Multi-tier heat maps for storage temperature prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current storage systems face challenges in accurately predicting storage object temperatures due to the wide range of granularity in heat map representations, which can lead to inefficient memory usage and resource management, as they often require a fixed heat map algorithm that struggles to adapt to varying storage system resources.
Innovation Solution
Implementing multi-tier heat maps, where a first heat map with a sophisticated prediction technique is used for volume-level temperature prediction and a second heat map with a less sophisticated technique is used for leaf-page level prediction, allowing for more accurate temperature assessments while conserving processing and memory resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a heat map with fine granularity (leaf page level) is used to represent temperatures of storage objects, then temperature prediction accuracy is improved, but memory storage space consumption increases significantly
Solution Approach 1:
The patent divides the storage hierarchy into multiple levels (volume level and leaf page level), creating separate heat maps for each level. This segmentation allows the system to maintain fine-grained temperature tracking for individual leaf pages while also providing coarse-grained volume-level temperature summaries, thereby improving prediction accuracy without requiring all leaf page data to be simultaneously active in memory.
Solution Approach 2:
The patent applies different heat map granularities to different levels of the storage hierarchy. Volume-level heat maps use coarser granularity to reduce memory consumption, while leaf page-level heat maps use finer granularity for accurate temperature prediction. This local quality approach optimizes the balance between memory usage and prediction accuracy at each hierarchical level.
2Quantity of substance
If a heat map with coarse granularity (volume level) is used to represent temperatures of storage objects, then memory storage space consumption is reduced, but temperature prediction accuracy deteriorates
Solution Approach 1:
The patent segments the temperature representation into multiple hierarchical levels, allowing volume-level heat maps to use coarse granularity for memory efficiency while leaf page-level heat maps provide fine granularity for accuracy when needed.
Solution Approach 2:
The patent adds a hierarchical dimension to the heat map structure, organizing temperature data across multiple levels (volume level and leaf page level). This dimensional approach allows the system to navigate between coarse and fine granularity as needed, optimizing both memory usage and prediction accuracy.
3Ease of manufacture
If a fixed heat map algorithm is used for temperature prediction, then implementation simplicity is maintained, but adaptability to varying storage system resources deteriorates
Solution Approach 1:
The patent implements a dynamic heat map system where the algorithm and granularity can adapt to varying storage system resources. The system can dynamically adjust between volume-level and leaf page-level heat maps based on available memory and processing resources, providing adaptability while maintaining implementation simplicity through a structured hierarchical approach.
Solution Approach 2:
The patent changes the parameters of the heat map algorithm based on storage system resources. By adjusting the granularity level and algorithm complexity according to available resources, the system maintains simplicity while achieving adaptability to different storage configurations and resource constraints.
Data Source
AI summary
Techniques for providing multi-tier heat maps in a storage system. The techniques include obtaining a temperature of a storage object using a first heat map of data IO activity at a storage object level of the data, and determining that the temperature of the storage object exceeds a predetermined threshold. The techniques further include, in response to determining that the temperature of the storage object exceeds the predetermined threshold, obtaining at least one temperature of at least one storage element associated with the storage object using a second heat map of data IO activity at a storage element level of the data, and performing a storage operation on the storage object based on the temperature of the storage object and/or the temperature of the storage element. Such use of multi-tier heat maps allow accurate temperature predictions to be made in a manner that conserves and adapts to available system resources.