proxy: add mcp.backend_depth_limit(int) #1137
Merged
+134
−23
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Outdated suggestions cannot be applied.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.
If a backend has a queue depth limt over this amount, fast-fail any further requests.
A global parallel request limit can mean a single slow or overloaded backend causes the entire proxy to stop working. As a first layer of defence the depth for a particular backend should be capped.
TODO:
- [ ] might add a counter for failed-due-to-bad while I'm in here.- [ ] might also add a tunable for fast-failing while be is connecting/validating. been meaning to do that forever.delaying further TODO's until after the TLS work is in testing.