summaryrefslogtreecommitdiffstats
path: root/health/health.d/ml.conf
diff options
context:
space:
mode:
Diffstat (limited to '')
-rw-r--r--health/health.d/ml.conf56
1 files changed, 56 insertions, 0 deletions
diff --git a/health/health.d/ml.conf b/health/health.d/ml.conf
new file mode 100644
index 00000000..aef9b036
--- /dev/null
+++ b/health/health.d/ml.conf
@@ -0,0 +1,56 @@
+# below are some examples of using the `anomaly-bit` option to define alerts based on anomaly
+# rates as opposed to raw metric values. You can read more about the anomaly-bit and Netdata's
+# native anomaly detection here:
+# https://learn.netdata.cloud/docs/agent/ml#anomaly-bit---100--anomalous-0--normal
+
+# some examples below are commented, you would need to uncomment and adjust as desired to enable them.
+
+# node level anomaly rate
+# https://learn.netdata.cloud/docs/agent/ml#node-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
+ summary: ML node anomaly rate
+ 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).
+# if anomaly rate is above 20% then critical (pick your own threshold that works best via tial and error).
+# template: ml_5min_cpu_dims
+# on: system.cpu
+# os: linux
+# hosts: *
+# lookup: average -5m anomaly-bit foreach *
+# calc: $this
+# units: %
+# every: 30s
+# warn: $this > (($status >= $WARNING) ? (5) : (20))
+# crit: $this > (($status == $CRITICAL) ? (20) : (100))
+# info: rolling 5min anomaly rate for each system.cpu dimension
+
+# alert per chart example
+# if anomaly rate is between 5-20% then warning (pick your own threshold that works best via tial and error).
+# if anomaly rate is above 20% then critical (pick your own threshold that works best via tial and error).
+# template: ml_5min_cpu_chart
+# on: system.cpu
+# os: linux
+# hosts: *
+# lookup: average -5m anomaly-bit of *
+# calc: $this
+# units: %
+# every: 30s
+# warn: $this > (($status >= $WARNING) ? (5) : (20))
+# crit: $this > (($status == $CRITICAL) ? (20) : (100))
+# info: rolling 5min anomaly rate for system.cpu chart
+