I am just checking math, not model. On Tue, Apr 13, 2010 at 10:48 AM, Time Less <timelessn...@gmail.com> wrote:
> > numRowsOnNode = 10B / 20 = 500M. 50 million > replicationFactor = 3. > rowsPerSStable = 128MB / 1K = 131k. > > Therefore worst-case iops per read on this cluster are: > (500M * 3 / 131k) * 3 = 150M / 131k = 11,450. This line isn't internally consistent. Where did 150M come from? 500 M * 9 = 4.5 Billion. My calculation for the whole thing is 3433. I am not claiming to be a Cassandra expert and therefore cannot vouch for the model at all. Paul Prescod
