Hard disk information management system and hard disk information management method

Abstract

This application discloses a hard disk information management system and a hard disk information management method, relating to the field of server technology. Addressing scenarios where different types of hard disks are mixed, it provides a hard disk module including a first hard disk unit for connecting a first type of hard disk and a second hard disk unit for connecting a second type of hard disk. The hard disk information management system can dynamically generate a logical disk order for the first type of hard disk that the controller cannot directly monitor. The controller receives the logical disk order sent by the boot module and obtains the physical information of the hard disks connected to the hard disk module. Through the controller, the logical disk order and physical information can be associated to obtain a mapping relationship between the logical disk order and physical information. Based on the mapping relationship, the controller can quickly locate the physical information of the hard disk to be managed. Through dynamic association, accurate and rapid association between the logical disk order and physical information of different types of hard disks is achieved, enabling efficient management of the hard disks.

Description

Technical Field

[0001] This application relates to the field of server technology, and in particular to a hard disk information management system and a hard disk information management method. Background Technology

[0002] With the rapid development of technologies such as cloud computing, big data, and artificial intelligence, server storage systems need to integrate multiple types of storage devices within a limited space to meet the balance between high performance and low cost. In this scenario, a mixed deployment mode of Serial Advanced Technology Attachment (SATA) hard drives and Non-Volatile Memory Express (NVMe) hard drives has become the mainstream choice. Currently, there are many problems with hard drive management in this scenario. The Baseboard Management Controller (BMC) has the ability to monitor the physical silkscreen of all hard drives through the Complex Programmable Logic Device (CPLD) on the backplane, and can obtain the physical location of the hard drives in the server in real time. However, for SATA hard drives that are directly output by the Central Processing Unit (CPU), such as those on Input / Output Hubs (IOHs), the BMC cannot directly monitor them. The BMC's management relies on the logical disk order assigned and reported by the Basic Input / Output System (BIOS) at startup. Since the logical drive order assigned by the BIOS is often static or based on fixed rules, it cannot flexibly adapt to the actual application scenarios of the hard drive, making it difficult to associate with the physical location of the hard drive, which affects the management of the hard drive.

[0003] In related technologies, given the complex and ever-changing configurations of server hard drives, how to quickly and accurately associate the logical disk order with the physical location of the hard drive, thereby achieving efficient hard drive management, has become an urgent technical problem to be solved. Summary of the Invention

[0004] This application provides a hard disk information management system and a hard disk information management method to at least solve the problem in related technologies of how to quickly and accurately associate the logical disk order of a hard disk with its physical location, thereby achieving efficient management of the hard disk.

[0005] This application provides a hard disk information management system, including:

[0006] The hard disk module includes a first hard disk unit for connecting a first type of hard disk and a second hard disk unit for connecting a second type of hard disk;

[0007] A boot module is connected to the hard disk module, and the boot module is used to generate a logical disk order for the first type of hard disk.

[0008] The controller is connected to both the startup module and the hard disk module.

[0009] The controller is configured to:

[0010] Receive the logical disk sequence sent by the startup module;

[0011] Obtain the physical information of the hard drive connected to the hard drive module;

[0012] Based on the logical disk order and the physical information, a mapping relationship between the logical disk order and the physical information of the hard disk is generated; wherein, the mapping relationship is used for hard disk information management of the hard disk.

[0013] This application also provides a method for hard disk information management, including:

[0014] Receive the logical disk order sent by the startup module;

[0015] Obtain the physical information of the hard drive connected to the hard drive module;

[0016] Based on the logical disk order and the physical information, a mapping relationship between the logical disk order and the physical information of the hard disk is generated; wherein, the mapping relationship is used for hard disk information management of the hard disk.

[0017] This application addresses scenarios where different types of hard drives are mixed, providing a hard drive module including a first hard drive unit for connecting a first type of hard drive and a second hard drive unit for connecting a second type of hard drive. The hard drive information management system can dynamically generate a logical disk order for the first type of hard drive that the controller cannot directly monitor. The controller receives the logical disk order sent by the boot module and obtains the physical information of the hard drives connected to the hard drive module. Through the controller, the logical disk order and physical information can be associated to obtain a mapping relationship between the logical disk order and physical information. Based on the mapping relationship, the controller can quickly locate the physical information of the hard drive that needs to be managed. In the face of complex and ever-changing server hard drive configurations, the system can achieve accurate and rapid association between the logical disk order and physical information of different types of hard drives through dynamic association, thereby achieving efficient hard drive management. Attached Figure Description

[0018] To more clearly illustrate the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 A schematic diagram of the hard disk information management system provided in this application embodiment. Figure 1 ;

[0020] Figure 2 A schematic diagram of the hard disk information management system provided in this application embodiment. Figure 2 ;

[0021] Figure 3 A schematic diagram of the hard disk information management system provided in this application embodiment. Figure 3 ;

[0022] Figure 4 A flowchart illustrating the hard disk information management method provided in this application embodiment. Figure 1 ;

[0023] Figure 5 A flowchart illustrating the hard disk information management method provided in this application embodiment. Figure 2 ;

[0024] Figure 6 This is a schematic diagram of the hard disk information management device provided in the embodiments of this application;

[0025] Figure 7 A schematic diagram of the structure of the electronic device provided in this application. Detailed Implementation

[0026] 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, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the protection scope of this application.

[0027] It should be noted that, in the description of this application, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. The terms "first," "second," etc., in this application are used to distinguish similar objects and are not used to describe a specific order or sequence.

[0028] The explosive growth of data volume necessitates servers integrating more storage devices within limited space, while achieving a balance between high performance and low cost. Against this backdrop, CPU-to-Host (IOH) systems, as core components connecting processors and storage devices, have adopted a mainstream deployment mode that mixes SATA and NVMe hard drives: SATA drives meet the needs of cold data storage with their large capacity and low cost; NVMe drives, with their high-speed Peripheral Component Interconnect Express (PCIe) interface, provide performance support for high-load scenarios such as Artificial Intelligence (AI) training and database read / write operations. Currently, hard drive management in this scenario faces numerous challenges. While the Backplane Component Management (BMC) has the capability to monitor the physical silkscreen of all hard drives via the backplane CPLD, allowing real-time acquisition of the hard drive's physical location within the server, the BMC cannot directly monitor SATA hard drives on CPU-to-Host systems. The industry commonly uses the BIOS to send information about SATA hard drives on the CPU-to-Host system. However, due to the vast differences in customer business needs and the complexity and variability of server hard drive configurations—for example, different customers may have different requirements for the number, brand, and capacity of hard drives, and even the same customer may replace or expand hard drives at different stages—these challenges remain. In this situation, the BIOS struggles to be compatible with all hard drive configurations, and the drive sequence information it sends cannot accurately correspond to the actual physical silkscreen markings on the hard drives. This drive sequence information can also be referred to as the logical drive sequence. Consequently, the logical-level hard drive information sent by the BIOS cannot be effectively integrated with the physical-level hard drive information obtained by the BMC through the CPLD. When managing, troubleshooting, or expanding server hard drives, maintenance personnel find it difficult to quickly and accurately match the logical drive sequence with the physical location, significantly reducing server hard drive management efficiency and increasing maintenance costs and complexity.

[0029] In related technologies, hard drive mapping is typically achieved through a single module, either BIOS or BMC. In the BIOS-dominated approach, the BIOS directly generates the logical drive order containing physical silkscreen information (e.g., "Slot1_Disk0"). However, this approach requires encoding the physical silkscreen information for each server model in the BIOS firmware, making it unsuitable for hardware differences between different server models. When a customer replaces the hard drive backplane, the BIOS firmware needs to be re-flashed, resulting in high maintenance costs. In the BMC-dominated approach, the BMC continuously polls the presence status of SATA and NVMe drives and reverses the logical drive order according to predetermined rules. However, this approach is prone to data conflicts and misjudgments in scenarios where multiple hard drives are hot-swapped simultaneously, and it is incompatible with the BIOS's dynamic device enumeration strategy.

[0030] In related technologies, traditional servers can also use a static mapping table of "port-physical silkscreen" to manage hard drives. However, this table only stores fixed hardware connection relationships and does not take into account the dynamic changes in the BIOS logical drive order. For example, a server's static mapping table defines "SATA_Port0→Slot1", but when the BIOS changes the enumeration order due to device driver upgrades, the hard drive corresponding to Slot1 may be marked as "other" by the BIOS, causing the logical-physical mapping to fail.

[0031] In related technologies, some enterprise-level servers still rely on maintenance personnel to manually configure hard drive mapping: manually associating logical drive order with physical silkscreen through the server management interface. This solution is not only inefficient but also prone to data loss due to human error. Especially in large-scale data center scenarios, manually configuring thousands of servers is almost impractical.

[0032] As can be seen from the above-mentioned technologies, existing technologies have failed to fundamentally solve the problem of logical and physical disconnect between server hard drives under complex configurations. There is an urgent need for a hard drive mapping solution that can dynamically adapt and collaborate across components. Given the complex and ever-changing configurations of server hard drives, how to quickly and accurately associate the logical drive order with the physical location of the hard drives, thereby achieving efficient hard drive management, has become a pressing technical problem to be solved.

[0033] To address the aforementioned issues, this application provides a hard disk information management system and a hard disk information management method. The hard disk information management system can dynamically generate a logical disk order for a first type of hard disk that cannot be directly monitored by the controller. The controller receives the logical disk order sent by the boot module and obtains the physical information of the hard disk connected to the hard disk module. Through the controller, the logical disk order and physical information can be associated to obtain a mapping relationship between the logical disk order and physical information. Based on the mapping relationship, the controller can quickly locate the physical information of the hard disk that needs to be managed.

[0034] In one possible implementation, this application focuses on overcoming the challenge of integrating physical silkscreen information of server hard drives, aiming to build an efficient and accurate mechanism for mapping physical silkscreen information. Through an innovative BIOS logical drive order allocation strategy and BMC intelligent mapping algorithm, it overcomes the technical bottlenecks of traditional solutions under complex hard drive configurations, achieving accurate association between the physical silkscreen information of NVMe hard drives and SATA hard drives on the IOH, providing reliable hardware management support for server storage systems, reducing operational complexity, and improving the overall operational efficiency of data centers.

[0035] To enable those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0036] Optionally, Figure 1A schematic diagram of the hard disk information management system provided in this application embodiment. Figure 1 ,like Figure 1 As shown, the hard disk information management system provided in this application embodiment includes a hard disk module 11, a startup module 12, and a controller 13.

[0037] The hard disk module 11 includes a first hard disk unit 110 for connecting a first type of hard disk and a second hard disk unit 111 for connecting a second type of hard disk.

[0038] Alternatively, the first type of hard drive can be a SATA hard drive or a Serial Attached SCSI Hard Disk Drive (SAS) hard drive. This type of hard drive cannot be directly monitored by the BMC.

[0039] It is understood that the embodiments of this application are explained with SATA hard drives as the first type of hard drive. The solutions of the embodiments of this application are also applicable to SAS hard drives or a combination of SAS hard drives and SATA hard drives as the first type of hard drive. The embodiments of this application can achieve accurate correspondence of physical silkscreen when different types of hard drives are mixed by appropriately adjusting the mapping rules and data processing methods, thereby further improving the versatility of the server storage system.

[0040] Optionally, the second type of hard drive can be an NVMe hard drive. The controller can manage the NVMe hard drive directly based on the obtained physical information of the NVMe hard drive and locate the physical location of the NVMe hard drive without the need for BIOS coordination.

[0041] The boot module 12 is connected to the hard disk module 11 and is used to generate a logical disk order for the first type of hard disk.

[0042] Optionally, the boot module 12 here is the BIOS in the hard disk information management system.

[0043] The controller 13 is connected to the startup module 12 and the hard disk module 11 respectively.

[0044] The controller 13 is configured to: receive the logical disk order sent by the boot module 12; obtain the physical information of the hard disk connected to the hard disk module 11; and generate a mapping relationship between the logical disk order and the physical information of the hard disk based on the logical disk order and the physical information.

[0045] Optionally, the BIOS can accurately identify the SATA hard drive port on the IOH during system startup and assign a unique logical drive order to the hard drive corresponding to each port. This logical drive order assignment needs to consider various factors such as the hard drive connection order and interface type to ensure the accuracy and uniqueness of the logical drive order.

[0046] Optionally, the controller 13 can be a BMC. This application embodiment mainly uses the controller 13 as a BMC as an example for explanation. The BMC is a standard management component of modern servers. It runs independently of the host CPU and is specifically responsible for hardware status monitoring, log recording and remote management, which can realize accurate and efficient management of hard disks.

[0047] It is understood that the controller 13 can also be a CPU, a microcontroller unit (MCU), or a field-programmable gate array (FPGA) or other devices that can perform the above functions.

[0048] The mapping relationship is used to manage hard drive information.

[0049] Optionally, physical information includes physical identification information and hard drive type.

[0050] Optionally, physical identification information is used to identify the physical location of the hard drive.

[0051] Optionally, the physical identification information includes at least one of physical silkscreen printing, i.e., silkscreen text printed on the hard drive bay, indicator lights or displays associated with the hard drive bay.

[0052] Optionally, the hard disk type is used to identify the type of hard disk, such as indicating that the hard disk is a first type of hard disk or indicating that the hard disk is a second type of hard disk.

[0053] This application addresses scenarios where different types of hard drives are mixed, providing a hard drive module including a first hard drive unit for connecting a first type of hard drive and a second hard drive unit for connecting a second type of hard drive. The hard drive information management system can dynamically generate a logical disk order for the first type of hard drive that the controller cannot directly monitor. The controller receives the logical disk order sent by the boot module and obtains the physical information of the hard drives connected to the hard drive module. Through the controller, the logical disk order and physical information can be associated to obtain a mapping relationship between the logical disk order and physical information. Based on the mapping relationship, the controller can quickly locate the physical information of the hard drive that needs to be managed. In the face of complex and ever-changing server hard drive configurations, the system can achieve accurate and rapid association between the logical disk order and physical information of different types of hard drives through dynamic association, thereby achieving efficient hard drive management.

[0054] Optionally, the startup module 12 is used to: identify a first type of hard disk connected to the first hard disk unit 110; obtain a preset allocation strategy; and generate a logical disk order for the first type of hard disk according to the preset allocation strategy.

[0055] In this embodiment, the startup module can automatically identify all first-type hard drives connected to the first hard drive unit, and then dynamically generate the logical disk order for the first-type hard drives according to a preset allocation strategy associated with them. Since the identification of the first-type hard drives is performed in real time, it can accurately and quickly identify all hard drives to be allocated logical disk orders, achieving accurate and rapid generation of logical disk orders. Combined with a flexible allocation strategy that does not rely on fixed static rules, it can adapt to a variety of application scenarios and different hard drive manufacturer configurations, improving the flexibility of hard drive management.

[0056] Optionally, the startup module 12 is configured to: send a hard disk enumeration command to the hard disk module 11 to obtain the interface status of the first hard disk unit 110; and identify the first type of hard disk connected to the first hard disk unit 110 based on the interface status.

[0057] The startup module of this application embodiment can obtain the interface status of the first hard disk unit by sending a hard disk enumeration command to the hard disk module. Based on the interface status, it can accurately identify the first type of hard disk connected to the hard disk unit. Through this setting, all first type hard disks can be detected comprehensively and accurately, thereby improving the accuracy of hard disk information management.

[0058] In one possible implementation, the BIOS generates and sends logical drive order data: During the server power-on startup phase, the BIOS first executes the Power-On Self-Test (POST) program to initialize and detect hardware devices. When a SATA controller on the IOH is detected, the SATA controller scanning module begins operation, obtaining the device connection status of each SATA port by sending specific device enumeration commands. If a SATA hard drive connection is detected, the logical drive order allocation module assigns a unique logical drive order to the hard drive according to a preset allocation strategy. For example, when using a port numbering order strategy, the hard drive connected to SATA port 1 will be assigned logical drive order 1, the hard drive connected to SATA port 2 will be assigned logical drive order 2, and so on. After allocation, the BIOS encapsulates the logical drive order information according to a specific data format and sends it to the BMC through a preset communication interface.

[0059] Optionally, the preset communication interface can be any one of shared memory, Intelligent Platform Management Interface (IPMI), Simple Network Management Protocol (SNMP) interface, or Redfish protocol interface.

[0060] Optionally, when sending the logical drive order, the BIOS may send other information related to the logical drive order, such as hard drive type identifier, port number, or logical drive order number, in the information sent.

[0061] Optionally, the startup module 12 is used to: obtain the allocation attribute information of the first hard disk unit according to a preset allocation strategy; and determine the logical disk order of the first type of hard disk according to the preset allocation strategy and the allocation attribute information.

[0062] Optionally, the preset allocation strategy includes at least one of the following: an allocation strategy based on port number order, an allocation strategy based on hard disk capacity, and an allocation strategy based on hard disk priority.

[0063] Optionally, if the preset allocation strategy includes an allocation strategy based on port number order, the allocation attribute information includes port number order; if the preset allocation strategy includes an allocation strategy based on hard disk capacity, the allocation attribute information includes hard disk capacity; if the preset allocation strategy includes an allocation strategy based on hard disk priority, the allocation attribute information includes hard disk priority.

[0064] It is understood that the preset allocation strategy here can be determined according to the actual situation, and the embodiments of this application do not impose specific restrictions on it.

[0065] Here, the embodiments of this application can obtain the corresponding allocation attribute information through a preset allocation strategy, and generate a logical disk order for each first type of hard disk quickly and accurately based on the allocation attribute information, thereby improving the flexibility and accuracy of hard disk management.

[0066] Optionally, the startup module 12 can access the server configuration file pre-stored in the non-volatile memory of the server, read the specified preferred disk order strategy field, and then read the allocation strategy information of the first type of hard disk. Based on the preferred disk order strategy field and the allocation strategy information, it can determine the target allocation strategy for generating the logical disk order from multiple preset allocation strategies, thereby dynamically realizing the accurate, fast and flexible generation of the logical disk order.

[0067] Optionally, the startup module 12 may obtain the preset allocation strategy in at least one of the following ways:

[0068] In response to the user's policy configuration operation, the policy configuration interface is displayed, and the user's input and / or selected preset allocation policy is obtained through the policy configuration interface.

[0069] Receive the preset allocation strategy sent by the controller 13.

[0070] Collect attribute information of the first type of hard disk, and determine the preset allocation strategy from multiple pre-configured allocation strategies based on the attribute information.

[0071] Optionally, the above policy configuration interface can be displayed on the server or on the user's terminal device.

[0072] The embodiments of this application can implement policy configuration in a variety of ways. They can be flexibly configured manually through the policy configuration interface to meet user needs, or automatically configured based on hard disk attributes, or policies can be directly issued by the controller for accurate configuration. By generating logical disk order flexibly and accurately, the compatibility of hard disk management is improved.

[0073] Optionally, the startup module 12 is configured to: respond to a hard disk hot-plug event and generate a logical disk order for the newly connected hard disk at a preset time.

[0074] Accordingly, the controller 13 is configured to: receive the logical disk order of the newly connected hard disk sent by the boot module 12 when a hard disk hot-plug event is detected; and update the mapping relationship between the logical disk order and physical information of the hard disk according to the logical disk order of the newly connected hard disk.

[0075] The embodiments of this application have the ability to dynamically respond to hard disk hot-plug events and update the mapping relationship in real time, thereby improving the availability of the system and the flexibility of association.

[0076] In this embodiment, dynamic management is supported. When a hard drive hot-swap event occurs on the server, the data can be updated in real time. The BMC automatically refreshes the mapping table and updates the physical silkscreen hardware identification and the display information of the remote management interface in a timely manner, thereby realizing dynamic management of the hard drive and ensuring the continuity and stability of the server storage system management.

[0077] Optionally, the physical information includes physical identification information and hard disk type; accordingly, the controller 13 is configured to: determine a mapping relationship generation strategy based on the hard disk type; and generate a mapping relationship between the logical disk order and the physical identification information of the hard disk based on the mapping relationship generation strategy and the physical identification information.

[0078] In this embodiment, the physical information includes physical identification information and hard disk type. The physical identification information is used to locate the physical location of the hard disk on the server, and the hard disk type is used by the controller to generate a targeted mapping relationship for different hard disks. This is applicable to the management of various types of hard disks and improves the accuracy and flexibility of hard disk information management.

[0079] Optionally, the controller 13 is configured to: determine the physical identification information of the first type of hard disk based on the hard disk type; and generate a mapping relationship between the logical disk order and the physical identification information of the first type of hard disk based on the physical identification information and logical disk order of the first type of hard disk.

[0080] Here, for the first type of hard disk, this embodiment of the application obtains the logical disk order through the startup module 12 and combines it with the physical identification information obtained by the controller 13 to determine the mapping relationship, thereby realizing accurate management of the information of the first type of hard disk.

[0081] Optionally, the physical information also includes a preset relationship between physical identification information and port number; correspondingly, the controller 13 is configured to: receive the logical disk number and the port number corresponding to the logical disk number sent by the boot module 12; and associate the physical identification information and logical disk number corresponding to the port number according to the preset relationship between physical identification information and port number to obtain the mapping relationship between the logical disk number and physical identification information of the first type of hard disk.

[0082] The information sent by the startup module in this embodiment includes the logical disk sequence and the corresponding port number. The physical identification information obtained by the controller has a preset relationship with the port number. By combining the port number, the logical disk sequence and the physical identification information can be accurately mapped.

[0083] Optionally, the controller 13 is configured to: determine the physical identification information of the second type of hard disk based on the hard disk type; and generate a mapping relationship between the logical disk order and the physical identification information of the second type of hard disk based on the physical identification information of the second type of hard disk and the preset second type logical disk order identifier.

[0084] In one possible implementation, the mapping relationship between logical drive order and physical silkscreen is established as follows: the BMC automatically identifies and binds the logical drive order and physical silkscreen sent by the BIOS. Specifically, for SATA hard drives, the BMC extracts the physical silkscreen from the list of non-NVMe drives belonging to the IOH board obtained from the CPLD, binds the corresponding logical drive order to the physical silkscreen according to the IOH physical port number sent by the BIOS, and generates a mapping entry containing the logical drive order, physical silkscreen, and hard drive type. For NVMe hard drives, the BMC directly uses the physical silkscreen marked as NVMe type by the CPLD as an identifier to generate a mapping entry. Exemplarily, for NVMe types, the logical drive order can be marked as none or a specific identifier, such as "NVMe_SlotX".

[0085] Optionally, after receiving the logical drive order from the BIOS and the physical silkscreen information of the hard drives from the backplane CPLD, the BMC can accurately map the logical drive order to the non-NVMe drives monitored in the CPLD. It is understood that the formulation of mapping rules needs to be combined with the server's hardware design and actual application scenarios to ensure the accuracy of the mapping results; this application embodiment does not impose specific limitations in this regard.

[0086] Alternatively, the physical screen printing can be obtained by BMC from the CPLD.

[0087] For the second type of hard drive, its physical identification information and logical disk order can be directly associated, without relying on the logical disk order dynamically generated by the boot module. Through direct association, hardware resources can be saved, and the logical disk order and physical identification information can be accurately and efficiently mapped, improving the accuracy and efficiency of hard drive information management.

[0088] Specifically, Figure 2 A schematic diagram of the hard disk information management system provided in this application embodiment. Figure 2 ,like Figure 2 As shown, the hard disk module 11 also includes a programmable controller 112.

[0089] The hard disk module 11 communicates with the controller 13 through a programmable controller 112.

[0090] Optionally, the programmable controller 112 is connected to the controller 13.

[0091] Optionally, the programmable controller 112 is connected to the first hard disk unit 110 and the second hard disk unit 111, respectively.

[0092] The programmable controller 112 is used to: acquire the physical identification information of the hard disk; and identify the hard disk type.

[0093] The controller 13 is used to read physical identification information and hard disk type through the connection channel between the controller 13 and the programmable controller 112.

[0094] This application embodiment obtains the physical identification information of the hard drive through a programmable controller and sends it to the controller. It reads information such as the physical silkscreen table, hard drive type identification data and non-NVMe disk list from a programmable controller such as a CPLD. The acquisition method is reliable and the information obtained is accurate, so as to achieve accurate acquisition of physical identification information and hard drive type.

[0095] Optionally, the programmable controller 112 is used to: access the storage unit 1122 of the programmable controller 112 to obtain physical identification information pre-stored in the storage unit 1122.

[0096] Optionally, the storage unit 1122 stores one or more physical information of each hard drive, including its actual physical silkscreen, interface type, and the IOH to which the SATA belongs.

[0097] Optionally, controller 13 is configured to store the mapping relationship in non-volatile memory.

[0098] Optionally, the storage unit 1122 is a non-volatile memory, specifically, it can be flash memory or an embedded multi-media card (eMMC).

[0099] Optionally, the mapping relationship can be stored to facilitate management and control.

[0100] The physical identification information is pre-stored in the storage unit, which enables efficient and accurate retrieval of the physical identification information.

[0101] Optionally, the programmable controller 112 is used to: detect the interface pin level status of the hard disk; and determine the hard disk type based on the interface pin level status.

[0102] Identifying hard drive type by detecting the level status of interface pins can improve the accuracy and efficiency of hard drive type detection.

[0103] In one possible implementation, the BMC acquires data from the CPLD: the BMC establishes a communication connection with the backplane CPLD via the Inter-Integrated Circuit (I2C) bus, and reads the physical silkscreen table, hard drive type identification data, and non-NVMe drive list from the CPLD. The physical silkscreen table records the physical silkscreen identifier corresponding to each hard drive bay; the hard drive type identification data determines whether the hard drive is a SATA or NVMe interface by detecting the specific pin level status of the hard drive interface through the CPLD; the non-NVMe drive list summarizes all physical silkscreens marked as SATA type.

[0104] Exemplary, Figure 3 A schematic diagram of the hard disk information management system provided in this application embodiment. Figure 3 ,like Figure 3 As shown, the programmable controller 112 includes a control unit 1120 and a bus unit 1121. The control unit 1120 includes, but is not limited to, a CPLD, MCU, or FPGA. The bus unit 1121 can be I2C.

[0105] The control unit 1120 and the bus unit 1121 are respectively connected to the first hard disk unit 110. The first hard disk unit 110 may be provided with at least one first type hard disk control submodule. Each first type hard disk control submodule is configured with multiple first ports, and the first type hard disk is connected to the first port.

[0106] The control unit 1120 and the bus unit 1121 are also connected to the second hard disk unit 111. The second hard disk unit 111 may be provided with at least one second type hard disk control submodule. Each second type hard disk control submodule is configured with multiple second ports, and the second type hard disk is connected to the second port.

[0107] Optionally, the bus unit 1121 is used to detect the specific pin level of the hard drive to determine whether it belongs to a SATA interface or an NVMe interface.

[0108] Optionally, controller 13 is a BMC module.

[0109] Optionally, the BMC module includes a hard disk management module, which is connected to the storage unit 1122 via a bus unit 1121.

[0110] Optionally, the BMC module includes an asset management module, which is connected to the startup module 12.

[0111] Optionally, the BMC module includes a hard disk logical-physical mapping engine that can perform at least one of the following functions: web interface display, light-emitting diode (LED) illumination, hard disk status monitoring and log alarm, hard disk information out-of-band management interface, and physical silkscreen storage unit.

[0112] Optionally, the hard drive module 11 is integrated into the server hard drive backplane, detects the hard drive's presence status through GPIO, reads the SATA interface voltage or PCIe link status through I2C, stores the physical silkscreen table, and provides information such as hard drive type identification data and non-NVMe disk list to the BMC.

[0113] Optionally, the first hard disk unit 110 can be a CPU direct output IOH module. The CPU direct output IOH module is directly output by the CPU, supports SATA hard disk connection, provides a physical connection port for SATA hard disks, and realizes data transmission between the CPU and SATA hard disks.

[0114] Optionally, the BMC module is integrated into the server motherboard. It receives logical drive sequence data sent by the BIOS through an interactive interface, and communicates with the backplane CPLD through the I2C bus to obtain data such as physical silkscreen. It has a built-in logical-physical mapping engine to establish the mapping relationship between logical drive sequence and physical silkscreen. It has a storage unit for storing the mapping table. It can also drive the physical silkscreen identification hardware and provide a remote management interface to display the mapping relationship.

[0115] Optionally, the BIOS module runs in the server BIOS firmware and is responsible for enumerating the SATA hard drives on the CPU direct output IOH and the NVMe hard drives when they are mixed during server startup or hard drive hot-swapping, generating logical disk order data and sending it to the BMC.

[0116] Optionally, the controller 13 is configured to: generate mapping relationship display information based on the mapping relationship; wherein the mapping relationship display information is a table and / or an undirected graph; determine the target hard disk in response to a user's query operation; and display the mapping relationship display information and / or the mapping relationship corresponding to the target hard disk based on the target hard disk.

[0117] Here, this application embodiment provides a function for displaying and querying mapping relationships, which makes it easier for users to understand hard disk information, realizes the visualization of hard disk information, and improves the user experience.

[0118] Optionally, the hard disk information management system further includes a physical identification indicator unit, which is bound to a corresponding hard disk; the physical identification indicator unit is connected to the controller; the controller is configured to send a type display command to the physical identification indicator unit according to the hard disk type; the physical identification indicator unit is used to indicate the hard disk type of the corresponding hard disk through different display states according to the type display command.

[0119] Optionally, the physical identification unit can be a corresponding LED light or LED screen. The controller distinguishes hard drive types by driving the physical silkscreen identification hardware, which helps users to intuitively and efficiently identify different hard drives and realize information management for different hard drives.

[0120] Optionally, a physical identification unit can also be used to indicate a faulty hard drive.

[0121] Optionally, the controller is configured to: monitor the operating status of the hard disk; determine the logical disk order of the faulty hard disk based on the operating status; determine the physical identification information of the faulty hard disk based on the logical disk order and mapping relationship of the faulty hard disk; and generate fault prompts and / or log alarm information based on the physical identification information of the faulty hard disk.

[0122] Optionally, the hard disk information management system also includes a physical silkscreen hard disk module, i.e., a physical identification indicator unit, which corresponds one-to-one with the server hard disk slots. It includes an LCD screen, a tri-color LED light group, etc., and is used to receive instructions from the BMC to display the logical disk order and type information of the hard disk.

[0123] Here, the embodiments of this application can monitor the hard disk status and locate faults in real time, thereby improving hard disk management efficiency and enhancing the stability and security of the server.

[0124] In one possible implementation, the hard drive information management system (BMC) provides dynamic updating and display of the mapping relationship: the BMC stores the final generated logical-physical mapping table in non-volatile memory. Simultaneously, the BMC displays the mapping relationship to maintenance personnel in several ways: firstly, it drives physical silkscreen identification hardware (such as front panel LEDs) to display information at the corresponding physical silkscreen location on the hard drive, distinguishing hard drive types by color (e.g., SATA hard drives are displayed in blue, NVMe hard drives in green); secondly, it provides a mapping table query function for maintenance personnel through remote management interfaces such as IPMI, SNMP, Redfish, or a web management interface. Maintenance personnel can obtain information such as the hard drive's physical silkscreen, type, and logical drive order through corresponding commands or operations. The BMC monitors the hard drives in real time, and when a corresponding alarm occurs, it also activates fault lights and logs according to the real-time location, facilitating troubleshooting and subsequent operations such as drive replacement by maintenance personnel.

[0125] Figure 4 A flowchart illustrating the hard disk information management method provided in this application embodiment. Figure 1 The execution entity of the hard disk information management method provided in this application embodiment can be the aforementioned controller 13, such as... Figure 4 As shown, embodiments of this application provide a hard disk information management method, which is described in detail below:

[0126] 401. Receive the logical disk sequence sent by the startup module.

[0127] 402. Obtain the physical information of the hard drive connected to the hard drive module.

[0128] 403. Generate the mapping relationship between the logical disk order and physical information of the hard drive.

[0129] The mapping relationship is used to manage hard drive information.

[0130] The execution methods of the aforementioned hard disk information management system can all be applied to the hard disk information management method in the embodiments of this application.

[0131] The following describes a method for managing hard drive information in a 2-Unit (2U) server where NVMe and SATA hard drives are mixed.

[0132] For example, if a 2U server's CPU direct output IOH provides 4 SATA hard drive slots (Slot1-Slot4), the server is also equipped with 4 NVMe hard drive slots (Slot5-Slot8).

[0133] Step 5.1: The backplane CPLD monitors the hard drive presence signal via GPIO. A high level indicates that the hard drive is inserted. It detects the SATA interface voltage via I2C; 3.3V indicates that the SATA hard drive is present and stores physical silkscreen information. As shown in Table 1, Table 1 is a schematic table of the correspondence between physical silkscreen and hard drive modules provided in the embodiments of this application.

[0134] Table 1. Diagram showing the correspondence between physical silkscreen markings and hard drive modules.

[0135]

[0136] Step 5.2: BIOS sends logical disk order data:

[0137] When the server starts, the BIOS calls the SATA controller driver of the IOH to enumerate the SATA hard drives on the IOH. If the "Device Present" status bit of the SATA interfaces in Slot1 and Slot3 is detected to be 1 (hard drive present), the BIOS assigns logical disk order according to the IOH controller sequence and the corresponding port sequence: for example, Slot1 corresponds to "BIOS_Disk0" (IOH0_SATA_Port0), and Slot3 corresponds to "BIOS_Disk1" (IOH0_SATA_Port2). Then, the BIOS sends the logical disk order, port number, and capacity information to the BMC through interactive interfaces such as IPMI / Redfish / shared memory: {Logical disk order: "BIOS_Disk0", port number: "IOH0_SATA_Port0", capacity: 2TB…}, {Logical disk order: "BIOS_Disk1", ​​port number: "IOH0_SATA_Port2", capacity: 4TB…}.

[0138] Step 5.3: BMC acquires CPLD data:

[0139] Data type (1): The BMC reads the CPLD data through the I2C bus and obtains: Physical silkscreen list: Slot1-Slot8;

[0140] Data type (2): Hard disk type data (specific pin level state): Slot1 (SATA interface, subordinate to IOHx) and Slot3 (SATA interface, subordinate to IOHx) are SATA type; Slot2 (PCIe), Slot4 (PCIe), and Slot5-Slot8 (PCIe) are NVMe type;

[0141] Data type (1): Non-NVMe disk list: Slot1, Slot3.

[0142] Step 5.4: Establish logical-physical mapping relationship:

[0143] Based on the logical drive order and the non-NVMe drive mapping monitored in the CPLD, the BMC arranges the non-NVMe drives sequentially according to the logical drive order sent by the BIOS, starting from the first non-NVMe drive, ensuring that the SATA hard drives sent by the BIOS correspond to the physical silkscreen. The automatically generated mapping table is shown in Table 2 below. Table 2 is a schematic table of SATA hard drive mapping provided in the embodiments of this application.

[0144] Table 2 SATA Hard Drive Mapping Diagram

[0145]

[0146] The above is a simple example to introduce the solution. For IOH, regardless of whether NVMe drives are inserted in the front, rear, or mixed in the middle, the same mapping and sorting method can be used to achieve accurate correspondence between the logical drive order and the physical silkscreen.

[0147] Optionally, Figure 5 A flowchart illustrating the hard disk information management method provided in this application embodiment. Figure 2 ,like Figure 5 As shown, the embodiments of this application include the following steps:

[0148] 501. Server startup or hot-plug event occurred.

[0149] 502. Determine whether it involves a Type 1 hard drive.

[0150] If so, then the following plan will be implemented:

[0151] 5031. The startup module invokes the first hard disk unit driver to enumerate the first type of hard disk.

[0152] 5032. Start the module to assign logical disk order and record port numbers.

[0153] If not, or if S5032 has already been executed in the case of yes, then perform the following operations:

[0154] 504. Start the module to package data and send it to the controller.

[0155] 505. The controller reads physical information through the integrated circuit bus.

[0156] 506. The controller establishes a mapping relationship based on a fixed mapping table.

[0157] 507. The controller stores the mapping table to flash memory.

[0158] 508. Controller drives the physical silkscreen marking hardware display.

[0159] 509. The controller displays the mapping table through the remote management interface.

[0160] Optionally, the embodiments of this application can accurately correspond logical and physical information. By sending the logical disk order through BIOS and dynamically establishing the mapping relationship by combining BMC with CPLD data, the problem of mismatch between the logical disk order and physical silkscreen of SATA hard drives on the CPU direct output IOH is effectively solved. This achieves accurate correspondence between logical and physical information when NVMe hard drives and SATA hard drives on IOH are mixed, providing an accurate data foundation for server hard drive management.

[0161] Optionally, the embodiments of this application can adapt to complex hard drive configurations. In response to the diverse hard drive configuration needs of customers, the BIOS can dynamically generate logical drive order, and the BMC can achieve flexible mapping through a fixed mapping table and CPLD data. Without the need for extensive modifications to hardware or software, it can adapt to hard drive configurations of different quantities, brands, and capacities, greatly improving the versatility and flexibility of server hard drive management.

[0162] Optionally, the embodiments of this application can improve operation and maintenance efficiency. Operation and maintenance personnel can intuitively obtain the logical disk sequence information of the hard drive through the physical silkscreen identification hardware, or quickly query the mapping table through the remote management interface, without having to perform tedious manual verification. The single disk location time is shortened, which improves the efficiency of server hard drive fault diagnosis, capacity expansion and other operation and maintenance operations, and reduces operation and maintenance costs.

[0163] Optionally, this application embodiment supports dynamic management. When a hard drive hot-swap event occurs on the server, the data can be updated in real time. The BMC automatically refreshes the mapping table and updates the physical silkscreen hardware and the display information of the remote management interface in a timely manner, thereby realizing dynamic management of the hard drive and ensuring the continuity and stability of the server storage system management.

[0164] Optionally, embodiments of this application can combine artificial intelligence and machine learning technologies to achieve intelligent management of hard drive physical silkscreen printing schemes. For example, by analyzing a large amount of server hard drive configuration and usage data, the algorithm for BIOS logical drive order allocation and BMC mapping rules can be automatically optimized, improving the automation level and accuracy of hard drive management. Simultaneously, artificial intelligence technology can be used to predict and analyze the operating status of hard drives, identifying potential hard drive failures in advance and further improving the reliability of the server system.

[0165] It should be noted that the functions that the above-mentioned hard disk information management system can achieve are all applicable to the hard disk information management method in the embodiments of this application, and will not be elaborated here.

[0166] For a description of the features in the embodiments of the hard disk information management method, please refer to the relevant descriptions in the embodiments of the hard disk information management system, which will not be repeated here.

[0167] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method.

[0168] Figure 6 This is a schematic diagram of the hard disk information management device provided in an embodiment of this application. Figure 6 As shown, embodiments of this application also provide a hard disk information management device 60, including:

[0169] The receiving module 601 is used to receive the logical disk sequence sent by the startup module.

[0170] Module 602 obtains the physical information of the hard drive connected to the hard drive module.

[0171] The generation module 603 generates a mapping relationship between the logical disk order and physical information of the hard disk based on the logical disk order and physical information; the mapping relationship is used for hard disk information management.

[0172] Figure 7 A schematic diagram of the structure of the electronic device provided in this application. Figure 7 As shown, the electronic device 70 provided in this embodiment includes at least one processor 701 and a memory 702. Optionally, the electronic device 70 further includes a communication component 703. The processor 701, memory 702, and communication component 703 are connected via a bus.

[0173] In a specific implementation, at least one processor 701 executes computer execution instructions stored in memory 702, causing at least one processor 701 to execute the above-described hard disk information management method embodiment.

[0174] The specific implementation process of processor 701 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0175] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the application can be directly manifested as being executed by a hardware processor, or executed by a combination of hardware and software modules within the processor.

[0176] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0177] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0178] Embodiments of this application also provide a computer-readable storage medium storing a computer program, wherein the computer program is configured to execute the steps in any of the above embodiments of the hard disk information management method when it is run.

[0179] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard disk, magnetic disk, or optical disk.

[0180] The embodiments of this application also provide a computer program product, which includes a computer program that, when executed by a processor, implements the steps in any of the above embodiments of the hard disk information management method.

[0181] Embodiments of this application also provide another computer program product, including a non-volatile computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps in any of the above embodiments of the hard disk information management method.

[0182] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0183] The above provides a detailed description of a hard disk information management method provided in this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only intended to help understand the method and its core ideas. It should be noted that those skilled in the art can make various improvements and modifications to this application without departing from its principles, and these improvements and modifications also fall within the protection scope of the claims of this application.

Claims

1. A hard disk information management system, characterized in that, include: The hard disk module includes a first hard disk unit for connecting a first type of hard disk and a second hard disk unit for connecting a second type of hard disk; A boot module, connected to the hard disk module, is used to generate a logical disk order for the first type of hard disk; the boot module is the BIOS in the hard disk information management system. The controller is connected to both the boot module and the hard disk module; the controller is a BMC; the first type of hard disk cannot be directly monitored by the BMC; The controller is configured to: Receive the logical disk sequence and the port number corresponding to the logical disk sequence sent by the startup module; Obtain the physical information of the hard drive connected to the hard drive module; the physical information includes a preset relationship between physical identification information and port number; Based on the preset relationship between the physical identification information and the port number, the physical identification information corresponding to the port number and the logical disk order are associated to obtain the mapping relationship between the logical disk order and the physical identification information of the first type of hard disk; wherein, the mapping relationship is used to manage the hard disk information.

2. The hard disk information management system according to claim 1, characterized in that, The startup module is used for: Identify the first type of hard drive connected to the first hard drive unit; Obtain the preset allocation strategy; Logical disk order is generated for the first type of hard disk according to the preset allocation strategy.

3. The hard disk information management system according to claim 2, characterized in that, The startup module is used for: According to the preset allocation strategy, the allocation attribute information of the first hard disk unit is obtained; The logical disk order of the first type of hard disk is determined based on the preset allocation strategy and the allocation attribute information.

4. The hard disk information management system according to claim 2, characterized in that, The startup module is used for: In response to the user's policy configuration operation, a policy configuration interface is displayed, and the user's input and / or selection of the preset allocation policy are obtained through the policy configuration interface; And / or, Receive the preset allocation strategy sent by the controller; And / or, Collect attribute information of the first type of hard disk, and determine the preset allocation strategy from multiple pre-configured allocation strategies based on the attribute information.

5. The hard disk information management system according to claim 2, characterized in that, The preset allocation strategy includes at least one of the following: allocation strategy based on port number order, allocation strategy based on hard disk capacity, and allocation strategy based on hard disk priority.

6. The hard disk information management system according to claim 2, characterized in that, The startup module is used for: Send a hard disk enumeration command to the hard disk module to obtain the interface status of the first hard disk unit; Based on the interface status, identify the first type of hard disk connected to the first hard disk unit.

7. The hard disk information management system according to claim 1, characterized in that, The startup module is also used for: The logical disk order is encapsulated to obtain logical disk order encapsulation information; The logical disk sequence encapsulation information is sent to the controller according to the preset communication interface.

8. The hard disk information management system according to any one of claims 1 to 7, characterized in that, The hard disk module also includes a programmable controller; the programmable controller is connected to the controller. The programmable controller is used for: Obtain the physical identification information of the hard drive; Identify the hard drive type; The controller is used to read the physical identification information and the hard disk type through the connection channel between the controller and the programmable controller.

9. The hard disk information management system according to claim 8, characterized in that, The programmable controller is used for: Access the storage unit of the programmable controller to obtain the physical identification information pre-stored in the storage unit.

10. The hard disk information management system according to claim 8, characterized in that, The programmable controller is used for: Detect the interface pin level status of the hard drive; The type of hard drive is determined based on the interface pin level status.

11. The hard disk information management system according to any one of claims 1 to 7, characterized in that, The startup module is configured as follows: In response to hard drive hot-plug events, generate a logical disk order for the newly connected hard drive within a preset time. Accordingly, the controller is configured to receive the logical disk order of the newly connected hard drive sent by the boot module when a hard drive hot-plug event is detected; Based on the logical disk order of the newly connected hard drive, update the mapping relationship between the logical disk order and physical information of the hard drive.

12. The hard disk information management system according to any one of claims 1 to 7, characterized in that, The controller is configured to: The mapping relationship is stored in non-volatile memory.

13. The hard disk information management system according to any one of claims 1 to 7, characterized in that, The controller is configured to: Based on the mapping relationship, mapping relationship display information is generated; wherein, the mapping relationship display information is a table and / or an undirected graph; In response to a user's query, determine the target hard drive; Based on the target hard drive, display the mapping relationship information and / or the mapping relationship corresponding to the target hard drive.

14. The hard disk information management system according to claim 1, characterized in that, It also includes a physical identifier indicator unit, which is bound to the corresponding hard drive; the physical identifier indicator unit is connected to the controller; The controller is configured to: Based on the hard drive type, a type display command is sent to the physical identification indication unit; The physical identifier indication unit is used to indicate the hard drive type of the corresponding hard drive through different display states according to the type display instruction.

15. The hard disk information management system according to any one of claims 1 to 7, characterized in that, The controller is configured to: Monitor the operating status of the hard drive; Based on the operating status, determine the logical disk order of the hard drive that caused the failure; Based on the logical disk order of the faulty hard drive and the mapping relationship, determine the physical identification information of the faulty hard drive; Based on the physical identification information of the hard drive that caused the failure, generate a fault message and / or log alarm information.

16. A hard disk information management method, characterized in that, The method, applied to a controller of a hard disk information management system as described in any one of claims 1 to 15, comprises: Receive the logical disk sequence and the port number corresponding to the logical disk sequence sent by the startup module; Obtain the physical information of the hard drive connected to the hard drive module; the physical information includes a preset relationship between physical identification information and port number; Based on the logical disk order and the physical information, a preset relationship between physical identification information and port number is established, and the physical identification information corresponding to the port number is associated with the logical disk order to obtain a mapping relationship between the logical disk order and physical identification information of the first type of hard disk; wherein, the mapping relationship is used for hard disk information management of the hard disk.

Images