CN111459684A - Cloud computing resource fusion scheduling management method, system and medium for multiprocessor architecture - Google Patents
Cloud computing resource fusion scheduling management method, system and medium for multiprocessor architecture Download PDFInfo
- Publication number
- CN111459684A CN111459684A CN202010332530.1A CN202010332530A CN111459684A CN 111459684 A CN111459684 A CN 111459684A CN 202010332530 A CN202010332530 A CN 202010332530A CN 111459684 A CN111459684 A CN 111459684A
- Authority
- CN
- China
- Prior art keywords
- host
- hosts
- virtual machine
- list
- cloud 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
Links
- 238000007726 management method Methods 0.000 title claims abstract description 36
- 230000004927 fusion Effects 0.000 title claims abstract description 30
- 238000000034 method Methods 0.000 claims description 21
- 238000004590 computer program Methods 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 125000004432 carbon atom Chemical group C* 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000005192 partition Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000000638 solvent extraction Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000007246 mechanism Effects 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
- 230000008569 process Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
- G06F9/5038—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals considering the execution order of a plurality of tasks, e.g. taking priority or time dependency constraints into consideration
-
- 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]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5011—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resources being hardware resources other than CPUs, Servers and Terminals
- G06F9/5016—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resources being hardware resources other than CPUs, Servers and Terminals the resource being the memory
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Stored Programmes (AREA)
Abstract
The invention discloses a cloud computing resource fusion scheduling management method, a system and a medium for a multiprocessor architectureiThe detailed step of selecting the target host comprises the steps of obtaining a host list HOSTS and the description of the virtualization capacity of each host in the host list HOSTS, and according to the VM of the virtual machineiThe HOSTS list is screened according to the requirements and the virtualization capability description of each host machine to obtain the requirement of meeting the VMiRequired host list VM _ HOSTSiFor host list VM _ HOSTSiSorting, selecting one host with the highest priority or one of a plurality of hosts with higher priorities as the virtual machine VMiThe target host of (1). The invention can realize the unified virtual scheduling management of resources under the multiprocessor architecture, automatically schedule and select heterogeneous resources and greatly improve the useUser experience and reduced resource management complexity.
Description
Technical Field
The invention relates to a virtualized resource scheduling management technology in the cloud computing field, in particular to a cloud computing resource fusion scheduling management method, a cloud computing resource fusion scheduling management system and a cloud computing resource fusion scheduling management medium for a multiprocessor architecture, which are particularly suitable for computing resource fusion scheduling management for the multiprocessor architecture comprising X86, ARM64, MIPS, Alpha and the like under the same cloud computing platform.
Background
With the development of cloud computing and virtualization technologies, cloud computing and its derivative products have been successfully deployed and applied to a plurality of industry fields. The data center hardware and the cloud computing technology can provide the capability of conveniently and quickly available infrastructure services, platform services, software services and the like for people. Compared with the traditional resource service mode, the application of the cloud computing technology not only greatly improves the resource utilization rate, but also greatly improves the operation and maintenance support capability of the system.
With the research and development of the independent controllable software and hardware products in China, the independent controllable basic platform is applied in a large scale in partial fields, a domestic multiprocessor instruction calculation architecture coexists, the CPU technology tends to be diversified and independently controllable, and gradually enters the construction of a data center to play an important supporting role.
Therefore, for heterogeneous computing resources such as a commercial X86 architecture, a domestic multiprocessor architecture and the like, how to realize cloud unified management scheduling of the heterogeneous resources faces a new challenge, 1, difference of virtualization support, under a production environment, different hardware platforms have different maturity of support capability for virtualization, some platforms can support multiple virtualization mechanisms such as KVM, Docker, L XC and the like, and some hardware platforms can only support light-weight virtualization such as Docker, L and the like, 2, management complexity, under the existing mode, hardware resources of different architectures can be partitioned in a partitioning mode to pool virtual resources, but under the partitioning mode, the hardware resources of different architectures need to be partitioned according to different CPU architectures and virtualization modes, such as a KVM virtualization partition of X86, a Docker virtualization partition of X86, a KVM virtualization partition of flying, a Docker partition of a core and the like, so that the use requirements of end users are met, a combination problem of hardware architecture and virtualization mode exists, and 3, a certain number of experience of users is reduced.
Disclosure of Invention
The technical problems to be solved by the invention are as follows: aiming at the problems in the prior art, the invention provides a method, a system and a medium for managing the fusion scheduling of cloud computing resources oriented to a multiprocessor architecture, which realize the unified virtual scheduling management of resources under the multiprocessor architecture including X86, ARM64, MIPS, Alpha and the like through a cloud computing platform, automatically schedule and select heterogeneous resources, and can greatly improve the user experience and reduce the complexity of resource management.
In order to solve the technical problems, the invention adopts the technical scheme that:
a cloud computing resource fusion scheduling management method for a multiprocessor architecture is a given virtual machine VMiThe detailed steps of selecting a target host include:
1) acquiring a host list HOSTS and a virtualization capability description of each host in the host list HOSTS, wherein the virtualization capability description comprises a processor architecture supported by the host;
2) according to virtual machine VMiThe HOSTS list is screened according to the requirements and the virtualization capability description of each host machine to obtain the requirement of meeting the VMiRequired host list VM _ HOSTSiThe virtual machine VMiIncluding a virtual machine VMiA required processor architecture;
3) to host list VM _ HOSTSiAccording to available resources, the host in (1) takes precedenceSorting the levels;
4) from the ordered list of HOSTS VM _ HOSTSiOne host with the highest priority or one of a plurality of hosts with higher priorities is selected as the virtual machine VMiThe target host of (1).
Optionally, the virtual machine VM in step 2)iThe requirements come from virtual machine attributes of the image file selected by the user when creating the virtual machine.
Optionally, the virtualization capability description of the host further includes virtualization types supported by the host, and the virtual machine VMiThe requirements of (2) also include a virtualization type; the detailed step of screening the host list HOSTS in step 2) comprises: initializing host list VM _ HOSTSiIf the host is empty, traversing and taking out one host from the host list HOSTS as the host of the current hostjIf the host is currently presentjThe supported processor architecture and virtualization type both meet the virtual machine VMiWill be the current hostjAdd host list VM _ HOSTSiAnd continuously traversing the HOSTS list until the traversal is finished.
Optionally, the virtual machine VMiThe method also comprises the requirements on CPU, memory and storage resources, and the method also comprises the steps of VM according to the virtual machine after the step 2) and before the step 3)iUpdating host machine list VM _ HOSTS according to requirements of CPU, memory and storage resourcesiAnd obtaining the host machine meeting the requirements of the CPU, the memory and the storage resources.
Optionally, the virtual machine VMiUpdating host machine list VM _ HOSTS according to requirements of CPU, memory and storage resourcesiComprises the following steps: respectively acquiring host machine list VM _ HOSTSiThe available CPU, memory and storage resources of each host machine are selected from the host machine list VM _ HOSTSiIn the traversal, one host is taken out to be used as the host of the current hostkIf the virtual machine VMiThe requirement for CPU resources divided by the current hostkThe available CPU resource is less than a first preset threshold value, and the virtual machine VMiMemory resource requirements divided by the current hostkThe available memory resources are smaller than a second preset threshold value, and the virtual machine VMiThe demand for storage resources divided by the current hostkIf the three conditions that the available storage resources are smaller than the third preset threshold value meet the preset conditions, the host computer host at present is startedkReserved, otherwise, current hostkEliminating and continuously traversing the VM _ HOSTS of the host machine listiObtaining an updated host machine list VM _ HOSTS finally until the traversal is finishedi。
Optionally, the host list VM _ HOSTS in step 3) is subjected to the processingiWhen the hosts in (1) perform priority ranking according to the available resources, the expression of the calculation function of the priority is shown as the following formula:
in the above formula, the first and second carbon atoms are,represents the jth hostjβ1Coefficient of available resources for CPU β2Coefficient of available resources for memory, β3To store coefficients of available resources, VMiCpu represents a virtual machine VMiRequirement for CPU resource, ava.res.cpu represents hostjAvailable CPU resources, VMiMem represents the virtual machine VMiRequirement on memory resource, ava.res.mem represents hostjAvailable memory resources, VMiDisk represents a virtual machine VMiRequirement for storage resources, ava.res.disk represents hostjAvailable storage resources.
Optionally, one of the host machines with higher priority is selected as the virtual machine VM in step 4)iThe detailed steps of the target host of (1) include: determining a host list VM _ HOSTSiWhether the number of elements is greater than a preset integer parameter Ran is true, if true, only VM _ HOSTS is reservediThe first Ran elements are deleted, and otherwise, the elements are kept unchanged; from host list VM _ HOSTSiIn randomly selecting an elementPlain as virtual machine VMiThe target host of (1).
In addition, the invention also provides a multiprocessor architecture-oriented cloud computing resource fusion scheduling management method, and the step of scheduling the given virtual machine set VMS to the host machine for instantiation comprises the following steps:
s1) traversing and selecting one virtual machine from the VMS as the current VMi;
S2) adopting the cloud computing resource fusion scheduling management method facing the multiprocessor architecture to serve as a given virtual machine VMiSelecting a target host machine;
s3) assigning the current virtual machine VMiScheduling the target host machine to instantiate;
s4) updating the records of available CPU, memory, storage resources of each host.
In addition, the invention also provides a cloud computing resource fusion scheduling management system facing to the multiprocessor architecture, which comprises a computer device, and is characterized in that the computer device is programmed or configured to execute the steps of the cloud computing resource fusion scheduling management method facing to the multiprocessor architecture, or a computer program programmed or configured to execute the cloud computing resource fusion scheduling management method facing to the multiprocessor architecture is stored in a memory of the computer device.
In addition, the present invention also provides a computer readable storage medium, which is characterized in that the computer readable storage medium stores thereon a computer program programmed or configured to execute the cloud computing resource fusion scheduling management method for a multiprocessor architecture.
Compared with the prior art, the invention has the following advantages:
1. the invention obtains the HOSTS of the host list and the virtualization capability description of each host in the HOSTS, and the VM of the virtual machine is obtainediThe HOSTS list is screened according to the requirements and the virtualization capability description of each host machine to obtain the requirement of meeting the VMiRequired host list VM _ HOSTSiFinally from the ordered list of hosts VM _ HOSTSiOne host with the highest priority or one of a plurality of hosts with higher priorities is selected as the virtual machine VMiTherefore, the target host machine can realize unified virtual scheduling management of resources under a multiprocessor architecture including X86, ARM64, MIPS, Alpha and the like through a cloud computing platform, automatically schedule and select heterogeneous resources, and greatly improve user experience and reduce complexity of resource management.
2. The invention comprises the steps of listing a host machine VM _ HOSTSiAccording to available resources, the host machines in the system are subjected to priority ordering, and a list VM _ HOSTS of the ordered host machines is obtainediOne host with the highest priority or one of a plurality of hosts with higher priorities is selected as the virtual machine VMiThereby realizing load balance of the host machine.
Drawings
FIG. 1 is a basic flow diagram of a method according to an embodiment of the present invention.
Detailed Description
As shown in fig. 1, in the cloud computing resource fusion scheduling management method for multiprocessor architecture of the present embodiment, a given virtual machine VM is usediThe detailed steps of selecting a target host include:
1) acquiring HOSTS (host computer list and virtualization capability description) of each host in HOSTS (host computer list and virtualization capability description), wherein the virtualization capability description comprises a processor architecture supported by the host;
2) according to virtual machine VMiThe HOSTS list is screened according to the requirements and the virtualization capability description of each host machine to obtain the requirement of meeting the VMiRequired host list VM _ HOSTSiVirtual machine VMiIncluding a virtual machine VMiA required processor architecture;
3) to host list VM _ HOSTSiThe host machines in the system are subjected to priority sequencing according to available resources;
4) from the ordered list of HOSTS VM _ HOSTSiTo select the host with the highest priority or to select the hosts with higher priorityOne as a virtual machine VMiThe target host of (1).
In this embodiment, the virtual machine VM in step 2)iThe method can realize automatic scheduling and selection of heterogeneous resources according to the image file selected by the user when the user creates the virtual machine under the condition of no sense of the user, and can greatly improve the user experience and reduce the complexity of resource management. Specifically, in this embodiment, a virtualization attribute image _ arch is added on the basis of an existing virtual machine image data structure, and the virtualization attribute image _ arch represents an architecture that an image can instantiate, that is, under which architecture an instance of the image needs to operate, values of the image come from a set { X86, ARM64, MIPS, Alpha }, which respectively represents a commercial X86 architecture, a soaring architecture, a loongson architecture, and a shenwei architecture, although values thereof may be modified and expanded in combination with different architecture names.
In this embodiment, a virtualization attribute image _ virt _ type is added on the basis of an existing virtual machine image data structure, where the virtualization attribute image _ virt _ type represents a virtualization type of an image, and a value of the virtualization attribute image _ virt _ type is from a set { KVM, Docker, and L XC }1,supported_virti,.. } define virtual machine instance constraints on the node that can support operation, the virtual machine instance constraints supporting _ virti① is not a virtual machine which can only run the X86 architecture on the commercial X86 platform, because the virtual machine can run other architectures such as ARM by simulation, therefore, the virt _ arch _ name does not need to be completely consistent with the host architecture in theory, and can be set as { X86, ARM64, Virt _ type, virt _ engineer according to actual requirements,MIPS, Alpha), etc., but in the production environment, basically consistent with the host, i.e. which architecture virtual machine runs under which architecture, ② virt _ type takes on values { KVM, Docker, L XC }, and virtual machine images that can run on the current host are described by virt _ arch _ name and virt _ type1,supported_virt2Supported _ virt, wherein supported _ virt1={ARM64,KVM,/usr/bin/qemu-system-aarch64},supported_virt2The host can run not only the KVM image of the ARM platform but also the Docker image of the ARM platform.
In order to implement the support of the requirement of multiple virtualization types, the virtualization capability description of the host in this embodiment further includes the virtualization types supported by the host, and the virtual machine VMiThe requirements of (2) also include virtualization type. The detailed step of screening the host list HOSTS in step 2) comprises: initializing host list VM _ HOSTSiIf the host is empty, traversing and taking out one host from the host list HOSTS as the host of the current hostjIf the host is currently presentjThe supported processor architecture and virtualization type both meet the virtual machine VMiWill be the current hostjAdd host list VM _ HOSTSiAnd continuously traversing the HOSTS list until the traversal is finished. In this embodiment, the specific formula is according to the virtual machine VMiScreening a host machine list VM _ HOSTS by virtualization attributes image _ arch and image _ virt _ type in the image of the medium virtual machineiI.e. by means of these two attributes and each host in the host list HOSTSjThe virtual machine instance constraint host _ supported _ virt of any kth element supported _ virtkComparing fields, if host existsjSatisfies the following conditions:
image.image_arch==host_supported_virt.supported_virtkvirt _ arch _ name and
image.mage_virt_type==host_supported_virt.supported_virtk.virt_type
the host is declared to be architecturally and virtuallyVirtual machine VM can be instantiated on a virtualized constraintiTherefore, the host is required to be currently ownedjAdd host list VM _ HOSTSi。
In the above formula, image _ image represents a virtualization attribute image _ image in the virtual machine image, image _ virt _ type represents a virtualization attribute image _ virt _ type in the virtual machine image, and host _ supported _ virtkVirt _ arch _ name represents hostjThe virtual machine instance constraint host _ supported _ virt of any kth element supported _ virtkSupported processor architecture of (1), host _ supported _ virtkVirt _ type denotes hostjThe virtual machine instance constraint host _ supported _ virt of any kth element supported _ virtkThe supported virtualization type of (2).
In order to support the node resource requirement, the virtual machine VM in this embodimentiThe method also comprises the requirements on CPU, memory and storage resources, and the method also comprises the steps of VM according to the virtual machine after the step 2) and before the step 3)iUpdating host machine list VM _ HOSTS according to requirements of CPU, memory and storage resourcesiAnd obtaining the host machine meeting the requirements of the CPU, the memory and the storage resources.
In this embodiment, the VM is a virtual machineiUpdating host machine list VM _ HOSTS according to requirements of CPU, memory and storage resourcesiComprises the following steps: respectively acquiring host machine list VM _ HOSTSiThe available CPU, memory and storage resources of each host machine are selected from the host machine list VM _ HOSTSiIn the traversal, one host is taken out to be used as the host of the current hostkIf the virtual machine VMiThe requirement for CPU resources divided by the current hostkThe available CPU resource is less than a first preset threshold value, and the virtual machine VMiMemory resource requirements divided by the current hostkThe available memory resources are smaller than a second preset threshold value, and the virtual machine VMiThe demand for storage resources divided by the current hostkIf the three conditions that the available storage resources are less than the third preset threshold satisfy the preset conditions (e.g., all are true, or some are true, etc.), thenHost the current hostkReserved, otherwise, current hostkEliminating and continuously traversing the VM _ HOSTS of the host machine listiObtaining an updated host machine list VM _ HOSTS finally until the traversal is finishedi. Virtual machine VMiThe requirements for CPU, memory, storage resources may be expressed as { VM }i.cpu,VMi.mem,VMiDisk, the satisfaction of the three conditions specifically means that all of the three conditions are satisfied, and the first preset threshold, the second preset threshold, and the third preset threshold all take the same value as the coefficient α (0)<α<1), then three conditions can be expressed as:
{VMi.cpu,VMi.mem,VMi.disk}<α*hostj.ava.res.{cpu,mem,disk}
in the above formula, α is a coefficient, hostjAv.res. { cpu, mem, disk } is hostjAvailable CPU, memory, storage resources.
In this embodiment, VM _ HOSTS is listed in the host machine list in step 3)iWhen the hosts in (1) perform priority ranking according to the available resources, the expression of the calculation function of the priority is shown as the following formula:
in the above formula, the first and second carbon atoms are,represents the jth hostjβ1β is the coefficient (value is between 0 and 1) of available resources of the CPU2β is the coefficient of available resources (value between 0 and 1) of the memory3For storing the coefficients (with values between 0 and 1) of the available resources, VMiCpu represents a virtual machine VMiRequirement for CPU resource, ava.res.cpu represents hostjAvailable CPU resources, VMiMem represents a virtual machine VMiRequirement on memory resource, ava.res.mem represents hostjAvailable memory resources, VMiDisk represents a virtual machine VMiRequirement for storage resources, ava.rDisk represents hostjAvailable storage resources.HostjCreate VMiThe greater the value of (A) indicates a virtual machine VMiIs dispatched to hostjThe better, of course in practical use, the function may be adjusted as required.
In this embodiment, step 4) includes sorting the ordered pair host machine lists VM _ HOSTSiThere are two alternative ways to select the host: as an optional implementation mode, one host with the highest priority is directly selected as the virtual machine VMiThe target host(s) of (1), specifically denoted as ordered host list VM _ HOSTSiThe first host is selected because the host has the highest priority. However, under this selection algorithm, if the configuration of a host in the cluster is especially large, i.e., there are especially many available resources, it is easy for all virtual machines to be scheduled to a node, so we can balance the scheduling results of the virtual machines by a randomization method.
In view of the above problems, this embodiment also provides another optional implementation manner, that is: selecting one of a plurality of host machines with higher priority as a virtual machine VMiThe target host of (1). The selection method can adopt the modes of random, alternate and the like according to the requirement. For example, in step 4) of this embodiment, one of the host machines with higher priority is selected as the virtual machine VMiThe detailed steps of the target host of (1) include: determining a host list VM _ HOSTSiWhether the number of elements is greater than a preset integer parameter Ran is true, if true, only VM _ HOSTS is reservediThe first Ran elements are deleted, and otherwise, the elements are kept unchanged; from host list VM _ HOSTSiRandomly selecting one element as a virtual machine VMiThereby balancing the scheduling result of the virtual machine by a randomization method.
In the method of this embodiment, the step of scheduling a given vm set VMS to a host for instantiation includes:
s1) traversing and selecting one virtual machine from the VMS as the current VMi;
S2) adopting the cloud computing resource fusion scheduling management method facing the multiprocessor architecture to perform Virtual Machine (VM) scheduling for the given virtual machineiSelecting a target host machine;
s3) assigning the current virtual machine VMiScheduling the target host machine to instantiate;
s4) updating the records of available CPU, memory, storage resources of each host.
The VMS virtual machine set containing n virtual machines can be expressed as { VM1,VM2,...,VMi,...,VMnEvery VM that needs to be creatediThe main requirements include { cpu, mem, disk, image }, and each VM needs to be installed according to the requirementsiAnd scheduling the host to be instantiated. In this embodiment, host is updated in step S4)jThe available CPU, memory, and storage resource recording modes are as follows:
hostj.ava.res.{cpu,mem,disk}=hostj.ava.res.{cpu,mem,disk}-VMi.{cpu,mem,disk}
in the above formula, hostjRes. { cpu, mem, disk } represents hostjAvailable CPU, memory, storage resources, VMi{ cpu, mem, disk } represents instantiating a virtual machine VMiRequired CPU, memory, storage resources. As an optional implementation manner, in this embodiment, the CPU resource may be expressed in percentage, the memory resource may be expressed in MB, the storage resource may be expressed in GB, the CPU resource is initially 100%, and the memory and the storage resource are configured according to actual memory and storage.
In addition, the embodiment also provides a system for managing the cloud computing resource convergence scheduling for the multiprocessor architecture, which includes a computer device programmed or configured to execute the steps of the foregoing method for managing the cloud computing resource convergence scheduling for the multiprocessor architecture, or a memory of the computer device having stored thereon a computer program programmed or configured to execute the foregoing method for managing the cloud computing resource convergence scheduling for the multiprocessor architecture.
In addition, the present embodiment also provides a computer-readable storage medium, on which a computer program programmed or configured to execute the foregoing cloud computing resource fusion scheduling management method for a multiprocessor architecture is stored.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein. The present application is directed to methods, apparatus (systems), and computer program products according to embodiments of the application wherein instructions, which execute via a flowchart and/or a processor of the computer program product, create means for implementing functions specified in the flowchart and/or block diagram block or blocks. These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments, and all technical solutions belonging to the idea of the present invention belong to the protection scope of the present invention. It should be noted that modifications and embellishments within the scope of the invention may occur to those skilled in the art without departing from the principle of the invention, and are considered to be within the scope of the invention.
Claims (10)
1. A cloud computing resource fusion scheduling management method oriented to a multiprocessor architecture is characterized in that a given virtual machine VM is adoptediThe detailed steps of selecting a target host include:
1) acquiring a host list HOSTS and a virtualization capability description of each host in the host list HOSTS, wherein the virtualization capability description comprises a processor architecture supported by the host;
2) according to virtual machine VMiThe HOSTS list is screened according to the requirements and the virtualization capability description of each host machine to obtain the requirement of meeting the VMiRequired host list VM _ HOSTSiThe virtual machine VMiIncluding a virtual machine VMiA required processor architecture;
3) to host list VM _ HOSTSiThe host machines in the system are subjected to priority sequencing according to available resources;
4) from the ordered list of HOSTS VM _ HOSTSiOne host with the highest priority or one of a plurality of hosts with higher priorities is selected as the virtual machine VMiThe target host of (1).
2. The cloud computing resource fusion scheduling management method for multiprocessor architecture as claimed in claim 1, wherein in step 2), the virtual machine VMiThe requirements come from virtual machine attributes of the image file selected by the user when creating the virtual machine.
3. The cloud computing resource fusion scheduling management method for multiprocessor architecture as claimed in claim 2, wherein the virtualization capability description of the host further includes virtualization types supported by the host, and the virtual machine VMiThe requirements of (2) also include the type of virtualization,the detailed step of screening the host list HOSTS in step 2) comprises: initializing host list VM _ HOSTSiIf the host is empty, traversing and taking out one host from the host list HOSTS as the host of the current hostjIf the host is currently presentjThe supported processor architecture and virtualization type both meet the virtual machine VMiWill be the current hostjAdd host list VM _ HOSTSiAnd continuously traversing the HOSTS list until the traversal is finished.
4. The multiprocessor architecture-oriented cloud computing resource fusion scheduling management method of claim 1, wherein the virtual machine VMiThe method also comprises the requirements on CPU, memory and storage resources, and the method also comprises the steps of VM according to the virtual machine after the step 2) and before the step 3)iUpdating host machine list VM _ HOSTS according to requirements of CPU, memory and storage resourcesiAnd obtaining the host machine meeting the requirements of the CPU, the memory and the storage resources.
5. The multiprocessor architecture-oriented cloud computing resource fusion scheduling management method of claim 4, wherein the VM is according to a virtual machineiUpdating host machine list VM _ HOSTS according to requirements of CPU, memory and storage resourcesiComprises the following steps: respectively acquiring host machine list VM _ HOSTSiThe available CPU, memory and storage resources of each host machine are selected from the host machine list VM _ HOSTSiIn the traversal, one host is taken out to be used as the host of the current hostkIf the virtual machine VMiThe requirement for CPU resources divided by the current hostkThe available CPU resource is less than a first preset threshold value, and the virtual machine VMiMemory resource requirements divided by the current hostkThe available memory resources are smaller than a second preset threshold value, and the virtual machine VMiThe demand for storage resources divided by the current hostkIf the three conditions that the available storage resources are smaller than the third preset threshold value meet the preset conditions, the host computer host at present is startedkReserved, otherwise, current hostkWill pickExcept that, the host machine list VM _ HOSTS is continuously traversediObtaining an updated host machine list VM _ HOSTS finally until the traversal is finishedi。
6. The method for managing the cloud computing resource fusion scheduling of the multiprocessor architecture as claimed in claim 1, wherein VM _ HOSTS is a host list in step 3)iWhen the hosts in (1) perform priority ranking according to the available resources, the expression of the calculation function of the priority is shown as the following formula:
in the above formula, the first and second carbon atoms are,represents the jth hostjβ1Coefficient of available resources for CPU β2Coefficient of available resources for memory, β3To store coefficients of available resources, VMiCpu represents a virtual machine VMiRequirement for CPU resource, ava.res.cpu represents hostjAvailable CPU resources, VMiMem represents a virtual machine VMiRequirement on memory resource, ava.res.mem represents hostjAvailable memory resources, VMiDisk represents a virtual machine VMiRequirement for storage resources, ava.res.disk represents hostjAvailable storage resources.
7. The method for managing the cloud computing resource fusion scheduling oriented to the multiprocessor architecture of claim 1, wherein in step 4), one of the host machines with higher priority is selected as the virtual machine VMiThe detailed steps of the target host of (1) include: determining a host list VM _ HOSTSiWhether the number of elements is greater than a preset integer parameter Ran is true, if true, only VM _ HOSTS is reservediThe first Ran elements are deleted, and otherwise, the elements are kept unchanged; from host list VM _ HOSTSiRandomly selecting one element as a virtual machine VMiThe target host of (1).
8. A multi-processor architecture-oriented cloud computing resource fusion scheduling management method is characterized in that a step of scheduling a given virtual machine set VMS to a host machine for instantiation comprises the following steps:
s1) traversing and selecting one virtual machine from the VMS as the current VMi;
S2) adopting the method for managing the fusion scheduling of the cloud computing resources oriented to the multiprocessor architecture in any one of claims 1 to 7 to serve as a given virtual machine VMiSelecting a target host machine;
s3) assigning the current virtual machine VMiScheduling the target host machine to instantiate;
s4) updating the records of available CPU, memory, storage resources of each host.
9. A cloud computing resource fusion scheduling management system for a multiprocessor architecture, comprising a computer device, wherein the computer device is programmed or configured to execute the steps of the cloud computing resource fusion scheduling management method for the multiprocessor architecture of any one of claims 1 to 8, or a memory of the computer device stores a computer program programmed or configured to execute the cloud computing resource fusion scheduling management method for the multiprocessor architecture of any one of claims 1 to 8.
10. A computer-readable storage medium, wherein the computer-readable storage medium stores thereon a computer program programmed or configured to execute the method for managing cloud computing resource convergence scheduling for a multiprocessor architecture according to any one of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010332530.1A CN111459684A (en) | 2020-04-24 | 2020-04-24 | Cloud computing resource fusion scheduling management method, system and medium for multiprocessor architecture |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010332530.1A CN111459684A (en) | 2020-04-24 | 2020-04-24 | Cloud computing resource fusion scheduling management method, system and medium for multiprocessor architecture |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111459684A true CN111459684A (en) | 2020-07-28 |
Family
ID=71683927
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010332530.1A Pending CN111459684A (en) | 2020-04-24 | 2020-04-24 | Cloud computing resource fusion scheduling management method, system and medium for multiprocessor architecture |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111459684A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112241304A (en) * | 2020-10-12 | 2021-01-19 | 北京计算机技术及应用研究所 | Scheduling method and device for super-converged resources in Loongson cluster and Loongson cluster |
CN113312142A (en) * | 2021-02-26 | 2021-08-27 | 阿里巴巴集团控股有限公司 | Virtualization processing system, method, device and equipment |
WO2022047621A1 (en) * | 2020-09-01 | 2022-03-10 | Huawei Cloud Computing Technologies Co., Ltd. | Systems and methods of hybrid centralized distributive scheduling on shared physical hosts |
CN114816672A (en) * | 2022-05-06 | 2022-07-29 | 中国电信股份有限公司 | Virtual machine creation method and device, electronic equipment and storage medium |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104010028A (en) * | 2014-05-04 | 2014-08-27 | 华南理工大学 | Dynamic virtual resource management strategy method for performance weighting under cloud platform |
CN109582433A (en) * | 2017-09-29 | 2019-04-05 | 腾讯科技(深圳)有限公司 | A kind of resource regulating method, device, cloud computing system and storage medium |
-
2020
- 2020-04-24 CN CN202010332530.1A patent/CN111459684A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104010028A (en) * | 2014-05-04 | 2014-08-27 | 华南理工大学 | Dynamic virtual resource management strategy method for performance weighting under cloud platform |
CN109582433A (en) * | 2017-09-29 | 2019-04-05 | 腾讯科技(深圳)有限公司 | A kind of resource regulating method, device, cloud computing system and storage medium |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2022047621A1 (en) * | 2020-09-01 | 2022-03-10 | Huawei Cloud Computing Technologies Co., Ltd. | Systems and methods of hybrid centralized distributive scheduling on shared physical hosts |
CN112241304A (en) * | 2020-10-12 | 2021-01-19 | 北京计算机技术及应用研究所 | Scheduling method and device for super-converged resources in Loongson cluster and Loongson cluster |
CN112241304B (en) * | 2020-10-12 | 2023-09-26 | 北京计算机技术及应用研究所 | Loongson cluster super-fusion resource scheduling method and device and Loongson cluster |
CN113312142A (en) * | 2021-02-26 | 2021-08-27 | 阿里巴巴集团控股有限公司 | Virtualization processing system, method, device and equipment |
CN113312142B (en) * | 2021-02-26 | 2023-12-26 | 阿里巴巴集团控股有限公司 | Virtualized processing system, method, device and equipment |
CN114816672A (en) * | 2022-05-06 | 2022-07-29 | 中国电信股份有限公司 | Virtual machine creation method and device, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111459684A (en) | Cloud computing resource fusion scheduling management method, system and medium for multiprocessor architecture | |
US11809913B2 (en) | Load balancing of cloned virtual machines | |
US11720408B2 (en) | Method and system for assigning a virtual machine in virtual GPU enabled systems | |
JP6893284B2 (en) | Resource scheduling methods, scheduling servers, cloud computing systems, and storage media | |
US9389924B2 (en) | System and method for performing resource allocation for a host computer cluster | |
CN106933669B (en) | Apparatus and method for data processing | |
EP2819010B1 (en) | Performance-driven resource management in a distributed computer system | |
US9183016B2 (en) | Adaptive task scheduling of Hadoop in a virtualized environment | |
CN114138486B (en) | Method, system and medium for arranging containerized micro-services for cloud edge heterogeneous environment | |
CN102971724B (en) | The method and apparatus relevant with the management based on modular virtual resource in data center environment | |
US20200133718A1 (en) | Virtual machine migration task management | |
TWI786564B (en) | Task scheduling method and apparatus, storage media and computer equipment | |
US8782646B2 (en) | Non-uniform memory access (NUMA) enhancements for shared logical partitions | |
JPH09237215A (en) | Operating system for uneven memory access multiprocessor system | |
US20120030675A1 (en) | Computer system | |
US20160196157A1 (en) | Information processing system, management device, and method of controlling information processing system | |
US11263054B2 (en) | Memory-aware placement for virtual GPU enabled systems | |
US11372683B2 (en) | Placement of virtual GPU requests in virtual GPU enabled systems using a requested memory requirement of the virtual GPU request | |
CN103605574A (en) | Virtual machine resource scheduling method and system for server clusters | |
CN114356543A (en) | Kubernetes-based multi-tenant machine learning task resource scheduling method | |
CN112052068A (en) | Method and device for binding CPU (central processing unit) of Kubernetes container platform | |
CN112015765B (en) | Spark cache elimination method and system based on cache value | |
CN115964176B (en) | Cloud computing cluster scheduling method, electronic equipment and storage medium | |
CN115102851B (en) | Fusion platform for HPC and AI fusion calculation and resource management method thereof | |
KR102045997B1 (en) | Method for scheduling task in big data analysis platform based on distributed file system, program and computer readable storage medium therefor |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200728 |