Bifurcated Counting Mechanism for Resource Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems face challenges in efficiently tracking and reporting shared resource utilization in computer systems, particularly in high-access-rate environments, as they require significant memory resources and bandwidth, leading to increased costs and reduced operating rates.
Innovation Solution
The implementation of a bifurcated counting mechanism using full and intermediate counters, where full counters are stored in lower-cost memory for delayed updates and intermediate counters in higher-cost memory for accurate accounting, allowing for efficient tracking and reporting of resource utilization at multiple levels of granularity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If centralized collection of accounting statistics from network devices is implemented, then resource utilization tracking is improved, but network bandwidth consumption increases
Solution Approach 1:
The patent segments resource tracking into two levels: aggregate-level counters that provide overall resource utilization summaries, and granular-level counters that provide detailed breakdowns. This segmentation allows the system to collect comprehensive resource statistics without transmitting excessive data, as granular information is only collected and reported when threshold violations occur, thereby reducing network bandwidth consumption while maintaining tracking precision.
Solution Approach 2:
The patent applies local quality by differentiating the level of detail collected for different resources based on their characteristics and importance. Critical resources that frequently exceed thresholds receive granular-level tracking, while stable resources use aggregate-level tracking. This localized approach optimizes bandwidth usage by allocating detailed monitoring resources only where necessary.
2Measurement precision
If granular-level resource tracking is implemented for all objects, then measurement precision is improved, but memory requirements increase
Solution Approach 1:
The patent divides resource tracking into aggregate-level and granular-level counters. Aggregate counters store overall resource usage in compact form, while granular counters provide detailed breakdowns only when needed. This segmentation dramatically reduces memory requirements by avoiding the storage of extensive granular data for all resources simultaneously, while maintaining high measurement precision through selective granular tracking.
Solution Approach 2:
The patent dynamically changes the level of tracking detail based on threshold violations. When resource usage exceeds predefined thresholds, the system transitions from aggregate-level to granular-level tracking for that specific resource. This parameter change allows the system to maintain high measurement precision only when necessary, optimizing memory usage by avoiding continuous granular tracking of all resources.
3Speed
If high access rate memory is used for resource tracking, then operational speed is improved, but device cost increases
Solution Approach 1:
The patent segments memory usage into two categories: fast memory for storing compact aggregate counters and threshold values, and slower, cheaper memory for storing detailed granular counter data when needed. This segmentation allows the system to maintain high operational speed for critical resource monitoring while reducing overall memory cost by using expensive fast memory only for essential aggregate tracking and occasional granular updates.
Solution Approach 2:
The patent implements periodic updates of granular counters from aggregate counters based on threshold violations rather than continuous updates. This periodic action reduces the demand for high-speed memory access, allowing the system to use lower-cost memory for granular data while maintaining operational speed by only performing expensive memory operations when necessary, specifically when resource thresholds are exceeded.
Data Source
AI summary
Described techniques enable the tracking and reporting of resource utilization at multiple levels of granularity, the highest of which involves tracking resource usage by a particular object in aggregate. When aggregate usage for the particular object is within certain parameters, actual resource usage is not reported at the lower level of granularity, but is replaced by placeholder values. When aggregate usage for the particular object exceeds a threshold, the particular object is considered to be a “hot spot.” Resource usage for the particular object can then be reported (and tracked, if not already) at the lower level of granularity until the particular object is no longer a “hot spot.” The efficiency of the tracking may be further enhanced by leveraging a bifurcated counting mechanism in which a full count is updated only at selected sample times, with intermediate counters used to store changes in between sample times.