Server management system and method, computer device, and storage medium

Abstract

The present application relates to the technical field of servers, and discloses a server management system and method, a computer device, and a storage medium. The system comprises: a baseboard management controller and a plurality of modules to be managed, wherein the baseboard management controller is arranged independently of a server motherboard, the baseboard management controller comprises a first target logic device, and each of said modules comprises a second target logic device; the baseboard management controller is interconnected to the server motherboard by means of a pluggable connector and is configured to send a power supply control signal to the second target logic devices by means of the first target logic device; the second target logic devices are configured to power up said modules on the basis of the power supply control signal; and the second target logic devices are also configured such that upon detecting that an in-place signal of the baseboard management controller is pulled high, the second target logic devices latch the power supply control signal previously sent by the baseboard management controller, so as to power up said modules on the basis of the latched power supply control signal.

Description

Server management system, methods, computer equipment and storage media

[0001] Cross-references to related applications

[0002] This application claims priority to Chinese Patent Application No. 202411028940.1, filed on July 30, 2024, entitled “Server Management System, Method, Computer Equipment and Storage Medium”, the entire contents of which are incorporated herein by reference. Technical Field

[0003] This application relates to the field of server technology, specifically to server management systems, methods, computer equipment, and storage media. Background Technology

[0004] In server products, the Baseboard Management Controller (BMC) is an indispensable component, used to manage the entire chassis.

[0005] With the development of cloud computing, to ensure high business reliability, many modules in servers are required to be designed to be hot-swappable, such as fan modules, power supply modules, and hard drive modules. By designing the modules in the server to be hot-swappable, maintenance personnel can replace and maintain the faulty components while the entire machine is still running normally when equipment malfunctions.

[0006] However, when the BMC malfunctions, maintenance personnel need to power off the entire machine, replace the BMC module, and then restart the service, resulting in low maintenance efficiency. Summary of the Invention

[0007] In a first aspect, this application provides a server management system, the system including: a baseboard management controller independently configured with the server motherboard and multiple modules to be managed, the baseboard management controller including a first target logic unit and the modules to be managed including a second target logic unit;

[0008] The baseboard management controller is interconnected with the server motherboard via a pluggable connector and is used to send power control signals to the second target logic in the module to be managed via the first target logic;

[0009] The second target logic unit is used to receive power control signals and power on the module to be managed based on the power control signals.

[0010] The second target logic unit is also used to identify the presence signal of the baseboard management controller. In response to the detection that the presence signal of the baseboard management controller is in a pulled-up state, it determines that the baseboard management controller is in a pulled-out state, latches the power control signal previously sent by the baseboard management controller, and powers on the module to be managed based on the latched power control signal.

[0011] In one alternative implementation, the substrate management controller further includes an in-situ module; the in-situ module is used for:

[0012] In response to the substrate management controller being in the unplugged state, the presence signal of the substrate management controller is updated to the pull-up state;

[0013] In response to the substrate management controller being in the inserted state, the presence signal of the substrate management controller is updated to the normal state.

[0014] In one alternative implementation, the module to be managed includes a fan module;

[0015] The second target logic unit corresponding to the fan module is used to control the fan module to operate at a safe speed in response to the detection that the on-premises signal of the baseboard management controller is in a high state.

[0016] In one alternative implementation, the substrate management controller is specifically used for:

[0017] After power-on, the power-on status of multiple modules to be managed is read. If the power-on status of multiple modules to be managed is not powered on, it is determined that the baseboard management controller has not been replaced. The power control signal is sent to the second target logic in the module to be managed through the first target logic.

[0018] In one alternative implementation, the substrate management controller is specifically used for:

[0019] After power-on, the power-on status of multiple modules to be managed is read. In response to the power-on status of multiple modules to be managed being powered on, the baseboard management controller is determined to be the replaced baseboard management controller. The status of the first target logic unit is updated to powered on, and the power control signal of the multiple modules to be managed in the first target logic unit is updated to the power-on status.

[0020] Send a latch release command to the second target logic unit;

[0021] The second target logic unit is used to receive latch release commands, and in response to the latch release commands, releases the power control signal of the latch and resumes the command receiving mode.

[0022] In an alternative implementation, the second target logic unit is further used for:

[0023] In response to the latch-based power control signal powering on the module to be managed and the presence signal of the baseboard management controller being detected as normal, it is determined whether a latch release command sent by the baseboard management controller has been received.

[0024] In response to the absence of a latch release command, the module under management continues to be powered on based on the latch power control signal.

[0025] In one alternative implementation, the module to be managed includes a fan module;

[0026] The baseboard management controller is also used for:

[0027] After the second target logic unit corresponding to the fan module releases the latched power control signal and resumes the command receiving mode, a fan control command is sent to the second target logic unit.

[0028] The second target logic unit corresponding to the fan module is used for:

[0029] Receive fan control commands and adjust the fan speed of the fan module based on the fan control commands.

[0030] In one alternative implementation, the baseboard management controller further includes a power soft-start module;

[0031] The power soft-start module is used to protect the power supply of the baseboard management controller the moment it is inserted into the server motherboard.

[0032] In one optional implementation, the baseboard management controller further includes: a signal isolation module;

[0033] The signal isolation module is used to protect the baseboard management controller from jitter the moment it is inserted into the server motherboard.

[0034] In an alternative implementation, the first target logic unit is further configured to:

[0035] Events where the on-state signal of the substrate management controller is high and events where the on-state signal of the substrate management controller is normal are recorded.

[0036] In an alternative implementation, the second target logic unit is further used for:

[0037] Whenever the presence signal of the substrate management controller is detected to be pulled high, the event of the presence signal of the substrate management controller being pulled high is recorded; and

[0038] Whenever the presence signal of the baseboard management controller is detected to be in a normal state, the event of the presence signal of the baseboard management controller being in a normal state is recorded.

[0039] Secondly, this application provides a server management method applied to a second target logic device in a module to be managed, the method comprising:

[0040] Receives power control signals sent by the baseboard management controller, which is independently configured from the server motherboard, through the first target logic unit;

[0041] Power on the module to be managed based on the power control signal; and

[0042] The presence signal of the baseboard management controller is identified. When the presence signal of the baseboard management controller is identified as being pulled high, it is determined that the baseboard management controller is in the unplugged state. The power control signal previously sent by the baseboard management controller is latched, and the module to be managed is powered on based on the latched power control signal.

[0043] The baseboard management controller includes a first target logic unit, and the baseboard management controller is interconnected with the server motherboard via a pluggable connector.

[0044] In one optional implementation, after power-on, the baseboard management controller reads the power-on status of multiple modules to be managed. In response to the power-on status of the multiple modules to be managed being powered on, it determines that the baseboard management controller is the replaced baseboard management controller, updates the status of the first target logic device to powered on, updates the power control signal of the multiple modules to be managed in the first target logic device to the power-on state, and sends a latch release command to the second target logic device. A server management method further includes: receiving a latch release command, releasing the latched power control signal in response to the latch release command, and restoring the command receiving mode.

[0045] In one optional implementation, a server management method further includes: powering on the module to be managed in response to a latch-based power control signal and identifying that the presence signal of the baseboard management controller is in a normal state, determining whether a latch release command sent by the baseboard management controller has been received; and continuing to power on the module to be managed based on the latch-based power control signal in response to not receiving a latch release command.

[0046] In one optional implementation, the module to be managed includes a fan module. After the baseboard management controller releases the latched power control signal from the second target logic unit corresponding to the fan module and resumes the command receiving mode, it sends a fan control command to the second target logic unit. A server management method further includes: receiving the fan control command and performing fan speed adjustment processing on the fan module based on the fan control command.

[0047] In one optional implementation, a server management method further includes: recording an event that the presence signal of the baseboard management controller is in a high state whenever the presence signal of the baseboard management controller is detected to be in a high state; and recording an event that the presence signal of the baseboard management controller is in a normal state whenever the presence signal of the baseboard management controller is detected to be in a normal state.

[0048] In one alternative implementation, the module to be managed includes a fan module; a server management method further includes: in response to recognizing that the presence signal of the baseboard management controller is in a high state, controlling the fan module to operate at a safe speed.

[0049] Thirdly, this application provides a computer device, including: a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to perform the server management method described in the second aspect.

[0050] Fourthly, this application provides one or more non-volatile computer-readable storage media storing computer-readable instructions, which, when executed by one or more processors, cause the one or more processors to perform the steps of the server management method as described in the third aspect above.

[0051] Fifthly, this application provides a computer program product, including computer instructions for causing a computer to execute the server management method described in the second aspect above. Attached Figure Description

[0052] To more clearly illustrate the technical solutions in the specific embodiments or related technologies of this application, the drawings used in the description of the specific embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0053] Figure 1 is a structural block diagram of a server management system according to one or more embodiments of this application;

[0054] Figure 2 is a structural block diagram of another server management system according to one or more embodiments of this application;

[0055] Figure 3 is a schematic flowchart of a server management method according to one or more embodiments of this application;

[0056] Figure 4 is a flowchart illustrating another server management method according to one or more embodiments of this application;

[0057] Figure 5 is a schematic diagram of the hardware structure of a computer device according to one or more embodiments of this application. Detailed Implementation

[0058] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0059] In addition to well-known components such as the Central Processing Unit (CPU), memory, hard drive, and network card, server products also include an indispensable module: the Baseboard Management Controller (BMC).

[0060] The primary function of the BMC (Body Control Controller) is chassis management, mainly handling server power-on / off actions, temperature monitoring of all modules within the server, and fan speed control. The BMC can adjust fan speeds based on varying temperature environments. It can also monitor the health of other server modules. When a device malfunctions, the BMC can issue alerts based on user needs, such as illuminating health indicator lights to show any abnormalities, or generating alarm logs. Even when the user is not physically present at the server, they can remotely log into the BMC's management interface to monitor for any anomalies and pinpoint their location.

[0061] In summary, the BMC is used to manage the entire server chassis and is an indispensable part of the server.

[0062] With the development of cloud computing, in order to ensure high reliability of business operations, many users require hot-swappable modules in server design. That is, many modules in the server are required to be designed to be hot-swappable. For example, fan modules, PSU power supplies, hard drives, and even PCIe cards such as network cards must support hot-swapping.

[0063] The advantage of designing hot-swappable modules in a server is that when a device malfunctions, maintenance personnel can replace and maintain the faulty component while the entire machine is running normally.

[0064] In related technologies, in server products, the BMC (Browser Controller Center) is designed on the same board as computing modules such as the CPU, Platform Controller Hub (PCH), and memory. When the BMC malfunctions, the entire board needs to be replaced, the entire machine's services need to be stopped, and the entire machine's power needs to be turned off. The board is replaced by disassembling the server to replace the BMC. After replacing the BMC, the system is restarted and the services can resume.

[0065] The existing technology cannot allow for arbitrary replacement of the BMC while it is powered on, resulting in low BMC maintenance efficiency and a significant impact on user experience. Replacing the BMC involves replacing the most critical board in the server, requiring the server to be taken off the rack for repair, which is time-consuming and costly.

[0066] This application provides a server management system that independently configures the baseboard management controller and the server motherboard, with the baseboard management controller interconnected to the server motherboard via a pluggable connector. When a second target logic unit detects that the baseboard management controller's presence signal is high, it determines that the baseboard management controller is in a disconnected state. At this time, the second target logic unit latches the power control signal previously sent by the baseboard management controller and powers on the managed module based on the latched power control signal. This allows for hot-swapping of the baseboard management controller without disassembling the server in case of a malfunction requiring maintenance, while ensuring the normal operation of other modules even when the baseboard management controller is disconnected, thus improving the maintenance efficiency of the baseboard management controller.

[0067] According to an embodiment of this application, a server management system is provided. Figure 1 is a structural block diagram of the server management system according to an embodiment of this application. As shown in Figure 1, the server management system includes a baseboard management controller 101 independently configured from the server motherboard and multiple modules to be managed 102. The baseboard management controller includes a first target logic unit, and the modules to be managed include a second target logic unit.

[0068] It should be noted that the target logic device can be a complex programmable logic device (CPLD). The baseboard management controller is set up independently from the server motherboard, that is, the BMC is separated from the server motherboard and designed as a separate board.

[0069] The baseboard management controller 101 is interconnected with the server motherboard via a pluggable connector and is used to send power control signals to a second target logic unit in the managed module via a first target logic unit.

[0070] The BMC board communicates with the server motherboard via a pluggable connector. Multiple manageable modules reside on independent boards. The BMC board is located in a separate pull-out box on the front or rear of the server, featuring hot-swappable slides and handles. Hot-swapping the BMC does not require disassembling the server; the BMC can be plugged or unplugged simply by operating the handle from the front or rear window.

[0071] It should be noted that the power control of the entire device by the baseboard management controller first sends the signal to the first target logic unit. Then, the general purpose I / O (GPIO) pins of the first target logic unit enable the power modules of other working modules. Only when the power modules of other modules are enabled and powered on can the other modules communicate with each other. In other words, the first target logic unit is the overall power management chip of the entire device. It connects the power management signal of the BMC, i.e., the power control signal, to the CPLD on the BMC board. The baseboard management controller sends the power control signal to the second target logic unit in the multiple managed modules 102 through the first target logic unit. Then, the CPLD in each managed module drives the power-on enable of each managed module, thereby realizing the power-on control of the managed modules.

[0072] The second target logic unit is used to receive the power control signal and power on the module to be managed based on the power control signal.

[0073] Among them, the second target logic unit in multiple modules to be managed is used to power on the modules to be managed based on the power control signal sent by the first target logic unit.

[0074] The second target logic unit is also used to identify the presence signal of the baseboard management controller. When the presence signal of the baseboard management controller is identified as being pulled high, it determines that the baseboard management controller is in the unplugged state, latches the power control signal previously sent by the baseboard management controller, and powers on the module to be managed based on the latched power control signal.

[0075] The baseboard management controller (BMC) features an on-premises signal, which is also connected to the second target logic unit of multiple managed modules. It's important to note that the on-premises signal is connected to ground on the BMC board, but connected to power in the managed modules. This design ensures that when the BMC is correctly installed and connected, its internal circuitry connects the on-premises signal line to ground, keeping the signal low. When the BMC is removed, no BMC is connected, pulling the on-premises signal low; the default on-premises signal is high.

[0076] When the second target logic unit of the module to be managed detects that the on-premises signal of the baseboard management controller is in a high state (i.e., high level), it determines that the baseboard management controller has been unplugged, latches the power control signal previously sent by the baseboard management controller, and powers on the module to be managed based on the latched power control signal.

[0077] It should be noted that the power control signal previously sent by the baseboard management controller may be the most recently received power control signal by the second target logic unit.

[0078] The server management system provided in this embodiment independently configures the baseboard management controller and the server motherboard. The baseboard management controller is interconnected with the server motherboard via a pluggable connector. In the event of a malfunction requiring maintenance of the baseboard management controller, the server does not need to be disassembled; the baseboard management controller can be hot-swapped directly. When the second target logic unit detects that the baseboard management controller's presence signal is high, it determines that the baseboard management controller is in a disconnected state. At this time, the second target logic unit latches the power control signal previously sent by the baseboard management controller and powers on the managed module based on the latched power control signal. This ensures the normal operation of other modules even when the baseboard management controller is disconnected, improving the maintenance efficiency of the baseboard management controller.

[0079] This embodiment provides a server management system. Figure 2 is a structural block diagram of the server management system according to an embodiment of this application. As shown in Figure 2, the server management system includes:

[0080] The baseboard management controller and multiple modules to be managed are set up independently from the server motherboard. The baseboard management controller includes a first target logic unit, and the modules to be managed include a second target logic unit.

[0081] The baseboard management controller interconnects with the server motherboard via a pluggable connector and is used to send power control signals to a second target logic unit in the managed module via a first target logic unit. For details, please refer to the baseboard management controller in the embodiment shown in Figure 1, which will not be repeated here.

[0082] The substrate management controller also includes an in-situ module (not shown in the figure). The in-situ module is used for:

[0083] When the Baseboard Management Controller (BMC) is in the unplugged state, the presence signal of the BMC is updated to a high state. That is, when the BMC malfunctions and needs to be unplugged, the presence signal from the BMC board to the managed module will be pulled high. After the second target logic unit of the managed module detects that the presence signal of the BMC board is pulled high, it recognizes that there is a malfunction in the BMC board, and the BMC is in the unplugged state.

[0084] When the substrate management controller is in the inserted state, update the substrate management controller's presence signal to the normal state.

[0085] When the baseboard management controller is in the inserted state, it indicates that the BMC is correctly installed and connected. The in-situ signal line is connected to the bottom line, so that the in-situ signal of the BMC is kept at a low level, which is the normal state.

[0086] The modules to be managed include the fan module. The second target logic unit corresponding to the fan module is used to control the fan module to operate at a safe speed when the presence signal of the baseboard management controller is detected to be high.

[0087] Specifically, when the second target logic unit corresponding to the fan module detects that the baseboard management controller is in a pulled-up state, it determines that the baseboard management controller is in a disconnected state. At this time, to ensure the normal operation of other managed modules, the second target logic unit corresponding to the fan module controls the fan module to operate at a safe speed. It should be noted that the second target logic unit corresponding to the fan module is a second target logic unit included within the fan module. The safe speed is set by technical personnel and is not specifically limited here.

[0088] Furthermore, Figure 2 illustrates the server management system using a pooled box (pooled area) as an example. This pooled box is a storage box. This box contains a BMC, hard drive modules and backplanes, fan modules and fan boards, a Serial Attached SCSI Expander (SAS Expander) module and expander board for expanding hard drives, and a power supply module and power board. The power board, SAS Expander module, and hard drive modules are not shown in the figure.

[0089] The fan board, hard drive backplane, and expander board each have a second target logic unit (CPLD). The CPLD on the fan board is mainly used for fan speed control, the CPLD on the hard drive backplane is mainly used for hard drive power-on / off control and hard drive indicator light control, and the CPLD on the expander board is generally used for power control and LED channel expansion. In this embodiment, the CPLDs on all other boards except the one on the BMC board are used as latching modules for power control signals from the BMC. When the presence signal of the baseboard management controller is detected as high, it determines that the baseboard management controller is in a disconnected state and latches the power control signals previously sent by the baseboard management controller.

[0090] Understandably, the BMC's CPLD is used to send multiple power control signals to the CPLDs on the fan board, power board, hard drive backplane, and Expander board, enabling each CPLD to power on and enable its respective module. In other words, the managed modules include the fan module, power module, hard drive module, and SAS Expander module. The first target logic unit sends multiple power control signals to the second target logic units of each managed module, causing the second target logic units to send enable signals to the corresponding power modules of the managed modules based on the power control signals, thus powering on the managed modules.

[0091] When the CPLD on the fan board detects that the BMC board has been removed (i.e., the baseboard management controller is in the removed state), it will control the fan module at a safe speed to ensure that other managed modules operate at normal temperatures. This design ensures that the power supply to other boards does not fail even after the BMC board is removed. The SAS Expander module and its board, hard drive module and its backplane, fan module and its board, and power module and its board continue to function normally, and the system's operations will not be interrupted.

[0092] The second target logic unit is used to receive the power control signal and power on the module to be managed based on the power control signal.

[0093] The second target logic unit is also used to identify the presence signal of the baseboard management controller. When the presence signal of the baseboard management controller is detected to be in a pulled-up state, it determines that the baseboard management controller is in a pulled-out state, latches the power control signal previously sent by the baseboard management controller, and powers on the module to be managed based on the latched power control signal. For details, please refer to the second target logic unit of the embodiment shown in Figure 1, which will not be described again here.

[0094] It should be noted that the second target logic unit is designed with a BMC status register, which is used to store the BMC's in-place state, such as the unplugged state or the normal state. This BMC status register can be easily modified by the BMC by issuing commands, and the latching state of the power control signal can be changed after modification.

[0095] When the BMC management module malfunctions and needs to be unplugged, the presence signal from the BMC board to other boards will go high. Upon detecting this high presence signal, the CPLDs on other boards recognize that the presence signal of the baseboard management controller is also high, confirming that the BMC board is malfunctioning and in a unplugged state. They then latch the control signal states previously received from the BMC board. At this time, the power control signals controlled by the BMC board to other boards will also change after the BMC board is unplugged. However, with the power control signal states latched, the CPLDs on other boards will ignore these power control signal changes and will not process them.

[0096] The server management system provided in this embodiment indicates whether the baseboard management controller is in a pulled-out state or an inserted state by the high state and normal state of the on-state signal. This determines whether the baseboard management controller sends a power control signal to the second target logic unit of the managed module to power on the managed module, or whether the second target logic unit powers on the managed module based on the latched power control signal.

[0097] When the second target logic unit corresponding to the fan module detects that the baseboard management controller is in a high state, it determines that the baseboard management controller has been unplugged. The second target logic unit then controls the fan module to operate at a safe speed to ensure the normal operation of other managed modules in the server and prevent the spread of faults caused by overheating of other managed modules.

[0098] In some alternative implementations, the substrate management controller is specifically used for:

[0099] After power-on, the power-on status of multiple modules to be managed is read. If the power-on status of multiple modules to be managed is not powered on, it is determined that the baseboard management controller has not been replaced. The power control signal is then sent to the second target logic in the module to be managed through the first target logic.

[0100] To ensure that the newly inserted baseboard management controller does not affect the normal operation of the modules to be managed, this embodiment does not immediately control the power-on operation of the modules to be managed after the baseboard management controller is powered on. The BMC first needs to contact the second target logic device on the modules to be managed through the Inter-Integrated Circuit (I2C) channel to read the current power-on and power-off states of the multiple modules to be managed. When the BMC detects that the power-on state of multiple modules to be managed is not power-on, it determines that the baseboard management controller has not been replaced, that is, the baseboard management controller is not the newly inserted baseboard management controller. Then, the BMC determines that it is not the newly inserted baseboard management controller. At this time, it performs power-on control on the multiple modules to be managed, that is, it sends a power control signal to the second target logic device among the multiple modules to be managed through the first target logic device, so that the second target logic device powers on the multiple modules to be managed based on the power control signal.

[0101] The server management system provided in this embodiment determines whether the baseboard management controller is a newly inserted baseboard management controller based on the power-on status of multiple managed modules after the baseboard management controller is powered on. If the power-on status of multiple managed modules is not powered on, it is determined that the baseboard management controller is not a newly inserted baseboard management controller. In this case, the power control signal is directly sent from the first target logic unit in the baseboard management controller to the second target logic unit in the managed module to achieve power-on control of the managed module. This ensures the accuracy of the power control signal sent by the baseboard management controller.

[0102] In some alternative implementations, the substrate management controller is specifically used for:

[0103] After power-on, the power-on status of multiple modules to be managed is read. If the power-on status of multiple modules to be managed is "power-on", the baseboard management controller is determined to be the replaced baseboard management controller. The status of the first target logic unit is updated to "power-on", and the power control signals of the multiple modules to be managed in the first target logic unit are updated to the power-on status.

[0104] Send a latch release command to the second target logic unit.

[0105] The second target logic unit is used to receive latch release commands, and in response to the latch release commands, releases the power control signal of the latch and resumes the command receiving mode.

[0106] Understandably, when the BMC and the first target logic unit disappear, according to the relevant technical description, the enable pin of the first target logic unit controlling the managed module will disappear, the enable function will also disappear, the power supply to the managed module will be turned off, the managed module will stop working, and the entire machine's services will stop. At this time, it is only necessary to lock the enable signal on the board where the managed module is located to ensure that the disappearance of the BMC does not affect the normal operation of other modules.

[0107] In other words, when a new BMC is inserted, the latching modules on other boards (i.e., the second target logic unit) cannot directly release the latched state, meaning they cannot release the latched power control signal. This is to prevent the managed module from mistaking the new enable signal in the BMC for a shutdown function, causing the managed module to power down and malfunction. Instead of directly releasing the latched state immediately after the new BMC is inserted, the second target logic unit waits until the BMC has started up. After the BMC identifies the powered-on state of the managed module, it no longer controls the managed module's power-on again, but only controls the power-on action of the board containing the BMC. Furthermore, the BMC sends a latch release command to the latch chip on the managed module board via a specific I2C channel. Upon receiving the latch release command, the latch chip in the managed module releases the latch and resumes normal command receiving mode. The second target logic unit receives the latch release command and, in response, releases the latched power control signal, resuming command receiving mode.

[0108] In this embodiment, when a new baseboard management controller is inserted, the presence signal of the BMC board will first return to the normal state, i.e., the low level state. At this time, the second target logic on the module to be managed will recognize the insertion of the new BMC. In order to prevent the newly inserted baseboard management controller from affecting the normal operation of the module to be managed, and to prevent abnormal operation of the new BMC, the second target logic on the module to be managed continues to power on the module to be managed based on the latched power control signal, and will not receive commands and signals from the new BMC.

[0109] In other words, in this embodiment, after the baseboard management controller (BMC) is powered on, it does not immediately control the power-on operation of the managed modules. The BMC first needs to contact the second target logic unit on the managed modules through the I2C channel to read the current power-on / off state of multiple managed modules. If the power-on state of multiple managed modules is "power on", it determines that the baseboard management controller is the replaced baseboard management controller, i.e., the newly inserted baseboard management controller. Then, the BMC determines itself to be the newly inserted BMC. At this time, it controls the first target logic unit to update it to the power-on state and restores the control signals of the first target logic unit to the state at power-on, i.e., updates the power control signals of the first target logic unit to the state at power-on.

[0110] After completing the above updates—that is, updating the state of the first target logic unit to power-on and updating the power control signals of the multiple managed modules in the first target logic unit to the power-on state—the BMC can send a latch release command to the second target logic unit among the multiple managed modules via I2C. This causes the second target logic unit to release the latched power control signals and restore the command-receiving mode. The command-receiving mode allows the device to receive commands sent by the BMC.

[0111] The server management system provided in this embodiment determines whether the baseboard management controller is a newly inserted baseboard management controller based on the power-on status of multiple modules to be managed after the baseboard management controller is powered on. If the power-on status of multiple modules to be managed is "power on", the baseboard management controller is determined to be a newly inserted baseboard management controller. In this case, the first target logic in the baseboard management controller needs to be updated to the power-on status and the power control signal of the first target logic for multiple modules to be managed needs to be updated to the power-on status. The baseboard management controller no longer controls the power-on of the modules to be managed again, but only controls the power-on action of the baseboard management controller.

[0112] Furthermore, after the newly inserted baseboard management controller is inserted, the second target logic unit on the managed module will not directly release the latched power control signal. This is to prevent the managed module from misusing the new enable signal in the baseboard management controller as a shutdown function upon startup, causing the managed module to power down and malfunction. The power control signal will only be released and the command receiving mode restored upon receiving a latch release command from the baseboard management controller. This achieves hot-swappable baseboard management controllers while ensuring uninterrupted operation of services and improving maintenance efficiency.

[0113] In some alternative implementations, the second target logic unit is also used for:

[0114] When the module to be managed is powered on using a latch-based power control signal and the presence signal of the baseboard management controller is detected as normal, it is determined whether a latch release command has been received from the baseboard management controller.

[0115] If no latch release command is received, the module to be managed will continue to be powered on based on the latch power control signal.

[0116] Specifically, the second target logic unit of the managed module, upon powering on the managed module based on the latched power control signal and recognizing that the on-premises signal of the baseboard management controller is in a normal state, determines that a newly inserted baseboard management controller has been identified. Until a latch release command is received from the newly inserted baseboard management controller, the managed module continues to be powered on based on the latched power control signal.

[0117] The server management system provided in this embodiment, when powering on the managed module based on a latched power control signal and recognizing the presence signal of the baseboard management controller as normal, determines that the baseboard management controller is a newly inserted baseboard management controller. After the newly inserted baseboard management controller is inserted, the second target logic unit on the managed module will not directly release the latched power control signal, to prevent the managed module from misusing the new enable signal in the baseboard management controller as a shutdown function, causing the managed module to power down and malfunction. Only upon receiving a latch release command from the baseboard management controller will the power control signal be released, resuming the command receiving mode. Otherwise, the managed module continues to be powered on based on the latched power control signal. This achieves hot-swappable baseboard management controllers while ensuring normal operation of services and improving maintenance efficiency.

[0118] In some alternative implementations, the module to be managed includes a fan module. The baseboard management controller is also used for:

[0119] After the second target logic unit corresponding to the fan module releases the latched power control signal and resumes the command receiving mode, a fan control command is sent to the second target logic unit.

[0120] After the second target logic unit corresponding to the fan module resumes the command receiving mode, the baseboard management controller can dynamically send fan control commands to the second target logic unit corresponding to the fan module based on the server's temperature information.

[0121] The second target logic unit corresponding to the fan module is used for:

[0122] Receive fan control commands and adjust the fan speed of the fan module based on the fan control commands.

[0123] The second target logic unit corresponding to the fan module performs fan speed regulation on the fan module according to the fan control instructions dynamically provided by the newly inserted BMC, so as to ensure the normal operation of other modules to be managed.

[0124] The server management system provided in this embodiment allows the baseboard management controller to send a fan control command to the second target logic device after the second target logic device releases the latched power control signal. This enables the second target logic device corresponding to the fan module to adjust the fan speed according to the command. This dynamic fan speed adjustment effectively improves the system's heat dissipation efficiency and reduces energy consumption.

[0125] In some alternative implementations, the baseboard management controller also includes a power soft-start module.

[0126] The power soft-start module is used to protect the power supply of the baseboard management controller the moment it is inserted into the server motherboard.

[0127] The power soft-start module is a standard hot-swappable module that prevents damage to the chips on the BMC board due to power fluctuations or sudden high power pulses when the BMC is inserted.

[0128] The server management system provided in this embodiment protects the baseboard management controller by using a power soft-start module, preventing damage to the baseboard management controller caused by power fluctuations or sudden high power pulses when the baseboard management controller is plugged into the server motherboard.

[0129] In some alternative implementations, the baseboard management controller further includes a signal isolation module.

[0130] The signal isolation module is used to protect the baseboard management controller from jitter the moment it is inserted into the server motherboard.

[0131] The signal isolation module is the same as that required for standard hot-swappable modules. This signal isolation module can also prevent high pulse damage to the chip caused by signal jitter due to human operation jitter at the moment of BMC board insertion.

[0132] The server management system provided in this embodiment uses a signal isolation module to protect the baseboard management controller from jitter, preventing high pulse damage to the chip caused by human operation jitter when the baseboard management controller is inserted into the server motherboard.

[0133] In some alternative implementations, the first target logic unit is further used for:

[0134] Events where the on-state signal of the substrate management controller is high and events where the on-state signal of the substrate management controller is normal are recorded.

[0135] The first target logic unit in the BMC can record events where the on-state signal of the baseboard management controller is high and events where the on-state signal of the baseboard management controller is normal, as needed. By recording this information, it is possible to determine how many times the BMC has been replaced, which facilitates subsequent review.

[0136] The server management system provided in this embodiment records events where the on-state signal of the baseboard management controller is in a high state and events where the on-state signal of the baseboard management controller is in a normal state through the first target logic device. This allows for real-time understanding of the on-state status of the baseboard management controller and helps to detect problems in a timely manner.

[0137] In some alternative implementations, the second target logic unit is also used for:

[0138] Whenever the presence signal of the substrate management controller is detected to be in a high state, the event of the presence signal of the substrate management controller being in a high state is recorded.

[0139] Whenever the presence signal of the baseboard management controller is detected to be in a normal state, the event of the presence signal of the baseboard management controller being in a normal state is recorded.

[0140] The second target logic unit can record events where the BMC's presence signal is high and events where the BMC's presence signal is normal, as needed, to determine how many times the BMC has been replaced, facilitating subsequent review. It can also be used to verify the events recorded by the first target logic unit, ensuring the accuracy of the recorded events.

[0141] The server management system provided in this embodiment records events where the on-state signal of the baseboard management controller is in a high state and events where the on-state signal of the baseboard management controller is in a normal state through the second target logic device. This allows for real-time understanding of the on-state status of the baseboard management controller and helps to detect problems in a timely manner.

[0142] In some alternative implementations, the server management system may also include a fault monitor.

[0143] The fault monitor is used to monitor the baseboard management controller. When the baseboard management controller malfunctions, it sends corresponding alarm information so that the user can determine that the baseboard management controller is malfunctioning based on the alarm information.

[0144] Understandably, users can replace the baseboard management controller based on the alarm information, that is, unplug the baseboard management controller currently inserted into the server and insert a new baseboard management controller.

[0145] It should be noted that the fault monitor is specifically used for:

[0146] Monitor the performance metrics of the baseboard management controller. These metrics may include CPU utilization, memory usage, response time, etc.

[0147] If performance indicators show abnormal increases or decreases and fail to return to normal within a preset time period, it is determined that the baseboard management controller is malfunctioning. The preset time period is set by technical personnel.

[0148] or,

[0149] Monitor system logs. These system logs record various events and error information during the operation of the baseboard management controller.

[0150] If the system log contains alarm information or abnormal events related to the baseboard management controller, it is determined that the baseboard management controller is malfunctioning.

[0151] or,

[0152] The monitored status information of the substrate management controller is compared with the preset status information. If there is a significant deviation between the monitored status information and the preset status information, it is determined that the substrate management controller is malfunctioning.

[0153] It should be noted that the preset status information refers to the status information of the baseboard management controller under normal operating conditions. A significant deviation between the monitored baseboard management controller status information and the preset status information is considered a deviation exceeding a preset deviation threshold. This preset deviation threshold is determined by technical personnel.

[0154] The server management system provided in this embodiment monitors the performance indicators, system logs, and status information of the baseboard management controller through various methods. This enables timely detection of abnormal situations in the baseboard management controller, preventing further deterioration of the problem and improving the stability and reliability of the server system.

[0155] According to an embodiment of this application, a server management method embodiment is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0156] This embodiment provides a server management method that can be used in the second target logic device in the module to be managed described above. Figure 3 is a flowchart of the server management method according to an embodiment of this application. As shown in Figure 3, the process includes the following steps:

[0157] Step S301: Receive the power control signal sent by the baseboard management controller, which is independently configured with the server motherboard, through the first target logic device.

[0158] Step S302: Power on the module to be managed based on the power control signal.

[0159] Step S303: Identify the presence signal of the baseboard management controller. If the presence signal of the baseboard management controller is identified as being pulled high, determine that the baseboard management controller is in the unplugged state. Latch the power control signal previously sent by the baseboard management controller and power on the module to be managed based on the latched power control signal.

[0160] The baseboard management controller includes a first target logic unit, and the baseboard management controller is interconnected with the server motherboard via a pluggable connector.

[0161] The further description of each step in this embodiment is the same as that in the corresponding embodiment described above, and will not be repeated here.

[0162] The server management method provided in this embodiment independently configures the baseboard management controller and the server motherboard. The baseboard management controller is interconnected with the server motherboard via a pluggable connector. In the event of a malfunction requiring maintenance of the baseboard management controller, the server does not need to be disassembled; the baseboard management controller can be hot-swapped directly. When the second target logic unit detects that the baseboard management controller's presence signal is high, it determines that the baseboard management controller is in a disconnected state. At this time, the second target logic unit latches the power control signal previously sent by the baseboard management controller and powers on the module to be managed based on the latched power control signal. This ensures the normal operation of other modules even when the baseboard management controller is disconnected, improving the maintenance efficiency of the baseboard management controller.

[0163] This embodiment provides a server management method. Figure 4 is a flowchart of the server management method according to an embodiment of this application. As shown in Figure 4, the process includes the following steps:

[0164] The first step is the power-on state. Correspondingly, the baseboard management controller sends a power control signal to the second target logic unit in the module to be managed through the first target logic unit. The second target logic unit receives the power control signal and powers on the module to be managed based on the power control signal.

[0165] The second step is to remove the BMC module. This means the BMC is in the removed state, and its presence signal is high.

[0166] The third step is that other boards detect a change in the BMC board's presence signal, i.e., the presence signal changes from the normal state to the high state.

[0167] The fourth step involves latching the CPLD status of other boards. Steps three and four correspond to the second target logic unit mentioned above, which is also used to identify the presence signal of the baseboard management controller. When the presence signal of the baseboard management controller is identified as being pulled high, it is determined that the baseboard management controller is in the unplugged state, and the power control signal previously sent by the baseboard management controller is latched.

[0168] Fifth, with all boards powered normally, the removal is complete. The power control signal corresponding to the second target logic unit mentioned above, based on the latched signal, powers on the module to be managed.

[0169] Step 6: BMC module insertion. This means the BMC is in the insertion state, and its presence signal is normal.

[0170] Step 7: Each board's CPLD ignores the transition. Corresponding to the aforementioned second target logic unit, when the module to be managed is powered on based on the latched power control signal and the presence signal of the baseboard management controller is detected as normal, it determines whether a latch release command sent by the baseboard management controller has been received; if no latch release command is received, it continues to power on the module to be managed based on the latched power control signal.

[0171] Step 8: The BMC board detects the status of other boards. This corresponds to the aforementioned baseboard management controller reading the power-on status of multiple modules to be managed after power-on.

[0172] Step 9: The BMC clears the latch states of other boards. Corresponding to the aforementioned situation where the baseboard management controller is in the "power on" state for multiple managed modules, the BMC determines that the baseboard management controller is the replaced one, updates the state of the first target logic unit to "power on," and updates the power control signals for the multiple managed modules in the first target logic unit to the "power on" state; a latch release command is sent to the second target logic unit; the second target logic unit receives the latch release command, and in response to the latch release command, releases the latched power control signals and resumes the command receiving mode.

[0173] Step 10: Insertion complete.

[0174] The server management method provided in this embodiment completes the BMC replacement operation when a BMC malfunctions through the above steps, thus achieving BMC hot-swapping. Throughout the process, the power supply to the managed module remains on, and services continue to operate normally, ensuring that the hot-swapping of the BMC does not affect the services or power supply of the entire machine.

[0175] In other words, the server management method provided in this embodiment requires no manual intervention in the business processes when the BMC malfunctions and needs replacement, especially no service interruption. Maintenance personnel simply need to locate the corresponding server in the server room, remove the BMC directly from the front or rear window, and replace it with a new one. The entire maintenance process does not require stopping the business, shutting down the power, removing the server from the rack, or disassembling the server. This truly separates the BMC from the business data, significantly shortening BMC maintenance time, improving maintenance efficiency, and reducing maintenance costs and manpower. By maintaining uninterrupted business operations, it achieves truly seamless maintenance, enhancing the user experience.

[0176] This application also provides a computer device. Referring to Figure 5, which is a schematic diagram of the structure of a computer device according to an optional embodiment of this application, the computer device includes one or more processors 501, a memory 502, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components communicate with each other using different buses and can be installed on a common motherboard or otherwise as needed. The processor can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if needed. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 5 uses one processor 501 as an example.

[0177] Processor 501 may be a central processing unit, a network processor, or a combination thereof. Processor 501 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0178] The memory 502 stores instructions executable by at least one processor 501 to cause at least one processor 501 to perform the method shown in the above embodiments.

[0179] Memory 502 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, memory 502 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, memory 502 may optionally include memory remotely located relative to processor 501, and this remote memory may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0180] Memory 502 may include volatile memory, such as random access memory; memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; memory 502 may also include combinations of the above types of memory.

[0181] The computer device also includes a communication interface 503 for communicating with other devices or communication networks.

[0182] This application also provides a computer-readable storage medium. The methods described in this application can be implemented in hardware or firmware, or implemented as recordable on a storage medium, or implemented as computer code downloaded over a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and subsequently stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the methods shown in the above embodiments are implemented.

[0183] A portion of this application can be applied as a computer program product, such as computer instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to this application through the operation of the computer. Those skilled in the art will understand that the forms in which computer instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer instructions are executed by a computer include, but are not limited to: the computer directly executing the instruction; or the computer compiling the instruction and then executing the corresponding compiled program; or the computer reading and executing the instruction; or the computer reading and installing the instruction and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0184] Although embodiments of this application have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of this application, and all such modifications and variations fall within the scope defined by the appended claims.

Claims

1. A server management system, characterized in that, The system includes: a baseboard management controller independently configured from the server motherboard and multiple modules to be managed. The baseboard management controller includes a first target logic unit, and each module to be managed includes a second target logic unit. The baseboard management controller is interconnected with the server motherboard via a pluggable connector and is used to send power control signals to the second target logic device in the managed module through the first target logic device. The second target logic unit is used to receive the power control signal and power on the module to be managed based on the power control signal; The second target logic unit is also used to identify the presence signal of the baseboard management controller, and in response to the identification that the presence signal of the baseboard management controller is in a pulled-up state, to determine that the baseboard management controller is in a pulled-out state, to latch the power control signal previously sent by the baseboard management controller, and to power on the module to be managed based on the latched power control signal.

2. The system according to claim 1, characterized in that, The substrate management controller further includes an in-situ module; the in-situ module is used for: In response to the substrate management controller being in the unplugged state, the presence signal of the substrate management controller is updated to a pulled-high state; and In response to the substrate management controller being in the inserted state, the presence signal of the substrate management controller is updated to the normal state.

3. The system according to claim 1, characterized in that, The module to be managed includes a fan module; The second target logic unit corresponding to the fan module is used to control the fan module to operate at a safe speed in response to the detection that the presence signal of the baseboard management controller is in a high state.

4. The system according to claim 1, characterized in that, The substrate management controller is specifically used for: After power-on, the power-on status of multiple modules to be managed is read. In response to the power-on status of multiple modules to be managed being not powered on, it is determined that the baseboard management controller has not been replaced. The power control signal is then sent to the second target logic device in the module to be managed through the first target logic device.

5. The system according to claim 1, characterized in that, The substrate management controller is specifically used for: After power-on, the power-on status of multiple modules to be managed is read. In response to the power-on status of multiple modules to be managed being powered on, the baseboard management controller is determined to be the replaced baseboard management controller. The status of the first target logic device is updated to powered on, and the power control signal of the first target logic device to the multiple modules to be managed is updated to the power-on status. and Send a latch release command to the second target logic unit; The second target logic unit is used to receive the latch release command, and in response to the latch release command, release the power control signal of the latch and resume the command receiving mode.

6. The system according to claim 1, characterized in that, The second target logic unit is also used for: In response to powering on the module to be managed in response to a latch-based power control signal, and upon recognizing that the presence signal of the baseboard management controller is in a normal state, it is determined whether a latch release command sent by the baseboard management controller has been received. and In response to the absence of the latch release command, the module to be managed continues to be powered on based on the latch power control signal.

7. The system according to claim 1, characterized in that, The module to be managed includes a fan module; The substrate management controller is also used for: After the second target logic unit corresponding to the fan module releases the latched power control signal and resumes the command receiving mode, a fan control command is sent to the second target logic unit. The second target logic unit corresponding to the fan module is used for: Receive the fan control command and adjust the fan speed of the fan module based on the fan control command.

8. The system according to claim 1, characterized in that, The baseboard management controller also includes a power soft-start module; The power soft-start module is used to protect the power supply of the baseboard management controller the moment it is inserted into the server motherboard.

9. The system according to claim 1, characterized in that, The baseboard management controller further includes: a signal isolation module; The signal isolation module is used to provide anti-jitter protection for the baseboard management controller at the moment it is inserted into the server motherboard.

10. The system according to claim 1, characterized in that, The first target logic unit is also used for: Events where the on-state signal of the substrate management controller is high and events where the on-state signal of the substrate management controller is normal are recorded.

11. The system according to claim 1, characterized in that, The second target logic unit is also used for: Whenever the presence signal of the substrate management controller is detected to be in a high state, the event of the presence signal of the substrate management controller being in a high state is recorded; and Whenever the presence signal of the baseboard management controller is detected to be in a normal state, the event of the presence signal of the baseboard management controller being in a normal state is recorded.

12. A server management method, characterized in that, The method, applied to a second target logic device in a module to be managed, includes: Receives power control signals sent by the baseboard management controller, which is independently configured from the server motherboard, through the first target logic unit; The module to be managed is powered on based on the power control signal; and The presence signal of the baseboard management controller is identified. In response to the detection that the presence signal of the baseboard management controller is in a pulled-up state, the baseboard management controller is determined to be in a pulled-out state. The power control signal previously sent by the baseboard management controller is latched, and the module to be managed is powered on based on the latched power control signal. The baseboard management controller includes a first target logic unit, and the baseboard management controller is interconnected with the server motherboard via a pluggable connector.

13. The method according to claim 12, characterized in that, After power-on, the baseboard management controller reads the power-on status of multiple modules to be managed. In response to the power-on status of multiple modules to be managed being powered on, it determines that the baseboard management controller is the replaced baseboard management controller, updates the status of the first target logic device to powered on, updates the power control signal of the multiple modules to be managed in the first target logic device to the power-on state, and sends a latch release command to the second target logic device. The method further includes: Upon receiving the latch release command, in response to the latch release command, the power control signal of the latch is released, and the command receiving mode is resumed.

14. The method according to claim 12, characterized in that, The method further includes: In response to powering on the managed module based on a latch-based power control signal, and upon detecting that the presence signal of the baseboard management controller is in a normal state, it determines whether a latch release command has been received from the baseboard management controller; and In response to the absence of the latch release command, the module to be managed continues to be powered on based on the latch power control signal.

15. The method according to claim 12, characterized in that, The module to be managed includes a fan module. After the baseboard management controller releases the latched power control signal from the second target logic unit corresponding to the fan module and resumes the command receiving mode, it sends a fan control command to the second target logic unit. The method further includes: Receive the fan control command and adjust the fan speed of the fan module based on the fan control command.

16. The method according to claim 12, characterized in that, The method further includes: Whenever the presence signal of the substrate management controller is detected to be in a high state, the event of the presence signal of the substrate management controller being in a high state is recorded; and Whenever the presence signal of the baseboard management controller is detected to be in a normal state, the event of the presence signal of the baseboard management controller being in a normal state is recorded.

17. The method according to claim 12, characterized in that, The module to be managed includes a fan module; The method further includes: In response to the detection that the presence signal of the baseboard management controller is high, the fan module is controlled to operate at a safe speed.

18. A computer device, characterized in that, include: A memory and a processor are communicatively connected, the memory stores computer instructions, and the processor executes the computer instructions to perform the server management method according to any one of claims 12-17.

19. One or more non-volatile computer-readable storage media storing computer-readable instructions, which, when executed by one or more processors, cause the one or more processors to perform the steps of the server management method as described in any one of claims 12-17.

20. A computer program product, characterized in that, Includes computer instructions for causing a computer to perform the server management method according to any one of claims 12-17.

Images