CN102103524A - Memory redundancy oriented virtual machine migration device and method - Google Patents
Memory redundancy oriented virtual machine migration device and method Download PDFInfo
- Publication number
- CN102103524A CN102103524A CN2010106031683A CN201010603168A CN102103524A CN 102103524 A CN102103524 A CN 102103524A CN 2010106031683 A CN2010106031683 A CN 2010106031683A CN 201010603168 A CN201010603168 A CN 201010603168A CN 102103524 A CN102103524 A CN 102103524A
- Authority
- CN
- China
- Prior art keywords
- virtual machine
- memory
- principal computer
- migration
- machine
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Abstract
The invention discloses a memory redundancy oriented virtual machine migration device and method, wherein the method comprises the following steps: integrating the characteristics of a virtual machine with memory data redundancy by using a data center, and before the virtual machine is subjected to formal migration, scanning a memory page of the virtual machine so as to obtain a memory descriptor of the virtual machine which is required to be migrated; comparing the obtained memory descriptor with a targeted-node memory page so as to obtain part of memory page list of the virtual machine which is required to be migrated; and according to the obtained memory page list, canceling the transmission of redundant memories, and reducing the transmission quantity of data for migration by using a data compression technology. Therefore, by using the device and method disclosed by the invention, in the process of virtual machine migration with the purpose of saving the memory resources of the data center, the network load can be reduced as far as possible, and the overall resource utilization ratio of the data center can be improved.
Description
(1) technical field
The present invention relates to a kind of virtual machine (vm) migration devices and methods therefor towards the internal memory redundancy, be the internal memory redundant information of utilizing on sourcesink main frame and the target host, reduce the memory copying in the virtual machine (vm) migration process, thereby improve migration velocity, reduce network traffics, belong to field of computer technology.
(2) background technology
Have thousands of server in the present data center, the single program of only moving certain company that these data centers have, some data center hires out the use to the client with huge computational resource and storage resources, and this mode is known as cloud computing.Popular along with cloud computing, increasing Web service and commercial the application are deployed in the cloud computing, and the data center of carrying cloud computing simultaneously is also more and more huger.For the server of magnanimity in the data center, how to improve the utilization factor of resource, reduce handling cost, become the focus of people's research.
The appearance of Intel Virtualization Technology makes and can move a plurality of virtual machines simultaneously on same physical machine, and these virtual machines have good isolation.This mode with a plurality of Server Consolidations to a physical node has greatly improved the utilization factor of resource, the therefore virtual core technology that becomes data center's raising resource utilization gradually.
Intel Virtualization Technology is meant the method for passing through software or hardware on hardware platform, makes up a virtual platform between computer hardware and operating system, for upper strata operating system fictionalizes a plurality of independently virtual hardware running environment, and shared hardware resource.Wherein, the virtual machine that comes out is virtual machine (VM), and the software that runs between hardware and the operating system is known as monitor of virtual machine (VMM), manages and distribute the operation of hardware resource and scheduling virtual machine by it.
Memory source is one of valuable source of system.Compare to the secondary mapping of physical page with virtual page number in the traditional operating system, Intel Virtualization Technology adopts virtual page number, physical page, and three grades of mappings of the machine page are to reach the purpose of internal memory virtualization.Because a plurality of virtual machines of the general operation of same physical machine may have a large amount of same physical pages between these virtual machines, the redundancy of these memory pages has caused the waste of resource.Therefore, up-to-date virtual memory management technology adopts the same physical page-map with a plurality of virtual machines to arrive the same machine page, to reduce the internal memory redundancy, improves the utilization factor of memory source.
The resource that provides in the data center comprises computational resource (CPU), memory source and Internet resources (bandwidth) etc.For memory source, because the existence of a large amount of virtual machines of data center, these virtual machines are because the identical redundancy that more or less has internal memory of the application of operating system and encapsulation.What of virutal machine memory redundancy to come the migration of virtual machine and placement in the heart in the guide data with as index, the redundant more virtual machine of internal memory is adjusted to same physical machine, and utilizing the shared mechanism of the machine page between the virtual machine, the memory source that can save data center's integral body effectively uses.
Yet, adjust the placement of virtual machine and generally adopt the virtual machine (vm) migration technology, present virtual machine (vm) migration technology adopts the virtual disk with virtual machine to be mapped to shared storage device (as SAN), transition process is mainly finished the copy of virutal machine memory data from the source node to the destination node, set up new virtual disk mapping then, restart virtual machine.Virtual machine (vm) migration need copy the virutal machine memory on the source VMM (monitor of virtual machine) to target VMM and continue the operation of virtual machine, this process need consume network bandwidth, for the environment of data center's magnanimity machine, a large amount of virtual machine (vm) migrations will cause big pressure to the network bandwidth.Therefore, the load that how reduces data center network in improving memory source in the utilization factor is to need the problem that solves.
Three) summary of the invention
The purpose of this invention is to provide a kind of virtual machine (vm) migration devices and methods therefor, the network bandwidth that is consumed in the virtual machine (vm) migration process can be reduced as far as possible, reach and reduce network resource consumption when improving the memory source utilization factor towards the internal memory redundancy.
For achieving the above object, the invention provides a kind of virtual machine (vm) migration device, comprising towards the internal memory redundancy:
1. first principal computer and second computing machine (any in the heart two computing machines in the representative data);
2. storage system;
3. communication network;
Described first principal computer and second principal computer comprise processor, input equipment, first host bus adaptor, second host bus adaptor, communication interface and computer-readable storage medium.
Described processor is responsible for controlling first principal computer and second principal computer, and is connected with computer-readable storage medium with described input equipment, first host bus adaptor, second host bus adaptor, communication interface; Application program in the described computer-readable storage medium and data can be read and be carried out by described processor, and can be transferred to any external unit by described first host bus adaptor, second host bus adaptor and described communication interface.
Described input equipment is used for the input of data and instruction;
Described first host bus adaptor is used to be connected disk array with second host bus adaptor;
Described communication interface is used to connect external network communication equipment;
Described computer-readable storage medium comprises the first migration control system, the second migration control system, first monitor of virtual machine, second monitor of virtual machine, virtual machine and application program;
Described computer-readable storage medium is used for stored program instructions and data, comprises random access memory (RAM) and nonvolatile memory (for example, ROM, flash memory, disk, CD etc.); And by described processor execution realization virtual machine (vm) migration process.
Three virtual machines on described first principal computer are by the first virtual machine monitoring management, and each virtual machine has one or more virtual drives associated therewith, and first host bus adaptor of each virtual drive by first principal computer is mapped on the disk logical block of the disk array that the second communication network connects.The virtual disc accesses of virtual machine is mapped as by the visit of second communication network to file on the disk array.The first migration control system is the accessory part of first monitor of virtual machine, the whole process of control virtual machine (vm) migration, the first migration control system utilizes first network adapter mutual by the second migration control system on first communication network and second principal computer, and then realizes the transmission of virutal machine memory data and status information.The function of the virtual machine in second principal computer, virtual drive, second host bus adaptor and the second migration control system, second monitor of virtual machine, second network adapter is identical with first principal computer with annexation.
Described first monitor of virtual machine and second monitor of virtual machine run directly on the hardware, for virtual machine provides virtual hardware execution environment; Described virtual machine provides virtual operating system execution environment for described application program; Described application program is identical with the true operation system environments at described virtual machine implementation effect; The described first migration control system and the second migration control system are responsible for controlling the transition process of virtual machine.
The described first migration control system and second is moved control system by interactive module, scan module, and comparison module, compression module is formed;
Interactive module is used for carrying out the reciprocal process of virtual machine (vm) migration process, comprises the initiation and the acceptance of migration request, the transmission of descriptor memory symbol and internal storage data;
Scan module is used to scan the pairing machine memory pages of each virtual memory page of virtual machine, utilizes hash algorithm to calculate the cryptographic hash of each machine memory pages data, and the descriptor memory of finally constructing a virtual machine accords with;
Comparison module, whether the virtual machine that is used for relatively need moving exists the consistent memory pages of content with target machine, by the scanning destination node, each machine page generates corresponding cryptographic hash, and in the virutal machine memory descriptor that source node transmits, search the project whether coupling is arranged, if there is the project of coupling then to need the further checking of process sampled data, judge not to be same page the memory pages tabulation that final generation migration virtual machine need transmit;
Compression module, the compression and the decompression that are used for needing to transmit data to reduce transmitted data amount, improve transmission speed.
Described storage system comprises disk array, memory interface, one or more phisical drive and storage medium; Described storage system can be embodied as storage area network (SAN).
Described disk array comprises a plurality of disk logical blocks (being lun151-155 in this example), and its each free disk array externally presents.A disk logical block can be mapped to the one or more phisical drives or the storage medium of disk array.Virtual machine can be the virtual disk of virtual machine with the disk logical unit mappings of disk array.
Described memory interface provides access interface for disk array.Can be implemented as provides the communicate by letter SAN switch supported to described disk array and described second communication network.One or more virtual drives of described virtual machine can pass through the connection between first host bus adaptor, first communication network and second communication network and the memory interface, be mapped on one or more lun of disk array the data of each lun storage respective virtual machine.
Described first communication network and second communication network are for providing communication support between first principal computer and second principal computer and the storage system.First communication network and second communication network are used between first principal computer and second principal computer and the data communication between first principal computer and second principal computer and the storage system, can be implemented as the data communication network of any kind and agreement.For example, in this example, first communication network can be implemented as the gigabit Ethernet network, and the second communication network can be implemented as optical-fibre channel or the iSCSI network that is connected to first principal computer and second principal computer by memory interface.
For achieving the above object, the invention provides a kind of virtual machine migration method, comprise five steps towards the internal memory redundancy, specific as follows:
Step 1: suspend the operation that needs the migration virtual machine on the source node, the scanning virutal machine memory page also generates the descriptor memory symbol, then the descriptor memory symbol is sent to destination node;
The interactive module of the first migration control system of first principal computer (source node) is initiated virtual machine (vm) migration request via first communication network to the second migration control system of second principal computer (destination node) by first network adapter, after obtaining responding, the first migration control system is suspended the operation of first virtual machine, and utilize scan module to scan the internal storage data of first virtual machine, generate the descriptor memory symbol of first virtual machine and it is sent to second principal computer by first network adapter via first communication network; The descriptor memory symbol of this first virtual machine mainly comprises the physical page sequence number of virutal machine memory, machine page sequence number, and by the cryptographic hash of memory pages content generation, and the data sampling of the memory pages content of 32 bytes;
The process of descriptor memory symbol that specifically scans and generate first virtual machine is as follows:
Step 101: the internal memory scan module at first finds the internal memory page table of first virtual machine, the descriptor memory symbol of initialization first virtual machine;
Step 102: according to the first virutal machine memory page table, utilize the SuperFastHash hash algorithm to calculate the content Hash value of the pairing machine memory pages of each virtual memory page, authorization information with 32 bytes in cryptographic hash and its corresponding physical page sequence number, machine page sequence number and the memory pages together is saved in the descriptor memory symbol of first virtual machine then, and the realization of SuperFastHash algorithm as follows;
Step 103: the descriptor memory symbol of first virtual machine that will generate sends to the second migration control system of second principal computer via first communication network by first network adapter;
Step 2: destination node scan this machine memory pages and with the descriptor memory symbol of need migrations virtual machine relatively, generate the memory pages tabulation that needs transmission and also return to source node;
After second principal computer obtains the descriptor memory symbol of first virtual machine, comparison module by the second migration control system, scan this node machine memory pages and compare with the descriptor memory of first virtual machine symbol, and then generate the page listings of first virutal machine memory that needs migration and send to first principal computer by second network adapter via first communication network, specifically relatively flow process is as follows:
Step 201: obtain the machine page listings of second principal computer, the page listings 622 that initialization need be moved;
Step 202: watch the end that whether arrives the second principal computer machine page listings, not, then jump to step 203; Be then to jump to step 208;
Step 203: the internal memory machine page that obtains next second principal computer that will compare;
Step 204: utilize the SuperFastHash hash algorithm to calculate the cryptographic hash of content of pages;
Step 205: in the descriptor memory symbol of first virtual machine, search whether to have and calculate the project that the gained cryptographic hash is complementary, be, then jump to step 206, not, then jump to step 207 with step 204;
Whether step 206: it is consistent further to utilize the memory pages verification msg to detect content of pages; Be then to jump to step 202; , then do not jump to step 207;
Step 207: the current physical page sequence number that will obtain from the descriptor memory symbol adds in the page listings that needs migration, jumps to step 202;
Step 208: finish comparison procedure;
Step 3: source node extracts the page in the internal memory tabulation and compresses the back and together sends destination node to virtual machine state information;
After first principal computer obtains needing the first virtual machine page listings of migration, the first migration control system is extracted the memory pages that needs migration and is utilized compression module that internal storage data is compressed from the internal memory of first principal computer, will send second principal computer by first network adapter to via first communication network through the data of overcompression then;
Concrete steps are as follows:
Step 301: the page listings that need to obtain transmission;
Step 302: extract the content of the first virtual machine page internal memory successively according to physical page numeric order in the page listings, form consecutive data block;
Step 303: utilize compression module to carry out the compression of internal storage data piece;
Step 304: the data after will compressing and the status information of virtual machine are transferred to the second migration control system of second principal computer via first communication network by first network adapter.
Step 4: the destination node decompressed data, create new memory pages according to memory content, and rebulid page-map according to migration virutal machine memory descriptor;
After second principal computer obtains the internal storage data of first virtual machine, utilize the compression module of the second migration control system to carry out data decompression, and on second principal computer, create new machine memory pages according to the descriptor memory of first virtual machine symbol and internal storage data, and set up the mapping relations of the new virtual machine physical page of first virtual machine to the machine page, concrete steps are as follows:
Step 401: the second migration control system of second principal computer connects the first virutal machine memory data and the virtual machine state information through overcompression that second principal computer transmits by second network adapter;
Step 402: the compression module of the second migration control system of second principal computer decompresses to internal storage data;
Step 403: the second migration control system of second principal computer is that first virtual machine distributes the new machine page, and creates new machine memory pages according to the internal storage data and the page listings of first virtual machine;
Step 404: the second migration control system is that the physical page of first virtual machine and the machine page of second principal computer are set up new page-map relation according to the descriptor memory symbol of first virtual machine;
Step 405: be written into the status information of first virtual machine at last, wait for operation.Step 5: the virtual drive of change migration virtual machine starts the virtual machine operation to the mapping relations of disk array.
First virtual drive of cancelling first virtual machine on first principal computer is via the mapping relations of second communication network to the lun152 of disk array, simultaneously on second principal computer, set up first virtual drive of the first new virtual machine via the mapping relations of second communication network to the lun152 of disk array, destroy first virtual machine on former first principal computer at last to reclaim resource, and starting the operation of first virtual machine on second principal computer, transition process finishes.
Advantage of the present invention and effect are: by the similarity degree of existing memory pages on the virutal machine memory page that need to move on scanning and the reference source physical node and the destination node, the memory pages collection that final decision need be moved, and be transferred to destination node after internal storage data compressed.To reduce the shared network bandwidth of virtual machine (vm) migration and to improve migration velocity.
(4) description of drawings
Fig. 1 is data center's virtualization system synoptic diagram
Fig. 2 is the computer equipment figure of virtual support machine migration
Fig. 3 is a virtual machine (vm) migration reciprocal process synoptic diagram
Fig. 4 is the process flow diagram of virtual machine (vm) migration implementation process
Fig. 5 generates descriptor memory symbol synoptic diagram for virutal machine memory scanning
Fig. 6 relatively generates synoptic diagram with the migration page listings for memory pages
Fig. 7 compares and migration page listings product process figure for memory pages
Fig. 8 is internal memory compression and transmission course synoptic diagram
Fig. 9 remaps synoptic diagram for migration back virutal machine memory
(5) embodiment
Below by drawings and Examples, technical scheme of the present invention is described in further detail:
The invention provides a kind of virtual machine (vm) migration device, comprising towards the internal memory redundancy:
1. principal computer 101,102 (any in the heart two computing machines in the representative data);
2. storage system 105;
3. communication network 106 and 107;
Described principal computer 101,102 comprises processor 201, input equipment 202, host bus adaptor 111,112, communication interface 204 and computer-readable storage medium 205.
Described processor 201 is responsible for control principal computer 101,102, and is connected with described input equipment 202, host bus adaptor 111,112, communication interface 204 and computer-readable storage medium 205; Application program 213 in the described computer-readable storage medium 205 and data can be read and be carried out by described processor 201, and can be transferred to any external unit by described host bus adaptor 111,112 and described communication interface 204.
Described input equipment 202 is used for the input of data and instruction;
Described host bus adaptor 111,112 is used to connect redundant array of inexpensive disks 1 04;
Described communication interface 204 is used to connect external network communication equipment;
Described computer-readable storage medium 205 comprises migration control system 121,122, monitor of virtual machine 123,124, virtual machine 131,132,133 and application program 213;
Described computer-readable storage medium 205 is used for stored program instructions and data, comprises random access memory (RAM) and nonvolatile memory (for example, ROM, flash memory, disk, CD etc.); And by described processor 201 execution realization virtual machine (vm) migration processes.
Three virtual machines 131,132,133 on the described principal computer 101 are by monitor of virtual machine 123 management, and each virtual machine has one or more virtual drives associated therewith 141,142,143, each virtual drive is mapped to the disk logical block (lun) 152 of the redundant array of inexpensive disks 1 04 of communication network 107 connections by the host bus adaptor 111 of principal computer 101,153, on 153,154.Virtual machine 131,132,133 virtual disc accesses are mapped as the visit by file on 107 pairs of redundant array of inexpensive disks 1 04 of communication network.Migration control system 121 is the accessory part of monitor of virtual machine 123, the whole process of control virtual machine (vm) migration, migration control system 121 utilizes network adapter 113 mutual with the migration control system 122 on the principal computer 102 by communication network 106, and then realizes the transmission of virutal machine memory data and status information.Virtual machine 134 in the principal computer 102, virtual drive 144, and host bus adaptor 112 and migration control system 122, monitor of virtual machine 124, the function of network adapter 114 is identical with principal computer 101 with annexation.
Described monitor of virtual machine 123,124 runs directly on the hardware, is virtual machine 131,132, and 133,134 provide virtual hardware execution environment; Described virtual machine 131,132,133,134 provides virtual operating system execution environment for described application program 213; Described application program 213 is identical with the true operation system environments at described virtual machine 131,132,133,134 implementation effects; Described migration control system 121,122 is responsible for the transition process of control virtual machine 131,132,133,134.
Described migration control system 121,122 is by interactive module 221, scan module 222, and comparison module 223, compression module 224 is formed;
Described storage system 105 comprises redundant array of inexpensive disks 1 04, memory interface 103, one or more phisical drive and storage medium; Described storage system 105 can be embodied as storage area network (SAN).
Described redundant array of inexpensive disks 1 04 comprises a plurality of disk logical blocks (being lun151-155 in this example), and its each free redundant array of inexpensive disks 1 04 externally presents.A disk logical block can be mapped to the one or more phisical drives or the storage medium of redundant array of inexpensive disks 1 04.Virtual machine can be the virtual disk of virtual machine with the disk logical unit mappings of disk array.
Described memory interface 103 provides access interface for redundant array of inexpensive disks 1 04.Can be implemented as provides the communicate by letter SAN switch supported to described redundant array of inexpensive disks 1 04 and described communication network 107.One or more virtual drives of described virtual machine can pass through host bus adaptor 111, communication network 106,107, and the connection between the memory interface 103 is mapped on one or more lun of disk array, the data of each lun storage respective virtual machine.
Described communication network 106,107 is that communication support is provided between principal computer 101,102 and the storage system 105.Communication network 106 and 107 be used between the principal computer 101,102 and principal computer 101,102 and storage system 105 between data communication, can be implemented as the data communication network of any kind and agreement.For example, in this example, communication network 106 can be implemented as the gigabit Ethernet network, and communication network 107 can be implemented as optical-fibre channel or the iSCSI network that is connected to principal computer 101,102 by memory interface 103.
For achieving the above object, the invention provides a kind of virtual machine migration method, comprise five steps towards the internal memory redundancy, specific as follows:
Step 1: suspend the operation that needs the migration virtual machine on the source node, the scanning virutal machine memory page also generates the descriptor memory symbol, then the descriptor memory symbol is sent to destination node;
The interactive module 221 of the first migration control system 121 of first principal computer 101 (source node) is initiated virtual machine (vm) migration request via first communication network 106 to the second migration control system 122 of second principal computer 102 (destination node) by first network adapter 113, after obtaining responding, the first migration control system 121 is suspended the operation of first virtual machine 131, and utilize scan module 222 to scan the internal storage data of first virtual machine 131, generate the descriptor memory symbol 521 of first virtual machine 131 and it is sent to second principal computer 102 by first network adapter 113 via first communication network 106; The descriptor memory symbol 521 of this first virtual machine 131 mainly comprises the physical page sequence number of virutal machine memory, machine page sequence number, and by the cryptographic hash of memory pages content generation, and the data sampling of the memory pages content of 32 bytes;
The process of descriptor memory symbol 521 that specifically scans and generate first virtual machine 131 is as follows:
Step 101: internal memory scan module 222 at first finds the internal memory page table of first virtual machine 131, the descriptor memory symbol 521 of initialization first virtual machine 131;
Step 102: according to first virtual machine, 131 internal memory page tables, utilize the SuperFastHash hash algorithm to calculate the content Hash value of the pairing machine memory pages of each virtual memory page, authorization information with 32 bytes in cryptographic hash and its corresponding physical page sequence number, machine page sequence number and the memory pages together is saved in the descriptor memory symbol 521 of first virtual machine 131 then, and the realization of SuperFastHash algorithm as follows; Step 103: the descriptor memory symbol 521 of first virtual machine 131 that will generate sends to the second migration control system 122 of second principal computer 102 via first communication network 106 by first network adapter 113;
Step 2: destination node scan this machine memory pages and with the descriptor memory symbol of need migrations virtual machine relatively, generate the memory pages tabulation that needs transmission and also return to source node;
After second principal computer 102 obtains the descriptor memory symbol 521 of first virtual machine 131, comparison module 223 by the second migration control system 122, scan this node machine memory pages and compare with the descriptor memory of first virtual machine 131 symbol 521, and then generate the page listings 622 of first virtual machine, 131 internal memories that need migration and send to first principal computer 101 by second network adapter 114 via first communication network 106, specifically relatively flow process is as follows:
Step 201: obtain the machine page listings of second principal computer 102, the page listings 622 that initialization need be moved;
Step 202: watch the end that whether arrives second principal computer, 102 machine page listings, not, then jump to step 203; Be then to jump to step 208;
Step 203: the internal memory machine page that obtains next second principal computer 102 that will compare;
Step 204: utilize the SuperFastHash hash algorithm to calculate the cryptographic hash of content of pages;
Step 205: in the descriptor memory symbol 521 of first virtual machine 131, search whether to have and calculate the project that the gained cryptographic hash is complementary, be, then jump to step 206, not, then jump to step 207 with step 204;
Whether step 206: it is consistent further to utilize the memory pages verification msg to detect content of pages; Be then to jump to step 202; , then do not jump to step 207;
Step 207: will accord with the current physical page sequence number that obtains 521 from descriptor memory and add in the page listings 622 that needs migration, and jump to step 202;
Step 208: finish comparison procedure;
Step 3: source node extracts the page in the internal memory tabulation and compresses the back and together sends destination node to virtual machine state information;
After first principal computer 101 obtains needing first virtual machine, 131 page listings 622 of migration, the first migration control system 121 is extracted the memory pages that needs migration and is utilized 224 pairs of internal storage datas of compression module to compress from the internal memory of first principal computer 101, will send second principal computer 102 by first network adapter 113 to via first communication network 106 through the data of overcompression then;
Concrete steps are as follows:
Step 301: the page listings 622 that need to obtain transmission;
Step 302: extract the content of first virtual machine, 131 page internal memories successively according to physical page numeric order in the page listings 622, form consecutive data block;
Step 303: utilize compression module 224 to carry out the compression of internal storage data piece;
Step 304: the status information of data after will compressing and virtual machine 131 is transferred to the second migration control system 122 of second principal computer 102 via first communication network 106 by first network adapter 113.Step 4: the destination node decompressed data, create new memory pages according to memory content, and rebulid page-map according to migration virutal machine memory descriptor;
After second principal computer 102 obtains the internal storage data of first virtual machine 131, utilize the compression module 224 of the second migration control system 122 to carry out data decompression, and on second principal computer 102, create new machine memory pages according to the descriptor memory of first virtual machine 131 symbol 521 and internal storage data, and set up the mapping relations of the new virtual machine physical page of first virtual machine 131 to the machine page, concrete steps are as follows:
Step 401: the second migration control system 122 of second principal computer 102 connects first virtual machine, 131 internal storage datas and the virtual machine state information through overcompression that second principal computer 102 transmits by second network adapter 114;
Step 402: 224 pairs of internal storage datas of compression module of the second migration control system 122 of second principal computer 102 decompress;
Step 403: the second migration control system 122 of second principal computer 102 is that first virtual machine 131 distributes the new machine page, and creates new machine memory pages according to the internal storage data and the page listings 622 of first virtual machine 131;
Step 404: the second migration control system 122 is that the physical page of first virtual machine 131 and the machine page of second principal computer 102 are set up new page-map relation according to the descriptor memory symbol 521 of first virtual machine 131;
Step 405: be written into the status information of first virtual machine 131 at last, wait for operation.Step 5: the virtual drive of change migration virtual machine starts the virtual machine operation to the mapping relations of disk array.
First virtual drive 141 of cancelling first virtual machine 131 on first principal computer 101 is via the mapping relations of second communication network 107 to the lun152 of redundant array of inexpensive disks 1 04, first virtual drive 141 of setting up simultaneously the first new virtual machine 131 on second principal computer 102 is via the mapping relations of second communication network 107 to the lun152 of redundant array of inexpensive disks 1 04, destroy first virtual machine 131 on former first principal computer 101 at last to reclaim resource, and starting the operation of first virtual machine 131 on second principal computer 102, transition process finishes.
It should be noted that at last: above embodiment only is used to illustrate technical scheme of the present invention but not limits it.The modification of carrying out for the embodiment of the invention and be equal to replacement and can not make amended technology put the protection domain that case breaks away from technical solution of the present invention.
Claims (2)
1. virtual machine (vm) migration device towards the internal memory redundancy is characterized in that: comprising:
First principal computer and second computing machine, storage system and communication network;
Described first principal computer and second principal computer comprise processor, input equipment, first host bus adaptor, second host bus adaptor, communication interface and computer-readable storage medium;
Described processor is responsible for controlling first principal computer and second principal computer, and is connected with computer-readable storage medium with described input equipment, first host bus adaptor, second host bus adaptor, communication interface; Application program in the described computer-readable storage medium and data are read and are carried out by described processor, and are transferred to any external unit by described first host bus adaptor, second host bus adaptor and described communication interface;
Described input equipment is used for the input of data and instruction;
Described first host bus adaptor is used to be connected disk array with second host bus adaptor;
Described communication interface is used to connect external network communication equipment;
Described computer-readable storage medium comprises the first migration control system, the second migration control system, first monitor of virtual machine, second monitor of virtual machine, virtual machine and application program;
Described computer-readable storage medium is used for stored program instructions and data, comprises random access memory and nonvolatile memory; And by described processor execution realization virtual machine (vm) migration process;
Three virtual machines on described first principal computer are by the first virtual machine monitoring management, and each virtual machine has one or more virtual drives associated therewith, and first host bus adaptor of each virtual drive by first principal computer is mapped on the disk logical block of the disk array that the second communication network connects; The virtual disc accesses of virtual machine is mapped as by the visit of second communication network to file on the disk array; The first migration control system is the accessory part of first monitor of virtual machine, the whole process of control virtual machine (vm) migration, the first migration control system utilizes first network adapter mutual by the second migration control system on first communication network and second principal computer, and then realizes the transmission of virutal machine memory data and status information;
Described first monitor of virtual machine and second monitor of virtual machine run directly on the hardware, for virtual machine provides virtual hardware execution environment; Described virtual machine provides virtual operating system execution environment for described application program; Described application program is identical with the true operation system environments at described virtual machine implementation effect; The described first migration control system and the second migration control system are responsible for controlling the transition process of virtual machine;
The described first migration control system and second is moved control system by interactive module, scan module, and comparison module, compression module is formed;
Interactive module is used for carrying out the reciprocal process of virtual machine (vm) migration process, comprises the initiation and the acceptance of migration request, the transmission of descriptor memory symbol and internal storage data;
Scan module is used to scan the pairing machine memory pages of each virtual memory page of virtual machine, utilizes hash algorithm to calculate the cryptographic hash of each machine memory pages data, and the descriptor memory of finally constructing a virtual machine accords with;
Comparison module, whether the virtual machine that is used for relatively need moving exists the consistent memory pages of content with target machine, by the scanning destination node, each machine page generates corresponding cryptographic hash, and in the virutal machine memory descriptor that source node transmits, search the project whether coupling is arranged, if there is the project of coupling then to need the further checking of process sampled data, judge not to be same page the memory pages tabulation that final generation migration virtual machine need transmit;
Compression module, the compression and the decompression that are used for needing to transmit data to reduce transmitted data amount, improve transmission speed;
Described storage system comprises disk array, memory interface, one or more phisical drive and storage medium; Described storage system is embodied as storage area network;
Described disk array comprises a plurality of disk logical blocks, and its each free disk array externally presents; A disk logical block is mapped to the one or more phisical drives or the storage medium of disk array; Virtual machine is the virtual disk of virtual machine with the disk logical unit mappings of disk array;
Described memory interface provides access interface for disk array; Being implemented as provides the communicate by letter SAN switch supported to described disk array and described second communication network; One or more virtual drives of described virtual machine are by the connection between first host bus adaptor, first communication network and second communication network and the memory interface, be mapped on one or more lun of disk array the data of each lun storage respective virtual machine;
Described first communication network and second communication network are for providing communication support between first principal computer and second principal computer and the storage system; First communication network and second communication network are used between first principal computer and second principal computer and the data communication between first principal computer and second principal computer and the storage system, are implemented as the data communication network of any kind and agreement; For example, in this example, first communication network is implemented as the gigabit Ethernet network, and the second communication network is implemented as optical-fibre channel or the iSCSI network that is connected to first principal computer and second principal computer by memory interface.
2. the virtual machine migration method towards the internal memory redundancy is characterized in that, comprises following step:
Step 1: suspend the operation that needs the migration virtual machine on the source node, the scanning virutal machine memory page also generates the descriptor memory symbol, then the descriptor memory symbol is sent to destination node;
First principal computer, be source node first the migration control system interactive module by first network adapter via first communication network to second principal computer, the second migration control system that is destination node is initiated the virtual machine (vm) migration request, after obtaining responding, the first migration control system is suspended the operation of first virtual machine, and utilize scan module to scan the internal storage data of first virtual machine, generate the descriptor memory symbol of first virtual machine and it is sent to second principal computer by first network adapter via first communication network; The descriptor memory symbol of this first virtual machine mainly comprises the physical page sequence number of virutal machine memory, machine page sequence number, and by the cryptographic hash of memory pages content generation, and the data sampling of the memory pages content of 32 bytes;
Step 2: destination node scan this machine memory pages and with the descriptor memory symbol of need migrations virtual machine relatively, generate the memory pages tabulation that needs transmission and also return to source node;
After second principal computer obtains the descriptor memory symbol of first virtual machine, comparison module by the second migration control system, scan this node machine memory pages and compare, and then generate the page listings of first virutal machine memory that needs migration and send to first principal computer via first communication network by second network adapter with the descriptor memory of first virtual machine symbol;
Step 3: source node extracts the page in the internal memory tabulation and compresses the back and together sends destination node to virtual machine state information;
After first principal computer obtains needing the first virtual machine page listings of migration, the first migration control system is extracted the memory pages that needs migration and is utilized compression module that internal storage data is compressed from the internal memory of first principal computer, will send second principal computer by first network adapter to via first communication network through the data of overcompression then;
Step 4: the destination node decompressed data, create new memory pages according to memory content, and rebulid page-map according to migration virutal machine memory descriptor;
After second principal computer obtains the internal storage data of first virtual machine, utilize the compression module of the second migration control system to carry out data decompression, and on second principal computer, create new machine memory pages, and set up the mapping relations of the new virtual machine physical page of first virtual machine to the machine page according to the descriptor memory of first virtual machine symbol and internal storage data;
Step 5: the virtual drive of change migration virtual machine starts the virtual machine operation to the mapping relations of disk array;
First virtual drive of cancelling first virtual machine on first principal computer is via the mapping relations of second communication network to the lun152 of disk array, simultaneously on second principal computer, set up first virtual drive of the first new virtual machine via the mapping relations of second communication network to the lun152 of disk array, destroy first virtual machine on former first principal computer at last to reclaim resource, and starting the operation of first virtual machine on second principal computer, transition process finishes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201010603168.3A CN102103524B (en) | 2010-12-23 | A kind of virtual machine (vm) migration devices and methods therefor of memory redundancy oriented |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201010603168.3A CN102103524B (en) | 2010-12-23 | A kind of virtual machine (vm) migration devices and methods therefor of memory redundancy oriented |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102103524A true CN102103524A (en) | 2011-06-22 |
| CN102103524B CN102103524B (en) | 2016-12-14 |
Family
ID=
Cited By (33)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102317910A (en) * | 2011-08-03 | 2012-01-11 | 华为技术有限公司 | Methods, devices and system for virtual data backup and reintegration |
| CN102609361A (en) * | 2012-01-16 | 2012-07-25 | 北京邮电大学 | Method and device for transferring storage data of virtual machine |
| CN102681913A (en) * | 2011-12-21 | 2012-09-19 | 中兴通讯股份有限公司 | Method and device for realizing live migration along virtual machines |
| WO2013049991A1 (en) * | 2011-10-04 | 2013-04-11 | International Business Machines Corporation | Network adapter hardware state migration discovery in a stateful environment |
| CN103207801A (en) * | 2012-01-11 | 2013-07-17 | 华为技术有限公司 | Method, device and system for migrating virtual machine and fiber channel switch |
| CN103353850A (en) * | 2013-06-13 | 2013-10-16 | 华为技术有限公司 | Virtual machine thermal migration memory processing method, device and system |
| WO2013190562A1 (en) * | 2012-06-22 | 2013-12-27 | Hewlett-Packard Development Company, L.P. | Optimal assignment of virtual machines and virtual disks using multiary tree |
| CN103618627A (en) * | 2013-11-27 | 2014-03-05 | 华为技术有限公司 | Method, device and system for managing virtual machines |
| CN103647849A (en) * | 2013-12-24 | 2014-03-19 | 华为技术有限公司 | Method and device for migrating businesses and disaster recovery system |
| WO2014082459A1 (en) * | 2012-11-30 | 2014-06-05 | 华为技术有限公司 | Method, apparatus, and system for implementing hot migration of virtual machine |
| CN103874979A (en) * | 2011-12-08 | 2014-06-18 | 株式会社日立制作所 | Remote copy system and remote copy control method |
| CN104052492A (en) * | 2013-03-15 | 2014-09-17 | 索尼电脑娱乐公司 | Compression of state information for data transfer over cloud-based networks |
| WO2014139470A1 (en) * | 2013-03-15 | 2014-09-18 | 中兴通讯股份有限公司 | System and method for managing excessive distribution of memory |
| CN104156254A (en) * | 2014-07-29 | 2014-11-19 | 北京高森明晨信息科技有限公司 | Method and device for migrating virtual machines |
| CN104320431A (en) * | 2014-09-24 | 2015-01-28 | 北京云巢动脉科技有限公司 | Method for sharing data of mobile terminal and virtual machine |
| CN104539716A (en) * | 2015-01-04 | 2015-04-22 | 国网四川省电力公司信息通信公司 | Cloud desktop management system desktop virtual machine dispatching control system and method |
| CN104657087A (en) * | 2015-02-04 | 2015-05-27 | 杭州华为数字技术有限公司 | Virtual disk mapping method, device and system |
| CN105446792A (en) * | 2014-08-27 | 2016-03-30 | 联想(北京)有限公司 | Deployment method, deployment device and management node of virtual machines |
| CN105468457A (en) * | 2015-11-24 | 2016-04-06 | 无锡江南计算技术研究所 | Parallel system local migration fault-tolerant method based on difference recognition |
| CN105786585A (en) * | 2014-12-15 | 2016-07-20 | 中国电信股份有限公司 | System and method for online transfer of memory data |
| CN103885830B (en) * | 2014-04-16 | 2017-02-15 | 中国科学院软件研究所 | Data processing method used in cross-data-center live migration process of virtual machine |
| US9588807B2 (en) | 2011-10-04 | 2017-03-07 | International Business Machines Corporation | Live logical partition migration with stateful offload connections using context extraction and insertion |
| CN106575235A (en) * | 2014-09-12 | 2017-04-19 | 英特尔公司 | Memory and resource management in a virtual computing environment |
| CN107608782A (en) * | 2016-07-11 | 2018-01-19 | 阿里巴巴集团控股有限公司 | The method and device of memory compression, operating system, electronic equipment |
| CN107818054A (en) * | 2016-09-12 | 2018-03-20 | 联发科技股份有限公司 | Distribute method and system of the continuous physical memory space to equipment |
| CN107967168A (en) * | 2017-12-08 | 2018-04-27 | 中南大学 | Virtual machine integration method based on the shared drive page in a kind of cloud data center |
| CN108073443A (en) * | 2017-12-08 | 2018-05-25 | 中南大学 | Virtual machine selection based on the shared drive page and laying method in a kind of cloud data center |
| CN109144659A (en) * | 2017-06-27 | 2019-01-04 | 英特尔公司 | Use the technology of decomposition computation resource migration virtual machine |
| CN110475272A (en) * | 2019-07-31 | 2019-11-19 | 苏州星际靶战网络信息技术有限公司 | A kind of virtualization network equipment library information transferring method and system |
| CN112328368A (en) * | 2020-11-20 | 2021-02-05 | 上海云轴信息科技有限公司 | Application layer storage method and device based on cloud platform |
| CN112416507A (en) * | 2019-08-22 | 2021-02-26 | 华为技术有限公司 | Virtual machine migration method and equipment |
| WO2021051563A1 (en) * | 2019-09-17 | 2021-03-25 | 平安科技（深圳）有限公司 | Target data archiving method and apparatus, and electronic device and computer non-volatile readable storage medium |
| CN113076175A (en) * | 2021-03-26 | 2021-07-06 | 北京汇钧科技有限公司 | Memory sharing method and device for virtual machine |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080222375A1 (en) * | 2007-02-21 | 2008-09-11 | Deutsche Telekom Ag | Method and system for the transparent migration of virtual machines storage |
| US20090063749A1 (en) * | 2007-08-27 | 2009-03-05 | International Business Machines Corporation | Tracking data updates during memory migration |
| CN101464812A (en) * | 2009-01-06 | 2009-06-24 | 北京航空航天大学 | Virtual machine migration method |
| CN101609419A (en) * | 2009-06-29 | 2009-12-23 | 北京航空航天大学 | The data back up method and the device of the migration of virtual machine consistently online |
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080222375A1 (en) * | 2007-02-21 | 2008-09-11 | Deutsche Telekom Ag | Method and system for the transparent migration of virtual machines storage |
| US20090063749A1 (en) * | 2007-08-27 | 2009-03-05 | International Business Machines Corporation | Tracking data updates during memory migration |
| CN101464812A (en) * | 2009-01-06 | 2009-06-24 | 北京航空航天大学 | Virtual machine migration method |
| CN101609419A (en) * | 2009-06-29 | 2009-12-23 | 北京航空航天大学 | The data back up method and the device of the migration of virtual machine consistently online |
Non-Patent Citations (1)
| Title |
|---|
| HAI JIN, LI DENG, SONG WU, XUANHUA SHI, XIAODONG PAN: "《Live Virtual Machine Migration with Adaptive Memory Compression》", 《IEEE INTERNATIONAL CONFERENCE ON CLUSTER COMPUTING AND WORKSHOPS》, 4 September 2009 (2009-09-04) * |
Cited By (59)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102317910B (en) * | 2011-08-03 | 2014-08-20 | 华为技术有限公司 | Methods, devices and system for virtual data backup and reintegration |
| CN102317910A (en) * | 2011-08-03 | 2012-01-11 | 华为技术有限公司 | Methods, devices and system for virtual data backup and reintegration |
| US9547605B2 (en) | 2011-08-03 | 2017-01-17 | Huawei Technologies Co., Ltd. | Method for data backup, device and system |
| US9588807B2 (en) | 2011-10-04 | 2017-03-07 | International Business Machines Corporation | Live logical partition migration with stateful offload connections using context extraction and insertion |
| US8830870B2 (en) | 2011-10-04 | 2014-09-09 | International Business Machines Corporation | Network adapter hardware state migration discovery in a stateful environment |
| GB2510508B (en) * | 2011-10-04 | 2015-07-08 | Ibm | Network adapter hardware state migration discovery in a stateful environment |
| WO2013049991A1 (en) * | 2011-10-04 | 2013-04-11 | International Business Machines Corporation | Network adapter hardware state migration discovery in a stateful environment |
| GB2510508A (en) * | 2011-10-04 | 2014-08-06 | Ibm | Network adapter hardware state migration discovery in a stateful environment |
| CN103843302A (en) * | 2011-10-04 | 2014-06-04 | 国际商业机器公司 | Network adapter hardware state migration discovery in a stateful environment |
| CN103874979A (en) * | 2011-12-08 | 2014-06-18 | 株式会社日立制作所 | Remote copy system and remote copy control method |
| CN102681913A (en) * | 2011-12-21 | 2012-09-19 | 中兴通讯股份有限公司 | Method and device for realizing live migration along virtual machines |
| CN103207801B (en) * | 2012-01-11 | 2016-09-14 | 华为技术有限公司 | The methods, devices and systems of virtual machine (vm) migration and fibre channel media |
| CN103207801A (en) * | 2012-01-11 | 2013-07-17 | 华为技术有限公司 | Method, device and system for migrating virtual machine and fiber channel switch |
| CN102609361A (en) * | 2012-01-16 | 2012-07-25 | 北京邮电大学 | Method and device for transferring storage data of virtual machine |
| CN102609361B (en) * | 2012-01-16 | 2015-06-24 | 北京红山世纪科技有限公司 | Method and device for transferring storage data of virtual machine |
| WO2013190562A1 (en) * | 2012-06-22 | 2013-12-27 | Hewlett-Packard Development Company, L.P. | Optimal assignment of virtual machines and virtual disks using multiary tree |
| CN104604187A (en) * | 2012-06-22 | 2015-05-06 | 惠普发展公司，有限责任合伙企业 | Optimal assignment of virtual machines and virtual disks using multiary tree |
| US9672075B2 (en) | 2012-11-30 | 2017-06-06 | Huawei Technologies Co., Ltd. | Method, apparatus, and system for implementing hot migration of virtual machine |
| WO2014082459A1 (en) * | 2012-11-30 | 2014-06-05 | 华为技术有限公司 | Method, apparatus, and system for implementing hot migration of virtual machine |
| WO2014139470A1 (en) * | 2013-03-15 | 2014-09-18 | 中兴通讯股份有限公司 | System and method for managing excessive distribution of memory |
| CN104052492A (en) * | 2013-03-15 | 2014-09-17 | 索尼电脑娱乐公司 | Compression of state information for data transfer over cloud-based networks |
| US9697053B2 (en) | 2013-03-15 | 2017-07-04 | Zte Corporation | System and method for managing excessive distribution of memory |
| CN104052492B (en) * | 2013-03-15 | 2019-05-14 | 索尼电脑娱乐公司 | Compression for the status information carried out data transmission by network based on cloud |
| CN103353850B (en) * | 2013-06-13 | 2017-02-22 | 华为技术有限公司 | Virtual machine thermal migration memory processing method, device and system |
| CN103353850A (en) * | 2013-06-13 | 2013-10-16 | 华为技术有限公司 | Virtual machine thermal migration memory processing method, device and system |
| CN103618627B (en) * | 2013-11-27 | 2017-01-04 | 华为技术有限公司 | A kind of manage the method for virtual machine, Apparatus and system |
| CN103618627A (en) * | 2013-11-27 | 2014-03-05 | 华为技术有限公司 | Method, device and system for managing virtual machines |
| CN103647849B (en) * | 2013-12-24 | 2017-02-08 | 华为技术有限公司 | Method and device for migrating businesses and disaster recovery system |
| CN103647849A (en) * | 2013-12-24 | 2014-03-19 | 华为技术有限公司 | Method and device for migrating businesses and disaster recovery system |
| WO2015096500A1 (en) * | 2013-12-24 | 2015-07-02 | 华为技术有限公司 | Service migration method and device and disaster tolerance system |
| CN103885830B (en) * | 2014-04-16 | 2017-02-15 | 中国科学院软件研究所 | Data processing method used in cross-data-center live migration process of virtual machine |
| CN104156254A (en) * | 2014-07-29 | 2014-11-19 | 北京高森明晨信息科技有限公司 | Method and device for migrating virtual machines |
| CN105446792B (en) * | 2014-08-27 | 2019-09-24 | 联想(北京)有限公司 | A kind of dispositions method of virtual machine, deployment device and management node |
| CN105446792A (en) * | 2014-08-27 | 2016-03-30 | 联想(北京)有限公司 | Deployment method, deployment device and management node of virtual machines |
| CN106575235B (en) * | 2014-09-12 | 2020-10-23 | 英特尔公司 | Memory and resource management in a virtualized computing environment |
| CN106575235A (en) * | 2014-09-12 | 2017-04-19 | 英特尔公司 | Memory and resource management in a virtual computing environment |
| CN104320431A (en) * | 2014-09-24 | 2015-01-28 | 北京云巢动脉科技有限公司 | Method for sharing data of mobile terminal and virtual machine |
| CN105786585B (en) * | 2014-12-15 | 2019-01-29 | 中国电信股份有限公司 | The system and method for online migration internal storage data |
| CN105786585A (en) * | 2014-12-15 | 2016-07-20 | 中国电信股份有限公司 | System and method for online transfer of memory data |
| CN104539716A (en) * | 2015-01-04 | 2015-04-22 | 国网四川省电力公司信息通信公司 | Cloud desktop management system desktop virtual machine dispatching control system and method |
| CN104657087B (en) * | 2015-02-04 | 2018-01-12 | 杭州华为数字技术有限公司 | A kind of method, apparatus and system of virtual disk mapping |
| CN104657087A (en) * | 2015-02-04 | 2015-05-27 | 杭州华为数字技术有限公司 | Virtual disk mapping method, device and system |
| CN105468457A (en) * | 2015-11-24 | 2016-04-06 | 无锡江南计算技术研究所 | Parallel system local migration fault-tolerant method based on difference recognition |
| CN105468457B (en) * | 2015-11-24 | 2019-04-09 | 无锡江南计算技术研究所 | A kind of parallel system local migration fault-tolerance approach based on difference identification |
| CN107608782A (en) * | 2016-07-11 | 2018-01-19 | 阿里巴巴集团控股有限公司 | The method and device of memory compression, operating system, electronic equipment |
| CN107818054A (en) * | 2016-09-12 | 2018-03-20 | 联发科技股份有限公司 | Distribute method and system of the continuous physical memory space to equipment |
| CN109144659A (en) * | 2017-06-27 | 2019-01-04 | 英特尔公司 | Use the technology of decomposition computation resource migration virtual machine |
| CN108073443A (en) * | 2017-12-08 | 2018-05-25 | 中南大学 | Virtual machine selection based on the shared drive page and laying method in a kind of cloud data center |
| CN107967168A (en) * | 2017-12-08 | 2018-04-27 | 中南大学 | Virtual machine integration method based on the shared drive page in a kind of cloud data center |
| CN108073443B (en) * | 2017-12-08 | 2021-10-26 | 中南大学 | Virtual machine selection and placement method based on shared memory page in cloud data center |
| CN107967168B (en) * | 2017-12-08 | 2021-11-12 | 中南大学 | Virtual machine integration method based on shared memory page in cloud data center |
| CN110475272A (en) * | 2019-07-31 | 2019-11-19 | 苏州星际靶战网络信息技术有限公司 | A kind of virtualization network equipment library information transferring method and system |
| CN112416507A (en) * | 2019-08-22 | 2021-02-26 | 华为技术有限公司 | Virtual machine migration method and equipment |
| WO2021051563A1 (en) * | 2019-09-17 | 2021-03-25 | 平安科技（深圳）有限公司 | Target data archiving method and apparatus, and electronic device and computer non-volatile readable storage medium |
| CN112328368A (en) * | 2020-11-20 | 2021-02-05 | 上海云轴信息科技有限公司 | Application layer storage method and device based on cloud platform |
| CN112328368B (en) * | 2020-11-20 | 2022-12-27 | 上海云轴信息科技有限公司 | Application layer storage method and device based on cloud platform |
| CN113076175A (en) * | 2021-03-26 | 2021-07-06 | 北京汇钧科技有限公司 | Memory sharing method and device for virtual machine |
| WO2022199206A1 (en) * | 2021-03-26 | 2022-09-29 | 北京汇钧科技有限公司 | Memory sharing method and device for virtual machines |
| CN113076175B (en) * | 2021-03-26 | 2022-09-30 | 北京汇钧科技有限公司 | Memory sharing method and device for virtual machine |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11281394B2 (en) | Replication across partitioning schemes in a distributed storage system | |
| US8291425B2 (en) | Computer, control method for virtual device, and program thereof | |
| Hu et al. | HMDC: Live virtual machine migration based on hybrid memory copy and delta compression | |
| CN103748545B (en) | Data storage system and data storage control method | |
| US10936454B2 (en) | Disaster recovery for virtualized systems | |
| CN114041112A (en) | Virtual storage system architecture | |
| US9563569B2 (en) | Memory transformation in virtual machine live migration | |
| EP2831716B1 (en) | File map compression | |
| US11099952B2 (en) | Leveraging server side cache in failover scenario | |
| Zhang et al. | Mvmotion: a metadata based virtual machine migration in cloud | |
| CN104735123A (en) | Mass storage virtualization for cloud computing | |
| US20200226107A1 (en) | Reinforcement learning for optimizing data deduplication | |
| CN115221089A (en) | Apparatus, method and computer program product for efficient software-defined network acceleration processing using storage local to a host | |
| Sharma et al. | A technical review for efficient virtual machine migration | |
| WO2021164163A1 (en) | Request processing method and apparatus, device and storage medium | |
| KR102326280B1 (en) | Method, apparatus, device and medium for processing data | |
| US10579419B2 (en) | Data analysis in storage system | |
| US10019182B2 (en) | Management system and management method of computer system | |
| CN113315800A (en) | Mirror image storage and downloading method, device and system | |
| US11507292B2 (en) | System and method to utilize a composite block of data during compression of data blocks of fixed size | |
| JP2013003691A (en) | Computing system and disk sharing method in computing system | |
| CN107885586A (en) | A kind of safety protecting method that virtual machine is migrated in private clound | |
| Modi et al. | Live migration of virtual machines with their local persistent storage in a data intensive cloud | |
| CN102103524A (en) | Memory redundancy oriented virtual machine migration device and method | |
| CN104333603A (en) | System and method for implementing file uploading to virtual machines |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| ASS | Succession or assignment of patent right |
Owner name: HUAWEI TECHNOLOGY CO LTD Free format text: FORMER OWNER: BEIJING AERONAUTICS AND ASTRONAUTICS UNIV. Effective date: 20110926 |
|
| C41 | Transfer of patent application or patent right or utility model | ||
| COR | Change of bibliographic data |
Free format text: CORRECT: ADDRESS; FROM: 100191 HAIDIAN, BEIJING TO: 518129 SHENZHEN, GUANGDONG PROVINCE |
|
| TA01 | Transfer of patent application right |
Effective date of registration: 20110926 Address after: 518129 headquarters building, Bantian HUAWEI base, Longgang District, Shenzhen, Shenzhen, Guangdong, Guangdong, China Applicant after: Huawei Technologies Co., Ltd. Address before: 100191 Beijing City, Haidian District Xueyuan Road No. 37 North College of computer Applicant before: Beihang University |
|
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20161214 Termination date: 20171223 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |