Spark: Difference between revisions

From NovaOrdis Knowledge Base
Jump to navigation Jump to search
No edit summary
 
Line 11: Line 11:
* [[Iceberg]]
* [[Iceberg]]
* [[Alluxio]]
* [[Alluxio]]
* [[Spark K8s Operator]]
* [[Spark Operator]]
* [[Genie]]
* [[Genie]]
* [[Livy]]
* [[Livy]]
Line 29: Line 29:
* Spark history server
* Spark history server
* Spark remote shuffle service
* Spark remote shuffle service
* [[Spark K8s Operator]]
* [[Spark Operator]]

Latest revision as of 16:25, 17 May 2022

External

Internal

Overview

Spark is a third generation unified analytics engine for large-scale data processing. It natively supports batch processing and stream processing. Stream processing is implemented as micro-batching. It uses HDFS as state backend.

Subjects

Organizatorium

  • Spark SQL
  • PySpark/Spark SQL in interactive mode on JupyterHub.
  • Spark batch and streaming.
  • Spark job.
  • Spark UI
  • Spark history server
  • Spark remote shuffle service
  • Spark Operator