159 results about "Wear leveling" patented technology

The invention relates to the technical field of storage, in particular to an SSD wear leveling method and device based on dynamic data migration and a medium. The method comprises the following steps: monitoring access frequency, recording read-write times of a logic block in real time, and identifying hotspot data; tracking a wear state, counting the erasure times of the physical flash memory block, and evaluating the wear degree of the physical flash memory block; data migration decision: determining whether to migrate data based on the access frequency and the wear frequency; preferentially migrating data with high access frequency and high wear degree according to access frequency and wear program sorting; and data migration execution: migrating the hotspot data from the high-wear area to the low-wear area, and updating the mapping relation. According to the method, the data storage position can be intelligently adjusted according to the real-time data access characteristics and the abrasion state, and therefore the service life of the SSD is more efficiently prolonged.

The invention relates to the technical field of embedded data storage, and discloses a method and a system for prolonging the service life of a FLASH simulation EEPROM (Electrically Erasable Programmable Read-Only Memory) in a single chip microcomputer, and the method comprises the following steps: firstly, initializing the FLASH, dividing the FLASH into a main data area, a mapping table area, a backup area and a transaction log area, selecting a physical block through a dynamic wear leveling algorithm when data is written, and writing the data into a database; the method comprises the following steps of: starting a backup area or a transaction log area, safely updating a mapping table by using a transaction mechanism, performing cyclic redundancy check when reading data, if the cyclic redundancy check fails, starting cascade recovery from the backup area or the transaction log area, and finally, updating a transaction log to record operation so as to form a closed-loop management process. According to the invention, through a set of dynamic wear leveling and data classification management mechanism, global and uniform distribution of the write load in the storage array is realized, the physical block with the least erasing times is selected during writing, the access frequency of the data can be identified, and cold data which is not changed frequently can be actively migrated.

The invention relates to a data processing method and system of an NAND FLASH storage array, computer equipment and a storage medium. The method comprises the following steps: receiving a data writing or reading instruction; and analyzing the instruction through the system-on-chip, and distributing the data to a target module in the plurality of NAND FLASH modules connected in parallel according to a preset strategy. And writing the data into the target module or reading the data from the target module through the control and communication line. And executing data management operation through the system-on-chip, specifically, writing data into different NAND FLASH modules in a dispersed manner by adopting a dynamic wear leveling algorithm so as to balance the erasing times of each module. And detecting and marking bad blocks in the NAND FLASH module in real time, and avoiding the bad blocks in calling operation after data storage. By the adoption of the method, the storage performance, reliability and expandability of satellite-borne storage can be comprehensively improved, and the method is suitable for task scenes with high reliability requirements.

The invention belongs to the technical field of storage media, and particularly relates to a storage medium abrasion balancing system based on cold and hot data perception, which comprises a cold and hot data perception module used for monitoring the access frequency and the update time of data in real time so as to judge the cold and hot degree of the data, and establishing a heat table, recording a heat value of each data block or data page; and the data feature prediction module is used for predicting features of a future heat change trend and a data volume increase trend of the data by utilizing a machine learning algorithm according to historical data access and update records. According to the method, the hot and cold data sensing module is used for monitoring data access and updating conditions in real time to calculate a hot value, and the storage medium management module is combined to preferentially store hot data into blocks with less erasing times and store cold data into blocks with more erasing times. Therefore, the erasing times of the blocks of the storage medium tend to be balanced, and excessive abrasion of individual blocks is avoided.

In some implementations, a memory device may receive, from a host device, a write command instructing the memory device to write host data to a portion of a memory associated with a logical address. The memory device may determine a physical location of the memory associated with the logical address by using a wear leveling algorithm to map the logical address to the physical location of the memory, wherein the portion of the memory is associated with a wear leveling pool, and wherein the wear leveling algorithm maps the logical address to a portion of the wear leveling pool based on a randomized parameter. The memory device may write the host data to the physical location of the memory.

The invention relates to the technical field of data storage optimization, and discloses a solid state disk wear leveling global optimization method and system based on multi-granularity data features. The solid state disk wear leveling global optimization method specifically comprises the following steps that S101, lightweight data feature monitoring points with blocks, units and chips as basic granularity are deployed in a solid state disk controller, and original multi-dimensional data features related to wear are continuously collected and quantified in real time, all collected multi-dimensional data features are converted into dimensionless feature scores which can be transversely compared through normalization processing. According to the method, multi-dimensional feature fusion and normalization processing of three-level granularity of blocks, units and chips of a fixed hard disk are utilized, a prediction model based on a time sequence is combined, a dynamic risk thermodynamic diagram covering the whole disk is generated, a system can accurately position current and future potential abrasion hot spots, and the system reliability is improved. And passive equalization operation is converted into active risk prevention.

The invention discloses an SSD B + tree indexing method and system based on wear leveling, and relates to the technical field of database indexing structure optimizing.The method comprises the steps that B + tree logic nodes and SSD physical addresses are decoupled, and a dynamic node mapping table is introduced; replacing local updating with additional updating, and writing the new version of the node into a new position of the SSD; when a write-in address is allocated to the node, an allocation strategy considering a block wear state is adopted, and write operation is guided to an area with relatively light wear; during garbage collection, high-wear blocks are preferentially treated to integrate wear. According to the method, the problems of writing hot spots and unbalanced abrasion of the B + tree on the SSD are effectively solved on the database software level, the service life of the SSD can be remarkably prolonged while the high performance of the B + tree is kept, and the method has very high universality and practical value.

Techniques are directed to wear leveling. Such techniques involve: determining, at least based on the type information of each redundant array of independent disks (RAID) group in a plurality of RAID groups, the write loss of each of the RAID groups. Such techniques further involve: determining the wear status of each of the RAID groups according to the status information and write loss of each of the RAID groups. Such techniques further involve: transferring at least a portion of data and / or a write task of a first RAID group to a second RAID group based on the write loss and the wear status of each of the RAID groups. With such wear leveling techniques, wear caused by write tasks can be evenly distributed among the RAID groups, so that the degree of wear among the RAID groups is more leveled.

The invention relates to the technical field of storage garbage recycling algorithms, in particular to a garbage recycling system based on a genetic algorithm, which comprises an environment sensing module, a dynamic excitation pool module, a gene coding module, a genetic operation module, a strategy evaluation module, a cold and hot data verification bridge module, a wear leveling compensator and an iterative deployment module. The environment sensing module is used for scene feature extraction and load mode classification. Through dynamic parameter optimization and a multi-scene adaptation mechanism, an optimal strategy parameter combination is automatically searched by utilizing a genetic algorithm, and controllable disturbance is introduced by dynamically adjusting sample weight and polynomial variation in combination with an entropy weight method, so that multi-target balance of write amplification, block efficiency and wear balance is realized; meanwhile, through a cold and hot data verification bridge and a wear leveling compensator module, the data state transition trend is predicted, parameter deviation is actively corrected, high robustness and long-term stability can still be kept in a complex load scene, and finally a closed-loop self-adaptive garbage collection strategy generation system is formed.

Systems, methods and apparatus of intelligent wear-leveling with reduced write-amplification for data storage devices configured on autonomous vehicles. For example, a data storage device of a vehicle includes: storage media components; a controller configured to store data into and retrieve data from the storage media components according to commands received in the data storage device; an address map configured to map between: logical addresses specified in the commands received in the data storage device, and physical addresses of memory cells in the storage media components; and an artificial neural network configured to receive, as input and as a function of time, operating parameters indicative a data access pattern, and generate, based on the input, a prediction to determine an optimized operation for wear leveling among memory cells in the data storage device. The controller is configured to perform the optimized operation for wear leveling based on the prediction.

A technique is directed to managing wear leveling between storage devices. The technique includes obtaining a wear level metric of a candidate storage extent that includes storage from multiple storage devices. The technique further includes performing an assessment operation that provides an indication that the candidate storage extent satisfies an access criterion. The access criterion is based on the wear level metric. The technique further includes, in response to the assessment operation providing the indication that the candidate storage extent satisfies the access criterion, performing a set of access operations that accesses the candidate storage extent.

A container system facilitates selective migrations of data from high-wear inducing data devices to spare data devices to promote SSD wear levelling. Storage capacity is configured into same-size cells with each container having the same number of cells as RAID width W. The cells are distributed over W SSDs. The containers are subdivided into equal-size data devices, each distributed over the same set of W SSDs as its associated container. Candidate migration source-target pairs are selected using heuristics guided by a prediction model that correlates disk wear rate with total writes of existing workloads. Wear rate predictions are computed using a weighted sum of write rates of all data devices on a disk. Wear rate predictions for candidate migration pairs are computed inclusive of additional wear caused by data migration to select a migration plan.

The invention relates to the technical field of intelligent chips, in particular to an NAND wear leveling method based on integrated circuit ECC (error correction code) and read delay, which comprises the following steps: acquiring read delay data and error correction code usage amount of a three-layer unit page of a target block in an NAND flash memory chip; on the basis of the read delay increment and the error correction code increment of the middle-layer page, the health index of the target block is calculated by combining the read delay difference value of the middle-layer page and the lower-layer page, the target block is divided into a plurality of health levels, and logic blocks of different health levels are mapped to different physical planes of the NAND flash memory chip; synchronously executing data migration and erasure operations of the plurality of blocks to be migrated by utilizing the parallel erasure capability of the multi-plane architecture for the target block of which the health level is degraded to a preset threshold value; and monitoring the deviation degree between the current read delay and the specification read delay in real time, and selecting the error correction strength grade of the error correction code according to the deviation degree.

The invention relates to a solid state disk dynamic wear balancing method and system based on data popularity, and the method comprises the steps: tracking the access characteristics of each data page in a solid state disk through a page-level counter, and enabling the access characteristics to comprise the write operation frequency, the modification period and the survival time; the data pages are dynamically divided into high-heat data, medium-heat data or cold data based on a preset threshold value, and corresponding heat layering labels are marked; collecting accumulated writing times and I / O request queue length of each channel of the solid state disk in real time, and calculating wear imbalance degree and load imbalance degree; performing data exchange according to a preset exchange mode priority based on the popularity hierarchical label, the wear imbalance degree and the load imbalance degree; and updating the logic mapping table and the channel state parameters, carrying out statistics on the balance income and the system overhead, and dynamically correcting the tolerance coefficient based on the current load type according to the income-overhead ratio.

The invention provides a solid state disk wear leveling method and device, electronic equipment and a storage medium, and relates to the technical field of computers. The method comprises the steps of determining a target recovery group corresponding to target data in a solid state disk SSD based on type characteristics of the target data; based on the cold and hot characteristics of the target data, writing the target data into a target data block corresponding to the cold and hot characteristics in the target recovery group; in response to the fact that the effective data proportion in the recycling unit is lower than a first threshold value, executing a first garbage recycling strategy; the first garbage recycling strategy recycles invalid data in the recycling group corresponding to the recycling unit; in response to the fact that the effective data proportion in the recycling unit is not lower than the first threshold value, executing a second garbage recycling strategy; the second garbage recycling strategy is used for recycling data in different data blocks in the recycling unit based on the wear degrees of the different data blocks in the recycling unit. Therefore, the response speed and recovery efficiency of the SSD can be improved, and the service life of the SSD is prolonged.

The invention relates to the technical field of solid state disks, in particular to a solid state disk intelligent read-write optimization method based on artificial intelligence, comprising an intelligent read-write scheduler, adaptive wear leveling, read-write performance optimization, fault prediction and health management, and safety protection and efficiency improvement. The use mode is analyzed through a machine learning algorithm, the cache strategy is optimized, fault prediction is carried out, the read-write performance and the data safety are improved, the read-write speed, stability and safety of the solid state disk can be remarkably improved, the requirements of diversified application scenes are met, faults are predicted, and the phenomenon that the solid state disk breaks down is avoided; through intelligent read-write optimization driven by artificial intelligence, the SSD can realize collaborative optimization of performance, service life and energy efficiency under a complex load, a high-reliability storage solution is provided for scenes such as a data center and edge computing, and the performance, service life and energy efficiency of the SSD can be improved by combining machine learning, reinforcement learning and a hardware collaborative technology.

The invention discloses a flash memory management method and a flash memory management device capable of balancing wear degree, and relates to the technical field of storage. According to the flash memory management method capable of balancing wear degree, blocks of different wear degree hierarchies are forced to be uniformly mixed and distributed to each region based on a hierarchical polling partitioning strategy, so that the wear degree is balanced; the abrasion degrees between the areas and in the areas are effectively promoted to approach to an equilibrium state, and the situation that local blocks fail in advance due to excessive abrasion is avoided; a double-layer erasure cycle sequence table is established for erasure operation of the flash memory, ascending sorting is performed according to the actual wear degree of each block, and the blocks with low wear degree are erased preferentially, so that global wear balance of the flash memory is synchronously realized while the complexity and the frequency of sorting calculation are reduced, the service life of the flash memory can be remarkably prolonged, and the service life of the flash memory is prolonged. And the calculation load and resource consumption of the system can be greatly reduced.

Techniques for wear leveling involve identifying a detected disk as a target disk in response to detecting the disk with a degree of wear greater than a first threshold in a plurality of disks of a storage array. Such techniques further involve determining, in response to the number of the target disks being greater than or equal to a second threshold, an updated weight for disk wear based on the degree of wear of the target disk and an impact attenuation factor associated with the degree of wear. Such techniques further involve performing, based on the updated weight for the disk wear, wear leveling for an input / output (IO) request on the plurality of disks in the storage array. In this way, it can effectively avoid deterioration of the storage performance caused by end of life (EOL) of too many disks at the same time point or cycle.

This disclosure provides for host-controller cooperation in managing NAND flash memory. The controller maintains information for each erase unit which tracks memory usage. This information assists the host in making decisions about specific operations, for example, initiating garbage collection, space reclamation, wear leveling or other operations. For example, metadata can be provided to the host identifying whether each page of an erase unit has been released, and the host can specifically then command each of consolidation and erase using direct addressing. By redefining host-controller responsibilities in this manner, much of the overhead association with FTL functions can be substantially removed from the memory controller, with the host directly specifying physical addresses. This reduces performance unpredictability and overhead, thereby facilitating integration of solid state drives (SSDs) with other forms of storage. The disclosed techniques are especially useful for direct-attached and / or network-attached storage.

Mechanisms for controlling background wear leveling are provided, including: increasing a first counter; comparing the first counter to a first threshold; and in response to the first counter meeting the first threshold: decreasing the first counter by a value of the first threshold; and triggering background wear leveling. In some embodiments, the first counter is increased in response to receiving a write trigger. In some embodiments, the first threshold is based upon a page size and a number of planes of physical media of an SSD. In some embodiments, the mechanisms further comprise: incrementing a second counter in response to receiving a host write trigger; comparing the second counter to a second threshold; and in response to the second counter meeting the second threshold, decreasing the second counter by the second threshold, wherein the increasing the first counter is performed in response to the second counter meeting the second threshold.

The application provides a super block management method and device and electronic equipment, comprising: obtaining a target storage block in a storage unit in a plurality of NandFlash; the block number of the target storage block is the same; initializing a minimum heap container; constructing a super block according to the target storage block; writing a first data structure of a first sub-super block in the super block in a full data state into a first minimum heap in the minimum heap container; and writing a second data structure of a second sub-super block in the super block in an unwritten data state into a second minimum heap in the minimum heap container; and managing the write operation and the garbage collection operation of the super block through the first minimum heap and the second minimum heap. The method improves the garbage collection and wear leveling algorithm efficiency of the SSD firmware.

The invention discloses a solid-state storage loss balancing method and system, and relates to the technical field of computer storage, and the method comprises the steps: dividing a solid-state storage device into a plurality of logic intervals according to the time sequence characteristics of data access, and calculating a corresponding thermal entropy value based on the data access behavior of each logic interval; constructing a cold and hot intensity matrix, and mapping the cold and hot intensity matrix into a corresponding storage block allocation sequence based on a binary search tree; constructing an idle storage block resource pool, covering a preset erasure interval by applying a gradient pointer mechanism, and executing cross-channel storage block allocation in combination with a channel state mask and a probabilistic selection algorithm; the storage blocks in all the channels are arranged in a descending order according to the thermal entropy values, and cross-channel migration operation is executed according to the sorting result. Storage resource allocation is optimized, and efficient layout of the storage blocks is achieved, so that the data migration frequency and storage fragmentation are reduced, the write amplification effect is reduced, and the service life of solid-state storage equipment is effectively prolonged.

This invention provides a wear leveling method and a memory storage device. The wear leveling method is used in a rewritable non-volatile memory module. The rewritable non-volatile memory module includes multiple physical erase units. The wear leveling method includes: determining whether each of the multiple physical erase units meets a preset condition based on the number of erases and the write time of each of the multiple physical erase units; if there is a current physical erase unit that meets the preset condition, determining whether the current physical erase unit is full; if the current physical erase unit is not full, performing a first wear leveling operation on the current physical erase unit; if the current physical erase unit is full, performing a second wear leveling operation on the current physical erase unit.

The invention relates to the technical field of satellite-borne computer file management, and discloses a management and maintenance method and system for NAND FLASH files on a satellite-borne computer, and the method comprises the steps: carrying out file-level read-write management on NAND FLASH through a Yaffs2 file system, and realizing transparent distribution of storage space based on a dynamic logic-physical address mapping table; uniformly distributing data writing operation to a plurality of physical sectors of the NAND FLASH by adopting a wear leveling algorithm, and controlling unevenness and wear of the sectors of the NAND FLASH; according to the method, factory bad blocks and bad blocks generated in the using process are recognized and marked, the bad blocks are dynamically replaced through redundant blocks, meanwhile, the mapping relation between logic addresses and physical addresses is updated, and the reliability of file data stored on the NAND FLASH is improved. Through an innovative wear leveling strategy, a delay bad block marking mechanism, a dynamic address mapping table design and high collaboration with a Yaffs2 file system, the aspects of prolonging the service life of a storage medium, guaranteeing data reliability, optimizing system performance and the like are remarkably improved.

A computer storage device having: a host interface; a controller; non-volatile storage media having memory units of different types and having different program erase budgets; and firmware. The firmware instructs the controller to: generate an address map mapping logical addresses to physical addresses of the memory units the different types; and adjust the address map based at least in part on the program erase budgets to level wear across the memory units of the different types.

The present invention belongs to the field of computer storage, and specifically relates to a ZNS SSD wear leveling method based on an LSM tree. The method comprises the following steps: inputting new data into a ZNS SSD, and classifying the heat level of the new data by using an LSM tree data heat classification method before input; dividing the ZNS SSD into multiple erase range intervals by using an erase range interval selection method, and determining the corresponding erase range interval according to the heat level of the new data; selecting an idle zone within the erase range interval corresponding to the new data to store the new data; and if no idle zone exists within the erase range interval, allocating an idle zone to the new data by using a wear-aware zone allocation method to further balance the wear between zones. The present invention balances the wear between zones in a ZNS SSD, effectively prolongs the service life of ZNS SSDs, and has low overhead.

A data storage system may include a memory device and a controller. The memory device may include a plurality of virtual blocks. The controller may include at least one processor and a memory. The memory may include instructions stored thereon, that when executed by the at least one processor, cause the at least one processor to: monitor a number of program / erase cycles for the plurality of virtual blocks; collect read errors for the plurality of virtual blocks; select a virtual block of the plurality of virtual blocks to open based on the number of program / erase cycles and the collected read errors; and write data to the selected open virtual block.

The invention discloses a door lock operation log management method applied to an intelligent door lock and the intelligent door lock. The door lock operation log management method comprises the following steps: receiving a door lock operation log plaintext, and converting the door lock operation log plaintext into coded log data in a preset format; determining an active sector in the plurality of storage sectors, and writing the coding log data into a current to-be-written address of the active sector; updating metadata of the active sector after writing, wherein the metadata at least comprises a next to-be-written address, the number of logs of the current sector and sector state information; and judging whether the active sector is fully written or not, and when the active sector is fully written, selecting a next storage sector from the plurality of storage sectors for erasing, and setting the next storage sector as a new active sector, so as to realize cyclic coverage and wear balance of the sectors. According to the invention, through log coding compression and sector rotation management, the space occupied by the log is reduced, and the FLASH utilization rate is improved; and wear balance is realized through cyclic coverage.

The application discloses a kind of support in-orbit program reconfiguration's satellite-borne solid-state memory, belong to electronic information field.Satellite-borne solid-state memory includes control core, data storage array, cache unit, refresh loading circuit, interface unit, program storage unit, control core realizes the control of storage array, parse host computer instruction, bad block management, wear leveling and address management, cache unit effectively prevents single event upset error.Storage array avoids the timing violation of FPGA that can appear under high main frequency and other difficult problems.Load refresh circuit uses refresh loading circuit to refresh FPGA internal program regularly, reduces the influence of single event upset.Interface unit realizes the control management of host computer to satellite-borne solid-state memory.Program storage unit selects storage carrier according to function, storage capacity size, read-write bandwidth requirement.The whole hardware design is with FPGA soft core to realize the control management function of satellite-borne solid-state memory, and special CPU hardware does not have to be designed.