GDB-286 Added monitoring for graphdb

* Added the necessary policy for the cloudwatch-agent
* Modified the user data script to enable the cloudwatch agent and configure it for the current tenant
* Added sample dashboard with a widget that monitors the cpu
* Added editorconfig
* Bumped GraphDB version to 10.4.0-RC8

.editorconfig

@@ -0,0 +1,9 @@
+root = true
+
+[*]
+end_of_line = lf
+charset = utf-8
+trim_trailing_whitespace = true
+insert_final_newline = true
+indent_style = space
+indent_size = 2

examples/vpc-with-multiple-az/main.tf

@@ -28,3 +28,10 @@ module "graphdb" {
   ami_id          = var.ami_id
   graphdb_version = var.graphdb_version
 }
+
+module "monitoring" {
+  source = "./monitoring"
+
+  aws_region           = var.aws_region
+  resource_name_prefix = var.resource_name_prefix
+}

examples/vpc-with-multiple-az/monitoring/README.md

@@ -0,0 +1,3 @@
+# GraphDB AWS Monitoring Module
+
+This module adds metrics scraping from GraphDB cluster to Cloudwatch.

examples/vpc-with-multiple-az/monitoring/main.tf

@@ -0,0 +1,33 @@
+resource "aws_cloudwatch_dashboard" "main" {
+  dashboard_name = "${var.resource_name_prefix}-dashboard"
+
+  dashboard_body = jsonencode({
+    widgets = [
+      {
+        "height" : 6,
+        "width" : 6,
+        "y" : 0,
+        "x" : 0,
+        "type" : "metric",
+        "properties" : {
+          "metrics" : [
+            [
+              {
+                "expression" : "SELECT AVG(graphdb_cpu_load) FROM \"${var.resource_name_prefix}-graphdb\" GROUP BY host",
+                "id" : "q1",
+                "label" : "CPU",
+                "region" : var.aws_region,
+                "stat" : "Average"
+              }
+            ]
+          ],
+          "region" : var.aws_region,
+          "stacked" : false,
+          "view" : "timeSeries",
+          "period" : 300,
+          "stat" : "Average"
+        }
+      }
+    ]
+  })
+}

examples/vpc-with-multiple-az/monitoring/variables.tf

@@ -0,0 +1,9 @@
+variable "resource_name_prefix" {
+  description = "Resource name prefix used for tagging and naming AWS resources"
+  type        = string
+}
+
+variable "aws_region" {
+  description = "AWS region where GraphDB is being deployed"
+  type        = string
+}

examples/vpc-with-multiple-az/monitoring/versions.tf

@@ -0,0 +1,10 @@
+terraform {
+  required_version = ">= 1.4.0"
+
+  required_providers {
+    aws = {
+      source  = "hashicorp/aws"
+      version = "~> 5.15"
+    }
+  }
+}

modules/iam/main.tf

@@ -3,6 +3,11 @@ resource "aws_iam_instance_profile" "graphdb" {
   role        = var.user_supplied_iam_role_name != null ? var.user_supplied_iam_role_name : aws_iam_role.graphdb[0].name
 }
 
+resource "aws_iam_role_policy_attachment" "cloudwatch-agent-policy" {
+  role       = aws_iam_role.graphdb[0].id
+  policy_arn = "arn:aws:iam::aws:policy/CloudWatchAgentServerPolicy"
+}
+
 resource "aws_iam_role" "graphdb" {
   count                = var.user_supplied_iam_role_name != null ? 0 : 1
   name_prefix          = "${var.resource_name_prefix}-graphdb-"

modules/user_data/main.tf

@@ -27,6 +27,7 @@ locals {
       zone_id       = var.zone_id
 
       jvm_max_memory = local.jvm_max_memory
+      resource_name_prefix = var.resource_name_prefix
     }
   )
 }

modules/user_data/templates/start_graphdb.sh.tpl

@@ -231,6 +231,14 @@ echo 'fs.file-max = 262144' | tee -a /etc/sysctl.conf
 
 sysctl -p
 
+tmp=$(mktemp)
+jq '.logs.metrics_collected.prometheus.log_group_name = "${resource_name_prefix}-graphdb"' /etc/graphdb/cloudwatch-agent-config.json > "$tmp" && mv "$tmp" /etc/graphdb/cloudwatch-agent-config.json
+jq '.logs.metrics_collected.prometheus.emf_processor.metric_namespace = "${resource_name_prefix}-graphdb"' /etc/graphdb/cloudwatch-agent-config.json > "$tmp" && mv "$tmp" /etc/graphdb/cloudwatch-agent-config.json
+cat /etc/prometheus/prometheus.yaml | yq '.scrape_configs[].static_configs[].targets = ["localhost:7201"]' > "$tmp" && mv "$tmp" /etc/prometheus/prometheus.yaml
+
+amazon-cloudwatch-agent-ctl -a start
+amazon-cloudwatch-agent-ctl -a fetch-config -m ec2 -s -c file:/etc/graphdb/cloudwatch-agent-config.json
+
 # the proxy service is set up in the AMI but not enabled there, so we enable and start it
 systemctl daemon-reload
 systemctl start graphdb

variables.tf

@@ -121,7 +121,7 @@ variable "ami_id" {
 variable "graphdb_version" {
   description = "GraphDB version"
   type        = string
-  default     = "10.4.0-RC5"
+  default     = "10.4.0-RC8"
   nullable    = false
 }