Present situation and future of spark

Spark is a cluster computing platform originating from the Amplab of the University of California, Berkeley, which is a rare versatile player, based on memory computing, starting with multiple iterations, and eclectic data warehousing, streaming and graph computing paradigms. Spark is now the Apache Foundation's top open source project, with a huge community support, technology is gradually maturing, but to really put into production, but also need to undergo a lot of optimization. With shark, Spark streaming and related projects as the theme, Spark summit invited to Yahoo, Adobe, Intel, Amazon, RedHat, Databricks and many other well-known corporate executives, Share Spark first-hand practice within the enterprise.

1. Current status and future of Dr. Matei Zaharia:spark, Ph. D., University of California, Berkeley

Matei Zaharia is a ph. D. In the AMP Lab at the University of California, Berkeley, and co-founder and incumbent CTO of Databricks Corporation. Zaharia is dedicated to systems and algorithms for large-scale data-intensive computing. Research projects include: Spark, Shark, Multi-resource fairness, MapReduce scheduling, SNAP Sequence Aligner, the Spark summit he mainly The present situation and future of Spark are elaborated in detail.

2. Databricks CEO Ion Stoica: converting data into value

Ion Stoica is UC Berkeley computer professor, Amplab co-founder, flexible Peer-to-peer protocol chord, cluster Memory computing framework spark, cluster resource management platform Mesos all from him. At the Spark summit on how to transform the data into value, mainly for the problem of increasing data volume. Databricks Company's goal is to build the next generation of large data analysis tools, Stoica from many aspects of the analysis of spark advantages.

3. Mike Franklin, director of the University of California, Berkeley Amp Laboratory:

Large data research in the AMP lab

Mike Franklin, director of the University of California, Berkeley Amp Laboratory, at the Spark Summit, gave a detailed description of the large data research team, resources, results and future challenges of the University of California Amp Laboratory.

Integrated Spark/shark to Yahoo data analysis platform

Tim Tully,yahoo Senior Engineer, at this spark summit from the Hadoop architecture issue, reflect on the shortcomings, by comparing the previous architecture of Yahoo, explain why Yahoo future architecture model Integration Spark/shark, and future shark hardware conditions and physical deployment.

5. Former vice president of Yahoo Hadoop project Eric Baldeschwieler:spark in the Hadoop ecosystem

Eric Baldeschwieler, the former vice-president of Yahoo's Hadoop project and Hortonworks's former CTO, has been the active whoop of the Spark+hadoop model, and he still doesn't change the way he used to be, from Yahoo's history of using Hadoop, As well as spark today, the advantages of the Spark+hadoop model is the future trend.

6. Sharethrough data expert Ryan Weald: product spark Streaming media

Ryan Weald is a Sharethrough data specialist focusing on Hadoop, Scala, scalding, Ruby, Rails, Machine Learning, SQL, and more. Ryan Weald's interest is in data and machine learning how to improve people's living standards and their applications in healthcare, driving business, and advertising data.

Co-founder and CEO of 7.Adatao company Christopher Nguyen: A large data solution supported by Spark, full-featured Enterprise

Christopher Nguyen, co-founder and CEO of Adatao, the theme of the speech is that data intelligence will be ubiquitous, sharing the spark-supported enterprise large data Solutions Adatao pinsight. Christopher Nguyen at the meeting focused on the performance of the Adatao Pinsight, as well as the network service providers, after-sales service, mobile platform and so on to explain its advantages, and finally demonstrated its strong extended performance.

8.Quantifind Company's Austin Gibbons: Sharing is love, let the Data science team use Laburnum

Austin Gibbons the Spark summit focused on Laburnum multi-user development environment, architecture, easy-to-use, powerful flexibility, visualization tools, and shared its greatest advantages--resource sharing and dynamic publishing spark query And also focuses on the powerful functions of the Sumac command-line parser. In a word, laburnum is very easy to use and open source.

9.Yahoo Senior architect Andy Feng: Unified collaboration with Yahoo. Hadoop and Spark

Andy Feng,yahoo Senior Architect, through the Spark summit focused on the status of Yahoo, through an illustrated presentation of Yahoo's homepage and personalized customization, as well as pilot e-commerce and advertising business, Focusing on the unified collaboration between Hadoop and Spark is the only solution to the many challenges Yahoo faces today.

10.Mesosphere Advanced software engineer Paco Nathan:spark Enterprise use case on elastic mesos

Mesosphere Senior Software engineer Paco Nathan at the summit detailed information on how to use Mesos, why Mesos, and its architecture, deployment, and Mesos resources.