CN112433812A - Method, system, equipment and computer medium for virtual machine cross-cluster migration - Google Patents
Method, system, equipment and computer medium for virtual machine cross-cluster migration Download PDFInfo
- Publication number
- CN112433812A CN112433812A CN202011306098.5A CN202011306098A CN112433812A CN 112433812 A CN112433812 A CN 112433812A CN 202011306098 A CN202011306098 A CN 202011306098A CN 112433812 A CN112433812 A CN 112433812A
- Authority
- CN
- China
- Prior art keywords
- target
- cluster
- virtual machine
- migration
- information
- 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.)
- Pending
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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Stored Programmes (AREA)
Abstract
The application discloses a method, a system, equipment and a computer medium for migrating virtual machines across clusters, which are applied to a source cluster of an OpenStack cloud platform and used for determining a target cluster and a target virtual machine to be migrated in the source cluster; configuring the storage back end of the target cluster as the storage back end of the source cluster, and migrating the storage information of the target virtual machine to the storage back end of the target cluster; determining a target physical host in a target cluster; determining a hot migration mode of the running information of the target virtual machine; and migrating the running information to the target physical host according to a hot migration mode. In the application, the source cluster migrates the storage information of the target virtual machine to the target cluster, so that the time of cross-cluster migration can be reduced, the migration risk can be reduced, then the live migration mode of the running information of the target virtual machine is determined, and the running information is migrated to the target physical host according to the live migration mode, so that the migration of the running information meets the live migration condition, and the applicability is good.
Description
Technical Field
The present application relates to the field of cloud platform technologies, and in particular, to a method, a system, a device, and a computer medium for cross-cluster migration of a virtual machine.
Background
With the rapid development of the internet and the IT industry, the application of the cloud platform is more and more extensive. The cloud platform refers to services based on hardware resources and software resources, and provides computing, network and storage capabilities. In the process, the cloud platform is managed through OpenStack.
Due to the fact that cloud data centers are built based on OpenStack, the cloud data centers are larger in scale, multi-cluster disaster tolerance, high-availability design and rapid iteration of OpenStack versions, enterprises or data centers inevitably have a plurality of OpenStack versions or clusters in the building process no matter from the requirements of cluster stability, data safety and functions, and accordingly cross-cluster migration work among a plurality of OpenStack platforms occurs.
In summary, how to implement cross-cluster migration of virtual machines is a problem to be solved urgently by those skilled in the art.
Disclosure of Invention
The application aims to provide a virtual machine cross-cluster migration method which can solve the technical problem of how to realize the cross-cluster migration of virtual machines to a certain extent. The application also provides a virtual machine cross-cluster migration system, equipment and a computer readable storage medium.
In order to achieve the above purpose, the present application provides the following technical solutions:
a virtual machine cross-cluster migration method is applied to a source cluster of an OpenStack cloud platform and comprises the following steps:
determining a target cluster and a target virtual machine to be migrated in the source cluster;
configuring the storage back end of the target cluster as the storage back end of the source cluster, and migrating the storage information of the target virtual machine to the storage back end of the target cluster;
determining a target physical host in the target cluster;
determining a hot migration mode of the running information of the target virtual machine;
and migrating the running information to the target physical host according to the hot migration mode.
Preferably, the determining a target physical host in the target cluster includes:
sending the virtual machine information of the target virtual machine to the target cluster so that the target cluster determines the physical host information of the target physical host based on the virtual machine information and NUMA perception;
receiving the physical host information returned by the target cluster;
determining the target physical host based on the physical host information.
Preferably, the determining a target physical host in the target cluster includes:
and determining the target physical host through a genetic algorithm based on the performance information of the physical hosts in the target cluster.
Preferably, the determining a live migration mode of the operation information of the target virtual machine includes:
acquiring the running information of the target virtual machine;
determining the heat transfer mode of the operation information based on an intelligent decision method;
the running information comprises CPU utilization rate, memory utilization rate, network bandwidth resources and dirty page rate; the hot migration mode comprises a migration acceleration method and/or a compression algorithm; the migration acceleration method comprises a multithreading compression method, an automatic convergence method and a post-copy method; the compression algorithm comprises a zstd algorithm, a zlib algorithm and an lz4 algorithm.
Preferably, the migrating the running information to the target physical host according to the live migration method includes:
determining dirty page updating frequency of a page in the target virtual machine;
determining the page with the dirty page updating frequency larger than a preset value as a target page;
and in the shutdown stage of the target virtual machine, migrating the target page to the target physical host.
Preferably, the configuring the storage backend of the target cluster as the storage backend of the source cluster includes:
judging whether the target cluster and the source cluster are logged in a secret-free manner or not;
if the target cluster and the source cluster are logged in a secret-free mode, judging whether the target virtual machine is in an operating state or not;
and if the target virtual machine is in a running state, executing the step of configuring the storage back end of the target cluster as the storage back end of the source cluster.
Preferably, after migrating the running information to the target physical host according to the live migration method, the method further includes:
judging whether the target virtual machine is migrated successfully or not;
if the migration is successful, deleting the virtual machine information of the target virtual machine in the source cluster;
and if the migration fails, rolling back the target virtual machine, and deleting the virtual machine information of the target virtual machine on the target physical host.
A virtual machine cross-cluster migration system is applied to a source cluster of an OpenStack cloud platform and comprises the following steps:
the first determining module is used for determining a target cluster and a target virtual machine to be migrated in the source cluster;
a first migration module, configured to configure a storage back end of the target cluster as a storage back end of the source cluster, and migrate storage information of the target virtual machine to the storage back end of the target cluster;
a second determining module, configured to determine a target physical host in the target cluster;
the third determining module is used for determining a live migration mode of the running information of the target virtual machine;
and the second migration module is used for migrating the running information to the target physical host according to the hot migration mode.
A virtual machine cross-cluster migration apparatus, comprising:
a memory for storing a computer program;
a processor, configured to implement the steps of the virtual machine cross-cluster migration method as described above when executing the computer program.
A computer readable storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps of the virtual machine cross cluster migration method as set out in any one of the preceding claims.
The method for migrating the virtual machines across the clusters is applied to a source cluster of an OpenStack cloud platform, and a target cluster and a target virtual machine to be migrated in the source cluster are determined; configuring the storage back end of the target cluster as the storage back end of the source cluster, and migrating the storage information of the target virtual machine to the storage back end of the target cluster; determining a target physical host in a target cluster; determining a hot migration mode of the running information of the target virtual machine; and migrating the running information to the target physical host according to a hot migration mode. In the application, the source cluster migrates the storage information of the target virtual machine to the target cluster, so that the time of cross-cluster migration can be reduced, the migration risk can be reduced, then the live migration mode of the running information of the target virtual machine is determined, and the running information is migrated to the target physical host according to the live migration mode, so that the migration of the running information meets the live migration condition, and the applicability is good. The system, the device and the computer readable storage medium for virtual machine cross-cluster migration solve the corresponding technical problems.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of a method for migrating a virtual machine across clusters according to an embodiment of the present disclosure;
fig. 2 is a schematic structural diagram of a virtual machine cross-cluster migration system according to an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of a virtual machine cross-cluster migration device according to an embodiment of the present application;
fig. 4 is another schematic structural diagram of a virtual machine cross-cluster migration device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Referring to fig. 1, fig. 1 is a flowchart of a virtual machine cross-cluster migration method according to an embodiment of the present disclosure.
The virtual machine cross-cluster migration method provided by the embodiment of the application is applied to a source cluster of an OpenStack cloud platform, and can comprise the following steps:
step S101: and determining target virtual machines to be migrated in the target cluster and the source cluster.
In practical application, because the virtual machines on the source cluster are to be migrated to other clusters, the source cluster may determine the target cluster and the target virtual machine to be migrated in the source cluster, and the target cluster is also the cluster after the target virtual machine is migrated.
The manner in which the source cluster determines the target cluster and the target virtual machine may be determined according to actual needs, for example, the source cluster may determine the corresponding cluster as the target cluster, and determine the corresponding virtual machine as the target virtual machine, under user operation.
Step S102: and configuring the storage back end of the target cluster as the storage back end of the source cluster, and migrating the storage information of the target virtual machine to the storage back end of the target cluster.
In practical application, the migration of the target virtual machine includes the migration of storage information and running information, and the migration of the storage information is long in time consumption and easy to cause risks.
Step S103: a target physical host in the target cluster is determined.
In practical application, the operation of the virtual machine needs to be performed by means of the physical host, so that the source cluster configures the storage back end of the target cluster as the storage back end of the source cluster, and after the storage information of the target virtual machine is migrated to the storage back end of the target cluster, when the operation information is migrated, the target physical host in the target cluster can be determined first, the target physical host is also the physical host receiving the target virtual machine, the number and the determination mode of the target physical host can be determined according to actual needs, and the application is not specifically limited herein.
Step S104: and determining a hot migration mode of the running information of the target virtual machine.
Step S105: and migrating the running information to the target physical host according to a hot migration mode.
In practical application, because Migration of running information of a virtual machine is mostly performed in a Live Migration manner, Live Migration (Live Migration) is called dynamic Migration and real-time Migration, that is, virtual machine storage/recovery, usually the running state of the whole virtual machine is completely stored, and meanwhile, the running state can be quickly recovered to an original hardware platform or even different hardware platforms, after recovery, the virtual machine still runs smoothly, and a user cannot perceive any difference; therefore, after determining the target physical host in the target cluster, the source cluster can determine the live migration mode of the running information of the target virtual machine, and migrate the running information to the target physical host according to the live migration mode, so as to complete the cross-cluster migration of the virtual machine.
The method for migrating the virtual machines across the clusters is applied to a source cluster of an OpenStack cloud platform, and a target cluster and a target virtual machine to be migrated in the source cluster are determined; configuring the storage back end of the target cluster as the storage back end of the source cluster, and migrating the storage information of the target virtual machine to the storage back end of the target cluster; determining a target physical host in a target cluster; determining a hot migration mode of the running information of the target virtual machine; and migrating the running information to the target physical host according to a hot migration mode. In the application, the source cluster migrates the storage information of the target virtual machine to the target cluster, so that the time of cross-cluster migration can be reduced, the migration risk can be reduced, then the live migration mode of the running information of the target virtual machine is determined, and the running information is migrated to the target physical host according to the live migration mode, so that the migration of the running information meets the live migration condition, and the applicability is good.
In the virtual machine cross-cluster migration method provided by the embodiment of the application, a source cluster can send virtual machine information of a target virtual machine to a target cluster in the process of determining the target physical host in the target cluster, so that the target cluster determines physical host information of the target physical host based on the virtual machine information and NUMA (non uniform memory access) perception; receiving physical host information returned by a target cluster; a target physical host is determined based on the physical host information.
That is, in practical applications, the target physical host may be automatically determined by the target cluster based on the virtual machine information of the target virtual machine, in this process, the target cluster may send an instruction to the source cluster to query the virtual machine information of the target virtual machine, and after receiving the instruction, the source cluster may return the virtual machine information, such as configuration information, hardware information, direct connection device information, specification information, mirror image information, network card information, information of a mount volume, tag information, basic attribute information, and the like, to the target cluster through an object; after the target cluster, establishing basic information of a target virtual machine to be migrated, such as an image file, a network card, specification information and the like, reserving corresponding CPU (central processing unit) resources, memory resources and the like, performing NUMA (non-uniform memory access) perception on a physical host of the target cluster according to NUMA information of the virtual machine, such as self-adaption of CPU binding, self-adaption of large memory pages, namely hugepage, check and verification of PCI (peripheral component interconnect) equipment and the like, determining physical host information of the target physical host, generating an object and returning the object to the source cluster, and enabling the source cluster to determine the target physical host according to the physical host information.
Note that NUMA (Non-Uniform Memory Access) is an architectural model of how multiple CPUs Access Memory, and today CPUs are basically NUMA architectures, and linux kernel 2.5 starts to support NUMA.
In the method for migrating the virtual machine across the clusters provided by the embodiment of the application, the source cluster determines the target physical host in the target cluster, and the target physical host can be determined through a genetic algorithm based on the performance information of the physical host in the target cluster.
That is, the source cluster may automatically determine the target physical host in the target cluster, and the performance information of the physical host according to the target physical host may include CPU resources, memory resources, resource energy consumption values, and the like, for example, the physical host with the optimal performance information may be determined as the target physical host.
In the virtual machine cross-cluster migration method provided by the embodiment of the application, in the process of determining the live migration mode of the running information of the target virtual machine, the source cluster can acquire the running information of the target virtual machine in order to determine the live migration mode; and determining a heat transfer mode of the operation information based on an intelligent decision method. The running information may include a CPU utilization rate, a memory utilization rate, a network bandwidth resource, and a dirty page rate; the hot migration mode can comprise a migration acceleration method and/or a compression algorithm; the migration acceleration method comprises a multithreading compression method, an automatic convergence method and a post-copy method; the compression algorithms include the zstd algorithm, zlib algorithm, lz4 algorithm.
It should be noted that the intelligent Decision method may be a Decision Tree algorithm, etc., the Decision Tree (Decision Tree) algorithm is a very common machine learning supervised classification algorithm, the Decision Tree generation algorithm has ID3, C4.5 and CART, etc., and is a Tree structure, where each internal node represents a judgment on an attribute, each branch represents an output of a judgment result, and finally each leaf node represents a classification result, and supervised learning is to give enough training samples, and each sample has a set of attributes and a classification result, so that a Decision Tree model is obtained by learning these samples, thereby obtaining the capability of correctly classifying new data; the zstd (zstandard) compression algorithm is a lossless data compression algorithm open source by Facebook, zstd has a compression ratio comparable to that of the deflata (. zip, gzip) algorithm in design, but has higher compression and decompression speeds; the zlib compression algorithm is a lossless compression algorithm, is an improvement on GZIP, removes some allowance information contained in the compressed file, and improves the compression speed of the data in the buffer area; the lz4 compression algorithm is the most efficient compression algorithm in the current synthesis, the compression and decompression speed is emphasized more, the compression ratio is not the first, in the current android and apple operating system, the lz4 algorithm is used in the memory compression technology, the mobile phone memory is compressed in time to bring more memory space, and the time is changed in space essentially; multithread compression, i.e., the use of multiple compression threads to accelerate live migration; when the dynamic migration is carried out during automatic convergence, the QEMU (virtual operating system simulator) can reduce the running speed of the virtual machine, thereby reducing the operation of writing the memory; the post-copy is that before all the RAMs (Random Access memories) are migrated to the target physical machine, the virtual machine is started on the target node, and pulls the rest pages as required; live Migration (Live Migration) is called Live Migration and real-time Migration, that is, storage/recovery of a virtual machine, generally, the running state of the entire virtual machine is completely stored, and meanwhile, the virtual machine can be quickly recovered to an original hardware platform or even different hardware platforms, after recovery, the virtual machine still runs smoothly, and a user cannot perceive any difference. In a specific application scenario, a migratetoriri 3() function of libvirt may be called to transfer a migration parameter corresponding to a live migration mode into QEMU for live migration.
In the virtual machine cross-cluster migration method provided by the embodiment of the application, some pages generate dirty data to form dirty pages, if one page always generates the dirty pages, the cross-cluster migration process of the virtual machine can have more time for transmitting the dirty pages to influence the migration of the target virtual machine, and in order to avoid excessive migration of the dirty pages, the source cluster can determine the dirty page update frequency of the pages in the target virtual machine in the process of migrating the running information to the target physical host according to a hot migration mode; determining the page with the dirty page updating frequency larger than the preset value as a target page; and in the shutdown stage of the target virtual machine, migrating the target page to the target physical host.
In the method for migrating the virtual machine across the clusters provided by the embodiment of the application, in the process that the source cluster configures the storage back end of the target cluster as the storage back end of the source cluster, whether the target cluster and the source cluster are logged in a secret-free manner can be judged; if the target cluster and the source cluster are logged in without secret, judging whether the target virtual machine is in a running state; and if the target virtual machine is in the running state, executing the step of configuring the storage back end of the target cluster as the storage back end of the source cluster.
That is, the cross-cluster migration method of the virtual machine provided by the present application can be really run only when the source cluster and the target cluster are in a secret-free login state and the target virtual machine is in a running state, so as to ensure that the virtual machine can complete the cross-cluster migration.
In the virtual machine cross-cluster migration method provided by the embodiment of the application, after the source cluster migrates the running information to the target physical host according to the live migration mode, whether the target virtual machine is successfully migrated can be judged; if the migration is successful, deleting the virtual machine information of the target virtual machine in the source cluster; and if the migration fails, rolling back the target virtual machine and deleting the virtual machine information of the target virtual machine on the target physical host.
Referring to fig. 2, fig. 2 is a schematic structural diagram of a virtual machine cross-cluster migration system according to an embodiment of the present disclosure.
The virtual machine cross-cluster migration system provided in the embodiment of the present application is applied to a source cluster of an OpenStack cloud platform, and may include:
a first determining module 101, configured to determine a target virtual machine to be migrated in a target cluster and a source cluster;
the first migration module 102 is configured to configure a storage back end of a target cluster as a storage back end of a source cluster, and migrate storage information of a target virtual machine to the storage back end of the target cluster;
a second determining module 103, configured to determine a target physical host in a target cluster;
a third determining module 104, configured to determine a live migration manner of the operation information of the target virtual machine;
the second migration module 105 is configured to migrate the running information to the target physical host according to a live migration manner.
The virtual machine cross-cluster migration system provided in the embodiment of the present application is applied to a source cluster of an OpenStack cloud platform, and the second determining module may include:
the first sending unit is used for sending the virtual machine information of the target virtual machine to the target cluster so that the target cluster can determine the physical host information of the target physical host based on the virtual machine information and NUMA (non uniform memory access);
the first receiving unit is used for receiving the physical host information returned by the target cluster;
a first determination unit to determine a target physical host based on the physical host information.
The virtual machine cross-cluster migration system provided in the embodiment of the present application is applied to a source cluster of an OpenStack cloud platform, and the second determining module may include:
and the second determining unit is used for determining the target physical host through a genetic algorithm based on the performance information of the physical hosts in the target cluster.
The virtual machine cross-cluster migration system provided in the embodiment of the present application is applied to a source cluster of an OpenStack cloud platform, and the third determining module may include:
the first acquisition unit is used for acquiring the running information of the target virtual machine;
and the third determining unit is used for determining the heat transfer mode of the operation information based on an intelligent decision method.
The running information comprises CPU utilization rate, memory utilization rate, network bandwidth resources and dirty page rate; the hot migration mode comprises a migration acceleration method and/or a compression algorithm; the migration acceleration method comprises a multithreading compression method, an automatic convergence method and a post-copy method; the compression algorithms include the zstd algorithm, zlib algorithm, lz4 algorithm.
The virtual machine cross-cluster migration system provided in the embodiment of the present application is applied to a source cluster of an OpenStack cloud platform, and the second migration module may include:
a fourth determining unit, configured to determine a dirty page update frequency of a page in the target virtual machine;
a fifth determining unit, configured to determine, as a target page, a page with a dirty page update frequency greater than a preset value;
and the first migration unit is used for migrating the target page to the target physical host at the shutdown stage of the target virtual machine.
The virtual machine cross-cluster migration system provided by the embodiment of the application is applied to a source cluster of an OpenStack cloud platform, and the first migration module may include:
the first judgment unit is used for judging whether the target cluster and the source cluster are logged in a secret-free mode or not; if the target cluster and the source cluster are logged in without secret, judging whether the target virtual machine is in a running state; and if the target virtual machine is in the running state, executing the step of configuring the storage back end of the target cluster as the storage back end of the source cluster.
The virtual machine cross-cluster migration system provided in the embodiment of the present application is applied to a source cluster of an OpenStack cloud platform, and may further include:
the first judgment module is used for judging whether the target virtual machine is successfully migrated or not after the second migration module migrates the running information to the target physical host according to the hot migration mode; if the migration is successful, deleting the virtual machine information of the target virtual machine in the source cluster; and if the migration fails, rolling back the target virtual machine and deleting the virtual machine information of the target virtual machine on the target physical host.
The application also provides a virtual machine cross-cluster migration device and a computer readable storage medium, which both have the corresponding effects of the virtual machine cross-cluster migration method provided by the embodiment of the application. Referring to fig. 3, fig. 3 is a schematic structural diagram of a virtual machine cross-cluster migration apparatus according to an embodiment of the present disclosure.
The virtual machine cross-cluster migration device provided by the embodiment of the application comprises a memory 201 and a processor 202, wherein a computer program is stored in the memory 201, and the processor 202 implements the following steps when executing the computer program:
determining a target virtual machine to be migrated in a target cluster and a source cluster;
configuring the storage back end of the target cluster as the storage back end of the source cluster, and migrating the storage information of the target virtual machine to the storage back end of the target cluster;
determining a target physical host in a target cluster;
determining a hot migration mode of the running information of the target virtual machine;
and migrating the running information to the target physical host according to a hot migration mode.
The virtual machine cross-cluster migration device provided by the embodiment of the application comprises a memory 201 and a processor 202, wherein a computer program is stored in the memory 201, and the processor 202 implements the following steps when executing the computer program: sending the virtual machine information of the target virtual machine to a target cluster so that the target cluster determines the physical host information of the target physical host based on the virtual machine information and NUMA perception; receiving physical host information returned by a target cluster; a target physical host is determined based on the physical host information.
The virtual machine cross-cluster migration device provided by the embodiment of the application comprises a memory 201 and a processor 202, wherein a computer program is stored in the memory 201, and the processor 202 implements the following steps when executing the computer program: and determining the target physical host through a genetic algorithm based on the performance information of the physical hosts in the target cluster.
The virtual machine cross-cluster migration device provided by the embodiment of the application comprises a memory 201 and a processor 202, wherein a computer program is stored in the memory 201, and the processor 202 implements the following steps when executing the computer program: acquiring running information of a target virtual machine; and determining a heat transfer mode of the operation information based on an intelligent decision method. The running information comprises CPU utilization rate, memory utilization rate, network bandwidth resources and dirty page rate; the hot migration mode comprises a migration acceleration method and/or a compression algorithm; the migration acceleration method comprises a multithreading compression method, an automatic convergence method and a post-copy method; the compression algorithms include the zstd algorithm, zlib algorithm, lz4 algorithm.
The virtual machine cross-cluster migration device provided by the embodiment of the application comprises a memory 201 and a processor 202, wherein a computer program is stored in the memory 201, and the processor 202 implements the following steps when executing the computer program: according to a hot migration mode, determining dirty page updating frequency of a page in a target virtual machine in the process of migrating running information to a target physical host; determining the page with the dirty page updating frequency larger than the preset value as a target page; and in the shutdown stage of the target virtual machine, migrating the target page to the target physical host.
The virtual machine cross-cluster migration device provided by the embodiment of the application comprises a memory 201 and a processor 202, wherein a computer program is stored in the memory 201, and the processor 202 implements the following steps when executing the computer program: judging whether the target cluster and the source cluster are logged in without secret; if the target cluster and the source cluster are logged in without secret, judging whether the target virtual machine is in a running state; and if the target virtual machine is in the running state, executing the step of configuring the storage back end of the target cluster as the storage back end of the source cluster.
The virtual machine cross-cluster migration device provided by the embodiment of the application comprises a memory 201 and a processor 202, wherein a computer program is stored in the memory 201, and the processor 202 implements the following steps when executing the computer program: according to a hot migration mode, after the running information is migrated to the target physical host, whether the migration of the target virtual machine is successful is judged; if the migration is successful, deleting the virtual machine information of the target virtual machine in the source cluster; and if the migration fails, rolling back the target virtual machine and deleting the virtual machine information of the target virtual machine on the target physical host.
Referring to fig. 4, another virtual machine cross-cluster migration device provided in the embodiment of the present application may further include: an input port 203 connected to the processor 202, for transmitting externally input commands to the processor 202; a display unit 204 connected to the processor 202, for displaying the processing result of the processor 202 to the outside; and the communication module 205 is connected with the processor 202 and is used for realizing communication between the virtual machine and the outside world across the cluster migration device. The display unit 204 may be a display panel, a laser scanning display, or the like; the communication method adopted by the communication module 205 includes, but is not limited to, mobile high definition link technology (HML), Universal Serial Bus (USB), High Definition Multimedia Interface (HDMI), and wireless connection: wireless fidelity technology (WiFi), bluetooth communication technology, bluetooth low energy communication technology, ieee802.11s based communication technology.
A computer-readable storage medium is provided in an embodiment of the present application, in which a computer program is stored, and when the computer program is executed by a processor, the computer program implements the following steps:
determining a target virtual machine to be migrated in a target cluster and a source cluster;
configuring the storage back end of the target cluster as the storage back end of the source cluster, and migrating the storage information of the target virtual machine to the storage back end of the target cluster;
determining a target physical host in a target cluster;
determining a hot migration mode of the running information of the target virtual machine;
and migrating the running information to the target physical host according to a hot migration mode.
A computer-readable storage medium is provided in an embodiment of the present application, in which a computer program is stored, and when the computer program is executed by a processor, the computer program implements the following steps: sending the virtual machine information of the target virtual machine to a target cluster so that the target cluster determines the physical host information of the target physical host based on the virtual machine information and NUMA perception; receiving physical host information returned by a target cluster; a target physical host is determined based on the physical host information.
A computer-readable storage medium is provided in an embodiment of the present application, in which a computer program is stored, and when the computer program is executed by a processor, the computer program implements the following steps: and determining the target physical host through a genetic algorithm based on the performance information of the physical hosts in the target cluster.
A computer-readable storage medium is provided in an embodiment of the present application, in which a computer program is stored, and when the computer program is executed by a processor, the computer program implements the following steps: acquiring running information of a target virtual machine; and determining a heat transfer mode of the operation information based on an intelligent decision method. The running information comprises CPU utilization rate, memory utilization rate, network bandwidth resources and dirty page rate; the hot migration mode comprises a migration acceleration method and/or a compression algorithm; the migration acceleration method comprises a multithreading compression method, an automatic convergence method and a post-copy method; the compression algorithms include the zstd algorithm, zlib algorithm, lz4 algorithm.
A computer-readable storage medium is provided in an embodiment of the present application, in which a computer program is stored, and when the computer program is executed by a processor, the computer program implements the following steps: determining dirty page updating frequency of a page in a target virtual machine; determining the page with the dirty page updating frequency larger than the preset value as a target page; and in the shutdown stage of the target virtual machine, migrating the target page to the target physical host.
A computer-readable storage medium is provided in an embodiment of the present application, in which a computer program is stored, and when the computer program is executed by a processor, the computer program implements the following steps: judging whether the target cluster and the source cluster are logged in without secret; if the target cluster and the source cluster are logged in without secret, judging whether the target virtual machine is in a running state; and if the target virtual machine is in the running state, executing the step of configuring the storage back end of the target cluster as the storage back end of the source cluster.
A computer-readable storage medium is provided in an embodiment of the present application, in which a computer program is stored, and when the computer program is executed by a processor, the computer program implements the following steps: according to a hot migration mode, after the running information is migrated to the target physical host, whether the migration of the target virtual machine is successful is judged; if the migration is successful, deleting the virtual machine information of the target virtual machine in the source cluster; and if the migration fails, rolling back the target virtual machine and deleting the virtual machine information of the target virtual machine on the target physical host.
The computer-readable storage media to which this application relates include Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage media known in the art.
For a description of relevant parts in the virtual machine cross-cluster migration system, the virtual machine cross-cluster migration device, and the computer readable storage medium provided in the embodiments of the present application, reference is made to detailed descriptions of corresponding parts in the virtual machine cross-cluster migration provided in the embodiments of the present application, and details are not described here again. In addition, parts of the above technical solutions provided in the embodiments of the present application, which are consistent with the implementation principles of corresponding technical solutions in the prior art, are not described in detail so as to avoid redundant description.
It is further noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method for migrating virtual machines across clusters is characterized by being applied to a source cluster of an OpenStack cloud platform and comprising the following steps:
determining a target cluster and a target virtual machine to be migrated in the source cluster;
configuring the storage back end of the target cluster as the storage back end of the source cluster, and migrating the storage information of the target virtual machine to the storage back end of the target cluster;
determining a target physical host in the target cluster;
determining a hot migration mode of the running information of the target virtual machine;
and migrating the running information to the target physical host according to the hot migration mode.
2. The method of claim 1, wherein the determining the target physical host in the target cluster comprises:
sending the virtual machine information of the target virtual machine to the target cluster so that the target cluster determines the physical host information of the target physical host based on the virtual machine information and NUMA perception;
receiving the physical host information returned by the target cluster;
determining the target physical host based on the physical host information.
3. The method of claim 1, wherein the determining the target physical host in the target cluster comprises:
and determining the target physical host through a genetic algorithm based on the performance information of the physical hosts in the target cluster.
4. The method of claim 1, wherein the determining the hot migration mode of the running information of the target virtual machine comprises:
acquiring the running information of the target virtual machine;
determining the heat transfer mode of the operation information based on an intelligent decision method;
the running information comprises CPU utilization rate, memory utilization rate, network bandwidth resources and dirty page rate; the hot migration mode comprises a migration acceleration method and/or a compression algorithm; the migration acceleration method comprises a multithreading compression method, an automatic convergence method and a post-copy method; the compression algorithm comprises a zstd algorithm, a zlib algorithm and an lz4 algorithm.
5. The method according to any one of claims 1 to 4, wherein the migrating the operation information to the target physical host according to the live migration mode includes:
determining dirty page updating frequency of a page in the target virtual machine;
determining the page with the dirty page updating frequency larger than a preset value as a target page;
and in the shutdown stage of the target virtual machine, migrating the target page to the target physical host.
6. The method of claim 5, wherein the configuring the storage backend of the target cluster as the storage backend of the source cluster comprises:
judging whether the target cluster and the source cluster are logged in a secret-free manner or not;
if the target cluster and the source cluster are logged in a secret-free mode, judging whether the target virtual machine is in an operating state or not;
and if the target virtual machine is in a running state, executing the step of configuring the storage back end of the target cluster as the storage back end of the source cluster.
7. The method of claim 5, wherein after migrating the operation information to the target physical host according to the live migration manner, further comprising:
judging whether the target virtual machine is migrated successfully or not;
if the migration is successful, deleting the virtual machine information of the target virtual machine in the source cluster;
and if the migration fails, rolling back the target virtual machine, and deleting the virtual machine information of the target virtual machine on the target physical host.
8. A virtual machine cross-cluster migration system is applied to a source cluster of an OpenStack cloud platform and comprises the following steps:
the first determining module is used for determining a target cluster and a target virtual machine to be migrated in the source cluster;
a first migration module, configured to configure a storage back end of the target cluster as a storage back end of the source cluster, and migrate storage information of the target virtual machine to the storage back end of the target cluster;
a second determining module, configured to determine a target physical host in the target cluster;
the third determining module is used for determining a live migration mode of the running information of the target virtual machine;
and the second migration module is used for migrating the running information to the target physical host according to the hot migration mode.
9. A virtual machine cross-cluster migration apparatus, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the virtual machine cross cluster migration method of any one of claims 1 to 7 when executing said computer program.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method for migrating a virtual machine across clusters according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011306098.5A CN112433812A (en) | 2020-11-19 | 2020-11-19 | Method, system, equipment and computer medium for virtual machine cross-cluster migration |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011306098.5A CN112433812A (en) | 2020-11-19 | 2020-11-19 | Method, system, equipment and computer medium for virtual machine cross-cluster migration |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112433812A true CN112433812A (en) | 2021-03-02 |
Family
ID=74692756
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011306098.5A Pending CN112433812A (en) | 2020-11-19 | 2020-11-19 | Method, system, equipment and computer medium for virtual machine cross-cluster migration |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112433812A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113672354A (en) * | 2021-08-25 | 2021-11-19 | 广东浪潮智慧计算技术有限公司 | Virtual machine migration method and related device |
| CN114675938A (en) * | 2022-04-21 | 2022-06-28 | 江苏安超云软件有限公司 | Heterogeneous cluster virtual machine migration method and system and cloud platform |
-
2020
- 2020-11-19 CN CN202011306098.5A patent/CN112433812A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113672354A (en) * | 2021-08-25 | 2021-11-19 | 广东浪潮智慧计算技术有限公司 | Virtual machine migration method and related device |
| CN113672354B (en) * | 2021-08-25 | 2024-01-23 | 广东浪潮智慧计算技术有限公司 | Virtual machine migration method and related device |
| CN114675938A (en) * | 2022-04-21 | 2022-06-28 | 江苏安超云软件有限公司 | Heterogeneous cluster virtual machine migration method and system and cloud platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109582433B (en) | Resource scheduling method and device, cloud computing system and storage medium | |
| US9432484B1 (en) | CIM-based data storage management system having a restful front-end | |
| CN110247984B (en) | Service processing method, device and storage medium | |
| CN111813713B (en) | Data acceleration operation processing method and device and computer readable storage medium | |
| CN107666493B (en) | Database configuration method and equipment thereof | |
| CN110635944A (en) | Cluster network configuration method and device, electronic equipment and storage medium | |
| CN107818104B (en) | Database deployment method, database deployment device, control equipment and system | |
| CN112433812A (en) | Method, system, equipment and computer medium for virtual machine cross-cluster migration | |
| CN105095103A (en) | Storage device management method and device used for cloud environment | |
| US20210158131A1 (en) | Hierarchical partitioning of operators | |
| US11706289B1 (en) | System and method for distributed management of hardware using intermediate representations of systems to satisfy user intent | |
| CN113051102B (en) | File backup method, device, system, storage medium and computer equipment | |
| CN112328365A (en) | Virtual machine migration method, device, equipment and storage medium | |
| CN107329802B (en) | Virtual machine creating method and electronic equipment | |
| CN112905596B (en) | Data processing method, device, computer equipment and storage medium | |
| CN112463296B (en) | Method and device for creating virtual machine | |
| EP4012573A1 (en) | Graph reconstruction method and apparatus | |
| CN116560803B (en) | Resource management method and related device based on SR-IOV | |
| WO2012103768A1 (en) | Method and apparatus for data processing, pci-e bus system and server | |
| US20220413995A1 (en) | Automated mocking of computer system deployments | |
| EP3264254B1 (en) | System and method for a simulation of a block storage system on an object storage system | |
| CN115150268A (en) | Network configuration method and device of Kubernetes cluster and electronic equipment | |
| CN113296876B (en) | Equipment direct connection method, equipment and storage medium of virtual machine | |
| CN114116655A (en) | Parallel file storage method, device, equipment and storage medium based on virtual machine | |
| US11531578B1 (en) | Profiling and debugging for remote neural network execution |
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 |