JPH11203151A - Method for estimating batch processing time - Google Patents

Abstract

PROBLEM TO BE SOLVED: To automatically find out an operation environment plan of a computer system which reduces batch processing time by seeking the operation environment plan and a job scheduling plan of a computer system which realize the reduction of batch processing time. SOLUTION: A parameter producing part 200 produces parameter information that is used for simulation based on data of a basic data part which sets operation environment value that can be configured by a computer system 001. A job scheduling analyzing part 004 performs simulation with produced parameter information as input information and gets batch processing time in an operation environment that is designated by the parameter information. A simulation controlling part 400 controls the part 004 and seeks an operation environment plan and a job scheduling plan of a computer system which realize the reduction of a batch processing time by repeating the simulation, while changing parameter information.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a method for predicting batch processing time in a computer system in which a plurality of jobs can operate in parallel.

[0002]

2. Description of the Related Art As a prior art, Japanese Patent Application Laid-Open No. 8-28695
No. 8 discloses a technique disclosed in Japanese Patent Publication No. JP-A-8-2869
No. 58 is intended to improve batch job scheduling efficiency, and to assist in effective job schedule planning based on past execution history information before performing batch processing. Provides a job scheduling analysis method that can perform job scheduling and, when there is a change in system operation such as job multiplicity, it is possible to estimate the result before the change based on the past execution history A job scheduling analysis method is provided.

[0003]

In the above prior art, in order to improve the scheduling efficiency of a batch job, it is necessary to change parameter information at the time of simulation, and to find out parameter information where the effect appears through trial and error. In addition, it was not possible to automatically find an effective job schedule.

Further, prior to the change of the system operation environment, the effect is estimated before the change, and the operation environment plan of the computer system which can reduce the batch processing time cannot be automatically found.

The present invention is directed to predicting a reduction in batch processing time, and has the following objects.

SUMMARY OF THE INVENTION It is an object of the present invention to provide a computer system operating environment plan and a job schedule plan that can reduce batch processing time.

[0007]

In order to achieve the above object, there is provided a job scheduling analysis section for analyzing job scheduling by simulation.
Parameter information to be input to the job scheduling analysis unit is provided. A parameter generation unit for generating parameter information is provided. A basic data section for storing information necessary for the simulation is provided. A simulation control unit for controlling the simulation is provided.

A parameter generation unit generates parameter information to be used for a simulation, based on data in a basic data section for setting an operation environment value that can be configured in a computer system. A simulation is performed by the job scheduling analysis unit using the generated parameter information as input information,
Get the batch processing time in the operating environment specified by the parameter information. The job scheduling analysis unit is controlled by the simulation control unit, and the simulation is repeated while changing the parameter information, thereby obtaining an operating environment plan and a job schedule plan of the computer system for realizing the reduction of the batch processing time.

[0009]

DESCRIPTION OF THE PREFERRED EMBODIMENTS As a method of analyzing job scheduling by simulation, a method disclosed in Japanese Patent Application Laid-Open No. 8-286958 is mentioned as an example. For this reason, the job scheduling analysis unit 004 used for describing the present invention and the parameter information 005 serving as input information of the job scheduling analysis unit
Are described in JP-A-8-286958, a job scheduling analysis unit 104, and
The description of the parameter information 114 is referred to, and the description is omitted here.

An embodiment of the present invention will be described in detail with reference to the drawings.

FIG. 1 shows a basic system configuration of an embodiment of the present invention.

Using the data of the basic data section 100, a parameter generation section 200 generates parameter information necessary for simulation. Simulation control unit 40
At 0, the simulation is controlled, and the result of the simulation is stored in the result storage unit 500.

The basic data section 100 has information necessary for simulation. In the basic data section, a range that can be set in the parameter information 005 and an operation condition value are specified from an operation environment that can be configured by the computer system. FIG. 2 shows a lower limit value 20, an upper limit value 40,.
Is shown.

The parameter generation unit 200 includes a basic data unit 1
Using the information designated as 00, parameter information necessary for the simulation is generated.

The parameter information storage unit 300 is configured as shown in the configuration example of FIG.

The record 301 has a list structure, and is configured to sequentially point to the next record by a pointer. It is created when the basic data section 100 is read by the parameter generation section 200.

Next, the flow of processing of the parameter generation unit 200 will be described with reference to the flowchart of FIG.

First, designated information is read from the basic data section 100 (step 201).

Based on the read information, step 203
Is continued until parameter information of all combinations is created (step 202).

The created parameter information is stored in the parameter information storage unit 300 (step 203). For storage, an area for a record to be newly stored is secured, information is stored in the area, and information for forming a list structure such as setting of a pointer for the new record from a list is set.

Thereafter, the process returns to step 201 to create the next parameter information.

The result storage unit 500 is roughly divided into a current result storage unit 501 and a simulation result storage unit 502 as shown in the configuration example of FIG.

The current result storage unit 501 is used when the simulation control unit 400 stores data of the current computer system.

The record 503 of the simulation result storage unit 502 has a list structure, and is configured to sequentially point to the next record by a pointer. It is used when the result of the simulation performed by the simulation control unit 400 using the parameter information 005 is stored.

Next, the flow of processing of the simulation control section 400 will be described with reference to the flowchart of FIG.

The simulation control unit 400 first
The simulation is performed without using the simulation execution condition of the parameter information 005 (step 40).
1). As a result, the operating environment of the current computer system,
And, it obtains how the job schedule is performed.

The simulation execution result is stored in a result storage unit 5.
00 is stored in the current state analysis result storage unit 501 (step 402).

Data is read from the parameter information storage unit 300, and the processing from step 404 to step 406 is continued until there is no more data in the parameter information storage unit 300 (step 403).

If there is data in the parameter information storage section 300, the read data is set in the parameter information 005 (step 404).

A simulation is performed using the set parameter information 005 as a simulation execution condition (step 405).

The simulation execution result is stored in a result storage unit 5.
00 is stored in the simulation result storage unit 502 (step 406). For storage, while securing an area for newly storing records, storing information in that area,
Information for forming the list structure, such as setting a pointer from the list for the new record, is set. When configuring the list structure, the batch processing time is configured as a key item so as to be in ascending order.

Thereafter, the flow returns to step 403.

When there is no more data in the parameter information storage unit 300, the information in the result storage unit 500 is output (step 407).

Next, an output example of the result 600 is shown in FIG.
The output information includes the current computer system environment 601
And parameter information at the time of simulation, and a batch processing time 602 obtained by simulation. A list 601 in FIG. 7 indicates that the current computer system environment has a job multiplicity of 30,... And the time required for batch processing is 12 hours and 10 minutes. Severe 40, ...
When the operating environment of the system is changed, the time required for batch processing is 9 hours and 45 minutes, and the ratio with the batch processing time of the current system environment is predicted to be 80%.

[0035]

According to the present invention, it is possible to obtain a computer system operating environment plan and a job schedule plan that realize a reduction in batch processing time.

[Brief description of the drawings]

FIG. 1 is an embodiment of a computer system for realizing a batch processing time prediction method according to the present invention.

FIG. 2 is an explanatory diagram of a basic data section 100 serving as input information of the present invention.

FIG. 3 is an explanatory diagram showing a structure of a parameter information storage unit 300 of the present invention.

FIG. 4 is a flowchart illustrating a processing flow of a parameter generation unit 200 according to the present invention.

FIG. 5 is an explanatory diagram showing a structure of a result storage unit 500 according to the present invention.

FIG. 6 is a flowchart illustrating a processing flow of a simulation control unit 400 according to the present invention.

FIG. 7 is an explanatory diagram of a result 600 serving as output information of the present invention.

[Explanation of symbols]

001: Computer, 002: CPU, 0
03: memory, 004: job scheduling analysis unit, 005: parameter information, 100: basic data unit, 200: parameter generation unit, 300: parameter information storage unit, 400: simulation control unit, 5
00: result storage unit, 600: result.

Claims (1)

[Claims] 1. A computer system capable of operating a plurality of jobs in parallel, wherein a batch operation time plan and a job schedule plan for a computer system realizing a reduction in batch processing time are obtained. How to reduce processing time.