JVM + still have Detected pause in JVM in spite heap size decreased

we have old hadoop cluster based on HDP from hortonworks version HDP 2.6.4 cluster include 2 namenode services when one is the standby namenode and the second is the active namenode , all machines in the cluster are rhel 7.2 version , and we not see any problem on OS level

also cluster include 12 workers machines ( worker include the datanode and node manager services )

the story begin when we get alerts from the smoke test script that complain about "Detected pause in JVM or host machine" on the standby namenode ,

so based on that we decided to increase the namenode heap size from 60G to 100G