Network Storage Message Segmentation for CPU Workload Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional network-attached storage devices are inefficient as they route all data messages through the CPU, leading to bottlenecks in processing power and communication bandwidth, making it difficult to scale storage capacity effectively.
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 tasks, 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 all data messages are routed through the CPU for processing, then centralized control and security monitoring are improved, but processing power requirements and communication bandwidth demands increase significantly
Solution Approach 1:
The patent segments message processing into two distinct paths: control messages go through the CPU for centralized security monitoring, while data messages bypass the CPU for direct storage access. This segmentation resolves the contradiction by allowing centralized control for security without overloading the CPU with data processing tasks.
Solution Approach 2:
The patent introduces a dedicated data processing path as an intermediary between network requests and storage operations. This intermediary path handles data messages independently of the CPU, enabling efficient data transfer without increasing CPU processing power requirements.
2Device complexity
If all messages pass through the CPU, then centralized management is simplified, but communication bandwidth requirements increase
Solution Approach 1:
The patent divides communication into control channel and data channel. Control messages with management information traverse the CPU over the network, while data messages use a dedicated direct path between storage and client. This reduces overall communication bandwidth consumption by eliminating redundant data transmissions through the CPU.
3Quantity of substance
If storage capacity is scaled up by adding more storage units, then storage capacity increases, but the processing device becomes overwhelmed
Solution Approach 1:
The patent segments processing responsibilities so that each storage unit has its own dedicated data processing path independent of the central CPU. This allows storage capacity to be scaled by adding more units without proportionally increasing CPU workload, as each unit handles its own data messages directly.
Solution Approach 2:
The patent implements partial processing at the storage unit level, where data messages are processed locally without requiring full CPU intervention. This partial action approach enables scaling beyond what a single CPU could handle while maintaining centralized control for critical functions.
Data Source
AI summary
A storage product manufactured as a computer component to facilitate network storage services. The storage product has a bus connector, a network interface, and a local storage device. A message selection configuration can be written into the storage product to control separation of incoming messages received in the network interface into first messages and third messages. The first messages are sent through the bus connector for processing by a local host system to generate second messages. The second messages and the third messages are sent to the local storage device. The local storage device processes the second messages and the third messages to implement the network storage services.