Sequential-Write File System for Durable SMR Object Storage

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing storage technologies, particularly those using shingled magnetic recording (SMR), increase areal density by overlapping tracks without guard spaces, leading to reduced reliability due to increased sensitivity to errors and failures.

Innovation Solution

A durable file system that writes object indexing information across multiple zones on independently accessible storage devices, updating a working index in memory only after persisting this information in persistent storage, allowing for efficient recovery and error tolerance.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If shingled magnetic recording (SMR) technology is used to increase areal density by overlapping tracks, then storage capacity increases, but reliability decreases due to increased sensitivity to errors and failures

Engineering Contradiction:
Improvestorage capacityVSAvoiddevice reliability
Core Design Contradiction:
Quantity of substanceVSReliability

Solution Approach 1:

The patent applies preliminary action by writing indexing information to persistent storage before updating the working index in memory. This preparatory step ensures that if a failure occurs during memory updates, the system can recover using the pre-written indexing information from persistent storage, thereby maintaining reliability while using high-density SMR storage.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent implements beforehand cushioning by creating a protective mechanism where indexing information is persisted to storage media before memory updates complete. This cushioning layer protects against data loss from interruptions, allowing the system to tolerate failures that would otherwise compromise reliability in high-density storage environments.

Inventive Principle:
Principle #11Beforehand cushioning (Prior cushioning)

2Reliability

If indexing information is written to persistent storage before updating working index in memory, then durability and error tolerance improve, but write operation complexity increases

Engineering Contradiction:
ImprovedurabilityVSAvoidwrite operation complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments the write operation into distinct phases: first writing indexing information to persistent storage, then separately updating the working index in memory. This segmentation simplifies the complexity management by creating clear boundaries between operations, allowing each phase to be handled independently with appropriate error handling.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces an intermediary mechanism where indexing information serves as a bridge between the object data and the working index. By persisting this intermediary indexing information to storage before memory updates, the system mediates the complexity of coordinated updates across multiple components.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Reliability

If indexing information is persisted across multiple zones on independently accessible storage devices, then fault tolerance improves, but access time increases

Engineering Contradiction:
Improvefault toleranceVSAvoidaccess time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent segments indexing information across multiple zones on independently accessible storage devices, distributing the data burden across separate physical locations. This segmentation enables parallel access operations and isolates failures to specific zones, improving fault tolerance while managing access time through distributed architecture.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent transitions from a single-location storage model to a multi-zone distributed storage model, adding the dimension of spatial distribution. By organizing indexing information across multiple zones and devices, the system achieves fault tolerance through redundancy while maintaining access efficiency through parallel operation capabilities.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Data Source

PatentUS12468467B2Sequential write based durable file system
Publication Date: 2025.11.11 NETAPP INC
  • US12468467B2 patent drawing
  • US12468467B2 patent drawing
  • US12468467B2 patent drawing

AI summary

A durable file system has been designed for storage devices that do not support write in place and/or that are susceptible to errors or failures. The durable file system also facilitates organization and access of large objects (e.g., gigabytes to terabytes in size). Regardless of whether target storage devices are configured with sequential write constraints, the durable file system writes object fragments across a set of sequences or ranges of storage units, such as logical blocks. The durable file system sequentially writes an object fragment into each storage unit sequence along with indexing information for the object fragments. In addition to writing the indexing information for the object fragments into the set of storage unit sequences, the durable file system updates the file system index with the object indexing information.