Processing system tolerant of loss of access to secondary storage

Patent 4608688 Issued on August 26, 1986. Estimated Expiration Date:

December 27, 2003. Estimated Expiration Date is calculated based on simple USPTO term provisions. It does not account for terminal disclaimers, term adjustments, failure to pay maintenance fees, or other factors which might affect the term of a patent.

Abstract Claims Description Full Text

Patent References

3771146

3882455

Management table apparatus in memory hierarchy system
Patent #: 4051461
Issued on: 09/27/1977
Inventor: Hashimoto , et al.

Circuit arrangement for an indirectly controlled exchange, in particular a telephone exchange
Patent #: 4211899
Issued on: 07/08/1980
Inventor: Ptacnik , et al.

Multiprocessor system
Patent #: 4356550
Issued on: 10/26/1982
Inventor: Katzman , et al.

Automatic fault recovery system for a multiple processor telecommunications switching control
Patent #: 4371754
Issued on: 02/01/1983
Inventor: De , et al.

Optional machine inhibition for feature malfunction
Patent #: 4377845
Issued on: 03/22/1983
Inventor: Markham , et al.

Storage element reconfiguration Patent #: 4430727
Issued on: 02/07/1984
Inventor: Moore , et al.

Inventors

Assignee

AT&T Bell Laboratories

Application

No. 06/566021 filed on 12/27/1983

US Classes:

714/6, Redundant stored data accessed (e.g., duplicated data, error correction coded data, or other parity-type data)714/10Of processor

Examiners

Primary: Atkinson, Charles E.

Attorney, Agent or Firm

Volejnicek; David

International Classes

G06F 11/00 (20060101)
G06F 11/20 (20060101)
G11C 29/00 (20060101)

Abstract

In a processing system (100) that swaps processes between a main memory (114 or 124) and a pair of duplicated disks (132, 142), system processing capability is protected against loss of access to both system-essential duplicated disks. Upon loss of access to one duplicated disk, processes designed as essential to the system's operation and not resident in the main memory are swapped into the main memory from the other duplicated disk. All essential processes are then locked into the main memory to prevent their removal therefrom. Thus the essential processes remain accessible to the processing system even upon loss of access to both of the disks. Upon loss of access to both of the disks, the system may undergo reconfiguration in an attempt to regain access to at least one of the disks. If reconfiguration fails, non-essential processes are killed and the system continues processing using only the essential processes. Upon restoration of access to one of the disks, the restored disk is initialized from tape and the system is then bootstrapped from the restored disk, and normal processing is resumed. Upon restoration of access to the second disk, the second disk is repopulated from the first disk and the essential processes are unlocked from the main memory.

Other References

Toy, Fault Tolerant Design of Local ESS Processors, Proceedings of the IEEE, vol. 66, No. 10, Oct. 1978, pp. 1126-1145
Bacete et al., Stored Program Multiregister Control Software, Electrical Communication, vol. 54, No. 4, 1979, pp. 281-291
A. H. Nolta et al., "Maintaining Cached DASD", IBM Technical Disclosure Bulletin, vol. 25, No. 2, Jul. 1982, pp. 823-824
C. F. Ault et al., "Memory Systems", 1A Processor, The Bell System Technical Journal, vol. 56, No. 2, Feb. 1977, pp. 191-192