From c14bf3a6606a4c1ccbdea6d9c05b652d41fd167c Mon Sep 17 00:00:00 2001
From: Jelte Fennema <github-tech@jeltef.nl>
Date: Wed, 31 Aug 2022 14:09:39 +0200
Subject: [PATCH] Add a job to CI to check tests for flakyness (#6276)

We have lots of flaky tests in CI and most of these random failures are
very hard/impossible to reproduce locally. This adds a job definition to
CI that allows adding a temporary job to rerun the same test in CI a lot
of times. This will very often reproduce the random failures. If you
then try to change the test or code to fix the random failure, you can
confirm that it's indeed fixed by using this job.

A future improvement to this job would be to run it (or a variant of it)
automatically for every newly added test, and maybe even changed tests.
This is not implemented in this PR.

An example of this job running can be found here:
https://app.circleci.com/pipelines/github/citusdata/citus/26682/workflows/a2638385-35bc-443c-badc-7713a8101313
---
 .circleci/config.yml | 115 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 115 insertions(+)

diff --git a/.circleci/config.yml b/.circleci/config.yml
index b846264e8..bab2abdff 100644
--- a/.circleci/config.yml
+++ b/.circleci/config.yml
@@ -22,6 +22,14 @@ parameters:
   style_checker_tools_version:
     type: string
     default: '0.8.18'
+  flaky_test:
+    type: string
+    default: ''
+  flaky_test_make:
+    type: string
+    default: check-minimal
+
+
 jobs:
   build:
     description: Build the citus extension
@@ -529,9 +537,116 @@ jobs:
           name: install dependencies and run ch_benchmark tests
           no_output_timeout: 20m
 
+  test-flakyness:
+    description: Runs a test multiple times to see if it's flaky
+    parallelism: 32
+    parameters:
+      pg_major:
+        description: 'postgres major version'
+        type: integer
+      image:
+        description: 'docker image to use as for the tests'
+        type: string
+        default: citus/exttester
+      image_tag:
+        description: 'docker image tag to use'
+        type: string
+      make:
+        description: 'make target'
+        type: string
+        default: check-minimal
+      test:
+        description: 'the test that should be run multiple times'
+        type: string
+      runs:
+        description: 'number of times that the test should be run in total'
+        type: integer
+        default: 1600
+    docker:
+      - image: '<< parameters.image >>:<< parameters.image_tag >><< pipeline.parameters.image_suffix >>'
+    working_directory: /home/circleci/project
+    resource_class: small
+    steps:
+      - checkout
+      - attach_workspace:
+          at: .
+      - run:
+          name: 'Install Extension'
+          command: |
+            tar xfv "${CIRCLE_WORKING_DIRECTORY}/install-${PG_MAJOR}.tar" --directory /
+      - run:
+          name: 'Configure'
+          command: |
+            chown -R circleci .
+            gosu circleci ./configure --without-pg-version-check
+      - run:
+          name: 'Enable core dumps'
+          command: |
+            ulimit -c unlimited
+      - run:
+          name: 'Run minimal tests'
+          command: |
+            gosu circleci make -C src/test/regress << parameters.make >> EXTRA_TESTS="$(for i in $(seq << parameters.runs >> | circleci tests split); do echo -n '<< parameters.test >> ' ; done)"
+          no_output_timeout: 2m
+      - run:
+          name: 'Regressions'
+          command: |
+            if [ -f "src/test/regress/regression.diffs" ]; then
+              cat src/test/regress/regression.diffs
+              exit 1
+            fi
+          when: on_fail
+      - run:
+          name: 'Copy coredumps'
+          command: |
+            mkdir -p /tmp/core_dumps
+            if ls core.* 1> /dev/null 2>&1; then
+                cp core.* /tmp/core_dumps
+            fi
+          when: on_fail
+      - store_artifacts:
+          name: 'Save regressions'
+          path: src/test/regress/regression.diffs
+      - store_artifacts:
+          name: 'Save mitmproxy output (failure test specific)'
+          path: src/test/regress/proxy.output
+      - store_artifacts:
+          name: 'Save results'
+          path: src/test/regress/results/
+      - store_artifacts:
+          name: 'Save core dumps'
+          path: /tmp/core_dumps
+      - store_artifacts:
+          name: 'Save coordinator log'
+          path: src/test/regress/tmp_check/master/log
+      - store_artifacts:
+          name: 'Save worker1 log'
+          path: src/test/regress/tmp_check/worker.57637/log
+      - store_artifacts:
+          name: 'Save worker2 log'
+          path: src/test/regress/tmp_check/worker.57638/log
+
 workflows:
   version: 2
+  flaky_test_debugging:
+    when: << pipeline.parameters.flaky_test >>
+    jobs:
+      - build:
+          name: build-flaky-15
+          pg_major: 15
+          image_tag: '<< pipeline.parameters.pg15_version >>'
+
+      - test-flakyness:
+          name: 'test-15_flaky'
+          pg_major: 15
+          image_tag: '<< pipeline.parameters.pg15_version >>'
+          requires: [build-flaky-15]
+          make: '<< pipeline.parameters.flaky_test_make >>'
+          test: '<< pipeline.parameters.flaky_test >>'
+
   build_and_test:
+    when:
+      not: << pipeline.parameters.flaky_test >>
     jobs:
       - build:
           name: build-13