Autonomously managed virtual machine anti-affinity rules in cloud computing environments

• US 9,652,271 B2
• Filed: 05/22/2014
• Issued: 05/16/2017
• Est. Priority Date: 01/06/2014
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Cropper, Joseph W.
• Primary Examiner(s): Dao, Thuy
• Assistant Examiner(s): Smith, Cheneca
• Application Number:
  US14/284,626
• Publication Number:
  US 20150193245A1
• Time in Patent Office: 1,090 Days
• Field of Search: None
• CPC Class Codes: G06F 2009/4557 Distribution of virtual machine instances; Migration and load balancing
• CPC Class Codes: G06F 2209/504 Resource capping
• CPC Class Codes: G06F 9/45533 Hypervisors; Virtual machine monitors
• CPC Class Codes: G06F 9/45558 Hypervisor-specific management and integration aspects
• CPC Class Codes: G06F 9/50 Allocation of resources, e.g. of the central processing unit [CPU]
• CPC Class Codes: G06F 9/5077 Logical partitioning of resources; Management or configuration of virtualized resources specific details on emulation or internal functioning of virtual machines G06F9/455
• CPC Class Codes: H04L 41/0893 Assignment of logical groups to network elements
• CPC Class Codes: H04L 41/0894 Policy-based network configuration management
• CPC Class Codes: H04L 41/0896 Bandwidth or capacity management, i.e. automatically increasing or decreasing capacities flow or congestion control using dynamic resource allocation, e.g. in-call renegotiation, H04L47/76
• CPC Class Codes: H04L 41/5096 wherein the managed service relates to distributed or central networked applications
• CPC Class Codes: H04L 43/08 Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
• CPC Class Codes: H04L 43/0817 by checking functioning
• CPC Class Codes: Y02D 10/00 Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

System, method, and computer program product to perform an operation comprising collecting performance metrics of a first virtual machine, and defining, based on the collected performance metrics, at least one rule to restrict collocation of the first virtual machine with other virtual machines on one or more host machines in a cloud computing environment.

Claims

1. A method comprising:

collecting performance metrics of;

(i) a first virtual machine, and (ii) a first host machine in a cloud computing environment executing the first virtual machine;

determining, based on the collected performance metrics, that use of a first system resource of the first host machine exceeds a first threshold;

detecting a resource conflict between the first virtual machine and a third virtual machine executing on the first host machine;

programmatically generating, based on the collected performance metrics, the resource conflict, and the use of the first system resource of the first host machine exceeding the first threshold, a first rule to restrict co-location of the first virtual machine with other virtual machines on host machines in the cloud computing environment;

associating the first rule with a parent image of the first virtual machine and the third virtual machine, wherein the first virtual machine is a clone of the parent image;

enforcing the first rule in the cloud computing environment by;

(i) restricting a second virtual machine cloned from the parent image from being co-located with the first virtual machine on the first host machine, (ii) deploying the second virtual machine on a second host machine in the cloud computing environment, and (iii) moving the third virtual machine from the first host machine to a third host machine to resolve the conflict;

collecting additional performance metrics of;

(i) the first and second virtual machines, and (ii) the first and second host machines;

determining, based on the additional performance metrics, that use of a second system resource of the first host machine exceeds a second threshold; and

modifying the first rule based on the additional performance metrics of the second system resource, wherein the modified first rule further restricts co-location of virtual machines based on the second system resource.

2. The method of claim 1, wherein modifying the first rule restricts co-location of the first and second virtual machines on the second host machine.

3. The method of claim 1, wherein the first rule is further generated upon determining:

(i) the collected performance metrics reflect that use of a second system resource of the host machine exceed a second threshold, and (ii) a system failure has occurred based on the use of the first and second system resources exceeding the thresholds.

4. The method of claim 1, wherein the performance metrics comprise at least one of:

(i) a processor utilization, (ii) a memory utilization, (iii) network I/O rates, and (iv) disk I/O rates.

5. The method of claim 1, wherein the first rule is further associated with a first class of virtual machines defined by a shared characteristic, wherein the first class of virtual machines includes:

(i) the first virtual machine, (ii) the parent image, (iii) subsequent instances of virtual machines cloned from the parent image, (iv) a third virtual machine, (v) a parent image of the third virtual machine, and (vi) subsequent instances of virtual machines cloned from the parent image of the third virtual machine, wherein the shared characteristic comprises a level of use of each of a plurality of system resources that exceeds a respective threshold level of use for each of the plurality of system resources.

6. The method of claim 1, further comprising:

determining, based on the additional performance metrics, that use of the first system resource of the first host machine does not exceed the first threshold; and

deleting the first rule based on the updated performance metrics and the use of the system resource not exceeding the first threshold.

7. The method of claim 6, further comprising subsequent to deleting the first rule:

collecting additional performance metrics of;

(i) the first and second virtual machines, and (ii) the first and second host machines;

determining, based on the additional performance metrics, that use of a third system resource of the first host and second machines exceeds a third threshold;

programmatically generating, based on the collected performance metrics and the use of the third system resource of the first host machine exceeding the third threshold, a third rule to restrict co-location of the first virtual machine with other virtual machines on host machines in the cloud computing environment; and

enforcing the third rule in the cloud computing environment by;

(i) restricting a third virtual machine cloned from the parent image from being co-located with the first and second virtual machines on the first and second host machines, respectively, and (ii) deploying the third virtual machine on a third host machine in the cloud computing environment.