A server restart method under a full-uninstall architecture and related device

Abstract

The application provides a server restart method under a full uninstallation architecture and related equipment. The method comprises the following steps: an uninstallation card receives a host restart request; the uninstallation card freezes disk writing of the uninstallation card and starts linkage restart of the uninstallation card and a host server according to the host restart request, the uninstallation card is arranged in the host server; and the uninstallation card generates a restart command, the restart command is used for restarting the host server. The above method can avoid directly restarting the uninstallation card, ensure that no damage is caused to related file systems and hardware in the restart process, and improve restart safety.

Description

Technical Field

[0001] This invention relates to the field of cloud computing technology, and in particular to a server restart method and related equipment under a full offload architecture. Background Technology

[0002] Cloud computing, as an emerging industry in recent years, has gained widespread attention from the scientific and industrial communities. Its global rise, characterized by its flexible, efficient, low-cost, and energy-saving operation, has become a crucial engine for promoting green industrial development and a new business platform for the 21st century. With the continuous increase in the scale of public clouds, both bare-metal servers (dedicated physical servers in the cloud) and elastic cloud servers (basic computing components consisting of CPU, memory, operating system, and cloud disks) are placing higher demands on computing performance. To provide higher computing performance under the same specifications, the industry currently uses offloading card technology to offload the server's storage, network services, and management to an offloading card, and further, to completely offload the server's management resources to the offloading card (i.e., a full offloading architecture) to achieve higher computing performance.

[0003] In a non-unloaded architecture, servers are restarted via local reboot commands. Since the servers managed by the management node in a non-unloaded architecture are those whose managed resources have not been unloaded, local reboot commands are sufficient. However, in a full-unloaded architecture, because almost all the host server's managed resources are unloaded onto the unload card, the management node directly manages the unload card instead of the host server. The management node can only issue reboot commands to the unload card, which then performs a local reboot. However, directly rebooting the unload card can lead to problems such as corrupted file systems, hardware damage, and the inability to reset the unload card.

[0004] Therefore, how to build the capability to safely restart the uninstallation card and the host server, and avoid directly restarting the uninstallation card, is a problem that urgently needs to be solved. Summary of the Invention

[0005] This invention discloses a server restart method and related equipment under a full offload architecture, which can avoid directly restarting the offload card, ensure that the relevant file system is not damaged during the restart process, and improve restart security.

[0006] In a first aspect, this application provides a server restart method under a fully offload architecture, the method comprising: an offload card receiving a host restart request; the offload card freezing disk writes and starting a coordinated restart of the offload card and the host server according to the host restart request, the offload card being inserted into the host server; and the offload card generating a restart command for restarting the host server.

[0007] In the solution provided in this application, the unmount card freezes disk writes and configures the linkage restart capability with the host server, so that the unmount card is restarted when the host server is restarted, thereby avoiding direct restart of the unmount card, avoiding damage to the relevant file system and hardware, and improving restart security.

[0008] In conjunction with the first aspect, in one possible implementation of the first aspect, the unloading card configures a complex programmable logic device (CPLD) register according to the host restart request, the CPLD register being used to ensure that the unloading card and the host server achieve synchronous restart.

[0009] In the solution provided in this application, the unloading card is configured with a CPLD register to ensure that the host server restarts while the unloading card is restarting, thereby avoiding related file system and hardware failures caused by directly restarting the unloading card.

[0010] In conjunction with the first aspect, in one possible implementation of the first aspect, the uninstallation card determines whether a remote command execution channel exists between itself and the host server, the remote command execution channel being used for communication between the uninstallation card and the host server; if it is determined that a remote command execution channel exists, the uninstallation card sends the restart command to the host server through the remote command execution channel.

[0011] In the solution provided in this application, after the unloading card is configured with the ability to restart in conjunction with the host server, it can send a restart command directly to the host server through a remote command execution channel, so that the host server restarts according to the restart command and drives the unloading card to restart at the same time.

[0012] In conjunction with the first aspect, in one possible implementation of the first aspect, when the unloading card determines that there is no remote command execution channel, the unloading card calls the remote restart interface to send the restart command to the central control module, so that the central control module calls the management interface to send the restart command to the server management module. The server management module is used to restart the host server according to the restart command. The central control module and the server management module are located on the same management node, and the management node manages and monitors the host server.

[0013] In the solution provided in this application, if there is no remote command execution channel between the unloading card and the host server, the unloading card will indirectly send a restart command to the host server through the central control module and the server management module in the management area. With the assistance of the central control module and the server management module, the host server will be restarted, and the unloading card will be restarted at the same time as the host server restarts.

[0014] In conjunction with the first aspect, in one possible implementation of the first aspect, the management interface includes an ironic interface and a nova interface.

[0015] In the solution provided in this application, the central control module can send a restart command to the server management module by calling different management interfaces for different management scenarios, so that the server management module can restart the host server, thus expanding the applicable scenarios.

[0016] Secondly, this application provides a server restart system under a full offload architecture. The system includes an offload card and a host server. The offload card is inserted into the host server, wherein: the offload card is used to receive a host restart request, freeze disk writing on the offload card according to the host restart request, and enable the linkage restart between the offload card and the host server to generate a restart command; the host server is used to restart according to the restart command.

[0017] In conjunction with the second aspect, in one possible implementation of the second aspect, the unloading card is further configured to configure the CPLD register according to the host restart request, the CPLD register being used to ensure that the unloading card and the host server achieve synchronous restart.

[0018] In conjunction with the second aspect, in one possible implementation of the second aspect, the uninstallation card is further used to determine whether a remote command execution channel exists between it and the host server, the remote command execution channel being used for communication between the uninstallation card and the host server; if it is determined that a remote command execution channel exists, the uninstallation card sends the restart command to the host server through the remote command execution channel.

[0019] In conjunction with the second aspect, in one possible implementation of the second aspect, the system further includes a central control module and a server management module, which are located on the same management node. The central control module is used to receive the restart command sent by the unloading card through the remote restart interface, and to send the restart command to the server management module through the management interface. The server management module is used to restart the host server according to the restart command.

[0020] In conjunction with the second aspect, in one possible implementation of the second aspect, the management interface includes an ironic interface and a nova interface.

[0021] Thirdly, this application provides an unloading card, comprising: a receiving unit for receiving a host restart request; a processing unit for freezing disk writing of the unloading card and enabling a linkage restart between the unloading card and the host server according to the host restart request, wherein the unloading card is inserted into the host server; and a generating unit for generating a restart command for restarting the host server.

[0022] In conjunction with the third aspect, in one possible implementation of the third aspect, the processing unit is specifically used to: configure the complex programmable logic device (CPLD) register according to the host restart request, wherein the CPLD register is used to ensure that the offloading card and the host server achieve synchronous restart.

[0023] In conjunction with the third aspect, in one possible implementation of the third aspect, the processing unit is further configured to determine whether a remote command execution channel exists between it and the host server, the remote command execution channel being used for communication between the unloading card and the host server; the generating unit is further configured to, if it is determined that a remote command execution channel exists, send the restart command to the host server through the remote command execution channel.

[0024] In conjunction with the third aspect, in one possible implementation of the third aspect, if the processing unit determines that there is no remote command execution channel, the generation unit is further configured to call the remote restart interface to send the restart command to the central control module, so that the central control module calls the management interface to send the restart command to the server management module, wherein the server management module is configured to restart the host server according to the restart command, the central control module and the server management module are located on the same management node, and the management node manages and monitors the host server.

[0025] In conjunction with the third aspect, in one possible implementation of the third aspect, the management interface includes an ironic interface and a nova interface.

[0026] Fourthly, this application provides a computing device, the computing device including a processor and a memory, the memory being used to store program code, and the processor being used to call the program code in the memory to execute the method described in the first aspect and any implementation thereof.

[0027] Fifthly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, can implement the process of the method provided in the first aspect and in combination with any of the implementations of the first aspect.

[0028] Sixthly, this application provides a computer program product including instructions that, when executed by a computer, enable the computer to perform the process of the method provided in the first aspect and in combination with any implementation of the first aspect. Attached Figure Description

[0029] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0030] Figure 1 This is a schematic diagram illustrating a server restart scenario provided in an embodiment of this application;

[0031] Figure 2 This is a schematic diagram of the structure of a server restart system provided in an embodiment of this application;

[0032] Figure 3 This is a flowchart illustrating a server restart method provided in an embodiment of this application;

[0033] Figure 4 This is a schematic diagram of the structure of an unloading card provided in an embodiment of this application;

[0034] Figure 5 This is a schematic diagram of the structure of a computing device provided in an embodiment of this application. Detailed Implementation

[0035] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0036] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0037] First, some of the terms and related technologies used in this application will be explained in conjunction with the accompanying drawings to facilitate understanding by those skilled in the art.

[0038] Cloud computing is a service related to information technology, software, and the Internet. Cloud computing aggregates multiple computing resources to form a shared pool of computing resources, which is also called the "cloud". Through software, automated management is achieved, and tenants can access resources on the "cloud" at any time according to their needs. In theory, the resources on the "cloud" can be expanded indefinitely.

[0039] Bare metal servers are an upgraded version of traditional physical servers. They possess the superior performance of traditional physical servers and the convenient management platform of cloud servers, bringing users excellent computing performance and meeting the high performance and stability requirements of core application scenarios.

[0040] Elastic cloud servers (ECS) are basic computing components consisting of CPU, memory, operating system, and cloud disks. Activating an ECS is a self-service process; users only need to specify the CPU, memory, operating system, specifications, and login authentication method. Users can also adjust the ECS specifications at any time according to their needs. Once successfully created, an ECS can be used in the cloud just like a local personal computer (PC) or physical server.

[0041] Offloading refers to transferring computation or processing from the CPU to a dedicated processing unit. An offloading card is a processing unit that implements this offloading function. It can take the form of a physical computing device. An offloading card can offload the storage, network services, and management functions (such as elastic load balancing), and control plane services of a server (including bare metal servers or elastic cloud servers). The server being offloaded is also called the host server. The offloading card and the host server use the same server management system. In a full offloading architecture, since most of the management resources on the host server are offloaded to the offloading card, in an operation and maintenance scenario, the management node directly manages (i.e., communicates with) the offloading card, not the host server.

[0042] Ironic aims to provide users with self-service bare metal management services, allowing them to manage bare metal nodes like virtual machines. Deploying bare metal is as simple as deploying virtual machines, providing users with bare metal cloud infrastructure for multi-tenant networks. Ironic primarily relies on PXE and IPMI technologies to achieve batch deployment and system control of bare metal nodes. Therefore, most physical server models can be installed and managed for power status through Ironic. For individual physical server models, targeted management drivers can be quickly developed based on Ironic's pluggable driver architecture. With its standard API, extensive driver support, and lightweight footprint, Ironic is suitable for a variety of use cases, from small edge deployments to large data centers, providing an ideal operating environment for hosting high-performance cloud applications and architectures.

[0043] Nova is a core service of OpenStack, responsible for maintaining and managing computing resources in the cloud environment. For example, virtual machine lifecycle management is implemented through Nova. Nova contains many components that run as sub-services. Through these components, Nova can manage and control virtual machines (such as Elastic Cloud Servers), including virtual machine creation, scheduling, and startup.

[0044] In scenarios requiring a restart of the uninstallation card, the management node directly sends a restart command to the uninstallation card, and the uninstallation card restarts according to the command sent by the management node. For example... Figure 1 As shown, the host server 100 deploys basic services 110. The host server 100 can be a bare metal server or an elastic cloud server. The offloading card 200 deploys management plane services 210, an operating system (OS), and drivers 220. Management plane services 210 are offloaded from the host server 100 to the offloading card 200 and are used to communicate directly with the management node 300. Management plane services 210 can specifically include various services such as operation and maintenance services and resource scheduling services. The management node 300 deploys a management control module 310 for managing the host server 100 and the offloading card 200. When the offloading card 200 needs to be restarted (e.g., when the offloading card 200 needs to be cold upgraded), the management control module 310 in the management node 300 sends a restart command to the management plane services 210 in the offloading card 200, and the management plane services 210 execute the restart operation according to the restart command.

[0045] As can be seen, the above-mentioned method of restarting the uninstallation card is completed by the management node directly sending a restart command to the uninstallation card. However, restarting the uninstallation card directly will lead to problems such as corruption of the relevant file system and hardware damage, and the safety of the uninstallation card restart process cannot be guaranteed.

[0046] Based on the above, this application provides a server restart method and related equipment under a full offload architecture. By executing this server restart method, it is possible to avoid directly restarting the offload card, ensuring that the relevant file system will not be damaged during the restart process, and improving restart security.

[0047] The technical solutions of this application can be applied to various scenarios requiring server restarts under a fully unloaded architecture, including but not limited to daily operation and maintenance scenarios and server upgrade scenarios.

[0048] Figure 2 A schematic diagram of a server restart system provided in an embodiment of this application is shown. Figure 2As shown, the server restart system 200 includes: a tenant area 210 and a management area 220. The tenant area 210 includes server models under various management scenarios based on a full offload architecture. Specifically, the tenant area 210 includes a server model 2110 with a remote command execution channel, a server model 2120 under nova management and a server model 2130 under ironic management without a remote command execution channel. Server model 2110 includes an offload card 21110 and its corresponding host server 21120. The offload card 21110 is deployed with management plane services 21111 and OS and drivers 21112. There is a remote command execution channel between the offload card 21110 and the host server 21120, which can communicate directly (for example, the offload card 21110 can directly issue a restart command to the host server 21120). Server model 2120 includes an offload card 21210 and its corresponding host server 21220. The host server 21220 can be an elastic cloud server. The offload card 21210 is also deployed with management plane services 21211 and OS and drivers 21212. However, there is no remote command execution channel between the offload card 21210 and the host server 21220, and they cannot communicate directly. Server model 2130 is similar to server model 2120, except that the host server 21320 is different from the host server 21220. The host server 21320 can be a bare metal server. The management area 220 is used to manage and control the tenant area 210. Specifically, it can take the form of one or more management nodes. The management area 220 deploys a central control module 2210 and a server management module 2220. The central control module 2210 includes a nova interface 2221 and an ironic interface 2222. The central control module is used to send restart requests to the offloading cards (e.g., offloading card 21110, offloading card 21210, and offloading card 21310) in the tenant area to enable the management plane service configuration in the offloading card to have a synchronized restart capability with the host server (i.e., restarting simultaneously with the host server). The system also restarts the unloading card. Then, it receives the restart command returned by the unloading card (i.e., unloading card 21210 and unloading card 21310) that has not deployed a remote command execution channel, and calls the nova interface 2221 or the ironic interface 2222 to send the restart command to the server management module 2220. The server management module 2220 restarts the host server 21220 or the host server 21320 according to the restart command, and causes the host server 21220 or the host server 21320 to restart the unloading card 21210 or the unloading card 21310 at the same time.

[0049] Based on the above, the server restart method and related equipment under the full offload architecture provided in this application embodiment are described below. See also Figure 3 , Figure 3This is a flowchart illustrating a server restart method under a fully unloaded architecture, as provided in an embodiment of this application.

[0050] like Figure 3 As shown, the method includes, but is not limited to, the following steps:

[0051] S301: The unloading card receives a host restart request.

[0052] Specifically, when the server needs to be restarted during operation and maintenance or when the server is cold-upgraded (e.g., when relevant configurations are modified at the OS or system level), the user sends a host restart request to the unloading card through the central control module 2210 in the management area 220.

[0053] S302: The unloading card freezes disk writes based on the host's restart request.

[0054] Specifically, after receiving a host restart request from the central control module 2210, the control plane service in the offload card uses the unified virtualization platform (UVP) command to freeze the disk of the offload card and prohibit writing to avoid subsequent file system failures and other problems.

[0055] S303: Uninstall card enables linkage restart with the host server.

[0056] Specifically, after the disk freeze is completed, the control plane service in the offloading card configures a restart linkage capability for the offloading card. That is, the control plane service will configure a register of a complex programmable logic device (CPLD). This register can be accessed by the host server. By configuring a register value, the host server can restart the offloading card when it sends a reset signal to the offloading card. For example, the register value can be set to 1. When the host server restarts, it will generate a reset signal and send it to the offloading card. Since the offloading card is pre-configured with a register value of 1, it will trigger the offloading card to restart. This ensures that the offloading card will also restart when the host server restarts, realizing a linkage restart between the offloading card and the host server.

[0057] As can be seen, by freezing disk writes and configuring the restart linkage capability with the host server, the unmount card can ensure that the unmount card restarts at the same time as the host server restarts, thus avoiding problems such as damage to the relevant file system and hardware caused by restarting directly on the unmount card.

[0058] S304: The unloading card determines whether a remote command execution channel exists between itself and the host server. If it exists, proceed to step S305; otherwise, proceed to step S306.

[0059] Specifically, after freezing disk writes and configuring the restart linkage capability with the host server, the control plane service in the offload card can check whether a remote command execution channel has been deployed between the offload card and the host server. This remote command execution channel is used for direct communication between the offload card and the host server, and its specific form can be a communication network.

[0060] S305: The unloading card uses the remote command execution channel to send a restart command to the host server.

[0061] Specifically, the control plane service in the offloading card generates a restart command to restart the host server. This restart command is then sent to the host server via a remote command execution channel, causing the host server to restart upon receiving the command, and simultaneously restarting the offloading card. For example, the control plane service 21111 in the offloading card 21110 generates a restart command and sends it to the host server 21120 via the remote command execution channel. The host server 21120 restarts, simultaneously restarting the offloading card 21110.

[0062] S306: The unloading card calls the remote restart interface to send a restart command to the central control module.

[0063] Specifically, when the unloading card determines that it cannot directly send a restart command to the host server, it will call the remote restart interface provided by the management area 220 and send a restart command to the central control module 2210 in the management area 220.

[0064] S307: The central control module calls the management interface to send a restart command to the server management module.

[0065] Specifically, the central control module 2210 calls the corresponding management interface to send a restart command to the server management module 2220 based on different management and control scenarios.

[0066] Optionally, for bare metal server scenarios, the central control module 2210 can call the nova interface to send a restart command to the server management module 2220; for elastic cloud server scenarios, the central control module 2210 can call the ironic interface to send a restart command to the server management module 2220.

[0067] S308: The server management module checks whether the current status of the host server supports restarting.

[0068] Specifically, after receiving a restart command, the server management module 2220 can use the scheduling module to detect whether the current state of the host server supports restarting. Optionally, for bare metal server scenarios, it can determine whether the host server supports restarting by detecting whether the bare metal server is currently in the state of distributing resources to tenants. For example, if the bare metal server is currently distributing resources to tenants, the bare metal server is in a non-restartable state; otherwise, the bare metal server is in a restartable state. For elastic cloud server scenarios, it can determine whether the host server supports restarting by detecting whether there are virtual machines of other tenants running on the host server. If there are virtual machines of other tenants, the current state of the host server does not support restarting, and it is necessary to shut down the virtual machines of other tenants or migrate the virtual machines of other tenants so that the host server can support restarting.

[0069] S309: The server management module restarts the host server.

[0070] Specifically, after determining that the current state of the host server supports restarting, the server management module 2220 can restart the host server by calling the intelligent platform management interface tool (IPMItool).

[0071] Optionally, for bare metal server scenarios, the server management module 2220 performs a power-down and power-on operation on the bare metal server by calling its corresponding power status modification interface, thereby restarting the bare metal server; for elastic cloud server scenarios, the server management module 2220 performs a stop and restart operation on the elastic cloud server by calling its corresponding start / stop interface, thereby restarting the elastic cloud server.

[0072] Furthermore, the host server will generate a reset signal during the restart process. The host server will send this reset signal to the unloading card. Since the unloading card is pre-configured with the corresponding register values, when the host server sends the reset signal, it will trigger the unloading card to restart as well, thus completing the linkage restart between the unloading card and the host server.

[0073] It can be seen that by executing Figure 3 The method shown involves freezing disk writes and pre-configuring the ability to restart in conjunction with the host server. Then, a restart command is sent to the host server through the management area. This ensures that the unmount card restarts simultaneously with the host server restarts, thereby avoiding damage to the relevant file system and hardware caused by directly restarting the unmount card and improving the security of the unmount card restart.

[0074] The methods of the embodiments of this application have been described in detail above. In order to facilitate better implementation of the above solutions of the embodiments of this application, relevant equipment for cooperating in implementing the above solutions is also provided below.

[0075] See Figure 4 , Figure 4 This is a schematic diagram of the structure of an unloading card provided in an embodiment of this application. The unloading card can be as described above. Figure 3 The unloading card in the method embodiment can execute... Figure 3 The server restart method embodiment under the described full-unload architecture uses the unload card as the execution subject, and includes the following methods and steps. For example... Figure 4 As shown, the unloading card 400 includes a receiving unit 410, a processing unit 420, and a generating unit 430. Among them,

[0076] The receiving unit 410 is used to receive host restart requests;

[0077] Processing unit 420 is used to freeze disk writing of the unloading card and enable the linkage restart of the unloading card and the host server according to the host restart request, wherein the unloading card is inserted into the host server;

[0078] The generation unit 430 is used to generate a restart command, which is used to restart the host server.

[0079] Specifically, the receiving unit 410 is used to execute the aforementioned step S301, and optionally executes a method selected in the aforementioned steps; the processing unit 420 is used to execute the aforementioned steps S302, S303, and S304, and optionally executes a method selected in the aforementioned steps; the generating unit 430 is used to execute the aforementioned steps S305 and S306, and optionally executes a method selected in the aforementioned steps. The three units can transmit data to each other through a communication path. It should be understood that the units included in the unloading card 400 can be software units, hardware units, or a combination of both.

[0080] As one embodiment, the processing unit is specifically used to: configure the complex programmable logic device (CPLD) register according to the host restart request, wherein the CPLD register is used to ensure that the offloading card and the host server achieve synchronous restart.

[0081] As an example, the processing unit 420 is further configured to determine whether a remote command execution channel exists between it and the host server, the remote command execution channel being used for communication between the uninstallation card and the host server; the generation unit 430 is further configured to, if it is determined that a remote command execution channel exists, send the restart command to the host server through the remote command execution channel.

[0082] As an example, if the processing unit 420 determines that there is no remote command execution channel, the generation unit 430 is further configured to call the remote restart interface to send the restart command to the central control module, so that the central control module calls the management interface to send the restart command to the server management module. The server management module is configured to restart the host server according to the restart command. The central control module and the server management module are located on the same management node, and the management node manages and monitors the host server.

[0083] As one example, the management interface includes an ironic interface and a nova interface.

[0084] It is understood that the receiving unit 410 in the embodiments of this application can be implemented by a transceiver or transceiver-related circuit components, and the processing unit 420 and the generating unit 430 can be implemented by a processor or processor-related circuit components.

[0085] It should be noted that the structure of the unloading card described above is merely an example and should not constitute a specific limitation. The various units within the unloading card can be added, removed, or merged as needed. Furthermore, the operation and / or function of each unit in this unloading card are to achieve the above-mentioned... Figure 3 For the sake of brevity, the corresponding process of the described method will not be elaborated here.

[0086] See Figure 5 , Figure 5 This is a schematic diagram of the structure of a computing device provided in an embodiment of this application. Figure 5 As shown, the computing device 500 includes a processor 510, a communication interface 520, and a memory 530, which are interconnected via an internal bus 540.

[0087] The processor 510 may consist of one or more general-purpose processors, such as a central processing unit (CPU), or a combination of a CPU and hardware chips. The hardware chips may be application-specific integrated circuits (ASICs), programmable logic devices (PLDs), or combinations thereof. The PLDs may be complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), generic array logic (GALs), or any combination thereof.

[0088] Bus 540 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. Bus 540 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 5 The symbol is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0089] The memory 530 may include volatile memory, such as random access memory (RAM); the memory 530 may also include non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid-state drive (SSD); the memory 530 may also include combinations of the above types.

[0090] It should be noted that the memory 530 of the computing device 500 stores the code corresponding to each unit of the unloading card 400. The processor 510 executes this code to implement the function of each unit of the unloading card 400, that is, to execute the methods S301-S309.

[0091] This application also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, which, when executed by a processor, can implement some or all of the steps described in any of the above method embodiments.

[0092] This invention also provides a computer program that includes instructions that, when executed by a computer, enable the computer to perform some or all of the steps of any method for distributing regional resources.

[0093] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0094] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0095] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical or other forms.

[0096] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0097] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

Claims

1. A server restart method under a full offload architecture, characterized in that, include: The unloading card receives a host restart request; According to the host restart request, the unloading card freezes the disk writing of the unloading card and enables the linkage restart between the unloading card and the host server. The unloading card is inserted into the host server. The uninstallation card generates a restart command, which is used to restart the host server. The uninstallation card enables the linkage and restart between the uninstallation card and the host server, including: The unloading card configures the complex programmable logic device (CPLD) register according to the host restart request. The CPLD register is used to ensure that the unloading card and the host server restart synchronously.

2. The method as described in claim 1, characterized in that, The method further includes: The unloading card determines whether a remote command execution channel exists between it and the host server. The remote command execution channel is used for communication between the unloading card and the host server. If a remote command execution channel is confirmed to exist, the uninstallation card sends the restart command to the host server through the remote command execution channel.

3. The method as described in claim 2, characterized in that, If the unloading card determines that there is no remote command execution channel, the method further includes: The unloading card calls the remote restart interface to send the restart command to the central control module, so that the central control module calls the management interface to send the restart command to the server management module. The server management module is used to restart the host server according to the restart command. The central control module and the server management module are located on the same management node, and the management node manages and monitors the host server.

4. The method as described in claim 3, characterized in that, The management interface includes a bare-metal ironic interface and a virtual machine nova interface.

5. A server restart system under a fully unloaded architecture, characterized in that, Includes an offloading card and a host server, wherein the offloading card is inserted into the host server, wherein: The unloading card is used to receive host restart requests, freeze disk writing on the unloading card according to the host restart requests, and enable the linkage restart between the unloading card and the host server to generate a restart command; The host server is used to restart according to the restart command; The unloading card is also used to configure the CPLD register according to the host restart request, and the CPLD register is used to ensure that the unloading card and the host server restart synchronously.

6. The system as described in claim 5, characterized in that, The unloading card is also used to determine whether a remote command execution channel exists between it and the host server. The remote command execution channel is used for communication between the unloading card and the host server. If a remote command execution channel is confirmed to exist, the uninstallation card sends the restart command to the host server through the remote command execution channel.

7. The system as described in claim 6, characterized in that, The system also includes a central control module and a server management module, which are located on the same management node. The central control module is used to receive the restart command sent by the unloading card through the remote restart interface, and to send the restart command to the server management module through the management interface. The server management module is used to restart the host server according to the restart command.

8. The system as described in claim 7, characterized in that, The management interface includes the ironic interface and the nova interface.

9. An unloading card, characterized in that, include: The receiving unit is used to receive host restart requests; The processing unit is configured to freeze disk writing of the unloading card and enable the linkage restart between the unloading card and the host server according to the host restart request, wherein the unloading card is inserted into the host server. A generation unit is used to generate a restart command, which is used to restart the host server; The processing unit is specifically used for: Configure the Complex Programmable Logic Device (CPLD) register according to the host restart request. The CPLD register is used to ensure that the offload card and the host server restart synchronously.

10. The unloading card as described in claim 9, characterized in that, The processing unit is further configured to determine whether a remote command execution channel exists between it and the host server, wherein the remote command execution channel is used for communication between the unloading card and the host server; The generation unit is further configured to, when it is determined that a remote command execution channel exists, send the restart command to the host server through the remote command execution channel.

11. The unloading card as described in claim 10, characterized in that, If the processing unit determines that there is no remote command execution channel, The generation unit is further configured to call the remote restart interface to send the restart command to the central control module, so that the central control module calls the management interface to send the restart command to the server management module. The server management module is configured to restart the host server according to the restart command. The central control module and the server management module are located on the same management node, and the management node manages and monitors the host server.

12. The unloading card as described in claim 11, characterized in that, The management interface includes the ironic interface and the nova interface.

13. A computing device, characterized in that, The computing device includes a memory and a processor, the processor executing computer instructions stored in the memory, causing the computing device to perform the method according to any one of claims 1-4.

14. A computer-readable storage medium storing a computer program that, when executed by a processor, performs the method according to any one of claims 1-4.

Images