CN103634330A - Automatic resource distribution method in cloud calculation environment - Google Patents
Automatic resource distribution method in cloud calculation environment Download PDFInfo
- Publication number
- CN103634330A CN103634330A CN201210296593.1A CN201210296593A CN103634330A CN 103634330 A CN103634330 A CN 103634330A CN 201210296593 A CN201210296593 A CN 201210296593A CN 103634330 A CN103634330 A CN 103634330A
- Authority
- CN
- China
- Prior art keywords
- resource
- user
- virtual machine
- configuration
- list
- 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
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to an automatic resource distribution method in a cloud calculation environment. The method comprises the following steps: A. a "resource pool" in the cloud calculation environment is defined and managed; B. a virtual machine is pre-established; C. when a resource application is put forward by a user, resources in the resource pool is automatically matched by a management system, and the resources are listed to an optional queue if types and configuration are both matched; if the number of the optional queue surpasses a requirement of the user, the resources are selected from the optional queue to be distributed to the user according to a presorting dynamic resource distribution algorithm; D. when the pre-established virtual machine cannot meet the requirement of the user, insufficient number of the virtual machines are established after the resource application of the user is submitted. E. the resources are automatically applied and returned, and user data are confidentially stored or selectively deleted according to the requirement; and F. statics and analysis are performed on the requirement of the user, and a resource distribution report form is automatically generated. The process of the method is rapid and safe and automation is realized so that complexity and management cost of resource distribution in the cloud calculation environment are reduced, working efficiency is enhanced and resource utilization rate is also scientifically enhanced.
Description
Technical field
The present invention relates to a kind of resource allocation methods, be specifically related to the resource auto-allocation method under a kind of cloud computing environment.
Background technology
Resource under cloud computing environment (as virtual machine, server etc.) is in large scale, and client is numerous, and major part is resources of virtual machine, after needing to create, could distribute.If system receives that user creates virtual distribution after applying for again, certainly will cause client to wait for, affect system effectiveness and customer satisfaction, if can be pre-created a large amount of virtual machine wait user resources applications in system, not only the waste of the resources such as system self disk will be caused, simultaneously, because the configuration of virtual machine in user's request is also Protean (such as the configuration of virtual machine disk space may be 1G, 2G, 3G, 4G, 5G, 8G, 10G, 16G ... other configurations in like manner, the virtual machine configuration that various configurations combine is by hundreds and thousands of), so being pre-created the virtual machine of various configurations hardly may, the number of times of various configuration applications simultaneously is also not quite similar, therefore, even if created the virtual machine of various configurations, also cannot meet some high-frequency application demand.Therefore, how resource distributes has become one of problem of paying close attention to most in current cloud computing application.
Manual allocation obviously cannot satisfy the demands, inefficiency not only, and if distribute improperly, the resource of too high configuration is distributed to the user of low configuration needs, not only wasted resource, also caused the economic loss of company; If the resource of too low configuration is distributed to the user of high configuration needs, will cause user's demand to be not being met again, reduce customer satisfaction.Mainly there is following shortcoming in prior art:
A, pre-create limited kinds " high demand " configuration virtual machine or pre-create the virtual machine of all Configuration Types: rule of thumb or individual user's demand, pre-create the virtual machine of certain several " high demand " configuration, although can save to a certain extent system resources consumption, and meet to a certain extent certain user's resource bid demand, but be not a kind of perfect scheme, by experience or personal user's demand, analyze the probably not really maximum configuration of all user's requests of " high demand " configuration, like this, the virtual machine creating just may can not be assigned with for a long time, thereby waste system resource, lengthen the time that user waits for that resource is distributed simultaneously, reduce allocative efficiency.
The virtual machine that pre-creates all Configuration Types obviously more cannot be met consumers' demand.The quantity of the virtual machine user demand of different configurations is different, not only causes the virtual machine waste system resource of low frequency application configuration, and meanwhile, most of user's request will be not being met, and lengthen the time that user waits for that resource is distributed, and reduce allocative efficiency.
B, the resource of low performance is distributed to user, reduce user satisfaction, if things go on like this, the benefit of cloud computing service provider will be affected: the resource satisfying the demands according to user's request Auto-matching, find and distribute, although improved dispensing rate, the sacrifice customer satisfaction of take is cost, is obviously unfavorable for the long-run development of cloud computing service provider.
C, the isolated resource distribution of considering in user's request, ignore the factors such as incidence relation between all resource bids of user and index performance: although which can improve dispensing rate, but such as user applies for a server and a database, if searched according to configuration, find any two servers that do not have an incidence relation and database to user, certainly will affect data access speed in user's use procedure.
Summary of the invention
For the deficiencies in the prior art, the invention provides the resource auto-allocation method under a kind of cloud computing environment, the method is according to resource indices, configuration, the data such as incidence relation, provided a kind of presort Dynamic Resource Allocation for Multimedia algorithm, by generate in advance and safeguard the performance ranking list about available resources in resource allocation system, when Resources allocation according to this list in conjunction with resource type, configuration, incidence relation and user's request, selection meets the resource that distributive condition and performance stand out and distributes, realize the application automatically as required of resource, give back, user data is kept secure as required.Once there is any abnormal or damage ring in resource use procedure; system is not selecting the efficient available resources of meeting consumers' demand to redistribute according to resource allocation algorithm in traffic affecting situation the mode with the fastest automatically; and automatically copy user data to newly assigned resource; delete user data in former resource simultaneously; whole process fast and safely; substantially realize automation; reduce complexity and management cost that in cloud computing environment, resource is distributed; increase work efficiency, also science improves resource utilization.
The object of the invention is to adopt following technical proposals to realize:
A resource auto-allocation method under cloud computing environment, its improvements are, described method comprises the steps:
A, definition are also managed " resource pool " under cloud computing environment;
B, pre-create virtual machine;
C, when user proposes resource bid, the resource in management system Auto-matching resource pool, alternative queue is listed in type (as server and virtual machine, application software etc.) and configuration all coupling in; If alternative queue number surpasses user's request, according to presort Dynamic Resource Allocation for Multimedia algorithm, from alternative queue, select resource to distribute to user;
D, when pre-creating virtual machine and cannot meet consumers' demand, after submitting to, user resources application creates the virtual machine of number deficiency;
E, resource are automatically applied for, are given back, and user data is kept secure or selection deletion as required;
F, user's request is carried out to statistical analysis, automatically generate resource and distribute form.
Wherein, in described steps A, described " resource pool " refers to management and distributes a logical abstraction concept of resource under cloud computing environment; Definition resource pool and device type, configuration, incidence relation, and the initial various types of resources of typing, configuration and incidence relation, management system arranges initial condition for " unallocated " for each resource automatically, and management system gathers relevant index (such as CPU number, cpu busy percentage, internal memory surplus etc.) automatically as the performance parameter of resource simultaneously.
Wherein, described step B pre-creates virtual machine and comprises the steps:
A, according to virtual machine configuration and the quantity of user application, by the virtual machine application number of difference configuration by from how to few sequence be divided into all ranks the first five, month rank the first five, all ranks the first six to ten, month rank the first six to ten, do not belong to all ranks the first five, month rank the first five, all ranks the first six to ten and month rank the first six to ten other configurations;
B, according to all ranks of all kinds of configuring virtual machine application numbers or month rank prioritization and pre-create virtual machine.
Wherein, described step b comprises following proposal:
The first five virtual machine configuration of I, all ranks applied for that a number pre-created in maximum day in one week; If the virtual machine remaining in management system in this configuration of part is not assigned with, pre-creating number is apply for number and be not assigned with the poor of number for maximum day, if difference is zero or negative, does not need to pre-create the virtual machine of this configuration;
II, month rank the first five but do not belong to the first five the virtual machine configuration of all ranks, according to the per day applications in month, pre-create; During establishment, to deduct the number of this configuring virtual machine being not yet assigned with in management system, if difference is zero or negative, not need to pre-create the virtual machine of this configuration;
III, the first six configuration of the virtual machine to top ten list of all ranks, pre-create according to one week interior per day applications; During establishment, to deduct equally the number of this configuring virtual machine being not yet assigned with in management system, if difference is zero or negative, not need to pre-create the virtual machine of this configuration;
IV, the first six virtual machine to top ten list of month rank configure, and according to management system own resource situation, create the virtual machine of this configuration;
V, do not belong to all ranks the first five, month rank the first five, all ranks the first six to ten and month rank the first six to the virtual machine configuration of ten, do not pre-create.
Wherein, in described scheme IV, described own resource comprises disk and internal memory etc.;
If management system own resource is sufficient, be that all kinds of resources of management system self all surpass the first six various configuration sum to the virtual machine of top ten list of month rank, the maximum utilization rate of every kind of resources left total amount of management of computing system self and resource is long-pending, divide exactly this configuration sum in the first six configuration of the virtual machine to top ten list of moon rank, round the minimum value of the business after removing as the establishment number of every kind of virtual machine;
If management system own resource is inadequate, be in system own resource, have at least a kind of lower than the moon the first six configuration of the correspondence to the virtual machine of top ten list sum of rank, monthly rank order creates, until management system own resource stops during higher than maximum utilization rate creating.
Wherein, the in the situation that of management of system resource deficiency, by Zhou Qianwu, month the first five, Zhou Qianliu to ten, month the first six to ten priority orders, carry out virtual machine and pre-create; Wherein Zhou Qianwu priority is the highest, and the moon, the first six was minimum to ten priority.
Wherein, described step C comprises the steps:
(1) performance presort;
(2) resource is distributed.
Wherein, in described step (1), described performance presort comprises following proposal:
1. based on described " resource pool ", according to resource index, configuration, incidence relation, generate and safeguard the performance ranking list of the available resources of all " unallocated ";
2. presort Dynamic Resource Allocation for Multimedia algorithm is determined resource performance value.
Wherein, described scheme 2. in, the performance number that represents a certain index of resource or configuration with P, W represents the weight in resource performance, and A represents a certain index of resource or configuration balance factor, and V represents a certain index of resource or configures actual value, I represents a certain index of resource or configures positive and negative influence value, the a certain index of described resource or resource allocation performance calculating formula are: P=V1*A1*W1*I1+V2*A2*W2*I2+ ... + Vn*An*Wn*In, wherein, n represents that impact changes index and the configurable number of resource performance; Vn represents the actual value of n performance index or configuration, and An represents the balance factor of this class index or configuration, and Wn represents the weight in resource performance of n index or configuration, In represent this class index or configuration positive and negative influence value.
Wherein, in described step (2), described resource distribution comprises the steps:
The first step: management system pre-creates virtual machine, and generate resource performance list;
Second step: management system receives after the resource bid of user's proposition, empties resource distribution list L0; Resource distribution list is for preserving management system, to distribute to a list of user's final resource;
The 3rd step: the Resources list of traversal user application, the consistent all resources of type (as server and virtual machine, application software etc.) of searching the resource of applying for user in resource pool obtain the Resources list L1;
If this Resources list L1 is empty, empty list is returned, and pointed out user not have resource to satisfy the demands;
If this Resources list is not empty, travel through this list, judge that whether manufacturer, model be consistent with user's request, if all unanimously, this resource is added to alternative resource list L2;
Otherwise continue to travel through next; After having traveled through the Resources list L1, proceed to the 4th step processing;
The 4th step: judge whether alternative resource list L2 is empty;
Empty if, the Resources list L1 is all added to alternative resource list L2;
If be not empty, judge in alternative resource list L2 whether only have a resource, if so, distributed to user; Otherwise, proceed to the 5th step and process;
The 5th step: select configuration in alternative resource list L2 meet consumers' demand or do not exceed maximum margin the Resources list L3, and sort by the priority of configuration, performance; Judge whether the Resources list L3 only has a resource; If only have one, added resource distribution list L0, and distributed to user; Otherwise, judge whether user applies for a plurality of resources that are associated, if so, proceed to the 6th step;
The 6th step: judge in user's application and whether have the resource bid being associated with current application resource type not to be assigned with, if had, to preserve current resource to resource distribution list, to return to the 3rd step, to search the correlated resources being not yet assigned with and distribute;
If the resource conservation that no, search performance is the highest from the Resources list L3 is in resource distribution list;
Judge whether user also has other resource bids not to be assigned with, if had, returns to the 3rd step, and the Resources list that continues traversal user application carries out resource distribution, if do not had, enters the 7th step;
The 7th step: the resource in resource distribution list is distributed to user.
Wherein, described step D comprises the steps:
I, management system are obtained after user's request, first judge the unallocated virtual machine that whether has this configuration in management system;
If ii exists, whether judge in management system that this configures unappropriated virtual machine number meets consumers' demand, if number meets, this pre-creating in system configured to unallocated virtual machine and distribute to user, number is the total number of this configuring virtual machine of user's application;
If number does not meet, judge whether management system own resource can create the virtual machine of differential section, if can, create the virtual machine of differential section, after having created by newly create with management system in pre-create this configure unallocated virtual machine and all distribute to user; If can not, point out user resources not enough, cannot satisfy the demands;
Iii, if there is no, judges whether management system own resource can create the virtual machine of user's specified quantity, if can, according to user's request, create the virtual machine of this configuration of specified quantity, after having created, distributed to user; If can not, point out user resources not enough, cannot satisfy the demands.
Wherein, described step e comprises the steps:
1) user proposes after resource bid, and management system is distributed according to resource allocation algorithm and policy selection resource automatically;
2) user's request comprises application service time and gives back the time, and to after date, whether management system gives back by note and mail inquiry user, and user selects to give back resource or continues to use resource;
3) if user selects to give back, management system inquires user whether user data is stored in need to be keep secret, and user selects kept secure data or deletes data, if select kept secure, management system will be encrypted storage to it.
Wherein, described step F comprises the steps:
One, user's request is carried out to statistical analysis, analyze resource bid quantity and frequency all types of and configuration, automatically generate resource bid form;
Two, the virtual machine application number of various configurations is carried out to this day, this week and the quantitative statistics of this month application number;
Three, resource distributes form to instruct the work of purchasing department and HR department.
Compared with the prior art, the beneficial effect that the present invention reaches is:
1, based on resource pool and the automatic Resources allocation of performance ranking algorithm, not only raise the efficiency, and can when meeting consumers' demand, provide the resource of optimum performance to user, increase customer satisfaction degree, solve some cloud computing service providers at present and only meet consumers' demand, cannot take the problem of resource serviceability into account.
2, resource bid is carried out to statistical analysis, science determines to pre-create Configuration Type and the quantity of resources of virtual machine, be not only fully rationally utilizing the resource of system own, also saved user and waited for the time that resource is distributed simultaneously, reduced the complexity that in large-scale cloud computing environment, resources of various types is distributed, simplified resource allocation flow, reached reduction management cost, the object of raising the efficiency.
3,, when meeting the demands such as user's configuration, in conjunction with other resource bids of user, according to formulation multidimensional resource allocation policies such as the incidence relations between resource, improve user resources service efficiency and performance.
4, in resource use procedure if there is abnormal or damage, system all can be redistributed efficient available resource automatically rapidly to user, and user data is carried out to safety transfer, speed is fast, safety is secure.After resource is finished using simultaneously, user can select data to maintain secrecy and retain or thoroughly delete, flexible.
Accompanying drawing explanation
Fig. 1 is the schematic diagram of " resource pool " under cloud computing environment provided by the invention;
Fig. 2 is the flow chart that resource provided by the invention is distributed;
Fig. 3 is the flow chart of the resource auto-allocation method under cloud computing environment provided by the invention.
Embodiment
Below in conjunction with accompanying drawing, the specific embodiment of the present invention is described in further detail.
The invention provides resource auto-allocation method flow chart under a kind of cloud computing environment as shown in Figure 3, the method comprises the steps:
A, definition are also managed " resource pool " under cloud computing environment:
" resource pool " refers to flexible management and distributes a logical abstraction concept of resource under cloud computing environment.Keeper defines resource pool and device type, configuration, incidence relation, and the initial various types of resources of typing and configuration and incidence relation, system arranges initial condition for " unallocated " for each resource automatically, and simultaneity factor gathers relevant index (such as CPU number, cpu busy percentage, internal memory surplus etc.) automatically as the performance parameter of resource.The schematic diagram of " resource pool " under cloud computing environment provided by the invention as shown in Figure 1.
According to the statistic analysis result of user's application, the virtual machine application number of difference configuration is carried out to week sequence and month sequence, according to ranking results, pre-create virtual machine, refer to step B.
When user proposes resource bid, the resource in system Auto-matching resource pool, type matching and configure the eligible alternative queue of listing in.If number surpasses user's request, according to presort Dynamic Resource Allocation for Multimedia algorithm, from alternative queue, select efficient available resource to distribute to user, refer to step C.If number is just met consumers' demand, directly the resource of all these configurations is distributed to user.
If alternative queue resource number cannot be met consumers' demand, judge whether the resource that user applies for is virtual machine, if, according to the configuration in user's request, create virtual machine and distribute to user, if not, point out user resources not enough, cannot satisfy the demands, refer to step D.
The resource mark of selected distribution is " distributing ", and resource is finished using or user resources application expires, and system all can inquire whether user gives back resource automatically.If user selects to give back, system will be carried out respective handling to its data according to user's request, by resource status modification, be then " unallocated ".
B, pre-create virtual machine, comprise the steps:
A, according to virtual machine configuration and the quantity of user application, by the virtual machine application number of difference configuration by from how to few sequence be divided into all ranks the first five, month rank the first five, all ranks the first six to ten, month rank the first six to ten, do not belong to all ranks the first five, month rank the first five, all ranks the first six to ten and month rank the first six to ten other configurations;
B, according to all ranks of all kinds of configuring virtual machine application numbers or month rank prioritization and pre-create virtual machine, comprise following scheme:
The first five virtual machine configuration of I, all ranks, in one week, maximum day apply for that number pre-creates, if the virtual machine remaining in system in this configuration of part is not assigned with, pre-create number for maximum day applying for number and be not assigned with the poor of number, if this value is zero or negative, do not need to pre-create.
For example, the virtual machine of certain configuration applies for that number is number two within one week, suppose to apply for within this week certain day that this configuring virtual machine number is maximum, value is a, the virtual machine remaining in supposing the system in addition b this configuration is not assigned with, if a-b value is 0 or negative, does not need to pre-create the virtual machine of this configuration, otherwise will pre-create the virtual machine of a-b this configuration.
II, month rank the first five but do not belong to the first five the virtual machine configuration of all ranks, according to the per day applications in month, pre-create.During establishment, to deduct equally the number of this configuring virtual machine being not yet assigned with in system, if difference is zero or negative, not need to pre-create.
III, the first six configuration of the virtual machine to top ten list of all ranks, pre-create according to one week interior per day applications.During establishment, to deduct equally the number of this configuring virtual machine being not yet assigned with in system, if difference is zero or negative, not need to pre-create.
IV, the first six configuration of the virtual machine to top ten list of month rank, create according to system own resource (as disk, internal memory etc.) actual conditions.
If system own resource sufficient (being that all kinds of resources of system self all surpass the first six various configuration sum to the virtual machine of top ten list of month rank), the maximum utilization rate of every kind of resources left total amount of computing system self and this resource long-pending (maximum utilization rate is determined by cloud computing service provider), then divide exactly this configuration sum in the first six configuration of the virtual machine to top ten list of moon rank, get these and divide exactly business's afterwards minimum value as the establishment number of every kind of virtual machine.
For example: system self residual disk space is 160G, the maximum utilization rate of disk is 90%, and in the first six configuration of the virtual machine to top ten list of month rank, disk demand sum is 50G, and dividing exactly business is 160*90%/50=2; System self EMS memory residual capacity is 50G, and the maximum utilization rate of internal memory is 80%, and in these virtual machine configurations, memory requirements sum is 10G, and dividing exactly business is 50*80%/10=4, so these virtual machine creating numbers are 2.
If system own resource inadequate (be have at least in system own resource a kind of lower than the moon the first six configuration of the correspondence to the virtual machine of top ten list sum of rank), monthly rank order creates, until certain resource of system self stops creating higher than maximum utilization rate.
No matter which kind of situation, all will deduct the number of this configuring virtual machine being not yet assigned with in system during establishment, if difference is zero or negative, do not need to pre-create.
V, do not belong to all ranks the first five, month rank the first five, all ranks the first six to ten and month rank the first six to the virtual machine configuration of ten, do not pre-create.
Above five kinds of schemes in the situation that of system resource deficiency, by Zhou Qianwu, month the first five, Zhou Qianliu to ten, month the first six to ten priority orders, carry out virtual machine and pre-create.Zhou Qianwu priority is the highest, and the moon, the first six was minimum to ten priority.
C, when user proposes resource bid, the resource in management system Auto-matching resource pool, alternative queue is listed in type (as server and virtual machine, application software etc.) and configuration all coupling in; If alternative queue number surpasses user's request, according to presort Dynamic Resource Allocation for Multimedia algorithm, from alternative queue, select resource to distribute to user; Comprise the steps:
(1) performance presort:
Performance presort comprises following proposal:
1. based on described " resource pool ", according to resource index, configuration, incidence relation, generate and safeguard the performance ranking list of the available resources of all " unallocated ";
2. presort Dynamic Resource Allocation for Multimedia algorithm is determined resource performance value:
Resource performance is determined jointly by factors such as resource indices, configuration and incidence relations.Resource index of the same type is identical with configuration, but each index and configuration have different weights, balance factor and positive and negative influence value, by these weights, balance factor and positive and negative influence value, calculate corresponding resource performance.Here, balance factor be one in order to the actual value of each factor of balance so that the value of computational resource performance.Generally we get all indexs and configure the least common multiple of mean value and the business of each index and configuration mean value as balance factor, therefore different indexs and configuration balance factor are generally different, if there are other specific factor impacts, we also can manually arrange this value.The mean value of each index and configuration is the mean value of the corresponding value of all resources of the same type in resource pool, is an average result that statistics draws.Positive and negative influence value is that each index or configuration cause the value of statistical indicant of positive influences or negative effect to performance, 1 by the performance number of cumulative this index or configuration in resource performance value, if-1 performance number that deducts this index or configuration in resource performance value if.
Presort Dynamic Resource Allocation for Multimedia algorithm: we represent the performance number of a certain index of resource or configuration with P, W represents its weight in resource performance, A represents its balance factor, V represents its actual value, I represents its positive and negative influence value, and the performance calculating formula of this index or configuration is so: P=V*A*W*I.The performance calculating formula of resource is: P=V1*A1*W1*I1+V2*A2*W2*I2+ ... + Vn*An*Wn*In, wherein, n represents that impact changes index and the configurable number of resource performance.Vn represents the actual value of n performance index or configuration, and An represents the balance factor of this class index or configuration, and Wn represents the weight in resource performance of this class index or configuration, In represent this class index or configuration positive and negative influence value.
(2) resource is distributed:
Resource allocation flow as shown in Figure 2, specifically describes as follows:
The first step: system pre-creates virtual machine, and generate resource performance list.
Second step: system receives after the resource bid of user's proposition, first empties resource distribution list L0.Resource distribution list is for saved system, to distribute to a list of user's final resource.
The 3rd step: the Resources list of traversal user application, search the type of the resource of applying for user in resource pool (as server, the type such as virtual machine, rack) consistent all resources obtain the Resources list L1, if this Resources list L1 is empty, empty list is returned, and pointed out user not have resource to satisfy the demands; If this Resources list is not empty, travel through this list, judge that whether manufacturer, model be consistent with user's request, if all unanimously, this resource is added to alternative resource list L2; Otherwise continue to travel through next.After having traveled through list, proceed to the 4th step processing.
The 4th step: judge whether alternative resource list L2 is empty, empty if, the Resources list L1 is all added to alternative resource list L2, if be not empty, judge in alternative resource list whether only have a resource, if so, distributed to user; If have a plurality ofly, proceed to the 5th step and process.
The 5th step: select configuration in alternative resource list meet consumers' demand or do not exceed maximum margin the Resources list L3, and sort by the priority of configuration, performance.Wherein maximum margin is predefined data, has a maximum margin, such as hard disk maximum margin is 16(G for each configuration and index), cpu number maximum margin is 1().If only have one, added resource distribution list L0, and distributed to user, if having a plurality ofly, judge whether user applies for a plurality of resources that are associated, if so, proceed to the 6th step.
The 6th step: judge in user's application and whether have the resource bid being associated with current application resource type not to be assigned with, if had, to preserve current resource to resource distribution list, then to enter the 3rd step, to search the correlated resources being not yet assigned with and distribute; If the resource conservation that no, search performance is the highest from list L3 is in resource distribution list.Judge whether user also has other resource bids not to be assigned with, if had, enters the 3rd step, and the Resources list that continues traversal user application carries out resource distribution, if do not had, enters the 7th step.
The 7th step: the resource in resource distribution list is distributed to user.
D, when pre-creating virtual machine and cannot meet consumers' demand, after submitting to, user resources application creates the virtual machine of number deficiency; Comprise the steps:
I, management system are obtained after user's request, first judge the unallocated virtual machine that whether has this configuration in management system;
If ii exists, whether judge in management system that this configures unappropriated virtual machine number meets consumers' demand, if number meets, this pre-creating in system configured to unallocated virtual machine and distribute to user, number is the total number of this configuring virtual machine of user's application;
If number does not meet, judge whether management system own resource can create the virtual machine of differential section, if can, create the virtual machine of differential section, after having created by newly create with management system in pre-create this configure unallocated virtual machine and all distribute to user; If can not, point out user resources not enough, cannot satisfy the demands;
Iii, if there is no, judges whether management system own resource can create the virtual machine of user's specified quantity, if can, according to user's request, create the virtual machine of this configuration of specified quantity, after having created, distributed to user; If can not, point out user resources not enough, cannot satisfy the demands.
E, resource are automatically applied for, are given back, and user data is kept secure or selection deletion as required; Comprise the steps:
1) user proposes after resource bid, and management system is distributed according to resource allocation algorithm and policy selection resource automatically;
2) user's request comprises application service time and gives back the time, and to after date, whether management system gives back by note and mail inquiry user, and user selects to give back resource or continues to use resource;
3) if user selects to give back, management system inquires user whether user data is stored in need to be keep secret, and user selects kept secure data or deletes data, if select kept secure, management system will be encrypted storage to it.
F, user's request is carried out to statistical analysis, automatically generate resource and distribute form; Comprise the steps:
One, user's request is carried out to statistical analysis, analyze resource bid quantity and the frequency of all types of (as server and virtual machine, application software etc.) and configuration, automatically generate resource bid form.
Two, the virtual machine application number of various configurations is carried out to this day, this week and the quantitative statistics of this month application number, to instruct, pre-create virtual machine strategy.
Three, resource distributes form to instruct the work of purchasing department and HR department.
Resource auto-allocation method under cloud computing environment provided by the invention, based on resource pool and the automatic Resources allocation of performance ranking algorithm, not only raise the efficiency, and can when meeting consumers' demand, provide the resource of optimum performance to user, increase customer satisfaction degree, solve some cloud computing service providers at present and only meet consumers' demand, cannot take the problem of resource serviceability into account.
Finally should be noted that: above embodiment is only in order to illustrate that technical scheme of the present invention is not intended to limit, although the present invention is had been described in detail with reference to above-described embodiment, those of ordinary skill in the field are to be understood that: still can modify or be equal to replacement the specific embodiment of the present invention, and do not depart from any modification of spirit and scope of the invention or be equal to replacement, it all should be encompassed in the middle of claim scope of the present invention.
Claims (13)
1. the resource auto-allocation method under cloud computing environment, is characterized in that, described method comprises the steps:
A, definition are also managed " resource pool " under cloud computing environment;
B, pre-create virtual machine;
C, when user proposes resource bid, the resource in management system Auto-matching resource pool, alternative queue is listed in type and configuration all coupling in; If alternative queue number surpasses user's request, according to presort Dynamic Resource Allocation for Multimedia algorithm, from alternative queue, select resource to distribute to user;
D, when pre-creating virtual machine and cannot meet consumers' demand, after submitting to, user resources application creates the virtual machine of number deficiency;
E, resource are automatically applied for, are given back, and user data is kept secure or selection deletion as required;
F, user's request is carried out to statistical analysis, automatically generate resource and distribute form.
2. the resource auto-allocation method under cloud computing environment as claimed in claim 1, is characterized in that, in described steps A, described " resource pool " refers to management and distribute a logical abstraction concept of resource under cloud computing environment; Definition resource pool and device type, configuration, incidence relation, and the initial various types of resources of typing, configuration and incidence relation, management system arranges initial condition for " unallocated " for each resource automatically, and management system gathers relevant index automatically as the performance parameter of resource simultaneously.
3. the resource auto-allocation method under cloud computing environment as claimed in claim 1, is characterized in that, described step B pre-creates virtual machine and comprises the steps:
A, according to virtual machine configuration and the quantity of user application, by the virtual machine application number of difference configuration by from how to few sequence be divided into all ranks the first five, month rank the first five, all ranks the first six to ten, month rank the first six to ten, do not belong to all ranks the first five, month rank the first five, all ranks the first six to ten and month rank the first six to ten other configurations;
B, according to all ranks of all kinds of configuring virtual machine application numbers or month rank prioritization and pre-create virtual machine.
4. the resource auto-allocation method under cloud computing environment as claimed in claim 3, is characterized in that, described step b comprises following proposal:
The first five virtual machine configuration of I, all ranks applied for that a number pre-created in maximum day in one week; If the virtual machine remaining in management system in this configuration of part is not assigned with, pre-creating number is apply for number and be not assigned with the poor of number for maximum day, if difference is zero or negative, does not need to pre-create the virtual machine of this configuration;
II, month rank the first five but do not belong to the first five the virtual machine configuration of all ranks, according to the per day applications in month, pre-create; During establishment, to deduct the number of this configuring virtual machine being not yet assigned with in management system, if difference is zero or negative, not need to pre-create the virtual machine of this configuration;
III, the first six configuration of the virtual machine to top ten list of all ranks, pre-create according to one week interior per day applications; During establishment, to deduct equally the number of this configuring virtual machine being not yet assigned with in management system, if difference is zero or negative, not need to pre-create the virtual machine of this configuration;
IV, the first six virtual machine to top ten list of month rank configure, and according to management system own resource situation, create the virtual machine of this configuration;
V, do not belong to all ranks the first five, month rank the first five, all ranks the first six to ten and month rank the first six to the virtual machine configuration of ten, do not pre-create.
5. the resource auto-allocation method under cloud computing environment as claimed in claim 4, is characterized in that, in described scheme IV, described own resource comprises disk and internal memory;
If management system own resource is sufficient, be that all kinds of resources of management system self all surpass the first six various configuration sum to the virtual machine of top ten list of month rank, the maximum utilization rate of every kind of resources left total amount of management of computing system self and resource is long-pending, divide exactly this configuration sum in the first six configuration of the virtual machine to top ten list of moon rank, round the minimum value of the business after removing as the establishment number of every kind of virtual machine;
If management system own resource is inadequate, be in system own resource, have at least a kind of lower than the moon the first six configuration of the correspondence to the virtual machine of top ten list sum of rank, monthly rank order creates, until management system own resource stops during higher than maximum utilization rate creating.
6. the resource auto-allocation method under the cloud computing environment as described in any one in claim 3-5, it is characterized in that, the in the situation that of management of system resource deficiency, by Zhou Qianwu, month the first five, Zhou Qianliu to ten, month the first six to ten priority orders, carry out virtual machine and pre-create; Wherein Zhou Qianwu priority is the highest, and the moon, the first six was minimum to ten priority.
7. the resource auto-allocation method under cloud computing environment as claimed in claim 1, is characterized in that, described step C comprises the steps:
(1) performance presort;
(2) resource is distributed.
8. the resource auto-allocation method under cloud computing environment as claimed in claim 7, is characterized in that, in described step (1), described performance presort comprises following proposal:
1. based on described " resource pool ", according to resource index, configuration, incidence relation, generate and safeguard the performance ranking list of the resource of all " unallocated ";
2. presort Dynamic Resource Allocation for Multimedia algorithm is determined resource performance value.
9. the resource auto-allocation method under cloud computing environment as claimed in claim 8, it is characterized in that, described scheme 2. in, the performance number that represents a certain index of resource or configuration with P, W represents the weight in resource performance, A represents a certain index of resource or configuration balance factor, V represents a certain index of resource or configures actual value, I represents a certain index of resource or configures positive and negative influence value, the a certain index of described resource or configuration performance calculating formula are: P=V1*A1*W1*I1+V2*A2*W2*I2+ ... + Vn*An*Wn*In, wherein, n represents that impact changes index and the configurable number of resource performance, Vn represents the actual value of n performance index or configuration, and An represents the balance factor of this class index or configuration, and Wn represents the weight in resource performance of n index or configuration, In represent this class index or configuration positive and negative influence value.
10. the resource auto-allocation method under cloud computing environment as claimed in claim 7, is characterized in that, in described step (2), described resource distribution comprises the steps:
The first step: management system pre-creates virtual machine, and generate resource performance list;
Second step: management system receives after the resource bid of user's proposition, empties resource distribution list L0; Resource distribution list is for preserving management system, to distribute to a list of user's final resource;
The 3rd step: the Resources list of traversal user application, the consistent all resources of type of searching the resource of applying for user in resource pool obtain the Resources list L1;
If this Resources list L1 is empty, empty list is returned, and pointed out user not have resource to satisfy the demands;
If this Resources list is not empty, travel through this list, judge that whether manufacturer, model be consistent with user's request, if all unanimously, this resource is added to alternative resource list L2;
Otherwise continue to travel through next; After having traveled through list, proceed to the 4th step processing;
The 4th step: judge whether alternative resource list L2 is empty;
Empty if, the Resources list L1 is all added to alternative resource list L2;
If be not empty, judge in alternative resource list whether only have a resource, if so, distributed to user; Otherwise, proceed to the 5th step and process;
The 5th step: select configuration in alternative resource list meet consumers' demand or do not exceed maximum margin the Resources list L3, and sort by the priority of configuration, performance; Judge whether the Resources list L3 only has a resource; If only have one, added resource distribution list L0, and distributed to user; Otherwise, judge whether user applies for a plurality of resources that are associated, if so, proceed to the 6th step;
The 6th step: judge in user's application and whether have the resource bid being associated with current application resource type not to be assigned with, if had, to preserve current resource to resource distribution list, to return to the 3rd step, to search the correlated resources being not yet assigned with and distribute;
If the resource conservation that no, search performance is the highest from the Resources list L3 is in resource distribution list;
Judge whether user also has other resource bids not to be assigned with, if had, returns to step 3, and the Resources list that continues traversal user application carries out resource distribution, if do not had, enters the 7th step;
The 7th step: the resource in resource distribution list is distributed to user.
Resource auto-allocation method under 11. cloud computing environments as claimed in claim 1, is characterized in that, described step D comprises the steps:
I, management system are obtained after user's request, first judge the unallocated virtual machine that whether has this configuration in management system;
If ii exists, whether judge in management system that this configures unappropriated virtual machine number meets consumers' demand, if number meets, this pre-creating in system configured to unallocated virtual machine and distribute to user, number is the total number of this configuring virtual machine of user's application;
If number does not meet, judge whether management system own resource can create the virtual machine of differential section, if can, create the virtual machine of differential section, after having created by newly create with management system in pre-create this configure unallocated virtual machine and all distribute to user; If can not, point out user resources not enough, cannot satisfy the demands;
Iii, if there is no, judges whether management system own resource can create the virtual machine of user's specified quantity, if can, according to user's request, create the virtual machine of this configuration of specified quantity, after having created, distributed to user; If can not, point out user resources not enough, cannot satisfy the demands.
Resource auto-allocation method under 12. cloud computing environments as claimed in claim 1, is characterized in that, described step e comprises the steps:
1) user proposes after resource bid, and management system is distributed according to resource allocation algorithm and policy selection resource automatically;
2) user's request comprises application service time and gives back the time, and to after date, whether management system gives back by note and mail inquiry user, and user selects to give back resource or continues to use resource;
3) if user selects to give back, management system inquires user whether user data is stored in need to be keep secret, and user selects kept secure data or deletes data, if select kept secure, management system will be encrypted storage to it.
Resource auto-allocation method under 13. cloud computing environments as claimed in claim 1, is characterized in that, described step F comprises the steps:
One, user's request is carried out to statistical analysis, analyze resource bid quantity and frequency all types of and configuration, automatically generate resource bid form;
Two, the virtual machine application number of various configurations is carried out to this day, this week and the quantitative statistics of this month application number;
Three, resource distributes form to instruct the work of purchasing department and HR department.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210296593.1A CN103634330A (en) | 2012-08-20 | 2012-08-20 | Automatic resource distribution method in cloud calculation environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210296593.1A CN103634330A (en) | 2012-08-20 | 2012-08-20 | Automatic resource distribution method in cloud calculation environment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103634330A true CN103634330A (en) | 2014-03-12 |
Family
ID=50214957
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210296593.1A Pending CN103634330A (en) | 2012-08-20 | 2012-08-20 | Automatic resource distribution method in cloud calculation environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103634330A (en) |
Cited By (32)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103973803A (en) * | 2014-05-19 | 2014-08-06 | 英华达（上海）科技有限公司 | Cloud resource distribution system and method, and computer readable record medium of stored program |
| CN104038540A (en) * | 2014-06-03 | 2014-09-10 | 山东乾云启创信息科技有限公司 | Method and system for automatically selecting application proxy server |
| CN104063265A (en) * | 2014-07-04 | 2014-09-24 | 云南电网公司 | Method for comprehensively evaluating virtual resources |
| CN104125293A (en) * | 2014-08-06 | 2014-10-29 | 曙光信息产业(北京)有限公司 | Cloud server and application method thereof |
| CN104461699A (en) * | 2014-12-29 | 2015-03-25 | 成都致云科技有限公司 | Virtual host creating method and device and distributed storage system |
| CN104572301A (en) * | 2015-01-04 | 2015-04-29 | 中国联合网络通信集团有限公司 | Resource distribution method and system |
| CN105589751A (en) * | 2015-11-27 | 2016-05-18 | 杭州华三通信技术有限公司 | Physical resource scheduling method and device |
| CN105988858A (en) * | 2015-05-15 | 2016-10-05 | 中国银联股份有限公司 | Virtual machine resource scheduling method, device and system |
| CN106302170A (en) * | 2016-09-22 | 2017-01-04 | 东南大学 | A kind of resource allocation methods of wireless cloud computing system |
| CN106453146A (en) * | 2016-11-17 | 2017-02-22 | 华胜信泰信息产业发展有限公司 | Private cloud computing resource distribution method and system |
| CN106993008A (en) * | 2016-01-20 | 2017-07-28 | 阿里巴巴集团控股有限公司 | A kind of resource regulating method and device |
| CN107045476A (en) * | 2016-12-20 | 2017-08-15 | 中电科华云信息技术有限公司 | Software test service implementing method and system based on virtualization |
| CN107133096A (en) * | 2017-04-13 | 2017-09-05 | 新华三技术有限公司 | A kind of resource allocation methods and device |
| CN107995269A (en) * | 2017-11-24 | 2018-05-04 | 合肥博焱智能科技有限公司 | A kind of resource dynamic distributing method based on cloud computing platform |
| CN108063784A (en) * | 2016-11-08 | 2018-05-22 | 阿里巴巴集团控股有限公司 | The methods, devices and systems of application cluster resource allocation under a kind of cloud environment |
| CN108664324A (en) * | 2017-03-30 | 2018-10-16 | 微软技术许可有限责任公司 | The Update log of cloud service example allocation |
| CN109426647A (en) * | 2017-08-30 | 2019-03-05 | 英特尔公司 | For coordinating the technology of the accelerator installation resource of depolymerization |
| CN109491798A (en) * | 2018-11-27 | 2019-03-19 | 郑州云海信息技术有限公司 | A kind of method and device of resource allocation |
| CN109697107A (en) * | 2018-12-18 | 2019-04-30 | 山东超越数控电子股份有限公司 | A kind of method and realization system of self-service resource bid |
| CN110717761A (en) * | 2019-12-12 | 2020-01-21 | 腾讯科技（深圳）有限公司 | Data processing method and device and computer storage medium |
| CN110740194A (en) * | 2019-11-18 | 2020-01-31 | 南京航空航天大学 | Micro-service combination method based on cloud edge fusion and application |
| CN111158595A (en) * | 2019-12-27 | 2020-05-15 | 中国建设银行股份有限公司 | Enterprise-level heterogeneous storage resource scheduling method and system |
| CN111399985A (en) * | 2020-03-19 | 2020-07-10 | 国网山东省电力公司 | Load balancing method based on storage difference iteration in cloud computing environment |
| CN111459656A (en) * | 2020-03-06 | 2020-07-28 | 北京百度网讯科技有限公司 | Server management method and device, electronic equipment and storage medium |
| CN111858014A (en) * | 2019-04-24 | 2020-10-30 | 中国移动通信集团河北有限公司 | Resource allocation method and device |
| CN112565320A (en) * | 2019-09-25 | 2021-03-26 | 大唐移动通信设备有限公司 | Load balancing method and device |
| CN112584526A (en) * | 2020-12-08 | 2021-03-30 | 厦门诚创网络股份有限公司 | Resource allocation method and system |
| CN114157701A (en) * | 2021-11-19 | 2022-03-08 | 北京百度网讯科技有限公司 | Task testing method, device, equipment and storage medium |
| CN114691992A (en) * | 2022-03-29 | 2022-07-01 | 阿里云计算有限公司 | Cloud product recommendation and display method, system, equipment and storage medium |
| CN117435298A (en) * | 2023-10-16 | 2024-01-23 | 常州大数据有限公司 | Data center energy efficiency intelligent tuning cloud platform based on large language model |
| US11977923B2 (en) | 2016-11-29 | 2024-05-07 | Intel Corporation | Cloud-based scale-up system composition |
| US12040889B2 (en) | 2016-07-22 | 2024-07-16 | Intel Corporation | Technologies for switching network traffic in a data center |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110283277A1 (en) * | 2010-05-11 | 2011-11-17 | International Business Machines Corporation | Virtualization and dynamic resource allocation aware storage level reordering |
| CN102523254A (en) * | 2011-11-29 | 2012-06-27 | 曙光信息产业(北京)有限公司 | Method for automatically distributing systematic resources of cloud computing environment |
| CN102521052A (en) * | 2011-12-06 | 2012-06-27 | 北京航空航天大学 | Resource allocation method of virtualized data center and virtual machine monitor |
-
2012
- 2012-08-20 CN CN201210296593.1A patent/CN103634330A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110283277A1 (en) * | 2010-05-11 | 2011-11-17 | International Business Machines Corporation | Virtualization and dynamic resource allocation aware storage level reordering |
| CN102523254A (en) * | 2011-11-29 | 2012-06-27 | 曙光信息产业(北京)有限公司 | Method for automatically distributing systematic resources of cloud computing environment |
| CN102521052A (en) * | 2011-12-06 | 2012-06-27 | 北京航空航天大学 | Resource allocation method of virtualized data center and virtual machine monitor |
Non-Patent Citations (1)
| Title |
|---|
| 许晓东: "《基于资源池的预排序动态资源分配算法》", 《中国通信》 * |
Cited By (48)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103973803B (en) * | 2014-05-19 | 2017-10-13 | 英华达（上海）科技有限公司 | High in the clouds resource allocation system, method |
| CN103973803A (en) * | 2014-05-19 | 2014-08-06 | 英华达（上海）科技有限公司 | Cloud resource distribution system and method, and computer readable record medium of stored program |
| CN104038540B (en) * | 2014-06-03 | 2017-03-22 | 山东乾云启创信息科技股份有限公司 | Method and system for automatically selecting application proxy server |
| CN104038540A (en) * | 2014-06-03 | 2014-09-10 | 山东乾云启创信息科技有限公司 | Method and system for automatically selecting application proxy server |
| CN104063265A (en) * | 2014-07-04 | 2014-09-24 | 云南电网公司 | Method for comprehensively evaluating virtual resources |
| CN104125293A (en) * | 2014-08-06 | 2014-10-29 | 曙光信息产业(北京)有限公司 | Cloud server and application method thereof |
| CN104125293B (en) * | 2014-08-06 | 2018-11-06 | 曙光信息产业(北京)有限公司 | A kind of Cloud Server and its application method |
| CN104461699A (en) * | 2014-12-29 | 2015-03-25 | 成都致云科技有限公司 | Virtual host creating method and device and distributed storage system |
| CN104572301A (en) * | 2015-01-04 | 2015-04-29 | 中国联合网络通信集团有限公司 | Resource distribution method and system |
| CN104572301B (en) * | 2015-01-04 | 2019-02-26 | 中国联合网络通信集团有限公司 | A kind of resource allocation methods and system |
| CN105988858A (en) * | 2015-05-15 | 2016-10-05 | 中国银联股份有限公司 | Virtual machine resource scheduling method, device and system |
| CN105589751B (en) * | 2015-11-27 | 2019-03-15 | 新华三技术有限公司 | A kind of physics resource scheduling method and device |
| CN105589751A (en) * | 2015-11-27 | 2016-05-18 | 杭州华三通信技术有限公司 | Physical resource scheduling method and device |
| CN106993008B (en) * | 2016-01-20 | 2020-03-10 | 阿里巴巴集团控股有限公司 | Resource scheduling method and device |
| CN106993008A (en) * | 2016-01-20 | 2017-07-28 | 阿里巴巴集团控股有限公司 | A kind of resource regulating method and device |
| US12040889B2 (en) | 2016-07-22 | 2024-07-16 | Intel Corporation | Technologies for switching network traffic in a data center |
| US12081323B2 (en) | 2016-07-22 | 2024-09-03 | Intel Corporation | Techniques to control system updates and configuration changes via the cloud |
| CN106302170B (en) * | 2016-09-22 | 2019-06-18 | 东南大学 | A kind of resource allocation methods of wireless cloud computing system |
| CN106302170A (en) * | 2016-09-22 | 2017-01-04 | 东南大学 | A kind of resource allocation methods of wireless cloud computing system |
| CN108063784A (en) * | 2016-11-08 | 2018-05-22 | 阿里巴巴集团控股有限公司 | The methods, devices and systems of application cluster resource allocation under a kind of cloud environment |
| CN106453146A (en) * | 2016-11-17 | 2017-02-22 | 华胜信泰信息产业发展有限公司 | Private cloud computing resource distribution method and system |
| US11995330B2 (en) | 2016-11-29 | 2024-05-28 | Intel Corporation | Technologies for providing accelerated functions as a service in a disaggregated architecture |
| US11977923B2 (en) | 2016-11-29 | 2024-05-07 | Intel Corporation | Cloud-based scale-up system composition |
| CN107045476A (en) * | 2016-12-20 | 2017-08-15 | 中电科华云信息技术有限公司 | Software test service implementing method and system based on virtualization |
| CN108664324B (en) * | 2017-03-30 | 2022-02-01 | 微软技术许可有限责任公司 | Update log for cloud service instance allocation |
| CN108664324A (en) * | 2017-03-30 | 2018-10-16 | 微软技术许可有限责任公司 | The Update log of cloud service example allocation |
| CN107133096A (en) * | 2017-04-13 | 2017-09-05 | 新华三技术有限公司 | A kind of resource allocation methods and device |
| CN109426647A (en) * | 2017-08-30 | 2019-03-05 | 英特尔公司 | For coordinating the technology of the accelerator installation resource of depolymerization |
| CN107995269A (en) * | 2017-11-24 | 2018-05-04 | 合肥博焱智能科技有限公司 | A kind of resource dynamic distributing method based on cloud computing platform |
| CN109491798A (en) * | 2018-11-27 | 2019-03-19 | 郑州云海信息技术有限公司 | A kind of method and device of resource allocation |
| CN109697107A (en) * | 2018-12-18 | 2019-04-30 | 山东超越数控电子股份有限公司 | A kind of method and realization system of self-service resource bid |
| CN111858014A (en) * | 2019-04-24 | 2020-10-30 | 中国移动通信集团河北有限公司 | Resource allocation method and device |
| CN112565320A (en) * | 2019-09-25 | 2021-03-26 | 大唐移动通信设备有限公司 | Load balancing method and device |
| CN110740194B (en) * | 2019-11-18 | 2020-11-20 | 南京航空航天大学 | Micro-service combination method based on cloud edge fusion and application |
| CN110740194A (en) * | 2019-11-18 | 2020-01-31 | 南京航空航天大学 | Micro-service combination method based on cloud edge fusion and application |
| CN110717761A (en) * | 2019-12-12 | 2020-01-21 | 腾讯科技（深圳）有限公司 | Data processing method and device and computer storage medium |
| CN111158595A (en) * | 2019-12-27 | 2020-05-15 | 中国建设银行股份有限公司 | Enterprise-level heterogeneous storage resource scheduling method and system |
| CN111158595B (en) * | 2019-12-27 | 2023-05-23 | 中国建设银行股份有限公司 | Enterprise-level heterogeneous storage resource scheduling method and system |
| CN111459656A (en) * | 2020-03-06 | 2020-07-28 | 北京百度网讯科技有限公司 | Server management method and device, electronic equipment and storage medium |
| CN111459656B (en) * | 2020-03-06 | 2023-11-03 | 北京百度网讯科技有限公司 | Server management method, device, electronic equipment and storage medium |
| CN111399985B (en) * | 2020-03-19 | 2021-02-19 | 国网山东省电力公司 | Load balancing method based on storage difference iteration in cloud computing environment |
| CN111399985A (en) * | 2020-03-19 | 2020-07-10 | 国网山东省电力公司 | Load balancing method based on storage difference iteration in cloud computing environment |
| CN112584526A (en) * | 2020-12-08 | 2021-03-30 | 厦门诚创网络股份有限公司 | Resource allocation method and system |
| CN114157701B (en) * | 2021-11-19 | 2023-11-28 | 北京百度网讯科技有限公司 | Task testing method, device, equipment and storage medium |
| CN114157701A (en) * | 2021-11-19 | 2022-03-08 | 北京百度网讯科技有限公司 | Task testing method, device, equipment and storage medium |
| CN114691992A (en) * | 2022-03-29 | 2022-07-01 | 阿里云计算有限公司 | Cloud product recommendation and display method, system, equipment and storage medium |
| CN117435298A (en) * | 2023-10-16 | 2024-01-23 | 常州大数据有限公司 | Data center energy efficiency intelligent tuning cloud platform based on large language model |
| CN117435298B (en) * | 2023-10-16 | 2024-05-28 | 常州大数据有限公司 | Data center energy efficiency intelligent tuning cloud platform based on large language model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103634330A (en) | Automatic resource distribution method in cloud calculation environment | |
| CN103426072B (en) | The order processing system of a kind of high concurrent competition stock and disposal route thereof | |
| CN104239141B (en) | Optimizing and scheduling task method based on workflow critical path in data center | |
| Shi et al. | Empirical evaluation of vector bin packing algorithms for energy efficient data centers | |
| US8380557B2 (en) | Multi-tenant database management for service level agreement (SLA) profit maximization | |
| JP5244236B2 (en) | Computer system, method, and program | |
| CN104601664B (en) | A kind of control system of cloud computing platform resource management and scheduling virtual machine | |
| US20110167034A1 (en) | System and method for metric based allocation of costs | |
| Karsten et al. | Inventory pooling games for expensive, low‐demand spare parts | |
| US8788315B2 (en) | Systems and methods for determining pack allocations | |
| CN103491024B (en) | Job scheduling method and device for streaming data | |
| JP5841240B2 (en) | Method and system for an improved reservation system that optimizes repeated search requests | |
| CN104679594B (en) | A kind of middleware distributed computing method | |
| CN102611735A (en) | Load balancing method and system of application services | |
| CN106407207A (en) | Real-time added data updating method and apparatus | |
| CN104023042B (en) | Cloud platform resource scheduling method | |
| US20120179507A1 (en) | Systems And Methods For Determining Pack Allocations | |
| CN110149394A (en) | Dispatching method, device and the storage medium of system resource | |
| CN108647081A (en) | Empty machine resource automatic distribution system based on order | |
| Xiao et al. | A priority based scheduling strategy for virtual machine allocations in cloud computing environment | |
| CN102629220A (en) | Dynamic task allocation and management method | |
| CN108737462A (en) | A kind of cloud computation data center method for scheduling task based on graph theory | |
| CN101963969A (en) | Method and database server for realizing load balancing in Oracle RAC (Real Application Cluster) system | |
| Babu et al. | Virtual machine placement for improved quality in IaaS cloud | |
| CN106233256A (en) | Utilize the scalable storage of load balance optimizing module |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140312 |