A liquid cooling server leakage protection method, device, equipment and storage medium

Abstract

The application provides a liquid cooling server leakage protection method, device, equipment and storage medium, which is applied to a BMC, and comprises the following steps: in the case that a leakage fault of a liquid cooling server is detected, a power-off instruction is sent to a power supply module through a power management bus, so that the power supply module stops current output; a return value returned by the power supply module according to the power-off instruction is received; when the return value matches a pre-stored return value, it is confirmed that the power-off instruction is normally executed; the communication link between the BMC and the power supply module is established by using the power management bus, and then the power supply module is controlled by the BMC to cut off the power supply, so that the liquid cooling server is completely powered off to prevent the short circuit condition and avoid the condition that the liquid cooling server fault is not repaired and the user mistakenly starts the machine, and the liquid cooling server leakage protection safety is higher.

Description

Technical Field

[0001] This invention relates to the field of server liquid cooling technology, and in particular to a method, apparatus, equipment and storage medium for protecting liquid-cooled servers from leakage. Background Technology

[0002] In related technologies, when a liquid-cooled server leaks, the leak is generally detected by the BMC (Baseboard Management Controller). When a leak is detected, the BMC directly notifies the server to shut down or shuts it down via the CPLD (Complex Programmable Logic Device). However, when using this method to protect the liquid-cooled server, the motherboard power supply is not completely cut off, and there is a possibility that the user may turn the server on directly when it is shut down, without resolving the leak problem, which poses a significant risk of server damage. Summary of the Invention

[0003] In view of this, the present invention aims to provide a method, device, equipment and storage medium for liquid-cooled server leakage protection, in order to solve the problem that the power supply to the liquid-cooled server is not completely cut off when the server is turned off, and users may directly turn the server on when it is turned off, but the leakage problem is not solved, resulting in a high risk of server damage.

[0004] To achieve the above objectives, the technical solution of the present invention is implemented as follows:

[0005] A method for protecting a liquid-cooled server from leakage, applied to a BMC (Brain Metal Cooling Machine), the method comprising:

[0006] In the event of a leak in the liquid-cooled server, a power-off command is sent to the power supply module via the power management bus to stop the power supply module from outputting current.

[0007] Receive the return value returned by the power supply module according to the power shutdown command;

[0008] When the returned value matches the pre-stored returned value, it is confirmed that the power-off command was executed normally.

[0009] Furthermore, before sending a power-off command to the power supply module via the power management bus, the method further includes:

[0010] Send an alarm log for the leakage fault to notify the user of the leakage fault information;

[0011] After receiving the return value returned by the power supply module according to the power shutdown command, the method further includes:

[0012] If the returned value does not match the pre-stored returned value, the alarm log is sent again, along with an alarm message indicating that power cannot be cut off, to notify the user of the leakage fault and the inability to cut off the power.

[0013] Furthermore, after receiving the return value returned by the power supply module according to the power-off command, the method further includes:

[0014] If the returned value does not match the pre-stored returned value, the host of the liquid-cooled server is shut down, and the power-off command is resent to the power supply module via the power management bus.

[0015] Furthermore, there are multiple power supply modules, and the step of sending a power-off command to the power supply modules via the power management bus includes:

[0016] The status of each of the power supply modules is obtained;

[0017] When the power supply module is in operation, the power shutdown command is sent sequentially to multiple power supply modules through the power management bus in a preset order.

[0018] Furthermore, before sending the power-off command sequentially to the plurality of power supply modules via the power management bus in a preset order, the method further includes:

[0019] Detect the location of the liquid leak in the liquid-cooled server;

[0020] Based on the location of the leak, a number of target power supply modules that need to be shut down are determined from among the multiple power supply modules.

[0021] The step of sending the power-off command sequentially to multiple power supply modules via the power management bus in a preset order includes:

[0022] The preset sequence is determined based on the location of the leak.

[0023] The power-off command is sent sequentially to multiple target power supply modules via the power management bus in a preset order.

[0024] Another objective of this invention is to propose a liquid-cooled server leakage protection method to address the problem that the power supply to the liquid-cooled server is not completely cut off when it is turned off, and users may directly turn the server on when it is turned off, without solving the leakage problem, which leads to a high risk of server damage.

[0025] To achieve the above objectives, the technical solution of the present invention is implemented as follows:

[0026] A method for protecting a liquid-cooled server from leakage, applied to a power supply module, includes:

[0027] Receive power-off commands sent by the BMC via the power management bus;

[0028] In response to the received power-off command, a corresponding return value is returned to the BMC via the power management bus;

[0029] Based on the power-off command, the power supply on the control output side is disconnected to stop the current output.

[0030] The liquid cooling server leakage protection method described above has the same advantages over the prior art as the liquid cooling server protection method described above, and will not be repeated here.

[0031] Another objective of this invention is to provide a liquid-cooled server leakage protection device to address the problem that the power supply to the liquid-cooled server is not completely cut off when it is turned off, and users may turn the server on directly when it is turned off, without solving the leakage problem, which leads to a high risk of server damage.

[0032] To achieve the above objectives, the technical solution of the present invention is implemented as follows:

[0033] A liquid-cooled server protection device, applied to BMC, includes:

[0034] A detection module is used to detect leakage faults in the liquid-cooled server;

[0035] The signal output module is used to send a power-off command to the power supply module via the power management bus when a liquid leakage fault of the liquid-cooled server is detected, so that the power supply module stops outputting current.

[0036] A signal receiving module is used to receive the return value returned by the power supply module according to the power off command;

[0037] The matching module is used to match the return value with the pre-stored return value;

[0038] The confirmation module is used to confirm that the power-off command was executed normally when the return value matches the pre-stored return value.

[0039] The liquid cooling server leakage protection device and the liquid cooling server leakage protection method described above have the same advantages over the prior art, and will not be elaborated here.

[0040] Another objective of this invention is to provide a liquid-cooled server leakage protection device to address the problem that the power supply to the liquid-cooled server is not completely cut off when it is turned off, and users may turn the server on directly when it is turned off, without solving the leakage problem, which leads to a high risk of server damage.

[0041] To achieve the above objectives, the technical solution of the present invention is implemented as follows:

[0042] A liquid-cooled server protection device, applied to a power supply module, comprising:

[0043] The signal receiving module is used to receive power-off commands sent by the BMC via the power management bus;

[0044] The signal output module is used to respond to the received power-off command by returning a corresponding return value to the BMC via the power management bus;

[0045] The control module is used to control the output-side power supply to disconnect based on the power-off command, so as to stop the current output.

[0046] The liquid cooling server leakage protection device and the liquid cooling server leakage protection method described above have the same advantages over the prior art, and will not be elaborated here.

[0047] Another objective of this invention is to provide an electronic device to address the problem that liquid-cooled servers are not completely powered off when shut down, and users may turn the server on directly when it is off, while the liquid leakage problem remains unresolved, leading to a high risk of server damage.

[0048] To achieve the above objectives, the technical solution of the present invention is implemented as follows:

[0049] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executed, implements the steps in the liquid-cooled server leakage protection method described above.

[0050] The electronic device described above has the same advantages over the prior art as the liquid-cooled server leakage protection method, and will not be elaborated here.

[0051] Another objective of this invention is to provide a computer-readable storage medium to address the problem that liquid-cooled servers are powered off but not completely disconnected, and users may turn the server on directly when it is powered off, while the liquid leakage problem remains unresolved, leading to a high risk of server damage.

[0052] To achieve the above objectives, the technical solution of the present invention is implemented as follows:

[0053] A computer-readable storage medium storing a computer program that performs the above-described liquid-cooled server leakage protection method.

[0054] Compared with existing technologies, the liquid-cooled server leakage protection method of the present invention has the following advantages:

[0055] This invention, upon detecting a liquid-cooled server leakage, sends a power-off command to the power supply module via the power management bus, causing the power supply module to stop current output. It then receives a return value from the power supply module based on the power-off command. If the return value matches a pre-stored return value, the power-off command is confirmed to have been executed correctly. This invention, by sending a power-off command to the power supply module via the power management bus upon detecting a liquid-cooled server leak, directly cuts off the power output, thus shutting down the server. This avoids the risk of server damage due to continued power input from an un-disabled BMC (Body Control Module). Furthermore, since shutting down the server via the power supply module requires the user to disconnect and reconnect the AC power, it reduces the risk of user forgetting about the leakage and directly powering on the server, potentially causing damage. Attached Figure Description

[0056] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings:

[0057] Figure 1 The following is a flowchart illustrating the steps of a liquid-cooled server leakage protection method according to Embodiment 1 of the present invention;

[0058] Figure 2 A flowchart illustrating the steps of a liquid-cooled server leakage protection method according to Embodiment 2 of the present invention is shown.

[0059] Figure 3 A flowchart illustrating the steps of a liquid-cooled server leakage protection method according to Embodiment 3 of the present invention is shown.

[0060] Figure 4 A flowchart illustrating the steps of a liquid-cooled server leakage protection method according to another embodiment of the present invention is shown.

[0061] Figure 5 A schematic diagram of a liquid-cooled server leakage protection device according to Embodiment 4 of the present invention is shown;

[0062] Figure 6 A schematic diagram of a liquid-cooled server leakage protection device according to Embodiment 5 of the present invention is shown. Detailed Implementation

[0063] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other.

[0064] In related technologies, when a liquid-cooled server experiences a leakage fault, the host is typically shut down directly via the BMC (Body Control Center) to stop the liquid-cooled server from operating, or the BMC uses a CPLD (Continuous Power Controller) to shut down the motherboard power to prevent damage. However, directly shutting down via the BMC cannot shut down the motherboard power, which still draws a small current. Furthermore, the BMC cannot shut down its own power, thus the liquid-cooled server remains at risk of damage. Using a CPLD to shut down the motherboard power, if the user forgets about the fault and fails to repair it, the liquid-cooled server may be powered on directly, potentially causing further damage.

[0065] In view of this, the applicant provides a method, device, equipment and storage medium for liquid cooling server leakage protection to solve the problem that the motherboard power cannot be turned off when shutting down via BMC and there is a risk of damage to the liquid cooling server caused by the user accidentally turning it on.

[0066] The present invention provides a method, apparatus, device, and storage medium for protecting a liquid-cooled server from leakage, which will be described in detail below with reference to the accompanying drawings and embodiments.

[0067] Example 1

[0068] Reference Figure 1 , Figure 1 This diagram illustrates a step flowchart of a liquid-cooled server leakage protection method according to an embodiment of the present invention. The liquid-cooled server leakage protection method of this embodiment is applied to a BMC (Body Controlled Module), such as... Figure 1 As shown, it includes:

[0069] S101, if a liquid leakage fault is detected in the liquid-cooled server, a power-off command is sent to the power supply module via the power management bus to stop the power supply module from outputting current.

[0070] In this embodiment, the BMC performs a leak monitoring task and automatically handles leak faults to reduce the risk of damage to the liquid-cooled server. The automatic handling involves shutting down the liquid-cooled server's power supply. It's important to understand that shutting down the power supply is not the same as simply shutting down the computer. Shutting down only shuts down the liquid-cooled server host; shutting down the host does not stop the BMC from operating. The BMC continues to run normally, and therefore, even when shutting down, the liquid-cooled server still faces the risk of damage due to a short circuit caused by leaks. In this embodiment, shutting down the power supply means cutting off the current output. With no current output, the entire liquid-cooled server is in a stopped state, and no current flows through it, preventing short circuits. Therefore, compared to simply shutting down the liquid-cooled server, shutting down the power supply is more effective in preventing damage from short circuits. Thus, this embodiment handles leak faults by shutting down the power supply.

[0071] Specifically, since the BMC and PSU (Power Supply Unit) have a communication link based on PMBus (Power Management Bus), which is used by the BMC to collect information from the PSU, such as its operating status, the BMC is configured to communicate with the PSU through PMBus, enabling the PSU to execute the BMC's commands. Thus, when the BMC sends a power-off command to the PSU through PMBus, the PSU will cut off the power on the output side, meaning the BMC can control the PSU to completely shut down the liquid-cooled server power.

[0072] By shutting down the power supply via the PSU, the PSU saves its registers upon receiving the power-off command. In this state, power can only be restored by disconnecting and then reconnecting the AC power, after which the user can turn on the server. This prevents users from accidentally turning on the server before the liquid-cooled server has been repaired, and also avoids the risk of accidental power-on damaging the liquid-cooled server. Furthermore, because the server power is cut off via the PSU, the entire server is without power, preventing situations where the motherboard remains powered even when the server is shut down via the BMC, thus avoiding damage to the motherboard from liquid leakage and ensuring higher safety.

[0073] Furthermore, sending a power-off command to the PSU via PMBus does not require additional hardware, thus achieving a complete power cut-off for the liquid-cooled server without the need for additional hardware.

[0074] S102, receive the return value returned by the power supply module according to the power shutdown command.

[0075] In this embodiment of the invention, since the BMC also stops operating after the power is completely turned off, it is necessary to confirm that the PSU can execute commands normally before execution to ensure that the PSU can execute commands normally. Specifically, to facilitate confirmation that the PSU has successfully executed the command to shut down the power, the BMC also needs to receive the return value returned by the PSU and use the return value to confirm whether the power shutdown command has been executed. In some embodiments, this can be a returned command response information, indicating that the PSU has successfully executed the power shutdown command. Alternatively, a predetermined return value can be used, and when the return value is the predetermined value (i.e., a correct return value), it is confirmed that the PSU has successfully executed the power shutdown command. In other embodiments, the PSU can return a corresponding return value while controlling its own relay to disconnect, indicating that the power shutdown command has been executed normally.

[0076] S103, when the return value matches the pre-stored return value, confirm that the power-off command was executed normally.

[0077] Specifically, by matching the received return value with a pre-stored return value, a match indicates that the power-off command was executed correctly. If the received return value does not match the pre-stored value, or if it does not match at all, it indicates that the power-off command was not executed correctly, and the power cannot be shut down properly. In this case, the host should be shut down first, or the administrator should be contacted to reduce damage caused by leakage. For example, if a return value of "1" is received and confirmed to be equal to the pre-stored return value, it means that the PSU successfully executed the shutdown command, completely powering down the liquid-cooled server. If a return value of "0" is received or no return value is received, it means that the PSU could not execute the corresponding command or the PSU did not receive the command. In this case, the BMC can control the server shutdown to reduce the risk of damage, and then notify the user to manually shut down the power. Because the return value confirms whether the PSU executed the power-off command correctly, the BMC can monitor the power-off process, promptly detect and handle situations where the power cannot be shut down, and avoid the risk of server damage due to leakage caused by the inability to shut down the power.

[0078] This invention employs a BMC (Brain Control Center) that sends control commands to the PSU (Power Supply Unit) via PMBus to shut down the power. The return value from the PSU confirms whether the power-down command was executed correctly. Since the PSU's output power is cut off, the liquid-cooled server is completely powered off. In this situation, the liquid-cooled server requires AC power to be disconnected and then re-energized before it can be powered on. This reduces the risk of damage caused by users turning on the liquid-cooled server before the leakage fault is repaired. Furthermore, completely cutting off the liquid-cooled server's power supply via the PSU is more thorough than simply shutting it down, preventing damage caused by the motherboard still receiving power after shutdown, further reducing the safety risks associated with leakage. In addition, the communication link established between the BMC and PSU via PMBus allows the BMC to directly control the PSU to cut off the power output without adding any hardware devices, eliminating the need to modify the server or PSU structure, making operation more convenient.

[0079] Example 2

[0080] Reference Figure 2 , Figure 2 This invention illustrates a flowchart of a liquid-cooled server leakage protection method according to an embodiment of the present invention. The method is applied to a power supply module, such as... Figure 2 As shown, it includes:

[0081] S201 receives the power-off command sent by the BMC via the power management bus.

[0082] Since the PMBus communication link is used by the BMC to collect relevant information from the PSU, no module is set up for the PSU to execute BMC commands. Therefore, in practical implementation, a separate command receiving module can be set up in the PSU to receive the power-off command sent by the BMC through the PMBus. A control module can then communicate with the command receiving module, enabling the PSU to cut off the output power supply based on the BMC's command. Thus, by communicating with the BMC through the PMBus, the PSU can accurately execute the power-off command received by the BMC through the PMBus in the event of a leak.

[0083] S202, in response to the received power-off command, return a corresponding return value to the BMC via the power management bus.

[0084] Specifically, since the PSU directly cuts off the output power after executing the command, thus completely shutting down the liquid-cooled server, the BMC cannot confirm whether the power-off command was executed correctly. Therefore, when the PSU receives the power-off command, it can determine whether it can execute the command. If it can, it returns the corresponding return value. For example, it returns "1" when it confirms that it can execute the power-off command, and "0" when it confirms that it cannot execute the power-off command. The specific return value setting can be set by the user or by the system itself. The PSU's confirmation of its ability to execute the command can be whether it can control the relay normally or whether the relay is working properly. For example, it can detect whether the current can be disconnected normally or whether the relay can be engaged or disengaged normally. The specific determination can be based on the actual situation, and this invention does not impose any specific limitations.

[0085] In some embodiments, the PSU may return a corresponding return value via PMBus while simultaneously cutting off its own relay according to the power-off command, so that the BMC can confirm that the PSU has executed the power-off command normally before the power is turned off.

[0086] S203, based on the power-off command, controls the output-side power supply to disconnect, so as to stop the current output.

[0087] Specifically, upon receiving a power-off command, the PSU controls its internal relay to disconnect the output power and enters the off state. Because the PSU saves its registers after receiving the power-off command before entering the off state, the user cannot directly turn on the power to start the liquid-cooled server. Instead, an AC power-off and power-on operation is required. Therefore, after the PSU is turned off, if the user wants to turn on the liquid-cooled server, they must first perform an AC power-off and power-on operation, preventing accidental power-on due to an unresolved liquid leakage fault.

[0088] In this embodiment of the invention, after receiving a power-off command from the BMC, the PSU sends a return value corresponding to the power-off command to the BMC, and finally shuts down the power based on the power-off command. This is achieved by controlling its internal relay to disconnect the output power, thus completely cutting off the power to the liquid-cooled server. By cutting off the PSU's output power, users are required to perform an AC power-off and power-on operation before turning on the liquid-cooled server, reducing the risk of damage caused by turning on the liquid-cooled server before the leakage fault is repaired. Furthermore, after the PSU cuts off the power, the entire liquid-cooled server is without power, avoiding the situation where the liquid-cooled server is powered off but the motherboard or BMC still has power, which could still cause damage. In addition, since the PSU and BMC communicate via PMBus, the BMC can directly control the PSU to cut off the power without adding any hardware.

[0089] Example 3

[0090] Reference Figure 3 , Figure 3 This diagram illustrates a step flowchart of a liquid-cooled server leakage protection method according to an embodiment of the present invention. The liquid-cooled server leakage protection method of this embodiment is applied to a BMC (Body Controlled Module), such as... Figure 3 As shown, it includes:

[0091] S301, if a liquid cooling server leakage fault is detected, an alarm log for the leakage fault is sent to notify the user of the leakage fault information.

[0092] In this embodiment of the invention, in order to inform the user of the liquid cooling server's leakage status for easy maintenance, the BMC records an alarm log when it detects a leakage fault and sends the alarm log to the remote backend to notify the user of the liquid cooling server's leakage status so that the user can carry out timely maintenance.

[0093] S302, obtain the status of each of the power supply modules.

[0094] In this embodiment of the invention, the liquid-cooled server is powered by multiple power supply units (PSUs). To shut down all power supply modules, a power-off command needs to be sent to the running PSUs. It's understood that the operation of the liquid-cooled server does not necessarily mean that all PSUs are running. Conventional liquid-cooled servers usually have backup PSUs. Therefore, before sending the command, it is necessary to obtain the PSU status to confirm which PSUs are running. Since the BMC itself collects PSU information, the running PSUs can be directly identified by accessing the PSU information stored within the BMC. In some embodiments, to confirm the real-time status of the PSUs, the PSU status can also be collected only when a leakage fault is detected, thus confirming the running PSUs.

[0095] S303, when the power supply module is in operation, the power shutdown command is sent sequentially to multiple power supply modules through the power management bus in a preset order.

[0096] In this embodiment of the invention, since each PSU has a corresponding slave address, the BMC needs to send power-off commands to the PSUs individually and sequentially. For example, when it is confirmed that PSUs with power sequence numbers 1, 2, and 3 are all running, the power-off command is sent to each PSU via the PMBus in ascending order of power sequence number; that is, the power-off command is sent to PSU 1 first, then PSU 2, and finally PSU 3. Alternatively, the power-off command can be sent to each running PSU in descending order of power sequence number. If PSUs with power sequence numbers 1 and 3 are detected to be running while PSU 2 is not running, the power-off command is only sent to the running PSUs 1 and 3. The power sequence number can be preset by the user or set by the liquid cooling server itself; this invention does not impose any specific limitations.

[0097] In some embodiments, since different motherboards in a liquid-cooled server may be powered by different PSUs (Power Supply Units), such as the CPU board and GPU board each using a separate PSU, the location of the liquid leak can be detected. The PSU shutdown order can be determined based on the leak location: first, the PSU corresponding to the motherboard closest to the leak location is shut down, then the PSUs corresponding to other motherboards are shut down. For example, if the leak is near the CPU board, the PSU corresponding to the CPU board is shut down, and then the corresponding PSUs of other motherboards are shut down. Therefore, by determining the PSU shutdown order based on the leak location, the PSUs closest to the leak location are shut down first to prevent the risk of short circuits, and then the liquid-cooled server power is shut down, reducing the risk of damage to the liquid-cooled server and thus improving the safety of leak protection.

[0098] In other embodiments, when leakage is detected, only the power supply of the motherboard corresponding to the leakage location can be turned off. For example, if leakage is detected at the CPU board location without affecting other motherboards, only the CPU motherboard power supply, i.e., the PSU corresponding to the CPU motherboard, can be turned off. In this way, the operation of other motherboards will not be affected while ensuring the safety of the liquid-cooled server.

[0099] S304, Receive the return value returned by the power supply module according to the power shutdown command.

[0100] Specifically, after receiving the return value from the PSU according to the power-off command, the BMC matches the return value with the pre-stored return value. If the received return value matches the pre-stored return value, step S305 is executed; otherwise, step S306 is executed. If no return value is received, the power-off command can be sent to the PSU again. If no return value is received for the second command or the return value does not match, step S306 is also executed.

[0101] S305, when the return value matches the pre-stored return value, confirm that the power-off command was executed normally.

[0102] In this embodiment of the invention, if it is confirmed that the return value returned by the PSU through the PMBus matches the return value of the corresponding instruction pre-stored by the BMC, the BMC confirms that the PSU has executed the power shutdown instruction normally, which can completely cut off the power supply to the liquid-cooled server.

[0103] S306, when the returned value does not match the pre-stored returned value, the alarm log is sent again and an alarm message indicating that power cannot be cut off is sent to notify the user of the leakage fault and that power cannot be cut off.

[0104] In this embodiment of the invention, if the returned value does not match the pre-stored returned value, it indicates that the power supply to the liquid-cooled server cannot be completely shut off via the PSU, and therefore, leakage protection for the liquid-cooled server cannot be provided. Thus, to promptly notify the user of the PSU damage and the liquid-cooled server leakage, a leakage fault alarm log is sent again, along with a warning message indicating that power cannot be cut off. Since each PSU carries a power supply serial number, the faulty PSU's serial number can be clearly identified in the alarm message to facilitate user repair. If the user does not manually cut off the power, the alarm message can be repeatedly sent to remind the user to cut off the power in time to prevent damage to the liquid-cooled server, until the user manually disconnects the power supply to the liquid-cooled server.

[0105] In some embodiments, in order to reduce the risk of damage to the liquid-cooled server, if it is confirmed that the power cannot be cut off by the PSU, the BMC first controls the liquid-cooled server to shut down. After reducing the risk of motherboard damage by shutting down, the BMC sends an alarm log and a PSU damage warning message to the user. Then, the user determines whether it is necessary to completely cut off the power supply to the liquid-cooled server based on the alarm log.

[0106] In other embodiments, since the BMC is still running after the power is off, the PSU can be shut down again after the liquid-cooled server is shut down. That is, the power-off command is sent to the PMBus again to try to shut down the power, so as to avoid the situation where the power-off command is not sent to the PSU.

[0107] In this embodiment of the invention, after the BMC detects a running PSU, the PMBus sends control commands to the running PSU according to the leakage sequence, controlling the PSU to shut down its power. The return value from the PSU determines whether the power shutdown command was executed correctly. Because this embodiment directly cuts off the output power of the PSU, the server needs to be powered off and then powered on again before it can be turned on. This reduces the risk of damage caused by the user turning on the server when the leakage fault is not yet repaired. Furthermore, cutting off the power supply according to the leakage sequence prevents short circuits near the leakage site, reducing the risk of damage to the liquid-cooled server. At the same time, completely cutting off the power supply to the liquid-cooled server through the PSU is more thorough than simply shutting down the liquid-cooled server, avoiding damage caused by the motherboard still receiving power after shutdown, further reducing the safety risks associated with leakage.

[0108] Furthermore, the communication link established between the BMC and PSU via PMBus allows the BMC to directly control the PSU to cut off power output without adding any hardware, eliminating the need to modify the liquid-cooled server structure or the PSU structure. This embodiment of the invention also confirms whether the power-off command was executed correctly based on the return value returned by the PSU. If the PSU fails to execute the power-off command correctly, the liquid-cooled server is powered off by shutting down or notifying the user to cut off the power supply, further improving the safety of the liquid-cooled server's leakage protection.

[0109] Reference Figure 4 , Figure 4 This diagram illustrates a step flowchart of a liquid-cooled server leakage protection method according to another embodiment of the present invention. The method is applied to a BMC (Body Controlled Module). Figure 4 As shown, it includes:

[0110] S401, if a liquid cooling server leakage fault is detected, an alarm log for the leakage fault is sent to notify the user of the leakage fault information.

[0111] The main functions of sending leakage fault alarm logs are twofold: first, to save alarm logs to record specific information about the leakage for easy maintenance; and second, to alert users that the liquid-cooled server is at risk of damage due to leakage. However, simply sending alarm logs to users may result in the liquid-cooled server not being powered off in time. Therefore, after sending alarm information, the BMC can also take corresponding measures to further reduce the risk of damage to the liquid-cooled server. In this embodiment of the invention, the BMC cuts off the power supply to the liquid-cooled server, completely de-energizing it and thus reducing the risk of damage.

[0112] S402 detects the location and extent of leakage in the liquid-cooled server, as well as the status of the power supply module.

[0113] In this embodiment of the invention, detecting the specific location and extent of leakage in the liquid-cooled server can determine the specific impact of the leakage fault. The leakage extent can be represented by the amount of leakage detected. When the leakage amount is within a certain threshold, it indicates a low leakage extent, minimal impact on the liquid-cooled server, and a low risk of damage. Conversely, if the leakage amount exceeds the threshold, it indicates a high leakage extent, significant impact on the liquid-cooled server, and a high risk of damage. Therefore, appropriate measures can be taken to automatically handle leakage faults under different leakage extent conditions. In specific implementation, a dedicated leakage detection line can be set up to detect the leakage amount, and then the BMC (Brain Controller) can determine the extent of the leakage. For example, the BMC can store a leakage amount threshold. When the leakage amount detected by the leakage detection line is greater than the threshold, it indicates a greater leakage extent; when the leakage amount detected by the leakage detection line is less than the threshold, it indicates a lesser leakage extent.

[0114] In the event of significant leakage, S403 sends power-off commands sequentially to the running power supply modules via the power management bus in a preset order.

[0115] Specifically, if the BMC detects a significant leakage, indicating a high risk of damage to the liquid-cooled server, it is determined that the power supply to the entire liquid-cooled server needs to be cut off. Therefore, after identifying the operating PSU, the BMC sends a power-off command to the operating PSU via the PMBus in a preset sequence, causing the PSU to cut off the power supply on the output side, thereby cutting off the power supply to the entire liquid-cooled server and reducing the risk of damage to the liquid-cooled server.

[0116] S404: In cases of minor leakage, a power-off command is sent to the power supply module corresponding to the leakage location.

[0117] Specifically, if the BMC detects a small degree of leakage, indicating a low risk of damage to the liquid-cooled server, it determines that only the power supply to the motherboard at the leakage location needs to be cut off. In this case, it sends a power-off command only to the PSU corresponding to that motherboard to shut down the power supply to that motherboard, thereby reducing the risk of damage to the liquid-cooled server while avoiding affecting the normal operation of other motherboards in the liquid-cooled server.

[0118] S405, receive the return value returned by the power supply module according to the power shutdown command.

[0119] The BMC receives the return value from the PSU to match it with the pre-stored return value corresponding to the power-off command, thereby confirming whether the PSU has executed the power-off command normally. This monitors the normal execution of the command and, if the PSU fails to execute the power-off command normally, executes a solution, such as shutting down the liquid-cooled server.

[0120] S406, when the return value matches the pre-stored return value, confirm that the power-off command was executed normally.

[0121] In this embodiment of the invention, if the BMC determines that the PSU cannot shut down normally, in order to reduce the risk of damage to the liquid-cooled server, it can send an alarm log to the user again and simultaneously send a warning message that the PSU cannot be shut down. Specifically, if the BMC detects a significant leakage, it will also add an alarm message about a significant leakage to the alarm log to remind the user that the liquid-cooled server is at high risk of damage and should be powered off immediately. In some embodiments, when the BMC determines that the PSU cannot shut down normally, it can first control the liquid-cooled server to shut down, and then repeat the power-off command to confirm whether the PSU is still not working properly. If it still cannot work properly, an alarm message will be sent to the user to remind the user that the PSU is abnormally unable to shut down the power. Alternatively, the alarm log can be sent to the user again only when the leakage is significant; if the leakage is minor, the BMC will only shut down the liquid-cooled server.

[0122] This invention utilizes a BMC (Brain Control Center) to detect the location and extent of a liquid-cooled server leak, thereby determining the risk of damage. When the risk is high, the entire liquid-cooled server is completely powered off; when the risk is low, only the motherboard corresponding to the leak location is powered off. By employing different measures for different levels of leakage, the safety of the liquid-cooled server is improved, and the impact on the normally functioning motherboard is avoided. Furthermore, by cutting off the server's power supply via the PSU (Power Supply Unit), the server requires AC power to be disconnected and then re-energized before it can be powered on. This reduces the risk of damage caused by users turning on the server while the leak is still present. Moreover, completely cutting off the power supply via the PSU is more thorough than simply shutting down the liquid-cooled server, preventing damage caused by the motherboard still receiving power after shutdown, further reducing the safety risks associated with leaks.

[0123] Furthermore, the communication link established between the BMC and PSU via PMBus allows the BMC to directly control the PSU to cut off power output without adding any hardware, eliminating the need to modify the liquid-cooled server structure or the PSU structure. This embodiment of the invention also verifies whether the PSU has correctly executed the power shutdown command by checking the PSU's return value. If the PSU fails to execute the power shutdown command correctly, the liquid-cooled server is powered off by shutting down or notifying the user to cut off the power supply, further improving the safety of the liquid-cooled server's leakage protection.

[0124] Example 4

[0125] Reference Figure 5, Figure 5 This diagram illustrates a liquid-cooled server leakage protection device according to an embodiment of the present invention. The liquid-cooled server leakage protection device of this embodiment is applied to a BMC (Body Controlled Module), such as... Figure 5 As shown, it includes:

[0126] The detection module 501 is used to detect leakage faults in liquid-cooled servers.

[0127] Signal output module 502 is used to send a power-off command to the power supply module via the power management bus so that the power supply module stops outputting current.

[0128] The signal receiving module 503 is used to receive the return value returned by the power supply module according to the power off command;

[0129] Matching module 504 is used to confirm that the power-off command is executed normally when the return value matches the pre-stored return value;

[0130] The confirmation module 505 is used to confirm that the power-off command was executed normally when the return value matches the pre-stored return value.

[0131] In some feasible embodiments, the apparatus further includes:

[0132] The forwarding module is used to send the alarm log of the leakage fault to notify the user of the leakage fault information;

[0133] The forwarding module also includes:

[0134] The forwarding submodule is used to resend the alarm log and send an alarm message indicating that power cannot be cut off when the returned value does not match the pre-stored return value, so as to notify the user of the leakage fault and that power cannot be cut off.

[0135] In some feasible embodiments, the apparatus further includes:

[0136] The control module is used to shut down the host of the liquid-cooled server when the return value does not match the pre-stored return value.

[0137] In some feasible embodiments, the apparatus further includes:

[0138] The acquisition module is used to acquire the status of the multiple power supply modules respectively.

[0139] In some feasible embodiments, the detection module 501 further includes:

[0140] The detection submodule is used to detect the location of leakage in the liquid-cooled server.

[0141] Example 5

[0142] Reference Figure 6 , Figure 6 This diagram illustrates a liquid-cooled server leakage protection device according to an embodiment of the present invention. The liquid-cooled server leakage protection device of this embodiment is applied to a power supply module, such as... Figure 6 As shown, it includes:

[0143] The signal receiving module 601 is used to receive the power-off command sent by the BMC through the power management bus;

[0144] The signal output module 602 is used to respond to the received power-off command by returning a corresponding return value to the BMC via the power management bus;

[0145] The control module 603 is used to control the output power supply to disconnect based on the power-off command, so as to stop the current output.

[0146] This invention also provides an electronic device, which may include a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is the liquid-cooled server leakage protection method described in any of the above embodiments.

[0147] This invention also provides a computer-readable storage medium, wherein when the instructions in the storage medium are executed by a processor, the processor is able to perform the operations performed by the liquid-cooled server leakage protection method described in any of the above embodiments.

[0148] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, embodiments of the present invention can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of the present invention can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0149] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0150] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0151] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0152] Although preferred embodiments of the present invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present invention.

[0153] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0154] The present invention provides a detailed description of a liquid-cooled server leakage protection method, apparatus, device, and storage medium. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for protecting a liquid-cooled server from leakage, characterized in that, Applied to BMC, the method includes: In the event of a leak in the liquid-cooled server, a power-off command is sent to the power supply module via the power management bus to stop the power supply module from outputting current, save the registers, and then switch to the shutdown state. Receive the return value returned by the power supply module according to the power shutdown command; When the return value matches the pre-stored return value, it is confirmed that the power-off command was executed normally; When the returned value does not match the pre-stored returned value, an alarm log is sent and an alarm message indicating that power cannot be cut off is sent to notify the user of the leakage fault and that power cannot be cut off; wherein, the alarm message includes the power supply serial number of the damaged power supply module.

2. The method for protecting a liquid-cooled server from leakage according to claim 1, characterized in that, Before sending a power-off command to the power supply module via the power management bus, the method further includes: Send an alarm log for the leakage fault to notify the user of the leakage fault information.

3. The method for protecting a liquid-cooled server from leakage according to claim 2, characterized in that, After receiving the return value returned by the power supply module according to the power shutdown command, the method further includes: If the returned value does not match the pre-stored returned value, the host of the liquid-cooled server is shut down, and the power-off command is resent to the power supply module via the power management bus.

4. The method for protecting a liquid-cooled server from leakage according to claim 1, characterized in that, The power supply module has multiple components, and the step of sending a power-off command to the power supply module via the power management bus includes: The status of each of the power supply modules is obtained; When the power supply module is in operation, the power shutdown command is sent sequentially to multiple power supply modules through the power management bus in a preset order.

5. The method for protecting a liquid-cooled server from leakage according to claim 4, characterized in that, Before sending the power-off command sequentially to the plurality of power supply modules via the power management bus in a preset order, the method further includes: Detect the location of the liquid leak in the liquid-cooled server; Based on the location of the leak, a number of target power supply modules that need to be shut down are determined from among the multiple power supply modules. The step of sending the power-off command sequentially to multiple power supply modules via the power management bus in a preset order includes: The preset sequence is determined based on the location of the leak. The power-off command is sent sequentially to multiple target power supply modules via the power management bus in a preset order.

6. A method for protecting a liquid-cooled server from leakage, characterized in that, Applied to a power supply module, the method includes: Receive power-off commands sent by the BMC via the power management bus; In response to the received power-off command, a corresponding return value is returned to the BMC via the power management bus, so that the BMC can confirm that the power-off command was executed normally when the return value matches the pre-stored return value; when the return value does not match the pre-stored return value, an alarm log is sent and an alarm message indicating that power cannot be cut off is sent to notify the user of a liquid leakage fault and that power cannot be cut off; wherein, the alarm message includes the power supply serial number of the damaged power supply module; Based on the power-off command, the power supply on the control output side is disconnected to stop the current output, the register is saved, and then the system returns to the off state.

7. A liquid-cooled server leakage protection device, characterized in that, Applied to BMC, the device includes: A detection module is used to detect leakage faults in the liquid-cooled server; The signal output module is used to send a power-off command to the power supply module via the power management bus when a liquid leakage fault of the liquid-cooled server is detected, so that the power supply module stops current output, saves the register, and then enters the shutdown state. A signal receiving module is used to receive the return value returned by the power supply module according to the power off command; The matching module is used to match the return value with the pre-stored return value; The confirmation module is used to confirm that the power-off command was executed normally when the return value matches the pre-stored return value; when the return value does not match the pre-stored return value, it sends an alarm log and an alarm message indicating that the power cannot be cut off, to notify the user of the liquid leakage fault and the inability to cut off the power; wherein, the alarm message includes the power supply serial number of the damaged power supply module.

8. A liquid-cooled server leakage protection device, characterized in that, The device, applied to a power supply module, includes: The signal receiving module is used to receive power-off commands sent by the BMC via the power management bus; The signal output module is used to respond to the received power-off command by returning a corresponding return value to the BMC via the power management bus, so that the BMC can confirm that the power-off command was executed normally when the return value matches the pre-stored return value; when the return value does not match the pre-stored return value, it sends an alarm log and an alarm message indicating that power cannot be cut off, to notify the user of a liquid leakage fault and that power cannot be cut off; wherein, the alarm message includes the power supply serial number of the damaged power supply module; The control module is used to control the output power to disconnect based on the power-off command, so as to stop the current output, save the register, and then switch to the shutdown state.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes, it implements the steps of the liquid cooling server leakage protection method as described in any one of claims 1-5 or the liquid cooling server leakage protection method as described in claim 6.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that performs the liquid cooling server leakage protection method according to any one of claims 1-5 or the liquid cooling server leakage protection method according to claim 6.

Images