Release/0.2.0

CHANGELOG

@@ -1,3 +1,7 @@
+Version 0.2.0 (2024-02-05)
+--------------------------
+Update LICENSE to SLULA (#9)
+
 Version 0.1.3 (2024-01-16)
 --------------------------
 Bump service module to 0.2.1 (#7)

README.md

@@ -53,6 +53,8 @@ resource "aws_sqs_queue" "db_message_queue" {
 module "transformer_wrp" {
   source  = "snowplow-devops/transformer-kinesis-ec2/aws"
 
+  accept_limited_use_license = true
+
   name       = "transformer-server-wrp"
   vpc_id     = var.vpc_id
   subnet_ids = var.subnet_ids
@@ -84,6 +86,8 @@ module "transformer_wrp" {
 module "db_loader" {
   source = "snowplow-devops/databricks-loader-ec2/aws"
 
+  accept_limited_use_license = true
+
   name       = "db-loader-server"
   vpc_id     = var.vpc_id
   subnet_ids = var.subnet_ids
@@ -133,7 +137,7 @@ module "db_loader" {
 |------|--------|---------|
 | <a name="module_instance_type_metrics"></a> [instance\_type\_metrics](#module\_instance\_type\_metrics) | snowplow-devops/ec2-instance-type-metrics/aws | 0.1.2 |
 | <a name="module_service"></a> [service](#module\_service) | snowplow-devops/service-ec2/aws | 0.2.1 |
-| <a name="module_telemetry"></a> [telemetry](#module\_telemetry) | snowplow-devops/telemetry/snowplow | 0.4.0 |
+| <a name="module_telemetry"></a> [telemetry](#module\_telemetry) | snowplow-devops/telemetry/snowplow | 0.5.0 |
 
 ## Resources
 
@@ -172,10 +176,13 @@ module "db_loader" {
 | <a name="input_ssh_key_name"></a> [ssh\_key\_name](#input\_ssh\_key\_name) | The name of the SSH key-pair to attach to all EC2 nodes deployed | `string` | n/a | yes |
 | <a name="input_subnet_ids"></a> [subnet\_ids](#input\_subnet\_ids) | The list of subnets to deploy Loader across | `list(string)` | n/a | yes |
 | <a name="input_vpc_id"></a> [vpc\_id](#input\_vpc\_id) | The VPC to deploy Loader within | `string` | n/a | yes |
+| <a name="input_accept_limited_use_license"></a> [accept\_limited\_use\_license](#input\_accept\_limited\_use\_license) | Acceptance of the SLULA terms (https://docs.snowplow.io/limited-use-license-1.0/) | `bool` | `false` | no |
 | <a name="input_amazon_linux_2_ami_id"></a> [amazon\_linux\_2\_ami\_id](#input\_amazon\_linux\_2\_ami\_id) | The AMI ID to use which must be based of of Amazon Linux 2; by default the latest community version is used | `string` | `""` | no |
+| <a name="input_app_version"></a> [app\_version](#input\_app\_version) | Version of rdb loader databricks | `string` | `"5.6.0"` | no |
 | <a name="input_associate_public_ip_address"></a> [associate\_public\_ip\_address](#input\_associate\_public\_ip\_address) | Whether to assign a public ip address to this instance | `bool` | `true` | no |
 | <a name="input_cloudwatch_logs_enabled"></a> [cloudwatch\_logs\_enabled](#input\_cloudwatch\_logs\_enabled) | Whether application logs should be reported to CloudWatch | `bool` | `true` | no |
 | <a name="input_cloudwatch_logs_retention_days"></a> [cloudwatch\_logs\_retention\_days](#input\_cloudwatch\_logs\_retention\_days) | The length of time in days to retain logs for | `number` | `7` | no |
+| <a name="input_config_override_b64"></a> [config\_override\_b64](#input\_config\_override\_b64) | App config uploaded as a base64 encoded blob. This variable facilitates dev flow, if config is incorrect this can break the deployment. | `string` | `""` | no |
 | <a name="input_custom_iglu_resolvers"></a> [custom\_iglu\_resolvers](#input\_custom\_iglu\_resolvers) | The custom Iglu Resolvers that will be used by Stream Shredder | <pre>list(object({<br>    name            = string<br>    priority        = number<br>    uri             = string<br>    api_key         = string<br>    vendor_prefixes = list(string)<br>  }))</pre> | `[]` | no |
 | <a name="input_databricks_aws_s3_folder_monitoring_stage_url"></a> [databricks\_aws\_s3\_folder\_monitoring\_stage\_url](#input\_databricks\_aws\_s3\_folder\_monitoring\_stage\_url) | AWS bucket URL of folder monitoring stage - must be within 'databricks\_aws\_s3\_bucket\_name' (NOTE: must be set if 'folder\_monitoring\_enabled' is true) | `string` | `""` | no |
 | <a name="input_databricks_aws_s3_folder_monitoring_transformer_output_stage_url"></a> [databricks\_aws\_s3\_folder\_monitoring\_transformer\_output\_stage\_url](#input\_databricks\_aws\_s3\_folder\_monitoring\_transformer\_output\_stage\_url) | AWS bucket URL of transformer output stage - must be within 'databricks\_aws\_s3\_bucket\_name'  (NOTE: must be set if 'folder\_monitoring\_enabled' is true) | `string` | `""` | no |
@@ -191,7 +198,7 @@ module "db_loader" {
 | <a name="input_health_check_timeout"></a> [health\_check\_timeout](#input\_health\_check\_timeout) | How long to wait for a response for health check query | `string` | `"1 min"` | no |
 | <a name="input_iam_permissions_boundary"></a> [iam\_permissions\_boundary](#input\_iam\_permissions\_boundary) | The permissions boundary ARN to set on IAM roles created | `string` | `""` | no |
 | <a name="input_instance_type"></a> [instance\_type](#input\_instance\_type) | The instance type to use | `string` | `"t3a.micro"` | no |
-| <a name="input_java_opts"></a> [java\_opts](#input\_java\_opts) | Custom JAVA Options | `string` | `"-Dorg.slf4j.simpleLogger.defaultLogLevel=info -XX:MinRAMPercentage=50 -XX:MaxRAMPercentage=75"` | no |
+| <a name="input_java_opts"></a> [java\_opts](#input\_java\_opts) | Custom JAVA Options | `string` | `"-XX:InitialRAMPercentage=75 -XX:MaxRAMPercentage=75"` | no |
 | <a name="input_retry_period"></a> [retry\_period](#input\_retry\_period) | How often batch of failed folders should be pulled into a discovery queue | `string` | `"10 min"` | no |
 | <a name="input_retry_queue_enabled"></a> [retry\_queue\_enabled](#input\_retry\_queue\_enabled) | Whether retry queue should be enabled or not | `bool` | `false` | no |
 | <a name="input_retry_queue_interval"></a> [retry\_queue\_interval](#input\_retry\_queue\_interval) | Artificial pause after each failed folder being added to the queue | `string` | `"10 min"` | no |
@@ -223,16 +230,9 @@ module "db_loader" {
 
 # Copyright and license
 
-The Terraform AWS Databricks Loader on EC2 project is Copyright 2023-2023 Snowplow Analytics Ltd.
-
-Licensed under the [Apache License, Version 2.0][license] (the "License");
-you may not use this software except in compliance with the License.
+Copyright 2023-current Snowplow Analytics Ltd.
 
-Unless required by applicable law or agreed to in writing, software
-distributed under the License is distributed on an "AS IS" BASIS,
-WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-See the License for the specific language governing permissions and
-limitations under the License.
+Licensed under the [Snowplow Limited Use License Agreement][license]. _(If you are uncertain how it applies to your use case, check our answers to [frequently asked questions][license-faq].)_
 
 [duration-doc]: https://github.com/lightbend/config/blob/main/HOCON.md#duration-format
 
@@ -242,8 +242,9 @@ limitations under the License.
 [ci]: https://github.com/snowplow-devops/terraform-aws-databricks-loader-ec2/actions?query=workflow%3Aci
 [ci-image]: https://github.com/snowplow-devops/terraform-aws-databricks-loader-ec2/workflows/ci/badge.svg
 
-[license]: https://www.apache.org/licenses/LICENSE-2.0
-[license-image]: https://img.shields.io/badge/license-Apache--2-blue.svg?style=flat
+[license]: https://docs.snowplow.io/limited-use-license-1.0/
+[license-image]: https://img.shields.io/badge/license-Snowplow--Limited--Use-blue.svg?style=flat
+[license-faq]: https://docs.snowplow.io/docs/contributing/limited-use-license-faq/
 
 [registry]: https://registry.terraform.io/modules/snowplow-devops/databricks-loader-ec2/aws/latest
 [registry-image]: https://img.shields.io/static/v1?label=Terraform&message=Registry&color=7B42BC&logo=terraform

main.tf

@@ -1,9 +1,9 @@
 locals {
   module_name    = "databricks-loader-ec2"
-  module_version = "0.1.3"
+  module_version = "0.2.0"
 
   app_name    = "rdb-loader-databricks"
-  app_version = "5.6.0"
+  app_version = var.app_version
 
   local_tags = {
     Name           = var.name
@@ -26,7 +26,7 @@ data "aws_caller_identity" "current" {}
 
 module "telemetry" {
   source  = "snowplow-devops/telemetry/snowplow"
-  version = "0.4.0"
+  version = "0.5.0"
 
   count = var.telemetry_enabled ? 1 : 0
 
@@ -365,7 +365,9 @@ locals {
   })
 
   user_data = templatefile("${path.module}/templates/user-data.sh.tmpl", {
-    config_b64        = base64encode(local.config)
+    accept_limited_use_license = var.accept_limited_use_license
+
+    config_b64        = var.config_override_b64 == "" ? base64encode(local.config) : var.config_override_b64
     iglu_resolver_b64 = base64encode(local.iglu_resolver)
     version           = local.app_version
 

templates/config.json.tmpl

@@ -169,5 +169,6 @@
     "autoGeneratedId": "${telemetry_auto_gen_id}"
     "moduleName": "${telemetry_module_name}"
     "moduleVersion": "${telemetry_module_version}"
+    "instanceId": $${INSTANCE_ID}
   }
 }

templates/user-data.sh.tmpl

@@ -13,8 +13,9 @@ sudo docker run \
   --log-opt max-size=10m \
   --log-opt max-file=5 \
 %{ endif ~}
-  -e 'JAVA_OPTS=-Dconfig.override_with_env_vars=true ${java_opts}' \
-  -e "CONFIG_FORCE_telemetry_instanceId=$(get_instance_id)" \
+  --env JDK_JAVA_OPTIONS='${java_opts}' \
+  --env ACCEPT_LIMITED_USE_LICENSE=${accept_limited_use_license} \
+  --env INSTANCE_ID=$(get_instance_id) \
   snowplow/rdb-loader-databricks:${version} \
   --config ${config_b64} \
   --iglu-config ${iglu_resolver_b64}

variables.tf

@@ -1,8 +1,31 @@
+variable "accept_limited_use_license" {
+  description = "Acceptance of the SLULA terms (https://docs.snowplow.io/limited-use-license-1.0/)"
+  type        = bool
+  default     = false
+
+  validation {
+    condition     = var.accept_limited_use_license
+    error_message = "Please accept the terms of the Snowplow Limited Use License Agreement to proceed."
+  }
+}
+
 variable "name" {
   description = "A name which will be prepended to the resources created"
   type        = string
 }
 
+variable "app_version" {
+  description = "Version of rdb loader databricks"
+  type        = string
+  default     = "5.6.0"
+}
+
+variable "config_override_b64" {
+  description = "App config uploaded as a base64 encoded blob. This variable facilitates dev flow, if config is incorrect this can break the deployment."
+  type        = string
+  default     = ""
+}
+
 variable "iam_permissions_boundary" {
   description = "The permissions boundary ARN to set on IAM roles created"
   default     = ""
@@ -68,7 +91,7 @@ variable "cloudwatch_logs_retention_days" {
 
 variable "java_opts" {
   description = "Custom JAVA Options"
-  default     = "-Dorg.slf4j.simpleLogger.defaultLogLevel=info -XX:MinRAMPercentage=50 -XX:MaxRAMPercentage=75"
+  default     = "-XX:InitialRAMPercentage=75 -XX:MaxRAMPercentage=75"
   type        = string
 }