CN113590342B - Resource allocation method and system in cloud computing system - Google Patents

Resource allocation method and system in cloud computing system Download PDF

Info

Publication number
CN113590342B
CN113590342B CN202111148022.9A CN202111148022A CN113590342B CN 113590342 B CN113590342 B CN 113590342B CN 202111148022 A CN202111148022 A CN 202111148022A CN 113590342 B CN113590342 B CN 113590342B
Authority
CN
China
Prior art keywords
virtual server
virtual
server
index
selection
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.)
Active
Application number
CN202111148022.9A
Other languages
Chinese (zh)
Other versions
CN113590342A (en
Inventor
石俊杰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ruizhi Technology Group Co ltd
Original Assignee
Ruizhi Technology Group Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Ruizhi Technology Group Co ltd filed Critical Ruizhi Technology Group Co ltd
Priority to CN202111148022.9A priority Critical patent/CN113590342B/en
Publication of CN113590342A publication Critical patent/CN113590342A/en
Application granted granted Critical
Publication of CN113590342B publication Critical patent/CN113590342B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5061—Partitioning or combining of resources
    • G06F9/5072—Grid computing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5061—Partitioning or combining of resources
    • G06F9/5077—Logical partitioning of resources; Management or configuration of virtualized resources

Abstract

The application relates to the technical field of cloud computing, in particular to a resource allocation method and system in a cloud computing system, which comprises the following steps: acquiring a characteristic parameter of an access request; calculating a selection index for selecting the virtual server according to the obtained characteristic parameters; taking a virtual server meeting the selection index requirement in the virtual servers as a target to be selected; obtaining an optimal virtual server from the target to be selected by considering the residual life value of the physical server; and processing the access request through the optimal virtual server. The method and the device can reasonably distribute the resources of the cloud computing system, and ensure the performance of the cloud computing system.

Description

Resource allocation method and system in cloud computing system
Technical Field
The present application relates to the field of cloud computing technologies, and in particular, to a method and a system for resource allocation in a cloud computing system.
Background
More and more applications are now migrating to the "cloud" such as various "cloud disk" storage that is exposed in life. In fact, "clouds" are not new, have been around for over 10 years, and are expanding into all areas. It is anticipated that in the next 10 years, almost all applications will be deployed to the cloud to provide a wide variety of services through the "cloud".
Therefore, as more and more applications are deployed to a remote location, the demand for resources in the cloud computing system will be higher and higher, and how to reasonably allocate the resources of the cloud computing system to ensure the performance of the cloud computing system is a technical problem that needs to be solved urgently by those skilled in the art at present.
Disclosure of Invention
The application provides a resource allocation method and system in a cloud computing system, which are used for reasonably allocating resources of the cloud computing system and ensuring the performance of the cloud computing system.
In order to solve the technical problem, the application provides the following technical scheme:
a resource allocation method in a cloud computing system comprises the following steps: step S110, acquiring characteristic parameters of the access request; step S120, calculating a selection index for selecting the virtual server according to the obtained characteristic parameters; step S130, taking a virtual server meeting the selection index requirement in the virtual servers as a target to be selected; step S140, obtaining an optimal virtual server from the target to be selected by considering the residual life value of the physical server; and step S150, processing the access request through the optimal virtual server.
The resource allocation method in the cloud computing system as described above, wherein preferably, the feature weight corresponding to the feature parameter is obtained according to the feature parameter; and obtaining a selection index for selecting the virtual server according to the obtained characteristic parameters and the characteristic weights corresponding to the characteristic parameters.
The resource allocation method in the cloud computing system as described above, wherein preferably, the resource remaining indicators of all the virtual servers belonging to the cloud computing data center are calculated; and comparing the obtained selection index with the resource residual index of each virtual server to select the virtual server meeting the selection index requirement, and taking the selected virtual server as a target to be selected.
The resource allocation method in the cloud computing system as described above, preferably, in a case that all the virtual servers do not meet the requirement of the selection index, one or more new virtual servers are created, or some virtual servers are destroyed first, then one or more new virtual servers are created, and then the computing capability of one or more original virtual servers is adjusted so as to meet the requirement of the selection index.
The resource allocation method in the cloud computing system as described above, wherein preferably, the remaining lifetime value of the physical server includes: the residual life value of the memory, the residual life value of the hard disk and the residual life value of the CPU.
A resource allocation system in a cloud computing system, comprising: the system comprises a characteristic acquisition module, an index calculation module, a virtual server selection module and an optimal virtual server confirmation module; the characteristic acquisition module acquires characteristic parameters of the access request; the index calculation module calculates a selection index for selecting the virtual server according to the obtained characteristic parameters; the virtual server selection module takes a virtual server meeting the selection index requirement in the virtual servers as a target to be selected; and the optimal virtual server confirmation module considers the residual life value of the physical server which depends on the optimal virtual server, obtains the optimal virtual server from the target to be selected, and processes the access request through the optimal virtual server.
In the resource allocation system in the cloud computing system, preferably, the index calculation module obtains a feature weight corresponding to the feature parameter according to the feature parameter, and obtains a selection index for selecting the virtual server according to the obtained feature parameter and the feature weight corresponding to the feature parameter.
In the resource allocation system in the cloud computing system, preferably, the virtual server selection module calculates resource remaining indicators of all virtual servers belonging to the cloud computing data center, compares the obtained selection indicator with the resource remaining indicator of each virtual server to select a virtual server meeting the selection indicator requirement, and uses the selected virtual server as the target to be selected.
The resource allocation system in the cloud computing system as described above, preferably, in a case that all the virtual servers do not meet the requirement of the selection index, the virtual server selection module creates one or more new virtual servers, or the virtual server selection module destroys some virtual servers first, and then creates one or more new virtual servers, or the virtual server selection module adjusts the computing capability of one or more original virtual servers, so that the computing capability of the one or more original virtual servers meets the requirement of the selection index.
The resource allocation system in the cloud computing system as described above, wherein preferably, the remaining lifetime value of the physical server includes: the residual life value of the memory, the residual life value of the hard disk and the residual life value of the CPU.
In order to solve the technical problem, according to the resource allocation method and system in the cloud computing system provided by the application, under the condition that the requirement of the selection index is met, the residual life value of the physical server on which the virtual server in the cloud computing system depends is considered, so that the physical resource of the physical server can be guaranteed to be utilized in a balanced manner, and only under the condition that the requirement of the selection index is not met, the virtual server in the cloud computing system is created, destroyed or adjusted, so that the change frequency of the virtual server is reduced, and the performance of the cloud computing system is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present invention, and other drawings can be obtained by those skilled in the art according to the drawings.
Fig. 1 is a flowchart of a resource allocation method in a cloud computing system according to an embodiment of the present application;
fig. 2 is a schematic diagram of a resource allocation system in a cloud computing system according to an embodiment of the present application.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative only and should not be construed as limiting the invention.
Example one
As shown in fig. 1, the present application provides a resource allocation method in a cloud computing system, including the following steps:
step S110, acquiring characteristic parameters of the access request;
the server of the cloud computing data center comprises a plurality of physical servers and a plurality of virtual servers erected on the physical servers, and in the application, physical resources (such as a memory, a hard disk space and a CPU) of the physical servers are expected to be utilized in a balanced manner, and the virtual servers erected on the physical servers are expected to reduce expenses as much as possible on the premise of meeting computing requirements, namely, the dynamic creation or destruction frequency of the virtual servers is reduced as much as possible, and the frequency of adjusting the computing capacity of the virtual servers is reduced as much as possible.
Receiving an access request sent by a terminal, and acquiring characteristic parameters of the access request, wherein the characteristic parameters comprise: category parameters, required memory parameters, required hard disk parameters, required CPU parameters, and the like. The feature parameter sets are combined to form the feature parameter set
Figure 833187DEST_PATH_IMAGE001
Wherein, in the step (A),
Figure 343803DEST_PATH_IMAGE002
is the 1 st characteristic parameter,
Figure 123540DEST_PATH_IMAGE003
Is the 2 nd characteristic parameter,
Figure 253170DEST_PATH_IMAGE004
Is the 3 rd characteristic parameter,
Figure 801963DEST_PATH_IMAGE005
Is as follows
Figure 358847DEST_PATH_IMAGE006
The characteristic parameters of the first and second groups are,
Figure 235667DEST_PATH_IMAGE006
is the number of elements in the set. For example:
Figure 168988DEST_PATH_IMAGE002
for category parameters (category parameters may be browsing web pages, playing multimedia, executing program files, etc.)
Figure 837866DEST_PATH_IMAGE003
For the required memory parameters,
Figure 565651DEST_PATH_IMAGE004
The required hard disk parameters,
Figure 54401DEST_PATH_IMAGE005
Are the required CPU parameters.
Step S120, calculating a selection index for selecting the virtual server according to the obtained characteristic parameters;
each characteristic parameter has a preset characteristic weight, so that the characteristic weight corresponding to the characteristic parameter is obtained according to the characteristic parameter, and the characteristic weights are collected together to form a characteristic weight set
Figure 650468DEST_PATH_IMAGE007
Wherein, in the step (A),
Figure 173853DEST_PATH_IMAGE008
the feature weight corresponding to the 1 st feature parameter,
Figure 338118DEST_PATH_IMAGE009
the feature weight corresponding to the 2 nd feature parameter,
Figure 314164DEST_PATH_IMAGE010
the feature weight corresponding to the 3 rd feature parameter,
Figure 323709DEST_PATH_IMAGE011
is as follows
Figure 576966DEST_PATH_IMAGE006
The feature weight corresponding to each feature parameter,
Figure 646554DEST_PATH_IMAGE006
is the number of elements in the set.
And obtaining a selection index for selecting the virtual server according to the obtained characteristic parameters and the characteristic weights corresponding to the characteristic parameters. Specifically, a selection index for selecting the virtual server is calculated according to the following formula:
Figure 109896DEST_PATH_IMAGE012
wherein, in the step (A),
Figure 923131DEST_PATH_IMAGE013
for the selection index to be used for selecting a virtual server,
Figure 280163DEST_PATH_IMAGE014
for the first acquired in the access request
Figure 786231DEST_PATH_IMAGE015
The characteristic parameters of the first and second groups are,
Figure 471290DEST_PATH_IMAGE016
is composed of
Figure 353796DEST_PATH_IMAGE014
The weight of the feature of (a) is,
Figure 440700DEST_PATH_IMAGE006
is the number of elements in the set.
Since the category parameters in the feature parameters are considered when calculating the selection index for selecting the virtual server, for example: browsing web pages, playing multimedia, executing program files, etc., so the calculated selection indicators reflect the types related to the access request to some extent, for example: if the user only needs to browse the webpage, the virtual server with less residual total memory amount, total hard disk amount and total CPU amount which can be applied can be selected as the target to be selected according to the calculated selection index so as to carry out the next operation; and if the user wants to watch the video, the virtual server with more residual memory total amount, hard disk total amount and CPU total amount which can be applied can be selected as the target to be selected according to the calculated selection index so as to carry out the next operation.
Step S130, taking a virtual server meeting the selection index requirement in the virtual servers as a target to be selected;
and calculating resource residual indexes of all virtual servers belonging to the cloud computing data center. Specifically, each virtual server has an operation status parameter, a memory occupancy rate, a hard disk occupancy rate, and a CPU utilization rate according to
Figure 990106DEST_PATH_IMAGE017
And calculating to obtain the resource residual index of each virtual server. Wherein the content of the first and second substances,
Figure 162461DEST_PATH_IMAGE018
the resource residual index of the virtual server is obtained;
Figure 317499DEST_PATH_IMAGE019
as a running state parameter, if the virtual server is runningState of then
Figure 790069DEST_PATH_IMAGE019
Is 1, if the virtual server is in a shutdown state, then
Figure 637939DEST_PATH_IMAGE019
Is 0;
Figure 422224DEST_PATH_IMAGE020
in order to achieve the memory usage rate,
Figure 380953DEST_PATH_IMAGE021
the influence factor of the memory occupancy rate on the resource residual index is obtained;
Figure 442450DEST_PATH_IMAGE022
as the occupancy rate of the hard disk,
Figure 461221DEST_PATH_IMAGE023
the hard disk occupancy rate is an influence factor of the resource residual index;
Figure 608169DEST_PATH_IMAGE024
in order to be able to use the CPU utilization,
Figure 245955DEST_PATH_IMAGE025
and the CPU utilization factor is the influence factor of the resource residual index.
And comparing the obtained selection index with the resource residual index of each virtual server to select the virtual server meeting the selection index requirement, and taking the selected virtual server as a target to be selected. In particular, if
Figure 161958DEST_PATH_IMAGE026
The virtual server meets the requirement of the selection index, the virtual server is taken as a target to be selected, and if the virtual server meets the requirement of the selection index, the virtual server is taken as the target to be selected
Figure 86052DEST_PATH_IMAGE027
Then the virtual server does not meet the requirements of the index, and the virtual server is not usedIs listed as a target to be selected, wherein
Figure 985875DEST_PATH_IMAGE028
To adjust the constant, it is an empirical value, taking the value 1.235.
Under the condition that all the virtual servers do not meet the requirement of the selection index, if the cloud computing data center has idle physical server resources (memory resources, hard disk resources, CPU resources and the like) meeting the requirement (namely meeting the requirement of processing the access request), one or more new virtual servers are created, so that the created new virtual servers meet the requirement of the selection index; or if the cloud computing data center does not have idle physical server resources meeting the requirements, destroying some virtual servers, and then creating one or more new virtual servers so as to enable the virtual servers to meet the selection index requirements; or, if the cloud computing data center has a certain amount of idle physical server resources, but the idle physical server resources do not meet the requirement of creating a new virtual server meeting the selection index requirement, adjusting the computing capacity of one or more original virtual servers to enable the computing capacity to meet the selection index requirement. By the virtual servers meeting the selection index requirement, the optimal virtual server can be selected from the virtual servers meeting the selection index to process the access request.
Step S140, obtaining an optimal virtual server from the target to be selected by considering the residual life value of the physical server;
specifically, the physical servers on which the virtual servers depend are of a lifetime, and the remaining lifetime values of the physical servers include: the residual life value of the memory, the residual life value of the hard disk, the residual life value of the CPU and the like. The residual life values of the physical servers depended by the virtual servers are integrated together to form a residual life value set
Figure 145461DEST_PATH_IMAGE029
Wherein, in the step (A),
Figure 447129DEST_PATH_IMAGE030
physical Server 1 stThe remaining life value,
Figure 542124DEST_PATH_IMAGE003
Is the 2 nd remaining life value of the physical server,
Figure 663664DEST_PATH_IMAGE031
Is a physical server
Figure 767886DEST_PATH_IMAGE032
The value of the remaining life of the battery,
Figure 268269DEST_PATH_IMAGE032
is the number of elements in the set. For example:
Figure 65323DEST_PATH_IMAGE030
is the residual life value of the memory of the physical server,
Figure 408580DEST_PATH_IMAGE033
Is the residual life value of the hard disk of the physical server,
Figure 316493DEST_PATH_IMAGE031
Is the remaining life value of the CPU of the physical server.
Obtaining the state value of each virtual server in the target to be selected through the following formula
Figure 61595DEST_PATH_IMAGE034
. Wherein the content of the first and second substances,
Figure 701655DEST_PATH_IMAGE035
the impact of the remaining lifetime value of the physical server on which the virtual server depends on the state value of the virtual server is weighted,
Figure 266629DEST_PATH_IMAGE036
the influence weight of the resource residual index of the virtual server on the state value of the resource residual index is determined,
Figure 978233DEST_PATH_IMAGE037
，
Figure 577841DEST_PATH_IMAGE038
，
Figure 575753DEST_PATH_IMAGE039
can be obtained by utilizing ant colony algorithm or neural network training
Figure 893602DEST_PATH_IMAGE040
And
Figure 143318DEST_PATH_IMAGE041
of course, they can be obtained empirically;
Figure 863012DEST_PATH_IMAGE042
is a physical server
Figure 907191DEST_PATH_IMAGE043
The value of the remaining life of the battery,
Figure 584773DEST_PATH_IMAGE044
is as follows
Figure 372600DEST_PATH_IMAGE043
The difference between the remaining life value and its standard life value.
Step S150, processing the access request through the optimal virtual server;
and after the optimal virtual server is selected, processing the access request through the optimal virtual server, and sending the obtained processing result to the terminal as the response of the access request.
Example two
As shown in fig. 2, the present application further provides a resource allocation system 200 in a cloud computing system, including: a feature acquisition module 210, an index calculation module 220, a virtual server selection module 230, and an optimal virtual server validation module 240.
The feature obtaining module 210 obtains feature parameters of the access request.
The server of the cloud computing data center comprises a plurality of physical servers and a plurality of virtual servers erected on the physical servers, and in the application, physical resources (such as a memory, a hard disk space and a CPU) of the physical servers are expected to be utilized in a balanced manner, and the virtual servers erected on the physical servers are expected to reduce expenses as much as possible on the premise of meeting computing requirements, namely, the dynamic creation or destruction frequency of the virtual servers is reduced as much as possible, and the frequency of adjusting the computing capacity of the virtual servers is reduced as much as possible.
Receiving an access request sent by a terminal, and acquiring characteristic parameters of the access request, wherein the characteristic parameters comprise: category parameters, required memory parameters, required hard disk parameters, required CPU parameters, and the like. The feature parameter sets are combined to form the feature parameter set
Figure 212380DEST_PATH_IMAGE045
Wherein, in the step (A),
Figure 427461DEST_PATH_IMAGE002
is the 1 st characteristic parameter,
Figure 454323DEST_PATH_IMAGE003
Is the 2 nd characteristic parameter,
Figure 170475DEST_PATH_IMAGE004
Is the 3 rd characteristic parameter,
Figure 864762DEST_PATH_IMAGE005
Is as follows
Figure 250744DEST_PATH_IMAGE006
The characteristic parameters of the first and second groups are,
Figure 30481DEST_PATH_IMAGE006
is the number of elements in the set. For example:
Figure 160111DEST_PATH_IMAGE002
as a category parameter (the category parameter may be browsing a web page)Playing multimedia, executing program files, etc.) (see fig.),
Figure 318691DEST_PATH_IMAGE003
For the required memory parameters,
Figure 406732DEST_PATH_IMAGE004
The required hard disk parameters,
Figure 408186DEST_PATH_IMAGE005
Are the required CPU parameters.
The index calculation module 220 calculates a selection index for selecting the virtual server according to the obtained characteristic parameters.
Each characteristic parameter has a preset characteristic weight, so that the characteristic weight corresponding to the characteristic parameter is obtained according to the characteristic parameter, and the characteristic weights are collected together to form a characteristic weight set
Figure 341507DEST_PATH_IMAGE046
Wherein, in the step (A),
Figure 479228DEST_PATH_IMAGE008
the feature weight corresponding to the 1 st feature parameter,
Figure 597225DEST_PATH_IMAGE009
the feature weight corresponding to the 2 nd feature parameter,
Figure 85975DEST_PATH_IMAGE010
the feature weight corresponding to the 3 rd feature parameter,
Figure 557408DEST_PATH_IMAGE011
is as follows
Figure 815214DEST_PATH_IMAGE006
The feature weight corresponding to each feature parameter,
Figure 245058DEST_PATH_IMAGE006
is the number of elements in the set.
And obtaining a selection index for selecting the virtual server according to the obtained characteristic parameters and the characteristic weights corresponding to the characteristic parameters. Specifically, a selection index for selecting the virtual server is calculated according to the following formula:
Figure 830892DEST_PATH_IMAGE047
wherein, in the step (A),
Figure 106015DEST_PATH_IMAGE013
for the selection index to be used for selecting a virtual server,
Figure 483907DEST_PATH_IMAGE014
for the first acquired in the access request
Figure 553494DEST_PATH_IMAGE043
The characteristic parameters of the first and second groups are,
Figure 141470DEST_PATH_IMAGE016
is composed of
Figure 220285DEST_PATH_IMAGE014
The weight of the feature of (a) is,
Figure 452683DEST_PATH_IMAGE006
is the number of elements in the set.
Since the category parameters in the feature parameters are considered when calculating the selection index for selecting the virtual server, for example: browsing web pages, playing multimedia, executing program files, etc., so the calculated selection indicators reflect the types related to the access request to some extent, for example: if the user only needs to browse the webpage, the virtual server with less residual total memory amount, total hard disk amount and total CPU amount which can be applied can be selected as the target to be selected according to the calculated selection index so as to carry out the next operation; and if the user wants to watch the video, the virtual server with more residual memory total amount, hard disk total amount and CPU total amount which can be applied can be selected as the target to be selected according to the calculated selection index so as to carry out the next operation.
The virtual server selection module 230 takes the virtual server satisfying the selection index requirement in the virtual servers as the target to be selected.
And calculating resource residual indexes of all virtual servers belonging to the cloud computing data center. Specifically, each virtual server has an operation status parameter, a memory occupancy rate, a hard disk occupancy rate, and a CPU utilization rate according to
Figure 693171DEST_PATH_IMAGE048
And calculating to obtain the resource residual index of each virtual server. Wherein the content of the first and second substances,
Figure 643810DEST_PATH_IMAGE018
the resource residual index of the virtual server is obtained;
Figure 136102DEST_PATH_IMAGE019
as an operation status parameter, if the virtual server is in an operation status
Figure 488586DEST_PATH_IMAGE019
Is 1, if the virtual server is in a shutdown state, then
Figure 165555DEST_PATH_IMAGE019
Is 0;
Figure 337910DEST_PATH_IMAGE049
in order to achieve the memory usage rate,
Figure 492948DEST_PATH_IMAGE021
the influence factor of the memory occupancy rate on the resource residual index is obtained;
Figure 824573DEST_PATH_IMAGE050
as the occupancy rate of the hard disk,
Figure 672443DEST_PATH_IMAGE023
the hard disk occupancy rate is an influence factor of the resource residual index;
Figure 332094DEST_PATH_IMAGE024
in order to be able to use the CPU utilization,
Figure 290823DEST_PATH_IMAGE051
and the CPU utilization factor is the influence factor of the resource residual index.
And comparing the obtained selection index with the resource residual index of each virtual server to select the virtual server meeting the selection index requirement, and taking the selected virtual server as a target to be selected. In particular, if
Figure 352320DEST_PATH_IMAGE052
If the virtual server meets the requirement of the selection index, the virtual server is taken as the target to be selected, and if the virtual server meets the requirement of the selection index, the virtual server is taken as the target to be selected
Figure 636671DEST_PATH_IMAGE053
If the virtual server does not meet the requirement of the index, the virtual server is not listed as the target to be selected, wherein
Figure 656055DEST_PATH_IMAGE054
To adjust the constant, it is an empirical value, taking the value 1.235.
Under the condition that all the virtual servers do not meet the requirement of the selection index, if the cloud computing data center has idle physical server resources (memory resources, hard disk resources, CPU resources and the like) meeting the requirement (namely meeting the requirement of processing the access request), one or more new virtual servers are created, so that the created new virtual servers meet the requirement of the selection index; or if the cloud computing data center does not have idle physical server resources meeting the requirements, destroying some virtual servers, and then creating one or more new virtual servers so as to enable the virtual servers to meet the selection index requirements; or, if the cloud computing data center has a certain amount of idle physical server resources, but the idle physical server resources do not meet the requirement of creating a new virtual server meeting the selection index requirement, adjusting the computing capacity of one or more original virtual servers to enable the computing capacity to meet the selection index requirement. By the virtual servers meeting the selection index requirement, the optimal virtual server can be selected from the virtual servers meeting the selection index to process the access request.
The optimal virtual server confirmation module 240 obtains an optimal virtual server from the target to be selected in consideration of the remaining lifetime value of the dependent physical server, so as to process the access request through the optimal virtual server.
Specifically, the physical servers on which the virtual servers depend are of a lifetime, and the remaining lifetime values of the physical servers include: the residual life value of the memory, the residual life value of the hard disk, the residual life value of the CPU and the like. The residual life values of the physical servers depended by the virtual servers are integrated together to form a residual life value set
Figure 152895DEST_PATH_IMAGE055
Wherein, in the step (A),
Figure 68899DEST_PATH_IMAGE056
is the 1 st remaining life value of the physical server,
Figure 258572DEST_PATH_IMAGE003
Is the 2 nd remaining life value of the physical server,
Figure 158394DEST_PATH_IMAGE031
Is a physical server
Figure 583560DEST_PATH_IMAGE032
The value of the remaining life of the battery,
Figure 354069DEST_PATH_IMAGE032
is the number of elements in the set. For example:
Figure 714644DEST_PATH_IMAGE030
is the residual life value of the memory of the physical server,
Figure 101763DEST_PATH_IMAGE057
Is the residual life value of the hard disk of the physical server,
Figure 940406DEST_PATH_IMAGE031
Is the remaining life value of the CPU of the physical server.
Obtaining the state value of each virtual server in the target to be selected through the following formula
Figure 706367DEST_PATH_IMAGE058
. Wherein the content of the first and second substances,
Figure 237843DEST_PATH_IMAGE059
the impact of the remaining lifetime value of the physical server on which the virtual server depends on the state value of the virtual server is weighted,
Figure 846679DEST_PATH_IMAGE060
the influence weight of the resource residual index of the virtual server on the state value of the resource residual index is determined,
Figure 754592DEST_PATH_IMAGE061
，
Figure 499694DEST_PATH_IMAGE062
，
Figure 326705DEST_PATH_IMAGE063
can be obtained by utilizing ant colony algorithm or neural network training
Figure 422837DEST_PATH_IMAGE064
And
Figure 603282DEST_PATH_IMAGE065
of course, they can be obtained empirically;
Figure 468470DEST_PATH_IMAGE066
is a physical server
Figure 341748DEST_PATH_IMAGE043
The value of the remaining life of the battery,
Figure 925176DEST_PATH_IMAGE067
is as follows
Figure 784679DEST_PATH_IMAGE043
The difference between the remaining life value and its standard life value.
And after the optimal virtual server is selected, processing the access request through the optimal virtual server, and sending the obtained processing result to the terminal as the response of the access request.
According to the method and the device, under the condition that the requirement of the selection index is met, the residual life value of the physical server on which the virtual server depends in the cloud computing system can be considered, so that the physical resource of the physical server can be guaranteed to be utilized in a balanced mode, and only under the condition that the requirement of the selection index is not met, the virtual server in the cloud computing system can be created, destroyed or adjusted, so that the change frequency of the virtual server is reduced, and the performance of the cloud computing system is improved.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.

Claims (10)

1. A resource allocation method in a cloud computing system is characterized by comprising the following steps:
step S110, acquiring characteristic parameters of the access request;
step S120, calculating a selection index for selecting the virtual server according to the obtained characteristic parameters;
step S130, taking a virtual server meeting the selection index requirement in the virtual servers as a target to be selected;
step S140, obtaining an optimal virtual server from the target to be selected by considering the residual life value of the physical server;
obtaining the state value of each virtual server in the target to be selected through the following formula
Figure 304227DEST_PATH_IMAGE001
；
Wherein the content of the first and second substances,
Figure 211003DEST_PATH_IMAGE002
the impact of the remaining lifetime value of the physical server on which the virtual server depends on the state value of the virtual server is weighted,
Figure 349729DEST_PATH_IMAGE003
the influence weight of the resource residual index of the virtual server on the state value of the resource residual index is determined,
Figure 87878DEST_PATH_IMAGE004
，
Figure 404590DEST_PATH_IMAGE005
，
Figure 798662DEST_PATH_IMAGE006
obtained by ant colony algorithm or neural network training
Figure 226233DEST_PATH_IMAGE007
And
Figure 271418DEST_PATH_IMAGE008
or obtained empirically
Figure 24610DEST_PATH_IMAGE007
And
Figure 702716DEST_PATH_IMAGE008
；
Figure 933977DEST_PATH_IMAGE009
is a physical server
Figure 584402DEST_PATH_IMAGE010
The value of the remaining life of the battery,
Figure 757763DEST_PATH_IMAGE011
is as follows
Figure 860848DEST_PATH_IMAGE010
The difference between each remaining life value and its standard life value;
Figure 895800DEST_PATH_IMAGE012
number of elements in the set of remaining lifetime values;
Figure 400731DEST_PATH_IMAGE013
the resource residual index of the virtual server is obtained;
and step S150, processing the access request through the optimal virtual server.
2. The method according to claim 1, wherein the resource allocation method comprises,
obtaining a feature weight corresponding to the feature parameter according to the feature parameter;
and obtaining a selection index for selecting the virtual server according to the obtained characteristic parameters and the characteristic weights corresponding to the characteristic parameters.
3. The method according to claim 1 or 2, wherein the resource allocation method includes the steps of,
calculating resource residual indexes of all virtual servers belonging to the cloud computing data center;
and comparing the obtained selection index with the resource residual index of each virtual server to select the virtual server meeting the selection index requirement, and taking the selected virtual server as a target to be selected.
4. The method according to claim 3, wherein the resource allocation method is further characterized in that,
under the condition that all the virtual servers do not meet the requirement of the selection index, one or more new virtual servers are created, or some virtual servers are destroyed firstly, then one or more new virtual servers are created, and then the computing capacity of one or more original virtual servers is adjusted to enable the computing capacity to meet the requirement of the selection index.
5. The method according to claim 1 or 2, wherein the remaining life value of the physical server comprises: the residual life value of the memory, the residual life value of the hard disk and the residual life value of the CPU.
6. A resource allocation system in a cloud computing system, comprising: the system comprises a characteristic acquisition module, an index calculation module, a virtual server selection module and an optimal virtual server confirmation module;
the characteristic acquisition module acquires characteristic parameters of the access request;
the index calculation module calculates a selection index for selecting the virtual server according to the obtained characteristic parameters;
the virtual server selection module takes a virtual server meeting the selection index requirement in the virtual servers as a target to be selected;
the optimal virtual server confirmation module considers the residual life value of the physical server which depends on the optimal virtual server and obtains the optimal virtual server from the target to be selected;
obtaining the state value of each virtual server in the target to be selected through the following formula
Figure 292463DEST_PATH_IMAGE014
；
Wherein the content of the first and second substances,
Figure 400621DEST_PATH_IMAGE015
the impact of the remaining lifetime value of the physical server on which the virtual server depends on the state value of the virtual server is weighted,
Figure 973685DEST_PATH_IMAGE016
the influence weight of the resource residual index of the virtual server on the state value of the resource residual index is determined,
Figure 333122DEST_PATH_IMAGE017
，
Figure 599018DEST_PATH_IMAGE018
，
Figure 473434DEST_PATH_IMAGE019
obtained by ant colony algorithm or neural network training
Figure 365035DEST_PATH_IMAGE020
And
Figure 844558DEST_PATH_IMAGE016
or obtained empirically
Figure 281356DEST_PATH_IMAGE020
And
Figure 580750DEST_PATH_IMAGE016
；
Figure 744884DEST_PATH_IMAGE021
is a physical server
Figure 141230DEST_PATH_IMAGE022
The value of the remaining life of the battery,
Figure 748929DEST_PATH_IMAGE023
is as follows
Figure 535619DEST_PATH_IMAGE022
The difference between each remaining life value and its standard life value;
Figure 519756DEST_PATH_IMAGE024
number of elements in the set of remaining lifetime values;
Figure 957559DEST_PATH_IMAGE025
the resource residual index of the virtual server is obtained;
and processing the access request through the optimal virtual server.
7. The resource allocation system of claim 6, wherein the index calculation module obtains a feature weight corresponding to the feature parameter according to the feature parameter, and obtains a selection index for selecting the virtual server according to the obtained feature parameter and the feature weight corresponding to the feature parameter.
8. The resource allocation system in the cloud computing system according to claim 6 or 7, wherein the virtual server selection module calculates resource remaining indicators of all virtual servers belonging to the cloud computing data center, compares the obtained selection indicator with the resource remaining indicator of each virtual server to select a virtual server meeting the selection indicator requirement, and uses the selected virtual server as a target to be selected.
9. The resource allocation system in the cloud computing system according to claim 8, wherein the virtual server selection module creates one or more new virtual servers when all the virtual servers do not meet the requirement of the selection index, or the virtual server selection module destroys some virtual servers first and then creates one or more new virtual servers, or the virtual server selection module adjusts the computing capability of one or more original virtual servers to meet the requirement of the selection index.
10. The resource allocation system in the cloud computing system according to claim 6 or 7, wherein the remaining life value of the physical server includes: the residual life value of the memory, the residual life value of the hard disk and the residual life value of the CPU.
CN202111148022.9A 2021-09-29 2021-09-29 Resource allocation method and system in cloud computing system Active CN113590342B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111148022.9A CN113590342B (en) 2021-09-29 2021-09-29 Resource allocation method and system in cloud computing system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111148022.9A CN113590342B (en) 2021-09-29 2021-09-29 Resource allocation method and system in cloud computing system

Publications (2)

Publication Number Publication Date
CN113590342A CN113590342A (en) 2021-11-02
CN113590342B true CN113590342B (en) 2022-01-18

Family

ID=78242706

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111148022.9A Active CN113590342B (en) 2021-09-29 2021-09-29 Resource allocation method and system in cloud computing system

Country Status (1)

Country Link
CN (1) CN113590342B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114546603B (en) * 2022-04-24 2022-07-29 睿至科技集团有限公司 Data processing method and system applied to Internet of things
CN114844899A (en) * 2022-04-28 2022-08-02 中国工商银行股份有限公司 Server selection method and device, processor and electronic equipment

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102917077A (en) * 2012-11-20 2013-02-06 无锡城市云计算中心有限公司 Resource allocation method in cloud computing system
CN104063181A (en) * 2013-03-18 2014-09-24 联想(北京)有限公司 SSD (solid state disk) management method and system as well as server
CN110109758A (en) * 2019-04-30 2019-08-09 温州职业技术学院 A kind of cloud computing resources distribution method

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102929687B (en) * 2012-10-12 2016-05-25 山东省计算中心（国家超级计算济南中心） A kind of energy-conservation cloud computing data center virtual machine laying method
CN107967179B (en) * 2017-12-12 2021-08-06 山东省计算中心（国家超级计算济南中心） Cloud computing resource allocation method supporting emergency
US11099743B2 (en) * 2018-06-29 2021-08-24 International Business Machines Corporation Determining when to replace a storage device using a machine learning module

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102917077A (en) * 2012-11-20 2013-02-06 无锡城市云计算中心有限公司 Resource allocation method in cloud computing system
CN104063181A (en) * 2013-03-18 2014-09-24 联想(北京)有限公司 SSD (solid state disk) management method and system as well as server
CN110109758A (en) * 2019-04-30 2019-08-09 温州职业技术学院 A kind of cloud computing resources distribution method

Also Published As

Publication number Publication date
CN113590342A (en) 2021-11-02

Similar Documents

Publication Publication Date Title
CN113590342B (en) Resource allocation method and system in cloud computing system
US20170344472A1 (en) Methods and systems for managing memory allocation
CN107295090B (en) Resource scheduling method and device
CN111190696A (en) Docker container deployment method, system, device and storage medium
CN111767142B (en) Method for setting current limiting threshold of service node and service terminal equipment
CN110839069B (en) Node data deployment method, node data deployment system and medium
CN111131841A (en) Live indirect access method and device, electronic equipment and storage medium
CN109614284B (en) Data processing method and device
CN103905517A (en) Data storage method and equipment
CN106598744A (en) Method and device for dynamic sub-tree partition in metadata cluster
Wong et al. Container deployment strategy for edge networking
TWI602431B (en) Method and device for transmitting information
CN109982158A (en) A kind of distribution method, device and the server of UGC video
CN104170343B (en) A kind of method for managing resource and management server
CN110083313B (en) Data caching method and device
CN108989387B (en) Method, device and equipment for controlling asynchronous request
CN110856183A (en) Edge server deployment method based on heterogeneous load complementation and application
US20150106820A1 (en) Method and apparatus for providing allocating resources
CN113691587B (en) Virtual resource processing method and device, electronic equipment and storage medium
Zhang et al. Personalized quality prediction for dynamic service management based on invocation patterns
CN111506425B (en) Method and device for processing quality of service data
CN115033551A (en) Database migration method and device, electronic equipment and storage medium
CN113791735A (en) Video data storage method and device, computer equipment and storage medium
CN110995620A (en) Method for improving cloud migration efficiency by fully utilizing bandwidth
CN108366022A (en) A kind of method and device of bandwidth allocation

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
GR01 Patent grant
GR01 Patent grant