├── .gitignore ├── LICENSE ├── README.md ├── config.tf ├── main.tf ├── modules ├── emr │ ├── main.tf │ ├── outputs.tf │ └── variables.tf ├── iam │ ├── main.tf │ └── outputs.tf ├── s3 │ ├── main.tf │ └── variables.tf └── security │ ├── main.tf │ ├── outputs.tf │ └── variables.tf ├── outputs.tf ├── scripts ├── bootstrap_actions.sh └── pyspark_quick_setup.sh ├── terraform.tfvars └── variables.tf /.gitignore: -------------------------------------------------------------------------------- 1 | 2 | # Created by https://www.gitignore.io/api/terraform 3 | # Edit at https://www.gitignore.io/?templates=terraform 4 | 5 | ### Terraform ### 6 | # Local .terraform directories 7 | **/.terraform/* 8 | 9 | # .tfstate files 10 | *.tfstate 11 | *.tfstate.* 12 | 13 | # Crash log files 14 | crash.log 15 | 16 | # Ignore any .tfvars files that are generated automatically for each Terraform run. Most 17 | # .tfvars files are managed as part of configuration and so should be included in 18 | # version control. 19 | # 20 | # example.tfvars 21 | 22 | # Ignore override files as they are usually used to override resources locally and so 23 | # are not checked in 24 | override.tf 25 | override.tf.json 26 | *_override.tf 27 | *_override.tf.json 28 | 29 | # Include override files you do wish to add to version control using negated pattern 30 | # 31 | # !example_override.tf 32 | 33 | # End of https://www.gitignore.io/api/terraform 34 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Copyright 2019 idealo internet GmbH. All rights reserved. 2 | 3 | Apache License 4 | Version 2.0, January 2004 5 | http://www.apache.org/licenses/ 6 | 7 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 8 | 9 | 1. Definitions. 10 | 11 | "License" shall mean the terms and conditions for use, reproduction, 12 | and distribution as defined by Sections 1 through 9 of this document. 13 | 14 | "Licensor" shall mean the copyright owner or entity authorized by 15 | the copyright owner that is granting the License. 16 | 17 | "Legal Entity" shall mean the union of the acting entity and all 18 | other entities that control, are controlled by, or are under common 19 | control with that entity. For the purposes of this definition, 20 | "control" means (i) the power, direct or indirect, to cause the 21 | direction or management of such entity, whether by contract or 22 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 23 | outstanding shares, or (iii) beneficial ownership of such entity. 24 | 25 | "You" (or "Your") shall mean an individual or Legal Entity 26 | exercising permissions granted by this License. 27 | 28 | "Source" form shall mean the preferred form for making modifications, 29 | including but not limited to software source code, documentation 30 | source, and configuration files. 31 | 32 | "Object" form shall mean any form resulting from mechanical 33 | transformation or translation of a Source form, including but 34 | not limited to compiled object code, generated documentation, 35 | and conversions to other media types. 36 | 37 | "Work" shall mean the work of authorship, whether in Source or 38 | Object form, made available under the License, as indicated by a 39 | copyright notice that is included in or attached to the work 40 | (an example is provided in the Appendix below). 41 | 42 | "Derivative Works" shall mean any work, whether in Source or Object 43 | form, that is based on (or derived from) the Work and for which the 44 | editorial revisions, annotations, elaborations, or other modifications 45 | represent, as a whole, an original work of authorship. For the purposes 46 | of this License, Derivative Works shall not include works that remain 47 | separable from, or merely link (or bind by name) to the interfaces of, 48 | the Work and Derivative Works thereof. 49 | 50 | "Contribution" shall mean any work of authorship, including 51 | the original version of the Work and any modifications or additions 52 | to that Work or Derivative Works thereof, that is intentionally 53 | submitted to Licensor for inclusion in the Work by the copyright owner 54 | or by an individual or Legal Entity authorized to submit on behalf of 55 | the copyright owner. For the purposes of this definition, "submitted" 56 | means any form of electronic, verbal, or written communication sent 57 | to the Licensor or its representatives, including but not limited to 58 | communication on electronic mailing lists, source code control systems, 59 | and issue tracking systems that are managed by, or on behalf of, the 60 | Licensor for the purpose of discussing and improving the Work, but 61 | excluding communication that is conspicuously marked or otherwise 62 | designated in writing by the copyright owner as "Not a Contribution." 63 | 64 | "Contributor" shall mean Licensor and any individual or Legal Entity 65 | on behalf of whom a Contribution has been received by Licensor and 66 | subsequently incorporated within the Work. 67 | 68 | 2. Grant of Copyright License. Subject to the terms and conditions of 69 | this License, each Contributor hereby grants to You a perpetual, 70 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 71 | copyright license to reproduce, prepare Derivative Works of, 72 | publicly display, publicly perform, sublicense, and distribute the 73 | Work and such Derivative Works in Source or Object form. 74 | 75 | 3. Grant of Patent License. Subject to the terms and conditions of 76 | this License, each Contributor hereby grants to You a perpetual, 77 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 78 | (except as stated in this section) patent license to make, have made, 79 | use, offer to sell, sell, import, and otherwise transfer the Work, 80 | where such license applies only to those patent claims licensable 81 | by such Contributor that are necessarily infringed by their 82 | Contribution(s) alone or by combination of their Contribution(s) 83 | with the Work to which such Contribution(s) was submitted. If You 84 | institute patent litigation against any entity (including a 85 | cross-claim or counterclaim in a lawsuit) alleging that the Work 86 | or a Contribution incorporated within the Work constitutes direct 87 | or contributory patent infringement, then any patent licenses 88 | granted to You under this License for that Work shall terminate 89 | as of the date such litigation is filed. 90 | 91 | 4. Redistribution. You may reproduce and distribute copies of the 92 | Work or Derivative Works thereof in any medium, with or without 93 | modifications, and in Source or Object form, provided that You 94 | meet the following conditions: 95 | 96 | (a) You must give any other recipients of the Work or 97 | Derivative Works a copy of this License; and 98 | 99 | (b) You must cause any modified files to carry prominent notices 100 | stating that You changed the files; and 101 | 102 | (c) You must retain, in the Source form of any Derivative Works 103 | that You distribute, all copyright, patent, trademark, and 104 | attribution notices from the Source form of the Work, 105 | excluding those notices that do not pertain to any part of 106 | the Derivative Works; and 107 | 108 | (d) If the Work includes a "NOTICE" text file as part of its 109 | distribution, then any Derivative Works that You distribute must 110 | include a readable copy of the attribution notices contained 111 | within such NOTICE file, excluding those notices that do not 112 | pertain to any part of the Derivative Works, in at least one 113 | of the following places: within a NOTICE text file distributed 114 | as part of the Derivative Works; within the Source form or 115 | documentation, if provided along with the Derivative Works; or, 116 | within a display generated by the Derivative Works, if and 117 | wherever such third-party notices normally appear. The contents 118 | of the NOTICE file are for informational purposes only and 119 | do not modify the License. You may add Your own attribution 120 | notices within Derivative Works that You distribute, alongside 121 | or as an addendum to the NOTICE text from the Work, provided 122 | that such additional attribution notices cannot be construed 123 | as modifying the License. 124 | 125 | You may add Your own copyright statement to Your modifications and 126 | may provide additional or different license terms and conditions 127 | for use, reproduction, or distribution of Your modifications, or 128 | for any such Derivative Works as a whole, provided Your use, 129 | reproduction, and distribution of the Work otherwise complies with 130 | the conditions stated in this License. 131 | 132 | 5. Submission of Contributions. Unless You explicitly state otherwise, 133 | any Contribution intentionally submitted for inclusion in the Work 134 | by You to the Licensor shall be under the terms and conditions of 135 | this License, without any additional terms or conditions. 136 | Notwithstanding the above, nothing herein shall supersede or modify 137 | the terms of any separate license agreement you may have executed 138 | with Licensor regarding such Contributions. 139 | 140 | 6. Trademarks. This License does not grant permission to use the trade 141 | names, trademarks, service marks, or product names of the Licensor, 142 | except as required for reasonable and customary use in describing the 143 | origin of the Work and reproducing the content of the NOTICE file. 144 | 145 | 7. Disclaimer of Warranty. Unless required by applicable law or 146 | agreed to in writing, Licensor provides the Work (and each 147 | Contributor provides its Contributions) on an "AS IS" BASIS, 148 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 149 | implied, including, without limitation, any warranties or conditions 150 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 151 | PARTICULAR PURPOSE. You are solely responsible for determining the 152 | appropriateness of using or redistributing the Work and assume any 153 | risks associated with Your exercise of permissions under this License. 154 | 155 | 8. Limitation of Liability. In no event and under no legal theory, 156 | whether in tort (including negligence), contract, or otherwise, 157 | unless required by applicable law (such as deliberate and grossly 158 | negligent acts) or agreed to in writing, shall any Contributor be 159 | liable to You for damages, including any direct, indirect, special, 160 | incidental, or consequential damages of any character arising as a 161 | result of this License or out of the use or inability to use the 162 | Work (including but not limited to damages for loss of goodwill, 163 | work stoppage, computer failure or malfunction, or any and all 164 | other commercial damages or losses), even if such Contributor 165 | has been advised of the possibility of such damages. 166 | 167 | 9. Accepting Warranty or Additional Liability. While redistributing 168 | the Work or Derivative Works thereof, You may choose to offer, 169 | and charge a fee for, acceptance of support, warranty, indemnity, 170 | or other liability obligations and/or rights consistent with this 171 | License. However, in accepting such obligations, You may act only 172 | on Your own behalf and on Your sole responsibility, not on behalf 173 | of any other Contributor, and only if You agree to indemnify, 174 | defend, and hold each Contributor harmless for any liability 175 | incurred by, or claims asserted against, such Contributor by reason 176 | of your accepting any such warranty or additional liability. 177 | 178 | END OF TERMS AND CONDITIONS 179 | 180 | APPENDIX: How to apply the Apache License to your work. 181 | 182 | To apply the Apache License to your work, attach the following 183 | boilerplate notice, with the fields enclosed by brackets "[]" 184 | replaced with your own identifying information. (Don't include 185 | the brackets!) The text should be enclosed in the appropriate 186 | comment syntax for the file format. We also recommend that a 187 | file or class name and description of purpose be included on the 188 | same "printed page" as the copyright notice for easier 189 | identification within third-party archives. 190 | 191 | Copyright [yyyy] [name of copyright owner] 192 | 193 | Licensed under the Apache License, Version 2.0 (the "License"); 194 | you may not use this file except in compliance with the License. 195 | You may obtain a copy of the License at 196 | 197 | http://www.apache.org/licenses/LICENSE-2.0 198 | 199 | Unless required by applicable law or agreed to in writing, software 200 | distributed under the License is distributed on an "AS IS" BASIS, 201 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 202 | See the License for the specific language governing permissions and 203 | limitations under the License. 204 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Terraform + EMR Bootstrap PySpark with Anaconda 2 | 3 | This code should help to jump start PySpark with Anaconda on AWS using Terraform. 4 | 5 | This project is no longer actively maintained and has been archived on Jan 7, 2025. 6 | 7 | ## Getting Started 8 | 1. Install Terraform on Mac: `brew install terraform` 9 | 2. Adjust the scripts (`bootstrap_actions.sh` and `pyspark_quick_setup.sh`) in `scripts` if necessary 10 | 3. Set parameters in `terraform.tfvars` 11 | 4. Start cluster: 12 | ``` 13 | terraform init 14 | terraform apply 15 | ``` 16 | 5. Destroy cluster: 17 | ``` 18 | terraform destroy 19 | ``` 20 | 21 | ### Notes 22 | * Configure AWS on your local machine: `aws configure` 23 | * [AWS instance cost](https://aws.amazon.com/emr/pricing/) for `eu-central-1` 24 | 25 | ## Maintainers 26 | * Dat Tran, github: [datitran](https://github.com/datitran) 27 | 28 | ## Copyright 29 | 30 | See [LICENSE](LICENSE) for details. 31 | -------------------------------------------------------------------------------- /config.tf: -------------------------------------------------------------------------------- 1 | terraform { 2 | backend "s3" { 3 | encrypt = true 4 | bucket = "terraform-persistence" 5 | key = "terraform-emr-pyspark.tfstate" 6 | region = "eu-central-1" 7 | } 8 | } 9 | 10 | provider "aws" { 11 | version = "~> 1.0" 12 | region = "${var.region}" 13 | } 14 | -------------------------------------------------------------------------------- /main.tf: -------------------------------------------------------------------------------- 1 | module "s3" { 2 | source = "./modules/s3" 3 | name = "${var.name}" 4 | } 5 | 6 | module "iam" { 7 | source = "./modules/iam" 8 | } 9 | 10 | module "security" { 11 | source = "./modules/security" 12 | name = "${var.name}" 13 | vpc_id = "${var.vpc_id}" 14 | ingress_cidr_blocks = "${var.ingress_cidr_blocks}" 15 | } 16 | 17 | module "emr" { 18 | source = "./modules/emr" 19 | name = "${var.name}" 20 | release_label = "${var.release_label}" 21 | applications = "${var.applications}" 22 | subnet_id = "${var.subnet_id}" 23 | key_name = "${var.key_name}" 24 | master_instance_type = "${var.master_instance_type}" 25 | master_ebs_size = "${var.master_ebs_size}" 26 | core_instance_type = "${var.core_instance_type}" 27 | core_instance_count = "${var.core_instance_count}" 28 | core_ebs_size = "${var.core_ebs_size}" 29 | emr_master_security_group = "${module.security.emr_master_security_group}" 30 | emr_slave_security_group = "${module.security.emr_slave_security_group}" 31 | emr_ec2_instance_profile = "${module.iam.emr_ec2_instance_profile}" 32 | emr_service_role = "${module.iam.emr_service_role}" 33 | emr_autoscaling_role = "${module.iam.emr_autoscaling_role}" 34 | } 35 | -------------------------------------------------------------------------------- /modules/emr/main.tf: -------------------------------------------------------------------------------- 1 | resource "aws_emr_cluster" "emr-spark-cluster" { 2 | name = "${var.name}" 3 | release_label = "${var.release_label}" 4 | applications = "${var.applications}" 5 | termination_protection = false 6 | keep_job_flow_alive_when_no_steps = true 7 | 8 | ec2_attributes { 9 | subnet_id = "${var.subnet_id}" 10 | key_name = "${var.key_name}" 11 | emr_managed_master_security_group = "${var.emr_master_security_group}" 12 | emr_managed_slave_security_group = "${var.emr_slave_security_group}" 13 | instance_profile = "${var.emr_ec2_instance_profile}" 14 | } 15 | 16 | ebs_root_volume_size = "12" 17 | 18 | instance_group { 19 | name = "EMR master" 20 | instance_role = "MASTER" 21 | instance_type = "${var.master_instance_type}" 22 | instance_count = "1" 23 | 24 | ebs_config { 25 | size = "${var.master_ebs_size}" 26 | type = "gp2" 27 | volumes_per_instance = 1 28 | } 29 | } 30 | 31 | instance_group { 32 | name = "EMR slave" 33 | instance_role = "CORE" 34 | instance_type = "${var.core_instance_type}" 35 | instance_count = "${var.core_instance_count}" 36 | 37 | ebs_config { 38 | size = "${var.core_ebs_size}" 39 | type = "gp2" 40 | volumes_per_instance = 1 41 | } 42 | } 43 | 44 | tags { 45 | Name = "${var.name} - Spark cluster" 46 | } 47 | 48 | service_role = "${var.emr_service_role}" 49 | autoscaling_role = "${var.emr_autoscaling_role}" 50 | 51 | bootstrap_action { 52 | name = "Bootstrap setup." 53 | path = "s3://${var.name}/scripts/bootstrap_actions.sh" 54 | } 55 | 56 | step = [ 57 | { 58 | name = "Copy script file from s3." 59 | action_on_failure = "CONTINUE" 60 | 61 | hadoop_jar_step { 62 | jar = "command-runner.jar" 63 | args = ["aws", "s3", "cp", "s3://${var.name}/scripts/pyspark_quick_setup.sh", "/home/hadoop/"] 64 | } 65 | }, 66 | { 67 | name = "Setup pyspark with conda." 68 | action_on_failure = "CONTINUE" 69 | 70 | hadoop_jar_step { 71 | jar = "command-runner.jar" 72 | args = ["sudo", "bash", "/home/hadoop/pyspark_quick_setup.sh"] 73 | } 74 | }, 75 | ] 76 | 77 | configurations_json = <> $HOME/.bashrc && source $HOME/.bashrc 8 | 9 | # install packages 10 | conda install -y notebook=5.7.* jupyter=1.0.* pandas seaborn 11 | 12 | #install findspark 13 | pip install --upgrade pip 14 | pip install findspark 15 | pip install sklearn 16 | -------------------------------------------------------------------------------- /scripts/pyspark_quick_setup.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | 3 | # bind conda to spark 4 | echo -e "\nexport PYSPARK_PYTHON=/home/hadoop/conda/bin/python" >> /etc/spark/conf/spark-env.sh 5 | echo "export PYSPARK_DRIVER_PYTHON=/home/hadoop/conda/bin/jupyter" >> /etc/spark/conf/spark-env.sh 6 | echo "export PYSPARK_DRIVER_PYTHON_OPTS='notebook --no-browser --port 8888 --ip=\"0.0.0.0\"'" >> /etc/spark/conf/spark-env.sh 7 | -------------------------------------------------------------------------------- /terraform.tfvars: -------------------------------------------------------------------------------- 1 | # EMR general configurations 2 | name = "spark-app" 3 | region = "eu-central-1" 4 | subnet_id = "" 5 | vpc_id = "" 6 | key_name = "" 7 | ingress_cidr_blocks = "0.0.0.0/0" 8 | release_label = "emr-5.16.0" 9 | applications = ["Hadoop", "Spark"] 10 | 11 | # Master node configurations 12 | master_instance_type = "m3.xlarge" 13 | master_ebs_size = "50" 14 | 15 | # Slave nodes configurations 16 | core_instance_type = "m3.xlarge" 17 | core_instance_count = 1 18 | core_ebs_size = "50" 19 | -------------------------------------------------------------------------------- /variables.tf: -------------------------------------------------------------------------------- 1 | variable "name" {} 2 | variable "region" {} 3 | variable "subnet_id" {} 4 | variable "vpc_id" {} 5 | variable "key_name" {} 6 | variable "release_label" {} 7 | variable "applications" { 8 | type = "list" 9 | } 10 | variable "master_instance_type" {} 11 | variable "master_ebs_size" {} 12 | variable "core_instance_type" {} 13 | variable "core_instance_count" {} 14 | variable "core_ebs_size" {} 15 | variable "ingress_cidr_blocks" {} 16 | --------------------------------------------------------------------------------