Error detection/correction and fault detection/recovery – Data processing system error or fault handling – Reliability and availability
Reexamination Certificate
1995-12-29
2001-12-25
Le, Dieu-Minh (Department: 2184)
Error detection/correction and fault detection/recovery
Data processing system error or fault handling
Reliability and availability
C714S710000
Reexamination Certificate
active
06334195
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Technical Field
The present invention relates generally to an improved data processing system, and in particular to an improved storage architecture in a data processing system. Still more particularly, the present invention relates to a method and apparatus for using spare storage devices to increase performance during RAID operations.
2. Description of the Related Art
In data processing systems, inexpensive high performance, high reliability memory is desirable. It is expensive to provide high reliability capability for various memory devices that are used within a data processing system. The problem becomes especially severe in the case of disk drive memory systems. Large disk drives capable of storing over one gigabytes of data are available. In many designs, the processor in the data processing system stores data files on the disk drive memory by writing the data for all files onto a single disk drive. The failure of such a single disk drive can result in the loss of significant amounts of data. Disk drives that are built to be high reliability units to minimize the possibility of this catastrophic loss of data. The cost of reliability, however, is high because reliable disk drives are expensive.
In critical situations, where the loss of data stored on the drive could cause a significant disruption in the operation of the processor in the data processing system, additional reliability may be obtained by disk “shadowing” or backing up each disk drive with an additional redundant disk drive. The provision of a second disk drive, however, to back up the primary disk drive will typically more than double the cost of storage for the data processing system. Various storage architectures have been presented to reduce the cost of providing disk shadowing backup protection. One architecture involves storing only changes that are made to the data stored on the disk drive. Another backs up only the most critical data stored on the disk drive. Yet another architecture periodically backs up data by storing it on a much less expensive data storage unit that also has a much slower data retrieval access time.
Another alternative for providing reliable storage includes using a number of smaller sized disk drives interconnected in a parallel array. In such a system, the microprocessor in the data processing system views the array of storage devices as a very large logical storage device with logical tracks thereon. Each logical track would be many times larger than any physical track extent of any of the physical storage devices forming the array. Such an architecture is often referred to as a direct access storage device (DASD) array, which includes a set of synchronously selected and operated DASDs.
One particular form of a DASD array is a redundant array of inexpensive disks (RAID) storage system, which has emerged as an alternative to large, expensive disk drives for use within data processing systems. Five different RAID levels are described in an article entitled “A Case For Redundant Arrays of Inexpensive Disks (RAID)” by David Patterson, et al., University of California Berkeley Report, No. UCD/CSD 87/391, December 1987. In traditional RAID systems, configurations typically involve one or two controllers that share drives in a protected environment. In this protected environment, disk drives are managed fairly simply because they are easily identified with the storage subsystem to which they are attached.
In these types of systems, disk drives within a disk drive storage subsystem may be designated as a hot spare device (HSD) that may be used by one or more controllers in the storage subsystem as a spare or replacement for another disk drive in the event that a disk drive within the storage subsystem fails. This set up provides for higher availability of data to the user, as well as a higher performance as a result of a quicker return to optimal redundancy modes after a device failure. In typical configurations, however, disk drives designated as hot spare devices are not used during normal operation, when other disk drives in the disk drive storage subsystem are working properly.
Therefore, it would be advantageous to have an improved method and apparatus for using HSDs or spare disk drives during normal operations to increase performance of a data processing system.
SUMMARY OF THE INVENTION
The present invention provides a method and apparatus for increasing performance in a data processing system. The data processing system includes a plurality of storage devices and a backup storage device. The backup storage device can be configured as a log device. After the backup storage device has been configured as a log device, data is logged to the backup storage device. In response to a failure of a storage device within the plurality of storage devices, the backup storage device is reconfigured to be used as a replacement for the failed storage device.
The above as well as additional objectives, features, and advantages of the present invention will become apparent in the following detailed written description.
REFERENCES:
patent: 4434487 (1984-02-01), Rubinson et al.
patent: 4914656 (1990-04-01), Dunphy et al.
patent: 4989205 (1991-01-01), Dunphy et al.
patent: 4989206 (1991-01-01), Dunphy et al.
patent: 5077736 (1991-12-01), Dunphy, Jr. et al.
patent: 5124987 (1992-06-01), Milligan et al.
patent: 5140592 (1992-08-01), Idleman et al.
patent: 5274645 (1993-12-01), Idleman et al.
patent: 5297258 (1994-03-01), Hale et al.
patent: 5418925 (1995-05-01), DeMoss et al.
DeKoning Rodney A.
Humlicek Donald R.
Rink Curtis W.
Le Dieu-Minh
LSI Logic Corporation
LandOfFree
Use of hot spare drives to boost performance during nominal... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Use of hot spare drives to boost performance during nominal..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Use of hot spare drives to boost performance during nominal... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2572460