From fe9c01fc683cdf685fda4220b8832be938492b0c Mon Sep 17 00:00:00 2001
From: Max Inden <mail@max-inden.de>
Date: Fri, 17 Jul 2020 09:43:57 +0200
Subject: [PATCH] .maintain/monitoring/alerting-rules: Remove HighCPUUsage
 alert (#6648)

The `HighCPUUsage` alert is based on the `cpu_usage_percentage` metric.
Instead of exposing the overall CPU usage in percent, the metric exposes
the per core usage summed over all cores.

This commit removes the alert for two reasons:

1. Substrate itself does not expose the core count and thus one can not
alert based on the `cpu_usage_percentage` metric.

2. Alerting based on CPU usage is generic and not specific to Substrate
or Blockchains. Thus any CPU usage alert suffice.
---
 .../alerting-rules/alerting-rule-tests.yaml   | 26 -------------------
 .../alerting-rules/alerting-rules.yaml        | 13 ----------
 2 files changed, 39 deletions(-)

diff --git a/substrate/.maintain/monitoring/alerting-rules/alerting-rule-tests.yaml b/substrate/.maintain/monitoring/alerting-rules/alerting-rule-tests.yaml
index 288750be3c..5b0daba3d8 100644
--- a/substrate/.maintain/monitoring/alerting-rules/alerting-rule-tests.yaml
+++ b/substrate/.maintain/monitoring/alerting-rules/alerting-rule-tests.yaml
@@ -42,34 +42,8 @@ tests:
             }'
             values: '1+1x3 4+0x13' # 1 2 3 4 4 4 4 4 4 4 4 4 ...
 
-          - series: 'polkadot_cpu_usage_percentage{
-              job="polkadot",
-              pod="polkadot-abcdef01234-abcdef",
-              instance="polkadot-abcdef01234-abcdef",
-            }'
-            values: '0+20x5 100+0x5' # 0 20 40 60 80 100 100 100 100 100 100
-
       alert_rule_test:
 
-          ######################################################################
-          # Resource usage
-          ######################################################################
-
-          - eval_time: 9m
-            alertname: HighCPUUsage
-            exp_alerts:
-          - eval_time: 10m
-            alertname: HighCPUUsage
-            exp_alerts:
-                - exp_labels:
-                      severity: warning
-                      pod: polkadot-abcdef01234-abcdef
-                      instance: polkadot-abcdef01234-abcdef
-                      job: polkadot
-                  exp_annotations:
-                      message: "The node polkadot-abcdef01234-abcdef has a CPU
-                      usage higher than 100% for more than 5 minutes"
-
           ######################################################################
           # Block production
           ######################################################################
diff --git a/substrate/.maintain/monitoring/alerting-rules/alerting-rules.yaml b/substrate/.maintain/monitoring/alerting-rules/alerting-rules.yaml
index 2ed3889a2c..12f46e17ad 100644
--- a/substrate/.maintain/monitoring/alerting-rules/alerting-rules.yaml
+++ b/substrate/.maintain/monitoring/alerting-rules/alerting-rules.yaml
@@ -2,19 +2,6 @@ groups:
 - name: polkadot.rules
   rules:
 
-  ##############################################################################
-  # Resource usage
-  ##############################################################################
-
-  - alert: HighCPUUsage
-    expr: polkadot_cpu_usage_percentage >= 100
-    for: 5m
-    labels:
-      severity: warning
-    annotations:
-      message: 'The node {{ $labels.instance }} has a CPU usage higher than 100%
-      for more than 5 minutes'
-
   ##############################################################################
   # Block production
   ##############################################################################