research-article

Optimizing inference serving on serverless platforms

Authors:

Ahsan Ali,

Riccardo Pinciroli,

Feng Yan,

Evgenia SmirniAuthors Info & Claims

Proceedings of the VLDB Endowment, Volume 15, Issue 10

Pages 2071 - 2084

https://doi.org/10.14778/3547305.3547313

Published: 01 June 2022 Publication History

Get Access

Abstract

Serverless computing is gaining popularity for machine learning (ML) serving workload due to its autonomous resource scaling, easy to use and pay-per-use cost model. Existing serverless platforms work well for image-based ML inference, where requests are homogeneous in service demands. That said, recent advances in natural language processing could not fully benefit from existing serverless platforms as their requests are intrinsically heterogeneous.

Batching requests for processing can significantly increase ML serving efficiency while reducing monetary cost, thanks to the pay-per-use pricing model adopted by serverless platforms. Yet, batching heterogeneous ML requests leads to additional computation overhead as small requests need to be "padded" to the same size as large requests within the same batch. Reaching effective batching decisions (i.e., which requests should be batched together and why) is non-trivial: the padding overhead coupled with the serverless auto-scaling forms a complex optimization problem.

To address this, we develop Multi-Buffer Serving (MBS), a framework that optimizes the batching of heterogeneous ML inference serving requests to minimize their monetary cost while meeting their service level objectives (SLOs). The core of MBS is a performance and cost estimator driven by analytical models supercharged by a Bayesian optimizer. MBS is prototyped and evaluated on AWS using bursty workloads. Experimental results show that MBS preserves SLOs while outperforming the state-of-the-art by up to 8 x in terms of cost savings while minimizing the padding overhead by up to 37 x with 3 x less number of serverless function invocations.

References

[1]

Martín Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, Manjunath Kudlur, Josh Levenberg, Rajat Monga, Sherry Moore, Derek Gordon Murray, Benoit Steiner, Paul A. Tucker, Vijay Vasudevan, Pete Warden, Martin Wicke, Yuan Yu, and Xiaoqiang Zheng. 2016. Tensorflow: A system for large-scale machine learning. In Proceedings of the Symposium on Operating Systems Design and Implementation (OSDI). USENIX, 265--283.

Abstract

References

Cited By

Recommendations

Cost-Efficient Serverless Inference Serving with Joint Batching and Multi-Processing

Characterizing serverless platforms with serverlessbench

Understanding Open Source Serverless Platforms: Design Considerations and Performance

Comments

Information

Published In

Publisher

Publication History

Badges

Qualifiers

Contributors

Other Metrics

Bibliometrics

Article Metrics

Other Metrics

Citations

Cited By

Get Access

Login options

Full Access

View options

PDF

eReader

Figures

Other

Share

Share this Publication link

Share on social media

Affiliations