Dell Products Inc.

Dell & Products L.p.

Young Hwan Jang

Lip Vui Kan

Chai Im Teoh

Min Thu Aung

Gokul Thiruchengode Vajravel

Ghim Teck Toh

Simon Kan

Seung Min Oh

An information handling system includes a flash device interface and a flash device. The flash device includes a flash controller and a flash array. The flash device interface programs a command register of the flash controller with a first value, and reads a status register of the flash controller. The flash device interface further determines that a usage of the flash device is in accordance with one of a first usage model and a second usage model based upon a value in the first status register. When the usage is in accordance with the first usage mode, the flash device interface retains the first value in the command register. When the usage is in accordance with the second usage model, the flash device interface reprograms the command register with a second value. The command register controls a read threshold count value for reading data from the flash array.

Dynamic NAND read/write access time for SSD reliability and performance enhancement

The compression and decompression of files can be selectively offloaded to a hardware controller. A hardware controller, such as the controller of an SSD or other drive, can include a compression engine that is configured to implement compression techniques. A filter driver in the I/O pathway on a computing device may be configured to intercept an application's attempt to write a file to or read a file from the SSD or other drive and to selectively offload compression or decompression of the file to a compression engine on the SSD or other drive.

Selectively offloading the compression and decompression of files to a hardware controller

Systems and methods are provided that may be implemented to collect and log (or record) data or information regarding logical block address (LBA) access activity occurring in a solid-state drive (SSD) non-volatile memory storage device of an information handling system. The LBA access activity may be collected, logged and store at the SSD storage controller-level, and may be retrieved and processed and/or analyzed to develop and then implement non-volatile memory management techniques to optimize and improve SSD device operation and performance (e.g., by decreasing read/write completion times), optimizing SSD media endurance (e.g., by extending the useful life of the SSD media), etc.

Systems and methods of intelligent logical block address (LBA) access trace log collection for performance optimization

Methods, systems, and devices for providing computer implemented services are disclosed. To provide the computer implemented services while managing limited hardware resources necessary to provide the services, a hibernation may be performed. To do so, a hibernation manager may facilitate management and storage of hibernation data for use during hibernation and startup of a system. To manage and store the hibernation data, the hibernation manager may identify an allocation of high-performance storage for the hibernation data, obtain a compression pipeline based on the allocation, and stream the hibernation data through the compression pipeline. By doing so, the speed in which the hibernation data is written and read may be increased. Thus, hibernation and startup of the system may be enhanced.

Accelerating windows fast startup for dram-less SSD

Aspects of this disclosure improve data availability by decreasing access times to obtain data from the storage device while still providing high memory density. A method may include receiving, by a controller of a non-volatile solid-state storage device, data with tags to be stored in a first portion configured as a first type and a second portion configured as a second type; receiving, by the controller, a storage command comprising an indicator, wherein at least some data associated with a tag identified by the indicator is stored in the first portion; and writing, by the controller based on receiving the storage command, the at least some data associated with the tag identified by the indicator from the first portion to the second portion. Other aspects are also disclosed.

Hybrid storage device with data migration for an information handling system

Systems and methods are provided that may be implemented to perform failure analysis and/or self-healing of information handling system storage. In one example, an information handling system may perform self-recovery actions to self-heal system storage issues when there is a OS boot failure due to a failure to detect a system storage drive by determining one or more possible recovery actions based on a current system storage drive status retrieved by an embedded controller (EC) or other programmable integrated circuit of the information handling system. In another example, manufacturing quality control analysis may be performed on boot failure information that is collected at a remote server from multiple failed information handling systems.

Systems and methods for self-healing and/or failure analysis of information handling system storage

A host memory buffer is configured as a write cache for prioritizing read operations. When a peripheral device (such as a solid-state drive) receives a mixture of read requests and write requests, the write requests may be suspended or deferred to first execute the read requests. The write requests may be cached to the host memory buffer, thus allowing the peripheral device to process the read requests for relatively immediate response. Once the read requests are completed, the peripheral device may begin executing a queue of the write requests stored to the host memory buffer. This caching strategy results in a thirty percent (30%) improvement in drive performance.

Information handling system having improved host memory buffer for input/output requests

An information handling system includes a memory array and a memory controller. The memory array stores data within the information handling system. The memory controller writes the data to the memory array. The memory controller also determines whether a temperature of the memory array is above a threshold temperature. The memory controller tags a plurality of memory locations within the memory array written with data while the temperature is above the threshold temperature. While a refresh operation is being executed, the memory controller determines whether the temperature of the memory array is below the threshold temperature. In response to the temperature of the memory array being below the threshold temperature and while the refresh operation is being executed, the memory controller rewrites the data in the tagged memory locations within the memory array.

System and method for refreshing data for integrity protection at a thermal excursion event

A method and information handling system, including a solid state drive (SSD) memory device having NAND flash memory and an SSD controller to execute instructions of an SSD adaptive profiling engine for random access memory (RAM) cache optimization, are disclosed. The SSD controller is configured to cache a partial flash translation layer (FTL) table in RAM including look-up addresses corresponding to LBA segments in the NAND flash memory having access counts reflecting SSD I/O operations. The SSD controller is further configured to detect an outlier LBA segment having look-up addresses in the cached, partial FTL table, wherein the outlier LBA segment has an I/O access counts at a threshold level below the mean of access counts of other LBA segments represented in the partial FTL table, and to evict the LBA segment look-up address of the outlier LBA segment from the cached portion of the FTL table. The partial FTL table may expanded to accommodate additional look-up addresses when no outlier LBA segments exist. A portion of the RAM not used for caching the partial FTL table may be used as a prefetch cache for I/O access operations.

System and method for adaptive optimization for performance in solid state drives based on segment access frequency

Methods and systems are provided for initializing a host IHS (Information Handling System) that includes an SSD (solid state storage device) connected using PCIe (Peripheral Component Interconnect Express). The SSD detects the transfer of boot data from the host to the persistent storage of the SSD. The SSD marks the detected boot data for pre-fetching. When the host is booted, memory is allocated for the PCIe connection. During the resulting delay, the SSD pre-fetches the marked boot data from persistent storage to a portion of a volatile memory used by the SSD for storing a mapping of the boot data in persistent storage. Upon configuring the PCIe connection, the SSD is provides pre-fetched boot data to the host immediately, thus improving boot times. In certain scenarios, the SSD pre-fetches successive portions of the boot data and provides each pre-fetched portion of the boot data to the host.

Booting of IHS from SSD using PCIe

Methods and systems that may be implemented for managing data migration from relatively higher performance and higher endurance solid state non-volatile memory media to relatively lower performance and lower endurance solid state non-volatile memory media. The disclosed methods and systems may be implemented to reduce write amplification that occurs to solid state non-volatile memory media of a memory device by using frequency of LBA update as a parameter for controlling and optimizing data eviction from a relatively higher performance and higher endurance input buffer section in the receiving front of a memory device to a relatively lower performance and lower endurance main memory section of the same memory device.

Methods and systems for managing data migration in solid state non-volatile memory

A method and information handling system and having a solid state drive (SSD) memory device including NAND flash memory with an SSD controller to execute instructions of an SSD adaptive profiling engine for RAM cache optimization and configured to cache a partial FTL table in RAM including look-up addresses corresponding to LBA segments in the NAND flash memory having access counts reflecting SSD I/O operations. The method and system further configured to determine whether the SSD memory device operation is write intensive (or read intensive) from assessment of stored read access counts and write access counts and further determine whether to load a partial FTL table into RAM cache and use remaining unoccupied RAM space for a data cache to enhance the SSD memory device operations.

Growing community of inventors

Gwangju-si, South Korea

Young Hwan Jang