NIC Conflict Handling for Shared Storage Access Requests
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In shared storage systems, processor resources of storage nodes are occupied for conflict management when multiple users access the same volume, leading to inefficiencies.
Innovation Solution
A network interface card device processes write conflicts independently, avoiding processor involvement by using metadata and processing policies to manage access conflicts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If traditional data processing methods are used, then implementation complexity is low, but processing speed and efficiency are insufficient
Solution Approach 1:
The patent segments the data processing workflow into multiple parallel processing threads, where each thread independently processes different aspects of data validation, transformation, and enrichment. This parallelization increases processing speed while maintaining manageable complexity through modular design.
Solution Approach 2:
The patent introduces a multi-dimensional processing architecture that operates across multiple layers simultaneously - including data validation layer, transformation layer, enrichment layer, and routing layer. This dimensional expansion enables concurrent processing operations that significantly improve throughput without linearly increasing system complexity.
2Reliability
If data validation and processing are performed on all incoming data, then data quality is improved, but processing time increases
Solution Approach 1:
The patent implements selective validation and processing where only critical data fields undergo rigorous validation while less critical fields receive streamlined processing. This partial action approach maintains data quality for essential elements while reducing overall processing time through differentiated treatment of data elements.
Solution Approach 2:
The patent performs preliminary data validation and filtering at the ingress point before data enters the main processing pipeline. By pre-validating data structure and format, the system prevents unnecessary processing of malformed data and reduces the validation burden on downstream processing stages.
3Productivity
If multiple processing threads are used, then processing efficiency is improved, but system complexity increases
Solution Approach 1:
The patent designs universal processing templates and standardized data structures that can be reused across multiple processing threads. This multi-functionality allows the same validation rules, transformation logic, and enrichment templates to serve multiple threads, reducing overall system complexity while maintaining high productivity through parallel execution.
Solution Approach 2:
The patent dynamically adjusts processing parameters such as thread priority, batch size, and validation depth based on data characteristics and system load. This parameter optimization enables the system to maintain high efficiency across varying conditions while avoiding the need for complex static architecture designs.
Data Source
Figure 1~2
Figure 3
Figure 4~6
AI summary
Embodiments of this application disclose a data processing method, which is used in a storage system. The method in embodiments of this application includes: A network interface card device receives a first access request of a first client, where the first access request carries an access address; the network interface card device detects whether the first access request has a conflict; and when the network interface card device detects that the first access request has a conflict, the network interface card device processes the conflict according to a processing policy. In embodiments of this application, when a conflict occurs, the network interface card device processes the conflict according to the processing policy. This avoids conflict management performed by a processor of a storage node, and saves a resource of the processor of the storage node.