QoS Logic Code Upload for Storage Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current QoS management in computing storage systems is inadequate for dynamically changing business needs, as it often relies on predefined options that do not account for varying customer requirements, leading to inefficient resource allocation and increased communication overhead.
Innovation Solution
Implementing a mechanism that allows customers to upload their own QoS logic directly to the storage system, enabling dynamic control of performance characteristics such as bandwidth and IOPS, thereby reducing the need for extensive management data storage and communication.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If predefined QoS options are used in storage systems, then device complexity is reduced, but adaptability to changing business needs deteriorates
Solution Approach 1:
The patent enables customers to upload their own QoS logic code directly to the storage system, allowing the system to serve itself with customized QoS policies rather than relying on predefined options. This self-service approach gives customers full control over QoS parameters while reducing the complexity of managing extensive predefined option sets.
Solution Approach 2:
The patent introduces dynamic QoS management by allowing customers to upload custom logic code that can adapt to changing business needs. The system transitions from static predefined options to dynamic, customer-defined QoS policies that can be modified as requirements change, improving adaptability without proportionally increasing system complexity.
2Measurement precision
If extensive QoS management data is stored and communicated, then measurement precision is improved, but loss of energy increases
Solution Approach 1:
The patent extracts QoS logic code from the storage system and places it on the customer's side, where it is uploaded directly to the storage system only when needed. This extraction reduces the amount of QoS management data that must be continuously stored and communicated, thereby reducing energy consumption while maintaining measurement precision through on-demand data transfer.
Solution Approach 2:
The patent implements periodic QoS logic uploads from customer systems to storage systems, rather than continuous data communication. The QoS logic is uploaded periodically or on-demand, reducing the ongoing energy required for data storage and communication while maintaining precise QoS management capabilities when needed.
3Productivity
If predefined QoS options are used, then ease of operation is improved, but productivity deteriorates due to inefficient resource allocation
Solution Approach 1:
The patent enables customers to define their own QoS logic through uploaded code, allowing them to optimize resource allocation according to their specific business needs. This self-service approach improves productivity by eliminating the inefficiencies of predefined options while keeping operations simple through automated policy application.
Solution Approach 2:
The patent allows dynamic changes to QoS parameters through customer-uploaded logic code. Instead of being limited to fixed predefined options, customers can modify QoS parameters such as bandwidth, IOPS, and latency thresholds to match changing business requirements, thereby improving resource allocation efficiency without complicating operations.
4Adaptability or versatility
If QoS logic code is uploaded to storage system, then adaptability is improved, but device complexity increases
Solution Approach 1:
The patent introduces QoS logic code as an intermediary between the customer's business requirements and the storage system's QoS implementation. This intermediary layer allows customers to express their needs in custom logic that is then translated into actionable QoS policies, improving adaptability while managing complexity through a structured intermediate representation.
Data Source
AI summary
Embodiments for performance management in a computing storage environment. At least one of a plurality of performance characteristics associated with a quality of service (QoS) between a storage system and a host is dynamically controlled by uploading code of a QoS logic, from the host to the storage system, for determining and specifying the at least one of the plurality of performance characteristics, thereby reducing overhead of QoS management data required to be stored within or communicated to the storage system.