As NAND flash memory manufacturers scale down to smaller process technology nodes and store more bits per cell, reliability and endurance of flash memory reduce. Wear-leveling and error correction coding can improve both reliability and endurance, but finding effective algorithms requires a strong understanding of flash memory error patterns. To enable such understanding, we have designed and implemented a framework for fast and accurate characterization of flash memory throughout its lifetime. This paper examines the complex flash errors that occur at 30-40nm flash technologies. We demonstrate distinct error patterns, such as cycle-dependency, location-dependency and value-dependency, for various types of flash operations. We analyze the discovered error patterns and explain why they exist from a circuit and device standpoint. Our hope is that the understanding developed from this characterization serves as a building block for new error tolerance algorithms for flash memory.

/pdf/error-patterns-in-mlc-nand-flash-memory-measurement-598fgyt3mx.pdf

Error patterns in MLC NAND flash memory: measurement, characterization, and analysis

With continued scaling of NAND flash memory process technology and multiple bits programmed per cell, NAND flash reliability and endurance are degrading. Understanding, characterizing, and modeling the distribution of the threshold voltages across different cells in a modern multi-level cell (MLC) flash memory can enable the design of more effective and efficient error correction mechanisms to combat this degradation. We show the first published experimental measurement-based characterization of the threshold voltage distribution of flash memory. To accomplish this, we develop a testing infrastructure that uses the read retry feature present in some 2Y-nm (i.e., 20-24nm) flash chips. We devise a model of the threshold voltage distributions taking into account program/erase (P/E) cycle effects, analyze the noise in the distributions, and evaluate the accuracy of our model. A key result is that the threshold voltage distribution can be modeled, with more than 95% accuracy, as a Gaussian distribution with additive white noise, which shifts to the right and widens as P/E cycles increase. The novel characterization and models provided in this paper can enable the design of more effective error tolerance mechanisms for future flash memories.

/pdf/threshold-voltage-distribution-in-mlc-nand-flash-memory-3iznque2z7.pdf

Threshold voltage distribution in MLC NAND flash memory: characterization, analysis, and modeling

We present Griffin, a hybrid storage device that uses a hard disk drive (HDD) as a write cache for a Solid State Device (SSD) Griffin is motivated by two observations: First, HDDs can match the sequential write bandwidth of mid-range SSDs Second, both server and desktop workloads contain a significant fraction of block overwrites By maintaining a log-structured HDD cache and migrating cached data periodically, Griffin reduces writes to the SSD while retaining its excellent performance We evaluate Griffin using a variety of I/O traces from Windows systems and show that it extends SSD lifetime by a factor of two and reduces average I/O latency by 56%

/pdf/extending-ssd-lifetimes-with-disk-based-write-caches-2qkp2e1a7t.pdf

Extending SSD lifetimes with disk-based write caches

Retention errors, caused by charge leakage over time, are the dominant source of flash memory errors. Understanding, characterizing, and reducing retention errors can significantly improve NAND flash memory reliability and endurance. In this paper, we first characterize, with real 2y-nm MLC NAND flash chips, how the threshold voltage distribution of flash memory changes with different retention age — the length of time since a flash cell was programmed. We observe from our characterization results that 1) the optimal read reference voltage of a flash cell, using which the data can be read with the lowest raw bit error rate (RBER), systematically changes with its retention age, and 2) different regions of flash memory can have different retention ages, and hence different optimal read reference voltages. Based on our findings, we propose two new techniques. First, Retention Optimized Reading (ROR) adaptively learns and applies the optimal read reference voltage for each flash memory block online. The key idea of ROR is to periodically learn a tight upper bound, and from there approach the optimal read reference voltage. Our evaluations show that ROR can extend flash memory lifetime by 64% and reduce average error correction latency by 10.1%, with only 768 KB storage overhead in flash memory for a 512 GB flash-based SSD. Second, Retention Failure Recovery (RFR) recovers data with uncorrectable errors offline by identifying and probabilistically correcting flash cells with retention errors. Our evaluation shows that RFR reduces RBER by 50%, which essentially doubles the error correction capability, and thus can effectively recover data from otherwise uncorrectable flash errors.

/pdf/data-retention-in-mlc-nand-flash-memory-characterization-3o3aqqzitw.pdf

Data retention in MLC NAND flash memory: Characterization, optimization, and recovery

With the continued scaling of NAND flash and multi-level cell technology, flash-based storage has gained widespread use in systems ranging from mobile platforms to enterprise servers. However, the robustness of NAND flash cells is an increasing concern, especially at nanometer-regime process geometries. NAND flash memory bit error rate increases exponentially with the number of program/erase cycles. Stronger error correcting codes (ECC) can be used to tolerate higher error rates, but these have diminishing returns with increasing P/E cycles and can have prohibitively high power, area, and latency overheads. The goal of this paper is to develop new techniques that can tolerate high bit error rates without requiring prohibitively strong ECC. Our techniques, called Flash Correct-and-Refresh (FCR) exploit the observation that the dominant error source in NAND flash memory is retention errors, caused by flash cells losing charge over time. The key idea is to periodically read, correct, and reprogram (in-place) or remap the stored data before it accumulates more retention errors than can be corrected by simple ECC. Detailed simulations of a solid-state drive (SSD) storage system driven by measured experimental data from error characterization on real flash memory chips show that our techniques provide 46× average lifetime improvement on a variety of workloads at no additional hardware cost. We also find that our techniques achieve lifetime improvements that cannot feasibly be achieved with stronger ECC.

/pdf/flash-correct-and-refresh-retention-aware-error-management-4cp1mtrmia.pdf

Flash correct-and-refresh: Retention-aware error management for increased flash memory lifetime

NAND flash memories have bit errors that are corrected by error-correction codes (ECC). We present raw error data from multi-level-cell devices from four manufacturers, identify the root-cause mechanisms, and estimate the resulting uncorrectable bit error rates (UBER). Write, retention, and read-disturb errors all contribute. Accurately estimating the UBER requires care in characterization to include all write errors, which are highly erratic, and guardbanding for variation in raw bit error rate. NAND UBER values can be much better than 10-15, but UBER is a strong function of program/erase cycling and subsequent retention time, so UBER specifications must be coupled with maximum specifications for these quantities.

Bit error rate in NAND Flash memories

Described are an apparatus, system, and method for improving read endurance for a non-volatile memory (NVM). The method comprises: determining a read count corresponding to a block of NVM; identifying whether the block of NVM is a partially programmed block (PPB); comparing the read count with a first threshold when it is identified that the block is a PPB; and when identified otherwise, comparing the read count with a second threshold, wherein the first threshold is smaller than the second threshold. The method further comprises: identifying a block that is a PPB; determining a first word line corresponding to un-programmed page of the PPB; and sending the first word line to the NVM, wherein the NVM to apply: a first read voltage level to word lines corresponding to the un-programmed pages of the PPB, and a second read voltage level to word lines corresponding to programmed pages of the PPB.

Apparatus, system, and method for improving read endurance for a non-volatile memory

Technology for an apparatus is described. The apparatus can include a first non-volatile memory, a second non-volatile memory to have a write access time faster than the first non-volatile memory, and a memory controller. The memory controller can be configured to detect corrupted data in a selected data region in the first non-volatile memory. The selected data region can be associated with an increased risk of data corruption after data is written from the second non-volatile memory to the first non-volatile memory. Uncorrupted data in the second non-volatile memory that corresponds to the corrupted data in the first non-volatile memory can be identified. Data recovery in the first non-volatile memory can be performed by replacing the corrupted data in the first non-volatile memory with uncorrupted data from the second non-volatile memory.

Data recovery in memory devices

According to one configuration, a memory system includes a configuration manager and multiple memory devices. The configuration manager includes status detection logic, retrieval logic, and configuration management logic. The status detection logic receives notification of a failed attempt by a first memory device to be initialized with custom configuration settings stored in the first memory device. In response to the notification, the retrieval logic retrieves a backup copy of configuration settings information from a second memory device in the memory system. The configuration management logic utilizes the backup copy of the configuration settings information retrieved from the second memory device to initialize the first memory device.

Configuration information backup in memory systems

Embodiments include apparatuses, method, and systems for organizing individual memory dice of a memory device into a plurality of virtual dice and designating one of the virtual dice of the memory device for storage of redundancy information In one embodiment, a memory controller includes memory allocation logic to organize memory resources of individual memory dice of a memory device into a plurality of virtual dice, including a redundancy virtual die for storing redundancy information and a plurality of data virtual dice for storing data The memory controller may further include input/output logic to write data to the data virtual dice of the non-volatile memory device, and redundancy information logic to generate redundancy information based on the data and to write the redundancy information to the redundancy virtual die of the non-volatile memory device

Ning Wu

Papers

Bit error rate in NAND Flash memories

Apparatus, system, and method for improving read endurance for a non-volatile memory

Data recovery in memory devices

Configuration information backup in memory systems

Managing redundancy information in a non-volatile memory