Aerospike schema: which one is the better design?

We have database requirements as follows:- 1. Huge number of records: 10-100 millions per set. 2. Huge number of bins: around 100 bins 3. Some point queries need to be run within milliseconds. Now which one of the following two schema design philosophy will be better for aerospike? 1. Have one set of each type with all possible bins (in hundreds). But would it degrade Aerospike performance? 2. Categorize bins and have multiple sets with each set have around 10 bins max. But this means redundant keys in each set. High space complexity and hard to combine data for same key from different bins.