DM-47656: Re-enable retries in Prompt Processing fan-out service #19
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
One parameter was missing, and others weren't valid Numpydoc.
Retries are only triggered on HTTP 503, which is sent by Prompt Processing to signal that retries are safe. While most HTTP 502 are retriable in principle, Knative/KEDA has no way of knowing whether there might be conflicts with the APDB or central repo.
Retries are now toggled with an environment variable, so that they can be turned off with a config change. Currently the switch is Knative-only, since PP's signaling will need to be completely rewritten for a non-server architecture.
These responses generally ask for a delay to clear the condition that caused the failure (e.g., a pod or worker restart).
The new log is analogous to the log for first-time requests, just with "initial" replaced with "retried".
kfindeisen
force-pushed
the
tickets/DM-47656
branch
from
7301cd9 to
b72e1c6
Compare
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Outdated suggestions cannot be applied.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.
This PR reactivates the old retry code, and adds support for a config switch and delayed retries.