From 4dd657bc2baac4466a2dcb4f186e3f8e3cf698ea Mon Sep 17 00:00:00 2001
From: aaa5kameric <aaakameric5@gmail.com>
Date: Wed, 28 Aug 2024 12:07:55 +0200
Subject: [PATCH] minor changes for consistency

---
 resources/prometheus/prometheus-rules.yaml    | 20 ++++++++
 .../unit_tests/CentralInstanceLimit.yaml      | 48 +++++++++++++++++++
 2 files changed, 68 insertions(+)
 create mode 100644 resources/prometheus/unit_tests/CentralInstanceLimit.yaml

diff --git a/resources/prometheus/prometheus-rules.yaml b/resources/prometheus/prometheus-rules.yaml
index 6521231..6b393c1 100644
--- a/resources/prometheus/prometheus-rules.yaml
+++ b/resources/prometheus/prometheus-rules.yaml
@@ -136,6 +136,16 @@ spec:
           annotations:
             summary: "Certificate expiring very soon: `{{ $labels.exported_namespace }}/{{ $labels.secret }}/{{ $labels.data_key }}`."
             description: "Certificate `{{ $labels.exported_namespace }}/{{ $labels.secret }}/{{ $labels.data_key }}` expires on {{ humanizeTimestamp $value}}."
+        - alert: CentralInstanceLimitCriticalCapacity
+          expr: |
+            acs_fleet_manager_cluster_status_capacity_max-acs_fleet_manager_cluster_status_capacity_used<=2
+          for: 5m
+          labels:
+            severity: critical
+          annotations:
+            summary: "Cluster ID: '{{ $labels.clusterID }}' is at a critical instance limit."
+            description: "Cluster '{{ $labels.clusterID }}' has '{{ $value }}' instances left before reaching limit"
+            sop_url: "https://gitlab.cee.redhat.com/stackrox/acs-cloud-service/runbooks/-/blob/master/sops/dp-031-central-instance-limit-reached.md"
         - alert: RHACSFleetshardCertificateExpiryWarning
           expr: |
             acs_fleetshard_certificate_expiration_timestamp <= 7* 24 * 60 * 60 + time()
@@ -144,6 +154,16 @@ spec:
           annotations:
             summary: "Certificate expiring soon: `{{ $labels.exported_namespace }}/{{ $labels.secret }}/{{ $labels.data_key }}`."
             description: "Certificate `{{ $labels.exported_namespace }}/{{ $labels.secret }}/{{ $labels.data_key }}` expires on {{ humanizeTimestamp $value}}."
+        - alert: CentralInstanceLimitWarningCapacity
+          expr: |
+            acs_fleet_manager_cluster_status_capacity_max-acs_fleet_manager_cluster_status_capacity_used<=10
+          for: 5m
+          labels:
+            severity: warning
+          annotations:
+            summary: "Cluster ID: '{{ $labels.clusterID }}' is reaching its instance limit."
+            description: "Cluster '{{ $labels.clusterID }}' has '{{ $value }}' instances left before reaching limit"
+            sop_url: "https://gitlab.cee.redhat.com/stackrox/acs-cloud-service/runbooks/-/blob/master/sops/dp-031-central-instance-limit-reached.md"
         - alert: RHACSFleetshardSyncReconciliationErrors
           expr: |
             acs_fleetshard_central_errors_per_reconciliations:ratio_rate10m > 0.10
diff --git a/resources/prometheus/unit_tests/CentralInstanceLimit.yaml b/resources/prometheus/unit_tests/CentralInstanceLimit.yaml
new file mode 100644
index 0000000..4379ac9
--- /dev/null
+++ b/resources/prometheus/unit_tests/CentralInstanceLimit.yaml
@@ -0,0 +1,48 @@
+rule_files:
+  - /tmp/prometheus-rules-test.yaml
+
+
+evaluation_interval: 1m
+
+
+tests:
+  - interval: 15s
+    input_series:
+      - series: acs_fleet_manager_cluster_status_capacity_max{clusterID="cluster1"}
+        values: 10 #critical
+      - series: acs_fleet_manager_cluster_status_capacity_used{clusterID="cluster1"}
+        values: 8 #critical
+      - series: acs_fleet_manager_cluster_status_capacity_max{clusterID="cluster-2"}
+        values: 15 #warning
+      - series: acs_fleet_manager_cluster_status_capacity_used{clusterID="cluster-2"}
+        values: 5 #warning
+    alert_rule_test:
+      - eval_time: 5m
+        alertname:  CentralInstanceLimitCriticalCapacity
+        exp_alerts:
+          - exp_labels:
+              alertname:  CentralInstanceLimitCriticalCapacity
+              clusterID: cluster1
+              severity: critical
+            exp_annotations:
+              summary: "Cluster ID: 'cluster1' is at a critical instance limit."
+              description: "Cluster 'cluster1' has '2' instances left before reaching limit"
+              sop_url: "https://gitlab.cee.redhat.com/stackrox/acs-cloud-service/runbooks/-/blob/master/sops/dp-031-central-instance-limit-reached.md"
+  - interval: 15s
+    input_series:
+      - series: acs_fleet_manager_cluster_status_capacity_max{clusterID="cluster-2"}
+        values: 15 #warning
+      - series: acs_fleet_manager_cluster_status_capacity_used{clusterID="cluster-2"}
+        values: 5 #warning
+    alert_rule_test:
+      - eval_time: 5m
+        alertname: CentralInstanceLimitWarningCapacity
+        exp_alerts:
+          - exp_labels:
+              alertname: CentralInstanceLimitWarningCapacity
+              clusterID: cluster-2
+              severity: warning
+            exp_annotations:
+              summary: "Cluster ID: 'cluster-2' is reaching its instance limit."
+              description: "Cluster 'cluster-2' has '10' instances left before reaching limit"
+              sop_url: "https://gitlab.cee.redhat.com/stackrox/acs-cloud-service/runbooks/-/blob/master/sops/dp-031-central-instance-limit-reached.md"