ML - Feasibility and performance of analyzing all data on a Vertica cluster?

emichaud

Is it possible to analyze the entire data universe of an entire Vertica cluster, no matter the size? Can it be done without affecting performance?

Asked during the BDC session Model Management and Data Preparation
@WD @Arash_Fard

Vertica_Curtis

Definitely it's possible to do that, but there's no such thing as a free lunch. There is a cost of doing, well, anything, I suppose. But for ML specifically, Vertica uses the BLOBDATA resource pool to control machine learning activities. So, like any other workload, you can control and scale the machine learning resources using that resource pool specifically.