CN103677959A - Virtual machine cluster migration method and system based on multicast - Google Patents
Virtual machine cluster migration method and system based on multicast Download PDFInfo
- Publication number
- CN103677959A CN103677959A CN201310690358.7A CN201310690358A CN103677959A CN 103677959 A CN103677959 A CN 103677959A CN 201310690358 A CN201310690358 A CN 201310690358A CN 103677959 A CN103677959 A CN 103677959A
- Authority
- CN
- China
- Prior art keywords
- virtual machine
- migration
- mapping table
- controller
- cluster
- 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
Images
Landscapes
- Information Transfer Between Computers (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention provides a virtual machine cluster migration method and system based on multicast. The virtual machine cluster migration method and system based on multicast are applied to the field of scheduling systems. The method includes the following steps that when a virtual machine is migrated, a migration request of a virtual machine cluster enters a task pool; a sender obtains information on a mapping list, an API is called and migrated according to tasks of the task pool and migration of the virtual machine cluster is finished. A multicast migration mechanism and a virtual machine arrangement strategy based on comprehensive computing strength are adopted for achieving migration of the virtual machine cluster in cloud computing, consumption of network resources in the migration process is reduced and the migration efficiency is improved.
Description
Technical field
The present invention relates to dispatching system field, relate in particular to a kind of cluster virtual machine moving method and system based on multicast.
Background technology
Current, cloud computing approved by industry gradually, and cloud data center operating system realizes and be committed to practice gradually.Virtual machine (vm) migration is the core of cloud computing scheduling, and the migrating technology of virtual machine is mainly single virtual machine (vm) migration at present, from single physical machine to single physical machine.
In practical application, the form that virtual machine is applied with the form of cluster is main flow more, but the migration of cluster virtual machine is the process of serial, and transit time is long, and the network bandwidth takies height.
Summary of the invention
The invention provides a kind of cluster virtual machine moving method and system based on multicast, to address the above problem.
The invention provides a kind of cluster virtual machine moving method based on multicast.Said method comprises the following steps:
When virtual machine moves, the migration request of cluster virtual machine enters task pool;
Transmitter obtains mapping table information and according to task pool task, calls migration API, completes cluster virtual machine migration.
The present invention also provides a kind of cluster virtual machine migratory system based on multicast, comprising: controller, mapping table, scheduler, transmitter, task pool, host; Scheduler is connected with mapping table by controller; Transmitter is connected with mapping table, task pool respectively;
Scheduler, for according to the virtual machine Placement Strategy of COMPREHENSIVE CALCULATING intensity, for virtual machine is determined object host, and is updated in mapping table by controller;
Described controller, for safeguarding mapping table information;
Described mapping table, for the mapping relations of storage virtual machine and object host;
Described task pool, for the migration request of sink virtual machine cluster;
Described transmitter, for obtaining mapping table information and according to task pool task, calling migration API, completes cluster virtual machine migration.
The present invention adopts the migration mechanism of multicast and the virtual machine Placement Strategy based on COMPREHENSIVE CALCULATING intensity, realizes cluster virtual machine migration in cloud computing, has gradually lacked the consumption of Internet resources in transition process, has improved transport efficiency.
Accompanying drawing explanation
Accompanying drawing described herein is used to provide a further understanding of the present invention, forms the application's a part, and schematic description and description of the present invention is used for explaining the present invention, does not form inappropriate limitation of the present invention.In the accompanying drawings:
Figure 1 shows that the cluster virtual machine migration structural drawing of the embodiment of the present invention 1;
Figure 2 shows that the cluster virtual machine migration process flow diagram of the embodiment of the present invention 2.
Embodiment
Hereinafter with reference to accompanying drawing, also describe the present invention in detail in conjunction with the embodiments.It should be noted that, in the situation that not conflicting, embodiment and the feature in embodiment in the application can combine mutually.
The invention provides a kind of cluster virtual machine moving method based on multicast, comprise the following steps:
When virtual machine moves, the migration request of cluster virtual machine enters task pool;
Transmitter obtains mapping table information and according to task pool task, calls migration API, completes cluster virtual machine migration.
Wherein, the mapping relations of storage virtual machine and object host in described mapping table.
Wherein, the update mode of described mapping table is: scheduler, according to the virtual machine Placement Strategy of COMPREHENSIVE CALCULATING intensity, for virtual machine is determined object host, and is updated in mapping table by controller.
Wherein, scheduler is according to the virtual machine Placement Strategy of COMPREHENSIVE CALCULATING intensity, and for virtual machine is determined object host, and the process being updated in mapping table by controller is:
Scheduler, according to the virtual machine Placement Strategy of COMPREHENSIVE CALCULATING intensity, for virtual machine is determined after object host, sends definite object host information to controller;
Controller receives after described object host information, the virtual machine in renewal mapping table and the mapping relations of object host.
Wherein, the virtual machine Placement Strategy of described COMPREHENSIVE CALCULATING intensity comprises: constraint function and migration running time prediction function.
Wherein, described constraint function is: Res (e)=(Atime_cost (e)+Cdelay (e)+Eload (e))/Bbandwidth (e); Wherein, time_cost: expected time, delay: maximum network postpones, load: physical machine integrated load, bandwidth: maximum network bandwidth.
Wherein, described migration running time prediction function is: EV (k+1)=l (k+1)/l (k) ((1-p) EV (k)+pRV (k)); Wherein, EV (k+1): the k time prediction execution time of physical node; L (k): load in the time of the k time; RV (k): last time actual execution time.
The cluster virtual machine migration structural drawing that Figure 1 shows that the embodiment of the present invention 1, is described as follows:
As shown in Figure 1, comprising: controller (Controller), mapping table (Mapping Table), scheduler (Scheduler), transmitter (Sender), task pool (Task Pool), host (Host OS).
Controller (Controller), Main Function is the information of safeguarding mapping table (Mapping Table), wherein, the mapping relations of mapping table (Mapping Table) storage virtual machine and object host.
When virtual machine moves, without computation process, directly, according to mapping table information, move.
Scheduler (Scheduler), mainly moves the virtual machine Placement Strategy based on COMPREHENSIVE CALCULATING intensity, in real time for virtual machine is determined optimum object host, and is updated in mapping table (Mapping Table) by controller (Controller); Wherein, the virtual machine Placement Strategy of COMPREHENSIVE CALCULATING intensity comprises: constraint function and migration running time prediction function.
Wherein,
√ constraint function
Res(e)=(Atime_cost(e)+Cdelay(e)+Eload(e))/Bbandwidth(e)
Time_cost: expected time
Delay: maximum network postpones
Load: physical machine integrated load
Bandwidth: maximum network bandwidth
√ running time prediction function
EV(k+1)=l(k+1)/l(k)((1-p)EV(k)+pRV(k))
EV (k+1): the k time prediction execution time of physical node
L (k): load in the time of the k time
RV (k): last time actual execution time
√, under constraint condition, selects the physical node of Res minimum to dispatch
Transmitter (Sender), according to task pool task, calls migration API, carries out cluster virtual machine migration.
Wherein, task pool (Task Pool): the migration request of cluster virtual machine enters task pool, is decomposed into single migration task in batches, by Thread Pool Technology, realizes migration concurrent operations and for the control of resource occupation.
Thread pool: thread pool is a kind of multithreading processing form, adds task to queue in processing procedure then automatically starts these tasks after creating thread; Thread pool thread is all background thread, and each thread is used the storehouse size of acquiescence, with the priority operation of giving tacit consent to, and in multiple thread units.
If certain thread is idle (as waited for certain event) in Managed Code, thread pool makes all processors keep busy another worker thread of insertion; If all thread pool threads all remain busy, but in queue, comprise the work of hang-up, thread pool will create another worker thread but the number of thread surpasses maximal value never over time, surpassing peaked thread can queue up, but they will wait until after other thread completes and just start.
Migration mechanism based on multicast is the framework of this invention, comprising: controller, mapping table, scheduler, transmitter, task pool; This framework, for generating and safeguard in advance host mapping table, without calculating host position, has reduced most of calculated amount during cluster migration; According to mapping table, locate fast cluster migrating objects collection.
Virtual machine Placement Strategy based on COMPREHENSIVE CALCULATING intensity is core algorithm of the present invention, constraint function and migration running time prediction model have been proposed, constraint function has taken into full account the factors such as bandwidth, delay, integrated load, has gradually lacked the consumption of Internet resources in transition process; Running time prediction model, predicts transit time, locates fast the host of minimum consuming time, improves transport efficiency.
Task pool technology is the administration module of migration task of the present invention, adopts the technology of thread pool, when task is concurrent, has utilized expeditiously resource.
The cluster virtual machine migration process flow diagram that Figure 2 shows that the embodiment of the present invention 2, is described as follows:
Step 201: when virtual machine moves, the migration request of cluster virtual machine enters task pool;
Step 202: transmitter obtains mapping table information and according to task pool task, calls migration API, completes cluster virtual machine migration.
Wherein, the mapping relations of storage virtual machine and object host in described mapping table (Mapping Table).
Wherein, the update mode of mapping table is:
Scheduler, according to the virtual machine Placement Strategy of COMPREHENSIVE CALCULATING intensity, in real time for virtual machine is determined optimum object host, and is updated in mapping table by controller; Wherein, the virtual machine Placement Strategy of COMPREHENSIVE CALCULATING intensity comprises: constraint function and migration running time prediction function.
Wherein, scheduler according to the virtual machine Placement Strategy of COMPREHENSIVE CALCULATING intensity, is determined after optimum object host for virtual machine, to controller, is sent definite object host information; Controller receives after described object host information, the virtual machine in renewal mapping table and the mapping relations of object host.
The present invention also provides a kind of cluster virtual machine migratory system based on multicast, comprising: controller, mapping table, scheduler, transmitter, task pool, host; Scheduler is connected with mapping table by controller; Transmitter is connected with mapping table, task pool respectively;
Scheduler, for according to the virtual machine Placement Strategy of COMPREHENSIVE CALCULATING intensity, for virtual machine is determined object host, and is updated in mapping table by controller;
Described controller, for safeguarding mapping table information;
Described mapping table, for the mapping relations of storage virtual machine and object host;
Described task pool, for the migration request of sink virtual machine cluster;
Described transmitter, for obtaining mapping table information and according to task pool task, calling migration API, completes cluster virtual machine migration.
The present invention adopts the migration mechanism of multicast and the virtual machine Placement Strategy based on COMPREHENSIVE CALCULATING intensity, realizes cluster virtual machine migration in cloud computing, has gradually lacked the consumption of Internet resources in transition process, has improved transport efficiency.
The foregoing is only the preferred embodiments of the present invention, be not limited to the present invention, for a person skilled in the art, the present invention can have various modifications and variations.Within the spirit and principles in the present invention all, any modification of doing, be equal to replacement, improvement etc., within all should being included in protection scope of the present invention.
Claims (8)
1. the cluster virtual machine moving method based on multicast, is characterized in that, comprises the following steps:
When virtual machine moves, the migration request of cluster virtual machine enters task pool;
Transmitter obtains mapping table information and according to task pool task, calls migration API, completes cluster virtual machine migration.
2. method according to claim 1, is characterized in that: the mapping relations of storage virtual machine and object host in described mapping table.
3. method according to claim 1, is characterized in that: the update mode of described mapping table is: scheduler, according to the virtual machine Placement Strategy of COMPREHENSIVE CALCULATING intensity, for virtual machine is determined object host, and is updated in mapping table by controller.
4. method according to claim 3, is characterized in that: scheduler is according to the virtual machine Placement Strategy of COMPREHENSIVE CALCULATING intensity, and for virtual machine is determined object host, and the process being updated in mapping table by controller is:
Scheduler, according to the virtual machine Placement Strategy of COMPREHENSIVE CALCULATING intensity, for virtual machine is determined after object host, sends definite object host information to controller;
Controller receives after described object host information, the virtual machine in renewal mapping table and the mapping relations of object host.
5. according to the method described in claim 3 or 4, it is characterized in that: the virtual machine Placement Strategy of described COMPREHENSIVE CALCULATING intensity comprises: constraint function and migration running time prediction function.
6. method according to claim 5, is characterized in that, described constraint function is: Res (e)=(Atime_cost (e)+Cdelay (e)+Eload (e))/Bbandwidth (e); Wherein, time_cost: expected time, delay: maximum network postpones, load: physical machine integrated load, bandwidth: maximum network bandwidth.
7. method according to claim 5, is characterized in that, described migration running time prediction function is: EV (k+1)=l (k+1)/l (k) ((1-p) EV (k)+pRV (k)); Wherein, EV (k+1): the k time prediction execution time of physical node; L (k): load in the time of the k time; RV (k): last time actual execution time.
8. the cluster virtual machine migratory system based on multicast, is characterized in that, comprising: controller, mapping table, scheduler, transmitter, task pool, host; Scheduler is connected with mapping table by controller; Transmitter is connected with mapping table, task pool respectively;
Scheduler, for according to the virtual machine Placement Strategy of COMPREHENSIVE CALCULATING intensity, for virtual machine is determined object host, and is updated in mapping table by controller;
Described controller, for safeguarding mapping table information;
Described mapping table, for the mapping relations of storage virtual machine and object host;
Described task pool, for the migration request of sink virtual machine cluster;
Described transmitter, for obtaining mapping table information and according to task pool task, calling migration API, completes cluster virtual machine migration.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310690358.7A CN103677959B (en) | 2013-12-16 | 2013-12-16 | A kind of virtual machine cluster migration method and system based on multicast |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310690358.7A CN103677959B (en) | 2013-12-16 | 2013-12-16 | A kind of virtual machine cluster migration method and system based on multicast |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103677959A true CN103677959A (en) | 2014-03-26 |
| CN103677959B CN103677959B (en) | 2017-05-31 |
Family
ID=50315616
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310690358.7A Active CN103677959B (en) | 2013-12-16 | 2013-12-16 | A kind of virtual machine cluster migration method and system based on multicast |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103677959B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104144135A (en) * | 2014-07-25 | 2014-11-12 | 电子科技大学 | Resource distribution method and survivability resource distribution method used for multicast virtual network |
| CN108279972A (en) * | 2018-01-26 | 2018-07-13 | 郑州云海信息技术有限公司 | A kind of LUA virtual machines task executing method and relevant apparatus |
| CN109408195A (en) * | 2018-09-05 | 2019-03-01 | 华为技术有限公司 | Live migration of virtual machine method and device |
| CN111104206A (en) * | 2019-12-25 | 2020-05-05 | 曙光信息产业(北京)有限公司 | Virtual machine storage migration method and device and computer equipment |
| CN111142788A (en) * | 2019-11-29 | 2020-05-12 | 浪潮电子信息产业股份有限公司 | Data migration method and device and computer readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070171921A1 (en) * | 2006-01-24 | 2007-07-26 | Citrix Systems, Inc. | Methods and systems for interacting, via a hypermedium page, with a virtual machine executing in a terminal services session |
| US20100106885A1 (en) * | 2008-10-24 | 2010-04-29 | International Business Machines Corporation | Method and Device for Upgrading a Guest Operating System of an Active Virtual Machine |
| CN101969475A (en) * | 2010-11-15 | 2011-02-09 | 张军 | Business data controllable distribution and fusion application system based on cloud computing |
| CN103345431A (en) * | 2013-07-23 | 2013-10-09 | 中国联合网络通信有限公司海南省分公司 | Service cloud platform system based on virtualization technology |
| CN103399778A (en) * | 2013-07-01 | 2013-11-20 | 华为技术有限公司 | Method and device for on-line integral migration of virtual machine |
-
2013
- 2013-12-16 CN CN201310690358.7A patent/CN103677959B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070171921A1 (en) * | 2006-01-24 | 2007-07-26 | Citrix Systems, Inc. | Methods and systems for interacting, via a hypermedium page, with a virtual machine executing in a terminal services session |
| US20100106885A1 (en) * | 2008-10-24 | 2010-04-29 | International Business Machines Corporation | Method and Device for Upgrading a Guest Operating System of an Active Virtual Machine |
| CN101969475A (en) * | 2010-11-15 | 2011-02-09 | 张军 | Business data controllable distribution and fusion application system based on cloud computing |
| CN103399778A (en) * | 2013-07-01 | 2013-11-20 | 华为技术有限公司 | Method and device for on-line integral migration of virtual machine |
| CN103345431A (en) * | 2013-07-23 | 2013-10-09 | 中国联合网络通信有限公司海南省分公司 | Service cloud platform system based on virtualization technology |
Non-Patent Citations (2)
| Title |
|---|
| 王光波 等: "云环境下面向负载均衡的分布式虚拟机迁移研究", 《计算机应用与软件》 * |
| 程春玲 等: "基于遗传算法的层次化云资源监测方法", 《南京大学学报（自然科学）》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104144135A (en) * | 2014-07-25 | 2014-11-12 | 电子科技大学 | Resource distribution method and survivability resource distribution method used for multicast virtual network |
| CN104144135B (en) * | 2014-07-25 | 2017-06-13 | 电子科技大学 | Resource allocation methods for multicast virtual network and anti-ruin resource allocation methods |
| CN108279972A (en) * | 2018-01-26 | 2018-07-13 | 郑州云海信息技术有限公司 | A kind of LUA virtual machines task executing method and relevant apparatus |
| CN109408195A (en) * | 2018-09-05 | 2019-03-01 | 华为技术有限公司 | Live migration of virtual machine method and device |
| CN111142788A (en) * | 2019-11-29 | 2020-05-12 | 浪潮电子信息产业股份有限公司 | Data migration method and device and computer readable storage medium |
| CN111142788B (en) * | 2019-11-29 | 2021-10-15 | 浪潮电子信息产业股份有限公司 | Data migration method and device and computer readable storage medium |
| CN111104206A (en) * | 2019-12-25 | 2020-05-05 | 曙光信息产业(北京)有限公司 | Virtual machine storage migration method and device and computer equipment |
| CN111104206B (en) * | 2019-12-25 | 2023-09-01 | 曙光信息产业(北京)有限公司 | Virtual machine storage migration method and device and computer equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103677959B (en) | 2017-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2017080273A1 (en) | Task management methods and system, and computer storage medium | |
| US8056083B2 (en) | Dividing a computer job into micro-jobs for execution | |
| US10467054B2 (en) | Resource management method and system, and computer storage medium | |
| CN103677959A (en) | Virtual machine cluster migration method and system based on multicast | |
| WO2012103728A1 (en) | Method for dispatching central processing unit of hotspot domain virtual machine and virtual machine system | |
| CN103927225A (en) | Multi-core framework Internet information processing and optimizing method | |
| CN105187327A (en) | Distributed message queue middleware | |
| KR20130087257A (en) | Method and apparatus for resource allocation of gpu | |
| CN108681481B (en) | Service request processing method and device | |
| CN112162835A (en) | Scheduling optimization method for real-time tasks in heterogeneous cloud environment | |
| CN106598740A (en) | System and method for limiting CPU (Central Processing Unit) occupancy rate of multi-thread program | |
| CN109582436A (en) | Fine granularity preemptive type resource scheduling system and method based on container cluster platform | |
| WO2016074130A1 (en) | Batch processing method and device for system invocation commands | |
| CN103488531A (en) | Software and hardware mixing real-time task scheduling method based on multi-core processor and FPGA | |
| CN113986497B (en) | Queue scheduling method, device and system based on multi-tenant technology | |
| US10853133B2 (en) | Method and apparatus for scheduling tasks to a cyclic schedule | |
| CN109656716B (en) | Slurm job scheduling method and system | |
| CN106354555A (en) | Operation system process scheduling calculation method | |
| CN109298919B (en) | Multi-core scheduling method of soft real-time system for high-utilization-rate task set | |
| KR101377195B1 (en) | Computer micro-jobs | |
| CN108874517B (en) | Method for optimizing utilization rate division energy consumption of standby system with fixed priority | |
| CN101976206A (en) | Interrupt handling method and device | |
| CN111930488B (en) | Priority inheritance method and system for task scheduling of operating system | |
| KR20150089665A (en) | Appratus for workflow job scheduling | |
| CN103777995A (en) | Synchronization optimized dispatching system and dispatching method based on group dispatching in virtualization environment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |