Exploiting Apache Spark platform for CMS computing analytics

TL;DR

This paper evaluates Apache Spark's effectiveness in analyzing large-scale CMS computing metadata, demonstrating its ability to handle billions of records efficiently for analytics and machine learning tasks.

Contribution

It presents a comprehensive evaluation of Spark for CMS data analytics, highlighting its suitability for processing extensive I/O intensive workloads using Scala and Python APIs.

Findings

Spark efficiently processes billions of records for CMS analytics.

Both Scala and PySpark APIs are effective for I/O intensive queries.

Spark enables valuable insights from CMS meta-data.

Abstract

The CERN IT provides a set of Hadoop clusters featuring more than 5 PBytes of raw storage with different open-source, user-level tools available for analytical purposes. The CMS experiment started collecting a large set of computing meta-data, e.g. dataset, file access logs, since 2015. These records represent a valuable, yet scarcely investigated, set of information that needs to be cleaned, categorized and analyzed. CMS can use this information to discover useful patterns and enhance the overall efficiency of the distributed data, improve CPU and site utilization as well as tasks completion time. Here we present evaluation of Apache Spark platform for CMS needs. We discuss two main use-cases CMS analytics and ML studies where efficient process billions of records stored on HDFS plays an important role. We demonstrate that both Scala and Python (PySpark) APIs can be successfully used to execute extremely I/O intensive queries and provide valuable data insight from collected meta-data.