Protected Mode Scheduling for Scalable Resource Allocation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current operating systems face inefficiencies due to centralized kernel scheduling, which limits scalability and forces all applications to use a single scheduling algorithm, failing to optimize resource allocation for diverse application needs.
Innovation Solution
Implementing protected mode scheduling domains that decentralize scheduling responsibility by creating virtual processors and allocating physical resources according to application-specific policies, allowing context switching within protected mode without transitioning to supervisor mode.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If centralized kernel scheduling is used, then system management is simplified, but scheduling efficiency and scalability deteriorate
Solution Approach 1:
The patent divides the centralized kernel scheduling function into multiple protected mode scheduling domains, each capable of independent scheduling operations. This segmentation allows parallel scheduling decisions to be made at the domain level, improving efficiency while maintaining manageable complexity through modular organization.
Solution Approach 2:
The patent introduces a new dimension of scheduling by implementing protected mode scheduling domains that operate independently from the traditional kernel mode. This creates a hierarchical scheduling structure where domain-level scheduling occurs in parallel with kernel-level scheduling, adding temporal and organizational dimensions to the scheduling process.
2Device complexity
If a single scheduling algorithm is used for all applications, then system simplicity is maintained, but resource allocation optimization deteriorates
Solution Approach 1:
The patent enables each protected mode scheduling domain to implement its own scheduling algorithm tailored to the specific requirements of applications within that domain. This local customization allows optimal resource allocation for different application types (e.g., real-time, batch, interactive) while maintaining overall system structure through the protected mode framework.
Solution Approach 2:
The patent allows scheduling parameters and algorithms to be dynamically configured at the protected mode domain level, enabling adaptation to different workload characteristics without changing the core kernel scheduling infrastructure. This flexibility optimizes resource allocation for diverse application needs while preserving system simplicity through parameterization rather than structural complexity.
3Reliability
If context switching occurs in supervisor mode, then system control is maintained, but switching overhead increases
Solution Approach 1:
The patent introduces protected mode scheduling domains as intermediary layers between user applications and the kernel. Context switching between applications within the same protected mode domain occurs at this intermediary level without requiring transitions to supervisor mode, thereby reducing switching overhead while maintaining system control through the domain's managed access to kernel resources.
Solution Approach 2:
The patent segments the context switching operation into two paths: switches within the same protected mode domain occur locally without kernel involvement, while switches between domains or requiring privileged operations involve the kernel. This segmentation reduces the frequency of expensive supervisor mode transitions while preserving system control for critical operations.
Data Source
Figure 1A
Figure 1B
Figure 1C
AI summary
The present invention extends to methods, systems, and computer program products for protected mode scheduling of operations. Protected mode (e.g., user mode) scheduling can facilitate the development of programming frameworks that better reflect the requirements of the workloads through the use of workload-specific execution abstractions. In addition, the ability to define scheduling policies tuned to the characteristics of the hardware resources available and the workload requirements has the potential of better system scaling characteristics. Further, protected mode scheduling decentralizes the scheduling responsibility by moving significant portions of scheduling functionality from supervisor mode (e.g., kernel mode) to an application.