Update default image to 2.2.2; add cache; update HPA

whylabs · Nov 26, 2024 · 5fe974a · 5fe974a
1 parent d298b90
commit 5fe974a
Show file tree

Hide file tree

Showing 7 changed files with 109 additions and 25 deletions.
diff --git a/charts/guardrails/CHANGELOG.md b/charts/guardrails/CHANGELOG.md
@@ -6,6 +6,17 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning]
 (https://semver.org/spec/v2.0.0.html).
 
+## [0.4.0] - 2024-11-26
+
+### Changed
+
+- Default image tag from `2.0.1` to `2.2.2`
+
+### Added
+
+- Caching support enabled with `cache.enable: true`
+- Horizontal Pod Autoscaler (HPA) support for configuring scaling behavior
+
 ## [0.3.1] - 2024-10-31
 
 ### Fixed

diff --git a/charts/guardrails/README.md b/charts/guardrails/README.md
@@ -31,11 +31,11 @@ You can manage the API keys and container secrets in one of two ways, depending
     # Helm release name (See installation for release_name usage)
     release_name=""
 
-    kubectl create secret generic "whylabs-${release_name}-api-key" \
+    kubectl create secret generic "whylabs-guardrails-api-key" \
       --namespace "${target_namespace}" \
       --from-literal=WHYLABS_API_KEY="${whylabs_api_key}"
 
-    kubectl create secret generic "whylabs-${release_name}-api-secret" \
+    kubectl create secret generic "whylabs-guardrails-api-secret" \
       --namespace "${target_namespace}" \
       --from-literal=CONTAINER_PASSWORD="${container_password}"
 
@@ -67,12 +67,12 @@ You can manage the API keys and container secrets in one of two ways, depending
 
     ```yaml
     envFrom:
-      whylabs-guardrails-api-key:
-        type: secretRef
-        optional: true
-      whylabs-guardrails-api-secret:
-        type: secretRef
-        optional: true
+      - secretRef:
+          name: whylabs-guardrails-api-key
+          optional: true
+      - secretRef:
+          name: whylabs-guardrails-api-secret
+          optional: true
     ```
 
 - File-based Secrets: If you are using a CSI driver, set envFrom: {} in your
@@ -195,9 +195,11 @@ utilization.
 | Key | Type | Default | Description |
 |-----|------|---------|-------------|
 | affinity | object | `{}` | Affinity settings for `Pod` [scheduling](https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/). If an explicit label selector is not provided for pod affinity or pod anti-affinity one will be created from the pod selector labels. |
-| autoscaling | object | `{"enabled":false,"maxReplicas":100,"minReplicas":1,"targetCPUUtilizationPercentage":70}` | [Horizontal Pod Autoscaler](https://kubernetes.io/docs/tasks/run-application/horizontal-pod-autoscale/) configuration for the `guardrails` container. |
+| autoscaling | object | `{"behavior":{"scaleDown":{"policies":[{"periodSeconds":180,"type":"Pods","value":"{{ .Values.replicaCount | int }}"},{"periodSeconds":180,"type":"Percent","value":30}],"selectPolicy":"Max","stabilizationWindowSeconds":300},"scaleUp":{"policies":[{"periodSeconds":180,"type":"Pods","value":"{{ .Values.replicaCount | int }}"},{"periodSeconds":180,"type":"Percent","value":50}],"selectPolicy":"Min","stabilizationWindowSeconds":180}},"enabled":false,"maxReplicas":100,"minReplicas":1,"targetCPUUtilizationPercentage":70}` | [Horizontal Pod Autoscaler](https://kubernetes.io/docs/tasks/run-application/horizontal-pod-autoscale/) configuration for the `guardrails` container. |
 | cache.annotations | object | `{}` |  |
+| cache.duration | string | `"1m"` |  |
 | cache.enable | bool | `false` |  |
+| cache.endpoint | string | `"api.whylabsapp.com"` |  |
 | cache.labels | object | `{}` |  |
 | cache.replicaCount | int | `1` |  |
 | commonLabels | object | `{}` | Labels to add to all chart resources. |
@@ -208,7 +210,7 @@ utilization.
 | fullnameOverride | string | `""` | Override the full name of the chart. |
 | image.pullPolicy | string | `"IfNotPresent"` | Image pull policy for the `guardrails` container. |
 | image.repository | string | `"registry.gitlab.com/whylabs/langkit-container"` | Image repository for the `guardrails` container. |
-| image.tag | string | `""` | Image tag for the `guardrails` container, this will default to `.Chart.AppVersion` if not set. |
+| image.tag | string | `"2.2.2"` | Image tag for the `guardrails` container, this will default to `.Chart.AppVersion` if not set. |
 | imagePullSecrets[0] | list | `{"name":""}` | Image pull secrets for the `guardrails` container. Defaults to `whylabs-{{ .Release.Name }}-registry-credentials` if `name: ""`. To exclude The ImagePullSecret entirely, set `imagePullSecrets: []` and comment out the list items. |
 | ingress | object | `{"annotations":{},"className":"","enabled":false,"hosts":[{"host":"chart-example.local","paths":[{"path":"/","pathType":"ImplementationSpecific"}]}],"tls":[]}` | [Ingress](https://kubernetes.io/docs/concepts/services-networking/ingress/) configuration for the `guardrails` container. |
 | livenessProbe | object | `{"failureThreshold":3,"httpGet":{"path":"/health","port":8000},"initialDelaySeconds":30,"periodSeconds":30}` | [Liveness probe](https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-startup-probes/) configuration for the `guardrails` container. |

diff --git a/charts/guardrails/README.md.gotmpl b/charts/guardrails/README.md.gotmpl
@@ -38,11 +38,11 @@ You can manage the API keys and container secrets in one of two ways, depending
     # Helm release name (See installation for release_name usage)
     release_name=""
 
-    kubectl create secret generic "whylabs-${release_name}-api-key" \
+    kubectl create secret generic "whylabs-guardrails-api-key" \
       --namespace "${target_namespace}" \
       --from-literal=WHYLABS_API_KEY="${whylabs_api_key}"
 
-    kubectl create secret generic "whylabs-${release_name}-api-secret" \
+    kubectl create secret generic "whylabs-guardrails-api-secret" \
       --namespace "${target_namespace}" \
       --from-literal=CONTAINER_PASSWORD="${container_password}"
 
@@ -74,12 +74,12 @@ You can manage the API keys and container secrets in one of two ways, depending
 
     ```yaml
     envFrom:
-      whylabs-guardrails-api-key:
-        type: secretRef
-        optional: true
-      whylabs-guardrails-api-secret:
-        type: secretRef
-        optional: true
+      - secretRef:
+          name: whylabs-guardrails-api-key
+          optional: true
+      - secretRef:
+          name: whylabs-guardrails-api-secret
+          optional: true
     ```
 
 - File-based Secrets: If you are using a CSI driver, set envFrom: {} in your

diff --git a/charts/guardrails/templates/configmap-cache.yaml b/charts/guardrails/templates/configmap-cache.yaml
@@ -47,12 +47,12 @@ data:
     }
   cache_config.conf: |
     proxy_cache my_cache;
-    proxy_cache_valid 200 403 1m;
+    proxy_cache_valid 200 403 {{ .Values.cache.duration }};
     proxy_cache_use_stale error timeout http_500 http_502 http_503 http_504;
     add_header X-Cache-Status $upstream_cache_status always;
   common_proxy.conf: |
-    proxy_pass https://songbird.development.whylabsdev.com;
-    proxy_set_header Host songbird.development.whylabsdev.com;
+    proxy_pass https://{{ .Values.cache.endpoint }};
+    proxy_set_header Host {{ .Values.cache.endpoint }};
     proxy_set_header X-Real-IP $remote_addr;
     proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
     proxy_set_header X-Forwarded-Proto $scheme;

diff --git a/charts/guardrails/templates/deployment-cache.yaml b/charts/guardrails/templates/deployment-cache.yaml
@@ -21,6 +21,8 @@ spec:
         app: {{ .Release.Name }}-cache
     spec:
       serviceAccountName: {{ include "guardrails.serviceAccountName" . }}
+      securityContext:
+        fsGroup: 101
       containers:
         - name: nginx
           securityContext:
@@ -30,7 +32,6 @@ spec:
             runAsNonRoot: true
             runAsUser: 101
             runAsGroup: 101
-            fsGroup: 101
             capabilities:
               drop: ["ALL"]
           image: "nginxinc/nginx-unprivileged:latest"

diff --git a/charts/guardrails/templates/hpa.yaml b/charts/guardrails/templates/hpa.yaml
@@ -10,8 +10,45 @@ spec:
     apiVersion: apps/v1
     kind: Deployment
     name: {{ include "guardrails.fullname" . }}
-  minReplicas: {{ .Values.autoscaling.minReplicas }}
-  maxReplicas: {{ .Values.autoscaling.maxReplicas }}
+  minReplicas: {{ default 1 .Values.autoscaling.minReplicas }}
+  maxReplicas: {{ default 20 .Values.autoscaling.maxReplicas }}
+  {{- with .Values.autoscaling.behavior }}
+  behavior:
+    {{- with .scaleUp }}
+    scaleUp:
+      {{- with .policies }}
+      policies:
+        {{- range . }}
+        - type: {{ .type }}
+          value: {{ tpl (toString .value) $ | int }}
+          periodSeconds: {{ .periodSeconds | int }}
+        {{- end }}
+      {{- end }}
+      {{- with .selectPolicy }}
+      selectPolicy: {{ . }}
+      {{- end }}
+      {{- with .stabilizationWindowSeconds }}
+      stabilizationWindowSeconds: {{ . | int }}
+      {{- end }}
+    {{- end }}
+    {{- with .scaleDown }}
+    scaleDown:
+      {{- with .policies }}
+      policies:
+        {{- range . }}
+        - type: {{ .type }}
+          value: {{ tpl (toString .value) $ | int }}
+          periodSeconds: {{ .periodSeconds | int }}
+        {{- end }}
+      {{- end }}
+      {{- with .selectPolicy }}
+      selectPolicy: {{ . }}
+      {{- end }}
+      {{- with .stabilizationWindowSeconds }}
+      stabilizationWindowSeconds: {{ . | int}}
+      {{- end }}
+    {{- end }}
+  {{- end }}
   metrics:
     {{- if .Values.autoscaling.targetCPUUtilizationPercentage }}
     - type: Resource

diff --git a/charts/guardrails/values.yaml b/charts/guardrails/values.yaml
@@ -1,6 +1,8 @@
 cache:
   enable: false
+  duration: 1m
   replicaCount: 1
+  endpoint: "api.whylabsapp.com"
   annotations: {}
   labels: {}
 
@@ -14,7 +16,7 @@ image:
   pullPolicy: IfNotPresent
   # -- (string) Image tag for the `guardrails` container, this will default to
   # `.Chart.AppVersion` if not set.
-  tag: ""
+  tag: "2.2.2"
 
 imagePullSecrets:
   # -- (list) Image pull secrets for the `guardrails` container. Defaults to
@@ -138,6 +140,37 @@ autoscaling:
   enabled: false
   minReplicas: 1
   maxReplicas: 100
+  behavior:
+    scaleUp:
+      policies:
+        - type: Pods
+          value: "{{ .Values.replicaCount | int }}"
+          periodSeconds: 180
+        - type: Percent
+          value: 50
+          periodSeconds: 180
+      # selectPolicy can be `Min` or `Max` and refers to scaling policy
+      # to choose when there are multiple policies; `Max` will choose the
+      # policy perform the largest scaling adjustment, while `Min` will
+      # choose the policy that performs the smallest scaling adjustment.
+      selectPolicy: Min
+      stabilizationWindowSeconds: 180
+    scaleDown:
+      policies:
+        - type: Pods
+          value: "{{ .Values.replicaCount | int }}"
+          # periodSeconds is the rate at which a policy can be applied;
+          # this policy may only be applied once per period.
+          periodSeconds: 180
+        - type: Percent
+          value: 30
+          # periodSeconds is the rate at which a policy can be applied;
+          # this policy may only be applied once per period.
+          periodSeconds: 180
+      selectPolicy: Max
+      # stabilizationWindowSeconds is how many seconds the HPA looks back
+      # to determine if a policy is being met.
+      stabilizationWindowSeconds: 300
   targetCPUUtilizationPercentage: 70
   # targetMemoryUtilizationPercentage: 70