CN118277025A - Virtual unit starting method and device and cloud computing system - Google Patents

Abstract

A virtual unit starting method and device and a cloud computing system belong to the technical field of cloud computers. The method is applied to a management platform in an intensive cloud computing system, and the intensive cloud computing system further comprises a first computing pool. The method comprises the following steps: acquiring at least one set of starting measurement information corresponding to a starting requirement of a first application and a target application, wherein the at least one set of starting measurement information corresponds to at least one starting scheme, and each set of starting measurement information is used for representing starting performance of starting the target application in the intensive cloud computing system based on the corresponding starting scheme, and the target application is matched with the first application; determining a first start-up scenario from the start-up complaints of the first application and the at least one set of start-up measurement information; and starting a first virtual unit of the first application in the first computing pool according to a first starting scheme. The virtual unit starting scheme provided by the application has better implementation performance in the intensive cloud computing system.

Description

Virtual unit starting method and device and cloud computing system

The present application claims priority from chinese patent application with application number 2022, 12, 23, 202211663651.X, application name "container start method and apparatus, cloud computing system", the entire contents of which are incorporated herein by reference.

Technical Field

The present application relates to the field of cloud computing technologies, and in particular, to a virtual unit starting method and apparatus, and a cloud computing system.

Background

With the development of virtualization technology, cloud computing systems may deploy applications (applications) in containers (containers) to implement resource isolation of different applications based on the containers. Typically, launching an application includes launching a container of the application (i.e., the container in which the application is deployed).

The current container starting scheme is designed for an non-intensive cloud computing system, and has poor performance in implementation in the intensive cloud computing system. The intensive cloud computing system comprises a plurality of intensive resource pools which are interconnected at high speed, wherein computing resources, memory resources or one type of resources in external memory resources are intensively distributed in each intensive resource pool. The non-intensive cloud computing system comprises a plurality of independent non-intensive resource pools, and the proportion of computing resources, memory resources and external memory resources in each non-intensive resource pool is equivalent.

Disclosure of Invention

The application provides a virtual unit starting method and device and a cloud computing system. The technical scheme of the application is as follows.

In a first aspect, a virtual unit starting method is provided, and the virtual unit starting method is applied to a management platform in an intensive cloud computing system, where the intensive cloud computing system further includes a first computing pool, and the method includes: acquiring a starting requirement of a first application; acquiring at least one set of starting measurement information corresponding to a target application, wherein the at least one set of starting measurement information corresponds to at least one starting scheme, and each set of starting measurement information in the at least one set of starting measurement information is used for representing starting performance of starting the target application in the intensive cloud computing system based on the corresponding starting scheme, and the target application is matched with a first application; determining a first startup scheme based on the startup complaint of the first application and the at least one set of startup measurement information, the at least one startup scheme including the first startup scheme; and starting a first virtual unit of the first application in the first computing pool according to a first starting scheme.

The first starting scheme is a starting scheme of the first application, the starting performance of the first starting scheme is matched with the starting requirement of the first application, and the starting performance of the first starting scheme meets the starting requirement of the first application. The management platform determines a first starting scheme according to the starting complaint sum of the first application and the at least one set of starting measurement information, namely the management platform determines the first starting scheme according to the starting performance of the at least one starting scheme corresponding to the starting complaint sum of the at least one set of starting measurement information.

According to the technical scheme provided by the application, the management platform in the intensive cloud computing system determines the first starting scheme according to the starting requirement of the first application and the starting performance of at least one starting scheme, and starts the virtual unit of the first application in the first computing pool in the intensive cloud computing system according to the first starting scheme, so that the performance of the virtual unit starting scheme implemented in the intensive cloud computing system is better, the extremely rapid starting of the first application can be realized, and the low-cost resources can be fully utilized. The management platform automatically selects the starting scheme according to the starting requirement of the first application, so that the usability of the scheme can be improved.

Optionally, the first starting scheme includes any one of the following: a warm boot scheme based on the first storage pool; a cold start scheme based on the first storage pool; a cold start scheme based on the second computing pool; wherein the first storage pool and the second computing pool are respectively interconnected with the first computing pool. For example, the first storage pool-based warm boot scheme is a first storage pool-based warm boot scheme based on memory snapshots stored in the first storage pool, the first storage pool-based cold boot scheme is a first storage pool-based cold boot scheme based on virtual unit snapshots stored in the first storage pool, and the second computing pool-based cold boot scheme is a second computing pool-based cold boot scheme based on virtual units running in the second computing pool.

Optionally, the first starting scheme includes a hot starting scheme based on a first storage pool, wherein a reference memory snapshot is stored in the first storage pool, the reference memory snapshot is obtained by snapshot of a memory of a reference virtual unit of the first application, and the first computing pool includes the first virtual unit; starting a first virtual unit of a first application in a first computing pool according to a first starting scheme, comprising: creating a first memory branch in the first computing pool according to the reference memory snapshot, wherein the first memory branch is used for storing memory data which changes relative to the reference memory snapshot in the operation process of the first virtual unit, and the memory data of the first virtual unit (namely, the data in the memory of the first virtual unit) is determined according to the data in the reference memory snapshot and the memory data stored in the first memory branch. The reference virtual unit of the first application is a virtual unit which is deployed with the first application and is started.

Optionally, a reference file system is further stored in the first storage pool, where the reference file system is a file system of the reference virtual unit; starting a first virtual unit of a first application in a first computing pool according to a first starting scheme, and further comprising: and creating a first read-write layer in the first computing pool according to the reference file system, wherein the first read-write layer is used for storing file data which changes relative to the reference file system in the operation process of the first virtual unit, and the file system of the first virtual unit is determined according to the file data in the reference file system and the file data stored in the first read-write layer.

Optionally, before the first virtual unit is started in the first computing pool according to the first starting scheme, the method further includes: acquiring the reference memory snapshot of the reference virtual unit in the process of operating the reference virtual unit; the reference memory snapshot is stored in a first memory pool.

According to the technical scheme provided by the application, the management platform acquires the reference memory snapshot and stores the reference memory snapshot into the first memory pool, so that the management unit can conveniently establish the first memory branch to start the first virtual unit according to the reference memory snapshot, the speed of starting the first virtual unit by the management platform is improved, and the starting speed of the first application is improved.

Optionally, before the first virtual unit is started in the first computing pool according to the first starting scheme, the method further includes: a first virtual unit is created in a first computing pool from an application image of a first application. I.e. at the preheating of the first virtual cell.

According to the technical scheme provided by the application, the management platform preheats the first virtual unit, so that the speed of the management platform for subsequently starting the first virtual unit can be increased, and the starting speed of the first application is increased, for example, the very-fast starting of the first application is realized.

Optionally, the first startup scheme includes a cold startup scheme based on a first storage pool, where a reference unit snapshot is stored in the first storage pool, where the reference unit snapshot is obtained by snapshot a reference virtual unit of the first application; starting a first virtual unit of a first application in a first computing pool according to a first starting scheme, comprising: a first virtual unit is created and started in a first computing pool according to the reference unit snapshot.

Optionally, before the first virtual unit is started in the first computing pool according to the first starting scheme, the method further includes: acquiring a reference unit snapshot of the reference virtual unit in the process of operating the reference virtual unit; the reference cell snapshot is stored in the first storage pool.

According to the technical scheme provided by the application, the management platform acquires the reference unit snapshot and stores the reference unit snapshot into the first storage pool, so that the management unit can conveniently establish the first virtual unit and start the first virtual unit according to the reference unit snapshot, the speed of starting the first virtual unit by the management platform is improved, and the starting speed of the first application is improved.

Optionally, the reference virtual unit runs in a first computing pool.

Optionally, the first starting scheme includes a cold starting scheme based on a second computing pool, in which a second virtual unit is operated, and the configuration of the second virtual unit is the same as that of the first virtual unit; starting a first virtual unit of a first application in a first computing pool according to a first starting scheme, comprising: a first virtual unit is created and started in the first computing pool according to the second virtual unit. Wherein the configuration of the second virtual unit is the same as the configuration of the first virtual unit includes: the metadata of the second virtual unit is the same as the metadata of the first virtual unit, and the description of the second virtual unit is the same as the description of the first virtual unit. For example, the attribute of the second virtual unit is the same as the attribute of the first virtual unit, and the application image corresponding to the second virtual unit is the same as the application image corresponding to the first virtual unit (e.g., the application image corresponding to the second virtual unit and the application image corresponding to the first virtual unit are both application images of the first application). By way of example, another markup language (yet another markup language, YAML) file of the second virtual unit is the same as the YAML file of the first virtual unit. The application image is a file storage form, is a software package which is lightweight and independently executable by an application, contains all contents required for running the application, and contains codes, system tools, libraries, environment variables, configuration files and the like.

Optionally, starting the first virtual unit according to the second virtual unit includes: creating a second memory branch in the first computing pool according to the memory of the second virtual unit, wherein the second memory branch is used for storing memory data which changes relative to the memory of the second virtual unit in the operation process of the first virtual unit, and the memory data of the first virtual unit is determined according to the memory data of the second virtual unit (namely, the data in the memory of the second virtual unit) and the memory data stored in the second memory branch.

Optionally, starting the first virtual unit according to the second virtual unit includes: creating a second read-write layer in the first computing pool according to the file system of the second virtual unit, wherein the second read-write layer is used for storing file data which changes relative to the file system of the second virtual unit in the operation process of the first virtual unit, and the file system of the first virtual unit is determined according to the file data in the file system of the second virtual unit and the memory data stored in the second memory branch.

Optionally, the intensive cloud computing system further includes a first storage pool, the first storage pool being interconnected with the first computing pool; the first storage pool is used for storing at least one of the following information of the first application: a snapshot of the memory of the virtual unit of the first application; a snapshot of virtual units of the first application; application mirroring of a first application. The storage location of the at least one piece of information for the first application in the first storage pool is determined based on at least one of the following metrics for the first application: importance, frequency of use, start-up requirements.

According to the technical scheme provided by the application, the storage positions of the information such as the memory snapshot of the virtual unit of the first application, the application mirror image of the first application and the like in the first storage pool are determined according to the indexes such as the importance, the use frequency and the start requirement of the first application, so that the information of the application with higher importance, higher use frequency and more strict start requirement can be stored in a storage medium with better performance, and the start performance of the application is ensured.

Optionally, the intensive cloud computing system further includes a mirror image repository, where the mirror image repository is configured to store a correspondence between indication information of an application mirror image and a storage location of the application mirror image in the first storage pool.

According to the technical scheme, the application mirror image is stored in the first storage pool, the mirror image warehouse is used for storing the corresponding relation between the indication information of the application mirror image and the storage position of the application mirror image, so that when the management platform creates a virtual unit of an application, the management platform obtains the storage position of the application mirror image from the mirror image warehouse according to the indication information of the application mirror image of the application, and further obtains the application mirror image from the first storage pool according to the storage position of the application mirror image.

Optionally, the first storage pool includes at least one of a memory pool and a memory pool.

Optionally, the memory pool and the external memory pool satisfy at least one of: the memory pool comprises at least two first storage media, and the types of the at least two first storage media are different; the external memory pool includes at least two second storage media, the at least two second storage media being different in type. Wherein the first storage medium and the second storage medium store data based on a differential algorithm, respectively.

According to the technical scheme provided by the application, the first storage medium and the second storage medium store data based on the differential algorithm respectively, so that for any data block, only the difference between any data block and the reference data block is stored in the first storage medium or the second storage medium, and the same data block is stored for only one part, so that the storage resource can be saved, and the storage cost can be reduced.

Optionally, the matching of the target application with the first application includes at least one of: the target application is a first application; the scale of the target application is matched with the scale of the first application; the size of the application image of the target application is matched with the size of the application image of the first application; the type of the target application matches the type of the first application.

Optionally, the start-up complaint of the first application includes at least one of a start-up duration complaint and a start-up cost complaint; the start-up measurement information includes at least one of a measured start-up duration and a measured start-up cost.

Optionally, obtaining at least one set of start measurement information corresponding to the target application includes: and performing a starting test on the target application in the intensive cloud computing system according to each starting scheme in the at least one starting scheme to obtain a group of starting measurement information corresponding to each starting scheme.

Optionally, the management platform is deployed in a first computing pool. From the perspective of the management platform, the first computing pool is referred to as a local computing pool, the second computing pool is referred to as a remote (remote) computing pool, and the first storage pool is referred to as a remote storage pool.

Optionally, the first virtual unit is a container or a virtual machine.

In a second aspect, a virtual unit activation apparatus is provided, comprising at least one module for performing the method as provided in the first aspect or any of the alternatives of the first aspect. The at least one module may be implemented based on software, hardware, or a combination of software and hardware, and the at least one module may be arbitrarily combined or partitioned based on the specific implementation.

In a third aspect, a virtual unit activation apparatus is provided, including a memory and a processor; the memory is used for storing a computer program; the processor is configured to execute a computer program stored in the memory to cause the virtual unit starting apparatus to perform a method as provided in the first aspect or any of the alternatives of the first aspect.

In a fourth aspect, a cloud computing system is provided, including the virtual unit activation apparatus provided in the second aspect or the third aspect.

Optionally, the cloud computing system comprises a computing pool and a storage pool, the computing pool being interconnected with the storage pool, the computing pool comprising the virtual unit activation apparatus as provided in the second or third aspect above. For example, the computing pool comprises a management platform comprising the virtual unit initiation means as provided in the second or third aspect above.

Optionally, the storage pool includes a memory pool and an external memory pool, and the memory pool and the external memory pool are respectively interconnected with the computing pool.

In a fifth aspect, there is provided a computer readable storage medium having stored therein a computer program which when executed implements a method as provided in the above first aspect or any of the alternatives of the first aspect.

In a sixth aspect, there is provided a computer program product comprising a program or code which when executed implements a method as provided in the first aspect or any of the alternatives of the first aspect.

The technical effects of the second aspect to the sixth aspect described above may refer to the technical effects of the first aspect, and are not described herein.

Drawings

FIG. 1 is a schematic diagram of an intensive cloud computing system according to an embodiment of the present application;

FIG. 2 is a schematic diagram of another enhanced cloud computing system provided by an embodiment of the present application;

FIG. 3 is a flowchart of a method for starting up a virtual unit according to an embodiment of the present application;

FIG. 4 is a schematic diagram of a first virtual unit according to an embodiment of the present application;

FIG. 5 is a schematic diagram of another embodiment of the present application for starting a first virtual unit;

FIG. 6 is a schematic diagram of a further embodiment of a first virtual unit activation;

fig. 7 is a schematic diagram of a virtual unit starting apparatus according to an embodiment of the present application;

fig. 8 is a schematic diagram of another virtual unit starting apparatus according to an embodiment of the present application.

Detailed Description

Embodiments of the present application will be further described below with reference to the accompanying drawings.

With the development of virtualization technology, cloud computing systems may deploy applications in containers to achieve resource isolation of different applications based on the containers. The application deployed in the container may be a serverless (serverless) application or other application, among others.

In a container-based application isolation scheme, typically, launching an application includes launching a container for the application. The container of an application may be a container in which the application is deployed (i.e., the application is already deployed in the container), a container in which the application is to be deployed (i.e., the application is to be deployed in the container), a container created for the application (e.g., a container created from an application image of the application), and so on, which may ultimately be used for the application to run.

Current container start-up schemes include hot start-up schemes and cold start-up schemes. In a warm-start scheme, a cloud computing system pre-creates (i.e., warms) a number of containers, and when the cloud computing system receives a container start request corresponding to an application, the cloud computing system allocates containers for the application among the pre-created containers according to the container start request and starts the containers. In a cold start scheme, for an application, a cloud computing system prepares in advance at least some of the components (e.g., container snapshots) required to create a container for the application, and when the cloud computing system receives a container start request corresponding to the application, the cloud computing system creates containers for the application based on the prepared components and starts the containers according to the container start request.

The continuous development of cloud native technology drives the evolution of the underlying hardware infrastructure into a resource pool of resource intensive high-speed interconnections, which makes the intensive cloud computing system. The intensive cloud computing system is also called as a separated data center (DISAGGREGATED DATA CENTER), and is characterized in that each type of resources are intensively distributed in corresponding resource pools, the resource pools are interconnected through a high-speed network, and the resource pools in the intensive cloud computing system are also called as intensive resource pools. For example, the intensive cloud computing system comprises a computing pool, a memory pool and an external memory pool which are interconnected at high speed, wherein the computing pool, the memory pool and the external memory pool are all intensive resource pools, computing resources are intensively distributed in the computing pool, memory resources are intensively distributed in the memory pool, and external memory resources are intensively distributed in the external memory pool. In addition, the computing pool also comprises a small amount of memory resources and/or external memory resources, the memory pool also comprises a small amount of computing resources and/or external memory resources, and the external memory pool also comprises a small amount of computing resources and/or internal memory resources. By way of example, a host equipped with a large amount of memory is a memory pool, a central processing unit (central processing unit, CPU) based host is a computing pool, and a host equipped with a large amount of memory is connected to a CPU based host via a remote direct memory access (remote direct memory access, RDMA) network. The non-intensive cloud computing system is characterized in that the proportion of different types of resources in each resource pool is equivalent, the resource pools in the non-intensive cloud computing system are also called non-intensive resource pools, for example, the non-intensive cloud computing system comprises a plurality of independent non-intensive resource pools, each non-intensive resource pool comprises computing resources, memory resources and external memory resources, and the proportion of the computing resources, the memory resources and the external memory resources in each non-intensive resource pool is equivalent.

The existing container starting scheme is designed for a non-intensive cloud computing system, and because the characteristics of the intensive cloud computing system are different from those of the non-intensive cloud computing system, the existing container starting scheme is directly implemented in the intensive cloud computing system, so that the problems of poor application starting performance, poor performance of the intensive cloud computing system and the like are easily caused. For example, if the current hot start scheme is directly implemented in the enhanced cloud computing system, since many containers cannot be preheated in a computing pool with a smaller memory allocation, when the enhanced cloud computing system receives a container start request corresponding to an application and the container start request is used to start up a plurality of containers, the number of containers preheated may be insufficient (for example, a user requests to start up 10 containers and only preheats 7 containers), which affects the start speed of the application, which is intolerable for a serverless application (the startup complaint of the serverless application on the containers is a very fast startup). For another example, if the current cold start scheme is directly implemented in the intensive cloud computing system, the intensive cloud computing system stores the container snapshot in the computing pool (when the current container start scheme starts the container based on the container snapshot, the container snapshot and the container are in the same non-intensive resource pool), but does not store the container snapshot in a storage pool (a memory pool or an external memory pool) that is interconnected with the computing pool at a high speed, compared to the storage resources in the storage pool, the cost of the storage resources in the computing pool is higher, which results in that the storage resources with low cost cannot be utilized, and thus in that the operation cost of the intensive cloud computing system is higher.

The embodiment of the application provides a virtual unit starting scheme which is applied to a management platform in an intensive cloud computing system, wherein the intensive cloud computing system further comprises a first computing pool. The management platform determines a first starting scheme according to at least one group of starting measurement information corresponding to the starting requirement of the first application and the target application, and starts a virtual unit of the first application in a first computing pool according to the first starting scheme. The at least one set of starting measurement information corresponds to at least one starting scheme, each set of starting measurement information is used for representing starting performance of a target application started in the intensive cloud computing system based on the corresponding starting scheme, the target application is matched with the first application, the at least one starting scheme comprises a first starting scheme, the management platform determines the first starting scheme according to starting complaints of the first application and the at least one set of starting measurement information, namely the management platform determines the first starting scheme according to the starting complaints and the starting performance of the at least one starting scheme. The management platform in the intensive cloud computing system determines the first starting scheme according to the starting requirement of the first application and the starting performance of at least one starting scheme corresponding to the target application, and starts the virtual unit of the first application in the first computing pool in the intensive cloud computing system according to the first starting scheme. Where the virtual unit is a container, virtual Machine (VM), or other unit for resource isolation, all "virtual units" herein may be replaced with "containers" or "virtual machines".

The technical scheme of the embodiment of the application is introduced, and the application scene of the embodiment of the application is introduced first.

The application scenario of the embodiment of the application provides an intensive cloud computing system, which comprises a plurality of intensive resource pools, wherein the plurality of intensive resource pools are interconnected, for example, the plurality of intensive resource pools are interconnected through a high-speed network, the plurality of intensive resource pools can be communicated through an application program interface (application program interface, API), and each of the plurality of intensive resource pools mainly comprises a class of resources. The plurality of intensive resource pools include at least one computing pool and at least one storage pool, the at least one storage pool including a memory pool and/or a memory pool, the computing pool including primarily computing resources, the memory pool including primarily memory resources, and the memory pool including primarily memory resources. The computing pool also comprises a small amount of memory resources and/or external memory resources, the memory pool also comprises a small amount of computing resources and/or external memory resources, and the external memory pool also comprises a small amount of computing resources and/or internal memory resources. The intensive cloud computing system is also called a separated data center, the computing pool is also called a computing resource pool, the memory pool is also called a memory resource pool or an internal storage resource pool, and the external memory pool is also called an external memory resource pool or an external storage resource pool. The external memory resources are typically disk resources, so that the external memory pool is also referred to as a disk pool, disk resource pool, or the like. The computing pool is exemplified by a host or server that is primarily computing resources, the memory pool is a host or server that is primarily memory resources, and the memory pool is a host or server that is primarily memory resources, which is not limited in this embodiment of the present application.

In an alternative embodiment, the at least one storage pool includes a memory pool and an external memory pool. The memory pool may be a heterogeneous memory pool including at least two first storage media, each of the at least two first storage media being a storage medium providing memory resources, the at least two first storage media being of a different type, e.g., the at least two first storage media including dynamic random access memory (dynamic random access memory, DRAM) and storage class memory (storage class memory, SCM). The flash pool may be a heterogeneous flash pool including at least two second storage media, each of which is a storage medium providing a flash resource, the at least two second storage media being of a different type, for example, the at least two second storage media including a solid state disk (solid STATE DRIVES, SSD) and a hard disk drive (HARD DISK DRIVE, HDD). Since the performance (e.g., speed), cost, etc. of the different types of storage media are different, the performance, cost, etc. of the above at least two first storage media are different, and the performance, cost, etc. of the above at least two second storage media are different. Optionally, the memory pool and the external memory pool both support storing data based on a differential algorithm. The difference algorithm refers to a difference (diff) between stored data blocks, for example, a difference between any one data block and a reference data block is stored for the any one data block. For example, data is stored in the same storage medium based on a differential algorithm, e.g., one reference data block for each storage medium, and for any data block to be stored in any storage medium, the difference between the any data block and the reference data block corresponding to the storage medium is stored in any storage medium. In the embodiment of the application, the memory pool and the external memory pool are both used for storing data based on the differential algorithm, so that the memory resource can be saved, and the memory cost can be reduced.

In an embodiment of the application, a virtual unit (for example, a virtual unit is created for an application) can be created in the intensive cloud computing system, and the application is deployed in the virtual unit, so as to realize resource isolation of different applications based on the virtual unit. The virtual unit is a calculation unit capable of independently running, and has own calculation resources, memory resources and file systems. The computing resources of the virtual units are the computing resources in a computing pool, and one virtual unit occupies part of the computing resources in one computing pool; the memory resources of the virtual units are the memory resources in the memory pool, and one virtual unit occupies part of the memory resources in one memory pool; the file systems of the virtual units may be located in a pool of memory, with the file system of one virtual unit occupying a portion of the memory resources in one pool of memory. That is, virtual units are a logical concept, and different resources of one virtual unit are distributed in multiple interconnected intensive resource pools. Wherein, multiple virtual units of an application may share the same memory resources in the memory pool and/or the same memory resources in the memory pool. For example, a memory pool stores a snapshot of the memory of a reference virtual unit (e.g., a virtual unit that has been created) of an application, and all virtual units of the application may share the snapshot of the memory of the reference virtual unit. Optionally, the intensive cloud computing system further includes a management platform, where the management platform is located in the computing pool or is set independently, and the management platform is used to manage the virtual units, create the virtual units in the intensive cloud computing system, deploy applications in the virtual units, start the virtual units, and so on. This management platform is also referred to as a virtual unit management platform. Wherein the virtual units are containers, virtual machines, or other units for resource isolation. For example, a virtual unit is a container, and the management platform is correspondingly referred to as a container management platform. For another example, the virtual units are virtual machines, and the management platform is correspondingly called a virtual machine management platform.

In an embodiment of the present application, a storage pool may be used to store various information needed to create a virtual unit of an application, including, but not limited to, a snapshot of the memory of a reference virtual unit of the application, a snapshot of a reference virtual unit of the application, an application image of the application, and so on. In one embodiment, a storage policy corresponding to the application is determined according to indexes such as importance, use frequency, start-up requirements (such as start-up duration, start-up cost, etc.) of the application (for example, determining whether to store the information corresponding to the application in a memory pool or a memory pool, and in which storage medium of the memory pool or in which storage medium of the memory pool in particular), and information corresponding to the application is stored in the memory pool according to the storage policy corresponding to the application. In another embodiment, information corresponding to the application is stored in a storage pool according to a preset storage policy or a specified storage policy of the intensive cloud computing system. Optionally, different information corresponding to the same application is stored in the same storage pool or different storage pools, and different information corresponding to the same application is stored in the same storage medium or different storage media. The application image is a file storage form, is a software package which is lightweight and independently executable by an application, contains all contents required for running the application, for example, the application image of any application contains all contents required for starting a virtual unit of the application, and the contents contain codes, system tools, libraries, environment variables, configuration files and the like.

In an alternative embodiment, the storage pool is configured to store application-specific images, the application-specific images satisfying at least one of: the most commonly used application image (e.g., an application image that uses a frequency greater than a preset frequency), the most recently used application image (e.g., the time difference between the time the application image was last used and the current time is less than a preset time difference), the application image of an important customer. For example, the storage index of a specific application image meets a preset storage index, and the storage index of any application image is obtained by weighting and calculating according to the use frequency of the application image, the latest use time of the application image and the client importance level corresponding to the application image. In the embodiment of the application, the storage pool comprises a memory pool and/or an external memory pool, and the memory pool and/or the external memory pool comprise at least two storage media, so that the application images of different applications can be stored in the same storage media or different storage media, and the application images can be stored in the storage pool in a distributed manner.

In an optional embodiment, the intensive cloud computing system further includes a mirror repository, where the mirror repository may be a distributed mirror repository, and the mirror repository is configured to store a correspondence between indication information of an application mirror and a storage location of the application mirror in a storage pool (simply referred to as a storage location of the application mirror, for example, the correspondence is referred to as a first correspondence. When the management platform creates a virtual unit of an application, the management platform determines a storage position of the application image according to the indication information of the application image of the application and a first corresponding relation stored in the image warehouse, and the management platform acquires the application image from the storage pool according to the storage position of the application image and creates the virtual unit based on the application image. The management platform sends a mirror image acquisition request to the mirror image warehouse, wherein the mirror image acquisition request carries indication information of an application mirror image of the application, the mirror image warehouse determines a storage position of the application mirror image according to the indication information of the application mirror image carried by the mirror image acquisition request and a first corresponding relation, and sends the storage position of the application mirror image to the management platform, and the management platform acquires the application mirror image from a storage pool according to the storage position of the application mirror image. Wherein the mirror repository may be deployed in a computing pool or a storage pool, may be deployed independent of the computing pool and the storage pool, e.g., the mirror repository may be deployed in a separate server. The indication information of the application image may be an identification of the application image, for example, an identification of a certain application is used as an identification of the application image of the application.

The mirror repository in the related art is used to centrally store application mirrors (i.e., different application mirrors are centrally stored in the mirror repository), and such a mirror repository is also called a centralized mirror repository. Under the condition of high concurrency virtual unit creation, the centralized mirror image warehouse has bandwidth bottleneck, so that the speed of acquiring the application mirror image is slower, and the time delay for virtual unit creation is larger. According to the embodiment of the application, the application mirror images are stored in the storage pool in a distributed manner, the corresponding relation between the indication information of the application mirror images stored in the mirror image warehouse and the storage positions of the application mirror images is set, when the management platform creates a virtual unit of an application, the management platform acquires the storage positions of the application mirror images from the mirror image warehouse according to the indication information of the application mirror images of the application, and further acquires the application mirror images from the distributed storage pool according to the storage positions of the application mirror images, so that the speed of acquiring the application mirror images can be improved, the time delay of creating the virtual unit is reduced, and the problem that the speed of acquiring the application mirror images in the centralized mirror image warehouse under the condition of high-concurrency virtual unit creation is slow and the time delay of virtual unit creation is large can be well solved.

Taking an intensive cloud computing system as an example, the intensive cloud computing system comprises two computing pools, a memory pool and an external memory pool. As an example, fig. 1 is a schematic diagram of an intensive cloud computing system 100 according to an embodiment of the present application. The intensive cloud computing system 100 includes a first computing pool 101, a second computing pool 102, and a first storage pool 103, the first storage pool 103 including a memory pool 31 and an external storage pool 32, the first computing pool 101, the second computing pool 102, and the first storage pool 103 being interconnected by a high-speed network. The first computing pool 101 and the second computing pool 102 are both intensive resource pools mainly containing computing resources, the memory pool 31 is an intensive resource pool mainly containing memory resources, and the external memory pool 32 is an intensive resource pool mainly containing external memory resources. For example, the first computing pool 101 and the second computing pool 102 are both hosts or servers that are primarily computing resources, the memory pool 31 is a host or server that is primarily memory resources, and the external memory pool 32 is a host or server that is primarily external memory resources. As shown in fig. 1, the memory pool 31 includes m first storage media 311 to 31m, where the types of the first storage media 311 to 31m are different, and the first storage media may store information such as a snapshot and an application mirror image corresponding to at least one application based on a differential algorithm. The external memory pool 32 includes n second storage media 321 to 32n, where the types of the second storage media 321 to 32n are different, and the second storage media can store information such as snapshots, application images and the like corresponding to at least one application based on a differential algorithm. The first computing pool 101 includes a management platform 11, and the management platform 11 creates a virtual unit in the intensive cloud computing system 100, deploys an application in the virtual unit, starts the virtual unit, and the like. For example, the management platform 11 creates a virtual unit of the first application in the first computing pool 101, where the computing resources of the virtual unit are computing resources in the first computing pool 101, and the memory resources of the virtual unit include memory resources in the memory pool 31, and the file system portion of the virtual unit is located in the external memory pool 32. Since the management platform 11 is in the first computing pool 101, from the perspective of the management platform 11, the first computing pool 101 is referred to as a local computing pool, the second computing pool 102 is referred to as a remote computing pool, the memory pool 31 is referred to as a remote memory pool, and the memory pool 32 is referred to as a remote memory pool. By way of example, the first computing pool 101 and the second computing pool 102 are both hosts that are primarily computing resources, the first computing pool 101 being referred to as a local host and the second computing pool 102 being referred to as a remote host.

As another example, fig. 2 is a schematic diagram of another intensive cloud computing system 100 provided by an embodiment of the present application. As shown in fig. 2, the intensive cloud computing system 100 further includes a mirror repository 104 on the basis of fig. 1. The mirror repository 104 may be deployed in the first computing pool 101, the second computing pool 102, or the first storage pool 103, or may be deployed independent of the first computing pool 101, the second computing pool 102, and the first storage pool 103, and fig. 2 illustrates that the mirror repository 104 is deployed independent of the first computing pool 101, the second computing pool 102, and the first storage pool 103. The first storage pool 103 is used to store various information needed to create virtual units of applications, which may be distributed among different storage media. Optionally, the first storage pool 103 is used to store an application image, the image repository 104 is a distributed image repository, and the image repository 104 is used to store a correspondence (for example, referred to as a first correspondence) between indication information of the application image and a storage location of the application image in the first storage pool 103. When the management platform 11 creates a virtual unit of an application, the management platform 11 determines a storage location of the application image according to the indication information of the application image of the application and the first corresponding relationship stored in the image repository 104, and the management platform 11 obtains the application image from the first storage pool 103 according to the storage location of the application image, and creates the virtual unit based on the application image.

The intensive cloud computing system shown in fig. 1 and fig. 2 is only used for example, and is not used for limiting the technical scheme of the embodiment of the present application. In the implementation process, the number of computing pools and storage pools in the intensive cloud computing system can be configured according to the needs, and the number and types of storage media in the storage pools can be configured according to the needs, which is not limited by the embodiment of the present application.

The above is an introduction to the application scenario of the present application, and the following describes an embodiment of the virtual unit starting method of the present application.

The virtual unit starting method provided by the embodiment of the application is applied to the management platform in the intensive cloud computing system, and the virtual unit starting method is executed by the management platform. The intensive cloud computing system further includes a first computing pool in which the management platform may be deployed. Optionally, the intensive cloud computing system further includes a first storage pool and a second computing pool, where the first storage pool includes at least one of a memory pool and an external storage pool, and the memory pool and the external storage pool may be heterogeneous storage pools. The first computing pool, the second computing pool and the first storage pool are interconnected, the first storage pool is used for storing a snapshot of a memory of a virtual unit of the first application, a snapshot of the virtual unit of the first application and an application image of the first application, and a storage position of the information of the first application in the first storage pool is determined according to importance, use frequency, starting requirements and the like of the first application. The intensive cloud computing system may further include a mirror repository for storing a correspondence of indication information of an application mirror to a storage location of the application mirror in the first storage pool. For example, as shown in fig. 1 or fig. 2, the intensive cloud computing system performs the virtual unit starting method by the management platform 11. As shown in fig. 3, the method includes the following steps S301 to S304.

S301, acquiring a starting requirement of the first application.

The first application is various possible applications for realizing resource isolation based on the virtual unit, for example, the first application is a server application, and the first application is a video application, an audio application, a mail application, a web page application or a microblog application. The virtual units may be containers, virtual machines, etc. that are computing units implemented based on virtualization technology.

Wherein the startup complaints of the first application include at least one of startup duration complaints and startup cost complaints. The start-up duration requirement may be that the start-up duration of the first application (i.e., the duration required to start up the first application) is less than a preset duration. The launch cost requirement may be that the launch cost of the first application (i.e., the cost required to launch the first application) is less than a preset cost. The starting time length of the first application is related to the starting time length of the virtual unit of the first application, and the starting cost of the first application is related to the starting cost of the virtual unit of the first application. In general, the starting of a virtual unit of an application means that the application is started, so the starting time of a first application is generally the starting time of the virtual unit of the first application, and the starting cost of the first application is generally the starting cost of the virtual unit of the first application. The starting time and the starting cost of the virtual unit of the first application are related to the starting mode of the virtual unit of the first application, storage positions of related information such as snapshots, application images and the like. For example, if a reference unit snapshot C0 of the first application (i.e., a snapshot of a reference virtual unit of the first application) is stored in a certain storage medium a, and one virtual unit of the first application (for example, referred to as a first virtual unit) is cold-started according to the reference unit snapshot C0, the starting time period of the first virtual unit depends on the time period of creating the first virtual unit, the time period of pulling the reference unit snapshot C0 from the storage medium a, and the like, and the starting cost of the first virtual unit depends on the cost of storing the reference unit snapshot C0 in the storage medium a.

In the embodiment of the present application, the starting requirement of the first application may be input to the management platform by a management user (for example, a development user of the first application, and a management user of the intensive cloud computing system), or may be determined by the management platform according to attribute information of the first application. In one embodiment, the management platform is provided with a user interface through which a management user interacts with the management platform, the management user inputs start-up appeal information to the management platform through the user interface, the management platform obtains the start-up appeal information input by the management user, and the start-up appeal information includes start-up appeal of the first application, wherein the user interface may be a User Interface (UI) interface. In another embodiment, the management platform obtains attribute information such as importance, use frequency, type and the like of the first application, and determines a start requirement of the first application according to the attribute information of the first application. For example, the startup duration of applications of higher importance, applications of higher frequency of use, and the like needs to be shorter.

S302, at least one set of starting measurement information corresponding to the target application is obtained, the at least one set of starting measurement information corresponds to at least one starting scheme, and each set of starting measurement information in the at least one set of starting measurement information is used for representing starting performance of the target application in the intensive cloud computing system based on the corresponding starting scheme, and the target application is matched with the first application.

The management platform may obtain at least one set of starting measurement information corresponding to the target application, where the at least one set of starting measurement information corresponds to at least one starting scheme, each set of starting measurement information is obtained by performing a starting test on the target application in an intensive cloud computing system (e.g., the intensive cloud computing system 100 shown in fig. 1 or fig. 2) according to the corresponding starting scheme, each set of starting measurement information is used to characterize starting performance of starting the target application in the intensive cloud computing system based on the corresponding starting scheme, and each set of starting measurement information includes at least one of a measured starting duration and a measured starting cost.

Wherein the at least one initiation scheme is pre-established, e.g. pre-established by a management platform or manually established and entered into the management platform, the management platform may be provided with a user interface through which a user may enter the initiation scheme into the management platform. Each of the at least one startup scheme includes a startup mode, which may be a hot startup or a cold startup, and a storage policy for storing snapshots, file systems, application images, etc. required to start the virtual unit, e.g., the storage policy includes storing each of the snapshots, the file systems, the application images, etc. in which storage media (e.g., which storage media in a memory pool the snapshots are stored in, which storage media in an external memory pool the application images are stored in, etc.), any combination of the startup mode and any storage policy may constitute one startup scheme. Optionally, the at least one start-up scheme includes at least one of: a first storage pool-based warm boot scheme, a first storage pool-based cold boot scheme, and a second computing pool-based cold boot scheme. The first computing pool, the second computing pool and the first storage pool are interconnected, and the first storage pool comprises at least one of a memory pool and an external memory pool. The measured starting time and the measured starting cost of the target application are related to the starting mode of the target application, the snapshot related to the target application, the storage medium where the information such as the application image is located, the storage position of the information related to the target application in the first storage pool and the like. For example, the hot start scheme based on the first storage pool is a start scheme based on a memory snapshot (for example, a snapshot of a memory of a virtual unit) stored in the first storage pool, and according to different storage media where the memory snapshot is located, the start duration and the start cost of the hot start scheme are different; the cold start scheme based on the first storage pool is based on a start scheme of a virtual unit snapshot (i.e. a snapshot of a virtual unit) stored in the first storage pool, and according to different storage media where the virtual unit snapshot is located, the start duration and the start cost of the cold start scheme are different; the cold start scheme based on the second computing pool is a start scheme based on virtual units running in the second computing pool.

In an alternative embodiment, the management platform performs a start test on the target application in the intensive cloud computing system according to each start scheme in the at least one start scheme to obtain a set of start measurement information corresponding to each start scheme, thereby obtaining at least one set of start measurement information corresponding to the at least one start scheme one to one. In a particular embodiment, for each of the at least one start-up scenario: and the management platform performs starting test on the target application in the intensive cloud computing system according to each starting scheme, and in the starting test process, the management platform counts the starting time and the starting cost of the target application to obtain the measured starting time and the measured starting cost corresponding to each starting scheme, namely, a group of starting measurement information corresponding to each starting scheme. Taking as an example the start-up test of a target application in the intensive cloud computing system 100 shown in fig. 1 or 2. For example, the management platform 11 prepares k start schemes 1 to k in advance, where k is a positive integer. The start-up scheme 1 may be: based on the memory snapshot stored in the first storage medium 311 and the hot-start scheme of the file system stored in the second storage medium 321. The start-up scheme 2 may be: based on the memory snapshot stored in the first storage medium 312 and the hot start scheme of the file system stored in the second storage medium 321. The start scheme 3 may be: based on the memory snapshot stored in the first storage medium 313 and the hot-start scheme of the file system stored in the second storage medium 322. The start scheme 4 may be: a cold start scheme based on a virtual unit snapshot of a file system stored in second storage medium 321. The startup scheme 5 may be a cold startup scheme based on virtual units running in the second computing pool 102. By analogy, any combination of a startup scheme and any storage policy may constitute a startup scheme. For example, the management platform 11 performs a start test on the target application in the intensive cloud computing system 100 according to the start scheme 1, to obtain a set of start measurement information 1 corresponding to the start scheme 1. The management platform 11 performs a starting test on the target application in the intensive cloud computing system 100 according to the starting scheme 2, and obtains a set of starting measurement information 2 corresponding to the starting scheme 2. And so on, the management platform 11 performs a starting test on the target application in the intensive cloud computing system 100 according to the starting scheme k, so as to obtain a group of starting measurement information k corresponding to the starting scheme k. The management platform 11 obtains the starting measurement information 1-k corresponding to the starting schemes 1-k one by performing the starting test on the target application. Each set of the start-up measurement information 1 to k includes at least one of a measurement start-up duration and a measurement start-up cost.

In an embodiment of the present application, the matching of the target application with the first application includes at least one of: the target application is a first application, the scale of the target application is matched with the scale of the first application, the size of the application image of the target application is matched with the size of the application image of the first application, and the type of the target application is matched with the type of the first application. Illustratively, the matching of the size of the target application to the size of the first application includes: the size of the sub-functions of the target application is comparable to the size of the sub-functions of the first application (e.g., the number of sub-functions of the target application differs from the number of sub-functions of the first application by less than a preset number), and the architecture of the target application is comparable to the architecture of the first application. The architecture of any application is for example: the any application includes which primary functions (or primary functions), which secondary functions are included under each primary function, which tertiary functions are included under each secondary function, and so on. The size matching of the application image of the target application with the size of the application image of the first application includes: the difference between the size of the application image of the target application and the size of the application image of the first application is smaller than a preset difference. The matching of the type of the target application with the type of the first application includes: the type of the target application is the same as the type of the first application, e.g. both the target application and the first application are video-type applications. In one embodiment, the first application is allowed to run in a test mode, the management platform uses the first application as a target application (the target application is the first application), and the management platform performs a starting test on the first application in the intensive cloud computing system according to each starting scheme in at least one starting scheme to obtain a set of starting measurement information corresponding to each starting scheme. In another embodiment, the first application is not allowed to run in a test mode, the management platform determines a target application matched with the first application according to the scale of the first application, the size of an application image of the first application, the type of the first application and the like, and the management platform performs a starting test on the target application in the intensive cloud computing system according to each starting scheme in at least one starting scheme to obtain a set of starting measurement information corresponding to each starting scheme.

S303, determining a first starting scheme according to the starting complaint of the first application and the at least one set of starting measurement information, wherein the at least one starting scheme comprises the first starting scheme.

The first starting scheme is one starting scheme with starting performance matched with the starting requirement of the first application, and the starting performance of the first starting scheme meets the starting requirement of the first application. For example, the start-up complaint of the first application includes at least one of a start-up complaint and a start-up cost complaint, the start-up complaint being that the start-up time of the first application is less than a preset time, the start-up complaint action in chief being that the start-up cost of the first application is less than a preset cost, and the corresponding start-up performance of the first start-up scheme satisfying the start-up complaint of the first application includes at least one of: the measurement starting time length corresponding to the first starting scheme is smaller than the preset time length, and the measurement starting cost corresponding to the first starting scheme is smaller than the preset cost.

In an alternative embodiment, the at least one set of start measurement information corresponds to the at least one start scheme one by one, each set of start measurement information is used for characterizing a start performance of a target application started in the intensive cloud computing system based on the corresponding start scheme, the management platform determines a start scheme with the start performance meeting a start requirement of the first application in the at least one start scheme according to the at least one set of start measurement information, and the management platform determines the first start scheme in the start schemes with the start performance meeting the start requirement of the first application. In one embodiment, only one of the at least one start-up scenario has start-up performance that meets the start-up requirements of the first application, and the management platform determines the one start-up scenario as the first start-up scenario. In another embodiment, the starting performance of a plurality of starting schemes in the at least one starting scheme meets the starting requirement of the first application, and the management platform determines one starting scheme in the plurality of starting schemes as the first starting scheme. For example, the management platform determines any one of the plurality of start-up schemes as the first start-up scheme, or the management platform determines a start-up scheme having the best start-up performance among the plurality of start-up schemes as the first start-up scheme. Wherein the starting scheme with optimal starting performance meets at least one of the following: the measurement starting time is minimum and the measurement starting cost is minimum. For example, the management platform determines a starting scheme with the smallest measured starting time length and the smallest measured starting cost among the plurality of starting schemes as a first starting scheme. As previously described, the at least one startup scheme includes at least one of a first storage pool-based warm startup scheme, a first storage pool-based cold startup scheme, and a second computing pool-based cold startup scheme, and thus the first startup scheme includes any one of: a first storage pool-based warm boot scheme, a first storage pool-based cold boot scheme, and a second computing pool-based cold boot scheme.

As an example, taking the example of performing a start test on a target application in the intensive cloud computing system 100 shown in fig. 1 or fig. 2 as an illustration, in S302, the management platform 11 obtains start measurement information 1 to k corresponding to the start schemes 1 to k one by one, and in S303, the management platform 11 determines, according to the start measurement information 1 to k, a start scheme whose start performance satisfies a start requirement of the first application in the start schemes 1 to k. In one embodiment, the starting performance of the starting scheme 1 meets the starting requirement of the first application, the starting performance of each of the starting schemes 2 to k does not meet the starting requirement of the first application, and the management platform 11 determines the starting scheme 1 as the first starting scheme. In another embodiment, the starting performance of the starting schemes 1 to 3 all meet the starting requirement of the first application, and the starting performance of the starting schemes 4 to k all do not meet the starting requirement of the first application; the management platform 11 determines any one of the startup schemes 1 to 3 (for example, the startup scheme 1) as a first startup scheme; or, among the starting schemes 1 to 3, the starting scheme 1 has the optimal starting performance, and the management platform 11 determines the starting scheme 1 (i.e., the starting scheme having the optimal starting performance) as the first starting scheme.

S304, starting a first virtual unit of the first application in the first computing pool according to a first starting scheme.

Wherein the first virtual unit is a computing unit implemented based on virtualization technology, such as a container, a virtual machine, etc.

After the management platform determines the first starting scheme, the management platform deploys the first starting scheme in the intensive cloud computing system according to the first application, for example, the management platform stores information such as a snapshot, an application mirror image and the like required by starting a virtual unit of the first application based on the first starting scheme in the intensive cloud computing system. When the management platform receives a starting request for starting the first application (or starting a virtual unit for starting the first application), the management unit starts the first virtual unit of the first application in the first computing pool according to a first starting scheme. Wherein the first starting scheme comprises any one of the following: a first storage pool-based warm boot scheme, a first storage pool-based cold boot scheme, and a second computing pool-based cold boot scheme. According to the difference of the first starting scheme, the management platform starts the first virtual unit in different implementation modes. Taking a first startup scheme as an example, the first startup scheme is a hot startup scheme based on a first storage pool, a cold startup scheme based on the first storage pool or a cold startup scheme based on a second computing pool, three embodiments describe an implementation manner in which the management platform starts the first virtual unit according to the first startup scheme.

First embodiment: the first starting scheme is a hot starting scheme based on a first storage pool, wherein a reference memory snapshot and a reference file system are stored in the first storage pool, the reference memory snapshot is obtained by snapshot of the memory of a reference virtual unit of a first application, the reference file system is a file system of the reference virtual unit, data in the reference memory snapshot and data in the reference file system are both read-only data, and the reference memory snapshot and the reference file system are both allowed to be read only and not written (i.e. are not allowed to be modified). The first computing pool includes a first virtual unit, where a memory of the first virtual unit has a mapping relationship with the reference memory snapshot (or the memory of the first virtual unit is associated with the reference memory snapshot), and a file system of the first virtual unit has a mapping relationship with the reference file system (or the file system of the first virtual unit is associated with the reference file system). The management platform starts a first virtual unit in a first computing pool according to a first starting scheme, and the management platform comprises the following steps: the management platform creates a first memory branch in a first computing pool according to the reference memory snapshot, and the management platform creates a first read-write layer in the first computing pool according to the reference file system. For example, the first computing pool includes a memory space in which the management platform creates a first memory branch and a memory space in which the management platform creates a first read-write layer.

The first memory branch is configured to store memory data that changes relative to the reference memory snapshot during operation of the first virtual unit (i.e., memory data that changes relative to the reference memory snapshot in a memory of the first virtual unit), where the memory data of the first virtual unit (i.e., data in the memory of the first virtual unit) may be determined according to the data in the reference memory snapshot and the memory data stored in the first memory branch. The first read-write layer is used for storing file data which changes relative to the reference file system in the running process of the first virtual unit (namely, file data which changes relative to the reference file system in the file system of the first virtual unit), and the file system of the first virtual unit is determined according to the file data in the reference file system and the file data stored in the first read-write layer. The reference virtual unit of the first application is a virtual unit which is deployed with the first application and is started, and the reference memory snapshot of the reference virtual unit is obtained by snapshot of the memory of the reference virtual unit at a certain moment after the starting of the reference virtual unit. The first memory pool may include a memory pool in which the reference memory snapshot may be stored and a memory pool in which the reference file system may be stored. The reference memory snapshot is stored in the memory pool or the external memory pool, the reference memory snapshot is specifically stored in which storage medium in the memory pool or in which storage medium in the external memory pool, the reference file system is stored in the memory pool or in which storage medium in the external memory pool, and the reference file system is specifically stored in which storage medium in the memory pool or in which storage medium in the external memory pool, which are determined according to the first starting scheme. In addition, the mapping relationship between the memory of the first virtual unit and the reference memory snapshot may include: the memory address of the reference memory snapshot is stored in the first virtual unit, for example, the memory address of the reference memory snapshot is stored in the memory of the first virtual unit. Because the memory of the first virtual unit has a mapping relationship with the reference memory snapshot, when the memory of the first virtual unit is accessed, the reference memory snapshot can be accessed according to the memory address of the reference memory snapshot, that is, the process of accessing the memory of the first virtual unit includes accessing the reference memory snapshot. Similarly, the mapping relationship between the file system of the first virtual unit and the reference file system may include: the first virtual unit stores a storage address of the reference file system, for example, a memory of the first virtual unit stores a storage address of the reference file system. Since the file system of the first virtual unit has a mapping relation with the reference file system, the reference file system can be accessed according to the storage address of the reference file system when the file system of the first virtual unit is accessed, that is, the actual access to the file system of the first virtual unit includes accessing the reference file system.

As one example, the first virtual unit U1 is started in the intensive cloud computing system 100 shown in fig. 2. Fig. 4 is a schematic diagram of starting a first virtual unit U1 in a first computing pool 101 according to a first starting scheme (a hot starting scheme based on a first storage pool 103) provided in an embodiment of the present application. As shown in fig. 4, a reference virtual unit U0 of the first application is running in a first computing pool 101, a first storage pool 103 includes a memory pool 31 and a memory pool 32, a reference memory snapshot P0 is stored in the memory pool 31, a reference file system F0 is stored in the memory pool 32, the first computing pool 101 includes a first virtual unit U1, a mapping relationship exists between a memory M1 of the first virtual unit U1 and the reference memory snapshot P0, and a mapping relationship exists between a file system F1 of the first virtual unit U1 and the reference file system F0. When the management platform 11 receives a start request for starting the first application, the management platform 11 creates a first memory branch B1 in the memory space in the first computing pool 101 according to the reference memory snapshot P0, and the management platform 11 creates a first read-write layer R1 in the memory space in the first computing pool 101 according to the reference file system F0. The management platform 11 invokes the memory M1 and the file system F1 of the first virtual unit U1 by creating the first memory branch B1 and the first read-write layer R1, thereby starting the first virtual unit U1. The first memory branch B1 is configured to store, after the first virtual unit U1 is started, memory data that changes in the memory M1 of the first virtual unit U1 relative to the reference memory snapshot P0 during an operation process of the first virtual unit U1, where the data in the memory M1 of the first virtual unit U1 is determined according to the data in the reference memory snapshot P0 and the memory data stored in the first memory branch B1, and accessing the memory M1 of the first virtual unit U1 includes accessing the reference memory snapshot P0 and the first memory branch B1. The first read-write layer R1 is configured to store file data that changes in the file system F1 of the first virtual unit U1 relative to the reference file system F0 in the operation process of the first virtual unit U1 after the first virtual unit U1 is started, where accessing the file system F1 of the first virtual unit U1 includes accessing the reference file system F0 and the first read-write layer R1, where the file system F1 of the first virtual unit U1 is determined according to the file data in the reference file system F0 and the file data stored in the first read-write layer R1. The reference virtual unit U0 is a virtual unit deployed with a first application and started, the reference memory snapshot P0 is obtained by taking a snapshot of the memory of the reference virtual unit U0 at a certain time after the reference virtual unit U0 is started, and the reference file system F0 is a file system of the reference virtual unit U0. Optionally, the data in the reference memory snapshot P0 and the data in the reference file system F0 are both read-only data, the reference memory snapshot P0 and the reference file system F0 are both read-only and not modified, the memory space in the first computing pool 101 may further include a reference memory branch B0 (not shown in fig. 4), the memory space in the first computing pool 101 may further include a reference read-write layer R0 (not shown in fig. 4), the reference memory branch B0 is used for storing the memory data that changes in the memory of the reference virtual unit U0 relative to the reference memory snapshot P0 during the operation of the reference virtual unit U0, the reference read-write layer R0 is used for storing the memory data that changes in the memory of the reference virtual unit U0 during the operation of the reference virtual unit U0, the file data in the file system of the reference virtual unit U0 that changes with respect to the reference file system F0 is not limited in this embodiment of the present application.

It should be noted that, fig. 4 only illustrates a portion of the enhanced cloud computing system 100 related to the first embodiment for brevity, for example, the second computing pool 103 is not illustrated in fig. 4. In addition, fig. 4 shows only that the reference memory snapshot P0 is stored in the memory pool 31, that the reference file system F0 is stored in the external memory pool 32, and that it is not shown in which storage medium in the memory pool 31 the reference memory snapshot P0 is stored in particular, and in which storage medium in the external memory pool 32 the reference file system F0 is stored in particular, and in which storage medium the reference memory snapshot P0 and the reference file system F0 are located in particular, are determined according to the first startup scheme. Other parts not shown in fig. 4 may refer to fig. 1 and 2, and are not described here.

Optionally, in this first embodiment, the management platform stores in advance a reference memory snapshot of the reference virtual unit of the first application in the first memory pool before starting the first virtual unit in the first computing pool according to the first starting scheme. The reference memory snapshot may be stored by the management platform in the first memory pool, or may be stored by another device in the first memory pool. In one embodiment, the reference virtual unit operates in a first computing pool, and the management platform obtains a reference memory snapshot of the reference virtual unit during operation of the reference virtual unit, and stores the reference memory snapshot in the first computing pool. Optionally, the first application is a common application, after the reference virtual unit of the first application is started normally, the management platform snapshots the memory of the reference virtual unit, obtains a reference memory snapshot of the reference virtual unit, and the first starting scheme may include a storage policy of the reference memory snapshot (i.e., which storage medium of the first storage pool the reference memory snapshot is stored in), where the management platform stores the reference memory snapshot into the first storage pool according to the storage policy. In one embodiment, a plurality of applications are deployed in the intensive cloud computing system, the first application is one application of the plurality of applications, for each of the plurality of applications, the management platform obtains a reference memory snapshot of a reference virtual unit of each of the plurality of applications after the reference virtual unit is normally started, and stores the reference memory snapshot in a first storage pool. Wherein, whether any application is a common application can be determined according to the use frequency of the application.

Optionally, in this first embodiment, the first virtual unit is created in the first computing pool in advance before the management platform starts the first virtual unit in the first computing pool according to the first start-up scheme. The first virtual unit may be created by the management platform in the first computing pool, or by other devices in the first computing pool. In one embodiment, the management platform obtains an application image of a first application, and creates a first virtual unit in a first computing pool according to the application image of the first application. The intensive cloud computing system provided by the embodiment of the application comprises a mirror image warehouse, wherein an application mirror image of a first application is stored in a first storage pool, the mirror image warehouse stores the corresponding relation between the indication information of the application mirror image and the storage position of the application mirror image (namely, the storage position of the application mirror image in the first storage pool), a management platform determines the storage position of the application mirror image from the mirror image warehouse according to the indication information of the application mirror image of the first application, and the management platform acquires the application mirror image from the first storage pool according to the storage position of the application mirror image and creates a first virtual unit in the first computing pool according to the application mirror image. After the management platform creates the first virtual unit in the first computing pool, the management platform establishes a mapping relationship between the memory of the first virtual unit and the reference memory snapshot of the reference virtual unit of the first application, and establishes a mapping relationship between the file system of the first virtual unit and the reference file system. In addition, before the management platform creates the first virtual unit in the first computing pool, the management platform prepares related components required for creating the virtual unit of the first application in advance, the management platform creates the first virtual unit based on the related components, and since the management platform prepares related components required for creating the virtual unit in advance, the management platform can directly use the related components when creating the first virtual unit, thereby helping to increase the speed of creating the first virtual unit. By way of example, these related components include control groups (cgroups), namespaces (namespaces), and the like.

As an example, please continue with fig. 4, before the management platform 11 creates the first virtual unit U1 in the first computing pool 101, the management platform 11 prepares related components required for creating the virtual unit of the first application in advance. As shown in fig. 4, the external memory pool 32 stores an application image 1 of a first application, the image repository 104 stores a correspondence (not shown in fig. 4) between indication information of the application image 1 and a storage location of the application image 1, when the management platform 11 creates a virtual unit (for example, a first virtual unit U1) of the first application, the management platform 11 determines the storage location of the application image 1 from the image repository 104 according to the indication information of the application image 1, the management platform 11 obtains the application image 1 from the external memory pool 32 according to the storage location of the application image 1, and the management platform 11 creates the first virtual unit U1 in the first computing pool 101 according to the application image 1. After the management platform 11 creates the first virtual unit U1, the management platform 11 associates the memory M1 of the first virtual unit U1 with the reference memory snapshot P0, and when accessing the memory of the first virtual unit U1, the reference memory snapshot P0 may be accessed according to the memory address of the reference memory snapshot P0, that is, the process of accessing the memory M1 of the first virtual unit U1 includes accessing the reference memory snapshot P0.

Second embodiment: the first starting scheme is a cold starting scheme based on a first storage pool, reference unit snapshots are stored in the first storage pool, the reference unit snapshots are obtained by snapshot of reference virtual units of a first application, and the management platform starts the first virtual units in a first computing pool according to the first starting scheme, and the method comprises the following steps: the management platform creates a first virtual unit in a first computing pool according to the reference unit snapshot and starts the first virtual unit. Illustratively, the management platform creates a first virtual unit in the first computing pool from the reference unit snapshot based on checkpoint/restore (checkpoint/restore in userspace, CRIU) techniques of the user space. In one embodiment, the first virtual unit is a container, and the management platform creates the container and starts the container based on CRIU technologies. The implementation process of creating the first virtual unit according to the reference unit snapshot and starting the first virtual unit by the management platform may refer to the implementation process of creating the container according to the container snapshot in the related art, which is not described herein.

The reference virtual unit of the first application is a virtual unit which is deployed with the first application and is started, the reference virtual unit snapshot is obtained by snapshot the reference virtual unit at a certain moment after the reference virtual unit is started, and the reference unit snapshot comprises memory data of the reference virtual unit and data in a file system of the reference unit snapshot. The first memory pool may include a memory pool and a memory pool, the reference cell snapshot being stored in the memory pool or the memory pool, the reference cell snapshot being stored in particular in which storage medium of the memory pool or in which storage medium of the memory pool, the reference cell snapshot being determined according to the first startup scheme.

As one example, the first virtual unit U1 is started in the intensive cloud computing system 100 shown in fig. 2. Fig. 5 is a schematic diagram of starting a first virtual unit U1 in a first computing pool 101 according to another first starting scheme (a cold starting scheme based on a first storage pool 103) provided by an embodiment of the present application. As shown in fig. 5, the reference virtual unit U0 of the first application runs in the first computing pool 101, and the first memory pool 103 includes a memory pool 31 and a memory pool 32, and the memory pool 31 stores a reference unit snapshot C0. When the management platform 11 receives a start request for starting the first application, the management platform 11 creates a first virtual unit U1 in the first computing pool 101 from the reference unit snapshot C0 and starts the first virtual unit U1. The reference unit snapshot C0 is obtained by taking a snapshot of the reference virtual unit U0 at a certain time after the reference virtual unit U0 is started, where the reference unit snapshot C0 includes memory data of the reference virtual unit U0 and data in a file system of the reference virtual unit U0, which is not limited in the embodiment of the present application. It should be noted that, fig. 5 only illustrates a portion of the enhanced cloud computing system 100 related to the second embodiment for brevity, for example, the second computing pool 103 is not illustrated in fig. 5. In addition, fig. 5 only shows that the reference unit snapshot C0 is stored in the memory pool 31 for brevity, and does not show in which storage medium in the memory pool 31 the reference unit snapshot C0 is specifically stored, the storage medium in which the reference unit snapshot C0 is specifically located is determined according to the first startup scheme. Other parts not shown in fig. 5 may refer to fig. 1 and 2, and are not described here.

Optionally, in this second embodiment, before the management platform starts the first virtual unit in the first computing pool according to the first start-up scheme, a reference unit snapshot of the reference virtual unit of the first application is stored in the first storage pool in advance. The reference unit snapshot of the reference virtual unit may be stored by the management platform in the first storage pool, or may be stored by another device in the first storage pool. In one embodiment, the reference virtual unit is operated in a first computing pool, and the management platform acquires a reference unit snapshot of the reference virtual unit in the process of operating the reference virtual unit, and stores the reference unit snapshot in the first storage pool. Optionally, the first application is a common application, after the reference virtual unit of the first application is normally started, the management platform snapshots the reference virtual unit based on CRIU technology, obtains a reference unit snapshot of the reference virtual unit, and the first starting scheme may include a storage policy of the reference unit snapshot, where the management platform stores the reference unit snapshot into the first storage pool according to the storage policy. In one embodiment, a plurality of applications are deployed in the intensive cloud computing system, the first application is one application of the plurality of applications, for each of the plurality of applications, the management platform obtains a reference internal unit snapshot of a reference virtual unit of each of the plurality of applications after the reference virtual unit is normally started, and stores the reference internal unit snapshot in a first storage pool.

Third embodiment: the first starting scheme is a cold starting scheme based on a second computing pool, a second virtual unit is operated in the second computing pool, the configuration of the second virtual unit is the same as that of the first virtual unit, and the management platform starts the first virtual unit in the first computing pool according to the first starting scheme, and the method comprises the following steps: the management platform creates a first virtual unit in the first computing pool according to the second virtual unit and starts the first virtual unit. In one embodiment, the management platform creates a first virtual unit in the first computing pool according to the configuration of the second virtual unit, e.g., the management platform creates the first virtual unit according to cgroups, namespace or the like of the second virtual unit, including creating the base component of the first virtual unit and creating the main process of the first virtual unit. After the management platform creates the first virtual unit, the management platform creates a second memory branch in the first computing pool according to the memory of the second virtual unit, and creates a second read-write layer in the first computing pool according to the file system of the second virtual unit so as to start the first virtual unit. For example, the first computing pool includes a memory space in which the management platform creates a second memory branch and a memory space in which the management platform creates a second read-write layer.

The second memory branch is configured to store memory data that changes relative to a memory of the second virtual unit during an operation of the first virtual unit (i.e., data that changes relative to a memory of the second virtual unit in a memory of the first virtual unit), where the memory data of the first virtual unit may be determined according to the memory data of the second virtual unit and the memory data stored in the second memory branch. The second read-write layer is used for storing file data which changes relative to the file system of the second virtual unit in the operation process of the first virtual unit (namely, file data which changes relative to the file system of the second virtual unit in the file system of the first virtual unit), and the file system of the first virtual unit is determined according to the file system of the second virtual unit and the file data stored in the second read-write layer. Wherein the second virtual unit may be a virtual unit started in the second computing pool based on the first embodiment or the second embodiment, and the configuration of the second virtual unit is the same as that of the first virtual unit and includes: metadata (metadata) of the second virtual unit is the same as metadata of the first virtual unit, and description of the second virtual unit is the same as description of the first virtual unit. For example, the attribute of the second virtual unit is the same as the attribute of the first virtual unit, for example, the application image corresponding to the second virtual unit is the same as the application image corresponding to the first virtual unit (for example, the application image corresponding to the second virtual unit and the application image corresponding to the first virtual unit are both application images of the first application). By way of example, the YAML file of the second virtual unit is the same as the YAML file of the first virtual unit.

As one example, the first virtual unit U1 is started in the intensive cloud computing system 100 shown in fig. 1 or fig. 2. Fig. 6 is a schematic diagram of starting a first virtual unit U1 in a first computing pool 101 according to a first starting scheme (a cold starting scheme based on a second computing pool 102) according to an embodiment of the present application. As shown in fig. 6, a second virtual unit U2 is operated in the second computing pool 102, and the configuration of the second virtual unit U2 is the same as that of the first virtual unit U1. When the management platform 11 receives a start request for starting the first application, the management platform 11 creates a first virtual unit U1 in the first computing pool 101 according to the second virtual unit U2, the management platform 11 creates a second memory branch B2 in a memory space in the first computing pool 101 according to a memory M2 of the second virtual unit U2, and the management platform 11 creates a second read-write layer R2 in an external memory space in the first computing pool 101 according to a file system F2 of the second virtual unit U2. The management platform 11 calls the memory M1 of the first virtual unit U1 and the file system F1 of the first virtual unit U1 by creating the second memory branch B2 and the second read-write layer R2, thereby starting the first virtual unit U1. The second memory branch B2 is configured to store, after the first virtual unit U1 is started, memory data that changes in the memory M1 of the first virtual unit U1 relative to the memory M2 of the second virtual unit U2 in the operation process of the first virtual unit U1, where the data in the memory M1 of the first virtual unit U1 is determined according to the data in the memory M2 of the second virtual unit U2 and the memory data stored in the second memory branch B2, and accessing the memory M1 of the first virtual unit U1 includes accessing the memory M2 of the second virtual unit U2 and the second memory branch B2. The second read-write layer R2 is configured to store file data that changes in the file system F1 of the first virtual unit U1 relative to the file system F2 of the second virtual unit U2 in the operation process of the first virtual unit U1 after the first virtual unit U1 is started, where the file system F1 of the first virtual unit U1 is determined according to the file system F2 of the second virtual unit U2 and the file data stored in the second read-write layer R2, and accessing the file system F1 of the first virtual unit U1 includes accessing the file system F2 of the second virtual unit U2 and the second read-write layer R2. It should be noted that, fig. 6 only illustrates portions of the enhanced cloud computing system 100 related to the third embodiment, for example, the first storage pool 102 and the mirror repository 104 are not illustrated in fig. 6. Other parts not shown in fig. 6 may refer to fig. 1 and 2, and are not described here.

In an alternative embodiment, the management platform operates in a first computing pool, which from the perspective of the management platform may be referred to as a local computing pool, a second computing pool may be referred to as a remote computing pool, and a first storage pool may be referred to as a remote storage pool. The above-mentioned first storage pool-based hot start scheme may be referred to as a remote storage pool-based hot start scheme, the above-mentioned first storage pool-based cold start scheme may be referred to as a remote storage pool-based cold start scheme, and the above-mentioned second computing pool-based cold start scheme may be referred to as a remote computing pool-based cold start scheme, which is not limited in this embodiment of the present application.

In summary, according to the technical solution provided by the embodiment of the present application, at least one set of starting measurement information corresponds to at least one starting solution, each set of starting measurement information is used to characterize the starting performance of a target application started in an intensive cloud computing system based on the corresponding starting solution, a management platform in the intensive cloud computing system determines a first starting solution according to the starting complaint of the first application and the at least one set of starting measurement information (i.e., the management platform determines the first starting solution according to the starting complaint of the first application and the starting performance of the at least one starting solution), and starts a virtual unit of the first application in a first computing pool according to the first starting solution. The management platform automatically selects the starting scheme according to the starting requirement of the first application, so that the usability of the virtual unit starting scheme can be improved.

The foregoing is an introduction to the method embodiments of the present application and the following description of the apparatus embodiments of the present application. The apparatus of the present application may be used to perform the method of the present application. For details not disclosed in the device embodiments of the present application, please refer to the method embodiments.

Referring to fig. 7, a schematic diagram of a virtual unit starting apparatus 700 according to an embodiment of the application is shown. The virtual unit activation apparatus 700 is applied to a management platform in an intensive cloud computing system, for example, the virtual unit activation apparatus 700 is the management platform or a functional component in the management platform. The virtual unit activation apparatus 700 is configured to perform all or part of the steps in the method embodiment shown in fig. 3. The intensive cloud computing system further comprises a first computing pool. Referring to fig. 7, the virtual unit activation apparatus 700 includes an acquisition module 710, a determination module 720, and an activation module 730.

The obtaining module 710 is configured to obtain a start-up requirement of the first application, and obtain at least one set of start-up measurement information corresponding to the target application, where each set of start-up measurement information in the at least one set of start-up measurement information is used to characterize a start-up performance of starting up the target application in the intensive cloud computing system based on the corresponding start-up scheme, and the target application is matched with the first application;

A determining module 720, configured to determine a first start-up scenario according to the start-up complaint of the first application and the at least one set of start-up measurement information, where the at least one start-up scenario includes the first start-up scenario;

A starting module 730, configured to start a first virtual unit of the first application in the first computing pool according to a first starting scheme.

Optionally, the first starting scheme includes any one of the following: a warm boot scheme based on the first storage pool; a cold start scheme based on the first storage pool; a cold start scheme based on the second computing pool. The first storage pool and the second computing pool are respectively interconnected with the first computing pool. The function of the start-up module 730 is different according to the first start-up scheme, and is described in three embodiments below.

First embodiment: the first starting scheme comprises a hot starting scheme based on a first storage pool, wherein a reference memory snapshot is stored in the first storage pool, the reference memory snapshot is obtained by snapshot of the memory of a reference virtual unit of a first application, and the first computing pool comprises a first virtual unit; the starting module 730 is configured to create a first memory branch in the first computing pool according to the reference memory snapshot, where the first memory branch is configured to store memory data that changes relative to the reference memory snapshot during operation of the first virtual unit.

Optionally, in the first embodiment, a reference file system is further stored in the first storage pool, where the reference file system is a file system of the reference virtual unit; the starting module 730 is further configured to create a first read-write layer in the first computing pool according to the reference file system, where the first read-write layer is configured to store file data that changes relative to the reference file system during operation of the first virtual unit.

Optionally, in the first embodiment, the obtaining module 710 is further configured to obtain, during operation of the reference virtual unit, a reference memory snapshot of the reference virtual unit before the starting module 730 starts the first virtual unit in the first computing pool according to the first starting scheme; with continued reference to fig. 7, the virtual unit activation apparatus 700 further includes: and the storage module 740 is configured to store the reference memory snapshot in the first memory pool.

Optionally, please continue to refer to fig. 7, in the first embodiment, the virtual unit starting apparatus 700 further includes: a creating module 750 is configured to create a first virtual unit in the first computing pool according to the application image of the first application before the starting module 730 starts the first virtual unit in the first computing pool according to the first starting scheme.

Second embodiment: the first starting scheme comprises a cold starting scheme based on a first storage pool, wherein a reference unit snapshot is stored in the first storage pool, and is obtained by snapshot of a reference virtual unit of a first application; a starting module 730 is configured to create and start a first virtual unit in the first computing pool according to the reference unit snapshot.

Optionally, in the second embodiment, the obtaining module 710 is further configured to obtain, during operation of the reference virtual unit, a reference unit snapshot of the reference virtual unit before the starting module 730 starts the first virtual unit in the first computing pool according to the first starting scheme;

With continued reference to fig. 7, the virtual unit activation apparatus 700 further includes: and a storage module 740, configured to store the reference unit snapshot in the first storage pool.

Optionally, the reference virtual unit runs in a first computing pool.

Third embodiment: the first starting scheme comprises a cold starting scheme based on a second computing pool, wherein a second virtual unit is operated in the second computing pool, and the configuration of the second virtual unit is the same as that of the first virtual unit; and a starting module 730, configured to create and start the first virtual unit in the first computing pool according to the second virtual unit.

Optionally, in the second embodiment, the starting module 730 is configured to create a second memory branch according to the memory of the second virtual unit in the first computing pool, where the second memory branch is used to store memory data that changes relative to the memory of the second virtual unit during the operation of the first virtual unit.

Optionally, in the second embodiment, the starting module 730 is configured to create a second read-write layer in the first computing pool according to the file system of the second virtual unit, where the second read-write layer is configured to store file data that changes relative to the file system of the second virtual unit during the operation of the first virtual unit.

Optionally, the intensive cloud computing system further includes a first storage pool, the first storage pool being interconnected with the first computing pool; the first storage pool is used for storing at least one of the following information of the first application: a snapshot of the memory of the virtual unit of the first application; a snapshot of virtual units of the first application; application mirroring of a first application.

Optionally, a storage location of the at least one piece of information of the first application in the first storage pool is determined according to at least one of the following indicators of the first application: importance, frequency of use, start-up requirements.

Optionally, the intensive cloud computing system further includes a mirror image repository, where the mirror image repository is configured to store a correspondence between indication information of an application mirror image and a storage location of the application mirror image in the first storage pool.

Optionally, the first storage pool includes at least one of a memory pool and a memory pool.

Optionally, the memory pool and the external memory pool satisfy at least one of:

the memory pool comprises at least two first storage media, and the types of the at least two first storage media are different;

The external memory pool includes at least two second storage media, the at least two second storage media being different in type.

Wherein the first storage medium and the second storage medium store data based on a differential algorithm, respectively.

Optionally, the matching of the target application with the first application includes at least one of: the target application is a first application; the scale of the target application is matched with the scale of the first application; the size of the application image of the target application is matched with the size of the application image of the first application; the type of the target application matches the type of the first application.

Optionally, the start-up complaint of the first application includes at least one of a start-up duration complaint and a start-up cost complaint; the start-up measurement information includes at least one of a measured start-up duration and a measured start-up cost.

Optionally, the obtaining module 710 is configured to perform a start test on the target application in the intensive cloud computing system according to each of the at least one start scheme, to obtain a set of start measurement information corresponding to each start scheme.

Optionally, the management platform is deployed in the first computing pool.

Optionally, the first virtual unit is a container or a virtual machine.

The acquisition module 710 may be configured to perform the relevant steps in S301, S302, and S304, and the functional implementation of the acquisition module 710 may refer to the relevant descriptions in S301, S302, and S304. The determining module 720 may be configured to perform S303 described above, and the functional implementation of the determining module 720 may refer to the relevant description in S303. The start-up module 730, the storage module 740 and the creation module 750 may be used to perform the relevant steps in S304, and the functional implementation of the start-up module 730, the storage module 740 and the creation module 750 may be referred to the relevant description in S304.

The acquisition module 710, the determination module 720, the start module 730, the storage module 740, and the creation module 750 may all be implemented by software, or may be implemented by hardware. The acquisition module 710 is described next as an example. Similarly, the implementation of the determining module 720, the starting module 730, the storing module 740, and the creating module 750 may refer to the implementation of the obtaining module 710.

Acquisition module 710 as an example of a software functional module, acquisition module 710 may include code that runs on a computing instance. Wherein the computing instance may comprise at least one of a physical host, a virtual machine, and a container. Further, the above-described computing examples may be one or more. For example, the acquisition module 710 may include code running on multiple hosts/virtual machines/containers. It should be noted that, multiple hosts/virtual machines/containers for running the code may be distributed in the same region (region), or may be distributed in different regions. Further, multiple hosts/virtual machines/containers for running the code may be distributed in the same availability zone (availability zone, AZ) or may be distributed in different AZs, each AZ comprising one data center or multiple geographically close data centers. Wherein typically a region may comprise a plurality of AZs.

Also, multiple hosts/virtual machines/containers for running the code may be distributed in the same virtual private cloud (virtual private cloud, VPC) or may be distributed in multiple VPCs. In general, one VPC is disposed in one region, and a communication gateway is disposed in each VPC for implementing inter-connection between VPCs in the same region and between VPCs in different regions.

Acquisition module 710 as an example of a hardware functional unit, the acquisition module 710 may include at least one computing device, or the acquisition module 710 may be a device implemented with an application-specific integrated circuit (ASIC) or a programmable logic device (programmable logic device, PLD), or the like. The PLD may be a complex program logic device (complex programmable logical device, CPLD), a field-programmable gate array (FPGA) GATE ARRAY, a general purpose array logic (GENERIC ARRAY logic, GAL), or any combination thereof.

The multiple computing devices included in the acquisition module 710 may be distributed in the same region or may be distributed in different regions. The plurality of computing devices included in the acquisition module 710 may be distributed among the same AZ or may be distributed among different AZ. Likewise, multiple computing devices included in the acquisition module 710 may be distributed in the same VPC or may be distributed among multiple VPCs. The plurality of computing devices may be any combination of computing devices ASIC, PLD, CPLD, FPGA and GAL, among others.

In summary, according to the technical solution provided by the embodiment of the present application, at least one set of start measurement information corresponds to at least one start solution, and each set of start measurement information is used to characterize the start performance of a target application started in an intensive cloud computing system based on the corresponding start solution, where a management platform in the intensive cloud computing system determines a first start solution according to the start complaint of the first application and the at least one set of start measurement information (i.e., the management platform determines the first start solution according to the start complaint of the first application and the start performance of the at least one start solution), and starts a virtual unit of the first application in a first computing pool according to the first start solution. The management platform automatically selects the starting scheme according to the starting requirement of the first application, so that the usability of the virtual unit starting scheme can be improved.

The embodiment of the application also provides a virtual unit starting device, which comprises a memory and a processor; the memory is used for storing a computer program; the processor is configured to execute a computer program stored in the memory to cause the virtual unit starting apparatus to perform all or part of the steps of the virtual unit starting method as provided in the above-described embodiment.

As an example, please refer to fig. 8, which illustrates a schematic diagram of another virtual unit starting apparatus 800 according to an embodiment of the present application. The virtual unit activation apparatus 800 may be a management platform in an intensive cloud computing system or a functional component in the management platform. As shown in fig. 8, the virtual unit initiation apparatus 800 includes a bus 802, a processor 804, a memory 806, and a communication interface 808. Communication between processor 804, memory 806, and communication interface 808 is via bus 802. It should be understood that embodiments of the present application do not limit the number of processors, memories in the virtual unit start apparatus 800.

Bus 802 may be a peripheral component interconnect (PERIPHERAL COMPONENT INTERCONNECT, PCI) bus, or an extended industry standard architecture (extended industry standard architecture, EISA) bus, among others. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, only one line is shown in fig. 8, but not only one bus or one type of bus. Bus 802 may include a path for transferring information between various components of virtual unit actuation apparatus 800 (e.g., memory 806, processor 804, communication interface 808).

The processor 804 may include any one or more of a central processing unit (central processing unit, CPU), a graphics processor (graphics processing unit, GPU), a Microprocessor (MP), or a digital signal processor (DIGITAL SIGNAL processor, DSP).

The memory 806 may include volatile memory (RAM), such as random access memory (random access memory). The processor 804 may also include non-volatile memory (ROM), such as read-only memory (ROM), flash memory, mechanical hard disk (HARD DISK DRIVE, HDD) or Solid State Disk (SSD), among others.

The memory 806 has stored therein executable program code that is executed by the processor 804 to implement the functions of the aforementioned acquisition module 710, determination module 720, start-up module 730, storage module 740, and creation module 750, respectively, to implement at least some of the steps of the virtual unit start-up method described above. That is, the memory 806 has stored thereon instructions for executing the virtual unit activation method described above.

The communication interface 808 enables communication between the virtual unit initiation apparatus 800 and other devices or communication networks using a transceiver module such as, but not limited to, a network interface card, transceiver, or the like.

The embodiment of the application also provides a cloud computing system, which comprises a computing pool and a storage pool, wherein the computing pool is interconnected with the storage pool, and the computing pool comprises a virtual unit starting device shown in fig. 7 or 8. For example, the computing pool includes a management platform, and the management platform includes a virtual unit starting device as shown in fig. 7 or fig. 8.

By way of example, the cloud computing system is an intensive cloud computing system 100 as shown in fig. 1 or fig. 2.

Embodiments of the present application provide a computer readable storage medium having stored therein a computer program which, when executed (e.g., by a virtual unit starting apparatus, a management platform, one or more processors, etc.), performs all or part of the steps of a method as provided by the method embodiments described above.

Embodiments of the present application provide a computer program product comprising a program or code that, when executed (e.g., by a virtual unit starting apparatus, a management platform, one or more processors, etc.), performs all or part of the steps of a method as provided by the method embodiments described above.

Embodiments of the present application provide a chip comprising programmable logic circuits and/or program instructions, which when executed is adapted to carry out all or part of the steps of the method as provided by the method embodiments described above.

It should be noted that, in the embodiments of the present application, the "virtual unit" may be a container or a virtual machine, and in the embodiments described above, the "virtual unit" may be replaced by the "container" or be replaced by the "virtual machine" entirely, and after replacement, the technical solution described in the embodiments described above is still satisfied.

In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be embodied in whole or in part in the form of a computer program product comprising one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present application, in whole or in part. The computer may be a general purpose computer, a network of computers, or other programmable devices. The computer instructions may be stored in or transmitted from one computer readable storage medium to another, for example, by wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means from one website, computer, server, or data center. The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device including one or more servers, data centers, etc. that can be integrated with the available medium. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium, or a semiconductor medium (e.g., solid state disk), etc.

It should be understood that the term "at least one" in the present application means one or more, and "a plurality" means two or more. The term "and/or" in the present application is merely an association relation describing the association object, and means that three kinds of relations may exist, for example, a and/or B may mean: a exists alone, A and B exist together, and B exists alone. In addition, for the purpose of clarity of description, the words "first," "second," "third," and the like are used herein to distinguish between identical or similar items that have substantially the same function and effect. Those skilled in the art will appreciate that the words "first," "second," "third," etc. do not limit the number and order of execution.

Different types of embodiments, such as a method embodiment and a device embodiment, provided by the embodiment of the present application may be referred to each other, and the embodiment of the present application is not limited to this. The sequence of the operations of the method embodiment provided by the embodiment of the application can be properly adjusted, the operations can also be increased or decreased according to the situation, and any method which is easily conceivable to be changed by a person skilled in the art within the technical scope of the disclosure of the application is covered in the protection scope of the application, so that the description is omitted.

In the corresponding embodiments provided in the present application, it should be understood that the disclosed apparatus and the like may be implemented by other structural means. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of modules is merely a logical division of functionality, and there may be additional divisions of actual implementation, e.g., multiple modules or components may be combined or integrated into another system, or some features may be omitted, or not performed.

The modules illustrated as separate components may or may not be physically separate, and the components described as modules may or may not be physical modules, may be located in one place, or may be distributed over a plurality of devices. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

While the application has been described with reference to exemplary embodiments, it will be understood by those skilled in the art that various changes and substitutions of equivalents may be made without departing from the spirit and scope of the application. Therefore, the protection scope of the application is subject to the protection scope of the claims.

Claims (48)

1. The virtual unit starting method is characterized by being applied to a management platform in an intensive cloud computing system, wherein the intensive cloud computing system further comprises a first computing pool, and the method comprises the following steps:

Acquiring a starting requirement of a first application;

Acquiring at least one set of starting measurement information corresponding to a target application, wherein the at least one set of starting measurement information corresponds to at least one starting scheme, and each set of starting measurement information in the at least one set of starting measurement information is used for representing starting performance of the target application started in the intensive cloud computing system based on the corresponding starting scheme, and the target application is matched with the first application;

determining a first start-up scenario according to the start-up complaints of the first application and the at least one set of start-up measurement information, the at least one start-up scenario comprising the first start-up scenario;

And starting a first virtual unit of the first application in the first computing pool according to the first starting scheme.

2. The method of claim 1, wherein the first initiation scheme comprises any one of:

A warm boot scheme based on the first storage pool;

A cold start scheme based on the first storage pool;

a cold start scheme based on the second computing pool;

Wherein the first storage pool and the second computing pool are respectively interconnected with the first computing pool.

3. The method of claim 2, wherein the first startup scheme comprises a warm startup scheme based on the first storage pool, wherein a reference memory snapshot is stored in the first storage pool, wherein the reference memory snapshot is obtained by snapshot of a memory of a reference virtual unit of the first application, and wherein the first computing pool comprises the first virtual unit;

The starting the first virtual unit of the first application in the first computing pool according to the first starting scheme includes: and creating a first memory branch in the first computing pool according to the reference memory snapshot, wherein the first memory branch is used for storing memory data which changes relative to the reference memory snapshot in the running process of the first virtual unit.

4. The method of claim 3, wherein the first storage pool further stores a reference file system, the reference file system being a file system of the reference virtual unit;

the starting the first virtual unit of the first application in the first computing pool according to the first starting scheme further includes: and creating a first read-write layer in the first computing pool according to the reference file system, wherein the first read-write layer is used for storing file data which changes relative to the reference file system in the running process of the first virtual unit.

5. The method of claim 3 or 4, wherein prior to launching the first virtual unit in the first computing pool according to the first launch scheme, the method further comprises:

acquiring the reference memory snapshot of the reference virtual unit in the process of operating the reference virtual unit;

And storing the reference memory snapshot into the first memory pool.

6. The method of any of claims 3 to 5, wherein prior to launching the first virtual unit in the first computing pool according to the first launch scheme, the method further comprises:

the first virtual unit is created in the first computing pool according to an application image of the first application.

7. The method of claim 2, wherein the first startup scheme comprises a cold startup scheme based on the first storage pool, the first storage pool having stored therein a reference cell snapshot obtained by snapshot of a reference virtual cell of the first application;

The starting the first virtual unit of the first application in the first computing pool according to the first starting scheme includes: and creating and starting the first virtual unit in the first computing pool according to the reference unit snapshot.

8. The method of claim 7, wherein prior to starting the first virtual unit in the first computing pool according to the first start-up scheme, the method further comprises:

acquiring a reference unit snapshot of the reference virtual unit in the process of operating the reference virtual unit;

And storing the reference unit snapshot into the first storage pool.

9. The method according to any one of claim 3 to 8, wherein,

The reference virtual unit runs in the first computing pool.

10. The method of claim 2, wherein the first start-up scheme comprises a cold start-up scheme based on the second computing pool having a second virtual unit running therein, the second virtual unit having a configuration identical to a configuration of the first virtual unit;

The starting the first virtual unit of the first application in the first computing pool according to the first starting scheme includes: creating and starting the first virtual unit in the first computing pool according to the second virtual unit.

11. The method of claim 10, wherein starting the first virtual unit from the second virtual unit comprises: and creating a second memory branch in the first computing pool according to the memory of the second virtual unit, wherein the second memory branch is used for storing memory data which changes relative to the memory of the second virtual unit in the running process of the first virtual unit.

12. The method according to claim 10 or 11, wherein starting the first virtual unit from the second virtual unit comprises: and creating a second read-write layer in the first computing pool according to the file system of the second virtual unit, wherein the second read-write layer is used for storing file data which changes relative to the file system of the second virtual unit in the operation process of the first virtual unit.

13. The method of any one of claims 1 to 12, wherein the intensive cloud computing system further comprises a first storage pool, the first storage pool being interconnected with the first computing pool;

the first storage pool is used for storing at least one of the following information of the first application:

a snapshot of the memory of the virtual unit of the first application;

A snapshot of a virtual unit of the first application;

an application image of the first application.

14. The method of claim 13, wherein the step of determining the position of the probe is performed,

The storage location of the at least one piece of information of the first application in the first storage pool is determined according to at least one of the following indicators of the first application: importance, frequency of use, start-up requirements.

15. The method according to claim 13 or 14, wherein,

The intensive cloud computing system further comprises a mirror image warehouse, wherein the mirror image warehouse is used for storing the corresponding relation between the indication information of the application mirror image and the storage position of the application mirror image in the first storage pool.

16. The method according to any one of claims 13 to 15, wherein,

The first storage pool includes at least one of a memory pool and a memory pool.

17. The method of claim 16, wherein the step of determining the position of the probe comprises,

The memory pool and the external memory pool satisfy at least one of the following:

The memory pool comprises at least two first storage media, and the types of the at least two first storage media are different;

the external memory pool comprises at least two second storage media, and the types of the at least two second storage media are different;

Wherein the first storage medium and the second storage medium store data based on a differential algorithm, respectively.

18. The method according to any one of claims 1 to 17, wherein,

Matching the target application with the first application includes at least one of:

The target application is the first application;

The scale of the target application is matched with the scale of the first application;

the size of the application image of the target application is matched with the size of the application image of the first application;

The type of the target application matches the type of the first application.

19. The method according to any one of claims 1 to 18, wherein,

The start-up complaints include at least one of a start-up duration complaint and a start-up cost complaint;

The start-up measurement information includes at least one of a measured start-up duration and a measured start-up cost.

20. The method according to any one of claims 1 to 19, wherein the obtaining at least one set of start-up measurement information corresponding to the target application includes: and performing a starting test on the target application in the intensive cloud computing system according to each starting scheme in the at least one starting scheme to obtain a group of starting measurement information corresponding to each starting scheme.

21. The method according to any one of claims 1 to 20, wherein,

The management platform is deployed in the first computing pool.

22. The method according to any one of claims 1 to 21, wherein,

The first virtual unit is a container or a virtual machine.

23. A virtual unit initiation device, applied to a management platform in an intensive cloud computing system, the intensive cloud computing system further comprising a first computing pool, the device comprising:

The system comprises an acquisition module, a target application and a first application, wherein the acquisition module is used for acquiring a starting requirement of the first application and acquiring at least one group of starting measurement information corresponding to the target application, the at least one group of starting measurement information corresponds to at least one starting scheme, and each group of starting measurement information in the at least one group of starting measurement information is used for representing starting performance of starting the target application in the intensive cloud computing system based on the corresponding starting scheme, and the target application is matched with the first application;

A determining module, configured to determine a first startup scheme according to a startup complaint of the first application and the at least one set of startup measurement information, where the at least one startup scheme includes the first startup scheme;

and the starting module is used for starting a first virtual unit of the first application in the first computing pool according to the first starting scheme.

24. The apparatus of claim 23, wherein the first initiation scheme comprises any one of:

A warm boot scheme based on the first storage pool;

A cold start scheme based on the first storage pool;

a cold start scheme based on the second computing pool;

Wherein the first storage pool and the second computing pool are respectively interconnected with the first computing pool.

25. The apparatus of claim 24, wherein the first boot scheme comprises a hot boot scheme based on the first storage pool, wherein a reference memory snapshot is stored in the first storage pool, wherein the reference memory snapshot is obtained by snapshot of a memory of a reference virtual unit of the first application, and wherein the first computing pool comprises the first virtual unit;

the starting module is configured to create a first memory branch in the first computing pool according to the reference memory snapshot, where the first memory branch is configured to store memory data that changes relative to the reference memory snapshot during the operation of the first virtual unit.

26. The apparatus of claim 25, wherein the first storage pool further stores a reference file system, the reference file system being a file system of the reference virtual unit; the starting module is further configured to create a first read-write layer in the first computing pool according to the reference file system, where the first read-write layer is configured to store file data that changes relative to the reference file system during the operation of the first virtual unit.

27. The apparatus of claim 25 or 26, wherein the device comprises a plurality of sensors,

The acquiring module is further configured to acquire, in a process of operating the reference virtual unit, the reference memory snapshot of the reference virtual unit before the starting module starts the first virtual unit in the first computing pool according to the first starting scheme;

The apparatus further comprises: and the storage module is used for storing the reference memory snapshot into the first storage pool.

28. The apparatus according to any one of claims 25 to 27, further comprising:

The creating module is used for creating the first virtual unit in the first computing pool according to the application image of the first application before the starting module starts the first virtual unit in the first computing pool according to the first starting scheme.

29. The apparatus of claim 24, wherein the first startup scheme comprises a cold startup scheme based on the first storage pool, the first storage pool having stored therein a reference cell snapshot obtained by snapshot of a reference virtual cell of the first application; the starting module is used for creating and starting the first virtual unit in the first computing pool according to the reference unit snapshot.

30. The apparatus of claim 29, wherein the device comprises a plurality of sensors,

The obtaining module is further configured to obtain, in a process of running the reference virtual unit, the reference unit snapshot of the reference virtual unit before the starting module starts the first virtual unit in the first computing pool according to the first starting scheme;

The apparatus further comprises: and the storage module is used for storing the reference unit snapshot into the first storage pool.

31. The device according to any one of claims 25 to 30, wherein,

The reference virtual unit runs in the first computing pool.

32. The apparatus of claim 24, wherein the first boot scheme comprises a cold boot scheme based on the second computing pool having a second virtual unit running therein, the second virtual unit having a configuration identical to a configuration of the first virtual unit; the starting module is used for creating and starting the first virtual unit in the first computing pool according to the second virtual unit.

33. The apparatus of claim 32, wherein the means for starting is configured to create a second memory branch in the first computing pool based on a memory of the second virtual unit, the second memory branch being configured to store memory data that changes relative to a memory of the second virtual unit during operation of the first virtual unit.

34. The apparatus according to claim 32 or 33, wherein the startup module is configured to create a second read-write layer in the first computing pool according to a file system of the second virtual unit, and the second read-write layer is configured to store file data that changes relative to the file system of the second virtual unit during operation of the first virtual unit.

35. The apparatus of any one of claims 23 to 34, wherein the intensive cloud computing system further comprises a first storage pool, the first storage pool being interconnected with the first computing pool;

the first storage pool is used for storing at least one of the following information of the first application:

a snapshot of the memory of the virtual unit of the first application;

A snapshot of a virtual unit of the first application;

an application image of the first application.

36. The apparatus of claim 35, wherein the device comprises a plurality of sensors,

The storage location of the at least one piece of information of the first application in the first storage pool is determined according to at least one of the following indicators of the first application: importance, frequency of use, start-up requirements.

37. The apparatus of claim 35 or 36, wherein the device comprises a plurality of sensors,

The intensive cloud computing system further comprises a mirror image warehouse, wherein the mirror image warehouse is used for storing the corresponding relation between the indication information of the application mirror image and the storage position of the application mirror image in the first storage pool.

38. The apparatus according to any one of claims 35 to 37, wherein,

The first storage pool includes at least one of a memory pool and a memory pool.

39. The apparatus of claim 38, wherein the device comprises a plurality of sensors,

The memory pool and the external memory pool satisfy at least one of the following:

The memory pool comprises at least two first storage media, and the types of the at least two first storage media are different;

the external memory pool comprises at least two second storage media, and the types of the at least two second storage media are different;

Wherein the first storage medium and the second storage medium store data based on a differential algorithm, respectively.

40. The apparatus of any one of claims 23 to 39, wherein,

Matching the target application with the first application includes at least one of:

The target application is the first application;

The scale of the target application is matched with the scale of the first application;

the size of the application image of the target application is matched with the size of the application image of the first application;

The type of the target application matches the type of the first application.

41. The device of any one of claims 23 to 40, wherein,

The start-up complaints include at least one of a start-up duration complaint and a start-up cost complaint;

The start-up measurement information includes at least one of a measured start-up duration and a measured start-up cost.

42. The apparatus according to any one of claims 23 to 41, wherein the obtaining module is configured to perform a start test on the target application in the intensive cloud computing system according to each of the at least one start scheme, to obtain a set of start measurement information corresponding to each start scheme.

43. The apparatus of any one of claims 23 to 42,

The management platform is deployed in the first computing pool.

44. The device of any one of claims 23 to 43,

The first virtual unit is a container or a virtual machine.

45. A virtual unit starting device, which is characterized by comprising a memory and a processor;

the memory is used for storing a computer program;

the processor is configured to execute a computer program stored in the memory to cause the virtual unit starting apparatus to perform the method according to any one of claims 1 to 22.

46. A cloud computing system comprising a computing pool and a storage pool, the storage pool being interconnected with the computing pool, the computing pool comprising the virtual unit activation apparatus of any one of claims 23 to 45.

47. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a computer program which, when executed, implements the method of any of claims 1 to 22.

48. A computer program product, characterized in that it comprises a program or code which, when executed, implements the method of any of claims 1 to 22.