[branch-4.0][test](auth) Move backup auth case to nonConcurrent

[shuke987]

Summary

• Move auth_call/test_ddl_backup_auth.groovy to nonConcurrent on branch-4.0
• Matches the master-side stabilization from [test](auth)Resolve the conflict in the backup auth case #61384 for backup lock contention during the case

Testing

• git diff --check
• Not run locally; regression case requires the branch-4.0 CI regression environment and S3 repository config

[hello-stephen]

Thank you for your contribution to Apache Doris.
Don't know what should be done next? See How to process your PR.

Please clearly describe your PR:

1. What problem was fixed (it's best to include specific error reporting information). How it was fixed.
2. Which behaviors were modified. What was the previous behavior, what is it now, why was it modified, and what possible impacts might there be.
3. What features were added. Why was this function added?
4. Which code was refactored and why was this part of the code refactored?
5. Which functions were optimized and what is the difference before and after the optimization?

[shuke987]

run buildall

[shuke987]

/review

[github-actions]

Review complete. I did not find any issue that needs an inline comment.

Critical checkpoints:

• Changed-file scope: reviewed the only changed file, regression-test/suites/auth_call/test_ddl_backup_auth.groovy.
• Diff behavior: the PR only adds the nonConcurrent suite tag to test_ddl_backup_auth.
• Regression framework: nonConcurrent is parsed from comma-separated tags, maps the suite to SINGLE execution, and keeps it out of the normal parallel path.
• CI selection: the nonConcurrent regression config selects testGroups = "nonConcurrent" and has the S3 repository config defaults needed by this backup/auth case.
• Backport consistency: #61384 made the same tag change on master for the same stabilization reason.
• Duplicate review context: no existing inline review threads or comments were present for this PR.
• User focus: no additional user-provided review focus was specified.
• Validation: git diff --check passed. I did not run the regression case locally because it requires the Doris regression environment and S3 repository credentials/config.

Subagent conclusions:

• optimizer-rewrite: no candidates; convergence round 1 returned NO_NEW_VALUABLE_FINDINGS.
• tests-session-config: no candidates; convergence round 1 returned NO_NEW_VALUABLE_FINDINGS.
• No candidates were accepted, dismissed, or merged as duplicates, and the final proposed inline comment set is empty.

Note: I could not find a repository-local code-review SKILL.md in this checkout after searching before the review, so I followed the review prompt and shared-ledger workflow directly.

[shuke987]

run buildall