Spark

Unravel For
Spark

Spark enables rapid innovation and high performance in your applications and Unravel makes Spark perform better and more reliably. Unravel provides deep insights and intelligence into the Spark runtime environment, and helps your team keep your data pipelines production-ready – and keep your applications running at optimal levels.

Unravel delivers peak performance and reliability for your Spark data pipelines

Unravel for Spark provides a comprehensive full-stack, intelligent, and automated approach to Spark operations and application performance management across the big data architecture. The Unravel platform helps you to analyze, optimize, and troubleshoot Spark applications and pipelines in a seamless, intuitive user experience.

Running Spark with clarity and KPIs

Instantly observe and understand Spark behavior

Unravel displays the inner workings of the Spark environment as well as running applications and data pipelines in an intuitive user interface. Data teams can quickly drill down to get detailed operational context and AI-powered recommendations from nravel. Unravel Spark insights include:

  • App-specific KPIs such as job status, duration, I/O, # of stages, tasks, and more.
  • Understanding data usage and access across the Spark stack.
  • Getting an interactive view of Spark application slowdowns, failures, killed jobs, and resource consumption.

Intuitive Spark tuning and troubleshooting

Unravel provides drill down views, workflows, and insights into Spark jobs and pipelines

Unravel enables you to work the way you intuitively want to work, with time saving automation and drill down workflows that include helpful metrics and insights:

  • Gantt chart of stage timelines to identify bottlenecks, errors, and misconfigurations.
  • Insights into Spark executor memory/instances,  parallelism, partitioning, garbage collection and more.
  • Automated root cause analysis with views and parameter tweaks to get failed apps back up and running

Optimal Spark pipelines through metrics and context

AI-driven intelligence engine provides insights, recommendations, alerts, and actions

Unravel uses AI, ML and other advanced analytics to provide insights, recommendations and auto-tuning for Spark applications and pipelines. This enables:

  • Policy-driven automation for resolving errors, auto-tuning Spark applications and much more.
  • Context sensitive recommendations delivered in plain language for advanced topics like RDD Caching, CPU resource contention, and container resource utilization to improve app efficiencies and stability.
  • Proactive alerting via PagerDuty, Slack, and emails on detection of SLA violations, cluster resource contention, and degraded cluster performance.

Diagram: Unravel integration with the Spark platform

Learn more about Unravel for Spark.

Uncover what is crippling your Spark data pipelines.

Request your free trial