12results about How to "Reduce write amplification" patented technology

This invention discloses a data management method and electronic device for a storage device, belonging to the field of storage technology. The data management method includes: when the lifetime of the hold table is less than the lifetime of the hold data area, writing data from the data cache to non-volatile memory, and the storage device entering a hibernation mode; when the lifetime of the hold table is greater than the lifetime of the hold data area, determining whether the data size in the data cache has reached a flush threshold; if the data size reaches the flush threshold, writing the data to non-volatile memory, and the storage device entering a hibernation mode; if the data size does not reach the flush threshold, saving the data to the hold data area, recording the boundary marker information of the data in the hold data area, and writing the system management data table to be migrated from the hold table to the non-volatile memory, and the storage device entering a hibernation mode. The data management method and electronic device for a storage device provided by this invention can extend the lifespan of the storage device.

The application relates to the technical field of hybrid solid state disks, and discloses a hybrid solid state disk dynamic optimization method and device based on a large language model, which systematically classifies the parameter space of a hybrid solid state disk, constructs a parameter sensitivity matrix based on the classified parameters, determines the influence difference parameters of the parameters on performance under different workloads, collects system state information of the hybrid solid state disk in real time, generates an optimized parameter configuration scheme based on a large language model according to the system state information, the influence difference parameters and historical configuration information. The application can realize real-time perception of work load changes and dynamic focusing on the most sensitive parameter combination under the current load, realize collaborative reasoning and adaptive adjustment among multiple parameters, significantly reduce the write amplification rate and operation delay, and solve the problem that the response efficiency, system stability and energy consumption performance of the hybrid SSD are poor under a dynamic work load in the prior art.

The invention discloses a duplication data deletion metadata management method based on a persistent memory. The method comprises the following steps: managing a global fingerprint table and a logic address to a fingerprint mapping cache in a DRAM (Dynamic Random Access Memory), and managing an additional redo log and a global mapping table in the persistent memory. The write-in path firstly writes metadata update into the DRAM and forms a transaction record, the transaction record is sequentially added to a persistent memory log in a group submission mode, persistence is aligned according to the read-write granularity of the persistent memory, and random write and lock competition is reduced; in the checkpoint stage, an aggregation strategy is dynamically selected according to the redundancy rate and the coverage write proportion obtained through online load detection, and therefore metadata write amplification is remarkably reduced on the premise that collapse consistency is guaranteed. Meanwhile, three self-adaptive deduplication modes are provided, fingerprint management is bypassed in the low redundancy stage, redundancy is sampled and estimated in the medium redundancy stage, and full deduplication is started in the high redundancy stage, so that the metadata management cost is stably reduced under different loads, and the system throughput is improved.

The application discloses a data management method and system suitable for IMR, wherein when a bottom track is updated, data of an effective top track is actively migrated to other free tracks; in the MFML data update strategy, a zigzag four-stage data management scheme is adopted, in the first stage, data of the bottom track is updated; in the second stage, the MFML strategy is adopted to update data of the bottom track; in the third stage and the fourth stage, data distribution and bottom track data update are continuously performed according to the mode of the second stage, and data management is realized. The application can make the MFML update strategy better play the performance in the four-stage data management scheme, and can also relieve the performance decline problem caused by the too high top track occupation amount of the multi-stage distribution scheme.

The invention relates to a solid state disk write-in balance optimization method which is applied to a solid state disk comprising a controller and a flash memory medium, and the controller maintains a mapping table from a logic address to a physical page and erasure frequency information; comprising the following steps: calculating a difference between a maximum value and a minimum value of erasing times of each erasing block in a preset statistical range as a wear difference index; dividing logic intervals according to logic addresses, and determining a certain logic interval as a candidate cold logic interval if the mapping failure update event does not occur in a time window; selecting a first candidate cold logic interval mapped to a high-wear block and a second candidate cold logic interval mapped to a low-wear block; under the condition that an existing effective user data page is not moved, physical page sets corresponding to the first candidate cold logic interval and the second candidate cold logic interval are exchanged only by updating physical page set identifiers or interval descriptors, used for subsequent writing, of the first candidate cold logic interval and the second candidate cold logic interval in the mapping table; and persistently writing the mapping table update record and the related block state in a log mode.

This invention discloses a mapping management method, apparatus, computer device, and storage medium for solid-state drives (SSDs). The method includes: establishing an SLC cache mapping table independent of the main mapping table; storing data written by the host in the SLC cache area and recording the mapping relationship between the logical page address and physical page address corresponding to the data in the SLC cache mapping table; when the SLC cache area meets the migration conditions, migrating the data in the SLC cache area to multiple programming data blocks and completing all programming steps for the data in the multiple programming data blocks; after confirming that the data has completed all programming steps in the multiple programming data blocks, deleting the mapping relationship corresponding to the data from the SLC cache mapping table and updating the mapping relationship to the main mapping table. By implementing the method of this invention, the performance and lifespan problems caused by dual mapping updates in existing QLC SSDs using SLC caching technology can be effectively solved.

This invention discloses a key-value storage system, electronic device, and medium based on an LSM-Tree, comprising: volatile memory for caching newly written data and retrieving newly written data; persistent memory including multiple cuckoo filters for indexing global data; the multiple cuckoo filters include several cuckoo filters, each containing a hash table with several hash buckets, each hash bucket containing four hash slots, each hash slot being 64 bytes in size, where the high 32 bytes are used to store the fingerprint of the key in the key-value pair, and the low 32 bytes are used to store the file number of the corresponding key-value pair; and a disk using a single-level file structure to persist key-value pair data and store data logs and system logs; wherein, the single-level file structure merges the files with the highest degree of overlap in the next round of merging operations based on the degree of overlap between files.

The invention relates to the technical field of storage systems, in particular to a ZNS storage method and system based on SSTable fine-grained heat perception and cross-regional dynamic wear leveling, and the method comprises the following steps: step 1, initializing a ZNS storage environment and constructing a global resource pool; step 2, writing request initiation and data popularity classification; step 3, performing Zone allocation based on types; 4, physical writing and metadata unified updating are carried out; and 5, garbage collection GC and wear balance circulation. According to the method, the problems of SSTable heat deflection, Zone stiffness and unbalanced wear in a ZenFS scene can be effectively solved.

The application discloses a kind of based on persistent memory's repeated data deletion metadata management method, including in DRAM management global fingerprint table and logical address to fingerprint mapping cache, in persistent memory management append redo log and global mapping table.Write path will first write metadata update into DRAM and form transaction record, sequentially append to persistent memory log using group commit mode, and with persistent memory read-write granularity size alignment persistence, reduce random write and lock contention;Checkpoint phase is according to the redundancy rate and the proportion of overwrite obtained by online load detection, dynamically select aggregation strategy, so as to significantly reduce metadata write amplification under the premise of ensuring crash consistency.Meanwhile, the application provides three kinds of adaptive deduplication mode: in low redundancy stage, by bypassing fingerprint management, in moderate redundancy stage, sample estimate redundancy, in high redundancy stage, enable full deduplication, so as to stably reduce metadata management cost and improve system throughput under different loads.

A compression method, a controller and a memory of mapping table data are disclosed. The compression method is used for mapping table data including a plurality of physical addresses, and includes: splitting each physical address into a plurality of segments according to the types of domain addresses contained in the physical address, each segment containing at least one type of domain address; grouping the segments containing the same type of domain address in each physical address of the plurality of physical addresses into a set corresponding to the domain address respectively; compressing consecutive domain addresses in each set; and storing the compressed sets in a cache unit in order of the split segments. The compression method of the present disclosure splits the physical addresses according to the different types of domain addresses, and then groups the sets, and compresses each set respectively, thereby having a high compression rate, greatly reducing the flash memory space occupied by the mapping table, reducing the write amplification, and prolonging the service life of the solid state disk.

The application relates to the field of storage devices, in particular to a metadata storage method, a metadata recovery method, a metadata large block recovery method and a storage device, which comprises the following steps: dividing metadata into a plurality of metadata data streams, taking the metadata data stream as a storage unit, and storing the metadata in a metadata large block. The application can solve the problems of quick recovery of a quick start technology and introduction of additional write amplification.

The present application relates to a solid state disk write balancing optimization method, applied to a solid state disk containing a controller and a flash memory medium, the controller maintaining a logical address to physical page mapping table and erase count information; comprising: calculating the difference between the maximum and minimum erase counts of each erase block in a predetermined statistical range as a wear difference indicator; dividing the logical address into logical intervals, if a certain logical interval does not occur in the mapping failure update event within the time window, it is determined as a candidate cold logical interval; selecting a first candidate cold logical interval mapped to a high wear block and a second candidate cold logical interval mapped to a low wear block; without moving existing valid user data pages, only by updating the physical page set identifier or interval descriptor used for subsequent writing of the first and second candidate cold logical intervals in the mapping table, exchanging the physical page sets corresponding to the first and second candidate cold logical intervals; the mapping table update record and related block state are written in a log mode.