summaryrefslogtreecommitdiffstats
path: root/health/health.d/ml.conf
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2022-08-12 07:26:17 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2022-08-12 07:26:17 +0000
commit7877a98bd9c00db5e81dd2f8c734cba2bab20be7 (patch)
treed18b767250f7c7ced9b8abe2ece784ac1fe24d3e /health/health.d/ml.conf
parentReleasing debian version 1.35.1-2. (diff)
downloadnetdata-7877a98bd9c00db5e81dd2f8c734cba2bab20be7.tar.xz
netdata-7877a98bd9c00db5e81dd2f8c734cba2bab20be7.zip
Merging upstream version 1.36.0.
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'health/health.d/ml.conf')
-rw-r--r--health/health.d/ml.conf36
1 files changed, 36 insertions, 0 deletions
diff --git a/health/health.d/ml.conf b/health/health.d/ml.conf
new file mode 100644
index 000000000..9bcc81e76
--- /dev/null
+++ b/health/health.d/ml.conf
@@ -0,0 +1,36 @@
+# 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/configure/machine-learning#anomaly-bit---100--anomalous-0--normal
+
+# examples below are commented, you would need to uncomment and adjust as desired to enable them.
+
+# 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 \ No newline at end of file