Micron Technology Incorporated

James P Crowley

Jiangang Wu

Yun Li

Michael Sheperek

Peng Xu

Bruce A Liikanen

Larry Joseph Koudele

Mark Ish

Gerald L Cadloni

Stuart A Bell

Karl David Schuh

Yuriy Pavlenko

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.

Performance control for a memory sub-system

Methods, systems, and devices for a read counter for quality of service design are described. First commands may be assigned to a first queue of a memory die of a memory sub-system, wherein the first queue is associated with a first priority level. The memory die may include a second queue associated with a second priority level different from the first priority level, the second queue comprising one or more second commands assigned. Based at least in part on a counter associated with the first queue and the first and second priority levels, it may be determined that a threshold number of the first commands of the first queue have issued without a command from the one or more second commands having issued. A command from the second commands may issue before issuing a next command of the first commands based at least in part on the counter.

Read counter for quality of service design

Methods, systems, and devices for memory die resource management are described. A resource manager can determine, from a set of global resources for multiple memory dies of a memory sub-system, a set of die-specific resources for a memory die of the multiple memory dies of the memory sub-system. In some case, the set of die-specific resources can be allocated for read commands for the memory die. The resource manager can assign a read command to a die-specific resource of the set of die-specific resources based on the die-specific resource being available and refrain from assigning the read command to the die-specific resource based on the die-specific resource being unavailable.

Memory die resource management

A die read counter and a block read counter are maintained for a specified block of a memory device. An estimated number of read events associated with the specified block is determined based on a value of the block read counter and a value of the die read counter. Responsive to determining that the estimated number of read events satisfies a criterion, a media management operation of one or more pages associated with the specified block is performed.

Mitigating read disturb effects in memory devices

Exemplary methods, apparatuses, and systems include a memory controller detecting that an asynchronous power loss event has occurred. Upon determining that a write operation is in progress to a first type of non-volatile memory element, the memory controller cancels the write operation and retrieves data associated with the write operation. The memory controller sends a request for a second physical address pointing to a second type of non-volatile memory element. Upon receiving a second physical address corresponding to a logical address, the memory controller stores the data at the second physical address.

Managing write operations during a power loss

A total read counter, a plurality of die read counters, and a plurality of block read counters are maintained. Each die read counter is associated with a respective die of a memory device. A value of a block read counter and a value of a die read counter are determined for a specified block. Based on the value of the block read counter, the value of the die read counter, and the value of the total read counter, an estimated number of read events associated with the specified block of the memory device is determined. Responsive to determining that the estimated number of read events satisfies a predefined criterion, a media management operation of one or more pages associated with the specified block is performed.

Feedback relating to errors in memory operations on a plurality of memory cells is received by a memory sub-system. At least one processing level corresponding to a program distribution is updated based on the feedback to adjust an error measure between pages of the plurality of memory cells and to adjust a read window budget within a page of the plurality of cells. The updating of the at least one processing level is based on information for the at least one processing level that is stored in a data-structure.

Data-structure based dynamic program targeting control

Resource management for memory die-specific operations

Exemplary methods, apparatuses, and systems include a memory controller receiving a first physical address corresponding to a logical address and data and initiating storage of the data at the first physical address. The memory controller sends a message indicating that the data has been successfully stored at the first physical address before determining if the data was successfully stored at the first physical address. Upon determining that the data failed to store at the first physical address, the memory controller retrieves the data from a volatile memory associated with the first physical address. The memory controller sends a request and receives a second physical address for the retrieved data. The memory controller initiates storage of the data at the second physical address.

Data recovery after storage failure in a memory system

A controller selects a redundancy context for eviction in response to a request for a redundancy context. The redundancy context includes buffer data and an identifier. The redundancy context is evicted by instructing a redundancy component to send the buffer data and identifier to a memory component to store in a buffer as an evicted context. The controller instructs the memory component to provide the evicted context for storage in a controller buffer. A new redundancy context is allocated to the requester following the eviction.

Growing community of inventors

Longmont, CO, United States of America

James P Crowley