From 2790c840a820b7dce799da81e52c4f6c01baaad4 Mon Sep 17 00:00:00 2001
From: Leon <82407168+sed-i@users.noreply.github.com>
Date: Tue, 29 Oct 2024 19:18:59 -0400
Subject: [PATCH 1/3] Update host_health.rules

Signed-off-by: Leon <82407168+sed-i@users.noreply.github.com>
---
 src/prometheus_alert_rules/host_health.rules | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/prometheus_alert_rules/host_health.rules b/src/prometheus_alert_rules/host_health.rules
index 803e2e5..f4a3814 100644
--- a/src/prometheus_alert_rules/host_health.rules
+++ b/src/prometheus_alert_rules/host_health.rules
@@ -7,7 +7,7 @@ groups:
     labels:
       severity: critical
     annotations:
-      summary: Host '{{labels.instance}}' is down.
+      summary: Host '{{ $labels.instance }}' is down.
       description: >-
         Host '{{ $labels.instance }}' is down.
           VALUE = {{ $value }}
@@ -18,7 +18,7 @@ groups:
     labels:
       severity: critical
     annotations:
-      summary: Metrics not received from host '{{labels.instance}}'.
+      summary: Metrics not received from host '{{ $labels.instance }}'.
       description: >-
         The metrics endpoint for host '{{ $labels.instance }}' is unreachable.
           VALUE = {{ $value }}

From b642c34a2b956efa49a6af13d470a89058509708 Mon Sep 17 00:00:00 2001
From: sed-i <82407168+sed-i@users.noreply.github.com>
Date: Tue, 29 Oct 2024 19:26:29 -0400
Subject: [PATCH 2/3] Move individual alerts under group

---
 .../high_cpu_iowait.rule                      | 19 +++++++++++--------
 src/prometheus_alert_rules/oomkill.rule       | 19 +++++++++++--------
 2 files changed, 22 insertions(+), 16 deletions(-)

diff --git a/src/prometheus_alert_rules/high_cpu_iowait.rule b/src/prometheus_alert_rules/high_cpu_iowait.rule
index eed0cd7..5b2dceb 100644
--- a/src/prometheus_alert_rules/high_cpu_iowait.rule
+++ b/src/prometheus_alert_rules/high_cpu_iowait.rule
@@ -1,8 +1,11 @@
-alert: HostCpuHighIowait
-expr: avg by (instance) (rate(node_cpu_seconds_total{mode="iowait"}[5m])) * 100 > 10
-for: 0m
-labels:
-  severity: warning
-annotations:
-  summary: Host CPU high iowait (instance {{ $labels.instance }})
-  description: "CPU iowait > 10%. A high iowait means that you are disk or network bound.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+groups:
+- name: HostCpu
+  rules:
+  - alert: HostCpuHighIowait
+    expr: avg by (instance) (rate(node_cpu_seconds_total{mode="iowait"}[5m])) * 100 > 10
+    for: 0m
+    labels:
+      severity: warning
+    annotations:
+      summary: Host CPU high iowait (instance {{ $labels.instance }})
+      description: "CPU iowait > 10%. A high iowait means that you are disk or network bound.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
diff --git a/src/prometheus_alert_rules/oomkill.rule b/src/prometheus_alert_rules/oomkill.rule
index e7fce3b..21c1200 100644
--- a/src/prometheus_alert_rules/oomkill.rule
+++ b/src/prometheus_alert_rules/oomkill.rule
@@ -1,8 +1,11 @@
-alert: HostOomKillDetected
-expr: increase(node_vmstat_oom_kill[1h]) > 0
-for: 0m
-labels:
-  severity: warning
-annotations:
-  summary: Host OOM kill detected (instance {{ $labels.instance }})
-  description: "OOM kill detected\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+groups:
+- name: HostMemory
+  rules:
+  - alert: HostOomKillDetected
+    expr: increase(node_vmstat_oom_kill[1h]) > 0
+    for: 0m
+    labels:
+      severity: warning
+    annotations:
+      summary: Host OOM kill detected (instance {{ $labels.instance }})
+      description: "OOM kill detected\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

From ca33d8e9b326d18164f6536338453a260752b2ca Mon Sep 17 00:00:00 2001
From: sed-i <82407168+sed-i@users.noreply.github.com>
Date: Tue, 29 Oct 2024 19:27:10 -0400
Subject: [PATCH 3/3] Rename ext to match contents

---
 .../{high_cpu_iowait.rule => high_cpu_iowait.rules}               | 0
 src/prometheus_alert_rules/{oomkill.rule => oomkill.rules}        | 0
 2 files changed, 0 insertions(+), 0 deletions(-)
 rename src/prometheus_alert_rules/{high_cpu_iowait.rule => high_cpu_iowait.rules} (100%)
 rename src/prometheus_alert_rules/{oomkill.rule => oomkill.rules} (100%)

diff --git a/src/prometheus_alert_rules/high_cpu_iowait.rule b/src/prometheus_alert_rules/high_cpu_iowait.rules
similarity index 100%
rename from src/prometheus_alert_rules/high_cpu_iowait.rule
rename to src/prometheus_alert_rules/high_cpu_iowait.rules
diff --git a/src/prometheus_alert_rules/oomkill.rule b/src/prometheus_alert_rules/oomkill.rules
similarity index 100%
rename from src/prometheus_alert_rules/oomkill.rule
rename to src/prometheus_alert_rules/oomkill.rules