[helm] Add support for monitoring stack

deploy/infrastructure/dependencies/terraform-commons-dss/helm.tf

@@ -91,6 +91,32 @@ resource "local_file" "helm_chart_values" {
     global = {
       cloudProvider = var.kubernetes_cloud_provider_name
     }
+
+    monitoring = {
+      enabled = false
+    },
+
+    prometheus = {
+      server = {
+        persistentVolume = {
+          storageClass = var.kubernetes_storage_class
+        }
+
+        global = {
+          external_labels = {
+            environment = "dev"
+            k8s_cluster = var.cluster_name
+          }
+        }
+      }
+    }
+
+    grafana = {
+      persistence = {
+        storageClassName = var.kubernetes_storage_class
+      }
+    }
+
     }) : yamlencode({
     cockroachdb = {
       enabled = false
@@ -261,6 +287,31 @@ resource "local_file" "helm_chart_values" {
     global = {
       cloudProvider = var.kubernetes_cloud_provider_name
     }
+
+    monitoring = {
+      enabled = false
+    },
+
+    prometheus = {
+      server = {
+        persistentVolume = {
+          storageClass = var.kubernetes_storage_class
+        }
+
+        global = {
+          external_labels = {
+            environment = "dev"
+            k8s_cluster = var.cluster_name
+          }
+        }
+      }
+    }
+
+    grafana = {
+      persistence = {
+        storageClassName = var.kubernetes_storage_class
+      }
+    }
   })
 
 }

deploy/infrastructure/dependencies/terraform-commons-dss/variables.gen.tf

@@ -55,6 +55,15 @@ variable "node_count" {
 }
 
 
+variable "cluster_name" {
+  type        = string
+  description = <<-EOT
+  Name of the kubernetes cluster that will host this DSS instance (should generally describe the DSS instance being hosted)
+
+  Example: `dss-che-1`
+  EOT
+}
+
 variable "image" {
   type        = string
   description = <<-EOT

deploy/infrastructure/modules/terraform-aws-dss/main.tf

@@ -16,6 +16,7 @@ module "terraform-aws-kubernetes" {
 
 module "terraform-commons-dss" {
   # See variables.tf for variables description.
+  cluster_name                     = var.cluster_name
   image                            = var.image
   image_pull_secret                = var.image_pull_secret
   kubernetes_namespace             = var.kubernetes_namespace

deploy/infrastructure/modules/terraform-google-dss/main.tf

@@ -16,6 +16,7 @@ module "terraform-google-kubernetes" {
 
 module "terraform-commons-dss" {
   # See variables.tf for variables description.
+  cluster_name                     = var.cluster_name
   image                            = var.image
   kubernetes_namespace             = var.kubernetes_namespace
   kubernetes_storage_class         = var.google_kubernetes_storage_class

deploy/infrastructure/utils/variables.py

@@ -23,7 +23,7 @@
 
 # Variables per project
 # For all */terraform-*
-GLOBAL_VARIABLES = ["app_hostname", "db_hostname_suffix", "datastore_type", "node_count"]
+GLOBAL_VARIABLES = ["app_hostname", "db_hostname_suffix", "datastore_type", "node_count", "cluster_name"]
 
 # dependencies/terraform-commons-dss
 COMMONS_DSS_VARIABLES = GLOBAL_VARIABLES + [
@@ -59,7 +59,6 @@
 
 # dependencies/terraform-*-kubernetes
 COMMON_KUBERNETES_VARIABLES = GLOBAL_VARIABLES + [
-    "cluster_name",
     "kubernetes_version",
 ]
 

deploy/services/helm-charts/dss/Chart.yaml

@@ -13,3 +13,11 @@ dependencies:
     repository: https://interuss.github.io/yugabyte-charts/
     version: 2025.1.0
     condition: yugabyte.enabled
+  - name: prometheus
+    repository: https://prometheus-community.github.io/helm-charts
+    version: 27.51.0
+    condition: monitoring.enabled
+  - name: grafana
+    repository: https://grafana.github.io/helm-charts
+    version: 10.3.1
+    condition: monitoring.enabled

deploy/services/helm-charts/dss/grafana_dashboards

@@ -0,0 +1 @@
+../../tanka/grafana_dashboards

deploy/services/helm-charts/dss/templates/grafana-dashboards.yaml

@@ -0,0 +1,17 @@
+{{- if $.Values.monitoring.enabled }}
+
+---
+
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: dss-grafana-dashboards-default
+  labels:
+    grafana_dashboard: "1"
+data:
+{{- range $path, $bytes := .Files.Glob "grafana_dashboards/*.json" }}
+  {{ base $path }}: |-
+{{ $.Files.Get $path | indent 4 }}
+  {{- end }}
+
+{{- end }}

deploy/services/helm-charts/dss/values.example.yaml

@@ -77,3 +77,15 @@ loadBalancers:
 
 global:
   cloudProvider: google
+
+monitoring:  # Set to true to enable monitoring stack
+  enabled: true
+
+prometheus:
+  server:
+    persistentVolume:
+      storageClass: standard  # If you need a specfic storage class, set it there
+
+grafana:
+  persistence:
+    storageClassName: standard  # If you need a specfic storage class, set it there

deploy/services/helm-charts/dss/values.schema.json

@@ -342,12 +342,23 @@
         }
       },
       "required": ["cloudProvider"]
+    },
+    "monitoring": {
+      "type": "object",
+      "properties": {
+        "enabled": {
+          "type": "boolean",
+          "description": "Enable monitoring stack with prometheus and grafana."
+        }
+      },
+      "required": ["enabled"]
     }
   },
   "required": [
     "loadBalancers",
     "dss",
-    "global"
+    "global",
+    "monitoring"
   ],
   "title": "Values",
   "type": "object"

deploy/services/helm-charts/dss/values.yaml

@@ -64,3 +64,209 @@ yugabyte:
       placement_cloud: "cloud-1"
       placement_region: "uss-1"
       placement_zone: "zone-1"
+
+monitoring:
+  enabled: false
+
+prometheus:
+  server:
+    global:
+      scrape_interval: 5s
+      scrape_timeout: 5s
+      evaluation_interval: 5s
+
+    service:
+      annotations:
+        'prometheus.io/scrape': 'true'
+        'prometheus.io/port': '9090'
+
+  prometheus-pushgateway:
+    enabled: false
+
+  prometheus-node-exporter:
+    enabled: false
+
+  kube-state-metrics:
+    enabled: false
+
+  alertmanager:
+    enabled: false
+
+  serverFiles:
+    prometheus.yml:
+      scrape_configs:
+        - job_name: K8s-Endpoints
+          tls_config:
+            insecure_skip_verify: true
+          relabel_configs:
+          - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape]
+            separator: ;
+            regex: "true"
+            replacement: $1
+            action: keep
+          - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scheme]
+            separator: ;
+            regex: (https?)
+            target_label: __scheme__
+            replacement: $1
+            action: replace
+          - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path]
+            separator: ;
+            regex: (.+)
+            target_label: __metrics_path__
+            replacement: $1
+            action: replace
+          - source_labels: [__address__, __meta_kubernetes_service_annotation_prometheus_io_port]
+            separator: ;
+            regex: ([^:]+)(?::\d+)?;(\d+)
+            target_label: __address__
+            replacement: $1:$2
+            action: replace
+          - separator: ;
+            regex: __meta_kubernetes_service_label_([^_]+)(_kubernetes_io_name)?$
+            replacement: $1
+            action: labelmap
+          - source_labels: [__meta_kubernetes_namespace]
+            separator: ;
+            target_label: kubernetes_namespace
+            replacement: $1
+            action: replace
+          - source_labels: [__meta_kubernetes_service_name]
+            separator: ;
+            target_label: kubernetes_name
+            replacement: $1
+            action: replace
+          - source_labels: [__meta_kubernetes_pod_label_statefulset_kubernetes_io_pod_name]
+            separator: ;
+            regex: (dss-cockroachdb-\d+)
+            target_label: pod_name
+            replacement: $1
+            action: replace
+          kubernetes_sd_configs:
+          - role: endpoints
+
+    recording_rules.yml:
+      "groups":
+        - "name": "rules/aggregation.rules"
+          "rules":
+          - "expr": "sum without(store) (capacity{app=\"cockroachdb\"})"
+            "record": "node:capacity"
+          - "expr": "sum without(instance) (node:capacity{app=\"cockroachdb\"})"
+            "record": "cluster:capacity"
+          - "expr": "sum without(store) (capacity_available{app=\"cockroachdb\"})"
+            "record": "node:capacity_available"
+          - "expr": "sum without(instance) (node:capacity_available{app=\"cockroachdb\"})"
+            "record": "cluster:capacity_available"
+          - "expr": "capacity_available{app=\"cockroachdb\"} / capacity{app=\"cockroachdb\"}"
+            "record": "capacity_available:ratio"
+          - "expr": "node:capacity_available{app=\"cockroachdb\"} / node:capacity{app=\"cockroachdb\"}"
+            "record": "node:capacity_available:ratio"
+          - "expr": "cluster:capacity_available{app=\"cockroachdb\"} / cluster:capacity{app=\"cockroachdb\"}"
+            "record": "cluster:capacity_available:ratio"
+          - "expr": "rate(txn_durations_bucket{app=\"cockroachdb\"}[1m])"
+            "record": "txn_durations_bucket:rate1m"
+          - "expr": "histogram_quantile(0.5, txn_durations_bucket:rate1m)"
+            "record": "txn_durations:rate1m:quantile_50"
+          - "expr": "histogram_quantile(0.75, txn_durations_bucket:rate1m)"
+            "record": "txn_durations:rate1m:quantile_75"
+          - "expr": "histogram_quantile(0.9, txn_durations_bucket:rate1m)"
+            "record": "txn_durations:rate1m:quantile_90"
+          - "expr": "histogram_quantile(0.95, txn_durations_bucket:rate1m)"
+            "record": "txn_durations:rate1m:quantile_95"
+          - "expr": "histogram_quantile(0.99, txn_durations_bucket:rate1m)"
+            "record": "txn_durations:rate1m:quantile_99"
+          - "expr": "rate(exec_latency_bucket{app=\"cockroachdb\"}[1m])"
+            "record": "exec_latency_bucket:rate1m"
+          - "expr": "histogram_quantile(0.5, exec_latency_bucket:rate1m)"
+            "record": "exec_latency:rate1m:quantile_50"
+          - "expr": "histogram_quantile(0.75, exec_latency_bucket:rate1m)"
+            "record": "exec_latency:rate1m:quantile_75"
+          - "expr": "histogram_quantile(0.9, exec_latency_bucket:rate1m)"
+            "record": "exec_latency:rate1m:quantile_90"
+          - "expr": "histogram_quantile(0.95, exec_latency_bucket:rate1m)"
+            "record": "exec_latency:rate1m:quantile_95"
+          - "expr": "histogram_quantile(0.99, exec_latency_bucket:rate1m)"
+            "record": "exec_latency:rate1m:quantile_99"
+          - "expr": "rate(round_trip_latency_bucket{app=\"cockroachdb\"}[1m])"
+            "record": "round_trip_latency_bucket:rate1m"
+          - "expr": "histogram_quantile(0.5, round_trip_latency_bucket:rate1m)"
+            "record": "round_trip_latency:rate1m:quantile_50"
+          - "expr": "histogram_quantile(0.75, round_trip_latency_bucket:rate1m)"
+            "record": "round_trip_latency:rate1m:quantile_75"
+          - "expr": "histogram_quantile(0.9, round_trip_latency_bucket:rate1m)"
+            "record": "round_trip_latency:rate1m:quantile_90"
+          - "expr": "histogram_quantile(0.95, round_trip_latency_bucket:rate1m)"
+            "record": "round_trip_latency:rate1m:quantile_95"
+          - "expr": "histogram_quantile(0.99, round_trip_latency_bucket:rate1m)"
+            "record": "round_trip_latency:rate1m:quantile_99"
+          - "expr": "rate(sql_exec_latency_bucket{app=\"cockroachdb\"}[1m])"
+            "record": "sql_exec_latency_bucket:rate1m"
+          - "expr": "histogram_quantile(0.5, sql_exec_latency_bucket:rate1m)"
+            "record": "sql_exec_latency:rate1m:quantile_50"
+          - "expr": "histogram_quantile(0.75, sql_exec_latency_bucket:rate1m)"
+            "record": "sql_exec_latency:rate1m:quantile_75"
+          - "expr": "histogram_quantile(0.9, sql_exec_latency_bucket:rate1m)"
+            "record": "sql_exec_latency:rate1m:quantile_90"
+          - "expr": "histogram_quantile(0.95, sql_exec_latency_bucket:rate1m)"
+            "record": "sql_exec_latency:rate1m:quantile_95"
+          - "expr": "histogram_quantile(0.99, sql_exec_latency_bucket:rate1m)"
+            "record": "sql_exec_latency:rate1m:quantile_99"
+          - "expr": "rate(raft_process_logcommit_latency_bucket{app=\"cockroachdb\"}[1m])"
+            "record": "raft_process_logcommit_latency_bucket:rate1m"
+          - "expr": "histogram_quantile(0.5, raft_process_logcommit_latency_bucket:rate1m)"
+            "record": "raft_process_logcommit_latency:rate1m:quantile_50"
+          - "expr": "histogram_quantile(0.75, raft_process_logcommit_latency_bucket:rate1m)"
+            "record": "raft_process_logcommit_latency:rate1m:quantile_75"
+          - "expr": "histogram_quantile(0.9, raft_process_logcommit_latency_bucket:rate1m)"
+            "record": "raft_process_logcommit_latency:rate1m:quantile_90"
+          - "expr": "histogram_quantile(0.95, raft_process_logcommit_latency_bucket:rate1m)"
+            "record": "raft_process_logcommit_latency:rate1m:quantile_95"
+          - "expr": "histogram_quantile(0.99, raft_process_logcommit_latency_bucket:rate1m)"
+            "record": "raft_process_logcommit_latency:rate1m:quantile_99"
+          - "expr": "rate(raft_process_commandcommit_latency_bucket{app=\"cockroachdb\"}[1m])"
+            "record": "raft_process_commandcommit_latency_bucket:rate1m"
+          - "expr": "histogram_quantile(0.5, raft_process_commandcommit_latency_bucket:rate1m)"
+            "record": "raft_process_commandcommit_latency:rate1m:quantile_50"
+          - "expr": "histogram_quantile(0.75, raft_process_commandcommit_latency_bucket:rate1m)"
+            "record": "raft_process_commandcommit_latency:rate1m:quantile_75"
+          - "expr": "histogram_quantile(0.9, raft_process_commandcommit_latency_bucket:rate1m)"
+            "record": "raft_process_commandcommit_latency:rate1m:quantile_90"
+          - "expr": "histogram_quantile(0.95, raft_process_commandcommit_latency_bucket:rate1m)"
+            "record": "raft_process_commandcommit_latency:rate1m:quantile_95"
+          - "expr": "histogram_quantile(0.99, raft_process_commandcommit_latency_bucket:rate1m)"
+            "record": "raft_process_commandcommit_latency:rate1m:quantile_99"
+
+grafana:
+
+  datasources:
+    datasources.yaml:
+      apiVersion: 1
+      datasources:
+        - name: prometheus
+          type: prometheus
+          access: proxy
+          orgId: 1
+          url: http://dss-prometheus-server:80
+          version: 1
+          editable: true
+
+  dashboardProviders:
+    dashboardproviders.yaml:
+      apiVersion: 1
+      providers:
+        - name: 'default'
+          orgId: 1
+          folder: ''
+          type: file
+          disableDeletion: false
+          editable: true
+          options:
+            path: /var/lib/grafana/dashboards/default
+
+  dashboardsConfigMaps:
+    default: "dss-grafana-dashboards-default"
+
+  persistence:
+    type: pvc
+    enabled: true
+>>>>>>> f3220540 ([helm] Add support for monitoring stack)