From 55b049eb2817541f0b6b989b3a31c1b6b5149332 Mon Sep 17 00:00:00 2001
From: Yonah Dissen <47282577+yonahd@users.noreply.github.com>
Date: Sun, 2 Oct 2022 19:05:30 +0300
Subject: [PATCH] add argocd rules (#309)

* add argocd rules

* fix(argocd): move contrib into _data/rules.yml instead of dist/...

Co-authored-by: Samuel Berthe <dev@samuel-berthe.fr>
---
 README.md       |  1 +
 _data/rules.yml | 20 +++++++++++++++++++-
 2 files changed, 20 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 2b567c4..c914de9 100644
--- a/README.md
+++ b/README.md
@@ -59,6 +59,7 @@ Collection available here: **[https://awesome-prometheus-alerts.grep.to](https:/
 - [Etcd](https://awesome-prometheus-alerts.grep.to/rules#etcd)
 - [Linkerd](https://awesome-prometheus-alerts.grep.to/rules#linkerd)
 - [Istio](https://awesome-prometheus-alerts.grep.to/rules#istio)
+- [ArgoCD](https://awesome-prometheus-alerts.grep.to/rules#argocd)
 
 #### Network, security and storage
 
diff --git a/_data/rules.yml b/_data/rules.yml
index c72ef75..286a567 100644
--- a/_data/rules.yml
+++ b/_data/rules.yml
@@ -27,7 +27,7 @@ groups:
               query: 'sum by (job) (up) == 0'
               severity: critical
             - name: Prometheus target missing with warmup time
-              description: Allow a job time to start up (10 minutes) before alerting that it's down. 
+              description: Allow a job time to start up (10 minutes) before alerting that it's down.
               query: 'sum by (instance, job) ((up == 0) * on (instance) group_right(job) (node_time_seconds - node_boot_time_seconds > 600))'
               severity: critical
             - name: Prometheus configuration reload failure
@@ -1952,6 +1952,24 @@ groups:
                 query: 'sum(rate(pilot_duplicate_envoy_clusters{}[5m])) > 0'
                 severity: critical
 
+      - name: ArgoCD
+        exporters:
+          - name: Embedded exporter
+            slug: embedded-exporter
+            doc_url: https://argo-cd.readthedocs.io/en/stable/operator-manual/metrics/
+            rules:
+              - name: ArgoCD service not synced
+                description: Service {{ $labels.name }} run by argo is currently not in sync.
+                query: 'argocd_app_info{sync_status!="Synced"} != 0'
+                severity: warning
+                for: 15m
+              - name: ArgoCD service unhealthy
+                description: Service {{ $labels.name }} run by argo is currently not healthy.
+                query: 'argocd_app_info{health_status!="Healthy"} != 0'
+                severity: warning
+                for: 15m
+
+
   - name: Network, security and storage
     services:
       - name: Ceph