Systems and methods are described for enabling garbage collection on data storage systems. Traditional garbage collection often attempts to track use of data items on an individual level, deleting each item when it is no longer used. In distributed systems, tracking use on an individual level is difficult, and may require centralized knowledge across the system with respect to individual data items. Provided herein is a “coarse-grained” garbage collection mechanism, which divides objects into logical groups referred to as “roots.” Each root has a life cycle. While active, new data can be stored in a root. While inactive, use of data within a root can cause that date to be copied to a different, active root. When the system detects that data hasn't been used in an inactive root for a threshold period, the root can be considered “dead” and data within the root may be deleted.

A memory system includes a memory array having a plurality of memory cells; and a controller coupled to the memory array, the controller configured to: designate a storage mode for a target set of memory cells based on valid data in a source block, wherein the target set of memory cells are configured with a capacity to store up to a maximum number of bits per cell, and the storage mode is for dynamically configuring the target set of memory cells in as cache memory that stores a number of bits less per cell than the corresponding maximum capacity.

In some examples, a system performs data deduplication using a deduplication fingerprint index in a hash data structure comprising a plurality of blocks, wherein a block of the plurality of blocks comprises fingerprints computed based on content of respective data values. The system merges, in a merge operation, updates for the deduplication fingerprint index to the hash data structure stored in a persistent storage. As part of the merge operation, the system mirrors the updates to a cached copy of the hash data structure in a cache memory, and updates, in an indirect block, information regarding locations of blocks in the cached copy of the hash data structure.

A method of operating a data storage device includes programming non-fully programmed memory blocks at a point in time when a reference time elapses from a point in time when each of the memory blocks is physically erased, acquiring a first interval and a second interval, calculating a disturb index based on the first interval and the second interval, selecting a victim block for garbage collection based on the disturb index, and copying valid page data of the victim block into a free block. The first interval is defined by a point in time when each of the memory blocks is physically erased and a point in time when each of the memory blocks is fully programmed. The second interval is an interval during which a fully programmed state is maintained after a point in time when each of the memory blocks is fully programmed.

Techniques for performing garbage collection on an object array using array chunk references is described. A garbage collector (GC) thread identifies an object array to be processed. The GC thread divides the object array into array chunks. The GC thread generates array chunk references corresponding respectively to the array chunks. Each array chunk reference comprises: (a) chunk start bits representing a memory address of a start of a corresponding array chunk, and (b) chunk length bits representing a chunk length of the corresponding array chunk. The GC thread pushes the array chunk references onto the processing stack. A single processing stack concurrently stores multiple array chunk references, associated with a same object array. One or more of the array chunk references, that are associated with the same object array and stored on the processing stack, may be distributed to other GC threads for processing.

A memory system includes a controller, a buffer, and a nonvolatile memory including a plurality of blocks, wherein each of the blocks includes a plurality of pages and each of the pages includes a plurality of unit data portions. The controller is configured to carry out garbage collection by reading data from one or more pages of a target block of the garbage collection and selectively copying valid unit data portions included in the read data to another block, count a number of invalid unit data portions included in the read data, and accept, in the buffer, unit data portions from a host as write data, up to a number determined based on the counted number, during the garbage collection.

Systems, apparatus and methods are provided for performing program operations in a non-volatile storage system. In one embodiment, there is provided a method that may comprise categorizing active storage blocks of a non-volatile storage device into a robust group and a less-robust group based on a number of factors including page error count, program time and number of Program/Erase (P/E) cycles; determining that a cache program operation needs to be performed; selecting a first storage block from the robust group to perform the cache program operation; determining that a regular program operation needs to be performed; and selecting a second storage block from the less-robust group to perform the regular program operation.

Techniques are disclosed for eliding load and store barriers while maintaining garbage collection invariants. Embodiments described herein include techniques for identifying an instruction, such as a safepoint poll, that checks whether to pause a thread between execution of a dominant and dominated access to the same data field. If a poll instruction is identified between the two data accesses, then a pointer for the data field may be recorded in an entry associated with the poll instruction. When the thread is paused to execute a garbage collection operation, the recorded information may be used to update values associated with the data field in memory such that the dominated access may be executed without any load or store barriers.

A plurality of entries associated with a media management operation for a plurality of transfer units are stored. A respective destination location for each of the respective transfer units are determined in connection with the garbage procedure such that a subset of the plurality of transfer units aligns with a codeword boundary on the memory page. A plurality of write commands in connection with the media management operation are issued based at least in part on the determining.

According to one embodiment, a memory system includes a nonvolatile memory, and a controller. The controller controls the nonvolatile memory. The nonvolatile memory includes a first area where specific software is capable of being stored, and a second area where the specific software is stored. The second area has higher reliability than the first area. The controller causes the specific software to be stored in the first area when receiving a command specifying the specific software, and executes loading of the specific software stored in the first area at startup of the controller.