WO2024103716A1

WO2024103716A1 - Method and apparatus for managing subnets in link, and device and readable medium

Info

Publication number: WO2024103716A1
Application number: PCT/CN2023/100829
Authority: WO
Inventors: 张砚凯; 赵帅
Original assignee: 苏州元脑智能科技有限公司
Priority date: 2022-11-16
Filing date: 2023-06-16
Publication date: 2024-05-23
Also published as: CN115499489B; CN115499489A

Abstract

Provided in the present application are a method and apparatus for managing subnets in a link, and a device and a readable medium. The method comprises: creating a configuration file at a preset position under a directory of a system, and writing, into the configuration file, information of subnets to be connected to; in response to receiving instructions for connecting to the subnets, parsing the configuration file so as to acquire the information of the subnets; calculating the range of IP addresses of the subnets according to the information of the subnets; and according to the calculated range of the IP addresses of the subnets, a host calling a connection establishment mechanism to respectively establish connections with the IP addresses within the range. By means of the solution of the present application, automatic connection between a plurality of devices can be realized, thereby reducing manual operations, saving on labor costs, and avoiding errors occurring in the human operations. The present application relates to the field of computers.

Description

A method, device, equipment and readable medium for subnet management in a link

CROSS-REFERENCE TO RELATED APPLICATIONS

This application claims priority to a Chinese patent application filed with the China Patent Office on November 16, 2022, with application number 202211430496.7 and application name “A method, device, equipment and readable medium for subnet management in a link”, all contents of which are incorporated by reference in this application.

Technical Field

The present application relates to the field of computers, and more specifically to a method, apparatus, device and readable medium for managing subnets in a link.

Background technique

RDMA (Remote-Direct Memory Access) is a high-speed network technology launched by Mellanox, Intel and other companies. Compared with traditional network technology, RDMA can bypass the operating system protocol stack, reduce the number of memory copies, and avoid the system state kernel state switching overhead, thereby providing higher bandwidth, lower latency, and occupying less system resources.

The above are the advantages of RDMA technology as an emerging network transmission technology. The basic principle is similar to the traditional TCP technology. Due to the promotion of manufacturers and the dedication of pioneers, the source code of some RDMA-related applications can also be found on open source websites. RDMA is similar to TCP, so it also has a process of establishing a connection. CM (Connection Management, a component of the RDMA driver, provides some events in the process of establishing a connection) as a component of the RDMA driver user state, plays a pivotal role in the process of establishing a connection. It implements some events on the driver side. Users can rely on these events to know what stage the current connection is in during the process of establishing a connection so as to make corresponding processing later. As we all know, TCP establishes a connection between the server and the client and realizes network communication between the two. The same is true for RDMA. In today's complex network environment, the era of the Internet of Everything, the connection scenarios are complex and the number of connections is large. When there are multiple devices on the same switch or in the LAN, it is an extremely complex task to manually realize the connection between these devices in sequence.

Application Contents

In view of this, the purpose of the embodiments of the present application is to propose a method, device, equipment and readable medium for subnet management in a link. By using the technical solution of the present application, automatic connection between multiple devices can be achieved, manual operation can be reduced, labor costs can be saved, and errors caused by human operation can be avoided.

Based on the above purpose, one aspect of an embodiment of the present application provides a method for subnet management in a link, comprising the following steps:

Create a configuration file in the preset location under the system directory and write the subnet information to be connected into the configuration file;

In response to receiving an instruction to connect to each subnet, parsing the configuration file to obtain subnet information;

Calculate the range of IP addresses of the subnet based on the subnet information;

According to the calculated range of IP addresses of the subnet, the host calls the connection establishment mechanism to establish connections with the IP addresses in the range respectively.

According to one embodiment of the present application, creating a configuration file at a preset location under a directory of the system, and writing the subnet information to be connected into the configuration file includes:

Create a configuration file with a preset name in a preset location under the system directory, and record the address and name of the configuration file;

Write the subnet information to be connected to the created configuration file. The format of the subnet information is IP address/subnet mask.

According to one embodiment of the present application, in response to receiving an instruction to connect to each subnet, parsing the configuration file to obtain subnet information includes:

In response to receiving the instruction to connect to each subnet, finding the configuration file with the corresponding name in the recorded address;

Parse the configuration file to get the values of IP address and subnet mask.

According to one embodiment of the present application, the range of the IP address of the subnet is calculated according to the subnet information, including:

Use the formula N = 2^(32-subnet mask) to calculate the number of IP addresses contained in the subnet information, where N is the number of IP addresses contained in the subnet information;

The range of IP addresses for the subnet is determined to be N-1 consecutive IP addresses after the IP address in the configuration file.

According to an embodiment of the present application, based on the calculated range of IP addresses of the subnet, the host calls a connection establishment mechanism to establish connections with the IP addresses in the range respectively, including:

Call the first API of RDMA and send information to determine whether the link is connected;

In response to receiving the first return information indicating link connectivity, calling the second API of the RDMA and sending information for determining whether the route is resolved successfully;

In response to receiving the second return information indicating successful route resolution, calling a third API of RDMA and sending information for establishing a connection;

In response to receiving the third return information indicating that the connection is successfully established, it is determined that the local device has successfully established a connection with an IP address in the IP address range.

According to one embodiment of the present application, it also includes:

In response to the host successfully establishing a connection with the subnet, the IP address of the subnet is recorded;

In response to the host failing to establish a connection with a subnet, the host re-establishes a connection with the subnet to which the connection failed after a threshold time has passed until a threshold number of times is reached.

According to one embodiment of the present application, it also includes:

In response to receiving an instruction to disconnect from each subnet, deleting the subnet information in the configuration file;

In response to detecting that there is no subnet information in the configuration file, the connection being established with the subnet is stopped, and the established connection is disconnected.

Another aspect of the embodiment of the present application further provides a device for subnet management in a link, the device comprising:

A writing module, wherein the writing module is configured to create a configuration file in a preset location under a system directory, and write the subnet information to be connected into the configuration file;

an acquisition module, the acquisition module being configured to parse the configuration file to acquire the subnet information in response to receiving an instruction to connect to each subnet;

A calculation module, the calculation module is configured to calculate a range of IP addresses of a subnet according to the subnet information;

The connection module is configured to, according to the calculated range of the IP address of the subnet, enable the host to call a connection establishment mechanism to establish connections with the IP addresses in the range respectively.

According to one embodiment of the present application, the writing module is further configured as:

According to one embodiment of the present application, the acquisition module is further configured to:

Parse the configuration file to get the values of IP address and subnet mask.

According to one embodiment of the present application, the computing module is further configured to:

According to one embodiment of the present application, the connection module is further configured as:

According to one embodiment of the present application, a deletion module is further included, and the deletion module is configured as follows:

Another aspect of the embodiments of the present application further provides a computer device, the computer device comprising:

at least one processor; and

The memory stores computer instructions executable on the processor, and the instructions implement the steps of any one of the above methods when executed by the processor.

Another aspect of the embodiments of the present application further provides a non-volatile readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the steps of any one of the above methods are implemented.

The present application has the following beneficial technical effects: the method for subnet management in a link provided by the embodiment of the present application creates a configuration file at a preset location under the system directory, and writes the subnet information to be connected into the configuration file; in response to receiving an instruction to connect to each subnet, the configuration file is parsed to obtain the subnet information; the range of the IP address of the subnet is calculated according to the subnet information; based on the calculated range of the IP address of the subnet, the host calls the connection establishment mechanism to establish connections with the IP addresses within the range respectively. The technical solution can realize automatic connection between multiple devices, reduce manual operations, save labor costs, and avoid errors caused by human operations.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other embodiments can be obtained based on these drawings without paying any creative work.

FIG1 is a schematic flow chart of a method for managing subnets in a link according to an embodiment of the present application;

FIG2 is a schematic diagram of a device for subnet management in a link according to an embodiment of the present application;

FIG3 is a schematic diagram of a computer device according to an embodiment of the present application;

FIG. 4 is a schematic diagram of a non-volatile readable storage medium according to an embodiment of the present application.

Detailed ways

In order to make the objectives, technical solutions and advantages of the present application more clearly understood, the embodiments of the present application are further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.

Based on the above purpose, the first aspect of the embodiment of the present application provides an embodiment of a method for managing subnets in a link. FIG1 shows a schematic flow chart of the method.

As shown in FIG. 1 , the method may include the following steps:

S1 creates a configuration file in a preset location under the system directory, and writes the subnet information to be connected into the configuration file. Design a configuration file to store subnet discovery configuration information, save the configuration file on the local system, and record the saved location and the name of the configuration file. For example, create a configuration file in the system directory, and create a configuration file named "subnet" in the /data directory. The user writes the subnet information expected to be connected into the subnet configuration file. The format of the subnet information is IP address/subnet mask. For example, the user writes 192.168.1.1/28 in the configuration file. The IP in front represents the first IP address in the subnet, and the 28 behind is the value of the subnet mask, which can also be a user-defined value, indicating the range of IP addresses of the subnet.

In response to receiving the instruction to connect to each subnet, S2 parses the configuration file to obtain the subnet information. When it is necessary to automatically connect to each subnet, the host reads the configuration file according to the location and name of the configuration file recorded, and obtains the subnet information in the configuration file, that is, obtains the value of the first IP address and the subnet mask or a custom value.

S3 calculates the range of the subnet IP address according to the subnet information. The calculation rule of the subnet IP address is set to find the range of the relevant IP address according to the subnet information filled in by the user. For example, the number of IP addresses contained in the subnet information is calculated according to the formula N=2^(32-subnet mask). As in the above example, N=2^(32-28)=16, that is, there are 16 IP addresses, so the range of the subnet IP address is 192.168.1.1~192.168.1.16.

S4 According to the calculated range of IP addresses of the subnet, the host calls the connection establishment mechanism to establish connections with the IP addresses in the range. After obtaining the IP address range, the host establishes a connection to each IP address in turn, relying on the RDMA CM connection establishment mechanism. From initiating a connection to successfully connecting, a total of three CM events (RDMA_CM_EVENT_ADDR_RESOLVED, RDMA_CM_EVENT_ROUTE_RESOLVED, RDMA_CM_EVENT_ESTABLISHED) are experienced. These three events are generated after calling three APIs (rdma_resolve_addr, rdma_resolve_route, rdma_connect). First, the host sends rdma_resolve_addr (cm_id, src_ip, dst_ip, timeout), where src_ip is the host IP address, dst_ip is the target IP address (i.e., the IP address in the IP address range), cm_id is a structure pointer of type (struct rdma_cm_id*), and establishing a connection requires creating the structure pointer by calling the rdma_create_id interface, and timeout is a custom timeout. The rdma_resolve_add process will be blocked. If rdma_resolve_addr does not return a result within the specified time, the function will time out and exit, indicating that rdma_resolve_addr has failed and needs to be retried until it succeeds. If the link is connected, you will receive RDMA_CM_EVENT_ADDR_RESOLVED to indicate success. If you receive RDMA_CM_EVENT_ADDR_ERROR, it means that there is a problem with the link and the connection cannot be established. At this time, you can send a warning to the administrator or wait for a certain period of time and try again. After receiving the success After receiving the return information, the host sends rdma_resolve_route(cm_id, timeout). If RDMA_CM_EVENT_ROUTE_RESOLVED is received, it means the route resolution is successful. If RDMA_CM_EVENT_ROUTE_ERROR is received, it means failure. After receiving the successful return information, the host sends rdma_connect(cm_id, arg), where arg is a structure pointer of type (struct rdma_conn_param*). Before calling rdma_connect to initiate a connection, you need to apply for a struct rdma_conn_param structure space. The main purpose is to fill in some attribute information of the local connection, such as queue depth, current queue number and other information to tell the target end of the connection. If RDMA_CM_EVENT_ESTABLISHED is received, it indicates that the connection is established successfully. If other events are received, it indicates that the connection fails. If the connection is established successfully with the current IP address, the current IP address information is recorded and the connection with the next IP address is started. When all IP addresses in the subnet have tried to establish a connection, a timer is set, for example, to try to establish a connection with the IP address that was not successfully connected after one minute, until the connection is successful or the maximum number of retries is reached.

By using the technical solution of the present invention, automatic connection between multiple devices can be achieved, manual operations can be reduced, labor costs can be saved, and errors caused by manual operations can be avoided.

In a preferred embodiment of the present application, creating a configuration file in a preset location under a system directory, and writing the subnet information to be connected into the configuration file includes:

Write the subnet information to be connected to the created configuration file. The format of the subnet information is IP address/subnet mask. For example, if the user writes 192.168.1.1/28 in the configuration file, the first IP represents the first IP address in the subnet, and the following 28 is the value of the subnet mask, which can also be a user-defined value, indicating the range of the subnet IP address. The subnet mask or the customized value ranges from 0 to 32.

In a preferred embodiment of the present application, in response to receiving an instruction to connect to each subnet, parsing the configuration file to obtain the subnet information includes:

Parse the configuration file to get the IP address and subnet mask values. You need to get the first IP address and subnet mask or a custom value.

In a preferred embodiment of the present application, the range of the IP address of the subnet calculated according to the subnet information includes:

The range of IP addresses of the subnet is determined as N-1 consecutive IP addresses after the IP address in the configuration file. For example, if the user writes 192.168.1.1/28 in the configuration file, then N = 2^(32-28) = 16, that is, there are 16 IP addresses, so the range of IP addresses of the subnet is 192.168.1.1 to 192.168.1.16.

In a preferred embodiment of the present application, according to the calculated range of the IP address of the subnet, the host calls the connection establishment mechanism to establish connections with the IP addresses in the range respectively, including:

Call the first API of RDMA and send information to determine whether the link is connected, the information is rdma_resolve_addr (cm_id, src_ip, dst_ip, timeout), where src_ip is the IP address of the host, and dst_ip is an IP address in the IP address range;

In response to receiving the first return information indicating link connectivity, calling the second API of RDMA and sending information for determining whether the route is resolved successfully, wherein the first return information is RDMA_CM_EVENT_ADDR_RESOLVED, and the information for determining whether the route is resolved successfully is rdma_resolve_route(cm_id, timeout);

In response to receiving the second return information indicating successful route resolution, calling the third API of RDMA and sending information for establishing a connection, wherein the second return information is RDMA_CM_EVENT_ROUTE_RESOLVED, and the information for establishing a connection is rdma_connect(cm_id, arg);

In response to receiving the third return information indicating that the connection is successfully established, it is determined that the local machine has successfully established a connection with an IP address in the IP address range, wherein the third return information is RDMA_CM_EVENT_ESTABLISHED. If the return information received in any step indicates failure, the next step is not performed, and a corresponding alarm may be issued to the management, or a retry may be performed after a certain period of time. When an IP address is successfully connected, the same steps are continued to establish a connection with the next IP address until all subnets are successfully connected.

In a preferred embodiment of the present application, it also includes:

In response to the host failing to establish a connection with the subnet, the host re-establishes a connection with the subnet that failed to establish a connection every threshold time until the threshold number of times is reached. Or when all IP addresses in the subnet have tried to establish a connection, a timer is set, such as one minute later, to try to establish a connection with the IP address that failed to connect again until the connection is successful or the maximum number of retries is reached.

In a preferred embodiment of the present application, it also includes:

In response to detecting that there is no subnet information in the configuration file, the connection being established with the subnet is stopped, and the established connection is disconnected. If the user wishes to disconnect all devices connected in the subnet, he only needs to delete the subnet information in the configuration file. When it is detected that there is no subnet information to be connected, the current connection is terminated first, and all IP addresses that have been successfully connected within the subnet range are disconnected.

In view of the huge workload and difficulty in establishing connections between multiple RDMA devices, the use of this subnet discovery technology based on RDMA links can easily achieve automatic connections between multiple devices, reduce manual operations, save labor costs, and avoid the error-prone characteristics of manual operations.

By using the technical solution of the present application, automatic connection between multiple devices can be achieved, manual operations can be reduced, labor costs can be saved, and errors caused by human operations can be avoided.

It should be noted that a person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the above-mentioned program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc. The above-mentioned computer program embodiments can achieve the same or similar effects as the corresponding above-mentioned arbitrary method embodiments.

In addition, the method disclosed in the embodiment of the present application can also be implemented as a computer program executed by a CPU, and the computer program can be stored in a non-volatile readable storage medium. When the computer program is executed by the CPU, the above functions defined in the method disclosed in the embodiment of the present application are performed.

Based on the above purpose, a second aspect of an embodiment of the present application provides a device for subnet management in a link. As shown in FIG2 , the device 200 includes:

In a preferred embodiment of the present application, the writing module is further configured as:

In a preferred embodiment of the present application, the acquisition module is further configured to:

Parse the configuration file to get the values of IP address and subnet mask.

In a preferred embodiment of the present application, the calculation module is further configured as:

In a preferred embodiment of the present application, the connection module is further configured as:

Call the first API of RDMA and send rdma_resolve_addr(cm_id, src_ip, dst_ip, timeout), where src_ip is the IP address of the host and dst_ip is an IP address in the IP address range;

In response to receiving the return information RDMA_CM_EVENT_ADDR_RESOLVED, the second API of RDMA is called and rdma_resolve_route(cm_id, timeout) is sent;

In response to receiving the return information RDMA_CM_EVENT_ROUTE_RESOLVED, the third API of RDMA is called and rdma_connect (cm_id, arg) is sent;

In response to receiving the return information RDMA_CM_EVENT_ESTABLISHED, it is determined that the local machine has successfully established a connection with an IP address in the IP address range.

In a preferred embodiment of the present application, a deletion module is further included, and the deletion module is configured as follows:

Based on the above purpose, the third aspect of the embodiment of the present application provides a computer device. FIG3 shows a schematic diagram of an embodiment of the computer device provided by the present application. As shown in FIG3, the embodiment of the present application includes the following apparatus: at least one processor 21; and a memory 22, the memory 22 stores computer instructions 23 that can be run on the processor, and when the instructions are executed by the processor, the following method is implemented:

Parse the configuration file to get the values of IP address and subnet mask.

In a preferred embodiment of the present application, it also includes:

Based on the above purpose, the fourth aspect of the embodiment of the present application provides a non-volatile readable storage medium. FIG4 is a schematic diagram of an embodiment of the non-volatile readable storage medium provided by the present application. As shown in FIG4, the non-volatile readable storage medium 31 stores a computer program 32 that performs the following method when executed by a processor:

Parse the configuration file to get the values of IP address and subnet mask.

In a preferred embodiment of the present application, it also includes:

In addition, the method disclosed in the embodiment of the present application can also be implemented as a computer program executed by a processor, and the computer program can be stored in a non-volatile readable storage medium. When the computer program is executed by the processor, the above functions defined in the method disclosed in the embodiment of the present application are performed.

In addition, the above method steps and system units may also be implemented using a controller and a non-volatile readable storage medium for storing a computer program that enables the controller to implement the above steps or unit functions.

It will also be appreciated by those skilled in the art that various exemplary logic blocks, modules, circuits and algorithmic steps described in conjunction with the disclosure herein can be implemented as electronic hardware, computer software or a combination of the two. In order to clearly illustrate this interchangeability of hardware and software, a general description has been given to the functions of various schematic components, blocks, modules, circuits and steps. Whether this function is implemented as software or implemented as hardware depends on specific application and the design constraints imposed on the entire system. Those skilled in the art can implement the function in various ways for every specific application, but this implementation decision should not be interpreted as causing a departure from the disclosed scope of the present application embodiment.

In one or more exemplary designs, the function can be implemented in hardware, software, firmware or any combination thereof. If implemented in software, the function can be stored on a computer-readable medium or transmitted by a computer-readable medium as one or more instructions or codes. Computer-readable media include computer storage media and communication media, and the communication media include any media that helps to transfer a computer program from one location to another. The storage medium can be any available medium that can be accessed by a general or special computer. As an example and not limiting, the computer-readable medium may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage devices, disk storage devices or other magnetic storage devices, or any other medium that can be used to carry or store the required program code in the form of an instruction or data structure and can be accessed by a general or special computer or a general or special processor. In addition, any connection can be appropriately referred to as a computer-readable medium. For example, if a coaxial cable, optical fiber cable, twisted pair, digital subscriber line (DSL) or wireless technologies such as infrared, radio and microwaves are used to send software from a website, server or other remote source, the above-mentioned coaxial cable, optical fiber cable, twisted pair, DSL or wireless technologies such as infrared, radio and microwaves are all included in the definition of the medium. As used herein, disk and disc include compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk, Blu-ray disc, wherein disks usually reproduce data magnetically, while optical discs reproduce data optically with lasers. Combinations of the above should also be included within the scope of computer-readable media.

The above are exemplary embodiments disclosed in the present application, but it should be noted that various changes and modifications may be made without departing from the scope disclosed in the embodiments of the present application as defined in the claims. The functions, steps and/or actions of the method claims according to the disclosed embodiments described herein do not need to be performed in any particular order. In addition, although the elements disclosed in the embodiments of the present application may be described or required in individual form, they may also be understood as multiple unless explicitly limited to the singular.

It should be understood that, as used herein, the singular forms "a", "an", and "the" are used unless the context clearly supports an exception. It is intended to include plural forms as well.It should also be understood that "and/or" used herein is meant to include any and all possible combinations of one or more of the associated listed items.

The serial numbers of the embodiments disclosed in the above-mentioned embodiments of the present application are only for description and do not represent the advantages or disadvantages of the embodiments.

A person of ordinary skill in the art will appreciate that all or part of the steps to implement the above embodiments may be accomplished by hardware, or may be accomplished by instructing related hardware through a program, and the program may be stored in a non-volatile readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk, or an optical disk, etc.

A person of ordinary skill in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of the disclosure of the embodiments of the present application (including the claims) is limited to these examples; under the idea of the embodiments of the present application, the technical features in the above embodiments or different embodiments may also be combined, and there are many other changes in different aspects of the embodiments of the present application as above, which are not provided in detail for the sake of simplicity. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present application shall be included in the protection scope of the embodiments of the present application.

Claims

A method for subnet management in a link, characterized by comprising the following steps:

Create a configuration file in the preset location under the system directory and write the subnet information to be connected into the configuration file;

In response to receiving an instruction to connect to each subnet, parsing the configuration file to obtain subnet information;

Calculate the range of IP addresses of the subnet based on the subnet information;

According to the calculated range of IP addresses of the subnet, the host calls the connection establishment mechanism to establish connections with the IP addresses in the range respectively.
The method according to claim 1 is characterized in that creating a configuration file in a preset location under a directory of the system, and writing the subnet information to be connected into the configuration file comprises:

Create a configuration file with a preset name in a preset location under the system directory, and record the address and name of the configuration file;

Write the subnet information to be connected to the created configuration file. The format of the subnet information is IP address/subnet mask.
The method according to claim 2, characterized in that, in response to receiving an instruction to connect to each subnet, parsing the configuration file to obtain the subnet information comprises:

In response to receiving the instruction to connect to each subnet, finding the configuration file with the corresponding name in the recorded address;

Parse the configuration file to get the values of IP address and subnet mask.
The method according to claim 3, characterized in that calculating the range of the IP address of the subnet according to the subnet information comprises:

Use the formula N = 2^(32-subnet mask) to calculate the number of IP addresses contained in the subnet information, where N is the number of IP addresses contained in the subnet information;

The range of IP addresses for the subnet is determined to be N-1 consecutive IP addresses after the IP address in the configuration file.
The method according to claim 1 is characterized in that, according to the calculated range of the IP addresses of the subnet, the host calls the connection establishment mechanism to establish connections with the IP addresses in the range respectively, comprising:

Call the first API of RDMA and send information to determine whether the link is connected;

In response to receiving the first return information indicating link connectivity, calling the second API of RDMA and sending the judgment route Information on whether the parsing was successful;

In response to receiving the second return information indicating successful route resolution, calling a third API of RDMA and sending information for establishing a connection;

In response to receiving the third return information indicating that the connection is successfully established, it is determined that the local device has successfully established a connection with an IP address in the IP address range.
The method according to claim 1, further comprising:

In response to the host successfully establishing a connection with the subnet, the IP address of the subnet is recorded;

In response to the host failing to establish a connection with a subnet, the host re-establishes a connection with the subnet to which the connection failed after a threshold time has passed until a threshold number of times is reached.
The method according to claim 1, further comprising:

In response to receiving an instruction to disconnect from each subnet, deleting the subnet information in the configuration file;

In response to detecting that there is no subnet information in the configuration file, stopping the connection being established with the subnet and disconnecting the established connection;
The method according to claim 5, further comprising:

After all IP addresses in the subnet have attempted to establish a connection with the host, a timer is set to attempt to establish a connection with the IP addresses that have not been successfully connected after a set time based on the timer until the connection is successful or the maximum number of retries is reached.
The method according to claim 5 is characterized in that the information for determining whether the link is connected is rdma_resolve_addr(cm_id, src_ip, dst_ip, timeout), wherein src_ip is the IP address of the host and dst_ip is an IP address in the IP address range.
The method according to claim 5 is characterized in that the first returned information is RDMA_CM_EVENT_ADDR_RESOLVED, and the information for determining whether the route is resolved successfully is rdma_resolve_route(cm_id, timeout).
The method according to claim 9 or 10 is characterized in that the timeout is a custom timeout period.
The method according to claim 5 is characterized in that the second return information is RDMA_CM_EVENT_ROUTE_RESOLVED, and the information for establishing the connection is rdma_connect(cm_id, arg).
The method according to claim 5 is characterized in that the third return information is RDMA_CM_EVENT_ESTABLISHED.
The method according to claim 5 is characterized in that an alarm message is issued when any one of the first return information, the second return information and the third return information indicates a failure.
The method according to claim 5 is characterized in that when any one of the first return information, the second return information and the third return information indicates failure, retrying after waiting for a predetermined period of time.
The method according to claim 1 is characterized in that after obtaining the range of IP addresses, it also includes: establishing a connection for each IP address in turn based on the RDMA CM connection mechanism.
The method according to claim 5 is characterized in that the following three CM events are passed from initiating the connection to successfully connecting: RDMA_CM_EVENT_ADDR_RESOLVED, RDMA_CM_EVENT_ROUTE_RESOLVE, and RDMA_CM_EVENT_ESTABLISHED; the three CM events are generated by calling the following three APIs respectively: rdma_resolve_addr, rdma_resolve_route, and rdma_connect.
A device for subnet management in a link, characterized in that the device comprises:

A writing module, wherein the writing module is configured to create a configuration file at a preset location under a directory of the system, and write the subnet information to be connected into the configuration file;

an acquisition module, the acquisition module being configured to parse the configuration file to acquire the subnet information in response to receiving an instruction to connect to each subnet;

A calculation module, wherein the calculation module is configured to calculate a range of IP addresses of a subnet according to the subnet information;

The connection module is configured to, according to the calculated range of the IP address of the subnet, enable the host to call a connection establishment mechanism to establish connections with the IP addresses in the range respectively.
A computer device, comprising:

at least one processor; and

A memory storing computer instructions executable on the processor, wherein the instructions, when executed by the processor, implement the steps of the method according to any one of claims 1 to 17.
A non-volatile readable storage medium storing a computer program, wherein the computer program implements the steps of the method described in any one of claims 1 to 17 when executed by a processor.