feat: Adding CPU / RAM configurations to helm network deployments (#8786

)

# Change 1: CPU/RAM Limits for node deployments

This PR assigns resource configurations to nodes that are part of helm
network deployments.
Adding such resource configurations helps Kubernetes balance and deploy
aztec nodes.

These initial values are chosen based on historical usage of the
currently deployed `devnet` environment in AWS ( [Grafana
Dashboard](https://grafana.aztec.network/d/cdtxao66xa1ogc/aztec-dashboard?orgId=1&refresh=1m&var-network=devnet&var-instance=All&var-protocol_circuit=All&var-min_block_build=20m&var-system_res_interval=$__auto_interval_system_res_interval&var-sequencer=All&var-prover=All&from=now-7d&to=now)
).

**Definitions**
`requests:` This is the minimum resource that must be available on the
underlying server before Kubernetes can deploy the component.
`limits:` After deployment, the component is allowed to flex up and
down, but never above this set limit. Using a limit keeps the shared
infra stable when there is memory leaks or unexpected application
behavior. Components are terminated and redeployed if exceeding the
assigned limit.


# Change 2: Options for bots and public networks

Additionally, this PR add configuration to turn bots as well as public
access on or off at the time of the helm deployment. This can be used
with the following helm syntax:

```
helm upgrade --install <installation name> . -n <kubernetes namespace> \ 
--set network.public=true --set network.enableBots=true
```

By default, `network.public` is `false` since enabling this deploys load
balancers which are not available when running a Kubernetes cluster on a
local machine and within CI environments.

---

These resource configurations have been tested by deploying the parent
helm chart to the spartan Kubernetes cluster in AWS.

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

@@ -136,7 +136,7 @@ metadata:
   labels:
     {{- include "aztec-network.labels" . | nindent 4 }}
 spec:
-  clusterIP: None
+  type: {{if .Values.network.public }}"LoadBalancer"{{ else }}"ClusterIP"{{ end }}
   selector:
     {{- include "aztec-network.selectorLabels" . | nindent 4 }}
     app: boot-node

spartan/aztec-network/templates/metrics.yaml

@@ -78,7 +78,7 @@ metadata:
   labels:
     {{- include "aztec-network.labels" . | nindent 4 }}
 spec:
-  type: {{ .Values.metrics.service.type }}
+  type: {{if .Values.network.public }}"LoadBalancer"{{ else }}"ClusterIP"{{ end }}
   ports:
     - port: {{ .Values.metrics.ports.otlp }}
       targetPort: otlp

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

@@ -106,7 +106,7 @@ metadata:
   labels:
     {{- include "aztec-network.labels" . | nindent 4 }}
 spec:
-  clusterIP: None
+  type: {{if .Values.network.public }}"LoadBalancer"{{ else }}"ClusterIP"{{ end }}
   selector:
     {{- include "aztec-network.selectorLabels" . | nindent 4 }}
     app: prover-node

spartan/aztec-network/templates/pxe.yaml

@@ -1,3 +1,4 @@
+{{- if .Values.network.enableBots }}
 apiVersion: apps/v1
 kind: Deployment
 metadata:
@@ -65,7 +66,7 @@ metadata:
   labels:
     {{- include "aztec-network.labels" . | nindent 4 }}
 spec:
-  type: {{ .Values.pxe.service.type }}
+  type: {{if .Values.network.public }}"LoadBalancer"{{ else }}"ClusterIP"{{ end }}
   selector:
     {{- include "aztec-network.selectorLabels" . | nindent 4 }}
     app: pxe
@@ -75,4 +76,5 @@ spec:
       targetPort: {{ .Values.pxe.service.targetPort }}
       {{- if and (eq .Values.pxe.service.type "NodePort") .Values.pxe.service.nodePort }}
       nodePort: {{ .Values.pxe.service.nodePort }}
-      {{- end }}
+      {{- end }}
+{{- end }}

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

@@ -1,3 +1,4 @@
+{{- if .Values.network.enableBots }}
 apiVersion: apps/v1
 kind: Deployment
 metadata:
@@ -99,4 +100,5 @@ spec:
       targetPort: {{ .Values.bot.service.targetPort }}
       {{- if and (eq .Values.bot.service.type "NodePort") .Values.bot.service.nodePort }}
       nodePort: {{ .Values.bot.service.nodePort }}
-      {{- end }}
+      {{- end }}
+{{- end }}

spartan/aztec-network/templates/validator.yaml

@@ -115,7 +115,7 @@ metadata:
   labels:
     {{- include "aztec-network.labels" . | nindent 4 }}
 spec:
-  clusterIP: None
+  type: {{if .Values.network.public }}"LoadBalancer"{{ else }}"ClusterIP"{{ end }}
   selector:
     {{- include "aztec-network.selectorLabels" . | nindent 4 }}
     app: validator

spartan/aztec-network/values.yaml

@@ -1,3 +1,10 @@
+test: "sample"
+scenario: "default"
+
+network:
+  public: false
+  enableBots: true
+
 images:
   test:
     image: aztecprotocol/end-to-end
@@ -38,7 +45,13 @@ bootNode:
     disabled: true
   p2p:
     enabled: "true"
-  resources: {}
+  resources:
+    requests:
+      memory: "2Gi"
+      cpu: "200m"
+    limits:
+      memory: "4Gi"
+      cpu: "4"
 
 validator:
   replicas: 0
@@ -54,7 +67,13 @@ validator:
     disabled: false
   p2p:
     enabled: "true"
-  resources: {}
+  resources:
+    requests:
+      memory: "2Gi"
+      cpu: "200m"
+    limits:
+      memory: "28Gi"
+      cpu: "7"
 
 proverNode:
   replicas: 1
@@ -64,14 +83,19 @@ proverNode:
   debug: "aztec:*"
   realProofs: false
   proverAgentEnabled: true
-  resources: {}
+  resources:
+    requests:
+      memory: "2Gi"
+      cpu: "200m"
+    limits:
+      memory: "120Gi"
+      cpu: "15"
 
 pxe:
   logLevel: "debug"
   debug: "aztec:*"
   replicas: 1
   service:
-    type: ClusterIP
     port: 8080
     targetPort: 8080
   readinessProbe:
@@ -80,7 +104,13 @@ pxe:
     timeoutSeconds: 5
     successThreshold: 1
     failureThreshold: 3
-  resources: {}
+  resources:
+    requests:
+      memory: "2Gi"
+      cpu: "200m"
+    limits:
+      memory: "4Gi"
+      cpu: "1"
 
 bot:
   logLevel: "debug"
@@ -104,7 +134,13 @@ bot:
     timeoutSeconds: 5
     successThreshold: 1
     failureThreshold: 3
-  resources: {}
+  resources:
+    requests:
+      memory: "2Gi"
+      cpu: "200m"
+    limits:
+      memory: "4Gi"
+      cpu: "1"
 
 ethereum:
   replicas: 1
@@ -126,11 +162,15 @@ ethereum:
     timeoutSeconds: 5
     successThreshold: 1
     failureThreshold: 3
-  resources: {}
+  resources:
+    requests:
+      memory: "2Gi"
+      cpu: "200m"
+    limits:
+      memory: "4Gi"
+      cpu: "1"
 
 metrics:
-  service:
-    type: ClusterIP
   ports:
     otlp: 4316
     metrics: 4315
@@ -143,6 +183,3 @@ metrics:
     timeoutSeconds: 5
     successThreshold: 1
     failureThreshold: 3
-
-test: "sample"
-scenario: "default"