Configuration method and device for network card of computing power resource container of intelligent computing center

Abstract

The invention provides an intelligent computing center computing power resource container network card configuration method and device, and relates to the technical field of intelligent computing centers, intelligent computing centers and computing power infrastructure, the method comprises the following steps: S1, creating a first virtual network card based on first information, the first information being used for indicating a first network segment and a first container, the first network segment is one of a plurality of network segments included in the container network, the container network is a network used when the container cluster distributes the network segments, the container cluster comprises a plurality of computing power resource containers, the first container is one of the computing power resource containers, and the first virtual network card is used for accessing the first network segment; s2, determining a first container in the plurality of computing power resource containers based on first information; and S3, migrating the first virtual network card into the first container, and executing network card configuration operation in the first container based on the first virtual network card. The network segment expansion efficiency of the container can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent computing centers, intelligent computing centers and computing power infrastructure, and particularly relates to a method and device for configuring a container network card of computing power resources in an intelligent computing center. Background Art

[0002] With the rapid development of artificial intelligence technology, "intelligent computing centers" and "intelligent computing centers" have emerged as the times require.

[0003] An "intelligent computing center" refers to a facility that provides the required computing power, data, and algorithms for artificial intelligence applications (such as scenarios of artificial intelligence deep learning model development, model training, and model inference) by using large-scale heterogeneous computing power resources, including general computing power and intelligent computing power. The intelligent computing center covers facilities, hardware, and software, and can provide full-stack capabilities from underlying computing power to top-level application enabling.

[0004] The "intelligent computing center" includes, but is not limited to, the "intelligent computing center".

[0005] An "intelligent computing center", that is, an artificial intelligence computing center, is a type of computing power infrastructure that provides computing power services, data services, and algorithm services required for artificial intelligence applications based on artificial intelligence theory and using an artificial intelligence computing architecture.

[0006] "Computing power" is the core of the "intelligent computing center" and the "intelligent computing center", which is the ability of a computer device or a computing / data center to process information, the ability of computer hardware and software to cooperate to jointly execute a certain computing requirement, the computing ability to achieve the output of a target result by processing information data, a new type of productive force integrating information computing power, network carrying capacity, and data storage capacity, and mainly provides services to society through computing power infrastructure.

[0007] Computing power resources are a part of the intelligent computing center, and the computing power resources run in containers. At present, the container network card configuration solutions provided by the prior art only support configuring the network card used by the container during the creation stage of the container. Therefore, when it is necessary to expand the network segment used by a certain container that is in use, it is necessary to first recycle the container and then regenerate a new container according to the new network card configuration, which makes the network segment expansion efficiency of the container very low.

[0008] That is to say, the container network card configuration solutions provided by the prior art have the problem of too low network segment expansion efficiency of the container. Summary of the Invention

[0009] The purpose of the present invention is to provide a method and device for configuring a container network card of computing power resources in an intelligent computing center, which are used to solve the technical problem of too low network segment expansion efficiency of the container existing in the container network card configuration solutions provided by the prior art.

[0010] To solve the above technical problems, the present invention is implemented as follows:

[0011] In a first aspect, the present invention provides a method for configuring a network card of a computing power resource container in an intelligent computing center, the method comprising:

[0012] Step S1, creating a first virtual network card based on first information, wherein the first information includes first data and second data, the first data is index data of a first network segment, the second data is index data of a first container, the first network segment is one of multiple network segments included in a container network, the container network is a network used when allocating network segments to a container cluster, the container cluster includes multiple computing power resource containers, the first container is one of the multiple computing power resource containers, and the first virtual network card is used to access the first network segment;

[0013] Step S2, determining the first container among the multiple computing power resource containers based on the first information;

[0014] Step S3, migrating the first virtual network card to the first container and performing network card configuration operations within the first container based on the first virtual network card.

[0015] In one embodiment, the method further includes:

[0016] Step S1', determining a second container and a second virtual network card among the multiple computing power resource containers based on second information, wherein the second information includes third data and fourth data, the third data is index data of a second network segment, the fourth data is index data of a second container, the second network segment is one of multiple network segments included in the container network, the second container is one of the multiple computing power resource containers, and the second virtual network card is a virtual network card among multiple virtual network cards included in the second container and used to access the second network segment;

[0017] Step S2', releasing network resources corresponding to the second virtual network card in the second container;

[0018] Step S3', deleting the second virtual network card from among the multiple virtual network cards included in the second container.

[0019] In one embodiment, the method further includes:

[0020] Step S41, determining a third container among the multiple computing power resource containers, wherein the third container is the computing power resource container that meets the network card expansion condition;

[0021] Step S42: Determine a third network segment from among at least one available network segment, where the available network segments are the network segments among the multiple network segments that are not allocated for use by the third container;

[0022] Step S43: Create a third virtual network card based on the network segment attributes of the third network segment, where the network segment attributes include the Internet Protocol address and the Media Access Control address of the corresponding network segment, and the third virtual network card is used to access the third network segment;

[0023] Step S44: Migrate the third virtual network card to the third container and perform network card configuration operations within the third container based on the third virtual network card.

[0024] In one embodiment, the network card expansion condition includes at least one of the following:

[0025] The first metric value of the computing power resource container is greater than or equal to a first threshold, and the metric corresponding to the first metric value is the network latency of the computing power resource container;

[0026] The second metric value of the computing power resource container is greater than or equal to a second threshold, and the metric corresponding to the second metric value is the network load of the computing power resource container;

[0027] The third metric value of the computing power resource container is greater than or equal to a third threshold, and the metric corresponding to the third metric value is the network packet loss rate of the computing power resource container.

[0028] In one embodiment, the first metric value is used to represent: the network latency of the computing power resource container during a target time period;

[0029] The second metric value is used to represent: the network load of the computing power resource container during the target time period;

[0030] The third metric value is used to represent: the network packet loss rate of the computing power resource container during the target time period.

[0031] In one embodiment, the method further includes:

[0032] Step S51: Determine a fourth container from among the multiple computing power resource containers, where the fourth container is the computing power resource container whose network usage rate is less than or equal to a fourth threshold;

[0033] Step S52: Among the multiple network segments used by the fourth container, determine the network segment with the lowest network traffic as the fourth network segment;

[0034] Step S53: Release the network resources corresponding to the fourth virtual network card in the fourth container, where the fourth virtual network card is the virtual network card among the multiple virtual network cards included in the fourth container and is used to access the fourth network segment.

[0035] Step S54: Delete the fourth virtual network card from among the multiple virtual network cards included in the fourth container.

[0036] In a second aspect, the present invention further provides a configuration device for the network card of the computing power resource container in an intelligent computing center. The device:

[0037] A network card creation module, configured to create a first virtual network card based on first information, where the first information includes first data and second data, the first data is index data of a first network segment, the second data is index data of a first container, the first network segment is one of the multiple network segments included in the container network, the container network is the network used when allocating network segments to a container cluster, the container cluster includes multiple computing power resource containers, the first container is one of the multiple computing power resource containers, and the first virtual network card is used to access the first network segment;

[0038] A container determination module, configured to determine the first container among the multiple computing power resource containers based on the first information;

[0039] A network card configuration module, configured to migrate the first virtual network card to the first container and perform a network card configuration operation in the first container based on the first virtual network card.

[0040] In a third aspect, the present invention further provides a server, including: a processor, a memory, and a program stored on the memory and executable on the processor. When the program is executed by the processor, it implements the steps in the configuration method for the network card of the computing power resource container in the intelligent computing center as described in the first aspect above.

[0041] In a fourth aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the steps in the configuration method for the network card of the computing power resource container in the intelligent computing center as described in the first aspect above.

[0042] In a fifth aspect, the present invention provides a computer program product, including computer instructions. When the computer instructions are executed by a processor, they implement the steps in the configuration method for the network card of the computing power resource container in the intelligent computing center as described in the first aspect above.

[0043] In the present invention, by creating a first virtual network card, migrating the first virtual network card to a first container, and performing network card configuration operations within the first container based on the first virtual network card, during the use of the first container, the first network segment accessed by the first virtual network card is configured as the network segment used by the first container, thereby realizing the network segment expansion of the first container. This eliminates the processes of container recycling and container regeneration, shortens the time-consuming for container network segment expansion, and can significantly improve the efficiency of container network segment expansion. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present invention. Moreover, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0045] Figure 1 is a flowchart of a method for configuring a network card of a computing power resource container in an intelligent computing center provided by the present invention;

[0046] Figure 2 is a schematic diagram of an example of dynamic configuration of a network card of a computing power resource container in an intelligent computing center provided by the present invention

[0047] Figure 3 is a schematic diagram of the structure of a device for configuring a network card of a computing power resource container in an intelligent computing center provided by the present invention;

[0048] Figure 4 is a schematic diagram of the structure of an electronic device provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0049] The following will clearly and completely describe the technical solutions in the present invention with reference to the drawings in the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present invention without making creative efforts belong to the scope of protection of the present invention.

[0050] First, the technical terms related to the present invention will be briefly described below.

[0051] The "computing power" referred to in the present invention means: the ability of a computer device or a computing / data center to process information, the ability of computer hardware and software to cooperate to jointly execute a certain computing requirement, the computing ability to process information data and output a target result, a new type of productive force integrating information computing power, network carrying capacity, and data storage capacity, and mainly providing services to society through computing power infrastructure.

[0052] The "Computational Power (CP)" described in the present invention refers to: the ability of a data center server to process data and output results, which is a comprehensive indicator for measuring the computing power of a data center and includes general computing power, supercomputing power, and intelligent computing power. The commonly used measurement unit is the number of floating-point operations per second (FLOPS, 1 EFLOPS = 10^18 FLOPS). The larger the value, the stronger the comprehensive computing power. It is estimated that 1 EFLOPS is approximately the computing power output of 5 Tianhe-2A or 500,000 mainstream server CPUs or 2 million mainstream laptops. The calculation formula is: CP = CP_general + CP_intelligent + CP_super.

[0053] The "Network Power (NP)" described in the present invention refers to: the performance of the data transmission ability of computing power facilities, which is a comprehensive ability including network architecture, network bandwidth, transmission delay, intelligent management and scheduling, etc., and involves network transmission within and between data centers, and is a comprehensive indicator for measuring network transmission scheduling ability.

[0054] The "Storage Power (SP)" described in the present invention refers to: the comprehensive ability of a data center in four aspects: data storage capacity, performance, security and reliability, and green and low-carbon, which is a comprehensive indicator for measuring the data storage ability of a data center and includes external storage devices such as storage arrays and server internal storage devices. The commonly used measurement unit for storage capacity is exabyte (EB, 1 EB = 2^60 bytes), the commonly used measurement unit for performance is the number of read and write operations per second per unit capacity (IOPS / TB, Input / Output Operations Per Second / TB), and the disaster recovery ratio is an important manifestation of security and reliability.

[0055] The "computing power infrastructure" described in the present invention refers to: a new type of information infrastructure integrating information computing power, network carrying power, and data storage power, which can realize the centralized computing, storage, transmission, and application of information.

[0056] The "new type of information infrastructure" described in the present invention mainly includes network infrastructures such as 5G networks, fiber broadband networks, backbone networks, international communication networks, and satellite Internet, computing power infrastructures such as data centers, general computing power centers, intelligent computing centers, and supercomputing centers, and new technology facilities such as artificial intelligence, blockchain, and quantum computing.

[0057] The "computing power" described in the present invention includes: general computing power, intelligent computing power, and supercomputing power.

[0058] The "general computing power" described in the present invention refers to the computing power provided by servers based on CPU (Central Processing Unit) chips, which is used to support basic general computing such as cloud computing and edge computing.

[0059] The "intelligent computing power" described in the present invention refers to: for various artificial intelligence innovation applications, a computing platform deployed on a large scale based on dedicated chips such as GPU (Graphics Processing Unit), FPGA (Field Programmable Gate Array), and ASIC (Application Specific Integrated Circuit), such as natural language processing, machine vision, etc.

[0060] The "super computing power" described in the present invention refers to: mainly the computing power provided by high-performance computing clusters such as supercomputers. It utilizes the centralized computing resources of multiple computer systems working in parallel and processes extremely complex or data-intensive problems through a dedicated operating system. It is mainly used for computing in cutting-edge scientific fields, such as planetary simulation, drug molecule design, gene analysis, etc.

[0061] The "intelligent computing center" described in the present invention refers to: a facility that provides the required computing power, data, and algorithms for artificial intelligence applications (such as scenarios like artificial intelligence deep learning model development, model training, and model inference) by using large-scale heterogeneous computing power resources, including general computing power (CPU) and intelligent computing power (GPU, FPGA, ASIC, etc.). The intelligent computing center covers facilities, hardware, and software, and can provide full-stack capabilities from underlying computing power to top-level application enabling.

[0062] The "intelligent computing center" described in the present invention includes, but is not limited to, the "intelligent computing center".

[0063] The "intelligent computing center" described in the present invention, that is, the artificial intelligence computing center, is a type of computing power infrastructure that provides computing power services, data services, and algorithm services required for artificial intelligence applications based on artificial intelligence theory and using an artificial intelligence computing architecture.

[0064] The "computing power center" described in the present invention refers to: a facility mainly composed of infrastructure such as wind, fire, water, and electricity and IT software and hardware devices, which has computing power, carrying capacity, and storage capacity, including general data centers, intelligent computing centers, supercomputing centers, etc.

[0065] The "supercomputing center" described in the present invention refers to: that is, the supercomputing data center, which is a data center based on supercomputers or large-scale computing clusters and can provide functions such as large-scale computing, storage, and network services, and is widely used in application scenarios such as aerospace, national defense, oil exploration, climate modeling, and genome sequencing.

[0066] The "computing power resources" referred to in the present invention mean: technologies and facilities with information computing, transmission, storage, and application capabilities required for the development of the digital society, including but not limited to computing resources such as CPUs and GPUs, network resources such as switches and routers, storage resources such as storage arrays and distributed storage, security resources such as firewalls and intrusion detection systems, and support and guarantee resources such as wind, fire, water, and electricity.

[0067] The "models" referred to in the present invention include but are not limited to "large language models" and "multimodal large models".

[0068] The "large language model" referred to in the present invention means a large-scale language model (LLM), which is a language model with a relatively large number of parameters, aiming to understand and generate human language, trained with a large amount of text data, and can perform a wide range of tasks including text summarization, translation, sentiment analysis, etc.

[0069] The "multimodal large model" (Multimodal Large Models) referred to in the present invention means: a model trained by jointly combining multimodal information such as text, images, videos, and audio, including but not limited to multimodal large language models.

[0070] The "container network" referred to in the present invention means: the network used when a container cluster assigns container network IP addresses, where the container cluster includes multiple computing power resource containers, and the computing power resources run in the corresponding computing power resource containers.

[0071] The "computing power resource container" referred to in the present invention means: a lightweight, portable, self-sufficient software packaging and running environment in which computing power resources run. Each computing power resource container runs in an independent namespace (NameSpace), that is, the namespaces where different computing power resource containers are located are different; and each computing power resource container is configured with one or more virtual network cards. The virtual network cards are created through virtualization technology, allowing multiple virtual machines or containers to share the network resources of the same physical network device. The virtual network cards simulate the functions of physical network cards and can be used to send and receive network traffic. Each virtual network card can be configured with an independent Internet Protocol (IP) address, Medium Access Control (MAC) address, and network configuration.

[0072] The "network segment" in the present invention refers to: a sub-network in the aforementioned "container network", which can be used for network transmission by computing power resource containers. A network segment can be used individually by a computing power resource container or jointly by multiple computing power resource containers. Different computing power resource containers using the same network segment can communicate at the second layer, while different computing power resource containers using different network segments need to be connected through a router to communicate data.

[0073] Please refer to Figure 1 , Figure 1 which is a method for configuring a network card of a computing power resource container in an intelligent computing center provided by the present invention. As Figure 1 shown, it includes the following steps:

[0074] Step S1: Create a first virtual network card based on the first information.

[0075] Among them, the first information includes first data and second data. The first data is index data of a first network segment, and the second data is index data of a first container. The first network segment is one of the multiple network segments included in the container network. The container network is the network used when allocating network segments to a container cluster. The container cluster includes multiple computing power resource containers, and the first container is one of the multiple computing power resource containers. The first virtual network card is used to access the first network segment.

[0076] The above first information is the information input by the user. The first data is used to uniquely identify the first network segment among the multiple network segments, and the second data is used to uniquely identify the first container among the multiple computing power resource containers.

[0077] Step S2: Determine the first container among the multiple computing power resource containers based on the first information.

[0078] More specifically, determine the first container among the multiple computing power resource containers based on the second data.

[0079] Step S3: Migrate the first virtual network card to the first container, and perform network card configuration operations in the first container based on the first virtual network card.

[0080] Among them, migrating the first virtual network card to the first container can also be understood as: migrating the first virtual network card to the namespace where the first container is located.

[0081] The network card configuration operation includes but is not limited to: adding an IP address of the first network segment to multiple IP addresses used by the first container, adding a route of the first network segment to multiple routes used by the first container, and adding a domain name system (Domain Name System, DNS) of the first network segment to multiple domain name systems (Domain Name System, DNS) used by the first container.

[0082] After the first virtual network card performs the network card configuration operation in the first container, the first container interacts and communicates with other computing resource containers and external devices (referring to devices that do not belong to the container cluster) in the first network segment.

[0083] In the present invention, by creating a first virtual network card, migrating the first virtual network card to the first container, and performing a network card configuration operation in the first container based on the first virtual network card, during the use of the first container, the first network segment connected to the first virtual network card is configured as the network segment used by the first container, thereby realizing the network segment expansion of the first container, which saves the process of container recycling and container regeneration, shortens the time spent on container network segment expansion, and can significantly improve the efficiency of container network segment expansion.

[0084] In one embodiment, the method further comprises:

[0085] Step S1', determining a second container and a second virtual network card in the multiple computing power resource containers based on the second information, wherein the second information includes third data and fourth data, the third data is index data of the second network segment, the fourth data is index data of the second container, the second network segment is one of the multiple network segments included in the container network, the second container is one of the multiple computing power resource containers, and the second virtual network card is a virtual network card for accessing the second network segment among the multiple virtual network cards included in the second container;

[0086] Step S2': in the second container, releasing the network resources corresponding to the second virtual network card;

[0087] Step S3': Delete the second virtual network card from the multiple virtual network cards included in the second container.

[0088] The above-mentioned second information is also information input by the user. The third data is used to uniquely identify the second network segment among the multiple network segments, and the fourth data is used to uniquely identify the second container among the multiple computing power resource containers.

[0089] In this embodiment, after determining the second container and the second virtual network card, the network resources corresponding to the second virtual network card are first released in the second container, and then the second virtual network card is deleted from the multiple virtual network cards included in the second container, so that during the use of the second container, the second network segment connected to the second virtual network card is removed from the multiple network segments used by the second container, thereby achieving network segment reduction for the second container. This also saves the process of container recycling and container regeneration, shortens the time spent on network segment reduction for the container, and cooperates with the settings of the aforementioned steps S1-S3, can achieve flexible adjustment of the network segment used by the container at an extremely low cost, so that the network segment adjustment efficiency of the container is significantly improved.

[0090] In the application, the above-mentioned process of step S1 to step S3, and the process of step S1' to step S3' can be implemented in the form of an interface, and the implemented interface can be integrated into the existing container tools (such as Kubernetes, Docker, Nomad, etc.), so as to realize the dynamic configuration of network card function while reusing the existing container tools, reduce the development difficulty of container tools that support the dynamic configuration of network card function, and facilitate developers to use the container tools that support the dynamic configuration of network card function.

[0091] Among them, the dynamic configuration of network cards function refers to: during the operation of the computing resource container, the function of adding or deleting the virtual network cards used in the container is realized without affecting the computing power calculation program already running in the container.

[0092] like Figure 2 As shown, Figure 2 In the above, pod1 and pod2 refer to two different computing resource containers, vnet1 and vnet2 refer to two different virtual network cards, Attach refers to the network card adding interface used to implement step S1-step S3, and Detach refers to the network card deleting interface used to implement step S1'-step S3'. Figure 2 It shows:

[0093] By calling the Attach interface, the virtual network card vnet2 can be expanded to be a virtual network card that can be used by the computing resource container pod1 without affecting the use of the virtual network card vnet1 by the computing resource container pod1;

[0094] Alternatively, by calling the Detach interface, the virtual network card vnet2 can be removed from the virtual network cards that can be used by the computing power resource container pod1 without affecting the use of the virtual network card vnet1 by the computing power resource container pod1.

[0095] In an example, the code implementation of adding an interface to the aforementioned network card may be as follows:

[0096]

[0097]

[0098] In this example, attachNic is the function name corresponding to the network card addition interface, pod is the container name of the computing power resource container to which the network card is to be added (i.e., the aforementioned second data), vnic is the network card name of the virtual network card to be added to the container (i.e., the aforementioned first data), netns can be understood as the computing power resource container to which the network card is to be added (i.e., the aforementioned first container), vNic can be understood as the virtual network card to be added to the container (i.e., the aforementioned first virtual network card), vNic.ip can be understood as the IP address of the virtual network card to be added to the container, and vNic.mac can be understood as the MAC address of the virtual network card to be added to the container.

[0099] In another example, the code implementation of the aforementioned network card deletion interface can be as follows:

[0100]

[0101] In this example, detachNic is the function name corresponding to the network card deletion interface, pod is the container name of the computing power resource container to which the network card is to be deleted (i.e., the aforementioned fourth data), vnic is the network card name of the virtual network card to be removed from the container (i.e., the aforementioned third data), defaultns is the default namespace (also known as the global namespace), and vNic is the virtual network card to be removed from the container (i.e., the aforementioned second virtual network card).

[0102] In one embodiment, the method further includes:

[0103] Step S41, determine a third container among the multiple computing power resource containers, where the third container is the computing power resource container that meets the network card expansion condition;

[0104] Step S42, determine a third network segment among at least one available network segment, where the available network segment is the network segment among the multiple network segments that is not allocated for use by the third container;

[0105] Step S43, create a third virtual network card based on the network segment attributes of the third network segment, where the network segment attributes include the Internet Protocol address and the Media Access Control address of the corresponding network segment, and the third virtual network card is used to access the third network segment;

[0106] Step S44, migrate the third virtual network card to the third container, and perform network card configuration operations in the third container based on the third virtual network card.

[0107] In this embodiment, by setting the network card expansion conditions, the computing power resource containers that need network card expansion can be automatically identified, and corresponding network card expansion processing can be performed on the identified computing power resource containers, which can further improve the network card expansion efficiency of the container cluster.

[0108] Exemplarily, the third network segment can be any available network segment among the at least one available network segment, or can be the available network segment with the minimum network latency among the at least one available network segment.

[0109] In one embodiment, the network card expansion conditions include at least one of the following:

[0110] The first metric value of the computing power resource container is greater than or equal to a first threshold, and the metric corresponding to the first metric value is the network latency of the computing power resource container;

[0111] The second metric value of the computing power resource container is greater than or equal to a second threshold, and the metric corresponding to the second metric value is the network load of the computing power resource container;

[0112] The third metric value of the computing power resource container is greater than or equal to a third threshold, and the metric corresponding to the third metric value is the network packet loss rate of the computing power resource container.

[0113] Among them, the network latency of the computing power resource container is: within a set time period, the average of the network latencies of multiple virtual network cards used by the computing power resource container. Exemplarily, multiple test signals can be transmitted using the virtual network card, and the multiple transmission delays of the multiple test signals can be recorded respectively, and then the average of the multiple transmission delays can be determined as the network latency corresponding to the virtual network card.

[0114] The network load of the computing power resource container is: within a set time period, the average of the data volumes of multiple virtual network cards used by the computing power resource container. Among them, the data volume can be understood as: the storage space size occupied by the data input through the corresponding virtual network card within a unit time (such as 10 kb, 10 Mb, etc.), and / or the storage space size occupied by the data output through the corresponding virtual network card.

[0115] The network packet loss rate of the computing power resource container is: the average of the packet loss rates of multiple virtual network cards used by the computing power resource container. Among them, the packet loss rate can be understood as: within a set time period, the ratio of the number of data packets lost through the corresponding virtual network card to the total number of data packets transmitted through the corresponding virtual network card. Among them, the set time period can be a time period traced back from the current moment for a first set duration (such as 10 seconds, half a minute, 5 minutes, etc.), or can be a certain historical time period before the current moment, or can be a time period traced forward from the current moment for a second set duration (such as 15 minutes, 1 hour, 1 day, etc.).

[0116] In this embodiment, based on one or more indicators such as network latency, network load, and network packet loss rate, it is determined whether the computing power resource container meets the network card expansion condition, which can make the determination of the third container more flexible to adapt to the network card expansion determination requirements in different scenarios.

[0117] In one embodiment, the first indicator value is used to represent the network latency of the computing power resource container in the target time period.

[0118] The second indicator value is used to represent the network load of the computing power resource container in the target time period.

[0119] The third indicator value is used to represent the network packet loss rate of the computing power resource container in the target time period.

[0120] Wherein, the start time of the target time period is the current time, and the duration of the target time period is a set duration.

[0121] Wherein, the starting point of the target time period is the current time, and the duration of the target time period is the aforementioned second set duration. In the application, the network latency / network load / network packet loss rate of the computing power resource container in the target time period can be predicted by analyzing the network latency / network load / network packet loss rate of the computing power resource container in the historical time period, where the current time can be understood as the end time of the historical time period.

[0122] Exemplarily, the above analysis can be completed by constructing a fitting curve or by model prediction.

[0123] The method of constructing a fitting curve is as follows: based on fitting algorithms such as linear fitting / least squares method, the network latency / network load / network packet loss rate of the computing power resource container in the historical time period is used as the data to be fitted for fitting to obtain a fitting curve, and then the network latency / network load / network packet loss rate of the computing power resource container in the target time period is predicted based on this fitting curve.

[0124] The method of model prediction is as follows: using a convolutional neural network model (such as a CNN model) as the initial model, the historical time period - the network latency / network load / network packet loss rate of the computing power resource container in the historical time period as the training samples of the model, training the initial model to obtain a prediction model, and then predicting the network latency / network load / network packet loss rate of the computing power resource container in the target time period based on this prediction model.

[0125] In this embodiment, by predicting the network latency, network load, and / or network packet loss rate of the computing power resource container in the target time period, the network card expansion process of the corresponding computing power resource container is completed in advance as much as possible before the situation of excessive network latency, excessive network load, and / or excessive network packet loss rate occurs in the computing power resource container, so that the corresponding computing power resource container can provide more stable and reliable computing power support in the target time period.

[0126] In one embodiment, the method further includes:

[0127] Step S51: Determine a fourth container among the multiple computing power resource containers, where the fourth container is the computing power resource container whose network usage rate is less than or equal to a fourth threshold;

[0128] Step S52: Among the multiple network segments used by the fourth container, determine the network segment with the lowest network traffic as the fourth network segment;

[0129] Step S53: In the fourth container, release the network resources corresponding to the fourth virtual network card, where the fourth virtual network card is the virtual network card among the multiple virtual network cards included in the fourth container that is used to access the fourth network segment;

[0130] Step S54: Delete the fourth virtual network card among the multiple virtual network cards included in the fourth container.

[0131] Among them, the network usage rate is the ratio of the first traffic to the second traffic, where the first traffic is the actual network traffic used by the corresponding computing power resource container in the historical time period, and the second traffic is the maximum network traffic of the corresponding computing power resource container in the historical time period.

[0132] The network traffic of a network segment is the input traffic and / or output traffic of the corresponding network segment in the historical time period.

[0133] In this embodiment, through the numerical determination of the network usage rate, the computing power resource container to be optimized for the network card is automatically identified among the multiple computing power resource containers, that is, the computing power resource container with too low network card utilization rate is identified. Then, among the multiple network segments used by the identified computing power resource container, through the numerical determination of the network traffic, the network segment to be optimized in the corresponding computing power resource container is identified, that is, the network segment that has been idle or has low traffic for a long time in the corresponding computing power resource container is identified. Then, the corresponding network segment is removed in the corresponding computing power resource container, so that the network traffic transmission capacity of each computing power resource container is fully utilized.

[0134] Please refer to Figure 3 , Figure 3 which is the structural diagram of a configuration device for the network card of a computing power resource container in an intelligent computing center provided by the present invention. As Figure 3As shown, the configuration device 300 for the network card of the computing power resource container in the intelligent computing center includes:

[0135] A network card creation module 301, configured to create a first virtual network card based on first information, where the first information includes first data and second data, the first data is index data of a first network segment, the second data is index data of a first container, the first network segment is one of multiple network segments included in the container network, the container network is the network used when allocating network segments for a container cluster, the container cluster includes multiple computing power resource containers, the first container is one of the multiple computing power resource containers, and the first virtual network card is used to access the first network segment;

[0136] A container determination module 302, configured to determine the first container among the multiple computing power resource containers based on the first information;

[0137] A network card configuration module 303, configured to migrate the first virtual network card to the first container and perform a network card configuration operation in the first container based on the first virtual network card.

[0138] In one embodiment, the configuration device 300 for the network card of the computing power resource container in the intelligent computing center further includes:

[0139] A first module, configured to determine a second container and a second virtual network card among the multiple computing power resource containers based on second information, where the second information includes third data and fourth data, the third data is index data of a second network segment, the fourth data is index data of a second container, the second network segment is one of multiple network segments included in the container network, the second container is one of the multiple computing power resource containers, and the second virtual network card is the virtual network card among the multiple virtual network cards included in the second container that is used to access the second network segment;

[0140] A second module, configured to release the network resources corresponding to the second virtual network card in the second container;

[0141] A network card deletion module, configured to delete the second virtual network card among the multiple virtual network cards included in the second container.

[0142] In one embodiment, the configuration device 300 for the network card of the computing power resource container in the intelligent computing center further includes:

[0143] A third module, configured to determine a third container among the multiple computing power resource containers, where the third container is the computing power resource container that meets the network card expansion condition;

[0144] The fourth module is used to determine a third network segment among at least one available network segment, where the available network segment is a network segment in the multiple network segments that is not allocated for use by the third container;

[0145] The fifth module is used to create a third virtual network card based on the network segment attributes of the third network segment, where the network segment attributes include the Internet Protocol address and the Media Access Control address of the corresponding network segment, and the third virtual network card is used to access the third network segment;

[0146] The sixth module is used to migrate the third virtual network card to the third container and perform network card configuration operations in the third container based on the third virtual network card.

[0147] In one embodiment, the configuration device 300 for the network card of the computing power resource container in the intelligent computing center further includes:

[0148] The network card expansion condition includes at least one of the following:

[0149] The first index value of the computing power resource container is greater than or equal to a first threshold value, and the index corresponding to the first index value is the network delay of the computing power resource container;

[0150] The second index value of the computing power resource container is greater than or equal to a second threshold value, and the index corresponding to the second index value is the network load of the computing power resource container;

[0151] The third index value of the computing power resource container is greater than or equal to a third threshold value, and the index corresponding to the third index value is the network packet loss rate of the computing power resource container.

[0152] In one embodiment, the first index value is used to represent: the network delay of the computing power resource container in the target time period;

[0153] The second index value is used to represent: the network load of the computing power resource container in the target time period;

[0154] The third index value is used to represent: the network packet loss rate of the computing power resource container in the target time period;

[0155] Wherein, the start time of the target time period is the current time, and the duration of the target time period is a set duration.

[0156] In one embodiment, the configuration device 300 for the network card of the computing power resource container in the intelligent computing center further includes:

[0157] The seventh module is used to determine a fourth container among the multiple computing power resource containers, where the fourth container is the computing power resource container with a network usage rate less than or equal to a fourth threshold value;

[0158] The eighth module is used to determine the network segment with the lowest network traffic among multiple network segments used by the fourth container as the fourth network segment;

[0159] The ninth module is used to release the network resources corresponding to the fourth virtual network card in the fourth container, where the fourth virtual network card is the virtual network card used to access the fourth network segment among multiple virtual network cards included in the fourth container;

[0160] The tenth module is used to delete the fourth virtual network card among multiple virtual network cards included in the fourth container.

[0161] The configuration device for the computing power resource container network card of the intelligent computing center provided by the present invention can implement each process of the above-mentioned configuration method for the computing power resource container network card of the intelligent computing center. The technical features correspond one by one and can achieve the same technical effects. To avoid repetition, they will not be elaborated here.

[0162] It should be noted that the configuration device for the computing power resource container network card of the intelligent computing center in the present invention can be a device, or a component, integrated circuit, or chip in an electronic device.

[0163] The present invention also provides an electronic device. Refer to Figure 4 , Figure 4 which is a schematic structural diagram of an electronic device provided in an embodiment of the present invention. The electronic device includes a memory 401, a processor 402, and a program or instruction running on the memory 4401. When the program or instruction is executed by the processor 402, it can implement Figure 1 any step in the corresponding embodiment of the configuration method for the computing power resource container network card of the intelligent computing center and achieve the same beneficial effects, which will not be elaborated here.

[0164] Among them, the processor 402 can be a CPU, ASIC, FPGA, or GPU.

[0165] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above-mentioned embodiment of the configuration method for the computing power resource container network card of the intelligent computing center can be completed by hardware related to program instructions, and the program can be stored in a readable medium.

[0166] The present invention also provides a readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it can implement the above-mentioned Figure 1Any step in the embodiment of the configuration method of the computing power resource container network card of the corresponding intelligent computing center can achieve the same technical effect. To avoid repetition, it will not be elaborated here. The storage medium includes, for example, Read-Only Memory (ROM), Random Access Memory (RAM), magnetic disk, or optical disc, etc.

[0167] The terms "first", "second", etc. in the present invention are used to distinguish similar objects and do not necessarily describe a specific order or sequence. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or node comprising a series of steps or units does not necessarily limit to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or nodes. In addition, the use of "and / or" in the present invention represents at least one of the connected objects. For example, A and / or B and / or C represents seven situations including A alone, B alone, C alone, A and B existing together, B and C existing together, A and C existing together, and A, B, and C existing together.

[0168] It should be noted that in this article, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements not only includes those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such a process, method, article, or device. Without further limitation, an element defined by the statement "comprising one..." does not exclude the existence of another identical element in the process, method, article, or device including the element.

[0169] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-described embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases, the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disc) and includes several instructions for causing a terminal (which can be a mobile phone, computer, server, air conditioner, or a second terminal node, etc.) to execute the methods of the various embodiments of the present invention.

[0170] The embodiments of the present invention are described above in conjunction with the accompanying drawings. However, the present invention is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present invention, those of ordinary skill in the art can also make many forms without departing from the spirit of the present invention and the scope protected by the claims, and all of them fall within the protection scope of the present invention.

Claims

1. A method for configuring a network card for a computing resource container in an intelligent computing center, characterized in that: The method: Step S1: Create a first virtual network card based on first information, wherein the first information includes first data and second data, the first data is index data of a first network segment, the second data is index data of a first container, the first network segment is one of multiple network segments included in a container network, the container network is a network used when a container cluster allocates network segments, the container cluster includes multiple computing resource containers, the first container is one of the multiple computing resource containers, and the first virtual network card is used to access the first network segment; Step S2: determining the first container among the multiple computing power resource containers based on the first information; Step S3: Migrate the first virtual network card to the first container, and perform a network card configuration operation in the first container based on the first virtual network card.

2. The method according to claim 1, characterized in that The method further comprises: Step S1', determining a second container and a second virtual network card in the multiple computing power resource containers based on the second information, wherein the second information includes third data and fourth data, the third data is index data of the second network segment, the fourth data is index data of the second container, the second network segment is one of the multiple network segments included in the container network, the second container is one of the multiple computing power resource containers, and the second virtual network card is a virtual network card for accessing the second network segment among the multiple virtual network cards included in the second container; Step S2': in the second container, releasing the network resources corresponding to the second virtual network card; Step S3': Delete the second virtual network card from the multiple virtual network cards included in the second container.

3. The method according to claim 1, characterized in that The method further comprises: Step S41: determining a third container among the multiple computing resource containers, wherein the third container is the computing resource container that meets the network card expansion condition; Step S42: determining a third network segment in at least one available network segment, wherein the available network segment is a network segment in the multiple network segments that is not allocated to the third container; Step S43: creating a third virtual network card based on the network segment attributes of the third network segment, wherein the network segment attributes include an Internet Protocol address and a Media Access Control address of the corresponding network segment, and the third virtual network card is used to access the third network segment; Step S44: migrate the third virtual network card to the third container, and perform network card configuration operations in the third container based on the third virtual network card.

4. The method according to claim 3, characterized in that in, The network card expansion condition includes at least one of the following: The first indicator value of the computing power resource container is greater than or equal to a first threshold, and the indicator corresponding to the first indicator value is the network delay of the computing power resource container; The second indicator value of the computing power resource container is greater than or equal to a second threshold, and the indicator corresponding to the second indicator value is the network load of the computing power resource container; The third indicator value of the computing power resource container is greater than or equal to a third threshold, and the indicator corresponding to the third indicator value is the network packet loss rate of the computing power resource container.

5. The method according to claim 4, characterized in that The first indicator value is used to represent: the network delay of the computing resource container in the target time period; The second indicator value is used to represent: the network load of the computing resource container in the target time period; The third indicator value is used to represent: the network packet loss rate of the computing power resource container in the target time period.

6. The method according to claim 2, characterized in that The method further comprises: Step S51: determining a fourth container from among the plurality of computing power resource containers, wherein the fourth container is the computing power resource container whose network usage rate is less than or equal to a fourth threshold; Step S52: among the multiple network segments used by the fourth container, determine the network segment with the lowest network traffic as the fourth network segment; Step S53: In the fourth container, release the network resources corresponding to the fourth virtual network card, wherein the fourth virtual network card is a virtual network card for accessing the fourth network segment among the multiple virtual network cards included in the fourth container; Step S54: Delete the fourth virtual network card from the multiple virtual network cards included in the fourth container.

7. A configuration device for a computing resource container network card of an intelligent computing center, characterized in that: The configuration device comprises: A network card creation module, configured to create a first virtual network card based on first information, wherein the first information includes first data and second data, the first data is index data of a first network segment, the second data is index data of a first container, the first network segment is one of multiple network segments included in a container network, the container network is a network used when a container cluster allocates network segments, the container cluster includes multiple computing resource containers, the first container is one of the multiple computing resource containers, and the first virtual network card is used to access the first network segment; A container determination module, configured to determine the first container among the plurality of computing power resource containers based on the first information; The network card configuration module is used to migrate the first virtual network card to the first container and perform a network card configuration operation in the first container based on the first virtual network card.

8. A server, characterized in that: include: A processor, a memory, and a program stored in the memory and executable on the processor, wherein when the program is executed by the processor, the steps of the method for configuring a network card of a computing power resource container of an intelligent computing center as described in any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method for configuring the computing power resource container network card of the intelligent computing center as described in any one of claims 1 to 6.

10. A computer program product, characterized in that It includes computer instructions, which, when executed by a processor, implement the steps of the configuration method of the intelligent computing center computing power resource container network card as described in any one of claims 1 to 6.

Images