Measuring host utilization in a datacenter

Patent metadata

Field	Value
Publication number	US-11263040-B2
Application number	US-202016882942-A
Country	US
Kind code	B2
Filing date	May 26, 2020
Priority date	May 26, 2020
Publication date	Mar 1, 2022
Grant date	Mar 1, 2022

Abstract

Various examples are disclosed for generating heatmaps and plotting utilization of hosts in a datacenter environment. A collector virtual machine can rove the datacenter and collect utilization data. The utilization data can be plotted on a heatmap to illustrate utilization hotspots in the datacenter environment.

First claim

Therefore, the following is claimed:

1. A system comprising:
at least one computing device; and
program instructions stored in memory and executable in the at least one computing device that, when executed by the at least one computing device, direct the at least one computing device to:
identify a plurality of host machines associated with a software defined datacenter, the host machines respectively configured to execute at least one workload associated with an enterprise;
generate a virtual machine instrumented to collect utilization data from a particular host machine in which the virtual machine is executed;
place the virtual machine onto a first one of the host machines, wherein the virtual machine collects the utilization data from the first one of the host machines;
obtain the utilization data for the first one of the host machines from the virtual machine;
migrate the virtual machine to at least one other host machine, wherein the virtual machine collects the utilization data from the at least one other host machine;
obtain the utilization data for the at least one other host machine from the virtual machine;
generate a utilization metric for respective ones of the host machines based on the utilization data from the first one of the host machines and the at least one other host machine; and
generate a heatmap for the software defined datacenter, the heatmap plotting the utilization metric for the respective ones of the host machines relative to other host machines within the software defined datacenter.

2. The system of claim 1 , wherein the virtual machine is migrated to the at least one other host machine using a random walk algorithm.

3. The system of claim 1 , wherein the virtual machine is migrated to the at least one other host machine using a gradient descent algorithm based upon previously identified highly utilized host machines or a systematic grid algorithm.

4. The system of claim 1 , wherein the utilization metric is a single metric based upon measured throughput observed on a host machine, measured latency observed on at least one workload on the host machine, or hardware resource utilization observed on the host machine.

5. The system of claim 1 , wherein the heatmap for the software defined datacenter is generated by constructing a three-dimensional heatmap, wherein the utilization metric is plotted by a host machine in a first axis, a second axis, and a third axis that are respectively associated with a parameter by which the plurality of host machines can be categorized.

6. The system of claim 5 , wherein the first axis, the second axis, and the third axis are associated with a respective octet of a respective internet protocol address of a respective host machine.

7. The system of claim 1 , wherein the at least one computing device is further directed to take a remedial action in response to generating the heatmap, the remedial action comprising: adjusting requests from client devices away from a hotspot, powering down at least one host machine that is underutilized in the software defined datacenter, or directing the requests to the at least one host machine that is underutilized.

8. A method comprising:
identifying a plurality of host machines associated with a software defined datacenter, the host machines respectively configured to execute at least one workload associated with an enterprise;
generating a virtual machine instrumented to collect utilization data from a particular host machine in which the virtual machine is executed;
placing the virtual machine onto a first one of the host machines, wherein the virtual machine collects the utilization data from the first one of the host machines;
obtaining the utilization data for the first one of the host machines from the virtual machine;
migrating the virtual machine to at least one other host machine, wherein the virtual machine collects the utilization data from the at least one other host machine;
obtaining the utilization data for the at least one other host machine from the virtual machine;
generating a utilization metric for respective ones of the host machines based on the utilization data from the first one of the host machines and the at least one other host machine; and
generating a heatmap for the software defined datacenter, the heatmap plotting the utilization metric for the respective ones of the host machines relative to other host machines within the software defined datacenter.

9. The method of claim 8 , wherein the virtual machine is migrated to the at least one other host machine using a random walk algorithm.

10. The method of claim 8 , wherein the virtual machine is migrated to the at least one other host machine using a gradient descent algorithm based upon previously identified highly utilized host machines or a systematic grid algorithm.

11. The method of claim 8 , wherein the utilization metric is a single metric based upon measured throughput observed on a host machine, measured latency observed on at least one workload on the host machine, or hardware resource utilization observed on the host machine.

12. The method of claim 8 , wherein the heatmap for the software defined datacenter is generated by constructing a three-dimensional heatmap, wherein the utilization metric is plotted by a host machine in a first axis, a second axis, and a third axis that are respectively associated with a parameter by which the host machines can be categorized.

13. The method of claim 12 , wherein the first axis, the second axis, and the third axis are associated with a respective octet of a respective internet protocol address of a respective host machine.

14. The method of claim 8 , further comprising taking a remedial action in response to generating the heatmap, the remedial action comprising: adjusting requests from client devices away from a hotspot, powering down at least one host machine that is underutilized in the software defined datacenter, or directing requests to the at least one host machine that is underutilized.

15. A non-transitory computer-readable medium embodying program instructions that, when executed on at least one computing device, direct the at least one computing device to:
identify a plurality of host machines associated with a software defined datacenter, the host machines respectively configured to execute at least one workload associated with an enterprise;
generate a virtual machine instrumented to collect utilization data from a particular host machine in which the virtual machine is executed;
place the virtual machine onto a first one of the host machines, wherein the virtual machine collects the utilization data from the first one of the host machines;
obtain the utilization data for the first one of the host machines from the virtual machine;
migrate the virtual machine to at least one other host machine, wherein the virtual machine collects the utilization data from the at least one other host machine;
obtain the utilization data for the at least one other host machine from the virtual machine;
generate a utilization metric for respective ones of the host machines based on the utilization data from the first one of the host machines and the at least one other host machine; and
generate a heatmap for the software defined datacenter, the heatmap plotting the utilization metric for the respective ones of the host machines relative to other host machines within the software defined datacenter.

16. The non-transitory computer-readable medium of claim 15 , wherein the virtual machine is migrated to the at least one other host machine using a random wa

Assignees

• Vmware Inc

Inventors

• Sivaraman Hari
• Kurkure Uday Pundalik
• Vu Lan

Classifications

• G06F2209/508

  Monitor · CPC title

• G06F9/5077

  Logical partitioning of resources; Management or configuration of virtualized resources (specific details on emulation or internal functioning of virtual machines G06F9/455) · CPC title

• G06F9/5027

  the resource being a machine, e.g. CPUs, Servers, Terminals · CPC title

• G06F2009/45562

  Creating, deleting, cloning virtual machine instances · CPC title

• G06F9/505

  considering the load · CPC title