WO2015172508A1

WO2015172508A1 - Performance data processing method and device

Info

Publication number: WO2015172508A1
Application number: PCT/CN2014/088671
Authority: WO
Inventors: 潘友才
Original assignee: 中兴通讯股份有限公司
Priority date: 2014-05-16
Filing date: 2014-10-15
Publication date: 2015-11-19
Also published as: CN105101281A

Abstract

A performance data processing method and device. The method comprises: collecting performance data statistical values of one or more measurement tasks; determining whether the performance data statistical values exceed a predetermined threshold; and if a determination result is Yes, performing overload control processing on the one or more measurement tasks. Therefore, the problem of a large delay of performance data reporting in the related art is solved, thereby achieving the effect of avoiding an overload operation of a performance statistics collection module to ensure real-time reporting of performance data.

Description

Performance data processing method and device

Technical field

The present invention relates to the field of communications, and in particular to a method and apparatus for processing performance data.

Background technique

In the telecom network management system, the main function of the performance statistics module is to perform performance monitoring on the network, network unit or device, collect relevant statistical data, evaluate the effectiveness of the network and network elements, report the status of the telecommunication equipment, support network planning and Network analysis to improve network performance and efficiency and improve operators' operational and service capabilities.

In order to understand the operation of equipment and network in a timely manner, operators have high requirements on the real-time performance data.

The network management system of the equipment provider usually provides not only the types of measurements required by the operators, but also the types of measurements required for the maintenance of their own equipment and the positioning of service problems. As the content of the telecommunication services continues to increase and the telecommunication equipments continue to be upgraded, the provided The type of measurement is also increasing. The processing efficiency of the network management server is limited. Too many measurement tasks (performance data collection tasks created for one measurement type) cause the performance statistics module to be overloaded, causing delays in performance data collection and reporting, which cannot meet the carrier's requirements. The need for performance data.

Therefore, in the related art, there is a problem that the performance data reporting delay is long.

Summary of the invention

The invention provides a performance data processing method and device, so as to at least solve the problem that the performance data reporting delay is long in the related art.

According to an aspect of the present invention, a performance data processing method includes: collecting performance data statistics of one or more measurement tasks; determining whether the performance data statistics exceeds a predetermined threshold; and determining that the result is yes And performing overload control processing on the one or more measurement tasks.

Preferably, in the case that the performance data statistics value is the total time of the performance data collection, collecting the performance data statistics of the one or more measurement tasks comprises: acquiring data collection time of each measurement task; The measurement task is summed to obtain the statistical value of the performance data.

Preferably, acquiring the data collection time of each measurement task comprises: acquiring a data packet processing time of the measurement task according to the following formula: a data packet processing time of the measurement task = a single data packet processing time of the measurement task * a data packet of the measurement task The data acquisition time of the measurement task is obtained according to the following formula: the data collection time of the measurement task=the data packet processing time+the storage time of the performance data corresponding to the measurement task.

Preferably, determining whether the performance data statistic exceeds the predetermined threshold comprises: determining whether the number of times the performance data statistic exceeds the predetermined threshold reaches a predetermined number of times; and if the determination result is YES, determining the one Or multiple measurement tasks are overloaded.

Preferably, performing overload control processing on the one or more measurement tasks comprises: classifying the one or more measurement tasks; and performing overload control on the one or more measurement tasks according to a level corresponding to the measurement task deal with.

According to another aspect of the present invention, a performance data processing apparatus includes: an acquisition module configured to collect performance data statistics of one or more measurement tasks; and a determination module configured to determine whether the performance data statistics are Exceeding a predetermined threshold; the processing module is configured to perform an overload control process on the one or more measurement tasks if the determination result of the determination module is YES.

Preferably, the acquiring module includes: an acquiring unit, configured to acquire a data collection time of each measurement task in a case where the performance data statistics value is a total time of performance data acquisition; a summation unit, set to measure all The task sums the statistical data of the performance data.

Preferably, the obtaining unit comprises: a first acquiring subunit, configured to acquire a data packet processing time of the measurement task according to the following formula: a data packet processing time of the measurement task = a single data packet processing time of the measurement task * the measurement task The second acquisition subunit is configured to acquire the data collection time of the measurement task according to the following formula: the data collection time of the measurement task=the data packet processing time+the performance data corresponding to the measurement task Storage time.

Preferably, the determining module includes: a determining unit, configured to determine whether the number of times the performance data statistical value exceeds the predetermined threshold exceeds a predetermined number of times; and the determining unit is configured to be a case that the determining result of the determining unit is yes Next, determining that the one or more measurement tasks are overloaded.

Preferably, the processing module includes: a dividing unit configured to divide the level of the one or more measurement tasks; and a processing unit configured to perform overload control on the one or more measurement tasks according to a level corresponding to the measurement task deal with.

According to the present invention, the performance data statistics of one or more measurement tasks are collected; whether the statistical value of the performance data exceeds a predetermined threshold is determined; if the determination result is yes, the one or more measurement tasks are performed. The load control process solves the problem that the performance data reporting delay is long in the related art, thereby achieving the overload operation of the performance statistics module to ensure the real-time reporting of performance data.

DRAWINGS

The drawings described herein are intended to provide a further understanding of the invention, and are intended to be a part of the invention. In the drawing:

1 is a flowchart of a performance data processing method according to an embodiment of the present invention;

2 is a block diagram showing the structure of a performance data processing apparatus according to an embodiment of the present invention;

3 is a block diagram showing a preferred structure of the acquisition module 22 in the performance data processing apparatus according to an embodiment of the present invention;

4 is a block diagram showing a preferred structure of the obtaining unit 32 in the acquisition module 22 in the performance data processing apparatus according to an embodiment of the invention;

FIG. 5 is a block diagram showing a preferred structure of the determining module 24 in the performance data processing apparatus according to an embodiment of the present invention; FIG.

6 is a block diagram showing a preferred structure of a processing module 26 in a performance data processing apparatus according to an embodiment of the present invention;

7 is a schematic structural diagram of a performance statistical overload analysis and control system according to an embodiment of the present invention;

8 is a flow chart of a method for analyzing and controlling overload of a performance statistics module according to an embodiment of the present invention.

detailed description

The invention will be described in detail below with reference to the drawings in conjunction with the embodiments. It should be noted that the embodiments in the present application and the features in the embodiments may be combined with each other without conflict.

In this embodiment, a performance data processing method is provided. FIG. 1 is a flowchart of a performance data processing method according to an embodiment of the present invention. As shown in FIG. 1, the process includes the following steps:

Step S102, collecting performance data statistics values of one or more measurement tasks;

Step S104, determining whether the statistical value of the performance data exceeds a predetermined threshold;

In step S106, if the determination result is YES, the overload control process is performed on one or more measurement tasks.

Through the foregoing steps, determining whether the one or more measurement tasks are overloaded to perform load control processing according to whether the performance value of the performance data of the measurement task exceeds a predetermined threshold, and whether the performance data of the measurement task is not compared with the related art The overload analysis processing not only solves the problem that the performance data reporting delay is long in the related technology, but also avoids the overload operation of the performance statistics module to ensure the real-time reporting of the performance data.

When the performance data statistics value is the total time of the performance data collection, the performance data statistics of one or more measurement tasks may be collected by acquiring the data collection time of each measurement task; summing performance of all measurement tasks. Statistical value of the data. The data collection time of each measurement task may be obtained by first obtaining the data packet processing time of the measurement task according to the following formula: the data packet processing time of the measurement task = the single data packet processing time of the measurement task * the measurement task The number of data packets; the data acquisition time of the measurement task is obtained according to the following formula: the data acquisition time of the measurement task = the data packet processing time + the storage time of the performance data corresponding to the measurement task.

In order to ensure whether the one or more measurement tasks are actually in an overload state, when determining whether the performance data statistics exceeds a predetermined threshold, it may first determine whether the number of times the performance data statistics exceeds a predetermined threshold reaches a predetermined number of times, the predetermined number of times may be based on Depending on the needs, for example, it can be set to 3 times; if the result of the determination is YES, it is determined that one or more measurement tasks are overloaded.

In order to satisfy different load control processes for different measurement tasks, the user may first classify one or more measurement tasks; perform overload control processing on one or more measurement tasks according to the level corresponding to the measurement tasks. For example, a measurement task that is of more interest to the user can be set to a higher level, and a measurement task that is less of a concern can be set to a normal level.

In the embodiment, a performance data processing device is also provided, which is used to implement the above-mentioned embodiments and preferred embodiments, and has not been described again. As used below, the term "module" may implement a combination of software and/or hardware of a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware, or a combination of software and hardware, is also possible and contemplated.

2 is a block diagram showing the structure of a performance data processing apparatus according to an embodiment of the present invention. As shown in FIG. 2, the apparatus includes an acquisition module 22, a determination module 24, and a processing module 26. The apparatus will be described below.

The collecting module 22 is configured to collect performance statistics of one or more measurement tasks; the determining module 24 is connected to the collecting module 22, and is configured to determine whether the statistical value of the performance data exceeds a predetermined threshold; and the processing module 26 Connected to the above-mentioned judging module 24, it is set to perform overload control processing on one or more measurement tasks when the judgment result of the judging module is YES.

FIG. 3 is a block diagram showing a preferred structure of the acquisition module 22 in the performance data processing apparatus according to the embodiment of the present invention. As shown in FIG. 3, the acquisition module 22 includes an acquisition unit 32 and a summation unit 34. Description.

The obtaining unit 32 is configured to acquire the data collection time of each measurement task if the performance data statistics value is the total time of the performance data collection; the summation unit 34 is connected to the obtaining unit 32, and is configured to And get performance data statistics.

FIG. 4 is a block diagram showing a preferred structure of the obtaining unit 32 in the acquisition module 22 in the performance data processing apparatus according to the embodiment of the present invention. As shown in FIG. 4, the obtaining unit 32 includes a first obtaining subunit 42 and a second obtaining subunit 44. The acquisition unit 32 will be described below.

The first obtaining sub-unit 42 is configured to acquire the data packet processing time of the measurement task according to the following formula: the data packet processing time of the measurement task = the single data packet processing time of the measurement task * the number of data packets of the measurement task; the second acquisition The subunit 44 is connected to the first obtaining subunit 42, and is configured to acquire the data collection time of the measurement task according to the following formula: the data acquisition time of the measurement task=the data packet processing time+the storage time of the performance data corresponding to the measurement task.

FIG. 5 is a block diagram showing a preferred structure of the determining module 24 in the performance data processing apparatus according to the embodiment of the present invention. As shown in FIG. 5, the determining module 24 includes a determining unit 52 and a determining unit 54, and the determining module 24 is described below. .

The determining unit 52 is configured to determine whether the number of times the performance data statistical value exceeds the predetermined threshold exceeds a predetermined number of times; the determining unit 54 is connected to the determining unit 52, and is configured to determine one or more if the determining result of the determining unit is yes One measurement task is overloaded.

FIG. 6 is a block diagram showing a preferred structure of the processing module 26 in the performance data processing apparatus according to the embodiment of the present invention. As shown in FIG. 6, the processing module 26 includes a dividing unit 62 and a processing unit 64, and the processing module 26 will be described below. .

The dividing unit 62 is configured to divide the level of one or more measurement tasks; the processing unit 64 is connected to the dividing unit 62, and is configured to perform overload control processing on one or more measurement tasks according to the level corresponding to the measurement task.

In the related technology, when the performance statistics module is overloaded, the network management system does not take any treatment measures, and the state is allowed to continue, resulting in the gradual accumulation of delays, and finally the performance data reporting delay time is longer and longer, and cannot be satisfied. In the embodiment, the problem of the operator's real-time performance requirement data is provided. In this embodiment, a technical solution for overload analysis and control of the network management system performance statistics module in data collection is provided. Through this solution, the problem of performance data collection and reporting delay caused by the overload operation of the performance statistics module can be effectively overcome, thereby realizing real-time reporting of performance data.

7 is a schematic structural diagram of a performance statistical overload analysis and control system according to an embodiment of the present invention. As shown in FIG. 1 , the structure includes the following modules: an overload parameter configuration module 72, and a performance data collection efficiency statistics module 74 (same as above). The acquisition module 22) and the overload analysis control module 76 (same as the determination module 24 and the processing module 26 described above) are described below.

The overload parameter configuration module 72 is configured to provide a configuration of related parameters required for overload analysis and control, and mainly includes a threshold value used for overload analysis, and the threshold value may include multiple types, and thus the threshold value is called There are many ways to do this, for example, performance data allows latency, performance acquisition time thresholds, etc., whatever the name, the role is to provide a threshold (or predetermined threshold) for overload analysis.

The performance data collection efficiency statistics module 74 is responsible for real-time measurement of performance data collection efficiency and provides data basis for overload analysis.

The overload analysis control module 76 performs the overload analysis by using the collection efficiency data collected by the performance data collection efficiency statistics module 74 (to calculate the total time of all performance data collections of the current entire granularity) (if the total time of performance data acquisition is greater than or exceeds If the set threshold is exceeded, the overload is considered. If the analysis result is overload, the overload control is performed (the overload control method can be various, see the following specific embodiment).

Based on the above system architecture, in this embodiment, a performance statistics module overload analysis and control method is also provided, and FIG. 8 is a flowchart of the performance statistics module overload analysis and control method according to an embodiment of the present invention, as shown in FIG. As shown, the method includes the following steps:

Step S802, performing parameter configuration of performance statistics overload analysis and control, mainly including threshold values of overload analysis;

Step S804: The performance statistics module collects performance data collection efficiency in the process of performing performance data collection, and stores the statistical efficiency data into a memory or (and) a permanent medium;

Step S806, the performance statistics overload analysis control module performs overload analysis according to the performance data collection efficiency data to determine whether an overload occurs;

In step S808, according to the analysis result of step S806, if an overload occurs, overload control is performed. Commonly used control methods include: deleting or suspending the currently active measurement task from low to high according to the measurement type level (ensure that the performance data of the high-level measurement task can be collected and reported in time) until the overload is restored.

Through the above solution, the overload operation of the performance statistics module can be avoided, and the performance data that the operator pays most attention to can be collected and reported in time.

Preferred embodiments of the present invention will now be described.

The overload parameter configuration module 72 is configured to configure related parameters required for overload analysis and control, and the related parameters may include multiple types, for example, the following may be included: a threshold value (or a threshold value) used by the overload analysis, The name of the threshold can be called differently, for example, performance data acquisition allows delay time, performance data acquisition time threshold, performance overload analysis threshold, etc. No matter what the name, its role is to provide a threshold for overload analysis. value.

In the overload control, if the method of overload control according to the measurement type level is adopted, the overload parameter configuration module 72 may further include setting of the measurement type level information, and the level of each measurement type is set by the operator according to his own needs. Set the type of measurement that it is most concerned with as important.

The threshold value used in the overload analysis generally refers to the allowable offset of the time when the operator receives the performance data from the network management system with respect to the data collection start time. For example, for data with a 5-minute granularity, the operator must receive 10:05 points for 10:08 points, ie the threshold is 3 minutes (180 seconds).

The level of the measurement type can be set according to the following rules: the type of measurement that the operator is most concerned with and the related types of specifications or protocols (for example, the CORBA specification, 3GPP protocol) are defined as important levels; the type of measurement that the operator generally focuses on is defined as Secondary level; the type of measurement used for device maintenance and problem location is defined as a normal level.

The performance data collection efficiency statistics module 74 performs statistics on performance data collection efficiency. The statistical data needs to be able to calculate the total acquisition time of all performance data of the current granularity. For example, the statistical content may include: the number of performance data packets per measurement type (or measurement task), the storage time of performance data (eg, data storage time, data write file time, etc.), single performance packet processing time , the total time of all performance packet processing, the total time of all performance data storage, and so on. The total data acquisition time is equal to the total time of packet processing plus the total time of all performance data storage.

The performance data collection efficiency statistics are stored in the memory or/and the permanent storage medium, so that the subsequent overload analysis control module 16 performs the efficiency data query.

After the collection efficiency data statistics are completed, the overload analysis control module 76 is notified to perform the overload analysis. The overload analysis analysis module 76 can also be triggered by the timer to perform overload analysis.

The overload analysis control module 76 performs the following overload analysis: the total data acquisition total time of the latest granularity is obtained from the performance data collection efficiency statistics module 74, and compared with the set threshold value (set by the overload parameter configuration module 72). If the total data acquisition time is greater than the threshold, it indicates an overload.

Here, you can also choose to increase the number of consecutive occurrences of overload, for example, if the overload occurs for 3 consecutive times, it is considered to be really overloaded. This can eliminate the occasional overall operational efficiency degradation of the network management system (for example, sudden high resource occupancy of individual processes) or performance statistics overload caused by network communication storms.

Judging the analysis result of the previous step, if an overload occurs, the overload control is performed, and the overload control method can have various options. For example, the following control processing methods can be adopted: (1) The network management system automatically deletes or suspends low-level tasks according to the measurement task level; (2) the network management system issues an overload alarm or notification, which is manually selected by the user to be deleted/hanged. The measurement task or the number of measurement objects in some measurement tasks (if the network management system supports selecting different counters to create measurement tasks, the number of counters in the measurement task can also be deleted).

The following describes the control method of (1) as an example:

Sort all the currently active measurement tasks from normal to important (the level of the measurement task can be set according to the level of the measurement type, or can be specified by the user when creating the measurement task), and then cycle the sorted measurement tasks. Processing as follows:

1) Obtain the performance data packet of the latest granularity of the measurement task from the performance data collection efficiency statistics module 74, the performance data storage time of the measurement task, the performance data packet number of all measurement tasks, and the total processing time of all performance data packets.

2) Calculate the data acquisition time of the measurement task:

Data acquisition time = single performance packet processing time * number of packets for the measurement task + performance data storage time for the measurement task

3) Calculate the length of time when the performance data collection time exceeds the threshold:

Exceeded time = total time of performance data acquisition - threshold

4) Suspend the measurement task (you can also choose to issue an alarm notification or log, indicating that the measurement task is automatically suspended by the system due to overload)

5) Subtract the data acquisition time of the measurement task from the excess time and determine whether the remaining excess time is greater than 0. If it is greater than 0, continue to process the next measurement task; if less than or equal to 0, the overload has been restored and exited. cycle.

Through the foregoing embodiments and the preferred embodiments, the performance statistics module is subjected to overload analysis and control, and the problem of delay reporting of important performance data is solved, and the performance data that the operator pays most attention to can be collected and reported in time.

In addition, it should be noted that since the flow of performance statistics and the model have very strong similarities under different communication standards, the embodiments and preferred embodiments of the present invention are various network management systems under the existing 3GPP protocol (for example, , CDMA2000, WCDMA, TD-SCDMA, etc. can also be implemented, with wide applicability and practical value.

It will be apparent to those skilled in the art that the various modules or steps of the present invention described above can be implemented by a general-purpose computing device that can be centralized on a single computing device or distributed across a network of multiple computing devices. Alternatively, they may be implemented by program code executable by the computing device such that they may be stored in the storage device by the computing device and, in some cases, may be different from the order herein. The steps shown or described are performed, or they are separately fabricated into individual integrated circuit modules, or a plurality of modules or steps thereof are fabricated as a single integrated circuit module. Thus, the invention is not limited to any specific combination of hardware and software.

The above description is only the preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes can be made to the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and scope of the present invention are intended to be included within the scope of the present invention.

Industrial applicability

As described above, the foregoing embodiments and the preferred embodiments solve the problem that the performance data reporting delay is long in the related art, and the overload operation of the performance statistics module is avoided to ensure the real-time reporting of the performance data.

Claims

A performance data processing method comprising:

Collecting performance data statistics for one or more measurement tasks;

Determining whether the statistical value of the performance data exceeds a predetermined threshold;

In the case where the determination result is YES, the one or more measurement tasks are subjected to overload control processing.
The method according to claim 1, wherein, in the case that the performance data statistic is a total time of performance data collection, collecting the performance data statistics of the one or more measurement tasks comprises:

Obtain the data collection time of each measurement task;

The performance data statistics are obtained by summing all measurement tasks.
The method of claim 2 wherein obtaining data acquisition time for each measurement task comprises:

Obtaining the data packet processing time of the measurement task according to the following formula: the data packet processing time of the measurement task = the single data packet processing time of the measurement task * the number of data packets of the measurement task;

The data collection time of the measurement task is obtained according to the following formula: the data collection time of the measurement task=the data packet processing time+the storage time of the performance data corresponding to the measurement task.
The method of claim 1, wherein determining whether the performance data statistic exceeds the predetermined threshold comprises:

Determining whether the number of times the performance data statistics exceeds the predetermined threshold reaches a predetermined number of times;

In the case where the determination result is yes, it is determined that the one or more measurement tasks are overloaded.
The method of any one of claims 1 to 4, wherein the overload control processing of the one or more measurement tasks comprises:

Dividing the one or more measurement tasks into levels;

Performing overload control processing on the one or more measurement tasks according to a level corresponding to the measurement task.
A performance data processing device comprising:

An acquisition module configured to collect performance data statistics of one or more measurement tasks;

a determining module, configured to determine whether the statistical value of the performance data exceeds a predetermined threshold;

The processing module is configured to perform an overload control process on the one or more measurement tasks if the determination result of the determination module is YES.
The apparatus of claim 6 wherein said acquisition module comprises:

Obtaining a unit, configured to acquire a data collection time of each measurement task when the performance data statistics value is a total performance data acquisition time;

A summation unit configured to sum all of the measurement tasks to obtain the performance data statistics.
The apparatus of claim 7, wherein the obtaining unit comprises:

a first acquiring subunit, configured to acquire a data packet processing time of the measurement task according to the following formula: a data packet processing time of the measurement task = a single data packet processing time of the measurement task * a data packet number of the measurement task;

The second acquiring subunit is configured to acquire the data collection time of the measurement task according to the following formula: the data collection time of the measurement task=the data packet processing time+the storage time of the performance data corresponding to the measurement task.
The apparatus of claim 6, wherein the determining module comprises:

a determining unit, configured to determine whether the number of times the performance data statistical value exceeds the predetermined threshold exceeds a predetermined number of times;

The determining unit is configured to determine that the one or more measurement tasks are overloaded if the determination result of the determining unit is YES.
The apparatus according to any one of claims 6 to 9, wherein the processing module comprises:

a dividing unit, configured to classify the one or more measurement tasks;

The processing unit is configured to perform an overload control process on the one or more measurement tasks according to a level corresponding to the measurement task.