International Business Machines Corporation

Errol Jay Calder

David Randall Blea

Todd Benjamin Schlomer

Gregory E McBride

John Jay Wolfgang

James E Damgar

Jimmie Lee Brundidge

William D Olsen

Trent T Cooper

James J Fagan

Richard T Solsten, Iii

Forrest E Townsend

Sarvesh S Patel

Kushal S Patel

David Michael Shackelford

Benjamin J Randall

Steven M Kern

Jeffrey R Placer

Jacob A Stevens

Astrid O Brockman

Provided are a computer program product, system, and method for managing retained container objects in storage having referenced chunks referenced in other objects. Reference counts are maintained for referenced chunks in a container object indicating a number of references to the referenced chunks in at least one application object resulting from deduplication. The container object is indicated as reclaim eligible while the reference counts for at least one of the referenced chunks for the container object is at least one. A reference count is decremented for one of the referenced chunks in the container object in response to the at least one application object expiring. The container object, including chunks for the container object, is indicated as eligible for deletion when the reference counts for the referenced chunks in the container object are zero and the container object is indicated as reclaim eligible.

Managing retained container objects in storage having referenced chunks referenced in other objects

A method for destaging data from cache is disclosed. In one embodiment, such a method includes maintaining, in cache, modified data to be destaged to persistent storage drives. The method further detects an emergency situation wherein the modified data needs to be promptly destaged to the persistent storage drives. In response to the emergency situation, the method automatically disables artificially-imposed throughput limits associated with the persistent storage drives. The method then destages the modified data to the persistent storage drives without restriction from the artificially-imposed throughput limits. A corresponding system and computer program product are also disclosed.

Storage system de-throttling to facilitate emergency cache destage

In one embodiment, automated storage target selection includes automatically selecting a storage node of a plurality of candidate storage nodes as a function of a plurality of selection criteria. Further, a backup data object is transmitted to the selected storage node. In one embodiment, selecting a storage node includes retrieving stored user-defined parameters for selection criteria for selecting a storage node, retrieving storage node-defined parameters for selection criteria, comparing user-defined parameters and storage node-defined parameters, and selecting a storage node as a function of the comparing. In another aspect of the present description, comparing user-defined parameters and storage node-defined parameters includes broadening a first user-defined parameter to a second user-defined parameter broader than the first user-defined parameter if no candidate storage nodes have a storage node-defined parameter within the first user-defined parameter. Other features and aspects may be realized, depending upon the particular application.

Automated storage target selection for data backup

A computer-implemented method according to one embodiment includes suspending a parent/control thread of a data storage system, and receiving a plurality of read requests while the parent/control thread is suspended, each read request having storage information associated therewith. The computer-implemented method further includes resuming the parent/control thread, analyzing the read requests, aggregating read requests requesting common data objects into a common read operation, and dispatching the common read operation to a multi-threaded I/O layer of the data storage system for retrieving data associated with the read requests. The analyzing includes sorting the read requests using the associated storage information.

Aggregation of read requests requesting common data objects into a common read operation in a data storage system for improving throughput

Provided are a method, system, and program for using a heartbeat signal to maintain data consistency for writes to source storage copied to target storage. A copy relationship associates a source storage and target storage pair, wherein writes received at the source storage are transferred to the target storage. A determination is made whether a signal has been received from a system within a receive signal interval. A freeze operation is initiated to cease receiving writes at the source storage from an application in response to determining that the signal has not been received within the receive signal interval. A thaw operation is initiated to continue receiving write operations at the source storage from applications after a lapse of a freeze timeout in response to the freeze operation, wherein after the thaw operation, received writes completed at the source storage are not transferred to the target storage.

Using a heartbeat signal to maintain data consistency for writes to source storage copied to target storage

A method for replicating a volume of data including selecting a target storage box to receive a physical copy of the actual volume of data stored on the source storage box for replication of the actual volume of data, selecting a point in time storage box to receive a physical copy of actual data stored on the target storage box, physically copying actual data stored on the target storage box to the point in time storage box, performing the replication of the actual volume of data by initiating the physical copying on the target storage box of the actual volume of data, and selectively undoing the physical copying on the target storage box of the actual volume of data by replacing the current actual data stored on the target storage box with the physical copy of actual target storage box data stored on the point in time storage box.

Replication management with undo and redo capabilities

A method is disclosed to provide commands to an information storage and retrieval comprising one or more data storage devices, where one or more first communication links interconnect one or more host computers and the data storage and retrieval system. The method supplies a computing device, where that computing device is external to the data storage and retrieval system, and where that computing device is external to each of the one or more host computers. Applicants' method further supplies a second communication link interconnecting the computing device and the data storage and retrieval system. The computing device generates a command signal, where said command signal comprises one or more command control words and a header. The computing device then provides that command signal to the data storage and retrieval system via the second communication link.

Apparatus and method to provide one or more commands to a data storage and retrieval system

An apparatus, system, and method are disclosed for initializing a synchronized remote database. A creation module creates a first backup table of a backup database from a schema for a primary table of a primary database. A read module reads each row from the primary table with an application server configured to manage access to the primary database by a database application. A construction module constructs a SQL command for each row of the primary table. Each SQL command inserts data of a primary table row in the first backup table. An application module applies each SQL command to the first backup table to mirror the primary table at the first backup table.

Apparatus, system, and method for initializing a synchronized remote database

This presentation allows for two or more storage management servers to be in an active high availability (HA) state for the same set of storage devices and copy services relationships; rather than having a single server be in an active HA state and the other servers being in a standby HA state. This makes each HA server to be able to accept commands at any time so that they will not have to issue a takeover command to a standby server just to start issuing commands. This will also ensure that the data replication pairs will continue copying data until an event of an actual disaster; in which the active servers would then cause the data replication to be suspended so that a consistent set of data is secured on the secondary site.

Active-active server for high availability of data replication management application

Disclosed is a technique for creating a copy services solution. A document describing the copy services solution is received. The document is converted to executable code. The code is executed to perform one or more base copy services solutions described with base copy types in the document.

Method, system, and program for autonomic copy services solutions

A computer program for automatically pairing target resourcessuch as volumes or logical units to source resourcescontaining data to be copied. Available target poolsof target volumes are determined eligible for copying based on a technical compatibility and a user-defined metric such as recovery point or recovery time. User defined metrics and a policy to implement the metrics may be stored in a medium and selected by a user. The source volumes are prioritized, and progressively larger segments of the eligible target pools are searched for a target volume that satisfies the technical compatibility and user-defined metric. Where subgroups such as nested volumes are present in the source volumes, subgroups are also prioritized for searching. Where no target volume can be paired, the corresponding source volume is marked as processed and a search begins for the next source volume. An output report includes pairings of source to target volumes and source volumes for which no pairing was made.

Growing community of inventors

Vail, AZ, United States of America

Errol Jay Calder