Fix alertmanager alert context "unkown -> unknown" (#3430)

SeldonIO · Jul 26, 2021 · 7d99f0f · 7d99f0f
1 parent a7a29d4
commit 7d99f0f
Show file tree

Hide file tree

Showing 13 changed files with 19 additions and 19 deletions.
diff --git a/helm-charts/seldon-core-analytics/files/prometheus/prometheus-config.yaml b/helm-charts/seldon-core-analytics/files/prometheus/prometheus-config.yaml
@@ -11,7 +11,7 @@ alerting:
   alertmanagers:
   - static_configs:
     - targets:
-      - alertmanager
+      - seldon-core-analytics-prometheus-alertmanager
 scrape_configs:
 - job_name: kubernetes-nodes
   tls_config:

diff --git a/helm-charts/seldon-core-analytics/files/prometheus/rules.default/cpu-usage.rules.yml b/helm-charts/seldon-core-analytics/files/prometheus/rules.default/cpu-usage.rules.yml
@@ -6,7 +6,7 @@ groups:
       * 100)) > 75
     for: 2m
     labels:
-      context: unkown
+      context: unknown
       severity: page
     annotations:
       DESCRIPTION: '{{$labels.instance}}: CPU usage is above 75% (current value is:

diff --git a/...arts/seldon-core-analytics/files/prometheus/rules.default/instance-availability.rules.yml b/...arts/seldon-core-analytics/files/prometheus/rules.default/instance-availability.rules.yml
@@ -5,7 +5,7 @@ groups:
     expr: up == 0
     for: 1m
     labels:
-      context: unkown
+      context: unknown
       severity: page
     annotations:
       description: '{{ $labels.instance }} of job {{ $labels.job }} has been down

diff --git a/helm-charts/seldon-core-analytics/files/prometheus/rules.default/low-disk-space.rules.yml b/helm-charts/seldon-core-analytics/files/prometheus/rules.default/low-disk-space.rules.yml
@@ -6,7 +6,7 @@ groups:
       / node_filesystem_size{mountpoint="/"} * 100) > 75
     for: 2m
     labels:
-      context: unkown
+      context: unknown
       severity: page
     annotations:
       DESCRIPTION: '{{$labels.instance}}: Root disk usage is above 75% (current value
@@ -17,7 +17,7 @@ groups:
       / node_filesystem_size{mountpoint="/data-disk"} * 100) > 75
     for: 2m
     labels:
-      context: unkown
+      context: unknown
       severity: page
     annotations:
       DESCRIPTION: '{{$labels.instance}}: Data disk usage is above 75% (current value

diff --git a/helm-charts/seldon-core-analytics/files/prometheus/rules.default/mem-usage.rules.yml b/helm-charts/seldon-core-analytics/files/prometheus/rules.default/mem-usage.rules.yml
@@ -6,7 +6,7 @@ groups:
       * 100) > 75
     for: 2m
     labels:
-      context: unkown
+      context: unknown
       severity: page
     annotations:
       DESCRIPTION: '{{$labels.instance}}: Swap usage usage is above 75% (current value
@@ -17,7 +17,7 @@ groups:
       * 100)) > 75
     for: 2m
     labels:
-      context: unkown
+      context: unknown
       severity: page
     annotations:
       DESCRIPTION: '{{$labels.instance}}: Memory usage is above 75% (current value

diff --git a/helm-charts/seldon-core-analytics/files/prometheus/rules/cpu-usage.rules.yml b/helm-charts/seldon-core-analytics/files/prometheus/rules/cpu-usage.rules.yml
@@ -6,7 +6,7 @@ groups:
       * 100)) > 75
     for: 2m
     labels:
-      context: unkown
+      context: unknown
       severity: page
     annotations:
       DESCRIPTION: '{{$labels.instance}}: CPU usage is above 75% (current value is:

diff --git a/helm-charts/seldon-core-analytics/files/prometheus/rules/instance-availability.rules.yml b/helm-charts/seldon-core-analytics/files/prometheus/rules/instance-availability.rules.yml
@@ -5,7 +5,7 @@ groups:
     expr: up == 0
     for: 1m
     labels:
-      context: unkown
+      context: unknown
       severity: page
     annotations:
       description: '{{ $labels.instance }} of job {{ $labels.job }} has been down

diff --git a/helm-charts/seldon-core-analytics/files/prometheus/rules/low-disk-space.rules.yml b/helm-charts/seldon-core-analytics/files/prometheus/rules/low-disk-space.rules.yml
@@ -6,7 +6,7 @@ groups:
       / node_filesystem_size{mountpoint="/"} * 100) > 75
     for: 2m
     labels:
-      context: unkown
+      context: unknown
       severity: page
     annotations:
       DESCRIPTION: '{{$labels.instance}}: Root disk usage is above 75% (current value
@@ -17,7 +17,7 @@ groups:
       / node_filesystem_size{mountpoint="/data-disk"} * 100) > 75
     for: 2m
     labels:
-      context: unkown
+      context: unknown
       severity: page
     annotations:
       DESCRIPTION: '{{$labels.instance}}: Data disk usage is above 75% (current value

diff --git a/helm-charts/seldon-core-analytics/files/prometheus/rules/mem-usage.rules.yml b/helm-charts/seldon-core-analytics/files/prometheus/rules/mem-usage.rules.yml
@@ -6,7 +6,7 @@ groups:
       * 100) > 75
     for: 2m
     labels:
-      context: unkown
+      context: unknown
       severity: page
     annotations:
       DESCRIPTION: '{{$labels.instance}}: Swap usage usage is above 75% (current value
@@ -17,7 +17,7 @@ groups:
       * 100)) > 75
     for: 2m
     labels:
-      context: unkown
+      context: unknown
       severity: page
     annotations:
       DESCRIPTION: '{{$labels.instance}}: Memory usage is above 75% (current value

diff --git a/monitoring/prometheus/rules.default/cpu-usage.rules b/monitoring/prometheus/rules.default/cpu-usage.rules
@@ -2,7 +2,7 @@ ALERT NodeCPUUsage
   IF (100 - (avg by (instance) (irate(node_cpu{component="node-exporter",mode="idle"}[5m])) * 100)) > 75
   FOR 2m
   LABELS {
-    context="unkown",
+    context="unknown",
     severity="page"
   }
   ANNOTATIONS {

diff --git a/monitoring/prometheus/rules.default/instance-availability.rules b/monitoring/prometheus/rules.default/instance-availability.rules
@@ -2,7 +2,7 @@ ALERT InstanceDown
   IF up == 0
   FOR 1m
   LABELS {
-    context="unkown",
+    context="unknown",
     severity = "page"
   }
   ANNOTATIONS {

diff --git a/monitoring/prometheus/rules.default/low-disk-space.rules b/monitoring/prometheus/rules.default/low-disk-space.rules
@@ -2,7 +2,7 @@ ALERT NodeLowRootDisk
   IF ((node_filesystem_size{mountpoint="/"} - node_filesystem_free{mountpoint="/"} ) / node_filesystem_size{mountpoint="/"} * 100) > 75
   FOR 2m
   LABELS {
-    context="unkown",
+    context="unknown",
     severity="page"
   }
   ANNOTATIONS {
@@ -14,7 +14,7 @@ ALERT NodeLowDataDisk
   IF ((node_filesystem_size{mountpoint="/data-disk"} - node_filesystem_free{mountpoint="/data-disk"} ) / node_filesystem_size{mountpoint="/data-disk"} * 100) > 75
   FOR 2m
   LABELS {
-    context="unkown",
+    context="unknown",
     severity="page"
   }
   ANNOTATIONS {

diff --git a/monitoring/prometheus/rules.default/mem-usage.rules b/monitoring/prometheus/rules.default/mem-usage.rules
@@ -2,7 +2,7 @@ ALERT NodeSwapUsage
   IF (((node_memory_SwapTotal-node_memory_SwapFree)/node_memory_SwapTotal)*100) > 75
   FOR 2m
   LABELS {
-    context="unkown",
+    context="unknown",
     severity="page"
   }
   ANNOTATIONS {
@@ -14,7 +14,7 @@ ALERT NodeMemoryUsage
   IF (((node_memory_MemTotal-node_memory_MemFree-node_memory_Cached)/(node_memory_MemTotal)*100)) > 75
   FOR 2m
   LABELS {
-    context="unkown",
+    context="unknown",
     severity="page"
   }
   ANNOTATIONS {