Decentralized processing method and system

• US 4,627,055 A
• Filed: 01/13/1984
• Issued: 12/02/1986
• Est. Priority Date: 01/09/1984
• Status: Expired due to Term

• Current Assignee: Hitachi, Ltd.
• Original Assignee: Hitachi, Ltd.
• Inventors: Miyamoto, Shoji, Ihara, Hirokazu, Mori, Kinji, Nohmi, Makoto
• Primary Examiner(s): Atkinson, Charles E.
• Application Number:
  US06/570,502
• Time in Patent Office: 1,054 Days
• Field of Search: 371/11, 371/9, 371/8, 371/16, 364/200
• US Class Current: 714/11
• CPC Class Codes: G06F 11/0763 by bit configuration check, e.g. of formats or tags
• CPC Class Codes: G06F 11/277 with comparison between actual response and known fault-free response
• CPC Class Codes: H04L 12/437 Ring fault isolation or reconfiguration for SDH/SONET ring networks H04J3/085

Abstract

A decentralized processing system having a plurality of subsystems of the same type which are connected to one another. Each subsystem has a diagnosis means for diagnosis of failure in other subsystems, and functions to take a suitable countermeasure in response to the result of the diagnosis. When a failure has occurred in any one of the subsystems constituting the processing system, each subsystem can conduct a suitable fault time processing in accordance with the state of the failure. After the recovery from the failure, each system can execute a processing for recovering the ordinary status. The subsystems can correspond with each other to conduct the processings in synchronization as required. It is, therefore, possible to attain synchronous operation of two or more subsystems in various control systems or the like.

Claims

1. A decentralized processing method in a system having a plurality of subsystems, each subsystem being coupled to the other subsystems by at least one transmission means and performing processing of an assigned function comprising the steps:

each subsystem checking whether all of one or more informations required for execution of the assigned function of that subsystem are available from other subsystems over said at least one transmission means; and

each subsystem executing its assigned function only when all of the one or more informations required to perform its assigned function are available.

2. A decentralized processing method according to claim 1 wherein each subsystem executes its checking by processing content codes which represent contents of each of the one or more informations.

3. A decentralized processing method according to claim 2 wherein said checking is executed during a status setting period in which content codes from other subsystems are received.

4. A decentralized processing method according to claim 1 in which each of said subsystems executes a fault time processing routine to identify a failure anywhere within the system.

5. A decentralized processing method according to claim 4 wherein each of said subsystems executes the steps of receiving the result of the fault time processing routine of the other subsystems and executes its fault time processing routine utilizing the results of the fault time processing routines of the other subsystems.

6. A decentralized processing method according to claim 1 wherein the at least one transmission means is connected to the subsystems to form a loop and each subsystem functions to diagnose a failure in any of the other subsystems.

7. A decentralized processing method in accordance with claim 6 wherein:

each subsystem detects a failure in a transmitting function of the other subsystems by the operation of the subsystem to detect a data transmission failure;

one of the subsystems upon detection of a failure in a transmitting function constructs a bypass route within the failed system when a bypass route is possible;

the subsystem constructing the bypass route within the failed subsystem informs the other subsystems of the bypass route within the failed system; and

one of the subsystems constructs a bypass route within a subsystem adjacent to the failed system when a bypass route within the failed system cannot be constructed.

8. A decentralized processing method in accordance with claim 1 wherein:

each subsystem prohibits the sending of data on the one or more transmission means other than data for synchronizing the operation of subsystems which have not failed during operation when the subsystems are synchronized with each other to perform synchronous processing.

9. A decentralized processing method in accordance with claim 1 wherein:

one of the subsystems prohibits the processing of a failed subsystem in synchronism with another subsystem when a bypass route of the failed system has been constructed.

10. A decentralized processing method in accordance with claim 1 wherein:

each of the subsystems sends a small loop check message to subsystems adjacent to a failed subsystem to check if data can be sent in a loop to which the failed subsystem and adjacent subsystem belongs.

11. A decentalized processing method in accordance with claim 1 wherein:

each of the subsystems sends a large loop check message to all of the subsystems in the system to check if data can be sent throughout the system.

12. In a decentralized processing system having a plurality of subsystems, each of the subsystems being coupled to the other subsystems by at least one transmission means and performing processing of a assigned function wherein each subsystem comprises:

a first memory for storing a plurality of content codes representing the contents of respective informations which are necessary for that subsystem to execute its assigned function;

a second memory for storing received content codes sent from the other subsystems;

processing means for comparing the content codes stored in said first memory means and the second memory means to judge that the assigned function inexecutable when all necessary content codes stored in the first memory have been found in the second memory; and

means for executing the assigned function when all codes in the first memory have been matched with codes in the second memory.

13. A decentralized processing method in a system having a plurality of subsystems, each of the subsystems being coupled to the other subsystems by at least one transmission means and performing processing of an assigned function comprising the steps:

each subsystem independently operating application programs in synchronism with other subsystems;

each subsystem checking the status of the transmission means to confirm that synchronous operation of the application programs is possible; and

operating the application programs when possible.

14. A decentralized processing method in accordance with claim 13 wherein the checking step checks whether there is a delay in the functioning for the synchronous operation.