Memory resource allocation processing method and device, storage medium and product

Abstract

The invention discloses a memory resource allocation processing method and device, a storage medium and a product, and relates to the technical field of computers, in the stage that a server is started to enter an operating system, whether memory reallocation is needed or not is accurately judged by monitoring the matching degree of total memory resources and all link interface requirements in real time, and the operation efficiency is improved. Unnecessary resource adjustment overhead is avoided; priority division is carried out on the link interfaces based on the hot plug function state, the memory resource requirement of the first link interface of the key equipment is guaranteed preferentially, and the problem that the equipment cannot be started due to insufficient resources is greatly solved. Besides, through intelligent management of configuration parameters of the boot loader, the original allocation mode can be stably used when the memory does not need to be reallocated, so that the system compatibility is ensured, and the overall operation stability is enhanced.

Description

Technical Field

[0001] This application relates to the field of computer technologies, and in particular, to a method, device, storage medium, and product for memory resource allocation and processing. Background Art

[0002] External expansion devices such as intelligent network cards are connected to a server through a PCI (Peripheral Component Interconnect) link interface. Since the external expansion devices connected by the PCI link undertake key tasks such as high-speed data processing, which affect the overall system performance and operation efficiency, and the memory address resources of the server are limited, it is necessary to reserve resources for some external expansion devices connected by the PCI link in advance.

[0003] In related technologies, when the server enters the operating system, it will reallocate the memory resources already allocated by the basic input / output system. The method of allocating memory resources first to the expansion devices identified first will cause the expansion devices that need to be used later to be identified later and lack effective memory resource allocation, thereby reducing the overall resource utilization efficiency of the server. Summary of the Invention

[0004] This application provides a method, device, storage medium, and product for memory resource allocation and processing, so as to at least solve the problem of low overall resource utilization efficiency in related technologies.

[0005] This application provides a method for memory resource allocation and processing, including: when it is detected that the server has completed booting and entered the operating system, determining whether it is necessary to reallocate memory resources for each link interface according to the total memory resources, where each link interface is used to connect each expansion device; if it is determined that memory resources need to be reallocated, detecting the resource reservation configuration information of each link interface, where the resource reservation configuration information is used to indicate whether the corresponding link interface needs to be preferentially allocated memory resources, and the resource reservation configuration information is configured for each link interface before the server enters the operating system; for each first link interface detected that needs to be preferentially allocated memory resources, allocating memory resources to each first link interface according to a first preset rule; for each second link interface detected that does not need to be preferentially allocated memory resources, after completing the allocation of memory resources to each first link interface, allocating memory resources to each second link interface according to a second preset rule; if it is determined that memory resources do not need to be reallocated, setting a parameter configuration instruction to enable the server to allocate memory resources to each link interface according to the original allocation method configured before entering the operating system.

[0006] This application also provides a device for memory resource allocation and processing, including:

[0007] The resource reallocation judgment module is used to judge whether it is necessary to reallocate memory resources for each link interface according to the total memory resources when detecting that the server has completed the startup and entered the operating system, wherein each link interface is used to connect each expansion device.

[0008] The configuration information detection module is used to detect the resource reservation configuration information of each link interface if it is determined that memory resources need to be reallocated, wherein the resource reservation configuration information is used to indicate whether the corresponding link interface needs to prioritize the allocation of memory resources, and the resource reservation configuration information is configured for each link interface before the server enters the operating system.

[0009] The first allocation module is used to allocate memory resources to each first link interface according to a first preset rule for each first link interface that needs to be preferentially allocated memory resources.

[0010] The second allocation module is used to allocate memory resources to each second link interface detected to which memory resources do not need to be allocated preferentially according to a second preset rule after completing the allocation of memory resources to each first link interface.

[0011] The resource use module is used to set parameter configuration instructions to enable the server to allocate memory resources to each link interface according to the original allocation method configured before entering the operating system if it is determined that the memory resources do not need to be reallocated.

[0012] The present application also provides a server, comprising: a memory for storing a computer program; and a processor for implementing the steps of any one of the above-mentioned memory resource allocation processing methods when executing the computer program.

[0013] The present application also provides a computer-readable storage medium, in which a computer program is stored, wherein when the computer program is executed by a processor, the steps of any of the above-mentioned memory resource allocation processing methods are implemented.

[0014] The present application also provides a computer program product, including a computer program, which implements the steps of any of the above-mentioned memory resource allocation processing methods when executed by a processor.

[0015] The memory resource allocation processing method, device, storage medium and product of the present application, at the stage when the server starts and enters the operating system, accurately determines whether memory needs to be reallocated by monitoring the matching degree between the total memory resources and the requirements of each link interface in real time, avoiding unnecessary resource adjustment overhead; divides the priorities of link interfaces based on the hot-plug function status, and preferentially guarantees the memory resource requirements of the first link interface of key devices, greatly reducing the problem that devices cannot be enabled due to insufficient resources. In addition, through the intelligent management of the configuration parameters of the boot loader, the original allocation method can be stably used without reallocating memory, which not only ensures system compatibility but also enhances the overall operation stability. Brief Description of the Drawings

[0016] To more clearly illustrate the embodiments of the present application, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0017] Figure 1 It is a schematic physical connection diagram of the server provided by the embodiment of the present application;

[0018] Figure 2 It is the overall flowchart of the memory resource allocation processing method provided by the embodiment of the present application;

[0019] Figure 3 It is a schematic diagram of the link interface configuration process provided by the embodiment of the present application;

[0020] Figure 4 It is a schematic structural diagram of the memory resource allocation processing device provided by the embodiment of the present application;

[0021] Figure 5 It is a schematic structural diagram of the server provided by the embodiment of the present application. Detailed Embodiments

[0022] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the protection scope of the present application.

[0023] It should be noted that in the description of this application, 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 not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, article or device. The terms "first", "second", etc. in this application are used to distinguish similar objects, rather than to describe a specific order or sequence.

[0024] To clearly understand the technical solution of this application, the solutions of the prior art will be introduced in detail first. In the server architecture of modern data centers, external expansion devices such as intelligent network cards and data processing units are mainly connected to the server system through PCI link interfaces. Such devices usually undertake key tasks such as high-speed data forwarding, network protocol offloading, encryption and decryption, and their performance directly affects the data processing efficiency and overall operation stability of the server. However, there are total limitations on the memory address resources of the server. If resources such as allocable physical memory are not reasonably allocated, resource contention and performance bottlenecks are likely to occur. Under the traditional server resource allocation mechanism, when the server completes the startup process and enters the operating system stage, the system usually reallocates the memory resources already allocated by the basic input / output system in the initial startup stage. According to the order of the expansion devices first recognized during the system startup process, memory resources are preferentially allocated to them. However, a large number of expansion devices undertaking key services are recognized in the later stage of system startup due to their long startup self-check process or dependence on specific initialization conditions. Once these devices are recognized, the limited memory resources have been exhausted by the previous devices, resulting in the inability of key expansion devices to be normally enabled or their performance being severely limited, thus greatly reducing the overall resource utilization efficiency of the server.

[0025] To solve the above technical problems, the inventor thought that when the server completes startup and enters the operating system, first judge whether memory needs to be reallocated based on the total memory resources. If reallocation is required, retrieve the reserved configuration information of each link interface resource configured before the server is powered on, and classify according to whether the link interface needs to preferentially allocate memory resources; for the first link interface that needs to preferentially allocate resources, allocate memory using the first preset rule that guarantees real-time requirements, and for the second link interface that does not need preferential allocation, after the former allocation is completed, allocate using the second preset rule that improves resource utilization; if reallocation is not required, use the original allocation method before power on. Through this memory resource allocation strategy with priorities, both the performance requirements of key expansion devices are guaranteed and the overall resource utilization efficiency of the server is improved.

[0026] To enable those skilled in the art of this technology to better understand the solution of this application, the following will further elaborate on this application in combination with the accompanying drawings and specific implementation manners.

[0027] In combination with the specific application environment architecture or specific hardware architecture on which the execution of the memory resource allocation processing method depends, the specific application environment architecture or specific hardware architecture is described herein. Figure 1 The following is a schematic diagram of the physical connections of the server provided by the embodiments of the present application. As Figure 1 shown, the server includes a baseboard management controller, an intelligent platform management interface, a basic input / output system, a first processor, a second processor, and multiple PCI link interfaces. The baseboard management controller is connected to the basic input / output system through the intelligent platform management interface, and both are connected to the first processor through a low pin count bus / peripheral component interconnect standard link. The baseboard management controller can also perform related operations through a USB network sharing. The first processor and the second processor are connected by a Compute Express Link / Peripheral Component Interconnect Express link and are respectively connected to multiple PCI link interfaces. These interfaces can be externally connected to expansion devices such as disk array cards and optical modules. In addition, the motherboard is provided with a universal serial bus interface and a serial ATA interface for connecting external devices and storage devices. The memory resource allocation processing method provided by the embodiments of the present application is exactly when the server completes booting and enters the operating system, for these expansion devices connected through the PCI link interfaces, it is determined whether it is necessary to reallocate memory resources based on the total memory resources. If reallocation is required, then according to the memory resource reservation configuration information of each link interface configured before power-on, memory resources are allocated to each link interface according to different rules. If reallocation is not required, the original allocation method before power-on is used.

[0028] In the embodiments provided by the present application, the execution subject of the memory resource allocation processing method is Figure 1 the server shown as follows. The detailed description of the memory resource allocation processing method is as follows:

[0029] S201: When it is detected that the server completes booting and enters the operating system, determine whether it is necessary to reallocate memory resources for each link interface, where each link interface is used to connect each expansion device.

[0030] Specifically, when it is monitored that the server completes the basic input / output system startup process and successfully enters the operating system running state, by comparing the total memory resources of the system and the memory resources used by the expansion devices connected to each link interface, determine whether it is necessary to reallocate memory resources for each link interface.

[0031] Specifically, the step of determining whether it is necessary to reallocate memory resources for each link interface according to the total memory resources includes Sa1 - Sa3:

[0032] Sa1: Obtain the capacity of the total memory resources of the server and the memory resources required by each link interface.

[0033] Sa2: If the capacity of the total memory resources is not less than the memory resources required by each link interface, there is no need to reallocate memory resources for each link interface.

[0034] Sa3: If the capacity of the total memory resources is less than the memory resources required by each link interface, it is necessary to reallocate memory resources for each link interface.

[0035] S202: If it is determined that memory resources need to be reallocated, the resource reservation configuration information of each link interface is detected, where the resource reservation configuration information is used to indicate whether the corresponding link interface needs to be preferentially allocated memory resources, and the resource reservation configuration information is configured for each link interface before the server enters the operating system.

[0036] Specifically, if the system determines that memory resources need to be reallocated, the resource reservation configuration information of each link interface preconfigured in the basic input / output system startup stage is immediately retrieved. By reading whether the hot-plug function corresponding to each link interface is enabled, the priority identification bits corresponding to each link interface are distinguished, and all link interfaces are divided into the first link interfaces that need to be preferentially allocated memory resources and the second link interfaces for normal allocation. Exemplarily, interfaces connecting key devices such as intelligent network cards and data processors are the first link interfaces, and interfaces connecting ordinary storage devices are the second link interfaces.

[0037] Specifically, the steps of detecting the resource reservation configuration information of each link interface include Sb1 - Sb4:

[0038] Sb1: Traverse and scan the device configuration information of each link interface, where the device configuration information includes the hot-plug function.

[0039] Specifically, after the system starts to execute the detection process, it first performs a traversal and scan operation on each link interface. During this process, the system reads and parses the device configuration information corresponding to each link interface one by one. Among them, the device configuration information covers various attributes and function parameters of the link interface, including the status flag related to the hot-plug function.

[0040] Sb2: Determine whether the hot-plug function of each link interface is enabled.

[0041] Specifically, the system determines whether the hot-plug function of each link interface is in the enabled or disabled state by identifying specific identification bits or parameter values in the configuration information.

[0042] Sb3: If the hot-plug function of any link interface is enabled, determine that any link interface is the first link interface that needs to be preferentially allocated memory resources.

[0043] Specifically, once the system detects that the hot-plug function of a certain link interface is in the enabled state, it immediately determines that the link interface is the first link interface that needs to be preferentially allocated memory resources.

[0044] Sb4: If the hot-plug function of any link interface is not enabled, it is determined that any link interface is the second link interface that does not need to be preferentially allocated memory resources.

[0045] Specifically, when the system confirms that the hot-plug function of a certain link interface is in the disabled state, it classifies the link interface as the second link interface that does not need to be preferentially allocated memory resources.

[0046] S203: For each detected first link interface that needs to be preferentially allocated memory resources, allocate memory resources to each first link interface according to the first preset rule.

[0047] Specifically, the process of allocating memory resources to each first link interface according to the first preset rule includes Sc1 - Sc3:

[0048] Sc1: Determine whether there is an expansion device under each first link interface.

[0049] Specifically, when the system allocates memory resources to the first link interface, it first conducts an expansion device existence detection for each first link interface. By sending a detection signal to a specific register of the first link interface, the system reads the return value to determine whether the link interface is actually connected to an expansion device.

[0050] Sc2: If there is an expansion device under any first link interface, allocate memory resources to any first link interface according to the reserved memory resources, where the reserved memory resources are configured for each first link interface before the server enters the operating system.

[0051] Specifically, when it is detected that there is an expansion device under a certain first link interface, the system immediately allocates the reserved memory resources pre-configured during the server startup phase.

[0052] Sc3: If there is no expansion device under any first link interface, allocate memory resources to any first link interface according to the preset resource parameters.

[0053] Specifically, if it is detected that there is no expansion device connected under a certain first link interface, the system will not idle the resource allocation permission of the link interface, but perform dynamic allocation according to the preset resource parameters.

[0054] Exemplarily, reserve 2M of memory resources for the first link interface without an expansion device for use when an expansion device is inserted.

[0055] S204: for each detected second link interface that does not need priority allocation of memory resources, after completing allocation of memory resources to each first link interface, allocate memory resources to each second link interface according to a second preset rule.

[0056] Specifically, after completing resource allocation for all first link interfaces, the system starts processing memory allocation requirements for second link interfaces. The step of allocating memory resources to each second link interface according to the second preset rule includes Sd1-Sd4:

[0057] Sd1: After completing the allocation of memory resources for each first link interface, determine whether there is an expansion device under each second link interface.

[0058] Specifically, the existence detection of the expansion device under each second link interface is started. This process obtains the device identification information of each second link interface by sending a configuration space read command to the link. For the link interface where the expansion device is detected, the system further reads the device ready bit in the status register of the expansion device to confirm whether the device is in a normal working state.

[0059] Sd2: If there is an expansion device under any second link interface, the binding relationship between any second link interface and the reserved memory resources of any second link interface is released, and the reserved memory resources are updated to the current remaining memory resources of the server, where the reserved memory resources are configured for the second link interface before the server enters the operating system.

[0060] Specifically, when an expansion device is detected under a second link interface, the system immediately performs the unbinding and recycling operations of the reserved resources. During the server startup phase, the basic input and output system pre-configures a certain amount of reserved memory resources for each second link interface. The system clears the original reserved address mapping relationship and marks the corresponding physical memory page frame as "available".

[0061] Sd3: Allocate memory resources to any second link interface according to the current remaining memory resources and the third preset rule.

[0062] Specifically, after completing the reserved resource recovery and updating the current remaining memory resources, the system allocates memory resources to the second link interface with the expansion device according to the third preset rule. The steps of allocating memory resources to any second link interface according to the third preset rule according to the current remaining memory resources include Se1-Se3:

[0063] Se1: Obtain the memory resources required by the expansion device under any second link interface.

[0064] Specifically, the memory resource requirement parameters declared when the device is initialized are obtained.

[0065] Se2: Determine whether the current remaining memory resources meet the memory resources required by the expansion device.

[0066] Specifically, after obtaining the specific resource requirements of the expansion device, first check whether there is a continuous physical memory block in the remaining memory pool that meets the device alignment requirements, and then calculate whether the total remaining available memory reaches the device minimum requirement threshold.

[0067] Se3: If the current remaining memory resources meet the memory resources required by the expansion device, allocate memory resources to any second link interface.

[0068] Specifically, when the system determines that the current remaining memory resources can meet the expansion device requirements, allocate memory resources to this second link interface.

[0069] Se4: If the current remaining memory resources do not meet the memory resources required by the expansion device, do not allocate memory resources to any second link interface, and perform resource isolation on any second link interface.

[0070] Specifically, when the current remaining memory resources cannot meet the expansion device requirements, in order to avoid resource competition and system instability, strict resource isolation measures will be taken for this second link interface. Disable the memory access and bus mastering functions of this link interface to prevent the device from initiating invalid memory requests.

[0071] Sd4: If there is no expansion device under any second link interface, do not allocate memory resources to any second link interface, and perform resource isolation on any second link interface.

[0072] Specifically, if it is detected that there is no expansion device under a certain second link interface, the system will take resource isolation measures to prevent resource waste. Disable the memory access permission of this link interface, and at the same time, the system will completely release the reserved memory resources corresponding to this link interface back to the system resource pool.

[0073] S205: If it is determined that memory resources do not need to be reallocated, configure the server to allocate memory resources to each link interface according to the original allocation method configured before entering the operating system by setting parameter configuration instructions.

[0074] Specifically, if the system determines that the current memory resources are sufficient and no reallocation is required, force the memory resource allocation state completed by the basic input / output system to be maintained by modifying the parameter configuration instructions.

[0075] Specifically, the steps of configuring the server to allocate memory resources to each link interface according to the original allocation method configured before entering the operating system by setting parameter configuration instructions include Sf1 - Sf3:

[0076] Sf1: Obtain the set of configuration parameters of the server's bootloader.

[0077] Specifically, first locate the storage location of the configuration file of the server's bootloader, read the content of the configuration file through the file system interface, and parse the set of configuration parameters therein.

[0078] Sf2: Determine whether the set of configuration parameters includes a parameter configuration instruction corresponding to the need to reallocate memory resources, where the parameter configuration instruction is used to indicate an operation to reallocate the memory resources of the server.

[0079] Specifically, after obtaining the complete set of configuration parameters, the system checks each parameter therein one by one to find the parameter configuration instruction directly related to the memory resource reallocation operation. Exemplarily, such as the pci=realloc parameter.

[0080] Sf3: If the set of configuration parameters includes a parameter configuration instruction, delete the parameter configuration instruction so that the server allocates memory resources for each link interface according to the original allocation method configured before entering the operating system.

[0081] Specifically, when the system confirms that there is a parameter configuration instruction related to memory reallocation in the set of configuration parameters, it immediately performs the parameter deletion operation. After the modification is completed, the system saves the configuration file and synchronizes the disk cache to ensure the persistence of the modification. Subsequently, the system will trigger the bootloader configuration update mechanism to make the modification take effect.

[0082] In summary, at the stage when the server starts and enters the operating system, by real-time monitoring the matching degree between the total memory resources and the requirements of each link interface, it accurately judges whether memory needs to be reallocated, avoiding unnecessary resource adjustment overhead; based on the hot plug function status, the link interfaces are prioritized, and the memory resource requirements of the first link interface of critical devices are preferentially guaranteed, greatly reducing the problem that devices cannot be enabled due to insufficient resources. In addition, through the intelligent management of the bootloader configuration parameters, the original allocation method can be stably used when memory does not need to be reallocated, which not only ensures system compatibility but also enhances the overall operation stability.

[0083] Figure 2 The overall flowchart of the memory resource allocation processing method provided by the embodiment of the present application, the execution subject of the memory resource allocation processing method is Figure 1 the server shown in Figure 2 as shown, this method includes:

[0084] When it is detected that the server has completed starting and entered the operating system, execute step S301: Determine whether it is necessary to reallocate memory resources for each link interface according to the total memory resources.

[0085] If it is determined that memory resources need to be reallocated, traverse and scan the device configuration information of each link interface, and execute step S302: Determine whether the hot-plug function of each link interface is enabled.

[0086] If the hot-plug function of the link interface is enabled, execute step S303: Determine whether there is an expansion device under the link interface.

[0087] If there is an expansion device under the link interface, execute step S304: Allocate the link interface according to the reserved memory resources.

[0088] If there is no expansion device under the link interface, execute step S305: Allocate memory resources for the link interface according to the preset resource parameters.

[0089] If the hot-plug function of the link interface is not enabled, execute step S306: Determine whether there is an expansion device under the link interface.

[0090] If there is an expansion device under the link interface, execute step S307: Release the binding relationship between the link interface and the reserved memory resources.

[0091] S308: Update the reserved memory resources to the current remaining memory resources of the server.

[0092] S309: Determine whether the current remaining memory resources meet the memory resources required by the expansion device.

[0093] If the current remaining memory resources meet the memory resources required by the expansion device, execute step S310: Allocate the required memory resources for the link interface where the expansion device is located.

[0094] If the current remaining memory resources do not meet the memory resources required by the expansion device, execute step S311: Do not allocate memory resources for the link interface and isolate the resources of the link interface.

[0095] If there is no expansion device under the link interface, execute step S312: Do not allocate memory resources for the link interface and isolate the resources of the link interface.

[0096] If it is determined that memory resources do not need to be reallocated, execute step S313: Delete the parameter configuration instruction in the boot loader;

[0097] S314: Allocate memory resources for each link interface according to the original allocation method configured before entering the operating system.

[0098] In summary, during the stage when the server boots up and enters the operating system, by monitoring in real time the matching degree between the total memory resources and the requirements of each link interface, it can accurately determine whether memory needs to be reallocated, avoiding unnecessary resource adjustment overhead; based on the hot-plug function status, the link interfaces are prioritized, and the memory resource requirements of the first link interface of critical devices are guaranteed first, greatly reducing the problem that devices cannot be enabled due to insufficient resources. In addition, through the intelligent management of the configuration parameters of the boot loader, when memory does not need to be reallocated, the original allocation method can be stably used, ensuring both system compatibility and enhancing the overall operation stability.

[0099] In another embodiment provided by the embodiment of the present application, before the server enters the operating system, it further includes a process of configuring each link interface, and this method includes S401 - S404:

[0100] S401: After the server boots up and enters the basic input / output system, it determines whether each link interface needs to be preferentially allocated memory resources according to the connection status of each link interface.

[0101] Specifically, the process of determining whether each link interface needs to be preferentially allocated memory resources according to the connection status of each link interface includes Sg1 - Sg7:

[0102] Sg1: Determine whether there are expansion devices under each link interface.

[0103] Specifically, the following steps Sh1 - Sh6 can be used to determine whether there are expansion devices under each link interface:

[0104] Sh1: Obtain the communication protocol specification followed by any link interface.

[0105] Sh2: According to the communication protocol specification, determine the device detection instruction corresponding to any link interface, where the device detection instruction includes a protocol-specific field for triggering the response of the expansion device.

[0106] Sh3: Send the device detection instruction to any link interface.

[0107] Sh4: If feedback data sent by any link interface is received within the preset response timeout period, perform protocol compliance verification on the feedback data.

[0108] Sh5: If the feedback data passes the protocol compliance verification and the feedback data includes the response information corresponding to the device detection instruction, it is determined that there is an expansion device under any link interface.

[0109] Sh6: If feedback data sent by any link interface is not received within the preset response timeout period, it is determined that there is no expansion device under any link interface.

[0110] Sg2: If there is no expansion device under any link interface, determine whether any link interface needs to access an expansion device.

[0111] Specifically, when it is found that there is no expansion device under a certain link interface, the system will further determine whether there is a future need to access an expansion device for this interface.

[0112] Sg3: If any link interface does not need to access an expansion device, determine that any link interface does not need to be preferentially allocated memory resources.

[0113] Specifically, if it is determined that this interface does not need to access an expansion device, it is determined that it does not need to be preferentially allocated memory resources.

[0114] Sg4: If any link interface needs to access an expansion device, determine that any link interface needs to be preferentially allocated memory resources.

[0115] Specifically, if it is judged that this interface needs to access an expansion device later, it is determined that it needs to be preferentially allocated memory resources.

[0116] Sg5: If there is an expansion device under any link interface, determine whether the expansion device is the target device according to the identifier of the expansion device.

[0117] Specifically, when it is detected that there is an expansion device under the link interface, the system will compare the identifier of the expansion device, such as the device identifier and the manufacturer identifier, with the pre-set target device list.

[0118] Sg6: If the expansion device is the target device, determine that any link interface needs to be preferentially allocated memory resources.

[0119] Specifically, if this device belongs to the target device, it is determined that this link interface needs to be preferentially allocated memory resources.

[0120] Sg7: If the expansion device is not the target device, determine that any link interface does not need to be preferentially allocated memory resources.

[0121] Specifically, if it does not belong to the target device, it is determined that this link interface does not need to be preferentially allocated memory resources.

[0122] S402: If any link interface needs to be preferentially allocated memory resources, determine any link interface as the first link interface.

[0123] Specifically, if it is found that any link interface is determined to need to be preferentially allocated memory resources, the system will immediately mark and determine this link interface as the first link interface.

[0124] S403: Configure the reserved memory resources of the first link interface and set the resource reservation configuration information of the first link interface.

[0125] Exemplarily, reserve the required memory resources for the first link interface and enable the hot plug function in the device configuration information of the first link interface.

[0126] S404: If any link interface does not require preferential allocation of memory resources, determine any link interface as the second link interface and configure the reserved memory resources of the second link interface.

[0127] Exemplarily, reserve the required memory resources for the second link interface and disable the hot plug function in the device configuration information of the second link interface.

[0128] In summary, by combining the device connection status, expansion demand prediction, and device type identification, it is possible to predict the resource priorities of each link interface before the operating system starts, mark the critical devices and the interfaces with expansion plans as the first link interfaces preferentially, reserve sufficient memory resources for them, and enable the hot plug function to ensure that the core business devices obtain immediate resource guarantee. At the same time, for non-critical interfaces, the hot plug function is disabled and the reserved resource amount is reasonably controlled, effectively reducing memory fragmentation and resource waste.

[0129] Figure 3 This is a schematic diagram of the link interface configuration process provided by the embodiment of the present application. As Figure 3 shown, the method includes:

[0130] After the server boots into the basic input / output system, execute step S501: Determine whether there is an expansion device under each link interface.

[0131] If there is an expansion device under the link interface, execute step S502: Determine whether it is a target device according to the identifier of the expansion device.

[0132] If the expansion device is a target device, execute step S503: Configure the reserved memory resources of the link interface where the expansion device is located.

[0133] S504: Enable the hot plug function of the link interface where the target device is located.

[0134] If the expansion device is not a target device, execute step S505: Configure the reserved memory resources of the link interface where the expansion device is located.

[0135] S506: Disable the hot plug function of the link interface where the expansion device is located.

[0136] If there is no expansion device under the link interface, execute step S507: Determine whether the link interface needs to access an expansion device.

[0137] If the link interface needs to access an expansion device, then step S508 is executed: configure reserved memory resources for the link interface and enable the hot plug function.

[0138] If the link interface does not need to access an expansion device, then step S509 is executed: do not configure reserved memory resources for the link interface and disable the hot plug function.

[0139] In summary, by combining the device connection status, expansion demand prediction, and device type identification, it is possible to predict the resource priorities of each link interface before the operating system starts, prioritize the critical devices and the interfaces with expansion plans as the first link interfaces, reserve sufficient memory resources for them, and enable the hot plug function to ensure that the core business devices obtain immediate resource guarantee. At the same time, for non-critical interfaces, the hot plug function is disabled and the reserved resource amount is reasonably controlled, effectively reducing memory fragmentation and resource waste.

[0140] In the embodiment provided in the present application, the process of determining whether to reallocate memory resources for each link interface according to the total memory resources can also be determined by judging whether the server has enabled a preset policy. The method includes:

[0141] S601: When it is detected that the server has completed startup and entered the operating system, judge whether a preset policy is enabled to prevent reallocation of memory resources for each link interface.

[0142] Specifically, the judgment process includes Si1-Si3:

[0143] Si1: Obtain the configuration parameters of memory allocation control in the basic input / output system settings, where the configuration parameters of memory allocation control include a memory allocation lock flag, and the memory allocation lock flag is used to indicate whether to prohibit the server from reallocating the memory resources of each link interface when entering the operating system.

[0144] Si2: If the memory allocation lock flag is in the on state, it is determined that the preset policy is enabled.

[0145] Si3: If the memory allocation lock flag is in the off state, it is determined that the preset policy is not enabled.

[0146] S602: If it is determined that the preset policy is enabled, do not reallocate memory resources for each link interface.

[0147] S603: If it is determined that the preset policy is not enabled, reallocate memory resources for each link interface.

[0148] In summary, when the memory allocation lock flag is enabled, that is, when the preset policy is enabled, the system will maintain the original memory allocation state, avoid resource conflicts caused by reallocation, and effectively ensure the continuous operation of critical services with high requirements for memory configuration stability; when the flag is not enabled, the system will promptly respond to the dynamic resource requirements of each link interface, start the reallocation process, and realize the reallocation of memory resources.

[0149] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases, the former is a better implementation method.

[0150] Figure 4 It is a schematic structural diagram of a memory resource allocation processing device provided by an embodiment of the present application. As Figure 4 shown, an embodiment of the present application also provides a memory resource allocation processing device, and the device includes: a reallocation resource judgment module 401, a configuration information detection module 402, a first allocation module 403, a second allocation module 404, and a resource reuse module 405.

[0151] The reallocation resource judgment module 401 is configured to, when it is detected that the server completes startup and enters the operating system, judge whether it is necessary to reallocate memory resources for each link interface according to the total memory resources, where each link interface is used to connect each expansion device.

[0152] The configuration information detection module 402 is configured to, if it is determined that memory resources need to be reallocated, detect the resource reservation configuration information of each link interface, where the resource reservation configuration information is used to indicate whether the corresponding link interface needs to be preferentially allocated memory resources, and the resource reservation configuration information is configured for each link interface before the server enters the operating system.

[0153] The first allocation module 403 is configured to, for each first link interface detected that needs to be preferentially allocated memory resources, allocate memory resources to each first link interface according to a first preset rule.

[0154] The second allocation module 404 is configured to, for each second link interface detected that does not need to be preferentially allocated memory resources, after allocating memory resources to each first link interface, allocate memory resources to each second link interface according to a second preset rule.

[0155] The resource reuse module 405 is configured to, if it is determined that memory resources do not need to be reallocated, enable the server to allocate memory resources to each link interface according to the original allocation method configured before entering the operating system by setting parameter configuration instructions.

[0156] In one possible implementation, the first allocation module 403 is specifically used to determine whether there is an expansion device under each first link interface; if there is an expansion device under any first link interface, any first link interface is allocated according to the reserved memory resources, where the reserved memory resources are configured for each first link interface before the server enters the operating system.

[0157] In a possible implementation manner, the first allocation module 403 is further configured to allocate memory resources to any first link interface according to preset resource parameters if no expansion device exists under any first link interface.

[0158] In one possible implementation, the second allocation module 404 is specifically used to determine whether there is an expansion device under each second link interface after completing the allocation of memory resources to each first link interface; if there is an expansion device under any second link interface, then release the binding relationship between any second link interface and any second link interface's reserved memory resources, and update the reserved memory resources to the server's current remaining memory resources, wherein the reserved memory resources are configured for the second link interface before the server enters the operating system; based on the current remaining memory resources, allocate memory resources to any second link interface according to a third preset rule.

[0159] In a possible implementation manner, the second allocation module 404 is further configured to not allocate memory resources to any second link interface if no expansion device exists under any second link interface, and to perform resource isolation on any second link interface.

[0160] In one possible implementation, the second allocation module 404 is also used to obtain the memory resources required by the expansion device under any second link interface; determine whether the current remaining memory resources meet the memory resources required by the expansion device; if the current remaining memory resources meet the memory resources required by the expansion device, allocate memory resources to any second link interface.

[0161] In a possible implementation, the second allocation module 404 is further configured to not allocate memory resources to any second link interface and to perform resource isolation on any second link interface if currently remaining memory resources do not meet memory resources required by the expansion device.

[0162] In one possible implementation, the resource use module 405 is specifically used to obtain a configuration parameter set of the server's boot loader; determine whether the configuration parameter set includes parameter configuration instructions corresponding to the need to reallocate memory resources, wherein the parameter configuration instructions are used to instruct the reallocation operation of the server's memory resources; if the configuration parameter set includes the parameter configuration instructions, the parameter configuration instructions are deleted so that the server allocates memory resources to each link interface according to the original allocation method configured before entering the operating system.

[0163] In a possible implementation, the configuration information detection module 402 is specifically configured to traverse and scan the device configuration information of each link interface, where the device configuration information includes a hot plug function; determine whether the hot plug function of each link interface is enabled; if the hot plug function of any link interface is enabled, determine that any link interface is a first link interface that needs to be preferentially allocated memory resources; if the hot plug function of any link interface is not enabled, determine that any link interface is a second link interface that does not need to be preferentially allocated memory resources.

[0164] In a possible implementation, the resource reallocation judgment module 401 is specifically configured to obtain the capacity of the total memory resources of the server and the memory resources required by each link interface; if the capacity of the total memory resources is not less than the memory resources required by each link interface, there is no need to reallocate memory resources for each link interface; if the capacity of the total memory resources is less than the memory resources required by each link interface, it is necessary to reallocate memory resources for each link interface.

[0165] In a possible implementation, the device further includes a link interface setting module, and the link interface setting module is configured to, after the server boots into the basic input / output system, determine whether each link interface needs to be preferentially allocated memory resources according to the connection status of each link interface; if any link interface needs to be preferentially allocated memory resources, determine that any link interface is a first link interface; configure the reserved memory resources of the first link interface, and set the resource reservation configuration information of the first link interface.

[0166] In a possible implementation, the interface setting module is further configured to, if any link interface does not need to be preferentially allocated memory resources, determine that any link interface is a second link interface, and configure the reserved memory resources of the second link interface.

[0167] In a possible implementation, the link interface setting module is further configured to determine whether there is an expansion device under each link interface; if there is no expansion device under any link interface, determine whether any link interface needs to access an expansion device; if any link interface does not need to access an expansion device, determine that any link interface does not need to be preferentially allocated memory resources; if any link interface needs to access an expansion device, determine that any link interface needs to be preferentially allocated memory resources.

[0168] In a possible implementation, the link interface setting module is further configured to, if there is an expansion device under any link interface, determine whether the expansion device is a target device according to the identifier of the expansion device; if the expansion device is a target device, determine that any link interface needs to be preferentially allocated memory resources; if the expansion device is not a target device, determine that any link interface does not need to be preferentially allocated memory resources.

[0169] In a possible implementation, a link interface setting module is provided. The link interface setting module is further configured to obtain the communication protocol specification followed by any link interface; determine a device detection instruction corresponding to any link interface according to the communication protocol specification, where the device detection instruction includes a protocol-specific field for triggering an extended device response; send the device detection instruction to any link interface; if feedback data sent by any link interface is received within a preset response timeout period, perform protocol compliance verification on the feedback data; if the feedback data passes the protocol compliance verification and the feedback data includes response information corresponding to the device detection instruction, determine that an extended device exists on any link interface; if feedback data sent by any link interface is not received within a preset response timeout period, determine that no extended device exists on any link interface.

[0170] In a possible implementation, the device further includes a second memory resource reallocation judgment module, which is configured to, when detecting that the server has completed startup and entered the operating system, determine whether a preset policy is enabled to prevent reallocation of memory resources for each link interface; if it is determined that the preset policy is enabled, do not reallocate memory resources for each link interface; if it is determined that the preset policy is not enabled, reallocate memory resources for each link interface.

[0171] In a possible implementation, the second memory resource reallocation judgment module is further configured to obtain configuration parameters of memory allocation control in the basic input / output system settings, where the configuration parameters of memory allocation control include a memory allocation lock flag, and the memory allocation lock flag is used to indicate whether the server is prohibited from reallocating the memory resources of each link interface when entering the operating system; if the memory allocation lock flag is in the on state, determine that the preset policy is enabled; if the memory allocation lock flag is in the off state, determine that the preset policy is not enabled.

[0172] For the description of the features in the embodiments corresponding to the memory resource allocation processing device, reference can be made to the relevant description in the embodiments corresponding to the memory resource allocation processing method, which will not be elaborated here one by one.

[0173] Figure 5 This is a schematic structural diagram of the server provided by the embodiments of the present application. As Figure 5 shown, the server provided in this embodiment includes at least one processor 501 and a memory 502. Optionally, the server further includes a communication component 503. Among them, the processor 501, the memory 502, and the communication component 503 are connected through a bus.

[0174] In a specific implementation process, at least one processor 501 executes computer execution instructions stored in the memory 502, so that at least one processor 501 executes the above-mentioned embodiments of the memory resource allocation processing method.

[0175] For the specific implementation process of the processor 501, reference can be made to the above method embodiments. Their implementation principles and technical effects are similar, and will not be elaborated here in this embodiment.

[0176] In the above embodiments, it should be understood that the processor may be a central processing unit (Central Processing Unit, abbreviated as CPU), or other general-purpose processors, digital signal processors (Digital Signal Processor, abbreviated as DSP), application specific integrated circuits (Application Specific Integrated Circuit, abbreviated as ASIC), etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the method disclosed in combination with the application can be directly implemented by the execution of the hardware processor, or implemented by the combination of hardware and software modules in the processor.

[0177] The memory may include high-speed memory (Random Access Memory, RAM), and may also include non-volatile memory (Non-volatile Memory, NVM), such as at least one disk memory.

[0178] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of representation, the bus in the drawings of this application is not limited to only one bus or one type of bus.

[0179] The embodiments of the present application also provide a computer-readable storage medium, in which a computer program is stored. The computer program is configured to execute the steps in any of the above method embodiments for memory resource allocation processing when running.

[0180] In an exemplary embodiment, the above computer-readable storage medium may include, but is not limited to: USB flash drives, read-only memories (Read-Only Memory, abbreviated as ROM), random access memories (Random Access Memory, abbreviated as RAM), mobile hard disks, magnetic disks, or optical discs and other media that can store computer programs.

[0181] An embodiment of the present application also provides a computer program product, including a computer program which, when executed by a processor, implements the steps in any of the above-mentioned embodiments of the memory resource allocation processing method.

[0182] An embodiment of the present application also provides 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-mentioned embodiments of the memory resource allocation processing method.

[0183] Those skilled in the art can further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Skilled professionals can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present application.

[0184] The above has introduced in detail a memory resource allocation processing method, device, storage medium, and product provided by the present application. Specific examples are used herein to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application. It should be noted that for those of ordinary skill in the art in the technical field, without departing from the principle of the present application, several improvements and modifications can be made to the present application, and these improvements and modifications also fall within the protection scope of the claims of the present application.

Claims

1. A method for processing memory resource allocation, characterized in that include: When it is detected that the server has completed booting and entered the operating system, judging whether it is necessary to reallocate memory resources for each link interface according to the total memory resources, wherein each link interface is used to connect each expansion device; If it is determined that memory resources need to be reallocated, resource reservation configuration information of each link interface is detected, wherein the resource reservation configuration information is used to indicate whether the corresponding link interface needs to be allocated memory resources preferentially, and the resource reservation configuration information is configured for each link interface before the server enters the operating system; For each detected first link interface to which memory resources need to be allocated preferentially, allocate memory resources to each first link interface according to a first preset rule; For each second link interface detected that does not need to allocate memory resources preferentially, after completing the allocation of memory resources to each first link interface, allocate memory resources to each second link interface according to a second preset rule; If it is determined that the memory resources do not need to be reallocated, a parameter configuration instruction is set to enable the server to allocate memory resources to each link interface according to the original allocation method configured before entering the operating system.

2. The memory resource allocation processing method according to claim 1, wherein The allocating memory resources to each first link interface according to a first preset rule includes: Determine whether there is an expansion device under each of the first link interfaces; If there is an expansion device under any first link interface, any first link interface is allocated according to the reserved memory resources, wherein the reserved memory resources are configured for each first link interface before the server enters the operating system.

3. The memory resource allocation processing method according to claim 2, wherein After determining whether there is an expansion device under each of the first link interfaces, the method further includes: If no expansion device exists under any first link interface, memory resources are allocated to any first link interface according to preset resource parameters.

4. The memory resource allocation processing method according to claim 1, characterized in that The allocating memory resources to each second link interface according to a second preset rule includes: After completing the allocation of memory resources for each of the first link interfaces, determining whether there is an expansion device under each of the second link interfaces; If there is an expansion device under any second link interface, unbinding the binding relationship between any second link interface and the reserved memory resources of any second link interface, and updating the reserved memory resources to the current remaining memory resources of the server, wherein the reserved memory resources are configured for the second link interface before the server enters the operating system; According to the current remaining memory resources, memory resources are allocated to any of the second link interfaces according to a third preset rule.

5. The memory resource allocation processing method according to claim 4, characterized in that After determining whether there is an extension device under each of the second link interfaces, the method further includes: If there is no expansion device under any second link interface, no memory resources are allocated to any second link interface, and resources of any second link interface are isolated.

6. The memory resource allocation processing method according to claim 4, wherein The allocating memory resources to any second link interface according to the current remaining memory resources and according to a third preset rule includes: Acquire memory resources required by an expansion device under any of the second link interfaces; Determining whether the current remaining memory resources meet the memory resources required by the expansion device; If the current remaining memory resources meet the memory resources required by the expansion device, allocate memory resources to any one of the second link interfaces.

7. The memory resource allocation processing method according to claim 6, characterized in that After determining whether the current remaining memory resources meet the memory resources required by the expansion device, it further includes: If the current remaining memory resources do not meet the memory resources required by the expansion device, do not allocate memory resources to any one of the second link interfaces, and perform resource isolation on any one of the second link interfaces.

8. The memory resource allocation processing method according to claim 1, characterized in that By setting parameter configuration instructions to enable the server to allocate memory resources to each link interface according to the original allocation method configured before entering the operating system, it includes: Obtain the configuration parameter set of the server's boot loader; Determine whether the configuration parameter set includes a parameter configuration instruction corresponding to the need to reallocate memory resources, where the parameter configuration instruction is used to indicate an operation to reallocate the memory resources of the server; If the configuration parameter set includes the parameter configuration instruction, delete the parameter configuration instruction so that the server allocates memory resources to each link interface according to the original allocation method configured before entering the operating system.

9. The memory resource allocation processing method according to claim 1, characterized in that Detect the resource reservation configuration information of each link interface, including: Traverse and scan the device configuration information of each link interface, where the device configuration information includes a hot plug function; Determine whether the hot plug function of each link interface is enabled; If the hot plug function of any one link interface is enabled, determine that the any one link interface is the first link interface that needs to be preferentially allocated memory resources; If the hot plug function of any one link interface is not enabled, determine that the any one link interface is the second link interface that does not need to be preferentially allocated memory resources.

10. The memory resource allocation processing method according to claim 1, wherein According to the total memory resources, determine whether it is necessary to reallocate memory resources for each link interface, including: Obtain the capacity of the total memory resources of the server and the memory resources required by each link interface; If the capacity of the total memory resources is not less than the memory resources required by each link interface, it is not necessary to reallocate memory resources for each link interface; If the capacity of the total memory resources is less than the memory resources required by each link interface, it is necessary to reallocate memory resources for each link interface.

11. The memory resource allocation processing method according to claim 1, wherein Before the server enters the operating system, it further includes: After the server boots into the basic input / output system, determine whether each link interface needs to be preferentially allocated memory resources according to the connection status of each link interface; If any one link interface needs to be preferentially allocated memory resources, determine the any one link interface as the first link interface; Configure the reserved memory resources of the first link interface and set the resource reservation configuration information of the first link interface.

12. The memory resource allocation processing method according to claim 11, wherein After determining whether each link interface needs to be preferentially allocated memory resources, it further includes: If any one link interface does not need to be preferentially allocated memory resources, determine the any one link interface as the second link interface and configure the reserved memory resources of the second link interface.

13. The memory resource allocation processing method according to claim 11, wherein According to the connection status of each link interface, determine whether each link interface needs to be preferentially allocated memory resources, including: Determine whether there is an expansion device under each of the link interfaces; If there is no expansion device under any of the link interfaces, determine whether the any link interface needs to access an expansion device; If the any link interface does not need to access an expansion device, determine that the any link interface does not need to be preferentially allocated memory resources; If the any link interface needs to access an expansion device, determine that the any link interface needs to be preferentially allocated memory resources.

14. The memory resource allocation processing method according to claim 13, wherein After determining whether there is an expansion device under each of the link interfaces, it further includes: If there is an expansion device under any of the link interfaces, determine whether the expansion device is a target device according to the identifier of the expansion device; If the expansion device is a target device, determine that the any link interface needs to be preferentially allocated memory resources; If the expansion device is not a target device, determine that the any link interface does not need to be preferentially allocated memory resources.

15. The memory resource allocation processing method according to claim 13, characterized in that Determining whether there is an expansion device under each of the link interfaces includes: Obtain the communication protocol specification followed by any link interface; According to the communication protocol specification, determine a device detection instruction corresponding to the any link interface, where the device detection instruction includes a protocol-specific field for triggering a response from the expansion device; Send the device detection instruction to the any link interface; If feedback data sent by the any link interface is received within a preset response timeout period, perform protocol compliance verification on the feedback data; If the feedback data passes the protocol compliance verification and the feedback data includes response information corresponding to the device detection instruction, determine that there is an expansion device under the any link interface; If no feedback data sent by the any link interface is received within the preset response timeout period, determine that there is no expansion device under the any link interface.

16. The memory resource allocation processing method according to claim 1, wherein It further includes: When it is detected that the server completes startup and enters the operating system, determine whether a preset policy is enabled to prevent reallocation of memory resources for each of the link interfaces; If it is determined that the preset policy is enabled, do not reallocate memory resources for each of the link interfaces; If it is determined that the preset policy is not enabled, reallocate memory resources for each of the link interfaces.

17. The memory resource allocation processing method according to claim 16, characterized in that Determining whether a preset policy is enabled to prevent reallocation of memory resources for each of the link interfaces includes: Obtain configuration parameters of memory allocation control in the basic input / output system settings, where the configuration parameters of memory allocation control include a memory allocation lock flag, and the memory allocation lock flag is used to indicate whether to prohibit the server from reallocating memory resources of each link interface when entering the operating system; If the memory allocation lock flag is in the on state, determine that the preset policy is enabled; If the memory allocation lock flag is in the off state, determine that the preset policy is not enabled.

18. A server, characterized in that, It includes: A memory for storing computer programs; A processor for implementing the steps of the memory resource allocation processing method according to any one of claims 1 to 17 when executing the computer programs.

19. A computer-readable storage medium, characterized in that, A computer program is stored in the computer-readable storage medium, wherein when the computer program is executed by a processor, the steps of the memory resource allocation processing method according to any one of claims 1 to 17 are implemented.

20. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, the steps of the memory resource allocation processing method according to any one of claims 1 to 17 are implemented.

Images