Electrical computers and digital data processing systems: input/ – Intrasystem connection – Bus interface architecture
Reexamination Certificate
2001-08-22
2003-06-17
Niebling, John F. (Department: 2812)
Electrical computers and digital data processing systems: input/
Intrasystem connection
Bus interface architecture
C710S001000, C710S052000
Reexamination Certificate
active
06581128
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Field of the Invention
The present invention relates to storage systems which include a storage controller for controlling storage device, such as a magnetic tape device, a semiconductor storage device, or an optical disk device connected to a large-scale computer, a network system or the like. More particularly, the present invention relates to a storage system which is highly extendable and which allows degraded operation and hot replace.
2. Description of the Related Art
A conventional storage system connected to large-scale computer is disclosed in, for example, JP-B-61-43742 (corresponding to U.S. Pat. No. 4,636,946). In the system disclosed therein, interfaces (host adaptors) with a higher-rank or host device (computer) (CPU), a cache memory, and interfaces (disk adaptors) with a storage device such as a magnetic disk device are interconnected by hot lines (dedicated lines).
FIG. 20
shows a schematic arrangement of a conventional storage system. In the drawing, reference numerals
201
-
1
to
201
-
n
denote host adaptors connected respectively to a plurality of host computers (CPUs) (logical modules connected to a host computer),
202
-
1
to
2
-
2
-
n
denote disk adaptors (logical modules connected to a storage device) connected to a shared large-scale disk device
205
,
203
denotes a cache memory shared with the plurality of host adaptors, and
206
denotes a shared management memory. In a conventional storage system, hot lines
207
-
1
to
207
-
n
and
208
-
1
to
208
-
n
are connected between the host adaptors
201
-
1
to
201
-
n
and cache memory
203
, between the cache memory
203
and disk adaptors
202
-
1
to
202
-
n,
between the host adaptors
201
-
1
to
201
-
n
and management memory
206
and between the management memory
206
and disk adaptors
202
-
1
to
202
-
n
respectively. Further, maintenance processors (SVPs, not shown), which carry out monitoring and maintenance operations over these host adaptors and disk adaptors, are connected to respective host and disk adaptors through respective dedicated lines.
In the prior art system described above, since the hot lines are wired between the host adaptors (logical modules connected to the host device) to the host device, the disk adaptors (logical modules connected to the storage device) to the storage device, and the cache memory (cache memory module), the system configuration becomes more complicated, and the host adaptors, cache memory, disk adaptors and disk device are poorer in extendability, which makes it impossible to realize a so-called scalable (extendable and reducible) system configuration. Further, in prior art systems, no consideration is paid to the fact that multiplexing of the system enables degraded operation (one of the system multiplexers is stopped and the other alone is operated) at the time of failure occurrence or Hot replace (a substrate or a circuit part is inserted for its exchange while the system is being operated). For this reason, prior art systems such as the one described above have a problem in that, when it is desired to perform an exchanger or replacement of parts at the time a system failure occurs or when it is time to up-grade a system control program, the entire system must be temporarily stopped to perform that purpose.
SUMMARY OF THE INVENTION
Therefore, it is an objective of the present invention to provide a storage system which solves the above problem in the prior art by employing a common bus system in such a manner that logical modules such as host adaptors and memory adaptors, a cache memory, and a storage medium can be connected according to the system configuration (scale or size) to thereby realize a scalable system. A further objective of the present invention is to provide a storage system which can realize degraded operation by multiplexing respective logical modules, a storage medium and a common bus, and also which can realize hot replacement of the respective logical modules and storage medium to thereby allow system maintenance without halt of the system.
In accordance with one preferred embodiment of the present invention, there is provided a storage system which comprises a plurality of logical units connected to a host device to form interfaces with the host device, a storage unit, a plurality of logical units connected to the storage unit to form interfaces with the storage unit, and cache memories (shared with the plurality of logical units connected to the host device and with the plurality of logical units connected to the storage unit) for temporarily storing therein data to be transferred between these devices and units. The plurality of logical units connected to the host device, the plurality of logical units connected to the storage unit, and the cache memories are interconnected by a common bus which is shared with these devices and units. As a result, there can be obtained a scalable system which realizes extension and modification of the plurality of logical units connected to the host device, the plurality of logical units connected to the memories, and the cache memory merely adding or modifying these on the common bus, and which realizes easy attainment of its upgrade based on the extended system provision.
Since the plurality of logical units connected to the host device, the plurality of logical units connected to the memories, and the cache memories are arranged in a duplexed form and the common bus is wired between these logical units and memory as divided into 2 channels, even when one of these units becomes faulty, the other unit can be used to perform degrade operation. In this connection, information indicative of the degraded operation status at the time of a failure occurrence is written in the shared memory.
In this case, since any of the plurality of logical units connected to the host device, the plurality of logical units connected to the storage unit, and the cache memories are provided with a connector which allows for hot replacement, the system allows maintenance and inspection to occur for exchange of a faulty parts, and also allows for the addition of parts to facilitate system extension, all without having to halt the system while in operation.
REFERENCES:
patent: 4158235 (1979-06-01), Call et al.
patent: 4300194 (1981-11-01), Bradley
patent: 4417334 (1983-11-01), Gunderson et al.
patent: 4453215 (1984-06-01), Reid
patent: 4486826 (1984-12-01), Wolff et al.
patent: 4490785 (1984-12-01), Strecker et al.
patent: 4636946 (1987-01-01), Hartung et al.
patent: 4695952 (1987-09-01), Howland
patent: 4754397 (1988-06-01), Varaiya et al.
patent: 4785453 (1988-11-01), Chandran et al.
patent: 5037310 (1991-08-01), Marinello
patent: 5089958 (1992-02-01), Horton et al.
patent: 5093826 (1992-03-01), Leichum
patent: 5123099 (1992-06-01), Shibata et al.
patent: 5148432 (1992-09-01), Gordon et al.
patent: 5155835 (1992-10-01), Belsan
patent: 5206939 (1993-04-01), Yanai
patent: 5224213 (1993-06-01), Dieffenderfer et al.
patent: 5237567 (1993-08-01), Nay et al.
patent: 5247618 (1993-09-01), Davis et al.
patent: 5283879 (1994-02-01), Carteau et al.
patent: 5335352 (1994-08-01), Yanai
patent: 5337414 (1994-08-01), Hashemi et al.
patent: 5345566 (1994-09-01), Tanji
patent: 5388215 (1995-02-01), Baker et al.
patent: 5430855 (1995-07-01), Walsh et al.
patent: 5459856 (1995-10-01), Inoue
patent: 5471586 (1995-11-01), Sefidvash et al.
patent: 5495585 (1996-02-01), Datwyler et al.
patent: 5625777 (1997-04-01), Takahashi et al.
patent: 5630056 (1997-05-01), Horvath et al.
patent: 5708784 (1998-01-01), Yanai
patent: 5819054 (1998-10-01), Ninomiya et al.
patent: 6012119 (2000-01-01), Ninomiya
patent: 5206939 (1990-12-01), None
patent: 0445479 (1991-09-01), None
patent: 6143742 (1986-09-01), None
patent: 2234254 (1990-09-01), None
patent: 331919 (1991-02-01), None
patent: 3192425 (1991-08-01), None
patent: 3245246 (1991-10-01), None
patent: 460846 (1992-02-01), None
patent: 496818 (1992-03-01), None
patent: 4155466 (1992-05-01), None
patent: 4157549 (1992-05-01), None
patent: 4223518 (1992-
Hoshino Masayuki
Inoue Yasuo
Isono Soichi
Iwasaki Hidehiko
Kurosawa Hiroyuki
Antonelli Terry Stout & Kraus LLP
Hitachi , Ltd.
Whitmore Stacy
LandOfFree
Storage system does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Storage system, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Storage system will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3149008