International Business Machines Corporation

Globalfoundries Inc.

David Michael Shackelford

Gregory E McBride

John Glenn Thompson

Lisa Joan Gundy

Beth Ann Peterson

Warren Keith Stanley

Alfred Emilio Sanchez

William Frank Micka

Cuong Minh Le

Ronald Maynard Kern

Robert Nelson Crockett

Nicolas Marc Clayton

John Richard Paveza

Eduard Aaron Diel

Robert Frederic Kern

Matthew J Kalos

Harry M Yudenfriend

David C Reed

Dale Francis Riedy, Jr

Susan Kay Candelaria

Scott Brady Compton

Deborah A Furman

Alan George McClure

Donald Reynold Blea

Dinesh C Verma

Dakshi Agrawal

Kaladhar Voruganti

Robert Beverley Basham

Kang-Won Lee

Kenneth Wayne Boyd

Sandeep Gopisetty

David Randall Blea

David B Petersen

Jeffrey Richard Suarez

Brent William Yardley

Khalid Filali-Adib

Tarek Makansi

Robert Stanley Gensler, Jr

James Mitchell Ratliff

Ernesto E Figueroa

Gail Andrea Spear

Clint Alan Hardy

Mark Francis Wilding

Jeffrey William Palm

Mark Alan Haye

Carol Santich Mellgren

Jeffrey Mark Nick

Yoram Novick

Robert Wesley Shomler

Donna N Eng Dillenberger

Ilene A Goldman

Nadim P Shehab

Ronald David Boenig, Ii

Donna Eng Dillenberger

Claus William Mikkelsen

Errol Jay Calder

Todd Benjamin Schlomer

Douglas Michael Zobre

Stephen C West

Bard Allen Doster

John Thomas Flynn, Jr

Robert Vaughn Geiner

Larry Richard Perry

Michael Aloysius Paulsen

Stephen F Edel

Mary Catherine Burton

Jimmie Lee Brundidge

Harold Glen Slone

Donna Weaver

Brian Michael Seaman

Thai T Pham

Susan Van Berkel

Anthony H Giang

A computer-implemented method according to one embodiment includes, prior to executing a point-in-time copy job, running a space checker program to generate a list that includes: source data sets that will be used in the point-in-time copy job and a pool of potential target volumes that are eligible to be used for the point-in-time copy job. The method further includes determining that insufficient space is available on the potential target volumes to perform the point-in-time copy job. An on-demand migration is issued against one or more target volumes of the pool of potential target volumes for ensuring there is sufficient space available on the one or more target volumes associated with the issued on-demand migration to perform the point-in-time copy job. The method further includes performing the point-in-time copy job.

Ensuring sufficient space is available on target volumes before performing a point-in-time copy job

A computer-implemented method related to dynamic resource provisioning, includes: receiving, at a computer, a request to facilitate a testing environment, where the request specifies a number and type of resources to be included in the testing environment. A database which lists available resources in systems and/or devices that are in communication with the computer is inspected and the available resources are compared to the number and type of resources specified in the request to be included in the testing environment. In response to determining that a valid combination of the available resources meets the number and type of resources specified in the request to be included in the testing environment, the database is updated to indicate that each of the resources in the valid combination are in use. Moreover, the request is satisfied by returning information about the resources in the valid combination.

Dynamic resource provisioning for use cases

A storage controller receives a command from a host application to perform a point-in-time backup of a source dataset to a storage cloud. The storage controller generates a target dataset via a point-in-time copy of the source dataset, and a mapping that indicates a correspondence between locations of the source dataset and locations of the target dataset. The storage controller copies the target dataset to the storage cloud to generate a backup dataset that is the point-in-time backup of the source dataset, wherein the backup dataset is accessible via reference to the locations of the source dataset.

Point-in-time backups via a storage controller to an object storage cloud

Described are techniques for utilization of a disaster recovery site including a method comprising receiving a mirrored data stream at a disaster recovery site from a production site. The mirrored data stream includes a workload instruction stored in a designated location of the mirrored data stream. The workload instruction indicates an operation to perform on a set of data that is replicated between the production site and the disaster recovery site and a time indicator indicating a correct version of the set of data. The method further comprises generating a consistency point by retrieving replicated data from the disaster recovery site corresponding to the correct version of the set of data in the production site. The method further comprises performing the operation on the consistency point, generating an output, and transmitting the output to the production site.

Workload coordination on disaster recovery site

Methods that can batch process data on a remote system or disaster recovery (DR) site are disclosed herein. One method includes determining, by a processor, a first performance level for a production site based on a set of first resources for the production site and determining a second performance level for a DR site based on a set of second resources for the DR site. The method further includes allocating a portion of a workload scheduled for processing on the production site to the DR site for processing on the DR site in response to determining that a set of predetermined parameters related to the first performance level, the second performance level, or both the first performance level and the second performance level is satisfied. Apparatus, systems, and computer program products that can include, perform, and/or implement the methods are also disclosed herein.

Apparatus, systems, and methods for remote system batch processing

Provided are a computer program product, system, and method verifying mirroring of source data units to target data units. Source data units in a source storage are mirrored to corresponding target data units in a target storage. The source data units are read to compare to corresponding mirrored target data units. The read source data units that did not match the corresponding target data units are saved in source version data. The source data units that were read and did not match the corresponding target data units are read. The mirroring of the source data units are verified in response to determining that for each mirrored source data unit, one of a read source data unit and the read source data unit saved in the source version data matches the corresponding target data unit.

Verifying mirroring of source data units to target data units

Described are techniques for utilization of a disaster recovery site including a method comprising receiving a mirrored data stream at a disaster recovery site from a production site. The mirrored data stream includes a workload instruction stored in a reserved record set type. The workload instruction indicates an operation to perform on a set of data that is replicated between the production site and the disaster recovery site and a time indicator indicating a correct version of the set of data. The method further comprises generating a consistency point by retrieving replicated data from the disaster recovery site corresponding to the correct version of the set of data in the production site. The method further comprises performing the operation on the consistency point, generating an output, and transmitting the output to the production site.

A method for copying data from a primary fully provisioned volume to a secondary thin-provisioned volume is disclosed. In one embodiment, such a method includes hosting, on a primary storage system, a fully provisioned volume comprising a plurality of storage elements. A volume table of contents (VTOC) associated with the fully provisioned volume is analyzed to determine which storage elements in the fully provisioned volume have been allocated to data sets. In certain embodiments, the VTOC is copied into memory of a secondary host system and the secondary host system analyzes the copy to determine which storage elements in the fully provisioned volume have been allocated to data sets. The method then copies, from the fully provisioned volume to a secondary thin-provisioned volume, data in only those storage elements that have been allocated to data sets. A corresponding system and computer program product are also disclosed.

Efficient asynchronous mirror copy of fully provisioned volumes to thin-provisioned volumes

A method for copying data from a primary thin-provisioned volume to a secondary thin-provisioned volume includes issuing a query to a primary storage system. The primary storage system hosts a thin-provisioned volume made up of multiple storage elements. The method returns, in response to the query, a reply indicating which storage elements in the thin-provisioned volume are backed by physical storage. In certain embodiments, the reply contains a bitmap having a bit for each storage element in the thin-provisioned volume. In other embodiments, the reply contains a starting address and ending address for each storage area that is backed, or not backed, by physical storage. The method then copies, from the primary storage system to a secondary storage system, data in only those storage elements that are backed by physical storage. A corresponding system and computer program product are also disclosed.

Efficient asynchronous mirror copy of thin-provisioned volumes

Embodiments of the present invention provide systems, methods, and computer program products for managing computing devices to handle an input/output (I/O) request. In one embodiment, the I/O request may eligible for performance throttling based, at least in part, on the associated importance level for performing the received I/O request and one or more characteristics of the received I/O request. Embodiments of the present invention provide systems, methods, and computer program products for throttling the I/O request and transmitting the I/O request to a storage controller.

Management of allocation for alias devices

A computer implemented method includes the steps of establishing a plurality of storage control sessions, wherein each storage control session associates at least one primary storage controller and at least one secondary storage controller with a predetermined path through a data transport network that interconnects the primary and secondary storage controllers; identifying storage control sessions that have data available to be transferred from primary storage controllers to secondary storage controllers; accumulating available data for each session and determining transfer time through the network for each data element to estimate prospective bandwidth utilization; and determining, for a predetermined time interval, whether transferring the available data would fully occupy available bandwidth of the data transport network for the predetermined time interval. When available bandwidth would be fully occupied, the available data accumulated during predetermined time intervals prior to the predetermined time interval in which fully occupied bandwidth was detected is transferred.

Optimizing data transfer across multiple asynchronous data replication sessions using shared bandwidth

When the mirrored point in time copy fails, at that point in time all the data for making the source and target of the point in time copy consistent is available on secondary volumes at disaster recovery site. The data for the source and target of the failed point in time copy are logically and physically equal at that point in time. This logical relationship can be maintained, and protected against ongoing physical updates to the affected tracks on the source secondary volume, by first reading the affected tracks from the source secondary volume, copying the data to the target secondary volume, and then writing the updated track to the source secondary volume.

Resolving failed mirrored point-in-time copies with minimum disruption

Growing community of inventors

Tucson, AZ, United States of America

David Michael Shackelford