KR20200075998A - Method and apparatus for measuring memory sharing rate in virtual envirnoment - Google Patents

Abstract

The present invention relates to a method and a device for measuring a memory sharing rate in a virtualized environment. According to one embodiment of the present invention, the method for measuring the memory sharing rate comprises the following steps of: generating sharing change information for a changed shared page when the shared page shared by at least one virtual machine is changed; generating a hash table based on the generated sharing change information; tracking a virtual machine using the changed shared page by using the generated hash table; and measuring the memory sharing rate used by the virtual machine based on the tracked virtual machine.

Description

METHOD AND APPARATUS FOR MEMORY SHARING RATE IN VIRTUAL ENVIRONMENT {METHOD AND APPARATUS FOR MEASURING MEMORY SHARING RATE IN VIRTUAL ENVIRNOMENT}

The present invention relates to a method and apparatus for measuring a memory sharing rate in a virtualized environment.

Various memory deduplication techniques exist to increase memory efficiency in a virtualized environment. At this time, the memory sharing that occurs in the virtualization environment may be divided into self-sharing and inter-sharing between virtual machines. Both shares are made by the host's memory deduplication module, but are divided according to the number of virtual machines using the shared page. Virtual machine internal sharing means a page shared only inside a single virtual machine, and sharing between virtual machines means that page sharing is performed between different virtual machines running on the same host. The Linux kernel supports kernel samepage merging (KSM) from version 2.6.32, and KSM can significantly increase memory efficiency in a virtualized environment by removing duplicate pages using content-based page sharing (CBPS).

However, KSM provides only the total number of pages shared by the entire system, and cannot distinguish between virtual machine internal sharing and virtual machine sharing. Accordingly, there have been attempts to measure the sharing between the virtual machine internal sharing and the virtual machine, but the prior art fails to measure this in real time and uses a method of generating a snapshot of the virtual machine and scanning the entire memory. This method does not match the characteristics of a virtualization environment that must continuously provide services, and when three or more virtual machines are executed, it takes too much time to measure and compare each virtual machine.

According to embodiments of the present invention, the virtual machine using the shared page can be tracked by generating sharing change information whenever the shared page used by the virtual machine is changed, thereby measuring the memory sharing rate used by the virtual machine. It is intended to provide a method and apparatus for measuring a memory sharing rate in an environment.

Embodiments of the present invention are to provide a method and apparatus for measuring a memory sharing rate in a virtualized environment, which can measure in real time by classifying the sharing occurring between the virtual machine and the sharing occurring in the virtual machine in a virtual environment.

According to an embodiment of the present invention, in a method for measuring a memory sharing rate performed by a virtualization device, when a shared page shared by at least one virtual machine is changed, generating sharing change information for the changed shared page ; Generating a hash table based on the generated sharing change information; Tracking a virtual machine using the changed shared page using the generated hash table; And measuring a memory sharing rate used by the virtual machine based on the tracked virtual machine.

In the step of generating the sharing change information, the sharing change information may be generated by using page information for the changed sharing page and process information of a process using the changed sharing page.

In the step of generating the sharing change information, when the sharing page is changed in a node of the stable tree in which the sharing page shared by at least one virtual machine is stored, sharing change information for the changed sharing page may be generated.

In the step of generating the sharing change information, when a new sharing page shared by at least one virtual machine is added or a sharing page being shared in advance is released, sharing of each of the added sharing page or the released sharing page Each change information can be generated.

In the generating of the hash table, based on the generated sharing change information, a double hash table having a frame number of the shared page and identification information of the virtual machine as a hash key may be generated.

The step of measuring the memory sharing rate is divided into internal sharing (Self-sharing) and virtual sharing (Inter-sharing) between the virtual machines based on the tracked virtual machine to measure the memory sharing ratio used by the virtual machine. can do.

In the measuring of the memory sharing rate, the memory sharing rate used by the virtual machine may be measured by accumulatively updating the number of virtual machines using the changed shared page whenever the shared page is changed in the stable tree node. have.

The method may further include terminating the virtual machine in which the measured memory sharing rate is less than a preset sharing rate based on the measured memory sharing rate.

The method may further include adjoining a virtual machine sharing the same page based on the measured memory sharing rate.

The method may further include selecting a virtual machine having the lowest memory sharing ratio as a virtual machine to migrate based on the measured memory sharing ratio.

On the other hand, according to another embodiment of the present invention, the memory for storing a shared page shared by at least one virtual machine; And a processor connected to the memory, wherein the processor generates sharing change information for the changed sharing page when the shared page shared by at least one virtual machine is changed, and based on the generated sharing change information. Create a hash table, track the virtual machine using the changed shared page using the generated hash table, and measure the memory sharing rate used by the virtual machine based on the tracked virtual machine A memory sharing rate measuring device may be provided.

The processor may generate the sharing change information using page information for the changed shared page and process information of a process using the changed shared page.

The processor may generate sharing change information for the changed shared page when the shared page is changed in a node of the stable tree in which the shared page shared by at least one virtual machine is stored.

When the new shared page shared by at least one virtual machine is added or the shared page being shared in advance is unshared, the processor generates sharing change information for each of the added shared page or the released shared page, respectively. Can.

The processor may generate a double hash table each having a hash key as a hash key for the frame number of the shared page and the identification information of the virtual machine, based on the generated share change information.

The processor may measure a memory sharing rate of the virtual machine by dividing it into a virtual machine internal sharing (Self-sharing) and a virtual machine sharing (Inter-sharing) based on the tracked virtual machine.

The processor may measure the memory sharing rate of the virtual machine by accumulatively updating the number of virtual machines using the changed shared page whenever the shared page is changed in a node of the stable tree.

The processor may terminate the virtual machine in which the measured memory sharing rate is less than a preset sharing rate based on the measured memory sharing rate.

The processor may adjoin a virtual machine sharing the same page based on the measured memory sharing rate.

The processor may select a virtual machine to migrate a virtual machine having the lowest memory sharing ratio based on the measured memory sharing ratio.

On the other hand, according to another embodiment of the present invention, in a recording medium readable by a computer recording a program for executing a memory sharing rate measurement method on a computer, when a shared page shared by at least one virtual machine is changed, the Generating sharing change information for the changed sharing page; Generating a hash table based on the generated sharing change information; Tracking a virtual machine using the changed shared page using the generated hash table; And a computer readable recording medium recording a program for executing a step of measuring a memory sharing rate used by the virtual machine based on the tracked virtual machine.

According to embodiments of the present invention, the internal sharing of the virtual machine and the sharing between the virtual machines are measured in real time to provide a memory sharing rate used by the virtual machine in real time. The internal sharing of a virtual machine is determined by the operating system of the corresponding virtual machine and an application running regardless of other virtual machines. On the other hand, sharing between virtual machines is determined by other virtual machines running on the same host. Therefore, embodiments of the present invention can increase the memory efficiency of the entire virtualization system by deploying and migrating the virtual machine in real time to the host so as to maximize sharing between the virtual machines.

1 is a view for explaining a KSM in a mobile device to which a general virtualization environment is applied.
2 is a view for explaining a KSM according to an embodiment of the present invention.
3 is a view for explaining a stable tree for storing a shared page used in an embodiment of the present invention.
4 is a flowchart illustrating a method for measuring a memory sharing rate according to an embodiment of the present invention.
5 is a flowchart illustrating a process for constructing a hash table when a shared page is added.
6 is a flowchart illustrating a process for constructing a hash table when page sharing is released.
7 is a flowchart illustrating an example of configuring a hash table based on provided hints.
8 is a flow chart for explaining the experimental results of measuring the sharing between the virtual machine internal sharing and the virtual machine according to an embodiment of the present invention.
9 is a flowchart for explaining a memory sharing pattern according to an operating system of a virtual machine.
10 is a flow chart for explaining a comparison result of the prior art and an embodiment of the present invention when the virtual machine needs to be migrated.
11 is a block diagram illustrating a configuration of a memory sharing rate measuring apparatus according to an embodiment of the present invention.

The present invention can be applied to various changes and can have various embodiments, and specific embodiments will be illustrated in the drawings and described in detail.

However, this is not intended to limit the present invention to specific embodiments, and should be understood to include all modifications, equivalents, and substitutes included in the spirit and scope of the present invention.

Terms such as first and second may be used to describe various components, but the components should not be limited by the terms. The terms are used only for the purpose of distinguishing one component from other components. For example, the first component may be referred to as a second component without departing from the scope of the present invention, and similarly, the second component may be referred to as a first component. The term and/or includes a combination of a plurality of related described items or any one of a plurality of related described items.

When an element is said to be "connected" or "connected" to another component, it is understood that other components may be directly connected or connected to the other component, but other components may exist in the middle. It should be. On the other hand, when a component is said to be "directly connected" or "directly connected" to another component, it should be understood that no other component exists in the middle.

The terms used in this application are only used to describe specific embodiments, and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. In this application, the terms "include" or "have" are intended to indicate the presence of features, numbers, steps, actions, components, parts or combinations thereof described in the specification, but one or more other features. It should be understood that the existence or addition possibilities of fields or numbers, steps, operations, components, parts or combinations thereof are not excluded in advance.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by a person skilled in the art to which the present invention pertains. Terms, such as those defined in a commonly used dictionary, should be interpreted as having meanings consistent with meanings in the context of related technologies, and should not be interpreted as ideal or excessively formal meanings unless explicitly defined in the present application. Does not.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. In order to facilitate the overall understanding in describing the present invention, the same reference numerals are used for the same components in the drawings, and duplicate descriptions for the same components are omitted.

1 is a view for explaining a KSM in a mobile device to which a general virtualization environment is applied.

As shown in FIG. 1, the mobile device 100 includes a host (host 110), a hypervisor (Hypervisor) 120, and at least one virtual machine (131, 132, 133) in a virtualized environment. Here, the mobile device 100 to which the virtualization environment is applied is not limited to a specific device. At least one virtual machine (131, 132, 133) is a kernel-based virtual machine (Kernel-based Virtual Machine), virtual machine 1 (VM1, 131), virtual machine 2 (VM2, 132), and virtual machine 3 ( VM3, 133). The hypervisor 120 may include a kernel samepage merging (KSM) 121.

As described above, the Linux kernel supports kernel samepage merging (KSM) from version 2.6.32, and KSM (121) removes duplicate pages in a content-based page sharing (CBPS) method to greatly increase memory efficiency in a virtualized environment. Can be increased. However, the KSM 121 provides only the total number of pages shared in the entire system, and does not distinguish between internal sharing of the virtual machine and sharing between the virtual machines. As such, it is not possible to classify pages between virtual machines.

2 is a view for explaining a KSM according to an embodiment of the present invention.

As shown in FIG. 2, the host 210 of the mobile device 200 according to an embodiment of the present invention tracks pages shared by the KSM 221 according to an embodiment of the present invention, and each virtual machine You can check the memory sharing rate of. As an example, the host 210 may include a memory sharing rate measurement device for measuring the memory sharing rate of each virtual machine VM1 231, VM2 232, and VM3 233. Figure 2 shows an embodiment of the present invention. Embodiments of the present invention are not limited to including a specific component, such as including a hypervisor 220, or applied to a specific device, such as mobile device 200.

The KSM 221 tracks a stable tree used to manage the shared page, and provides a hint for distinguishing the virtual machine using the shared page. Here, the hint may be referred to as information on which the sharing page is changed, that is, sharing change information. The KSM 221 leaves a hint in the system when a new page is added to the share and when an existing shared page is released from the share. In addition, the KSM 221 may configure a double hash table based on the provided hint, and cumulatively update the number of virtual machines using the shared page for each shared page.

3 is a view for explaining a stable tree for storing a shared page used in an embodiment of the present invention.

KSM is a Linux kernel module that allows you to use memory more efficiently by sharing duplicate anonymous pages that exist between multiple processes. The KSM module manages pages to be merged through two red-black trees: a stable tree (300) and an unstable tree. Among them, the shared page is stored in the stable tree 300, and the unshared page is managed in the unstable tree.

In an embodiment of the present invention, each node of the stable tree 300 may be tracked to provide a hint 313 to the system. When a new page is inserted into the stable tree 300, the new page participates in sharing, and when the page is deleted from the stable tree 300, it can be seen that the sharing of the shared page is released. As an example, the node 310 of FIG. 3 is inserted with a shared page 311 in advance. At this time, new sharing pages (Sharing pages 312) may be inserted. Accordingly, whenever a page is added or deleted in the stable tree 300, a hint 313 is provided and tracked to construct a hash table. At this time, the hint 313 includes page information about a page to be added or deleted, and process information of a process using the page. Since this method uses KSM's red black tree structure, it is possible to measure the share by utilizing an existing scan without additional scan overhead.

4 is a flowchart illustrating a method for measuring a memory sharing rate according to an embodiment of the present invention.

In step S101, the memory sharing rate measuring apparatus checks whether a sharing page shared by at least one virtual machine is changed.

In step S102, when the sharing page shared by the at least one virtual machine is changed, the memory sharing rate measuring apparatus generates sharing change information for the changed sharing page. According to various embodiments of the present disclosure, the memory sharing rate measuring apparatus may generate sharing change information using page information for the changed shared page and process information of a process using the changed shared page. According to various embodiments of the present disclosure, when a shared page is changed in a node of a stable tree in which a shared page shared by at least one virtual machine is stored, the memory sharing rate measuring apparatus may generate sharing change information for the changed shared page. According to various embodiments of the present disclosure, when a new sharing page shared by at least one virtual machine is added or a sharing page being shared in advance is unshared, the memory sharing rate measuring device shares each of the added sharing page or the released sharing page. Each change information can be generated.

In step S103, the memory sharing rate measuring apparatus generates a hash table based on the sharing change information. According to various embodiments of the present disclosure, the apparatus for measuring a memory sharing rate may generate a double hash table having a hash key for each of the frame number of the shared page and the identification information of the virtual machine based on the generated sharing change information.

In step S104, the memory sharing rate measuring apparatus may track the virtual machine using the shared page using the hash table.

In step S105, the memory sharing rate measuring apparatus measures the memory sharing rate of the virtual machine based on the tracking result. According to various embodiments of the present disclosure, the memory sharing rate measurement device is configured to measure a memory sharing rate used by the virtual machine by dividing it into a virtual machine internal sharing (self-sharing) and a virtual machine sharing (inter-sharing) based on the tracking result. Can. According to various embodiments of the present disclosure, the memory sharing ratio measurement apparatus cumulatively updates the number of virtual machines using the changed shared page whenever a shared page is changed in a node of the stable tree to measure the memory sharing ratio used by the virtual machine. Can.

Meanwhile, according to various embodiments of the present disclosure, the memory sharing rate measuring apparatus may terminate the virtual machine in which the memory sharing rate measured based on the measured memory sharing rate is less than a preset sharing rate.

According to various embodiments of the present disclosure, the memory sharing rate measuring apparatus may adjoin a virtual machine sharing the same page based on the measured memory sharing rate.

According to various embodiments of the present disclosure, the memory sharing ratio measurement apparatus may select a virtual machine to which the virtual machine having the lowest memory sharing ratio is to be migrated based on the measured memory sharing ratio.

Hereinafter, a process for constructing a hash table will be described with reference to FIGS. 5 and 6.

5 is a flowchart illustrating a process for constructing a hash table when a shared page is added.

In step S201, the memory sharing ratio measurement device confirms that a new shared page is added to the stable tree.

In step S202, the memory sharing ratio measurement device checks whether an element whose key is PFN is searched.

In step S203, when the memory sharing rate measuring apparatus searches for an element using PFN as a key in a hash table, a hash entry using PID as a key is searched in an internal hash table.

In step S204, the memory sharing rate measuring apparatus increases the number of virtual machines using the shared page.

On the other hand, in step S205, the memory sharing rate measuring apparatus adds a new element whose key is PFN to the hash table if the element whose key is PFN is not found in the hash table.

6 is a flowchart illustrating a process for constructing a hash table when page sharing is released.

In step S301, the memory sharing rate measuring device confirms that the shared page is deleted from the node of the stable tree.

In step S302, the memory sharing rate measuring apparatus checks whether an element whose key is PFN is searched. Here, the memory sharing rate measuring apparatus ends the process for constructing a hash table if an element whose PFN is a key is not searched in the hash table.

In step S303, when the memory sharing rate measuring apparatus searches for a PFN-keyed element in a hash table, a PID-keyed hash entry is searched for in an internal hash table.

In step S304, the memory sharing ratio measuring apparatus reduces the number of virtual machines using the shared page.

In step S305, the memory sharing ratio measurement device checks whether the number of virtual machines using the shared page is all zero. Here, if the number of virtual machines using the shared page is not 0, the memory sharing rate measuring apparatus ends the process for constructing the hash table.

In step S306, if the number of virtual machines using the shared page is 0, the memory sharing rate measuring apparatus deletes the element from the hash table.

Through this process, the memory sharing rate measurement device can track the shared page used by a plurality of virtual machines in real time. In addition, the memory sharing rate measurement apparatus can measure the internal virtual machine of each virtual machine and the virtual machine-to-virtual machine share between virtual machines without additional scan overhead.

7 is a flowchart illustrating an example of configuring a hash table based on provided hints.

The memory sharing rate measuring device configures a hash table based on the provided hint to track the virtual machines using each shared page in real time. The hash table consists of a double hash table that has a page frame number (PFN) indicating a page frame number as a hash key, and internally has a PID (Process ID) of the virtual machine as a key. . For example, the PID of a virtual machine consists of numbers such as 2066 and 1244. The virtual machines VM1, VM2, and VM3 described while describing one embodiment of the present invention are given names to each virtual machine for easy understanding. PID can be a number that does not exceed a maximum of 32,768, such as 1244 or 2066 for 32-bit machines. The hash table includes the number of shared pages according to the PID of each virtual machine based on the PFN. The memory sharing rate measuring device updates and manages the hash table in real time whenever a hint is provided from KSM.

8 is a flow chart for explaining the experimental results of measuring the sharing between the virtual machine internal sharing and the virtual machine according to an embodiment of the present invention.

Using one embodiment of the present invention, the internal sharing of virtual machines and the sharing between virtual machines are measured in real time in various scenarios. In an experiment according to an embodiment of the present invention, after starting three virtual machines at the same time, running a desktop application, decompressing the kernel source file, and proceeding with the scenario of executing kernel compilation. The three virtual machines consisted of Ubuntu 12.04, Ubuntu 10.10, and Ubuntu 10.04, respectively, and allocated 2 GB of memory.

As shown in FIG. 8, the internal sharing of the virtual machines of the three virtual machines VM1, VM2, and VM3 may be measured through an embodiment of the present invention, respectively. Virtual machines 1 and 2 (VM 1&2), virtual machines 2 and 3 (VM 2&3), virtual machines 1 and 3 (VM 1&3), and virtual machines 1,2 and 3 (VM 1&2&3) share virtual machines in real time, respectively Can be measured. Virtual machine 1 (VM1) is virtual machine 2 (VM2), 3 (VM3) and the main version of the operating system is different, so it is hard to achieve sharing between virtual machines. On the other hand, virtual machines 2 (VM2) and 3 (VM3) have 51 MB of sharing between virtual machines when the application is not running anything. In addition, the virtual machines 2 (VM2) and 3 (VM3) have a share between virtual machines of up to 514 MB when decompression (Untar) is performed. When the virtual machines 2 (VM2) and 3 (VM3) did kernel compile, it was measured that they had a share between the virtual machines of up to 141 MB.

9 is a flow chart for explaining a memory sharing pattern according to the operating system of the virtual machine.

When such a real-time measurement is used, a memory sharing pattern according to the operating system of the virtual machine can be analyzed as shown in the table in FIG. 9.

Based on this, homogeneous operating systems that share large amounts of virtual machines can be placed on the same host to increase memory efficiency. As an example, virtual machines 2 (VM2) and 3 (VM3) using the same operating systems such as Ubuntu 10.04 and Ubuntu 10.10 have a 51 MB sharing rate between virtual machines, so placing them on the same host can increase memory efficiency. . On the other hand, since the virtual machine 1 (VM1) has a sharing rate of 0.1 MB with the virtual machine 2 (VM2), and also has a sharing rate of 0.1 MB with the virtual machine 3 (VM3), it is preferable to place it on another host.

10 is a flow chart for explaining the result of comparison between the prior art and an embodiment of the present invention when the virtual machine needs to be migrated.

When the virtual machine needs to be migrated to secure the memory of the host, the method for measuring the memory sharing rate according to an embodiment of the present invention can more accurately calculate the predictable secured memory. This allows the host to accurately select the virtual machine to migrate.

As illustrated in FIG. 10, in a situation in which the internal sharing of the virtual machines and the sharing between the virtual machines are not known, the virtual machines to be migrated are selected based on the size of the memory used by each virtual machine. Therefore, we will decide to migrate Virtual Machine 2 (VM2) for Ubuntu 10.10, which uses the most memory.

However, if the memory sharing is measured by dividing the internal sharing of the virtual machine and the sharing between the virtual machines, the virtual machine 2 (VM2) using Ubuntu 10.10 forms a large share with the virtual machine 3 (VM3) using Ubuntu 10.04. . Therefore, it is more effective to migrate the virtual machine 1 (VM1) using Ubuntu 12.04.

11 is a block diagram for explaining the configuration of a memory sharing rate measuring apparatus according to an embodiment of the present invention.

As illustrated in FIG. 11, the apparatus 10 for measuring a memory sharing rate according to an embodiment of the present invention includes a memory 11 and a processor 12. However, not all of the illustrated components are essential components. It may be implemented by more components than the illustrated components, or may be implemented by fewer components.

Hereinafter, a specific configuration and operation of each component of the memory sharing rate measuring apparatus 10 of FIG. 11 will be described.

The memory 11 stores a shared page shared by at least one virtual machine.

The processor 12 is connected to the memory 11. The processor 12 can execute a host for at least one virtual machine.

When the sharing page shared by at least one virtual machine is changed, the processor 12 generates sharing change information for the changed sharing page, and generates a hash table based on the generated sharing change information. , Track the virtual machine using the changed shared page by using the generated hash table, and measure the memory sharing rate used by the virtual machine based on the tracked virtual machine.

According to various embodiments, the processor 12 may generate the sharing change information using page information for the changed shared page and process information of a process using the changed shared page.

According to various embodiments of the present disclosure, when the shared page is changed in a node of the stable tree in which the shared page shared by at least one virtual machine is stored, the processor 12 may generate sharing change information for the changed shared page.

According to various embodiments of the present disclosure, when a new shared page shared by at least one virtual machine is added or a shared page that is being pre-shared is unshared, the processor 12 may add the shared page or each of the released shared pages. Each share change information can be generated.

According to various embodiments of the present disclosure, the processor 12 may generate a double hash table having a hash key for each of the frame number of the shared page and the identification information of the virtual machine, based on the generated share change information.

According to various embodiments, the processor 12 may measure a memory sharing rate of the virtual machine by dividing it into a virtual machine internal sharing (Self-sharing) and a virtual machine sharing (Inter-sharing) based on the tracked virtual machine. You can.

According to various embodiments of the present disclosure, the processor 12 may cumulatively update the number of virtual machines using the changed shared page whenever a shared page is changed in a stable tree node to measure the memory sharing ratio of the virtual machine. .

According to various embodiments of the present disclosure, the processor 12 may terminate the virtual machine in which the measured memory sharing rate is less than a preset sharing rate based on the measured memory sharing rate.

According to various embodiments of the present disclosure, the processor 12 may adjoin a virtual machine sharing the same page based on the measured memory sharing rate.

According to various embodiments, the processor 12 may select a virtual machine to which the virtual machine having the lowest memory sharing ratio is to be migrated based on the measured memory sharing ratio.

The memory sharing rate measurement method according to the above-described embodiments of the present invention may be implemented as computer readable codes on a computer readable recording medium. The method for measuring a memory sharing rate according to embodiments of the present invention may be implemented in a form of program instructions that can be executed through various computer means and may be recorded in a computer-readable recording medium.

In a recording medium readable by a computer recording a program for executing a method for measuring a memory sharing rate according to embodiments of the present invention in a computer, when the sharing page shared by at least one virtual machine is changed, the changed sharing page is Generating sharing change information for the generated data, generating a hash table based on the generated shared change information, and tracking a virtual machine using the changed shared page using the generated hash table. , And a computer readable recording medium recording a program for executing a step of measuring a memory sharing rate used by the virtual machine based on the tracked virtual machine.

Computer-readable recording media includes all kinds of recording media storing data that can be read by a computer system. For example, there may be a read only memory (ROM), a random access memory (RAM), a magnetic tape, a magnetic disk, a flash memory, and an optical data storage device. In addition, the computer-readable recording medium may be distributed over computer systems connected through a computer communication network, and stored and executed as code readable in a distributed manner.

Specifically, the described features can be implemented in digital electronic circuitry, or computer hardware, firmware, or combinations thereof. Features can be implemented in a computer program product implemented in storage in a machine-readable storage device, eg, for execution by a programmable processor. And the features can be performed by a programmable processor executing a program of instructions for performing the functions of the described embodiments by operating on input data and generating output. The described features include at least one programmable processor, at least one input device, and at least one output coupled to receive data and directives from a data storage system and to transmit data and directives to the data storage system. It can be executed in one or more computer programs that can be executed on a programmable system including a device. A computer program includes a set of directives that can be used directly or indirectly within a computer to perform a specific action on a given result. A computer program is written in any form of programming language, including compiled or interpreted languages, and is included as a module, element, subroutine, or other unit suitable for use in other computer environments, or as a standalone program. Can be used in any form.

Suitable processors for the execution of the program of instructions include, for example, both general purpose and special purpose microprocessors, and either a single processor or multiple processors of other types of computers. Also suitable for implementing computer program instructions and data embodying the described features are storage devices suitable for use as magnetic devices such as semiconductor memory devices such as EPROM, EEPROM, and flash memory devices, internal hard disks and removable disks. Devices, magneto-optical disks and all forms of non-volatile memory, including CD-ROM and DVD-ROM disks. The processor and memory may be integrated within application-specific integrated circuits (ASICs) or added by ASICs.

The present invention described above has been described based on a series of functional blocks, but is not limited by the above-described embodiments and the accompanying drawings, and various substitutions, modifications, and changes without departing from the spirit of the present invention. It will be apparent to those skilled in the art that the present invention is possible.

Combinations of the above-described embodiments are not limited to the above-described embodiments, and various forms of combinations may be provided as well as the above-described embodiments according to implementation and/or needs.

In the above-described embodiments, the methods are described based on a flowchart as a series of steps or blocks, but the present invention is not limited to the order of steps, and some steps may occur in a different order than the steps described above or simultaneously. have. In addition, those skilled in the art may recognize that the steps in the flowchart are not exclusive, other steps may be included, or one or more steps in the flowchart may be deleted without affecting the scope of the present invention. You will understand.

The foregoing embodiments include examples of various aspects. It is not possible to describe all possible combinations to represent various aspects, but a person skilled in the art will recognize that other combinations are possible. Accordingly, the present invention will be said to include all other replacements, modifications and changes that fall within the scope of the following claims.

100, 200: mobile device
110, 210: host
120, 220: hypervisor
121, 221: KSM
131, 231: virtual machine 1
132, 232: virtual machine 2
133, 233: virtual machine 3
10: memory sharing rate measuring device
11: Memory
12: Processor

Claims (21)

In the memory sharing rate measurement method performed by the virtualization device,
If the sharing page shared by at least one virtual machine is changed, generating sharing change information for the changed sharing page;
Generating a hash table based on the generated sharing change information;
Tracking a virtual machine using the changed shared page using the generated hash table; And
And measuring a memory sharing rate used by the virtual machine based on the tracked virtual machine. According to claim 1,
The step of generating the sharing change information,
A memory sharing rate measurement method for generating the sharing change information using page information on the changed shared page and process information of a process using the changed shared page. According to claim 1,
The step of generating the sharing change information,
A method for measuring a memory sharing rate that generates sharing change information for the changed shared page when a shared page is changed in a node of the stable tree in which the shared page shared by at least one virtual machine is stored. According to claim 1,
The step of generating the sharing change information,
When a new sharing page shared by at least one virtual machine is added or a sharing page being shared in advance is unshared, a memory sharing rate measurement for generating sharing change information for each of the added sharing page or each of the released sharing pages is measured. Way. According to claim 1,
The step of generating the hash table,
A memory sharing rate measurement method for generating a double hash table having a hash key for each of the shared page frame number and the virtual machine identification information based on the generated sharing change information. According to claim 1,
Measuring the memory sharing rate,
A memory sharing rate measurement method for measuring a memory sharing rate used by a virtual machine by dividing it into a virtual machine internal sharing (Self-sharing) and a sharing between virtual machines (Inter-sharing) based on the tracked virtual machine. According to claim 1,
Measuring the memory sharing rate,
A memory sharing rate measurement method for measuring a memory sharing rate used by a virtual machine by accumulatively updating the number of virtual machines using the changed shared page whenever a shared page is changed in a node of the stable tree. According to claim 1,
And terminating the virtual machine in which the measured memory sharing rate is less than a preset sharing rate based on the measured memory sharing rate. According to claim 1,
A method of measuring a memory sharing rate further comprising adjoining a virtual machine sharing the same page based on the measured memory sharing rate. According to claim 1,
And selecting a virtual machine to migrate the virtual machine having the lowest memory sharing ratio based on the measured memory sharing ratio. A memory for storing a shared page shared by at least one virtual machine; And
A processor connected to the memory,
When the shared page shared by at least one virtual machine is changed, the processor generates sharing change information for the changed shared page,
A hash table is generated based on the generated sharing change information,
The virtual machine using the changed shared page is tracked using the generated hash table,
A memory sharing rate measuring device that measures a memory sharing rate used by the virtual machine based on the tracked virtual machine. The method of claim 11,
The processor,
A memory sharing rate measurement device that generates the sharing change information by using page information for the changed shared page and process information of a process using the changed shared page. The method of claim 11,
The processor,
A memory sharing rate measuring device that generates sharing change information for the changed shared page when a shared page is changed in a node of the stable tree in which the shared page shared by at least one virtual machine is stored. The method of claim 11,
The processor,
When a new sharing page shared by at least one virtual machine is added or a sharing page being shared in advance is unshared, a memory sharing rate measurement for generating sharing change information for each of the added sharing page or each of the released sharing pages is measured. Device. The method of claim 11,
The processor,
A memory sharing rate measurement device for generating a double hash table having a hash key for each frame number of a shared page and identification information of a virtual machine based on the generated sharing change information. The method of claim 11,
The processor,
A memory sharing rate measurement device that measures a memory sharing rate of a virtual machine by dividing it into a virtual machine internal sharing (Self-sharing) and a sharing between virtual machines (Inter-sharing) based on the tracked virtual machine. The method of claim 11,
The processor,
A memory sharing rate measuring device that measures the memory sharing rate of a virtual machine by accumulatively updating the number of virtual machines using the changed shared page whenever a shared page is changed in a node of the stable tree. The method of claim 11,
The processor,
A memory sharing rate measuring apparatus for terminating a virtual machine in which the measured memory sharing rate is less than a preset sharing rate based on the measured memory sharing rate. The method of claim 11,
The processor,
A memory sharing rate measuring device adjacent to a virtual machine sharing the same page based on the measured memory sharing rate. The method of claim 11,
The processor,
A memory sharing rate measuring device for selecting a virtual machine to migrate a virtual machine having the lowest memory sharing rate based on the measured memory sharing rate. A computer-readable recording medium having a program for executing a memory sharing rate measurement method in a computer,
If the sharing page shared by at least one virtual machine is changed, generating sharing change information for the changed sharing page;
Generating a hash table based on the generated sharing change information;
Tracking a virtual machine using the changed shared page using the generated hash table; And
A computer-readable recording medium recording a program for executing a step of measuring a memory sharing rate used by a virtual machine based on the tracked virtual machine.

Images