├── main.tf ├── variables.tf ├── iam.tf ├── .gitignore ├── gce.tf ├── project.tf ├── README.md ├── bq-dm.tf ├── bq-dwh.tf ├── gcs.tf └── LICENSE /main.tf: -------------------------------------------------------------------------------- 1 | provider "google" { 2 | } 3 | -------------------------------------------------------------------------------- /variables.tf: -------------------------------------------------------------------------------- 1 | locals { 2 | region = "asia-southeast1" 3 | unique_id = "cloud-iac" 4 | billing_id = "" 5 | } -------------------------------------------------------------------------------- /iam.tf: -------------------------------------------------------------------------------- 1 | # Sample IAM permission 2 | module "project_iam_binding" { 3 | source = "terraform-google-modules/iam/google//modules/projects_iam/" 4 | projects = [google_project.data-lake.project_id] 5 | mode = "additive" 6 | bindings = { 7 | # Bigquery 8 | "roles/bigquery.admin" = ["user:${local.unique_id}-de@gmail.com"] 9 | # GCS 10 | "roles/storage.admin" = ["user:${local.unique_id}-de@gmail.com"] 11 | # Compute 12 | "roles/compute.admin" = ["user:${local.unique_id}-de@gmail.com"] 13 | } 14 | } -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | # Local .terraform directories 2 | **/.terraform/* 3 | 4 | # .tfstate files 5 | *.tfstate 6 | *.tfstate.* 7 | 8 | # Crash log files 9 | crash.log 10 | 11 | # Ignore any .tfvars files that are generated automatically for each Terraform run. Most 12 | # .tfvars files are managed as part of configuration and so should be included in 13 | # version control. 14 | # 15 | # example.tfvars 16 | 17 | # Ignore override files as they are usually used to override resources locally and so 18 | # are not checked in 19 | override.tf 20 | override.tf.json 21 | *_override.tf 22 | *_override.tf.json 23 | 24 | # Include override files you do wish to add to version control using negated pattern 25 | # 26 | # !example_override.tf 27 | 28 | # Include tfplan files to ignore the plan output of command: terraform plan -out=tfplan 29 | # example: *tfplan* 30 | -------------------------------------------------------------------------------- /gce.tf: -------------------------------------------------------------------------------- 1 | # Create VPC network 2 | resource "google_compute_network" "vpc-network" { 3 | project = google_project.data-lake.project_id 4 | name = "vpc-network" 5 | depends_on = [google_project_service.data-lake-service] 6 | } 7 | 8 | # Create static external IP address 9 | resource "google_compute_address" "orchestration-ip-static" { 10 | project = google_project.data-lake.project_id 11 | region = local.region 12 | name = "${local.unique_id}-external-ip" 13 | depends_on = [google_project_service.data-lake-service] 14 | } 15 | 16 | # Create orchestration instance 17 | resource "google_compute_instance" "orchestration" { 18 | project = google_project.data-lake.project_id 19 | zone = "${local.region}-a" 20 | name = "orchestration" 21 | machine_type = "e2-micro" 22 | 23 | boot_disk { 24 | initialize_params { 25 | image = "ubuntu-2004-focal-v20200701" 26 | } 27 | } 28 | network_interface { 29 | network = google_compute_network.vpc-network.name 30 | access_config { 31 | nat_ip = google_compute_address.orchestration-ip-static.address 32 | } 33 | } 34 | depends_on = [google_project_service.data-lake-service, google_compute_address.orchestration-ip-static, google_compute_network.vpc-network] 35 | } 36 | 37 | -------------------------------------------------------------------------------- /project.tf: -------------------------------------------------------------------------------- 1 | # Project definition 2 | resource "google_project" "data-lake" { 3 | name = "Data Lake" 4 | project_id = "${local.unique_id}-data-lake" 5 | billing_account = local.billing_id 6 | } 7 | 8 | resource "google_project" "data-warehouse" { 9 | name = "Data Warehouse" 10 | project_id = "${local.unique_id}-data-warehouse" 11 | billing_account = local.billing_id 12 | } 13 | 14 | resource "google_project" "data-marts" { 15 | name = "Data Marts" 16 | project_id = "${local.unique_id}-data-marts" 17 | billing_account = local.billing_id 18 | } 19 | 20 | # Enable APIs in projects 21 | resource "google_project_service" "data-lake-service" { 22 | for_each = toset([ 23 | "compute.googleapis.com", 24 | "bigquery.googleapis.com" 25 | ]) 26 | service = each.key 27 | project = google_project.data-lake.project_id 28 | disable_on_destroy = false 29 | } 30 | 31 | resource "google_project_service" "data-warehouse-service" { 32 | for_each = toset([ 33 | "bigquery.googleapis.com" 34 | ]) 35 | service = each.key 36 | project = google_project.data-warehouse.project_id 37 | disable_on_destroy = false 38 | } 39 | 40 | resource "google_project_service" "data-marts-service" { 41 | for_each = toset([ 42 | "bigquery.googleapis.com" 43 | ]) 44 | service = each.key 45 | project = google_project.data-marts.project_id 46 | disable_on_destroy = false 47 | } 48 | 49 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Data lake on GCP using Terraform 2 | Use Terraform to set up infrastructure-as-code for a Data Lake on Google Cloud Platform. 3 | ## Before we start 4 | You will need to do the following for this project: 5 | * Download and setup Terraform CLI: Use this getting started guide to install terraform CLI on your local machine. 6 | * Create a Google Cloud account: Sign up for a Google Cloud account, if you haven't already. You will get $300 credit when signing up, more than enough to get you through this tutorial without spending a dollar. 7 | * Get your billing ID: Follow the guide here to find out your billing ID on GCP. You will need it for later use. 8 | * Install gcloud CLI: Use this link to help you install gcloud CLI locally. 9 | 10 | ## Getting started with IaC using Terraform on GCP 11 | ### Clone the project 12 | Clone the project locally by running: 13 | ``` 14 | git clone https://github.com/tuanchris/data-lake-iac.git 15 | cd data-lake-iac 16 | ``` 17 | Or you can fork the project to your account. 18 | ### Authenticate with GCP 19 | First, authenticate with GCP. Paste the following command to a terminal and follow the instructions. 20 | ``` 21 | gcloud auth application-default login 22 | ``` 23 | ### Init project 24 | Run the following to init our project 25 | ``` 26 | terraform init 27 | ``` 28 | ### Change the parameters on Variables.tf 29 | Change the parameters in this file. Refer back to my [article](https://towardsdatascience.com/data-lake-on-gcp-using-terraform-469062a205ad) and the code for what the parameter is used for. 30 | 31 | ### Create the infrastructure 32 | Run the following to create the infrastructure 33 | ``` 34 | terraform apply 35 | ``` 36 | ### Customize IAM permissions 37 | Customize permissions in the `bq-dwh.tf`, `bq-dm.tf`, `gcs.tf`, and `iam.tf` to your specifications. 38 | ### Clean up 39 | Clean up the resources by running 40 | ``` 41 | terraform destroy 42 | ``` 43 | 44 | Any feedback is welcome :) 45 | -------------------------------------------------------------------------------- /bq-dm.tf: -------------------------------------------------------------------------------- 1 | # Data warehouse 2 | resource "google_bigquery_dataset" "dwh-bq-marketing" { 3 | dataset_id = "MARKETING" 4 | description = "" 5 | project = google_project.data-marts.project_id 6 | location = local.region 7 | depends_on = [google_project_service.data-marts-service] 8 | # Order of access matters 9 | # WRITER -> OWNER -> READER 10 | # access { 11 | # role = "WRITER" 12 | # group_by_email = "${local.unique_id}-ds@gmail.com" 13 | # } 14 | # access { 15 | # role = "OWNER" 16 | # group_by_email = "${local.unique_id}-de@gmail.com" 17 | # } 18 | # access { 19 | # role = "READER" 20 | # group_by_email = "${local.unique_id}-da@gmail.com" 21 | # } 22 | } 23 | 24 | resource "google_bigquery_dataset" "dwh-bq-finance" { 25 | dataset_id = "FINANCE" 26 | description = "" 27 | project = google_project.data-marts.project_id 28 | location = local.region 29 | depends_on = [google_project_service.data-marts-service] 30 | # access { 31 | # role = "WRITER" 32 | # group_by_email = "${local.unique_id}-ds@gmail.com" 33 | # } 34 | # access { 35 | # role = "OWNER" 36 | # group_by_email = "${local.unique_id}-de@gmail.com" 37 | # } 38 | # access { 39 | # role = "READER" 40 | # group_by_email = "${local.unique_id}-da@gmail.com" 41 | # } 42 | } 43 | 44 | resource "google_bigquery_dataset" "dwh-bq-sales" { 45 | dataset_id = "SALES" 46 | description = "" 47 | project = google_project.data-marts.project_id 48 | location = local.region 49 | depends_on = [google_project_service.data-marts-service] 50 | # access { 51 | # role = "WRITER" 52 | # group_by_email = "${local.unique_id}-ds@gmail.com" 53 | # } 54 | # access { 55 | # role = "OWNER" 56 | # group_by_email = "${local.unique_id}-de@gmail.com" 57 | # } 58 | # access { 59 | # role = "READER" 60 | # group_by_email = "${local.unique_id}-da@gmail.com" 61 | # } 62 | } -------------------------------------------------------------------------------- /bq-dwh.tf: -------------------------------------------------------------------------------- 1 | # Data warehouse 2 | resource "google_bigquery_dataset" "dwh-bq-system1" { 3 | dataset_id = "SYSTEM1" 4 | description = "" 5 | project = google_project.data-warehouse.project_id 6 | location = local.region 7 | depends_on = [google_project_service.data-warehouse-service] 8 | # Order of access matters 9 | # WRITER -> OWNER -> READER 10 | # access { 11 | # role = "WRITER" 12 | # group_by_email = "${local.unique_id}-ds@gmail.com" 13 | # } 14 | # access { 15 | # role = "OWNER" 16 | # group_by_email = "${local.unique_id}-de@gmail.com" 17 | # } 18 | # access { 19 | # role = "READER" 20 | # group_by_email = "${local.unique_id}-da@gmail.com" 21 | # } 22 | } 23 | 24 | resource "google_bigquery_dataset" "dwh-bq-system2" { 25 | dataset_id = "SYSTEM2" 26 | description = "" 27 | project = google_project.data-warehouse.project_id 28 | location = local.region 29 | depends_on = [google_project_service.data-warehouse-service] 30 | # access { 31 | # role = "WRITER" 32 | # group_by_email = "${local.unique_id}-ds@gmail.com" 33 | # } 34 | # access { 35 | # role = "OWNER" 36 | # group_by_email = "${local.unique_id}-de@gmail.com" 37 | # } 38 | # access { 39 | # role = "READER" 40 | # group_by_email = "${local.unique_id}-da@gmail.com" 41 | # } 42 | } 43 | 44 | resource "google_bigquery_dataset" "dwh-bq-system3" { 45 | dataset_id = "SYSTEM3" 46 | description = "" 47 | project = google_project.data-warehouse.project_id 48 | location = local.region 49 | depends_on = [google_project_service.data-warehouse-service] 50 | # access { 51 | # role = "WRITER" 52 | # group_by_email = "${local.unique_id}-ds@gmail.com" 53 | # } 54 | # access { 55 | # role = "OWNER" 56 | # group_by_email = "${local.unique_id}-de@gmail.com" 57 | # } 58 | # access { 59 | # role = "READER" 60 | # group_by_email = "${local.unique_id}-da@gmail.com" 61 | # } 62 | } -------------------------------------------------------------------------------- /gcs.tf: -------------------------------------------------------------------------------- 1 | # GCS resources 2 | resource "google_storage_bucket" "gcs-data-lake-landing" { 3 | name = "${google_project.data-lake.project_id}-landing" 4 | project = google_project.data-lake.project_id 5 | location = local.region 6 | force_destroy = true 7 | storage_class = "STANDARD" 8 | } 9 | 10 | resource "google_storage_bucket" "gcs-data-lake-sensitive" { 11 | name = "${google_project.data-lake.project_id}-sensitive" 12 | project = google_project.data-lake.project_id 13 | location = local.region 14 | force_destroy = true 15 | storage_class = "STANDARD" 16 | } 17 | 18 | resource "google_storage_bucket" "gcs-data-lake-work" { 19 | name = "${google_project.data-lake.project_id}-work" 20 | project = google_project.data-lake.project_id 21 | location = local.region 22 | force_destroy = true 23 | storage_class = "STANDARD" 24 | } 25 | 26 | resource "google_storage_bucket" "gcs-data-lake-backup" { 27 | name = "${google_project.data-lake.project_id}-backup" 28 | project = google_project.data-lake.project_id 29 | location = local.region 30 | force_destroy = true 31 | storage_class = "STANDARD" 32 | } 33 | 34 | # ACL configs 35 | # resource "google_storage_bucket_acl" "gcs-data-lake-landing-acl" { 36 | # bucket = google_storage_bucket.gcs-data-lake-landing.name 37 | # role_entity = [ 38 | # # Leave the user prefix. Chane to other when necessary 39 | # "OWNER:user-${local.unique_id}-de@gmail.com", 40 | # "READER:${local.unique_id}-ds@gmail.com", 41 | # ] 42 | # } 43 | 44 | # resource "google_storage_bucket_acl" "gcs-data-lake-sensitive-acl" { 45 | # bucket = google_storage_bucket.gcs-data-lake-sensitive.name 46 | # role_entity = [ 47 | # "OWNER:user-${local.unique_id}-de@gmail.com", 48 | # "READER:${local.unique_id}-ds@gmail.com", 49 | # ] 50 | # } 51 | 52 | # resource "google_storage_bucket_acl" "gcs-data-lake-work-acl" { 53 | # bucket = google_storage_bucket.gcs-data-lake-work.name 54 | # role_entity = [ 55 | # "OWNER:user-${local.unique_id}-de@gmail.com", 56 | # "WRITER:${local.unique_id}-ds@gmail.com", 57 | # ] 58 | # } 59 | 60 | # resource "google_storage_bucket_acl" "gcs-data-lake-backup-acl" { 61 | # bucket = google_storage_bucket.gcs-data-lake-backup.name 62 | # role_entity = [ 63 | # "OWNER:user-${local.unique_id}-de@gmail.com", 64 | # "READER:${local.unique_id}-ds@gmail.com", 65 | # ] 66 | # } -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | --------------------------------------------------------------------------------