Bump Citus version to 11.0.3

(cherry picked from commit c33915c3e6)

.circleci/config.yml

@@ -0,0 +1,805 @@
+version: 2.1
+orbs:
+  codecov: codecov/codecov@1.1.1
+  azure-cli: circleci/azure-cli@1.0.0
+
+parameters:
+  image_suffix:
+    type: string
+    default: '-vabaecad'
+  pg13_version:
+    type: string
+    default: '13.4'
+  pg14_version:
+    type: string
+    default: '14.0'
+  upgrade_pg_versions:
+    type: string
+    default: '13.4-14.0'
+jobs:
+  build:
+    description: Build the citus extension
+    parameters:
+      pg_major:
+        description: postgres major version building citus for
+        type: integer
+      image:
+        description: docker image to use for the build
+        type: string
+        default: citus/extbuilder
+      image_tag:
+        description: tag to use for the docker image
+        type: string
+    docker:
+      - image: '<< parameters.image >>:<< parameters.image_tag >><< pipeline.parameters.image_suffix >>'
+    steps:
+      - checkout
+      - run:
+          name: 'Configure, Build, and Install'
+          command: |
+            ./ci/build-citus.sh
+      - persist_to_workspace:
+          root: .
+          paths:
+            - build-<< parameters.pg_major >>/*
+            - install-<<parameters.pg_major >>.tar
+
+  check-style:
+    docker:
+      - image: 'citus/stylechecker:latest'
+    steps:
+      - checkout
+      - run:
+          name: 'Check Style'
+          command: citus_indent --check
+      - run:
+          name: 'Fix whitespace'
+          command: ci/editorconfig.sh && git diff --exit-code
+      - run:
+          name: 'Remove useless declarations'
+          command: ci/remove_useless_declarations.sh && git diff --cached --exit-code
+      - run:
+          name: 'Normalize test output'
+          command: ci/normalize_expected.sh && git diff --exit-code
+      - run:
+          name: 'Check for C-style comments in migration files'
+          command: ci/disallow_c_comments_in_migrations.sh && git diff --exit-code
+      - run:
+          name: 'Check for comment--cached ns that start with # character in spec files'
+          command: ci/disallow_hash_comments_in_spec_files.sh && git diff --exit-code
+      - run:
+          name: 'Check for gitignore entries .for source files'
+          command: ci/fix_gitignore.sh && git diff --exit-code
+      - run:
+          name: 'Check for lengths of changelog entries'
+          command: ci/disallow_long_changelog_entries.sh
+      - run:
+          name: 'Check for banned C API usage'
+          command: ci/banned.h.sh
+      - run:
+          name: 'Check for tests missing in schedules'
+          command: ci/check_all_tests_are_run.sh
+      - run:
+          name: 'Check if all CI scripts are actually run'
+          command: ci/check_all_ci_scripts_are_run.sh
+      - run:
+          name: 'Check if all GUCs are sorted alphabetically'
+          command: ci/check_gucs_are_alphabetically_sorted.sh
+
+  check-sql-snapshots:
+    docker:
+      - image: 'citus/extbuilder:latest'
+    steps:
+      - checkout
+      - run:
+          name: 'Check Snapshots'
+          command: ci/check_sql_snapshots.sh
+
+  test-pg-upgrade:
+    description: Runs postgres upgrade tests
+    parameters:
+      old_pg_major:
+        description: 'postgres major version to use before the upgrade'
+        type: integer
+      new_pg_major:
+        description: 'postgres major version to upgrade to'
+        type: integer
+      image:
+        description: 'docker image to use as for the tests'
+        type: string
+        default: citus/pgupgradetester
+      image_tag:
+        description: 'docker image tag to use'
+        type: string
+        default: 12-13
+    docker:
+      - image: '<< parameters.image >>:<< parameters.image_tag >><< pipeline.parameters.image_suffix >>'
+    working_directory: /home/circleci/project
+    steps:
+      - checkout
+      - attach_workspace:
+          at: .
+      - run:
+          name: 'Install Extension'
+          command: |
+            tar xfv "${CIRCLE_WORKING_DIRECTORY}/install-<< parameters.old_pg_major >>.tar" --directory /
+            tar xfv "${CIRCLE_WORKING_DIRECTORY}/install-<< parameters.new_pg_major >>.tar" --directory /
+      - run:
+          name: 'Configure'
+          command: |
+            chown -R circleci .
+            gosu circleci ./configure
+      - run:
+          name: 'Enable core dumps'
+          command: |
+            ulimit -c unlimited
+      - run:
+          name: 'Install and test postgres upgrade'
+          command: |
+            gosu circleci \
+              make -C src/test/regress \
+                check-pg-upgrade \
+                old-bindir=/usr/lib/postgresql/<< parameters.old_pg_major >>/bin \
+                new-bindir=/usr/lib/postgresql/<< parameters.new_pg_major >>/bin
+          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
+      - run:
+          name: 'Copy pg_upgrade logs for newData dir'
+          command: |
+            mkdir -p /tmp/pg_upgrade_newData_logs
+            if ls src/test/regress/tmp_upgrade/newData/*.log 1> /dev/null 2>&1; then
+                cp src/test/regress/tmp_upgrade/newData/*.log /tmp/pg_upgrade_newData_logs
+            fi
+          when: on_fail
+      - store_artifacts:
+          name: 'Save regressions'
+          path: src/test/regress/regression.diffs
+      - store_artifacts:
+          name: 'Save core dumps'
+          path: /tmp/core_dumps
+      - store_artifacts:
+          name: 'Save pg_upgrade logs for newData dir'
+          path: /tmp/pg_upgrade_newData_logs
+      - codecov/upload:
+          flags: 'test_<< parameters.old_pg_major >>_<< parameters.new_pg_major >>,upgrade'
+
+  test-arbitrary-configs:
+    description: Runs tests on arbitrary configs
+    parallelism: 6
+    parameters:
+      pg_major:
+        description: 'postgres major version to use'
+        type: integer
+      image:
+        description: 'docker image to use as for the tests'
+        type: string
+        default: citus/failtester
+      image_tag:
+        description: 'docker image tag to use'
+        type: string
+        default: 12-13
+    docker:
+      - image: '<< parameters.image >>:<< parameters.image_tag >><< pipeline.parameters.image_suffix >>'
+    resource_class: xlarge
+    working_directory: /home/circleci/project
+    steps:
+      - checkout
+      - attach_workspace:
+          at: .
+      - run:
+          name: 'Install Extension'
+          command: |
+            tar xfv "${CIRCLE_WORKING_DIRECTORY}/install-<< parameters.pg_major >>.tar" --directory /
+      - run:
+          name: 'Configure'
+          command: |
+            chown -R circleci .
+            gosu circleci ./configure
+      - run:
+          name: 'Enable core dumps'
+          command: |
+            ulimit -c unlimited
+      - run:
+          name: 'Test arbitrary configs'
+          command: |
+            TESTS=$(src/test/regress/citus_tests/print_test_names.py | circleci tests split)
+            # Our test suite expects comma separated values
+            TESTS=$(echo $TESTS | tr ' ' ',')
+            # TESTS will contain subset of configs that will be run on a container and we use multiple containers
+            # to run the test suite
+            gosu circleci \
+              make -C src/test/regress \
+                check-arbitrary-configs parallel=4 CONFIGS=$TESTS
+          no_output_timeout: 2m
+      - run:
+          name: 'Show regressions'
+          command: |
+            find src/test/regress/tmp_citus_test/ -name "regression*.diffs" -exec cat {} +
+            lines=$(find src/test/regress/tmp_citus_test/ -name "regression*.diffs" | wc -l)
+            if [ $lines -ne 0 ]; then
+               exit 1
+            fi
+
+          when: on_fail
+      - run:
+          name: 'Copy logfiles'
+          command: |
+            mkdir src/test/regress/tmp_citus_test/logfiles
+            find src/test/regress/tmp_citus_test/ -name "logfile_*" -exec cp -t src/test/regress/tmp_citus_test/logfiles/ {} +
+          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 core dumps'
+          path: /tmp/core_dumps
+      - store_artifacts:
+          name: 'Save logfiles'
+          path: src/test/regress/tmp_citus_test/logfiles
+      - codecov/upload:
+          flags: 'test_<< parameters.pg_major >>,upgrade'
+
+  test-citus-upgrade:
+    description: Runs citus upgrade tests
+    parameters:
+      pg_major:
+        description: 'postgres major version'
+        type: integer
+      image:
+        description: 'docker image to use as for the tests'
+        type: string
+        default: citus/citusupgradetester
+      image_tag:
+        description: 'docker image tag to use'
+        type: string
+    docker:
+      - image: '<< parameters.image >>:<< parameters.image_tag >><< pipeline.parameters.image_suffix >>'
+    working_directory: /home/circleci/project
+    steps:
+      - checkout
+      - attach_workspace:
+          at: .
+      - run:
+          name: 'Configure'
+          command: |
+            chown -R circleci .
+            gosu circleci ./configure
+      - run:
+          name: 'Enable core dumps'
+          command: |
+            ulimit -c unlimited
+      - run:
+          name: 'Install and test citus upgrade'
+          command: |
+            # run make check-citus-upgrade for all citus versions
+            # the image has ${CITUS_VERSIONS} set with all verions it contains the binaries of
+            for citus_version in ${CITUS_VERSIONS}; do \
+              gosu circleci \
+                make -C src/test/regress \
+                  check-citus-upgrade \
+                  bindir=/usr/lib/postgresql/${PG_MAJOR}/bin \
+                  citus-old-version=${citus_version} \
+                  citus-pre-tar=/install-pg${PG_MAJOR}-citus${citus_version}.tar \
+                  citus-post-tar=/home/circleci/project/install-$PG_MAJOR.tar; \
+            done;
+
+            # run make check-citus-upgrade-mixed for all citus versions
+            # the image has ${CITUS_VERSIONS} set with all verions it contains the binaries of
+            for citus_version in ${CITUS_VERSIONS}; do \
+              gosu circleci \
+                make -C src/test/regress \
+                  check-citus-upgrade-mixed \
+                  citus-old-version=${citus_version} \
+                  bindir=/usr/lib/postgresql/${PG_MAJOR}/bin \
+                  citus-pre-tar=/install-pg${PG_MAJOR}-citus${citus_version}.tar \
+                  citus-post-tar=/home/circleci/project/install-$PG_MAJOR.tar; \
+            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 core dumps'
+          path: /tmp/core_dumps
+      - codecov/upload:
+          flags: 'test_<< parameters.pg_major >>,upgrade'
+
+  test-citus:
+    description: Runs the common tests of citus
+    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
+    docker:
+      - image: '<< parameters.image >>:<< parameters.image_tag >><< pipeline.parameters.image_suffix >>'
+    working_directory: /home/circleci/project
+    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
+      - run:
+          name: 'Enable core dumps'
+          command: |
+            ulimit -c unlimited
+      - run:
+          name: 'Run Test'
+          command: |
+            gosu circleci make -C src/test/regress << parameters.make >>
+          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
+      - codecov/upload:
+          flags: 'test_<< parameters.pg_major >>,<< parameters.make >>'
+          when: always
+
+  tap-test-citus:
+    description: Runs tap tests for citus
+    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
+      suite:
+        description: 'name of the tap test suite to run'
+        type: string
+      make:
+        description: 'make target'
+        type: string
+        default: installcheck
+    docker:
+      - image: '<< parameters.image >>:<< parameters.image_tag >><< pipeline.parameters.image_suffix >>'
+    working_directory: /home/circleci/project
+    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
+      - run:
+          name: 'Enable core dumps'
+          command: |
+            ulimit -c unlimited
+      - run:
+          name: 'Run Test'
+          command: |
+            gosu circleci make -C src/test/<< parameters.suite >> << parameters.make >>
+          no_output_timeout: 2m
+      - 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 tap logs'
+          path: /home/circleci/project/src/test/<< parameters.suite >>/tmp_check/log
+      - store_artifacts:
+          name: 'Save core dumps'
+          path: /tmp/core_dumps
+      - codecov/upload:
+          flags: 'test_<< parameters.pg_major >>,tap_<< parameters.suite >>_<< parameters.make >>'
+          when: always
+
+  check-merge-to-enterprise:
+    docker:
+      - image: citus/extbuilder:<< pipeline.parameters.pg13_version >>
+    working_directory: /home/circleci/project
+    steps:
+      - checkout
+      - run:
+          command: |
+            ci/check_enterprise_merge.sh
+
+  ch_benchmark:
+    docker:
+      - image: buildpack-deps:stretch
+    working_directory: /home/circleci/project
+    steps:
+      - checkout
+      - azure-cli/install
+      - azure-cli/login-with-service-principal
+      - run:
+          command: |
+            cd ./src/test/hammerdb
+            sh run_hammerdb.sh citusbot_ch_benchmark_rg
+          name: install dependencies and run ch_benchmark tests
+          no_output_timeout: 20m
+
+  tpcc_benchmark:
+    docker:
+      - image: buildpack-deps:stretch
+    working_directory: /home/circleci/project
+    steps:
+      - checkout
+      - azure-cli/install
+      - azure-cli/login-with-service-principal
+      - run:
+          command: |
+            cd ./src/test/hammerdb
+            sh run_hammerdb.sh citusbot_tpcc_benchmark_rg
+          name: install dependencies and run ch_benchmark tests
+          no_output_timeout: 20m
+
+workflows:
+  version: 2
+  build_and_test:
+    jobs:
+      - build:
+          name: build-13
+          pg_major: 13
+          image_tag: '<< pipeline.parameters.pg13_version >>'
+      - build:
+          name: build-14
+          pg_major: 14
+          image_tag: '<< pipeline.parameters.pg14_version >>'
+
+      - check-style
+      - check-sql-snapshots
+
+      - test-citus:
+          name: 'test-13_check-multi'
+          pg_major: 13
+          image_tag: '<< pipeline.parameters.pg13_version >>'
+          make: check-multi
+          requires: [build-13]
+      - test-citus:
+          name: 'test-13_check-multi-1'
+          pg_major: 13
+          image_tag: '<< pipeline.parameters.pg13_version >>'
+          make: check-multi-1
+          requires: [build-13]
+      - test-citus:
+          name: 'test-13_check-mx'
+          pg_major: 13
+          image_tag: '<< pipeline.parameters.pg13_version >>'
+          make: check-multi-mx
+          requires: [build-13]
+      - test-citus:
+          name: 'test-13_check-vanilla'
+          pg_major: 13
+          image_tag: '<< pipeline.parameters.pg13_version >>'
+          make: check-vanilla
+          requires: [build-13]
+      - test-citus:
+          name: 'test-13_check-isolation'
+          pg_major: 13
+          image_tag: '<< pipeline.parameters.pg13_version >>'
+          make: check-isolation
+          requires: [build-13]
+      - test-citus:
+          name: 'test-13_check-worker'
+          pg_major: 13
+          image_tag: '<< pipeline.parameters.pg13_version >>'
+          make: check-worker
+          requires: [build-13]
+      - test-citus:
+          name: 'test-13_check-operations'
+          pg_major: 13
+          image_tag: '<< pipeline.parameters.pg13_version >>'
+          make: check-operations
+          requires: [build-13]
+      - test-citus:
+          name: 'test-13_check-follower-cluster'
+          pg_major: 13
+          image_tag: '<< pipeline.parameters.pg13_version >>'
+          make: check-follower-cluster
+          requires: [build-13]
+      - test-citus:
+          name: 'test-13_check-columnar'
+          pg_major: 13
+          image_tag: '<< pipeline.parameters.pg13_version >>'
+          make: check-columnar
+          requires: [build-13]
+      - test-citus:
+          name: 'test-13_check-columnar-isolation'
+          pg_major: 13
+          image_tag: '<< pipeline.parameters.pg13_version >>'
+          make: check-columnar-isolation
+          requires: [build-13]
+      - tap-test-citus:
+          name: 'test_13_tap-recovery'
+          pg_major: 13
+          image_tag: '<< pipeline.parameters.pg13_version >>'
+          suite: recovery
+          requires: [build-13]
+      - tap-test-citus:
+          name: 'test-13_tap-columnar-freezing'
+          pg_major: 13
+          image_tag: '<< pipeline.parameters.pg13_version >>'
+          suite: columnar_freezing
+          requires: [build-13]
+      - test-citus:
+          name: 'test-13_check-failure'
+          pg_major: 13
+          image: citus/failtester
+          image_tag: '<< pipeline.parameters.pg13_version >>'
+          make: check-failure
+          requires: [build-13]
+
+      - test-citus:
+          name: 'test-13_check-enterprise'
+          pg_major: 13
+          image_tag: '<< pipeline.parameters.pg13_version >>'
+          make: check-enterprise
+          requires: [build-13]
+      - test-citus:
+          name: 'test-13_check-enterprise-isolation'
+          pg_major: 13
+          image_tag: '<< pipeline.parameters.pg13_version >>'
+          make: check-enterprise-isolation
+          requires: [build-13]
+      - test-citus:
+          name: 'test-13_check-enterprise-isolation-logicalrep-1'
+          pg_major: 13
+          image_tag: '<< pipeline.parameters.pg13_version >>'
+          make: check-enterprise-isolation-logicalrep-1
+          requires: [build-13]
+      - test-citus:
+          name: 'test-13_check-enterprise-isolation-logicalrep-2'
+          pg_major: 13
+          image_tag: '<< pipeline.parameters.pg13_version >>'
+          make: check-enterprise-isolation-logicalrep-2
+          requires: [build-13]
+      - test-citus:
+          name: 'test-13_check-enterprise-isolation-logicalrep-3'
+          pg_major: 13
+          image_tag: '<< pipeline.parameters.pg13_version >>'
+          make: check-enterprise-isolation-logicalrep-3
+          requires: [build-13]
+      - test-citus:
+          name: 'test-13_check-enterprise-failure'
+          pg_major: 13
+          image: citus/failtester
+          image_tag: '<< pipeline.parameters.pg13_version >>'
+          make: check-enterprise-failure
+          requires: [build-13]
+
+      - test-citus:
+          name: 'test-14_check-enterprise'
+          pg_major: 14
+          image_tag: '<< pipeline.parameters.pg14_version >>'
+          make: check-enterprise
+          requires: [build-14]
+      - test-citus:
+          name: 'test-14_check-enterprise-isolation'
+          pg_major: 14
+          image_tag: '<< pipeline.parameters.pg14_version >>'
+          make: check-enterprise-isolation
+          requires: [build-14]
+      - test-citus:
+          name: 'test-14_check-enterprise-isolation-logicalrep-1'
+          pg_major: 14
+          image_tag: '<< pipeline.parameters.pg14_version >>'
+          make: check-enterprise-isolation-logicalrep-1
+          requires: [build-14]
+      - test-citus:
+          name: 'test-14_check-enterprise-isolation-logicalrep-2'
+          pg_major: 14
+          image_tag: '<< pipeline.parameters.pg14_version >>'
+          make: check-enterprise-isolation-logicalrep-2
+          requires: [build-14]
+      - test-citus:
+          name: 'test-14_check-enterprise-isolation-logicalrep-3'
+          pg_major: 14
+          image_tag: '<< pipeline.parameters.pg14_version >>'
+          make: check-enterprise-isolation-logicalrep-3
+          requires: [build-14]
+      - test-citus:
+          name: 'test-14_check-enterprise-failure'
+          pg_major: 14
+          image: citus/failtester
+          image_tag: '<< pipeline.parameters.pg14_version >>'
+          make: check-enterprise-failure
+          requires: [build-14]
+      - test-citus:
+          name: 'test-14_check-multi'
+          pg_major: 14
+          image_tag: '<< pipeline.parameters.pg14_version >>'
+          make: check-multi
+          requires: [build-14]
+      - test-citus:
+          name: 'test-14_check-multi-1'
+          pg_major: 14
+          image_tag: '<< pipeline.parameters.pg14_version >>'
+          make: check-multi-1
+          requires: [build-14]
+      - test-citus:
+          name: 'test-14_check-mx'
+          pg_major: 14
+          image_tag: '<< pipeline.parameters.pg14_version >>'
+          make: check-multi-mx
+          requires: [build-14]
+      - test-citus:
+          name: 'test-14_check-vanilla'
+          pg_major: 14
+          image_tag: '<< pipeline.parameters.pg14_version >>'
+          make: check-vanilla
+          requires: [build-14]
+      - test-citus:
+          name: 'test-14_check-isolation'
+          pg_major: 14
+          image_tag: '<< pipeline.parameters.pg14_version >>'
+          make: check-isolation
+          requires: [build-14]
+      - test-citus:
+          name: 'test-14_check-worker'
+          pg_major: 14
+          image_tag: '<< pipeline.parameters.pg14_version >>'
+          make: check-worker
+          requires: [build-14]
+      - test-citus:
+          name: 'test-14_check-operations'
+          pg_major: 14
+          image_tag: '<< pipeline.parameters.pg14_version >>'
+          make: check-operations
+          requires: [build-14]
+      - test-citus:
+          name: 'test-14_check-follower-cluster'
+          pg_major: 14
+          image_tag: '<< pipeline.parameters.pg14_version >>'
+          make: check-follower-cluster
+          requires: [build-14]
+      - test-citus:
+          name: 'test-14_check-columnar'
+          pg_major: 14
+          image_tag: '<< pipeline.parameters.pg14_version >>'
+          make: check-columnar
+          requires: [build-14]
+      - test-citus:
+          name: 'test-14_check-columnar-isolation'
+          pg_major: 14
+          image_tag: '<< pipeline.parameters.pg14_version >>'
+          make: check-columnar-isolation
+          requires: [build-14]
+      - tap-test-citus:
+          name: 'test_14_tap-recovery'
+          pg_major: 14
+          image_tag: '<< pipeline.parameters.pg14_version >>'
+          suite: recovery
+          requires: [build-14]
+      - tap-test-citus:
+          name: 'test-14_tap-columnar-freezing'
+          pg_major: 14
+          image_tag: '<< pipeline.parameters.pg14_version >>'
+          suite: columnar_freezing
+          requires: [build-14]
+      - test-citus:
+          name: 'test-14_check-failure'
+          pg_major: 14
+          image: citus/failtester
+          image_tag: '<< pipeline.parameters.pg14_version >>'
+          make: check-failure
+          requires: [build-14]
+
+      - test-arbitrary-configs:
+          name: 'test-13_check-arbitrary-configs'
+          pg_major: 13
+          image_tag: '<< pipeline.parameters.pg13_version >>'
+          requires: [build-13]
+      - test-arbitrary-configs:
+          name: 'test-14_check-arbitrary-configs'
+          pg_major: 14
+          image_tag: '<< pipeline.parameters.pg14_version >>'
+          requires: [build-14]
+
+      - test-pg-upgrade:
+          name: 'test-13-14_check-pg-upgrade'
+          old_pg_major: 13
+          new_pg_major: 14
+          image_tag: '<< pipeline.parameters.upgrade_pg_versions >>'
+          requires: [build-13, build-14]
+
+      - test-citus-upgrade:
+          name: test-13_check-citus-upgrade
+          pg_major: 13
+          image_tag: '<< pipeline.parameters.pg13_version >>'
+          requires: [build-13]
+
+      - ch_benchmark:
+          requires: [build-13]
+          filters:
+            branches:
+              only:
+                - /ch_benchmark\/.*/ # match with ch_benchmark/ prefix
+      - tpcc_benchmark:
+          requires: [build-13]
+          filters:
+            branches:
+              only:
+                - /tpcc_benchmark\/.*/ # match with tpcc_benchmark/ prefix

.codeclimate.yml

@@ -1,7 +0,0 @@
-exclude_patterns:
-  - "src/backend/distributed/utils/citus_outfuncs.c"
-  - "src/backend/distributed/deparser/ruleutils_*.c"
-  - "src/include/distributed/citus_nodes.h"
-  - "src/backend/distributed/safeclib"
-  - "src/backend/columnar/safeclib"
-  - "**/vendor/"

.devcontainer/.gdbinit

@@ -1,33 +0,0 @@
-# gdbpg.py contains scripts to nicely print the postgres datastructures
-# while in a gdb session. Since the vscode debugger is based on gdb this
-# actually also works when debugging with vscode. Providing nice tools
-# to understand the internal datastructures we are working with.
-source /root/gdbpg.py
-
-# when debugging postgres it is convenient to _always_ have a breakpoint
-# trigger when an error is logged. Because .gdbinit is sourced before gdb
-# is fully attached and has the sources loaded. To make sure the breakpoint
-# is added when the library is loaded we temporary set the breakpoint pending
-# to on. After we have added out breakpoint we revert back to the default
-# configuration for breakpoint pending.
-# The breakpoint is hard to read, but at entry of the function we don't have
-# the level loaded in elevel. Instead we hardcode the location where the
-# level of the current error is stored. Also gdb doesn't understand the
-# ERROR symbol so we hardcode this to the value of ERROR. It is very unlikely
-# this value will ever change in postgres, but if it does we might need to
-# find a way to conditionally load the correct breakpoint.
-set breakpoint pending on
-break elog.c:errfinish if errordata[errordata_stack_depth].elevel == 21
-set breakpoint pending auto
-
-echo \n
-echo ----------------------------------------------------------------------------------\n
-echo when attaching to a postgres backend a breakpoint will be set on elog.c:errfinish \n
-echo it will only break on errors being raised in postgres \n
-echo \n
-echo to disable this breakpoint from vscode run `-exec disable 1` in the debug console \n
-echo this assumes it's the first breakpoint loaded as it is loaded from .gdbinit \n
-echo this can be verified with `-exec info break`, enabling can be done with \n
-echo `-exec enable 1` \n
-echo ----------------------------------------------------------------------------------\n
-echo \n

.devcontainer/.gitignore

@@ -1 +0,0 @@
-postgresql-*.tar.bz2

.devcontainer/.psqlrc

@@ -1,7 +0,0 @@
-\timing on
-\pset linestyle unicode
-\pset border 2
-\setenv PAGER 'pspg --no-mouse -bX --no-commandbar --no-topbar'
-\set HISTSIZE 100000
-\set PROMPT1 '\n%[%033[1m%]%M %n@%/:%> (PID: %p)%R%[%033[0m%]%# '
-\set PROMPT2 '  '

.devcontainer/.vscode/Pipfile

@@ -1,12 +0,0 @@
-[[source]]
-url = "https://pypi.org/simple"
-verify_ssl = true
-name = "pypi"
-
-[packages]
-docopt = "*"
-
-[dev-packages]
-
-[requires]
-python_version = "3.9"

.devcontainer/.vscode/Pipfile.lock

@@ -1,28 +0,0 @@
-{
-    "_meta": {
-        "hash": {
-            "sha256": "6956a6700ead5804aa56bd597c93bb4a13f208d2d49d3b5399365fd240ca0797"
-        },
-        "pipfile-spec": 6,
-        "requires": {
-            "python_version": "3.9"
-        },
-        "sources": [
-            {
-                "name": "pypi",
-                "url": "https://pypi.org/simple",
-                "verify_ssl": true
-            }
-        ]
-    },
-    "default": {
-        "docopt": {
-            "hashes": [
-                "sha256:49b3a825280bd66b3aa83585ef59c4a8c82f2c8a522dbe754a8bc8d08c85c491"
-            ],
-            "index": "pypi",
-            "version": "==0.6.2"
-        }
-    },
-    "develop": {}
-}

.devcontainer/.vscode/generate_c_cpp_properties-json.py

@@ -1,84 +0,0 @@
-#! /usr/bin/env pipenv-shebang
-"""Generate C/C++ properties file for VSCode.
-
-Uses pgenv to iterate postgres versions and generate
-a C/C++ properties file for VSCode containing the
-include paths for the postgres headers.
-
-Usage:
-  generate_c_cpp_properties-json.py <target_path>
-  generate_c_cpp_properties-json.py (-h | --help)
-  generate_c_cpp_properties-json.py --version
-
-Options:
-  -h --help     Show this screen.
-  --version     Show version.
-
-"""
-import json
-import subprocess
-
-from docopt import docopt
-
-
-def main(args):
-    target_path = args['<target_path>']
-
-    output = subprocess.check_output(['pgenv', 'versions'])
-    # typical output is:
-    #      14.8      pgsql-14.8
-    #  *   15.3      pgsql-15.3
-    #      16beta2    pgsql-16beta2
-    # where the line marked with a * is the currently active version
-    #
-    # we are only interested in the first word of each line, which is the version number
-    # thus we strip the whitespace and the * from the line and split it into words
-    # and take the first word
-    versions = [line.strip('* ').split()[0] for line in output.decode('utf-8').splitlines()]
-
-    # create the list of configurations per version
-    configurations = []
-    for version in versions:
-        configurations.append(generate_configuration(version))
-
-    # create the json file
-    c_cpp_properties = {
-        "configurations": configurations,
-        "version": 4
-    }
-
-    # write the c_cpp_properties.json file
-    with open(target_path, 'w') as f:
-        json.dump(c_cpp_properties, f, indent=4)
-
-
-def generate_configuration(version):
-    """Returns a configuration for the given postgres version.
-
-    >>> generate_configuration('14.8')
-    {
-        "name": "Citus Development Configuration - Postgres 14.8",
-        "includePath": [
-            "/usr/local/include",
-            "/home/citus/.pgenv/src/postgresql-14.8/src/**",
-            "${workspaceFolder}/**",
-            "${workspaceFolder}/src/include/",
-        ],
-        "configurationProvider": "ms-vscode.makefile-tools"
-    }
-    """
-    return {
-        "name": f"Citus Development Configuration - Postgres {version}",
-        "includePath": [
-            "/usr/local/include",
-            f"/home/citus/.pgenv/src/postgresql-{version}/src/**",
-            "${workspaceFolder}/**",
-            "${workspaceFolder}/src/include/",
-        ],
-        "configurationProvider": "ms-vscode.makefile-tools"
-    }
-
-
-if __name__ == '__main__':
-    arguments = docopt(__doc__, version='0.1.0')
-    main(arguments)

.devcontainer/.vscode/launch.json

@@ -1,40 +0,0 @@
-{
-    "version": "0.2.0",
-    "configurations": [
-        {
-            "name": "Attach Citus (devcontainer)",
-            "type": "cppdbg",
-            "request": "attach",
-            "processId": "${command:pickProcess}",
-            "program": "/home/citus/.pgenv/pgsql/bin/postgres",
-            "additionalSOLibSearchPath": "/home/citus/.pgenv/pgsql/lib",
-            "setupCommands": [
-                {
-                    "text": "handle SIGUSR1 noprint nostop pass",
-                    "description": "let gdb not stop when SIGUSR1 is sent to process",
-                    "ignoreFailures": true
-                }
-            ],
-        },
-        {
-            "name": "Open core file",
-            "type": "cppdbg",
-            "request": "launch",
-            "program": "/home/citus/.pgenv/pgsql/bin/postgres",
-            "coreDumpPath": "${input:corefile}",
-            "cwd": "${workspaceFolder}",
-            "MIMode": "gdb",
-        }
-    ],
-    "inputs": [
-        {
-            "id": "corefile",
-            "type": "command",
-            "command": "extension.commandvariable.file.pickFile",
-            "args": {
-                "dialogTitle": "Select core file",
-                "include": "**/core*",
-            },
-        },
-    ],
-}

.devcontainer/Dockerfile

@@ -1,222 +0,0 @@
-FROM ubuntu:22.04 AS base
-
-# environment is to make python pass an interactive shell, probably not the best timezone given a wide variety of colleagues
-ENV TZ=UTC
-RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone
-
-# install build tools
-RUN apt update && apt install -y \
-    bison \
-    bzip2 \
-    cpanminus \
-    curl \
-    docbook-xml \
-    docbook-xsl \
-    flex \
-    gcc \
-    git \
-    libcurl4-gnutls-dev \
-    libicu-dev \
-    libkrb5-dev \
-    liblz4-dev \
-    libpam0g-dev \
-    libreadline-dev \
-    libselinux1-dev \
-    libssl-dev \
-    libxml2-utils \
-    libxslt-dev \
-    libzstd-dev \
-    locales \
-    make \
-    perl \
-    pkg-config \
-    python3 \
-    python3-pip \
-    software-properties-common \
-    sudo \
-    uuid-dev \
-    valgrind \
-    xsltproc \
-    zlib1g-dev \
- && add-apt-repository ppa:deadsnakes/ppa -y \
- && apt install -y \
-    python3.9-full \
- # software properties pulls in pkexec, which makes the debugger unusable in vscode
- && apt purge -y \
-    software-properties-common \
- && apt autoremove -y \
- && apt clean
-
-RUN sudo pip3 install pipenv pipenv-shebang
-
-RUN cpanm install IPC::Run
-
-RUN locale-gen en_US.UTF-8
-
-# add the citus user to sudoers and allow all sudoers to login without a password prompt
-RUN useradd -ms /bin/bash citus \
- && usermod -aG sudo citus \
- && echo '%sudo ALL=(ALL) NOPASSWD:ALL' >> /etc/sudoers
-
-WORKDIR /home/citus
-USER citus
-
-# run all make commands with the number of cores available
-RUN echo "export MAKEFLAGS=\"-j \$(nproc)\"" >> "/home/citus/.bashrc"
-
-RUN git clone --branch v1.3.2 --depth 1 https://github.com/theory/pgenv.git .pgenv
-COPY --chown=citus:citus pgenv/config/ .pgenv/config/
-ENV PATH="/home/citus/.pgenv/bin:${PATH}"
-ENV PATH="/home/citus/.pgenv/pgsql/bin:${PATH}"
-
-USER citus
-
-# build postgres versions separately for effective parrallelism and caching of already built versions when changing only certain versions
-FROM base AS pg15
-RUN MAKEFLAGS="-j $(nproc)" pgenv build 15.13
-RUN rm .pgenv/src/*.tar*
-RUN make -C .pgenv/src/postgresql-*/ clean
-RUN make -C .pgenv/src/postgresql-*/src/include install
-
-# create a staging directory with all files we want to copy from our pgenv build
-# we will copy the contents of the staged folder into the final image at once
-RUN mkdir .pgenv-staging/
-RUN cp -r .pgenv/src .pgenv/pgsql-* .pgenv/config .pgenv-staging/
-RUN rm .pgenv-staging/config/default.conf
-
-FROM base AS pg16
-RUN MAKEFLAGS="-j $(nproc)" pgenv build 16.9
-RUN rm .pgenv/src/*.tar*
-RUN make -C .pgenv/src/postgresql-*/ clean
-RUN make -C .pgenv/src/postgresql-*/src/include install
-
-# create a staging directory with all files we want to copy from our pgenv build
-# we will copy the contents of the staged folder into the final image at once
-RUN mkdir .pgenv-staging/
-RUN cp -r .pgenv/src .pgenv/pgsql-* .pgenv/config .pgenv-staging/
-RUN rm .pgenv-staging/config/default.conf
-
-FROM base AS pg17
-RUN MAKEFLAGS="-j $(nproc)" pgenv build 17.5
-RUN rm .pgenv/src/*.tar*
-RUN make -C .pgenv/src/postgresql-*/ clean
-RUN make -C .pgenv/src/postgresql-*/src/include install
-
-# create a staging directory with all files we want to copy from our pgenv build
-# we will copy the contents of the staged folder into the final image at once
-RUN mkdir .pgenv-staging/
-RUN cp -r .pgenv/src .pgenv/pgsql-* .pgenv/config .pgenv-staging/
-RUN rm .pgenv-staging/config/default.conf
-
-FROM base AS uncrustify-builder
-
-RUN sudo apt update && sudo apt install -y cmake tree
-
-WORKDIR /uncrustify
-RUN curl -L https://github.com/uncrustify/uncrustify/archive/uncrustify-0.68.1.tar.gz | tar xz
-WORKDIR /uncrustify/uncrustify-uncrustify-0.68.1/
-RUN mkdir build
-WORKDIR /uncrustify/uncrustify-uncrustify-0.68.1/build/
-RUN cmake ..
-RUN MAKEFLAGS="-j $(nproc)" make -s
-
-RUN make install DESTDIR=/uncrustify
-
-# builder for all pipenv's to get them contained in a single layer
-FROM base AS pipenv
-
-WORKDIR /workspaces/citus/
-
-# tools to sync pgenv with vscode
-COPY --chown=citus:citus .vscode/Pipfile .vscode/Pipfile.lock .devcontainer/.vscode/
-RUN ( cd .devcontainer/.vscode && pipenv install )
-
-# environment to run our failure tests
-COPY --chown=citus:citus src/ src/
-RUN ( cd src/test/regress && pipenv install )
-
-# assemble the final container by copying over the artifacts from separately build containers
-FROM base AS devcontainer
-
-LABEL org.opencontainers.image.source=https://github.com/citusdata/citus
-LABEL org.opencontainers.image.description="Development container for the Citus project"
-LABEL org.opencontainers.image.licenses=AGPL-3.0-only
-
-RUN yes | sudo unminimize
-
-# install developer productivity tools
-RUN sudo apt update \
- && sudo apt install -y \
-    autoconf2.69 \
-    bash-completion \
-    fswatch \
-    gdb \
-    htop \
-    libdbd-pg-perl \
-    libdbi-perl \
-    lsof \
-    man \
-    net-tools \
-    psmisc \
-    pspg \
-    tree \
-    vim \
- && sudo apt clean
-
-# Since gdb will run in the context of the root user when debugging citus we will need to both
-# download the gdbpg.py script as the root user, into their home directory, as well as add .gdbinit
-# as a file owned by root
-# This will make that as soon as the debugger attaches to a postgres backend (or frankly any other process)
-# the gdbpg.py script will be sourced and the developer can direcly use it.
-RUN sudo curl -o /root/gdbpg.py https://raw.githubusercontent.com/tvesely/gdbpg/6065eee7872457785f830925eac665aa535caf62/gdbpg.py
-COPY --chown=root:root .gdbinit /root/
-
-# install developer dependencies in the global environment
-RUN --mount=type=bind,source=requirements.txt,target=requirements.txt pip install -r requirements.txt
-
-# for persistent bash history across devcontainers we need to have
-# a) a directory to store the history in
-# b) a prompt command to append the history to the file
-# c) specify the history file to store the history in
-# b and c are done in the .bashrc to make it persistent across shells only
-RUN sudo install -d -o citus -g citus /commandhistory \
- && echo "export PROMPT_COMMAND='history -a' && export HISTFILE=/commandhistory/.bash_history" >> "/home/citus/.bashrc"
-
-# install citus-dev
-RUN git clone --branch develop https://github.com/citusdata/tools.git citus-tools \
- && ( cd citus-tools/citus_dev && pipenv install ) \
- && mkdir -p ~/.local/bin \
- && ln -s /home/citus/citus-tools/citus_dev/citus_dev-pipenv .local/bin/citus_dev \
- && sudo make -C citus-tools/uncrustify install bindir=/usr/local/bin pkgsysconfdir=/usr/local/etc/ \
- && mkdir -p ~/.local/share/bash-completion/completions/ \
- && ln -s ~/citus-tools/citus_dev/bash_completion ~/.local/share/bash-completion/completions/citus_dev
-
-# TODO some LC_ALL errors, possibly solved by locale-gen
-RUN git clone https://github.com/so-fancy/diff-so-fancy.git \
- && mkdir -p ~/.local/bin \
- && ln -s /home/citus/diff-so-fancy/diff-so-fancy .local/bin/
-
-COPY --link --from=uncrustify-builder /uncrustify/usr/ /usr/
-
-COPY --link --from=pg15 /home/citus/.pgenv-staging/ /home/citus/.pgenv/
-COPY --link --from=pg16 /home/citus/.pgenv-staging/ /home/citus/.pgenv/
-COPY --link --from=pg17 /home/citus/.pgenv-staging/ /home/citus/.pgenv/
-
-COPY --link --from=pipenv /home/citus/.local/share/virtualenvs/ /home/citus/.local/share/virtualenvs/
-
-# place to run your cluster with citus_dev
-VOLUME /data
-RUN sudo mkdir /data \
- && sudo chown citus:citus /data
-
-COPY --chown=citus:citus .psqlrc .
-
-# with the copy linking of layers github actions seem to misbehave with the ownership of the
-# directories leading upto the link, hence a small patch layer to have to right ownerships set
-RUN sudo chown --from=root:root citus:citus -R ~
-
-# sets default pg version
-RUN pgenv switch 17.5
-
-# make connecting to the coordinator easy
-ENV PGPORT=9700

.devcontainer/Makefile

@@ -1,11 +0,0 @@
-
-init: ../.vscode/c_cpp_properties.json ../.vscode/launch.json
-
-../.vscode:
-	mkdir -p ../.vscode
-
-../.vscode/launch.json: ../.vscode .vscode/launch.json
-	cp .vscode/launch.json ../.vscode/launch.json
-
-../.vscode/c_cpp_properties.json: ../.vscode
-	./.vscode/generate_c_cpp_properties-json.py ../.vscode/c_cpp_properties.json

.devcontainer/devcontainer.json

@@ -1,37 +0,0 @@
-{
-    "image": "ghcr.io/citusdata/citus-devcontainer:main",
-    "runArgs": [
-        "--cap-add=SYS_PTRACE",
-        "--ulimit=core=-1",
-    ],
-    "forwardPorts": [
-        9700
-    ],
-    "customizations": {
-        "vscode": {
-            "extensions": [
-                "eamodio.gitlens",
-                "GitHub.copilot-chat",
-                "GitHub.copilot",
-                "github.vscode-github-actions",
-                "github.vscode-pull-request-github",
-                "ms-vscode.cpptools-extension-pack",
-                "ms-vsliveshare.vsliveshare",
-                "rioj7.command-variable",
-            ],
-            "settings": {
-                "files.exclude": {
-                    "**/*.o": true,
-                    "**/.deps/": true,
-                }
-            },
-        }
-    },
-    "mounts": [
-        "type=volume,target=/data",
-        "source=citus-bashhistory,target=/commandhistory,type=volume",
-    ],
-    "updateContentCommand": "./configure",
-    "postCreateCommand": "make -C .devcontainer/",
-}
-

.devcontainer/pgenv/config/default.conf

@@ -1,15 +0,0 @@
-PGENV_MAKE_OPTIONS=(-s)
-
-PGENV_CONFIGURE_OPTIONS=(
-    --enable-debug
-    --enable-depend
-    --enable-cassert
-    --enable-tap-tests
-    'CFLAGS=-ggdb -Og -g3 -fno-omit-frame-pointer -DUSE_VALGRIND'
-    --with-openssl
-    --with-libxml
-    --with-libxslt
-    --with-uuid=e2fs
-    --with-icu
-    --with-lz4
-)

.devcontainer/requirements.txt

@@ -1,9 +0,0 @@
-black==23.11.0
-click==8.1.7
-isort==5.12.0
-mypy-extensions==1.0.0
-packaging==23.2
-pathspec==0.11.2
-platformdirs==4.0.0
-tomli==2.0.1
-typing_extensions==4.8.0

.devcontainer/src/test/regress/Pipfile

@@ -1,28 +0,0 @@
-[[source]]
-name = "pypi"
-url = "https://pypi.python.org/simple"
-verify_ssl = true
-
-[packages]
-mitmproxy = {editable = true, ref = "main", git = "https://github.com/citusdata/mitmproxy.git"}
-construct = "*"
-docopt = "==0.6.2"
-cryptography = ">=41.0.4"
-pytest = "*"
-psycopg = "*"
-filelock = "*"
-pytest-asyncio = "*"
-pytest-timeout = "*"
-pytest-xdist = "*"
-pytest-repeat = "*"
-pyyaml = "*"
-werkzeug = "==2.3.7"
-
-[dev-packages]
-black = "*"
-isort = "*"
-flake8 = "*"
-flake8-bugbear = "*"
-
-[requires]
-python_version = "3.9"

.editorconfig

@@ -17,7 +17,13 @@ trim_trailing_whitespace = true
 insert_final_newline = unset
 trim_trailing_whitespace = unset
 
-[*.{sql,sh,py,toml}]
+# Don't change test/regress/output directory, this needs to be a separate rule
+# for some reason
+[/src/test/regress/output/**]
+insert_final_newline = unset
+trim_trailing_whitespace = unset
+
+[*.{sql,sh,py}]
 indent_style = space
 indent_size = 4
 tab_width = 4

.flake8

@@ -1,7 +0,0 @@
-[flake8]
-# E203 is ignored for black
-extend-ignore = E203
-# black will truncate to 88 characters usually, but long string literals it
-# might keep. That's fine in most cases unless it gets really excessive.
-max-line-length = 150
-exclude = .git,__pycache__,vendor,tmp_*

.gitattributes

@@ -16,6 +16,7 @@ README.*	conflict-marker-size=32
 
 # Test output files that contain extra whitespace
 *.out					-whitespace
+src/test/regress/output/*.source	-whitespace
 
 # These files are maintained or generated elsewhere.  We take them as is.
 configure				-whitespace
@@ -25,9 +26,11 @@ configure				-whitespace
 
 # except these exceptions...
 src/backend/distributed/utils/citus_outfuncs.c -citus-style
-src/backend/distributed/deparser/ruleutils_15.c -citus-style
-src/backend/distributed/deparser/ruleutils_16.c -citus-style
-src/backend/distributed/deparser/ruleutils_17.c -citus-style
+src/backend/distributed/utils/pg11_snprintf.c -citus-style
+src/backend/distributed/deparser/ruleutils_11.c -citus-style
+src/backend/distributed/deparser/ruleutils_12.c -citus-style
+src/backend/distributed/deparser/ruleutils_13.c -citus-style
+src/backend/distributed/deparser/ruleutils_14.c -citus-style
 src/backend/distributed/commands/index_pg_source.c -citus-style
 
 src/include/distributed/citus_nodes.h -citus-style

.github/actions/parallelization/action.yml

@@ -1,23 +0,0 @@
-name: 'Parallelization matrix'
-inputs:
-  count:
-    required: false
-    default: 32
-outputs:
-  json:
-    value: ${{ steps.generate_matrix.outputs.json }}
-runs:
-  using: "composite"
-  steps:
-    - name: Generate parallelization matrix
-      id: generate_matrix
-      shell: bash
-      run: |-
-        json_array="{\"include\": ["
-        for ((i = 1; i <= ${{ inputs.count }}; i++)); do
-            json_array+="{\"id\":\"$i\"},"
-        done
-        json_array=${json_array%,}
-        json_array+=" ]}"
-        echo "json=$json_array" >> "$GITHUB_OUTPUT"
-        echo "json=$json_array"

.github/actions/save_logs_and_results/action.yml

@@ -1,38 +0,0 @@
-name: save_logs_and_results
-inputs:
-  folder:
-    required: false
-    default: "log"
-runs:
-  using: composite
-  steps:
-  - uses: actions/upload-artifact@v4.6.0
-    name: Upload logs
-    with:
-      name: ${{ inputs.folder }}
-      if-no-files-found: ignore
-      path: |
-        src/test/**/proxy.output
-        src/test/**/results/
-        src/test/**/tmp_check/master/log
-        src/test/**/tmp_check/worker.57638/log
-        src/test/**/tmp_check/worker.57637/log
-        src/test/**/*.diffs
-        src/test/**/out/ddls.sql
-        src/test/**/out/queries.sql
-        src/test/**/logfile_*
-        /tmp/pg_upgrade_newData_logs
-  - name: Publish regression.diffs
-    run: |-
-      diffs="$(find src/test/regress -name "*.diffs" -exec cat {} \;)"
-      if ! [ -z "$diffs" ]; then
-        echo '```diff' >> $GITHUB_STEP_SUMMARY
-        echo -E "$diffs" >> $GITHUB_STEP_SUMMARY
-        echo '```' >> $GITHUB_STEP_SUMMARY
-        echo -E $diffs
-      fi
-    shell: bash
-  - name: Print stack traces
-    run: "./ci/print_stack_trace.sh"
-    if: failure()
-    shell: bash

.github/actions/setup_extension/action.yml

@@ -1,35 +0,0 @@
-name: setup_extension
-inputs:
-  pg_major:
-    required: false
-  skip_installation:
-    required: false
-    default: false
-    type: boolean
-runs:
-  using: composite
-  steps:
-  - name: Expose $PG_MAJOR to Github Env
-    run: |-
-        if [ -z "${{ inputs.pg_major }}" ]; then
-          echo "PG_MAJOR=${PG_MAJOR}" >> $GITHUB_ENV
-        else
-          echo "PG_MAJOR=${{ inputs.pg_major }}" >> $GITHUB_ENV
-        fi
-    shell: bash
-  - uses: actions/download-artifact@v4.1.8
-    with:
-      name: build-${{ env.PG_MAJOR }}
-  - name: Install Extension
-    if: ${{ inputs.skip_installation == 'false' }}
-    run: tar xfv "install-$PG_MAJOR.tar" --directory /
-    shell: bash
-  - name: Configure
-    run: |-
-      chown -R circleci .
-      git config --global --add safe.directory ${GITHUB_WORKSPACE}
-      gosu circleci ./configure --without-pg-version-check
-    shell: bash
-  - name: Enable core dumps
-    run: ulimit -c unlimited
-    shell: bash

.github/actions/upload_coverage/action.yml

@@ -1,27 +0,0 @@
-name: coverage
-inputs:
-  flags:
-    required: false
-  codecov_token:
-    required: true
-runs:
-  using: composite
-  steps:
-  - uses: codecov/codecov-action@v3
-    with:
-      flags: ${{ inputs.flags }}
-      token: ${{ inputs.codecov_token }}
-      verbose: true
-      gcov: true
-  - name: Create codeclimate coverage
-    run: |-
-      lcov --directory . --capture --output-file lcov.info
-      lcov --remove lcov.info -o lcov.info '/usr/*'
-      sed "s=^SF:$PWD/=SF:=g" -i lcov.info # relative pats are required by codeclimate
-      mkdir -p /tmp/codeclimate
-      cc-test-reporter format-coverage -t lcov -o /tmp/codeclimate/${{ inputs.flags }}.json lcov.info
-    shell: bash
-  - uses: actions/upload-artifact@v4.6.0
-    with:
-      path: "/tmp/codeclimate/*.json"
-      name: codeclimate-${{ inputs.flags }}

.github/packaging/packaging_ignore.yml

@@ -1,3 +0,0 @@
-base:
-  - ".* warning: ignoring old recipe for target [`']check'"
-  - ".* warning: overriding recipe for target [`']check'"

.github/packaging/validate_build_output.sh

@@ -1,51 +0,0 @@
-#!/bin/bash
-
-set -ex
-
-# Function to get the OS version
-get_rpm_os_version() {
-    if [[ -f /etc/centos-release ]]; then
-        cat /etc/centos-release | awk '{print $4}'
-    elif [[ -f /etc/oracle-release ]]; then
-        cat /etc/oracle-release | awk '{print $5}'
-    else
-        echo "Unknown"
-    fi
-}
-
-package_type=${1}
-
-# Since $HOME is set in GH_Actions as /github/home, pyenv fails to create virtualenvs.
-# For this script, we set $HOME to /root and then set it back to /github/home.
-GITHUB_HOME="${HOME}"
-export HOME="/root"
-
-eval "$(pyenv init -)"
-pyenv versions
-pyenv virtualenv ${PACKAGING_PYTHON_VERSION} packaging_env
-pyenv activate packaging_env
-
-git clone -b v0.8.27 --depth=1  https://github.com/citusdata/tools.git tools
-python3 -m pip install -r tools/packaging_automation/requirements.txt
-
-
-echo "Package type: ${package_type}"
-echo "OS version: $(get_rpm_os_version)"
-
- # For RHEL 7, we need to install urllib3<2 due to below execution error
- # ImportError: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl'
- # module is compiled with 'OpenSSL 1.0.2k-fips  26 Jan 2017'.
- # See: https://github.com/urllib3/urllib3/issues/2168
-if [[ ${package_type} == "rpm" && $(get_rpm_os_version) == 7* ]]; then
-    python3 -m pip uninstall -y urllib3
-    python3 -m pip install 'urllib3<2'
-fi
-
-python3 -m tools.packaging_automation.validate_build_output --output_file output.log \
-                                                            --ignore_file .github/packaging/packaging_ignore.yml \
-                                                            --package_type ${package_type}
-pyenv deactivate
-# Set $HOME back to /github/home
-export HOME=${GITHUB_HOME}
-
-# Print the output to the console

.github/workflows/build_and_test.yml

@@ -1,545 +0,0 @@
-name: Build & Test
-run-name: Build & Test - ${{ github.event.pull_request.title || github.ref_name }}
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
-  cancel-in-progress: true
-on:
-  workflow_dispatch:
-    inputs:
-      skip_test_flakyness:
-        required: false
-        default: false
-        type: boolean
-  push:
-    branches:
-      - "main"
-      - "release-*"
-  pull_request:
-    types: [opened, reopened,synchronize]
-  merge_group:
-jobs:
-  # Since GHA does not interpolate env varibles in matrix context, we need to
-  # define them in a separate job and use them in other jobs.
-  params:
-    runs-on: ubuntu-latest
-    name: Initialize parameters
-    outputs:
-      build_image_name: "ghcr.io/citusdata/extbuilder"
-      test_image_name: "ghcr.io/citusdata/exttester"
-      citusupgrade_image_name: "ghcr.io/citusdata/citusupgradetester"
-      fail_test_image_name: "ghcr.io/citusdata/failtester"
-      pgupgrade_image_name: "ghcr.io/citusdata/pgupgradetester"
-      style_checker_image_name: "ghcr.io/citusdata/stylechecker"
-      style_checker_tools_version: "0.8.18"
-      sql_snapshot_pg_version: "17.5"
-      image_suffix: "-dev-d28f316"
-      pg15_version: '{ "major": "15", "full": "15.13" }'
-      pg16_version: '{ "major": "16", "full": "16.9" }'
-      pg17_version: '{ "major": "17", "full": "17.5" }'
-      upgrade_pg_versions: "15.13-16.9-17.5"
-    steps:
-      # Since GHA jobs need at least one step we use a noop step here.
-      - name: Set up parameters
-        run: echo 'noop'
-  check-sql-snapshots:
-    needs: params
-    runs-on: ubuntu-latest
-    container:
-      image: ${{ needs.params.outputs.build_image_name }}:${{ needs.params.outputs.sql_snapshot_pg_version }}${{ needs.params.outputs.image_suffix }}
-      options: --user root
-    steps:
-    - uses: actions/checkout@v4
-    - name: Check Snapshots
-      run: |
-        git config --global --add safe.directory ${GITHUB_WORKSPACE}
-        ci/check_sql_snapshots.sh
-  check-style:
-    needs: params
-    runs-on: ubuntu-latest
-    container:
-      image: ${{ needs.params.outputs.style_checker_image_name }}:${{ needs.params.outputs.style_checker_tools_version }}${{ needs.params.outputs.image_suffix }}
-    steps:
-    - name: Check Snapshots
-      run: |
-        git config --global --add safe.directory ${GITHUB_WORKSPACE}
-    - uses: actions/checkout@v4
-      with:
-        fetch-depth: 0
-    - name: Check C Style
-      run: citus_indent --check
-    - name: Check Python style
-      run: black --check .
-    - name: Check Python import order
-      run: isort --check .
-    - name: Check Python lints
-      run: flake8 .
-    - name: Fix whitespace
-      run: ci/editorconfig.sh && git diff --exit-code
-    - name: Remove useless declarations
-      run: ci/remove_useless_declarations.sh && git diff --cached --exit-code
-    - name: Sort and group includes
-      run: ci/sort_and_group_includes.sh && git diff --exit-code
-    - name: Normalize test output
-      run: ci/normalize_expected.sh && git diff --exit-code
-    - name: Check for C-style comments in migration files
-      run: ci/disallow_c_comments_in_migrations.sh && git diff --exit-code
-    - name: 'Check for comment--cached ns that start with # character in spec files'
-      run: ci/disallow_hash_comments_in_spec_files.sh && git diff --exit-code
-    - name: Check for gitignore entries .for source files
-      run: ci/fix_gitignore.sh && git diff --exit-code
-    - name: Check for lengths of changelog entries
-      run: ci/disallow_long_changelog_entries.sh
-    - name: Check for banned C API usage
-      run: ci/banned.h.sh
-    - name: Check for tests missing in schedules
-      run: ci/check_all_tests_are_run.sh
-    - name: Check if all CI scripts are actually run
-      run: ci/check_all_ci_scripts_are_run.sh
-    - name: Check if all GUCs are sorted alphabetically
-      run: ci/check_gucs_are_alphabetically_sorted.sh
-    - name: Check for missing downgrade scripts
-      run: ci/check_migration_files.sh
-  build:
-    needs: params
-    name: Build for PG${{ fromJson(matrix.pg_version).major }}
-    strategy:
-      fail-fast: false
-      matrix:
-        image_name:
-          - ${{ needs.params.outputs.build_image_name }}
-        image_suffix:
-          - ${{ needs.params.outputs.image_suffix}}
-        pg_version:
-          - ${{ needs.params.outputs.pg15_version }}
-          - ${{ needs.params.outputs.pg16_version }}
-          - ${{ needs.params.outputs.pg17_version }}
-    runs-on: ubuntu-latest
-    container:
-      image: "${{ matrix.image_name }}:${{ fromJson(matrix.pg_version).full }}${{ matrix.image_suffix }}"
-      options: --user root
-    steps:
-    - uses: actions/checkout@v4
-    - name: Expose $PG_MAJOR to Github Env
-      run: echo "PG_MAJOR=${PG_MAJOR}" >> $GITHUB_ENV
-      shell: bash
-    - name: Build
-      run: "./ci/build-citus.sh"
-      shell: bash
-    - uses: actions/upload-artifact@v4.6.0
-      with:
-        name: build-${{ env.PG_MAJOR }}
-        path: |-
-          ./build-${{ env.PG_MAJOR }}/*
-          ./install-${{ env.PG_MAJOR }}.tar
-  test-citus:
-    name: PG${{ fromJson(matrix.pg_version).major }} - ${{ matrix.make }}
-    strategy:
-      fail-fast: false
-      matrix:
-        suite:
-          - regress
-        image_name:
-          - ${{ needs.params.outputs.test_image_name }}
-        pg_version:
-          - ${{ needs.params.outputs.pg15_version }}
-          - ${{ needs.params.outputs.pg16_version }}
-          - ${{ needs.params.outputs.pg17_version }}
-        make:
-          - check-split
-          - check-multi
-          - check-multi-1
-          - check-multi-mx
-          - check-vanilla
-          - check-isolation
-          - check-operations
-          - check-follower-cluster
-          - check-columnar
-          - check-columnar-isolation
-          - check-enterprise
-          - check-enterprise-isolation
-          - check-enterprise-isolation-logicalrep-1
-          - check-enterprise-isolation-logicalrep-2
-          - check-enterprise-isolation-logicalrep-3
-        include:
-          - make: check-failure
-            pg_version: ${{ needs.params.outputs.pg15_version }}
-            suite: regress
-            image_name: ${{ needs.params.outputs.fail_test_image_name }}
-          - make: check-failure
-            pg_version: ${{ needs.params.outputs.pg16_version }}
-            suite: regress
-            image_name: ${{ needs.params.outputs.fail_test_image_name }}
-          - make: check-failure
-            pg_version: ${{ needs.params.outputs.pg17_version }}
-            suite: regress
-            image_name: ${{ needs.params.outputs.fail_test_image_name }}
-          - make: check-enterprise-failure
-            pg_version: ${{ needs.params.outputs.pg15_version }}
-            suite: regress
-            image_name: ${{ needs.params.outputs.fail_test_image_name }}
-          - make: check-enterprise-failure
-            pg_version: ${{ needs.params.outputs.pg16_version }}
-            suite: regress
-            image_name: ${{ needs.params.outputs.fail_test_image_name }}
-          - make: check-enterprise-failure
-            pg_version: ${{ needs.params.outputs.pg17_version }}
-            suite: regress
-            image_name: ${{ needs.params.outputs.fail_test_image_name }}
-          - make: check-pytest
-            pg_version: ${{ needs.params.outputs.pg15_version }}
-            suite: regress
-            image_name: ${{ needs.params.outputs.fail_test_image_name }}
-          - make: check-pytest
-            pg_version: ${{ needs.params.outputs.pg16_version }}
-            suite: regress
-            image_name: ${{ needs.params.outputs.fail_test_image_name }}
-          - make: check-pytest
-            pg_version: ${{ needs.params.outputs.pg17_version }}
-            suite: regress
-            image_name: ${{ needs.params.outputs.fail_test_image_name }}
-          - make: installcheck
-            suite: cdc
-            image_name: ${{ needs.params.outputs.test_image_name }}
-            pg_version: ${{ needs.params.outputs.pg15_version }}
-          - make: installcheck
-            suite: cdc
-            image_name: ${{ needs.params.outputs.test_image_name }}
-            pg_version: ${{ needs.params.outputs.pg16_version }}
-          - make: installcheck
-            suite: cdc
-            image_name: ${{ needs.params.outputs.test_image_name }}
-            pg_version: ${{ needs.params.outputs.pg17_version }}
-          - make: check-query-generator
-            pg_version: ${{ needs.params.outputs.pg15_version }}
-            suite: regress
-            image_name: ${{ needs.params.outputs.fail_test_image_name }}
-          - make: check-query-generator
-            pg_version: ${{ needs.params.outputs.pg16_version }}
-            suite: regress
-            image_name: ${{ needs.params.outputs.fail_test_image_name }}
-          - make: check-query-generator
-            pg_version: ${{ needs.params.outputs.pg17_version }}
-            suite: regress
-            image_name: ${{ needs.params.outputs.fail_test_image_name }}
-    runs-on: ubuntu-latest
-    container:
-      image: "${{ matrix.image_name }}:${{ fromJson(matrix.pg_version).full }}${{ needs.params.outputs.image_suffix }}"
-      options: --user root --dns=8.8.8.8
-      # Due to Github creates a default network for each job, we need to use
-      # --dns= to have similar DNS settings as our other CI systems or local
-      # machines. Otherwise, we may see different results.
-    needs:
-    - params
-    - build
-    steps:
-    - uses: actions/checkout@v4
-    - uses: "./.github/actions/setup_extension"
-    - name: Run Test
-      run: gosu circleci make -C src/test/${{ matrix.suite }} ${{ matrix.make }}
-      timeout-minutes: 20
-    - uses: "./.github/actions/save_logs_and_results"
-      if: always()
-      with:
-        folder: ${{ fromJson(matrix.pg_version).major }}_${{ matrix.make }}
-    - uses: "./.github/actions/upload_coverage"
-      if: always()
-      with:
-        flags: ${{ env.PG_MAJOR }}_${{ matrix.suite }}_${{ matrix.make }}
-        codecov_token: ${{ secrets.CODECOV_TOKEN }}
-  test-arbitrary-configs:
-    name: PG${{ fromJson(matrix.pg_version).major }} - check-arbitrary-configs-${{ matrix.parallel }}
-    runs-on: ["self-hosted", "1ES.Pool=1es-gha-citusdata-pool"]
-    container:
-      image: "${{ matrix.image_name }}:${{ fromJson(matrix.pg_version).full }}${{ needs.params.outputs.image_suffix }}"
-      options: --user root
-    needs:
-      - params
-      - build
-    strategy:
-      fail-fast: false
-      matrix:
-        image_name:
-          - ${{ needs.params.outputs.fail_test_image_name }}
-        pg_version:
-          - ${{ needs.params.outputs.pg15_version }}
-          - ${{ needs.params.outputs.pg16_version }}
-          - ${{ needs.params.outputs.pg17_version }}
-        parallel: [0,1,2,3,4,5] # workaround for running 6 parallel jobs
-    steps:
-    - uses: actions/checkout@v4
-    - uses: "./.github/actions/setup_extension"
-    - name: Test arbitrary configs
-      run: |-
-        # we use parallel jobs to split the tests into 6 parts and run them in parallel
-        # the script below extracts the tests for the current job
-        N=6  # Total number of jobs (see matrix.parallel)
-        X=${{ matrix.parallel }}  # Current job number
-        TESTS=$(src/test/regress/citus_tests/print_test_names.py |
-          tr '\n' ',' | awk -v N="$N" -v X="$X" -F, '{
-            split("", parts)
-            for (i = 1; i <= NF; i++) {
-                parts[i % N] = parts[i % N] $i ","
-            }
-            print substr(parts[X], 1, length(parts[X])-1)
-        }')
-        echo $TESTS
-        gosu circleci \
-          make -C src/test/regress \
-            check-arbitrary-configs parallel=4 CONFIGS=$TESTS
-    - uses: "./.github/actions/save_logs_and_results"
-      if: always()
-      with:
-        folder: ${{ env.PG_MAJOR }}_arbitrary_configs_${{ matrix.parallel }}
-    - uses: "./.github/actions/upload_coverage"
-      if: always()
-      with:
-        flags: ${{ env.PG_MAJOR }}_arbitrary_configs_${{ matrix.parallel }}
-        codecov_token: ${{ secrets.CODECOV_TOKEN }}
-  test-pg-upgrade:
-    name: PG${{ matrix.old_pg_major }}-PG${{ matrix.new_pg_major }} - check-pg-upgrade
-    runs-on: ubuntu-latest
-    container:
-      image: "${{ needs.params.outputs.pgupgrade_image_name }}:${{ needs.params.outputs.upgrade_pg_versions }}${{ needs.params.outputs.image_suffix }}"
-      options: --user root
-    needs:
-    - params
-    - build
-    strategy:
-      fail-fast: false
-      matrix:
-        include:
-          - old_pg_major: 15
-            new_pg_major: 16
-          - old_pg_major: 16
-            new_pg_major: 17
-          - old_pg_major: 15
-            new_pg_major: 17
-    env:
-      old_pg_major: ${{ matrix.old_pg_major }}
-      new_pg_major: ${{ matrix.new_pg_major }}
-    steps:
-    - uses: actions/checkout@v4
-    - uses: "./.github/actions/setup_extension"
-      with:
-        pg_major: "${{ env.old_pg_major }}"
-    - uses: "./.github/actions/setup_extension"
-      with:
-        pg_major: "${{ env.new_pg_major }}"
-    - name: Install and test postgres upgrade
-      run: |-
-        gosu circleci \
-          make -C src/test/regress \
-            check-pg-upgrade \
-            old-bindir=/usr/lib/postgresql/${{ env.old_pg_major }}/bin \
-            new-bindir=/usr/lib/postgresql/${{ env.new_pg_major }}/bin
-    - name: Copy pg_upgrade logs for newData dir
-      run: |-
-        mkdir -p /tmp/pg_upgrade_newData_logs
-        if ls src/test/regress/tmp_upgrade/newData/*.log 1> /dev/null 2>&1; then
-            cp src/test/regress/tmp_upgrade/newData/*.log /tmp/pg_upgrade_newData_logs
-        fi
-      if: failure()
-    - uses: "./.github/actions/save_logs_and_results"
-      if: always()
-      with:
-        folder: ${{ env.old_pg_major }}_${{ env.new_pg_major }}_upgrade
-    - uses: "./.github/actions/upload_coverage"
-      if: always()
-      with:
-        flags: ${{ env.old_pg_major }}_${{ env.new_pg_major }}_upgrade
-        codecov_token: ${{ secrets.CODECOV_TOKEN }}
-  test-citus-upgrade:
-    name: PG${{ fromJson(needs.params.outputs.pg15_version).major }} - check-citus-upgrade
-    runs-on: ubuntu-latest
-    container:
-      image: "${{ needs.params.outputs.citusupgrade_image_name }}:${{ fromJson(needs.params.outputs.pg15_version).full }}${{ needs.params.outputs.image_suffix }}"
-      options: --user root
-    needs:
-    - params
-    - build
-    steps:
-    - uses: actions/checkout@v4
-    - uses: "./.github/actions/setup_extension"
-      with:
-        skip_installation: true
-    - name: Install and test citus upgrade
-      run: |-
-        # run make check-citus-upgrade for all citus versions
-        # the image has ${CITUS_VERSIONS} set with all verions it contains the binaries of
-        for citus_version in ${CITUS_VERSIONS}; do \
-          gosu circleci \
-            make -C src/test/regress \
-              check-citus-upgrade \
-              bindir=/usr/lib/postgresql/${PG_MAJOR}/bin \
-              citus-old-version=${citus_version} \
-              citus-pre-tar=/install-pg${PG_MAJOR}-citus${citus_version}.tar \
-              citus-post-tar=${GITHUB_WORKSPACE}/install-$PG_MAJOR.tar; \
-        done;
-        # run make check-citus-upgrade-mixed for all citus versions
-        # the image has ${CITUS_VERSIONS} set with all verions it contains the binaries of
-        for citus_version in ${CITUS_VERSIONS}; do \
-          gosu circleci \
-            make -C src/test/regress \
-              check-citus-upgrade-mixed \
-              citus-old-version=${citus_version} \
-              bindir=/usr/lib/postgresql/${PG_MAJOR}/bin \
-              citus-pre-tar=/install-pg${PG_MAJOR}-citus${citus_version}.tar \
-              citus-post-tar=${GITHUB_WORKSPACE}/install-$PG_MAJOR.tar; \
-        done;
-    - uses: "./.github/actions/save_logs_and_results"
-      if: always()
-      with:
-        folder: ${{ env.PG_MAJOR }}_citus_upgrade
-    - uses: "./.github/actions/upload_coverage"
-      if: always()
-      with:
-        flags: ${{ env.PG_MAJOR }}_citus_upgrade
-        codecov_token: ${{ secrets.CODECOV_TOKEN }}
-  upload-coverage:
-    if: always()
-    env:
-      CC_TEST_REPORTER_ID: ${{ secrets.CC_TEST_REPORTER_ID }}
-    runs-on: ubuntu-latest
-    container:
-      image: ${{ needs.params.outputs.test_image_name }}:${{ fromJson(needs.params.outputs.pg17_version).full }}${{ needs.params.outputs.image_suffix }}
-    needs:
-      - params
-      - test-citus
-      - test-arbitrary-configs
-      - test-citus-upgrade
-      - test-pg-upgrade
-    steps:
-      - uses: actions/download-artifact@v4.1.8
-        with:
-          pattern: codeclimate*
-          path: codeclimate
-          merge-multiple: true
-      - name: Upload coverage results to Code Climate
-        run: |-
-          cc-test-reporter sum-coverage codeclimate/*.json -o total.json
-          cc-test-reporter upload-coverage -i total.json
-  ch_benchmark:
-    name: CH Benchmark
-    if: startsWith(github.ref, 'refs/heads/ch_benchmark/')
-    runs-on: ubuntu-latest
-    needs:
-    - build
-    steps:
-    - uses: actions/checkout@v4
-    - uses: azure/login@v1
-      with:
-        creds: ${{ secrets.AZURE_CREDENTIALS }}
-    - name: install dependencies and run ch_benchmark tests
-      uses: azure/CLI@v1
-      with:
-        inlineScript: |
-          cd ./src/test/hammerdb
-          chmod +x run_hammerdb.sh
-          run_hammerdb.sh citusbot_ch_benchmark_rg
-  tpcc_benchmark:
-    name: TPCC Benchmark
-    if: startsWith(github.ref, 'refs/heads/tpcc_benchmark/')
-    runs-on: ubuntu-latest
-    needs:
-    - build
-    steps:
-    - uses: actions/checkout@v4
-    - uses: azure/login@v1
-      with:
-        creds: ${{ secrets.AZURE_CREDENTIALS }}
-    - name: install dependencies and run tpcc_benchmark tests
-      uses: azure/CLI@v1
-      with:
-        inlineScript: |
-          cd ./src/test/hammerdb
-          chmod +x run_hammerdb.sh
-          run_hammerdb.sh citusbot_tpcc_benchmark_rg
-  prepare_parallelization_matrix_32:
-    name: Prepare parallelization matrix
-    if: ${{ needs.test-flakyness-pre.outputs.tests != ''}}
-    needs: test-flakyness-pre
-    runs-on: ubuntu-latest
-    outputs:
-      json: ${{ steps.parallelization.outputs.json }}
-    steps:
-      - uses: actions/checkout@v4
-      - uses: "./.github/actions/parallelization"
-        id: parallelization
-        with:
-          count: 32
-  test-flakyness-pre:
-    name: Detect regression tests need to be ran
-    if: ${{ !inputs.skip_test_flakyness }}}
-    runs-on: ubuntu-latest
-    needs: build
-    outputs:
-      tests: ${{ steps.detect-regression-tests.outputs.tests }}
-    steps:
-    - uses: actions/checkout@v4
-      with:
-        fetch-depth: 0
-    - name: Detect regression tests need to be ran
-      id: detect-regression-tests
-      run: |-
-        detected_changes=$(git diff origin/main... --name-only --diff-filter=AM | (grep 'src/test/regress/sql/.*\.sql\|src/test/regress/spec/.*\.spec\|src/test/regress/citus_tests/test/test_.*\.py' || true))
-        tests=${detected_changes}
-
-        # split the tests to be skipped --today we only skip upgrade tests
-        skipped_tests=""
-        not_skipped_tests=""
-        for test in $tests; do
-            if [[ $test =~ ^src/test/regress/sql/upgrade_ ]]; then
-                skipped_tests="$skipped_tests $test"
-            else
-                not_skipped_tests="$not_skipped_tests $test"
-            fi
-        done
-
-        if [ ! -z "$skipped_tests" ]; then
-            echo "Skipped tests " $skipped_tests
-        fi
-
-        if [ -z "$not_skipped_tests" ]; then
-            echo "Not detected any tests that flaky test detection should run"
-        else
-            echo "Detected tests " $not_skipped_tests
-        fi
-
-        echo 'tests<<EOF' >> $GITHUB_OUTPUT
-        echo "$not_skipped_tests" >> "$GITHUB_OUTPUT"
-        echo 'EOF' >> $GITHUB_OUTPUT
-  test-flakyness:
-    if: ${{ needs.test-flakyness-pre.outputs.tests != ''}}
-    name: Test flakyness
-    runs-on: ubuntu-latest
-    container:
-      image: ${{ needs.params.outputs.fail_test_image_name }}:${{ fromJson(needs.params.outputs.pg17_version).full }}${{ needs.params.outputs.image_suffix }}
-      options: --user root
-    env:
-      runs: 8
-    needs:
-    - params
-    - build
-    - test-flakyness-pre
-    - prepare_parallelization_matrix_32
-    strategy:
-      fail-fast: false
-      matrix: ${{ fromJson(needs.prepare_parallelization_matrix_32.outputs.json) }}
-    steps:
-    - uses: actions/checkout@v4
-    - uses: actions/download-artifact@v4.1.8
-    - uses: "./.github/actions/setup_extension"
-    - name: Run minimal tests
-      run: |-
-        tests="${{ needs.test-flakyness-pre.outputs.tests }}"
-        tests_array=($tests)
-        for test in "${tests_array[@]}"
-        do
-            test_name=$(echo "$test" | sed -r "s/.+\/(.+)\..+/\1/")
-            gosu circleci src/test/regress/citus_tests/run_test.py $test_name --repeat ${{ env.runs }} --use-whole-schedule-line
-        done
-      shell: bash
-    - uses: "./.github/actions/save_logs_and_results"
-      if: always()
-      with:
-        folder: test_flakyness_parallel_${{ matrix.id }}

.github/workflows/codeql.yml

@@ -1,79 +0,0 @@
-name: "CodeQL"
-
-on:
-  schedule:
-    - cron: '59 23 * * 6'
-  workflow_dispatch:
-
-jobs:
-  analyze:
-    name: Analyze
-    runs-on: ubuntu-22.04
-    permissions:
-      actions: read
-      contents: read
-      security-events: write
-
-    strategy:
-      fail-fast: false
-      matrix:
-        language: [ 'cpp', 'python']
-
-    steps:
-    - name: Checkout repository
-      uses: actions/checkout@v4
-
-    - name: Initialize CodeQL
-      uses: github/codeql-action/init@v3
-      with:
-        languages: ${{ matrix.language }}
-
-    - name: Install package dependencies
-      run: |
-        # Create the file repository configuration:
-        sudo sh -c 'echo "deb http://apt.postgresql.org/pub/repos/apt $(lsb_release -cs)-pgdg main 15" > /etc/apt/sources.list.d/pgdg.list'
-        # Import the repository signing key:
-        wget --quiet -O - https://www.postgresql.org/media/keys/ACCC4CF8.asc | sudo apt-key add -
-        sudo apt-get update
-        sudo apt-get install -y --no-install-recommends \
-          autotools-dev \
-          build-essential \
-          ca-certificates \
-          curl \
-          debhelper \
-          devscripts \
-          fakeroot \
-          flex \
-          libcurl4-openssl-dev \
-          libdistro-info-perl \
-          libedit-dev \
-          libfile-fcntllock-perl \
-          libicu-dev \
-          libkrb5-dev \
-          liblz4-1 \
-          liblz4-dev \
-          libpam0g-dev \
-          libreadline-dev \
-          libselinux1-dev \
-          libssl-dev \
-          libxslt-dev \
-          libzstd-dev \
-          libzstd1 \
-          lintian \
-          postgresql-server-dev-15 \
-          postgresql-server-dev-all \
-          python3-pip \
-          python3-setuptools \
-          wget \
-          zlib1g-dev
-
-
-    - name: Configure, Build and Install Citus
-      if: matrix.language == 'cpp'
-      run: |
-        ./configure
-        make -sj8
-        sudo make install-all
-
-    - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@v3

.github/workflows/devcontainer.yml

@@ -1,54 +0,0 @@
-name: "Build devcontainer"
-
-# Since building of containers can be quite time consuming, and take up some storage,
-# there is no need to finish a build for a tag if new changes are concurrently being made.
-# This cancels any previous builds for the same tag, and only the latest one will be kept.
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
-on:
-  push:
-    paths:
-      - ".devcontainer/**"
-  workflow_dispatch:
-
-jobs:
-  docker:
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      packages: write
-      attestations: write
-      id-token: write
-    steps:
-      -
-        name: Docker meta
-        id: meta
-        uses: docker/metadata-action@v5
-        with:
-          images: |
-            ghcr.io/citusdata/citus-devcontainer
-          tags: |
-            type=ref,event=branch
-            type=sha
-      -
-        name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v2
-      -
-        name: 'Login to GitHub Container Registry'
-        uses: docker/login-action@v3
-        with:
-          registry: ghcr.io
-          username: ${{github.actor}}
-          password: ${{secrets.GITHUB_TOKEN}}
-      -
-        name: Build and push
-        uses: docker/build-push-action@v5
-        with:
-          context: "{{defaultContext}}:.devcontainer"
-          push: true
-          tags: ${{ steps.meta.outputs.tags }}
-          labels: ${{ steps.meta.outputs.labels }}
-          cache-from: type=gha
-          cache-to: type=gha,mode=max

.github/workflows/flaky_test_debugging.yml

@@ -1,79 +0,0 @@
-name: Flaky test debugging
-run-name: Flaky test debugging - ${{ inputs.flaky_test }} (${{ inputs.flaky_test_runs_per_job }}x${{ inputs.flaky_test_parallel_jobs }})
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
-  cancel-in-progress: true
-on:
-  workflow_dispatch:
-    inputs:
-      flaky_test:
-        required: true
-        type: string
-        description: Test to run
-      flaky_test_runs_per_job:
-        required: false
-        default: 8
-        type: number
-        description: Number of times to run the test
-      flaky_test_parallel_jobs:
-        required: false
-        default: 32
-        type: number
-        description: Number of parallel jobs to run
-jobs:
-  build:
-    name: Build Citus
-    runs-on: ubuntu-latest
-    container:
-      image: ${{ vars.build_image_name }}:${{ vars.pg15_version  }}${{ vars.image_suffix }}
-      options: --user root
-    steps:
-    - uses: actions/checkout@v4
-    - name: Configure, Build, and Install
-      run: |
-        echo "PG_MAJOR=${PG_MAJOR}" >> $GITHUB_ENV
-        ./ci/build-citus.sh
-      shell: bash
-    - uses: actions/upload-artifact@v4.6.0
-      with:
-        name: build-${{ env.PG_MAJOR }}
-        path: |-
-          ./build-${{ env.PG_MAJOR }}/*
-          ./install-${{ env.PG_MAJOR }}.tar
-  prepare_parallelization_matrix:
-    name: Prepare parallelization matrix
-    runs-on: ubuntu-latest
-    outputs:
-      json: ${{ steps.parallelization.outputs.json }}
-    steps:
-      - uses: actions/checkout@v4
-      - uses: "./.github/actions/parallelization"
-        id: parallelization
-        with:
-          count: ${{ inputs.flaky_test_parallel_jobs }}
-  test_flakyness:
-    name: Test flakyness
-    runs-on: ubuntu-latest
-    container:
-      image: ${{ vars.fail_test_image_name }}:${{ vars.pg15_version  }}${{ vars.image_suffix }}
-      options: --user root
-    needs:
-      [build, prepare_parallelization_matrix]
-    env:
-      test: "${{ inputs.flaky_test }}"
-      runs: "${{ inputs.flaky_test_runs_per_job }}"
-      skip: false
-    strategy:
-      fail-fast: false
-      matrix: ${{ fromJson(needs.prepare_parallelization_matrix.outputs.json) }}
-    steps:
-    - uses: actions/checkout@v4
-    - uses: "./.github/actions/setup_extension"
-    - name: Run minimal tests
-      run: |-
-          gosu circleci src/test/regress/citus_tests/run_test.py ${{ env.test }} --repeat ${{ env.runs }} --use-whole-schedule-line
-      shell: bash
-    - uses: "./.github/actions/save_logs_and_results"
-      if: always()
-      with:
-          folder: check_flakyness_parallel_${{ matrix.id }}

.github/workflows/packaging-test-pipelines.yml

@@ -1,177 +0,0 @@
-name: Build tests in packaging images
-
-on:
-  pull_request:
-    types: [opened, reopened,synchronize]
-  merge_group:
-
-  workflow_dispatch:
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
-jobs:
-
-  get_postgres_versions_from_file:
-    runs-on: ubuntu-latest
-    outputs:
-      pg_versions: ${{ steps.get-postgres-versions.outputs.pg_versions }}
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 2
-      - name: Get Postgres Versions
-        id: get-postgres-versions
-        run: |
-          set -euxo pipefail
-          # Postgres versions are stored in .github/workflows/build_and_test.yml
-          # file in json strings with major and full keys.
-          # Below command extracts the versions and get the unique values.
-          pg_versions=$(cat .github/workflows/build_and_test.yml | grep -oE '"major": "[0-9]+", "full": "[0-9.]+"' | sed -E 's/"major": "([0-9]+)", "full": "([0-9.]+)"/\1/g' | sort | uniq | tr '\n', ',')
-          pg_versions_array="[ ${pg_versions} ]"
-          echo "Supported PG Versions: ${pg_versions_array}"
-          # Below line is needed to set the output variable to be used in the next job
-          echo "pg_versions=${pg_versions_array}" >> $GITHUB_OUTPUT
-        shell: bash
-  rpm_build_tests:
-    name: rpm_build_tests
-    needs: get_postgres_versions_from_file
-    runs-on: ubuntu-latest
-    strategy:
-      fail-fast: false
-      matrix:
-        # While we use separate images for different Postgres versions in rpm
-        # based distros
-        # For this reason, we need to use a "matrix" to generate names of
-        # rpm images, e.g. citus/packaging:centos-7-pg12
-        packaging_docker_image:
-          - oraclelinux-8
-          - almalinux-8
-          - almalinux-9
-        POSTGRES_VERSION: ${{ fromJson(needs.get_postgres_versions_from_file.outputs.pg_versions) }}
-
-    container:
-      image: citus/packaging:${{ matrix.packaging_docker_image }}-pg${{ matrix.POSTGRES_VERSION }}
-      options: --user root
-
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-
-      - name: Set Postgres and python parameters for rpm based distros
-        run: |
-          echo "/usr/pgsql-${{ matrix.POSTGRES_VERSION }}/bin" >> $GITHUB_PATH
-          echo "/root/.pyenv/bin:$PATH" >> $GITHUB_PATH
-          echo "PACKAGING_PYTHON_VERSION=3.8.16" >> $GITHUB_ENV
-
-      - name: Configure
-        run: |
-          echo "Current Shell:$0"
-          echo "GCC Version: $(gcc --version)"
-          ./configure 2>&1 | tee output.log
-
-      - name: Make clean
-        run: |
-          make clean
-
-      - name: Make
-        run: |
-          git config --global --add safe.directory ${GITHUB_WORKSPACE}
-          make CFLAGS="-Wno-missing-braces" -sj$(cat /proc/cpuinfo | grep "core id" | wc -l) 2>&1 | tee -a output.log
-
-          # Check the exit code of the make command
-          make_exit_code=${PIPESTATUS[0]}
-
-          # If the make command returned a non-zero exit code, exit with the same code
-          if [[ $make_exit_code -ne 0 ]]; then
-              echo "make command failed with exit code $make_exit_code"
-              exit $make_exit_code
-          fi
-
-      - name: Make install
-        run: |
-          make CFLAGS="-Wno-missing-braces" install 2>&1 | tee -a output.log
-
-      - name: Validate output
-        env:
-          POSTGRES_VERSION: ${{ matrix.POSTGRES_VERSION }}
-          PACKAGING_DOCKER_IMAGE: ${{ matrix.packaging_docker_image }}
-        run: |
-          echo "Postgres version: ${POSTGRES_VERSION}"
-          ./.github/packaging/validate_build_output.sh "rpm"
-
-  deb_build_tests:
-    name: deb_build_tests
-    needs: get_postgres_versions_from_file
-    runs-on: ubuntu-latest
-    strategy:
-      fail-fast: false
-      matrix:
-        # On deb based distros, we use the same docker image for
-        # builds based on different Postgres versions because deb
-        # based images include all postgres installations.
-        # For this reason, we have multiple runs --which is 3 today--
-        # for each deb based image and we use POSTGRES_VERSION to set
-        # PG_CONFIG variable in each of those runs.
-        packaging_docker_image:
-          - debian-bookworm-all
-          - debian-bullseye-all
-          - ubuntu-focal-all
-          - ubuntu-jammy-all
-
-        POSTGRES_VERSION: ${{ fromJson(needs.get_postgres_versions_from_file.outputs.pg_versions) }}
-
-    container:
-      image: citus/packaging:${{ matrix.packaging_docker_image }}
-      options: --user root
-
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-
-      - name: Set pg_config path and python parameters for deb based distros
-        run: |
-          echo "PG_CONFIG=/usr/lib/postgresql/${{ matrix.POSTGRES_VERSION }}/bin/pg_config" >> $GITHUB_ENV
-          echo "/root/.pyenv/bin:$PATH" >> $GITHUB_PATH
-          echo "PACKAGING_PYTHON_VERSION=3.8.16" >> $GITHUB_ENV
-
-      - name: Configure
-        run: |
-          echo "Current Shell:$0"
-          echo "GCC Version: $(gcc --version)"
-          ./configure 2>&1 | tee output.log
-
-      - name: Make clean
-        run: |
-          make clean
-
-      - name: Make
-        shell: bash
-        run: |
-          set -e
-          git config --global --add safe.directory ${GITHUB_WORKSPACE}
-          make -sj$(cat /proc/cpuinfo | grep "core id" | wc -l) 2>&1 | tee -a output.log
-
-          # Check the exit code of the make command
-          make_exit_code=${PIPESTATUS[0]}
-
-          # If the make command returned a non-zero exit code, exit with the same code
-          if [[ $make_exit_code -ne 0 ]]; then
-              echo "make command failed with exit code $make_exit_code"
-              exit $make_exit_code
-          fi
-
-
-      - name: Make install
-        run: |
-          make install 2>&1 | tee -a output.log
-
-      - name: Validate output
-        env:
-          POSTGRES_VERSION: ${{ matrix.POSTGRES_VERSION }}
-          PACKAGING_DOCKER_IMAGE: ${{ matrix.packaging_docker_image }}
-        run: |
-          echo "Postgres version: ${POSTGRES_VERSION}"
-          ./.github/packaging/validate_build_output.sh "deb"

.gitignore

@@ -38,9 +38,6 @@ lib*.pc
 /Makefile.global
 /src/Makefile.custom
 /compile_commands.json
-/src/backend/distributed/cdc/build-cdc-*/*
-/src/test/cdc/tmp_check/*
-
 
 # temporary files vim creates
 *.swp
@@ -54,7 +51,3 @@ lib*.pc
 
 # style related temporary outputs
 *.uncrustify
-.venv
-
-# added output when modifying check_gucs_are_alphabetically_sorted.sh
-guc.out

CODE_OF_CONDUCT.md

@@ -1,9 +0,0 @@
-# Microsoft Open Source Code of Conduct
-
-This project has adopted the [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/).
-
-Resources:
-
-- [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/)
-- [Microsoft Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/)
-- Contact [opencode@microsoft.com](mailto:opencode@microsoft.com) with questions or concerns

CONTRIBUTING.md

@@ -11,65 +11,8 @@ sign a Contributor License Agreement (CLA). For an explanation of
 why we ask this as well as instructions for how to proceed, see the
 [Microsoft CLA](https://cla.opensource.microsoft.com/).
 
-### Devcontainer / Github Codespaces
-
-The easiest way to start contributing is via our devcontainer. This container works both locally in visual studio code with docker-desktop/docker-for-mac as well as [Github Codespaces](https://github.com/features/codespaces). To open the project in vscode you will need the [Dev Containers extension](https://marketplace.visualstudio.com/items?itemName=ms-vscode-remote.remote-containers). For codespaces you will need to [create a new codespace](https://codespace.new/citusdata/citus).
-
-With the extension installed you can run the following from the command pallet to get started
-
-```
-> Dev Containers: Clone Repository in Container Volume...
-```
-
-In the subsequent popup paste the url to the repo and hit enter.
-
-```
-https://github.com/citusdata/citus
-```
-
-This will create an isolated Workspace in vscode, complete with all tools required to build, test and run the Citus extension. We keep this container up to date with the supported postgres versions as well as the exact versions of tooling we use.
-
-To quickly start we suggest splitting your terminal once to have two shells. The left one in the `/workspaces/citus`, the second one changed to `/data`. The left terminal will be used to interact with the project, the right one with a testing cluster.
-
-To get citus installed from source we run `make install -s` in the first terminal. Once installed you can start a Citus cluster in the second terminal via `citus_dev make citus`. The cluster will run in the background, and can be interacted with via `citus_dev`. To get an overview of the available commands.
-
-With the Citus cluster running you can connect to the coordinator in the first terminal via `psql -p9700`. Because the coordinator is the most common entrypoint the `PGPORT` environment is set accordingly, so a simple `psql` will connect directly to the coordinator.
-
-### Debugging in the VS code
-
-1. Start Debugging: Press F5 in VS Code to start debugging. When prompted, you'll need to attach the debugger to the appropriate PostgreSQL process.
-
-2. Identify the Process: If you're running a psql command, take note of the PID that appears in your psql prompt. For example:
-```
-[local] citus@citus:9700 (PID: 5436)=#
-```
-This PID (5436 in this case) indicates the process that you should attach the debugger to.
-If you are uncertain about which process to attach, you can list all running PostgreSQL processes using the following command:
-```
-ps aux | grep postgres
-```
-
-Look for the process associated with the PID you noted. For example:
-```
-citus      5436  0.0  0.0  0  0 ?        S    14:00   0:00 postgres: citus citus
-```
-4. Attach the Debugger: Once you've identified the correct PID, select that process when prompted in VS Code to attach the debugger. You should now be able to debug the PostgreSQL session tied to the psql command.
-
-5. Set Breakpoints and Debug: With the debugger attached, you can set breakpoints within the code. This allows you to step through the code execution, inspect variables, and fully debug the PostgreSQL instance running in your container.
-
 ### Getting and building
 
-[PostgreSQL documentation](https://www.postgresql.org/support/versioning/) has a
-section on upgrade policy.
-
-	We always recommend that all users run the latest available minor release [for PostgreSQL] for whatever major version is in use.
-
-We expect Citus users to honor this recommendation and use latest available
-PostgreSQL minor release. Failure to do so may result in failures in our test
-suite. There are some known improvements in PG test architecture such as
-[this commit](https://github.com/postgres/postgres/commit/3f323956128ff8589ce4d3a14e8b950837831803)
-that are missing in earlier minor versions.
-
 #### Mac
 
 1. Install Xcode
@@ -87,19 +30,11 @@ that are missing in earlier minor versions.
 
   cd citus
   ./configure
-  # If you have already installed the project, you need to clean it first
-  make clean
   make
   make install
   # Optionally, you might instead want to use `make install-all`
   # since `multi_extension` regression test would fail due to missing downgrade scripts.
   cd src/test/regress
-
-  pip install pipenv
-  pipenv --rm
-  pipenv install
-  pipenv shell
-
   make check
   ```
 
@@ -118,7 +53,7 @@ that are missing in earlier minor versions.
                           autoconf flex git libcurl4-gnutls-dev libicu-dev \
                           libkrb5-dev liblz4-dev libpam0g-dev libreadline-dev \
                           libselinux1-dev libssl-dev libxslt1-dev libzstd-dev \
-                          make uuid-dev
+                          make uuid-dev mitmproxy
   ```
 
 2. Get, build, and test the code
@@ -127,19 +62,11 @@ that are missing in earlier minor versions.
   git clone https://github.com/citusdata/citus.git
   cd citus
   ./configure
-  # If you have already installed the project previously, you need to clean it first
-  make clean
   make
   sudo make install
   # Optionally, you might instead want to use `sudo make install-all`
   # since `multi_extension` regression test would fail due to missing downgrade scripts.
   cd src/test/regress
-
-  pip install pipenv
-  pipenv --rm
-  pipenv install
-  pipenv shell
-
   make check
   ```
 
@@ -179,25 +106,53 @@ that are missing in earlier minor versions.
   git clone https://github.com/citusdata/citus.git
   cd citus
   PG_CONFIG=/usr/pgsql-14/bin/pg_config ./configure
-  # If you have already installed the project previously, you need to clean it first
-  make clean
   make
   sudo make install
   # Optionally, you might instead want to use `sudo make install-all`
   # since `multi_extension` regression test would fail due to missing downgrade scripts.
   cd src/test/regress
-
-  pip install pipenv
-  pipenv --rm
-  pipenv install
-  pipenv shell
-
   make check
   ```
 
 ### Following our coding conventions
 
-Our coding conventions are documented in [STYLEGUIDE.md](STYLEGUIDE.md).
+CircleCI will automatically reject any PRs which do not follow our coding
+conventions. The easiest way to ensure your PR adheres to those conventions is
+to use the [citus_indent](https://github.com/citusdata/tools/tree/develop/uncrustify)
+tool. This tool uses `uncrustify` under the hood.
+
+```bash
+# Uncrustify changes the way it formats code every release a bit. To make sure
+# everyone formats consistently we use version 0.68.1:
+curl -L https://github.com/uncrustify/uncrustify/archive/uncrustify-0.68.1.tar.gz | tar xz
+cd uncrustify-uncrustify-0.68.1/
+mkdir build
+cd build
+cmake ..
+make -j5
+sudo make install
+cd ../..
+
+git clone https://github.com/citusdata/tools.git
+cd tools
+make uncrustify/.install
+```
+
+Once you've done that, you can run the `make reindent` command from the top
+directory to recursively check and correct the style of any source files in the
+current directory. Under the hood, `make reindent` will run `citus_indent` and
+some other style corrections for you.
+
+You can also run the following in the directory of this repository to
+automatically format all the files that you have changed before committing:
+
+```bash
+cat > .git/hooks/pre-commit << __EOF__
+#!/bin/bash
+citus_indent --check --diff || { citus_indent --diff; exit 1; }
+__EOF__
+chmod +x .git/hooks/pre-commit
+```
 
 ### Making SQL changes
 
@@ -234,50 +189,3 @@ style `#include` statements like this:
 
 Any other SQL you can put directly in the main sql file, e.g.
 `src/backend/distributed/sql/citus--8.3-1--9.0-1.sql`.
-
-### Backporting a commit to a release branch
-
-1. Check out the release branch that you want to backport to `git checkout release-11.3`
-2. Make sure you have the latest changes `git pull`
-3. Create a new release branch with a unique name `git checkout -b release-11.3-<yourname>`
-4. Cherry-pick the commit that you want to backport `git cherry-pick -x <sha>` (the `-x` is important)
-5. Push the branch `git push`
-6. Wait for tests to pass
-7. If the cherry-pick required non-trivial merge conflicts, create a PR and ask
-   for a review.
-8. After the tests pass on CI, fast-forward the release branch `git push origin release-11.3-<yourname>:release-11.3`
-
-### Running tests
-
-See [`src/test/regress/README.md`](https://github.com/citusdata/citus/blob/master/src/test/regress/README.md)
-
-### Documentation
-
-User-facing documentation is published on [docs.citusdata.com](https://docs.citusdata.com/). When adding a new feature, function, or setting, you can open a pull request or issue against the [Citus docs repo](https://github.com/citusdata/citus_docs/).
-
-Detailed descriptions of the implementation for Citus developers are provided in the [Citus Technical Documentation](src/backend/distributed/README.md). It is currently a single file for ease of searching. Please update the documentation if you make any changes that affect the design or add major new features.
-
-# Making a pull request ready for reviews
-
-Asking for help and asking for reviews are two different things. When you're asking for help, you're asking for someone to help you with something that you're not expected to know.
-
-But when you're asking for a review, you're asking for someone to review your work and provide feedback. So, when you're asking for a review, you're expected to make sure that:
-
-* Your changes don't perform **unnecessary line addition / deletions / style changes on unrelated files / lines**.
-
-* All CI jobs are **passing**, including **style checks** and **flaky test detection jobs**. Note that if you're an external contributor, you don't have to wait CI jobs to run (and finish) because they don't get automatically triggered for external contributors.
-
-* Your PR has necessary amount of **tests** and that they're passing.
-
-* You separated as much as possible work into **separate PRs**, e.g., a prerequisite bugfix, a refactoring etc..
-
-* Your PR doesn't introduce a typo or something that you can easily fix yourself.
-
-* After all CI jobs pass, code-coverage measurement job (CodeCov as of today) then kicks in. That's why it's important to make the **tests passing** first. At that point, you're expected to check **CodeCov annotations** that can be seen in the **Files Changed** tab and expected to make sure that it doesn't complain about any lines that are not covered. For example, it's ok if CodeCov complains about an `ereport()` call that you put for an "unexpected-but-better-than-crashing" case, but it's not ok if it complains about an uncovered `if` branch that you added.
-
-* And finally, perform a **self-review** to make sure that:
-  * Code and code-comments reflects the idea **without requiring an extra explanation** via a chat message / email / PR comment.
-    This is important because we don't expect developers to reach out to author / read about the whole discussion in the PR to understand the idea behind a commit merged into `main` branch.
-  * PR description is clear enough.
-  * If-and-only-if you're **introducing a user facing change / bugfix**, your PR has a line that starts with `DESCRIPTION: <Present simple tense word that starts with a capital letter, e.g., Adds support for / Fixes / Disallows>`.
-  * **Commit messages** are clear enough if the commits are doing logically different things.

DEVCONTAINER.md

@@ -1,43 +0,0 @@
-# Devcontainer
-
-## Coredumps
-When postgres/citus crashes, there is the option to create a coredump. This is useful for debugging the issue. Coredumps are enabled in the devcontainer by default. However, not all environments are configured correctly out of the box. The most important configuration that is not standardized is the `core_pattern`. The configuration can be verified from the container, however, you cannot change this setting from inside the container as the filesystem containing this setting is in read only mode while inside the container.
-
-To verify if corefiles are written run the following command in a terminal. This shows the filename pattern with which the corefile will be written.
-```bash
-cat /proc/sys/kernel/core_pattern
-```
-
-This should be configured with a relative path or simply a simple filename, such as `core`. When your environment shows an absolute path you will need to change this setting. How to change this setting depends highly on the underlying system as the setting needs to be changed on the kernel of the host running the container.
-
-You can put any pattern in `/proc/sys/kernel/core_pattern` as you see fit. eg. You can add the PID to the core pattern in one of two ways;
-- You either include `%p` in the core_pattern. This gets substituted with the PID of the crashing process.
-- Alternatively you could set `/proc/sys/kernel/core_uses_pid` to `1` in the same way as you set `core_pattern`. This will append the PID to the corefile if `%p` is not explicitly contained in the core_pattern.
-
-When a coredump is written you can use the debug/launch configuration `Open core file` which is preconfigured in the devcontainer. This will open a fileprompt that lists all coredumps that are found in your workspace. When you want to debug coredumps from `citus_dev` that are run in your `/data` directory, you can add the data directory to your workspace. In the command pallet of vscode you can run `>Workspace: Add Folder to Workspace...` and select the `/data` directory. This will allow you to open the coredumps from the `/data` directory in the `Open core file` debug configuration.
-
-### Windows (docker desktop)
-When running in docker desktop on windows you will most likely need to change this setting. The linux guest in WSL2 that runs your container is the `docker-desktop` environment. The easiest way to get onto the host, where you can change this setting, is to open a powershell window and verify you have the docker-desktop environment listed.
-
-```powershell
-wsl --list
-```
-
-Among others this should list both `docker-desktop` and `docker-desktop-data`. You can then open a shell in the `docker-desktop` environment.
-
-```powershell
-wsl -d docker-desktop
-```
-
-Inside this shell you can verify that you have the right environment by running
-
-```bash
-cat /proc/sys/kernel/core_pattern
-```
-
-This should show the same configuration as the one you see inside the devcontainer. You can then change the setting by running the following command.
-This will change the setting for the current session. If you want to make the change permanent you will need to add this to a startup script.
-
-```bash
-echo "core" > /proc/sys/kernel/core_pattern
-```

Makefile

@@ -11,18 +11,12 @@ endif
 
 include Makefile.global
 
-all: extension
+all: extension pg_send_cancellation
 
-
-# build columnar only
-columnar:
-	$(MAKE) -C src/backend/columnar all
 # build extension
-extension: $(citus_top_builddir)/src/include/citus_version.h columnar
+extension: $(citus_top_builddir)/src/include/citus_version.h
 	$(MAKE) -C src/backend/distributed/ all
-install-columnar: columnar
-	$(MAKE) -C src/backend/columnar install
-install-extension: extension install-columnar
+install-extension: extension
 	$(MAKE) -C src/backend/distributed/ install
 install-headers: extension
 	$(MKDIR_P) '$(DESTDIR)$(includedir_server)/distributed/'
@@ -33,35 +27,37 @@ install-headers: extension
 
 clean-extension:
 	$(MAKE) -C src/backend/distributed/ clean
-	$(MAKE) -C src/backend/columnar/ clean
 clean-full:
 	$(MAKE) -C src/backend/distributed/ clean-full
 .PHONY: extension install-extension clean-extension clean-full
 
 install-downgrades:
 	$(MAKE) -C src/backend/distributed/ install-downgrades
-install-all: install-headers
-	$(MAKE) -C src/backend/columnar/ install-all
+install-all: install-headers install-pg_send_cancellation
 	$(MAKE) -C src/backend/distributed/ install-all
 
+# build citus_send_cancellation binary
+pg_send_cancellation:
+	$(MAKE) -C src/bin/pg_send_cancellation/ all
+install-pg_send_cancellation: pg_send_cancellation
+	$(MAKE) -C src/bin/pg_send_cancellation/ install
+clean-pg_send_cancellation:
+	$(MAKE) -C src/bin/pg_send_cancellation/ clean
+.PHONY: pg_send_cancellation install-pg_send_cancellation clean-pg_send_cancellation
 
 # Add to generic targets
-install: install-extension install-headers
-clean: clean-extension
+install: install-extension install-headers install-pg_send_cancellation
+clean: clean-extension clean-pg_send_cancellation
 
 # apply or check style
 reindent:
 	${citus_abs_top_srcdir}/ci/fix_style.sh
 check-style:
-	black . --check --quiet
-	isort . --check --quiet
-	flake8
 	cd ${citus_abs_top_srcdir} && citus_indent --quiet --check
 .PHONY: reindent check-style
 
 # depend on install-all so that downgrade scripts are installed as well
 check: all install-all
-	# explicetely does not use $(MAKE) to avoid parallelism
-	make -C src/test/regress check
+	$(MAKE) -C src/test/regress check-full
 
 .PHONY: all check clean install install-downgrades install-all

Makefile.global.in

@@ -64,8 +64,8 @@ $(citus_top_builddir)/Makefile.global: $(citus_abs_top_srcdir)/configure $(citus
 $(citus_top_builddir)/config.status: $(citus_abs_top_srcdir)/configure $(citus_abs_top_srcdir)/src/backend/distributed/citus.control
 	cd @abs_top_builddir@ && ./config.status --recheck && ./config.status
 
-# Regenerate configure if configure.ac changed
-$(citus_abs_top_srcdir)/configure: $(citus_abs_top_srcdir)/configure.ac
+# Regenerate configure if configure.in changed
+$(citus_abs_top_srcdir)/configure: $(citus_abs_top_srcdir)/configure.in
 	cd ${citus_abs_top_srcdir} && ./autogen.sh
 
 # If specified via configure, replace the default compiler. Normally

README.md

@@ -1,14 +1,8 @@
-| **<br/>The Citus database is 100% open source.<br/><img width=1000/><br/>Learn what's new in the [Citus 13.0 release blog](https://www.citusdata.com/blog/2025/02/06/distribute-postgresql-17-with-citus-13/) and the [Citus Updates page](https://www.citusdata.com/updates/).<br/><br/>**|
-|---|
-<br/>
-
-
-
-![Citus Banner](images/citus-readme-banner.png)
+![Citus Banner](/citus-readme-banner.png)
 
 [![Latest Docs](https://img.shields.io/badge/docs-latest-brightgreen.svg)](https://docs.citusdata.com/)
 [![Stack Overflow](https://img.shields.io/badge/Stack%20Overflow-%20-545353?logo=Stack%20Overflow)](https://stackoverflow.com/questions/tagged/citus)
-[![Slack](https://cituscdn.azureedge.net/images/social/slack-badge.svg)](https://slack.citusdata.com/)
+[![Slack Status](http://slack.citusdata.com/badge.svg)](https://citus-public.slack.com/)
 [![Code Coverage](https://codecov.io/gh/citusdata/citus/branch/master/graph/badge.svg)](https://app.codecov.io/gh/citusdata/citus)
 [![Twitter](https://img.shields.io/twitter/follow/citusdata.svg?label=Follow%20@citusdata)](https://twitter.com/intent/follow?screen_name=citusdata)
 
@@ -25,21 +19,18 @@ With Citus, you extend your PostgreSQL database with new superpowers:
 - **References tables** are replicated to all nodes for joins and foreign keys from distributed tables and maximum read performance.
 - **Distributed query engine** routes and parallelizes SELECT, DML, and other operations on distributed tables across the cluster.
 - **Columnar storage** compresses data, speeds up scans, and supports fast projections, both on regular and distributed tables.
-- **Query from any node** enables you to utilize the full capacity of your cluster for distributed queries
 
 You can use these Citus superpowers to make your Postgres database scale-out ready on a single Citus node. Or you can build a large cluster capable of handling **high transaction throughputs**, especially in **multi-tenant apps**, run **fast analytical queries**, and process large amounts of **time series** or **IoT data** for **real-time analytics**. When your data size and volume grow, you can easily add more worker nodes to the cluster and rebalance the shards.
 
 Our [SIGMOD '21](https://2021.sigmod.org/) paper [Citus: Distributed PostgreSQL for Data-Intensive Applications](https://doi.org/10.1145/3448016.3457551) gives a more detailed look into what Citus is, how it works, and why it works that way.
 
-![Citus scales out from a single node](images/citus-scale-out.png)
+![Citus scales out from a single node](/citus-scale-out.png)
 
 Since Citus is an extension to Postgres, you can use Citus with the latest Postgres versions. And Citus works seamlessly with the PostgreSQL tools and extensions you are already familiar with.
 
 - [Why Citus?](#why-citus)
 - [Getting Started](#getting-started)
 - [Using Citus](#using-citus)
-- [Schema-based sharding](#schema-based-sharding)
-- [Setting up with High Availability](#setting-up-with-high-availability)
 - [Documentation](#documentation)
 - [Architecture](#architecture)
 - [When to Use Citus](#when-to-use-citus)
@@ -65,11 +56,11 @@ Developers choose Citus for two reasons:
 
 ## Getting Started
 
-The quickest way to get started with Citus is to use the [Azure Cosmos DB for PostgreSQL](https://learn.microsoft.com/azure/cosmos-db/postgresql/quickstart-create-portal) managed service in the cloud—or [set up Citus locally](https://docs.citusdata.com/en/stable/installation/single_node.html).
+The quickest way to get started with Citus is to use the [Hyperscale (Citus)](https://docs.microsoft.com/azure/postgresql/quickstart-create-hyperscale-portal) deployment option in the Azure Database for PostgreSQL managed service—or [set up Citus locally](https://docs.citusdata.com/en/stable/installation/single_node.html).
 
-### Citus Managed Service on Azure
+### Hyperscale (Citus) on Azure Database for PostgreSQL
 
-You can get a fully-managed Citus cluster in minutes through the [Azure Cosmos DB for PostgreSQL portal](https://azure.microsoft.com/products/cosmos-db/). Azure will manage your backups, high availability through auto-failover, software updates, monitoring, and more for all of your servers. To get started Citus on Azure, use the [Azure Cosmos DB for PostgreSQL Quickstart](https://learn.microsoft.com/azure/cosmos-db/postgresql/quickstart-create-portal).
+You can get a fully-managed Citus cluster in minutes through the Hyperscale (Citus) deployment option in the [Azure Database for PostgreSQL](https://azure.microsoft.com/services/postgresql/) portal. Azure will manage your backups, high availability through auto-failover, software updates, monitoring, and more for all of your servers. To get started with Hyperscale (Citus), use the [Hyperscale (Citus) Quickstart](https://docs.microsoft.com/azure/postgresql/quickstart-create-hyperscale-portal) in the Azure docs.
 
 ### Running Citus using Docker
 
@@ -95,14 +86,14 @@ Install packages on Ubuntu / Debian:
 ```bash
 curl https://install.citusdata.com/community/deb.sh > add-citus-repo.sh
 sudo bash add-citus-repo.sh
-sudo apt-get -y install postgresql-17-citus-13.0
+sudo apt-get -y install postgresql-14-citus-10.2
 ```
 
-Install packages on Red Hat:
+Install packages on CentOS / Fedora / Red Hat:
 ```bash
 curl https://install.citusdata.com/community/rpm.sh > add-citus-repo.sh
 sudo bash add-citus-repo.sh
-sudo yum install -y citus130_17
+sudo yum install -y citus102_14
 ```
 
 To add Citus to your local PostgreSQL database, add the following to `postgresql.conf`:
@@ -124,7 +115,7 @@ If you want to set up a multi-node cluster, you can also set up additional Postg
 
 ```sql
 -- before adding the first worker node, tell future worker nodes how to reach the coordinator
-SELECT citus_set_coordinator_host('10.0.0.1', 5432);
+-- SELECT citus_set_coordinator_host('10.0.0.1', 5432);
 
 -- add worker nodes
 SELECT citus_add_node('10.0.0.2', 5432);
@@ -234,42 +225,7 @@ WHERE device_type_id = 55;
 Time: 209.961 ms
 ```
 
-Co-location also helps you scale [INSERT..SELECT](https://docs.citusdata.com/en/stable/articles/aggregation.html), [stored procedures](https://www.citusdata.com/blog/2020/11/21/making-postgres-stored-procedures-9x-faster-in-citus/), and [distributed transactions](https://www.citusdata.com/blog/2017/06/02/scaling-complex-sql-transactions/).
-
-### Distributing Tables without interrupting the application
-
-
-Some of you already start with Postgres, and decide to distribute tables later on while your application using the tables. In that case, you want to avoid downtime for both reads and writes. `create_distributed_table` command block writes (e.g., DML commands) on the table until the command is finished. Instead, with `create_distributed_table_concurrently` command, your application can continue to read and write the data even during the command.
-
-
-```sql
-CREATE TABLE device_logs (
-  device_id bigint primary key,
-  log text
-);
-
--- insert device logs
-INSERT INTO device_logs (device_id, log)
-SELECT s, 'device log:'||s FROM generate_series(0, 99) s;
-
--- convert device_logs into a distributed table without interrupting the application
-SELECT create_distributed_table_concurrently('device_logs', 'device_id', colocate_with := 'devices');
-
-
--- get the count of the logs, parallelized across shards
-SELECT count(*) FROM device_logs;
-
-┌───────┐
-│ count │
-├───────┤
-│   100 │
-└───────┘
-(1 row)
-
-Time: 48.734 ms
-```
-
-
+Co-location also helps you scale [INSERT..SELECT]( https://docs.citusdata.com/en/stable/articles/aggregation.html), [stored procedures]( https://www.citusdata.com/blog/2020/11/21/making-postgres-stored-procedures-9x-faster-in-citus/), and [distributed transactions](https://www.citusdata.com/blog/2017/06/02/scaling-complex-sql-transactions/).
 
 ### Creating Reference Tables
 
@@ -348,74 +304,11 @@ When using columnar storage, you should only load data in batch using `COPY` or
 
 To learn more about columnar storage, check out the [columnar storage README](https://github.com/citusdata/citus/blob/master/src/backend/columnar/README.md).
 
-## Schema-based sharding
-
-Available since Citus 12.0, [schema-based sharding](https://docs.citusdata.com/en/stable/get_started/concepts.html#schema-based-sharding) is the shared database, separate schema model, the schema becomes the logical shard within the database. Multi-tenant apps can a use a schema per tenant to easily shard along the tenant dimension. Query changes are not required and the application usually only needs a small modification to set the proper search_path when switching tenants. Schema-based sharding is an ideal solution for microservices, and for ISVs deploying applications that cannot undergo the changes required to onboard row-based sharding.
-
-### Creating distributed schemas
-
-You can turn an existing schema into a distributed schema by calling `citus_schema_distribute`:
-
-```sql
-SELECT citus_schema_distribute('user_service');
-```
-
-Alternatively, you can set `citus.enable_schema_based_sharding` to have all newly created schemas be automatically converted into distributed schemas:
-
-```sql
-SET citus.enable_schema_based_sharding TO ON;
-
-CREATE SCHEMA AUTHORIZATION user_service;
-CREATE SCHEMA AUTHORIZATION time_service;
-CREATE SCHEMA AUTHORIZATION ping_service;
-```
-
-### Running queries
-
-Queries will be properly routed to schemas based on `search_path` or by explicitly using the schema name in the query.
-
-For [microservices](https://docs.citusdata.com/en/stable/get_started/tutorial_microservices.html) you would create a USER per service matching the schema name, hence the default `search_path` would contain the schema name. When connected the user queries would be automatically routed and no changes to the microservice would be required.
-
-```sql
-CREATE USER user_service;
-CREATE SCHEMA AUTHORIZATION user_service;
-```
-
-For typical multi-tenant applications, you would set the search path to the tenant schema name in your application:
-
-```sql
-SET search_path = tenant_name, public;
-```
-
-## Setting up with High Availability
-
-One of the most popular high availability solutions for PostgreSQL, [Patroni 3.0](https://github.com/zalando/patroni), has [first class support for Citus 10.0 and above](https://patroni.readthedocs.io/en/latest/citus.html#citus), additionally since Citus 11.2 ships with improvements for smoother node switchover in Patroni.
-
-An example of patronictl list output for the Citus cluster:
-
-```bash
-postgres@coord1:~$ patronictl list demo
-```
-
-```text
-+ Citus cluster: demo ----------+--------------+---------+----+-----------+
-| Group | Member  | Host        | Role         | State   | TL | Lag in MB |
-+-------+---------+-------------+--------------+---------+----+-----------+
-|     0 | coord1  | 172.27.0.10 | Replica      | running |  1 |         0 |
-|     0 | coord2  | 172.27.0.6  | Sync Standby | running |  1 |         0 |
-|     0 | coord3  | 172.27.0.4  | Leader       | running |  1 |           |
-|     1 | work1-1 | 172.27.0.8  | Sync Standby | running |  1 |         0 |
-|     1 | work1-2 | 172.27.0.2  | Leader       | running |  1 |           |
-|     2 | work2-1 | 172.27.0.5  | Sync Standby | running |  1 |         0 |
-|     2 | work2-2 | 172.27.0.7  | Leader       | running |  1 |           |
-+-------+---------+-------------+--------------+---------+----+-----------+
-```
-
 ## Documentation
 
-If you’re ready to get started with Citus or want to know more, we recommend reading the [Citus open source documentation](https://docs.citusdata.com/en/stable/). Or, if you are using Citus on Azure, then the [Azure Cosmos DB for PostgreSQL](https://learn.microsoft.com/azure/cosmos-db/postgresql/introduction) is the place to start.
+If you’re ready to get started with Citus or want to know more, we recommend reading the [Citus open source documentation](https://docs.citusdata.com/en/stable/). Or, if you are using Citus on Azure, then the [Hyperscale (Citus) documentation](https://docs.microsoft.com/azure/postgresql/hyperscale/) is online and available as part of the Azure Database for PostgreSQL docs.
 
-Our Citus docs contain comprehensive use case guides on how to build a [multi-tenant SaaS application](https://docs.citusdata.com/en/stable/use_cases/multi_tenant.html), [real-time analytics dashboard]( https://docs.citusdata.com/en/stable/use_cases/realtime_analytics.html), or work with [time series data](https://docs.citusdata.com/en/stable/use_cases/timeseries.html).
+Our Citus docs contain comprehensive use case guides on how to build a [multi-tenant SaaS application]( https://docs.citusdata.com/en/stable/use_cases/multi_tenant.html), [real-time analytics dashboard]( https://docs.citusdata.com/en/stable/use_cases/realtime_analytics.html), or work with [time series data]( https://docs.citusdata.com/en/stable/use_cases/timeseries.html).
 
 ## Architecture
 
@@ -423,13 +316,10 @@ A Citus database cluster grows from a single PostgreSQL node into a cluster by a
 
 Data in distributed tables is stored in “shards”, which are actually just regular PostgreSQL tables on the worker nodes. When querying a distributed table on the coordinator node, Citus will send regular SQL queries to the worker nodes. That way, all the usual PostgreSQL optimizations and extensions can automatically be used with Citus.
 
-![Citus architecture](images/citus-architecture.png)
+![Citus architecture](/citus-architecture.png)
 
 When you send a query in which all (co-located) distributed tables have the same filter on the distribution column, Citus will automatically detect that and send the whole query to the worker node that stores the data. That way, arbitrarily complex queries are supported with minimal routing overhead, which is especially useful for scaling transactional workloads. If queries do not have a specific filter, each shard is queried in parallel, which is especially useful in analytical workloads. The Citus distributed executor is adaptive and is designed to handle both query types at the same time on the same system under high concurrency, which enables large-scale mixed workloads.
 
-The schema and metadata of distributed tables and reference tables are automatically synchronized to all the nodes in the cluster. That way, you can connect to any node to run distributed queries. Schema changes and cluster administration still need to go through the coordinator.
-
-Detailed descriptions of the implementation for Citus developers are provided in the [Citus Technical Documentation](src/backend/distributed/README.md).
 
 ## When to use Citus
 
@@ -440,56 +330,48 @@ Citus is uniquely capable of scaling both analytical and transactional workloads
 
   The advanced parallel, distributed query engine in Citus combined with PostgreSQL features such as [array types](https://www.postgresql.org/docs/current/arrays.html), [JSONB](https://www.postgresql.org/docs/current/datatype-json.html), [lateral joins](https://heap.io/blog/engineering/postgresqls-powerful-new-join-type-lateral), and extensions like [HyperLogLog](https://github.com/citusdata/postgresql-hll) and [TopN](https://github.com/citusdata/postgresql-topn) allow you to build responsive analytics dashboards no matter how many customers or how much data you have.
 
-  Example real-time analytics users: [Algolia](https://www.citusdata.com/customers/algolia)
+  Example real-time analytics users: [Algolia](https://www.citusdata.com/customers/algolia), [Heap](https://www.citusdata.com/customers/heap)
 
 - **[Time series data](http://docs.citusdata.com/en/stable/use_cases/timeseries.html)**:
   Citus enables you to process and analyze very large amounts of time series data. The biggest Citus clusters store well over a petabyte of time series data and ingest terabytes per day.
 
-  Citus integrates seamlessly with [Postgres table partitioning](https://www.postgresql.org/docs/current/ddl-partitioning.html) and has [built-in functions for partitioning by time](https://www.citusdata.com/blog/2021/10/22/how-to-scale-postgres-for-time-series-data-with-citus/), which can speed up queries and writes on time series tables. You can take advantage of Citus’s parallel, distributed query engine for fast analytical queries, and use the built-in *columnar storage* to compress old partitions.
+  Citus integrates seamlessly with [Postgres table partitioning](https://www.postgresql.org/docs/current/ddl-partitioning.html) and [pg_partman](https://www.citusdata.com/blog/2018/01/24/citus-and-pg-partman-creating-a-scalable-time-series-database-on-PostgreSQL/), which can speed up queries and writes on time series tables. You can take advantage of Citus’s parallel, distributed query engine for fast analytical queries, and use the built-in *columnar storage* to compress old partitions.
 
-  Example users: [MixRank](https://www.citusdata.com/customers/mixrank)
+  Example users: [MixRank](https://www.citusdata.com/customers/mixrank), [Windows team](https://techcommunity.microsoft.com/t5/azure-database-for-postgresql/architecting-petabyte-scale-analytics-by-scaling-out-postgres-on/ba-p/969685)
 
 - **[Software-as-a-service (SaaS) applications](http://docs.citusdata.com/en/stable/use_cases/multi_tenant.html)**:
   SaaS and other multi-tenant applications need to be able to scale their database as the number of tenants/customers grows. Citus enables you to transparently shard a complex data model by the tenant dimension, so your database can grow along with your business.
 
   By distributing tables along a tenant ID column and co-locating data for the same tenant, Citus can horizontally scale complex (tenant-scoped) queries, transactions, and foreign key graphs. Reference tables and distributed DDL commands make database management a breeze compared to manual sharding. On top of that, you have a built-in distributed query engine for doing cross-tenant analytics inside the database.
 
-  Example multi-tenant SaaS users: [Salesloft](https://fivetran.com/case-studies/replicating-sharded-databases-a-case-study-of-salesloft-citus-data-and-fivetran), [ConvertFlow](https://www.citusdata.com/customers/convertflow)
-
-- **[Microservices](https://docs.citusdata.com/en/stable/get_started/tutorial_microservices.html)**: Citus supports schema based sharding, which allows distributing regular database schemas across many machines. This sharding methodology fits nicely with typical Microservices architecture, where storage is fully owned by the service hence can’t share the same schema definition with other tenants. Citus allows distributing horizontally scalable state across services, solving one of the [main problems](https://stackoverflow.blog/2020/11/23/the-macro-problem-with-microservices/) of microservices.
+  Example multi-tenant SaaS users: [Copper](https://www.citusdata.com/customers/copper), [Salesloft](https://fivetran.com/case-studies/replicating-sharded-databases-a-case-study-of-salesloft-citus-data-and-fivetran), [ConvertFlow](https://www.citusdata.com/customers/convertflow)
 
 - **Geospatial**:
   Because of the powerful [PostGIS](https://postgis.net/) extension to Postgres that adds support for geographic objects into Postgres, many people run spatial/GIS applications on top of Postgres. And since spatial location information has become part of our daily life, well, there are more geospatial applications than ever. When your Postgres database needs to scale out to handle an increased workload, Citus is a good fit.
 
-  Example geospatial users: [Helsinki Regional Transportation Authority (HSL)](https://customers.microsoft.com/story/845146-transit-authority-improves-traffic-monitoring-with-azure-database-for-postgresql-hyperscale), [MobilityDB](https://www.citusdata.com/blog/2020/11/09/analyzing-gps-trajectories-at-scale-with-postgres-mobilitydb/).
+  Example geospatial users: [Helsinki Regional Transportation Authority (HSL)](https://customers.microsoft.com/en-us/story/845146-transit-authority-improves-traffic-monitoring-with-azure-database-for-postgresql-hyperscale), [MobilityDB]( https://www.citusdata.com/blog/2020/11/09/analyzing-gps-trajectories-at-scale-with-postgres-mobilitydb/).
 
 ## Need Help?
 
 - **Slack**: Ask questions in our Citus community [Slack channel](https://slack.citusdata.com).
 - **GitHub issues**: Please submit issues via [GitHub issues](https://github.com/citusdata/citus/issues).
 - **Documentation**: Our [Citus docs](https://docs.citusdata.com ) have a wealth of resources, including sections on [query performance tuning](https://docs.citusdata.com/en/stable/performance/performance_tuning.html), [useful diagnostic queries](https://docs.citusdata.com/en/stable/admin_guide/diagnostic_queries.html), and [common error messages](https://docs.citusdata.com/en/stable/reference/common_errors.html).
-- **Docs issues**: You can also submit documentation issues via [GitHub issues for our Citus docs](https://github.com/citusdata/citus_docs/issues).
-- **Updates & Release Notes**: Learn about what's new in each Citus version on the [Citus Updates page](https://www.citusdata.com/updates/).
+- **Docs issues**: You can also submit documentation issues via [GitHub
+  issues for our Citus docs](https://github.com/citusdata/citus_docs/issues).
 
 ## Contributing
 
 Citus is built on and of open source, and we welcome your contributions. The [CONTRIBUTING.md](CONTRIBUTING.md) file explains how to get started developing the Citus extension itself and our code quality guidelines.
 
-## Code of Conduct
-
-This project has adopted the [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/).
-For more information see the [Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/) or
-contact [opencode@microsoft.com](mailto:opencode@microsoft.com) with any additional questions or comments.
-
 ## Stay Connected
 
 - **Twitter**: Follow us [@citusdata](https://twitter.com/citusdata) to track the latest posts & updates on what’s happening.
-- **Citus Blog**: Read our popular [Citus Open Source Blog](https://www.citusdata.com/blog/) for posts about PostgreSQL and Citus.
+- **Citus Blog**: Read our popular [Citus Blog](https://www.citusdata.com/blog/) for useful & informative posts about PostgreSQL and Citus.
 - **Citus Newsletter**: Subscribe to our monthly technical [Citus Newsletter](https://www.citusdata.com/join-newsletter) to get a curated collection of our favorite posts, videos, docs, talks, & other Postgres goodies.
-- **Slack**: Our [Citus Public slack](https://slack.citusdata.com/) is a good way to stay connected, not just with us but with other Citus users.
-- **Sister Blog**: Read the PostgreSQL posts on the [Azure Cosmos DB for PostgreSQL blog](https://devblogs.microsoft.com/cosmosdb/category/postgresql/) about our managed service on Azure.
+- **Slack**: Our [Citus Public slack]( https://slack.citusdata.com/) is a good way to stay connected, not just with us but with other Citus users.
+- **Sister Blog**: Read our Azure Database for PostgreSQL [sister blog on Microsoft TechCommunity](https://techcommunity.microsoft.com/t5/azure-database-for-postgresql/bg-p/ADforPostgreSQL) for posts relating to Postgres (and Citus) on Azure.
 - **Videos**: Check out this [YouTube playlist](https://www.youtube.com/playlist?list=PLixnExCn6lRq261O0iwo4ClYxHpM9qfVy) of some of our favorite Citus videos and demos. If you want to deep dive into how Citus extends PostgreSQL, you might want to check out Marco Slot’s talk at Carnegie Mellon titled [Citus: Distributed PostgreSQL as an Extension](https://youtu.be/X-aAgXJZRqM) that was part of Andy Pavlo’s Vaccination Database Talks series at CMUDB.
-- **Our other Postgres projects**: Our team also works on other awesome PostgreSQL open source extensions & projects, including: [pg_cron](https://github.com/citusdata/pg_cron), [HyperLogLog](https://github.com/citusdata/postgresql-hll), [TopN](https://github.com/citusdata/postgresql-topn), [pg_auto_failover](https://github.com/citusdata/pg_auto_failover), [activerecord-multi-tenant](https://github.com/citusdata/activerecord-multi-tenant), and [django-multitenant](https://github.com/citusdata/django-multitenant).
+- **Our other Postgres projects**: Our team also works on other awesome PostgreSQL open source extensions & projects, including: [pg_cron]( https://github.com/citusdata/pg_cron), [HyperLogLog](https://github.com/citusdata/postgresql-hll), [TopN](https://github.com/citusdata/postgresql-topn), [pg_auto_failover](https://github.com/citusdata/pg_auto_failover), [activerecord-multi-tenant](https://github.com/citusdata/activerecord-multi-tenant), and [django-multitenant](https://github.com/citusdata/django-multitenant).
 
 ___
 

SECURITY.md

@@ -1,41 +0,0 @@
-<!-- BEGIN MICROSOFT SECURITY.MD V0.0.8 BLOCK -->
-
-## Security
-
-Microsoft takes the security of our software products and services seriously, which includes all source code repositories managed through our GitHub organizations, which include [Microsoft](https://github.com/microsoft), [Azure](https://github.com/Azure), [DotNet](https://github.com/dotnet), [AspNet](https://github.com/aspnet), [Xamarin](https://github.com/xamarin), and [our GitHub organizations](https://opensource.microsoft.com/).
-
-If you believe you have found a security vulnerability in any Microsoft-owned repository that meets [Microsoft's definition of a security vulnerability](https://aka.ms/opensource/security/definition), please report it to us as described below.
-
-## Reporting Security Issues
-
-**Please do not report security vulnerabilities through public GitHub issues.**
-
-Instead, please report them to the Microsoft Security Response Center (MSRC) at [https://msrc.microsoft.com/create-report](https://aka.ms/opensource/security/create-report).
-
-If you prefer to submit without logging in, send email to [secure@microsoft.com](mailto:secure@microsoft.com).  If possible, encrypt your message with our PGP key; please download it from the [Microsoft Security Response Center PGP Key page](https://aka.ms/opensource/security/pgpkey).
-
-You should receive a response within 24 hours. If for some reason you do not, please follow up via email to ensure we received your original message. Additional information can be found at [microsoft.com/msrc](https://aka.ms/opensource/security/msrc).
-
-Please include the requested information listed below (as much as you can provide) to help us better understand the nature and scope of the possible issue:
-
-  * Type of issue (e.g. buffer overflow, SQL injection, cross-site scripting, etc.)
-  * Full paths of source file(s) related to the manifestation of the issue
-  * The location of the affected source code (tag/branch/commit or direct URL)
-  * Any special configuration required to reproduce the issue
-  * Step-by-step instructions to reproduce the issue
-  * Proof-of-concept or exploit code (if possible)
-  * Impact of the issue, including how an attacker might exploit the issue
-
-This information will help us triage your report more quickly.
-
-If you are reporting for a bug bounty, more complete reports can contribute to a higher bounty award. Please visit our [Microsoft Bug Bounty Program](https://aka.ms/opensource/security/bounty) page for more details about our active programs.
-
-## Preferred Languages
-
-We prefer all communications to be in English.
-
-## Policy
-
-Microsoft follows the principle of [Coordinated Vulnerability Disclosure](https://aka.ms/opensource/security/cvd).
-
-<!-- END MICROSOFT SECURITY.MD BLOCK -->

STYLEGUIDE.md

@@ -1,160 +0,0 @@
-# Coding style
-
-The existing code-style in our code-base is not super consistent. There are multiple reasons for that. One big reason is because our code-base is relatively old and our standards have changed over time. The second big reason is that our style-guide is different from style-guide of Postgres and some code is copied from Postgres source code and is slightly modified. The below rules are for new code. If you're changing existing code that uses a different style, use your best judgement to decide if you use the rules here or if you match the existing style.
-
-## Using citus_indent
-
-CI pipeline will automatically reject any PRs which do not follow our coding
-conventions. The easiest way to ensure your PR adheres to those conventions is
-to use the [citus_indent](https://github.com/citusdata/tools/tree/develop/uncrustify)
-tool. This tool uses `uncrustify` under the hood.
-
-```bash
-# Uncrustify changes the way it formats code every release a bit. To make sure
-# everyone formats consistently we use version 0.68.1:
-curl -L https://github.com/uncrustify/uncrustify/archive/uncrustify-0.68.1.tar.gz | tar xz
-cd uncrustify-uncrustify-0.68.1/
-mkdir build
-cd build
-cmake ..
-make -j5
-sudo make install
-cd ../..
-
-git clone https://github.com/citusdata/tools.git
-cd tools
-make uncrustify/.install
-```
-
-Once you've done that, you can run the `make reindent` command from the top
-directory to recursively check and correct the style of any source files in the
-current directory. Under the hood, `make reindent` will run `citus_indent` and
-some other style corrections for you.
-
-You can also run the following in the directory of this repository to
-automatically format all the files that you have changed before committing:
-
-```bash
-cat > .git/hooks/pre-commit << __EOF__
-#!/bin/bash
-citus_indent --check --diff || { citus_indent --diff; exit 1; }
-__EOF__
-chmod +x .git/hooks/pre-commit
-```
-
-## Other rules we follow that citus_indent does not enforce
-
-* We almost always use **CamelCase**, when naming functions, variables etc., **not snake_case**.
-
-* We also have the habits of using a **lowerCamelCase** for some variables named from their type or from their function name, as shown in the examples:
-
-  ```c
-  bool IsCitusExtensionLoaded = false;
-
-
-  bool
-  IsAlterTableRenameStmt(RenameStmt *renameStmt)
-  {
-    AlterTableCmd *alterTableCommand = NULL;
-    ..
-    ..
-
-    bool isAlterTableRenameStmt = false;
-    ..
-  }
-  ```
-
-* We **start functions with a comment**:
-
-  ```c
-  /*
-   * MyNiceFunction <something in present simple tense, e.g., processes / returns / checks / takes X as input / does Y> ..
-   * <some more nice words> ..
-   * <some more nice words> ..
-   */
-  <static?> <return type>
-  MyNiceFunction(..)
-  {
-    ..
-    ..
-  }
-  ```
-
-* `#includes` needs to be sorted based on below ordering and then alphabetically and we should not include what we don't need in a file:
-
-  * System includes (eg. #include<...>)
-  * Postgres.h (eg. #include "postgres.h")
-  * Toplevel imports from postgres, not contained in a directory (eg. #include "miscadmin.h")
-  * General postgres includes (eg . #include "nodes/...")
-  * Toplevel citus includes, not contained in a directory (eg. #include "citus_verion.h")
-  * Columnar includes (eg. #include "columnar/...")
-  * Distributed includes (eg. #include "distributed/...")
-
-* Comments:
-  ```c
-  /* single line comments start with a lower-case */
-
-  /*
-   * We start multi-line comments with a capital letter
-   * and keep adding a star to the beginning of each line
-   * until we close the comment with a star and a slash.
-   */
-  ```
-
-* Order of function implementations and their declarations in a file:
-
-  We define static functions after the functions that call them. For example:
-
-  ```c
-  #include<..>
-  #include<..>
-  ..
-  ..
-  typedef struct
-  {
-    ..
-    ..
-  } MyNiceStruct;
-  ..
-  ..
-  PG_FUNCTION_INFO_V1(my_nice_udf1);
-  PG_FUNCTION_INFO_V1(my_nice_udf2);
-  ..
-  ..
-  // ..  somewhere on top of the file …
-  static void MyNiceStaticlyDeclaredFunction1(…);
-  static void MyNiceStaticlyDeclaredFunction2(…);
-  ..
-  ..
-
-
-  void
-  MyNiceFunctionExternedViaHeaderFile(..)
-  {
-    ..
-    ..
-    MyNiceStaticlyDeclaredFunction1(..);
-    ..
-    ..
-    MyNiceStaticlyDeclaredFunction2(..);
-    ..
-  }
-
-  ..
-  ..
-
-  // we define this first because it's called by MyNiceFunctionExternedViaHeaderFile()
-  // before MyNiceStaticlyDeclaredFunction2()
-  static void
-  MyNiceStaticlyDeclaredFunction1(…)
-  {
-  }
-  ..
-  ..
-
-  // then we define this
-  static void
-  MyNiceStaticlyDeclaredFunction2(…)
-  {
-  }
-  ```

autogen.sh

@@ -1,6 +1,6 @@
 #!/bin/bash
 #
-# autogen.sh converts configure.ac to configure and creates
+# autogen.sh converts configure.in to configure and creates
 # citus_config.h.in. The resuting resulting files are checked into
 # the SCM, to avoid everyone needing autoconf installed.
 

ci/README.md

@@ -283,14 +283,6 @@ actually run in CI. This is most commonly forgotten for newly added CI tests
 that the developer only ran locally. It also checks that all CI scripts have a
 section in this `README.md` file and that they include `ci/ci_helpers.sh`.
 
-## `check_migration_files.sh`
-
-A branch that touches a set of upgrade scripts is also expected to touch
-corresponding downgrade scripts as well. If this script fails, read the output
-and make sure you update the downgrade scripts in the printed list. If you
-really don't need a downgrade to run any SQL. You can write a comment in the
-file explaining why a downgrade step is not necessary.
-
 ## `disallow_c_comments_in_migrations.sh`
 
 We do not use C-style comments in migration files as the stripped
@@ -371,8 +363,11 @@ This was deemed to be error prone and not worth the effort.
 
 This script checks and fixes issues with `.gitignore` rules:
 
+1. Makes sure git ignores the `.sql` files and expected output files that are generated
+   from `.source` template files. If you created or deleted a `.source` file in a commit,
+   git ignore rules should be updated to reflect this change.
 
-1. Makes sure we do not commit any generated files that should be ignored. If there is an
+2. Makes sure we do not commit any generated files that should be ignored. If there is an
    ignored file in the git tree, the user is expected to review the files that are removed
    from the git tree and commit them.
 
@@ -381,22 +376,3 @@ This script checks and fixes issues with `.gitignore` rules:
 This script checks the order of the GUCs defined in `shared_library_init.c`.
 To solve this failure, please check `shared_library_init.c` and make sure that the GUC
 definitions are in alphabetical order.
-
-## `print_stack_trace.sh`
-
-This script prints stack traces for failed tests, if they left core files.
-
-## `sort_and_group_includes.sh`
-
-This script checks and fixes issues with include grouping and sorting in C files.
-
-Includes are grouped in the following groups:
- - System includes (eg. `#include <math>`)
- - Postgres.h include (eg. `#include "postgres.h"`)
- - Toplevel postgres includes (includes not in a directory eg. `#include "miscadmin.h`)
- - Postgres includes in a directory (eg. `#include "catalog/pg_type.h"`)
- - Toplevel citus includes (includes not in a directory eg. `#include "pg_version_constants.h"`)
- - Columnar includes (eg. `#include "columnar/columnar.h"`)
- - Distributed includes (eg. `#include "distributed/maintenanced.h"`)
-
-Within every group the include lines are sorted alphabetically.

ci/build-citus.sh

@@ -15,6 +15,9 @@ PG_MAJOR=${PG_MAJOR:?please provide the postgres major version}
 codename=${VERSION#*(}
 codename=${codename%)*}
 
+# get project from argument
+project="${CIRCLE_PROJECT_REPONAME}"
+
 # we'll do everything with absolute paths
 basedir="$(pwd)"
 
@@ -25,7 +28,7 @@ build_ext() {
   pg_major="$1"
 
   builddir="${basedir}/build-${pg_major}"
-  echo "Beginning build for PostgreSQL ${pg_major}..." >&2
+  echo "Beginning build of ${project} for PostgreSQL ${pg_major}..." >&2
 
   # do everything in a subdirectory to avoid clutter in current directory
   mkdir -p "${builddir}" && cd "${builddir}"

ci/check_all_ci_scripts_are_run.sh

@@ -14,8 +14,8 @@ ci_scripts=$(
     grep -v -E '^(ci_helpers.sh|fix_style.sh)$'
 )
 for script in $ci_scripts; do
-    if ! grep "\\bci/$script\\b" -r .github > /dev/null; then
-        echo "ERROR: CI script with name \"$script\" is not actually used in .github folder"
+    if ! grep "\\bci/$script\\b" .circleci/config.yml > /dev/null; then
+        echo "ERROR: CI script with name \"$script\" is not actually used in .circleci/config.yml"
         exit 1
     fi
     if ! grep "^## \`$script\`\$" ci/README.md > /dev/null; then

ci/check_all_tests_are_run.sh

@@ -7,12 +7,13 @@ source ci/ci_helpers.sh
 
 cd src/test/regress
 
-# 1. Find all *.sql and *.spec files in the sql, and spec directories
+# 1. Find all *.sql *.spec and *.source files in the sql, spec and input
+#    directories
 # 2. Strip the extension and the directory
 # 3. Ignore names that end with .include, those files are meant to be in an C
 #    preprocessor #include statement. They should not be in schedules.
 test_names=$(
-    find sql spec -iname "*.sql" -o -iname "*.spec" |
+    find sql spec input -iname "*.sql" -o -iname "*.spec" -o -iname "*.source" |
     sed -E 's#^\w+/([^/]+)\.[^.]+$#\1#g' |
     grep -v '.include$'
 )

ci/check_enterprise_merge.sh

@@ -0,0 +1,96 @@
+#!/bin/bash
+
+# Testing this script locally requires you to set the following environment
+# variables:
+# CIRCLE_BRANCH, GIT_USERNAME and GIT_TOKEN
+
+# fail if trying to reference a variable that is not set.
+set -u
+# exit immediately if a command fails
+set -e
+# Fail on pipe failures
+set -o pipefail
+
+PR_BRANCH="${CIRCLE_BRANCH}"
+ENTERPRISE_REMOTE="https://${GIT_USERNAME}:${GIT_TOKEN}@github.com/citusdata/citus-enterprise"
+
+# shellcheck disable=SC1091
+source ci/ci_helpers.sh
+
+# List executed commands. This is done so debugging this script is easier when
+# it fails. It's explicitly done after git remote add so username and password
+# are not shown in CI output (even though it's also filtered out by CircleCI)
+set -x
+
+check_compile () {
+    echo "INFO: checking if merged code can be compiled"
+    ./configure --without-libcurl
+    make -j10
+}
+
+# Clone current git repo (which should be community) to a temporary working
+# directory and go there
+GIT_DIR_ROOT="$(git rev-parse --show-toplevel)"
+TMP_GIT_DIR="$(mktemp --directory -t citus-merge-check.XXXXXXXXX)"
+git clone "$GIT_DIR_ROOT" "$TMP_GIT_DIR"
+cd "$TMP_GIT_DIR"
+
+# Fails in CI without this
+git config user.email "citus-bot@microsoft.com"
+git config user.name "citus bot"
+
+# Disable "set -x" temporarily, because $ENTERPRISE_REMOTE contains passwords
+{ set +x ; } 2> /dev/null
+git remote add enterprise "$ENTERPRISE_REMOTE"
+set -x
+
+git remote set-url --push enterprise no-pushing
+
+# Fetch enterprise-master
+git fetch enterprise enterprise-master
+
+
+git checkout "enterprise/enterprise-master"
+
+if git merge --no-commit "origin/$PR_BRANCH"; then
+    echo "INFO: community PR branch could be merged into enterprise-master"
+    # check that we can compile after the merge
+    if check_compile; then
+        exit 0
+    fi
+
+    echo "WARN: Failed to compile after community PR branch was merged into enterprise"
+fi
+
+# undo partial merge
+git merge --abort
+
+# If we have a conflict on enterprise merge on the master branch, we have a problem.
+# Provide an error message to indicate that enterprise merge is needed to fix this check.
+if [[ $PR_BRANCH = master ]]; then
+    echo "ERROR: Master branch has merge conflicts with enterprise-master."
+    echo "Try re-running this CI job after merging your changes into enterprise-master."
+    exit 1
+fi
+
+if ! git fetch enterprise "$PR_BRANCH" ; then
+    echo "ERROR: enterprise/$PR_BRANCH was not found and community PR branch could not be merged into enterprise-master"
+    exit 1
+fi
+
+# Show the top commit of the enterprise PR branch to make debugging easier
+git log -n 1 "enterprise/$PR_BRANCH"
+
+# Check that this branch contains the top commit of the current community PR
+# branch. If it does not it means it's not up to date with the current PR, so
+# the enterprise branch should be updated.
+if ! git merge-base --is-ancestor "origin/$PR_BRANCH" "enterprise/$PR_BRANCH" ; then
+    echo "ERROR: enterprise/$PR_BRANCH is not up to date with community PR branch"
+    exit 1
+fi
+
+# Now check if we can merge the enterprise PR into enterprise-master without
+# issues.
+git merge --no-commit "enterprise/$PR_BRANCH"
+# check that we can compile after the merge
+check_compile

ci/check_gucs_are_alphabetically_sorted.sh

@@ -4,22 +4,7 @@ set -euo pipefail
 # shellcheck disable=SC1091
 source ci/ci_helpers.sh
 
-# Find the line that exactly matches "RegisterCitusConfigVariables(void)" in
-# shared_library_init.c. grep command returns something like
-# "934:RegisterCitusConfigVariables(void)" and we extract the line number
-# with cut.
-RegisterCitusConfigVariables_begin_linenumber=$(grep -n "^RegisterCitusConfigVariables(void)$" src/backend/distributed/shared_library_init.c | cut -d: -f1)
-
-# Consider the lines starting from $RegisterCitusConfigVariables_begin_linenumber,
-# grep the first line that starts with "}" and extract the line number with cut
-# as in the previous step.
-RegisterCitusConfigVariables_length=$(tail -n +$RegisterCitusConfigVariables_begin_linenumber src/backend/distributed/shared_library_init.c | grep -n -m 1 "^}$" | cut -d: -f1)
-
-# extract the function definition of RegisterCitusConfigVariables into a temp file
-tail -n +$RegisterCitusConfigVariables_begin_linenumber src/backend/distributed/shared_library_init.c | head -n $(($RegisterCitusConfigVariables_length)) > RegisterCitusConfigVariables_func_def.out
-
-# extract citus gucs in the form of <tab><tab>"citus.X"
-grep -P "^[\t][\t]\"citus\.[a-zA-Z_0-9]+\"" RegisterCitusConfigVariables_func_def.out > gucs.out
-LC_COLLATE=C sort -c gucs.out
+# extract citus gucs in the form of "citus.X"
+grep -o -E "(\.*\"citus.\w+\")," src/backend/distributed/shared_library_init.c > gucs.out
+sort -c gucs.out
 rm gucs.out
-rm RegisterCitusConfigVariables_func_def.out

ci/check_migration_files.sh

@@ -1,33 +0,0 @@
-#! /bin/bash
-
-set -euo pipefail
-# shellcheck disable=SC1091
-source ci/ci_helpers.sh
-
-# This file checks for the existence of downgrade scripts for every upgrade script that is changed in the branch.
-
-# create list of migration files for upgrades
-upgrade_files=$(git diff --name-only origin/main | { grep "src/backend/distributed/sql/citus--.*sql" || exit 0 ; })
-downgrade_files=$(git diff --name-only origin/main | { grep "src/backend/distributed/sql/downgrades/citus--.*sql" || exit 0 ; })
-ret_value=0
-
-for file in $upgrade_files
-do
-    # There should always be 2 matches, and no need to avoid splitting here
-    # shellcheck disable=SC2207
-    versions=($(grep --only-matching --extended-regexp "[0-9]+\.[0-9]+[-.][0-9]+" <<< "$file"))
-
-    from_version=${versions[0]};
-    to_version=${versions[1]};
-
-    downgrade_migration_file="src/backend/distributed/sql/downgrades/citus--$to_version--$from_version.sql"
-
-    # check for the existence of migration scripts
-    if [[ $(grep --line-regexp --count "$downgrade_migration_file" <<< "$downgrade_files") == 0 ]]
-    then
-        echo "$file is updated, but $downgrade_migration_file is not updated in branch"
-        ret_value=1
-    fi
-done
-
-exit $ret_value;

ci/fix_gitignore.sh

@@ -1,12 +1,27 @@
 #! /bin/bash
+# shellcheck disable=SC2012
+
 set -euo pipefail
 # shellcheck disable=SC1091
 source ci/ci_helpers.sh
 
+# We list all the .source files in alphabetical order, and do a substitution
+# before writing the resulting file names that are created by those templates in
+# relevant .gitignore files
+#
+# 1. Capture the file name without the .source extension
+# 2. Add the desired extension at the end
+# 3. Add a / character at the beginning of each line to conform to .gitignore file format
+#
+# e.g. multi_copy.source -> /multi_copy.sql
+ls -1 src/test/regress/input | sed -E "s#(.*)\.source#/\1.sql#" > src/test/regress/sql/.gitignore
+
+# e.g. multi_copy.source -> /multi_copy.out
+ls -1 src/test/regress/output | sed -E "s#(.*)\.source#/\1.out#" > src/test/regress/expected/.gitignore
+
 # Remove all the ignored files from git tree, and error out
 # find all ignored files in git tree, and use quotation marks to prevent word splitting on filenames with spaces in them
-# NOTE: Option --cached is needed to avoid a bug in git ls-files command.
-ignored_lines_in_git_tree=$(git ls-files --ignored --cached --exclude-standard | sed 's/.*/"&"/')
+ignored_lines_in_git_tree=$(git ls-files --ignored --exclude-standard | sed 's/.*/"&"/')
 
 if [[ -n $ignored_lines_in_git_tree ]]
 then

ci/fix_style.sh

@@ -9,8 +9,6 @@ cidir="${0%/*}"
 cd ${cidir}/..
 
 citus_indent . --quiet
-black . --quiet
-isort . --quiet
 ci/editorconfig.sh
 ci/remove_useless_declarations.sh
 ci/disallow_c_comments_in_migrations.sh
@@ -18,5 +16,3 @@ ci/disallow_hash_comments_in_spec_files.sh
 ci/disallow_long_changelog_entries.sh
 ci/normalize_expected.sh
 ci/fix_gitignore.sh
-ci/print_stack_trace.sh
-ci/sort_and_group_includes.sh

ci/include_grouping.py

@@ -1,157 +0,0 @@
-#!/usr/bin/env python3
-"""
-easy command line to run against all citus-style checked files:
-
-$ git ls-files \
-  | git check-attr --stdin citus-style \
-  | grep 'citus-style: set' \
-  | awk '{print $1}' \
-  | cut -d':' -f1 \
-  | xargs -n1 ./ci/include_grouping.py
-"""
-
-import collections
-import os
-import sys
-
-
-def main(args):
-    if len(args) < 2:
-        print("Usage: include_grouping.py <file>")
-        return
-
-    file = args[1]
-    if not os.path.isfile(file):
-        sys.exit(f"File '{file}' does not exist")
-
-    with open(file, "r") as in_file:
-        with open(file + ".tmp", "w") as out_file:
-            includes = []
-            skipped_lines = []
-
-            # This calls print_sorted_includes on a set of consecutive #include lines.
-            # This implicitly keeps separation of any #include lines that are contained in
-            # an #ifdef, because it will order the #include lines inside and after the
-            # #ifdef completely separately.
-            for line in in_file:
-                # if a line starts with #include we don't want to print it yet, instead we
-                # want to collect all consecutive #include lines
-                if line.startswith("#include"):
-                    includes.append(line)
-                    skipped_lines = []
-                    continue
-
-                # if we have collected any #include lines, we want to print them sorted
-                # before printing the current line. However, if the current line is empty
-                # we want to perform a lookahead to see if the next line is an #include.
-                # To maintain any separation between #include lines and their subsequent
-                # lines we keep track of all lines we have skipped inbetween.
-                if len(includes) > 0:
-                    if len(line.strip()) == 0:
-                        skipped_lines.append(line)
-                        continue
-
-                    # we have includes that need to be grouped before printing the current
-                    # line.
-                    print_sorted_includes(includes, file=out_file)
-                    includes = []
-
-                    # print any skipped lines
-                    print("".join(skipped_lines), end="", file=out_file)
-                    skipped_lines = []
-
-                print(line, end="", file=out_file)
-
-    # move out_file to file
-    os.rename(file + ".tmp", file)
-
-
-def print_sorted_includes(includes, file=sys.stdout):
-    default_group_key = 1
-    groups = collections.defaultdict(set)
-
-    # define the groups that we separate correctly. The matchers are tested in the order
-    # of their priority field. The first matcher that matches the include is used to
-    # assign the include to a group.
-    # The groups are printed in the order of their group_key.
-    matchers = [
-        {
-            "name": "system includes",
-            "matcher": lambda x: x.startswith("<"),
-            "group_key": -2,
-            "priority": 0,
-        },
-        {
-            "name": "toplevel postgres includes",
-            "matcher": lambda x: "/" not in x,
-            "group_key": 0,
-            "priority": 9,
-        },
-        {
-            "name": "postgres.h",
-            "matcher": lambda x: x.strip() in ['"postgres.h"'],
-            "group_key": -1,
-            "priority": -1,
-        },
-        {
-            "name": "toplevel citus inlcudes",
-            "matcher": lambda x: x.strip()
-            in [
-                '"citus_version.h"',
-                '"pg_version_compat.h"',
-                '"pg_version_constants.h"',
-            ],
-            "group_key": 3,
-            "priority": 0,
-        },
-        {
-            "name": "columnar includes",
-            "matcher": lambda x: x.startswith('"columnar/'),
-            "group_key": 4,
-            "priority": 1,
-        },
-        {
-            "name": "distributed includes",
-            "matcher": lambda x: x.startswith('"distributed/'),
-            "group_key": 5,
-            "priority": 1,
-        },
-    ]
-    matchers.sort(key=lambda x: x["priority"])
-
-    # throughout our codebase we have some includes where either postgres or citus
-    # includes are wrongfully included with the syntax for system includes. Before we
-    # try to match those we will change the <> to "" to make them match our system. This
-    # will also rewrite the include to the correct syntax.
-    common_system_include_error_prefixes = ["<nodes/", "<distributed/"]
-
-    # assign every include to a group
-    for include in includes:
-        # extract the group key from the include
-        include_content = include.split(" ")[1]
-
-        # fix common system includes which are secretly postgres or citus includes
-        for common_prefix in common_system_include_error_prefixes:
-            if include_content.startswith(common_prefix):
-                include_content = '"' + include_content.strip()[1:-1] + '"'
-                include = include.split(" ")[0] + " " + include_content + "\n"
-                break
-
-        group_key = default_group_key
-        for matcher in matchers:
-            if matcher["matcher"](include_content):
-                group_key = matcher["group_key"]
-                break
-
-        groups[group_key].add(include)
-
-    # iterate over all groups in the natural order of its keys
-    for i, group in enumerate(sorted(groups.items())):
-        if i > 0:
-            print(file=file)
-        includes = group[1]
-        print("".join(sorted(includes)), end="", file=file)
-
-
-if __name__ == "__main__":
-    main(sys.argv)

ci/print_stack_trace.sh

@@ -1,25 +0,0 @@
-#!/bin/bash
-
-set -euo pipefail
-
-# shellcheck disable=SC1091
-source ci/ci_helpers.sh
-
-# find all core files
-core_files=( $(find . -type f -regex .*core.*\d*.*postgres) )
-if [ ${#core_files[@]} -gt 0 ]; then
-    # print stack traces for the core files
-    for core_file in "${core_files[@]}"
-    do
-        # set print frame-arguments all: show all scalars + structures in the frame
-        # set print pretty on:           show structures in indented mode
-        # set print addr off:            do not show pointer address
-        # thread apply all bt full:      show stack traces for all threads
-        gdb --batch \
-            -ex "set print frame-arguments all" \
-            -ex "set print pretty on" \
-            -ex "set print addr off" \
-            -ex "thread apply all bt full" \
-            postgres "${core_file}"
-    done
-fi

ci/sort_and_group_includes.sh

@@ -1,12 +0,0 @@
-#!/bin/bash
-
-set -euo pipefail
-# shellcheck disable=SC1091
-source ci/ci_helpers.sh
-
-git ls-files \
-  | git check-attr --stdin citus-style \
-  | grep 'citus-style: set' \
-  | awk '{print $1}' \
-  | cut -d':' -f1 \
-  | xargs -n1 ./ci/include_grouping.py

config/general.m4

@@ -10,7 +10,7 @@
 # argument (other than "yes/no"), etc.
 #
 # The point of this implementation is to reduce code size and
-# redundancy in configure.ac and to improve robustness and consistency
+# redundancy in configure.in and to improve robustness and consistency
 # in the option evaluation code.
 
 

configure

@@ -1,6 +1,6 @@
 #! /bin/sh
 # Guess values for system-dependent variables and create Makefiles.
-# Generated by GNU Autoconf 2.69 for Citus 13.2devel.
+# Generated by GNU Autoconf 2.69 for Citus 11.0.3.
 #
 #
 # Copyright (C) 1992-1996, 1998-2012 Free Software Foundation, Inc.
@@ -579,8 +579,8 @@ MAKEFLAGS=
 # Identity of this package.
 PACKAGE_NAME='Citus'
 PACKAGE_TARNAME='citus'
-PACKAGE_VERSION='13.2devel'
-PACKAGE_STRING='Citus 13.2devel'
+PACKAGE_VERSION='11.0.3'
+PACKAGE_STRING='Citus 11.0.3'
 PACKAGE_BUGREPORT=''
 PACKAGE_URL=''
 
@@ -644,7 +644,6 @@ LDFLAGS
 CFLAGS
 CC
 vpath_build
-with_pg_version_check
 PATH
 PG_CONFIG
 FLEX
@@ -693,7 +692,6 @@ ac_subst_files=''
 ac_user_opts='
 enable_option_checking
 with_extra_version
-with_pg_version_check
 enable_coverage
 with_libcurl
 with_reports_hostname
@@ -1262,7 +1260,7 @@ if test "$ac_init_help" = "long"; then
   # Omit some internal or obsolete options to make the list less imposing.
   # This message is too long to be a string in the A/UX 3.1 sh.
   cat <<_ACEOF
-\`configure' configures Citus 13.2devel to adapt to many kinds of systems.
+\`configure' configures Citus 11.0.3 to adapt to many kinds of systems.
 
 Usage: $0 [OPTION]... [VAR=VALUE]...
 
@@ -1324,7 +1322,7 @@ fi
 
 if test -n "$ac_init_help"; then
   case $ac_init_help in
-     short | recursive ) echo "Configuration of Citus 13.2devel:";;
+     short | recursive ) echo "Configuration of Citus 11.0.3:";;
    esac
   cat <<\_ACEOF
 
@@ -1339,8 +1337,6 @@ Optional Packages:
   --without-PACKAGE       do not use PACKAGE (same as --with-PACKAGE=no)
   --with-extra-version=STRING
                           append STRING to version
-  --without-pg-version-check
-                          do not check postgres version during configure
   --without-libcurl       do not use libcurl for anonymous statistics
                           collection
   --with-reports-hostname=HOSTNAME
@@ -1429,7 +1425,7 @@ fi
 test -n "$ac_init_help" && exit $ac_status
 if $ac_init_version; then
   cat <<\_ACEOF
-Citus configure 13.2devel
+Citus configure 11.0.3
 generated by GNU Autoconf 2.69
 
 Copyright (C) 2012 Free Software Foundation, Inc.
@@ -1912,7 +1908,7 @@ cat >config.log <<_ACEOF
 This file contains any messages produced by compilers while
 running configure, to aid debugging if configure makes a mistake.
 
-It was created by Citus $as_me 13.2devel, which was
+It was created by Citus $as_me 11.0.3, which was
 generated by GNU Autoconf 2.69.  Invocation command line was
 
   $ $0 $@
@@ -2559,36 +2555,7 @@ if test -z "$version_num"; then
   as_fn_error $? "Could not detect PostgreSQL version from pg_config." "$LINENO" 5
 fi
 
-
-
-
-# Check whether --with-pg-version-check was given.
-if test "${with_pg_version_check+set}" = set; then :
-  withval=$with_pg_version_check;
-  case $withval in
-    yes)
-      :
-      ;;
-    no)
-      :
-      ;;
-    *)
-      as_fn_error $? "no argument expected for --with-pg-version-check option" "$LINENO" 5
-      ;;
-  esac
-
-else
-  with_pg_version_check=yes
-
-fi
-
-
-
-
-if test "$with_pg_version_check" = no; then
-    { $as_echo "$as_me:${as_lineno-$LINENO}: building against PostgreSQL $version_num (skipped compatibility check)" >&5
-$as_echo "$as_me: building against PostgreSQL $version_num (skipped compatibility check)" >&6;}
-elif test "$version_num" != '15' -a  "$version_num" != '16' -a  "$version_num" != '17'; then
+if test "$version_num" != '13' -a "$version_num" != '14'; then
    as_fn_error $? "Citus is not compatible with the detected PostgreSQL version ${version_num}." "$LINENO" 5
 else
    { $as_echo "$as_me:${as_lineno-$LINENO}: building against PostgreSQL $version_num" >&5
@@ -5393,7 +5360,7 @@ cat >>$CONFIG_STATUS <<\_ACEOF || ac_write_fail=1
 # report actual input values of CONFIG_FILES etc. instead of their
 # values after options handling.
 ac_log="
-This file was extended by Citus $as_me 13.2devel, which was
+This file was extended by Citus $as_me 11.0.3, which was
 generated by GNU Autoconf 2.69.  Invocation command line was
 
   CONFIG_FILES    = $CONFIG_FILES
@@ -5455,7 +5422,7 @@ _ACEOF
 cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1
 ac_cs_config="`$as_echo "$ac_configure_args" | sed 's/^ //; s/[\\""\`\$]/\\\\&/g'`"
 ac_cs_version="\\
-Citus config.status 13.2devel
+Citus config.status 11.0.3
 configured by $0, generated by GNU Autoconf 2.69,
   with options \\"\$ac_cs_config\\"
 

configure.in

@@ -5,7 +5,7 @@
 # everyone needing autoconf installed, the resulting files are checked
 # into the SCM.
 
-AC_INIT([Citus], [13.2devel])
+AC_INIT([Citus], [11.0.3])
 AC_COPYRIGHT([Copyright (c) Citus Data, Inc.])
 
 # we'll need sed and awk for some of the version commands
@@ -74,13 +74,7 @@ if test -z "$version_num"; then
   AC_MSG_ERROR([Could not detect PostgreSQL version from pg_config.])
 fi
 
-PGAC_ARG_BOOL(with, pg-version-check, yes,
-              [do not check postgres version during configure])
-AC_SUBST(with_pg_version_check)
-
-if test "$with_pg_version_check" = no; then
-    AC_MSG_NOTICE([building against PostgreSQL $version_num (skipped compatibility check)])
-elif test "$version_num" != '15' -a  "$version_num" != '16' -a  "$version_num" != '17'; then
+if test "$version_num" != '13' -a "$version_num" != '14'; then
    AC_MSG_ERROR([Citus is not compatible with the detected PostgreSQL version ${version_num}.])
 else
    AC_MSG_NOTICE([building against PostgreSQL $version_num])

pyproject.toml

@@ -1,40 +0,0 @@
-[tool.isort]
-profile = 'black'
-
-[tool.black]
-include = '(src/test/regress/bin/diff-filter|\.pyi?|\.ipynb)$'
-
-[tool.pytest.ini_options]
-addopts = [
-    "--import-mode=importlib",
-    "--showlocals",
-    "--tb=short",
-]
-pythonpath = 'src/test/regress/citus_tests'
-asyncio_mode = 'auto'
-
-# Make test discovery quicker from the root dir of the repo
-testpaths = ['src/test/regress/citus_tests/test']
-
-# Make test discovery quicker from other directories than root directory
-norecursedirs = [
-    '*.egg',
-    '.*',
-    'build',
-    'venv',
-    'ci',
-    'vendor',
-    'backend',
-    'bin',
-    'include',
-    'tmp_*',
-    'results',
-    'expected',
-    'sql',
-    'spec',
-    'data',
-    '__pycache__',
-]
-
-# Don't find files with test at the end such as run_test.py
-python_files = ['test_*.py']

src/backend/columnar/.gitattributes

@@ -16,6 +16,7 @@ README.*	conflict-marker-size=32
 
 # Test output files that contain extra whitespace
 *.out					-whitespace
+src/test/regress/output/*.source	-whitespace
 
 # These files are maintained or generated elsewhere.  We take them as is.
 configure				-whitespace

src/backend/columnar/.gitignore

@@ -1,3 +0,0 @@
-# The directory used to store columnar sql files after pre-processing them
-# with 'cpp' in build-time, see src/backend/columnar/Makefile.
-/build/

src/backend/columnar/Makefile

@@ -1,60 +0,0 @@
-citus_subdir = src/backend/columnar
-citus_top_builddir = ../../..
-safestringlib_srcdir = $(citus_abs_top_srcdir)/vendor/safestringlib
-SUBDIRS = . safeclib
-SUBDIRS +=
-ENSURE_SUBDIRS_EXIST := $(shell mkdir -p $(SUBDIRS))
-OBJS += \
-	$(patsubst $(citus_abs_srcdir)/%.c,%.o,$(foreach dir,$(SUBDIRS), $(sort $(wildcard $(citus_abs_srcdir)/$(dir)/*.c))))
-
-MODULE_big = citus_columnar
-EXTENSION = citus_columnar
-
-template_sql_files = $(patsubst $(citus_abs_srcdir)/%,%,$(wildcard $(citus_abs_srcdir)/sql/*.sql))
-template_downgrade_sql_files = $(patsubst $(citus_abs_srcdir)/sql/downgrades/%,%,$(wildcard $(citus_abs_srcdir)/sql/downgrades/*.sql))
-generated_sql_files = $(patsubst %,$(citus_abs_srcdir)/build/%,$(template_sql_files))
-generated_downgrade_sql_files += $(patsubst %,$(citus_abs_srcdir)/build/sql/%,$(template_downgrade_sql_files))
-
-DATA_built = $(generated_sql_files)
-
-PG_CPPFLAGS += -I$(libpq_srcdir) -I$(safestringlib_srcdir)/include
-
-include $(citus_top_builddir)/Makefile.global
-
-SQL_DEPDIR=.deps/sql
-SQL_BUILDDIR=build/sql
-
-$(generated_sql_files): $(citus_abs_srcdir)/build/%: %
-	@mkdir -p $(citus_abs_srcdir)/$(SQL_DEPDIR) $(citus_abs_srcdir)/$(SQL_BUILDDIR)
-	@# -MF is used to store dependency files(.Po) in another directory for separation
-	@# -MT is used to change the target of the rule emitted by dependency generation.
-	@# -P is used to inhibit generation of linemarkers in the output from the preprocessor.
-	@# -undef is used to not predefine any system-specific or GCC-specific macros.
-	@# `man cpp` for further information
-	cd $(citus_abs_srcdir) && cpp -undef -w -P -MMD -MP -MF$(SQL_DEPDIR)/$(*F).Po -MT$@ $< > $@
-
-$(generated_downgrade_sql_files): $(citus_abs_srcdir)/build/sql/%: sql/downgrades/%
-	@mkdir -p $(citus_abs_srcdir)/$(SQL_DEPDIR) $(citus_abs_srcdir)/$(SQL_BUILDDIR)
-	@# -MF is used to store dependency files(.Po) in another directory for separation
-	@# -MT is used to change the target of the rule emitted by dependency generation.
-	@# -P is used to inhibit generation of linemarkers in the output from the preprocessor.
-	@# -undef is used to not predefine any system-specific or GCC-specific macros.
-	@# `man cpp` for further information
-	cd $(citus_abs_srcdir) && cpp -undef -w -P -MMD -MP -MF$(SQL_DEPDIR)/$(*F).Po -MT$@ $< > $@
-
-.PHONY: install install-downgrades install-all
-
-cleanup-before-install:
-	rm -f $(DESTDIR)$(datadir)/$(datamoduledir)/citus_columnar.control
-	rm -f $(DESTDIR)$(datadir)/$(datamoduledir)/columnar--*
-	rm -f $(DESTDIR)$(datadir)/$(datamoduledir)/citus_columnar--*
-
-install: cleanup-before-install
-
-# install and install-downgrades should be run sequentially
-install-all: install
-	$(MAKE) install-downgrades
-
-install-downgrades: $(generated_downgrade_sql_files)
-	$(INSTALL_DATA) $(generated_downgrade_sql_files) '$(DESTDIR)$(datadir)/$(datamoduledir)/'
-

src/backend/columnar/README.md

@@ -52,7 +52,8 @@ Benefits of Citus Columnar over cstore_fdw:
   ... FOR UPDATE``)
 * No support for serializable isolation level
 * Support for PostgreSQL server versions 12+ only
-* No support for foreign keys
+* No support for foreign keys, unique constraints, or exclusion
+  constraints
 * No support for logical decoding
 * No support for intra-node parallel scans
 * No support for ``AFTER ... FOR EACH ROW`` triggers
@@ -89,25 +90,38 @@ data.
 Set options using:
 
 ```sql
-ALTER TABLE my_columnar_table SET
-  (columnar.compression = none, columnar.stripe_row_limit = 10000);
+alter_columnar_table_set(
+    relid REGCLASS,
+    chunk_group_row_limit INT4 DEFAULT NULL,
+    stripe_row_limit INT4 DEFAULT NULL,
+    compression NAME DEFAULT NULL,
+    compression_level INT4)
+```
+
+For example:
+
+```sql
+SELECT alter_columnar_table_set(
+    'my_columnar_table',
+    compression => 'none',
+    stripe_row_limit => 10000);
 ```
 
 The following options are available:
 
-* **columnar.compression**: `[none|pglz|zstd|lz4|lz4hc]` - set the compression type
+* **compression**: `[none|pglz|zstd|lz4|lz4hc]` - set the compression type
   for _newly-inserted_ data. Existing data will not be
   recompressed/decompressed. The default value is `zstd` (if support
   has been compiled in).
-* **columnar.compression_level**: ``<integer>`` - Sets compression level. Valid
+* **compression_level**: ``<integer>`` - Sets compression level. Valid
   settings are from 1 through 19. If the compression method does not
   support the level chosen, the closest level will be selected
   instead.
-* **columnar.stripe_row_limit**: ``<integer>`` - the maximum number of rows per
+* **stripe_row_limit**: ``<integer>`` - the maximum number of rows per
   stripe for _newly-inserted_ data. Existing stripes of data will not
   be changed and may have more rows than this maximum value. The
   default value is `150000`.
-* **columnar.chunk_group_row_limit**: ``<integer>`` - the maximum number of rows per
+* **chunk_group_row_limit**: ``<integer>`` - the maximum number of rows per
   chunk for _newly-inserted_ data. Existing chunks of data will not be
   changed and may have more rows than this maximum value. The default
   value is `10000`.
@@ -233,14 +247,16 @@ CREATE TABLE perf_columnar(LIKE perf_row) USING COLUMNAR;
 ## Data
 
 ```sql
-CREATE OR REPLACE FUNCTION random_words(n INT4) RETURNS TEXT LANGUAGE sql AS $$
-  WITH words(w) AS (
-    SELECT ARRAY['zero','one','two','three','four','five','six','seven','eight','nine','ten']
-  ),
-  random (word) AS (
-    SELECT w[(random()*array_length(w, 1))::int] FROM generate_series(1, $1) AS i, words
-  )
-  SELECT string_agg(word, ' ') FROM random;
+CREATE OR REPLACE FUNCTION random_words(n INT4) RETURNS TEXT LANGUAGE plpython2u AS $$
+import random
+t = ''
+words = ['zero','one','two','three','four','five','six','seven','eight','nine','ten']
+for i in xrange(0,n):
+  if (i != 0):
+    t += ' '
+  r = random.randint(0,len(words)-1)
+  t += words[r]
+return t
 $$;
 ```
 

src/backend/columnar/citus_columnar.control

@@ -1,6 +0,0 @@
-# Columnar extension
-comment = 'Citus Columnar extension'
-default_version = '12.2-1'
-module_pathname = '$libdir/citus_columnar'
-relocatable = false
-schema = pg_catalog

src/backend/columnar/columnar.c

@@ -11,20 +11,17 @@
  *-------------------------------------------------------------------------
  */
 
+#include "postgres.h"
+
 #include <sys/stat.h>
 #include <unistd.h>
 
-#include "postgres.h"
-
 #include "miscadmin.h"
-
 #include "utils/guc.h"
 #include "utils/rel.h"
 
 #include "citus_version.h"
-
 #include "columnar/columnar.h"
-#include "columnar/columnar_tableam.h"
 
 /* Default values for option parameters */
 #define DEFAULT_STRIPE_ROW_COUNT 150000
@@ -56,14 +53,6 @@ static const struct config_enum_entry columnar_compression_options[] =
 	{ NULL, 0, false }
 };
 
-void
-columnar_init(void)
-{
-	columnar_init_gucs();
-	columnar_tableam_init();
-}
-
-
 void
 columnar_init_gucs()
 {

src/backend/columnar/columnar_compression.c

@@ -13,22 +13,16 @@
  */
 #include "postgres.h"
 
+#include "citus_version.h"
 #include "common/pg_lzcompress.h"
 #include "lib/stringinfo.h"
 
-#include "citus_version.h"
-#include "pg_version_constants.h"
-
 #include "columnar/columnar_compression.h"
 
 #if HAVE_CITUS_LIBLZ4
 #include <lz4.h>
 #endif
 
-#if PG_VERSION_NUM >= PG_VERSION_16
-#include "varatt.h"
-#endif
-
 #if HAVE_LIBZSTD
 #include <zstd.h>
 #endif

src/backend/columnar/columnar_customscan.c

@@ -10,17 +10,18 @@
  *-------------------------------------------------------------------------
  */
 
-#include <math.h>
+#include "citus_version.h"
 
 #include "postgres.h"
 
-#include "miscadmin.h"
+#include <math.h>
 
 #include "access/amapi.h"
 #include "access/skey.h"
 #include "catalog/pg_am.h"
 #include "catalog/pg_statistic.h"
 #include "commands/defrem.h"
+#include "miscadmin.h"
 #include "nodes/extensible.h"
 #include "nodes/makefuncs.h"
 #include "nodes/nodeFuncs.h"
@@ -32,10 +33,6 @@
 #include "optimizer/paths.h"
 #include "optimizer/plancat.h"
 #include "optimizer/restrictinfo.h"
-#if PG_VERSION_NUM >= PG_VERSION_16
-#include "parser/parse_relation.h"
-#include "parser/parsetree.h"
-#endif
 #include "utils/builtins.h"
 #include "utils/lsyscache.h"
 #include "utils/relcache.h"
@@ -43,13 +40,10 @@
 #include "utils/selfuncs.h"
 #include "utils/spccache.h"
 
-#include "citus_version.h"
-
 #include "columnar/columnar.h"
 #include "columnar/columnar_customscan.h"
 #include "columnar/columnar_metadata.h"
 #include "columnar/columnar_tableam.h"
-
 #include "distributed/listutils.h"
 
 /*
@@ -127,15 +121,14 @@ static void ColumnarScan_ExplainCustomScan(CustomScanState *node, List *ancestor
 static const char * ColumnarPushdownClausesStr(List *context, List *clauses);
 static const char * ColumnarProjectedColumnsStr(List *context,
 												List *projectedColumns);
+#if PG_VERSION_NUM >= 130000
 static List * set_deparse_context_planstate(List *dpcontext, Node *node,
 											List *ancestors);
+#endif
 
 /* other helpers */
 static List * ColumnarVarNeeded(ColumnarScanState *columnarScanState);
 static Bitmapset * ColumnarAttrNeeded(ScanState *ss);
-#if PG_VERSION_NUM >= PG_VERSION_16
-static Bitmapset * fixup_inherited_columns(Oid parentId, Oid childId, Bitmapset *columns);
-#endif
 
 /* saved hook value in case of unload */
 static set_rel_pathlist_hook_type PreviousSetRelPathlistHook = NULL;
@@ -207,7 +200,7 @@ columnar_customscan_init()
 		&EnableColumnarCustomScan,
 		true,
 		PGC_USERSET,
-		GUC_NO_SHOW_ALL | GUC_NOT_IN_SAMPLE,
+		GUC_NO_SHOW_ALL,
 		NULL, NULL, NULL);
 	DefineCustomBoolVariable(
 		"columnar.enable_qual_pushdown",
@@ -217,7 +210,7 @@ columnar_customscan_init()
 		&EnableColumnarQualPushdown,
 		true,
 		PGC_USERSET,
-		GUC_NO_SHOW_ALL | GUC_NOT_IN_SAMPLE,
+		GUC_NO_SHOW_ALL,
 		NULL, NULL, NULL);
 	DefineCustomRealVariable(
 		"columnar.qual_pushdown_correlation_threshold",
@@ -231,7 +224,7 @@ columnar_customscan_init()
 		0.0,
 		1.0,
 		PGC_USERSET,
-		GUC_NO_SHOW_ALL | GUC_NOT_IN_SAMPLE,
+		GUC_NO_SHOW_ALL,
 		NULL, NULL, NULL);
 	DefineCustomIntVariable(
 		"columnar.max_custom_scan_paths",
@@ -243,7 +236,7 @@ columnar_customscan_init()
 		1,
 		1024,
 		PGC_USERSET,
-		GUC_NO_SHOW_ALL | GUC_NOT_IN_SAMPLE,
+		GUC_NO_SHOW_ALL,
 		NULL, NULL, NULL);
 	DefineCustomEnumVariable(
 		"columnar.planner_debug_level",
@@ -284,11 +277,6 @@ ColumnarSetRelPathlistHook(PlannerInfo *root, RelOptInfo *rel, Index rti,
 	 * into the scan of the table to minimize the data read.
 	 */
 	Relation relation = RelationIdGetRelation(rte->relid);
-	if (!RelationIsValid(relation))
-	{
-		ereport(ERROR, (errmsg("could not open relation with OID %u", rte->relid)));
-	}
-
 	if (relation->rd_tableam == GetColumnarTableAmRoutine())
 	{
 		if (rte->tablesample != NULL)
@@ -363,7 +351,7 @@ ColumnarGetRelationInfoHook(PlannerInfo *root, Oid relationObjectId,
 
 		/* disable index-only scan */
 		IndexOptInfo *indexOptInfo = NULL;
-		foreach_declared_ptr(indexOptInfo, rel->indexlist)
+		foreach_ptr(indexOptInfo, rel->indexlist)
 		{
 			memset(indexOptInfo->canreturn, false, indexOptInfo->ncolumns * sizeof(bool));
 		}
@@ -381,7 +369,7 @@ RemovePathsByPredicate(RelOptInfo *rel, PathPredicate removePathPredicate)
 	List *filteredPathList = NIL;
 
 	Path *path = NULL;
-	foreach_declared_ptr(path, rel->pathlist)
+	foreach_ptr(path, rel->pathlist)
 	{
 		if (!removePathPredicate(path))
 		{
@@ -428,7 +416,7 @@ static void
 CostColumnarPaths(PlannerInfo *root, RelOptInfo *rel, Oid relationId)
 {
 	Path *path = NULL;
-	foreach_declared_ptr(path, rel->pathlist)
+	foreach_ptr(path, rel->pathlist)
 	{
 		if (IsA(path, IndexPath))
 		{
@@ -513,11 +501,6 @@ ColumnarIndexScanAdditionalCost(PlannerInfo *root, RelOptInfo *rel,
 				   &indexCorrelation, &fakeIndexPages);
 
 	Relation relation = RelationIdGetRelation(relationId);
-	if (!RelationIsValid(relation))
-	{
-		ereport(ERROR, (errmsg("could not open relation with OID %u", relationId)));
-	}
-
 	uint64 rowCount = ColumnarTableRowCount(relation);
 	RelationClose(relation);
 	double estimatedRows = rowCount * indexSelectivity;
@@ -544,7 +527,7 @@ ColumnarIndexScanAdditionalCost(PlannerInfo *root, RelOptInfo *rel,
 	 * "anti-correlated" (-1) since both help us avoiding from reading the
 	 * same stripe again and again.
 	 */
-	double absIndexCorrelation = float_abs(indexCorrelation);
+	double absIndexCorrelation = Abs(indexCorrelation);
 
 	/*
 	 * To estimate the number of stripes that we need to read, we do linear
@@ -613,11 +596,6 @@ static int
 RelationIdGetNumberOfAttributes(Oid relationId)
 {
 	Relation relation = RelationIdGetRelation(relationId);
-	if (!RelationIsValid(relation))
-	{
-		ereport(ERROR, (errmsg("could not open relation with OID %u", relationId)));
-	}
-
 	int nattrs = relation->rd_att->natts;
 	RelationClose(relation);
 	return nattrs;
@@ -663,7 +641,7 @@ CheckVarStats(PlannerInfo *root, Var *var, Oid sortop, float4 *absVarCorrelation
 	 * If the Var is not highly correlated, then the chunk's min/max bounds
 	 * will be nearly useless.
 	 */
-	if (float_abs(varCorrelation) < ColumnarQualPushdownCorrelationThreshold)
+	if (Abs(varCorrelation) < ColumnarQualPushdownCorrelationThreshold)
 	{
 		if (absVarCorrelation)
 		{
@@ -671,7 +649,7 @@ CheckVarStats(PlannerInfo *root, Var *var, Oid sortop, float4 *absVarCorrelation
 			 * Report absVarCorrelation if caller wants to know why given
 			 * var is rejected.
 			 */
-			*absVarCorrelation = float_abs(varCorrelation);
+			*absVarCorrelation = Abs(varCorrelation);
 		}
 		return false;
 	}
@@ -783,7 +761,7 @@ ExtractPushdownClause(PlannerInfo *root, RelOptInfo *rel, Node *node)
 		List *pushdownableArgs = NIL;
 
 		Node *boolExprArg = NULL;
-		foreach_declared_ptr(boolExprArg, boolExpr->args)
+		foreach_ptr(boolExprArg, boolExpr->args)
 		{
 			Expr *pushdownableArg = ExtractPushdownClause(root, rel,
 														  (Node *) boolExprArg);
@@ -833,18 +811,6 @@ ExtractPushdownClause(PlannerInfo *root, RelOptInfo *rel, Node *node)
 		}
 	}
 
-	if (IsA(node, ScalarArrayOpExpr))
-	{
-		if (!contain_volatile_functions(node))
-		{
-			return (Expr *) node;
-		}
-		else
-		{
-			return NULL;
-		}
-	}
-
 	if (!IsA(node, OpExpr) || list_length(((OpExpr *) node)->args) != 2)
 	{
 		ereport(ColumnarPlannerDebugLevel,
@@ -1051,15 +1017,6 @@ FindCandidateRelids(PlannerInfo *root, RelOptInfo *rel, List *joinClauses)
 
 	candidateRelids = bms_del_members(candidateRelids, rel->relids);
 	candidateRelids = bms_del_members(candidateRelids, rel->lateral_relids);
-
-	/*
-	 * For the relevant PG16 commit requiring this addition:
-	 * postgres/postgres@2489d76
-	 */
-#if PG_VERSION_NUM >= PG_VERSION_16
-	candidateRelids = bms_del_members(candidateRelids, root->outer_join_rels);
-#endif
-
 	return candidateRelids;
 }
 
@@ -1321,9 +1278,6 @@ AddColumnarScanPath(PlannerInfo *root, RelOptInfo *rel, RangeTblEntry *rte,
 
 	cpath->methods = &ColumnarScanPathMethods;
 
-	/* necessary to avoid extra Result node in PG15 */
-	cpath->flags = CUSTOMPATH_SUPPORT_PROJECTION;
-
 	/*
 	 * populate generic path information
 	 */
@@ -1386,43 +1340,7 @@ AddColumnarScanPath(PlannerInfo *root, RelOptInfo *rel, RangeTblEntry *rte,
 		cpath->custom_private = list_make2(NIL, NIL);
 	}
 
-	int numberOfColumnsRead = 0;
-#if PG_VERSION_NUM >= PG_VERSION_16
-	if (rte->perminfoindex > 0)
-	{
-		/*
-		 * If perminfoindex > 0, that means that this relation's permission info
-		 * is directly found in the list of rteperminfos of the Query(root->parse)
-		 * So, all we have to do here is retrieve that info.
-		 */
-		RTEPermissionInfo *perminfo = getRTEPermissionInfo(root->parse->rteperminfos,
-														   rte);
-		numberOfColumnsRead = bms_num_members(perminfo->selectedCols);
-	}
-	else
-	{
-		/*
-		 * If perminfoindex = 0, that means we are skipping the check for permission info
-		 * for this relation, which means that it's either a partition or an inheritance child.
-		 * In these cases, we need to access the permission info of the top parent of this relation.
-		 * After thorough checking, we found that the index of the top parent pointing to the correct
-		 * range table entry in Query's range tables (root->parse->rtable) is found under
-		 * RelOptInfo rel->top_parent->relid.
-		 * For reference, check expand_partitioned_rtentry and expand_inherited_rtentry PG functions
-		 */
-		Assert(rel->top_parent);
-		RangeTblEntry *parent_rte = rt_fetch(rel->top_parent->relid, root->parse->rtable);
-		RTEPermissionInfo *perminfo = getRTEPermissionInfo(root->parse->rteperminfos,
-														   parent_rte);
-		numberOfColumnsRead = bms_num_members(fixup_inherited_columns(perminfo->relid,
-																	  rte->relid,
-																	  perminfo->
-																	  selectedCols));
-	}
-#else
-	numberOfColumnsRead = bms_num_members(rte->selectedCols);
-#endif
-
+	int numberOfColumnsRead = bms_num_members(rte->selectedCols);
 	int numberOfClausesPushed = list_length(allClauses);
 
 	CostColumnarScan(root, rel, rte->relid, cpath, numberOfColumnsRead,
@@ -1442,69 +1360,6 @@ AddColumnarScanPath(PlannerInfo *root, RelOptInfo *rel, RangeTblEntry *rte,
 }
 
 
-#if PG_VERSION_NUM >= PG_VERSION_16
-
-/*
- * fixup_inherited_columns
- *
- * Exact function Copied from PG16 as it's static.
- *
- * When user is querying on a table with children, it implicitly accesses
- * child tables also. So, we also need to check security label of child
- * tables and columns, but there is no guarantee attribute numbers are
- * same between the parent and children.
- * It returns a bitmapset which contains attribute number of the child
- * table based on the given bitmapset of the parent.
- */
-static Bitmapset *
-fixup_inherited_columns(Oid parentId, Oid childId, Bitmapset *columns)
-{
-	Bitmapset *result = NULL;
-
-	/*
-	 * obviously, no need to do anything here
-	 */
-	if (parentId == childId)
-	{
-		return columns;
-	}
-
-	int index = -1;
-	while ((index = bms_next_member(columns, index)) >= 0)
-	{
-		/* bit numbers are offset by FirstLowInvalidHeapAttributeNumber */
-		AttrNumber attno = index + FirstLowInvalidHeapAttributeNumber;
-
-		/*
-		 * whole-row-reference shall be fixed-up later
-		 */
-		if (attno == InvalidAttrNumber)
-		{
-			result = bms_add_member(result, index);
-			continue;
-		}
-
-		char *attname = get_attname(parentId, attno, false);
-		attno = get_attnum(childId, attname);
-		if (attno == InvalidAttrNumber)
-		{
-			elog(ERROR, "cache lookup failed for attribute %s of relation %u",
-				 attname, childId);
-		}
-
-		result = bms_add_member(result,
-								attno - FirstLowInvalidHeapAttributeNumber);
-
-		pfree(attname);
-	}
-
-	return result;
-}
-
-
-#endif
-
-
 /*
  * CostColumnarScan calculates the cost of scanning the columnar table. The
  * cost is estimated by using all stripe metadata to estimate based on the
@@ -1544,19 +1399,13 @@ static Cost
 ColumnarPerStripeScanCost(RelOptInfo *rel, Oid relationId, int numberOfColumnsRead)
 {
 	Relation relation = RelationIdGetRelation(relationId);
-	if (!RelationIsValid(relation))
-	{
-		ereport(ERROR, (errmsg("could not open relation with OID %u", relationId)));
-	}
-
-	List *stripeList = StripesForRelfilelocator(RelationPhysicalIdentifier_compat(
-													relation));
+	List *stripeList = StripesForRelfilenode(relation->rd_node);
 	RelationClose(relation);
 
 	uint32 maxColumnCount = 0;
 	uint64 totalStripeSize = 0;
 	StripeMetadata *stripeMetadata = NULL;
-	foreach_declared_ptr(stripeMetadata, stripeList)
+	foreach_ptr(stripeMetadata, stripeList)
 	{
 		totalStripeSize += stripeMetadata->dataLength;
 		maxColumnCount = Max(maxColumnCount, stripeMetadata->columnCount);
@@ -1602,13 +1451,7 @@ static uint64
 ColumnarTableStripeCount(Oid relationId)
 {
 	Relation relation = RelationIdGetRelation(relationId);
-	if (!RelationIsValid(relation))
-	{
-		ereport(ERROR, (errmsg("could not open relation with OID %u", relationId)));
-	}
-
-	List *stripeList = StripesForRelfilelocator(RelationPhysicalIdentifier_compat(
-													relation));
+	List *stripeList = StripesForRelfilenode(relation->rd_node);
 	int stripeCount = list_length(stripeList);
 	RelationClose(relation);
 
@@ -1667,12 +1510,6 @@ ColumnarScanPath_PlanCustomPath(PlannerInfo *root,
 	cscan->scan.plan.targetlist = list_copy(tlist);
 	cscan->scan.scanrelid = best_path->path.parent->relid;
 
-#if (PG_VERSION_NUM >= 150000)
-
-	/* necessary to avoid extra Result node in PG15 */
-	cscan->flags = CUSTOMPATH_SUPPORT_PROJECTION;
-#endif
-
 	return (Plan *) cscan;
 }
 
@@ -1930,6 +1767,11 @@ ColumnarScan_EndCustomScan(CustomScanState *node)
 	 */
 	TableScanDesc scanDesc = node->ss.ss_currentScanDesc;
 
+	/*
+	 * Free the exprcontext
+	 */
+	ExecFreeExprContext(&node->ss.ps);
+
 	/*
 	 * clean out the tuple table
 	 */
@@ -2119,6 +1961,8 @@ ColumnarVarNeeded(ColumnarScanState *columnarScanState)
 }
 
 
+#if PG_VERSION_NUM >= 130000
+
 /*
  * set_deparse_context_planstate is a compatibility wrapper for versions 13+.
  */
@@ -2128,3 +1972,6 @@ set_deparse_context_planstate(List *dpcontext, Node *node, List *ancestors)
 	PlanState *ps = (PlanState *) node;
 	return set_deparse_context_plan(dpcontext, ps->plan, ancestors);
 }
+
+
+#endif

src/backend/columnar/columnar_debug.c

@@ -11,12 +11,13 @@
 #include "postgres.h"
 
 #include "funcapi.h"
-#include "miscadmin.h"
-
+#include "pg_config.h"
 #include "access/nbtree.h"
 #include "access/table.h"
 #include "catalog/pg_am.h"
 #include "catalog/pg_type.h"
+#include "distributed/pg_version_constants.h"
+#include "miscadmin.h"
 #include "storage/fd.h"
 #include "storage/smgr.h"
 #include "utils/guc.h"
@@ -25,8 +26,6 @@
 #include "utils/tuplestore.h"
 
 #include "pg_version_compat.h"
-#include "pg_version_constants.h"
-
 #include "columnar/columnar.h"
 #include "columnar/columnar_storage.h"
 #include "columnar/columnar_version_compat.h"
@@ -117,6 +116,8 @@ columnar_storage_info(PG_FUNCTION_ARGS)
 							   RelationGetRelationName(rel))));
 	}
 
+	RelationOpenSmgr(rel);
+
 	Datum values[STORAGE_INFO_NATTS] = { 0 };
 	bool nulls[STORAGE_INFO_NATTS] = { 0 };
 
@@ -161,5 +162,5 @@ MemoryContextTotals(MemoryContext context, MemoryContextCounters *counters)
 		MemoryContextTotals(child, counters);
 	}
 
-	context->methods->stats(context, NULL, NULL, counters, true);
+	context->methods->stats_compat(context, NULL, NULL, counters, true);
 }

src/backend/columnar/columnar_metadata.c

@@ -19,62 +19,46 @@
  */
 
 
-#include <sys/stat.h>
-
 #include "postgres.h"
 
-#include "miscadmin.h"
-#include "port.h"
 #include "safe_lib.h"
 
+#include "citus_version.h"
+#include "columnar/columnar.h"
+#include "columnar/columnar_storage.h"
+#include "columnar/columnar_version_compat.h"
+#include "distributed/listutils.h"
+
+#include <sys/stat.h>
 #include "access/heapam.h"
 #include "access/htup_details.h"
 #include "access/nbtree.h"
 #include "access/xact.h"
 #include "catalog/indexing.h"
-#include "catalog/namespace.h"
-#include "catalog/pg_collation.h"
 #include "catalog/pg_namespace.h"
+#include "catalog/pg_collation.h"
 #include "catalog/pg_type.h"
+#include "catalog/namespace.h"
 #include "commands/defrem.h"
 #include "commands/sequence.h"
 #include "commands/trigger.h"
 #include "executor/executor.h"
 #include "executor/spi.h"
-#include "lib/stringinfo.h"
+#include "miscadmin.h"
 #include "nodes/execnodes.h"
+#include "lib/stringinfo.h"
+#include "port.h"
 #include "storage/fd.h"
 #include "storage/lmgr.h"
 #include "storage/procarray.h"
 #include "storage/smgr.h"
 #include "utils/builtins.h"
 #include "utils/fmgroids.h"
-#include "utils/lsyscache.h"
 #include "utils/memutils.h"
+#include "utils/lsyscache.h"
 #include "utils/rel.h"
-
-#include "citus_version.h"
-#include "pg_version_constants.h"
-
-#include "columnar/columnar.h"
-#include "columnar/columnar_storage.h"
-#include "columnar/columnar_version_compat.h"
-
-#include "distributed/listutils.h"
-
-#if PG_VERSION_NUM >= PG_VERSION_16
-#include "parser/parse_relation.h"
-#include "storage/relfilelocator.h"
-#include "utils/relfilenumbermap.h"
-#else
 #include "utils/relfilenodemap.h"
-#endif
 
-#define COLUMNAR_RELOPTION_NAMESPACE "columnar"
-#define SLOW_METADATA_ACCESS_WARNING \
-	"Metadata index %s is not available, this might mean slower read/writes " \
-	"on columnar tables. This is expected during Postgres upgrades and not " \
-	"expected otherwise."
 
 typedef struct
 {
@@ -98,7 +82,6 @@ typedef enum RowNumberLookupMode
 	FIND_GREATER
 } RowNumberLookupMode;
 
-static void ParseColumnarRelOptions(List *reloptions, ColumnarOptions *options);
 static void InsertEmptyStripeMetadataRow(uint64 storageId, uint64 stripeId,
 										 uint32 columnCount, uint32 chunkGroupRowCount,
 										 uint64 firstRowNumber);
@@ -123,7 +106,7 @@ static Oid ColumnarChunkGroupRelationId(void);
 static Oid ColumnarChunkIndexRelationId(void);
 static Oid ColumnarChunkGroupIndexRelationId(void);
 static Oid ColumnarNamespaceId(void);
-static uint64 LookupStorageId(RelFileLocator relfilelocator);
+static uint64 LookupStorageId(RelFileNode relfilenode);
 static uint64 GetHighestUsedRowNumber(uint64 storageId);
 static void DeleteStorageFromColumnarMetadataTable(Oid metadataTableId,
 												   AttrNumber storageIdAtrrNumber,
@@ -235,154 +218,6 @@ InitColumnarOptions(Oid regclass)
 }
 
 
-/*
- * ParseColumnarRelOptions - update the given 'options' using the given list
- * of DefElem.
- */
-static void
-ParseColumnarRelOptions(List *reloptions, ColumnarOptions *options)
-{
-	ListCell *lc = NULL;
-
-	foreach(lc, reloptions)
-	{
-		DefElem *elem = castNode(DefElem, lfirst(lc));
-
-		if (elem->defnamespace == NULL ||
-			strcmp(elem->defnamespace, COLUMNAR_RELOPTION_NAMESPACE) != 0)
-		{
-			ereport(ERROR, (errmsg("columnar options must have the prefix \"%s\"",
-								   COLUMNAR_RELOPTION_NAMESPACE)));
-		}
-
-		if (strcmp(elem->defname, "chunk_group_row_limit") == 0)
-		{
-			options->chunkRowCount = (elem->arg == NULL) ?
-									 columnar_chunk_group_row_limit : defGetInt64(elem);
-			if (options->chunkRowCount < CHUNK_ROW_COUNT_MINIMUM ||
-				options->chunkRowCount > CHUNK_ROW_COUNT_MAXIMUM)
-			{
-				ereport(ERROR, (errmsg("chunk group row count limit out of range"),
-								errhint("chunk group row count limit must be between "
-										UINT64_FORMAT " and " UINT64_FORMAT,
-										(uint64) CHUNK_ROW_COUNT_MINIMUM,
-										(uint64) CHUNK_ROW_COUNT_MAXIMUM)));
-			}
-		}
-		else if (strcmp(elem->defname, "stripe_row_limit") == 0)
-		{
-			options->stripeRowCount = (elem->arg == NULL) ?
-									  columnar_stripe_row_limit : defGetInt64(elem);
-
-			if (options->stripeRowCount < STRIPE_ROW_COUNT_MINIMUM ||
-				options->stripeRowCount > STRIPE_ROW_COUNT_MAXIMUM)
-			{
-				ereport(ERROR, (errmsg("stripe row count limit out of range"),
-								errhint("stripe row count limit must be between "
-										UINT64_FORMAT " and " UINT64_FORMAT,
-										(uint64) STRIPE_ROW_COUNT_MINIMUM,
-										(uint64) STRIPE_ROW_COUNT_MAXIMUM)));
-			}
-		}
-		else if (strcmp(elem->defname, "compression") == 0)
-		{
-			options->compressionType = (elem->arg == NULL) ?
-									   columnar_compression : ParseCompressionType(
-				defGetString(elem));
-
-			if (options->compressionType == COMPRESSION_TYPE_INVALID)
-			{
-				ereport(ERROR, (errmsg("unknown compression type for columnar table: %s",
-									   quote_identifier(defGetString(elem)))));
-			}
-		}
-		else if (strcmp(elem->defname, "compression_level") == 0)
-		{
-			options->compressionLevel = (elem->arg == NULL) ?
-										columnar_compression_level : defGetInt64(elem);
-
-			if (options->compressionLevel < COMPRESSION_LEVEL_MIN ||
-				options->compressionLevel > COMPRESSION_LEVEL_MAX)
-			{
-				ereport(ERROR, (errmsg("compression level out of range"),
-								errhint("compression level must be between %d and %d",
-										COMPRESSION_LEVEL_MIN,
-										COMPRESSION_LEVEL_MAX)));
-			}
-		}
-		else
-		{
-			ereport(ERROR, (errmsg("unrecognized columnar storage parameter \"%s\"",
-								   elem->defname)));
-		}
-	}
-}
-
-
-/*
- * ExtractColumnarOptions - extract columnar options from inOptions, appending
- * to inoutColumnarOptions. Return the remaining (non-columnar) options.
- */
-List *
-ExtractColumnarRelOptions(List *inOptions, List **inoutColumnarOptions)
-{
-	List *otherOptions = NIL;
-
-	ListCell *lc = NULL;
-	foreach(lc, inOptions)
-	{
-		DefElem *elem = castNode(DefElem, lfirst(lc));
-
-		if (elem->defnamespace != NULL &&
-			strcmp(elem->defnamespace, COLUMNAR_RELOPTION_NAMESPACE) == 0)
-		{
-			*inoutColumnarOptions = lappend(*inoutColumnarOptions, elem);
-		}
-		else
-		{
-			otherOptions = lappend(otherOptions, elem);
-		}
-	}
-
-	/* validate options */
-	ColumnarOptions dummy = { 0 };
-	ParseColumnarRelOptions(*inoutColumnarOptions, &dummy);
-
-	return otherOptions;
-}
-
-
-/*
- * SetColumnarRelOptions - apply the list of DefElem options to the
- * relation. If there are duplicates, the last one in the list takes effect.
- */
-void
-SetColumnarRelOptions(RangeVar *rv, List *reloptions)
-{
-	ColumnarOptions options = { 0 };
-
-	if (reloptions == NIL)
-	{
-		return;
-	}
-
-	Relation rel = relation_openrv(rv, AccessShareLock);
-	Oid relid = RelationGetRelid(rel);
-	relation_close(rel, NoLock);
-
-	/* get existing or default options */
-	if (!ReadColumnarOptions(relid, &options))
-	{
-		/* if extension doesn't exist, just return */
-		return;
-	}
-
-	ParseColumnarRelOptions(reloptions, &options);
-
-	SetColumnarOptions(relid, &options);
-}
-
-
 /*
  * SetColumnarOptions writes the passed table options as the authoritive options to the
  * table irregardless of the optiones already existing or not. This can be used to put a
@@ -602,15 +437,14 @@ ReadColumnarOptions(Oid regclass, ColumnarOptions *options)
  * of columnar.chunk.
  */
 void
-SaveStripeSkipList(RelFileLocator relfilelocator, uint64 stripe,
-				   StripeSkipList *chunkList,
+SaveStripeSkipList(RelFileNode relfilenode, uint64 stripe, StripeSkipList *chunkList,
 				   TupleDesc tupleDescriptor)
 {
 	uint32 columnIndex = 0;
 	uint32 chunkIndex = 0;
 	uint32 columnCount = chunkList->columnCount;
 
-	uint64 storageId = LookupStorageId(relfilelocator);
+	uint64 storageId = LookupStorageId(relfilenode);
 	Oid columnarChunkOid = ColumnarChunkRelationId();
 	Relation columnarChunk = table_open(columnarChunkOid, RowExclusiveLock);
 	ModifyState *modifyState = StartModifyRelation(columnarChunk);
@@ -669,10 +503,10 @@ SaveStripeSkipList(RelFileLocator relfilelocator, uint64 stripe,
  * SaveChunkGroups saves the metadata for given chunk groups in columnar.chunk_group.
  */
 void
-SaveChunkGroups(RelFileLocator relfilelocator, uint64 stripe,
+SaveChunkGroups(RelFileNode relfilenode, uint64 stripe,
 				List *chunkGroupRowCounts)
 {
-	uint64 storageId = LookupStorageId(relfilelocator);
+	uint64 storageId = LookupStorageId(relfilenode);
 	Oid columnarChunkGroupOid = ColumnarChunkGroupRelationId();
 	Relation columnarChunkGroup = table_open(columnarChunkGroupOid, RowExclusiveLock);
 	ModifyState *modifyState = StartModifyRelation(columnarChunkGroup);
@@ -705,8 +539,7 @@ SaveChunkGroups(RelFileLocator relfilelocator, uint64 stripe,
  * ReadStripeSkipList fetches chunk metadata for a given stripe.
  */
 StripeSkipList *
-ReadStripeSkipList(RelFileLocator relfilelocator, uint64 stripe,
-				   TupleDesc tupleDescriptor,
+ReadStripeSkipList(RelFileNode relfilenode, uint64 stripe, TupleDesc tupleDescriptor,
 				   uint32 chunkCount, Snapshot snapshot)
 {
 	int32 columnIndex = 0;
@@ -714,27 +547,19 @@ ReadStripeSkipList(RelFileLocator relfilelocator, uint64 stripe,
 	uint32 columnCount = tupleDescriptor->natts;
 	ScanKeyData scanKey[2];
 
-	uint64 storageId = LookupStorageId(relfilelocator);
+	uint64 storageId = LookupStorageId(relfilenode);
 
 	Oid columnarChunkOid = ColumnarChunkRelationId();
 	Relation columnarChunk = table_open(columnarChunkOid, AccessShareLock);
+	Relation index = index_open(ColumnarChunkIndexRelationId(), AccessShareLock);
 
 	ScanKeyInit(&scanKey[0], Anum_columnar_chunk_storageid,
-				BTEqualStrategyNumber, F_INT8EQ, Int64GetDatum(storageId));
+				BTEqualStrategyNumber, F_OIDEQ, UInt64GetDatum(storageId));
 	ScanKeyInit(&scanKey[1], Anum_columnar_chunk_stripe,
-				BTEqualStrategyNumber, F_INT8EQ, Int64GetDatum(stripe));
+				BTEqualStrategyNumber, F_OIDEQ, Int32GetDatum(stripe));
 
-	Oid indexId = ColumnarChunkIndexRelationId();
-	bool indexOk = OidIsValid(indexId);
-	SysScanDesc scanDescriptor = systable_beginscan(columnarChunk, indexId,
-													indexOk, snapshot, 2, scanKey);
-
-	static bool loggedSlowMetadataAccessWarning = false;
-	if (!indexOk && !loggedSlowMetadataAccessWarning)
-	{
-		ereport(WARNING, (errmsg(SLOW_METADATA_ACCESS_WARNING, "chunk_pkey")));
-		loggedSlowMetadataAccessWarning = true;
-	}
+	SysScanDesc scanDescriptor = systable_beginscan_ordered(columnarChunk, index,
+															snapshot, 2, scanKey);
 
 	StripeSkipList *chunkList = palloc0(sizeof(StripeSkipList));
 	chunkList->chunkCount = chunkCount;
@@ -746,7 +571,8 @@ ReadStripeSkipList(RelFileLocator relfilelocator, uint64 stripe,
 			palloc0(chunkCount * sizeof(ColumnChunkSkipNode));
 	}
 
-	while (HeapTupleIsValid(heapTuple = systable_getnext(scanDescriptor)))
+	while (HeapTupleIsValid(heapTuple = systable_getnext_ordered(scanDescriptor,
+																 ForwardScanDirection)))
 	{
 		Datum datumArray[Natts_columnar_chunk];
 		bool isNullArray[Natts_columnar_chunk];
@@ -811,7 +637,8 @@ ReadStripeSkipList(RelFileLocator relfilelocator, uint64 stripe,
 		}
 	}
 
-	systable_endscan(scanDescriptor);
+	systable_endscan_ordered(scanDescriptor);
+	index_close(index, AccessShareLock);
 	table_close(columnarChunk, AccessShareLock);
 
 	chunkList->chunkGroupRowCounts =
@@ -822,9 +649,9 @@ ReadStripeSkipList(RelFileLocator relfilelocator, uint64 stripe,
 
 
 /*
- * FindStripeByRowNumber returns StripeMetadata for the stripe that has the
- * smallest firstRowNumber among the stripes whose firstRowNumber is grater
- * than given rowNumber. If no such stripe exists, then returns NULL.
+ * FindStripeByRowNumber returns StripeMetadata for the stripe whose
+ * firstRowNumber is greater than given rowNumber. If no such stripe
+ * exists, then returns NULL.
  */
 StripeMetadata *
 FindNextStripeByRowNumber(Relation relation, uint64 rowNumber, Snapshot snapshot)
@@ -914,7 +741,8 @@ StripeGetHighestRowNumber(StripeMetadata *stripeMetadata)
 /*
  * StripeMetadataLookupRowNumber returns StripeMetadata for the stripe whose
  * firstRowNumber is less than or equal to (FIND_LESS_OR_EQUAL), or is
- * greater than (FIND_GREATER) given rowNumber.
+ * greater than (FIND_GREATER) given rowNumber by doing backward index
+ * scan on stripe_first_row_number_idx.
  * If no such stripe exists, then returns NULL.
  */
 static StripeMetadata *
@@ -928,7 +756,7 @@ StripeMetadataLookupRowNumber(Relation relation, uint64 rowNumber, Snapshot snap
 	uint64 storageId = ColumnarStorageGetStorageId(relation, false);
 	ScanKeyData scanKey[2];
 	ScanKeyInit(&scanKey[0], Anum_columnar_stripe_storageid,
-				BTEqualStrategyNumber, F_INT8EQ, Int64GetDatum(storageId));
+				BTEqualStrategyNumber, F_OIDEQ, Int32GetDatum(storageId));
 
 	StrategyNumber strategyNumber = InvalidStrategy;
 	RegProcedure procedure = InvalidOid;
@@ -943,73 +771,33 @@ StripeMetadataLookupRowNumber(Relation relation, uint64 rowNumber, Snapshot snap
 		procedure = F_INT8GT;
 	}
 	ScanKeyInit(&scanKey[1], Anum_columnar_stripe_first_row_number,
-				strategyNumber, procedure, Int64GetDatum(rowNumber));
+				strategyNumber, procedure, UInt64GetDatum(rowNumber));
+
 
 	Relation columnarStripes = table_open(ColumnarStripeRelationId(), AccessShareLock);
+	Relation index = index_open(ColumnarStripeFirstRowNumberIndexRelationId(),
+								AccessShareLock);
+	SysScanDesc scanDescriptor = systable_beginscan_ordered(columnarStripes, index,
+															snapshot, 2,
+															scanKey);
 
-	Oid indexId = ColumnarStripeFirstRowNumberIndexRelationId();
-	bool indexOk = OidIsValid(indexId);
-	SysScanDesc scanDescriptor = systable_beginscan(columnarStripes, indexId, indexOk,
-													snapshot, 2, scanKey);
-
-	static bool loggedSlowMetadataAccessWarning = false;
-	if (!indexOk && !loggedSlowMetadataAccessWarning)
+	ScanDirection scanDirection = NoMovementScanDirection;
+	if (lookupMode == FIND_LESS_OR_EQUAL)
 	{
-		ereport(WARNING, (errmsg(SLOW_METADATA_ACCESS_WARNING,
-								 "stripe_first_row_number_idx")));
-		loggedSlowMetadataAccessWarning = true;
+		scanDirection = BackwardScanDirection;
+	}
+	else if (lookupMode == FIND_GREATER)
+	{
+		scanDirection = ForwardScanDirection;
+	}
+	HeapTuple heapTuple = systable_getnext_ordered(scanDescriptor, scanDirection);
+	if (HeapTupleIsValid(heapTuple))
+	{
+		foundStripeMetadata = BuildStripeMetadata(columnarStripes, heapTuple);
 	}
 
-	if (indexOk)
-	{
-		ScanDirection scanDirection = NoMovementScanDirection;
-		if (lookupMode == FIND_LESS_OR_EQUAL)
-		{
-			scanDirection = BackwardScanDirection;
-		}
-		else if (lookupMode == FIND_GREATER)
-		{
-			scanDirection = ForwardScanDirection;
-		}
-		HeapTuple heapTuple = systable_getnext_ordered(scanDescriptor, scanDirection);
-		if (HeapTupleIsValid(heapTuple))
-		{
-			foundStripeMetadata = BuildStripeMetadata(columnarStripes, heapTuple);
-		}
-	}
-	else
-	{
-		HeapTuple heapTuple = NULL;
-		while (HeapTupleIsValid(heapTuple = systable_getnext(scanDescriptor)))
-		{
-			StripeMetadata *stripe = BuildStripeMetadata(columnarStripes, heapTuple);
-			if (!foundStripeMetadata)
-			{
-				/* first match */
-				foundStripeMetadata = stripe;
-			}
-			else if (lookupMode == FIND_LESS_OR_EQUAL &&
-					 stripe->firstRowNumber > foundStripeMetadata->firstRowNumber)
-			{
-				/*
-				 * Among the stripes with firstRowNumber less-than-or-equal-to given,
-				 * we're looking for the one with the greatest firstRowNumber.
-				 */
-				foundStripeMetadata = stripe;
-			}
-			else if (lookupMode == FIND_GREATER &&
-					 stripe->firstRowNumber < foundStripeMetadata->firstRowNumber)
-			{
-				/*
-				 * Among the stripes with firstRowNumber greater-than given,
-				 * we're looking for the one with the smallest firstRowNumber.
-				 */
-				foundStripeMetadata = stripe;
-			}
-		}
-	}
-
-	systable_endscan(scanDescriptor);
+	systable_endscan_ordered(scanDescriptor);
+	index_close(index, AccessShareLock);
 	table_close(columnarStripes, AccessShareLock);
 
 	return foundStripeMetadata;
@@ -1083,8 +871,8 @@ CheckStripeMetadataConsistency(StripeMetadata *stripeMetadata)
 
 /*
  * FindStripeWithHighestRowNumber returns StripeMetadata for the stripe that
- * has the row with highest rowNumber. If given relation is empty, then returns
- * NULL.
+ * has the row with highest rowNumber by doing backward index scan on
+ * stripe_first_row_number_idx. If given relation is empty, then returns NULL.
  */
 StripeMetadata *
 FindStripeWithHighestRowNumber(Relation relation, Snapshot snapshot)
@@ -1094,49 +882,22 @@ FindStripeWithHighestRowNumber(Relation relation, Snapshot snapshot)
 	uint64 storageId = ColumnarStorageGetStorageId(relation, false);
 	ScanKeyData scanKey[1];
 	ScanKeyInit(&scanKey[0], Anum_columnar_stripe_storageid,
-				BTEqualStrategyNumber, F_INT8EQ, Int64GetDatum(storageId));
+				BTEqualStrategyNumber, F_OIDEQ, Int32GetDatum(storageId));
 
 	Relation columnarStripes = table_open(ColumnarStripeRelationId(), AccessShareLock);
+	Relation index = index_open(ColumnarStripeFirstRowNumberIndexRelationId(),
+								AccessShareLock);
+	SysScanDesc scanDescriptor = systable_beginscan_ordered(columnarStripes, index,
+															snapshot, 1, scanKey);
 
-	Oid indexId = ColumnarStripeFirstRowNumberIndexRelationId();
-	bool indexOk = OidIsValid(indexId);
-	SysScanDesc scanDescriptor = systable_beginscan(columnarStripes, indexId, indexOk,
-													snapshot, 1, scanKey);
-
-	static bool loggedSlowMetadataAccessWarning = false;
-	if (!indexOk && !loggedSlowMetadataAccessWarning)
+	HeapTuple heapTuple = systable_getnext_ordered(scanDescriptor, BackwardScanDirection);
+	if (HeapTupleIsValid(heapTuple))
 	{
-		ereport(WARNING, (errmsg(SLOW_METADATA_ACCESS_WARNING,
-								 "stripe_first_row_number_idx")));
-		loggedSlowMetadataAccessWarning = true;
+		stripeWithHighestRowNumber = BuildStripeMetadata(columnarStripes, heapTuple);
 	}
 
-	if (indexOk)
-	{
-		/* do one-time fetch using the index */
-		HeapTuple heapTuple = systable_getnext_ordered(scanDescriptor,
-													   BackwardScanDirection);
-		if (HeapTupleIsValid(heapTuple))
-		{
-			stripeWithHighestRowNumber = BuildStripeMetadata(columnarStripes, heapTuple);
-		}
-	}
-	else
-	{
-		HeapTuple heapTuple = NULL;
-		while (HeapTupleIsValid(heapTuple = systable_getnext(scanDescriptor)))
-		{
-			StripeMetadata *stripe = BuildStripeMetadata(columnarStripes, heapTuple);
-			if (!stripeWithHighestRowNumber ||
-				stripe->firstRowNumber > stripeWithHighestRowNumber->firstRowNumber)
-			{
-				/* first or a greater match */
-				stripeWithHighestRowNumber = stripe;
-			}
-		}
-	}
-
-	systable_endscan(scanDescriptor);
+	systable_endscan_ordered(scanDescriptor);
+	index_close(index, AccessShareLock);
 	table_close(columnarStripes, AccessShareLock);
 
 	return stripeWithHighestRowNumber;
@@ -1153,29 +914,23 @@ ReadChunkGroupRowCounts(uint64 storageId, uint64 stripe, uint32 chunkGroupCount,
 {
 	Oid columnarChunkGroupOid = ColumnarChunkGroupRelationId();
 	Relation columnarChunkGroup = table_open(columnarChunkGroupOid, AccessShareLock);
+	Relation index = index_open(ColumnarChunkGroupIndexRelationId(), AccessShareLock);
 
 	ScanKeyData scanKey[2];
 	ScanKeyInit(&scanKey[0], Anum_columnar_chunkgroup_storageid,
-				BTEqualStrategyNumber, F_INT8EQ, Int64GetDatum(storageId));
+				BTEqualStrategyNumber, F_OIDEQ, UInt64GetDatum(storageId));
 	ScanKeyInit(&scanKey[1], Anum_columnar_chunkgroup_stripe,
-				BTEqualStrategyNumber, F_INT8EQ, Int64GetDatum(stripe));
+				BTEqualStrategyNumber, F_OIDEQ, Int32GetDatum(stripe));
 
-	Oid indexId = ColumnarChunkGroupIndexRelationId();
-	bool indexOk = OidIsValid(indexId);
 	SysScanDesc scanDescriptor =
-		systable_beginscan(columnarChunkGroup, indexId, indexOk, snapshot, 2, scanKey);
-
-	static bool loggedSlowMetadataAccessWarning = false;
-	if (!indexOk && !loggedSlowMetadataAccessWarning)
-	{
-		ereport(WARNING, (errmsg(SLOW_METADATA_ACCESS_WARNING, "chunk_group_pkey")));
-		loggedSlowMetadataAccessWarning = true;
-	}
+		systable_beginscan_ordered(columnarChunkGroup, index, snapshot, 2, scanKey);
 
+	uint32 chunkGroupIndex = 0;
 	HeapTuple heapTuple = NULL;
 	uint32 *chunkGroupRowCounts = palloc0(chunkGroupCount * sizeof(uint32));
 
-	while (HeapTupleIsValid(heapTuple = systable_getnext(scanDescriptor)))
+	while (HeapTupleIsValid(heapTuple = systable_getnext_ordered(scanDescriptor,
+																 ForwardScanDirection)))
 	{
 		Datum datumArray[Natts_columnar_chunkgroup];
 		bool isNullArray[Natts_columnar_chunkgroup];
@@ -1186,16 +941,24 @@ ReadChunkGroupRowCounts(uint64 storageId, uint64 stripe, uint32 chunkGroupCount,
 
 		uint32 tupleChunkGroupIndex =
 			DatumGetUInt32(datumArray[Anum_columnar_chunkgroup_chunk - 1]);
-		if (tupleChunkGroupIndex >= chunkGroupCount)
+		if (chunkGroupIndex >= chunkGroupCount ||
+			tupleChunkGroupIndex != chunkGroupIndex)
 		{
 			elog(ERROR, "unexpected chunk group");
 		}
 
-		chunkGroupRowCounts[tupleChunkGroupIndex] =
+		chunkGroupRowCounts[chunkGroupIndex] =
 			(uint32) DatumGetUInt64(datumArray[Anum_columnar_chunkgroup_row_count - 1]);
+		chunkGroupIndex++;
 	}
 
-	systable_endscan(scanDescriptor);
+	if (chunkGroupIndex != chunkGroupCount)
+	{
+		elog(ERROR, "unexpected chunk group count");
+	}
+
+	systable_endscan_ordered(scanDescriptor);
+	index_close(index, AccessShareLock);
 	table_close(columnarChunkGroup, AccessShareLock);
 
 	return chunkGroupRowCounts;
@@ -1248,13 +1011,13 @@ InsertEmptyStripeMetadataRow(uint64 storageId, uint64 stripeId, uint32 columnCou
 
 
 /*
- * StripesForRelfilelocator returns a list of StripeMetadata for stripes
+ * StripesForRelfilenode returns a list of StripeMetadata for stripes
  * of the given relfilenode.
  */
 List *
-StripesForRelfilelocator(RelFileLocator relfilelocator)
+StripesForRelfilenode(RelFileNode relfilenode)
 {
-	uint64 storageId = LookupStorageId(relfilelocator);
+	uint64 storageId = LookupStorageId(relfilenode);
 
 	return ReadDataFileStripeList(storageId, GetTransactionSnapshot());
 }
@@ -1269,9 +1032,9 @@ StripesForRelfilelocator(RelFileLocator relfilelocator)
  * returns 0.
  */
 uint64
-GetHighestUsedAddress(RelFileLocator relfilelocator)
+GetHighestUsedAddress(RelFileNode relfilenode)
 {
-	uint64 storageId = LookupStorageId(relfilelocator);
+	uint64 storageId = LookupStorageId(relfilenode);
 
 	uint64 highestUsedAddress = 0;
 	uint64 highestUsedId = 0;
@@ -1385,27 +1148,21 @@ UpdateStripeMetadataRow(uint64 storageId, uint64 stripeId, bool *update,
 
 	ScanKeyData scanKey[2];
 	ScanKeyInit(&scanKey[0], Anum_columnar_stripe_storageid,
-				BTEqualStrategyNumber, F_INT8EQ, Int64GetDatum(storageId));
+				BTEqualStrategyNumber, F_OIDEQ, Int32GetDatum(storageId));
 	ScanKeyInit(&scanKey[1], Anum_columnar_stripe_stripe,
-				BTEqualStrategyNumber, F_INT8EQ, Int64GetDatum(stripeId));
+				BTEqualStrategyNumber, F_OIDEQ, Int32GetDatum(stripeId));
 
 	Oid columnarStripesOid = ColumnarStripeRelationId();
 
 	Relation columnarStripes = table_open(columnarStripesOid, AccessShareLock);
+	Relation columnarStripePkeyIndex = index_open(ColumnarStripePKeyIndexRelationId(),
+												  AccessShareLock);
 
-	Oid indexId = ColumnarStripePKeyIndexRelationId();
-	bool indexOk = OidIsValid(indexId);
-	SysScanDesc scanDescriptor = systable_beginscan(columnarStripes, indexId, indexOk,
-													&dirtySnapshot, 2, scanKey);
+	SysScanDesc scanDescriptor = systable_beginscan_ordered(columnarStripes,
+															columnarStripePkeyIndex,
+															&dirtySnapshot, 2, scanKey);
 
-	static bool loggedSlowMetadataAccessWarning = false;
-	if (!indexOk && !loggedSlowMetadataAccessWarning)
-	{
-		ereport(WARNING, (errmsg(SLOW_METADATA_ACCESS_WARNING, "stripe_pkey")));
-		loggedSlowMetadataAccessWarning = true;
-	}
-
-	HeapTuple oldTuple = systable_getnext(scanDescriptor);
+	HeapTuple oldTuple = systable_getnext_ordered(scanDescriptor, ForwardScanDirection);
 	if (!HeapTupleIsValid(oldTuple))
 	{
 		ereport(ERROR, (errmsg("attempted to modify an unexpected stripe, "
@@ -1440,7 +1197,8 @@ UpdateStripeMetadataRow(uint64 storageId, uint64 stripeId, bool *update,
 
 	CommandCounterIncrement();
 
-	systable_endscan(scanDescriptor);
+	systable_endscan_ordered(scanDescriptor);
+	index_close(columnarStripePkeyIndex, AccessShareLock);
 	table_close(columnarStripes, AccessShareLock);
 
 	/* return StripeMetadata object built from modified tuple */
@@ -1451,10 +1209,6 @@ UpdateStripeMetadataRow(uint64 storageId, uint64 stripeId, bool *update,
 /*
  * ReadDataFileStripeList reads the stripe list for a given storageId
  * in the given snapshot.
- *
- * Doesn't sort the stripes by their ids before returning if
- * stripe_first_row_number_idx is not available --normally can only happen
- * during pg upgrades.
  */
 static List *
 ReadDataFileStripeList(uint64 storageId, Snapshot snapshot)
@@ -1464,32 +1218,27 @@ ReadDataFileStripeList(uint64 storageId, Snapshot snapshot)
 	HeapTuple heapTuple;
 
 	ScanKeyInit(&scanKey[0], Anum_columnar_stripe_storageid,
-				BTEqualStrategyNumber, F_INT8EQ, Int64GetDatum(storageId));
+				BTEqualStrategyNumber, F_OIDEQ, Int32GetDatum(storageId));
 
 	Oid columnarStripesOid = ColumnarStripeRelationId();
 
 	Relation columnarStripes = table_open(columnarStripesOid, AccessShareLock);
+	Relation index = index_open(ColumnarStripeFirstRowNumberIndexRelationId(),
+								AccessShareLock);
 
-	Oid indexId = ColumnarStripeFirstRowNumberIndexRelationId();
-	bool indexOk = OidIsValid(indexId);
-	SysScanDesc scanDescriptor = systable_beginscan(columnarStripes, indexId,
-													indexOk, snapshot, 1, scanKey);
+	SysScanDesc scanDescriptor = systable_beginscan_ordered(columnarStripes, index,
+															snapshot, 1,
+															scanKey);
 
-	static bool loggedSlowMetadataAccessWarning = false;
-	if (!indexOk && !loggedSlowMetadataAccessWarning)
-	{
-		ereport(WARNING, (errmsg(SLOW_METADATA_ACCESS_WARNING,
-								 "stripe_first_row_number_idx")));
-		loggedSlowMetadataAccessWarning = true;
-	}
-
-	while (HeapTupleIsValid(heapTuple = systable_getnext(scanDescriptor)))
+	while (HeapTupleIsValid(heapTuple = systable_getnext_ordered(scanDescriptor,
+																 ForwardScanDirection)))
 	{
 		StripeMetadata *stripeMetadata = BuildStripeMetadata(columnarStripes, heapTuple);
 		stripeMetadataList = lappend(stripeMetadataList, stripeMetadata);
 	}
 
-	systable_endscan(scanDescriptor);
+	systable_endscan_ordered(scanDescriptor);
+	index_close(index, AccessShareLock);
 	table_close(columnarStripes, AccessShareLock);
 
 	return stripeMetadataList;
@@ -1552,7 +1301,7 @@ BuildStripeMetadata(Relation columnarStripes, HeapTuple heapTuple)
  * metadata tables.
  */
 void
-DeleteMetadataRows(RelFileLocator relfilelocator)
+DeleteMetadataRows(RelFileNode relfilenode)
 {
 	/*
 	 * During a restore for binary upgrade, metadata tables and indexes may or
@@ -1563,7 +1312,7 @@ DeleteMetadataRows(RelFileLocator relfilelocator)
 		return;
 	}
 
-	uint64 storageId = LookupStorageId(relfilelocator);
+	uint64 storageId = LookupStorageId(relfilenode);
 
 	DeleteStorageFromColumnarMetadataTable(ColumnarStripeRelationId(),
 										   Anum_columnar_stripe_storageid,
@@ -1591,7 +1340,7 @@ DeleteStorageFromColumnarMetadataTable(Oid metadataTableId,
 {
 	ScanKeyData scanKey[1];
 	ScanKeyInit(&scanKey[0], storageIdAtrrNumber, BTEqualStrategyNumber,
-				F_INT8EQ, Int64GetDatum(storageId));
+				F_INT8EQ, UInt64GetDatum(storageId));
 
 	Relation metadataTable = try_relation_open(metadataTableId, AccessShareLock);
 	if (metadataTable == NULL)
@@ -1600,30 +1349,25 @@ DeleteStorageFromColumnarMetadataTable(Oid metadataTableId,
 		return;
 	}
 
-	bool indexOk = OidIsValid(storageIdIndexId);
-	SysScanDesc scanDescriptor = systable_beginscan(metadataTable, storageIdIndexId,
-													indexOk, NULL, 1, scanKey);
+	Relation index = index_open(storageIdIndexId, AccessShareLock);
 
-	static bool loggedSlowMetadataAccessWarning = false;
-	if (!indexOk && !loggedSlowMetadataAccessWarning)
-	{
-		ereport(WARNING, (errmsg(SLOW_METADATA_ACCESS_WARNING,
-								 "on a columnar metadata table")));
-		loggedSlowMetadataAccessWarning = true;
-	}
+	SysScanDesc scanDescriptor = systable_beginscan_ordered(metadataTable, index, NULL,
+															1, scanKey);
 
 	ModifyState *modifyState = StartModifyRelation(metadataTable);
 
 	HeapTuple heapTuple;
-	while (HeapTupleIsValid(heapTuple = systable_getnext(scanDescriptor)))
+	while (HeapTupleIsValid(heapTuple = systable_getnext_ordered(scanDescriptor,
+																 ForwardScanDirection)))
 	{
 		DeleteTupleAndEnforceConstraints(modifyState, heapTuple);
 	}
 
-	systable_endscan(scanDescriptor);
+	systable_endscan_ordered(scanDescriptor);
 
 	FinishModifyRelation(modifyState);
 
+	index_close(index, AccessShareLock);
 	table_close(metadataTable, AccessShareLock);
 }
 
@@ -1636,8 +1380,12 @@ StartModifyRelation(Relation rel)
 {
 	EState *estate = create_estate_for_relation(rel);
 
+#if PG_VERSION_NUM >= PG_VERSION_14
 	ResultRelInfo *resultRelInfo = makeNode(ResultRelInfo);
 	InitResultRelInfo(resultRelInfo, rel, 1, NULL, 0);
+#else
+	ResultRelInfo *resultRelInfo = estate->es_result_relation_info;
+#endif
 
 	/* ExecSimpleRelationInsert, ... require caller to open indexes */
 	ExecOpenIndices(resultRelInfo, false);
@@ -1667,7 +1415,7 @@ InsertTupleAndEnforceConstraints(ModifyState *state, Datum *values, bool *nulls)
 	ExecStoreHeapTuple(tuple, slot, false);
 
 	/* use ExecSimpleRelationInsert to enforce constraints */
-	ExecSimpleRelationInsert(state->resultRelInfo, state->estate, slot);
+	ExecSimpleRelationInsert_compat(state->resultRelInfo, state->estate, slot);
 }
 
 
@@ -1685,7 +1433,7 @@ DeleteTupleAndEnforceConstraints(ModifyState *state, HeapTuple heapTuple)
 	simple_heap_delete(state->rel, tid);
 
 	/* execute AFTER ROW DELETE Triggers to enforce constraints */
-	ExecARDeleteTriggers(estate, resultRelInfo, tid, NULL, NULL, false);
+	ExecARDeleteTriggers(estate, resultRelInfo, tid, NULL, NULL);
 }
 
 
@@ -1698,8 +1446,12 @@ FinishModifyRelation(ModifyState *state)
 	ExecCloseIndices(state->resultRelInfo);
 
 	AfterTriggerEndQuery(state->estate);
+#if PG_VERSION_NUM >= PG_VERSION_14
 	ExecCloseResultRelations(state->estate);
 	ExecCloseRangeTableRelations(state->estate);
+#else
+	ExecCleanUpTriggerState(state->estate);
+#endif
 	ExecResetTupleTable(state->estate->es_tupleTable, false);
 	FreeExecutorState(state->estate);
 
@@ -1726,13 +1478,15 @@ create_estate_for_relation(Relation rel)
 	rte->relid = RelationGetRelid(rel);
 	rte->relkind = rel->rd_rel->relkind;
 	rte->rellockmode = AccessShareLock;
-
-#if PG_VERSION_NUM >= PG_VERSION_16
-	List *perminfos = NIL;
-	addRTEPermissionInfo(&perminfos, rte);
-	ExecInitRangeTable(estate, list_make1(rte), perminfos);
-#else
 	ExecInitRangeTable(estate, list_make1(rte));
+
+#if PG_VERSION_NUM < PG_VERSION_14
+	ResultRelInfo *resultRelInfo = makeNode(ResultRelInfo);
+	InitResultRelInfo(resultRelInfo, rel, 1, NULL, 0);
+
+	estate->es_result_relations = resultRelInfo;
+	estate->es_num_result_relations = 1;
+	estate->es_result_relation_info = resultRelInfo;
 #endif
 
 	estate->es_output_cid = GetCurrentCommandId(true);
@@ -1746,9 +1500,6 @@ create_estate_for_relation(Relation rel)
 
 /*
  * DatumToBytea serializes a datum into a bytea value.
- *
- * Since we don't want to limit datum size to RSIZE_MAX unnecessarily,
- * we use memcpy instead of memcpy_s several places in this function.
  */
 static bytea *
 DatumToBytea(Datum value, Form_pg_attribute attrForm)
@@ -1765,16 +1516,19 @@ DatumToBytea(Datum value, Form_pg_attribute attrForm)
 			Datum tmp;
 			store_att_byval(&tmp, value, attrForm->attlen);
 
-			memcpy(VARDATA(result), &tmp, attrForm->attlen); /* IGNORE-BANNED */
+			memcpy_s(VARDATA(result), datumLength + VARHDRSZ,
+					 &tmp, attrForm->attlen);
 		}
 		else
 		{
-			memcpy(VARDATA(result), DatumGetPointer(value), attrForm->attlen); /* IGNORE-BANNED */
+			memcpy_s(VARDATA(result), datumLength + VARHDRSZ,
+					 DatumGetPointer(value), attrForm->attlen);
 		}
 	}
 	else
 	{
-		memcpy(VARDATA(result), DatumGetPointer(value), datumLength); /* IGNORE-BANNED */
+		memcpy_s(VARDATA(result), datumLength + VARHDRSZ,
+				 DatumGetPointer(value), datumLength);
 	}
 
 	return result;
@@ -1793,12 +1547,8 @@ ByteaToDatum(bytea *bytes, Form_pg_attribute attrForm)
 	 * after the byteaDatum is freed.
 	 */
 	char *binaryDataCopy = palloc0(VARSIZE_ANY_EXHDR(bytes));
-
-	/*
-	 * We use IGNORE-BANNED here since we don't want to limit datum size to
-	 * RSIZE_MAX unnecessarily.
-	 */
-	memcpy(binaryDataCopy, VARDATA_ANY(bytes), VARSIZE_ANY_EXHDR(bytes)); /* IGNORE-BANNED */
+	memcpy_s(binaryDataCopy, VARSIZE_ANY_EXHDR(bytes),
+			 VARDATA_ANY(bytes), VARSIZE_ANY_EXHDR(bytes));
 
 	return fetch_att(binaryDataCopy, attrForm->attbyval, attrForm->attlen);
 }
@@ -1920,15 +1670,7 @@ ColumnarChunkGroupIndexRelationId(void)
 static Oid
 ColumnarNamespaceId(void)
 {
-	Oid namespace = get_namespace_oid("columnar_internal", true);
-
-	/* if schema is earlier than 11.1-1 */
-	if (!OidIsValid(namespace))
-	{
-		namespace = get_namespace_oid("columnar", false);
-	}
-
-	return namespace;
+	return get_namespace_oid("columnar", false);
 }
 
 
@@ -1937,11 +1679,10 @@ ColumnarNamespaceId(void)
  * false if the relation doesn't have a meta page yet.
  */
 static uint64
-LookupStorageId(RelFileLocator relfilelocator)
+LookupStorageId(RelFileNode relfilenode)
 {
-	Oid relationId = RelidByRelfilenumber(RelationTablespace_compat(relfilelocator),
-										  RelationPhysicalIdentifierNumber_compat(
-											  relfilelocator));
+	Oid relationId = RelidByRelfilenode(relfilenode.spcNode,
+										relfilenode.relNode);
 
 	Relation relation = relation_open(relationId, AccessShareLock);
 	uint64 storageId = ColumnarStorageGetStorageId(relation, false);
@@ -1971,13 +1712,6 @@ columnar_relation_storageid(PG_FUNCTION_ARGS)
 {
 	Oid relationId = PG_GETARG_OID(0);
 	Relation relation = relation_open(relationId, AccessShareLock);
-
-	if (!object_ownercheck(RelationRelationId, relationId, GetUserId()))
-	{
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_TABLE,
-					   get_rel_name(relationId));
-	}
-
 	if (!IsColumnarTableAmTable(relationId))
 	{
 		elog(ERROR, "relation \"%s\" is not a columnar table",
@@ -2004,10 +1738,11 @@ ColumnarStorageUpdateIfNeeded(Relation rel, bool isUpgrade)
 		return;
 	}
 
-	BlockNumber nblocks = smgrnblocks(RelationGetSmgr(rel), MAIN_FORKNUM);
+	RelationOpenSmgr(rel);
+	BlockNumber nblocks = smgrnblocks(rel->rd_smgr, MAIN_FORKNUM);
 	if (nblocks < 2)
 	{
-		ColumnarStorageInit(RelationGetSmgr(rel), ColumnarMetadataNewStorageId());
+		ColumnarStorageInit(rel->rd_smgr, ColumnarMetadataNewStorageId());
 		return;
 	}
 
@@ -2041,7 +1776,7 @@ GetHighestUsedRowNumber(uint64 storageId)
 	List *stripeMetadataList = ReadDataFileStripeList(storageId,
 													  GetTransactionSnapshot());
 	StripeMetadata *stripeMetadata = NULL;
-	foreach_declared_ptr(stripeMetadata, stripeMetadataList)
+	foreach_ptr(stripeMetadata, stripeMetadataList)
 	{
 		highestRowNumber = Max(highestRowNumber,
 							   StripeGetHighestRowNumber(stripeMetadata));

src/backend/columnar/columnar_reader.c

@@ -22,15 +22,16 @@
 #include "access/xact.h"
 #include "catalog/pg_am.h"
 #include "commands/defrem.h"
+#include "distributed/listutils.h"
 #include "nodes/makefuncs.h"
 #include "nodes/nodeFuncs.h"
-#include "optimizer/clauses.h"
 #include "optimizer/optimizer.h"
+#include "optimizer/clauses.h"
 #include "optimizer/restrictinfo.h"
 #include "storage/fd.h"
 #include "utils/guc.h"
-#include "utils/lsyscache.h"
 #include "utils/memutils.h"
+#include "utils/lsyscache.h"
 #include "utils/rel.h"
 
 #include "columnar/columnar.h"
@@ -38,8 +39,6 @@
 #include "columnar/columnar_tableam.h"
 #include "columnar/columnar_version_compat.h"
 
-#include "distributed/listutils.h"
-
 #define UNEXPECTED_STRIPE_READ_ERR_MSG \
 	"attempted to read an unexpected stripe while reading columnar " \
 	"table %s, stripe with id=" UINT64_FORMAT " is not flushed"
@@ -255,9 +254,8 @@ ColumnarReadFlushPendingWrites(ColumnarReadState *readState)
 {
 	Assert(!readState->snapshotRegisteredByUs);
 
-	RelFileNumber relfilenumber = RelationPhysicalIdentifierNumber_compat(
-		RelationPhysicalIdentifier_compat(readState->relation));
-	FlushWriteStateForRelfilenumber(relfilenumber, GetCurrentSubTransactionId());
+	Oid relfilenode = readState->relation->rd_node.relNode;
+	FlushWriteStateForRelfilenode(relfilenode, GetCurrentSubTransactionId());
 
 	if (readState->snapshot == InvalidSnapshot || !IsMVCCSnapshot(readState->snapshot))
 	{
@@ -880,7 +878,7 @@ ReadChunkGroupNextRow(ChunkGroupReadState *chunkGroupReadState, Datum *columnVal
 	memset(columnNulls, true, sizeof(bool) * chunkGroupReadState->columnCount);
 
 	int attno;
-	foreach_declared_int(attno, chunkGroupReadState->projectedColumnList)
+	foreach_int(attno, chunkGroupReadState->projectedColumnList)
 	{
 		const ChunkData *chunkGroupData = chunkGroupReadState->chunkGroupData;
 		const int rowIndex = chunkGroupReadState->currentRow;
@@ -986,8 +984,7 @@ ColumnarTableRowCount(Relation relation)
 {
 	ListCell *stripeMetadataCell = NULL;
 	uint64 totalRowCount = 0;
-	List *stripeList = StripesForRelfilelocator(RelationPhysicalIdentifier_compat(
-													relation));
+	List *stripeList = StripesForRelfilenode(relation->rd_node);
 
 	foreach(stripeMetadataCell, stripeList)
 	{
@@ -1015,8 +1012,7 @@ LoadFilteredStripeBuffers(Relation relation, StripeMetadata *stripeMetadata,
 
 	bool *projectedColumnMask = ProjectedColumnMask(columnCount, projectedColumnList);
 
-	StripeSkipList *stripeSkipList = ReadStripeSkipList(RelationPhysicalIdentifier_compat(
-															relation),
+	StripeSkipList *stripeSkipList = ReadStripeSkipList(relation->rd_node,
 														stripeMetadata->id,
 														tupleDescriptor,
 														stripeMetadata->chunkCount,
@@ -1489,7 +1485,7 @@ ProjectedColumnMask(uint32 columnCount, List *projectedColumnList)
 	bool *projectedColumnMask = palloc0(columnCount * sizeof(bool));
 	int attno;
 
-	foreach_declared_int(attno, projectedColumnList)
+	foreach_int(attno, projectedColumnList)
 	{
 		/* attno is 1-indexed; projectedColumnMask is 0-indexed */
 		int columnIndex = attno - 1;
@@ -1561,7 +1557,7 @@ DeserializeDatumArray(StringInfo datumBuffer, bool *existsArray, uint32 datumCou
 										   datumTypeLength);
 		currentDatumDataOffset = att_addlength_datum(currentDatumDataOffset,
 													 datumTypeLength,
-													 datumArray[datumIndex]);
+													 currentDatumDataPointer);
 		currentDatumDataOffset = att_align_nominal(currentDatumDataOffset,
 												   datumTypeAlign);
 

src/backend/columnar/columnar_storage.c

@@ -36,16 +36,14 @@
 
 #include "postgres.h"
 
-#include "miscadmin.h"
 #include "safe_lib.h"
 
 #include "access/generic_xlog.h"
 #include "catalog/storage.h"
+#include "miscadmin.h"
 #include "storage/bufmgr.h"
 #include "storage/lmgr.h"
 
-#include "pg_version_compat.h"
-
 #include "columnar/columnar.h"
 #include "columnar/columnar_storage.h"
 
@@ -169,11 +167,7 @@ ColumnarStorageInit(SMgrRelation srel, uint64 storageId)
 	}
 
 	/* create two pages */
-#if PG_VERSION_NUM >= PG_VERSION_16
-	PGIOAlignedBlock block;
-#else
 	PGAlignedBlock block;
-#endif
 	Page page = block.data;
 
 	/* write metapage */
@@ -192,7 +186,7 @@ ColumnarStorageInit(SMgrRelation srel, uint64 storageId)
 			 (char *) &metapage, sizeof(ColumnarMetapage));
 	phdr->pd_lower += sizeof(ColumnarMetapage);
 
-	log_newpage(RelationPhysicalIdentifierBackend_compat(&srel), MAIN_FORKNUM,
+	log_newpage(&srel->smgr_rnode.node, MAIN_FORKNUM,
 				COLUMNAR_METAPAGE_BLOCKNO, page, true);
 	PageSetChecksumInplace(page, COLUMNAR_METAPAGE_BLOCKNO);
 	smgrextend(srel, MAIN_FORKNUM, COLUMNAR_METAPAGE_BLOCKNO, page, true);
@@ -200,7 +194,7 @@ ColumnarStorageInit(SMgrRelation srel, uint64 storageId)
 	/* write empty page */
 	PageInit(page, BLCKSZ, 0);
 
-	log_newpage(RelationPhysicalIdentifierBackend_compat(&srel), MAIN_FORKNUM,
+	log_newpage(&srel->smgr_rnode.node, MAIN_FORKNUM,
 				COLUMNAR_EMPTY_BLOCKNO, page, true);
 	PageSetChecksumInplace(page, COLUMNAR_EMPTY_BLOCKNO);
 	smgrextend(srel, MAIN_FORKNUM, COLUMNAR_EMPTY_BLOCKNO, page, true);
@@ -360,7 +354,8 @@ ColumnarStorageGetReservedOffset(Relation rel, bool force)
 bool
 ColumnarStorageIsCurrent(Relation rel)
 {
-	BlockNumber nblocks = smgrnblocks(RelationGetSmgr(rel), MAIN_FORKNUM);
+	RelationOpenSmgr(rel);
+	BlockNumber nblocks = smgrnblocks(rel->rd_smgr, MAIN_FORKNUM);
 
 	if (nblocks < 2)
 	{
@@ -444,7 +439,8 @@ ColumnarStorageReserveData(Relation rel, uint64 amount)
 	PhysicalAddr final = LogicalToPhysical(nextReservation - 1);
 
 	/* extend with new pages */
-	BlockNumber nblocks = smgrnblocks(RelationGetSmgr(rel), MAIN_FORKNUM);
+	RelationOpenSmgr(rel);
+	BlockNumber nblocks = smgrnblocks(rel->rd_smgr, MAIN_FORKNUM);
 
 	while (nblocks <= final.blockno)
 	{
@@ -551,7 +547,8 @@ ColumnarStorageTruncate(Relation rel, uint64 newDataReservation)
 			 rel->rd_id, newDataReservation);
 	}
 
-	BlockNumber old_rel_pages = smgrnblocks(RelationGetSmgr(rel), MAIN_FORKNUM);
+	RelationOpenSmgr(rel);
+	BlockNumber old_rel_pages = smgrnblocks(rel->rd_smgr, MAIN_FORKNUM);
 	if (old_rel_pages == 0)
 	{
 		/* nothing to do */
@@ -630,7 +627,8 @@ ColumnarOverwriteMetapage(Relation relation, ColumnarMetapage columnarMetapage)
 static ColumnarMetapage
 ColumnarMetapageRead(Relation rel, bool force)
 {
-	BlockNumber nblocks = smgrnblocks(RelationGetSmgr(rel), MAIN_FORKNUM);
+	RelationOpenSmgr(rel);
+	BlockNumber nblocks = smgrnblocks(rel->rd_smgr, MAIN_FORKNUM);
 	if (nblocks == 0)
 	{
 		/*

src/backend/columnar/columnar_writer.c

@@ -16,37 +16,28 @@
 
 #include "postgres.h"
 
-#include "miscadmin.h"
 #include "safe_lib.h"
 
 #include "access/heapam.h"
 #include "access/nbtree.h"
 #include "catalog/pg_am.h"
+#include "miscadmin.h"
 #include "storage/fd.h"
 #include "storage/smgr.h"
 #include "utils/guc.h"
 #include "utils/memutils.h"
 #include "utils/rel.h"
-
-#include "pg_version_compat.h"
-#include "pg_version_constants.h"
+#include "utils/relfilenodemap.h"
 
 #include "columnar/columnar.h"
 #include "columnar/columnar_storage.h"
 #include "columnar/columnar_version_compat.h"
 
-#if PG_VERSION_NUM >= PG_VERSION_16
-#include "storage/relfilelocator.h"
-#include "utils/relfilenumbermap.h"
-#else
-#include "utils/relfilenodemap.h"
-#endif
-
 struct ColumnarWriteState
 {
 	TupleDesc tupleDescriptor;
 	FmgrInfo **comparisonFunctionArray;
-	RelFileLocator relfilelocator;
+	RelFileNode relfilenode;
 
 	MemoryContext stripeWriteContext;
 	MemoryContext perTupleContext;
@@ -93,7 +84,7 @@ static StringInfo CopyStringInfo(StringInfo sourceString);
  * data load operation.
  */
 ColumnarWriteState *
-ColumnarBeginWrite(RelFileLocator relfilelocator,
+ColumnarBeginWrite(RelFileNode relfilenode,
 				   ColumnarOptions options,
 				   TupleDesc tupleDescriptor)
 {
@@ -133,7 +124,7 @@ ColumnarBeginWrite(RelFileLocator relfilelocator,
 												options.chunkRowCount);
 
 	ColumnarWriteState *writeState = palloc0(sizeof(ColumnarWriteState));
-	writeState->relfilelocator = relfilelocator;
+	writeState->relfilenode = relfilenode;
 	writeState->options = options;
 	writeState->tupleDescriptor = CreateTupleDescCopy(tupleDescriptor);
 	writeState->comparisonFunctionArray = comparisonFunctionArray;
@@ -183,10 +174,8 @@ ColumnarWriteRow(ColumnarWriteState *writeState, Datum *columnValues, bool *colu
 		writeState->stripeSkipList = stripeSkipList;
 		writeState->compressionBuffer = makeStringInfo();
 
-		Oid relationId = RelidByRelfilenumber(RelationTablespace_compat(
-												  writeState->relfilelocator),
-											  RelationPhysicalIdentifierNumber_compat(
-												  writeState->relfilelocator));
+		Oid relationId = RelidByRelfilenode(writeState->relfilenode.spcNode,
+											writeState->relfilenode.relNode);
 		Relation relation = relation_open(relationId, NoLock);
 		writeState->emptyStripeReservation =
 			ReserveEmptyStripe(relation, columnCount, chunkRowCount,
@@ -404,10 +393,8 @@ FlushStripe(ColumnarWriteState *writeState)
 
 	elog(DEBUG1, "Flushing Stripe of size %d", stripeBuffers->rowCount);
 
-	Oid relationId = RelidByRelfilenumber(RelationTablespace_compat(
-											  writeState->relfilelocator),
-										  RelationPhysicalIdentifierNumber_compat(
-											  writeState->relfilelocator));
+	Oid relationId = RelidByRelfilenode(writeState->relfilenode.spcNode,
+										writeState->relfilenode.relNode);
 	Relation relation = relation_open(relationId, NoLock);
 
 	/*
@@ -499,10 +486,10 @@ FlushStripe(ColumnarWriteState *writeState)
 		}
 	}
 
-	SaveChunkGroups(writeState->relfilelocator,
+	SaveChunkGroups(writeState->relfilenode,
 					stripeMetadata->id,
 					writeState->chunkGroupRowCounts);
-	SaveStripeSkipList(writeState->relfilelocator,
+	SaveStripeSkipList(writeState->relfilenode,
 					   stripeMetadata->id,
 					   stripeSkipList, tupleDescriptor);
 
@@ -544,9 +531,6 @@ SerializeBoolArray(bool *boolArray, uint32 boolArrayLength)
 /*
  * SerializeSingleDatum serializes the given datum value and appends it to the
  * provided string info buffer.
- *
- * Since we don't want to limit datum buffer size to RSIZE_MAX unnecessarily,
- * we use memcpy instead of memcpy_s several places in this function.
  */
 static void
 SerializeSingleDatum(StringInfo datumBuffer, Datum datum, bool datumTypeByValue,
@@ -568,13 +552,15 @@ SerializeSingleDatum(StringInfo datumBuffer, Datum datum, bool datumTypeByValue,
 		}
 		else
 		{
-			memcpy(currentDatumDataPointer, DatumGetPointer(datum), datumTypeLength); /* IGNORE-BANNED */
+			memcpy_s(currentDatumDataPointer, datumBuffer->maxlen - datumBuffer->len,
+					 DatumGetPointer(datum), datumTypeLength);
 		}
 	}
 	else
 	{
 		Assert(!datumTypeByValue);
-		memcpy(currentDatumDataPointer, DatumGetPointer(datum), datumLength); /* IGNORE-BANNED */
+		memcpy_s(currentDatumDataPointer, datumBuffer->maxlen - datumBuffer->len,
+				 DatumGetPointer(datum), datumLength);
 	}
 
 	datumBuffer->len += datumLengthAligned;
@@ -728,12 +714,7 @@ DatumCopy(Datum datum, bool datumTypeByValue, int datumTypeLength)
 	{
 		uint32 datumLength = att_addlength_datum(0, datumTypeLength, datum);
 		char *datumData = palloc0(datumLength);
-
-		/*
-		 * We use IGNORE-BANNED here since we don't want to limit datum size to
-		 * RSIZE_MAX unnecessarily.
-		 */
-		memcpy(datumData, DatumGetPointer(datum), datumLength); /* IGNORE-BANNED */
+		memcpy_s(datumData, datumLength, DatumGetPointer(datum), datumLength);
 
 		datumCopy = PointerGetDatum(datumData);
 	}
@@ -756,12 +737,8 @@ CopyStringInfo(StringInfo sourceString)
 		targetString->data = palloc0(sourceString->len);
 		targetString->len = sourceString->len;
 		targetString->maxlen = sourceString->len;
-
-		/*
-		 * We use IGNORE-BANNED here since we don't want to limit string
-		 * buffer size to RSIZE_MAX unnecessarily.
-		 */
-		memcpy(targetString->data, sourceString->data, sourceString->len); /* IGNORE-BANNED */
+		memcpy_s(targetString->data, sourceString->len,
+				 sourceString->data, sourceString->len);
 	}
 
 	return targetString;

src/backend/columnar/mod.c

@@ -18,15 +18,13 @@
 #include "citus_version.h"
 
 #include "columnar/columnar.h"
+#include "columnar/mod.h"
+
 #include "columnar/columnar_tableam.h"
 
-
-PG_MODULE_MAGIC;
-
-void _PG_init(void);
-
 void
-_PG_init(void)
+columnar_init(void)
 {
-	columnar_init();
+	columnar_init_gucs();
+	columnar_tableam_init();
 }

src/backend/columnar/safeclib

@@ -1 +0,0 @@
-../../../vendor/safestringlib/safeclib/

src/backend/columnar/sql/citus_columnar--11.1-0--11.1-1.sql

@@ -1,32 +0,0 @@
--- add columnar objects back
-ALTER EXTENSION citus_columnar ADD SCHEMA columnar;
-ALTER EXTENSION citus_columnar ADD SCHEMA columnar_internal;
-ALTER EXTENSION citus_columnar ADD SEQUENCE columnar_internal.storageid_seq;
-ALTER EXTENSION citus_columnar ADD TABLE columnar_internal.options;
-ALTER EXTENSION citus_columnar ADD TABLE columnar_internal.stripe;
-ALTER EXTENSION citus_columnar ADD TABLE columnar_internal.chunk_group;
-ALTER EXTENSION citus_columnar ADD TABLE columnar_internal.chunk;
-
-ALTER EXTENSION citus_columnar ADD FUNCTION columnar_internal.columnar_handler;
-ALTER EXTENSION citus_columnar ADD ACCESS METHOD columnar;
-ALTER EXTENSION citus_columnar ADD FUNCTION pg_catalog.alter_columnar_table_set;
-ALTER EXTENSION citus_columnar ADD FUNCTION pg_catalog.alter_columnar_table_reset;
-
-ALTER EXTENSION citus_columnar ADD FUNCTION citus_internal.upgrade_columnar_storage;
-ALTER EXTENSION citus_columnar ADD FUNCTION citus_internal.downgrade_columnar_storage;
-ALTER EXTENSION citus_columnar ADD FUNCTION citus_internal.columnar_ensure_am_depends_catalog;
-
-ALTER EXTENSION citus_columnar ADD FUNCTION columnar.get_storage_id;
-ALTER EXTENSION citus_columnar ADD VIEW columnar.storage;
-ALTER EXTENSION citus_columnar ADD VIEW columnar.options;
-ALTER EXTENSION citus_columnar ADD VIEW columnar.stripe;
-ALTER EXTENSION citus_columnar ADD VIEW columnar.chunk_group;
-ALTER EXTENSION citus_columnar ADD VIEW columnar.chunk;
-
--- move citus_internal functions to columnar_internal
-
-ALTER FUNCTION citus_internal.upgrade_columnar_storage(regclass) SET SCHEMA columnar_internal;
-ALTER FUNCTION citus_internal.downgrade_columnar_storage(regclass) SET SCHEMA columnar_internal;
-ALTER FUNCTION citus_internal.columnar_ensure_am_depends_catalog() SET SCHEMA columnar_internal;
-
-

src/backend/columnar/sql/citus_columnar--11.1-0.sql

@@ -1 +0,0 @@
--- fake sql file 'Y'

src/backend/columnar/sql/citus_columnar--11.1-1--11.2-1.sql

@@ -1,19 +0,0 @@
--- citus_columnar--11.1-1--11.2-1
-
-#include "udfs/columnar_ensure_am_depends_catalog/11.2-1.sql"
-
-DELETE FROM pg_depend
-WHERE classid = 'pg_am'::regclass::oid
-    AND objid IN (select oid from pg_am where amname = 'columnar')
-    AND objsubid = 0
-    AND refclassid = 'pg_class'::regclass::oid
-    AND refobjid IN (
-        'columnar_internal.stripe_first_row_number_idx'::regclass::oid,
-        'columnar_internal.chunk_group_pkey'::regclass::oid,
-        'columnar_internal.chunk_pkey'::regclass::oid,
-        'columnar_internal.options_pkey'::regclass::oid,
-        'columnar_internal.stripe_first_row_number_idx'::regclass::oid,
-        'columnar_internal.stripe_pkey'::regclass::oid
-    )
-    AND refobjsubid = 0
-    AND deptype = 'n';

src/backend/columnar/sql/citus_columnar--11.1-1.sql

@@ -1,435 +0,0 @@
--- complain if script is sourced in psql, rather than via CREATE EXTENSION
-\echo Use "CREATE EXTENSION citus_columnar" to load this file. \quit
-
--- columnar--9.5-1--10.0-1.sql
-
-CREATE SCHEMA IF NOT EXISTS columnar;
-SET search_path TO columnar;
-
-
-CREATE SEQUENCE IF NOT EXISTS storageid_seq MINVALUE 10000000000 NO CYCLE;
-
-CREATE TABLE IF NOT EXISTS options (
-    regclass regclass NOT NULL PRIMARY KEY,
-    chunk_group_row_limit int NOT NULL,
-    stripe_row_limit int NOT NULL,
-    compression_level int NOT NULL,
-    compression name NOT NULL
-) WITH (user_catalog_table = true);
-
-COMMENT ON TABLE options IS 'columnar table specific options, maintained by alter_columnar_table_set';
-
-CREATE TABLE IF NOT EXISTS stripe (
-    storage_id bigint NOT NULL,
-    stripe_num bigint NOT NULL,
-    file_offset bigint NOT NULL,
-    data_length bigint NOT NULL,
-    column_count int NOT NULL,
-    chunk_row_count int NOT NULL,
-    row_count bigint NOT NULL,
-    chunk_group_count int NOT NULL,
-    first_row_number bigint NOT NULL,
-    PRIMARY KEY (storage_id, stripe_num),
-    CONSTRAINT stripe_first_row_number_idx UNIQUE (storage_id, first_row_number)
-) WITH (user_catalog_table = true);
-
-COMMENT ON TABLE stripe IS 'Columnar per stripe metadata';
-
-CREATE TABLE IF NOT EXISTS chunk_group (
-    storage_id bigint NOT NULL,
-    stripe_num bigint NOT NULL,
-    chunk_group_num int NOT NULL,
-    row_count bigint NOT NULL,
-    PRIMARY KEY (storage_id, stripe_num, chunk_group_num)
-);
-
-COMMENT ON TABLE chunk_group IS 'Columnar chunk group metadata';
-
-CREATE TABLE IF NOT EXISTS chunk (
-    storage_id bigint NOT NULL,
-    stripe_num bigint NOT NULL,
-    attr_num int NOT NULL,
-    chunk_group_num int NOT NULL,
-    minimum_value bytea,
-    maximum_value bytea,
-    value_stream_offset bigint NOT NULL,
-    value_stream_length bigint NOT NULL,
-    exists_stream_offset bigint NOT NULL,
-    exists_stream_length bigint NOT NULL,
-    value_compression_type int NOT NULL,
-    value_compression_level int NOT NULL,
-    value_decompressed_length bigint NOT NULL,
-    value_count bigint NOT NULL,
-    PRIMARY KEY (storage_id, stripe_num, attr_num, chunk_group_num)
-) WITH (user_catalog_table = true);
-
-COMMENT ON TABLE chunk IS 'Columnar per chunk metadata';
-
-DO $proc$
-BEGIN
-
--- from version 12 and up we have support for tableam's if installed on pg11 we can't
--- create the objects here. Instead we rely on citus_finish_pg_upgrade to be called by the
--- user instead to add the missing objects
-IF substring(current_Setting('server_version'), '\d+')::int >= 12 THEN
-  EXECUTE $$
---#include "udfs/columnar_handler/10.0-1.sql"
-CREATE OR REPLACE FUNCTION columnar.columnar_handler(internal)
-    RETURNS table_am_handler
-    LANGUAGE C
-AS 'MODULE_PATHNAME', 'columnar_handler';
-COMMENT ON FUNCTION columnar.columnar_handler(internal)
-    IS 'internal function returning the handler for columnar tables';
-
--- postgres 11.8 does not support the syntax for table am, also it is seemingly trying
--- to parse the upgrade file and erroring on unknown syntax.
--- normally this section would not execute on postgres 11 anyway. To trick it to pass on
--- 11.8 we wrap the statement in a plpgsql block together with an EXECUTE. This is valid
--- syntax on 11.8 and will execute correctly in 12
-DO $create_table_am$
-BEGIN
-  EXECUTE 'CREATE ACCESS METHOD columnar TYPE TABLE HANDLER columnar.columnar_handler';
-END $create_table_am$;
-
---#include "udfs/alter_columnar_table_set/10.0-1.sql"
-CREATE OR REPLACE FUNCTION pg_catalog.alter_columnar_table_set(
-    table_name regclass,
-    chunk_group_row_limit int DEFAULT NULL,
-    stripe_row_limit int DEFAULT NULL,
-    compression name DEFAULT null,
-    compression_level int DEFAULT NULL)
-    RETURNS void
-    LANGUAGE C
-AS 'MODULE_PATHNAME', 'alter_columnar_table_set';
-
-COMMENT ON FUNCTION pg_catalog.alter_columnar_table_set(
-    table_name regclass,
-    chunk_group_row_limit int,
-    stripe_row_limit int,
-    compression name,
-    compression_level int)
-IS 'set one or more options on a columnar table, when set to NULL no change is made';
-
-
---#include "udfs/alter_columnar_table_reset/10.0-1.sql"
-CREATE OR REPLACE FUNCTION pg_catalog.alter_columnar_table_reset(
-    table_name regclass,
-    chunk_group_row_limit bool DEFAULT false,
-    stripe_row_limit bool DEFAULT false,
-    compression bool DEFAULT false,
-    compression_level bool DEFAULT false)
-    RETURNS void
-    LANGUAGE C
-AS 'MODULE_PATHNAME', 'alter_columnar_table_reset';
-
-COMMENT ON FUNCTION pg_catalog.alter_columnar_table_reset(
-    table_name regclass,
-    chunk_group_row_limit bool,
-    stripe_row_limit bool,
-    compression bool,
-    compression_level bool)
-IS 'reset on or more options on a columnar table to the system defaults';
-
-  $$;
-END IF;
-END$proc$;
-
--- (this function being dropped in 10.0.3)->#include "udfs/columnar_ensure_objects_exist/10.0-1.sql"
-
-RESET search_path;
-
--- columnar--10.0.-1 --10.0.2
-GRANT USAGE ON SCHEMA columnar TO PUBLIC;
-GRANT SELECT ON ALL tables IN SCHEMA columnar TO PUBLIC ;
-
--- columnar--10.0-3--10.1-1.sql
-
--- Drop foreign keys between columnar metadata tables.
-
-
--- columnar--10.1-1--10.2-1.sql
-
--- For a proper mapping between tid & (stripe, row_num), add a new column to
--- columnar.stripe and define a BTREE index on this column.
--- Also include storage_id column for per-relation scans.
-
-
--- Populate first_row_number column of columnar.stripe table.
---
--- For simplicity, we calculate MAX(row_count) value across all the stripes
--- of all the columanar tables and then use it to populate first_row_number
--- column. This would introduce some gaps however we are okay with that since
--- it's already the case with regular INSERT/COPY's.
-DO $$
-DECLARE
-  max_row_count bigint;
-  -- this should be equal to columnar_storage.h/COLUMNAR_FIRST_ROW_NUMBER
-  COLUMNAR_FIRST_ROW_NUMBER constant bigint := 1;
-BEGIN
-  SELECT MAX(row_count) INTO max_row_count FROM columnar.stripe;
-  UPDATE columnar.stripe SET first_row_number = COLUMNAR_FIRST_ROW_NUMBER +
-                                                (stripe_num - 1) * max_row_count;
-END;
-$$;
-
--- columnar--10.2-1--10.2-2.sql
-
--- revoke read access for columnar.chunk from unprivileged
--- user as it contains chunk min/max values
-REVOKE SELECT ON columnar.chunk FROM PUBLIC;
-
-
--- columnar--10.2-2--10.2-3.sql
-
--- Since stripe_first_row_number_idx is required to scan a columnar table, we
--- need to make sure that it is created before doing anything with columnar
--- tables during pg upgrades.
---
--- However, a plain btree index is not a dependency of a table, so pg_upgrade
--- cannot guarantee that stripe_first_row_number_idx gets created when
--- creating columnar.stripe, unless we make it a unique "constraint".
---
--- To do that, drop stripe_first_row_number_idx and create a unique
--- constraint with the same name to keep the code change at minimum.
-
--- columnar--10.2-3--10.2-4.sql
-
-
--- columnar--11.0-2--11.1-1.sql
-
-CREATE OR REPLACE FUNCTION pg_catalog.alter_columnar_table_set(
-    table_name regclass,
-    chunk_group_row_limit int DEFAULT NULL,
-    stripe_row_limit int DEFAULT NULL,
-    compression name DEFAULT null,
-    compression_level int DEFAULT NULL)
-    RETURNS void
-    LANGUAGE plpgsql AS
-$alter_columnar_table_set$
-declare
-  noop BOOLEAN := true;
-  cmd  TEXT    := 'ALTER TABLE ' || table_name::text || ' SET (';
-begin
-  if (chunk_group_row_limit is not null) then
-    if (not noop) then cmd := cmd || ', '; end if;
-    cmd := cmd  || 'columnar.chunk_group_row_limit=' || chunk_group_row_limit;
-    noop := false;
-  end if;
-  if (stripe_row_limit is not null) then
-    if (not noop) then cmd := cmd || ', '; end if;
-    cmd := cmd || 'columnar.stripe_row_limit=' || stripe_row_limit;
-    noop := false;
-  end if;
-  if (compression is not null) then
-    if (not noop) then cmd := cmd || ', '; end if;
-    cmd := cmd || 'columnar.compression=' || compression;
-    noop := false;
-  end if;
-  if (compression_level is not null) then
-    if (not noop) then cmd := cmd || ', '; end if;
-    cmd := cmd || 'columnar.compression_level=' || compression_level;
-    noop := false;
-  end if;
-  cmd := cmd || ')';
-  if (not noop) then
-    execute cmd;
-  end if;
-  return;
-end;
-$alter_columnar_table_set$;
-
-COMMENT ON FUNCTION pg_catalog.alter_columnar_table_set(
-    table_name regclass,
-    chunk_group_row_limit int,
-    stripe_row_limit int,
-    compression name,
-    compression_level int)
-IS 'set one or more options on a columnar table, when set to NULL no change is made';
-
-CREATE OR REPLACE FUNCTION pg_catalog.alter_columnar_table_reset(
-    table_name regclass,
-    chunk_group_row_limit bool DEFAULT false,
-    stripe_row_limit bool DEFAULT false,
-    compression bool DEFAULT false,
-    compression_level bool DEFAULT false)
-    RETURNS void
-    LANGUAGE plpgsql AS
-$alter_columnar_table_reset$
-declare
-  noop BOOLEAN := true;
-  cmd  TEXT    := 'ALTER TABLE ' || table_name::text || ' RESET (';
-begin
-  if (chunk_group_row_limit) then
-    if (not noop) then cmd := cmd || ', '; end if;
-    cmd := cmd   || 'columnar.chunk_group_row_limit';
-    noop := false;
-  end if;
-  if (stripe_row_limit) then
-    if (not noop) then cmd := cmd || ', '; end if;
-    cmd := cmd || 'columnar.stripe_row_limit';
-    noop := false;
-  end if;
-  if (compression) then
-    if (not noop) then cmd := cmd || ', '; end if;
-    cmd := cmd || 'columnar.compression';
-    noop := false;
-  end if;
-  if (compression_level) then
-    if (not noop) then cmd := cmd || ', '; end if;
-    cmd := cmd || 'columnar.compression_level';
-    noop := false;
-  end if;
-  cmd := cmd || ')';
-  if (not noop) then
-    execute cmd;
-  end if;
-  return;
-end;
-$alter_columnar_table_reset$;
-
-COMMENT ON FUNCTION pg_catalog.alter_columnar_table_reset(
-    table_name regclass,
-    chunk_group_row_limit bool,
-    stripe_row_limit bool,
-    compression bool,
-    compression_level bool)
-IS 'reset on or more options on a columnar table to the system defaults';
-
--- rename columnar schema to columnar_internal and tighten security
-
-REVOKE ALL PRIVILEGES ON ALL TABLES IN SCHEMA columnar FROM PUBLIC;
-ALTER SCHEMA columnar RENAME TO columnar_internal;
-REVOKE ALL PRIVILEGES ON SCHEMA columnar_internal FROM PUBLIC;
-
--- create columnar schema with public usage privileges
-
-CREATE SCHEMA columnar;
-GRANT USAGE ON SCHEMA columnar TO PUBLIC;
-
---#include "udfs/upgrade_columnar_storage/10.2-1.sql"
-CREATE OR REPLACE FUNCTION columnar_internal.upgrade_columnar_storage(rel regclass)
-  RETURNS VOID
-  STRICT
-  LANGUAGE c AS 'MODULE_PATHNAME', $$upgrade_columnar_storage$$;
-
-COMMENT ON FUNCTION columnar_internal.upgrade_columnar_storage(regclass)
-  IS 'function to upgrade the columnar storage, if necessary';
-
-
---#include "udfs/downgrade_columnar_storage/10.2-1.sql"
-
-CREATE OR REPLACE FUNCTION columnar_internal.downgrade_columnar_storage(rel regclass)
-  RETURNS VOID
-  STRICT
-  LANGUAGE c AS 'MODULE_PATHNAME', $$downgrade_columnar_storage$$;
-
-COMMENT ON FUNCTION columnar_internal.downgrade_columnar_storage(regclass)
-  IS 'function to downgrade the columnar storage, if necessary';
-
--- update UDF to account for columnar_internal schema
-CREATE OR REPLACE FUNCTION columnar_internal.columnar_ensure_am_depends_catalog()
-  RETURNS void
-  LANGUAGE plpgsql
-  SET search_path = pg_catalog
-AS $func$
-BEGIN
-  INSERT INTO pg_depend
-  WITH columnar_schema_members(relid) AS (
-    SELECT pg_class.oid AS relid FROM pg_class
-      WHERE relnamespace =
-            COALESCE(
-	       (SELECT pg_namespace.oid FROM pg_namespace WHERE nspname = 'columnar_internal'),
-	       (SELECT pg_namespace.oid FROM pg_namespace WHERE nspname = 'columnar')
-	    )
-        AND relname IN ('chunk',
-                        'chunk_group',
-                        'chunk_group_pkey',
-                        'chunk_pkey',
-                        'options',
-                        'options_pkey',
-                        'storageid_seq',
-                        'stripe',
-                        'stripe_first_row_number_idx',
-                        'stripe_pkey')
-  )
-  SELECT -- Define a dependency edge from "columnar table access method" ..
-         'pg_am'::regclass::oid as classid,
-         (select oid from pg_am where amname = 'columnar') as objid,
-         0 as objsubid,
-         -- ... to each object that is registered to pg_class and that lives
-         -- in "columnar" schema. That contains catalog tables, indexes
-         -- created on them and the sequences created in "columnar" schema.
-         --
-         -- Given the possibility of user might have created their own objects
-         -- in columnar schema, we explicitly specify list of objects that we
-         -- are interested in.
-         'pg_class'::regclass::oid as refclassid,
-         columnar_schema_members.relid as refobjid,
-         0 as refobjsubid,
-         'n' as deptype
-  FROM columnar_schema_members
-  -- Avoid inserting duplicate entries into pg_depend.
-  EXCEPT TABLE pg_depend;
-END;
-$func$;
-COMMENT ON FUNCTION columnar_internal.columnar_ensure_am_depends_catalog()
-  IS 'internal function responsible for creating dependencies from columnar '
-     'table access method to the rel objects in columnar schema';
-
-SELECT columnar_internal.columnar_ensure_am_depends_catalog();
-
--- add utility function
-
-CREATE FUNCTION columnar.get_storage_id(regclass) RETURNS bigint
-    LANGUAGE C STRICT
-    AS 'citus_columnar', $$columnar_relation_storageid$$;
-
--- create views for columnar table information
-
-CREATE VIEW columnar.storage WITH (security_barrier) AS
-  SELECT c.oid::regclass AS relation,
-         columnar.get_storage_id(c.oid) AS storage_id
-    FROM pg_class c, pg_am am
-    WHERE c.relam = am.oid AND am.amname = 'columnar'
-      AND pg_has_role(c.relowner, 'USAGE');
-COMMENT ON VIEW columnar.storage IS 'Columnar relation ID to storage ID mapping.';
-GRANT SELECT ON columnar.storage TO PUBLIC;
-
-CREATE VIEW columnar.options WITH (security_barrier) AS
-  SELECT regclass AS relation, chunk_group_row_limit,
-         stripe_row_limit, compression, compression_level
-    FROM columnar_internal.options o, pg_class c
-    WHERE o.regclass = c.oid
-      AND pg_has_role(c.relowner, 'USAGE');
-COMMENT ON VIEW columnar.options
-  IS 'Columnar options for tables on which the current user has ownership privileges.';
-GRANT SELECT ON columnar.options TO PUBLIC;
-
-CREATE VIEW columnar.stripe WITH (security_barrier) AS
-  SELECT relation, storage.storage_id, stripe_num, file_offset, data_length,
-         column_count, chunk_row_count, row_count, chunk_group_count, first_row_number
-    FROM columnar_internal.stripe stripe, columnar.storage storage
-    WHERE stripe.storage_id = storage.storage_id;
-COMMENT ON VIEW columnar.stripe
-  IS 'Columnar stripe information for tables on which the current user has ownership privileges.';
-GRANT SELECT ON columnar.stripe TO PUBLIC;
-
-CREATE VIEW columnar.chunk_group WITH (security_barrier) AS
-  SELECT relation, storage.storage_id, stripe_num, chunk_group_num, row_count
-    FROM columnar_internal.chunk_group cg, columnar.storage storage
-    WHERE cg.storage_id = storage.storage_id;
-COMMENT ON VIEW columnar.chunk_group
-  IS 'Columnar chunk group information for tables on which the current user has ownership privileges.';
-GRANT SELECT ON columnar.chunk_group TO PUBLIC;
-
-CREATE VIEW columnar.chunk WITH (security_barrier) AS
-  SELECT relation, storage.storage_id, stripe_num, attr_num, chunk_group_num,
-         minimum_value, maximum_value, value_stream_offset, value_stream_length,
-         exists_stream_offset, exists_stream_length, value_compression_type,
-         value_compression_level, value_decompressed_length, value_count
-    FROM columnar_internal.chunk chunk, columnar.storage storage
-    WHERE chunk.storage_id = storage.storage_id;
-COMMENT ON VIEW columnar.chunk
-  IS 'Columnar chunk information for tables on which the current user has ownership privileges.';
-GRANT SELECT ON columnar.chunk TO PUBLIC;
-

src/backend/columnar/sql/citus_columnar--11.2-1--11.3-1.sql

@@ -1 +0,0 @@
--- citus_columnar--11.2-1--11.3-1

src/backend/columnar/sql/citus_columnar--11.3-1--12.2-1.sql

@@ -1 +0,0 @@
--- citus_columnar--11.3-1--12.2-1

src/backend/columnar/sql/columnar--10.1-1--10.2-1.sql

@@ -28,5 +28,5 @@ $$;
 #include "udfs/downgrade_columnar_storage/10.2-1.sql"
 
 -- upgrade storage for all columnar relations
-PERFORM citus_internal.upgrade_columnar_storage(c.oid) FROM pg_class c, pg_am a
+SELECT citus_internal.upgrade_columnar_storage(c.oid) FROM pg_class c, pg_am a
   WHERE c.relam = a.oid AND amname = 'columnar';

src/backend/columnar/sql/columnar--10.2-2--10.2-3.sql

@@ -10,17 +10,6 @@
 --
 -- To do that, drop stripe_first_row_number_idx and create a unique
 -- constraint with the same name to keep the code change at minimum.
---
--- If we have a pg_depend entry for this index, we can not drop it as
--- the extension depends on it. Remove the pg_depend entry if it exists.
-DELETE FROM pg_depend
-WHERE classid = 'pg_am'::regclass::oid
-    AND objid IN (select oid from pg_am where amname = 'columnar')
-    AND objsubid = 0
-    AND refclassid = 'pg_class'::regclass::oid
-    AND refobjid = 'columnar.stripe_first_row_number_idx'::regclass::oid
-    AND refobjsubid = 0
-    AND deptype = 'n';
 DROP INDEX columnar.stripe_first_row_number_idx;
 ALTER TABLE columnar.stripe ADD CONSTRAINT stripe_first_row_number_idx
 UNIQUE (storage_id, first_row_number);

src/backend/columnar/sql/columnar--10.2-3--10.2-4.sql

@@ -2,4 +2,4 @@
 
 #include "udfs/columnar_ensure_am_depends_catalog/10.2-4.sql"
 
-PERFORM citus_internal.columnar_ensure_am_depends_catalog();
+SELECT citus_internal.columnar_ensure_am_depends_catalog();

src/backend/columnar/sql/columnar--11.0-3--11.1-1.sql

@@ -1,71 +0,0 @@
-#include "udfs/alter_columnar_table_set/11.1-1.sql"
-#include "udfs/alter_columnar_table_reset/11.1-1.sql"
-
--- rename columnar schema to columnar_internal and tighten security
-
-REVOKE ALL PRIVILEGES ON ALL TABLES IN SCHEMA columnar FROM PUBLIC;
-ALTER SCHEMA columnar RENAME TO columnar_internal;
-REVOKE ALL PRIVILEGES ON SCHEMA columnar_internal FROM PUBLIC;
-
--- create columnar schema with public usage privileges
-
-CREATE SCHEMA columnar;
-GRANT USAGE ON SCHEMA columnar TO PUBLIC;
-
--- update UDF to account for columnar_internal schema
-#include "udfs/columnar_ensure_am_depends_catalog/11.1-1.sql"
-
--- add utility function
-
-CREATE FUNCTION columnar.get_storage_id(regclass) RETURNS bigint
-    LANGUAGE C STRICT
-    AS 'citus_columnar', $$columnar_relation_storageid$$;
-
--- create views for columnar table information
-
-CREATE VIEW columnar.storage WITH (security_barrier) AS
-  SELECT c.oid::regclass AS relation,
-         columnar.get_storage_id(c.oid) AS storage_id
-    FROM pg_class c, pg_am am
-    WHERE c.relam = am.oid AND am.amname = 'columnar'
-      AND pg_has_role(c.relowner, 'USAGE');
-COMMENT ON VIEW columnar.storage IS 'Columnar relation ID to storage ID mapping.';
-GRANT SELECT ON columnar.storage TO PUBLIC;
-
-CREATE VIEW columnar.options WITH (security_barrier) AS
-  SELECT regclass AS relation, chunk_group_row_limit,
-         stripe_row_limit, compression, compression_level
-    FROM columnar_internal.options o, pg_class c
-    WHERE o.regclass = c.oid
-      AND pg_has_role(c.relowner, 'USAGE');
-COMMENT ON VIEW columnar.options
-  IS 'Columnar options for tables on which the current user has ownership privileges.';
-GRANT SELECT ON columnar.options TO PUBLIC;
-
-CREATE VIEW columnar.stripe WITH (security_barrier) AS
-  SELECT relation, storage.storage_id, stripe_num, file_offset, data_length,
-         column_count, chunk_row_count, row_count, chunk_group_count, first_row_number
-    FROM columnar_internal.stripe stripe, columnar.storage storage
-    WHERE stripe.storage_id = storage.storage_id;
-COMMENT ON VIEW columnar.stripe
-  IS 'Columnar stripe information for tables on which the current user has ownership privileges.';
-GRANT SELECT ON columnar.stripe TO PUBLIC;
-
-CREATE VIEW columnar.chunk_group WITH (security_barrier) AS
-  SELECT relation, storage.storage_id, stripe_num, chunk_group_num, row_count
-    FROM columnar_internal.chunk_group cg, columnar.storage storage
-    WHERE cg.storage_id = storage.storage_id;
-COMMENT ON VIEW columnar.chunk_group
-  IS 'Columnar chunk group information for tables on which the current user has ownership privileges.';
-GRANT SELECT ON columnar.chunk_group TO PUBLIC;
-
-CREATE VIEW columnar.chunk WITH (security_barrier) AS
-  SELECT relation, storage.storage_id, stripe_num, attr_num, chunk_group_num,
-         minimum_value, maximum_value, value_stream_offset, value_stream_length,
-         exists_stream_offset, exists_stream_length, value_compression_type,
-         value_compression_level, value_decompressed_length, value_count
-    FROM columnar_internal.chunk chunk, columnar.storage storage
-    WHERE chunk.storage_id = storage.storage_id;
-COMMENT ON VIEW columnar.chunk
-  IS 'Columnar chunk information for tables on which the current user has ownership privileges.';
-GRANT SELECT ON columnar.chunk TO PUBLIC;

src/backend/columnar/sql/downgrades/citus_columnar--11.1-1--11.1-0.sql

@@ -1,116 +0,0 @@
-CREATE OR REPLACE FUNCTION pg_catalog.alter_columnar_table_set(
-    table_name regclass,
-    chunk_group_row_limit int DEFAULT NULL,
-    stripe_row_limit int DEFAULT NULL,
-    compression name DEFAULT null,
-    compression_level int DEFAULT NULL)
-    RETURNS void
-    LANGUAGE C
-AS 'MODULE_PATHNAME', 'alter_columnar_table_set';
-
-COMMENT ON FUNCTION pg_catalog.alter_columnar_table_set(
-    table_name regclass,
-    chunk_group_row_limit int,
-    stripe_row_limit int,
-    compression name,
-    compression_level int)
-IS 'set one or more options on a columnar table, when set to NULL no change is made';
-CREATE OR REPLACE FUNCTION pg_catalog.alter_columnar_table_reset(
-    table_name regclass,
-    chunk_group_row_limit bool DEFAULT false,
-    stripe_row_limit bool DEFAULT false,
-    compression bool DEFAULT false,
-    compression_level bool DEFAULT false)
-    RETURNS void
-    LANGUAGE C
-AS 'MODULE_PATHNAME', 'alter_columnar_table_reset';
-
-COMMENT ON FUNCTION pg_catalog.alter_columnar_table_reset(
-    table_name regclass,
-    chunk_group_row_limit bool,
-    stripe_row_limit bool,
-    compression bool,
-    compression_level bool)
-IS 'reset on or more options on a columnar table to the system defaults';
-
-CREATE OR REPLACE FUNCTION columnar_internal.columnar_ensure_am_depends_catalog()
-  RETURNS void
-  LANGUAGE plpgsql
-  SET search_path = pg_catalog
-AS $func$
-BEGIN
-  INSERT INTO pg_depend
-  SELECT -- Define a dependency edge from "columnar table access method" ..
-         'pg_am'::regclass::oid as classid,
-         (select oid from pg_am where amname = 'columnar') as objid,
-         0 as objsubid,
-         -- ... to each object that is registered to pg_class and that lives
-         -- in "columnar" schema. That contains catalog tables, indexes
-         -- created on them and the sequences created in "columnar" schema.
-         --
-         -- Given the possibility of user might have created their own objects
-         -- in columnar schema, we explicitly specify list of objects that we
-         -- are interested in.
-         'pg_class'::regclass::oid as refclassid,
-         columnar_schema_members.relname::regclass::oid as refobjid,
-         0 as refobjsubid,
-         'n' as deptype
-  FROM (VALUES ('columnar.chunk'),
-               ('columnar.chunk_group'),
-               ('columnar.chunk_group_pkey'),
-               ('columnar.chunk_pkey'),
-               ('columnar.options'),
-               ('columnar.options_pkey'),
-               ('columnar.storageid_seq'),
-               ('columnar.stripe'),
-               ('columnar.stripe_first_row_number_idx'),
-               ('columnar.stripe_pkey')
-       ) columnar_schema_members(relname)
-  -- Avoid inserting duplicate entries into pg_depend.
-  EXCEPT TABLE pg_depend;
-END;
-$func$;
-COMMENT ON FUNCTION columnar_internal.columnar_ensure_am_depends_catalog()
-  IS 'internal function responsible for creating dependencies from columnar '
-     'table access method to the rel objects in columnar schema';
-
-DROP VIEW columnar.options;
-DROP VIEW columnar.stripe;
-DROP VIEW columnar.chunk_group;
-DROP VIEW columnar.chunk;
-DROP VIEW columnar.storage;
-DROP FUNCTION columnar.get_storage_id(regclass);
-
-DROP SCHEMA columnar;
-
--- move columnar_internal functions back to citus_internal
-
-ALTER FUNCTION columnar_internal.upgrade_columnar_storage(regclass) SET SCHEMA citus_internal;
-ALTER FUNCTION columnar_internal.downgrade_columnar_storage(regclass) SET SCHEMA citus_internal;
-ALTER FUNCTION columnar_internal.columnar_ensure_am_depends_catalog() SET SCHEMA citus_internal;
-
-ALTER SCHEMA columnar_internal RENAME TO columnar;
-GRANT USAGE ON SCHEMA columnar TO PUBLIC;
-GRANT SELECT ON columnar.options TO PUBLIC;
-GRANT SELECT ON columnar.stripe TO PUBLIC;
-GRANT SELECT ON columnar.chunk_group TO PUBLIC;
-
--- detach relations from citus_columnar
-
-ALTER EXTENSION citus_columnar DROP SCHEMA columnar;
-ALTER EXTENSION citus_columnar DROP SEQUENCE columnar.storageid_seq;
--- columnar tables
-ALTER EXTENSION citus_columnar DROP TABLE columnar.options;
-ALTER EXTENSION citus_columnar DROP TABLE columnar.stripe;
-ALTER EXTENSION citus_columnar DROP TABLE columnar.chunk_group;
-ALTER EXTENSION citus_columnar DROP TABLE columnar.chunk;
-
-ALTER EXTENSION citus_columnar DROP FUNCTION columnar.columnar_handler;
-ALTER EXTENSION citus_columnar DROP ACCESS METHOD columnar;
-ALTER EXTENSION citus_columnar DROP FUNCTION pg_catalog.alter_columnar_table_set;
-ALTER EXTENSION citus_columnar DROP FUNCTION pg_catalog.alter_columnar_table_reset;
-
--- functions under citus_internal for columnar
-ALTER EXTENSION citus_columnar DROP FUNCTION citus_internal.upgrade_columnar_storage;
-ALTER EXTENSION citus_columnar DROP FUNCTION citus_internal.downgrade_columnar_storage;
-ALTER EXTENSION citus_columnar DROP FUNCTION citus_internal.columnar_ensure_am_depends_catalog;

src/backend/columnar/sql/downgrades/citus_columnar--11.2-1--11.1-1.sql

@@ -1,4 +0,0 @@
--- citus_columnar--11.2-1--11.1-1
-
--- Note that we intentionally do not re-insert the pg_depend records that we
--- deleted via citus_columnar--11.1-1--11.2-1.sql.

src/backend/columnar/sql/downgrades/citus_columnar--11.3-1--11.2-1.sql

@@ -1 +0,0 @@
--- citus_columnar--11.3-1--11.2-1

src/backend/columnar/sql/downgrades/citus_columnar--12.2-1--11.3-1.sql

@@ -1 +0,0 @@
--- citus_columnar--12.2-1--11.3-1

src/backend/columnar/sql/downgrades/columnar--10.2-1--10.1-1.sql

@@ -8,16 +8,5 @@ DROP FUNCTION citus_internal.upgrade_columnar_storage(regclass);
 DROP FUNCTION citus_internal.downgrade_columnar_storage(regclass);
 
 -- drop "first_row_number" column and the index defined on it
---
--- If we have a pg_depend entry for this index, we can not drop it as
--- the extension depends on it. Remove the pg_depend entry if it exists.
-DELETE FROM pg_depend
-WHERE classid = 'pg_am'::regclass::oid
-    AND objid IN (select oid from pg_am where amname = 'columnar')
-    AND objsubid = 0
-    AND refclassid = 'pg_class'::regclass::oid
-    AND refobjid = 'columnar.stripe_first_row_number_idx'::regclass::oid
-    AND refobjsubid = 0
-    AND deptype = 'n';
 DROP INDEX columnar.stripe_first_row_number_idx;
 ALTER TABLE columnar.stripe DROP COLUMN first_row_number;

src/backend/columnar/sql/downgrades/columnar--10.2-3--10.2-2.sql

@@ -1,14 +1,4 @@
 -- columnar--10.2-3--10.2-2.sql
---
--- If we have a pg_depend entry for this index, we can not drop it as
--- the extension depends on it. Remove the pg_depend entry if it exists.
-DELETE FROM pg_depend
-WHERE classid = 'pg_am'::regclass::oid
-    AND objid IN (select oid from pg_am where amname = 'columnar')
-    AND objsubid = 0
-    AND refclassid = 'pg_class'::regclass::oid
-    AND refobjid = 'columnar.stripe_first_row_number_idx'::regclass::oid
-    AND refobjsubid = 0
-    AND deptype = 'n';
+
 ALTER TABLE columnar.stripe DROP CONSTRAINT stripe_first_row_number_idx;
 CREATE INDEX stripe_first_row_number_idx ON columnar.stripe USING BTREE(storage_id, first_row_number);