Hard Disk Controller Offloading Server IO Pressure via In-Place Data Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In data processing systems, servers often become performance bottlenecks due to high input/output (IO) and processor processing pressures when accessing and processing data from hard disks, as they typically require data to be read into memory for operations like querying, modifying, or deleting.
Innovation Solution
A data processing method where a hard disk receives call instructions with function identifiers and operation addresses, allowing it to perform operations directly on data using stored functions, reducing data exchange with the server and offloading processing tasks, such as querying, modifying, or deleting data, through interfaces like NVMe, thereby reducing IO and processor pressures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If data is read from hard disk to server memory for processing, then data processing operations can be performed, but input/output pressure and processor pressure on the server increase
Solution Approach 1:
The patent extracts the data processing function from the server and relocates it to the hard disk. The hard disk controller executes processing instructions directly on the hard disk, separating the processing workload from the server's IO and processor, thereby reducing server pressure while maintaining data processing capability
Solution Approach 2:
The patent introduces a hard disk controller as an intermediary between the server and the hard disk. The controller receives processing instructions from the server, executes them directly on the hard disk, and returns results, acting as a mediator that offloads processing tasks from the server without requiring data transfer to server memory
2Ease of operation
If data is transferred between server and hard disk for processing, then data operations can be completed, but the amount of data exchanged increases
Solution Approach 1:
The patent extracts only the necessary processing instructions from the server to the hard disk controller, leaving the actual data processing to occur in-place on the hard disk. This extraction approach minimizes data transfer by moving only control information rather than bulk data
Solution Approach 2:
The patent uses a copying approach where processing instructions are copied from the server to the hard disk controller, but the actual data remains on the hard disk and is processed in-place. This avoids the need to copy large amounts of data to server memory, reducing the quantity of data exchanged
Data Source
AI summary
Embodiments of the present invention disclose a data processing solution. In this solution, a hard disk receives a call instruction sent by a server, where the call instruction includes a function identifier of a to-be-called function and an operation address; and the hard disk calls the function in the hard disk based on the function identifier, and performs, based on the function, an operation on data corresponding to the operation address.