Repository navigation
Refactor Operator test packages - #12359
Conversation
There was a problem hiding this comment.
Upgrading surefire to fix SUREFIRE-1926.
There was a problem hiding this comment.
This workaround should be no longer needed with the newer surefire version: SUREFIRE-1983.
f6fb64a to
070c956
Compare
There was a problem hiding this comment.
This is to make surefire happy. Without this change it tries to run **.cluster.** tests inside all integration-arquillian modules, even those without tests, so it fails.
|
The failed tests seem to be unrelated to this change. |
|
Thanks for taking care of this @vmuzikar . I have no problem with the "Refactor Operator test packages" applied in this PR. Would you mind separating in 2 PRs:
|
|
@vmuzikar don't take me wrong, I'm ok with it, but, since it's a change that affects the entire project I feel like it needs different reviewers. |
DGuhr
left a comment
There was a problem hiding this comment.
imo it is ok to sneak this bump in here. I checked the tests out locally and ran (parts of) the arq testsuite and the whole quarkus testsuite, no problem there. as the testsuite is green: works for me. but no hard opinions, could also be split up into two. 🤷♂️
andreaTP
left a comment
There was a problem hiding this comment.
Not fussy about separating in 2 PRs. LGTM
There was a problem hiding this comment.
For future reference, I don't have any better proposal now.
But this approach to running all of the tests in the verify phase compromises the speed of running plain unit tests and we might want to re-iterate in the future.
There was a problem hiding this comment.
Yes, and not only unit tests unfortunately. Even the integration tests could be run at test phase. Basically, we need verify only when testing in the "remote" mode (operator deployed in the cluster). Maybe we could introduce some special profile for this scenario.
|
@vmuzikar I'm fine about merging it based on the review here. But we need to rebase/resolve conflicts. |
|
@abstractj Sorry, I was too quick. 🙂 Rebased, let's wait for the CI... |
|
@vmuzikar I still see the conflicts, could you please take a look? |
DGuhr
left a comment
There was a problem hiding this comment.
assuming the tests get green, LGTM (again) ;)
|
@abstractj Sorry, another conflict was caused by merging #12404. Should be good to go now. |
|
@vmuzikar could you please check the test failures? |
|
@abstractj I believe the test errors are unrelated to these changes. |
DGuhr
left a comment
There was a problem hiding this comment.
PR still LGTM.
The test failures should be unrelated. For the undertow-map failure, I added it here: #12445 (pls help me out there in the future ;) )
For the quarkus group 3 failure (https://github.com/keycloak/keycloak/runs/6835918820?check_suite_focus=true#step:8:2059 ) : Should also be unrelated. I've seen this exact test fail pretty often the last days, but not yet in the quarkus testsuite. See also the other comments in #12445, they show the exact same test failing.
Not sure who to reach out to about this test. Ideas are appreciated :)
Closes #12353
The change from failsafe to surefire was motivated by the test classes renaming. It was also a good opportunity to align with rest of the KC project and use surefire.