Dual Layer Cache Index Mirroring for Storage Bottlenecks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In dual-controller storage systems, the cache mirroring technology leads to significant mirror data transmission between controllers, resulting in slow data transmission and potential performance bottlenecks due to the need for consistent data storage across both controllers.
Innovation Solution
The method involves dividing the cache space of each node into upper-layer and lower-layer cache spaces, mirroring only the index information and not the actual data, and synchronizing the cache records across nodes to reduce unnecessary data transmission.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If cache mirroring technology is employed to protect cached data in dual-controller systems, then data reliability is improved, but data transmission speed deteriorates due to significant mirror data transmission between controllers
Solution Approach 1:
The cache space is segmented into two distinct layers: upper-layer cache space for storing IO requests and lower-layer cache space for storing cached data and index information. This segmentation allows different types of data to be stored in optimized locations, reducing unnecessary mirror data transmission while maintaining data reliability through selective mirroring of only index information between controllers.
Solution Approach 2:
The patent extracts only the essential index information from the lower-layer cache space for mirroring between controllers, rather than mirroring the entire cached data. This extraction principle significantly reduces the amount of data that needs to be transmitted between controllers while still enabling data recovery and access in case of controller failure, thus improving transmission speed without sacrificing reliability.
2Reliability
If consistent dirty data copies are stored in cache spaces of two controllers, then data protection is improved, but system performance deteriorates due to data transmission queuing at the NTB
Solution Approach 1:
The cache space is divided into upper-layer and lower-layer cache spaces, allowing different mirroring strategies for different data types. IO requests in the upper layer can be processed with standard mirroring, while the lower layer uses optimized index-only mirroring, reducing NTB queuing and improving overall system performance while maintaining data protection.
Solution Approach 2:
Only index information is extracted and mirrored between controllers for the lower-layer cache space, rather than mirroring complete data copies. This dramatically reduces the transmission burden on the NTB, eliminating queuing delays and improving system performance while still enabling data recovery through the index information.
Solution Approach 3:
The patent introduces a hierarchical dimension to cache management by creating upper and lower layers with different mirroring characteristics. This dimensional change allows the system to optimize for both data protection and performance by applying appropriate mirroring strategies at different hierarchical levels, reducing NTB bottlenecks.
3Stability of the object's composition
If the NTB of the dual-controller storage device is fixed, then structural stability is improved, but data transmission efficiency deteriorates due to queuing and waiting situations
Solution Approach 1:
The cache space segmentation into upper and lower layers allows different data types to be handled through optimized paths. This segmentation reduces the volume of data requiring NTB transmission, improving transmission efficiency while maintaining the fixed NTB structure and its inherent stability.
Solution Approach 2:
By extracting only index information for mirroring in the lower-layer cache space, the patent minimizes NTB transmission requirements. This extraction approach maintains the fixed NTB structure's stability while dramatically improving data transmission efficiency by reducing queuing and waiting situations.
Data Source
AI summary
The present application discloses a method and apparatus for reducing a mirror data transmission amount by a dual layer cache, and a device and a medium. The method includes: after receiving an input/output (IO) request, writing, by a first node, the IO request into a first upper-layer cache space; writing, by the first node, first cached data corresponding to the IO request into a first lower-layer cache space according to the IO request, and generating, by the first node, first index information for the first cached data; writing mirror data of the IO request into a second upper-layer cache space of a second node; and writing mirror data of the first index information into a second lower-layer cache space of the second node.