JP2003241981A - Method for taking over data between computers - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To shorten the processing time of data takeover by enabling the execution of job groups performing the takeover of intermediate data on differ ent computers in parallel. <P>SOLUTION: A data takeover judgment part 6 finds out a processing capable of taking over data between computers on the basis of file access histories acquired by system operation information acquisition parts 8 and 9, and a batch processing conversion part 7 forms a batch processing for performing the data takeover processing between computers on the basis of this result. Job schedulers 10 and 11 execute the batch processing for performing the data takeover processing between computers, and input and output management parts 12 and 13 perform synchronous control between input and output jobs, whereby the jobs performing the data takeover processing between different computers are executed in parallel. <P>COPYRIGHT: (C)2003,JPO

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a method for taking over data between computer systems, and more particularly to a method for taking over data between computers for efficiently carrying out data between a plurality of computers.

[0002]

2. Description of the Related Art When data is transferred between a job (processing unit in a computer) and another job, a writing-side job first stores a file composed of inherited data in a storage device, A method in which a job on the reading side starts accessing the file and reads the inherited data after the access to the file is completed is widely used.

According to this method, the file access from the read job cannot be started while the data writing to the data takeover file is completed halfway. This is because the current computer only performs file-by-file synchronous processing when accessing a general file, and access on the writing side and reading side cannot be performed at the same time. Therefore, in the above method, the writing job and the reading job cannot be executed in parallel.

Japanese Patent Laid-Open No. 1-180316 discloses that when data is transferred from a job being executed on the same computer to another job,
In particular, a data transfer method is disclosed when it is not necessary to store data to be transferred. In this method, the write job and the read job access the same file at the same time, and the synchronization is realized not on a file basis but on a record basis constituting a file. Therefore, the feature is that the file access on the writing side and the reading side can be executed in parallel. As a result, processing time is shortened and CP
U overhead can be reduced.

In these methods, the takeover data is temporarily stored in the data takeover area prepared in the main memory or a storage device equivalent thereto. Input / output execution history information for enabling synchronization in record units is also prepared in the main memory or a storage device conforming thereto. These storage devices must be unique to each computer.

By the way, the operation of the computer system, including the job for carrying out the data takeover process, consists of sequentially executing a series of jobs according to a certain rule. Such processing is called batch processing. In batch processing, the same processing is repeated at regular intervals such as one day or one month. A computer system that executes batch processing has a function of recording a job execution history such as accessing a normal file. By examining the job execution history, it is possible to know the contents of the batch processing to some extent. For example, as described above, batch processing repeats the same processing at regular intervals, so if there is a record of file access in the job execution history, file access is repeated every time batch processing is executed. it is conceivable that.

[0007]

The method shown in the conventional example is a method of taking over data between jobs executed by the same computer, and a buffer area and a buffer area are provided in a storage area unique to one computer. Secure the input / output execution history information,
Data inheritance processing is possible while synchronizing in record units. However, in a plurality of computer systems sharing a storage device, the publication does not disclose a case where data is handed over between jobs executed by different computers.

Further, in order to perform the data transfer processing between computers, it is necessary to first find a job to which the data transfer processing between computers can be applied from the existing jobs and change the corresponding job. .

An object of the present invention is to provide a method for finding a job to which data inheritance processing can be applied from jobs being executed by different computers in a computer system sharing a storage device. It is to provide a data transfer method between computers that enables a write job and a read job that perform data transfer processing to be executed in parallel.

[0010]

[Means for Solving the Problems] Typical means for solving the above problems are as follows.

A method of transferring data between computers according to the present invention is a computer system in which a plurality of computers share a storage device, and a job consisting of a series of sequentially executed processes is executed by the plurality of computers. Using the operation information including the file name, the file access start time, the file access end time, the access order of the records in the file, and the access type (discrimination between reading and writing). Both the first process and the second process that make up the job access the same file, the first process is a write process for the file, and the second process is a read process for the file. Yes, and the file access end time for the file in the first process is before the second process. The access order of the in-file records to the file in the first processing is earlier than the file access start time to the file, and the access order of the in-file records to the file in the second processing is equal to the access order. A step of discovering one process and a second process, a step of creating a first job consisting of only the first process and a second job consisting of only the second process, the first job and the above Executing the second job on a different computer of the computer system.

The data transfer method between computers according to the present invention is a computer system in which a plurality of computers share a first external storage device and a second external storage device. A computer that reads the series of data written by a second job executed by a second computer after the first job executed by the computer completes writing the series of data in the first storage device. In the system, a step of accepting a data write request from the first job to the first external storage device by a first operating system that controls the first computer; and the first operating system, Changing the write request to write to the second external storage device instead of the first external storage device and writing the data; The rating system notifies the second operating system controlling the second computer of the completion of writing, and the second operating system is configured to execute the second job of the second job being executed by the second computer. Trapping a write request to one external storage device, wherein the second operating system receives the completion notification from the first operating system and replaces the first external storage with the second external storage device. Reading data from the external storage and passing the data to the second job.

[0013]

The same file is accessed from the system operation information, the first process is a write process for the file, the second process is a read process for the file, and the first process is a read process for the file. The file access end time for the file of the first process is earlier than the file access start time for the file of the second process, and the access sequence of the records in the file for the file of the first process is the file of the second process. Equal to the access order of records in the file for
Discover the first process and the second process. Even if the first process and the second process satisfying this are executed in parallel, the data can be taken over.

When the first process and the second process are executed in parallel, if they are executed on another computer of the system, the parallelism becomes higher. Therefore, in the next step, if the first process and the first process are executed in the same job, the job is the first job that performs the same operation as the first process, and the second process. Convert to a second job that does the same operation as. When accessing the same file in the same job, the first access must always be completed before the next access is started.However, by dividing the original job into two jobs, the same file can be accessed. It is possible to perform access at the same time. Furthermore, by executing the first job and the second job on different computers, the effect of parallel execution becomes higher.

In order to properly perform the data transfer processing between the first job and the second job executed on different computers, the information shown below is used to perform the data transfer processing between the output processing and the input processing. Performs synchronous control.

In the shared storage device, a data takeover recording area for managing transfer of intermediate data between an output job and an input job and a data takeover buffer area are provided. Using the information provided in the data transfer recording area, the output job sequentially writes the data in the buffer area, and the input job sequentially reads the data from the buffer area. At this time, if there is no space in the buffer, the output job is put in the wait state, and when there is space, the output job is released from the wait state. If the required data is not output to the buffer, the input job is put into the wait state, and when the required data is output, the wait state of the input job is released. In this way, data transfer is performed between the output job and the input job that are being executed in parallel, based on the information in the data transfer recording area.

In this way, in a computer system consisting of a plurality of computers sharing a common storage device,
Jobs can be executed in parallel even when data is handed over between jobs executed on different computers. As a result, the elapsed processing time can be shortened.

[0018]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS FIG. 1 is a diagram showing the principle of the present invention. In FIG. 1, 1 and 2 are computers. Reference numerals 3 and 4 are storage devices unique to the computer 1 and the computer 2, respectively. A shared storage device 5 is connected to both the computer 1 and the computer 2.

Reference numeral 6 is a data inheritance determination unit. Reference numeral 7 is a batch processing conversion unit. The data transfer determination unit 6 and the batch processing conversion unit 7 need only be present in the operating system of any one or more computers in the computer system, and in the present embodiment, they are placed in the operating system of the computer 1. To do. Reference numeral 8 is a system operation information acquisition unit of the computer 1. Reference numeral 9 is a system operation information acquisition unit of the computer 2. Reference numeral 10 is a job scheduler of the computer 1, and 11 is a job scheduler of the computer 2. 1
Reference numeral 2 is an input / output management unit of the computer 1, and 13 is an input / output management unit of the computer 2. Reference numeral 14 is a synchronization processing unit of the computer 1, and 15 is a synchronization processing unit of the computer 2. Reference numeral 16 is a record processing unit of the computer 1, and 17 is a record processing unit of the computer 2. Reference numeral 18 is a batch processing recording file placed in the unique storage device 3 of the computer 1. Reference numeral 19 is a batch processing recording file placed in the unique storage device 4 of the computer 2. Reference numeral 22 is a convertible job recording file placed in the shared storage device 5. Reference numeral 23 is a data transfer record file placed in the shared storage device 5. Reference numeral 24 denotes a data takeover buffer area placed in the shared storage device 5.

Known system operation information acquisition units 8 and 9
Records in the access history recording files 20 and 21 the history of all file accesses executed during the operation on the computers 1 and 2, respectively. The access history recording files 20 and 21 are used for discovering a process capable of transferring data between systems. Details of the process will be described with reference to FIG.

FIG. 2 is a configuration diagram of access history records written in the access history recording files 20 and 21 by the system operation information acquisition units 8 and 9. The system operation information acquisition units 8 and 9 use the file name 2 when the file access from the job being executed on the local computer is completed.
01, file access start time 202, file access end time 203, in-file record access order 204, access type 205, accessed job name 206, computer name that executed the accessed job 2
The access history record 200 including 07 and is added to the access history recording file 20 or 21. The access history record record 200 is used for discovering a process that can transfer data between systems, and the details of the method of use will be described with reference to FIG.

FIG. 3 is a process flow chart when the data takeover judging unit 6 searches for a process capable of taking over data between computers based on the access history recording files 20 and 21.

First, one arbitrary record is taken out from the access history recording files 20 and 21, and the record is set as record 1 (step 301). Next, records other than the record 1 are arbitrarily extracted from the access history recording files 20 and 21, and the record is set as the record 2 (step 302).

The following checks are performed on record 1 and record 2. That is, the used file names 201 in the record 1 and the record 2 are equal (step 303), the access type 205 in the record 1 is “write processing” (step 304), and the access type 205 in the record 2 is Is "reading process" (step 305), and the access end time in record 1 is 20
3 is earlier than the access start time 202 in record 2
(Step 306) And it is checked whether the record access order 204 in the record 1 and the record access order 204 in the record 2 are the same (step 307).

When the record 1 and the record 2 satisfy the above condition, the inter-system data transfer determination unit 6 determines
1 is added to the convertible job recording file 22 (step 308). At this time, in the newly added convertible job record record 400, the access job name 206 in record 1 is stored as the output job name 401, and the computer name 207 in record 1 is output job execution computer name 40.
Stored as 2, and access job name 2 in record 2
06 as the input job name 403 and record 2
Enter the computer name 207 in the job execution computer name 40
4 and the file name 201 in record 1 is stored as a file name 405. Since it is possible to access the same file repeatedly within one job, the output job name 401 and the input job name 403 may be the same.

The record 1 and the record 2 are step 303.
If the conditions of Step 307 to Step 307 are not satisfied, if another record exists in the access history record files 20 and 21, Step 3 is performed for those records.
02 to step 308 are sequentially repeated (step 30
9).

Steps 301 to 309 are repeated for the case where all the access history record records existing in the access history record files 20 and 21 are set to record 1 (step 310). At this time, regarding the processing determined to be able to take over the data between the systems, the information is written in the changeable job recording file 22. The convertible job recording file 22 created here is used when creating a job for performing data transfer processing between computers thereafter, and the details will be described with reference to FIG.

The job schedulers 10 and 11 are known techniques. Job schedulers 10 and 11
Executes jobs sequentially based on the batch process recording files 18 and 19. The batch process recording files 18 and 19 are job description records 5 having the structure shown in FIG.
It consists of 00. The job description record 500 includes a job name 501, execution program information 502, and access file information 503. Only one job name 501 can be stored in one job description record, but a plurality of execution program information 502 and access file information 503 can be stored. When the job schedulers 10 and 11 execute the jobs described in the job description record 500, they sequentially execute the programs specified by the execution program information 502 in the job description record 500, and the job description record 50
The files designated by the access file information 503 within 0 are sequentially accessed.

Generally, when batch processing is performed in a computer system, the same batch processing record file is used at regular intervals such as one day or one month. Therefore, normally, the same batch process is executed every cycle of a fixed period. On the contrary, by changing the content of the batch process recording file to be used, it becomes possible to perform a new process from the time when the batch process is executed in the next cycle. In the present embodiment, the batch processing conversion unit 7 changes the contents of the batch processing recording files 18 and 19 in order to carry out the inter-system data transfer by utilizing the nature of this batch processing execution.

The batch processing converting section 7 is a section for changing the batch processing recording files 18 and 19 based on the changeable job recording file 22 created by the data transfer determining section 6. As described above, by rewriting the batch process recording files 18 and 19, the inter-system data transfer process can be executed.

FIG. 6 is a processing flowchart when the batch processing conversion unit 7 changes the batch processing recording files 18 and 19 for carrying out the data transfer processing based on the changeable job recording file 22.

First, one arbitrary changeable job record record 400 is taken out from the changeable job record file 22 (step 601). As described above, the changeable job record record 400 includes the output job name 401 and the input job name 403 of the process determined to be capable of transferring data between systems. Here, the output job name 401 is job 1 and the input job name 403 is job 2 (step 602).

Next, batch processing recording files 18 and 1
A job description record 500 having a job name equal to job 1 or job 2 is searched from among 9 and set as record 1 and record 2, respectively (step 603). Here, the subsequent processing differs depending on whether job 1 and job 2 are the same job or not.

If job 1 and job 2 are the same job (step 604), record 1 and record 2 are the same record. During execution of the job described by the record, the same file is sequentially accessed for writing and reading. So the job description record 500 for the job
There are file access information 503 for write access to the file and file access information 503 for read access to the file. Here, two new job description records 500 are created (step 605), and the job description records 500 are referred to as record 3 and record 4, respectively. Job names 501 belonging to record 3 and record 4 store arbitrary job names unique in the system. Further, the execution program information 502 and the access file information 503 of the record 3 store the execution program information 502 and the access file information 503 of the part of the job 1 in which the writing process to the file is described. Further, in the execution program information 502 and the access file information 503 of the record 4, the job 1 is recorded, respectively.
Execution program information 502 and access file information 5 of the part that describes the reading processing from the file
Stores 03. The newly created record 3 and record 4 are replaced with new record 1 and record 2, respectively.
(Step 606).

The following processing is commonly performed when job 1 and job 2 are the same job and when they are not.

The record 1 and the record 2 each have access file information 503 which describes access processing to the file used for data transfer. The file name of that portion is rewritten to the name of the data transfer file defined by the system (step 607).
However, the file name must be unique within the system. At the time when the job is actually executed, the input / output management units 12 and 13 of each computer judge whether or not to carry out the data transfer between the systems based on this file name.

Next, the newly created or modified record 1 and record 2 are replaced with the original record 1 and record 2 by the batch processing recording file 18 or 19
To store. Here, the batch processing recording files 18 and 19 are unique to each computer 1 or computer 2. Therefore, in order to transfer data between the systems, the newly created or changed record 1 and record 2 must be stored in the batch processing recording files 18 or 19 of different computers.

When Job 1 and Job 2 are originally executed on different computers, that is, when the output job execution computer name 402 and the input job execution computer name 404 in the convertible job record record 400 are different ( Step 608), record 1 is stored in the batch processing recording file 18 or 19 of the computer indicated by the output job execution computer name 402, and record 2 is stored in the batch processing recording file 18 or 19 of the computer indicated by the input job execution computer name 404. (Step 609).

When the output job execution computer name 402 and the input job execution computer name 404 in the convertible job record 400 are the same, the two jobs are jobs that were conventionally executed on the same computer. In this case, the record 1 is stored in the batch processing recording file 18 or 19 of the computer indicated by the output job execution computer name 402 and the input job execution computer name 404, and the record 2 is stored in the batch processing recording file 18 or 1 of another computer other than that.
9 (step 610).

All changeable job record records 40
The processing shown in steps 601 to 610 is repeated for 0 (step 611). By applying the new batch process recording files 18 and 19 created here, it is possible to recognize whether or not the process can be inherited from the next batch process execution.

The job schedulers 10 and 11 of the respective computers use the newly created job processing record file 18
Batch processing is executed in the same manner as in the conventional method on the basis of Nos. 19 and 19. At this time, the job schedulers 10 and 11
Does not care whether the job to be executed is performing the transfer of data between systems. The inter-system data transfer processing is performed when an input / output request from the job is issued to the input / output management units 12 and 13 during execution of the job. At that time, the data to be handed over between jobs is stored in the data takeover buffer area 24 by the record processing units 16 and 17 of each computer. Further, the input / output management units 12 and 13 of each computer utilize the information stored in the data takeover recording file 23 in order to normally perform the synchronous control of the data takeover of one record unit between the output process and the input process. The information stored in the data transfer record file 23 is in the form of the data transfer record record 700 shown in FIG. 7 for each data transfer process.

The data transfer record record 700 is stored in the intersystem shared storage device 5 by the synchronous processing unit 14 or the synchronous processing unit 15 when either the writing job or the reading job first issues the open command. It is added to the data transfer record file 23. at the same time,
The data takeover buffer area 24 for temporarily storing the takeover data is also secured in the intersystem shared storage device 5. The data takeover record record 700 and the data takeover buffer area 17 are deleted from the shared storage device 5 when both the write job and the read job issue a close command.

In the data transfer record 700 shown in FIG. 7, the file name 701 records the file name designated by the output job and the input job at the time of file access. Data transfer is supported by this file name. In the buffer address 702, the start address of the corresponding data takeover buffer area 24 is recorded. In the block number 703 of the buffer, the block number of the corresponding data takeover buffer area 24 is recorded. In the data input / output unit length 704, the length of data (data length) handled at the time of one input / output specified at the time of starting the output job and the input job is recorded. In the write block number 705, the block number in the data takeover buffer area 24 in which data is written when the output job next issues an output command is recorded. The read block number 706 records which block number of data in the data transfer buffer area 24 is input when the input job issues an input command. In the write count 707, the number of times data is written in the data transfer buffer area 24 due to the output command issuance of the output job is recorded. The number of times of reading 708 records the number of times of reading the data from the data transfer buffer area 24 by issuing the input command of the input job.

The output job open flag 709 is a flag indicating whether or not the output job has issued the open command. When the output job issues an open command, the output job open flag 709 is turned on. However,
When the output job issues an open command, the open flag 70 already in the data transfer record file 23
If 9 is ON, it means that another output job is being accessed, so the input / output management units 12 and 13 prohibit access from the output job.

The input job open flag 710 is a flag indicating whether or not the input job has issued the open command. When the input job issues an open command, the input job open flag 710 is turned on. However,
When the input job issues the open command, the open flag 71 in the data transfer record file 23 has already been entered.
If 0 is ON, it means that another input job is being accessed, so the input / output management units 12 and 13 prohibit access from the input job.

The output job close flag 711 is a flag indicating whether or not the output job has issued a close command. When the output job issues a close command, the output job close flag 711 is turned on. The input job close flag 712 is a flag indicating whether or not the input job has issued a close command. When the input job issues a close command, the input job close flag 712 is turned on.

The output job wait flag 713 is a flag indicating whether or not the output job is in a wait state. When the output job is in the wait state, the output job wait flag 713 is turned on, and when the wait state is released, the output job wait flag 713 is turned off. The input job wait flag 714 is a flag indicating whether or not the input job is in a wait state. When the input job is in the wait state, the input job wait flag 714 is turned on, and when the wait state is released, the input job wait flag 714 is turned off.

The output processing computer name 715 is the name of the computer that is executing the output job. Input processing computer name 7
Reference numeral 16 is the name of the computer that is executing the input job. It is recorded when each job starts access.

Data to be handed over between jobs is stored in order from the beginning of the data takeover buffer area 24. At this time, there may be a situation in which the amount of data to be taken over is larger than the number of blocks in the data taking-over buffer region 24 and all the data cannot be stored in the data taking-over buffer region 24. In such a case, the data takeover process is continued by reusing the data takeover buffer area 24. In other words, since the data that has already been written and read is unnecessary, new data may be overwritten in the area storing the relevant data. In this way, when the data is written up to the end of the data takeover buffer area 24, the processing is continued by returning to the beginning of the data takeover buffer area 24. However, when the data of the corresponding block in the data transfer buffer area 24 has not been read yet, the input / output management units 12 and 13 make the output processing job wait. On the contrary, when new data is not written in the corresponding block in the corresponding data transfer buffer area 24, the input / output management units 12 and 13 make the input processing job wait.

Here, it is possible to secure a large data transfer buffer area 24 in advance so that all the transfer data can be stored. However, the amount of data to be transferred normally is not known in advance, and the memory is effective. In this embodiment, as described above, the data takeover buffer area 24 is reused in order to utilize the data. However, also in the present embodiment, when the amount of data to be handed over between jobs is smaller than the number of blocks in the data takeover buffer area 24, the processing ends without reusing the data takeover buffer area 24.

In order to carry out the data takeover processing on a record-by-record basis while reusing the data takeover buffer area 24, the data takeover recording record 700 is used and the synchronization processing units 14 and 15 use the data takeover recording record 700 as described above. The output side processing and the input side processing must be controlled synchronously. The details of the synchronization processing executed by the synchronization processing units 14 and 15 are shown in FIG. 8 and FIG. 9 separately for the writing processing and the reading processing.

FIG. 8 is a flow chart of processing when the synchronization processing units 14 and 15 receive a file write request from a job. When there is a data write request, the instruction is first trapped (step 801). Further, it is judged whether or not the write request is made to the data transfer file (step 802).
The above-described determination is to search all the records in the data transfer recording file 23, and execute whether or not there is a record in which the file name 701 matches the file name for which the write request is issued. Done by.

If the write request is not made to the data transfer file, the normal output procedure is executed (step 803). If it is a write request made to the data transfer file, it is continuously determined whether data can be written in the data transfer buffer area 24 (step 804). Here, if the difference between the write block number 705 and the read block number 706 in the data transfer record record 700 corresponding to the file is equal to the buffer block number 703, the data transfer failure in the data transfer buffer area 24 is not possible. It is determined that the data is writable, and in other cases, it is determined that the data can be written.

When it is judged that the data cannot be written, the job which issued the write request is made to wait, and the output job wait flag 713 is turned on (step 80).
5). The operating system of the computer that is executing the output job in the wait state releases the wait state of the output job and turns off the output job wait flag 713 at the time of receiving the notification of the release cancellation of the output job (step 806). After that (step 807), the following processing is continued. Here, the wait / unwait execution of a job can be executed only by the operating system that is executing the job. Therefore, when it is desired to cancel the wait state of a job being executed by another computer, it is necessary to notify the operating system of the computer executing the job in this way.

Next, the data transfer buffer area 24
Of these, data is written in the block indicated by the write block number 705 (step 808), and the write block number 705 and the write count 707 are updated (step 809).
To do. Here, when the write block number 705 exceeds the block number 703 of the buffer, the value of the write block number 705 is returned to 1.

Further, the input job wait flag 714 is on (step 810), and the difference between the number of times of writing 707 and the number of times of reading 708 is the number of blocks in the buffer 703.
(Step 811), the operating system of the input processing computer name 716 is notified (step 812). The operating system of the computer that has received the notification releases the wait state of the corresponding input job.

By the way, if the wait / wait release control occurs frequently, the processing time may be lengthened due to the influence thereof. Therefore, in this embodiment, the wait state of the input job is not released when at least one data is written in the data transfer buffer area 24, but the input job Cancel the wait state. If this method is adopted, there is no waiting again while inputting data for at least one round of the buffer. As a result, the job released from the wait state is repeatedly waited immediately after that, which prevents the processing time from becoming long.

FIG. 9 is a flow chart of processing when the synchronization processing units 14 and 15 receive a request for reading a file from a job. When there is a data write request, the instruction is first trapped (step 901). Further, it is judged whether or not the read request is made to the data transfer file (step 902).
This determination is performed by searching all the records in the data transfer recording file 23 and executing whether or not the record in the records has the file name 701 that matches the file name for which the read request is issued. Done.

If the read request is not made to the data transfer file, a normal input procedure is executed (step 903). If it is a read request made to the data transfer file, it is continuously determined whether data can be read from the data transfer buffer area 24 (step 904). Here, the write block number 70 in the corresponding data transfer record
When 5 and the read block number 706 are equal, it is determined that the data cannot be read from the data transfer buffer area 24, and in other cases, it is determined that the data can be read.

When it is determined that the data cannot be read, the job that issued the read request is made to wait and the input job wait flag 714 is turned on (step 90).
5). The operating system of the computer that is executing the input job in the wait state cancels the wait state of the input job and turns off the input job wait flag 714 at the time of receiving the notification for canceling the wait of the input job (step 906). After that (step 907), the following processing is continued.

Next, the data transfer buffer area 24
Of these, the data is read from the block indicated by the read block number 706 (step 908), and the read block number 706 and the read count 708 are updated (step 90).
9) Do. At this time, if the read block number 706 exceeds the buffer block number 703, the value of the read block number 706 is returned to 1.

Further, when the output job wait flag 713 is on (step 910) and the number of writes 707 and the number of reads 708 are equal (step 911), the operating system of the output processing computer name 715 is notified (step 910). 912) The operating system of the computer which received the notification releases the wait state of the corresponding output job.

Similar to the case of canceling the wait state of the input job shown in FIG. 8, when canceling the wait state of the output job, a measure is taken to prevent frequent wait / wait cancel control. That is, when there is an output job that is waiting, it is possible to cancel the wait state of the output job when at least one free block occurs in the data transfer buffer area 24. The wait state of the output job is released when all the blocks in the buffer area 24 have become empty. At this time, the output job does not wait again while at least the data for one round of the buffer is output. That is, it is possible to prevent the wait / wait release control from being frequently performed.

As described above, according to the present embodiment, in a computer system sharing a storage device, when data is taken over between systems, it is possible to take over the data not in file units but in record units. Next to
Write access and read access to the same file can be executed simultaneously. As a result, it is possible to shorten the processing time of the data transfer processing between the systems.

[0065]

According to the present invention, in a computer system sharing a storage device, a group of jobs for inheriting intermediate data can be executed in parallel on different computers.
The processing time can be shortened.

[Brief description of drawings]

FIG. 1 is an explanatory view of the principle of the present invention.

FIG. 2 is an explanatory diagram of an access history record record.

FIG. 3 is an explanatory diagram of a convertible job record record.

FIG. 4 is a processing flowchart of a data takeover determination unit.

FIG. 5 is an explanatory diagram of a job description record.

FIG. 6 is a processing flowchart of a batch processing conversion unit.

FIG. 7 is an explanatory diagram of a data transfer record.

FIG. 8 is a flowchart of a data writing process.

FIG. 9 is a flowchart of a data reading process.

[Explanation of symbols]

1, 2 ... Computer, 3, 4 ... Unique storage device, 5 ... Shared storage device, 6 ... Data transfer determination unit, 7 ... Batch processing conversion unit, 8, 9 ... System operation information acquisition unit, 10, 11 ... Job scheduler , 12, 13, ... Input / output management unit, 14,
15 ... Synchronous processing unit, 16, 17 ... Record processing unit, 1
8, 19 ... Batch processing recording file, 20, 21 ... Access history recording file, 22 ... Convertible job recording file, 23 ... Data transfer recording file, 24 ... Data transfer buffer area.

─────────────────────────────────────────────────── ───

[Procedure amendment]

[Submission date] February 17, 2003 (2003.2.1
7)

[Procedure Amendment 1]

[Document name to be amended] Statement

[Name of item to be amended] Claims

[Correction method] Change

[Correction content]

[Claims]

   ─────────────────────────────────────────────────── ─── Continued front page    (72) Inventor Masayuki Inoue             5030 Totsuka Town, Totsuka Ward, Yokohama City, Kanagawa Prefecture             Ceremony Company Hitachi Software Development Division (72) Inventor Hirofumi Nagasuka             1099 Ozenji, Aso-ku, Kawasaki City, Kanagawa Prefecture             Ceremony company Hitachi Systems Development Laboratory F-term (reference) 5B045 CC06 DD15 EE06                 5B082 GB06                 5B098 AA03 AA10 GA01 GA02 GD03                       GD15

Claims (2)

[Claims] 1. A computer system in which a job consisting of a series of processes executed sequentially is executed by a plurality of computers sharing a storage device, wherein a file name used by the job, a file access start time, a file access end time, The step of obtaining the operation information including the access order and the access type of the records in the file, and the first processing and the second processing constituting the job using the operation information are the same in the shared storage device. File is accessed, the first process is a write process for the file, the second process is a read process for the file, and the file access end time for the file in the first process is the second process. Of the file of the first process earlier than the file access start time for the file of The order of accessing the records in the file to the file is the same as the order of accessing the records in the file to the file in the second process, and the first process and the second process only. And a step of creating a second job consisting only of a second process, and a step of executing the first job and the second job on different computers of the computer system. A method of transferring data between computers characterized by the following. 2. A computer system in which a plurality of computers share a first external storage device and a second external storage device, wherein a first job executed by the first computer of the computer system is In a computer system, in which after writing a series of data to the first storage device, a second job executed by a second computer reads the written series of data, the first job from the first job A step of accepting a data write request to a first external storage device by a first operating system that controls the first computer; the first operating system traps the write request, and a first external system Changing to writing to the second external storage device instead of the storage device and performing the writing process, and the first operating system System notifies the second operating system controlling the second computer of the completion of writing, and the second operating system is configured so that the second operating system executes the first job of the second job being executed on the second computer. Trapping a read request to the external storage device of the second operating system, the second operating system receives the completion notification from the first operating system, and replaces the second external storage with the second external storage. A step of reading data from an external storage and passing the data to the second job.