CN105573815B - A kind of method and device of virtual machine (vm) migration - Google Patents

A kind of method and device of virtual machine (vm) migration Download PDF

Info

Publication number
CN105573815B
CN105573815B CN201510909660.6A CN201510909660A CN105573815B CN 105573815 B CN105573815 B CN 105573815B CN 201510909660 A CN201510909660 A CN 201510909660A CN 105573815 B CN105573815 B CN 105573815B
Authority
CN
China
Prior art keywords
node
relay node
relay
virtual machine
source
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
CN201510909660.6A
Other languages
Chinese (zh)
Other versions
CN105573815A (en
Inventor
郑毅
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.)
China United Network Communications Group Co Ltd
Original Assignee
China United Network Communications Group 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 China United Network Communications Group Co Ltd filed Critical China United Network Communications Group Co Ltd
Priority to CN201510909660.6A priority Critical patent/CN105573815B/en
Publication of CN105573815A publication Critical patent/CN105573815A/en
Application granted granted Critical
Publication of CN105573815B publication Critical patent/CN105573815B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44Arrangements for executing specific programs
    • G06F9/455Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
    • G06F9/45533Hypervisors; Virtual machine monitors
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46Multiprogramming arrangements
    • G06F9/48Program initiating; Program switching, e.g. by interrupt
    • G06F9/4806Task transfer initiation or dispatching
    • G06F9/4843Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
    • G06F9/485Task life-cycle, e.g. stopping, restarting, resuming execution
    • G06F9/4856Task life-cycle, e.g. stopping, restarting, resuming execution resumption being on a different machine, e.g. task migration, virtual machine migration

Abstract

The invention discloses a kind of methods of virtual machine (vm) migration, are related to field of communication technology, and the distance limitation migrated online is effectively relieved.In the present invention, when virtual machine needs to do online migration over long distances between two nodes apart from each other, from the limitation according to storage I/O time delay, several relay nodes are first selected, in transition process, it sends all relay nodes and destination node simultaneously by storing data.When start node and a nearest node meet transition condition, triggers and migrated to first relay node.Meanwhile the network relevant configuration of start node is transferred to first relay node, realize the purpose that flow is guided to first relay node.After the completion of this process, start node closes and discharges related resource.First relay node replaces start node, continues to initiate the migration to next node, repeats above-mentioned process, until virtual machine finally moves to destination node.During the embodiment of the present invention is suitable for virtual machine (vm) migration.

Description

A kind of method and device of virtual machine (vm) migration
Technical field
The present invention relates to field of communication technology more particularly to a kind of method and devices of virtual machine (vm) migration.
Background technique
With the development of communication technology, especially virtualization technology is universal, and cloud computation data center is usually using virtual Machine executes task.In practical applications, due to energy saving, the standby guarantee of calamity, business migration, the nearby needs such as service, often By the method for virtual machine (vm) migration without interrupting the service, the physical location change of service node is realized.
Virtual machine (vm) migration needs to complete two parts work, first is that the migration of system mode.This refers to the behaviour on source host Make system and application program is moved to destination host, and can be operated normally on destination host.Second is that storage state turns It moves.If migration front and back two virtual machine shares storage medium, which be can be omitted.If two virtual machines in migration front and back Storage medium is not shared, then is needed also consistent by synchronous hold mode between two storage mediums.
During virtual machine (vm) migration, whether the outward service run thereon is interrupted, and can be classified as migrating offline With online migration.
Relative to offline migration, due to having ensured business continuance, application is more extensive for online migration.Online migration In the process, due in transition process business do not interrupt, the system mode and storage state of source virtual machine are still constantly changing.In order to Guarantee that migration front and back system is synchronous with storage state, the dirty data being written in transition process can be notified mesh by source virtual machine Virtual machine.When the two state is very nearly the same, source host is suspended, and there is no memory refreshings.Last dirty data is passed Purpose virtual machine is transported to, entire transition process is completed.For the continuity for ensureing business, it is desirable that this dirty data is sufficiently small, not shadow External service performance after ringing destination host starting.It is therefore desirable to which the synchronization delayed time between source virtual machine and purpose virtual machine is enough It is small, and the propagation delay time of the time delay i.e. synchronization signal in a fiber.The time delay limits between source host and destination host Distance, limit the availability and flexibility ratio migrated online.
Summary of the invention
The embodiment of the present invention provides a kind of method and device of virtual machine (vm) migration, and the distance limit migrated online is effectively relieved System.
In order to achieve the above objectives, the embodiment of the present invention adopts the following technical scheme that
The embodiment of the invention provides a kind of methods of virtual machine (vm) migration, comprising:
According to the spacing between system synchronisation requirement and source node and destination node, at least one relay node is determined;
The system mode of virtual machine in source node and current storage status are copied to all subsequent relay nodes and mesh Node;
When needing to replicate there is no new dirty data between the source node and first relay node, by the source The network configuration of node is transferred to first relay node, while hanging up the source node;First relay node is With the source node apart from nearest relay node at least one determining described relay node;
The dirty data that virtual machine in first relay node generates is copied to all subsequent relay nodes and purpose section Point;
It, will be described when needing to replicate there is no new dirty data between first relay node and the second relay node The network configuration of first relay node is transferred to second relay node, while hanging up first relay node;Described Two relay nodes are at least one fixed described relay node and in nearest subsequent of the first relay node distance After node;
And so on, until there is no new dirty datas to need again between the last one relay node and the destination node When processed, the network configuration of the last one relay node is transferred to the destination node, at the same hang up it is described the last one Relay node, so that the virtual machine of the source node operates in the destination node.
The embodiment of the invention also provides a kind of devices of virtual machine (vm) migration, comprising:
Determination unit, for determining at least according to the spacing between system synchronisation requirement and source node and destination node One relay node;
Copied cells, it is all subsequent for the system mode of virtual machine in source node and current storage status to be copied to Relay node and destination node;
Buanch unit, for when there is no new dirty datas to need again between the source node and first relay node When processed, the network configuration of the source node is transferred to first relay node, while hanging up the source node;Described first Relay node is with the source node at least one fixed described relay node apart from nearest relay node;
The replica node, be also used to by first relay node virtual machine generate dirty data be copied to it is all after Continuous relay node and destination node;
The buanch unit is also used to when there is no new dirty numbers between first relay node and the second relay node When according to needing to replicate, the network configuration of first relay node is transferred to second relay node, while described in hang-up First relay node;Second relay node is to save at least one fixed described relay node with first relaying Point is apart from nearest subsequent relay node;And so on, until not deposited between the last one relay node and the destination node When new dirty data needs to replicate, the network configuration of the last one relay node is transferred to the destination node, together When hang up the last one described relay node so that the virtual machine of the source node operates in the destination node.
The method and device of a kind of virtual machine (vm) migration provided in an embodiment of the present invention, when virtual machine is needed apart from each other When doing online migration over long distances between two nodes, which can first select several relayings to save from the limitation according to storage I/O time delay Point, in transition process, which first can send all relay nodes and destination node for storing data simultaneously.When initial section When point meets transition condition with a nearest node, triggers and migrated to first relay node.Meanwhile by the net of start node Network relevant configuration is transferred to first relay node, realizes the purpose that flow is guided to first relay node.This process is complete Cheng Hou, start node close and discharge related resource.First relay node replaces start node, continues to initiate to next section The migration of point repeats above-mentioned process, until virtual machine finally moves to destination node.Since storage is to be simultaneously sent to migration section All nodes after point are greatly saved storage synchronization time, ensure that long-distance migration, business during subsequent migration It is not offline.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with It obtains other drawings based on these drawings.
Fig. 1 is a kind of composition block diagram of virtual machine (vm) migration system provided in an embodiment of the present invention;
Fig. 2 is a kind of method flow diagram of virtual machine (vm) migration provided in an embodiment of the present invention;
Fig. 3 is a kind of composition block diagram of the device of virtual machine (vm) migration provided in an embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other Embodiment shall fall within the protection scope of the present invention.
The embodiment of the present invention is supplied to a kind of method of virtual machine (vm) migration, is suitable for a kind of virtual machine (vm) migration system, Composition is as shown in Figure 1, include virtual platform management system, network SDN controller, database, source node, several relayings section Point, destination node.
Virtual platform management system is responsible for the management of virtual machine and storage in all nodes.It is responsible in all nodes Select one or more relay nodes of meet demand.When discovery virtual machine meets online transition condition between two neighboring node When, trigger online transition process.
Network SDN controller is responsible for the management of all meshed network equipment.
Database records current all data middle positions and its mutual transmission range.Format is as shown in the table:
Transmission range example between 1 node of table
Node A Node B Node C
Node A 0km 150km 70km
Node B 150km 0km 90km
Node C 70km 90km 0km
Source node initiates the back end of virtual machine (vm) migration.
Destination node, the back end where purpose virtual machine.
Relay node, during virtual machine (vm) migration from synergism back end, might have multiple.Synergism Be embodied in, relay node can a certain moment can substitute source node in transition process virtual machine business is externally provided, ensure industry Business is not interrupted.
It is described based on aforementioned system structure, method provided in an embodiment of the present invention is by virtual platform management system, network The process of SDN controller cooperative achievement, each self-operating of the two equipment can be configured as needed, this method as shown in Fig. 2, Include:
101, according to the spacing between system synchronisation requirement and source node and destination node, at least one relaying section is determined Point.
The specific embodiment of the step is to determine maximum node spacing according to the system synchronisation requirement;According to the source Spacing and the maximum node spacing between node and destination node, determine at least one relay node.
Wherein, maximum node spacing is determined by rigid requirements such as system synchronization delayed times, and synchronization is completed in transition process The maximum distance of two nodes.
102, the system mode of virtual machine in source node and current storage status are copied to all subsequent relay nodes And destination node.
Referring herein to system mode and current storage status not only include being related to depositing for virtual machine to be migrated in node Data, the static datas such as system data are stored up, the dynamic datas such as dirty data generated when further include virtual machine being user service.
103, when needing to replicate there is no new dirty data between the source node and first relay node, by institute The network configuration for stating source node is transferred to first relay node, while hanging up the source node.
Wherein, first relay node be at least one fixed described relay node with the source node distance Nearest relay node.
At this point, source node no longer service for user, after virtual machine (vm) migration, IP address and MAC Address are not Become, therefore the data flow that user sends can be immediately sent to the first relay node, and by the virtual machine in the first relay node Continue to service, is equivalent to virtual machine and is migrated by source node to the first relay node.The subsequent data being related to of the embodiment of the present invention are multiple System, node hang up etc. the realization principle of operations with it is similar herein.
104, the dirty data that virtual machine in first relay node generates is copied to all subsequent relay nodes and mesh Node.
It 105, will when needing to replicate there is no new dirty data between first relay node and the second relay node The network configuration of first relay node is transferred to second relay node, while hanging up first relay node.
Wherein, second relay node is to save at least one fixed described relay node with first relaying Point is apart from nearest subsequent relay node.
106, and so on, until there is no new dirty datas to need between the last one relay node and the destination node When replicating, the network configuration of the last one relay node is transferred to the destination node, while being hung up described last One relay node, so that the virtual machine of the source node operates in the destination node.
Supplementary explanation, the embodiment of the present invention do not limit the number of relay node, can not have during realizing, There can be one or more, this will be determined according between source and destination node away from the synchronous requirement of discrete system.
The method of a kind of virtual machine (vm) migration provided in an embodiment of the present invention, when virtual machine is needed in two sections apart from each other When doing online migration over long distances between point, which can first select several relay nodes from the limitation according to storage I/O time delay, In transition process, which first can send all relay nodes and destination node for storing data simultaneously.When start node with When a nearest node meets transition condition, triggers and migrated to first relay node.Meanwhile by the network phase of start node It closes configuration and is transferred to first relay node, realize the purpose that flow is guided to first relay node.After the completion of this process, Start node closes and discharges related resource.First relay node replaces start node, continues to initiate to next node Migration repeats above-mentioned process, until virtual machine finally moves to destination node.Since storage is after being simultaneously sent to migration node All nodes storage synchronization time is greatly saved, ensure that long-distance migration during subsequent migration, business not under Line.
The embodiment of the invention also provides a kind of devices of virtual machine (vm) migration, as shown in Figure 3, comprising:
Determination unit 21, for determining extremely according to the spacing between system synchronisation requirement and source node and destination node A few relay node.
Copied cells 22, for by the system mode of virtual machine in source node and current storage status be copied to it is all after Continuous relay node and destination node.
Buanch unit 23, for when there is no new dirty datas to need between the source node and first relay node When duplication, the network configuration of the source node is transferred to first relay node, while hanging up the source node;Described One relay node is with the source node at least one fixed described relay node apart from nearest relay node.
The replica node 22 is also used to for the dirty data that virtual machine in first relay node generates being copied to all Subsequent relay node and destination node.
The buanch unit 23 is also used to when there is no newly dirty between first relay node and the second relay node When data need to replicate, the network configuration of first relay node is transferred to second relay node, while hanging up institute State the first relay node;Second relay node is to relay at least one fixed described relay node with described first The nearest subsequent relay node of nodal distance;And so on, until between the last one relay node and the destination node not When needing to replicate there are new dirty data, the network configuration of the last one relay node is transferred to the destination node, The last one described relay node is hung up simultaneously, so that the virtual machine of the source node operates in the destination node.
Optionally, the determination unit 21 includes:
First determining module 211, for determining maximum node spacing according to the system synchronisation requirement.
Second determining module 212, for according to the spacing between the source node and destination node and described maximum saving Point spacing, determines at least one relay node.
The device of a kind of virtual machine (vm) migration provided in an embodiment of the present invention, when virtual machine is needed in two sections apart from each other When doing online migration over long distances between point, which can first select several relay nodes from the limitation according to storage I/O time delay, In transition process, which first can send all relay nodes and destination node for storing data simultaneously.When start node with When a nearest node meets transition condition, triggers and migrated to first relay node.Meanwhile by the network phase of start node It closes configuration and is transferred to first relay node, realize the purpose that flow is guided to first relay node.After the completion of this process, Start node closes and discharges related resource.First relay node replaces start node, continues to initiate to next node Migration repeats above-mentioned process, until virtual machine finally moves to destination node.Since storage is after being simultaneously sent to migration node All nodes storage synchronization time is greatly saved, ensure that long-distance migration during subsequent migration, business not under Line.
Through the above description of the embodiments, it is apparent to those skilled in the art that the present invention can borrow Help software that the mode of required common hardware is added to realize, naturally it is also possible to which the former is more preferably by hardware, but in many cases Embodiment.Based on this understanding, the portion that technical solution of the present invention substantially in other words contributes to the prior art Dividing can be embodied in the form of software products, which stores in a readable storage medium, such as count The floppy disk of calculation machine, hard disk or CD etc., including some instructions are used so that computer equipment (it can be personal computer, Server or the network equipment etc.) execute method described in each embodiment of the present invention.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain Lid is within protection scope of the present invention.Therefore, protection scope of the present invention should be based on the protection scope of the described claims.

Claims (4)

1. a kind of method of virtual machine (vm) migration characterized by comprising
According to the spacing between system synchronisation requirement and source node and destination node, at least one relay node is determined;
The system mode of virtual machine in source node and current storage status are copied to all subsequent relay nodes and purpose section Point;
When needing to replicate there is no new dirty data between the source node and the first relay node, by the net of the source node Network configuration is transferred to first relay node, while hanging up the source node;First relay node is fixed institute It states at least one relay node with the source node apart from nearest relay node;
The dirty data that virtual machine in first relay node generates is copied to all subsequent relay nodes and destination node;
When needing to replicate there is no new dirty data between first relay node and the second relay node, by described first The network configuration of relay node is transferred to second relay node, while hanging up first relay node;In described second After node be with first relay node at least one fixed described relay node apart from nearest subsequent relay section Point;
And so on, until needing to replicate there is no new dirty data between the last one relay node and the destination node When, the network configuration of the last one relay node is transferred to the destination node, while described in hang-up in the last one After node, so that the virtual machine of the source node operates in the destination node.
2. the method according to claim 1, wherein described according to system synchronisation requirement and source node and purpose Spacing between node determines that at least one relay node includes:
Maximum node spacing is determined according to the system synchronisation requirement;
According to the spacing and the maximum node spacing between the source node and destination node, at least one relaying section is determined Point.
3. a kind of device of virtual machine (vm) migration characterized by comprising
Determination unit, for determining at least one according to the spacing between system synchronisation requirement and source node and destination node Relay node;
Copied cells, for the system mode of virtual machine in source node and current storage status to be copied to all subsequent relays Node and destination node;
Buanch unit, for inciting somebody to action when needing to replicate there is no new dirty data between the source node and the first relay node The network configuration of the source node is transferred to first relay node, while hanging up the source node;The first relaying section Point is with the source node at least one fixed described relay node apart from nearest relay node;
The copied cells, be also used to by first relay node virtual machine generate dirty data be copied to it is all it is subsequent in After node and destination node;
The buanch unit is also used to when there is no new dirty datas to need between first relay node and the second relay node When replicating, the network configuration of first relay node is transferred to second relay node, while hanging up described first Relay node;Second relay node be at least one fixed described relay node with first relay node away from From nearest subsequent relay node;And so on, until there is no new between the last one relay node and the destination node Dirty data when needing to replicate, the network configuration of the last one relay node is transferred to the destination node, is hung simultaneously The last one described relay node is played, so that the virtual machine of the source node operates in the destination node.
4. device according to claim 3, which is characterized in that the determination unit includes:
First determining module, for determining maximum node spacing according to the system synchronisation requirement;
Second determining module, for according to the spacing and the maximum node spacing between the source node and destination node, Determine at least one relay node.
CN201510909660.6A 2015-12-10 2015-12-10 A kind of method and device of virtual machine (vm) migration Active CN105573815B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510909660.6A CN105573815B (en) 2015-12-10 2015-12-10 A kind of method and device of virtual machine (vm) migration

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510909660.6A CN105573815B (en) 2015-12-10 2015-12-10 A kind of method and device of virtual machine (vm) migration

Publications (2)

Publication Number Publication Date
CN105573815A CN105573815A (en) 2016-05-11
CN105573815B true CN105573815B (en) 2019-02-15

Family

ID=55883987

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510909660.6A Active CN105573815B (en) 2015-12-10 2015-12-10 A kind of method and device of virtual machine (vm) migration

Country Status (1)

Country Link
CN (1) CN105573815B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111064789B (en) * 2019-12-18 2022-09-20 北京三快在线科技有限公司 Data migration method and system

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104123171A (en) * 2014-06-10 2014-10-29 浙江大学 Virtual machine migrating method and system based on NUMA architecture
CN104750541A (en) * 2015-04-22 2015-07-01 成都睿峰科技有限公司 Virtual machine migration method
CN104750542A (en) * 2015-04-22 2015-07-01 成都睿峰科技有限公司 Data migration method based on cloud platform

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9477506B2 (en) * 2013-02-12 2016-10-25 Futurewei Technologies, Inc. Dynamic virtual machines migration over information centric networks
JP6160253B2 (en) * 2013-05-30 2017-07-12 富士通株式会社 Virtual machine management apparatus, virtual machine management method, and information processing system

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104123171A (en) * 2014-06-10 2014-10-29 浙江大学 Virtual machine migrating method and system based on NUMA architecture
CN104750541A (en) * 2015-04-22 2015-07-01 成都睿峰科技有限公司 Virtual machine migration method
CN104750542A (en) * 2015-04-22 2015-07-01 成都睿峰科技有限公司 Data migration method based on cloud platform

Also Published As

Publication number Publication date
CN105573815A (en) 2016-05-11

Similar Documents

Publication Publication Date Title
US11200079B2 (en) System and method for virtual machine live migration
US11320991B2 (en) Identifying sub-health object storage devices in a data storage system
CN105933391B (en) A kind of node expansion method, apparatus and system
WO2017097059A1 (en) Distributed database system and self-adaptation method therefor
CN105187464B (en) Method of data synchronization, apparatus and system in a kind of distributed memory system
WO2014082052A4 (en) Scaling computing clusters
CN103618627B (en) A kind of manage the method for virtual machine, Apparatus and system
CN105407117B (en) The methods, devices and systems of distributed backup data
CN104407911B (en) Virtual machine migration method and device
CN105095317A (en) Distributive database service management system
CN104506654A (en) Cloud computing system and backup method of dynamic host configuration protocol server
WO2017114447A1 (en) Method for forwarding packet
WO2016177231A1 (en) Dual-control-based active-backup switching method and device
JP2015509635A (en) Data storage method and apparatus
CN111026510A (en) Cross-storage thermal migration method for virtual machine in cloud environment
CN102497288A (en) Dual-server backup method and dual system implementation device
CN110262893A (en) The method, apparatus and computer storage medium of configuration mirroring memory
CN104468759A (en) Method and device for achieving application migration in PaaS platform
CN108140035A (en) The database copy method and device of distributed system
CN105573815B (en) A kind of method and device of virtual machine (vm) migration
CN112087506B (en) Cluster node management method and device and computer storage medium
KR102172607B1 (en) Method for balanced scale-out of resource on distributed and collaborative container platform environment
CN116095145B (en) Data control method and system of VPC cluster
JP2016532927A (en) System and method for managing logical volumes
JP6229684B2 (en) Storage device, storage control method, and storage control program

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant