Merge branch 'main' into aman/issue-199

CHANGELOG.md

@@ -2,6 +2,41 @@
 
 All notable changes to this project will be documented in this file.
 
+### [4.12.2](https://github.com/wandb/terraform-aws-wandb/compare/v4.12.1...v4.12.2) (2024-06-17)
+
+
+### Bug Fixes
+
+* Revert resolve conflicts var ([#233](https://github.com/wandb/terraform-aws-wandb/issues/233)) ([778f147](https://github.com/wandb/terraform-aws-wandb/commit/778f147aa9962fde6a74b7d35501ec7dd7abf2a9))
+
+### [4.12.1](https://github.com/wandb/terraform-aws-wandb/compare/v4.12.0...v4.12.1) (2024-06-17)
+
+
+### Bug Fixes
+
+* Remove white space ([#231](https://github.com/wandb/terraform-aws-wandb/issues/231)) ([974b4f3](https://github.com/wandb/terraform-aws-wandb/commit/974b4f3ec0d01b34cf6d83008c9fe2a0d3d8ee7a))
+
+## [4.12.0](https://github.com/wandb/terraform-aws-wandb/compare/v4.11.0...v4.12.0) (2024-06-17)
+
+
+### Features
+
+* Added support yace ([#218](https://github.com/wandb/terraform-aws-wandb/issues/218)) ([12e053d](https://github.com/wandb/terraform-aws-wandb/commit/12e053d520f6998689d3bec0352b320a9105ba9e))
+
+## [4.11.0](https://github.com/wandb/terraform-aws-wandb/compare/v4.10.2...v4.11.0) (2024-05-18)
+
+
+### Features
+
+* Changes to Connect to AWS S3 and KMS using IAM role for EKS service account ([#186](https://github.com/wandb/terraform-aws-wandb/issues/186)) ([a07a45e](https://github.com/wandb/terraform-aws-wandb/commit/a07a45e6d5b979ec2ef8fbb79b63a5d15867da08))
+
+### [4.10.2](https://github.com/wandb/terraform-aws-wandb/compare/v4.10.1...v4.10.2) (2024-05-13)
+
+
+### Bug Fixes
+
+* Amend standard sizes ([#214](https://github.com/wandb/terraform-aws-wandb/issues/214)) ([a1763f9](https://github.com/wandb/terraform-aws-wandb/commit/a1763f93ef507a99e76940fc8c7a0223b5498ff3))
+
 ### [4.10.1](https://github.com/wandb/terraform-aws-wandb/compare/v4.10.0...v4.10.1) (2024-05-08)
 
 

NOTICE

@@ -10,4 +10,6 @@
    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.
+   limitations under the License.
+
+   .

README.md

@@ -102,13 +102,14 @@ resources that lack official modules.
 Users can update the EKS cluster version to the latest version offered by AWS. This can be done using the environment variable `eks_cluster_version`. Note that, cluster and nodegroup version updates can only be done in increments of one version at a time. For example, if your current cluster version is `1.21` and the latest version available is `1.25` - you'd need to:
 
 1. update the cluster version in the app_eks module from `1.21` to `1.22`
-2.  run `terraform apply`
+2. run `terraform apply`
 3. update the cluster version to `1.23`
 4. run `terraform apply`
 5. update the cluster version to `1.24`
-...and so on and so forth.
+   ...and so on and so forth.
 
 Upgrades must be executed in step-wise fashion from one version to the next. You cannot skip versions when upgrading EKS.
+
 <!-- BEGIN_TF_DOCS -->
 
 ### Notes on EKS Add-ons
@@ -252,7 +253,11 @@ CLI and re-run the apply. Running pods will not be impacted.
 
 ## Migrations
 
-#### Upgrading from 3.x -> 4.x
+### Upgrading to Operator
+
+See our upgrade guide [here](./docs/operator-migration/readme.md)
+
+### Upgrading from 3.x -> 4.x
 
 - If egress access for retrieving the wandb/controller image is not available, Terraform apply may experience failures.
 - It's necessary to supply a license variable within the module, as shown:

deployment-size.tf

@@ -7,19 +7,19 @@ locals {
   deployment_size = {
     small = {
       db            = "db.r6g.large",
-      node_count    = 3,
+      node_count    = 2,
       node_instance = "r6i.xlarge"
       cache         = "cache.m6g.large"
     },
     medium = {
       db            = "db.r6g.xlarge",
-      node_count    = 3,
+      node_count    = 2,
       node_instance = "r6i.xlarge"
       cache         = "cache.m6g.large"
     },
     large = {
       db            = "db.r6g.2xlarge",
-      node_count    = 3,
+      node_count    = 2,
       node_instance = "r6i.2xlarge"
       cache         = "cache.m6g.xlarge"
     },

docs/operator-migration/post-operator.tf.disabled

@@ -0,0 +1,113 @@
+provider "aws" {
+  region = "us-west-2"
+
+  default_tags {
+    tags = {
+      GithubRepo = "terraform-aws-wandb"
+      GithubOrg  = "wandb"
+      Enviroment = "Example"
+      Example    = "PublicDnsExternal"
+    }
+  }
+}
+
+terraform {
+  required_version = "~> 1.0"
+  required_providers {
+    aws = {
+      source  = "hashicorp/aws"
+      version = "~> 4.0" # Post-Operator
+    }
+    kubernetes = {
+      source  = "hashicorp/kubernetes"
+      version = "~> 2.23"
+    }
+  }
+}
+
+module "wandb_infra" {
+  source  = "wandb/wandb/aws"
+  version = "4.7.2"
+
+  namespace     = var.namespace
+  public_access = true
+  external_dns  = true
+
+  enable_dummy_dns    = var.enable_dummy_dns    # Post-Operator
+  enable_operator_alb = var.enable_operator_alb # Post-Operator
+  deletion_protection = false
+
+  database_instance_class      = var.database_instance_class
+  database_engine_version      = var.database_engine_version
+  database_snapshot_identifier = var.database_snapshot_identifier
+  database_sort_buffer_size    = var.database_sort_buffer_size
+
+  database_performance_insights_kms_key_arn = null
+
+  allowed_inbound_cidr      = var.allowed_inbound_cidr
+  allowed_inbound_ipv6_cidr = ["::/0"]
+
+  eks_cluster_version            = "1.25"
+  kubernetes_public_access       = true
+  kubernetes_public_access_cidrs = ["0.0.0.0/0"]
+
+  domain_name = var.domain_name
+  zone_id     = var.zone_id
+  subdomain   = var.subdomain
+
+  # Add License Post-Operator
+  license = var.wandb_license
+
+  # Use standard sizing Post-Operator
+  size = var.size
+
+  # Set the External DNS Custom Domain Filter Post-Operator
+  custom_domain_filter = var.custom_domain_filter
+
+  bucket_name        = var.bucket_name
+  bucket_kms_key_arn = var.bucket_kms_key_arn
+  use_internal_queue = true
+
+  aws_loadbalancer_controller_tags = var.aws_loadbalancer_controller_tags
+}
+
+data "aws_eks_cluster" "app_cluster" {
+  name = module.wandb_infra.cluster_id
+}
+
+data "aws_eks_cluster_auth" "app_cluster" {
+  name = module.wandb_infra.cluster_id
+}
+
+provider "kubernetes" {
+  host                   = data.aws_eks_cluster.app_cluster.endpoint
+  cluster_ca_certificate = base64decode(data.aws_eks_cluster.app_cluster.certificate_authority[0].data)
+  token                  = data.aws_eks_cluster_auth.app_cluster.token
+  exec {
+    api_version = "client.authentication.k8s.io/v1beta1"
+    args        = ["eks", "get-token", "--cluster-name", data.aws_eks_cluster.app_cluster.name]
+    command     = "aws"
+  }
+}
+
+# Enable the Helm provider
+provider "helm" {
+  kubernetes {
+    host                   = data.aws_eks_cluster.app_cluster.endpoint
+    cluster_ca_certificate = base64decode(data.aws_eks_cluster.app_cluster.certificate_authority[0].data)
+    token                  = data.aws_eks_cluster_auth.app_cluster.token
+    exec {
+      api_version = "client.authentication.k8s.io/v1beta1"
+      args        = ["eks", "get-token", "--cluster-name", data.aws_eks_cluster.app_cluster.name]
+      command     = "aws"
+    }
+  }
+}
+
+output "bucket_name" {
+  value = module.wandb_infra.bucket_name
+}
+
+output "bucket_queue_name" {
+  value = module.wandb_infra.bucket_queue_name
+}

docs/operator-migration/post-operator.tfvars

@@ -0,0 +1,12 @@
+namespace     = "operator-upgrade"
+domain_name   = "sandbox-aws.wandb.ml"
+zone_id       = "Z032246913CW32RVRY0WU"
+subdomain     = "operator-upgrade"
+wandb_license = "eyJh"
+# wandb_version = "0.51.2" Is now coming from the Release Channel or set in the User Spec.
+
+# Needed Operator Variables for Upgrade
+size                 = "small"
+enable_dummy_dns     = true
+enable_operator_alb  = true
+custom_domain_filter = "sandbox-aws.wandb.ml" 

docs/operator-migration/pre-operator.tf

@@ -0,0 +1,112 @@
+provider "aws" {
+  region = "us-west-2"
+
+  default_tags {
+    tags = {
+      GithubRepo = "terraform-aws-wandb"
+      GithubOrg  = "wandb"
+      Enviroment = "Example"
+      Example    = "PublicDnsExternal"
+    }
+  }
+}
+
+terraform {
+  required_version = "~> 1.0"
+  required_providers {
+    aws = {
+      source  = "hashicorp/aws"
+      version = "~> 3.6" # Pre-Operator
+    }
+    kubernetes = {
+      source  = "hashicorp/kubernetes"
+      version = "~> 2.23"
+    }
+  }
+}
+
+module "wandb_infra" {
+  source  = "wandb/wandb/aws"
+  version = "1.16.10"
+
+  namespace     = var.namespace
+  public_access = true
+  external_dns  = true
+
+  deletion_protection = false
+
+  database_instance_class      = var.database_instance_class
+  database_engine_version      = var.database_engine_version
+  database_snapshot_identifier = var.database_snapshot_identifier
+  database_sort_buffer_size    = var.database_sort_buffer_size
+
+  database_performance_insights_kms_key_arn = null
+
+  allowed_inbound_cidr      = var.allowed_inbound_cidr
+  allowed_inbound_ipv6_cidr = ["::/0"]
+
+  eks_cluster_version            = "1.25"
+  kubernetes_public_access       = true
+  kubernetes_public_access_cidrs = ["0.0.0.0/0"]
+
+  domain_name = var.domain_name
+  zone_id     = var.zone_id
+  subdomain   = var.subdomain
+
+  bucket_name        = var.bucket_name
+  bucket_kms_key_arn = var.bucket_kms_key_arn
+  use_internal_queue = true
+}
+
+data "aws_eks_cluster" "app_cluster" {
+  name = module.wandb_infra.cluster_id
+}
+
+data "aws_eks_cluster_auth" "app_cluster" {
+  name = module.wandb_infra.cluster_id
+}
+
+provider "kubernetes" {
+  host                   = data.aws_eks_cluster.app_cluster.endpoint
+  cluster_ca_certificate = base64decode(data.aws_eks_cluster.app_cluster.certificate_authority[0].data)
+  token                  = data.aws_eks_cluster_auth.app_cluster.token
+  exec {
+    api_version = "client.authentication.k8s.io/v1beta1"
+    args        = ["eks", "get-token", "--cluster-name", data.aws_eks_cluster.app_cluster.name]
+    command     = "aws"
+  }
+}
+
+module "wandb_app" {
+  source  = "wandb/wandb/kubernetes"
+  version = "1.12.0"
+
+  license = var.wandb_license
+
+  host                       = module.wandb_infra.url
+  bucket                     = "s3://${module.wandb_infra.bucket_name}"
+  bucket_aws_region          = module.wandb_infra.bucket_region
+  bucket_queue               = "internal://"
+  bucket_kms_key_arn         = module.wandb_infra.kms_key_arn
+  database_connection_string = "mysql://${module.wandb_infra.database_connection_string}"
+  redis_connection_string    = "redis://${module.wandb_infra.elasticache_connection_string}?tls=true&ttlInSeconds=604800"
+
+  wandb_image   = var.wandb_image
+  wandb_version = var.wandb_version
+
+  service_port = module.wandb_infra.internal_app_port
+
+  depends_on = [module.wandb_infra]
+
+  other_wandb_env = merge({
+    "GORILLA_CUSTOMER_SECRET_STORE_SOURCE" = "aws-secretmanager://${var.namespace}?namespace=${var.namespace}"
+  }, var.other_wandb_env)
+}
+
+output "bucket_name" {
+  value = module.wandb_infra.bucket_name
+}
+
+output "bucket_queue_name" {
+  value = module.wandb_infra.bucket_queue_name
+}

docs/operator-migration/pre-operator.tfvars

@@ -0,0 +1,7 @@
+namespace     = "operator-upgrade"
+domain_name   = "sandbox-aws.wandb.ml"
+zone_id       = "Z032246913CW32RVRY0WU"
+subdomain     = "operator-upgrade"
+wandb_license = "eyJh"
+wandb_version = "0.51.2"
+# size          = "small"