├── .github
└── workflows
│ └── ci.yaml
├── .gitignore
├── .terraform-docs.yml
├── .terraform.lock.hcl
├── CHANGELOG.md
├── CONTRIBUTING.md
├── LICENSE
├── README.md
├── images
├── logging_export_ops_dashboard.png
└── logging_export_to_splunk.png
├── main.tf
├── monitoring.tf
├── network.tf
├── outputs.tf
├── permissions.tf
├── pipeline.tf
├── replay.tf
├── sample.tfvars
├── variables.tf
└── versions.tf
/.github/workflows/ci.yaml:
--------------------------------------------------------------------------------
1 | name: Check quality gates
2 | on:
3 | push:
4 | branches: [ main ]
5 | pull_request:
6 | branches: [ main ]
7 |
8 | jobs:
9 | tflint:
10 | name: Run TFlint
11 | runs-on: ubuntu-latest
12 |
13 | steps:
14 | - uses: actions/checkout@v2
15 | name: Checkout source code
16 |
17 | - uses: actions/cache@v2
18 | name: Cache plugin dir
19 | with:
20 | path: ~/.tflint.d/plugins
21 | key: ubuntu-latest-tflint-${{ hashFiles('.tflint.hcl') }}
22 |
23 | - uses: terraform-linters/setup-tflint@v2
24 | name: Setup TFLint
25 | with:
26 | tflint_version: v0.42.2
27 |
28 | - name: Show version
29 | run: tflint --version
30 |
31 | - name: Init TFLint
32 | run: tflint --init
33 |
34 | - name: Run TFLint
35 | run: tflint -f compact
36 | fmt:
37 | name: Run Terraform format
38 | runs-on: ubuntu-latest
39 |
40 | steps:
41 | - uses: actions/checkout@v2
42 | name: Checkout source code
43 |
44 | - uses: hashicorp/setup-terraform@v2
45 | with:
46 | terraform_version: 1.1.7
47 | name: Install Terraform
48 |
49 | - name: Run terraform fmt
50 | run: terraform fmt -check=true -write=false
51 | docs:
52 | name: Validate docs
53 | runs-on: ubuntu-latest
54 | steps:
55 | - uses: actions/checkout@v2
56 | name: Checkout source code
57 |
58 | - name: Render terraform docs inside the README.md and fail if changes are presented
59 | uses: terraform-docs/gh-actions@v1.0.0
60 | with:
61 | working-dir: .
62 | config-file: .terraform-docs.yml
63 | fail-on-diff: "true"
64 |
--------------------------------------------------------------------------------
/.gitignore:
--------------------------------------------------------------------------------
1 | .terraform
2 | terraform.tfvars*
3 | terraform.tfstate*
4 |
5 | *.swp
6 |
--------------------------------------------------------------------------------
/.terraform-docs.yml:
--------------------------------------------------------------------------------
1 | formatter: markdown table
2 | output:
3 | file: README.md
4 | mode: inject
5 | template: |-
6 |
7 | {{ .Content }}
8 |
9 | sort:
10 | enabled: true
11 | by: required
12 | content: |-
13 | {{ .Inputs }}
14 | {{ .Outputs }}
15 | settings:
16 | indent: 4
17 | escape: false
18 | default: true
19 | required: true
20 | html: true
21 | type: true
22 |
--------------------------------------------------------------------------------
/.terraform.lock.hcl:
--------------------------------------------------------------------------------
1 | # This file is maintained automatically by "terraform init".
2 | # Manual edits may be lost in future updates.
3 |
4 | provider "registry.terraform.io/hashicorp/google" {
5 | version = "4.52.0"
6 | constraints = ">= 3.54.0"
7 | hashes = [
8 | "h1:Nlb8C/liQ7fnT4sNXSjTGxTlwzw/w28K96kp3TI7DWo=",
9 | "zh:1e36ac7c1be43cbb1d05fe1e5497dd058d1d87e03f848fd200bb043b1d6883f9",
10 | "zh:40a023e6e2f4f3137a156ba368815de5294be1c9d8049945768211d1868a5e0c",
11 | "zh:4bb0e3e97c95b32de5ccba13c3092fd929b95a646245ebe6829bb014863d8da0",
12 | "zh:59d11a98a80105273511343321b1d1af7a9e39c8474a6563761c8e7e8075dbb3",
13 | "zh:5c080d5368e898625f640a3397e8ab5f565a2a0c965642ecc124098f42c343a8",
14 | "zh:72fd8356a90941ec6e2ec1e838b00c1946eba7aabfe9fb25e32258e49d42e368",
15 | "zh:750f28b778dfecb0bed1d0b4df40a5e91fff16eb3ca4de64bed7c9945fea4e36",
16 | "zh:7e28085c105b96687bf6491f72e9ca915496352749a7af1a65013f7e5e89452b",
17 | "zh:83c8ecd116387032f7c4a1d9d4d921529746ce6e81d0766c9a0780c0b2e12993",
18 | "zh:bfd2d4cb2daba199db49a33ff507c808a3c94a657e4597b8bd6f2de51dc7a729",
19 | "zh:d9fd24b3d492013bca0021f29bfb670b76f01df5fd45f62c61eec53adac1b47d",
20 | "zh:f569b65999264a9416862bca5cd2a6177d94ccb0424f3a4ef424428912b9cb3c",
21 | ]
22 | }
23 |
24 | provider "registry.terraform.io/hashicorp/random" {
25 | version = "3.4.3"
26 | constraints = ">= 2.1.0"
27 | hashes = [
28 | "h1:xZGZf18JjMS06pFa4NErzANI98qi59SEcBsOcS2P2yQ=",
29 | "zh:41c53ba47085d8261590990f8633c8906696fa0a3c4b384ff6a7ecbf84339752",
30 | "zh:59d98081c4475f2ad77d881c4412c5129c56214892f490adf11c7e7a5a47de9b",
31 | "zh:686ad1ee40b812b9e016317e7f34c0d63ef837e084dea4a1f578f64a6314ad53",
32 | "zh:78d5eefdd9e494defcb3c68d282b8f96630502cac21d1ea161f53cfe9bb483b3",
33 | "zh:84103eae7251384c0d995f5a257c72b0096605048f757b749b7b62107a5dccb3",
34 | "zh:8ee974b110adb78c7cd18aae82b2729e5124d8f115d484215fd5199451053de5",
35 | "zh:9dd4561e3c847e45de603f17fa0c01ae14cae8c4b7b4e6423c9ef3904b308dda",
36 | "zh:bb07bb3c2c0296beba0beec629ebc6474c70732387477a65966483b5efabdbc6",
37 | "zh:e891339e96c9e5a888727b45b2e1bb3fcbdfe0fd7c5b4396e4695459b38c8cb1",
38 | "zh:ea4739860c24dfeaac6c100b2a2e357106a89d18751f7693f3c31ecf6a996f8d",
39 | "zh:f0c76ac303fd0ab59146c39bc121c5d7d86f878e9a69294e29444d4c653786f8",
40 | "zh:f143a9a5af42b38fed328a161279906759ff39ac428ebcfe55606e05e1518b93",
41 | ]
42 | }
43 |
--------------------------------------------------------------------------------
/CHANGELOG.md:
--------------------------------------------------------------------------------
1 | # Changelog
2 |
3 | The project is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) and [Semantic Versioning](https://semver.org/). All notable changes to this project will be documented in this file.
4 |
5 |
6 | ## [Unreleased] - 202X-XX-XX
7 |
8 | ### Added
9 |
10 | - Option `use_externally_managed_dataflow_sa` to be able to use pre-existing externally-managed service account as Dataflow worker service account. User is expected to apply and manage IAM permissions over external resources (e.g. Cloud KMS key or Secret version) outside of this module.
11 | - Enable uniform bucket-level access for the temporary Cloud Storage bucket used by Dataflow pipeline. This change disables ACLs for individual objects in this bucket, in favor for a uniform access control over entire bucket and IAM-based security features (e.g. Domain Restricted Sharing, IAM Conditions).
12 |
13 | ### Removed
14 |
15 | - `providers` configuration because it prevents usage of this module with `count` and `for_each`. This module now inherits the default provider configuration from the caller, thereby simplifying module re-usability.
16 |
17 | ### Fixed
18 |
19 | - Removed hardcoded project numbers in log panels in dashboard's JSON description
20 |
21 |
22 | ## [v1.0.0] - 2022-12-20
23 |
24 | - Initial version
25 |
--------------------------------------------------------------------------------
/CONTRIBUTING.md:
--------------------------------------------------------------------------------
1 | # How to Contribute
2 |
3 | We'd love to accept your patches and contributions to this project. There are
4 | just a few small guidelines you need to follow.
5 |
6 | ## Contributor License Agreement
7 |
8 | Contributions to this project must be accompanied by a Contributor License
9 | Agreement. You (or your employer) retain the copyright to your contribution;
10 | this simply gives us permission to use and redistribute your contributions as
11 | part of the project. Head over to to see
12 | your current agreements on file or to sign a new one.
13 |
14 | You generally only need to submit a CLA once, so if you've already submitted one
15 | (even if it was for a different project), you probably don't need to do it
16 | again.
17 |
18 | ## Code Reviews
19 |
20 | All submissions, including submissions by project members, require review. We
21 | use GitHub pull requests for this purpose. Consult
22 | [GitHub Help](https://help.github.com/articles/about-pull-requests/) for more
23 | information on using pull requests.
24 |
25 | ## Quality gates
26 | The project has several Quality gates.
27 | Make sure to run them localy before raising PR.
28 | 1. Run [tflint](https://github.com/terraform-linters/tflint) with default settings
29 | ```
30 | tflint .
31 | ```
32 | 2. Run terraform format
33 | ```
34 | terraform fmt .
35 | ```
36 | 3. Generate documentation with help of [terraform-docs](https://terraform-docs.io/)
37 | ```
38 | terraform-docs .
39 | ```
40 |
41 | ## Community Guidelines
42 |
43 | This project follows [Google's Open Source Community
44 | Guidelines](https://opensource.google/conduct/).
--------------------------------------------------------------------------------
/LICENSE:
--------------------------------------------------------------------------------
1 |
2 | Apache License
3 | Version 2.0, January 2004
4 | http://www.apache.org/licenses/
5 |
6 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
7 |
8 | 1. Definitions.
9 |
10 | "License" shall mean the terms and conditions for use, reproduction,
11 | and distribution as defined by Sections 1 through 9 of this document.
12 |
13 | "Licensor" shall mean the copyright owner or entity authorized by
14 | the copyright owner that is granting the License.
15 |
16 | "Legal Entity" shall mean the union of the acting entity and all
17 | other entities that control, are controlled by, or are under common
18 | control with that entity. For the purposes of this definition,
19 | "control" means (i) the power, direct or indirect, to cause the
20 | direction or management of such entity, whether by contract or
21 | otherwise, or (ii) ownership of fifty percent (50%) or more of the
22 | outstanding shares, or (iii) beneficial ownership of such entity.
23 |
24 | "You" (or "Your") shall mean an individual or Legal Entity
25 | exercising permissions granted by this License.
26 |
27 | "Source" form shall mean the preferred form for making modifications,
28 | including but not limited to software source code, documentation
29 | source, and configuration files.
30 |
31 | "Object" form shall mean any form resulting from mechanical
32 | transformation or translation of a Source form, including but
33 | not limited to compiled object code, generated documentation,
34 | and conversions to other media types.
35 |
36 | "Work" shall mean the work of authorship, whether in Source or
37 | Object form, made available under the License, as indicated by a
38 | copyright notice that is included in or attached to the work
39 | (an example is provided in the Appendix below).
40 |
41 | "Derivative Works" shall mean any work, whether in Source or Object
42 | form, that is based on (or derived from) the Work and for which the
43 | editorial revisions, annotations, elaborations, or other modifications
44 | represent, as a whole, an original work of authorship. For the purposes
45 | of this License, Derivative Works shall not include works that remain
46 | separable from, or merely link (or bind by name) to the interfaces of,
47 | the Work and Derivative Works thereof.
48 |
49 | "Contribution" shall mean any work of authorship, including
50 | the original version of the Work and any modifications or additions
51 | to that Work or Derivative Works thereof, that is intentionally
52 | submitted to Licensor for inclusion in the Work by the copyright owner
53 | or by an individual or Legal Entity authorized to submit on behalf of
54 | the copyright owner. For the purposes of this definition, "submitted"
55 | means any form of electronic, verbal, or written communication sent
56 | to the Licensor or its representatives, including but not limited to
57 | communication on electronic mailing lists, source code control systems,
58 | and issue tracking systems that are managed by, or on behalf of, the
59 | Licensor for the purpose of discussing and improving the Work, but
60 | excluding communication that is conspicuously marked or otherwise
61 | designated in writing by the copyright owner as "Not a Contribution."
62 |
63 | "Contributor" shall mean Licensor and any individual or Legal Entity
64 | on behalf of whom a Contribution has been received by Licensor and
65 | subsequently incorporated within the Work.
66 |
67 | 2. Grant of Copyright License. Subject to the terms and conditions of
68 | this License, each Contributor hereby grants to You a perpetual,
69 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable
70 | copyright license to reproduce, prepare Derivative Works of,
71 | publicly display, publicly perform, sublicense, and distribute the
72 | Work and such Derivative Works in Source or Object form.
73 |
74 | 3. Grant of Patent License. Subject to the terms and conditions of
75 | this License, each Contributor hereby grants to You a perpetual,
76 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable
77 | (except as stated in this section) patent license to make, have made,
78 | use, offer to sell, sell, import, and otherwise transfer the Work,
79 | where such license applies only to those patent claims licensable
80 | by such Contributor that are necessarily infringed by their
81 | Contribution(s) alone or by combination of their Contribution(s)
82 | with the Work to which such Contribution(s) was submitted. If You
83 | institute patent litigation against any entity (including a
84 | cross-claim or counterclaim in a lawsuit) alleging that the Work
85 | or a Contribution incorporated within the Work constitutes direct
86 | or contributory patent infringement, then any patent licenses
87 | granted to You under this License for that Work shall terminate
88 | as of the date such litigation is filed.
89 |
90 | 4. Redistribution. You may reproduce and distribute copies of the
91 | Work or Derivative Works thereof in any medium, with or without
92 | modifications, and in Source or Object form, provided that You
93 | meet the following conditions:
94 |
95 | (a) You must give any other recipients of the Work or
96 | Derivative Works a copy of this License; and
97 |
98 | (b) You must cause any modified files to carry prominent notices
99 | stating that You changed the files; and
100 |
101 | (c) You must retain, in the Source form of any Derivative Works
102 | that You distribute, all copyright, patent, trademark, and
103 | attribution notices from the Source form of the Work,
104 | excluding those notices that do not pertain to any part of
105 | the Derivative Works; and
106 |
107 | (d) If the Work includes a "NOTICE" text file as part of its
108 | distribution, then any Derivative Works that You distribute must
109 | include a readable copy of the attribution notices contained
110 | within such NOTICE file, excluding those notices that do not
111 | pertain to any part of the Derivative Works, in at least one
112 | of the following places: within a NOTICE text file distributed
113 | as part of the Derivative Works; within the Source form or
114 | documentation, if provided along with the Derivative Works; or,
115 | within a display generated by the Derivative Works, if and
116 | wherever such third-party notices normally appear. The contents
117 | of the NOTICE file are for informational purposes only and
118 | do not modify the License. You may add Your own attribution
119 | notices within Derivative Works that You distribute, alongside
120 | or as an addendum to the NOTICE text from the Work, provided
121 | that such additional attribution notices cannot be construed
122 | as modifying the License.
123 |
124 | You may add Your own copyright statement to Your modifications and
125 | may provide additional or different license terms and conditions
126 | for use, reproduction, or distribution of Your modifications, or
127 | for any such Derivative Works as a whole, provided Your use,
128 | reproduction, and distribution of the Work otherwise complies with
129 | the conditions stated in this License.
130 |
131 | 5. Submission of Contributions. Unless You explicitly state otherwise,
132 | any Contribution intentionally submitted for inclusion in the Work
133 | by You to the Licensor shall be under the terms and conditions of
134 | this License, without any additional terms or conditions.
135 | Notwithstanding the above, nothing herein shall supersede or modify
136 | the terms of any separate license agreement you may have executed
137 | with Licensor regarding such Contributions.
138 |
139 | 6. Trademarks. This License does not grant permission to use the trade
140 | names, trademarks, service marks, or product names of the Licensor,
141 | except as required for reasonable and customary use in describing the
142 | origin of the Work and reproducing the content of the NOTICE file.
143 |
144 | 7. Disclaimer of Warranty. Unless required by applicable law or
145 | agreed to in writing, Licensor provides the Work (and each
146 | Contributor provides its Contributions) on an "AS IS" BASIS,
147 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
148 | implied, including, without limitation, any warranties or conditions
149 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
150 | PARTICULAR PURPOSE. You are solely responsible for determining the
151 | appropriateness of using or redistributing the Work and assume any
152 | risks associated with Your exercise of permissions under this License.
153 |
154 | 8. Limitation of Liability. In no event and under no legal theory,
155 | whether in tort (including negligence), contract, or otherwise,
156 | unless required by applicable law (such as deliberate and grossly
157 | negligent acts) or agreed to in writing, shall any Contributor be
158 | liable to You for damages, including any direct, indirect, special,
159 | incidental, or consequential damages of any character arising as a
160 | result of this License or out of the use or inability to use the
161 | Work (including but not limited to damages for loss of goodwill,
162 | work stoppage, computer failure or malfunction, or any and all
163 | other commercial damages or losses), even if such Contributor
164 | has been advised of the possibility of such damages.
165 |
166 | 9. Accepting Warranty or Additional Liability. While redistributing
167 | the Work or Derivative Works thereof, You may choose to offer,
168 | and charge a fee for, acceptance of support, warranty, indemnity,
169 | or other liability obligations and/or rights consistent with this
170 | License. However, in accepting such obligations, You may act only
171 | on Your own behalf and on Your sole responsibility, not on behalf
172 | of any other Contributor, and only if You agree to indemnify,
173 | defend, and hold each Contributor harmless for any liability
174 | incurred by, or claims asserted against, such Contributor by reason
175 | of your accepting any such warranty or additional liability.
176 |
177 | END OF TERMS AND CONDITIONS
178 |
179 | APPENDIX: How to apply the Apache License to your work.
180 |
181 | To apply the Apache License to your work, attach the following
182 | boilerplate notice, with the fields enclosed by brackets "[]"
183 | replaced with your own identifying information. (Don't include
184 | the brackets!) The text should be enclosed in the appropriate
185 | comment syntax for the file format. We also recommend that a
186 | file or class name and description of purpose be included on the
187 | same "printed page" as the copyright notice for easier
188 | identification within third-party archives.
189 |
190 | Copyright [yyyy] [name of copyright owner]
191 |
192 | Licensed under the Apache License, Version 2.0 (the "License");
193 | you may not use this file except in compliance with the License.
194 | You may obtain a copy of the License at
195 |
196 | http://www.apache.org/licenses/LICENSE-2.0
197 |
198 | Unless required by applicable law or agreed to in writing, software
199 | distributed under the License is distributed on an "AS IS" BASIS,
200 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
201 | See the License for the specific language governing permissions and
202 | limitations under the License.
203 |
--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 | # Terraform templates for Google Cloud log export to Splunk
2 |
3 | Terraform scripts for deploying log export to Splunk per Google Cloud reference guide:
4 | [Deploying production-ready log exports to Splunk using Dataflow](https://cloud.google.com/architecture/deploying-production-ready-log-exports-to-splunk-using-dataflow)
5 | .
6 |
7 | Resources created include an optional [Cloud Monitoring custom dashboard](#monitoring-dashboard-batteries-included) to monitor your log export operations. For more details on custom metrics in Splunk Dataflow template, see [New observability features for your Splunk Dataflow streaming pipelines](https://cloud.google.com/blog/products/data-analytics/simplify-your-splunk-dataflow-ops-with-improved-pipeline-observability).
8 |
9 | These deployment templates are provided as is, without warranty. See [Copyright & License](#copyright-&-license) below.
10 |
11 | ### Architecture Diagram
12 |
13 | 
14 |
15 | ### Terraform Module
16 |
17 | #### Inputs
18 |
19 | | Name | Description | Type | Default | Required |
20 | |------|-------------|------|---------|:--------:|
21 | | [dataflow_job_name](#input_dataflow_job_name) | Dataflow job name. No spaces | `string` | n/a | yes |
22 | | [log_filter](#input_log_filter) | Log filter to use when exporting logs | `string` | n/a | yes |
23 | | [network](#input_network) | Network to deploy into | `string` | n/a | yes |
24 | | [project](#input_project) | Project ID to deploy resources in | `string` | n/a | yes |
25 | | [region](#input_region) | Region to deploy regional-resources into. This must match subnet's region if deploying into existing network (e.g. Shared VPC). See `subnet` parameter below | `string` | n/a | yes |
26 | | [splunk_hec_url](#input_splunk_hec_url) | Splunk HEC URL to write data to. Example: https://[MY_SPLUNK_IP_OR_FQDN]:8088 | `string` | n/a | yes |
27 | | [create_network](#input_create_network) | Boolean value specifying if a new network needs to be created. | `bool` | `false` | no |
28 | | [dataflow_job_batch_count](#input_dataflow_job_batch_count) | Batch count of messages in single request to Splunk | `number` | `50` | no |
29 | | [dataflow_job_disable_certificate_validation](#input_dataflow_job_disable_certificate_validation) | Boolean to disable SSL certificate validation | `bool` | `false` | no |
30 | | [dataflow_job_machine_count](#input_dataflow_job_machine_count) | Dataflow job max worker count | `number` | `2` | no |
31 | | [dataflow_job_machine_type](#input_dataflow_job_machine_type) | Dataflow job worker machine type | `string` | `"n1-standard-4"` | no |
32 | | [dataflow_job_parallelism](#input_dataflow_job_parallelism) | Maximum parallel requests to Splunk | `number` | `8` | no |
33 | | [dataflow_job_udf_function_name](#input_dataflow_job_udf_function_name) | Name of JavaScript function to be called | `string` | `""` | no |
34 | | [dataflow_job_udf_gcs_path](#input_dataflow_job_udf_gcs_path) | GCS path for JavaScript file | `string` | `""` | no |
35 | | [dataflow_template_version](#input_dataflow_template_version) | Dataflow template release version (default 'latest'). Override this for version pinning e.g. '2021-08-02-00_RC00'. Must specify version only since template GCS path will be deduced automatically: 'gs://dataflow-templates/`version`/Cloud_PubSub_to_Splunk' | `string` | `"latest"` | no |
36 | | [dataflow_worker_service_account](#input_dataflow_worker_service_account) | Name of Dataflow worker service account to be created and used to execute job operations. In the default case of creating a new service account (`use_externally_managed_dataflow_sa=false`), this parameter must be 6-30 characters long, and match the regular expression [a-z]([-a-z0-9]*[a-z0-9]). If the parameter is empty, worker service account defaults to project's Compute Engine default service account. If using external service account (`use_externally_managed_dataflow_sa=true`), this parameter must be the full email address of the external service account. | `string` | `""` | no |
37 | | [deploy_replay_job](#input_deploy_replay_job) | Determines if replay pipeline should be deployed or not | `bool` | `false` | no |
38 | | [gcs_kms_key_name](#input_gcs_kms_key_name) | Cloud KMS key resource ID, to be used as default encryption key for the temporary storage bucket used by the Dataflow job.
If set, make sure to pre-authorize Cloud Storage service agent associated with that bucket to use that key for encrypting and decrypting. | `string` | `""` | no |
39 | | [primary_subnet_cidr](#input_primary_subnet_cidr) | The CIDR Range of the primary subnet | `string` | `"10.128.0.0/20"` | no |
40 | | [scoping_project](#input_scoping_project) | Cloud Monitoring scoping project ID to create dashboard under.
This assumes a pre-existing scoping project whose metrics scope contains the `project` where dataflow job is to be deployed.
See [Cloud Monitoring settings](https://cloud.google.com/monitoring/settings) for more details on scoping project.
If parameter is empty, scoping project defaults to value of `project` parameter above. | `string` | `""` | no |
41 | | [splunk_hec_token](#input_splunk_hec_token) | Splunk HEC token. Must be defined if `splunk_hec_token_source` if type of `PLAINTEXT` or `KMS`. | `string` | `""` | no |
42 | | [splunk_hec_token_kms_encryption_key](#input_splunk_hec_token_kms_encryption_key) | The Cloud KMS key to decrypt the HEC token string. Required if `splunk_hec_token_source` is type of KMS | `string` | `""` | no |
43 | | [splunk_hec_token_secret_id](#input_splunk_hec_token_secret_id) | Id of the Secret for Splunk HEC token. Required if `splunk_hec_token_source` is type of SECRET_MANAGER | `string` | `""` | no |
44 | | [splunk_hec_token_source](#input_splunk_hec_token_source) | Define in which type HEC token is provided. Possible options: [PLAINTEXT, KMS, SECRET_MANAGER]. | `string` | `"PLAINTEXT"` | no |
45 | | [subnet](#input_subnet) | Subnet to deploy into. This is required when deploying into existing network (`create_network=false`) (e.g. Shared VPC) | `string` | `""` | no |
46 | | [use_externally_managed_dataflow_sa](#input_use_externally_managed_dataflow_sa) | Determines if the worker service account provided by `dataflow_worker_service_account` variable should be created by this module (default) or is managed outside of the module. In the latter case, user is expected to apply and manage the service account IAM permissions over external resources (e.g. Cloud KMS key or Secret version) before running this module. | `bool` | `false` | no |
47 | #### Outputs
48 |
49 | | Name | Description |
50 | |------|-------------|
51 | | [dataflow_input_topic](#output_dataflow_input_topic) | n/a |
52 | | [dataflow_job_id](#output_dataflow_job_id) | n/a |
53 | | [dataflow_log_export_dashboard](#output_dataflow_log_export_dashboard) | n/a |
54 | | [dataflow_output_deadletter_subscription](#output_dataflow_output_deadletter_subscription) | n/a |
55 |
56 |
57 | ### Monitoring Dashboard (Batteries Included)
58 |
59 | Deployment templates include an optional Cloud Monitoring custom dashboard to monitor your log export operations:
60 | 
61 |
62 | ### Permissions Required
63 |
64 | At a minimum, you must have the following roles before you deploy the resources in this Terraform:
65 | - Logs Configuration Writer (`roles/logging.configWriter`) at the project and/or organization level
66 | - Compute Network Admin (`roles/compute.networkAdmin`) at the project level
67 | - Compute Security Admin (`roles/compute.securityAdmin`) at the project level
68 | - Dataflow Admin (`roles/dataflow.admin`) at the project level
69 | - Pub/Sub Admin (`roles/pubsub.admin`) at the project level
70 | - Storage Admin (`roles/storage.admin`) at the project level
71 |
72 | To ensure proper pipeline operation, Terraform creates necessary IAM bindings at the resources level as part of this deployment to grant access between newly created resources. For example, Log sink writer is granted Pub/Sub Publisher role over the input topic which collects all the logs, and Dataflow worker service account is granted both Pub/Sub subscriber over the input subscription, and Pub/Sub Publisher role over the deadletter topic.
73 |
74 | #### Dataflow permissions
75 |
76 | The Dataflow worker service service account is the identity used by the Dataflow worker VMs. This module offers three options in terms of which worker service account to use and how to manage their IAM permissions:
77 |
78 | 1. Module uses your project's [Compute Engine default service account](https://cloud.google.com/compute/docs/access/service-accounts#default_service_account) as Dataflow worker service account, and manages any required IAM permissions. The module grants that service account necessary IAM roles such as `roles/dataflow.worker` and IAM permissions over Google Cloud resources required by the job such as Pub/Sub, Cloud Storage, and secret or KMS if applicable. This is the **default behavior**.
79 |
80 | 2. Module creates a dedicated service account to be used as Dataflow worker service account, and manages any required IAM permissions. The module grants that service account necessary IAM roles such as `roles/dataflow.worker` and IAM permissions over Google Cloud resources required by the job such as Pub/Sub, Cloud Storage, and secret or KMS key if applicable. To use this option, set `dataflow_worker_service_account` to the name of this new service account.
81 |
82 | 3. Module uses a service account managed outside of the module. The module grants that service account necessary IAM permissions over Google Cloud resources created by the module such as Pub/Sub, Cloud Storage. You must grant this service account the required IAM roles (`roles/dataflow.worker` ) and IAM permissions over external resources such as any provided secret or KMS key (more below), _before_ running this module. To use this option, set `use_externally_managed_dataflow_sa` to `true` and set `dataflow_worker_service_account` to the email address of this external service account.
83 |
84 | For production workloads, as a security best practice, it's recommended to use option 2 or 3, both of which rely on user-managed worker service account, instead of the Compute Engine default service account. This ensures a minimally-scoped service account dedicated for this pipeline.
85 |
86 | For option 3, make sure to grant:
87 | - The provided Dataflow service account the following roles:
88 | - `roles/dataflow.worker`
89 | - `roles/secretmanager.secretAccessor` on secret - if `SECRET_MANAGER` HEC token source is used
90 | - `roles/cloudkms.cryptoKeyDecrypter` on KMS key- if `KMS` HEC token source is used
91 |
92 | For option 1 & 3, make sure to grant:
93 | - Your user account or service account used to run Terraform the following role:
94 | - `roles/iam.serviceAccountUser` on the Dataflow service account in order to impersonate the service account. See following note for more details.
95 |
96 | **Note about Dataflow worker service account impersonation**: To run this Terraform module, you must have permission to impersonate the Dataflow worker service account in order to attach that service account to Dataflow worker VMs. In case of the default Dataflow worker service account (Option 1), ensure you have `iam.serviceAccounts.actAs` permission over Compute Engine default service account in your project. For security purposes, this Terraform does not modify access to your existing Compute Engine default service account due to risk of granting broad permissions. On the other hand, if you choose to create and use a user-managed worker service account (Option 2) by setting `dataflow_worker_service_account` (and keeping `use_externally_managed_dataflow_sa` = `false`), this Terraform will add necessary impersonation permission over the new service account.
97 |
98 | See [Security and permissions for pipelines](https://cloud.google.com/dataflow/docs/concepts/security-and-permissions#security_and_permissions_for_pipelines_on) to learn more about Dataflow service accounts and their permissions.
99 |
100 | ### Getting Started
101 |
102 | #### Requirements
103 | * Terraform 0.13+
104 | * Splunk Dataflow template 2022-04-25-00_RC00 or later
105 |
106 | #### Enabling APIs
107 | Before deploying the Terraform in a Google Cloud Platform Project, the following APIs must be enabled:
108 | * Compute Engine API
109 | * Dataflow API
110 |
111 | For information on enabling Google Cloud Platform APIs, please see [Getting Started: Enabling APIs](https://cloud.google.com/apis/docs/getting-started#enabling_apis).
112 |
113 | #### Setup working directory
114 |
115 | 1. Copy placeholder vars file `sample.tfvars` into new `terraform.tfvars` to hold your own settings.
116 | 2. Update placeholder values in `terraform.tfvars` to correspond to your GCP environment and desired settings. See [list of input parameters](#configurable-parameters) above.
117 | 3. Initialize Terraform working directory and download plugins by running:
118 |
119 | ```shell
120 | $ terraform init
121 | ```
122 |
123 | #### Authenticate with GCP
124 | Note: You can skip this step if this module is inheriting the Terraform Google provider (e.g. from a parent module) with pre-configured credentials.
125 |
126 | ```shell
127 | $ gcloud auth application-default login --project
128 | ```
129 |
130 | This assumes you are running Terraform on your workstation with your own identity. For other methods to authenticate such as using a Terraform-specific service account, see [Google Provider authentication docs](https://registry.terraform.io/providers/hashicorp/google/latest/docs/guides/provider_reference#authentication).
131 |
132 | #### Deploy log export pipeline
133 |
134 | ```shell
135 | $ terraform plan
136 | $ terraform apply
137 | ```
138 |
139 | #### View log export monitoring dashboard
140 |
141 | 1. Retrieve dashboard id from terraform output
142 | ```shell
143 | $ terraform output dataflow_log_export_dashboard
144 | ```
145 | The output is of the form `"projects/{project_id_or_number}/dashboards/{dashboard_id}"`.
146 |
147 | Take note of dashboard_id value.
148 |
149 | 2. Visit newly created Monitoring Dashboard in Cloud Console by replacing dashboard_id in the following URL: https://console.cloud.google.com/monitoring/dashboards/builder/{dashboard_id}
150 |
151 | #### Deploy replay pipeline when needed
152 |
153 | The replay pipeline is not deployed by default; instead it is only used to move failed messages from the PubSub deadletter subscription back to the input topic, in order to be redelivered by the main log export pipeline (as depicted in above [diagram](#architecture-diagram)). Refer to [Handling delivery failures](https://cloud.google.com/architecture/deploying-production-ready-log-exports-to-splunk-using-dataflow#handling_delivery_failures) for more detail.
154 |
155 | **Caution**: Make sure to deploy replay pipeline only after the root cause of the delivery failure has been fixed. Otherwise, the replay pipeline will cause an infinite loop where failed messages are sent back for re-delivery, only to fail again, causing an infinite loop and wasted resources. For that same reason, make sure to tear down the replay pipeline once the failed messages from the deadletter subscription are all processed or replayed.
156 |
157 | 1. To deploy replay pipeline, set `deploy_replay_job` variable to `true`, then follow the sequence of `terraform plan` and `terraform apply`.
158 | 2. Once the replay pipeline is no longer needed (i.e. the number of messages in the PubSub deadletter subscription is 0), set `deploy_replay_job` variable to `false`, then follow the sequence of `terraform plan` and `terraform apply`.
159 |
160 | ### Cleanup
161 |
162 | To delete resources created by Terraform, run the following then confirm:
163 | ``` shell
164 | $ terraform destroy
165 | ```
166 |
167 | ### Using customer-managed encryption keys (CMEK)
168 |
169 | For those who require CMEK, this module accepts CMEK keys for the following services:
170 | - Cloud Storage: see `gcs_kms_key_name` input parameter. You are responsible for granting Cloud Storage service agent the role Cloud KMS CryptoKey Encrypter/Decrypter (`roles/cloudkms.cryptoKeyEncrypterDecrypter`) in order to use the provided Cloud KMS key for encrypting and decrypting objects in the temporary storage bucket. The Cloud KMS key must be available in the location that the temporary bucket is created in (specified in `var.region`). For more details, see [Use customer-managed encryption keys](https://cloud.google.com/storage/docs/encryption/using-customer-managed-keys) in Cloud Storage docs.
171 |
172 | ### Authors
173 |
174 | * **Roy Arsan** - [rarsan](https://github.com/rarsan)
175 | * **Nick Predey** - [npredey](https://github.com/npredey)
176 | * **Igor Lakhtenkov** - [Lakhtenkov-iv](https://github.com/Lakhtenkov-iv)
177 |
178 | ### Copyright & License
179 |
180 | Copyright 2021 Google LLC
181 |
182 | Terraform templates for Google Cloud Log Export to Splunk are licensed under the Apache license, v2.0. Details can be found in [LICENSE](./LICENSE) file.
183 |
--------------------------------------------------------------------------------
/images/logging_export_ops_dashboard.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/GoogleCloudPlatform/terraform-splunk-log-export/123d101f228ac90062635b7ee14fab8df4c46fc6/images/logging_export_ops_dashboard.png
--------------------------------------------------------------------------------
/images/logging_export_to_splunk.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/GoogleCloudPlatform/terraform-splunk-log-export/123d101f228ac90062635b7ee14fab8df4c46fc6/images/logging_export_to_splunk.png
--------------------------------------------------------------------------------
/main.tf:
--------------------------------------------------------------------------------
1 | # Copyright 2021 Google LLC
2 | #
3 | # Licensed under the Apache License, Version 2.0 (the "License");
4 | # you may not use this file except in compliance with the License.
5 | # You may obtain a copy of the License at
6 | #
7 | # https://www.apache.org/licenses/LICENSE-2.0
8 | #
9 | # Unless required by applicable law or agreed to in writing, software
10 | # distributed under the License is distributed on an "AS IS" BASIS,
11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 | # See the License for the specific language governing permissions and
13 | # limitations under the License.
14 |
15 | data "google_project" "project" {
16 | project_id = var.project
17 | }
18 |
19 | data "google_client_openid_userinfo" "provider_identity" {}
20 |
21 | # Generate new random hex to be used for bucket name
22 | resource "random_id" "bucket_suffix" {
23 | byte_length = 4
24 | }
25 |
26 | # Generate new random id each time we switch to a new template version id,
27 | # to be used for pipeline job name to force job replacement vs in-place update
28 | resource "random_id" "dataflow_job_instance" {
29 | byte_length = 2
30 | keepers = {
31 | dataflow_template_version = var.dataflow_template_version
32 | }
33 | }
34 |
35 | locals {
36 | dataflow_temporary_gcs_bucket_name = "${var.project}-${var.dataflow_job_name}-${random_id.bucket_suffix.hex}"
37 | dataflow_temporary_gcs_bucket_path = "tmp/"
38 |
39 | dataflow_splunk_template_gcs_path = "gs://dataflow-templates/${var.dataflow_template_version}/Cloud_PubSub_to_Splunk"
40 | dataflow_pubsub_template_gcs_path = "gs://dataflow-templates/${var.dataflow_template_version}/Cloud_PubSub_to_Cloud_PubSub"
41 |
42 | # If provided, set Dataflow worker to new user-managed service account;
43 | # otherwise, use Compute Engine default service account
44 | dataflow_worker_service_account = ((var.dataflow_worker_service_account != "") ?
45 | ((var.use_externally_managed_dataflow_sa == false) ?
46 | google_service_account.dataflow_worker_service_account[0].email :
47 | var.dataflow_worker_service_account) :
48 | "${data.google_project.project.number}-compute@developer.gserviceaccount.com")
49 |
50 | # Cross validate Dataflow service account variables
51 | # TODO: Remove once https://github.com/hashicorp/terraform/issues/25609 is resolved or use pre-conditions if version > 1.2.0
52 | # tflint-ignore: terraform_unused_declarations
53 | validate_sa_settings = (var.use_externally_managed_dataflow_sa && var.dataflow_worker_service_account == "") ? tobool("Please pass dataflow_worker_service_account if you want to manage it externally.") : true
54 | # Grant Dataflow worker service account required IAM roles over external resources
55 | # **unless** using an externally managed worker service account (Option 1 and 2):
56 | grant_service_account_roles = var.use_externally_managed_dataflow_sa == false
57 | # Grant caller (you!) permissions to impersonate service account
58 | # **only** when creating a new worker service account (Option 2)
59 | grant_service_account_impersonation = (
60 | var.dataflow_worker_service_account != "" && var.use_externally_managed_dataflow_sa == false
61 | )
62 |
63 | subnet_name = coalesce(var.subnet, "${var.network}-${var.region}")
64 | project_log_sink_name = "${var.dataflow_job_name}-project-log-sink"
65 | # tflint-ignore: terraform_unused_declarations
66 | organization_log_sink_name = "${var.dataflow_job_name}-organization-log-sink"
67 |
68 | dataflow_main_job_name = "${var.dataflow_job_name}-main-${random_id.dataflow_job_instance.hex}"
69 | dataflow_replay_job_name = "${var.dataflow_job_name}-replay-${random_id.dataflow_job_instance.hex}"
70 |
71 | dataflow_input_topic_name = "${var.dataflow_job_name}-input-topic"
72 | dataflow_input_subscription_name = "${var.dataflow_job_name}-input-subscription"
73 | dataflow_output_deadletter_topic_name = "${var.dataflow_job_name}-deadletter-topic"
74 | dataflow_output_deadletter_sub_name = "${var.dataflow_job_name}-deadletter-subscription"
75 | # Store HEC token secret and secret version IDs in two separate local values.
76 | # This is needed to disambiguate between the two given that the Dataflow template expects
77 | # secret version ID whereas the IAM policy binding expects parent secret ID
78 | splunk_hec_token_secret_version_id = var.splunk_hec_token_secret_id
79 | # Infer secret ID from input which is actually the secret *version* ID
80 | splunk_hec_token_secret_id = ((var.splunk_hec_token_secret_id != "")
81 | ? regex("^(projects\\/[^\\n\\r\\/]+\\/secrets\\/[^\\n\\r\\/]+)\\/versions\\/[^\\n\\r\\/]+$", var.splunk_hec_token_secret_id)[0]
82 | : "")
83 |
84 | # Dataflow job parameters (not externalized for this project)
85 | dataflow_job_include_pubsub_message = true
86 | dataflow_job_enable_batch_logs = false
87 | dataflow_job_enable_gzip_http_compression = true
88 |
89 | # Metrics scope for Monitoring dashboard defaults to project unless explicitly provided
90 | scoping_project = (var.scoping_project != "") ? var.scoping_project : var.project
91 | }
92 |
93 | resource "google_pubsub_topic" "dataflow_input_pubsub_topic" {
94 | project = var.project
95 | name = local.dataflow_input_topic_name
96 | }
97 |
98 | resource "google_pubsub_subscription" "dataflow_input_pubsub_subscription" {
99 | project = var.project
100 | name = local.dataflow_input_subscription_name
101 | topic = google_pubsub_topic.dataflow_input_pubsub_topic.name
102 |
103 | # messages retained for 7 days (max)
104 | message_retention_duration = "604800s"
105 | ack_deadline_seconds = 30
106 |
107 | # subscription never expires
108 | expiration_policy {
109 | ttl = ""
110 | }
111 | }
112 |
113 | resource "google_logging_project_sink" "project_log_sink" {
114 | project = var.project
115 | name = local.project_log_sink_name
116 | destination = "pubsub.googleapis.com/projects/${var.project}/topics/${google_pubsub_topic.dataflow_input_pubsub_topic.name}"
117 | filter = var.log_filter
118 |
119 | exclusions {
120 | name = "exclude_dataflow"
121 | description = "Exclude dataflow logs to not create an infinite loop"
122 | filter = "resource.type=\"dataflow_step\" AND resource.labels.job_name = \"${local.dataflow_main_job_name}\""
123 | }
124 |
125 | unique_writer_identity = true
126 | }
127 |
128 | # resource "google_logging_organization_sink" "organization_log_sink" {
129 | # name = local.organization_log_sink_name
130 | # org_id = "ORGANIZATION_ID"
131 | # destination = "pubsub.googleapis.com/projects/${var.project}/topics/${google_pubsub_topic.dataflow_input_pubsub_topic.name}"
132 | # filter = var.log_filter
133 | #
134 | # include_children = "true"
135 | # }
136 |
--------------------------------------------------------------------------------
/monitoring.tf:
--------------------------------------------------------------------------------
1 | # Copyright 2021 Google LLC
2 | #
3 | # Licensed under the Apache License, Version 2.0 (the "License");
4 | # you may not use this file except in compliance with the License.
5 | # You may obtain a copy of the License at
6 | #
7 | # https://www.apache.org/licenses/LICENSE-2.0
8 | #
9 | # Unless required by applicable law or agreed to in writing, software
10 | # distributed under the License is distributed on an "AS IS" BASIS,
11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 | # See the License for the specific language governing permissions and
13 | # limitations under the License.
14 |
15 | resource "google_monitoring_group" "splunk-export-pipeline-group" {
16 | display_name = "Splunk Log Export Group"
17 | project = local.scoping_project
18 |
19 | filter = "resource.metadata.name=starts_with(\"${var.dataflow_job_name}\")"
20 | }
21 |
22 | resource "google_monitoring_dashboard" "splunk-export-pipeline-dashboard" {
23 | project = local.scoping_project
24 | dashboard_json = < 0 ? google_compute_router_nat.dataflow_nat[0].name : ""}\"",
805 | "secondaryAggregation": {
806 | "alignmentPeriod": "60s"
807 | }
808 | }
809 | }
810 | }
811 | ],
812 | "timeshiftDuration": "0s",
813 | "yAxis": {
814 | "label": "y1Axis",
815 | "scale": "LINEAR"
816 | }
817 | }
818 | }
819 | }
820 | ]
821 | }
822 | }
823 |
824 | EOF
825 | }
826 |
--------------------------------------------------------------------------------
/network.tf:
--------------------------------------------------------------------------------
1 | resource "google_compute_network" "splunk_export" {
2 | count = var.create_network == true ? 1 : 0
3 |
4 | project = var.project
5 | name = var.network
6 | auto_create_subnetworks = false
7 | }
8 |
9 | resource "google_compute_subnetwork" "splunk_subnet" {
10 | count = var.create_network == true ? 1 : 0
11 |
12 | project = var.project
13 | name = local.subnet_name
14 | ip_cidr_range = var.primary_subnet_cidr
15 | region = var.region
16 | network = google_compute_network.splunk_export[count.index].id
17 | private_ip_google_access = true
18 |
19 | # Optional configuration to log network traffic at the subnet level
20 | # log_config {
21 | # aggregation_interval = "INTERVAL_15_MIN"
22 | # flow_sampling = 0.1
23 | # metadata = "INCLUDE_ALL_METADATA"
24 | # }
25 |
26 | }
27 |
28 | # Create DNS policy that enables logging of DNS queries in new network
29 | resource "google_dns_policy" "splunk_network_dns_policy" {
30 | count = var.create_network == true ? 1 : 0
31 |
32 | project = var.project
33 | name = "${var.network}-dns-policy"
34 |
35 | enable_logging = true
36 |
37 | networks {
38 | network_url = google_compute_network.splunk_export[count.index].id
39 | }
40 | }
41 |
42 | resource "google_compute_router" "dataflow_to_splunk_router" {
43 | count = var.create_network == true ? 1 : 0
44 |
45 | project = var.project
46 | name = "${var.network}-${var.region}-router"
47 | region = google_compute_subnetwork.splunk_subnet[count.index].region
48 | network = google_compute_network.splunk_export[count.index].id
49 | }
50 |
51 | resource "google_compute_address" "dataflow_nat_ip_address" {
52 | count = var.create_network == true ? 1 : 0
53 |
54 | project = var.project
55 | name = "dataflow-splunk-nat-ip-address"
56 | region = google_compute_subnetwork.splunk_subnet[count.index].region
57 | }
58 |
59 | resource "google_compute_router_nat" "dataflow_nat" {
60 | count = var.create_network == true ? 1 : 0
61 |
62 | project = var.project
63 | name = "${var.network}-${var.region}-router-nat"
64 | router = google_compute_router.dataflow_to_splunk_router[count.index].name
65 | region = google_compute_router.dataflow_to_splunk_router[count.index].region
66 | nat_ip_allocate_option = "MANUAL_ONLY"
67 | source_subnetwork_ip_ranges_to_nat = "LIST_OF_SUBNETWORKS"
68 | nat_ips = google_compute_address.dataflow_nat_ip_address[*].self_link
69 | min_ports_per_vm = 128
70 | subnetwork {
71 | name = google_compute_subnetwork.splunk_subnet[count.index].id
72 | source_ip_ranges_to_nat = ["PRIMARY_IP_RANGE"]
73 | }
74 |
75 | log_config {
76 | enable = true
77 | filter = "ERRORS_ONLY"
78 | }
79 | }
80 |
81 | # Creating firewall rule so that dataflow jobs with > 1 worker can communicate over internal IPs.
82 | # Source: https://cloud.google.com/dataflow/docs/guides/routes-firewall#firewall_rules_required_by
83 | resource "google_compute_firewall" "connect_dataflow_workers" {
84 | count = var.create_network == true ? 1 : 0
85 |
86 | project = var.project
87 | name = "dataflow-internal-ip-fwr"
88 | network = google_compute_network.splunk_export[count.index].id
89 |
90 | allow {
91 | protocol = "tcp"
92 | ports = ["12345-12346"]
93 | }
94 |
95 | source_tags = ["dataflow"]
96 | target_tags = ["dataflow"]
97 | }
98 |
--------------------------------------------------------------------------------
/outputs.tf:
--------------------------------------------------------------------------------
1 | output "dataflow_job_id" {
2 | value = google_dataflow_job.dataflow_job.job_id
3 | }
4 |
5 | output "dataflow_input_topic" {
6 | value = google_pubsub_topic.dataflow_input_pubsub_topic.name
7 | }
8 |
9 | output "dataflow_output_deadletter_subscription" {
10 | value = google_pubsub_subscription.dataflow_deadletter_pubsub_sub.name
11 | }
12 |
13 | output "dataflow_log_export_dashboard" {
14 | value = google_monitoring_dashboard.splunk-export-pipeline-dashboard.id
15 | }
16 |
--------------------------------------------------------------------------------
/permissions.tf:
--------------------------------------------------------------------------------
1 | # Copyright 2022 Google LLC
2 | #
3 | # Licensed under the Apache License, Version 2.0 (the "License");
4 | # you may not use this file except in compliance with the License.
5 | # You may obtain a copy of the License at
6 | #
7 | # https://www.apache.org/licenses/LICENSE-2.0
8 | #
9 | # Unless required by applicable law or agreed to in writing, software
10 | # distributed under the License is distributed on an "AS IS" BASIS,
11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 | # See the License for the specific language governing permissions and
13 | # limitations under the License.
14 |
15 | resource "google_pubsub_topic_iam_binding" "input_sub_publisher" {
16 | project = google_pubsub_topic.dataflow_input_pubsub_topic.project
17 | topic = google_pubsub_topic.dataflow_input_pubsub_topic.name
18 | role = "roles/pubsub.publisher"
19 | members = [
20 | google_logging_project_sink.project_log_sink.writer_identity
21 | ]
22 | }
23 |
24 | resource "google_pubsub_subscription_iam_binding" "input_sub_subscriber" {
25 | project = google_pubsub_subscription.dataflow_input_pubsub_subscription.project
26 | subscription = google_pubsub_subscription.dataflow_input_pubsub_subscription.name
27 | role = "roles/pubsub.subscriber"
28 | members = [
29 | "serviceAccount:${local.dataflow_worker_service_account}"
30 | ]
31 | }
32 |
33 | resource "google_pubsub_subscription_iam_binding" "input_sub_viewer" {
34 | project = google_pubsub_subscription.dataflow_input_pubsub_subscription.project
35 | subscription = google_pubsub_subscription.dataflow_input_pubsub_subscription.name
36 | role = "roles/pubsub.viewer"
37 | members = [
38 | "serviceAccount:${local.dataflow_worker_service_account}"
39 | ]
40 | }
41 |
42 | resource "google_pubsub_topic_iam_binding" "deadletter_topic_publisher" {
43 | project = google_pubsub_topic.dataflow_deadletter_pubsub_topic.project
44 | topic = google_pubsub_topic.dataflow_deadletter_pubsub_topic.name
45 | role = "roles/pubsub.publisher"
46 | members = [
47 | "serviceAccount:${local.dataflow_worker_service_account}"
48 | ]
49 | }
50 |
51 | resource "google_storage_bucket_iam_binding" "dataflow_worker_bucket_access" {
52 | bucket = google_storage_bucket.dataflow_job_temp_bucket.name
53 | role = "roles/storage.objectAdmin"
54 | members = [
55 | "serviceAccount:${local.dataflow_worker_service_account}"
56 | ]
57 | }
58 |
59 | resource "google_project_iam_binding" "dataflow_worker_role" {
60 | count = (local.grant_service_account_roles == true) ? 1 : 0
61 | project = var.project
62 | role = "roles/dataflow.worker"
63 | members = [
64 | "serviceAccount:${local.dataflow_worker_service_account}"
65 | ]
66 | }
67 |
68 | resource "google_secret_manager_secret_iam_member" "dataflow_worker_secret_access" {
69 | count = (var.splunk_hec_token_source == "SECRET_MANAGER" &&
70 | var.splunk_hec_token_secret_id != "" &&
71 | local.grant_service_account_roles == true) ? 1 : 0
72 | project = var.project
73 | secret_id = local.splunk_hec_token_secret_id # Use secret ID inferred from input secret version ID
74 | role = "roles/secretmanager.secretAccessor"
75 | member = "serviceAccount:${local.dataflow_worker_service_account}"
76 | }
77 |
78 | resource "google_kms_crypto_key_iam_member" "dataflow_worker_kms_access" {
79 | count = (var.splunk_hec_token_source == "KMS" &&
80 | var.splunk_hec_token_kms_encryption_key != "" &&
81 | local.grant_service_account_roles == true) ? 1 : 0
82 | crypto_key_id = var.splunk_hec_token_kms_encryption_key
83 | role = "roles/cloudkms.cryptoKeyDecrypter"
84 | member = "serviceAccount:${local.dataflow_worker_service_account}"
85 | }
86 |
87 | # To deploy Dataflow jobs, terraform caller identity must have permission to impersonate
88 | # worker service account in order to attach that service account to Compute Engine VMs.
89 | # In case of user-managed worker service account, add necessary permission over new service account,
90 | # (id: google_service_account.dataflow_worker_service_account[0].id)
91 | # In case of default worker service account (i.e. Compute Engine default service account), caller
92 | # must have permission to impersonate Compute Engine default service account; otherwise, job
93 | # deployment will return an error. For security purposes, we do not modify access to existing
94 | # default Compute Engine service account
95 | resource "google_service_account_iam_binding" "terraform_caller_impersonate_dataflow_worker" {
96 | count = (local.grant_service_account_impersonation == true) ? 1 : 0
97 | service_account_id = google_service_account.dataflow_worker_service_account[0].id
98 | role = "roles/iam.serviceAccountUser"
99 |
100 | members = [
101 | "user:${data.google_client_openid_userinfo.provider_identity.email}"
102 | ]
103 | }
104 |
--------------------------------------------------------------------------------
/pipeline.tf:
--------------------------------------------------------------------------------
1 | # Copyright 2021 Google LLC
2 | #
3 | # Licensed under the Apache License, Version 2.0 (the "License");
4 | # you may not use this file except in compliance with the License.
5 | # You may obtain a copy of the License at
6 | #
7 | # https://www.apache.org/licenses/LICENSE-2.0
8 | #
9 | # Unless required by applicable law or agreed to in writing, software
10 | # distributed under the License is distributed on an "AS IS" BASIS,
11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 | # See the License for the specific language governing permissions and
13 | # limitations under the License.
14 |
15 |
16 | resource "google_pubsub_topic" "dataflow_deadletter_pubsub_topic" {
17 | project = var.project
18 | name = local.dataflow_output_deadletter_topic_name
19 | }
20 |
21 | resource "google_pubsub_subscription" "dataflow_deadletter_pubsub_sub" {
22 | project = var.project
23 | name = local.dataflow_output_deadletter_sub_name
24 | topic = google_pubsub_topic.dataflow_deadletter_pubsub_topic.name
25 |
26 | # messages retained for 7 days (max)
27 | message_retention_duration = "604800s"
28 |
29 | # subscription never expires
30 | expiration_policy {
31 | ttl = ""
32 | }
33 | }
34 |
35 | resource "google_storage_bucket" "dataflow_job_temp_bucket" {
36 | project = var.project
37 | name = local.dataflow_temporary_gcs_bucket_name
38 | location = var.region
39 | storage_class = "REGIONAL"
40 | uniform_bucket_level_access = true
41 | dynamic "encryption" {
42 | for_each = (var.gcs_kms_key_name == "") ? [] : [1]
43 | content {
44 | default_kms_key_name = var.gcs_kms_key_name
45 | }
46 | }
47 | }
48 |
49 | resource "google_storage_bucket_object" "dataflow_job_temp_object" {
50 | name = local.dataflow_temporary_gcs_bucket_path
51 | content = "Placeholder for Dataflow to write temporary files"
52 | bucket = google_storage_bucket.dataflow_job_temp_bucket.name
53 | }
54 |
55 | resource "google_service_account" "dataflow_worker_service_account" {
56 | count = (var.dataflow_worker_service_account != "" && var.use_externally_managed_dataflow_sa == false) ? 1 : 0
57 | project = var.project
58 | account_id = var.dataflow_worker_service_account
59 | display_name = "Dataflow worker service account to execute pipeline operations"
60 | }
61 |
62 | resource "google_dataflow_job" "dataflow_job" {
63 | project = var.project
64 | name = local.dataflow_main_job_name
65 | template_gcs_path = local.dataflow_splunk_template_gcs_path
66 | temp_gcs_location = "gs://${local.dataflow_temporary_gcs_bucket_name}/${local.dataflow_temporary_gcs_bucket_path}"
67 | service_account_email = local.dataflow_worker_service_account
68 | machine_type = var.dataflow_job_machine_type
69 | max_workers = var.dataflow_job_machine_count
70 | parameters = merge({
71 | inputSubscription = google_pubsub_subscription.dataflow_input_pubsub_subscription.id
72 | outputDeadletterTopic = google_pubsub_topic.dataflow_deadletter_pubsub_topic.id
73 | url = var.splunk_hec_url
74 | parallelism = var.dataflow_job_parallelism
75 | batchCount = var.dataflow_job_batch_count
76 | includePubsubMessage = local.dataflow_job_include_pubsub_message
77 | disableCertificateValidation = var.dataflow_job_disable_certificate_validation
78 | enableBatchLogs = local.dataflow_job_enable_batch_logs # Supported as of 2022-03-21-00_RC01
79 | enableGzipHttpCompression = local.dataflow_job_enable_gzip_http_compression # Supported as of 2022-04-25-00_RC00
80 | tokenSource = var.splunk_hec_token_source # Supported as of 2022-03-14-00_RC00
81 | },
82 | (var.dataflow_job_udf_gcs_path != "" && var.dataflow_job_udf_function_name != "") ?
83 | {
84 | javascriptTextTransformGcsPath = var.dataflow_job_udf_gcs_path
85 | javascriptTextTransformFunctionName = var.dataflow_job_udf_function_name
86 | } : {},
87 | (var.splunk_hec_token_source == "PLAINTEXT") ?
88 | {
89 | token = var.splunk_hec_token
90 | } : {},
91 | (var.splunk_hec_token_source == "KMS") ?
92 | {
93 | token = var.splunk_hec_token
94 | tokenKMSEncryptionKey = var.splunk_hec_token_kms_encryption_key
95 | } : {},
96 | (var.splunk_hec_token_source == "SECRET_MANAGER") ?
97 | {
98 | tokenSecretId = local.splunk_hec_token_secret_version_id # Supported as of 2022-03-14-00_RC00
99 | } : {},
100 | )
101 | region = var.region
102 | network = var.network
103 | subnetwork = "regions/${var.region}/subnetworks/${local.subnet_name}"
104 | ip_configuration = "WORKER_IP_PRIVATE"
105 |
106 | lifecycle {
107 | ignore_changes = [
108 | additional_experiments # Ignore default experiments that may be added by Dataflow templates API
109 | ]
110 | }
111 |
112 | depends_on = [
113 | google_compute_subnetwork.splunk_subnet,
114 | google_storage_bucket_object.dataflow_job_temp_object
115 | ]
116 | }
117 |
--------------------------------------------------------------------------------
/replay.tf:
--------------------------------------------------------------------------------
1 | # Copyright 2021 Google LLC
2 | #
3 | # Licensed under the Apache License, Version 2.0 (the "License");
4 | # you may not use this file except in compliance with the License.
5 | # You may obtain a copy of the License at
6 | #
7 | # https://www.apache.org/licenses/LICENSE-2.0
8 | #
9 | # Unless required by applicable law or agreed to in writing, software
10 | # distributed under the License is distributed on an "AS IS" BASIS,
11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 | # See the License for the specific language governing permissions and
13 | # limitations under the License.
14 |
15 | /*
16 | When the replay job needs to be run, simply run terraform with overriding variable
17 | `terraform apply -var deploy_replay_job="true"` or change the value in tfvars file.
18 | After the deadletter Pub/Sub topic has no more messages, set `deploy_replay_job` value to `false ` and
19 | run a regular terraform deployment (ex. terraform apply).
20 | */
21 |
22 |
23 | resource "google_dataflow_job" "splunk_dataflow_replay" {
24 | count = var.deploy_replay_job == true ? 1 : 0
25 |
26 | project = var.project
27 | name = local.dataflow_replay_job_name
28 | template_gcs_path = local.dataflow_pubsub_template_gcs_path
29 | temp_gcs_location = "gs://${local.dataflow_temporary_gcs_bucket_name}/${local.dataflow_temporary_gcs_bucket_path}"
30 | machine_type = var.dataflow_job_machine_type
31 | max_workers = var.dataflow_job_machine_count
32 | parameters = {
33 | inputSubscription = google_pubsub_subscription.dataflow_deadletter_pubsub_sub.id
34 | outputTopic = google_pubsub_topic.dataflow_input_pubsub_topic.id
35 | }
36 | region = var.region
37 | network = var.network
38 | subnetwork = "regions/${var.region}/subnetworks/${local.subnet_name}"
39 | ip_configuration = "WORKER_IP_PRIVATE"
40 |
41 | on_delete = "cancel"
42 |
43 | lifecycle {
44 | ignore_changes = [
45 | additional_experiments # Ignore default experiments that may be added by Dataflow templates API
46 | ]
47 | }
48 |
49 | depends_on = [
50 | google_compute_subnetwork.splunk_subnet,
51 | google_storage_bucket_object.dataflow_job_temp_object
52 | ]
53 | }
54 |
--------------------------------------------------------------------------------
/sample.tfvars:
--------------------------------------------------------------------------------
1 | # Copyright 2021 Google LLC
2 | #
3 | # Licensed under the Apache License, Version 2.0 (the "License");
4 | # you may not use this file except in compliance with the License.
5 | # You may obtain a copy of the License at
6 | #
7 | # https://www.apache.org/licenses/LICENSE-2.0
8 | #
9 | # Unless required by applicable law or agreed to in writing, software
10 | # distributed under the License is distributed on an "AS IS" BASIS,
11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 | # See the License for the specific language governing permissions and
13 | # limitations under the License.
14 |
15 | project = "[MY_PROJECT]"
16 | region = "[MY_REGION]"
17 |
18 | create_network = false
19 | network = ""
20 | subnet = ""
21 | primary_subnet_cidr = "10.128.0.0/20"
22 |
23 | # Log sink details
24 | log_filter = ""
25 |
26 | # Dataflow job output
27 | splunk_hec_url = ""
28 | splunk_hec_token_source = ""
29 | splunk_hec_token = ""
30 | splunk_hec_token_secret_id = ""
31 | splunk_hec_token_kms_encryption_key = ""
32 |
33 | # Dataflow job parameters
34 | dataflow_worker_service_account = "export-pipeline-worker"
35 | use_externally_managed_dataflow_sa = false
36 | dataflow_job_name = "export-pipeline"
37 | dataflow_job_machine_type = "n1-standard-4"
38 | dataflow_job_machine_count = 2
39 | dataflow_job_parallelism = 16
40 | dataflow_job_batch_count = 10
41 | dataflow_job_disable_certificate_validation = false
42 | dataflow_job_udf_gcs_path = ""
43 | dataflow_job_udf_function_name = ""
44 |
45 | # Dashboard parameters
46 | scoping_project = "[MY_PROJECT]"
47 |
48 | # Replay job settings
49 | deploy_replay_job = false
50 |
--------------------------------------------------------------------------------
/variables.tf:
--------------------------------------------------------------------------------
1 | # Copyright 2021 Google LLC
2 | #
3 | # Licensed under the Apache License, Version 2.0 (the "License");
4 | # you may not use this file except in compliance with the License.
5 | # You may obtain a copy of the License at
6 | #
7 | # https://www.apache.org/licenses/LICENSE-2.0
8 | #
9 | # Unless required by applicable law or agreed to in writing, software
10 | # distributed under the License is distributed on an "AS IS" BASIS,
11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 | # See the License for the specific language governing permissions and
13 | # limitations under the License.
14 |
15 | variable "project" {
16 | type = string
17 | description = "Project ID to deploy resources in"
18 | }
19 |
20 | variable "region" {
21 | type = string
22 | description = "Region to deploy regional-resources into. This must match subnet's region if deploying into existing network (e.g. Shared VPC). See `subnet` parameter below"
23 | }
24 |
25 | variable "create_network" {
26 | description = "Boolean value specifying if a new network needs to be created."
27 | default = false
28 | type = bool
29 | }
30 |
31 | variable "network" {
32 | description = "Network to deploy into"
33 | type = string
34 | }
35 |
36 | variable "subnet" {
37 | type = string
38 | description = "Subnet to deploy into. This is required when deploying into existing network (`create_network=false`) (e.g. Shared VPC)"
39 | default = ""
40 | }
41 |
42 | variable "primary_subnet_cidr" {
43 | type = string
44 | description = "The CIDR Range of the primary subnet"
45 | default = "10.128.0.0/20"
46 | }
47 |
48 | # Dashboard parameters
49 |
50 | variable "scoping_project" {
51 | type = string
52 | description = <<-EOF
53 | Cloud Monitoring scoping project ID to create dashboard under.
54 | This assumes a pre-existing scoping project whose metrics scope contains the `project` where dataflow job is to be deployed.
55 | See [Cloud Monitoring settings](https://cloud.google.com/monitoring/settings) for more details on scoping project.
56 | If parameter is empty, scoping project defaults to value of `project` parameter above.
57 | EOF
58 | default = ""
59 | }
60 |
61 | # Log sink details
62 |
63 | variable "log_filter" {
64 | type = string
65 | description = "Log filter to use when exporting logs"
66 | }
67 |
68 | # Dataflow job output
69 |
70 | variable "splunk_hec_url" {
71 | type = string
72 | description = "Splunk HEC URL to write data to. Example: https://[MY_SPLUNK_IP_OR_FQDN]:8088"
73 |
74 | validation {
75 | condition = can(regex("https?://.*(:[0-9]+)?", var.splunk_hec_url))
76 | error_message = "Splunk HEC url must of the form ://: ."
77 | }
78 | }
79 |
80 | variable "splunk_hec_token_source" {
81 | type = string
82 | default = "PLAINTEXT"
83 | description = "Define in which type HEC token is provided. Possible options: [PLAINTEXT, KMS, SECRET_MANAGER]."
84 |
85 | validation {
86 | condition = contains(["PLAINTEXT", "KMS", "SECRET_MANAGER"], var.splunk_hec_token_source)
87 | error_message = "Valid values for var: dataflow_token_source are ('PLAINTEXT', 'KMS', 'SECRET_MANAGER')."
88 | }
89 | }
90 |
91 | variable "splunk_hec_token" {
92 | type = string
93 | description = "Splunk HEC token. Must be defined if `splunk_hec_token_source` if type of `PLAINTEXT` or `KMS`."
94 | default = ""
95 | sensitive = true
96 | }
97 |
98 | variable "splunk_hec_token_kms_encryption_key" {
99 | type = string
100 | description = "The Cloud KMS key to decrypt the HEC token string. Required if `splunk_hec_token_source` is type of KMS"
101 | default = ""
102 | validation {
103 | condition = can(regex("^projects\\/[^\\n\\r\\/]+\\/locations\\/[^\\n\\r\\/]+\\/keyRings\\/[^\\n\\r\\/]+\\/cryptoKeys\\/[^\\n\\r\\/]+$", var.splunk_hec_token_kms_encryption_key)) || var.splunk_hec_token_kms_encryption_key == ""
104 | error_message = "HEC token encryption key must match rex: '^projects\\/[^\\n\\r\\/]+\\/locations\\/[^\\n\\r\\/]+\\/keyRings\\/[^\\n\\r\\/]+\\/cryptoKeys\\/[^\\n\\r\\/]+$' pattern."
105 | }
106 | }
107 |
108 | # TODO: Make cross variable validation once https://github.com/hashicorp/terraform/issues/25609 is resolved
109 | variable "splunk_hec_token_secret_id" {
110 | type = string
111 | description = "Id of the Secret for Splunk HEC token. Required if `splunk_hec_token_source` is type of SECRET_MANAGER"
112 | default = ""
113 | validation {
114 | condition = can(regex("^projects\\/[^\\n\\r\\/]+\\/secrets\\/[^\\n\\r\\/]+\\/versions\\/[^\\n\\r\\/]+$", var.splunk_hec_token_secret_id)) || var.splunk_hec_token_secret_id == ""
115 | error_message = "HEC token secret id key must match rex: '^projects\\/[^\\n\\r\\/]+\\/secrets\\/[^\\n\\r\\/]+\\/versions\\/[^\\n\\r\\/]+$' pattern."
116 | }
117 | }
118 |
119 | variable "gcs_kms_key_name" {
120 | type = string
121 | description = <