CN106506655B - A kind of container group scheduling method suitable for cloud platform - Google Patents

A kind of container group scheduling method suitable for cloud platform Download PDF

Info

Publication number
CN106506655B
CN106506655B CN201611015647.7A CN201611015647A CN106506655B CN 106506655 B CN106506655 B CN 106506655B CN 201611015647 A CN201611015647 A CN 201611015647A CN 106506655 B CN106506655 B CN 106506655B
Authority
CN
China
Prior art keywords
container
scheduler
container group
physical node
group
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201611015647.7A
Other languages
Chinese (zh)
Other versions
CN106506655A (en
Inventor
钟健波
杨松
季统凯
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
G Cloud Technology Co Ltd
Original Assignee
G Cloud Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by G Cloud Technology Co Ltd filed Critical G Cloud Technology Co Ltd
Priority to CN201611015647.7A priority Critical patent/CN106506655B/en
Publication of CN106506655A publication Critical patent/CN106506655A/en
Application granted granted Critical
Publication of CN106506655B publication Critical patent/CN106506655B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00Network arrangements or protocols for supporting network services or applications
    • H04L67/50Network services
    • H04L67/60Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources
    • H04L67/63Routing a service request depending on the request content or context
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00Network arrangements or protocols for supporting network services or applications
    • H04L67/01Protocols
    • H04L67/10Protocols in which an application is distributed across nodes in the network

Abstract

The present invention relates to field of cloud computer technology, the dispatching method of especially a kind of container group suitable for cloud platform.The present invention creates a container mirror image first, for creating container group;Container group is the container set created with the same mirror image;Then it according to scheduling, expansion strategy, is scheduled, expanded by scheduler.The present invention solves in cloud platform that container resource utilization is low, the big problem of management workload, improves the stability of container operation., to same type of Container Management distribution of material, the utilization rate of physical resource is improved by container group, reduces O&M cost, improve the working efficiency of operation maintenance personnel;It is arranged according to different scheduling strategies, can satisfy the needs of client's different scenes.

Description

A kind of container group scheduling method suitable for cloud platform
Technical field
The present invention relates to field of cloud computer technology, especially a kind of container group scheduling method suitable for cloud platform.
Background technique
The method of cloud platform management container is by being packaged the method created again to single application runtime environment come real The rapid deployment operation now applied.Due to the diversity of user's application demand, this single container creation method is not It is able to satisfy demand, and following problem can be brought:
First is that operation management personnel needs take considerable time for the Container Management to cloud platform, whenever there is container delay machine Or when other problems, operation maintenance personnel must be handled at once, and from delay machine to restoring, container is normal, and the time not can determine that.
Second is that the application that container is disposed in build environment operates in ebb and peak period occupies identical resource, lead to object The utilization rate for managing resource is not high.
In order to mitigate operation maintenance personnel administrative burden, reduces O&M cost, enhance fully and rationally using for platform resource, improve Product stability needs a kind of container group scheduling method suitable for cloud platform.
Summary of the invention
The invention reside in a kind of container group scheduling method suitable for cloud platform is provided, solving cloud platform single container makes With physical node resource efficiency it is low, using stablizing continuous service, the big problem of O&M difficulty.
The technical solution that the present invention solves above-mentioned technical problem is: including the following steps:
The method includes the creation of container group and scheduling;Specifically includes the following steps:
Step 1: creating and upload a container mirror image, for creating the container object in cloud platform;
Step 2: container group inner pressurd vessel number is arranged in the mirror image creation container group uploaded in selection step 1;
Step 3: the scheduling strategy of setting container group, including cpu utilization rate, memory usage amount, disk io, network io;
Step 4: the expanding policy of setting container group determines extension, reduction according to amount of access, container payload;
Step 5: scheduler obtains all container groups in cloud platform and traverses container group, obtains the scheduling strategy of container group;
Step 6: judging whether there is container delay machine in container group, physical node is distributed if having and re-creates container;
Step 7: according to container group scheduling strategy, scheduler compares whether physical node meets schedulable condition, holds if meeting Row step 8, it is no to then follow the steps 10;
Step 8: scheduler obtains the configuration of container group, distributes and the physical node of scheduling is suitble to be adjusted back to container group Degree;
Step 9: scheduler creates a new container using container group mirror image according to distribution physical node, after the completion of creation A container is deleted from original container group;
Step 10: scheduling obtains the load of container group, amount of access, judges whether to meet extension, reduction preset value;It is held if meeting Row step 11, it is no to then follow the steps 15;
Step 11: scheduler judgement needs to extend, and executes step 12,;Judgement needs to reduce, and executes step 14:
Step 12: scheduler obtains the configuration of container group, distributes and the physical node of scheduling is suitble to be adjusted back to container group Degree;
Step 13: scheduler creates a new container using container group mirror image according to distribution physical node;
Step 14: scheduler, which obtains, to be loaded minimum container in container group and closes;
Step 15: terminating.
Container mirror image is the mirror image that physical node that can be all in cloud platform after uploading all is read;Container group content Device number refers to the container number created when the initialization of container group.
The scheduler judges container host physical node cpu in container group, and memory, disk io, whether network io etc. Meet the threshold value of scheduling strategy setting;When these segmentation symbols match, according to scheduling strategy, basis is correspondingly arranged choosing in remaining physical node Optimal physical node is selected to be scheduled;It is included in container group in target physical node using designated mirror creation container;
The scheduler, when meeting extension, selects in remaining physical node in extension, reduction according to strategy Optimal physical node is created;When meeting reduction, optimal container is chosen according to strategy and is closed.
The scheduler is reported the cpu utilization rate of physical node by monitoring module timing by monitoring module, and memory makes Dosage, disk io, network io to scheduler;And in collection vessel group container load, container ip amount of access to scheduler.
The present invention solves in cloud platform that container resource utilization is low, the big problem of management workload, improves container fortune Capable stability., to same type of Container Management distribution of material, the utilization rate of physical resource is improved by container group, reduced O&M cost improves the working efficiency of operation maintenance personnel;It is arranged according to different scheduling strategies, can satisfy client's different scenes It needs.
Detailed description of the invention
The following further describes the present invention with reference to the drawings:
Fig. 1 is that the method for the present invention creates container group flow chart;
Fig. 2 is the method for the present invention container group scheduling flow chart.
Specific implementation method
As shown in Figure 1, 2, the present invention creates a container group first, and container is arranged in initialization container group inner pressurd vessel quantity Scheduling strategy, setting container expansion reduce strategy:
For the container group that needs are dispatched, following method is called to distribute available physical node the appearance new for schedule creating Device.

Claims (5)

1. a kind of dispatching method of the container group suitable for cloud platform, it is characterised in that: the method includes the creation of container group And scheduling;Specifically includes the following steps:
Step 1: creating and upload a container mirror image, for creating the container object in cloud platform;
Step 2: container group inner pressurd vessel number is arranged in the mirror image creation container group uploaded in selection step 1;
Step 3: the scheduling strategy of setting container group, including cpu utilization rate, memory usage amount, disk io, network io;
Step 4: the expanding policy of setting container group determines extension, reduction according to amount of access, container payload;
Step 5: scheduler obtains all container groups in cloud platform and traverses container group, obtains the scheduling strategy of container group;
Step 6: judging whether there is container delay machine in container group, physical node is distributed if having and re-creates container;
Step 7: according to container group scheduling strategy, scheduler compares whether physical node meets schedulable condition, executes step if meeting Rapid 8, it is no to then follow the steps 10;
Step 8: scheduler obtains the configuration of container group, distributes and the physical node of scheduling is suitble to be scheduled back to container group;
Step 9: scheduler creates a new container using container mirror image according to distribution physical node, from original after the completion of creation A container is deleted in container group;
Step 10: scheduler obtains the load of container group, amount of access, judges whether to meet extension, reduction preset value;If meeting execution Step 11, no to then follow the steps 15;
Step 11: scheduler judgement needs to extend, and executes step 12;Judgement needs to reduce, and executes step 14;
Step 12: scheduler obtains the configuration of container group, distributes and the physical node of scheduling is suitble to be scheduled back to container group;
Step 13: scheduler creates a new container using container mirror image according to distribution physical node;
Step 14: scheduler, which obtains, to be loaded minimum container in container group and closes;
Step 15: terminating.
2. according to the method described in claim 1, it is characterized by: container mirror image is can be all in cloud platform after uploading The mirror image that physical node is all read;
Container group inner pressurd vessel number refers to the container number created when the initialization of container group.
3. method according to claim 1 or 2, it is characterised in that: the scheduler judges container host in container group Whether physical node cpu, memory, disk io, network io meet the threshold value of scheduling strategy setting;When these segmentation symbols match, according to scheduling plan Basis, which is correspondingly arranged, slightly in remaining physical node selects optimal physical node to be scheduled;Make in target physical node It is included in container group with designated mirror creation container;
The scheduler, when meeting extension, selects in remaining physical node optimal in extension, reduction according to strategy Physical node created;When meeting reduction, optimal container is chosen according to strategy and is closed.
4. method according to claim 1 or 2, it is characterised in that: the scheduler is reported by monitoring module timing The cpu utilization rate of physical node, memory usage amount, disk io, network io to scheduler;And in collection vessel group container it is negative It carries, container ip amount of access to scheduler.
5. according to the method described in claim 3, it is characterized by: the scheduler passes through monitoring module, by monitoring module The cpu utilization rate of physical node, memory usage amount, disk io, network io to scheduler are reported in timing;And hold in collection vessel group The load of device, container ip amount of access to scheduler.
CN201611015647.7A 2016-11-18 2016-11-18 A kind of container group scheduling method suitable for cloud platform Active CN106506655B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201611015647.7A CN106506655B (en) 2016-11-18 2016-11-18 A kind of container group scheduling method suitable for cloud platform

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201611015647.7A CN106506655B (en) 2016-11-18 2016-11-18 A kind of container group scheduling method suitable for cloud platform

Publications (2)

Publication Number Publication Date
CN106506655A CN106506655A (en) 2017-03-15
CN106506655B true CN106506655B (en) 2019-04-26

Family

ID=58324997

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201611015647.7A Active CN106506655B (en) 2016-11-18 2016-11-18 A kind of container group scheduling method suitable for cloud platform

Country Status (1)

Country Link
CN (1) CN106506655B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10949250B2 (en) 2018-02-07 2021-03-16 Red Hat, Inc. Image subunit based guest scheduling
CN114265704B (en) * 2022-03-03 2022-05-17 环球数科集团有限公司 Hybrid container cloud scheduling system based on convex optimization

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105119952A (en) * 2015-07-07 2015-12-02 北京京东尚科信息技术有限公司 Method and system for automatically and flexibly assigning resource under cloud platform
CN105245373A (en) * 2015-10-12 2016-01-13 天津市普迅电力信息技术有限公司 Construction and operation method of container cloud platform system
CN105554102A (en) * 2015-12-14 2016-05-04 中电科华云信息技术有限公司 Elastic expansion method based on container cluster and application system thereof
CN106020930A (en) * 2016-05-13 2016-10-12 深圳市中润四方信息技术有限公司 Application container based application management method and system

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9946527B2 (en) * 2013-03-15 2018-04-17 Bmc Software, Inc. Service placement techniques for a cloud datacenter
US9692666B2 (en) * 2014-12-22 2017-06-27 Rovio Entertainment Ltd. Container manager

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105119952A (en) * 2015-07-07 2015-12-02 北京京东尚科信息技术有限公司 Method and system for automatically and flexibly assigning resource under cloud platform
CN105245373A (en) * 2015-10-12 2016-01-13 天津市普迅电力信息技术有限公司 Construction and operation method of container cloud platform system
CN105554102A (en) * 2015-12-14 2016-05-04 中电科华云信息技术有限公司 Elastic expansion method based on container cluster and application system thereof
CN106020930A (en) * 2016-05-13 2016-10-12 深圳市中润四方信息技术有限公司 Application container based application management method and system

Also Published As

Publication number Publication date
CN106506655A (en) 2017-03-15

Similar Documents

Publication Publication Date Title
CN104317658B (en) A kind of loaded self-adaptive method for scheduling task based on MapReduce
CN106445675B (en) B2B platform distributed application scheduling and resource allocation method
Lee et al. A dynamic priority scheduling algorithm on service request scheduling in cloud computing
CN105302630B (en) A kind of dynamic adjusting method and its system of virtual machine
CN100473021C (en) System and method for autonomic system management through modulation of network controls
CN104657205B (en) A kind of video content analysis method and system based on virtualization
CN104468407A (en) Method and device for performing service platform resource elastic allocation
CN102307241A (en) Cloud calculation resource disposition method based on dynamic prediction
CN110362392A (en) A kind of ETL method for scheduling task, system, equipment and storage medium
CN108319359A (en) A kind of energy consumption optimization method based on thin cloud
Tighe et al. Integrating cloud application autoscaling with dynamic VM allocation
CN106506655B (en) A kind of container group scheduling method suitable for cloud platform
CN104765640A (en) Intelligent service scheduling method
CN104112049B (en) Based on the MapReduce task of P2P framework across data center scheduling system and method
CN105302641B (en) The method and device of node scheduling is carried out in virtual cluster
CN112015536A (en) Kubernetes cluster container group scheduling method, device and medium
Liaqat et al. Virtual machine migration enabled cloud resource management: A challenging task
Xu et al. IBIS: Interposed big-data I/O scheduler
Hanafy et al. A new infrastructure elasticity control algorithm for containerized cloud
CN114064229A (en) Cluster node processing method, system, device and medium
CN112099932A (en) Optimal pricing method and system for soft-hard deadline task offloading in edge computing
Peri et al. Orchestrating the Execution of Serverless Functions in Hybrid Clouds
CN106155793A (en) A kind of resource regulating method and device
CN105049365A (en) Adaptive frequency modulation energy-saving method for multi-core multi-thread intrusion detection device
Bagga et al. Moldable load scheduling using demand adjustable policies

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
CB02 Change of applicant information

Address after: 523808 19th Floor, Cloud Computing Center, Chinese Academy of Sciences, No. 1 Kehui Road, Songshan Lake Hi-tech Industrial Development Zone, Dongguan City, Guangdong Province

Applicant after: G-Cloud Technology Co., Ltd.

Address before: 523808 No. 14 Building, Songke Garden, Songshan Lake Science and Technology Industrial Park, Dongguan City, Guangdong Province

Applicant before: G-Cloud Technology Co., Ltd.

CB02 Change of applicant information
GR01 Patent grant
GR01 Patent grant