Dynamic External Storage Scaling for Diskless Cloud Hosts
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Customers with diskless host subscriptions face challenges in managing variable storage capacity needs for management software in a software-defined data center (SDDC) due to the inability to leverage local storage, leading to inefficient over-provisioning and increased costs.
Innovation Solution
A storage manager in the cloud dynamically manages external storage capacity by batching and processing requests from the SDDC to expand or release capacity as needed, optimizing storage usage based on actual requirements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If external storage capacity is over-provisioned to support all possible management software types and features, then the storage capacity requirement is met, but storage costs increase significantly
Solution Approach 1:
The patent implements dynamic storage capacity adjustment by batching storage requests and expanding capacity only when needed. The storage manager monitors actual usage patterns and expands external storage capacity dynamically based on real demand rather than static over-provisioning, allowing the system to adapt storage resources to actual management software requirements over time.
Solution Approach 2:
The patent uses preliminary batching of storage requests to plan capacity expansion in advance. By collecting and batching multiple storage requests before executing capacity expansion, the system prepares for future needs while avoiding premature over-provisioning. This allows the system to anticipate requirements and expand capacity at optimal moments rather than continuously over-provisioning.
2Adaptability or versatility
If storage capacity is continuously expanded to accommodate varying management software needs, then storage requirements are met, but resource utilization efficiency decreases
Solution Approach 1:
The patent implements feedback mechanisms where the storage manager continuously monitors actual storage usage by management software and adjusts capacity accordingly. Usage patterns are tracked and fed back into the storage management system, enabling data-driven decisions about when and how much capacity to expand, thereby avoiding continuous expansion and optimizing resource utilization efficiency.
Solution Approach 2:
The patent employs periodic batching of storage requests, where multiple storage operations are collected and processed in periodic cycles rather than continuously. This periodic action allows the system to evaluate usage patterns over time and expand capacity at strategic intervals rather than continuously, reducing unnecessary resource allocation and improving overall efficiency.
3Quantity of substance
If a batch processing approach is used for storage requests, then storage cost optimization is achieved, but request processing time increases
Solution Approach 1:
The patent performs preliminary batching of storage requests, where multiple individual storage operations are collected and grouped into batches before processing. This preliminary organization of requests allows the system to process multiple operations more efficiently in single execution cycles, reducing the total number of system calls and optimizing both cost and processing time by minimizing redundant operations.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An example method of managing external storage for a software-defined data center (SDDC) executing in a cloud is described. The method includes receiving, at a storage manager from the SDDC, requests to consume capacity of the external storage, the external storage allocated for the SDDC according to a cloud subscription; determining, by the storage manager based on a batch of the requests in combination, an amount by which to expand a current capacity of the external storage to a target capacity comprising a sum of an expanded capacity and the current capacity; executing, by the storage manager in cooperation with a storage server of the external storage, a first activity to obtain the target capacity of the external storage; and sending, from the storage manager to the SDDC, at least one identifier that enables software executing in the SDDC to use the expanded capacity for the batch of requests.