Mid-Level Mapping Block Repair in Data Storage Systems

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Large file systems face inefficiencies in metadata check and repair due to the global scope of corruption in mid-level mapping pages, leading to slow and unwieldy processes that require scanning millions of leaf pages, making it challenging to isolate and repair block-sharing related metadata corruptions efficiently.

Innovation Solution

The technique involves maintaining additional metadata in an on-disk mapping structure, using family IDs and volume logical offsets to limit the scope of scanning, and performing a two-pass process to identify and prune leaf pages associated with non-corrupted mid-level pages, creating a replacement mid-level page with pointers to the remaining leaf pages, and incorporating it into the indirect addressing structure.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a global scan of all leaf pages is performed to repair corrupted mid-level mapping pages, then completeness of repair is improved, but processing time and system downtime increase significantly

Engineering Contradiction:
Improvecompleteness of repairVSAvoidsystem downtime
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent segments the global leaf page scan into family-specific subsets by organizing leaf pages according to family IDs stored in mid-level mapping pages. Instead of scanning all leaf pages globally, the system divides the search space into manageable segments corresponding to specific storage object families, allowing parallel or selective processing that reduces overall repair time while maintaining completeness.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies local quality by making the repair process adaptive to the specific corruption scenario. The system determines which family groups are affected by the corruption and focuses repair efforts only on those local segments. This localized approach maintains high repair completeness for affected areas while avoiding unnecessary processing of unaffected portions, thereby reducing system downtime.

Inventive Principle:
Principle #3Local quality

2Reliability

If all leaf pages are scanned to ensure complete repair coverage, then repair thoroughness is improved, but processing resources and computational overhead increase

Engineering Contradiction:
Improverepair thoroughnessVSAvoidprocessing resources
Core Design Contradiction:
ReliabilityVSUse of energy by moving object

Solution Approach 1:

The patent segments the repair workload by organizing leaf pages into family-specific groups using family IDs. This segmentation allows the system to process only the relevant subset of leaf pages associated with corrupted mid-level mapping pages, rather than scanning the entire leaf page space. The segmentation maintains repair thoroughness for affected families while significantly reducing the computational resources required.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies partial action by performing repairs only on the specific family groups affected by corruption rather than conducting a complete global repair. The system identifies which mid-level mapping pages are corrupted, determines the associated family IDs, and limits the repair scope to only those families. This partial approach ensures thorough repair of affected areas while conserving processing resources by avoiding unnecessary work on unaffected portions.

Inventive Principle:
Principle #16Partial or excessive action

3Reliability

If the entire mapper is taken offline for metadata repair, then data consistency is improved, but system availability and usability deteriorate

Engineering Contradiction:
Improvedata consistencyVSAvoidsystem availability
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The patent segments the mapper into family-specific portions that can be repaired independently. By organizing metadata according to family IDs and enabling selective repair of individual family groups, the system can maintain availability of non-affected families while repairing corrupted ones. This segmentation allows the mapper to remain partially operational during repair operations, improving system availability while maintaining data consistency through targeted repairs.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies partial action by taking only the necessary portion of the mapper offline for repair rather than the entire system. The system identifies and isolates the specific family groups affected by corruption, then performs repairs only on those segments. This approach maintains data consistency for the affected portions while keeping the rest of the mapper available for normal operations, thereby improving system availability without compromising data integrity.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentUS10990486B2Data storage system with repair of mid-level mapping blocks of internal file system
Publication Date: 2021.04.27 EMC IP HLDG CO LLC
  • US10990486B2 patent drawing
  • US10990486B2 patent drawing
  • US10990486B2 patent drawing

AI summary

A technique for repairing an indirect addressing structure of a file system damaged by corruption of a mid-level mapping (MID) page includes scanning selected leaf pages to identify leaf pages associated with the corrupted MID page, then recreating the MID page by recreating pointers to the identified leaf pages. The scanning includes (1) based on an association of groups of leaf pages with corresponding sets of families of storage objects, scanning the leaf pages of only those groups of leaf pages associated with the family of storage objects for the corrupted MID page. The scanning further includes (2) performing a two-pass process including first identifying all leaf pages for the logical offset range of the corrupted MID page and then pruning those identified leaf pages that are reachable via non-corrupted MID pages, yielding the leaf pages for the corrupted MID page only, usable to recreate the corrupted MID page.