Performance Considerations for Gigabyte per Second Transcontinental Disk-to-Disk File Transfers

TL;DR

This paper discusses the configuration and measurement of disk subsystems capable of supporting gigabyte-per-second data transfers across transcontinental distances, highlighting the performance of multi-disk stripes.

Contribution

It presents empirical measurements and configurations of disk subsystems achieving multi-gigabyte per second transfer rates for transcontinental data movement.

Findings

24-disk stripe achieves 1.2 GBps

32-disk stripe achieves 1.7 GBps

up to 3.5 GBps with advanced systems

Abstract

Moving data from CERN to Pasadena at a gigabyte per second using the next generation Internet requires good networking and good disk IO. Ten Gbps Ethernet and OC192 links are in place, so now it is simply a matter of programming. This report describes our preliminary work and measurements in configuring the disk subsystem for this effort. Using 24 SATA disks at each endpoint we are able to locally read and write an NTFS volume is striped across 24 disks at 1.2 GBps. A 32-disk stripe delivers 1.7 GBps. Experiments on higher performance and higher-capacity systems deliver up to 3.5 GBps.