Server
By introducing the front hard disk backplane, PCH, CPLD and BMC into the server, the level signal is used to determine the hard disk slot number and indicate the abnormal hard disk position through the identification light, the problem of the abnormal hard disk being unable to quickly locate the abnormal hard disk in the liquid-cooled cabinet is solved, and the positioning efficiency is improved.
Patent Information
- Application Number
- CN202510456187.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-11
- Publication Date
- 2025-07-25
AI Technical Summary
In liquid-cooled cabinets, the prior art cannot quickly and accurately determine the physical location of an abnormal hard disk, resulting in complex and time-consuming positioning.
By introducing the front hard disk backplane, PCH, CPLD and BMC into the server, the level signal of the power port is used to obtain the power port to determine the physical slot number of the hard disk slot. The BMC establishes the correspondence between the logical slot number and the physical slot number, and indicates the location of the abnormal hard disk through the identification light.
It realizes rapid and accurate positioning of abnormal hard disks in the liquid-cooled cabinet, without the need for additional hard disk indicators and server lifting operations, improving positioning efficiency.
Smart Images

Figure CN120371089A_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present application relate to the technical field of servers, and particularly to a server. Background Art
[0002] A server includes multiple hard disks, and each hard disk corresponds to a hard disk indicator light. When an abnormality occurs in a certain hard disk, the hard disk indicator light corresponding to the abnormal hard disk is controlled to emit light, so that the position of the abnormal hard disk in the server can be determined according to the lit hard disk indicator light, so as to perform abnormality processing.
[0003] Since a large amount of heat is generated when the server is working, in order to dissipate the heat of the server, the server is immersed in a liquid cooling cabinet to use the coolant in the liquid cooling cabinet to absorb the heat of the server, so as to achieve the purpose of dissipating the heat of the server. However, when the server is immersed in the liquid cooling cabinet, the hard disk indicator lights are usually blocked, and thus the position of the abnormal hard disk cannot be indicated by the hard disk indicator lights of the server immersed in the liquid cooling cabinet. When the server is immersed in the liquid cooling cabinet, how to quickly and accurately determine the position of the abnormal hard disk in the server is a problem to be solved. Summary of the Invention
[0004] In view of the above problems, the embodiments of the present application provide a server, which is used to solve the problem in the prior art that the physical position of the abnormal hard disk of the server immersed in the liquid cooling cabinet cannot be quickly and accurately determined.
[0005] According to one aspect of the embodiments of the present application, a server is provided. The server includes a front hard disk backplane, a Platform Controller Hub (PCH), a Complex Programmable Logic Device (CPLD), a Baseboard Management Controller (BMC), and an identification light. The front hard disk backplane is provided with n hard disk slots and n power ports in one-to-one correspondence. The n hard disk slots are installed with n hard disks, and each hard disk slot corresponds to a physical slot number and a logical slot number. The n power ports are respectively used to provide working power to the n hard disks, where n is a positive integer and n≥2. The CPLD is used to obtain the first level signals of the n power ports, and then send a control signal to the i-th power port to connect the i-th power port to the power supply and provide working power to the i-th hard disk. Then, the second level signals of the n power ports are obtained, where the i-th hard disk is installed in the i-th hard disk slot corresponding to the i-th power port, i is a positive integer and i≤n. The CPLD is further used to determine the physical slot number of the i-th hard disk slot according to the first level signals and the second level signals. The BMC is used to obtain the physical slot number of the i-th hard disk slot determined by the CPLD, and obtain the first hard disk information and the second hard disk information through the PCH, where the first hard disk information and the second hard disk information are the information of the n hard disks obtained by the CPLD before and after sending the control signal to the i-th power port respectively. The BMC is further used to determine the logical slot number of the i-th hard disk slot according to the first hard disk information and the second hard disk information, establish a corresponding relationship between the logical slot number and the physical slot number of the i-th hard disk slot, and store the logical slot number of the i-th hard disk slot, the physical slot number of the i-th hard disk slot, and the corresponding relationship between the two. The BMC is further used to, when the second hard disk information includes the abnormal information of the i-th hard disk, determine the physical slot number corresponding to the logical slot number of the i-th hard disk slot according to the corresponding relationship, and control the identification light to flash to indicate the physical slot number of the i-th hard disk slot through the identification light.
[0006] In an optional manner, the CPLD is used to perform an exclusive OR operation on the first level signals and the second level signals, determine the i-th power port whose level changes compared with the first level signals according to the result of the exclusive OR operation, and determine the physical slot number of the i-th hard disk slot corresponding to the i-th power port.
[0007] In an alternative manner, after the CPLD stores the physical slot number of the i-th hard disk slot into a register in the CPLD, the CPLD sends an information acquisition signal to the BMC, where the information acquisition signal is used to prompt the BMC to acquire the second hard disk information; the BMC is used to acquire the second hard disk information through the PCH after receiving the information acquisition signal.
[0008] In an alternative manner, the information acquisition signal is further used to prompt the BMC to read the data stored in the register; the BMC is used to read the data stored in the register after receiving the information acquisition signal, so as to acquire the physical slot number of the i-th hard disk slot.
[0009] In an alternative manner, the n hard disk slots are hard disk slots arranged in multiple rows and multiple columns, and the identification lights include a first light-emitting diode and a second light-emitting diode; when the second hard disk information includes the abnormal information of the i-th hard disk, the BMC is used to determine the physical slot number corresponding to the logical slot number of the i-th hard disk slot according to the corresponding relationship, and control the first light-emitting diode to flash to indicate the position of the i-th hard disk slot in the rows of the multiple rows, and control the second light-emitting diode to flash to indicate the position of the i-th hard disk slot in the columns of the multiple columns, so as to indicate the physical slot number of the i-th hard disk slot.
[0010] In an alternative manner, the BMC is used to control the number of times the first light-emitting diode flashes to indicate the position of the i-th hard disk slot in the rows of the multiple rows; the BMC is used to control the number of times the second light-emitting diode flashes to indicate the position of the i-th hard disk slot in the columns of the multiple columns.
[0011] In an alternative manner, the anode of the first light-emitting diode and the cathode of the second light-emitting diode are connected to the power supply through a first resistor; the anode of the first light-emitting diode and the cathode of the second light-emitting diode are connected to a first control pin of the BMC through a second resistor; the cathode of the first light-emitting diode and the anode of the second light-emitting diode are connected to a second control pin of the BMC through a third resistor; the cathode of the first light-emitting diode and the anode of the second light-emitting diode are connected to the power supply through the third resistor and a fourth resistor, where the third resistor and the fourth resistor are connected in series; the first control pin is used to output a high-level signal and the second control pin is used to output a low-level signal to make the first light-emitting diode emit light; the first control pin is used to output a low-level signal and the second control pin is used to output a high-level signal to make the second light-emitting diode emit light.
[0012] In an alternative manner, the server is used to be installed in a liquid-cooled cabinet, and multiple servers are installed in the liquid-cooled cabinet; the BMC is further used to indicate the server from the multiple servers by controlling the first light-emitting diode to be in a constantly-on state.
[0013] In an alternative manner, the server further includes a server indication button; the BMC is used to respond to the operation of the server indication button being selected, control the first control pin to output a high-level signal and control the second control pin to output a low-level signal, so that the first light-emitting diode is in the constantly-on state, to indicate the server from the multiple servers.
[0014] In an alternative manner, after obtaining the second hard disk information, the BMC is further used to send a completion signal to the CPLD; the CPLD is used to receive the completion signal and send the control signal to the next power port.
[0015] In the embodiments of the present application, by re-determining the correspondence between the physical slot numbers and the logical slot numbers of each hard disk slot, when a hard disk installed in the hard disk slot corresponding to a certain logical slot number is abnormal, through this correspondence, the physical slot number of the hard disk slot where the abnormal hard disk is located can be accurately determined. And by using the identification lights of the server to indicate the position of the abnormal hard disk, there is no need to additionally set multiple hard disk indicator lights, nor to lift the server out of the liquid-cooled cabinet and then locate the abnormal hard disk according to the hard disk indicator lights of the server, so that the position of the abnormal hard disk can be quickly determined.
[0016] The above description is only an overview of the technical solutions of the embodiments of the present application. In order to be able to understand the technical means of the embodiments of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the embodiments of the present application more obvious and understandable, the following specifically illustrates the embodiments of the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] The drawings are only used to illustrate the embodiments and are not considered to limit the present application. And throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:
[0018] Figure 1 A schematic diagram of a server provided by an embodiment of the present application is shown. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0019] The exemplary embodiments of the present application will be described in more detail below with reference to the drawings. Although the exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein.
[0020] The backplane of the front hard disk in the server is provided with multiple hard disk slots for installing hard disks. A hard disk indicator is provided on the front panel of the server chassis to indicate the status of the hard disk. When multiple hard disks are installed in the server, if a certain hard disk malfunctions, the hard disk indicator corresponding to the abnormal hard disk can be controlled to emit light, so that the position of the abnormal hard disk in the server can be determined according to the lit hard disk indicator, so as to perform abnormal processing.
[0021] In order to ensure the sealing performance of the immersion liquid cooling cabinet to keep the coolant clean and prevent evaporation, the immersion liquid cooling cabinet is usually provided with only one opening for putting the server into and taking out of the liquid cooling cabinet. In order to facilitate the server placed in the liquid cooling cabinet to access the working power supply, when the server is put into the liquid cooling cabinet, the side with the power interface of the server is usually placed facing the opening direction of the liquid cooling cabinet, so that the working power supply can still be accessed from the outside after the server is immersed in the coolant.
[0022] However, since the front panel of the server chassis and the power interface of the server are located on different sides of the server respectively, when the server is immersed in the liquid cooling cabinet, the front panel of the chassis may face the inside of the cabinet instead of the opening direction. This will cause the hard disk indicator on the front panel to be blocked by the structure of the liquid cooling cabinet or the coolant, so that the status of the hard disk indicator cannot be directly observed, and the physical position of the abnormal hard disk cannot be determined according to the hard disk indicator on the front panel.
[0023] When a hard disk in the server immersed in the liquid cooling cabinet malfunctions, in order to locate the position of the abnormal hard disk, the server can be powered off first, and the server can be lifted from the liquid cooling cabinet filled with coolant by a gantry crane. Then, after the coolant is drained, the server is placed in a position where the hard disk light on the front panel can be viewed, and the server is powered on again. The operation and maintenance personnel then perform the hard disk lighting operation through the hard disk lighting instruction method of the remote management interface to light the hard disk indicator corresponding to the abnormal hard disk. Then the staff can confirm the position of the lit hard disk indicator to locate the position of the abnormal hard disk and perform abnormal processing operations such as hard disk replacement. However, the above operation of locating the position of the abnormal hard disk is relatively complex and time-consuming.
[0024] The power interface of the server is usually set on the rear panel. In order to quickly locate the position of the abnormal hard disk, if multiple hard disk indicators are set on the rear panel to indicate each hard disk respectively, it will increase the cost of the indicators, and also increase the complexity of laying out and wiring for the added hard disk indicators on the rear panel. And due to the limited space in the design of the rear window structure of the server, it is difficult to display the newly set multiple hard disk indicators.
[0025] The rear panel of the server is provided with a Unit Identification (UID) light, which is the identification light of the server and is used to indicate the status of the server or identify the unique identity of the server. Since the identification light faces the opening of the liquid-cooled cabinet when the server is immersed in the liquid-cooled cabinet, the staff can directly see the identification light. If the identification light can be used to indicate the location of the abnormal hard disk, the problem of being unable to quickly determine the location of the abnormal hard disk in the server can be solved.
[0026] Hard disks are installed in hard disk slots, and each hard disk slot corresponds to a physical slot number and a logical slot number. Among them, the physical slot number represents the physical location of the hard disk slot in the server. For example, if there are 12 hard disk slots on the front hard disk backplane, the physical slot numbers corresponding to these 12 hard disk slots are 0 to 11 respectively, and each hard disk slot is distinguished by a different physical slot number. The logical slot number is the number assigned to the hard disk slot by the operating system or management software. For example, the logical slot numbers corresponding to 12 hard disk slots are slot ID0 to slot ID11 respectively. The wiring method between the backplane SAS / SATA interface and the motherboard SAS / SATA port will affect the correspondence between the logical slot number and the physical slot number of the hard disk slot. If the backplane is connected to the motherboard not in the order of the physical slot number and the logical slot number, then the order of the logical slot number and the physical slot number of the hard disk slot is different. For example, if the SAS / SATA interface controlling the fifth hard disk slot on the backplane is connected to the first SAS / SATA interface on the motherboard, then the logical slot number corresponding to the hard disk slot with the physical slot number 4 is slot ID0, that is, the logical slot number corresponding to the hard disk slot with the physical slot number 4 is not slot ID4. Therefore, after obtaining the logical slot number of the abnormal hard disk, how to accurately determine the location of the abnormal hard disk is also a problem that needs to be solved.
[0027] Based on this, an embodiment of the present application proposes a server, which includes a front hard disk backplane, a Platform Controller Hub (PCH), a Complex Programmable Logic Device (CPLD), a Baseboard Management Controller (BMC), and an identification light. The front hard disk backplane is provided with a plurality of hard disk slots and a plurality of power ports in one-to-one correspondence. Each hard disk slot is installed with a hard disk, and each hard disk slot corresponds to a physical slot number and a logical slot number. The CPLD sequentially sends control signals to each power port to enable each power port to access power and provide working power to the hard disk installed in the corresponding hard disk slot, so as to respectively determine the physical slot numbers of each hard disk slot according to the change of the level signals of all power ports before and after the hard disk is powered on. The BMC obtains the hard disk information before and after the hard disk is powered on determined by the CPLD through the PCH, respectively determines the logical slot numbers of each hard disk slot according to the obtained hard disk information, and establishes a corresponding relationship between the physical slot numbers and the logical slot numbers of each hard disk slot. Subsequently, when an abnormality occurs in a certain hard disk, after obtaining the logical slot number of the hard disk slot where the abnormal hard disk is located, the physical slot number of the abnormal hard disk slot can be determined according to the logical slot number of the hard disk slot where the abnormal hard disk is located and this corresponding relationship, and the identification light is controlled to flash, so as to indicate the physical slot number of the hard disk slot where the abnormal hard disk is located through the identification light, thereby positioning the location of the abnormal hard disk.
[0028] Figure 1 shows a schematic diagram of the server provided by the embodiment of the present application. As Figure 1 shown, the server includes a front hard disk backplane, a PCH, a CPLD, a BMC, and an identification light. Among them, the front hard disk backplane is provided with three hard disk slots and three power ports in one-to-one correspondence, namely the first hard disk slot, the second hard disk slot, and the third hard disk slot, and the first power port, the second power port, and the third power port. The first hard disk slot, the second hard disk slot, and the third hard disk slot are respectively installed with a first hard disk (not shown in the figure), a second hard disk (not shown in the figure), and a third hard disk (not shown in the figure). Among them, the physical slot numbers of the first hard disk slot, the second hard disk slot, and the third hard disk slot are 0, 1, and 2 respectively.
[0029] In order to establish the correspondence between the physical slot number and the logical slot number of the first hard disk slot (any one of the first hard disk slot, the second hard disk slot, and the third hard disk slot), the CPLD first obtains the first level signal of the three power supply ports and stores the first level signal in register b. At this time, since the CPLD has not powered on any of the three power supply ports, the level signal of each power supply port is at a low level, that is, the first level signal is 000. Then the CPLD sends a control signal to the first power supply port (any one of the first power supply port, the second power supply port, and the third power supply port) to enable the first power supply port to access power and provide working power to the corresponding hard disk. After that, the CPLD obtains the second level signal of the three power supply ports and stores the second level signal in register a. Since only the first power supply port is powered on at this time, and the level signal is at a high level after the power supply port is powered on, the level signal corresponding to the first power supply port in the second level signal is a high level signal at this time. Then, by performing an exclusive OR operation on the first level signal and the second level signal to compare the first level signal stored in register b and the second level signal stored in register a, it can be known which power supply port among the first power supply port, the second power supply port, and the third power supply port the first power supply port is, and thus the physical slot number of the first hard disk slot corresponding to the first power supply port can be known. For example, if the first power supply port is the first power supply port, the second level signal is 001. By performing an exclusive OR operation on the first level signal and the second level signal, it is found that only the level signal corresponding to the first power supply port changes according to the result of the exclusive OR operation. Therefore, it can be determined that the first power supply port is the first power supply port, and the hard disk slot corresponding to the first power supply port is the first hard disk slot. Thus, the physical slot number of the first hard disk slot can be determined to be 0. After the CPLD determines the physical slot number of the first hard disk slot, it transmits the physical slot number of the first hard disk slot to the BMC.
[0030] Before and after the CPLD powers on the first power supply port, the PCH reads the first hard disk information and the second hard disk information of the three hard disks through the SATA / SAS interface. The hard disk information includes the logical slot number of the first hard disk slot where the hard disk is located. When a hard disk fails, the hard disk information also includes the fault code of the hard disk. After the PCH reads the first hard disk information and the second hard disk information, it transmits them to the BMC through the Enhanced Serial Peripheral Interface (ESPI) pins.
[0031] Since the PCH can only read the information of the hard disk after the hard disk is connected to the working power supply. Therefore, before the CPLD powers on the first power supply port, since no hard disk is connected to the working power supply, the first hard disk information does not include any information, and the second hard disk information includes the information of the first hard disk (one of the first, second, and third hard disks) corresponding to the first power supply port. After the BMC receives the second hard disk information transmitted by the PCH, that is, after obtaining the logical slot number of the first hard disk slot, it can establish a correspondence between the logical slot number of the first hard disk slot and the physical slot number of the first hard disk slot obtained above, and store the logical slot number, physical slot number of the first hard disk slot, and the correspondence between the two.
[0032] In order to enable the BMC to obtain the second hard disk information through the PCH in a timely manner, after the CPLD determines the physical slot number of the hard disk slot, it stores the currently determined physical slot number of the hard disk slot in register c, and sends an information acquisition signal to the BMC. After receiving the information acquisition signal, the BMC reads the data in register c through the I2C link and obtains the second hard disk information through the PCH. Or after the CPLD stores the currently determined physical slot number of the hard disk slot in register c, the BMC periodically reads the data in register c to obtain the currently determined physical slot number of the hard disk slot.
[0033] In order to establish the correspondence between the physical slot numbers and logical slot numbers of each hard disk slot as soon as possible, after the BMC obtains the second hard disk information through the PCH, the BMC sends a completion signal to the CPLD. The CPLD receives the completion signal and sends a control signal to the next power supply port to establish the correspondence between the physical slot number and logical slot number of the next hard disk slot.
[0034] In order to establish the correspondence between the physical slot number and logical slot number of the second hard disk slot. On the basis of the above, the CPLD first clears the data in register b, stores the data in register a in register b, and clears the data in register a. Then the CPLD continues to send a control signal to the second power supply port (any one of the remaining two unpowered power supply ports) to enable the second power supply port to be connected to the power supply and provide working power to the corresponding hard disk. After that, the CPLD obtains the level signals of the three power supply ports and stores them in register a.
[0035] Since the first power supply port and the second power supply port are powered on this time, compared with the last time, the second power supply port is powered on additionally. Therefore, at this time, one of the level signals stored in register a and register b is different from the level signal corresponding to the power supply port. Furthermore, the second power supply port can be determined based on the difference between the level signals stored in register a and register b, and the physical slot number of the second hard disk slot corresponding to the second power supply port can be determined. For example, if the level signal stored in register a is 011 and the level signal stored in register b is 001, then the second power supply port can be determined as the second power supply port based on the difference between the level signals stored in register a and register b, that is, the second hard disk slot corresponding to the second power supply port is the second hard disk slot. Thus, the physical slot number of the second hard disk slot can be determined as 1. After the CPLD determines the physical slot number of the second hard disk slot, it transmits the physical slot number of the second hard disk slot to the BMC.
[0036] After the CPLD powers on the second power supply port, the PCH reads the hard disk information of the three hard disks through the SATA / SAS interface and transmits it to the BMC through the ESPI pin. Since both the first hard disk and the second hard disk are connected to the working power supply currently, the hard disk information read by the PCH at this time includes the hard disk information of the first hard disk and the hard disk information of the second hard disk. After receiving the latest hard disk information transmitted by the PCH, the BMC determines the logical slot number of the second hard disk slot by comparing the latest received hard disk information with the hard disk information received last time, which has increased the hard disk information of the second hard disk. Then the BMC can establish a corresponding relationship between the logical slot number of the second hard disk slot and the physical slot number of the second hard disk slot obtained above, and store the logical slot number, physical slot number of the second hard disk slot, and the corresponding relationship between the two.
[0037] It should be noted that the principle and specific method of establishing the corresponding relationship between the physical slot number and the logical slot number of the third hard disk slot are the same as those of establishing the corresponding relationship between the physical slot number and the logical slot number of the second hard disk slot described above. Therefore, the principle and specific method of establishing the corresponding relationship between the physical slot number and the logical slot number of the third hard disk slot can be referred to the principle and specific method of establishing the corresponding relationship between the physical slot number and the logical slot number of the second hard disk slot described above, and will not be elaborated here.
[0038] In the embodiment of the present application, through the above method, the corresponding relationship between the physical slot number and the logical slot number of each hard disk slot can be accurately determined.
[0039] It should be noted that in the embodiments of the present application, only a server including three power ports, hard disk slots, and hard disks is taken as an example for introduction, and it does not limit the number of power ports, hard disk slots, and hard disks. The server may also include two power ports, hard disk slots, and hard disks, or include four or more power ports, hard disk slots, and hard disks.
[0040] The identification light is the aforementioned UID light, including a first light-emitting diode LED1 and a second light-emitting diode LED2. For the convenience of distinguishing the first light-emitting diode LED1 and the second light-emitting diode LED2.
[0041] The anode of the first light-emitting diode LED1 and the cathode of the second light-emitting diode LED2 are connected to the power supply VDD through a first resistor (including resistor R1 and resistor R3). The anode of the first light-emitting diode LED1 and the cathode of the second light-emitting diode LED2 are connected to the first control pin (GPIO pin) of the BMC through a second resistor (including resistor R3). The cathode of the first light-emitting diode LED1 and the anode of the second light-emitting diode LED2 are connected to the second control pin (UID pin) of the BMC through a third resistor (including resistor R4). The cathode of the first light-emitting diode LED1 and the anode of the second light-emitting diode LED2 are connected to the power supply VDD through a third resistor (including resistor R2) and a fourth resistor (including resistor R4).
[0042] When multiple hard disks are simultaneously connected to the working power supply, the hard disk information obtained by the BMC through the PCH includes multiple copies of hard disk information, with each hard disk corresponding to one copy of hard disk information. Each copy of hard disk information includes the logical slot number of the hard disk slot where the corresponding hard disk is located. When a hard disk is abnormal, the hard disk information corresponding to the abnormal hard disk will also include a fault code. In order to be able to monitor whether a hard disk is abnormal, the BMC can regularly obtain the hard disk information through the PCH to timely determine whether a hard disk is abnormal.
[0043] When a certain hard disk is abnormal, the BMC determines the physical slot number of the hard disk slot where the abnormal hard disk is located according to the logical slot number in the hard disk information corresponding to the abnormal hard disk and the corresponding relationship between the logical slot number and the physical slot number stored by it, and then controls the first light-emitting diode LED1 to blink or the second light-emitting diode LED2 to blink, so as to indicate the physical slot number of the hard disk slot where the abnormal hard disk is located through the blinking light-emitting diode, thereby achieving the purpose of positioning the abnormal hard disk and facilitating the staff to perform abnormal processing.
[0044] For example, if the hard disks on the front hard disk backplane in the server are all in the same row (or the same column), the BMC can indicate the position of the hard disk slot where the abnormal hard disk is located by controlling the number of times the first light-emitting diode LED1 or the second light-emitting diode LED2 flashes. For example, if the third hard disk is abnormal, the BMC can control the first light-emitting diode LED1 or the second light-emitting diode LED2 to flash three times in total to indicate that the third hard disk is abnormal.
[0045] Alternatively, the BMC can indicate the position of the hard disk slot where the abnormal hard disk is located by controlling the lighting duration of the first light-emitting diode LED1 or the second light-emitting diode LED2. For example, if the third hard disk is abnormal, the BMC can control the first light-emitting diode LED1 or the second light-emitting diode LED2 to have a lighting duration of 3s to indicate that the third hard disk is abnormal.
[0046] If multiple hard disks on the front hard disk backplane in the server are arranged in multiple rows and multiple columns, the BMC can indicate the row position of the hard disk slot where the abnormal hard disk is located by controlling the number of times the first light-emitting diode LED1 flashes, and indicate the column position of the hard disk slot where the abnormal hard disk is located by controlling the number of times the second light-emitting diode LED2 flashes, so as to indicate the position of the hard disk slot where the abnormal hard disk is located, for the purpose of locating the abnormal hard disk. Among them, when the GPIO pin of the BMC outputs a high-level signal and the UID pin outputs a low-level signal, the first light-emitting diode LED1 can be made to emit light. When the GPIO pin outputs a low-level signal and the UID pin outputs a high-level signal, the second light-emitting diode can be made to emit light. For example, if the hard disk in the third row and fourth column on the front hard disk backplane in the server is abnormal, the BMC can control the first light-emitting diode LED1 to flash three times to indicate that the hard disk slot where the abnormal hard disk is located is in the third row, and control the second light-emitting diode LED2 to flash four times to indicate that the hard disk slot where the abnormal hard disk is located is in the fourth column. Alternatively, the BMC can indicate the position of the hard disk slot where the abnormal hard disk is located by controlling the lighting duration of the first light-emitting diode LED1 and the second light-emitting diode LED2. For example, if the hard disk in the third row and fourth column on the front hard disk backplane in the server is abnormal, the BMC can control the first light-emitting diode LED1 to have a lighting duration of 3s to indicate that the hard disk slot where the abnormal hard disk is located is in the third row, and control the second light-emitting diode LED2 to have a lighting duration of 4s to indicate that the hard disk slot where the abnormal hard disk is located is in the fourth column.
[0047] Preferably, the first light-emitting diode LED1 and the second light-emitting diode LED2 are light-emitting diodes of two different colors, and the positions of the rows and columns of the hard disk slot where the abnormal hard disk is located are indicated by distinguishing the colors of the light-emitting diodes. For example, the first light-emitting diode LED1 is a red light LED. When the staff observes the flashing of the LED emitting red light, they can judge the position of the row of the hard disk slot where the abnormal hard disk is located accordingly. When the staff observes the flashing of the LED emitting green light, they can judge the position of the column of the hard disk slot where the abnormal hard disk is located accordingly. Of course, the first light-emitting diode LED1 and the second light-emitting diode LED2 can also be light-emitting diodes of the same color, and there is a label corresponding to each light-emitting diode near each light-emitting diode to identify whether the position indicated by each of them belongs to the row position or the column position.
[0048] In the embodiment of the present application, the position of the abnormal hard disk can be located by using the identification lights of the server, without the need to additionally set multiple hard disk indicator lights, nor to lift the server out of the liquid-cooled cabinet and then locate the abnormal hard disk according to the hard disk indicator lights of the server, thereby improving the efficiency of locating the abnormal hard disk.
[0049] As introduced above, each server has a UID light, and the server can be identified through the UID light of the server. When multiple servers are placed in the liquid-cooled cabinet, in order to distinguish each server, in the embodiment of the present application, the server further includes a server indication button, which can be manually pressed or remotely selected. When the staff manages multiple servers in the liquid-cooled cabinet and detects that a certain server is abnormal through monitoring, by selecting the server indication button of the abnormal server, the BMC in the abnormal server responds to the operation of the server indication button being selected, controls the GPIO pin to output a high-level signal and controls the UID pin to output a low-level signal, so that the first light-emitting diode LED1 is in a constant-on state, so that the staff can identify the abnormal server from multiple servers in the liquid-cooled cabinet.
[0050] In some embodiments, the operation and maintenance personnel can manage the "hard disk monitoring" function through the management interface. The hard disk monitoring function includes hard disk information, hard disk status, abnormal hard disk location, etc. Before the abnormal hard disk location function is enabled, the server location function needs to be turned off first to avoid conflicts in the flashing of the identification lights, and then the BMC controls the identification lights to flash to locate the position of the abnormal hard disk.
[0051] The server of the present application retains the traditional server UID positioning function, and supports manual pressing of the UID button or remote commands to switch between constant on / turn off. The default UID pin and GPIO pin maintain a high level. When the UID is pressed, a falling edge is triggered at UID_BTN. At this time, the BMC reverses the level of the UID pin, and the first light-emitting diode is constantly on. Pressing UID_BTN again triggers a falling edge. At this time, the BMC reverses the level of the UID pin, and the first light-emitting diode turns off.
[0052] The server of the present application also supports hot-swap of hard disks in the normal working state. When hot-swapping a hard disk, it will automatically detect the level status of the corresponding power supply port, compare it with the level status stored in the register, and determine the address bit where the level changes (the data in register a will automatically change according to the level changes of each power supply port at this time. After the data in register a changes, the CPLD compares the data in register b and register a, obtains the address value where the level changes, writes it into register c, and then synchronizes the data in register a to register b). Then, it obtains the hard disk information to obtain the logical slot number of the hard disk slot where the hard disk is located, and then updates the correspondence between the logical slot number and the physical slot number of the hard disk slot. The CPLD uses the Alert signal to remind the BMC to obtain the current hard disk information. When the power supply port level is enabled, the PCH will automatically obtain the current hard disk information from the hard disk backplane through the SATA / SAS interface. The BMC sends the obtained hard disk information (including the logical slot number of the hard disk slot and the fault code) through the ESPI data link. The BMC obtains the data in register c (such as 0x00) through the I2C data link, points to the physical slot number in the corresponding correspondence, and at the same time parses the hard disk information sent by the PCH, and writes the new hard disk slot ID into the logical slot number list in the mapping table.
[0053] It should be noted that the above embodiments illustrate the present application rather than limit the present application, and those skilled in the art can design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present application can be implemented by means of hardware including several different elements and by means of a properly programmed computer. In the claims listing several devices, several units or modules of these devices may be embodied by the same item of hardware. The use of the words first, second, and third, etc. does not denote any order. These words can be interpreted as names.
[0054] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation to the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.
Claims
1. A server, characterized in that, The server includes a front hard disk backplane, a Platform Controller Hub (PCH), a Complex Programmable Logic Device (CPLD), a Baseboard Management Controller (BMC), and an identification light; the front hard disk backplane is provided with n hard disk slots and n power ports in one-to-one correspondence, where n hard disks are installed in the n hard disk slots, and each hard disk slot corresponds to a physical slot number and a logical slot number. The n power ports are respectively used to provide operating power to the n hard disks, where n is a positive integer and n≥2; The CPLD is used to obtain the first level signals of the n power ports, and then send a control signal to the i-th power port to connect the i-th power port to the power supply and provide operating power to the i-th hard disk. Then, the second level signals of the n power ports are obtained, where the i-th hard disk is installed in the i-th hard disk slot corresponding to the i-th power port, and i is a positive integer and i≤n; The CPLD is further used to determine the physical slot number of the i-th hard disk slot according to the first level signals and the second level signals; The BMC is used to obtain the physical slot number of the i-th hard disk slot determined by the CPLD, and obtain first hard disk information and second hard disk information through the PCH, where the first hard disk information and the second hard disk information are respectively the information of the n hard disks obtained by the CPLD before and after sending the control signal to the i-th power port; The BMC is further used to determine the logical slot number of the i-th hard disk slot according to the first hard disk information and the second hard disk information, establish a corresponding relationship between the logical slot number and the physical slot number of the i-th hard disk slot, and store the logical slot number of the i-th hard disk slot, the physical slot number of the i-th hard disk slot, and the corresponding relationship between the two; The BMC is further used to, when the second hard disk information includes the abnormal information of the i-th hard disk, determine the physical slot number corresponding to the logical slot number of the i-th hard disk slot according to the corresponding relationship, and control the identification light to flash, so as to indicate the physical slot number of the i-th hard disk slot through the identification light; 2. The server according to claim 1, wherein The CPLD is used to perform an exclusive OR operation on the first level signals and the second level signals, determine the i-th power port whose level changes when the second level signal is compared with the first level signal according to the result of the exclusive OR operation, and determine the physical slot number of the i-th hard disk slot corresponding to the i-th power port; 3. The server according to claim 1, wherein, The CPLD is used to store the physical slot number of the i-th hard disk slot in a register in the CPLD, and then send an information acquisition signal to the BMC, where the information acquisition signal is used to prompt the BMC to acquire the second hard disk information; The BMC is used to acquire the second hard disk information through the PCH after receiving the information acquisition signal; 4. The server according to claim 3, wherein The information acquisition signal is further used to prompt the BMC to read the data stored in the register; After receiving the information acquisition signal, the BMC reads the data stored in the register to obtain the physical slot number of the i-th hard disk slot.
5. The server according to claim 1, wherein The n hard disk slots are arranged in multiple rows and columns, and the identification lights include a first light-emitting diode and a second light-emitting diode; When the second hard disk information includes the abnormal information of the i-th hard disk, the BMC determines the physical slot number corresponding to the logical slot number of the i-th hard disk slot according to the corresponding relationship, controls the first light-emitting diode to blink to indicate the position of the i-th hard disk slot in the multiple rows, and controls the second light-emitting diode to blink to indicate the position of the i-th hard disk slot in the multiple columns, so as to indicate the physical slot number of the i-th hard disk slot.
6. The server according to claim 5, wherein The BMC is used to control the number of times the first light-emitting diode blinks to indicate the position of the i-th hard disk slot in the multiple rows; The BMC is used to control the number of times the second light-emitting diode blinks to indicate the position of the i-th hard disk slot in the multiple columns.
7. The server according to claim 5, wherein The anode of the first light-emitting diode and the cathode of the second light-emitting diode are connected to the power supply through a first resistor; The anode of the first light-emitting diode and the cathode of the second light-emitting diode are connected to the first control pin of the BMC through a second resistor; The cathode of the first light-emitting diode and the anode of the second light-emitting diode are connected to the second control pin of the BMC through a third resistor; The cathode of the first light-emitting diode and the anode of the second light-emitting diode are connected to the power supply through the third resistor and a fourth resistor, where the third resistor and the fourth resistor are connected in series; The first control pin is used to output a high-level signal and the second control pin is used to output a low-level signal to make the first light-emitting diode emit light; The first control pin is used to output a low-level signal and the second control pin is used to output a high-level signal to make the second light-emitting diode emit light.
8. The server according to claim 7, wherein The server is used to be installed in a liquid-cooled cabinet, and multiple servers are installed in the liquid-cooled cabinet; The BMC is further used to indicate the server from the multiple servers by controlling the first light-emitting diode to be in a constantly-on state.
9. The server according to claim 8, wherein The server further includes a server indication button; The BMC is used to respond to the operation of selecting the server indication button, control the first control pin to output a high-level signal and control the second control pin to output a low-level signal to make the first light-emitting diode in the constantly-on state, so as to indicate the server from the multiple servers.
10. The server according to claim 1, characterized in that The BMC is further used to send a completion signal to the CPLD after obtaining the second hard disk information; The CPLD is used to receive the completion signal and send the control signal to the next power port.