Storage Controller Centralized Encryption for Mirrored Data

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing storage systems require multiple encryptions of data for mirrored storage, leading to increased computational load and inefficiency, as both primary and backup storage nodes encrypt data separately and again for transmission.

Innovation Solution

A storage platform that performs a single encryption for both data-at-rest and secure transmission using a shared encryption key, employing Authenticated Encryption with Associated Data (AEAD) to encrypt data once and separately encrypt metadata, reducing computational burden and improving performance.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If separate encryption is performed at each storage node for mirrored storage, then data security is maintained, but computational load increases and system efficiency decreases

Engineering Contradiction:
Improvedata securityVSAvoidsystem efficiency
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent merges the encryption functions across multiple storage nodes by designating one node as the encryption owner that performs centralized encryption for all mirrored copies. Instead of each node independently encrypting data, the encryption operations are consolidated into a single responsible node, reducing redundant computational efforts while maintaining security through coordinated key management among all nodes.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The encryption key management system is designed to be universal across all storage nodes. A single encryption key generated by the encryption owner is distributed to all other nodes, enabling them to decrypt and verify data without performing independent encryption. This universal key management approach allows the system to maintain security protocols while eliminating redundant encryption computations at each node.

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

2Reliability

If multiple encryptions are performed for transmission and storage, then data confidentiality is enhanced, but computational overhead increases

Engineering Contradiction:
Improvedata confidentialityVSAvoidcomputational overhead
Core Design Contradiction:
ReliabilityVSUse of energy by moving object

Solution Approach 1:

The patent combines transmission encryption and storage encryption into a single encryption operation performed by the encryption owner node. The encrypted data is then transmitted to other nodes and stored without requiring additional encryption layers, as the initial encryption already provides both transmission and storage security. This merging eliminates redundant encryption computations while preserving confidentiality through secure key distribution.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The encryption is performed in advance by the encryption owner node before data transmission and storage operations. By completing the encryption operation preliminarily, the system avoids the need for repeated encryption during transmission and storage phases. The pre-encrypted data can be securely transmitted and stored using the same encryption key, reducing computational overhead while maintaining confidentiality throughout the data lifecycle.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS20240129122A1Efficient encryption in storage providing data-at-rest encryption and data mirroring
Publication Date: 2024.04.18 NVIDIA CORP
  • US20240129122A1 patent drawing
  • US20240129122A1 patent drawing
  • US20240129122A1 patent drawing

AI summary

A storage platform (100) with secured mirroring of data and data-at-rest encryption reduces repetitive encryption of data. A storage controller (120) is responsible for both encryption data-at-rest encryption and data encryption for transmissions to backup storage, allowing encryption to be only performed once within the storage platform (100). This reduces the amount of computation the storage platform (100) must perform, improving overall system performance.