From f995680e2a64d54adcf3c1d6f3ba7d9c27d01e28 Mon Sep 17 00:00:00 2001
From: kranthi guttikonda <kranthi.guttikonda9@gmail.com>
Date: Wed, 10 Oct 2018 11:02:45 -0400
Subject: [PATCH] Prometheus kubelet.rules change

kube_node_status_ready and up metrics are obsolete to check the kubernetes
node condition. When a kubelet is down that means node itself in NotReady
state. With 1.3.1 kube-state-metrics exporter kube_node_status_condition
metric provides the status value of the kubelet (essentially node).
https://github.com/kubernetes/kube-state-metrics/blob/master/Documentation
/node-metrics.md

kube_node_status_condition includes condition=Ready and status as true,
flase and unknown. When a kubelet is stopped the status will be unknown
since the kubelet itself will unable to talk to API. In other cases it
will be false. When the node is registered and available it will be set to
true.

Replaced the kube_node_status_ready with kube_node_status_condition and
changed the 1h to 1m and increased the severity to "critical". Also
modified the K8SKubeletDown definitions with 1m and critical sevrity

Implements: Bug 1797133
Closes-Bug: #1797133
Change-Id: I025adb13c9d8642a218dfda1ff30f1577fa8c826
Signed-off-by: Kranthi Kiran Guttikonda <kranthi.guttikonda@b-yond.com>
---
 prometheus/values.yaml | 28 ++++++++++++++++++----------
 1 file changed, 18 insertions(+), 10 deletions(-)

diff --git a/prometheus/values.yaml b/prometheus/values.yaml
index 09b2fa0ff..d590cffb0 100644
--- a/prometheus/values.yaml
+++ b/prometheus/values.yaml
@@ -1177,15 +1177,23 @@ conf:
         - name: kubelet.rules
           rules:
           - alert: K8SNodeNotReady
-            expr: kube_node_status_ready{condition="true"} == 0
-            for: 1h
+            expr: kube_node_status_condition{condition="Ready", status="unknown"} == 1 or kube_node_status_condition{condition="Ready", status="false"} == 1
+            for: 1m
             labels:
-              severity: warning
+              severity: critical
             annotations:
-              description: The Kubelet on {{ $labels.node }} has not checked in with the API, or has set itself to NotReady, for more than an hour
-              summary: Node status is NotReady
+              description: The Kubelet on {{ $labels.node }} has not checked in with the API, or has set itself to NotReady, for more than a minute
+              summary: '{{ $labels.node }} Node status is NotReady and {{ $labels.status }}'
           - alert: K8SManyNodesNotReady
-            expr: count(kube_node_status_ready{condition="true"} == 0) > 1 and (count(kube_node_status_ready{condition="true"} == 0) / count(kube_node_status_ready{condition="true"})) > 0.2
+            expr: count(kube_node_status_condition{condition="Ready", status="unknown"} == 1) > 1 and (count(kube_node_status_condition{condition="Ready", status="unknown"} == 1) / count(kube_node_status_condition{condition="Ready", status="unknown"})) > 0.2
+            for: 1m
+            labels:
+              severity: critical
+            annotations:
+              description: '{{ $value }} Kubernetes nodes (more than 10% are in the NotReady state).'
+              summary: Many Kubernetes nodes are Not Ready
+          - alert: K8SManyNodesNotReady
+            expr: count(kube_node_status_condition{condition="Ready", status="false"} == 1) > 1 and (count(kube_node_status_condition{condition="Ready", status="false"} == 1) / count(kube_node_status_condition{condition="Ready", status="false"})) > 0.2
             for: 1m
             labels:
               severity: critical
@@ -1193,7 +1201,7 @@ conf:
               description: '{{ $value }} Kubernetes nodes (more than 10% are in the NotReady state).'
               summary: Many Kubernetes nodes are Not Ready
           - alert: K8SNodesNotReady
-            expr: count(kube_node_status_ready{condition="true"} == 0) > 0
+            expr: count(kube_node_status_condition{condition="Ready", status="false"} == 1) > 0 or count(kube_node_status_condition{condition="Ready", status="unknown"} == 1) > 0
             for: 1m
             labels:
               severity: critical
@@ -1202,15 +1210,15 @@ conf:
               summary: One or more Kubernetes nodes are Not Ready
           - alert: K8SKubeletDown
             expr: count(up{job="kubelet"} == 0) / count(up{job="kubelet"}) > 0.03
-            for: 1h
+            for: 1m
             labels:
-              severity: warning
+              severity: critical
             annotations:
               description: Prometheus failed to scrape {{ $value }}% of kubelets.
               summary: Many Kubelets cannot be scraped
           - alert: K8SKubeletDown
             expr: absent(up{job="kubelet"} == 1) or count(up{job="kubelet"} == 0) / count(up{job="kubelet"}) > 0.1
-            for: 1h
+            for: 1m
             labels:
               severity: critical
             annotations: