Sequence-to-sequence models for workload interference

TL;DR

This paper introduces a sequence-to-sequence neural network approach to predict resource interference in data-center job scheduling, aiming to improve placement decisions by modeling job behavior over time.

Contribution

It proposes a novel methodology using recurrent neural networks to forecast resource usage during co-scheduled jobs, moving beyond traditional workload summarization techniques.

Findings

Model accurately predicts resource usage trends.

Effective on both seen and unseen job combinations.

Validated with diverse HPC benchmarks and frameworks.

Abstract

Co-scheduling of jobs in data-centers is a challenging scenario, where jobs can compete for resources yielding to severe slowdowns or failed executions. Efficient job placement on environments where resources are shared requires awareness on how jobs interfere during execution, to go far beyond ineffective resource overbooking techniques. Current techniques, most of them already involving machine learning and job modeling, are based on workload behavior summarization across time, instead of focusing on effective job requirements at each instant of the execution. In this work we propose a methodology for modeling co-scheduling of jobs on data-centers, based on their behavior towards resources and execution time, using sequence-to-sequence models based on recurrent neural networks. The goal is to forecast co-executed jobs footprint on resources along their execution time, from the profile shown by the individual jobs, to enhance resource managers and schedulers placement decisions. The methods here presented are validated using High Performance Computing benchmarks based on different frameworks (like Hadoop and Spark) and applications (CPU bound, IO bound, machine learning, SQL queries...). Experiments show that the model can correctly identify the resource usage trends from previously seen and even unseen co-scheduled jobs.