FIRM: An Intelligent Fine-Grained Resource Management Framework for SLO-Oriented Microservices
By Haoran Qiu, Subho Sankar Banerjee, Saurabh Jha, Zbigniew T. Kalbarczyk, R. Iyer. USENIX Symposium on Operating Systems Design and Implementation, 2020
373 citations recorded by the source corpus.
Modern user-facing latency-sensitive web services include numerous distributed, intercommunicating microservices that promise to simplify software development and operation. However, multiplexing of compute resources across microservices is still challenging in production because contention for shared resources can cause latency spikes that violate the service-level objectives (SLOs) of user requests. This paper presents FIRM, an intelligent fine-grained resource management framework for predictable sharing of resources across microservices to drive up overall utilization. FIRM leverages online telemetry data and machine-learning methods to adaptively (a) detect/localize microservices that cause SLO violations, (b) identify low-level resources in contention, and (c) take actions to mitigate SLO violations via dynamic reprovisioning. Experiments across four microservice benchmarks demonstrate that FIRM reduces SLO violations by up to 16x while reducing the overall requested CPU limit by up to 62%. Moreover, FIRM improves performance predictability by reducing tail latencies by up to 11x.
Subfields: Computer Networks and Communications, Information Systems
View Paper: https://www.semanticscholar.org/paper/09aaa85c6fe92ec2e894700dc2bab4d481c5b27d
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Chengzhong Xu
- Chengzhi Lu
- Liping Zhang
- Yu Ding
- Shutian Luo
- Jian He
- Guoyao Xu
- Huanle Xu
Citations in the corpus
- Characterizing Microservice Dependency and Performance: Alibaba Trace Analysis (2021, methodology): “In addition, the recently developed machine learning schemes are either based on CNN neural networks or reinforcement learning approaches, which cannot capture the dynamic dependency of microservice call graphs [17, 23, 40].”