CN107908457B - Containerized cloud resource allocation method based on stable matching - Google Patents
Containerized cloud resource allocation method based on stable matching Download PDFInfo
- Publication number
- CN107908457B CN107908457B CN201711089127.5A CN201711089127A CN107908457B CN 107908457 B CN107908457 B CN 107908457B CN 201711089127 A CN201711089127 A CN 201711089127A CN 107908457 B CN107908457 B CN 107908457B
- Authority
- CN
- China
- Prior art keywords
- container
- virtual machine
- queue
- container service
- matching
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 19
- 238000013468 resource allocation Methods 0.000 title claims abstract description 15
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000013507 mapping Methods 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 5
- 238000012790 confirmation Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000005265 energy consumption Methods 0.000 abstract description 8
- 238000005516 engineering process Methods 0.000 abstract description 8
- 238000005457 optimization Methods 0.000 abstract description 4
- 238000010801 machine learning Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 6
- 238000011160 research Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—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 containerization cloud resource allocation method based on stable matching, which is characterized in that a traditional stable marital matching algorithm is improved into a many-to-one stable matching algorithm, and a common similarity algorithm in machine learning is used as a preference rule of the stable matching algorithm to generate a preference list, so that load balance of a containerization cloud environment is realized, and energy consumption of a data center is reduced. The invention belongs to a centralized scheduling algorithm, in the process of resource allocation, the utilization rate of four types of virtual machine resources of each cloud computing node is weighed and matched with a task to be allocated, so that the influence on the energy consumption of a whole system can be generated. The invention provides an optimization algorithm for allocating task-level containers to system-level virtual machines in a cloud computing system under a container virtualization technology, and solves the problem of energy consumption optimization in a containerized cloud environment by improving the resource utilization rate at the server and virtual machine level.
Description
Technical Field
The invention relates to a containerization cloud resource allocation method based on stable matching, in particular to a resource allocation method based on system overall energy consumption optimization under a container virtualization technology, and belongs to the technical field of virtual resource allocation of cloud computing.
Background
In recent years, container virtualization technologies have been widely used, and similar to conventional virtual machine technologies (VirtualMachine), container virtualization technologies provide an isolated virtual environment, while improving the efficiency of resource utilization due to their low overhead and lightweight. In addition, since the containers share the kernel of the host operating system, the configuration problem is fundamentally a software management problem. The container technology is considered as the next important direction of cloud computing development, while most of the existing research is mainly directed at the virtual cloud computing technology of the virtual machine, the research on the allocation algorithm of the container virtual resources and the performance thereof is still an open subject, and especially the research on the resource allocation and scheduling method based on the overall energy consumption optimization of the container cloud computing system is still in a discussion stage.
With the development of virtual technologies, operating system level virtualized containers become the mainstream of virtual resource deployment in cloud computing, and containers, i.e., services, are also increasingly popularized and become a main deployment model in a cloud computing environment, but a resource allocation technology for containers is not sufficiently researched, the number of containers in the containerized cloud environment is large, and how to rapidly and efficiently deploy the large number of containers to a suitable virtual machine to achieve the purpose of reducing energy consumption of a data center becomes an urgent problem to be solved.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the task-level container is deployed to a proper system-level virtual machine quickly and efficiently, and the purpose of reducing energy consumption of a data center is achieved.
The invention adopts the following technical scheme for solving the technical problems:
a containerization cloud resource allocation method based on stable matching comprises a task allocator end and a virtual machine end capable of allocating container services;
wherein, the task distributor end comprises the following steps:
step 1-1, initializing a task distributor, and acquiring the residual allocable resources of all virtual machines;
step 1-2, storing the to-be-distributed container services arriving at the task distributor in a cache of the task distributor, and establishing a to-be-deployed container queue L (L) (i), i being 1,2, …, m, L (i) representing the ith to-be-distributed container service, and m being the number of the to-be-distributed container services according to the arrival sequence of the to-be-distributed container services;
step 1-3, if the queue of the containers to be deployed is not empty, calculating the matching value of each container service L (i) to be distributed in the queue and all virtual machines which can accept the container service, sequencing the matching values from large to small, and establishing a queue P of distributable virtual machines according to the sequencing resulti(ii) a Let i equal to 1;
step 1-4, reading an allocable virtual machine queue P corresponding to the ith to-be-allocated container service in a to-be-allocated container queueiStarting from the virtual machine with the highest matching value with the ith container service to be distributed, sending a container deployment request to the virtual machine which does not refuse to accept the container deployment request, and if the virtual machine is refused to accept, continuing to send the container deployment request to the queue PiThe next virtual machine in the system sends a container deployment request until the virtual machine replies to accept or suspends accepting the deployment request;
step 1-5, changing i to i +1 and checking whether to traverse the queue L, if not, returning to step 1-4, otherwise, entering step 1-6;
step 1-6, the task distributor sends a deployment ending message to all virtual machines capable of distributing container services to indicate that the resource matching process is ended, and if the message of all the virtual machines is received to confirm the ending or wait for overtime, the step 1-7 is carried out;
step 1-7, the task distributor end receives the matched container service ID and the virtual machine mapping, and returns to the step 1-1;
the virtual machine end of the allocable container service comprises the following steps:
step 2-1, initializing the optimal matching degree values M of all virtual machinespSetting the recorded container service ID set to be 0 and emptying the recorded container service ID set;
step 2-2, waiting for the task distributor to send a message, and if the message of the task distributor is received, judging: if the message is finished to be deployed or the virtual machine waits for overtime, entering the step 2-5; if the message is a container deployment request, entering step 2-3;
step 2-3, when the virtual machine receives the container deployment request, calculating the power consumption matching degree value M of the container service for sending the container deployment request to the virtual machinebIf the power consumption matching degree value is less than or equal to the optimal matching degree value, returning to the step 2-2, and if the power consumption matching degree value is greater than the optimal matching degree value, updating the optimal matching degree value of the virtual machine to MbAnd recording the ID of the corresponding container service;
step 2-4, marking the container service recorded with the ID as a temporary accepting container service, simultaneously sending the ID and the mark thereof to the task distributor, and then returning to the step 2-2;
and 2-5, changing the state of the container service marked as the deferred acceptance currently into the acceptance state, sending the mapping relation between the container service ID and the virtual machine to the task distributor, sending a confirmation finishing deployment message to the task distributor, starting to execute the deployment of the container service in the current round, and returning to the step 2-1 after the deployment is finished.
As a preferred embodiment of the present invention, the method for calculating the matching degree value in steps 1 to 3 is a Tanimoto coefficient calculation method.
As a preferred embodiment of the present invention, the calculation formula of the Tanimoto coefficient calculation method is:
wherein T (x, y) represents a matching value between the container service x to be allocated and the virtual machine y that can accept the container service, x and y are four-dimensional vectors, and k is 1,2,3,4, which respectively represent the following four utilization rates required by the container service and available by the virtual machine: processor utilization, memory utilization, network bandwidth utilization, storage space utilization.
As a preferable scheme of the invention, the power consumption matching degree in the steps 2 to 3Value MbThe calculation formula is as follows:
wherein, MIPSL(i)Representing the expected processor utilization rate of the ith container to be allocated in million instructions per second; TotalMIPS represents the processing speed of the virtual machine in millions of instructions per second.
Compared with the prior art, the invention adopting the technical scheme has the following technical effects:
1. aiming at the container deployment process, the power consumption of the system is optimally distributed, a calculation method based on the matching degree of four types of virtual resources is adopted as a preference rule of a container selection virtual machine, and the preference rule of the virtual machine to the container adopts a preference rule of a greedy algorithm based on the processor utilization rate according to whether the resources of the virtual machine can support the deployment of the container, namely the processor resources can be provided according to the actual occupation of the processor utilization rate and are sorted from high to low, so that the execution efficiency of tasks is improved, and the system energy consumption is minimized.
2. The method optimizes and matches the container service to be distributed and the virtual machine under the condition of ensuring that the task is completed in the specified time, so that the deployment of the container service task achieves an optimal matching effect, and further higher benefits are created for the cloud computing architecture.
Drawings
Fig. 1 is a schematic system architecture diagram of a containerization cloud resource allocation method based on stable matching according to the present invention.
Fig. 2 is a stage a1 flow diagram at the task dispatcher end.
Fig. 3 is a stage a2 flowchart at the task dispatcher end.
Fig. 4 is a stage a3 flowchart at the task dispatcher end.
Fig. 5 is a stage B1 flow diagram at the virtual machine end of the allocable container service.
Fig. 6 is a stage B2 flow diagram at the virtual machine end of the allocable container service.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
Fig. 1 is a schematic diagram of a system architecture of a containerization cloud resource allocation method based on stable matching according to the present invention. The allocation target of the cloud computing system is to deploy the container service to the virtual machine in the system, and the algorithm of the cloud computing system at the task allocator end is mainly divided into three stages:
stage a1 flowchart at the task dispatcher end, as shown in fig. 2:
step A1-1, initializing the task allocator, and acquiring the remaining allocable resources of all the virtual machines, assuming that the number of allocable containers is m.
Step A1-2, storing the batch container tasks arriving at the task distributor in the buffer, and establishing a container queue L to be deployed for the container service to be distributed in the buffer according to the arrival sequence of the tasks, wherein the size of the queue is the number m of the distributable containers.
Step A1-3, if the queue L of the container to be deployed is not empty, starting to read the ith unit L (i) in the queue, and calculating the matching values of the container and all virtual machines which can accept the container in the cloud computing system according to the matching similarity calculation method defined as follows. The matching degree value in the invention mainly adopts Tanimoto coefficient and the calculation formula is as follows:
in the invention, x represents a task to be allocated by a container service, y represents an allocable virtual machine, and we define that x and y are both four-dimensional vectors which respectively represent the following four aspects required by the container service and available by the virtual machine: calculating the matching degree by four variables of processor utilization rate, memory utilization rate, network bandwidth utilization rate and storage space utilization rate, and sequencing according to the matching degree valueAnd establishes a queue P for assignable virtual machinesiStep A1-3 is repeated until all cells in queue L are traversed, and then stage A2 is entered.
Stage a2 flowchart at the task dispatcher end, as shown in fig. 3:
step A2-1, setting i to 1, the reading unit selects the assignable virtual machine queue P in L (i)iThe jth virtual machine P with the highest median matching value and never rejectedi,jSending a container deployment request and dequeuing the virtual machine from queue Pi。
Step A2-2, queue P to an allocable virtual machine if the request is rejected (Reject) by the virtual machineiThe virtual machine with the second matching degree value sends a container deployment request, if the request is accepted by the virtual machine (waitinglist) temporarily, i is added with 1 and whether to traverse the queue L is checked, if the queue L is not traversed, the step A2-1 is returned, and if the queue L is traversed, the step A3 is entered.
Stage a3 flowchart at the task dispatcher end, as shown in fig. 4:
and step A3-1, the task distributor sends a finish deployment message to the virtual machine ends of all the allocable containers to indicate finish resource allocation, and if the message of all the virtual machines confirms finish or the waiting time of the task distributor is overtime, the step A3-2 is executed.
And step A3-2, sending the matched container and virtual machine mapping to a task distributor to start executing container deployment, and returning to the stage A1 after the execution is finished.
The algorithm steps synchronously executed at the virtual machine end of the distributable container service are mainly divided into the following two stages:
stage B1 flow diagram at the virtual machine end of the allocable container service, as shown in FIG. 5:
step B1-1, initializing the optimal power consumption matching degree MpAt 0, the assignable container ID is empty.
And step B1-2, waiting for the allocation request of the task allocator, entering a stage B2 if the request initiated by the task allocator is a deployment ending message or the waiting time of the virtual machine end is overtime, or entering a step B1-3 if the request of the task allocator is an allocation request.
Step B1-3, calculating the power consumption matching degree value M of the container which will make the allocation request to the virtual machinebThe calculation formula is as follows, if the matching degree MbLess than or equal to the optimum matching degree MpIf not, no change is made and the process returns to step B1-2; if the matching degree MbGreater than the optimum degree of matching MpProceed to step B1-4.
Here MIPSL(i)It is referred to that the expected processor utilization for the ith container task is in units of million instructions per second, and TotalMIPS represents the processing speed of the virtual machine in units of million instructions per second.
Step B1-4, updating the best matching degree to MbAnd records the ID of the corresponding container.
Step B1-5, mark the container as a suspended allocation container task for the virtual machine, and return to step B1-1.
A flow chart at stage B2 on the virtual machine side of the allocable container service, as shown in fig. 6:
and step B2-1, changing the state of all containers marked as tentative allocation to Accept allocation (Accept), and sending the final container and allocation mapping of the virtual machines to the task allocator.
And step B2-2, sending a confirmation ending deployment message to the task distributor.
And step B2-3, starting to execute task deployment of the container service of the current round.
Step B2-4, return to stage B1.
The above embodiments are only for illustrating the technical idea of the present invention, and the protection scope of the present invention is not limited thereby, and any modifications made on the basis of the technical scheme according to the technical idea of the present invention fall within the protection scope of the present invention.
Claims (3)
1. A containerization cloud resource allocation method based on stable matching is characterized by comprising a task allocator end and a virtual machine end capable of allocating container services;
wherein, the task distributor end comprises the following steps:
step 1-1, initializing a task distributor, and acquiring the residual allocable resources of all virtual machines;
step 1-2, storing the to-be-distributed container services arriving at the task distributor in a cache of the task distributor, and establishing a to-be-deployed container queue L (L) (i), i being 1,2, …, m, L (i) representing the ith to-be-distributed container service, and m being the number of the to-be-distributed container services according to the arrival sequence of the to-be-distributed container services;
step 1-3, if the queue of the containers to be deployed is not empty, calculating the matching value of each container service L (i) to be distributed in the queue and all virtual machines which can accept the container service, sequencing the matching values from large to small, and establishing a queue P of distributable virtual machines according to the sequencing resulti(ii) a Let i equal to 1;
step 1-4, reading an allocable virtual machine queue P corresponding to the ith to-be-allocated container service in a to-be-allocated container queueiStarting from the virtual machine with the highest matching value with the ith container service to be distributed, sending a container deployment request to the virtual machine which does not refuse to accept the container deployment request, and if the virtual machine is refused to accept, continuing to send the container deployment request to the queue PiThe next virtual machine in the system sends a container deployment request until the virtual machine replies to accept or suspends accepting the deployment request;
step 1-5, changing i to i +1 and checking whether to traverse the queue L, if not, returning to step 1-4, otherwise, entering step 1-6;
step 1-6, the task distributor sends a deployment ending message to all virtual machines capable of distributing container services to indicate that the resource matching process is ended, and if the message of all the virtual machines is received to confirm the ending or wait for overtime, the step 1-7 is carried out;
step 1-7, the task distributor end receives the matched container service ID and the virtual machine mapping, and returns to the step 1-1;
the virtual machine end of the allocable container service comprises the following steps:
step 2-1, initializing best match metric values M for all virtual machinespSetting the recorded container service ID set to be 0 and emptying the recorded container service ID set;
step 2-2, waiting for the task distributor to send a message, and if the message of the task distributor is received, judging: if the message is finished to be deployed or the virtual machine waits for overtime, entering the step 2-5; if the message is a container deployment request, entering step 2-3;
step 2-3, when the virtual machine receives the container deployment request, calculating the power consumption matching degree value M of the container service for sending the container deployment request to the virtual machinebIf the power consumption matching degree value is less than or equal to the optimal matching degree value, rejecting the container deployment request and returning to the step 2-2, and if the power consumption matching degree value is greater than the optimal matching degree value, updating the optimal matching degree value of the virtual machine to MbAnd recording the ID of the corresponding container service;
step 2-4, marking the container service recorded with the ID as a temporary accepting container service, simultaneously sending the ID and the mark thereof to the task distributor, and then returning to the step 2-2;
and 2-5, changing the state of the container service marked as the deferred acceptance currently into the acceptance state, sending the mapping relation between the container service ID and the virtual machine to the task distributor, sending a confirmation finishing deployment message to the task distributor, starting to execute the deployment of the container service in the current round, and returning to the step 2-1 after the deployment is finished.
2. The containerized cloud resource allocation method based on stable matching according to claim 1, wherein the calculation method of the matching degree value in steps 1-3 is a Tanimoto coefficient calculation method.
3. The containerized cloud resource allocation method based on stable matching according to claim 1, wherein the power consumption matching degree value M is obtained in steps 2-3bThe calculation formula is as follows:
wherein,MIPSL(i)representing the expected processor utilization rate of the ith container to be allocated in million instructions per second; TotalMIPS represents the processing speed of the virtual machine in millions of instructions per second.
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 CN107908457A (en) | 2018-04-13 |
| CN107908457B true 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) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108920269B (en) * | 2018-07-19 | 2021-03-19 | 中国联合网络通信集团有限公司 | Scheduling method and device for I/O transmission 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 |
| CN109714400B (en) * | 2018-12-12 | 2020-09-22 | 华南理工大学 | Container cluster-oriented energy consumption optimization resource scheduling system and method thereof |
| CN109656717A (en) * | 2018-12-18 | 2019-04-19 | 广东石油化工学院 | A kind of containerization cloud resource distribution method |
| CN109788046B (en) * | 2018-12-29 | 2020-06-16 | 河海大学 | Multi-strategy edge computing resource scheduling method based on improved bee colony algorithm |
| 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 |
| 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 |
| 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 |
| 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 |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| 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 |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150019344A1 (en) * | 2013-07-15 | 2015-01-15 | Peachjar, Inc. | Flyer Approval and Distribution System |
| US10073880B2 (en) * | 2015-08-06 | 2018-09-11 | International Business Machines Corporation | Vertical tuning of distributed analytics clusters |
-
2017
- 2017-11-08 CN CN201711089127.5A patent/CN107908457B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
|---|
| "A container-based elastic cloud architecture for real-time full-motion video (FMV) target tracking";Ryan Wu et al.;《2014 IEEE Applied Imagery Pattern Recognition Workshop (》;20150216;全文 * |
| "A Novel Resource Scheduling Approach in Container Based Clouds";Xin Xu et al.;《2014 IEEE 17th International Conference on Computational Science and Engineering》;20141221;全文 * |
| "Harmony: Dynamic Heterogeneity-Aware Resource Provisioning in the Cloud";Qi Zhang et al.;《2013 IEEE 33rd International Conference on Distributed Computing Systems》;20131213;全文 * |
| "一种云平台中优化的虚拟机部署机制";温少君;《中国优秀硕士学位论文全文数据库 信息科技辑》;20120915;全文 * |
| "一种基于Docker容器的集群分段伸缩方法";苗立尧 等;《计算机应用与软件》;20170131;第34卷(第1期);全文 * |
| "基于Wu_Manber算法的大规模URL模式串匹配算法";贾博威 等;《智能计算机与应用》;20171031;第7卷(第5期);全文 * |
| "基于容器技术的云计算资源自适应管理方法";树岸 等;《计算机科学》;20170731;第44卷(第7期);全文 * |
| "基于遗传算法的电力电容器宽频建模方法";戴丽莉 等;《电力科学与工程》;20151130;第31卷(第11期);全文 * |
| "无线异构网络的资源分配策略";胡致远 等;《计算机应用》;20110430;第31卷(第4期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107908457A (en) | 2018-04-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107908457B (en) | Containerized cloud resource allocation method based on stable matching | |
| US11669372B2 (en) | Flexible allocation of compute resources | |
| US10325343B1 (en) | Topology aware grouping and provisioning of GPU resources in GPU-as-a-Service platform | |
| CN107222531B (en) | Container cloud resource scheduling method | |
| CN110990154B (en) | Big data application optimization method, device and storage medium | |
| US8527988B1 (en) | Proximity mapping of virtual-machine threads to processors | |
| CN108900626B (en) | Data storage method, device and system in cloud environment | |
| CN109408229A (en) | A kind of dispatching method and device | |
| CN112416585A (en) | GPU resource management and intelligent scheduling method for deep learning | |
| CN108055292B (en) | Optimization method for mapping from virtual machine to physical machine | |
| WO2018126771A1 (en) | Storage controller and io request processing method | |
| Pattanaik et al. | Performance study of some dynamic load balancing algorithms in cloud computing environment | |
| WO2020134133A1 (en) | Resource allocation method, substation, and computer-readable storage medium | |
| CN106998340B (en) | Load balancing method and device for board resources | |
| KR101557747B1 (en) | System and method for allocating virtual machine for effective use of multi resource in cloud | |
| CN103548324A (en) | Method for virtual machine assignment and device for virtual machine assignment | |
| CN111159859B (en) | Cloud container cluster deployment method and system | |
| CN108984286A (en) | A kind of resource regulating method and system of cloud computing platform | |
| CN113778617B (en) | Container horizontal expansion and contraction method and device, electronic equipment and storage medium | |
| CN113626173B (en) | Scheduling method, scheduling device and storage medium | |
| CN109189581B (en) | Job scheduling method and device | |
| CN111796932A (en) | GPU resource scheduling method | |
| CN115361349B (en) | Resource using method and device | |
| Darji et al. | Dynamic load balancing for cloud computing using heuristic data and load on server | |
| CN107590000A (en) | Secondary random sources management method/system, computer-readable storage medium and equipment |
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 |