JPH11338788A - Processing method for input/output error and recording medium recording recovery processing program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To reduce a real memory and to minimize an influence upon ordinary system operation concerning the processing method for input/output error at an input/output device provided with a buffer inside a hardware and used for processing data from a host. SOLUTION: When any error occurs during the write of data, unwritten data are stagnated in a hardware buffer 1. A virtual storage area 2a is used as an area for saving these data and paging is utilized for data transfer. At such a time, pages 3a are fixed to a real memory 3 just for the amount required for executing input/output with the input/output device and by sending out data, which are not directly related to input/output execution, to the virtual storage area 2a, without securing the large capacity of the real memory, the memory is not lacked. Concerning the increase of paging load in the virtual storage area 2a, waiting is performed while considering time spent for the paging load so that the pading load can be lowered.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an input / output error processing method, and more particularly, to an input / output (I / O) method for an input / output device having a data processing buffer in hardware.
The present invention relates to a method for processing an input / output error that is performed without increasing the system load when a large amount of data in the hardware is moved in a recovery process or the like when an error occurs.

In a configuration of a host (general-purpose computer) that performs data processing and an input / output device that holds data processed by the host, when an I / O error occurs while the host is using the input / output device, usually, And rerun the job. However, when a failure has occurred in the target input / output device, the retry with the same input / output device does not succeed. Therefore, the medium used in the input / output device in which the I / O error has occurred is moved to another input / output device, and the I / O operation is performed in another new input / output device. This is a dynamic device reorganization (DDR).
This is a method called Reconfiguration, which guarantees continuous execution of a job using another input / output device when an irrecoverable I / O error occurs.

[0003]

2. Description of the Related Art In recent years, an input / output device, for example, a magnetic tape device, has a buffer (hereinafter referred to as a hardware buffer) inside hardware, and the hardware buffer is used for writing and reading from a host. I'm using For example, when a write request is issued from the host, write data is stored in the hardware buffer, and when a certain amount is stored, a write process to the magnetic tape medium is performed. As a result, the writing / reading to / from the magnetic tape medium and the I / O request on the host side are desynchronized, and the I / O request from the host is
The access time is shortened, and the high speed performance of the I / O operation is brought out.

Here, if an I / O error occurs during, for example, writing processing from a host to a magnetic tape medium, unwritten data will remain in a hardware buffer. . This data is stored in the I / O error I / O
Before the O request is retried by the DDR processing software, it must be recorded on the magnetic tape medium by another input / output device. A process until another input / output device writes data stored in such a hardware buffer to a magnetic tape medium will be described below.

FIG. 6 is a block diagram for explaining processing of unwritten data, and FIG. 7 is a flowchart showing a procedure of processing of unwritten data. In FIG. 6, a real memory 100 provided in a host, an input / output device 110 in which an I / O error has occurred, and a destination input / output device 1 for writing unwritten data in place of the input / output device 110
20 are shown. The input / output devices 110 and 120 include hardware buffers 111 and 121, respectively. Some areas in the real memory 100 are
4 shows an unwritten data storage area 101 for collecting data stored in the hardware buffer 111 of the input / output device 110 in which the / O error has occurred.

Here, when an I / O error occurs while data is being written to a medium by the input / output device 110, first, as shown in FIG. Is grasped (step S1). Next, an unwritten data storage area 101 is acquired in the real memory 100 as an area for data processing (step S2),
The page of the entire acquisition area is fixed (step S3). After that, the hardware buffer 111 of the input / output device 110
If there are, for example, n blocks of unwritten data, the unwritten data is sequentially read into the unwritten data storage area 101 of the real memory 100 in block units (steps S4a to 4n).

Here, the medium is removed from the I / O device 110 in which the I / O error has occurred, and the I / O device 120 at the movement destination is removed.
(Step S5). This input / output device 120
The transfer of the medium to the device is performed by an operator or the system uses a robot.

Next, in the input / output device 120, the head position is moved to the last recording position of the already written data (step S5), and based on the data downloaded to the unwritten data storage area 101 of the real memory 100. To write data to the medium (steps S7a to S7a).
7n).

Then, the page fixation of the area acquired in the real memory 100 for processing unwritten data is released (step S8), and the acquired area is released (step S8).
9). After the above processing is completed, an I / O error occurs and the I / O of data not transferred to the hardware buffer 111 of the input / output device 110 is retried. As a result, the data staying in the hardware buffer 111 at the time of the occurrence of the I / O error can be guaranteed.

[0010]

As described above, when processing the unwritten data in the hardware buffer, an area is acquired in the real memory, and the unwritten data is sucked into the area. However, although the real memory was used for the processing area for unwritten data, the processing speed was high, but the upper limit was set for the area that could be obtained, and the larger the unwritten data exceeded the upper limit, the larger the amount. In such a case, there is a problem that the recovery process cannot be performed.

In order to process a large amount of unwritten data, the real memory may be expanded. However, even if the real memory is expanded, a large amount of the real memory required for system operation is provided as a processing area for the unwritten data. However, there is a possibility that the system becomes inoperable due to a shortage of the real memory, or the response of the system is deteriorated.

SUMMARY OF THE INVENTION The present invention has been made in view of the above-described circumstances, and when an input / output device that has a buffer inside hardware and is used for processing data from a host generates an input / output error, It is an object of the present invention to provide a method of processing an input / output error that does not increase the area acquired in the real memory for the recovery process and guarantees normal system operation.

[0013]

FIG. 1 is a diagram showing a basic configuration of the present invention for achieving the above object. When an input / output error occurs while data is being written to the input / output device, the hardware buffer 1 of the input / output device stores
It is assumed that a large amount of unwritten data remains. In the recovery processing for guaranteeing the writing of the unwritten data, first, the amount of the unwritten data in the hardware buffer 1 in the input / output device in which the input / output error occurred is grasped, and the secondary storage device is determined in accordance with the data amount. 2 obtains a virtual storage area 2a for data processing. On the real memory 3, a page 3a is fixed according to the amount of processing performed at one time, data is read from the hardware buffer 1 of the input / output device into the page 3a, the page 3a is released, and input / output is performed on the real memory. Page out of the area used for. In real memory 3,
Since page fixing is performed only for an area necessary for one process, a large amount of real memory is not used for processing unwritten data, and there is no shortage of memory. Also, at the time of paging, the system load is measured before and after page-out, the system load is predicted from the difference between them, and a wait is performed until the next data reading. As a result, paging is performed in consideration of the system load. The process from page fixing to waiting is repeated until all data staying in the hardware buffer 1 is saved in the virtual storage area 2 a of the secondary storage device 2.

Thereafter, the medium is moved from the input / output device having the input / output error to another input / output device, and the head position is moved. Next, a process of writing the unwritten data saved in the secondary storage device 2 using the input / output device of the transfer destination is performed. First, a page is fixed according to the amount of processing performed once, but before and after that, the system load is measured, and queuing is performed according to the system load predicted from the difference therebetween. Since an amount of data corresponding to one processing amount is allocated to the page 3a of the real memory 3 by the page fixing, after the waiting, the data is written to the hardware buffer 4 of the destination input / output device, Release the page fixation of the area used for input / output, and discard the data of that page. When the processing from the page fixing to the discarding of the real memory 3 is performed for all data in the virtual storage area 2 a of the secondary storage device 2, the virtual storage area 2
Release a and end. Thereafter, the erroneous I / O request is made to the destination I / O device.

As described above, I / O to an input / output device having a buffer for data processing inside hardware
When an error occurs, for example, when realizing recovery processing using another I / O device, a virtual area is used as an area for processing a large amount of unwritten data. By fixing only the amount necessary to execute the output, the real memory uses only the minimum necessary area, and there is no problem of paging load on the system or shortage of the real memory. Further, an increase in the paging load on the virtual storage area 2a is mitigated by performing queuing according to the system load and dispersing it over time, thereby minimizing the effect on the entire system.

Further, according to the present invention, a recovery processing program which is executed when an input / output error occurs in an input / output device used for data processing from a host having a buffer in hardware is recorded. In a computer-readable recording medium, a data amount calculation means for calculating an amount of data which has not been written in the buffer in the hardware, and an unwritten data saving area which secures an unwritten data saving area in virtual storage. Area securing means, data reading means for reading unwritten data stored in the hardware into an unwritten data saving area of the virtual memory, writing to the medium from the position where the last writing was performed on the medium Write start position control means to be a start position, unwritten data saved in the unwritten data save area Data writing means for writing embedded data to the medium, a system load reducing means for measuring a system load and waiting for reading and writing of unwritten data, and an input / output request retry means for retrying an errored input / output request. A computer-readable recording medium on which a program is recorded is provided.

By causing a computer to execute a recovery processing program recorded on the medium, a data amount calculating unit, an unwritten data saving area securing unit, a data reading unit, a writing start position control unit, a data writing The functions of the means, the system load reducing means, and the input / output request retry means can be realized by a computer.

[0018]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, an embodiment of the present invention will be described by way of an example in which a buffer is provided in hardware and an input / output device used for data processing from a host is applied to a magnetic tape device. explain.

FIG. 2 is a diagram showing the configuration of a system having a magnetic tape device. In the system of FIG. 2, a plurality of magnetic tape devices 11, 12, 13,.
There is a large general-purpose machine connected to the host. That is, the magnetic tape devices 11, 12, 13,.
Are connected to the input / output control device 21, and the input / output control device 21 is connected to the input / output channel device 30.
This input / output channel device 30 is a central processing unit (CP
U) 41 and a real memory 42. The I / O channel device 30 is also connected to a plurality of magnetic disk devices 51, 52, 53,.

Here, each of the magnetic tape devices 11, 12, 1
3, ..., hardware buffers 11a, 12a, used for reading and writing data from the host.
13a,. Also, in some cases, the hardware buffer 2
1a.

The real memory 42 has an area 42a in which an operating system is expanded, and an area 42b as an area acquired for data processing for the magnetic tape devices 11, 12, 13,... ing.

Here, the flow of processing when an I / O error occurs while the central processing unit 41 is writing data to a certain magnetic tape device will be described. The flowchart is divided into a hardware buffer reading process for saving the unwritten data remaining in the hardware buffer of the magnetic tape device and a writing process of the unwritten data for writing the saved unwritten data to a medium. This will be described with reference to FIG.

FIG. 3 is a flowchart showing the flow of the processing for reading the hardware buffer. When reading and saving the unwritten data remaining in the hardware buffer, first, the amount of unwritten data is grasped (step S11), and the data processing area for that amount is acquired in the virtual storage. (Step S12). That is, a page data set is created in the magnetic disk device. Here, it is determined whether all the I / O processes have been completed (step S13). If all the I / O processes have not been completed, a page is fixed as a data processing area in the real memory according to the amount of processing performed once (step S).
14). Data for the fixed page is read (steps S15a to 15n). This data reading is performed a plurality of times in block units, for example, according to the size of the page. When the I / O is completed, next, the I / O
The page fixation of the area used for the request is released (step S16). Next, the read data is driven out to the page data set, but before that, the system load is measured (step S17). Thereafter, a process of page-out of the area used for the I / O, that is, flushing the page data to the virtual storage is performed (step S18). Next, the system load is measured again (step S19). Then, a difference between system loads measured before and after the page out is detected (step S20). Based on the difference between the measured values obtained in this way, a wait is performed in anticipation of how long to wait according to the load (step S21). For example, the time before and after the page-out is measured, and the waiting is performed according to the length of time spent in the paging process. By performing this queuing, paging for only data reading does not occur in a concentrated manner, and a decrease in response of the entire system due to an increase in paging load can be reduced. Step S1 above
The processes from 4 to S21 are repeated until all the I / O processes are completed. As a result, data reading can be executed according to the system load without affecting the operation of other running applications.

The above-described measurement of the system load is intended to reduce the influence on the operation.
The system load is determined using all or part of the capacity, memory resources, and the like. Here, the system load is measured in a page-out range, but may be measured in a range including a fixed page.

After the above-described saving of the unwritten data to the virtual storage, the magnetic tape medium is moved to another magnetic tape device, and the saved unwritten data is written to the medium using the magnetic tape device at the destination. Processing is performed.

FIG. 4 is a flowchart showing the flow of the write processing of the unwritten data. In the writing process of the unwritten data, first, it is determined whether or not all the I / O processes have been completed (step S31). All I
If the / O processing is not completed, first, the system load is measured (step S32), and the page is fixed to the real memory in accordance with the processing amount of each processing (step S33). The system load is measured again (step S34). Next, a difference between the measured values of the system load before and after the page is fixed is detected (step S35), and a waiting expected based on the difference is performed (step S3).
6). After the waiting, data writing to the hardware buffer of the fixed page is performed (steps S37a to 37n). Next, the page fixing of the area used for the I / O request is released (step S38), and
O Discard the data in the area used for the request (step S
39). By repeating the above steps S32 to S39,
Finally, when all the I / Os have been completed, the acquired virtual storage area is released (step S40), and the write processing ends.

Here, the system load is measured in a fixed page range, but may be measured in a range including page out. After that, when an I / O error occurs, an I / O request for data remaining in the real memory without being transferred to the hardware buffer is retried. FIG. 5 is a diagram illustrating the relationship between the real memory and the virtual storage area. The virtual storage area where unwritten data is saved is a page data set created in the magnetic disk device. Page fixing in the real memory is performed for only an area required for one processing, and a virtual storage area is sequentially allocated to each area required for one processing.

When reading unwritten data in the hardware buffer, first, an area is acquired in the virtual storage. The real memory allocates an amount of real memory necessary for processing the first I / O. Similarly, only the necessary amount is allocated in the second and subsequent times.

Conversely, when writing unwritten data, since the entire virtual storage area is allocated by the page data set, the pages are fixed in the real memory only for the area required for each processing.
When processing the first I / O, data from the area initially allocated to the virtual storage area is put into the real memory and transferred to the magnetic tape device. The data transfer at this time is
Actually, since the processing is performed in block units, when each area allocated to the virtual storage area is n blocks, the processing is performed n times. Similarly, the data of the area allocated after the second is fixed to a necessary amount of area by pages, and then transferred to the magnetic tape device via the area of the real memory.

Further, the processing contents of the functions that each computer should have can be described in a program recorded on a computer-readable recording medium. By executing this program on a computer, the above processing can be realized on a computer. Examples of the computer-readable recording medium include a magnetic recording device and a semiconductor memory. When distributing to the market,
CD-ROM (Compact Disk Read)
The program is stored in a portable recording medium such as an Only Memory or a floppy disk and distributed.
It can also be stored in a storage device of a computer connected via a network and transferred to another computer via the network. When the program is executed by the computer, the program is stored in a hard disk device or the like in the computer, and is loaded into the main memory and executed.

[0031]

As described above, according to the present invention, a virtual storage area is used as a save area for data staying in a hardware buffer, and paging is used. Therefore, the system can be operated by the conventional operation procedure. That is, there is no need for the user to prepare a dedicated data set, and it is not necessary to newly create a recovery procedure manual or the like, so that there is no need to change the operation procedure.

In order to process unwritten data,
When a virtual area is used, and when data is read from or written to the input / output device, the virtual area is fixed on the real memory by an amount necessary for performing I / O with the input / output device. did. As a result, when paging is used, if a large amount of real memory is used, paging load on the system, shortage of real memory, or DDR
A decrease in the response of the entire system due to an increase in the paging load on the virtual storage area used by the server is eliminated.

[0033] Further, with respect to the flushing of unwritten data to the page data set, the paging load increases due to the increase in the number of flushes, but the time spent in the DDR for paging processing is increased. In consideration of the above, by performing the queuing, the paging load is reduced, the influence on the entire system is eliminated, and troubles in the system operation can be avoided.

[Brief description of the drawings]

FIG. 1 is a diagram showing a basic configuration of the present invention.

FIG. 2 is a diagram illustrating a configuration of a system including a magnetic tape device.

FIG. 3 is a flowchart illustrating a flow of a reading process of a hardware buffer.

FIG. 4 is a flowchart illustrating a flow of a writing process of unwritten data.

FIG. 5 is a diagram illustrating a relationship between a real memory and a virtual storage area.

FIG. 6 is a configuration diagram illustrating processing of unwritten data.

FIG. 7 is a flowchart illustrating a procedure of processing of unwritten data.

[Explanation of symbols]

 1, 4 hardware buffer 2 secondary storage device 2a virtual storage area 3 real memory 3a page 11, 12, 13 ... magnetic tape device 11a, 12a, 13a ... hardware buffer 21, 22 input / output control device 21a Hardware buffer 30 I / O channel device 41 Central processing unit 42 Real memory 51, 52, 53 ... Magnetic disk device

 ────────────────────────────────────────────────── ─── Continuing on the front page (72) Inventor Toshinori Namba 4-1-1 Kamikadanaka, Nakahara-ku, Kawasaki City, Kanagawa Prefecture Inside Fujitsu Limited (72) Inventor Yoshiyuki Shimoyama 4-1-1 Kamiodanaka, Nakahara-ku, Kawasaki City, Kanagawa Prefecture No. 1 Fujitsu Limited (72) Inventor Hidemasa Hatano 4-1-1, Kamiodanaka, Nakahara-ku, Kawasaki-shi, Kanagawa Prefecture Fujitsu Limited

Claims (6)

[Claims] 1. A method for processing an input / output error in a recovery process when an input / output device having a buffer in the hardware and used for processing data from a host generates an input / output error. The amount of unwritten data in the buffer is calculated, an area for saving unwritten data is secured in virtual storage, and the unwritten data stored in hardware is written in unwritten data in the virtual storage. Read into the save area, move the medium to another I / O device, move the write start position on the medium to the last write position on the medium with the another I / O device, Writing the unwritten data saved in the data save area to the medium using the another input / output device, and retrying the I / O request in error; A method for processing an input / output error, comprising: 2. The method according to claim 1, wherein the step of reading the unwritten data in the area for saving unwritten data includes fixing only an area corresponding to a processing amount at a time of reading unwritten data from the buffer in the real memory. Item 2. An input / output error processing method according to item 2. 3. The input / output error processing according to claim 1, wherein the step of reading into the unwritten data save area measures a system load and executes a wait in accordance with the measured system load. Method. 4. The method according to claim 1, wherein the step of writing the unwritten data to the medium includes fixing only an area corresponding to a processing amount at one time when writing the unwritten data from the virtual storage in the real memory. Item 1. An input / output error processing method according to item 1. 5. The input / output error processing method according to claim 4, wherein in the step of writing the unwritten data to the medium, a system load is measured, and a wait is executed according to the measured system load. . 6. A computer-readable recording medium storing a recovery processing program to be executed when an input / output error occurs in an input / output device having a buffer inside hardware and used for processing data from a host. A data amount calculating means for calculating an amount of data which has not been written in the buffer in hardware; an unwritten data saving area securing means for securing an unwritten data saving area in virtual storage; Data reading means for reading unwritten data stored in the unwritten data saving area of the virtual memory, and starting writing from the position where the last writing was performed on the medium to the writing start position on the medium Position control means for storing the unwritten data saved in the unwritten data save area in the medium; Computer which records a program having data writing means for writing data to the system, system load reducing means for measuring the system load and waiting for reading and writing of unwritten data, and input / output request retry means for retrying an errored input / output request A readable recording medium.