Object Addressable Storage Fragment Routing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing storage systems face inefficiencies in managing fragments of objects across multiple tiers, particularly in content addressable storage systems where frequent modifications lead to excessive storage space consumption due to the creation of new versions for each change, and there is a need for a method to automatically determine the appropriate storage tier for fragments based on their characteristics and usage patterns.

Innovation Solution

Implementing a policy-based approach in a multi-tier object addressable storage system that accesses metadata and policies to select the appropriate storage tier for each fragment, allowing for transparent management of storage operations across different tiers, with policies defined by user input specifying metadata criteria and target tier capabilities, and applying hierarchical rules for tier selection.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If content addressable storage systems create new versions for each modification, then data integrity and version tracking are improved, but storage space consumption increases excessively

Engineering Contradiction:
Improvedata integrityVSAvoidstorage space consumption
Core Design Contradiction:
ReliabilityVSQuantity of substance

Solution Approach 1:

The system segments objects into fragments and stores them in a multi-tiered architecture. Frequently modified fragments are separated from static fragments, allowing the system to create new versions only for the modified portions while reusing unchanged fragments across versions, thereby reducing overall storage space consumption while maintaining data integrity.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

Different storage tiers are assigned different quality characteristics - transactional storage tiers handle frequently modified fragments with high write performance, while fixed content storage tiers handle static fragments with high storage efficiency. This local optimization allows the system to maintain reliability for modified portions while minimizing storage space for unchanged portions.

Inventive Principle:
Principle #3Local quality

2Device complexity

If all object fragments are stored in the same storage tier, then system complexity is reduced, but storage performance and cost efficiency deteriorate

Engineering Contradiction:
Improvesystem complexityVSAvoidstorage performance
Core Design Contradiction:
Device complexityVSProductivity

Solution Approach 1:

The system implements dynamic tier selection based on fragment characteristics and usage patterns. Fragments are automatically routed to appropriate storage tiers (transactional or fixed content) based on their modification frequency and access patterns, allowing the system to optimize performance without requiring manual configuration or complex user intervention.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The storage system automatically performs tier selection and fragment routing based on metadata and usage patterns without requiring external management. The system self-manages the distribution of fragments across tiers, reducing the operational complexity while maintaining high storage performance through automated optimization.

Inventive Principle:
Principle #25Self-service

3Productivity

If manual management of fragment storage locations is implemented, then storage optimization is improved, but operational complexity and time consumption increase

Engineering Contradiction:
Improvestorage optimizationVSAvoidtime consumption
Core Design Contradiction:
ProductivityVSLoss of time

Solution Approach 1:

The system automatically determines the appropriate storage tier for each fragment based on its metadata and usage patterns, eliminating the need for manual intervention. The automated tier selection process optimizes storage performance and space utilization without requiring user time or effort, thereby improving productivity without increasing time consumption.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system uses metadata and usage patterns as feedback to automatically adjust fragment placement decisions. By continuously monitoring access patterns and modification frequencies, the system dynamically optimizes fragment distribution across tiers without manual input, achieving storage optimization while minimizing operational time requirements.

Inventive Principle:
Principle #23Feedback

Data Source

PatentUS9424187B1Policy-based storage of portions of an object in a multi-tiered storage system
Publication Date: 2016.08.23 EMC IP HLDG CO LLC
  • US9424187B1 patent drawing
  • US9424187B1 patent drawing
  • US9424187B1 patent drawing

AI summary

Some embodiments are directed to an object addressable storage (OAS) system that stores a plurality of objects, a method for use in an OAS system and at least one non-transitory computer readable storage medium encoded with instruction that, when executed by a computer perform a method for use in an OAS system. A tiered storage environment comprising a plurality of storage tiers may be used. In response to a command, metadata associated with the object and a policy may be accessed. A storage tier may be selected for one or more portions of the object based on the policy and the metadata associated with the object.