Closed-Loop Feedback Mechanism for Achieving Optimum Performance in a Consolidated Workload Environment

Patent metadata

Field	Value
Publication number	US-2015169350-A1
Application number	US-201414305033-A
Country	US
Kind code	A1
Filing date	Jun 16, 2014
Priority date	Dec 12, 2013
Publication date	Jun 18, 2015
Grant date	—

Abstract

Mechanisms are provided for dynamically adjusting assignment of software threads to hardware threads in virtual machine (VM) environments. The mechanisms receive, by a virtual machine manager (VMM), an indication of workload priority from a plurality of VMs. The indication indicates a priority of a workload executing on each VM in the plurality of VMs. The mechanisms provide, by the VMM, an indication of physical resource usage to each VM. The indication of physical resource usage is an indication of physical resource usage across all VMs in the plurality of VMs. The mechanisms automatically adjust, by each VM, assignment of corresponding software threads to hardware threads based on the indication of physical resource usage and a priority of a workload executing on the VM to achieve a balance of usage of hardware threads across all VMs in the plurality of VMs.

First claim

1 . A method, in a data processing system comprising at least one physical processor and a memory, for dynamically adjusting assignment of software threads to hardware threads in virtual machine (VM) environments, the method comprising:
receiving, by a virtual machine manager (VMM) executing in the data processing system, an indication of workload priority from a plurality of VMs executing in the data processing system, wherein the indication indicates a priority of a workload executing on each VM in the plurality of VMs; providing, by the VMM, an indication of physical resource usage to each VM in the plurality of VMs, wherein the indication of physical resource usage is an indication of physical resource usage across all VMs in the plurality of VMs executing in the data processing system; and automatically adjusting, by each VM in the plurality of VMs, assignment of corresponding software threads to hardware threads based on the indication of physical resource usage and a priority of a workload executing on the VM, to achieve a balance of usage of hardware threads across all VMs in the plurality of VMs.

2 . The method of claim 1 , wherein automatically adjusting, by each VM in the plurality of VMs, assignment of corresponding software threads to hardware threads comprises performing one of folding or unfolding a number of virtual processors (VPs) allocated to the VM based on the indication of physical resource usage and the priority of the workload executing on the VM.

3 . The method of claim 2 , wherein performing one of folding or unfolding a number of VPs allocated to the VM comprises:
determining whether utilization, by the VM, of the at least one physical processor is less than an entitlement associated with the VM; and in response to the utilization, by the VM, of the at least one physical processor being less than the entitlement associated with the VM, folding a number of VPs allocated to the VM down to a minimum number required for the workload executing on the VM.

4 . The method of claim 2 , wherein performing one of folding or unfolding a number of VPs allocated to the VM comprises:
determining whether utilization, by the VM, of the at least one physical processor is less than an entitlement associated with the VM; and in response to the utilization, by the VM, of the at least one physical processor being equal to or greater than the entitlement associated with the VM, folding a number of VPs allocated to the VM down to a minimum number required for the workload executing on the VM and assigning software threads to all of the hardware threads to achieve complete utilization of remaining VPs of the VM.

5 . The method of claim 2 , wherein performing one of folding or unfolding a number of VPs allocated to the VM comprises:
determining whether utilization, by the VM, of the at least one physical processor is greater than an entitlement associated with the VM; in response to the utilization, by the VM, of the at least one physical processor being greater than the entitlement associated with the VM, determining if there are shared resources available in the data processing system; in response to shared resources not being available in the data processing system, folding or unfolding the number of VPs allocated to the VM to equal a number of available physical processors in the data processing system; and in response to shared resources being available in the data processing system, unfolding the number of VPs allocated to the VM to a maximum number of VPs associated with the VM and assigning software threads to only the primary hardware threads in the at least one physical processor.

6 . The method of claim 2 , wherein performing one of folding or unfolding a number of VPs allocated to the VM comprises:
determining whether utilization, by the VM, of the at least one physical processor is greater than an entitlement associated with the VM; and in response to the utilization, by the VM, of the at least one physical processor being not being greater than the entitlement associated with the VM, unfolding a number of VPs allocated to the VM to equal an entitlement associated with the VM.

7 . The method of claim 1 , wherein providing, by the VMM, an indication of physical resource usage to each VM in the plurality of VMs comprises:
in accordance with an established business policy, sending notifications to VMs in the plurality of VMs that are over-provisioned, with regard to a number of VPs allocated to the VMs, to fold down their number of VPs.

8 . The method of claim 7 , wherein notifications are sent in accordance with priorities of workloads executing on the VMs in the plurality of VMs such that notifications are sent to relatively low priority VMs prior to sending notifications to relatively high priority VMs in the plurality of VMs.

9 . The method of claim 7 , wherein the notifications instruct relatively low priority VMs in the plurality of VMs to reduce their allocated number of VPs by a greater amount than relatively higher priority VMs in the plurality of VMs.

10 . The method of claim 1 , the VMM is a hypervisor executing in the data processing system.

11 - 20 . (canceled)

Assignees

• IBM

Inventors

• Anand Vaijayanthimala K
• Burdick Dean J
• Mealey Bruce G
• Michel Dirk

Classifications

• G06F2009/4557

  Distribution of virtual machine instances; Migration and load balancing · CPC title

• G06F9/45558 Primary

  Hypervisor-specific management and integration aspects · CPC title

• G06F9/4881

  Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues · CPC title

• G06F2209/5021

  Priority · 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