Virtual machine consolidation

Patent metadata

Field	Value
Publication number	US-10379898-B2
Application number	US-201715468683-A
Country	US
Kind code	B2
Filing date	Mar 24, 2017
Priority date	Mar 24, 2017
Publication date	Aug 13, 2019
Grant date	Aug 13, 2019

Abstract

Systems, methods and tools for managing the job queues of virtual machines, maintaining a low energy profile and a quality of service within the contractual service agreement. The systems migrate jobs to a new VM queue when a assigned VM has failed. The systems employ machine learning techniques to make decisions whether or not to reallocate the job to a VM running in an active mode (non-scalable mode) or a VM operating under a dynamic voltage and frequency scaling (DVFS) mode. The systems reconcile job failures, transfer and/or complete jobs using the network of VMs without degrading the service quality, maintaining a lower power consumption policy through scalable modes, including idle, busy, sleep, DVFS gradient and DVFS maximum modes, improving the overall reliability of the data center by switching the jobs to scalable nodes, increasing the recoverability of the systems in the virtualized environments.

First claim

What is claimed:

1. A method for reassigning failed jobs in a virtual network of virtual machines, said method comprising the steps of:
calculating, by a processor, whether a job queue of the virtual network is overloaded as a function of a length of an extended job queue being greater than a length of the job queue;
setting, by the processor, each job in the job queue to be processed in a scalable mode of operation as a function of the job queue being overloaded;
defining, by the processor, a number of virtual machines in each scalable mode of operation;
apportioning, by the processor, a job in the job queue to a virtual machine in the virtual network operating in the scalable mode of operation;
failing, by the processor, to complete the job queued by the virtual machine;
computing, by the processor, a probability of failing to complete the job by the virtual machine as a function of an amount of time to execute the job to completion, a repair time, a failure rate and an amount of time remaining to complete the job within a time designated by a service level agreement; and
determining, by the processor, as a function of the probability of failing to complete the job, whether to complete the job queued by the virtual machine or transfer the job to a queue of a second virtual machine operating in a dynamic voltage and frequency scaling (DVFS) mode or an active mode.

2. The method of claim 1 , said method further comprising the steps of:
transferring, by the processor, the job queued by the virtual machine to the job queue of the second virtual machine operating in DVFS mode having a selected gradient factor of μ.

3. The method of claim 2 , said method further comprising the step of:
simultaneously repairing, by the processor, the virtual machine while the second virtual machine completes the job.

4. The method of claim 1 , said method further comprising the steps of:
repairing, by the processor, the virtual machine failing to complete the job; and
completing, by the processor, the job using the virtual machine after being repaired.

5. The method of claim 1 , wherein each scalable mode of operation is selected from the group consisting of power nap to active mode, inactive to power nap to active mode, and active mode to DVFS mode.

6. The method of claim 1 , said method further comprising the step of:
automatically transferring, by the processor from the job queue of the virtual machine to the second virtual machine, a critical job having the amount of time remaining to complete the job within a time designated by a service level agreement that is less than the repair time.

7. The method of claim 1 , wherein the step of computing comprises computing that the repair time and the amount of time to execute the job to completion on the virtual machine are greater than the amount of time remaining to complete the job, wherein a transition time to the second virtual machine plus the amount of time to execute the job on the second virtual machine is greater than the amount of time remaining to complete the job, and wherein the job is assigned to the second virtual machine operating in active mode.

8. The method of claim 1 , said method further comprising the step of:
providing at least one support service for at least one of creating, integrating, hosting, maintaining, and deploying computer-readable program code in a computer system, where the computer-readable program code in combination with the computer system is configured to implement the steps of calculating, setting, defining, apportioning, failing, computing, and determining.

9. A computer system, comprising: a processor; a memory device coupled to the processor; and a computer readable storage device coupled to the processor, wherein the storage device contains program code executable by the processor via the memory device to implement a method for reassigning failed jobs in a virtual network of virtual machines, said method comprising the steps of:
calculating, by the processor, whether a job queue of the virtual network is overloaded as a function of a length of an extended job queue being greater than a length of the job queue;
setting, by the processor, each job in the job queue to be processed in a scalable mode of operation as a function of the job queue being overloaded;
defining, by the processor, a number of virtual machines in each scalable mode of operation;
apportioning, by the processor, a job in the job queue to a virtual machine in the virtual network operating in the scalable mode of operation;
failing, by the processor, to complete the job queued by the virtual machine;
computing, by the processor, a probability of failing to complete the job by the virtual machine as a function of an amount of time to execute the job to completion, a repair time, a failure rate and an amount of time remaining to complete the job within a time designated by a service level agreement; and
determining, by the processor, as a function of the probability of failing to complete the job, whether to complete the job queued by the virtual machine or transfer the job to a queue of a second virtual machine operating in a dynamic voltage and frequency scaling (DVFS) mode or an active mode.

10. The computer system of claim 9 , said method further comprising the steps of:
transferring, by the processor, the job queued by the virtual machine to the job queue of the second virtual machine operating in DVFS mode having a selected gradient factor of μ.

11. The computer system of claim 10 , said method further comprising the steps of:
simultaneously repairing, by the processor, the virtual machine while the second virtual machine completes the job.

12. The computer system of claim 9 , said method further comprising the steps of:
repairing, by the processor, the virtual machine failing to complete the job; and
completing, by the processor, the job using the virtual machine after being repaired.

13. The computer system of claim 9 , wherein each scalable mode of operation is selected from the group consisting of power nap to active mode, inactive to power nap to active mode, and active mode to DVFS mode.

14. The computer system of claim 9 , said method further comprising the step of:
automatically transferring, by the processor from the job queue of the virtual machine to the second virtual machine, a critical job having the amount of time remaining to complete the job within a time designated by a service level agreement that is less than the repair time.

15. A computer program product comprising: one or more computer readable hardware storage devices having computer readable program code stored therein, said program code containing instructions executable by one or more processors to implement a method for reassigning failed jobs in a virtual network of virtual machines, said method comprising the steps of:
calculating, by the processor, whether a job queue of the virtual network is overloaded as a function of a length of an extended job queue being greater than a length of the job queue;
setting, by the processor, each job in the job queue to be processed in a scalable mode of operation as a function of the job queue being overloaded;
defining, by the processor, a number of virtual machines in each scalable mode of operation;
apportioning, by the processor, a job in the job queue to a virtual machine in the virtual network operating in the scalable mode of operation;
failing, by the processor, to complete the job queued by the virtual machine;
computing, by the processor, a probability of failing to complete the job by the virtual machine as a f

Assignees

• IBM

Inventors

• Malik Pooja
• Yadav Vikram

Classifications

• G06F2009/45595

  Network integration; Enabling network access in virtual machine instances · CPC title

• G06F9/4856 Primary

  resumption being on a different machine, e.g. task migration, virtual machine migration (G06F9/5088 takes precedence) · CPC title

• G06F9/45558 Primary

  Hypervisor-specific management and integration aspects · 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

• Y02D10/24

  Cross-Sectional Technologies · mapped topic