Abstract: A system that automatically determines ideal temporary backup targets (TBTs) to store and restore backup data. For multiple TBTs, backup data is saved with location information to restore incremental backup data from these multiple targets. Hashes of each file are stored in a Merkle tree to enable data restore workflows and minimizing an amount of storage required to hold backup data. The lowest tree level comprises hashes of the backup data chunks, and higher levels contain hashes of the next lower levels. A backup target location value is added to non-data chunk hash records in the higher levels to identify where any piece of backup data is located so that restore operations can occur when the backup data is spread across multiple backup targets.

Abstract: This application discloses a data writing method. A network controller performs erasure code encoding on original data, and writes a third quantity of target data blocks of a plurality of obtained target data blocks into a storage node. The network controller reads a first quantity of target data blocks of the third quantity of the target data blocks from the storage node, and decodes the read target data blocks. The plurality of target data blocks include a first quantity of original data blocks and a second quantity of check data blocks, two ends of a target data block include same version information, and the third quantity is greater than the first quantity.

Abstract: A computing device is operable to receive a plurality of partition allocation requests based on execution of a corresponding plurality of query operations in conjunction with execution of a corresponding query. Processing a first partition allocation request of the plurality of partition allocation requests corresponding to execution of a first operation of the corresponding plurality of query operations is based on allocating a set of partitions of a plurality of partitions. Content is loaded into the set of partitions for access in executing the first operation. Access to the content via the set of partitions is facilitated in conjunction with execution of the first operation. The set of partitions are released based on determining the first operation has completed access of the content in conjunction with the execution of the first operation.

Abstract: A method, comprising: selecting an HBA entity that is currently turned on and which is part of a host device, the host device being coupled to a storage array, the host device being configured to read and write data to the storage array; identifying an identifier of the HBA entity; identifying, based on the identifier, a switch that is coupled to the HBA entity via a communications path; identifying one or more other communications paths that span between the host device and the switch; detecting whether a redundancy policy would be violated if the HBA entity were to be turned off, the redundancy policy including at least one rule that specifies a minimum number of active paths that must be present between the host device and the switch at any given time; turning off the HBA entity in response to detecting that the redundancy policy would not be violated.

Abstract: There are provided systems and methods for configurable storage resource usage through a multi-phase data processing pipeline for data storage efficiency. A service provider may provide online digital computing services, such as electronic transaction processing, account, and the like through online platforms and digital content that may be loaded and served on webpages and through applications of the service provider. The service provider may process and serve data, which may be stored in various data storages and databases of the service provider. The service provider may configure and optimize storage resource usage by processing data through a multi-phased processing pipeline that analyzes the data for reductions in data storage size, duplications, and/or storage times to convert data into a more efficient structure. This may include converting the data to smaller data pieces, deduplicating the same or similar data, or limiting storage in resource intensive data stores.

Abstract: A controller includes at least one register configured to store a doorbell regarding a submission queue storing at least one request generated by a host, a first cache configured to store data corresponding to a first result of an operation performed in response to the at least one request, a second cache configured to store data corresponding to a second result of an operation performed in response to a read look ahead (RLA) request generated based on the at least one request, and a cache size manager configured to adjust a size of the second cache based on an update cycle of the doorbell and a change of a number of the at least one request corresponding to the doorbell.

Abstract: A block-based storage system hosts logical volumes that are implemented via multiple replicas of volume data stored on multiple resource hosts in different failure domains. Also, the block-based storage service allows multiple client computing devices to attach to a same given logical volume at the same time. In order to prevent unnecessary failovers, a primary node storing a primary replica is configured with a health check application programmatic interface (API) and a secondary node storing a secondary replica determines whether or not to initiate a failover based on the health of the primary replica.

Abstract: According to one embodiment, a magnetic disk device comprises a control part configured to execute a cache control based on accompanying information included in a command wherein the command includes a data write command to a disk or a data read command from the disk.

Abstract: Per channel thermal management techniques are described herein. In one example, a memory controller receives channel temperature information for one or more channels of one or more dies in the stack. The memory controller can then throttle commands at a channel-level based on the channel temperature information. In one example, row commands and column commands to a channel are throttled at independent rates based on the channel temperature information. In one example, a row command throttling rate or column command throttling rate is based on a ratio of alternating on-time to off time of throttling signals, or a window of time in which commands are enabled or disabled to a channel. In one example, the row and column command throttling signals can be staggered across channels or pseudo channels.

Abstract: Methods, systems, and devices for techniques for temperature-based access operations are described. A memory system may be configured to write temperature information to metadata during a write operation. The temperature information may indicate a temperature range within which the memory system may be during the write operation. The memory system may perform a corresponding read operation based on the temperature information written to the metadata and a temperature of the memory system during the read operation. A server may determine and indicate parameters associated with writing the temperature information to the metadata. Additionally, or alternatively, the server may indicate trim parameters for use in performing read operations based on temperature information received from the memory system. In some examples, the memory system may perform targeted refresh operations at locations based on temperature information stored associated with the locations.

Abstract: A storage device is provided. The storage device includes: a first non-volatile memory including a plurality of cell strings storing a plurality of logical address values and a plurality of physical address values; a second non-volatile memory including a plurality of memory cells corresponding to the plurality of physical address values; and a storage controller configured to read a first physical address value from the first non-volatile memory based on a first logical address value, and control a read operation on the second non-volatile memory based on the first physical address value. A first cell string among the plurality of cell strings includes: a plurality of first memory cells storing the first logical address value and respectively connected to word lines in a first group; and at least one second memory cell storing the first physical address value and connected to at least one word line in a second group.

Abstract: A method for managing application migration includes: inferring dependencies and connectivity among applications executing on a system; generating a target infrastructure node (IN) configuration template based on the inferred dependencies and connectivity; making a determination that a configuration of a target IN does not satisfy the template, in which an application is executing on an IN, in which the application is not executing on the target IN; in response to the determination: obtaining a weight for each inferred parameter in the template, in which the inferred parameters comprises the inferred dependencies and connectivity, in which the weight for each inferred parameter is configured by a user; executing, based on the weights, a model to obtain a deviation score for a second target IN; generating, based on the deviation score, a migration recommendation specifying the second target IN; and initiating a display of the migration recommendation to the user.

Abstract: Embodiments are described for a system that automatically determines the ideal backup target to send backup data. Temporary backup targets are automatically created to handle backups for mobile data assets. A backup agent sends incremental backups to any temporary backup target (TBT), which are later consolidated with primary backup target (PBT) data. To facilitate data backup to a TBT and restore operations from data located on a PBT or TBT, a Backup Location Catalog (BLC) is created for each asset to reside on the asset. A Change Record Catalog (CRC) is created for each TBT backup per asset and each CRC resides on the asset until the associated data is consolidated back to the PBT. Assets thus have access to all backups, including the data on the TBT(s) before that data is consolidated back to the PBT.

Abstract: The present disclosure generally relates to utilizing improved DL training models stored in non-volatile memory to optimize data transfer and storage. The proposed system would identify workloads of DNN training and occasionally check the difference rate between successive data transfers (representing successive training iterations of the model). Comparing the difference rate to given thresholds could indicate “recommendation-system” typical use case. In such a case the NAND operating system would apply systematic compression of the data by saving only the changed parameters between successive iteration cycles (“batches”). The host may indicate the checkpoint storage configuration of the training model (every iteration, every several iterations etc. . . . ) and other elements. The system may be efficiently utilized combining the NAND based DNN training interface, adding the checkpoint configuration information to the dedicated interface.

Abstract: Key data is processed using a hash table data structure. Control data storage locations have a write-availability indicated by a first write-availability state indicating that the location is available to be written to, and a second write-availability state indicating that the location is not available to be written to. A temporary label value is stored in a selected control data storage location to render the selected location and a corresponding key data storage location inactive for read-out. The write-availability of the control data storage location is changed to the second write-availability state in association with the storage of the processed label value in the selected location. A read-out label value is obtained and the temporary label value stored in the selected control data storage location is over-written with the obtained read-out label value, to render the selected control data storage location and corresponding key data storage location active for read-out.

Abstract: A software Redundant Array of Independent Disk (RAID)/management trusted storage-device-based communication system includes a chassis housing a software Redundant Array of Independent Disk (RAID) subsystem, a storage device that is coupled to the software RAID subsystem and that includes a storage device memory subsystem, and a management subsystem that is coupled to the storage device. The management subsystem authenticates the storage device to establish management subsystem/storage device trust between the management subsystem and the storage device and, in response, uses the storage device to establish management subsystem/software RAID subsystem trust between the management subsystem and the software RAID subsystem. In response to establishing the management subsystem/storage device trust and the management subsystem/software RAID subsystem trust, the management subsystem transmits communications with the software RAID subsystem via the storage device memory subsystem in the storage device.

Abstract: Systems, computer program products, and methods are described herein for automated data retrieval from an integrated circuit (IC). An example system receives an alert indicating a trigger event associated with the IC; extracts, using a scan island (e.g., a partition of the IC that is isolated for data retrieval), data from a plurality of scan chains and a plurality of random-access memories (RAMs) associated with the IC in response to receiving the alert; stores the data in an external non-volatile storage media; and reboots the IC upon storing the data in the external non-volatile storage media. In this way, embodiments of the present invention offer a scalable and secure method for real-time data extraction and processing in the event of an integrated circuit malfunction, improving diagnostics while ensuring cost-effectiveness and data security.

Abstract: A multi-platform data storage system that facilitates sharing of containers including one or more virtual storage resources. The multi-platform data storage system can, for example, include a storage interface configured to enable access to a plurality of storage platforms that use different storage access and/or management protocols, the plurality of storage platforms storing data objects in physical data storage; and a storage mobility and management layer providing virtual management of virtual storage resources corresponding to one or more data objects stored in the plurality of storage platforms, the storage mobility and management layer including at least a transfer module coupled to at least one network and configured to transfer at least one of the data objects. The transfer module can transfer the at least one of the data objects between the multi-platform data storage system and another data storage system.

Abstract: A system, method, and machine-readable storage medium for determining an amount of unique data in a distributed storage system are provided. In some embodiments, a combined efficiency set for a first data set stored in the distributed storage system, such as at a volume, may be generated. The first data set may include a first subset of data and a second subset of data in the distributed storage system. Additionally, a set of efficiency sets for the first subset of data may be generated. A set difference based on the combined efficiency set and the set of efficiency sets may be computed. An amount of memory used for storing unique data of the second subset of data may be estimated based on the set difference. The unique data may be present in the second subset of data but absent from the first subset of data.

Abstract: Adding a bypass module and a pattern detector module to a data path of a controller will increase the efficiency of both sanitize block erase audit and sanitize crypto erase audit operations. The sanitize crypto erase audit skips an end to end (E2E) protection module to provide decrypted data to a static random access memory (SRAM) buffer and ultimately a host device through a direct memory access (DMA) module. The sanitize block erase audit utilizes the pattern detector module to provide a known pattern to the SRAM buffer and host through the DMA module. The bypass module and pattern detector module feed into a multiplexer (Mux) prior to the SRAM buffer.