Presented By
O’Reilly + Cloudera
Make Data Work
29 April–2 May 2019
London, UK
Rohit Karlupia

Rohit Karlupia
Technical Director , Qubole

Website

Rohit Karlupia is a technical director at Qubole, where his primary focus is making big data as a service debuggable, scalable, and performant. His current work includes SparkLens (open source Spark profiler) and GC/CPU-aware task scheduling for Spark and Qubole Chunked Hadoop File System. Rohit’s primary research interests are performance and scalability of cloud applications. Over his career, he’s mainly been writing high-performance server applications and has deep expertise in messaging, API gateways, and mobile applications. He holds a bachelors of technology in computer science and engineering from IIT Delhi.

Sessions

16:35–17:15 Wednesday, 1 May 2019
Scalability-aware autoscaling of a Spark application
Data Engineering and Architecture
 Location: S11 A
Secondary topics:  AI and Data technologies in the cloud, Data Integration and Data Pipelines
Anirudha Beria (Qubole), Rohit Karlupia (Qubole)
Average rating: ***..
(3.67, 3 ratings)
Autoscaling of resources aims to achieve low latency for a big data application while reducing resource costs at the same time. Scalability-aware autoscaling uses historical information to make better scaling decisions. Anirudha Beria and Rohit Karlupia explain how to measure the efficiency of autoscaling policies and discuss more efficient autoscaling policies, in terms of latency and costs. Read more.