JPS63155468A - Recovery processing system for duplex volume - Google Patents

Abstract

PURPOSE:To execute in parallel a recovery processing and an input/output processing by providing a first means for executing a release processing, for instance, by one cylinder each, and a second means for suspending a release (copying) processing for a prescribed period, after having completed a release (copying) processing of one cylinder portion. CONSTITUTION:The titled system is provided with means 10, 20 for suspending a copying processing for a prescribed period. When a computer system is executing an on-line service 50, if a fault is generated in a direct access storage device DASD duplicated in a volume unit, and a release processing 40 for recovering it from a one face state 1 to a duplex state is started, for instance, a one cylinder portion copying processing means 10 is started through an access switching means 60 to the DASD, and the release processing is started to the DASD. When the copying processing of one cylinder portion is completed, a copying processing dormant period generating means 20 is started, and in the access switching means 60 to the DASD, an input/output processing 30 which occurs from the on-line service 50 is selected, and the input/output processing to the DASD is executed.

Description

[Detailed Description of the Invention] [Summary] In a direct access storage device (DASD) in which each volume is duplexed, a state in which one of the duplexed volumes is disconnected due to a failure is changed to a duplexed state in which both volumes are valid. a first means for performing the restoration process for one full cylinder, for example;
By providing a second means for suspending the restoration (copying) processing for a certain period after completing the restoration (copying) processing for the l cylinders, the restoration processing is suspended by the second means. During the period, perform general input/output processing,
The above recovery process and input/output process are executed in parallel.

[Industrial application field]

The present invention relates to a recovery processing method for a duplicated volume in a direct access storage device (DASD), such as a disk device, in which each volume is duplicated.

In current computer systems, especially online systems, most of the data processed by the system is stored semi-permanently or temporarily on direct access storage devices (DASD).
stored in the upper volume.

Therefore, when it becomes impossible to process the data on the direct access storage device (DASD) volume due to a hardware failure, it has a serious impact on the computing system.

Therefore, usually the direct access storage device W (DASD)
By duplicating and using the above data in units of volumes, a configuration (for example, a know-down system configuration) is adopted that greatly reduces the impact of the above hardware failure on the system.

Specifically, this is a configuration in which two physically independent volumes having the same data are used to logically form one volume.

In such a direct access storage device (DASD) that is duplexed for each volume, when one of the volumes is disconnected due to a failure etc. and is providing online service with only one lung, when returning to a duplexed state where both volumes are valid, the online In a system, it is necessary to perform the recovery process without stopping services to users.

[Conventional technology]

FIG. 3 is a diagram illustrating a conventional duplex volume recovery processing method.

As previously mentioned, direct access storage devices (hereinafter referred to as
In order to improve the reliability of DASD
A method has been adopted in which data on a volume is duplicated on a volume-by-volume basis.

In the configuration state of the duplex volume, both volumes 2a
, 2b are valid, and 8. There is a single-sided state 1 in which one volume 1b has been separated due to a failure or the like and is being serviced by one volume.

In order to restore the volume 1a that has entered the single-sided state 1 to the duplex volume 2, for example, a management table provided on the main storage device is created under the control of an operating system (O3) not shown. ASD lb is used to allocate a new ASD lb, and all data in the volume la in the single-sided state l is copied to that DAsolve.

In the conventional method, during this copying process, access from the service program to the volumes la and lb is inhibited, and input/output processing requests that arrive at that time are held in an input/output management program (not shown). It was executed after the copying process was completed.

[Problem that the invention seeks to solve]

Therefore, in the conventional duplex volume recovery processing method described above, there is a problem in that during the copying process, certain services are in a state that is almost equivalent to being interrupted.

Therefore, recovery from a single-sided state to a dual-sided state during online service was not performed.

Therefore, a method can be considered in which the copying process for restoring the single-sided volume A1 to the dual-sided volume B2 and the general input/output request processing (access from the service program) for the volume are executed in parallel. The following points needed to be resolved.

FIG. 4 is a diagram illustrating problems in executing copy processing and input/output processing in parallel.

+11 Between read ■ and write ■ of copy processing,
-If the update light for sailor output processing is entered,
There is a problem in that the update write (2) is invalidated by the write (2) of the copy process, and the update input/output is treated as being inactive, which appears to the user as data destruction.

(2) Also, among input/output requests for -In, if the access type is read, it is sufficient to uniformly access the volume on the copying side 1a, but in the case of write, the copied area (hatched ), copy side 1a+
Write to both the volumes on the side 1b and the copying side 1b, and write to the uncopied area as in the case of reading.
It is necessary to perform this only for the copying volume 1a.

Here, '0NDUAL' indicates a volume that has been allocated and is valid, and 'NEUTRAL' indicates a volume that has been allocated but is invalid without valid data.

(3) Since read/write for copying is a sequential access from the smallest cylinder position, the arm operation time (seek time) is almost "0", but -m input/output request When input/output operations occur randomly, the access positions are different from each other, causing disturbances in the arm operations, resulting in a problem in which the overall throughput decreases.

(4) During the copying process, the impact of -S on the response time to input/output requests is unavoidable, but the degree of this impact is
It is necessary to be able to adjust according to the system load situation.

In view of the above-mentioned drawbacks of the conventional art, the present invention prevents normal access from service programs to users when returning from a single-sided state to a dual-sided state in a DAS [) in which each volume is duplexed. The purpose is to provide a method for solving problems.

[Means for solving problems]

FIG. 1 is a diagram showing a configuration example of a duplex volume recovery processing method according to the present invention.

In the present invention, the recovery process 40 is used to restore a duplexed state in which one of the duplexed volumes is disconnected due to a failure to a duplexed state in which both volumes are valid.
For example, a first means 10 that executes for l cylinders, and a second means 20 that suspends the recovery (copy) process for a certain period after completing the recovery (copy) process for the next cylinder.
and the recovery process 40 is performed by the second means 20.
The configuration is such that general input/output processing 30 is executed during the period when the processing is suspended.

[Effect]

That is, according to the present invention, in a direct access storage device (DASD) in which each volume is duplexed, from a state in which one of the duplexed volumes is disconnected due to a failure, it is possible to recover the capacity of both volumes (recovery to an effective duplication state). For example, a first means executes the recovery process for one cylinder, and a second means suspends the recovery (copy) process for a certain period after completing the recovery (copy) process for the one cylinder. By providing a means of
Since the recovery process and the input/output process are executed in parallel, it is possible to recover from a single-sided state to a dual-sided state during online service, and the average recovery time is reduced. (MTTR) will be shortened,
The incidence of service outages due to double-sided failure is reduced,
This has the effect of improving confidence in the system.

〔Example〕

Embodiments of the present invention will be described in detail below with reference to the drawings.

The above-mentioned FIG. 1 is a diagram showing a configuration example of the duplex volume recovery processing method of the present invention, and FIG. 2 is a diagram explaining the operation of the recovery processing according to the present invention. , for example, 10.2 means for stopping the copying process for a certain period of time when the copying process is completed to the cylinder;
0 are the means necessary to implement the invention. Note that the same reference numerals refer to the same objects throughout the plan.

The duplex volume recovery processing method of the present invention will be explained below with reference to FIGS. 1 and 2.

First, while the computer system is running the online service 50, a failure occurs in the duplexed DASD in volume units, and when the recovery process 40 is started to recover from the single-sided state to the duplexed state, access to the DASD is interrupted. For example, the one-cylinder copy processing means 10 is activated via the switching means 6o, and recovery processing for the DASD is started. (See FIG. 2, "nth cylinder copying process.") When the copying process for the one cylinder is completed, the copying process dead period generation means 20 is started, and the access switching means 6o for the DASD starts the online service. The input/output process 30 originating from the DASD is selected and the input/output process for the DASD is executed. (Refer to Figure 2 "Duration of pause rtJi") As shown in Figure 2, this input/output processing includes one write (W) and update (R/W) processing, for example, A processing request that occurs during the n-th cylinder copy processing period waits until the copy processing 10 is interrupted and the pause period 20 occurs. , so there is little impact on online processing.

In addition, the execution of the recovery process 40 and the general input/output process 30 is as follows:
As is clear from FIG. 2, since it is serialized, the above problem (1) is solved, and the general input/output processing 30
Since the recovery process 40 is stopped while the area is being executed, it is easy to distinguish between copied and uncopied locations, and access to the copied area (copied (write to both volumes on the side and the side to be copied), and
Access to the uncopied area (writing only to the copying volume) can be easily achieved.

In addition, since the copying process is executed in units of one cylinder,
The number of occurrences of disturbances in arm operation is reduced, and the reduction in throughput (problem (3) above) can be suppressed to some extent.

Furthermore, by giving the suspension period 20 of the copying process as a parameter, the recovery process 40 is performed.

-i can perform load adjustment with the input/output processing 30. (See problem (4)) As described above, the present invention enables the copying process in the recovery process for a DASD failure that occurs during online service to be
For example, after executing the copy process for one cylinder and executing the copy process for one cylinder, the copy process is paused for a certain period of time, and during this time, general input/output request processing is executed and the copy process is completed. The feature is that the processing of the general input/output request and the processing of the general input/output request are repeated alternately, and both processing are carried out in parallel.

In the above embodiment, the copying process was explained as a method of copying to one cylinder, but it is not necessary to limit it to one cylinder. For example, it is generally possible to copy to n cylinders as long as it does not affect online services. Needless to say, it is a good thing.

〔Effect of the invention〕

As described above in detail, the duplex volume recovery processing method of the present invention is capable of recovering a duplex volume from a state in which one of the duplex volumes is disconnected due to a failure in a duplex direct access storage device (DASD) for each volume. In order to restore the duplex state in which both volumes are valid, the first method is to execute the restoration process for one cylinder, for example, and the second method is to execute the restoration process for one cylinder for a certain period of time after completing the restoration (copying) process for the one cylinder. By providing a second means for interrupting the recovery (copying) process, the second means executes general input/output processing during the period in which the recovery process is interrupted, and performs the recovery process. Since input/output processing is executed in parallel, it is possible to recover from a single-sided state to a dual-sided state during online service, and the mean time to repair (MTTR) is shortened, so that it is possible to recover from a double-sided state due to a double-sided failure. This has the effect of reducing the incidence of service outages and improving system reliability.

[Brief explanation of the drawing]

FIG. 1 is a diagram showing a configuration example of a duplex volume recovery processing method according to the present invention. FIG. 2 is a diagram explaining the operation of recovery processing according to the present invention. FIG. 3 is a diagram illustrating a conventional duplex volume recovery processing method. FIG. 4 is a diagram illustrating problems in executing copy processing and input/output processing in parallel. It is. In the drawing, 1 is a single-sided state of a direct access storage device fi (DASD). 1a is a valid volume, lb is an invalid volume. 2 is a duplex state of direct access storage devices (DASD). 10 is an n-cylinder copy processing means or copy processing. Reference numeral 20 denotes a copy processing suspension period generation means or suspension period. 30 is input/output processing, and 40 is recovery processing. 70 is a DASD access switching means. vO is an online service. ■～■ are access 11α order for DASDc. The Roda-oga of the Ryuum that concerns the world
JX? ! ,]kGF41 child j Figure n\i Higezuki (two [] Bokusai: affn pleasure T and J Tomoe Moon ζro 5a 弗 2 Figure piece ill missing state two soil conversion one piece ゛ sadness)

Claims (1)

[Claims] In a direct access storage device in which each volume is duplexed, in order to recover from a one-sided state in which one of the duplexed volumes is disconnected due to a failure to a duplexed state in which both volumes are valid, a first means (10) for executing a recovery process (40) for n cylinders (n=1, ~); and after completing the recovery (copy) process for the n cylinders, the recovery (copy) is performed for a certain period of time; Second means for interrupting processing (20
), and by means of the second means (20), general input/output processing (30) is executed during the period when the recovery processing (40) by the first means is suspended. This is a recovery processing method for duplexed volumes.