Apache Spark

Apache Spark is a unified analytics engine for large-scale data processing, offering high performance for both batch and streaming data. It extends the MapReduce model to efficiently support more types of computations, including interactive queries, streaming analytics, machine learning, and…

Key facts

First appeared
2010
Category
technology
Problem solved
Apache Spark was created to address the limitations of Apache Hadoop MapReduce, particularly its inefficiency for iterative algorithms (e.g., machine learning, graph processing) and interactive queries, which required repeated disk I/O between stages. MapReduce's batch-only processing model also struggled with real-time data streams and complex workflows that needed to chain multiple operations with shared data.
Platforms
Kubernetes, Linux, Apache Mesos, Cloud platforms (AWS EMR, Azure HDInsight/Synapse Analytics, Google Cloud Dataproc), macOS, Windows, Standalone cluster manager, Apache Hadoop YARN

Related technologies

Notable users

  • Uber
  • Netflix
  • Capital One
  • Microsoft
  • Amazon
  • Walmart
  • Alibaba
  • Adobe
  • Google