Nodes Stats: disk_service_time

Hi,

debugging a performance problem on an Elasticsearch cluster (running Elasticsearch version 1.7.5) and I suspect that disk I/O might be the bottleneck (since CPU and memory are clearly not).
I am monitoring the /_nodes/stats metrics from all the nodes, and I noticed disk_service_time among the fs metrics.
Can someone explain what this metric says precisely?

Thanks in advance

This topic was automatically closed 28 days after the last reply. New replies are no longer allowed.