Hitachi, Ltd.

Nippon Petrochemicals Company, Limited

Hitachi Software Engineering Company, Ltd.

Naoya Takahashi

Yasuo Inoue

Hidefumi Masuzaki

Hidehiko Iwasaki

Soichi Isono

Hiroyuki Kurosawa

Masayuki Hoshino

Tatuya Ninomiya

Kazuo Nakagoshi

Satoshi Narui

Akira Yamamoto

Atsushi Sato

Akira Kurano

Eiju Katsuragi

Mikito Ogata

Toshihiko Tamiya

Makoto Kogai

Keiji Endo

Eiichi Matsuzaka

Minoru Yoshida

Kenichi Takamoto

Yoshinori Okami

Hisao Honma

Hitoshi Yanagishita

Yasuo Togami

Ken-ichi Takamoto

Masahiko Sato

Yutaka Takata

Isoo Shimizu

Shigenobu Kawakami

Akira Chuma

Yoshio Yukawa

Haruka Kashiwazaki

Ryoichi Miura

Osamu Sotoyanagi

A storage system, coupled to a host computer, including at least one controller receiving data from the host computer, and a plurality of memory units connected to the controller. The controller generates parity data and sends the data and the parity data to the memory units. The memory units include a semiconductor memory device which stores the data and the parity data permanently.

Storage system having a semiconductor memory device which stores data and parity data permanently

A storage system to be connected to a large-scale computer includes a plurality of host adaptors connected to a host device, a plurality of storage device for storing data from the host device, a plurality of disk adaptors connected to the storage devices, a plurality of caches for temporarily storing data transferred between the host adaptors and the disk adaptors, and two buses connected to the host disk adaptors, and the caches. The buses transfer data among the host and disk adaptors and the caches.

Storage system having data format conversion function

A disk array device selects a redundant generation method for reducing the overhead and improving the reliability associated with generating redundant data. The disk array device includes a disk controller connected to and controlling an array of disk drives. The disk controller includes a redundant data generator, a difference data generator, and a redundant data generation method selector. The redundant data generator is able to generate redundant data via a read and modify method and an all stripes method. The disk array device selects a method of generating redundant data from a method of read and modify and all stripes, and a method of generation in a drive and a method of difference, both of which are executed to generate redundant data on a disk drive.

Disk array device with selectable method for generating redundant data

A disk array device selects a redundant generation method for reducing the overhead and improving the reliability associated with generating redundant data. The disk array device includes a disk controller connected to and controlling an array of disk drives. The disk controller includes a redundant data generator, a difference data generator, and a redundant data generation method selector. The redundant data generator is able to generate redundant data via a read and modify method and an all stripes method. The disk array device selects a method of generating redundant data from a method of read and modify and all stripes, and a method of generation in a drive and a method of difference, both of which are executed to generate redundant data on a disk drive. The disk array device selects the method of generating redundant data that will minimize the time required to process, transfer and store both the received host data and the generated redundant data based on the length of write data received from the host, an access pattern specified by the host, by the current load state of the disk drives, and by the existence of a failure state in a disk drive. Divided write data and previous data to be updated may be transferred depending on the write data length.

Storage system

A storage system to be connected to a large-scale computer includes a plurality of first logical units connected to a host device, a plurality of second logical units connected to a storage device, a plurality of cache memories, and a common bus wired between these logical units and memories. The plurality of first logical units, the plurality of second logical units, and the plurality of cache memories are all made in the form of modules. The modules are detachably mounted to the common bus disposed on a back plane. The storage device can be made up of a plurality of small-size storage units arranged in an array. Thus, the storage system realizes its scalability. Since the plurality of first logical units, the plurality of second logical units, and the plurality of cache memories are duplexed and the common bus is made in the form of 2 channels, the storage system can perform degrade operation. Since plurality of first logical units, the plurality of second logical units, and the plurality of cache memories allow hot replace, the storage system can realize its non-stop maintenance.

Storage system having plural buses

A disk array device selects a redundant data generation method for reducing the overhead and improving the reliability associated with generating redundant data. The disk array device includes a disk controller connected to and controlling an array of disk drives. The disk controller includes a redundant data generator, a difference data generator, and a redundant data generation method selector. The redundant data generator is able to generate redundant data via a read and modify method and an all stripes method. The disk array device selects a method of generating redundant data from a method of read and modify and all stripes, and a method of generation in a drive and a method of difference, both of which are executed to generate redundant data on a disk drive. The disk array device selects the method of generating redundant data that will minimize the time required to process, transfer and store both the received host data and the generated redundant data based on the length of write data received from the host, an access pattern specified by the host, by the current load state of the disk drives, and by the existence of a failure state in a disk drives. Divided write data and previous data to be updated may be transferred depending on the write data length.

Storage system realizing scalability and fault tolerance

The write data is entered from the upper unit into a nonvolatile cache provided in a controller inside of each disk unit through a channel adaptor, a cache shared by each disk, and a disk adaptor. The data from the cache is compressed by the data compressing and restoring device and is written in the disk. At a time, the management information for compressed data is written in the cache and the disk as well. In case of breaking the management information of the cache when a failure takes place in the cache memory, the management information is written for each disk. Hence, the breakage does not have an adverse effect on the other disks. If the management information of the cache is broken, the management information given into the disk may be replaced with the broken information.

Data storing system and data transfer method

A semiconductor storage device transfers data with an information processing device and includes a non-volatile semiconductor memory in which data is electrically re-writable, a volatile semiconductor memory connected to the non-volatile memory and temporarily storing data of the non-volatile semiconductor memory, and a CPU connected to the volatile semiconductor memory and the non-volatile semiconductor memory. The CPU controls the transfer of data among the non-volatile memory, the volatile memory and the CPU. The CPU also transfers data with the information processing device in accordance with a fixed-length form for data. When an access from the CPU to the volatile semiconductor makes a miss hit (i.e., misses), the CPU accesses the non-volatile semiconductor memory. When a failure is generated in the non-volatile semiconductor memory or when a predicted service life of the non-volatile semiconductor memory is elapsed, the non-volatile semiconductor memory can be substituted by an alternate memory.

Semiconductor disk storage

An external storage system is connected to a host system. A controller unit interposed between disk drives and the host system has a large capacity buffer memory with a battery providing non-volatile storage, a plurality of host interfaces and a plurality of drive interfaces. All the accesses made to the disk drives from the host system are realized via the buffer memory which allows a high-speed access. Read/write processing performed for the buffer memory by the host system is executed asynchronously with read/write processing performed between the buffer memory and the disk drives. The drive interface and the host interface area released during a period in which operation of the disk drive is waited for and recoupled upon data transfer.

System for controlling data flow between plurality of host interfaces

In an information storage system having at least a storage medium which includes a plurality of storage areas. Each storage area is associated with one logical drive. Using a control device and in conjunction with an I/O control device and a memory, the system can process coexisting code and image information to permit a designated logical drive to access an area of the storage areas that corresponds to the designated logical drive according to correspondence relation information.

System and method for control of coexisting code and image data in memory

A semiconductor storage device is connected to at least one magnetic storage device. The input and output of data is made between the semiconductor storage device and an information processing device. The semiconductor storage device includes an electrically erasable non-volatile semiconductor memory which stores directory information of data stored in the magnetic storage device, a volatile semiconductor memory which has a storage capacity smaller than that of the non-volatile semiconductor memory and the storage contents of which are updated to store a part of the directory information having a higher frequency of access from the information processing device, and a CPU connected to the volatile semiconductor memory and the non-volatile semiconductor memory for making access to the volatile semiconductor memory and the non-volatile semiconductor memory in accordance with an access request from the information processing device, wherein when access to the volatile semiconductor memory made for access from the information processing device to the magnetic storage device hits on the part of the directory information, the CPU transfers the part of the directory information to the information processing device without making access to the non-volatile semiconductor memory and the information processing device makes access to the magnetic storage device on the basis of the part of the directory information When a failure is generated in the non-volatile semiconductor memory or when a predicted service life of the non-volatile semiconductor memory is elapsed, the non-volatile semiconductor memory is substituted by an alternate memory.

Semiconductor disc storage

Growing community of inventors

Yokohama, Japan

Naoya Takahashi