Atys: An Efficient Profiling Framework for Identifying Hotspot Functions in Large-scale Cloud Microservices

TL;DR

Atys is a profiling framework designed for large-scale cloud microservices that efficiently identifies performance hotspots across diverse languages and distributed environments, reducing profiling costs while maintaining accuracy.

Contribution

It introduces a novel, language-agnostic profiling framework with a two-level aggregation, function selective pruning, and dynamic sampling adjustment for large-scale microservices.

Findings

FSP reduces profiling time by 6.8% with 0.58% MAPE.

FDA scheme cuts profiling cost by 87.6% while preserving accuracy.

Framework effectively identifies hotspot functions in distributed microservices.

Abstract

To handle the high volume of requests, large-scale services are comprised of thousands of instances deployed in clouds. These services utilize diverse programming languages and are distributed across various nodes as encapsulated containers. Given their vast scale, even minor performance enhancements can lead to significant cost reductions. In this paper, we introduce Atys1, an efficient profiling framework specifically designed to identify hotspot functions within large-scale distributed services. Atys presents four key features. First, it implements a language-agnostic adaptation mechanism for multilingual microservices. Second, a two-level aggregation method is introduced to provide a comprehensive overview of flamegraphs. Third, we propose a function selective pruning (FSP) strategy to enhance the efficiency of aggregating profiling results. Finally, we develop a frequency dynamic adjustment (FDA) scheme that dynamically modifies sampling frequency based on service status, effectively minimizing profiling cost while maintaining accuracy. Cluster-scale experiments on two benchmarks show that the FSP strategy achieves a 6.8% reduction in time with a mere 0.58% mean average percentage error (MAPE) in stack traces aggregation. Additionally, the FDA scheme ensures that the mean squared error (MSE) remains on par with that at high sampling rates, while achieving an 87.6% reduction in cost.