CN107908457A - A kind of containerization cloud resource distribution method based on stable matching - Google Patents
A kind of containerization cloud resource distribution method based on stable matching Download PDFInfo
- Publication number
- CN107908457A CN107908457A CN201711089127.5A CN201711089127A CN107908457A CN 107908457 A CN107908457 A CN 107908457A CN 201711089127 A CN201711089127 A CN 201711089127A CN 107908457 A CN107908457 A CN 107908457A
- Authority
- CN
- China
- Prior art keywords
- container
- mrow
- virtual machine
- msub
- angle value
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of containerization cloud resource distribution method based on stable matching, traditional stable marriage matching algorithm is improved to a kind of many-to-one stable matching algorithm, and generate list of preferences using the common similarity algorithm in machine learning as the preference rules of stable matching algorithm, to realize the load balancing of containerization cloud environment, the energy consumption of data center is reduced.The invention belongs to a kind of centralized scheduling algorithm, during to resource allocation, to weigh four class resources of virtual machine utilization rates of each cloud computing node, and the influence that it is matched with task-cycle to be allocated and therefore can be produced to total system energy consumption.The present invention is proposed in a kind of cloud computing system under container virtualization technology, a kind of optimization algorithm distribution of task level container being deployed on system-level virtual machine, by improving resource utilization on server and virtual machine level, energy optimization in containerization cloud environment is solved the problems, such as.
Description
Technical field
The present invention relates to a kind of containerization cloud resource distribution method based on stable matching, and in particular to a kind of empty in container
The resource allocation methods based on system entirety energy optimization under planization technology, belong to the virtual resource allocation technology neck of cloud computing
Domain.
Background technology
Container virtualization technology gradually receives extensive use, and traditional virtual machine technique (Virtual in recent years
Machine) similar, containerization technique provides a kind of virtual environment of isolation, simultaneously because their low overheads and lightweight carry
The high efficiency of resource utilization.Further, since container shares host operating system kernel, its allocation problem is fundamentally main
It is a kind of problem of management of software.Container technique is considered as next important directions of cloud computing development, and existing at present
Most of research is primarily directed to the virtualization cloud computing technology of virtual machine, allocation algorithm and its property to container virtual resource
The research of energy is still an open problem, is based especially on the resource allocation of containerization cloud computing system entirety energy optimization
With Research of Scheduling Method also in the stage of discussion.
With the development of virtual technology, the container of OS-Level virtual becomes the virtual resource deployment in cloud computing
Mainstream, container are to service the major deployments model also increasingly popularized and become in cloud computing environment, but for the resource of container
Distribution technique is not yet sufficiently studied, and number of containers is numerous in containerization cloud environment, how that numerous containers is quickly high
Effect being deployed on suitable virtual machine and achieve the purpose that it is a kind of reduction consumption of data center have become one it is urgently to be resolved hurrily
The problem of.
The content of the invention
The technical problems to be solved by the invention are:A kind of containerization cloud resource distribution side based on stable matching is provided
Method, by the suitable system-level virtual machine of task level container being deployed to rapidly and efficiently, realizes the mesh for reducing consumption of data center
's.
The present invention uses following technical scheme to solve above-mentioned technical problem:
A kind of containerization cloud resource distribution method based on stable matching, including task distributor end take with that can distribute container
Virtual generator terminal two parts of business;
Wherein, task distributor end comprises the following steps:
Step 1-1, initialization task distributor, obtains the remaining allowable resources of all virtual machines;
Step 1-2, the container service to be allocated for reaching task distributor is stored in its caching, and according to appearance to be allocated
The sequencing that device service reaches establishes one and treats that deployment container queue L=[L (i), i=1,2 ..., m], L (i) are represented i-th
Container service to be allocated, m are the number of container service to be allocated;
Step 1-3, if treating deployment container queue not empty, to each container service L (i) to be allocated in the queue, meter
Its matching angle value with all virtual machines for being subjected to the container services is calculated, and will match that angle value is descending to be ranked up, root
Virtual machine queue P can be distributed by establishing one according to ranking resultsi;Make i=1;
Step 1-4, reading are treated to distribute virtual fleet corresponding to i-th of container service to be allocated in deployment container queue
Arrange Pi, since with the highest virtual machine of matching angle value of i-th of container service to be allocated, receive its void to never refusal
Plan machine sends container deployment request, if being rejected receiving, continues to queue PiIn next virtual machine send container deployment
Request receives or postpones to receive deployment request until there is virtual machine to reply;
Step 1-5, by i=i+1 and checks whether traversal queue L, the return to step 1-4 if not traveling through, otherwise enters step
Rapid 1-6;
Step 1-6, task distributor, which is sent, terminates deployment message to all virtual machines signal knots for distributing container service
The resource matched process of beam, if the message authentication for receiving all virtual machines terminates or waits time-out, enters step 1-7;
Step 1-7, task distributor termination receives the container service ID matched and is mapped with virtual machine, and return to step 1-
1;
The virtual generator terminal that container service can be distributed comprises the following steps:
Step 2-1, initializes the best match angle value M of all virtual machinesp=0, and the container service ID of record is gathered
Empty;
Step 2-2, waits task distributor to send message, judges if the message of task distributor is received:If
Terminate deployment message or virtual machine waits time-out, then enter step 2-5;Entered step if message is container deployment request
2-3;
Step 2-3, when virtual machine receives container deployment request, calculates the appearance that container deployment request is sent to the virtual machine
The power consumption matching angle value M of device servicebIf power consumption matching angle value is less than or equal to best match angle value, return to step 2-2, if
Power consumption matching angle value is more than best match angle value, then the best match angle value of the virtual machine is updated to Mb, and record corresponding
The ID of container service;
Step 2-4, the container service for being recorded ID is sent out labeled as postponement receiving vessel service, while by ID and its mark
Task distributor is given, is then back to step 2-2;
Step 2-5, current markers are changed to receive to postpone the state of container service received, and by container service ID with
Virtual machine mapping relations are sent to task distributor, send and confirm to terminate deployment message to task distributor, and start to perform sheet
Take turns the deployment of container service, return to step 2-1 after deployment.
As a preferred embodiment of the present invention, the computational methods that angle value is matched described in step 1-3 are Tanimoto coefficients
Computational methods.
As a preferred embodiment of the present invention, the calculation formula of the Tanimoto coefficient calculation methods is:
Wherein, T (x, y) represents the matching angle value of virtual machine ys of the container service x to be allocated with being subjected to the container service, x
It is four dimensional vectors with y, k=1,2,3,4, represent that container service is required and the available following four profit of virtual machine respectively
With rate:Processor utilization, memory usage, network bandwidth utilization factor, memory space utilization rate.
As a preferred embodiment of the present invention, power consumption matching angle value M described in step 2-3bCalculation formula is:
Wherein, MIPSL(i)Represent processor utilization expected from i-th of container service to be allocated, unit is million instructions
It is per second;TotalMIPS represents the processing speed of the virtual machine, and unit is per second for million instructions.
The present invention compared with prior art, has following technique effect using above technical scheme:
1st, during the present invention is for container deployment, distribution is optimized to the power consumption of system, by using a kind of base
In preference rules of the computational methods as container selection virtual machine of the matching degree of four class virtual resources, and virtual machine is to container
Whether preference rules, then can support the deployment of the container to employ one kind and be based on processor utilization according to the resource of virtual machine
Greedy algorithm preference rules, i.e., the size of processor resource can actually be provided by being accounted for according to processor utilization arranges from high to low
Sequence, so as to improve the execution efficiency of task and minimize system energy consumption.
2nd, the method for the present invention ensure task the stipulated time complete in the case of Optimized Matching container service to be allocated and
Virtual machine so that the deployment of container service task reaches a kind of effect of best match, and then creates higher for cloud computing framework
Benefit.
Brief description of the drawings
Fig. 1 is a kind of system architecture schematic diagram of the containerization cloud resource distribution method based on stable matching of the present invention.
Fig. 2 is the stage A1 flow chart in task distributor tip.
Fig. 3 is the stage A2 flow chart in task distributor tip.
Fig. 4 is the stage A3 flow chart in task distributor tip.
Fig. 5 is can to distribute the stage B1 flow chart of the virtual generator terminal of container service.
Fig. 6 is can to distribute the stage B2 flow chart of the virtual generator terminal of container service.
Embodiment
Embodiments of the present invention are described below in detail, the example of the embodiment is shown in the drawings.Below by
The embodiment being described with reference to the drawings is exemplary, and is only used for explaining the present invention, and is not construed as limiting the claims.
As shown in Figure 1, it is that a kind of system architecture of the containerization cloud resource distribution method based on stable matching of the present invention is shown
It is intended to.The distribution target of cloud computing system of the present invention is that container service is deployed in the virtual machine in system, it is in task point
The algorithm at orchestration end is broadly divided into three phases:
In the stage A1 flow chart of task distributor tip, as shown in Figure 2:
Step A1-1, initialization task distributor, obtains the remaining allowable resource of all virtual machines, it is assumed that assignable
Container number is m.
Step A1-2, the container task for the batch for reaching task distributor is stored in its caching, and is arrived according to task
Container service to be allocated in caching is established one and treats deployment container queue L by the order reached, and the size of the queue is to distribute
Container number m.
If step A1-3, treating deployment container queue L non-NULLs, start to read i-th of unit L (i) in queue, according to such as
Undefined matching similarity algorithm calculates the matching of the container and all virtual machines for being subjected to the container in cloud computing system
Angle value.Mainly using Tanimoto coefficients, its calculation formula is as follows for matching angle value in the present invention:
X represents container service task to be allocated in the present invention, and y represents assignable virtual machine, we define x and y
All it is four dimensional vectors, it is represented respectively, and container service is required and the available following four aspect of virtual machine:Processing
Device utilization rate, memory usage, network bandwidth utilization factor, memory space utilization rate this four variables calculate matching degree, then
Sorted according to the matching angle value and establish one on virtual machine queue P can be distributedi, repeat step A1-3 is until traversal queue L
In all units, subsequently into stage A2.
In the stage A2 flow chart of task distributor tip, as shown in Figure 3:
Step A2-1, i is arranged to 1, reading unit selects to distribute virtual machine queue P in L (i)iMiddle matching angle value
Highest and j-th of virtual machine P for never refusing iti,jContainer deployment request is sent, and the virtual machine is removed into queue Pi。
Step A2-2, to virtual machine queue P can be distributed if asking to refuse to receive (Reject) by the virtual machineiMiddle matching
The angle value virtual machine of next sends container deployment request, if request is postponed receiving (Waiting List) by the virtual machine, by i
Add 1 and check whether traversal queue L, the return to step A2-1 if queue L is not traveled through, if completing traversal queue L enters the stage
A3。
In the stage A3 flow chart of task distributor tip, as shown in Figure 4:
Step A3-1, task distributor sends end deployment message and terminates to all virtual generator terminals signals for distributing container
Resource allocation, if the message authentication for receiving all virtual machines terminates or the wait of task distributor time-out, performs step
A3-2。
Step A3-2, the container matched and virtual machine mapping are sent to task distributor to start to perform container deployment,
Return stage A1 after execution terminates.
Following two benches are broadly divided into the algorithm steps that the virtual generator terminal that can distribute container service synchronously performs:
The stage B1 flow chart of the virtual generator terminal of container service can be being distributed, as shown in Figure 5:
Step B1-1, optimal power matching degree M is initializedpFor 0, assignable Container ID is sky.
Step B1-2, the distribution request of task distributor is waited, if the request that task distributor is initiated is disposed for end
Message or virtual generator terminal wait time-out then to enter stage B2, else if the request of task distributor is distribution request, then enter
Step B1-3.
Step B1-3, the container that distribution request is proposed to the virtual machine is calculated into its power consumption matching angle value MbIts calculation formula
It is as follows, if matching degree MbLess than or equal to best match degree Mp, then simultaneously return to step B1-2 is not changed;If matching degree MbGreatly
In best match degree Mp, enter step B1-4.
Here MIPSL(i)Refer to that its unit of processor utilization is that million instructions are per second expected from i-th of container task,
And what TotalMIPS was represented is that the processing speed unit of the virtual machine is that million instructions are per second.
Step B1-4, best match degree is updated to Mb, and the ID of corresponding container is recorded into
Step B1-5, the Container Tag is distributed to container task, and return to step B1-1 for the postponement of virtual machine.
In the flow chart of the stage B2 for the virtual generator terminal that can distribute container service, as shown in Figure 6:
Step B2-1, the state of container of the current all marks for distribution is changed to receive distribution (Accept), and
The allocation map of final container and virtual machine is issued into task distributor.
Step B2-2, send and confirm to terminate deployment message to task distributor.
Step B2-3, the task deployment of execution epicycle container service is started.
Step B2-4, stage B1 is returned to.
Above example is merely illustrative of the invention's technical idea, it is impossible to protection scope of the present invention is limited with this, it is every
According to technological thought proposed by the present invention, any change done on the basis of technical solution, each falls within the scope of the present invention
Within.
Claims (4)
1. a kind of containerization cloud resource distribution method based on stable matching, it is characterised in that including task distributor end and can
Distribute virtual generator terminal two parts of container service;
Wherein, task distributor end comprises the following steps:
Step 1-1, initialization task distributor, obtains the remaining allowable resources of all virtual machines;
Step 1-2, the container service to be allocated for reaching task distributor is stored in its caching, and is taken according to container to be allocated
The sequencing that business reaches establishes one and treats deployment container queue L=[L (i), i=1,2 ..., m], and L (i) represents to treat for i-th point
Dispensing container service, m are the number of container service to be allocated;
Step 1-3, if treating deployment container queue not empty, to each container service L (i) to be allocated in the queue, calculates it
With the matching angle value of all virtual machines for being subjected to the container services, and it will match that angle value is descending to be ranked up, according to row
Sequence result, which establishes one, can distribute virtual machine queue Pi;Make i=1;
Step 1-4, reading are treated to distribute virtual machine queue P corresponding to i-th of container service to be allocated in deployment container queuei,
Since with the highest virtual machine of matching angle value of i-th of container service to be allocated, receive its virtual machine to never refusal
Container deployment request is sent, if being rejected receiving, is continued to queue PiIn next virtual machine send container deployment request
Receive or postpone to receive deployment request until there is virtual machine to reply;
Step 1-5, by i=i+1 and checks whether traversal queue L, the return to step 1-4 if not traveling through, otherwise enters step 1-
6;
Step 1-6, task distributor, which is sent, terminates deployment message to all virtual machine signal end moneys for distributing container service
Source matching process, if the message authentication for receiving all virtual machines terminates or waits time-out, enters step 1-7;
Step 1-7, task distributor termination receives the container service ID matched and is mapped with virtual machine, and return to step 1-1;
The virtual generator terminal that container service can be distributed comprises the following steps:
Step 2-1, initializes the best match angle value M of all virtual machinesp=0, and the container service ID set of record is emptied;
Step 2-2, waits task distributor to send message, judges if the message of task distributor is received:If end
Dispose message or virtual machine waits time-out, then enter step 2-5;2-3 is entered step if message is container deployment request;
Step 2-3, when virtual machine receives container deployment request, calculates and is taken to the container of virtual machine transmission container deployment request
The power consumption matching angle value M of businessbIf power consumption matching angle value is less than or equal to best match angle value, return to step 2-2, if power consumption
Matching angle value is more than best match angle value, then the best match angle value of the virtual machine is updated to Mb, and record corresponding container
The ID of service;
Step 2-4, the container service for being recorded ID is sent to labeled as postponement receiving vessel service, while by ID and its mark
Task distributor, is then back to step 2-2;
Step 2-5, the state of container service of the current markers to postpone receiving is changed to receive, and by container service ID and virtually
Machine mapping relations are sent to task distributor, send and confirm to terminate deployment message to task distributor, and start execution epicycle and hold
The deployment of device service, return to step 2-1 after deployment.
2. the containerization cloud resource distribution method based on stable matching according to claim 1, it is characterised in that step 1-3
The computational methods of the matching angle value are Tanimoto coefficient calculation methods.
3. the containerization cloud resource distribution method based on stable matching according to claim 2, it is characterised in that described
The calculation formula of Tanimoto coefficient calculation methods is:
<mrow>
<mi>T</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<mrow>
<mi>x</mi>
<mo>&CenterDot;</mo>
<mi>y</mi>
</mrow>
<mrow>
<mo>|</mo>
<mo>|</mo>
<mi>x</mi>
<mo>|</mo>
<msup>
<mo>|</mo>
<mn>2</mn>
</msup>
<mo>|</mo>
<mo>|</mo>
<mi>y</mi>
<mo>|</mo>
<msup>
<mo>|</mo>
<mn>2</mn>
</msup>
<mo>-</mo>
<mi>x</mi>
<mo>&CenterDot;</mo>
<mi>y</mi>
</mrow>
</mfrac>
<mo>=</mo>
<mfrac>
<mrow>
<mo>&Sigma;</mo>
<msub>
<mi>x</mi>
<mi>k</mi>
</msub>
<msub>
<mi>y</mi>
<mi>k</mi>
</msub>
</mrow>
<msqrt>
<mrow>
<mo>&Sigma;</mo>
<msup>
<msub>
<mi>x</mi>
<mi>k</mi>
</msub>
<mn>2</mn>
</msup>
<mo>+</mo>
<msqrt>
<mrow>
<mo>&Sigma;</mo>
<msup>
<msub>
<mi>y</mi>
<mi>k</mi>
</msub>
<mn>2</mn>
</msup>
</mrow>
</msqrt>
<mo>-</mo>
<mo>&Sigma;</mo>
<msub>
<mi>x</mi>
<mi>k</mi>
</msub>
<msub>
<mi>y</mi>
<mi>k</mi>
</msub>
</mrow>
</msqrt>
</mfrac>
</mrow>
Wherein, T (x, y) represents the matching angle value of virtual machine ys of the container service x to be allocated with being subjected to the container service, x and y
It is four dimensional vectors, k=1,2,3,4, represent that container service is required and the available following four of virtual machine utilizes respectively
Rate:Processor utilization, memory usage, network bandwidth utilization factor, memory space utilization rate.
4. the containerization cloud resource distribution method based on stable matching according to claim 1, it is characterised in that step 2-3
The power consumption matching angle value MbCalculation formula is:
<mrow>
<msub>
<mi>M</mi>
<mi>b</mi>
</msub>
<mo>=</mo>
<mfrac>
<mrow>
<msub>
<mi>MIPS</mi>
<mrow>
<mi>L</mi>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
</mrow>
</msub>
</mrow>
<mrow>
<mi>T</mi>
<mi>o</mi>
<mi>t</mi>
<mi>a</mi>
<mi>l</mi>
<mi>M</mi>
<mi>I</mi>
<mi>P</mi>
<mi>S</mi>
</mrow>
</mfrac>
</mrow>
Wherein, MIPSL(i)Represent processor utilization expected from i-th of container service to be allocated, unit is per second for million instructions;
TotalMIPS represents the processing speed of the virtual machine, and unit is per second for million instructions.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711089127.5A CN107908457B (en) | 2017-11-08 | 2017-11-08 | Containerized cloud resource allocation method based on stable matching |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711089127.5A CN107908457B (en) | 2017-11-08 | 2017-11-08 | Containerized cloud resource allocation method based on stable matching |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107908457A true CN107908457A (en) | 2018-04-13 |
CN107908457B CN107908457B (en) | 2020-03-17 |
Family
ID=61842747
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711089127.5A Active CN107908457B (en) | 2017-11-08 | 2017-11-08 | Containerized cloud resource allocation method based on stable matching |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107908457B (en) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108920269A (en) * | 2018-07-19 | 2018-11-30 | 中国联合网络通信集团有限公司 | The dispatching method and device of the I/O transformation task of container |
CN109146084A (en) * | 2018-09-06 | 2019-01-04 | 郑州云海信息技术有限公司 | A kind of method and device of the machine learning based on cloud computing |
CN109656717A (en) * | 2018-12-18 | 2019-04-19 | 广东石油化工学院 | A kind of containerization cloud resource distribution method |
CN109714400A (en) * | 2018-12-12 | 2019-05-03 | 华南理工大学 | A kind of energy optimization resource scheduling system and its method towards container cluster |
CN109788046A (en) * | 2018-12-29 | 2019-05-21 | 河海大学 | A kind of more tactful edge calculations resource regulating methods based on improvement ant colony algorithm |
CN111158908A (en) * | 2019-12-27 | 2020-05-15 | 重庆紫光华山智安科技有限公司 | Kubernetes-based scheduling method and device for improving GPU utilization rate |
CN112148420A (en) * | 2019-06-28 | 2020-12-29 | 杭州海康威视数字技术股份有限公司 | Abnormal task processing method based on container technology, server and cloud platform |
US11687380B2 (en) | 2020-09-10 | 2023-06-27 | International Business Machines Corporation | Optimizing resource allocation for distributed stream processing systems |
CN116522002A (en) * | 2023-06-27 | 2023-08-01 | 交通运输部水运科学研究所 | Container recommendation method and system of navigation service system based on machine learning |
CN117076142A (en) * | 2023-10-17 | 2023-11-17 | 阿里云计算有限公司 | Multi-tenant resource pool configuration method and multi-tenant service system |
CN117112123A (en) * | 2023-02-13 | 2023-11-24 | 深圳市同行者科技有限公司 | Kubernetes-based load balancing method and related equipment |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150019344A1 (en) * | 2013-07-15 | 2015-01-15 | Peachjar, Inc. | Flyer Approval and Distribution System |
CN105357296A (en) * | 2015-10-30 | 2016-02-24 | 河海大学 | Elastic caching system based on Docker cloud platform |
CN105681217A (en) * | 2016-04-27 | 2016-06-15 | 深圳市中润四方信息技术有限公司 | Dynamic load balancing method and system for container cluster |
CN105843670A (en) * | 2016-03-22 | 2016-08-10 | 浙江大学 | Cloud platform based virtual cluster deployment and integration method |
CN105867998A (en) * | 2016-03-24 | 2016-08-17 | 国云科技股份有限公司 | Virtual machine cluster deployment algorithm |
US20170039236A1 (en) * | 2015-08-06 | 2017-02-09 | International Business Machines Corporation | Vertical tuning of distributed analytics clusters |
CN106487775A (en) * | 2015-09-01 | 2017-03-08 | 阿里巴巴集团控股有限公司 | A kind for the treatment of method and apparatus of the business datum based on cloud platform |
CN106685684A (en) * | 2015-12-22 | 2017-05-17 | 北京轻元科技有限公司 | System-level management method of container in cloud calculating |
CN107070965A (en) * | 2016-12-22 | 2017-08-18 | 广东石油化工学院 | A kind of Multi-workflow resource provision method virtualized under container resource |
CN107222531A (en) * | 2017-05-23 | 2017-09-29 | 北京科技大学 | A kind of container cloud resource dispatching method |
-
2017
- 2017-11-08 CN CN201711089127.5A patent/CN107908457B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150019344A1 (en) * | 2013-07-15 | 2015-01-15 | Peachjar, Inc. | Flyer Approval and Distribution System |
US20170039236A1 (en) * | 2015-08-06 | 2017-02-09 | International Business Machines Corporation | Vertical tuning of distributed analytics clusters |
CN106487775A (en) * | 2015-09-01 | 2017-03-08 | 阿里巴巴集团控股有限公司 | A kind for the treatment of method and apparatus of the business datum based on cloud platform |
CN105357296A (en) * | 2015-10-30 | 2016-02-24 | 河海大学 | Elastic caching system based on Docker cloud platform |
CN106685684A (en) * | 2015-12-22 | 2017-05-17 | 北京轻元科技有限公司 | System-level management method of container in cloud calculating |
CN105843670A (en) * | 2016-03-22 | 2016-08-10 | 浙江大学 | Cloud platform based virtual cluster deployment and integration method |
CN105867998A (en) * | 2016-03-24 | 2016-08-17 | 国云科技股份有限公司 | Virtual machine cluster deployment algorithm |
CN105681217A (en) * | 2016-04-27 | 2016-06-15 | 深圳市中润四方信息技术有限公司 | Dynamic load balancing method and system for container cluster |
CN107070965A (en) * | 2016-12-22 | 2017-08-18 | 广东石油化工学院 | A kind of Multi-workflow resource provision method virtualized under container resource |
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 (9)
Title |
---|
QI ZHANG ET AL.: ""Harmony: Dynamic Heterogeneity-Aware Resource Provisioning in the Cloud"", 《2013 IEEE 33RD INTERNATIONAL CONFERENCE ON DISTRIBUTED COMPUTING SYSTEMS》 * |
RYAN WU ET AL.: ""A container-based elastic cloud architecture for real-time full-motion video (FMV) target tracking"", 《2014 IEEE APPLIED IMAGERY PATTERN RECOGNITION WORKSHOP (》 * |
XIN XU ET AL.: ""A Novel Resource Scheduling Approach in Container Based Clouds"", 《2014 IEEE 17TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE AND ENGINEERING》 * |
戴丽莉 等: ""基于遗传算法的电力电容器宽频建模方法"", 《电力科学与工程》 * |
树岸 等: ""基于容器技术的云计算资源自适应管理方法"", 《计算机科学》 * |
温少君: ""一种云平台中优化的虚拟机部署机制"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
胡致远 等: ""无线异构网络的资源分配策略"", 《计算机应用》 * |
苗立尧 等: ""一种基于Docker容器的集群分段伸缩方法"", 《计算机应用与软件》 * |
贾博威 等: ""基于Wu_Manber算法的大规模URL模式串匹配算法"", 《智能计算机与应用》 * |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108920269A (en) * | 2018-07-19 | 2018-11-30 | 中国联合网络通信集团有限公司 | The dispatching method and device of the I/O transformation task of container |
CN109146084B (en) * | 2018-09-06 | 2022-06-07 | 郑州云海信息技术有限公司 | Machine learning method and device based on cloud computing |
CN109146084A (en) * | 2018-09-06 | 2019-01-04 | 郑州云海信息技术有限公司 | A kind of method and device of the machine learning based on cloud computing |
CN109714400A (en) * | 2018-12-12 | 2019-05-03 | 华南理工大学 | A kind of energy optimization resource scheduling system and its method towards container cluster |
CN109656717A (en) * | 2018-12-18 | 2019-04-19 | 广东石油化工学院 | A kind of containerization cloud resource distribution method |
CN109788046A (en) * | 2018-12-29 | 2019-05-21 | 河海大学 | A kind of more tactful edge calculations resource regulating methods based on improvement ant colony algorithm |
CN112148420A (en) * | 2019-06-28 | 2020-12-29 | 杭州海康威视数字技术股份有限公司 | Abnormal task processing method based on container technology, server and cloud platform |
CN112148420B (en) * | 2019-06-28 | 2024-04-02 | 杭州海康威视数字技术股份有限公司 | Abnormal task processing method based on container technology, server and cloud platform |
CN111158908B (en) * | 2019-12-27 | 2021-05-25 | 重庆紫光华山智安科技有限公司 | Kubernetes-based scheduling method and device for improving GPU utilization rate |
CN111158908A (en) * | 2019-12-27 | 2020-05-15 | 重庆紫光华山智安科技有限公司 | Kubernetes-based scheduling method and device for improving GPU utilization rate |
US11687380B2 (en) | 2020-09-10 | 2023-06-27 | International Business Machines Corporation | Optimizing resource allocation for distributed stream processing systems |
CN117112123A (en) * | 2023-02-13 | 2023-11-24 | 深圳市同行者科技有限公司 | Kubernetes-based load balancing method and related equipment |
CN116522002A (en) * | 2023-06-27 | 2023-08-01 | 交通运输部水运科学研究所 | Container recommendation method and system of navigation service system based on machine learning |
CN116522002B (en) * | 2023-06-27 | 2023-09-08 | 交通运输部水运科学研究所 | Container recommendation method and system of navigation service system based on machine learning |
CN117076142A (en) * | 2023-10-17 | 2023-11-17 | 阿里云计算有限公司 | Multi-tenant resource pool configuration method and multi-tenant service system |
CN117076142B (en) * | 2023-10-17 | 2024-01-30 | 阿里云计算有限公司 | Multi-tenant resource pool configuration method and multi-tenant service system |
Also Published As
Publication number | Publication date |
---|---|
CN107908457B (en) | 2020-03-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107908457A (en) | A kind of containerization cloud resource distribution method based on stable matching | |
CN104881322B (en) | A kind of cluster resource dispatching method and device based on vanning model | |
CN107222531A (en) | A kind of container cloud resource dispatching method | |
CN104536832B (en) | A kind of virtual machine deployment method | |
CN105183543B (en) | A kind of gunz based on mobile social networking calculates online method for allocating tasks | |
CN104333569A (en) | Cloud task scheduling algorithm based on user satisfaction | |
CN106506670A (en) | A kind of cloud platform virtual resource high speed dispatching method and system | |
CN109858915A (en) | Transaction system and method for processing business | |
CN106502918B (en) | A kind of scheduling memory method and device | |
CN107871262A (en) | A kind of Order splitting processing method and server | |
CN108572867A (en) | The method and apparatus disposed distributed container cluster for application and execute the application | |
CN109542608A (en) | A kind of cloud artificial tasks dispatching method based on mixing queuing network | |
CN108886486A (en) | Virtualize network function intercommunication | |
CN109471725A (en) | Resource allocation methods, device and server | |
CN111159859B (en) | Cloud container cluster deployment method and system | |
Kumar et al. | Innovative task scheduling algorithm in cloud computing | |
CN111476376A (en) | Alliance learning method, alliance learning device and alliance learning system | |
CN103870992B (en) | Cross-border Multiple Currencies data handling system and method | |
CN110297959A (en) | Date storage method, device, storage medium and Edge Server | |
CN109582461A (en) | A kind of calculation resource disposition method and system for linux container | |
CN104184685B (en) | Data center resource distribution method, apparatus and system | |
CN109544234A (en) | A kind of resource pricing method based on Pareto optimality under cloud environment | |
CN109408230A (en) | Docker container dispositions method and system based on energy optimization | |
CN106445683B (en) | A kind of server resource distribution method and device | |
CN107589980A (en) | A kind of dispatching method of cloud computing resources |
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 |