HDD Metadata Storage in NAND Flash via Adaptive Data Shaping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The increasing track densities in hard disk drives (HDDs) require sophisticated algorithms for reliable data storage and retrieval, leading to high costs and power consumption due to the large size of metadata, which is often stored in volatile memory like DRAM.
Innovation Solution
A data storage device with a controller that identifies patterns and structures of metadata, performs data shaping, content-aware decoding, adaptive data trimming, and adaptive metablock sizing, and writes tailored metadata to non-volatile memory, optimizing storage in SLC or TLC memory based on endurance and speed requirements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If metadata is stored in DRAM to enable reliable data storage and retrieval, then data access speed and reliability are improved, but cost and power consumption increase
Solution Approach 1:
The patent stores metadata in non-volatile memory (NVM) instead of volatile DRAM, using a storage medium that retains data without continuous power. This replaces the expensive, high-power DRAM with a cheaper, lower-power NVM solution, accepting that NVM has different characteristics (slower write speed) that are managed through selective updating of only changed metadata blocks.
Solution Approach 2:
The patent changes the storage medium parameter from volatile DRAM to non-volatile memory, fundamentally altering the power consumption and reliability characteristics. This parameter change enables metadata to persist without power while reducing overall system power requirements, as NVM does not require continuous refresh operations like DRAM.
2Quantity of substance
If track density is increased to reduce HDD cost, then storage capacity improves, but metadata size and complexity increase
Solution Approach 1:
The patent extracts only the essential metadata information needed for high track density operation and stores it in NVM, rather than storing all possible metadata in DRAM. By selectively updating and storing only changed metadata blocks, the system reduces the effective metadata management complexity while supporting increased track density.
3Quantity of substance
If larger DRAM is used to store metadata, then metadata storage capacity increases, but cost and power consumption are driven up
Solution Approach 1:
The patent replaces expensive DRAM with cheaper non-volatile memory for metadata storage. NVM provides sufficient storage capacity for metadata at a lower cost per gigabyte, eliminating the need for large amounts of expensive DRAM while maintaining adequate metadata storage capabilities.
4Use of energy by moving object
If metadata is stored in non-volatile memory, then cost and power consumption are reduced, but write speed decreases
Solution Approach 1:
The patent performs partial writes to NVM by updating only the metadata blocks that have changed, rather than rewriting entire metadata structures. This selective updating approach reduces the total write volume to NVM, mitigating the slower write speed characteristic of non-volatile memory while maintaining the power and cost benefits.
Solution Approach 2:
The patent performs metadata updates in DRAM first, then selectively writes only the changed blocks to NVM. This preliminary processing in faster DRAM allows the system to prepare data for NVM writing, reducing the frequency and volume of NVM write operations and thus mitigating the write speed limitation.
Data Source
AI summary
A data storage device includes a hard disk drive coupled to a printed circuit board (PCB), a volatile memory device coupled to the PCB, a non-volatile memory device coupled to the PCB, and a controller coupled to the PCB, such that the controller is in communication with the hard disk drive, the volatile memory device, and the non-volatile memory device. The controller is configured to identify patterns and/or structures of metadata for the hard disk drive, perform one or more of the following to the metadata to tailor the metadata: data shaping, content aware decoding, adaptive data trimming, and/or adaptive metablock sizing, and write the tailored metadata to the non-volatile memory device. The metadata is at least one of repeatable run out metadata, positioning error signal metadata, adjacent track interference metadata, and/or emergency power off metadata.