SQL and NoSQL on Hadoop – a look at performance

Dear HUG UK members,

I am pleased to announce our September meetup - details below.

This meetup will be sponsored by EXASOL and Bigstep and our evening hosts will be King.

Looking forward to seeing you there.

Best,

Sebastian

TIME: Tuesday September 16 - Doors open 6:30pm, Presentations from 7:00pm to 8:30pm.

LOCATION: King, Central Saint Giles, 1 St Giles High Street, London, WC2H 8AG

AGENDA

Session 1: SQL and high performance computing on Hadoop

Speaker: Graham Mossman, Senior Solutions Engineer at EXASOL

Abstract: As usage of Hadoop has broadened, alternative frameworks are emerging which offer more high performance computing based on SQL and ‘SQL-like’ technologies. In this talk, Graham considers how Hadoop and SQL alternatives compare in terms of use cases, best practice, functionality and performance. He goes on to consider future possible market outcomes with regard to Hadoop and SQL architectures and integration options.

Short bio: Graham is an expert in data warehouse architecture and the integration and optimisation of ETL and BI tools to meet both operational and business requirements. Graham won the DM Review ‘World Class Solution’ Award in 2005, as Data Architect for Caudwell Communications’ pioneering Netezza data warehouse, and has spent the last ten years specialising in MPP (Massively Parallel Processing).

Session 2: Platform performance comparisons, bare metal and cloud hosting alternatives

Speaker: Dave Shuttleworth, Principal Consultant at EXASOL

Abstract: Choosing the right database technology and deployment platform can have a major impact on performance and total cost of ownership in production environments. Using the industry TPC-DS benchmark, Dave will present findings from a performance and TCO comparison of EXASOL on dedicated servers, Bigstep bare metal cloud and AWS. The presentation will be a tutorial on performance benchmarking.

Short bio: Dave is a recognised authority in the database field and has been instrumental in helping to develop the global landscape for parallel processing for commercial databases. He has worked in pre and post sales for the likes of Data General, Teradata, and Kognitio and was previously a Director of intelligent Edge Group, where he specialised in the migration and implementation of data warehouses.

Session 3: Connecting Hadoop with Couchbase: Engineering for performance

Speakers: Calin-Andrei Burloiu, Big Data Engineer @ Avira; Radu Pastia, Software Developer @ Orange; Alex Bordei, Product Manager @ Bigstep

Abstract: We needed a bridge between the real-time tier, where we used Couchbase, and the batch tier, built on Hadoop. For lack of something better, we built our own: Couchdoop – an open-source Hadoop connector for Couchbase. Our presentation will discuss best practices on how to create a Hadoop connector for a NoSQL database. We will talk about the challenges we encountered while developing Couchdoop and share how we tuned it for performance. Together with Bigstep we worked on performance benchmarks for our technology, which show how much throughput that can be squeezed from a Hadoop connector.

Short bios: Calin-Andrei has been working as a Big Data Engineer for Avira since 2013. His exploration of big data started in 2012 during an internship at the National University of Singapore where he had his first contact with the Hadoop ecosystem. He holds a M.Sc. in Computer Science and is currently working on a Ph.D. Follow him on Twitter @CalinBurloi.

Radu Pastia: I've been working with Hadoop two years ago, when I started the Big Data Team at Avira. At first I was oriented more towards the operations side - sizing and setting up our new Hadoop cluster to run smoothly. As our setup stabilized, I started delving deeper into data science and machine learning. I have been coding ever since I had my first home computer running BASIC and my background before Hadoop is in backend scripting for web-based applications.

Alex has been developing infrastructure products for over nine years. Before becoming Bigstep's Product Manager, he was one of the core developers for Hostway Corporation's provisioning platform. After successfully launching two public clouds based on VMware software, he created the first prototype of Bigstep's Full Metal Cloud in 2011. He now focuses on guaranteeing that the Full Metal Cloud is the highest performance cloud in the world, for big data applications. Twitter: @alexandrubordei