Agreed. If your data model is good and no major read latencies due to little or
no data skew, wide partitions, or tombstones, you can literally scale linearly.
You could also consider having a plan in which you ramp up as the traffic
increases.
Rahul Singh
Chief Executive Officer
m
Not a great idea to make config changes without testing. For a lot of
changes you can make the change on one node and measure of three is an
improvement however.
You'd probably be best to add nodes (double should be sufficient), do
tuning and testing afterwards, and then decommission a few nodes
Currently our cassandra prod is 18 node 3 dc cluster and application does
55 million reads per day and want to add load and make it 90 millon reads
per day.they need a guestimate of resources which we need to bump without
testing ..on top of my head we can increase heap and native trasport value
