test(e2e): warm up before disruption in streaming-request spec - #2378
Open
elevran wants to merge 1 commit into
Open
test(e2e): warm up before disruption in streaming-request spec#2378elevran wants to merge 1 commit into
elevran wants to merge 1 commit into
Conversation
The streaming-disruption spec sent its first request through a raw, non-retrying client, unlike its sibling specs which warm up via runCompletion first. That first request can race Envoy's initial active health check on the EPP's ext_proc cluster (see llm-d#1961), producing a local no-healthy-upstream reply that the spec misreports as a failed connection. Fixes llm-d#2377 Signed-off-by: Etai Lev Ran <elevran@gmail.com>
github-actions
Bot
added
the
size/XS
This file contains hidden or 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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What type of PR is this?
/kind test
What this PR does / why we need it:
The "A decode pod is killed while a streaming request is in-flight" e2e spec sent its first request through a raw, non-retrying client, unlike its sibling disruption specs, which all warm up via
runCompletionfirst. That first request can race Envoy's initial active health check on the EPP's ext_proc cluster (10s interval, see #1961), producing a local "no healthy upstream" reply that the spec misreports as "streaming request failed to connect."Adds the same pre-disruption warm-up used by the other disruption specs, closing the race by construction instead of adding retry logic to the raw streaming client.
Which issue(s) this PR fixes:
Fixes #2377
Release note (write
NONEif no user-facing change):