Flash memory reliability evaluation and failure early warning method based on storage channel noise spectrum characteristics

A technology of channel noise and spectrum characteristics, applied in the field of solid-state storage, can solve the problems of difficult data recovery, data loss, reliability differences of flash memory blocks, etc., to achieve the effect of sensitive data monitoring and simple data acquisition methods

Active Publication Date: 2021-08-27
HARBIN INST OF TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, unlike mechanical storage devices, solid-state storage devices are frequently damaged, and once data is lost, it is difficult to recover. Therefore, it is of great significance to monitor the working status and abnormal status warning of flash memory devices.
The current mainstream method is to limit the number of P / E cycles of flash memory, but the reliability of different flash memory blocks is different, and the P / E tolerance is also very different
When the flash memory controller strictly limits the number of P / E cycles, it will cause waste of storage resources, but relaxing the limit on the number of P / E cycles will cause data loss due to flash memory failure
[0003] The current solid-state memory mainly uses NAND Flash as the storage core, and there is a greater risk of accidental failure due to factors such as Program / Erase (P / E) wear and tear during use

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Flash memory reliability evaluation and failure early warning method based on storage channel noise spectrum characteristics
  • Flash memory reliability evaluation and failure early warning method based on storage channel noise spectrum characteristics
  • Flash memory reliability evaluation and failure early warning method based on storage channel noise spectrum characteristics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] Next, the technical solutions in the embodiments of the present invention will be described in conjunction with the accompanying drawings, which is apparent from the accompanying drawings, is apparent from the embodiments of the present invention, not all of the embodiments; EXEGITIONITION TECHNICAL OF THE INVENTION REFERENCE Embodiments obtained without making creative labor prevision are within the scope of the present invention.

[0039] A flash reliability assessment and failure warning method based on storage channel noise spectrum characteristics, mainly divided into noise assessment principle and noise data analysis

[0040] The method includes the following steps:

[0041] Step 1, start running, continuously read operations for the monitored flash memory, read raw bit error rate data, the original error rate data is noise data;

[0042] Step 2, the test data is time domain frequency domain conversion, obtain the flash channel noise spectrum characteristics;

[0043]...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides a flash memory reliability evaluation and failure early warning method based on storage channel noise spectrum characteristics. The method comprises the steps: carrying out the continuous reading operation of a monitored flash memory, and reading the original bit error rate data; performing time domain and frequency domain conversion on the test data to obtain flash memory channel noise spectrum features; and judging whether the power spectrum density of the flash memory channel noise spectrum feature exceeds a threshold value or not. According to the method, the noise data of the current storage channel can be quickly obtained, and the reliability of the current data of the flash memory can be evaluated and failure early warning can be performed by using noise spectrum features; and all-time internal data reliability monitoring and timely failure early warning can be realized on the premise of not influencing normal work of the flash memory, and the storage bit reliability of a threshold voltage overlapping region can be calculated by using a noise frequency entropy function to dynamically update a flash memory storage bit LLR table.

Description

Technical field [0001] The present invention belongs to the field of solid state storage, and in particular to a flash reliability assessment and failure early warning method based on a memory channel noise spectrum feature. Background technique [0002] Solid State Drives (SSDS) has the advantages of fast read / write speed, low power consumption, strong earthquake resistance, and the excellent characteristics of SSDS have gradually replaced traditional mechanical rotary disks, which is currently widely used in embedded and consumer electronics. Wait mobile storage device. Unlike mechanical storage equipment, the solid storage device is damaged and the data is high. Once the data is lost, it is difficult to recover, so it is of great significance for the operational state monitoring and abnormal state warning of flash devices. At present, the mainstream method is to limit the number of flash P / E periods, but there are differences in reliability of different flash blocks, and P...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G11C29/50
CPCG11C29/50
Inventor 魏德宝张京超冯骅朴哲龙乔立岩彭喜元
Owner HARBIN INST OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products