CN111858014A - Resource allocation method and device - Google Patents
Resource allocation method and device Download PDFInfo
- Publication number
- CN111858014A CN111858014A CN201910335161.9A CN201910335161A CN111858014A CN 111858014 A CN111858014 A CN 111858014A CN 201910335161 A CN201910335161 A CN 201910335161A CN 111858014 A CN111858014 A CN 111858014A
- Authority
- CN
- China
- Prior art keywords
- task
- dimension
- attribute information
- resource allocation
- resource
- 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
- 238000013468 resource allocation Methods 0.000 title claims abstract description 154
- 238000000034 method Methods 0.000 title claims abstract description 60
- 239000013598 vector Substances 0.000 claims abstract description 60
- 238000010606 normalization Methods 0.000 claims abstract description 32
- 239000011159 matrix material Substances 0.000 claims description 39
- 230000006870 function Effects 0.000 claims description 18
- 238000004891 communication Methods 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 13
- 238000012360 testing method Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000008602 contraction Effects 0.000 abstract description 4
- 238000004458 analytical method Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 238000012546 transfer 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]
- G06F9/5061—Partitioning or combining of resources
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a resource allocation method and a device, wherein the method comprises the following steps: determining task attribute information of multiple dimensions corresponding to each resource allocation task in a resource allocation queue; respectively inquiring a normalization weight vector which is stored in a background database and corresponds to the task attribute information of each dimension aiming at the task attribute information of each dimension contained in the task attribute information of the plurality of dimensions, and determining a dimension weight value corresponding to the task attribute information of the dimension according to an inquiry result; determining a task weight value of the resource allocation task according to a dimension weight value corresponding to each dimension of task attribute information contained in the multi-dimension task attribute information; and allocating resources for each resource allocation task in the resource allocation queue according to the task weight value of each resource allocation task. The distribution mode does not need manual intervention, avoids the problems of frequent restart, expansion and contraction of the system, and improves the system efficiency.
Description
Technical Field
The invention relates to the field of electronic information, in particular to a resource allocation method and device.
Background
At present, in order to achieve reasonable utilization of resources, network resources can be shared by a plurality of devices by using a technique such as a virtual machine. In this scenario, network resources need to be reasonably allocated to meet the requirements of each device. In a conventional resource allocation manner, each resource allocation task is usually added to a preset resource allocation queue in sequence according to task generation time, so that the resource allocation tasks are extracted from the resource allocation queue in sequence in a first-in first-out manner for processing. In this way, the weight values of the resource allocation tasks are equal, and the allocation is performed only according to the sequence of the task generation time. However, since some tasks have a high degree of urgency and need to be executed immediately, in order to ensure the normal operation of the tasks, in the above manner, an urgency flag is set for the urgent task so as to allocate resources to the urgent task preferentially.
However, the inventors found that the resource allocation method has at least the following disadvantages in the process of implementing the present invention: the resource allocation tasks are processed only according to the task generation time, and only a few emergency tasks can be manually set with emergency marks so as to be processed preferentially. However, in actual situations, the types of resource allocation tasks are various, and the urgency level, the importance level, and the resource demand amount of each resource allocation task are different, so that the task with a high urgency level and a high importance level cannot be preferentially executed in some cases by adopting the allocation method. Therefore, the resource allocation method cannot realize effective utilization of resources and timely processing of tasks. Moreover, the emergency task in the resource allocation mode is mainly handled in a manual intervention mode, which easily causes frequent restart, expansion and contraction of the system, often needs which resources urgently, and is adjusted according to needs, so that the business can be changed in and out repeatedly, and the system efficiency is greatly reduced.
Disclosure of Invention
In view of the above, the present invention is proposed to provide a resource allocation method and apparatus that overcomes or at least partially solves the above problems.
According to an aspect of the present invention, there is provided a resource allocation method, including:
determining task attribute information of multiple dimensions corresponding to each resource allocation task in a resource allocation queue;
respectively inquiring a normalization weight vector corresponding to the task attribute information of each dimension in the background database aiming at the task attribute information of each dimension contained in the task attribute information of the plurality of dimensions, and determining a dimension weight value corresponding to the task attribute information of each dimension according to an inquiry result;
determining a task weight value of the resource allocation task according to a dimension weight value corresponding to each dimension of task attribute information contained in the multi-dimension task attribute information;
and allocating resources for each resource allocation task in the resource allocation queue according to the task weight value of each resource allocation task.
According to another aspect of the present invention, there is provided a resource allocation apparatus, including: the task attribute determining module is suitable for determining task attribute information of multiple dimensions corresponding to each resource allocation task in the resource allocation queue;
The dimension weight determining module is suitable for respectively inquiring the normalization weight vector which is stored in the background database and corresponds to the task attribute information of each dimension in the task attribute information of the plurality of dimensions, and determining the dimension weight value corresponding to the task attribute information of the dimension according to the inquiry result;
the task weight determining module is suitable for determining a task weight value of the resource allocation task according to a dimension weight value corresponding to each dimension of task attribute information contained in the multi-dimension task attribute information;
and the allocation module is suitable for allocating resources for each resource allocation task in the resource allocation queue according to the task weight value of each resource allocation task.
According to still another aspect of the present invention, there is provided an electronic apparatus including: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction enables the processor to execute the operation corresponding to the resource allocation method.
According to still another aspect of the present invention, a computer storage medium is provided, where at least one executable instruction is stored in the storage medium, and the executable instruction causes a processor to perform an operation corresponding to the resource allocation method as described above.
In the resource allocation method and the resource allocation device, the task attribute information of multiple dimensions corresponding to the resource allocation task can be determined for each resource allocation task in the resource allocation queue; and respectively determining a dimension weight value corresponding to the task attribute information of the dimension aiming at the task attribute information of each dimension contained in the task attribute information of the dimensions, thereby determining the task weight value of the resource allocation task according to the dimension weight value corresponding to the task attribute information of each dimension contained in the task attribute information of the dimensions, and further reasonably allocating resources. Therefore, the method can determine the task attribute information of multiple dimensions corresponding to each resource allocation task so as to describe the task from different dimensions, and further calculate the task weight value of each task according to the preset dimension weight value corresponding to the task attribute information of each dimension, so that the weight value of each task is reasonably determined by combining the task attribute information of different dimensions, the weight can be reasonably allocated to each task, and the resources are reasonably utilized. Moreover, the allocation mode can be automatically implemented without manual intervention, the problems of frequent restart, expansion and contraction of the system are avoided, and the system efficiency is improved.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
fig. 1 is a flowchart illustrating a resource allocation method according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating a resource allocation method according to a second embodiment of the present invention;
fig. 3 is a block diagram illustrating a resource allocation apparatus according to a third embodiment of the present invention;
fig. 4 shows a schematic structural diagram of an electronic device according to a fifth embodiment of the present invention;
FIG. 5 illustrates one form of a resource application parse tree.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Example one
Fig. 1 shows a flowchart of a resource allocation method according to an embodiment of the present invention. As shown in fig. 1, the method includes:
step S110: and determining task attribute information of multiple dimensions corresponding to each resource allocation task in the resource allocation queue.
The resource allocation queue is used for storing a plurality of resource allocation tasks, and the resource allocation tasks in the system are more in number, so the resource allocation tasks need to be stored through the resource allocation queue. The resource allocation queue may be in other forms such as a list and a set, as long as it can be used for storing a plurality of resource allocation tasks.
Specifically, each resource allocation task is described by task attribute information of multiple dimensions, and therefore, the task attribute information may also be referred to as task description information. The task attribute information is generally determined according to a resource allocation target, a resource allocation rule, and/or a resource allocation influence factor related to the resource allocation task. For example, task attribute information divided from the dimension of the business function and/or business type, task attribute information divided from the dimension of the system type, and the like may be included. In summary, all factors related to resource allocation can be used as task attribute information of one dimension. The task can be fully described through the task attribute information with different dimensions, so that the weight value of the task can be determined subsequently.
Step S120: and respectively inquiring a normalization weight vector corresponding to the task attribute information of the dimension stored in a background database aiming at the task attribute information of each dimension contained in the task attribute information of the plurality of dimensions, and determining a dimension weight value corresponding to the task attribute information of the dimension according to an inquiry result.
The background database stores normalization weight vectors corresponding to the task attribute information of each dimension in advance. Each normalized weight vector is used for determining a dimension weight value of the task attribute information of the corresponding dimension. For example, for the task attribute information of the business function dimension, the attribute element set corresponding to the task attribute information of the business function dimension includes the following three attribute elements: correspondingly, the normalized weight vector corresponding to the task attribute information of the business function dimension comprises three weight values respectively corresponding to each attribute element, so that the dimension weight value of the task attribute information can be quickly determined according to the normalized weight vector. The attribute element set is used for storing various values of task attribute information of corresponding dimensions, correspondingly, one attribute element in the attribute element set corresponds to one value of the task attribute information, for example, a business system element corresponds to task attribute information of which the value is a business system, so that the dimension weight value of the current task attribute information can be quickly determined according to the weight value of the attribute element corresponding to the value of the current task attribute information stored in the normalized weight vector.
Step S130: and determining the task weight value of the resource allocation task according to the dimension weight value corresponding to the task attribute information of each dimension contained in the task attribute information of the multiple dimensions.
Specifically, since the task attribute information of each dimension has a corresponding dimension weight value, a plurality of dimension weight values can be obtained, and each dimension weight value reflects the priority of the task from different dimensions, so that the priority of the task can be more comprehensively evaluated by determining the task weight value of the resource allocation task by integrating each dimension weight value. In specific implementation, the task weight value can be determined by multiplying the multiple dimension weight values, and the specific determination mode of the task weight value is not limited by the invention.
Step S140: and allocating resources for each resource allocation task in the resource allocation queue according to the task weight value of each resource allocation task.
Through the steps, different task weight values can be set for each resource allocation task in the resource allocation queue, accordingly, according to the task weight values of each resource allocation task, the mode of allocating resources for each resource allocation task in the resource allocation queue can comprehensively consider a plurality of factors such as the urgency degree and the importance degree of the tasks, and therefore resource allocation is more reasonable.
Therefore, the method can determine the task attribute information of multiple dimensions corresponding to each resource allocation task so as to describe the task from different dimensions, and further calculate the task weight value of each task according to the preset dimension weight value corresponding to the task attribute information of each dimension, so that the weight value of each task is reasonably determined by combining the task attribute information of different dimensions, the weight can be reasonably allocated to each task, and the resources are reasonably utilized. Moreover, the allocation mode can be automatically implemented without manual intervention, the problems of frequent restart, expansion and contraction of the system are avoided, and the system efficiency is improved.
Example two
Fig. 2 shows a flowchart of a resource allocation method according to a second embodiment of the present invention. In this embodiment, a resource allocation process in a virtual machine system is described as an example, but the method in this embodiment can be applied to systems other than the virtual machine system. The virtual host is a network server with a certain disk space, and a user can rent the space to place a site and an application component for the user and provide necessary data storage and transmission functions. The virtual host technology is a technology which is adopted by an internet server and saves the hardware cost of the server, is mainly applied to HTTP (Hypertext Transfer Protocol) service, logically divides a certain item or all service contents of one server into a plurality of service units, and represents the service units as a plurality of servers, thereby fully utilizing the hardware resources of the servers. The virtual host uses special software and hardware technology to divide a real physical server host into a plurality of logical storage units. Each logical unit has no physical entities, but each logical unit can work on the network like a real physical host, with individual IP addresses (or shared IP addresses), independent domain names, and full Internet server (supporting WWW, FTP, E-mail, etc.) functionality. The mainstream virtual machine technologies at present are VMWare, Citrix, Microsoft, etc. The key technology of the virtual host is that different server programs opened for a plurality of users run on the same hardware and the same operating system without interference. Each user has a part of his own system resources (IP address, document storage space, memory, CPU, etc.). The virtual machines are completely independent, and each virtual machine and a single host are completely identical in appearance to the outside. Such virtualized logical hosts are referred to visually as "virtual hosts". The VMWare virtual machine software is a 'virtual PC' software, and can simultaneously run two or more Windows, DOS and LINUX systems on one machine. VMWare employs a completely different concept compared to "multi-boot" systems. The multi-start system can only operate one system at a time, and a machine needs to be restarted when the system is switched. Therefore, the resource types and resource division in the virtual host system are more complex, and therefore, the embodiment can provide convenience for the resource allocation process of the virtual host system. As shown in fig. 2, the method includes:
Step S200: the method comprises the steps of determining multiple influence factors related to resource allocation in advance, and setting task attribute information of multiple dimensions according to the multiple influence factors.
The multi-dimension task attribute information is used for describing resource allocation tasks from different dimensions, and the task attribute information of each dimension has preset influence on resource allocation. Specifically, the task attribute information of the multiple dimensions may be in a parallel relationship or a hierarchical relationship, for example, each dimension in the task attribute information of the multiple dimensions may be further divided into multiple hierarchies.
In this embodiment, first, the project factors for applying for the virtual resource are standardized and explained, that is: factors related to applying for resources are set forth as task attribute information. Accordingly, when the virtual resources are subsequently applied, the factors related to the resource allocation task provided by each applicant are comparable to each other. In specific implementation, the task attribute information is divided into three dimensions with hierarchical relationship. The first layer is task attribute information of business function dimensionality, and values of the task attribute information specifically comprise a business system, an accounting system and/or a customer service system; the second layer is task attribute information of system type dimensionality, and values of the task attribute information specifically comprise a formal system, a test system, a joint debugging system and/or a temporary system; the third layer is task attribute information of a service name dimension, and the value of the task attribute information may be various specific services, such as a new interface machine service and the like.
In the three layers of task attribute information, the normalization weight vectors corresponding to the first layer and the second layer can be preset and solidified, so that the time consumption of subsequent frequent adjustment is avoided, and the weight determination speed is increased. The normalization weight vector corresponding to the second layer can be dynamically adjusted according to the change condition of the on-line service. Of course, the normalized weight vectors corresponding to the three layers may be all set to be dynamically adjusted, which is not limited in the present invention.
Step S210: and aiming at the task attribute information of each dimension, determining a normalization weight vector corresponding to the task attribute information of the dimension, and storing the normalization weight vector corresponding to the task attribute information of each dimension into a background database.
The normalization weight vector corresponding to the task attribute information of each dimension is used for representing dimension weight values corresponding to various values of the task attribute information of the dimension. Specifically, for the task attribute information of each dimension, determining an attribute element set corresponding to the task attribute information of the dimension; generating a normalization weight vector corresponding to the task attribute information of the dimension according to each attribute element contained in the attribute element set; and storing the normalized weight vector corresponding to the task attribute information of each dimension into a background database. The specific implementation of this step is described in detail below:
First, for task attribute information of each dimension, a set of attribute elements corresponding to the task attribute information of the dimension is determined. The attribute element set of the task attribute information of each dimension is used for storing various possible values of the task attribute information of the corresponding dimension. For example, for the task attribute information as a business function dimension of the first layer, the attribute element set includes at least one of the following attribute elements: business system elements, accounting system elements, IT management and control elements, security management elements, and customer service system elements. For the task attribute information as a system type dimension of the second layer, at least one of the following attribute elements is contained in the attribute element set: a regular application element, a temporary application element, an emergency application element, a formal system element, a test system element, a joint debugging system element, and a temporary system element.
And then, generating a normalized weight vector corresponding to the task attribute information of the dimension according to each attribute element contained in the attribute element set, so that the normalized weight vector corresponding to the task attribute information of each dimension is stored in a background database. Specifically, a comparison result between every two attribute elements in the attribute element set is obtained; generating a comparison matrix corresponding to each attribute element in the attribute element set according to a comparison result between every two attribute elements; carrying out normalization processing on each column in the comparison matrix to obtain a normalization matrix, and carrying out summation processing on each row in the normalization matrix to obtain a comparison weight vector; and carrying out normalization processing on the contrast weight vector to obtain a normalized weight vector. In specific implementation, the method can be realized by a hierarchical analysis matrix algorithm.
For example, in a specific example, task attribute information as a business function dimension of a first layer is taken as an example for explanation. The value of the task attribute information of the service function dimension comprises the following steps: correspondingly, the business system, the account system, and the customer service system … … IT auxiliary system need to perform importance comparison for each two values, and create a comparison matrix as shown in table 1 according to the comparison result:
TABLE 1
Expressed in matrix form as follows:
then, each column of the matrix B is normalized by adding all elements of one column to obtain a column sum, and then dividing each element by the converted column sum, thereby completing normalization, assuming that the obtained normalized matrix is as follows:
and then summing according to rows to obtain a contrast weight vector:
normalizing again to obtain a normalized weight vector:
the weight values of the four attribute elements can be quickly determined through the normalized weight vector.
Similarly, for the task attribute information of the system type dimension of the second layer, a contrast matrix as shown in table 2 may also be constructed:
TABLE 2
A contrast matrix of the form:
and obtaining a normalized weight vector corresponding to the task attribute information of the system type dimension according to the comparison matrix. Therefore, through the steps, the normalization weight vectors corresponding to the task attribute information of each dimension can be obtained respectively and stored in the background database so as to be convenient for inquiring in the resource allocation process.
Step S220: and determining task attribute information of multiple dimensions corresponding to each resource allocation task in the resource allocation queue.
Specifically, each resource allocation task is described by task attribute information of multiple dimensions. The task attribute information may be included as an input parameter in the resource application request. For example, when the resource application client submits a resource application request through the H5 page, the task attribute information may be set according to the received input parameters. Wherein, the input parameters include: the resources correspond to services (business systems, accounting systems, client systems, IT management and control, security management and the like), and resource usage types (regular application, temporary application, emergency application, and the like). Further, the input parameters may further include a resource application condition: CPU, memory, storage, remark information, etc. Correspondingly, after receiving the resource application request, ordering the same services under the existing service and resource usage types, and inserting the resource allocation task corresponding to the resource application request into the resource allocation queue, for example, assuming that the application is of a resource suitable for a business system \ a conventional application \ an internet of things interface service (new interface machine), the service of the resource application request needs to be compared with each service under the business system \ the conventional application, and the internet of things interface service (new interface machine) is brought into the resource allocation queue. In the above example, the task attribute information of multiple dimensions corresponding to the resource allocation task specifically includes: task attribute information of service function dimension is taken as a business system; task attribute information of a system type dimension is valued as conventional application; and the task attribute information of the service name dimension is valued as a new interface machine.
Step S230: and respectively inquiring a normalization weight vector corresponding to the task attribute information of the dimension stored in a background database aiming at the task attribute information of each dimension contained in the task attribute information of the plurality of dimensions, and determining a dimension weight value corresponding to the task attribute information of the dimension according to an inquiry result.
For example, still taking the above example as an example, since the value of the task attribute information of the business function dimension is the business system, correspondingly, the weight value corresponding to the attribute element of the business system is obtained from the corresponding normalized weight vector, and is used as the dimension weight value corresponding to the task attribute information of the business function dimension, which is also called the business function dimension weight value. Because the value of the task attribute information of the system type dimension is conventional application, correspondingly, a weight value corresponding to the attribute element of the conventional application is obtained from the corresponding normalized weight vector and is used as a dimension weight value corresponding to the task attribute information of the system type dimension, also called the system type dimension weight value. Because the value of the task attribute information of the service name dimension is the new interface machine, correspondingly, the weight value corresponding to the attribute element of the new interface machine is obtained from the corresponding normalized weight vector and is used as the dimension weight value corresponding to the task attribute information of the service name dimension, also called the service name dimension weight value. Therefore, the dimension weight values corresponding to the dimensions can be respectively determined through the step.
Step S240: and determining the task weight value of the resource allocation task according to the dimension weight value corresponding to the task attribute information of each dimension contained in the task attribute information of the multiple dimensions.
Specifically, the product of each dimension weight value corresponding to each dimension of task attribute information contained in the multi-dimension task attribute information is calculated, and the task weight value of the resource allocation task is determined according to the calculation result. The method can comprehensively determine the task weight value of one task by integrating the dimension weight values of different dimensions, so that the weight setting of the task is more reasonable.
Step S250: and determining resource type information corresponding to the resource allocation task, and determining a resource type weight value of the resource type information corresponding to the resource allocation task according to a resource weight vector corresponding to each resource type information preset in a background database.
The inventor finds that the importance degree and the scarcity degree of different types of resources are different in the process of implementing the invention, so that when the resources are allocated, the resources are allocated according to the importance degree, the scarcity degree and other factors of the types of the resources to be allocated, and accordingly, in the embodiment, a resource weight vector corresponding to each type of resource information is preset in a background database in advance so as to determine the weight values of the types of the resources corresponding to each type of the resources. Specifically, the resource type information includes: CPU, memory, hard disk and other information. Correspondingly, the resource weight vector is used for storing the weight proportion among various resource information such as a CPU, a memory, a hard disk and the like. In a specific implementation, the resource weight vector may be generated by referring to the generation method of the normalized weight vector. For example, the comparison result between each two of the three types of CPU, memory, and hard disk is evaluated first to generate a comparison matrix, and then the resource weight vector is obtained according to the comparison matrix. The comparison result between every two types of resources can be determined according to the occupation data of each type of resource, for example, statistical results such as the total amount of resources, the occupation amount, the remaining amount, the occupation ratio and the like, and specifically, the occupation data of each type of resource can be acquired once every preset period, so that the comparison result between each type of resource is set according to the occupation data of the period and/or N history periods (N is a natural number greater than 1), and the value of the resource weight vector is determined. For example, assuming that the CPU resources are more abundant than the memory resources, the comparison result between the CPU resources and the memory resources may be 3:1, so that the CPU resources are preferentially allocated. Specifically, for the CPU, the memory, and the hard disk, the process of listing each type of resource application in each dimension, such as (1C,2C, 4C), (128M, 256M ….2G), (200G, 800G … 1T), finally forms a 2-element structure similar to a multi-way tree.
Optionally, in this embodiment, in order to make the resource allocation result more reasonable, the following operations may be further performed: determining a type adjustment coefficient corresponding to each resource type information according to the resource occupation data corresponding to each resource type information which is obtained dynamically; and according to the type adjustment coefficient, adjusting the weight value of the resource type information corresponding to the resource allocation task. The resource occupation data corresponding to each resource type information can be dynamically acquired every preset time interval, so that a type adjustment coefficient corresponding to each resource type information is determined: the larger the resource occupation amount is, the less the remaining available resources are, and the lower the type adjustment coefficient is, thereby enabling the resource allocation to be more practicable. For example, assuming that the resource type corresponding to the resource allocation task is a CPU, if the recent CPU occupancy is large, the type adjustment coefficient of the CPU needs to be reduced, so as to reduce the weight value of the CPU allocation task to prevent the CPU resource from being exhausted.
Step S260: and allocating resources for each resource allocation task in the resource allocation queue according to the task weight value of each resource allocation task and by combining the resource type weight value.
Through the steps, different task weight values can be set for each resource allocation task in the resource allocation queue, accordingly, according to the task weight values of each resource allocation task and in combination with the mode that the resource type weight values allocate resources for each resource allocation task in the resource allocation queue, multiple factors such as the urgency degree and the importance degree of the tasks can be comprehensively considered, and therefore resource allocation is more reasonable.
Specifically, the task weight value and the resource type weight value may be subjected to a preset operation, such as an addition operation, so as to determine whether to allocate a resource to the task according to an operation result. The method can comprehensively consider the task weight value of each resource allocation task and combine the resource type weight value.
Finally, to facilitate an understanding of the present invention, a specific example is given. In this example, a tree structure is first constructed. FIG. 5 illustrates one form of a resource application parse tree. The left branch of the tree is used for determining the normalized weight vector of the task attribute information of each dimension, and the right branch of the tree is used for determining the resource weight vector. The left branch is further divided into three levels, namely a service type level, an application type level and a specific application level. The dimension weight value of each level is determined by a corresponding contrast matrix. For example, the dimension weight value of the service type level is determined by a B matrix, the dimension weight value of the application type level is represented by a C matrix, and the dimension weight value of a specific application level is represented by an a matrix. And one value in each comparison matrix represents a comparison result between two attribute elements corresponding to the value. The comparison result can be determined according to the importance degree between the attribute elements and the service historical data. Preferably, in order to ensure that the scheme can be automatically implemented, historical operating data corresponding to each service and each application can be obtained according to a system log, monitoring data and the like, the historical operating data comprises various data such as online time, the number of active users, resource occupation data and the like of each type of service or application, and a comparison result between every two attribute elements can be determined according to the historical operating data. For example, the comparison result between the traffic type with a large number of historically active users and the traffic type with a small number of historically active users is necessarily greater than 1. Similarly, the right branch corresponds to a resource type, and the weight value of each resource type is determined by a resource weight vector. Specifically, the resource weight vector may also be determined by a comparison matrix constructed from comparison results between the respective types of resources. When the comparison result between every two resource types is determined, historical occupation data corresponding to various resources can be obtained by combining the system logs, the monitoring data and the like, and the historical occupation data comprises the occupation amount of each resource and the occupation amount of various services or applications for various resources. For example, for the CPU type, not only the total occupied amount of the CPU but also the number of CPUs occupied by various types of services respectively are counted, and a comparison result between each two types of resources can be determined according to historical occupied data. Specifically, the weight result value of a task can be determined by the following formula: b C A + lambda D A; wherein, B represents a contrast matrix corresponding to the service type, C represents a contrast matrix corresponding to the application type, A represents a contrast matrix corresponding to the specific service, D represents a contrast matrix corresponding to the resource type, and λ represents a type adjustment coefficient of the resource type. The core of the above formula is: and the total task weight is the service type weight and the lambda resource occupation weight. Wherein, if the existing resources are in shortage, the lambda needs to be increased; if the resources are sufficient, λ drops. The same comparison results of various resource types, such as CPU, memory and hard disk, can be dynamically adjusted, and if the current hard disk is in tension, the contrast coefficient of the hard disk in the matrix is increased. And finally, after the total weight of the tasks is calculated, distributing the virtual resources according to the current residual resource condition, and carrying out on-time swap-out processing on the services which occupy the resources and have low weight. This approach enables dynamic resource allocation using a hierarchical analysis algorithm.
In summary, the method of the invention calculates the resource priority and dynamically allocates the resource through the hierarchical matrix, and adds the occupation analysis of the existing resource in the hierarchical factors, thereby not only improving the objectivity of the resource allocation queuing standard, but also avoiding the resource adjustment condition of repeatedly changing in and out. The hierarchical analysis matrix periodically analyzes the existing resource use condition, collects the background resource adjustment condition and calculates the resource weight vector. This approach has at least the following advantages: firstly, resources are dynamically allocated by utilizing a hierarchical analysis matrix, the matrix not only evaluates the newly applied resources, but also evaluates the existing resources, and a complete matrix weight analysis system is established. Secondly, the service priority and the resource condition are subjected to bidirectional evaluation, and the resource condition matrix is applied to adjust the resource distribution condition through the resource weight coefficient instead of being divided according to the service emergency priority, so that the healthy operation of the system is ensured. In addition, the mode avoids the generation of human intervention errors.
EXAMPLE III
Fig. 3 is a schematic structural diagram of a resource allocation apparatus according to a third embodiment of the present invention, where the apparatus includes:
A task attribute determining module 31, adapted to determine, for each resource allocation task in the resource allocation queue, multi-dimensional task attribute information corresponding to the resource allocation task;
the dimension weight determining module 32 is adapted to query the normalized weight vector corresponding to the task attribute information of each dimension stored in the background database aiming at the task attribute information of each dimension contained in the task attribute information of the plurality of dimensions, and determine a dimension weight value corresponding to the task attribute information of the dimension according to a query result;
the task weight determining module 33 is adapted to determine a task weight value of the resource allocation task according to a dimension weight value corresponding to each dimension of task attribute information included in the multi-dimension task attribute information;
and the allocating module 34 is adapted to allocate resources to each resource allocation task in the resource allocation queue according to the task weight value of each resource allocation task.
Optionally, the apparatus further comprises:
the storage module is suitable for determining an attribute element set corresponding to the task attribute information of each dimension aiming at the task attribute information of the dimension; generating a normalization weight vector corresponding to the task attribute information of the dimension according to each attribute element contained in the attribute element set; and storing the normalized weight vector corresponding to the task attribute information of each dimension into the background database.
Optionally, the storage module is specifically adapted to:
obtaining a comparison result between every two attribute elements in the attribute element set;
generating a comparison matrix corresponding to each attribute element in the attribute element set according to the comparison result between every two attribute elements;
carrying out normalization processing on each column in the contrast matrix to obtain a normalization matrix, and carrying out summation processing on each row in the normalization matrix to obtain a contrast weight vector;
and carrying out normalization processing on the contrast weight vector to obtain the normalization weight vector.
Optionally, the task attribute information of the multiple dimensions corresponding to the resource allocation task includes at least one of the following:
task attribute information of a service function dimension, task attribute information of a system type dimension, and/or task attribute information of a service name dimension;
wherein, the attribute element set corresponding to the task attribute information of the service function dimension includes at least one of the following attribute elements: a business system element, an accounting system element, and/or a customer service system element; the attribute element set corresponding to the task attribute information of the system type dimension comprises at least one of the following attribute elements: formal system elements, test system elements, joint debugging system elements, and/or temporary system elements.
Optionally, the allocation module is further adapted to:
determining resource type information corresponding to the resource allocation task, and determining a resource type weight value of the resource type information corresponding to the resource allocation task according to a resource weight vector corresponding to each resource type information preset in the background database; and distributing resources for each resource distribution task in the resource distribution queue by combining the resource type weight value.
Optionally, the allocation module is specifically adapted to:
determining a type adjustment coefficient corresponding to each resource type information according to the resource occupation data corresponding to each resource type information which is obtained dynamically;
and adjusting the weight value of the resource type information corresponding to the resource allocation task according to the type adjustment coefficient.
Optionally, the apparatus is applied to a virtual machine system, and the resource type information includes: CPU, memory, hard disk;
and, the task weight determination module is specifically adapted to:
and calculating the product of each dimension weight value corresponding to each dimension of task attribute information contained in the multi-dimension task attribute information, and determining the task weight value of the resource allocation task according to the calculation result.
The specific structure and operation principle of each module described above may refer to the description of the corresponding part in the method embodiment, and are not described herein again.
Example four
An embodiment of the present application provides a non-volatile computer storage medium, where the computer storage medium stores at least one executable instruction, and the computer executable instruction may execute the resource allocation method in any method embodiment described above. The executable instructions may be specifically configured to cause a processor to perform respective operations corresponding to the above-described method embodiments.
EXAMPLE five
Fig. 4 is a schematic structural diagram of an electronic device according to a fifth embodiment of the present invention, and the specific embodiment of the present invention does not limit the specific implementation of the electronic device.
As shown in fig. 4, the electronic device may include: a processor (processor)402, a Communications Interface 406, a memory 404, and a Communications bus 408.
Wherein:
the processor 402, communication interface 406, and memory 404 communicate with each other via a communication bus 408.
A communication interface 406 for communicating with network elements of other devices, such as clients or other servers.
The processor 402 is configured to execute the program 410, and may specifically perform relevant steps in the foregoing resource allocation method embodiment.
In particular, program 410 may include program code comprising computer operating instructions.
The processor 402 may be a central processing unit CPU, or an application specific Integrated circuit asic, or one or more Integrated circuits configured to implement an embodiment of the present invention. The electronic device comprises one or more processors, which can be the same type of processor, such as one or more CPUs; or may be different types of processors such as one or more CPUs and one or more ASICs.
And a memory 404 for storing a program 410. The memory 404 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
The program 410 may specifically be configured to enable the processor 402 to perform the respective operations in the above-described method embodiments.
The algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. Moreover, the present invention is not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components in a voice input information based lottery system according to embodiments of the present invention. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
Claims (10)
1. A method of resource allocation, comprising:
determining task attribute information of multiple dimensions corresponding to each resource allocation task in a resource allocation queue;
respectively inquiring a normalization weight vector corresponding to the task attribute information of each dimension in the background database aiming at the task attribute information of each dimension contained in the task attribute information of the plurality of dimensions, and determining a dimension weight value corresponding to the task attribute information of each dimension according to an inquiry result;
Determining a task weight value of the resource allocation task according to a dimension weight value corresponding to each dimension of task attribute information contained in the multi-dimension task attribute information;
and allocating resources for each resource allocation task in the resource allocation queue according to the task weight value of each resource allocation task.
2. The method of claim 1, wherein prior to performing the method, further comprising:
determining an attribute element set corresponding to the task attribute information of each dimension aiming at the task attribute information of each dimension;
generating a normalization weight vector corresponding to the task attribute information of the dimension according to each attribute element contained in the attribute element set;
and storing the normalized weight vector corresponding to the task attribute information of each dimension into the background database.
3. The method according to claim 2, wherein the generating a normalized weight vector corresponding to the task attribute information of the dimension according to each attribute element included in the attribute element set comprises:
obtaining a comparison result between every two attribute elements in the attribute element set;
generating a comparison matrix corresponding to each attribute element in the attribute element set according to the comparison result between every two attribute elements;
Carrying out normalization processing on each column in the contrast matrix to obtain a normalization matrix, and carrying out summation processing on each row in the normalization matrix to obtain a contrast weight vector;
and carrying out normalization processing on the contrast weight vector to obtain the normalization weight vector.
4. The method of claim 2 or 3, wherein the plurality of dimensions of task attribute information corresponding to the resource allocation task include at least one of:
task attribute information of a service function dimension, task attribute information of a system type dimension, and/or task attribute information of a service name dimension;
wherein, the attribute element set corresponding to the task attribute information of the service function dimension includes at least one of the following attribute elements: a business system element, an accounting system element, and/or a customer service system element; the attribute element set corresponding to the task attribute information of the system type dimension comprises at least one of the following attribute elements: formal system elements, test system elements, joint debugging system elements, and/or temporary system elements.
5. The method according to any one of claims 1 to 3, wherein after determining the task weight value of the resource allocation task according to the dimension weight value corresponding to the task attribute information of each dimension included in the task attribute information of the plurality of dimensions, the method further includes:
Determining resource type information corresponding to the resource allocation task, and determining a resource type weight value of the resource type information corresponding to the resource allocation task according to a resource weight vector corresponding to each resource type information preset in the background database;
the allocating resources for each resource allocation task in the resource allocation queue according to the task weight value of each resource allocation task includes:
and distributing resources for each resource distribution task in the resource distribution queue by combining the resource type weight value.
6. The method of claim 5, wherein the determining, according to a resource weight vector preset in the background database and corresponding to each resource type information, a resource type weight value of the resource type information corresponding to the resource allocation task comprises:
determining a type adjustment coefficient corresponding to each resource type information according to the resource occupation data corresponding to each resource type information which is obtained dynamically;
and adjusting the weight value of the resource type information corresponding to the resource allocation task according to the type adjustment coefficient.
7. The method according to any one of claims 1-3, wherein the method is applied to a virtual machine system, and the resource type information includes: CPU, memory, hard disk;
And, the determining, according to each dimension weight value corresponding to each dimension of task attribute information included in the multi-dimension task attribute information, a task weight value of the resource allocation task includes:
and calculating the product of each dimension weight value corresponding to each dimension of task attribute information contained in the multi-dimension task attribute information, and determining the task weight value of the resource allocation task according to the calculation result.
8. A resource allocation apparatus, comprising:
the task attribute determining module is suitable for determining task attribute information of multiple dimensions corresponding to each resource allocation task in the resource allocation queue;
the dimension weight determining module is suitable for respectively inquiring the normalization weight vector which is stored in the background database and corresponds to the task attribute information of each dimension in the task attribute information of the plurality of dimensions, and determining the dimension weight value corresponding to the task attribute information of the dimension according to the inquiry result;
the task weight determining module is suitable for determining a task weight value of the resource allocation task according to a dimension weight value corresponding to each dimension of task attribute information contained in the multi-dimension task attribute information;
And the allocation module is suitable for allocating resources for each resource allocation task in the resource allocation queue according to the task weight value of each resource allocation task.
9. An electronic device, comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction causes the processor to execute the operation corresponding to the resource allocation method according to any one of claims 1-7.
10. A computer storage medium having stored therein at least one executable instruction for causing a processor to perform operations corresponding to the resource allocation method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910335161.9A CN111858014A (en) | 2019-04-24 | 2019-04-24 | Resource allocation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910335161.9A CN111858014A (en) | 2019-04-24 | 2019-04-24 | Resource allocation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111858014A true CN111858014A (en) | 2020-10-30 |
Family
ID=72952260
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910335161.9A Pending CN111858014A (en) | 2019-04-24 | 2019-04-24 | Resource allocation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111858014A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112689087A (en) * | 2020-12-14 | 2021-04-20 | 浙江大华技术股份有限公司 | Control authority distribution method and device of cloud deck, electronic device and storage medium |
| CN112817757A (en) * | 2021-01-25 | 2021-05-18 | 卓望数码技术（深圳）有限公司 | Method and device for flexibly allocating pre-adjusted resources, electronic equipment and storage medium |
| CN115987750A (en) * | 2022-11-22 | 2023-04-18 | 西安鹏迪信息科技有限公司 | Limited resource dynamic allocation method based on layering |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103634330A (en) * | 2012-08-20 | 2014-03-12 | 曙光信息产业(北京)有限公司 | Automatic resource distribution method in cloud calculation environment |
| CN104168318A (en) * | 2014-08-18 | 2014-11-26 | 中国联合网络通信集团有限公司 | Resource service system and resource distribution method thereof |
| CN105491085A (en) * | 2014-09-16 | 2016-04-13 | 阿里巴巴集团控股有限公司 | Method and device for on-line requesting for queuing |
| CN106471773A (en) * | 2014-06-30 | 2017-03-01 | 微软技术许可有限责任公司 | The distribution of integrated form global resource and load balance |
| CN106658727A (en) * | 2016-04-28 | 2017-05-10 | 电子科技大学 | Business importance determining and resource allocating method based on multiple correlated attributes |
| US20170249574A1 (en) * | 2016-02-26 | 2017-08-31 | A2PS Consulting and Software LLC | System for monitoring of workflows capable of automatic task allocation and monitoring of resources |
| CN107135135A (en) * | 2017-05-02 | 2017-09-05 | 北京邮电大学 | A kind of mapping method of virtual network and device sorted based on bottom layer node |
| CN107704320A (en) * | 2017-05-12 | 2018-02-16 | 贵州白山云科技有限公司 | The method for allocating tasks and system of a kind of distributed system |
| CN108762907A (en) * | 2018-05-31 | 2018-11-06 | 口口相传(北京)网络技术有限公司 | Task processing method based on multiple client and system |
-
2019
- 2019-04-24 CN CN201910335161.9A patent/CN111858014A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103634330A (en) * | 2012-08-20 | 2014-03-12 | 曙光信息产业(北京)有限公司 | Automatic resource distribution method in cloud calculation environment |
| CN106471773A (en) * | 2014-06-30 | 2017-03-01 | 微软技术许可有限责任公司 | The distribution of integrated form global resource and load balance |
| CN104168318A (en) * | 2014-08-18 | 2014-11-26 | 中国联合网络通信集团有限公司 | Resource service system and resource distribution method thereof |
| CN105491085A (en) * | 2014-09-16 | 2016-04-13 | 阿里巴巴集团控股有限公司 | Method and device for on-line requesting for queuing |
| US20170249574A1 (en) * | 2016-02-26 | 2017-08-31 | A2PS Consulting and Software LLC | System for monitoring of workflows capable of automatic task allocation and monitoring of resources |
| CN106658727A (en) * | 2016-04-28 | 2017-05-10 | 电子科技大学 | Business importance determining and resource allocating method based on multiple correlated attributes |
| CN107135135A (en) * | 2017-05-02 | 2017-09-05 | 北京邮电大学 | A kind of mapping method of virtual network and device sorted based on bottom layer node |
| CN107704320A (en) * | 2017-05-12 | 2018-02-16 | 贵州白山云科技有限公司 | The method for allocating tasks and system of a kind of distributed system |
| CN108762907A (en) * | 2018-05-31 | 2018-11-06 | 口口相传(北京)网络技术有限公司 | Task processing method based on multiple client and system |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112689087A (en) * | 2020-12-14 | 2021-04-20 | 浙江大华技术股份有限公司 | Control authority distribution method and device of cloud deck, electronic device and storage medium |
| CN112689087B (en) * | 2020-12-14 | 2022-03-01 | 浙江大华技术股份有限公司 | Control authority distribution method and device of cloud deck, electronic device and storage medium |
| CN112817757A (en) * | 2021-01-25 | 2021-05-18 | 卓望数码技术（深圳）有限公司 | Method and device for flexibly allocating pre-adjusted resources, electronic equipment and storage medium |
| CN112817757B (en) * | 2021-01-25 | 2024-05-24 | 卓望数码技术（深圳）有限公司 | Pre-adjusted resource elastic allocation method and device, electronic equipment and storage medium |
| CN115987750A (en) * | 2022-11-22 | 2023-04-18 | 西安鹏迪信息科技有限公司 | Limited resource dynamic allocation method based on layering |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200364608A1 (en) | Communicating in a federated learning environment | |
| EP3073374B1 (en) | Thread creation method, service request processing method and related device | |
| US6321265B1 (en) | System and method for enforcing politeness while scheduling downloads in a web crawler | |
| US7784053B2 (en) | Management of virtual machines to utilize shared resources | |
| EP2255286B1 (en) | Routing workloads and method thereof | |
| US8544005B2 (en) | Autonomic method, system and program product for managing processes | |
| US9250886B2 (en) | Optimizing provisioning workflows in cloud computing | |
| US20050081208A1 (en) | Framework for pluggable schedulers | |
| JP5121936B2 (en) | RESOURCE ALLOCATION DEVICE, RESOURCE ALLOCATION PROGRAM, RECORDING MEDIUM, AND RESOURCE ALLOCATION METHOD | |
| US11513860B2 (en) | Serverless function colocation with storage pools | |
| CN111858014A (en) | Resource allocation method and device | |
| Yousif et al. | Clustering cloud workload traces to improve the performance of cloud data centers | |
| US20060248372A1 (en) | Intelligent resource provisioning based on on-demand weight calculation | |
| CN111930493A (en) | NodeManager state management method and device in cluster and computing equipment | |
| US8612597B2 (en) | Computing scheduling using resource lend and borrow | |
| CN107204998B (en) | Method and device for processing data | |
| CN113315825A (en) | Distributed request processing method, device, equipment and storage medium | |
| US8290995B1 (en) | Model and method of an N-tier quality-of-service (QOS) | |
| CN108897858B (en) | Distributed cluster index fragmentation evaluation method and device and electronic equipment | |
| CN115640113A (en) | Multi-plane flexible scheduling method | |
| CN113504988A (en) | Control method, system, medium and device for system computing power resource scheduling | |
| CN117076133A (en) | Cloud game platform heterogeneous resource allocation method, computer device and storage medium | |
| CN115904729A (en) | Method, device, system, equipment and medium for connection allocation | |
| Yeh et al. | Realizing integrated prioritized service in the Hadoop cloud system | |
| Thai et al. | Algorithms for optimising heterogeneous Cloud virtual machine clusters |
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: 20201030 |