Abstract: A data bus inversion (DBI) circuit of a memory device includes a first processing component configured to generate first combination data by combining read data read from a memory cell region and previous data previously outputted from a data line, and generate second combination data by selectively inverting the first combination data depending on a result of comparing the first combination data and the previous data; and a second processing component configured to generate data to be outputted from the data line, by combining the second combination data and the previous data, wherein the second processing component generates bits of unnecessary bit positions in the data to be the same as bits of the unnecessary bit positions in the previous data.

Abstract: A plurality of computing devices are communicatively coupled to each other via a network, and each of the plurality of computing devices is operably coupled to one or more of a plurality of storage devices. The storage devices may be assigned to one of a plurality of memory tiers, and the data in a storage device may be reassigned to another storage device in a different memory tier.

Abstract: A transmission control method includes: determining transmission performance in a transmission line by using a parameter that determines a size of an opening of an eye pattern; and adjusting a transmission parameter that is a parameter having an influence on transmission quality in the transmission line on the basis of a result of the determination.

Abstract: Techniques for managing disks involve: determining, from multiple disks, a first disk set for providing redundant storage, the number of disks included in the first disk set being not less than a first threshold number that corresponds to the number of disks required to be included in a redundant array of independent disks; determining, based on the multiple disks, a candidate solution in which at least the first disk set is used to provide redundant storage; determining an unavailable capacity that the candidate solution will have; and determining, based on the unavailable capacity and the candidate solution, a target solution for providing the redundant storage. Accordingly, such techniques can promote efficient management of disks.

Abstract: Data synchronization includes receiving an update request from a client system for a first record set, wherein the update request includes search criteria used to initially determine the first record set and hash summaries of records of the first record set, and searching a data storage device for records matching the search criteria. The searching generates a second record set of records having hash summaries. Record identifiers of records of the second record set may be compared with record identifiers of the hash summaries of the first record set.

Abstract: Disclosed are systems and methods for efficient power management for storage devices. A method includes receiving a request to transition a flash memory to a first stand-by mode, wherein the flash memory comprises a plurality of dies. The method also includes causing one or more guard dies of the plurality of dies to transition to the first stand-by mode while causing one or more other dies of the plurality of dies to transition to a second stand-by mode, wherein the second stand-by mode is configured to consume less power than the first stand-by mode. The method also includes receiving an input/output (I/O) request for the flash memory. The method also includes causing the I/O request to be performed on the one or more guard dies that are in the first stand-by mode but not in the second stand-by mode.

Abstract: An embodiment includes mapping, responsive to receiving a request for a container image from a container host, the requested container image to a first computer memory on a registry server. The embodiment also includes exposing a window storing the mapped container image to the container host using a collective window-creation call with the container host. The embodiment also includes processing a Remote Direct Memory Access (RDMA) data transfer request to select a lock type for the window during the RDMA data transfer. The embodiment also includes imposing the selected lock type on the window during the RDMA data transfer. The embodiment also includes releasing the selected lock type from the window upon detecting completion of the RDMA data transfer.

Abstract: In one implementation, a method of sharing a physical device between multiple virtual machines is provided. The method includes receiving, from a first virtual machine, a request to access a physical device of a computing device. The method also includes assigning, by a processing device, the physical device to the first virtual machine in view of power state information associated with the physical device of the computing device, wherein the power state information is received from one or more other virtual machines of the computing device.

Abstract: Devices and techniques for NAND device mixed parity management are described herein. A first portion of data that corresponds to a first data segment and a second data segment—respectively defined with respect to a structure of a NAND device—are received. A parity value using the first portion of data and the second portion of data is computed and then stored for error correction operations.

Abstract: A method for execution by a dispersed storage network (DSN). The method begins by obtaining a data object for synchronized storage within a plurality of storage vaults, identifying a plurality of storage vaults, encoding the data object for each storage vault, initiating storage of data slices for each storage vault and interpreting received data slice information from at least some of the storage vaults to determine a number of storage vaults that have successfully stored the corresponding plurality of sets of encoded data slices and when the vault threshold number of storage vaults have not successfully stored the corresponding plurality of sets of encoded data slices within a synchronization timeframe, initiating a rollback process to abandon storage of the data object in the plurality of storage vaults and a store data response to indicate unsuccessful synchronized storage of the data object in the plurality of storage vaults.

Abstract: Techniques are described for reducing power consumption in a distributed data storage system using a hierarchy rule that is generated based on a spreading policy and a set of tolerable failures. A method may operate to distribute erasure-encoded data of a first data object across first and second portions of a distributed storage system using a hierarchy rule corresponding to a spreading policy based on a set of tolerable failures from which the first data object can be recovered. The method disables the first portion of the distributed storage system that includes a first portion of the erasure-encoded data. The first portion of the distributed storage system is determined according to the spreading policy and the hierarchy rule identifies the set of tolerable failures.

Abstract: Systems and methods are disclosed for detecting shingled overwrite errors. When a read error is encountered when reading from shingled recording tracks, a processor may determine whether the read error is an error caused by shingled overwriting. The processor may determine whether the read error is caused by shingled overwriting by determining read signal quality of one or more sectors preceding the read error, such as based on a bit error count or bit error ratio (BER), and comparing the read signal quality to a threshold value. The processor may determine that the read error is caused by shingled overwriting when the read signal quality value is lower than the threshold.

Abstract: A method, a system, and a computer program product for execution master data substitution. One or more first data objects in a master data storage are determined for replacement. One or more second data objects are identified for replacing the first data objects for storage in the master data storage. Replacement of the first data objects with the second data objects is performed in accordance with one or more data object requirements. Replacement of the first data objects by the second data objects is executed in accordance with the one or more data object requirements. A resulting replacement data set is generated and stored.

Abstract: In response to receiving data to be stored in a storage system that includes a plurality of N drives, a method may include storing a first quantity of the data in a first N portions across a first half of the N drives; storing a second quantity of the data in a second N portions across a second half of the N drives; determining first parities to be stored on a first parity drive; determining second parities and storing them on a second parity drive; and calculating third parities based on both the first quantity of the data and the second quantity of the data, wherein the third parities are calculated in a diagonal fashion based on distinct elements of the first N portions and distinct elements of the second N portions, and storing the third parities on a third parity drive.

Abstract: In some examples, a system includes a Fibre Channel (FC) interface to communicate over an FC network, and a network stack including a network layer and a transport layer. Machine-readable instructions are executable to produce a command packet including a payload including data for transmission to another system, the payload further including headers for the network layer and the transport layer, where the command packet is according to a storage interface protocol. The FC interface is to communicate the command packet over the FC network.

Abstract: A method for tracking a progress of data copying for a live migration includes transferring, by a storage controller, a first data structure to a live migration server, the first data structure including a first status identifier indicating a location of a source data to be copied from a source storage to a target storage, and selectively generating or selectively clearing, by the storage controller, a second status identifier in or from a second data structure, based on a first current copying location of the live migration server, the second status identifier indicating a location of a first user data write to the source storage.

Abstract: A system and method for satisfying Quality of Service (QoS) attributes for a stream using a storage device with multi-stream capability is described. The storage device may include memory to store data. A host interface may receive requests, some of which may be associated with a stream. A host interface layer may schedule the requests in a manner that may satisfy the QoS attribute for the stream.

Abstract: A stretched volume may be configured from N volumes of N data storage systems configured as a cluster. N may be an integer greater than two. Each of the N volumes may be included in a different one of the N data storage systems. The N volumes may be exposed to a host as a logical volume having a unique identifier over a plurality of paths from the N data storage systems. The N volumes may be configured for multidirectional synchronous replication. At a first system of the cluster, a write operation may be received that writes to a target logical address of the stretched volume. Servicing the first write may include synchronously replicating the first write to every other one of the N data storage systems of the cluster. Also described are techniques for handling lock contention and avoiding deadlock in connection with processing writes to the stretched volume.

Abstract: The described technology is generally directed towards an input/output (I/O) load balancer of a data storage system that detects an I/O overloaded (“hot”) storage unit and logically moves its hot data to a non-overloaded (“cold”) storage unit. Threshold load levels can be used to determine hot and cold storage units. In one implementation, new writes to the hot storage unit are prevented while its hot data is logically moved to a cold storage unit. To avoid reads from the hot storage unit, the hot data can be recreated from redundant data obtained via a recovery path. To avoid a capacity imbalance, once enough hot data has been moved so that the (formerly) hot storage device is no longer considered hot, cold data from the cold storage device can be written to the formerly hot storage device. New data writes to the formerly hot storage device can then resume.

Abstract: The invention relates to a method, a non-transitory computer program product, and an apparatus for managing data storage. The method performed by a flash controller includes: obtaining information indicating a subregion to be activated, where the subregion is associated with a logical block address (LBA) range; triggering a garbage collection (GC) process being performed in background to migrate user data of all the or a portion of the LBA range associated with the subregion to continuous physical addresses in a flash device; and updating content of a plurality of entries associated with the subregion according to migration results, where each entry includes information indicating which physical address that user data of a corresponding logical address is physically stored in the flash device.

Abstract: Flexible deprovisioning of distributed storage is disclosed. For example, an orchestrator executes on a processor to measure a current storage demand factor based on a current count of service guests and a storage capacity of a plurality of storage nodes. A projected storage demand factor is calculated by (i) adjusting the current count of service guests with a timing factor resulting in a projected count, and (ii) combining the projected count with a storage class associated with the service guests. The orchestrator determines that the projected storage demand factor is lower than the current storage demand factor, and in response requests termination of a first storage node of the plurality of storage nodes based on the first storage node lacking an active communication session with the service guests. Cancel termination of the first storage node based on an association between the first storage node and a second storage node.

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: A cloud tethering subsystem is configured to ship snapshots of an application production storage group to a cloud repository. Dynamic storage group resizing operations are allowed on the application production storage group after creation of a snapshot and before transmission of the snapshot to the cloud, or while the snapshot is accessing data of the application production storage group in connection with shipping the snapshot to the cloud. Example dynamic storage group resizing operations include adding one or more volumes to the application production storage group, removing one or more volumes from the application production storage group, and resizing one or more of the volumes of the application production storage group. The cloud tethering subsystem maintains information about the size of the snapshot at the time of creation and uses the snapshot size to prevent dynamic storage group resizing operations from interfering with cloud snapshot shipping operations.

Abstract: Embodiments of the present disclosure relate to a system and an operating method thereof. According to embodiments of the present disclosure, a memory system may transmit a first type response indicating that first data has been cached in a cache to the host when receiving a first command requesting to write the first data from the host, and may transmit a second type response indicating success or failure of an operation of storing the first data in the memory device to the host after transmitting the first type response to the host. Further, the host may delete the first data from a write buffer after the operation of storing the first data in the memory device succeeds.

Abstract: A one-time programmable (OTP) memory has a plurality of pages. A predefined section of each page is configured to store error policy bits. When an indicator in a first predefined location has a first value, the page is configured to store data with error correction code (ECC) bits, and when the indicator has a second value, at least a portion of the page is configured to store data with redundancy. Address translation circuitry is configured to, in response to receiving an access address, use a second predefined location of an accessed page of the plurality of pages accessed by the access address to determine a physical address in the accessed page which corresponds to the access address.

Abstract: The present disclosure generally relates to methods of operating storage devices. The storage device comprises a controller and a storage unit divided into a plurality of streams. The storage unit comprises a plurality of dies, where each die comprises two planes. One erase block from each plane of a die is selected for stream formation. Each erase block comprises a plurality of wordlines. A stream comprises one or two dies dedicated to storing parity data and a plurality of dies dedicated to storing user data. The stream further comprises space devoted for controller metadata. The storage device restricts a host device to send write commands in a minimum write size to increase programming efficiency. The minimum write size equals one wordline from one erase block from each plane of each die in the stream dedicated to storing user data minus the space dedicated to metadata.

Abstract: Temporarily limiting access to a storage device, including: determining that a storage device of a plurality of storage devices in a storage system is operating outside of a defined performance range; determining that the storage device operating outside of the defined performance range may be caused by a rehabilitative action performed on the storage device; and modifying a storage operation issuance policy for one or more storage devices of the plurality of storage devices until a determination that the storage device is operating within the defined performance range.

Abstract: A data service layer running on a storage director node generates a request to destage host data from a plurality of cache slots in a single back-end track. The destage request includes pointers to addresses of the cache slots and indicates an order in which the host application data in the cache slots is to be included in the back-end track. A back-end redundant array of independent drives (RAID) subsystem running on a drive adapter is responsive to the request to calculate parity information using the host application data in the cache slots. The back-end RAID subsystem assembles the single back-end track comprising the host application data from the plurality of cache slots of the request, and destages the single back-end track to a non-volatile drive in a single back-end input-output (IO) operation.

Abstract: A storage device is provided including a memory controller having a neural processing unit (NPU); a first nonvolatile memory (NVM) connected to the memory controller through a first channel; and a second NVM connected to the memory controller through a second channel. The first NVM stores first weight data for the NPU and the second stores second weight data for the NPU. The memory controller is configured to determine one of the first and second channels that is less frequently accessed upon receiving an inference request from the neural processor, and access a corresponding one of the first weight data and the second weight data using the determined one channel.

Abstract: Methods, systems, and devices for performance control for a memory sub-system are described. A memory sub-system can monitor a backend for writing data to a memory device. The memory sub-system can determine that the bandwidth of the backend satisfies one or more performance criteria that are based on performance between the memory sub-system and a host system. In some embodiments, the memory sub-system can allocate a quantity of slots of a buffer to a frontend of the memory sub-system based on determining that the bandwidth of the backend satisfies the one or more performance criteria. Slots of the buffer can be configured to receive data from the frontend for writing to the memory device by the backend.

Abstract: Metadata of a storage object is managed. An example method for managing metadata of a storage object comprises: in response to receiving a request to access metadata of a storage object, obtaining a first identifier of the storage object from the request; determining, based on the first identifier, a second identifier of a page where the metadata is located, an address of the page and the second identifier being stored in association in an entry of a page table distributed among a plurality of storage devices with different access speeds; determining, from the plurality of storage devices, a storage device storing the entry; and obtaining the address of the page by accessing the entry from the storage device, so as to access the metadata from the page.

Abstract: A storage system comprises stripes, extents comprised in one stripe among the stripes residing on storage devices in the storage system, respectively. A failed stripe is determined among the stripes, the failed stripe comprising a group of failed extents residing on a group of failed storage devices, respectively, a number of failed storage devices in the group being less than or equal to parity width of the storage system. Distribution of the group of failed extents in the failed stripe is obtained. A rebuild parameter for rebuilding data in the failed stripe is generated based on the obtained distribution. The generated rebuild parameter is stored for rebuilding the storage system. Accordingly, a rebuild parameter generated for one failed stripe is reused for other failed stripe with the same distribution. The performance of rebuild operations may be improved, and time of rebuild operations may be reduced.

Abstract: A method, computer program product, and computing system for receiving a plurality of discrete write requests on a first computing device until the end of a consolidation window; combining the plurality of discrete write requests received into a consolidated write request; and transmitting the consolidated write request to a second computing device.

Abstract: A RAID storage-device-assisted parity data update system includes a first RAID primary data drive that DMA's second primary data from a host system, and XOR's it with first primary data to produce first interim parity data for a first data stripe. A second RAID primary data drive DMA's fourth primary data from the host system, and XOR's it with third primary data to produce second interim parity data for a second data stripe. A first RAID parity data drive DMAs the first interim parity data and XOR's it with first parity data to produce second parity data for the first data stripe that overwrites the first parity data. A second RAID parity data drive DMA's the second interim parity data and XOR's it with third parity data to produce fourth parity data for the second data stripe that overwrites the third parity data.

Abstract: A data storage system includes a host configured to provide a read request; a plurality of storage devices constituting a redundant array of independent disks (RAID); and a RAID controller configured to a plurality of read commands in response to the read request, the read commands being provided to the plurality of storage devices according to a RAID setting, wherein one data storage device of the plurality of data storage devices includes a nonvolatile memory device; an error handling information storage circuit to store error handling information; and an error detection and correction circuit configured to detect an error in data output from the nonvolatile memory device according to a read command and to selectively correct the error according to the error handling information.

Abstract: Techniques are disclosed to safely and performantly store data in a distributed graph database. In various embodiments, a combination of a replication protocol for data redundancy with a chain-commit protocol is used to ensure a safe ordering of concurrent updates across servers. The resulting protocol allows a distributed graph database to simultaneously uphold ACID properties and a useful degree of scalability through concurrent processing of updates in the typical case, and serialization of updates only where data integrity would otherwise be at risk.

Abstract: Embodiments of the present disclosure relate to a memory system, a memory controller, and an operation method thereof, in which a data storage space of a memory device is divided into N namespaces, and in which each namespace is controlled so as to share a super memory block with other namespaces or to occupy the same exclusively, thereby minimizing an increase in the time taken to format each of a plurality of namespaces while efficiently storing data in a plurality of namespaces.

Abstract: A non-transitory computer-readable medium is provided. The medium comprises a set of instructions, which, when executed by a processing system associated with a database or data warehouse, causes the processing system to retrieve data from a data source in accordance with a mapping between a first set of partitions and a second set of partitions, the first set of partitions being associated with the data source and the second set of partitions being associated with the database. The set of instructions, when executed by the processing system, further causes the processing system to load the retrieved data into the database. Retrieving the data and loading the retrieved data comprise a single logical unit of work. A database system and a method executed by a processing system associated with a database are also provided.

Abstract: Risk assessment for a computing system being developed can include receiving a user input specifying a proposed topology for a computing system. The proposed topology is defined by a first software product to be used and an architecture having a first non-functional component. A problem knowledge repository is searched using a processor for records of problems correlated with the proposed topology. A level of risk in implementing the computing system using the proposed topology is calculated according to the searching using the processor.

Abstract: A storage control apparatus comprising: a memory; and a processor coupled to the memory and configured to: receive a release request for a first storage area in a virtual storage area, release, among unit storage areas included in a physical storage area, one or more first unit storage areas allocated to the first storage area from the first storage area, execute overwrite processing of writing 0 to each of the first unit storage areas at a timing asynchronous with the release of the first unit storage areas, and when a write request is received to write data to the virtual storage area, execute write processing in which an unallocated unit storage area among the unit storage areas included in the physical storage area is allocated to a write destination area for the write data in the virtual storage area.

Abstract: A subset of drives with protection groups that have D data members and P parity members is created with (D+P+1) drives each having (D+P) partitions. One of the protection groups is used for spare capacity. (D+P) sequentially numbered protection groups are created by distributing protection group members such that members of protection group (X+Y) modulo (D+P+1) are located on the partition at drive X of partition Y. Alternatively, members of protection group (X?Y) modulo (D+P+1) are located on the partition at drive X of partition Y. New drives are added in single drive increments. When a new drive is added the first (D+P) protection group members of the lowest numbered unrotated partition of the (D+P) lowest numbered drives are rotated onto the new drive. Members are rotated in ascending order by drive to locations in ascending order by partition. A new protection group is created in the partitions made available due to rotation.

Abstract: Data associated with storage media utilized by one or more storage systems is received. The data is provided as an input to a machine learning model executed by a processing device. The machine learning model identifies one or more deterministic characteristics from the data. The one or more deterministic characteristics associated with the storage media are received from the machine learning model. A data structure comprising the one or more deterministic characteristics is generated for use in a telemetry process to qualify types of storage media.

Abstract: Risk assessment for a computing system being developed can include receiving a user input specifying a proposed topology for a computing system. The proposed topology is defined by a first software product to be used and an architecture having a first non-functional component. A problem knowledge repository is searched using a processor for records of problems correlated with the proposed topology. A level of risk in implementing the computing system using the proposed topology is calculated according to the searching using the processor.

Abstract: A data storage system includes multiple head nodes and multiple data storage sleds mounted in a rack. For a particular volume or volume partition one of the head nodes is designated as a primary head node for the volume or volume partition. The primary head node is configured to store data for the volume in a data storage of the primary head node and cause the data to be replicated to a secondary head node. The primary head node is also configured to cause the data for the volume to be stored in a plurality of respective mass storage devices each in different ones of the plurality of data storage sleds of the data storage system.

Abstract: Modifying storage distribution in a storage system that includes one or more storage devices, including: detecting, for a storage device among the one or more storage devices, that a storage capacity of the storage device is different from a storage capacity of another storage device of the one or more storage devices, and responsive to detecting that the storage capacity for the storage device is different from the storage capacity of the other storage devices of the one or more storage devices, modifying a distribution of shards of data for a data stripe among the one or more storage devices.

Abstract: Techniques and solutions are described for determining a set of elements of a second set that may correspond to a given element of a first set of elements. The elements can be, in specific examples, components of a database system, such as tables (or entities), attributes, or records. Significance metric values are calculated for elements in the first and second sets. The significance metric values can be a number of records in an entity or a number of read or write access operations for an entity or for a record of an entity. A significance metric value for the given element can be used at least in part to select elements of the second set as potential match candidates, based at least in part on significance metric values for elements of the second set. Selecting elements can include selecting elements based on a window of elements of the second set or a range of significance metric values.

Abstract: A plurality of computing devices are communicatively coupled to each other via a network, and each of the plurality of computing devices is operably coupled to one or more of a plurality of storage devices. The computing devices may take snapshots to store points in time coherently for a distributed storage system.

Abstract: Techniques to control a storage system involve: determining whether available power capable of being supplied by a supplying apparatus of the storage system is less than power required by the storage system; and in response to a determination that the available power is less than the power required by the storage system, adjusting an operation parameter of the storage system based on the available power so as to match the power required by the storage system with the available power. In this way, the performance of the storage system can be at a higher level while the performance of the storage system can remain stable in a case where power of a processor is limited.

Abstract: Techniques involve detecting whether a transaction of modifying configuration data of a storage system is initiated, the configuration data being stored in a database and a buffered version being stored in memory independent of the database. The techniques further involve in accordance with detection that the transaction is initiated, building a data buffer to buffer a section to be modified, the data buffer being mapped to a storage sector of the memory in which the section is expected to be stored. The techniques further involve determining whether the transaction successfully completed and in accordance with a determination that the transaction fails to successfully complete, releasing the data buffer and aborting the transaction, without modifying the buffered version. Accordingly, the configuration data in the memory remains as the previous version and are not modified before the transaction is successfully completed, which makes it possible to abort the transaction.

Abstract: A switch according to an embodiment includes a first PCIe interface that can be connected to a host on the basis of a PCIe standard. In addition, the switch includes a plurality of second PCIe interfaces that can be connected to a plurality of storage devices, respectively, on the basis of the PCIe standard. The switch further includes a control unit that distributes an access request which is comply with an NVMe standard and is transmitted from the host to any one of the plurality of second PCIe interfaces. The distribution includes a process of constructing an NVMe command of the access request and a process of constructing a data transmission descriptor list of the access request.