MLProxy: SLA-Aware Reverse Proxy for Machine Learning Inference Serving on Serverless Computing Platforms

Abstract

Serving machine learning inference workloads on the cloud is still a challenging task on the production level. Optimal configuration of the inference workload to meet SLA requirements while optimizing the infrastructure costs is highly complicated due to the complex interaction between batch configuration, resource configurations, and variable arrival process. Serverless computing has emerged in recent years to automate most infrastructure management tasks.Workload batching has revealed the potential to improve the response time and cost-effectiveness of machine learning serving workloads. However, it has not yet been supported out of the box by serverless computing platforms. Our experiments have shown that for various machine learning workloads, batching can hugely improve the system's efficiency by reducing the processing overhead per request.In this work, we present MLProxy, an adaptive reverse proxy to support efficient machine learning serving workloads on serverless computing systems. MLProxy supports adaptive batching to ensure SLA compliance while optimizing serverless costs. We performed rigorous experiments on Knative to demonstrate the effectiveness of MLProxy. We showed that MLProxy could reduce the cost of serverless deployment by up to 92% while reducing SLA violations by up to 99% that can be generalized across state-of-the-art model serving frameworks.

IRIS: Interference and Resource Aware Predictive Orchestration for ML Inference Serving

“…Towards this direction, several works with different approaches have been conducted, aiming to address the problem of efficient resource orchestration and optimization for ML inference serving systems. Adaptive and pre-defined batching techniques [30]- [33] have been introduced aiming to support ML inference, while auto-scaling approaches are also considered [32], [34], [35], [35], [36]. Furthermore, aiming to support efficient ML inference, serverless approaches have been considered [33], [37], while MLbased and predictive solutions for load request and resource utilization have been widely utilized [13], [14], [38]- [43], [43], [44], such as reinforcement learning-based solutions [43].…”

“…Adaptive and pre-defined batching techniques [30]- [33] have been introduced aiming to support ML inference, while auto-scaling approaches are also considered [32], [34], [35], [35], [36]. Furthermore, aiming to support efficient ML inference, serverless approaches have been considered [33], [37], while MLbased and predictive solutions for load request and resource utilization have been widely utilized [13], [14], [38]- [43], [43], [44], such as reinforcement learning-based solutions [43]. Aiming to provide lightweight decision making, the approach of model-less decision making has also been considered as an alternative [27], [45].…”