CN115277691A - An information processing method and device - Google Patents

The application provides an information processing method and device. The method is applied to an operating system management module in any service server in the distributed cluster networking, and comprises the following steps: when a preset condition is met, computing power information and health state information of the service server are acquired; and sending the acquired computing power information and health state information to the cluster client in the service server through the cluster client in the service server, so that the cluster management server determines the service servers needing to process a plurality of sub-service tasks corresponding to the target service task based on the received computing power information and health state information of at least one service server, and distributes each sub-service task to the corresponding service server for processing. The method and the device can improve user experience under distributed cluster networking.

一种信息处理方法及装置An information processing method and device

技术领域technical field

本申请涉及通信技术领域，尤其涉及一种信息处理方法及装置。The present application relates to the technical field of communications, and in particular to an information processing method and device.

背景技术Background technique

在现有的分布式集群组网中，通常包括一台集群管理服务器和多台业务服务器。其中，集群管理服务器负责将用户需要处理的业务任务拆分成多个子业务任务，并基于设定的分发规则将这些子业务任务分发给一些业务服务器进行处理；这些业务服务器负责对集群管理服务器分发的子业务任务进行处理，然后将处理结果反馈给集群管理服务器，由集群管理服务器汇总所有的子业务任务的处理结果并呈现给用户。在这里，在设定的分发规则中，所有的业务服务器的处理能力视为相同。In an existing distributed cluster network, it usually includes a cluster management server and multiple service servers. Among them, the cluster management server is responsible for splitting the business tasks that users need to process into multiple sub-business tasks, and distributes these sub-business tasks to some business servers for processing based on the set distribution rules; these business servers are responsible for distributing the sub-business tasks to the cluster management server The sub-business tasks are processed, and then the processing results are fed back to the cluster management server, and the cluster management server summarizes the processing results of all sub-business tasks and presents them to the user. Here, in the set distribution rule, the processing capabilities of all the service servers are considered to be the same.

实际上，各台业务服务器的处理性能并非完全相同，对于处理性能差一些的业务服务器而言，处理一次子业务任务的耗时通常较长，这样一来，就容易导致相应的业务任务的总处理时长较长，影响用户体验。In fact, the processing performance of each business server is not exactly the same. For a business server with poor processing performance, it usually takes a long time to process a sub-business task. The processing time is long, which affects the user experience.

发明内容Contents of the invention

为克服相关技术中存在的问题，本申请提供了一种信息处理方法及装置。In order to overcome the problems existing in the related technologies, the present application provides an information processing method and device.

根据本申请实施例的第一方面，提供一种信息处理方法，所述方法应用于分布式集群组网中的任一台业务服务器中的操作系统管理模块，所述方法包括：According to the first aspect of the embodiments of the present application, an information processing method is provided, the method is applied to an operating system management module in any service server in a distributed cluster network, and the method includes:

在满足预设条件时，获取该台业务服务器的算力信息和健康状态信息，其中，所述算力信息用于表征该台业务服务器的计算性能；When the preset condition is met, obtain computing power information and health status information of the business server, wherein the computing power information is used to characterize the computing performance of the business server;

通过该台业务服务器中的集群客户端，将获取到的算力信息和所述健康状态信息发送给所述分布式集群组网中的集群管理服务器，以使所述集群管理服务器基于接收到的至少一台业务服务器的算力信息和健康状态信息，确定需要处理目标业务任务对应的多个子业务任务的业务服务器，并将每个子业务任务分发给对应的业务服务器进行处理。Through the cluster client in the business server, the obtained computing power information and the health status information are sent to the cluster management server in the distributed cluster network, so that the cluster management server can The computing power information and health status information of at least one business server, determine the business server that needs to process multiple sub-business tasks corresponding to the target business task, and distribute each sub-business task to the corresponding business server for processing.

根据本申请实施例的第二方面，提供一种信息处理装置，所述装置应用于分布式集群组网中的任一台业务服务器中的操作系统管理模块，所述装置包括：According to the second aspect of the embodiment of the present application, an information processing device is provided, the device is applied to the operating system management module in any service server in the distributed cluster network, and the device includes:

获取单元，用于在所述操作系统管理模块满足预设条件时，获取该台业务服务器的算力信息和健康状态信息，其中，所述算力信息用于表征该台业务服务器的计算性能；An acquisition unit, configured to acquire computing power information and health status information of the business server when the operating system management module meets preset conditions, wherein the computing power information is used to characterize the computing performance of the business server;

处理单元，用于通过该台业务服务器中的集群客户端，将获取到的算力信息和所述健康状态信息发送给所述分布式集群组网中的集群管理服务器，以使所述集群管理服务器基于接收到的至少一台业务服务器的算力信息和健康状态信息，确定需要处理目标业务任务对应的多个子业务任务的业务服务器，并将每个子业务任务分发给对应的业务服务器进行处理。The processing unit is configured to send the acquired computing power information and the health state information to the cluster management server in the distributed cluster networking through the cluster client in the business server, so that the cluster Based on the received computing power information and health status information of at least one business server, the management server determines the business server that needs to process multiple sub-business tasks corresponding to the target business task, and distributes each sub-business task to the corresponding business server for processing .

本申请的实施例提供的技术方案可以包括以下有益效果：The technical solutions provided by the embodiments of the present application may include the following beneficial effects:

在本申请实施例中，分布式集群组网中的各台业务服务器中的操作系统管理模块在自己满足预设条件的情形下，会获取自己所属的业务服务器的算力信息和健康状态信息；然后通过自己所属的业务服务器中的集群客户端，将获取到的算力信息和健康状态信息发送给分布式集群组网中的集群管理服务器，以便于集群管理服务器可以基于这些算力信息和健康状态信息，确定需要处理目标业务任务对应的多个子业务任务的业务服务器，并将每个子业务任务分发给对应的业务服务器进行处理。这样一来，集群管理服务器可以基于这些业务服务器的处理能力合理地分发子业务任务，使得相应的业务服务器可以快速处理分发的子业务任务，从而缩短目标业务任务的总处理时长，进而提高了用户体验。In the embodiment of this application, the operating system management module in each business server in the distributed cluster network will obtain the computing power information and health status information of the business server to which it belongs when it meets the preset conditions. ; Then send the obtained computing power information and health status information to the cluster management server in the distributed cluster network through the cluster client in the business server to which it belongs, so that the cluster management server can use these computing power information and health status information, determine the business server that needs to process multiple sub-business tasks corresponding to the target business task, and distribute each sub-business task to the corresponding business server for processing. In this way, the cluster management server can reasonably distribute sub-business tasks based on the processing capabilities of these business servers, so that the corresponding business servers can quickly process the distributed sub-business tasks, thereby shortening the total processing time of the target business tasks and improving the user experience. experience.

应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，并不能限制本申请。It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.

附图说明Description of drawings

此处的附图被并入说明书中并构成本申请的一部分，示出了符合本申请的实施例，并与说明书一起用于解释本申请的原理。The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description serve to explain the principles of the application.

图1为本申请实施例提供的分布式集群组网的架构示意图；FIG. 1 is a schematic diagram of the architecture of the distributed cluster network provided by the embodiment of the present application;

图2为本申请实施例提供的一种信息处理方法的流程示意图；FIG. 2 is a schematic flowchart of an information processing method provided in an embodiment of the present application;

图3为本申请实施例提供的一种信息处理装置的结构示意图。FIG. 3 is a schematic structural diagram of an information processing device provided by an embodiment of the present application.

具体实施方式Detailed ways

这里将详细地对示例性实施例进行说明，其示例表示在附图中。下面的描述涉及附图时，除非另有表示，不同附图中的相同数字表示相同或相似的要素。以下示例性实施例中所描述的实施方式并不代表与本申请相一致的所有实施方式。相反，它们仅是与如所附权利要求书中所详述的、本申请的一些方面相一致的装置和方法的例子。Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with aspects of the present application as recited in the appended claims.

在本申请使用的术语是仅仅出于描述特定实施例的目的，而非旨在限制本申请。在本申请和所附权利要求书中所使用的单数形式的“一种”、“所述”和“该”也旨在包括多数形式，除非上下文清楚地表示其他含义。还应当理解，本文中使用的术语“和/或”是指并包含一个或多个相关联的列出项目的任何或所有可能组合。The terminology used in this application is for the purpose of describing particular embodiments only, and is not intended to limit the application. As used in this application and the appended claims, the singular forms "a", "the", and "the" are intended to include the plural forms as well, unless the context clearly dictates otherwise. It should also be understood that the term "and/or" as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

接下来对本申请实施例进行详细说明。Next, the embodiments of the present application will be described in detail.

本申请实施例提供了一种信息处理方法，该方法应用于分布式集群组网中的任一台业务服务器(例如，如图1所示的业务服务器1)中的操作系统管理模块，如图2所示，该方法可以包括如下步骤：The embodiment of the present application provides an information processing method, which is applied to the operating system management module in any service server (for example, the service server 1 shown in FIG. 1 ) in the distributed cluster network, such as As shown in Figure 2, the method may include the following steps:

S21、在满足预设条件时，获取该台业务服务器的算力信息和健康状态信息。S21. Obtain computing power information and health status information of the business server when the preset condition is met.

在本步骤中，算力信息主要用于表征该台业务服务器的计算性能。In this step, the computing power information is mainly used to characterize the computing performance of the business server.

S22、通过该台业务服务器中的集群客户端，将获取到的算力信息和健康状态信息发送给分布式集群组网中的集群管理服务器，以使集群管理服务器基于接收到的至少一台业务服务器的算力信息和健康状态信息，确定需要处理目标业务任务对应的多个子业务任务的业务服务器，并将每个子业务任务分发给对应的业务服务器进行处理。S22. Through the cluster client in the business server, send the obtained computing power information and health status information to the cluster management server in the distributed cluster network, so that the cluster management server can based on the received at least one The computing power information and health status information of the business server determines the business server that needs to process multiple sub-business tasks corresponding to the target business task, and distributes each sub-business task to the corresponding business server for processing.

具体地，在上述步骤S11中，上述预设条件为该台业务服务器初始上电、到达设定周期或者通过集群客户端接收到集群管理服务器发送的用于查询该台业务服务器的算力信息和健康状态信息的查询请求。Specifically, in the above-mentioned step S11, the above-mentioned preset condition is that the business server is initially powered on, reaches the set period, or receives the computing power information and Query request for health status information.

也就是说，对于操作系统管理模块而言，可以在以下几种情形下执行获取该台业务服务器的算力信息和健康状态信息的步骤：That is to say, for the operating system management module, the steps of obtaining the computing power information and health status information of the business server can be performed in the following situations:

第一种情形：自身所属的业务服务器初始上电。The first situation: the service server to which it belongs is initially powered on.

第二种情形：到达设定周期。The second situation: the set period is reached.

在这里，设定周期可根据操作系统管理模块所属的业务服务器所在的分布式集群组网的实际网络需求来设定。Here, the setting period can be set according to the actual network requirements of the distributed cluster network where the business server to which the operating system management module belongs is located.

第三种情形：通过集群客户端接收到集群管理服务器发送的用于查询该台业务服务器的算力信息和健康状态信息的查询请求。The third situation: the cluster client receives a query request sent by the cluster management server for querying the computing power information and health status information of the business server.

另外，在上述步骤S11中，该台业务服务器的算力信息可以包括该台业务服务器中的各个指定硬件的参数；这些指定硬件可以包括中央处理器(Central Processing Unit，CPU)、图形处理器(graphics processing unit，GPU)、输入/输出(Input/Output，I/O)存储器的参数、内存的参数等。例如，在某个指定硬件为CPU时，该CPU的参数可以包括频率、型号、使用率等。In addition, in the above step S11, the computing power information of the business server may include the parameters of each designated hardware in the business server; these designated hardware may include a central processing unit (Central Processing Unit, CPU), a graphics processing unit ( graphics processing unit, GPU), input/output (Input/Output, I/O) memory parameters, memory parameters, etc. For example, when a certain specified hardware is a CPU, the parameters of the CPU may include frequency, model, usage rate, and the like.

在上述步骤S12中，上述健康状态信息包括该台业务服务器运行的各个指定软件的健康状态和该业务服务器中的各个指定硬件(与上面提及的指定硬件相同)的健康状态。In the above step S12, the health status information includes the health status of each specified software running on the service server and the health status of each specified hardware (same as the specified hardware mentioned above) in the service server.

在这种情形下，操作系统管理模块可以通过以下方式获取该业务服务器中的各个指定硬件的健康状态：In this case, the operating system management module can obtain the health status of each specified hardware in the business server in the following ways:

获取各个指定硬件的运行参数；在这里，每个指定硬件的运行参数可以是对应指定硬件的当前使用率；Acquiring the operating parameters of each specified hardware; here, the operating parameters of each specified hardware may be the current usage rate of the corresponding specified hardware;

将获取到的运行参数发送给该台业务服务器中的基板管理控制器BMC；Send the obtained operating parameters to the baseboard management controller BMC in the service server;

接收BMC发送的指定硬件的健康状态，其中，指定硬件的健康状态为BMC基于获取到的运行参数确定出的。The health status of the designated hardware sent by the BMC is received, wherein the health status of the designated hardware is determined by the BMC based on the acquired operating parameters.

需要说明的是，在本申请实施例中，操作系统管理模块执行完上述步骤S12之后，对于集群管理服务器而言，可以基于接收到的至少一台业务服务器的算力信息和健康状态信息，确定需要处理目标业务任务对应的多个子业务任务的业务服务器，这样一来，集群管理服务器可以基于这些业务服务器的处理能力合理地分发子业务任务，使得相应的业务服务器可以快速处理分发的子业务任务，从而缩短目标业务任务的总处理时长，进而提高了用户体验。It should be noted that, in this embodiment of the application, after the operating system management module executes the above step S12, for the cluster management server, based on the received computing power information and health status information of at least one business server, determine Business servers that need to process multiple sub-business tasks corresponding to target business tasks, so that the cluster management server can reasonably distribute sub-business tasks based on the processing capabilities of these business servers, so that the corresponding business servers can quickly process the distributed sub-business tasks , thereby shortening the total processing time of the target business task, thereby improving user experience.

具体地，集群管理服务器在基于接收到的至少一台业务服务器的算力信息和健康状态信息，确定需要处理目标业务任务对应的多个子业务任务的业务服务器时，可以通过以下方式实现：Specifically, when the cluster management server determines the business server that needs to process multiple sub-business tasks corresponding to the target business task based on the received computing power information and health status information of at least one business server, it can be implemented in the following manner:

针对每个子业务任务，集群管理服务器将运行的各指定软件的健康状态和各指定硬件的健康状态均为正常的业务服务器，确定为候选业务服务器；For each sub-business task, the cluster management server will determine the business server whose health status of each specified software and the health status of each specified hardware is normal as a candidate business server;

集群管理服务器根据每台候选业务服务器的算力信息，确定一台满足预设条件的候选业务服务器，并将确定出的业务服务器作为需要处理该子业务任务的业务服务器。The cluster management server determines a candidate service server that satisfies preset conditions according to the computing power information of each candidate service server, and uses the determined service server as the service server that needs to process the sub-service task.

在一个例子中，集群管理服务器在确定一台满足预设条件的候选业务服务器时，可以采用如下方式确定：In an example, when the cluster management server determines a candidate service server that satisfies preset conditions, it may be determined in the following manner:

将算力信息中包括的各指定硬件的使用率均不大于各自对应的设定阈值的候选业务服务器，确定为满足预设条件的候选业务服务器。A candidate service server whose usage rate of each designated hardware included in the computing power information is not greater than a corresponding set threshold is determined as a candidate service server satisfying a preset condition.

在另一个例子中，集群管理服务器在确定一台满足预设条件的候选业务服务器时，可以采用如下方式确定：In another example, when the cluster management server determines a candidate service server that satisfies preset conditions, it may be determined in the following manner:

集群管理服务器据针对该子业务任务设置的各指定硬件的权重系数和每台候选业务服务器的算力信息中包括的各指定硬件的使用率，计算每台候选业务服务器的性能评估值；The cluster management server calculates the performance evaluation value of each candidate service server according to the weight coefficient of each specified hardware set for the sub-service task and the utilization rate of each specified hardware included in the computing power information of each candidate service server;

将计算出的性能评估值最大的候选业务服务器，确定为满足预设条件的候选业务服务器。The candidate service server whose calculated performance evaluation value is the largest is determined as the candidate service server satisfying the preset condition.

在这里，针对该子业务任务，集群管理服务器在计算每台候选业务服务器的性能评估值时，可以采用如下方式计算：Here, for this sub-business task, when the cluster management server calculates the performance evaluation value of each candidate business server, it can be calculated in the following manner:

针对每台候选业务服务器，集群管理服务器根据该台候选业务服务器的算力信息中包括的各指定硬件的使用率，计算该台候选业务服务器的中的各指定硬件的剩余使用率；For each candidate service server, the cluster management server calculates the remaining utilization rate of each specified hardware in the candidate service server according to the utilization rate of each specified hardware included in the computing power information of the candidate service server;

集群管理服务器将该台候选业务服务器中的每个指定硬件的剩余使用率与该指定硬件的权重系数进行求积运算，并计算所有的运算结果之和，得到该台候选业务服务器的性能评估值。The cluster management server calculates the remaining utilization rate of each specified hardware in the candidate service server and the weight coefficient of the specified hardware, and calculates the sum of all calculation results to obtain the performance evaluation value of the candidate service server .

当然，集群管理服务器在确定一台满足预设条件的候选业务服务器时，还可以采用其他方式来确定，在此不再一一列举。Of course, when the cluster management server determines a candidate service server that meets the preset conditions, it can also use other methods to determine, which will not be listed here.

例如，假设图1中的集群管理服务器接收到了业务服务器1至业务服务器5发送的算力信息和健康状态信息；假设集群服务器将需要处理的业务任务1拆分成了3个子业务任务，分别为子业务任务11、子业务任务12和子业务任务13；假设集群管理服务器采用上述任一种确定方式确定出需要处理子业务任务11的业务服务器是业务服务器1，那么，集群管理服务器会将子业务任务11分发给业务服务器1进行处理；假设集群管理服务器采用上述任一种确定方式确定出需要处理子业务任务12的业务服务器是业务服务器3，那么，集群管理服务器会将子业务任务12分发给业务服务器3进行处理；假设集群管理服务器采用上述任一种确定方式确定出需要处理子业务任务13的业务服务器是业务服务器5，那么，集群管理服务器会将子业务任务13分发给业务服务器5进行处理。For example, assume that the cluster management server in Figure 1 has received the computing power information and health status information sent by business server 1 to business server 5; suppose that the cluster server splits business task 1 to be processed into three sub-business tasks, respectively Sub-business task 11, sub-business task 12 and sub-business task 13; assuming that the cluster management server uses any of the above determination methods to determine that the business server that needs to process sub-business task 11 is business server 1, then the cluster management server will sub-business Task 11 is distributed to business server 1 for processing; assuming that the cluster management server determines that the business server that needs to process sub-business task 12 is business server 3 by using any of the above determination methods, then the cluster management server will distribute sub-business task 12 to The business server 3 is processed; assuming that the cluster management server uses any of the above-mentioned determination methods to determine that the business server that needs to process the sub-business task 13 is the business server 5, then the cluster management server will distribute the sub-business task 13 to the business server 5 for processing. deal with.

进一步地，在本申请实施例中，为了节省该台业务服务器的资源消耗，操作系统管理模块还可以执行以下操作：Further, in this embodiment of the application, in order to save the resource consumption of the business server, the operating system management module can also perform the following operations:

在监测到集群客户端的工作状态为空闲状态时，控制该台业务服务器进入节能模式。When it is detected that the working state of the cluster client is idle, the service server is controlled to enter the energy-saving mode.

更进一步地，在本申请实施例中，为了进一步提高用户体验，操作系统管理模块还可以执行以下操作：Furthermore, in this embodiment of the application, in order to further improve user experience, the operating system management module can also perform the following operations:

在接收到管理员输入的设备维护指令时，通过集群客户端将设备维护指令发送给集群管理服务器，以使集群管理服务器在设备维护指令所指示的维护时间段内不向该台业务服务器下发子业务。When the device maintenance instruction input by the administrator is received, the device maintenance instruction is sent to the cluster management server through the cluster client, so that the cluster management server does not send the device maintenance instruction to the service server within the maintenance time period indicated by the device maintenance instruction. sub business.

由以上技术方案可以看出，在本申请实施例中，分布式集群组网中的各台业务服务器中的操作系统管理模块在自己满足预设条件的情形下，会获取自己所属的业务服务器的算力信息和健康状态信息；然后通过自己所属的业务服务器中的集群客户端，将获取到的算力信息和健康状态信息发送给分布式集群组网中的集群管理服务器，以便于集群管理服务器可以基于这些算力信息和健康状态信息，确定需要处理目标业务任务对应的多个子业务任务的业务服务器，并将每个子业务任务分发给对应的业务服务器进行处理。这样一来，集群管理服务器可以基于这些业务服务器的处理能力合理地分发子业务任务，使得相应的业务服务器可以快速处理分发的子业务任务，从而缩短目标业务任务的总处理时长，进而提高了用户体验。It can be seen from the above technical solutions that in the embodiment of the present application, the operating system management module in each business server in the distributed cluster network will obtain the business server to which it belongs if it satisfies the preset conditions. The computing power information and health status information; and then through the cluster client in the business server to which it belongs, the obtained computing power information and health status information are sent to the cluster management server in the distributed cluster network, so that the cluster Based on these computing power information and health status information, the management server can determine the service servers that need to process multiple sub-service tasks corresponding to the target service task, and distribute each sub-service task to the corresponding service server for processing. In this way, the cluster management server can reasonably distribute sub-business tasks based on the processing capabilities of these business servers, so that the corresponding business servers can quickly process the distributed sub-business tasks, thereby shortening the total processing time of the target business tasks and improving the user experience. experience.

基于同一发明构思，本申请还提供了一种信息处理装置，所述装置应用于分布式集群组网中的任一台业务服务器中的操作系统管理模块，其结构示意图如图3所示，具体包括：Based on the same inventive concept, this application also provides an information processing device, which is applied to the operating system management module of any service server in a distributed cluster network, and its structural diagram is shown in Figure 3. Specifically include:

获取单元31，用于在所述操作系统管理模块满足预设条件时，获取该台业务服务器的算力信息和健康状态信息，其中，所述算力信息用于表征该台业务服务器的计算性能；An acquisition unit 31, configured to acquire computing power information and health status information of the business server when the operating system management module meets preset conditions, wherein the computing power information is used to characterize the computing performance of the business server ;

处理单元32，用于通过该台业务服务器中的集群客户端，将获取到的算力信息和所述健康状态信息发送给所述分布式集群组网中的集群管理服务器，以使所述集群管理服务器基于接收到的至少一台业务服务器的算力信息和健康状态信息，确定需要处理目标业务任务对应的多个子业务任务的业务服务器，并将每个子业务任务分发给对应的业务服务器进行处理。The processing unit 32 is configured to send the obtained computing power information and the health status information to the cluster management server in the distributed cluster network through the cluster client in the business server, so that the Based on the received computing power information and health status information of at least one business server, the cluster management server determines the business server that needs to process multiple sub-business tasks corresponding to the target business task, and distributes each sub-business task to the corresponding business server for processing. deal with.

优选地，所述预设条件为该台业务服务器初始上电、到达设定周期或者通过所述集群客户端接收到所述集群管理服务器发送的用于查询该台业务服务器的算力信息和健康状态信息的查询请求。Preferably, the preset condition is that the business server is initially powered on, reaches a set period, or receives the computing power information and health of the business server from the cluster management server through the cluster client. Query request for status information.

优选地，所述健康状态信息包括该台业务服务器运行的各个指定软件的健康状态和该业务服务器中的各个指定硬件的健康状态；Preferably, the health status information includes the health status of each designated software running on the business server and the health status of each designated hardware in the business server;

所述获取单元31，具体用于通过以下方式获取该业务服务器中的各个指定硬件的健康状态：The acquisition unit 31 is specifically configured to acquire the health status of each designated hardware in the service server in the following manner:

获取所述各个指定硬件的运行参数；Obtaining the operating parameters of each designated hardware;

将获取到的运行参数发送给该台业务服务器中的基板管理控制器BMC；Send the obtained operating parameters to the baseboard management controller BMC in the service server;

接收所述BMC发送的所述各个指定硬件的健康状态，其中，所述指定硬件的健康状态为所述BMC基于获取到的运行参数确定出的。receiving the health status of each designated hardware sent by the BMC, wherein the health status of the designated hardware is determined by the BMC based on the acquired operating parameters.

优选地，所述装置还包括：Preferably, the device also includes:

控制单元(图3中未示出)，用于在监测到所述集群客户端的工作状态为空闲状态时，控制该台业务服务器进入节能模式。A control unit (not shown in FIG. 3 ) is configured to control the service server to enter an energy-saving mode when it detects that the working state of the cluster client is idle.

优选地，所述处理单元，还用于：Preferably, the processing unit is also used for:

在接收到管理员输入的设备维护指令时，通过所述集群客户端将所述设备维护指令发送给所述集群管理服务器，以使所述集群管理服务器在所述设备维护指令所指示的维护时间段内不向该台业务服务器分发子业务。When receiving the device maintenance instruction input by the administrator, the cluster client sends the device maintenance instruction to the cluster management server, so that the cluster management server will perform maintenance at the maintenance time indicated by the device maintenance instruction. Sub-services are not distributed to this service server within the segment.

由以上技术方案可以看出，在本申请实施例中，分布式集群组网中的各台业务服务器中的操作系统管理模块在自己满足预设条件的情形下，会获取自己所属的业务服务器的算力信息和健康状态信息；然后通过自己所属的业务服务器中的集群客户端，将获取到的算力信息和健康状态信息发送给分布式集群组网中的集群管理服务器，以便于集群管理服务器可以基于这些算力信息和健康状态信息，确定需要处理目标业务任务对应的多个子业务任务的业务服务器，并将每个子业务任务分发给对应的业务服务器进行处理。这样一来，集群管理服务器可以基于这些业务服务器的处理能力合理地分发子业务任务，使得相应的业务服务器可以快速处理分发的子业务任务，从而缩短目标业务任务的总处理时长，进而提高了用户体验。It can be seen from the above technical solutions that in the embodiment of the present application, the operating system management module in each business server in the distributed cluster network will obtain the business server to which it belongs if it satisfies the preset conditions. The computing power information and health status information; and then through the cluster client in the business server to which it belongs, the obtained computing power information and health status information are sent to the cluster management server in the distributed cluster network, so that the cluster Based on these computing power information and health status information, the management server can determine the service servers that need to process multiple sub-service tasks corresponding to the target service task, and distribute each sub-service task to the corresponding service server for processing. In this way, the cluster management server can reasonably distribute sub-business tasks based on the processing capabilities of these business servers, so that the corresponding business servers can quickly process the distributed sub-business tasks, thereby shortening the total processing time of the target business tasks and improving the user experience. experience.

以上所述仅为本申请的较佳实施例而已，并不用以限制本申请，凡在本申请的精神和原则之内，所做的任何修改、等同替换、改进等，均应包含在本申请保护的范围之内。The above is only a preferred embodiment of the application, and is not intended to limit the application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the application should be included in the application. within the scope of protection.