Electrical computers and digital processing systems: memory – Storage accessing and control – Specific memory composition
Reexamination Certificate
2000-02-04
2002-07-23
Nguyen, Hiep T. (Department: 2187)
Electrical computers and digital processing systems: memory
Storage accessing and control
Specific memory composition
C711S114000, C714S006130, C714S006130
Reexamination Certificate
active
06425049
ABSTRACT:
BACKGROUND OF THE INVENTION
The present invention relates to a storage system used in a computer system, and more particularly to a disk array system having a plurality of disk storage apparatuses and a method of changing the configuration of the disk array system.
As an example of a storage system used in a computer system, a disk array system disclosed in “A Case for Redundant Arrays of Inexpensive Disks (RAID)” by D. Patterson, et al., ACM SIGMOD Conference Proceeding, Chicago, Ill., June 1-3, 1988, pp. 109-116, is known. A disk array system achieves high performance by making a plurality of physical disk storage apparatuses appear to the processor as one disk storage apparatus. Normally, redundant data is stored on a disk storage apparatus which is separate from a disk storage apparatus on which data is stored. This allows data to be recovered even when an error occurs on the disk storage apparatus on which the data is stored, thus increasing reliability. In relation to data allocation on a disk array, the above publication also describes how to recover data when parity information is used as redundant data. In a disk array system, data is written in bits or bytes or in blocks which are units of data written by the processor. A plurality of pieces of divided data are written on separate disk storage apparatuses. At this time, data is written onto the plurality of disk storage apparatuses concurrently to nominally increase the data transfer rate. For example, if data is distributed on n disk storage apparatuses, the data transfer rate nominally becomes n times faster. In the description given below, a group of disk storage apparatuses on which distributed data is stored is called a RAID group. The host computer identifies one RAID group as one logical drive.
Recently, a fibre channel has been getting much attention as an interface between a disk array and a host computer. The fibre channel is a serial interface the ANSI (American National Standards Institute) X3T11 committee is working toward standardization. The fibre channel allows a maximum of 10 Km between each two nodes and a maximum transfer rate of 1 G bits/second at each node. An FC-AL (Fibre Channel-Arbitrated Loop: hereinafter called an FC loop), when used as the connection topology of a fibre channel, allows up to 127 nodes. That is, as compared with SCSI (Small Computer System Interface), a fibre channel used as the interface (hereinafter called a back-end interface) between a disk array controller, which controls a disk array, and the disk storage apparatuses allows more disk storage apparatuses to be connected to one channel. In addition, the fibre channel, which may be used even if the distance between two nodes is long, enables the array controller to be separated from disk storage apparatuses and allows a plurality of array controllers and a plurality of disk storage apparatuses to be distributed in, and connected to, one FC loop. For example, a communication system with a connection switching switch for changing the configuration of the devices on an FC loop is disclosed in U.S. Pat. No. 5,841,997. The technology disclosed in this patent allows the user to change, through the software, the configuration of an FC-loop-based system, making it easy to change the configuration manually.
SUMMARY OF THE INVENTION
The publication describing the above technology discloses how to change the configuration of an FC loop through the software but not how to apply it to an actual system. That is, the publication does not describe the problem of how to change and manage the configuration of a disk array system when an FC loop is formed as the back-end interface of the disk array system. Neither does it describe an increase in performance which is achieved by changing the configuration of a disk array system.
It is an object of the present invention to make the configuration of a disk array system be changed easily.
It is another object of the present invention to provide a disk array system which utilizes the expandability of a fibre channel.
To achieve the above objects, the disk array system according to the present invention comprises a disk storage group having at least one disk storage apparatus, an array controller reading data from, or writing data to, the disk storage group, a disk interface connecting unit having a plurality of ports to which the array controller and the disk storage group are connected, and a disk interface connection changing unit controlling a connection status among the plurality of ports in the disk interface connecting unit. The array controller comprises an array configuration information memory storing therein array configuration information indicating a relation between the array controller and the disk storage group controlled by the array controller, an array configuration changing portion changing the array configuration information in response to a user's request, and a connection changing interface informing the disk interface connection changing unit of a connection change based on the changed array configuration information. The disk interface connection changing unit sends instruction information on setting up the connection status among the plurality of ports to the disk interface connecting unit to establish the configuration indicated by the array configuration information. The disk interface connecting unit changes the port connection according to the instruction information sent from the disk interface connection changing unit.
REFERENCES:
patent: 5574851 (1996-11-01), Rathunde
patent: 5787459 (1998-07-01), Stallmo et al.
patent: 5809224 (1998-09-01), Schultz et al.
patent: 5841997 (1998-11-01), Bleiweiss et al.
patent: 5941994 (1999-08-01), DeKoning et al.
ACM SIGMOD Conference Proceedings, Jun. 1-3, 1988, “A case for redundant arrays of inexpensive disks (RAID)”, D. Patterson et al, pp. 109-116.
Matsumoto Jun
Matsunami Naoto
Sato Masahiko
Yagisawa Ikuya
Yamamoto Masayuki
Hitachi , Ltd.
Mattingly Stanger & Malur, P.C.
Nguyen Hiep T.
LandOfFree
Disk array system and method of changing the configuration... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Disk array system and method of changing the configuration..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Disk array system and method of changing the configuration... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2831789