CN112217895A - Virtualized container-based super-fusion cluster scheduling method and device and physical host - Google Patents
Virtualized container-based super-fusion cluster scheduling method and device and physical host Download PDFInfo
- Publication number
- CN112217895A CN112217895A CN202011086307.XA CN202011086307A CN112217895A CN 112217895 A CN112217895 A CN 112217895A CN 202011086307 A CN202011086307 A CN 202011086307A CN 112217895 A CN112217895 A CN 112217895A
- Authority
- CN
- China
- Prior art keywords
- super
- convergence
- container
- fusion
- service
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/60—Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources
Abstract
The invention provides a virtualized container-based super-converged cluster scheduling method and device and a physical host, and relates to the technical field of cloud computing. By configuring corresponding super-fusion services for the virtualized containers, each virtualized container can be applied not only in a light-weight scene, but also in a heavy-weight scene such as an application super-fusion cluster, so that container virtualization can be more widely applied.
Description
Technical Field
The invention relates to the technical field of cloud computing, in particular to a dispatching method and device of a super-fusion cluster based on a virtualization container and a physical host.
Background
The container virtualization technology is an emerging technology at present, which is based on the same kernel of a physical host, and then utilizes a namespace technology to mirror and isolate programs between an application layer and a service layer. And finally, controlling resources through a cgroups technology, thereby realizing the virtualization of the container.
At present, with the continuous development of virtualization technologies, the virtualization technology of the container is applied in practice, but because the container virtualization has the characteristic of light weight, the current application can only be in a light-weight scene, and the application scene is limited.
Disclosure of Invention
The invention aims to provide a dispatching method and a device of a super-converged cluster based on a virtualized container and a physical host, so that container virtualization can be widely applied.
The invention adopts the following technical scheme, and provides a physical host, which comprises: one or more processors for executing program instructions, memory of different forms;
the memory is used for storing programs;
the processor is used for calling and running the program in the memory, so that the physical host can create a plurality of virtualized containers on the physical host based on the same kernel of the physical host and configure corresponding super-fusion services for each virtualized container, wherein each virtualized container configured with the corresponding super-fusion service is a super-fusion container node, the plurality of super-fusion container nodes form a super-fusion cluster, and finally, the processor can schedule the super-fusion services on the super-fusion cluster according to the running condition of the super-fusion cluster so as to realize load balancing of the super-fusion cluster.
Preferably, the system further comprises a communication interface and a bus.
The invention also provides a dispatching method of the super-fusion cluster based on the virtualization container, which comprises the following steps: the method comprises the following steps:
step S100: creating a plurality of virtualized containers on a physical host based on the same kernel of the physical host;
step S200: configuring corresponding super-fusion services for each virtualized container, wherein each virtualized container configured with the corresponding super-fusion services is a super-fusion container node, and a plurality of super-fusion container nodes form a super-fusion cluster;
step S300: and scheduling the super-convergence service on the super-convergence cluster according to the running condition of the super-convergence cluster.
Preferably, in step S300, the physical host obtains a load generated when each super-convergence container node runs the super-convergence service, determines a part of super-convergence container nodes with a load greater than a threshold from the super-convergence cluster, and determines another part of super-convergence container nodes with a load less than or equal to the threshold; then, the physical host dispatches part of the super-convergence service on one part of the super-convergence container nodes to another part of the super-convergence container for running, so that the load of each dispatched super-convergence container node is smaller than or equal to a threshold value.
Preferably, in step S300, the physical host acquires the load generated when each super-convergence container node operates the super-convergence service, and then, the physical host determines a threshold value between the maximum value and the minimum value according to the maximum value and the minimum value of the load generated when each super-convergence container node operates the super-convergence service: and finally, the physical host determines a part of super-fusion container nodes with the load greater than the threshold value and another part of super-fusion container nodes with the load less than or equal to the threshold value from the super-fusion cluster according to the load generated by the super-fusion service operated by each super-fusion container node and the threshold value.
Preferably, when scheduling the super-convergence service in step S300, the super-convergence service includes: the storage service, the network service and the computing service, therefore, the physical host dispatches one or two of the storage service, the network service and the computing service on one part of the super-convergence container node to another part of the super-convergence container node to run.
The invention also provides a dispatching device of the super-integration cluster based on the virtualization container, which comprises the following steps:
the system comprises a container creating module, a storage module and a processing module, wherein the container creating module is used for creating a plurality of virtualized containers on a physical host based on the same inner core of the physical host;
the container configuration module is used for configuring corresponding super-fusion services for each virtualized container, wherein each virtualized container configured with the corresponding super-fusion services is a super-fusion container node, and a plurality of super-fusion container nodes form a super-fusion cluster;
and the cluster scheduling module is used for scheduling the super-fusion service on the super-fusion cluster according to the running condition of the super-fusion cluster.
Preferably, the cluster scheduling module is specifically configured to obtain a load generated when each super-fusion container node runs a super-fusion service, determine, from the super-fusion cluster, a part of super-fusion container nodes whose loads are greater than a threshold, and determine another part of super-fusion container nodes whose loads are less than or equal to the threshold; and scheduling the partial super-convergence service on one part of super-convergence container nodes to the other part of super-convergence container nodes for operation, so that the load of each scheduled super-convergence container node is less than or equal to the threshold.
Preferably, the cluster scheduling module is specifically configured to determine the threshold between the maximum value and the minimum value according to the maximum value and the minimum value of the load generated by each super-fusion container node running the super-fusion service, determine a part of super-fusion container nodes with a load greater than the threshold from the super-fusion cluster according to the load generated by each super-fusion container node running the super-fusion service and the threshold, and determine another part of super-fusion container nodes with a load less than or equal to the threshold.
Preferably, the super-convergence service includes: the cluster scheduling module is further used for scheduling one or two of the storage service, the network service and the computing service on one part of the super-convergence container nodes to another part of the super-convergence container nodes for operation.
The beneficial effects of the invention include: by configuring corresponding super-fusion services for the virtualized containers, each virtualized container can be applied not only in a light-weight scene, but also in a heavy-weight scene such as an application super-fusion cluster, so that container virtualization can be more widely applied.
Drawings
Fig. 1 is a block diagram of a physical host according to the present invention;
FIG. 2 is a flowchart of a scheduling method of a super-converged cluster based on a virtualized container according to the present invention;
fig. 3 is a block diagram of a scheduling apparatus of a super-converged cluster based on a virtualized container according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.
Referring to fig. 1, the present invention provides a physical host 20, the physical host 20 comprising a communication interface 21, one or more processors 24 for executing program instructions, a bus 22, and different forms of memory 23, such as a disk, ROM, or RAM, or any combination thereof. Illustratively, the computer platform may also include program instructions stored in ROM, RAM, or other types of non-transitory storage media, or any combination thereof.
The memory 23 is used for storing programs;
the processor 24 is configured to call and run the program in the memory 23, so that the physical host 20 can create a plurality of virtualized containers on the physical host 20 based on the same kernel of the physical host, and configure a corresponding super-fusion service for each virtualized container, where each virtualized container configured with the corresponding super-fusion service is a super-fusion container node, and the plurality of super-fusion container nodes form a super-fusion cluster, and finally, the processor 24 can schedule the super-fusion service on the super-fusion cluster according to the running condition of the super-fusion cluster, so as to implement load balancing of the super-fusion cluster.
Referring to fig. 2, the present invention provides a virtualized container-based super-converged cluster scheduling method, where the virtualized container-based super-converged cluster scheduling method may be applied to a physical host 20, and the virtualized container-based super-converged cluster scheduling method includes: step S100, step S200, and step S300.
Step S100: creating a plurality of virtualized containers on a physical host 20 based on the same kernel of the physical host 20;
step S200: configuring corresponding super-fusion services for each virtualized container, wherein each virtualized container configured with the corresponding super-fusion services is a super-fusion container node, and a plurality of super-fusion container nodes form a super-fusion cluster;
step S300: and scheduling the super-convergence service on the super-convergence cluster according to the running condition of the super-convergence cluster.
In this embodiment, for step S300, the physical host 20 may obtain the load generated by each super-fusion container node running the super-fusion service, determine a part of super-fusion container nodes with the load greater than the threshold value from the super-fusion cluster, and determine another part of super-fusion container nodes with the load less than or equal to the threshold value; then, the physical host 20 may schedule a part of the super-convergence services on a part of the super-convergence container nodes to another part of the super-convergence containers for running, so that the load of each scheduled super-convergence container node is less than or equal to a threshold value, so as to implement load balancing.
Further, as an exemplary way to determine the threshold in step S300, the physical host 20 may obtain the load generated by each super-convergence container node running the super-convergence service. Then, the physical host 20 determines a threshold value between the maximum value and the minimum value according to the maximum value and the minimum value of the loads generated by each super-fusion container node running the super-fusion service: finally, the physical host 20 determines a part of the super-convergence container nodes with the load greater than the threshold value and another part of the super-convergence container nodes with the load less than or equal to the threshold value from the super-convergence cluster according to the load generated by each super-convergence container node running the super-convergence service and the threshold value.
Further, as an exemplary manner of scheduling the super-convergence service in step S300, the super-convergence service may include: storage services, network services, and computing services, and thus, physical hosts 20 may schedule one or both of the storage services, network services, and computing services on one portion of the super-converged container node to run on another portion of the super-converged container node.
Referring to fig. 3, the present invention further provides a dispatching apparatus 100 for a super-converged cluster based on a virtualized container, where the dispatching apparatus 100 for a super-converged cluster based on a virtualized container is applied to a physical host 20, and the dispatching apparatus 100 for a super-converged cluster based on a virtualized container includes:
a container creating module 110, configured to create a plurality of virtualized containers on the physical host 20 based on the same kernel of the physical host 20;
a container configuration module 120, configured to configure a corresponding super-fusion service for each virtualized container, where each virtualized container configured with the corresponding super-fusion service is a super-fusion container node, and multiple super-fusion container nodes form a super-fusion cluster;
and the cluster scheduling module 130 is configured to schedule the super-fusion service on the super-fusion cluster according to the operation condition of the super-fusion cluster.
Optionally, the cluster scheduling module 130 is specifically configured to obtain a load generated when each super-fusion container node runs a super-fusion service, determine, from the super-fusion cluster, a part of super-fusion container nodes whose load is greater than a threshold, and determine another part of super-fusion container nodes whose load is less than or equal to the threshold; and scheduling the partial super-convergence service on one part of super-convergence container nodes to the other part of super-convergence container nodes for operation, so that the load of each scheduled super-convergence container node is less than or equal to the threshold.
Optionally, the cluster scheduling module 130 is specifically configured to determine the threshold between the maximum value and the minimum value according to the maximum value and the minimum value of the load generated by each super-convergence container node running the super-convergence service, determine, according to the load generated by each super-convergence container node running the super-convergence service and the threshold, a part of super-convergence container nodes whose load is greater than the threshold from the super-convergence cluster, and determine another part of super-convergence container nodes whose load is less than or equal to the threshold.
Optionally, the super-convergence service includes: the cluster scheduling module 130 is further configured to schedule one or two of the storage service, the network service, and the computing service on the one part of super-convergence container node onto the other part of super-convergence container node to run.
In summary, the embodiments of the present invention provide a scheduling method and apparatus for a super-converged cluster based on a virtualized container, and a physical host. By configuring corresponding super-fusion services for the virtualized containers, each virtualized container can be applied not only in a light-weight scene, but also in a heavy-weight scene such as an application super-fusion cluster, so that container virtualization can be more widely applied.
The above description is only an example of the present application and is not intended to limit the scope of the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. A physical host, comprising: one or more processors for executing program instructions, memory of different forms;
the memory is used for storing programs;
the processor is used for calling and running the program in the memory, so that the physical host can create a plurality of virtualized containers on the physical host based on the same kernel of the physical host and configure corresponding super-fusion services for each virtualized container, wherein each virtualized container configured with the corresponding super-fusion service is a super-fusion container node, the plurality of super-fusion container nodes form a super-fusion cluster, and finally, the processor can schedule the super-fusion services on the super-fusion cluster according to the running condition of the super-fusion cluster so as to realize load balancing of the super-fusion cluster.
2. The physical host of claim 1, further comprising a communication interface, a bus.
3. A dispatching method of a super-converged cluster based on a virtualized container is characterized by comprising the following steps: the method comprises the following steps:
step S100: creating a plurality of virtualized containers on a physical host based on the same kernel of the physical host;
step S200: configuring corresponding super-fusion services for each virtualized container, wherein each virtualized container configured with the corresponding super-fusion services is a super-fusion container node, and a plurality of super-fusion container nodes form a super-fusion cluster;
step S300: and scheduling the super-convergence service on the super-convergence cluster according to the running condition of the super-convergence cluster.
4. The method according to claim 3, wherein in step S300, the physical host obtains the load generated by each super-convergence container node running the super-convergence service, determines a part of super-convergence container nodes with the load greater than a threshold value from the super-convergence cluster, and determines another part of super-convergence container nodes with the load less than or equal to the threshold value; then, the physical host dispatches part of the super-convergence service on one part of the super-convergence container nodes to another part of the super-convergence container for running, so that the load of each dispatched super-convergence container node is smaller than or equal to a threshold value.
5. The method according to claim 4, wherein in step S300, the physical host obtains the loads generated by each super-convergence container node running the super-convergence service, and then the physical host determines the threshold value between the maximum value and the minimum value according to the maximum value and the minimum value of the loads generated by each super-convergence container node running the super-convergence service: and finally, the physical host determines a part of super-fusion container nodes with the load greater than the threshold value and another part of super-fusion container nodes with the load less than or equal to the threshold value from the super-fusion cluster according to the load generated by the super-fusion service operated by each super-fusion container node and the threshold value.
6. The method according to claim 5, wherein, in the step S300, when scheduling the super convergence service, the super convergence service includes: the storage service, the network service and the computing service, therefore, the physical host dispatches one or two of the storage service, the network service and the computing service on one part of the super-convergence container node to another part of the super-convergence container node to run.
7. A dispatching device of a super-converged cluster based on a virtualized container is characterized by comprising:
the system comprises a container creating module, a storage module and a processing module, wherein the container creating module is used for creating a plurality of virtualized containers on a physical host based on the same inner core of the physical host;
the container configuration module is used for configuring corresponding super-fusion services for each virtualized container, wherein each virtualized container configured with the corresponding super-fusion services is a super-fusion container node, and a plurality of super-fusion container nodes form a super-fusion cluster;
and the cluster scheduling module is used for scheduling the super-fusion service on the super-fusion cluster according to the running condition of the super-fusion cluster.
8. The apparatus according to claim 7, wherein the cluster scheduling module is specifically configured to obtain a load generated by each super-convergence container node running a super-convergence service, determine, from the super-convergence cluster, a part of the super-convergence container nodes having a load greater than a threshold, and determine another part of the super-convergence container nodes having a load less than or equal to the threshold; and scheduling the partial super-convergence service on one part of super-convergence container nodes to the other part of super-convergence container nodes for operation, so that the load of each scheduled super-convergence container node is less than or equal to the threshold.
9. The apparatus according to claim 8, wherein the cluster scheduling module is specifically configured to determine the threshold between the maximum and the minimum according to a maximum and a minimum of the loads generated by each super-convergence container node operating the super-convergence service, determine a part of the super-convergence container nodes from the super-convergence cluster where the loads are greater than the threshold according to the loads generated by each super-convergence container node operating the super-convergence service and the threshold, and determine another part of the super-convergence container nodes where the loads are less than or equal to the threshold.
10. The apparatus of claim 9, wherein the super convergence service comprises: the cluster scheduling module is further used for scheduling one or two of the storage service, the network service and the computing service on one part of the super-convergence container nodes to another part of the super-convergence container nodes for operation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011086307.XA CN112217895A (en) | 2020-10-12 | 2020-10-12 | Virtualized container-based super-fusion cluster scheduling method and device and physical host |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011086307.XA CN112217895A (en) | 2020-10-12 | 2020-10-12 | Virtualized container-based super-fusion cluster scheduling method and device and physical host |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112217895A true CN112217895A (en) | 2021-01-12 |
Family
ID=74052736
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011086307.XA Pending CN112217895A (en) | 2020-10-12 | 2020-10-12 | Virtualized container-based super-fusion cluster scheduling method and device and physical host |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112217895A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108089912A (en) * | 2017-12-19 | 2018-05-29 | 深信服科技股份有限公司 | A kind of virtual machine surpasses emerging system construction method and device with container |
| US20190034237A1 (en) * | 2017-02-25 | 2019-01-31 | Vmware, Inc. | Methods and apparatus to manage compute resources in a hyperconverged infrastructure computing environment |
| CN109313544A (en) * | 2016-05-23 | 2019-02-05 | W·特纳 | The super emerging system framework of the deployment based on container with virtual machine |
| CN109684071A (en) * | 2017-10-18 | 2019-04-26 | 慧与发展有限责任合伙企业 | Any distribution of the workload between super aggregators |
| CN110597623A (en) * | 2019-08-13 | 2019-12-20 | 平安普惠企业管理有限公司 | Container resource allocation method and device, computer equipment and storage medium |
-
2020
- 2020-10-12 CN CN202011086307.XA patent/CN112217895A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109313544A (en) * | 2016-05-23 | 2019-02-05 | W·特纳 | The super emerging system framework of the deployment based on container with virtual machine |
| US20190034237A1 (en) * | 2017-02-25 | 2019-01-31 | Vmware, Inc. | Methods and apparatus to manage compute resources in a hyperconverged infrastructure computing environment |
| CN109684071A (en) * | 2017-10-18 | 2019-04-26 | 慧与发展有限责任合伙企业 | Any distribution of the workload between super aggregators |
| CN108089912A (en) * | 2017-12-19 | 2018-05-29 | 深信服科技股份有限公司 | A kind of virtual machine surpasses emerging system construction method and device with container |
| CN110597623A (en) * | 2019-08-13 | 2019-12-20 | 平安普惠企业管理有限公司 | Container resource allocation method and device, computer equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 李强: "QEMU KVM源码解析与应用", 机械工业出版社 * |
| 毛祺等: "基于Docker Swarm集群的容器迁移策略的实现", 《信息技术》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111078363B (en) | NUMA node scheduling method, device, equipment and medium of virtual machine | |
| US10334034B2 (en) | Virtual machine live migration method, virtual machine deployment method, server, and cluster system | |
| CN105052074B (en) | For providing method, system and the computer-readable medium of virtualization diameter network framework and the diameter resource instances for portfolio to be routed to D ynamic instantiation | |
| US8954982B2 (en) | Resource management using reliable and efficient delivery of application performance information in a cloud computing system | |
| CN107122233B (en) | TSN service-oriented multi-VCPU self-adaptive real-time scheduling method | |
| US20120117242A1 (en) | Service linkage system and information processing system | |
| CN110838939B (en) | Scheduling method based on lightweight container and edge Internet of things management platform | |
| Ullah et al. | Task classification and scheduling based on K-means clustering for edge computing | |
| CN105491150A (en) | Load balance processing method based on time sequence and system | |
| CN114579285B (en) | Task running system and method and computing device | |
| CN112162835A (en) | Scheduling optimization method for real-time tasks in heterogeneous cloud environment | |
| KR102052964B1 (en) | Method and system for scheduling computing | |
| CN105100180A (en) | Cluster node dynamic loading method, device and system | |
| CN115686805A (en) | GPU resource sharing method and device, and GPU resource sharing scheduling method and device | |
| CN111459681B (en) | Dynamic elastic telescoping method based on micro-service load | |
| CN112860396A (en) | GPU (graphics processing Unit) scheduling method and system based on distributed deep learning | |
| CN105208111A (en) | Information processing method and physical machine | |
| CN109597674A (en) | A kind of shared virtualization pool share dispatching method and system | |
| Hamzeh et al. | A new approach to calculate resource limits with fairness in kubernetes | |
| CN105653347A (en) | Server, resource management method and virtual machine manager | |
| CN108829516B (en) | Resource virtualization scheduling method for graphic processor | |
| CN112217895A (en) | Virtualized container-based super-fusion cluster scheduling method and device and physical host | |
| CN113986497B (en) | Queue scheduling method, device and system based on multi-tenant technology | |
| CN107783823A (en) | A kind of load-balancing method and device | |
| CN110874256B (en) | Computing cluster updating system, method and device |
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 |