Compressed data per node

The vertica Hardware planning Guide indicates the following

“Each node should have 1–9 TB of storage post RAID”

I understand having a large amount of data per node will result in longer node recovery times if an entire node needs to be recovered.

In many uses cases this will not work as the CPUS would be overwhelmed if the data was moderately active.  In my use case the majority of the data is rarely accessed. 

I was curious if anyone was running any clusters with 9TB or more PER node?  



Leave a Comment

BoldItalicStrikethroughOrdered listUnordered list
Align leftAlign centerAlign rightToggle HTML viewToggle full pageToggle lights
Drop image/file