VM Memory Trending for Out-of-Memory Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing techniques for detecting out-of-memory events in virtual machines often generate high volumes of false alarms or miss significant events due to reliance on fixed thresholds, leading to inefficient management and potential system failures.
Innovation Solution
A system that analyzes time-series data from virtual machines using a trend-estimation technique, computing a time window based on high-activity patterns, and matching features to an out-of-memory pattern to detect and estimate the risk of out-of-memory events, thereby reducing false alarms and improving detection accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If fixed thresholds are used for detecting out-of-memory events, then the detection method is simple, but false alarms increase and detection accuracy decreases
Solution Approach 1:
The patent applies dynamics by transitioning from static fixed thresholds to dynamic adaptive thresholds. The system continuously monitors memory usage patterns and adjusts detection thresholds based on observed behavior, allowing the detection mechanism to adapt to changing workload conditions and reduce false alarms while maintaining accuracy.
Solution Approach 2:
The patent implements feedback mechanisms where detection results and memory usage patterns are continuously fed back into the system to refine future detections. This feedback loop enables the system to learn from past detections and improve its accuracy over time, reducing both false positives and missed detections.
2Ease of manufacture
If fixed thresholds are used for detecting out-of-memory events, then implementation is easy, but system reliability decreases due to false alarms
Solution Approach 1:
The patent applies preliminary action by establishing baseline memory usage patterns and detecting high-activity events before actual OOM conditions occur. The system proactively identifies trends and patterns that indicate potential memory issues, allowing for early intervention and improving reliability while maintaining ease of implementation through automated baseline establishment.
3Device complexity
If simple detection methods are used, then system complexity is low, but detection precision and false alarm reduction are insufficient
Solution Approach 1:
The patent applies segmentation by dividing the detection process into distinct phases: baseline establishment, high-activity event detection, trend analysis, and OOM risk assessment. Each phase handles a specific aspect of memory monitoring, allowing the system to achieve high precision through modular analysis while keeping overall complexity manageable through structured decomposition.
Data Source
AI summary
The disclosed embodiments provide a system that detects anomalous events in a virtual machine. During operation, the system obtains time-series virtual machine (VM) data including garbage-collection (GC) data collected during execution of a virtual machine in a computer system. Next, the system computes, by a service processor, a time window for analyzing the time-series VM data based at least in part on a working time scale of high-activity patterns in the time-series GC data. The system then uses a trend-estimation technique to analyze the time-series VM data within the time window to determine an out-of-memory (OOM) risk in the virtual machine. Finally, the system stores an indication of the OOM risk for the virtual machine based at least in part on determining the OOM risk in the virtual machine.