Most large web-scale applications are now built by composing collections (from a few up to 100s or 1000s) of microservices. Operators need to decide how many resources are allocated to each microservice, and these allocations can have a large impact on application performance. Manually determining allocations that are both cost-efficient and meet performance requirements is challenging, even for experienced operators. In this paper we present AutoTune, an end-to-end tool that automatically minimizes resource utilization while maintaining good application performance.
@article{arxiv.2106.10334,
title = {AutoTune: Improving End-to-end Performance and Resource Efficiency for Microservice Applications},
author = {Michael Alan Chang and Aurojit Panda and Hantao Wang and Yuancheng Tsai and Rahul Balakrishnan and Scott Shenker},
journal= {arXiv preprint arXiv:2106.10334},
year = {2021}
}