We are running with 3 DC's in a cluster (all are running on core Cassandra) and couple of keyspaces replicating over all 3 DC's and some only 2 DC's.
During the load tests we are noticing huge spike on Mutations and Backpressure rejections, resulting read and write timeouts for couple seconds. And this is happening once in entire load test (we use to do 2 hours load test) so that's little concerning us because if servers are overloaded this should happen very frequently right! during 2 hours load test.
DSE Version: 6.7.3 Workloads: Cassandra
I would like to understand, what is backpressure and how is this causing read and write timeouts?
Thanks in Advance.