Storage server liquid cooling apparatus, maintenance method, system, device, and media

Abstract

The application relates to a storage server liquid cooling device, a maintenance method, a system, equipment and a medium, wherein the maintenance method comprises the following steps: in response to a hard disk in a hard disk group being in a fault state, determining position information of a target hard disk group and a target hard disk node where the hard disk in the fault state is located; generating corresponding coding information according to the position information of the target hard disk group and the target hard disk node, and issuing a start instruction to start a lifting unit to move the target hard disk node; acquiring real-time position information of the target hard disk node, and in response to the real-time position information of the target hard disk node being consistent with the coding information, controlling the lifting unit to stop moving, so that the heat dissipation efficiency and the maintenance efficiency are improved.

Description

Technical Field

[0001] This application relates to the field of storage servers, and in particular to a liquid cooling device, maintenance method, system, equipment and medium for a storage server. Background Technology

[0002] With the development of the internet industry and the large-scale application of cloud computing and big data technologies in recent years, the scale of data centers has shown a rapid growth trend. Current computing platforms are becoming increasingly powerful and complex, posing challenges to data center cooling systems in terms of energy consumption and maintenance. To reduce energy consumption and improve heat dissipation efficiency, liquid cooling technology has become a development trend for data center cooling systems, and many large enterprises have established liquid-cooled data centers.

[0003] Storage servers are an indispensable type of server in data centers, used to store the data required by the entire center. Storage servers typically employ a multi-node design, dividing the storage server's hard drives into multiple nodes. Each node supports several working hard drives, and a hard drive failure in one node can avoid affecting other nodes. During maintenance, the node is removed, exposing the hard drives within for servicing. In liquid-cooled data centers, storage servers are placed in a liquid cooling pool. When a hard drive module in the server fails, maintenance personnel use a mechanical crane to lift the hard drive node, exposing it to the coolant surface, allowing engineers to repair or replace the hard drive. However, currently, when lifting a failed hard drive node in a liquid-cooled server for repair, maintenance engineers typically pull out the entire failed node. Sometimes, due to improper operation or over-lifting, the entire server is also pulled out. Furthermore, when maintenance engineers pull out the entire node for maintenance, the continued operation of other hard drives can lead to poor heat dissipation for those drives. Therefore, existing liquid cooling systems suffer from low maintenance efficiency and low heat dissipation efficiency. Summary of the Invention

[0004] Based on this, this application provides a liquid cooling device, maintenance method, system, equipment, and medium for a storage server to improve heat dissipation efficiency and maintenance efficiency.

[0005] On one hand, a liquid cooling device for a storage server is provided. The liquid cooling device includes a liquid cooling pool and a lifting unit. The storage server includes a baseboard management controller. The storage server is placed in the liquid cooling pool and has multiple hard disk nodes. The lifting unit is connected to the hard disk nodes to lift them. Each hard disk node includes multiple hard disks. A row of hard disks in each hard disk node, perpendicular to the direction in which the lifting unit lifts the hard disk node, forms a hard disk group. Multiple positioning marks are provided on the inner wall of the storage server chassis along the direction in which the lifting unit lifts the hard disk nodes. The positions of the positioning marks correspond one-to-one with the positions of the hard disk groups when the hard disk nodes are not lifted by the lifting unit. Each hard disk node is provided with a photoelectric sensor for detecting the positioning marks. The baseboard management controller is communicatively connected to the photoelectric sensor and the lifting unit.

[0006] In one embodiment, each of the hard disk nodes is further provided with a stop switch, and the liquid cooling device further includes an input / output controller for receiving signals from the photoelectric sensor. The substrate management controller is communicatively connected to the input / output controller, and the input / output controller is communicatively connected to the stop switch.

[0007] In one embodiment, the hard disk node includes a tray on which a hard disk backplane and the hard disk assembly are disposed, the tray being slidably connected to the chassis of the storage service server, and the lifting unit being connected to the tray.

[0008] In one embodiment, one photoelectric sensor is provided, and one positioning mark is provided corresponding to each of the hard disk groups. When the hard disk node is not lifted by the lifting unit, the photoelectric sensor is aligned with the positioning mark at the bottom of the inner wall of the storage server chassis.

[0009] In one embodiment, two photoelectric sensors are provided, and two positioning marks are provided corresponding to each hard disk group. When one photoelectric sensor is aligned with one of the positioning marks, the other photoelectric sensor is aligned with the other positioning mark. The two photoelectric sensors are arranged on the hard disk node along the sliding direction of the hard disk node. When the hard disk node is not lifted by the lifting unit, the two photoelectric sensors are aligned with the two positioning marks at the bottom of the inner wall of the storage server chassis, respectively. The two photoelectric sensors are redundant.

[0010] In one embodiment, the stop switch is located at the bottom of the hard disk node. When the hard disk node is not pulled up by the lifting unit, the stop switch is in a compressed state, and when the hard disk node is pulled up by the lifting unit, the stop switch is in a free state.

[0011] In one embodiment, the liquid cooling device further includes an alarm unit, which consists of multiple alarm lights, one alarm light corresponding to one hard disk group, and the alarm unit is communicatively connected to the input / output controller.

[0012] In one embodiment, the positioning identifier is a black Mylar film.

[0013] On the other hand, a maintenance method is provided, the maintenance method comprising:

[0014] In response to a disk in the disk group being in a fault state, determine the target disk group and the location information of the target disk node where the faulty disk is located;

[0015] Based on the location information of the target hard disk group and the target hard disk node, corresponding encoding information is generated, and a start command is issued to start the lifting unit, which moves the target hard disk node.

[0016] The real-time location information of the target hard disk node is obtained, and in response to the real-time location information of the target hard disk node being consistent with the encoded information, the lifting unit is controlled to stop moving.

[0017] In one embodiment, the process of moving the target hard disk node via the lifting unit further includes:

[0018] In response to the output signal of the stop switch, a start command is sent to the photoelectric sensor to start the photoelectric sensor to detect the positioning mark;

[0019] Wherein, when the stop switch is in the compressed state, the output signal of the stop switch is, and when the stop switch is in the free state, the output signal of the stop switch is.

[0020] In one embodiment, obtaining the real-time location information of the target hard disk node includes:

[0021] Receive the output signal of the photoelectric sensor, and determine the number of periodic changes of the output signal of the photoelectric sensor based on the output signal of the photoelectric sensor;

[0022] The number of cycles is used as the real-time location information of the target hard disk node;

[0023] Wherein, when the photoelectric sensor is aligned with the positioning mark, the output signal of the photoelectric sensor is [value]; when the photoelectric sensor is not aligned with the positioning mark, the output signal of the photoelectric sensor is [value].

[0024] In one embodiment, the number of photoelectric sensors is one, and determining the number of periodic changes in the output signal of the photoelectric sensor includes:

[0025] Determine the number of cycles in which the output signal of the photoelectric sensor changes from 1 to 0.

[0026] In one embodiment, the photoelectric sensor includes a first photoelectric sensor and a second photoelectric sensor, with the first photoelectric sensor located below the second photoelectric sensor. Determining the number of periodic changes in the output signal of the photoelectric sensor includes:

[0027] The number of cycles in which the output signal of the first photoelectric sensor changes from 1→0→1→0 is determined.

[0028] In one embodiment, determining the number of periodic changes in the output signal of the photoelectric sensor includes:

[0029] Determine the number of cycles in which the output signal of the second photoelectric sensor changes from 1 to 0.

[0030] In one embodiment, controlling the lifting unit to stop moving in response to the real-time location information of the target hard disk node being consistent with the encoded information includes:

[0031] The real-time location information of the target hard disk node is compared with the encoded information;

[0032] When the real-time location information of the target hard disk node is consistent with the encoded information, the lifting unit is controlled to stop moving the target hard disk node.

[0033] In one embodiment, after the lifting unit stops moving, the method further includes:

[0034] In response to the hard drive that was in a faulty state returning to normal, the lifting unit is controlled to move the corresponding target hard drive node;

[0035] In response to the output signal of the stop switch, the lifting unit is controlled to stop moving the corresponding target hard disk node.

[0036] In one embodiment, the method further includes:

[0037] The alarm color of the corresponding alarm light is determined based on the location information of the target hard disk node, and a corresponding alarm command is generated.

[0038] The alarm command is sent to the input / output controller to control the alarm light to turn on according to the alarm command.

[0039] In one embodiment, the encoded information is stored in the register of the input / output controller. The encoded information includes an eight-bit register value, the lower four bits of which are the location information of the target hard disk group, the fifth bit of which is the output information of one of the photoelectric sensors, the sixth bit of which is the output information of the other photoelectric sensor, and the seventh bit of which is the output information of the stop switch.

[0040] Furthermore, a maintenance system is provided, the maintenance system comprising:

[0041] The target determination module, in response to a hard drive in the hard drive group being in a fault state, determines the target hard drive group and the location information of the target hard drive node where the faulty hard drive is located;

[0042] The information acquisition module is used to generate corresponding encoded information based on the target hard disk group and the target hard disk node location information, and send the encoded information to the lifting unit to control the lifting unit to move the target hard disk node;

[0043] The device control module is used to acquire the real-time location information of the target hard disk node, and in response to the real-time location information of the target hard disk node being consistent with the encoded information, controls the lifting unit to stop moving.

[0044] In another aspect, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, performs the following steps:

[0045] In response to a disk in the disk group being in a fault state, determine the target disk group and the location information of the target disk node where the faulty disk is located;

[0046] Based on the location information of the target hard disk group and the target hard disk node, corresponding encoding information is generated, and a start command is issued to start the lifting unit, which moves the target hard disk node.

[0047] The real-time location information of the target hard disk node is obtained, and in response to the real-time location information of the target hard disk node being consistent with the encoded information, the lifting unit is controlled to stop moving.

[0048] In another aspect, a computer-readable storage medium is provided, the computer-readable storage medium storing a program that, when executed by a processor, causes the processor to perform the following steps:

[0049] In response to a disk in the disk group being in a fault state, determine the target disk group and the location information of the target disk node where the faulty disk is located;

[0050] Based on the location information of the target hard disk group and the target hard disk node, corresponding encoding information is generated, and a start command is issued to start the lifting unit, which moves the target hard disk node.

[0051] The real-time location information of the target hard disk node is obtained, and in response to the real-time location information of the target hard disk node being consistent with the encoded information, the lifting unit is controlled to stop moving.

[0052] The technical solution described in this application has the following advantages over the prior art:

[0053] The aforementioned liquid cooling device, maintenance method, system, equipment, and media for storage servers use a lifting unit to pull the faulty hard drive clusters from the hard drive nodes to the outside of the storage server chassis. This exposes the faulty hard drive clusters, facilitating maintenance personnel to perform maintenance on the faulty drives. Furthermore, the liquid cooling pool can still dissipate heat and cool the normally functioning hard drive clusters inside the storage server chassis, without reducing the cooling efficiency of the liquid cooling device. In addition, the baseboard management controller automatically controls the lifting unit to move the hard drive nodes to the required positions, thus exposing the faulty hard drive clusters within the storage server chassis while keeping the normally functioning hard drives within the chassis. This effectively improves both heat dissipation and maintenance efficiency. Attached Figure Description

[0054] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0055] Figure 1 This is a schematic diagram of the structure of the liquid cooling device for the storage server provided in the embodiments of this application;

[0056] Figure 2 This is a schematic diagram of the stop point of the liquid cooling device for the storage server provided in the embodiments of this application;

[0057] Figure 3This is a schematic diagram of the positioning marker structure of the liquid cooling device for the storage server provided in this application embodiment;

[0058] Figure 4 This is a schematic diagram of the circuit structure of the liquid cooling device for the storage server provided in the embodiments of this application;

[0059] Figure 5 This is a flowchart of a method for maintaining a liquid cooling device for a storage server provided in an embodiment of this application;

[0060] Figure 6 This is a system structure diagram of the maintenance system for the liquid cooling device of the storage server provided in the embodiments of this application;

[0061] Figure 7 This is a device structure diagram of the computer device provided in the embodiments of this application.

[0062] Explanation of reference numerals in the instruction manual:

[0063] 1. Liquid cooling tank; 2. Lifting unit; 3. Hard disk node; 4. Hard disk assembly; 5. Hard disk; 6. Positioning marker; 7. Stop switch; 8. Photoelectric sensor; 9. Tray; 10. Hard disk backplane; 11. Storage server. Detailed Implementation

[0064] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0065] Example 1

[0066] Reference Figure 1 As shown, Figure 1 This is a structural diagram of the liquid cooling device for a storage server provided in an embodiment of this application.

[0067] The liquid cooling device includes a liquid cooling pool 1 and a lifting unit 2. The storage server includes a baseboard management controller. The storage server 11 is placed in the liquid cooling pool 1. The storage server 11 has multiple hard disk nodes 3. The lifting unit 2 is connected to the hard disk nodes 3 to lift the hard disk nodes 3. Each hard disk node 3 includes multiple hard disks 5. A row of hard disks 5 in each hard disk node 3 along the direction perpendicular to the direction in which the lifting unit 2 lifts the hard disk node 3 forms a hard disk group 4. Multiple positioning marks 6 are provided on the inner wall of the chassis of the storage server 11 along the direction in which the lifting unit 2 lifts the hard disk nodes 3. The position of the positioning marks 6 corresponds one-to-one with the position of the hard disk group 4 when the hard disk node 3 is not lifted by the lifting unit 2. Each hard disk node 3 is provided with a photoelectric sensor 8 for detecting the positioning marks 6. The baseboard management controller is communicatively connected to the photoelectric sensor 8 and the lifting unit 2.

[0068] Specifically, the liquid cooling device for the storage server includes a liquid cooling pool 1 and a lifting unit 2. The storage server 11 is placed in the liquid cooling pool 1, and the liquid cooling pool 1 dissipates heat and cools the storage server 11. The storage server 11 is equipped with multiple hard disk nodes 3. The lifting unit 2 is connected to the hard disk nodes 3 to move them by lifting them. Each hard disk node 3 includes multiple hard disks 5, such as... Figure 2 As shown, Figure 2 Taking a 16-disk storage server as an example, a disk node 3 includes 16 disks, which are arranged in 4 rows, with 4 disks in each row forming a disk group 4. Figure 2 The lifting direction of the middle lifting unit 2 to the hard disk node 3 is vertical, such as... Figure 2 As indicated by the middle arrow, hard disk node 3 is divided into hard disk groups 4 horizontally. That is, a row of hard disks 5 in each hard disk node 3, perpendicular to the direction in which the lifting unit 2 extracts the hard disk node 3, forms a hard disk group 4. When any hard disk 5 in this hard disk node 3 is in a faulty state, the lifting unit 2 performs a lifting operation on the hard disk node 3, lifting the hard disk node 3 to a suitable position to maintain the faulty hard disk 5. Figure 2 As shown, the arrow indicates the lifting direction of the lifting unit 2 on the hard disk node 3. Multiple positioning markers 6 are provided on the inner wall of the storage server 11 chassis along the direction in which the lifting unit 2 extracts the hard disk node 3. The positions of the positioning markers 6 correspond one-to-one with the positions of the hard disk assembly 4 when the hard disk node 3 is not lifted by the lifting unit 2. Specifically, the positioning markers 6 are used to identify the positions of the hard disk node 3, such as... Figure 3 As shown, when all hard disks 5 on storage server 11 are in normal working condition, all hard disk nodes 3 ( Figure 3 Taking a single hard disk node as an example, all three are located at the bottom of the chassis of storage server 11. At this point, the direction in which the hard disk node 3 is pulled along the lifting unit 2 is... Figure 3 In the vertical direction, multiple virtual stop points are set on the inner wall of the storage server 11 chassis corresponding to the positions of hard disk group 4. Each stop point is a virtual position corresponding to hard disk group 4 and does not actually exist. Then, a positioning mark 6 is set at the position corresponding to the stop point, such as... Figure 3 As shown, hard disk node 3 is defined from top to bottom as the first hard disk group, the second hard disk group, the third hard disk group, and the fourth hard disk group. When hard disk node 3 is located at the lowest point inside the storage server 11 chassis, the lowest position of hard disk node 3 is at stop point 0 (at this time, the first, second, third, and fourth hard disk groups are all inside the storage server 11 chassis); when the first hard disk group on hard disk node 3 is lifted to expose the storage server 11 chassis, the lowest position of hard disk node 3 is at stop point 1 (at this time, the second, third, and fourth hard disk groups are all inside the storage server 11 chassis); when the first and second hard disk groups on hard disk node 3 are lifted to expose the storage server 11 chassis, the lowest position of hard disk node 3 is at stop point 2 (at this time, the third and fourth hard disk groups are both inside the storage server 11 chassis); when the first, second, and third hard disk groups on hard disk node 3 are lifted to expose the storage server 11 chassis, the hard disk node... The lowest position of point 3 is located at stop point 3 (at this time, all four hard disk groups are inside the chassis of storage server 11); when the first, second, third, and fourth hard disk groups on hard disk node 3 are lifted to expose the chassis of storage server 11, the lowest position of hard disk node 3 is located at stop point 4 (at this time, no hard disk group is inside the chassis of storage server 11); the stop point corresponds one-to-one with the positioning mark 6 on the chassis of storage server 11, and the positioning mark 6 on the chassis corresponds one-to-one with the position of hard disk group 4 when hard disk node 3 is not lifted by lifting unit 2. In this way, the position of hard disk group 4 on hard disk node 3 is indicated by the positioning mark 6 corresponding to the stop point, and the specific position information of hard disk node 3 being lifted by lifting unit 2 is located by this position. Specifically, when photoelectric sensor 8 is aligned with the positioning mark 6 at stop point 0, it indicates that hard disk node 3 is at the lowest position inside the chassis; when photoelectric sensor 8 is aligned with the positioning mark 6 at stop point 1, it indicates that hard disk node 3 is at stop point 1, and so on. Each hard disk node 3 is equipped with a photoelectric sensor 8 for detecting the positioning mark 6. The photoelectric sensor 8 is used to detect the positioning mark 6 so as to determine the moving position of the hard disk node 3 through the output signal of the photoelectric sensor 8.

[0069] The aforementioned liquid cooling device for the storage server allows the lifting unit 2 to pull the faulty hard drive group 4 from the hard drive node 3 to the outside of the storage server 11 chassis, exposing the faulty hard drive group 4 to the chassis. This facilitates maintenance personnel in maintaining the faulty hard drive 5. Furthermore, the liquid cooling pool 1 can still cool the normally functioning hard drive group 4 inside the storage server 11 chassis without reducing the cooling efficiency of the liquid cooling device. In addition, the baseboard management controller automatically controls the lifting unit 2 to move the hard drive node 3 to the required position, thus exposing the faulty hard drive group 4 to the storage server 11 chassis while keeping the normally functioning hard drive 5 inside the chassis. This effectively improves both heat dissipation and maintenance efficiency.

[0070] In one embodiment, each of the hard disk nodes 3 is further provided with a stop switch 7, and the liquid cooling device also includes an input / output controller for receiving signals from the photoelectric sensor 8. The substrate management controller is communicatively connected to the input / output controller, and the input / output controller is communicatively connected to the stop switch 7.

[0071] Each hard disk node 3 is also equipped with a stop switch 7, which has two states: a compressed state and a free state. When the stop switch 7 is in the compressed state, it indicates that the hard disk node 3 has not been lifted by the lifting unit 2, and the stop switch 7 sends an output signal indicating that the hard disk node 3 has not been lifted by the lifting unit 2. When the stop switch 7 is in the free state, it indicates that the hard disk node 3 has been lifted by the lifting unit 2, and at this time, the stop switch 7 sends an output signal indicating that the hard disk node 3 has been lifted by the lifting unit 2, so that the photoelectric sensor 8 performs the detection action of the positioning mark 6. The liquid cooling device includes an input / output controller, which is communicatively connected to the photoelectric sensor 8 and the stop switch 7 to receive the output signals of the photoelectric sensor 8 and the stop switch 7; the substrate management controller is communicatively connected to the input / output controller and the lifting unit 2, and the substrate management controller receives the signals from the input / output controller and controls the lifting unit 2 to perform the lifting action on the hard disk node 3. In one embodiment, the hard disk node 3 includes a tray 9 on which a hard disk backplane 10 and the hard disk assembly 4 are disposed. The tray 9 is slidably connected to the chassis of the storage server 11, and the lifting unit 2 is connected to the tray 9.

[0072] Specifically, such as Figure 3As shown, each hard disk node 3 includes a tray 9, on which a hard disk backplane 10 and a hard disk assembly 4 are mounted. The tray 9 is slidably connected to the chassis of the storage server 11. Simultaneously, the tray 9 is connected to a lifting unit 2, thereby enabling the lifting unit 2 to lift the tray 9, which in turn enables the lifting unit 2 to lift the hard disk node 3. The hard disk backplane 10 is equipped with the control circuitry for the liquid cooling system of the storage server 11. The control circuitry is as follows: Figure 4 As shown, the workflow implemented by this control circuit is as follows: In response to a faulty state in hard disk 5 within hard disk group 4, the location information of the target hard disk group and target hard disk node where the faulty hard disk 5 is located is determined; corresponding encoded information is generated based on the location information of the target hard disk group and target hard disk node, and a start command is issued to activate the lifting unit 2, which moves the target hard disk node; real-time location information of the target hard disk node is acquired, and in response to the real-time location information of the target hard disk node matching the encoded information, the lifting unit 2 is controlled to stop moving; in response to the faulty hard disk 5 returning to normal, the lifting unit 2 is controlled to move the corresponding target hard disk node; in response to the output signal of the stop switch 7 being 0 (the stop switch 7 is in a compressed state), the lifting unit 2 is controlled to stop moving the corresponding target hard disk node. Specifically, as... Figure 4 As shown, one end of the photoelectric sensor 8 is connected to a power supply (3V), and the other end of the photoelectric sensor 8 is connected to a Schmitt trigger through an amplifier circuit. Both Schmitt triggers are connected to the input / output controller. One end of the stop switch 7 is connected to a power supply (3V), and the other end of the stop switch 7 is connected to the input / output controller. At the same time, the mechanical part of the stop switch 7 cooperates with the inner wall of the storage server 11. The input / output controller is connected to the alarm unit and the substrate management controller. The substrate management controller is connected to the lifting unit 2. The input / output controller and the substrate management controller communicate via I2C signals.

[0073] In one embodiment, one photoelectric sensor 8 is provided, and one positioning mark 6 is provided corresponding to each of the hard disk groups 4. When the hard disk node 3 is not pulled up by the lifting unit 2, the photoelectric sensor 8 is aligned with the positioning mark 6 at the bottom of the inner wall of the chassis of the storage server 11.

[0074] Specifically, each hard disk node 3 is equipped with a photoelectric sensor 8, and a positioning mark 6 is set corresponding to each hard disk group 4. The photoelectric sensor 8 detects the positioning mark 6 to determine the real-time position information of the hard disk node 3. When the hard disk node 3 is not lifted by the lifting unit 2, the photoelectric sensor 8 is aligned with the positioning mark 6 at the bottom of the inner wall of the chassis of the storage server 11, and at this time the hard disk node 3 is in normal working condition.

[0075] In one embodiment, two photoelectric sensors 8 are provided, and two positioning marks 6 are provided corresponding to each of the hard disk groups 4. When one photoelectric sensor 8 is aligned with one of the positioning marks 6, the other photoelectric sensor 8 is aligned with the other positioning mark 6. The two photoelectric sensors 8 are arranged on the hard disk node 3 along the sliding direction of the hard disk node 3. When the hard disk node 3 is not lifted by the lifting unit 2, the two photoelectric sensors 8 are aligned with the two positioning marks 6 at the bottom of the inner wall of the chassis of the storage server 11, and the two photoelectric sensors 8 are redundant to each other.

[0076] Specifically, in addition to one photoelectric sensor 8, two photoelectric sensors 8 can be set, and the two photoelectric sensors 8 are redundant to improve the stability of the liquid cooling device. Specifically, two photoelectric sensors 8 are set, and two positioning marks 6 are set corresponding to each hard disk group 4. When one photoelectric sensor 8 is aligned with one positioning mark 6, the other photoelectric sensor 8 is aligned with the other positioning mark 6. This redundancy between the two photoelectric sensors 8 can determine the position information of the hard disk node 3, avoiding the situation where only one photoelectric sensor 8 exists and malfunctions, making it impossible to locate the faulty hard disk 5 on the storage server 11. The two photoelectric sensors 8 are arranged along the sliding direction of the hard disk node 3. When the hard disk node 3 is not lifted by the lifting unit 2, the two photoelectric sensors are aligned with the two positioning marks 6 at the bottom of the inner wall of the storage server 11 chassis. One stop point corresponds to two positioning marks 6. Figure 3 As shown, two photoelectric sensors 8 are respectively disposed on the upper and lower sides of the hard disk backplate 10, and the light channels of the photoelectric sensors are disposed on the tray 9. Figure 3 (not shown in the image) so that the light emitted by the photoelectric sensor 8 can pass through the light channel and illuminate the positioning mark 6 or the non-positioning mark.

[0077] In one embodiment, the stop switch 7 is located at the bottom of the hard disk node 3. When the hard disk node 3 is not pulled up by the lifting unit 2, the stop switch 7 is in a compressed state. When the hard disk node 3 is pulled up by the lifting unit 2, the stop switch 7 is in a free state.

[0078] Specifically, the output signal of the stop switch 7 is used to trigger the working state of the photoelectric sensor 8, such as... Figure 3As shown, the stop switch 7 is located at the bottom of the hard disk node 3. When the hard disk node 3 is not pulled up by the lifting unit 2, the stop switch 7 is in a compressed state and is compressed by the inner wall of the bottom of the chassis. At this time, the stop switch 7 outputs a signal to make the photoelectric sensor 8 non-working. When the hard disk node 3 is pulled up by the lifting unit 2, the stop switch 7 is in a free state. At this time, the stop switch 7 outputs a signal to make the photoelectric sensor 8 working to perform a detection action on the positioning mark 6.

[0079] In one embodiment, the liquid cooling device further includes an alarm unit, which consists of multiple alarm lights, one alarm light corresponding to one hard disk group 4, and the alarm unit is communicatively connected to the input / output controller.

[0080] Specifically, after receiving the signal from the input / output controller, the baseboard management controller determines the location information of hard disk node 3 based on the signal, and then determines the display status of the alarm light based on the location information. Specifically, taking the aforementioned 16 hard disks as an example, one hard disk group 4 corresponds to one alarm light, and each alarm light includes both red and green display colors. Figure 4 LED1 corresponds to the first hard drive group, LED2 to the second hard drive group, LED3 to the third hard drive group, and LED4 to the fourth hard drive group. When hard drive node 3 is at the bottom of the storage server 11 chassis and operating normally (i.e., at stop point 0), all four LEDs are green. When hard drive node 3 is pulled up to stop point 1, the first hard drive group is exposed and in maintenance mode, while the other three hard drive groups operate normally; LED1 turns red, and LEDs 2-4 remain green. When hard drive node 3 is pulled up to stop point 2, the first and second hard drive groups are exposed and in maintenance mode, while the other two hard drive groups operate normally; LEDs 1 and 2 turn red, and LEDs 3 and 4 remain green, and so on. When hard drive node 3 is fully pulled out, all four LEDs flash red, warning maintenance personnel that the node has been pulled up to its maximum extent, and further pulling could damage the server. This allows maintenance engineers to determine whether hard drive node 3 has been pulled up correctly based on the LED status. The baseboard controller transmits the current position information of hard disk node 3 to the controller of lifting unit 2 via RJ45 port to achieve automatic control. Furthermore, the alarm unit's alarm methods are not limited to alarm lights, but also include SMS, email, and voice alarms.

[0081] In one embodiment, the positioning identifier 6 is a black Mylar sheet.

[0082] Specifically, when the light emitted by the photoelectric sensor 8 shines on the black Mylar film, the intensity of the light reflected back through the black Mylar film is greatly reduced. Therefore, the black Mylar film is used as the positioning mark 6. Furthermore, when the hard disk node 3 is at the stop point 0, the photoelectric sensor 8 is aligned with the positioning mark 6 at the stop point 0. Since the positioning mark 6 is black, the reflected light received by the photoelectric sensor 8 is weak, and after processing by the amplification and filtering circuit, it outputs an electrical signal 0. When the hard disk node 3 is lifted, the photoelectric sensor 8 moves with the hard disk node 3 to a position other than the positioning mark 6. The reflected light received by the photoelectric sensor 8 becomes stronger, and after processing by the amplification and filtering circuit, it outputs an electrical signal 1. The position information of the hard disk node 3 is determined by the change in the signal.

[0083] Example 2

[0084] Reference Figure 5 As shown, Figure 5 A flowchart illustrating the maintenance method provided in this application embodiment.

[0085] The method includes the following steps:

[0086] S101, in response to the fault state of hard disk 5 in hard disk group 4, determine the location information of the target hard disk group and the target hard disk node where the faulty hard disk 5 is located;

[0087] Specifically, the system monitors the working status of hard drives 5 in each hard drive group 4 within the storage server 11 in real time. When any hard drive 5 is in a faulty state, the system determines the location information of the hard drive group 4 and hard drive node 3 containing the faulty hard drive 5. This includes the specific address of the hard drive group 4 containing the faulty hard drive 5 (referred to as the specific address of the target hard drive group) and the specific location of the hard drive node 3 containing the faulty hard drive 5 (referred to as the specific location of the target hard drive node). The hard drive group 4 containing the faulty hard drive 5 is called the target hard drive group, and the hard drive node containing the faulty hard drive 5 is called the target hard drive node.

[0088] S102, generate corresponding encoding information based on the location information of the target hard disk group and the target hard disk node, and issue a start command to start the lifting unit 2, and move the target hard disk node through the lifting unit 2;

[0089] Specifically, after determining the location information of the target hard disk group and the target hard disk node, corresponding encoding information is generated based on the location information of the target hard disk group and the target hard disk node. The encoding information stores the location information of the target hard disk group and the target hard disk node where the hard disk 5 in the faulty state is located. The encoding information is stored in the register of the input / output controller. The input / output controller sends the encoding information to the baseboard management controller. After receiving the encoding information, the baseboard management controller sends a start command to the lifting unit 2. After receiving the start command, the lifting unit 2 starts and controls the movement of the target hard disk node.

[0090] S103, obtain the real-time location information of the target hard disk node, and in response to the real-time location information of the target hard disk node being consistent with the encoded information, control the lifting unit 2 to stop moving.

[0091] Specifically, the target hard disk node moves under the control of the lifting unit 2. The target hard disk node needs to be moved to the corresponding position. For example, if the location of the hard disk 5 in the faulty state is the second hard disk group in the target hard disk node, then the target hard disk node needs to be moved to the position corresponding to the stop point 2 by the lifting unit 2. That is, the lowest position of the hard disk node 3 is located at the stop point 2 (at this time, the third hard disk group and the fourth hard disk group are both inside the chassis of the storage server 11). Since the location information of the target hard disk group and the target hard disk node where the hard disk 5 in the faulty state is located has been stored in the encoding information, it is necessary to obtain the real-time location information of the target hard disk node and compare the real-time location information of the target hard disk node with the encoding information. When the real-time location information of the target hard disk node is consistent with the encoding information, it means that the target hard disk node has been moved into place. At this time, the hard disk 5 in the faulty state is exposed in the chassis of the storage server 11, which is convenient for maintenance personnel to perform maintenance.

[0092] The maintenance method of this application enables the lifting unit 2 to automatically lift the hard disk node 3 to the corresponding position, so that the hard disk group 4 in the faulty state is exposed in the chassis of the storage server 11, while the hard disk 5 in the normal state is located inside the chassis of the storage server 11, thereby effectively improving heat dissipation efficiency and maintenance efficiency.

[0093] In one embodiment, when controlling the lifting unit 2 to move the target hard disk node, the method further includes:

[0094] In response to the output signal of the stop switch 7 being 1, a start command is sent to the photoelectric sensor 8 to start the photoelectric sensor 8 to detect the positioning mark 6;

[0095] When the stop switch 7 is in the compressed state, the output signal of the stop switch 7 is 0; when the stop switch 7 is in the free state, the output signal of the stop switch 7 is 1.

[0096] Specifically, when the stop switch 7 is in the compressed state, its output signal is 0; when it is in the free state, its output signal is 1. Therefore, when the lifting unit 2 moves the target hard disk node, the target hard disk node moves, and the stop switch 7 below it changes from the compressed state to the free state. The output signal of the stop switch 7 changes from 0 to 1. When the output signal of the stop switch 7 changes from 0 to 1, a start command is sent to the photoelectric sensor 8 to activate the photoelectric sensor 8 to detect the positioning mark 6, thereby obtaining the position information of the target hard disk node through the detection result of the positioning mark 6.

[0097] In one embodiment, obtaining the real-time location information of the target hard disk node includes:

[0098] Receive the output signal of the photoelectric sensor 8, and determine the number of periodic changes of the output signal of the photoelectric sensor 8 based on the output signal of the photoelectric sensor 8;

[0099] The number of cycles is used as the real-time location information of the target hard disk node;

[0100] When the photoelectric sensor 8 is aligned with the positioning mark 6, the output signal of the photoelectric sensor 8 is 0; when the photoelectric sensor 8 is not aligned with the positioning mark 6, the output signal of the photoelectric sensor 8 is 1.

[0101] Specifically, when photoelectric sensor 8 is aligned with positioning marker 6, its output signal is 0; when they are misaligned, its output signal is 1. Therefore, when the target hard disk node is at the lowest point of the storage server 11 chassis, photoelectric sensor 8 is aligned with positioning marker 6, and its output signal is 0; when lifting unit 2 moves the target hard disk node, photoelectric sensor 8 is misaligned, and its output signal is 1. Thus, the number of periodic changes in the output signal of photoelectric sensor 8 can be obtained, and the real-time position information of the target hard disk node can be reflected by the number of periodic changes in photoelectric sensor 8.

[0102] In one embodiment, the number of photoelectric sensors 8 is one, and determining the number of periodic changes in the output signal of the photoelectric sensor 8 includes:

[0103] The number of cycles in which the output signal of the photoelectric sensor 8 changes from 1 to 0 is determined.

[0104] Specifically, there is one photoelectric sensor 8, and the positioning mark 6 corresponds one-to-one with the photoelectric sensor 8, so there is one positioning mark 6. When the lifting unit 2 does not lift the target hard disk node, the photoelectric sensor 8 is aligned with the positioning mark 6, and the output signal of the photoelectric sensor 8 is 0. When the lifting unit 2 lifts the target hard disk node, the photoelectric sensor 8 is not aligned with the positioning mark 6, and the output signal of the photoelectric sensor 8 changes from 0 to 1. When the photoelectric sensor 8 is aligned with the next positioning mark 6, the output signal of the photoelectric sensor 8 changes from 1 to 0. Therefore, if there is only one photoelectric sensor 8, the number of times the output signal of the photoelectric sensor 8 changes from 1 to 0 is recorded. That is, when the number of times the output signal of the photoelectric sensor 8 changes from 1 to 0 is 1, it means that the target hard disk node is located at the stop point 1, the first hard disk group is exposed outside the chassis of the storage server 11, and the second, third, and fourth hard disk groups are all inside the chassis of the storage server 11. When the number of times the output signal of the photoelectric sensor 8 changes from 1 to 0 is 2, it means that the target hard disk node is located at the stop point 2, the first and second hard disk groups are exposed outside the chassis of the storage server 11, and the third and fourth hard disk groups are all inside the chassis of the storage server 11, and so on.

[0105] In one embodiment, the photoelectric sensor 8 includes a first photoelectric sensor and a second photoelectric sensor, with the first photoelectric sensor located below the second photoelectric sensor. Determining the number of periodic changes in the output signal of the photoelectric sensor 8 includes:

[0106] The number of cycles in which the output signal of the first photoelectric sensor changes from 1→0→1→0 is determined.

[0107] In one embodiment, determining the number of periodic changes in the output signal of the photoelectric sensor 8 includes:

[0108] Determine the number of cycles in which the output signal of the second photoelectric sensor changes from 1 to 0.

[0109] Specifically, such as Figure 3As shown, taking two photoelectric sensors 8 as an example, including a first photoelectric sensor and a second photoelectric sensor, the first photoelectric sensor is located below the second photoelectric sensor. Specifically, when the target hard disk node is not lifted by the lifting unit 2, the output signal of the stop switch 7 is 0, the output signal of the first photoelectric sensor is 0, the output signal of the second photoelectric sensor is 0, and the target hard disk node is located at the stop point 0; when the target hard disk node is lifted by the lifting unit 2 and both the first and second photoelectric sensors leave the stop point 0, the output signal of the stop switch 7 is 1, the output signal of the first photoelectric sensor changes from 0 to 1; the output signal of the second photoelectric sensor changes from 0 to 1 to 0 to 1. When the target hard disk node is pulled to stop point 1, the output signal of stop switch 7 is 1, the output signal of the first photoelectric sensor is 0, the output signal of the second photoelectric sensor is 0, and the target hard disk node is located at stop point 1; before the target hard disk node reaches stop point 1, the output signal of the first photoelectric sensor changes from 1→0→1→0; the output signal of the second photoelectric sensor changes from 1→0; when the target hard disk node is pulled to stop point 2, the output signal of stop switch 7 is 1, the output signal of the first photoelectric sensor is 0, the output signal of the second photoelectric sensor is 0, and the target hard disk node is located at stop point 2. Before the target hard disk node reaches stop point 2, the output signal of the first photoelectric sensor changes from 1→0→1→0; the output signal of the second photoelectric sensor changes from 1→0. When the target hard disk node is pulled to stop point 3, the output signal of the stop switch 7 is 1, the output signal of the first photoelectric sensor is 0, the output signal of the second photoelectric sensor is 0, and the target hard disk node is located at stop point 3. When the target hard disk node is pulled to stop point 4, the output signal of the stop switch 7 is 1, the output signal of the first photoelectric sensor is 0, the output signal of the second photoelectric sensor is 0, and the target hard disk node is located at stop point 4. From the above analysis, it can be seen that when there are two photoelectric sensors 8, the number of periodic changes in the output signal of the photoelectric sensors 8 can be determined in two ways: one is the number of periodic changes in the output signal of the first photoelectric sensor from 1→0→1→0, and the other is the number of periodic changes in the output signal of the second photoelectric sensor from 1→0.

[0110] In one embodiment, the step of controlling the lifting unit 2 to stop moving in response to the real-time position information of the target hard disk node being consistent with the encoded information includes:

[0111] The real-time location information of the target hard disk node is compared with the encoded information;

[0112] Specifically, the real-time position information of the target hard disk node is reflected by the change in the output signal of the photoelectric sensor 8, that is, the position of the target hard disk node when the lifting unit 2 moves the target hard disk node. The encoded information stores the position information of the target hard disk group where the faulty hard disk 5 is located and the target hard disk node, which is the destination position to be moved. Therefore, the real-time position information of the target hard disk node needs to be compared with the encoded information to determine whether the target hard disk node has been moved to the correct position.

[0113] When the real-time location information of the target hard disk node is consistent with the encoded information, the lifting unit 2 is controlled to stop moving the target hard disk node.

[0114] Specifically, the real-time location information of the target hard disk node is compared with the encoded information to determine whether the target hard disk node has been moved into place. When the real-time location information of the target hard disk node is consistent with the encoded information, it means that the target hard disk node has been moved into place. The lifting unit 2 needs to be controlled to stop moving the target hard disk node, and the maintenance personnel can then perform maintenance on the hard disk 5 that is in a faulty state.

[0115] In one embodiment, after the lifting unit 2 stops moving, the method further includes:

[0116] In response to the hard disk 5, which was in a faulty state, returning to normal, the lifting unit 2 is controlled to move the corresponding target hard disk node;

[0117] Specifically, after the baseboard management controller stops the lifting unit 2 from moving, the maintenance personnel maintain the hard drive 5 that is in a faulty state, repair or replace the faulty hard drive 5, so that the hard drive 5 in a faulty state returns to normal. When the baseboard management controller detects that the fault of the target hard drive group on the target hard drive node has disappeared and returned to normal, it controls the lifting unit 2 to move the corresponding target hard drive node, so that the target hard drive node returns to its initial position, that is, the target hard drive node returns to the chassis of the storage server 11 to continue to dissipate heat and cool down.

[0118] In response to the output signal of the stop switch 7 being 0, the lifting unit 2 is controlled to stop moving the corresponding target hard disk node.

[0119] Specifically, when the baseboard management controller controls the target hard disk node to move and restore its initial position, the stop switch 7 will be compressed by the inner wall of the storage server 11 chassis, and the output signal of the stop switch 7 will become 0. When the output signal of the stop switch 7 becomes 0, it means that the target hard disk node has been moved into place and restored to its initial position. Then the baseboard management controller stops moving the target hard disk node and completes the maintenance operation.

[0120] In one embodiment, the method further includes:

[0121] The alarm color of the corresponding alarm light is determined based on the location information of the target hard disk node, and a corresponding alarm command is generated.

[0122] Specifically, to facilitate a clear understanding of the hard disks 5 on storage server 11, alarms are triggered based on the location information of the target hard disk nodes to determine the status of the corresponding hard disk group 4. Specifically, the alarm color for hard disk group 4 exposed within the storage server 11 chassis is red, while the alarm color for hard disk group 4 located inside the storage server 11 chassis is green. Different alarm colors generate corresponding alarm commands.

[0123] The alarm command is sent to the input / output controller to control the alarm light to turn on according to the alarm command.

[0124] Specifically, after generating the alarm command, the alarm command is sent to the input / output controller. The input / output controller communicates with the alarm light and controls the alarm light to perform the lighting operation according to the alarm command, so that the alarm light corresponding to hard disk group 4 displays the corresponding alarm color.

[0125] In one embodiment, the encoded information is stored in the register of the input / output controller. The encoded information includes an eight-bit register value. The lower four bits of the register value are the location information of the target hard disk group. The fifth bit of the register value is the output information of one of the photoelectric sensors 8. The sixth bit of the register value is the output information of the other photoelectric sensor 8. The seventh bit of the register value is the output information of the stop switch 7.

[0126] Specifically, as shown in Table 1, the encoded information is stored in the register of the input / output controller. For example, if a hard disk 5 in the second hard disk group of a certain hard disk node 3 is in a faulty state, the first and second hard disk groups need to be exposed to the chassis of the storage server 11 by the movement operation of the lifting unit 2 so that maintenance personnel can perform maintenance. At this time, the target hard disk node needs to be lifted to the stop point 2. The corresponding encoded information is 01000010 in the table. When the baseboard management controller controls the lifting unit 2 to move the target hard disk node, when the real-time position of the target hard disk node is consistent with the stop point information stored in the encoded information, the baseboard management controller controls the lifting unit 2 to stop moving. At this time, the target hard disk node is exactly located at the stop point 2.

[0127] Table 1 Encoding Information Table

[0128]

[0129]

[0130] It should be understood that, although Figure 5 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 5 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0131] Example 3

[0132] Reference Figure 6 As shown, Figure 6 This is a system architecture diagram of the maintenance system provided in the embodiments of this application.

[0133] The maintenance system of this embodiment includes:

[0134] The target determination module, in response to the fact that hard disk 5 in hard disk group 4 is in a fault state, determines the location information of the target hard disk group and the target hard disk node where the faulty hard disk 5 is located;

[0135] The target determination module is used to monitor the working status of hard disks 5 in each hard disk group 4 within the storage server 11 in real time. When any hard disk 5 is in a faulty state, it determines the location information of the hard disk group 4 and hard disk node 3 where the faulty hard disk 5 is located. That is, the specific address of the hard disk group 4 where the faulty hard disk 5 is located (called the specific address of the target hard disk group) and the specific location of the hard disk node 3 where the faulty hard disk 5 is located (called the specific location of the target hard disk node).

[0136] The information acquisition module is used to generate corresponding encoded information based on the target hard disk group and the target hard disk node location information, and send the encoded information to the lifting unit 2 to control the lifting unit 2 to move the target hard disk node;

[0137] After determining the location information of the target hard disk group and the target hard disk node, the information acquisition module generates corresponding encoded information based on the location information of the target hard disk group and the target hard disk node. The encoded information stores the location information of the target hard disk group and the target hard disk node where the hard disk 5 in the faulty state is located. The encoded information is stored in the register of the input / output controller. The input / output controller sends the encoded information to the baseboard management controller. After receiving the encoded information, the baseboard management controller sends a start command to the lifting unit 2. After receiving the start command, the lifting unit 2 starts and controls the movement of the target hard disk node.

[0138] The device control module is used to acquire the real-time location information of the target hard disk node, and in response to the real-time location information of the target hard disk node being consistent with the encoded information, controls the lifting unit 2 to stop moving.

[0139] The target hard disk node moves under the control of the lifting unit 2. It needs to be moved to the corresponding position. For example, if the location of the faulty hard disk 5 is the second hard disk group in the target hard disk node, then the target hard disk node needs to be moved to the position corresponding to the stop point 2 by the lifting unit 2. That is, the lowest position of the hard disk node 3 is located at the stop point 2 (at this time, the third hard disk group and the fourth hard disk group are both inside the chassis of the storage server 11). Since the location information of the target hard disk group and the target hard disk node where the faulty hard disk 5 is located has been stored in the encoding information, it is necessary to obtain the real-time location information of the target hard disk node through the device control module and compare the real-time location information of the target hard disk node with the encoding information. When the real-time location information of the target hard disk node is consistent with the encoding information, it means that the target hard disk node has been moved into place. At this time, the faulty hard disk 5 is exposed in the chassis of the storage server 11, which is convenient for maintenance personnel to perform maintenance.

[0140] For specific limitations regarding the maintenance system, please refer to the method limitations described above, which will not be repeated here. Each module in the aforementioned maintenance system can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in the computer device in hardware form, or stored in the memory of the computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0141] Example 4

[0142] This embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of a maintenance method.

[0143] This computer device can be a terminal, and its internal structure diagram can be as follows: Figure 7As shown, the computer device includes a processor, memory, network interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used to communicate with external terminals via a network connection. The computer programs are executed by the processor to implement maintenance methods. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0144] Those skilled in the art should understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0145] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the following steps:

[0146] In response to a disk in the disk group being in a fault state, determine the target disk group and the location information of the target disk node where the faulty disk is located;

[0147] Based on the location information of the target hard disk group and the target hard disk node, corresponding encoding information is generated, and a start command is issued to start the lifting unit, which moves the target hard disk node.

[0148] The real-time location information of the target hard disk node is obtained, and in response to the real-time location information of the target hard disk node being consistent with the encoded information, the lifting unit is controlled to stop moving.

[0149] Example 5

[0150] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, it performs the following steps:

[0151] In response to a disk in the disk group being in a fault state, determine the target disk group and the location information of the target disk node where the faulty disk is located;

[0152] Based on the location information of the target hard disk group and the target hard disk node, corresponding encoding information is generated, and a start command is issued to start the lifting unit, which moves the target hard disk node.

[0153] The real-time location information of the target hard disk node is obtained, and in response to the real-time location information of the target hard disk node being consistent with the encoded information, the lifting unit is controlled to stop moving.

[0154] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0155] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0156] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A liquid cooling device for a storage server, characterized in that, The liquid cooling device includes a liquid cooling pool (1) and a lifting unit (2). The storage server includes a baseboard management controller. The storage server (11) is placed in the liquid cooling pool (1). The storage server (11) is provided with multiple hard disk nodes (3). The lifting unit (2) is connected to the hard disk nodes (3) to lift the hard disk nodes (3). Each hard disk node (3) includes multiple hard disks (5). Each hard disk node (3) has a row of hard disks along a direction perpendicular to the direction in which the lifting unit (2) extracts the hard disk node (3). The disks (5) form a hard disk group (4). Multiple positioning marks (6) are provided on the inner wall of the chassis of the storage server (11) along the direction of the lifting unit (2) to extract the hard disk node (3). The position of the positioning mark (6) corresponds one-to-one with the position of the hard disk group (4) when the hard disk node (3) is not lifted by the lifting unit (2). Each hard disk node (3) is provided with a photoelectric sensor (8) for detecting the positioning mark (6). The baseboard management controller is communicatively connected to the photoelectric sensor (8) and the lifting unit (2).

2. The liquid cooling device for a storage server according to claim 1, characterized in that, Each of the hard disk nodes (3) is also provided with a stop switch (7). The liquid cooling device also includes an input / output controller for receiving signals from the photoelectric sensor (8). The substrate management controller is communicatively connected to the input / output controller, and the input / output controller is communicatively connected to the stop switch (7).

3. The liquid cooling device for a storage server according to claim 1, characterized in that, The hard disk node (3) includes a tray (9), on which a hard disk backplate (10) and the hard disk group (4) are provided. The tray (9) is slidably connected to the chassis of the storage server (11), and the lifting unit (2) is connected to the tray (9).

4. The liquid cooling device for a storage server according to claim 1, characterized in that, One photoelectric sensor (8) is provided, and one positioning mark (6) is provided corresponding to each of the hard disk groups (4). When the hard disk node (3) is not lifted by the lifting unit (2), the photoelectric sensor (8) is aligned with the positioning mark (6) at the bottom of the inner wall of the chassis of the storage server (11).

5. The liquid cooling device for a storage server according to claim 1, characterized in that, Two photoelectric sensors (8) are provided, and two positioning marks (6) are provided corresponding to each hard disk group (4). When one photoelectric sensor (8) is aligned with one of the positioning marks (6), the other photoelectric sensor (8) is aligned with the other positioning mark (6). The two photoelectric sensors (8) are arranged on the hard disk node (3) along the sliding direction of the hard disk node (3). When the hard disk node (3) is not lifted by the lifting unit (2), the two photoelectric sensors (8) are aligned with the two positioning marks (6) at the bottom of the inner wall of the chassis of the storage server (11). The two photoelectric sensors (8) are redundant to each other.

6. The liquid cooling device for a storage server according to claim 2, characterized in that, The stop switch (7) is located at the bottom of the hard disk node (3). When the hard disk node (3) is not pulled up by the lifting unit (2), the stop switch (7) is in a compressed state. When the hard disk node (3) is pulled up by the lifting unit (2), the stop switch (7) is in a free state.

7. The liquid cooling device for a storage server according to claim 2, characterized in that, The liquid cooling device also includes an alarm unit, which consists of multiple alarm lights, one of which corresponds to one of the hard disk groups (4). The alarm unit is communicatively connected to the input / output controller.

8. The liquid cooling device for a storage server according to any one of claims 1 to 7, characterized in that, The positioning mark (6) is a black Mylar film.

9. A maintenance method for a storage server using the liquid cooling device as described in any one of claims 1 to 8, characterized in that, The maintenance method includes: In response to a fault state of hard disk (5) in hard disk group (4), the location information of the target hard disk group and the target hard disk node where the hard disk (5) in the fault state is located is determined; Based on the location information of the target hard disk group and the target hard disk node, corresponding encoding information is generated, and a start command is issued to start the lifting unit (2), and the target hard disk node is moved through the lifting unit (2); The real-time location information of the target hard disk node is obtained, and in response to the real-time location information of the target hard disk node being consistent with the encoded information, the lifting unit (2) is controlled to stop moving.

10. The maintenance method according to claim 9, characterized in that, When moving the target hard disk node via the lifting unit (2), the method further includes: In response to the output signal of the stop switch (7) being 1, a start command is sent to the photoelectric sensor (8) to start the photoelectric sensor (8) to detect the positioning mark (6); When the stop switch (7) is in the compressed state, the output signal of the stop switch (7) is 0, and when the stop switch (7) is in the free state, the output signal of the stop switch (7) is 1.

11. The maintenance method according to claim 10, characterized in that, The step of obtaining the real-time location information of the target hard disk node includes: Receive the output signal of the photoelectric sensor (8), and determine the number of periodic changes of the output signal of the photoelectric sensor (8) based on the output signal of the photoelectric sensor (8); The number of cycles is used as the real-time location information of the target hard disk node; When the photoelectric sensor (8) and the positioning mark (6) are aligned, the output signal of the photoelectric sensor (8) is 0; when the photoelectric sensor (8) and the positioning mark (6) are not aligned, the output signal of the photoelectric sensor (8) is 1.

12. The maintenance method according to claim 11, characterized in that, The number of photoelectric sensors (8) is one, and determining the number of periodic changes in the output signal of the photoelectric sensor (8) includes: Determine the number of cycles in which the output signal of the photoelectric sensor (8) changes from 1 to 0.

13. The maintenance method according to claim 11, characterized in that, The photoelectric sensor (8) includes a first photoelectric sensor and a second photoelectric sensor, with the first photoelectric sensor located below the second photoelectric sensor. Determining the number of periodic changes in the output signal of the photoelectric sensor (8) includes: The number of cycles in which the output signal of the first photoelectric sensor changes from 1→0→1→0 is determined.

14. The maintenance method according to claim 13, characterized in that, Determining the number of periodic changes in the output signal of the photoelectric sensor (8) includes: Determine the number of cycles in which the output signal of the second photoelectric sensor changes from 1 to 0.

15. The maintenance method according to claim 9, characterized in that, The response that the real-time position information of the target hard disk node is consistent with the encoded information, controlling the lifting unit (2) to stop moving includes: The real-time location information of the target hard disk node is compared with the encoded information; When the real-time location information of the target hard disk node is consistent with the encoded information, the lifting unit (2) is controlled to stop moving the target hard disk node.

16. The maintenance method according to claim 10, characterized in that, After the lifting unit (2) stops moving, the method further includes: In response to the hard disk (5) in a faulty state returning to normal, the lifting unit (2) is controlled to move the corresponding target hard disk node; In response to the output signal of the stop switch (7) being 0, the lifting unit (2) is controlled to stop moving the corresponding target hard disk node.

17. The maintenance method according to claim 9, characterized in that, The method further includes: The alarm color of the corresponding alarm light is determined based on the location information of the target hard disk node, and a corresponding alarm command is generated. The alarm command is sent to the input / output controller to control the alarm light to turn on according to the alarm command.

18. The maintenance method according to claim 11, characterized in that, The encoded information is stored in the register of the input / output controller. The encoded information includes an eight-bit register value. The lower four bits of the register value are the location information of the target hard disk group. The fifth bit of the register value is the output information of one of the photoelectric sensors (8). The sixth bit of the register value is the output information of the other photoelectric sensor (8). The seventh bit of the register value is the output information of the stop switch (7).

19. A maintenance system for a liquid cooling device of a storage server as described in any one of claims 1 to 8, characterized in that, The maintenance system includes: The target determination module, in response to the hard disk (5) in the hard disk group (4) being in a fault state, determines the location information of the target hard disk group and the target hard disk node where the hard disk (5) in the fault state is located; The information acquisition module is used to generate corresponding encoded information based on the target hard disk group and the target hard disk node location information, and send the encoded information to the lifting unit (2) to control the lifting unit (2) to move the target hard disk node; The device control module is used to acquire the real-time location information of the target hard disk node, and in response to the real-time location information of the target hard disk node being consistent with the encoded information, controls the lifting unit (2) to stop moving.

20. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 9 to 18.

21. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program that, when executed by a processor, causes the processor to perform the steps of the method as described in any one of claims 9 to 18.

Images