A topology identification method of a service system and related equipment

Abstract

The specification provides a topology identification method of a service system and related equipment. The service system includes a switching device and a plurality of service devices; the switching device provides a plurality of interconnected ports, the interconnected ports are connected with any service device in the plurality of service devices, so that the plurality of service devices are interconnected through the plurality of interconnected ports; the method is applied to the switching device. The method comprises: sending an acquisition request to the plurality of service devices connected with the plurality of interconnected ports respectively, to acquire internal topology information of the plurality of service devices and identity information of the plurality of service devices; based on the connection relationship between the plurality of interconnected ports and the plurality of service devices, and the acquired internal topology information of the plurality of service devices and the identity information of the plurality of service devices, generating topology information of the service system.

Description

Technical Field

[0001] This specification relates to the field of data communication technology, and in particular to a topology identification method and related equipment for a service system. Background Technology

[0002] With the continuous surge in data volume, data centers face the use of a large number of servers. The development of server technology today is increasingly trending towards modularity and resource centralization. Whether it's the current prevalence of Artificial Intelligence (AI) leading to integrated Graphics Processing Unit (GPU) servers, storage expansion leading to hard drive expansion servers, or future memory expansion servers, all are emerging. These GPU integrated servers, hard drive expansion servers, and memory expansion servers can all serve as different modules within a system and can be interconnected and networked through different schemes, such as through a switch matrix, ultimately forming a multi-machine interconnected whole integrating a Central Processing Unit (CPU), GPU, hard drive, and memory.

[0003] However, the various devices in the system are interconnected and interdependent. Therefore, it is crucial to determine the interconnection relationships between the devices and clarify the system topology during system operation for the application and maintenance of the entire system. Summary of the Invention

[0004] In view of this, one or more embodiments of this specification provide a topology identification method and related equipment for a service system.

[0005] Firstly, this specification provides a topology identification method for a service system, the service system comprising a switching device and multiple service devices; the switching device provides multiple interconnect ports, the interconnect ports being connected to any one of the multiple service devices, so that the multiple service devices are interconnected through the multiple interconnect ports; the method is applied to the switching device; the method includes:

[0006] Send acquisition requests to the multiple service devices connected to the multiple interconnect ports respectively, in order to obtain the internal topology information and the identity information of the multiple service devices;

[0007] Based on the connection relationships between the multiple interconnect ports and the multiple service devices, as well as the obtained internal topology information and identity information of the multiple service devices, the topology information of the service system is generated.

[0008] Secondly, this specification provides a topology identification device for a service system, the service system comprising a switching device and multiple service devices; the switching device provides multiple interconnect ports, the interconnect ports being connected to any one of the multiple service devices, so that the multiple service devices are interconnected through the multiple interconnect ports; the device is applied to the switching device; the device includes:

[0009] The acquisition unit is configured to send acquisition requests to the plurality of service devices connected to the plurality of interconnect ports respectively, in order to acquire the internal topology information and the identity information of the plurality of service devices;

[0010] The topology generation unit is used to generate the topology information of the service system based on the connection relationship between the multiple interconnect ports and the multiple service devices, as well as the obtained internal topology information and identity information of the multiple service devices.

[0011] Thirdly, this specification provides a service system, which includes switching equipment and multiple service devices;

[0012] The switching device provides multiple interconnect ports, which are connected to any one of the multiple service devices, so that the multiple service devices can be interconnected through the multiple interconnect ports;

[0013] The switching device is configured to send acquisition requests to the plurality of service devices connected to the plurality of interconnect ports respectively, to acquire the internal topology information and identity information of the plurality of service devices; and to generate the topology information of the service system based on the connection relationship between the plurality of interconnect ports and the plurality of service devices, as well as the acquired internal topology information and identity information of the plurality of service devices.

[0014] Accordingly, this specification also provides a server, including: a memory and a processor; the memory stores a computer program / instructions executable by the processor; when the processor executes the computer program / instructions, it performs the topology identification method of the service system described in the first aspect above.

[0015] Accordingly, this specification also provides a computer-readable storage medium having a computer program / instructions stored thereon, which, when executed by a processor, performs the topology identification method of the service system as described in the first aspect above.

[0016] Accordingly, this specification also provides a computer program product, which includes a computer program / instruction that, when executed by a processor, performs the topology identification method of the service system as described in the first aspect above.

[0017] In summary, this application considers that the internal topology of each device is fixed during module manufacturing. Therefore, it can first obtain the internal topology information and the device's own identity information. Then, the switching device can integrate the obtained internal topology information and identity information of multiple devices to generate the entire system topology. Thus, this application achieves accurate identification of the system topology, thereby enabling flexible construction of the system topology. This allows for flexible interconnection between devices. Even if the interconnection relationship is adjusted (for example, if port 1 of the switching device was originally connected to service device 1, and then port 1 is changed to be connected to service device 2), the system topology identification method provided in this application can still efficiently and accurately identify the adjusted system topology. This ensures that during system operation, each device can determine its location and interconnection relationship based on the identified system topology structure, allowing it to obtain the necessary resources from the accurate location. Attached Figure Description

[0018] Figure 1 This is a schematic diagram of the system architecture of a service system provided in an exemplary embodiment;

[0019] Figure 2 This is a schematic diagram of the system architecture of another service system provided in an exemplary embodiment;

[0020] Figure 3 This is a flowchart illustrating a topology identification method for a service system provided in an exemplary embodiment;

[0021] Figure 4 This is a schematic diagram of the topology of a service system provided in an exemplary embodiment;

[0022] Figure 5 This is a schematic diagram of the structure of a topology identification device for a service system provided in an exemplary embodiment;

[0023] Figure 6 This is a schematic diagram of the structure of a server provided in an exemplary embodiment. Detailed Implementation

[0024] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with one or more embodiments of this specification. Rather, they are merely examples of apparatuses and methods consistent with some aspects of one or more embodiments of this specification as detailed in the appended claims.

[0025] It should be noted that the steps of the corresponding methods are not necessarily performed in the order shown and described in this specification in other embodiments. In some other embodiments, the methods may include more or fewer steps than described in this specification. Furthermore, a single step described in this specification may be broken down into multiple steps in other embodiments; and multiple steps described in this specification may be combined into a single step in other embodiments.

[0026] It should be noted that the terms "first" and "second" used in this application are only used to distinguish different objects and do not limit the order or priority of the two.

[0027] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0028] With the technological advancements in data centers, servers are becoming increasingly modular and resource-centralized. For instance, a data center system may include switching devices and multiple service devices, which can function as different modules (or nodes) within the system. The switching device provides multiple interconnect ports, allowing the service devices to interconnect. In one illustrated embodiment, the service devices primarily include computing devices providing computing capabilities (i.e., computing-type service devices) and storage devices providing storage capabilities (i.e., storage-type computing devices).

[0029] For example, a computing device may include a CPU device (i.e., a CPU integrated server, or a CPU BOX) and a GPU device (i.e., a GPU integrated server, or a GPU BOX), wherein the CPU device may contain at least one CPU, the GPU device may contain at least one GPU, and so on, without being specifically limited in this specification.

[0030] For example, the storage device may include a disk storage device, such as a Just a Bunch of Disks (JBOD), which may contain at least one disk; it may also include a flash storage device, such as a Just a Bunch of Flash (JBOF), which may contain at least one flash memory; it may also include a memory storage device, such as a Just a Bunch of Memory (JBOM), which may contain at least one memory module, etc., and this specification does not specifically limit it in this regard.

[0031] However, existing system software often lacks the flexibility to identify system topology, meaning it cannot proactively recognize the interconnections between devices. This results in a fixed topology in existing systems; for example, port 1 of a switch is always connected to the GPU, port 2 to the disk storage device, port 3 to the CPU, and so on. This is to ensure that during system operation, each device can determine its location and interconnections based on the known, fixed system topology, allowing it to obtain necessary resources from the precise location or accurately pinpoint the location of a fault, and so on.

[0032] Based on this, this specification provides a technical solution that first obtains the internal topology information and identity information of multiple service devices connected to multiple interconnect ports of the switching device, and then the switching device integrates all the information to generate the topology information of the entire system.

[0033] In implementation, the service system may include a switching device and multiple service devices. The switching device provides multiple interconnect ports, each of which can connect to any one of the service devices, enabling interconnection between the multiple service devices. In one illustrated embodiment, the switching device can send acquisition requests to each of the service devices connected to its multiple interconnect ports to obtain the internal topology information and identity information of each service device. Further, the switching device can generate the topology information of the entire service system based on the connection relationships between the multiple interconnect ports and the multiple service devices, as well as the obtained internal topology information and identity information of the multiple service devices.

[0034] In the above technical solutions, this application considers that the internal topology of each device is fixed during module manufacturing. Therefore, the internal topology information and the device's identity information can be obtained first. Then, the switching device can integrate the obtained internal topology information and identity information of multiple devices to generate the entire system topology. In this way, this application achieves accurate identification of the system topology, thereby enabling flexible construction of the system topology. This allows for flexible interconnection between devices. Even if the interconnection relationship is adjusted (for example, port 1 of the switching device was originally connected to service device 1, and then port 1 is changed to be connected to service device 2), the system topology identification method provided by this application can still efficiently and accurately identify the adjusted system topology. This ensures that during system operation, each device can determine its location and interconnection relationship based on the identified system topology structure, and obtain the necessary resources from the accurate location.

[0035] Please see Figure 1 , Figure 1 This is a schematic diagram of a service system architecture provided in an exemplary embodiment. One or more embodiments provided in this specification can... Figure 1 The specific implementation is within the system architecture shown or a similar system architecture. For example... Figure 1 As shown, the system may include a switching device 100 and multiple service devices, such as service devices 200a, 200b, 200c and 200d.

[0036] like Figure 1 As shown, the switching device 100 provides multiple interconnect ports, each of which can be flexibly connected to any one of the multiple service devices, enabling interconnection between the multiple service devices via the interconnect ports. For example, as... Figure 1 As shown, port 0 of switching device 100 can be connected to service device 200a, port 1 of switching device 100 can be connected to service device 200b, port 2 of switching device 100 can be connected to service device 200c, port 3 of switching device 100 can be connected to service device 200d, and so on. This specification does not make specific limitations on these connections.

[0037] For example, when connecting the interconnect port provided by the switching device 100 to the corresponding service device, the interconnect port provided by the switching device 100 can be connected to the port of the corresponding service device itself via a physical cable.

[0038] In one illustrated embodiment, service devices 200a, 200b, 200c, and 200d may include control units. Figure 1(Not shown), the control unit may include a microcontroller embedded in the server device, such as a Baseboard Management Controller (BMC). Alternatively, the control unit may be other chips used for management, such as a CPU. This specification does not specifically limit this; the following embodiments will use a BMC as an example. The BMC is a microcontroller specifically designed for remote server monitoring and management. It is typically located on the server motherboard and is responsible for monitoring server hardware and providing remote management functions. BMCs are widely used in data centers and are an indispensable part of modern data centers. They improve server manageability and reliability, making remote monitoring and maintenance more convenient and efficient.

[0039] Understandably, based on the initial design and development, the internal topology of the switching device 100 and each service device is fixed during manufacturing, and will not change during subsequent system operation.

[0040] However, the interconnection relationships between the various service devices are flexible and variable. For example, each service device can adjust the interaction ports of the switching devices it is connected to, for instance. Figure 1 In the example, port 1 of the switching device 100 was originally connected to service device 200b, and port 2 was originally connected to service device 200c. Later, port 1 can be reconnected to service device 200c, and port 2 can be reconnected to service device 200b, and so on. This specification does not specify any particular connection method. Another example is the addition of a new service device to the service system, such as service device 200e... Figure 1 (Not shown in the image) By adding this service system, port 5 of switch 100 can be connected to service device 200e. Alternatively, the original service device can be removed from the service system, for example, by... Figure 1 The service device 200c is removed from the service system, the connection between the service device 200c and port 2 of the switching device 100 is disconnected, etc., which are not specifically limited in this specification.

[0041] Based on this, when identifying the topology of the entire system, this application can mainly include obtaining the internal topology information of each device (including switching devices and service devices), as well as the corresponding connection relationship between each interactive port provided by the switching device and each service device.

[0042] In one illustrated embodiment, such as Figure 1As shown, in order to identify the current system topology, the switching device 100 can send acquisition requests to service devices 200a, 200b, 200c, and 200d connected to its respective interconnect ports. Correspondingly, the BMC (Browser Control Center) on service device 200a can obtain the internal topology information and identity information of service device 200a based on the received acquisition requests, and then send both the obtained internal topology information and identity information to the switching device 100. The same applies to service devices 200b, 200c, and 200d, and will not be elaborated further here.

[0043] Accordingly, the switching device 100 can receive the internal topology information and identity information of the service devices respectively sent by the BMCs mounted in the service devices 200a, 200b, 200c, and 200d. In one illustrated embodiment, the switching device 100 also carries a BMC, which can obtain the internal topology information and identity information of the switching device 100.

[0044] Furthermore, the switching device 100 can generate, based on the connection relationships between multiple interconnect ports and multiple service devices, as well as the obtained internal topology information and identity information of the multiple service devices, and the internal topology information and identity information of the switching device 100 itself. Figure 1 The topology information of the entire service system shown can be used to generate a topology diagram of the entire service system. The specific generation process is described below. Figure 3 The description of the corresponding embodiments will not be repeated here.

[0045] As described above, this application considers that the internal topology of each device is fixed during module manufacturing. Therefore, the internal topology information and the device's identity information can be obtained first through the control unit (e.g., BMC) built into the device. Then, the control unit of each device can send the obtained information to the switching device connected to it. The switching device can then integrate the received internal topology information and identity information of multiple devices to generate the entire system topology. In this way, this application achieves accurate identification of the system topology, thereby enabling flexible construction of the system topology. This allows for flexible interconnection between devices. Even if the interconnection relationship is adjusted, the system topology identification method provided in this application can still efficiently and accurately identify the adjusted system topology, thus ensuring the front-end application and back-end operation and maintenance of the entire system.

[0046] In one illustrated embodiment, the aforementioned switching device 100 and multiple service devices may be servers with the aforementioned functions. Specifically, it may be a single server or a server cluster consisting of multiple servers, etc. This specification does not make any specific limitations in this regard.

[0047] It should be understood that Figure 1 The system architecture described above is merely illustrative; in some possible implementations, it may include more advanced technologies. Figure 1 The number of devices shown may be more or less, for example, it may include two or more switching devices, etc., but this specification does not specifically limit this.

[0048] Please see Figure 2 , Figure 2 This is a schematic diagram of the system architecture of another service system provided in an exemplary embodiment. One or more embodiments provided in this specification can... Figure 2 The specific implementation is within the system architecture shown or a similar system architecture. For example... Figure 2 As shown above, Figure 1 The multiple service devices shown may specifically include computing devices such as GPU BOX and CPU BOX, and storage devices such as JBOD, JBOF and JBOM. The switching device may be a switch BOX used for interconnection between the various devices.

[0049] like Figure 2 As shown, in addition to several CPUs, the CPU BOX may also include other peripheral devices, such as memory and storage, etc. This manual does not make specific limitations on this.

[0050] like Figure 2 As shown, the switch box, GPU box, CPU box, and JBOD / JBOF / JBOM can establish high-speed interconnection via PCIe bus, NVLink bus, or CXL bus, or via any other possible type of high-speed bus; this specification does not specifically limit this. In one illustrated embodiment, the switch box can also interconnect with the BMC mounted in the GPU box, CPU box, and JBOD / JBOF / JBOM via the Intelligent Platform Management Interface (IPMI), or via other interfaces or buses with the same function, such as I2C, I3C, USB, and UART, etc.; this specification does not specifically limit this.

[0051] Among them, Peripheral Component Interconnect Express (PCIe) is a high-speed serial computer expansion bus standard that supports point-to-point connections, provides higher bandwidth and lower latency, and is widely used in various peripheral connections, such as graphics cards, storage devices, network adapters, etc.

[0052] Compute Express Link (CXL) is a new high-speed interconnect technology designed to accelerate high-speed interconnection between the CPU and peripheral devices (such as memory, storage, and accelerators), improving the performance of data-intensive workloads. CXL supports Coherent Memory Access (CMA), allowing multiple processors to share memory resources, thereby increasing overall system memory bandwidth and reducing latency. While CXL shares some similarities with PCIe technology, it focuses more on memory consistency, whereas PCIe is more general and not limited to memory consistency.

[0053] NVIDIA Link (NVLink) is a high-speed interconnect technology developed by NVIDIA, primarily used for high-speed communication between GPUs to improve parallel computing performance. NVLink offers higher bandwidth and lower latency than PCIe, making it particularly suitable for scenarios requiring large data transfers, such as deep learning and scientific computing, to accelerate data processing. Similar to CXL, NVLink is a high-speed interconnect technology designed for high-performance computing, but it focuses more on communication between GPUs.

[0054] It should be understood that Figure 2 The system architecture described above is merely illustrative; in some possible implementations, it may include more advanced technologies. Figure 2 The specification may include more or fewer devices, such as JBOF, etc., but this specification does not specifically limit this.

[0055] As described above, this application, based on a modular chassis (BOX) architecture and considering current and future possible networking schemes, identifies the interconnection relationships between various devices in a system consisting of computing devices including CPUs / GPUs, storage expansion devices including hard disks / flash memory / RAM, and switches for interconnection between these devices. It establishes correspondences between CPUs and switches, CPUs and components (such as switches, CPUs, GPUs, or various components mounted in JBOD / JBOF / JBOM), devices and components, and cables and ports, thereby providing an accurate system topology framework for front-end applications and back-end operations and maintenance.

[0056] Please see Figure 3 , Figure 3 This is a flowchart illustrating a topology identification method for a service system, provided in an exemplary embodiment. This method can be applied to... Figure 1 or Figure 2 In the system architecture shown, specifically, this method can be applied to Figure 1 or Figure 2 The system architecture shown includes a switching device that provides multiple interconnect ports. Each interconnect port can connect to any one of multiple service devices, enabling interconnection between the service devices. For example... Figure 3 As shown, the method may specifically include the following steps S301-S303.

[0057] Step S301: Send acquisition requests to multiple service devices connected to multiple interconnect ports respectively to obtain the internal topology information and identity information of the multiple service devices.

[0058] As mentioned above, each service device is equipped with a control unit (e.g., a BMC), and the internal topology of each service device remains fixed during manufacturing and after delivery. Based on this, the BMC in each service device can first obtain the internal topology information of the service device.

[0059] In one illustrated embodiment, the switching device can send an acquisition request to a service device connected to its respective interconnect ports, so that the BMC (Browser Control Center) on the service device can acquire the internal topology information of the service device according to the acquisition request. Further, the BMC can send the acquired internal topology information of the service device to the switching device.

[0060] Alternatively, in one illustrated embodiment, when any service device joins the service system and connects to any switching port of the switching device, the BMC mounted on the service device can proactively obtain the internal topology information of the service device and proactively send it to the switching device, etc. This specification does not specifically limit this.

[0061] In one illustrated embodiment, in addition to the BMC, each service device may also carry multiple devices, which may include multiple first devices. These multiple first devices may be connected to the BMC through multiple ports of the I2C bus, or they may be connected to the BMC through other buses with the same function such as I3C. This specification does not specifically limit this, and the following embodiments will use I2C as an example for illustration.

[0062] The Inter-Integrated Circuit (I2C) bus is a simple bidirectional two-wire serial bus protocol that allows a microcontroller (such as a BMC) to communicate with multiple peripheral devices (i.e., first devices). Examples of these first devices include A / D converters, temperature sensors, fan controllers, and power monitoring chips, etc., which are not specifically limited in this specification.

[0063] Accordingly, the internal topology information of the service device may include the I2C bus topology corresponding to the plurality of first devices.

[0064] In one illustrated embodiment, the I2C bus topology may include the physical location information of the plurality of first devices, such as the connection relationships between the plurality of first devices and multiple ports of the I2C bus. Here, multiple ports of the I2C bus can refer to multiple independent I2C buses extended from a single I2C bus. For example, first device 0 may be connected to I2C-0, first device 1 may be connected to I2C-1, first device 2 may be connected to I2C-2, and so on; this specification does not specifically limit this.

[0065] In one illustrated embodiment, the internal topology information of the service device may further include the identity information of the plurality of first devices. For example, the identity information of the first devices may include the type and identifier of the first device, or any other information that may be used to identify the first device. Thus, based on the identity information of the plurality of first devices within the service device and the I2C bus topology corresponding to the plurality of first devices, the topology information related to the I2C bus within the service device can be clearly defined, so as to subsequently generate the topology information of the entire system.

[0066] In one illustrated embodiment, the type of the first device can be represented by the Part Number (PN) of the first device. The PN code is a unique identifier assigned by the manufacturer to a specific model or type of device; it is typically a string and can be numbers, letters, or a combination thereof. The PN code is used to uniquely identify a specific model or type of device.

[0067] In one illustrated embodiment, the identifier of the first device may be represented by the device's Serial Number (SN). The SN is a unique serial number assigned by the manufacturer to each specific device; it is typically a string that can be numbers, letters, or a combination thereof. The SN is used to uniquely identify each device, ensuring that each device is unique globally.

[0068] In one illustrated embodiment, the identity information of the first device may only include the PN code of the first device. If multiple first devices are of the same type, i.e., have the same PN code, the BMC may further obtain the SN code of the first device to uniquely identify the identity of each first device.

[0069] It should be noted that this specification does not specifically limit the method by which the BMC mounted in the service device obtains the internal topology information of the service device. In one illustrated embodiment, the BMC mounted in the service device can obtain the identity information of each first device within the service device through out-of-band I2C, and can also construct the internal topology diagram of the service device based on its own I2C bus topology, etc. This specification does not specifically limit these aspects.

[0070] In one illustrated embodiment, in addition to the I2C bus, the aforementioned multiple first devices can also connect to the BMC via the SMBus (System Management Bus). Correspondingly, the BMC integrated in the service device can obtain the identity information of each first device within the service device via the SMBus bus, and can construct an internal topology diagram of the service device based on its own SMBus bus topology, etc. This specification does not specifically limit this. SMBus is a subset of the I2C protocol, primarily used for system management, especially for communication with management chips on the motherboard. Besides inheriting the basic characteristics of I2C, SMBus adds more command sets and protocol support, which will not be detailed here.

[0071] In one illustrated embodiment, the multiple devices carried by the service device may further include multiple second devices, which may be connected to the service device's own ports via multiple ports of a PCIe bus, an NVLink bus, or a CXL bus. For example, if the service device is a CPU device, the multiple second devices may be multiple CPUs; if the service device is a CPU device, the multiple second devices may be multiple GPUs, and so on. This specification does not specifically limit the scope of these devices.

[0072] In one illustrated embodiment, the second device and the first device described above may also be the same device, that is, the device has both an out-of-band channel managed via, for example, an I2C bus (or an I3C bus, etc.) and an in-band channel used in practice via, for example, a PCIe bus, etc. This specification does not specifically limit this.

[0073] Correspondingly, in addition to the identity information of the multiple first devices and the I2C bus topology, the internal topology information of the service device may also include the identity information of the multiple second devices, as well as the PCIe bus topology, Nvlink bus topology, or CXL bus topology corresponding to the multiple second devices.

[0074] In one of the illustrated embodiments, the identity information of the second device can be referenced from the identity information of the first device described above, and will not be repeated here.

[0075] In one illustrated embodiment, the PCIe bus topology may include the physical location information of the plurality of second devices, such as the connection relationships between the plurality of second devices and the plurality of ports of the PCIe bus. The plurality of ports of the PCIe bus can refer to multiple independent PCIe buses extended from a single PCIe bus. For example, second device 0 may be connected to PCIe-0, second device 1 may be connected to PCIe-1, second device 2 may be connected to PCIe-2, and so on; this specification does not specifically limit this. Generally, a PCIe port can be configured with a maximum bandwidth of x16, i.e., a maximum of 16 transmission lanes (Lanes), and a minimum bandwidth of x16, i.e., a minimum of 4 transmission lanes. However, in some possible embodiments, it may also be configured with x24 bandwidth or x2 bandwidth, etc., which this specification does not specifically limit.

[0076] In one illustrated embodiment, the Nvlink bus topology may include the physical location information of the plurality of second devices, such as the connection relationships between the plurality of second devices and multiple ports of the Nvlink bus. Here, multiple ports of the Nvlink bus can refer to multiple independent Nvlink buses extended from a single Nvlink bus. For example, second device 0 may be connected to Nvlink-0, second device 1 may be connected to Nvlink-1, second device 2 may be connected to Nvlink-2, and so on; this specification does not specifically limit this.

[0077] In one illustrated embodiment, the CXL bus topology may include the physical location information of the plurality of second devices, such as the connection relationships between the plurality of second devices and multiple ports of the CXL bus. Here, the multiple ports of the CXL bus can refer to multiple independent CXL buses extended from a single CXL bus. For example, second device 0 may be connected to CXL-0, second device 1 may be connected to CXL-1, second device 2 may be connected to CXL-2, and so on; this specification does not specifically limit this.

[0078] In this way, based on the identity information of multiple second devices within the service device and the corresponding PCIe bus topology, NVlink bus topology, or CXL bus topology, the topology information related to the PCIe / NVlink / CXL bus within each service device can be clearly identified, so as to generate the topology information of the entire system in the future.

[0079] Furthermore, it should be noted that within the internal topology of the service device, each port of the PCIe bus and multiple ports of the I2C bus are bound together and connected to the corresponding ports of the service device itself. For example, PCIe-0 can be bound to I2C-0 and both connected to port0 of the service device itself, and so on. This specification does not impose specific limitations on this.

[0080] In one illustrated embodiment, the BMC integrated in the service device can obtain not only the internal topology information of the service device, but also the identity information of the service device, and send the identity information of the service device to the switching device. For example, the identity information of the service device may include the device type and device identifier of the service device, or any other information that may be used to represent the identity of the service device.

[0081] In one illustrated embodiment, the device type of the service device can be the type represented by the PN code of the service device, such as computing type or storage type; the device identifier of the service device can be the identifier represented by the SN code of the service device. For details, please refer to the description of the PN code and SN code in the identity information of the first device above, which will not be repeated here.

[0082] It should be noted that this manual does not specifically limit the method by which the BMC mounted on the service device obtains the identity information of the service device.

[0083] In one illustrated implementation, each service device in the system can function as a Field Replaceable Unit (FRU). Correspondingly, the Base Control Center (BMC) onboard each service device can obtain the local service device's identity information through the FRU information, including, for example, the service device's PN code and SN code. The FRU information contains multiple fields that help users and maintenance personnel quickly identify and manage FRUs; among these are the commonly used fields, namely the service device's PN code and SN code.

[0084] Similarly, switching equipment also incorporates control units (such as BMC or MCPU), and the internal topology of the switching equipment remains fixed during manufacturing and after delivery. The control units within the switching equipment can also access the switching equipment's internal topology and identity information; for details, please refer to the descriptions of internal topology and identity information in the aforementioned service equipment section, which will not be repeated here.

[0085] Furthermore, the switching device can receive the internal topology information and identity information of the service device from the BMC (Browser Control Center) integrated within the service device. Ultimately, the switching device can obtain the internal topology information and identity information of multiple service devices connected to its multiple interconnect ports.

[0086] In one illustrated embodiment, the switching device and the BMC (Browser Control Center) integrated in the service device can establish an interconnection via an IPMI bus for communication. In this way, the BMC can send the internal topology and identity information of the service device it has acquired to the switching device via the IPMI bus. Correspondingly, the switching device can obtain the internal topology and identity information of multiple service devices from the BMCs integrated in multiple service devices via the IPMI bus. IPMI is primarily used for remote monitoring and management of servers, including functions such as health status monitoring, event logging, and power management. Using the IPMI protocol for communication supports remote management over a network. IPMI is closely related to the BMC and is typically used for the low-level management and maintenance of servers.

[0087] Step S302: Based on the connection relationship between multiple interconnect ports and multiple service devices, as well as the obtained internal topology information and identity information of multiple service devices, generate the topology information of the service system.

[0088] Furthermore, after obtaining the internal topology information and identity information of the multiple service devices connected to its multiple interconnect ports, the switching device can generate the topology information of the entire service system based on the corresponding connection relationship between the multiple interconnect ports and the multiple service devices, as well as the obtained internal topology information and identity information of the multiple service devices.

[0089] In one illustrated embodiment, the topology information of the service system may include a topology diagram of the service system.

[0090] In one illustrated embodiment, when generating the topology information of the entire service system based on the corresponding connection relationships between the multiple interconnect ports and the multiple service devices, and the obtained internal topology information and identity information of the multiple service devices, the process may specifically include: creating a switching node corresponding to the switching device based on the identity information of the switching device itself; the switching node may include multiple topology interfaces corresponding to the multiple interconnect ports of the switching device; then, creating multiple service nodes corresponding to the multiple service devices based on the obtained identity information of the multiple service devices; then, connecting the multiple service nodes to the multiple topology interfaces based on the connection relationships between the multiple interconnect ports and the multiple service devices, thereby obtaining an external topology diagram corresponding to the multiple service nodes; then, creating an internal topology diagram corresponding to the multiple service nodes based on the obtained internal topology information of the multiple service devices; and finally, creating an internal topology diagram corresponding to the switching node based on the internal topology information of the switching device itself. Furthermore, based on the above external and internal topology diagrams, a topology diagram of the entire service system can be generated, providing an accurate system topology framework for the front-end applications and back-end operations and maintenance of the service system, ensuring the stability and reliability of the entire service system.

[0091] In one illustrated embodiment, the topology diagram of the service system can be a tree diagram that includes the corresponding connection relationships between interconnect ports and service devices, as well as the internal topology of each device.

[0092] For example, please refer to Figure 4 , Figure 4 This is a schematic diagram of the topology of a service system provided in an exemplary embodiment. For example... Figure 4 As shown, the service system includes a switch (SW) and multiple service devices, such as CPU BOX, GPU BOX0, GPU BOX1, JBOD, and JBOM. The CPU BOX is connected to port 0 of the SW, GPU BOX0 is connected to port 1 of the SW, GPU BOX1 is connected to port 2 of the SW, JBOD is connected to port 3 of the SW, and JBOM is connected to port 4 of the SW.

[0093] like Figure 4 As shown, in the internal topology of GPU BOX1, the BMC connects to multiple devices via the I2C bus, such as connecting to Device 0 via I2C-0, Device 1 via I2C-1, and Device 2 via I2C-2, etc. Furthermore, the internal topology of GPU BOX1 can also include multiple GPUs (…). Figure 4(not shown in the image), each GPU can be connected to the corresponding port of GPU BOX1 via the PCIe bus.

[0094] like Figure 4 As shown, the BMC in GPU BOX1 can be interconnected with SW via the IPMI bus.

[0095] It should be understood that Figure 4 The internal topology diagrams of SW, CPU BOX, GPU BOX0, JBOD, and JBOM, which are not shown in the diagram, can be found in GPU BOX1. This manual does not make any specific limitations on them.

[0096] In one illustrated embodiment, the topology information of the service system may also include the BDF (Bus, Device, Function) number of the device, where Bus refers to the PCIe bus number (there may be multiple PCIe buses in a system), Device refers to the number of a device connected to the bus, and Function refers to the number of different functions on the same device. This specification does not make specific limitations on this.

[0097] Furthermore, in one illustrated embodiment, after obtaining the identity information of multiple service devices, the switching device can also configure the port type of each interconnect port to match the device type of the service device it is connected to, such as an uplink port type or a downlink port type (i.e., configure the port as an uplink port or a downlink port).

[0098] As mentioned above, the device type of a service device can include computing type (e.g., Figure 4 The CPU BOX, GPU BOX0, GPU BOX1, and storage type (e.g., shown) are also shown. Figure 4 (As shown in JBOD and JBOM). Accordingly, when configuring the port type of each interconnect port to match the port type of the service device it is connected to, this may specifically include: configuring the port type of the interconnect port connected to the computing type service device among multiple interconnect ports to the uplink port type, for example... Figure 4 Ports 0, 1, and 2, which are connected to CPU BOX, GPU BOX0, and GPU BOX1 respectively, can all be configured as uplink ports; the port type of the interconnect port connected to the storage type service device among the multiple interconnect ports can be configured as a downlink port type, for example... Figure 4 Ports 3 and 4, which are connected to JBOD and JBOM respectively, can both be configured as downlink ports; this manual does not impose any specific restrictions on this.

[0099] Thus, after the system software flexibly identifies the system topology, this application can flexibly adjust and configure the correspondence between the uplink and downlink ports of the SW according to the identified system topology. Furthermore, it can manage each interconnect port according to the port type of each interconnect port. For example, more bandwidth resources can be configured for the uplink port, and less bandwidth resources can be configured for the downlink port, etc., thereby optimizing the network performance of the entire system topology and ensuring the reliable and stable operation of the system.

[0100] Furthermore, after generating the topology information of the entire service system based on all the acquired information, the switching device can then transmit the topology information of the service system (e.g., as described above) Figure 4 The tree diagram shown is sent to multiple service devices so that the multiple service devices can determine the location and interconnection relationship of each device in the system based on the topology information of the service system, thereby ensuring the application and operation and maintenance of the entire system.

[0101] In one illustrated embodiment, a first service device among a plurality of service devices can determine a path to a target device among a second service device based on the topology information of the service system. Based on this path, it obtains target resources from the target device in the second service device to execute the target task in the first service device using those resources. In one illustrated embodiment, the path may include a path formed by a first interconnect port connected to the first service device, a second interconnect port connected to the second service device, an I2C bus port of the target device, or a PCIe / NVlink / CXL bus port, etc.

[0102] For example, still using Figure 4 Taking the system topology shown as an example, assuming the first service device is CPU BOX, the second service device is GPU BOX1, and the target device is Device1 in GPU BOX1, then CPU BOX can... Figure 4 The system topology shown indicates that the path to access Device1 is: SW port0 → SW port2 → I2C-1. Data in Device1 can be obtained through this path to execute the corresponding target task.

[0103] Thus, after the system software flexibly identifies the system topology, this application can flexibly allocate system resources according to the identified system topology. That is, each device can determine the location and interconnection relationship of each device according to the identified system topology, so as to obtain the required resources from the accurate location and ensure the performance of the entire system.

[0104] Furthermore, during the chassis management process, if a fault occurs, the location and information of the faulty component, device, BOX, or link can be accurately determined based on the identified system topology. The system can also monitor and issue accurate alarms at the CPU, SW, and BOX BMC terminals, thereby ensuring the availability of the entire system.

[0105] In summary, this application considers that the internal topology of each device is fixed during manufacturing. Therefore, the internal topology information and the device's identity information can be obtained first through the control unit built into the device. Then, the control unit of each device can send the obtained information to the switching device connected to it. The switching device can then integrate the received internal topology information and identity information of multiple devices to generate the entire system topology. In this way, this application achieves accurate identification of the system topology, thereby enabling flexible construction of the system topology, that is, flexible system networking, allowing flexible interconnection between devices. Even if the interconnection relationship is adjusted, the system topology identification method provided in this application can still efficiently and accurately identify the adjusted system topology, thus ensuring the front-end application and back-end operation and maintenance of the entire system.

[0106] Corresponding to the above method and process implementation, embodiments of this specification also provide a topology identification device for a service system. Please refer to... Figure 5 , Figure 5 This is a schematic diagram of a topology identification device for a service system provided in an exemplary embodiment. The device 50 can be applied to… Figure 1 or Figure 2 The system architecture shown includes a switching device that provides multiple interconnect ports. Each interconnect port can connect to any one of multiple service devices, enabling interconnection between the multiple service devices. For example... Figure 5 As shown, the device 50 includes:

[0107] The acquisition unit 501 is configured to send acquisition requests to the plurality of service devices connected to the plurality of interconnection ports respectively, in order to acquire the internal topology information and the identity information of the plurality of service devices;

[0108] The topology generation unit 502 is used to generate the topology information of the service system based on the connection relationship between the multiple interconnect ports and the multiple service devices, as well as the obtained internal topology information and identity information of the multiple service devices.

[0109] In one illustrated embodiment, the topology information of the service system includes a topology diagram of the service system; the topology generation unit 502 is specifically used for:

[0110] Create a switching node corresponding to the switching device, wherein the switching node includes multiple topology interfaces corresponding to the multiple interconnect ports;

[0111] Based on the obtained identity information of the multiple service devices, multiple service nodes corresponding to the multiple service devices are created;

[0112] Based on the connection relationships between the multiple interconnect ports and the multiple service devices, the multiple service nodes are connected to the multiple topology interfaces respectively, resulting in an external topology diagram corresponding to the multiple service nodes; and...

[0113] Based on the obtained internal topology information of the multiple service devices, an internal topology diagram corresponding to the multiple service nodes is created;

[0114] Based on the external topology diagram and the internal topology diagram, the topology diagram of the service system is generated.

[0115] In one illustrated embodiment, the service device includes a control unit for acquiring the internal topology information and identity information of the service device; the acquisition unit 501 is specifically used for:

[0116] The system receives the internal topology information and identity information of the multiple service devices from the control unit mounted on the multiple service devices.

[0117] In one illustrated embodiment, the control unit includes a microcontroller embedded in the service device.

[0118] In one illustrated embodiment, the microcontroller includes a motherboard management control unit (BMC).

[0119] In one illustrated embodiment, the service device further includes a plurality of first devices; the plurality of first devices are respectively connected to the BMC through multiple ports of the internal integrated circuit I2C bus; the internal topology information of the service device includes the identity information of the plurality of first devices and the I2C bus topology; the I2C bus topology includes the connection relationship between the plurality of first devices and the multiple ports of the I2C bus.

[0120] In one illustrated embodiment, the service device also includes a plurality of second devices;

[0121] The plurality of second devices are connected to the ports of the service device via multiple ports of the PCIe bus through peripheral components; the internal topology information of the service device includes the identity information of the plurality of second devices and the PCIe bus topology; the PCIe bus topology includes the connection relationships between the plurality of second devices and the multiple ports of the PCIe bus; or...

[0122] The plurality of second devices are respectively connected to the ports of the service device through multiple ports of the NVIDIA NVLink bus; the internal topology information of the service device includes the identity information of the plurality of second devices and the NVLink bus topology; the NVLink bus topology includes the connection relationships between the plurality of second devices and the multiple ports of the NVLink bus; or...

[0123] The plurality of second devices are respectively connected to the ports of the service device by calculating multiple ports of the CXL bus; the internal topology information of the service device includes the identity information of the plurality of second devices and the CXL bus topology structure; the CXL bus topology structure includes the connection relationship between the plurality of second devices and the multiple ports of the CXL bus.

[0124] In one illustrated embodiment, the identity information of the service device includes the device type of the service device; the apparatus 50 further includes a port type configuration unit 503, used for:

[0125] Configure the port types of the multiple interconnected ports to match the port types of the service devices they are connected to;

[0126] The multiple interconnect ports are managed based on their port types.

[0127] In one illustrated embodiment, the device type of the service device includes computing type and storage type; the port type configuration unit 503 is specifically used for:

[0128] Configure the port type of the interconnect port that is connected to the service device of the computing type among the plurality of interconnect ports as an uplink port type;

[0129] Configure the port type of the interconnect port that is connected to the service device of the storage type among the plurality of interconnect ports as a downlink port type.

[0130] In one illustrated embodiment, the computing type service device includes any one or more of the following: a central processing unit (CPU) device and a graphics processing unit (GPU) device; wherein the CPU device includes at least one CPU and the GPU device includes at least one GPU;

[0131] The storage type of service device includes any one or more of the following: disk storage device, memory storage device, and flash storage device; wherein the disk storage device includes at least one disk, the memory storage device includes at least one memory, and the flash storage device includes at least one flash memory.

[0132] The specific implementation process of the functions and roles of each unit in the aforementioned device 50 is detailed in the description of the above embodiments and will not be repeated here. It should be understood that the aforementioned device 50 can be implemented through software, hardware, or a combination of both. Taking software implementation as an example, as a logical device, it is formed by the processor (CPU) of the device loading the corresponding computer program instructions into memory for execution. From a hardware perspective, in addition to the CPU and memory, the device typically includes other hardware such as chips for wireless signal transmission and reception, and / or other hardware such as boards for implementing network communication functions.

[0133] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the units or modules can be selected to achieve the purpose of the solution described in this specification, depending on actual needs. Those skilled in the art can understand and implement this without any inventive effort.

[0134] The devices, units, and modules described in the above embodiments can be implemented by computer chips or physical entities, or by products with certain functions. A typical implementation device is a computer, which can take the form of a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email sending and receiving device, game console, tablet computer, wearable device, or any combination of these devices.

[0135] Corresponding to the above method embodiments, this specification also provides a server. Please refer to... Figure 6 , Figure 6 This is a schematic diagram of the structure of a server provided in an exemplary embodiment. For example, the server may be as described above. Figure 1 or Figure 2 The system architecture shown depicts a server for a switching device. This switching device provides multiple interconnect ports, each of which can connect to any of the multiple service devices, enabling interconnection between the service devices. For example... Figure 6As shown, the server may include a processor 1001 and a memory 1002, and may further include an input device 1004 (e.g., a keyboard) and an output device 1005 (e.g., a display). The processor 1001, memory 1002, input device 1004, and output device 1005 may be connected via a bus or other means. Figure 6 As shown, the memory 1002 includes a computer-readable storage medium 1003 storing a computer program executable by the processor 1001. The processor 1001 may be a general-purpose processor, a microprocessor, or an integrated circuit for controlling the execution of the above method embodiments. When running the stored computer program, the processor 1001 can execute various steps of the topology identification method for the service system in the embodiments of this specification, including: sending acquisition requests to multiple service devices connected to multiple interconnect ports respectively to obtain internal topology information and identity information of the multiple service devices; generating topology information of the service system based on the connection relationship between the multiple interconnect ports and the multiple service devices, and the obtained internal topology information and identity information of the multiple service devices, etc. For a detailed description of each step of the above-described topology identification method for the service system, please refer to the previous content; it will not be repeated here.

[0136] Corresponding to the above-described method embodiments, this specification also provides a computer-readable storage medium storing computer programs that, when run by a processor, execute the various steps of the topology identification method for the service system in this specification. Please refer to the description of the above embodiments for details, which will not be repeated here.

[0137] The above description is merely a preferred embodiment of this specification and is not intended to limit this specification. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this specification should be included within the scope of protection of this specification.

[0138] In a typical configuration, a terminal device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0139] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0140] Computer-readable media, including both permanent and non-permanent, removable and non-removable media, can store information using any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data.

[0141] Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information that can be accessed by a computer. As defined herein, computer-readable media does not include transient media, such as modulated data signals and carrier waves.

[0142] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0143] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, the embodiments of this specification can take the form of computer program products implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

Claims

1. A topology identification method for a service system, characterized in that, The service system includes a switching device and multiple service devices; the switching device provides multiple interconnect ports, which are connected to any one of the multiple service devices, enabling interconnection between the multiple service devices through the multiple interconnect ports; the method is applied to the switching device; the method includes: Send acquisition requests to the multiple service devices connected to the multiple interconnect ports respectively, in order to obtain the internal topology information and the identity information of the multiple service devices; Based on the connection relationships between the multiple interconnect ports and the multiple service devices, as well as the obtained internal topology information and identity information of the multiple service devices, the topology information of the service system is generated.

2. The method according to claim 1, characterized in that, The topology information of the service system includes a topology diagram of the service system; the generation of the service system topology information based on the connection relationships between the multiple interconnect ports and the multiple service devices, as well as the obtained internal topology information and identity information of the multiple service devices, includes: Create a switching node corresponding to the switching device, wherein the switching node includes multiple topology interfaces corresponding to the multiple interconnect ports; Based on the obtained identity information of the multiple service devices, multiple service nodes corresponding to the multiple service devices are created; Based on the connection relationships between the multiple interconnect ports and the multiple service devices, the multiple service nodes are connected to the multiple topology interfaces respectively, resulting in an external topology diagram corresponding to the multiple service nodes; and... Based on the obtained internal topology information of the multiple service devices, an internal topology diagram corresponding to the multiple service nodes is created; Based on the external topology diagram and the internal topology diagram, the topology diagram of the service system is generated.

3. The method according to claim 1, characterized in that, The service device is equipped with a control unit, which is used to acquire the internal topology information and identity information of the service device; acquiring the internal topology information and identity information of the multiple service devices includes: The system receives the internal topology information and identity information of the multiple service devices from the control unit mounted on the multiple service devices.

4. The method according to claim 3, characterized in that, The control unit includes a microcontroller embedded in the service device.

5. The method according to claim 4, characterized in that, The microcontroller includes a motherboard management control unit (BMC).

6. The method according to claim 5, characterized in that, The service device also includes multiple first devices; the multiple first devices are connected to the BMC through multiple ports of the internal integrated circuit I2C bus; the internal topology information of the service device includes the identity information of the multiple first devices and the I2C bus topology; the I2C bus topology includes the connection relationship between the multiple first devices and the multiple ports of the I2C bus.

7. The method according to claim 5, characterized in that, The service equipment also includes multiple second devices; The plurality of second devices are connected to the ports of the service device via multiple ports of the PCIe bus through peripheral components; the internal topology information of the service device includes the identity information of the plurality of second devices and the PCIe bus topology; the PCIe bus topology includes the connection relationship between the plurality of second devices and the multiple ports of the PCIe bus; or, The plurality of second devices are respectively connected to the ports of the service device through multiple ports of the NVIDIA NVlink bus; the internal topology information of the service device includes the identity information of the plurality of second devices and the NVlink bus topology; the NVlink bus topology includes the connection relationship between the plurality of second devices and the multiple ports of the NVlink bus; or, The plurality of second devices are respectively connected to the ports of the service device by calculating multiple ports of the CXL bus; the internal topology information of the service device includes the identity information of the plurality of second devices and the CXL bus topology structure; the CXL bus topology structure includes the connection relationship between the plurality of second devices and the multiple ports of the CXL bus.

8. The method according to any one of claims 1-7, characterized in that, The identity information of the service device includes the device type of the service device; the method further includes: Configure the port types of the multiple interconnected ports to match the port types of the service devices they are connected to; The multiple interconnect ports are managed based on their port types.

9. The method according to claim 8, characterized in that, The service devices include computing and storage types; configuring the port types of the multiple interconnect ports connected to the multiple service devices to match the device types of the multiple service devices includes: Configure the port type of the interconnect port that is connected to the service device of the computing type among the plurality of interconnect ports as an uplink port type; Configure the port type of the interconnect port that is connected to the service device of the storage type among the plurality of interconnect ports as a downlink port type.

10. The method according to claim 9, characterized in that, The computing type of service device includes any one or more of the following: a central processing unit (CPU) device and a graphics processing unit (GPU) device; wherein the CPU device includes at least one CPU, and the GPU device includes at least one GPU; The storage type of service device includes any one or more of the following: disk storage device, memory storage device, and flash storage device; wherein the disk storage device includes at least one disk, the memory storage device includes at least one memory, and the flash storage device includes at least one flash memory.

11. A topology identification device for a service system, characterized in that, The service system includes a switching device and multiple service devices; the switching device provides multiple interconnect ports, which are connected to any one of the multiple service devices to enable interconnection between the multiple service devices through the multiple interconnect ports; the apparatus is applied to the switching device; the apparatus includes: The acquisition unit is configured to send acquisition requests to the plurality of service devices connected to the plurality of interconnect ports respectively, in order to acquire the internal topology information and the identity information of the plurality of service devices; The topology generation unit is used to generate the topology information of the service system based on the connection relationship between the multiple interconnect ports and the multiple service devices, as well as the obtained internal topology information and identity information of the multiple service devices.

12. A service system, characterized in that, The service system includes switching equipment and multiple service devices; The switching device provides multiple interconnect ports, which are connected to any one of the multiple service devices, so that the multiple service devices can be interconnected through the multiple interconnect ports; The switching device is configured to send acquisition requests to the plurality of service devices connected to the plurality of interconnect ports respectively, to acquire the internal topology information and identity information of the plurality of service devices; and to generate the topology information of the service system based on the connection relationship between the plurality of interconnect ports and the plurality of service devices, as well as the acquired internal topology information and identity information of the plurality of service devices.

13. A server, characterized in that, include: Memory and processor; The memory stores computer programs / instructions that can be executed by the processor; When the processor runs the computer program / instructions, it performs the method as described in any one of claims 1-10.

14. A computer-readable storage medium, characterized in that, It stores computer programs / instructions thereon, which, when executed by a processor, implement the method as described in any one of claims 1-10.

15. A computer program product, characterized in that, The computer program product includes a computer program / instruction that, when executed by a processor, implements the method as described in any one of claims 1-10.

Images