Resource monitoring method, device and system and computer readable storage medium

Abstract

The invention discloses a resource monitoring method, device and system and a computer readable storage medium, and relates to the technical field of networks. The resource monitoring method comprises the following steps: obtaining monitoring information of a computing power network resource layer, a computing power network control layer and a computing power network service layer related to a computing power network; and according to the monitoring information and a measurement result of the computing power network resource layer, generating computing network multi-factor monitoring information comprising a service identifier of a computing power network service provided by the computing power network service layer, an identifier of a user using the computing power network service, and a computing power identifier of a computing power resource provided by the computing power network resource layer. According to the invention, a network detection mechanism based on users and services is introduced, and the network detection mechanism based on services further monitors computing power resources and network resources. Therefore, effective integration of computing power and network monitoring is realized.

Description

Technical Field

[0001] The present invention relates to the field of network technology, and in particular to a resource monitoring method, device, system and computer-readable storage medium. Background Art

[0002] In cloud-network integration and computing network scenarios, it is necessary to monitor a variety of heterogeneous resources in real time, such as computing resources and network resources. By providing the best computing resource services and network connections based on the different demands of different users for computing power, we can provide all users with strict target service quality assurance.

[0003] In the related art, computing resources and network resources are monitored independently. Summary of the invention

[0004] After analysis, the inventors found that since the computing power resources and network resource monitoring in the relevant technologies are independent and unrelated, there may be a situation where the computing power resources are available but there are problems with the network resources, or there may be a situation where the network resources are normal but the computing power resources alarm, resulting in a decline in user application experience or even unusable application.

[0005] A technical problem to be solved by the embodiments of the present invention is: how to provide services based on computing resources and network resources with better application experience.

[0006] According to the first aspect of some embodiments of the present invention, a resource monitoring method is provided, comprising: obtaining monitoring information of a computing power network resource layer, a computing power network control layer, and a computing power network service layer involved in a computing power network; generating, based on the monitoring information and the measurement results of the computing power resource layer, computing power network multi-factor monitoring information including a service identifier of a computing power network service provided by the computing power network service layer, an identifier of a user using the computing power network service, and a computing power identifier of a computing power resource provided by the computing power network resource layer.

[0007] In some embodiments, the computing power network resource layer includes infrastructure resources.

[0008] In some embodiments, the infrastructure resources include at least one of computing resources, network resources, and storage resources.

[0009] In some embodiments, the monitoring information of the computing power network control layer includes monitoring information of resource control functions.

[0010] In some embodiments, the monitoring information of the resource control function includes at least one of the duration of resource information collection and the access control of resource types.

[0011] In some embodiments, the monitoring information of the computing power network service layer includes monitoring information of the operating status of the computing power network service.

[0012] In some embodiments, the monitoring information of the operating status of the computing power network service includes at least one of the resource information processing status and the transaction process execution creation status.

[0013] In some embodiments, obtaining monitoring information of the computing power network resource layer includes: sending a subscription request to the monitored network resources in the computing power network resource layer; and obtaining operation, management and maintenance information reported by the monitored network resources.

[0014] In some embodiments, the subscription request includes a condition for triggering an alarm, and the condition for triggering the alarm includes at least one of a threshold and a threshold of a change amount within a preset time period.

[0015] In some embodiments, obtaining the operation, management and maintenance information reported by the monitored network resources includes: in response to an alarm being triggered, obtaining the operation, management and maintenance information reported by the monitored network resources.

[0016] In some embodiments, the monitoring indicators of the computing power network service layer include at least one of service alarm status indicators, average load, average response time, and maximum number of sessions.

[0017] In some embodiments, the monitoring parameters of the computing resources in the computing power network resource layer include at least one of an alarm status indication, an average CPU utilization rate, an available number of CPUs, an average GPU utilization rate, and an available number of GPUs.

[0018] In some embodiments, the monitoring parameters of the network resources in the computing power network resource layer include at least one of an alarm status indication, incoming available bandwidth, outgoing available bandwidth, average latency, jitter, and packet loss.

[0019] In some embodiments, the monitoring parameters of the storage resources in the computing power network resource layer include at least one of an alarm status indication, a random access memory capacity, an average utilization rate of the random access memory, and a used size of the random access memory.

[0020] In some embodiments, the monitoring parameters of the computing power network control layer include at least one of alarm status indication, computing resource monitoring duration, computing resource monitoring threshold, network resource monitoring duration, network resource monitoring threshold, computing resource monitoring threshold, storage resource monitoring duration, storage resource monitoring threshold, service monitoring duration, and service monitoring threshold.

[0021] In some embodiments, the computing power network resource layer includes network resources on the user side and network resources on the computing power resource pool side, and the monitoring method also includes: sending a subscription request to the network resources on the user side so that the network resources on the user side initiate measurement of the network resources on the computing power resource pool side, wherein the request initiated by the network resources on the user side carries user side information and the destination network protocol address of the computing power resource pool; receiving the measurement results sent by the network resources on the user side.

[0022] In some embodiments, the measurement method of the network resources on the computing power resource pool side initiated by the user-side network resources is continuity measurement, performance measurement or frame delay measurement.

[0023] According to a second aspect of some embodiments of the present invention, a resource monitoring device is provided, including: a monitoring module, configured to obtain monitoring information of a computing power network resource layer, a computing power network control layer and a computing power network service layer involved in the computing power network; a generation module, configured to generate computing power network multi-factor monitoring information including a service identifier of a computing power network service provided by the computing power network service layer, a user identifier of a user using the computing power network service, and a computing power identifier of a computing power resource provided by the computing power network resource layer based on the monitoring information and the measurement results of the computing power resource layer.

[0024] According to a third aspect of some embodiments of the present invention, there is provided a resource monitoring device, comprising: a memory; and a processor coupled to the memory, wherein the processor is configured to execute any one of the aforementioned resource monitoring methods based on instructions stored in the memory.

[0025] According to a fourth aspect of some embodiments of the present invention, a computing power operation management and maintenance module is provided, comprising: a monitoring device for any one of the aforementioned resources.

[0026] According to a fifth aspect of some embodiments of the present invention, a resource monitoring system is provided, including: a computing power operation management and maintenance module; a computing power network resource layer; a computing power network control layer; and a computing power network service layer.

[0027] In some embodiments, the computing power network control layer is further configured to perform at least one of resource configuration, resource collection, and network scheduling on the computing power network resource layer based on the computing network multi-factor monitoring information.

[0028] In some embodiments, the computing power network service layer is further configured to perform at least one of information analysis and processing, billing, and session execution on one or more services in the computing power network service layer.

[0029] In some embodiments, the computing power operation management and maintenance module is further configured to send the computing network multi-factor monitoring information to the computing power network service layer; the computing power network service layer is further configured to analyze the computing network multi-factor monitoring information and send the analysis results to the computing power network control layer.

[0030] According to a sixth aspect of some embodiments of the present invention, there is provided a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any one of the aforementioned resource monitoring methods.

[0031] Some embodiments of the above invention have the following advantages or beneficial effects. The embodiments of the present invention introduce a user- and service-based network detection mechanism into the network, wherein the service-based network detection mechanism further monitors computing power resources and network resources. Thus, the effective integration of computing power and network monitoring is achieved, and more accurate and comprehensive monitoring and measurement of computing network quality is achieved. Therefore, the embodiments of the present invention can associate the monitoring information of computing power resources and network resources, thereby avoiding resource waste and improving the user experience of application services.

[0032] Further features and advantages of the present invention will become apparent from the following detailed description of exemplary embodiments of the present invention with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0034] Figure 1 A schematic diagram of a scenario in which network resources and computing resources are independently monitored is shown.

[0035] Figure 2 The network diagram of the resource monitoring system of some embodiments of the present invention is exemplarily shown.

[0036] Figure 3 A schematic flow chart of a resource monitoring method according to some embodiments of the present invention is shown.

[0037] Figure 4 A schematic flow chart of a method for measuring network resources according to some embodiments of the present invention is shown.

[0038] Figure 5 A schematic flow chart of a resource monitoring method according to some other embodiments of the present invention is shown.

[0039] Figure 6 A schematic structural diagram of a resource monitoring device according to some embodiments of the present invention is shown.

[0040] Figure 7 A schematic structural diagram of a resource monitoring device according to some other embodiments of the present invention is shown.

[0041] Figure 8 A schematic structural diagram of a resource monitoring device according to yet other embodiments of the present invention is shown. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. The following description of at least one exemplary embodiment is actually only illustrative and is by no means intended to limit the present invention and its application or use. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0043] The relative arrangement of components and steps, the numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.

[0044] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0045] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered as part of the specification.

[0046] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0047] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0048] Figure 1 Figure 1 shows a schematic diagram of a scenario in which network resources and computing resources are independently monitored. Figure 1As shown, the network management platform 11 is connected to the network resource module 12, the network resource module 12 collects and reports information to the network management platform 11, and the network management platform 11 configures network resources for the network resource module 12. The network resource module 12 includes resources such as switches (Switch, abbreviated as: SW), routers, and gateways (GateWay, abbreviated as: GW). The computing power management platform 13 is connected to the computing power resource module 14, the computing power resource module 14 collects and reports information to the computing power management platform 13, and the computing power management platform 13 configures computing power resources for the computing power resource module 14. The computing power resource module 14 includes storage, CPU, GPU and other resources. Figure 1 It can be seen that the network management platform 11 and the computing power management platform 13 are independent of each other, that is, the computing power resources and network resource monitoring are independent and unrelated, so there may be a situation where the computing power resources are available but there are problems with the network resources, or there may be a situation where the network resources are normal but the computing power resources alarm, resulting in a decline in user application experience or even unusable application.

[0049] In response to the above technical problems, the present invention provides a new resource monitoring method, which can perform integrated computing network resource monitoring on computing resources and network resources (collectively referred to as computing network resources) from a user / service perspective.

[0050] Figure 2 The network diagram of the resource monitoring system of some embodiments of the present invention is exemplarily shown. Figure 2 As shown, the system of this embodiment includes a computing network orchestration management layer 21, a computing power network service layer 22, a computing power network control layer 23 and a computing power network resource layer 24.

[0051] The computing network orchestration management layer 21 includes a computing power operation management and maintenance (OAM) module 210. The computing power operation management and maintenance module 210 includes, for example, a resource monitoring device, such as a computing network resource monitoring platform, which is used to monitor computing power services, computing power resources and network resources. The service can be a computing application service provided to users, such as a service for training a certain model. During the operation of the service, computing power resources and network resources need to be called. The computing power resources can be a computing power resource pool, such as storage, central processing unit (CPU), graphics processing unit (Graphics Processing Unit, referred to as GPU) and other resources, and network resources include SW, routing, GW and other resources. The resources required for a certain service can be determined based on user needs, network conditions, resource usage, etc. For example, for the training task of the image processing model, storage and GPU resources are required. When the user has higher requirements for processing efficiency, more cache resources and GPUs need to be provided to meet the needs of the user. The computing power operation management and maintenance module 210 obtains computing network multi-factor monitoring information by monitoring the service and the computing resources and network resources involved, which is used to characterize the integrated monitoring results of users, services, computing power resources and network resources.

[0052] The computing power network service layer 22 performs at least one of resource information processing, billing, and transaction process execution on one or more services. Resource information processing can be performed on the monitoring results of the service and the computing resources and network resources involved. Billing is used to bill the user for the process of using the service, such as billing by time, or billing by the number or type of resources used by the user. Transaction process execution is used to support the flow of processes between users and services and resources. The monitoring information (such as monitoring results) of the computing power network service layer 22 includes monitoring information of the operating status of the computing power network service. The monitoring information of the operating status of the computing power network service includes, for example, at least one of the resource information processing status and the transaction process execution creation status. In some embodiments, the monitoring indicators of the computing power network service layer 22 include at least one of the service alarm status indicator, average load, average response time, and maximum number of sessions.

[0053] The computing power network control layer 23 is used to perform at least one of resource information collection, resource allocation, and network connection scheduling on computing power resources and network resources based on the computing network multi-factor monitoring information. Resource information collection refers to adding new resources to the resource pool. Resource allocation refers to selecting corresponding resources for services. Network connection scheduling refers to scheduling computing power resources and network resources. The monitoring information of the computing power network control layer 23 includes monitoring information of the resource control function. The monitoring information of the resource control function includes, for example, at least one of the duration of resource information collection and access control of resource types.

[0054] In some embodiments, the monitoring parameters of the computing power network control layer include at least one of alarm status indication, computing resource monitoring duration, computing resource monitoring threshold, network resource monitoring duration, network resource monitoring threshold, computing resource monitoring threshold, storage resource monitoring duration, storage resource monitoring threshold, service monitoring duration, and service monitoring threshold.

[0055] The computing power network resource layer 24 includes infrastructure resources, which include at least one of computing resources, network resources, storage resources, and service resources. The computing power network resource layer may include network resources on the user side and network resources on the computing power resource pool side.

[0056] In some embodiments, the monitoring parameters of the computing resources in the computing power network resource layer include at least one of an alarm status indication, an average CPU utilization rate, an available number of CPUs, an average GPU utilization rate, and an available number of GPUs.

[0057] In some embodiments, the monitoring parameters of the network resources in the computing power network resource layer include at least one of an alarm status indication, incoming available bandwidth, outgoing available bandwidth, average latency, jitter, and packet loss.

[0058] In some embodiments, the monitoring parameters of the storage resources in the computing power network resource layer include at least one of an alarm status indication, a random access memory capacity, an average utilization rate of the random access memory, and a used size of the random access memory.

[0059] A mature interface protocol can be used between the computing network orchestration management layer 21, the computing network service layer 22, the computing network control layer 23 and the computing network resource layer 24, and the fields in the protocol can be expanded according to specific circumstances. Thus, the deployment difficulty can be reduced.

[0060] Reference below Figure 3 An embodiment of the resource monitoring method of the present invention is described. This embodiment is executed by, for example, a computing power operation management and maintenance module, or may also be executed by other electronic devices, which will not be described in detail here.

[0061] Figure 3FIG. 2 is a flow chart showing a method for monitoring resources according to some embodiments of the present invention. Figure 3 As shown, the resource monitoring method of this embodiment includes steps S302 to S304.

[0062] In step S302, monitoring information of the computing power network resource layer, computing power network control layer and computing power network service layer involved in the computing power network is obtained.

[0063] The monitored objects are, for example, monitoring indicators of services and computing resources and network resources involved in the services. The monitoring indicators corresponding to services, computing resources, and network resources can be completely different or overlap.

[0064] In some embodiments, obtaining monitoring information of the computing power network resource layer may include: sending a subscription request to the monitored network resources in the computing power network resource layer; obtaining operation management and maintenance information reported by the monitored network resources, the operation management and maintenance information including monitoring information. For example, when the monitored indicator exceeds a threshold, or when the change amount of the monitored indicator exceeds a threshold within a preset time period, the operation management and maintenance information may be triggered.

[0065] In some embodiments, the subscription request includes alarm triggering conditions, and the alarm triggering conditions include at least one of a threshold and a threshold of a change amount within a preset time period, so that an alarm can be triggered when the alarm triggering conditions are met, thereby triggering the reporting process of monitoring information.

[0066] In addition, at least one of the alarm monitoring threshold and the scheduled monitoring duration can be sent to the service used by the user and the computing resources and network resources involved in the service; and the monitoring information sent by the service and the computing resources and network resources involved in the service can be obtained. After sending the alarm monitoring threshold or the scheduled monitoring duration, the service, computing resources and network resources can determine the monitoring information according to the alarm monitoring threshold, or monitor periodically according to the scheduled monitoring duration. For example, the monitoring information includes monitored indicators whose values ​​exceed the alarm monitoring threshold, that is, the monitoring information is reported only when the value of the monitored indicator exceeds the alarm monitoring threshold. Of course, services, computing resources and network resources can also report any monitoring results, regardless of whether they exceed the alarm monitoring threshold. In addition, in an embodiment of the present invention, exceeding the alarm monitoring threshold means being lower than the alarm monitoring lower limit or higher than the alarm monitoring upper limit.

[0067] The above monitoring indicators are only exemplary, and those skilled in the art can add or delete them as needed.

[0068] In some embodiments, the monitoring information of the computing power network resource layer, the computing power network control layer, and the computing power network service layer may include one or more of user identification, service identification, and computing power identification.

[0069] Through step S302, computing network monitoring information based on the service perspective can be obtained.

[0070] In addition to monitoring information, you can also obtain measurement results of the computing power network resource layer.

[0071] In some embodiments, a subscription request is sent to the network resource on the user side; and the measurement result sent by the network resource on the user side is received. The network resource on the user side can initiate the measurement of the network resource on the computing resource pool side in response to the subscription request. In some embodiments, the request initiated by the network resource on the user side carries the user side information and the destination network protocol address of the computing resource pool. Other information can also be carried as needed, which will not be repeated here.

[0072] In some embodiments, the user-side network resource initiates the measurement of the computing power resource pool-side network resource in the form of continuity check (CC), performance measurement (PM), or delay measurement (DM). The DM method will be described exemplarily below.

[0073] In some embodiments, the measurement results of the computing power resource pool side network resources initiated by the user-side network resources include the measured indicators whose values ​​exceed the local alarm monitoring threshold. That is, the monitoring information is reported only when the value of the measured indicator exceeds the local alarm monitoring threshold. Of course, the user-side network resources can also report any monitoring results, regardless of whether they exceed the local alarm monitoring threshold. In addition, in an embodiment of the present invention, exceeding the local alarm monitoring threshold means being lower than the alarm monitoring lower limit or higher than the alarm monitoring upper limit.

[0074] By obtaining the measurement results, computing network monitoring information based on the user's perspective can be obtained.

[0075] In step S304, based on the monitoring information and measurement results, computing network multi-factor monitoring information including service identification, user identification and computing power identification is generated, for example, computing network multi-factor monitoring information including the service identification of the computing power network service provided by the computing power network service layer, the identification of the user using the computing power network service, and the computing power identification of the computing power resource provided by the computing power network resource layer.

[0076] An exemplary computing network multi-factor monitoring information is: {service identification, user identification, computing resource identification, computing power alarm status indicator, available CPU number, available GPU number, available MEM number, network alarm status indicator, available bandwidth, latency, jitter, packet loss, service alarm status indicator, average load, average response time, maximum number of sessions}.

[0077] Through step S304, the monitoring results of computing resources, network resources, and services can be integrated together to comprehensively evaluate the services used by the user and the computing resources and network resources involved.

[0078] After obtaining the computing network multi-factor monitoring information, the computing power resources and network resources can be controlled based on the information. For example, at least one of resource configuration, resource collection, and network scheduling is performed on the computing power resources and network resources based on the computing network multi-factor monitoring information.

[0079] For example, by analyzing the multi-factor monitoring information, it is found that the average response time is long. After further analysis, it is found that the delay of network resources is normal, so the long response time may be caused by low computing power resource configuration. At this time, the computing power resources of the user's current service can be reconfigured, such as increasing the number of CPUs associated with the service to improve the response speed.

[0080] The above embodiment introduces a user- and service-based network detection mechanism into the network, wherein the service-based network detection mechanism further monitors computing power resources and network resources. Thus, the effective integration of computing power and network monitoring is achieved, and more accurate and comprehensive monitoring and measurement of computing network quality is achieved. Therefore, the embodiment of the present invention can associate the monitoring information of computing power resources and network resources, thereby avoiding resource waste and improving the user experience of application services.

[0081] Reference below Figure 4 An embodiment of a method for measuring network resources is exemplarily described.

[0082] Figure 4 FIG. 2 is a flow chart showing a method for measuring network resources according to some embodiments of the present invention. Figure 4 As shown, the network resource measurement method of this embodiment includes steps S402 to S408.

[0083] In step S402, the first sending time of the user-side network resources to send the service message and the first receiving time of the computing power resource pool-side network resources to receive the service message are determined.

[0084] For example, the user-side network resource sets the dye position 1 for the sent service message, that is, marks position 1 for "dyeing", and the counter starts recording the first sending time t0 of the service message. After network forwarding, the computing power resource pool-side network resource receives the first service message with dye position 1 in this measurement period, and records the first receiving time t1 of the service message.

[0085] In step S404, a second sending time of a return message for sending a service message by the network resources on the computing power resource pool side and a second receiving time of a return message for receiving by the network resources on the user side are determined.

[0086] For example, the computing resource pool side network resource sets the color position 1 for the sent return message, and the counter starts recording the second sending time t2 of the return message. Then, after network forwarding, the user side network resource receives the first return message with the color position 1 in this measurement period, and records the second receiving time t3 of the return message.

[0087] In step S406, the two-way delay between the user-side network resources and the computing power resource pool-side network resources is determined based on the first sending time, the first receiving time, the second sending time, and the second receiving time.

[0088] For example, the two-way delay is = (t1-t0) + (t3-t2) = (t3-t0) - (t2-t1).

[0089] In step S408, a measurement result is determined according to the two-way delay.

[0090] For example, the measurement result may be the two-way delay itself, or may include other measurement results in addition to the two-way delay, or the two-way delay and other results may be weighted and calculated to obtain further calculation results.

[0091] The above measurement process can be initiated by multiple user-side network resources to multiple computing resource pool-side network resources. For example, when the user-side network resources include UA and UB and the computing resource pool-side network resources include CA and CB, the network conditions between UA and CA, UB and CA, UA and CB, and UB and CB can be measured.

[0092] The above embodiment uses the service message between the user-side network resources and the computing power-side network resources and the return message of the service message for testing, so there is no need to send additional test messages, saving communication overhead. Through the above test, the computing network monitoring information based on the user's perspective can be obtained, which can be more helpful to control the computing network resources to improve the user experience.

[0093] Below Figure 2Taking the networking structure of as an example, an implementation example of the interaction process between each layer is described.

[0094] Figure 5 FIG. 2 shows a flow chart of a resource monitoring method according to some other embodiments of the present invention. Figure 5 As shown, the resource monitoring method of this embodiment includes steps S502 to S518.

[0095] In step S502, the computing network resource monitoring platform sends the preset alarm monitoring thresholds, scheduled monitoring duration and other requirements to the monitored network resources, computing power resources and application services through the configuration interface of the computing power network control layer.

[0096] In step S504, the computing resources of the computing network resource layer, the computing network service layer, and the computing network control layer are monitored regularly according to the monitoring duration, and the monitoring indicators are analyzed to see whether they exceed the local alarm monitoring threshold. If so, they are reported to the computing network resource monitoring platform.

[0097] In step S506, the user-side network resources initiate measurement of all computing resource pool-side network resources in the network to obtain measurement information.

[0098] In step S508, after receiving the measurement information sent by the user-side network resources, the network resources on the computing power resource pool side feed back relevant network information such as available bandwidth, latency, packet loss, etc. according to the measurement requirements, and carry the computing power identification information of the computing power resources.

[0099] In step S510, after receiving the feedback measurement message, the user-side network resources analyze whether the network alarm indicator in the message exceeds the local network alarm monitoring threshold. If exceeded, it is reported to the computing network resource monitoring platform through the network collection interface of the computing power network control layer.

[0100] In step S512, the multi-factor information integration module integrates all the collected monitoring information according to the identifier to generate multi-factor monitoring information of the computing network based on "service identifier + user identifier + computing power identifier".

[0101] In step S514, the computing network resource monitoring platform sends the computing network multi-factor monitoring information to the computing power network service layer for analysis and processing.

[0102] In step S516, the computing power network service layer conducts a comprehensive analysis of the computing network multi-factor monitoring information and sends the analysis results to the computing power network control layer.

[0103] In step S518, the computing power network control layer forms control strategies for network resources and computing power resources respectively, and sends them to corresponding computing power resources or network resources.

[0104] Thus, through the cooperation between the above layers, a network detection mechanism based on users and services can be realized. Thus, the effective integration of computing power and network monitoring is achieved, and more accurate and comprehensive monitoring and measurement of computing network quality is achieved. Therefore, the embodiments of the present invention can associate the monitoring information of computing power resources and network resources, thereby avoiding resource waste and improving the user experience of application services.

[0105] Reference below Figure 6 An embodiment of a resource monitoring device according to the present invention is described.

[0106] Figure 6 FIG. 4 is a schematic diagram showing a structure of a resource monitoring device according to some embodiments of the present invention. Figure 6 As shown, the resource monitoring device 60 of this embodiment includes: a monitoring module 610, which is configured to obtain monitoring information of a computing power network resource layer, a computing power network control layer and a computing power network service layer involved in the computing power network; a generation module 620, which is configured to generate computing network multi-factor monitoring information including a service identifier of a computing power network service provided by the computing power network service layer, a user identifier of a user using the computing power network service, and a computing power identifier of a computing power resource provided by the computing power network resource layer according to the monitoring information and the measurement result of the computing power resource layer.

[0107] In some embodiments, the computing power network resource layer includes infrastructure resources.

[0108] In some embodiments, the infrastructure resources include at least one of computing resources, network resources, and storage resources.

[0109] In some embodiments, the monitoring information of the computing power network control layer includes monitoring information of resource control functions.

[0110] In some embodiments, the monitoring information of the resource control function includes at least one of the duration of resource information collection and the access control of resource types.

[0111] In some embodiments, the monitoring information of the computing power network service layer includes monitoring information of the operating status of the computing power network service.

[0112] In some embodiments, the monitoring information of the operating status of the computing power network service includes at least one of the resource information processing status and the transaction process execution creation status.

[0113] In some embodiments, the monitoring module 610 is further configured to: send a subscription request to the monitored network resources in the computing power network resource layer; and obtain operation management and maintenance information reported by the monitored network resources.

[0114] In some embodiments, the subscription request includes a condition for triggering an alarm, and the condition for triggering the alarm includes at least one of a threshold and a threshold of a change amount within a preset time period.

[0115] In some embodiments, the monitoring module 610 is further configured to: in response to an alarm being triggered, obtain operation management and maintenance information reported by the monitored network resources.

[0116] In some embodiments, the monitoring indicators of the computing power network service layer include at least one of service alarm status indicators, average load, average response time, and maximum number of sessions.

[0117] In some embodiments, the monitoring parameters of the computing resources in the computing power network resource layer include at least one of an alarm status indication, an average CPU utilization rate, an available number of CPUs, an average GPU utilization rate, and an available number of GPUs.

[0118] In some embodiments, the monitoring parameters of the network resources in the computing power network resource layer include at least one of an alarm status indication, incoming available bandwidth, outgoing available bandwidth, average latency, jitter, and packet loss.

[0119] In some embodiments, the monitoring parameters of the storage resources in the computing power network resource layer include at least one of an alarm status indication, a random access memory capacity, an average utilization rate of the random access memory, and a used size of the random access memory.

[0120] In some embodiments, the monitoring parameters of the computing power network control layer include at least one of alarm status indication, computing resource monitoring duration, computing resource monitoring threshold, network resource monitoring duration, network resource monitoring threshold, computing resource monitoring threshold, storage resource monitoring duration, storage resource monitoring threshold, service monitoring duration, and service monitoring threshold.

[0121] In some embodiments, the computing power network resource layer includes network resources on the user side and network resources on the computing power resource pool side, and the monitoring device 60 also includes: a measurement module 630, which is configured to send a subscription request to the network resources on the user side so that the network resources on the user side initiate measurement of the network resources on the computing power resource pool side, wherein the request initiated by the network resources on the user side carries user side information and the destination network protocol address of the computing power resource pool; and receives the measurement results sent by the network resources on the user side.

[0122] In some embodiments, the measurement method of the network resources on the computing power resource pool side initiated by the user-side network resources is continuity measurement, performance measurement or frame delay measurement.

[0123] Figure 7 FIG. 2 shows a schematic diagram of a resource monitoring device according to another embodiment of the present invention. Figure 7 As shown, the resource monitoring device 70 of this embodiment includes: a memory 710 and a processor 720 coupled to the memory 710 , and the processor 720 is configured to execute the resource monitoring method in any one of the aforementioned embodiments based on instructions stored in the memory 710 .

[0124] The memory 710 may include, for example, a system memory, a fixed non-volatile storage medium, etc. The system memory may store, for example, an operating system, an application program, a boot loader, and other programs.

[0125] Figure 8 FIG. 2 shows a schematic diagram of a resource monitoring device according to some other embodiments of the present invention. Figure 8 As shown, the resource monitoring device 80 of this embodiment includes: a memory 810 and a processor 820, and may also include an input / output interface 830, a network interface 840, a storage interface 850, etc. These interfaces 830, 840, 850 and the memory 810 and the processor 820 may be connected, for example, via a bus 860. Among them, the input / output interface 830 provides a connection interface for input / output devices such as a display, a mouse, a keyboard, and a touch screen. The network interface 840 provides a connection interface for various networked devices. The storage interface 850 provides a connection interface for external storage devices such as SD cards and USB flash drives.

[0126] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein the program implements any of the aforementioned resource monitoring methods when executed by a processor.

[0127] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable non-transient storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0128] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0129] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0130] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0131] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A resource monitoring method, comprising: Obtain monitoring information of the computing network resource layer, computing network control layer, and computing network service layer involved in the computing network; Based on the monitoring information and the measurement results of the computing power resource layer, computing network multi-factor monitoring information is generated, including the service identifier of the computing power network service provided by the computing power network service layer, the identifier of the user using the computing power network service, and the computing power identifier of the computing power resource provided by the computing power network resource layer.

2. The monitoring method according to claim 1, wherein: The computing power network resource layer includes infrastructure resources, and the infrastructure resources include at least one of computing resources, network resources, and storage resources.

3. The monitoring method according to claim 1, wherein: The monitoring information of the computing power network control layer includes monitoring information of the resource control function, and the monitoring information of the resource control function includes at least one of the duration of resource information collection and access control of resource types.

4. The monitoring method according to claim 1, wherein: The monitoring information of the computing power network service layer includes monitoring information of the running status of the computing power network service, and the monitoring information of the running status of the computing power network service includes at least one of resource information processing status and transaction process execution creation status.

5. The monitoring method according to claim 1, wherein: Obtaining monitoring information of the computing power network resource layer includes: Sending a subscription request to the monitored network resources in the computing power network resource layer; Obtaining operation management and maintenance information reported by the monitored network resources.

6. The monitoring method according to claim 5, wherein: The subscription request includes an alarm triggering condition, and the alarm triggering condition includes at least one of a threshold and a threshold of a change amount within a preset time period.

7. The monitoring method according to claim 6, wherein: The obtaining of the operation management and maintenance information reported by the monitored network resource comprises: In response to the alarm being triggered, operation management and maintenance information reported by the monitored network resources is obtained.

8. The monitoring method according to claim 1, wherein: The monitoring indicators of the computing power network service layer include at least one of service alarm status indicators, average load, average response time, and maximum number of sessions.

9. The monitoring method according to claim 1, wherein: The monitoring parameters of the computing resources in the computing power network resource layer include at least one of an alarm status indication, an average central processing unit utilization rate, an available number of central processing units, an average graphics processing unit utilization rate, and an available number of graphics processing units.

10. The monitoring method according to claim 1, wherein: The monitoring parameters of the network resources in the computing power network resource layer include at least one of an alarm status indication, incoming available bandwidth, outgoing available bandwidth, average delay, jitter, and packet loss.

11. The monitoring method according to claim 1, wherein: The monitoring parameters of the storage resources in the computing power network resource layer include at least one of an alarm status indication, a random access memory capacity, an average utilization rate of the random access memory, and a used size of the random access memory.

12. The monitoring method according to claim 1, wherein: The monitoring parameters of the computing power network control layer include at least one of alarm status indication, computing resource monitoring duration, computing resource monitoring threshold, network resource monitoring duration, network resource monitoring threshold, computing resource monitoring threshold, storage resource monitoring duration, storage resource monitoring threshold, service monitoring duration, and service monitoring threshold.

13. The monitoring method according to any one of claims 1 to 12, wherein: The computing power network resource layer includes network resources on the user side and network resources on the computing power resource pool side, and the monitoring method further includes: Sending a subscription request to the network resource on the user side so that the network resource on the user side initiates measurement of the network resource on the computing power resource pool side, wherein the request initiated by the network resource on the user side carries user side information and a destination network protocol address of the computing power resource pool; Receive the measurement result sent by the network resource on the user side.

14. The monitoring method according to claim 13, wherein: The measurement method of the network resources on the computing power resource pool side initiated by the user side network resources is continuity measurement, performance measurement or frame delay measurement.

15. A resource monitoring device, comprising: A monitoring module is configured to obtain monitoring information of a computing network resource layer, a computing network control layer, and a computing network service layer involved in the computing network; The generation module is configured to generate computing network multi-factor monitoring information including the service identifier of the computing power network service provided by the computing power network service layer, the user identifier of the user using the computing power network service, and the computing power identifier of the computing power resource provided by the computing power network resource layer based on the monitoring information and the measurement results of the computing power resource layer.

16. A resource monitoring device, comprising: Memory; as well as A processor coupled to the memory, wherein the processor is configured to execute the resource monitoring method according to any one of claims 1 to 14 based on instructions stored in the memory.

17. A computing power operation management and maintenance module, comprising: A resource monitoring device as claimed in claim 15 or 16.

18. A resource monitoring system, comprising: The computing power operation management and maintenance module as claimed in claim 17; Computing network resource layer; Computing network control layer; as well as Computing power network service layer.

19. The monitoring system according to claim 18, wherein: The computing power network control layer is further configured to perform at least one of resource configuration, resource collection, and network scheduling on the computing power network resource layer based on the computing network multi-factor monitoring information.

20. The monitoring system of claim 18, wherein: The computing power network service layer is further configured to perform at least one of information analysis and processing, billing, and session execution on one or more services in the computing power network service layer.

21. The monitoring system of claim 18, wherein: The computing power operation management and maintenance module is further configured to send the computing network multi-factor monitoring information to the computing power network service layer; The computing power network service layer is further configured to analyze the computing network multi-factor monitoring information and send the analysis results to the computing power network control layer.

22. A computer-readable storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the resource monitoring method according to any one of claims 1 to 14 is implemented.

Images