ELIXIR proof of concept study on the availability of big datasets on remote compute infrastructure

Part of the EOSC-Hub project proposal it to establish an ELIXIR Competency Centre (ECC).  The EOSC-Hub proposal is currently under review by the EC and a funding decision is expected around late summer 2017 with a tentative project start date of January 2018. The focus of the ECC is to look at the distribution of reference data sets within the EOSC environment and it is proposed by the Compute Platform ExCo to kick-start the work within the ECC through a proof of concept study (funded by the ELIXIR-Hub) on making big data sets available on remote compute infrastructures.

Therefore the overall purpose of this Proof of Concept Study is to bring together funded work already taking place within ELIXIR-Excelerate, EUDAT2020 and the ELIXIR nodes into an integrated activity:

  • Deployment and integration of FTS3 by CESNET for use by ELIXIR and integrated into the ELIXIR AAI for use by RDSDS and other activities.
  • Deploy and test in a wide area testbed the first pre-releases from EMBL-EBI of the Reference Data Set Distribution Service (RDSDS) currently being developed by EMBL-EBI within the EUDAT 2020 project.
  • The expansion and performance of the current data transfer testbed to explore FTS3 and RDSDS by identifying ELIXIR nodes (and others) capable of hosting large reference data sets and the reference data sets that will be transferred to test the system

This study is now completed, the work is described in the end report. The outcome of this study is summarised in a webinar:

This study is associated with: The use of Cloud & VM for training.

Duration
1st October 2017 - 31st March 2018