On Tue, Apr 13, 2010 at 12:00 PM, Benjamin Black <b...@b3k.us> wrote: >> I am probably being totally naive, but is the answer to the question >> "worst iops on read" just: >> >> 3 reads per SSTable * 4 SStables * ReplicationFactor ? >> >> = 3 * 4 * 3 = 36? >> > > Why does RF enter this?
A simplistic model for a consistent read that is asking all replicas what their value is for the key. If the key is in the fourth SSTable of all nodes, won't they all have to do 12 IOPs to find it? Paul Prescod
