You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
There's no one-fits-all solution here, so feel free to override the default weighted 10ms limit per I/O if your environment hits the saturation limit way too frequently. If you believe the limit is generally very low (across various disk types) and should be increased, feel free to submit a PR.
Hi folks, I would like to understand how the threshold value of 10 was chosen for
diskIOSaturationThreshold
? I'm getting this alert from some EC2s and I'd like to understand the logic behind it. The disk is an SSD/NVMe. Relevant PR - https://github.com/prometheus/node_exporter/pull/2644/files#diff-781d91aa142e0ecff9a8504a8c48971f7573e624bc6be4b787d07099e92b31feR78-R80 @v-zhuravlevThe text was updated successfully, but these errors were encountered: