Philips Wellcentive Case Study (PDF)
Pepperdata Shines a Light into Philips Wellcentive
“Before Pepperdata, we experimented with various approaches to solve our performance issues and we could never see deep enough into the cluster to get insight.
Platform Spotlight shined a bright light into our Hadoop environment and provided the detailed data that helped us isolate and resolve the problem.”
– Geovanie Marquez, Philips Wellcentive Software Architect
Philips Wellcentive processes over 35 million patients and three billion medical records daily. Their cluster became unpredictable when jobs and SLAs failed due to a critical performance issue. Despite engaging third-party support, the Hadoop technical team spent six months diagnosing the problem without success. Existing monitoring solutions didn’t provide the data to pinpoint the problem. As jobs failed, resolving the issue was the top priority.
Philips Wellcentive deployed Platform Spotlight to collect hundreds of metrics associated with the consumption of CPU, memory, disk I/O, and network resources by container/task, job, user, and group in their cluster. Platform Spotlight Capacity Optimizer was also enabled, to increase cluster throughput and streamline the operations process to meet daily revenue targets.
Philips Wellcentive fixed the root cause of the critical performance issue within days of installing Platform Spotlight. The cluster achieved a significant increase in cluster performance throughput. Jobs completed on time and SLAs were met. The technical team returned to focusing on core initiatives, streamlining operations, and meeting revenue targets.