Method and system for improving real-time migration efficiency of virtual machine, medium and product

Abstract

The invention discloses a method and system for improving the real-time migration efficiency of a virtual machine, a medium and a product, and the method for improving the real-time migration efficiency of the virtual machine comprises the steps that a source physical server carries out preprocessing on a migrated service virtual machine, and preprocessing comprises temporary file cleaning and cache; generating a memory snapshot for the memory state of the migrated business virtual machine; memory bandwidth optimization is carried out by using a hardware acceleration framework on the source physical server, and the business virtual machine data packet after memory bandwidth optimization is sent to the target physical server; and enabling the target physical server to locally create the business virtual machine and recover the memory snapshot by using the business virtual machine data packet obtained after memory bandwidth optimization to complete migration of the business virtual machine. The invention aims at solving the problems of low real-time migration speed and large resource consumption of the virtual machine in the prior art, and improving the real-time migration efficiency of the virtual machine and the real-time migration success rate of the virtual machine.

Description

Technical Field

[0001] The present invention relates to the field of cloud computing technology, and in particular to a method, system, medium and product for improving the efficiency of real-time migration of virtual machines. Background Art

[0002] With the continuous development of cloud computing technology, live migration of virtual machines has become one of the key technologies to improve data center resource utilization and system reliability. The traditional method of live migration of virtual machines adopts post-copy technology. In the initial stage after migration, since the virtual machine needs to continuously request memory pages that have not been copied from the source host during operation, this will cause frequent page fault exceptions, seriously affecting the performance and stability of the system. It will cause slow migration speed and high resource consumption, resulting in reduced virtual machine migration efficiency. When facing large-scale data centers and complex application scenarios, traditional methods of live migration of virtual machines often have problems such as slow migration speed and high resource consumption, which seriously affects the performance and availability of the system. Summary of the invention

[0003] Technical problem to be solved by the present invention: In view of the above-mentioned problems in the prior art, a method, system, medium and product for improving the efficiency of real-time migration of virtual machines are provided. The present invention aims to solve the problems of slow speed and high resource consumption of real-time migration of virtual machines in the prior art, and to improve the efficiency of real-time migration of virtual machines and the success rate of real-time migration of virtual machines.

[0004] In order to solve the above technical problems, the technical solution adopted by the present invention is: A method for improving the efficiency of virtual machine real-time migration includes the following steps: S1, the source physical server pre-processes the migrated business virtual machine, which includes cleaning temporary files and cache; S2, the source physical server generates a memory snapshot of the memory state of the migrated business virtual machine; S3, the source physical server uses the hardware acceleration framework on the source physical server to optimize the memory bandwidth of the memory snapshot to obtain a business virtual machine data packet after memory bandwidth optimization; S4, the source physical server sends the business virtual machine data packet after memory bandwidth optimization to the destination physical server, so that the destination physical server creates a business virtual machine locally and uses the business virtual machine data packet obtained after memory bandwidth optimization to restore the memory snapshot to complete the migration of the business virtual machine.

[0005] Optionally, step S3 includes: S3.1, read the memory snapshot stored in the hard disk into the memory and pack it after optimizing the memory access mode; S3.2, pre-fetching and caching the packaged business virtual machine data packets; S3.3, the data pre-fetched and cached business virtual machine data packets are respectively compressed in parallel using the data processing units in the hardware acceleration framework to obtain business virtual machine data packets after memory bandwidth optimization.

[0006] Optionally, in step S3.1, the memory snapshots stored in the hard disk are optimized for memory access mode, read into the memory and packaged, including: opening up two specified-size, continuous dedicated data processing spaces A and B on the memory of the source physical server; the virtual machine software runs a memory access mode optimization algorithm, and packages the memory snapshots stored in the hard disk into business virtual machine data packets according to the specified size through the memory access mode optimization algorithm, and stores them alternately in the dedicated data processing spaces A and B and marks the serial numbers of the business virtual machine data packets.

[0007] Optionally, when two continuous dedicated data processing spaces A and B of specified size are opened up on the memory of the source physical server, the specified size is 16GB, and packaging the memory snapshots stored on the hard disk into business virtual machine data packets according to the specified size means packaging the memory snapshots stored on the hard disk into business virtual machine data packets according to the size of 512M.

[0008] Optionally, in step S3.2, the business virtual machine data packets packaged for data pre-fetching and caching include: determining the sequence number of the business virtual machine data packet required for the next step according to the progress of performing parallel compression processing on the business virtual machine data packets that are pre-fetched and cached using data processing units in the hardware acceleration framework; and pre-fetching the business virtual machine data packet required for the next step from the dedicated data processing spaces A and B according to the sequence number of the business virtual machine data packet required for the next step and reading it into the cache of the hardware acceleration framework.

[0009] Optionally, in step S4, the source physical server sending the business virtual machine data packet after memory bandwidth optimization to the destination physical server specifically means that the source physical server sends the business virtual machine data packet after memory bandwidth optimization to the destination physical server after forwarding through the cloud server.

[0010] Optionally, in step S4, the destination physical server locally creates a business virtual machine and uses the business virtual machine data packet obtained after the memory bandwidth optimization to restore the memory snapshot to complete the migration of the business virtual machine, including: S101, the destination physical server creates a service virtual machine locally; S102, the destination physical server uses data processing units in a local hardware acceleration framework to perform parallel decompression processing on the service virtual machine data packets obtained after the memory bandwidth optimization to obtain service virtual machine data packets; S103, the destination physical server restores the memory snapshot according to the business virtual machine data packet to complete the migration of the business virtual machine.

[0011] In addition, the present invention also provides a system for improving the efficiency of real-time migration of virtual machines, comprising a microprocessor and a memory connected to each other, wherein the microprocessor is programmed or configured to execute the method for improving the efficiency of real-time migration of virtual machines.

[0012] In addition, the present invention also provides a computer-readable storage medium, in which a computer program or instruction is stored. The computer program or instruction is programmed or configured to execute the method for improving the efficiency of real-time migration of virtual machines through a processor.

[0013] In addition, the present invention also provides a computer program product, including a computer program or instruction, which is programmed or configured to execute the method of improving the efficiency of real-time migration of virtual machines through a processor. Compared with the prior art, the present invention mainly has the following advantages: the present invention includes a source physical server preprocessing the migrated business virtual machine, the preprocessing including cleaning temporary files and caches; the source physical server generates a memory snapshot of the memory state of the migrated business virtual machine; the source physical server optimizes the memory bandwidth of the memory snapshot using the hardware acceleration framework on the source physical server to obtain a business virtual machine data packet after memory bandwidth optimization; the source physical server sends the business virtual machine data packet after memory bandwidth optimization to the destination physical server, so that the destination physical server creates a business virtual machine locally and uses the business virtual machine data packet obtained after memory bandwidth optimization to restore the memory snapshot to complete the migration of the business virtual machine. Through the combination of the above methods, the problems of slow real-time migration of virtual machines and high resource consumption in the prior art can be solved, and the efficiency of real-time migration of virtual machines and the success rate of real-time migration of virtual machines can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 Schematic diagram of the basic flow of the method of the embodiment of the present invention.

[0015] Figure 2 Schematic diagram of the system topology structure in an embodiment of the present invention.

[0016] Figure 3 The figure is a schematic diagram of the working principle of the memory bandwidth optimization framework in an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to enable those skilled in the art to better understand the solution of the present invention, the following will take the Kylin virtual machine software as an example, combined with the drawings in the embodiments of the present invention, to clearly and completely describe the technical solution in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them, and the present invention does not depend on specific virtual machine software. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] like Figure 1 As shown, the method for improving the efficiency of real-time migration of virtual machines in this embodiment includes the following steps: S1, the source physical server pre-processes the migrated business virtual machine, which includes cleaning temporary files and cache; S2, the source physical server generates a memory snapshot of the memory state of the migrated business virtual machine; S3, the source physical server uses the hardware acceleration framework on the source physical server to optimize the memory bandwidth of the memory snapshot to obtain a business virtual machine data packet after memory bandwidth optimization; S4, the source physical server sends the business virtual machine data packet after memory bandwidth optimization to the destination physical server, so that the destination physical server creates a business virtual machine locally and uses the business virtual machine data packet obtained after memory bandwidth optimization to restore the memory snapshot to complete the migration of the business virtual machine. The key to the method of improving the efficiency of virtual machine real-time migration in this embodiment is to improve the efficiency of virtual machine real-time migration based on the Kylin virtual machine environment using the hardware acceleration framework and memory bandwidth optimization technology, thereby solving the problems of slow virtual machine real-time migration speed and high resource consumption in the prior art, improving the efficiency of virtual machine real-time migration, and the success rate of virtual machine real-time migration, and improving work efficiency.

[0019] Figure 2 This is a schematic diagram of the system topology in this embodiment, see Figure 2 In this embodiment, both the source physical server and the destination physical server are Inspur servers, and both are installed with the Kylin Advanced Server V10-SP3-2403 system, on which the Kylin virtual machine and the hardware acceleration framework are running. The source physical server and the destination physical server are connected through a cloud server. The memory analysis accelerator function is enabled during the startup of the Inspur server, and the Kylin virtual machine software and related drivers are installed to ensure that the Kylin virtual machine software can recognize and use the memory analysis accelerator function. The hardware acceleration framework is a dedicated data processing unit. The hardware acceleration framework contains multiple dedicated processing units, which are optimized for different data processing tasks. One part is used for data compression and decompression dedicated hardware processing units, and the other part is used for parallel transmission processing of data.

[0020] In step S1 of this embodiment, the source physical server pre-processes the migrated business virtual machine. The pre-processing includes cleaning up temporary files and caches, which is intended to reduce the amount of data that needs to be migrated.

[0021] In step S2 of this embodiment, the source physical server generates a memory snapshot of the memory state of the migrated business virtual machine, specifically using the Kylin virtual machine software command to take a snapshot of the memory state of the business virtual machine system. This snapshot will contain the memory data of the business virtual machine system at the time of migration so that it can be restored on the target server.

[0022] In this embodiment, step S3 of the source physical server uses the hardware acceleration framework on the source physical server to optimize the memory bandwidth of the memory snapshot to obtain the business virtual machine data packet after the memory bandwidth optimization is achieved by using the memory bandwidth optimization framework on the source physical server. Figure 3 This is a schematic diagram of the working principle of the memory bandwidth optimization framework. The main principle of memory bandwidth optimization in the memory bandwidth optimization framework is to apply four technical points: memory access mode optimization, data prefetching and caching technology, data parallel processing, and data compression and decompression. Figure 3 In this embodiment, step S3 includes: S3.1, optimize the memory access mode of the memory snapshot (original business virtual machine data packet) stored in the hard disk, read it into the memory and package it; S3.2, pre-fetching and caching the packaged business virtual machine data packets; S3.3, the data pre-fetched and cached business virtual machine data packets are respectively compressed in parallel using the data processing units in the hardware acceleration framework to obtain business virtual machine data packets after memory bandwidth optimization.

[0023] In step S3.1 of this embodiment, the memory snapshot stored in the hard disk is optimized for memory access mode, read into the memory and packaged, including: opening two specified sizes and continuous dedicated data processing spaces A and B on the memory of the source physical server; the virtual machine software runs the memory access mode optimization algorithm, and the memory snapshot stored in the hard disk is packaged into business virtual machine data packets according to the specified size through the memory access mode optimization algorithm, and alternately stored in the dedicated data processing spaces A and B and marked with the serial number of the business virtual machine data packet. Before the migration of the business virtual machine system, the Kylin virtual machine software will open up two 16GB continuous dedicated data processing spaces on the Inspur server RAM. The principle of memory access mode optimization is that the Kylin virtual machine uses the two 16GB continuous dedicated data processing spaces on the Inspur server RAM (memory) to open up two 16GB continuous dedicated data processing spaces, named as the dedicated data processing space in area A and the dedicated data processing space in area B respectively. The Kylin virtual machine software runs the memory access mode optimization algorithm, pre-fetches the business virtual machine system data from the disk to the dedicated data processing space in area A, and packages the fragmented data and small data files in the business virtual machine into group data packets according to the specified size. When processing fragmented data in the business virtual machine in area A, the Kylin virtual machine software starts to pre-fetch the memory data in area B, pre-fetches the business virtual machine system data from the disk to the dedicated data processing space in area B, and packages the fragmented data and small data files in the business virtual machine into groups of data packets according to the specified size. The memory access mode optimization algorithm completes the packaging of data packets in area A and area B memory into groups and marks the sequence number, thereby improving the utilization of memory bandwidth.

[0024] In this embodiment, when two continuous dedicated data processing spaces A and B of specified size are opened on the memory of the source physical server, the specified size is 16GB, and the memory snapshots stored on the hard disk are packaged into business virtual machine data packets according to the specified size, which means that the memory snapshots stored on the hard disk are packaged into business virtual machine data packets according to the size of 512M.

[0025] Data pre-fetching and caching technology uses the Kirin memory analysis accelerator to predict the data that the Kirin virtual machine may need to access next, and reads these data from the memory into the cache of the hardware acceleration framework in advance. In this way, when the Kirin virtual machine needs to access these data, it can be directly obtained from the cache without waiting for the delay of reading data from the memory, thereby improving the speed of data acquisition and reducing frequent requests for memory bandwidth. In step S3.2 of this embodiment, the business virtual machine data packet packaged for data pre-fetching and caching includes: determining the sequence number of the business virtual machine data packet required for the next step according to the progress of parallel compression processing of the business virtual machine data packet pre-fetched and cached by the data processing unit in the hardware acceleration framework, and pre-fetching the business virtual machine data packet required for the next step from the dedicated data processing space A and B according to the sequence number of the business virtual machine data packet required for the next step and reading it into the cache of the hardware acceleration framework. The memory data in area B is executed in the same way as the memory data in area A. The Kirin virtual machine software loops and executes the above operations in area A memory and area B memory until the business virtual machine system data packet is processed.

[0026] In step S3.3 of this embodiment, the data pre-fetched and cached business virtual machine data packets are respectively compressed in parallel by the data processing unit in the hardware acceleration framework to obtain the business virtual machine data packets after the memory bandwidth is optimized. The data processing unit in the hardware acceleration framework executes the kycanned compression algorithm, and the hardware acceleration parallel processing of the marked group data packet compression work is effectively reduced. The system time of the compressed business virtual machine is uploaded to the cloud server in real time. It should be noted that the method of this embodiment does not depend on a specific compression algorithm. For example, the LZ4 algorithm, Snappy algorithm, LZW algorithm, LZMA algorithm and KAEzip algorithm can also be used as needed. These can all use the corresponding acceleration hardware (such as FPGA chip or CPU built-in acceleration engine) to achieve parallel compression processing. Parallel compression processing is that the memory analysis accelerator supports multiple data channels for data transmission at the same time, similar to a multi-lane highway, which can transmit multiple data packets at the same time and improve the parallelism of data transmission. In this way, more data can be transmitted at the same time, effectively utilizing the memory bandwidth and improving the efficiency of data transmission. Data compression and decompression are to compress data to reduce the amount of data, thereby reducing the bandwidth required for storage and transmission in memory. When data is compressed, the same amount of data occupies less memory space, and the amount of data transmitted on the memory bus is also reduced accordingly. Therefore, Kylin VM uses hardware acceleration framework and memory bandwidth optimization technology to implement a method that effectively improves the speed and reliability of real-time migration of VMs.

[0027] As an optional implementation, in step S4 of this embodiment, the source physical server sends the business virtual machine data packet after memory bandwidth optimization to the destination physical server, which specifically means that the source physical server sends the business virtual machine data packet after memory bandwidth optimization to the destination physical server after transferring it through the cloud server.

[0028] In this embodiment, in step S4, the destination physical server creates a service virtual machine locally and uses the service virtual machine data packet obtained after the memory bandwidth optimization to restore the memory snapshot to complete the migration of the service virtual machine, including: S101, the destination physical server creates a service virtual machine locally; S102, the destination physical server uses data processing units in a local hardware acceleration framework to perform parallel decompression processing on the service virtual machine data packets obtained after the memory bandwidth optimization to obtain service virtual machine data packets; S103, the destination physical server restores the memory snapshot according to the business virtual machine data packet to complete the migration of the business virtual machine.

[0029] The cloud server then distributes it to the target physical server. After the target server receives the compressed data of the business virtual machine system, the Kylin virtual machine software will mark the data packets with serial numbers and send them to multiple dedicated processing units of the hardware acceleration framework in sequence. Each dedicated processing unit executes the kycanned decompression algorithm to perform hardware acceleration parallel processing on the decompression work of the marked group data packets, thereby effectively reducing the decompression time of the business virtual machine system. The hardware acceleration capability makes the decompression process very fast, and can restore the memory data of the virtual machine to the state before migration in a short time. Similarly, the target physical server uses the data processing units in the local hardware acceleration framework to perform parallel decompression processing on the business virtual machine data packets obtained after the memory bandwidth optimization to obtain the business virtual machine data packets. It can also use the LZ4 algorithm, Snappy algorithm, LZW algorithm, LZMA algorithm and KAEzip algorithm as needed, and use the corresponding acceleration hardware (such as FPGA chip or CPU built-in acceleration engine) to achieve parallel compression processing, which will not be described in detail here. Finally, the target physical server starts the Kylin virtual machine software, runs the business virtual machine system distributed from the cloud server, runs the automated testing tool, and the test results show that the business virtual machine works normally.

[0030] In summary, the method for improving the efficiency of virtual machine real-time migration in this embodiment provides an efficient and reliable virtual machine real-time migration solution for Kylin virtual machines. The method for improving the efficiency of virtual machine real-time migration in this embodiment uses hardware acceleration framework and memory bandwidth optimization technology based on Kylin virtual machines to maximize the efficiency of virtual machine real-time migration. Moreover, the method for improving the efficiency of virtual machine real-time migration in this embodiment does not depend on specific virtual machine software, and can also use the required compression / decompression algorithm and the hardware acceleration framework that supports the compression / decompression algorithm as needed.

[0031] In addition, this embodiment also provides a system for improving the efficiency of real-time migration of virtual machines, including a microprocessor and a memory connected to each other, and the microprocessor is programmed or configured to execute the method for improving the efficiency of real-time migration of virtual machines.

[0032] In addition, this embodiment further provides a computer-readable storage medium, in which a computer program or instruction is stored. The computer program or instruction is programmed or configured to execute the method for improving the efficiency of real-time migration of virtual machines through a processor.

[0033] In addition, this embodiment also provides a computer program product, including a computer program or instructions, which are programmed or configured to execute the method for improving the efficiency of real-time migration of virtual machines through a processor.

[0034] Those skilled in the art should understand that the technical solutions provided by the embodiments of the present application may be in the form of methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the process Figure 1 A process or multiple processes and / or boxes Figure 1These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing device to work in a specific way, so that the instructions stored in the computer-readable memory produce a product including an instruction device, which implements the functions specified in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide for implementing the process in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0035] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A method for improving the efficiency of real-time migration of virtual machines, characterized in that: The steps include: S1, the source physical server pre-processes the migrated business virtual machine, which includes cleaning temporary files and cache; S2, the source physical server generates a memory snapshot of the memory state of the migrated business virtual machine; S3, the source physical server uses the hardware acceleration framework on the source physical server to optimize the memory bandwidth of the memory snapshot to obtain a business virtual machine data packet after memory bandwidth optimization; S4, the source physical server sends the business virtual machine data packet after memory bandwidth optimization to the destination physical server, so that the destination physical server creates a business virtual machine locally and uses the business virtual machine data packet obtained after memory bandwidth optimization to restore the memory snapshot to complete the migration of the business virtual machine.

2. The method for improving the efficiency of real-time migration of virtual machines according to claim 1, characterized in that: Step S3 includes: S3.1, read the memory snapshot stored in the hard disk into the memory and pack it after optimizing the memory access mode; S3.2, pre-fetching and caching the packaged business virtual machine data packets; S3.3, the data pre-fetched and cached business virtual machine data packets are respectively compressed in parallel using the data processing units in the hardware acceleration framework to obtain business virtual machine data packets after memory bandwidth optimization.

3. The method for improving the efficiency of real-time migration of virtual machines according to claim 2, characterized in that: In step S3.1, the memory snapshots stored in the hard disk are optimized for memory access mode, read into the memory and packaged, including: opening up two specified-size, continuous dedicated data processing spaces A and B on the memory of the source physical server; the virtual machine software runs a memory access mode optimization algorithm, and packages the memory snapshots stored in the hard disk into business virtual machine data packets according to the specified size through the memory access mode optimization algorithm, and stores them alternately in the dedicated data processing spaces A and B and marks the serial numbers of the business virtual machine data packets.

4. The method for improving the efficiency of real-time migration of virtual machines according to claim 3, characterized in that: When two specified-size, continuous dedicated data processing spaces A and B are opened up on the memory of the source physical server, the specified size is 16GB, and packaging the memory snapshots stored on the hard disk into business virtual machine data packets according to the specified size means packaging the memory snapshots stored on the hard disk into business virtual machine data packets according to the size of 512M.

5. The method for improving the efficiency of real-time migration of virtual machines according to claim 2, characterized in that: In step S3.2, the business virtual machine data packets packaged are pre-fetched and cached, including: determining the sequence number of the business virtual machine data packet required for the next step according to the progress of parallel compression processing of the business virtual machine data packets pre-fetched and cached by the data processing units in the hardware acceleration framework; and pre-fetching the business virtual machine data packet required for the next step from the dedicated data processing spaces A and B according to the sequence number of the business virtual machine data packet required for the next step and reading it into the cache of the hardware acceleration framework.

6. The method for improving the efficiency of real-time migration of virtual machines according to claim 1, characterized in that: In step S4, the source physical server sends the business virtual machine data packet after memory bandwidth optimization to the destination physical server, which specifically means that the source physical server sends the business virtual machine data packet after memory bandwidth optimization to the destination physical server after forwarding through the cloud server.

7. The method for improving the efficiency of real-time migration of virtual machines according to claim 1, characterized in that: In step S4, the destination physical server creates a business virtual machine locally and uses the business virtual machine data packet obtained after memory bandwidth optimization to restore the memory snapshot to complete the migration of the business virtual machine, including: S101, the destination physical server creates a service virtual machine locally; S102, the destination physical server uses data processing units in a local hardware acceleration framework to perform parallel decompression processing on the service virtual machine data packets obtained after the memory bandwidth optimization to obtain service virtual machine data packets; S103, the destination physical server restores the memory snapshot according to the business virtual machine data packet to complete the migration of the business virtual machine.

8. A system for improving the efficiency of real-time migration of virtual machines, comprising a microprocessor and a memory connected to each other, characterized in that: The microprocessor is programmed or configured to execute the method for improving the efficiency of real-time migration of virtual machines as described in any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program or instruction stored therein, characterized in that: The computer program or instruction is programmed or configured to execute the method for improving the efficiency of real-time migration of virtual machines as described in any one of claims 1 to 7 through a processor.

10. A computer program product comprising a computer program or instructions, characterized in that The computer program or instruction is programmed or configured to execute the method for improving the efficiency of real-time migration of virtual machines as described in any one of claims 1 to 7 through a processor.

Images