est. Priority Date: 06/26/2013
• Status: Active Grant

• Current Assignee: Vmware LLC (Broadcom, Inc.)
• Original Assignee: VMware, Inc. (Broadcom, Inc.)
• Inventors: ANTONY, JINTO
• Granted Patent: US 9,294,407 B2
• Time in Patent Office: Days
• US Class Current: 709/224
• CPC Class Codes: H04L 43/0882 Utilisation of link capacity
• CPC Class Codes: H04L 47/125 by balancing the load, e.g. traffic engineering
• CPC Class Codes: H04L 67/1001 for accessing one among a plurality of replicated servers
• CPC Class Codes: H04L 67/1036 Load balancing of requests to servers for services different from user content provisioning, e.g. load balancing across domain name servers
• CPC Class Codes: H04L 67/1038 Load balancing arrangements to avoid a single path through a load balancer

Abstract

Techniques for balancing network load at network devices in a virtualized computing environment are disclosed. In one embodiment, a first network device having network load above a threshold value is determined. Further, a first host coupled to the first network device is identified. The first host executes a workload that transmits and receives network traffic via the first network device. If the first host is not coupled to any other network device, the network load at the first network device is reduced by initiating migration of at least a part of the workload to a second host coupled to any other network device. If the first host is coupled to a second network device, the network load at the first network device is reduced by instructing a virtual switch of the first host to route at least a part of the network traffic between the workload and second network device.

Claims

1. An automated method for balancing network load at network devices in a virtualized computing environment comprising:

determining a first network device having network load above a threshold value;

identifying a first host computing system coupled to the first network device, the first host computing system executing a workload that transmits and receives network traffic via the first network device;

if the first host computing system is not coupled to any other network device, reducing the network load at the first network device by initiating migration of at least a part of the workload to a second host computing system coupled to any other network device; and

if the first host computing system is coupled to a second network device, reducing the network load at the first network device by instructing a virtual switch of the first host computing system to route at least a part of the network traffic between the workload and the second network device.

2. The method of claim 1, further comprising:

determining whether the network load at the first network device is still above the threshold value; and

if so, repeating the steps of identifying, initiating migration, and instructing a virtual switch for other host computing systems coupled to the first network device until the network load at the first network device is less than the threshold value.

3. The method of claim 2, further comprising:

if not, terminating balancing the network load at the first network device.

4. The method of claim 1, wherein, in instructing the virtual switch to route at least the part of the network traffic between the workload and the second network device, the second network device is selected based on network traffic at the second network device.

5. The method of claim 4, wherein the second network device is selected using a resource scheduling framework.

6. The method of claim 1, wherein, in initiating the migration of at least the part of the workload to the second host computing system, the second host computing system is selected based on network traffic at the other network device.

7. The method of claim 6, wherein the second host computing system is selected using a resource scheduling framework.

8. A system comprising:

a plurality of network devices;

a plurality of host computing systems; and

a remote server comprising a network load balancing module to automatically balance network load at the plurality of network devices in a virtualized computing environment, by;

determining a first network device having network load above a threshold value;

identifying a first host computing system coupled to the first network device, the first host computing system executing a workload that transmits and receives network traffic via the first network device;

if the first host computing system is not coupled to any other network device, reducing the network load at the first network device by initiating migration of at least a part of the workload to a second host computing system coupled to any other network device; and

if the first host computing system is coupled to a second network device, reducing the network load at the first network device by instructing a virtual switch of the first host computing system to route at least a part of the network traffic between the workload and the second network device.

9. The system of claim 8, wherein the network load balancing module is further configured to:

determine whether the network load at the first network device is still above the threshold value; and

if so, repeat the steps of identifying, initiating migration, and instructing a virtual switch for other host computing systems coupled to the first network device until the network load at the first network device is less than the threshold value.

10. The system of claim 9, wherein the network load balancing module is further configured to:

if not, terminate balancing the network load at the first network device.

11. The system of claim 8, wherein the network load balancing module instructs the virtual switch to route at least the part of the network traffic between the workload and the second network device based on network traffic at the second network device.

12. The system of claim 11, wherein the second network device is selected using a resource scheduling framework.

13. The system of claim 8, wherein the network load balancing module initiates the migration of at least the part of the workload to the second host computing system based on network traffic at the other network device.

14. The system of claim 13, wherein the second host computing system is selected using a resource scheduling framework.

15. A computer-readable storage medium including instructions that are configured, when executed by a computing device, to perform an automated method for balancing network load at network devices in a virtualized computing environment comprising:

determining a first network device having network load above a threshold value;

identifying a first host computing system coupled to the first network device, the first host computing system executing a workload that transmits and receives network traffic via the first network device;

if the first host computing system is not coupled to any other network device, reducing the network load at the first network device by initiating migration of at least a part of the workload to a second host computing system coupled to any other network device; and

if the first host computing system is coupled to a second network device, reducing the network load at the first network device by instructing a virtual switch of the first host computing system to route at least a part of the network traffic between the workload and the second network device.

16. The computer-readable storage medium of claim 15, further comprising:

determining whether the network load at the first network device is still above the threshold value; and

if so, repeating the steps of identifying, initiating migration, and instructing a virtual switch for other host computing systems coupled to the first network device until the network load at the first network device is less than the threshold value.

17. The computer-readable storage medium of claim 16, further comprising:

if not, terminating balancing the network load at the first network device.

18. The computer-readable storage medium of claim 15, wherein, in instructing the virtual switch to route at least the part of the network traffic between the workload and the second network device, the second network device is selected based on network traffic at the second network device.

19. The computer-readable storage medium of claim 18, wherein the second network device is selected using a resource scheduling framework.

20. The computer-readable storage medium of claim 15, wherein, in initiating the migration of at least the part of the workload to the second host computing system, the second host computing system is selected based on network traffic at the other network device.

21. The computer-readable storage medium of claim 20, wherein the second host computing system is selected using a resource scheduling framework.