Reply
Highlighted
Contributor
Posts: 27
Registered: ‎07-20-2016

Hadoop process swap memory

Some of the Hadoop processes like YarnChild, DataNode, NodeManager are slightly using swap memory (10MB),  there is enough memory available (usage is only 20GB of 500GB, buff/cache 450GB), enough heap available for these processes.

 

CentOS 7, CDH enterprise 5.14.0,

RAM 500GB

vm.swappiness=1 

 

When we run

 

echo 3 > /proc/sys/vm/drop_caches

 

its not swapping any more, again started swapping when buff/cache reached around 450GB

 

any suggestion? thanks

 

 

Announcements