I have a 3 node solr datastax cluster and if I run the following apache bench curl against node3, I see higher load against node1 by a lot.
ab -k -c 100 -n 10000 "http://node3:8983/solr/test.solr/select?q=*%3A*&wt=xml&indent=true"
It doesn't matter what node I query in the cluster, node1 always has higher cpu load? Can this be explained?