CN116719614A - Virtual machine monitor selection method, device, computer equipment and storage medium - Google Patents
Virtual machine monitor selection method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN116719614A CN116719614A CN202311008842.7A CN202311008842A CN116719614A CN 116719614 A CN116719614 A CN 116719614A CN 202311008842 A CN202311008842 A CN 202311008842A CN 116719614 A CN116719614 A CN 116719614A
- Authority
- CN
- China
- Prior art keywords
- virtual machine
- machine monitor
- computing node
- application
- deployment request
- 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
- 238000010187 selection method Methods 0.000 title claims abstract description 23
- 238000012549 training Methods 0.000 claims abstract description 64
- 238000000034 method Methods 0.000 claims abstract description 36
- 238000012545 processing Methods 0.000 claims abstract description 29
- 230000006870 function Effects 0.000 claims description 83
- 238000003066 decision tree Methods 0.000 claims description 37
- 238000004590 computer program Methods 0.000 claims description 25
- 238000012544 monitoring process Methods 0.000 claims description 23
- 238000007637 random forest analysis Methods 0.000 claims description 13
- 238000005070 sampling Methods 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 abstract description 8
- 241001026509 Kata Species 0.000 description 16
- 238000010586 diagram Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 8
- 238000004891 communication Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000000605 extraction Methods 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
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
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
- G06F11/301—Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system is a virtual computing platform, e.g. logically partitioned systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/60—Software deployment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
-
- 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
-
- 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
- G06F2009/45595—Network integration; Enabling network access in virtual machine instances
-
- 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)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Quality & Reliability (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a virtual machine monitor selection method, a device, computer equipment and a storage medium, wherein the method comprises the following steps: acquiring an application deployment request; the application deployment request carries function requirement information and computing node information of an application to be deployed; acquiring performance index data of a corresponding target computing node according to the computing node information; invoking a prediction model after training, and processing the function requirement information and the performance index data to obtain a virtual machine monitor type aiming at the application deployment request; transmitting the virtual machine monitor class to a control node in the cluster; the control node is used for deploying the virtual machine monitor corresponding to the virtual machine monitor category to the target computing node. The method can improve the selection efficiency of the category of the monitor of the virtual machine and meet the rapid construction requirement of short-period application.
Description
Technical Field
The present application relates to the field of machine learning technology, and in particular, to a virtual machine monitor selection method, apparatus, computer device, storage medium, and computer program product.
Background
With the development of container technology, in addition to the advantages of containers, the safety problem of the containers themselves has been widely paid attention, and various schemes for enhancing the safety of the containers have been developed. The Kata container scheme is based on an extensible architecture design and is a technical scheme mainly used in the current industry. In the Kata container scheme, since Kata provides a plurality of virtual machine monitors (Virtual Machine Monitor, VMM) and the performance and functions of different virtual machine monitors are different, kata users need to select a virtual machine monitor to be deployed among the plurality of virtual machine monitors.
For Kata users, when selecting various virtual machine monitors, factors to be considered are complicated, but in practice Kata is generally applied to short-period applications such as function applications in a server-less architecture (server), and the applications are more required to be quickly built, and if a manual selection mode is adopted, the quick building requirement of the short-period applications cannot be met.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a virtual machine monitor selection method, apparatus, computer device, computer readable storage medium, and computer program product that address the problem of slow build rate in the virtual machine monitor selection method described above.
In a first aspect, the present application provides a virtual machine monitor selection method. The method comprises the following steps:
acquiring an application deployment request; the application deployment request carries function requirement information and computing node information of an application to be deployed, and the computing node information is used for positioning a target computing node for deploying the application in a cluster;
acquiring performance index data of a corresponding target computing node according to the computing node information;
invoking a prediction model after training, and processing the function requirement information and the performance index data to obtain a virtual machine monitor type aiming at the application deployment request;
transmitting the virtual machine monitor class to a control node in the cluster; the control node is used for deploying the virtual machine monitor corresponding to the virtual machine monitor category to the target computing node.
In one embodiment, the acquiring the application deployment request includes:
acquiring the application deployment request from a preset queue to be deployed;
the application deployment request in the queue to be deployed is obtained by intercepting the application deployment request under the condition that the application deployment request sent by the user side is monitored.
In one embodiment, the obtaining performance index data of the corresponding target computing node according to the computing node information includes:
acquiring performance index data of a corresponding target computing node from a monitoring system according to the computing node information;
the performance index data in the monitoring system are reported by the control nodes and each computing node in the cluster.
In one embodiment, the predictive model is trained by:
acquiring a historical dataset; the historical data set comprises a plurality of pieces of historical data, wherein each piece of historical data comprises performance index data of a historical computing node, functional requirement information of an application deployed on the historical computing node and a virtual machine monitor category deployed on the historical computing node;
sampling the historical data set for multiple times to obtain a plurality of training sample sets;
respectively training a decision tree model through each training sample set to obtain a plurality of trained decision tree models;
and forming the plurality of trained decision tree models into a random forest model serving as the prediction model.
In one embodiment, the performance index data includes data corresponding to a plurality of performance indexes, and the function requirement information includes data corresponding to a plurality of function indexes;
Training a decision tree model through each training sample set to obtain a plurality of trained decision tree models, wherein the training sample sets comprise:
in each training sample set, taking the plurality of performance indexes and the plurality of function indexes as candidate characteristics of nodes;
and selecting one target feature at a time as a node feature to split through the information gain ratio of each candidate feature until reaching an ending condition, so as to obtain the plurality of trained decision tree models.
In one embodiment, before the step of calling the trained prediction model to process the functional requirement information and the performance index data to obtain the virtual machine monitor class for the application deployment request, the method further includes:
preprocessing the functional requirement information to obtain processed functional requirement information meeting the requirements of the prediction model;
the step of calling a prediction model which is completed by training, and processing the function requirement information and the performance index data to obtain a virtual machine monitor class aiming at the application deployment request, wherein the step of calling the prediction model comprises the following steps:
and calling a prediction model after training, and processing the processed function demand information and the performance index data to obtain the category of the virtual machine monitor aiming at the application deployment request.
In a second aspect, the application further provides a virtual machine monitor selection device. The device comprises:
the request acquisition module is used for acquiring an application deployment request; the application deployment request carries function requirement information and computing node information of an application to be deployed, and the computing node information is used for positioning a target computing node for deploying the application in a cluster;
the data acquisition module is used for acquiring performance index data of the corresponding target computing node according to the computing node information;
the category prediction module is used for calling a prediction model after training is completed, and processing the function requirement information and the performance index data to obtain a virtual machine monitor category aiming at the application deployment request;
the category sending module is used for sending the category of the virtual machine monitor to the control nodes in the cluster; the control node is used for deploying the virtual machine monitor corresponding to the virtual machine monitor category to the target computing node.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor which when executing the computer program performs the steps of:
Acquiring an application deployment request; the application deployment request carries function requirement information and computing node information of an application to be deployed, and the computing node information is used for positioning a target computing node for deploying the application in a cluster;
acquiring performance index data of a corresponding target computing node according to the computing node information;
invoking a prediction model after training, and processing the function requirement information and the performance index data to obtain a virtual machine monitor type aiming at the application deployment request;
transmitting the virtual machine monitor class to a control node in the cluster; the control node is used for deploying the virtual machine monitor corresponding to the virtual machine monitor category to the target computing node.
In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
acquiring an application deployment request; the application deployment request carries function requirement information and computing node information of an application to be deployed, and the computing node information is used for positioning a target computing node for deploying the application in a cluster;
Acquiring performance index data of a corresponding target computing node according to the computing node information;
invoking a prediction model after training, and processing the function requirement information and the performance index data to obtain a virtual machine monitor type aiming at the application deployment request;
transmitting the virtual machine monitor class to a control node in the cluster; the control node is used for deploying the virtual machine monitor corresponding to the virtual machine monitor category to the target computing node.
In a fifth aspect, the present application also provides a computer program product. The computer program product comprises a computer program which, when executed by a processor, implements the steps of:
acquiring an application deployment request; the application deployment request carries function requirement information and computing node information of an application to be deployed, and the computing node information is used for positioning a target computing node for deploying the application in a cluster;
acquiring performance index data of a corresponding target computing node according to the computing node information;
invoking a prediction model after training, and processing the function requirement information and the performance index data to obtain a virtual machine monitor type aiming at the application deployment request;
Transmitting the virtual machine monitor class to a control node in the cluster; the control node is used for deploying the virtual machine monitor corresponding to the virtual machine monitor category to the target computing node.
The virtual machine monitor selection method, the device, the computer equipment, the storage medium and the computer program product, after the application deployment request is acquired, the function requirement information of the application to be deployed carried by the application deployment request is determined, and the performance index data of the corresponding target computing node is acquired according to the computing node information carried by the application deployment request; then, calling a prediction model after training is completed, and processing the function requirement information and the performance index data to obtain a virtual machine monitor class aiming at the application deployment request; and sending the virtual machine monitor categories to control nodes in the cluster, and deploying the virtual machine monitors corresponding to the virtual machine monitor categories to target computing nodes by the control nodes. According to the method, the applied function demand information and the performance index data of the computing nodes are used as influence factors, the two influence factors are analyzed through the prediction model, and the category of the virtual machine monitor is determined, so that automatic and accurate selection of the category of the virtual machine monitor is realized, manual assignment and configuration are not needed by a user, the selection efficiency of the category of the virtual machine monitor can be improved, and the rapid construction requirement of short-period application can be further met.
Drawings
FIG. 1 is an application environment diagram of a virtual machine monitor selection method in one embodiment;
FIG. 2 is a flow diagram of a virtual machine monitor selection method in one embodiment;
FIG. 3 is a flow diagram of a predictive model training process in one embodiment;
FIG. 4 is a schematic diagram of an architecture of a virtual machine monitor selection system in one embodiment;
FIG. 5 is a flow chart of a method for selecting a monitor of a virtual machine according to another embodiment;
FIG. 6 is a block diagram of a virtual machine monitor selection device in one embodiment;
fig. 7 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
It will be appreciated that with respect to the deployment of a containerized application, a Kata runtime is first deployed in a computing node of a cluster, a Virtual Machine Monitor (VMM) is deployed in the Kata runtime, and the application is run through the virtual machine monitor. In the prior art, the virtual machine monitor of the Kata running time is manually specified by a user, or all the Kata running times use the same virtual machine monitor.
However, the prior art method has the following drawbacks:
(1) When the selection is performed manually, different factors among different virtual machine monitors need to be considered, and the progress of selecting the virtual machine monitors can be influenced, so that the construction rate of the application is influenced.
(2) The virtual machine monitor is manually designated and configured by a user, and an automatic selection mechanism is lacked, so that the virtual machine monitor cannot adapt to a large-scale application scene.
(3) The user-specified virtual machine monitor scheme is not necessarily suitable for all applications in the cluster, and requires readjustment of the network scheme, but lacks an automatic selection and replacement mechanism.
(4) If a virtual machine monitor scheme is fixed, the function and performance requirements of various applications can not be met easily.
Therefore, in view of the above problems, the present application proposes a virtual machine monitor scheme selection method in Kata, which is used to analyze and learn the monitoring data of the cluster application in combination with a machine learning method, and automatically select the virtual machine monitor scheme in Kata when a new application is deployed.
The virtual machine monitor selection method provided by the embodiment of the application can be applied to a terminal or a server, and the embodiment takes the application of the method to the terminal as an example, and the corresponding application scene diagram is shown in fig. 1 and comprises a terminal 102 and a cluster 104. Wherein the terminals 102 communicate with the clusters 104 via a network. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things devices, and portable wearable devices, where the internet of things devices may be smart speakers, smart televisions, smart air conditioners, smart vehicle devices, and the like. The portable wearable device may be a smart watch, smart bracelet, headset, or the like. The cluster 104 includes a plurality of computing nodes and a control node, where the computing nodes may be computers such as servers, workstations, desktops, etc., and each computing node is connected to the cluster through a network, and the control node is used to communicate with the terminal 102, so as to implement deployment of a virtual machine monitor.
In the application scenario of the present application, after acquiring an application deployment request carrying function requirement information and computing node information of an application to be deployed, a terminal 102 acquires performance index data of a corresponding target computing node according to the computing node information; invoking a pre-trained prediction model, and processing the function requirement information and the performance index data to obtain a virtual machine monitor class aiming at an application deployment request; the virtual machine monitor class is sent to the control nodes in the cluster 104, so that the control nodes deploy virtual machine monitors corresponding to the virtual machine monitor class to target computing nodes in the cluster 104.
In one embodiment, as shown in fig. 2, a virtual machine monitor selection method is provided, and the method is applied to the terminal 102 in fig. 1 for illustration, and includes the following steps:
step S210, obtaining an application deployment request; the application deployment request carries function requirement information and computing node information of the application to be deployed, and the computing node information is used for positioning a target computing node of the deployed application in the cluster.
The function requirement information may be understood as a function required by an application to be deployed, for example, the function requirement information may be requirement information about CPU hot plug, memory hot plug, PCI (Peripheral Component Interconnect, peripheral component interconnect standard, an interface) device hot plug, and the like.
The computing node information may be information that characterizes the uniqueness of the computing node, such as a node identifier, a node number, and the like, so that it may be determined to which computing node the application corresponding to the application deployment request needs to be deployed through the computing node information.
The application deployment request is a request for deploying the application, which is sent by the user.
Step S220, according to the computing node information, performance index data of the corresponding target computing node is obtained.
The performance index data is data representing performance of the computing node, for example, the performance index data may be starting performance, memory occupancy rate, CPU utilization rate, and the like.
In a specific implementation, the monitoring system can collect data of each computing node in the cluster on indexes such as starting performance, memory occupancy rate, CPU (central processing unit) utilization rate and the like, and store performance index data of each computing node, and then after acquiring computing node information carried in an application deployment request, a corresponding target computing node can be determined according to the computing node information, and current performance index data of the target computing node can be acquired from the monitoring system.
It can be understood that the performance index data of each computing node in the cluster is not invariable, but dynamically changes along with deployment, unloading, use and other conditions of the application, so that the performance index data of each computing node stored in the monitoring system is also updated regularly, so as to ensure the accuracy of the category of the virtual machine monitor selected based on the performance index data.
And step S230, calling a prediction model after training, and processing the function requirement information and the performance index data to obtain the category of the virtual machine monitor aiming at the application deployment request.
The prediction model may be a random forest model, which is composed of a plurality of decision trees.
The virtual machine monitor Virtual Machine Monitor, VMM, also called virtual machine monitor, virtual machine manager, is a software, firmware, or hardware on a computer that can be used to build and execute a virtual machine.
Among other categories, the categories of virtual machine monitors may include Qemu, firecracker, stratoVirt, dragonball, as well as other categories. Wherein QEMU is a set of analog processor software that distributes source code with open source license (GNU General Public License, GPL); firecracker is a virtualization technology specifically used to create and manage multi-tenant containers and function-based services; stratvirt is an enterprise-level virtualization platform for cloud data centers in the computing industry; dragonball is a virtual machine manager designed optimally for secure container scenarios.
In a specific implementation, after function requirement information of an application to be deployed and performance index data of a target computing node to which the application is to be deployed are determined, the function requirement information and the performance index data can be input into a random forest model, and decision processing is carried out on the function requirement information and the performance index data by each decision tree in the random forest model, wherein each decision tree can obtain a decision result of a virtual machine monitor class aiming at an application deployment request, and a virtual machine monitor class corresponding to the decision result with the largest occurrence number in each decision result can be taken as a prediction result of the random forest model.
As shown in table 1 below, an example table of recommended results for making recommendations for different functional requirement information and performance index data. It will be appreciated that, among the requirements of the respective indicators of the functional requirement information and the performance indicator data, some are characteristics that must be satisfied, some are characteristics that must not be satisfied, so the recommended results may be different, for example, the first column of data in table 1 is a characteristic that must be satisfied, the second column of data is a characteristic that must not be satisfied, and the third column of data is a recommended result determined according to the required characteristic of the first column and the unnecessary characteristic of the second column, for example, as shown in the second row of data in table 1, for an application that must satisfy the memory requirement and needs to support the CPU hot plug, without having to have an application that starts up quickly and occupies little memory, the class of the virtual machine monitor that matches it is Qemu.
Table 1 virtual machine monitor deployment recommendation table
Step S240, the virtual machine monitor class is sent to the control nodes in the cluster; the control node is used for deploying the virtual machine monitor corresponding to the virtual machine monitor category to the target computing node.
In the specific implementation, after the virtual machine monitor category is determined, the virtual machine monitor category can be sent to a control node in the cluster, the control node converts the virtual machine monitor category into a deployment scheme, and according to the deployment scheme, the virtual machine monitor corresponding to the virtual machine monitor category is deployed on the target computing node.
In the virtual machine monitor selection method, after an application deployment request is acquired, determining that the application deployment request carries function requirement information of an application to be deployed, and acquiring performance index data of a corresponding target computing node according to computing node information carried by the application deployment request; then, calling a prediction model after training is completed, and processing the function requirement information and the performance index data to obtain a virtual machine monitor class aiming at the application deployment request; and sending the virtual machine monitor categories to control nodes in the cluster, and deploying the virtual machine monitors corresponding to the virtual machine monitor categories to target computing nodes by the control nodes. According to the method, the applied function demand information and the performance index data of the computing nodes are used as influence factors, the two influence factors are analyzed through the prediction model, and the category of the virtual machine monitor is determined, so that automatic and accurate selection of the category of the virtual machine monitor is realized, manual assignment and configuration are not needed by a user, the selection efficiency of the category of the virtual machine monitor can be improved, and the rapid construction requirement of short-period application can be further met.
In an exemplary embodiment, the acquiring the application deployment request sent by the terminal in step S210 includes: acquiring an application deployment request from a preset queue to be deployed; the application deployment request in the to-be-deployed queue is obtained by intercepting the application deployment request under the condition that the application deployment request sent by the user side is monitored.
The queue to be deployed may be a first-in first-out queue, that is, application deployment requests stored in the queue to be deployed first are fetched from the queue to be deployed first for processing, so as to ensure the ordering of the application deployment requests.
In a specific implementation, in order to know the receiving condition of the application deployment request in time, the application deployment request can be monitored. After the application deployment request sent by the user side is monitored, the application deployment request can be automatically intercepted, and the application deployment request is stored in a preset queue to be deployed for waiting to be processed. And then, the terminal takes out one application deployment request from the queue to be deployed for processing each time, and takes out the next application deployment request after the processing is completed, so that each application deployment request cached in the queue to be deployed is circularly processed in sequence.
In this embodiment, by automatically intercepting an application deployment request sent by a user terminal, storing the application deployment request in a queue and sequentially processing the application deployment request, the flow of the application deployment request can be controlled, and the application deployment request can be cached in a peak period, so as to avoid system breakdown caused by a large number of application deployment requests.
In an exemplary embodiment, the step S220 obtains performance index data of the corresponding target computing node according to the computing node information, including: acquiring performance index data of a corresponding target computing node from a monitoring system according to the computing node information; the performance index data in the monitoring system are reported by the control nodes and each computing node in the cluster.
In a specific implementation, the index reporting capability can be increased in advance in a control node and each computing node in the cluster, each computing node in the cluster actively reports the respective performance index data to the control node, then the control node reports the performance index data of each computing node to a monitoring system, and after the monitoring system receives the performance index data reported by the computing nodes, a mapping relation between each computing node and each respective performance index data can be established, and the performance index data of each computing node is stored according to the mapping relation.
Further, after the computing node information carried in the application deployment request is obtained, the computing node information can be sent to the monitoring system, so that the monitoring system determines the performance index data of the corresponding target computing node according to the mapping relation between the preset monitoring node and the performance index data and returns the determined performance index data, and the performance index data of the target computing node corresponding to the computing node information carried in the application deployment request is obtained.
The time when each computing node in the cluster reports the performance index data to the control node may be reporting according to a preset time interval, i.e. reporting at regular intervals, for example, every 10 minutes; the state of the application, the virtual machine monitor, the Kata runtime deployed on the computing node may also be reported when the state changes, for example, the application, the virtual machine monitor, or the Kata runtime is newly deployed, or the deployed application, the virtual machine monitor, or the Kata runtime is uninstalled or modified, etc.
In this embodiment, the control node and each computing node in the cluster report the performance index data to the monitoring system for storage, so that when the application deployment request is processed and the performance index data of the computing node needs to be obtained, the performance index data of the required computing node can be directly and rapidly obtained from the monitoring system, and the obtaining efficiency of the performance index data is improved, thereby improving the selection efficiency of the virtual machine monitor, and further meeting the rapid construction requirement of short-period application.
In an exemplary embodiment, the prediction model in the step S230 may be constructed as follows:
step S231, acquiring a historical data set; the historical data set comprises a plurality of pieces of historical data, wherein each piece of historical data comprises performance index data of a historical computing node, functional requirement information of an application deployed on the historical computing node and a virtual machine monitor category deployed on the historical computing node;
step S232, performing multiple sampling processing on the historical data set to obtain multiple training sample sets;
step S233, respectively training a decision tree model through each training sample set to obtain a plurality of trained decision tree models;
Step S234, a plurality of trained decision tree models are formed into a random forest model which is used as a prediction model.
In a specific implementation, the function requirement information of applications which are arranged on all computing nodes in the cluster in a historical manner can be obtained, performance index data of all computing nodes in the deployment process and the category of deployed virtual machine monitors can be obtained, and an initial historical data set formed by the historical data is used as a training sample. Data in several index dimensions for four alternative virtual machine monitor schemes, qemu, stratoVirt, cloud Hypervisor and Firecracker, are shown in table 2 below.
Table 2 example of historical dataset
It may be understood that the function requirement information may include data corresponding to a plurality of function indexes, and the format of the function requirement information of the application collected by the terminal may not meet the preset requirement, for example, a certain function index is not specifically represented by direct data, but is represented by data of a plurality of sub-indexes or some codes or some other forms, where the data of the function index cannot be directly used, and information extraction needs to be performed on the data of the sub-indexes corresponding to the function index, and the information extraction result is used as the data of the function index. For another example, if the data format of a certain function index is inconsistent with the preset requirement, the data format of the function index needs to be converted. In view of the above, after the initial historical data set composed of the historical data is obtained, it may be further preprocessed to obtain the historical data set.
After the historical data set is obtained, a self-service method (BootStraping algorithm) can be used for randomly sampling the historical data set with a put back mode, and n training sample sets can be generated by sampling n times. Further training a decision tree model by adopting n training sample sets respectively, thereby obtaining n decision tree models, and forming a random forest model by the n obtained decision tree models as a prediction model for predicting the category of the virtual machine monitor. The trained prediction model is saved and is called by other modules through an API (Application Programming Interface ) and the like.
Further, in an exemplary embodiment, the performance index data includes data corresponding to a plurality of performance indexes, and the function requirement information includes data corresponding to a plurality of function indexes;
step S233 trains a decision tree model through each training sample set, to obtain a plurality of trained decision tree models, including: in each training sample set, taking a plurality of performance indexes and a plurality of function indexes as candidate characteristics of the nodes; and selecting one target feature at a time as a node feature to split through the information gain ratio of each candidate feature until reaching an ending condition, so as to obtain a plurality of trained decision tree models.
In the specific implementation, for a single decision tree model, training is performed for corresponding times according to the number of features in a training sample set, and each splitting is performed by selecting the features according to the information gain ratio.
More specifically, in the construction process of each decision tree model, feature selection and splitting are sequentially performed from a root node until an end condition is reached, wherein each time a feature is selected, each performance index and each function index are taken as candidate features, the information gain ratio of each candidate feature is calculated, the optimal feature is selected from each candidate feature according to the information gain ratio and is taken as a target feature, splitting is performed, each node performs feature selection according to the method until the end condition is reached, namely, the feature is used up or all data on the node belong to the same category, and the construction of the decision tree is completed.
To facilitate a better understanding of the training method of the predictive model of the present application, fig. 3 shows a complete schematic diagram of the training process of the predictive model, comprising the steps of:
(1) And acquiring a historical data set, and preprocessing the historical data set according to model requirements.
(2) And randomly putting back samples from the training set by using a BootStraping method to take out samples, and generating n training sets by n times of sampling.
(3) And training the n training sets respectively to obtain n decision tree models.
(4) And for a single decision tree model, training for corresponding times according to the number of training sample features, and selecting features according to the information gain ratio for splitting each time.
(5) Each decision tree splits until all sample data on a node belongs to the same class.
(6) And forming the generated multiple decision trees into a random forest model, and deploying the random forest model.
According to the embodiment, the historical data set is divided into the training sample sets through multiple times of random sampling, each training sample set trains one decision tree, a random forest model formed by each trained decision tree is used as a prediction model for predicting the category of the virtual machine monitor and is deployed into the terminal, so that after an application deployment request of a user side is acquired, the prediction model can be called to determine the category of the virtual machine monitor corresponding to the application deployment request, quick selection of the virtual machine monitor is achieved, and decision efficiency is improved.
In an exemplary embodiment, before invoking the trained prediction model in step S230 to process the functional requirement information and the performance index data to obtain the virtual machine monitor class for the application deployment request, the method further includes: preprocessing the functional demand information to obtain processed functional demand information meeting the demand of the prediction model;
Correspondingly, step S230 may be adjusted to: and calling a prediction model after training, and processing the processed functional requirement information and performance index data to obtain the category of the virtual machine monitor aiming at the application deployment request.
Specifically, the function requirement information may include data corresponding to a plurality of function indexes, the data of a certain function index in the function requirement information carried by the application deployment request may be a directly collected data table, that is, the function index is not specifically and directly represented by data of a plurality of sub-indexes, in this case, the data of the function index cannot be directly used, information extraction needs to be performed on the data of the sub-index corresponding to the function index, and the information extraction result is used as the data of the function index. Or if the data format of a certain function index is inconsistent with the preset prediction model requirement, the data format of the function index needs to be converted. In view of the above, after the function requirement information carried by the application deployment request is obtained, the function requirement information can be further preprocessed to obtain the processed function requirement information. And further calling a prediction model after training, and analyzing and processing the processed functional demand information and performance index data to obtain the category of the virtual machine monitor aiming at the application deployment request.
In this embodiment, the function requirement information is preprocessed, so that the processed function requirement information is matched with the requirement of the prediction model, thereby ensuring that the prediction model can smoothly predict the function requirement information and the performance index data, and determining the category of the virtual machine monitor aiming at the application deployment request.
In one embodiment, to facilitate understanding of embodiments of the application by those skilled in the art, a specific example will be described below in conjunction with the accompanying drawings. Referring to fig. 4, a schematic system architecture for implementing a virtual machine monitor selection method according to an embodiment of the present application is shown in fig. 4, where a VMM (virtual machine monitor) selection module is added to the system for implementing automatic selection of a VMM solution in Kata with a control node, and specifically, the VMM (virtual machine monitor) selection module includes two sub-modules: a policy module and a selection module. Wherein:
and the strategy module is used for performing machine learning model training according to the applied function demand information and the performance index data of the computing node, generating an automatic VMM scheme selection model and deploying the model into the automatic selection module.
And the selection module is used for calling the VMM selection module to generate a VMM scheme recommendation when the application is to be deployed, and then automatically configuring the VMM scheme of the application deployed on the node into the most suitable VMM.
The functions added on the basis of the existing clusters in the application comprise:
1. and adding performance index data reporting capacity at the control node and the computing node, and reporting the performance index data to the monitoring system.
2. The policy module obtains performance index data of the computing node, such as starting performance, memory occupancy rate, CPU utilization rate and the like, from the monitoring system.
3. The strategy module carries out training of the prediction model through the performance index data and the application of the function demand information of the strategy module, and the trained prediction model is deployed to the selection module.
4. Intercepting an application deployment request, storing the application deployment request into a queue to be deployed, and waiting for generating a recommendation strategy.
5. Adding a deployment scheduling policy in the control node: the control node obtains the VMM scheme which is most suitable for the application and calculated by the prediction model from the selection module through the interface, converts the recommended result into a deployment scheme, and the control node completes application deployment.
Referring to fig. 5, a complete flow chart of a virtual machine monitor selection method is shown in an embodiment, which includes the following steps:
step S510, under the condition that an application deployment request sent by a user terminal is monitored, intercepting the application deployment request;
step S520, storing the intercepted application deployment request into a preset queue to be deployed;
Step S530, sequentially taking out application deployment requests from the queues to be deployed; the application deployment request carries function requirement information and computing node information of an application to be deployed, and the computing node information is used for positioning a target computing node for deploying the application in the cluster;
step S540, according to the information of the computing nodes, performance index data of the corresponding target computing nodes are obtained from the monitoring system; the performance index data in the monitoring system are reported by the control nodes and each computing node in the cluster;
step S550, preprocessing the function demand information to obtain processed function demand information meeting the demand of the prediction model;
step S560, calling a prediction model after training, and analyzing the processed function demand information and performance index data to obtain a virtual machine monitor class aiming at an application deployment request;
step S570, the virtual machine monitor class is sent to the control nodes in the cluster; the control node is used for deploying the virtual machine monitor corresponding to the virtual machine monitor category to the target computing node.
According to the virtual machine monitor selection method, the applied function requirement information and the performance index data of the computing nodes are used as influence factors, the two influence factors are analyzed through the prediction model, and the category of the virtual machine monitor is determined, so that automatic and accurate selection of the category of the virtual machine monitor is achieved, manual assignment and configuration are not needed by a user, selection efficiency of the category of the virtual machine monitor can be improved, and further the quick construction requirement of short-period application can be met.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides a virtual machine monitor selection device for realizing the virtual machine monitor selection method. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation in the embodiments of the virtual machine monitor selection device or devices provided below may be referred to the limitation of the virtual machine monitor selection method hereinabove, and will not be repeated herein.
In one embodiment, as shown in fig. 6, there is provided a virtual machine monitor selection apparatus including: a request acquisition module 610, a data acquisition module 620, a category prediction module 630, and a category transmission module 640, wherein:
a request acquisition module 610, configured to acquire an application deployment request; the application deployment request carries function requirement information and computing node information of an application to be deployed, and the computing node information is used for positioning a target computing node for deploying the application in the cluster;
the data obtaining module 620 is configured to obtain performance index data of the corresponding target computing node according to the computing node information;
the class prediction module 630 is configured to invoke a prediction model after training is completed, and process the functional requirement information and the performance index data to obtain a class of the virtual machine monitor for the application deployment request;
a class sending module 640, configured to send the virtual machine monitor class to a control node in the cluster; the control node is used for deploying the virtual machine monitor corresponding to the virtual machine monitor category to the target computing node.
In one embodiment, the request obtaining module 610 is further configured to obtain an application deployment request from a preset queue to be deployed; the application deployment request in the to-be-deployed queue is obtained by intercepting the application deployment request under the condition that the application deployment request sent by the user side is monitored.
In one embodiment, the data obtaining module 620 is further configured to obtain, from the monitoring system, performance index data of the corresponding target computing node according to the computing node information; the performance index data in the monitoring system are reported by the control nodes and each computing node in the cluster.
In one embodiment, the apparatus further includes a model training module for acquiring a historical dataset; the historical data set comprises a plurality of pieces of historical data, wherein each piece of historical data comprises performance index data of a historical computing node, functional requirement information of an application deployed on the historical computing node and a virtual machine monitor category deployed on the historical computing node; sampling the historical data set for multiple times to obtain a plurality of training sample sets; respectively training a decision tree model through each training sample set to obtain a plurality of trained decision tree models; and forming a random forest model by a plurality of trained decision tree models, and taking the random forest model as a prediction model.
In one embodiment, the performance index data includes data corresponding to a plurality of performance indexes, and the function requirement information includes data corresponding to a plurality of function indexes; the model training module is also used for taking a plurality of performance indexes and a plurality of functional indexes as candidate characteristics of the nodes in each training sample set; and selecting one target feature at a time as a node feature to split through the information gain ratio of each candidate feature until reaching an ending condition, so as to obtain a plurality of trained decision tree models.
In one embodiment, the category prediction module 630 is further configured to pre-process the functional requirement information to obtain processed functional requirement information that meets the requirement of the prediction model; and calling a prediction model after training, and analyzing the processed functional requirement information and performance index data to obtain the category of the virtual machine monitor aiming at the application deployment request.
The respective modules in the above-described virtual machine monitor selection apparatus may be implemented in whole or in part by software, hardware, and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a terminal, and the internal structure of which may be as shown in fig. 7. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program, when executed by a processor, implements a virtual machine monitor selection method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structure shown in FIG. 7 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In an embodiment, there is also provided a computer device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method embodiments described above when the computer program is executed.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, carries out the steps of the method embodiments described above.
In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the method embodiments described above.
It should be noted that, the user information (including but not limited to user equipment information, user personal information, etc.) and the data (including but not limited to data for analysis, stored data, presented data, etc.) related to the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data need to comply with the related laws and regulations and standards of the related country and region.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the embodiments provided herein may include at least one of a relational database and a non-relational database. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processor referred to in the embodiments provided in the present application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, or the like, but is not limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples illustrate only a few embodiments of the application and are described in detail herein without thereby limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.
Claims (10)
1. A method of virtual machine monitor selection, the method comprising:
acquiring an application deployment request; the application deployment request carries function requirement information and computing node information of an application to be deployed, and the computing node information is used for positioning a target computing node for deploying the application in a cluster;
acquiring performance index data of a corresponding target computing node according to the computing node information;
Invoking a prediction model after training, and processing the function requirement information and the performance index data to obtain a virtual machine monitor type aiming at the application deployment request;
transmitting the virtual machine monitor class to a control node in the cluster; the control node is used for deploying the virtual machine monitor corresponding to the virtual machine monitor category to the target computing node.
2. The method of claim 1, wherein the obtaining an application deployment request comprises:
acquiring the application deployment request from a preset queue to be deployed;
the application deployment request in the queue to be deployed is obtained by intercepting the application deployment request under the condition that the application deployment request sent by the user side is monitored.
3. The method according to claim 1, wherein the obtaining performance index data of the corresponding target computing node according to the computing node information includes:
acquiring performance index data of a corresponding target computing node from a monitoring system according to the computing node information;
The performance index data in the monitoring system are reported by the control nodes and each computing node in the cluster.
4. The method according to claim 1, wherein the predictive model is trained by:
acquiring a historical dataset; the historical data set comprises a plurality of pieces of historical data, wherein each piece of historical data comprises performance index data of a historical computing node, functional requirement information of an application deployed on the historical computing node and a virtual machine monitor category deployed on the historical computing node;
sampling the historical data set for multiple times to obtain a plurality of training sample sets;
respectively training a decision tree model through each training sample set to obtain a plurality of trained decision tree models;
and forming the plurality of trained decision tree models into a random forest model serving as the prediction model.
5. The method of claim 4, wherein the performance index data comprises data corresponding to a plurality of performance indexes, and the functional requirement information comprises data corresponding to a plurality of functional indexes;
training a decision tree model through each training sample set to obtain a plurality of trained decision tree models, wherein the training sample sets comprise:
In each training sample set, taking the plurality of performance indexes and the plurality of function indexes as candidate characteristics of nodes;
and selecting one target feature at a time as a node feature to split through the information gain ratio of each candidate feature until reaching an ending condition, so as to obtain the plurality of trained decision tree models.
6. The method of claim 1, wherein the invoking the trained predictive model, before processing the functional requirement information and the performance metric data to obtain a virtual machine monitor class for the application deployment request, further comprises:
preprocessing the functional requirement information to obtain processed functional requirement information meeting the requirements of the prediction model;
the step of calling a prediction model which is completed by training, and processing the function requirement information and the performance index data to obtain a virtual machine monitor class aiming at the application deployment request, wherein the step of calling the prediction model comprises the following steps:
and calling a prediction model after training, and processing the processed function demand information and the performance index data to obtain the category of the virtual machine monitor aiming at the application deployment request.
7. A virtual machine monitor selection apparatus, the apparatus comprising:
the request acquisition module is used for acquiring an application deployment request; the application deployment request carries function requirement information and computing node information of an application to be deployed, and the computing node information is used for positioning a target computing node for deploying the application in a cluster;
the data acquisition module is used for acquiring performance index data of the corresponding target computing node according to the computing node information;
the category prediction module is used for calling a prediction model after training is completed, and processing the function requirement information and the performance index data to obtain a virtual machine monitor category aiming at the application deployment request;
the category sending module is used for sending the category of the virtual machine monitor to the control nodes in the cluster; the control node is used for deploying the virtual machine monitor corresponding to the virtual machine monitor category to the target computing node.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the virtual machine monitor selection method of any of claims 1 to 6 when the computer program is executed.
9. A computer readable storage medium having stored thereon a computer program, characterized in that the computer program when executed by a processor implements the steps of the virtual machine monitor selection method of any of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program when executed by a processor implements the steps of the virtual machine monitor selection method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311008842.7A CN116719614A (en) | 2023-08-11 | 2023-08-11 | Virtual machine monitor selection method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311008842.7A CN116719614A (en) | 2023-08-11 | 2023-08-11 | Virtual machine monitor selection method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116719614A true CN116719614A (en) | 2023-09-08 |
Family
ID=87875647
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311008842.7A Pending CN116719614A (en) | 2023-08-11 | 2023-08-11 | Virtual machine monitor selection method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116719614A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102521014A (en) * | 2011-12-06 | 2012-06-27 | 北京航空航天大学 | Deploying method and deploying device for virtual machine |
| CN106020934A (en) * | 2016-05-24 | 2016-10-12 | 浪潮电子信息产业股份有限公司 | Optimized deployment method based on virtual cluster online migration |
| CN106897109A (en) * | 2017-02-13 | 2017-06-27 | 云南大学 | Based on the virtual machine performance Forecasting Methodology that random forest is returned |
| CN112052072A (en) * | 2020-09-10 | 2020-12-08 | 华云数据控股集团有限公司 | Scheduling strategy and super-fusion system of virtual machine |
| CN112835684A (en) * | 2021-03-02 | 2021-05-25 | 浙江工业大学 | Virtual machine deployment method facing mobile edge calculation |
| CN114327739A (en) * | 2020-09-27 | 2022-04-12 | 华为云计算技术有限公司 | Method and device for deploying computing instance |
| WO2022105589A1 (en) * | 2020-11-20 | 2022-05-27 | 上海连尚网络科技有限公司 | Resource scheduling method and apparatus, electronic device and computer readable medium |
| CN114995957A (en) * | 2022-06-24 | 2022-09-02 | 中国电信股份有限公司 | Container group deployment method, device, electronic equipment and computer-readable storage medium |
| CN116366453A (en) * | 2023-04-18 | 2023-06-30 | 中国电子科技集团公司第三十八研究所 | Self-adaptive dynamic deployment method for heterogeneous network element service demand characterization and virtual network element |
-
2023
- 2023-08-11 CN CN202311008842.7A patent/CN116719614A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102521014A (en) * | 2011-12-06 | 2012-06-27 | 北京航空航天大学 | Deploying method and deploying device for virtual machine |
| CN106020934A (en) * | 2016-05-24 | 2016-10-12 | 浪潮电子信息产业股份有限公司 | Optimized deployment method based on virtual cluster online migration |
| CN106897109A (en) * | 2017-02-13 | 2017-06-27 | 云南大学 | Based on the virtual machine performance Forecasting Methodology that random forest is returned |
| CN112052072A (en) * | 2020-09-10 | 2020-12-08 | 华云数据控股集团有限公司 | Scheduling strategy and super-fusion system of virtual machine |
| CN114327739A (en) * | 2020-09-27 | 2022-04-12 | 华为云计算技术有限公司 | Method and device for deploying computing instance |
| WO2022105589A1 (en) * | 2020-11-20 | 2022-05-27 | 上海连尚网络科技有限公司 | Resource scheduling method and apparatus, electronic device and computer readable medium |
| CN112835684A (en) * | 2021-03-02 | 2021-05-25 | 浙江工业大学 | Virtual machine deployment method facing mobile edge calculation |
| CN114995957A (en) * | 2022-06-24 | 2022-09-02 | 中国电信股份有限公司 | Container group deployment method, device, electronic equipment and computer-readable storage medium |
| CN116366453A (en) * | 2023-04-18 | 2023-06-30 | 中国电子科技集团公司第三十八研究所 | Self-adaptive dynamic deployment method for heterogeneous network element service demand characterization and virtual network element |
Non-Patent Citations (1)
| Title |
|---|
| 刘杨;肖侬;沈立;: "Xen虚拟集群监控器的设计与实现", 武汉理工大学学报, no. 20, pages 184 - 188 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10922206B2 (en) | Systems and methods for determining performance metrics of remote relational databases | |
| US10534753B2 (en) | Caseless file lookup in a distributed file system | |
| GB2583718A (en) | Method, apparatus and computer program for updating a cluster probability model | |
| CN111858617A (en) | User searching method and device, computer readable storage medium and electronic equipment | |
| CN114089921A (en) | Power system data storage method and device, computer equipment and storage medium | |
| WO2021236423A1 (en) | Identifying claim complexity by integrating supervised and unsupervised learning | |
| WO2024112411A1 (en) | Learned workload synthesis | |
| CN116991800A (en) | File acquisition system, method, device, computer equipment and storage medium | |
| CN117112096A (en) | Page display method and device and computer equipment | |
| CN117033766A (en) | Service processing behavior prediction method, device, computer equipment and storage medium | |
| CN111553749A (en) | Activity push strategy configuration method and device | |
| CN116719614A (en) | Virtual machine monitor selection method, device, computer equipment and storage medium | |
| CN115130002A (en) | Recommendation request processing method and device, computer equipment and storage medium | |
| CN117453759B (en) | Service data processing method, device, computer equipment and storage medium | |
| CN106528577B (en) | Method and device for setting file to be cleaned | |
| CN116450808B (en) | Data processing method and device and storage medium | |
| CN112765479B (en) | Information recommendation method and device, electronic equipment and readable storage medium | |
| CN117314036A (en) | Work order distribution method, apparatus, device, storage medium and program product | |
| CN116738000A (en) | Data storage relationship processing method and device, electronic equipment and storage medium | |
| CN116932891A (en) | Resource object display method, device, equipment, storage medium and product | |
| CN116909684A (en) | Deployment method and device of low-code application, computer equipment and storage medium | |
| CN116523308A (en) | Training method and device of risk prediction model and user behavior risk prediction method | |
| CN116882648A (en) | Account resource allocation method, device, computer equipment and storage medium | |
| CN118586499A (en) | Artificial intelligence model operation method and computer equipment | |
| WO2024196614A1 (en) | Recommendation system with time series data generated implicit ratings |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230908 |
|
| RJ01 | Rejection of invention patent application after publication |