globus online Simplify big data sharing with Globus Online Steve - PowerPoint PPT Presentation

globus online Simplify big data sharing with Globus Online Steve Tuecke Computation Institute University of Chicago and Argonne National Laboratory

The Challenge: Moving and Sharing Big Data Easily • What should be trivial … “I need my data over there – at Transfer my _____” ( supercomputing Facility My center, campus server, etc.) Data S h a r e Colleague “I need to share my data with …”) • … can be tedious, time-consuming and expensive “GAAAH! ! ¡Accounts ¡& ¡access ¡control ¡ %&@#&” ! ¡Config ¡issues ¡ Data Data ! ¡Firewall ¡issues ¡ Source Destination ! ¡Unexpected ¡failure ¡ = ¡manual ¡retry ¡ www.globusonline.org 2

What is Globus Online? • Move, sync, share files – Easy “fire-and-forget” transfers – Share with any Globus user or group – Automatic fault recovery & high performance – Across multiple security domains – Web, command line, and REST interfaces • Minimize IT costs – Software as a Service (SaaS) • No client software installation • New features automatically available – Consolidated support & troubleshooting – Simple endpoint installation with Globus Connect and GridFTP • Recommended by EGI, XSEDE, NERSC, ESnet, ALCF, Blue Waters, NCAR, many Universities www.globusonline.org 3

globus online Globus Online Demo 4

Globus Online PaaS Research data management Platform as a Service (PaaS) 5

Globus Online Platform-as-a-Service • Create custom (web) applications that leverage Globus Online services – User identities, profiles, groups (Nexus) – File transfer, synchronization, sharing • Integrate via – REST APIs – Scriptable command line interface – Branded web pages www.globusonline.org 6

Globus Nexus: For when you want to … Manage groups Manage profiles Manage identities www.globusonline.org 7

Globus Genomics Focus on research, not IT. • Eliminate data transfer, sharing, and management challenges • Leverage best-practice anal- ysis pipelines (RNA-Seq, Ex- ome-Seq, ChIP-Seq, etc.) • Develop custom pipelines with full control over algorithms, applications, and parameters • Dramatically reduce sequenc- ing analysis turnaround time • Institutionalize bioinformatics expertise • Uses Globus Online & Galaxy platforms www.globusonline.org

support.globusonline.org www.globusonline.org

A platform for integration www.globusonline.org

Open Research Exeter data repository www.globusonline.org

Earth System Grid – Portal integration • Outsource ¡data ¡transfer ¡to ¡Globus ¡ – Data ¡download ¡to ¡user ¡machine ¡ from ¡search ¡ – Data ¡transfer ¡to ¡another ¡server ¡ by ¡user ¡ – Replica:on ¡of ¡data ¡between ¡sites ¡ by ¡administrator ¡ • No ¡ESGF ¡client ¡so?ware ¡needed ¡ www.globusonline.org 12

Non-profit Provider Plans ¡Planning ¡for ¡ Sustainability ¡ … ¡ … ¡ … ¡ … ¡ … ¡ … ¡ www.globusonline.org 13 h@ps://www.globusonline.org/provider-­‑plans/ ¡

For More Information • Visit www.globusonline.org/signup to: – Get a free account to start moving and sharing files • Visit www.globusonline.org for: – Tutorials, FAQs, Pro Tips, Troubleshooting – Papers, Case Studies • Visit support.globusonline.org or contact support@globusonline.org for: – Help – Forums • Follow us at @globusonline on Twitter and Globus Online on Facebook www.globusonline.org 14