CN105573815A - Virtual machine migration method and device - Google Patents
Virtual machine migration method and device Download PDFInfo
- Publication number
- CN105573815A CN105573815A CN201510909660.6A CN201510909660A CN105573815A CN 105573815 A CN105573815 A CN 105573815A CN 201510909660 A CN201510909660 A CN 201510909660A CN 105573815 A CN105573815 A CN 105573815A
- Authority
- CN
- China
- Prior art keywords
- node
- via node
- virtual machine
- migration
- destination
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/48—Program initiating; Program switching, e.g. by interrupt
- G06F9/4806—Task transfer initiation or dispatching
- G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
- G06F9/485—Task life-cycle, e.g. stopping, restarting, resuming execution
- G06F9/4856—Task 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 virtual machine migration method relating to the communication technical field. In adoption of the method, the distance restriction of online migration can be effectively relieved. In the method, when a virtual machine needs to carry out long distance online migration between two nodes relatively far apart from each other, firstly, a plurality of relay nodes are selected according to a storage I/O delay restriction; in the migration process, storage data are simultaneously sent to all relay nodes and the target node; when the initial node and the nearest node satisfy a migration condition, a first relay node is triggered to migrate; meanwhile, the network related configuration of the initial node is transferred to the first relay node, thus guiding traffic to the first relay node; after the process is finished, the initial node closes and releases related resources; the initial node is replaced by the first relay node; the first relay node continues to initiate the migration to the next node; the process is repeated until the virtual machine is migrated to the target node. The method and the device of the invention are applicable to a virtual machine migration process.
Description
Technical field
The present invention relates to communication technical field, particularly relate to a kind of method and device of virtual machine (vm) migration.
Background technology
Along with the development of the communication technology, especially Intel Virtualization Technology is universal, and cloud computation data center uses virtual machine to execute the task usually.In actual applications, owing to saving energy consumption, the standby needs such as guarantee, business migration, nearby service of calamity, often will by the method for virtual machine (vm) migration when non-interrupting service, the physical location realizing service node changes.
Virtual machine (vm) migration has needed two parts work, and one is the migration of system state.This refers to and the operating system on source host and application program is moved to destination host, and normally can run on destination host.Two is transfers of store status.If two virtual machines share storage medium before and after migration, then this step can be omitted.If two virtual machines do not share storage medium before and after migration, then need between two storage mediums also consistent by synchronous hold mode.
According in virtual machine (vm) migration process, whether the outward service that it runs interrupts, and off-line can be divided into again to move and online migration.
Relative to off-line migration, move owing to having ensured business continuance online, therefore apply more extensive.In online transition process, because in transition process, business is not interrupted, the system state of source virtual machine and store status are still in continuous change.Synchronous in order to system and store status before and after ensureing to move, source virtual machine can be notified object virtual machine by transition process by the dirty data rewritten.Until when both states are very nearly the same, source host is suspended, no longer include memory refreshing.Last dirty data is transferred to object virtual machine, completes whole transition process.For ensureing the continuity of business, requiring that this dirty data is enough little, not affecting the external service performance after destination host startup.Therefore, require that the synchronization delayed time between source virtual machine and object virtual machine is enough little, and this time delay i.e. synchronizing signal propagation delay time in a fiber.This time delay limits the distance between source host and destination host, limits availability and the flexibility ratio of online migration.
Summary of the invention
Embodiments of the invention provide a kind of method and device of virtual machine (vm) migration, effectively alleviate the distance limit of online migration.
For achieving the above object, embodiments of the invention adopt following technical scheme:
Embodiments provide a kind of method of virtual machine (vm) migration, comprising:
According to system synchronization demand and the spacing between source node and destination node, determine at least one via node;
The system state of virtual machine in source node and current storage status are copied to all subsequent relay nodes and destination node;
Between described source node and described first via node, there is not new dirty data when needing to copy, the network configuration of described source node is transferred to described first via node, hangs up described source node simultaneously; Described first via node is via node nearest with described source node in fixed at least one via node described;
The dirty data that virtual machine in described first via node produces is copied to all subsequent relay nodes and destination node;
Between described first via node and the second via node, there is not new dirty data when needing to copy, the network configuration of described first via node is transferred to described second via node, hangs up described first via node simultaneously; Described second via node is subsequent relay node nearest with described first via node in fixed at least one via node described;
The like, until there is not new dirty data between last via node and described destination node when needing to copy, the network configuration of last via node described is transferred to described destination node, hang up last via node described simultaneously, operate in described destination node to make the virtual machine of described source node.
The embodiment of the present invention additionally provides a kind of device of virtual machine (vm) migration, comprising:
Determining unit, for according to system synchronization demand and the spacing between source node and destination node, determines at least one via node;
Copied cells, for being copied to all subsequent relay nodes and destination node by the system state of virtual machine in source node and current storage status;
Buanch unit, for do not exist between described source node and described first via node new dirty data need to copy time, the network configuration of described source node is transferred to described first via node, hangs up described source node simultaneously; Described first via node is via node nearest with described source node in fixed at least one via node described;
Described replica node, the dirty data also for being produced by virtual machine in described first via node is copied to all subsequent relay nodes and destination node;
Described buanch unit, also for do not exist between described first via node and the second via node new dirty data need to copy time, the network configuration of described first via node is transferred to described second via node, hangs up described first via node simultaneously; Described second via node is subsequent relay node nearest with described first via node in fixed at least one via node described; The like, until there is not new dirty data between last via node and described destination node when needing to copy, the network configuration of last via node described is transferred to described destination node, hang up last via node described simultaneously, operate in described destination node to make the virtual machine of described source node.
The method of a kind of virtual machine (vm) migration that the embodiment of the present invention provides and device, when virtual machine needs to do length between apart from each other two nodes apart from when moving online, this system can from the restriction according to storage I/O time delay, first select some via nodes, in transition process, storage data first can be sent to all via nodes and destination node by this system simultaneously.When start node and nearest node meet transition condition, trigger to first via node migration.Meanwhile, the network relevant configuration of start node is transferred to first via node, realize object flow being guided to first via node.After this process completes, start node is closed and is discharged related resource.First via node replaces start node, continues to initiate the migration to next node, repeats above-mentioned flow process, until virtual machine finally moves to destination node.Because storage is all nodes that synchronized transmission arrives after migration node, in subsequent migration process, greatly save and store lock in time, ensure that long-distance migration, business does not roll off the production line.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
The composition frame chart of a kind of virtual machine (vm) migration system that Fig. 1 provides for the embodiment of the present invention;
The method flow diagram of a kind of virtual machine (vm) migration that Fig. 2 provides for the embodiment of the present invention;
The composition frame chart of the device of a kind of virtual machine (vm) migration that Fig. 3 provides for the embodiment of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.
The embodiment of the present invention is supplied to a kind of method of virtual machine (vm) migration, be applicable to a kind of virtual machine (vm) migration system, its composition as shown in Figure 1, comprises virtual platform management system, network SDN controller, database, source node, some via nodes, destination node.
Virtual platform management system, is responsible for the management of virtual machine and storage in all nodes.Be responsible for the one or more via nodes selecting to satisfy the demands in all nodes.When finding that virtual machine meets online transition condition between adjacent two nodes, trigger online transition process.
Network SDN controller, is responsible for the management of all meshed network equipment.
Database, records current all data centre positions and mutual transmission range thereof.Form is as shown in the table:
Table 1 inter-node transmission distance examples
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 at object virtual machine place.
Via node, plays the back end of synergism in virtual machine (vm) migration process, may have multiple.Synergism is embodied in, and via node externally can provide business by the virtual machine of a certain moment meeting alternate source node in transition process, and guarantee business is not interrupted.
Describe based on aforementioned system structure, the method that the embodiment of the present invention provides is by virtual platform management system, network SDN controller cooperative achievement, and the flow process of these two each self-operatings of equipment can be configured as required, and the method as shown in Figure 2, comprising:
101, according to system synchronization demand and the spacing between source node and destination node, at least one via node is determined.
The embodiment of this step is according to described system synchronization demand determination maximum node spacing; According to the spacing between described source node and destination node and described maximum node spacing, determine at least one via node.
Wherein, maximum node spacing is decided by hard requirement such as system synchronization time delays, completes the maximum distance of two synchronous nodes in transition process.
102, the system state of virtual machine in source node and current storage status are copied to all subsequent relay nodes and destination node.
The system state herein mentioned and current storage status not only comprise in node the static data such as storage data, system data relating to virtual machine to be migrated, and also comprising virtual machine is the dynamic datas such as the dirty data that produces when serving of user.
103, between described source node and described first via node, there is not new dirty data when needing to copy, the network configuration of described source node is transferred to described first via node, hangs up described source node simultaneously.
Wherein, described first via node is via node nearest with described source node in fixed at least one via node described.
Now, source node is no longer for user carries out having served, after virtual machine (vm) migration, IP address and MAC Address constant, therefore the data stream that user sends can directly be sent to the first via node, and continue service by the virtual machine in the first via node, be equivalent to virtual machine and migrate to the first via node by source node.What the follow-up data Replica, node hang-up etc. related to of the embodiment of the present invention operated realizes principle with similar herein.
104, the dirty data that virtual machine in described first via node produces is copied to all subsequent relay nodes and destination node.
105, between described first via node and the second via node, there is not new dirty data when needing to copy, the network configuration of described first via node is transferred to described second via node, hangs up described first via node simultaneously.
Wherein, described second via node is subsequent relay node nearest with described first via node in fixed at least one via node described.
106, the like, until there is not new dirty data between last via node and described destination node when needing to copy, the network configuration of last via node described is transferred to described destination node, hang up last via node described simultaneously, operate in described destination node to make the virtual machine of described source node.
Supplementary notes, do not limit the number of via node, can not have, can have one or more yet in embodiment of the present invention implementation procedure, this will require to decide according to the internodal Distance geometry system synchronization of source and destination.
The method of a kind of virtual machine (vm) migration that the embodiment of the present invention provides, when virtual machine needs to do length between apart from each other two nodes apart from when moving online, this system can from the restriction according to storage I/O time delay, first select some via nodes, in transition process, storage data first can be sent to all via nodes and destination node by this system simultaneously.When start node and nearest node meet transition condition, trigger to first via node migration.Meanwhile, the network relevant configuration of start node is transferred to first via node, realize object flow being guided to first via node.After this process completes, start node is closed and is discharged related resource.First via node replaces start node, continues to initiate the migration to next node, repeats above-mentioned flow process, until virtual machine finally moves to destination node.Because storage is all nodes that synchronized transmission arrives after migration node, in subsequent migration process, greatly save and store lock in time, ensure that long-distance migration, business does not roll off the production line.
The embodiment of the present invention additionally provides a kind of device of virtual machine (vm) migration, as shown in Figure 3, comprising:
Determining unit 21, for according to system synchronization demand and the spacing between source node and destination node, determines at least one via node.
Copied cells 22, for being copied to all subsequent relay nodes and destination node by the system state of virtual machine in source node and current storage status.
Buanch unit 23, for do not exist between described source node and described first via node new dirty data need to copy time, the network configuration of described source node is transferred to described first via node, hangs up described source node simultaneously; Described first via node is via node nearest with described source node in fixed at least one via node described.
Described replica node 22, the dirty data also for being produced by virtual machine in described first via node is copied to all subsequent relay nodes and destination node.
Described buanch unit 23, also for do not exist between described first via node and the second via node new dirty data need to copy time, the network configuration of described first via node is transferred to described second via node, hangs up described first via node simultaneously; Described second via node is subsequent relay node nearest with described first via node in fixed at least one via node described; The like, until there is not new dirty data between last via node and described destination node when needing to copy, the network configuration of last via node described is transferred to described destination node, hang up last via node described simultaneously, operate in described destination node to make the virtual machine of described source node.
Optionally, described determining unit 21 comprises:
First determination module 211, for according to described system synchronization demand determination maximum node spacing.
Second determination module 212, for according to the spacing between described source node and destination node and described maximum node spacing, determines at least one via node.
The device of a kind of virtual machine (vm) migration that the embodiment of the present invention provides, when virtual machine needs to do length between apart from each other two nodes apart from when moving online, this system can from the restriction according to storage I/O time delay, first select some via nodes, in transition process, storage data first can be sent to all via nodes and destination node by this system simultaneously.When start node and nearest node meet transition condition, trigger to first via node migration.Meanwhile, the network relevant configuration of start node is transferred to first via node, realize object flow being guided to first via node.After this process completes, start node is closed and is discharged related resource.First via node replaces start node, continues to initiate the migration to next node, repeats above-mentioned flow process, until virtual machine finally moves to destination node.Because storage is all nodes that synchronized transmission arrives after migration node, in subsequent migration process, greatly save and store lock in time, ensure that long-distance migration, business does not roll off the production line.
Through the above description of the embodiments, those skilled in the art can be well understood to the mode that the present invention can add required common hardware by software and realize, and can certainly pass through hardware, but in a lot of situation, the former is better embodiment.Based on such understanding, technical scheme of the present invention can embody with the form of software product the part that prior art contributes in essence in other words, this computer software product is stored in the storage medium that can read, as the floppy disk of computing machine, hard disk or CD etc., comprise some instructions and perform method described in each embodiment of the present invention in order to make a computer equipment (can be personal computer, server, or the network equipment etc.).
The above; be only the specific embodiment of the present invention, but protection scope of the present invention is not limited thereto, is anyly familiar with those skilled in the art in the technical scope that the present invention discloses; change can be expected easily or replace, all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection domain of described claim.
Claims (4)
1. a method for virtual machine (vm) migration, is characterized in that, comprising:
According to system synchronization demand and the spacing between source node and destination node, determine at least one via node;
The system state of virtual machine in source node and current storage status are copied to all subsequent relay nodes and destination node;
Between described source node and described first via node, there is not new dirty data when needing to copy, the network configuration of described source node is transferred to described first via node, hangs up described source node simultaneously; Described first via node is via node nearest with described source node in fixed at least one via node described;
The dirty data that virtual machine in described first via node produces is copied to all subsequent relay nodes and destination node;
Between described first via node and the second via node, there is not new dirty data when needing to copy, the network configuration of described first via node is transferred to described second via node, hangs up described first via node simultaneously; Described second via node is subsequent relay node nearest with described first via node in fixed at least one via node described;
The like, until there is not new dirty data between last via node and described destination node when needing to copy, the network configuration of last via node described is transferred to described destination node, hang up last via node described simultaneously, operate in described destination node to make the virtual machine of described source node.
2. method according to claim 1, is characterized in that, described according to system synchronization demand and the spacing between source node and destination node, determines that at least one via node comprises:
According to described system synchronization demand determination maximum node spacing;
According to the spacing between described source node and destination node and described maximum node spacing, determine at least one via node.
3. a device for virtual machine (vm) migration, is characterized in that, comprising:
Determining unit, for according to system synchronization demand and the spacing between source node and destination node, determines at least one via node;
Copied cells, for being copied to all subsequent relay nodes and destination node by the system state of virtual machine in source node and current storage status;
Buanch unit, for do not exist between described source node and described first via node new dirty data need to copy time, the network configuration of described source node is transferred to described first via node, hangs up described source node simultaneously; Described first via node is via node nearest with described source node in fixed at least one via node described;
Described replica node, the dirty data also for being produced by virtual machine in described first via node is copied to all subsequent relay nodes and destination node;
Described buanch unit, also for do not exist between described first via node and the second via node new dirty data need to copy time, the network configuration of described first via node is transferred to described second via node, hangs up described first via node simultaneously; Described second via node is subsequent relay node nearest with described first via node in fixed at least one via node described; The like, until there is not new dirty data between last via node and described destination node when needing to copy, the network configuration of last via node described is transferred to described destination node, hang up last via node described simultaneously, operate in described destination node to make the virtual machine of described source node.
4. device according to claim 3, is characterized in that, described determining unit comprises:
First determination module, for according to described system synchronization demand determination maximum node spacing;
Second determination module, for according to the spacing between described source node and destination node and described maximum node spacing, determines at least one via node.
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 true CN105573815A (en) | 2016-05-11 |
CN105573815B 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) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111064789A (en) * | 2019-12-18 | 2020-04-24 | 北京三快在线科技有限公司 | Data migration method and system |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140229944A1 (en) * | 2013-02-12 | 2014-08-14 | Futurewei Technologies, Inc. | Dynamic Virtual Machines Migration Over Information Centric Networks |
CN104123171A (en) * | 2014-06-10 | 2014-10-29 | 浙江大学 | Virtual machine migrating method and system based on NUMA architecture |
US20140359616A1 (en) * | 2013-05-30 | 2014-12-04 | Fujitsu Limited | Virtual machine managing apparatus, method of managing virtual machine, and information processing system |
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 |
-
2015
- 2015-12-10 CN CN201510909660.6A patent/CN105573815B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140229944A1 (en) * | 2013-02-12 | 2014-08-14 | Futurewei Technologies, Inc. | Dynamic Virtual Machines Migration Over Information Centric Networks |
US20140359616A1 (en) * | 2013-05-30 | 2014-12-04 | Fujitsu Limited | Virtual machine managing apparatus, method of managing virtual machine, and information processing system |
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 |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111064789A (en) * | 2019-12-18 | 2020-04-24 | 北京三快在线科技有限公司 | Data migration method and system |
Also Published As
Publication number | Publication date |
---|---|
CN105573815B (en) | 2019-02-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9372726B2 (en) | Gang migration of virtual machines using cluster-wide deduplication | |
EP3620905B1 (en) | Method and device for identifying osd sub-health, and data storage system | |
CN107846358B (en) | Data transmission method, device and network system | |
Wood et al. | CloudNet: Dynamic pooling of cloud resources by live WAN migration of virtual machines | |
US10091120B2 (en) | Secondary input queues for maintaining a consistent network state | |
US10129101B2 (en) | Application driven and adaptive unified resource management for data centers with Multi-Resource Schedulable Unit (MRSU) | |
WO2017097059A1 (en) | Distributed database system and self-adaptation method therefor | |
US20140189128A1 (en) | Cluster system with calculation and storage converged | |
CN105095317A (en) | Distributive database service management system | |
WO2014082052A4 (en) | Scaling computing clusters | |
CN111638957B (en) | Method for realizing cluster sharing type public cloud load balance | |
CN102932409B (en) | The method and system that a kind of virtual machine moves online | |
JP6432955B2 (en) | Method, apparatus and system for migrating virtual network function instances | |
WO2017161979A1 (en) | Cloud platform-based method and device for managing servers | |
CN102316043B (en) | Port virtualization method, switch and communication system | |
CN109981493B (en) | Method and device for configuring virtual machine network | |
CN104506654A (en) | Cloud computing system and backup method of dynamic host configuration protocol server | |
WO2017114447A1 (en) | Method for forwarding packet | |
CN103581324A (en) | Cloud computing resource pool system and implement method thereof | |
CN111165019A (en) | Controller communication in an access network | |
CN110830574B (en) | Method for realizing intranet load balance based on docker container | |
WO2017097006A1 (en) | Real-time data fault-tolerance processing method and system | |
AU2018303662B2 (en) | Scalable statistics and analytics mechanisms in cloud networking | |
CN103729237A (en) | Method for transferring virtual machine across storage pools | |
KR102172607B1 (en) | Method for balanced scale-out of resource on distributed and collaborative container platform environment |
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 |