Adding the emr cluster version as a variable (#79)

* Adding the emr cluster version as a variable

Author: hrdamani

aws_datalake/README.md

@@ -54,6 +54,7 @@ mkdir segment-datalakes-tf
       * **Note - Existing users** may be using the `sourceID` here instead of the `workspaceID`, which was the previous configuration. Setting this value as the `sourceID` is still supported for existing users for backwards compatibility. Follow instructions [here](#Using-workspaceID-as-the-externalID) to migrate to `workspaceID`. This will ensure you do not need to update this value for each source you want to add.
     * Update the `name` in the `aws_s3_bucket` resource to the desired name of your S3 bucket
     * Update the `subnet_id` in the `emr` module to the subnet in which to create the EMR cluster
+    * Update the `emr_cluster_version` in the `emr` module to the version that you want to use. We recommend using any 6.x or 7.x versions.
 
 ```hcl
 provider "aws" {
@@ -111,6 +112,7 @@ module "emr" {
 
   s3_bucket = aws_s3_bucket.segment_datalake_s3.id
   subnet_id = "subnet-XXX" # Replace this with the subnet ID you want the EMR cluster to run in.
+  emr_cluster_version = "7.0.0"
 
   # LEAVE THIS AS-IS
   iam_emr_autoscaling_role = module.iam.iam_emr_autoscaling_role

aws_datalake/modules/emr/main.tf

@@ -2,7 +2,7 @@
 # https://www.terraform.io/docs/providers/aws/r/emr_cluster.html
 resource "aws_emr_cluster" "segment_data_lake_emr_cluster" {
   name          = var.cluster_name
-  release_label = "emr-5.33.0"
+  release_label = "emr-${var.emr_cluster_version}"
   applications  = ["Hadoop", "Hive", "Spark"]
 
   log_uri = "s3://${var.s3_bucket}/${var.emr_logs_s3_prefix}"

aws_datalake/modules/emr/variables.tf

@@ -95,6 +95,12 @@ variable "task_instance_max_count" {
   default     = "4"
 }
 
+variable "emr_cluster_version" {
+  description = "Version of emr cluster"
+  type        = string
+  default     = "6.5.0"
+}
+
 locals {
   tags = merge(tomap({"vendor" = "segment"}), var.tags)
 }

aws_datalake/test/test_fixture/aws_main.tf

@@ -31,6 +31,7 @@ module "emr" {
   subnet_id    = "subnet-00f137e4f3a6f8356"
   tags         = local.tags
   cluster_name = "test-cluster"
+  emr_cluster_version = "7.0.0"
 
   # LEAVE THIS AS-IS
   iam_emr_autoscaling_role = module.iam.iam_emr_autoscaling_role