Hybrid Storage Mapping for Random Write Consolidation

Solution Overview

Problem

Current data storage systems face inefficiencies with sequential and semi-sequential storage media, which are slow and inefficient for random data writes, while solid state drives (SSDs) offer high speed but are costly and low in capacity, necessitating a solution for mapping random data to sequential storage effectively.

Innovation Solution

A data storage system comprising a first SSD layer for initial data writes, a second sequential or semi-sequential storage layer, and a data organizer that groups data based on attributes and policies to optimize storage and movement between layers, leveraging the speed of SSDs and capacity of sequential storage.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If sequential or semi-sequential storage media are used, then storage cost is reduced and storage density is increased, but access speed decreases and IOPS decreases

Engineering Contradiction:

Improvestorage capacityVSAvoidaccess speed

Core Design Contradiction:

Quantity of substanceVSSpeed

Solution Approach 1:

The storage system is segmented into multiple layers: a first storage layer using random-access devices (SSDs) for fast writes, and a second storage layer using sequential-access devices for high-capacity storage. This segmentation allows each layer to optimize for its specific function, resolving the contradiction between speed and capacity.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The first storage layer acts as an intermediary buffer between the host system and the second storage layer. Random writes are initially directed to the first layer, which then consolidates and sequentially transfers data to the second layer, mediating between random access requirements and sequential storage efficiency.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Speed

If SSD storage is used, then access speed increases and IOPS increases, but storage cost increases and storage capacity decreases

Engineering Contradiction:

Improveaccess speedVSAvoidstorage capacity

Core Design Contradiction:

SpeedVSQuantity of substance

Solution Approach 1:

The storage system is segmented into multiple layers: a first storage layer using random-access devices (SSDs) for fast writes, and a second storage layer using sequential-access devices for high-capacity storage. This segmentation allows each layer to optimize for its specific function, resolving the contradiction between speed and capacity.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system transitions from a single-dimension storage approach to a multi-layered hierarchical structure, adding the dimension of storage layering. This allows simultaneous optimization for both speed (first layer) and capacity (second layer) by operating in different storage dimensions.

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

3Adaptability or versatility

If random data writes are performed on sequential storage media, then data flexibility increases, but write efficiency decreases and latency increases

Engineering Contradiction:

Improvedata flexibilityVSAvoidwrite efficiency

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

The storage system is segmented into multiple layers: a first storage layer using random-access devices (SSDs) for fast writes, and a second storage layer using sequential-access devices for high-capacity storage. This segmentation allows each layer to optimize for its specific function, resolving the contradiction between speed and capacity.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Data is preliminarily written to the first storage layer in random fashion, allowing immediate flexibility and fast writes. The consolidation and sequential transfer to the second layer is performed as a preliminary organized action, maintaining write efficiency while preserving data flexibility.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS11531491B2Systems and methods for random to sequential storage mapping

Publication Date: 2022.12.20 ALTER DOMUS (US) LLC AS AGENT FOR THE SECURED PARTIES

AI summary

A data storage system includes a first storage layer, a second storage layer, an I/O manager, and a data organizer. The first storage layer utilizes a first type of data storage device. The first storage layer includes (i) a first data bucket that includes first data having a first data attribute, the first data bucket including a first data limit, and (ii) a second data bucket. The second storage layer utilizes a second type of data storage device. The I/O manager receives a data write request from the user and directs the data write request to the first storage layer. The data organizer (a) determines whether data in the data write request has the first data attribute; and (b) stores the data in the data write request in at least one of the first data bucket and the second data bucket if the data in the data write request has the first data attribute. When a volume of data in the first data bucket reaches the first data limit, the data organizer moves the volume of data in the first data bucket from the first storage layer to the second storage layer.