Sandisk Technologies Inc.

Western Digital Technologies, Inc.

Sandisk Corporation

Micron Technology Incorporated

Lexar Media, Inc.

Alan David Bennett

Sergey Anatolievich Gorobets

Liam Michael Parker

Daniel Lee Helmick

Alan Welsh Sinclair

Peter John Smith

Andrew John Tomlin

William S Wu

Shai Traister

Peter Grayson

Alan Douglas Bryce

Eugene Zilberman

Steven Theodore Sprouse

Alexander Paley

Charles Michael Schroter

Ryan R Jones

Bum Suck So

Yuval Shohet

Michelle Martin

Horst-Christoph Georg Hellwig

Thomas Hugh Shippey

Yehuda Hahn

Carlos J Gonzalez

Jason T Lin

Neil David Hutchison

Matias Bjorling

Robert George Young

David Landsman

Leena Patel

Neil D Hutchison

Marielle Bundukin

Liang Li

Kevin M Conley

Abhijeet Manohar

Karin Inbar

Narendhiran Chinnaanangur Ravimohan

Reuven Elhamias

Muralitharan Jayaraman

Xuan Tian

Uri Peltz

Yosief Ataklti

Einat Lev

Kevin Patrick Kealy

Ameen Aslam

Bryan John Mee

Vincent Yin

Roi Kirshenbaum

Dandan Yi

Robert Jackson

Jojo Xing

Matias Bjørling

Philip D Royall

Tom Hugh Shippey

Yauheni Yaromenka

Ofer Sharon

Yongke Sun

Stephen T Sprouse

The present disclosure generally relates to improving programming to data storage devices, such as solid state drives (SSDs). A first memory device has a first XOR element and a second memory device has a second XOR element. The ratio of the first XOR element to the capacity of the first memory device is substantially smaller than the ratio of the second XOR element to the capacity of the second memory device. A read verify operation to find program failures is executed on either a wordline to wordline basis, an erase block to erase block basis, or both a wordline to wordline basis and an erase block to erase block basis. Because the program failures are found and fixed prior to programming to the second memory device, the second XOR element may be decreased substantially.

TLC data programming with hybrid parity

Rather than having unused die blocks, partial die blocks can contribute to a super block. In so doing, as much of the available physical capacity of the data storage device may be achieved. The result could be an increase in over provisioning (OP) and good capacity for the data storage device or an increase in die yield. An increase in good capacity through the use of previously unused physical blocks would lead to an increase in performance and endurance. A yield increase would result in a reduction in cost per die and per data storage device. A partial die block is the solution.

Partial die blocks

In some situations, a leak on a wordline may be a localized problem that causes data loss in a block that contains the wordline. In other situations, such as when the leak occurs near a peripheral wordline routing area, the leak can affect the entire memory die. The storage system provided herein has a fatal wordline leak detector that determines the type of leak and, accordingly, whether just the block should be retired or whether related blocks should be retired.

Storage system and method for proactive die retirement by fatal wordline leakage detection

Instead of having all zones open across all dies, optimizing caching of non-direct write active zones using a host append point (HAP) for maximum write bandwidth is sufficient. The controller will calculate the write rate for a jumbo device (JD). Based on the JD with lowest total write rate, the controller will assign the JD a new zone. The controller will then determine whether the write rate is either appropriate for a cache write or for a direct write. Based on the determination, the controller will write data to the new zone. If the controller direct writes to the new zone, then the controller will close the zone when the zone is full. If the controller cache writes the data to the new zone, then the controller will copy the zone to the direct write area and return the cache write zone to a zone pool. The controller will reclassify the zone if the initial classification is incorrect.

Cache writing to zones to maximize write bandwidth

A storage system receives a request to read data that is located in a wordline undergoing a program operation. Instead of waiting for the program operation to complete, which would increase read latency, the storage system aborts the program operation and reconstructs the data from successfully-programmed memory cells in the wordline and from data latches associated with unsuccessfully-programmed memory cells in the wordline. The reconstructed data is then sent to the host. The program abort command can be similar to one used to provide a graceful shutdown in a power-loss situation.

Storage system and method for improving read latency during mixed read/write operations

The present disclosure generally relates to methods of operating storage devices. The storage device comprises a controller and a media unit. The capacity of the media unit is divided into a plurality of zones. The controller is configured to make informed use of errors by update zone metadata to indicate one or more first logical block addresses were skipped and to indicate the next valid logical block address is available to store data. The controller is further configured to update zone metadata to recommend to the host device to reset one or more full zones, to recommend to the host device to transition one or more open zones to a full state, to alert the host device that one or more open zones have been transitioned to the full state, and to notify the host device of the writeable zone capacity of each of the plurality of zones.

Zoned namespaces in solid-state drives

The present disclosure generally relates to methods of operating storage devices. The storage device comprises a controller and a media unit divided into a plurality of zones. Data associated with one or more first commands is written to a first portion of a first zone. Upon a predetermined amount of time passing, dummy data is written to a second portion of the first zone to fill the first zone to a zone capacity. Upon receiving one or more second commands to write data, a second zone is allocated and opened, and the data associated with the one or more second commands is written to a first portion of the second zone. The data associated with the one or more first commands is then optionally re-written to a second portion of the second zone to fill the second zone to a zone capacity, and the first zone is erased.

Keeping zones open with intermediate padding

A method and system for improved foggy-fine programming includes data that can be written to SLC memory. Then, the data can be decoded and then both foggy and finely written to MLC. After the decoding, the data can be stored in DRAM located in a front end or in a SRAM located in a flash manager prior to being written to MLC. After storing in either the DRAM or SRAM, the data is then decoded and written to MLC.

QLC programming method with staging of fine data

A data storage device includes one or more memory devices that each includes one or more superblocks and a controller coupled to the one or more memory devices. Each superblock includes a plurality of wordlines. The controller is configured to write data to a first wordline of the plurality of wordlines, write data to a second wordline of the plurality of wordlines, perform a read verify operation on the first wordline, and perform a read verify operation on the second wordline. At least one of the first wordline and the second wordline does not include an XOR parity element and one or more wordlines of the plurality of wordlines includes the XOR parity element.

QLC data programming

The present disclosure generally relates to methods of operating storage devices. The storage device comprises a controller and a storage unit divided into a plurality of streams. The storage unit comprises a plurality of dies, where each die comprises two planes. One erase block from each plane of a die is selected for stream formation. Each erase block comprises a plurality of wordlines. A stream comprises one or two dies dedicated to storing parity data and a plurality of dies dedicated to storing user data. The stream further comprises space devoted for controller metadata. The storage device restricts a host device to send write commands in a minimum write size to increase programming efficiency. The minimum write size equals one wordline from one erase block from each plane of each die in the stream dedicated to storing user data minus the space dedicated to metadata.

Storage devices having minimum write sizes of data

The present disclosure generally relates to methods of operating storage devices. The storage device comprises a controller comprising first random access memory (RAM1), second random access memory (RAM2), and a storage unit divided into a plurality of zones. A first command to write data to a first zone is received, first XOR data is generated in the RAM1, and the data of the first command is written to the first zone. When a second command to write data to a second zone is received, the generated first XOR data is copied from the RAM1 to the RAM2, and second XOR data for the second zone is copied from the RAM2 to the RAM1. The second XOR data is updated with the second command, and the data of the second command is written to the second zone. The updated second XOR data is copied from the RAM1 to the RAM2.

ZNS parity swapping to DRAM

The present disclosure generally relates to methods of operating storage devices. The storage device comprises a controller and a media unit. The capacity of the media unit is divided into a plurality of zones. The media unit comprises a plurality of dies, and each of the plurality of dies comprising a plurality of erase blocks. The controller is configured to compare an estimated age of a first available erase block in each of the plurality of dies to one another and select one or more of the first available erase blocks from one or more dies of the plurality of dies based on the estimated ages to form a first zone. At least one first available erase block from at least one die of the plurality of die is excluded from the first zone.

Zone formation for zoned namespaces

The present disclosure generally relates to methods of operating storage devices. A controller of the storage device is configured to retrieve a first command to write data to one or more first logical blocks of a first zone, and direct memory access (DMA) read and write the data associated with the first command to the first logical blocks. The first logical blocks are between a zone starting point of the first zone and a zone capacity of the first zone. The controller is configured to retrieve a second command to write data to one or more second logical blocks of the first zone, and DMA read and write the data associated with the second command to the second logical blocks. The second logical blocks are between the zone starting and the zone capacity of the first zone, and the first logical blocks are non-sequential to the second logical blocks.

Non-sequential zoned namespaces

The present disclosure generally relates to methods of operating storage devices. The storage device comprises a controller and a storage unit divided into a plurality of zones. The storage unit comprises a plurality of dies, where each die comprises two planes. One erase block from each plane of a die is selected for zone formation. Each erase block comprises a plurality of wordlines. A zone comprises one or two dies dedicated to storing parity data and a plurality of dies dedicated to storing user data. The zone further comprises space devoted for controller metadata. The storage device restricts a host device to send write commands in a minimum write size to increase programming efficiency. The minimum write size equals one wordline from one erase block from each plane of each die in the zone dedicated to storing user data minus the space dedicated to metadata.

Growing community of inventors

Edinburgh, United Kingdom

Alan David Bennett