JPS58175065A - Processing system of multiplex volume - Google Patents

Abstract

PURPOSE:To reduce the required time and overhead for the equivalence guaranteeing processing, by performing the equivalence guaranteeing processing in the range represented with all journal records on each physical volume. CONSTITUTION:When an input/output request origin program 4 requests a write request to an input/output control program 5, a journal updating display processing 9 displays ''under update'' on a journal recording area on a main storage device (MM). When system-down takes place during the updata of data, the display of ''under updata'' is left in the journal record on the physical volume. Thus, after the system-down and before the use of the said logical volume, an equivalence restoration processing 12 of a system control program 6 checks the journal record on each physical volume and performs the processing of equivalence restoration as to the part of ''under update''.

Description

Detailed Description of the Invention (a) Technical Field of the Invention The present invention relates to a data processing system, and particularly to a data processing system that writes the same data on a plurality of physical volumes and logically combines these multiple volumes into one volume. The present invention relates to a data processing system having a multiplexed volume function that allows handling of multiple volumes.

(b) Conventional technology and problems It is possible to reduce the impact caused by failures in input/output devices or input/output paths by overlapping data on external storage, especially direct access storage devices (DM8D), in units of volumes. It is being done. For this purpose, it is necessary to place the same data on a plurality of physically different volumes and to make it possible to treat these volumes logically as one volume.

FIG. 1 is a conceptual diagram of a multiplexed volume, where solid line polygons are physical volumes and dotted line volumes are logical volumes. As shown, the same data person is stored in all physical volumes. The only volume that the user's general program is aware of is the logical volume indicated by the broken line, and the data person can only see one volume.

In order for the physical volumes 1 to n shown in FIG. 1 to be logically viewed as one volume, all physical volumes must have the same data. In this way, the fact that all volumes contain the same data is called "equivalence".

This "equivalence" is ■ System down during data update (write operation).

■ Lost due to I/O failure during data update (when it occurs for at least one ah physical volume).

If this equivalence is lost, it is necessary to perform equidominance guarantee processing between volumes at the next system startup or volume mount.

Conventionally, this method ■ How to copy the entire volume.

■ How to compare the contents of a volume and copy only the parts that differ.

has been adopted. However, both of these methods require a large amount of time and overhead, and are not suitable for systems having large volumes or multiplexed volumes.In particular, these methods have the drawback of significantly increasing system startup time.

(C) Purpose of the Invention The present invention aims to shorten system start-up time by reducing the time required for equality guarantee processing and overhead in a data processing system having multiplexed volumes.

(b) Structure of the Invention In order to achieve the above object, the present invention provides a multiplexing system that enables writing the same data on multiple physically different volumes and treating these multiple volumes logically as one volume. In a data processing system having a storage volume function, a journal record area is provided in each of the plurality of physical volumes, and when a write request is made to the physical volume, update range information indicating a predetermined update range in which write processing is performed is provided. Create journal information that includes version number information indicating the update number, and write the journal information in each journal record area of the physical volume with the above w number. When starting up after a system down, etc., the above The content of the journal record area of multiple physical volumes is referenced, the data area that is in the updating state is identified based on the above update range information, and the equidominance guarantee process for the data content of the data area is performed. Features.

(E) Examples of the invention Hereinafter, the present invention will be explained with reference to the drawings.

ts2 is a block diagram of the data processing system according to the embodiment of the present invention, FIG. 118 is a diagram showing the format of journal records in the embodiment, FIG. FIG.

In the WX2 diagram, 1 is a data processing device consisting of a central processing unit (CPU) and a main memory (MM), etc., 2 and 8
is a volume consisting of a direct access storage device (DASD), 4 is an input/output request source program, 5 is an input/output control program, 6 is a system control program, 7 is a journal record area, 8 is a data area, 9 is a journal update display process 10 is an input/output control section, 11 is a journal update display erasure processing section, and 12 is an isosulfuric recovery processing section.

In FIG. 8, 20 and 21 are version number information holding units, and 22 is an update range information holding unit that indicates the cylinder being updated in bitmap format.

The operation of the embodiment is as follows.

First, when the input/output request source program 4 requests a write request to the input/output control program 5, the journal updating display processing unit 9 displays "updating" in the journal record area 7 on the main memory (MM). That is, in the update range information holding unit 22 shown in FIG. 8, the bit corresponding to the cylinder containing the update data is turned on ('1').

In FIG. 8, each bit of the update range information holding section 22 is provided corresponding to a specific cylinder. Thereafter, the input/output control unit 10 issues an input/output device activation command (8IO command) to each volume.

As a result, the contents of the journal record area 7 and the contents of the data area 8 are respectively written to the corresponding areas of each volume. When the writing is completed, an I10 interrupt is sent from each volume, so the input/output control unit 10 notifies the input/output request source program 4 of the completion of writing.

Then, when the data update is successfully completed on all physical volumes, the journal update display deletion processing unit 11 clears the update range information holding unit 22 in the journal record area 7. In other words, the "updating" display is deleted. Thereafter, the contents of this new journal record area 7 are hidden in each physical volume when a subsequent I/O request occurs or when an appropriate amount of time has elapsed.

Next, the operation when the system goes down while updating data is as follows.

If the system goes down while data is being updated, a message "Updating 1" is left in the journal record of physical volume L. Therefore, after the system goes down, before using the relevant logical volume, the system control program 6.
The isodominance recovery processing unit 12 examines the journal records on each physical volume IJ, -, and performs isodominance recovery processing on the portion that is "r updating".

The recovery processing procedure is as shown in FIG.

■ First, read the journal records from each physical volume.

(2) Next, the latest journal for each physical polyneme is determined based on the contents of the version number information holding section 20.21 in the journal record. Note that if the contents of the holding units 20 and 21 are equal, the record is considered to be correct.

■ Then determine the journal as a logical volume. This determination method differs depending on how the journal is taken.

■ And on the journal as a logical volume:
Copy the part that is "updating" to another volume.

(2) With the above steps, the equal paperness recovery process is completed, and the current volume is mounted.

jl15s indicates how data is copied from any normal physical volume to another physical volume for the cylinder part corresponding to the bit position where Ill is set ("updating") in the journal record. be.

Various methods can be used to determine the latest journal.

First, instead of only one journal record, it is possible to configure a track so that a plurality of records exist on the track in order to speed up processing. Furthermore, from the viewpoint of reliability, multiple tracks are used cyclically,
It can also be configured so that even if an error occurs while updating the journal, a new version remains.

In this case, to determine the latest journal, it is sufficient to read all tracks containing journal records and find the record with the maximum version number.

Next, in determining a journal as a logical volume, the journal as a logical volume is determined from the latest journal of the latest volume of each physical volume.

In other words, (1) If a journal is recorded every time data is updated, the journal with the highest version number among the journals for each physical volume, (it) The part updated on the physical volume is the one that was updated last time. If a new journal is to be written when the new journal is different from the previous journal, the logical volume's journal will be the merged version of the latest journals of each physical volume.

In the actual flow side of L, the cylinder is used as a unit of one update range, but the present invention is not limited to this.
It is also possible to use a track, a physical block, or the like as one update range unit.

(f) Detailed Description of the Invention According to the present invention, the range that was being updated when the system goes down is clarified, and when the system is started up,
When mounting a volume, all journal records on each physical volume are read, the latest journal information is obtained (if the version number is the maximum, it is the latest), and equality guarantee processing is performed for the range indicated on this journal. Since this is done, the time required and overhead for the homodominance guarantee process can be significantly reduced.

[Brief explanation of drawings]

FIG. 111 is a conceptual diagram of a multiplexed volume, FIG. 2 is a block diagram of a data processing system according to an embodiment of the present invention, and FIG.
The figures are diagrams showing the format of journal records in the embodiment, Figure 4 is a diagram showing the operation flow of isodominant recovery processing, and Figure 5 is a diagram showing the operation flow of the isodominant recovery process.
The figure shows how data is copied between volumes. In Figure 82, 1 is a data processing device, 2.8 is a volume, 7 is a journal record area, 8 is a data area,
9 is a journal update display processing section, and 11 is a journal update display deletion processing section.

Claims (1)

[Claims] In a data processing system having a multiplex volume function that allows writing the same data on multiple physically different volumes and treating these multiple volumes as one logical volume, A journal record area is provided for each, and when a write request is made to the physical volume, journal information is created that includes update range information indicating a predetermined update range in which write processing is performed and version information indicating the update frequency. The journal information is written to each of the journal record areas of multiple physical volumes, and when the system is started up after going down, etc., the contents of the journal record areas of the multiple physical volumes are referenced.
A multiplexed volume processing method characterized in that a data area that is a mid-update portion is judged based on the update range information, and equidominance guarantee processing is performed on the data contents of the data area.