Coupling Overhead Compensation in Distributed Systems

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Distributed computing systems face inefficiencies due to coupling overhead, which affects software pricing and capacity utilization, as it depends on hardware levels, network technology, and distance between components, leading to variable and fluctuating performance and increased software licensing costs.

Innovation Solution

A method and system to compensate for coupling overhead by determining coupling efficiency using dynamic and static indicators, and adding missing processing capacity to ensure effective processing capacity matches billable targets, utilizing an overhead calculator and hypervisor to adjust capacity without affecting software pricing.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If distributed computing systems use coupling facilities to enable data sharing and coordination between multiple computer systems, then system availability and scalable capacity are improved, but coupling overhead increases machine cycle consumption and reduces effective processing capacity

Engineering Contradiction:
Improvesystem availabilityVSAvoideffective processing capacity
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent introduces an overhead calculator as an intermediary component that measures and quantifies the coupling overhead consumed by data sharing operations. This mediator allows the system to track the actual overhead consumption and use this information to adjust capacity allocation, thereby maintaining high availability while compensating for the productivity loss through dynamic resource management

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent dynamically changes the parameter of capacity allocation based on measured overhead consumption. By adjusting the effective capacity parameters in response to varying overhead conditions, the system optimizes the balance between maintaining availability through coupling facilities and preserving effective processing capacity for application workloads

Inventive Principle:
Principle #35Parameter changes

2Ease of operation

If software pricing is based on static capacity definitions, then pricing simplicity is maintained, but coupling overhead consumption is not accounted for leading to increased software licensing costs

Engineering Contradiction:
Improvepricing simplicityVSAvoidsoftware licensing costs
Core Design Contradiction:
Ease of operationVSLoss of energy

Solution Approach 1:

The patent implements a feedback mechanism where the overhead calculator continuously measures coupling overhead consumption and feeds this information back to the capacity adjustment controller. This feedback loop enables dynamic capacity adjustment that accounts for actual overhead usage, allowing the system to optimize software licensing costs by aligning capacity allocation with measured overhead consumption while maintaining pricing simplicity through automated adjustments

Inventive Principle:
Principle #23Feedback

Data Source

PatentUS8881166B2Method, data processing program, and computer program product to compensate for coupling overhead in a distributed computing system, and corresponding overhead calculator for a distributed computing system and corresponding computer system
Publication Date: 2014.11.04 INTERNATIONAL BUSINESS MACHINE CORPORATION
  • US8881166B2 patent drawing
  • US8881166B2 patent drawing
  • US8881166B2 patent drawing

AI summary

An improved method to compensate for coupling overhead in a distributed computing system offering a raw processing capacity, comprising an effective processing capacity (404) and the coupling overhead, is disclosed, wherein the distributed computing system comprises at least one computer system and at least one coupling facility. The method comprises determining a coupling efficiency, determining and adding an amount of missing processing capacity to the effective processing capacity based on the coupling efficiency in a way that the effective processing capacity of the raw processing capacity corresponds to a billable target processing capacity.