System and method for structuring self-provisioning workloads deployed in virtualized data centers
View Patent ↗The system and method for structuring self-provisioning workloads deployed in virtualized data centers described herein may provide a scalable architecture that can inject intelligence and embed policies into managed workloads to provision and tune resources allocated to the managed workloads, thereby enhancing workload portability across various cloud and virtualized data centers. In particular, the self-provisioning workloads may have a packaged software stack that includes resource utilization instrumentation to collect utilization metrics from physical resources that a virtualization host allocates to the workload, a resource management policy engine to communicate with the virtualization host to effect tuning the physical resources allocated to the workload, and a mapping that the resource management policy engine references to request tuning the physical resources allocated to the workload from a management domain associated with the virtualization host.
1. A set of executable instructions residing in a non-transitory computer-readable medium for execution on a processor, comprising:
configuring, via the processor, a workload for delivery to a virtualization host having physical hardware resources, wherein the workload is an aggregation of services that are configured to work together and wherein the virtualization host is a virtual hosting environment partitioned from the physical hardware resources and the virtual hosting environment including multiple Virtual Machines (VMs), wherein the workload is configured to process within a guest operating system configured for and processing within the virtual hosting environment;
provisioning, via the processor, the workload with a metric collection mechanism, a resource policy enforcement mechanism, and configuration files that define ranges for allocation of the physical hardware resources for processing the workload within the guest operating system of the virtualization host and configuring a policy engine for processing customized corrective actions identified in policies and processed when the allocation defined in the configuration files fail to comply with the ranges during usage of the physical hardware resources and when the workload processes based on bandwidth violations and storage capacity violations, the resource policy enforcement mechanism utilizing metrics from the metric collection mechanism to adjust real time allocations of the physical hardware resources based on the configuration files, and wherein the metrics are gathered by the metric collection mechanism and the metrics include information relevant to utilization of specific hardware resources used by the workload when the workload processes within the virtualization host;
deploying, via the processor, the configured and provisioned workload to the virtualization host; and
isolating, via the processor, differences between a policy engine interface for the policy engine in the virtualization host between other policy engine interfaces for other policy engines in other virtualization hosts in a virtualization host specific mapping for controlling and sharing the physical hardware resources between the virtualization host and the other virtualization hosts.
2. The medium of claim 1 , wherein configuring further includes selecting the virtualization host for the workload based, at least in part, on the configuration files and the physical hardware resources of the virtualization host.
3. The medium of claim 2 , wherein selecting further includes using attributes and parameters associated with the workload to assist in selecting the virtualization host.
4. The medium of claim 3 , wherein using further includes acquiring a service level agreement defining memory, processor, and network constraints for the workload, wherein the service level agreement is one of the attributes.
5. The medium of claim 1 , wherein provisioning further includes configuring the workload with the metric collection mechanism, the resource policy enforcement mechanism, and the configuration files for the workload to self-provision the physical hardware resources when deployed in the virtualization host.
6. The medium of claim 1 , wherein provisioning further includes configuring the metric collection mechanism to monitor and report usage metrics of the workload when deployed in the virtualization host.
7. The medium of claim 1 , wherein provisioning further includes configuring the metric collection mechanism as a packaged module loaded within a kernel of the guest operating system of the virtualization host.
8. The medium of claim 1 , wherein provisioning further includes configuring the configuration files with a service level agreement for the physical hardware resources.
9. The medium of claim 1 , wherein provisioning further includes configuring the resource policy enforcement mechanism to interact with the metric collection mechanism to gather real time usage metrics for the workload on the physical hardware resources and compare those usage metrics with information included in the configuration files.
10. The medium of claim 1 , wherein provisioning further includes configuring the resource policy enforcement mechanism to dynamically tune usage and particular allocations of the physical hardware resources for the workload while the workload processes within the virtual host.
11. A set of executable instructions residing in a non-transitory computer-readable medium for execution on a processor, comprising:
loading, via the processor, a workload as a virtual distribution on physical hardware resources, and wherein the workload is an aggregation of services that are configured to work together and to process within a virtualization host, and wherein the virtualization host is a virtual hosting environment partitioned from the physical hardware resources based on ranges of allocation for those physical hardware resources within a guest operating system configured for and processing within the virtualization host, and wherein the virtual distribution is a specific VM configured to process the workload within the virtualization host and the virtual distribution including customized corrective actions for processing defined in policies and processed when the allocation fails to comply with the ranges during usages of the physical hardware resources when the workload processes based on bandwidth violations and storage capacity violations;
initiating, via the processor, a packaged module within a kernel of an operating system for the specific VM;
self-tuning, via the processor, allocations of the physical hardware resources used by the workload as the workload processes within the specific VM based on constraints for the allocations managed by the packaged module and actions taken by the packaged module as the packaged module processes within the specific VM, and wherein the constraints relevant to utilization metrics of the physical hardware resources as the workload processes within the specific VM; and
isolating, via the processor, differences between a policy engine interface for processing the customized corrective actions in the virtualization host between other policy engine interfaces for other customized corrective actions in other virtualization hosts in a virtualization host specific mapping for controlling and sharing the physical hardware resources between the virtualization host and the other virtualization hosts.
12. The medium of claim 11 further comprising, processing the method within a cloud environment.
13. The medium of claim 11 , wherein self-tuning further includes obtaining usage metrics for processing the workload on the physical hardware resources.
14. The medium of claim 11 , wherein self-tuning further includes obtaining the constraints as a service level agreement for the workload.
15. The medium of claim 11 , wherein self-tuning further includes obtaining the constraints as configuration files for the workload.
16. The medium of claim 11 , wherein self-tuning further includes obtaining the constraints as attributes or parameters associated with the workload.
17. The medium of claim 15 , wherein self-tuning further includes tuning the physical hardware resources.
18. A system, comprising:
a memory having workload provision manager; and
a processor coupled to the memory to execute the workload provision manager from the memory;
wherein the workload provision manager is configured to deploy a workload configured for ranges of allocation assigned to physical hardware resources within a guest operating system configured for and processing within a virtualization host and the workload further configured to dynamically self-adjust and self-provision itself for the physical hardware resources based on processing conditions of the physical hardware resources when the workload processes within the virtualization host and the workload configured with customized corrective actions defined in policies for processing when the allocation fails to comply with the ranges during usage of the physical hardware resources when the workload processes based on bandwidth violations and storage capacity violations, and wherein the workload is an aggregation of services that are configured to work together and to process within the virtualization host, and wherein the virtualization host is a virtual hosting environment partitioned from the physical hardware resources, and the workload provision manager is further configured to isolate differences between a policy engine interface for processing the customized corrective actions in the virtualization host between other policy engine interfaces for other customized corrective actions in other virtualization hosts in a virtualization host specific mapping for controlling and sharing the physical hardware resources between the virtualization host and the other virtualization hosts.
19. The system of claim 18 , wherein the workload includes a packaged module that is configured to be loaded into the guest operating system of the physical hardware resources for performing the dynamic self-adjustment and self-provisioning.
20. The system of claim 19 , wherein the packaged module includes a hardware metrics reporting mechanism, a policy enforcement mechanism, and hardware resource constraint information, each of which is configured to interact with, one another within the operating system of the virtualization host.