Abstract:
Technology described herein provides methods whereby a two-level indexing/hashing structure is used to efficiently coordinate storage of sensor measurements between local digital memory (e.g., at a mobile device) and remote digital memory (e.g., at a cloud storage system). The first level of the two-level indexing/hashing structure may be include an array of first-level nodes that are sorted according to priority values. The priority values may be determined based on user data-querying activity. The second level of the two-level indexing/hashing structure may include second-level hash tables wherein buckets are associated with memory blocks of a predefined size. Sensor measurements that were taken during a specific time period may be stored near each other in memory and may be downloaded for local storage if user activity suggests that the user frequently has interest in data from that time period.
Abstract:
An improved interface for managing disparate read, write, and erase sizes and operations in data storage devices is provided. By improving an interface between a storage system driver layer and associated storage devices, performance of data storage is improved, including improving data storage speed and storage media endurance. Storage media management operations are made more efficient and consistent by providing improved types and sequences of commands sent from the driver layer to the device control layer such that data write operations are performed in a sequential manner as write commands are directed to portions of data as opposed to buffering individual portions of data followed by a large wholescale write/erase process for the buffered data.
Abstract:
Systems and methods which implement one or more data organization techniques that facilitate efficient access to source data stored by a storage system are disclosed. Data organization techniques implemented according to embodiments are adapted to optimize (e.g., maximize) input/output efficiency and/or (e.g., minimize) storage overhead, while maintaining mean time to data loss, repair efficiency, and/or traffic efficiency. Data organization techniques as may be implemented by embodiments include blob based organization techniques, grouped symbols organization techniques, data ordering organization techniques, and combinations thereof.
Abstract:
Examples may include techniques for adaptive compression for data stored in a memory device. The techniques include monitoring a data access pattern to a file or a block for data stored in the memory device and determining a data compression action based on, at least in part, the monitored data access patterns for the file or the block and on an assessed relationship of the file or the block with other files or other blocks. The data compression action including compressing data accessed via the file or the block, decompressing compressed data accessed via the file or the block or no compression action for data accessed via the file or the block.
Abstract:
Embodiments of the invention provide systems and methods for managing processing, memory, storage, network, and cloud computing to significantly improve the efficiency and performance of processing nodes. Embodiments can implement an object memory fabric including object memory modules storing memory objects created natively within the object memory module and may be a managed at a memory layer. The memory module object directory may index all memory objects within the object memory module. A hierarchy of object routers communicatively coupling the object memory modules may each include a router object directory that indexes all memory objects and portions contained in object memory modules below the object router in the hierarchy. The hierarchy of object routers may behave in aggregate as a single object directory communicatively coupled to all object memory modules and to process requests based on the router object directories.
Abstract:
Functionality is disclosed herein for providing an asynchronous processing service for processing storage mapping information. The asynchronous processing service is configured to receive a storage request including identification of a storage object and a description of a storage operation, perform the storage operation for the storage object in response to receiving the storage request, and asynchronously update mapping information for the performed storage operation.
Abstract:
Apparatuses, methods and storage media associated with memory management in virtualized computing are disclosed herein. An apparatus may include a virtual machine manager to manage operations of a plurality of virtual machines, having a memory manager to manage allocation and de-allocation of physical memory to and from the plurality of virtual machines. Allocation and de-allocation may include de-allocation of unused and used physical memory allocated to a first of the plurality of virtual machines to recover physical memory for allocation to one or more other ones of the plurality of virtual machines, and re-allocation of physical memory for the previously de-allocated unused and used physical memory of the first virtual machine.
Abstract:
A unifying memory controller (UMC) to send and receive data to and from a local host. The UMC also may manage data placement and retrieval by using an address mapper. The UMC may also selectively provide power to a plurality of memory locations. The UMC may also manage data placement based on a policy that can make use of a property stored in the metadata storage location. The property may be a property describing the data that is being managed. The UMC also may use its own local cache that may store copies of data managed by the circuit.