CN108268355A - For the monitoring system and method for data center - Google Patents

Abstract

This application relates to a monitoring system and method for a data center. The monitoring system includes a monitoring resource layer, a monitoring data aggregation layer, a monitoring center, and a configuration center. The monitoring data aggregation layer has a multi-layer structure, and the monitoring resource layer includes multiple monitoring resource groups. , each monitoring resource group collects monitoring data according to the rules issued by the configuration center, and reports the monitoring data to the monitoring data aggregation layer; the monitoring data aggregation layer receives and sends the monitoring data sent by the monitoring resource layer, classifies the monitoring data, and The monitoring data is aggregated and processed; the monitoring center is used to store the monitoring data; the configuration center is used to configure the grouping information of the monitoring resource group, the grouping information of the aggregation nodes and the aggregation strategy of the monitoring data aggregation layer, and send them to the monitoring resource layer and Monitoring data aggregation layer.

Description

Monitoring system and method for data center

technical field

The present application generally relates to the field of computer and network technology, and more specifically, to a monitoring system and method for a data center.

Background technique

With the continuous improvement of social information technology and the rapid popularization of Internet technology, there are more and more computer equipment. It can be expected that in the near future, the number of equipment involved in ultra-large-scale data centers will reach hundreds of thousands or even millions. Therefore, , more and more data needs to be processed, and the demand for massive data processing in various fields is also increasing. Under the background that the storage space and computing power of a single machine can no longer meet people's demand for massive data processing, distributed computing and parallel computing began to develop and apply rapidly, and eventually developed into grid computing. The monitoring information of a large-scale distributed system is massive, and the monitoring resources are multi-level and multi-sourced. The dynamics and complexity of the big data platform bring many difficulties to the monitoring system of the big data platform.

Contents of the invention

According to one aspect of the present application, a monitoring system for a data center is provided. The monitoring system includes a monitoring resource layer, a monitoring data aggregation layer, a monitoring center, and a configuration center. The monitoring data aggregation layer has a multi-layer structure, and the monitoring resource layer Including multiple monitoring resource groups, each monitoring resource group collects monitoring data according to the rules issued by the configuration center, and reports the monitoring data to the monitoring data aggregation layer; the monitoring data aggregation layer receives and sends the monitoring data sent by the monitoring resource layer, and performs monitoring data Classify and aggregate each type of monitoring data; the monitoring center is used to store monitoring data; the configuration center is used to configure the grouping information of the monitoring resource group, the grouping information of the aggregation node and the aggregation strategy of the monitoring data aggregation layer, and download Send to the monitoring resource layer and the monitoring data aggregation layer.

According to another aspect of the present application, a monitoring method for a data center is provided. The monitoring method is executed in a monitoring system including a monitoring resource layer, a monitoring data aggregation layer, a monitoring center, and a configuration center, wherein the monitoring data The aggregation layer has a multi-layer structure. The monitoring method includes: the monitoring resource layer collects monitoring data and reports the monitoring data to the monitoring data aggregation layer. The monitoring resource layer includes multiple monitoring resource groups. Rules collect monitoring data; the monitoring data aggregation layer receives and sends the monitoring data sent by the monitoring resource layer, classifies the monitoring data, and aggregates each type of monitoring data; the monitoring center stores the monitoring data; and the configuration center configures the grouping information of the monitoring resource group 1. Monitor the aggregation node grouping information and aggregation strategy of the monitoring data aggregation layer, and issue them to the monitoring resource layer and the monitoring data aggregation layer. .

The monitoring system and method for a data center according to the embodiments of the present application provides a technical solution that can reduce the pressure on the monitoring center.

Description of drawings

The present application can be better understood according to the description of the embodiments of the present application in conjunction with the following drawings, wherein:

Fig. 1 shows a schematic structural diagram of a monitoring system for a data center according to an embodiment of the present application;

Fig. 2 shows a flow chart of a monitoring method for a data center according to an embodiment of the present application;

Fig. 3 shows the operation flowchart of the monitoring center according to one embodiment of the present application; and

Fig. 4 shows a schematic structural diagram of an information processing device that can implement one or more of the monitoring resource layer node, monitoring data convergence layer node, monitoring center, and configuration center of the present application.

Detailed ways

Features and exemplary embodiments of various aspects of the present application will be described in detail below. The following description covers numerous specific details in order to provide a thorough understanding of the application. It will be apparent, however, to one skilled in the art that the present application may be practiced without some of these specific details. The following description of the embodiments is only to provide a clearer understanding of the present application by showing examples of the present application. The present application is by no means limited to any specific configuration presented below, but covers any modifications, substitutions and improvements of related features, structures, operations, etc. without departing from the spirit of the present application.

Monitoring is an important part of the big data platform. With the significant increase of monitoring data, the current systems and methods can no longer meet the monitoring needs of the increasingly large data center, resulting in monitoring delays, partial loss of collected data, and resource consumption of monitoring center equipment. Problems such as high and low, so that effective monitoring of data cannot be achieved.

In addition, when the server cluster of the big data system statistically analyzes and summarizes relevant software and hardware information, it may be due to the large number of servers, the large variety of deployed software, and the complexity of related information indicators, which may lead to heavy workloads for abnormal alarms, monitoring and alarming. low efficiency etc.

This application adopts the idea of multi-layer monitoring structure, gathers corresponding resources in each layer, analyzes and processes the resources of each layer at the same time, greatly reduces the pressure on the monitoring center, and realizes effective monitoring of big data.

Fig. 1 shows a schematic structural diagram of a monitoring system 100 for a data center according to an embodiment of the present application.

In one embodiment, the system 100 may include a monitoring resource layer 102 , a monitoring data aggregation layer 101 , a monitoring center 103 and a configuration center 104 . In one embodiment, the monitoring data aggregation layer 101 has a multi-layer structure. In one embodiment, according to the scale of the data center and the amount to be monitored, the monitoring data aggregation layer can be divided into N layers according to business, region, network conditions, etc., where N is a positive integer, for example, as shown in Figure 1, the monitoring Data convergence layer 1 101_1, monitoring data convergence layer 2 101_2, monitoring data convergence layer 3 101_3..., and monitoring data convergence layer N 101_N. This application does not limit the number of monitoring data aggregation layers, but with the increase of data processing layers, additional monitoring delay will be added. Therefore, the number of layers needs to be set according to the business volume and business characteristics of the data center.

In one embodiment, the monitoring resource layer 102 may serve as the base layer of the system 100 . In one embodiment, the monitoring resource layer 102 may include multiple monitoring resource groups 1021 , and each monitoring resource group 1021 may collect monitoring data according to the rules issued by the configuration center 104 and report the monitoring data to the monitoring data aggregation layer 101 .

In one embodiment, at least one monitoring resource group 1021 among the plurality of monitoring resource groups 1021 may include resources that need to be monitored. Resources can be, for example, various attributes of software, hardware, or a combination thereof, for example, service attributes.

In an embodiment, a monitoring node may be deployed for each resource to be monitored, so as to monitor the resource and collect data. In one embodiment, a monitoring node may be an agent.

In one embodiment, the monitoring data aggregation layer 101 receives and sends the monitoring data sent by the monitoring resource layer 102, classifies the monitoring data, and performs aggregation processing on each type of monitoring data.

In one embodiment, the monitoring center 103 is used to store monitoring data.

In one embodiment, the configuration center 104 configures the grouping information of the monitoring resource group, the grouping information of the aggregation nodes and the aggregation strategy of the monitoring data aggregation layer, and sends them to the monitoring resource layer and the monitoring data aggregation layer.

In an embodiment, each monitoring node may report the collected data, for example, to the first monitoring data aggregation layer (eg, monitoring data aggregation layer one 101_1 ). In one embodiment, the main monitoring node can be selected from the monitoring nodes in each monitoring resource group according to predetermined rules, and other monitoring nodes gather the collected data to the main monitoring node, and the main monitoring node reports the data. In one embodiment, according to predetermined rules, the above two methods may be used for different resource monitoring groups to report to the monitoring data aggregation layer.

In one embodiment, the monitoring data aggregation layer 101 may include a first monitoring data aggregation layer and a second monitoring data aggregation layer, for example, a monitoring data aggregation layer one 101_1 and a monitoring data aggregation layer two 101_2 (not shown in FIG. 1 ) , the second monitoring data convergence layer may be an upper layer convergence layer of the first monitoring data convergence layer.

In one embodiment, the first monitoring data aggregation layer receives and sends the monitoring data sent by the monitoring resource layer 102, and is used to aggregate the monitoring data to obtain the first monitoring information, and send the first monitoring information to the second monitoring data aggregation layer .

In one embodiment, the second monitoring data aggregation layer receives the first monitoring information from the first monitoring data aggregation layer, aggregates the first monitoring information to obtain the second monitoring information, and sends the second monitoring information to the monitoring center 103 Or the upper layer convergence layer of the second monitoring data convergence layer (for example, monitoring data convergence layer two 101_3).

In one embodiment, the monitoring center 103 can be responsible for one or more of the storage and analysis of monitoring information, the analysis of automatic system fault response mechanism actions, the delivery of automatic fault handling actions, and the sending of alarm information, for example. .

In one embodiment, the monitoring center 103 may include a monitoring data center 1031 . In one embodiment, the monitoring data center 1031 can be used to store monitoring data. In one embodiment, the monitoring data center 1031 stores all monitoring data. In one embodiment, part of the monitoring data is stored in the monitoring data center 1031 .

In one embodiment, the monitoring center 103 may include a monitoring data analysis center 1032 . In one embodiment, the monitoring data analysis center 1032 can be used to analyze the monitoring data. In one embodiment, the monitoring data analysis center 1032 can perform one or more of the following items: preliminary analysis and determination of fault information, system performance data analysis, service performance status data analysis, resource trend analysis, equipment carrying capacity analysis, Analyze resource expansion requirements and generate various monitoring-related reports.

In one embodiment, the monitoring center 103 may include a monitoring notification and alarm center 1033 . In one embodiment, the monitoring notification and alarm center 1033 may be responsible for sending notification and alarm information of the monitoring system. In one embodiment, the monitoring notification and alarm center 1033 may send corresponding notification and alarm information to corresponding personnel according to corresponding configurations.

In one embodiment, the monitoring center 103 may include a monitoring custom self-healing analysis center 1034 . In one embodiment, the monitoring self-healing analysis center 1034 can be used to further analyze the failures initially analyzed by the monitoring data analysis center 1032, and generate corresponding solutions for troubleshooting (for example, equipment crashes, failures at the equipment system level, business failure, etc.) instructions.

In one embodiment, the monitoring center 103 may include a monitoring custom action delivery center 1035 . In one embodiment, the monitoring custom action delivery center 1035 can deliver the instructions generated by the monitoring custom self-healing analysis center 1034 to corresponding device nodes to solve the fault. In one embodiment, the issued instructions may include but not limited to: restart the system, restart the device, restart the business, power off the device or re-power it to hard restart (in the case of connecting to the corresponding power management device), etc. .

In one embodiment, the monitoring data aggregation layer may include multiple data aggregation groups 1011, and each data aggregation group operates according to the rules issued by the configuration center. In one embodiment, the data aggregation group 1011 may include multiple nodes. In one embodiment, a certain node may be selected among multiple nodes in the data aggregation group 1011 as the main aggregation node for sending monitoring information.

In one embodiment, the monitoring data aggregation layer can classify the monitoring data, specifically including: classifying the monitoring data into real-time monitoring information, non-real-time monitoring information and non-monitoring information according to the real-time monitoring attributes and monitoring effectiveness of the monitoring data.

In one embodiment, the monitoring data aggregation layer aggregates each type of monitoring data, specifically including: if the received monitoring data is real-time monitoring information, sending real-time monitoring information in real time; if the received monitoring data is non-real-time monitoring information, sending Non-real-time monitoring information is sent to the monitoring center asynchronously; if the received monitoring data is non-monitoring information, the non-monitoring information is discarded. As a result, the response speed can be improved and the pressure on the monitoring center can be reduced.

In one embodiment, the real-time information has the highest priority, and the real-time information can be sent to the monitoring center 103 or a higher-level monitoring data aggregation layer by the main aggregation node of the data aggregation group 1011 in real time. In one embodiment, the main aggregation node may asynchronously send the non-real-time information directly to the monitoring center 103 according to resource usage, network traffic, and the like. In one embodiment, non-monitoring information (for example, including invalid information or information that is no longer needed) can be directly discarded by each node or discarded by the main sink node. As a result, the pressure on the monitoring center 103 and higher-level monitoring data aggregation layers will be relieved.

In one embodiment, the configuration center 104 can be used to store various configuration policies and issue them to corresponding nodes.

In one embodiment, the configuration strategy may include: monitoring the grouping information of the resource layer 102, the main monitoring node selection mechanism of the monitoring resource layer 102, the monitoring strategy, the aggregation strategy of the monitoring data aggregation layer, and the main aggregation node of the monitoring data aggregation layer Selection mechanism.

In one embodiment, configuration center 104 may include monitoring group configuration 1041 . In one embodiment, the monitoring group configuration 1041 may store group information configurations of monitoring resources. In other words, the monitoring group configuration 1041 may store information related to monitored resources, including but not limited to the monitoring resource group to which each resource belongs. In one embodiment, the configuration center 104 can group monitoring resources according to business information, physical area, business logic, network area, and so on. In one embodiment, since a monitoring node (for example, an agent) is deployed for each resource, after the monitoring resource group to which each resource belongs is configured, the monitoring node also has a corresponding group.

In one embodiment, configuration center 104 may include aggregation group configuration 1042 . In one embodiment, the aggregation group configuration 1042 can store the node group information configuration of the monitoring data aggregation layer. In other words, the aggregation group configuration 1042 may store information related to the nodes monitoring the data aggregation layer, including but not limited to the data aggregation group to which each node belongs and the level to which the data aggregation group belongs.

In one embodiment, configuration center 104 may include monitoring policy configuration 1043 . In one embodiment, monitoring policy configuration 1043 may store policy configurations related to monitoring. In one embodiment, the policy configuration includes but is not limited to: the information to be collected, the frequency of collecting information, the method of collecting information, and which node of the monitoring data aggregation layer the monitoring resource layer should report the information to, etc. In an embodiment, the policy configuration may also include a monitoring and detection policy for resources in the same group that the master monitoring node needs to actively initiate, for example, network delay checks in the same group, node survivability checks in the same group, and the like.

In one embodiment, configuration center 104 may include aggregation policy configuration 1044 . In one embodiment, the aggregation policy configuration 1044 can store the aggregation policy configuration of the monitoring data aggregation layer. In one embodiment, the aggregation policy configuration may include the monitoring data aggregation layer's preliminary analysis strategy for the aggregated information, information classification strategy (dividing information into real-time information, non-real-time information, non-monitoring information, etc.), main aggregation node The upper-level receiving node configuration (for example, which node in which data aggregation group receives information), the non-real-time monitoring information asynchronous upload monitoring center strategy (for example, asynchronous upload timing, method, etc.), etc.

In one embodiment, the configuration center 104 may include a monitoring group/aggregation group master node selection mechanism configuration 1045 . In one embodiment, the monitoring group/convergence group master node selection mechanism configuration 1045 may store the monitoring group master monitoring node/convergence group master sink node selection mechanism configuration. Due to the complex environment and different resources of large data centers, the master node selection strategy of each monitoring group/aggregation group is limited by the corresponding node resources, network resources, input and output (I/O) resources, etc. and corresponding monitoring strategies.

In an embodiment, each monitoring group/aggregation group can set a corresponding selection mechanism according to its own business characteristics. For example, in a monitoring resource group with heavy I/O resource pressure, it may be set to preferentially select a node with less I/O resource pressure as the main monitoring node. For example, in a monitoring resource group that consumes a large amount of processing resources (for example, a processor), a node with a lower usage rate of processing resources may be set to be the primary monitoring node first. In a more complex environment, the strategy for selecting the master node may need to combine multiple factors.

For example, the above strategies may vary depending on the specific business, for example, the strategies corresponding to the analysis business and business business are different. For example, in one embodiment, for analysis services, the utilization rate of processing resources at a specific time point or time period may not be considered, but for business services, this attribute needs to be considered.

In one embodiment, for various businesses, the attributes to be considered in corresponding different policies include but not limited to one or more of the following: I/O resource usage, processing resource usage, network traffic , number of links, etc. In an embodiment, some services may not need to consider any of the above attributes, while other services may need to consider all attributes.

In an embodiment, the considered attribute may be real-time data or non-real-time historical data.

In one embodiment, the configuration center 104 may include a configuration policy distribution center 1046 . In one embodiment, the configuration policy delivery center 1046 can be responsible for delivering the configuration policy of the monitoring resource layer nodes/monitoring data convergence layer nodes. 1044. The policy configuration of one or more of the monitoring group/aggregation group master node selection mechanism configurations in 1045 is delivered to corresponding nodes.

Fig. 2 shows a flow chart 200 of a monitoring method for a data center according to an embodiment of the present application. The monitoring method can be implemented in a monitoring system including a monitoring resource layer, a monitoring data aggregation layer, a monitoring center and a configuration center, wherein the monitoring data aggregation layer has a multi-layer structure.

At step 201, the configuration center configures the grouping information of the monitoring resource group, the grouping information of the aggregation node and the aggregation strategy of the monitoring data aggregation layer, and delivers them to the monitoring resource layer and the monitoring data aggregation layer.

At step 202, the monitoring resource layer collects monitoring data and reports the monitoring data to the monitoring data aggregation layer. The monitoring resource layer includes multiple monitoring resource groups, and each monitoring resource group collects monitoring data according to the rules issued by the configuration center.

At step 203, the monitoring data aggregation layer receives and sends the monitoring data sent by the monitoring resource layer, classifies the monitoring data, and aggregates each type of monitoring data.

At step 204, the monitoring center stores the monitoring data.

In an embodiment, the monitoring resource layer may include multiple monitoring resource groups, and each monitoring resource group may include one or more nodes.

In one embodiment, the monitoring data aggregation layer includes at least a first monitoring data aggregation layer and a second monitoring data aggregation layer, and the second monitoring data aggregation layer is an upper aggregation layer of the first monitoring data aggregation layer. The method 200 may include: A monitoring data aggregation layer receives and sends monitoring data sent by the monitoring resource layer, and is used to aggregate the monitoring data to obtain first monitoring information, and sends the first monitoring information to the second monitoring data aggregation layer; the second monitoring data aggregation layer receives from The first monitoring data aggregation layer receives the first monitoring information, aggregates the first monitoring information to obtain second monitoring information, and sends the second monitoring information to the monitoring center or the upper aggregation layer of the second monitoring data aggregation layer.

In one embodiment, in step 203, the monitoring data aggregation layer classifies the monitoring data may include: according to the real-time monitoring attributes and monitoring effectiveness of the monitoring data, the monitoring data is divided into real-time monitoring information, non-real-time monitoring information and non-monitoring information .

In one embodiment, in step 203, the aggregation processing of each type of monitoring data by the monitoring data aggregation layer in step 203 may include: if the received monitoring data is real-time monitoring information, sending real-time monitoring information in real time; if the received monitoring data is non-real-time monitoring information , to asynchronously send non-real-time monitoring information to the monitoring center; if the received monitoring data is non-monitoring information, discard the non-monitoring information.

In one embodiment, the method 200 further includes configuring the following items by the configuration center: the main monitoring node selection mechanism of the monitoring resource layer, the monitoring strategy, the aggregation strategy of the monitoring data aggregation layer, and the main aggregation node selection mechanism of the monitoring data aggregation layer . For example, policies related to monitoring are configured in the configuration center. As above, the configuration center delivers the policies to nodes in the monitoring resource layer. For example, the aggregation policy configuration of the monitoring data aggregation layer is configured in the configuration center. As above, the configuration center sends the aggregation policy configuration to the nodes in each monitoring data aggregation layer.

In one embodiment, the configuration center can configure the following items: the main monitoring node selection mechanism of the monitoring resource layer, the monitoring strategy, the aggregation strategy of the monitoring data aggregation layer, and the main aggregation node selection mechanism of the monitoring data aggregation layer.

In an embodiment, the monitoring data aggregation layer may include multiple data aggregation groups, and the method 200 may further include: each data aggregation group performs an operation according to a rule issued by the configuration center.

In an embodiment, the method 200 may further include: selecting a main aggregation node from multiple nodes in the monitoring data aggregation group to send monitoring information.

In one embodiment, each node of the monitoring resource group in the monitoring resource layer summarizes the collected data to the main monitoring node of the corresponding monitoring resource group, and the main monitoring node sends the collected data upward to the monitoring data convergence layer . In one embodiment, each node of the monitoring resource group in the monitoring resource layer directly sends the collected data upward to the monitoring data aggregation layer.

In one embodiment, the nodes at the monitoring data aggregation layer can classify the data received from the monitoring resource layer or lower-level monitoring data aggregation layer, and then aggregate the corresponding data to the main aggregation node of the data aggregation group. In an embodiment, the main aggregation node of the monitoring data aggregation layer may classify the data after aggregation to the data of other nodes in the data aggregation group.

Fig. 3 shows an operation flowchart 300 of the monitoring center according to an embodiment of the present application.

In one embodiment, at 301, the monitoring data aggregation layer 101 sends the collected real-time or non-real-time data to the monitoring center 103 in a synchronous or asynchronous manner, and the monitoring center 103 stores the data in the monitoring data center 1031.

In one embodiment, at 302, the monitoring data analysis center 1032 reads the data of the monitoring data center 1031 for analysis.

In one embodiment, at 303 , the monitoring data analysis center 1032 stores the analysis results in the monitoring data center 1031 .

In one embodiment, the monitoring data analysis center 1032 analyzes the data read from the monitoring data center 1031, and if a fault is found, at 304, the configuration center 104 will be notified to update the configuration information of the node related to the faulty node.

In one embodiment, the monitoring data analysis center 1032 performs preliminary analysis and processing on the fault.

In one embodiment, at 305, if the fault is not within the scope of the self-healing strategy, the monitoring data analysis center 1032 notifies the monitoring notification and alarm center 1033 to send corresponding notification and alarm information to corresponding personnel, so as to perform manual processing.

In one embodiment, at 306, if the fault is within the scope of the self-healing strategy, the monitoring data analysis center 1032 sends the fault information to the monitoring self-healing analysis center 1034 .

In one embodiment, at 307 , the monitoring self-healing analysis center 1034 analyzes the fault information, generates a corresponding self-healing instruction, and sends the self-healing instruction to the monitoring custom action issuing center 1035 .

In one embodiment, the monitoring custom action issuing center 1035 issues the corresponding self-healing operation instruction to the corresponding node to perform the self-healing operation. For example, at 309, the monitoring custom action issuing center 1035 issues the self-healing operation instruction for the monitoring resource node to the corresponding monitoring resource node to perform the self-healing operation. For example, at 309, the monitoring custom action issuing center 1035 issues the self-healing operation instruction for the monitoring data aggregation node to the corresponding monitoring data aggregation node to perform the self-healing operation.

In one embodiment, if the self-healing operation of the faulty node is successful at 310 , then at 311 , the configuration center 104 is notified to deliver the policy of the relevant node, so as to bring the corresponding node into the monitoring range again.

In one embodiment, if the self-healing operation of the faulty node fails at 312, then at 313, the notification monitoring notification and alarm center 1033 sends a corresponding notification alarm to corresponding personnel for manual processing.

Figure 4 shows a schematic structural diagram of an information processing device 400, one or more of the monitoring resource layer nodes, monitoring data aggregation layer nodes, monitoring center, and configuration center in the embodiment of the present application can be implemented by the information processing device 400 to achieve. As shown in FIG. 4, the device 400 may include one or more of the following components: a processor 420, a memory 430, a power supply component 440, an input/output (I/O) interface 460, and a communication interface 480. These components may, for example, Communicatively connected via bus 410 .

The processor 420 controls the operations of the device 400 as a whole, such as those associated with data communication and computational processing, among others. The processor 420 may include one or more processing cores, and is capable of executing instructions to implement all or part of the steps of the methods described in this application. Processor 420 may include various devices with processing capabilities, including but not limited to general purpose processors, special purpose processors, microprocessors, microcontrollers, graphics processing units (GPUs), digital signal processors (DSPs), application specific integrated circuit (ASIC), programmable logic device (PLD), field programmable logic gate array (FPGA), etc. The processor 420 may include or be in communication with a cache 425 to increase data access speed.

The memory 430 is configured to store various types of instructions and/or data to support the operation of the device 400 . Examples of data include instructions, data, etc. for any application or method operating on device 400 . Memory 430 may be implemented by any type or combination of volatile or non-volatile storage devices. Memory 430 may include semiconductor memory such as random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), read only memory (ROM), programmable read only memory (PROM), erasable In addition to programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), flash memory, etc. Memory 430 may also include, for example, any memory using paper, magnetic, and/or optical media, such as paper tape, hard disk, magnetic tape, floppy disk, magneto-optical disk (MO), CD, DVD, Blue-ray, and the like.

The power supply component 440 provides power to various components of the device 400 . Power component 440 may include an internal battery and/or an external power interface, and may include a power management system and other components associated with generating, managing, and distributing power for device 400 .

I/O interface 460 provides an interface that enables a user to interact with device 400 . For example, the I/O interface 460 may include interfaces based on technologies such as PS/2, RS-232, USB, FireWire, Lightening, VGA, HDMI, DisplayPort, etc., enabling users to Peripheral devices such as a microphone, a speaker, a display, a camera, and a projection port interact with the device 400 .

The communication interface 480 is configured to enable the device 400 to communicate with other devices in a wired or wireless manner. The device 400 can access wireless networks based on one or more communication standards through the communication interface 480, such as Wi-Fi, 2G, 3G, and 4G communication networks. In an exemplary embodiment, the communication interface 480 may also receive a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. Exemplary communication interfaces 480 may include interfaces based on near field communication (NFC) technology, radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra wideband (UWB) technology, Bluetooth (BT) technology and other communication methods.

The functional blocks shown in the structural block diagrams described above may be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic circuit, an application specific integrated circuit (ASIC), suitable firmware, a plug-in, a function card, or the like. When implemented in software, the elements of the invention are the programs or code segments employed to perform the required tasks. Programs or code segments can be stored in machine-readable media, or transmitted over transmission media or communication links by data signals carried in carrier waves. "Machine-readable medium" may include any medium that can store or transmit information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, and the like. Code segments may be downloaded via a computer network such as the Internet, an Intranet, or the like.

"One embodiment" is mentioned above, but it should be understood that the features mentioned in each embodiment are not necessarily only applicable to this embodiment, but may be used in other embodiments or used in combination with other embodiments.

The application has been described above with reference to the specific embodiments of the application, but those skilled in the art understand that the implementation methods mentioned herein are all statements of the application, and the specific embodiments listed are only application examples of the application. It does not represent that the present application is limited to such application examples, and various modifications, combinations and changes can be made to these specific embodiments without departing from the spirit and scope of the present application defined by the appended claims or their equivalents.

Claims (12)

1. a kind of monitoring system for data center, which is characterized in that the monitoring system includes monitoring resource layer, monitoring number According to convergence-level, monitoring center and configuration center, the monitoring data convergence-level is multilayered structure,

The monitoring resource layer includes multiple monitoring resource groups, what each monitoring resource group was issued according to the configuration center Rule acquisition monitoring data, and the monitoring data is reported to the monitoring data convergence-level；

The monitoring data convergence-level picks the monitoring data that the monitoring resource layer is sent, and the monitoring data is divided Class, and convergence processing is carried out to every class monitoring data；

The monitoring center, for storing the monitoring data；

The configuration center, for the convergence section of the grouping information of the monitoring resource group, the monitoring data convergence-level to be configured Point grouping information and convergence strategy, and it is handed down to the monitoring resource layer and the monitoring data convergence-level.

2. monitoring system as described in claim 1, which is characterized in that the monitoring data convergence-level includes at least the first monitoring Data convergence-level and the second monitoring data convergence-level, the second monitoring data convergence-level are the first monitoring data convergence-level Upper strata convergence-level；

The first monitoring data convergence-level picks the monitoring data that the monitoring resource layer is sent, for the monitoring data It is converged to obtain the first monitoring information, and first monitoring information is sent to the second monitoring data convergence-level；

The second monitoring data convergence-level receives first monitoring information, to institute from the first monitoring data convergence-level The first monitoring information is stated to be converged to obtain the second monitoring information, and by second monitoring information be sent to monitoring center or The upper strata convergence-level of second monitoring data convergence-level.

3. monitoring system as claimed in claim 1 or 2, which is characterized in that the monitoring data convergence-level is to the monitoring number According to classifying, specifically include：

According to the real time monitoring attribute of the monitoring data and effective monitoring, the monitoring data is divided into real time monitoring letter Breath, non real-time monitoring information and non-supervised information.

4. monitoring system as claimed in claim 3, which is characterized in that the monitoring data convergence-level to every class monitoring data into Row convergence processing, specifically includes：

If the monitoring data received is real time monitoring information, the real time monitoring information is sent in real time；

If the monitoring data received is non real-time monitoring information, will be in the non real-time monitoring information asynchronous transmission to the monitoring The heart；

If the monitoring data received is non-supervised information, the non-supervised information is abandoned.

5. monitoring system as described in claim 1, which is characterized in that the configuration center is additionally operable to be configured：

The main monitoring node selection mechanism of the monitoring resource layer, the convergence plan of tactful, the described monitoring data convergence-level of monitoring Slightly, the main aggregation node selection mechanism of the monitoring data convergence-level.

6. monitoring system as described in claim 1, which is characterized in that the monitoring data convergence-level is converged including multiple data Group, each data convergence group are operated according to the rule that the configuration center issues.

7. a kind of monitoring method for data center, which is characterized in that the monitoring method is including monitoring resource layer, monitoring It is performed in the monitoring system of data convergence-level, monitoring center and configuration center, wherein, the monitoring data convergence-level is multilayer Structure, the monitoring method include：

The aggregation node grouping of the grouping information, the monitoring data convergence-level of the configuration center configuration monitoring resource group Information and convergence strategy, and it is handed down to the monitoring resource layer and the monitoring data convergence-level；

The monitoring data is simultaneously reported to the monitoring data convergence-level, the prison by the monitoring resource layer acquisition monitoring data It controls resource layer and includes multiple monitoring resource groups, the rule acquisition prison that each monitoring resource group is issued according to the configuration center Control data；

The monitoring data convergence-level picks the monitoring data that the monitoring resource layer is sent, and the monitoring data is divided Class, and convergence processing is carried out to every class monitoring data；And

The monitoring center stores the monitoring data.

8. monitoring method as claimed in claim 7, which is characterized in that the monitoring data convergence-level includes at least the first monitoring Data convergence-level and the second monitoring data convergence-level, the second monitoring data convergence-level are the first monitoring data convergence-level Upper strata convergence-level, the method includes：

The first monitoring data convergence-level picks the monitoring data that the monitoring resource layer is sent, for the monitoring data It is converged to obtain the first monitoring information, and first monitoring information is sent to the second monitoring data convergence-level；

The second monitoring data convergence-level receives first monitoring information from the first monitoring data convergence-level, to described First monitoring information is converged to obtain the second monitoring information, and second monitoring information is sent to monitoring center or The upper strata convergence-level of two monitoring data convergence-levels.

9. monitoring method as claimed in claim 7 or 8, which is characterized in that the monitoring data convergence-level is to the monitoring number Include according to classification is carried out：

According to the real time monitoring attribute of the monitoring data and effective monitoring, the monitoring data is divided into real time monitoring letter Breath, non real-time monitoring information and non-supervised information.

10. monitoring method as claimed in claim 9, which is characterized in that the monitoring data convergence-level is to every class monitoring data Convergence processing is carried out to include：

If the monitoring data received is real time monitoring information, the real time monitoring information is sent in real time；

If the monitoring data received is non real-time monitoring information, will be in the non real-time monitoring information asynchronous transmission to the monitoring The heart；

If the monitoring data received is non-supervised information, the non-supervised information is abandoned.

11. monitoring method as claimed in claim 7, which is characterized in that the configuration center is also configured following item：Institute State the convergence strategy, described of the main monitoring node selection mechanism of monitoring resource layer, tactful, the described monitoring data convergence-level of monitoring The main aggregation node selection mechanism of monitoring data convergence-level.

12. monitoring method as claimed in claim 7, which is characterized in that the monitoring data convergence-level is converged including multiple data Poly group, the monitoring method include：Each data convergence group is operated according to the rule that the configuration center issues.