Multi-Level Cache Concurrency Control for Storage Bandwidth
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional multi-level cache storage systems fail to dynamically adjust internal access requests based on the operating conditions of storage devices, leading to slow responses and increased contention for bandwidth, which results in ineffective user access and potential errors.
Innovation Solution
Implementing a concurrency number control mechanism in the multi-level cache device to dynamically manage access requests by determining a permitted concurrency number associated with the state of storage devices, allowing only requests that do not exceed this number to be executed, thereby reducing backend service requests and improving response times.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If the cache device continues to send internal access requests without dynamic control, then the cache device can maintain high access speed and respond quickly, but the storage device becomes overwhelmed and cannot respond to user access requests within effective time
Solution Approach 1:
The patent implements dynamic control of the concurrency number based on the operational state of storage devices. The controller monitors storage device states in real-time and adjusts the permitted concurrency number dynamically, transitioning from a static to a dynamic control mechanism that adapts to changing system conditions.
Solution Approach 2:
The controller obtains feedback information about the operational state of storage devices and uses this feedback to adjust the concurrency number. This closed-loop control ensures that the cache device's internal access requests are regulated based on actual storage device capacity to handle requests.
2Productivity
If the cache device processes all internal access requests, then data access speed is maintained, but bandwidth contention increases and system response time deteriorates
Solution Approach 1:
The patent changes the parameter of concurrency number from a fixed value to a dynamically adjustable parameter. By modifying this parameter based on storage device state, the system optimizes the balance between processing internal access requests efficiently and maintaining appropriate response times.
Data Source
AI summary
Embodiments include a method performed by a computing device. The method includes (a) receiving a plurality of access requests to access data of a multilayered storage system; (b) in response to determining that a first access request can be served from a top data layer, executing the first access request by accessing the top data layer; (c) in response to determining that a second access request cannot be served from the top data layer, determining whether a current concurrency number of the top data layer is less than a permitted concurrency number (PCN) of the top data layer; and (d) in response to determining that the current concurrency number of the top data layer is not less than the PCN, waiting until the current concurrency number of the top data layer is less than the PCN and then executing the second access request by accessing another data layer below the top layer.