diff options
author | Andrew Maguire <andrewm4894@gmail.com> | 2023-09-13 14:21:52 +0100 |
---|---|---|
committer | GitHub <noreply@github.com> | 2023-09-13 16:21:52 +0300 |
commit | 92515e41a52344fb1d346df5b54b953cb9de5055 (patch) | |
tree | 704f796a76dd16a7e0c39dc39a3ae37f0fd27881 | |
parent | db25063e9018078354e8063bc962f8596145071c (diff) |
enable `ml_1min_node_ar` as a default alert (#14687)
Co-authored-by: Ilya Mashchenko <ilya@netdata.cloud>
-rw-r--r-- | health/health.d/ml.conf | 32 |
1 files changed, 17 insertions, 15 deletions
diff --git a/health/health.d/ml.conf b/health/health.d/ml.conf index 6836ce7b1a..94d6303ed8 100644 --- a/health/health.d/ml.conf +++ b/health/health.d/ml.conf @@ -3,23 +3,25 @@ # native anomaly detection here: # https://learn.netdata.cloud/docs/agent/ml#anomaly-bit---100--anomalous-0--normal -# examples below are commented, you would need to uncomment and adjust as desired to enable them. +# some examples below are commented, you would need to uncomment and adjust as desired to enable them. -# node level anomaly rate example +# node level anomaly rate # https://learn.netdata.cloud/docs/agent/ml#node-anomaly-rate -# if node level anomaly rate is between 1-5% then warning (pick your own threshold that works best via tial and error). -# if node level anomaly rate is above 5% then critical (pick your own threshold that works best via tial and error). -# template: ml_1min_node_ar -# on: anomaly_detection.anomaly_rate -# os: linux -# hosts: * -# lookup: average -1m foreach anomaly_rate -# calc: $this -# units: % -# every: 30s -# warn: $this > (($status >= $WARNING) ? (1) : (5)) -# crit: $this > (($status == $CRITICAL) ? (5) : (100)) -# info: rolling 1min node level anomaly rate +# if node level anomaly rate is above 1% then warning (pick your own threshold that works best via trial and error). + template: ml_1min_node_ar + on: anomaly_detection.anomaly_rate + class: Workload + type: System +component: ML + os: * + hosts: * + lookup: average -1m of anomaly_rate + calc: $this + units: % + every: 30s + warn: $this > 1 + info: rolling 1min node level anomaly rate + to: silent # alert per dimension example # if anomaly rate is between 5-20% then warning (pick your own threshold that works best via tial and error). |