CN116701098A

CN116701098A - Liquid leakage detection method, server and computing equipment

Info

Publication number: CN116701098A
Application number: CN202211125459.5A
Authority: CN
Inventors: 王彦斌; 童建利; 任海
Original assignee: XFusion Digital Technologies Co Ltd
Current assignee: Henan Kunlun Technology Co ltd
Priority date: 2022-09-15
Filing date: 2022-09-15
Publication date: 2023-09-05

Abstract

The embodiment of the application provides a liquid leakage detection method, a server and computing equipment. The liquid leakage detection method is applied to a liquid cooling heat dissipation server, wherein the server comprises a plurality of electronic devices, and the method comprises the following steps: monitoring a plurality of first signals of the server, wherein the first signals are operation signals of corresponding electronic devices; if the liquid cooling component of the server leaks to the electronic device, the first signal corresponding to the electronic device is abnormal, and alarm information is reported. The liquid leakage detection method can realize full coverage of detection positions without depending on a special detection circuit, has a wide detection range, and ensures the accuracy and timeliness of liquid leakage detection.

Description

Liquid leakage detection method, server and computing equipment

Technical Field

The embodiment of the application relates to the technical field of electronics, in particular to a liquid leakage detection method, a server and computing equipment.

Background

With the development of networks, the data volume processing requirements are larger and larger, the performance requirements of servers are higher and higher, and the servers can generate a large amount of heat during working and need to dissipate heat. At present, a liquid cooling radiator can be arranged inside a server, the liquid cooling radiator is connected with a refrigerating device and a pump, the pump enables liquid to flow in the liquid cooling radiator, heat emitted by a heating element inside the server is conducted to flowing liquid, and the liquid is radiated through the refrigerating device, so that the heat radiation of the heating element by the radiating device is realized.

Liquid-cooled heat sinks may be at risk of leakage, which once it can cause short circuits inside the server, resulting in device damage. Therefore, it is necessary to monitor the liquid-cooled radiator for leakage. How to effectively detect the liquid leakage of the liquid cooling radiator is a technical problem to be solved.

Disclosure of Invention

The embodiment of the application provides a liquid leakage detection method, a server and computing equipment. The liquid leakage detection method in the embodiment of the application can realize detection without depending on a special detection circuit, has wide detection range and ensures the accuracy and timeliness of liquid leakage detection.

In a first aspect, an embodiment of the present application provides a method for detecting leakage. The liquid leakage detection method is applied to a liquid cooling heat dissipation server, wherein the server comprises a plurality of electronic devices, and the method comprises the following steps:

monitoring a plurality of first signals of the server, wherein the first signals are operation signals of corresponding electronic devices;

if the liquid cooling component of the server leaks to the electronic device, the first signal corresponding to the electronic device is abnormal, and alarm information is reported.

In this embodiment, whether the liquid cooling component of the server leaks is determined by monitoring whether the plurality of first signals are abnormal. The method can realize detection without depending on a special detection circuit, has wider detection range, and ensures the accuracy and timeliness of liquid leakage detection.

In addition, when monitoring that a certain first signal is abnormal, the electronic device corresponding to the first signal can determine which position of the liquid cooling assembly is leaked, compared with the situation that whether the liquid is leaked or not can only be detected by the water intrusion rope, the position of the liquid leakage cannot be determined, maintenance personnel can know the position of the liquid leakage according to reported alarm information, and the server is rapidly and effectively maintained.

In one possible implementation, the plurality of first signals of the server are monitored by a complex programmable logic device PCLD of the server. It can be understood that the operation signals of the electronic devices of the server are monitored by the CPLD, and the first signal is an abnormal operation signal which can occur when the first signal contacts with the cooling liquid, and compared with the monitoring of the first signal by other electronic devices, the monitoring of the first signal by the CPLD reduces the steps of the other electronic devices for acquiring the first signal from the CPLD, reduces the time delay of data transmission, and improves the monitoring efficiency and the monitoring timeliness. Of course, in other implementations, the plurality of first signals of the server may also be monitored by the FPGA or the BMC.

In one possible implementation manner, the plurality of electronic devices include a power supply unit, a motherboard, a board card, a hard disk, a memory, a central processing unit, and a fan, so as to ensure accuracy and timeliness of liquid leakage detection. Of course, in other implementations, the plurality of electronic devices includes at least two of a power supply unit, a motherboard, a board, a hard disk, a memory, a central processing unit, and a fan, and the number of monitoring the first signals is reduced on the basis of realizing the leakage detection.

In one possible implementation manner, the board card comprises a network card, a redundant array of independent disks RAID card, a power back plate and a hard disk back plate, so as to ensure the accuracy and timeliness of liquid leakage detection. Of course, in other implementations, the board card may include at least one of a network card, a redundant array of independent disks RAID card, a power backplane, or a hard disk backplane due to different configurations of different servers.

In one possible implementation, the first signal may include a circuit status signal, a power status signal, or a traffic status signal. It can be understood that the circuit state signal, the power state signal and the service state signal are all signals which are easy to generate abnormality when the electronic device encounters water, and the accuracy of liquid leakage detection can be improved by monitoring the signals.

In one possible implementation manner, the main board is provided with a plurality of first signals, and the plurality of first signals can be a circuit state signal of an overcurrent protection circuit of a CPU system of the main board, a circuit state signal of a fan overcurrent protection circuit of the main board, a circuit state signal of a USB interface overcurrent protection circuit of the main board, a signal of a CPU power supply, a signal of a memory power supply, a signal of a south bridge power supply and a temperature of the overcurrent protection circuit.

In one possible implementation manner, the first signals of the board, the hard disk, the memory and the CPU can be reset signals, and the accuracy of liquid leakage detection is ensured by detecting the reset signals of the board, the hard disk, the memory and the CPU.

In a possible implementation manner, the power supply unit may have a plurality of first information, and the plurality of first signals may be an input normal signal, an output normal signal and an in-place signal, and by monitoring all signals of the power supply unit, the detection range is ensured to be wide, and the accuracy of liquid leakage detection can be effectively improved.

In a possible implementation manner, the method further includes: the liquid cooling assembly of the server leaks liquid to the electronic device, and when a first signal corresponding to the electronic device is abnormal, the switch valve of the server is controlled to be closed, so that liquid is prevented from flowing into the liquid cooling pipe from the liquid inlet of the liquid cooling pipe, and further, the short circuit or damage of the electronic device in the server caused by the expansion of the liquid leakage area is avoided, and the fault diffusion is prevented.

In a possible implementation manner, when the first signal is abnormal, each electronic device such as the motherboard, the board card, the hard disk, the power supply unit and the like is also controlled to be powered down so as to avoid damage to the electronic device in the server.

In a possible implementation manner, the liquid cooling component of the server leaks liquid to the electronic device, and when the first signal corresponding to the electronic device is abnormal, the electronic device with the abnormal first signal is controlled to be powered down so as to play a role in fault isolation, and the electronic device with the abnormal first signal can continue to operate so as to avoid the service from being greatly influenced.

In a second aspect, an embodiment of the present application provides a server. The server comprises a controller, a liquid cooling assembly and a plurality of electronic devices, wherein the liquid cooling assembly dissipates heat for at least one electronic device, the controller is coupled with the plurality of electronic devices, and the controller is used for:

The server provided in this embodiment determines whether the liquid cooling component of the server leaks liquid by monitoring whether the plurality of first signals are abnormal. The detection can be realized without depending on a special detection circuit, the detection range is wider, and the accuracy and timeliness of liquid leakage detection are ensured.

In a possible implementation manner, the server further comprises a switch valve, the liquid cooling component comprises a liquid cooling pipe, the controller is electrically connected with the switch valve, and the controller is further used for controlling the switch valve to be closed when a first signal corresponding to the electronic device is abnormal if the liquid cooling component of the server leaks to the electronic device, so that liquid is prevented from flowing into the liquid cooling pipe from a liquid inlet of the liquid cooling pipe, and further short circuit or damage to the electronic device inside the server due to expansion of the area of the leaked liquid is avoided, and fault diffusion is prevented.

In a possible implementation manner, the server further comprises a power connector, wherein the power connector is used for externally connecting a power supply to supply power for the server, and the switch valve is electrically connected with the power connector.

It should be noted that, the bus connection of power connection and power supply is in order to supply power for the server, and the ooff valve is through the power connection power supply of being connected with the bus connection of power supply, compares in the ooff valve is through the inside other electronic device power supply of server, can not appear other electronic device damage and the condition of losing power, has guaranteed the power supply reliability of ooff valve, and the power-on time of ooff valve can be earlier than the other electronic device of server and power on, and then guarantees that the ooff valve is in time cut off when liquid cooling subassembly weeping, avoids the inside electronic device of server to send short circuit and damage.

In one possible implementation manner, when the controller or the switch valve is powered down, the switch valve is closed, so that the CPLD or the switch valve can be guaranteed to prevent cooling liquid from continuously flowing into the liquid cooling pipe when the CPLD or the switch valve cannot work, and the short circuit or damage of electronic devices in the server caused by the expansion of the liquid leakage area can be avoided, and the fault diffusion can be prevented.

In a possible implementation manner, the server further comprises a switch circuit, wherein the switch circuit is connected between the controller and the switch valve, and the switch circuit is arranged in the switch valve or the switch circuit is arranged outside the switch valve. It can be understood that the switch circuit is arranged inside the switch valve, compared with the switch circuit arranged outside the switch valve, the circuit is not required to be added on the main board, the cost can be effectively reduced, and the space of the main board can be saved.

In a third aspect, an embodiment of the present application provides a server. The server comprises a shell, an electronic component, a controller and a liquid cooling component; the electronic component comprises a plurality of electronic devices, wherein the electronic devices comprise a main board, a Central Processing Unit (CPU), a network card, a hard disk and a power supply unit, the CPU and the controller are all arranged on the main board and are electrically connected with the main board, the controller is coupled with the CPU, the network card, the hard disk and the power supply unit, the liquid cooling component dissipates heat for at least one of the CPU and the power supply unit, and the controller is used for monitoring a plurality of first signals of the server, wherein the first signals are operation signals of the corresponding electronic devices; if the liquid cooling component of the server leaks to the electronic device, the first signal corresponding to the electronic device is abnormal, and alarm information is reported; the first signal includes a circuit status signal, a power status signal, or a traffic status signal.

The controller of the server in this embodiment determines whether the liquid cooling component of the server leaks by monitoring whether the plurality of first signals are abnormal. The detection can be realized without depending on a special detection circuit, the detection range is wider, and the accuracy and timeliness of liquid leakage detection are ensured.

The first signal comprises a circuit state signal, a power state signal or a service state signal, wherein the circuit state signal, the power state signal and the service state signal are signals which are easy to generate abnormality when the electronic device encounters water, and the accuracy of liquid leakage detection can be improved by monitoring the signals.

In a fourth aspect, embodiments of the present application provide a computing device. The computing device comprises a cabinet and the server of any one of the above, wherein the server is arranged in the cabinet.

In a possible implementation manner, the number of servers is multiple, and each server in the cabinet monitors the first signal through the electronic device originally owned by the server to judge whether the liquid cooling assembly leaks, so that single-point protection is realized, and normal operation of other servers is not affected. In other words, the plurality of servers in the cabinet server can independently control the leakage condition of the servers, so that the servers with leakage are ensured to be powered down for maintenance, and the servers without leakage can also normally operate.

Drawings

FIG. 1 is a schematic diagram of a computing device in one embodiment provided by an embodiment of the present application;

FIG. 2 is a partial schematic diagram of the computing device shown in FIG. 1 in some embodiments;

FIG. 3 is a partial schematic diagram of the computing device shown in FIG. 2 in some embodiments;

FIG. 4 is a schematic view of the fluid circulation device of FIG. 3 at another angle in some embodiments;

FIG. 5 is a schematic view of a portion of the structure of FIG. 3 at another angle;

FIG. 6 is a schematic diagram of the internal architecture of the server of FIG. 3 in some embodiments;

FIG. 7A is a schematic view of a portion of the structure of the server shown in FIG. 6;

FIG. 7B is a schematic diagram of the server shown in FIG. 6 in another embodiment;

FIG. 7C is a schematic diagram of a portion of the circuit of the server shown in FIG. 6;

FIG. 7D is a partial circuit schematic of another embodiment of the server shown in FIG. 6;

FIG. 8 is a schematic diagram of another embodiment of the server shown in FIG. 6;

FIG. 9 is a schematic diagram of another embodiment of the server shown in FIG. 8;

FIG. 10 is a schematic diagram of another embodiment of the server shown in FIG. 6;

fig. 11 is a schematic flow chart of a liquid leakage detection method provided in this embodiment.

Detailed Description

In order to enable those skilled in the art to better understand the embodiments of the present application, the following description will clearly describe the technical solutions of the embodiments of the present application with reference to the accompanying drawings.

In embodiments of the present application, "at least one" means one or more, and "a plurality" means two or more. "and/or", describes an association relationship of an association object, and indicates that there may be three relationships, for example, a and/or B, and may indicate: a alone, a and B together, and B alone, wherein a, B may be singular or plural. The character "/" generally indicates that the context-dependent object is an "or" relationship. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (one) of a, b or c may represent: a, b, c, a and b, a and c, b and c or a, b and c, wherein a, b and c can be single or multiple. In addition, in the embodiments of the present application, the words "first", "second", and the like do not limit the number and order.

It should be noted that, in the embodiments of the present application, words such as "exemplary" or "such as" are used to mean serving as an example, instance, or illustration. Any embodiment or design described herein as "exemplary" or "e.g." in an embodiment of the present application is not to be taken as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "such as" is intended to present related concepts in a concrete fashion.

It is to be understood that the specific embodiments described herein are merely illustrative of the application and are not limiting of the application. It should be noted that, for convenience of description, only the portions related to the application are shown in the drawings.

FIG. 1 is a schematic diagram of a computing device in one embodiment, provided by an embodiment of the application.

Referring to fig. 1, a computing device 100 may be a rack server, or may be another device requiring liquid cooling. The following description exemplifies a computing device 100 as a rack server.

The computing device 100 may include a cabinet 10, a fluid circulation device 20, and a server 30. At least part of the liquid circulation device 20 and the server 30 are arranged inside the cabinet 10, the liquid circulation device 20 is used for providing circulating cooling liquid for the server 30, the cooling liquid circulates in a liquid cooling assembly in the server 30 so as to exchange heat with electronic devices heating inside the server 30, and heat emitted by the electronic devices heating can be transmitted to the outside through the liquid circulation device 20, so that the effect of effectively radiating heat for the server 30 is achieved.

In other embodiments, computing device 100 may also include a switch, repeater, or host, among other devices requiring liquid-cooled heat dissipation. In some embodiments, the computing device 100 may not include a cabinet, e.g., the computing device 100 may include only the server 30 and the fluid circulation device 20, in which case the server 30 may be disposed on other carrying devices. In some embodiments, when the computing device is not a rack server, but is other electronic device, the server may be other devices requiring heat dissipation.

The number of the servers 30 may be plural, and the plural servers 30 are stacked and disposed in the cabinet 10, so as to reduce the space occupied by the plural servers 30. The number of the liquid circulation devices 20 may be one, and one liquid circulation device 20 supplies the circulated cooling liquid to each of the plurality of servers 30. The configuration of the liquid circulation device 20 can be simplified and the cabinet 10 can be miniaturized by supplying the circulating coolant to the plurality of servers 30 with respect to the plurality of liquid circulation devices.

Of course, in other embodiments, the number of the liquid circulation devices 20 may be plural, and each liquid circulation device 20 provides circulating cooling liquid for one or more servers 30, so that providing circulating cooling liquid for all servers 30 relative to one liquid circulation device 20 can provide more precise management.

Referring to fig. 1 and 2, fig. 2 is a schematic diagram of a portion of the computing device 100 shown in fig. 1 in some embodiments.

The cabinet 10 may include a cabinet body 11 and a cabinet back (not shown). The cabinet backboard is arranged inside the cabinet body 11, can be positioned on the side edge of the cabinet body 11, can be arranged on the top of the cabinet body 11, and can be positioned at other positions of the cabinet body 11. The server 30 is provided inside the cabinet 11, along with a part of the liquid circulation device 20. The cabinet 11 is used for accommodating and protecting devices or components provided therein. The plurality of servers 30 are each electrically connected to the cabinet backplane, with each server 30 being signal interconnected through the cabinet backplane. A power supply is further arranged in the cabinet 10, and the plurality of servers 30 can be connected with the power supply through buses (bus bars) to ensure power supply of the plurality of servers 30.

Of course, in other embodiments, the number of servers 30 may be one. One server 30 is connected to the cabinet back. Alternatively, in another embodiment, when the number of servers 30 is plural, the plural servers 30 may be interconnected by other forms of switching devices such as switches, instead of the signal interconnection through the cabinet backplane.

Referring to fig. 3 and 4, fig. 3 is a schematic diagram of a portion of the computing device 100 shown in fig. 2 in some embodiments; fig. 4 is a schematic view of another angle of the fluid circulation device 20 shown in fig. 3 in some embodiments.

The liquid circulation device 20 may include a first liquid separation pipe 21, a second liquid separation pipe 22, and a condenser (not shown). The first liquid-separating tube 21 may include a first tube body 211, a first liquid inlet tube 212 and a plurality of first liquid outlet tubes 213, which are communicated with the first tube body 211. The second liquid separating tube 22 may include a second tube 221, and a plurality of second liquid inlet tubes 222 and a second liquid outlet tube 223 which are communicated with the second tube 221. The liquid outlet of the condenser is connected with the first liquid inlet pipe 212 of the first liquid separating pipe 21, and the liquid inlet of the condenser is connected with the second liquid outlet pipe 223 of the second liquid separating pipe 22.

The first liquid outlet pipes 213 and the second liquid inlet pipes 222 may correspond to the servers 30 one by one, and the liquid inlet of the liquid cooling assembly of one server 30 is communicated with one first liquid outlet pipe 213, and the liquid outlet of the liquid cooling assembly is communicated with one second liquid inlet pipe 222.

The cooling liquid condensed by the condenser enters the first pipe body 211 through the first liquid inlet pipe 212, then enters the liquid cooling assemblies of the servers 30 through the first liquid outlet pipes 213 respectively, the cooling liquid entering the liquid cooling assemblies exchanges heat with the heating electronic devices of the corresponding servers 30, the cooling liquid after heat exchange enters the second pipe body 221 from the corresponding second liquid inlet pipe 222, flows out through the second liquid outlet pipe 223 after being gathered, enters the condenser, and the condenser can re-condense the cooling liquid, so that the liquid circulation device 20 can realize circulation refrigeration, and continuous cooling liquid is provided for the servers 30.

Of course, in one implementation of other embodiments, the liquid circulation device may also include only a condenser and one liquid dividing tube. There are two independent inner spaces in a liquid separating pipe, the liquid outlet of the condenser is communicated with one inner space, the space is also communicated with the liquid inlet of the liquid cooling component of one or more servers, the liquid inlet of the condenser is communicated with the other inner space, and the inner space is also communicated with the outlet of the liquid cooling component of one or more servers. That is, one liquid-dividing pipe may function as two liquid-dividing pipes.

Of course, the number of liquid cooling components of one server may be plural, which is not limited in the embodiment of the present application, as long as the liquid circulation device 20 can provide circulated cooling liquid for the liquid cooling components disposed electronically.

Of course, in another implementation scenario of other embodiments, the number of the first liquid outlet pipes and the second liquid inlet pipes may also be set as required. For example, a plurality of first liquid outlet pipes may provide cooling liquid for one server. Or a first outlet pipe provides cooling fluid for a plurality of servers. The embodiment of the application does not limit the number of the first liquid inlet pipe, the first liquid outlet pipe, the server, the second liquid outlet pipe and the matching mode between the first liquid inlet pipe, the first liquid outlet pipe, the server, the second liquid outlet pipe and the second liquid outlet pipe.

In this embodiment, as shown in fig. 3, the first liquid inlet pipe 212 and the second liquid outlet pipe 223 may be staggered along a first direction, where the first direction is a direction in which the first pipe body 211 (or the second pipe body 221) extends. This arrangement reduces or avoids interference between the first liquid inlet pipe 212 and the second liquid outlet pipe 223, improves convenience in connection between the first liquid inlet pipe 212 and other components (such as the condenser outlet), and convenience in connection between the second liquid outlet pipe 223 and other components (such as the condenser inlet), thereby improving convenience in installation of the two liquid separation pipes. Of course, the positional relationship of the first liquid inlet pipe 212 and the second liquid outlet pipe 223 is not limited in the embodiment of the present application.

Referring to fig. 2 and 4, in the present embodiment, the first liquid distribution pipe 21 and the second liquid distribution pipe 22 are both fixed inside the cabinet 11, and the plurality of first liquid outlet pipes 213 and the plurality of second liquid inlet pipes 222 are disposed opposite to the plurality of servers 30, so that the first liquid outlet pipes 213 and the second liquid inlet pipes 222 are communicated with the liquid cooling components of the corresponding servers 30. Of course, in other embodiments, the first liquid outlet pipe and the second liquid inlet pipe may not be disposed opposite to the server. The first liquid outlet pipe and the second liquid inlet pipe can be communicated with the liquid cooling assembly of the corresponding server through pipelines.

Referring to fig. 3 and 5, fig. 5 is a schematic view of a portion of the structure shown in fig. 3 at another angle.

It will be appreciated that during transportation, no coolant is present within the fluid circulation device 20 to prevent freezing expansion of the coolant due to extreme conditions encountered during transportation, and damage to the fluid circulation device 20. Therefore, before transportation, the cooling liquid in the liquid circulation device is discharged and dried, so that the liquid circulation device 20 is not damaged in the transportation process.

In this embodiment, the first liquid dividing pipe 21 and the second liquid dividing pipe 22 may each include a drain pipe. The cooling liquid inside the first liquid-dividing pipe 21 and the second liquid-dividing pipe 22 can be discharged through the respective drain pipes. The connection relationship between the drain pipe and the first and second liquid-dividing pipes 21 and 22 may be the same or different, and the first liquid-dividing pipe 21 is described as an example. For example, the gravitational end of the first tube 211 may have a first port 2110. It is understood that the gravitational direction is the gravitational direction of the first liquid dividing tube 21 in the use state. The drain pipe 214 may communicate with the first pipe body 211 through a first port 2110. It will be appreciated that the drain outlet is open only when draining so that coolant can drain from the drain, and closed when the first body 211 does not require draining. By providing the first port 2110 at the end of the first pipe body 211 in the gravitational direction, the first port 2110 can be located close to the bottom wall 2111 of the first pipe body 211 or at the bottom wall 2111 of the first pipe body 211. The liquid flows downwards under the action of gravity, so that the liquid in the first pipe body 211 can be discharged through the drain pipe 214, the liquid discharging efficiency of the first pipe body 211 can be improved, the liquid can be discharged from the first pipe body 211 conveniently, and the residual quantity of the liquid in the first pipe body 211 after liquid discharging is reduced. Meanwhile, since the first liquid separation pipe 21 needs to be dried after liquid discharge so as to be convenient for transportation, the first liquid separation pipe 21 in this embodiment can reduce the residual quantity of the liquid in the first pipe body 211 after liquid discharge, and improve the drying efficiency.

In this embodiment, the first port 2110 is located at the bottom wall 2111 of the first pipe body 211, so that the liquid in the first pipe body 211 can be discharged through the first port 2110 and the drain pipe 214 under the action of gravity, and no other structure is required to be arranged to introduce the liquid at the bottom of the first pipe body 211 into the drain pipe 214, so that on one hand, the efficiency of discharging the liquid through the drain pipe 214 is improved, on the other hand, the liquid is discharged from the first pipe body 211 conveniently, the residual amount of the liquid in the first pipe body 211 after liquid discharge can be reduced, and the drying efficiency of the first pipe body 211 is improved. Of course, in other embodiments, the first port 2110 may also be positioned proximate to the bottom wall 2111 of the first tube 211.

In this embodiment, the drain pipe 214 may be directly connected to the first port 2110, or the connection between the drain pipe 214 and the first port 2110 may be achieved through the adapter 215, that is, the adapter 215 is connected between the drain pipe 214 and the first port 2110.

In this embodiment, the drain pipe 214 may extend to a side of the first pipe body 211 away from the first liquid outlet pipe 213, for example, to a side away from the server 30, so as to avoid mutual interference between the drain pipe 214 and the plurality of first liquid outlet pipes 213.

In some examples, the drain 214 may include a flexible pipe section. It will be appreciated that the drain pipe 214 may include flexible pipe sections such that the drain pipe 214 can flex in different directions, thereby avoiding interference between the drain pipe 214 and other piping and facilitating maintenance and disassembly. In addition, since the drain pipe 214 can be bent in different directions, the risk of collision between the drain pipe 214 and the first drain pipe 213, the second drain pipe 222 and other pipelines can be reduced, the risk of damage to the drain pipe 214 can be reduced, and the reliability of the first liquid separation pipe 21 can be improved.

In this embodiment, at least part of the drain pipe 214 is made of transparent material, so that after the liquid remaining in the first pipe body 211 is dried, whether the residual liquid exists in the first pipe body 211 can be visually observed by visually observing the drain pipe 214.

For example, when residual liquid is observed to exist in the drain pipe 214 by naked eyes, it may be determined that residual liquid still exists in the first pipe 211, and it is necessary to continue drying the first pipe 211. When it is observed with the naked eye that there is no residual liquid in the drain pipe 214, it may be determined that the first pipe body 211 is dried, so that the drying of the first pipe body 211 may be stopped.

That is, at least part of the drain pipe 214 is made of transparent material, so that the risk of residual liquid in the first pipe body 211 after the first pipe body 211 is dried can be reduced, for example, the risk of damage and breakage of the first pipe body 211 caused by freezing and expanding of the residual liquid when the ambient temperature is reduced during transportation of the first liquid distribution pipe 21 can be reduced, and the reliability of the first liquid distribution pipe 21 can be improved, thereby improving the reliability of the liquid circulation device 20.

Further, since the first port 2110 is located at the end of the first pipe body 211 in the direction of gravity, it is possible to improve the accuracy of determining whether or not the residual liquid exists in the first pipe body 211 by visually inspecting the drain pipe 214.

In addition, the drain pipe 214 is at least partially made of transparent material to observe whether residual liquid exists in the first pipe body 211, so that on one hand, no other instrument (such as a dryness-humidity detector) is needed to detect whether residual liquid exists in the first pipe body 211, and cost is saved. On the other hand, when no residual liquid exists in the drain pipe 214, it can be determined that the first pipe body 211 is dried, so that the continuous drying of the first pipe body 211 is stopped, and the problem of long drying time caused by the fact that the drying state of the first pipe body 211 cannot be obtained in time is avoided. That is, by visually observing the drain pipe 214, it is possible to know whether the first pipe body 211 is dried or not in time, improving drying efficiency and reducing drying cost.

Through setting up the at least part of drain pipe 214 and being transparent material, can also naked eye whether there is residual impurity in the drain pipe 214 to confirm whether there is residual impurity in the first body 211, avoid residual impurity to influence drain pipe 214's sealed effect, reduced the risk of revealing of first branch liquid pipe 21, improved the reliability of first branch liquid pipe 21, thereby improve the reliability of liquid circulating device 20.

For example, when residual impurities can be visually observed through the transparent portion of the drain pipe 214, the first pipe body 211 may be subjected to a cleaning process to remove residual impurities existing in the first pipe body 211, thereby improving the reliability of the first liquid-dividing pipe 21.

In some examples, drain 214 is entirely transparent. In other examples, a portion of drain 214 is a transparent material. By way of example, the length of the transparent portion of drain pipe 214 is greater than 2cm, avoiding the transparent portion from being too short in length, which would affect the viewing effect. Of course, in other embodiments, the length of the transparent portion of the drain pipe 214 may be set as desired.

In some examples, at least a portion of the drain pipe 214 may be at least one of fluorinated ethylene propylene copolymer (Fluorinated Ethylene Propylene, FEP), polytetrafluoroethylene (Poly Tetra Fluoroethylene, PTFE), and Polycarbonate (PC).

In some embodiments, the fluid circulation device 20 may further include a circulation pump (not shown) to drive the circulation of the cooling fluid in the fluid cooled components of the fluid circulation device 20 and the server 30.

Referring to fig. 3 and 6, fig. 6 is a schematic diagram illustrating an internal structure of the server 30 of the structure shown in fig. 3 in some embodiments.

The server 30 may include a housing 31, a main board 32, a central processing unit (central processing unit, CPU) 33, a board card 34, a hard disk 35, and a power supply unit 36. The housing 31 has a housing cavity 310, and the motherboard 32, the CPU33, the board 34, the hard disk 35 and the power unit 36 can be disposed in the housing cavity 310, however, in some embodiments, the board 34, the hard disk 35 and the power unit 36 can be disposed outside the housing cavity 310. The CPU33 is mounted on the motherboard 32 and is electrically connected to the motherboard 32. The board 34, the hard disk 35 and the power supply unit 36 are electrically connected to the motherboard 32, and the CPU33 can access electronic devices such as the board 34, the hard disk 35 and the like through a high-speed serial computer expansion bus standard (peripheral component interconnect express, PCIe) bus.

It will be appreciated that the PCIe Bus is just one example and may be replaced with other buses, such as a Unified Bus (UB) Bus, etc.

The power supply unit 36 is connected to the power supply via a bus to supply power to the main board 32, the central processing unit, the hard disk 35, and the like. The electronic components such as the motherboard 32, the board 34, the hard disk 35, and the power supply unit 36 together form an electronic component of the server 30, in other words, the electronic component includes the electronic components such as the motherboard 32, the board 34, the hard disk 35, and the power supply unit 36.

Motherboard 32 (Motherboard, mainBoard, mobo), also known as a Motherboard, system Board, logic board (logic Board), motherboard, backplane, etc., is the central or main circuit board that forms a complex electronic system such as a server, computer, or other computing device. Motherboard 32 may refer to a printed circuit board (Printed circuit board, PCB) with expansion capability. Motherboard 32 can provide a series of joints for the engagement of devices such as CPU33, board 34, hard disk 35, and power supply unit 36.

The CPU33 is an operation core and a control core of the server 30. One or more CPUs 33 may be included in the server 30, and the server 30 shown in fig. 6 includes two CPUs 33. The CPU33 may be a very large scale integrated circuit. An operating system and other software programs are installed in the CPU33, so that the CPU33 can realize access to the hard disk 35 and various boards 34. It will be appreciated that in embodiments of the invention, the CPU33 may be replaced by an integrated circuit (Application Specific Integrated Circuit, ASIC), other general purpose processor, digital signal processor (digital signal processing, DSP), application specific integrated circuit (application specific integrated circuit, ASIC), field programmable gate array (field programmable gate array, FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or the like.

The board cards 34 may include one or more of a network card, a power backplane, a hard disk backplane, a redundant array of independent disks (Redundant Array of Independent Disks, RAID) card, and the like. The network card, the RAID card, etc. may be PCIe cards. The power supply back plane is a circuit board for providing the power supply unit 36, and the power supply unit 36 may be interconnected with the main board 32 through the power supply back plane. The hard disk back plate is a circuit board for setting a hard disk, and the hard disk 35 may be interconnected with the main board 32 through the hard disk back plate.

The hard disk 35 is a memory of the server 30. The hard disk 35 is typically used to store various running software in the operating system, input and output data, information exchanged with external memory, and the like. The hard disk 35 may be a dynamic random access Memory (Dynamic Random Access Memory, DRAM), a static random access Memory (Static Random Access Memory, SRAM), a Read Only Memory (ROM). For read-only memory, for example, it may be a programmable read-only memory (Programmable Read Only Memory, PROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, EPROM), etc. The present embodiment is not limited in the number and type of hard disks 35. In addition, the hard disk 35 may be configured to have a power-saving function. The power-saving function means that the data stored in the memory is not lost when the system is powered down and powered up again. The hard disk 35 having a power-retaining function is called a nonvolatile memory.

The server 30 may also include electronic components such as complex programmable logic devices (Complex Programming logic device, CPLD) 41, field programmable gate arrays (Field Programmable Gate Array, FPGA), and baseboard management controllers (Baseboard Management Controller, BMC). The CPLD41, the FPGA and the BMC are all mounted on the motherboard 32.CPLD41, the FPGA and BMC are all coupled to motherboard 32.

The BMC may perform firmware upgrades to the server 30, manage the running state of the server, troubleshoot, and the like. The BMC may also maintain program code in memory, including upgrades or recovery, and the like. The BMC may also control a power supply circuit or a clock circuit in the server 30, and the like. In summary, the BMC can implement management of the server 30 in the above manner. In some embodiments, CPU33 may communicate with sensors to manage and maintain the computer devices.

It should be noted that, the different servers 30 may be referred to as BMCs differently, for example, some companies may be referred to as BMCs, some companies may be referred to as iLO, and another company may be referred to as iDRAC. Either called BMC or iLO or iracc may be understood as BMC in embodiments of the present invention.

In other embodiments, the server 30 may also include the CPU33, and one or two or three of the CPLD41, FPGA, or BMC.

As shown in fig. 6, in the present embodiment, the server 30 may further include a power connector 37, where the power connector 37 is fixed to the housing 31, and one end is located outside the housing 31 and electrically connected to a bus bar (bus bar), and the other end is located inside the housing 31 and electrically connected to the power unit 36. In other words, the power supply unit 36 is connected to the power supply via the power connector 37 and the bus bar.

Referring to fig. 3, 6 and 7A, fig. 7A is a schematic diagram of a portion of the structure of the server 30 shown in fig. 6.

In this embodiment, the server 30 may further include a liquid cooling component 38, where the liquid cooling component 38 dissipates heat for the heat-generating electronic device. The liquid cooling assembly 38 may include a liquid cooling tube 381 and a cold plate 382 in communication with the liquid cooling tube 381. A cold plate 382 and at least a portion of the liquid cold tube 381 are located within the receiving cavity 310, the cold plate 382 being capable of exchanging heat with the heat generating electronics.

The liquid inlet of the liquid cooling pipe 381 is connected to the first liquid outlet pipe 213 of the corresponding first liquid dividing pipe 21, and the liquid outlet of the liquid cooling pipe 381 is communicated to the second liquid inlet pipe 222 of the corresponding second liquid dividing pipe 22. The liquid inlet of the liquid cooling pipe 381 is the liquid inlet of the liquid cooling assembly 38, and the liquid outlet of the liquid cooling pipe 381 is the liquid outlet of the liquid cooling assembly 38.

The liquid circulation device 20 provides circulating cooling liquid for the liquid cooling assembly 38, when the liquid cooling assembly works, the cooling liquid flows into the liquid cooling tube 381 from the first liquid outlet tube 213 of the first liquid separation tube 21 through the liquid inlet of the liquid cooling tube 381, then enters the cold plate 382, after heat exchange between the cold plate 382 and the electronic device generating heat, enters the second liquid inlet tube 222 of the second liquid separation tube 22 through the liquid outlet of the liquid cooling tube 381, then enters the second tube 221, and flows into the liquid cooling tube 381 after refrigerating in the liquid circulation device 20, so that the circulation of the cooling liquid is realized.

In this embodiment, the coolant may be water or a refrigerant such as freon.

In some embodiments, as in fig. 7B, server 30 may further include an adapter 50, adapter 50 for enabling communication between liquid cold pipe 381 and first and second liquid separation pipes 21 and 22. For example, the adapter 50 may include a body 51 and two adapter tubes 52 fixed to the body 51, where the body 51 is fixed to the housing 31, one ends of the two adapter tubes 52 are located in the accommodating cavity 310 and are respectively communicated with the liquid inlet and the liquid outlet of the liquid cooling tube 381, and the other ends of the two adapter tubes 52 penetrate through the housing 31 to be communicated with the first liquid outlet tube 213 and the second liquid inlet tube 222 located outside the housing 31. The body 51 of the adapter 50 is fixed to the housing 31, ensuring a stable connection between the adapter 50 and the liquid cooling assembly 38 and the liquid circulation device 20.

Of course, in some embodiments, the liquid inlet and the liquid outlet of the liquid cooling pipe 381 may also directly penetrate the housing 31 and be exposed outside the housing 31, so that the liquid inlet of the liquid cooling pipe 381 is directly connected to the first liquid outlet pipe 213 of the corresponding first liquid separating pipe 21, and the liquid outlet of the liquid cooling pipe 381 is directly connected to the second liquid inlet pipe 222 of the corresponding second liquid separating pipe 22, so as to achieve direct communication between the liquid cooling pipe 381 and the liquid circulation device 20.

The cold plate 382 can cover the surface of the electronic device that generates heat, and is in direct contact with the surface of the electronic device or in contact with the surface of the electronic device through a heat exchange layer, so that the cold plate 382 and the electronic device have a larger heat exchange area, and the heat dissipation efficiency of the electronic device is improved conveniently. The heat generating electronic device may be, for example, an electronic device that generates a large amount of heat during operation, such as the CPU33, the power supply unit 36, and the board 34. The heat exchange layer may be a layer structure with a good heat transfer effect, such as an adhesive sheet, a heat conductive layer, etc. with a good heat transfer effect. The heat exchange layer may be adhesive and also may function to secure the cold plate 382 to the electronic device, although the heat exchange layer may be non-adhesive.

It can be appreciated that, compared with air cooling, the heat exchange efficiency of the liquid cooling heat dissipation method is higher and the heat dissipation effect is better, so that the heat dissipation requirement of the server 30 can be satisfied even if the heat dissipation capacity of the server 30 is increased due to the increase of power consumption and the like.

As shown in fig. 6 and 7A, in the present embodiment, the number of the cold plates 382 is three, and for convenience of understanding, the three cold plates are a first cold plate 3821, a second cold plate 3822, and a third cold plate 3823, respectively. The first and second cold plates 3821 and 3822 are respectively in contact with the two CPUs 33, and the third cold plate 3823 is in contact with the power supply unit 36. The liquid cooling tube 381 may include a liquid inlet section 3811, a liquid cooling section 3812, and a liquid outlet section 3813, which are sequentially connected. The opening of the liquid inlet section 3811 far from the liquid cooling section 3812 is the liquid inlet of the liquid cooling pipe 381, and the opening of the liquid outlet section 3813 far from the liquid cooling section 3812 is the liquid outlet of the liquid cooling pipe 381.

In this embodiment, the liquid cooling section 3812 may include a first liquid inlet pipe 101, a first liquid outlet pipe 102, a second liquid inlet pipe 201, a second liquid outlet pipe 202, a third liquid inlet pipe 301, and a third liquid outlet pipe 302. The first liquid inlet pipe 101, the second liquid inlet pipe 202 and the third liquid outlet pipe 302 are all communicated with the liquid inlet section 3811, the first liquid outlet pipe 102, the second liquid outlet pipe 202 and the third liquid outlet pipe 302 are all communicated with the liquid outlet section 3813, the first cold plate 3821 is communicated between the first liquid inlet pipe 101 and the first liquid outlet pipe 102, the second cold plate 3822 is communicated between the second liquid inlet pipe 201 and the second liquid outlet pipe 202, and the third cold plate 3823 is communicated between the third liquid inlet pipe 301 and the third liquid outlet pipe 302. It can be understood that the liquid inlet section 3811 is a main liquid inlet pipe of the first liquid inlet pipe 101, the second liquid inlet pipe 202 and the third liquid outlet pipe 302, and the liquid outlet section 3813 is a main liquid outlet pipe of the first liquid outlet pipe 102, the second liquid outlet pipe 202 and the third liquid outlet pipe 302.

It can be understood that the cooling liquid entering through the liquid inlet section 3811 is divided into three paths, and the first path of cooling liquid enters the first cooling plate 3821 through the first liquid inlet pipe 101 and then flows into the liquid outlet section 3813 through the first liquid outlet pipe 102; the second cooling liquid enters the second cold plate 3822 through the second liquid inlet pipe 201 and then flows into the liquid outlet section 3813 through the second liquid outlet pipe 202; the third cooling liquid enters the third cold plate 3823 through the third liquid inlet pipe 301, then flows into the liquid outlet section 3813 through the third liquid outlet pipe 302, and is discharged through the liquid outlet section 3813.

In this embodiment, each cold plate 382 corresponds to one liquid inlet pipe, and compared with a plurality of liquid inlet pipes 381 which share one liquid inlet pipe, each cold plate 382 can be ensured to have a good heat dissipation effect. Of course, in other embodiments, the plurality of cold plates 382 may share a common liquid inlet pipe, that is, the plurality of cold plates 382 are connected in series between one liquid cooling pipe 381, and the cooling liquid passes through one cold plate 382 and then enters the other cold plate 382 through the liquid cooling section 3812. Compared with a liquid inlet pipe corresponding to each cold plate 382, the scheme can save the consumable cost of the liquid cooling pipes and reduce the cost of the server 30 on the basis of guaranteeing heat dissipation.

In this embodiment, one cold plate 382 radiates heat for one heat-generating electronic device, and of course, in other embodiments, multiple cold plates 382 radiate heat for one heat-generating electronic device. Alternatively, one cold plate 382 radiates heat for a plurality of heat-generating electronic devices, so long as the heat radiation effect of the electronic devices can be ensured.

In this embodiment, the material of the cold plate 382 may be a material with good heat transfer performance, such as copper or aluminum, so as to improve the heat transfer performance of the cold plate 382.

In other embodiments, the number of cold plates 382 may be other than three, for example, the number of cold plates 382 may be one, two, four, etc. When the number of cold plates 382 is one, one cold plate 382 communicates with the liquid cooling section 3812. When the number of the cold plates 382 is two, the liquid cooling section 3812 may have two liquid inlet pipes and two liquid outlet pipes, which are respectively communicated with the two cold plates 382.

In other embodiments, the server 30 may also include only the liquid-cooled tube 381, and no cold plate is included, and the liquid-cooled segment 3812 of the liquid-cooled tube 381 directly cooperates with the heat-generating electronic device to dissipate heat from the electronic device, and the exemplary liquid-cooled segment 3812 may be in direct contact with a surface of the electronic device, or in contact with a surface of the electronic device through a heat exchange layer.

In other embodiments, the liquid cooling assembly 38 may also dissipate heat for one, two or three other heat generating electronic devices, and the heat generating electronic devices may not be limited to the CPU33, the board 34, the hard disk, the power supply unit, and other electronic devices.

As shown in fig. 6, in this embodiment, the server 30 may further include a fan 39, where the fan 39 is configured to perform air cooling and heating for the electronic devices that generate heat inside the server 30. The server 30 in this embodiment radiates heat by adopting air cooling and liquid cooling at the same time, so that heat dissipation is effectively performed for the electronic device of the server 30, the heat dissipation effect is ensured, and the performance of the server 30 is ensured. The number of fans 39 may be one or more. Of course, in other embodiments, the server 30 may not include a fan.

In this embodiment, as shown in fig. 6 and 7A, the server 30 may further include an on-off valve 40, where the on-off valve 40 is disposed at a position of the liquid inlet section 3811 and the liquid outlet section 3813 away from the liquid cooling section 3812. In another implementation, the on-off valve 40 is positioned at and near the inlet and outlet of the inlet and outlet sections 3811, 3813. The on-off valve 40 is used to control the on-off of the liquid cooling pipe 381. For example, when the liquid cooling assembly 38 leaks, the switch valve 40 may be closed to prevent the liquid from flowing into the liquid cooling tube from the liquid inlet of the liquid cooling tube, that is, to prevent the cooling liquid from continuously flowing into the liquid cooling segment 3812 through the liquid inlet segment 3811, so as to prevent the short circuit or damage of the electronic device inside the server 30 caused by the expansion of the liquid leakage area, and prevent the fault from diffusing.

In this embodiment, the on-off valve 40 may be a solenoid valve or other on-off valve capable of controlling the on-off of the liquid cooling pipe 381.

Of course, in other embodiments, the on-off valve 40 may also be disposed at a location of the liquid intake section 3811 away from the liquid cooling section 3812. In other words, the on-off valve 40 is provided near the liquid inlet of the liquid cooling pipe 381. That is, the on-off valve 40 is used to control the on-off of the intake section 3811. When the liquid cooling assembly 38 leaks, the switch valve 40 can be closed to prevent the cooling liquid from continuously flowing into the liquid cooling section 3812, and meanwhile, the liquid already existing in the liquid cooling pipe 381 can flow out from the liquid outlet section 3813, so that the liquid already existing in the liquid cooling pipe 381 is prevented from continuously leaking out through the leaking part to damage the electronic devices inside the server 30.

Of course, in an implementation scenario of other embodiments, the number of the switch valves 40 may be two, where one switch valve is disposed at a position of the liquid inlet section 3811 away from the liquid cooling section 3812, for controlling on-off of the liquid inlet section 3811, and one switch valve is disposed at a position of the liquid outlet section 3813 away from the liquid cooling section 3812, for controlling on-off of the liquid outlet section 3813.

In another implementation scenario of other embodiments, an on-off valve is disposed at a position of the liquid inlet section 3811 and the liquid outlet section 3813 away from the liquid cooling section 3812, but the on-off valve can selectively control on-off of the liquid inlet section 3811 or the liquid outlet section 3813. For example, the on-off valve may include two valves, one valve controlling the on-off of the inlet section 3811 and the other valve controlling the on-off of the outlet section 3813. One or both of the intake section 3811 or the discharge section 3813 may be selectively closed depending on the liquid leakage location or degree of the liquid cooling assembly. For example, the liquid inlet section 3811 and the liquid outlet section 3813 may be closed at the same time when the degree of liquid leakage is less severe, and only the liquid inlet section 3811 may be closed when the degree of liquid leakage is more severe. The on-off of the liquid inlet section or the liquid outlet section is selectively controlled according to the liquid leakage condition, so that the server can be better protected.

In still another implementation scenario of other embodiments, the number of the switch valves may be multiple, and the switch valves may be disposed at a position away from the liquid cooling section 3812 in the liquid inlet section 3811 (or the liquid outlet section 3813) at intervals, so as to prevent one switch valve from being failed, and the other switch valve may ensure on-off of the liquid inlet section 3811 (or the liquid outlet section 3813).

In this embodiment, as shown in fig. 7A, the on-off valve 40 is electrically connected to the power connector 37, and power is supplied to the on-off valve 40 through the power connector 37. It should be noted that, the power connector 37 is connected with the bus of the power supply device to supply power to the server 30, the switch valve 40 supplies power through the power connector 37 connected with the bus of the power supply device, compared with the situation that the switch valve 40 supplies power through other electronic devices inside the server 30, other electronic devices cannot be damaged and power is lost, the power supply reliability of the switch valve 40 is guaranteed, the power-on time of the switch valve 40 can be earlier than that of other electronic devices of the server 30, and further the switch valve 40 is guaranteed to be turned off in time when the liquid cooling assembly 38 leaks liquid, and short circuit and damage of the electronic devices inside the server 30 are avoided.

Of course, in other embodiments, electronics within computing device 100 may also be electrically connected to the on-off valve to power the on-off valve. The electronic device may be, for example, a power supply unit 36, a motherboard 32, a power supply back plane, etc.

In this embodiment, as shown in fig. 6 and 7A, the switch valve 40 may also be coupled to a controller, for example, a CPLD41, where after the server 30 is powered on, the CPLD41 controls the switch valve 40 to open, and the cooling component 38 is introduced with cooling fluid. When the CPLD41 determines that the liquid cooling assembly 38 may leak, the CPLD41 may control the switch valve 40 to close, so as to avoid the cooling liquid from continuing to enter the liquid cooling pipe 381.

It should be noted that, when the server 30 is powered on, the CPLD41 is powered on and initialized, and then the switch valve 40 is controlled to be opened, so that the cooling liquid is conveniently introduced into the cooling assembly 38 as soon as possible, and then the motherboard is controlled to be powered on, so that each electronic device powered through the motherboard is powered on. In this embodiment, the switch valve 40 is controlled to be opened first, so that the cooling liquid is introduced into the heat dissipation assembly 38, and then the electronic devices are controlled to be powered on to run, so as to ensure the heat dissipation effect of each electronic device.

Of course, in other embodiments, after the CPLD41 is initialized, the various electronic devices may be controlled to power up while controlling the on-off valve 40 to open.

Referring to fig. 7C, fig. 7C is a schematic circuit diagram of a portion of the server shown in fig. 6.

In this embodiment, one power supply 361 of the power supply unit is electrically connected to the CPLD41, so that when the server 30 is powered on, the CPLD41 is also powered on, so that the CPLD41 operates the switch valve 40 before the service of the server 30 runs. The CPLD41 is connected with the switch valve 40 through a lead 61, one end of a resistor 62 is connected with the power supply 361, the other end of the resistor is connected between the CPLD41 and the switch valve 40, namely the other end of the resistor is connected with the lead 61, so that the CPLD41 can realize the on-off of the switch valve 40 by controlling the on-off between the lead 61 and the ground. For example, when CPLD41 controls conduction between wire 61 and ground, switching valve 40 is in an off state, and when CPLD41 controls disconnection between wire 61 and ground, switching valve 40 is in an on state.

In some embodiments, server 30 may further include a switching circuit connected between switching valve 40 and CPLD41, where CPLD41 may control the on/off of switching valve 40 by controlling the switching or closing of the switching circuit.

The switching circuit may include a metal-oxide-semiconductor field-effect transistor (MOS) or the like.

In this embodiment, the switch circuit may be disposed inside the switch valve 40, so that the cost can be effectively reduced and the space of the main board 32 can be saved compared with the switch circuit disposed outside the switch valve 40 without adding a circuit on the main board 32.

Of course, in an implementation scenario of other embodiments, the switch circuit may also be provided on the motherboard 32. Alternatively, the switch circuit may be provided on a separate circuit board or on a circuit board of another board card.

In another implementation of other embodiments, the controller may also be other electronic devices such as FPGA or BMC, and the switch valve 40 may be coupled to other electronic devices such as FPGA or BMC. Other electronic devices such as an FPGA or a BMC determine that the liquid cooling assembly 38 may leak, and the other electronic devices such as the FPGA or the BMC may control the switch valve 40 to close, so as to prevent the cooling liquid from continuing to enter the liquid cooling pipe 381.

In this embodiment, as shown in fig. 6 and 7A, the operation signals of the electronic devices of the server 30 may be monitored by the CPLD41, that is, the CPLD41 has various operation signals of the electronic devices of the server 30, and the CPLD41 selects the first signals from the operation signals and monitors the first signals. The first signal is a signal that the corresponding electronic device may be abnormal after the contact cooling liquid fails. In other words, if the liquid cooling module 38 of the server 30 leaks to the electronic device, the first signal corresponding to the electronic device is abnormal.

In this embodiment, the motherboard 32, the board 34, the hard disk 35, the power unit 36, the fan, and the electronic devices such as the memory and the CPU disposed on the motherboard 32 all have one or more first signals. Of course, in other embodiments, the plurality of first signals may also be first signals of at least two electronic devices in the motherboard 32, the board 34, the hard disk 35, and the power supply unit 36. Alternatively, other electronic devices such as graphics processors (graphics processing unit, GPUs), BMC, FPGA, CPLD may each have one or more first signals.

When the CPLD41 monitors that the first signal is abnormal, the control switch valve 40 is closed and reports the alarm information to the BMC, and the BMC reports the alarm information to the client management interface. When the CPLD41 monitors that the first signal is abnormal, the CPLD41 may also control the electronic devices such as the motherboard 32, the board 34, the hard disk 35, the power supply unit 36, and the like to power down so as to avoid damaging the electronic devices in the server 30. It should be noted that, when the electronic device in the server 30 contacts the conductive medium such as the cooling liquid, some operation signals of the electronic device may be abnormal, and these operation signals are first signals indicating whether the liquid cooling assembly 38 leaks, by monitoring these first signals, in other words, if one or more first signals are abnormal, in other words, at least one first signal is abnormal, it is indicated that the position where the electronic device corresponding to the one or more first signals may leak, and the CPLD41 immediately reports the alarm information.

That is, the present embodiment determines whether the liquid cooling assembly 38 leaks by monitoring whether the plurality of first signals are abnormal. Compared with the method for detecting whether the liquid cooling assembly 38 leaks through the water invasion rope, the method can realize detection without depending on a special detection circuit, and ensures the accuracy and timeliness of the liquid leakage detection.

When monitoring that a certain first signal is abnormal, the embodiment can determine which position of the liquid cooling assembly 38 has liquid leakage through the electronic device corresponding to the first signal, and compared with the situation that whether the liquid leakage exists only can be detected by a water invasion rope, the position of the liquid leakage cannot be determined, so that maintenance personnel can know the position of the liquid leakage according to reported alarm information, and the server 30 can be maintained rapidly and effectively.

In addition, through a plurality of first signals of the monitoring server, because the plurality of first signals are running signals of electronic devices distributed at each position of the server, the monitoring range is wide, and compared with the situation that the water invasion rope is limited in coverage area when the liquid cooling assembly is detected through the water invasion rope, the detection position coverage is wider, and the liquid leakage detection is more accurate.

In this embodiment, when the first signal is abnormal, the switch valve 40 is also closed, so as to avoid the expansion of the liquid leakage area and reduce the loss. At the same time, the electronics within the server 30 are controlled to power down to avoid damage to the electronics within the server 30.

The operation signals of the electronic devices are monitored by the CPLD41, and compared with the monitoring of other electronic devices, the monitoring of the first signals by the CPLD41 reduces the steps of the other electronic devices for acquiring the first signals from the CPLD41, reduces the time delay of data transmission, and improves the monitoring efficiency and the monitoring timeliness.

In this embodiment, the server 30 monitors the first signal through its own electronic device to determine whether the liquid cooling assembly 38 leaks, so as to implement single-point protection, and the normal operation of other servers 30 will not be affected. In other words, the plurality of servers 30 in the cabinet server individually control the leakage condition of the servers to ensure that the servers 30 with leakage are powered down for maintenance, and the servers 30 without leakage can also operate normally. Of course, in other embodiments, the first signal may also be monitored by other electronics external to the server 30, such as through a backplane within the cabinet 10.

In this embodiment, when the CPLD41 monitors that the first signal is abnormal, all electronic devices such as the motherboard 32, the board 34, the hard disk 35, the power supply unit 36 and the like are controlled to be powered down, so as to avoid damage to other electronic devices caused by continued diffusion of leakage liquid after the electronic devices only controlling the first signal to be abnormal are powered down.

Of course, in other embodiments, when the CPLD41 monitors that the first signal is abnormal, only the electronic device with the first signal abnormal may be controlled to power down to perform the fault isolation function, and the electronic device with the first signal not abnormal may continue to operate, so as to avoid the service from being greatly affected. Or, when the CPLD41 monitors that the first signal is abnormal, only the electronic device with the first signal abnormal is controlled to power down, and the electronic device without the first signal abnormal is powered down again at intervals, during which time, each electronic device can prepare for power down, for example, save related data, and send the service to other servers to complete, so as to minimize the influence of power down of the servers on the service.

In other embodiments, when the CPLD41 monitors that the first signal is abnormal, the information about the occurrence of the first signal is sent to the BMC, and the BMC controls the electronic devices such as the motherboard 32, the board 34, the hard disk 35, the power supply unit 36, and the like to power down.

In some embodiments, the first signal may be a circuit status signal, a power status signal, or a traffic status signal, etc. that is indicative of a drain. The circuit state signal, the power state signal and the service state signal are signals which are easy to generate abnormality when the electronic device encounters water, and the accuracy of liquid leakage detection can be improved by detecting the signals. It will be appreciated that each electronic device may have one or more of the first signals described previously.

The circuit state signal is a signal for determining whether the overcurrent protection circuit state is normal. The motherboard may include multiple paths of over-current protection circuits, each path having a circuit status signal. Such as a circuit status signal of an over-current protection circuit of a CPU system of the main board, a circuit status signal of a fan over-current protection circuit of the main board, a circuit status signal of a USB interface over-current protection circuit of the main board, etc. It should be noted that, the overcurrent protection function and the slow start function are implemented by the same circuit, and the overcurrent protection circuit may be understood as a slow start circuit.

The power state signal is a signal that determines whether the power state of the electronic device is normal. The power state differs for different electronic devices. For example, the motherboard may include multiple power supplies, and the power state of each power supply may be the power output state of the power supply. The power state signal can be a signal of any power supply of the main board. Any power supply can be, for example, a CPU power supply, a power supply of a memory on a motherboard, a south bridge power supply, and the like. The signal of the Power supply may be, for example, a Power OK signal.

The power state of the power supply unit includes a power Input state and a power Output state, and the power state signal includes an Input OK signal for determining whether the power Input state is normal, and an Output OK signal for determining whether the power Output state is normal.

The service status signal may be a signal for determining whether the service of the electronic device is normal, and in general, when the electronic device encounters water, the key function of the electronic device is abnormal, which may cause the service status signal to be abnormal. For example, the traffic state signal anomaly may be a traffic drop or the traffic state anomaly may be a traffic parameter anomaly. The traffic status signal may be different for different electronic devices.

In this embodiment, the first signals of the board card, the hard disk, the memory, and the CPU may be service status signals, and the service status signals may be reset signals. When the reset signal is abnormal, the service of the electronic device corresponding to the reset signal is disconnected. When the number of the boards is plural, the first signal of each board may be a reset signal. Similarly, when the number of hard disks, memories and CPUs is plural, the first signal of each hard disk, memory and CPU may be a reset signal.

In some embodiments, the traffic state signal may be a traffic operating parameter. The service operation parameter may be a temperature of any electronic device, for example, a temperature of an air outlet or an air inlet of a fan, and a temperature of an overcurrent protection circuit of each electronic device.

In some embodiments, the traffic state signal may also be a bit signal, for example, when the bit signal of the power supply unit is abnormal, the traffic of the power supply unit is dropped.

In this embodiment, the main board may have a plurality of first signals, where the plurality of first signals may be a circuit state signal of an overcurrent protection circuit of a CPU system of the main board, a circuit state signal of a fan overcurrent protection circuit of the main board, a circuit state signal of a USB interface overcurrent protection circuit of the main board, a signal of a CPU power supply, a signal of a memory power supply, a signal of a south bridge power supply, a signal of an overcurrent protection circuit, and a signal representing leakage, so as to ensure accuracy of leakage detection. Of course, in other embodiments, the plurality of first signals of the motherboard may also be one or more of the signals listed above.

The first signals of the board card, the hard disk, the memory and the CPU can be reset signals.

The power supply unit can be provided with a plurality of first information, and the plurality of first signals can be signals representing leakage, such as input normal signals, output normal signals, on-site signals and the like, so that the accuracy of leakage detection is ensured. Of course, in other embodiments, the plurality of first signals of the power supply unit may also be one or more of the signals listed above.

The first signal of the fan comprises signals representing leakage, such as the temperature of the air outlet or the air inlet, so as to ensure the accuracy of leakage detection.

The embodiment does not limit the form of the alarm information, and the alarm information can be a prompt message or a prompt signal. When the alarm information is a prompt information, the maintenance personnel needs to actively process the accident of the liquid cooling assembly 38 after receiving the prompt information. When the alarm information is a prompt, the prompt is used to prompt the server 30 to fail, so as to prompt maintenance personnel to process as soon as possible, and reduce loss.

The alarm information may be, for example, at least one of a buzzer, an indicator light, a pop-up window in a display interface, or a window flashing window in a display interface, where the buzzer and the indicator light may be disposed in an area where the server 30 is located, or may also be disposed in a control room, so that maintenance personnel may receive the alarm information as soon as possible. In this solution, maintenance personnel are required to deal with the problem of the liquid cooling assembly 38 in time after acquiring the alarm information.

In this embodiment, the CPLD41 may also control each electronic device to save data before powering down each electronic device such as the motherboard 32, the board 34, the hard disk 35, the power unit 36, etc., so as to reduce losses.

In this embodiment, when the power failure of the CPLD41 results in power failure of the CPLD41, the switching valve 40 is not supplied with power, or the CPLD41 is immersed in water or the power failure of the CPLD41 is caused by a failure, the switching valve 40 is in an off state, so that when the CPLD41 or the switching valve does not work, it is ensured that the cooling liquid can also be prevented from continuously flowing into the liquid cooling section 3812 through the liquid inlet section 3811, short circuit or damage to electronic devices inside the server 30 caused by expansion of the area of the leaked liquid is avoided, and failure diffusion is prevented.

The power failure of the CPLD41 may cause the CPLD41 to be powered down when the power supply unit is immersed in water, so that the CPLD is powered down when no power is supplied.

For example, due to the circuit design shown in fig. 7C, when power failure of CPLD41 causes CPLD41 to be powered down, since power supply 361 shown in fig. 7C is powered down, conductor 61 is also unpowered, and switching valve 40 is in a closed state. Also, when the on-off valve 40 is not electrically supplied, the on-off valve 40 is not controlled by the CPLD and is also in the off state.

For example, as shown in fig. 7D, when CPLD41 is immersed in water or fails to cause power failure of CPLD41, but power supply 361 of CPLD41 is not in problem, since CPLD41 is not working, switching valve 40 is directly connected to power supply 361, and at this time, CPLD41 cannot control switching valve 40 to be closed, in this case, the present application can control switching valve 40 to be closed through BMC 70.

As shown in fig. 7d, BMC70 is connected to CPLD41, and BMC70 is also connected to conductor 61. When the CPLD41 fails to operate, the BMC70 controls the connection of the wire 61 to ground to control the on-off valve 40 to close.

Of course, in an implementation scenario of other embodiments, if the FPGA controls the on/off of the switch valve 40, the FPGA may obtain the first signals from the CPLD41 and monitor the first signals, and if the FPGA monitors that the first signals are abnormal, the FPGA controls the switch valve 40 to close and report the alarm information to the BMC, and the BMC reports the alarm information to the client management interface. The electronic devices such as the motherboard 32, the board card 34, the power supply unit 36, etc. are controlled to be powered down to avoid damage to the electronic devices in the server 30. If the FPGA is immersed in water or other faults cause power failure, or the on-off valve 40 is in an off state when no power is supplied to the on-off valve 40, it is ensured that the cooling liquid can be prevented from continuously flowing into the liquid cooling section 3812 through the liquid inlet section 3811 when the FPGA is not in operation, short circuit or damage to electronic devices in the server 30 caused by expansion of liquid leakage area is avoided, and fault diffusion is prevented.

In another implementation scenario of other embodiments, if the BMC controls the on/off of the switch valve 40, the BMC may obtain the first signals from the CPLD41 and monitor the first signals, and if the BMC monitors that the first signals are abnormal, the BMC controls the switch valve 40 to close and report the alarm information to the customer management interface, and simultaneously controls the electronic devices such as the motherboard 32, the board card 34, the power supply unit 36, etc. to power down so as to avoid damaging the electronic devices in the server 30. If the BMC is immersed in water or other faults to cause power failure, or the switch valve 40 is in an off state when no power is supplied, the switch valve 40 is in an off state, so that cooling liquid can be prevented from continuously flowing into the liquid cooling section 3812 through the liquid inlet section 3811 when the BMC is not in operation, short circuit or damage to electronic devices in the server 30 caused by expansion of liquid leakage area can be avoided, and fault diffusion can be prevented.

Of course, in other embodiments, the computing device 100 may not include a switch valve, and when the CPLD41 monitors that the first signal is abnormal, it reports the alarm information to the BMC, and the BMC reports the alarm information to the client management interface, and simultaneously controls all electronic devices such as the motherboard 32, the board 34, the hard disk 35, the power supply unit 36, and the like to power down so as to avoid damage to the electronic devices in the server 30. Alternatively, in other embodiments, when the computing device 100 does not include the switch valve 40, the cpld41 monitors that the first signal is abnormal, reports the alarm information to the BMC, and the BMC reports the alarm information to the client management interface. The BMC may not control the powering down of various electronic devices, such as the motherboard 32, the card 34, the hard disk 35, the power unit 36, and the like.

Referring to fig. 8, fig. 8 is a schematic structural diagram of another embodiment of the server 30 shown in fig. 6.

The server 30 of the present embodiment is substantially the same as the server 30 shown in fig. 6, and the same parts are not repeated. In contrast, the switching circuit of the present embodiment may also be provided outside the switching valve 40. Illustratively, the switching circuitry is formed on a separate circuit board 42. The switching circuit is connected between the power connection 37 and the switching valve 40, and the power connection 37 supplies power to the switching valve 40 through the switching circuit. CPLD41 is coupled with a switching circuit, and CPLD41 can control the on/off of switching valve 40 by controlling the switching or closing of the switching circuit. In this embodiment, the switch is provided outside the on-off valve 40, so that the on-off valve 40 does not need to be modified, and the design is simple.

Of course, in other embodiments, if the FPGA or BMC controls the switch valve 40 to be turned off instead of the CPLD41, the FPGA or BMC is coupled to the switch circuit to control the on/off of the switch valve 40 by controlling the switch or closing of the switch circuit.

Referring to fig. 9, fig. 9 is a schematic structural diagram of another embodiment of the server 30 shown in fig. 8.

The server 30 of the present embodiment is substantially the same as the server 30 shown in fig. 8, and the same parts are not repeated. In contrast, the server 30 of the present embodiment further includes a voltage transformation circuit 43, where the voltage transformation circuit 43 is connected between the power connector 37 and the switching circuit, and the voltage transformation circuit 43 is used to convert the voltage of the power supplied by the power connector 37 into a voltage adapted to the switching valve 40, so that the server 30 of the present embodiment can adapt to the switching valve 40 of various voltage input requirements.

The voltage transformation circuit 43 may be a voltage boosting circuit, a voltage reducing circuit, or a circuit with both voltage boosting and voltage reducing functions, so as to ensure that the switching valve 40 with various voltage input requirements is suitable.

Of course, in other embodiments, the voltage transformation circuit 43 may also be provided between the switching circuit and the switching valve 40.

In other embodiments, the server 30 in the embodiment shown in fig. 6 may also include a voltage transformation circuit 43, as shown in fig. 10, where the voltage transformation circuit 43 may be connected after the power connector 37 and the switch valve 40 to convert the voltage of the power supplied by the power connector 37 into a voltage suitable for the switch valve 40.

Referring to fig. 11, fig. 11 is a flow chart of a liquid leakage detection method according to the present embodiment. The liquid leakage detection method is applied to the server 30 of any of the above embodiments. The liquid leakage detection method includes the following steps S110 to S130.

S110: a plurality of first signals of the server 30 are determined.

Specifically, in connection with fig. 6, the controller determines a plurality of first signals of the server 30, where the server includes a plurality of electronic devices, and the first signals are operation signals of the corresponding electronic devices. The one or more first signals of each electronic device together comprise a plurality of first signals of the server. It should be noted that, when the electronic device in the server 30 contacts a conductive medium such as a cooling liquid, some operation signals of the electronic device may be abnormal, and these operation signals are first signals indicating whether the liquid cooling assembly 38 leaks. That is, the first signal is a signal that an electronic device corresponding to the signal is abnormal after the contact coolant fails, in other words, if the liquid cooling module 38 of the server 30 leaks to the electronic device, the first signal corresponding to the electronic device is abnormal.

In this embodiment, the controller is a CPLD41, and the operation signals of the electronic devices of the server 30 are all monitored by the CPLD41, that is, the CPLD41 has various operation signals of the electronic devices of the server 30, and the CPLD41 selects the first signal from the operation signals.

Examples of the electronic devices include a motherboard 32, a board 34, a hard disk 35, a power supply unit 36, a fan, and a memory and a CPU provided on the motherboard 32. The board card 34 may include one or more of a network card, a power backplane, a hard disk backplane, a RAID card, and the like.

In this embodiment, the motherboard 32, the board 34, the hard disk 35, the power unit 36, the fan, and the memory and the CPU disposed on the motherboard 32 all have one or more first signals. The one or more first signals of these electronics together constitute a plurality of first signals of the server 30 to ensure accuracy of water leakage detection. Of course, in other embodiments, the plurality of first signals may also be first signals of at least two electronic devices in the motherboard 32, the board 34, the hard disk 35, and the power supply unit 36. Alternatively, other electronic devices such as graphics processors (graphics processing unit, GPUs), BMC, FPGA, CPLD may each have one or more first signals.

By way of example, the first signal may be a circuit status signal, a power status signal, or a traffic status signal, etc. that is characteristic of a drain. It will be appreciated that each electronic device may have one or more of the first signals described previously.

The circuit state signal is a signal for determining whether the overcurrent protection circuit state is normal. The motherboard may include multiple paths of over-current protection circuits, each path having a circuit status signal. For example, a circuit state signal of an over-current protection circuit of a CPU system of the main board, a circuit state signal of a fan over-current protection circuit of the main board, a circuit state signal of a USB interface slow start work over-current protection circuit of the main board, and the like. It should be noted that, the overcurrent protection function and the slow start function are implemented by the same circuit, and the overcurrent protection circuit may be understood as a slow start circuit.

The power state signal is a signal that determines whether the power state of the electronic device is normal. The power state differs for different electronic devices. For example, the motherboard may include multiple power supplies, and the power state of each power supply may be the power output state of the power supply. The power state signal may be a signal of any power supply of the motherboard, where any power supply may be, for example, a CPU power supply, a power supply of a memory on the motherboard, a south bridge power supply, and so on. The signal of the Power supply may be, for example, a Power OK signal.

The power state of the power supply unit may include a power Input state and a power Output state, and the power state signal includes an Input OK signal for determining whether the power Input state is normal, and an Output OK signal for determining whether the power Output state is normal.

Of course, in other embodiments, the controller may also be an FPGA, BMC or other electronic device that may determine the first signals of each electronic device and then obtain these first signals from CPLD 41.

S120: a plurality of first signals of the server 30 are monitored.

For example, referring to fig. 6, the cpld41 monitors the first signal of each electronic device, if any one of the first signals is abnormal, in other words, at least one of the first signals is abnormal, which indicates that the position of the electronic device corresponding to the one or more first signals may have a leakage, and then S130 is performed.

Of course, in other embodiments, the first signal of each electronic device may also be monitored by the FPGA, the BMC, or other electronic devices, where the FPGA, the BMC, or other electronic devices first obtain the first signal from the CPLD41, and then monitor the first signal.

S130: if the liquid cooling component of the server leaks to the electronic device, the first signal corresponding to the electronic device is abnormal, and alarm information is reported.

Specifically, referring to fig. 6, if at least one first signal is abnormal, the warning information is reported, and when the CPLD41 monitors that at least one first signal is abnormal, the warning information is reported to the BMC, and the BMC reports the warning information to the client management interface, so that maintenance personnel can maintain the server 30.

By monitoring the first signals, if at least one first signal is abnormal, the embodiment of the application indicates that the position of the electronic device corresponding to the at least one first signal may have a leakage condition, and the CPLD41 immediately reports the alarm information. That is, the present embodiment determines whether the liquid cooling assembly 38 leaks by monitoring whether the plurality of first signals are abnormal. Compared with the method for detecting whether the liquid cooling assembly 38 leaks through the water invasion rope, the method can realize detection without depending on a special detection circuit, and ensures the accuracy and timeliness of the liquid leakage detection.

In this embodiment, the leakage detection method monitors the first signal through the electronic device originally existing in the server 30 to determine whether the liquid cooling assembly 38 leaks, so as to realize single-point protection, and not affect the normal operation of other servers 30. In other words, the plurality of servers 30 in the cabinet server individually control the leakage condition of the servers to ensure that the servers 30 with leakage are powered down for maintenance, and the servers 30 without leakage can also operate normally. Of course, in other embodiments, the leak detection method may also monitor the first signal through other electronics external to the server 30, such as through a backplane within the cabinet.

In some embodiments, when CPLD41 monitors the first signal for an abnormality, it also controls various electronic devices such as motherboard 32, board card 34, hard disk 35, power supply unit 36, etc. to power down to avoid damaging the electronic devices within server 30. For example, the CPLD41 controls the various electronic devices such as the motherboard 32, the board 34, the hard disk 35, the power unit 36, and the like to save data before powering down, so as to reduce losses.

In some embodiments, when the CPLD41 monitors that the first signal is abnormal, the switch valve 40 is also controlled to be closed, so that the liquid is prevented from flowing into the liquid cooling pipe from the liquid inlet of the liquid cooling pipe, and further, the liquid leakage area is prevented from being enlarged, and the loss is reduced.

In some embodiments, when the CPLD41 monitors that the first signal is abnormal, only the electronic device with the first signal abnormal may be controlled to power down, so as to perform a fault isolation function, and the electronic device with the first signal without the first signal abnormal may continue to operate, so as to avoid the service from being greatly affected. Or, when the CPLD41 monitors that the first signal is abnormal, only the electronic device with the first signal abnormal is controlled to power down, and the electronic device without the first signal abnormal is powered down again at intervals, during which time, each electronic device can prepare for power down, for example, save related data, and send the service to other servers to complete, so as to minimize the influence of power down of the servers on the service.

In some embodiments, the BMC may also monitor the state of the CPLD41, and if the CPLD41 itself causes the CPLD41 to power down due to flooding or other reasons, the BMC controls the switch valve 40 to close, so as to avoid that the cooling liquid can be prevented from continuously flowing into the liquid cooling section through the liquid inlet section when the CPLD41 is not working, and avoid that the area of the leaked liquid is enlarged to cause short circuit or damage of electronic devices in the server, and prevent fault diffusion. It should be noted that, under the condition of no conflict, the embodiments of the present application and features in the embodiments may be combined with each other, and any combination of features in different embodiments is also within the scope of the present application, that is, the above-described embodiments may also be combined arbitrarily according to actual needs.

It should be noted that all the foregoing drawings are exemplary illustrations of the present application, and do not represent actual sizes of products. And the dimensional relationships among the components in the drawings are not intended to limit the actual products of the application.

The present application is not limited to the above embodiments, and any changes or substitutions within the technical scope of the present application should be covered by the scope of the present application. Therefore, the protection scope of the application is subject to the protection scope of the claims.

Claims

1. A liquid leakage detection method, characterized in that the method is applied to a server for liquid cooling and heat dissipation, the server comprises a plurality of electronic devices, and the method comprises:

monitoring a plurality of first signals of the server, wherein the first signals are operation signals of the corresponding electronic devices;

2. The method of claim 1, wherein the plurality of electronic devices comprises at least two of a power supply unit, a motherboard, a board card, a hard disk, a memory, a central processing unit, or a fan.

3. The method of claim 2, wherein the board card comprises at least one of a network card, a redundant array of independent disks RAID card, a power backplane, or a hard disk backplane.

4. A method according to any one of claims 1 to 3, wherein the first signal comprises a circuit status signal, a power status signal or a traffic status signal.

5. The method according to any one of claims 1 to 4, further comprising:

And the liquid cooling component of the server leaks liquid to the electronic device, and the first signal corresponding to the electronic device is abnormal, so that the switch valve of the server is controlled to be closed.

6. The utility model provides a server, its characterized in that includes controller, liquid cooling subassembly and a plurality of electron device, liquid cooling subassembly is for at least one electron device heat dissipation, the controller is coupled with a plurality of electron device, the controller is used for:

7. The server of claim 6, further comprising a switch valve, wherein the liquid cooling assembly comprises a liquid cooling tube, the controller is electrically connected to the switch valve, and the controller is further configured to control the switch valve to close if the liquid cooling assembly of the server leaks into the electronic device, and the first signal corresponding to the electronic device is abnormal, so as to prevent liquid from flowing into the liquid cooling tube from a liquid inlet of the liquid cooling tube.

8. The server of claim 6 or 7, further comprising a power connector for externally connecting a power source to power the server, the switch valve being electrically connected to the power connector.

9. The server according to any one of claims 6 to 8, wherein the on-off valve is closed when the controller or the on-off valve is powered down.

10. The server is characterized by comprising a shell, an electronic component, a controller and a liquid cooling component; the electronic component, the controller and the liquid cooling component are all arranged in the shell, the electronic component comprises a plurality of electronic devices, the electronic devices comprise a main board, a Central Processing Unit (CPU), a network card, a hard disk and a power supply unit, the CPU and the controller are all arranged on the main board and are electrically connected with the main board, the controller is coupled with the CPU, the network card, the hard disk and the power supply unit, the liquid cooling component dissipates heat for at least one of the CPU and the power supply unit, and the controller is used for monitoring a plurality of first signals of the server, wherein the first signals are operation signals of the corresponding electronic devices; if the liquid cooling component of the server leaks to the electronic device, the first signal corresponding to the electronic device is abnormal, and alarm information is reported; the first signal includes a circuit status signal, a power status signal, or a traffic status signal.

11. A computing device comprising a cabinet and the server of any one of claims 6-10, the server being disposed within the cabinet.