Sinan: Data Driven Resource Management for Cloud Microservices

TL;DR

Sinan is a cluster management system for microservices that uses tracing data to optimize resource allocation, ensuring QoS while maintaining resource efficiency in cloud applications.

Contribution

It introduces a data-driven resource management approach for microservices that relies on tracing data instead of empirical methods.

Findings

Sinan effectively maintains QoS in microservices-based social network.

The approach improves resource efficiency compared to traditional methods.

It demonstrates practical viability in real-world microservice deployments.

Abstract

Cloud applications are increasingly shifting to interactive and loosely-coupled microservices. Despite their advantages, microservices complicate resource management, due to inter-tier dependencies. We present Sinan, a cluster manager for interactive microservices that leverages easily-obtainable tracing data instead of empirical decisions, to infer the impact of a resource allocation on on end-to-end performance, and allocate appropriate resources to each tier. In a preliminary evaluation of Sinan with an end-to-end social network built with microservices, we show that Sinan's data-driven approach, allows the service to always meet its QoS without sacrificing resource efficiency.