feat(splunk): improve Forge O11y dashboards

modules/integrations/splunk_o11y_conf_shared/README.md

@@ -21,6 +21,7 @@
 | <a name="module_dashboard_billing"></a> [dashboard\_billing](#module\_dashboard\_billing) | ./dashboards/billing | n/a |
 | <a name="module_dashboard_dynamodb"></a> [dashboard\_dynamodb](#module\_dashboard\_dynamodb) | ./dashboards/dynamodb | n/a |
 | <a name="module_dashboard_ebs"></a> [dashboard\_ebs](#module\_dashboard\_ebs) | ./dashboards/ebs | n/a |
+| <a name="module_dashboard_forge_impact"></a> [dashboard\_forge\_impact](#module\_dashboard\_forge\_impact) | ./dashboards/forge_impact | n/a |
 | <a name="module_dashboard_lambda"></a> [dashboard\_lambda](#module\_dashboard\_lambda) | ./dashboards/lambda | n/a |
 | <a name="module_dashboard_runner_ec2"></a> [dashboard\_runner\_ec2](#module\_dashboard\_runner\_ec2) | ./dashboards/runner_ec2 | n/a |
 | <a name="module_dashboard_runner_k8s"></a> [dashboard\_runner\_k8s](#module\_dashboard\_runner\_k8s) | ./dashboards/runner_k8s | n/a |

modules/integrations/splunk_o11y_conf_shared/dashboards.tf

@@ -84,6 +84,17 @@ module "dashboard_ebs" {
   dashboard_group   = signalfx_dashboard_group.forgecicd.id
 }
 
+module "dashboard_forge_impact" {
+  source = "./dashboards/forge_impact"
+
+  providers = {
+    signalfx = signalfx
+  }
+
+  tenant_names    = var.dashboard_variables.runner_k8s.tenant_names
+  dashboard_group = signalfx_dashboard_group.forgecicd.id
+}
+
 # Cost and usage
 module "dashboard_billing" {
   source = "./dashboards/billing"

modules/integrations/splunk_o11y_conf_shared/dashboards/billing/README.md

@@ -21,10 +21,12 @@ No modules.
 | Name | Type |
 | ---- | ---- |
 | [signalfx_dashboard.billing](https://registry.terraform.io/providers/splunk-terraform/signalfx/latest/docs/resources/dashboard) | resource |
+| [signalfx_list_chart.top_tenant_service_net_cost](https://registry.terraform.io/providers/splunk-terraform/signalfx/latest/docs/resources/list_chart) | resource |
 | [signalfx_time_chart.cost_per_service](https://registry.terraform.io/providers/splunk-terraform/signalfx/latest/docs/resources/time_chart) | resource |
 | [signalfx_time_chart.cost_per_tenant](https://registry.terraform.io/providers/splunk-terraform/signalfx/latest/docs/resources/time_chart) | resource |
 | [signalfx_time_chart.net_cost_per_service](https://registry.terraform.io/providers/splunk-terraform/signalfx/latest/docs/resources/time_chart) | resource |
 | [signalfx_time_chart.net_cost_per_tenant](https://registry.terraform.io/providers/splunk-terraform/signalfx/latest/docs/resources/time_chart) | resource |
+| [signalfx_time_chart.runner_related_net_cost](https://registry.terraform.io/providers/splunk-terraform/signalfx/latest/docs/resources/time_chart) | resource |
 | [signalfx_time_chart.total_cost](https://registry.terraform.io/providers/splunk-terraform/signalfx/latest/docs/resources/time_chart) | resource |
 | [signalfx_time_chart.total_net_cost](https://registry.terraform.io/providers/splunk-terraform/signalfx/latest/docs/resources/time_chart) | resource |
 

modules/integrations/splunk_o11y_conf_shared/dashboards/billing/main.tf

@@ -4,8 +4,8 @@ resource "signalfx_time_chart" "cost_per_service" {
 
   program_text = <<-EOF
 A = data('forge.per_service.cost_usd')
-B = A.max(by=['usage_date', 'service', 'forgecicd_tenant','usage_month', 'usage_year'])
-C = B.sum(by=['service', 'forgecicd_tenant','usage_month', 'usage_year'])
+B = A.max(by=['usage_date', 'service', 'forgecicd_tenant', 'usage_month', 'usage_year'])
+C = B.sum(by=['service', 'forgecicd_tenant', 'usage_month', 'usage_year'])
 
 # publish both current and baseline
 C.publish(label='current')
@@ -35,8 +35,8 @@ resource "signalfx_time_chart" "net_cost_per_service" {
 
   program_text = <<-EOF
 A = data('forge.per_service.net_cost_usd')
-B = A.max(by=['usage_date', 'service', 'forgecicd_tenant','usage_month', 'usage_year'])
-C = B.sum(by=['service', 'forgecicd_tenant','usage_month', 'usage_year'])  # removes usage_date from label
+B = A.max(by=['usage_date', 'service', 'forgecicd_tenant', 'usage_month', 'usage_year'])
+C = B.sum(by=['service', 'forgecicd_tenant', 'usage_month', 'usage_year'])  # removes usage_date from label
 
 # publish both current and baseline
 C.publish(label='current')
@@ -65,8 +65,8 @@ resource "signalfx_time_chart" "net_cost_per_tenant" {
 
   program_text = <<-EOF
 A = data('forge.per_service.net_cost_usd')
-B = A.max(by=['usage_date', 'service', 'forgecicd_tenant','usage_month', 'usage_year'])
-C = B.sum(by=['forgecicd_tenant','usage_month', 'usage_year'])
+B = A.max(by=['usage_date', 'service', 'forgecicd_tenant', 'usage_month', 'usage_year'])
+C = B.sum(by=['forgecicd_tenant', 'usage_month', 'usage_year'])
 D = C.timeshift('29d')
 
 # publish both current and baseline
@@ -97,8 +97,8 @@ resource "signalfx_time_chart" "cost_per_tenant" {
 
   program_text = <<-EOF
 A = data('forge.per_service.cost_usd')
-B = A.max(by=['usage_date', 'service', 'forgecicd_tenant','usage_month', 'usage_year'])
-C = B.sum(by=['forgecicd_tenant','usage_month', 'usage_year'])
+B = A.max(by=['usage_date', 'service', 'forgecicd_tenant', 'usage_month', 'usage_year'])
+C = B.sum(by=['forgecicd_tenant', 'usage_month', 'usage_year'])
 D = C.timeshift('29d')
 
 # publish both current and baseline
@@ -131,8 +131,8 @@ resource "signalfx_time_chart" "total_cost" {
   program_text = <<-EOF
 A = data('forge.per_service.cost_usd')
 
-# Take max per day/service/tenant, carrying forward last value if missing
-B = A.max(by=['usage_date', 'service', 'forgecicd_tenant','usage_month', 'usage_year'])
+# Take max per daily cost stream before collapsing to the total
+B = A.max(by=['usage_date', 'service', 'forgecicd_tenant', 'usage_month', 'usage_year'])
 
 # Sum by month, still carrying forward where needed
 C = B.sum(by=['usage_month', 'usage_year'])
@@ -176,8 +176,8 @@ resource "signalfx_time_chart" "total_net_cost" {
   program_text = <<-EOF
 A = data('forge.per_service.net_cost_usd')
 
-# Take max per day/service/tenant, carrying forward last value if missing
-B = A.max(by=['usage_date', 'service', 'forgecicd_tenant','usage_month', 'usage_year'])
+# Take max per daily cost stream before collapsing to the total
+B = A.max(by=['usage_date', 'service', 'forgecicd_tenant', 'usage_month', 'usage_year'])
 
 # Sum by month, still carrying forward where needed
 C = B.sum(by=['usage_month', 'usage_year'])
@@ -207,6 +207,73 @@ EOF
   }
 }
 
+resource "signalfx_time_chart" "runner_related_net_cost" {
+  name        = "Runner-related net cost"
+  description = "Shows net cost for AWS services that commonly back Forge runners and the job-log pipeline."
+
+  program_text = <<-EOF
+A = data('forge.per_service.net_cost_usd', filter=filter('service', 'AmazonEC2', 'AmazonEKS', 'AWSLambda', 'AmazonSQS', 'AmazonDynamoDB', 'AmazonS3', 'AmazonVPC', 'AmazonCloudWatch', 'awskms', 'AWSSecretsManager', 'AmazonECR'))
+B = A.max(by=['usage_date', 'service', 'forgecicd_tenant', 'usage_month', 'usage_year'])
+C = B.sum(by=['service', 'forgecicd_tenant', 'usage_month', 'usage_year'])
+C.publish(label='current')
+EOF
+
+  plot_type      = "AreaChart"
+  axes_precision = 0
+  time_range     = 3600
+
+  on_chart_legend_dimension = "service"
+
+  histogram_options {
+    color_theme = "gold"
+  }
+
+  viz_options {
+    axis         = "left"
+    color        = "blue"
+    display_name = "current"
+    label        = "current"
+  }
+}
+
+resource "signalfx_list_chart" "top_tenant_service_net_cost" {
+  name        = "Top tenant/service net cost"
+  description = "Ranks tenant and service combinations by current net cost."
+
+  program_text = <<-EOF
+A = data('forge.per_service.net_cost_usd')
+B = A.max(by=['usage_date', 'service', 'forgecicd_tenant', 'usage_month', 'usage_year'])
+C = B.sum(by=['forgecicd_tenant', 'service']).top(count=20).publish(label='A')
+EOF
+
+  sort_by = "-value"
+
+  disable_sampling        = false
+  hide_missing_values     = true
+  max_precision           = 4
+  secondary_visualization = "None"
+  time_range              = 3600
+  unit_prefix             = "Metric"
+
+  legend_options_fields {
+    enabled  = true
+    property = "forgecicd_tenant"
+  }
+  legend_options_fields {
+    enabled  = true
+    property = "service"
+  }
+  legend_options_fields {
+    enabled  = false
+    property = "sf_metric"
+  }
+
+  viz_options {
+    display_name = "Net cost"
+    label        = "A"
+  }
+}
+
 resource "signalfx_dashboard" "billing" {
   name            = "Billing"
   description     = "Forge CICD cost and net cost by service and tenant."
@@ -220,7 +287,7 @@ resource "signalfx_dashboard" "billing" {
     description            = ""
     values                 = []
     value_required         = false
-    values_suggested       = var.tenant_names
+    values_suggested       = sort(var.tenant_names)
     restricted_suggestions = true
   }
 
@@ -286,4 +353,20 @@ resource "signalfx_dashboard" "billing" {
     width    = 6
     height   = 1
   }
+
+  chart {
+    chart_id = signalfx_time_chart.runner_related_net_cost.id
+    row      = 3
+    column   = 0
+    width    = 6
+    height   = 1
+  }
+
+  chart {
+    chart_id = signalfx_list_chart.top_tenant_service_net_cost.id
+    row      = 3
+    column   = 6
+    width    = 6
+    height   = 1
+  }
 }

modules/integrations/splunk_o11y_conf_shared/dashboards/dynamodb/main.tf

@@ -506,7 +506,7 @@ resource "signalfx_dashboard" "dynamodb" {
     description            = ""
     values                 = []
     value_required         = false
-    values_suggested       = var.tenant_names
+    values_suggested       = sort(var.tenant_names)
     restricted_suggestions = true
   }
 

modules/integrations/splunk_o11y_conf_shared/dashboards/ebs/main.tf

@@ -535,7 +535,7 @@ resource "signalfx_dashboard" "ebs" {
     description            = ""
     values                 = []
     value_required         = false
-    values_suggested       = var.tenant_names
+    values_suggested       = sort(var.tenant_names)
     restricted_suggestions = true
   }
 

modules/integrations/splunk_o11y_conf_shared/dashboards/forge_impact/README.md

@@ -0,0 +1,48 @@
+<!-- BEGIN_TF_DOCS -->
+## Requirements
+
+| Name | Version |
+| ---- | ------- |
+| <a name="requirement_terraform"></a> [terraform](#requirement\_terraform) | ~> 1.11 |
+| <a name="requirement_signalfx"></a> [signalfx](#requirement\_signalfx) | < 10.0.0 |
+
+## Providers
+
+| Name | Version |
+| ---- | ------- |
+| <a name="provider_signalfx"></a> [signalfx](#provider\_signalfx) | 9.30.1 |
+| <a name="provider_terraform"></a> [terraform](#provider\_terraform) | n/a |
+
+## Modules
+
+No modules.
+
+## Resources
+
+| Name | Type |
+| ---- | ---- |
+| [signalfx_dashboard.forge_impact](https://registry.terraform.io/providers/splunk-terraform/signalfx/latest/docs/resources/dashboard) | resource |
+| [signalfx_list_chart.active_ec2_runners_by_tenant](https://registry.terraform.io/providers/splunk-terraform/signalfx/latest/docs/resources/list_chart) | resource |
+| [signalfx_list_chart.active_ec2_runners_by_tenant_and_instance_type](https://registry.terraform.io/providers/splunk-terraform/signalfx/latest/docs/resources/list_chart) | resource |
+| [signalfx_list_chart.ec2_runner_hours_by_tenant](https://registry.terraform.io/providers/splunk-terraform/signalfx/latest/docs/resources/list_chart) | resource |
+| [signalfx_list_chart.ec2_runner_hours_by_tenant_and_instance_type](https://registry.terraform.io/providers/splunk-terraform/signalfx/latest/docs/resources/list_chart) | resource |
+| [signalfx_list_chart.k8s_runner_hours_by_tenant](https://registry.terraform.io/providers/splunk-terraform/signalfx/latest/docs/resources/list_chart) | resource |
+| [signalfx_list_chart.k8s_runners_by_tenant](https://registry.terraform.io/providers/splunk-terraform/signalfx/latest/docs/resources/list_chart) | resource |
+| [signalfx_list_chart.runner_minutes_by_runtime](https://registry.terraform.io/providers/splunk-terraform/signalfx/latest/docs/resources/list_chart) | resource |
+| [signalfx_list_chart.runner_totals_by_runtime](https://registry.terraform.io/providers/splunk-terraform/signalfx/latest/docs/resources/list_chart) | resource |
+| [signalfx_list_chart.total_ec2_runners_by_tenant](https://registry.terraform.io/providers/splunk-terraform/signalfx/latest/docs/resources/list_chart) | resource |
+| [signalfx_list_chart.total_k8s_runners_by_tenant](https://registry.terraform.io/providers/splunk-terraform/signalfx/latest/docs/resources/list_chart) | resource |
+| [signalfx_time_chart.active_ec2_runners_by_tenant_and_instance_type](https://registry.terraform.io/providers/splunk-terraform/signalfx/latest/docs/resources/time_chart) | resource |
+| [terraform_data.dashboard_parent](https://registry.terraform.io/providers/hashicorp/terraform/latest/docs/resources/data) | resource |
+
+## Inputs
+
+| Name | Description | Type | Default | Required |
+| ---- | ----------- | ---- | ------- | :------: |
+| <a name="input_dashboard_group"></a> [dashboard\_group](#input\_dashboard\_group) | Dashboard group name for organizing dashboards. | `string` | n/a | yes |
+| <a name="input_tenant_names"></a> [tenant\_names](#input\_tenant\_names) | Tenant namespaces that run Forge ARC runners. | `list(string)` | n/a | yes |
+
+## Outputs
+
+No outputs.
+<!-- END_TF_DOCS -->