What are your initial thoughts when you look at the following screenshot showing a Cassandra cluster which is running in the cloud and balanced across three AZs with a replication factor three, instance types and architectures are the same across them all? Is it that a few nodes are being hit hard? More compactions? The parameters are not consistent? Different versions of Cassandra? Bad hosts?
Figure 7.36: Two nodes are having different GC patterns than the rest
As we know that all the nodes have same instance type and architecture, we are comparing similar things. If you know different types of GCs are ...
