Data Protection System Using HMAT for SCM Namespace Ranking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Selecting the best-performing Storage Class Memory (SCM) namespace for data protection operations is challenging due to varying performance attributes and latencies across different namespaces, especially when multiple destinations are available, impacting overall operation efficiency.
Innovation Solution
A data protection system that generates and updates a Heterogeneous Memory Attribute Table (HMAT) and global view to rank namespaces based on latency and bandwidth, allowing for dynamic selection of the best-performing namespace for data transfer operations, considering factors like fabric and source latencies, and workload impacts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If multiple SCM namespaces are available for data protection operations, then data redundancy and flexibility are improved, but it becomes difficult to determine which namespace has the best performance and should be selected
Solution Approach 1:
The system performs preliminary actions by generating a Heterogeneous Memory Attribute Table (HMAT) that pre-captures performance attributes of multiple SCM namespaces before data protection operations begin. This allows the system to have performance data ready in advance, eliminating the need to measure and compare namespace performance in real-time during operations.
Solution Approach 2:
The patent introduces a Heterogeneous Memory Attribute Table (HMAT) as an intermediary data structure that mediates between multiple SCM namespaces and the data protection system. The HMAT stores and organizes performance attributes, serving as a reference that simplifies the selection process by providing a centralized location to query namespace performance characteristics.
2Speed
If SCM performance varies between different namespaces, then optimal performance can be achieved by selecting the best namespace, but determining the best namespace becomes complex due to varying attributes and latencies
Solution Approach 1:
The system implements feedback by continuously monitoring and updating the Heterogeneous Memory Attribute Table (HMAT) with current performance attributes of SCM namespaces. This feedback mechanism allows the data protection system to adapt to changing namespace performance conditions and make informed selection decisions based on real-time or near-real-time data.
Solution Approach 2:
The patent utilizes parameter changes by dynamically updating performance attributes in the HMAT, such as latency measurements and bandwidth characteristics. By tracking how these parameters change over time and under different workload conditions, the system can identify the best-performing namespace for specific data protection operations.
3Productivity
If performance attributes are monitored in real-time, then optimal namespace selection is improved, but the overhead of continuous monitoring and updates increases system complexity
Solution Approach 1:
The system applies partial action by monitoring and updating only the critical performance attributes needed for namespace selection, rather than comprehensively tracking all possible SCM parameters. The Heterogeneous Memory Attribute Table (HMAT) focuses on key metrics such as latency and bandwidth that directly impact data protection performance, reducing monitoring overhead while maintaining selection accuracy.
Data Source
AI summary
One example method includes selecting a best performing memory for an operation. A data protection system may maintain a global view of performance data for multiple namespaces. The performance data may reflect latency and/or bandwidth for each of the namespaces. The global view may be updated. When performing an operation, the best performing namespace can be selected from the global view based on performance.