Hardware Flow Classification for Storage Services

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing software-only solutions for flow classification in network storage systems disrupt storage server operations by adding unpredictable processing overhead, especially in high-end systems with increasing line rates and traffic, making it challenging to meet Service Level Agreements (SLAs) and Quality of Service (QoS) constraints.

Innovation Solution

A hardware-based storage flow classification system utilizing ternary content addressable memory (TCAM) for matching operations, which classifies information elements like packets based on attributes and performs actions according to SLA or QoS parameters, including identifying storage service customers, access protocols, and target storage entities.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If software-only solutions are used for flow classification, then the system can be implemented with standard processing components, but the storage server system is disrupted by adding additional processing overhead along the execution path

Engineering Contradiction:

Improveimplementation easeVSAvoidprocessing throughput

Core Design Contradiction:

Ease of manufactureVSProductivity

Solution Approach 1:

The patent replaces software-based flow classification with a hardware-based system using Ternary Content Addressable Memory (TCAM). This substitution moves the classification function from the software processing layer to dedicated hardware circuitry, eliminating the processing overhead and disruption to the storage server system while maintaining implementation feasibility through standardized hardware components.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Device complexity

If software-only solutions are used for flow classification, then the system architecture remains simple, but the processing becomes unpredictable and cannot meet SLA or QoS constraints in high-end storage systems

Engineering Contradiction:

Improvesystem architecture complexityVSAvoidQoS guarantee

Core Design Contradiction:

Device complexityVSReliability

Solution Approach 1:

The patent substitutes software-based classification with hardware-based TCAM classification to achieve predictable processing times and reliable QoS guarantees. The hardware implementation provides deterministic performance that can meet SLA constraints, while the added complexity is confined to the classification subsystem rather than the entire system architecture.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Adaptability or versatility

If software-only solutions are used for flow classification, then existing processors can be utilized, but the processing overhead increases and disrupts the storage server system

Engineering Contradiction:

Improveprocessor compatibilityVSAvoidprocessing overhead

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The patent extracts the flow classification function from the main processor workflow and implements it in dedicated hardware using TCAM. This extraction removes the classification overhead from the processor's execution path, eliminating the disruption to the storage server system while allowing the processor to focus on its primary storage management functions.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The patent replaces software-based classification processing with hardware-based TCAM classification. This substitution eliminates the processing overhead associated with software interpretation and execution, providing fast, deterministic classification without disrupting the storage server system's processor resources.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

4Productivity

If hardware-based TCAM is used for flow classification, then processing becomes predictable and does not disrupt storage server operations, but the device complexity increases

Engineering Contradiction:

Improveclassification speedVSAvoidhardware complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent uses hardware-based TCAM to replace software classification, achieving predictable processing speeds that do not disrupt storage server operations. The increased device complexity is localized to the classification subsystem, while the overall system benefits from improved productivity and reliability.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS8407413B1Hardware flow classification for data storage services

Publication Date: 2013.03.26 NETAPP INC

AI summary

The techniques introduced here provide a system and method for hardware implemented storage service flow classification using content addressable memory. The techniques described here allow for classification and handling of storage service requests according to service level agreement (SLA) or quality of service (QoS) parameters without consuming valuable storage server resources.