Add config for request timeout in seconds #1019
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Before or while filing an issue please feel free to join our
slack channel to get in touch with development team, ask questions, find out what's cooking and more!
Issue #, if available:
Description of changes:
Response timeout is documented to be in seconds. However, in the actual code, it's interpreted in minutes.
By the way, TorchServe has the exact same config variable, but it's interpreted in seconds.
For backward compatibility reasons, it feels risky to just change it, since it could theoretically break a bunch of models currently working in production. So, for now, this PR changes the internal logic to process the timeout in seconds, and uses "seconds" in the variable name for all related variables that represent the timeout in seconds. It then adds an extra config with a "_SECONDS" prefix, to give users a way to configure a timeout in seconds (with less than a minute).
We'll probably just change it to work as documented later. But at least this unblocks customers that want a timeout that's less then one minute, which the code before this PR doesn't allow for that at all.
Testing done:
Added a new unit test and verified that the code builds and the unit tests pass.
To run CI tests on your changes refer README.md
By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.