JPH10307801A - Data update system - Google Patents

Abstract

(57) Abstract: The present invention relates to a data update system in which a plurality of processor modules access data on a shared memory and perform processing, the data updating system having a copy of data of the shared memory in a main memory of each PM, An object of the present invention is to cope with a case where one of a plurality of PMs goes down while updating the shared memory, without giving a heavy load to each PM. Each processor module includes a shared memory for storing data used by a plurality of processor modules, a main memory for storing data, and a main memory management process for storing data in the shared memory in the main memory. The main memory management process refers to the shared memory, stores the data in the main memory, and notifies another processor module of an instruction to update the data in the main memory when the standby processor module operates instead of the current one. Means.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

[0001] 1. Field of the Invention [0002] The present invention relates to a data update system in which a plurality of processor modules access data on a shared memory and perform processing.

Recently, a plurality of processor modules (P
M) to perform shared processing by accessing a shared memory. At this time, depending on the task (for example, schedule management task for many employees), each PM needs to update data at high speed.

[0003]

2. Description of the Related Art Conventionally, in a system composed of a plurality of PMs, a shared memory is provided for guaranteeing data identity, and each PM accesses the shared memory to update data and perform business processing. Was like that.

[0004]

As described above, when a plurality of PMs perform business processing, data may be stored in a shared memory in order to guarantee data consistency between the PMs.
Business processes were performed by referring to data in the shared memory. For this reason, the access speed of the shared memory is generally slow, and when a plurality of PMs access the shared memory at the same time, one of them is put on standby. There was a problem that it could not be performed.

According to the present invention, in order to solve this problem, in a system in which a plurality of PMs perform processing, data of a shared memory is copied to a main memory of each PM, and one of the plurality of PMs is used as a shared memory. Even if the PM goes down during the update, it is necessary to deal with it without giving a large load to each PM.

[0006]

Means for solving the problem will be described with reference to FIG. In FIG. 1, PM1
Is a processor module that reads a program from a storage medium, loads the program on the main storage 2, starts it, and performs various business processes.
And a CPU 3 and the like.

The main memory 2 stores data and programs. The CPU 3 performs various business processes according to a program.
The PM1 comprises a shared memory management process 4 and a main memory management process 5, and the standby PM1 comprises a standby process 3
1, a shared memory management process 4 and a main memory management process 5.

The standby process 31 is a process of the standby PM 1 and performs various processes required for standby. The shared memory management process 4 updates the shared memory 6 and the like.

The main memory management process 5 updates the main memory 2 with reference to the shared memory. The shared memory 6 is a memory for guaranteeing data identity among a plurality of PMs 1.

Next, the operation will be described. After the PM 1 updates the content of the shared memory 6 and copies it to the main memory 2, the PM 1 notifies the other PM 1 of the update of the shared memory 6, and the main memory management process 5 of the other PM 1 that has received the update notification updates the shared memory 6.
, The data is copied to the main memory 3 to ensure the data identity.

At this time, after the working PM 1 updates the data in the shared memory 6 and copies it to the main memory 3, it notifies all other working and standby PMs of the update.

In addition, the standby PM periodically monitors the occurrence of a failure in any of the working PMs 1 and, when a failure occurs, copies the contents of the shared memory 6 to the main memory 2 and takes over the work based on the ID. Then, an instruction to rewrite each main memory is sent to the other PMs.

[0013]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Next, an embodiment and operation of the present invention will be sequentially described in detail with reference to FIGS.

FIG. 1 shows a system configuration diagram of the present invention.
In FIG. 1, PM1 is a processor module connected to a bus 7, and here, main memory 2 and CP
U3.

The main memory 2 is a memory for storing and reading data and programs. Here, the same data as the data in the shared memory 6 is stored and referred to at a high speed to quickly perform business processing. It is for doing.

The CPU 3 performs various business processes in accordance with a program on the main memory 2 loaded from the storage medium. In this case, the active PM 1 includes a shared memory management process 4 and a main memory management process 5, The standby PM 1 includes a standby process 31, a shared memory management process 4, and a main storage management process 5.

The standby process 31 performs various processes required for the standby PM 1 to wait. The shared memory management process 4 updates the data in the shared memory 6 in response to a data update request from the terminal 8 or the like, and updates the main memory management process 5 when the data in the shared memory 6 is updated.
To notify that the data in the shared memory 6 has been updated.

When the main memory management process 5 receives a notification from the shared memory management process 4 or another main memory management process 5 that the shared memory 6 has been updated, the data read out with reference to the shared memory 6 is read. Is stored in the main memory 2 to ensure the identity of the data in the shared memory 6 and the data in the main memory 2. Further, the main memory management process 5 stores the data read with reference to the shared memory 6 in the main memory 2 and then notifies the main memory management process 5 of another PM 1 that the data in the shared memory 6 has been updated. Notice.

The shared memory 6 is a memory that is shared by a plurality of PMs 1 and guarantees data identity between the plurality of PMs 1. The bus 7 has a plurality of PM1s.
Are buses for mutually accessing the shared memory 6.

The terminal 8 requests the current PM 1 to update the data in the shared memory 6. Next, the operation of the configuration of FIG. 1 will be described in detail with reference to FIG.

FIG. 2 is a diagram for explaining the operation of the present invention. Here, PM (# 1) and PM (# 2) are active and PM
(# 3) is standby. In FIG. 2, in S1, the shared memory management process 4 of the active PM 1 receives the definition information update. This receives an update of the definition information in the shared memory 6 from the terminal 8 in FIG.

In step S2, the shared memory is updated based on the update information. This is because the shared memory management process 4 uses the shared memory 6 based on the update information (definition information) received in S1.
Is updated (for example, the schedule is updated).

At step S3, the shared memory is updated. This is because the shared memory management process 5 that has updated the shared memory 6 in S2 updates the shared memory 6 with the main storage management process 5 and prompts the main memory 2 to update the data in order to guarantee data consistency. Make a notification.

In step S11, the main memory management process 5 receives the update notification in response to the update notification in step S3. S12
The main memory management process 5 updates the main memory 2 based on the contents of the shared memory 6. As a result, the data in the main memory 2 becomes the same as the data in the shared memory 6, and the data identity is guaranteed.

In step S13, a notification of the update of the shared memory is sent to all other working and standby PM1s. Then, S21 or S22 in the current PM (# 2) 1 and the standby PM
(# 3) In the same manner as in S11 and S12 described above in S31 and S32, the main memory 2 is determined based on the contents of the shared memory 6.
To ensure data identity.

As described above, when the terminal 8 issues a request to update data in the shared memory 6, the shared memory management process 4 of the current PM 1 updates the contents of the shared memory 6, and then notifies the main memory of the update. The main memory management process 5 refers to the shared memory 6 and notifies the main memory 2
Is updated, the main storage management process 4 of the other active PM1 and the standby PM1 is notified of the update.
The main memory management process 4 of the M1 updates the main memory 2 with reference to the shared memory 6, and the data in the main memory 2 of the plurality of PMs 1 is guaranteed to be identical with the data in the shared memory 6, and each P1
M1 can execute business processing at high speed with reference to the data in the main memory 2 respectively.

FIG. 3 is a flow chart when a failure occurs according to the present invention. This shows an operation when a failure occurs in any one of the plurality of working or standby PMs 1 in FIG. Here, the standby PM1 is periodically
1 has processing means for checking whether a failure has occurred.

In FIG. 3, S41 acquires the ID of the PM in which a failure has occurred. In this case, since a failure has occurred in any one of the plurality of working or standby PMs 1 in FIG. 1, the ID used by the failed PM 1 is acquired.

In step S42, the failed PM is registered in the shared memory 6 as standby. That is, based on the ID acquired in S41, the earliest standby PM 1 registers the failed PM in the shared memory 6 as the standby PM (the current PM or the standby PM is registered as the standby PM).

In step S43, the contents of the shared memory are copied to the main memory. This is because the earliest standby PM1 has shared memory 6
Is copied to its own main memory 2. In step S44, it is determined whether the failed PM is in use. If yes,
Since the PM 1 in which the failure has occurred is found to be working, the shared memory 6 is used for all other PMs (other working and standby PMs) in S45.
Is notified, and the process proceeds to S46. On the other hand, NO in S44
In the case of, the failed PM1 is found to be the standby PM1, and the process proceeds to S46.

In step S46, the task is taken over based on the ID.
This takes over the current business or the standby business based on the ID of the failed PM1. In step S47, the operation is restarted.

As described above, the current or standby PM 1
When a failure occurs, the standby PM1 immediately fails P
Acquire the ID of M1 and wait for PM1 that has failed PM1
After that, the contents of the shared memory 6 are copied to the main memory 2, and if the PM 1 in which the failure has occurred is the active PM 1, the other PMs 1 are notified of the update of the shared memory 6 and the business is resumed. On the other hand, the failed PM1 is the standby PM
In the case of 1, the business is resumed as it is. Thus, even if a failure occurs in any of the PMs 1, the contents of the shared memory 6 accessed by the plurality of PMs 1 and the contents of the main memory 2 in each PM 1 are guaranteed, and then the main memory 2 is stored. It is possible to execute business processes at high speed by referring to them.

In FIG. 3, S51 restarts the failed PM. This causes an OS (operating system) (not shown) to restart the PM in which a failure has occurred. S52
Recognizes a standby based on information in the shared memory. This is because the standby PM 1 taken over in S42 described above registers the ID of the failed PM 1 in the shared memory 6 as standby, and the OS recognizes the failed PM 1 as standby based on this information.

In step S53, a standby process is started. This is because the standby process 31 in the standby PM (# 3) 1 in FIG.
Start A step S54 copies the contents of the shared memory to the main storage. As a result, the identity of the contents of the shared memory 6 and the contents of the main memory 2 of the failed PM 1 is guaranteed.

In step S55, it is determined whether or not it is in use. Here, N
Since it becomes O and it is standby, it waits as standby in S57.
As described above, the failed PM1 is registered as the standby PM1 in the shared memory 6 in the above-described step S42, and the OS finds the registered standby PM1 in which the failure has occurred and restarts the processing by steps S51 to S57. It is possible for the standby PM 1 to copy the contents of the shared memory 6 to the main memory 2 to ensure the identity and then resume the business as the standby PM 1 (usually waiting for the failure of the active PM 1). Become.

[0036]

As described above, according to the present invention,
In a system in which a plurality of processor modules (PM) perform processing, a configuration is employed in which data in the shared memory 6 is copied to the main memory of each processor module, and each processor module periodically checks whether there is a change in the shared memory. Therefore, the load on each processor module can be reduced.

[Brief description of the drawings]

FIG. 1 is a system configuration diagram of the present invention.

FIG. 2 is a diagram illustrating the operation of the present invention.

FIG. 3 is a flowchart when a failure occurs according to the present invention.

[Explanation of symbols]

 1: PM (processor module) 2: main memory 3: CPU 31: standby process 4: shared memory management process 5: main memory management process 6: shared memory 7: bus 8: terminal

Claims (3)

[Claims] 1. A data updating system in which a plurality of processor modules access data on a shared memory to perform processing, a shared memory storing data used by the plurality of processor modules, a main memory storing data, And a main memory management process for storing data in the shared memory in the main memory. When the standby processor module operates on behalf of the current operation, the main memory management process is executed by the shared memory. A data updating system comprising means for storing data in a main memory with reference to the above and notifying another processor module of an instruction to update data in the main memory. 2. When one of the active processor modules fails, the ID of the processor module is written to the shared memory, and the one standby processor module copies the contents of the shared memory to the main memory and stores the ID in the shared memory.
2. The current business is taken over based on
Data update system as described. 3. A program for storing data used by a plurality of processor modules in a shared memory, a program for storing data in the shared memory in a main memory by referring to the data in the shared memory, and a standby processor module operating in place of the current one. A storage medium that stores a program that sometimes refers to the shared memory to store data in the main memory and notifies another processor module of an instruction to update data in the main memory.