From 1b5a0e928961013a380eebf5a4475c34d7252abc Mon Sep 17 00:00:00 2001
From: Yury Kovalev <ykovalev@redhat.com>
Date: Mon, 16 Mar 2026 10:53:35 +0100
Subject: [PATCH] ROX-33584: Reduce the severity of the fleetshard-sync
 unavailability alerts

---
 resources/prometheus/prometheus-rules.yaml                  | 6 +++---
 .../unit_tests/RHACSFleetshardSyncContainerDown.yaml        | 2 +-
 .../RHACSFleetshardSyncContainerFrequentlyRestarting.yaml   | 2 +-
 .../unit_tests/RHACSFleetshardSyncScrapeFailed.yaml         | 2 +-
 4 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/resources/prometheus/prometheus-rules.yaml b/resources/prometheus/prometheus-rules.yaml
index 19bdcafb..a4c94ee0 100644
--- a/resources/prometheus/prometheus-rules.yaml
+++ b/resources/prometheus/prometheus-rules.yaml
@@ -106,7 +106,7 @@ spec:
             (avg_over_time(up{pod=~"fleetshard-sync-.*"}[10m]) < 0.5 and ON(pod) kube_pod_container_status_ready{pod=~"fleetshard-sync-.*"} == 1) or absent(up{pod=~"fleetshard-sync-.*"})
           for: 20m
           labels:
-            severity: critical
+            severity: warning
           annotations:
             summary: "Prometheus unable to scrape metrics from target `{{ $labels.pod }}` in namespace `{{ $labels.namespace }}`."
             description: "During the last 10 minutes, only `{{ $value | humanizePercentage }}` of scrapes of target `{{ $labels.pod }}` in namespace `{{ $labels.namespace }}` were successful. This alert is raised when less than 50% of scrapes are successful."
@@ -116,7 +116,7 @@ spec:
             avg_over_time(kube_pod_container_status_ready{pod=~"fleetshard-sync-.*"}[10m]) < 0.5
           for: 20m
           labels:
-            severity: critical
+            severity: warning
           annotations:
             summary: "Fleetshard synchronizer container `{{ $labels.pod }}/{{ $labels.container }}` in namespace `{{ $labels.namespace }}` is down or in a CrashLoopBackOff status."
             description: "Fleetshard synchronizer container `{{ $labels.pod }}/{{ $labels.container }}` in namespace `{{ $labels.namespace }}` has been down or in a CrashLoopBackOff status for at least 10 minutes."
@@ -124,7 +124,7 @@ spec:
         - alert: RHACSFleetshardSyncContainerFrequentlyRestarting
           expr: increase(kube_pod_container_status_restarts_total{pod=~"fleetshard-sync-.*"}[30m]) > 3
           labels:
-            severity: critical
+            severity: warning
           annotations:
             summary: "Fleetshard synchronizer container `{{ $labels.pod }}/{{ $labels.container }}` in namespace `{{ $labels.namespace }}` restarted more than 3 times."
             description: "Fleetshard synchronizer container `{{ $labels.pod }}/{{ $labels.container }}` in namespace `{{ $labels.namespace }}` has restarted more than 3 times during the last 30 minutes."
diff --git a/resources/prometheus/unit_tests/RHACSFleetshardSyncContainerDown.yaml b/resources/prometheus/unit_tests/RHACSFleetshardSyncContainerDown.yaml
index 571d641f..31f64239 100644
--- a/resources/prometheus/unit_tests/RHACSFleetshardSyncContainerDown.yaml
+++ b/resources/prometheus/unit_tests/RHACSFleetshardSyncContainerDown.yaml
@@ -20,7 +20,7 @@ tests:
               container: fleetshard-sync
               namespace: rhacs
               pod: fleetshard-sync-1234
-              severity: critical
+              severity: warning
             exp_annotations:
               summary: "Fleetshard synchronizer container `fleetshard-sync-1234/fleetshard-sync` in namespace `rhacs` is down or in a CrashLoopBackOff status."
               description: "Fleetshard synchronizer container `fleetshard-sync-1234/fleetshard-sync` in namespace `rhacs` has been down or in a CrashLoopBackOff status for at least 10 minutes."
diff --git a/resources/prometheus/unit_tests/RHACSFleetshardSyncContainerFrequentlyRestarting.yaml b/resources/prometheus/unit_tests/RHACSFleetshardSyncContainerFrequentlyRestarting.yaml
index f9a64490..f1cd10d1 100644
--- a/resources/prometheus/unit_tests/RHACSFleetshardSyncContainerFrequentlyRestarting.yaml
+++ b/resources/prometheus/unit_tests/RHACSFleetshardSyncContainerFrequentlyRestarting.yaml
@@ -20,7 +20,7 @@ tests:
               container: fleetshard-sync
               namespace: rhacs
               pod: fleetshard-sync-1234
-              severity: critical
+              severity: warning
             exp_annotations:
               summary: "Fleetshard synchronizer container `fleetshard-sync-1234/fleetshard-sync` in namespace `rhacs` restarted more than 3 times."
               description: "Fleetshard synchronizer container `fleetshard-sync-1234/fleetshard-sync` in namespace `rhacs` has restarted more than 3 times during the last 30 minutes."
diff --git a/resources/prometheus/unit_tests/RHACSFleetshardSyncScrapeFailed.yaml b/resources/prometheus/unit_tests/RHACSFleetshardSyncScrapeFailed.yaml
index 0d45493c..362bd4c9 100644
--- a/resources/prometheus/unit_tests/RHACSFleetshardSyncScrapeFailed.yaml
+++ b/resources/prometheus/unit_tests/RHACSFleetshardSyncScrapeFailed.yaml
@@ -22,7 +22,7 @@ tests:
               instance: 1.2.3.4:9090
               namespace: rhacs
               pod: fleetshard-sync-1234
-              severity: critical
+              severity: warning
             exp_annotations:
               summary: "Prometheus unable to scrape metrics from target `fleetshard-sync-1234` in namespace `rhacs`."
               description: "During the last 10 minutes, only `40%` of scrapes of target `fleetshard-sync-1234` in namespace `rhacs` were successful. This alert is raised when less than 50% of scrapes are successful."