Abstract: An apparatus and method for training a search engine generates synthetic search arguments and target information that are provided to the search engine as training. A search argument simulator ingests product information and historical interaction data, determines relevant descriptors, creates compound descriptors, and creates candidate search arguments. A trainer checks the candidates against historical search arguments, identifies similar search arguments and determines likely search arguments that are used for training. An evaluator monitors search engine responses and triggers retraining of the search engine.

Abstract: A method and system for use in managing data objects is disclosed. In at least one embodiment, the method and system comprises based on at least one policy set, determining that a data object stored on a first device is eligible for mobile enablement and a level of mobile enablement for the data object; mobile enabling the data object, wherein mobile enabling the data object comprises causing a mobile data storage tier associated with the first device to include the data object; and providing access to the data object to a second device, wherein access is defined by the level of mobile enablement.

Abstract: A client computer migrates data objects from a first data store employing a flat namespace to a second data store employing a hierarchical directory-based file system. File storing includes (1) generating a data object (for user data file) and an object identifier which is returned to an application for use in retrieving the user data file; (2) mapping the object identifier to originate a subdirectory name; and (3) sending a write request to the file system to create the named subdirectory and store the data object therein. File retrieving includes (4) sending a read request including the object identifier to the first data store; (5) extracting a user data file from a received data object and returning it to the application; and (6) performing the steps of the file storing to store the data object at the second data store, completing the migration of the data object.

Abstract: A file is initially created to have metadata and a data block allocation for direct mapping without access to any indirect blocks. Therefore file access performance is increased because the direct mapping eliminates delay otherwise caused by fetching one or more indirect blocks. When needed, the functionality enabled by indirect mapping is provided by creating an indirect mapping for the file and then accessing the file using the indirect mapping. When the functionality enabled by the indirect mapping is no longer needed, the file is reorganized to a direct mapping and then accessed using the direct mapping. For example, a container file for a network attached SCSI LUN is created and accessed without a performance degradation until conversion to an indirect mapping occurs automatically and seamlessly upon activation of a supplementary storage service such as a file-based snapshot copy and replication facility.

Abstract: A data storage server is programmed with common software modules for management, version control, and scheduling of replication of data storage objects of multiple data storage object types. The multiple data storage object types include iSCSI LUNs, file systems, virtual servers, directories, and files. The version control determines if two data storage objects are the same or have a common base so that only a difference needs to be transmitted for replication or restoration. The scheduler controls the timing of snapshot creation and deletion, and replication transmission to one or more remote destinations. The scheduler may ensure that a replica of a data storage object is out-of-sync with the original of the data storage object by no more than a specified amount of time.

Abstract: A method, computer program product, and cache management system for receiving an indication of a data portion update within an electromechanical storage system. Information concerning the data portion update is provided to at least one proprietary, solid-state, non-volatile, cache memory system. The proprietary, solid-state, non-volatile, cache memory system is associated with at least a first of a plurality of computing devices and is not associated with at least a second of the plurality of computing devices.

Abstract: A file server provides access to a file system built on a logical volume of data storage. The file system includes multiple cylinder groups of file system blocks, and the logical volume includes slices of the cylinder groups. The file server has a storage reorganizer for identifying allocated file system blocks in a selected slice, and evacuating the identified allocated file system blocks from the selected slice. The selected slice is evacuated by reverse mapping each identified allocated block to identify a file to which the identified allocated block is allocated, allocating a new block in another slice, copying data from the identified allocated block to the new block, and substituting the new block for the identified allocated block in the file.

Abstract: A method, computer program product, and cache management system for receiving an indication of a data portion update within an electromechanical storage system. Information concerning the data portion update is provided to at least one proprietary, solid-state, non-volatile, cache memory system. The proprietary, solid-state, non-volatile, cache memory system is associated with at least a first of a plurality of computing devices and is not associated with at least a second of the plurality of computing devices.

Abstract: In response to detection of an error in a filesystem file of a virtually provisioned volume or iSCSI LUN host, where the filesystem file is represented in a container filesystem, a Media Sector Error is returned at the virtual volume layer or the virtual iSCSI layer. The error may be a file allocation correction because of a shared block detected by a filesystem check of the container filesystem. The container may flag the shared block to prompt return of the Media Sector Error in response to attempted access of the block by the host. The host is operative to process the Media Sector Error like a storage subsystem Read Media Error, such that the flagged block is overwritten by the host to clear the error.

Abstract: Storage tiering uses file system awareness of storage class for storage allocation or migration of a storage object from one class of storage to another. For example, the storage object is a production file system, a logical unit number (LUN) of storage, or a snapshot copy of the production file system or LUN. Each storage class may comprise a different back-end disk type, such as Fiber Channel, ATA, etc. Storage allocation or migration is based on storage class to implement a storage policy, such as: (a) move snapshots off the class of storage of the production object and onto a different class of storage; (b) direct new writes to a specified class of storage; or (c) writes targeting a particular storage object are targeted to a particular class of storage.

Abstract: When a directory tree is migrated from a source file system to a target file system, the directories of the directory tree are retained in the source file system, and handle translation entries are substituted for the regular data files of the directory tree in the source file system. The handle translation entries provide new file handles for the regular data files when the source file system is accessed with old file handles of the regular data files. For example, each handle translation entry includes the old file handle, a file system identifier, and the new file handle. The old file handle provides verification of the file handle being used for accessing the handle translation entry, and the file system identifier identifies the target file system in which the new file handle is valid.

Abstract: Client computers, a namespace server, and file servers are linked in a data network so that the namespace server provides the clients with NFS or CIFS access to a virtual file system including files stored in the file servers, and also provides migration of files between the file servers in a fashion transparent to the client access using NFS or CIFS. The client computers and storage arrays storing the file data are also linked in a storage area network so that the clients have high speed block access to the file data using a file mapping protocol. The namespace server redirects a metadata access request in the file mapping protocol from a client to the appropriate file server when the file is not being migrated, and otherwise denies the metadata access request when the file is being migrated so that the client reverts to NFS or CIFS access.

Abstract: When a client requests creation of a production file system or logical unit number (LUN) of storage, a sparse metavolume and a container file system built on the sparse metavolume are implicitly created for containing the production file system or LUN. By implicitly creating one container file system for each production file system or LUN, it is possible to hide the management of the container file system from the client or end user. The creation of snapshot copies in the container file system can also be hidden from the client or end user. Customer service level expectations and thin provisioning can be met automatically by storage policies implemented upon the container file system and the underlying sparse metavolume.

Abstract: A data storage server is programmed for management, version control, and scheduling of replication of multiple types of data storage objects including iSCSI LUNs and file systems. The version control determines if two data storage objects are the same or have a common base so that only a difference needs to be transmitted for replication or restoration. A replication job may specify a “one-to-many” replication or a cascaded replication, and any snapshot retention policy is propagated during a cascaded replication. Concurrent replication sessions to the same destination are paced in accordance with respective allocation shares of the reception bandwidth. File handle information is replicated so that a file handle issued by a primary data storage server can be used for accessing a replicated file in a secondary data storage server.

Abstract: Consistency errors may arise during replication of diverse data storage objects from servers in a data network. For preventing consistency errors, a server is programmed for responding to a request for a report of whether or not the server can replicate the dataset without causing a consistency error. Such a report is useful for replicating a consistency group of objects from more than one server. Preparation for replication can be begun at each of the servers, and if any of the servers fail to report that replication can be done without causing a consistency error, the preparation can be aborted so that write access by applications will not be disrupted while the potential problem is diagnosed and eliminated.

Abstract: A self healing file system is designed for proactive detection and containment of faults, errors, and corruptions, in order to enable in place (online) and non-intrusive recovery. For proactive fault detection, the file system maintains certain per-block metadata of each file system block. The per-block metadata includes a redundancy check, and for file system data blocks, an inode identifier, and an offset of the file system data block in the file including the file system data block. The redundancy check is used to detect and mark bad file system blocks. The inode identifier and offset is used for validating connectivity of the file system blocks to the inodes, and for tracing bad blocks to files that contain the bad blocks.

Abstract: A container file system is built on a sparse metavolume for enhanced decoupling of logical storage from physical storage and for providing common supplementary storage services for iSCSI block access and for NFS or CIFS file system access. The container file system contains a production file system or iSCSI LUN and may also contain snapshot copies of the production file system or iSCSI LUN. The container file system manages storage space among the production file system or iSCSI LUN and its snapshot copies, and also improves fault containment. The sparse metavolume provides thin provisioning of the container file system. A slice map indicates whether or not each slice of logical storage in the sparse metavolume is provisioned with an associated configured slice of data storage.

Abstract: For disaster recovery of a file server at an active site, the files that define the user environment of the file server are replicated to a virtual server at a disaster recovery site. To switch over user access from the active site to the disaster recovery site, the disaster recovery system determines whether there are sufficient network interfaces and file system mounts at the disaster recovery site. If so, the required resources are reserved, and user access is switched over. If not, an operator is given a list of missing resources or discrepancies, and a choice of termination or forced failover. Interruptions during the failover can be avoided by maintaining a copy of user mappings and a copy of session information at the disaster recovery site, and keeping alive client-server connections and re-directing client requests from the active site to the disaster recovery site.