Abstract: Storage disaggregation is an attractive storage consumption model as it comes with a lot of benefits, including the ability to independently scale compute and storage resources and achieve higher hardware utilization. In this presentation we introduce Crail, a system built specifically for fast networking and storage hardware and demonstrate how it enables Hadoop and Spark to use disaggregated storage efficiently.
Bio: Ioannis Koltsidas is a Research Staff Member at IBM Research – Zurich. He received a B.S. degree in Electrical and Computer Engineering from the National Technical University of Athens, Greece and a Ph.D. degree in Computer Science from the University of Edinburgh, UK. He subsequently joined IBM Research, where he is technical leader for R&D on Flash and Software-Defined Storage.