Policy-Driven Storage Token Allocation for Microserver QoS
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In microserver computing environments, managing storage Quality of Service (QoS) is challenging due to uneven storage performance among compute nodes, lack of centralized control, and inability to enforce storage policies dynamically across all host platforms and operating systems, leading to suboptimal storage bandwidth allocation and potential starvation of resources.
Innovation Solution
A policy-driven storage system that uses tokens to manage I/O operations and enforce storage access policies centrally, ensuring fair allocation of shared storage resources by allocating tokens to command descriptors and throttling I/O operations based on policy contexts, allowing for dynamic and centralized management of storage QoS across all compute nodes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If tokens are allocated to command descriptors to manage I/O operations, then storage resource allocation fairness is improved, but device complexity increases
Solution Approach 1:
The patent introduces tokens as intermediary objects that mediate between compute nodes and shared storage resources. These tokens act as a control mechanism that simplifies the management of I/O operations by providing a standardized way to allocate and track storage resource access rights, thereby improving fairness without directly increasing operational complexity
Solution Approach 2:
The patent changes the parameter of resource allocation from direct I/O operation control to token-based control. By transforming the allocation mechanism into a token system with specific parameters (token count, token validity, token assignment rules), the system achieves more manageable and fair resource distribution while keeping the underlying complexity encapsulated in the token management logic
2Adaptability or versatility
If storage policies are enforced dynamically across all host platforms and operating systems, then adaptability is improved, but device complexity increases
Solution Approach 1:
The patent creates a universal token-based policy enforcement mechanism that can operate across different host platforms and operating systems. The token system serves multiple functions: it acts as a policy enforcement tool, a resource allocation mechanism, and a cross-platform communication standard, thereby improving adaptability without proportionally increasing complexity
Solution Approach 2:
The patent uses command descriptors as copyable data structures that can be replicated and managed across different platforms. By copying and managing these standardized descriptors with associated tokens, the system achieves cross-platform policy enforcement while maintaining consistent behavior across diverse operating systems and hardware configurations
3Productivity
If centralized control is implemented for storage QoS management, then storage performance optimization is improved, but device complexity increases
Solution Approach 1:
The patent extracts the QoS management functionality from individual compute nodes and concentrates it in a centralized controller. This extracted centralized control logic manages token allocation and policy enforcement for all compute nodes, improving overall storage performance optimization while isolating the complexity within the centralized controller rather than distributing it across all nodes
4Ease of operation
If I/O operations are throttled based on policy contexts, then storage resource fairness is improved, but productivity decreases
Solution Approach 1:
The patent implements periodic token allocation and I/O operation throttling based on policy contexts. Instead of continuous throttling, the system periodically evaluates policy compliance and adjusts token availability accordingly, allowing I/O throughput to fluctuate within fair limits rather than being constantly restricted, thus maintaining resource fairness while preserving productivity during compliant operation periods
Data Source
AI summary
An example method for facilitating policy-driven storage in a microserver computing environment is provided and includes receiving, at an input/output (I/O) adapter in a microserver chassis having a plurality of compute nodes and a shared storage resource, policy contexts prescribing storage access parameters of respective compute nodes and enforcing the respective policy contexts on I/O operations by the compute nodes, in which respect a particular I/O operation by any compute node is not executed if the respective policy context does not allow the particular I/O operation. The method further includes allocating tokens to command descriptors associated with I/O operations for accessing the shared storage resource, identifying a violation of any policy context of any compute node based on availability of the tokens, and throttling I/O operations by other compute nodes until the violation disappears.