Interposer Card Storage Nodes for Failure Blast Radius Containment

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing server designs with standard hard disk drives suffer from wasted space in the server chassis, leading to inadequate computing or storage capacity, and centralized controllers increase the risk of unrecoverable failures affecting multiple drives.

Innovation Solution

Implementing interposer cards with individual servers for each mass storage device, eliminating wasted space and reducing failure impact by creating independent logical nodes within the same chassis, allowing for component replacement without affecting others.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If standard off-the-shelf hard disk drives are used in server designs, then cost-effectiveness is improved, but storage density and space utilization deteriorate due to wasted space in server chassis

Engineering Contradiction:
Improvecost-effectivenessVSAvoidstorage density
Core Design Contradiction:
Ease of manufactureVSQuantity of substance

Solution Approach 1:

The system segments the server architecture by implementing individual servers for each mass storage device using interposer cards. Each interposer card creates a separate logical node that independently manages its associated storage device, eliminating the traditional centralized server structure and thereby eliminating wasted space while maintaining cost-effectiveness through modular standard components.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

Interposer cards serve as intermediary components between the backplane and mass storage devices. These interposer cards implement individual servers that mediate between the storage devices and the network, enabling standard off-the-shelf drives to be utilized efficiently without requiring additional chassis space for centralized controllers.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Device complexity

If a centralized controller is used to control accesses to hard disk drives, then device complexity is reduced, but reliability deteriorates because a controller failure causes all hard disk drives to be unreachable

Engineering Contradiction:
Improvecontroller architectureVSAvoidsystem availability
Core Design Contradiction:
Device complexityVSReliability

Solution Approach 1:

The centralized controller architecture is segmented into multiple distributed controllers, with each interposer card implementing its own server and controller functionality. This segmentation isolates failures to individual logical nodes, so that a failure in one controller affects only its associated mass storage device rather than rendering all drives unreachable.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system changes the architectural parameter from centralized control to distributed control across multiple logical nodes. Each interposer card operates as an independent server with its own control logic, fundamentally changing the system's reliability characteristics by eliminating the single point of failure inherent in centralized controller designs.

Inventive Principle:
Principle #35Parameter changes

3Productivity

If multiple hard disk drives are arranged in a traditional server chassis, then computing capacity is improved, but maintenance efficiency deteriorates because component replacement affects the entire system

Engineering Contradiction:
Improvecomputing capacityVSAvoidmaintenance efficiency
Core Design Contradiction:
ProductivityVSEase of repair

Solution Approach 1:

The system segments the server into independent logical nodes where each interposer card and its associated mass storage device form an isolated unit. This segmentation enables maintenance personnel to replace individual components without affecting other parts of the system, as each logical node operates independently through its own server implementation.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The modular logical node architecture enables efficient discarding and recovery of individual components. When a mass storage device or interposer card fails, only that specific component needs to be replaced rather than the entire server system, minimizing downtime and maintaining computing capacity through parallel operation of unaffected logical nodes.

Inventive Principle:
Principle #34Discarding and recovering

Data Source

PatentUS12482503B2Limited blast radius storage server system
Publication Date: 2025.11.25 AMAZON TECH INC
  • US12482503B2 patent drawing
  • US12482503B2 patent drawing
  • US12482503B2 patent drawing

AI summary

A device includes an interposer card that includes a processor, such as a system on a chip (SoC), and memory devices. The interposer card mounts to a mass storage device and has a shape that corresponds to a size of an end of the mass storage device to which the interposer card is mounted. The SoC of the interposer card is configured to implement an individual server for the mass storage device to which the interposer card is mounted. In some embodiments, a data storage system includes multiple mass storage devices mounted in a chassis and coupled to one or more backplanes, wherein interposer cards are connected between the mass storage devices and the one or more backplanes.