摘要:
A particularly efficient storage system makes redundant copies of data on tape by waiting until a rewind/unload command is received and then copying stored data objects en masse, thereby benefitting from any data compression used to store the objects along with the lower overhead for the copy operation. This copy operation is more efficient than the data objects' original storage, because there is less overhead in copying the data objects en masse; also, there is less data to copy if the data objects were stored with any data compression. Efficiency may be further increased by dividing the task of originally writing the data objects between paired tape drives, and then exchanging data objects between the tape drives upon issuance of the rewind/unload command.
摘要:
A data storage library system and a method for storing, and maintaining and tracking synchronism between, multiple copies of identifiable data volumes between hosts and a plurality of data storage libraries, and transparent to the hosts. The library controller of each library provides an updatable synchronization token directly associated with each data volume. A plurality of directors are provided, each separate from and coupled to the hosts and each separate from and coupled to each data storage library. Each director responds to ones of separate, partitioned access addresses addressed by the hosts. The responding director supplies each data volume supplied from a host to all of the data storage libraries, and updates each synchronization token directly associated with the supplied data volume. Thus, the directors store duplicate copies of the data volume in the data storage libraries without involvement by the host. The currency of the data volumes are each tracked by means of the directly associated synchronization token, and the synchronization token is not tracked by the host nor is a central tracking database required.
摘要:
Provided are a method, system, and program for providing a mirror copy of data. An update to a primary storage is received and transferred to an intermediate system in a first transfer mode. The update is transferred from the intermediate system to a secondary storage in a second transfer mode, wherein the secondary storage provides a mirror copy of updates to the primary storage.
摘要:
A system and method, employing a data storage device, for providing communication between a plurality of processing units which are respectively unconnected to each other, with the processing units each separately coupled to the data storage device. A data storage device controller coupled to storage interfaces and to a buffer, recognizes “broadcast” commands and any message accompanying the “broadcast” commands, and recognizes “read message” commands, received from the processing units. The controller stores the message accompanying the “broadcast” command in the buffer, and forwards, at the storage interfaces, a “message ready” signal to at least one of the processing units. The processing units then send a “read message” command to the data storage device. The controller responds to a “read message” command at one of the storage interfaces, supplying the message stored in the buffer at the storage interface to the sending processing unit.
摘要:
A disk caching method for an intermediary controller is disclosed. Requests for data blocks are made and then disk caching is performed according to a most expedient cache method. The disk caching method may be performed by asynchronously requesting a data record from both a intermediary controller disk storage and from a intermediary controller cache and using a first received copy of the data record, the first received copy being a copy received first from the intermediary controller disk storage. Alternatively, the disk caching may be performed by searching an intermediary controller cache to determine whether requested data is located in the cache of the intermediary controller, searching a storage device of the intermediary controller to determine whether requested data is located in the storage device of the intermediary controller and retrieving the requested data from a disk controller coupled to the intermediary controller when the requested data is not in the cache or storage device of the intermediary controller. The intermediary controller maintains a cache hit ratio for cache in a disk controller cache and chooses a cache method based upon a comparison of the hit ratio to the threshold. The intermediary controller selects an item to replace in the intermediary controller cache, moves data into the intermediary controller cache, determines whether the hit ratio of the disk controller is greater than the threshold and moves the item into the intermediary controller storage device when the hit ratio of the disk controller cache is greater than the threshold. The intermediary controller discards the item form the cache of the intermediary controller when the hit ratio of the disk controller is not greater than the threshold.
摘要:
Drive image providers of a virtualization system for an automated data storage library provide an image of a fixed plurality of virtual data storage drives with fixed identifications to a host application. A drive resource provider, at any one time, assigns any number “m” of a pool of “n” drives to the drive image providers, and “n”−“m” of the pool are freed and available for assignment. The drive resource provider responds to a triggering event requesting a drive, and dedicates one of the “n”−“m” drives of the pool to the virtual drive. The drive image provider characterizes and directs communication between the host and the dedicated drive as a fixed virtual drive; and prior to the dedication of a drive, characterizes the virtual drive to the requesting host application as “not ready”.
摘要:
A system and method, employing a data storage device, for providing communication between a plurality of processing units which are respectively unconnected to each other, with the processing units each separately coupled to the data storage device. The data storage device is coupled to the processing units by means of peripheral or storage interfaces, each coupled to one of the processing units for receiving commands and signals sent from each of the processing units and for supplying signals to each of the processing units. A controller coupled to the storage interfaces and to a buffer, recognizes “broadcast” commands and any message accompanying the “broadcast” commands, and recognizes “read message” commands, received from the processing units. The controller stores the message accompanying the “broadcast” command in the buffer, and the controller forwards, at the storage interfaces, a “message ready” signal to at least one of the processing units. The processing units then send a “read message” command to the data storage device. The controller responds to a “read message” command at one of the storage interfaces, supplying the message stored in the buffer at the storage interface to the sending processing unit.
摘要:
A data storage library subsystem and a method for storing, and maintaining and tracking synchronism between, multiple copies of identifiable data volumes between hosts and a plurality of data storage libraries, and transparent to the hosts. The library controller of each library provides an updatable synchronization token directly associated with each data volume. A plurality of directors are provided, each separate from and coupled to the hosts and each separate from and coupled to each data storage library. Each director responds to ones of separate, partitioned access addresses addressed by the hosts. The responding director supplies each data volume supplied from a host to all of the data storage libraries, and updates each synchronization token directly associated with the supplied data volume. Thus, the directors store duplicate copies of the data volume in the data storage libraries without involvement by the host. The currency of the data volumes are each tracked by means of the directly associated synchronization token, and the synchronization token is not tracked by the host nor is a central tracking database required.
摘要:
A plurality of processing entities of a computer processing system employ messages for communicating with each other, and are updatable to newer versions at each of the processing entities by an initialization process. To maintain continuous availability, compatibility for the messages is established between the processing entities by maintaining, for message types, at each processing entity, identification values of the maximum and of the minimum versions of the message type supported at the entity. An initializing processing entity requests the maximum and minimum version identification values for the message types from other processing entities of the system. The initializing entity compares its maintained maximum and minimum version identification values to received maximum and minimum version identification values, and selects, as its current version, the maximum version whose identification value intersects with the maintained maximum and minimum version identification values and the maximum and the minimum version identification values of all the other processing entities.
摘要:
Data storage drives of an automated data storage library are allocated to received requests. A drive resource provider, upon receiving a request for a drive when all of the drives of the pool are allocated, holds any mount of a portable data storage cartridge relative to the request, releasing the hold when a drive is allocated. Spare drives are provided, outside of the pool. A spare drive may be allocated in response to the request, and a message is posted indicating use of the spare data storage drive. The posted message may comprise a notification that action may be taken to permanently transfer a spare data storage drive to the pool.