Dynamic Write Balancing for Storage Adapter Priority
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data storage systems face inefficiencies in handling data transfers between storage devices, particularly in synchronous and asynchronous modes, due to latency issues and priority management challenges, especially when dealing with changing workload queues and long distances between storage devices.
Innovation Solution
A dynamic priority balancing system that identifies transmission mode groups and assigns priority weights based on logarithmic factors and queue lengths, allowing for efficient servicing of both synchronous and asynchronous data transfers by determining if groups are busy and adjusting weights accordingly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If synchronous RDF transmission is used to ensure data consistency between primary and secondary storage devices, then data reliability is improved, but transmission latency increases due to waiting for acknowledgment
Solution Approach 1:
The system dynamically adjusts the priority weight of synchronous RDF groups based on current queue lengths and system conditions. The priority weight is not fixed but changes over time according to the logarithm of the queue length, allowing the system to adapt to varying workload conditions and optimize between consistency and latency
Solution Approach 2:
The system changes the parameter of priority weight calculation from a static value to a dynamic value based on the logarithm of queue length. This parameter change allows the system to prioritize groups differently based on their current state, resolving the contradiction by adjusting priorities according to real-time conditions
2Productivity
If multiple RDF groups are serviced by the same adapter, then device utilization is improved, but priority management complexity increases due to competing write requests
Solution Approach 1:
The system introduces a dynamic priority weight parameter that is calculated based on the logarithm of queue length. This parameter transformation simplifies the comparison and prioritization of multiple competing groups by converting queue length differences into manageable weight values
Solution Approach 2:
The system continuously monitors queue lengths and adjusts priority weights accordingly. This feedback mechanism ensures that groups with longer queues receive higher priority dynamically, automatically balancing the load across the adapter without complex manual intervention
3Ease of operation
If priority weight is based solely on queue length, then simple scheduling is maintained, but responsiveness to changing workload conditions deteriorates
Solution Approach 1:
The system transforms the queue length parameter into a priority weight using a logarithmic function. This transformation maintains the simplicity of queue-based scheduling while improving adaptability, as the logarithmic scale compresses large queue length variations into manageable weight differences that respond smoothly to changing conditions
Solution Approach 2:
The priority weight becomes a dynamic value that automatically adjusts as queue lengths change. This dynamic adjustment provides workload adaptability while maintaining the conceptual simplicity of queue-based prioritization, as the system automatically responds to changing conditions without complex scheduling logic
Data Source
AI summary
A system for dynamic balancing of writes between multiple storage devices in which Remote Data Facility (RDF) groups may be assigned weights according to a dynamic priority parameter. The dynamic priority parameter provides the ability to control the weight of an asynchronous RDF group compared to that of a synchronous RDF group. Thus, when the same RDF adapter includes a mix of asynchronous RDF groups and synchronous RDF groups, a dynamic balance of the write priorities between the two group types may be obtained.