CN110647381A - Virtual machine resource balancing and deployment optimizing method - Google Patents
Virtual machine resource balancing and deployment optimizing method Download PDFInfo
- Publication number
- CN110647381A CN110647381A CN201910880143.9A CN201910880143A CN110647381A CN 110647381 A CN110647381 A CN 110647381A CN 201910880143 A CN201910880143 A CN 201910880143A CN 110647381 A CN110647381 A CN 110647381A
- Authority
- CN
- China
- Prior art keywords
- physical machine
- machine
- virtual machine
- physical
- virtual
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
- G06F2009/4557—Distribution of virtual machine instances; Migration and load balancing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Debugging And Monitoring (AREA)
Abstract
The invention discloses a virtual machine resource balancing and deployment optimizing method, which comprises the following specific steps: step 1: preparing data; step 2: manually inputting parameters; and step 3: constructing a virtual machine load evaluation model; and 4, step 4: constructing a physical machine load evaluation model; and 5: classifying the state of the physical machine; step 6: selecting a virtual machine migration queue in the current state; and 7: selecting a proper target physical machine; and 8: carrying out virtual machine migration and updating the current use condition of the physical machine; and step 9: and (6) iterating steps 6, 7 and 8 until the maximum algorithm iteration number is reached or the load balance of the virtual machine is reached. The method has the advantages of high availability, energy conservation and load balance, can effectively realize resource balance and deployment optimization of the virtual machine, and achieves the effects of improving the service quality of the virtual machine and saving energy.
Description
Technical Field
The invention relates to the technology in the field of computers, in particular to a virtual machine resource balancing and deployment optimizing method.
Background
In the past, a passive strategy is often adopted for migration of a virtual machine on a physical machine, that is, when a fault occurs due to an excessively high operating load of the physical machine, such as a physical fault or downtime or a related warning notification, the virtual machine on the physical machine is passively migrated so as to improve the service quality of the currently promoted virtual machine; in this process, migration failure may also be caused by insufficient resources of the migration target physical machine, and therefore when the passive virtual machine migration is triggered, the situation that the service quality of the virtual machine has been continuously reduced often occurs, and there is a certain risk.
By setting a reasonable active migration virtual machine strategy, the occurrence of the above situation can be avoided, and a special goal can be achieved: if the virtual machine on the physical machine with higher load is migrated to the physical machine with lower load to realize resource balance, or the virtual machine on the physical machine with lower load is migrated to other physical machines to close the idle physical machine, the effect of energy saving is finally achieved; in addition, practical factors such as the use characteristics and high availability conditions of different physical machines need to be considered in the process. The method is realized by constructing a physical machine-virtual machine deployment relation model, a physical machine load evaluation model and a virtual machine load evaluation model, so that resource balance and deployment optimization of the virtual machine are effectively realized, and the effects of improving the service quality of the virtual machine and saving energy are achieved.
Disclosure of Invention
The invention aims to provide a virtual machine resource balancing and deployment optimizing method, which comprises the following specific steps:
step 1: preparing data; the physical machine data includes: the number of the physical machines and the configuration of each physical machine comprise the number of CPU cores, the size of a memory, the capacity of a disk, the bandwidth of network I/O and the like; the virtual machine data includes: the service type of each virtual machine, resource allocation of different dimensions, including CPU core number, memory size, disk capacity, network I/O bandwidth and the like, a host physical machine where the virtual machine is currently located, and time sequence data of each virtual machine on each resource dimension;
step 2: manually inputting parameters; the parameters include: physical machine utilization high threshold in either dimension: high _ use _ ratio; physical machine utilization underthreshold in either dimension: low _ use _ ratio; carrying a maximum number threshold value of virtual machines of the same service system on a physical machine: max _ same _ business _ num; a maximum number threshold for virtual machines on physical machines: max _ vm _ num;
and step 3: constructing a virtual machine load evaluation model; in the running process of an actual virtual machine, the use conditions of various resources of the virtual machine are interfered by unexpected interference, the CPU data are suddenly increased or decreased irregularly and temporarily, in order to avoid the influence of the extremely small-probability abnormal conditions on the load calculation of the virtual machine, abnormal values of time sequence data of each virtual machine in the virtual machine data on various resource dimensions are respectively eliminated, an abnormal value detection method is adopted and is an abnormal detection model integrated by combining a plurality of algorithms such as an STL time sequence decomposition method, an LOF clustering algorithm and the like, an abnormal point with higher abnormal values of various dimensions is screened out by adopting a voting mechanism, the median statistic of normal data in a residual time sequence is taken as the resource consumption of the normal data on the dimension, and the utilization rate of the virtual machine on the dimension is obtained;
and 4, step 4: constructing a physical machine load evaluation model; after the load condition of the virtual machine is obtained, accumulating the resource usage amount of the virtual machine set on each physical machine in any dimension to obtain the total usage amount of the virtual machine group, and dividing the value by the resource allocation amount of the physical machine in the dimension to obtain the utilization rate of the physical machine in the dimension; constructing a load evaluation model of the physical machine through calculation of each dimension;
and 5: classifying the state of the physical machine; carrying out state classification on the physical machine by using the prepared data, the virtual machine load evaluation model and the physical machine load evaluation model; by physical machine utilization high threshold in either dimension: high _ use _ ratio and physical machine utilization low threshold in either dimension: low _ use _ ratio; all indexes can be lower than the low utilization threshold of the dimension physical machine: setting the physical machine of low _ use _ ratio as a low-utilization queue physical machine, and enabling the utilization rate of any index physical machine to be higher than a high threshold value: setting a physical machine of high _ use _ ratio as a high-utilization-rate queue physical machine, and setting the other physical machines as migration target queue physical machines; the low-utilization-rate queue physical machine is a physical machine which realizes energy saving by migrating a virtual machine on the type of physical machine, and the high-utilization-rate queue physical machine is a physical machine which realizes resource balance by migrating a virtual machine on the type of physical machine;
step 6: selecting a virtual machine migration queue in the current state; selecting a physical machine with the lowest utilization rate from the low-utilization-rate queue physical machines, and selecting a virtual machine in a physical machine with the highest utilization rate from the high-utilization-rate queue physical machines as an object to be migrated; the physical machine with low utilization rate needs to migrate all virtual machines on the physical machine to other physical machines to achieve the aim of energy conservation; for a physical machine with high utilization rate, the physical machine only needs to be migrated until the utilization rate is lower than a high threshold value, namely, the upper part of virtual machines are selected for migration, and different strategies can be selected for virtual machine selection: in order to realize the high availability target, a type of virtual machine with the largest number of the same service systems can be selected, and in order to utilize the characteristics of the physical machine to the maximum extent, the virtual machine with the largest difference with the characteristics of the physical machine can be selected; quantitatively describing the characteristic difference between the virtual machine and the physical machine by designing a calculation scheme based on the configuration quantity of the physical machine and the usage quantity of the virtual machine;
and 7: selecting a proper target physical machine; after the virtual machine migration queue is selected, selecting a proper target physical machine to perform migration of the virtual machine, and adopting a greedy strategy on the selection method of the physical machine, namely preferentially considering the physical machine in the migration target queue physical machine obtained in the step 5;
and 8: carrying out virtual machine migration and updating the current use condition of the physical machine; after the virtual machine is migrated, updating the utilization rates and other indexes of a source physical machine and a target physical machine of the virtual machine, wherein the utilization rates and other indexes comprise the number of service systems carried on the physical machine and the number of virtual machines to be updated so as to perform a subsequent migration plan;
and step 9: and (6) iterating steps 6, 7 and 8 until the maximum algorithm iteration number is reached or the load balance of the virtual machine is reached.
Preferably, the conditions that the target physical machine should have in step 7 include:
a) after the physical machine is migrated into the virtual machine, the utilization rate of the physical machine is not increased suddenly, so that the physical machine becomes a high-utilization-rate queue physical machine;
b) the physical machine has the following high availability conditions: that is, the number of service systems of the virtual machine deployed on the physical machine is as small as possible and always smaller than max _ same _ business _ num;
c) the number of virtual machines of the physical machine is less than a specified threshold value max _ vm _ num of the maximum number of virtual machines;
d) it should be preferred to have a physical machine with low utilization and no identity to the virtual machine business system.
Compared with the prior art, the invention has the advantages that:
1) high availability: the number of the same service systems on each physical machine does not exceed the limit;
2) load balancing: the resource indexes are distributed on each physical machine in a balanced manner;
3) energy conservation: and closing the physical machine with low overall resource utilization rate to save energy.
Drawings
FIG. 1 is a flow chart of a method for balancing and optimizing deployment of virtual machine resources;
FIG. 2 is a schematic diagram of a virtual machine resource balancing and deployment optimization operation.
Detailed Description
The following detailed description of the embodiments of the present invention is provided with reference to the accompanying drawings, as shown in fig. 1, the following steps are performed:
step 1: and (4) preparing data. The physical machine data includes: the number of the physical machines and the configuration of each physical machine comprise the number of CPU cores, the size of a memory, the capacity of a disk, the bandwidth of network I/O and the like; the virtual machine data includes: the service type of each virtual machine, resource allocation of different dimensions, including CPU core number, memory size, disk capacity, network I/O bandwidth and the like, a host physical machine where the virtual machine is currently located, and time sequence data of each virtual machine on each resource dimension;
step 2: manually inputting parameters; the parameters include: physical machine utilization high threshold in either dimension: high _ use _ ratio; physical machine utilization underthreshold in either dimension: low _ use _ ratio; carrying a maximum number threshold value of virtual machines of the same service system on a physical machine: max _ same _ business _ num; a maximum number threshold for virtual machines on physical machines: max _ vm _ num;
and step 3: constructing a virtual machine load evaluation model; in the running process of an actual virtual machine, the use conditions of various resources of the virtual machine are interfered by unexpected interference, the CPU data are suddenly increased or decreased irregularly and temporarily, in order to avoid the influence of the extremely small-probability abnormal conditions on the load calculation of the virtual machine, abnormal values of time sequence data of each virtual machine in the virtual machine data on various resource dimensions are respectively eliminated, an abnormal value detection method is adopted and is an abnormal detection model integrated by combining a plurality of algorithms such as an STL time sequence decomposition method, an LOF clustering algorithm and the like, an abnormal point with higher abnormal values of various dimensions is screened out by adopting a voting mechanism, the median statistic of normal data in a residual time sequence is taken as the resource consumption of the normal data on the dimension, and the utilization rate of the virtual machine on the dimension is obtained;
and 4, step 4: constructing a physical machine load evaluation model; after the load condition of the virtual machine is obtained, accumulating the resource usage amount of the virtual machine set on each physical machine in any dimension to obtain the total usage amount of the virtual machine group, and dividing the value by the resource allocation amount of the physical machine in the dimension to obtain the utilization rate of the physical machine in the dimension; constructing a load evaluation model of the physical machine through calculation of each dimension;
and 5: classifying the state of the physical machine; as shown in fig. 2, the physical machine state classification is performed by using the prepared data, the virtual machine load evaluation model and the physical machine load evaluation model; by physical machine utilization high threshold in either dimension: high _ use _ ratio and physical machine utilization low threshold in either dimension: low _ use _ ratio; all indexes can be lower than the low utilization threshold of the dimension physical machine: setting the physical machine of low _ use _ ratio as a low-utilization queue physical machine, and enabling the utilization rate of any index physical machine to be higher than a high threshold value: setting a physical machine of high _ use _ ratio as a high-utilization-rate queue physical machine, and setting the other physical machines as migration target queue physical machines; the low-utilization-rate queue physical machine is a physical machine which realizes energy saving by migrating a virtual machine on the type of physical machine, and the high-utilization-rate queue physical machine is a physical machine which realizes resource balance by migrating a virtual machine on the type of physical machine;
step 6: selecting a virtual machine migration queue in the current state; selecting a physical machine with the lowest utilization rate from the low-utilization-rate queue physical machines, and selecting a virtual machine in a physical machine with the highest utilization rate from the high-utilization-rate queue physical machines as an object to be migrated; the physical machine with low utilization rate needs to migrate all virtual machines on the physical machine to other physical machines to achieve the aim of energy conservation; for a physical machine with high utilization rate, the physical machine only needs to be migrated until the utilization rate is lower than a high threshold value, namely, the upper part of virtual machines are selected for migration, and different strategies can be selected for virtual machine selection: in order to realize the high availability target, a type of virtual machine with the largest number of the same service systems can be selected, and in order to utilize the characteristics of the physical machine to the maximum extent, the virtual machine with the largest difference with the characteristics of the physical machine can be selected; quantitatively describing the characteristic difference between the virtual machine and the physical machine by designing a calculation scheme based on the configuration quantity of the physical machine and the usage quantity of the virtual machine;
and 7: selecting a proper target physical machine; after the virtual machine migration queue is selected, selecting a proper target physical machine to perform migration of the virtual machine, and adopting a greedy strategy on the selection method of the physical machine, namely preferentially considering the physical machine in the migration target queue physical machine obtained in the step 5; the conditions that the target physical machine should have include:
a) after the physical machine is migrated into the virtual machine, the utilization rate of the physical machine is not increased suddenly, so that the physical machine becomes a high-utilization-rate queue physical machine;
b) the physical machine has the following high availability conditions: that is, the number of service systems of the virtual machine deployed on the physical machine is as small as possible and always smaller than max _ same _ business _ num;
c) the number of virtual machines of the physical machine is less than a specified threshold value max _ vm _ num of the maximum number of virtual machines;
d) it should be preferred to have a physical machine with low utilization and no identity to the virtual machine business system.
And 8: carrying out virtual machine migration and updating the current use condition of the physical machine; after the virtual machine is migrated, updating the utilization rates and other indexes of a source physical machine and a target physical machine of the virtual machine, wherein the utilization rates and other indexes comprise the number of service systems carried on the physical machine and the number of virtual machines to be updated so as to perform a subsequent migration plan;
and step 9: and (6) iterating steps 6, 7 and 8 until the maximum algorithm iteration number is reached or the load balance of the virtual machine is reached, and outputting a migration scheme.
While the present invention has been described with reference to a limited number of embodiments and drawings, as described above, various modifications and changes will become apparent to those skilled in the art to which the present invention pertains. Accordingly, other embodiments are within the scope and spirit of the following claims and equivalents thereto.
Claims (2)
1. A virtual machine resource balancing and deployment optimization method specifically comprises the following steps:
step 1: preparing data; the physical machine data includes: the number of the physical machines and the configuration of each physical machine comprise the number of CPU cores, the size of a memory, the capacity of a disk, the bandwidth of network I/O and the like; the virtual machine data includes: the service type of each virtual machine, resource allocation of different dimensions, including CPU core number, memory size, disk capacity, network I/O bandwidth and the like, a host physical machine where the virtual machine is currently located, and time sequence data of each virtual machine on each resource dimension;
step 2: manually inputting parameters; the parameters include: physical machine utilization high threshold in either dimension: high _ use _ ratio; physical machine utilization underthreshold in either dimension: low _ use _ ratio; carrying a maximum number threshold value of virtual machines of the same service system on a physical machine: max _ same _ business _ num; a maximum number threshold for virtual machines on physical machines: max _ vm _ num;
and step 3: constructing a virtual machine load evaluation model; in the running process of an actual virtual machine, the use conditions of various resources of the virtual machine are interfered by unexpected interference, the CPU data are suddenly increased or decreased irregularly and temporarily, in order to avoid the influence of the extremely small-probability abnormal conditions on the load calculation of the virtual machine, abnormal values of time sequence data of each virtual machine in the virtual machine data on various resource dimensions are respectively eliminated, an abnormal value detection method is adopted and is an abnormal detection model integrated by combining a plurality of algorithms such as an STL time sequence decomposition method, an LOF clustering algorithm and the like, an abnormal point with higher abnormal values of various dimensions is screened out by adopting a voting mechanism, the median statistic of normal data in a residual time sequence is taken as the resource consumption of the normal data on the dimension, and the utilization rate of the virtual machine on the dimension is obtained;
and 4, step 4: constructing a physical machine load evaluation model; after the load condition of the virtual machine is obtained, accumulating the resource usage amount of the virtual machine set on each physical machine in any dimension to obtain the total usage amount of the virtual machine group, and dividing the value by the resource allocation amount of the physical machine in the dimension to obtain the utilization rate of the physical machine in the dimension; constructing a load evaluation model of the physical machine through calculation of each dimension;
and 5: classifying the state of the physical machine; carrying out state classification on the physical machine by using the prepared data, the virtual machine load evaluation model and the physical machine load evaluation model; by physical machine utilization high threshold in either dimension: high _ use _ ratio and physical machine utilization low threshold in either dimension: low _ use _ ratio; all indexes can be lower than the low utilization threshold of the dimension physical machine: setting the physical machine of low _ use _ ratio as a low-utilization queue physical machine, and enabling the utilization rate of any index physical machine to be higher than a high threshold value: setting a physical machine of high _ use _ ratio as a high-utilization-rate queue physical machine, and setting the other physical machines as migration target queue physical machines; the low-utilization-rate queue physical machine is a physical machine which realizes energy saving by migrating a virtual machine on the type of physical machine, and the high-utilization-rate queue physical machine is a physical machine which realizes resource balance by migrating a virtual machine on the type of physical machine;
step 6: selecting a virtual machine migration queue in the current state; selecting a physical machine with the lowest utilization rate from the low-utilization-rate queue physical machines, and selecting a virtual machine in a physical machine with the highest utilization rate from the high-utilization-rate queue physical machines as an object to be migrated; the physical machine with low utilization rate needs to migrate all virtual machines on the physical machine to other physical machines to achieve the aim of energy conservation; for a physical machine with high utilization rate, the physical machine only needs to be migrated until the utilization rate is lower than a high threshold value, namely, the upper part of virtual machines are selected for migration, and different strategies can be selected for virtual machine selection: in order to realize the high availability target, a type of virtual machine with the largest number of the same service systems can be selected, and in order to utilize the characteristics of the physical machine to the maximum extent, the virtual machine with the largest difference with the characteristics of the physical machine can be selected; quantitatively describing the characteristic difference between the virtual machine and the physical machine by designing a calculation scheme based on the configuration quantity of the physical machine and the usage quantity of the virtual machine;
and 7: selecting a proper target physical machine; after the virtual machine migration queue is selected, selecting a proper target physical machine to perform migration of the virtual machine, and adopting a greedy strategy on the selection method of the physical machine, namely preferentially considering the physical machine in the migration target queue physical machine obtained in the step 5;
and 8: carrying out virtual machine migration and updating the current use condition of the physical machine; after the virtual machine is migrated, updating the utilization rates and other indexes of a source physical machine and a target physical machine of the virtual machine, wherein the utilization rates and other indexes comprise the number of service systems carried on the physical machine and the number of virtual machines to be updated so as to perform a subsequent migration plan;
and step 9: and (6) iterating steps 6, 7 and 8 until the maximum algorithm iteration number is reached or the load balance of the virtual machine is reached.
2. The method for balancing and optimizing the deployment of the resources of the virtual machine according to claim 1, wherein: the conditions that the target physical machine should have in step 7 include:
a) after the physical machine is migrated into the virtual machine, the utilization rate of the physical machine is not increased suddenly, so that the physical machine becomes a high-utilization-rate queue physical machine;
b) the physical machine has the following high availability conditions: that is, the number of service systems of the virtual machine deployed on the physical machine is as small as possible and always smaller than max _ same _ business _ num;
c) the number of virtual machines of the physical machine is less than a specified threshold value max _ vm _ num of the maximum number of virtual machines;
d) it should be preferred to have a physical machine with low utilization and no identity to the virtual machine business system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910880143.9A CN110647381B (en) | 2019-09-18 | 2019-09-18 | Virtual machine resource balancing and deployment optimizing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910880143.9A CN110647381B (en) | 2019-09-18 | 2019-09-18 | Virtual machine resource balancing and deployment optimizing method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110647381A true CN110647381A (en) | 2020-01-03 |
| CN110647381B CN110647381B (en) | 2023-06-06 |
Family
ID=69010745
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910880143.9A Active CN110647381B (en) | 2019-09-18 | 2019-09-18 | Virtual machine resource balancing and deployment optimizing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110647381B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111538560A (en) * | 2020-03-09 | 2020-08-14 | 西安电子科技大学 | Virtual machine deployment method and device, electronic equipment and storage medium thereof |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012164624A1 (en) * | 2011-06-01 | 2012-12-06 | 株式会社日立製作所 | Virtual machine resource management device and management method |
| CN104008002A (en) * | 2014-06-17 | 2014-08-27 | 电子科技大学 | Target host selection method for deploying virtual machine under cloud platform environment |
| CN105279023A (en) * | 2015-11-27 | 2016-01-27 | 浪潮(北京)电子信息产业有限公司 | Virtual machine migration method and device |
| US20170286147A1 (en) * | 2014-09-22 | 2017-10-05 | China Unionpay Co., Ltd. | System and method for load estimation of virtual machines in a cloud environment and serving node |
| CN108897598A (en) * | 2018-06-13 | 2018-11-27 | 南京享达汉辰网络科技有限公司 | A kind of virtual machine Autonomic Migration Framework system and method for optimization |
| US20190028435A1 (en) * | 2017-07-20 | 2019-01-24 | Nicira, Inc. | Enhanced network processing of virtual node data packets |
-
2019
- 2019-09-18 CN CN201910880143.9A patent/CN110647381B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012164624A1 (en) * | 2011-06-01 | 2012-12-06 | 株式会社日立製作所 | Virtual machine resource management device and management method |
| CN104008002A (en) * | 2014-06-17 | 2014-08-27 | 电子科技大学 | Target host selection method for deploying virtual machine under cloud platform environment |
| US20170286147A1 (en) * | 2014-09-22 | 2017-10-05 | China Unionpay Co., Ltd. | System and method for load estimation of virtual machines in a cloud environment and serving node |
| CN105279023A (en) * | 2015-11-27 | 2016-01-27 | 浪潮(北京)电子信息产业有限公司 | Virtual machine migration method and device |
| US20190028435A1 (en) * | 2017-07-20 | 2019-01-24 | Nicira, Inc. | Enhanced network processing of virtual node data packets |
| CN108897598A (en) * | 2018-06-13 | 2018-11-27 | 南京享达汉辰网络科技有限公司 | A kind of virtual machine Autonomic Migration Framework system and method for optimization |
Non-Patent Citations (2)
| Title |
|---|
| 兰文姗: "《基于SLA 的云数据中心负载均衡理论研究》", 《武汉理工大学学报( 信息与管理工程版)》 * |
| 张智俊: "《基于LP＆GＲ 算法的多优先级》", 《APPLICATION ＲESEARCH OF COMPUTERS》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111538560A (en) * | 2020-03-09 | 2020-08-14 | 西安电子科技大学 | Virtual machine deployment method and device, electronic equipment and storage medium thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110647381B (en) | 2023-06-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107592345B (en) | Transaction current limiting device, method and transaction system | |
| CN103595651B (en) | Distributed data stream processing method and system | |
| CN112685170B (en) | Dynamic optimization of backup strategies | |
| Chen et al. | Elastic parameter server load distribution in deep learning clusters | |
| CN102724277A (en) | Virtual machine thermomigration method, virtual machine arrangement method, server and cluster system | |
| CN103023801B (en) | A kind of network intermediate node cache optimization method analyzed based on traffic characteristic | |
| CN104679594B (en) | A kind of middleware distributed computing method | |
| US20220300345A1 (en) | Entity and Method Performed therein for Handling Computational Resources | |
| CN111708629B (en) | Resource allocation method and device, electronic equipment and storage medium | |
| CN104484600B (en) | Intrusion detection method and device based on improved density clustering | |
| US20220035665A1 (en) | Sharing of compute resources between the virtualized radio access network (vran) and other workloads | |
| CN112711479A (en) | Load balancing system, method and device of server cluster and storage medium | |
| CN110597598B (en) | Control method for virtual machine migration in cloud environment | |
| CN107203256B (en) | Energy-saving distribution method and device under network function virtualization scene | |
| CN110647381B (en) | Virtual machine resource balancing and deployment optimizing method | |
| CN118138590A (en) | Data center load balancing method | |
| CN114691372A (en) | Group intelligent control method of multimedia end edge cloud system | |
| CN105740077B (en) | Task allocation method suitable for cloud computing | |
| CN110728372B (en) | Cluster design method and cluster system for dynamic loading of artificial intelligent model | |
| CN104050189B (en) | The page shares processing method and processing device | |
| CN106569728B (en) | Processing method and device for sharing write cache by multiple disk arrays RAID (redundant array of independent disks) | |
| CN113867736B (en) | Deployment scheme generation method and device | |
| WO2017213065A1 (en) | Service management system, service management method, and recording medium | |
| CN108829520B (en) | Server resource allocation method and device in cloud environment | |
| CN114816691A (en) | Method and device for optimizing parallelism of flow calculation task, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |