feat: add prometheus panels to grafana (#118)

* fix: Prometheus data-source authentication * feat: add panels for Prometheus metrics * Update terraform/monitoring/panels/app/identity/invalid_unregister_jwt.libsonnet Co-authored-by: Szymon Rząd <sz.rzad@gmail.com> * Update terraform/monitoring/panels/app/identity/invalid_register_cacao.libsonnet Co-authored-by: Szymon Rząd <sz.rzad@gmail.com> * Update terraform/monitoring/panels/app/invite/invalid_register_jwt.libsonnet Co-authored-by: Szymon Rząd <sz.rzad@gmail.com> * Update terraform/monitoring/panels/app/invite/invalid_unregister_jwt.libsonnet Co-authored-by: Szymon Rząd <sz.rzad@gmail.com> --------- Co-authored-by: Szymon Rząd <sz.rzad@gmail.com>
WalletConnect · Aug 24, 2023 · 9e99609 · 9e99609
1 parent 06424db
commit 9e99609
Show file tree

Hide file tree

Showing 19 changed files with 272 additions and 16 deletions.
diff --git a/terraform/ecs/outputs.tf b/terraform/ecs/outputs.tf
@@ -22,3 +22,8 @@ output "load_balancer_arn_suffix" {
   description = "The ARN suffix of the load balancer"
   value       = aws_lb.load_balancer.arn_suffix
 }
+
+output "ecs_task_family" {
+  description = "The family of the task definition"
+  value       = aws_ecs_task_definition.app_task.family
+}
diff --git a/terraform/monitoring/dashboard.jsonnet b/terraform/monitoring/dashboard.jsonnet
@@ -20,6 +20,7 @@ local vars  = {
   notifications:    std.parseJson(std.extVar('notifications')),
 
   ecs_service_name: std.extVar('ecs_service_name'),
+  ecs_task_family:  std.extVar('ecs_task_family'),
   load_balancer:    std.extVar('load_balancer'),
   target_group:     std.extVar('target_group'),
   docdb_cluster_id: std.extVar('docdb_cluster_id'),
@@ -50,23 +51,38 @@ dashboard.new(
 )
 .addPanels(grafana.layout.generate_grid([
   row.new('Application'),
-    panels.app.cpu(ds, vars)                      { gridPos: pos._2 },
-    panels.app.memory(ds, vars)                   { gridPos: pos._2 },
+    panels.app.identity.resolved(ds, vars)                { gridPos: pos._3 },
+    panels.app.identity.register(ds, vars)                { gridPos: pos._3 },
+    panels.app.identity.unregister(ds, vars)              { gridPos: pos._3 },
+
+    panels.app.identity.invalid_register_cacao(ds, vars)  { gridPos: pos._2 },
+    panels.app.identity.invalid_unregister_jwt(ds, vars)  { gridPos: pos._2 },
+
+    panels.app.invite.resolved(ds, vars)                  { gridPos: pos._3 },
+    panels.app.invite.register(ds, vars)                  { gridPos: pos._3 },
+    panels.app.invite.unregister(ds, vars)                { gridPos: pos._3 },
+
+    panels.app.invite.invalid_register_jwt(ds, vars)      { gridPos: pos._2 },
+    panels.app.invite.invalid_unregister_jwt(ds, vars)    { gridPos: pos._2 },
+
+  row.new('ECS'),
+    panels.ecs.cpu(ds, vars)                              { gridPos: pos._2 },
+    panels.ecs.memory(ds, vars)                           { gridPos: pos._2 },
 
   row.new('Load Balancer'),
-    panels.lb.active_connections(ds, vars)        { gridPos: pos._2 },
-    panels.lb.healthy_hosts(ds, vars)             { gridPos: pos._2 },
+    panels.lb.active_connections(ds, vars)                { gridPos: pos._2 },
+    panels.lb.healthy_hosts(ds, vars)                     { gridPos: pos._2 },
 
-    panels.lb.requests(ds, vars)                  { gridPos: pos._3 },
-    panels.lb.error_4xx(ds, vars)                 { gridPos: pos._3 },
-    panels.lb.error_5xx(ds, vars)                 { gridPos: pos._3 },
+    panels.lb.requests(ds, vars)                          { gridPos: pos._3 },
+    panels.lb.error_4xx(ds, vars)                         { gridPos: pos._3 },
+    panels.lb.error_5xx(ds, vars)                         { gridPos: pos._3 },
 
   row.new('DocumentDB'),
-    panels.docdb.cpu(ds, vars)                    { gridPos: pos._3 },
-    panels.docdb.available_memory(ds, vars)       { gridPos: pos._3 },
-    panels.docdb.connections(ds, vars)            { gridPos: pos._3 },
+    panels.docdb.cpu(ds, vars)                            { gridPos: pos._3 },
+    panels.docdb.available_memory(ds, vars)               { gridPos: pos._3 },
+    panels.docdb.connections(ds, vars)                    { gridPos: pos._3 },
 
-    panels.docdb.low_mem_op_throttled(ds, vars)   { gridPos: pos._3 },
-    panels.docdb.volume(ds, vars)                 { gridPos: pos._3 },
-    panels.docdb.buffer_cache_hit_ratio(ds, vars) { gridPos: pos._3 },
+    panels.docdb.low_mem_op_throttled(ds, vars)           { gridPos: pos._3 },
+    panels.docdb.volume(ds, vars)                         { gridPos: pos._3 },
+    panels.docdb.buffer_cache_hit_ratio(ds, vars)         { gridPos: pos._3 },
 ]))
diff --git a/terraform/monitoring/dashboard.tf b/terraform/monitoring/dashboard.tf
@@ -12,6 +12,7 @@ data "jsonnet_file" "dashboard" {
     notifications = jsonencode(var.notification_channels)
 
     ecs_service_name = var.ecs_service_name
+    ecs_task_family  = var.ecs_task_family
     load_balancer    = var.load_balancer_arn
     target_group     = var.ecs_target_group_arn
     docdb_cluster_id = var.keystore_cluster_id

diff --git a/terraform/monitoring/data_sources.tf b/terraform/monitoring/data_sources.tf
@@ -1,6 +1,7 @@
 module "monitoring-role" {
   source          = "app.terraform.io/wallet-connect/monitoring-role/aws"
   version         = "1.0.2"
+  context         = module.this
   remote_role_arn = var.monitoring_role_arn
 }
 
@@ -12,7 +13,7 @@ resource "grafana_data_source" "prometheus" {
   json_data_encoded = jsonencode({
     httpMethod         = "GET"
     sigV4Auth          = true
-    sigV4AuthType      = "workspace-iam-role"
+    sigV4AuthType      = "ec2_iam_role"
     sigV4Region        = module.this.region
     sigV4AssumeRoleArn = module.monitoring-role.iam_role_arn
   })

diff --git a/terraform/monitoring/panels/app/identity/invalid_register_cacao.libsonnet b/terraform/monitoring/panels/app/identity/invalid_register_cacao.libsonnet
@@ -0,0 +1,21 @@
+local grafana        = import '../../../grafonnet-lib/grafana.libsonnet';
+local panels         = grafana.panels;
+local targets        = grafana.targets;
+
+local defaults  = import '../../defaults.libsonnet';
+
+{
+  new(ds, vars)::
+    panels.timeseries(
+      title       = 'Identity - Invalid CACAO during Registration',
+      datasource  = ds.prometheus,
+    )
+    .configure(defaults.configuration.timeseries)
+
+    .addTarget(targets.prometheus(
+      datasource  = ds.prometheus,
+      expr        = 'sum(rate(invalid_identity_register_cacao{aws_ecs_task_family="%s"}[5m]))' % vars.ecs_task_family,
+      refId       = "sources",
+      exemplar    = true,
+    ))
+}
diff --git a/terraform/monitoring/panels/app/identity/invalid_unregister_jwt.libsonnet b/terraform/monitoring/panels/app/identity/invalid_unregister_jwt.libsonnet
@@ -0,0 +1,21 @@
+local grafana        = import '../../../grafonnet-lib/grafana.libsonnet';
+local panels         = grafana.panels;
+local targets        = grafana.targets;
+
+local defaults  = import '../../defaults.libsonnet';
+
+{
+  new(ds, vars)::
+    panels.timeseries(
+      title       = 'Identity - Invalid JWT during Unregistration',
+      datasource  = ds.prometheus,
+    )
+    .configure(defaults.configuration.timeseries)
+
+    .addTarget(targets.prometheus(
+      datasource  = ds.prometheus,
+      expr        = 'sum(rate(invalid_identity_unregister_jwt{aws_ecs_task_family="%s"}[5m]))' % vars.ecs_task_family,
+      refId       = "sources",
+      exemplar    = true,
+    ))
+}
diff --git a/terraform/monitoring/panels/app/identity/register.libsonnet b/terraform/monitoring/panels/app/identity/register.libsonnet
@@ -0,0 +1,21 @@
+local grafana        = import '../../../grafonnet-lib/grafana.libsonnet';
+local panels         = grafana.panels;
+local targets        = grafana.targets;
+
+local defaults  = import '../../defaults.libsonnet';
+
+{
+  new(ds, vars)::
+    panels.timeseries(
+      title       = 'Identity - Registrations',
+      datasource  = ds.prometheus,
+    )
+    .configure(defaults.configuration.timeseries)
+
+    .addTarget(targets.prometheus(
+      datasource  = ds.prometheus,
+      expr        = 'sum(rate(identity_register{aws_ecs_task_family="%s"}[5m]))' % vars.ecs_task_family,
+      refId       = "sources",
+      exemplar    = true,
+    ))
+}
diff --git a/terraform/monitoring/panels/app/identity/resolved.libsonnet b/terraform/monitoring/panels/app/identity/resolved.libsonnet
@@ -0,0 +1,21 @@
+local grafana        = import '../../../grafonnet-lib/grafana.libsonnet';
+local panels         = grafana.panels;
+local targets        = grafana.targets;
+
+local defaults  = import '../../defaults.libsonnet';
+
+{
+  new(ds, vars)::
+    panels.timeseries(
+      title       = 'Identity - Resolutions',
+      datasource  = ds.prometheus,
+    )
+    .configure(defaults.configuration.timeseries)
+
+    .addTarget(targets.prometheus(
+      datasource  = ds.prometheus,
+      expr        = 'sum(rate(identity_resolved{aws_ecs_task_family="%s"}[5m]))' % vars.ecs_task_family,
+      refId       = "sources",
+      exemplar    = true,
+    ))
+}
diff --git a/terraform/monitoring/panels/app/identity/unregister.libsonnet b/terraform/monitoring/panels/app/identity/unregister.libsonnet
@@ -0,0 +1,21 @@
+local grafana        = import '../../../grafonnet-lib/grafana.libsonnet';
+local panels         = grafana.panels;
+local targets        = grafana.targets;
+
+local defaults  = import '../../defaults.libsonnet';
+
+{
+  new(ds, vars)::
+    panels.timeseries(
+      title       = 'Identity - Unregistrations',
+      datasource  = ds.prometheus,
+    )
+    .configure(defaults.configuration.timeseries)
+
+    .addTarget(targets.prometheus(
+      datasource  = ds.prometheus,
+      expr        = 'sum(rate(identity_unregister{aws_ecs_task_family="%s"}[5m]))' % vars.ecs_task_family,
+      refId       = "sources",
+      exemplar    = true,
+    ))
+}
diff --git a/terraform/monitoring/panels/app/invite/invalid_register_jwt.libsonnet b/terraform/monitoring/panels/app/invite/invalid_register_jwt.libsonnet
@@ -0,0 +1,21 @@
+local grafana        = import '../../../grafonnet-lib/grafana.libsonnet';
+local panels         = grafana.panels;
+local targets        = grafana.targets;
+
+local defaults  = import '../../defaults.libsonnet';
+
+{
+  new(ds, vars)::
+    panels.timeseries(
+      title       = 'Invite - Invalid JWT during Registration',
+      datasource  = ds.prometheus,
+    )
+    .configure(defaults.configuration.timeseries)
+
+    .addTarget(targets.prometheus(
+      datasource  = ds.prometheus,
+      expr        = 'sum(rate(invalid_invite_register_jwt{aws_ecs_task_family="%s"}[5m]))' % vars.ecs_task_family,
+      refId       = "sources",
+      exemplar    = true,
+    ))
+}
diff --git a/terraform/monitoring/panels/app/invite/invalid_unregister_jwt.libsonnet b/terraform/monitoring/panels/app/invite/invalid_unregister_jwt.libsonnet
@@ -0,0 +1,21 @@
+local grafana        = import '../../../grafonnet-lib/grafana.libsonnet';
+local panels         = grafana.panels;
+local targets        = grafana.targets;
+
+local defaults  = import '../../defaults.libsonnet';
+
+{
+  new(ds, vars)::
+    panels.timeseries(
+      title       = 'Invite - Invalid JWT during Unregistration',
+      datasource  = ds.prometheus,
+    )
+    .configure(defaults.configuration.timeseries)
+
+    .addTarget(targets.prometheus(
+      datasource  = ds.prometheus,
+      expr        = 'sum(rate(invalid_invite_unregister_jwt{aws_ecs_task_family="%s"}[5m]))' % vars.ecs_task_family,
+      refId       = "sources",
+      exemplar    = true,
+    ))
+}
diff --git a/terraform/monitoring/panels/app/invite/register.libsonnet b/terraform/monitoring/panels/app/invite/register.libsonnet
@@ -0,0 +1,21 @@
+local grafana        = import '../../../grafonnet-lib/grafana.libsonnet';
+local panels         = grafana.panels;
+local targets        = grafana.targets;
+
+local defaults  = import '../../defaults.libsonnet';
+
+{
+  new(ds, vars)::
+    panels.timeseries(
+      title       = 'Invite - Registrations',
+      datasource  = ds.prometheus,
+    )
+    .configure(defaults.configuration.timeseries)
+
+    .addTarget(targets.prometheus(
+      datasource  = ds.prometheus,
+      expr        = 'sum(rate(invite_register{aws_ecs_task_family="%s"}[5m]))' % vars.ecs_task_family,
+      refId       = "sources",
+      exemplar    = true,
+    ))
+}
diff --git a/terraform/monitoring/panels/app/invite/resolved.libsonnet b/terraform/monitoring/panels/app/invite/resolved.libsonnet
@@ -0,0 +1,21 @@
+local grafana        = import '../../../grafonnet-lib/grafana.libsonnet';
+local panels         = grafana.panels;
+local targets        = grafana.targets;
+
+local defaults  = import '../../defaults.libsonnet';
+
+{
+  new(ds, vars)::
+    panels.timeseries(
+      title       = 'Invite - Resolutions',
+      datasource  = ds.prometheus,
+    )
+    .configure(defaults.configuration.timeseries)
+
+    .addTarget(targets.prometheus(
+      datasource  = ds.prometheus,
+      expr        = 'sum(rate(invite_resolved{aws_ecs_task_family="%s"}[5m]))' % vars.ecs_task_family,
+      refId       = "sources",
+      exemplar    = true,
+    ))
+}
diff --git a/terraform/monitoring/panels/app/invite/unregister.libsonnet b/terraform/monitoring/panels/app/invite/unregister.libsonnet
@@ -0,0 +1,21 @@
+local grafana        = import '../../../grafonnet-lib/grafana.libsonnet';
+local panels         = grafana.panels;
+local targets        = grafana.targets;
+
+local defaults  = import '../../defaults.libsonnet';
+
+{
+  new(ds, vars)::
+    panels.timeseries(
+      title       = 'Invite - Unregistrations',
+      datasource  = ds.prometheus,
+    )
+    .configure(defaults.configuration.timeseries)
+
+    .addTarget(targets.prometheus(
+      datasource  = ds.prometheus,
+      expr        = 'sum(rate(invite_unregister{aws_ecs_task_family="%s"}[5m]))' % vars.ecs_task_family,
+      refId       = "sources",
+      exemplar    = true,
+    ))
+}
diff --git a/...aform/monitoring/panels/app/cpu.libsonnet → ...aform/monitoring/panels/ecs/cpu.libsonnet b/...aform/monitoring/panels/app/cpu.libsonnet → ...aform/monitoring/panels/ecs/cpu.libsonnet
diff --git a/...rm/monitoring/panels/app/memory.libsonnet → ...rm/monitoring/panels/ecs/memory.libsonnet b/...rm/monitoring/panels/app/memory.libsonnet → ...rm/monitoring/panels/ecs/memory.libsonnet
diff --git a/terraform/monitoring/panels/panels.libsonnet b/terraform/monitoring/panels/panels.libsonnet
@@ -1,7 +1,24 @@
 {
+  ecs: {
+    cpu: (import 'ecs/cpu.libsonnet').new,
+    memory: (import 'ecs/memory.libsonnet').new,
+  },
+
   app: {
-    cpu: (import 'app/cpu.libsonnet').new,
-    memory: (import 'app/memory.libsonnet').new,
+    invite: {
+      register: (import 'app/invite/register.libsonnet').new,
+      resolved: (import 'app/invite/resolved.libsonnet').new,
+      unregister: (import 'app/invite/unregister.libsonnet').new,
+      invalid_register_jwt: (import 'app/invite/invalid_register_jwt.libsonnet').new,
+      invalid_unregister_jwt: (import 'app/invite/invalid_unregister_jwt.libsonnet').new,
+    },
+    identity: {
+      register: (import 'app/identity/register.libsonnet').new,
+      resolved: (import 'app/identity/resolved.libsonnet').new,
+      unregister: (import 'app/identity/unregister.libsonnet').new,
+      invalid_register_cacao: (import 'app/identity/invalid_register_cacao.libsonnet').new,
+      invalid_unregister_jwt: (import 'app/identity/invalid_unregister_jwt.libsonnet').new,
+    },
   },
 
   lb: {

diff --git a/terraform/monitoring/variables.tf b/terraform/monitoring/variables.tf
@@ -32,3 +32,8 @@ variable "monitoring_role_arn" {
   description = "The ARN of the monitoring role."
   type        = string
 }
+
+variable "ecs_task_family" {
+  description = "The name of the ECS task family."
+  type        = string
+}
diff --git a/terraform/res_monitoring.tf b/terraform/res_monitoring.tf
@@ -9,4 +9,5 @@ module "monitoring" {
   load_balancer_arn     = module.ecs.load_balancer_arn_suffix
   keystore_cluster_id   = module.keystore.cluster_id
   monitoring_role_arn   = data.terraform_remote_state.monitoring.outputs.grafana_workspaces.main.iam_role_arn
+  ecs_task_family       = module.ecs.ecs_task_family
 }