An AWS Lambda function that, in partnership with the AWS API Gateway, sends your Travis CI build logs to Papertrail for easy aggregation, search and alerts.
Well, partly for fun. But also because I like having all my logs aggregated to the same place. It makes it simple and easy to search, view, and be alerted of issues in a familiar interface, and I like the simplicity of Papertrail.
Builds will fail on a non-zero exit code, and pass on a zero exit code.
But how often have you had builds pass when they shouldn't? Maybe you forgot to catch a rejected Promise, or maybe you piped output to a command that clobbered your exit code. In those instances, you won't notice a build that should have failed unless you happen to check the logs.
But if the logs are aggregated and you have alerts set up on key terms, you can be alerted anyway.
Or perhaps you want to alerted by outputted 'warning' text in your builds, even though a warning usually isn't enough to fail a build.
Instructions to come.
Instructions to come.
Add the following to your .travis.yml:
notifications:
webhooks:
urls: https://YOUR_API_ID.execute-api.YOUR_REGION.amazonaws.com/API_STAGE/API_ENDPOINT
You don't need to change any of the on_success/on_failure etc. flags from the default, unless you particularly want to only log errors dependent on certain outcomes.
The on_start setting technically isn't supported by this script yet, as the intention is to retrieve and send your job's logs after it has completed. It shouldn't be too hard to expand to cover a live logging scenario beginning at the start, but this will probably mean your Lambda will need to run for the duration of your build. This can both increase your costs, and risk logs being cut off if your job continues longer than your Lambda timeout (the maximum AWS allows is 5 minutes).
You'll probably want to set up Papertrail alerts to make the most of aggregating your build logs there. Think about what you want to keep an eye out for, then do a search for it. Check your results are what you expect, then you can save the search and set up an alert for it.
You can craft your searches to return only the results you want, and exclude those you don't want.
This is my current setting:
( error OR warning ) -'-Werror=format' -'to give useful error messages' -SNIMissingWarning -InsecurePlatformWarning
To run all tests at once:
yarn test
To run:
yarn unit-tests
Unit tests are yet to be written, and will currently just pass.
To run:
yarn docker-tests
Integration tests require Docker. They run in lambci/lambda:nodejs6.10 (GitHub | Docker Hub).
The following environment variables must be defined on your system:
PAPERTRAIL_HOSTPAPERTRAIL_PORTTRAVIS_API_TOKENCI- optional
You can get your Papertrail details from the bar at the top of this page, and your Travis API token from the top left of your profile (if you're using Travis Pro, make sure you get your token from your travis-ci.com profile).
The final CI variable above is optional, but recommended. If set (which it is by default on Travis CI, for instance), it will 1) cause errors to be thrown rather than returned as an API Gateway style response, and 2) only log the final line of the test job rather than all 500-odd lines.
- Complete the instructions in this file.
- Better error handling for when logs are not available and/or stream cannot be read.
- Add proper support for travis-ci.com (passing access token and pro API option to the API wrapper)
- Add unit tests.
- Add webhook verification to ensure it comes from Travis (see here for an example).
This would have taken a lot longer to put together without travis-log-stream. Thanks Julian Gruber!
MIT.