Learning to Schedule: A Supervised Learning Framework for Network-Aware Scheduling of Data-Intensive Workloads

TL;DR

This paper introduces a supervised learning-based network-aware scheduler for data-intensive workloads in distributed cloud environments, improving placement accuracy and job performance by considering network conditions.

Contribution

It presents a novel supervised learning framework for real-time, network-aware job scheduling in multi-site clusters, enhancing placement decisions over traditional resource-based methods.

Findings

Achieved 34-54% higher accuracy in node selection.

Improved job completion times through network-aware scheduling.

Validated on geo-distributed Kubernetes cluster with Spark workloads.

Abstract

Distributed cloud environments hosting data-intensive applications often experience slowdowns due to network congestion, asymmetric bandwidth, and inter-node data shuffling. These factors are typically not captured by traditional host-level metrics like CPU or memory. Scheduling without accounting for these conditions can lead to poor placement decisions, longer data transfers, and suboptimal job performance. We present a network-aware job scheduler that uses supervised learning to predict the completion time of candidate jobs. Our system introduces a prediction-and-ranking mechanism that collects real-time telemetry from all nodes, uses a trained supervised model to estimate job duration per node, and ranks them to select the best placement. We evaluate the scheduler on a geo-distributed Kubernetes cluster deployed on the FABRIC testbed by running network-intensive Spark workloads. Compared to the default Kubernetes scheduler, which makes placement decisions based on current resource availability alone, our proposed supervised scheduler achieved 34-54% higher accuracy in selecting optimal nodes for job placement. The novelty of our work lies in the demonstration of supervised learning for real-time, network-aware job scheduling on a multi-site cluster.