Techniques involve: determining, according to a determination that a performance level of a target storage unit is lower than a threshold level, whether idle disk slices that can be used for reconstructing malfunctioning disk slices in the target storage unit exist in a slice pool; determining a priority of the target storage unit according to a determination that the idle disk slices do not exist; and selecting replacing disk slices for reconstructing the malfunctioning disk slices from available storage units based at least in part on the priority, wherein the available storage units have performance levels not lower than the threshold level. In this way, data loss due to the off-line of storage units is prevented; and meanwhile, the performance of the entire storage system can be globally stabilized.

Verifying that data has been correctly replicated to a replication target, including: replicating a dataset stored at a first computing system to a second computing system; and determining, based at least on a comparison of a first hash and a second hash, validity of the dataset stored at the second computing system, wherein the first hash is generated by applying a hash function to a copy of the dataset that is stored at the first computing system and the second hash is generated by applying the hash function to a copy of the dataset that is stored at the second computing system.

Embodiments for accessing data are provided. A method of accessing data comprises: receiving a request to access first data in a storage device, at least a part of data in the storage device being cached in a cache, and index information of the at least a part of data being recorded in an index structure associated with the cache; querying the index structure to determine whether the first data is cached in the cache; and accessing the first data based on a result of the query. Embodiments of the present disclosure can improve data accessing efficiency while saving memory consumption.

A computer-implemented method according to one embodiment includes receiving, by a target system from a source system, a description of a set of data updates that are to be written to the target system. For each given portion of data of the target system that is to be rewritten during performance of the set of data updates, forward lookup is performed on the target system for determining a physical storage address of the given portion of data. The method further includes marking each of the determined physical storage addresses of the portions of data of the target system in a copy of a reverse lookup table of the target system. The marked-up reverse lookup table is used for determining an ordering in which the performance of the set of data updates would result in a least amount of garbage collection being performed while performing the set of data updates.

A storage system for sensor data includes a plurality of storage modules coupled together via a network fabric, each storage module including a plurality of form factor non-volatile memory (NVMe) storage units. The system also includes an integrated processor coupled to the network fabric and storage modules. The integrated processor is configured for control functions and data processing. The integrated processor configuration includes instructions such that the plurality of storage devices receive data via a data centric publish subscribe (DCPS) notification followed by a remote direct memory access (RDMA) transfer.

Methods, systems, and devices related to a memory system or scheme that includes a first memory device configured for low-energy access operations and a second memory device configured for storing high-density information and operations of the same are described. The memory system may include an array configured for high-density information and may interface with a host via a controller and a cache or another array of a relatively fast memory type. The memory system may support signals communicated according to one or several modulation schemes, including a modulation scheme or schemes that employ two, three, or more voltage levels (e.g., NRZ, PAM4). The memory system may include, e.g., separate channels configured to communicate using different modulation schemes between a host and between memory arrays or memory types within the memory system.

Example implementations relate to managing ownership transfer of a file system instance in a virtualized distributed storage system. The virtualized distributed storage system includes a first node having a first virtual controller that acts as an owner of a file system instance in a distributed storage, and a second node having a second virtual controller coupled to the first node over a network. A failure condition associated with a first node is detected. Further, in response to detection of the failure condition, an ownership of the file system instance may be transferred from the first virtual controller to the second virtual controller no later than an IP address switchover of the first virtual controller.

Performing replicated data integrity, including: generating, at a first computer system, a local hash of a local dataset; replicating the local dataset; receiving, at the first computer system from a second computer system, a remote hash of a remote dataset generated from the local dataset replicated from the first computer system; and determining, based at least on a comparison of the local hash of the local dataset with the remote hash of the remote dataset, validity of the remote dataset generated from the local dataset replicated from the first computer system.

A storage system includes a first storage device that includes a first memory and a first processor coupled to the first memory; and a second storage device that includes a second memory and a second processor coupled to the second memory, wherein the first processor is configured to: when migrating data in object units, generate dummy data that corresponds to the data instead of the data in object units, and transmit management information used to manage an object and the dummy data to the second storage device, and the second processor is configured to: store the management information in a storage unit in association with the object, and discard the dummy data.

A storage system and method for user-defined data archiving are provided. In one embodiment, the method comprises: receiving a write command from a host; determining whether the storage system received an indicator from the host indicating that data of the write command is archive data; in response to determining that the storage system received the indicator, storing the data in the multi-level memory cells; and in response to determining that the storage system did not receive the indicator, storing the data in the single-level memory cells. Other embodiments are provided.