Dynamic Workload Capping in Mainframe Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Mainframe computing systems face challenges in efficiently managing capacity limits to prioritize high-importance workloads while minimizing costs, as existing methods either underutilize resources or lead to substantial cost increases when adjusting capacity limits.
Innovation Solution
A dynamic capping system that adjusts capacity limits based on workload importance and cost factors across multiple billing entities, allowing for the sharing of processing capacity within defined limits to ensure high-importance workloads receive necessary resources without exceeding cost constraints.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If capacity limits are increased to prioritize high-importance workloads, then throughput for high-importance work is improved, but costs increase substantially
Solution Approach 1:
The patent implements dynamic capacity limit adjustment by continuously monitoring workload importance levels and automatically modifying capacity limits in real-time. The system transitions from static to dynamic limit setting, allowing capacity limits to adapt to changing workload conditions without manual intervention, thereby optimizing throughput while controlling costs.
Solution Approach 2:
The system changes the parameter of capacity limits based on workload importance metrics. By adjusting the capacity limit parameter dynamically according to the importance level of workloads, the system ensures high-importance workloads receive necessary resources while preventing excessive resource allocation that would drive up costs.
2Loss of energy
If capacity limits are decreased to control costs, then costs are reduced, but high-importance workloads may not receive necessary resources
Solution Approach 1:
The system implements a feedback mechanism that continuously monitors the importance level of workloads and adjusts capacity limits accordingly. This closed-loop control ensures that when high-importance workloads are detected, capacity limits are increased to ensure adequate resource availability, while for lower-importance workloads, limits are reduced to control costs.
Solution Approach 2:
The patent makes capacity limits dynamic rather than static, allowing them to respond to real-time workload conditions. This dynamic adjustment ensures that resource availability for high-importance workloads is maintained while costs are controlled during periods of lower demand.
3Device complexity
If static capacity limits are used, then system simplicity is maintained, but resource utilization is inefficient
Solution Approach 1:
The system implements self-service automation where the workload manager automatically monitors workload importance and adjusts capacity limits without requiring manual intervention. This self-adjusting mechanism improves resource utilization efficiency while adding minimal operational complexity, as the system serves itself by making automated decisions based on monitored conditions.
Data Source
Figure 1
Figure 2
Figure 3~4
AI summary
A mainframe computing system (105) includes a central processor complex, a plurality of billing entities (160), each billing entity having a respective capacity limit, and a workload manager (132, 174) that schedules work requested by the plurality of billing entities on the central processor complex and tracks, by billing entity, a rolling average of millions of service units. The mainframe also includes a dynamic capping policy (142) that identifies a maximum millions of service unit (MSU) limit, a maximum cost limit, a subset of the plurality of billing entities, and, for each billing entity in the subset, information from which to determine a MSU entitlement value and cost entitlement value. The mainframe also includes a dynamic capping master (122) that adjusts the respective capacity limits of the subset of the plurality of billing entities. The workload manager schedules work within the respective capacity limits such that the central processor complex executes the work without exceeding the maximum cost limit and the MSU limit.