External cable, external cable in-place detection device, power-on self-test method and system

CN116627729BActive Publication Date: 2026-10-30INSPUR SUZHOU INTELLIGENT TECH CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202310504486.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-05-06
Publication Date
2026-10-30
Estimated Expiration
2043-05-06

AI Technical Summary

Technical Problem

[0005]针对现有技术存在的在位校验不准确的问题,本发明提供了外接线缆、外接线缆在位检测装置、开机自检方法及系统,以解决上述技术问题

Benefits of technology

[0043]本发明的有益效果在于,本发明提供的外接线缆、外接线缆在位检测装置、开机自检方法及系统,通过针对外接电缆设置在位检测回路,且在位检测回路在第一设备端第一端口的第一管脚连接第一设备的内部控制器件,内部控制器件基于回路通断状态判断外接线缆是否在位,该种方式可以保证检测准确度,且异构传感器内部可以快速定位异常外接线缆,保证开机后所有外接线缆均可用。

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116627729B_ABST
    Figure CN116627729B_ABST
Patent Text Reader

Abstract

The application belongs to the technical field of heterogeneous servers, and specifically provides an external cable, an external cable in-place detection device, a power-on self-test method and system. The device comprises: a first device comprising a plurality of first ports, a first port being connected with a first connector of an external cable, the first port comprising a first pin, the first pin being connected with a first in-place pin of the first connector; the first pin being electrically connected with a detection power supply; the first pin being connected with an internal control device of the first device; a second device comprising a plurality of second ports, a second port being connected with a second connector of an external cable, the second port comprising a second pin, the second pin being connected with a second in-place pin of the second connector, the second in-place pin being electrically connected with the first in-place pin; and the second pin being grounded. The application can ensure detection accuracy, and the heterogeneous sensor can quickly locate an abnormal external cable, so as to ensure that all external cables can be used after power-on.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention belongs to the field of heterogeneous server technology, specifically relating to an external cable, an external cable presence detection device, a power-on self-test method and system. Background Technology

[0002] The significant advantage of heterogeneous computing lies in its ability to optimize performance and cost by adjusting power consumption by allowing the most suitable dedicated hardware to do the most suitable task. As the hardware carrier of heterogeneous computing, heterogeneous servers achieve optimal cost-effectiveness and efficiency in typical scenarios such as deep learning, image recognition, and speech recognition by using different ratios of CPUs and GPUs.

[0003] The advantages of a heterogeneous server design with a front-end (CPU server) and a rear-end (GPU server) are smaller footprint, flexible configuration, and relatively efficient assembly and transportation. The disadvantages are that the front-end and rear-end are interconnected by cables located outside the chassis, using a high-speed PCIe bus with numerous interfaces. A poor connection in any cable can cause malfunctions in the heterogeneous server. Currently, the method for detecting external cables is to design a link status indicator light near the rear-end cable. If the cable is not properly connected, the corresponding interface is not linked, and the indicator light will not illuminate.

[0004] The drawback of the existing in-situ detection method is that the link status indicator light is only effective after the system is powered on and the PCIe device enumeration is completed in the BIOS phase. If the light is not lit at this time, replugging the cable is equivalent to hot-plugging, and the indicator light will light up. However, because the system has completed the enumeration and the BDF has been assigned, the downstream device corresponding to the cable that is plugged in afterward cannot actually be used, and an error will still occur. It requires restarting the machine head and cannot constrain the on-site operators. Summary of the Invention

[0005] To address the problem of inaccurate in-situ verification in existing technologies, this invention provides an external cable, an external cable in-situ detection device, a power-on self-test method, and a system to solve the aforementioned technical problems.

[0006] In a first aspect, the present invention provides an external cable, comprising: a cable and a first connector and a second connector disposed at both ends of the cable, the first connector including a first in-place pin, the second connector including a second in-place pin, the first in-place pin and the second in-place pin being electrically connected; the length of the first in-place pin being the minimum length among all the pin lengths of the first connector, and the length of the second in-place pin being the minimum length among all the pin lengths of the second connector.

[0007] Secondly, the present invention provides an external cable presence detection device, wherein the heterogeneous server includes a first device and a second device, and the device includes:

[0008] The first device includes multiple first ports, each first port being connected to a first connector of an external cable. Each first port includes a first pin, which is connected to a first in-situ pin of the first connector. The first pin is electrically connected to a detection power supply. The first pin is connected to an internal control device of the first device.

[0009] The second device includes multiple second ports, each of which is connected to a second connector of an external cable. Each second port includes a second pin, which is connected to a second in-place pin of the second connector. The second in-place pin is electrically connected to a first in-place pin. The second pin is grounded.

[0010] Furthermore, the internal control device includes a first BMC and a first input / output expansion board of the first device, a first pin of the first port is connected to a corresponding pin of the first input / output expansion board, and the first input / output expansion board is connected to the first BMC of the first device.

[0011] Furthermore, the internal control device is connected to the input port of the second input / output expansion board, and the output end of the second input / output expansion board is connected to a digital display, which includes, but is not limited to, a seven-segment display.

[0012] Furthermore, with the first device and the second device respectively inserted at both ends of the external cable, the first BMC is connected to the second BMC of the second device through a specific external cable.

[0013] Thirdly, the present invention provides a power-on self-test method, comprising:

[0014] After the first BMC is powered on, it prioritizes capturing the register data of the first input / output expansion board. The register data includes the level state of each pin of the first input / output expansion board.

[0015] Based on the correspondence between each pin of the first input / output expansion board and the first port, the level state of each pin of the first input / output expansion board is converted into the connection state of each external cable.

[0016] The digital display shows the number of the external cable that is in an abnormal connection state through coding.

[0017] Furthermore, based on the correspondence between each pin of the first input / output expansion board and the first port, the voltage level of each pin of the first input / output expansion board is converted into the connection status of each external cable, including:

[0018] Based on the connection relationship between each pin of the first input / output expansion board and the first port, a one-to-one mapping relationship between the first port number and the pin number of the first input / output expansion board is established in advance, and the first port number is bound to the associated second port number;

[0019] A pre-defined rule for converting a level state to a connected state is provided, wherein a high level state corresponds to an abnormal state and a low level state corresponds to a normal state.

[0020] Based on the one-to-one mapping relationship and the rules, the level state of each pin of the first input / output expansion board is converted into the connection state of the external cable between the corresponding first port and the second port.

[0021] Furthermore, the digital display is controlled by encoding to show the number of the external cable in an abnormal connection state, including:

[0022] A unique identification number is pre-generated for the external cable between the first port and the second port;

[0023] The identification number of the external cable whose connection status is abnormal is written into the register of the second input / output expansion board, so that the second input / output expansion board controls the digital tube to display the identification number based on the digital tube control rules.

[0024] Furthermore, after converting the voltage levels of each pin of the first input / output expansion board to the connection states of each external cable based on the correspondence between each pin and the first port, the method further includes:

[0025] Determine if there are any external cables in an abnormal connection state:

[0026] If so, then pause the startup process;

[0027] If not, the power-on procedure is executed, and a power-on prompt message is sent to the second BMC of the second device. The power-on prompt message is used to notify the second BMC to execute the power-on procedure.

[0028] Fourthly, the present invention also provides a power-on self-test system, comprising:

[0029] The data capture module is used to capture the register data of the first input / output expansion board first after the first BMC is powered on. The register data includes the level state of each pin of the first input / output expansion board.

[0030] The data conversion module is used to convert the voltage level of each pin of the first input / output expansion board into the connection state of each external cable based on the correspondence between each pin of the first input / output expansion board and the first port.

[0031] The data display module is used to control the digital display to show the number of the external cable that is in an abnormal connection state through encoding.

[0032] Furthermore, the data transformation module includes:

[0033] The mapping establishment unit is used to establish a one-to-one mapping relationship between the first port number and the pin number of the first input / output expansion board based on the connection relationship between each pin of the first input / output expansion board and the first port in advance, and the first port number is bound to the associated second port number;

[0034] The rule setting unit is used to pre-set rules for converting the level state to the connection state. The rules include a high level state corresponding to an abnormal state and a low level state corresponding to a normal state.

[0035] The data conversion unit is used to convert the level state of each pin of the first input / output expansion board into the connection state of the external cable between the corresponding first port and the second port based on the one-to-one mapping relationship and the rules.

[0036] Furthermore, the data display module includes:

[0037] The numbering generation unit is used to pre-generate a unique identification number for the external cable between the first port and the second port;

[0038] The number display unit is used to write the identification number of the external cable whose connection status is abnormal into the register of the second input / output expansion board, so that the second input / output expansion board controls the digital tube to display the identification number based on the digital tube control rules.

[0039] Furthermore, the system also includes:

[0040] The status determination module is used to determine whether there is an external cable in an abnormal connection state;

[0041] The first execution module is used to suspend the execution of the boot program if there is an external cable in an abnormal connection state.

[0042] The second execution module is used to execute the power-on procedure if there is no external cable in an abnormal connection state, and to send a power-on prompt message to the second BMC of the second device. The power-on prompt message is used to notify the second BMC to execute the power-on procedure.

[0043] The beneficial effects of the present invention are as follows: the external cable, external cable presence detection device, power-on self-test method and system provided by the present invention, by setting a presence detection circuit for the external cable, and the presence detection circuit is connected to the internal control device of the first device through the first pin of the first port of the first device, the internal control device determines whether the external cable is in place based on the circuit on / off state. This method can ensure detection accuracy, and the heterogeneous sensor can quickly locate abnormal external cables, ensuring that all external cables are available after power-on.

[0044] Furthermore, the design principle of this invention is reliable, the structure is simple, and it has a very wide range of application prospects. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 This is a schematic diagram of the structure of an external cable presence detection device according to an embodiment of this application.

[0047] Figure 2 This is a schematic diagram of the structure of an external cable according to an embodiment of this application.

[0048] Figure 3 This is an exemplary flowchart of a power-on self-test method according to an embodiment of the present invention.

[0049] Figure 4 This is another exemplary flowchart of a power-on self-test method according to an embodiment of the present invention.

[0050] Figure 5 This is an exemplary block diagram of a power-on self-test system according to an embodiment of the present invention.

[0051] Among them, 1. Gold finger; 2. In-situ pin; 3. Detection line; 4. I2C bus. Detailed Implementation

[0052] To enable those skilled in the art to better understand the technical solutions of this invention, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this invention.

[0053] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other.

[0054] In the description of this invention, it should be understood that the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined with "first," "second," etc., may explicitly or implicitly include one or more of that feature. In the description of this invention, unless otherwise stated, "a plurality of" means two or more.

[0055] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art will understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0056] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.

[0057] The key terms used in this invention will be explained below.

[0058] BMC, short for Baseboard Management Controller, is a remote server management controller. It allows for operations such as firmware upgrades and device monitoring even when the machine is not powered on. Fully implementing IPMI functionality in a BMC requires a powerful 16-bit or 32-bit microcontroller, RAM for data storage, flash memory for non-volatile data storage, and firmware. It provides basic remote manageability for secure remote reboots, secure power-on, LAN alerts, and system health monitoring. In addition to basic IPMI and system monitoring functions, the mBMC can also enable fast BIOS component selection and protection by utilizing one of the two flash memories to store the previous BIOS. For example, if the system fails to boot after a remote BIOS upgrade, remote administrators can switch back to the previous BIOS image to boot the system. Once the BIOS is upgraded, the BIOS image can also be locked to effectively prevent virus attacks.

[0059] The I2C bus is a simple, bidirectional, two-wire synchronous serial bus developed by Philips. It requires only two wires to transmit information between devices connected to the bus. The master device initiates data transmission and generates a clock to enable transmission; any addressed device is considered a slave. The master-slave and send-receive relationships on the bus are not constant but depend on the direction of data transmission. If the master wants to send data to a slave device, it first addresses the slave device, then actively sends data to the slave device, and finally terminates the data transmission. If the master wants to receive data from a slave device, it first addresses the slave device, then receives the data sent by the slave device, and finally terminates the receiving process. In this case, the master is responsible for generating the timing clock and terminating the data transmission.

[0060] BIOS is an abbreviation for "Basic Input Output System." On IBM PC-compatible systems, it's an industry-standard firmware interface. It's a set of programs embedded in a ROM chip on the computer's motherboard. It stores the computer's most important basic input / output programs, power-on self-test (POST) programs, and system boot programs. It can read and write specific system settings from the CMOS. Its main function is to provide the lowest-level, most direct hardware settings and control for the computer. In addition, the BIOS provides some system parameters to the operating system. Changes to system hardware are hidden by the BIOS; programs use BIOS functions rather than directly controlling the hardware. Modern operating systems often bypass the abstraction layer provided by the BIOS and directly control hardware components.

[0061] The CPU (Central Processing Unit) is the core of a computer system for computation and control, and is the final execution module for information processing and program execution.

[0062] A graphics processing unit (GPU), also known as a display core, visual processor, or display chip, is a microprocessor specifically designed for performing image and graphics-related calculations on personal computers, workstations, game consoles, and some mobile devices (such as tablets and smartphones).

[0063] The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0064] The present invention also provides, for example Figure 1The external cable shown has the following specific structure: a cable and a first connector and a second connector located at both ends of the cable. The first connector includes a first in-place pin, and the second connector includes a second in-place pin. The first in-place pin and the second in-place pin are electrically connected. The length of the first in-place pin is the minimum length among all the pin lengths of the first connector, and the length of the second in-place pin is the minimum length among all the pin lengths of the second connector.

[0065] The head and tail are interconnected using high-speed cables (taking MiniSAS-HD as an example). The number of cables depends on the model and configuration. Each gold finger 1 at both ends of the cable is designed with a standby pin 2. The standby pin 2 is shorter than other information pins. The standby pin 2 only makes contact with the corresponding pin of the connector when the cable port is fully inserted into the board connector. The standby pins 2 at both ends of the gold fingers are connected by a detection line (cable) 3. At the same time, there is an I2C bus 4 in the cable.

[0066] Based on the aforementioned external cable, a method is provided as follows: Figure 2 The external cable presence detection device shown defines the GPU service device of the heterogeneous server as the first device and the CPU service device of the heterogeneous server as the second device. Multiple external cables connect the first device and the second device. The specific structure includes:

[0067] The first device includes multiple first ports, each first port being connected to a first connector of an external cable. Each first port includes a first pin, which is connected to a first in-place pin of the first connector. The first pin is electrically connected to a detection power supply. The first pin is connected to an internal control device of the first device. The second device includes multiple second ports, each second port being connected to a second connector of an external cable. Each second port includes a second pin, which is connected to a second in-place pin of the second connector. The second in-place pin is electrically connected to the first in-place pin. The second pin is grounded.

[0068] The external cable, the interface ports of the first and second devices, and the power supply on the line form a detection loop. When the external cable is properly connected, the detection loop is open after the server is powered on; if it is not properly connected, the detection loop is open. The internal control device of the first device can determine the presence of the external cable by monitoring the continuity of the detection loop.

[0069] In one implementation, the internal control device includes a first BMC (Browser Controller) and a first I / O expansion board (IO Expander) of the first device. A first pin of the first port is connected to a corresponding pin of the first I / O expansion board, and the first I / O expansion board is connected to the first BMC of the first device. By using the BMC as the core chip of the internal control device, in conjunction with the first I / O expansion board, accurate positioning of out-of-position external cables can be achieved without major hardware modifications; only the addition of an I / O Expander is required.

[0070] Existing methods for locating and detecting external cables, such as those that use software to check ping connectivity to determine cable presence, generate numerous log alerts when the external cable is missing. This requires maintenance personnel to analyze the logs and locate the faulty cable based on its device type. The log alert method is not intuitive. Therefore, in one embodiment of this invention, the internal control device is connected to the input port of a second input / output expansion board, and the output of the second input / output expansion board is connected to a digital display, including but not limited to a seven-segment display.

[0071] Specifically, the cable presence pin of the high-speed connector at the head end is connected to GND. The tail end features a cable presence detection circuit, with the IO Expander pin connected to the cable presence pin of the high-speed connector. The IO Expander is connected to the tail end BMC via an I2C bus. When an external high-speed cable is not inserted, or when one end of the cable is not inserted, the corresponding pin of the tail end IO Expander is at a high level. When both ends of the high-speed cable are inserted, the corresponding pin of the tail end IO Expander is at a low level. The BMC can obtain the connection status of each cable by polling the IO Expander register via the I2C bus. The front window at the tail end features two 8-digit LED displays to poll and display the serial numbers of external cables that are not correctly connected. Each segment of the LED display is controlled by an independent pin of the IO Expander. The BMC encodes the numbers "0-9" to be displayed and writes the encoded values ​​to the IO Expander register via the I2C bus to display the numerical values, allowing field operators to quickly and intuitively obtain information about cables with abnormal connections.

[0072] Furthermore, when the second device detects the presence of the external cable, it needs to notify the first device. Therefore, in one embodiment of the present invention, with the two ends of the external cable inserted into the first and second devices respectively, the first BMC communicates with the second BMC of the second device via a specific external cable. Specifically, the head unit and the tail unit use the IPMB protocol for data exchange. The head unit BMC controls the head unit's power-on timing by reading the external cable presence information detected by the tail unit BMC.

[0073] The first and second input / output expansion boards can use either an IO Expander or a CPLD GPIO.

[0074] The detection process of the external cable presence detection device includes: After the tail unit's standby power is turned on, the tail unit's BMC starts first. Before the tail unit's BMC detects that all cables are in place, it turns off all indicator lights on the tail unit. If any external cable is not properly connected, the digital display will cycle through and show the sequence number of the cable that is not properly connected, allowing on-site personnel to identify the anomaly and troubleshoot the corresponding cable connection according to the sequence number indicated by the digital display. Once all cables are correctly connected, the front window digital display turns off, other indicator lights display normally, and the tail unit starts up normally. After the head unit's standby power is turned on, the head unit's BMC starts first and obtains the cable presence information detected by the tail unit's BMC via the IPMB bus. If any cable is not in place, all indicator lights on the head unit turn off until the tail unit's BMC detects that all cables are in place, the head unit's indicator lights display normally, and then it waits for the tail unit to start up. After the tail unit starts up, the head unit starts up normally.

[0075] The power-on self-test method provided in this embodiment of the invention is executed by a computer device, and correspondingly, the power-on self-test system runs in the computer device.

[0076] Figure 3 This is a schematic flowchart illustrating a method according to an embodiment of the present invention. Wherein, Figure 3 The executing entity can be a power-on self-test system. Depending on different requirements, the order of the steps in this flowchart can be changed, and some steps can be omitted.

[0077] like Figure 3 As shown, the method includes:

[0078] Step 310: After the first BMC is powered on, it first captures the register data of the first input / output expansion board. The register data includes the level state of each pin of the first input / output expansion board.

[0079] Step 320: Based on the correspondence between each pin of the first input / output expansion board and the first port, convert the level state of each pin of the first input / output expansion board into the connection state of each external cable.

[0080] Step 330: The external cable number in an abnormal connection state is displayed on the digital display by encoding control.

[0081] To facilitate understanding of the present invention, the following description further illustrates the power-on self-test method provided by the present invention, based on the principle of the power-on self-test method and the process of performing a power-on self-test on a heterogeneous server in the embodiments.

[0082] External cables use the PCIe bus, unlike SAS / SATA, optical ports, and network ports which support hot-swapping. Inserting them before or after power-on has no impact on the system. However, the PCIe bus between the rear and front of the computer must be reliably connected before power-on; otherwise, the corresponding devices will not be recognized. For details, please refer to [link / reference needed]. Figure 4 The power-on self-test method includes:

[0083] S1. After the first BMC is powered on, it first captures the register data of the first input / output expansion board. The register data includes the level state of each pin of the first input / output expansion board.

[0084] After power-on, the first BMC of the first device first executes a detection program, which reads the data recording the level status of each pin in the register of the first input / output expansion board through the I2C bus.

[0085] After the heterogeneous server is powered on, the detection power supply in the external cable presence detection device powers the detection circuit. If the external cable is plugged in, the voltage level of each pin of the first input / output expansion board should be low.

[0086] After the machine is powered on but before it is turned on, all indicator lights (power indicator, health indicator, etc.) should remain off until the external cables are confirmed to be correctly connected, to alert on-site operators to any abnormalities and to allow for further troubleshooting.

[0087] S2. Based on the correspondence between each pin of the first input / output expansion board and the first port, convert the level state of each pin of the first input / output expansion board into the connection state of each external cable.

[0088] Based on the connection relationship between each pin of the first input / output expansion board and the first port, a one-to-one mapping relationship is established between the first port number and the pin number of the first input / output expansion board, and the first port number is bound to the associated second port number; a rule for converting the level state to the connection state is preset, the rule includes that a high level state corresponds to an abnormal state and a low level state corresponds to a normal state; based on the one-to-one mapping relationship and the rule, the level state of each pin of the first input / output expansion board is converted to the connection state of the external cable between the corresponding first port and the second port.

[0089] For example, when the external high-speed cable is not inserted, or when one end of the cable is not inserted, the pin corresponding to the IO Expander at the tail end is at a high level. When both ends of the high-speed cable are inserted, the pin corresponding to the IO Expander at the tail end is at a low level. The BMC can obtain the connection status of each cable by polling the IO Expander register through the I2C bus.

[0090] S3. The digital display is controlled by encoding to show the number of the external cable that is in an abnormal connection state.

[0091] A unique identification number is pre-generated for the external cable between the first port and the second port; the identification number of the external cable with an abnormal connection status is written into the register of the second input / output expansion board, so that the second input / output expansion board controls the digital tube to display the identification number based on the digital tube control rules.

[0092] For example, the front window at the rear of the machine is designed with two 8-digit LED displays to poll and display the serial numbers of external cables that are not connected correctly. Each field of the LED display is controlled by an independent pin of the IO Expander. The BMC encodes the "0-9" to be displayed and writes the encoded value to the IO Expander register through the I2C bus to display the value, so that the field operators can quickly and intuitively obtain information about the abnormally connected cables.

[0093] By detecting the presence of information at both ends of the external cable and displaying the cable serial number with abnormal connection through a digital tube, the system provides on-site operators with a quick and accurate direction for inspection, avoiding reliance on the operator's skill and proficiency.

[0094] S4. The first BMC of the first device will send the in-place detection result to the second BMC of the second device, and the first BMC and the second BMC will negotiate to power on based on the detection result.

[0095] The first BMC determines whether there is an external cable in an abnormal connection state: if yes, it suspends the execution of the power-on procedure; if no, it executes the power-on procedure and sends a power-on prompt message to the second BMC of the second device. The power-on prompt message is used to notify the second BMC to execute the power-on procedure.

[0096] After the tail unit's standby power is turned on, the tail unit's BMC starts first. Before detecting that all cables are in place, the tail unit's BMC turns off all indicator lights. If any external cable is not properly connected, the digital display will cycle through and show the sequence number of the missing cable, allowing on-site personnel to identify the anomaly and troubleshoot the corresponding cable connection according to the digital display's sequence number. Once all cables are correctly connected, the front window digital display turns off, other indicator lights display normally, and the tail unit powers on normally. After the head unit's standby power is turned on, the head unit's BMC starts first, acquiring cable presence information detected by the tail unit's BMC via the IPMB bus. If any cable is missing, all head unit indicator lights turn off until the tail unit's BMC detects that all cables are in place, at which point the head unit indicator lights display normally, and then waits for the tail unit to power on. After the tail unit powers on, the head unit powers on normally.

[0097] By using the correctness of cable connections as a constraint for controlling the startup of the server head and tail, a large number of repair requests due to improper operation during server racking and relocation are avoided, thus improving the robustness of the system and the convenience of racking and maintenance.

[0098] In some embodiments, the power-on self-test system 500 may include multiple functional modules composed of computer program segments. The computer programs of each program segment in the power-on self-test system 500 may be stored in the memory of a computer device and executed by at least one processor to perform (see details). Figure 3 (Description) The power-on self-test function.

[0099] In this embodiment, the power-on self-test system 500 can be divided into multiple functional modules according to the functions it performs, such as... Figure 5 As shown. The functional modules may include: a data acquisition module 510, a data conversion module 520, and a data display module 530. The module referred to in this invention is a series of computer program segments that can be executed by at least one processor and perform a fixed function, and which are stored in memory. In this embodiment, the functions of each module will be described in detail in subsequent embodiments.

[0100] The data capture module 510 is used to capture the register data of the first input / output expansion board first after the first BMC is powered on. The register data includes the level state of each pin of the first input / output expansion board.

[0101] The data conversion module 520 is used to convert the voltage level of each pin of the first input / output expansion board into the connection state of each external cable based on the correspondence between each pin of the first input / output expansion board and the first port.

[0102] The data display module 530 is used to control the digital display to show the number of an external cable that is in an abnormal connection state through encoding.

[0103] Optionally, as an embodiment of the present invention, the data conversion module includes:

[0104] The mapping establishment unit is used to establish a one-to-one mapping relationship between the first port number and the pin number of the first input / output expansion board based on the connection relationship between each pin of the first input / output expansion board and the first port in advance, and the first port number is bound to the associated second port number;

[0105] The rule setting unit is used to pre-set rules for converting the level state to the connection state. The rules include a high level state corresponding to an abnormal state and a low level state corresponding to a normal state.

[0106] The data conversion unit is used to convert the level state of each pin of the first input / output expansion board into the connection state of the external cable between the corresponding first port and the second port based on the one-to-one mapping relationship and the rules.

[0107] Optionally, as an embodiment of the present invention, the data display module includes:

[0108] The numbering generation unit is used to pre-generate a unique identification number for the external cable between the first port and the second port;

[0109] The number display unit is used to write the identification number of the external cable whose connection status is abnormal into the register of the second input / output expansion board, so that the second input / output expansion board controls the digital tube to display the identification number based on the digital tube control rules.

[0110] Optionally, as an embodiment of the present invention, the system further includes:

[0111] The status determination module is used to determine whether there is an external cable in an abnormal connection state;

[0112] The first execution module is used to suspend the execution of the boot program if there is an external cable in an abnormal connection state.

[0113] The second execution module is used to execute the power-on procedure if there is no external cable in an abnormal connection state, and to send a power-on prompt message to the second BMC of the second device. The power-on prompt message is used to notify the second BMC to execute the power-on procedure.

[0114] Therefore, this invention sets up an in-place detection circuit for external cables, and the first pin of the in-place detection circuit is connected to the internal control device of the first device at the first port of the first device. The internal control device determines whether the external cable is in place based on the circuit's on / off state. This method can ensure detection accuracy, and the heterogeneous sensor can quickly locate abnormal external cables, ensuring that all external cables are usable after power-on. The technical effects achieved by this embodiment can be seen in the description above, and will not be repeated here.

[0115] The same or similar parts between the various embodiments in this specification can be referred to mutually. In particular, the terminal embodiments are basically similar to the method embodiments, so the description is relatively simple, and the relevant parts can be referred to the description in the method embodiments.

[0116] In the embodiments provided by this invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between systems or modules may be electrical, mechanical, or other forms.

[0117] The modules described as separate components may or may not be physically separate. The components shown as modules 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 modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0118] In addition, the functional modules in the various embodiments of the present invention can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0119] Although the present invention has been described in detail with reference to the accompanying drawings and preferred embodiments, the invention is not limited thereto. Various equivalent modifications or substitutions can be made to the embodiments of the invention by those skilled in the art without departing from the spirit and essence of the invention, and such modifications or substitutions should all be within the scope of the invention. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the invention should also be covered within the protection scope of the invention. Therefore, the protection scope of the invention should be determined by the scope of the claims.

Claims

1. An external cable presence detection device, based on an external cable used for PCIe bus interconnection between a first device and a second device in a heterogeneous server, the external cable comprising: The cable includes a first connector and a second connector located at both ends of the cable. The first connector is used to connect to a first device, and the second connector is used to connect to a second device. The first connector includes a first in-situ pin, and the second connector includes a second in-situ pin. The first in-situ pin and the second in-situ pin are electrically connected through an internal conductor of the cable. The length of the first in-situ pin is the minimum length among all pins of the first connector, and the length of the second in-situ pin is the minimum length among all pins of the second connector. This ensures that when the cable is fully inserted into both devices, the first in-situ pin is connected to the detection power supply of the first device, and the second in-situ pin is connected to the grounding terminal of the second device, forming an in-situ detection loop across devices. The heterogeneous server includes a first device and a second device, and the device includes: The first device includes multiple first ports, each first port being connected to a first connector of an external cable. Each first port includes a first pin, which is connected to a first in-situ pin of the first connector. The first pin is electrically connected to a detection power supply. The first pin is connected to an internal control device of the first device. The second device includes multiple second ports, each of which connects to a second connector of an external cable. Each second port includes a second pin, which connects to a second in-situ pin of the second connector. The second in-situ pin is electrically connected to a first in-situ pin. The second pin is grounded to form an in-situ detection loop across the device together with the first pin and the detection power supply. The internal control device of the first device is connected to the BMC of the second device for communication. Based on the on / off state of the in-situ detection loop, it coordinates the power-on process of the first and second devices to avoid the PCIe device being unable to be enumerated due to improper cable connection.

2. The apparatus according to claim 1, characterized in that, The internal control device includes a first BMC and a first input / output expansion board of the first device. The first pin of the first port is connected to the corresponding pin of the first input / output expansion board, and the first input / output expansion board is connected to the first BMC of the first device.

3. The apparatus according to claim 1, characterized in that, The internal control device is connected to the input port of the second input / output expansion board, and the output end of the second input / output expansion board is connected to the digital display, which includes, but is not limited to, a seven-segment display.

4. The apparatus according to claim 2, characterized in that, With the first device and the second device plugged into the two ends of the external cable respectively, the first BMC communicates with the second BMC of the second device through the external cable.

5. A power-on self-test method, based on the external cable presence detection device according to any one of claims 1-4, characterized in that, include: After the first BMC is powered on, it first captures the register data of the first input / output expansion board. The register data includes the level state of each pin of the first input / output expansion board. The level state reflects whether the cross-device detection loop of the corresponding external cable is conductive. Based on the correspondence between each pin of the first input / output expansion board and the first port, and the binding relationship between the first port and the second port, the level state of each pin of the first input / output expansion board is converted into the connection state of each external cable. The digital display is controlled by encoding to show the numbers of external cables in abnormal connection states. If an external cable in an abnormal connection state is found, the digital display is controlled to show the unique identification number of the abnormal external cable, and the boot process of the first and second devices is paused until all external cables are in a normal connection state, and then the first BMC and the second BMC are triggered to jointly execute the boot process.

6. The method according to claim 5, characterized in that, Based on the correspondence between each pin of the first input / output expansion board and the first port, the voltage level of each pin of the first input / output expansion board is converted into the connection status of each external cable, including: Based on the connection relationship between each pin of the first input / output expansion board and the first port, a one-to-one mapping relationship between the first port number and the pin number of the first input / output expansion board is established in advance, and the first port number is bound to the associated second port number; A pre-defined rule for converting a level state to a connected state is provided, wherein a high level state corresponds to an abnormal state and a low level state corresponds to a normal state. Based on the one-to-one mapping relationship and the rules, the level state of each pin of the first input / output expansion board is converted into the connection state of the external cable between the corresponding first port and the second port.

7. The method according to claim 5, characterized in that, The digital display shows the external cable number that is in an abnormal connection state, controlled by encoding. A unique identification number is pre-generated for the external cable between the first port and the second port; The identification number of the external cable whose connection status is abnormal is written into the register of the second input / output expansion board, so that the second input / output expansion board controls the digital tube to display the identification number based on the digital tube control rules.

8. The method according to claim 5, characterized in that, After converting the voltage levels of each pin of the first input / output expansion board to the connection states of each external cable based on the correspondence between each pin and the first port, the method further includes: Determine if there are any external cables in an abnormal connection state: If so, then pause the boot process; If not, the power-on procedure is executed, and a power-on prompt message is sent to the second BMC of the second device. The power-on prompt message is used to notify the second BMC to execute the power-on procedure.

9. A power-on self-test system, used to implement the method as described in any one of claims 5-7, characterized in that, include: The data capture module is used to capture the register data of the first input / output expansion board first after the first BMC is powered on. The register data includes the level state of each pin of the first input / output expansion board. The level state reflects whether the cross-device detection loop of the corresponding external cable is conductive. The data conversion module is used to convert the voltage level of each pin of the first input / output expansion board into the connection state of each external cable based on the correspondence between each pin of the first input / output expansion board and the first port, as well as the binding relationship between the first port and the second port. The data display module is used to control the digital display to display the number of external cables in an abnormal connection state through encoding. If there is an external cable in an abnormal connection state, the digital display is controlled to display the unique identification number of the abnormal external cable, and the boot program of the first and second devices is paused until all external cables are in a normal connection state, and then the first BMC and the second BMC are triggered to jointly execute the boot program.

Citation Information

Patent Citations

  • Method and device for judging mounting faults of high-speed connectors

    CN109581140A

  • Connectivity detection system for Cable and connector

    CN110515787A

  • Power-on self-test code display device, method, server and system

    CN116010181A