VAMP: Visual Analytics for Microservices Performance

TL;DR

VAMP tackles the challenge of system-wide performance analysis in microservices by linking RPC-level attributes to end-to-end latency through two interactive visualizations: an aggregated RPC tree and a latency histogram. It supports forward and backward analysis to uncover how RPC execution time and invocation frequency relate to latency modes across many end-to-end requests. Evaluated on 33 datasets from the TrainTicket microservice system, vamp demonstrates the ability to reveal meaningful RPC-time deviations and structural patterns that are hard to detect with traditional distributed tracing tools. The work advances observability by providing integrated, interactive analyses and sets a path toward scalable deployment with further efficiency and real-world validation.

Abstract

Analysis of microservices' performance is a considerably challenging task due to the multifaceted nature of these systems. Each request to a microservices system might raise several Remote Procedure Calls (RPCs) to services deployed on different servers and/or containers. Existing distributed tracing tools leverage swimlane visualizations as the primary means to support performance analysis of microservices. These visualizations are particularly effective when it is needed to investigate individual end-to-end requests' performance behaviors. Still, they are substantially limited when more complex analyses are required, as when understanding the system-wide performance trends is needed. To overcome this limitation, we introduce vamp, an innovative visual analytics tool that enables, at once, the performance analysis of multiple end-to-end requests of a microservices system. Vamp was built around the idea that having a wide set of interactive visualizations facilitates the analyses of the recurrent characteristics of requests and their relation w.r.t. the end-to-end performance behavior. Through an evaluation of 33 datasets from an established open-source microservices system, we demonstrate how vamp aids in identifying RPC execution time deviations with significant impact on end-to-end performance. Additionally, we show that vamp can support in pinpointing meaningful structural patterns in end-to-end requests and their relationship with microservice performance behaviors.

Figures (10)

• Figure 1: Swimlane visualization.
• Figure 2: End-to-end response time distribution.
• Figure 3: Visual Components
• Figure 4: Interaction modalities
• Figure 5: vamp's Dashboard