Sandisk Technologies Inc.

Western Digital Technologies, Inc.

Yosief Ataklti

Daniel Edward Tuers

Sergey Anatolievich Gorobets

Abhijeet Manohar

Shai Traister

J James Tringali

Dana Lee

Alan David Bennett

Yoav Weinberg

Phil Reusswig

Oleg Kragel

Hongmei Xie

Aajna Karki

Bryan John Mee

Xiaoying Li

Ji-Hyun In

Kwangyoung Lee

Thomas Tam Ta

Abhijeet Mahohar

Aspects of a storage device including a memory and a controller are provided. In certain aspects, the controller may determine that data stored on a first block satisfies a threshold data-error condition, the data comprising invalid data and valid data. For example, the first block may have a high ratio of valid data to invalid data that satisfies or exceeds a threshold value. In certain aspects, the controller may determine a close block boundary associated with the first block, wherein the close block boundary is configured to bifurcate the first block into a first portion and a second portion, wherein the first portion comprises the data. For example, the controller may determine a boundary defined by a data length, an indirection mapping unit, a physical program boundary, etc.

Open block relocation

The present disclosure generally relates to increasing data storage device lifetime by detecting synthetic PLP tests. Both upper and lower PLP time thresholds are set. When the PLP time is above the upper threshold, the data storage device is in a defensive PLP idle state. When the PLP time is between the upper and lower thresholds, the data storage device is in a defensive PLP detecting state. When the PLP time is below the lower threshold, the data storage device may enter the defensive PLP state if the number of times the PLP time is below the lower PLP time threshold either a consecutive number of times or a set number of times within a predefined window of time. While in the defensive PLP state, mounting is not completed and hence, a host device will not send any I/O commands and thus, not waste a PEC count.

Back-to-back power loss protection

A memory controller includes, in one implementation, a host interface, a memory interface, and a flash translation layer (FTL). The FTL is configured to receive a request from a host device to store data in a zone of a solid-state memory. The FTL is also configured to determine a zone reset rate classification as one of a hot classification, a cold classification, and a normal classification. The FTL is further configured to allocate the zone to a memory die with the fewest free die blocks when the zone reset rate classification is the hot classification. The FTL is also configured to allocate the zone to a memory die with the most free die blocks when the zone reset rate classification is the cold classification. The FTL is further configured to send the data to the memory die for storage therein.

Zone allocation for data storage device based on zone reset behavior

A storage controller is configured to find a last-written page in a block in a memory by sending a command to the memory to read a page of data, receiving at least some of the data from that page, and analyzing the at least some of the data from that page to determine if that page is a written page. In one embodiment, the storage controller instructs the memory to read the page of data using a sense time that is shorter than a sense time used to read a page of data in response to a read request from a host controller. Additionally or alternatively, the amount of the data received by the storage controller can be less than the amount of data received when reading a page of data in response to a read request from a host controller.

Storage module and method for improving boot time during block binary searches

In non-volatile memory devices, the accessing of data on word line can degrade the data quality on a neighboring word line, in what is called a read disturb. Techniques are presented for determining word lines likely to suffer read disturbs by use of a hash tree for tracking the number of reads. Read counters are maintained for memory units at a relatively coarse granularity, such as a die or block. When the counter for one of these units reaches a certain level, it is subdivided into sub-units, each with their own read counter, in a process that be repeated to determine frequently read word lines with a fine level of granularity while only using a relatively modest amount of RAM on the controller to store the counters.

Finding read disturbs on non-volatile memories

A controller circuit for a non-volatile memory of one or more memory circuits is described. The controller is connectable by a port with the memory circuits through a bus structure and can operate the memory circuits according to one or more threads. The controller includes a command processing section to issue high level commands for execution in the memory circuits and a memory circuit interface module to issue in sequence by the port to the memory circuits a series of instruction derived from the high level commands. A queue manager on the controller derives the series of instructions from the high level commands. When deriving a series of instruction from a set of high level data access commands, the queue manager can modify the timing for the issuance to the memory circuit interface module of memory circuit check status instructions based upon feedback from the memory circuit interface module and the state of earlier instruction in the series.

Adaptive context disbursement for improved performance in non-volatile memory systems

A portion of a nonvolatile memory array that is likely to contain, partially programmed data may be identified from a high sensitivity read, by applying stricter than usual ECC requirements, or using pointers to programmed sectors. The last programmed data may be treated as likely to be partially programmed data. Data in the identified portion may be copied to another location, or left where it is with an indicator to prohibit further programming to the same cells. To avoid compromising previously stored data during subsequent programming, previously stored data may be backed up. Backing up may be done selectively, for example, only for nonsequential data, or only when the previously stored data contains an earlier version of data being programmed. If a backup copy already exists, another backup copy is not created. Sequential commands are treated as a single command if received within a predetermined time period.

Data protection after possible write abort or erase abort

The variable latency associated with flash memory due to background data integrity operations is managed in order to allow the flash memory to be used in isochronous systems. A system processor is notified regularly of the nature and urgency of requests for time to ensure data integrity. Minimal interruptions of system processing are achieved and operation is ensured in the event of a power interruption.

Urgency and time window manipulation to accommodate unpredictable memory operations

Command cycles incorporate mechanisms to inform a host processor in advance of a need to service the memory so that the host can respond when it suits the host, but in time for the service to be performed before a catastrophic failure. The regular host cycle need not be interrupted for such notification.

Growing community of inventors

Fremont, CA, United States of America

Yosief Ataklti