Control method, device and equipment of multi-path server system and medium

Abstract

The invention discloses a control method, device and equipment of a multi-path server system and a medium, and relates to the technical field of servers. The method comprises the following steps: disconnecting a bus between a main central processing unit and each central processing unit to be thermally closed; according to the method, the target signal is used for controlling the internal memory and the external equipment connected with each central processing unit to be subjected to hot shutdown to be in the hot shutdown state, hot shutdown of each central processing unit to be subjected to hot shutdown and the internal memory and the external equipment connected with the central processing unit to be subjected to hot shutdown is realized, and the energy consumption of the multi-path server system is reduced; the central processing unit connected with the main central processing unit, the memory corresponding to the central processing unit and the external equipment are closed, the main central processing unit is not closed, so that available central processing units exist, and normal operation of the multi-channel server system is guaranteed; the central processing units in the multi-path server system are connected with one another, and each central processing unit has a corresponding memory and external equipment, so that delay can be reduced, the data transmission rate can be improved, and the overall system performance can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of servers, and in particular to a control method, device, equipment and medium for a multi-channel server system. Background Art

[0002] In order to meet the increasingly complex data processing requirements, multi-way server systems are widely used. In a multi-way server system, the configuration of multiple central processing units (CPUs) can evenly distribute tasks to different CPUs, and multiple CPUs can process computing tasks in parallel, significantly improving the computing efficiency of the server system.

[0003] However, in actual use, not all CPUs and the memory and PCIE resources attached to them are used at the same time for different business needs or processing different data types. For example, for some simple business needs, sometimes a single or two CPUs with a small amount of memory space can meet the current application needs. In this case, all CPUs and memories are in operation, resulting in a huge waste of power consumption; and some devices attached to the CPU will not be called for a long time and are in an idle state, but these peripherals in the state will not be completely stopped under the system, but will continue to supply power, supply clocks and operate in the background at all times, which greatly wastes power.

[0004] It can be seen that how to reduce the energy consumption of a multi-way server system is a technical problem that people in this field need to solve urgently. Summary of the invention

[0005] The purpose of the present invention is to provide a control method, device, equipment and medium for a multi-way server system to solve the technical problem of high energy consumption of the multi-way server system.

[0006] In order to solve the above technical problems, the present invention provides a control method for a multi-way server system, comprising:

[0007] In the case of detecting an instruction for characterizing a CPU to be shut down, obtaining each CPU to be thermally shut down connected to the main CPU, and the memory and external devices connected to the CPU to be thermally shut down; wherein each CPU in the multi-way server system is connected to each other, and each CPU has a corresponding memory and external device; the main CPU is a CPU in the multi-way server system;

[0008] Disconnecting the bus between the main central processing unit and each of the central processing units to be thermally shut down;

[0009] An instruction to disable a target signal is sent to the memory and external devices connected to each of the central processing units to be thermally shut down, so that the memory and external devices connected to each of the central processing units to be thermally shut down are controlled by the target signal to be in a thermally disabled state; wherein the target signal includes at least a power-on signal, a clock signal, and a reset signal.

[0010] On the one hand, in the case where the instruction for characterizing the central processor to be shut down is detected, before acquiring each central processor to be thermally shut down connected to the main central processor, and the memory and external devices connected to the central processor to be thermally shut down, the method further includes:

[0011] Obtain the computational load of the business to be processed;

[0012] Determine whether the computing amount of the business to be processed is less than or equal to a preset value; wherein the preset value is determined by the computing power of a preset number of integrated components, and the preset number is equal to the total number of central processing units of the multi-way server system minus 1; the integrated components include a central processing unit, a memory connected to the central processing unit, and an external device; the preset number of integrated components includes an integrated component composed of the main central processing unit, a memory connected to the main central processing unit, and an external device;

[0013] If yes, sending an instruction for indicating that the CPU is to be shut down;

[0014] If not, all central processing units in the multi-way server system are kept in operation.

[0015] On the other hand, in the case where an instruction for characterizing a CPU to be shut down is detected, obtaining each CPU to be thermally shut down connected to the main CPU, and a memory and an external device connected to the CPU to be thermally shut down includes:

[0016] When an instruction for indicating that the central processor to be shut down is detected, the size of the computing power of each integrated component is obtained;

[0017] Determine a central processor for processing the business to be processed according to the computing volume of the business to be processed and the computing capacity of each integrated component;

[0018] Obtaining the remaining central processors in the multi-way server system; wherein the remaining central processors are the central processors among all the central processors in the multi-way server system except the central processor for processing the business to be processed;

[0019] Using the remaining CPUs as the CPUs to be thermally shut down;

[0020] The memory and the external devices connected to each of the central processing units to be thermally shut down are acquired.

[0021] On the other hand, disconnecting the bus between the main central processor and each of the central processors to be thermally shut down comprises:

[0022] Disconnecting the bus between the main central processing unit and each of the central processing units to be thermally shut down through the operating system;

[0023] The instruction of sending a disable target signal to the memory and the external device connected to each of the CPUs to be thermally shut down comprises:

[0024] An instruction to disable the target signal is sent through a controller to the memory and external devices connected to each central processing unit to be thermally shut down; wherein the controller is a controller having at least a timing control function.

[0025] On the other hand, after disconnecting the bus between the main central processor and each of the central processors to be thermally shut down, the method further includes:

[0026] Determine whether new pending business is received;

[0027] If not, then entering the step of sending an instruction of disabling a target signal to the memory and external device connected to each of the CPUs to be thermally shut down, so as to control the memory and external device connected to each of the CPUs to be thermally shut down to be in a thermally disabled state through the target signal;

[0028] If yes, then obtaining the computational load of the new service to be processed;

[0029] Obtain the computing power of the currently operating integrated component to determine the size;

[0030] When it is detected that the computing capacity of the currently normally operating integrated component is greater than or equal to the computing capacity of the new service to be processed, the new service to be processed is processed by using the currently normally operating integrated component;

[0031] When it is detected that the computing capacity of the currently normally operating integrated component is smaller than the computing capacity of the new service to be processed, obtaining the difference between the computing capacity of the new service to be processed and the computing capacity of the currently normally operating integrated component;

[0032] Determining the number of integrated components to be added according to the difference;

[0033] Selecting a central processor to be added from the remaining central processors according to the number of the integrated components to be added;

[0034] The central processor to be added and the central processor in the currently normally operating integrated component are used as new central processors to be enabled;

[0035] A bus connecting the main central processing unit and the central processing unit to be added;

[0036] Sending an instruction to enable a target signal to the memory and external device connected to each new CPU to be enabled, so as to control the memory and external device connected to each new CPU to be enabled to be in an enabled state through the target signal;

[0037] The new business to be processed is processed using the currently normally running integrated components and the integrated components to be added.

[0038] On the other hand, the bus connecting the main central processor and the central processor to be added includes:

[0039] Connecting a bus between the main central processing unit and the central processing unit to be added through an operating system;

[0040] The instruction of sending a disable target signal to the memory and the external device connected to each of the CPUs to be thermally shut down comprises:

[0041] An instruction to enable a target signal is sent through a controller to the memory and external devices connected to each new central processing unit to be enabled; wherein the controller is a controller having at least a timing control function.

[0042] On the other hand, after sending the instruction of disabling the target signal to the memory and the external device connected to each of the CPUs to be thermally shut down, the method further includes:

[0043] Receiving the process and execution result of the hot shutdown through the operating system and printing out the process and execution result of the hot shutdown using the operating system;

[0044] After the instruction of sending the activation target signal to the memory and external devices connected to each new CPU to be activated, the method further includes:

[0045] The hot-enabled process and execution result are received through the operating system and the hot-enabled process and execution result are printed out using the operating system.

[0046] In order to solve the above technical problems, the present invention further provides a control device for a multi-way server system, comprising:

[0047] an acquisition module, for acquiring, when an instruction for characterizing a central processor to be shut down is detected, each central processor to be thermally shut down connected to a main central processor, and a memory and an external device connected to the central processor to be thermally shut down; wherein each central processor in a multi-way server system is connected to each other, and each central processor has a corresponding memory and an external device; and the main central processor is a central processor in a multi-way server system;

[0048] A disconnection module, used to disconnect the bus between the main central processing unit and each central processing unit to be thermally shut down;

[0049] A sending module is used to send an instruction to disable a target signal to the memory and external devices connected to each of the central processing units to be thermally shut down, so as to control the memory and external devices connected to each of the central processing units to be thermally shut down to be in a thermally disabled state through the target signal; wherein the target signal includes at least a power-on signal, a clock signal and a reset signal.

[0050] In order to solve the above technical problems, the present invention further provides a control device for a multi-way server system, comprising:

[0051] Memory for storing computer programs;

[0052] The processor is used to implement the steps of the control method of the multi-way server system when executing the computer program.

[0053] In order to solve the above technical problem, the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the control method of the multi-way server system are implemented.

[0054] The beneficial effects of the present invention are as follows: first, in the method, by disconnecting the bus between the main central processor and each central processor to be thermally shut down; sending an instruction to disable the target signal to the memory and external devices connected to each central processor to be thermally shut down, thereby controlling the memory and external devices connected to each central processor to be thermally shut down to be in a thermally disabled state through the target signal, thereby realizing thermal shutdown of each central processor to be thermally shut down, the memory and external devices connected to the central processor to be thermally shut down, and reducing the energy consumption of the multi-way server system; secondly, when thermally shutting down the central processor, the memory and external devices corresponding to the central processor, the central processor connected to the main central processor, the memory and external devices corresponding to the central processor are shut down, while the main central processor, the memory and external devices corresponding to the central processor are not shut down, thereby ensuring that there is an available central processor in the multi-way server system and ensuring the normal operation of the multi-way server system; thirdly, the central processors in the multi-way server system are connected to each other, and each central processor has corresponding memory and external devices, which can reduce delays, increase data transmission rates, and thus improve overall system performance.

[0055] In addition, when an instruction for characterizing a central processor to be shut down is detected, before obtaining each central processor to be thermally shut down connected to the main central processor, and the memory and external devices connected to the central processor to be thermally shut down, if it is determined that the amount of computation of the business to be processed is less than or equal to a preset value, an instruction for characterizing the central processor to be shut down is sent, that is, for simple business needs, some central processors, memories and external devices are shut down, thereby achieving the purpose of energy saving while ensuring normal business processing.

[0056] The central processing unit used to process the business to be processed is determined according to the computing volume of the business to be processed and the computing power of each integrated component, and all the central processing units in the multi-way server system except the central processing unit used to process the business to be processed are used as central processing units to be thermally shut down, and the memories and external devices connected to each central processing unit to be thermally shut down are determined, thereby achieving a more accurate shutdown of the central processing unit and its corresponding memory and external devices.

[0057] By disconnecting the bus operating system between the main central processing unit and each central processing unit to be thermally shut down through the operating system, the central processing unit resources can be centrally controlled and managed to achieve more efficient resource allocation; by sending instructions to disable target signals to the memory and external devices connected to each central processing unit to be thermally shut down through a controller having at least a timing control function, it can be ensured that when the central processing unit is shut down, the memory and external devices connected to the central processing unit can also safely stop working to avoid data loss or damage.

[0058] After hot shutting down some central processors, if new business to be processed is received, the number of integrated components to be added is determined when it is detected that the computing power of the currently normally operating integrated components is less than the computing capacity of the new business to be processed, and the central processors to be added are selected from the remaining central processors according to the number of integrated components to be added, the bus between the main central processor and the central processor to be added is connected, and the target signal is enabled to control the memory and external devices connected to each new central processor to be enabled to be in an enabled state, thereby ensuring that there are enough central processors to process the business and improving the efficiency of business processing.

[0059] In addition, the present invention also provides a control device for a multi-way server system, a control equipment for a multi-way server system, and a computer-readable storage medium, which have the same or corresponding technical features as the control method for the multi-way server system mentioned above, and have the same effects as above. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0061] Figure 1 A flow chart of a control method for a multi-way server system provided by an embodiment of the present invention;

[0062] Figure 2 A schematic diagram of a multi-way server system architecture provided by an embodiment of the present invention;

[0063] Figure 3 A schematic diagram of a hardware circuit control provided by an embodiment of the present invention;

[0064] Figure 4 A schematic diagram of hot switching of a four-way server to a two-way server provided in an embodiment of the present invention;

[0065] Figure 5 A structural diagram of a control device of a multi-way server system provided in another embodiment of the present invention. DETAILED DESCRIPTION

[0066] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0067] The core of the present invention is to provide a control method, device, equipment and medium for a multi-way server system to solve the technical problem of high energy consumption of the multi-way server system.

[0068] With the rapid development of the electronic information industry, all walks of life have higher and higher requirements for server performance, and the number of server deployments is also growing exponentially. While providing more efficient services, a large number of servers are also consuming high amounts of electricity. The power consumption issue has become the focus of attention for many server users. Multi-way servers provide users with higher computing speed and computing density. Multiple CPUs can process computing tasks in parallel, significantly improving the overall computing power of the server, which is especially important for application scenarios that require processing large amounts of data and high-intensity computing. Multi-way servers can better allocate system resources and avoid overloading a single CPU. Through the load balancing mechanism, tasks can be evenly distributed to different CPUs, improving the utilization of system resources and system reliability. This redundant design greatly reduces the risk of system downtime due to hardware failures.

[0069] The current multi-way server system assumes that all CPUs, memory, and PCIE devices are in working state by default after power-on. In actual use, not all CPUs and the attached memory and PCIE resources are used at the same time for different business needs or processing different data types. For four-way or eight-way server systems, for some simple business needs, sometimes a single or two CPUs with a small amount of memory space can meet the current application needs. In this case, all CPUs and memories are in running state, resulting in a huge waste of power consumption. Moreover, some devices attached to these CPUs will be in idle state for a long time and will not be called, but these peripherals in idle state will not be completely stopped under the system, but will continue to supply power, supply clocks and operate in the background at all times. Some high-performance devices such as network cards and GPUs will have a large power consumption demand even in idle state, and these unused devices will cause a huge waste of power.

[0070] Therefore, it is very necessary to provide a multi-way server system design that supports mode hot switching for energy saving in server data centers. For business types with smaller loads, it supports flexible switching of multi-way servers to dual-way or single-way server systems, thereby reducing power consumption waste caused by redundant CPUs, dual in-line memory modules (DIMMs) and PCIE devices.

[0071] In order to enable those skilled in the art to better understand the solution of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. Figure 1 A flow chart of a control method for a multi-way server system provided by an embodiment of the present invention, such as Figure 1 As shown, the method includes:

[0072] S10: when an instruction for indicating a CPU to be shut down is detected, obtaining each CPU to be thermally shut down connected to the main CPU, and a memory and an external device connected to the CPU to be thermally shut down;

[0073] S11: disconnecting the bus between the main CPU and each CPU to be thermally shut down;

[0074] S12: Sending instructions to disable target signals to the memories and external devices connected to each central processing unit to be thermally shut down, so as to control the memories and external devices connected to each central processing unit to be thermally shut down to be in a thermally disabled state through the target signals; wherein the target signals include at least a power-on signal, a clock signal and a reset signal.

[0075] There is no limitation on the selected main CPU and the situation of sending the instruction for characterizing the CPU to be shut down. In order to ensure the hardware resources required for normal business processing, in implementation, when the instruction for characterizing the CPU to be shut down is detected, before obtaining each CPU to be thermally shut down connected to the main CPU, the memory and external devices connected to the CPU to be thermally shut down, it also includes:

[0076] Obtain the computational load of the business to be processed;

[0077] Determine whether the computing amount of the business to be processed is less than or equal to a preset value; wherein the preset value is determined by the computing power of a preset number of integrated components, and the preset number is equal to the total number of central processing units of the multi-way server system minus 1; the integrated components include a central processing unit, a memory connected to the central processing unit, and an external device; the preset number of integrated components includes an integrated component composed of a main central processing unit, a memory connected to the main central processing unit, and an external device;

[0078] If yes, sending an instruction for indicating that the CPU is to be shut down;

[0079] If not, all CPUs in the multi-way server system are kept running.

[0080] In the case of receiving an instruction for characterizing a CPU to be shut down, in order to make the shut down CPU more appropriate, in the case of detecting an instruction for characterizing a CPU to be shut down, obtaining each CPU to be thermally shut down connected to the main CPU, the memory connected to the CPU to be thermally shut down, and the external device including:

[0081] When an instruction for indicating that the central processor to be shut down is detected, the size of the computing power of each integrated component is obtained;

[0082] Determine the central processor for processing the business to be processed according to the computing volume of the business to be processed and the computing capacity of each integrated component;

[0083] Obtaining the remaining central processors in the multi-way server system; wherein the remaining central processors are the central processors in the multi-way server system except the central processors for processing the business to be processed;

[0084] The remaining CPUs are used as CPUs to be thermally shut down;

[0085] Get the memory and external devices connected to each CPU to be thermally shut down.

[0086] The external device may be a PCIE device. After determining the CPUs to be thermally shut down connected to the main CPU, the memory and the external devices connected to the CPUs to be thermally shut down, the bus between the main CPU and the CPUs to be thermally shut down is disconnected through the operating system; and an instruction to disable the target signal is sent to the memory and the external devices connected to the CPUs to be thermally shut down through the controller; wherein the controller is a controller having at least a timing control function.

[0087] In the above-mentioned process of hot shutting down the central processing unit, the user can actively evaluate the hardware resources required for the current business process, and screen out the CPU and its related memory and PCIE devices that can be hot shut down in the current process; the user can input a control command through the baseboard management controller (Baseboard Management Controller, BMC) interface or the operating system, and the operating system will first control the disconnection of the bus interconnecting the CPUs, so that the CPU to be shut down is isolated from the normally operating CPU, and the related memory and PCIE devices are isolated; then the operating system will control the power off of the CPU and its attached memory and PCIE devices through a controller (such as a chip such as a complex programmable logic device (Complex Programmable Logic Device, CPLD)).

[0088] The above process is to thermally shut down the CPU, the memory and the external devices under the CPU, so as to achieve the purpose of energy saving. In practice, after thermally shutting down the CPU, the memory and the external devices under the CPU, if there is a new business to be processed. In order to process the new business, after disconnecting the bus between the main central processor and each central processor to be thermally shut down, it also includes:

[0089] Determine whether new pending business is received;

[0090] If not, entering the step of sending an instruction to disable the target signal to the memory and external devices connected to each CPU to be thermally shut down, so as to control the memory and external devices connected to each CPU to be thermally shut down to be in a thermally disabled state through the target signal;

[0091] If yes, the computational load of the new business to be processed is obtained;

[0092] Obtain the computing power of the currently operating integrated component to determine the size;

[0093] When it is detected that the computing capacity of the currently normally operating integrated component is greater than or equal to the computing capacity of the new service to be processed, the new service to be processed is processed by using the currently normally operating integrated component;

[0094] When it is detected that the computing capacity of the currently normally operating integrated component is smaller than the computing capacity of the new service to be processed, the difference between the computing capacity of the new service to be processed and the computing capacity of the currently normally operating integrated component is obtained;

[0095] Determining the number of integrated components to be added according to the difference;

[0096] Selecting a CPU to be added from the remaining CPUs according to the number of integrated components to be added;

[0097] The CPU to be added and the CPU in the currently normally operating integrated component are used as new CPUs to be enabled;

[0098] A bus connecting the main central processing unit and the central processing unit to be added;

[0099] Sending an instruction to enable a target signal to the memory and external device connected to each new CPU to be enabled, so as to control the memory and external device connected to each new CPU to be enabled to be in an enabled state through the target signal;

[0100] Use the currently operating integrated components and the integrated components to be added to process new services to be processed.

[0101] It is worth noting that, in implementation, if the number of integrated components to be added is less than the number of remaining central processors, a central processor having the same number as the number of integrated components to be added is randomly selected from the remaining central processors as the central processor to be added;

[0102] If the number of integrated components to be added is equal to the number of remaining CPUs, all remaining CPUs are used as CPUs to be added;

[0103] If the number of integrated components to be added is greater than the number of remaining central processing units, the integrated component with the highest processing efficiency among all integrated components is obtained, and the remaining tasks in the new business to be processed are allocated to the integrated component with the highest processing efficiency for processing.

[0104] By judging the size of the number of integrated components to be added and the number of remaining central processors, it is ensured that all tasks on the new business to be processed can be processed. When the number of integrated components to be added is greater than the number of remaining central processors, the remaining tasks in the new business to be processed are processed by the integrated component with the highest processing efficiency, thereby improving the processing efficiency of the business.

[0105] In addition, in implementation, the bus between the main central processing unit and the central processing unit to be added is connected through the operating system; the controller sends an instruction to enable the target signal to the memory and external devices connected to each new central processing unit to be enabled; wherein the controller is a controller with at least a timing control function.

[0106] In order to facilitate the user to understand the process and result of thermal shutdown or thermal enablement, after sending the instruction of disabling the target signal to the memory and external devices connected to each CPU to be thermally shut down, it also includes:

[0107] receiving the hot shutdown process and execution result through the operating system and printing out the hot shutdown process and execution result using the operating system;

[0108] After sending an instruction of enabling the target signal to the memory and external devices connected to each new CPU to be enabled, the method further includes:

[0109] The hot-enabled process and execution result are received through the operating system and the hot-enabled process and execution result are printed out using the operating system.

[0110] In order to enable those skilled in the art to better understand the solution of the present invention, the present invention will be further described in detail below by taking a four-way server as an example in conjunction with the accompanying drawings and specific implementation methods. Figure 2 A schematic diagram of a multi-way server system architecture provided by an embodiment of the present invention, such as Figure 2As shown, they are CPU 1, CPU 2, CPU 3, and CPU 4, respectively. Each CPU corresponds to memory and external devices one by one. Each CPU is connected to each other through an interconnected high-speed bus S1; each CPU is connected to the corresponding memory through a high-speed interconnect bus S2, and each CPU is connected to the corresponding external device through a high-speed interconnect bus S3. CPU 1 is used as the main CPU. When running a simpler business, the user can evaluate the needs and hot-close the relevant functions of one or more of the three CPUs, CPU 2, CPU 3, and CPU 4, under the system and power off the CPU. When hot-removing or hot-adding a CPU, bus S1 should first disconnect the communication or reconnect; when hot-closing the CPU, the corresponding memory will also be hot-removed and powered off under the system. At the same time, the user can also control the re-enabling of the relevant CPU and related memory under the operating system according to the actual needs of the business. When hot-closing the CPU, the external devices on the corresponding CPU will also be hot-removed and powered off under the system. At the same time, the user can also control the re-enabling of the relevant CPU and external devices under the operating system according to the actual needs of the business.

[0111] Figure 3 A schematic diagram of a hardware circuit control provided by an embodiment of the present invention. Figure 3 As shown, it includes an operating system, a controller (a chip with functions such as timing control), a power supply module, and a reset control module. The operating system can be used by users to thermally shut down or thermally enable the CPU (such as Figure 2 The controller receives control information from the upstream operating system through the L2 bus. When it is necessary to perform hot-add CPU / DIMM / PCIE device operations, the controller will control the power supply on the motherboard through the L3 bus to provide power to the external device to be enabled, and control the enabling of the central processor and external devices such as releasing reset, providing clock (L4, L5 and L6), etc., and control all signals required to restore the peripherals according to the timing and logic requirements. Similarly, when it is necessary to perform a hot deactivation operation, the chip with functions such as timing control will also receive control information from the upstream operating system, and disable various key signals such as power supply required by the relevant central processor and peripherals according to the timing and logic requirements, so as to achieve the purpose of hot deactivation and energy saving of the target device.

[0112] The processes and results of hot start or hot stop of the CPU, memory and external devices by the above modules will also be fed back to the operating system through the relevant bus and the processes and results will be printed out in the operating system. In this way, the unnecessary CPU and external devices can be hot started or hot deactivated without disassembling the system while ensuring stable operation of the system. The main result of the above operation is the realization of flexible switching of the number of CPUs in multi-way servers without shutting down the system. The CPU and related memory and external devices can be enabled or disabled according to actual business needs, and the multi-way server can be flexibly switched to a dual-way or single-way server system to achieve precise energy saving.

[0113] Figure 4 A schematic diagram of a four-way server hot-swap dual-way provided by an embodiment of the present invention. The user actively evaluates the hardware resources required for the current business process and selects the central processor and its related memory and external devices that can be hot-shut down in the current process. Figure 4 When a four-way server is hot-swapped to a two-way server, the devices in the dotted box are those that need to be hot-removed; the user inputs a control command under the operating system, and the operating system will first control the disconnection of the bus interconnecting the central processors, so that the central processor to be shut down is isolated from the normally operating central processor, and the related memory and external devices are isolated.

[0114] Chips with functions such as timing control receive control information from the upstream operating system. When hot-add CPU / DIMM / PCIE device operations need to be performed, the chip with functions such as timing control will control the power supply on the motherboard through the bus to provide power to the external device to be enabled, and control the release of reset, clock supply, etc. required to enable the central processor and external devices, and control all signals required to restore the central processor and peripherals according to timing and logic requirements. Similarly, when hot deactivation operations need to be performed, chips with functions such as timing control will also receive control information from the upstream operating system, and disable various key signals such as power supply required by the relevant central processor and peripherals according to timing and logic requirements, so as to achieve the purpose of hot deactivation and energy saving of the target device.

[0115] The method provided in the embodiment of the present invention mainly aims at the problem of extra power consumption of the server caused by the central processing unit and peripherals in the idle state that will not be used in the business process, and supports the flexible switching of multi-way servers to dual-way or single-way server systems, thereby reducing the power consumption waste caused by redundant CPUs, DIMMs and external devices. The idle external devices are hot-started or hot-deactivated while ensuring the stable operation of the system and without disassembling the machine, thereby reducing the problem of extra power consumption of the server. Moreover, hot deactivation of long-term redundant equipment can reduce the loss of the equipment and increase the service life of the equipment.

[0116] In the above embodiments, the control method of the multi-way server system is described in detail, and the present invention also provides a control device of the multi-way server system and a corresponding embodiment of the control equipment of the multi-way server system. It should be noted that the present invention describes the embodiments of the device part from two perspectives, one is based on the perspective of the functional module, and the other is based on the perspective of the hardware.

[0117] A control device for a multi-way server system provided by an embodiment of the present invention includes, based on the perspective of functional modules:

[0118] The acquisition module is used to acquire each CPU to be thermally shut down connected to the main CPU, and the memory and external devices connected to the CPU to be thermally shut down, when an instruction for characterizing the CPU to be shut down is detected; wherein each CPU in the multi-way server system is connected to each other, and each CPU has corresponding memory and external devices; the main CPU is a CPU in the multi-way server system;

[0119] A disconnect module, used to disconnect the bus between the main central processing unit and each central processing unit to be thermally shut down;

[0120] The sending module is used to send instructions to disable target signals to the memories and external devices connected to each central processing unit to be thermally shut down, so as to control the memories and external devices connected to each central processing unit to be thermally shut down to be in a thermally disabled state through the target signals; wherein the target signals include at least a power-on signal, a clock signal and a reset signal.

[0121] In some embodiments, the control device of the multi-way server system further includes:

[0122] A first acquisition module, used to acquire the computational load of the business to be processed;

[0123] The first judgment module is used to judge whether the computing amount of the business to be processed is less than or equal to a preset value; wherein the preset value is determined by the computing power of a preset number of integrated components, and the preset number is equal to the total number of central processing units of the multi-way server system minus 1; the integrated components include a central processing unit, a memory connected to the central processing unit, and an external device; the preset number of integrated components includes an integrated component composed of a main central processing unit, a memory connected to the main central processing unit, and an external device; if so, the first sending module is triggered; if not, the holding module is triggered;

[0124] A first sending module, used for sending an instruction for indicating a central processing unit to be shut down;

[0125] The maintenance module is used to keep all the central processors in the multi-way server system in operation.

[0126] In some embodiments, the control device of the multi-way server system further includes:

[0127] A second judgment module is used to judge whether a new service to be processed is received; if not, the sending module is triggered; if so, the second acquisition module is triggered;

[0128] A second acquisition module is used to acquire the computing amount of a new business to be processed;

[0129] The third acquisition module is used to determine the computing power size of the currently normally operating integrated component;

[0130] A first processing module is used to process the new service to be processed by using the currently normally operating integrated component when it is detected that the computing capacity of the currently normally operating integrated component is greater than or equal to the computing capacity of the new service to be processed;

[0131] A fourth acquisition module is used to acquire the difference between the computing capacity of the new business to be processed and the computing capacity of the current normally operating integrated component, if it is detected that the computing capacity of the currently normally operating integrated component is less than the computing capacity of the new business to be processed;

[0132] A determination module, used for determining the number of integrated components to be added according to the difference;

[0133] A selection module, used for selecting a central processing unit to be added from the remaining central processing units according to the number of integrated components to be added;

[0134] As a module, it is used to use the central processor to be added and the central processor in the currently normally operating integrated component as the new central processor to be enabled;

[0135] A first connection module, used for connecting a bus between the main central processing unit and the central processing unit to be added;

[0136] A second sending module is used to send an instruction to enable a target signal to the memory and external device connected to each new CPU to be enabled, so as to control the memory and external device connected to each new CPU to be enabled to be in an enabled state through the target signal;

[0137] The second processing module is used to process new services to be processed by utilizing the currently normally operating integrated components and the integrated components to be added.

[0138] In some embodiments, the control device of the multi-way server system further includes:

[0139] A first receiving and printing module, used for receiving the process and execution result of the thermal shutdown through the operating system and printing out the process and execution result of the thermal shutdown using the operating system;

[0140] In some embodiments, the control device of the multi-way server system further includes:

[0141] The second receiving and printing module is used to receive the thermally enabled process and execution result through the operating system and print out the thermally enabled process and execution result using the operating system, with the same effect as above.

[0142] Since the embodiments of the apparatus part correspond to the embodiments of the method part, please refer to the description of the embodiments of the method part for the embodiments of the apparatus part, which will not be repeated here.

[0143] Figure 5 This is a structural diagram of a control device for a multi-way server system provided by another embodiment of the present invention. This embodiment is based on the hardware perspective, such as Figure 5 As shown, the control device of the multi-way server system includes:

[0144] A memory 20, used for storing computer programs;

[0145] The processor 21 is used to implement the steps of the method for controlling the multi-way server system mentioned in the above embodiment when executing the computer program.

[0146] Among them, the processor 21 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 21 can be implemented in at least one hardware form of a digital signal processor (DSP), a field-programmable gate array (FPGA), and a programmable logic array (PLA). The processor 21 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU; the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 21 may be integrated with a graphics processing unit (GPU, which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 21 may also include an artificial intelligence (AI) processor, which is used to process computing operations related to machine learning.

[0147] The memory 20 may include one or more computer-readable storage media, which may be non-transitory. The memory 20 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In this embodiment, the memory 20 is at least used to store the following computer program 201, wherein, after the computer program is loaded and executed by the processor 21, it can implement the relevant steps of the control method of the multi-way server system disclosed in any of the aforementioned embodiments. In addition, the resources stored in the memory 20 may also include an operating system 202 and data 203, etc., and the storage method may be temporary storage or permanent storage. Among them, the operating system 202 may include Windows, Unix, Linux, etc. The data 203 may include, but is not limited to, the data involved in the control method of the multi-way server system mentioned above, etc.

[0148] In some embodiments, the control device of the multi-way server system may also include a display screen 22 , an input / output interface 23 , a communication interface 24 , a power supply 25 , and a communication bus 26 .

[0149] Those skilled in the art will understand that Figure 5 The structure shown in the figure does not constitute a limitation on the control device of the multi-way server system, and may include more or fewer components than those shown in the figure.

[0150] The control device of the multi-way server system provided by the embodiment of the present invention includes a memory and a processor. When the processor executes the program stored in the memory, it can implement the following method: the control method of the multi-way server system, the effect is the same as above.

[0151] An embodiment of the present invention further provides a computer program product, including a computer program / instruction, which implements the steps of the above-mentioned control method for the multi-way server system when executed by a processor.

[0152] Finally, the present invention also provides an embodiment corresponding to a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps recorded in the above method embodiment are implemented.

[0153] It is understandable that if the method in the above embodiment is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc. Various media that can store program codes.

[0154] The computer-readable storage medium provided by the present invention includes the control method of the multi-way server system mentioned above, and the effect is the same as above.

[0155] The control method, device, equipment and medium of a multi-way server system provided by the present invention are introduced in detail above. The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the embodiments can be referenced to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description. It should be pointed out that for ordinary technicians in this technical field, without departing from the principle of the present invention, several improvements and modifications can be made to the present invention, and these improvements and modifications also fall within the scope of protection of the present invention.

[0156] It should also be noted that, in this specification, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

Claims

1. A control method for a multi-way server system, characterized in that: include: In the case of detecting an instruction for characterizing a CPU to be shut down, obtaining each CPU to be thermally shut down connected to the main CPU, and the memory and external devices connected to the CPU to be thermally shut down; wherein each CPU in the multi-way server system is connected to each other, and each CPU has a corresponding memory and external device; the main CPU is a CPU in the multi-way server system; Disconnecting the bus between the main central processing unit and each of the central processing units to be thermally shut down; An instruction to disable a target signal is sent to the memory and external devices connected to each of the central processing units to be thermally shut down, so that the memory and external devices connected to each of the central processing units to be thermally shut down are controlled by the target signal to be in a thermally disabled state; wherein the target signal includes at least a power-on signal, a clock signal, and a reset signal.

2. The control method of a multi-way server system according to claim 1, characterized in that: Before acquiring each CPU to be thermally shut down connected to the main CPU, and the memory and external devices connected to the CPU to be thermally shut down, upon detecting the instruction for characterizing the CPU to be thermally shut down, the method further includes: Obtain the computational load of the business to be processed; Determine whether the computing amount of the business to be processed is less than or equal to a preset value; wherein the preset value is determined by the computing power of a preset number of integrated components, and the preset number is equal to the total number of central processing units of the multi-way server system minus 1; the integrated components include a central processing unit, a memory connected to the central processing unit, and an external device; the preset number of integrated components includes an integrated component composed of the main central processing unit, a memory connected to the main central processing unit, and an external device; If yes, sending an instruction for indicating that the CPU is to be shut down; If not, all central processing units in the multi-way server system are kept in operation.

3. The control method of a multi-way server system according to claim 2, characterized in that: In the case where an instruction for characterizing a CPU to be shut down is detected, obtaining each CPU to be thermally shut down connected to the main CPU, and a memory and an external device connected to the CPU to be thermally shut down comprises: When an instruction for indicating that the central processor to be shut down is detected, the size of the computing power of each integrated component is obtained; Determine a central processor for processing the business to be processed according to the computing volume of the business to be processed and the computing capacity of each integrated component; Obtaining the remaining central processors in the multi-way server system; wherein the remaining central processors are the central processors among all the central processors in the multi-way server system except the central processor for processing the business to be processed; Using the remaining CPUs as the CPUs to be thermally shut down; The memory and the external devices connected to each of the central processing units to be thermally shut down are acquired.

4. The control method of a multi-way server system according to claim 1, characterized in that: The step of disconnecting the bus between the main CPU and each of the CPUs to be thermally shut down comprises: Disconnecting the bus between the main central processing unit and each of the central processing units to be thermally shut down through the operating system; The instruction of sending a disable target signal to the memory and the external device connected to each of the CPUs to be thermally shut down comprises: An instruction to disable the target signal is sent through a controller to the memory and external devices connected to each central processing unit to be thermally shut down; wherein the controller is a controller having at least a timing control function.

5. The control method of a multi-way server system according to claim 3, characterized in that: After disconnecting the bus between the main central processor and each of the central processors to be thermally shut down, the method further includes: Determine whether new pending business is received; If not, then entering the step of sending an instruction of disabling a target signal to the memory and external device connected to each of the CPUs to be thermally shut down, so as to control the memory and external device connected to each of the CPUs to be thermally shut down to be in a thermally disabled state through the target signal; If yes, then obtaining the computational load of the new service to be processed; Obtain the computing power of the currently operating integrated component to determine the size; When it is detected that the computing capacity of the currently normally operating integrated component is greater than or equal to the computing capacity of the new service to be processed, the new service to be processed is processed by using the currently normally operating integrated component; When it is detected that the computing capacity of the currently normally operating integrated component is smaller than the computing capacity of the new service to be processed, obtaining the difference between the computing capacity of the new service to be processed and the computing capacity of the currently normally operating integrated component; Determining the number of integrated components to be added according to the difference; Selecting a central processor to be added from the remaining central processors according to the number of the integrated components to be added; The central processor to be added and the central processor in the currently normally operating integrated component are used as new central processors to be enabled; A bus connecting the main central processing unit and the central processing unit to be added; Sending an instruction to enable a target signal to the memory and external device connected to each new CPU to be enabled, so as to control the memory and external device connected to each new CPU to be enabled to be in an enabled state through the target signal; The new business to be processed is processed using the currently normally running integrated components and the integrated components to be added.

6. The control method of a multi-way server system according to claim 5, characterized in that: The bus connecting the main central processor and the central processor to be added includes: Connecting a bus between the main central processing unit and the central processing unit to be added through an operating system; The instruction of sending a disable target signal to the memory and the external device connected to each of the CPUs to be thermally shut down comprises: An instruction to enable a target signal is sent through a controller to the memory and external devices connected to each new central processing unit to be enabled; wherein the controller is a controller having at least a timing control function.

7. The control method of a multi-way server system according to claim 5 or 6, characterized in that: After sending the instruction of disabling the target signal to the memory and the external device connected to each of the CPUs to be thermally shut down, the method further includes: Receiving the process and execution result of the hot shutdown through the operating system and printing out the process and execution result of the hot shutdown using the operating system; After the instruction of sending the activation target signal to the memory and external devices connected to each new CPU to be activated, the method further includes: The hot-enabled process and execution result are received through the operating system and the hot-enabled process and execution result are printed out using the operating system.

8. A control device for a multi-way server system, characterized in that: include: an acquisition module, for acquiring, when an instruction for characterizing a central processor to be shut down is detected, each central processor to be thermally shut down connected to a main central processor, and a memory and an external device connected to the central processor to be thermally shut down; wherein each central processor in a multi-way server system is connected to each other, and each central processor has a corresponding memory and an external device; and the main central processor is a central processor in a multi-way server system; A disconnection module, used to disconnect the bus between the main central processing unit and each central processing unit to be thermally shut down; A sending module is used to send an instruction to disable a target signal to the memory and external devices connected to each of the central processing units to be thermally shut down, so as to control the memory and external devices connected to each of the central processing units to be thermally shut down to be in a thermally disabled state through the target signal; wherein the target signal includes at least a power-on signal, a clock signal and a reset signal.

9. A control device for a multi-way server system, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the steps of the method for controlling a multi-way server system as claimed in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the control method of the multi-way server system according to any one of claims 1 to 7 are implemented.

Images