feat(HPA): Adds autoscaling config

dhruv-shah-sumo · dhruv-shah-sumo · commit b2f64ad49834 · 2025-11-19T19:51:36.000+05:30
OSC-1200

Signed-off-by: Dhruv Shah &lt;dhruv.shah@sumologic.com&gt;
diff --git a/.changelog/4026.added.txt b/.changelog/4026.added.txt
@@ -0,0 +1 @@
+feat(HPA): Adds autoscaling config
diff --git a/deploy/helm/sumologic/README.md b/deploy/helm/sumologic/README.md
diff --git a/deploy/helm/sumologic/templates/instrumentation/otelcol-instrumentation/hpa.yaml b/deploy/helm/sumologic/templates/instrumentation/otelcol-instrumentation/hpa.yaml
@@ -16,6 +16,10 @@ spec:
     name: {{ template "sumologic.metadata.name.otelcolinstrumentation.statefulset" . }}
   minReplicas: {{ $otelcolInstrumentation.autoscaling.minReplicas }}
   maxReplicas: {{ $otelcolInstrumentation.autoscaling.maxReplicas }}
+{{- if $otelcolInstrumentation.autoscaling.behavior }}
+  behavior:
+    {{- toYaml $otelcolInstrumentation.autoscaling.behavior | nindent 4 }}
+{{- end }}
   metrics:
 {{- if $otelcolInstrumentation.autoscaling.targetMemoryUtilizationPercentage }}
   - type: Resource
diff --git a/deploy/helm/sumologic/templates/instrumentation/traces-gateway/hpa.yaml b/deploy/helm/sumologic/templates/instrumentation/traces-gateway/hpa.yaml
@@ -16,6 +16,10 @@ spec:
     name: {{ template "sumologic.metadata.name.tracesgateway.deployment" . }}
   minReplicas: {{ $tracesGateway.autoscaling.minReplicas }}
   maxReplicas: {{ $tracesGateway.autoscaling.maxReplicas }}
+{{- if $tracesGateway.autoscaling.behavior }}
+  behavior:
+    {{- toYaml $tracesGateway.autoscaling.behavior | nindent 4 }}
+{{- end }}
   metrics:
 {{- if $tracesGateway.autoscaling.targetMemoryUtilizationPercentage }}
   - type: Resource
diff --git a/deploy/helm/sumologic/templates/logs/common/hpa.yaml b/deploy/helm/sumologic/templates/logs/common/hpa.yaml
@@ -14,6 +14,10 @@ spec:
     name: {{ template "sumologic.metadata.name.logs.statefulset" . }}
   minReplicas: {{ .Values.metadata.logs.autoscaling.minReplicas }}
   maxReplicas: {{ .Values.metadata.logs.autoscaling.maxReplicas }}
+{{- if .Values.metadata.logs.autoscaling.behavior }}
+  behavior:
+    {{- toYaml .Values.metadata.logs.autoscaling.behavior | nindent 4 }}
+{{- end }}
   metrics:
 {{- if .Values.metadata.logs.autoscaling.targetMemoryUtilizationPercentage }}
   - type: Resource
diff --git a/deploy/helm/sumologic/templates/metrics/collector/otelcol/opentelemetrycollector.yaml b/deploy/helm/sumologic/templates/metrics/collector/otelcol/opentelemetrycollector.yaml
@@ -95,6 +95,10 @@ spec:
 {{- if .Values.sumologic.metrics.collector.otelcol.autoscaling.targetMemoryUtilizationPercentage }}
     targetMemoryUtilization: {{ .Values.sumologic.metrics.collector.otelcol.autoscaling.targetMemoryUtilizationPercentage }}
 {{- end }}
+{{- if .Values.sumologic.metrics.collector.otelcol.autoscaling.behavior }}
+    behavior:
+{{ toYaml .Values.sumologic.metrics.collector.otelcol.autoscaling.behavior | indent 6 }}
+{{- end }}
 {{- end }}
   env:
   - name: METADATA_METRICS_SVC
diff --git a/deploy/helm/sumologic/templates/metrics/common/hpa.yaml b/deploy/helm/sumologic/templates/metrics/common/hpa.yaml
@@ -14,6 +14,10 @@ spec:
     name: {{ template "sumologic.metadata.name.metrics.statefulset" . }}
   minReplicas: {{ .Values.metadata.metrics.autoscaling.minReplicas }}
   maxReplicas: {{ .Values.metadata.metrics.autoscaling.maxReplicas }}
+{{- if .Values.metadata.metrics.autoscaling.behavior }}
+  behavior:
+    {{- toYaml .Values.metadata.metrics.autoscaling.behavior | nindent 4 }}
+{{- end }}
   metrics:
 {{- if .Values.metadata.metrics.autoscaling.targetMemoryUtilizationPercentage }}
   - type: Resource
diff --git a/deploy/helm/sumologic/values.yaml b/deploy/helm/sumologic/values.yaml
@@ -518,6 +518,7 @@ sumologic:
           maxReplicas: 10
           targetCPUUtilizationPercentage: 70
           targetMemoryUtilizationPercentage: 70
+          behavior: {}
 
         nodeSelector: {}
 
@@ -1388,6 +1389,7 @@ otelcolInstrumentation:
     maxReplicas: 10
     targetCPUUtilizationPercentage: 100
     # targetMemoryUtilizationPercentage: 50
+    behavior: {}
 
   statefulset:
     nodeSelector: {}
@@ -1706,6 +1708,7 @@ metadata:
       maxReplicas: 10
       targetCPUUtilizationPercentage: 80
       # targetMemoryUtilizationPercentage: 50
+      behavior: {}
 
     ## Option to specify PodDisrutionBudgets
     ## You can specify only one of maxUnavailable and minAvailable in a single PodDisruptionBudget
@@ -1824,6 +1827,7 @@ metadata:
       maxReplicas: 10
       targetCPUUtilizationPercentage: 80
       # targetMemoryUtilizationPercentage: 50
+      behavior: {}
 
     ## Option to specify PodDisrutionBudgets
     ## You can specify only one of maxUnavailable and minAvailable in a single PodDisruptionBudget
@@ -1845,6 +1849,7 @@ tracesGateway:
     maxReplicas: 10
     targetCPUUtilizationPercentage: 100
     # targetMemoryUtilizationPercentage: 50
+    behavior: {}
 
   deployment:
     replicas: 1
diff --git a/tests/helm/testdata/goldenfile/metrics_collector_otc/debug.input.yaml b/tests/helm/testdata/goldenfile/metrics_collector_otc/debug.input.yaml
@@ -3,3 +3,24 @@ debug:
     collector:
       print: true
       stopLogsIngestion: true
+
+sumologic:
+  metrics:
+    collector:
+      otelcol:
+        enabled: true
+        autoscaling:
+          enabled: true
+          behavior:
+            scaleUp:
+              stabilizationWindowSeconds: 60
+              policies:
+                - type: Percent
+                  value: 100
+                  periodSeconds: 60
+            scaleDown:
+              stabilizationWindowSeconds: 60
+              policies:
+                - type: Percent
+                  value: 100
+                  periodSeconds: 60
diff --git a/tests/helm/testdata/goldenfile/metrics_collector_otc/debug.output.yaml b/tests/helm/testdata/goldenfile/metrics_collector_otc/debug.output.yaml
@@ -42,6 +42,20 @@ spec:
     minReplicas: 1
     targetCPUUtilization: 70
     targetMemoryUtilization: 70
+    behavior:
+      scaleUp:
+        stabilizationWindowSeconds: 60
+        policies:
+          - type: Percent
+            value: 100
+            periodSeconds: 60
+      scaleDown:
+        stabilizationWindowSeconds: 60
+        policies:
+          - type: Percent
+            value: 100
+            periodSeconds: 60
+
   env:
     - name: METADATA_METRICS_SVC
       valueFrom:
diff --git a/tests/integration/features.go b/tests/integration/features.go
@@ -683,6 +683,31 @@ func GetMultipleMultilineLogsFeature() features.Feature {
 		Feature()
 }
 
+func GetHPAFeature(releaseName string) features.Feature {
+	expectedHPA := []string{
+		fmt.Sprintf("%s-sumologic-metrics-collector", releaseName),
+		fmt.Sprintf("%s-sumologic-otelcol-instrumentation", releaseName),
+		fmt.Sprintf("%s-sumologic-otelcol-logs", releaseName),
+		fmt.Sprintf("%s-sumologic-otelcol-metrics", releaseName),
+		fmt.Sprintf("%s-sumologic-traces-gateway", releaseName),
+	}
+	expectedMetrics := map[string]map[string]int{}
+	for _, hpa := range expectedHPA {
+		expectedMetrics[hpa] = map[string]int{
+			"cpu":    75,
+			"memory": 75,
+		}
+	}
+	return features.New("HPA").
+		Assess("HPA configured", stepfuncs.WaitUntilHPAConfigured(
+			expectedHPA,
+			expectedMetrics,
+			waitDuration,
+			tickDuration,
+		)).
+		Feature()
+}
+
 func GetEventsFeature() features.Feature {
 	return features.New("events").
 		Assess("events present", stepfuncs.WaitUntilExpectedLogsPresent(
diff --git a/tests/integration/helm_ot_hpa_test.go b/tests/integration/helm_ot_hpa_test.go
@@ -0,0 +1,29 @@
+//go:build allversions
+// +build allversions
+
+package integration
+
+import (
+	"testing"
+
+	strings_internal "github.com/SumoLogic/sumologic-kubernetes-collection/tests/integration/internal/strings"
+)
+
+func Test_Helm_OT_HPA(t *testing.T) {
+	installChecks := []featureCheck{
+		CheckSumologicSecret(15),
+		CheckOtelcolMetadataLogsInstall,
+		CheckOtelcolMetadataMetricsInstall,
+		CheckOtelcolEventsInstall,
+		CheckOtelcolMetricsCollectorInstall,
+		CheckOtelcolLogsCollectorInstall,
+		CheckTracesInstall,
+	}
+
+	featInstall := GetInstallFeature(installChecks)
+
+	releaseName := strings_internal.ReleaseNameFromT(t)
+	featHPA := GetHPAFeature(releaseName)
+
+	testenv.Test(t, featInstall, featHPA)
+}
diff --git a/tests/integration/internal/stepfuncs/assess_funcs.go b/tests/integration/internal/stepfuncs/assess_funcs.go
@@ -4,6 +4,7 @@ import (
 	"context"
 	"errors"
 	"fmt"
+	"os"
 	"regexp"
 	"sort"
 	"strings"
@@ -12,6 +13,7 @@ import (
 
 	appsv1 "k8s.io/api/apps/v1"
 	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
+	"k8s.io/client-go/kubernetes"
 	log "k8s.io/klog/v2"
 	"sigs.k8s.io/e2e-framework/klient/k8s"
 	"sigs.k8s.io/e2e-framework/klient/k8s/resources"
@@ -351,6 +353,84 @@ func WaitUntilExpectedMetricLabelsPresent(
 	}
 }
 
+// WaitUntilHPAConfigured returns a features.Func that can be used in `Assess` calls.
+// It will wait until all the provided HPA are configured and active.
+func WaitUntilHPAConfigured(
+	expectedHPAMetadata []string,
+	expectedMetrics map[string]map[string]int,
+	waitDuration time.Duration,
+	tickDuration time.Duration,
+) features.Func {
+	return WaitUntilHPAPresent(
+		expectedHPAMetadata,
+		expectedMetrics,
+		waitDuration,
+		tickDuration,
+	)
+}
+
+// WaitUntilHPAPresent returns a features.Func that can be used in `Assess` calls.
+// It will wait until all the provided HPA are configured and active. It will not verify the
+// functionality of the HPA.
+func WaitUntilHPAPresent(expectedHPAMetadata []string,
+	expectedMetrics map[string]map[string]int,
+	waitDuration time.Duration,
+	tickDuration time.Duration,
+) features.Func {
+	return func(ctx context.Context, t *testing.T, envConf *envconf.Config) context.Context {
+		namespace := ctxopts.Namespace(ctx)
+		if namespace == "" {
+			log.Fatalf("Namespace not found in test context")
+		}
+
+		cfg := envconf.New().WithKubeconfigFile(os.Getenv("KUBECONFIG"))
+		c, err := kubernetes.NewForConfig(cfg.Client().RESTConfig())
+		require.NoError(t, err)
+
+		assert.Eventually(t, func() bool {
+			totalCount := len(expectedHPAMetadata)
+			currCount := 0
+			for _, expectedHPA := range expectedHPAMetadata {
+				hpa, err := c.AutoscalingV2().HorizontalPodAutoscalers(namespace).
+					Get(ctx, expectedHPA, metav1.GetOptions{})
+				if err != nil {
+					log.Errorf("failed to list HPAs: %v", err)
+					return false
+				}
+
+				if hpa == nil || hpa.Spec.Metrics == nil || len(hpa.Spec.Metrics) == 0 || hpa.Spec.Behavior == nil {
+					log.Infof("HPA %s is not configured. HPA: %v", expectedHPA, hpa)
+					return false
+				}
+
+				if len(hpa.Spec.Metrics) >= 2 && hpa.Spec.Behavior.ScaleUp != nil && hpa.Spec.Behavior.ScaleDown != nil {
+
+					resourceName1 := hpa.Spec.Metrics[0].Resource.Name
+					val1 := hpa.Spec.Metrics[0].Resource.Target.AverageUtilization
+					expectedVal1 := expectedMetrics[expectedHPA][string(resourceName1)]
+
+					resourceName2 := hpa.Spec.Metrics[0].Resource.Name
+					val2 := hpa.Spec.Metrics[1].Resource.Target.AverageUtilization
+					expectedVal2 := expectedMetrics[expectedHPA][string(resourceName2)]
+
+					if int(*val1) != expectedVal1 || int(*val2) != expectedVal2 {
+						log.Infof("HPA %s is configured and active but expectedValue: [%d, %d] "+
+							"did not match current value [%d, %d].",
+							expectedHPA, expectedVal1, expectedVal2, int(*val1), int(*val2))
+						return false
+					}
+					log.Infof("HPA %s is configured and active.", expectedHPA)
+					currCount += 1
+				}
+			}
+			log.Infof("Total HPA count: %d, Current HPA count: %d, expectedHPA: %v",
+				totalCount, currCount, expectedHPAMetadata)
+			return currCount == totalCount
+		}, waitDuration, tickDuration)
+		return ctx
+	}
+}
+
 // WaitUntilExpectedMetricsPresent returns a features.Func that can be used in `Assess` calls.
 // It will wait until the provided number of logs with the provided labels are returned by sumologic-mock's HTTP API on
 // the provided Service and port, until it succeeds or waitDuration passes.
diff --git a/tests/integration/values/values_helm_ot_hpa.yaml b/tests/integration/values/values_helm_ot_hpa.yaml
