Hello All,
I have a 12 node cluster with 64GB RAM and 31GB heap memory. Often late i am having issues with Elasticsearch performance, i happen to observe that there are major and minor page faults as below.
ps -ef | grep -E "[e]lastic.*java" | awk '{print $2}' | xargs -I {} ps -o min_flt,maj_flt {} && sleep 60 && ps -ef | grep -E "[e]lastic.*java" | awk '{print $2}' | xargs -I {} ps -o min_flt,maj_flt {}
MINFL MAJFL
185689007 298915
MINFL MAJFL
185717299 298918
ps -ef | grep -E "[e]lastic.*java" | awk '{print $2}' | xargs -I {} ps -o min_flt,maj_flt {} && sleep 60 && ps -ef | grep -E "[e]lastic.*java" | awk '{print $2}' | xargs -I {} ps -o min_flt,maj_flt {}
MINFL MAJFL
283503608 2427945
MINFL MAJFL
283544632 2428401
ps -ef | grep -E "[e]lastic.*java" | awk '{print $2}' | xargs -I {} ps -o min_flt,maj_flt {} && sleep 60 && ps -ef | grep -E "[e]lastic.*java" | awk '{print $2}' | xargs -I {} ps -o min_flt,maj_flt {}
MINFL MAJFL
277297674 1118228
MINFL MAJFL
277341921 1118338
and so on.
Could this indicate a problem? CPU, Memory, IOWAIT utilizations are pretty much very low values. Increasing the memory beyond 64GB would help?