Fixes issue:8631: Update the steps of test case to get rgw_alerts (#1…

…0407) * Fixes issue:8631: Update the steps of test case to get rgw_alerts Signed-off-by: Akarsha-rai <[email protected]>
red-hat-storage · Sep 9, 2024 · 83f552b · 83f552b
1 parent 9c477c0
commit 83f552b
Show file tree

Hide file tree

Showing 2 changed files with 20 additions and 5 deletions.
diff --git a/tests/functional/monitoring/conftest.py b/tests/functional/monitoring/conftest.py
@@ -905,8 +905,17 @@ def stop_rgw():
         nonlocal rgw_deployments
         for rgw_deployment in rgw_deployments:
             rgw = rgw_deployment["metadata"]["name"]
-            logger.info(f"Downscaling deployment {rgw} to 0")
-            oc.exec_oc_cmd(f"scale --replicas=0 deployment/{rgw}")
+            logger.info(
+                f"Updating readiness probe of deployment {rgw} to make rgw pod down"
+            )
+            cmd = (
+                '[{"op": "replace", "path": "/spec/template/spec/containers/0/readinessProbe", '
+                '"value": {"exec": {"command": ["bash", "-c", "#!/usr/bin/env bash\n\nexit 100"]}}}]'
+            )
+            if not oc.patch(resource_name=rgw, params=cmd, format_type="json"):
+                logger.error(f"Patch command failed to run on deployment {rgw}")
+                raise CommandFailed
+            logger.info(f"Succeeded: {cmd} patched on deployment {rgw}")
         logger.info(f"Waiting for {run_time} seconds")
         time.sleep(run_time)
         return rgw_deployments
@@ -930,8 +939,8 @@ def stop_rgw():
     logger.info("Return RGW pods")
     for rgw_deployment in rgw_deployments:
         rgw = rgw_deployment["metadata"]["name"]
-        logger.info(f"Upscaling deployment {rgw} to 1")
-        oc.exec_oc_cmd(f"scale --replicas=1 deployment/{rgw}")
+        logger.info("To bring the pod running delete the deployment")
+        oc.delete(resource_name=rgw)
 
     return measured_op
 

diff --git a/tests/functional/monitoring/prometheus/alerts/test_rgw.py b/tests/functional/monitoring/prometheus/alerts/test_rgw.py
@@ -18,13 +18,15 @@
 @tier4c
 @pytest.mark.polarion_id("OCS-2323")
 @pytest.mark.bugzilla("1953615")
+@pytest.mark.bugzilla("2218190")
 @skipif_managed_service
 def test_rgw_unavailable(measure_stop_rgw, threading_lock):
     """
     Test that there is appropriate alert when RGW is unavailable and that
     this alert is cleared when the RGW interface is back online.
 
     """
+
     api = prometheus.PrometheusAPI(threading_lock=threading_lock)
 
     # get alerts from time when manager deployment was scaled down
@@ -38,7 +40,11 @@ def test_rgw_unavailable(measure_stop_rgw, threading_lock):
             "Please check Ceph cluster health or RGW connection."
         )
     else:
-        target_msg = "Cluster Object Store is in unhealthy state. Please check Ceph cluster health."
+        target_msg = (
+            "Cluster Object Store is in unhealthy state or number of ready replicas for "
+            "Rook Ceph RGW deployments is less than the desired replicas in "
+            f"namespace:cluster {config.ENV_DATA['cluster_namespace']}:."
+        )
     states = ["pending", "firing"]
 
     prometheus.check_alert_list(