BETTER PERFORMANCE FOR SPARK ON HADOOP GUIDE READ MORE
Application Spotlight: Powerful Application Performance Monitoring
Get a 360° APM View of Your Big Data Applications
Pepperdata Application Spotlight provides you with a 360° view of all your data in one place, so you can gauge performance in the context of the entire cluster. Application performance monitoring allows you to quickly diagnose application performance issues up to 90% faster, and improve overall efficiency. Pepperdata also delivers job-specific recommendations and allows you to set up alerts on specific behaviors and outcomes to avoid the risk of failure.

Understand whether performance issues were caused by your application or are a result of cluster performance.

Profile and optimize application performance via recommendations and key performance indicators.

Understand exactly what CPU and memory resources an application requested – what it needs, what it used, and what it wasted.

Identify the impact that queue congestion, bottlenecks, and hardware failures have on application performance.
Get Recommendations
to Optimize Spark
Improve the performance and efficiency of your Spark applications. Achieve optimal application performance on multi-tenant systems no matter where you’re running your workloads on (i.e, on premises, AWS, Azure, or Google Cloud).


Change configuration parameters
to optimize performance.

Tune CPU based on actual consumption and get self-service recommendations on container sizes and heap reservations.

Change queue selection based
on cluster activity.
Create and Receive Alerts
on Application Performance
Create and receive alerts about events that interfere with application performance.


Use a real-time big data APM to identify resource bottlenecks, including CPU, memory, and IO.

Pinpoint straggling tasks or poor parallelization that can impact runtime.

Identify applications at risk of missing an SLA – alert on duration, amount of data processed, or other milestones.
Benefits

Operators
- Reduce the number of performance incidents in production
- Communicate detailed performance issues back to developers

Developers
- Highlight applications that need monitoring.
- Automatically identify bottlenecks, and alert on duration, failure conditions, and resource usage.
- Search applications running on a cluster, compare current and previous runs, visualize for root cause failure analysis and performance tuning.

Enterprise Organizations
- Improve communication of performance issues between Dev and Ops teams
- Shorten time to production
- Increase cluster ROI with application performance monitoring
