feat: gating test

.github/workflows/ci.yml

@@ -715,6 +715,10 @@ jobs:
             values: 16-validators
             runner_type: 16core-tester-x86
             timeout: 60
+          - test: gating-passive.test.ts
+            values: 16-validators
+            runner_type: 16core-tester-x86
+            timeout: 60
     steps:
       - uses: actions/checkout@v4
         with: { ref: "${{ env.GIT_COMMIT }}" }

spartan/aztec-chaos-scenarios/Chart.yaml

@@ -0,0 +1,6 @@
+apiVersion: v2
+name: aztec-chaos-scenarios
+description: Chaos scenarios for spartan using chaos-mesh
+type: application
+version: 0.1.0
+appVersion: "1.0.0"

spartan/network-shaping/templates/_helpers.tpl → spartan/aztec-chaos-scenarios/templates/_helpers.tpl

@@ -1,7 +1,7 @@
 {{/*
 Create a default fully qualified app name.
 */}}
-{{- define "network-shaping.fullname" -}}
+{{- define "aztec-chaos-scenarios.fullname" -}}
 {{- if .Values.fullnameOverride }}
 {{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" }}
 {{- else }}
@@ -14,17 +14,12 @@ Create a default fully qualified app name.
 {{- end }}
 {{- end }}
 
-{{/*
-Selector labels
-*/}}
-{{- define "chaos-mesh.selectorLabels" -}}
-{{- end }}
 
 {{/*
 Common labels
 */}}
-{{- define "network-shaping.labels" -}}
-app.kubernetes.io/name: {{ include "network-shaping.fullname" . }}
+{{- define "aztec-chaos-scenarios.labels" -}}
+app.kubernetes.io/name: {{ include "aztec-chaos-scenarios.fullname" . }}
 app.kubernetes.io/instance: {{ .Release.Name }}
 {{- if .Chart.AppVersion }}
 app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}

spartan/aztec-chaos-scenarios/templates/boot-node-failure.yaml

@@ -0,0 +1,21 @@
+{{- if .Values.bootNodeFailure.enabled }}
+---
+apiVersion: chaos-mesh.org/v1alpha1
+kind: PodChaos
+metadata:
+  name: {{ .Values.global.targetNamespace }}-boot-node-failure
+  namespace: {{ .Values.global.chaosMeshNamespace }}
+  labels:
+    {{- include "aztec-chaos-scenarios.labels" . | nindent 4 }}
+  annotations:
+    "helm.sh/resource-policy": keep
+spec:
+  action: pod-failure
+  mode: all
+  selector:
+    namespaces:
+      - {{ .Values.global.targetNamespace }}
+    labelSelectors:
+      app: boot-node
+  duration: {{ .Values.bootNodeFailure.duration }}
+{{- end }}

spartan/network-shaping/templates/network-chaos.yaml → spartan/aztec-chaos-scenarios/templates/network-shaping.yaml

@@ -7,7 +7,7 @@ metadata:
   name: {{ .Values.global.targetNamespace }}-latency
   namespace: {{ .Values.global.chaosMeshNamespace }}
   labels:
-    {{- include "network-shaping.labels" . | nindent 4 }}
+    {{- include "aztec-chaos-scenarios.labels" . | nindent 4 }}
   annotations:
     "helm.sh/hook": post-install,post-upgrade
     "helm.sh/hook-weight": "0"
@@ -31,7 +31,7 @@ metadata:
   name: {{ .Values.global.targetNamespace }}-bandwidth
   namespace: {{ .Values.global.chaosMeshNamespace }}
   labels:
-    {{- include "network-shaping.labels" . | nindent 4 }}
+    {{- include "aztec-chaos-scenarios.labels" . | nindent 4 }}
   annotations:
     "helm.sh/hook": post-install,post-upgrade
     "helm.sh/hook-weight": "0"
@@ -57,7 +57,7 @@ metadata:
   name: {{ .Values.global.targetNamespace }}-packet-loss
   namespace: {{ .Values.global.chaosMeshNamespace }}
   labels:
-    {{- include "network-shaping.labels" . | nindent 4 }}
+    {{- include "aztec-chaos-scenarios.labels" . | nindent 4 }}
   annotations:
     "helm.sh/resource-policy": keep
 spec:
@@ -72,26 +72,4 @@ spec:
   duration: 8760h
 {{- end }}
 
-{{- if .Values.networkShaping.conditions.killProvers.enabled }}
----
-apiVersion: chaos-mesh.org/v1alpha1
-kind: PodChaos
-metadata:
-  name: {{ .Values.global.targetNamespace }}-kill-provers
-  namespace: {{ .Values.global.chaosMeshNamespace }}
-  labels:
-    {{- include "network-shaping.labels" . | nindent 4 }}
-  annotations:
-    "helm.sh/resource-policy": keep
-spec:
-  action: pod-failure
-  mode: all
-  selector:
-    namespaces:
-      - {{ .Values.global.targetNamespace }}
-    labelSelectors:
-      app: prover-node
-  duration: {{ .Values.networkShaping.conditions.killProvers.duration }}
 {{- end }}
-
-{{- end }}

spartan/aztec-chaos-scenarios/templates/prover-failure.yaml

@@ -0,0 +1,21 @@
+{{- if .Values.proverFailure.enabled }}
+---
+apiVersion: chaos-mesh.org/v1alpha1
+kind: PodChaos
+metadata:
+  name: {{ .Values.global.targetNamespace }}-prover-failure
+  namespace: {{ .Values.global.chaosMeshNamespace }}
+  labels:
+    {{- include "aztec-chaos-scenarios.labels" . | nindent 4 }}
+  annotations:
+    "helm.sh/resource-policy": keep
+spec:
+  action: pod-failure
+  mode: all
+  selector:
+    namespaces:
+      - {{ .Values.global.targetNamespace }}
+    labelSelectors:
+      app: prover-node
+  duration: {{ .Values.proverFailure.duration }}
+{{- end }}

spartan/aztec-chaos-scenarios/templates/validator-kill.yaml

@@ -0,0 +1,21 @@
+{{- if .Values.validatorKill.enabled }}
+---
+apiVersion: chaos-mesh.org/v1alpha1
+kind: PodChaos
+metadata:
+  name: {{ .Values.global.targetNamespace }}-validator-kill
+  namespace: {{ .Values.global.chaosMeshNamespace }}
+  labels:
+    {{- include "aztec-chaos-scenarios.labels" . | nindent 4 }}
+  annotations:
+    "helm.sh/resource-policy": keep
+spec:
+  action: pod-kill
+  mode: fixed-percent
+  value: {{ .Values.validatorKill.percent | quote }}
+  selector:
+    namespaces:
+      - {{ .Values.global.targetNamespace }}
+    labelSelectors:
+      app: validator
+{{- end }}

spartan/network-shaping/values.yaml → spartan/aztec-chaos-scenarios/values.yaml

@@ -1,3 +1,6 @@
+nameOverride: null
+fullnameOverride: null
+
 global:
   # When deploying, override the namespace to where spartan will deploy to, this will apply all chaos experiments to all pods within that namespace
   # run deployment with --values global.namespace=your-namespace
@@ -7,12 +10,12 @@ global:
 # Network shaping configuration
 networkShaping:
   # Master switch to enable network shaping
-  enabled: true
+  enabled: false
 
   # Default settings
   defaultSettings:
     mode: all
-    # Set duration to 1 year so the the experiment will run indefinitely unless overridden
+    # Set duration to 1 year so the experiment will run indefinitely unless overridden
     duration: 8760h
 
   # Network conditions to apply
@@ -62,9 +65,17 @@ networkShaping:
       # Buffer = smoother bandwidth restriction but higher memory usage
       buffer: 1000
 
-    killProvers:
-      enabled: false
-      duration: 13m
+proverFailure:
+  enabled: false
+  duration: 13m
+
+validatorKill:
+  enabled: false
+  percent: 30
+
+bootNodeFailure:
+  enabled: false
+  duration: 60m
 ## Here are some exciting example configurations created by claude:
 # Example use cases for different configurations:
 

spartan/aztec-chaos-scenarios/values/boot-node-failure.yaml

@@ -0,0 +1,6 @@
+global:
+  namespace: "smoke"
+
+bootNodeFailure:
+  enabled: true
+  duration: 60m

spartan/network-shaping/values/moderate.yaml → spartan/aztec-chaos-scenarios/values/moderate.yaml

@@ -22,4 +22,4 @@ networkShaping:
     packetLoss:
       enabled: true
       loss: "0.5"
-      correlation: "60"
+      correlation: "60"

spartan/aztec-chaos-scenarios/values/network-requirements.yaml

@@ -0,0 +1,23 @@
+# Imposes the network conditions that are stated as requirements for node operators
+global:
+  namespace: "smoke"
+
+networkShaping:
+  enabled: true
+  conditions:
+    latency:
+      enabled: true
+      delay:
+        # Regional network latency (e.g., cross-country)
+        latency: 100ms
+        jitter: 20ms
+        correlation: "75"
+    bandwidth:
+      enabled: true
+      rate: 250mbps
+      limit: 125000000
+      buffer: 25000
+    packetLoss:
+      enabled: true
+      loss: "0.5"
+      correlation: "60"

spartan/aztec-chaos-scenarios/values/prover-failure.yaml

@@ -0,0 +1,6 @@
+global:
+  namespace: "smoke"
+
+proverFailure:
+  enabled: true
+  duration: 13m

spartan/aztec-chaos-scenarios/values/validator-kill.yaml

@@ -0,0 +1,6 @@
+global:
+  namespace: "smoke"
+
+validatorKill:
+  enabled: true
+  percent: 25

spartan/aztec-network/templates/_helpers.tpl

@@ -78,7 +78,7 @@ http://{{ include "aztec-network.fullname" . }}-boot-node-0.{{ include "aztec-ne
 {{- if .Values.validator.externalTcpHost -}}
 http://{{ .Values.validator.externalTcpHost }}:{{ .Values.validator.service.nodePort }}
 {{- else -}}
-http://{{ include "aztec-network.fullname" . }}-validator-0.{{ include "aztec-network.fullname" . }}-validator.{{ .Release.Namespace }}.svc.cluster.local:{{ .Values.validator.service.nodePort }}
+http://{{ include "aztec-network.fullname" . }}-validator.{{ .Release.Namespace }}.svc.cluster.local:{{ .Values.validator.service.nodePort }}
 {{- end -}}
 {{- end -}}
 

spartan/aztec-network/templates/prover-node.yaml

@@ -18,7 +18,7 @@ spec:
         app: prover-node
     spec:
       initContainers:
-        - name: wait-for-boot-node
+        - name: wait-for-services
           image: {{ .Values.images.curl.image }}
           command:
             - /bin/sh

spartan/aztec-network/templates/pxe.yaml

@@ -49,7 +49,7 @@ spec:
             - name: ETHEREUM_HOST
               value: {{ include "aztec-network.ethereumHost" . | quote }}
             - name: AZTEC_NODE_URL
-              value: {{ include "aztec-network.bootNodeUrl" . | quote }}
+              value: {{ include "aztec-network.validatorUrl" . | quote }}
             - name: LOG_JSON
               value: "1"
             - name: LOG_LEVEL

spartan/aztec-network/templates/setup-l2-contracts.yaml

@@ -32,7 +32,7 @@ spec:
               echo "L2 contracts initialized"
           env:
             - name: PXE_URL
-              value: {{ include "aztec-network.pxeUrl" . | quote }}
+              value: {{ include "aztec-network.bootNodeUrl" . | quote }}
             - name: DEBUG
               value: "aztec:*"
             - name: LOG_LEVEL

spartan/aztec-network/templates/transaction-bot.yaml

@@ -25,7 +25,7 @@ spec:
               {{- if .Values.bot.nodeUrl }}
               value: "{{ .Values.bot.nodeUrl }}"
               {{- else }}
-              value: {{ include "aztec-network.bootNodeUrl" . | quote }}
+              value: {{ include "aztec-network.validatorUrl" . | quote }}
               {{- end }}
           command:
             - /bin/sh
@@ -47,7 +47,7 @@ spec:
               {{- if .Values.bot.nodeUrl }}
               value: "{{ .Values.bot.nodeUrl }}"
               {{- else }}
-              value: {{ include "aztec-network.bootNodeUrl" . | quote }}
+              value: {{ include "aztec-network.validatorUrl" . | quote }}
               {{- end }}
             - name: LOG_JSON
               value: "1"