├── .github └── workflows │ ├── publish.yml │ └── test.yml ├── .gitignore ├── Justfile ├── LICENSE ├── README.md ├── build.sh ├── datasette_litestream ├── __init__.py └── templates │ └── litestream.html ├── demo └── metadata.yaml ├── download.sh ├── pyproject.toml ├── pytest.ini └── tests └── test_datasette_litestream.py /.github/workflows/publish.yml: -------------------------------------------------------------------------------- 1 | name: Publish Python Package 2 | 3 | on: 4 | release: 5 | types: [created] 6 | 7 | permissions: 8 | contents: read 9 | 10 | jobs: 11 | test: 12 | if: false 13 | runs-on: ubuntu-latest 14 | strategy: 15 | matrix: 16 | python-version: ["3.9", "3.10", "3.11", "3.12", "3.13"] 17 | steps: 18 | - uses: actions/checkout@v4 19 | - name: Set up Python ${{ matrix.python-version }} 20 | uses: actions/setup-python@v5 21 | with: 22 | python-version: ${{ matrix.python-version }} 23 | cache: pip 24 | cache-dependency-path: setup.py 25 | - name: Install dependencies 26 | run: | 27 | pip install '.[test]' 28 | - name: Run tests 29 | run: | 30 | python -m pytest 31 | deploy: 32 | runs-on: ubuntu-latest 33 | #needs: [test] 34 | steps: 35 | - uses: actions/checkout@v4 36 | - name: Set up Python 37 | uses: actions/setup-python@v5 38 | with: 39 | python-version: "3.13" 40 | cache: pip 41 | cache-dependency-path: setup.py 42 | - name: Install dependencies 43 | run: | 44 | pip install setuptools wheel twine build 45 | - name: Build wheels 46 | run: | 47 | ./download.sh 48 | ./build.sh 49 | - name: Publish 50 | env: 51 | TWINE_USERNAME: __token__ 52 | TWINE_PASSWORD: ${{ secrets.PYPI_TOKEN }} 53 | run: | 54 | python -m build 55 | twine upload dist/* 56 | -------------------------------------------------------------------------------- /.github/workflows/test.yml: -------------------------------------------------------------------------------- 1 | name: Test 2 | 3 | on: [push, pull_request] 4 | 5 | permissions: 6 | contents: read 7 | 8 | jobs: 9 | test: 10 | runs-on: ubuntu-latest 11 | strategy: 12 | matrix: 13 | python-version: ["3.9", "3.10", "3.11", "3.12", "3.13"] 14 | steps: 15 | - uses: actions/checkout@v4 16 | - name: Set up Python ${{ matrix.python-version }} 17 | uses: actions/setup-python@v5 18 | with: 19 | python-version: ${{ matrix.python-version }} 20 | cache: pip 21 | cache-dependency-path: setup.py 22 | - id: cache-litestream 23 | uses: actions/cache@v3 24 | with: 25 | path: $HOME/.local/bin/litestream 26 | key: ${{ runner.os }}-primes 27 | - run: mkdir -p $HOME/.local/bin 28 | - if: steps.cache-litestream.outputs.cache-hit != 'true' 29 | run: curl -L https://github.com/benbjohnson/litestream/releases/download/v0.3.11/litestream-v0.3.11-linux-amd64.tar.gz |tar -xz -C $HOME/.local/bin 30 | - run: echo "$HOME/.local/bin" >> $GITHUB_PATH 31 | - name: Install dependencies 32 | run: | 33 | pip install '.[test]' 34 | - name: Run tests 35 | run: | 36 | python -m pytest 37 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | .venv 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | venv 6 | .eggs 7 | .pytest_cache 8 | *.egg-info 9 | .DS_Store 10 | .vscode 11 | dist 12 | build 13 | 14 | 15 | *.db 16 | *.db-shm 17 | *.db-wal 18 | .env 19 | 20 | *-litestream 21 | *-backup 22 | *.whl 23 | 24 | datasette_litestream/bin/* 25 | tmp/ 26 | 27 | *.tar.gz 28 | -------------------------------------------------------------------------------- /Justfile: -------------------------------------------------------------------------------- 1 | dev: 2 | DATASETTE_SECRET=abc123 watchexec --signal SIGKILL --restart --clear -e py,ts,html,js,css,yaml -- \ 3 | python3 -m datasette --root demo/*.db --metadata=demo/metadata.yaml -p 8002 4 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # datasette-litestream 2 | 3 | [![PyPI](https://img.shields.io/pypi/v/datasette-litestream.svg)](https://pypi.org/project/datasette-litestream/) 4 | [![Changelog](https://img.shields.io/github/v/release/datasette/datasette-litestream?include_prereleases&label=changelog)](https://github.com/datasette/datasette-litestream/releases) 5 | [![Tests](https://github.com/datasette/datasette-litestream/workflows/Test/badge.svg)](https://github.com/datasette/datasette-litestream/actions?query=workflow%3ATest) 6 | [![License](https://img.shields.io/badge/license-Apache%202.0-blue.svg)](https://github.com/datasette/datasette-litestream/blob/main/LICENSE) 7 | 8 | A Datasette <-> Litestream plugin. 9 | 10 | ## Installation 11 | 12 | The plugin requires a recent alpha version of Datasette 1.0, whcih can be installed with: 13 | 14 | pip install datasette==1.0a6 15 | 16 | Then install this plugin in the same environment as Datasette. 17 | 18 | datasette install datasette-litestream 19 | 20 | ## Usage 21 | 22 | ### Replicate a single database to S3 23 | 24 | To replicate `my_database.db` to S3, use the following configuration in your `metadata.yaml` file: 25 | 26 | ```yaml 27 | databases: 28 | my_database: 29 | plugins: 30 | datasette-litestream: 31 | replicas: 32 | - url: s3://my-bucket/my_database 33 | ``` 34 | 35 | Then make sure you export `LITESTREAM_ACCESS_KEY_ID` and `LITESTREAM_SECRET_ACCESS_KEY` with your S3 credentials (or `AWS_ACCESS_KEY_ID` `AWS_SECRET_ACCESS_KEY`), then run with: 36 | 37 | ``` 38 | datasette my_database.db -m metadata.yaml 39 | ``` 40 | 41 | ### Replicate all databases 42 | 43 | If you have multiple attached databases in Datasette and want to replicate all of them, the top-level `all-replicate` key can be used. 44 | 45 | ```yaml 46 | plugins: 47 | datasette-litestream: 48 | all-replicate: 49 | - s3://my-bucket/$DB_NAME 50 | ``` 51 | 52 | When `all-replicate` is used, a new replica URL is generated for each attached database. In this case, if you had a database named `parking_tickets` and another named `city_budget`, then `datasette-litestream` will replicate them to `s3://my-bucket/parking_tickets` and `s3://my-bucket/city_budget`. 53 | 54 | This is done with "variables" that `datasette-litestream` replaces in the `all-replicate` URL. The supported variables are: 55 | 56 | - `$DB_NAME`: The name of the Datasette database to replicate. 57 | - `$DB_DIRECTORY`: The full parent directory that the SQLite database resides. 58 | - `$PWD`: The current working directory of the Datasette process. 59 | 60 | ## Config 61 | 62 | Some configuration in the `metadata.yaml` will be used to auto-generate the [`litestream.yml`](https://litestream.io/reference/config/) file under the hood. You can use this to customize the Litestream replication process. 63 | 64 | ### Top-level 65 | 66 | The following are valid keys that are allowed when specifying top-level plugin configuration: 67 | 68 | - `all-replicate`: A template replica URL used to replicate all attached Datasette databases, see aboce for details. 69 | - `metrics-addr`: Defines the [`addr:` Litestream option](https://litestream.io/reference/config/#metrics), which will expose a Prometheus endpoint at the given URL. Use which caution on public Datasette instances! When defined, the metrics info will appear on the `datasette-litestream` status page. 70 | - `access-key-id`: An alternate way to provide a S3 access key (though the `LITESTREAM_ACCESS_KEY_ID` environment variable is preferred). 71 | - `secret-access-key`: An alternate way to provide a S3 secret key (though the `LITESTREAM_SECRET_ACCESS_KEY` environment variable is preferred). 72 | 73 | None of these keys are required. 74 | 75 | Example: 76 | 77 | ```yaml 78 | plugins: 79 | datasette-litestream: 80 | all-replicate: 81 | - XXX 82 | - YYY 83 | metrics-addr: :5001 84 | access-key-id: $YOUR_KEY 85 | secret-access-key: $YOUR_SECRET 86 | ``` 87 | 88 | ### Database-level 89 | 90 | The following options are allowed on database-level plugin configuration. 91 | 92 | - `replicas` 93 | - `monitor-interval` 94 | - `checkpoint-interval` 95 | - `min-checkpoint-page-count` 96 | - `max-checkpoint-page-count` 97 | 98 | ```yaml 99 | databases: 100 | my_database: 101 | plugins: 102 | datasette-litestream: 103 | replicas: 104 | - s3://... 105 | - file://... 106 | monitor-interval: XXX 107 | checkpoint-interval: XXX 108 | min-checkpoint-page-count: XXX 109 | max-checkpoint-page-count: XXX 110 | ``` 111 | 112 | See [Litestream Database settings](https://litestream.io/reference/config/#database-settings) for more information. 113 | 114 | ## Development 115 | 116 | To set up this plugin locally, first checkout the code. Then create a new virtual environment: 117 | 118 | cd datasette-litestream 119 | python3 -m venv venv 120 | source venv/bin/activate 121 | 122 | Now install the dependencies and test dependencies: 123 | 124 | pip install -e '.[test]' 125 | 126 | To run the tests: 127 | 128 | pytest 129 | -------------------------------------------------------------------------------- /build.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | DATASETTE_LITESTREAM_VERSION="$(python3 -c "import tomllib; print(tomllib.loads(open('pyproject.toml', 'r').read())['project']['version'])")" 4 | 5 | mkdir -p datasette_litestream/bin 6 | 7 | function build_wheel { 8 | cp $1 datasette_litestream/bin/litestream 9 | python3 -m build . --wheel 10 | mv dist/datasette_litestream-*-py3-none-any.whl $2 11 | } 12 | 13 | 14 | build_wheel tmp/litestream-darwin-amd64 "dist/datasette_litestream-$DATASETTE_LITESTREAM_VERSION-py3-none-macosx_10_6_x86_64.whl" 15 | build_wheel tmp/litestream-darwin-arm64 "dist/datasette_litestream-$DATASETTE_LITESTREAM_VERSION-py3-none-macosx_11_0_arm64.whl" 16 | build_wheel tmp/litestream-linux-amd64 "dist/datasette_litestream-$DATASETTE_LITESTREAM_VERSION-py3-none-manylinux1_x86_64.whl" 17 | build_wheel tmp/litestream-linux-arm7 "dist/datasette_litestream-$DATASETTE_LITESTREAM_VERSION-py3-none-linux_armv7l.whl" 18 | build_wheel tmp/litestream-linux-arm64 "dist/datasette_litestream-$DATASETTE_LITESTREAM_VERSION-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl" 19 | 20 | rm datasette_litestream/bin/litestream 21 | python3 -m build . --sdist 22 | 23 | 24 | -------------------------------------------------------------------------------- /datasette_litestream/__init__.py: -------------------------------------------------------------------------------- 1 | from datasette import hookimpl, Permission, Forbidden 2 | from datasette.utils.asgi import Response 3 | from pathlib import Path 4 | import atexit 5 | import httpx 6 | import json 7 | import os 8 | import shutil 9 | import subprocess 10 | import tempfile 11 | import time 12 | import uuid 13 | from prometheus_client.parser import text_string_to_metric_families 14 | 15 | 16 | class LitestreamProcess: 17 | """ """ 18 | 19 | # The underyling subprocess.Popen() that gets kicked off 20 | process = None 21 | 22 | # the litestream.yaml config, as a dict 23 | litestream_config = None 24 | 25 | # Temporary file where the subprocess logs get forwarded too 26 | logfile = None 27 | 28 | # Temporary file where the litestream.yaml gets saved to 29 | configfile = None 30 | 31 | def __init__(self): 32 | self.logfile = tempfile.NamedTemporaryFile(suffix=".log", delete=True) 33 | 34 | def start_replicate(self): 35 | """starts the litestream process with the given config, logging to logfile""" 36 | 37 | litestream_path = resolve_litestream_path() 38 | 39 | self.configfile = tempfile.NamedTemporaryFile(suffix=".yml", delete=False) 40 | 41 | with self.configfile as f: 42 | f.write(bytes(json.dumps(self.litestream_config), "utf-8")) 43 | config_path = Path(f.name) 44 | 45 | self.process = subprocess.Popen( 46 | [litestream_path, "replicate", "-config", str(config_path)], 47 | stderr=self.logfile, 48 | ) 49 | 50 | # wait 500ms to see if there are instant errors (typically config typos) 51 | time.sleep(0.5) 52 | status = self.process.poll() 53 | if status is not None: 54 | logs = open(self.logfile.name, "r").read() 55 | raise Exception( 56 | f"datasette-litestream litestream process failed with return code {status}. Logs:" 57 | + logs 58 | ) 59 | 60 | # Sometimes Popen doesn't die on exit, so explicitly attempt to kill it on proccess exit 61 | def onexit(): 62 | self.process.kill() 63 | Path(self.configfile.name).unlink() 64 | 65 | atexit.register(onexit) 66 | 67 | 68 | # global variable that tracks each datasette-litestream instance. There is usually just 1, 69 | # but in test suites there may be multiple Datasette instances. 70 | # The keys are a UUID generated in the startup hook, values are a LitestreamProcess 71 | processes = {} 72 | 73 | # The uuid generated at startup is stored on the datasette object, stored in this key attr. 74 | # Meant so we can retrieve it in the separate litestream_status route 75 | DATASETTE_LITESTREAM_PROCESS_KEY = "__DATASETTE_LITESTREAM_PROCESS_KEY__" 76 | 77 | 78 | def resolve_litestream_path(): 79 | """resolives the full path to a litestream binary. Hopefully is bundled in the installed wheel""" 80 | 81 | # First try to see if litestream was bundled with that package, in a pre-built wheel 82 | wheel_path = Path(__file__).resolve().parent / "bin" / "litestream" 83 | if wheel_path.exists(): 84 | return str(wheel_path) 85 | 86 | # Fallback to any litestream binary on the system. 87 | executable_path = shutil.which("litestream") 88 | 89 | if executable_path is None: 90 | raise Exception("litestream not found.") 91 | 92 | return str(executable_path) 93 | 94 | 95 | @hookimpl 96 | def register_permissions(datasette): 97 | return [ 98 | Permission( 99 | name="litestream-view-status", 100 | abbr=None, 101 | description="View litestream statistics and status updates.", 102 | takes_database=False, 103 | takes_resource=False, 104 | default=False, 105 | ) 106 | ] 107 | 108 | 109 | @hookimpl 110 | def permission_allowed(actor, action): 111 | # TODO only root can see it? 112 | if action == "litestream-view-status" and actor and actor.get("id") == "root": 113 | return True 114 | 115 | 116 | @hookimpl 117 | def menu_links(datasette, actor): 118 | async def inner(): 119 | if ( 120 | await datasette.permission_allowed( 121 | actor, "litestream-view-status", default=False 122 | ) 123 | # TODO why is this needed? 124 | and datasette.plugin_config("datasette-litestream") is not None 125 | ): 126 | return [ 127 | { 128 | "href": datasette.urls.path("/-/litestream-status"), 129 | "label": "Litestream Status", 130 | }, 131 | ] 132 | 133 | return inner 134 | 135 | 136 | @hookimpl 137 | def startup(datasette): 138 | global processes 139 | 140 | litestream_process = LitestreamProcess() 141 | litestream_process.litestream_config = {"dbs": []} 142 | 143 | plugin_config_top = datasette.plugin_config("datasette-litestream") or {} 144 | 145 | if "access-key-id" in plugin_config_top: 146 | litestream_process.litestream_config["access-key-id"] = plugin_config_top.get( 147 | "access-key-id" 148 | ) 149 | 150 | if "secret-access-key" in plugin_config_top: 151 | litestream_process.litestream_config[ 152 | "secret-access-key" 153 | ] = plugin_config_top.get("secret-access-key") 154 | 155 | if "metrics-addr" in plugin_config_top: 156 | litestream_process.litestream_config["addr"] = plugin_config_top.get( 157 | "metrics-addr" 158 | ) 159 | 160 | all_replicate = plugin_config_top.get("all-replicate") 161 | 162 | for db_name, db in datasette.databases.items(): 163 | if db.path is None: 164 | continue 165 | 166 | db_path = Path(db.path) 167 | 168 | plugin_config_db = datasette.plugin_config( 169 | "datasette-litestream", db_name, fallback=False 170 | ) 171 | 172 | # skip this DB is "all-replicate" was not defined or no db-level config was given 173 | if plugin_config_db is None and all_replicate is None: 174 | continue 175 | 176 | db_litestream_config = { 177 | "path": str(db_path.resolve()), 178 | } 179 | if plugin_config_db is not None: 180 | # TODO restrict the possible keys here. We don't want to plugins to redefine "replicas" or "path" 181 | db_litestream_config = {**db_litestream_config, **plugin_config_db} 182 | 183 | if all_replicate is not None: 184 | for i, template in enumerate(all_replicate): 185 | url = ( 186 | template.replace("$DB_NAME", db_name) 187 | .replace("$DB_DIRECTORY", str(db_path.resolve().parent)) 188 | .replace("$PWD", os.getcwd()) 189 | ) 190 | 191 | if "replicas" in db_litestream_config: 192 | db_litestream_config["replicas"].append( 193 | {"url": url, "name": f"t{i}"} 194 | ) 195 | else: 196 | db_litestream_config["replicas"] = [{"url": url, "name": f"t{i}"}] 197 | 198 | litestream_process.litestream_config["dbs"].append(db_litestream_config) 199 | 200 | # don't run litestream if no top-level or db-level datasette-litestream config was given 201 | if not plugin_config_top and len(litestream_process.litestream_config["dbs"]) == 0: 202 | return 203 | 204 | startup_id = str(uuid.uuid4()) 205 | processes[startup_id] = litestream_process 206 | setattr(datasette, DATASETTE_LITESTREAM_PROCESS_KEY, startup_id) 207 | 208 | litestream_process.start_replicate() 209 | 210 | 211 | @hookimpl 212 | def register_routes(): 213 | return [ 214 | (r"^/-/litestream-status$", litestream_status), 215 | ] 216 | 217 | 218 | async def litestream_status(scope, receive, datasette, request): 219 | if not await datasette.permission_allowed( 220 | request.actor, "litestream-view-status", default=False 221 | ): 222 | raise Forbidden("Permission denied for litestream-view-status") 223 | 224 | startup_id = getattr(datasette, DATASETTE_LITESTREAM_PROCESS_KEY, None) 225 | 226 | if startup_id is None: 227 | return Response.html("

Litestream not running

") 228 | 229 | global proccesses 230 | litestream_process = processes.get(startup_id) 231 | 232 | if litestream_process is None: 233 | return Response.html("

Litestream not running

") 234 | 235 | replica_operations = { 236 | "bytes": [], 237 | "total": [], 238 | } 239 | metrics_by_db = {} 240 | go_stats = {} 241 | 242 | metrics_enabled = litestream_process.litestream_config.get("addr") is not None 243 | 244 | if metrics_enabled: 245 | # litestream metrics give the absolute path to the database, so create a mapping 246 | # to the datasette db names 247 | db_name_lookup = {} 248 | for db_name, db in datasette.databases.items(): 249 | if db.path is None: 250 | continue 251 | db_name_lookup[str(Path(db.path).resolve())] = db_name 252 | 253 | # TODO detect when non-localhost addresses are used 254 | addr = litestream_process.litestream_config.get("addr") 255 | metrics_page = httpx.get(f"http://localhost{addr}/metrics").text 256 | 257 | for family in text_string_to_metric_families(metrics_page): 258 | for sample in family.samples: 259 | # TODO also ??? 260 | if sample.name == "litestream_replica_operation_bytes_total": 261 | replica_operations["bytes"].append({ 262 | **sample.labels, 263 | "value": sample.value, 264 | }) 265 | elif sample.name == "litestream_replica_operation_total": 266 | replica_operations["total"].append({ 267 | **sample.labels, 268 | "value": sample.value, 269 | }) 270 | 271 | elif ( 272 | sample.name.startswith("litestream_") 273 | # litestream_replica_validation_total has `name` and `status` values that I don't understand 274 | and sample.name != "litestream_replica_validation_total" 275 | ): 276 | print(sample.name) 277 | db = db_name_lookup[sample.labels.get("db")] 278 | 279 | if metrics_by_db.get(db) is None: 280 | metrics_by_db[db] = {} 281 | 282 | metrics_by_db[db][sample.name] = sample.value 283 | elif sample.name in ["go_goroutines", "go_threads"]: 284 | go_stats[sample.name] = sample.value 285 | 286 | return Response.html( 287 | await datasette.render_template( 288 | "litestream.html", 289 | context={ 290 | "process": { 291 | "pid": litestream_process.process.pid, 292 | "status": "alive" 293 | if litestream_process.process.poll() is None 294 | else "died", 295 | }, 296 | "logs": open(litestream_process.logfile.name, "r").read(), 297 | "metrics_enabled": metrics_enabled, 298 | # TODO redact credentials if they are in here :( 299 | "litestream_config": json.dumps( 300 | litestream_process.litestream_config, indent=2 301 | ), 302 | "replica_operations": replica_operations, 303 | "metrics_by_db": metrics_by_db, 304 | "go_stats": go_stats, 305 | }, 306 | ) 307 | ) 308 | -------------------------------------------------------------------------------- /datasette_litestream/templates/litestream.html: -------------------------------------------------------------------------------- 1 | {% extends "base.html" %} 2 | 3 | {% block title %}Litestream status{% endblock %} 4 | 5 | {% block extra_head %} 6 | {% endblock %} 7 | 8 | {% block content %} 9 |

Litestream Status

10 | 11 | PID: {{process.get("pid")}} 12 | status: {{process.get("status")}} 13 | 14 |

litestream.yaml Config

15 | 
 16 |   {{ litestream_config }}
 17 |
18 | 19 |

Logs

20 | 
 21 | {{ logs }}
 22 |
23 | 24 | {% if not metrics_enabled %} 25 | WARNING: metrics-addr was not defined, so no litestream metrics are available. 26 | {% else %} 27 |

Metrics

28 | 29 |
Goroutines: {{ go_stats.get("go_goroutines") }}
30 |
Go threads: {{ go_stats.get("go_threads") }}
31 | 32 | 33 | {% if replica_operations.get("bytes") | length > 0 %} 34 | Replica operation bytes 35 | 36 | 37 | 38 | 39 | 40 | 41 | 42 | 43 | 44 | {% for row in replica_operations.get("bytes") %} 45 | 46 | 47 | 48 | 49 | 50 | {% endfor %} 51 | 52 |
OperationReplica TypeBytes
{{ row.get("operation") }}{{ row.get("replica_type") }}{{ row.get("value") }}
53 | {% endif %} 54 | 55 | {% if replica_operations.get("total") | length > 0 %} 56 | Replica total operations 57 | 58 | 59 | 60 | 61 | 62 | 63 | 64 | 65 | 66 | {% for row in replica_operations.get("total") %} 67 | 68 | 69 | 70 | 71 | 72 | {% endfor %} 73 | 74 |
OperationReplica TypeNumber of operations
{{ row.get("operation") }}{{ row.get("replica_type") }}{{ row.get("value") }}
75 | {% endif %} 76 | 77 | {% for db, metrics in metrics_by_db.items() %} 78 |

{{ db }}

79 | 80 | 81 | 82 | 83 | 84 | 85 | 86 | 87 | {% for key, value in metrics.items() %} 88 | 89 | 90 | 91 | 92 | {% endfor %} 93 |
KeyValue
{{ key }}{{ value }}
94 | {% endfor %} 95 | 96 | {% endif %} 97 | 98 | 108 | {% endblock %} 109 | -------------------------------------------------------------------------------- /demo/metadata.yaml: -------------------------------------------------------------------------------- 1 | plugins: 2 | datasette-litestream: 3 | metrics-addr: :9090 4 | all-replicate: 5 | - file://$PWD/$DB-backup 6 | -------------------------------------------------------------------------------- /download.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | set -euo pipefail 3 | 4 | curl -LO https://github.com/benbjohnson/litestream/releases/download/v0.3.11/litestream-v0.3.11-darwin-amd64.zip 5 | curl -LO https://github.com/benbjohnson/litestream/releases/download/v0.3.11/litestream-v0.3.11-darwin-arm64.zip 6 | curl -LO https://github.com/benbjohnson/litestream/releases/download/v0.3.11/litestream-v0.3.11-linux-amd64.tar.gz 7 | curl -LO https://github.com/benbjohnson/litestream/releases/download/v0.3.11/litestream-v0.3.11-linux-arm64.tar.gz 8 | curl -LO https://github.com/benbjohnson/litestream/releases/download/v0.3.11/litestream-v0.3.11-linux-arm7.tar.gz 9 | 10 | unzip -j litestream-v0.3.11-darwin-amd64.zip litestream -d tmp 11 | mv tmp/litestream tmp/litestream-darwin-amd64 12 | unzip -j litestream-v0.3.11-darwin-arm64.zip litestream -d tmp 13 | mv tmp/litestream tmp/litestream-darwin-arm64 14 | tar -xvzf litestream-v0.3.11-linux-amd64.tar.gz -C tmp litestream 15 | mv tmp/litestream tmp/litestream-linux-amd64 16 | tar -xvzf litestream-v0.3.11-linux-arm64.tar.gz -C tmp litestream 17 | mv tmp/litestream tmp/litestream-linux-arm64 18 | tar -xvzf litestream-v0.3.11-linux-arm7.tar.gz -C tmp litestream 19 | mv tmp/litestream tmp/litestream-linux-arm7 20 | 21 | 22 | rm litestream-v0.3.11-darwin-amd64.zip 23 | rm litestream-v0.3.11-darwin-arm64.zip 24 | rm litestream-v0.3.11-linux-amd64.tar.gz 25 | rm litestream-v0.3.11-linux-arm64.tar.gz 26 | rm litestream-v0.3.11-linux-arm7.tar.gz 27 | -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- 1 | [project] 2 | name = "datasette-litestream" 3 | version = "0.0.1a10" 4 | description = "" 5 | readme = "README.md" 6 | authors = [{name = "Alex Garcia"}] 7 | license = {text = "Apache-2.0"} 8 | classifiers = [ 9 | "License :: OSI Approved :: Apache Software License" 10 | ] 11 | dependencies = ["datasette>=1.0a3", "prometheus-client"] 12 | 13 | [project.urls] 14 | Homepage = "https://github.com/datasette/datasette-litestream" 15 | Changelog = "https://github.com/datasette/datasette-litestream/releases" 16 | Issues = "https://github.com/datasette/datasette-litestream/issues" 17 | CI = "https://github.com/datasette/datasette-litestream/actions" 18 | 19 | 20 | [project.entry-points.datasette] 21 | litestream = "datasette_litestream" 22 | 23 | [project.optional-dependencies] 24 | test = ["pytest", "pytest-asyncio"] 25 | 26 | [tool.setuptools.packages.find] 27 | namespaces = false 28 | 29 | [tool.setuptools.package-data] 30 | datasette_litestream = ["bin/*", "templates/*.html"] 31 | -------------------------------------------------------------------------------- /pytest.ini: -------------------------------------------------------------------------------- 1 | [pytest] 2 | asyncio_mode = strict 3 | asyncio_default_fixture_loop_scope = function -------------------------------------------------------------------------------- /tests/test_datasette_litestream.py: -------------------------------------------------------------------------------- 1 | from datasette.app import Datasette 2 | import pytest 3 | import sqlite_utils 4 | from pathlib import Path 5 | import time 6 | 7 | actor_root = {"a": {"id": "root"}} 8 | 9 | 10 | @pytest.fixture 11 | def students_db_path(tmpdir): 12 | path = str(tmpdir / "students.db") 13 | db = sqlite_utils.Database(path) 14 | db["students"].insert_all( 15 | [ 16 | {"name": "alex", "age": 10}, 17 | {"name": "brian", "age": 20}, 18 | {"name": "craig", "age": 30, "[weird (column)]": 1}, 19 | ] 20 | ) 21 | db.execute("create table courses(name text primary key) without rowid") 22 | db["courses"].insert_all( 23 | [ 24 | {"name": "MATH 101"}, 25 | {"name": "MATH 102"}, 26 | ] 27 | ) 28 | return path 29 | 30 | 31 | @pytest.mark.asyncio 32 | async def test_plugin_is_installed(): 33 | datasette = Datasette(memory=True) 34 | response = await datasette.client.get("/-/plugins.json") 35 | assert response.status_code == 200 36 | installed_plugins = {p["name"] for p in response.json()} 37 | assert "datasette-litestream" in installed_plugins 38 | 39 | 40 | @pytest.mark.asyncio 41 | async def test_no_litestream_config(): 42 | datasette = Datasette(memory=True) 43 | 44 | response = await datasette.client.get("/-/litestream-status") 45 | assert response.status_code == 403 46 | 47 | response = await datasette.client.get( 48 | "/-/litestream-status", 49 | cookies={"ds_actor": datasette.sign(actor_root, "actor")}, 50 | ) 51 | assert response.status_code == 200 52 | assert response.text == "

Litestream not running

" 53 | 54 | 55 | @pytest.mark.asyncio 56 | async def test_basic_db_level(students_db_path): 57 | backup_dir = str(Path(students_db_path).parents[0] / "students-backup") 58 | 59 | assert not Path(backup_dir).exists() 60 | 61 | datasette = Datasette( 62 | [students_db_path], 63 | metadata={ 64 | "databases": { 65 | "students": { 66 | "plugins": { 67 | "datasette-litestream": {"replicas": [{"path": backup_dir}]} 68 | } 69 | } 70 | } 71 | }, 72 | ) 73 | 74 | response = await datasette.client.get("/-/litestream-status") 75 | assert response.status_code == 403 76 | 77 | response = await datasette.client.get( 78 | "/-/litestream-status", 79 | cookies={"ds_actor": datasette.sign(actor_root, "actor")}, 80 | ) 81 | assert response.status_code == 200 82 | assert "Litestream status" in response.text 83 | assert ( 84 | "WARNING: metrics-addr was not defined, so no litestream metrics are available." 85 | in response.text 86 | ) 87 | 88 | # have to wait a second for litestream to write the first replica 89 | time.sleep(1) 90 | assert Path(backup_dir).exists() 91 | assert (Path(backup_dir) / "generations").exists() 92 | 93 | 94 | @pytest.mark.asyncio 95 | async def test_metrics(students_db_path): 96 | backup_dir = str(Path(students_db_path).parents[0] / "students-backup") 97 | 98 | assert not Path(backup_dir).exists() 99 | 100 | datasette = Datasette( 101 | [students_db_path], 102 | metadata={ 103 | "plugins": {"datasette-litestream": {"metrics-addr": ":9998"}}, 104 | "databases": { 105 | "students": { 106 | "plugins": { 107 | "datasette-litestream": {"replicas": [{"path": backup_dir}]} 108 | } 109 | } 110 | }, 111 | }, 112 | ) 113 | 114 | response = await datasette.client.get( 115 | "/-/litestream-status", 116 | cookies={"ds_actor": datasette.sign(actor_root, "actor")}, 117 | ) 118 | 119 | assert response.status_code == 200 120 | assert "Litestream status" in response.text 121 | assert "

Metrics

" in response.text 122 | --------------------------------------------------------------------------------