Network-Ready Storage Message Routing for CPU Bottleneck
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional network-attached storage devices are inefficient due to the CPU bottleneck in processing data messages, leading to high power consumption and communication bandwidth requirements, which limits the scalability of storage capacity.
Innovation Solution
Implementing separate processing paths for control messages and data messages, where control messages are routed through the processing device for administrative and management operations, while data messages are directly communicated between the storage device and the storage client without going through the processing device, reducing the workload on the CPU and improving efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If data messages are processed through the CPU in conventional network-attached storage devices, then administrative control and security management are maintained, but power consumption increases and processing efficiency decreases
Solution Approach 1:
The patent segments message processing into two distinct paths: control messages are routed through the CPU for administrative processing, while data messages are routed directly between the storage device and network interface. This segmentation allows the CPU to focus only on control functions, reducing its workload and power consumption while maintaining administrative control over the storage system.
Solution Approach 2:
The patent introduces a message routing mechanism that acts as an intermediary to direct different types of messages to appropriate processing paths. The router determines whether each message is a control message or data message and routes it accordingly, enabling the system to maintain security and control without requiring the CPU to process all messages.
2Reliability
If all messages are processed through the CPU, then centralized control is maintained, but communication bandwidth requirements increase
Solution Approach 1:
The patent divides message traffic into control messages and data messages, routing them through different paths. Control messages traverse the CPU while data messages bypass it, flowing directly between the storage device and network interface. This segmentation reduces the communication bandwidth burden on the CPU and its connected bus, allowing centralized control to be maintained with lower bandwidth requirements.
3Adaptability or versatility
If the CPU processes all storage operations, then unified management is achieved, but scalability of storage capacity is limited
Solution Approach 1:
The patent implements a segmented processing architecture where the CPU handles only control messages related to unified management and configuration, while data messages are processed independently by the storage device. This allows the system to scale storage capacity by adding more storage devices without proportionally increasing CPU processing requirements, as each storage device can handle its own data operations autonomously.
Solution Approach 2:
The storage device is empowered to process data messages independently without CPU intervention, effectively making it self-service for data operations. The device can autonomously handle read/write requests, manage its own buffer memory, and communicate directly with the network interface, reducing the CPU's burden and enabling easier scaling of storage capacity.
4Productivity
If control messages are processed separately from data messages, then processing efficiency improves, but system complexity increases
Solution Approach 1:
The patent introduces a message routing mechanism that mediates between the network interface and the CPU/storage device. The router examines incoming messages and directs them to the appropriate destination based on their type. While this adds a routing component, it simplifies the overall system architecture by providing a clear separation of concerns and enabling efficient parallel processing paths.
Data Source
AI summary
A storage product having a network interface and a bus switch connecting a random-access memory, a processing device, and a storage device, and connected via an external computer bus to an external processor. The storage product can receive via the network interface first messages and second messages for network storage services. The bus switch is operable to provide a first bus between the processing device and the random-access memory to buffer the first messages into the random-access memory, a second bus between the processing device and the storage device to buffer the second messages into a local memory of the storage device, and a third bus between the processor and the random-access memory to retrieve the first messages from the random-access memory and generate third messages. The storage device is configured to process the second and third messages to provide network storage services.