Abstract: A host based caching technique may be used to determine caching policies for a hybrid hard disk drive. Because the host based caching may make use of knowledge about what data is being cached, improved performance may be achieved in some cases.

Abstract: A host based caching technique may be used to determine caching policies for a hybrid hard disk drive. Because the host based caching may make use of knowledge about what data is being cached, improved performance may be achieved in some cases.

Abstract: Disclosed is a data management system configured to provide a key-value data structure architecture for use with a storage device. The key-value data structure includes a logic tree having a tree-based index and a hash table having a hash-based index. For a ‘scan’ (or range query) operation, the data management system scans the tree-based index to determine which keys exist between two search keys in the tree-based index. For a ‘get’ (e.g., a value request) operation, the data management system applies a hash function to a provided key to determine an index in the hash table by which to retrieve a value that corresponds with the provided key. Other operations (e.g., ‘put’, ‘update’, ‘delete’) may include updating both the tree-based index and the hash-based index. The logic tree stores keys and stores a zero byte-sized value with each of the keys, to limit the size of the logic tree.

Abstract: A host based caching technique may be used to determine caching policies for a hybrid hard disk drive. Because the host based caching may make use of knowledge about what data is being cached, improved performance may be achieved in some cases.

Abstract: A host based caching technique may be used to determine caching policies for a hybrid hard disk drive. Because the host based caching may make use of knowledge about what data is being cached, improved performance may be achieved in some cases.

Abstract: Memory allocation for fast platform hibernation and resumption of computing systems. An embodiment of an apparatus includes logic at least partially implemented in hardware, the logic to: dynamically allocate at least a first portion of a nonvolatile memory; in response to a command to enter the apparatus into a standby state, the logic to store at least a portion of a context data from a volatile memory to the dynamically allocated first portion of the nonvolatile memory; and in response to a resumption of operation of the apparatus, the logic to copy at least the portion of the context data from the first portion of the nonvolatile memory to the volatile memory, and to reclaim the first portion of the nonvolatile memory for dynamic allocation.

Abstract: Memory allocation for fast platform hibernation and resumption of computing systems. An embodiment of an apparatus includes logic at least partially implemented in hardware, the logic to: dynamically allocate at least a first portion of a nonvolatile memory; in response to a command to enter the apparatus into a standby state, the logic to store at least a portion of a context data from a volatile memory to the dynamically allocated first portion of the nonvolatile memory; and in response to a resumption of operation of the apparatus, the logic to copy at least the portion of the context data from the first portion of the nonvolatile memory to the volatile memory, and to reclaim the first portion of the nonvolatile memory for dynamic allocation.

Abstract: A host based caching technique may be used to determine caching policies for a hybrid hard disk drive. Because the host based caching may make use of knowledge about what data is being cached, improved performance may be achieved in some cases.

Abstract: Apparatus, systems, methods, and articles, operate to create a log file in a non-volatile data storage medium. The log file includes a header record, a trailer record, and at least one partial parity value associated with a stripe in a redundant array of inexpensive disks (RAID) sub-system. The stripe includes a first data strip to be updated, the first data strip located on an operational first disk drive, a second data strip located on a failed disk drive, and a stripe parity strip located on an operational disk drive, among others.

Abstract: Provided are a method, system, and program for migrating data between storage volumes. A source map is provided indicating blocks of data striped across a first plurality of storage units and a destination map is provided indicating blocks of data striped across a second plurality of storage units, wherein data is migrated from stripes indicated in the source map to corresponding stripes indicated in the destination map. In response to determining that the source stripe and the destination stripe occupy a same physical location on the storage units, the data from a source stripe is written to a copy area and writing the data from the copy area to a corresponding destination stripe.

Abstract: In one embodiment, a method is provided that may include, issuing a read request to request reading of at least one portion of data stored in a first storage device and issuing a write request to request writing of the at least one portion of the data into a second storage device or at least one location in the first storage device. The at least one location may be comprised in a volume of a redundant array of inexpensive disks (RAID), the at least one portion of data being stored in a non-RAID volume in the first storage device. The method of this embodiment also may include, if a request to access one or more other portions of the data is received and/or issued by one or more operating system processes while the reading and/or the writing is occurring, issuing an access request to request accessing of the one or more other portions of the data. Of course, many modifications are possible without departing from this embodiment.

Abstract: In one embodiment, a method is provided that may include, if a change in configuration of storage occurs during one mode of operation of a device, storing, in the storage, data indicative, at least in part, of resulting configuration of the storage resulting after the change. The device may have a relatively lower power consumption rate while the device is operating in the one mode of operation compared to a relatively higher power consumption rate that the device may have while the device is operating in another mode of operation. Of course, many modifications, variations, and alternatives are possible without departing from this embodiment.

Abstract: In one embodiment, a method is provided that may include generating, at least in part, an identifier to be associated with a group of devices. The group of devices may comprise at least two devices. The identifier may be generated, at least in part, based, at least in part, upon respective source identifiers identifying, at least in part, respective sources of the at least two devices. Of course, many modifications, variations, and alternatives are possible without departing from this embodiment.

Abstract: Provided are a method, system, and program for managing data migration from one data organization type to another. In one embodiment, a migration manager defers writing progress indicators to reduce data write operations during the migration process. In one embodiment, progress indicators are written to configuration areas of disk drives when a condition is met. One example of a condition is the expiration of a time period since the last progress indicator was written. Another example of a condition is an overlap between the destination of a unit of data being migrated and the source of the unit of data. Yet another example is an overlap between the destination of a unit of data and a portion of the data source which has been copied but a progress indicator has not yet been written covering the data source portion.

Abstract: In certain embodiments, a plurality of nodes of a hierarchical data structure are generated, wherein each node of the hierarchical data structure represents a set of at least one locked logical block. A request is received to exclusively access a set of at least one logical block. A determination is made, by traversing at least one node of the hierarchical data structure, whether the set of at least one logical block overlaps sets of at least one locked logical block represented by the plurality of nodes of the hierarchical data structure.

Abstract: A method, system, and program manages updates of user data and parity data stored in stripes across a plurality of disk storage units arranged in a data organization type such as a RAID array. In one embodiment, a record of stripes potentially containing inconsistent user and parity data is stored on a disk storage unit. In another aspect, before writing a record of stripes to a disk storage unit, stripe entries for a plurality of write processes is permitted to accumulate. In another aspect, a record of stripes may be written to different disk storage units and a generation number is used to identify the latest record of stripes.