JP2002099448A - Performance monitoring apparatus and its method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a performance monitoring apparatus to maintain a predetermined performance of a WWW site with prior predictions of changes of performance of the WWW site owing to external conditions and with performing preventive measures according to the results of the predictions. SOLUTION: At a measuring module 11 for service performance, response time is periodically measured to store into a measuring results database 112. Next, at a predicting module 12 for service performance, response time of the prediction time specified from acquired data. After computing predicted values of the response time, at a detecting module 13 for service performance, computed values and predicted values of the response time are acquired to compare with a predetermined warranty values. As the result, if it is detected that the predicted do not satisfy the warranty values, a becoming worse of performance is informed of registered informing targets in a registered manner through an informing module 14 for service performance.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a WWW (World Wide Web) site that predicts fluctuations in performance due to external conditions in advance and takes preventive measures based on the results.
The present invention relates to a performance monitoring device for maintaining a predetermined performance of a W site and a method thereof.

[0002]

2. Description of the Related Art At present, business via the WWW is about to rise at a rapid pace. In such WWW sites, it can be considered essential to provide high-performance and reliable services for securing and maintaining customers. Therefore, at present, the WWW
An operation management method called SLM (Service Level Management) that quantitatively sets the service quality of a site and adheres to the quality is attracting attention. In order to maintain such a predetermined quality of service, it is necessary to take preventive measures before a problem occurs, instead of taking an ex post measure for some kind of failure. Conventionally, devices for performing such performance monitoring can be roughly classified into the following three types. (1) Performance monitoring of server resources and handling of resource failures Performance monitoring devices classified into such categories generally individually monitor the performance of components of WWW sites such as servers and network devices. . When the value of the monitoring item exceeds a predetermined value, an alarm is generated and a predetermined action is taken. (2) Service performance monitoring device The performance monitoring device classified into this category is actually a WWW.
It accumulates quality data (response time values, etc.) of WWW sites experienced by site customers, and analyzes and reports them. Some of such devices analyze and predict trends in the acquired quality data, but they are shown as ex-post result reports. (3) Operation and maintenance support in a client-server system This includes a technique disclosed in Japanese Patent Application Laid-Open No. 10-083382. The purpose of this performance monitoring device is to perform performance management at the business level in a general distributed system, and proposes a method of predicting a future performance state.

[0003]

However, if the purpose of the present invention is not to respond ex post facto to any kind of failure but to take preventive measures before the problem occurs, the above-mentioned conventional performance is not sufficient. The monitoring device has the following problems. In other words, the performance monitoring devices classified into the above (1) cannot set performance monitoring items as WWW sites that originally need to be managed. Therefore, the setter sets the monitoring items of individual components to the WWW site performance. There was a problem that it had to be set by experience and feeling to match. In addition, the performance monitoring device classified into the above (2), in the quality data shown as the ex-post result report, when the performance suddenly deteriorates due to a change in some external condition, the performance monitoring device There was a problem that it was not possible to analyze and take measures. Further, in the performance monitoring apparatus classified into the above (3), a method of deriving the performance at the business level by predicting the state of each resource constituting the system is proposed. Since it is assumed that the relationship between the performance monitoring device and the performance at the business level is clear, it has the same problem as the performance monitoring device classified into the above (1). Further, some examples of the prediction method are shown, but it is assumed that this method is suitable for this apparatus and that the optimum prediction method can be selected. Therefore, it is effective for a system such as an in-house system whose usage can be roughly grasped. However, a WW that is connected via the Internet and provides services to unspecified customers is available.
In the case of the W site, there is a possibility that an appropriate method may not be known, and there is a problem.

[0004] The present invention has been made in view of the above problems, and predicts fluctuations in the performance of a WWW site due to external conditions in advance and takes preventive measures based on the results.
It is an object of the present invention to provide a performance monitoring device that maintains a predetermined performance of a WW site. More specifically, (1) monitoring the performance values experienced by customers of the WWW site,
The quality is directly managed. (2) Predict the performance fluctuation in real time based on the performance value data to be monitored. (3) Judge and select the most appropriate prediction method by itself. Accordingly, it is an object of the present invention to provide a performance monitoring device that maintains a predetermined performance of a WWW site by predicting fluctuations in performance in advance and taking preventive measures based on the results, and a method thereof.

[0005]

SUMMARY OF THE INVENTION In order to solve the above problems, the present invention relates to a performance of an information providing system for providing information by one or a plurality of devices connected to a computer network via an interface device. A performance monitoring device that measures the performance of the information providing system at predetermined time intervals and records the performance measurement results in a time series; and a time series performance measured by the performance measurement means. From the measurement result, a performance prediction unit that calculates the predicted performance after a predetermined time, and a comparison between the predicted performance predicted by the performance prediction unit and the guaranteed performance that is guaranteed to a predetermined user, is performed for a specified time. And a performance judging means for judging whether or not the guaranteed performance can be maintained later.

According to the present invention, in the performance monitoring device, the performance predicting means obtains a predicted performance after a designated time from a prediction model obtained by regression analysis of the time series performance measurement results measured by the performance measuring means. Features.

According to the present invention, in the performance monitoring device, the performance predicting means calculates a plurality of regression models simultaneously at the time of regression analysis, and uses the regression model having the highest correlation coefficient with the performance measurement result as the prediction model. It is characterized by. With the above configuration, it is possible to predict the performance after a specified time by using an optimal prediction model that reproduces the tendency of the measured data.

According to the present invention, in the performance monitoring apparatus, the performance judging means automatically compares the predicted performance with the guaranteed performance at a predetermined time interval, and can maintain the guaranteed performance after the specified time. It is characterized by judging whether or not it is. With the above configuration, it is possible to always automatically obtain the latest performance judgment result.

According to the present invention, in the above-mentioned performance monitoring device, when the performance judging means judges that the guaranteed performance cannot be maintained after a designated time, the performance judging device further comprises a performance notifying means for notifying the judgment result outside the performance monitoring device. It is characterized by having been provided. With the above configuration, the performance after the specified time is predicted, and if it is determined that the predicted performance does not satisfy the predetermined performance guarantee value, the administrator of the information providing system or other information providing system The result of the judgment is notified to the system / device for monitoring the performance, and it is possible to take immediate measures before a problem occurs.

According to the present invention, in the performance monitoring device, the performance of the information system is a response time of the information providing system until the information providing system discloses information in response to an information disclosure request to the information providing system. It is characterized by.

The present invention relates to a performance monitoring method for monitoring the performance of an information providing system for providing information by one or a plurality of devices connected to a computer network via an interface device, comprising: Measures the performance of the information provision system at intervals and records the performance measurement results in time series, and calculates the predicted performance after a specified time from the time series performance measurement results measured by the performance measurement processing Performance prediction processing to compare the predicted performance predicted by the performance prediction processing with the guaranteed performance guaranteed to the user specified in advance, and determine whether the guaranteed performance can be maintained after a specified time. And characterized in that:

According to the present invention, in the performance monitoring method described above, the performance predicting process includes obtaining a predicted performance after a designated time from a predictive model obtained by regression analysis of a time series performance measurement result measured by the performance measuring process. Features.

According to the present invention, in the performance monitoring method described above, the performance prediction processing includes calculating a plurality of regression models simultaneously during regression analysis, and using a regression model having the highest correlation coefficient with the performance measurement result as a prediction model. It is characterized by.

[0014]

Embodiments of the present invention will be described below with reference to the drawings. First, an example of the configuration of the entire system using the performance monitoring device of the present embodiment will be described with reference to FIG. In FIG. 15, reference numeral 1 denotes a performance monitoring device according to the present embodiment. Reference numeral 2 is a WW of a performance monitoring target.
An information providing system that is a W site and discloses information to an accessing client. Reference numeral 3 denotes a client (a customer of the WWW site 2). Code 4
Is the Internet (computer network) connecting the WWW site 2 and the client 3. Also,
The WWW site 2 includes a WWW server 21, a content database 22, and a network device 23. The WWW server 21 receives an information disclosure request from the client 3 and provides the corresponding information to the client 3. The content database 22
This is a database in which information contents provided by the WWW site 2 are recorded in advance. The network device 23 is an interface device for a computer network including a router that connects the Internet 4 and the WWW server 21. In FIG. 15, when the client 3 accesses the WWW site 2 via the Internet 4 and requests disclosure of information, the WWW site 2 extracts the requested information from the content database 22 and provides the requested information by the WWW server 21. I do. The performance monitoring device 1 sends a signal similar to the information disclosure request output by the client 3 to the WWW site 2, and measures a response time until the requested information is provided from the WWW site 2 as a service performance.

Next, a performance monitoring apparatus according to this embodiment will be described with reference to FIG. FIG. 1 is a block diagram including a detailed configuration of the performance monitoring device 1 according to the present embodiment. In FIG. 1, reference numeral 1 denotes a performance monitoring device according to the present embodiment, as in FIG. Reference numeral 2 is a WWW site that provides information, as in FIG. Reference numeral 5 is an administrator of the WWW site 2. The performance monitoring device 1 includes a service performance measurement module 11 and a service performance prediction module 12
, A service performance determination module 13 and a service performance notification module 14.

The service performance measuring module 11 is a performance measuring means for measuring the response time of the WWW site 2 at predetermined time intervals and recording the response time in chronological order.
It further includes a performance measurement function unit 111, a measurement result database 112, and a measurement result notification function unit 113. The performance measurement function unit 111 measures the response time of the specified WWW site 2 in accordance with the measurement conditions specified by the measurement module setting file 114,
The time series data is recorded as the performance measurement result. As illustrated in FIG. 2, an example of the measurement module setting file 114 specifies a WWW site to be measured, a measurement time interval during measurement, a measurement service definition that defines which service is to be measured, and the like. . Performance measurement function unit 11
1 is a series of URLs of WWW resources for measuring performance from a WWW site to be measured and a measurement service definition (1) http://www.nttdata.co.jp/index.htm (2) http: // www.nttdata.co.jp/search.htm (3) Deriving http://www.nttdata.co.jp/searchResult.cgi, acquiring the WWW resources indicated by the above URL in order, and the time required for acquisition Is measured as the response time. The measurement result database 112 is a database that records the time-series data measured by the performance measurement function unit 111 in association with the measurement date and time for each measured service item. FIG. 3 shows an example of the performance measurement result recorded in the measurement result database 112. In FIG. 3, measurement data at each measurement time interval is recorded for each of the information search service and the article purchase service. The measurement result notification function unit 113 notifies the service performance prediction module 12 of the time series data of the performance measurement result recorded in the measurement result database 112 and notifies the service performance determination module 13 of the latest measurement result.

The service performance prediction module 12 is a performance prediction means for calculating a predicted performance after a predetermined time from the performance measurement results of the time series measured by the service performance measurement module 12, and receives the measurement results in more detail. It comprises a function unit 121, a performance prediction function unit 122, a prediction result database 123, and a prediction result notification function unit 124. The measurement result receiving function unit 121 receives the time series data of the performance measurement result transmitted from the service performance measurement module 11. The performance prediction function unit 122 performs a prediction process of the performance measurement result received from the service performance measurement module 11 according to the prediction condition specified by the prediction module setting file 125. As illustrated in FIG. 4, an example of the prediction module setting file 125 includes a prediction interval specifying a time interval for obtaining a prediction result, a prediction range specifying an elapsed time from the present to be predicted, and a past time range used for prediction. , A registered prediction model used for prediction, and the like. The prediction logic will be described later. The prediction result database 123
This is a database that records the performance prediction result in the specified prediction range calculated by the performance prediction function unit 122 in association with the calculation date and time and the prediction time for each predicted service item. FIG. 5 shows an example of the performance prediction result recorded in the prediction result database. In FIG. 5, the predicted response time of the WWW site 2, which is the predicted performance after 180 seconds, is recorded for each of the information search service and the article purchase service. The prediction result notification function unit 124 notifies the service performance determination module 13 of the performance prediction result data recorded in the prediction result database 125.

Here, the prediction logic used by the service performance prediction module 12 will be described with reference to the flowchart of FIG. 6 which explains the operation of the service performance prediction module. First, a time-series performance measurement result is obtained (step S1). Here, the data to be obtained is determined by the performance prediction function unit 122 according to the history range specified in the prediction module setting file 125.
, Request and acquire the performance measurement result between the current time and the time in the history range from the service performance measurement module 12. Next, the acquired performance measurement result is converted so that the prediction model can be easily adapted (step S2). Here, for example, normalization and coordinate conversion of the acquired values, smoothing processing of irregular variation, and exclusion of abnormal value data are performed. Here, as a simple example, the time data of the performance measurement result shown in FIG.
FIG. 7 shows an example in which the unit time is divided into 60 seconds and coordinate conversion is performed. Then, a prediction model is determined for the data thus processed. As shown in a schematic diagram illustrating the derivation of the prediction model and a prediction example in FIG.
Apply several types of prediction models specified in the above to the processed data. For example, determination of this model is calculated by the following model determination method. (1) Within a certain range, the measurement time and the response time value have a linear relationship. In this model, the relationship is

(Equation 1) It is expressed in the form. (2) Within a certain range, the measurement time and the response time value have a quadratic curve relationship. In this model, the relationship is

(Equation 2) It is expressed in the form. The coefficients of these models are derived by regression analysis from the given data, and the models are determined (step S3). As each model, not only a simple regression model as described above, but also a method using a neural network or the like in addition to a non-linear regression model represented by an exponential function, a logarithmic function or the like can be considered. Then, the prediction model theoretical value calculated by each model is compared with the performance measurement result, and the most suitable model is determined as the current prediction model (step S4). Here, as a method of determining the most suitable model, for example, there is a method of obtaining a correlation coefficient between a predicted model theoretical value and a performance measurement result, and employing a model having the largest correlation coefficient. In FIG. 8, the quadratic curve model (square model) is specified as the best-fit model. In the present embodiment, X and Y shown in FIG.
Are <linear model> and <square model> shown in FIG.
It is considered that it can be expressed by a function defined by three types of models <root model>. Then, optimal coefficients a and b such that the combination of X and Y best fit the model are obtained by the minimum approximation method shown in FIG. As a result, the correlation coefficient of each model shown in FIG. 9 is obtained, and here, the root model having the highest correlation coefficient value is determined as the prediction model most suitable this time. Using the prediction model determined as described above, the module calculates a predicted value of the response time in the set prediction range (step S5).

The service performance judgment module 13 compares the predicted performance predicted by the service performance prediction module 12 with the guaranteed performance guaranteed to the user specified in advance, and determines whether the guaranteed performance can be maintained after a specified time. This is a performance judging means for judging the judgment, and comprises a measurement / prediction result receiving function unit 131, a performance judgment function unit 132, and a judgment result notification function unit 133 in more detail. The measurement / prediction result receiving function unit 131 includes the service performance measurement module 1
1 and the latest performance prediction result transmitted from the service performance prediction module 12 are received. The performance determination function unit 132 determines whether the specified service performance can be maintained according to the determination conditions specified by the service performance definition file 134. As illustrated in FIG. 11, an example of the service performance definition file 134 specifies a determination interval for specifying a time interval for determining performance, a performance definition for defining performance for each service, and the like. FIG. 12 shows an example of service performance information received by the measurement / prediction result receiving function unit 131 and used by the performance determining function unit 132. Decision result notification function unit 133
Outputs the result determined by the performance determination function unit 132 to the service performance notification module 14 as information as illustrated in FIG.

The service performance notifying module 14 determines that the service performance determining module 13
If the WW site 2 determines that the guaranteed performance cannot be maintained, the WW site 2 sends the notification to a predetermined notification destination outside the performance monitoring device 1.
This is a performance notifying means for notifying the judgment result by a notifying method specified in advance.

Note that the measurement result database 112 of the service performance measurement module 11 and the prediction result database 123 of the service performance prediction module 12 include a non-volatile memory such as a hard disk device, a magneto-optical disk device, a flash memory, or a CD-ROM. And the like, a recording medium that can only be read, a volatile memory such as a RAM (Random Access Memory), or a computer-readable and writable recording medium using a combination thereof.

Also, the performance measurement function unit 111 and the measurement result notification function unit 113 of the service performance measurement module 11, and the measurement result reception function unit 121, the performance prediction function unit 122, and the prediction result notification function unit 124 of the service performance prediction module 12 , And the measurement of the service performance judgment module 13
The prediction result receiving function unit 131, the performance judgment function unit 132, the judgment result notification function unit 133, and the service performance notification module 14 are a service performance measurement module 11, a service performance prediction module 12, a service performance judgment module 13, and a service performance Notification module 14
In the above, the program may be realized by dedicated hardware, or may be configured by a memory and a CPU (Central Processing Unit), and load and execute a program for realizing the function of each unit described above into the memory. Thus, the function may be realized.

It is assumed that an input device, a display device, and the like (both not shown) are connected to the performance monitoring device 1 as peripheral devices. Here, the input device refers to an input device such as a keyboard and a mouse. What is a display device?
It refers to a T (Cathode Ray Tube) display device, a liquid crystal display device, or the like.

Next, the operation of the first embodiment will be described with reference to FIG. FIG. 14 is a flowchart illustrating the operation of the performance monitoring device 1 according to the present embodiment. In FIG. 14, first, the performance measurement function unit 111 of the service performance measurement module 11 periodically measures response time as service performance (step S11). Then, the measured response time is stored in the measurement result database 112 as time-series data (step S12). Next, the service performance prediction module 12 predicts the response time at the specified prediction time from the acquired data (step S13). When the predicted value of the response time can be calculated, the performance determining function unit 132 of the service performance determining module 14 acquires the measured value and the predicted value of the response time and compares them with the predetermined guaranteed value of the response time (step S14). ). Then, as a result of the comparison, it is determined whether or not the predicted value of the response time satisfies the guaranteed value of the response time (step S15). If it is determined in step S15 that the predicted value of the response time does not satisfy the guaranteed value of the response time (NO in step S15), the service performance notification module 14 determines the information as described in FIG. Notify the result (step S1
6). The service performance notification module notified of the determination result notifies the registered notification destination of the performance deterioration tendency by the registered method. (Step S1
7). Here, the notification destination is assumed to be a case where human judgment is required, and the administrator 5 of the WWW site 2 that provides the information is provided.
And If it is determined in step S15 that the predicted value of the response time satisfies the guaranteed value of the response time (YES in step S15), the process returns to step S11, and the performance monitoring device 1 monitors the performance of the WWW site 2. to continue.

In the above-described embodiment, it is assumed that the service performance notification module 14 notifies the result of the performance determination to the WWW site 2 that provides information, assuming a case where human judgment is required. However, as a notification target, a system for restricting access to the WWW site 2, a system for increasing the resource performance of the WWW site 2, and a system / apparatus such as an existing integrated operation management tool The service performance may be automatically managed.

The performance monitoring device 1 shown in FIG.
Records a program for realizing the function on a computer-readable recording medium, causes a computer system to read the program recorded on the recording medium, and executes the program. May be realized.

Here, the “computer system” includes an OS and hardware such as peripheral devices.
If a WW (World Wide Web) system is used, a homepage providing environment (or display environment) is also included. The "computer-readable recording medium" is a floppy (registered trademark) disk, a magneto-optical disk, a ROM, a CD-ROM.
And a storage device such as a hard disk built in a computer system. Further, a “computer-readable recording medium” refers to a medium that dynamically stores a program for a short time, such as transmitting a program via a computer network such as the Internet or a communication line such as a telephone line. (Transmission medium or transmission wave), in which case a program holding a program for a certain period of time, such as a volatile memory in a computer system serving as a server or a client, is also included.

Further, the above-mentioned program may be for realizing a part of the above-mentioned functions, and may be for realizing the above-mentioned functions in combination with a program already stored in the computer system, that is, a so-called program. It may be a difference file (difference program).

[0029]

As described above, according to the present invention, in a performance monitoring device for monitoring the performance of an information providing system for providing information by one or more devices connected to a computer network via an interface device, Performance measuring means for measuring the performance of the information providing system at a predetermined time interval, and recording the performance measurement results in time series;
A performance prediction unit that calculates a predicted performance after a predetermined time from the performance measurement result of the time series measured by the performance measurement unit, and a predicted performance predicted by the performance prediction unit and a guaranteed performance guaranteed to a predetermined user. And a performance judgment means for judging whether or not the guaranteed performance can be maintained after a designated time, and an optimal prediction method based on a plurality of prediction models obtained from regression analysis of the performance measurement results by the performance prediction means. The prediction model was extracted and the prediction performance after the specified time was obtained.

Further, according to the present invention, in the above-mentioned performance monitoring apparatus, when the performance judging means judges that the guaranteed performance cannot be maintained after a designated time, the performance notifying means notifies the outside of the performance monitoring apparatus of the judgment result. Is provided to notify the outside of the situation of performance deterioration before a problem occurs.
Accordingly, the performance after the specified time is predicted, and if it is determined that the predicted performance does not satisfy the predetermined performance guarantee value, the performance of the information providing system administrator or other information providing system is determined. It is possible to notify the monitoring system / apparatus of the result of the judgment and take immediate measures before a problem occurs.

Therefore, by preliminarily predicting fluctuations in the performance of the WWW site due to external conditions and taking preventive measures based on the results, it is possible to maintain the predetermined performance of the WWW site. .

[Brief description of the drawings]

FIG. 1 is a block diagram illustrating a configuration of an embodiment of the present invention.

FIG. 2 is a schematic diagram illustrating an example of a measurement module setting file set in the service performance measurement module according to the embodiment.

FIG. 3 is a schematic diagram illustrating an example of a performance measurement result recorded in a measurement result database of the service performance measurement module according to the embodiment.

FIG. 4 is a schematic diagram illustrating an example of a prediction module setting file set in the service performance prediction module according to the embodiment.

FIG. 5 is a schematic diagram illustrating an example of an information table in which a prediction model is recorded in the service performance prediction module according to the embodiment.

FIG. 6 is a flowchart illustrating an operation of the service performance prediction module according to the embodiment.

FIG. 7 is a schematic diagram illustrating an example of a performance measurement result after preprocessing in the service performance prediction module according to the embodiment.

FIG. 8 is a schematic diagram illustrating derivation of a prediction model and a prediction example of the service performance prediction module of the embodiment.

FIG. 9 is a schematic diagram illustrating an example of an information table for deriving and selecting a prediction model in the service performance prediction module according to the embodiment.

FIG. 10 is a schematic diagram illustrating an example of a calculation method for deriving a prediction model in the service performance prediction module according to the embodiment.

FIG. 11 is a schematic diagram illustrating an example of a service performance definition file set in the service performance determination module according to the embodiment.

FIG. 12 is a schematic diagram illustrating an example of service performance information used in the service performance determination module according to the embodiment.

FIG. 13 is a schematic diagram illustrating an example of a performance determination result notification message transmitted from the service performance determination module according to the embodiment.

FIG. 14 is a flowchart illustrating an operation of the performance monitoring device of the embodiment.

FIG. 15 is a schematic diagram illustrating a configuration example of an entire system in which the performance monitoring device of the embodiment is used.

[Explanation of symbols]

 1 Performance Monitoring Device 2 WWW Site 3 Client 4 Internet 5 Site Administrator 11 Service Performance Measurement Module 12 Service Performance Prediction Module 13 Service Performance Determination Module 14 Service Performance Notification Module 21 WWW Server 22 Content Database 23 Network Device 111 Performance Measurement Function Unit 112 Measurement result database 113 Measurement result notification function unit 114 Measurement module setting file 121 Measurement result reception function unit 122 Performance prediction function unit 123 Prediction result database 124 Prediction result notification function unit 125 Prediction module setting file 131 Measurement / prediction result reception function unit 132 Performance Judgment function unit 133 Judgment result notification function unit 134 Service performance definition file

Continued on the front page F term (reference) 5B042 GA12 GA18 GC10 GC16 JJ06 JJ08 JJ15 JJ23 KK09 KK13 MA14 MB03 MC31 5B089 GA04 GB02 HA10 JA22 KA12 KA14 MC02 MC03 MC03

Claims (9)

[Claims] 1. A performance monitoring device for monitoring the performance of an information providing system for providing information by one or more devices connected to a computer network via an interface device, comprising: A performance measuring unit that measures the performance of the information providing system and records the performance measurement results in a time series, and calculates a predicted performance after a predetermined time from the time series performance measurement results measured by the performance measurement unit. And comparing the predicted performance predicted by the performance predicting unit with the guaranteed performance guaranteed to the user specified in advance, and determining whether or not the guaranteed performance can be maintained after a specified time. A performance monitoring device comprising: a performance judgment unit; 2. The method according to claim 1, wherein the performance predicting unit obtains a predicted performance after a specified time from a prediction model obtained by regression analysis of the performance measurement result of the time series measured by the performance measuring unit. 2. The performance monitoring device according to 1. 3. The performance predicting means calculates a plurality of regression models simultaneously during regression analysis, and uses a regression model having the highest correlation coefficient with the performance measurement result as a prediction model. 3. The performance monitoring device according to 2. 4. The performance determining means automatically compares the predicted performance and the guaranteed performance at a predetermined time interval, and determines whether the guaranteed performance can be maintained after a specified time. 4. The performance monitoring device according to claim 1, wherein 5. A performance notifying means for notifying the result of the determination to the outside of the performance monitoring device when the performance determining means determines that the guaranteed performance cannot be maintained after a designated time. The performance monitoring device according to any one of claims 1 to 4, wherein 6. The performance of the information system is a response time of the information providing system until the information providing system discloses information in response to an information disclosure request to the information providing system. The performance monitoring device according to claim 1. 7. A performance monitoring method for monitoring the performance of an information providing system for providing information by one or a plurality of devices connected to a computer network via an interface device, comprising: A performance measurement process of measuring the performance of the information providing system and recording the performance measurement results in time series, and calculating a predicted performance after a predetermined time from the time series performance measurement results measured by the performance measurement process. Performing a performance prediction process, and comparing the predicted performance predicted by the performance prediction process with a guaranteed performance guaranteed to a user specified in advance, and determining whether the guaranteed performance can be maintained after a specified time. A performance monitoring method, comprising: a performance judgment process. 8. The performance prediction processing according to claim 1, wherein a prediction performance after a designated time is obtained from a prediction model obtained by a regression analysis of the performance measurement result of the time series measured by the performance measurement processing. 7. The performance monitoring method according to 7. 9. The performance prediction process according to claim 1, wherein a plurality of regression models are simultaneously calculated during regression analysis, and a regression model having the highest correlation coefficient with the performance measurement result is used as a prediction model. 9. The performance monitoring method according to 8.