From d0217290e801461a1a3644efbcd985759dcedd9c Mon Sep 17 00:00:00 2001
From: Andre da Silva <2917611+ndr-ds@users.noreply.github.com>
Date: Fri, 21 Feb 2025 13:57:02 -0300
Subject: [PATCH] Port of #2994 - Send Prometheus metrics to Grafana Cloud
 (#3373)

## Motivation

We need this to deploy one validator with Grafana Cloud

## Proposal

Port to `testnet_archimedes`

## Test Plan

CI
---
 kubernetes/linera-validator/helmfile.yaml     | 27 +++++++++---------
 .../templates/grafana-cloud-auth-secret.yaml  | 10 +++++++
 ...es-local.yaml => values-local.yaml.gotmpl} | 28 ++++++++++++++++---
 3 files changed, 48 insertions(+), 17 deletions(-)
 create mode 100644 kubernetes/linera-validator/templates/grafana-cloud-auth-secret.yaml
 rename kubernetes/linera-validator/{values-local.yaml => values-local.yaml.gotmpl} (67%)

diff --git a/kubernetes/linera-validator/helmfile.yaml b/kubernetes/linera-validator/helmfile.yaml
index cc40c08fc243..48d774c4476c 100644
--- a/kubernetes/linera-validator/helmfile.yaml
+++ b/kubernetes/linera-validator/helmfile.yaml
@@ -1,3 +1,11 @@
+environments:
+  default:
+    values:
+      - writeToGrafanaCloud: {{ env "LINERA_WRITE_TO_GRAFANA_CLOUD" | default "false" }}
+        validatorLabel: {{ env "LINERA_VALIDATOR_LABEL" | default (printf "local-%s" (env "USER")) }}
+
+---
+
 repositories:
   - name: scylla
     url: https://scylla-operator-charts.storage.googleapis.com/stable
@@ -16,22 +24,15 @@ releases:
     needs:
       - scylla/scylla
     values:
-      - {{ env "LINERA_HELMFILE_VALUES_LINERA_CORE" | default "values-local.yaml" }}
+      {{ if .Values.writeToGrafanaCloud -}}
+      - grafanaCloudUsername: {{ fetchSecretValue (env "LINERA_GRAFANA_CLOUD_USERNAME_SECRET") | quote }}
+        grafanaCloudAPIToken: {{ fetchSecretValue (env "LINERA_GRAFANA_CLOUD_API_TOKEN_SECRET") | quote }}
+      {{- end }}
+      - writeToGrafanaCloud: {{ .Values.writeToGrafanaCloud }}
+      - {{ env "LINERA_HELMFILE_VALUES_LINERA_CORE" | default "values-local.yaml.gotmpl" }}
     set:
       - name: installCRDs
         value: "true"
-      - name: validator.serverConfig
-        value: {{ env "LINERA_HELMFILE_SET_SERVER_CONFIG" | default "working/server_1.json" }}
-      - name: validator.genesisConfig
-        value: {{ env "LINERA_HELMFILE_SET_GENESIS_CONFIG" | default "working/genesis.json" }}
-      - name: numShards
-        value: {{ env "LINERA_HELMFILE_SET_NUM_SHARDS" | default 10 }}
-      - name: lineraImage
-        value: {{ env "LINERA_HELMFILE_LINERA_IMAGE" | default "linera:latest" }}
-      - name: staticIpGcpName
-        value: {{ env "LINERA_HELMFILE_STATIC_IP_GCP_NAME" | default "" }}
-      - name: validatorDomainName
-        value: {{ env "LINERA_HELMFILE_VALIDATOR_DOMAIN_NAME" | default "" }}
   - name: scylla
     version: v1.13.0
     namespace: scylla
diff --git a/kubernetes/linera-validator/templates/grafana-cloud-auth-secret.yaml b/kubernetes/linera-validator/templates/grafana-cloud-auth-secret.yaml
new file mode 100644
index 000000000000..ebf74a60e35b
--- /dev/null
+++ b/kubernetes/linera-validator/templates/grafana-cloud-auth-secret.yaml
@@ -0,0 +1,10 @@
+{{- if .Values.writeToGrafanaCloud }}
+apiVersion: v1
+kind: Secret
+metadata:
+  name: grafana-cloud-auth-secret
+type: kubernetes.io/basic-auth
+stringData:
+  username: {{ .Values.grafanaCloudUsername | quote }}
+  password: {{ .Values.grafanaCloudAPIToken | quote }}
+{{- end }}
diff --git a/kubernetes/linera-validator/values-local.yaml b/kubernetes/linera-validator/values-local.yaml.gotmpl
similarity index 67%
rename from kubernetes/linera-validator/values-local.yaml
rename to kubernetes/linera-validator/values-local.yaml.gotmpl
index 3ce2b7de99b8..2855c14c243c 100644
--- a/kubernetes/linera-validator/values-local.yaml
+++ b/kubernetes/linera-validator/values-local.yaml.gotmpl
@@ -1,12 +1,12 @@
 # Values for charts linera-validator for local validators.
 
 # Linera
-lineraImage: "" # Is set by helmfile.
+lineraImage: {{ env "LINERA_HELMFILE_LINERA_IMAGE" | default "linera:latest" }}
 lineraImagePullPolicy: Never
 logLevel: "debug"
 proxyPort: 19100
 metricsPort: 21100
-numShards: 10
+numShards: {{ env "LINERA_HELMFILE_SET_NUM_SHARDS" | default 10 }}
 
 # Loki
 loki-stack:
@@ -40,6 +40,26 @@ kube-prometheus-stack:
       - grafana-piechart-panel
   prometheus:
     prometheusSpec:
+      {{- if .Values.writeToGrafanaCloud }}
+      scrapeInterval: 90s
+      remoteWrite:
+        - url: https://prometheus-prod-13-prod-us-east-0.grafana.net/api/prom/push
+          basicAuth:
+            username:
+              name: grafana-cloud-auth-secret
+              key: username
+            password:
+              name: grafana-cloud-auth-secret
+              key: password
+          writeRelabelConfigs:
+            - sourceLabels: [__name__]
+              regex: (apiextensions|apiserver|csi|kube|kubelet|kubernetes|node|prober|prometheus|rest|storage|volume|etcd|net|grafana|authentication|code|workqueue|cluster|go|alertmanager|authorization|namespace|scrape|up|field|registered|process|scylla).+
+              action: drop
+            - regex: endpoint|instance|namespace|pod|prometheus|prometheus_replica|service|name|resource|id
+              action: labeldrop
+      externalLabels:
+        validator: {{ .Values.validatorLabel }}
+      {{- end }}
       retention: 2d
       retentionSize: 1GB
       storageSpec:
@@ -101,5 +121,5 @@ environment: "kind"
 
 # Validator
 validator:
-  serverConfig: "" # Is set by helmfile.
-  genesisConfig: "" # Is set by helmfile.
+  serverConfig: {{ env "LINERA_HELMFILE_SET_SERVER_CONFIG" | default "working/server_1.json" }}
+  genesisConfig: {{ env "LINERA_HELMFILE_SET_GENESIS_CONFIG" | default "working/genesis.json" }}