Hitachi, Ltd.

Mitsuaki Niida

Tomohiro Murata

Kenzo Kurihara

Kazuhiro Kawashima

A plurality of processors of a disk controller are divided into a plurality of clusters. In normal operation, data is transferred between a host computer and a disk drive in a cluster non-restricted processing mode in which a job can be distributedly processed among processors belonging to any clusters without regard to cluster. In response to a program version upgrading command from an operator, the cluster mode is shifted from the cluster non-restricted processing mode to a cluster restricted processing mode in which the cluster to which processors which are permitted to distributedly process one job belong is restricted. When the shifting to the cluster restricted processing mode is completed, one cluster is selected as a cluster to be maintained and versions of the programs to be executed by the processors belonging to the cluster to be maintained are upgraded. When the versions of the programs of all processors of the cluster to be maintained have been upgraded, the acceptance of a new job by the processors belonging to the cluster to be maintained is resumed and the execution of the new programs is started. The selection of the cluster, the version upgrading of the programs and the start of the execution of the new programs are repeated sequentially for all clusters. When the version upgrading of the programs of all processors is completed, the cluster mode is returned from the cluster restricted processing mode to the cluster non-restricted process mode.

Multi-processor system, disk controller using the same and nondisruptive maintenance method thereof

A plurality of processors of a disk controller are divided into a plurality of clusters. In normal operation, data is transferred between a host computer and a disk drive in a cluster non-restricted processing mode in which a job can be distributedly processed among processors belonging to any clusters without regard to cluster. In response to a program version upgrading command from an operator, the cluster mode is shifted from the cluster non-restricted processing mode to a cluster restricted processing mode in which the cluster to which processors which are permitted to distributedly process one job belong is restricted. When the shifting to the cluster restricted processing mode is completed, one cluster is selected as a cluster to be maintained and versions of the programs to be executed by the processors belonging to the cluster to be maintained are upgraded. When the versions of the programs of all processors of the cluster to be maintained have been upgraded, the acceptance of a new job by the processors belonging to the cluster to be maintained is resumed and the execution of the new programs is started. The selection of the cluster, the version upgrading of the programs and the start of the execution of the new programs are repeated sequentially for all clusters. When the version of the programs of all processors is completed, the cluster mode is returned from the cluster restricted processing mode to the cluster non-restricted processing mode.

System for processing an I/O request using an old program while loading a new program which upon completion used to process the I/O request

A plurality of processors of a disk controller are divided into a plurality of clusters. In normal operation, data is transferred between a host computer and a disk drive in a cluster non-restricted processing mode in which a job can be distributedly processed among processors belonging to any clusters without regard to cluster. In response to a program version upgrading command from an operator, the cluster mode is shifted from the cluster non-restricted processing mode to a cluster restricted processing mode in which the cluster to which processors which are permitted to distributedly process one job belong is restricted. When the shifting to the cluster restricted processing mode is completed, one cluster is selected as a cluster to be maintained and version of the programs to be executed by the processors belonging to the cluster to be maintained are upgraded. When the version of the programs of all processors of the cluster to be maintained have been upgraded, the acceptance of a new job by the processors belonging to the cluster to be maintained is resumed and the execution of the new programs is started. The selection of the cluster, the version upgrading of the programs and the start of the execution of the new programs are repeated sequentially for all clusters. When the version upgrading of the programs of all processors is completed, the cluster mode is returned from the cluster restricted processing mode to the cluster non-restricted processing mode.

System for selecting one cluster of processors and upgrading the version

A disk controller itself performs the serial inspection process in the following way. It divides a track into a current track group directly available for an external computer and a spare track group available for the disk controller independently of the external computer before registering the groups in it. It also automatically selects a track available in the spare track group as an alternative track. It further copies to the alternative track data recorded on a current track to be inspected. In turn, the disk controller writes a test pattern on the current track. With this, it detects a defect position on a surface of a recording medium of the current track. It also registers the defect position detected on the surface of the recording medium to the current track. It further copies the data having been copied on the alternative track to the current track.

Growing community of inventors

Chigasaki, Japan

Mitsuaki Niida