Sync Terraform & Helm changes

GitOrigin-RevId: fe824dfdfa1dd4543969154c974702f04a34b3b8

terraform/aptos-node-testnet/aws/variables.tf

@@ -175,7 +175,7 @@ variable "utility_instance_type" {
 variable "validator_instance_type" {
   description = "Instance type used for validator and fullnodes"
   type        = string
-  default     = "c6i.8xlarge"
+  default     = "c6i.16xlarge"
 }
 
 ### Forge

terraform/aptos-node-testnet/gcp/variables.tf

@@ -218,7 +218,7 @@ variable "utility_instance_type" {
 variable "validator_instance_type" {
   description = "Instance type used for validator and fullnodes"
   type        = string
-  default     = "t2d-standard-16"
+  default     = "t2d-standard-60"
 }
 
 variable "utility_instance_enable_taint" {

terraform/aptos-node/aws/variables.tf

@@ -202,7 +202,7 @@ variable "utility_instance_enable_taint" {
 variable "validator_instance_type" {
   description = "Instance type used for validator and fullnodes"
   type        = string
-  default     = "c6i.8xlarge"
+  default     = "c6i.16xlarge"
 }
 
 variable "validator_instance_num" {

terraform/aptos-node/gcp/variables.tf

@@ -196,7 +196,7 @@ variable "utility_instance_type" {
 variable "validator_instance_type" {
   description = "Instance type used for validator and fullnodes"
   type        = string
-  default     = "t2d-standard-16"
+  default     = "t2d-standard-60"
 }
 
 variable "utility_instance_enable_taint" {

terraform/fullnode/aws/addons.tf

@@ -78,11 +78,6 @@ resource "helm_release" "pfn-addons" {
         acm_certificate          = var.zone_id != "" ? aws_acm_certificate.ingress[0].arn : null
         loadBalancerSourceRanges = var.client_sources_ipv4
       }
-      load_test = {
-        config = {
-          numFullnodeGroups = var.num_fullnodes
-        }
-      }
     }),
     jsonencode(var.pfn_helm_values),
   ]

terraform/fullnode/aws/variables.tf

@@ -134,7 +134,7 @@ variable "utility_instance_type" {
 variable "fullnode_instance_type" {
   description = "Instance type used for validator and fullnodes"
   type        = string
-  default     = "c6i.8xlarge"
+  default     = "c6i.16xlarge"
 }
 
 variable "num_extra_instance" {

terraform/fullnode/gcp/addons.tf

@@ -85,11 +85,6 @@ resource "helm_release" "pfn-addons" {
         gce_managed_certificate_domains = var.create_google_managed_ssl_certificate ? join(",", distinct(concat([local.domain], var.tls_sans))) : ""
         # loadBalancerSourceRanges = var.client_sources_ipv4 # not supported yet
       }
-      load_test = {
-        config = {
-          numFullnodeGroups = var.num_fullnodes
-        }
-      }
     }),
     jsonencode(var.pfn_helm_values),
   ]

terraform/fullnode/gcp/variables.tf

@@ -119,7 +119,7 @@ variable "utility_instance_type" {
 variable "fullnode_instance_type" {
   description = "Instance type used for validator and fullnodes"
   type        = string
-  default     = "t2d-standard-16"
+  default     = "t2d-standard-60"
 }
 
 variable "utility_instance_enable_taint" {

terraform/helm/aptos-node/files/haproxy.cfg

@@ -22,9 +22,10 @@ defaults
 
     # Set the default mode to TCP
     mode tcp
+    log-format "%ci:%cp [%t] %ft %b/%s %Tw/%Tc/%Tt %B %ts %ac/%fc/%bc/%sc/%rc %sq/%bq"
 
     # Don't log normal events
-    option dontlog-normal
+    # option dontlog-normal
 
     # Set timeouts for connections
     timeout client 60s

terraform/helm/aptos-node/templates/fullnode.yaml

@@ -107,9 +107,6 @@ spec:
         {{- if $.Values.metrics.destination }}
         aptos.dev/metrics-destination: {{ $.Values.metrics.destination }}
         {{- end}}
-        {{- with $.Values.validator.podAnnotations }}
-        {{- toYaml $.Values.validator.podAnnotations | nindent 8 }}
-        {{- end }}
     spec:
       securityContext:
         seccompProfile:

terraform/helm/aptos-node/templates/validator.yaml

@@ -87,9 +87,6 @@ spec:
         {{- if $.Values.metrics.destination }}
         aptos.dev/metrics-destination: {{ $.Values.metrics.destination }}
         {{- end}}
-        {{- with $.Values.fullnode.podAnnotations }}
-        {{- toYaml $.Values.fullnode.podAnnotations | nindent 8 }}
-        {{- end }}
     spec:
       securityContext:
         seccompProfile:

terraform/helm/aptos-node/values.yaml

@@ -87,9 +87,10 @@ validator:
   affinity: {}
   # -- Validator configuration. See NodeConfig https://github.com/aptos-labs/aptos-core/blob/main/config/src/config/mod.rs
   config: {}
-
+  # -- DEPRECATED: it's broken with Cillium a.k.a. GKE DataplaneV2.
+  # -- templates/networkpolicy.yaml kept around for reference in case we want to resurrect it.
   # -- Lock down network ingress and egress with Kubernetes NetworkPolicy
-  enableNetworkPolicy: true
+  enableNetworkPolicy: false
 
 fullnode:
   # -- Specify fullnode groups by `name` and number of `replicas`

terraform/helm/fullnode/templates/backup-compaction.yaml

@@ -61,7 +61,7 @@ spec:
                 fieldRef:
                   fieldPath: metadata.name
             - name: PUSH_METRICS_ENDPOINT
-              value: "{{- include "backup.pushMetricsEndpoint" $ }}/api/v1/import/prometheus?extra_label=role={{- .jobName | default "db_backup_compaction" }}&extra_label=kubernetes_pod_name=$(KUBERNETES_POD_NAME)"
+              value: "{{- include "backup.pushMetricsEndpoint" $ }}/api/v1/import/prometheus?extra_label=role={{- .jobName | default "db_backup_compaction" }}&extra_label=kubernetes_pod_name=$(KUBERNETES_POD_NAME)&extra_label=chain_name={{ $.Values.chain.label | default $.Values.chain.name }}"
             {{- end }}
             {{- include "backup.backupEnvironment" (dict "config" $.Values.backup.config "era" $.Values.chain.era) | nindent 12 }}
             {{- with .Values.backup_compaction }}

terraform/helm/fullnode/templates/backup-verify.yaml

@@ -59,7 +59,7 @@ spec:
                 fieldRef:
                   fieldPath: metadata.name
             - name: PUSH_METRICS_ENDPOINT
-              value: "{{- include "backup.pushMetricsEndpoint" $ }}/api/v1/import/prometheus?extra_label=role={{- .jobName | default "db_backup_verify" }}&extra_label=kubernetes_pod_name=$(KUBERNETES_POD_NAME)"
+              value: "{{- include "backup.pushMetricsEndpoint" $ }}/api/v1/import/prometheus?extra_label=role={{- .jobName | default "db_backup_verify" }}&extra_label=kubernetes_pod_name=$(KUBERNETES_POD_NAME)&extra_label=chain_name={{ $.Values.chain.label | default $.Values.chain.name }}"
             {{- end }}
             {{- include "backup.backupEnvironment" (dict "config" $.Values.backup.config "era" $.Values.chain.era) | nindent 12 }}
             {{- with .Values.backup_verify }}

terraform/helm/fullnode/templates/backup.yaml

@@ -75,7 +75,7 @@ spec:
             fieldRef:
               fieldPath: metadata.name
         - name: PUSH_METRICS_ENDPOINT
-          value: "{{- include "backup.pushMetricsEndpoint" $ }}/api/v1/import/prometheus?extra_label=role={{- .jobName | default "db_backup" }}&extra_label=kubernetes_pod_name=$(KUBERNETES_POD_NAME)"
+          value: "{{- include "backup.pushMetricsEndpoint" $ }}/api/v1/import/prometheus?extra_label=role={{- .jobName | default "db_backup" }}&extra_label=kubernetes_pod_name=$(KUBERNETES_POD_NAME)&extra_label=chain_name={{ $.Values.chain.label | default $.Values.chain.name }}"
         {{- end }}
         {{- include "backup.backupEnvironment" (dict "config" .config "era" $.Values.chain.era) | nindent 8 }}
         volumeMounts:

terraform/helm/pfn-addons/README.md

@@ -18,31 +18,8 @@ Additional components for a public fullnode fleet deployment
 | ingress.gce_security_policy | string | `nil` | Security policy to apply to the backend services behind the ingress |
 | ingress.health_check_duration_secs | string | `nil` | The maximum number of seconds that a PFN is allowed to be behind to be considered healthy and be allowed to serve traffic |
 | ingress.loadBalancerSourceRanges | string | `nil` |  |
+| ingress.logging.enabled | bool | `false` |  |
 | ingress.wafAclArn | string | `nil` |  |
-| load_test.affinity | object | `{}` |  |
-| load_test.config.duration | int | `300` | How long to emit transactions for |
-| load_test.config.expected_max_txns | int | `6000000` | Default 20k * $duration |
-| load_test.config.max_transactions_per_account | int | `5` |  |
-| load_test.config.mempool_backlog | int | `5000` | Number of transactions outstanding in mempool |
-| load_test.config.mint_key | string | `nil` | The private key used to mint to fund load test |
-| load_test.config.numFullnodeGroups | string | `nil` | The number of fullnode groups to run traffic against |
-| load_test.config.target_tps | int | `0` | Whether to target a constant TPS, or 0 if not used. Cannot be used with mempool_backlog. |
-| load_test.config.transaction_type | string | `"coin-transfer"` |  |
-| load_test.config.txn_expiration_time_secs | int | `30` | How long to wait for transactions to be expired |
-| load_test.config.use_pfns | bool | `true` | If true, run $numFullnodeGroups parallel load tests |
-| load_test.config.use_validators | bool | `false` | Whether to submit transactions through validator REST API |
-| load_test.enabled | bool | `false` | Whether to enable the load test CronJob |
-| load_test.fullnode | object | `{"groups":[{"name":"fullnode"}]}` | The fullnode groups to target |
-| load_test.image.pullPolicy | string | `"IfNotPresent"` | Image pull policy to use for tools image |
-| load_test.image.repo | string | `"aptoslabs/tools"` | Image repo to use for tools image for running load tests |
-| load_test.image.tag | string | `nil` | Image tag to use for tools image |
-| load_test.intervalMins | int | `15` | How many minutes between load test runs |
-| load_test.nodeSelector | object | `{}` |  |
-| load_test.resources.limits.cpu | int | `4` |  |
-| load_test.resources.limits.memory | string | `"4Gi"` |  |
-| load_test.resources.requests.cpu | int | `4` |  |
-| load_test.resources.requests.memory | string | `"4Gi"` |  |
-| load_test.tolerations | list | `[]` |  |
 | service.aws_tags | string | `nil` |  |
 | service.domain | string | `nil` |  |
 | service.enableOnchainDiscovery | bool | `false` |  |
@@ -53,4 +30,4 @@ Additional components for a public fullnode fleet deployment
 | serviceAccount.name | string | `nil` | The name of the service account to use. If not set and create is true, a name is generated using the fullname template |
 
 ----------------------------------------------
-Autogenerated from chart metadata using [helm-docs v1.13.1](https://github.com/norwoodj/helm-docs/releases/v1.13.1)
+Autogenerated from chart metadata using [helm-docs v1.14.2](https://github.com/norwoodj/helm-docs/releases/v1.14.2)

terraform/helm/pfn-addons/templates/service.yaml

@@ -39,6 +39,8 @@ spec:
   securityPolicy:
     name: {{ .Values.ingress.gce_security_policy }}
   {{- end }}
+  logging:
+    enable: {{ .Values.ingress.logging.enabled }}
   connectionDraining:
     drainingTimeoutSec: 30
   healthCheck:

terraform/helm/pfn-addons/values.yaml

@@ -22,6 +22,8 @@ ingress:
   loadBalancerSourceRanges:
   enableStickyness: true
   cookieDurationSeconds: 86400
+  logging:
+    enabled: false
   # the below only work for gce ingress
   gce_managed_certificate:
   gce_managed_certificate_domains:
@@ -32,51 +34,3 @@ ingress:
   # -- The maximum number of seconds that a PFN is allowed to be behind
   # to be considered healthy and be allowed to serve traffic
   health_check_duration_secs:
-
-load_test:
-  # -- Whether to enable the load test CronJob
-  enabled: false
-  image:
-    # -- Image repo to use for tools image for running load tests
-    repo: aptoslabs/tools
-    # -- Image tag to use for tools image
-    tag:
-    # -- Image pull policy to use for tools image
-    pullPolicy: IfNotPresent
-  resources:
-    limits:
-      cpu: 4
-      memory: 4Gi
-    requests:
-      cpu: 4
-      memory: 4Gi
-  nodeSelector: {}
-  tolerations: []
-  affinity: {}
-  # -- How many minutes between load test runs
-  intervalMins: 15
-  # -- The fullnode groups to target
-  fullnode:
-    groups:
-      - name: fullnode
-  config:
-    # -- The number of fullnode groups to run traffic against
-    numFullnodeGroups:
-    # -- The private key used to mint to fund load test
-    mint_key:
-    # -- Number of transactions outstanding in mempool
-    mempool_backlog: 5000
-    # -- Whether to target a constant TPS, or 0 if not used. Cannot be used with mempool_backlog.
-    target_tps: 0
-    # -- How long to emit transactions for
-    duration: 300
-    # -- How long to wait for transactions to be expired
-    txn_expiration_time_secs: 30
-    # -- Whether to submit transactions through validator REST API
-    use_validators: false
-    # -- If true, run $numFullnodeGroups parallel load tests
-    use_pfns: true
-    # -- Default 20k * $duration
-    expected_max_txns: 6000000
-    max_transactions_per_account: 5
-    transaction_type: coin-transfer