International Business Machines Corporation

Storage Technology Corporation

Amdahl Corporation

Michael Richard Crater

Steven Christopher Fraioli

Christopher James West

David Glenn Hostetter

David P Haldeman

Chris Satterlee

Jim Lloyd Mechalke, Jr

Dave Dooley

George Zalewski

A method and system are provided for improving efficiency of storing and accessing data blocks for systems that are limited to small size, host accessible data blocks, such as having a maximum size of 512 bytes, by allowing larger size subsystem data blocks to be created from the smaller size logical data blocks. A host command is analyzed to determine whether the host accessible logical data block aligns with the larger subsystem block. If so, the larger block(s) is(are) sent to the host. If the command does not align, the larger block is processed into a plurality of segments so that the addressed data block(s) can be aligned, and any error correction coding verified. The present invention allows a subsystem to store and manage efficiently sized blocks of data while still supporting a host's need to access smaller, single architecturally defined addressable blocks. The present invention is particularly suited for use with storage architectures arranged to compress data and add CRC redundancy codes, such as a shared virtual array (SVA) architecture.

Method and system of reformatting data blocks for storage as larger size data blocks

An interface for expanding the number of SCSI hosts that can access a storage array includes a SCSI interface chip for receiving a SCSI command from a host via a SCSI bus, a domain indicator for providing a domain number assigned to the SCSI chip, a memory device for storing data and code, and a processing unit responsive to the code and operative to generate a device address from the domain number, the target number, and the logical unit number, and to execute the SCSI command with a particular device of the storage array corresponding to the device address. The domain indicator may be either hardware based (e.g., a mechanical selector switch) or software based (e.g. written to a data storage device of the interface via a SCSI host or WIE the storage array). A method for interfacing a SCSI host with a storage array includes the steps of receiving a SCSI command from the host via a connection to the SCSI bus, the SCSI command including a target number and an LUN, receiving a domain number assigned to the connection to the SCSI bus, generating a device address from the domain number, the target number, and the LUN, and executing the SCSI command with one of the storage devices corresponding to the generated device address.

System and method for host expansion and connection adaptability for a

A system incorporating the invention stores data on communicating disk drives in such a manner as to enable recovery of the data in the event a failure of one of the disk drives. The system includes a first disk drive and a second disk drive, both for storing compressed data records in compressed track formats. Each compressed data record includes a CRC value. A cache stores compressed tracks of data records that are read from the first disk drive and a CRC value is calculated for each stored track of compressed data records. That CRC value is appended to the compressed track. A switch is coupled between the cache, a host processor and the second disk drive for dispatching and receiving tracks of compressed data records between the first disk drive and the second disk drive. The switch includes computational circuitry for calculating a CRC value for each track of compressed data records received from the cache and for determining a match or non-match state with the CRC value appended to each track of compressed data records. In such manner, a system which is primarily adapted to handle records with appended CRC values is adapted to handle tracks of compressed data records with appended CRC values so as to assure data integrity.

Method and apparatus for enabling transfer of compressed data record

The invention provides a method and apparatus for generating a signature signal which indicates a probable location for an error-causing mechanism within a digital system, where the digital system has control-signal and data-signal carrying busses and error detection means for detecting error conditions in the signals carried by those busses. The signature generating method comprises the steps of: counting the total number of errors detected by the error detection means during a signature generating run; and counting the number of errors detected by the error detection means during a signature generating run where those errors were accompanied by the presence of accompanying signals on the signal-carrying busses, the accompanying signals being ones which belong to a predefined subset of all signals appearing on the system signal-carrying busses.

Signature detecting method and apparatus for isolating source of

The data storage subsystem of the present invention uses a large plurality of small form factor disk drives to implement an inexpensive, high performance, high reliability disk drive memory that emulates the format and capability of large form factor disk drives. The data transmitted by the associated computer system is used to generate redundancy information which is written with the data across N+M disk drives in a redundancy group in the data storage subsystem. To clear the redundancy accumulator memory, an associated pointer memory is used to indicate the ones of the redundancy accumulator memory byte positions that were used in the previous redundancy calculation. As data is received from the computer system, the pointer memory is checked to determine whether this next byte position need be reset to erase the previously stored redundancy calculation residue. If not, the data is simply stored therein.

Growing community of inventors

Arvada, CO, United States of America

Michael Richard Crater