KR20100138689A - Management server and method for providing cloud computing services - Google Patents

Abstract

Disclosed are a management server and method for providing a cloud computing service for quickly and reasonably providing a cloud computing service suitable for a personal user. According to an aspect, a management server managing a cloud server that provides a cloud computing service provides a client with a virtual device for operating on a virtual machine and multiplexes the virtual machine as a computing resource, and provides a demand for the computing resource in advance. It is configured to provide a fast service in anticipation.

Description

Management server and method for providing cloud computing service

One or more aspects relate to a cloud computing system, and more particularly to a system for efficiently providing resources of a cloud infrastructure.

Cloud computing refers to internet-based (cloud) -based computing technology. In a computer network diagram, the Internet is represented by a cloud, which represents a complex and hidden infrastructure. Cloud computing is a computing style in which IT-related functions are provided in the form of services. Users can access services from the Internet without having expertise or control over the technology infrastructure they support. That is, the user may be provided with the computing resources he / she wants anytime, anywhere through the Internet using cloud computing. Computing resources are typically managed by separate resource providers, such as large data centers, whose targets may be hardware resources such as CPU capabilities, memory, storage, or development platforms, applications, and the like. A service provided by a resource provider to use a computing capability using a computing resource in a terminal is called a cloud computing service.

It provides a management server and method for providing cloud computing services to provide cloud computing services suitable for personal users quickly and reasonably.

According to an aspect, a management server that manages one or more servers providing cloud computing services may include a virtual machine manager, a virtual device manager, and a request handler. The virtual machine manager deploys at least one virtual machine to one or more servers in preparation for a client's computing service request. The virtual device manager deploys at least one virtual device on the deployed virtual machine in preparation for the client's computing service request. The request handler processes the client's computing service request and provides the deployed virtual machine and virtual device to the client.

The management server includes a resource pool that includes a management list for managing all virtual machines and virtual devices running on one or more servers, the resource pool determining whether to provide a virtual device in response to a computing service request. Is used. The management list includes at least one of state information, performance information, accessor information, and computing service information of the virtual machine and the virtual device.

The management server may further include a predictor that predicts the type and number of virtual devices to operate in one or more servers. The request handler controls the virtual machine manager and the virtual device manager to secure the virtual machine manager and the virtual machine manager as many as the number of virtual machines for providing the predicted virtual device before the client's request is received, and request the client's computing service. If there is, it is possible to provide a secured virtual device.

The predictor predicts the minimum number of virtual machines required to secure the predicted number and type of virtual devices.

The prediction unit includes a log information storage unit, a log information collection unit, and an analysis unit. The log information storage unit accumulates and stores the computing service log information. The log information collecting unit receives the computing service request information of the client and collects and stores log information generated from the computing service request information in the log information storage unit. The analyzer predicts the type and number of virtual devices to operate in one or more servers by using the information stored in the log information storage unit.

The log information may include virtual device information requested by a plurality of clients, computing service usage time, and computing service request time.

The management server stores user-specific data generated and stored for each computing service used by the client in a separate storage, and when the client's computing service request requests a previously used computing service, the management server responds to the computing service request. Restore to the virtual device, and provides the restored virtual device to the client.

According to another aspect, a method of providing a cloud computing service in a server farm includes: receiving a cloud computing service request from a client, and computing a computing service request using at least one prepared virtual device operating on one or more servers It includes an operation to perform an operation. The virtual device operates on the virtual machine and is configured to multiplex the virtual machine.

According to an embodiment of the present disclosure, a virtual device generated by emulating a virtual machine suitable for a CE terminal for a client's computing service request may be provided to provide a fast and low-cost cloud computing service suitable for a CE terminal. In addition, the management server managing the servers in the server farm can respond quickly to the client's computing service request by analyzing the log information of the clients and predicting the cloud computing resources to be used.

Hereinafter, an embodiment of the present invention will be described in detail with reference to the accompanying drawings. In the following description of the present invention, if it is determined that detailed descriptions of related well-known functions or configurations may unnecessarily obscure the subject matter of the present invention, the detailed description thereof will be omitted. In addition, terms to be described below are terms defined in consideration of functions in the present invention, which may vary according to intention or custom of a user or an operator. Therefore, the definition should be based on the contents throughout this specification.

1 is a diagram illustrating an example of a system structure for providing a cloud computing service.

The system for providing a cloud computing service according to an exemplary embodiment has a structure in which a client 100, a management server 200, and a server farm 300 are connected to a network 10.

The client 110 may be various electronic devices capable of network connection, such as a mobile phone, a digital television, a set top box, an MP3 player, a PMP player, a laptop, and the like.

The management server 200 serves as a kind of gateway or hub in the server farm 300 to manage resources of one or more servers 310, 320, and 330, and the one or more servers 310, 320, and 330 may store storage 340. Control to operate the computing service using the necessary resource information. In FIG. 1, the management server 200 is illustrated as being separately located outside the server farm 300, but the management server 200 may be located inside the server farm 300.

Server farm 300 refers to a group of servers centralized into multiple computers. The server farm 300 may include one or more servers 310, 320, 330, and storage 340 that perform operations for providing computing services to the client 100. There is no limit to the number of one or more servers, and each server may individually have or share a separate operating system.

If cloud computing targets expand from business to business (B2B) to business to customer (B2C), individual users tend to be sensitive to the response rate to computing service requests, so the computing service response rate should be faster and the cost of computing services available This should be reasonable. Typically, in cloud computing services targeting B2B, service providers check the services available at the time of a computing service request, and if there are no virtual machines required for computing services, start up new virtual machines. A process of registering a running service to a list of running computing services is performed. However, it is not suitable for use by individual users because of the long response time to start up a new virtual machine and provide the computing service required by the client.

 The cloud computing service providing system according to an exemplary embodiment operates to provide a cloud computing service at a high speed at a reasonable cost even when the client 100 is not only an enterprise but also an individual user. To this end, the cloud computing service according to an exemplary embodiment operates on a virtual machine and provides a virtual device, which is generated by emulating a virtual machine, to the client 100 as a computing resource.

Virtual machines are being provided to enterprise cloud computing services as virtual machines that multiplex the physical hardware to enable a plurality of different operating systems to run on a single piece of hardware. In contrast, the virtual device has a form optimized for CE (Customer Electronics) mainly used by a personal user, and may be generated by emulating or simulating a virtual machine to multiplex one virtual machine. Virtual devices include an operating system, development platform, and applications for CE. In addition, a plurality of application programs may be configured to operate on the virtual device like a conventional virtual machine. Thus, on the client 100 side, the virtual device is seen as operating as a computing service.

Referring to FIG. 1, server 1 310 includes virtual device 1 313 and virtual device 2 314 that operate on virtual machine 1 312 and virtual machine 1 312 on hardware 1 311. do. In server 2 320, virtual machine 2 322 and virtual machine 3 323 run on hardware 2 321, virtual device 1 324 runs on virtual machine 2 322, and the virtual machine Virtual device 2 325 is driven on 3 323. In server 3 330, virtual machine 4 332 is driven on hardware 3 331, and virtual device 1 333 to virtual device n 334 are driven on virtual machine 4 332. As such, a cloud computing service having a concept of providing a client with a virtual device defined as described above by a user's request may be referred to as a device as a service (DaaS).

The management server 200 receives a cloud computing service request from the client 100 and uses one or more servers 310, 320, at least one previously prepared virtual device operating in one or more servers 310, 320, 330. The 330 manages one or more servers 310, 320, and 330 to perform a computing operation according to a computing service request. In detail, the management server 200 analyzes the computing service usage information of a plurality of clients, including the client 100 using the server farm 300, and computes the computing resources that are driven in the server farm 300, that is, the virtual device and the virtual. The demand of the machine may be predicted, and computing resources according to the predicted demand may be secured as available resources to the servers 310, 320, and 330 of the server farm 300 in advance.

For example, around 5 pm, 1000 clients can be expected to use Google's Android platform as a virtual device. Through this, when the client 100 requests a computing service, the management server 200 may quickly provide a service by preparing a predicted service in advance. As such, by predicting the demand of the virtual device and the virtual machine, the cost is reduced in addition to the fast response speed.

Cloud computing uses a pay-per-use model that pays for use, so you can save money if you can perform the same level of service while using the least resources. For example, if you can perform up to five virtual devices on one virtual machine, and the number of requests for the current predicted virtual device is 100, then having 20 virtual machine instances is the most efficient. to be.

2 is a diagram illustrating an example of a configuration of a management server managing cloud resources.

Referring to FIG. 2, the management server 200 may include a request handler 210, a predictor 220, a VM manager 230, a virtual machine manager, a VD manager 240, and a resource pool. 250).

The request handler 210 processes the computing service request of the client 100 to quickly provide the requested computing service so that the predictor 220, the VM manager 230, the VD manager 240, and the resource pool 250 are provided. Control the operation of

The request handler 210 requests a computing service using a resource pool 250 that includes a management list for managing all virtual machines and virtual devices running on the servers 310, 320, 330 of the server farm 300. It may be determined whether to provide a virtual device according to. According to the determination result, the request handler 210 performs an operation for providing the virtual device to the client 100 according to the computing service request.

The predictor 220 predicts the type and number of virtual devices that will operate on one or more servers 310, 320, and 330. The prediction unit 220 may acquire a virtual machine or a virtual device by analyzing information of computing service request records, patterns, usage statuses, etc. of the clients.

The prediction unit 220 may predict the minimum number of virtual machines required to secure the predicted number and type of virtual devices in order to increase the efficiency of resource usage. The request handler 210 may include the VM manager 230 to obtain as many virtual machines (or virtual machine instances) as the number of virtual machines for providing the predicted virtual device and the predicted virtual device before the request of the client is received. The VD manager 240 is controlled. The request handler 210 may provide a virtual device secured in advance when a client request is made.

The VM manager 230 performs operations related to the virtual machine, for example, loading the virtual machine image, booting the virtual machine image, shutting down the virtual machine instance, and the like. A virtual machine instance refers to a virtual machine that is in a launched state with the virtual machine available on the server. The VM manager 230 may deploy, that is, boot and load at least one virtual machine into at least one server 310, 320, or 330 in preparation for a computing service request of the client 100. The VM manager 230 may deploy the virtual machine required for the prediction result to an available server of the server farm 300.

The VD manager 240 performs operations related to the virtual device, for example, loading the virtual device image, booting the virtual device image, shutting down the virtual device instance, and the like. A virtual device instance refers to a virtual device in a state in which the virtual device is launched as available on the server. The VD manager 240 may deploy at least one virtual device on the deployed virtual machine in preparation for the computing service request of the client 100. The VD manager 240 may deploy the required virtual device to an available server of the server farm 300 according to the prediction result of the predictor 220.

The resource pool 250 stores and manages a management list for managing all virtual machines and virtual devices running on one or more servers 310, 320, 330 of the server farm 300. The management list may include state information, performance information, accessor information, computing service information, etc. of the virtual machine and the virtual device.

The storage 340 may store an image 341 of virtual machines, an image 342 of virtual devices, and user specific data 343 as file storage. Although FIG. 1 illustrates that the storage 340 is located inside the server farm 300 separately from the management server 200, the storage 340 may be located outside the server farm 300. It may also be configured to integrate with (200).

The virtual machine image 341 is an image used when running a virtual machine on a server. The virtual device image 342 is an image used when driving a virtual device on the server. The user-only data 343 refers to all data generated and modified by the client 100 after the virtual machine and the virtual device are driven at the request of the client 100.

The request handler 210 stores user-specific data 253 generated and stored for each computing service used by the client 100 in the storage 340. When the computing service request of the client 100 is a computing service request previously used, the stored user-only data is restored to the virtual device corresponding to the computing service request, and the restored virtual device is provided to the client 100. As the user-only data is provided together with the computing service, the client 100 may be provided with the service in the state of the virtual device which has been recently used.

3 is a diagram illustrating an example of a configuration of a prediction unit included in the management server of FIG. 2.

The predictor 220 includes a log information collector 222, a log information storage 224, and an analyzer 224.

The log information collecting unit 222 receives the computing service request information of the client, generates log information from the computing service request information, and stores the generated log information in the log information storage unit 224. In detail, when the computing service request is received from the client 100, the log information collecting unit 222 receives the type of virtual device that the client wants to receive the computing service, the time of requesting the computing service, the computing service using time, and the client device information. Log information, including user information, is stored in the log information storage unit 224.

The log information storage unit 224 stores log information collected each time a computing service request is received by the log information collecting unit 222. Log information of a plurality of clients is accumulated and stored in the log information storage unit 224. Log information of the log information storage unit 224 may be managed for each client.

The analyzer 226 predicts the type and number of virtual devices to operate in one or more servers 310, 320, and 330 using the log information stored in the log information storage 224. The analyzer 226 may analyze the stored information by using a known statistical method or a pattern discovery method. If the type and number information of the virtual device is predicted, the number of required virtual machine instances may be calculated, and the predicted virtual device instance and the virtual machine instance may be secured in advance.

4 is a diagram illustrating an example of a method of providing a cloud computing service.

The management server 200 receives a computing service request from the client 100 (410).

Computing according to a computing service request by using a prepared virtual device operating in the server farm 300 by controlling the operation of one or more servers 310, 320, and 330 included in the server farm 300 by the management server 200. The operation is performed (420). In the server of the server farm 300, at least one virtual device may operate on one virtual machine that is driven, and the virtual device refers to information generated by emulating a virtual machine.

The management server 200 secures the virtual device and the virtual machine instance according to the type and number of the virtual devices and the number of the virtual machine instances predicted by the above-described method, so that the virtual machine is required in the computing service request of the client 100. It can respond immediately without taking time to load and boot, and by using a virtual device configured for an individual user, the client 100 can prevent the use of a lot of cloud resources unnecessarily, the client 100 Can lower the cost of using resources.

5 is a diagram illustrating an example of a computing service providing method.

2 and 5, the request handler 210 receives a computing service request of the client 100 (510). The computing service request of the client 100 may include information requesting a specific virtual device.

The request handler 210 determines whether there is an available virtual device by referring to the list managed in the resource pool 250 (512). If there is a virtual device available in the resource pool 250 as predicted by the prediction unit 220 according to the computing service request situation of the actual clients on the network (512), the request handler 210 is a service request in the resource pool 250 Obtain 514 the resulting virtual device. Obtaining a virtual device includes identifying an identifier of a virtual device currently available in the resource pool 250.

The request handler 210 checks whether the virtual device obtained using the virtual device identifier or the like is the virtual device previously used by the client 100 (516). When the obtained virtual device is a virtual device previously used by the client 100, a user of the client 100 generated by the client 100 using the virtual device previously from the storage 340 outside the management server 200. The dedicated data is loaded and restored or connected to the virtual device (518). After the resource allocation procedure of the request handler 210 is completed, the client 100 provides a computing service providing a computing result according to the request of the client 100 using the allocated computing resource (520).

On the other hand, if it is determined that there are no virtual devices available in the resource pool 250 (512), the request handler 210 refers to the management list managed in the resource pool 250, the virtual machine available to the resource pool 250 ( Or a virtual machine instance) (522). If there is no virtual device available (512), but it is determined that there is an available virtual machine in the resource pool 250 (522), the operation of installing the virtual device requested by the user in the available virtual machine is performed.

To this end, the request handler 210 obtains a virtual machine (524). Next, the request handler 210 controls the VD manager 240 to load the virtual device image corresponding to the service request of the client to the server obtained from the storage 340 (526). The VD manager 240 boots 528 a virtual device image loaded on the server. The request handler 210 registers booted virtual device information in the virtual device pool of the resource pool 250 (530). The operation then proceeds to operation 516, and then operations 518 and 520 are performed.

If it is determined that there are no virtual devices available in the resource pool 250 (512) and that there are no virtual machine instances available in the resource pool 250 (522), the request handler 210 is required to drive the virtual device. After installing the virtual machine, the client 100 performs an operation of installing the requested virtual device.

First, request handler 210 first controls VM manager 230 to load a virtual machine image from storage 340 to a given server in server farm 300 on which the virtual machine will operate for virtual machine instance creation ( 532). The VM manager 230 boots 534 the loaded virtual machine image. Next, the request handler 210 registers the virtual machine information corresponding to the virtual machine instance generated by booting the virtual machine image to the virtual machine pool of the resource pool 250 (536). When the virtual machine information is registered, the request handler 210 controls the VD manager 240 to load a virtual device image according to the client's computing service request on the registered virtual machine instance from the storage 340 (526), The VD manager 240 boots 528 the loaded virtual device image. Then, the request handler 210 registers the booted virtual device information in the virtual device pool of the resource pool 250 (530). The operation then proceeds to operation 516, and then operations 518 and 520 are performed.

6 is a diagram illustrating an example of a cloud resource prediction operation.

2, 3 and 6, when the client requests the DaaS service, the request handler 210 receives the computing service request, and transfers the received computing service request information to the log information collection unit 222. The log information collector 222 receives a computing service request (610). The log information collecting unit 222 collects log information from the computing service request information every time a computing service request is received from the request handler 210 and stores the collected log information in the log information storage unit 224 ( 620).

When the information is secured to a predetermined level or more, or the predetermined time, the analysis unit 226 analyzes the information stored in the log information storage unit 224 (620). The analyzer 226 may analyze the type and number of virtual devices to be secured at the present time. The analysis unit 226 predicts the minimum number of virtual machine instances that need to be launched in order to secure the predicted type and number of virtual devices based on the analyzed result (640).

The prediction result is transferred to the VM manager 230, and the VM manager 230 generates a minimum virtual machine instance according to the prediction result in advance (650).

In addition, the prediction result is transferred to the VD manager 240, and the VD manager 240 generates 660 virtual device instances in advance on the generated virtual machine instance in advance (660).

As such, the management server may prepare the virtual machines and the virtual devices that are expected to use by analyzing the log information of the accumulated client every hour or at a predetermined point in time, thus providing services on demand for the server farm. Minimize time to prepare. This provides a smoother service in a system that provides resources for server farms to individual users. In addition, by creating a virtual device using the resources of the server farm, it is possible to use a device that the user does not have. For example, a user with an Android-based cell phone can use a device that he doesn't have physically by using a server farm's resources to provide a Symbian-based virtual device.

One aspect of the present invention may be embodied as computer readable code on a computer readable recording medium. The code and code segments implementing the above program can be easily deduced by a computer programmer in the field. Computer-readable recording media include all kinds of recording devices that store data that can be read by a computer system. Examples of the computer-readable recording medium include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical disk, and the like. The computer-readable recording medium may also be distributed over a networked computer system and stored and executed in computer readable code in a distributed manner.

It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit or scope of the invention. Therefore, the scope of the present invention should not be limited to the above-described embodiments, but should be construed to include various embodiments within the scope of the claims.

1 is a diagram illustrating an example of a system structure for providing a cloud computing service.

2 is a diagram illustrating an example of a configuration of a management server managing cloud resources.

3 is a diagram illustrating an example of a configuration of a prediction unit included in the management server of FIG. 2.

4 is a diagram illustrating an example of a method of providing a cloud computing service.

5 is a diagram illustrating an example of a computing service providing method.

6 is a diagram illustrating an example of a cloud resource prediction operation.

Claims (17)

A management server that manages one or more servers that provide cloud computing services. A virtual machine manager for deploying at least one virtual machine to the one or more servers in preparation for the client's computing service request; A virtual device manager that deploys at least one virtual device on the deployed virtual machine in preparation for a computing service request of the client; And And a request handler that processes the client's computing service request and provides the deployed virtual machine and the virtual device to the client. The method of claim 1, The management server, A resource pool including a management list for managing all virtual machines and virtual devices running on the one or more servers, The resource pool is used to determine whether to provide a virtual device in response to the computing service request. The method of claim 2, The management list includes at least one of state information, performance information, accessor information, and computing service information of a virtual machine and a virtual device. The method of claim 1, The management server, The management server further comprises a prediction unit for predicting the type and number of the virtual device to operate in the one or more servers. The method of claim 4, wherein The request handler controls the virtual machine manager and the virtual device manager to secure the virtual machine as many as the number of virtual machines for providing the predicted virtual device and the predicted virtual device before the client request is received. And providing the secured virtual device when the client requests a computing service. The method of claim 4, wherein The predicting unit predicts the minimum number of virtual machines required to secure the predicted number and type of virtual devices. The method of claim 4, wherein The prediction unit, A log information storage unit for accumulating and storing log information about a computing service; A log information collecting unit configured to receive computing service request information of a client and store the log information generated from the computing service request information in the log information storage unit; And And an analyzer configured to predict the type and number of the virtual devices to operate in the one or more servers by using the information stored in the log information storage unit. The method of claim 7, wherein The log information includes virtual device information requested by a plurality of clients, computing service usage time, and computing service request time. The method of claim 1, The management server stores user-specific data generated and stored for each computing service used by a client in a separate storage, and when the computing service request of the client requests a computing service previously used, the stored user-only data is computed. A management server for restoring to a virtual device corresponding to a service request and providing the restored virtual device to the client. A method of providing cloud computing services in a server farm that includes one or more servers. Receiving a cloud computing service request from a client; And Performing a computing operation according to the computing service request by using at least one prepared virtual device operating in the one or more servers, The virtual device operating on a virtual machine and configured to multiplex the virtual machine. The method of claim 10, Determining whether a virtual device in response to the computing service request can be provided using a resource pool including a management list for managing all virtual machines and virtual devices running on the one or more servers. . The method of claim 11, The management list includes at least one of state information, performance information, accessor information, and computing service information of a virtual machine and a virtual device. The method of claim 10, Estimating the type and number of the virtual devices to operate in the server farm to prepare in advance at least one virtual device operating on the one or more servers; Estimating the number of virtual machines required according to the prediction result; Deploying the predicted number of virtual machines on the one or more servers; And Deploying the required virtual device on the deployed virtual machine according to the prediction result. The method of claim 13, Predicting the required number of virtual machines according to the prediction result, wherein the minimum number of virtual machines required to secure the predicted number and type of virtual devices is predicted. The method of claim 13, Predicting the type and number of the virtual device, Storing computing service log information of a plurality of clients in a log information storage unit; And Predicting the type and number of the virtual devices to operate in the one or more servers using the stored log information. The method of claim 15, The computing service log information includes requested virtual device information, computing service usage time, and computing service request time of a plurality of clients. The method of claim 10, Storing user-specific data generated for each computing service used by the client in a separate storage; Restoring the stored user-only data to the virtual device corresponding to the computing service request if the computing service request of the client is a request of a computing service previously used; And Providing the restored virtual device to the client.

Images