Harry M. Yudenfriend

Bio: Harry M. Yudenfriend is an academic researcher from IBM. The author has contributed to research in topics: Input/output & Host (network). The author has an hindex of 35, co-authored 196 publications receiving 3480 citations.

Peer-to-peer backup system with failure-triggered device switching honoring reservation of primary device

Abstract: A peer-to-peer backup storage system automatically switches from a primary storage site to a mirrored backup site in response to a primary site failure, where the secondary site then honors any existing host initiated reservation of primary storage. Each site includes a storage controller and storage, where the primary site receives and stores data and forwards the received data to the secondary site for storage to mirror contents of primary storage. The primary and secondary sites are coupled to one or more hosts. Whenever the primary controller receives a reserve request from a host, it reserves the primary storage (or a subpart thereof) for the exclusive use of the reserve-initiating host. This may involve, for example, the primary controller storing a path group ID that identifies the reserving host. The primary controller also notifies the secondary controller of the reservation, e.g., sending the path group ID involved in the reservation operation to the secondary site. Responsive to a primary site failure, the system performs “switch” operation where the system stops forwarding data from the primary site to the secondary site. Furthermore, the secondary site is operated in substitution for the primary site, to receive and store data from the hosts. Importantly, the secondary site honors the existing reservation of the primary storage by reserving the secondary storage to the first reserve-initiating host.

Concurrent switch to shadowed device for storage controller and device errors

Abstract: A disaster recovery system providing remote data shadowing between a primary and a secondary site uses a method and apparatus for swapping, or switching, host directed I/O operations from a primary data storage device to a secondary data storage device in a remote copy duplex pair. Application programs running in a host processor at the primary site first quiesce all I/O operations and record updates targeted to the primary data storage device. The remote copy duplex pair is checked to verify that the secondary data storage device is a fully synchronized copy of the primary data storage device. The secondary data storage device is then swapped with the primary data storage device by terminating the remote copy duplex pair, establishing an opposite direction remote copy duplex pair such that the secondary data storage device is a primary device of the duplex pair and the primary data storage device is a shadowing device, and updating the application programs running in the primary host processor with a device address of the secondary data storage device substituted as a device address of the primary data storage device. Finally, the primary host processor resumes its application programs such that subsequent I/O operations and record updates targeted for the primary data storage device are directed through a secondary storage controller to the secondary data storage device, and copied to the primary data storage device.

Database backup system ensuring consistency between primary and mirrored backup database copies despite backup interruption

Abstract: A database management system ensures consistency between primary and mirrored backup copies of a database, despite occurrence of a suspending condition interrupting the normal process of mirroring the primary database. One or more primary controllers are provided, each having a data storage unit with multiple primary data storage devices. Multiple secondary controllers each have multiple associated secondary data storage devices, each secondary controller being coupled to one primary controller. One or more primary databases reside on the primary devices, with a corresponding number of secondary databases residing on the secondary devices. Each secondary database mirrors a corresponding primary database. Either a host, attached to a primary controller, or one of the primary controllers itself, maintains a map cross-referencing each primary and secondary database with the primary and secondary devices containing portions thereof. If a predefined “suspending condition” affecting data mirroring occurs, the host or primary controller consults its map to identify all primary and secondary devices affected by the condition. Then, each primary controller stops all ongoing and future read/writes with each of its affected primary devices. Each primary controller also directs each secondary controller having an affected secondary device to stop mirroring the primary databases stored on that device. Then, the primary controller starts intermediate change recording and resumes read/writes with its primary devices. When the suspending condition ends, each primary controller applies the appropriate logged changes to its secondary database(s) and then reactivates each secondary database.

Dynamically changing a system i/o configuration definition

Abstract: A mechanism for changing the system I/O configuration definition in the channel subsystem of a data processing system without having to do a power on reset operation. The data processing system includes one or more central processing units, an I/O processor, a storage addressable by the central processors and the I/O processor, and a command mechanism for creating command-request blocks in the storage, each of which contains a requested command and data for the I/O Processor to add, delete or change elements of the I/O configuration definitions of the channel subsystem. Response-blocks are created in the storage for passing status information from the I/O processor to the central processing unit(s) indicating either successful execution of the requested command or that the I/O configuration definitions were unchanged by the command of the request-block, or when associated functions may have been performed in the execution of the command of the request-block by the I/O processor.

Method and means for limiting duration of input/output (I/O) requests

Abstract: An I/O request time limit value is set in a request-based, device-based, data-set-based, or workload-based time limit field, for transactions performing I/O operations to I/O devices in a data processing system. A scan routine compares the total time for the I/O request (including waiting time and retry time) against the appropriate time limit(s), and terminates the I/O request if the time limit is exceeded. If an active I/O request is interrupted as a result of an I/O error, retry is prohibited if the total I/O request time (including retry time) exceeds the appropriate time limit, or is within a threshold value of the appropriate time limit.

Virtual disk drive system and method

Abstract: A disk drive system and method capable of dynamically allocating data is provided. The disk drive system may include a RAID subsystem having a pool of storage, for example a page pool of storage that maintains a free list of RAIDs, or a matrix of disk storage blocks that maintain a null list of RAIDs, and a disk manager having at least one disk storage system controller. The RAID subsystem and disk manager dynamically allocate data across the pool of storage and a plurality of disk drives based on RAID-to-disk mapping. The RAID subsystem and disk manager determine whether additional disk drives are required, and a notification is sent if the additional disk drives are required. Dynamic data allocation and data progression allow a user to acquire a disk drive later in time when it is needed. Dynamic data allocation also allows efficient data storage of snapshots/point-in-time copies of virtual volume pool of storage, instant data replay and data instant fusion for data backup, recovery etc., remote data storage, and data progression, etc.

Systems and methods for backing up data files

Abstract: The invention provides systems and methods for continuous back up of data stored on a computer network. To this end the systems of the invention include a synchronization process that replicates selected source data files data stored on the network and to create a corresponding set of replicated data files, called the target data files, that are stored on a back up server. This synchronization process builds a baseline data structure of target data files. In parallel to this synchronization process, the system includes a dynamic replication process that includes a plurality of agents, each of which monitors a portion of the source data files to detect and capture, at the byte-level, changes to the source data files. Each agent may record the changes to a respective journal file, and as the dynamic replication process detects that the journal files contain data, the journal files are transferred or copied to the back up server so that the captured changes can be written to the appropriate ones of the target data files.

Storage router and method for providing virtual local storage

Abstract: A storage router and method for providing virtual local storage on remote storage devices to devices are provided. Devices are connected to a first transport medium, and a plurality of storage devices are connected to a second transport medium. In one embodiment, the storage router maintains a map to allocate storage space on the remote storage devices to devices connected to the first transport medium by associating representations of the devices connected to the first transport medium with representations of storage space on the remote storage devices, wherein each representation of a device connected to the first transport medium is associated with one or more representations of storage space on the remote storage devices and controls access from the devices connected to the first transport medium to the storage space on the remote storage devices in accordance with the map and using native low level block protocol.

Method for automatically configuring devices including a network adapter without manual intervention and without prior configuration information

Abstract: A system for configuring a network adapter of a computer without user intervention. Device information for the devices of the computer, including each network adapter, is collected to uniquely identify the devices and to describe the device characteristics associated with the operation of those devices with the computer. Computer resources, which support the functions of the devices within the computer, are allocated based upon this device information. This allocation process prevents a potential conflicting use of computer resources by the installed devices. A device driver, which enables communications between a corresponding device and the computer, is also identified and loaded for each of the devices in response to the allocation of computer resources. In response to loading the driver for each network adapter, each network configuration routine or layer for a particular interface of the corresponding network adapter is identified. In response to the identification of these layers, each identified layer for the particular interface is loaded. In turn, layers are identified and loaded for each of the remaining interfaces of the corresponding network adapter.

Flexible remote data mirroring

Abstract: Methods, systems, and configured storage media are provided for flexible data mirroring. In particular, the invention provides many-to-one data mirroring, including mirroring from local servers running the same or different operating systems and/or file systems at two or more geographically dispersed locations. The invention also provides one-to-many data mirroring, mirroring with or without a dedicated private telecommunications link, and mirroring with or without a dedicated server or another server at the destination(s) to assist the remote mirroring unit(s). In addition, the invention provides flexibility by permitting the use of various combinations of one or more external storage units and/or RAID units to hold mirrored data. Spoofing, SCSI and other bus emulations, and further tools and techniques are used in various embodiments of the invention.