CN108897606A - Multi-tenant container cloud platform virtual network resource self-adapting dispatching method and system - Google Patents
Multi-tenant container cloud platform virtual network resource self-adapting dispatching method and system Download PDFInfo
- Publication number
- CN108897606A CN108897606A CN201810827859.8A CN201810827859A CN108897606A CN 108897606 A CN108897606 A CN 108897606A CN 201810827859 A CN201810827859 A CN 201810827859A CN 108897606 A CN108897606 A CN 108897606A
- Authority
- CN
- China
- Prior art keywords
- tenant
- container
- cloud
- data center
- resource
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/24—Accounting or billing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5011—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resources being hardware resources other than CPUs, Servers and Terminals
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/02—Details
- H04L12/14—Charging, metering or billing arrangements for data wireline or wireless communications
- H04L12/1403—Architecture for metering, charging or billing
- H04L12/1407—Policy-and-charging control [PCC] architecture
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M15/00—Arrangements for metering, time-control or time indication ; Metering, charging or billing arrangements for voice wireline or wireless communications, e.g. VoIP
- H04M15/66—Policy and charging system
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M15/00—Arrangements for metering, time-control or time indication ; Metering, charging or billing arrangements for voice wireline or wireless communications, e.g. VoIP
- H04M15/70—Administration or customization aspects; Counter-checking correct charges
- H04M15/765—Linked or grouped accounts, e.g. of users or devices
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M15/00—Arrangements for metering, time-control or time indication ; Metering, charging or billing arrangements for voice wireline or wireless communications, e.g. VoIP
- H04M15/70—Administration or customization aspects; Counter-checking correct charges
- H04M15/785—Reserving amount on the account
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M15/00—Arrangements for metering, time-control or time indication ; Metering, charging or billing arrangements for voice wireline or wireless communications, e.g. VoIP
- H04M15/80—Rating or billing plans; Tariff determination aspects
- H04M15/8016—Rating or billing plans; Tariff determination aspects based on quality of service [QoS]
-
- 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
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
- G06F2009/4557—Distribution of virtual machine instances; Migration and load balancing
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Quality & Reliability (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention belongs to network technique fields, disclose a kind of multi-tenant container cloud platform virtual network resource self-adapting dispatching method and system, data center's selection strategy based on availability and user preference, using container between the communication path description container, from the available alternate data centralization of cloud service provider, each tenant is assigned to nearest data center, determines that multi-tenant data places optimal data center's subset；Carry out the Internet resources adaptive scheduling mechanism under server selection policies and multi-tenant container cloud data center based on effectiveness.The present invention proposes under a kind of cloud service environment of multi-tenant multiple data centers, carry out adaptive scheduling in container cloud platform between various Internet resources in a collaborative manner, the overall situation considers the network resource management problem under cloud computing environment, under the premise of guaranteeing service-level agreement, the balance of interest of cloud service both sides of supply and demand is realized.
Description
Technical field
The invention belongs to network technique field more particularly to a kind of multi-tenant container cloud platform virtual network resource are adaptive
Dispatching method and system.
Background technique
Currently, the prior art commonly used in the trade is such：
Cloud broker is to provide a kind of new trend of service using cloudy and mixed cloud in recent years for user, and be proposed as
A kind of basic cloud service mode, by renting the progress cloud network selection of cloud service provider example and being multiplexed relatively small
Tenant's demand is minimized with cost of implementation and profit maximization.
Multi-tenant multiple data centers select to share 9 tenants and 10 data centers in common scene, across 4 continents.
Different tenants carries out multiple data centers selection according to data center's availability and itself preference, and the prior art only uses a data
The mechanism at center is not able to satisfy the demand of aggregation of data analysis, it cannot be guaranteed that faster local data analysis.
In conclusion problem of the existing technology is：
(1) prior art only uses the mechanism of a data center, is not able to satisfy the demand of aggregation of data analysis, and cannot
Guarantee faster local data analysis, and does not have more inexpensive.
(2) the prior art does not consider that reserved and real time resources price variances, can not reflect tenant's demand in time
Dynamic characteristic.
(3) it is confined to be selected in multiple cloud platforms that the same cloud service provider possesses, it is difficult to take in multiple clouds
It is unfolded between business provider.
Solve the difficulty and meaning of above-mentioned technical problem：
It is in large scale, high failure rate：The number of servers interconnected in current publicly-owned cloud data center is more than 105Quantity
Grade, the quantity of switching node also reach 104The order of magnitude, the increasingly huge data center of scale is to the network architecture, transport protocol
And system administration is proposed new requirement.Moreover, network failure rates can increase and rapid growth with system scale, wherein
Especially with the failure of network configuration failure (accounting for 38%) and unknown cause, (such as interchanger stops forwarding flow suddenly, accounts for 23%) most
It is significant.
Flow is complicated, and Longitudinal Extension is at high cost：Since height happens suddenly, Incast caused by the many-one communication mode of high dynamic
Problem, the development of the compute-intensive applications such as MapReduce, Hadoop and being widely used for virtualization technology, are not only caused
The complexity of network-flow characteristic, and bring serious traffic load.Simultaneously as data center's " east-west traffic " accounts for
According to relatively high and tree structure convergence ratio problem, cause data center's Longitudinal Extension cost extremely expensive, it is unsustainable.
Resource utilization is low, comes in every shape：Conventional data exchange (such as VLAN) and communication identifier (such as IP) technology are effectively kept away
Multiple applications interfering with each other when disposing simultaneously in Mian Liao data center, but also limit simultaneously Internet resources be multiplexed it is flexible
Property, cause the utilization rate of Internet resources generally lower.In addition, foring and coming in every shape due to the traction by different performance demand
Network coexisted situation, including enhanced ethernet, InfiniBand high speed interconnection storage net and specialized high-speed net etc..
Summary of the invention
In view of the problems of the existing technology, the present invention provides a kind of multi-tenant container cloud platform virtual network resources certainly
Adaption scheduling method and system.
The invention is realized in this way a kind of multi-tenant container cloud platform virtual network resource self-adapting dispatching method, packet
It includes：
Data center's selection strategy based on availability and user preference, using container to [srcDocker,
DstDocker] description container between communication path will be every from the available alternate data centralization of cloud service provider
One tenant assigns to nearest data center, determines that multi-tenant data places optimal data center's subset；
Server selection policies based on effectiveness：Container tenant specifies the effectiveness parameters of application according to application feature,
[α, β] is combined by setting Performance Coefficient, and different grades of network service is provided；
Internet resources adaptive scheduling mechanism under multi-tenant container cloud data center：It is online adaptive based on historical information
Cloud network selection algorithm is answered, resource reservation meter is divided to the historical information estimation that cloud service provider resource uses according to each tenant
Take cycle TiWith resource multiplex charging time slot τi；If niThe instance number that charging time slot enables, C are multiplexed for i-thiIt is multiplexed for i-th
The total cost of charging time slot, then the optimization aim of the online adaptive cloud network selection algorithm based on historical information is according to tenant
Historical information determines longest resource reservation metering period and resource multiplex charging time slot τi。
Further, [srcDocker, dstDocker] is described using container in the communication path between container, container is to i
Number of paths be expressed as pi, the bandwidth of the container pair is distributed to by vectorIt indicates, x in formulaij
Indicate i-th of container to the bandwidth distributed on the j of path；The number of current data centre point device pair is n, global bandwidth distribution
Vector is expressed asRoute matrix is expressed as：
Further, in the server selection policies based on effectiveness, container tenant is according to the specified application of application feature
Effectiveness parameters, format be under [ApplicationID, srcDocker, dstDocker, Bmin, α, β], B in formulaminIndicate application
Minimum bandwidth requirement, α and β respectively indicate the handling capacity and delay sensitive coefficient of application, combined by setting Performance Coefficient [α,
β] different grades of network service is provided, Efficiency Function is：
In formula, u represents container to the set of paths used；The link set that v delegated path uses；xkwIt represents on link w
Distribute to the bandwidth using k, 1/ γwIndicate the congestion time delay desired value on link w；Performance Coefficient αkAnd βkIt respectively represents using k
Handling capacity and delay sensitive characteristic.
Further, the Internet resources adaptive scheduling mechanism under multi-tenant container cloud data center further includes：System is built
Mould：Own cost is reduced using the price variance between resource reservation and real-time rental.
Realize that the multi-tenant container cloud platform virtual network resource is adaptive another object of the present invention is to provide a kind of
Answer the computer program of dispatching method.
Realize that the multi-tenant container cloud platform virtual network resource is adaptive another object of the present invention is to provide a kind of
Answer the information data processing terminal of dispatching method.
Another object of the present invention is to provide a kind of computer readable storage mediums, including instruction, when it is in computer
When upper operation, so that computer executes multi-tenant container cloud platform virtual network resource self-adapting dispatching method described in item.
Realize that the multi-tenant container cloud platform virtual network resource is adaptive another object of the present invention is to provide a kind of
The multi-tenant container cloud platform virtual network resource self-adapting dispatching system of dispatching method is answered, including：
Data center's selection strategy unit based on availability and user preference, using container to [srcDocker,
DstDocker] description container between communication path will be every from the available alternate data centralization of cloud service provider
One tenant assigns to nearest data center, determines that multi-tenant data places optimal data center's subset；
Server selection policies unit based on effectiveness：Container tenant joins according to the efficiency of the specified application of application feature
Number combines [α, β] by setting Performance Coefficient and provides different grades of network service；
Internet resources adaptive scheduling mechanism unit under multi-tenant container cloud data center, based on the online of historical information
It is pre- to divide resource to the historical information estimation that cloud service provider resource uses according to each tenant for adaptive cloud network selection algorithm
Stay metering period TiWith resource multiplex charging time slot τi；If niThe instance number that charging time slot enables, C are multiplexed for i-thiIt is i-th
It is multiplexed the total cost of charging time slot, then according to the optimization aim of the online adaptive cloud network selection algorithm based on historical information
Tenant's historical information determines longest resource reservation metering period and resource multiplex charging time slot τi。
Another object of the present invention is to provide one kind equipped with the multi-tenant container cloud platform virtual network resource from
The network billing platforms of adaption scheduling system.
In conclusion advantages of the present invention and good effect are：
The present invention proposes under a kind of cloud service environment of multi-tenant multiple data centers, various Internet resources in container cloud platform
Between carry out adaptive scheduling in a collaborative manner, the overall situation considers the network resource management problem under cloud computing environment, is guaranteeing to take
Under the premise of level protocol of being engaged in, the balance of interest of cloud service both sides of supply and demand is realized.
The present invention is quasi- to divide resource reservation meter to the historical information estimation that cloud service provider resource uses according to each tenant
Take cycle TiWith resource multiplex charging time slot τi.If setting niThe instance number that charging time slot enables, C are multiplexed for i-thiIt is multiple for i-th
The total cost for time-consuming gap of using tricks, then the optimization aim of algorithm is that longest resource reservation charging week is determined according to tenant's historical information
Phase and resource multiplex charging time slot τi, so that the Income Maximum of cloud broker.
With only with the mechanism of a data center compared with, the present invention is not only able to satisfy number using the mechanism of multiple data centers
According to the demand of comprehensive analysis, and it can guarantee faster local data analysis and have more inexpensive.
Detailed description of the invention
Fig. 1 is multi-tenant container cloud platform virtual network resource self-adapting dispatching method process provided in an embodiment of the present invention
Figure.
Fig. 2 is data center's tree topology figure that Fat-Tree provided in an embodiment of the present invention is Typical Representative.
Fig. 3 is cloud broker network resource multiplex mode exemplary diagram provided in an embodiment of the present invention.
Fig. 4 is multi-tenant container cloud platform virtual network resource self-adapting dispatching system signal provided in an embodiment of the present invention
Figure.
In figure：1, data center's selection strategy unit based on availability and user preference；2, based on the clothes of effectiveness
Business device selection strategy unit；3, the Internet resources adaptive scheduling mechanism unit under multi-tenant container cloud data center.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to embodiments, to the present invention
It is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not used to
Limit the present invention.
The prior art only uses the mechanism of a data center, is not able to satisfy the demand of aggregation of data analysis, and cannot protect
Faster local data analysis is demonstrate,proved, and is not had more inexpensive.
Multi-tenant container cloud platform virtual network resource self-adapting dispatching method provided in an embodiment of the present invention, including：
S101：Data center's selection strategy based on availability and user preference, using container between logical description container
Believe that each tenant is assigned to nearest data from the available alternate data centralization of cloud service provider by path
Center determines that multi-tenant data places optimal data center's subset；
S102：Server selection policies based on effectiveness：Container tenant is according to the specified efficiency applied of application feature
Parameter is combined by setting Performance Coefficient and provides different grades of network service；
S103：Internet resources adaptive scheduling mechanism under multi-tenant container cloud data center：Based on historical information
The adaptive cloud network selection algorithm of line divides resource to the historical information estimation that cloud service provider resource uses according to each tenant
Reserved metering period and resource multiplex charging time slot；It is set as the instance number of i-th of multiplexing charging time slot enabling, for i-th of multiplexing
The total cost of charging time slot, then the optimization aim of the online adaptive cloud network selection algorithm based on historical information is according to tenant
Historical information determines longest resource reservation metering period and resource multiplex charging time slot.
In step S101, the communication path between container is described to [srcDocker, dstDocker] using container, is taken from cloud
The business available alternate data centralization of provider sets out, each tenant is assigned to nearest data center, determines rent more
User data places optimal data center's subset；
In step S102, [α, β] is combined by setting Performance Coefficient, different grades of network service is provided；
Step S103：Resource reservation meter is divided to the historical information estimation that cloud service provider resource uses according to each tenant
Take cycle T i and resource multiplex charging time slot τi；If ni is the instance number that i-th of multiplexing charging time slot enables, Ci is multiple i-th
The total cost for time-consuming gap of using tricks, then the optimization aim of the online adaptive cloud network selection algorithm based on historical information is according to rent
Family historical information determines longest resource reservation metering period and resource multiplex charging time slot τi。
Below with reference to concrete analysis, the invention will be further described.
One, data center's selection strategy based on availability and user preference：
Multi-tenant multiple data centers select to share 9 tenants and 10 data centers in common scene, across 4 continents.
Different tenants carries out multiple data centers selection according to data center's availability and itself preference, and only with data center
Mechanism is compared, and the demand of aggregation of data analysis is not only able to satisfy using the mechanism of multiple data centers, but also can guarantee faster
Local data analysis simultaneously has more inexpensive.
By taking Fat-Tree is as shown in Figure 2 for data center's tree topology of Typical Representative as an example, by access layer, convergence
Layer and core layer are constituted.Wherein the communication path quantity across container cluster is determined by core layer switch quantity, and in container cluster
Communication path quantity is determined by the interchanger quantity of convergence layer in cluster.
The topological structure can be described with the non-directed graph G=(N, L) of cum rights, and wherein N indicates interchanger set；L=1,
2..., l } (l >=2) expression physics link set；The bandwidth capacity and residual capacity of link use vector respectivelyWithIt indicates.
The present invention is intended that with container to the communication path between [srcDocker, dstDocker] description container, if container is to i
Available number of paths is expressed as pi, then the bandwidth for distributing to the container pair can be by vectorTable
Show, x in formulaijIndicate i-th of container to the bandwidth distributed on the j of path.Assuming that the number of current data centre point device pair is
N, then global bandwidth allocation vector is represented byRoute matrix is represented by：
The data that the present invention plans each tenant are only stored in a data center, it is made to meet following target：
Preference data is placed：Maximum weighted between tenant and selected data center is apart from minimization.
Transmission cost minimizes data and places：Weighted distance and minimization between tenant and selected data center.
Fair data are placed：Maximum distance minimization between tenant and selected data center.
Totle drilling cost minimization：The sum of tenant's cost minimization.
Based on the above target, the present invention is quasi- from the available alternate data centralization of cloud service provider, it is intended to will
Each tenant assigns to the data center of (totle drilling cost i.e. between user and selected data center is minimum) recently, more with determination
Tenant data places optimal data center's subset.
Two, based on the server selection policies of effectiveness：
In order to provide fine granularity differentiable bandwidth allocation service, the present invention is that container tenant devises one kind based on application
The bandwidth allocation mode of efficiency.Container tenant can be according to application feature come the effectiveness parameters of specified application, and format is as follows
[ApplicationID,srcDocker,dstDocker,Bmin, α, β], B in formulaminIndicate application minimum bandwidth requirement, α and
β respectively indicates the handling capacity and delay sensitive coefficient of application, combines [α, β] by setting Performance Coefficient and provides different grades of net
Network service, the Efficiency Function that the present invention designs are as follows：
In formula, u represents container to the set of paths used；The link set that v delegated path uses；xkwIt represents on link w
Distribute to the bandwidth using k, 1/ γwIndicate the congestion time delay desired value on link w；Performance Coefficient αkAnd βkIt respectively represents using k
Handling capacity and delay sensitive characteristic.The Efficiency Function that the present invention designs is by used all container sets, path and chain
Road codetermines.
Three, the Internet resources adaptive scheduling mechanism under multi-tenant container cloud data center：
By the system of many factors such as virtualization resource pricing method, lease period and across cloud service provider data transmission
About, it is that cloud network selects in current and following one period that cloud broker, which provides service using single cloud service provider example,
Basic mode.Cloud broker passes through the mechanism such as resource reservation and dynamic adjustment and is multiplexed multi-tenant network demand, is ensuring user's clothes
Self benefits are maximized under the premise of business agreement.
Related content of the present invention based on the fact that：
Tenant's demand：According to each tenant's historical information and plan of needs, cloud broker can estimate to rent in a longer term T
The aggregate demand at family, and the increase of total demand curve T at any time is monotonic increase.
Cloud service provider price：The increase strictly monotone increasing of resource reservation expense T at any time, and average cost then with
The increase strictly monotone decreasing of time T.
System modelling：
Due to the dynamic change of tenant's demand, the price variance between cloud broker is rented using resource reservation and in real time is reduced
Own cost, cloud broker frequently with Internet resources multiplex mode example it is as shown in Figure 3.
Online adaptive cloud network selection algorithm based on historical information：
Internet resources multiplex mode according to Fig.3, the present invention is quasi- to make cloud service provider resource according to each tenant
Historical information estimation divides resource reservation metering period TiWith resource multiplex charging time slot τi.If setting niFor i-th of multiplexing meter
The instance number that time-consuming gap enables, CiThe total cost of charging time slot is multiplexed for i-th, then the optimization aim of algorithm is to go through according to tenant
History information determines longest resource reservation metering period and resource multiplex charging time slot τi, so that the Income Maximum of cloud broker.
Such as Fig. 4, the embodiment of the present invention provides a kind of multi-tenant container cloud platform virtual network resource self-adapting dispatching system,
Including：
Data center's selection strategy unit 1 based on availability and user preference, using container to [srcDocker,
DstDocker] description container between communication path will be every from the available alternate data centralization of cloud service provider
One tenant assigns to nearest data center, determines that multi-tenant data places optimal data center's subset；
Server selection policies unit 2 based on effectiveness：Container tenant is according to the specified efficiency applied of application feature
Parameter combines [α, β] by setting Performance Coefficient and provides different grades of network service；
Internet resources adaptive scheduling mechanism unit 3 under multi-tenant container cloud data center, based on historical information
The adaptive cloud network selection algorithm of line divides resource to the historical information estimation that cloud service provider resource uses according to each tenant
Reserved metering period TiWith resource multiplex charging time slot τi；If niThe instance number that charging time slot enables, C are multiplexed for i-thiIt is i-th
The total cost of a multiplexing charging time slot, then the optimization aim of the online adaptive cloud network selection algorithm based on historical information is root
Longest resource reservation metering period and resource multiplex charging time slot τ are determined according to tenant's historical informationi。
In the above-described embodiments, can come wholly or partly by software, hardware, firmware or any combination thereof real
It is existing.When using entirely or partly realizing in the form of a computer program product, the computer program product include one or
Multiple computer instructions.When loading on computers or executing the computer program instructions, entirely or partly generate according to
Process described in the embodiment of the present invention or function.The computer can be general purpose computer, special purpose computer, computer network
Network or other programmable devices.The computer instruction may be stored in a computer readable storage medium, or from one
Computer readable storage medium is transmitted to another computer readable storage medium, for example, the computer instruction can be from one
A web-site, computer, server or data center pass through wired (such as coaxial cable, optical fiber, Digital Subscriber Line (DSL)
Or wireless (such as infrared, wireless, microwave etc.) mode is carried out to another web-site, computer, server or data center
Transmission).The computer-readable storage medium can be any usable medium or include one that computer can access
The data storage devices such as a or multiple usable mediums integrated server, data center.The usable medium can be magnetic Jie
Matter, (for example, floppy disk, hard disk, tape), optical medium (for example, DVD) or semiconductor medium (such as solid state hard disk Solid
State Disk (SSD)) etc..
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Made any modifications, equivalent replacements, and improvements etc., should all be included in the protection scope of the present invention within mind and principle.
Claims (8)
1. a kind of multi-tenant container cloud platform virtual network resource self-adapting dispatching method, which is characterized in that the multi-tenant is held
Device cloud platform virtual network resource self-adapting dispatching method includes：
Data center's selection strategy based on availability and user preference, retouches [srcDocker, dstDocker] using container
The communication path between container is stated, from the available alternate data centralization of cloud service provider, each tenant is assigned
To nearest data center, determine that multi-tenant data places optimal data center's subset；
Server selection policies based on effectiveness：Container tenant passes through according to the effectiveness parameters of the specified application of application feature
Performance Coefficient is set, the different grades of network service of [α, β] offer is provided；
Internet resources adaptive scheduling mechanism under multi-tenant container cloud data center：Online adaptive cloud based on historical information
Network selection algorithm divides resource reservation charging week to the historical information estimation that cloud service provider resource uses according to each tenant
Phase TiWith resource multiplex charging time slot τi；If niThe instance number that charging time slot enables, C are multiplexed for i-thiFor i-th of multiplexing charging
The total cost of time slot, then the optimization aim of the online adaptive cloud network selection algorithm based on historical information is according to tenant's history
Information determines longest resource reservation metering period and resource multiplex charging time slot τi。
2. multi-tenant container cloud platform virtual network resource self-adapting dispatching method as described in claim 1, which is characterized in that
[srcDocker, dstDocker] is described using container in the communication path between container, container is expressed as the number of paths of i
pi, the bandwidth of the container pair is distributed to by vectorIt indicates, x in formulaijIndicate i-th of container pair
The bandwidth distributed on the j of path；The number of current data centre point device pair is n, and global bandwidth allocation vector is expressed asRoute matrix is expressed as：
3. multi-tenant container cloud platform virtual network resource self-adapting dispatching method as described in claim 1, which is characterized in that
In server selection policies based on effectiveness, effectiveness parameters of the container tenant according to the specified application of application feature, lattice
Formula be under [ApplicationID, srcDocker, dstDocker, Bmin, α, β], B in formulaminIndicate that the minimum bandwidth of application needs
Ask, α and β respectively indicate the handling capacity and delay sensitive coefficient of application, by setting Performance Coefficient combine [α, β] provide it is different etc.
The network service of grade, Efficiency Function are：
In formula, u represents container to the set of paths used；The link set that v delegated path uses；xkwIt represents and is distributed on link w
To the bandwidth of application k, 1/ γwIndicate the congestion time delay desired value on link w；Performance Coefficient αkAnd βkRespectively represent gulping down using k
The amount of spitting and delay sensitive characteristic.
4. multi-tenant container cloud platform virtual network resource adaptive scheduling described in a kind of realization claims 1 to 3 any one
The computer program of method.
5. multi-tenant container cloud platform virtual network resource adaptive scheduling described in a kind of realization claims 1 to 3 any one
The information data processing terminal of method.
6. a kind of computer readable storage medium, including instruction, when run on a computer, so that computer is executed as weighed
Benefit requires multi-tenant container cloud platform virtual network resource self-adapting dispatching method described in 1-3 any one.
7. a kind of multi-tenant for realizing multi-tenant container cloud platform virtual network resource self-adapting dispatching method described in claim 1
Container cloud platform virtual network resource self-adapting dispatching system, which is characterized in that the multi-tenant container cloud platform virtual network
Resource-adaptive dispatches system：
Data center's selection strategy unit based on availability and user preference, using container to [srcDocker,
DstDocker] description container between communication path will be every from the available alternate data centralization of cloud service provider
One tenant assigns to nearest data center, determines that multi-tenant data places optimal data center's subset；
Server selection policies unit based on effectiveness：Container tenant specifies the effectiveness parameters of application according to application feature,
[α, β] is combined by setting Performance Coefficient, and different grades of network service is provided；
Internet resources adaptive scheduling mechanism unit under multi-tenant container cloud data center, it is online adaptive based on historical information
Cloud network selection algorithm is answered, resource reservation meter is divided to the historical information estimation that cloud service provider resource uses according to each tenant
Take cycle TiWith resource multiplex charging time slot τi；If niThe instance number that charging time slot enables, C are multiplexed for i-thiIt is multiplexed for i-th
The total cost of charging time slot, then the optimization aim of the online adaptive cloud network selection algorithm based on historical information is according to tenant
Historical information determines longest resource reservation metering period and resource multiplex charging time slot τi。
8. a kind of network equipped with multi-tenant container cloud platform virtual network resource self-adapting dispatching system described in claim 7
Charging platform.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810827859.8A CN108897606B (en) | 2018-07-25 | 2018-07-25 | Self-adaptive scheduling method and system for virtual network resources of multi-tenant container cloud platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810827859.8A CN108897606B (en) | 2018-07-25 | 2018-07-25 | Self-adaptive scheduling method and system for virtual network resources of multi-tenant container cloud platform |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108897606A true CN108897606A (en) | 2018-11-27 |
| CN108897606B CN108897606B (en) | 2021-06-29 |
Family
ID=64352038
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810827859.8A Active CN108897606B (en) | 2018-07-25 | 2018-07-25 | Self-adaptive scheduling method and system for virtual network resources of multi-tenant container cloud platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108897606B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109669946A (en) * | 2018-12-14 | 2019-04-23 | 中南设计集团（武汉）工程技术研究院有限公司 | A kind of complicated permission system data isolation system and method based on mass users |
| CN110740168A (en) * | 2019-09-24 | 2020-01-31 | 安徽大学 | Self-adaptive method for multi-tenant server in cloud |
| CN111800284A (en) * | 2019-04-08 | 2020-10-20 | 阿里巴巴集团控股有限公司 | Method and device for selecting edge cloud node set and electronic equipment |
| CN112202688A (en) * | 2020-09-22 | 2021-01-08 | 临沂大学 | Data evacuation method and system suitable for cloud data center network |
| WO2021104451A1 (en) * | 2019-11-27 | 2021-06-03 | 华为技术有限公司 | Sharing method and apparatus for multi-account cloud service usage package and related device |
| CN115037956A (en) * | 2022-06-06 | 2022-09-09 | 天津大学 | Traffic scheduling method for cost optimization of edge server |
| WO2023005993A1 (en) * | 2021-07-30 | 2023-02-02 | 华为技术有限公司 | Method and apparatus for selecting cloud platform, and device, and medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102651775A (en) * | 2012-03-05 | 2012-08-29 | 国家超级计算深圳中心(深圳云计算中心) | Method, equipment and system for managing shared objects of a plurality of lessees based on cloud computation |
| CN105554015A (en) * | 2015-12-31 | 2016-05-04 | 北京轻元科技有限公司 | Management network and method for multi-tenant container cloud computing system |
| CN105610715A (en) * | 2016-03-14 | 2016-05-25 | 山东大学 | Cloud data center multi-virtual machine migration scheduling method based on SDN (Software Defined Network) |
| CN105812222A (en) * | 2016-03-10 | 2016-07-27 | 汉柏科技有限公司 | Multi-tenant virtual network and realization method based on virtual machine and container |
| US20160218948A1 (en) * | 2015-01-26 | 2016-07-28 | Ciena Corporation | Dynamic policy engine for multi-layer network management |
| CN106131158A (en) * | 2016-06-30 | 2016-11-16 | 上海天玑科技股份有限公司 | Resource scheduling device based on cloud tenant's credit rating under a kind of cloud data center environment |
| CN106453492A (en) * | 2016-08-30 | 2017-02-22 | 浙江大学 | Docker container cloud platform container scheduling method based on fuzzy mode recognition |
| CN107222531A (en) * | 2017-05-23 | 2017-09-29 | 北京科技大学 | A kind of container cloud resource dispatching method |
-
2018
- 2018-07-25 CN CN201810827859.8A patent/CN108897606B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102651775A (en) * | 2012-03-05 | 2012-08-29 | 国家超级计算深圳中心(深圳云计算中心) | Method, equipment and system for managing shared objects of a plurality of lessees based on cloud computation |
| US20160218948A1 (en) * | 2015-01-26 | 2016-07-28 | Ciena Corporation | Dynamic policy engine for multi-layer network management |
| CN105554015A (en) * | 2015-12-31 | 2016-05-04 | 北京轻元科技有限公司 | Management network and method for multi-tenant container cloud computing system |
| CN105812222A (en) * | 2016-03-10 | 2016-07-27 | 汉柏科技有限公司 | Multi-tenant virtual network and realization method based on virtual machine and container |
| CN105610715A (en) * | 2016-03-14 | 2016-05-25 | 山东大学 | Cloud data center multi-virtual machine migration scheduling method based on SDN (Software Defined Network) |
| CN106131158A (en) * | 2016-06-30 | 2016-11-16 | 上海天玑科技股份有限公司 | Resource scheduling device based on cloud tenant's credit rating under a kind of cloud data center environment |
| CN106453492A (en) * | 2016-08-30 | 2017-02-22 | 浙江大学 | Docker container cloud platform container scheduling method based on fuzzy mode recognition |
| CN107222531A (en) * | 2017-05-23 | 2017-09-29 | 北京科技大学 | A kind of container cloud resource dispatching method |
Non-Patent Citations (1)
| Title |
|---|
| 冯文超: "容器云平台网络资源配置管理系统的设计", 《工业仪表与自动化装置》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109669946A (en) * | 2018-12-14 | 2019-04-23 | 中南设计集团（武汉）工程技术研究院有限公司 | A kind of complicated permission system data isolation system and method based on mass users |
| CN111800284A (en) * | 2019-04-08 | 2020-10-20 | 阿里巴巴集团控股有限公司 | Method and device for selecting edge cloud node set and electronic equipment |
| CN110740168A (en) * | 2019-09-24 | 2020-01-31 | 安徽大学 | Self-adaptive method for multi-tenant server in cloud |
| CN110740168B (en) * | 2019-09-24 | 2022-06-03 | 安徽大学 | Self-adaptive method for multi-tenant server in cloud |
| WO2021104451A1 (en) * | 2019-11-27 | 2021-06-03 | 华为技术有限公司 | Sharing method and apparatus for multi-account cloud service usage package and related device |
| CN112202688A (en) * | 2020-09-22 | 2021-01-08 | 临沂大学 | Data evacuation method and system suitable for cloud data center network |
| WO2023005993A1 (en) * | 2021-07-30 | 2023-02-02 | 华为技术有限公司 | Method and apparatus for selecting cloud platform, and device, and medium |
| CN115037956A (en) * | 2022-06-06 | 2022-09-09 | 天津大学 | Traffic scheduling method for cost optimization of edge server |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108897606B (en) | 2021-06-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108897606A (en) | Multi-tenant container cloud platform virtual network resource self-adapting dispatching method and system | |
| US9497139B2 (en) | Client-allocatable bandwidth pools | |
| US9154589B1 (en) | Bandwidth-optimized cloud resource placement service | |
| US10552221B2 (en) | Systems, apparatus and methods for managing resources in computer systems | |
| US9306870B1 (en) | Emulating circuit switching in cloud networking environments | |
| Popa et al. | FairCloud: Sharing the network in cloud computing | |
| Hong et al. | Achieving high utilization with software-driven WAN | |
| CN105191214A (en) | Network bandwidth allocation in multi-tenancy cloud computing networks | |
| US10846788B1 (en) | Resource group traffic rate service | |
| Shi et al. | An online auction mechanism for dynamic virtual cluster provisioning in geo-distributed clouds | |
| Wanis et al. | Efficient modeling and demand allocation for differentiated cloud virtual-network as-a service offerings | |
| Leivadeas et al. | Dynamic traffic steering of multi-tenant virtualized network functions in SDN enabled data centers | |
| Weinman | The future of cloud computing | |
| Chen et al. | A case for pricing bandwidth: Sharing datacenter networks with cost dominant fairness | |
| Divakaran et al. | Probabilistic-bandwidth guarantees with pricing in data-center networks | |
| Shi et al. | An online mechanism for dynamic virtual cluster provisioning in geo-distributed clouds | |
| Datar et al. | A mechanism for price differentiation and slicing in wireless networks | |
| Zhang et al. | Price and QoS competition in data communication services | |
| Paganelli et al. | Profit-aware placement of multi-flavoured VNF chains | |
| Naudts et al. | A dynamic pricing algorithm for a network of virtual resources | |
| Toka et al. | On pricing of 5g services | |
| Narman et al. | DDSS: Dynamic dedicated servers scheduling for multi priority level classes in cloud computing | |
| Hoshino et al. | An on-line algorithm to determine the location of the server in a server migration service | |
| Elkael et al. | Joint placement, routing and dimensioning at the network edge for energy minimization | |
| Datar | Resource allocation and pricing in 5g network slicing |
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 |