WO2025200512A1 - 端口的识别方法及系统、非易失性可读存储介质及电子装置 - Google Patents
端口的识别方法及系统、非易失性可读存储介质及电子装置Info
- Publication number
- WO2025200512A1 WO2025200512A1 PCT/CN2024/134531 CN2024134531W WO2025200512A1 WO 2025200512 A1 WO2025200512 A1 WO 2025200512A1 CN 2024134531 W CN2024134531 W CN 2024134531W WO 2025200512 A1 WO2025200512 A1 WO 2025200512A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- mapping relationship
- resource pool
- speed signal
- port
- bmc
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/104—Peer-to-peer [P2P] networks
- H04L67/1087—Peer-to-peer [P2P] networks using cross-functional networking aspects
- H04L67/1091—Interfacing with client-server systems or between P2P systems
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L61/00—Network arrangements, protocols or services for addressing or naming
- H04L61/09—Mapping addresses
- H04L61/25—Mapping addresses of the same type
- H04L61/2503—Translation of Internet protocol [IP] addresses
- H04L61/255—Maintenance or indexing of mapping tables
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L61/00—Network arrangements, protocols or services for addressing or naming
- H04L61/50—Address allocation
- H04L61/5007—Internet protocol [IP] addresses
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L61/00—Network arrangements, protocols or services for addressing or naming
- H04L61/50—Address allocation
- H04L61/5061—Pools of addresses
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/14—Session management
- H04L67/141—Setup of application sessions
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/14—Session management
- H04L67/146—Markers for unambiguous identification of a particular session, e.g. session cookie or URL-encoding
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/2866—Architectures; Arrangements
Definitions
- connection topology relationship i.e., the third mapping relationship
- a port identification method including: configuring a first mapping relationship between multiple first port identifiers and multiple first high-speed signal ports of an IO resource pool, wherein the first port identifier is used to identify an identification device of the IO resource pool, and the multiple identification devices correspond one-to-one to the multiple first high-speed signal ports; receiving a second mapping relationship sent by a second BMC of the device resource pool, wherein the second mapping relationship is used to indicate a correspondence between the second high-speed signal port and the second port identifier, the second high-speed signal port is a high-speed signal port of the device resource pool, and the multiple first port identifiers include the second port identifier; determining a third mapping relationship based on the first mapping relationship and the second mapping relationship, wherein the third mapping relationship is used to indicate a one-to-one correspondence between a third high-speed signal port corresponding to a communication channel in a connected state and the second high-speed signal port, the communication channel in
- receiving the second mapping relationship sent by the second BMC of the device resource pool includes one of the following: sending acquisition requests to the multiple second BMCs according to the first IP addresses of the multiple device resource pools, so as to obtain the multiple second mapping relationships through the acquisition requests, wherein the first IP address is used for the first BMC and the second BMC of the IO resource pool to perform network communication; and receiving the multiple second mapping relationships sent by the multiple second BMCs according to a preset frequency.
- determining a third mapping relationship based on the first mapping relationship and the second mapping relationship includes: determining multiple second port identifiers and multiple second high-speed signal ports indicated by multiple second mapping relationships; matching multiple second port identifiers among the multiple first port identifiers, and matching multiple third high-speed signal ports corresponding to the multiple second port identifiers; and establishing a third mapping relationship based on the multiple second high-speed signal ports and the multiple third high-speed signal ports.
- the method further includes: upon receiving an update request sent by the second BMC, parsing a fourth mapping relationship from the update request, wherein the fourth mapping relationship is used to indicate the correspondence between the second high-speed signal port and the second port identifier; and in response to the update request, updating the third mapping relationship based on the fourth mapping relationship.
- the second BMC is configured to report an update request to the first BMC when determining that a topological connection relationship between high-speed signal ports has changed.
- a port identification method including: determining a second mapping relationship between a second high-speed signal port of a device resource pool and a second port identifier, wherein the second port identifier is used to identify an identification device of the IO resource pool; sending the second mapping relationship to a first BMC of the IO resource pool to instruct the first BMC to determine a third mapping relationship based on pre-configured first mapping relationships and second mapping relationships, wherein the first mapping relationship is used to indicate a one-to-one correspondence between multiple first port identifiers of multiple identification devices and multiple first high-speed signal ports of the IO resource pool, the multiple first port identifiers include the second port identifier, and the third mapping relationship is used to indicate a one-to-one correspondence between a third high-speed signal port corresponding to a communication channel in a connected state and the second high-speed signal port, the communication channel in a connected state is used for communication between the IO resource pool and the device resource pool, and
- determining a second mapping relationship between a second high-speed signal port of a device resource pool and a second port identifier includes: when the device resource pool is powered on, scanning an identification device of an IO resource pool through multiple fourth high-speed signal ports of the device resource pool; determining a fourth high-speed signal port of the identification device scanned among the multiple fourth high-speed signal ports as a second high-speed signal port, and determining a second port identifier of the identification device scanned through the second high-speed signal port; and determining a second mapping relationship based on the second high-speed signal port and the second port identifier.
- verifying whether the IO resource pool and the device resource pool belong to the same system based on the second IP address includes: verifying whether the IO resource pool and the device resource pool belong to the same converged architecture cabinet based on the second IP address, wherein the converged architecture cabinet includes an IO resource pool and multiple device resource pools that are independent of each other; if it is verified based on the second IP address that the IO resource pool and the device resource pool belong to the same converged architecture cabinet, determining that the IO resource pool and the device resource pool belong to the same system.
- an electronic device including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.
- FIG1 is a hardware structure block diagram of a central processing unit of a port identification method according to an embodiment of the present application
- FIG4 is a flow chart (I) of a method for identifying a port according to an embodiment of the present application
- FIG6 is a schematic flow chart of a method for identifying a high-speed signal port topology according to an embodiment of the present application
- FIG7 is a schematic diagram showing the connection of high-speed signal ports of a converged architecture system according to an embodiment of the present application.
- FIG9 is a diagram (II) of a hardware circuit design for high-speed signal port topology identification in a converged architecture system according to an embodiment of the present application;
- FIG10 is a structural block diagram of a port identification system according to an embodiment of the present application.
- FIG1 is a hardware structure block diagram of a central processing unit according to a port identification method of an embodiment of the present application.
- the central processing unit may include one or more (only one is shown in FIG1 ) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the central processing unit may also include a transmission device 106 and an input/output device 108 for communication functions.
- FIG1 is only for illustration and does not limit the structure of the central processing unit.
- the central processing unit may also include more or fewer components than those shown in FIG1 , or have a configuration different from that shown in FIG1 .
- the memory 104 can be configured to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the port identification method in the embodiment of the present application.
- the processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, implementing the above-mentioned method.
- the memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory.
- the memory 104 may include a memory remotely located relative to the processor 102, and these remote memories may be connected to the central processing unit via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
- the transmission device 106 is configured to receive or transmit data via a network.
- the aforementioned network may include a wireless network provided by the communication provider of the central processing unit.
- the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to communicate with the Internet.
- the transmission device 106 can be a radio frequency (RF) module, which is configured to communicate with the Internet wirelessly.
- NIC network interface controller
- RF radio frequency
- FIG4 is a flow chart (I) of a method for identifying a port according to an embodiment of the present application. As shown in FIG4 , the process includes the following steps:
- Step S402 configuring a first mapping relationship between a plurality of first port identifiers and a plurality of first high-speed signal ports of an IO (Input/Output) resource pool, wherein the first port identifier is used to identify an identification device of the IO resource pool, and the plurality of identification devices correspond one-to-one to the plurality of first high-speed signal ports;
- IO Input/Output
- Step S404 receiving a second mapping relationship sent by a second BMC (Baseboard Management Controller) of the device resource pool, wherein the second mapping relationship is used to indicate a correspondence between a second high-speed signal port and a second port identifier, the second high-speed signal port being a high-speed signal port of the device resource pool, and the plurality of first port identifiers including the second port identifier;
- BMC Baseboard Management Controller
- Step S406 Determine a third mapping relationship based on the first mapping relationship and the second mapping relationship, wherein the third mapping relationship is used to indicate a one-to-one correspondence between the third high-speed signal port and the second high-speed signal port corresponding to the communication channel in a connected state, the communication channel in a connected state is used for communication between the IO resource pool and the device resource pool, and the multiple first high-speed signal ports include the third high-speed signal port.
- the first BMC first configures a first mapping relationship between multiple first high-speed signal ports of the IO resource pool and multiple first port identifiers of multiple identification devices, and then receives a second mapping relationship sent by the second BMC of the device resource pool, the second mapping relationship being used to indicate the correspondence between the second high-speed signal port of the device resource pool and the second port identifier; finally, a third mapping relationship is determined based on the first mapping relationship and the second mapping relationship, the third mapping relationship being used to indicate the correspondence between the third high-speed signal port and the second high-speed corresponding to the communication channel in a connected state, and the communication channel in a connected state is used for communication between the IO resource pool and the device resource pool; using the above solution, it is only necessary to configure the identification device for the high-speed signal port on the IO Box (IO resource pool), first through the device Box (device resource pool) Determine the correspondence between the high-speed signal port with the communication channel and the port identifier of the identification device (i.e., the second mapping relationship
- the execution entity of the above steps may be the first BMC, etc., but is not limited thereto.
- step S402 and step S404 can be interchanged, that is, step S404 can be executed first, and then step S402.
- the method before executing step S404: receiving the second mapping relationship sent by the second BMC of the device resource pool, the method further includes: obtaining first IP (Internet Protocol) addresses of multiple device resource pools in the converged architecture cabinet, wherein the multiple device resource pools and the IO resource pool belong to the same system, and the converged architecture cabinet includes: multiple device resource pools, an IO resource pool, and the first IP address is used for the first BMC of the IO resource pool to communicate with the second BMC over the network; when it is determined that multiple device resource pools are powered on, the second IP address of the IO resource pool is sent to the multiple device resource pools according to the first IP address, wherein the second IP address is used for the second BMC to communicate with the first BMC over the network.
- IP Internet Protocol
- the node management service in the IO Box BMC i.e. the above-mentioned first BMC
- IPMI Intelligent Platform Management Interface
- Redfish request in preparation for subsequent network interaction.
- the IO resource pool and the device resource pool exchange each other's IP addresses in advance, so that in the subsequent process of determining the topology relationship (that is, the third mapping relationship mentioned above), the IO Box BMC and the device Box BMC can exchange information through the network channel.
- a complete converged architecture system includes an IO box (IO resource pool) and multiple device boxes.
- the device boxes include the host box (computing resource pool), GPU box, SSD box (SSD storage resource pool), and memory box (memory resource pool). This facilitates flexible reconfiguration and rapid upgrades of key devices such as the CPU (central processing unit), memory, GPU (graphics processing unit), and SSD (solid state drive box).
- receiving the second mapping relationship sent by the second BMC of the device resource pool includes one of the following: sending acquisition requests to multiple second BMCs according to the first IP addresses of multiple device resource pools, so as to obtain multiple second mapping relationships through the acquisition requests, wherein the first IP address is used for the first BMC and the second BMC of the IO resource pool to perform network communication; receiving multiple second mapping relationships sent by multiple second BMCs according to a preset frequency.
- the second mapping relationship can be actively obtained by the IO BMC (i.e., the first BMC mentioned above) by actively initiating an acquisition request, or can be actively reported by the device BMC (i.e., the second BMC); for example, the IO BMC can send acquisition requests to each device resource pool according to its first IP address, and the device BMC sends the second mapping relationship to the IO BMC in response to the acquisition request; or it can be regularly counted and reported at a fixed frequency (i.e., the preset frequency mentioned above) after the device resource pool is powered on.
- a fixed frequency i.e., the preset frequency mentioned above
- step S406 determining the third mapping relationship based on the first mapping relationship and the second mapping relationship can be implemented through the following scheme, including: determining multiple second port identifiers and multiple second high-speed signal ports indicated by multiple second mapping relationships; matching multiple second port identifiers among multiple first port identifiers, and matching multiple third high-speed signal ports corresponding to the multiple second port identifiers; establishing a third mapping relationship based on the multiple second high-speed signal ports and the multiple third high-speed signal ports.
- multiple second port identifiers and multiple second high-speed signal ports indicated by multiple second mapping relationships sent from multiple device resource pools are determined; then, these multiple second port identifiers are matched with the multiple first port identifiers of the first mapping relationship, and matched with the corresponding third high-speed signal ports in the first mapping relationship; and the third mapping relationship is established based on the multiple second high-speed signal ports and the multiple third high-speed signal ports with the determined corresponding relationships.
- the IO BMC obtains the second mapping relationship on each device Box, and after aggregation processing, it can obtain the port connection topology of the entire system.
- the method further includes: upon receiving an update request sent by the second BMC, parsing a fourth mapping relationship from the update request, wherein the fourth mapping relationship is used to indicate the correspondence between the second high-speed signal port and the second port identifier; and in response to the update request, updating the third mapping relationship according to the fourth mapping relationship.
- the first BMC parses the update request to obtain the fourth mapping relationship carried therein, and then automatically updates the third mapping relationship according to the fourth mapping relationship.
- the device resource pool when it is determined that the topological connection relationship between high-speed signal ports has changed, the device resource pool will actively report it and assist the IO resource pool to automatically update the third mapping relationship; thereby ensuring the timeliness and effectiveness of the third mapping relationship.
- the method after determining the third mapping relationship according to the first mapping relationship and the second mapping relationship, the method also includes: sending a control instruction to the IO resource pool to instruct the IO resource pool to determine the target communication channel corresponding to the control instruction according to the third mapping relationship, and sending the control instruction to the target device resource pool corresponding to the control instruction through the target communication channel, wherein the control instruction is used to control the target device resource pool.
- the third mapping relationship can be used to accurately and quickly determine the communication channel for transmitting data instructions (i.e., the above-mentioned control instructions) to ensure that the data instructions are accurately sent to the specific port of the target device.
- data instructions i.e., the above-mentioned control instructions
- FIG5 is a flow chart (II) of a method for identifying a port according to an embodiment of the present application. As shown in FIG5 , the process includes the following steps:
- Step S502 determining a second mapping relationship between a second high-speed signal port of the device resource pool and a second port identifier, wherein the second port identifier is used to identify an identification device of the IO resource pool;
- Step S504 Send the second mapping relationship to the first BMC of the IO resource pool to instruct the first BMC to determine a third mapping relationship based on the pre-configured first mapping relationship and the second mapping relationship, wherein the first mapping relationship is used to indicate a one-to-one correspondence between multiple first port identifiers of multiple identification devices and multiple first high-speed signal ports of the IO resource pool, and the multiple first port identifiers include the second port identifier; the third mapping relationship is used to indicate a one-to-one correspondence between the third high-speed signal port corresponding to the communication channel in a connected state and the second high-speed signal port, and the communication channel in a connected state is used for communication between the IO resource pool and the device resource pool, and the multiple first high-speed signal ports include the third high-speed signal port.
- the second BMC first determines the second mapping relationship between the second high-speed signal port of the device resource pool and the second port identifier, where the second port identifier is used to identify the identification device of the IO resource pool; the second mapping relationship is sent to the first BMC of the IO resource pool, instructing the first BMC to determine the third mapping relationship based on the pre-configured first mapping relationship and the second mapping relationship; wherein the first mapping relationship is a one-to-one correspondence between multiple first port identifiers of multiple identification devices and multiple first high-speed signal ports of the IO resource pool, and the third mapping relationship is used to indicate a one-to-one correspondence between the third high-speed signal port and the second high-speed signal port corresponding to the communication channel in a connected state, and the communication channel in a connected state is used for communication between the IO resource pool and the device resource pool; using the above solution, it is only necessary to configure the high-speed signal port on the IO Box (IO resource pool) To set up an identification device, first determine the correspondence
- the execution entity of the above steps may be the second BMC, etc., but is not limited thereto.
- the method before sending the second mapping relationship to the first BMC of the IO resource pool, the method further includes: upon receiving the second IP address sent by the first BMC, verifying whether the IO resource pool and the device resource pool belong to the same system based on the second IP address, wherein the second IP address is used for network communication between the second BMC and the first BMC; and when it is determined that the IO resource pool and the device resource pool belong to the same system, sending the second mapping relationship to the first BMC based on the second IP address.
- the device box After the device box is powered on, if it receives the second IP address sent by the first BMC, it will first verify based on the second IP address whether the IO resource pool that sends the second IP address and the device resource pool belong to the same converged architecture cabinet to ensure the information transmission security of the converged architecture cabinet; if the verification passes, the second mapping relationship will be sent to the first BMC through the network channel based on the second IP address.
- sending the second mapping relationship to the first BMC of the IO resource pool includes one of the following: sending the second mapping relationship to the first BMC according to the acquisition request when receiving the acquisition request sent by the first BMC; sending the second mapping relationship to the first BMC according to the second IP address of the IO resource pool at a preset frequency, wherein the second IP address is used for network communication between the second BMC and the first BMC.
- the second mapping relationship can be actively obtained by the IO BMC (i.e., the first BMC mentioned above) by actively initiating an acquisition request, or can be actively reported by the device BMC (i.e., the second BMC); for example, the IO BMC can send acquisition requests to each device resource pool according to its first IP address, and the device BMC sends the second mapping relationship to the IO BMC in response to the acquisition request; or it can be regularly counted and reported at a fixed frequency (i.e., the preset frequency mentioned above) after the device resource pool is powered on.
- a fixed frequency i.e., the preset frequency mentioned above
- step S502 determining the second mapping relationship between the second high-speed signal port of the device resource pool and the second port identifier can be implemented through the following scheme, including: when the device resource pool is powered on, scanning the identification device of the IO resource pool through multiple fourth high-speed signal ports of the device resource pool; determining the fourth high-speed signal port of the identification device scanned among the multiple fourth high-speed signal ports as the second high-speed signal port, and determining the second port identifier of the identification device scanned through the second high-speed signal port; and determining the second mapping relationship based on the second high-speed signal port and the second port identifier.
- each device BMC actively counts the topological connection relationship of its own part and sends it to the IO BMC for summary, thereby helping the IO BMC quickly complete the statistics of the third mapping relationship.
- the method further includes: re-determining the fourth mapping relationship between the second high-speed signal port and the second port identifier at the current moment according to a preset frequency; comparing whether the fourth mapping relationship is consistent with the second mapping relationship; and if the fourth mapping relationship is inconsistent with the second mapping relationship, sending an update request to the first BMC to instruct the first BMC to update the third mapping relationship according to the fourth mapping relationship, wherein the update request carries the fourth mapping relationship.
- the device BMC will perform a scan regularly at a preset frequency to determine the fourth mapping relationship between the high-speed signal ports of the device resource pool and the IO resource pool at the current moment; then compare it with the second mapping relationship sent to the IO BMC. If it is determined to be inconsistent, it is determined that the topology connection relationship has been updated, and an update request is sent to the IO BMC to instruct the IO BMC to update.
- the device resource pool when it is determined that the topological connection relationship between high-speed signal ports has changed, the device resource pool will actively report it and assist the IO resource pool to automatically update the third mapping relationship; thereby ensuring the timeliness and effectiveness of the third mapping relationship.
- the identification device of the IO resource pool is scanned through multiple fourth high-speed signal ports of the device resource pool, including: scanning multiple communication channels in sequence through the topology identification service to obtain multiple scanning results, wherein the multiple communication channels correspond one-to-one to the multiple fourth high-speed signal ports; when the scanning result is a first scanning result, determining that the communication channel corresponding to the first scanning result is in a connected state, wherein the first scanning result is used to indicate that the identification device is scanned; when the scanning result is a second scanning result, determining that the communication channel corresponding to the second scanning result is in a disconnected state, wherein the second scanning result is used to indicate that the identification device is not scanned.
- the device BMC scans multiple communication channels corresponding to multiple fourth high-speed signal ports in sequence through the topology identification service to obtain multiple scanning results. If the scanning result indicates that an identified device is scanned, it is determined that the corresponding communication channel is in a connected state; if the scanning result indicates that no identified device is scanned, it is determined that the corresponding communication channel is in a disconnected state, that is, the corresponding fourth high-speed signal port has not established a connection with the high-speed signal port of the IO resource pool.
- I/O resources are centralized in a single IO Box, with device boxes mounted underneath.
- the IO Box and device boxes are equipped with multiple high-speed signal ports. Connectors connect the high-speed signal ports on the device box to the IO Box for high-speed signal transmission. Because an IO Box can host multiple device boxes of the same or different types, and device boxes of the same type share identical physical structures, accurately identifying the connection topology of high-speed signal ports across the entire system is a significant challenge.
- the SW (Switch) number is used to distinguish PCIe (Peripheral Component Interconnect Express) switch devices; the box type is used to distinguish between the five types of boxes; the box number is used to distinguish between multiple device boxes of the same type; and the CDFP port number is used to distinguish between different CDFP ports on a device box.
- PCIe Peripheral Component Interconnect Express
- the CDFP port identifier is configured by setting eight bits in the identification device PCA9554.
- the bits corresponding to the box type and CDFP port number are fixed and require hardware pre-set.
- the bits corresponding to the box number are dynamically set by the device box's BMC.
- the CDFP port on the device box is connected to the IO box via a connector.
- the topology identification logic is shown in Figure 6. After each box is powered on, the IO box's BMC, acting as the host, begins CDFP port topology identification. It sequentially scans the I2C channels corresponding to all CDFP ports on the IO box to see if it can identify the identification device PCA9554 on the device box side.
- the IO box determines which port on which type of box is connected. After scanning all I2C channels, the type of device boxes attached to the IO box and the number of each type of box are known. The device box BMC then needs to act as a slave (from the device) to receive instructions and configure the box number identification bit.
- each device box After identifying a group of device boxes of a specified type to be configured, each device box is assigned a unique box number and sent to each device box to configure the CDFP port identification for each device box.
- the IO box BMC After configuration is complete, the IO box BMC then sequentially scans all I2C channels where the CDFP ports are located, reading the CDFP port identification from the PCA9554 identification device on both the IO box and the device box sides on each channel. After the scan, the connection topology of all CDFP ports in the entire system is obtained.
- the present application provides a method for identifying high-speed signal port topology in a resource pool under a converged architecture.
- the method includes: configuring an identification device for each high-speed signal port on an IO Box as a port identifier.
- the identifier must include the SW number and CDFP port number information, and the identifier must be unique.
- High-speed signal ports on the device box no longer require an identification device for port identification, because each high-speed signal port on a device box resides on a different communication channel, and each high-speed signal port can be distinguished by the communication channel. Only software numbering is required, and the number is mapped to the communication channel where each high-speed signal port resides.
- the management module in the device box After the IO Box and device box are powered on, the management module in the device box sequentially scans the communication channel where each high-speed signal port on the device box resides to see if it can identify the identification device on the IO Box side. If it can be identified, it indicates that the CDFP port on the device box is connected to a port on the IO Box via a connector; if it cannot be identified, it indicates that it is not connected. By reading the port identifier in the identification device, the high-speed signal port on the IO Box is identified. After scanning the communication channels for all high-speed signal ports, the management module in the device box obtains a mapping between the software numbers of all high-speed signal ports on the device box and the corresponding high-speed signal port identifiers on the IO Box.
- the IO Box management module interacts with the management modules on each device box over the network. Through active reporting from the device box or active acquisition by the IO Box, the IO Box management module obtains the mappings for each device box. After aggregation and processing, the port connection topology for the entire system is obtained.
- a converged architecture cabinet contains an IO Box and multiple device Boxes.
- Each Box's management module is a Baseboard Management (BMC).
- the BMC firmware uses the Open BMC (Open Baseboard Management Controller) architecture. All BMCs are connected to the same network switch, forming a local area network (LAN).
- the BMC in the IO Box serves as the master BMC, and the BMCs in each device Box serve as slave BMCs.
- the master BMC communicates with each slave BMC over the network to implement management and control functions for the entire system.
- the IO Box BMC needs to implement a node management module that manages the IP addresses of all the device Box BMCs in the cabinet and communicates with the BMC of each device Box through the network.
- the IO Box contains four layers of switch boards, each with two PCIe switch devices. These expand, network, and distribute the PCIe resources of multiple CPUs within the Host Box.
- a PCIe switch is an IO device configured to expand a single set of PCIe signals into multiple sets of PCIe signals, expanding CPU IO resources.
- Each PCIe switch device provides five CDFP ports (high-speed signal ports), ultimately providing a total of 40 (8 x 5) CDFP ports. These 40 CDFP ports are software-numbered as CDFP0-0 through CDFP0-4, ..., CDFP7-0 through CDFP7-4.
- Each CDFP port contains a set of PCIe 5.0 x 16 high-speed IO signals.
- Each device box is also equipped with a corresponding CDFP port, which is connected via a connector, as shown in Figure 7.
- FIG. 8 shows the hardware circuit design for port topology identification on the IO Box.
- Each CDFP port is configured with an identification device, PCA9554, which is set to write and store the CDFP port identifier.
- the device address of all PCA9554 devices is configured to 0100000.
- the PCA9554 has 8 IO inputs. Based on the actual needs of the IO Box, the definitions of bits 7 to 0 are given. For each PCA9554, bits 7:6 default to 0; bits 5:3 are the SW numbers, i.e., the numbers of the 8 PCIe Switch devices; bits 2:0 are the CDFP port numbers, i.e., the numbers of the 5 CDFP ports on a PCIe Switch device. This is shown in Table 3:
- mapping relationship between the software numbers and port identifiers of the first-layer switch board (with two PCIe switch devices) and the 10 CDFP ports on the IO Box is shown in Table 4:
- mapping between software numbers and port identifiers for CDFP ports on other Layer 3 switch boards is similar to that for Layer 1.
- This mapping is configured in the IO Box BMC configuration file in JSON format.
- the SW number and CDFP port number identifier in the port identification device on the IO Box must be pre-assigned by the hardware.
- Figure 8 takes two SSD Boxes and one GPU Box as examples to show some of the hardware designs for device Box port topology identification.
- the CDFP port on the device Box does not need to be configured with an identification device to identify the port. Since each CDFP port is located on a different I2C channel, the CDFP port can be distinguished through the I2C channel.
- the six CDFP ports are software numbered as: CDFP0 to CDFP5.
- the six CDFP ports are respectively connected to the six channels of the I2C expansion device PCA9548.
- the I2C (Inter-Integrated Circuit, two-wire serial bus) channels where the six CDFP ports are located are defined as virtual bus numbers through aliases, which are 50 to 55 respectively.
- the corresponding relationship is shown in Table 5:
- the main logic of topology identification includes the following steps:
- the node management service in the IO Box BMC sends the IP address information of all the device boxes in sequence through IPMI or Redfish requests, preparing for subsequent network interactions;
- the topology identification service After each device Box is powered on, the topology identification service starts running. Taking the SSD Box as an example, the topology identification service in the BMC scans the virtual I2C bus numbers 50 to 55 in sequence to see if it can scan the device PCA9554 with the address 0100000 on the IO Box. If it can be scanned, it means that this CDFP port on the SSD Box is connected to a CDFP port on the IO Box, and then reads the port identifier in PCA9554; otherwise, it is not connected. After scanning all the virtual I2C bus numbers, the mapping relationship B between the software numbers of the 6 CDFP ports on the SSD Box and the CDFP port identifiers on the IO Box side can be obtained and stored on the Dbus. It also provides an IPMI or Redfish interface for querying the mapping relationship.
- the Redfish interface is an open standard RESTful API (application programming interface) launched by the Distributed Management Task Force (DMTF) for managing data center hardware;
- the topology identification service in the IO Box BMC loads the mapping relationship A between the software number of the CDFP port of the Switch board and the port identifier configured in the JSON file, and then sends IPMI or Redfish requests to all device Box BMCs in turn to obtain the asset information and mapping relationship B of the device Box.
- the connection topology of the CDFP ports on the IO Box of the entire system and the CDFP ports on each device Box can be obtained, so that data instructions can be accurately sent to the specific CDFP port of a specific device Box;
- the topology identification service in the device Box BMC identifies that the mapping relationship B has changed, it actively reports it to the IO Box BMC through IPMI or Redfish request to update the connection topology.
- the IO Box BMC is not connected to the CDFP port identification device PCA9554 via the I2C channel. Therefore, the SW number and CDFP port number identifier in the port identification device must be pre-assigned by hardware. This embodiment solves this problem.
- the topology identification circuit design is shown in Figure 9. The IO Box BMC is connected to the identification device PCA9554 of each CDFP port via PCA9548.
- connection between the device box and the IO box is no longer limited by the complexity of the scanning logic.
- the high-speed signal port on the device box can be connected to any port on the IO box, and the connection relationship can be fully automatically identified.
- module may refer to a combination of software and/or hardware that implements a predetermined function.
- the devices described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.
- the above modules can be implemented through software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.
- An embodiment of the present application further provides a computer non-volatile readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.
- the above-mentioned computer non-volatile readable storage medium may include but is not limited to: USB flash drive, read-only memory (ROM), random access memory (RAM), mobile hard disk, magnetic disk or optical disk, and other non-volatile readable storage media that can store computer programs.
- An embodiment of the present application further provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.
- the electronic device may further include a transmission device and an input/output device, wherein the transmission device is connected to the processor, and the input/output device is connected to the processor.
- An embodiment of the present application further provides a computer program product, including a computer non-volatile readable storage medium, wherein the computer non-volatile readable storage medium stores the computer program product, and when the computer program is executed by a processor, the steps of the method in each embodiment of the present application are implemented.
- modules or steps of the present application described above can be implemented using a general-purpose computing device, they can be concentrated on a single computing device, or distributed across a network composed of multiple computing devices, they can be implemented using program code executable by the computing device, and thus, they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be performed in a different order than herein, or they can be fabricated into separate integrated circuit modules, or multiple modules or steps can be fabricated into a single integrated circuit module for implementation.
- the present application is not limited to any specific combination of hardware and software.
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computing Systems (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
- Small-Scale Networks (AREA)
Abstract
本申请实施例提供了一种端口的识别方法及系统、非易失性可读存储介质及电子装置,其中,该端口的识别方法包括:配置多个第一端口标识与IO资源池的多个第一高速信号端口的第一映射关系;接收设备资源池的第二BMC发送的第二映射关系,其中,第二映射关系用于指示第二高速信号端口和第二端口标识之间的对应关系,第二高速信号端口为设备资源池的高速信号端口;根据第一映射关系和第二映射关系确定第三映射关系,其中,第三映射关系用于指示处于连通状态的通信通道对应的第三高速信号端口与第二高速信号端口之间的一一对应关系,处于连通状态的通信通道用于IO资源池与设备资源池进行通信,多个第一高速信号端口包括第三高速信号端口。
Description
相关申请的交叉引用
本申请要求于2024年3月29日提交中国专利局,申请号为202410379845.X,申请名称为“映射关系的确定方法及系统、存储介质及电子装置”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
本申请实施例涉及计算机领域,特别的,涉及一种端口的识别方法及系统、非易失性可读存储介质及电子装置。
为了满足人工智能、机器学习、智能计算等不同应用场景、不同需求下的资源灵活调配需求,数据中心正加速从以计算为中心的架构向以数据为中心的融合架构转变。在融合架构内,通过IO Box的管理软件对整个系统进行资源管理时,需要知道IO Box与设备Box之间高速信号端口的连接拓扑,以保证数据指令能够准确发送到特定设备Box的特定端口。目前的识别连接拓扑的技术方案是在IO Box设备和设备Box的每个高速信号端口(即CDFP端口)上都设置一个识别设备,用来存储和配置CDFP端口标识,通过识别设备来标识每个高速信号端口对应的详细信息,进而确定系统内的连接拓扑关系。
通过该方案虽然可以识别出整个系统内的高速信号端口的连接拓扑,但通过该方案需要在IO Box和设备Box上的每个高速信号端口都配置一个识别设备做端口标识,且同一个通信通道上识别设备的从地址需不一样,硬件电路设计复杂,增加成本。
针对相关技术中确定IO Box与设备Box之间高速信号端口的连接拓扑关系(即第三映射关系)的方案,需要为IO Box和设备Box上的每个高速信号端口均配置一个识别设备,成本过高且实现逻辑复杂的技术问题,尚未提出有效的解决方案。
本申请实施例提供了一种端口的识别方法及系统、非易失性可读存储介质及电子装置,以至少解决相关技术中确定IO Box与设备Box之间高速信号端口的连接拓扑关系(即第三映射关系)的方案,需要为IO Box和设备Box上的每个高速信号端口均配置一个识别设备,成本过高且实现逻辑复杂的问题。
根据本申请的实施例的第一方面,提供了一种端口的识别方法,包括:配置多个第一端口标识与IO资源池的多个第一高速信号端口的第一映射关系,其中,第一端口标识用于标识IO资源池的识别设备,多个识别设备与多个第一高速信号端口一一对应;接收设备资源池的第二BMC发送的第二映射关系,其中,第二映射关系用于指示第二高速信号端口和第二端口标识之间的对应关系,第二高速信号端口为设备资源池的高速信号端口,多个第一端口标识包括第二端口标识;根据第一映射关系和第二映射关系确定第三映射关系,其中,第三映射关系用于指示处于连通状态的通信通道对应的第三高速信号端口与第二高速信号端口之间的一一对应关系,处于连通状态的通信通道用于IO资源池与设备资源池进行通信,多个第一高速信号端口包括第三高速信号端口。
在一个示例性实施例中,接收设备资源池的第二BMC发送的第二映射关系之前,方法还包括:获取多个设备资源池的第一IP地址,其中,多个设备资源池与IO资源池属于同一系统,第一IP地址用于IO资源池的第一BMC与第二BMC进行网络通信;在确定多个设备资源池上电的情况下,根据第一IP地址将IO资源池的第二IP地址发送给多个设备资源池,其中,第二IP地址用于第二BMC与第一BMC进行网络通信。
在一个示例性实施例中,接收设备资源池的第二BMC发送的第二映射关系,包括以下之一:根据多个设备资源池的第一IP地址分别向多个第二BMC发送获取请求,以通过获取请求获取多个第二映射关系,其中,第一IP地址用于IO资源池的第一BMC与第二BMC进行网络通信;接收多个第二BMC按照预设频率发送的多个第二映射关系。
在一个示例性实施例中,根据第一映射关系和第二映射关系确定第三映射关系,包括:确定多个第二映射关系所指示的多个第二端口标识和多个第二高速信号端口;在多个第一端口标识中匹配多个第二端口标识,以及匹配多个第二端口标识对应的多个第三高速信号端口;根据多个第二高速信号端口和多个第三高速信号端口建立第三映射关系。
在一个示例性实施例中,根据第一映射关系和第二映射关系确定第三映射关系之后,方法还包括:在接收到第二BMC发送的更新请求的情况下,从更新请求中解析出第四映射关系,其中,第四映射关系用于指示第二高速信号端口和第二端口标识之间的对应关系;响应更新请求,根据第四映射关系对第三映射关系进行更新。
在一个示例性实施例中,根据第一映射关系和第二映射关系确定第三映射关系之后,方法还包括:将控制指令发送给IO资源池,以指示IO资源池根据第三映射关系确定控制指令对应的目标通信通道,并通过目标通信通道将控制指令发送给控制指令对应的目标设备资源池,其中,控制指令用于控制目标设备资源池。
在一个示例性实施例中,根据第一IP地址将IO资源池的第二IP地址发送给多个设备资源池,包括:根据第一IP地址通过智能平台管理接口请求依次向多个设备资源池发送第二IP地址;或者根据第一IP地址通过可扩展平台管理的应用程序接口请求依次向多个设备资源池发送第二IP地址。
在一个示例性实施例中,第二BMC被设置为在确定高速信号端口之间的拓扑连接关系发生改变时,向第一BMC上报更新请求。
在一个示例性实施例中,第一BMC中存储了目标文件,目标文件用于配置多个第一端口标识与多个第一高速信号端口之间的映射关系,配置多个第一端口标识与IO资源池的多个第一高速信号端口的第一映射关系,包括:将第一映射关系按照jason格式配置至目标文件中;第一BMC中包括拓扑识别服务,在配置多个第一端口标识与IO资源池的多个第一高速信号端口的第一映射关系之后,方法还包括:在IO资源池上电后,通过拓扑识别服务加载目标文件中配置的第一映射关系。
根据本申请实施例的第二方面,提供了一种端口的识别方法,包括:确定设备资源池的第二高速信号端口与第二端口标识的第二映射关系,其中,第二端口标识用于标识IO资源池的识别设备;将第二映射关系发送至IO资源池的第一BMC,以指示第一BMC根据预先配置的第一映射关系和第二映射关系确定第三映射关系,其中,第一映射关系用于指示多个识别设备的多个第一端口标识与IO资源池的多个第一高速信号端口的一一对应关系,多个第一端口标识包括第二端口标识,第三映射关系用于指示处于连通状态的通信通道对应的第三高速信号端口与第二高速信号端口之间的一一对应关系,处于连通状态的通信通道用于IO资源池与设备资源池进行通信,多个第一高速信号端口包括第三高速信号端口。
在一个示例性实施例中,将第二映射关系发送至IO资源池的第一BMC之前,方法还包括:在接收到第一BMC发送的第二IP地址的情况下,根据第二IP地址校验IO资源池与设备资源池是否属于同一融合架构机柜系统,其中,融合架构机柜包括一个IO资源池和多个设备资源池,第二IP地址用于第二BMC与第一BMC进行网络通信;在确定IO资源池与设备资源池属于同一融合架构机柜系统的情况下,根据第二IP地址将第二映射关系发送至第一BMC。
在一个示例性实施例中,将第二映射关系发送至IO资源池的第一BMC,包括以下之一:在接收到第一BMC发送的获取请求的情况下,根据获取请求将第二映射关系发送至第一BMC;按照预设频率根据IO资源池的第二IP地址将第二映射关系发送至第一BMC,其中,第二IP地址用于第二BMC与第一BMC进行网络通信。
在一个示例性实施例中,确定设备资源池的第二高速信号端口与第二端口标识的第二映射关系,包括:在设备资源池上电的情况下,通过设备资源池的多个第四高速信号端口扫描IO资源池的识别设备;将多个第四高速信号端口中扫描到识别设备的第四高速信号端口确定为第二高速信号端口,以及确定通过第二高速信号端口扫描到的识别设备的第二端口标识;根据第二高速信号端口与第二端口标识确定出第二映射关系。
在一个示例性实施例中,确定设备资源池的第二高速信号端口与第二端口标识的第二映射关系之后,方法还包括:按照预设频率重新确定第二高速信号端口与第二端口标识在当前时刻的第四映射关系;比对第四映射关系与第二映射关系是否一致;在第四映射关系与第二映射关系不一致的情况下,向第一BMC发送更新请求,以指示第一BMC根据第四映射关系更新第三映射关系,其中,更新请求携带有第四映射关系。
在一个示例性实施例中,通过设备资源池的多个第四高速信号端口扫描IO资源池的识别设备,包括:通过拓扑识别服务依次扫描多个通信通道,得到多个扫描结果,其中,多个通信通道与多个第四高速信号端口一一对应;在扫描结果为第一扫描结果的情况下,确定第一扫描结果对应的通信通道处于连通状态,其中,第一扫描结果用于指示扫描到识别设备;在扫描结果为第二扫描结果的情况下,确定第二扫描结果对应的通信通道处于断开状态,其中,第二扫描结果用于指示未扫描到识别设备。
在一个示例性实施例中,根据第二IP地址校验IO资源池与设备资源池是否属于同一系统,包括:根据第二IP地址校验IO资源池与设备资源池是否属于同一个融合架构机柜,其中,融合架构机柜包括相互独立的一个IO资源池和多个设备资源池;在根据第二IP地址校验出IO资源池与设备资源池属于同一个融合架构机柜的情况下,确定IO资源池与设备资源池属于同一系统。
根据本申请实施例的第三方面,提供了一种端口的识别系统,包括:第一BMC,被设置为配置多个第一端口标识与IO资源池的多个第一高速信号端口的第一映射关系,其中,第一端口标识用于标识IO资源池的识别设备,多个识别设备与多个第一高速信号端口一一对应;第二BMC,被设置为确定设备资源池的第二高速信号端口与第二端口标识的第二映射关系,并将第二映射关系发送至第一BMC,其中,第二端口标识用于标识IO资源池的识别设备,多个第一端口标识包括第二端口标识;第一BMC,还被设置为根据第一映射关系和第二映射关系确定第三映射关系,其中,第三映射关系用于指示处于连通状态的通信通道对应的第三高速信号端口与第二高速信号端口之间的一一对应关系,处于连通状态的通信通道用于IO资源池与设备资源池进行通信,多个第一高速信号端口包括第三高速信号端口。
根据本申请实施例的第四方面,还提供了一种计算机非易失性可读存储介质,计算机非易失性可读存储介质中存储有计算机程序,其中,计算机程序被设置为运行时执行上述任一项方法实施例中的步骤。
根据本申请实施例的第五方面,还提供了一种电子装置,包括存储器和处理器,存储器中存储有计算机程序,处理器被设置为运行计算机程序以执行上述任一项方法实施例中的步骤。
根据本申请实施例的第六方面,还提供了一种计算机程序产品,包括计算机程序,计算机程序被处理器执行时实现本申请各个实施例中方法的步骤。
通过本申请,第一BMC先配置IO资源池的多个第一高速信号端口与多个识别设备的多个第一端口标识的第一映射关系,然后接收设备资源池的第二BMC发送的第二映射关系,第二映射关系用于指示设备资源池的第二高速信号端口与第二端口标识之间的对应关系;最后根据第一映射关系和第二映射关系确定出第三映射关系,第三映射关系用于指示处于连通状态的通信通道对应的第三高速信号端口与第二高速,处于连通状态的通信通道用于IO资源池与设备资源池进行通信;采用上述方案,仅需为IO Box(IO资源池)上的高速信号端口配置识别设备,先通过设备Box(设备资源池)确定建立有通信通道的高速信号端口与识别设备的端口标识的对应关系(即第二映射关系),再根据保存的IO Box的高速信号端口与识别设备的端口标识的对应关系(第一映射关系),从而根据第一映射关系与第二映射关系快速确定出IO Box与设备Box之间高速信号端口的连接拓扑关系(即上述第三映射关系),既节省了硬件成本,又简化了处理逻辑;进而解决了相关技术中,确定IO Box与设备Box之间高速信号端口的连接拓扑关系(即第三映射关系)的方案,需要为IO Box和设备Box上的每个高速信号端口均配置一个识别设备,成本过高且实现逻辑复杂的问题。
图1是根据本申请实施例的一种端口的识别方法的中央处理器的硬件结构框图;
图2是根据本申请的一种融合架构的系统结构图;
图3是根据本申请实施例的一种高速信号端口拓扑识别硬件电路设计图;
图4是根据本申请实施例的一种端口的识别方法的流程图(一);
图5是根据本申请实施例的一种端口的识别方法的流程图(二);
图6是根据本申请实施例的一种高速信号端口拓扑识别方法的流程示意图;
图7是根据本申请实施例的一种融合架构系统的高速信号端口的连接示意图;
图8是根据本申请实施例的一种融合架构系统高速信号端口拓扑识别硬件电路设计图(一);
图9是根据本申请实施例的一种融合架构系统高速信号端口拓扑识别硬件电路设计图(二);
图10是根据本申请实施例的端口的识别系统的结构框图。
下文中将参考附图并结合实施例来详细说明本申请的实施例。
需要说明的是,本申请的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象,而不必用于描述特定的顺序或先后次序。
本申请实施例中所提供的方法实施例可以在中央处理器或者类似的运算装置中执行。以运行在中央处理器上为例,图1是根据本申请实施例的一种端口的识别方法的中央处理器的硬件结构框图。如图1所示,中央处理器可以包括一个或多个(图1中仅示出一个)处理器102(处理器102可以包括但不限于微处理器MCU或可编程逻辑器件FPGA等的处理装置)和用于存储数据的存储器104,其中,上述中央处理器还可以包括用于通信功能的传输设备106以及输入输出设备108。本领域普通技术人员可以理解,图1所示的结构仅为示意,其并不对上述中央处理器的结构造成限定。例如,中央处理器还可包括比图1中所示更多或者更少的组件,或者具有与图1所示不同的配置。
存储器104可被设置为存储计算机程序,例如,应用软件的软件程序以及模块,如本申请实施例中的端口的识别方法对应的计算机程序,处理器102通过运行存储在存储器104内的计算机程序,从而执行各种功能应用以及数据处理,即实现上述的方法。存储器104可包括高速随机存储器,还可包括非易失性存储器,如一个或者多个磁性存储装置、闪存、或者其他非易失性固态存储器。在一些实例中,存储器104可包括相对于处理器102远程设置的存储器,这些远程存储器可以通过网络连接至中央处理器。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
传输设备106被设置为经由一个网络接收或者发送数据。上述的网络可选实例可包括中央处理器的通信供应方提供的无线网络。在一个实例中,传输设备106包括一个网络适配器(Network Interface Controller,简称为NIC),其可通过基站与其他网络设备相连从而可与互联网进行通讯。在一个实例中,传输设备106可以为射频(Radio Frequency,简称为RF)模块,其被设置为通过无线方式与互联网进行通讯。
在本实施例中提供了一种端口的识别方法,图4是根据本申请实施例的一种端口的识别方法的流程图(一),如图4所示,该流程包括如下步骤:
步骤S402,配置多个第一端口标识与IO(Input/Output,输入/输出)资源池的多个第一高速信号端口的第一映射关系,其中,第一端口标识用于标识IO资源池的识别设备,多个识别设备与多个第一高速信号端口一一对应;
步骤S404,接收设备资源池的第二BMC(Baseboard Management Controller,基板管理控制器)发送的第二映射关系,其中,第二映射关系用于指示第二高速信号端口和第二端口标识之间的对应关系,第二高速信号端口为设备资源池的高速信号端口,多个第一端口标识包括第二端口标识;
步骤S406,根据第一映射关系和第二映射关系确定第三映射关系,其中,第三映射关系用于指示处于连通状态的通信通道对应的第三高速信号端口与第二高速信号端口之间的一一对应关系,处于连通状态的通信通道用于IO资源池与设备资源池进行通信,多个第一高速信号端口包括第三高速信号端口。
通过上述步骤,第一BMC先配置IO资源池的多个第一高速信号端口与多个识别设备的多个第一端口标识的第一映射关系,然后接收设备资源池的第二BMC发送的第二映射关系,第二映射关系用于指示设备资源池的第二高速信号端口与第二端口标识之间的对应关系;最后根据第一映射关系和第二映射关系确定出第三映射关系,第三映射关系用于指示处于连通状态的通信通道对应的第三高速信号端口与第二高速,处于连通状态的通信通道用于IO资源池与设备资源池进行通信;采用上述方案,仅需为IO Box(IO资源池)上的高速信号端口配置识别设备,先通过设备Box(设备资源池)确定建立有通信通道的高速信号端口与识别设备的端口标识的对应关系(即第二映射关系),再根据保存的IO Box的高速信号端口与识别设备的端口标识的对应关系(第一映射关系),从而根据第一映射关系与第二映射关系快速确定出IO Box与设备Box之间高速信号端口的连接拓扑关系(即上述第三映射关系),既节省了硬件成本,又简化了处理逻辑;进而解决了相关技术中,确定IO Box与设备Box之间高速信号端口的连接拓扑关系(即第三映射关系)的方案,需要为IO Box和设备Box上的每个高速信号端口均配置一个识别设备,成本过高且实现逻辑复杂的问题。
其中,上述步骤的执行主体可以为第一BMC等,但不限于此。
步骤S402和步骤S404的执行顺序是可以互换的,即可以先执行步骤S404,然后再执行S402。
在一个示例性实施例中,执行上述步骤S404:接收设备资源池的第二BMC发送的第二映射关系之前,方法还包括:获取融合架构机柜中多个设备资源池的第一IP(Internet Protocol,网际互连协议)地址,其中,多个设备资源池与IO资源池属于同一系统,融合架构机柜中包括:多个设备资源池,IO资源池,第一IP地址用于IO资源池的第一BMC与第二BMC进行网络通信;在确定多个设备资源池上电的情况下,根据第一IP地址将IO资源池的第二IP地址发送给多个设备资源池,其中,第二IP地址用于第二BMC与第一BMC进行网络通信。
IO Box(即上述IO资源池)和设备Box(即上述设备资源池)上电后,IO Box BMC(即上述第一BMC)中的节点管理服务,通过IPMI(Intelligent Platform Management Interface,智能平台管理接口)或Redfish请求依次向所有设备Box发送其IP地址信息(即上述第二IP地址),为后面网络交互做准备。
通过上述方案,IO资源池与设备资源池预先交换彼此的IP地址,以便于后续确定拓扑关系(即上述第三映射关系)的过程中,IO Box BMC与设备Box BMC之间能够通过网络通道进行信息交互。
需要说明的是,上述设备资源池与IO资源池所属的同一系统可以理解为融合架构系统或融合架构机柜,融合架构的设计特点之一是“资源解耦”,将整个系统解耦为不同的独立池化模块。在融合架构机柜内,这些独立池化模块是以单独Box(资源池)的形式存在。如图2所示,一个完整的融合架构系统包括一个IO Box(IO资源池)和多个设备Box。设备Box包括Host Box(计算资源池)、GPU Box、SSD Box(SSD存储资源池)和Memory Box(内存资源池),有利于CPU(Central Processing Unit,中央处理器)、内存、GPU(Graphics Processing Unit,图形处理单元)、SSD(Solid State Drive Box,固态硬盘)等关键设备的灵活改配与快速升级。
可选的,接收设备资源池的第二BMC发送的第二映射关系,包括以下之一:根据多个设备资源池的第一IP地址分别向多个第二BMC发送获取请求,以通过获取请求获取多个第二映射关系,其中,第一IP地址用于IO资源池的第一BMC与第二BMC进行网络通信;接收多个第二BMC按照预设频率发送的多个第二映射关系。
可选的,第二映射关系可以由IO BMC(即上述第一BMC)主动发起获取请求主动获取,也可以由设备BMC(即上述第二BMC)主动上报;例如,IO BMC可以根据各个设备资源池的第一IP地址分别向其发送获取请求,设备BMC响应于获取请求将第二映射关系发送给IO BMC;也可以是由设备资源池上电后,按照固定频率(即上述预设频率)定期统计并上报。
可选的,上述步骤S406:根据第一映射关系和第二映射关系确定第三映射关系,可以通过以下方案来实现,包括:确定多个第二映射关系所指示的多个第二端口标识和多个第二高速信号端口;在多个第一端口标识中匹配多个第二端口标识,以及匹配多个第二端口标识对应的多个第三高速信号端口;根据多个第二高速信号端口和多个第三高速信号端口建立第三映射关系。
先确定多个设备资源池发送来的多个第二映射关系所指示的多个第二端口标识和多个第二高速信号端口;然后在第一映射关系的多个第一端口标识中匹配这多个第二端口标识,并匹配上第一映射关系中对应的第三高速信号端口;根据确定出对应关系的多个第二高速信号端口和多个第三高速信号端口建立出该第三映射关系。
采用上述方案,IO BMC得到每个设备Box上的第二映射关系,进行汇总处理后即可得到整个系统的端口连接拓扑。
基于上述步骤,根据第一映射关系和第二映射关系确定第三映射关系之后,方法还包括:在接收到第二BMC发送的更新请求的情况下,从更新请求中解析出第四映射关系,其中,第四映射关系用于指示第二高速信号端口和第二端口标识之间的对应关系;响应更新请求,根据第四映射关系对第三映射关系进行更新。
若接收到某一设备资源池的第二BMC发送的更新请求,则第一BMC从更新请求中解析出携带的第四映射关系,然后根据该第四映射关系对第三映射关系进行自动更新。
采用上述方案,在确定高速信号端口之间的拓扑连接关系发生改变时,设备资源池会主动上报,协助IO资源池自动完成第三映射关系的更新;从而保证了第三映射关系的及时性和有效性。
基于上述步骤,根据第一映射关系和第二映射关系确定第三映射关系之后,方法还包括:将控制指令发送给IO资源池,以指示IO资源池根据第三映射关系确定控制指令对应的目标通信通道,并通过目标通信通道将控制指令发送给控制指令对应的目标设备资源池,其中,控制指令用于控制目标设备资源池。
建立好第三映射关系之后,在通过IO Box中的管理软件(例如IO BMC)对整个系统(包括一个IO Box和多个设备Box)进行资源管理时,可以通过第三映射关系准确快速地确定数据指令(即上述控制指令)进行传输的通信通道,以保证数据指令准确发送到目标设备的特定端口。
可选的,本申请提供了另一种端口的识别方法,图5是根据本申请实施例的一种端口的识别方法的流程图(二),如图5所示,该流程包括如下步骤:
步骤S502,确定设备资源池的第二高速信号端口与第二端口标识的第二映射关系,其中,第二端口标识用于标识IO资源池的识别设备;
步骤S504,将第二映射关系发送至IO资源池的第一BMC,以指示第一BMC根据预先配置的第一映射关系和第二映射关系确定第三映射关系,其中,第一映射关系用于指示多个识别设备的多个第一端口标识与IO资源池的多个第一高速信号端口的一一对应关系,多个第一端口标识包括第二端口标识,第三映射关系用于指示处于连通状态的通信通道对应的第三高速信号端口与第二高速信号端口之间的一一对应关系,处于连通状态的通信通道用于IO资源池与设备资源池进行通信,多个第一高速信号端口包括第三高速信号端口。
通过上述步骤,第二BMC先确定设备资源池的第二高速信号端口与第二端口标识的第二映射关系,第二端口标识用于标识IO资源池的识别设备;将第二映射关系发送给IO资源池的第一BMC,指示第一BMC根据预先配置的第一映射关系和第二映射关系确定出第三映射关系;其中,第一映射关系为多个识别设备的多个第一端口标识和IO资源池的多个第一高速信号端口的一一对应关系,第三映射关系用于指示处于连通状态的通信通道对应的第三高速信号端口与第二高速信号端口之间的一一对应关系,处于连通状态的通信通道用于IO资源池与设备资源池进行通信;采用上述方案,仅需为IO Box(IO资源池)上的高速信号端口配置识别设备,先通过设备Box(设备资源池)确定建立有通信通道的高速信号端口与识别设备的端口标识的对应关系(即第二映射关系),再根据保存的IO Box的高速信号端口与识别设备的端口标识的对应关系(第一映射关系),从而根据第一映射关系与第二映射关系快速确定出IO Box与设备Box之间高速信号端口的连接拓扑关系(即上述第三映射关系),既节省了硬件成本,又简化了处理逻辑;进而解决了相关技术中,确定IO Box与设备Box之间高速信号端口的连接拓扑关系(即第三映射关系)的方案,需要为IO Box和设备Box上的每个高速信号端口均配置一个识别设备,成本过高且实现逻辑复杂的问题。
其中,上述步骤的执行主体可以为第二BMC等,但不限于此。
可选的,将第二映射关系发送至IO资源池的第一BMC之前,方法还包括:在接收到第一BMC发送的第二IP地址的情况下,根据第二IP地址校验IO资源池与设备资源池是否属于同一系统,其中,第二IP地址用于第二BMC与第一BMC进行网络通信;在确定IO资源池与设备资源池属于同一系统的情况下,根据第二IP地址将第二映射关系发送至第一BMC。
需要说明的是,上述设备资源池与IO资源池所属的同一系统可以理解为融合架构系统或融合架构机柜。
设备Box上电后,若接收到了第一BMC下发的第二IP地址,则先根据第二IP地址校验发送该第二IP地址的IO资源池与设备资源池是否属于同一融合架构机柜,以保障融合架构机柜的信息传输安全;若校验通过,则根据第二IP地址将该第二映射关系通过网络通道发送至第一BMC。
通过上述方案,IO资源池与设备资源池预先交换彼此的IP地址,以便于后续确定拓扑关系(即上述第三映射关系)的过程中,IO Box BMC与设备Box BMC之间能够通过网络通道进行信息交互。
可选的,将第二映射关系发送至IO资源池的第一BMC,包括以下之一:在接收到第一BMC发送的获取请求的情况下,根据获取请求将第二映射关系发送至第一BMC;按照预设频率根据IO资源池的第二IP地址将第二映射关系发送至第一BMC,其中,第二IP地址用于第二BMC与第一BMC进行网络通信。
可选的,第二映射关系可以由IO BMC(即上述第一BMC)主动发起获取请求主动获取,也可以由设备BMC(即上述第二BMC)主动上报;例如,IO BMC可以根据各个设备资源池的第一IP地址分别向其发送获取请求,设备BMC响应于获取请求将第二映射关系发送给IO BMC;也可以是由设备资源池上电后,按照固定频率(即上述预设频率)定期统计并上报。
可选的,上述步骤S502:确定设备资源池的第二高速信号端口与第二端口标识的第二映射关系,可以通过以下方案来实现,包括:在设备资源池上电的情况下,通过设备资源池的多个第四高速信号端口扫描IO资源池的识别设备;将多个第四高速信号端口中扫描到识别设备的第四高速信号端口确定为第二高速信号端口,以及确定通过第二高速信号端口扫描到的识别设备的第二端口标识;根据第二高速信号端口与第二端口标识确定出第二映射关系。
设备资源池上电后,第二BMC通过设备资源池的多个第四高速信号端口尝试扫描IO资源池的识别设备;若扫描到了,则将其确定为第二高速信号端口,并确定通过该第二高速信号端口扫描到的第二端口标识;然后根据第二高速信号端口和第二端口标识确定出第二映射关系。
采用上述方案,各个设备BMC主动统计自身部分的拓扑连接关系,并发送给IO BMC进行汇总,从而帮助IO BMC快速完成第三映射关系的统计。
基于上述步骤,确定设备资源池的第二高速信号端口与第二端口标识的第二映射关系之后,方法还包括:按照预设频率重新确定第二高速信号端口与第二端口标识在当前时刻的第四映射关系;比对第四映射关系与第二映射关系是否一致;在第四映射关系与第二映射关系不一致的情况下,向第一BMC发送更新请求,以指示第一BMC根据第四映射关系更新第三映射关系,其中,更新请求携带有第四映射关系。
设备BMC会按照预设频率定期进行一次扫描,确定当前时刻下设备资源池与IO资源池的高速信号端口的第四映射关系;然后与发送给IO BMC的第二映射关系进行比对,若确定不一致,即确定拓扑连接关系发生了更新,向IO BMC发送更新请求,指示IO BMC进行更新。
采用上述方案,在确定高速信号端口之间的拓扑连接关系发生改变时,设备资源池会主动上报,协助IO资源池自动完成第三映射关系的更新;从而保证了第三映射关系的及时性和有效性。
可选的,通过设备资源池的多个第四高速信号端口扫描IO资源池的识别设备,包括:通过拓扑识别服务依次扫描多个通信通道,得到多个扫描结果,其中,多个通信通道与多个第四高速信号端口一一对应;在扫描结果为第一扫描结果的情况下,确定第一扫描结果对应的通信通道处于连通状态,其中,第一扫描结果用于指示扫描到识别设备;在扫描结果为第二扫描结果的情况下,确定第二扫描结果对应的通信通道处于断开状态,其中,第二扫描结果用于指示未扫描到识别设备。
设备BMC通过拓扑识别服务依次扫描多个第四高速信号端口对应的多个通信通道,得到多个扫描结果,若扫描结果指示扫描到识别设备,则确定对应的通信通道处于连通状态;若扫描结果指示未扫描到识别设备,则确定对应的通信通道处于断开状态,即对应的第四高速信号端口未与IO资源池的高速信号端口建立连接。
在融合架构内,所有IO资源集中于一个IO Box,设备Box均挂载于IO Box之下。IO Box和设备Box上设置有多个高速信号端口。通过连接器将设备Box上的高速信号端口与IO Box相连,用来实现高速信号的传输。由于IO Box可下挂多个同类型或不同类型的设备Box,同类型的设备Box物理结构又完全相同,故如何准确识别整个系统内高速信号端口的连接拓扑是一大难题。
相关技术中,为了先确定出整个系统内的高速信号端口的连接拓扑,需要在IO Box和设备Box的每个高速信号端口(即CDFP端口)上都设置一个识别设备,用来存储和配置CDFP端口标识;硬件电路设计如图3所示。IO Box上的每个CDFP端口标识(图3中PCA9554的ID(Identity document,身份证标识号))需要包含SW编号和CDFP端口编号信息,如表1所示;而设备Box上的每个CDFP端口标识需要包含Box编号、Box类型和CDFP端口编号信息,如表2所示。其中SW(Switch,交换机)编号用来区分PCIe(Peripheral Component Interconnect Express,高速串行计算机扩展总线标准)Switch设备;Box类型用来区分五种Box;Box编号用来区分多个同类型的设备Box;CDFP端口编号用来区分一个设备Box上不同的CDFP端口。
表1
表2
通过设置识别设备PCA9554中的8个标识位来配置CDFP端口标识,其中Box类型和CDFP端口编号对应的标识位是固定的,需要硬件预先设置好。Box编号对应的标识位需要设备Box BMC来进行动态设置。通过连接器将设备Box上的CDFP端口与IO Box相连。拓扑识别逻辑如图6所示,各Box上电后,IO Box BMC作为Host(主机)开始进行CDFP端口拓扑识别,依次扫描IO Box上所有CDFP端口所在的I2C通道,看能否识别设备Box侧的识别设备PCA9554,识别到后,说明IO Box上此CDFP端口已通过连接器与某个设备Box上的某个CDFP端口相连接。继续读取设备Box侧的识别设备PCA9554中存储的CDFP端口标识,通过Box类型和CDFP端口标识位,可判断出是与哪一种Box上的哪一个端口相连。扫描完所有的I2C通道后,可知IO Box下挂的设备Box类型和每种Box的数量。然后需要设备Box BMC作为Slave(从设备)端接收指令对Box编号标识位做配置。在识别到指定类型的一组待配置设备Box的情况下,为每个待配置设备Box分配唯一的Box编号,将Box编号分别发送给每个待配置设备Box,以为每个待配置设备Box配置CDFP端口标识。配置完成后,这样IO Box BMC再依次扫描所有CDFP端口所在的I2C通道,分别读取每条通道上IO Box侧和设备Box侧识别设备PCA9554中的CDFP端口标识。扫描完后,得到整个系统内所有CDFP端口的连接拓扑。
通过上述方案虽然能够得到整个系统内所有CDFP端口的连接拓扑,但由于需要为IO Box和设备Box上的每个高速信号端口都配置一个识别设备,且同一个通信通道上识别设备的从地址须不一样,导致硬件电路设计复杂且硬件成本过高。
为了解决上述问题,本申请提供了一种融合架构下资源池高速信号端口拓扑识别方法,该方法包括:IO Box上的每个高速信号端口需要配置一个识别设备做端口标识,标识需要包含SW编号和CDFP端口编号信息,且标识唯一。设备Box上高速信号端口不再需要用识别设备做端口标识,因为一个设备Box上每个高速信号端口所在的通信通道不同,通过通信通道即可区分出每个高速信号端口。只需做软件编号定义,并将编号与每个高速信号端口所在的通信通道做映射。IO Box和设备Box上电后,设备Box中的管理模块依次扫描设备Box上每个高速信号端口所在的通信通道,看能否识别到IO Box侧的识别设备。若能识别到,说明设备Box上此CDFP端口已通过连接器与IO Box上的某个端口相连接;若识别不到,则说明未连接。读取识别设备中的端口标识,即可知道是IO Box上的哪个高速信号端口。设备Box中的管理模块扫描完所有高速信号端口所在的通信通道后,得到设备Box上所有高速信号端口软件编号与IO Box上对应高速信号端口标识的映射关系。IO Box管理模块通过网络与各设备Box上的管理模块交互,通过设备Box主动上报或者IO Box主动获取的方式,IO Box管理模块得到每个设备Box上的映射关系,汇总处理后即可得到整个系统的端口连接拓扑。
以下结合实施例对上述方法进行说明。
假设融合架构机柜内有一个IO Box和多个设备Box,各Box中的管理模块为BMC。BMC固件采用Open BMC(开放基板管理控制器)架构。所有BMC接到同一网络交换机下,组成一个局域网,IO Box中的BMC作为主BMC,各设备Box BMC作为从BMC,主BMC可通过网络与各个从BMC进行通信,实现整个系统的管理控制功能。
IO Box BMC需要实现一个节点管理模块,该模块可管理机柜内所有设备Box BMC的IP地址。通过网络与各设备Box的BMC通信。
可选的,IO Box内包含4层Switch板卡,每层板卡有两个PCIe Switch设备,将Host Box中多个CPU的PCIe资源进行拓展、组网、分配,PCIe Switch设备是一种被设置为将一组PCIe信号拓展为多组PCIe信号的IO设备,被设置为对CPU IO资源的拓展。每颗PCIe Switch设备出5个CDFP端口(高速信号端口),整个IO Box最终可对外给出40(8*5)个CDFP端口,对40个CDFP端口进行软件编号分别为:CDFP0-0至CDFP0-4,……,CDFP7-0至CDFP7-4。每个CDFP端口包含一组PCIe 5.0×16的高速IO信号。各设备Box上也配置有相应的CDFP端口,通过连接器将其连接,如图7所示。
图8给出了IO Box上端口拓扑识别的部分硬件电路设计,每个CDFP端口都配置一个识别设备PCA9554,被设置为CDFP端口标识的写入和存储,所有PCA9554设备地址配置为0100000。PCA9554有8路IO输入,针对IO Box的实际需求情况,给出其bit7(比特7)至bit0的定义,对于每个PCA9554,其bit7:6默认为0;bit5:3为SW编号,即8个PCIe Switch设备的编号;bit2:0为CDFP端口编号,即一个PCIe Switch设备上5个CDFP端口的编号。如表3所示:
表3
按照此定义,IO Box上第一层Switch板卡(上有两个PCIe Switch设备)、10个CDFP端口的软件编号与端口标识的映射关系如表4所示:
表4
其他三层Switch板卡CDFP端口的软件编号与端口标识的映射关系与第一层类似。映射关系以json格式配置到IO Box BMC的配置文件中。IO Box上端口的识别设备中的SW编号和CDFP端口编号标识位需要硬件预先指定好。
图8以两个SSD Box和一个GPU Box为例,给出了设备Box端口拓扑识别的部分硬件设计。设备Box上的CDFP端口不需要配置识别设备来做端口标识,由于每个CDFP端口所在的I2C通道不同,通过I2C通道即可区分出是哪一个CDFP端口。以SSD Box为例,按照CDFP端口的物理位置,将6个CDFP端口进行软件编号分别为:CDFP0至CDFP5。6个CDFP端口分别连接在I2C扩展设备PCA9548的6个channel(通道)下,在设备树dts(Device Tree Source)配置文件中将6个CDFP端口所在的I2C(Inter-Integrated Circuit,两线式串行总线)通道通过aliases(别名)定义虚拟bus(总线)号,分别为50至55,对应关系如表5所示:
表5
拓扑识别的主要逻辑包括以下步骤:
(1)IO Box和设备Box上电后,IO Box BMC中的节点管理服务,通过IPMI或Redfish请求依次向所有设备Box发送其IP地址信息,为后面网络交互做准备;
(2)各设备Box在上电后,拓扑识别服务开始运行。以SSD Box为例,BMC中的拓扑识别服务依次扫描虚拟I2C bus号50至55,看能否扫描到IO Box上地址为0100000的设备PCA9554,若能扫描到,则说明SSD Box上此CDFP端口连接到了IO Box上的某一个CDFP端口上,然后读取PCA9554中的端口标识;否则,未连接。扫描完所有的虚拟I2C bus号后,即可得到该SSD Box上6个CDFP端口软件编号与IO Box侧CDFP端口标识的映射关系B,将其存储到Dbus上。并提供查询该映射关系的IPMI或Redfish接口,Redfish接口是由分布式管理任务组(DMTF)推出的一种用于管理数据中心硬件的开放标准RESTful API(应用程序编程接口);
(3)IO Box BMC中的拓扑识别服务,加载json文件配置的Switch板卡CDFP端口软件编号与端口标识的映射关系A,然后依次向所有设备Box BMC发送IPMI或Redfish请求,获取设备Box的资产信息和映射关系B。将所有的映射关系B和配置的映射关系A做处理后,即可得到整个系统IO Box上CDFP端口和各设备Box上CDFP端口的连接拓扑,从而使数据指令能够准确发送到特定设备Box的特定CDFP端口;
(4)设备Box BMC中的拓扑识别服务识别到映射关系B发生变化时,主动通过IPMI或Redfish请求上报到IO Box BMC,更新连接拓扑。
在上述实施例中,IO Box BMC未通过I2C通道与CDFP端口的识别设备PCA9554相连,故端口的识别设备中的SW编号和CDFP端口编号标识位需要硬件预先指定好。在本实施例中可以解决这个问题,拓扑识别电路设计如图9所示,IO Box BMC通过PCA9548与每个CDFP端口的识别设备PCA9554相连。
将IO Box上CDFP端口的软件编号、端口标识、识别设备所在I2C通道的虚拟Bus号的映射关系以json格式配置到文件中,在IO Box上电后,BMC中的拓扑识别服务加载该配置文件,依次扫描所有CDFP端口所在的I2C通道,识别端口的识别设备PCA9554,写入配置文件中配置的端口标识,然后通知设备Box BMC中的拓扑识别服务开始扫描,拓扑识别的其他处理逻辑与上述实施例类似。
通过上述实施例可以看出,本申请所提出的上述方法,能够解决相关技术中存在的诸多不足,具有以下优点:
(1)只需在IO Box上的每个高速信号端口配置识别设备做端口标识,设备Box上不用再配置识别设备做端口标识,减少了硬件资源的使用;
(2)不需要再定义复杂的设备Box高速信号端口标识,设备Box中的管理模块不需要再动态设置Box编号标识位;
(3)在本申请中无需对设备Box的类型进行区分,IO Box可以清晰地确定每一个设备Box之间的不同,IO Box管理模块处理逻辑也更清晰,获取到所有设备Box上的映射关系,做汇总处理后即可得到整个系统的端口连接拓扑。不用再识别同类型设备Box的数量,分配Box编号;
(4)由于采用本方案的实现逻辑简单,设备Box与IO Box之间的连接不再受限于扫描逻辑的复杂性,设备Box上的高速信号端口能与IO Box上任意一个端口连接,连接关系能做到完全自动识别。
通过以上的实施方式的描述,本领域的技术人员可以清楚地了解到根据上述实施例的方法可借助软件加必需的通用硬件平台的方式来实现,当然也可以通过硬件,但很多情况下前者是更佳的实施方式。基于这样的理解,本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个非易失性可读存储介质(如ROM/RAM、磁碟、光盘)中,包括若干指令用以使得一台终端设备(可以是手机,计算机,服务器,或者网络设备等)执行本申请各个实施例的方法。
在本实施例中还提供了一种端口的识别系统,该系统被设置为实现上述实施例及可选实施方式,已经进行过说明的不再赘述。如以下所使用的,术语“模块”可以实现预定功能的软件和/或硬件的组合。尽管以下实施例所描述的装置较佳地以软件来实现,但是硬件,或者软件和硬件的组合的实现也是可能并被构想的。
图10是根据本申请实施例的端口的识别系统的结构框图,如图10所示,该系统包括:
第一BMC1002,被设置为配置多个第一端口标识与IO资源池的多个第一高速信号端口的第一映射关系,其中,第一端口标识用于标识IO资源池的识别设备,多个识别设备与多个第一高速信号端口一一对应;
第二BMC1004,被设置为确定设备资源池的第二高速信号端口与第二端口标识的第二映射关系,并将第二映射关系发送至第一BMC,其中,第二端口标识用于标识IO资源池的识别设备,多个第一端口标识包括第二端口标识;
第一BMC1002,还被设置为根据第一映射关系和第二映射关系确定第三映射关系,其中,第三映射关系用于指示处于连通状态的通信通道对应的第三高速信号端口与第二高速信号端口之间的一一对应关系,处于连通状态的通信通道用于IO资源池与设备资源池进行通信,多个第一高速信号端口包括第三高速信号端口。
通过上述系统,第一BMC先配置IO资源池的多个第一高速信号端口与多个识别设备的多个第一端口标识的第一映射关系,然后接收设备资源池的第二BMC确定设备资源池的第二高速信号端口与第二端口标识的第二映射关系,并将其发送至第一BMC,第二端口标识用于标识IO资源池的识别设备,多个第一端口标识包括该第二端口标识;发送的第二映射关系,第二映射关系用于指示设备资源池的第二高速信号端口与第二端口标识之间的对应关系;最后第一BMC根据第一映射关系和第二映射关系确定出第三映射关系,第三映射关系用于指示处于连通状态的通信通道对应的第三高速信号端口与第二高速,处于连通状态的通信通道用于IO资源池与设备资源池进行通信;采用上述方案,仅需为IO Box(IO资源池)上的高速信号端口配置识别设备,先通过设备Box(设备资源池)确定建立有通信通道的高速信号端口与识别设备的端口标识的对应关系(即第二映射关系),再根据保存的IO Box的高速信号端口与识别设备的端口标识的对应关系(第一映射关系),从而根据第一映射关系与第二映射关系快速确定出IO Box与设备Box之间高速信号端口的连接拓扑关系(即上述第三映射关系),既节省了硬件成本,又简化了处理逻辑;进而解决了相关技术中,确定IO Box与设备Box之间高速信号端口的连接拓扑关系(即第三映射关系)的方案,需要为IO Box和设备Box上的每个高速信号端口均配置一个识别设备,成本过高且实现逻辑复杂的问题。
可选的,上述接收模块1004第一BMC1002,还被设置为获取融合架构机柜中多个设备资源池的第一IP地址,其中,融合架构机柜中包括:多个设备资源池,IO资源池,第一IP地址用于IO资源池的第一BMC与第二BMC进行网络通信;在确定多个设备资源池上电的情况下,根据第一IP地址将IO资源池的第二IP地址发送给多个设备资源池,其中,第二IP地址用于第二BMC与第一BMC进行网络通信。
可选的,上述第一BMC1002接收模块1004,还被设置为执行以下步骤之一:根据多个设备资源池的第一IP地址分别向多个第二BMC发送获取请求,以通过获取请求获取多个第二映射关系,其中,第一IP地址用于IO资源池的第一BMC与第二BMC进行网络通信;接收多个第二BMC按照预设频率发送的多个第二映射关系。
可选的,上述第一BMC1002,还被设置为确定多个第二映射关系所指示的多个第二端口标识和多个第二高速信号端口;在多个第一端口标识中匹配多个第二端口标识,以及匹配多个第二端口标识对应的多个第三高速信号端口;根据多个第二高速信号端口和多个第三高速信号端口建立第三映射关系。
可选的,上述第一BMC1002,还被设置为在接收到第二BMC发送的更新请求的情况下,从更新请求中解析出第四映射关系,其中,第四映射关系用于指示第二高速信号端口和第二端口标识之间的对应关系;响应更新请求,根据第四映射关系对第三映射关系进行更新。
可选的,上述第一BMC1002,还被设置为将控制指令发送给IO资源池,以指示IO资源池根据第三映射关系确定控制指令对应的目标通信通道,并通过目标通信通道将控制指令发送给控制指令对应的目标设备资源池,其中,控制指令用于控制目标设备资源池。
可选的,上述第二BMC1004,还被设置为在接收到第一BMC发送的第二IP地址的情况下,根据第二IP地址校验IO资源池与设备资源池是否属于同一融合架构机柜,其中,融合架构机柜包括一个IO资源池和多个设备资源池,第二IP地址用于第二BMC与第一BMC进行网络通信;在确定IO资源池与设备资源池属于同一融合架构机柜的情况下,根据第二IP地址将第二映射关系发送至第一BMC。
可选的,上述第二BMC1004,还被设置为执行以下步骤之一:在接收到第一BMC发送的获取请求的情况下,根据获取请求将第二映射关系发送至第一BMC;按照预设频率根据IO资源池的第二IP地址将第二映射关系发送至第一BMC,其中,第二IP地址用于第二BMC与第一BMC进行网络通信。
可选的,上述第二BMC1004,还被设置为在设备资源池上电的情况下,通过设备资源池的多个第四高速信号端口扫描IO资源池的识别设备;将多个第四高速信号端口中扫描到识别设备的第四高速信号端口确定为第二高速信号端口,以及确定通过第二高速信号端口扫描到的识别设备的第二端口标识;根据第二高速信号端口与第二端口标识确定出第二映射关系。
可选的,上述第二BMC1004,还被设置为按照预设频率重新确定第二高速信号端口与第二端口标识在当前时刻的第四映射关系;比对第四映射关系与第二映射关系是否一致;在第四映射关系与第二映射关系不一致的情况下,向第一BMC发送更新请求,以指示第一BMC根据第四映射关系更新第三映射关系,其中,更新请求携带有第四映射关系。
可选的,上述第二BMC1004,还被设置为通过拓扑识别服务依次扫描多个通信通道,得到多个扫描结果,其中,多个通信通道与多个第四高速信号端口一一对应;在扫描结果为第一扫描结果的情况下,确定第一扫描结果对应的通信通道处于连通状态,其中,第一扫描结果用于指示扫描到识别设备;在扫描结果为第二扫描结果的情况下,确定第二扫描结果对应的通信通道处于断开状态,其中,第二扫描结果用于指示未扫描到识别设备。
需要说明的是,上述各个模块是可以通过软件或硬件来实现的,对于后者,可以通过以下方式实现,但不限于此:上述模块均位于同一处理器中;或者,上述各个模块以任意组合的形式分别位于不同的处理器中。
本申请的实施例还提供了一种计算机非易失性可读存储介质,该计算机非易失性可读存储介质中存储有计算机程序,其中,该计算机程序被设置为运行时执行上述任一项方法实施例中的步骤。
在一个示例性实施例中,上述计算机非易失性可读存储介质可以包括但不限于:U盘、只读存储器(Read-Only Memory,简称为ROM)、随机存取存储器(Random Access Memory,简称为RAM)、移动硬盘、磁碟或者光盘等各种可以存储计算机程序的非易失性可读存储介质。
本申请的实施例还提供了一种电子装置,包括存储器和处理器,该存储器中存储有计算机程序,该处理器被设置为运行计算机程序以执行上述任一项方法实施例中的步骤。
在一个示例性实施例中,上述电子装置还可以包括传输设备以及输入输出设备,其中,该传输设备和上述处理器连接,该输入输出设备和上述处理器连接。
本申请的实施例还提供了一种计算机程序产品,包括计算机非易失性可读存储介质,计算机非易失性可读存储介质存储计算机程序产品,计算机程序被处理器执行时实现本申请各个实施例中方法的步骤。
本实施例中的可选示例可以参考上述实施例及示例性实施方式中所描述的示例,本实施例在此不再赘述。
显然,本领域的技术人员应该明白,上述的本申请的各模块或各步骤可以用通用的计算装置来实现,它们可以集中在单个的计算装置上,或者分布在多个计算装置所组成的网络上,它们可以用计算装置可执行的程序代码来实现,从而,可以将它们存储在存储装置中由计算装置来执行,并且在某些情况下,可以以不同于此处的顺序执行所示出或描述的步骤,或者将它们分别制作成各个集成电路模块,或者将它们中的多个模块或步骤制作成单个集成电路模块来实现。这样,本申请不限制于任何特定的硬件和软件结合。
以上仅为本申请的可选实施例而已,并不用于限制本申请,对于本领域的技术人员来说,本申请可以有各种更改和变化。凡在本申请的原则之内,所作的任何修改、等同替换、改进等,均应包含在本申请的保护范围之内。
Claims (20)
- 一种端口的识别方法,应用于用于管理IO资源池的第一BMC,其特征在于,包括:配置多个第一端口标识与所述IO资源池的多个第一高速信号端口的第一映射关系,其中,所述第一端口标识用于标识所述IO资源池的识别设备,多个所述识别设备与所述多个第一高速信号端口一一对应;接收设备资源池的第二BMC发送的第二映射关系,其中,所述第二BMC被设置为管理所述设备资源池,所述第二映射关系用于指示第二高速信号端口和第二端口标识之间的对应关系,所述第二高速信号端口为所述设备资源池的高速信号端口,所述多个第一端口标识包括所述第二端口标识;根据所述第一映射关系和所述第二映射关系确定第三映射关系,其中,所述第三映射关系用于指示处于连通状态的通信通道对应的第三高速信号端口与第二高速信号端口之间的一一对应关系,所述处于连通状态的通信通道用于所述IO资源池与所述设备资源池进行通信,所述多个第一高速信号端口包括所述第三高速信号端口。
- 根据权利要求1所述的方法,其特征在于,接收设备资源池的第二BMC发送的第二映射关系之前,所述方法还包括:获取多个所述设备资源池的第一IP地址,其中,多个所述设备资源池与所述IO资源池属于同一系统,所述第一IP地址用于所述IO资源池的第一BMC与所述第二BMC进行网络通信;在确定多个所述设备资源池上电的情况下,根据所述第一IP地址将所述IO资源池的第二IP地址发送给多个所述设备资源池,其中,所述第二IP地址用于所述第二BMC与所述第一BMC进行网络通信。
- 根据权利要求1所述的方法,其特征在于,接收设备资源池的第二BMC发送的第二映射关系,包括以下之一:根据多个所述设备资源池的第一IP地址分别向多个所述第二BMC发送获取请求,以通过所述获取请求获取多个所述第二映射关系,其中,所述第一IP地址用于所述IO资源池的第一BMC与所述第二BMC进行网络通信;接收多个所述第二BMC按照预设频率发送的多个所述第二映射关系。
- 根据权利要求3所述的方法,其特征在于,根据所述第一映射关系和所述第二映射关系确定第三映射关系,包括:确定多个所述第二映射关系所指示的多个所述第二端口标识和多个所述第二高速信号端口;在所述多个第一端口标识中匹配多个所述第二端口标识,以及匹配多个所述第二端口标识对应的多个所述第三高速信号端口;根据多个所述第二高速信号端口和多个所述第三高速信号端口建立所述第三映射关系。
- 根据权利要求1所述的方法,其特征在于,根据所述第一映射关系和所述第二映射关系确定第三映射关系之后,所述方法还包括:在接收到所述第二BMC发送的更新请求的情况下,从所述更新请求中解析出第四映射关系,其中,所述第四映射关系用于指示所述第二高速信号端口和所述第二端口标识之间的对应关系;响应所述更新请求,根据所述第四映射关系对所述第三映射关系进行更新。
- 根据权利要求1所述的方法,其特征在于,根据所述第一映射关系和所述第二映射关系确定第三映射关系之后,所述方法还包括:将控制指令发送给所述IO资源池,以指示所述IO资源池根据所述第三映射关系确定所述控制指令对应的目标通信通道,并通过所述目标通信通道将所述控制指令发送给所述控制指令对应的目标设备资源池,其中,所述控制指令用于控制所述目标设备资源池。
- 根据权利要求2所述的方法,其特征在于,所述根据所述第一IP地址将所述IO资源池的第二IP地址发送给多个所述设备资源池,包括:根据所述第一IP地址通过智能平台管理接口请求依次向多个所述设备资源池发送所述第二IP地址;或者根据所述第一IP地址通过可扩展平台管理的应用程序接口请求依次向多个所述设备资源池发送所述第二IP地址。
- 根据权利要求5所述的方法,其特征在于,所述第二BMC被设置为在确定高速信号端口之间的拓扑连接关系发生改变时,向所述第一BMC上报所述更新请求。
- 根据权利要求1所述的方法,其特征在于,所述第一BMC中存储了目标文件,所述目标文件用于配置所述多个第一端口标识与多个所述第一高速信号端口之间的映射关系,所述配置多个第一端口标识与所述IO资源池的多个第一高速信号端口的第一映射关系,包括:将所述第一映射关系按照jason格式配置至所述目标文件中;所述第一BMC中包括拓扑识别服务,在所述配置多个第一端口标识与所述IO资源池的多个第一高速信号端口的第一映射关系之后,所述方法还包括:在所述IO资源池上电后,通过所述拓扑识别服务加载所述目标文件中配置的所述第一映射关系。
- 一种端口的识别方法,应用于用于管理设备资源池的第二BMC,其特征在于,包括:确定所述设备资源池的第二高速信号端口与第二端口标识的第二映射关系,其中,所述第二端口标识用于标识IO资源池的识别设备;将所述第二映射关系发送至所述IO资源池的第一BMC,以指示所述第一BMC根据预先配置的第一映射关系和所述第二映射关系确定第三映射关系,其中,所述第一BMC被设置为管理所述IO资源池,所述第一映射关系用于指示多个所述识别设备的多个第一端口标识与所述IO资源池的多个第一高速信号端口的一一对应关系,所述多个第一端口标识包括所述第二端口标识,所述第三映射关系用于指示处于连通状态的通信通道对应的第三高速信号端口与第二高速信号端口之间的一一对应关系,所述处于连通状态的通信通道用于所述IO资源池与所述设备资源池进行通信,所述多个第一高速信号端口包括所述第三高速信号端口。
- 根据权利要求10所述的方法,其特征在于,将所述第二映射关系发送至所述IO资源池的第一BMC之前,所述方法还包括:在接收到所述第一BMC发送的第二IP地址的情况下,根据所述第二IP地址校验所述IO资源池与所述设备资源池是否属于同一系统,其中,所述第二IP地址用于所述第二BMC与所述第一BMC进行网络通信;在确定所述IO资源池与所述设备资源池属于同一系统的情况下,根据所述第二IP地址将所述第二映射关系发送至所述第一BMC。
- 根据权利要求10所述的方法,其特征在于,将所述第二映射关系发送至所述IO资源池的第一BMC,包括以下之一:在接收到所述第一BMC发送的获取请求的情况下,根据所述获取请求将所述第二映射关系发送至所述第一BMC;按照预设频率根据所述IO资源池的第二IP地址将所述第二映射关系发送至所述第一BMC,其中,所述第二IP地址用于所述第二BMC与所述第一BMC进行网络通信。
- 根据权利要求10所述的方法,其特征在于,确定所述设备资源池的第二高速信号端口与第二端口标识的第二映射关系,包括:在所述设备资源池上电的情况下,通过所述设备资源池的多个第四高速信号端口扫描所述IO资源池的识别设备;将所述多个第四高速信号端口中扫描到所述识别设备的第四高速信号端口确定为所述第二高速信号端口,以及确定通过所述第二高速信号端口扫描到的所述识别设备的所述第二端口标识;根据所述第二高速信号端口与所述第二端口标识确定出所述第二映射关系。
- 根据权利要求10所述的方法,其特征在于,确定所述设备资源池的第二高速信号端口与第二端口标识的第二映射关系之后,所述方法还包括:按照预设频率重新确定所述第二高速信号端口与所述第二端口标识在当前时刻的第四映射关系;比对所述第四映射关系与所述第二映射关系是否一致;在所述第四映射关系与所述第二映射关系不一致的情况下,向所述第一BMC发送更新请求,以指示所述第一BMC根据所述第四映射关系更新所述第三映射关系,其中,所述更新请求携带有所述第四映射关系。
- 根据权利要求13所述的方法,其特征在于,通过所述设备资源池的多个第四高速信号端口扫描所述IO资源池的识别设备,包括:通过拓扑识别服务依次扫描多个通信通道,得到多个扫描结果,其中,所述多个通信通道与所述多个第四高速信号端口一一对应;在扫描结果为第一扫描结果的情况下,确定所述第一扫描结果对应的通信通道处于连通状态,其中,所述第一扫描结果用于指示扫描到所述识别设备;在扫描结果为第二扫描结果的情况下,确定所述第二扫描结果对应的通信通道处于断开状态,其中,所述第二扫描结果用于指示未扫描到所述识别设备。
- 根据权利要求11所述的方法,其特征在于,所述根据所述第二IP地址校验所述IO资源池与所述设备资源池是否属于同一系统,包括:根据所述第二IP地址校验所述IO资源池与所述设备资源池是否属于同一个融合架构机柜,其中,所述融合架构机柜包括相互独立的一个IO资源池和多个设备资源池;在根据所述第二IP地址校验出所述IO资源池与所述设备资源池属于同一个融合架构机柜的情况下,确定所述IO资源池与所述设备资源池属于同一系统。
- 一种端口的识别系统,其特征在于,包括:第一BMC,被设置为配置多个第一端口标识与IO资源池的多个第一高速信号端口的第一映射关系,其中,所述第一端口标识用于标识所述IO资源池的识别设备,多个所述识别设备与所述多个第一高速信号端口一一对应;第二BMC,被设置为确定设备资源池的第二高速信号端口与第二端口标识的第二映射关系,并将所述第二映射关系发送至所述第一BMC,其中,所述第二端口标识用于标识IO资源池的识别设备,所述多个第一端口标识包括所述第二端口标识;所述第一BMC,还被设置为根据所述第一映射关系和所述第二映射关系确定第三映射关系,其中,所述第三映射关系用于指示处于连通状态的通信通道对应的第三高速信号端口与第二高速信号端口之间的一一对应关系,所述处于连通状态的通信通道用于所述IO资源池与所述设备资源池进行通信,所述多个第一高速信号端口包括所述第三高速信号端口。
- 一种计算机非易失性可读存储介质,其特征在于,所述计算机非易失性可读存储介质中存储有计算机程序,其中,所述计算机程序被处理器执行时实现所述权利要求1至9或10至16任一项中所述的方法的步骤。
- 一种电子装置,包括存储器、处理器以及存储在所述存储器上并可在所述处理器上运行的计算机程序,其特征在于,所述处理器执行所述计算机程序时实现所述权利要求1至9或10至16任一项中所述的方法的步骤。
- 一种计算机程序产品,包括计算机程序,其特征在于,所述计算机程序被处理器执行时实现权利要求1至9或10至16中任一项所述方法的步骤。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410379845.XA CN117978811B (zh) | 2024-03-29 | 2024-03-29 | 映射关系的确定方法及系统、存储介质及电子装置 |
| CN202410379845.X | 2024-03-29 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2025200512A1 true WO2025200512A1 (zh) | 2025-10-02 |
Family
ID=90853568
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2024/134531 Pending WO2025200512A1 (zh) | 2024-03-29 | 2024-11-26 | 端口的识别方法及系统、非易失性可读存储介质及电子装置 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN117978811B (zh) |
| WO (1) | WO2025200512A1 (zh) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117978811B (zh) * | 2024-03-29 | 2024-05-31 | 苏州元脑智能科技有限公司 | 映射关系的确定方法及系统、存储介质及电子装置 |
| CN118394533B (zh) * | 2024-06-27 | 2024-10-01 | 苏州元脑智能科技有限公司 | 资源调度方法、计算机设备、存储介质及程序产品 |
| CN118467434B (zh) * | 2024-07-10 | 2024-11-08 | 苏州元脑智能科技有限公司 | 服务系统、输入输出机箱、设备机箱以及机箱识别方法 |
| CN119906687B (zh) * | 2025-03-31 | 2025-06-20 | 浪潮电子信息产业股份有限公司 | 一种服务器及其设备监控系统、方法 |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170286352A1 (en) * | 2016-04-01 | 2017-10-05 | Mohan J. Kumar | Mechanism for pcie cable topology discovery in a rack scale architecture environment |
| CN115687220A (zh) * | 2023-01-03 | 2023-02-03 | 苏州浪潮智能科技有限公司 | 多服务器标识的识别电路、识别方法、电子设备、存储介质 |
| CN116069701A (zh) * | 2023-02-15 | 2023-05-05 | 宁畅信息产业(北京)有限公司 | 一种pcie资源识别方法、装置、设备及存储介质 |
| CN117978811A (zh) * | 2024-03-29 | 2024-05-03 | 苏州元脑智能科技有限公司 | 映射关系的确定方法及系统、存储介质及电子装置 |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102567239A (zh) * | 2010-12-29 | 2012-07-11 | 鸿富锦精密工业(深圳)有限公司 | 计算机装置及其多网卡识别方法 |
| CN110399280A (zh) * | 2019-06-18 | 2019-11-01 | 苏州浪潮智能科技有限公司 | 一种pcie设备的管理方法、管理系统及相关装置 |
| CN111107049B (zh) * | 2019-10-18 | 2022-07-05 | 苏州浪潮智能科技有限公司 | 一种存储设备建立连接的方法、设备及介质 |
| CN113312143B (zh) * | 2021-03-03 | 2024-01-23 | 阿里巴巴新加坡控股有限公司 | 云计算系统、命令处理方法及虚拟化仿真装置 |
| US20210397530A1 (en) * | 2021-06-25 | 2021-12-23 | Intel Corporation | Methods and apparatus to transmit central processing unit performance information to an operating system |
| CN116541320B (zh) * | 2023-05-22 | 2024-01-23 | 深圳市海思科自动化技术有限公司 | 一种智能io模块总线通讯方法、io模块、终端及介质 |
-
2024
- 2024-03-29 CN CN202410379845.XA patent/CN117978811B/zh active Active
- 2024-11-26 WO PCT/CN2024/134531 patent/WO2025200512A1/zh active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170286352A1 (en) * | 2016-04-01 | 2017-10-05 | Mohan J. Kumar | Mechanism for pcie cable topology discovery in a rack scale architecture environment |
| CN115687220A (zh) * | 2023-01-03 | 2023-02-03 | 苏州浪潮智能科技有限公司 | 多服务器标识的识别电路、识别方法、电子设备、存储介质 |
| CN116069701A (zh) * | 2023-02-15 | 2023-05-05 | 宁畅信息产业(北京)有限公司 | 一种pcie资源识别方法、装置、设备及存储介质 |
| CN117978811A (zh) * | 2024-03-29 | 2024-05-03 | 苏州元脑智能科技有限公司 | 映射关系的确定方法及系统、存储介质及电子装置 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117978811A (zh) | 2024-05-03 |
| CN117978811B (zh) | 2024-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2025200512A1 (zh) | 端口的识别方法及系统、非易失性可读存储介质及电子装置 | |
| US11487690B2 (en) | Universal host and non-volatile memory express storage domain discovery for non-volatile memory express over fabrics | |
| US11960430B2 (en) | Remote mapping method, apparatus and device for computing resources, and storage medium | |
| US11394607B2 (en) | Method and system for network configuration | |
| US11575592B2 (en) | Message processing method and apparatus, control-plane device, and computer storage medium | |
| CN104753697B (zh) | 一种控制网络设备自动开局的方法、设备及系统 | |
| CN109951325A (zh) | 一种网络线缆连接检查方法和装置 | |
| WO2019237588A1 (zh) | Linux虚拟服务器的创建方法、装置、计算机设备及存储介质 | |
| US10712947B2 (en) | Data processing method and related storage device | |
| CN103516547B (zh) | 一种网络参数分配方法及装置 | |
| EP3163459B1 (en) | Automatic configuration method and device for storage array, and storage system | |
| US11757794B2 (en) | Port configuration method and communications device | |
| US9432474B2 (en) | Control method, control device, and processor in software defined network | |
| EP4418704A1 (en) | Sidecar deployment method and apparatus in service mesh, electronic device and storage medium | |
| CN116996908A (zh) | 主从网关和无线ap的融合管理方法、装置、设备和介质 | |
| WO2016101856A1 (zh) | 数据访问方法及装置 | |
| CN112416495A (zh) | 一种超融合云终端资源统一管理系统及方法 | |
| CN105634635A (zh) | 一种共享rtc的方法、装置和系统 | |
| CN111726367B (zh) | 一种用户设备cpe接入绑定方法、装置、系统及设备 | |
| CN115454896B (zh) | 基于smbus的ssd mctp控制消息验证方法、装置、计算机设备及存储介质 | |
| CN110505075B (zh) | 设备管理方法及相关设备 | |
| CN116633989A (zh) | 服务器的控制方法和装置、存储介质及电子装置 | |
| CN118626424A (zh) | 逻辑端口的管理方法、装置、设备及介质 | |
| CN116055312A (zh) | 虚拟化平台的融合方法、装置、设备及存储介质 | |
| CN114830604B (zh) | 信息处理方法、装置及设备 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 24932666 Country of ref document: EP Kind code of ref document: A1 |