IP Library Granted Patent US 9,600,311
Granted Patent B2
US 9,600,311 · App. 14/382,597 · Granted Mar 21, 2017

Virtual-machine managing device and virtual-machine managing method

View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 9,600,311
App. No.
14/382,597
Granted
Mar 21, 2017
Kind
B2
Abstract

Provided is a virtual-machine managing device including: a model acquiring unit that acquires, for each server device, a performance model indicative of plural correspondent relationships between a workload amount and performance information on a workload; a performance-information acquiring unit that acquires the performance information on a virtual machine to be moved running on a current server device; a conversion unit that converts the performance information on the virtual machine to be moved into a combination of the workload amount and the workload characteristic value concerning the virtual machine to be moved, by using the performance model of the current server device; and an estimating unit that estimates performance information on the virtual machine to be moved on a destination server device serving as a candidate for a destination of movement of the virtual machine to be moved, by applying the combination converted by the conversion unit to the performance model of the destination server device.

Claims (35)

1. A virtual-machine managing method performed by at least one computer and including:

acquiring a performance model for each physical server device of a plurality of physical server devices, the performance model indicating associations between a plurality of combinations of workload parameters and an amount of resources of one of the physical server devices consumed by a workload configured with the combination of the workload parameters associated therewith, wherein a processing load on the physical server device depends on the combination of the plurality of the workload parameters with which the workload is configured;

acquiring performance information on a target virtual machine running on a first physical server device, the performance information on the target virtual machine running on the first physical server device indicating an amount of resources of the first physical server device consumed by the target virtual machine, the target virtual machine running the workload and being moved onto a second physical server device;

converting the amount of resources indicated by the performance information on the target virtual machine running on the first physical server device into one of a first plurality of combinations of the workload parameters that is associated, by the performance model of the first physical server device, with the amount of resources indicated by the performance information on the target virtual machine running on the first physical server device;

estimating an amount of resources of the second physical server device expected to be consumed in a case of that the target virtual machine runs on the second physical server device, the amount of resources of the second physical server device expected to be consumed being estimated as the amount of resources of the second physical server device associated, by the performance model of the second physical server device, with the combination of the plurality of the workload parameters obtained as a result of the conversion;

storing a second plurality of combinations of the workload parameters, which is associated with an amount of resources of a third physical server device that the target virtual machine consumed when the target virtual machine ran on the third physical server device in a past; obtaining a common set of the first plurality of combinations of the workload parameters and the second plurality of combinations of the workload parameters, and converting the amount of resources indicated by the performance information on the target virtual machine running on the first physical server device into one of the plurality of combinations of the workload parameters included in the obtained common set; and

moving the target virtual machine to the second physical server device.

2. A virtual-machine managing device, comprising:

a model acquiring unit that acquires a performance model for each physical server device of a plurality of physical server devices, the performance model indicating associations between a plurality of combinations of workload parameters and an amount of resources of one of the physical server devices consumed by a workload configured with the combination of the workload parameters associated therewith, wherein a processing load on the physical server device depends on the combination of the plurality of the workload parameters with which the workload is configured;

a performance-information acquiring unit that acquires performance information on a target virtual machine running on a first physical server device, the performance information on the target virtual machine running on the first physical server device indicating an amount of resources of the first physical server device consumed by the target virtual machine, the target virtual machine running the workload and being moved onto a second physical server device;

a conversion unit that converts the amount of resources indicated by the performance information on the target virtual machine running on the first physical server device into one of a first plurality of combinations of the workload parameters that is associated, by the performance model of the first physical server device, with the amount of resources indicated by the performance information on the target virtual machine running on the first physical server device;

an estimating unit that estimates an amount of resources of the second physical server device expected to be consumed in a case of that the target virtual machine runs on the second physical server device, the amount of resources of the second physical server device expected to be consumed being estimated as the amount of resources of the second physical server device associated, by the performance model of the second physical server device, with the combination of the plurality of the workload parameters obtained as a result of the conversion performed by the conversion unit; and

a characteristic-information storage unit that stores a second plurality of combinations of the workload parameters, which is associated with an amount of resources of a third physical server device that the target virtual machine consumed when the target virtual machine ran on the third physical server device in a past,

wherein the conversion unit obtains a common set of the first plurality of combinations of the workload parameters and the second plurality of combinations of the workload parameters, and converts the amount of resources indicated by the performance information on the target virtual machine running on the first physical server device into one of the plurality of combinations of the workload parameters included in the obtained common set, and

wherein the target virtual machine is moved to the second physical server device.

3. The virtual-machine managing device according to claim 2 , further comprising:

a workload controlling unit that causes a virtual machine for measurement, which is arranged on each of the physical server devices, to execute a plurality of workloads, each of the workloads being configured with a different one of a plurality of combinations of the workload parameters;

a performance-information collecting unit that collects workload performance information on each workload running on each physical server device, the performance information on a workload running on a physical server device indicating an amount of resources of the physical server device consumed by the workload; and

a model generating unit that generates the performance model of each of the server devices on the basis of a plurality of correspondences between the plurality of combinations of the workload parameters and the workload performance information on each workload running on each physical server device.

4. The virtual-machine managing device according to claim 2 , wherein in a case where the target virtual machine was moved from the third physical server device onto the first physical server device, the target virtual machine having been running on the third physical server device, the performance-information acquiring unit acquires the performance information on the target virtual machine running on the first physical server device on the basis of an increase of a total amount or resources indicated by pieces of the performance information on a group of virtual machines in a predetermined unit running on the first physical server device, or acquires the performance information on the target virtual machine running on the first physical server device on the basis of a decrease of a total amount or resources indicated by the pieces of the performance information on a group of virtual machines in a predetermined unit running on the first physical server device.

5. The virtual-machine managing device according to claim 2 ,

wherein the performance model indicates the associations between the plurality of combinations of the workload parameters and the amount of resources of the first physical server device consumed by a workload configured with the combination of the workload parameters, for each of a plurality of types of resources of the first physical server device,

wherein the performance-information acquiring unit acquires the performance information on the target virtual machine running on the first physical server device, for each of the plurality of types of resources of the first physical server device,

wherein the conversion unit converts, for each of the plurality of types of resources of the first physical server device, the amount of resources indicated by the performance information on the target virtual machine running on the first physical server device into one of the first plurality of combinations of the workload parameters, using the performance model of the first physical server device for each of the plurality of types of resources of the first physical server device, and

wherein the estimating unit estimates the amount of resources of the second physical server device expected to be consumed in a case of that the target virtual machine runs on the second physical server device, for each of the plurality of types of resources of the second physical server device.

6. A virtual-machine managing system comprising the virtual-machine managing device according to claim 2 and a plurality of server devices, wherein each of the plurality of server devices includes:

a performance-information measuring unit that measures performance information on a virtual machine running on one of the physical server devices, or integrated performance information on a group of virtual machines in a predetermined unit running on the one of the physical server devices.

7. A non-transitory computer-readable storage medium storing a program for causing at least one computer to realize:

a model acquiring unit that acquires a performance model for each physical server device of a plurality of physical server devices, the performance model indicating associations between a plurality of combinations of workload parameters and an amount of resources of one of the physical server devices consumed by a workload configured with the combination of the workload parameters associated therewith, wherein a processing load on the physical server device depends on the combination of the plurality of the workload parameters with which the workload is configured;

a performance-information acquiring unit that acquires performance information on a target virtual machine running on a first physical server device, the performance information on the target virtual machine running on the first physical server device indicating an amount of resources of the first physical server device consumed by the target virtual machine, the target virtual machine running the workload and being moved onto a second physical server;

a conversion unit that converts the amount of resources indicated by the performance information on the target virtual machine running on the first physical server device into one of a first plurality of combinations of the workload parameters that is associated, by the performance model of the first physical server device, with the amount of resources indicated by the performance information on the target virtual machine running on the first physical server device;

an estimating unit that estimates an amount of resources of the second physical server device expected to be consumed in a case of that the target virtual machine runs on the second physical server device, the amount of resources of the second physical server device expected to be consumed being estimated as the amount of resources of the second physical server device associated, by the performance model of the second physical server device, with the combination of the plurality of the workload parameters obtained as a result of the conversion performed by the conversion unit; and

a characteristic-information storage unit that stores a second plurality of combinations of the workload parameters, which is associated with an amount of resources of a third physical server device that the target virtual machine consumed when the target virtual machine ran on the third physical server device in a past,

wherein the conversion unit obtains a common set of the first plurality of combinations of the workload parameters and the second plurality of combinations of the workload parameters, and converts the amount of resources indicated by the performance information on the target virtual machine running on the first physical server device into one of the plurality of combinations of the workload parameters included in the obtained common set, and

wherein the target virtual machine is moved to the second physical server device.

Assignments (3)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 27, 2024
From: NEC ASIA PACIFIC PTE LTD.
To: NEC CORPORATION
Reel/Frame 066268/0870 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 17, 2023
From: NEC CORPORATION
To: NEC ASIA PACIFIC PTE LTD.
Reel/Frame 063349/0459 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 3, 2014
From: FUJIWAKA, MASAYA
To: NEC CORPORATION
Reel/Frame 033658/0383 →