├── .circleci └── config.yml ├── .dockerignore ├── .gitignore ├── DCO ├── Dockerfile ├── LICENSE ├── Makefile ├── README.md ├── curator.py ├── curator_test.py ├── docker-compose.yaml └── testing └── create_indices.py /.circleci/config.yml: -------------------------------------------------------------------------------- 1 | orbs: 2 | architect: giantswarm/architect@0.4.5 3 | 4 | version: 2.1 5 | jobs: 6 | build: 7 | machine: true 8 | steps: 9 | - checkout 10 | 11 | - run: | 12 | wget -q $(curl -sS -H "Authorization: token $RELEASE_TOKEN" https://api.github.com/repos/giantswarm/architect/releases/tags/v1.0.0 | grep browser_download_url | head -n 1 | cut -d '"' -f 4) 13 | chmod +x ./architect 14 | ./architect version 15 | 16 | - run: make test 17 | - run: ./architect build 18 | - run: ./architect publish --pipeline=false --channels=wip-${CIRCLE_SHA1} 19 | 20 | - store_test_results: 21 | path: /tmp/results 22 | 23 | - persist_to_workspace: 24 | root: . 25 | paths: 26 | - ./curator 27 | - ./architect 28 | 29 | deploy: 30 | machine: true 31 | steps: 32 | - checkout 33 | - attach_workspace: 34 | at: . 35 | - deploy: 36 | command: | 37 | ./architect deploy 38 | 39 | workflows: 40 | build: 41 | jobs: 42 | - build 43 | 44 | # Push to Aliyun should execute without manual approval on master. 45 | - architect/push-to-docker-legacy: 46 | name: push-curator-to-aliyun-master 47 | image: "registry-intl.cn-shanghai.aliyuncs.com/giantswarm/curator" 48 | username_envar: "ALIYUN_USERNAME" 49 | password_envar: "ALIYUN_PASSWORD" 50 | requires: 51 | - build 52 | # Needed to trigger job only on merge to master. 53 | filters: 54 | branches: 55 | only: master 56 | - deploy: 57 | name: deploy 58 | requires: 59 | - push-curator-to-aliyun-master 60 | filters: 61 | branches: 62 | only: master 63 | -------------------------------------------------------------------------------- /.dockerignore: -------------------------------------------------------------------------------- 1 | venv/ 2 | testing/ 3 | .git 4 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | venv/ 2 | *.pyc 3 | -------------------------------------------------------------------------------- /DCO: -------------------------------------------------------------------------------- 1 | Developer Certificate of Origin 2 | Version 1.1 3 | 4 | Copyright (C) 2004, 2006 The Linux Foundation and its contributors. 5 | 660 York Street, Suite 102, 6 | San Francisco, CA 94110 USA 7 | 8 | Everyone is permitted to copy and distribute verbatim copies of this 9 | license document, but changing it is not allowed. 10 | 11 | 12 | Developer's Certificate of Origin 1.1 13 | 14 | By making a contribution to this project, I certify that: 15 | 16 | (a) The contribution was created in whole or in part by me and I 17 | have the right to submit it under the open source license 18 | indicated in the file; or 19 | 20 | (b) The contribution is based upon previous work that, to the best 21 | of my knowledge, is covered under an appropriate open source 22 | license and I have the right under that license to submit that 23 | work with modifications, whether created in whole or in part 24 | by me, under the same open source license (unless I am 25 | permitted to submit under a different license), as indicated 26 | in the file; or 27 | 28 | (c) The contribution was provided directly to me by some other 29 | person who certified (a), (b) or (c) and I have not modified 30 | it. 31 | 32 | (d) I understand and agree that this project and the contribution 33 | are public and that a record of the contribution (including all 34 | personal information I submit with it, including my sign-off) is 35 | maintained indefinitely and may be redistributed consistent with 36 | this project or the open source license(s) involved. 37 | -------------------------------------------------------------------------------- /Dockerfile: -------------------------------------------------------------------------------- 1 | FROM alpine:3.8 2 | 3 | 4 | RUN apk add --no-cache python3 && \ 5 | python3 -m ensurepip && \ 6 | rm -r /usr/lib/python*/ensurepip && \ 7 | pip3 install --upgrade pip setuptools && \ 8 | if [ ! -e /usr/bin/pip ]; then ln -s pip3 /usr/bin/pip ; fi && \ 9 | if [[ ! -e /usr/bin/python ]]; then ln -sf /usr/bin/python3 /usr/bin/python; fi && \ 10 | rm -r /root/.cache 11 | 12 | RUN pip install elasticsearch 13 | 14 | ADD ./curator.py /curator.py 15 | 16 | ENTRYPOINT ["python", "/curator.py"] 17 | -------------------------------------------------------------------------------- /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 2018 Giant Swarm GmbH 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 | -------------------------------------------------------------------------------- /Makefile: -------------------------------------------------------------------------------- 1 | 2 | 3 | test: 4 | python --version 5 | pip install elasticsearch freezegun 6 | # Syntax check 7 | python -m py_compile ./curator.py 8 | python ./curator_test.py 9 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | [![CircleCI](https://circleci.com/gh/giantswarm/curator.svg?style=shield&circle-token=706c3ae485e0c0d5d577eb67af13e67ea1fd90dd)](https://circleci.com/gh/giantswarm/curator) [![Docker Repository on Quay](https://quay.io/repository/giantswarm/curator/status "Docker Repository on Quay")](https://quay.io/repository/giantswarm/curator) 2 | 3 | # Curator for Elasticsearch 4 | 5 | Simplistic cousin of [Elasticsearch curator](https://github.com/elastic/curator), 6 | created for one purpose only: Delete log indices created by fluentd which are 7 | older than a certain number of days. 8 | 9 | ## Configuration 10 | 11 | The following environment variables can be used for configuration: 12 | 13 | - `ELASTICSEARCH_HOST`: Name of the host that's running elasticsearch (default: `elasticsearch:9200`) 14 | - `RETENTION_DAYS`: Number of days to keep indices for (default: `14`) 15 | - `INDEX_NAME_PREFIX`: Name prefix of the temporal index (default: `fluentd-`). This can also be a space-separated list of names, which means that there are several indexes per temporal unit. 16 | - `INDEX_NAME_TIMEFORMAT`: Temporal string format in the index name (default: `%Y.%m.%d`) 17 | -------------------------------------------------------------------------------- /curator.py: -------------------------------------------------------------------------------- 1 | # coding: utf8 2 | 3 | from datetime import date 4 | from datetime import timedelta 5 | from elasticsearch import Elasticsearch 6 | import json 7 | import os 8 | import sys 9 | 10 | # read environment variables 11 | elasticsearch_host = os.getenv("ELASTICSEARCH_HOST", "elasticsearch:9200") 12 | retention_days = int(os.getenv("RETENTION_DAYS", "14")) 13 | index_name_prefix = os.getenv("INDEX_NAME_PREFIX", "fluentd- gslogs-") 14 | index_name_timeformat = os.getenv("INDEX_NAME_TIMEFORMAT", "%Y.%m.%d") 15 | 16 | 17 | def log(level="info", message="", extra=None): 18 | """ 19 | Prints a JSON-formatted log message 20 | """ 21 | msg = { 22 | "level": level, 23 | "message": message 24 | } 25 | if extra is not None: 26 | msg["extra"] = extra 27 | print(json.dumps(msg)) 28 | 29 | 30 | def get_valid_indices(nameprefix, retention_days, timeformat): 31 | """ 32 | Returns a set of valid index names to keep 33 | """ 34 | out = set() 35 | for n in range(retention_days): 36 | today = date.today() - timedelta(days=n) 37 | index_name_format = nameprefix + timeformat 38 | string = today.strftime(index_name_format) 39 | out.add(string) 40 | return out 41 | 42 | 43 | def main(): 44 | global index_name_prefix 45 | global retention_days 46 | global index_name_timeformat 47 | global elasticsearch_host 48 | 49 | # Initial validation 50 | 51 | if retention_days < 1: 52 | log("error", "Retention period in days is too short (RETENTION_DAYS=%d)" % retention_days) 53 | sys.exit(1) 54 | 55 | if index_name_prefix == "": 56 | log("error", "Index name prefix is empty (INDEX_NAME_PREFIX='')") 57 | sys.exit(1) 58 | 59 | if index_name_timeformat == "": 60 | log("error", "Index name time format is empty (INDEX_NAME_TIMEFORMAT='')") 61 | sys.exit(1) 62 | 63 | if elasticsearch_host == "": 64 | log("error", "Elasticsearch host is empty (ELASTICSEARCH_HOST='')") 65 | sys.exit(1) 66 | 67 | # index name prefixes from space-separated string 68 | index_name_prefix_list = index_name_prefix.split() 69 | 70 | for index_name_prefix in index_name_prefix_list: 71 | 72 | log("info", "Removing indices with name format '{prefix}{timeformat}' older than {days} days from host '{host}'".format( 73 | prefix=index_name_prefix, 74 | timeformat=index_name_timeformat, 75 | days=retention_days, 76 | host=elasticsearch_host, 77 | )) 78 | 79 | # Create a set of names with index names that should be kept for now 80 | valid = get_valid_indices(index_name_prefix, retention_days, index_name_timeformat) 81 | if len(valid) == 0: 82 | log("error", "The current index name settings yield no index names to retain") 83 | sys.exit(1) 84 | 85 | try: 86 | es = Elasticsearch([elasticsearch_host]) 87 | except Exception as e: 88 | log("error", "Could not connect to elasticsearch", extra={ 89 | "exception": e 90 | }) 91 | sys.exit(1) 92 | 93 | searchterm = index_name_prefix + "*" 94 | 95 | try: 96 | indices = es.indices.get(searchterm) 97 | except Exception as e: 98 | log("error", "Could not list indices for '%s'" % searchterm, extra={ 99 | "exception": e 100 | }) 101 | sys.exit(1) 102 | 103 | if len(indices) == 0: 104 | log("info", "No indices found") 105 | sys.exit() 106 | 107 | for index in es.indices.get(searchterm): 108 | if index not in valid: 109 | try: 110 | es.indices.delete(index=index) 111 | log("info", "Deleted index %s" % index) 112 | except Exception as e: 113 | log("error", "Error deleting index '%s'" % index, extra={ 114 | "exception": e 115 | }) 116 | 117 | 118 | if __name__ == "__main__": 119 | main() 120 | -------------------------------------------------------------------------------- /curator_test.py: -------------------------------------------------------------------------------- 1 | from curator import get_valid_indices 2 | from freezegun import freeze_time 3 | import unittest 4 | 5 | class TestMethods(unittest.TestCase): 6 | 7 | @freeze_time("2018-01-01") 8 | def test_get_valid_indices(self): 9 | # this is how our result should look like 10 | inset = set(["foo-2018.01.01", "foo-2017.12.31", "foo-2017.12.30"]) 11 | outset = get_valid_indices("foo-", 3, "%Y.%m.%d") 12 | self.assertEqual(inset, outset) 13 | 14 | 15 | if __name__ == '__main__': 16 | unittest.main() 17 | -------------------------------------------------------------------------------- /docker-compose.yaml: -------------------------------------------------------------------------------- 1 | version: "3" 2 | 3 | services: 4 | 5 | elasticsearch: 6 | image: quay.io/giantswarm/elasticsearch-oss:6.1.1 7 | ports: 8 | - 9200:9200 9 | 10 | curator: 11 | build: . 12 | image: quay.io/giantswarm/curator:latest 13 | depends_on: 14 | - elasticsearch 15 | -------------------------------------------------------------------------------- /testing/create_indices.py: -------------------------------------------------------------------------------- 1 | # coding: utf8 2 | 3 | # This script creates a bunch of indices in elasticsearch 4 | 5 | import elasticsearch 6 | from datetime import timedelta 7 | from datetime import date 8 | from elasticsearch import Elasticsearch 9 | 10 | 11 | es = Elasticsearch(["localhost:9200"]) 12 | 13 | try: 14 | es.indices.create(index=".kibana") 15 | except: 16 | pass 17 | 18 | for n in range(30): 19 | today = date.today() - timedelta(days=n) 20 | string = today.strftime("fluentd-%Y.%m.%d") 21 | print(string) 22 | try: 23 | es.indices.create(index=string) 24 | except: 25 | pass 26 | --------------------------------------------------------------------------------