CN117793129B - A cloud computing network system and service method based on computing cluster - Google Patents

Abstract

The application provides a cloud computing network system and a service method based on a computing cluster. The cloud computing network system comprises a website service layer, a database layer and a server cluster, wherein the website service layer is used for receiving a reservation request of a user reservation target image, the database layer responds to the reservation request submitted by the user and increases reservation records associated with the reservation request, the server cluster is communicated with the database layer and a data storage system accessible by each user, the target image is started to be an example in a preset time period when the target image in the reservation records in the database layer is inquired to be in a first state, a writing catalog in the data storage system is mapped to be a first mounting disk, and the data catalog is mapped to be a second mounting disk. Therefore, a user can conveniently analyze and process the experimental data locally, the cross-regional processing of the experimental data is avoided, the working efficiency is greatly improved, and the data safety is ensured.

Description

Cloud computing network system and service method based on computing cluster

Technical Field

The application relates to the technical field of communication, in particular to a cloud computing network system and a service method based on a computing cluster.

Background

At present, the public service platform of data analysis is ubiquitous in institutions such as universities, scientific research institutions, laboratories and the like, experimenters need to reserve on the public service platform of data analysis in advance, experimental data to be processed needs to be carried to the public service platform of data analysis by utilizing a USB flash disk/a mobile hard disk and the like, moreover, the public service platform of data analysis has limited processing capacity, and only a few experimenters are allowed to use the public service platform of data analysis to conduct data analysis processing in the same time period, for example, one workstation can only process one analysis task for one student.

On the one hand, experimental data are copied to an instrument in a data analysis public service platform by adopting a USB flash disk/a mobile hard disk and the like, the USB port of the instrument is required to be opened, the USB flash disk possibly increases the data security risk, and if security accidents such as poisoning/data leakage/data locking and the like occur, the subsequent use of the instrument is greatly influenced. On the other hand, the experimenter needs to carry experimental data to achieve the purpose of processing the data by the data analysis public service platform, if the experimenter and the data analysis public service platform are located in different areas, the experimenter needs to process the experimental data in a cross-regional or cross-school area mode, so that the time of the experimenter is wasted greatly, and the working efficiency is reduced. In addition, in the same time period, the number of the experimenters who can carry out data processing on the data analysis public service platform is small, the period of waiting to process the experimental data of the experimenters is prolonged, and the working efficiency is reduced.

Disclosure of Invention

The present application has been made in view of the above-mentioned technical problems occurring in the prior art. The application aims to provide a cloud computing network system and a service method based on a computing cluster, which can enable a user to conveniently analyze and process experimental data locally, avoid cross-regional processing of the experimental data, greatly improve the working efficiency and ensure the data safety.

According to a first scheme of the application, a cloud computing network system based on a computing cluster is provided, the cloud computing network system comprises a website service layer, a database layer and a server cluster, a plurality of images are pre-configured in the server cluster, the website service layer is used for receiving a reservation request of a user reservation target image, the database layer responds to the reservation request submitted by a user, adds reservation records associated with the reservation request, sets the state of the target image in the reservation records to be a first state representing reserved and not started, the reservation records at least comprise the state and reservation time of the target image, the server cluster is communicated with the database layer and a data storage system accessible by each user, the data storage system is configured with a write directory and a data directory for each user, the target image is started to be an example in a preset time period before the reservation time is queried in the first state, the target image in the data storage system is set to be a first state, the target image in the reservation record is read from the first state, the first state is mapped to be a second state, and the second state is set to be a second state is a second state.

According to a second scheme of the application, the service method of the cloud computing network based on the computing cluster comprises the steps that a website service layer is used for receiving a reservation request of a target mirror image reserved by a user, a database layer responds to the reservation request submitted by the user, reservation records associated with the reservation request are added, the state of the target mirror image in the reservation records is set to be a first state representing reserved and not started, the reservation records at least comprise the state and reservation time of the target mirror image, a server cluster is used for starting the target mirror image as an example in a preset time period before the reservation time when the target mirror image in the reservation record in the database layer is in the first state, the first mounting disk is used for storing processed data, the server cluster and each user-accessible data storage system are communicated, the data storage system is provided with a writing directory and a data directory for each user, and the server cluster is used for enabling the second mounting disk to be mounted with the second mounting disk in response to the user-accessible data storage system to be a second mounting disk, and the second mounting disk can be processed based on the second data.

Compared with the prior art, the embodiment of the application has the beneficial effects that:

According to the cloud computing network system provided by the embodiment of the application, a plurality of images are pre-configured in the server cluster, a user can reserve a target image through a website service layer, and reserved relevant information is stored in a database layer. The server cluster can communicate with the database layer, periodically scans the database layer, starts the target image as an example in a preset time period before the reservation time when the reservation record in the database layer is in a first state, maps the writing catalog of the user in the data storage system to a first mounting disk of the target image, and maps the data catalog to a second mounting disk. Therefore, the user can analyze the experimental data locally through the target mirror image by using the data analysis public service platform which is far away from the user, and the experimental data analysis is not needed to be performed in a transregional way, so that great convenience is brought to the user. Meanwhile, the server cluster maps the data catalogue into the second mounting disc, so that a user can directly acquire experimental data to be processed based on the second mounting disc, the experimental data to be processed does not need to be copied to a data analysis public service platform through a mobile hard disk and the like, and the user is facilitated and the safety of the experimental data is ensured.

In addition, the server cluster maps the writing catalogue in the data storage system to the first mounting disk while starting the target mirror image as an example, and therefore, experimental results obtained after the user analyzes and processes the experimental data based on the data analysis public service platform are automatically stored in the first mounting disk. After the experimental data processing is finished, the user does not need to copy the processed experimental data result, and the website is directly closed. The user can find the processed experimental data result in the data catalog in the data storage system, so that the working efficiency and the safety of the user for processing the experimental data are improved.

The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.

Drawings

In the drawings, which are not necessarily drawn to scale, like numerals may describe similar components in different views. Like reference numerals with letter suffixes or different letter suffixes may represent different examples of similar components. The drawings illustrate generally, by way of example, and not by way of limitation, various embodiments, and together with the description and claims serve to explain the disclosed embodiments. Such embodiments are illustrative and exemplary, and are not intended to be exhaustive or exclusive embodiments of the present system, method, or non-transitory computer readable medium having instructions for implementing the method.

Fig. 1 shows a schematic structural diagram of a cloud computing network system according to an embodiment of the present application.

FIG. 2 shows a schematic diagram of displaying mirror associated information for each mirror on a display interface according to an embodiment of the application.

Fig. 3 shows a schematic diagram of displaying a reserved period on a display interface according to an embodiment of the present application.

Fig. 4 shows a flowchart of a service method of a cloud computing network based on a computing cluster according to an embodiment of the application.

Detailed Description

The present application will be described in detail below with reference to the drawings and detailed description to enable those skilled in the art to better understand the technical scheme of the present application. Embodiments of the present application will be described in further detail below with reference to the drawings and specific examples, but not by way of limitation.

The terms "first," "second," and the like, as used herein do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. As used herein, the word "comprising" or "comprises" and the like means that elements preceding the word encompass the elements recited after the word, and that no other elements are excluded from the possible coverage as well. In the present application, the arrows shown in the figures of the respective steps are merely examples of the execution sequence, and the technical solution of the present application is not limited to the execution sequence described in the embodiments, and the respective steps in the execution sequence may be performed in combination, may be performed in decomposition, and may be exchanged as long as the logical relationship of the execution contents is not affected.

All terms (including technical or scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs, unless specifically defined otherwise. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein. Techniques and equipment known to those of ordinary skill in the relevant art may not be discussed in detail, but should be considered part of the specification where appropriate.

Fig. 1 shows a schematic structural diagram of a cloud computing network system according to an embodiment of the present application. The cloud computing network system comprises a website service layer 101, a database layer 102 and a server cluster 103, wherein the server cluster 103 comprises a plurality of computing servers 104, and a plurality of images are preconfigured in the server cluster 103. In particular, the method of pre-configuring images in the server cluster 103 may include selecting appropriate image tools to create a base image, wherein the image tools may be Docker, kubernetes, etc., by which images may be created, managed, and deployed. The created base image includes the operating system, applications, and related components that are intended to be deployed in the server cluster 103. The created base image is then uploaded to an image repository, such as a Docker Hub or a proprietary image repository, so that each computing server 104 in the server cluster 103 can access and use the base image. Each computing server 104 in the server cluster 103 pulls the uploaded base image to run on, once the base image is pulled onto the computing servers 104, the image tool can be used to deploy the image, creating the same running environment on each computing server 104.

This is merely taken as an example, and does not constitute a specific limitation in which a plurality of images are preconfigured on the server cluster 103. The method for pre-configuring a plurality of images on the server cluster 103 can be set by a user, for example, the user can pre-configure the images according to different used image tools and comprehensively considering the problems of security, availability and the like.

The website service layer 101 is configured to receive a reservation request for a user to reserve a target image. For example, the user registers by logging into the website and enters a display interface on which each mirror image is displayed. The user can determine the target image from the images and reserve the target image.

And responding to the reservation request submitted by a user, adding a reservation record associated with the reservation request, and setting the state of a target image in the reservation record to be a first state which is reserved and not started, wherein the reservation record at least comprises the state of the target image and reservation time. Specifically, for example, the user selects a target image on the website and submits a reservation request, and the database layer 102 increases a reservation record of the reservation request in response to the reservation request submitted by the user, where the reservation record includes at least the number, reservation time, and status of the target image. The reservation time is used for indicating the time when the user will enable the target image, and the state refers to the current state of the target image. In addition, the database layer 102 also reads and stores the account number and the password of the user.

The server cluster 103 communicates with the database layer 102 and with a data storage system 105 accessible to the respective user, the data storage system 105 being configured with a write directory and a data directory for the respective user. The data storage system 105 and the cloud computing network system according to the embodiment of the present application belong to two independent different systems, and the data storage system 105 is mainly used for storing and managing experimental data, but hardly provides a secondary processing function for the experimental data. For example, a API (Application Programming Interface) interface may be opened at the data storage system 105, and the server cluster 103 may read data on the data storage system 105 through an API interface.

Specifically, after the user performs the experiment, implementation-related information such as the obtained experimental data may be stored on the data storage system 105. The user may access the data storage system 105 by verifying personal information such as the user's account number and password to manage or download the relevant experimental data. The data storage system 105 is configured with a write directory and a data directory for each user, wherein the write directory may be empty or may already store processed experimental data. For example, the written directory includes folders named by dates, specifically, user names/writedata/20231211, user names/writedata/20231210, and user names/writedata/20231209. The date may be a storage date on which the processed experimental data result is stored. In each folder, the processed experimental data processing results may be stored, or the written directory may be empty. By way of example only, the specific naming or other management of the write directory and the data directory is not limited.

The data directory stores original experiment data of the user, for example, each time the user performs an experiment, the experiment data is stored in the data directory. Of course, the data directory and the writing directory are different, the original experimental data is stored in the data directory, and the writing directory is used for storing the experimental data processing result after the original experimental data is processed.

The server cluster 103 starts the target image as an instance in a preset time period before the reservation time when it is queried that the target image in the reservation record in the database layer 102 is in a first state, and maps the writing directory of the user in the data storage system 105 to a first mounting disc in the target image, where the first mounting disc is used for storing the processed data. That is, the server cluster 103 may communicate with the database layer 102, and the server cluster 103 may query the database layer 102 periodically, and when the server cluster 103 queries the database layer 102, not only may query each reservation record, but also may query other content, which is not limited thereto.

The server cluster 103 can acquire at least the number, state, and reservation time of the target image in each reservation record by querying the reservation record in the database layer 102. If the server cluster 103 queries that the target image is in the first state, the number and the reserved time of the target image are stored, and the target image is started as an instance within a preset time period before the reserved time. That is, the server cluster 103 does not start the target image immediately when it is queried that the target image is in the first state, but starts according to the reserved time of the target image. The preset time period may be 3 minutes, 4 minutes or 5 minutes before the reserved time, which is not limited, and the user may set the preset time period by himself. The target image is started within a preset time period before the reservation time, and enough time is reserved for starting the target image, for example, a required running environment can be installed and configured on the computing server 104 running the target image within the preset time period, and the target image uploaded before being pulled on the container engine so as to run on the target image, and the like. By way of illustration only, the specific limitation of launching the target image as an example is not construed as being a limitation, and in fact, the specific embodiments may be different in the process of launching the target image as an example due to differences in the used container engines and the like, and thus, the embodiments for launching the target image as an example may be configured by the user themselves.

The server cluster 103, while starting the target image as an instance, maps the user's write directory in the data storage system 105 to the first mounted disk in the target image. Specifically, the data storage system 105 is preconfigured with a write directory for each user, which may be empty or may already store processed data. When the server cluster 103 starts the target image on the computing server 104 as an instance within a preset period of time, the user's write directory in the data storage system 105 is suspended on a Z disk to the instance, which is a mapping of the write directory in the data storage system 105 on the instance.

The server cluster 103 maps the data directory to a second mounted disk in the target image in response to a user selecting the data directory in the data storage system 105, so that the user can read data to be processed based on the second mounted disk. Specifically, the server cluster 103 initiates the target image as an instance, where the instance can be understood as a virtual machine instance, and the user can enter the instance through various modes of SSH connection, remote desktop connection, web console, and the like, connect to the desktop of the virtual machine instance, and implement a desktop interface similar to operating the virtual machine instance on a local computer. On the desktop interface of the instance, a data synchronization catalog mount may be provided for the user, through which the user enters the data storage system 105. The user may then select a data catalog in the data storage system 105 that he or she will process the experimental data. The server cluster 103 mounts the data directory selected by the user as the second mount disc of the instance in response to the selection operation of the user on the data directory, for example, mounts the D disc of the instance when one data directory is selected, and mounts the D disc, E disc and F disc of the instance when three data directories are selected. The number of second mounted discs may be determined according to the number of selected data directories. Therefore, on the desktop interface of the example, the user can find the experimental data by opening the mounted D disc, E disc or F disc, so that the need of carrying the experimental data by using a mobile hard disk and the like is avoided, the experimental data is copied to a data processing public service platform, and the user is facilitated and the data security is improved.

The cloud computing network system provided by the embodiment of the application can realize that a plurality of users can perform analysis and processing of experimental data based on the data processing public service platform or other public service platforms in the same period, and the users can conveniently log in an instance through remote desktop connection or other remote connection modes, remotely use the data processing public service platform or other experimental data processing platforms and process the experimental data. The method is greatly convenient for users, avoids using a public data processing service platform or other experimental data processing platforms in a transregional mode, and improves the working efficiency of the users. In addition, after the user enters the example, the experimental data to be processed can be conveniently obtained, and the processed experimental data can be conveniently stored into the data storage system 105 through the first mounting disc, so that the original experimental data to be processed and the experimental data after secondary processing do not need to be copied through mobile hardware equipment.

In some embodiments of the present application, after the server cluster 103 boots the target image as an instance, boot information about the target image is fed back to the database layer 102, where the boot information includes at least an address and a port of the target image. In addition, the startup information further includes a number of the target image, and the database layer 102 updates the state of the target image in the reservation record to a second state indicating that the target image is started based on the startup information. That is, the information on the state of the target image stored in the reservation record in the database layer 102 may be updated according to the start-up information fed back by the server cluster 103. For example, after the server cluster 103 starts the target image as an instance, start information is automatically returned to the database layer 102, and the database layer 102 updates the state of the target image in the reservation record to a second state that can be characterized by that the target image has been started as an instance, has been executed, has been started, or the like based on the start information. Taking this as an example only, the method of characterizing the second state is not limited.

In some embodiments of the present application, the cloud computing network system is communicatively connected to a user terminal, and the website service layer 101 obtains the state of the target image based on the database layer 102, and displays the state of the target image on a display interface of the user terminal. For example, a user terminal may access the internet through a home or enterprise network, using a public IP address or domain name provided by a cloud service provider to access a cloud computing network system. The web service layer 101 reads data of the database layer 102, for example, can read each reservation record in the database layer 102, and acquire a state of a target image of each reservation record. For example, if the target image stored in the reservation record is in the second state, the web service layer 101 displays the state of the target image on the display interface of the user terminal, so that the user can view the state of the target image on the display interface. Specifically, when the reservation time is about to be reached, a user can log in the cloud computing network system through the user terminal, if the target mirror image is viewed to be displayed on the display interface and is in the second state, the target mirror image is indicated to be started as an example at the moment, the user can click a key near the target mirror image to directly enter the example, and the user can operate in the example so as to remotely use the data processing public service platform to process and analyze data.

In some embodiments of the present application, the server cluster 103 provides a data synchronization directory mount after the target image is started as an instance. Specifically, the data synchronization catalog mount program may be packaged into the image during the process of pre-configuring the image in the server cluster 103, so that the data synchronization catalog mount program available for the user is automatically provided on the display desktop of the instance during the process of starting the target image as the instance by the server cluster 103.

The server cluster 103 maps the data directory to a second mounted disk in the target image in response to a user selecting the data directory in the data storage system 105 via the data synchronization directory mounting program. The data storage system 105 is connected to the computing servers 104 in the server cluster 103 through an API interface, and a user starts a data synchronization directory mounting program and automatically enters the data storage system 105, so as to realize selection of a data directory.

In some embodiments of the present application, the database layer 102 stores the image information of each image in advance, that is, the number of each image and the required information about the CPU, GPU, memory, and license are all stored in the database layer 102 in advance.

The website service layer 101 obtains the mirror image information of each mirror image based on the database layer 102, and displays each mirror image and the mirror image information thereof on a display interface of a user terminal, so that a user can determine a target mirror image based on the mirror image information, and reserve the target mirror image. As shown in fig. 2, at least a mirror name 201, mirror information 202 and a reservation item 203 are displayed on a display interface, names and numbers of mirrors for a user to select reservation are displayed in the mirror name 201, and information including at least a required CPU, a required GPU and the like is displayed in the mirror information 202, for example, the cloud computing item 01, the required CPU is 2 cores, and the required GPU is 2 cores. A reservation key available for reservation by the user is displayed in the reservation item 203 to facilitate reservation by the user. This is merely taken as an example and does not limit the specific embodiments.

In some embodiments of the application, the server cluster 103 includes a plurality of compute servers 104, each of which is configured with a set of compute servers on which it can be run. For example, the mirror image a may run on the number 1 computing server, the number 3 computing server, and the number 5 computing server, and the computing server group on which the mirror image a may run includes the number 1 computing server, the number 3 computing server, and the number 5 computing server. Mirror B may run on compute server No. 1 and compute server No. 2, then the compute server set of mirror B includes compute server No. 1 and compute server No. 2. By way of example only, a user may configure a computing server group of individual images according to computing server 104 and the images themselves.

In some embodiments of the present application, the website service layer 101 responds to the reservation operation of the user on the target image, and obtains the remaining resources of the computing server group capable of running the target image in the corresponding reservation time. That is, the web service layer 101 may communicate with the database layer 102, and can acquire mirror information of each mirror stored in advance in the database layer 102 and information of each computing server 104 in the server cluster 103. Moreover, since the server cluster 103 returns the startup information of each target image to the database layer 102 after the target image is started as an instance, the database layer 102 can calculate the usage of each computing server 104 at each reservation time.

For example, in the case where the computing server group of the target image a includes a No. 1 computing server, a No. 3 computing server, and a No. 5 computing server, the web service layer 101 acquires the reservation time of the target image a reserved by the user through the reservation record in the database layer 102, and automatically calculates the remaining resources of the computing server group of the running target image a at the reservation time, and displays at least the remaining resources satisfying the reservation-capable period of running the target image a to the display interface of the user terminal. As shown in fig. 3, the periods of fig. 3 that are not gray are all periods that a user can reserve, for example, the user can reserve 15:30, 16:00, etc. shown in fig. 3. In addition, on the display interface shown in fig. 3, a period that may not be reserved and a period that has been reserved may also be displayed.

In some embodiments of the present application, the database layer 102 updates a state in a reservation record of a target image with respect to the target image to a third state in characterizing resource allocation in response to a user's reservation operation for the target image. That is, after the user reserves the target image, the state of the target image in the reservation record in the database layer 102 may be updated to a third state in resource allocation, resource calculation, resource acquisition, etc., to indicate that the website service layer 101 is calculating and allocating the remaining available resources in the calculation server group of the target image. For example, in the case where the computing server group of the target image a includes a computing server No. 1, a computing server No. 3, and a computing server No. 5, if the web service layer 101 calculates that the remaining resources of the computing server No. 5 at the reservation time of the user are 0, but the sum of the remaining resources of the computing server No. 1 and the computing server No. 3 is sufficient to run the target image a, the computing server No. 1 and the computing server No. 3 may be allocated to run the target image a. This is merely taken as an example and does not limit the specific embodiments.

The embodiment of the application provides a service method of a cloud computing network based on a computing cluster, which comprises steps S401 to S404 shown in FIG. 4. In step S401, the web service layer is configured to receive a reservation request for a user to reserve a target image. In step S402, the database layer responds to the reservation request submitted by the user, adds a reservation record associated with the reservation request, and sets the state of the target image in the reservation record to a first state which characterizes reserved and not started, wherein the reservation record at least comprises the state of the target image and reservation time. In step S403, when the server cluster queries that the target image in the reservation record in the database layer is in the first state, starting the target image as an instance in a preset period of time before the reservation time, and mapping the writing directory of the user in the data storage system to a first mounting disk in the target image, where the first mounting disk is used to store the processed data, where the server cluster communicates with the data storage systems accessible to each user, and the data storage system is configured with a writing directory and a data directory for each user. In step S404, in response to a user selecting a data directory in the data storage system, the server cluster maps the data directory to a second mount disk in the target image, so that the user can read data to be processed based on the second mount disk. Therefore, the user can remotely analyze the experimental data through the target mirror image by using the data analysis public service platform which is far away from the user, and the experimental data analysis is not needed to be performed in a transregional way, so that great convenience is brought to the user. Meanwhile, the server cluster is started as an example and simultaneously maps the writing catalogue in the data storage system to the first mounting disc of the target image, so that a user can directly acquire experimental data to be processed based on the first mounting disc, the experimental data to be processed is not required to be copied to the data analysis public service platform through a mobile hard disk and the like, and the user is facilitated and the safety of the experimental data is ensured.

In the present application, the arrows shown in the figures of the respective steps are merely examples of the execution sequence, and the technical solution of the present application is not limited to the execution sequence described in the embodiments, and the respective steps in the execution sequence may be performed in combination, may be performed in decomposition, and may be exchanged as long as the logical relationship of the execution contents is not affected.

Other steps of the cloud computing network system based on the computing cluster provided in the embodiment of the present application may be combined herein, and are not described herein.

The present application describes various operations or functions that may be implemented or defined as software code or instructions. Such content may be source code or differential code ("delta" or "patch" code) ("object" or "executable" form) that may be executed directly. The software code or instructions may be stored in a computer readable storage medium and, when executed, may cause a machine to perform the functions or operations described and include any mechanism that stores information in a form accessible by a machine (e.g., computing device, electronic system, etc.), such as recordable or non-recordable media (e.g., read Only Memory (ROM), random Access Memory (RAM), magnetic disk storage media, optical storage media, flash memory devices, etc.).

Implementations of such methods may include software code, such as microcode, assembly language code, higher-level language code, or the like. Various software programming techniques may be used to create various programs or program modules. For example, program portions or program modules may be designed in or with the aid of Java, python, C, C ++, assembly language, or any known programming language. One or more of such software portions or modules may be integrated into a computer system and/or computer readable medium. Such software code may include computer readable instructions for performing various methods. The software code may form part of a computer program product or a computer program module. Furthermore, in examples, the software code may be tangibly stored on one or more volatile, non-transitory, or non-volatile tangible computer-readable media, such as during execution or at other times. Examples of such tangible computer-readable media may include, but are not limited to, hard disks, removable magnetic disks, removable optical disks (e.g., optical disks and digital video disks), magnetic cassettes, memory cards or sticks, random Access Memories (RAMs), read Only Memories (ROMs), and the like.

Furthermore, although exemplary embodiments have been described herein, the scope thereof includes any and all embodiments having equivalent elements, modifications, omissions, combinations (e.g., of the various embodiments across), adaptations or alterations as pertains to the present application. The elements in the claims are to be construed broadly based on the language employed in the claims and are not limited to examples described in the present specification or during the practice of the application, which examples are to be construed as non-exclusive. It is intended, therefore, that the specification and examples be considered as exemplary only, with a true scope and spirit being indicated by the following claims and their full scope of equivalents.

The above description is intended to be illustrative and not restrictive. For example, the above-described examples (or one or more aspects thereof) may be used in combination with each other. For example, other embodiments may be used by those of ordinary skill in the art upon reading the above description. In addition, in the above detailed description, various features may be grouped together to streamline the application. This is not to be interpreted as an intention that the disclosed features not being claimed are essential to any claim. Rather, inventive subject matter may lie in less than all features of a particular disclosed embodiment. Thus, the claims are hereby incorporated into the detailed description as examples or embodiments, with each claim standing on its own as a separate embodiment, and it is contemplated that these embodiments may be combined with one another in various combinations or permutations. The scope of the application should be determined with reference to the appended claims, along with the full scope of equivalents to which such claims are entitled.

The above embodiments are only exemplary embodiments of the present application and are not intended to limit the present application, the scope of which is defined by the claims. Various modifications and equivalent arrangements of this application will occur to those skilled in the art, and are intended to be within the spirit and scope of the application.

Claims (10)

1. A cloud computing network system based on a computing cluster is characterized by comprising a website service layer, a database layer and a server cluster, wherein a plurality of images are preconfigured in the server cluster,

The website service layer is used for receiving a reservation request of a user for reserving a target image;

The database layer responds to the reservation request submitted by a user, increases reservation records associated with the reservation request, and sets the state of a target image in the reservation records to be a first state representing reserved and not started, wherein the reservation records at least comprise the state of the target image and reservation time;

The server cluster is communicated with the database layer and a data storage system accessible by each user, and the data storage system is configured with a writing catalog and a data catalog for each user;

under the condition that a target image in reservation records in the database layer is in a first state, starting the target image as an example in a preset time period before reservation time by a server cluster, and mapping a writing catalog of a user in the data storage system into a first mounting disc in the target image, wherein the first mounting disc is used for storing processed data;

And the server cluster responds to the operation of selecting the data catalogue in the data storage system by a user, and maps the data catalogue to a second mounting disc in the target image so that the user can read the data to be processed based on the second mounting disc.

2. The cloud computing network system of claim 1, wherein after the server cluster boots the target image as an instance, feeding back boot information about the target image to the database layer, the boot information including at least an address and a port of the target image;

And the database layer updates the state of the target image in the reservation record to a second state representing that the target image is started based on the starting information.

3. The cloud computing network system of claim 2, wherein the cloud computing network system is communicatively connected to a user terminal;

and the website service layer acquires the state of the target mirror image based on the database layer and displays the state of the target mirror image on a display interface of the user terminal.

4. The cloud computing network system of claim 1, wherein the server cluster, after launching the target image as an instance, provides a data synchronization catalog mount procedure;

And responding to the operation that a user selects a data directory in the data storage system through the data synchronization directory mounting program, and mapping the data directory into a second mounting disk in a target image.

5. The cloud computing network system of claim 1, wherein the database layer stores mirror information of each mirror in advance;

The website service layer obtains the mirror image information of each mirror image based on the database layer, and displays each mirror image and the mirror image information thereof on a display interface of the user terminal, so that a user can determine a target mirror image based on the mirror image information and reserve the target mirror image.

6. The cloud computing network system of claim 5, wherein said mirrored information comprises information about a CPU, GPU, memory and license.

7. The cloud computing network system of claim 5, wherein the server cluster comprises a plurality of computing servers, each image being configured with a group of computing servers operable thereon.

8. The cloud computing network system of claim 7, wherein the web service layer obtains remaining resources of a computing server group capable of running the target image in a corresponding reservation time in response to a reservation operation of the target image by a user;

And displaying at least the reserved time period of the residual resource meeting the running of the target image to a display interface of the user terminal.

9. The cloud computing network system of claim 8, wherein the database layer updates a state in a reservation record of a target image with respect to the target image to a third state in characterizing resource allocation in response to a reservation operation of the target image by a user.

10. A service method of a cloud computing network based on a computing cluster, the service method comprising:

The website service layer is used for receiving a reservation request of a user reservation target image;

The method comprises the steps that a database layer responds to a reservation request submitted by a user, a reservation record associated with the reservation request is added, and the state of a target image in the reservation record is set to be a first state which characterizes reservation and non-starting, wherein the reservation record at least comprises the state of the target image and reservation time;

Under the condition that a target mirror image in reservation records in a database layer is in a first state, starting the target mirror image as an example in a preset time period before reservation time, mapping a writing catalog of a user in a data storage system into a first mounting disk in the target mirror image, wherein the first mounting disk is used for storing processed data, the server cluster is communicated with the data storage systems accessible by all users, and the data storage systems are configured with writing catalogs and data catalogs for all users;

And the server cluster responds to the operation of selecting the data catalogue in the data storage system by a user, and maps the data catalogue to a second mounting disc in the target image so that the user can read the data to be processed based on the second mounting disc.