Resiliency SLO Protocol Layer for Dynamic Storage Array Adaptation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current storage array configurations do not account for network-based events, leading to performance degradation, and lack dynamic adjustments based on historical, current, or anticipated network conditions and input/output workloads.
Innovation Solution
The method involves establishing and managing subnets and physical links based on a resiliency service level objective (SLO), assigning logical unit numbers with corresponding SLOs, and implementing mitigation techniques to handle subnet or link failures by adjusting operational delays based on retransmit thresholds.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If storage array configurations are made static and simple, then device complexity is reduced, but performance degrades due to inability to adapt to network conditions
Solution Approach 1:
The storage array configuration is transformed from static to dynamic through the introduction of a resiliency SLO protocol layer that continuously monitors network conditions and automatically adjusts configuration parameters. The system dynamically provisions application, hardware, and circuitry components based on real-time resiliency SLO requirements, enabling adaptation to changing network conditions without manual intervention.
Solution Approach 2:
The system implements a feedback mechanism where the resiliency SLO protocol layer continuously monitors actual network performance and compares it against target resiliency SLOs. Based on this feedback, the system automatically adjusts configuration parameters such as provisioning components, establishing subnets, and modifying physical links to maintain optimal performance aligned with resiliency objectives.
2Productivity
If dynamic adjustments are implemented based on network conditions, then performance is enhanced, but device complexity increases
Solution Approach 1:
The storage array is equipped with self-service capabilities through the resiliency SLO protocol layer, which autonomously monitors network conditions, evaluates performance against resiliency SLOs, and automatically adjusts configurations without external intervention. The system provisions components, manages subnets, and adapts physical links based on its own performance assessments, reducing the need for complex external management while maintaining high performance.
Solution Approach 2:
The system performs preliminary actions by pre-establishing resiliency SLOs and provisioning frameworks before network conditions deteriorate. The resiliency SLO protocol layer proactively configures application, hardware, and circuitry components based on anticipated needs, and pre-establishes subnets and physical links to ensure rapid response when performance degradation is detected, avoiding the need for complex reactive configurations.
3Adaptability or versatility
If resiliency SLO protocol layer is added, then adaptability to network conditions improves, but device complexity increases
Solution Approach 1:
The resiliency SLO protocol layer is designed as a universal multi-functional component that consolidates multiple responsibilities including monitoring network conditions, evaluating resiliency SLOs, provisioning application/hardware/circuitry components, managing subnets, and controlling physical links. By combining these functions into a single protocol layer, the system achieves high adaptability without proportionally increasing overall complexity, as the protocol layer serves multiple purposes simultaneously.
Data Source
AI summary
One or more aspects of the present disclosure relate to dynamically selecting a storage array and corresponding input/output (IO) paths between a host and the storage array. In embodiments, a virtual storage volume (VSV) can be established for a host entity using one or more storage device portions from a plurality of storage arrays. In addition, IO servicing metric parameters can be dynamically measured. The servicing metric parameters can define metrics corresponding to the VSV's assigned ports on each of the storage arrays or network latency between the host and each of the plurality of storage arrays. Further, a primary storage array from the plurality of storage arrays can be selected based on the IO servicing metrics.