If you are at the scale you can't dump it on just 1-2 nodes and call it a day [which is when you are start looking at Cassandra or a dedicated TSD] ...you really need 3 DC availability usually and Redis simply cannot do that in any reasonable way.
Even if you don't need a dedicated TSD with redundancy - Redis would still be more expensive to run given that you you would need to keep everything in memory. Given that you won't read 90% of the data most of the time, it makes little sense to store all of it in memory
If you are at the scale you can't dump it on just 1-2 nodes and call it a day [which is when you are start looking at Cassandra or a dedicated TSD] ...you really need 3 DC availability usually and Redis simply cannot do that in any reasonable way.