Chengliang Zhang, Minchen Yu, and Wei Wang, Hong Kong University of Science and Technology; Feng Yan, University of Nevada, Reno
The advances of Machine Learning (ML) have sparked a growing demand of ML-as-a-Service: developers train ML models and publish them in the cloud as online services to provide low-latency inference at scale. The key challenge of ML model serving is to meet the response-time Service-Level Objectives (SLOs) of inference workloads while minimizing the serving cost. In this paper, we tackle the dual challenge of SLO compliance and cost effectiveness with MArk (Model Ark), a general-purpose inference serving system built in Amazon Web Services (AWS). MArk employs three design choices tailor-made for inference workload. First, MArk dynamically batches requests and opportunistically serves them using expensive hardware accelerators (e.g., GPU) for improved performance-cost ratio. Second, instead of relying on feedback control scaling or over-provisioning to serve dynamic workload, which can be too slow or too expensive for inference serving, MArk employs predictive autoscaling to hide the provisioning latency at low cost. Third, given the stateless nature of inference serving, MArk exploits the flexible, yet costly serverless instances to cover the occasional load spikes that are hard to predict. We evaluated the performance of MArk using several state-of-the-art ML models trained in popular frameworks including TensorFlow, MXNet, and Keras. Compared with the premier industrial ML serving platform SageMaker, MArk reduces the serving cost up to 7.8× while achieving even better latency performance.
Open Access Media
USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are posted after the event are also free and open to everyone. Support USENIX and our commitment to Open Access.
author = {Chengliang Zhang and Minchen Yu and Wei Wang and Feng Yan},
title = {{MArk}: Exploiting Cloud Services for {Cost-Effective}, {SLO-Aware} Machine Learning Inference Serving},
booktitle = {2019 USENIX Annual Technical Conference (USENIX ATC 19)},
year = {2019},
isbn = {978-1-939133-03-8},
address = {Renton, WA},
pages = {1049--1062},
url = {https://www.usenix.org/conference/atc19/presentation/zhang-chengliang},
publisher = {USENIX Association},
month = jul
}