Server leakage detection method, device, equipment and storage medium

Abstract

This application relates to a server leakage detection method, apparatus, device, and storage medium, applied to a server leakage detection system. The system includes N single nodes, which are connected via a backplane. The main technical solution includes: each single node selector switch acquires the detection signal sent by the corresponding leakage detection unit in real time; when any selector switch acquires a leakage signal, the main power state of the single node corresponding to the selector switch is acquired, and based on the main power state, the field-programmable gate array (FPGA) or chassis management controller is notified to power off each single node of the server; when the detection signals acquired by the selector switches of each single node are all normal signals, the chassis management controller is notified to power on each single node of the server. This application improves the safety factor of server operation by powering off the server after leakage is detected.

Description

Technical Field

[0001] This application relates to the field of server technology, and in particular to a server leakage detection method, apparatus, device, and storage medium. Background Technology

[0002] With the continuous development of technologies such as big data, deep computing, and cloud computing, the power consumption of various electronic devices is also constantly increasing. The ever-increasing integration and power consumption of these devices pose new challenges to their heat dissipation capabilities, making heat dissipation a crucial factor restricting industry development. The server industry is no exception. With the rapid development of artificial intelligence, AI servers and multi-node servers have emerged. Because multi-node servers have stronger computing power and more compact structural designs, they place even higher demands on server heat dissipation.

[0003] Traditional implementations typically employ liquid-cooled servers, including single-socket, dual-socket, and AI box configurations. When a liquid-cooled server connected using these methods experiences a leak, it notifies the BMC (Battery Management Center), which then sends an alarm message and logs the alarm via web interface. However, simply notifying the BMC without taking other measures is dangerous. Server maintenance personnel must constantly monitor the server's alarm logs; even slight negligence can lead to serious consequences. Summary of the Invention

[0004] Based on this, this application provides a server leakage detection method, apparatus, device, and storage medium, which improves the safety factor of server operation by cutting off power after detecting leakage in the server.

[0005] Firstly, a server leakage detection method is provided, applied to a server leakage detection system. The server leakage detection system includes N single nodes, which are connected via a backplane. Each single node includes a leakage detection unit, a selector switch connected to the leakage detection unit, and a field-programmable gate array (FPGA) connected to the selector switch. The FPGA and the backplane are connected, and one end of the backplane furthest from the FPGA is connected to a chassis management controller. The method includes:

[0006] Each single-node selector switch acquires the detection signal sent by the corresponding leakage detection unit in real time; the detection signal includes leakage signal and normal signal;

[0007] When the detection signal obtained by any selector switch is a leakage signal, the main power status of the single node of the corresponding selector switch is obtained, and the field programmable gate array or chassis management controller is notified to perform power-off operation on each single node of the server based on the main power status.

[0008] When the detection signals obtained by the selector switches of each individual node are all normal signals, the chassis management controller is notified to power on each individual node of the server.

[0009] According to one achievable method in the embodiments of this application, the main power status of each individual node of the server includes a main power-on state and a main power-off state; and based on the main power status, the field-programmable gate array or chassis management controller is notified to perform a power-off operation on each individual node of the server, including:

[0010] If the main power of a single node of the corresponding selector switch is energized, then the main power of each single node of the field programmable gate array control server is disconnected.

[0011] If the single node of the corresponding selector switch is in a main power-off state, then the chassis management controller is notified to disconnect the standby power of each single node of the server.

[0012] According to one achievable method in an embodiment of this application, after the step of notifying each individual node of the field-programmable gate array control server to disconnect the main power, the method further includes:

[0013] The field-programmable gate array (FPGA) sends a power-off command to the chassis management controller to notify the chassis management controller to disconnect the standby power of each individual node of the control server.

[0014] According to one feasible method in the embodiments of this application, before the step of notifying the field-programmable gate array or chassis management controller to perform power-off operation on each individual node of the server based on the main power status, the method includes:

[0015] The field-programmable gate array acquires the power-off confirmation command set by the user in the chassis management controller. The power-off confirmation command includes a power-off command after leakage and a power-on command after leakage.

[0016] If the power-off confirmation command is a power-off command after leakage, the field-programmable gate array and the chassis management controller will perform a power-off operation based on the received corresponding power-off notification; otherwise, no operation will be performed.

[0017] According to one possible implementation method in an embodiment of this application, two chassis management controllers are provided, including a master chassis management controller and a slave chassis management controller, and the method includes:

[0018] When both the main chassis management controller and the slave chassis management controller are in place, the main chassis management controller participates in the leakage detection of each individual node, while the slave chassis management controller is in standby mode.

[0019] When the main chassis management controller fails, it switches from the chassis management controller to the main chassis management controller, which takes over the leakage detection work of each individual node.

[0020] According to one possible implementation method in an embodiment of this application, each single node further includes a substrate management controller, and the substrate management controller and the leakage detection unit are communicatively connected. The method includes:

[0021] Each single-node substrate management controller monitors the detection signals sent by the corresponding leakage detection unit in real time;

[0022] When a leak signal is detected from any leak detection unit, an alarm signal is issued and an alarm log is generated for easy viewing by staff.

[0023] According to one possible implementation in an embodiment of this application, each single node further includes a leakage simulation connector, and the leakage simulation connector is communicatively connected to a field-programmable gate array. The method includes:

[0024] The substrate management controller sends a liquid leakage simulation command to the chassis management controller via the I2C bus;

[0025] The chassis management controller instructs each single-node field-programmable gate array to send a simulated leakage signal based on the leakage simulation command.

[0026] Each single-node leakage simulation connector initiates leakage simulation detection based on the simulated leakage signal.

[0027] Secondly, a server leakage detection device is provided, applied to a server leakage detection system. The server leakage detection system includes N single nodes, which are communicatively connected via a backplane. Each single node includes a leakage detection unit, a selector switch communicatively connected to the leakage detection unit, and a field-programmable gate array (FPGA) communicatively connected to the selector switch. The FPGA is communicatively connected to the backplane, and one end of the backplane furthest from the FPGA is communicatively connected to a chassis management controller. The device is installed in the server leakage detection system and includes:

[0028] The signal acquisition module is used by each single-node selector switch to acquire the detection signal sent by the corresponding leakage detection unit in real time; the detection signal includes leakage signal and normal signal.

[0029] The power-off module is used to obtain the main power status of the single node of the corresponding selector switch when the detection signal obtained by any selector switch is a leakage signal, and to notify the field programmable gate array or chassis management controller to perform power-off operation on each single node of the server based on the main power status.

[0030] The power-on module is used to notify the chassis management controller to power on each node of the server when the detection signals obtained by the selector switches of each node are all normal signals.

[0031] Thirdly, a computer device is provided, comprising:

[0032] At least one processor; and

[0033] A memory that is communicatively connected to at least one processor; wherein,

[0034] The memory stores computer instructions that can be executed by at least one processor to enable the at least one processor to perform the methods involved in the first aspect above.

[0035] Fourthly, a computer-readable storage medium is provided, having stored thereon computer instructions, characterized in that the computer instructions are used to cause a computer to perform the methods involved in the first aspect above.

[0036] According to the technical content provided in the embodiments of this application, each single-node selector switch acquires the detection signal sent by the corresponding leakage detection unit in real time. When the detection signal acquired by any selector switch is a leakage signal, the main power status of the single node of the corresponding selector switch is acquired, and based on the main power status, the field-programmable gate array or chassis management controller is notified to perform a power-off operation on each single node of the server. When the detection signals acquired by the selector switches of each single node are all normal signals, the chassis management controller is notified to perform a power-on operation on each single node of the server. The above operation determines whether to automatically power off or automatically power on each single node of the server based on the detection signal sent by the leakage detection unit, so as to improve the safety factor of each single node of the server and provide further protection for the normal operation of each single node of the server. Attached Figure Description

[0037] Figure 1 This is a system architecture diagram of a server leakage detection method in one embodiment;

[0038] Figure 2 This is a flowchart illustrating a server leakage detection method in one embodiment;

[0039] Figure 3 This is a schematic diagram of a preferred process for a server leakage detection method in one embodiment;

[0040] Figure 4 This is a structural block diagram of a server leakage detection device in one embodiment;

[0041] Figure 5 This is a schematic structural diagram of a computer device in one embodiment. Detailed Implementation

[0042] The present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the scope of the present application.

[0043] For ease of understanding, the system to which this application applies will first be described. This application provides a server leakage detection method, which can be applied to, for example... Figure 1 The server leakage detection system shown is a high-density system comprising N single nodes. These nodes are interconnected via a backplane to enable communication between them. Each single node includes a leakage detection connector, a leakage detection unit connected to the connector, a selector switch connected to the unit, and a field-programmable gate array (FPGA) connected to the switch. The FPGA is connected to the backplane, with the end of the backplane furthest from the FPGA connected to a chassis management controller.

[0044] Each individual node's leak detection connector can send the leak detection signal from the leak detection cable to the corresponding leak detection unit in real time. The leak detection unit can be a leak detection circuit, which is powered by a power supply unit (PSU). Therefore, the leak detection unit can detect the detection signal sent by the leak detection connector in real time and send the detection result to the selector switch.

[0045] The selector switch can be a switch IC, used to determine the output of different power-off commands based on the detection results, and to determine whether the main power of the single node of the corresponding selector switch exists. It should be noted that when a selector switch of a single node detects a leakage signal, it is necessary to determine the main power status of the single node to which the selector switch belongs, and to make further instructions based on the main power status of that single node.

[0046] A Field Programmable Gate Array (FPGA) is a further development based on programmable devices such as PAL, GAL, and CPLD. It emerged as a semi-custom circuit in the field of Application-Specific Integrated Circuits (ASICs), addressing the shortcomings of custom circuits while overcoming the limited gate count of traditional programmable devices. In this application, it is used to control the power-off operation of each individual node of the server and send power-off commands to the chassis management controller.

[0047] The chassis management controller can be a CMC (Chain Management Controller), which internally contains a Complex Programmable Logic Device (CPLD). CPLDs are devices evolved from PAL and GAL devices; they are relatively large and complex in structure, and are digital integrated circuits whose logic functions can be customized by the user according to their needs. Here, it is used to disconnect the standby power of each individual node of the server based on a power-off command sent by a selection switch or a field-programmable gate array.

[0048] Figure 2 A flowchart illustrating a server leakage detection method provided in this application embodiment, the method can be performed by, for example... Figure 1 The system shown is executing. (As indicated) Figure 2 As shown, the method may include the following steps:

[0049] Step 201: Each single node selector switch acquires the detection signal sent by the corresponding leakage detection unit in real time.

[0050] The detection signals include leakage signals and normal signals.

[0051] Here, each individual node's leakage detection unit is in real-time monitoring mode, sending the detection signal to the corresponding Switch IC in real time. Since the detection signal includes both leakage and normal signals, the Switch IC will perform different operations based on different signals.

[0052] Step 203: When the detection signal obtained by any selector switch is a leakage signal, the main power status of the single node of the corresponding selector switch is obtained, and the field programmable gate array or chassis management controller is notified to perform power-off operation on each single node of the server based on the main power status.

[0053] When a leakage signal is detected by any Switch IC, it indicates that leakage has occurred in that single node. The system then further acquires the main power status of the single node corresponding to the selector switch and, based on this status, notifies the field-programmable gate array (FPGA) to either power off the main power of each single node or notifies the chassis management controller to power off the standby power of each single node. Here, acquiring the main power status of the single node corresponding to the selector switch primarily involves acquiring the main power status of the last electrical node under that single node, i.e., the powergood signal of the last main power. The reason for acquiring the main power status of the last electrical node under that single node is that the electrical nodes of each server node have a time sequence. If the main power of the last electrical node of a single node exists, it means that all electrical nodes of that single node are good; if the main power of the last electrical node of a single node does not exist, it means that all electrical nodes of that single node are disconnected. Here, main power can be represented by "main power," and standby power can be represented by "stby."

[0054] Step 205: When the detection signals obtained by the selector switches of each individual node are all normal signals, the chassis management controller is notified to power on each individual node of the server.

[0055] Here, when all the detection signals obtained by the selector switches of each individual node are normal, it indicates that the server is currently not leaking liquid. Any selector switch can then notify the chassis management controller to power on each individual node of the server. This power-on primarily refers to the standby power being executed by the CPLD in the CMC. The CPLD controls the standby power (stby power) of each individual node. It should be noted that this operation is primarily performed because when a leak occurs in a single node of the server, personnel will repair it. After repair, a re-inspection is required. If no leak is detected, the CPLD will control the stby power of each individual node to power on. Therefore, regardless of whether a power outage has occurred previously, as long as all detection signals are normal, the power-on operation will be performed to further ensure the normal operation of the server.

[0056] As can be seen, this embodiment acquires the detection signal sent by the corresponding leakage detection unit in real time through the selection switch of each single node. When the detection signal acquired by any selection switch is a leakage signal, the main power status of the single node of the corresponding selection switch is acquired, and the field programmable gate array or chassis management controller is notified to perform a power-off operation on each single node of the server based on the main power status. When the detection signals acquired by the selection switches of each single node are all normal signals, the chassis management controller is notified to perform a power-on operation on each single node of the server. The above operation determines whether to automatically power off or automatically power on each single node of the server based on the detection signal sent by the leakage detection unit, so as to improve the safety factor of each single node of the server and provide further protection for the normal operation of each single node of the server.

[0057] The following describes in detail, with reference to an embodiment, step 203 above, "and based on the main power status, notify the field programmable gate array or chassis management controller to perform power-off operation on each individual node of the server".

[0058] The main power status of each server node includes a main power-on state and a main power-off state. If the node corresponding to the selector switch is in the main power-on state, the field-programmable gate array (FPGA) is notified to disconnect the main power of each server node. At the same time, the FPGA sends a power-off command to the chassis management controller to notify the chassis management controller to disconnect the standby power of each server node. If the node corresponding to the selector switch is in the main power-off state, the chassis management controller is notified to disconnect the standby power of each server node.

[0059] Here, the selector determines further instruction output based on the main power status of each individual node of the server. If the individual node corresponding to the selector is in a state of main power being on, i.e., main power exists, a main power disconnect instruction is sent to the FPGA to notify the FPGA to control the main power of each individual node of the server to be disconnected, i.e., to control the main power to be de-energized. At the same time, after disconnecting each individual node, the FPGA also needs to send a stby power-off instruction to the CPLD on the CMC. After receiving the stby power-off instruction, the CPLD controls the standby power (i.e., stby power) of each individual node of the server to be de-energized.

[0060] When the main power of a single node of the selector switch is off, the Switch IC directly notifies the CPLD control server on the CMC to power down the standby (stby) power of each node. It should be noted that both the main power disconnection of each node on the FPGA control server and the power-down of the standby (stby) power of each node on the CMC's CPLD control server are achieved through communication via the backplane. This operation, by sequentially disconnecting the main and standby power of each node after determining that any single node of the server has leaked, improves the safety of the server leak detection system.

[0061] In some embodiments, before the step of notifying the field-programmable gate array (FPGA) or chassis management controller to perform a power-off operation on each individual node of the server based on the main power status, the method includes: the FPGA obtaining a power-off confirmation instruction set by the user on the chassis management controller; if the power-off confirmation instruction is a power-off instruction after leakage, the FPGA and the chassis management controller perform a power-off operation based on the received corresponding power-off notification; otherwise, no operation is performed.

[0062] Here, users can configure the power-off operation and confirmation command after a leak in the CMC web interface according to their needs. The power-off confirmation command includes both a power-off command and a power-on command. Power-off includes disconnecting the main power and standby power. If set to power-off, the server leak detection system will automatically power off when any node leaks. If set to power-on, neither the main power nor standby power will be disconnected when any node leaks. After the user completes the configuration in the CMC web interface, it is sent to the CMC's CPLD via the I2C (Inter-Integrated Circuit) bus. The CPLD can directly determine whether to perform a power-off upon receiving a power-off command notification from the Switch IC based on this confirmation command. It should be noted that if the user does not configure this, the default is generally no power-off after a leak.

[0063] In one feasible approach, the FPGA obtains the power-off confirmation command set by the user. If the power-off confirmation command is a power-off command after leakage, the FPGA will directly perform the power-off operation of each single node's main power after receiving the main power-off command notification sent by the Switch IC.

[0064] In another possible implementation, if the power-off confirmation command is a power-off command after leakage, the CPLD will directly perform the stby power-off operation after receiving the stby power-off command notification sent by the Switch IC.

[0065] In some embodiments, when both the main chassis management controller and the slave chassis management controller are in place, the main chassis management controller participates in the leakage detection of each individual node, while the slave chassis management controller is in standby mode. When the main chassis management controller fails, the slave chassis management controller switches to the main chassis management controller and takes its place in the leakage detection of each individual node.

[0066] Here, there are two chassis management controllers: a primary chassis management controller (CMC0) and a secondary chassis management controller (CMC1). This dual chassis management controller configuration provides redundancy for the server leak detection system. Normally, only CMC0 is active. That is, when both CMC0 and CMC1 are present, only CMC0 participates in leak detection for each individual node, while CMC1 remains in standby mode.

[0067] When CMC0 malfunctions and cannot function properly, CMC1 will switch to CMC0. After the switch is completed, CMC1 will replace CMC0 in the leakage detection work of each single node, thereby ensuring the stability of the server leakage detection system.

[0068] In some embodiments, each single-node substrate management controller monitors the detection signals sent by the corresponding leakage detection unit in real time; when a leakage signal is detected by any leakage detection unit, an alarm signal is issued and an alarm log is generated for easy viewing by staff.

[0069] Each node also includes a baseboard management controller, which can be a BMC (Base Management Controller). The baseboard management controller and the leakage detection unit are connected in communication.

[0070] Here, each individual node BMC monitors the detection signals sent by the corresponding leakage detection unit in real time. When a leakage signal is detected from any leakage detection unit, an alarm signal is issued to attract the attention of the staff. At the same time, an alarm log is generated so that the staff can maintain the server leakage detection system based on the alarm log later.

[0071] In some embodiments, the method further includes: the substrate management controller sending a leakage simulation command to the chassis management controller via an I2C bus; the chassis management controller notifying each single-node field-programmable gate array to send a simulated leakage signal based on the leakage simulation command; and each single-node leakage simulation connector initiating a leakage simulation detection operation based on the simulated leakage signal.

[0072] Each node also includes a leakage simulation connector, a leakage simulation connector and a field-programmable gate array communication connection.

[0073] Here, a simulated detection circuit is typically included in the server leakage detection system to simulate the leakage detection process on the server. This simulated detection circuit is initiated by the BMC, which sends a leakage simulation command to the CMC via the I2C bus. After receiving the leakage simulation command, the CMC sends it to the FPGA of each individual node. Upon receiving the leakage simulation command, the FPGA controls the MOS switch to turn on and sends a leakage simulation signal to the corresponding leakage simulation connector. The leakage simulation connector then initiates the leakage simulation detection operation based on the leakage simulation signal, providing further assurance for the normal operation and accuracy of the leakage detection work.

[0074] Based on the implementation methods in the above embodiments, the following will be combined with... Figure 3 A preferred method flow provided in an embodiment of this application will be described by way of example. For instance... Figure 3 As shown, the method may include the following steps:

[0075] Step 301: Each single-node selector switch acquires the detection signal sent by the corresponding leakage detection unit in real time; when the detection signal acquired by any selector switch is a leakage signal, proceed to step 302; when the detection signals acquired by each single-node selector switch are all normal signals, proceed to step 306.

[0076] Step 302: Obtain the main power status of the single node of the corresponding selector switch; if the single node of the corresponding selector switch is in the state of main power being energized, then proceed to step 303; if the single node of the corresponding selector switch is in the state of main power being de-energized, then proceed to step 305.

[0077] Step 303 then instructs the field-programmable gate array to disconnect the main power of each individual node of the server.

[0078] Step 304: The field-programmable gate array sends a power-off command to the chassis management controller to notify the chassis management controller to disconnect the standby power of each individual node of the server.

[0079] Step 305 then notifies the chassis management controller to disconnect the standby power of each individual node of the server.

[0080] Step 306 then instructs the chassis management controller to power on each individual node of the server.

[0081] It should be understood that, although Figures 2-3 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated in this application, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Furthermore, Figures 2-3At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0082] The above method embodiments can be applied to a variety of application scenarios, such as scenarios including but not limited to leak detection of N single nodes of a high-density server.

[0083] Figure 4 This is a schematic diagram of a server leakage detection device provided in an embodiment of this application. It is applied to a server leakage detection system, which includes N single nodes connected via a backplane. Each single node includes a leakage detection unit, a selector switch connected to the leakage detection unit, and a field-programmable gate array (FPGA) connected to the selector switch. The FPGA and the backplane are connected, with one end of the backplane furthest from the FPGA connected to a chassis management controller. This device can be installed in... Figure 1 In the system shown, it is used to perform such Figures 2-3 The method flow is shown below. Figure 4 As shown, the device may include: a signal acquisition module 401, a power-off module 403, and a power-on module 405. The main functions of each component module are as follows:

[0084] The signal acquisition module 401 is used for each single-node selection switch to acquire the detection signal sent by the corresponding leakage detection unit in real time; wherein, the detection signal includes leakage signal and normal signal;

[0085] The power-off module 403 is used to obtain the main power status of the single node of the corresponding selector switch when the detection signal obtained by any selector switch is a leakage signal, and to notify the field programmable gate array or chassis management controller to perform power-off operation on each single node of the server based on the main power status.

[0086] The power-on module 405 is used to notify the chassis management controller to power on each node of the server when the detection signals obtained by the selector switches of each node are all normal signals.

[0087] In some embodiments, the main power status of each individual node of the server includes a main power-on state and a main power-off state. The power-off module 403 is further used for:

[0088] If the main power of a single node of the corresponding selector switch is energized, then the main power of each single node of the field programmable gate array control server is disconnected.

[0089] If the single node of the corresponding selector switch is in a main power-off state, then the chassis management controller is notified to disconnect the standby power of each single node of the server.

[0090] In some embodiments, the power-off module 403 is further configured to:

[0091] The field-programmable gate array (FPGA) sends a power-off command to the chassis management controller to notify the chassis management controller to disconnect the standby power of each individual node of the control server.

[0092] In some embodiments, the device is further used for:

[0093] The field-programmable gate array acquires the power-off confirmation command set by the user in the chassis management controller. The power-off confirmation command includes a power-off command after leakage and a power-on command after leakage.

[0094] If the power-off confirmation command is a power-off command after leakage, the field-programmable gate array and the chassis management controller will perform a power-off operation based on the received corresponding power-off notification; otherwise, no operation will be performed.

[0095] In some embodiments, two chassis management controllers are provided, including a master chassis management controller and a slave chassis management controller, and the device is further used for:

[0096] When both the main chassis management controller and the slave chassis management controller are in place, the main chassis management controller participates in the leakage detection of each individual node, while the slave chassis management controller is in standby mode.

[0097] When the main chassis management controller fails, it switches from the chassis management controller to the main chassis management controller, which takes over the leakage detection work of each individual node.

[0098] In some embodiments, each single node further includes a substrate management controller, which is communicatively connected to the leakage detection unit. The device is also used for:

[0099] Each single-node substrate management controller monitors the detection signals sent by the corresponding leakage detection unit in real time;

[0100] When a leak signal is detected from any leak detection unit, an alarm signal is issued and an alarm log is generated for easy viewing by staff.

[0101] In some embodiments, each node further includes a leakage simulation connector, a leakage simulation connector and a field-programmable gate array communication connection, and the device is also used for:

[0102] The substrate management controller sends a liquid leakage simulation command to the chassis management controller via the I2C bus;

[0103] The chassis management controller instructs each single-node field-programmable gate array to send a simulated leakage signal based on the leakage simulation command.

[0104] Each single-node leakage simulation connector initiates leakage simulation detection based on the simulated leakage signal.

[0105] The same or similar parts among the above embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the device embodiments are basically similar to the method embodiments, so the description is relatively simple, and the relevant parts can be referred to the description of the method embodiments.

[0106] It should be noted that the embodiments of this application may involve the use of user data. In practical applications, user-specific personal data may be used in the scheme described herein within the scope permitted by applicable laws and regulations, provided that it complies with the applicable laws and regulations of the country (e.g., explicit consent from the user, actual notification to the user, explicit authorization from the user, etc.).

[0107] According to embodiments of this application, this application also provides a computer device and a computer-readable storage medium.

[0108] like Figure 5 The diagram shown is a block diagram of a computer device according to an embodiment of this application. The term "computer device" is intended to represent various forms of digital computers or mobile devices. The digital computer may include a desktop computer, a portable computer, a workbench, a personal digital assistant, a server, a mainframe computer, and other suitable computers. The mobile device may include a tablet computer, a smartphone, a wearable device, etc.

[0109] like Figure 5 As shown, device 500 includes a computing unit 501, a ROM 502, a RAM 503, a bus 504, and an input / output (I / O) interface 505. The computing unit 501, ROM 502, and RAM 503 are interconnected via the bus 504. The input / output (I / O) interface 505 is also connected to the bus 504.

[0110] The computing unit 501 can execute various processes in the method embodiments of this application according to computer instructions stored in the read-only memory (ROM) 502 or computer instructions loaded from the storage unit 508 into the random access memory (RAM) 503. The computing unit 501 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. The computing unit 501 can include, but is not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. In some embodiments, the methods provided in the embodiments of this application can be implemented as computer software programs, which are tangibly contained in a computer-readable storage medium, such as the storage unit 508.

[0111] RAM 503 can also store various programs and data required for the operation of device 500. Part or all of the computer program can be loaded and / or installed on device 500 via ROM 502 and / or communication unit 509.

[0112] The input unit 506, output unit 507, storage unit 508, and communication unit 509 in device 500 can be connected to I / O interface 505. The input unit 506 can be, for example, a keyboard, mouse, touchscreen, or microphone; the output unit 507 can be, for example, a display, speaker, or indicator light. Device 500 can exchange information and data with other devices through the communication unit 509.

[0113] It should be noted that the device may also include other components necessary for normal operation. It may also include only the components necessary for implementing the solution of this application, without necessarily including all the components shown in the figures.

[0114] Various implementations of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SOCs), payload programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof.

[0115] The computer instructions used to implement the methods of this application may be written in any combination of one or more programming languages. These computer instructions may be provided to the computing unit 501 such that when executed by the computing unit 501, such as a processor, the computer instructions cause the execution of the steps involved in the embodiments of the methods of this application.

[0116] The computer-readable storage medium provided in this application can be a tangible medium that can contain or store computer instructions for performing the steps involved in the method embodiments of this application. The computer-readable storage medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, and other forms of storage media.

[0117] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for detecting server leakage, characterized in that, An application is made in a server leakage detection system, the server leakage detection system comprising N single nodes, the N single nodes being communicatively connected via a backplane; each single node comprising a leakage detection unit, a selector switch communicatively connected to the leakage detection unit, and a field-programmable gate array (FPGA) communicatively connected to the selector switch; the FPGA and the backplane are communicatively connected, and one end of the backplane furthest from the FPGA is communicatively connected to a chassis management controller; the method includes: Each single-node selector switch acquires the detection signal sent by the corresponding leakage detection unit in real time; wherein, the detection signal includes leakage signal and normal signal; When the detection signal obtained by any selector switch is a leakage signal, the main power status of the corresponding single node of the selector switch is obtained. The main power status of each single node of the server includes the main power on state and the main power off state. And based on the main power status, instruct the field-programmable gate array or the chassis management controller to perform a power-off operation on each individual node of the server, including: If the single node of the corresponding selector switch is in a state of main power-on, then the field programmable gate array is notified to control the main power of each single node of the server to be disconnected, and the field programmable gate array sends a power-off command to the chassis management controller to notify the chassis management controller to control the standby power of each single node of the server to be disconnected. If the single node of the corresponding selector switch is in a main power-off state, then the chassis management controller is notified to control the standby power-off of each single node of the server. When the detection signals obtained by the selector switches of each individual node are all normal signals, the chassis management controller is notified to power on each individual node of the server.

2. The method according to any one of claims 1, characterized in that, Before the step of notifying the field-programmable gate array or the chassis management controller to perform a power-off operation on each individual node of the server based on the main power status, the following steps are included: The field-programmable gate array acquires the power-off confirmation command set by the user in the chassis management controller, wherein the power-off confirmation command includes a power-off command after leakage and a power-on command after leakage; If the power-off confirmation command is a power-off command after leakage, the field-programmable gate array and the chassis management controller will perform a power-off operation based on the received corresponding power-off notification; otherwise, no operation will be performed.

3. The method according to any one of claims 1-2, characterized in that, The chassis management controller is provided in two forms, including a master chassis management controller and a slave chassis management controller. The method includes: When both the main chassis management controller and the slave chassis management controller are in place, the main chassis management controller participates in the leakage detection of each single node, while the slave chassis management controller is in standby mode. When the main chassis management controller malfunctions, the slave chassis management controller switches to the main chassis management controller to replace it in the leakage detection work of each individual node.

4. The method according to claim 1, characterized in that, Each single node further includes a substrate management controller, which is communicatively connected to the leakage detection unit. The method includes: Each single-node substrate management controller monitors the detection signal sent by the corresponding leakage detection unit in real time; When a leak signal is detected from any leak detection unit, an alarm signal is issued and an alarm log is generated for easy viewing by staff.

5. The method according to claim 4, characterized in that, Each single node further includes a leakage simulation connector, which is communicatively connected to the field-programmable gate array. The method includes: The substrate management controller sends a leakage simulation command to the chassis management controller via the I2C bus; The chassis management controller instructs each single-node field-programmable gate array to send a simulated leakage signal based on the leakage simulation command. Each single-node leakage simulation connector initiates leakage simulation detection based on the simulated leakage signal.

6. A server leakage detection device, characterized in that, An application is provided in a server leakage detection system, which includes N single nodes connected via a backplane. Each single node includes a leakage detection unit, a selector switch connected to the leakage detection unit, and a field-programmable gate array (FPGA) connected to the selector switch. The FPGA and the backplane are connected, and the end of the backplane furthest from the FPGA is connected to a chassis management controller. The device is installed in the server leakage detection system, and the device includes: The signal acquisition module is used for each single-node selection switch to acquire the detection signal sent by the corresponding leakage detection unit in real time; wherein, the detection signal includes leakage signal and normal signal; The power-off module is used to obtain the main power status of a single node of the corresponding selector switch when the detection signal obtained by any selector switch is a leakage signal. The main power status of each single node of the server includes a main power on state and a main power off state. The power-off module is also used to notify the field-programmable gate array (FPGA) or the chassis management controller to perform a power-off operation on each individual node of the server based on the main power status. This includes: if the individual node of the corresponding selector switch is in a state where the main power is on, then the FPGA is notified to control the main power of each individual node of the server to be disconnected, and the FPGA sends a power-off command to the chassis management controller to notify the chassis management controller to control the standby power of each individual node of the server to be disconnected; if the individual node of the corresponding selector switch is in a state where the main power is off, then the chassis management controller is notified to control the standby power of each individual node of the server to be disconnected. The power-on module is used to notify the chassis management controller to power on each node of the server when the detection signals obtained by the selector switches of each node are all normal signals.

7. A computer device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores computer instructions executable by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the method of any one of claims 1-5.

8. A computer-readable storage medium storing computer instructions thereon, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1 to 5.

Images