CN104580328A - Virtual machine migration method, device and system - Google Patents
Virtual machine migration method, device and system Download PDFInfo
- Publication number
- CN104580328A CN104580328A CN201310518434.6A CN201310518434A CN104580328A CN 104580328 A CN104580328 A CN 104580328A CN 201310518434 A CN201310518434 A CN 201310518434A CN 104580328 A CN104580328 A CN 104580328A
- Authority
- CN
- China
- Prior art keywords
- node
- address
- idle
- migration
- data block
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/56—Provisioning of proxy services
- H04L67/563—Data redirection of data network streams
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention provides a virtual machine migration method, device and system. The method comprises the following steps: determining a first address of a free node in a first super node by a first control node, wherein the free node is a node with free resource in the first super node; sending the first address of the free node to a first node by the first control node to ensure that the first node migrates a migration data block to a second node through the first address, wherein the migration data block is a part of data prepared to be migrated from the first node to the second node and the second node is arranged in a second super node. According to the virtual machine migration method, device and system, the data to be migrated in the first node is divided into a plurality of migration data blocks and the migration data blocks are migrated from the first address of the first node to the second node through corresponding free nodes, so that the influences from the virtual machine migration to the other applications connected in the migration network and the performance of the virtual machine are reduced, the scheduling as required is realized, and the utilization rate of the free resources in the data is improved.
Description
Technical field
The present invention relates to the communication technology, particularly relate to a kind of virtual machine migration method, Apparatus and system.
Background technology
Virtual machine (vm) migration is had, namely when not interrupting any host services in operating system to be migrated, by operating system migration on another one physical node in the important technology that modern virtual machine technique provides.
In prior art, virtual machine (vm) migration between source node and destination node mainly comprises: use transmission control protocol/IP(Internet Protocol), or use Convertion cable technology and long-distance inner directly to access (Remote Direct Memory Access, referred to as RDMA) mode that combines, carry out page copy between a source node and a destination node
But, virtual machine is moved to the process of destination node from source node, due to the network interface card limited bandwidth between source node and destination node, causes the hydraulic performance decline of other virtual machines be connected between source node and destination node.
Summary of the invention
The invention provides a kind of virtual machine migration method, Apparatus and system, in order to improve the performance of other virtual machines be connected between source node and destination node.
First aspect, provides a kind of virtual machine migration method, it is characterized in that, comprising:
First Controlling vertex determines the first address of the first idle node in the first supernode, described first idle node is the node of available free resource in described first supernode, and described first supernode comprises described first Controlling vertex, first node and the first idle node described at least one;
Described first Controlling vertex sends described first address of described first idle node to described first node, with make described first node by migration data block by described first address transfer to Section Point, described migration data block is a part of data preparing to move to from described first node Section Point, and described Section Point is arranged in the second supernode.
In the first possible implementation of first aspect, described first Controlling vertex, to after described first node sends described first address of described first idle node, also comprises:
Described first Controlling vertex receives the address maps message that described second Controlling vertex sends, to make to determine the mapping relations between the 3rd address of the second idle node and described first address, described address maps message comprises the mapping relations between the second address of described Section Point and the 3rd address of described second idle node, and described second idle node is the node of resource free time in described second supernode.
In first aspect or the first possible implementation of first aspect, in the implementation that the second is possible, described first Controlling vertex also comprises before sending the first address of described idle node to described first node:
Described first Controlling vertex receives the idle node request that described first node sends, and described idle node request is in order to idle node described in request dispatching;
Described first Controlling vertex sends described first address of described idle child node to described first node, comprising:
Described idle node, according to described idle node request, is distributed to described first node by described first Controlling vertex.
Second aspect, provides a kind of virtual machine migration method, comprising:
First node receives the first address of the first idle node that the first Controlling vertex sends, in order to migration data block is passed through described first address transfer to Section Point, described migration data block is a part of data preparing to move to from described first node Section Point, and described Section Point is arranged in the second supernode;
Described migration data block is moved to described Section Point by described first idle node by described first node.
In the first possible implementation of second aspect, described first node also comprises before by described first idle node described migration data block being moved to described Section Point:
Described first node sends migration data information to described first idle node, to make the address mapping relation described in described first idle node foundation and described first node between migration data block, described migration data information comprises the size information of described migration data block, and the address information of described migration data block in described first node.
In second aspect or the first possible implementation of second aspect, in the implementation that the second is possible, described first node also comprises before receiving the first address of the first idle child node that described first Controlling vertex sends:
Described first node sends idle node request to described first Controlling vertex, and described idle node request is in order to idle node described in request dispatching.
3rd aspect, provides a kind of virtual machine (vm) migration device, comprising:
Determination module, for determining the first address of the first idle node in the first supernode, described first idle node is the node of available free resource in described first supernode, and described first supernode comprises described first Controlling vertex, first node and the first idle node described at least one;
Sending module, for sending described first address of described first idle node to described first node, with make described first node by migration data block by described first address transfer to Section Point, described migration data block is a part of data preparing to move to from described first node Section Point, and described Section Point is arranged in the second supernode.
In the first possible implementation of the third aspect, also comprise: receiver module;
Described receiver module, for receiving the address maps message that described second Controlling vertex sends, to make to determine the mapping relations between the 3rd address of the second idle node and described first address, described address maps message comprises the mapping relations between the second address of described Section Point and the 3rd address of described second idle node, and described second idle node is the node of resource free time in described second supernode.
In the third aspect or the first possible implementation of the third aspect, in the implementation that the second is possible, described receiver module, also for receiving the idle node request that described first node sends, described idle node request is in order to idle node described in request dispatching;
Described sending module, also for according to described idle node request, distributes to described first node by described idle node.
4th aspect, provides a kind of virtual machine (vm) migration device, comprising:
Sending module, for receiving the first address of the first idle node that the first Controlling vertex sends, in order to migration data block is passed through described first address transfer to Section Point, described migration data block is a part of data preparing to move to from described first node Section Point, and described Section Point is arranged in the second supernode;
Transferring module, for moving to described Section Point by described first idle node by described migration data block.
In the first possible implementation of fourth aspect, described transferring module, also send migration data information for described first node to described first idle node, to make the address mapping relation described in described first idle node foundation and described first node between migration data block, described migration data information comprises the size information of described migration data block, and the address information of described migration data block in described first node.
In fourth aspect or the first possible implementation of fourth aspect, in the implementation that the second is possible, described sending module, also for sending idle node request to described first Controlling vertex, described idle node request is in order to idle node described in request dispatching.
5th aspect, provides a kind of virtual machine (vm) migration system, comprising: the virtual machine (vm) migration device as described in as arbitrary in the third aspect and the virtual machine (vm) migration device as described in fourth aspect.
The virtual machine migration method that the embodiment of the present invention provides, Apparatus and system, determine the first address of idle node in the first supernode by the first Controlling vertex, wherein, this idle node is the node of available free resource in the first supernode; Then, first Controlling vertex sends the first address of idle node to first node, with make first node by migration data block by the first address transfer to Section Point, wherein, migration data block is a part of data preparing to move to from first node Section Point, and Section Point is arranged in the second supernode.Thus achieve by prepare in first node move data be divided into multiple migration data block, and by this migration data block by corresponding idle node from the first address transfer of first node to Section Point, reduce the performance of virtual machine (vm) migration to other application be connected in migration network and virtual machine.Further, achieve scheduling on demand, and improve the utilance of the idling-resource in data.
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 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 flow chart of the virtual machine migration method that Fig. 1 provides for one embodiment of the invention;
The flow chart of the virtual machine migration method that Fig. 2 provides for another embodiment of the present invention;
The flow chart of the virtual machine migration method that Fig. 3 provides for yet another embodiment of the invention;
The structural representation of the virtual machine (vm) migration device that Fig. 4 provides for one embodiment of the invention;
The structural representation of the virtual machine (vm) migration device that Fig. 5 provides for another embodiment of the present invention;
The structural representation of the virtual machine (vm) migration device that Fig. 6 provides for yet another embodiment of the invention;
The structural representation of the virtual machine (vm) migration device that Fig. 7 provides for one embodiment of the invention;
The structural representation of the virtual machine (vm) migration device that Fig. 8 provides for another embodiment of the present invention.
Embodiment
For making the object of the embodiment of the present invention, technical scheme and advantage clearly, below in conjunction with the accompanying drawing in the embodiment of the present invention, technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is 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 virtual machine migration method that the embodiment of the present invention provides specifically can be applied to the virtual machine (vm) migration between the supernode that interconnected by internal memory shared network, the virtual machine migration method that the present embodiment provides specifically can be performed by virtual machine migration method device, and this virtual machine (vm) migration device can adopt the mode of software and/or hardware to realize.The virtual machine migration method provided the present embodiment below, Apparatus and system are described in detail.
The flow chart of the virtual machine migration method that Fig. 1 provides for one embodiment of the invention.As shown in Figure 1, the method for the present embodiment comprises:
Step 101, the first Controlling vertex determine the first address of the first idle node in the first supernode, and wherein, this first idle node is the node of available free resource in the first supernode.
In the present embodiment, the first supernode comprises the first Controlling vertex, first node and at least one idle child node.
It should be noted that, this first Controlling vertex is responsible for the network of each node and the idle condition of central processing unit in monitoring first supernode.If the network of the node that the first monitor node is determined in the first supernode is in idle condition, then determine that this node is the first idle node, and determine that this address of node is the first address of the first idle node further.
Step 102, the first Controlling vertex send the first address of the first idle node to first node, with make first node by migration data block by the first address transfer to Section Point.
In the present embodiment, migration data block is a part of data preparing to move to from first node Section Point, that is, the Data Placement that preparation is moved to Section Point from first node by first node is multiple data block, and this migration data block is one in the plurality of data block; Wherein, Section Point is arranged in the second supernode, and first node can be virutal machine memory.
Concrete, after the first Controlling vertex determines the first address of the first idle node in the first supernode, first address is sent to first node, then, the size of migration data block and migration data block correspondence are sent to this first idle node at the first address of first node by first node, then, this first idle node is monitored the migration data block of self correspondence in first node, finally, first idle node controls (NIC) by network node and self correspondence is sent to Section Point at the migration data block of first node, i.e. destination node.
It should be noted that, each first idle node correspondence address interconnect of migration data block in first node is non-intersect.
In the present embodiment, determined the first address of the first idle node in the first supernode by the first Controlling vertex, wherein, this first idle node is the node of available free resource in the first supernode; Then, first Controlling vertex sends the first address of the first idle node to first node, with make first node by migration data block by the first address transfer to Section Point, wherein, migration data block is a part of data preparing to move to from first node Section Point, and Section Point is arranged in the second supernode.Thus achieve by prepare in first node move data be divided into multiple migration data block, and by this migration data block by the first corresponding idle node from the first address transfer of first node to Section Point, reduce the performance of virtual machine (vm) migration to other application be connected in migration network and virtual machine.Further, achieve scheduling on demand, and improve the utilance of the idling-resource in data.
Optionally, after step 102, can also comprise: the first Controlling vertex receives the address maps message that the second Controlling vertex sends, to make to determine the mapping relations between the 3rd address of the second idle node and the first address, wherein, this address maps message comprises the mapping relations between the second address of Section Point and the 3rd address of the second idle node, and the second idle node is the node of resource free time in the second supernode.
Concrete, when the heavier loads of Section Point, second controller node can adopt the method similar with the first Controlling vertex, the second idle node is applied in the second supernode, in order to when receiving the migration data block of first node, receive migration data block by the second idle node, and migration data block is written in Section Point.
On the basis of above-described embodiment, before step 101, can also comprise:
First Controlling vertex receives the first idle node request that first node sends, and this first idle node request is first node in order to request dispatching first idle node;
Further, the first Controlling vertex according to idle node request, can distribute idle node to first node.
It should be noted that, first node can send idle node request to the first Controlling vertex, and this idle node request is first node in order to request dispatching idle node, and wherein, this idle node is at least one.Then, the idle node request that the first Controlling vertex sends according to first node, can inform first node by response mode by the first address of the first idle node.Such as, when virtual machine (vm) migration is initial, Data Migration includes 4 Data Migration blocks, M1, M2, M3 and M4, and the size of each Data Migration block is respectively 1GB, first node sends idle node request to the first Controlling vertex, and this idle node request needs request 3 idle node to be first node, further, first node sends the second address of Section Point to the first Controlling vertex.Then, the information of the first address of these three idle node, three available idle node N1 being detected, after N2, N3, can be sent to first node, i.e. source node by the first Controlling vertex.
The flow chart of the virtual machine migration method that Fig. 2 provides for another embodiment of the present invention.As shown in Figure 2, the method for the present embodiment comprises:
Step 201, first node receive the first address of the first idle node that the first Controlling vertex sends, in order to migration data block is passed through the first address transfer to Section Point.
Migration data block in the present embodiment is a part of data preparing to move to from first node Section Point, and wherein, Section Point is arranged in the second supernode.
Concrete, this first Controlling vertex is responsible for monitoring the idle condition of central processor CPU in the network of each node and the first supernode.If the network of the node that the first monitor node is determined in the first supernode is in idle condition, then determine that this node is the first idle node, and further this address of node is sent to first node as the first address of idle child node.
Migration data block is moved to Section Point by the first idle node by step 202, first node.
Concrete, after first node receives the first address of the first idle node that the first Controlling vertex sends, first node determines the particular location of the first idle node in the first supernode, then, first node and the first idle node are corresponding by self respectively by the NIC of self, and the data be namely responsible for are sent in the memory block of the virtual machine in Section Point.
In the present embodiment, the first address of the first idle node that the first Controlling vertex sends is received by first node, in order to migration data block is passed through the first address transfer to Section Point, then, migration data block is moved to Section Point by the first idle node by first node.Thus achieve by prepare in first node move data be divided into multiple migration data block, and by this migration data block by the first corresponding idle node from the first address transfer of first node to Section Point, reduce the performance of virtual machine (vm) migration to other application be connected in migration network and virtual machine.Further, achieve scheduling on demand, and improve the utilance of the idling-resource in data.
On the basis of above-described embodiment, after step 201, can also comprise:
First node sends migration data information to the first idle node, to make the address mapping relation in the foundation of the first idle node and first node between migration data block, wherein, this migration data information comprises the size information of this migration data block, and the address information of this migration data block in first node.
In the present embodiment, first node sends migration data information to the first idle node, each first idle node can set up the address mapping relation with migration data block in corresponding first node respectively, then, first idle node can read migration data block by the NIC of self from corresponding first node, such as, read-only memory mode is adopted directly from first node, to read data.Further, after each first idle node can set up the address mapping relation of corresponding migration data block respectively, first node locks to migration data block, to avoid the data in migration data block to be modified, guarantees the correctness of the data in migration data block.
On the basis of above-described embodiment, before step 201, can also comprise:
First node sends the first idle node request to the first Controlling vertex, and this first idle node request is described first node in order to request dispatching first idle node.
It should be noted that, the first idle node request can also comprise the number that first node needs application first idle node.
The flow chart of the virtual machine migration method that Fig. 3 provides for yet another embodiment of the invention.As shown in Figure 3, the method for the present embodiment comprises:
Step 301, first node send the first idle node request to the first Controlling vertex, and this first idle node request is described first node in order to request dispatching first idle node.
It should be noted that, this first idle node request can comprise the number of first node needs to the first idle node of the first Controlling vertex application.
Step 302, the first Controlling vertex, according to monitored results, send the first address of the first idle node to first node.
In the present embodiment, this first Controlling vertex is responsible for monitoring the idle condition of central processor CPU in the network of each node and the first supernode.First Controlling vertex is according to monitored results, and to reply the first address sending the first idle node at that time to first node, namely in the first supernode, network is in the address of node of idle condition.
Step 303, first node send migration data information to the first idle node.
Migration data information in the present embodiment comprises the size information of this migration data block, and the positional information of this migration data block in first node.Further, first node carries out locking protection to migration data block, ensures the correctness of data.
Step 304, the first idle node set up the address mapping relation between the migration data block corresponding with first node.
First idle node, by the network adapter NIC of self this locality, is sent in position corresponding to Section Point answerable migration data block by step 305, first node.
Further, on the basis of above-described embodiment, when Section Point heavier loads, Section Point can apply for the first idle node, and the concrete step 301 that adopts is to the implementation of step 304, does not repeat them here.
It should be noted that, before step 305, can also comprise:
Step 314, the first Controlling vertex receive the second address maps message that the second Controlling vertex sends.
In the present embodiment, this second address maps message comprises the second idle node and corresponding address mapping relation between Section Point, and wherein, the second idle node is the node of resource free time in the second supernode.After the first Controlling vertex receives the second address maps message of the second Controlling vertex transmission, first control point can according to the information of the first address sending the first idle node to first node, determine the corresponding relation of each idle node between first node and Section Point, thus, the migration data block of first node can be sent to Section Point by the first idle node and the second idle node.
It should be noted that, at the Data Migration that will prepare in first node to move in the process of Section Point, can after migration data block be moved to Section Point by the above-mentioned implementation method of employing, circulate above-mentioned implementation method, and only need to pay close attention to the data not having to move, i.e. dirty page.First node can continue to the first control point application idle node according to the size of data of having moved, until the data in first node reach preset value, then, first node is disposable by remaining data, namely dirty page copies destination node, thus virtual machine (vm) migration process terminates.
The structural representation of the virtual machine (vm) migration device that Fig. 4 provides for one embodiment of the invention.As shown in Figure 4, this virtual machine (vm) migration device, comprising: determination module 41 and sending module 42, wherein,
Determination module 41, for determining the first address of the first idle node in the first supernode, the first idle node is the node of available free resource in the first supernode, and the first supernode comprises the first Controlling vertex, first node and at least one the first idle node;
Sending module 42, for sending the first address of the first idle node to first node, with make first node by migration data block by the first address transfer to Section Point, migration data block is a part of data preparing to move to from first node Section Point, and Section Point is arranged in the second supernode.
In the present embodiment, achieve and the data preparing in first node to move are divided into multiple migration data block, and by this migration data block by corresponding idle node from the first address transfer of first node to Section Point, reduce the performance of virtual machine (vm) migration to other application be connected in migration network and virtual machine.Further, achieve scheduling on demand, and improve the utilance of the idling-resource in data.
The structural representation of the virtual machine (vm) migration device that Fig. 5 provides for another embodiment of the present invention.As shown in Figure 5, on the basis of above-described embodiment, this virtual machine (vm) migration device, can also comprise: receiver module 43.Concrete, receiver module 43, for receiving the address maps message that the second Controlling vertex sends, to make to determine the mapping relations between the 3rd address of the second idle node and the first address, address maps message comprises the mapping relations between the second address of Section Point and the 3rd address of the second idle node, and the second idle node is the node of resource free time in the second supernode.
On the basis of above-described embodiment, receiver module 43, also for receiving the idle node request that first node sends, idle node request is in order to request dispatching idle node;
Sending module 42, also for according to idle node request, distributes to first node by idle node.
In the present embodiment, can realize distributing according to the demand of first node to idle node.
The structural representation of the virtual machine (vm) migration device that Fig. 6 provides for yet another embodiment of the invention.As shown in Figure 6, this virtual machine (vm) migration device, comprising: sending module 61 and transferring module 62, wherein,
Sending module 61, for receiving the first address of the first idle node that the first Controlling vertex sends, in order to migration data block is passed through the first address transfer to Section Point, migration data block is a part of data preparing to move to from first node Section Point, and Section Point is arranged in the second supernode;
Transferring module 62, for moving to Section Point by the first idle node by migration data block.
In the present embodiment, first node locks to migration data block, to avoid the data in migration data block to be modified, guarantees the correctness of the data in migration data block.
On the basis of above-described embodiment, transferring module 62, also send migration data information for first node to the first idle node, to make the address mapping relation in the first idle node foundation and first node between migration data block, migration data information comprises the size information of migration data block, and the address information of migration data block in first node.
Further, on the basis of above-described embodiment, sending module 61, also for sending idle node request to the first Controlling vertex, idle node request is in order to request dispatching idle node.
In the present embodiment, can realize carrying out request dispatching to the demand of idle node.
The present embodiment provides a kind of virtual machine (vm) migration system, comprising: the arbitrary virtual machine (vm) migration device in the arbitrary virtual machine (vm) migration device as shown in Figure 3 or Figure 4 in embodiment and as shown in Figure 6 embodiment.
The structural representation of the virtual machine (vm) migration device that Fig. 7 provides for one embodiment of the invention.As shown in Figure 7, this virtual machine (vm) migration device, comprising: processor 71 and transmitter 72, wherein,
Processor 71, for determining the first address of the first idle node in the first supernode, the first idle node is the node of available free resource in the first supernode, and the first supernode comprises the first Controlling vertex, first node and at least one the first idle node;
Transmitter 72, for sending the first address of the first idle node to first node, with make first node by migration data block by the first address transfer to Section Point, migration data block is a part of data preparing to move to from first node Section Point, and Section Point is arranged in the second supernode.
In the present embodiment, achieve and the data preparing in first node to move are divided into multiple migration data block, and by this migration data block by corresponding idle node from the first address transfer of first node to Section Point, reduce the performance of virtual machine (vm) migration to other application be connected in migration network and virtual machine.Further, achieve scheduling on demand, and improve the utilance of the idling-resource in data.
Further, on the basis of above-described embodiment, this virtual machine (vm) migration device, can also comprise: receiver 73.Concrete, receiver 73, for receiving the address maps message that the second Controlling vertex sends, to make to determine the mapping relations between the 3rd address of the second idle node and the first address, address maps message comprises the mapping relations between the second address of Section Point and the 3rd address of the second idle node, and the second idle node is the node of resource free time in the second supernode.
On the basis of above-described embodiment, receiver 73, also for receiving the idle node request that first node sends, idle node request is in order to request dispatching idle node;
Sending module 72, also for according to idle node request, distributes to first node by idle node.
In the present embodiment, can realize distributing according to the demand of first node to idle node.
The structural representation of the virtual machine (vm) migration device that Fig. 8 provides for another embodiment of the present invention.As shown in Figure 8, this virtual machine (vm) migration device, comprising: transmitter 81 and processor 82, wherein,
Transmitter 81, for receiving the first address of the first idle node that the first Controlling vertex sends, in order to migration data block is passed through the first address transfer to Section Point, migration data block is a part of data preparing to move to from first node Section Point, and Section Point is arranged in the second supernode;
Processor 82, for moving to Section Point by the first idle node by migration data block.
In the present embodiment, first node locks to migration data block, to avoid the data in migration data block to be modified, guarantees the correctness of the data in migration data block.
On the basis of above-described embodiment, processor 82, also send migration data information for first node to the first idle node, to make the address mapping relation in the first idle node foundation and first node between migration data block, migration data information comprises the size information of migration data block, and the address information of migration data block in first node.
Further, on the basis of above-described embodiment, transmitter 81, also for sending idle node request to the first Controlling vertex, idle node request is in order to request dispatching idle node.
In the present embodiment, can realize carrying out request dispatching to the demand of idle node.
The present embodiment provides a kind of virtual machine (vm) migration system, comprising: the arbitrary virtual machine (vm) migration device in the arbitrary virtual machine (vm) migration device as shown in Figure 7 in embodiment and as shown in Figure 8 embodiment.
One of ordinary skill in the art will appreciate that: all or part of step realizing above-mentioned each embodiment of the method can have been come by the hardware that program command is relevant.Aforesaid program can be stored in a computer read/write memory medium.This program, when performing, performs the step comprising above-mentioned each embodiment of the method; And aforesaid storage medium comprises: ROM, RAM, magnetic disc or CD etc. various can be program code stored medium.
Last it is noted that above each embodiment is only in order to illustrate technical scheme of the present invention, be not intended to limit; Although with reference to foregoing embodiments to invention has been detailed description, those of ordinary skill in the art is to be understood that: it still can be modified to the technical scheme described in foregoing embodiments, or carries out equivalent replacement to wherein some or all of technical characteristic; And these amendments or replacement, do not make the essence of appropriate technical solution depart from the scope of various embodiments of the present invention technical scheme.
Claims (13)
1. a virtual machine migration method, is characterized in that, comprising:
First Controlling vertex determines the first address of the first idle node in the first supernode, described first idle node is the node of available free resource in described first supernode, and described first supernode comprises described first Controlling vertex, first node and the first idle node described at least one;
Described first Controlling vertex sends described first address of described first idle node to described first node, with make described first node by migration data block by described first address transfer to Section Point, described migration data block is a part of data preparing to move to from described first node Section Point, and described Section Point is arranged in the second supernode.
2. method according to claim 1, is characterized in that, described first Controlling vertex, to after described first node sends described first address of described first idle node, also comprises:
Described first Controlling vertex receives the address maps message that described second Controlling vertex sends, to make to determine the mapping relations between the 3rd address of the second idle node and described first address, described address maps message comprises the mapping relations between the second address of described Section Point and the 3rd address of described second idle node, and described second idle node is the node of resource free time in described second supernode.
3. method according to claim 1 and 2, is characterized in that, described first Controlling vertex also comprises before sending the first address of described idle node to described first node:
Described first Controlling vertex receives the idle node request that described first node sends, and described idle node request is in order to idle node described in request dispatching;
Described first Controlling vertex sends described first address of described idle child node to described first node, comprising:
Described idle node, according to described idle node request, is distributed to described first node by described first Controlling vertex.
4. a virtual machine migration method, is characterized in that, comprising:
First node receives the first address of the first idle node that the first Controlling vertex sends, in order to migration data block is passed through described first address transfer to Section Point, described migration data block is a part of data preparing to move to from described first node Section Point, and described Section Point is arranged in the second supernode;
Described migration data block is moved to described Section Point by described first idle node by described first node.
5. method according to claim 4, is characterized in that, described first node also comprises before by described first idle node described migration data block being moved to described Section Point:
Described first node sends migration data information to described first idle node, to make the address mapping relation described in described first idle node foundation and described first node between migration data block, described migration data information comprises the size information of described migration data block, and the address information of described migration data block in described first node.
6. the method according to claim 4 or 5, is characterized in that, described first node also comprises before receiving the first address of the first idle child node that described first Controlling vertex sends:
Described first node sends idle node request to described first Controlling vertex, and described idle node request is in order to idle node described in request dispatching.
7. a virtual machine (vm) migration device, is characterized in that, comprising:
Determination module, for determining the first address of the first idle node in the first supernode, described first idle node is the node of available free resource in described first supernode, and described first supernode comprises described first Controlling vertex, first node and the first idle node described at least one;
Sending module, for sending described first address of described first idle node to described first node, with make described first node by migration data block by described first address transfer to Section Point, described migration data block is a part of data preparing to move to from described first node Section Point, and described Section Point is arranged in the second supernode.
8. device according to claim 7, is characterized in that, also comprises: receiver module;
Described receiver module, for receiving the address maps message that described second Controlling vertex sends, to make to determine the mapping relations between the 3rd address of the second idle node and described first address, described address maps message comprises the mapping relations between the second address of described Section Point and the 3rd address of described second idle node, and described second idle node is the node of resource free time in described second supernode.
9. the device according to claim 7 or 8, is characterized in that, described receiver module, and also for receiving the idle node request that described first node sends, described idle node request is in order to idle node described in request dispatching;
Described sending module, also for according to described idle node request, distributes to described first node by described idle node.
10. a virtual machine (vm) migration device, is characterized in that, comprising:
Sending module, for receiving the first address of the first idle node that the first Controlling vertex sends, in order to migration data block is passed through described first address transfer to Section Point, described migration data block is a part of data preparing to move to from described first node Section Point, and described Section Point is arranged in the second supernode;
Transferring module, for moving to described Section Point by described first idle node by described migration data block.
11. devices according to claim 10, it is characterized in that, described transferring module, also send migration data information for described first node to described first idle node, to make the address mapping relation described in described first idle node foundation and described first node between migration data block, described migration data information comprises the size information of described migration data block, and the address information of described migration data block in described first node.
12. devices according to claim 10 or 11, is characterized in that, described sending module, and also for sending idle node request to described first Controlling vertex, described idle node request is in order to idle node described in request dispatching.
13. 1 kinds of virtual machine (vm) migration systems, is characterized in that, comprising: the virtual machine (vm) migration device as described in as arbitrary in claim 7-9 and the virtual machine (vm) migration device as described in claim 10-12.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310518434.6A CN104580328A (en) | 2013-10-28 | 2013-10-28 | Virtual machine migration method, device and system |
| PCT/CN2014/087734 WO2015062390A1 (en) | 2013-10-28 | 2014-09-29 | Virtual machine migration method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310518434.6A CN104580328A (en) | 2013-10-28 | 2013-10-28 | Virtual machine migration method, device and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104580328A true CN104580328A (en) | 2015-04-29 |
Family
ID=53003301
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310518434.6A Pending CN104580328A (en) | 2013-10-28 | 2013-10-28 | Virtual machine migration method, device and system |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN104580328A (en) |
| WO (1) | WO2015062390A1 (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108351802A (en) * | 2015-11-13 | 2018-07-31 | 华为技术有限公司 | The method of computer data processing system and the optimization based on communication flows communicated for virtual machine |
| CN110971647A (en) * | 2018-09-30 | 2020-04-07 | 南京工程学院 | Node migration method of big data system |
| CN114048041A (en) * | 2022-01-14 | 2022-02-15 | 湖南大学 | Safe memory sharing method based on idle node initiative |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101924693A (en) * | 2009-04-01 | 2010-12-22 | 威睿公司 | Be used for method and system in migrating processes between virtual machines |
| CN102479099A (en) * | 2010-11-22 | 2012-05-30 | 中兴通讯股份有限公司 | Virtual machine management system and use method thereof |
| US20120221744A1 (en) * | 2011-02-25 | 2012-08-30 | International Business Machines Corporation | Migrating Virtual Machines with Adaptive Compression |
| CN103250139A (en) * | 2012-11-07 | 2013-08-14 | 华为技术有限公司 | A method and an apparatus for migrating computing nodes ` |
-
2013
- 2013-10-28 CN CN201310518434.6A patent/CN104580328A/en active Pending
-
2014
- 2014-09-29 WO PCT/CN2014/087734 patent/WO2015062390A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101924693A (en) * | 2009-04-01 | 2010-12-22 | 威睿公司 | Be used for method and system in migrating processes between virtual machines |
| CN102479099A (en) * | 2010-11-22 | 2012-05-30 | 中兴通讯股份有限公司 | Virtual machine management system and use method thereof |
| US20120221744A1 (en) * | 2011-02-25 | 2012-08-30 | International Business Machines Corporation | Migrating Virtual Machines with Adaptive Compression |
| CN103250139A (en) * | 2012-11-07 | 2013-08-14 | 华为技术有限公司 | A method and an apparatus for migrating computing nodes ` |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108351802A (en) * | 2015-11-13 | 2018-07-31 | 华为技术有限公司 | The method of computer data processing system and the optimization based on communication flows communicated for virtual machine |
| CN110971647A (en) * | 2018-09-30 | 2020-04-07 | 南京工程学院 | Node migration method of big data system |
| CN110971647B (en) * | 2018-09-30 | 2023-12-05 | 南京工程学院 | Node migration method of big data system |
| CN114048041A (en) * | 2022-01-14 | 2022-02-15 | 湖南大学 | Safe memory sharing method based on idle node initiative |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2015062390A1 (en) | 2015-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10083053B2 (en) | System and method for virtual machine live migration | |
| CN102316043B (en) | Port virtualization method, switch and communication system | |
| US20180210752A1 (en) | Accelerator virtualization method and apparatus, and centralized resource manager | |
| CN108028833A (en) | A kind of method, system and the relevant device of NAS data accesses | |
| KR101480867B1 (en) | System and method for accelerating mapreduce operation | |
| US10331470B2 (en) | Virtual machine creation according to a redundancy policy | |
| EP2667296A1 (en) | Method and apparatus of data processing | |
| EP3993346A1 (en) | Method and device for distributed data storage | |
| US8849905B2 (en) | Centralized computing | |
| CN110830574B (en) | Method for realizing intranet load balance based on docker container | |
| CN109426566B (en) | Connecting accelerator resources using a switch | |
| CN104461716A (en) | Access method of multi-nucleus heterogeneous system and multi-nucleus heterogeneous system | |
| CN104536702A (en) | Storage array system and data writing request processing method | |
| CN102870374B (en) | Load-sharing method and apparatus, and veneer, | |
| CN105808374A (en) | Snapshot processing method and associated equipment | |
| CN103617024B (en) | A kind of concurrent data disposal route, device and system | |
| CN115686875A (en) | Method, apparatus and program product for transferring data between multiple processes | |
| CN104580328A (en) | Virtual machine migration method, device and system | |
| CN105700823A (en) | Method and apparatus for transmitting data between IP hard disks | |
| CN104125292A (en) | Data processing device, cloud server and use method thereof | |
| TWI571077B (en) | Integration network device and service integration method thereof | |
| CN113254160B (en) | IO resource request method and device | |
| CN110661869B (en) | Node online method, system, device, equipment and computer storage medium | |
| US11172021B2 (en) | File objects download and file objects data exchange | |
| CN101441661A (en) | System and method for sharing file resource between multiple embedded systems |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150429 |