Electrical computers and digital processing systems: memory – Storage accessing and control – Specific memory composition
Reexamination Certificate
2002-06-20
2004-06-22
Moazzami, Nasser (Department: 2187)
Electrical computers and digital processing systems: memory
Storage accessing and control
Specific memory composition
C714S006130
Reexamination Certificate
active
06754770
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Field of the Invention
The present invention relates to a RAID subsystem, and more particularly, to a coherence preservation method of duplicated data in RAID subsystem.
2. Background of the Related Art
Generally, RAID (redundant array of inexpensive disks) subsystems provide storage management with the effectiveness by recognizing several physical devices as one logical device, and support a characteristic of high availability allowing high performance data input/output and failure in accordance with RAID levels (RAID
0
to RAID
9
).
The RAID subsystem supports several levels of RAID, duplicating and storing the data at a disk array consisting of a number of disk drives, and implements the input/output in parallel. In addition, the subsystem requires a method capable of supporting the availability of the data without not interrupting the service of the system when the error occurs in each RAID level, and rapidly recovering an error data.
For example, RAID
1
of a disk mirroring type corresponding to a level
1
of the RAID is any one level of RAID in that the same data is duplicated and stored in different several number of disks to improve the availability and reliability of the data, and the load balancing is implemented from the duplicated data of several disk with respect to the write operation. Temporary and permanent errors generated in the existing RAID subsystem supporting the RIAD
1
cause a problem of coherence in the duplicated data.
In particular, the temporary error is generated when access to the disk is not allowed temporally due to several situations, thereby resulting in a problem of data coherence or inconsistency among the disks. The permanent error is generated from a physical failure of the disk, so that it is inevitable to replace the disk and to recover the entire data of the disk in which the error occurs.
Accordingly, the conventional RAID subsystem supporting the RAID
1
has to consider a method of preventing the data failure due to the error and of managing the coherence among the duplicated data to maintain the data properly. In order to solve the problem, it has been a method of preventing the data failure from the error by comparing the contents stored in the respective cache to coincide with each other by use of two RAID controllers, thereby securing the correction of the data, and implementing the write on the disk from the cache of the controller used when the error occurs.
Proposed is another method for maintaining the coherence among the duplicated data of the RAID
1
in which busy/stale bit used in Petal of virtual disk system is adopted.
According to a method for maintaining the data coherence in the Petal, if the write operation on the data is requested, a busy bit is set to “1” before the operation. If the write operation on the entire disks consisting the RAID
1
is normally completed, a busy nit is set to “0” . If an error occurs in an arbitrary disk, a stale bit is set to “1” with respect to a data block to be used from now on. The set stale bit is used upon implementing the temporary error recovery of the disk, and selection recovery is performed with respect to the data blocks with “1” of the stale bit.
The Petal method needs the operation expense with respect to the bit every operation, and requires a separate stable disk for the busy/stale bit.
In addition, in order to maintain the data coherence and secure the correction of the data, a method of reading the contents of the respective disk and comparing the contents fo the duplicated data is simple, it provides a drawback of increasing load of the system.
SUMMARY OF THE INVENTION
Accordingly, the present invention is directed to a coherence preservation method of duplicated data in RAID subsystem that substantially obviates one or more problems due to limitations and disadvantages of the related art.
An object of the present invention is to a coherence preservation method of duplicated data in RAID subsystem, in which when an error occurs in disks of the RAID subsystem supporting RAID
1
of disk mirroring type, a bitmap managing the information of data coherence (called as FBB (failed block bitmap)) is added, so that it secures the coherence of the duplicated data and supports rapid recovery of the data having improper coherence from a temporary or permanent error, and which when recovering the data due to the permanent error of an arbitrary disk, it is possible to disperse the load on a write operation, and to decrease the recovery expense.
To achieve the object and other advantages, according to one aspect of the present invention, there is provided a coherence preservation method of duplicated data in RAID subsystem, the method comprising the steps of: if a read operation is requested by the RAID subsystem, selecting an arbitrary target disk among disks having duplicated data, and implementing the read operation on the selected disk; implementing a read error handling to determine whether an error occurs in the disks selected upon the read operation, and if the error occurs in the read operation of the selected target disk, repeating the read error handling until the read operation of the data succeeds by circulating the remaining metering-treated disks in turns; after the read error handling, if the read operation on the remaining disk in all succeeds, completing the read error handling, and if the read operation on the remaining disk in all fails, returning the error to the disk, and completing the read error handling; if a write operation is requested by the RAID subsystem, implementing the write operation on the disks having duplicated data; after implementing the write operation, if a temporary error occurs in the duplicated data, implementing a temporary error handling to maintain the data coherence in the disks having the duplicated data and to recover the temporary error; and after implementing the write operation, if a permanent error occurs in the duplicated data, implementing a permanent error handling to maintain the data coherence in the disks having the duplicated data and to recover the permanent error.
It is to be understood that both the foregoing general description and the following detailed description of the present invention are exemplary and explanatory and are intended to provide further explanation of the invention as claimed.
REFERENCES:
patent: 6058054 (2000-05-01), Islam et al.
patent: 11-85410 (1999-03-01), None
patent: 2001-11204 (2001-02-01), None
Edward K. Lee and Chandramohan A. Thekkath; Petal:Distributed Virtual Disks;Systems Research Center, Digital Equipment Corporation; 7thInternational Conference on Architectural Support for Programming Languages and Operating Systems; 1996; pp. 1-9.
Bak Yu Hyeon
Kang Dong Jae
Kim Chang Soo
Kim Young Ho
Shin Bum Joo
Electronics and Telecommunications Research Institute
Jacobson & Holman PLLC
Moazzami Nasser
LandOfFree
Coherence preservation method of duplicated data in RAID... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Coherence preservation method of duplicated data in RAID..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Coherence preservation method of duplicated data in RAID... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3360792