Merge branch 'revert-733ce4aa' into 'master'

Revert merge request !46321

See merge request gitlab-org/gitlab!46409

.gitlab/ci/test-metadata.gitlab-ci.yml

 .tests-metadata-state:
+  variables:
+    TESTS_METADATA_S3_BUCKET: "gitlab-ce-cache"
   before_script:
     - source scripts/utils.sh
   artifacts:

doc/development/testing_guide/ci.md

@@ -6,7 +6,7 @@ Our current CI parallelization setup is as follows:
 
 1. The `retrieve-tests-metadata` job in the `prepare` stage ensures we have a
    `knapsack/report-master.json` file:
-   - The `knapsack/report-master.json` file is fetched from the latest `master` artifacts, if it's not here
+   - The `knapsack/report-master.json` file is fetched from S3, if it's not here
      we initialize the file with `{}`.
 1. Each `[rspec|rspec-ee] [unit|integration|system|geo] n m` job are run with
    `knapsack rspec` and should have an evenly distributed share of tests:
@@ -19,7 +19,7 @@ Our current CI parallelization setup is as follows:
 1. The `update-tests-metadata` job (which only runs on scheduled pipelines for
    [the canonical project](https://gitlab.com/gitlab-org/gitlab) takes all the
    `knapsack/rspec*_pg_*.json` files and merge them all together into a single
-   `knapsack/report-master.json` file that is saved as artifact.
+   `knapsack/report-master.json` file that is then uploaded to S3.
 
 After that, the next pipeline will use the up-to-date `knapsack/report-master.json` file.
 

scripts/rspec_helpers.sh

@@ -4,11 +4,11 @@ function retrieve_tests_metadata() {
   mkdir -p knapsack/ rspec_flaky/ rspec_profiling/
 
   if [[ ! -f "${KNAPSACK_RSPEC_SUITE_REPORT_PATH}" ]]; then
-    wget -O "${KNAPSACK_RSPEC_SUITE_REPORT_PATH}" "https://gitlab.com/gitlab-org/gitlab/-/jobs/artifacts/master/raw/${KNAPSACK_RSPEC_SUITE_REPORT_PATH}?job=retrieve-tests-metadata" || echo "{}" > "${KNAPSACK_RSPEC_SUITE_REPORT_PATH}"
+    wget -O "${KNAPSACK_RSPEC_SUITE_REPORT_PATH}" "http://${TESTS_METADATA_S3_BUCKET}.s3.amazonaws.com/${KNAPSACK_RSPEC_SUITE_REPORT_PATH}" || echo "{}" > "${KNAPSACK_RSPEC_SUITE_REPORT_PATH}"
   fi
 
   if [[ ! -f "${FLAKY_RSPEC_SUITE_REPORT_PATH}" ]]; then
-    wget -O "${FLAKY_RSPEC_SUITE_REPORT_PATH}" "https://gitlab.com/gitlab-org/gitlab/-/jobs/artifacts/master/raw/${FLAKY_RSPEC_SUITE_REPORT_PATH}?job=retrieve-tests-metadata" || echo "{}" > "${FLAKY_RSPEC_SUITE_REPORT_PATH}"
+    wget -O "${FLAKY_RSPEC_SUITE_REPORT_PATH}" "http://${TESTS_METADATA_S3_BUCKET}.s3.amazonaws.com/${FLAKY_RSPEC_SUITE_REPORT_PATH}" || echo "{}" > "${FLAKY_RSPEC_SUITE_REPORT_PATH}"
   fi
 }
 
@@ -16,11 +16,29 @@ function update_tests_metadata() {
   echo "{}" > "${KNAPSACK_RSPEC_SUITE_REPORT_PATH}"
 
   scripts/merge-reports "${KNAPSACK_RSPEC_SUITE_REPORT_PATH}" knapsack/rspec*.json
+  if [[ -n "${TESTS_METADATA_S3_BUCKET}" ]]; then
+    if [[ "$CI_PIPELINE_SOURCE" == "schedule" ]]; then
+      scripts/sync-reports put "${TESTS_METADATA_S3_BUCKET}" "${KNAPSACK_RSPEC_SUITE_REPORT_PATH}"
+    else
+      echo "Not uplaoding report to S3 as the pipeline is not a scheduled one."
+    fi
+  fi
+
   rm -f knapsack/rspec*.json
 
-  export FLAKY_RSPEC_GENERATE_REPORT="true"
   scripts/merge-reports "${FLAKY_RSPEC_SUITE_REPORT_PATH}" rspec_flaky/all_*.json
+
+  export FLAKY_RSPEC_GENERATE_REPORT="true"
   scripts/flaky_examples/prune-old-flaky-examples "${FLAKY_RSPEC_SUITE_REPORT_PATH}"
+
+  if [[ -n ${TESTS_METADATA_S3_BUCKET} ]]; then
+    if [[ "$CI_PIPELINE_SOURCE" == "schedule" ]]; then
+      scripts/sync-reports put "${TESTS_METADATA_S3_BUCKET}" "${FLAKY_RSPEC_SUITE_REPORT_PATH}"
+    else
+      echo "Not uploading report to S3 as the pipeline is not a scheduled one."
+    fi
+  fi
+
   rm -f rspec_flaky/all_*.json rspec_flaky/new_*.json
 
   if [[ "$CI_PIPELINE_SOURCE" == "schedule" ]]; then