Reducing the Impact of I/O Contention in Numerical Weather Prediction Workflows at Scale Using DAOS

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Manubens, Nicolau, Smart, Simon D., Danovaro, Emanuele, Quintino, Tiago, Jackson, Adrian
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911827562070016
author Manubens, Nicolau
Smart, Simon D.
Danovaro, Emanuele
Quintino, Tiago
Jackson, Adrian
author_facet Manubens, Nicolau
Smart, Simon D.
Danovaro, Emanuele
Quintino, Tiago
Jackson, Adrian
contents Operational Numerical Weather Prediction (NWP) workflows are highly data-intensive. Data volumes have increased by many orders of magnitude over the last 40 years, and are expected to continue to do so, especially given the upcoming adoption of Machine Learning in forecast processes. Parallel POSIX-compliant file systems have been the dominant paradigm in data storage and exchange in HPC workflows for many years. This paper presents ECMWF's move beyond the POSIX paradigm, implementing a backend for their storage library to support DAOS -- a novel high-performance object store designed for massively distributed Non-Volatile Memory. This system is demonstrated to be able to outperform the highly mature and optimised POSIX backend when used under high load and contention, as per typical forecast workflow I/O patterns. This work constitutes a significant step forward, beyond the performance constraints imposed by POSIX semantics.
format Preprint
id arxiv_https___arxiv_org_abs_2404_03107
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Reducing the Impact of I/O Contention in Numerical Weather Prediction Workflows at Scale Using DAOS
Manubens, Nicolau
Smart, Simon D.
Danovaro, Emanuele
Quintino, Tiago
Jackson, Adrian
Distributed, Parallel, and Cluster Computing
Operational Numerical Weather Prediction (NWP) workflows are highly data-intensive. Data volumes have increased by many orders of magnitude over the last 40 years, and are expected to continue to do so, especially given the upcoming adoption of Machine Learning in forecast processes. Parallel POSIX-compliant file systems have been the dominant paradigm in data storage and exchange in HPC workflows for many years. This paper presents ECMWF's move beyond the POSIX paradigm, implementing a backend for their storage library to support DAOS -- a novel high-performance object store designed for massively distributed Non-Volatile Memory. This system is demonstrated to be able to outperform the highly mature and optimised POSIX backend when used under high load and contention, as per typical forecast workflow I/O patterns. This work constitutes a significant step forward, beyond the performance constraints imposed by POSIX semantics.
title Reducing the Impact of I/O Contention in Numerical Weather Prediction Workflows at Scale Using DAOS
topic Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2404.03107