Flow Aging Timer Tuning via Zombie Flow Ratio Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing computer networks face challenges in determining the optimal aging time for flows, leading to inefficient resource allocation and performance issues, as aging times that are too short or too long can result in premature resource release or resource wastage, affecting both performance and accuracy.
Innovation Solution
A method is introduced to monitor flows in a computer network, estimating the ratio of zombie flows by tracking the total flow time and zombie flow time, allowing for the prediction of capacity improvements, performance hits, and accuracy hits based on tuned aging parameters, enabling dynamic adjustment of aging timers to optimize resource utilization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the aging time is set short to release resources quickly, then resource allocation efficiency is improved, but flow accuracy deteriorates causing premature resource release and performance degradation
Solution Approach 1:
The system performs preliminary monitoring of flow silence periods before triggering aging. By tracking silent periods and comparing them against the aging timer threshold, the system prepares to release resources only when the flow has been genuinely inactive for the required duration, preventing premature release while maintaining efficient resource turnover.
2Reliability
If the aging time is set long to maintain flow accuracy, then flow accuracy is improved, but resource allocation efficiency deteriorates causing resource wastage
Solution Approach 1:
The system dynamically adjusts the aging timer based on flow type characteristics. Different flow types (e.g., TCP with FIN, UDP, TCP without FIN) have different aging timers configured based on their expected behavior patterns. This dynamic configuration allows the system to use shorter aging times for flows that typically close cleanly and longer aging times for flows that may remain silent briefly before resuming, optimizing both accuracy and resource efficiency for each flow type.
3Device complexity
If a fixed aging timer is used for all flows, then device complexity is reduced, but adaptability deteriorates causing suboptimal performance for different flow types
Solution Approach 1:
The system applies different aging timer values to different flow types based on their specific characteristics. Each flow type (TCP with FIN, UDP, TCP without FIN) has a locally optimized aging timer configured according to its expected behavior. This allows the system to maintain simple fixed timers within each flow type category while achieving high adaptability across different flow types through localized optimization.
Data Source
AI summary
In one embodiment, flows are monitored that are open for a length of time until ending by either a distinct ending or by being silent longer than a configured aging timer (wherein a silent flow is a “zombie flow”). In response to each first flow ending, a total flow time value may be increased by a length of time that first flow was open, and in response to each second flow ending by aging, a zombie flow time value may be increased by the aging timer. A ratio of zombie flows at a particular time in the computer network that will be ended by aging may be estimated as the zombie flow time value divided by the total flow time value. Also, in other embodiments, a capacity improvement, performance hit, and accuracy hit may be predicted based on a new aging timer value.