The final step in testing was to ingest 10 TB of data, which is 10 times the amount of data than the 1 TB that was used for all the other steps that are described in this white paper. The goal was simple: test the ingest of a lot of data.
We used curl to ingest the data into the storage pool. The ingest was completed successfully with no performance issues or errors. The ability of the Big Data Cluster to ingest 10 TB of data was consistent. Because resolving issues takes valuable time and delays projects, achieving consistency is important. The Big Data Cluster enabled big data management and data virtualization, and it performed well on the PowerFlex system.