Smart Partitioning in Apache Apex (Next Gen Hadoop)

Presenter: Tushar Gosavi is a Software Development Engineer at DataTorrent and committer at Apache Apex.

Description: Stream processing is becoming increasingly popular because of the speed at which results are available for consumption by organizations. A typical scenario includes consuming data from a message queue and performing transformation and extracting important attributes from the data, which are later saved to external store or files. These applications keep running for months without taking any downtime. These applications have different resource requirements during peak hours and off-peak hours. Such applications can make use of the dynamic scalability feature of Apache Apex to optimally manage cluster under varying load. In this talk will focus on how to achieve smart partitioning under varying load load in Apache Apex.

Bio: Tushar Gosavi is a Software Development Engineer at DataTorrent and committer at Apache Apex. He has been working with DataTorrent from past 3 years before which he has worked on GPFS (IBM proprietary clustered filesystem) and Veritas Volume Manage.

Please use the following link to register for the webinar: https://attendee.gotowebinar.com/register/1246288015151420929

After registering, you will receive a confirmation email containing information about joining the webinar.

For deeper engagement with Apache Apex (http://apex.apache.org/), download (https://www.datatorrent.com/download/?utm_source=meetup&utm_medium=meetup_links&utm_campaign=links_in_description), view past meetup webinars (https://www.datatorrent.com/webinars/?utm_source=meetup&utm_medium=meetup_links&utm_campaign=links_in_description), slides (http://www.slideshare.net/DataTorrent), and docs (http://docs.datatorrent.com/?utm_source=meetup&utm_medium=meetup_links&utm_campaign=links_in_description).

To reduce time to market, look at operable app-templates (https://www.datatorrent.com/apphub/?utm_source=meetup&utm_campaign=links_in_description&utm_medium=meetup_links) that you can quickly import and launch.

Examples: HDFS-Sync (https://www.datatorrent.com/apphub/hdfs-sync/?utm_source=meetup&utm_campaign=links_in_description&utm_medium=meetup_links), Kafka-HDFS (https://www.datatorrent.com/apphub/kafka-to-hdfs-sync/?utm_source=meetup&utm_campaign=links_in_description&utm_medium=meetup_links), HDFS-Line-Copy (https://www.datatorrent.com/apphub/hdfs-to-hdfs-line-copy/?utm_source=meetup&utm_campaign=links_in_description&utm_medium=meetup_links), S3-HDFS (https://www.datatorrent.com/apphub/s3-to-hdfs-sync/?utm_source=meetup&utm_campaign=links_in_description&utm_medium=meetup_links) and HDFS-Kafka (https://www.datatorrent.com/apphub/hdfs-to-kafka-sync/?utm_source=meetup&utm_campaign=links_in_description&utm_medium=meetup_links).

Free DataTorrent Enterprise Edition for qualifying startups. Check it out (https://www.datatorrent.com/products-services/start-up-accelerator/?utm_source=meetup&utm_campaign=links_in_description_startup_accelerator&utm_medium=links)!

Brought to you by DataTorrent (https://www.datatorrent.com/?utm_source=meetup&utm_campaign=links_in_description&utm_medium=meetup_links), creators of Apache Apex.