Merge pull request #284 from stackrox/increase-tenant-workload-memory…

…-alert-threshold Increase tenant workload memory alert threshold to 90%
stackrox · Oct 29, 2024 · b3ee599 · b3ee599
2 parents e0167fe + afe0e28
commit b3ee599
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 4 deletions.
diff --git a/resources/prometheus/prometheus-rules.yaml b/resources/prometheus/prometheus-rules.yaml
@@ -241,7 +241,7 @@ spec:
           record: rhacs_tenants:namespace:pod:container:max_memory_usage_ratio
         - alert: RHACSTenantWorkloadMemoryUtilizationHigh
           expr: |
-            rhacs_tenants:namespace:pod:container:max_memory_usage_ratio{container="central"} >= 0.85
+            rhacs_tenants:namespace:pod:container:max_memory_usage_ratio{container="central"} >= 0.9
           for: 30m
           labels:
             severity: warning

diff --git a/resources/prometheus/unit_tests/RHACSTenantWorkloadMemoryUtilizationHigh.yaml b/resources/prometheus/unit_tests/RHACSTenantWorkloadMemoryUtilizationHigh.yaml
@@ -7,8 +7,8 @@ tests:
   - interval: 1m
     input_series:
       - series: container_memory_working_set_bytes{namespace="rhacs-aaaaaaaaaaaaaaaaaaaa", pod="mypod", container="central"}
-        # first 10 minutes no alert and then 85% CPU usage for 40 minutes
-        values: "50+0x10 85+0x40"
+        # first 10 minutes no alert and then 90% CPU usage for 40 minutes
+        values: "50+0x10 90+0x40"
       - series: container_spec_memory_limit_bytes{namespace="rhacs-aaaaaaaaaaaaaaaaaaaa",pod="mypod", container="central"}
         values: "100+0x40"
     alert_rule_test:
@@ -26,7 +26,7 @@ tests:
               container: central
             exp_annotations:
               summary: tenant 'rhacs-aaaaaaaaaaaaaaaaaaaa' container 'central' in pod 'mypod' is reaching its memory limit.
-              description: tenant 'rhacs-aaaaaaaaaaaaaaaaaaaa' container 'central' in pod 'mypod' reached 85% of its memory limit and is at risk of being OOM killed.
+              description: tenant 'rhacs-aaaaaaaaaaaaaaaaaaaa' container 'central' in pod 'mypod' reached 90% of its memory limit and is at risk of being OOM killed.
               sop_url: "https://gitlab.cee.redhat.com/stackrox/acs-cloud-service/runbooks/-/blob/master/sops/dp-039-tenant-workload-memory-utilization-high.md"
   - interval: 1m
     input_series: