Storage Controller IO Request Scheduling via Multi-Core Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing storage controller systems have a low IOPS fulfillment rate due to limited processing speed and inefficiencies in scheduling IO requests across different storage units, leading to difficulties in meeting Quality of Service (QoS) parameters.
Innovation Solution
A storage controller architecture with multiple cores, including distribution, ranking, and request processing cores, uses a shared processing ranking index to prioritize and schedule IO requests based on IOPS parameters, improving processing efficiency and accuracy by generating and updating processing ranking indexes for each storage unit.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the storage controller processes IO requests at a limited speed using existing scheduling methods, then the processing speed is maintained, but the IOPS fulfillment rate is low and QoS parameters cannot be met
Solution Approach 1:
The storage controller is divided into multiple independent cores (distribution core, ranking core, request processing core) that work in parallel. Each core handles specific scheduling tasks for different storage units, enabling concurrent processing of multiple IO requests and significantly improving IOPS fulfillment rate without requiring a single complex scheduling mechanism
Solution Approach 2:
The patent introduces a shared processing ranking index as a new scheduling parameter that dynamically changes based on IOPS parameters and request characteristics. This parameter enables the system to prioritize requests and adjust processing order in real-time, improving QoS parameter fulfillment while maintaining manageable scheduling complexity
2Productivity
If the storage controller uses a simple scheduling method, then the device complexity is low, but the IOPS fulfillment rate and QoS parameter compliance are poor
Solution Approach 1:
The distribution core pre-processes IO requests by distributing them to appropriate ranking cores based on storage unit identification. This preliminary action organizes requests before detailed scheduling and processing, reducing overall processing time and improving IOPS fulfillment rate through efficient request routing
Solution Approach 2:
Multiple ranking cores and request processing cores operate continuously and in parallel, ensuring that scheduling and processing actions are ongoing without idle periods. This continuous operation maximizes resource utilization and reduces average IO request processing time while maintaining high IOPS fulfillment rates
Data Source
Figure 1
Figure 2
Figure 3
AI summary
This application relates to the field of storage technologies, and discloses a storage controller. The storage controller includes a distribution core, a plurality of ranking cores, and a request processing core. The three types of cores are respectively configured to: distribute input/output IO requests to different ranking cores, generate a processing ranking index for each IO request, and process the IO request based on a value of the processing ranking index of the IO request, to flexibly schedule an IO request received by the storage controller.