CN114450669A

CN114450669A - Data processing method, device, system and storage medium

Info

Publication number: CN114450669A
Application number: CN201980100724.4A
Authority: CN
Inventors: 王加龙; 张云; 李栈; 任志星; 宋军
Original assignee: Alibaba Group Holding Ltd
Current assignee: Alibaba Group Holding Ltd
Priority date: 2019-11-20
Filing date: 2019-11-20
Publication date: 2022-05-06
Also published as: WO2021097714A1

Abstract

The embodiment of the application provides a data processing method, equipment, a system and a storage medium. In the embodiment of the application, for a hierarchical resource system, based on a resource aggregation relationship among multiple layers of resource subsystems in the resource system, monitoring data of the multiple layers of resource subsystems are aggregated to obtain state representation values of the multiple layers of resource subsystems, and hierarchical logic is arranged among the state representation values of the multiple layers of resource subsystems, so that an operator can be helped to quickly and accurately monitor the state of the resource system, and the difficulty of state monitoring is reduced.

Description

Data processing method, device, system and storage medium

Technical Field

The present application relates to the field of data processing technologies, and in particular, to a data processing method, device, system, and storage medium.

Background

A data center is a large and very complex system that includes many different types of equipment, such as servers, cabinets, refrigeration equipment, power equipment, and the like. Each device has a number of monitored data, such as data relating to temperature, power, performance, etc. The whole data center can have thousands of monitoring data or even more, and in the face of a large amount of monitoring data, operators can hardly perceive monitoring items, and the monitoring requirements of the data center cannot be met.

Disclosure of Invention

Aspects of the present application provide a data processing method, device, system, and storage medium, which are used to quickly and accurately monitor the state of a resource system, and reduce the difficulty of state monitoring.

The embodiment of the application provides a data processing method, which is suitable for computing equipment, and comprises the following steps: acquiring monitoring data of a multi-layer resource subsystem existing in a resource system, wherein a resource aggregation relation exists between the multi-layer resource system; aggregating the state representation values of the multilayer resource subsystems according to the monitoring data of the multilayer resource subsystems and the resource aggregation relation between the multilayer resource subsystems; and monitoring the state of the resource system according to the state characterization value of the multilayer resource subsystem.

An embodiment of the present application further provides a data processing method, which is applicable to a computing device, and the method includes: acquiring monitoring data of a target resource subsystem, wherein the target resource subsystem is one of multilayer resource subsystems in a resource system, and the multilayer resource subsystems have a resource aggregation relation; combining the resource aggregation relation between the target resource subsystem and other resource subsystems, and aggregating the state representation value of the target resource subsystem according to the monitoring data of the target resource subsystem; and outputting the state representation value of the target resource subsystem for state monitoring of the target resource subsystem.

The embodiment of the present application further provides a data processing method, which is applicable to a computing device, and the method includes: acquiring monitoring data of each resource subsystem on a target layer, wherein the target layer is one of a plurality of resource layers corresponding to a plurality of layers of resource subsystems in a resource system, and resource aggregation relations exist among the plurality of layers of resource subsystems; combining the resource aggregation relation between each resource subsystem on the target layer and other resource subsystems, and aggregating the state representation values of each resource subsystem on the target layer according to the monitoring data of each resource subsystem on the target layer; and outputting the state representation values of all the resource subsystems on the target layer for carrying out state monitoring on the target layer.

An embodiment of the present application further provides a data processing system, including: a computing device and a resource system; a multi-layer resource subsystem exists in the resource system, and a resource aggregation relation exists among the multi-layer resource system; the computing device is used for acquiring monitoring data of the multilayer resource subsystem; aggregating the state representation values of the multilayer resource subsystems according to the monitoring data of the multilayer resource subsystems and the resource aggregation relation between the multilayer resource subsystems; and monitoring the state of the resource system according to the state characterization value of the multilayer resource subsystem.

An embodiment of the present application further provides a resource system, including: the system comprises a plurality of layers of resource subsystems, wherein a resource aggregation relation exists between the plurality of layers of resource subsystems; wherein there is a first resource subsystem comprising a computing device or module among the multi-tier resource subsystems; the computing device or module to: acquiring monitoring data of the first resource subsystem; combining the resource aggregation relation between the first resource subsystem and other resource subsystems, and aggregating the state representation value of the first resource subsystem according to the monitoring data of the first resource subsystem; and outputting the state representation value of the first resource subsystem for state monitoring of the first resource subsystem.

An embodiment of the present application further provides a resource system, including: the resource aggregation method comprises the following steps that multiple layers of resource subsystems exist, and a resource aggregation relation exists among the multiple layers of resource subsystems; wherein a first resource layer containing computing equipment or modules exists in a plurality of resource layers corresponding to the multi-layer resource subsystem; the computing device or module to: acquiring monitoring data of each resource subsystem on the first resource layer, and aggregating state representation values of each resource subsystem on the first resource layer according to the monitoring data of each resource subsystem on the first resource layer by combining resource aggregation relations between each resource subsystem on the first resource layer and other resource subsystems; and outputting the state representation values of the resource subsystems on the first resource layer to monitor the state of the first resource layer.

An embodiment of the present application further provides a computing device, including: a memory and a processor; the memory for storing a computer program; the processor, coupled with the memory, to execute the computer program to: acquiring monitoring data of a multi-layer resource subsystem existing in a resource system, wherein a resource aggregation relation exists between the multi-layer resource system; aggregating the state representation values of the multilayer resource subsystems according to the monitoring data of the multilayer resource subsystems and the resource aggregation relation between the multilayer resource subsystems; and monitoring the state of the resource system according to the state characterization value of the multilayer resource subsystem.

An embodiment of the present application further provides a computing device, including: a memory and a processor; the memory for storing a computer program; the processor, coupled with the memory, to execute the computer program to: acquiring monitoring data of a target resource subsystem to which the computing equipment belongs, wherein the target resource subsystem is one of multilayer resource subsystems existing in a resource system, and the multilayer resource subsystems are in a resource aggregation relation; combining the resource aggregation relation between the target resource subsystem and other resource subsystems, and aggregating the state representation value of the target resource subsystem according to the monitoring data of the target resource subsystem; and outputting the state representation value of the target resource subsystem for state monitoring of the target resource subsystem.

An embodiment of the present application further provides a computing device, including: a memory and a processor; the memory for storing a computer program; the processor, coupled with the memory, to execute the computer program to: acquiring monitoring data of each resource subsystem on a target layer of the computing equipment, wherein the target layer is one of a plurality of resource layers corresponding to a plurality of layers of resource subsystems in the resource system, and the plurality of layers of resource subsystems have a resource aggregation relation; combining the resource aggregation relation between each resource subsystem on the target layer and other resource subsystems, and aggregating the state representation values of each resource subsystem on the target layer according to the monitoring data of each resource subsystem on the target layer; and outputting the state representation values of all the resource subsystems on the target layer for carrying out state monitoring on the target layer.

Embodiments of the present application also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to implement the steps in the method embodiments of the present application.

The embodiment of the application also provides a data processing method, which is suitable for a data center system, wherein the data center system sequentially comprises at least two layers of a server resource layer, a cabinet resource layer, a cold and hot channel resource layer, an inter-package resource layer and a machine room resource layer from bottom to top; the method comprises the following steps: according to monitoring data on each resource layer, sequentially aggregating state representation values of resources on at least two layers of a server resource layer, a cabinet resource layer, a cold and hot channel resource layer, an inter-bundle resource layer and a machine room resource layer from bottom to top; and displaying resource state representation values on at least two layers of a server resource layer, a cabinet resource layer, a cold-hot channel resource layer, an inter-package resource layer and a machine room resource layer according to a bottom-to-top aggregation relation so as to enable a user to locate a fault reason when the data center system has a fault.

In the embodiment of the application, for a hierarchical resource system, based on a resource aggregation relationship among multiple layers of resource subsystems in the resource system, monitoring data of the multiple layers of resource subsystems are aggregated to obtain state representation values of the multiple layers of resource subsystems, and hierarchical logic is arranged among the state representation values of the multiple layers of resource subsystems, so that an operator can be helped to quickly and accurately monitor the state of the resource system, and the difficulty of state monitoring is reduced.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:

FIG. 1a is a block diagram of a data processing system according to an exemplary embodiment of the present application;

FIG. 1b is a schematic diagram of a data processing system applied to a data center according to an exemplary embodiment of the present application;

FIG. 1c is a schematic flow chart of a hierarchical aggregation provided by an exemplary embodiment of the present application;

fig. 2 is a schematic flow chart of a data processing method according to an exemplary embodiment of the present application;

FIG. 3a is a schematic structural diagram of a resource system according to an exemplary embodiment of the present application;

FIG. 3b is a schematic flow chart diagram of another data processing method provided in an exemplary embodiment of the present application;

FIG. 3c is a schematic diagram of another resource system according to an exemplary embodiment of the present application;

FIG. 3d is a schematic flow chart diagram illustrating yet another data processing method according to an exemplary embodiment of the present application;

fig. 3e is a schematic flowchart of another data processing method provided in an exemplary embodiment of the present application;

FIG. 4a is a schematic structural diagram of a computing device according to an exemplary embodiment of the present application;

FIG. 4b is a schematic block diagram of another computing device provided in an exemplary embodiment of the present application;

fig. 4c is a schematic structural diagram of another computing device according to an exemplary embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described in detail and completely with reference to the following specific embodiments of the present application and the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

The existing data center system faces the technical problems that an operator is difficult to perceive monitoring items and cannot meet the monitoring requirements of a data center. Aiming at the technical problems, in the embodiment of the application, for a layered resource system, the monitoring data of the multilayer resource subsystems are aggregated according to the resource aggregation relation among the multilayer resource subsystems in the resource system to obtain the state representation values of the multilayer resource subsystems, and the state representation values of the multilayer resource subsystems have a hierarchical logic, so that an operator can be helped to quickly and accurately monitor the state of the resource system, and the difficulty of state monitoring is reduced.

The technical solutions provided by the embodiments of the present application are described in detail below with reference to the accompanying drawings.

Fig. 1a is a schematic structural diagram of a data processing system according to an exemplary embodiment of the present application. As shown in fig. 1a, the data processing system comprises: a computing device 101 and a resource system 102.

In this embodiment, the implementation form of the resource system 102 is not limited, and the resource system may be any system structure having a certain physical resource, for example, a data center system, a computer room system, a cluster system, or some industrial systems. The physical resources in the resource system 102 mainly refer to some devices, chips, communication lines between devices, and the like. Of course, the physical resources included in different resource systems may be different, and this embodiment does not limit this. Taking an internet system such as a data center system, a machine room system or a cluster system as an example, physical resources in these systems include IT-type devices such as a computer, a server, a cabinet, a storage device, a router, a gateway, a switch, a printer, etc., refrigeration devices such as an air conditioning system, a water cooling system, etc., Power devices such as an Uninterruptible Power Supply (UPS), a High Voltage Direct Current (HVDC), a storage battery, etc., and communication lines between these devices, such as an optical fiber, a twisted pair, a coaxial cable, etc. In fig. 1a, circles, squares, diamonds, and ovals filled in black represent resource subsystems on different resource layers.

In this embodiment, the physical resources in the resource system 102 are layered to form a plurality of resource layers, and each resource layer includes at least one resource subsystem. The resource subsystems on a plurality of resource layers have inclusion relation on physical space, and the resource subsystems on the same resource layer have the same parallel relation. Each resource subsystem comprises at least one type of resource device or module, etc. The resource devices or modules in each resource subsystem may include computing devices or modules, may include storage devices or modules, may include devices or modules that do not have computing and storage capabilities, and so on.

In this embodiment, a resource aggregation relationship exists between resource subsystems on multiple resource layers, which is referred to as a resource aggregation relationship between multiple layers of resource subsystems. The resource aggregation relationship between the multi-layer resource subsystems can be from top to bottom or from bottom to top. In the embodiments of the present application, a bottom-up aggregation relationship is taken as an example for description. On the basis of the technical solution disclosed in the embodiments of the present application and described in the context of bottom-up aggregation, those skilled in the art can learn the implementation manner when the top-down aggregation is adopted without creative effort.

For the bottom-up aggregation approach, the resource aggregation relationship between the multi-layer resource subsystems can be understood as: the resource subsystem of the previous layer is aggregated by the resource subsystem of the next layer, in other words, for any resource subsystem on the non-lowest resource layer, the resource subsystems of the next layer can be aggregated. In the embodiments of the present application, "a plurality" indicates that the number is not definite, and the number indicated may be one, or may be two or more. For the resource subsystem on the lowest resource layer, it can be considered as the smallest resource system among the resource systems, and is the basis for forming the resource subsystem on other resource layers. Each resource layer has its own hierarchy, the hierarchies of the resource layers can be from low to high according to a bottom-up aggregation mode, and resource subsystems on a high-level resource layer are aggregated by resource subsystems on a low-level resource layer.

It should be noted that, in different application scenarios, the resource layer may be divided differently. In some application scenarios, the resource subsystem on the highest resource layer may be the resource system 102 itself, but the highest resource layer is not aggregated to the dimension of the resource system 102 in all application scenarios, which may be determined by the partitioning of the resource layer.

Assuming that the resource system 102 is an Internet Data Center (IDC), the IDC may include seven resource layers, in order from bottom to top, a first resource layer with a server as a resource subsystem, a second resource layer with a cabinet as a resource subsystem, a third resource layer with a machine column as a resource subsystem, a fourth resource layer with a hot and cold aisle as a resource subsystem, a fifth resource layer with a bay as a resource subsystem, a sixth resource layer with a machine room as a resource subsystem, and a seventh resource layer with the IDC as a resource subsystem. The server comprises a plurality of servers, a plurality of machine columns, a plurality of cold and hot channels, a plurality of rooms, a machine room and an IDC (Internet data center), wherein the servers can be aggregated into one machine cabinet, the machine cabinets are aggregated into one machine row, the machine rows are aggregated into one cold and hot channel, the cold and hot channels are aggregated into one bay, the bays are aggregated into one machine room, and the machine rooms are aggregated into one IDC. In this example, the highest resource layer is the seventh resource layer, and the resource subsystem on the seventh resource layer is the IDC, i.e., the resource system 102 itself.

In order to ensure the operational reliability and stability of the resource system 102, it is necessary to monitor the state of the resource system 102. The status monitoring may be the overall status of the resource system 102 or the status of a particular resource subsystem in the resource system 102. Monitoring the status of the resource system 102 relies on monitoring data in the resource system 102. There are many kinds of monitoring data related to state monitoring, such as monitoring data related to an ambient temperature, an internal temperature of a device, power consumption of the device, a Central Processing Unit (CPU) frequency, a CPU load, and a CPU performance.

In this embodiment, a computing device 101 is added to a resource system 102. The computing device 101 may use the resource subsystems as the granularity to distinguish the monitoring data in the resource system 102, and obtain the monitoring data of the multi-layer resource subsystems; furthermore, the state representation values of the multilayer resource subsystems can be aggregated according to the monitoring data of the multilayer resource subsystems and the resource aggregation relationship between the multilayer resource subsystems, and the state of the resource system 102 can be monitored according to the state representation values of the multilayer resource subsystems. Here, "monitoring the state of the resource system 102" includes: the overall status of the resource system 102 is monitored, and/or the status of particular resource subsystems in the resource system 102 is monitored.

Wherein the process of monitoring the status of the resource system 102 may be performed autonomously by the computing device. For example, the computing device 101 may monitor whether the resource system 102 fails, and when it is monitored that the resource system 102 fails, locate a failure cause of the resource system 102 according to the state characterization values of the multi-layer resource subsystems.

Alternatively, the process of monitoring the status of the resource system 102 may be performed by an operator of the resource system 102. In this case, to facilitate the operator's status monitoring of the resource system 102, the computing device 101 may present status indicators for the multi-tier resource subsystems to facilitate the relevant operator's status monitoring of the resource system 102 accordingly. For example, in the event of a failure of the resource system 102, an operator may quickly and conveniently locate the cause of the failure based on the state characterization values of the multi-tier resource subsystems.

Further optionally, the computing device 101 may present the state representation values of the multi-tier resource subsystems in terms of resource aggregation relationships between the multi-tier resource subsystems. The present embodiment does not limit the specific implementation of displaying the state representation values of the multi-layer resource subsystem. Optionally, between different resource layers, the state representation values of the resource subsystems of different layers may be displayed in a differentiated manner. For example, the status indicator values of different layers of resource subsystems may be shown in different colors, such as green for a first layer of resource subsystems, red for a second layer of resource subsystems, and so on. As another example, different graphics or patterns may be used to represent the status characterizing values of different layers of resource subsystems, such as a circle representing the status characterizing value of a first layer of resource subsystems, a square representing the status characterizing value of a second layer of resource subsystems, and so on. Optionally, for the same resource layer, the state representation values of different resource subsystems in the resource layer may be displayed in a differentiated manner. Optionally, for the same resource layer, the abnormal state characterization value in the resource layer and the identification information of the resource subsystem corresponding to the abnormal state characterization value may be highlighted. The abnormal state characteristic value may be a maximum, minimum or out-of-range state characteristic value.

In this embodiment, the device form of the computing device 101 is not limited, and any computing device with certain computing capability may be used, for example, a terminal device such as a smart phone, a tablet computer, a personal computer, an Internet of Things (IOT) device, and the like, or a server device such as a conventional server, a cloud host, a virtual center, or a server array, and the like.

In this embodiment, the resource subsystems are used as the granularity, the resource aggregation relationship among the multilayer resource subsystems is used as the basis, the monitoring data of the multilayer resource subsystems are respectively aggregated into the state representation values, and based on the state representation values of the multilayer resource subsystems and the hierarchical logic between the state representation values, no matter the operator of the resource system or the monitoring system corresponding to the resource system, the state monitoring of the resource subsystems and the resource system can be intuitively, conveniently, quickly and accurately performed, so that the difficulty of state monitoring is reduced.

In addition, by combining the hierarchical logic between the state representation values of the multilayer resource subsystems, an operator can clearly know the state of each resource subsystem on the same resource layer, and can perform deep analysis and exploration downwards according to the hierarchical logic according to monitoring requirements, so that the monitoring requirements are greatly met.

It is noted that in the above or below embodiments of the present application, the resource system 102 may be monitored for status at any time or during any period of time. For example, the status of the resource system 102 at a historical time may be monitored, the status of the resource system 102 at the current time may be monitored, the status of the resource system 102 at a historical time may be monitored, or the status of the resource system 102 at the current time may be monitored. The "state" herein may include the overall state of the resource system 102, or may include the state of a particular resource subsystem in the resource system 102.

If the state of the resource system 102 at a certain historical time is monitored, the computing device 101 may obtain monitoring data of the multilayer resource subsystems in the resource system 102 at the historical time, and aggregate state characterization values of the multilayer resource subsystems at the historical time according to the monitoring data of the multilayer resource subsystems at the historical time and a resource aggregation relationship among the multilayer resource subsystems; and monitoring the state of the resource system 102 at the historical moment according to the state representation value of the multi-layer resource subsystem at the historical moment.

If the state of the resource system 102 at the current time is monitored, the computing device 101 may obtain the monitoring data of the multilayer resource subsystem in the resource system 102 at the current time, and aggregate a state characterization value of the multilayer resource subsystem at the current time according to the monitoring data of the multilayer resource subsystem at the current time and a resource aggregation relationship between the multilayer resource subsystems; and monitoring the state of the resource system 102 at the current moment according to the state representation value of the multilayer resource subsystem at the current moment.

Optionally, as shown in fig. 1a, the data processing system of this embodiment further includes a database 103, where the database 103 corresponds to the resource system 102, and may store monitoring data of multiple layers of resource subsystems in the resource system 102 at each time. Based on this, the computing device 101 may obtain monitoring data of the multi-tier resource subsystem at historical or current times from the database 103.

It should be noted that, for the condition of monitoring the state of the resource system 102 at the current time, the computing device 101 may also directly collect the monitoring data of the multi-layer resource subsystem at the current time from the resource system 102, and a specific collection manner is not limited.

In some embodiments of the present application, when an operator wishes to perform state monitoring on the resource system 102, monitoring requirement description information may be submitted to the computing device 101. Based on this, the computing device 101 may obtain, from the database, the monitoring data of the multi-layer resource subsystem existing in the resource system 102 according to the monitoring requirement description information; aggregating state representation values of the multilayer resource subsystems according to the monitoring data of the multilayer resource subsystems and the resource aggregation relation among the multilayer resource subsystems; and monitoring the state of the resource system 102 according to the state representation value of the multi-layer resource subsystem.

In alternative 1, the monitoring demand description information includes a specific time, and the specific time indicates which time the resource system 102 needs to be monitored for the status. The specified time may be the current time or a certain historical time. Based on this, the computing device 101 may obtain, from the database, the monitoring data generated by the multi-layer resource subsystem at the specified time according to the specified time in the monitoring requirement description information; aggregating state representation values of the multilayer resource subsystems at the designated time according to monitoring data generated by the multilayer resource subsystems at the designated time and a resource aggregation relation among the multilayer resource subsystems; and monitoring the state of the resource system 102 at the specified time according to the state representation value of the multi-layer resource subsystem at the specified time.

In alternative 2, the monitoring demand description information includes a specific data category in addition to the specific time. The specified data category represents a category of monitoring data required for performing status monitoring on the resource system 102, and may include, for example, a frequency of the CPU and a load of the CPU, or an internal temperature and power consumption, or may also include the frequency of the CPU, the load of the CPU, the internal temperature and the power consumption, and so on. Based on this, the computing device 101 may obtain, from the database, the monitoring data belonging to the specified data category generated by the multi-layer resource subsystem at the specified time according to the specified time and the specified data category in the monitoring requirement description information; aggregating state representation values of the multilayer resource subsystems at the appointed time according to the monitoring data which are generated by the multilayer resource subsystems at the appointed time and belong to the appointed data category and the resource aggregation relation among the multilayer resource subsystems; and monitoring the state of the resource system 102 at the specified time according to the state representation value of the multi-layer resource subsystem at the specified time.

In alternative 3, the monitoring demand description information may include a specific resource hierarchy in addition to a specific time and a specific data category. The designated resource hierarchy is used to define which resource levels need to be used in the process of monitoring the state of the resource system 102, i.e., the resource level that needs the identification of the designated resource hierarchy and other resource levels with a hierarchy lower than the designated resource hierarchy. Taking the example where the resource system 102 includes four resource layers, the corresponding levels of the four resource layers are 1-4, assuming that the specified resource level is 3, this means that resource layers 1,2 and 3 need to be used in the status monitoring process. Based on this, the computing device 101 may obtain monitoring data belonging to a specified data category generated by each resource subsystem on the resource layers 1-3 at a specified time; aggregating state representation values of the resource subsystems on the resource layers 1-3 at the appointed time according to monitoring data which are generated by the resource subsystems on the resource layers 1-3 at the appointed time and belong to the appointed data category and the resource aggregation relation among the resource subsystems on the resource layers 1-3; and monitoring the state of the resource system 102 at the specified time according to the state representation values of the resource subsystems at the specified time on the resource layers 1-3.

As can be seen from option 3, the multi-layer resource subsystems used in the process of monitoring the state of the resource system 102 may be resource subsystems on all resource layers in the resource system 102, or may also be resource subsystems on some resource layers, and may be flexibly set according to monitoring requirements.

It should be noted that, in the above alternative 2, only the specified data category may be included, and the specified time is not included. Similarly, in the above alternative 3, only the specified resource hierarchy may be included, and the specified time and the specified data category are not included; alternatively, a specified resource level and a specified time may be included, without including a specified data category, and so on. According to the actual monitoring requirement, various condition information can be carried in the monitoring requirement description information, and the embodiment of the application is not limited. The condition information listed in the above alternatives 1 to 3 is only an example and does not limit the scope of protection of the present application.

In the embodiment of the present application, a manner in which an operator submits monitoring requirement description information to the computing device 101 is not limited, and may specifically be determined according to a human-computer interaction manner supported by the computing device 101.

For example, if the computing device 101 supports voice interaction, the operator may provide the monitoring requirement description information to the computing device 101 in a voice manner.

For another example, if the computing device 101 has an electronic screen and provides a human-computer interaction interface to an operator, the operator may provide the monitoring requirement description information to the computing device 101 through the human-computer interaction interface. The human-machine interface provided by the computing device 101 may be a command window, and the operator may provide the monitoring requirement description information to the computing device 101 through an interaction command supported by the command window. Or the human-machine interaction interface provided by the computing device 101 is a web page or an application page, and the operator may provide the monitoring requirement description information to the computing device 101 through controls such as information items or input boxes on the web page or the application page.

For another example, if the computing device 101 supports remote communication, the operator may send the monitoring requirement description information to the computing device 101 through a terminal device such as a mobile phone or a personal computer. For example, the monitoring requirement description information may be sent to the computing device 101 by a terminal device such as a mobile phone or a personal computer in a manner of mail, short message, or application message.

In the foregoing or following embodiments of the present application, in the process of aggregating the state characterizing values of the multi-layer resource subsystems according to the resource aggregation relationship between the monitoring data of the multi-layer resource subsystems and the multi-layer resource subsystems, the computing device 101 may aggregate the state characterizing values of the resource subsystems of each layer according to the resource aggregation relationship between the monitoring data of the multi-layer resource subsystems and the multi-layer resource subsystems, in a bottom-to-top order of the resource layers. The multi-layer resource subsystem refers to a plurality of resource subsystems on a plurality of resource layers, and the number of the resource subsystems is multiple. Each layer of resource subsystem refers to a resource subsystem on each resource layer, and the number of resource subsystems can be one or more. In this embodiment, the resource aggregation relationship between the multi-tier resource subsystems is bottom-up.

For the computing device 101, the state representation values of each layer of resource subsystems (i.e., the resource subsystems on each resource layer) may be sequentially aggregated according to the resource aggregation relationship among the multiple layers of resource subsystems and the order of the resource layers from bottom to top. In this aggregation process, the computing device 101 needs to aggregate the state token values of each resource subsystem in the multi-layer resource subsystem, and the aggregation process of the state token values is the same or similar for each resource subsystem. The aggregation process of the state token value is described below by taking the first resource subsystem as an example. The first resource subsystem is any one of the multi-tier resource subsystems.

For the first resource subsystem, it may be determined whether the resource layer to which it belongs is the lowest resource layer in the resource system 102; if yes, it means that the first resource subsystem is the smallest resource subsystem in the resource system 102, and the state representation value of the first resource subsystem can be aggregated directly according to the monitoring data of the first resource subsystem; if not, the first resource subsystem is aggregated by the next resource subsystem, the state of the first resource subsystem is related to the state of the next resource subsystem, and the state of the first resource subsystem is affected by the state of the next resource subsystem, so that the state representation value of the first resource subsystem can be aggregated by combining the monitoring data of the first resource subsystem and the state representation value of the next resource subsystem having a resource aggregation relation with the first resource subsystem. The resource aggregation relation between the first resource subsystem and the next resource subsystem may be one or more. In addition, the aggregation process of the state characteristic value of the next layer resource subsystem having the resource aggregation relation with the first resource subsystem is the same as the aggregation process of the state characteristic value of the first resource subsystem, and is obtained by aggregation before the first resource subsystem.

In an alternative embodiment, an aggregation process consists essentially of: two operations of dimensionless processing and aggregation operation are not limited to this. The dimensionless processing is a data preprocessing mode, the monitoring data and the state representation value can be standardized through the dimensionless processing, the problem that units, formats, names and the like of the monitoring data and the state representation value are not uniform is solved, and convenience is provided for subsequent aggregation operation. The aggregation operation refers to a process of quantizing the data after the dimensionless processing into a state representation value by adopting a certain algebraic operation.

The process of aggregating the state characterizing value of the first resource subsystem according to the monitoring data of the first resource subsystem includes: carrying out dimensionless processing on the monitoring data of the first resource subsystem; and carrying out aggregation operation on the monitoring data subjected to dimensionless processing to obtain a state representation value of the first resource subsystem.

Accordingly, an optional implementation of the above aggregating the state representation value of the first resource subsystem according to the monitoring data of the first resource subsystem and the state representation value of the next resource subsystem having a resource aggregation relationship with the first resource subsystem includes: carrying out dimensionless processing on the monitoring data of the first resource subsystem and the state representation value of the next layer resource subsystem having a resource aggregation relation with the first resource subsystem; and carrying out aggregation operation on the monitoring data subjected to dimensionless processing and the state characteristic value to obtain the state characteristic value of the first resource subsystem.

In addition to the foregoing embodiments, according to the monitoring data of the first resource subsystem and the state characterizing value of the next resource subsystem having a resource aggregation relationship with the first resource subsystem, the following embodiments may be further adopted to aggregate the state characterizing value of the first resource subsystem: carrying out dimensionless processing on the monitoring data of the first resource subsystem; performing aggregation operation on the dimensionless processed monitoring data to obtain a resource state intermediate value of the first resource subsystem; and correcting the resource state intermediate value of the first resource subsystem according to the state representation value of the next resource subsystem having a resource aggregation relation with the first resource subsystem to obtain the state representation value of the first resource subsystem.

In the present embodiment, the correction method is not limited. For example, the state representation value of the first resource subsystem may be obtained by weighting the resource state intermediate value of the first resource subsystem by using the state representation value of the next resource subsystem having a resource aggregation relationship with the first resource subsystem. For another example, an average value of state characterizing values of the next-layer resource subsystems having a resource aggregation relationship with the first resource subsystem may be calculated, and if the average value is greater than a set threshold, the resource state intermediate value of the first resource subsystem is increased by a specified step value to obtain the state characterizing value of the first resource subsystem; if the average value is smaller than or equal to the set threshold value, reducing the resource state intermediate value of the first resource subsystem by a specified step value to obtain a state representation value of the first resource subsystem. The manner of increasing the resource state intermediate value by the designated step value when the average value is greater than the set threshold value and decreasing the resource state intermediate value by the designated step value when the average value is less than or equal to the set threshold value is merely exemplary, and different implementations are possible in different scenarios. For example, in some scenarios, the resource state median may be decreased by a specified step value when the mean is greater than a set threshold, and increased by a specified step value when the mean is less than or equal to the set threshold.

In the two optional embodiments, the different usage manners of the "state representation value of the next layer resource subsystem having a resource aggregation relationship with the first resource subsystem" are both exemplary descriptions.

In the above or below embodiments of the present application, the dimensionless processing manner is not limited, and flexible processing may be performed according to an application scenario. For example, some monitoring data with non-uniform names can be unified into internal names supported by the aggregation operation. For the monitoring data with uneven numerical value ranges, normalization processing can be carried out on the monitoring data in a normalization mode. Similarly, in the above or below embodiments of the present application, the use of an algebraic algorithm in the aggregation operation is not limited.

In the foregoing embodiment or the following embodiment of the present application, after the state characterizing value of the multilayer resource subsystem is obtained, the state of the resource system may be monitored according to the state characterizing value of the multilayer resource subsystem. The monitoring of the state of the resource system includes, but is not limited to, the following modes:

in an alternative embodiment, the overall state of the resource system may be monitored based on the state characterizing values of the multi-tier resource subsystems.

In an alternative embodiment, the status of a particular resource subsystem in the resource system may be monitored based on the status characterizing values of the multi-tier resource subsystems.

In yet another alternative embodiment, the overall state of the resource system and the state of a particular resource subsystem in the resource system may be monitored simultaneously based on the state characterization values of the multiple layers of resource subsystems.

In different application scenarios, the physical meanings represented by the state representation values are different, and the states of the resource systems or resource subsystems corresponding to the state representation values are also different. For example, in some scenarios, the state characterization value represents power consumption, and then the state of the resource system or resource subsystem refers to the power consumption situation of the resource system or resource subsystem. In other scenarios, the state characterization value represents a CPU load, and the state of the resource system or the resource subsystem refers to a load condition of the resource system or the resource subsystem. In still other scenarios, the state characterization value represents performance, and the state of the resource system or resource subsystem refers to the performance condition of the resource system or resource subsystem. Different application scenarios, the manner of monitoring the overall state of the resource system or the state of a specific resource subsystem in the resource system may be different according to the state characterization values of the multi-layer resource subsystems, and several exemplary embodiments are given below, but are not limited thereto.

In an alternative embodiment, the mapping relationship between the overall state and the token value of the resource system may be predefined. Based on this, one embodiment of monitoring the overall state of the resource system based on the state characterizing values of the multi-tier resource subsystems includes: weighting and summing the state representation values of the multilayer resource subsystems to obtain an overall state representation value; and inquiring the mapping relation between the preset integral state and the representation value according to the integral state representation value to obtain the integral state of the resource system. Further, if the overall state of the resource system is not good, more attention can be paid to the resource system, and the resource system can be subjected to troubleshooting, upgrading or improving and the like.

In an optional embodiment, in a scenario of monitoring the state of a specific resource subsystem in a resource system, monitoring may be performed layer by layer in a top-down order of resource layers; if the state of the resource subsystem of the upper layer is healthy, which means that the state of the resource subsystem of the lower layer is also healthy, the monitoring process can be ended; and only when the resource subsystem with the abnormal or suspicious state is found, continuing to monitor the state of the next layer of resource subsystems which are aggregated to the resource subsystem with the abnormal or suspicious state. Based on the above, in the process of monitoring the state of a specific resource subsystem in the resource system according to the state representation value of the multilayer resource subsystem, whether the resource subsystem in the highest resource layer has abnormal state or suspicious resource subsystems to be monitored exists or not can be monitored according to the state representation value of the resource subsystem in the highest resource layer in the multilayer resource subsystem; if the resource subsystem exists, monitoring whether the abnormal or suspicious resource subsystem exists in the next layer resource subsystem having the resource aggregation relation with the resource subsystem to be monitored according to the state representation value of the next layer resource subsystem having the resource aggregation relation with the resource subsystem to be monitored until the abnormal or suspicious resource subsystem does not exist or all resource subsystems are monitored.

For convenience of description, whether a resource subsystem with abnormal or suspicious state is searched in a resource subsystem at the highest resource layer or a resource subsystem with abnormal or suspicious state is continuously searched in a resource subsystem at the next layer having a resource aggregation relationship with the resource subsystem to be monitored, is collectively referred to as searching the resource subsystem with abnormal or suspicious state in the resource subsystem set. The resource subsystems in the set of resource subsystems may differ in different situations.

The method for searching for the resource subsystem with abnormal or suspicious state in the resource subsystem set can adopt, but is not limited to, the following modes:

mode 1: comparing the state representation value of each resource subsystem in the resource subsystem set with a set threshold value; and regarding the resource subsystems with the state characteristic values smaller than the threshold value as the resource subsystems with abnormal or suspicious states. Of course, according to different scenarios, the resource subsystem with the state representation value greater than the threshold may also be regarded as a resource subsystem with abnormal or suspicious state.

For example, in an application scenario, taking a resource subsystem in the resource subsystem set as a server and needing to monitor power consumption of the server as an example, a state representation value of the server represents a size of the power consumption of the server; if the state representation value is larger than the power consumption threshold value, the power consumption of the server is over high; if the state characterising value is less than the power consumption threshold, it means that the power consumption of the server is within a normal range. In this example, a server with a state characterising value greater than a power consumption threshold belongs to a server with an abnormal state.

Mode 2: comparing the state representation value of each resource subsystem in the resource subsystem set with a set threshold range; resource subsystems whose state characterizing values are not within the threshold range are considered to be resource subsystems whose state is abnormal or suspect. Of course, according to different scenarios, the resource subsystems with the state representation values within the threshold range may also be regarded as resource subsystems with abnormal or suspicious states.

For example, in an application scenario, taking a resource subsystem in a resource subsystem set as a machine room and needing to monitor an ambient temperature in the machine room as an example, a state representation value of the machine room represents a magnitude of the ambient temperature in the machine room, and a threshold range represents a normal temperature range; if the state representation value is not in the threshold range, the environment temperature in the machine room is over-high or over-low; if the state characterizing value is within the threshold value range, the ambient temperature in the machine room is within the normal temperature range. In this example, a machine room whose state characterizing value is not within the threshold range belongs to a machine room whose state is abnormal.

Mode 3: comparing the state representation values of all resource subsystems in the resource subsystem set; and if the difference value between the maximum state characteristic value and the minimum state characteristic value is larger than the set difference value threshold value, the resource subsystem corresponding to the minimum state characteristic value is regarded as a resource subsystem with abnormal or suspicious state. Of course, according to different scenarios, the resource subsystem corresponding to the maximum state characterization value may also be regarded as a resource subsystem with abnormal or suspicious state.

Mode 4: and calculating the average value of the state characteristic values of all the resource subsystems in the resource subsystem set, and regarding the resource subsystems with the state characteristic values lower than the average value as the resource subsystems with abnormal or suspicious states. Of course, according to different scenarios, the resource subsystem with the state representation value greater than the mean value may also be regarded as a resource subsystem with abnormal or suspicious state.

In the embodiment of the application, monitoring data of the multi-layer resource subsystems are aggregated for the layered resource systems based on a resource aggregation relation among the multi-layer resource subsystems in the resource systems, so as to obtain state representation values of the multi-layer resource subsystems. The monitoring data is quantized into state representation values, and operators or a monitoring system can intuitively and conveniently judge which resource subsystems are abnormal or suspicious in state; from the perspective of the resource layer, the states and state differences of the resource subsystems on the resource layer can be clearly known; according to the hierarchical logic between the state representation values of the multilayer resource subsystems, the state abnormity or the reason of the suspicious resource subsystem abnormity can be conveniently and definitely searched downwards, the state monitoring of the resource system can be rapidly and accurately carried out, and the difficulty of the state monitoring is reduced.

The data processing system shown in fig. 1a may be applied to different resource systems, for example, may be applied to a data center system, or a computer room system, or a cluster system. Taking the application of the data processing system shown in fig. 1a in a data center as an example, a structure of a data processing system applied to a data center is shown in fig. 1b, and includes: a computing device 11 and an IDC system 12. The IDC system 12 may have various implementations, which are not limited thereto. As shown in fig. 1b, the IDC system 12 comprises: the system comprises a plurality of machine rooms, wherein each machine room comprises a plurality of bunkers, each bunker comprises a plurality of hot and cold channels, each hot channel comprises a plurality of machine columns, each machine column comprises a plurality of cabinets, and each cabinet comprises a plurality of servers. The IDC system 12 shown in fig. 1b is an example only; similarly, in fig. 1b, the computing device 11 is illustrated as a desktop computer, but is not limited thereto.

In this embodiment, the physical resources in the IDC system 12 have a hierarchical characteristic, and are divided into 7 resource layers from bottom to top according to the resource aggregation direction, which are: a first resource layer comprising a plurality of server subsystems; the second resource layer comprises a plurality of cabinet subsystems; the third resource layer comprises a plurality of machine line subsystems, and the fourth resource layer comprises a plurality of cold and hot channel subsystems; a fifth resource layer comprising a plurality of inter-packet subsystems; the sixth resource layer comprises a plurality of machine room subsystems; and the seventh resource layer comprises a plurality of data center subsystems. In this embodiment, a server may be used as a server subsystem, but is not limited thereto. Several server subsystems on the same cabinet are aggregated into a cabinet subsystem; the machine cabinet subsystems in the same row are aggregated into a machine row subsystem, the machine row subsystems on the same cold and hot channel are aggregated into a cold and hot channel subsystem, a plurality of cold and hot channel subsystems in the same compartment are aggregated into a compartment subsystem, and a plurality of compartment subsystems in the same machine room are aggregated into a machine room subsystem; machine room subsystems in the same data center are aggregated into a data center subsystem.

As can be seen from the above analysis, the IDC system 12 shown in fig. 1b has many system levels, a complex structure, and a huge amount of monitoring data. If only the monitoring data of the macro level is seen, the problem of the local level is difficult to find in time, so that the untimely prevention is caused, and the fault is caused; if the monitoring data of each local hierarchy is observed, the data volume is huge and the difficulty is high. To solve these technical problems, in the present embodiment, the computing device 11 performs hierarchical aggregation on the monitoring data in the IDC system 12 according to a resource aggregation relationship between 4 resource layers. Wherein the process of the layer polymerization is shown in fig. 1 c.

Monitoring data XL1_1, XL1_2, …, XL1_ i, and XL1_ n1 of each server subsystem on the first resource layer are used as input, and monitoring data XL1_1, XL1_2, XL1_ n1 are aggregated to obtain a state representation value of each server subsystem. On one hand, the state representation values of all the server subsystems are output to a database; and on the other hand, the state representation values of the server subsystems are sent to the calculation of the second resource layer. XL1_ i represents monitoring data of the ith server subsystem in the first resource layer, L1 represents the first resource layer, and the value of i is 1,2,3, …, n1, and n1 are positive integers. The monitoring data of the server subsystem may include, but is not limited to: average temperature of the server, total power consumption, CPU frequency, CPU load, etc.

Monitoring data XL2_1, XL2_2, …, XL2_ i, and XL2_ n2 of each cabinet subsystem on the second resource layer and state representation values of each server subsystem are used as input, and the monitoring data XL2_1, XL2_2, XL2_ n2 and the state representation values of each server subsystem are aggregated to obtain the state representation values of each cabinet subsystem. On one hand, the state representation values of all the cabinet subsystems are output to a database; on one hand, the state representation values of all the cabinet subsystems are sent to the calculation of the third resource layer. Wherein, XL2_ i represents the monitoring data of the ith cabinet system in the second resource layer, L2 represents the second resource layer, and the value of i is 1,2,3, …, n2, and n2 is a positive integer. The monitoring data of the rack subsystem may include, but is not limited to: average temperature of the cabinet, total power consumption, etc.

Monitoring data XL3_1, XL3_2, …, XL3_ i, and XL3_ n3 of each machine train subsystem on the third resource layer and state representation values of each cabinet subsystem are used as input, and the monitoring data XL3_1, XL3_2, XL3_ n3 and the state representation values of each cabinet subsystem are aggregated to obtain the state representation values of each machine train subsystem. On one hand, the state representation values of all the train subsystems are output to a database; on one hand, the state representation values of all the machine train subsystems are sent to the calculation of the fourth resource layer. Wherein, XL3_ i represents the monitoring data of the ith train subsystem in the third resource layer, L3 represents the third resource layer, and the value of i is 1,2,3, …, n3, and n3 is a positive integer. The monitoring data of the train subsystem may include, but is not limited to: average temperature of the train, total power consumption, etc.

Monitoring data XL4_1, XL4_2, …, XL4_ i, and XL4_ n4 of each cold and hot channel subsystem on the fourth resource layer and state representation values of each machine train subsystem are used as input, and the monitoring data XL4_1, XL4_2, XL4_ n4 and the state representation values of each machine train subsystem are aggregated to obtain the state representation values of each cold and hot channel subsystem. On one hand, the state representation values of the cold and hot channel subsystems are output to a database; on one hand, the state representation values of the cold and hot channel subsystems are sent to the calculation of the fifth resource layer. Wherein, XL4_ i represents monitoring data of the ith cold-hot channel subsystem in the fourth resource layer, L4 represents the fourth resource layer, and the value of i is 1,2,3, …, n4, and n4 is a positive integer. The monitoring data of the cold-hot channel subsystem may include, but is not limited to: average temperature of cold and hot channels, total power consumption, etc.

Monitoring data XL5_1, XL5_2, …, XL5_ i, XL5_ n5 of each inter-subsystem on the fifth resource layer and state characterization values of each cold-hot channel subsystem are used as input, and the monitoring data XL5_1, XL5_2, XL5_ n5 and the state characterization values of each cold-hot channel subsystem are aggregated to obtain the state characterization values of each inter-subsystem. On one hand, the state representation values of the inter-packet subsystems are output to a database; on one hand, the state representation values of the inter-packet subsystems are sent to the calculation of the sixth resource layer. XL5 — i represents monitoring data of the ith inter-packet subsystem in the fifth resource layer, L5 represents the fifth resource layer, and the value of i is 1,2,3, …, n5, and n5 is a positive integer. The monitoring data of the inter-packet subsystem may include, but is not limited to: average temperature between packets, total power consumption, etc.

Monitoring data XL6_1, XL6_2, …, XL6_ i, and XL6_ n6 of each machine room subsystem on the sixth resource layer and state representation values of each inter-subsystem are used as input, and the monitoring data XL6_1, XL6_2, XL6_ n6 and the state representation values of each inter-subsystem are aggregated to obtain the state representation values of each machine room subsystem. On one hand, the state representation values of all machine room subsystems are output to a database; on one hand, the state representation values of all the machine room subsystems are sent to the calculation of the seventh resource layer. XL6_ i represents monitoring data of the ith computer room subsystem in the sixth resource layer, L6 represents the sixth resource layer, and the value of i is 1,2,3, …, n6, and n6 are positive integers. The monitoring data of the machine room subsystem may include, but is not limited to: average temperature of the machine room, total power consumption, etc.

Monitoring data XL7_1, XL7_2, …, XL7_ i, and XL7_ n7 of each IDC subsystem on a seventh resource layer and state representation values of each machine room subsystem are used as input, and the monitoring data XL7_1, XL7_2, XL7_ n7 and the state representation values of each machine room subsystem are aggregated to obtain the state representation values of each IDC subsystem. And on one hand, the state representation values of the IDC subsystems are output to the database. Wherein, XL7_ i represents the monitoring data of the ith IDC subsystem in the seventh resource layer, L7 represents the seventh resource layer, and the value of i is 1,2,3, …, n7, and n7 is a positive integer. It should be noted that in the system shown in fig. 1b, there is only one IDC subsystem, i.e., the IDC system 12, on the seventh resource level. The monitoring data of the IDC system 12 may include, but is not limited to: average temperature of IDC, total power consumption, etc.

To this end, the database stores state representation values of subsystems on 7 resource layers, and the state representation values have hierarchical logic therebetween, that is, hierarchical logic between the subsystems. Further, the status representation values of the subsystems on the 7 resource layers can be displayed on an electronic screen or a display as required. For example, the status representation values of the subsystems on the 7 resource layers can be displayed on an electronic screen or a display according to a display request of an operator, or the status representation values of the subsystems on the 7 resource layers can be automatically displayed on the electronic screen or the display for the operator to view.

It should be noted that, in the present embodiment, the IDC system 12 includes 7 resource layers for an example, but is not limited thereto. In practical applications, one or more resource layers may be skipped, for example, the resource layer without hot and cold channels may be directly aggregated into a compartment.

For the IDC system 12 including multiple layers of resource subsystems, the resource subsystems on the same resource layer are in the same type of parallel relationship, and by using the same layer of parallel relationship, the resource subsystems on the same resource layer can be compared with each other, so that the weak or risky resource subsystems are found. For resource subsystems on different resource layers, a bottom-up aggregation transfer relationship exists among the resource subsystems, and the resource subsystems can be explored from the top-down stratum layer to discover the resource subsystems with relatively weak subordinate levels or risks. Therefore, for an operator of the data center, based on the state characteristic values and the hierarchical logic between the state characteristic values, the state condition of each subsystem on any resource layer can be clearly sensed, and for a certain abnormal subsystem, the root cause of the abnormality can be rapidly detected layer by layer downwards, so that the monitoring difficulty is effectively reduced. For example, if the machine room subsystem is abnormal, the states of the cabinet subsystems gathered out of the machine room subsystem can be further inquired, the abnormal cabinet subsystem can be quickly locked, and further whether the abnormal cabinet subsystem is caused by the server subsystem having a problem or not can be continuously detected.

Fig. 2 is a schematic flowchart of a data processing method according to an exemplary embodiment of the present application. The method is described from the perspective of a computing device in the system embodiment shown in FIG. 1a or FIG. 1 b. As shown in fig. 2, the method includes:

21a, acquiring monitoring data of a multilayer resource subsystem existing in a resource system, wherein a resource aggregation relation exists between the multilayer resource system.

And 22a, aggregating the state representation values of the multilayer resource subsystems according to the monitoring data of the multilayer resource subsystems and the resource aggregation relation between the multilayer resource subsystems.

And 23a, monitoring the state of the resource system according to the state characterization value of the multilayer resource subsystem.

In this embodiment, the physical resources in the resource system are layered to form a plurality of resource layers, and each resource layer includes at least one resource subsystem. The resource subsystems on a plurality of resource layers have inclusion relation on physical space, and the resource subsystems on the same resource layer have the same parallel relation. Each resource subsystem comprises at least one type of resource device or module, etc. Resource aggregation relations exist among resource subsystems on a plurality of resource layers, and are referred to as resource aggregation relations among the resource subsystems in a plurality of layers. In the present embodiment, the resource aggregation relationship among the multi-layer resource subsystems is from bottom to top, that is, the resource subsystem in the previous layer is aggregated by the resource subsystem in the next layer.

In order to ensure the operational reliability and stability of the resource system, it is necessary to monitor the state of the resource system. In this embodiment, the resource subsystems are used as the granularity to distinguish the monitoring data in the resource system, and obtain the monitoring data of the multi-layer resource subsystems; furthermore, the state representation values of the multilayer resource subsystems can be aggregated according to the monitoring data of the multilayer resource subsystems and the resource aggregation relation between the multilayer resource subsystems, and the state of the resource system can be monitored according to the state representation values of the multilayer resource subsystems. The "monitoring the state of the resource system" herein includes: the overall status of the resource system is monitored, and/or the status of particular resource subsystems in the resource system is monitored.

In an alternative embodiment, the implementation of step 22a includes: and according to the monitoring data of the multilayer resource subsystems and the resource aggregation relation between the multilayer resource subsystems, aggregating the state representation values of the resource subsystems of each layer according to the sequence of the resource layers from bottom to top.

In the process of aggregating the state representation values of each layer of resource subsystems according to the sequence of the resource layers from bottom to top, the state representation values of each resource subsystem in the multi-layer resource subsystems need to be aggregated. The aggregation process of the state characterising values is the same or similar for each resource subsystem. The following describes an aggregation process of the state representation values by taking the first resource subsystem as an example. The first resource subsystem is any one of the multi-tier resource subsystems.

For a first resource subsystem, if a resource layer to which the first resource subsystem belongs is not the lowest resource layer in the resource system, aggregating a state representation value of the first resource subsystem according to monitoring data of the first resource subsystem and a state representation value of a next-layer resource subsystem having a resource aggregation relation with the first resource subsystem; and if the resource layer to which the first resource subsystem belongs is the lowest resource layer in the resource system, aggregating the state representation value of the first resource subsystem according to the monitoring data of the first resource subsystem.

In an optional embodiment, aggregating the state characterizing value of the first resource subsystem according to the monitoring data of the first resource subsystem and the state characterizing value of the next resource subsystem having a resource aggregation relationship with the first resource subsystem includes: carrying out dimensionless processing on the monitoring data of the first resource subsystem and the state representation value of the next layer resource subsystem having a resource aggregation relation with the first resource subsystem; and carrying out aggregation operation on the monitoring data subjected to dimensionless processing and the state characteristic value to obtain the state characteristic value of the first resource subsystem.

In another optional embodiment, aggregating the state characterizing value of the first resource subsystem according to the monitoring data of the first resource subsystem and the state characterizing value of the next layer resource subsystem having a resource aggregation relationship with the first resource subsystem includes: carrying out dimensionless processing on the monitoring data of the first resource subsystem; performing aggregation operation on the monitoring data subjected to dimensionless processing to obtain a resource state intermediate value of the first resource subsystem; and correcting the resource state intermediate value of the first resource subsystem according to the state representation value of the next resource subsystem having a resource aggregation relation with the first resource subsystem to obtain the state representation value of the first resource subsystem.

In an optional embodiment, aggregating the state characterizing value of the first resource subsystem according to the monitoring data of the first resource subsystem includes: carrying out dimensionless processing on the monitoring data of the first resource subsystem; and carrying out aggregation operation on the monitoring data subjected to dimensionless processing to obtain a state representation value of the first resource subsystem.

In an alternative embodiment, the implementation of step 23a includes: monitoring the overall state of the resource system according to the state representation value of the multilayer resource subsystem; or monitoring the state of a specific resource subsystem in the resource system according to the state representation value of the multilayer resource subsystem; or, according to the state representation values of the multi-layer resource subsystems, the overall state of the resource system and the state of a specific resource subsystem in the resource system are monitored simultaneously.

Further, one way to monitor the overall state of the resource system based on the state characterizing values of the multi-tier resource subsystems includes: weighting and summing the state representation values of the multilayer resource subsystems to obtain an overall state representation value; and inquiring the mapping relation between the preset integral state and the representation value according to the integral state representation value to obtain the integral state of the resource system.

Further, one way to monitor the status of a particular resource subsystem in the resource system based on the status characterizing values of the multi-tier resource subsystems comprises: monitoring whether a resource subsystem to be monitored with abnormal or suspicious state exists in the resource subsystem at the highest resource layer according to the state representation value of the resource subsystem at the highest resource layer in the multi-layer resource subsystems; if the resource subsystem exists, monitoring whether an abnormal or suspicious resource subsystem exists in the next layer resource subsystem having the resource aggregation relation with the resource subsystem to be monitored according to the state representation value of the next layer resource subsystem having the resource aggregation relation with the resource subsystem to be monitored until the abnormal or suspicious resource subsystem does not exist or all the resource subsystems are monitored. If not, the monitoring process can be ended.

In an alternative embodiment, one way of step 23a includes: and displaying the state representation values of the multilayer resource subsystems according to the resource aggregation relation among the multilayer resource subsystems so as to facilitate relevant operators to monitor the state of the resource system.

In an alternative embodiment, one way of step 21a includes: and acquiring the monitoring data of the multilayer resource subsystem from a database corresponding to the resource system according to the monitoring demand description information.

Further optionally, if the monitoring requirement description information includes the specified time, acquiring the monitoring data of the multi-layer resource subsystem from the database corresponding to the resource system according to the monitoring requirement description information, including: and acquiring monitoring data generated by the multi-layer resource subsystem at a specified moment from the database.

Further optionally, if the monitoring requirement description information further includes a specified data category, acquiring, from the database, monitoring data generated by the multi-layer resource subsystem at a specified time includes: and acquiring monitoring data which belongs to a specified data category and is generated by the multi-layer resource subsystem at a specified time from the database.

For the detailed description of the steps or operations in the above method, reference may be made to the corresponding description in the foregoing system embodiments, which are not repeated herein.

In this embodiment, the resource subsystems are used as the granularity, the resource aggregation relationship among the multilayer resource subsystems is used as the basis, the monitoring data of the multilayer resource subsystems are respectively aggregated into the state representation values, and based on the state representation values of the multilayer resource subsystems and the hierarchical logic between the state representation values, no matter the operator of the resource system or the monitoring system corresponding to the resource system, the state monitoring of the resource subsystems and the resource system can be intuitively, conveniently, quickly and accurately performed, so that the difficulty of state monitoring is reduced. In addition, by combining the hierarchical logic between the state representation values of the multilayer resource subsystems, an operator can clearly know the states of the resource subsystems on the same resource layer and can perform deep analysis and exploration downwards according to the hierarchical logic according to monitoring requirements, the monitoring requirements are greatly met, and the monitoring difficulty is reduced.

The technical solution provided in the embodiment of the present application may be centrally deployed on one computing device to be implemented, just as in the foregoing embodiment of the present application, the computing device 101 is independent from the resource system, and the state representation values of the multiple layers of resource subsystems in the resource system are centrally aggregated by the computing device 101. It should be noted that, besides centralized deployment and implementation, the technical solutions provided in the embodiments of the present application may also adopt a distributed deployment manner. The following describes an exemplary case where the technical solution of the embodiment of the present application is implemented in a distributed deployment.

Fig. 3a is a schematic structural diagram of a resource system according to an exemplary embodiment of the present application. As shown in fig. 3a, the resource system 30a includes: the resource subsystems 31a are distributed on different resource layers to form a multi-layer resource subsystem; there is a resource aggregation relationship between the multi-tier resource subsystems 31 a.

In this embodiment, the implementation form of the resource system 30a is not limited, and the resource system may be any system structure having certain physical resources, for example, a data center system, a computer room system, a cluster system, or some industrial systems. The physical resources in the resource system 30a mainly refer to some devices, chips, communication lines between devices, and the like. Of course, the physical resources included in different resource systems may be different, and this embodiment does not limit this. Taking an internet system such as a data center system, a machine room system or a cluster system as an example, physical resources in these systems include IT-type devices such as computers, servers, cabinets, storage devices, routers, gateways, switches, printers, etc., refrigeration devices such as air conditioning systems, water cooling systems, etc., power devices such as UPS, HVDC, storage batteries, etc., and communication lines between these devices, such as optical fibers, twisted pairs, coaxial cables, etc. For convenience of illustration, the resource system 30a is illustrated in fig. 3a by taking the IDC system as an example, and the IDC system includes 4 resource layers in fig. 3a as an example, but is not limited thereto. In fig. 3a, the multi-tier resource subsystem 31a includes: the IDC subsystem comprises a server subsystem in a first resource layer, a cabinet subsystem in a second resource layer, a machine room subsystem in a third resource layer and an IDC subsystem in a fourth resource layer.

In this embodiment, the physical resources in the resource system 30a are layered to form a plurality of resource layers, each resource layer includes at least one resource subsystem 31a, and each resource subsystem 31a includes at least one type of resource device or module. The resource devices or modules in each resource subsystem 31a may include computing devices or modules, may also include storage devices or modules, may also include some devices or modules that do not have computing and storage functions, and so on. The resource subsystems 31a on multiple resource layers have an inclusion relationship in a physical space, and the resource subsystems 31a on the same resource layer have a similar parallel relationship.

In this embodiment, a resource aggregation relationship exists between the resource subsystems 31a on multiple resource layers, which is referred to as a resource aggregation relationship between multiple layers of resource subsystems. In the present embodiment, it is assumed that the resource aggregation relationship among the multi-layer resource subsystems is from bottom to top, and this is taken as an example for explanation. For the bottom-up aggregation approach, the resource aggregation relationship between the multi-layer resource subsystems can be understood as: the resource subsystem of the previous layer is aggregated by the resource subsystem of the next layer, in other words, for any resource subsystem on the non-lowest resource layer, the resource subsystems of the next layer can be aggregated. The expression "a plurality" herein means an indefinite number, and the number represented may be one, or two or more. For the resource subsystem on the lowest resource layer, it can be considered as the smallest resource system in the resource systems, and is the basis for forming the resource subsystems on other resource layers. Each resource layer has its own hierarchy, the hierarchies of the resource layers can be from low to high according to a bottom-up aggregation mode, and resource subsystems on a high-level resource layer are aggregated by resource subsystems on a low-level resource layer.

In order to ensure the operational reliability and stability of the resource system 30a, it is necessary to monitor the status of the resource system 30 a. In this embodiment, the resource subsystem 31a is used as a granularity, and a state characterization value of the multilayer resource subsystem is aggregated by combining a resource aggregation relationship among the multilayer resource subsystems, and the state of the resource system 30a is monitored according to the state characterization value of the multilayer resource subsystem. Here, "monitoring the state of the resource system 30 a" includes: the overall status of resource system 30a is monitored, and/or the status of particular resource subsystems in resource system 30a is monitored. There are many kinds of monitoring data related to state monitoring, such as monitoring data related to ambient temperature, device internal temperature, device power consumption, CPU frequency, CPU load, and CPU performance.

Among the multi-tier resource subsystems of the resource system 30a, some of the resource subsystems 31a have computing capabilities, and the physical resources of these resource subsystems 31a contain computing devices or modules. These computing devices or modules in the resource subsystem 31a may be native or otherwise configured for the resource subsystem at a later time. For the case of additional configuration, some edge computing devices may be configured as computing devices or modules of resource subsystem 31 a. In this embodiment, the aggregation process of the state representation values is distributed to the resource subsystems 31a by virtue of the computing power of the resource subsystems 31a, so that a dedicated computing device does not need to be deployed.

For ease of description and differentiation, in the present embodiment, the resource subsystems that comprise a computing device or module are collectively referred to as a first resource subsystem. The first resource subsystem may be one or more. For the case that there are multiple first resource subsystems, the first resource subsystems may be from the same resource layer or from different resource layers. It is not limited to which resource subsystems of the multi-layer resource subsystems contain computing devices or modules, and which resource subsystems do not contain computing devices or modules, depending on the resource system 30 a.

In this embodiment, the computing device or module is not limited, and may be any device or module with computing capability. For example, the chip may be a computer device, a server, a mobile phone, or the like, or may be a CPU, a Graphics Processing Unit (GPU), a Digital Signal Processor (DSP) chip, an Artificial Intelligence (AI) chip, or the like.

In this embodiment, for the first resource subsystem, the state representation value of the first resource subsystem may be aggregated by using its own computing capability. The aggregation process may be specifically performed by a computing device or module in the first resource subsystem. A computing device or module in the first resource subsystem may obtain monitoring data of the first resource subsystem; combining with a resource aggregation relation between the first resource subsystem and other resource subsystems, and aggregating a state representation value of the first resource subsystem according to the monitoring data of the first resource subsystem; and outputting the state representation value of the first resource subsystem for state monitoring of the first resource subsystem. Optionally, the state characterizing value of the first resource subsystem may be output to a database; alternatively, the state representation value of the first resource subsystem may be output to a terminal device used by an operator, such as a smartphone or a personal computer.

In some application scenarios: each resource subsystem 31a in the resource system 30a contains a computing device or module (i.e., has computing capabilities). These resource subsystems 31a, which comprise computing devices or modules, all belong to the first resource subsystem, and can aggregate their own state characterization values by means of their own computing power and output them.

Based on the above, when the computing device or module in the first resource subsystem aggregates the state characterizing value of the first resource subsystem, the computing device or module is specifically configured to: judging whether the resource layer to which the first resource subsystem belongs is the lowest resource layer in the resource system or not by combining the resource aggregation relation between the first resource subsystem and other resource subsystems; if not, the first resource subsystem is aggregated by the next resource subsystem, the state of the first resource subsystem is related to the state of the next resource subsystem, and the state of the first resource subsystem is influenced by the state of the next resource subsystem, and the state representation value of the first resource subsystem can be aggregated by combining the monitoring data of the first resource subsystem and the state representation value of the next resource subsystem having a resource aggregation relation with the first resource subsystem; if yes, the first resource subsystem is the smallest resource subsystem in the resource system, and the state representation value of the first resource subsystem can be aggregated directly according to the monitoring data of the first resource subsystem.

In an optional embodiment, the process of aggregating the state representation value of the first resource subsystem according to the monitoring data of the first resource subsystem includes: carrying out dimensionless processing on the monitoring data of the first resource subsystem; and carrying out aggregation operation on the monitoring data subjected to dimensionless processing to obtain a state representation value of the first resource subsystem.

In an optional embodiment, an optional implementation of aggregating the state representation value of the first resource subsystem according to the monitoring data of the first resource subsystem and the state representation value of the next resource subsystem having a resource aggregation relationship with the first resource subsystem includes: carrying out dimensionless processing on the monitoring data of the first resource subsystem and the state representation value of the next layer resource subsystem having a resource aggregation relation with the first resource subsystem; and carrying out aggregation operation on the monitoring data subjected to dimensionless processing and the state characteristic value to obtain the state characteristic value of the first resource subsystem.

In another optional embodiment, an optional implementation of aggregating the state representation value of the first resource subsystem according to the monitoring data of the first resource subsystem and the state representation value of the next resource subsystem in the resource aggregation relationship with the first resource subsystem includes: carrying out dimensionless processing on the monitoring data of the first resource subsystem; performing aggregation operation on the dimensionless processed monitoring data to obtain a resource state intermediate value of the first resource subsystem; and correcting the resource state intermediate value of the first resource subsystem according to the state representation value of the next resource subsystem having a resource aggregation relation with the first resource subsystem to obtain the state representation value of the first resource subsystem.

For the first resource subsystem, if the resource layer to which the first resource subsystem belongs is not the highest resource layer in the resource system, after the state characterizing value of the first resource subsystem is aggregated, the state characterizing value of the first resource subsystem can be reported to the previous resource subsystem having the resource aggregation relationship.

Taking the IDC system shown in fig. 3a as an example, it is assumed that each server, each cabinet, each room, and IDC all have their own computing device or module. For each server, a calculation module (such as a CPU) can be utilized to aggregate a state representation value of the server according to monitoring data of the server; for each cabinet, a state representation value of the cabinet can be aggregated according to monitoring data of the cabinet and the state representation value of a lower-layer server by using own computing equipment (for example, a certain server included in the cabinet); for each machine room, a state characteristic value of the machine room can be aggregated according to monitoring data of the machine room and the state characteristic value of the lower cabinet by using own computing equipment (for example, a certain server contained in the machine room); for the IDC, a state characteristic value of the IDC may also be aggregated according to monitoring data of the IDC and a state characteristic value of a lower computer room by using a computing device of the IDC (for example, a certain server included in the IDC).

In other application scenarios: some of the resource subsystems 31a in the resource system 30a include computing modules or devices (i.e., have computing capabilities), and some of the resource subsystems 31a do not include computing modules or devices (i.e., have no computing capabilities). For ease of description and distinction, the resource subsystem containing the computing module or device is referred to as the first resource subsystem; resource subsystems that do not contain a computing module or device are collectively referred to as a second resource subsystem. In these application scenarios, for the second resource subsystem, because the second resource subsystem does not have computing capability, the second resource subsystem cannot aggregate its own state characterizing value by itself, but the state characterizing value can be aggregated for the second resource subsystem by virtue of the computing capability of the first resource subsystem in the higher resource layer, which has a resource aggregation relationship with the first resource subsystem, that is, the state characterizing value of the second resource subsystem can be aggregated by the computing device or module in the first resource subsystem which has a resource aggregation relationship with the second resource subsystem and has a higher level than the resource layer to which the second resource subsystem belongs. For the first resource subsystem, not only the state representation value of the first resource subsystem can be aggregated, but also the state representation value of the lower resource subsystem having the resource aggregation relation with the first resource subsystem can be aggregated.

Based on the above, when the computing device or module in the first resource subsystem aggregates the state characterizing value of the first resource subsystem, the computing device or module is specifically configured to: judging whether the resource layer to which the first resource subsystem belongs is the lowest resource layer in the resource system or not by combining the resource aggregation relation between the first resource subsystem and other resource subsystems; if yes, the first resource subsystem is the smallest resource subsystem in the resource system, and the state representation value of the first resource subsystem can be aggregated directly according to the monitoring data of the first resource subsystem; if not, it means that the first resource subsystem is aggregated by the next resource subsystem, and the state of the first resource subsystem is affected by the state of the next resource subsystem, so that it can be further determined whether the next resource subsystem having a resource aggregation relationship with the first resource subsystem includes a computing device or a module.

If the next resource subsystem having the resource aggregation relationship with the first resource subsystem includes the computing device or module, it is indicated that the computing device or module in the first resource subsystem can directly obtain the state representation value of the next resource subsystem having the resource aggregation relationship with the first resource subsystem, and therefore, the state representation value of the first resource subsystem can be aggregated by combining the monitoring data of the first resource subsystem and the state representation value of the next resource subsystem having the resource aggregation relationship with the first resource subsystem.

If the next resource subsystem having the resource aggregation relationship with the first resource subsystem does not include the computing device or module, it indicates that the computing device or module in the first resource subsystem cannot directly acquire the state representation value of the next resource subsystem having the resource aggregation relationship with the first resource subsystem. In this case, the computing device or module in the first resource subsystem may aggregate the state characterizing values of the first resource subsystem and each layer of resource subsystems according to the monitoring data of the first resource subsystem and the monitoring data of each layer of resource subsystems, which have a resource aggregation relationship with the first resource subsystem and have a hierarchy lower than the resource layer to which the first resource subsystem belongs.

For example, the following steps are carried out: assuming that the resource layer to which the first resource subsystem belongs is the third resource layer, and each resource subsystem aggregated by the first resource subsystem on the second resource layer does not have the computing capability, the computing device or module in the first resource subsystem may aggregate the state representation value of the resource subsystem on the first resource layer, the state representation value of the resource subsystem on the second resource layer, and the state representation value of the first resource subsystem according to the monitoring data of the first resource subsystem, the monitoring data of the resource subsystem having a resource aggregation relationship with the first resource subsystem on the second resource layer (referred to as the resource subsystem on the second resource layer for short), and the monitoring data of the resource subsystem having a resource aggregation relationship with the first resource subsystem on the first resource layer (referred to as the resource subsystem on the first resource layer for short). The aggregation process here is similar to the aggregation process implemented by the computing device in the embodiment shown in fig. 1a, fig. 1b, and fig. 2, that is, for each layer of resource subsystems having a resource aggregation relationship, state representation values of each layer of resource subsystems may be sequentially calculated according to a sequence of the resource layers from bottom to top, and detailed processes are not described again, and reference may be made to the foregoing embodiment.

For the first resource subsystem, if the resource layer to which the first resource subsystem belongs is not the highest resource layer in the resource system, after the status characterizing values of the resource subsystems of the first resource subsystem and the lower layer thereof are aggregated, the status characterizing values of the resource subsystems of the first resource subsystem and the lower layer thereof can be reported to the resource subsystem of the upper layer which has the resource aggregation relationship.

No matter which application scenarios are described above, the state representation values of the multi-layer resource subsystems in the resource system can be finally obtained. And then, the state of the resource system or a specific resource subsystem in the resource system can be monitored according to the state representation values of the multilayer resource subsystems, so that the state monitoring of the resource subsystems and the resource system can be intuitively, conveniently, quickly and accurately carried out, and the difficulty of state monitoring is reduced. In this embodiment, the operation of hierarchical aggregation is distributed to resource subsystems with computing capability in the resource system, so that the computing resources in the resource system can be fully utilized, and the efficiency of the aggregation process can be improved.

Fig. 3b is a schematic flow chart of another data processing method according to an exemplary embodiment of the present application. The method is described from the perspective of a computing device or module in the system embodiment shown in fig. 3 a. As shown in fig. 3b, the method comprises:

31b, the computing device or the module obtains the monitoring data of the target resource subsystem to which the computing device or the module belongs, wherein the target resource subsystem is one of the multilayer resource subsystems existing in the resource system, and the resource aggregation relation among the multilayer resource subsystems is realized.

32b, the computing device or the module combines the resource aggregation relation between the target resource subsystem and other resource subsystems, and aggregates the state representation value of the target resource subsystem according to the monitoring data of the target resource subsystem.

33b, the computing device or the module outputs the state representation value of the target resource subsystem for state monitoring of the target resource subsystem.

For ease of description and differentiation, in this embodiment, the resource subsystem to which the computing device or module belongs is referred to as the target resource subsystem. The target resource subsystem is one of a plurality of resource subsystems present in the resource system. For the description of the resource system and the multi-layer resource subsystem, reference may be made to the embodiment shown in fig. 3a, which is not described herein again.

In an alternative embodiment, the implementation of step 32b includes: if the resource layer to which the target resource subsystem belongs is not the lowest resource layer in the resource system, the state representation value of the target resource subsystem can be aggregated according to the monitoring data of the target resource subsystem and the state representation value of the next layer resource subsystem having a resource aggregation relation with the target resource subsystem.

Further optionally, an optional implementation manner of aggregating the state representation value of the first resource subsystem according to the monitoring data of the first resource subsystem and the state representation value of the next resource subsystem having a resource aggregation relationship with the first resource subsystem includes: carrying out dimensionless processing on the monitoring data of the first resource subsystem and the state representation value of the next layer resource subsystem having a resource aggregation relation with the first resource subsystem; and carrying out aggregation operation on the monitoring data subjected to dimensionless processing and the state characteristic value to obtain the state characteristic value of the first resource subsystem. Or

Further optionally, an optional implementation manner of aggregating the state representation value of the first resource subsystem according to the monitoring data of the first resource subsystem and the state representation value of the next resource subsystem having a resource aggregation relationship with the first resource subsystem includes: carrying out dimensionless processing on the monitoring data of the first resource subsystem; performing aggregation operation on the dimensionless processed monitoring data to obtain a resource state intermediate value of the first resource subsystem; and correcting the resource state intermediate value of the first resource subsystem according to the state representation value of the next resource subsystem having a resource aggregation relation with the first resource subsystem to obtain the state representation value of the first resource subsystem.

In another alternative embodiment, the implementation of step 32b includes: and if the resource layer to which the target resource subsystem belongs is not the lowest resource layer in the resource system, aggregating the state representation value of the target resource subsystem according to the monitoring data of the target resource subsystem and the monitoring data of each layer of resource subsystems which have a resource aggregation relation with the target resource subsystem and have a hierarchy lower than the resource layer to which the target resource subsystem belongs. The aggregation process here is similar to the aggregation process implemented by the computing device in the embodiment shown in fig. 1a, fig. 1b, and fig. 2, that is, for each layer of resource subsystems having a resource aggregation relationship, state representation values of each layer of resource subsystems may be sequentially calculated according to a sequence of the resource layers from bottom to top, and detailed processes are not described again, and reference may be made to the foregoing embodiment.

In yet another alternative embodiment, the implementation of step 32b includes: and if the resource layer where the target resource subsystem is located is the lowest resource layer in the resource system, aggregating the state representation value of the target resource subsystem according to the monitoring data of the target resource subsystem.

Further optionally, the process of aggregating the state representation value of the first resource subsystem according to the monitoring data of the first resource subsystem includes: carrying out dimensionless processing on the monitoring data of the first resource subsystem; and carrying out aggregation operation on the monitoring data subjected to dimensionless processing to obtain a state representation value of the first resource subsystem.

Further optionally, after the status characterizing value of the target resource subsystem is aggregated, the method further includes: and if the resource layer to which the target resource subsystem belongs is not the highest resource layer in the resource system, reporting the state representation value of the target resource subsystem to the previous resource subsystem having a resource aggregation relation with the target resource subsystem.

For the description of each step in this embodiment, reference may be made to the corresponding description in the embodiment shown in fig. 3a, which is not repeated herein.

Fig. 3c is a schematic structural diagram of another resource system according to an exemplary embodiment of the present application. As shown in fig. 3c, the resource system 30c includes: the resource subsystems 31c are distributed on different resource layers to form a multi-layer resource subsystem; there is a resource aggregation relationship between the multi-tier resource subsystems 31 c. For convenience of illustration, the resource system 30c is illustrated in fig. 3c by taking the IDC system as an example, and fig. 3c illustrates that the IDC system includes 4 resource layers, but the present invention is not limited thereto. In fig. 3c, the multi-tier resource subsystem 31c includes: the IDC subsystem comprises a server subsystem in a first resource layer, a cabinet subsystem in a second resource layer, a machine room subsystem in a third resource layer and an IDC subsystem in a fourth resource layer.

The resource system 30c and the resource subsystem 31c in this embodiment are the same as or similar to the resource system 30a and the resource subsystem 31a in the embodiment shown in fig. 3a, and related descriptions may refer to the embodiment shown in fig. 3a, which is not described herein again.

Similar to the embodiment shown in fig. 3a, in this embodiment, the resource subsystem 31c is used as a granularity, and a resource aggregation relationship among the multiple layers of resource subsystems is combined to aggregate state characterizing values of the multiple layers of resource subsystems, and according to the state characterizing values of the multiple layers of resource subsystems, the resource system 30c is monitored for a state, so as to ensure operational reliability and stability of the resource system 30 c. For the related description of the condition monitoring, reference may be made to the embodiment shown in fig. 3a, which is not described herein again.

In the embodiment shown in fig. 3a, the aggregation process of the state characterizations is distributed to the resource subsystems by using the resource subsystems as a granularity and by means of the computing power of the resource subsystems. In this embodiment, the aggregation process of the state representation values is distributed to the resource layers by using the resource layers as the granularity and using the computing power of each resource layer.

For convenience of description and distinction, in the present embodiment, a resource layer (i.e., a resource layer with computing capabilities) containing a computing device or module is referred to as a first resource layer. The first resource layer may be one or more. It is not limited to which resource layers include computing devices or modules and which resource layers do not include computing devices or modules, which may vary from resource system 30c to resource system. Similarly, the present embodiment also does not limit the computing devices or modules, and may be any device or module with computing capability. For example, the device may be a computer device, a server, a mobile phone, etc., or may be a CPU, a GPU, a DSP chip, an AI chip, etc.

The computing device or module in the first resource layer may be a computing device or module in a certain resource subsystem 31c in the resource layer, or may be a computing device or module that is independently deployed or configured from each resource subsystem 31c in the resource layer. For the first resource layer, the computing device or module is responsible for aggregating the state representation values of the resource subsystems on the first resource layer.

For a computing device or module in a first resource layer, acquiring monitoring data of each resource subsystem on the first resource layer, and aggregating state representation values of each resource subsystem on the first resource layer according to the monitoring data of each resource subsystem on the first resource layer by combining resource aggregation relations between each resource subsystem on the first resource layer and other resource subsystems; and outputting the state representation values of all the resource subsystems on the first resource layer for carrying out state monitoring on the first resource layer. Optionally, the state characterizing value of the first resource subsystem may be output to a database; alternatively, the state representation value of the first resource subsystem may be output to a terminal device used by an operator, such as a smartphone or a personal computer.

In some application scenarios: each resource layer in resource system 30c contains computing devices or modules. The resource layers containing the computing devices or modules all belong to the first resource layer, and state representation values of all resource subsystems on the resource layer can be aggregated by means of own computing power and output.

And the aggregation processes of the state representation values of the resource subsystems in the first resource layer are the same or similar. Taking the first resource subsystem in the first resource layer as an example, the aggregation process of the state characterizing value is explained. The first resource subsystem is any resource subsystem in the first resource layer. When aggregating the state representation value of the first resource subsystem, the computing device or the module in the first resource layer is specifically configured to: under the condition that the first resource layer is not the lowest resource layer in the resource system, combining the monitoring data of the first resource subsystem and the state representation value of the next resource subsystem which has a resource aggregation relation with the first resource subsystem to aggregate the state representation value of the first resource subsystem; under the condition that the first resource layer is the lowest resource layer in the resource system, the state representation value of the first resource subsystem can be aggregated directly according to the monitoring data of the first resource subsystem. For a detailed implementation of aggregating the state representation value of the first resource subsystem, reference may be made to the corresponding description in the embodiment shown in fig. 3a, which is not described herein again.

If the first resource layer is not the highest resource layer in the resource system, after the status representation values of the resource subsystems on the first resource layer are aggregated, the status representation values of the resource subsystems can be reported to the resource subsystem on the previous layer having a resource aggregation relationship with the resource subsystems.

Taking the IDC system shown in fig. 3c as an example, it is assumed that each of the first, second, third and fourth resource layers has its own computing device or module. For the first resource layer, a computing device (e.g., a server) of the first resource layer may be used to aggregate the state representation values of the servers according to the monitoring data of the servers in the first resource layer; for the second resource layer, the state representation values of the cabinets can also be aggregated by using own computing equipment (for example, a certain server in a certain cabinet) according to the monitoring data of the cabinets in the second resource layer and the state representation values of the lower-layer servers corresponding to the cabinets; for the third resource layer, the state representation values of the machine rooms can also be aggregated by using own computing equipment (for example, a certain server in a certain machine room) according to the monitoring data of the machine rooms on the third resource layer and the state representation values of the lower-layer cabinets corresponding to the machine rooms; for the fourth resource layer, the state characteristic value of the IDC may also be aggregated by using its own computing device (for example, a server included in the IDC) according to the monitoring data of the IDC and the state characteristic values of the lower computer rooms.

In other application scenarios: in resource system 30c, a portion of the resource layer contains computing modules or devices (i.e., has computing capabilities), and a portion of the resource layer does not contain computing modules or devices (i.e., has no computing capabilities). For ease of description and distinction, the resource layer containing the computing module or device is referred to as the first resource layer; and setting the resource layer which does not contain the computing module or the equipment as a second resource layer. In these application scenarios, for the second resource layer, because the second resource layer does not have the computing capability, the state representation values of the resource subsystems on the resource layer cannot be aggregated by itself, but the state representation values of the resource subsystems can be aggregated for the second resource layer by the computing capability in the higher resource layer, that is, the state representation values of the resource subsystems on the second resource layer can be aggregated by the computing device or module in the first resource layer higher in hierarchy than the second resource layer. Preferably, if the previous resource layer of the second resource layer has the computing capability, the state representation values of the resource subsystems on the second resource layer are aggregated preferentially by the computing capability of the previous resource layer of the second resource layer.

Based on the above, in the process of aggregating the state characterizing values of the resource subsystems on the first resource layer, the computing device or the module in the first resource layer may also aggregate the state characterizing values of the resource subsystems on the second resource layer, which have a resource aggregation relationship with the resource subsystems. Still taking the first resource subsystem in the first resource layer as an example, when the computing device or the module in the first resource layer aggregates the state characterizing value of the first resource subsystem, the computing device or the module in the first resource layer is specifically configured to: under the condition that the first resource layer is the lowest resource layer in the resource system, the state representation value of the first resource subsystem can be aggregated directly according to the monitoring data of the first resource subsystem; in the event that the first resource layer is not the lowest resource layer in the resource system, it may be further determined whether the next resource layer contains a computing device or module.

If the next resource layer includes the computing device or module, it is indicated that the computing device or module in the first resource layer can directly obtain the state representation value of the next resource subsystem having the resource aggregation relationship with the first resource subsystem, and therefore, the state representation value of the first resource subsystem can be aggregated by combining the monitoring data of the first resource subsystem and the state representation value of the next resource subsystem having the resource aggregation relationship with the first resource subsystem.

If the next resource layer does not contain the computing device or module, it is indicated that the computing device or module in the first resource layer cannot directly acquire the state representation value of the next resource subsystem having the resource aggregation relationship with the first resource subsystem. In this case, the computing device or module in the first resource layer may aggregate the state characterizing values of the first resource subsystem and each layer of resource subsystems according to the monitoring data of the first resource subsystem and the monitoring data of each layer of resource subsystems, which have a resource aggregation relationship with the first resource subsystem and have a hierarchy lower than that of the first resource layer.

For a detailed implementation of aggregating the state representation value of the first resource subsystem, reference may be made to the corresponding description in the embodiment shown in fig. 3a, which is not described herein again.

Fig. 3d is a schematic flowchart of another data processing method according to an exemplary embodiment of the present application. The present embodiment is described from the perspective of a computing device or module in the system shown in fig. 3 c. As shown in fig. 3d, the method comprises:

31d, the computing device or the module acquires monitoring data of each resource subsystem on a target layer to which the computing device or the module belongs, wherein the target layer is one of a plurality of resource layers corresponding to a plurality of layers of resource subsystems in the resource system, and a resource aggregation relation exists among the plurality of layers of resource subsystems.

And 32d, the computing equipment or the module combines the resource aggregation relation between each resource subsystem on the target layer and other resource subsystems, and aggregates the state representation values of each resource subsystem on the target layer according to the monitoring data of each resource subsystem on the target layer.

And 33d, outputting the state representation values of the resource subsystems on the target layer by the computing equipment or the computing module so as to monitor the state of the target layer.

For ease of description and differentiation, in this embodiment, the resource layer to which the computing device or module belongs is referred to as the target layer. The target layer is one of a plurality of resource layers existing in the resource system. For the description of the resource system, the resource layer, and the multi-layer resource subsystem, reference may be made to the embodiment shown in fig. 3a, which is not described herein again.

In an alternative embodiment, the implementation of step 32d includes: and if the target layer is not the lowest resource layer in the resource system, aggregating the state representation values of the resource subsystems on the target layer according to the monitoring data of the resource subsystems on the target layer and the state representation values of the resource subsystems on the next layer which have a resource aggregation relation with the resource subsystems on the target layer.

Further, aggregating the state representation values of the resource subsystems on the target layer according to the monitoring data of the resource subsystems on the target layer and the state representation values of the resource subsystems on the next layer having a resource aggregation relationship with the resource subsystems on the target layer, including: for the first resource subsystem, aggregating the state representation value of the first resource subsystem according to the monitoring data of the first resource subsystem and the state representation value of the next layer resource subsystem having a resource aggregation relation with the first resource subsystem; the first resource subsystem is any one of the resource subsystems on the target layer.

In another alternative embodiment, the implementation of step 32d includes: and if the target layer is not the lowest resource layer in the resource system, aggregating the state representation values of the resource subsystems on the target layer according to the monitoring data of the resource subsystems on the target layer and the monitoring data of the resource subsystems on each layer which have a resource aggregation relation with the resource subsystems on the target layer and have a hierarchy lower than that of the target layer.

Further, aggregating the state representation values of the resource subsystems on the target layer according to the monitoring data of the resource subsystems on the target layer and the monitoring data of the resource subsystems on each layer which has a resource aggregation relation with the resource subsystems on the target layer and has a hierarchy lower than the target layer, and the method comprises the following steps: and for the first resource subsystem, aggregating the state representation value of the first resource subsystem according to the monitoring data of the first resource subsystem and the monitoring data of each layer of resource subsystems which have a resource aggregation relation with the first resource subsystem and have a hierarchy lower than the target layer. The first resource subsystem is any one of the resource subsystems on the target layer. In the process, the state representation values of the resource subsystems of the layers which have the resource aggregation relation with the first resource subsystem and have the hierarchy lower than the target layer can be aggregated.

In yet another alternative embodiment, the implementation of step 32d includes: and if the target layer is the lowest resource layer in the resource system, aggregating the state representation values of all the resource subsystems on the target layer according to the monitoring data of all the resource subsystems on the target layer.

For the description of each step in this embodiment, refer to the corresponding description in the embodiments shown in fig. 3c and fig. 3a, and are not repeated herein.

It should be noted that the method embodiments described above may be applied to different resource systems, for example, may be applied to a data center system, or a computer room system, or a cluster system. The following description will be made by applying the above method embodiment to a data center system.

Fig. 3e is a schematic flowchart of another data processing method according to an exemplary embodiment of the present application. The data processing method is applied to a data center system, and the data center system sequentially comprises at least two layers of a server resource layer, a cabinet resource layer, a cold and hot channel resource layer, an inter-package resource layer and a machine room resource layer from bottom to top. It should be noted that the resource layers included in the data center system are not limited to the ones listed here, and may also include more other resource layers, and of course, may also include only some of the resource layers listed here. As shown in fig. 3e, the method comprises:

31e, according to the monitoring data on each resource layer in the data center system, aggregating the state representation values of resources on at least two layers of the server resource layer, the cabinet resource layer, the cold and hot channel resource layer, the inter-package resource layer and the machine room resource layer from bottom to top in sequence.

And 32e, displaying resource state representation values on at least two layers of the server resource layer, the cabinet resource layer, the cold and hot channel resource layer, the inter-package resource layer and the machine room resource layer according to a bottom-to-top aggregation relation so as to enable a user to locate a fault reason when the data center system has a fault.

Wherein, the resources on different resource layers are different. For example, the resource on the server resource layer refers to each server, the resource on the rack resource layer refers to each rack, the resource on the cold/hot channel resource layer refers to each cold/hot channel, the resource on the inter-bay resource layer refers to each inter-bay, and the resource on the machine room resource layer refers to each machine room.

In the embodiment, according to the aggregation relationship from bottom to top among resource layers in the data center system, the state representation values of the resources on the resource layers included in the data center are aggregated; and then, displaying the state representation values of the resources on each resource layer, so that a user (such as an operator of the data center) can conveniently locate the fault reason when the data center system has a fault.

For a detailed implementation manner of step 31e, reference may be made to the description in the foregoing embodiments, and details are not described herein.

In step 32e, the specific implementation of displaying the state representation values of the resources on at least two layers of the server resource layer, the cabinet resource layer, the hot and cold aisle resource layer, the inter-bundle resource layer, and the machine room resource layer is not limited. When the state representation values of resources on at least two layers of the server resource layer, the cabinet resource layer, the cold and hot channel resource layer, the inter-pack resource layer and the machine room resource layer are displayed, at least one display mode which is not limited to the following mode can be adopted:

the display mode 1: and displaying the state representation values of the resources on different resource layers in a differentiated mode among different resource layers. For example, different colors may be used to show the status indicator of resources on different resource layers, such as green indicating the status indicator of each room on the room resource layer, red indicating the status indicator of each room on the inter-room resource layer, blue indicating the status indicator of each cold/hot channel on the cold/hot channel resource layer, and so on. For another example, different graphs or patterns may be used to show the status indicators of resources on different resource layers, such as a circle representing the status indicator of each machine room on the machine room resource layer, a square representing the status indicator of each inter-room on the inter-room resource layer, a pentagon representing the status indicator of each cold/hot channel on the cold/hot channel resource layer, and so on. Alternatively, the state characterizing values of the respective resources may be written inside the respective graph.

The display mode 2: and for the same resource layer, displaying the state representation values of different resources on the resource layer in a differentiated mode. For example, in the case of displaying the status indicators of the resources on different resource layers in different colors, for each resource layer, the status indicators of the different resources on the resource layer may be displayed in different patterns. Taking the machine room resource layer as an example, a circle with a green numerical value is used for representing the state characteristic value of the first machine room, a square with a green numerical value is used for representing the state characteristic value of the second machine room, a pentagon with a yellow numerical value is used for representing the state characteristic value of the third machine room, and the like. For another example, in the case that different shapes or patterns are used to represent the status characterizing values of resources on different resource layers, for each resource layer, different colors may be used to show the status characterizing values of different resources on the resource layer, taking a machine room resource layer as an example, a circle with a red numerical value is used to represent the status characterizing value of a first machine room, a circle with a green numerical value is used to represent the status characterizing value of a second machine room, a circle with a yellow numerical value is used to represent the status characterizing value of a third machine room, and so on.

Display mode 3: and highlighting the abnormal state representation value on each resource layer and the resource identifier corresponding to the abnormal state representation value. The embodiment does not limit the manner of highlighting, and may be, for example, highlighting, underlining, dynamic display, or the like. Dynamic display modes include, but are not limited to: pop, blink, shake, etc.

It should be noted that the execution subjects of the steps of the methods provided in the above embodiments may be the same device, or different devices may be used as the execution subjects of the methods. For example, the execution subjects of steps 31b to 33b may be device a; for another example, the execution subject of steps 31B and 32B may be device a, and the execution subject of step 33B may be device B; and so on.

In addition, in some of the flows described in the above embodiments and the drawings, a plurality of operations are included in a specific order, but it should be clearly understood that the operations may be executed out of the order presented herein or in parallel, and the order of the operations, such as 31b, 32b, etc., is merely used for distinguishing different operations, and the order itself does not represent any execution order. Additionally, the flows may include more or fewer operations, and the operations may be performed sequentially or in parallel. It should be noted that, the descriptions of "first", "second", etc. in this document are used for distinguishing different messages, devices, modules, etc., and do not represent a sequential order, nor limit the types of "first" and "second" to be different.

Fig. 4a is a schematic structural diagram of a computing device according to an exemplary embodiment of the present application. As shown in fig. 4a, the computing device includes: a memory 41a and a processor 42 a.

The memory 41a is used to store computer programs and may be configured to store other various data to support operations on the computing device. Examples of such data include instructions, messages, pictures, videos, etc. for any application or method operating on a computing device.

A processor 42a, coupled to the memory 41a, for executing the computer program in the memory 41a to: acquiring monitoring data of multilayer resource subsystems in the resource systems, wherein resource aggregation relations exist among the multilayer resource systems; according to the monitoring data of the multilayer resource subsystem and the resource aggregation relation between the multilayer resource subsystems, aggregating the state representation values of the multilayer resource subsystems; and monitoring the state of the resource system according to the state representation value of the multilayer resource subsystem.

In an optional embodiment, when aggregating the state characterization values of the multi-layer resource subsystem, the processor 42a is specifically configured to: and according to the monitoring data of the multilayer resource subsystems and the resource aggregation relation between the multilayer resource subsystems, aggregating the state representation values of the resource subsystems of each layer according to the sequence of the resource layers from bottom to top.

Further optionally, when the processor 42a aggregates the state representation values of the resource subsystems of each layer according to the order of the resource layers from bottom to top, the processor is specifically configured to: for a first resource subsystem, if a resource layer to which the first resource subsystem belongs is not the lowest resource layer in the resource system, aggregating a state representation value of the first resource subsystem according to monitoring data of the first resource subsystem and a state representation value of a next-layer resource subsystem having a resource aggregation relation with the first resource subsystem; wherein the first resource subsystem is any one of the multi-tier resource subsystems.

Further, when the processor 42a aggregates the state representation value of the first resource subsystem according to the monitoring data of the first resource subsystem and the state representation value of the next layer resource subsystem having a resource aggregation relationship with the first resource subsystem, it is specifically configured to: carrying out dimensionless processing on the monitoring data of the first resource subsystem and the state representation value of the next layer resource subsystem having a resource aggregation relation with the first resource subsystem; and carrying out aggregation operation on the monitoring data subjected to dimensionless processing and the state characteristic value to obtain the state characteristic value of the first resource subsystem.

Or

Further, when the processor 42a aggregates the state representation value of the first resource subsystem according to the monitoring data of the first resource subsystem and the state representation value of the next layer resource subsystem having a resource aggregation relationship with the first resource subsystem, it is specifically configured to: carrying out dimensionless processing on the monitoring data of the first resource subsystem; performing aggregation operation on the dimensionless processed monitoring data to obtain a resource state intermediate value of the first resource subsystem; and correcting the resource state intermediate value of the first resource subsystem according to the state representation value of the next resource subsystem having a resource aggregation relation with the first resource subsystem to obtain the state representation value of the first resource subsystem.

Further optionally, when the state characterizing value of the first resource subsystem is aggregated, the processor 42a is specifically configured to: and if the resource layer to which the first resource subsystem belongs is the lowest resource layer in the resource system, aggregating the state representation value of the first resource subsystem according to the monitoring data of the first resource subsystem.

Further, when the processor 42a aggregates the state characterizing value of the first resource subsystem according to the monitoring data of the first resource subsystem, it is specifically configured to: carrying out dimensionless processing on the monitoring data of the first resource subsystem; and carrying out aggregation operation on the monitoring data subjected to dimensionless processing to obtain a state representation value of the first resource subsystem.

In an optional embodiment, the processor 42a is specifically configured to perform at least one of the following operations when performing state monitoring on the resource system according to the state characterizing value of the multi-layer resource subsystem:

monitoring the overall state of the resource system according to the state representation value of the multilayer resource subsystem;

and monitoring the state of a specific resource subsystem in the resource system according to the state characterization value of the multilayer resource subsystem.

Further optionally, when monitoring the overall state of the resource system, the processor 42a is specifically configured to: weighting and summing the state representation values of the multilayer resource subsystems to obtain an overall state representation value; and inquiring the mapping relation between the preset integral state and the representation value according to the integral state representation value to obtain the integral state of the resource system.

Further optionally, when monitoring the status of a specific resource subsystem in the resource system, the processor 42a is specifically configured to: monitoring whether a resource subsystem to be monitored with abnormal or suspicious state exists in the resource subsystem at the highest resource layer according to the state representation value of the resource subsystem at the highest resource layer in the multi-layer resource subsystems; if the resource subsystem exists, monitoring whether an abnormal or suspicious resource subsystem exists in the next layer resource subsystem having the resource aggregation relation with the resource subsystem to be monitored according to the state representation value of the next layer resource subsystem having the resource aggregation relation with the resource subsystem to be monitored until the abnormal or suspicious resource subsystem does not exist or all the resource subsystems are monitored.

In an optional embodiment, the processor 42a is specifically configured to, when performing state monitoring on the resource system: and displaying the state representation values of the multilayer resource subsystems according to the resource aggregation relation among the multilayer resource subsystems so as to facilitate relevant operators to monitor the state of the resource system.

In an optional embodiment, when acquiring the monitoring data of the multi-layer resource subsystem existing in the resource system, the processor 42a is specifically configured to: and acquiring the monitoring data of the multilayer resource subsystem from a database corresponding to the resource system according to the monitoring demand description information.

Further optionally, the monitoring demand description information includes a specified time. Based on this, when the processor 42a obtains the monitoring data of the multi-layer resource subsystem from the database, it is specifically configured to: and acquiring monitoring data generated by the multi-layer resource subsystem at a specified moment from the database.

Further optionally, the monitoring requirement description information further comprises a specified data category. Based on this, when the processor 42a obtains the monitoring data of the multi-layer resource subsystem from the database, it is specifically configured to: and acquiring monitoring data which belongs to a specified data category and is generated by the multi-layer resource subsystem at a specified time from the database.

Optionally, the resource system in this embodiment may be a computer room system, a cluster system, or a data center system, but is not limited thereto.

Further, under the condition that the resource system is a data center system, the data center system sequentially comprises at least two layers of a server resource layer, a cabinet resource layer, a cold and hot channel resource layer, an inter-package resource layer and a machine room resource layer from bottom to top. Based on this, the processor 42a is specifically configured to: according to monitoring data on each resource layer, sequentially aggregating state representation values of resources on at least two layers of a server resource layer, a cabinet resource layer, a cold and hot channel resource layer, an inter-bundle resource layer and a machine room resource layer from bottom to top; and according to the aggregation relation from bottom to top, resource state representation values on at least two layers of a server resource layer, a cabinet resource layer, a cold-hot channel resource layer, an inter-package resource layer and a machine room resource layer are displayed so as to enable a user to locate a fault reason when the data center system fails.

Further optionally, the processor 42a may display the state representation values of the resources on at least two of the server resource layer, the cabinet resource layer, the hot and cold aisle resource layer, the inter-bundle resource layer, and the machine room resource layer by using, but not limited to, at least one of the following display manners:

displaying state representation values of resources on different resource layers in a differentiation mode among different resource layers;

displaying the state representation values of different resources on the same resource layer in a differentiated mode;

and highlighting the abnormal state representation value on each resource layer and the resource identifier corresponding to the abnormal state representation value.

Further, as shown in fig. 4a, the computing device further comprises: communication components 43a, display 44a, power components 45a, audio components 46a, and the like. Only some of the components are schematically shown in fig. 4a, and the computing device is not meant to include only the components shown in fig. 4 a. In addition, depending on the implementation of the computing device, the components within the dashed box in FIG. 4a are optional components, not mandatory components. For example, when the computing device is implemented as a terminal device such as a smartphone, tablet, or desktop computer, the components within the dashed box in fig. 4a may be included; when the computing device is implemented as a server-side device such as a conventional server, a cloud server, a data center, or an array of servers, the components within the dashed box in fig. 4a may not be included.

Accordingly, the present application further provides a computer-readable storage medium storing a computer program, where the computer program can implement the steps in the method embodiment shown in fig. 2 when executed.

Fig. 4b is a schematic structural diagram of a computing device according to an exemplary embodiment of the present application. As shown in fig. 4b, the computing device includes: a memory 41b and a processor 42 b.

The memory 41b is used for storing computer programs and may be configured to store other various data to support operations on the computing device. Examples of such data include instructions, messages, pictures, videos, etc. for any application or method operating on a computing device.

A processor 42b, coupled to the memory 41b, for executing the computer program in the memory 41b for: acquiring monitoring data of a target resource subsystem to which the computing equipment belongs, wherein the target resource subsystem is one of multilayer resource subsystems in a resource system, and a resource aggregation relation among the multilayer resource subsystems; aggregating the state representation value of the target resource subsystem according to the monitoring data of the target resource subsystem by combining the resource aggregation relation between the target resource subsystem and other resource subsystems; and outputting the state representation value of the target resource subsystem for state monitoring of the target resource subsystem.

In an optional embodiment, when aggregating the state characterizing value of the target resource subsystem, the processor 42b is specifically configured to: if the resource layer to which the target resource subsystem belongs is not the lowest resource layer in the resource system, aggregating the state representation value of the target resource subsystem according to the monitoring data of the target resource subsystem and the state representation value of the next resource subsystem having a resource aggregation relation with the target resource subsystem; or if the resource layer to which the target resource subsystem belongs is not the lowest resource layer in the resource system, aggregating the state representation value of the target resource subsystem according to the monitoring data of the target resource subsystem and the monitoring data of each layer of resource subsystems which have a resource aggregation relation with the target resource subsystem and have a hierarchy lower than the resource layer to which the target resource subsystem belongs.

In another optional embodiment, when aggregating the state characterizing value of the target resource subsystem, the processor 42b is specifically configured to: and if the resource layer where the target resource subsystem is located is the lowest resource layer in the resource system, aggregating the state representation value of the target resource subsystem according to the monitoring data of the target resource subsystem.

In an alternative embodiment, the processor 42b is further configured to: and if the resource layer to which the target resource subsystem belongs is not the highest resource layer in the resource system, after the state representation value of the target resource subsystem is aggregated, reporting the state representation value of the target resource subsystem to a previous resource subsystem having a resource aggregation relation with the target resource subsystem.

Further, as shown in fig. 4b, the computing device further comprises: communication components 43b, display 44b, power components 45b, audio components 46b, and the like. Only some of the components are schematically shown in fig. 4b, and the computing device is not meant to include only the components shown in fig. 4 b. In addition, the components within the dashed box in FIG. 4b are optional components, not mandatory components, depending on the implementation of the computing device. For example, when the computing device is implemented as a terminal device such as a smartphone, tablet, or desktop computer, the components within the dashed box in fig. 4b may be included; when the computing device is implemented as a server-side device such as a conventional server, a cloud server, a data center, or an array of servers, the components within the dashed box in fig. 4b may not be included.

Accordingly, the present application further provides a computer-readable storage medium storing a computer program, where the computer program can implement the steps in the method embodiment shown in fig. 3b when executed.

Fig. 4c is a schematic structural diagram of a computing device according to an exemplary embodiment of the present application. As shown in fig. 4c, the computing device includes: a memory 41c and a processor 42 c.

A memory 41c for storing computer programs and may be configured to store other various data to support operations on the computing device. Examples of such data include instructions, messages, pictures, videos, etc. for any application or method operating on a computing device.

A processor 42c, coupled to the memory 41c, for executing the computer program in the memory 41c for: acquiring monitoring data of each resource subsystem on a target layer of the computing equipment, wherein the target layer is one of a plurality of resource layers corresponding to a plurality of layers of resource subsystems in the resource system, and resource aggregation relations exist among the plurality of layers of resource subsystems; combining the resource aggregation relation between each resource subsystem and other resource subsystems on the target layer, and aggregating the state representation values of each resource subsystem on the target layer according to the monitoring data of each resource subsystem on the target layer; and outputting the state representation values of all the resource subsystems on the target layer for carrying out state monitoring on the target layer.

In an optional embodiment, when aggregating the state characterizing values of the resource subsystems on the target layer, the processor 42c is specifically configured to: if the target layer is not the lowest resource layer in the resource system, aggregating the state representation values of all the resource subsystems on the target layer according to the monitoring data of all the resource subsystems on the target layer and the state representation values of the resource subsystems on the next layer which have a resource aggregation relation with all the resource subsystems on the target layer; or if the target layer is not the lowest resource layer in the resource system, aggregating the state representation values of the resource subsystems on the target layer according to the monitoring data of the resource subsystems on the target layer and the monitoring data of the resource subsystems on each layer which have a resource aggregation relation with the resource subsystems on the target layer and have a hierarchy lower than that of the target layer.

Further optionally, when the state representation value of each resource subsystem on the target layer is aggregated according to the monitoring data of each resource subsystem on the target layer and the state representation value of the resource subsystem on the next layer having the resource aggregation relationship with each resource subsystem on the target layer, the processor 42c is specifically configured to: for the first resource subsystem, aggregating the state representation value of the first resource subsystem according to the monitoring data of the first resource subsystem and the state representation value of the next layer resource subsystem having a resource aggregation relation with the first resource subsystem; the first resource subsystem is any one of the resource subsystems on the target layer.

Further optionally, when the state representation value of each resource subsystem on the target layer is aggregated according to the monitoring data of each resource subsystem on the target layer and the monitoring data of each resource subsystem on each layer, which has a resource aggregation relationship with each resource subsystem on the target layer and has a hierarchy lower than the target layer, the processor 42c is specifically configured to: and for the first resource subsystem, aggregating the state representation value of the first resource subsystem according to the monitoring data of the first resource subsystem and the monitoring data of each layer of resource subsystems which have a resource aggregation relation with the first resource subsystem and have a hierarchy lower than the target layer. The first resource subsystem is any one of the resource subsystems on the target layer.

In another optional embodiment, when aggregating the state characterizing values of the resource subsystems on the target layer, the processor 42c is specifically configured to: and if the target layer is the lowest resource layer in the resource system, aggregating the state representation values of all the resource subsystems on the target layer according to the monitoring data of all the resource subsystems on the target layer.

Further, as shown in fig. 4c, the computing device further comprises: communication component 43c, display 44c, power component 45c, audio component 46c, and the like. Only some of the components are schematically shown in fig. 4c, and the computing device is not meant to include only the components shown in fig. 4 c. In addition, the components within the dashed box in FIG. 4c are optional components, not mandatory components, depending on the implementation of the computing device. For example, when the computing device is implemented as a terminal device such as a smartphone, tablet, or desktop computer, the components within the dashed box in fig. 4c may be included; when the computing device is implemented as a server-side device such as a conventional server, a cloud server, a data center, or a server array, the components within the dashed box in fig. 4c may not be included.

Accordingly, the present application further provides a computer-readable storage medium storing a computer program, where the computer program can implement the steps in the method embodiment shown in fig. 3d when executed.

The communication components of fig. 4 a-4 c described above are configured to facilitate communication between the device in which the communication component is located and other devices in a wired or wireless manner. The device where the communication component is located can access a wireless network based on a communication standard, such as a WiFi, a 2G, 3G, 4G/LTE, 5G and other mobile communication networks, or a combination thereof. In an exemplary embodiment, the communication component receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component may further include a Near Field Communication (NFC) module, Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and the like.

The displays in fig. 4 a-4 c described above include screens, which may include Liquid Crystal Displays (LCDs) and Touch Panels (TPs). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation.

The power supply components of fig. 4 a-4 c described above provide power to the various components of the device in which the power supply components are located. The power components may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device in which the power component is located.

The audio components of fig. 4 a-4 c described above may be configured to output and/or input audio signals. For example, the audio component includes a Microphone (MIC) configured to receive an external audio signal when the device in which the audio component is located is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal may further be stored in a memory or transmitted via a communication component. In some embodiments, the audio assembly further comprises a speaker for outputting audio signals.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

A data processing method applied to a computing device is characterized by comprising the following steps:

acquiring monitoring data of a multi-layer resource subsystem existing in a resource system, wherein a resource aggregation relation exists between the multi-layer resource system;

aggregating the state representation values of the multilayer resource subsystems according to the monitoring data of the multilayer resource subsystems and the resource aggregation relation between the multilayer resource subsystems;

and monitoring the state of the resource system according to the state characterization value of the multilayer resource subsystem.
The method of claim 1, wherein aggregating the state characterization values of the multi-layer resource subsystem according to the monitoring data of the multi-layer resource subsystem and the resource aggregation relationship between the multi-layer resource subsystem comprises:

and according to the monitoring data of the multilayer resource subsystems and the resource aggregation relation between the multilayer resource subsystems, aggregating the state representation values of the resource subsystems of each layer according to the sequence of the resource layers from bottom to top.
The method of claim 2, wherein aggregating the status characterizing values of the resource subsystems of each layer according to the resource aggregation relationship between the monitoring data of the multi-layer resource subsystem and the order of the resource layers from bottom to top comprises:

for a first resource subsystem, if a resource layer to which the first resource subsystem belongs is not the lowest resource layer in the resource system, aggregating a state representation value of the first resource subsystem according to monitoring data of the first resource subsystem and a state representation value of a next-layer resource subsystem having a resource aggregation relation with the first resource subsystem;

wherein the first resource subsystem is any one of the multi-tier resource subsystems.
The method of claim 3, wherein aggregating the state representation value of the first resource subsystem according to the monitoring data of the first resource subsystem and the state representation value of the next resource subsystem having a resource aggregation relationship with the first resource subsystem comprises:

carrying out dimensionless processing on the monitoring data of the first resource subsystem and the state representation value of the next layer resource subsystem having a resource aggregation relation with the first resource subsystem;

and carrying out aggregation operation on the monitoring data subjected to dimensionless processing and the state characteristic value to obtain the state characteristic value of the first resource subsystem.
The method of claim 3, wherein aggregating the state representation value of the first resource subsystem according to the monitoring data of the first resource subsystem and the state representation value of the next resource subsystem having a resource aggregation relationship with the first resource subsystem comprises:

carrying out dimensionless processing on the monitoring data of the first resource subsystem;

performing aggregation operation on the dimensionless processed monitoring data to obtain a resource state intermediate value of the first resource subsystem;

and correcting the resource state intermediate value of the first resource subsystem according to the state characteristic value of the next resource subsystem having a resource aggregation relation with the first resource subsystem to obtain the state characteristic value of the first resource subsystem.
The method of claim 3, further comprising:

and if the resource layer to which the first resource subsystem belongs is the lowest resource layer in the resource system, aggregating the state representation value of the first resource subsystem according to the monitoring data of the first resource subsystem.
The method of claim 6, wherein aggregating the status-characterizing value of the first resource subsystem from the monitored data of the first resource subsystem comprises:

carrying out dimensionless processing on the monitoring data of the first resource subsystem;

and performing aggregation operation on the monitoring data subjected to dimensionless processing to obtain a state representation value of the first resource subsystem.
The method according to any one of claims 1-7, wherein performing the status monitoring of the resource system based on the status characterizing value of the multi-tier resource subsystem comprises at least one of:

monitoring the overall state of the resource system according to the state representation value of the multilayer resource subsystem;

and monitoring the state of a specific resource subsystem in the resource system according to the state characterization value of the multilayer resource subsystem.
The method of claim 8, wherein monitoring the overall state of the resource system based on the state characterization values for the multi-tier resource subsystems comprises:

weighting and summing the state representation values of the multilayer resource subsystems to obtain an integral state representation value;

and inquiring the mapping relation between a preset integral state and the characteristic value according to the integral state characteristic value to obtain the integral state of the resource system.
The method of claim 8, wherein monitoring the status of a particular resource subsystem in the resource system based on the status characterizing values of the multi-tier resource subsystems comprises:

monitoring whether a resource subsystem to be monitored with abnormal or suspicious state exists in the resource subsystem at the highest resource layer according to the state representation value of the resource subsystem at the highest resource layer in the multi-layer resource subsystems;

if the resource subsystem exists, monitoring whether an abnormal or suspicious resource subsystem exists in the next layer resource subsystem having the resource aggregation relation with the resource subsystem to be monitored according to the state representation value of the next layer resource subsystem having the resource aggregation relation with the resource subsystem to be monitored until the abnormal or suspicious resource subsystem does not exist or all the resource subsystems are monitored.
The method of any one of claims 1 to 7, wherein obtaining monitoring data for multi-tier resource subsystems present in the resource system comprises:

and acquiring the monitoring data of the multilayer resource subsystem from a database corresponding to the resource system according to the monitoring demand description information.
The method according to claim 11, wherein if the monitoring requirement description information includes a specific time, acquiring the monitoring data of the multi-layer resource subsystem from a database corresponding to the resource system according to the monitoring requirement description information includes:

and acquiring the monitoring data generated by the multilayer resource subsystem at the appointed moment from the database.
The method of claim 12, wherein the monitoring requirement description information further includes a specific data category, and the obtaining the monitoring data generated by the multi-layer resource subsystem at the specific time from the database comprises:

and acquiring the monitoring data which is generated by the multilayer resource subsystem at the specified moment and belongs to the specified data category from the database.
The method of any one of claims 1-7, wherein the resource system is a computer room system, a cluster system, or a data center system.
A data processing method applied to a computing device is characterized by comprising the following steps:

acquiring monitoring data of a target resource subsystem, wherein the target resource subsystem is one of multilayer resource subsystems in a resource system, and the multilayer resource subsystems have a resource aggregation relation;

combining the resource aggregation relation between the target resource subsystem and other resource subsystems, and aggregating the state representation value of the target resource subsystem according to the monitoring data of the target resource subsystem;

and outputting the state representation value of the target resource subsystem for state monitoring of the target resource subsystem.
The method according to claim 15, wherein aggregating the status-characterizing value of the target resource subsystem according to the monitoring data of the target resource subsystem in combination with the resource aggregation relationship between the target resource subsystem and other resource subsystems comprises:

if the resource layer to which the target resource subsystem belongs is not the lowest resource layer in the resource system, aggregating the state representation value of the target resource subsystem according to the monitoring data of the target resource subsystem and the state representation value of the next layer resource subsystem having a resource aggregation relation with the target resource subsystem;

or

And if the resource layer to which the target resource subsystem belongs is not the lowest resource layer in the resource system, aggregating the state representation value of the target resource subsystem according to the monitoring data of the target resource subsystem and the monitoring data of each layer of resource subsystems which have a resource aggregation relation with the target resource subsystem and have a hierarchy lower than the resource layer to which the target resource subsystem belongs.
The method of claim 16, further comprising:

and if the resource layer where the target resource subsystem is located is the lowest resource layer in the resource system, aggregating the state representation value of the target resource subsystem according to the monitoring data of the target resource subsystem.
The method according to any of claims 15-17, further comprising, after aggregating the state characterizing values of the target resource subsystem:

and if the resource layer to which the target resource subsystem belongs is not the highest resource layer in the resource system, reporting the state representation value of the target resource subsystem to a previous resource subsystem having a resource aggregation relation with the target resource subsystem.
A data processing method applied to a computing device is characterized by comprising the following steps:

acquiring monitoring data of each resource subsystem on a target layer, wherein the target layer is one of a plurality of resource layers corresponding to a plurality of layers of resource subsystems in a resource system, and resource aggregation relations exist among the plurality of layers of resource subsystems;

combining the resource aggregation relation between each resource subsystem on the target layer and other resource subsystems, and aggregating the state representation values of each resource subsystem on the target layer according to the monitoring data of each resource subsystem on the target layer;

and outputting the state representation values of all the resource subsystems on the target layer for carrying out state monitoring on the target layer.
The method according to claim 19, wherein aggregating the status characterizing value of each resource subsystem on the target layer according to the monitoring data of each resource subsystem on the target layer in combination with the resource aggregation relationship between each resource subsystem on the target layer and other resource subsystems comprises:

if the target layer is not the lowest resource layer in the resource system, aggregating the state representation values of the resource subsystems on the target layer according to the monitoring data of the resource subsystems on the target layer and the state representation values of the resource subsystems on the next layer which have a resource aggregation relation with the resource subsystems on the target layer;

or

And if the target layer is not the lowest resource layer in the resource system, aggregating the state representation values of the resource subsystems on the target layer according to the monitoring data of the resource subsystems on the target layer and the monitoring data of the resource subsystems on each layer which have a resource aggregation relation with the resource subsystems on the target layer and are lower in hierarchy than the target layer.
The method according to claim 20, wherein aggregating the status characterizing values of the resource subsystems on the target layer according to the monitoring data of the resource subsystems on the target layer and the status characterizing values of the resource subsystems on the next layer having a resource aggregation relationship with the resource subsystems on the target layer comprises:

for a first resource subsystem, aggregating a state representation value of the first resource subsystem according to monitoring data of the first resource subsystem and the state representation value of a next-layer resource subsystem having a resource aggregation relation with the first resource subsystem;

wherein the first resource subsystem is any one of the resource subsystems on the target layer.
The method according to claim 20, wherein aggregating the status characterizing values of the resource subsystems on the target layer according to the monitoring data of the resource subsystems on the target layer and the monitoring data of the resource subsystems on each layer which has a resource aggregation relationship with the resource subsystems on the target layer and has a hierarchy lower than the target layer comprises:

and for a first resource subsystem, aggregating a state representation value of the first resource subsystem according to the monitoring data of the first resource subsystem and the monitoring data of each layer of resource subsystems which have a resource aggregation relation with the first resource subsystem and have a hierarchy lower than the target layer.

Wherein the first resource subsystem is any one of the resource subsystems on the target layer.
The method of any one of claims 20-22, further comprising:

and if the target layer is the lowest resource layer in the resource system, aggregating the state representation values of all the resource subsystems on the target layer according to the monitoring data of all the resource subsystems on the target layer.
A data processing system, comprising: a computing device and a resource system; the resource system comprises a plurality of layers of resource subsystems, and a resource aggregation relation exists between the plurality of layers of resource subsystems;

the computing device is used for acquiring monitoring data of the multilayer resource subsystem; aggregating the state representation values of the multilayer resource subsystems according to the monitoring data of the multilayer resource subsystems and the resource aggregation relation between the multilayer resource subsystems; and monitoring the state of the resource system according to the state characterization value of the multilayer resource subsystem.
A resource system, comprising: the system comprises a plurality of layers of resource subsystems, wherein a resource aggregation relation exists between the plurality of layers of resource subsystems; wherein there is a first resource subsystem comprising a computing device or module among the multi-tier resource subsystems;

the computing device or module to: acquiring monitoring data of the first resource subsystem; combining the resource aggregation relation between the first resource subsystem and other resource subsystems, and aggregating the state representation value of the first resource subsystem according to the monitoring data of the first resource subsystem; and outputting the state representation value of the first resource subsystem for state monitoring of the first resource subsystem.
The system of claim 25, wherein the computing device or module is specifically configured to:

under the condition that the resource layer to which the first resource subsystem belongs is not the lowest resource layer in the resource system, aggregating the state representation value of the first resource subsystem according to the monitoring data of the first resource subsystem and the state representation value of the next resource subsystem having a resource aggregation relation with the first resource subsystem;

or

And under the condition that the resource layer to which the first resource subsystem belongs is not the lowest resource layer in the resource system, aggregating state characterization values of the first resource subsystem and each layer of resource subsystems according to the monitoring data of the first resource subsystem and the monitoring data of each layer of resource subsystems, which have a resource aggregation relation with the first resource subsystem and have a hierarchy lower than the resource layer to which the first resource subsystem belongs.
The system of claim 26, wherein the computing device or module is further configured to:

and under the condition that the resource layer to which the first resource subsystem belongs is the lowest resource layer in the resource system, aggregating the state representation value of the first resource subsystem according to the monitoring data of the first resource subsystem.
The system of claim 25, wherein there is also a second resource subsystem of the multi-tier resource subsystem that does not contain a computing device or module; and the state representation value of the second resource subsystem is obtained by aggregating computing equipment or modules in a first resource subsystem which has an aggregation relation with the second resource subsystem and is higher in hierarchy than the resource layer to which the second resource subsystem belongs.
The system according to any one of claims 25-28, wherein the resource system is a data center system; in order from bottom to top of the resource hierarchy, the multi-layered resource subsystem comprises: the system comprises a server subsystem, a cabinet subsystem, a train subsystem, a cold and hot channel subsystem, an inter-pack subsystem, a machine room subsystem and an IDC subsystem.
A resource system, comprising: the resource aggregation method comprises the following steps that multiple layers of resource subsystems exist, and a resource aggregation relation exists among the multiple layers of resource subsystems; wherein a first resource layer containing computing equipment or modules exists in a plurality of resource layers corresponding to the multi-layer resource subsystem;

the computing device or module to: acquiring monitoring data of each resource subsystem on the first resource layer, and aggregating state representation values of each resource subsystem on the first resource layer according to the monitoring data of each resource subsystem on the first resource layer by combining resource aggregation relations between each resource subsystem on the first resource layer and other resource subsystems; and outputting the state representation values of all the resource subsystems on the first resource layer so as to monitor the state of the first resource layer.
The system of claim 30, wherein there is also a second resource layer of the plurality of resource layers that does not contain a computing device or module; and the state representation values of the resource subsystems on the second resource layer are obtained by aggregating computing equipment or modules in a first resource layer which has a resource aggregation relation with the resource subsystems on the second resource layer and is higher in hierarchy than the second resource layer.
The system of claim 30 or 31, wherein the resource system is a data center system; in order from bottom to top of the resource hierarchy, the multi-layered resource subsystem comprises: the system comprises a server subsystem, a cabinet subsystem, a train subsystem, a cold and hot channel subsystem, an inter-pack subsystem, a machine room subsystem and an IDC subsystem.
A computing device, comprising: a memory and a processor;

the memory for storing a computer program;

the processor, coupled with the memory, to execute the computer program to:

acquiring monitoring data of a multi-layer resource subsystem existing in a resource system, wherein a resource aggregation relation exists between the multi-layer resource system;

aggregating the state representation values of the multilayer resource subsystems according to the monitoring data of the multilayer resource subsystems and the resource aggregation relation between the multilayer resource subsystems;

and monitoring the state of the resource system according to the state characterization value of the multilayer resource subsystem.
A computing device, comprising: a memory and a processor;

the memory for storing a computer program;

the processor, coupled with the memory, to execute the computer program to:

acquiring monitoring data of a target resource subsystem to which the computing equipment belongs, wherein the target resource subsystem is one of multilayer resource subsystems existing in a resource system, and the multilayer resource subsystems are in a resource aggregation relation;

combining the resource aggregation relation between the target resource subsystem and other resource subsystems, and aggregating the state representation value of the target resource subsystem according to the monitoring data of the target resource subsystem;

and outputting the state representation value of the target resource subsystem for state monitoring of the target resource subsystem.
A computing device, comprising: a memory and a processor;

the memory for storing a computer program;

the processor, coupled with the memory, to execute the computer program to:

acquiring monitoring data of each resource subsystem on a target layer of the computing equipment, wherein the target layer is one of a plurality of resource layers corresponding to a plurality of layers of resource subsystems in the resource system, and resource aggregation relations exist among the plurality of layers of resource subsystems;

combining resource aggregation relations between the resource subsystems on the target layer and other resource subsystems, and aggregating state representation values of the resource subsystems on the target layer according to the monitoring data of the resource subsystems on the target layer;

and outputting the state representation values of all the resource subsystems on the target layer for carrying out state monitoring on the target layer.
A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, causes the processor to carry out the steps of the method according to any one of claims 1 to 24.
A data processing method is suitable for a data center system, and is characterized in that the data center system sequentially comprises at least two layers of a server resource layer, a cabinet resource layer, a cold and hot channel resource layer, an inter-package resource layer and a machine room resource layer from bottom to top; the method comprises the following steps:

according to monitoring data on each resource layer, sequentially aggregating state representation values of resources on at least two layers of a server resource layer, a cabinet resource layer, a cold and hot channel resource layer, an inter-bundle resource layer and a machine room resource layer from bottom to top;

and displaying resource state representation values on at least two layers of a server resource layer, a cabinet resource layer, a cold-hot channel resource layer, an inter-package resource layer and a machine room resource layer according to a bottom-to-top aggregation relation so as to enable a user to locate a fault reason when the data center system has a fault.
The method of claim 37, wherein displaying the status representation of resources on at least two of the server resource layer, the cabinet resource layer, the hot and cold aisle resource layer, the inter-enclosure resource layer, and the machine room resource layer comprises at least one of:

displaying state representation values of resources on different resource layers in a differentiated mode among different resource layers;

displaying the state representation values of different resources on the same resource layer in a differentiated mode;

and highlighting the abnormal state representation value on each resource layer and the resource identifier corresponding to the abnormal state representation value.