databricks blk

Optimizing Apache Spark™ on Databricks

In this course, students will explore five key problems that represent the vast majority of performance problems in an Apache Spark application: skew, spill, shuffle, storage, and serialization. With...

Read More
$1,500 USD
Course Code OPTSPARK
Duration 2 days
Available Formats Classroom
6320 Reviews star_rate star_rate star_rate star_rate star_half
Course Image

In this course, students will explore five key problems that represent the vast majority of performance problems in an Apache Spark application: skew, spill, shuffle, storage, and serialization. With each of these topics, we explore coding examples based on 100 GB to 1+ TB datasets that demonstrate how these problems are introduced, how to diagnose these problems with tools like the Spark UI, and conclude by discussing mitigation strategies for each of these problems.

We continue the conversation by looking at a series of key ingestion concepts that promote strategies for processing terabytes of data including managing Spark partition sizes, disk-partitioning, bucketing, z-ordering, and more. With each of these topics, we explore when and how each of these techniques should be implemented, new challenges that productionalizing these solutions might provide along with corresponding mitigation strategies.

Finally, we introduce a couple of other key topics such as issues with data locality, IO caching and spark caching, pitfalls of broadcast Joins, and new features like Spark 3’s Adaptive Query Execution and Dynamic Partition Pruning. We then conclude the course with discussions and exercises on designing and configuring clusters for optimal performance given specific use cases, personas, the divergent needs of various teams, and cross-team security concerns.

Who Can Benefit

  • Data engineer
  • Data architect

Prerequisites

  • Intermediate to advanced programming experience in Python or Scala
  • Hands-on experience developing Apache Spark applications

Course Details

Day 1 Morning: Introduction and the 5 Most Common Performance Problems

  • Setup, Introductions
  • Spark Architecture Review
  • Spark UI Review, Lab
  • Skew, Labs

Day 1 Afternoon: The 5 Most Common Performance Problems Continued

  • Spill, Labs
  • Shuffle
  • Storage, Labs
  • Serialization, Labs

Day 2 Morning: Key Ingestion Concepts

  • Ingestion Basics, Labs
  • Predicate Push Downs, Labs
  • Disk Partitioning, Lab
  • Z-Ordering, Labs
  • Bucketing, Labs

Day 2 Afternoon: Optimizing with AQE and High Performance; Designing Clusters for High Performance

  • Tuning Shuffle Partitions, Lab
  • Join Optimizations, Lab
  • Skew Join Optimizations, Lab
  • Dynamic Partition Pruning, Lab
  • Designing Clusters for High Performance
  • Cluster Configurations Scenarios
  • Designing Clusters Breakout
Contact Us 1-800-803-3948
Contact Us
FAQ Get immediate answers to our most frequently asked qestions. View FAQs arrow_forward