Memory Leak Detection Algorithms in the Cloud-based Infrastructure

TL;DR

This paper introduces two novel machine learning algorithms, LBR and Precog, for detecting memory leaks in cloud infrastructure using only memory utilization data, achieving high accuracy and efficiency.

Contribution

It presents new ML-based algorithms that detect memory leaks without internal application knowledge, using only memory utilization metrics.

Findings

PrecogMF achieves 85% accuracy in leak detection.

PrecogMF reduces compute time by 80% compared to LBR.

Memory leak patterns are classified based on visual representations.

Abstract

A memory leak in an application deployed on the cloud can affect the availability and reliability of the application. Therefore, identifying and ultimately resolve it quickly is highly important. However, in the production environment running on the cloud, memory leak detection is a challenge without the knowledge of the application or its internal object allocation details. This paper addresses this challenge of detection of memory leaks in cloud-based infrastructure without having any internal knowledge by introducing two novel machine learning-based algorithms: Linear Backward Regression (LBR) and Precog and, their two variants: Linear Backward Regression with Change Points Detection (LBRCPD) and Precog with Maximum Filteration (PrecogMF). These algorithms only use one metric i.e the system's memory utilization on which the application is deployed for detection of a memory leak. The developed algorithm's accuracy was tested on 60 virtual machines manually labeled memory utilization data and it was found that the proposed PrecogMF algorithm achieves the highest accuracy score of 85%. The same algorithm also achieves this by decreasing the overall compute time by 80% when compared to LBR's compute time. The paper also presents the different memory leak patterns found in the various memory leak applications and are further classified into different classes based on their visual representation.