CN117331690A - Method for efficiently utilizing computing resources based on cloud computing - Google Patents

Method for efficiently utilizing computing resources based on cloud computing Download PDF

Info

Publication number
CN117331690A
CN117331690A CN202311269346.7A CN202311269346A CN117331690A CN 117331690 A CN117331690 A CN 117331690A CN 202311269346 A CN202311269346 A CN 202311269346A CN 117331690 A CN117331690 A CN 117331690A
Authority
CN
China
Prior art keywords
instance
computing resources
server
super
computing
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
Application number
CN202311269346.7A
Other languages
Chinese (zh)
Inventor
王春苏
庞景秋
齐井春
李绍俊
李波
刘海涛
池海洲
张继伟
于亮
陈钰明
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Changchun Jiacheng Information Technology Co ltd
Original Assignee
Changchun Jiacheng Information Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Changchun Jiacheng Information Technology Co ltd filed Critical Changchun Jiacheng Information Technology Co ltd
Priority to CN202311269346.7A priority Critical patent/CN117331690A/en
Publication of CN117331690A publication Critical patent/CN117331690A/en
Pending legal-status Critical Current

Links

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
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5061—Partitioning or combining of resources
    • G06F9/5072—Grid computing
    • 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
    • H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
    • H04L67/1004—Server selection for load balancing

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention discloses a method for efficiently utilizing computing resources based on cloud computing, which comprises the steps of super distributing computing resources of a physical server to a plurality of virtual machines for use according to a certain super-distribution proportion before using the physical server, so as to realize super-distribution of the physical server; simultaneously, parameters of related examples which can be operated after the physical servers are over-configured are planned; before creating an instance, finding an optimal physical server based on an algorithm to deploy and run the instance; and finally, destroying the idle examples through a visual interface and automatically releasing occupied computing resources. According to the method and the system, the computing resources are subjected to visual planning, the instance is automatically selected to create the optimal server based on the planning and the use data of the computing resources, and a user can not only adjust the configuration of the computing resources after the server is super-matched according to own requirements, but also manage and utilize the resources more conveniently and rapidly, so that the method and the system have extremely high extensibility and customizable performance.

Description

Method for efficiently utilizing computing resources based on cloud computing
Technical Field
The present invention relates to a method for utilizing computing resources, and in particular, to a method for efficiently utilizing computing resources based on cloud computing.
Background
Cloud computing is an internet-based computing manner by which software and hardware resources are shared. The method is a product of the development fusion of traditional computer technologies and network technologies such as distributed computing, parallel computing, network computing, utility computing, network storage, virtualization and load balancing. The users uniformly manage and schedule a large amount of computing resources and application programs connected by using the network, and a computing resource pool is formed to provide the users with on-demand services. With the continuous popularization and use of cloud computing services, many problems, such as exceeding the application requirement configuration example, no-longer-used resources not being released in time, etc., are also caused, so that the problems of computing resource waste and fragmentation are gradually highlighted, and idle or overload of computing resources of a physical server is easy to occur.
Disclosure of Invention
In order to solve the defects of the technology, the invention provides a method for efficiently utilizing computing resources based on cloud computing.
In order to solve the technical problems, the invention adopts the following technical scheme: a method for efficiently utilizing computing resources based on cloud computing, comprising:
designing a visual interface by utilizing Vue, and super-distributing computing resources of a physical server to a plurality of virtual machines according to a certain super-distribution proportion before using the physical server so as to realize super-distribution of the physical server; simultaneously, parameters of the running examples of the super-configured physical servers are planned, and calculation resources of the super-configured physical servers are checked and adjusted on a visual interface; before creating an instance, automatically selecting an optimal server algorithm based on the instance creation, and finding an optimal physical server to deploy and run the instance; and finally, manually destroying the idle examples through a visual interface, and automatically releasing occupied computing resources.
Further, the method for efficiently utilizing computing resources based on cloud computing of the invention comprises the following steps: setting and changing the super-allocation proportion in the visual interface before the computing resource is super-divided according to a certain super-allocation proportion;
after the computing resources are superdivided according to a certain superdistribution proportion, based on the interaction function of the front end and the back end of the visual interface, the front end submits the proportion data to the back end, and the back end stores the proportion data in the database.
After the computing resource is superdivided according to a certain superdistribution proportion, the superdistributed CPU core number is obtained, and the method for computing the total CPU core number after superdistribution of each physical server comprises the following steps:
wherein, C is the number of CPU cores used in the example specification, and is the unit vCPUs; n is the number of example specification seeds, and the unit seeds; s is an example specification; x is the number of the example specifications; i is a certain example specification; j is the server number;
after the computing resources are superdivided according to a certain superdistribution proportion, the total memory after superdistribution is obtained, and the method for computing the total memory after superdistribution of each physical server comprises the following steps:
wherein M is the memory space used by the example specification, and the unit is GB; n is the number of example specification seeds, and the unit seeds; s is an example specification; x is the number of the example specifications; i is a certain example specification; j is the server number.
Further, the method for efficiently utilizing computing resources based on cloud computing of the invention comprises the following steps: after the physical servers are used and planned, the planned instance specification and quantity information in each server is submitted to the back end in a structured mode and then stored in a database.
Further, the method for efficiently utilizing computing resources based on cloud computing of the invention comprises the following steps: the instance creation automatically selects the optimal server algorithm as:
I；＝nmaXx((X)
wherein I is an example; x is the number of the example specifications; i is a certain example specification; j is the server number.
Further, the method for efficiently utilizing computing resources based on cloud computing of the invention comprises the following steps: after the optimal physical server is found and an instance is created, subtracting one operation from corresponding instance specification data in the physical server computing resource planning data, and then deploying and operating the instance;
the subtracting operation is to find all nodes with the instance specification according to the instance specification corresponding to the instance to be created, judge that the number of the creatable specifications of the nodes in all the nodes is the largest, create the instance on the node, and then the number of the creatable specifications of the nodes is subjected to subtracting operation.
Further, the method for efficiently utilizing computing resources based on cloud computing comprises the following steps: the automatic release of occupied computing resources is based on interaction of the front end and the back end of the visual interface, and when the deletion of the instance under the node is monitored, the number of the creatable specifications under the node is subjected to addition operation.
The invention discloses a method for efficiently utilizing computing resources based on cloud computing, which develops key technologies of a visual computing resource supersubstance proportion setting module, a visual computing resource planning module, an instance creation automatic selection optimal server module and a computing resource release module, and performs experimental verification, and has the following beneficial effects:
1. through visual computing resource planning, a user can adjust the configuration of computing resources after the super-configuration of each server according to own requirements, so that the method has extremely high expandability and customizable degree, and personalized customization and optimization are carried out according to different application scenes;
2. the user can manage and utilize the resources more conveniently and rapidly, and automatically creates an optimal server for the user selection instance, so that better resource utilization effect and data management efficiency are realized.
Drawings
FIG. 1 is a schematic diagram of a method for efficiently utilizing computing resources according to the present invention.
FIG. 2 is a schematic diagram of an interface of a visual computing resource planning module according to the present invention.
FIG. 3 is an exemplary diagram of a workflow for automatically selecting an optimal server module for an example creation of the present invention.
Detailed Description
The invention will be described in further detail with reference to the drawings and the detailed description.
A method for efficiently utilizing computing resources based on cloud computing, comprising:
1: and (5) computing the resource super-proportion setting.
Before using the physical server and the computing resources, the user can set the overestimate proportion of the computing resources of the physical server, i.e. the computing resources of the physical server are overestimated according to a certain proportion. The super-divided computing resources can be distributed to more virtual machines for use, so that the elasticity and fault tolerance of the system are improved. The visual interface is designed by utilizing the front-end development framework of the Vue, the proportion can be set on the visual interface, proportion data is submitted to the back end through the interaction capability of the front end and the back end of the Vue, and the back end stores the data in a local database or a relational database so as to realize the visual computing resource planning use.
The relationship between the physical CPU and the virtual machine vCPU, a 2U (thickness) physical server is generally configured with 2 physical CPUs, each CPU has a plurality of cores, and after the Hyper-Threading technology is started, each core has 2 threads (threads); one vCPU corresponds to one Thread in the virtualized environment.
The physical server computing resources refer to various hardware resources owned by the physical server, and the various hardware resources together form the overall computing power of the physical server, including:
processor (CPU): a core component responsible for performing computing tasks;
memory (RAM): temporary space for storing programs and data;
a storage device: the system comprises a hard disk, a solid state disk and the like, and is used for permanently storing data;
network interface: connected to other devices and services through a network;
display card (GPU): can be used for high-performance computing, machine learning and other tasks.
The physical server superdivision is realized on the basis of KVM (virtual machine), each VM is a QEMU process of a user space in the open source virtualization KVM, the vCPU allocated to the virtual machine is a Thread derived from the QEMU process, the virtual machine is dynamically scheduled to the physical CPU based on time division multiplexing by the Linux kernel to run, and the KVM can support vCPU superdivision (over-limit) per se, so that the number of vCPUs allocated to the virtual machine can exceed the total number of physical CPU threads. Therefore, in cloud computing, a user can superdivide a CPU according to different superproportions of 1:1, 1:2, 1:4 and the like according to the load of a service, for example, a previous physical CPU core is 20 cores, and a hyper-thread is started to be 40 cores; if the super division is performed according to the ratio of 1:2, the allocatable resource becomes 80 cores, so that more virtual machine resources can be created.
Memory superdivision, in open source virtualized KVM, memory is also an over-use (over-commit) allowed, and KVM enables the total amount of memory allocated to a virtual machine to be greater than the total amount of physical memory actually available. Because the operating system of the virtual machine and the application programs running by the operating system of the virtual machine do not always use 100% of the memory allocated by the operating system of the virtual machine, and the utilization rate of the memory of a plurality of virtual machines on a host machine generally cannot reach 100% at the same time, the memory can be oversubscribed. The super allocation ratio of the memory is similar to that of the CPU, and the super allocation ratio can be different according to different proportions of 1:1, 1:2 and the like, for example, the physical memory is 8G, and the super allocation ratio of 1:2 can allocate 16G to the virtual machine. In practical application, in order to ensure service performance, the memory super-proportion is lower.
The computing resources after the physical server is super-configured comprise a CPU, a memory and the like.
The present embodiment follows the following formula:
11: the calculation formula of the total CPU core number after each physical server is super-configured,
wherein, C is the number of CPU cores used in the example specification, and the unit is VCPUs; n is the number of example specification seeds, and the unit is the seeds; s is an example specification; x is the number of the example specifications; i is a certain example specification; j is the server number.
12: the total memory calculation formula after each physical server is overduned,
wherein M is the memory space used by the example specification, and the unit is GB; n is the number of example specification seeds, and the unit seeds; s is an example specification; x is the number of the example specifications; i is a certain example specification; j is the server number.
2: the computing resource plan is visualized.
Before using the physical servers and the computing resources, the user needs to perform a usage plan of the computing resources, i.e. plan out the specification of the running examples and the number of the running examples after the servers are over-matched. Through a visual interface, a user can check and adjust the configuration and allocation conditions of the computing resources after the server is over-allocated, so that the computing resources after the server is over-allocated are abstracted into grids on the interface for facilitating the user resource planning, and the user can fill up the small grids representing the computing resources after the server is over-allocated by using the instance specification, thereby indicating that the computing resources after the server is over-allocated by the server are planned. The planning data stores the specification and quantity information of each server executable instance in a structured form into a database for subsequent management and instance creation for use by the optimal selection server algorithm.
3: instance creation automatically selects the optimal server algorithm.
When the computing resource is used for instance creation, the server with the largest data volume for creating the specification instance is found from the computing resource planning data, namely the optimal server is used for deploying and operating the instance, and meanwhile, the corresponding instance specification data in the computing resource planning data of the instance deployment server is automatically subtracted by one. For example, there are 3 nodes in the current cluster, the specification of the c4m8 instance in each Node is shown in the following table, if an instance of c4m8 is to be created, it is determined that the number of the allowable creation specifications of the c4m8 instance in the Node1 is the largest, so the algorithm will create the instance on the Node 1; after being distributed to the Node1, the Node can create a specification number of which is obtained by subtracting 1 from 8 and then obtaining 7.
An example is a basic computing resource unit in cloud computing, which generally refers to an independent computing unit where virtual machines run on a cloud computing platform. Each instance has its own independent operating system, computing resources, network configuration, etc., and can perform operations such as creation, start, stop, release, etc. according to the needs of the user.
An instance specification is a parameter used in cloud computing services to describe the configuration of virtual machine resources, and generally includes vCPU core number, memory size, and network performance. Different cloud computing providers may provide a variety of different instance specifications to meet different business needs and budget constraints for users.
The present embodiment follows the following formula:
31: the optimal server algorithm formula is automatically preferred,
I i ＝max(X ij )；
wherein I is an example; x is the number of the example specifications; i is a certain example specification; j is the server number.
4: and (3) releasing the computing resources.
After the computing resources are used, when a user does not need some examples, the computing resources can be destroyed through a visual interface, and occupied computing resources can be automatically released when the computing resources are destroyed. The method comprises the steps of deleting the instance on the node where the idle instance is located, and adding the number of the created specifications by the node. This reduces unnecessary waste of resources and fragmentation while enabling the computing resources to be reused.
Fig. 1 is a schematic diagram of a method for efficiently utilizing computing resources based on cloud computing according to a first embodiment of the present invention, and as shown in fig. 1, a visual computing resource planning form of the present invention includes:
examples specification list includes c1m1, c1m2, c2m2, c2m4, c2m8, c4m4, c4m8, c4m16, c8m8, c8m16, and c16m32; the example specifications listed in the list may be used, and the example specifications are interpreted as configurations of the CPU and the memory, for example, c2m4 corresponds to a 2-core CPU and a 4G memory. Each instance specification in the list can be added to the right CPU-available resources, the memory-available resources and the node resource allocation list by a double-click or drag operation, for example, the c4m4 specification in the double-click or drag list is to the right, 4 squares in the CPU-available resources are occupied (light gray is changed to dark gray), and 4 squares in the memory-available resources are occupied (light gray is changed to dark gray).
Each grid in the legend of the CPU available resource framework represents CPU resources for 1 core:
the grey grid with triangles represents server computing resources that have been used, here CPU resources that have been used, cannot be used by other instances;
the light grey grid represents the CPU resources of the server to be allocated, i.e. the CPU resources which can be used;
the dark grey grid represents the allocated server CPU resources, i.e. the CPU resources that have been occupied.
Each cell in the legend of the memory-available resource framework represents 1GB of memory resources:
the grey grid with triangles represents server computing resources that have been used, here referring to memory resources that have been used, and cannot be used by other instances;
the light grey grid represents memory resources that can be used by the server memory resources to be allocated;
the dark grey grid represents allocated server memory resources, i.e. memory resources that have been occupied.
In the super-configuration framework, the super-configuration proportion of the CPU and the memory of the current server can be checked and modified; as shown in fig. 1, the physical resources available to the server are a 16-core CPU, a 16GB memory, and the number of cores of the CPU is super-configured to be 125% according to the legend, and the number of cores of the CPU after super-configuration is 20 cores (16 cores x 125% = 20 cores); the memory is over-matched by 150%, and the memory after over-matching is 20GB (16 GB. Times.150% =24 GB).
The node resource allocation resource list is displayed with specification names, CPU core number (unit is vCPU), memory (unit is GB), allocation quantity and operation; the specification name corresponds to an instance specification in the instance specification list by adjusting the specification allocation number in the allocation number column. The number increase is a grid which automatically occupies CPU and memory available resources (changing from light gray to dark gray), and the number increase is determined by a specification attribute, such as the example specification of c1m2 in the figure, which is interpreted as a grid which occupies 1 CPU available resource and a grid which occupies 2 memory available resources. The amount of reduction is to automatically release CPU memory available resource grids (from dark grey to light grey), the amount of reduction is determined by specification attributes, e.g. specification c1m2, 1 CPU available resource grid will be released, and 2 memory available resource grids will be released. The deleting operation in the operation will automatically release the CPU and the available resource grid of the memory. If the specification number of c1m2 in the deletion diagram is 4, the number of lattices of the released CPU available resources is 4 (1*4 =4), and the number of lattices of the released memory available resources is 8 (2×4=8); if the specification number of the deleted examples is c4m4 and is 1, the number of grids of the released CPU available resources is 4, and the number of grids of the released memory available resources is 4; if the specification number of the deleted instance is c1m1, the number of grids of the released CPU available resources is 2, and the number of grids of the released memory available resources is 2; if the specification number of the deleted example is c2m2, the specification number is 4, the number of lattices of the available resources of the released CPU is 8, and the number of lattices of the available resources of the released memory is 8. And submitting the specification names and the corresponding numbers in the resource allocation list to the back end during storage, and storing the specification names and the corresponding numbers in a database.
Fig. 2 is a schematic diagram of a method for efficiently utilizing computing resources based on cloud computing according to a second embodiment of the present invention, and as shown in fig. 2, a workflow diagram for automatically selecting an optimal server module is created according to an embodiment of the present invention, including the following steps:
step S1: initially, a user submits a request for creating an instance;
step S2: the system checks indexes such as calculation resource planning data, specification service conditions and the like of all the current servers;
step S3: automatically selecting a best server algorithm to select a best server based on the instance creation; when an instance is created, a server with the largest number of the instances with the specifications can be created from the computer resource planning data, namely an optimal server is found to deploy and run the instance, and meanwhile, the operation of subtracting one from the corresponding instance specification data in the resource planning data is calculated for the instance deployment server;
step S4: the system creates and runs an instance on the selected server, ending the automatic selection.
The third embodiment of the present invention provides a method for efficiently utilizing computing resources based on cloud computing, where a cloud management platform manages using physical server computing resources using the method of the present invention, including:
1: the physical server calculates the resource superstrate setting. After the cloud management platform imports the virtualized cluster, the super-allocation proportion of the computing resources of each physical server in the cluster is set, and the logic computing resources which can be used by each physical server are determined.
2: the computing resource plan is visualized. And planning the specifications and the quantity of the operable examples for each server by using a visualized computing resource planning interface, thereby determining that each server can create different specifications of examples and quantity, fully occupying computing resources of the servers and maximizing the computing resource utilization rate of the physical servers.
3: the instance creation automatically selects the optimal server. When an instance is created, the cloud management platform automatically selects an optimal server algorithm according to the instance creation to automatically find a server which is most suitable for deploying and operating the instance, manual intervention is not needed in the whole process, and the instance is created completely according to the computing resource planning data. The waste of computing resources is reduced, and the use efficiency of the computing resources is improved.
4: and (5) releasing the computing resources. When the user does not need some examples, destroying the unnecessary examples in the server of the cloud management platform by utilizing the visual interface, and releasing the computing resources when destroying the unnecessary examples. The problem of fragmentation is reduced, and the overall efficiency of the system is improved.
The above embodiments are not intended to limit the present invention, and the present invention is not limited to the above examples, but is also intended to be limited to the following claims.

Claims (10)

1. A method for efficiently utilizing computing resources based on cloud computing is characterized by comprising the following steps:
designing a visual interface by utilizing a visual development tool, and superdividing the computing resources of a physical server into a plurality of virtual machines for use according to a certain supermatch proportion before using the physical server; simultaneously, parameters of the running examples of the super-configured physical servers are planned, and calculation resources of the super-configured physical servers are checked and adjusted on a visual interface; before creating an instance, automatically selecting an optimal server algorithm based on the instance creation, and finding an optimal physical server to deploy and run the instance; and finally, manually destroying the idle examples through a visual interface, and automatically releasing occupied computing resources.
2. The method for efficiently utilizing computing resources based on cloud computing of claim 1, wherein: and setting and changing the super-match proportion in the visual interface before the computing resource is super-divided according to a certain super-match proportion.
3. The method for efficiently utilizing computing resources based on cloud computing of claim 2, wherein: after the computing resources are super-divided according to a certain super-allocation proportion, based on the front-end and back-end interaction function of the visual development tool, the front-end submits the proportion data to the back-end, and the back-end stores the proportion data in the database.
4. The method for efficiently utilizing computing resources based on cloud computing as recited in claim 3, wherein: after the proportion data is stored in a database, the number of CPU cores after super-division is obtained, and the method for calculating the total number of CPU cores after super-allocation of each physical server comprises the following steps:
wherein, C is the number of CPU cores used in the example specification, and is the unit vCPUs; n is the number of example specification seeds, and the unit seeds; s is an example specification; x is the number of the example specifications; i is a certain example specification; j is the server number.
5. The method for efficiently utilizing computing resources based on cloud computing as recited in claim 3, wherein: after the proportion data is stored in the database, the total memory after super-division is obtained, and the total memory after super-allocation of each physical server is calculated by the following steps:
wherein M is the memory space used by the example specification, and the unit is GB; n is the number of example specification seeds, and the unit seeds; s is an example specification; x is the number of the example specifications; i is a certain example specification; j is the server number.
6. The method for efficiently utilizing computing resources based on cloud computing of claim 1, wherein: and after the physical servers are used and planned, submitting the planned instance specification and quantity information in each server to the back end in a structured form, and then storing the instance specification and quantity information in a database.
7. The method for efficiently utilizing computing resources based on cloud computing of claim 1, wherein: the physical server with the most specifications capable of creating the instance is found from planning data of the computing resource to be the optimal server, and the instance creation automatically selects the optimal server algorithm to be:
I i ＝max(X ij )；
wherein I is an example; x is the number of the example specifications; i is a certain example specification; j is the server number.
8. The method for efficiently utilizing computing resources based on cloud computing of claim 7, wherein: after the optimal physical server is found and the instance is created, subtracting one operation is carried out on the corresponding instance specification data in the physical server computing resource planning data, and then the instance is deployed and operated.
9. The cloud computing-based efficient utilization method of computing resources of claim 8, wherein: the subtracting operation is to find all nodes with the instance specification according to the instance specification corresponding to the instance to be created, judge that the number of the creatable specifications of the nodes in all the nodes is the largest, create the instance on the node, and then the number of the creatable specifications of the nodes is subjected to subtracting operation.
10. The method for efficiently utilizing computing resources based on cloud computing of claim 1, wherein: the automatic release of occupied computing resources is based on interaction of the front end and the back end of the visual interface, and when the fact that the instance under the node is deleted is monitored, the number of the creatable specifications under the node is subjected to addition operation.
CN202311269346.7A 2023-09-28 2023-09-28 Method for efficiently utilizing computing resources based on cloud computing Pending CN117331690A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311269346.7A CN117331690A (en) 2023-09-28 2023-09-28 Method for efficiently utilizing computing resources based on cloud computing

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311269346.7A CN117331690A (en) 2023-09-28 2023-09-28 Method for efficiently utilizing computing resources based on cloud computing

Publications (1)

Publication Number Publication Date
CN117331690A true CN117331690A (en) 2024-01-02

Family

ID=89294571

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311269346.7A Pending CN117331690A (en) 2023-09-28 2023-09-28 Method for efficiently utilizing computing resources based on cloud computing

Country Status (1)

Country Link
CN (1) CN117331690A (en)

Similar Documents

Publication Publication Date Title
Zhong et al. A cost-efficient container orchestration strategy in kubernetes-based cloud computing infrastructures with heterogeneous resources
US20210218796A1 (en) Efficient, automated distributed-search methods and systems
US9977689B2 (en) Dynamic scaling of management infrastructure in virtual environments
CN101290583B (en) Method and system for providing image for virtual machine
CN103620548B (en) Memory manager with enhanced application metadata
CN113342477B (en) Container group deployment method, device, equipment and storage medium
CN102981929B (en) The management method of disk mirroring and system
CN103036946B (en) A kind of method and system processing file backup task for cloud platform
DE102013205572B4 (en) USING SOFTWARE COMPONENT METADATA TO PROVIDE VIRTUAL MACHINES IN A NETWORKED DATA PROCESSING ENVIRONMENT
CN103635876B (en) Memory management model and interface for unmodified application
CN109240825A (en) Elastic method for scheduling task, device, equipment and computer readable storage medium
DE112010005705T5 (en) Reschedule workload in a hybrid computing environment
CN105184847A (en) 3D game rendering engine rendering method
CN101430670B (en) I/O equipment reconstruction method and system in virtualization surroundings
US20230393879A1 (en) Coordinated Container Scheduling For Improved Resource Allocation In Virtual Computing Environment
CN105183566A (en) Resource management method for 3D game rendering engine
De Alfonso et al. An energy management system for cluster infrastructures
CN109800067A (en) Database connection optimization method, device and relevant device based on cloud monitoring
CN109032788A (en) Reserved resource pool dynamic dispatching method, device, computer equipment and storage medium
US9798483B2 (en) Object storage power consumption optimization
CN105930202B (en) A kind of virtual machine migration method of three threshold values
CN117331690A (en) Method for efficiently utilizing computing resources based on cloud computing
Lannurien et al. HeROfake: Heterogeneous Resources Orchestration in a Serverless Cloud–An Application to Deepfake Detection
US20220374702A1 (en) Methods and systems for predicting behavior of distributed applications
Lufei et al. vStarCloud: An operating system architecture for Cloud computing

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