CXL Storage Cluster Caching for Sudden Power-Off Recovery

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Sudden power off (SPO) situations in storage devices can lead to data loss due to the limited capacity of batteries used for additional power supply, especially when moving and storing data from volatile memory to another storage space, which increases with larger memory sizes.

Innovation Solution

A computing system utilizing a Compute Express Link (CXL) storage cluster with a switch providing an interface between CXL storage devices, allowing data stored in a volatile memory to be transferred to another storage device upon SPO, ensuring data caching and preservation through a CXL memory controller and switch configuration.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If the size of volatile memory is increased to store more data, then the amount of data that can be moved and stored increases, but the capacity limitation of battery-powered additional power supply becomes more severe

Engineering Contradiction:
Improveamount of dataVSAvoidpower supply capacity
Core Design Contradiction:
Quantity of substanceVSUse of energy by moving object

Solution Approach 1:

The patent combines multiple storage devices into a storage cluster where data can be distributed across multiple nodes. When one device experiences SPO, the data migration workload is shared across the cluster rather than relying on a single battery-powered device, effectively pooling power supply capacity to handle larger data volumes.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent divides the storage system into multiple independent storage devices within a cluster, each with its own power supply. This segmentation allows data to be distributed across multiple devices, so that the power supply burden is divided among multiple batteries rather than concentrated in one, enabling larger total data capacity to be protected.

Inventive Principle:
Principle #1Segmentation

2Reliability

If data is moved from volatile memory to another storage device during SPO, then data loss is prevented, but system complexity increases due to multiple storage devices and coordination requirements

Engineering Contradiction:
Improvedata loss preventionVSAvoidsystem complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent introduces a storage cluster manager as an intermediary that coordinates data migration during SPO events. This centralized controller simplifies the complexity by providing a single point of decision-making for data redistribution, managing the migration process across multiple devices without requiring complex peer-to-peer coordination between all devices.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The storage cluster is designed with universal interfaces and protocols (CXL) that allow any storage device to potentially take over data from any other device in the cluster. This multi-functionality reduces complexity by using standardized mechanisms rather than device-specific custom solutions, making the system more manageable despite having multiple devices.

Inventive Principle:
Principle #6Universality (Multi-functionality)

3Device complexity

If a single battery is used for additional power supply during SPO, then the system remains simple, but the capacity to move and store large amounts of data is limited

Engineering Contradiction:
Improvepower supply structureVSAvoiddata migration capacity
Core Design Contradiction:
Device complexityVSQuantity of substance

Solution Approach 1:

The patent merges the power supply resources of multiple storage devices into a collective pool. Instead of relying on a single battery, the system combines the auxiliary power capacity of all cluster members, enabling sufficient energy to migrate larger volumes of data while maintaining relatively simple individual device designs.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent transitions from a single-device vertical power supply architecture to a multi-device horizontal power supply architecture. By distributing power resources across multiple devices in a cluster, the system gains increased total power capacity for data migration without significantly increasing the complexity of individual device power management.

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

Data Source

PatentUS20250306772A1Computing system and operating method thereof
Publication Date: 2025.10.02 SAMSUNG ELECTRONICS CO LTD
  • US20250306772A1 patent drawing
  • US20250306772A1 patent drawing
  • US20250306772A1 patent drawing

AI summary

Computing system and operating method thereof are provided. The computing system comprises a storage cluster which includes at least one storage devices, and a switch which is configured to provide an interface between the storage devices included in the storage cluster, in which the storage cluster includes a first storage device and a second storage device, the first storage device includes a first storage controller, a first non-volatile memory which is controlled by the first storage controller, and a first volatile memory which includes a first memory region and a second memory region, in which the first storage device is configured to provide first data stored in the first memory region to the second storage device through the switch, in response to power not being supplied at the first storage device, and the first data is caching data.