The Case for Task Sampling based Learning for Cluster Job Scheduling

08/24/2021
by   Akshay Jajoo, et al.
0

The ability to accurately estimate job runtime properties allows a scheduler to effectively schedule jobs. State-of-the-art online cluster job schedulers use history-based learning, which uses past job execution information to estimate the runtime properties of newly arrived jobs. However, with fast-paced development in cluster technology (in both hardware and software) and changing user inputs, job runtime properties can change over time, which lead to inaccurate predictions. In this paper, we explore the potential and limitation of real-time learning of job runtime properties, by proactively sampling and scheduling a small fraction of the tasks of each job. Such a task-sampling-based approach exploits the similarity among runtime properties of the tasks of the same job and is inherently immune to changing job behavior. Our study focuses on two key questions in comparing task-sampling-based learning (learning in space) and history-based learning (learning in time): (1) Can learning in space be more accurate than learning in time? (2) If so, can delaying scheduling the remaining tasks of a job till the completion of sampled tasks be more than compensated by the improved accuracy and result in improved job performance? Our analytical and experimental analysis of 3 production traces with different skew and job distribution shows that learning in space can be substantially more accurate. Our simulation and testbed evaluation on Azure of the two learning approaches anchored in a generic job scheduler using 3 production cluster job traces shows that despite its online overhead, learning in space reduces the average Job Completion Time (JCT) by 1.28x, 1.56x, and 1.32x compared to the prior-art history-based predictor.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

08/25/2021

A Case for Sampling Based Learning Techniques in Coflow Scheduling

Coflow scheduling improves data-intensive application performance by imp...
03/16/2022

NURD: Negative-Unlabeled Learning for Online Datacenter Straggler Prediction

Datacenters execute large computational jobs, which are composed of smal...
01/23/2018

Mistral Supercomputer Job History Analysis

In this technical report, we show insights and results of operational da...
11/16/2021

Saath: Speeding up CoFlows by Exploiting the Spatial Dimension

Coflow scheduling improves data-intensive application performance by imp...
04/25/2016

Do the Hard Stuff First: Scheduling Dependent Computations in Data-Analytics Clusters

We present a scheduler that improves cluster utilization and job complet...
03/07/2022

Fabchain: Managing Audit-able 3D Print Job over Blockchain

Improvements in fabrication devices such as 3D printers are becoming pos...
02/23/2022

The Tiny-Tasks Granularity Trade-Off: Balancing overhead vs. performance in parallel systems

Models of parallel processing systems typically assume that one has l wo...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.