From 690d5d0b5122a041706cecaf3e7c56651b5cc398 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Thu, 2 Sep 2021 13:55:40 +0300
Subject: [PATCH] consoles: exclude iowait and steal from CPU Utilisation

'iowait' and 'steal' indicate specific idle/wait states, which shouldn't
be counted into CPU Utilisation. Also see
https://github.com/prometheus-operator/kube-prometheus/pull/796 and
https://github.com/kubernetes-monitoring/kubernetes-mixin/pull/667.

Per the iostat man page:

%idle
    Show the percentage of time that the CPU or CPUs were idle and the
    system did not have an outstanding disk I/O request.

%iowait
     Show the percentage of time that the CPU or CPUs were idle during
     which the system had an outstanding disk I/O request.

%steal
     Show the percentage of time spent in involuntary wait by the
     virtual CPU or CPUs while the hypervisor was servicing another
     virtual processor.

Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
---
 consoles/node-cpu.html      | 2 +-
 consoles/node-overview.html | 2 +-
 consoles/node.html          | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/consoles/node-cpu.html b/consoles/node-cpu.html
index d6c515d2d..284ad738f 100644
--- a/consoles/node-cpu.html
+++ b/consoles/node-cpu.html
@@ -47,7 +47,7 @@
   <script>
   new PromConsole.Graph({
     node: document.querySelector("#cpuGraph"),
-    expr: "sum by (mode)(irate(node_cpu_seconds_total{job='node',instance='{{ .Params.instance }}',mode!='idle'}[5m]))",
+    expr: "sum by (mode)(irate(node_cpu_seconds_total{job='node',instance='{{ .Params.instance }}',mode!='idle',mode!='iowait',mode!='steal'}[5m]))",
     renderer: 'area',
     max: {{ with printf "count(count by (cpu)(node_cpu_seconds_total{job='node',instance='%s'}))" .Params.instance | query }}{{ . | first | value }}{{ else}}undefined{{end}},
     yAxisFormatter: PromConsole.NumberFormatter.humanizeNoSmallPrefix,
diff --git a/consoles/node-overview.html b/consoles/node-overview.html
index 92f53ba87..4ae8984b9 100644
--- a/consoles/node-overview.html
+++ b/consoles/node-overview.html
@@ -69,7 +69,7 @@
   <script>
   new PromConsole.Graph({
     node: document.querySelector("#cpuGraph"),
-    expr: "sum by (mode)(irate(node_cpu_seconds_total{job='node',instance='{{ .Params.instance }}',mode!='idle'}[5m]))",
+    expr: "sum by (mode)(irate(node_cpu_seconds_total{job='node',instance='{{ .Params.instance }}',mode!='idle',mode!='iowait',mode!='steal'}[5m]))",
     renderer: 'area',
     max: {{ with printf "count(count by (cpu)(node_cpu_seconds_total{job='node',instance='%s'}))" .Params.instance | query }}{{ . | first | value }}{{ else}}undefined{{end}},
     yAxisFormatter: PromConsole.NumberFormatter.humanizeNoSmallPrefix,
diff --git a/consoles/node.html b/consoles/node.html
index 9a37544ee..c1dfc1a89 100644
--- a/consoles/node.html
+++ b/consoles/node.html
@@ -21,7 +21,7 @@
 <tr>
   <td><a href="node-overview.html?instance={{ .Labels.instance }}">{{ reReplaceAll "(.*?://)([^:/]+?)(:\\d+)?/.*" "$2" .Labels.instance }}</a></td>
   <td{{ if eq (. | value) 1.0 }}>Yes{{ else }} class="alert-danger">No{{ end }}</td>
-  <td>{{ template "prom_query_drilldown" (args (printf "100 * (1 - avg by(instance)(irate(node_cpu_seconds_total{job='node',mode='idle',instance='%s'}[5m])))" .Labels.instance) "%" "printf.1f") }}</td>
+  <td>{{ template "prom_query_drilldown" (args (printf "100 * (1 - avg by(instance) (sum without(mode) (irate(node_cpu_seconds_total{job='node',mode=~'idle|iowait|steal',instance='%s'}[5m]))))" .Labels.instance) "%" "printf.1f") }}</td>
   <td>{{ template "prom_query_drilldown" (args (printf "node_memory_MemFree_bytes{job='node',instance='%s'} + node_memory_Cached_bytes{job='node',instance='%s'} + node_memory_Buffers_bytes{job='node',instance='%s'}" .Labels.instance .Labels.instance .Labels.instance) "B" "humanize1024") }}</td>
 </tr>
 {{ else }}