JP2008158996A - Information processor and information processing method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To predict an increase of a processing load in an information processor. <P>SOLUTION: A managing device 20 comprises: a load information database 253 for storing the load information of a business server 10; and a model information database 251 for storing model information including a missing period. The managing device 20 calculates the model increasing rate by dividing, by the missing time, accumulated value of state variable of state varying history information corresponding to the time from the start time to the finish time of the missing period, also calculates the present increasing rate by dividing, by the missing time, the accumulated value of state variable of load information from the present time to the time before the missing time, and predicts that the business server 10 has high load when the difference between the model increasing rate and the present increasing rate is a predetermined threshold or lower. <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention relates to an information processing apparatus and an information processing method.

In an information processing system that performs information processing according to input data, when input data exceeding the processing capability of one information processing device is given, load distribution that assigns processing to other information processing devices is performed. (For example, refer to Patent Document 1). In a conventional load distribution system, the processing load of an information processing device is monitored, and when the processing load exceeds a predetermined value, part of the processing load is transferred to another information processing device. .
Japanese Patent Application Laid-Open No. 6-214962

  However, if processing is delegated to another computer after the processing load of a certain computer has increased, the processing capability of the system will be reduced until the processing is delegated to another computer.

  The present invention has been made in view of such a background, and an object thereof is to provide an information processing apparatus and an information processing method capable of predicting an increase in processing load in the information processing apparatus.

  The invention according to claim 1 of the present invention for solving the above-described problem is an information processing apparatus that performs information processing according to input data, wherein the input data is associated with a time when the input data is received. An input history storage unit that stores the data amount of data, a period input unit that receives an input of a period in which a problem has occurred in the information processing in the past, and an input from the start time of the period to the end time of the period A first increase value that is a quotient obtained by totaling the data amount of the input data to calculate a first cumulative value, and dividing the calculated first cumulative value by a problem occurrence time that is the length of the period. A model increase rate calculation unit to be calculated, and a second cumulative value is calculated by adding the data amount of the input data input up to the current time from the time before the problem occurrence time before the current time. The second cumulative value The current increase rate calculation unit for calculating the second increase rate that is a quotient divided by the problem occurrence time, and whether the difference between the first and second increase rates is equal to or less than a predetermined threshold value, A high-load prediction unit that determines whether or not the information processing apparatus has a high load.

  According to the information processing apparatus of the present invention, based on the history of the amount of data input in the past, the information processing apparatus according to whether or not the increase rate of the current input data amount approaches the increase rate of the cumulative value. Can be predicted to become a high load. Therefore, the user can prevent a reduction in the processing capability of the information processing apparatus before the information processing apparatus is overloaded by delegating part of the processing to another information processing apparatus based on this prediction. Can do.

The invention according to claim 2 of the present invention is the information processing apparatus according to claim 1, wherein the information processing apparatus is connected to a plurality of other information processing apparatuses, and the information processing apparatus is determined to have a high load. In this case, for each of the other information processing apparatuses, the data amount of the input data input from the time before the problem occurrence time before the current time to the current time is acquired, and the acquired data amount is A comparative increase rate calculation unit that calculates a third increase value that is a quotient obtained by dividing the calculated third cumulative value by the problem occurrence time; And a delegation destination candidate output unit that outputs information indicating the other information processing apparatus having the smallest comparison increase rate.
In this case, another information processing apparatus in which the amount of input data has not increased so much can be presented as a processing delegation destination. Therefore, the user can easily specify another information processing apparatus to which the process is to be delegated. For example, even when the user needs to manually delegate the process, the process is quickly delegated. It becomes possible.

Moreover, invention of Claim 3 among this invention is the information processing apparatus of Claim 2, Comprising: The said information processing apparatus used by the said information processing according to the data amount of the said input data Based on the received input data, based on the usage amount determination information storage unit that stores the usage amount determination information for determining the amount of resources, the data amount of the received input data, and the usage amount determination information A usage amount determining unit that determines a usage planned amount that is the amount of the resource used by performing the information processing; and when the determined usage planned amount is greater than a predetermined value, the other information processing apparatus Free space for acquiring the current usage amount that is the amount that the resource is currently used from, and calculating the free resource amount that is the difference between the resource amount and the current usage amount that the other information processing apparatus has Resource calculation And the delegation destination candidate output unit has the smallest comparison increase rate among the other information processing devices having the free resource amount larger than the difference between the planned use amount and the predetermined value. Is output as the delegation destination.
In this case, another information processing apparatus that is predicted to have a low increase in processing load in the future can be presented as a delegation destination candidate.

  Moreover, invention of Claim 4 among this invention is the information processing apparatus of Claim 2, Comprising: The said input data are weather data, The position in which the said other information processing apparatus is installed is shown. When the installation position storage unit to store and the weather data includes the position of the typhoon, for each of the other information processing apparatuses, the position of the typhoon and the position where the other information processing apparatus is installed An installation distance calculation unit that calculates a distance between the other information processing apparatuses as transfer destinations of the process according to the distance and the comparative increase rate. It will be decided.

  Moreover, invention of Claim 5 among this invention is the information processing apparatus of Claim 4, Comprising: The said input log | history memory part memorize | stores the data amount of the said weather data for every scale of typhoon. The period input unit accepts the input of the typhoon scale together with the period, and the model increase rate calculation unit includes, for each typhoon scale, the weather data corresponding to the typhoon scale among the weather data. The first cumulative value is calculated by adding the data amount of what is input from the start time to the end time, and the current increase rate calculation unit, when the weather data includes the scale of the typhoon, Of the meteorological data corresponding to the scale of the typhoon, the second cumulative value is calculated by summing up the data amount of data input from the time before the problem occurrence time to the current time among the current time. , Candidate delegation The section indicates information indicating the other information processing apparatus as the delegation destination when a difference between the first and second increase rates for the same typhoon scale is equal to or less than the predetermined threshold value. Is output.

  Moreover, invention of Claim 6 among this invention is the information processing apparatus of Claim 2, Comprising: The comparative increase rate list which displays the said comparative increase rate about each of said another information processing apparatus as a list A display unit is provided.

  Further, the invention according to claim 7 of the present invention is the information processing apparatus according to claim 1, wherein low priority processing that is executed when a load on the information processing apparatus is lower than a predetermined value is executed. A low-priority process execution history storage unit that stores the time when the low-priority process execution history storage unit is identified from the low-priority process execution history storage unit, Let the period be the period in which the problem occurs.

  Moreover, invention of Claim 8 among this invention is the information processing apparatus of Claim 1, Comprising: The data amount of the said input data input in the past, The time when the said input data was input, A model information input unit that accepts input of model information including: the model increase rate calculation unit sums the data amount included in the model information corresponding to the time from the start time to the end time, and The first cumulative value is calculated.

  Other problems and solutions to be disclosed by the present application will be made clear by the embodiments of the invention and the drawings.

  According to the present invention, it is possible to predict an increase in processing load in the information processing apparatus.

Hereinafter, an information processing system according to an embodiment of the present invention will be described.
The information processing system according to the present embodiment is data (hereinafter referred to as state change data) indicating changes in the state of various power facilities such as a power plant and a substation (for example, on / off of a switch) in an electric power company. Is input, and information processing such as statistical analysis is performed on the input state change data.

  Electric power facilities are easily affected by the weather. For example, when a typhoon strikes, the state of the facilities is likely to change, and the amount of state change data input to the information processing system (hereinafter referred to as state variables). ) Will also increase. As the state change data input increases, the processing load on the business server 10 in charge of information processing also increases. When the processing load of the business server 10 exceeds a certain limit, it is necessary to delegate a part of information processing performed by the business server 10 to another business server 10.

  In the information processing system of this embodiment, based on the change in the input amount of the state change data when a typhoon hits in the past, it is predicted whether the current processing addition of the business server 10 will be a heavy load, and the business server When 10 is predicted to have a high load, candidates for other business servers 10 to which a part of information processing of the business server 10 is delegated are presented.

== System configuration ==
FIG. 1 is a diagram illustrating an overall configuration of an information processing system according to the present embodiment. As shown in the figure, the information processing system of this embodiment includes a business server 10, a management device 20, and a weather data providing device 30. The business server 10, the management device 20, and the weather data providing device 30 are connected to each other via a communication network 40 so that they can communicate with each other.

  The business server 10 is a computer that performs business by executing application programs. The business server 10 acquires status change data from various power facilities (not shown) via the communication network 40, and performs information processing related to the business according to the acquired status change data. The business server 10 manages the history of the number of acquired state change data (hereinafter referred to as the number of state change data) and the execution history of the business such as the execution result of the application program (hereinafter referred to as the business log information). 20 to send.

  The weather data providing device 30 is a computer that provides weather data. The weather data providing device 30 is operated by, for example, the Japan Meteorological Agency or a private weather company. In the present embodiment, the weather data providing device 30 provides only weather data related to typhoons and lightning.

  The management device 20 is a computer operated by an administrator. The management device 20 receives the history of the number of state change data and the business log information from the business server 10, and also receives the weather data from the weather data providing device 30, and based on these, the processing load on the business server 10 increases. Predict.

== Configuration of Management Device 20 ==
FIG. 2 is a diagram illustrating a hardware configuration of the management apparatus 20. As shown in the figure, the management device 20 includes a CPU 201, a memory 202, a storage device 203, a communication interface 204, an input device 205, and an output device 206. The storage device 203 stores various application programs and data, for example, a hard disk drive, a CD-ROM drive, a flash memory, or the like. The CPU 201 implements various functions by reading an application program stored in the storage device 203 into the memory 202 and executing it. The communication interface 204 is an interface for connecting to the communication network 40. The communication interface 204 is, for example, an adapter for connecting to Ethernet (registered trademark) or a modem for connecting to a public telephone line network. The input device 205 is a keyboard, mouse, touch panel, or the like that accepts data input. The output device 206 is, for example, a display or a printer that outputs data.

  FIG. 3 is a diagram illustrating a software configuration of the management apparatus 20. As shown in the figure, the management device 20 includes a model information input unit 211, a weather data acquisition unit 212, a load information acquisition unit 213, a high load prediction unit 214, a delegation destination output unit 215, a model information database 251 and a server information database. 252, a load information database 253, and a load characteristic information storage unit 254.

  The model information database 251 stores information including state variables at the time of past typhoon attacks (hereinafter referred to as model information). FIG. 4 is a diagram illustrating a configuration example of model information stored in the model information database 251. As shown in the figure, the model information includes typhoon scale, missing period, and state change history information.

The typhoon scale is one of “weak”, “average”, “strong”, “very strong”, and “furious”. The typhoon scale is determined by the maximum wind speed. Table 1 shows the correspondence between maximum wind speed and typhoon scale.

  The missing period is a period during which the business server 10 is heavily loaded (a period in which a problem has occurred in information processing in the past). In this embodiment, it is assumed that the status change data recording job has a lower priority than other jobs, and the business server 10 has a high load during the period when the status change data recording job is missing. It is supposed to be.

  The state change history information includes a stationary number and a state variable in association with the date and time. The stationary number is a data amount of data (hereinafter referred to as stationary data) that is constantly input without being affected by weather conversion.

  FIG. 5 is a diagram showing an example in which state variables included in the state change history information are shown in a graph. In the example of FIG. 5, a cumulative value of state variables (hereinafter referred to as a cumulative state variable) 311 is displayed. As will be described later, in the information processing system according to the present embodiment, it is determined whether the business server 10 has a high load by using the slope of the cumulative variable 311 in the missing period 312.

  The model information input unit 211 receives input of model information. For example, the model information input unit 211 may accept input of model information from the input device 205 such as a keyboard or a mouse, or may accept designation of a period during which a typhoon hits, and obtain weather data in the designated period. It may be acquired from the weather data providing device 30 and the history of the steady number and state variables in the above period may be acquired from the business server 10. The model information input unit 211 registers the input model information in the model information database 251.

  The server information database 252 stores information related to the business server 10 (hereinafter referred to as server information). FIG. 6 shows a configuration example of server information stored in the server information database 252. As shown in the figure, the server information includes a site, an address, an installation position, and a forecast point code. The site is identification information of the business server 10. The address is an address of the business server 10 in the communication network 40 such as an IP address. The installation position indicates a place where the business server 10 is physically installed. The installation position is expressed by latitude and mildness, for example. The forecast point code is information indicating a weather forecast point corresponding to the place where the business server 10 is installed. For example, an AMeDAS point number can be used as the forecast point code.

The weather data acquisition unit 212 acquires weather data from the weather data providing device 30.
The load information database 253 stores information related to the processing load of the business server 10 (hereinafter referred to as load information). FIG. 7 is a diagram illustrating a configuration example of load information stored in the load information database 253. As shown in the figure, the load information includes the site, date and time, stationary number, state variable, and CPU usage rate. The site is information indicating the business server 10. The CPU usage rate is information indicating the load on the business server 10.

  The load information acquisition unit 213 acquires load information from each of the business servers 10 included in the information processing system of the present embodiment, and registers the acquired load information in the load information database 253. In the present embodiment, the load information acquisition unit 213 transmits a command for acquiring load information (hereinafter referred to as a load information acquisition request) to each business server 10 and responds to the load information acquisition request from each business server 10. Load information about each business server 10 is acquired by receiving the load information transmitted in this manner. In the present embodiment, for the sake of simplicity, the load information acquisition unit 213 acquires load information from each business server 10 at predetermined time intervals such as 1 minute, 10 minutes, 30 minutes, and 1 hour. .

  The load characteristic information storage unit 254 stores necessary information for predicting the processing load of the business server 10 (hereinafter referred to as load characteristic information). A configuration example of the load characteristic information stored in the load characteristic information storage unit 254 is shown in FIG. As shown in the figure, the load characteristic information includes a steady load and a load generation function. The steady load is a processing load related to steady data processing (in the present embodiment, indicated by the usage rate of the CPU 201). In the example of FIG. 8, the steady load is “10%”, which means that the CPU 210 is always used by 10% without being affected by weather fluctuations. The load generation function is information necessary for calculating a processing load related to the state change data (hereinafter referred to as state change load). In this embodiment, the load generation function is expressed as a function for obtaining a usage rate of the CPU 201 by giving a state variable. In the example of FIG. 8, when the state variable is x and the usage rate of the CPU 201 is y, if x is less than 30, “y = 0.4x”, and if x is 30 or more, “y = 0.2x ". Therefore, the usage rate of the CPU 210 in the business server 10 can be calculated by adding a value obtained based on the load generation function to the steady load. FIG. 9 is a diagram illustrating an example of a graph representing a change in the usage rate of the CPU 201 according to the state variable. As shown in the figure, the usage rate of the CPU 201 is the sum of the steady load 301 and the state variable load 302. For example, when the state variable is “30” at a certain time, the usage rate y of the CPU 201 is obtained as “y = 0.4 × 100 + 10 = 50”.

The usage rate y of the CPU 201 is obtained as “y = 0.4 × 100 + 10 = 50”.

  The high load prediction unit 214 predicts whether or not the business server 10 will be heavily loaded when a typhoon warning or a warning is issued. The high load predicting unit 214 predicts the state variable based on the model information, calculates the usage rate of the CPU 201 based on the predicted state variable and the load characteristic information, and the calculated usage rate of the CPU 201 is 100% (or alternatively It is also possible to set a predetermined rate such as 90%.) It is predicted whether or not the business server 10 will be heavily loaded depending on whether or not it exceeds. The state variable prediction process based on the model information will be described later.

  In the graph of FIG. 9, when the state variable is Nmax, the usage rate of the CPU 201 is 100%. However, when the state variable N predicted by the high load prediction unit 214 based on the model information exceeds Nmax, the use of the CPU 201 is performed. The rate is 100 + α%, and the business server 10 is predicted to be heavily loaded.

  When it is predicted that the business server 10 will be heavily loaded, the delegation destination output unit 215 determines and outputs another business server 10 to which a part of information processing is delegated. As described above, when the usage rate of the CPU 201 is predicted to be “100 + α%”, the delegation destination output unit 215 determines that the processing load of the other business servers 10 is “100−α%” or less. Decide as a delegation destination. Details of the process of outputting the delegation destination will be described later.

== Processing by Management Device 20 ==
FIG. 10 is a diagram illustrating a flow of processing in the management apparatus 20. Note that the management device 20 performs the processing in FIG. 10 every time weather data is received from the weather data providing device 30, for example, or every predetermined time.

  The management device 20 acquires weather data (hereinafter referred to as alarm data) representing an alarm (including warning information) from the weather data providing device 30 (S401), and the business server 10 is installed based on the acquired alarm data. It is determined whether a typhoon warning (including a typhoon warning) is issued in any of the areas that are being operated (S402).

  When a typhoon warning is issued in any region (S402: YES), the management device 20 acquires a prediction point code indicating the region where the typhoon warning is issued (S403), and for each of the acquired prediction point codes. The delegation destination output process shown in FIG. 11 is performed (S404).

  The management device 20 calculates an increase rate of the cumulative variable based on the model information (hereinafter referred to as a model increase rate, which corresponds to the first increase rate of the present invention) (S421). The flow of the model increase rate calculation process is shown in FIG.

  The management device 20 acquires weather data related to the typhoon (hereinafter referred to as typhoon data) from the weather data providing device 30 (S441). It is assumed that the typhoon data includes the typhoon position and the maximum wind speed. The management apparatus 20 specifies the typhoon scale corresponding to the maximum wind speed contained in typhoon data from said Table 1 (S442). The management device 20 reads model information corresponding to the identified typhoon scale from the model information database 251 (S443), and extracts state change history information corresponding to the date and time within the missing period included in the read model information ( S444). The management device 20 calculates a cumulative state variable for each of the extracted state change history information (hereinafter referred to as “extraction history information”) in order of date and time (S445), and from the cumulative state variable for the last extracted history information, A quotient obtained by dividing the value obtained by subtracting the cumulative variable for the extraction history information by the missing time is set as the model increase rate (S446). The model increase rate is calculated as described above.

  Next, the management device 20 calculates an increase rate of the cumulative variable in the business server 10 based on the load information (hereinafter referred to as a current increase rate, which corresponds to the second increase rate of the present invention) (S422). The flow of the current increase rate calculation process is shown in FIG.

  The management device 20 reads the site corresponding to the forecast code from the server information database 252 (S461), and among the load information corresponding to the read site, the load information database in which the date and time is within the missing period of the model information in order of date and time. Read from 253 (S462). The management device 20 calculates a cumulative state variable for each of the read load information (S463), and obtains a value obtained by subtracting the cumulative state variable for the first load information from the cumulative state variable for the last load information. The quotient divided by the missing time is set as the current increase rate (S464). The current increase rate is calculated as described above.

  The management apparatus 20 compares the model increase rate calculated as described above with the current increase rate, and determines whether the difference between the model increase rate and the current increase rate is equal to or less than a predetermined threshold value. It is predicted whether or not will become a high load (S423). When the difference between the model increase rate and the current increase rate is equal to or less than a predetermined threshold, that is, when the business server 10 is predicted to be heavily loaded (S423: YES), part of the information processing is delegated. A candidate for another business server 10 to be a destination (hereinafter referred to as a delegation destination candidate) is determined (S424). FIG. 14 shows the flow of the transfer destination candidate determination process.

  The management device 20 calculates the average value of the state variables of the state change history information within the missing period and sets it to N (S481). The management device 20 sets L to a value obtained by summing the steady load stored in the load characteristic information storage unit 253 and the result of giving the above N to the load generation function (S482). The management apparatus 20 sets the value obtained by subtracting 100 from L as the processing load α to be delegated to another business server 10 (S483). The management apparatus 20 performs the following processing for each server information registered in the server information database 252.

  The management device 20 reads the latest load information corresponding to the site of the server information from the load information database 253 (S484). When the difference obtained by subtracting the CPU usage rate of the load information from 100 is larger than α (S485: YES), the management device 20 sets the delegation flag to “OK” (S486), otherwise (S485: NO), delegation The flag is set to “NG” (S487).

Next, the management device 20 performs an increasing tendency calculation process shown in FIG. 15 (S488).
The management apparatus 20 sets the time before the missing time to be t1 from the current time as t1 (S501), and sets the time before the missing time as t2 from the current time (S502). The management apparatus 20 corresponds to the server information site, reads the load information whose date and time is after t1 and before t2 from the load information database 253, and creates the list 1 (S503). Is read from the load information database 253 as list 2 (S504). The management apparatus 20 calculates cumulative variables for each of the lists 1 and 2 in order of date and time (S505). The management device 20 calculates an increase rate 1 by dividing a value obtained by subtracting the cumulative state variable for the first load information included in the list 1 from the cumulative state variable for the last load information included in the list 1 by the missing time. (S506). Similarly, the management apparatus 20 divides the value obtained by subtracting the cumulative state variable for the first load information included in the list 2 from the cumulative state variable for the last load information included in the list 2 by the missing time, and increases the increase rate. 2 is calculated (S507). The management apparatus 20 sets the difference obtained by subtracting the increase rate 1 from the increase rate 2 as an increasing tendency (corresponding to the third increase rate of the present invention) (S508).

  When calculating the increasing tendency as described above, the management device 20 calculates the distance between the installation position of the server information and the position of the typhoon included in the typhoon data and sets it as the distance from the typhoon (S489). .

  After the above processing is repeated for each business server 10, the management device 20 has the delegation flag “OK” and the smallest increase in the server information, or the shortest distance from the typhoon. A thing is determined as a transfer destination candidate (S490).

  The management apparatus 20 outputs the transfer destination candidate determined as described above (S425). FIG. 16 shows an example of a screen for outputting a transfer destination candidate. In the example of FIG. 16, the screen 60 displays a delegation flag, a free CPU, an increasing tendency, and a typhoon distance for each business server 10. The free CPU is a value obtained by subtracting the CPU usage rate from 100. That is, the free CPU indicates the computing capacity of the CPU that can be used in the business server 10. The increasing trend is not a specific value, but is “invariant” if the absolute value of the calculated increasing trend is less than or equal to a predetermined threshold, “increase” if the calculated increasing trend is a positive value, and a negative value If so, “decrease” is displayed.

  The administrator can easily determine the business server 10 to be delegated by referring to the screen 60. For example, when the administrator performs setting so that a part of the application program executed on the business server 10 having a high load is executed on the other business server 10 presented on the screen 60, the high It is possible to prevent a reduction in processing capacity of the load business server 10 and improve information processing efficiency in the entire information processing system.

  As described above, according to the information processing system of the present embodiment, when the increase rate of the currently input state variable approaches the increase rate of the cumulative value of the state variable input in the past, The fact that processing should be delegated to the business server 10 can be output. Therefore, before the business server 10 becomes a high load, it is possible to promptly delegate the processing to another business server 10 in advance. Therefore, it is possible to avoid a decrease in the processing performance of the business server 10 while delegating the processing to another business server 10. Therefore, it is possible to prevent a decrease in processing performance of the entire information processing system and perform efficient information processing.

  Further, according to the information processing system of the present embodiment, it is predicted whether or not the business server 10 will be heavily loaded based on changes in state variables at the time of past typhoons. Therefore, accurate prediction is expected for data that increases or decreases in conjunction with changes in weather, such as state change data from power facilities.

  Further, according to the information processing system of this embodiment, when it is predicted that the business server 10 will be heavily loaded, candidates for the business server 10 that can afford to perform the process when a part of the process is delegated are selected. This can be determined based on the usage rate of the CPU 201. Therefore, the delegated process can be reliably performed at the destination to which the process is delegated. In addition, the business server 10 having a low tendency to increase state variables or the business server 10 that is far from the typhoon can be preferentially selected as a delegation destination. Therefore, it is possible to present the business server 10 that is considered to have little change in the state variables due to the movement of the typhoon or the like as the delegation destination. Therefore, for example, after the process is delegated, in the delegation destination business server 10, the state variable increases due to the progress of the typhoon, and the delegation destination business server 10 is prevented from being overloaded. Can do.

  In this embodiment, it is assumed that information processing is performed by inputting status change data. However, the present invention is not limited to this, and the information processing system of this embodiment performs information processing according to all types of input data. It can cope with the case of doing.

  In the present embodiment, the typhoon scale is determined based on the maximum wind speed, but may be determined based on the central pressure of the typhoon. In this case, for example, when the central atmospheric pressure is 990 hp or more, the typhoon scale is “weak”, and when the central atmospheric pressure is 950 hp or more and less than 990 hp, the typhoon scale is “normal” and the central atmospheric pressure is 930 hp or more and less than 950 hp. , The typhoon scale is “strong”, the central pressure is 900 hp or more and less than 930 hp, the typhoon scale is “very strong”, and the central pressure is less than 900 hp, the typhoon scale is “furious”. It is.

  In the present embodiment, the business server 10 to which the process is transferred is determined according to the scale and position of the typhoon. However, the present invention is not limited to this, and the determination is made based on weather conditions other than the typhoon. Also good.

  In the present embodiment, it is assumed that model information is input. However, input of only the scale of the typhoon and the missing period is accepted, and the load information in the missing period is read from the load information database 253 and read. The model increase rate may be calculated based on the load information.

  Further, in the present embodiment, the business server 10 having the smallest increase tendency or the business server 10 having the shortest distance from the typhoon is determined as a candidate for delegation, but the thunder in the area where each business server 10 is installed. It may be determined where the number of occurrences is small.

  Although the present embodiment has been described above, the above embodiment is intended to facilitate understanding of the present invention and is not intended to limit the present invention. The present invention can be changed and improved without departing from the gist thereof, and the present invention includes equivalents thereof.

It is a figure showing the whole information processing system composition concerning this embodiment. 2 is a diagram illustrating a hardware configuration of a management device 20. FIG. 2 is a diagram illustrating a software configuration of a management device 20. FIG. It is a figure which shows the structural example of the model information memorize | stored in the model information database. It is a figure which shows the example which showed the state variable contained in state change log | history information on the graph. It is a figure which shows the structural example of the server information memorize | stored in the server information database. It is a figure which shows the structural example of the load information memorize | stored in the load information database. It is a figure which shows the structural example of the load characteristic information memorize | stored in the load characteristic information storage part 254. It is a figure which shows an example of the graph showing the change of the usage rate of CPU201 according to a state variable. FIG. 4 is a diagram showing a flow of processing in the management device 20. It is a figure which shows the flow of the output process of a transfer destination. It is a figure which shows the flow of a calculation process of a model increase rate. It is a figure which shows the flow of a calculation process of the present increase rate. It is a figure which shows the flow of a determination process of a transfer destination candidate. It is a figure which shows the flow of a calculation process of an increase tendency. It is a figure which shows the example of a screen which outputs a transfer destination candidate.

Explanation of symbols

DESCRIPTION OF SYMBOLS 10 Business server 20 Management apparatus 30 Weather data provision apparatus 40 Communication network 201 CPU
202 Memory 203 Storage Device 204 Communication Interface 205 Input Device 206 Output Device 211 Model Information Input Unit 212 Weather Data Acquisition Unit 213 Load Information Acquisition Unit 214 High Load Prediction Unit 215 Delegation Destination Output Unit 251 Model Information Database 252 Server Information Database 253 Load Information Database 254 Load characteristic information storage unit

Claims (9)

An information processing apparatus that performs information processing according to input data,
An input history storage unit that stores the data amount of the input data in association with the time when the input data is received;
A period input unit that receives an input of a period in which a problem has occurred in the information processing in the past;
The first cumulative value is calculated by adding the data amount of the input data input from the start time of the period to the end time of the period, and the calculated first cumulative value is the length of the period. A model increase rate calculation unit that calculates a first increase rate that is a quotient divided by the problem occurrence time;
From the time before the problem occurrence time before the current time, the data amount of the input data input up to the current time is summed to calculate a second cumulative value, and the calculated second cumulative value is A current increase rate calculation unit for calculating a second increase rate that is a quotient divided by the problem occurrence time;
A high-load prediction unit that determines whether or not the information processing apparatus has a high load depending on whether or not the difference between the first and second increase rates is equal to or less than a predetermined threshold;
An information processing apparatus comprising: The information processing apparatus according to claim 1,
Connected to multiple other information processing devices,
Data of the input data input from the time before the problem occurrence time to the current time for each of the other information processing devices when it is determined that the information processing device is highly loaded The amount is acquired, the acquired data amount is totaled to calculate a third cumulative value, and a third increase rate which is a quotient obtained by dividing the calculated third cumulative value by the problem occurrence time is calculated. A comparative increase rate calculation unit;
As a delegation destination of processing performed by the information processing apparatus, a delegation destination candidate output unit that outputs information indicating the other information processing apparatus having the smallest comparison increase rate;
An information processing apparatus comprising: An information processing apparatus according to claim 2,
A usage amount determination information storage unit that stores usage amount determination information for determining the amount of resources of the information processing device used by the information processing according to the data amount of the input data;
Based on the received data amount of the input data and the usage amount determination information, a planned usage amount, which is the amount of the resource to be used, is determined by performing the information processing according to the received input data. A usage determination unit;
If the determined scheduled use amount is greater than a predetermined value, the current use amount, which is the amount currently using the resource, is acquired from each of the other information processing devices, and the other information processing device has A free resource amount calculation unit that calculates a free resource amount that is a difference between the amount of the resource and the current usage amount;
With
The delegation destination candidate output unit includes information indicating the one having the smallest comparison increase rate among the other information processing devices having the free resource amount larger than the difference between the scheduled use amount and the predetermined value. Output as delegation destination,
An information processing apparatus characterized by the above. An information processing apparatus according to claim 2,
The input data is meteorological data;
An installation position storage unit for storing a position where the other information processing apparatus is installed;
Installation distance for calculating the distance between the position of the typhoon and the position where the other information processing apparatus is installed for each of the other information processing apparatuses when the weather data includes the position of the typhoon. A calculation unit;
With
The delegation destination candidate output unit determines the other information processing apparatus to be the delegation destination of the process according to the distance and the comparative increase rate;
An information processing apparatus characterized by the above. The information processing apparatus according to claim 4,
The input history storage unit stores the data amount of the weather data for each typhoon scale,
The period input unit receives an input of the typhoon scale together with the period,
For each typhoon scale, the model increase rate calculation unit sums the data amount of the weather data corresponding to the typhoon scale that is input from the start time to the end time, and Calculate the cumulative value of 1,
The current increase rate calculation unit, when the weather data includes the size of the typhoon, among the weather data corresponding to the size of the typhoon, from the time before the problem occurrence time to the current time among the weather data corresponding to the size of the typhoon To calculate the second cumulative value by summing the data amount of the input to
The delegation destination candidate output unit, when the difference between the first and second increase rates for the same typhoon scale is equal to or less than the predetermined threshold, the other information to be the delegation destination Outputting information indicating the processing device;
An information processing apparatus characterized by the above. An information processing apparatus according to claim 2,
An information processing apparatus comprising: a comparative increase rate list display unit that displays a list of the comparative increase rates for each of the other information processing apparatuses. The information processing apparatus according to claim 1,
A low-priority processing execution history storage unit that stores a time at which low-priority processing executed when the load on the information processing apparatus is lower than a predetermined value;
The period information input unit specifies a period in which the low priority process is not executed from the low priority process execution history storage unit, and sets the specified period as the period in which the problem has occurred.
An information processing apparatus characterized by the above. The information processing apparatus according to claim 1,
A model information input unit that receives input of model information including a data amount of the input data input in the past and a time when the input data is input;
The model increase rate calculation unit calculates the first cumulative value by summing the data amount included in the model information corresponding to the time from the start time to the end time;
An information processing apparatus characterized by the above. A method of performing information processing according to input data,
A computer that is communicably connected to another information processing apparatus
Accepting the input data;
Corresponding to the time when the input data is received, the data amount of the input data is stored, and an input during a period when a problem has occurred in the information processing in the past is received,
The first cumulative value is calculated by summing the data amount of the input data input from the start time of the period to the end time of the period, and the calculated first cumulative value is the length of the period. To calculate the first rate of increase, which is the quotient divided by the problem occurrence time
The second cumulative value is calculated by summing the data amount of the input data input up to the current time from the time before the problem occurrence time before the current time, and the calculated second cumulative value is Calculate the second rate of increase, which is the quotient divided by the problem occurrence time,
Determining whether or not the information processing apparatus is subjected to a high load according to whether or not a difference between the first and second increase rates is equal to or less than a predetermined threshold;
An information processing method characterized by the above.

Images