Power backup system, method, device, equipment, medium and computer program product
By designing a power backup system that intelligently monitors power supply failures in a pooled memory environment, using the power backup module to intervene in the power supply outage or power supply failure, ensuring that memory resources are continuously powered and the dumping strategy is implemented, the traditional solution cannot be fully implemented. The problem of dumping data improves system reliability and data security.
Patent Information
- Application Number
- CN202411034707.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-30
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-07-30
AI Technical Summary
In a pooled memory environment, traditional power backup management solutions cannot fully dump memory data in the event of loss of mains or power failure, resulting in data loss and system instability.
A power reserve system was designed to intelligently monitor the power supply fault status through the first substrate management controller in the interconnection exchange board, flexibly adjust the power reserve strategy according to different fault statuses, and use the power reserve module to power outage or power supply mode in the mains power supply or power supply mode. Quickly intervene when the group power supply is lost to ensure that the memory resources are continuously powered and that the memory resource dumping policy or pre-dumping policy is executed.
Effectively prevent data loss and ensure stable operation of the system, significantly improve the system reliability and data security, improve the utilization rate of server hardware resources, and reduce maintenance costs.
Smart Images

Figure CN118567462B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of memory technology, and in particular to a backup power system, method, device, equipment, medium and computer program product. Background Art
[0002] With the development of cloud computing, artificial intelligence, high-performance computing and other technologies, the computing power of processors has been continuously improved, and the number of cores has been continuously increasing, which has promoted the evolution of memory systems towards larger capacity and higher bandwidth. In order to meet the increasing demand for memory resources, it is necessary to re-examine the server resource management architecture based on the traditional server hardware architecture. Server architects have optimized and reconstructed the traditional server architecture, and proposed an integrated reorganization architecture solution for server memory resource pooling in order to improve resource utilization and reduce maintenance costs.
[0003] In a pooled memory environment, memory resources in the memory resource pool will be provided to multiple different host computing nodes. Once the integrated machine loses power or a power failure causes power supply abnormality, it will affect the normal operation of all memory resources in the integrated machine and the services of the host computing nodes.
[0004] In the related art, in order to solve the above problem, a solution is adopted to manage the backup power of the server system by using a BBU or a supercapacitor module. However, this solution is subject to the power supply time limit of the BBU module and can only dump some important memory data. For the memory resource pool scenario, there is a large amount of memory data, and the power supply time provided by the BBU is not enough to dump all the memory data into the non-volatile storage device. Summary of the invention
[0005] The purpose of the embodiments of the present invention is to provide a backup power system, method, apparatus, device, medium and computer program product. The specific technical solutions are as follows:
[0006] In a first aspect of the implementation of the present invention, a backup power system is first provided, the backup power system comprising the interconnection switching board, the computing node board, the memory resource board, the power module and the backup power module; the interconnection switching board comprises a first baseboard management controller and an interconnection switching chip; the interconnection switching chip is used to connect the computing nodes in the computing node board and the memory modules in the memory resource board;
[0007] The first baseboard management controller is used to obtain the power supply fault state corresponding to the memory resource integrated machine; if the power supply fault state is a first power supply fault state, then based on the external power supply power-off signal sent by the complex programmable logic device in the interconnection switching board, the backup power module is controlled to supply power to the memory resource integrated machine, and a memory resource dump strategy is executed; if the power supply fault state is a second power supply fault state, a memory pre-dump strategy is executed, and when it is detected that the power supply module is in a power loss state, the backup power module is controlled to supply power to the memory resource integrated machine, and a memory resource dump strategy is executed.
[0008] Optionally, the backup power system further includes a network switching chip board;
[0009] The computing node board, the memory resource board and the interconnection switching board are connected via the network switching chip board.
[0010] Optionally, the computing node board, the interconnection switch board and the memory resource board are connected in a preset topology connection manner.
[0011] Optionally, the preset topology connection method includes the interconnection switching chip being connected upstream to the port of the computing node board, and being connected downstream to the memory resource board; by managing the computing node configuration upstream and downstream interconnection relationship of the interconnection switching chip and memory resource slice management, the first baseboard management controller of the interconnection switching board interacts with the management computing node through a network preset interface, obtains the downstream port corresponding to the memory resource of the upstream computing node of the interconnection switching chip of the interconnection switching board, and forms a connection topology between computing resources and memory resources.
[0012] Optionally, the interconnection switch board includes a management computing node and a first baseboard management controller;
[0013] The management computing node is used to control the interconnection switching chip to manage and configure the memory resource information;
[0014] The first baseboard management controller is connected to the management computing node through a preset network, and the first baseboard management controller is used to interact with the management computing node to obtain the memory resource information.
[0015] Optionally, the memory resource board includes a memory controller, a second baseboard management controller and a memory module;
[0016] The memory controller is used to connect to the interconnection switching board through a preset interface, monitor and manage the memory resource information, and transfer the interconnection switching bus of the memory module to the interconnection switching chip in the interconnection switching board, so that the computing node board uses the memory resource information corresponding to the memory module;
[0017] The second baseboard management controller is connected to the memory controller via a preset bus, and is used to monitor and manage the interconnect exchange memory. The second baseboard management controller controls power on and off of the memory modules in each of the memory controllers.
[0018] In a second aspect of the implementation of the present invention, a backup power method is also provided, which is applied to a first baseboard management controller in an interconnection switching board in a backup power system, wherein the backup power system includes the interconnection switching board, a computing node board, a memory resource board, a power module, and a backup power module; the interconnection switching board includes a first baseboard management controller and an interconnection switching chip; the interconnection switching chip is used to connect a computing node in the computing node board and a memory module in the memory resource board, and the method includes:
[0019] Obtaining a power supply fault status corresponding to the memory resource integrated machine;
[0020] If the power supply fault state is a first power supply fault state, the backup power module is controlled to supply power to the memory resource integrated machine based on an external power supply power-off signal sent by the complex programmable logic device in the interconnection switching board, and a memory resource dump strategy is executed;
[0021] If the power supply failure state is the second power supply failure state, the memory pre-dump strategy is executed, and when it is detected that the power supply module is in a power loss state, the backup power module is controlled to supply power to the memory resource integrated machine, and the memory resource dump strategy is executed.
[0022] Optionally, obtaining the power supply fault state corresponding to the memory resource integrated machine includes:
[0023] In case of receiving an external power supply off signal sent by the complex programmable logic device in the interconnection switch board, determining that the power supply fault state is a first power supply fault state;
[0024] When it is detected that the power module is in a fault state, the power supply fault state is determined to be a second power supply fault state.
[0025] Optionally, the external power supply off signal is generated when the complex programmable logic device in the interconnection switch board recognizes that the voltage corresponding to the external power supply card is lower than a preset voltage.
[0026] Optionally, when detecting that the power module is in a fault state, determining that the power supply fault state is a second power supply fault state includes:
[0027] Monitoring the power status corresponding to the power module through a power management bus command;
[0028] Determining whether the power module is in a fault state based on the power state;
[0029] In the case where it is detected that the power module is in a fault state, determining that the power supply fault state is a second power supply fault state;
[0030] Among them, the fault state includes at least one of the power supply module being in a power redundancy loss state, the output voltage corresponding to the power supply module being in an abnormal state, the output current corresponding to the power supply module being in an abnormal state, and the power supply module being in an AC power interruption state.
[0031] Optionally, the executing memory pre-dump strategy includes:
[0032] Send power module failure warning information to the computing nodes in the computing node board, and transfer the memory data corresponding to the computing nodes to a preset non-volatile storage device.
[0033] Optionally, when it is detected that the power module is in a power loss state, controlling the backup power module to supply power to the memory resource integrated machine includes:
[0034] When it is detected that the memory pre-dump strategy is executed and the power module is in a power loss state, the backup power module is controlled to supply power to the memory resource integrated machine.
[0035] Optionally, the executing memory resource dump strategy includes:
[0036] Acquire first target memory data, wherein the target memory data is in a dump completion state; and perform hot removal processing on the first target memory data.
[0037] Optionally, performing hot removal processing on the first target memory data includes:
[0038] Determine a first target computing node corresponding to the first target memory data according to the first target memory data;
[0039] Control the first target computing node to power off.
[0040] Optionally, the executing memory resource dump strategy includes:
[0041] Acquire second target memory data, wherein the second target memory data is in an undumped state;
[0042] The second target memory data is transferred to the corresponding preset non-volatile storage device.
[0043] Optionally, after the step of sending a power supply signal to the backup power module according to the external power supply off signal so that the backup power module supplies power to the memory resource integrated machine, the method includes:
[0044] A power consumption limiting signal is sent to a third baseboard management controller corresponding to a computing node in each computing node board.
[0045] In a third aspect of the implementation of the present invention, a backup power device is further provided, which is applied to a first baseboard management controller in an interconnection switching board in a backup power system, wherein the backup power system comprises the interconnection switching board, a computing node board, a memory resource board, a power module and a backup power module; the interconnection switching board comprises a first baseboard management controller and an interconnection switching chip; the interconnection switching chip is used to connect a computing node in the computing node board and a memory module in the memory resource board, and the device comprises:
[0046] An acquisition module, used to acquire a power supply fault status corresponding to the memory resource integrated machine;
[0047] A first execution module, configured to control the backup power module to supply power to the memory resource integrated machine based on an external power supply power-off signal sent by a complex programmable logic device in the interconnection switching board if the power supply fault state is a first power supply fault state, and to execute a memory resource dump strategy;
[0048] The second execution module is used to execute the memory pre-dump strategy if the power supply fault state is the second power supply fault state, and control the backup power module to supply power to the memory resource integrated machine when it is detected that the power supply module is in a power loss state, and execute the memory resource dump strategy.
[0049] In a fourth aspect of the present invention, there is also provided an electronic device, comprising: a processor;
[0050] a memory for storing instructions executable by the processor;
[0051] Wherein, the processor is configured to execute the instructions to implement the power backup method as described in any one of the second aspects.
[0052] In a fifth aspect of the implementation of the present invention, a computer-readable storage medium is further provided, wherein instructions are stored in the computer-readable storage medium, and when the computer-readable storage medium is executed on a computer, the computer implements the power backup method as described in any one of the first aspects.
[0053] In a sixth aspect of the implementation of the present invention, a computer program product is also provided, including a computer program / instruction, and when the computer program / instruction is executed by a processor, the backup power method as described in any one of the first aspects is implemented.
[0054] The backup power system provided by the embodiment of the present invention comprises the interconnection switching board, the computing node board, the memory resource board, the power module and the backup power module; the interconnection switching board comprises a first baseboard management controller and an interconnection switching chip; the interconnection switching chip is used to connect the computing nodes in the computing node board and the memory modules in the memory resource board; the first baseboard management controller is used to obtain the power supply fault state corresponding to the memory resource integrated machine; if the power supply fault state is the first power supply fault state, the backup power module is controlled to supply power to the memory resource integrated machine based on the external power supply power-off signal sent by the complex programmable logic device in the interconnection switching board, and the memory resource dump strategy is executed; if the power supply fault state is the second power supply fault state, the memory pre-dump strategy is executed, and when it is detected that the power module is in a power loss state, the backup power module is controlled to supply power to the memory resource integrated machine, and the memory resource dump strategy is executed. In the embodiment of the present invention, the backup power system provided by the embodiment of the present invention intelligently monitors the power supply fault state through the first baseboard management controller in the interconnection switching board, and flexibly adjusts the backup power strategy according to different fault states (the first or second power supply fault state). In the event of a city power outage or power loss to the power module, the backup power module can quickly intervene to ensure continuous power supply to the memory resource all-in-one machine, while executing the memory resource dump strategy or pre-dump strategy to effectively prevent data loss, ensure stable system operation, and significantly improve system reliability and data security. BRIEF DESCRIPTION OF THE DRAWINGS
[0055] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art are briefly introduced below.
[0056] Figure 1 A schematic diagram of the architecture of a backup power system provided by an embodiment of the present invention;
[0057] Figure 2 is a flowchart of a power backup method provided by an embodiment of the present invention;
[0058] Figure 3 is a device block diagram of a power backup device provided by an embodiment of the present invention;
[0059] Figure 4 is a schematic diagram of an electronic device provided by an embodiment of the present invention;
[0060] Figure 5 is a schematic diagram of a network connection topology of a backup power system provided by an embodiment of the present invention;
[0061] Figure 6 is an overall schematic diagram of an exemplary power backup method provided by an embodiment of the present invention;
[0062] Figure 7 is an overall schematic diagram of another exemplary power backup method provided by an embodiment of the present invention;
[0063] Figure 8 The present invention provides a memory hot-swap control topology diagram. DETAILED DESCRIPTION
[0064] To make the purpose, technical scheme and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings. However, it will be appreciated by those skilled in the art that in the embodiments of the present invention, many technical details are proposed in order to enable the reader to better understand the present application. However, even without these technical details and various changes and modifications based on the following embodiments, the technical scheme claimed in the present application can be implemented. The division of the following embodiments is for the convenience of description, and should not constitute any limitation on the specific implementation of the present invention. The various embodiments can be combined and referenced with each other without contradiction.
[0065] It should be noted that in the embodiments of the present application, in order to facilitate the understanding of the technical solution of the present application, some contents are explained: CPU Board is a computing node board, CXL SW Board is an interconnection switching board, DIMM Board is a memory resource board, LAN SW Board is a network switching chip board, CXL SW chip is an interconnection interaction chip, MXC is a memory controller, the full name is Memory Expander Controller, BMC is a baseboard management controller (BMC, Baseboard Management Controller), CXL (Compute Express Link) is a new type of high-speed interconnection technology, mCPU (Management CPU) is a management computing node, a memory resource management CPU, BBU (Battery Backup Unit), is a battery backup unit, which is a backup power module in the embodiments of the present application, and PSU is a power supply module.
[0066] Reference Figure 1 , shows a schematic diagram of the architecture of a backup power system provided by an embodiment of the present invention, the backup power system includes a memory resource integrated machine, the memory resource integrated machine includes the interconnection switching board, the computing node board, the memory resource board, the power module and the backup power module; the interconnection switching board includes a first baseboard management controller and an interconnection switching chip; the interconnection switching chip is used to connect the computing nodes in the computing node board and the memory modules in the memory resource board;
[0067] The first baseboard management controller is used to obtain the power supply fault state corresponding to the memory resource integrated machine; if the power supply fault state is a first power supply fault state, then based on the external power supply power-off signal sent by the complex programmable logic device in the interconnection switching board, the backup power module is controlled to supply power to the memory resource integrated machine, and a memory resource dump strategy is executed; if the power supply fault state is a second power supply fault state, a memory pre-dump strategy is executed, and when it is detected that the power supply module is in a power loss state, the backup power module is controlled to supply power to the memory resource integrated machine, and a memory resource dump strategy is executed.
[0068] Furthermore, the backup power system also includes a network switching chip board;
[0069] The computing node board, the memory resource board and the interconnection switching board are connected via the network switching chip board.
[0070] It should be noted that in the embodiments of the present application, reference is made to Figure 1 , Figure 1 This is a schematic diagram of a memory resource all-in-one system architecture provided by an embodiment of the present invention. In the integrated architecture, various resources are allocated to different hardware boards, where the boards may include a CPU board for processing computing tasks, an interconnection switch board responsible for interconnection switching, a DIMM board for managing memory resources, and a LAN SW board for network switching. These boards are connected through the LAN SW board to form a unified BMC management network. The physical connection cables between the CPU board, the interconnection switch board, and the DIMM board are pre-set, which can be referred to Figure 5 , Figure 5 It is a schematic diagram of a memory resource all-in-one machine network connection topology provided by an embodiment of the present invention. The memory resource all-in-one machine network connection topology describes how various components in an integrated architecture are connected and communicated through a network.
[0071] Furthermore, the computing node board, the interconnection switch board and the memory resource board are connected in a preset topology connection mode. The preset topology connection mode includes the interconnection switch chip being connected upstream to the port of the computing node board and being connected downstream to the memory resource board; by managing the computing node to configure the upstream and downstream interconnection relationship of the interconnection switch chip and the memory resource slice management, the first baseboard management controller of the interconnection switch board interacts with the management computing node through a preset network interface, obtains the downstream port corresponding to the memory resource of the computing node upstream of the interconnection switch chip of the interconnection switch board, and forms a connection topology between computing resources and memory resources.
[0072] It should be noted that in the embodiment of the present application, the hardware topology connection between the CXL SW chip and the upstream and downstream is fixed, the upstream is connected to the port of the computing node CPU Board, and the downstream is connected to the DIMM Board memory resources. The mCPU configures the upstream and downstream Fabric interconnection relationship of the CXL SW chip and the memory resource slice management. The CXL SW Board BMC interacts with the mCPU through the network Redfish interface to obtain which downstream ports correspond to the memory resources used by the current CXL SW chip upstream computing node CPU, and forms the connection topology of computing resources and memory resources.
[0073] Further, the interconnection switch board includes a management computing node and a first baseboard management controller;
[0074] The management computing node is used to control the interconnection switching chip to manage and configure the memory resource information;
[0075] The first baseboard management controller is connected to the management computing node through a preset network, and the first baseboard management controller is used to interact with the management computing node to obtain the memory resource information.
[0076] It should be noted that in the embodiment of the present application, in the interconnection switch board, the main CPU (mCPU) is responsible for commanding the interconnection switch chip, managing and configuring the interconnection switch memory resources. The BMC is connected to the mCPU via the SGMII network. Through this connection, the BMC can communicate with the mCPU to obtain and adjust the allocation of memory resources.
[0077] Among them, the interconnection switching chip is the CXL SW chip. The functions of the CXL SW chip (probably referring to the CXL switching chip) are mainly reflected in the following aspects:
[0078] Connection function: The CXL SW chip acts as a bridge to connect the upstream computing node CPU Board with the downstream DIMMBoard memory resources. This connection ensures that the computing node can effectively access and manage memory resources.
[0079] Configuration management: The upstream and downstream fabric interconnection relationship and memory resource slice management of the CXL SW chip are configured by the mCPU (which may be the main control CPU). This means that the CXL SW chip needs to support complex configuration logic to adjust its connection and resource allocation according to the instructions of the mCPU.
[0080] Communication interface: The CXL SW chip interacts with the mCPU through its Board BMC (Baseboard Management Controller) through the network Redfish interface. This interaction enables the CXL SW chip to obtain detailed information about the memory resources used by the computing node CPU, thereby dynamically adjusting the connection topology between computing resources and memory resources.
[0081] Resource optimization: Through the above-mentioned connection and configuration management, the CXL SW chip helps optimize the use of computing resources and memory resources, improving the overall performance and efficiency of the system.
[0082] Further, the memory resource board includes a memory controller, a second baseboard management controller and a memory module;
[0083] The memory controller is used to connect to the interconnection switching board through a preset interface, monitor and manage the memory resource information, and transfer the interconnection switching bus of the memory module to the interconnection switching chip in the interconnection switching board, so that the computing node board uses the memory resource information corresponding to the memory module;
[0084] The second baseboard management controller is connected to the memory controller via a preset bus, and is used to monitor and manage the interconnect exchange memory. The second baseboard management controller controls power on and off of the memory modules in each of the memory controllers.
[0085] It should be noted that in the embodiment of the present application, in the DIMM board, MXC plays the role of a memory controller, which is connected to the interconnect exchange memory through DDR and SMBus, is responsible for monitoring and managing these memories, and connects the interconnect exchange bus to the interconnect exchange chip so that the computing nodes can access and use these memory resources. The BMC of the DIMM board is connected to the MXC via the SMBus, thereby realizing the monitoring and management of the interconnect exchange memory. In addition, the BMC is also connected to the eFuse via an I2C hardware link to control the power status of each MXC memory module.
[0086] The PSU power module provides power for the entire system, while the BBU serves as a backup power module, charging when the PSU power is working normally. When there is a problem with the PSU power, the BBU will provide power to ensure the continuous operation of the system.
[0087] It should be noted that in the memory resource all-in-one system architecture, in addition to the above-mentioned resource allocation and interactive boards, it also includes a PSU power module and a BBU backup power module. In order to facilitate the subsequent explanation of the technical solution, the PSU power module is called the power module and the BBU backup power module is called the backup power module.
[0088] The backup power system provided by the embodiment of the present invention comprises the interconnection switching board, the computing node board, the memory resource board, the power module and the backup power module; the interconnection switching board comprises a first baseboard management controller and an interconnection switching chip; the interconnection switching chip is used to connect the computing nodes in the computing node board and the memory modules in the memory resource board; the first baseboard management controller is used to obtain the power supply fault state corresponding to the memory resource integrated machine; if the power supply fault state is the first power supply fault state, the backup power module is controlled to supply power to the memory resource integrated machine based on the external power supply power-off signal sent by the complex programmable logic device in the interconnection switching board, and the memory resource dump strategy is executed; if the power supply fault state is the second power supply fault state, the memory pre-dump strategy is executed, and when it is detected that the power module is in a power loss state, the backup power module is controlled to supply power to the memory resource integrated machine, and the memory resource dump strategy is executed. In the embodiment of the present invention, the backup power system provided by the embodiment of the present invention intelligently monitors the power supply fault state through the first baseboard management controller in the interconnection switching board, and flexibly adjusts the backup power strategy according to different fault states (the first or second power supply fault state). In the event of a city power outage or power loss to the power module, the backup power module can quickly intervene to ensure continuous power supply to the memory resource all-in-one machine, while executing the memory resource dump strategy or pre-dump strategy to effectively prevent data loss, ensure stable system operation, and significantly improve system reliability and data security.
[0089] In the memory resource integrated machine described in this application, memory resources will be provided to multiple different Host computing nodes for use. Once the memory resource integrated machine loses power or a power failure causes power supply abnormality, it will affect the normal operation of all memory resources and Host computing nodes in the memory resource integrated machine. Therefore, this application also provides a method for ensuring normal power supply in the event of a failure, that is, a backup power method. For details, refer to Figure 2 , shows a flowchart of the steps of a backup power method provided by an embodiment of the present invention, which is applied to a first baseboard management controller in an interconnection switching board in a backup power system, the backup power system includes a memory resource integrated machine, the memory resource integrated machine includes the interconnection switching board, a computing node board, a memory resource board, a power module and a backup power module; the interconnection switching board includes a first baseboard management controller and an interconnection switching chip; the interconnection switching chip is used to connect the computing nodes in the computing node board and the memory modules in the memory resource board, the method includes:
[0090] Step 101, obtaining a power supply fault status corresponding to the memory resource integrated machine;
[0091] It should be noted that, in the embodiment of the present application, the backup power trigger involves two scenarios, the first is triggered by a mains power outage, and the second is triggered by an irrecoverable fault of the PSU power supply.
[0092] Therefore, it is necessary to first determine the current scenario, that is, to confirm whether the power module is in a fault state.
[0093] Whether the power module is in a faulty state is the triggering of the second scenario, that is, an irrecoverable PSU power fault.
[0094] Further, step 101, that is, obtaining the power supply fault state corresponding to the memory resource integrated machine includes:
[0095] S1011, upon receiving an external power supply off signal sent by the complex programmable logic device in the interconnect switch board, determining that the power supply fault state is a first power supply fault state;
[0096] S1012: When it is detected that the power module is in a fault state, determine that the power supply fault state is a second power supply fault state.
[0097] The external power supply off signal is generated when the complex programmable logic device in the interconnection switch board recognizes that the voltage corresponding to the external power supply board is lower than a preset voltage.
[0098] Further, when the power module is detected to be in a fault state, determining that the power supply fault state is a second power supply fault state includes:
[0099] Monitoring the power status corresponding to the power module through a power management bus command;
[0100] Determining whether the power module is in a fault state based on the power state;
[0101] In the case where it is detected that the power module is in a fault state, determining that the power supply fault state is a second power supply fault state;
[0102] Among them, the fault state includes at least one of the power supply module being in a power redundancy loss state, the output voltage corresponding to the power supply module being in an abnormal state, the output current corresponding to the power supply module being in an abnormal state, and the power supply module being in an AC power interruption state.
[0103] Step 102, if the power supply fault state is a first power supply fault state, controlling the backup power module to supply power to the memory resource integrated machine based on an external power supply power-off signal sent by the complex programmable logic device in the interconnection switch board, and executing a memory resource dump strategy;
[0104] If an unrecoverable fault is detected in the PSU, the memory pre-dump strategy is triggered first. When the CPLD detects that the PSU power supply is lost, the memory backup power data protection solution is triggered.
[0105] Furthermore, the execution of the memory pre-dump strategy includes:
[0106] Send power module failure warning information to the computing nodes in the computing node board, and transfer the memory data corresponding to the computing nodes to a preset non-volatile storage device.
[0107] Further, when it is detected that the power module is in a power loss state, controlling the backup power module to supply power to the memory resource integrated machine includes:
[0108] When it is detected that the memory pre-dump strategy is executed and the power module is in a power loss state, the backup power module is controlled to supply power to the memory resource integrated machine.
[0109] Further, refer to Figure 6 , Figure 6 It refers to the data preservation scheme of backup memory triggered by the loss of mains power, in which the external power supply power failure signal is the signal of mains power loss.
[0110] If the BBU backup power is triggered by the loss of mains power, the memory backup power data preservation solution is directly triggered.
[0111] Specifically, the mains power failure triggers: When the CPLD identifies that the standby voltage of the mains power supply card is lower than the threshold voltage, it determines that the mains power is off and the PSU power supply capacity is insufficient, triggering the BBU backup power module to supply power to the entire system, thereby triggering the memory dump operation to transfer the memory data to the non-volatile storage unit.
[0112] 1) When the CXL SW Board CPLD identifies that the standby voltage of the AC power supply board is lower than the threshold voltage, it determines that the AC power is lost. It immediately notifies the BBU backup power module MCU, which then supplies power to the entire system. It also notifies the CXL SW Board BMC of the power loss through hardware links such as GPIO or SMBus, triggering the BBU backup power control logic;
[0113] 2) The CXL SW Board BMC informs each computing node BMC through the network hardware link and software protocols such as IPMI or Redfish to control the CPU power consumption cap of the computing node, reduce the power consumption of the computing node, and extend the BBU power supply time;
[0114] 3) The CXL SW Board BMC notifies the Host computing node CPU through the network Redfish interface to trigger the memory resource pool memory data dump logic;
[0115] 4) The upper-layer system management software running in the CPU of each Host computing node transfers the memory data to a non-volatile storage device such as a hard disk, stores the CXL memory tag of the dumped memory data, and notifies the CXL SW Board BMC through the network Redfish interface;
[0116] 5) The CXL SW Board BMC processes the received CXL memory information after the memory data is dumped, matches it with the CXL memory resource allocation topology established and saved in the CXL SWBoard BMC, and matches it to the upstream computing node that uses this memory resource. When all the CXL memory resources matched in the computing node topology have completed the memory data dump, the hot plug of this part of the memory resources is triggered, and this part of the CXL memory is hot removed (for specific solutions, refer to the memory hot plug solution), reducing the power consumption of memory resources and further extending the power supply time of the BBU.
[0117] For the host computing node that has completed the memory data transfer, the CXL SW Board BMC sends a Redfish command through the network to inform the corresponding host computing node BMC to control the CPU of the computing node to shut down and power off. This realizes the power-off of the unit in the memory pool resource all-in-one machine scenario, further reduces the power consumption of the whole machine in the BBU backup power module power supply scenario, and further extends the BBU power supply time, thereby saving more memory data without loss.
[0118] Step 103, if the power supply fault state is the second power supply fault state, execute the memory pre-dump strategy, and when it is detected that the power supply module is in a power loss state, control the backup power module to supply power to the memory resource integrated machine, and execute the memory resource dump strategy.
[0119] If the BBU backup power is triggered by the loss of mains power, the memory backup power data preservation solution is directly triggered.
[0120] In one embodiment, executing the memory resource dump strategy includes:
[0121] Acquire first target memory data, wherein the target memory data is in a dump completion state; and perform hot removal processing on the first target memory data.
[0122] Furthermore, the hot removal processing for the target memory data includes: determining a first target computing node corresponding to the first target memory data according to the first target memory data; and controlling the first target computing node to power off.
[0123] In another embodiment, the executing memory resource dump strategy includes:
[0124] Acquire second target memory data, wherein the second target memory data is in an undumped state;
[0125] The second target memory data is transferred to the corresponding preset non-volatile storage device.
[0126] Further, in step 103, the controlling the backup power module to supply power to the memory resource integrated machine based on the external power supply power-off signal sent by the complex programmable logic device in the interconnection switch board includes:
[0127] S1031, receiving an external power supply off signal sent by a complex programmable logic device in an interconnect switch board, wherein the external power supply off signal is generated based on the voltage of a mains power supply board being lower than a threshold voltage;
[0128] S1032: Send a power supply signal to the backup power module according to the external power supply off signal, so that the backup power module supplies power to the memory resource integrated machine.
[0129] After the above S1032, the method may include: sending a power consumption limit signal to a third baseboard management controller corresponding to a computing node in each computing node board.
[0130] Further, refer to Figure 7 , Figure 7 It means that a power failure triggers the backup power memory data preservation solution. If an unrecoverable failure of the PSU is detected, the memory pre-dump strategy is triggered first. When the CPLD detects that the PSU power supply is lost, the memory backup power data protection solution is triggered again.
[0131] Specifically, an unrecoverable fault of the PSU power supply is triggered. The CXL SW Board BMC monitors the health status of the PSU power supply module through PMBus. If an unrecoverable serious fault is triggered, the memory pre-dump operation is started to dump the memory resources to the non-volatile storage unit. Once the power supply is lost, the CPLD recognizes that the board standby voltage is lower than the threshold, determines that the power supply is abnormal, and triggers the BBU backup power module to supply power to the entire system. Based on the pre-dump, the memory resource dump operation continues to be performed to transfer more memory data to the non-volatile storage unit.
[0132] 1) CXL SW Board BMC monitors the health status of the PSU power supply module through PMBus commands. If it is identified that the PSU power supply module has power redundancy loss, and the power supply has abnormal output voltage, abnormal output current, AC Lost and other abnormal alarm states, the memory data pre-dump strategy is triggered;
[0133] 2) CXL SW Board BMC informs the host computing node CPU upper management software through the network to transfer the memory data to non-volatile storage devices such as hard disks in advance, and stores the CXL memory tag of the dumped memory data, and notifies CXL SW Board BMC through the network Redfish interface;
[0134] 3) If during the memory data pre-dump process, the CPLD identifies that the standby voltage of the power supply card is lower than the threshold voltage, it is determined that the power supply is lost. Take the following measures:
[0135] a. Immediately notify the BBU backup power module MCU, which will supply power to the entire system. It will also inform the CXL SW Board BMC of power loss through hardware links such as GPIO or SMBus, triggering the BBU backup power control logic.
[0136] b. The CXL SW Board BMC identifies the CXL memory that has completed the memory dump and performs hot removal processing;
[0137] c. The CXL SW Board BMC sends a Redfish command through the network to inform the corresponding Host computing node BMC to control the CPU of the computing node to shut down and power off.
[0138] d. For the memory that has not been dumped, continue to perform the pre-dump operation. After completion, perform the memory hot-swap and host power-off processing.
[0139] It should be noted that, refer to Figure 8 , Figure 8 It is a memory hot-swap topology. After the CXL SW Board BMC recognizes that all memory resources corresponding to a computing node in the topology have completed memory data dump, it notifies the DIMM Board BMC through the network, and then sends a command to the eFuse device corresponding to this part of the memory through I2C to power off this part of the memory resources.
[0140] The CXL SW Board BMC sends a Redfish command through the network to inform the corresponding Host computing node BMC to control the CPU of the computing node to shut down and power off. This enables the unit in the memory pool resource all-in-one machine scenario to power off, further reducing the power consumption of the entire machine in the BBU backup power module power supply scenario, further extending the BBU power supply time, and thus saving more memory data without loss.
[0141] Therefore, the backup power method provided by the embodiment of the present invention intelligently monitors the power supply fault state through the first baseboard management controller in the interconnected switching board, and flexibly adjusts the backup power strategy according to different fault states (first or second power supply fault state). In the case of a city power outage or power loss of the power module, the backup power module can quickly intervene to ensure the continuous power supply of the memory resource integrated machine, and at the same time execute the memory resource dump strategy or pre-dump strategy to effectively prevent data loss, ensure the stable operation of the system, and significantly improve the reliability and data security of the system. That is, the present application is essentially to reorganize computing resources and memory resources in an integrated resource architecture solution, dynamically allocate all-in-one machine memory resources to different computing resource service nodes, greatly improve the utilization rate of server hardware resources, and reduce the operation and maintenance costs of maintaining multiple different resource server cabinets separately. Under the integrated architecture, the topological connection relationship between memory resources and different Host computing nodes is monitored. Once the all-in-one machine loses city power or a power failure causes power supply abnormality, in order to avoid affecting the normal operation of all memory resources and Host computing nodes in the all-in-one machine. Based on the memory resource data dump, an automatic controlled hot-swap strategy is adopted for the CXL memory resources after the dump is completed. The memory resources that have completed the data dump are hot-plugged and powered off, and the Host computing nodes that use the corresponding Device memory resources are controlled to shut down and power off, further reducing the power consumption of the entire machine, thereby extending the power supply time of the BBU backup power module and ensuring that more memory resources complete the data dump migration.
[0142] In addition, in the power backup method provided by the embodiment of the present invention, when the CXL SW Board CPLD identifies that the Standby voltage of the mains power supply board is lower than the threshold voltage, it is determined that the mains power is lost. The BBU backup power module MCU is immediately notified, and the BBU module supplies power to the entire system, and the CXL SW Board BMC is notified of the power loss through hardware links such as GPIO or SMBus, thereby triggering the BBU backup power control logic.
[0143] In the power backup method provided in the embodiment of the present invention, the CXL SW Board BMC notifies each computing node BMC through a network hardware link and a software protocol such as IPMI or Redfish, controls the CPU power consumption capping limit of the computing node, reduces the power consumption of the computing node, and extends the BBU power supply time.
[0144] In the power backup method provided by the embodiment of the present invention, the CXL SW Board BMC notifies the Host computing node CPU through the network Redfish interface to trigger the memory resource pool memory data dump logic.
[0145] In the power backup method provided by the embodiment of the present invention, the upper-layer system management software running in each Host computing node CPU transfers the memory data to a non-volatile storage device such as a hard disk, stores the CXL memory tag of the dumped memory data, and notifies the CXL SW Board BMC through the network Redfish interface.
[0146] In the backup power method provided by the embodiment of the present invention, the CXL memory information after the memory data is dumped is processed by the CXL SW Board BMC, matched with the CXL memory resource allocation topology established and saved in the CXL SW Board BMC, and matched to the computing node using the memory resource. When all the CXL memory resources matched in the computing node topology have completed the memory data dump, the hot plug of the part of the memory resource is triggered, and the part of the CXL memory is hot removed, thereby reducing the power consumption of the memory resource and further extending the power supply time of the BBU.
[0147] In the power backup method provided in the embodiment of the present invention, after the CXL SW Board BMC identifies that all memory resources corresponding to a computing node in the topology have completed memory data dumping, this part of memory information is sent to the DIMMBoard BMC through the network, and then the eFuse device corresponding to this part of memory is notified through I2C to power off this part of memory resources.
[0148] In the backup power method provided in the embodiment of the present invention, the CXL SW Board BMC sends a Redfish command through the network to inform the corresponding Host computing node BMC, and controls the CPU of the computing node to shut down and power off. The unit power-off of the memory pool resource all-in-one machine scenario is realized, the power consumption of the whole machine in the BBU backup power module power supply scenario is further reduced, and the power supply time of the BBU is further extended, so that more memory data can be saved without loss.
[0149] Reference Figure 3 , shows a schematic diagram of the structure of a backup power device provided by an embodiment of the present invention, which is applied to a baseboard management controller in an interconnection switching board in a memory resource integrated machine, wherein the memory resource integrated machine includes the interconnection switching board, a power supply module and a backup power module, and the device includes:
[0150] Confirmation module 301, used to obtain the power supply fault status corresponding to the memory resource integrated machine;
[0151] The first execution module 302 is used to control the backup power module to supply power to the memory resource integrated machine based on the external power supply power-off signal sent by the complex programmable logic device in the interconnection switching board if the power supply fault state is a first power supply fault state, and to execute a memory resource dump strategy;
[0152] The second execution module 303 is used to execute the memory pre-dump strategy if the power supply fault state is the second power supply fault state, and control the backup power module to supply power to the memory resource integrated machine when it is detected that the power supply module is in a power loss state, and execute the memory resource dump strategy.
[0153] The backup power device provided by the embodiment of the present invention intelligently monitors the power supply fault state through the first baseboard management controller in the interconnected switching board, and flexibly adjusts the backup power strategy according to different fault states (first or second power supply fault state). In the case of a city power outage or power loss of the power supply module, the backup power module can quickly intervene to ensure the continuous power supply of the memory resource integrated machine, and at the same time execute the memory resource dump strategy or pre-dump strategy, effectively preventing data loss, ensuring the stable operation of the system, and significantly improving the reliability of the system and data security.
[0154] The embodiment of the present invention also provides a communication device, such as Figure 4 As shown, it includes a processor 401, a communication interface 402, a memory 403 and a communication bus 404, wherein the processor 401, the communication interface 402, and the memory 403 communicate with each other through the communication bus 404.
[0155] Memory 403, used for storing computer programs;
[0156] The processor 401 can implement the above-mentioned power backup method when it is used to execute the program stored in the memory 403.
[0157] Among them, the memory and the processor are connected in a bus manner, and the bus may include any number of interconnected buses and bridges, and the bus connects various circuits of one or more processors and memories together. The bus can also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits together, which are all well known in the art, so this article will not further describe them. The bus interface provides an interface between the bus and the transceiver. The transceiver can be one element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices on a transmission medium. The data processed by the processor can be transmitted on a wired medium or on a wireless medium through an antenna. Further, the antenna also receives data and transmits the data to the processor. The processor is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. The memory can be used to store data used by the processor when performing operations.
[0158] The communication bus mentioned in the above terminal can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.
[0159] The communication interface is used for communication between the above terminal and other devices.
[0160] The memory may include a random access memory (RAM) or a non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.
[0161] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
[0162] In another embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium stores instructions. When the instructions are executed on a computer, the computer executes the power backup method described in any one of the above embodiments.
[0163] In another embodiment of the present invention, a computer program product including instructions is provided. When the computer program product is run on a computer, the computer executes the power backup method described in any one of the above embodiments.
[0164] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive Solid State Disk (SSD)), etc.
[0165] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.
[0166] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.
[0167] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.
Claims
1. A backup power system, characterized in that: The backup power system includes a memory resource integrated machine, which includes an interconnection switching board, a computing node board, a memory resource board, a power module and a backup power module; the interconnection switching board includes a first baseboard management controller and an interconnection switching chip; the interconnection switching chip is used to connect the computing nodes in the computing node board and the memory modules in the memory resource board; The first baseboard management controller is used to obtain the power supply fault state corresponding to the memory resource integrated machine; if the power supply fault state is the first power supply fault state, the backup power module is controlled to supply power to the memory resource integrated machine based on the external power supply power-off signal sent by the complex programmable logic device in the interconnection switching board, and a memory resource dump strategy is executed; If the power supply fault state is the second power supply fault state, the memory pre-dump strategy is executed, and when it is detected that the power supply module is in a power loss state, the backup power module is controlled to supply power to the memory resource integrated machine, and the memory resource dump strategy is executed; The obtaining of the power supply fault status corresponding to the memory resource integrated machine includes: In case of receiving an external power supply off signal sent by the complex programmable logic device in the interconnection switch board, determining that the power supply fault state is a first power supply fault state; In the case where it is detected that the power module is in a fault state, determining that the power supply fault state is a second power supply fault state; The execution of the memory pre-dump strategy includes: Sending power module failure warning information to the computing nodes in the computing node board, and transferring the memory data corresponding to the computing nodes to a preset non-volatile storage device; The execution memory resource dump strategy includes: Acquire second target memory data, wherein the second target memory data is in an undumped state; The second target memory data is transferred to a corresponding preset non-volatile storage device.
2. The system according to claim 1, characterized in that The backup power system also includes a network switching chip board; The computing node board, the memory resource board and the interconnection switching board are connected via the network switching chip board.
3. The system according to claim 2, characterized in that The computing node board, the interconnection switch board and the memory resource board are connected according to a preset topology connection mode.
4. The system according to claim 3, characterized in that The preset topology connection method includes connecting the interconnection switching chip upstream to the port of the computing node board and downstream to the memory resource board; configuring the upstream and downstream interconnection relationship of the interconnection switching chip and the memory resource slice management by the management computing node, and the first baseboard management controller of the interconnection switching board interacts with the management computing node through a network preset interface to obtain the downstream port corresponding to the memory resource of the upstream computing node of the interconnection switching chip of the interconnection switching board, and form a connection topology between the computing resources and the memory resources.
5. The system according to claim 1, characterized in that The interconnection switch board includes a management computing node and a first baseboard management controller; The management computing node is used to control the interconnection switching chip to manage and configure the memory resource information; The first baseboard management controller is connected to the management computing node through a preset network, and the first baseboard management controller is used to interact with the management computing node to obtain the memory resource information.
6. The system according to claim 1, characterized in that The memory resource board includes a memory controller, a second baseboard management controller and a memory module; The memory controller is used to connect to the interconnection switching board through a preset interface, monitor and manage memory resource information, and transfer the interconnection switching bus of the memory module to the interconnection switching chip in the interconnection switching board, so that the computing node board uses the memory resource information corresponding to the memory module; The second baseboard management controller is connected to the memory controller via a preset bus, and is used to monitor and manage the interconnect exchange memory. The second baseboard management controller controls power on and off of the memory modules in each of the memory controllers.
7. A power backup method, characterized in that: A first baseboard management controller applied to an interconnection switching board in a backup power system, wherein the backup power system includes a memory resource integrated machine, the memory resource integrated machine includes the interconnection switching board, a computing node board, a memory resource board, a power module and a backup power module; the interconnection switching board includes a first baseboard management controller and an interconnection switching chip; The interconnection switching chip is used to connect the computing nodes in the computing node board and the memory modules in the memory resource board. The method includes: Obtaining a power supply fault status corresponding to the memory resource integrated machine; If the power supply fault state is a first power supply fault state, the backup power module is controlled to supply power to the memory resource integrated machine based on an external power supply power-off signal sent by the complex programmable logic device in the interconnection switching board, and a memory resource dump strategy is executed; If the power supply fault state is the second power supply fault state, the memory pre-dump strategy is executed, and when it is detected that the power supply module is in a power loss state, the backup power module is controlled to supply power to the memory resource integrated machine, and the memory resource dump strategy is executed; The obtaining of the power supply fault status corresponding to the memory resource integrated machine includes: In case of receiving an external power supply off signal sent by the complex programmable logic device in the interconnection switch board, determining that the power supply fault state is a first power supply fault state; In the case where it is detected that the power module is in a fault state, determining that the power supply fault state is a second power supply fault state; The execution of the memory pre-dump strategy includes: Sending power module failure warning information to the computing nodes in the computing node board, and transferring the memory data corresponding to the computing nodes to a preset non-volatile storage device; The execution memory resource dump strategy includes: Acquire second target memory data, wherein the second target memory data is in an undumped state; The second target memory data is transferred to a corresponding preset non-volatile storage device.
8. The method according to claim 7, characterized in that The external power supply off signal is generated when the complex programmable logic device in the interconnection switch board recognizes that the voltage corresponding to the external power supply board is lower than a preset voltage.
9. The method according to claim 8, characterized in that In the case where it is detected that the power module is in a fault state, determining that the power supply fault state is a second power supply fault state includes: Monitoring the power status corresponding to the power module through a power management bus command; Determining whether the power module is in a fault state based on the power state; In the case where it is detected that the power module is in a fault state, determining that the power supply fault state is a second power supply fault state; Among them, the fault state includes at least one of the power supply module being in a power redundancy loss state, the output voltage corresponding to the power supply module being in an abnormal state, the output current corresponding to the power supply module being in an abnormal state, and the power supply module being in an AC power interruption state.
10. The method according to claim 7, characterized in that When it is detected that the power module is in a power loss state, controlling the backup power module to supply power to the memory resource integrated machine includes: When it is detected that the memory pre-dump strategy is executed and the power module is in a power loss state, the backup power module is controlled to supply power to the memory resource integrated machine.
11. The method according to claim 7, characterized in that The execution memory resource dump strategy includes: Acquire first target memory data, wherein the target memory data is in a dump completion state; and perform hot removal processing on the first target memory data.
12. The method according to claim 11, characterized in that The performing hot removal processing on the first target memory data includes: Determine a first target computing node corresponding to the first target memory data according to the first target memory data; Control the first target computing node to power off.
13. The method according to claim 7, characterized in that The controlling the backup power module to supply power to the memory resource integrated machine based on the external power supply power-off signal sent by the complex programmable logic device in the interconnection switch board includes: Receiving an external power supply off signal sent by a complex programmable logic device in an interconnect switch board, wherein the external power supply off signal is generated based on a mains power supply card voltage being lower than a threshold voltage; A power supply signal is sent to the backup power module according to the external power supply off signal, so that the backup power module supplies power to the memory resource integrated machine.
14. The method according to claim 13, characterized in that After the step of sending a power supply signal to the backup power module according to the external power supply off signal so that the backup power module supplies power to the memory resource integrated machine, the method includes: A power consumption limiting signal is sent to a third baseboard management controller corresponding to a computing node in each computing node board.
15. A power backup device, characterized in that: A first baseboard management controller applied to an interconnection switching board in a backup power system, wherein the backup power system includes a memory resource integrated machine, the memory resource integrated machine includes the interconnection switching board, a computing node board, a memory resource board, a power module and a backup power module; the interconnection switching board includes a first baseboard management controller and an interconnection switching chip; The interconnection switching chip is used to connect the computing nodes in the computing node board and the memory modules in the memory resource board. The device includes: An acquisition module, used to acquire a power supply fault status corresponding to the memory resource integrated machine; A first execution module, configured to control the backup power module to supply power to the memory resource integrated machine based on an external power supply power-off signal sent by a complex programmable logic device in the interconnection switching board if the power supply fault state is a first power supply fault state, and to execute a memory resource dump strategy; A second execution module is used to execute the memory pre-dump strategy if the power supply fault state is a second power supply fault state, and control the backup power module to supply power to the memory resource integrated machine when detecting that the power supply module is in a power loss state, and execute the memory resource dump strategy; The obtaining of the power supply fault status corresponding to the memory resource integrated machine includes: In case of receiving an external power supply off signal sent by the complex programmable logic device in the interconnection switch board, determining that the power supply fault state is a first power supply fault state; In the case where it is detected that the power module is in a fault state, determining that the power supply fault state is a second power supply fault state; The execution of the memory pre-dump strategy includes: Sending power module failure warning information to the computing nodes in the computing node board, and transferring the memory data corresponding to the computing nodes to a preset non-volatile storage device; The execution memory resource dump strategy includes: Acquire second target memory data, wherein the second target memory data is in an undumped state; The second target memory data is transferred to a corresponding preset non-volatile storage device.
16. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the power backup method as described in any one of claims 7 to 14.
17. A storage medium for storing a program, characterized in that: When the program is executed by the processor, the power backup method as described in any one of claims 7 to 14 is implemented.
18. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the power backup method as described in any one of claims 7 to 14 is implemented.
Citation Information
Patent Citations
Log storage method and device
CN113721746A
Memory resource management system, method, device and equipment and storage medium
CN117992270A
Storage control system managing file-level and block-level storage services, and methods for controlling such storage control system
US20180137013A1
Application-Managed Fault Detection For Cross-Region Replicated Object Stores
US20230393927A1
Method of controlling an apparatus, which is operated by a solid-state processor and powered by an electric mains, in case of a power failure and apparatus employing said method
US4412284A
