The Petascale DTN Project: High Performance Data Transfer for HPC Facilities

TL;DR

This paper details the Petascale DTN Project, which achieved over 1PB/week data transfer rates between HPC facilities by designing specialized Data Transfer Nodes and optimizing software and configurations for large-scale data movement.

Contribution

It introduces a scalable data transfer infrastructure for HPC facilities, demonstrating high-performance data movement at petascale levels.

Findings

Achieved routine data transfer rates over 1PB/week

Designed and optimized Data Transfer Node clusters

Enabled large-scale data movement for scientific collaborations

Abstract

The movement of large-scale (tens of Terabytes and larger) data sets between high performance computing (HPC) facilities is an important and increasingly critical capability. A growing number of scientific collaborations rely on HPC facilities for tasks which either require large-scale data sets as input or produce large-scale data sets as output. In order to enable the transfer of these data sets as needed by the scientific community, HPC facilities must design and deploy the appropriate data transfer capabilities to allow users to do data placement at scale. This paper describes the Petascale DTN Project, an effort undertaken by four HPC facilities, which succeeded in achieving routine data transfer rates of over 1PB/week between the facilities. We describe the design and configuration of the Data Transfer Node (DTN) clusters used for large-scale data transfers at these facilities, the software tools used, and the performance tuning that enabled this capability.