code reading notes from last weekend

.dockerignore

@@ -24,4 +24,3 @@
 !storage_controller/
 !vendor/postgres-*/
 !workspace_hack/
-!build_tools/patches

.github/ISSUE_TEMPLATE/bug-template.md

@@ -3,7 +3,6 @@ name: Bug Template
 about: Used for describing bugs
 title: ''
 labels: t/bug
-type: Bug
 assignees: ''
 
 ---

.github/ISSUE_TEMPLATE/epic-template.md

@@ -4,7 +4,6 @@ about: A set of related tasks contributing towards specific outcome, comprising
   more than 1 week of work.
 title: 'Epic: '
 labels: t/Epic
-type: Epic
 assignees: ''
 
 ---

.github/actionlint.yml

@@ -4,7 +4,6 @@ self-hosted-runner:
     - large
     - large-arm64
     - small
-    - small-metal
     - small-arm64
     - us-east-2
 config-variables:
@@ -26,5 +25,3 @@ config-variables:
   - PGREGRESS_PG17_PROJECT_ID
   - SLACK_ON_CALL_QA_STAGING_STREAM
   - DEV_AWS_OIDC_ROLE_MANAGE_BENCHMARK_EC2_VMS_ARN
-  - SLACK_ON_CALL_STORAGE_STAGING_STREAM
-  - SLACK_CICD_CHANNEL_ID

.github/actions/neon-project-create/action.yml

@@ -17,34 +17,6 @@ inputs:
   compute_units:
     description: '[Min, Max] compute units'
     default: '[1, 1]'
-  # settings below only needed if you want the project to be sharded from the beginning
-  shard_split_project:
-    description: 'by default new projects are not shard-split, specify true to shard-split'
-    required: false
-    default: 'false'
-  admin_api_key:
-    description: 'Admin API Key needed for shard-splitting. Must be specified if shard_split_project is true'
-    required: false
-  shard_count:
-    description: 'Number of shards to split the project into, only applies if shard_split_project is true'
-    required: false
-    default: '8'
-  stripe_size:
-    description: 'Stripe size, optional, in 8kiB pages.  e.g. set 2048 for 16MB stripes. Default is 128 MiB, only applies if shard_split_project is true'
-    required: false
-    default: '32768'
-  psql_path:
-    description: 'Path to psql binary - it is caller responsibility to provision the psql binary'
-    required: false
-    default: '/tmp/neon/pg_install/v16/bin/psql'
-  libpq_lib_path:
-    description: 'Path to directory containing libpq library - it is caller responsibility to provision the libpq library'
-    required: false
-    default: '/tmp/neon/pg_install/v16/lib'
-  project_settings:
-    description: 'A JSON object with project settings'
-    required: false
-    default: '{}'
 
 outputs:
   dsn:
@@ -76,7 +48,7 @@ runs:
               \"provisioner\": \"k8s-neonvm\",
               \"autoscaling_limit_min_cu\": ${MIN_CU},
               \"autoscaling_limit_max_cu\": ${MAX_CU},
-              \"settings\": ${PROJECT_SETTINGS}
+              \"settings\": { }
             }
           }")
 
@@ -91,23 +63,6 @@ runs:
         echo "project_id=${project_id}" >> $GITHUB_OUTPUT
 
         echo "Project ${project_id} has been created"
-
-        if [ "${SHARD_SPLIT_PROJECT}" = "true" ]; then
-          # determine tenant ID
-          TENANT_ID=`${PSQL} ${dsn} -t -A -c "SHOW neon.tenant_id"`
-
-          echo "Splitting project ${project_id} with tenant_id ${TENANT_ID} into $((SHARD_COUNT)) shards with stripe size $((STRIPE_SIZE))"
-
-          echo "Sending PUT request to https://${API_HOST}/regions/${REGION_ID}/api/v1/admin/storage/proxy/control/v1/tenant/${TENANT_ID}/shard_split"
-          echo "with body {\"new_shard_count\": $((SHARD_COUNT)), \"new_stripe_size\": $((STRIPE_SIZE))}"
-
-          # we need an ADMIN API KEY to invoke storage controller API for shard splitting (bash -u above checks that the variable is set)
-          curl -X PUT \
-            "https://${API_HOST}/regions/${REGION_ID}/api/v1/admin/storage/proxy/control/v1/tenant/${TENANT_ID}/shard_split" \
-            -H "Accept: application/json" -H "Content-Type: application/json" -H "Authorization: Bearer ${ADMIN_API_KEY}" \
-            -d "{\"new_shard_count\": $SHARD_COUNT, \"new_stripe_size\": $STRIPE_SIZE}"
-        fi
-
       env:
         API_HOST: ${{ inputs.api_host }}
         API_KEY: ${{ inputs.api_key }}
@@ -115,10 +70,3 @@ runs:
         POSTGRES_VERSION: ${{ inputs.postgres_version }}
         MIN_CU: ${{ fromJSON(inputs.compute_units)[0] }}
         MAX_CU: ${{ fromJSON(inputs.compute_units)[1] }}
-        SHARD_SPLIT_PROJECT: ${{ inputs.shard_split_project }}
-        ADMIN_API_KEY: ${{ inputs.admin_api_key }}
-        SHARD_COUNT: ${{ inputs.shard_count }}
-        STRIPE_SIZE: ${{ inputs.stripe_size }}
-        PSQL: ${{ inputs.psql_path }}
-        LD_LIBRARY_PATH: ${{ inputs.libpq_lib_path }}
-        PROJECT_SETTINGS: ${{ inputs.project_settings }}

.github/actions/run-python-test-set/action.yml

@@ -121,8 +121,6 @@ runs:
         export DEFAULT_PG_VERSION=${PG_VERSION#v}
         export LD_LIBRARY_PATH=${POSTGRES_DISTRIB_DIR}/v${DEFAULT_PG_VERSION}/lib
         export BENCHMARK_CONNSTR=${BENCHMARK_CONNSTR:-}
-        export ASAN_OPTIONS=detect_leaks=0:detect_stack_use_after_return=0:abort_on_error=1:strict_string_checks=1:check_initialization_order=1:strict_init_order=1
-        export UBSAN_OPTIONS=abort_on_error=1:print_stacktrace=1
 
         if [ "${BUILD_TYPE}" = "remote" ]; then
           export REMOTE_ENV=1

.github/file-filters.yaml

@@ -1,5 +1,4 @@
 rust_code: ['**/*.rs', '**/Cargo.toml', '**/Cargo.lock']
-rust_dependencies: ['**/Cargo.lock']
 
 v14: ['vendor/postgres-v14/**', 'Makefile', 'pgxn/**']
 v15: ['vendor/postgres-v15/**', 'Makefile', 'pgxn/**']

.github/workflows/_benchmarking_preparation.yml

@@ -17,7 +17,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        platform: [ aws-rds-postgres, aws-aurora-serverless-v2-postgres, neon, neon_pg17 ]
+        platform: [ aws-rds-postgres, aws-aurora-serverless-v2-postgres, neon ]
         database: [ clickbench, tpch, userexample ]
 
     env:
@@ -41,9 +41,6 @@ jobs:
           neon)
             CONNSTR=${{ secrets.BENCHMARK_CAPTEST_CONNSTR }}
             ;;
-          neon_pg17)
-            CONNSTR=${{ secrets.BENCHMARK_CAPTEST_CONNSTR_PG17 }}
-            ;;
           aws-rds-postgres)
             CONNSTR=${{ secrets.BENCHMARK_RDS_POSTGRES_CONNSTR }}
             ;;

.github/workflows/_build-and-test-locally.yml

@@ -23,11 +23,6 @@ on:
         description: 'a json object of postgres versions and lfc states to run regression tests on'
         required: true
         type: string
-      sanitizers:
-        description: 'enabled or disabled'
-        required: false
-        default: 'disabled'
-        type: string
 
 defaults:
   run:
@@ -92,7 +87,6 @@ jobs:
       - name: Set env variables
         env:
           ARCH: ${{ inputs.arch }}
-          SANITIZERS: ${{ inputs.sanitizers }}
         run: |
           CARGO_FEATURES="--features testing"
           if [[ $BUILD_TYPE == "debug" && $ARCH == 'x64' ]]; then
@@ -105,14 +99,8 @@ jobs:
             cov_prefix=""
             CARGO_FLAGS="--locked --release"
           fi
-          if [[ $SANITIZERS == 'enabled' ]]; then
-            make_vars="WITH_SANITIZERS=yes"
-          else
-            make_vars=""
-          fi
           {
             echo "cov_prefix=${cov_prefix}"
-            echo "make_vars=${make_vars}"
             echo "CARGO_FEATURES=${CARGO_FEATURES}"
             echo "CARGO_FLAGS=${CARGO_FLAGS}"
             echo "CARGO_HOME=${GITHUB_WORKSPACE}/.cargo"
@@ -148,39 +136,37 @@ jobs:
 
       - name: Build postgres v14
         if: steps.cache_pg_14.outputs.cache-hit != 'true'
-        run: mold -run make ${make_vars} postgres-v14 -j$(nproc)
+        run: mold -run make postgres-v14 -j$(nproc)
 
       - name: Build postgres v15
         if: steps.cache_pg_15.outputs.cache-hit != 'true'
-        run: mold -run make ${make_vars} postgres-v15 -j$(nproc)
+        run: mold -run make postgres-v15 -j$(nproc)
 
       - name: Build postgres v16
         if: steps.cache_pg_16.outputs.cache-hit != 'true'
-        run: mold -run make ${make_vars} postgres-v16 -j$(nproc)
+        run: mold -run make postgres-v16 -j$(nproc)
 
       - name: Build postgres v17
         if: steps.cache_pg_17.outputs.cache-hit != 'true'
-        run: mold -run make ${make_vars} postgres-v17 -j$(nproc)
+        run: mold -run make postgres-v17 -j$(nproc)
 
       - name: Build neon extensions
-        run: mold -run make ${make_vars} neon-pg-ext -j$(nproc)
+        run: mold -run make neon-pg-ext -j$(nproc)
 
       - name: Build walproposer-lib
-        run: mold -run make ${make_vars} walproposer-lib -j$(nproc)
+        run: mold -run make walproposer-lib -j$(nproc)
 
       - name: Run cargo build
-        env:
-          WITH_TESTS: ${{ inputs.sanitizers != 'enabled' && '--tests' || '' }}
         run: |
-          export ASAN_OPTIONS=detect_leaks=0
-          ${cov_prefix} mold -run cargo build $CARGO_FLAGS $CARGO_FEATURES --bins ${WITH_TESTS}
+          PQ_LIB_DIR=$(pwd)/pg_install/v16/lib
+          export PQ_LIB_DIR
+          ${cov_prefix} mold -run cargo build $CARGO_FLAGS $CARGO_FEATURES --bins --tests
 
       # Do install *before* running rust tests because they might recompile the
       # binaries with different features/flags.
       - name: Install rust binaries
         env:
           ARCH: ${{ inputs.arch }}
-          SANITIZERS: ${{ inputs.sanitizers }}
         run: |
           # Install target binaries
           mkdir -p /tmp/neon/bin/
@@ -195,7 +181,7 @@ jobs:
           done
 
           # Install test executables and write list of all binaries (for code coverage)
-          if [[ $BUILD_TYPE == "debug" && $ARCH == 'x64' && $SANITIZERS != 'enabled' ]]; then
+          if [[ $BUILD_TYPE == "debug" && $ARCH == 'x64' ]]; then
             # Keep bloated coverage data files away from the rest of the artifact
             mkdir -p /tmp/coverage/
 
@@ -228,10 +214,11 @@ jobs:
           role-duration-seconds: 18000 # 5 hours
 
       - name: Run rust tests
-        if: ${{ inputs.sanitizers != 'enabled' }}
         env:
           NEXTEST_RETRIES: 3
         run: |
+          PQ_LIB_DIR=$(pwd)/pg_install/v16/lib
+          export PQ_LIB_DIR
           LD_LIBRARY_PATH=$(pwd)/pg_install/v17/lib
           export LD_LIBRARY_PATH
 
@@ -242,13 +229,8 @@ jobs:
           ${cov_prefix} cargo nextest run $CARGO_FLAGS $CARGO_FEATURES -E '!package(pageserver)'
 
           # run pageserver tests with different settings
-          for get_vectored_concurrent_io in sequential sidecar-task; do
-            for io_engine in std-fs tokio-epoll-uring ; do
-              NEON_PAGESERVER_UNIT_TEST_GET_VECTORED_CONCURRENT_IO=$get_vectored_concurrent_io \
-                NEON_PAGESERVER_UNIT_TEST_VIRTUAL_FILE_IOENGINE=$io_engine \
-                ${cov_prefix} \
-                cargo nextest run $CARGO_FLAGS $CARGO_FEATURES  -E 'package(pageserver)'
-            done
+          for io_engine in std-fs tokio-epoll-uring ; do
+            NEON_PAGESERVER_UNIT_TEST_VIRTUAL_FILE_IOENGINE=$io_engine ${cov_prefix} cargo nextest run $CARGO_FLAGS $CARGO_FEATURES  -E 'package(pageserver)'
           done
 
           # Run separate tests for real S3
@@ -284,27 +266,6 @@ jobs:
           path: /tmp/neon
           aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
-      - name: Check diesel schema
-        if: inputs.build-type == 'release' && inputs.arch == 'x64'
-        env:
-          DATABASE_URL: postgresql://localhost:1235/storage_controller
-          POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
-        run: |
-          export ASAN_OPTIONS=detect_leaks=0
-          /tmp/neon/bin/neon_local init
-          /tmp/neon/bin/neon_local storage_controller start
-
-          diesel print-schema > storage_controller/src/schema.rs
-
-          if [ -n "$(git diff storage_controller/src/schema.rs)" ]; then
-            echo >&2 "Uncommitted changes in diesel schema"
-
-            git diff .
-            exit 1
-          fi
-
-          /tmp/neon/bin/neon_local storage_controller stop
-
       # XXX: keep this after the binaries.list is formed, so the coverage can properly work later
       - name: Merge and upload coverage data
         if: inputs.build-type == 'debug'
@@ -337,7 +298,7 @@ jobs:
       - name: Pytest regression tests
         continue-on-error: ${{ matrix.lfc_state == 'with-lfc' && inputs.build-type == 'debug' }}
         uses: ./.github/actions/run-python-test-set
-        timeout-minutes: ${{ inputs.sanitizers != 'enabled' && 60 || 180 }}
+        timeout-minutes: 60
         with:
           build_type: ${{ inputs.build-type }}
           test_selection: regress
@@ -353,9 +314,7 @@ jobs:
           CHECK_ONDISK_DATA_COMPATIBILITY: nonempty
           BUILD_TAG: ${{ inputs.build-tag }}
           PAGESERVER_VIRTUAL_FILE_IO_ENGINE: tokio-epoll-uring
-          PAGESERVER_GET_VECTORED_CONCURRENT_IO: sidecar-task
           USE_LFC: ${{ matrix.lfc_state == 'with-lfc' && 'true' || 'false' }}
-          SANITIZERS: ${{ inputs.sanitizers }}
 
       # Temporary disable this step until we figure out why it's so flaky
       # Ref https://github.com/neondatabase/neon/issues/4540

.github/workflows/_check-codestyle-rust.yml

@@ -1,89 +0,0 @@
-name: Check Codestyle Rust
-
-on:
-  workflow_call:
-    inputs:
-      build-tools-image:
-        description: "build-tools image"
-        required: true
-        type: string
-      archs:
-        description: "Json array of architectures to run on"
-        type: string
-
-
-defaults:
-  run:
-    shell: bash -euxo pipefail {0}
-
-# No permission for GITHUB_TOKEN by default; the **minimal required** set of permissions should be granted in each job.
-permissions: {}
-
-jobs:
-  check-codestyle-rust:
-    strategy:
-      matrix:
-        arch: ${{ fromJson(inputs.archs) }}
-    runs-on: ${{ fromJson(format('["self-hosted", "{0}"]', matrix.arch == 'arm64' && 'small-arm64' || 'small')) }}
-
-    container:
-      image: ${{ inputs.build-tools-image }}
-      credentials:
-        username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
-        password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
-      options: --init
-
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-        with:
-          submodules: true
-
-      - name: Cache cargo deps
-        uses: actions/cache@v4
-        with:
-          path: |
-            ~/.cargo/registry
-            !~/.cargo/registry/src
-            ~/.cargo/git
-            target
-          key: v1-${{ runner.os }}-${{ runner.arch }}-cargo-${{ hashFiles('./Cargo.lock') }}-${{ hashFiles('./rust-toolchain.toml') }}-rust
-
-      # Some of our rust modules use FFI and need those to be checked
-      - name: Get postgres headers
-        run: make postgres-headers -j$(nproc)
-
-      # cargo hack runs the given cargo subcommand (clippy in this case) for all feature combinations.
-      # This will catch compiler & clippy warnings in all feature combinations.
-      # TODO: use cargo hack for build and test as well, but, that's quite expensive.
-      # NB: keep clippy args in sync with ./run_clippy.sh
-      #
-      # The only difference between "clippy --debug" and "clippy --release" is that in --release mode,
-      # #[cfg(debug_assertions)] blocks are not built. It's not worth building everything for second
-      # time just for that, so skip "clippy --release".
-      - run: |
-          CLIPPY_COMMON_ARGS="$( source .neon_clippy_args; echo "$CLIPPY_COMMON_ARGS")"
-          if [ "$CLIPPY_COMMON_ARGS" = "" ]; then
-            echo "No clippy args found in .neon_clippy_args"
-            exit 1
-          fi
-          echo "CLIPPY_COMMON_ARGS=${CLIPPY_COMMON_ARGS}" >> $GITHUB_ENV
-      - name: Run cargo clippy (debug)
-        run: cargo hack --features default --ignore-unknown-features --feature-powerset clippy $CLIPPY_COMMON_ARGS
-
-      - name: Check documentation generation
-        run: cargo doc --workspace --no-deps --document-private-items
-        env:
-          RUSTDOCFLAGS: "-Dwarnings -Arustdoc::private_intra_doc_links"
-
-      # Use `${{ !cancelled() }}` to run quck tests after the longer clippy run
-      - name: Check formatting
-        if: ${{ !cancelled() }}
-        run: cargo fmt --all -- --check
-
-      # https://github.com/facebookincubator/cargo-guppy/tree/bec4e0eb29dcd1faac70b1b5360267fc02bf830e/tools/cargo-hakari#2-keep-the-workspace-hack-up-to-date-in-ci
-      - name: Check rust dependencies
-        if: ${{ !cancelled() }}
-        run: |
-          cargo hakari generate --diff  # workspace-hack Cargo.toml is up-to-date
-          cargo hakari manage-deps --dry-run  # all workspace crates depend on workspace-hack

.github/workflows/approved-for-ci-run.yml

@@ -67,9 +67,9 @@ jobs:
 
       - uses: actions/checkout@v4
         with:
-          ref: ${{ github.event.pull_request.head.sha }}
+          ref: main
           token: ${{ secrets.CI_ACCESS_TOKEN }}
-
+      
       - name: Look for existing PR
         id: get-pr
         env:
@@ -77,7 +77,7 @@ jobs:
         run: |
           ALREADY_CREATED="$(gh pr --repo ${GITHUB_REPOSITORY} list --head ${BRANCH} --base main --json number --jq '.[].number')"
           echo "ALREADY_CREATED=${ALREADY_CREATED}" >> ${GITHUB_OUTPUT}
-
+      
       - name: Get changed labels
         id: get-labels
         if: steps.get-pr.outputs.ALREADY_CREATED != ''
@@ -94,6 +94,8 @@ jobs:
           echo "LABELS_TO_ADD=${LABELS_TO_ADD}" >> ${GITHUB_OUTPUT}
           echo "LABELS_TO_REMOVE=${LABELS_TO_REMOVE}" >> ${GITHUB_OUTPUT}
 
+      - run: gh pr checkout "${PR_NUMBER}"
+
       - run: git checkout -b "${BRANCH}"
 
       - run: git push --force origin "${BRANCH}"
@@ -101,7 +103,7 @@ jobs:
 
       - name: Create a Pull Request for CI run (if required)
         if: steps.get-pr.outputs.ALREADY_CREATED == ''
-        env:
+        env: 
           GH_TOKEN: ${{ secrets.CI_ACCESS_TOKEN }}
         run: |
           cat << EOF > body.md
@@ -138,7 +140,7 @@ jobs:
 
       - run: git push --force origin "${BRANCH}"
         if: steps.get-pr.outputs.ALREADY_CREATED != ''
-
+             
   cleanup:
     # Close PRs and delete branchs if the original PR is closed.
 

.github/workflows/benchmarking.yml

@@ -63,15 +63,11 @@ jobs:
       fail-fast: false
       matrix:
         include:
-          - PG_VERSION: 16
+          - DEFAULT_PG_VERSION: 16
             PLATFORM: "neon-staging"
             region_id: ${{ github.event.inputs.region_id || 'aws-us-east-2' }}
             RUNNER: [ self-hosted, us-east-2, x64 ]
-          - PG_VERSION: 17
-            PLATFORM: "neon-staging"
-            region_id: ${{ github.event.inputs.region_id || 'aws-us-east-2' }}
-            RUNNER: [ self-hosted, us-east-2, x64 ]
-          - PG_VERSION: 16
+          - DEFAULT_PG_VERSION: 16
             PLATFORM: "azure-staging"
             region_id: 'azure-eastus2'
             RUNNER: [ self-hosted, eastus2, x64 ]
@@ -79,7 +75,7 @@ jobs:
       TEST_PG_BENCH_DURATIONS_MATRIX: "300"
       TEST_PG_BENCH_SCALES_MATRIX: "10,100"
       POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
-      PG_VERSION: ${{ matrix.PG_VERSION }}
+      DEFAULT_PG_VERSION: ${{ matrix.DEFAULT_PG_VERSION }}
       TEST_OUTPUT: /tmp/test_output
       BUILD_TYPE: remote
       SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref_name == 'main' ) }}
@@ -116,7 +112,7 @@ jobs:
       uses: ./.github/actions/neon-project-create
       with:
         region_id: ${{ matrix.region_id }}
-        postgres_version: ${{ env.PG_VERSION }}
+        postgres_version: ${{ env.DEFAULT_PG_VERSION }}
         api_key: ${{ secrets.NEON_STAGING_API_KEY }}
 
     - name: Run benchmark
@@ -126,7 +122,7 @@ jobs:
         test_selection: performance
         run_in_parallel: false
         save_perf_report: ${{ env.SAVE_PERF_REPORT }}
-        pg_version: ${{ env.PG_VERSION }}
+        pg_version: ${{ env.DEFAULT_PG_VERSION }}
         aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
         # Set --sparse-ordering option of pytest-order plugin
         # to ensure tests are running in order of appears in the file.
@@ -317,11 +313,7 @@ jobs:
                       { "pg_version": 16, "region_id": "azure-eastus2",          "platform": "neonvm-azure-captest-freetier", "db_size": "3gb" ,"runner": '"$runner_azure"',   "image": "neondatabase/build-tools:pinned-bookworm" },
                       { "pg_version": 16, "region_id": "azure-eastus2",          "platform": "neonvm-azure-captest-new",      "db_size": "10gb","runner": '"$runner_azure"',   "image": "neondatabase/build-tools:pinned-bookworm" },
                       { "pg_version": 16, "region_id": "azure-eastus2",          "platform": "neonvm-azure-captest-new",      "db_size": "50gb","runner": '"$runner_azure"',   "image": "neondatabase/build-tools:pinned-bookworm" },
-                      { "pg_version": 16, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-sharding-reuse", "db_size": "50gb","runner": '"$runner_default"', "image": "'"$image_default"'" },
-                      { "pg_version": 17, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-freetier",       "db_size": "3gb" ,"runner": '"$runner_default"', "image": "'"$image_default"'" },
-                      { "pg_version": 17, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-new",            "db_size": "10gb","runner": '"$runner_default"', "image": "'"$image_default"'" },
-                      { "pg_version": 17, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-new-many-tables","db_size": "10gb","runner": '"$runner_default"', "image": "'"$image_default"'" },
-                      { "pg_version": 17, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-new",            "db_size": "50gb","runner": '"$runner_default"', "image": "'"$image_default"'" }]
+                      { "pg_version": 16, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-sharding-reuse", "db_size": "50gb","runner": '"$runner_default"', "image": "'"$image_default"'" }]
         }'
 
         if [ "$(date +%A)" = "Saturday" ] || [ ${RUN_AWS_RDS_AND_AURORA} = "true" ]; then
@@ -337,15 +329,12 @@ jobs:
         matrix='{
           "platform": [
             "neonvm-captest-reuse"
-          ],
-          "pg_version" : [
-            16,17
           ]
         }'
 
         if [ "$(date +%A)" = "Saturday" ] || [ ${RUN_AWS_RDS_AND_AURORA} = "true" ]; then
-          matrix=$(echo "$matrix" | jq '.include += [{ "pg_version": 16, "platform": "rds-postgres" },
-                                                     { "pg_version": 16, "platform": "rds-aurora"   }]')
+          matrix=$(echo "$matrix" | jq '.include += [{ "platform": "rds-postgres" },
+                                                     { "platform": "rds-aurora"   }]')
         fi
 
         echo "matrix=$(echo "$matrix" | jq --compact-output '.')" >> $GITHUB_OUTPUT
@@ -357,14 +346,14 @@ jobs:
           "platform": [
             "neonvm-captest-reuse"
           ],
-          "pg_version" : [
-            16,17
+          "scale": [
+            "10"
           ]
         }'
 
         if [ "$(date +%A)" = "Saturday" ] || [ ${RUN_AWS_RDS_AND_AURORA} = "true" ]; then
-          matrix=$(echo "$matrix" | jq '.include += [{ "pg_version": 16, "platform": "rds-postgres" },
-                                                     { "pg_version": 16, "platform": "rds-aurora"   }]')
+          matrix=$(echo "$matrix" | jq '.include += [{ "platform": "rds-postgres", "scale": "10" },
+                                                     { "platform": "rds-aurora",   "scale": "10" }]')
         fi
 
         echo "matrix=$(echo "$matrix" | jq --compact-output '.')" >> $GITHUB_OUTPUT
@@ -389,7 +378,7 @@ jobs:
       TEST_PG_BENCH_DURATIONS_MATRIX: "60m"
       TEST_PG_BENCH_SCALES_MATRIX: ${{ matrix.db_size }}
       POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
-      PG_VERSION: ${{ matrix.pg_version }}
+      DEFAULT_PG_VERSION: ${{ matrix.pg_version }}
       TEST_OUTPUT: /tmp/test_output
       BUILD_TYPE: remote
       SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref_name == 'main' ) }}
@@ -427,7 +416,7 @@ jobs:
       uses: ./.github/actions/neon-project-create
       with:
         region_id: ${{ matrix.region_id }}
-        postgres_version: ${{ env.PG_VERSION }}
+        postgres_version: ${{ env.DEFAULT_PG_VERSION }}
         api_key: ${{ secrets.NEON_STAGING_API_KEY }}
         compute_units: ${{ (contains(matrix.platform, 'captest-freetier') && '[0.25, 0.25]') || '[1, 1]' }}
 
@@ -458,7 +447,7 @@ jobs:
 
         echo "connstr=${CONNSTR}" >> $GITHUB_OUTPUT
 
-    # we want to compare Neon project OLTP throughput and latency at scale factor 10 GB
+    # we want to compare Neon project OLTP throughput and latency at scale factor 10 GB 
     # without (neonvm-captest-new)
     # and with (neonvm-captest-new-many-tables) many relations in the database
     - name: Create many relations before the run
@@ -470,7 +459,7 @@ jobs:
         run_in_parallel: false
         save_perf_report: ${{ env.SAVE_PERF_REPORT }}
         extra_params: -m remote_cluster --timeout 21600 -k test_perf_many_relations
-        pg_version: ${{ env.PG_VERSION }}
+        pg_version: ${{ env.DEFAULT_PG_VERSION }}
         aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
       env:
         BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
@@ -486,7 +475,7 @@ jobs:
         run_in_parallel: false
         save_perf_report: ${{ env.SAVE_PERF_REPORT }}
         extra_params: -m remote_cluster --timeout 21600 -k test_pgbench_remote_init
-        pg_version: ${{ env.PG_VERSION }}
+        pg_version: ${{ env.DEFAULT_PG_VERSION }}
         aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
       env:
         BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
@@ -501,7 +490,7 @@ jobs:
         run_in_parallel: false
         save_perf_report: ${{ env.SAVE_PERF_REPORT }}
         extra_params: -m remote_cluster --timeout 21600 -k test_pgbench_remote_simple_update
-        pg_version: ${{ env.PG_VERSION }}
+        pg_version: ${{ env.DEFAULT_PG_VERSION }}
         aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
       env:
         BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
@@ -516,7 +505,7 @@ jobs:
         run_in_parallel: false
         save_perf_report: ${{ env.SAVE_PERF_REPORT }}
         extra_params: -m remote_cluster --timeout 21600 -k test_pgbench_remote_select_only
-        pg_version: ${{ env.PG_VERSION }}
+        pg_version: ${{ env.DEFAULT_PG_VERSION }}
         aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
       env:
         BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
@@ -560,19 +549,14 @@ jobs:
         include:
           - PLATFORM: "neonvm-captest-pgvector"
             RUNNER: [ self-hosted, us-east-2, x64 ]
-            postgres_version: 16
-          - PLATFORM: "neonvm-captest-pgvector-pg17"
-            RUNNER: [ self-hosted, us-east-2, x64 ]
-            postgres_version: 17
           - PLATFORM: "azure-captest-pgvector"
             RUNNER: [ self-hosted, eastus2, x64 ]
-            postgres_version: 16
 
     env:
       TEST_PG_BENCH_DURATIONS_MATRIX: "15m"
       TEST_PG_BENCH_SCALES_MATRIX: "1"
       POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
-      PG_VERSION: ${{ matrix.postgres_version }}
+      DEFAULT_PG_VERSION: 16
       TEST_OUTPUT: /tmp/test_output
       BUILD_TYPE: remote
 
@@ -590,20 +574,32 @@ jobs:
     steps:
     - uses: actions/checkout@v4
 
-    - name: Configure AWS credentials
-      uses: aws-actions/configure-aws-credentials@v4
-      with:
-        aws-region: eu-central-1
-        role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
-        role-duration-seconds: 18000 # 5 hours
+    # until https://github.com/neondatabase/neon/issues/8275 is fixed we temporarily install postgresql-16
+    # instead of using Neon artifacts containing pgbench
+    - name: Install postgresql-16 where pytest expects it
+      run: |
+        # Just to make it easier to test things locally on macOS (with arm64)
+        arch=$(uname -m | sed 's/x86_64/amd64/g' | sed 's/aarch64/arm64/g')
 
-    - name: Download Neon artifact
-      uses: ./.github/actions/download
-      with:
-        name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
-        path: /tmp/neon/
-        prefix: latest
-        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        cd /home/nonroot
+        wget -q "https://apt.postgresql.org/pub/repos/apt/pool/main/p/postgresql-17/libpq5_17.2-1.pgdg120+1_${arch}.deb"
+        wget -q "https://apt.postgresql.org/pub/repos/apt/pool/main/p/postgresql-16/postgresql-client-16_16.6-1.pgdg120+1_${arch}.deb"
+        wget -q "https://apt.postgresql.org/pub/repos/apt/pool/main/p/postgresql-16/postgresql-16_16.6-1.pgdg120+1_${arch}.deb"
+        dpkg -x libpq5_17.2-1.pgdg120+1_${arch}.deb pg
+        dpkg -x postgresql-16_16.6-1.pgdg120+1_${arch}.deb pg
+        dpkg -x postgresql-client-16_16.6-1.pgdg120+1_${arch}.deb pg
+
+        mkdir -p /tmp/neon/pg_install/v16/bin
+        ln -s /home/nonroot/pg/usr/lib/postgresql/16/bin/pgbench /tmp/neon/pg_install/v16/bin/pgbench
+        ln -s /home/nonroot/pg/usr/lib/postgresql/16/bin/psql    /tmp/neon/pg_install/v16/bin/psql
+        ln -s /home/nonroot/pg/usr/lib/$(uname -m)-linux-gnu     /tmp/neon/pg_install/v16/lib
+
+        LD_LIBRARY_PATH="/home/nonroot/pg/usr/lib/$(uname -m)-linux-gnu:${LD_LIBRARY_PATH:-}"
+        export LD_LIBRARY_PATH
+        echo "LD_LIBRARY_PATH=${LD_LIBRARY_PATH}" >> ${GITHUB_ENV}
+
+        /tmp/neon/pg_install/v16/bin/pgbench --version
+        /tmp/neon/pg_install/v16/bin/psql --version
 
     - name: Set up Connection String
       id: set-up-connstr
@@ -612,9 +608,6 @@ jobs:
           neonvm-captest-pgvector)
             CONNSTR=${{ secrets.BENCHMARK_PGVECTOR_CONNSTR }}
             ;;
-          neonvm-captest-pgvector-pg17)
-            CONNSTR=${{ secrets.BENCHMARK_PGVECTOR_CONNSTR_PG17 }}
-            ;;
           azure-captest-pgvector)
             CONNSTR=${{ secrets.BENCHMARK_PGVECTOR_CONNSTR_AZURE }}
             ;;
@@ -626,6 +619,13 @@ jobs:
 
         echo "connstr=${CONNSTR}" >> $GITHUB_OUTPUT
 
+    - name: Configure AWS credentials
+      uses: aws-actions/configure-aws-credentials@v4
+      with:
+        aws-region: eu-central-1
+        role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        role-duration-seconds: 18000 # 5 hours
+
     - name: Benchmark pgvector hnsw indexing
       uses: ./.github/actions/run-python-test-set
       with:
@@ -634,7 +634,7 @@ jobs:
         run_in_parallel: false
         save_perf_report: ${{ env.SAVE_PERF_REPORT }}
         extra_params: -m remote_cluster --timeout 21600 -k test_pgvector_indexing
-        pg_version: ${{ env.PG_VERSION }}
+        pg_version: ${{ env.DEFAULT_PG_VERSION }}
         aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
       env:
         VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
@@ -649,7 +649,7 @@ jobs:
         run_in_parallel: false
         save_perf_report: ${{ env.SAVE_PERF_REPORT }}
         extra_params: -m remote_cluster --timeout 21600
-        pg_version: ${{ env.PG_VERSION }}
+        pg_version: ${{ env.DEFAULT_PG_VERSION }}
         aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
       env:
         BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
@@ -696,7 +696,7 @@ jobs:
 
     env:
       POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
-      PG_VERSION: ${{ matrix.pg_version }}
+      DEFAULT_PG_VERSION: 16
       TEST_OUTPUT: /tmp/test_output
       TEST_OLAP_COLLECT_EXPLAIN: ${{ github.event.inputs.collect_olap_explain }}
       TEST_OLAP_COLLECT_PG_STAT_STATEMENTS: ${{ github.event.inputs.collect_pg_stat_statements }}
@@ -739,18 +739,7 @@ jobs:
       run: |
         case "${PLATFORM}" in
           neonvm-captest-reuse)
-            case "${PG_VERSION}" in
-              16)
-                CONNSTR=${{ secrets.BENCHMARK_CAPTEST_CLICKBENCH_10M_CONNSTR }}
-                ;;
-              17)
-                CONNSTR=${{ secrets.BENCHMARK_CAPTEST_CLICKBENCH_CONNSTR_PG17 }}
-                ;;
-              *)
-                echo >&2 "Unsupported PG_VERSION=${PG_VERSION} for PLATFORM=${PLATFORM}"
-                exit 1
-                ;;
-            esac
+            CONNSTR=${{ secrets.BENCHMARK_CAPTEST_CLICKBENCH_10M_CONNSTR }}
             ;;
           rds-aurora)
             CONNSTR=${{ secrets.BENCHMARK_RDS_AURORA_CLICKBENCH_10M_CONNSTR }}
@@ -774,7 +763,7 @@ jobs:
         run_in_parallel: false
         save_perf_report: ${{ env.SAVE_PERF_REPORT }}
         extra_params: -m remote_cluster --timeout 43200 -k test_clickbench
-        pg_version: ${{ env.PG_VERSION }}
+        pg_version: ${{ env.DEFAULT_PG_VERSION }}
         aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
       env:
         VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
@@ -810,7 +799,7 @@ jobs:
     # We might change it after https://github.com/neondatabase/neon/issues/2900.
     #
     # *_TPCH_S10_CONNSTR: DB generated with scale factor 10 (~10 GB)
-    # if: ${{ !cancelled() && (github.event.inputs.run_only_pgvector_tests == 'false' || github.event.inputs.run_only_pgvector_tests == null) }}
+    if: ${{ !cancelled() && (github.event.inputs.run_only_pgvector_tests == 'false' || github.event.inputs.run_only_pgvector_tests == null) }}
     permissions:
       contents: write
       statuses: write
@@ -823,11 +812,12 @@ jobs:
 
     env:
       POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
-      PG_VERSION: ${{ matrix.pg_version }}
+      DEFAULT_PG_VERSION: 16
       TEST_OUTPUT: /tmp/test_output
       BUILD_TYPE: remote
       SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref_name == 'main' ) }}
       PLATFORM: ${{ matrix.platform }}
+      TEST_OLAP_SCALE: ${{ matrix.scale }}
 
     runs-on: [ self-hosted, us-east-2, x64 ]
     container:
@@ -859,24 +849,13 @@ jobs:
       run: |
         case "${PLATFORM}" in
           neonvm-captest-reuse)
-            case "${PG_VERSION}" in
-              16)
-                CONNSTR_SECRET_NAME="BENCHMARK_CAPTEST_TPCH_S10_CONNSTR"
-                ;;
-              17)
-                CONNSTR_SECRET_NAME="BENCHMARK_CAPTEST_TPCH_CONNSTR_PG17"
-                ;;
-              *)
-                echo >&2 "Unsupported PG_VERSION=${PG_VERSION} for PLATFORM=${PLATFORM}"
-                exit 1
-                ;;
-            esac
+            ENV_PLATFORM=CAPTEST_TPCH
             ;;
           rds-aurora)
-            CONNSTR_SECRET_NAME="BENCHMARK_RDS_AURORA_TPCH_S10_CONNSTR"
+            ENV_PLATFORM=RDS_AURORA_TPCH
             ;;
           rds-postgres)
-            CONNSTR_SECRET_NAME="BENCHMARK_RDS_POSTGRES_TPCH_S10_CONNSTR"
+            ENV_PLATFORM=RDS_POSTGRES_TPCH
             ;;
           *)
             echo >&2 "Unknown PLATFORM=${PLATFORM}. Allowed only 'neonvm-captest-reuse', 'rds-aurora', or 'rds-postgres'"
@@ -884,6 +863,7 @@ jobs:
             ;;
         esac
 
+        CONNSTR_SECRET_NAME="BENCHMARK_${ENV_PLATFORM}_S${TEST_OLAP_SCALE}_CONNSTR"
         echo "CONNSTR_SECRET_NAME=${CONNSTR_SECRET_NAME}" >> $GITHUB_ENV
 
     - name: Set up Connection String
@@ -901,13 +881,13 @@ jobs:
         run_in_parallel: false
         save_perf_report: ${{ env.SAVE_PERF_REPORT }}
         extra_params: -m remote_cluster --timeout 21600 -k test_tpch
-        pg_version: ${{ env.PG_VERSION }}
+        pg_version: ${{ env.DEFAULT_PG_VERSION }}
         aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
       env:
         VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
         PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
         BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
-        TEST_OLAP_SCALE: 10
+        TEST_OLAP_SCALE: ${{ matrix.scale }}
 
     - name: Create Allure report
       id: create-allure-report
@@ -929,7 +909,7 @@ jobs:
         SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
 
   user-examples-compare:
-    # if: ${{ !cancelled() && (github.event.inputs.run_only_pgvector_tests == 'false' || github.event.inputs.run_only_pgvector_tests == null) }}
+    if: ${{ !cancelled() && (github.event.inputs.run_only_pgvector_tests == 'false' || github.event.inputs.run_only_pgvector_tests == null) }}
     permissions:
       contents: write
       statuses: write
@@ -942,7 +922,7 @@ jobs:
 
     env:
       POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
-      PG_VERSION: ${{ matrix.pg_version }}
+      DEFAULT_PG_VERSION: 16
       TEST_OUTPUT: /tmp/test_output
       BUILD_TYPE: remote
       SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref_name == 'main' ) }}
@@ -979,18 +959,7 @@ jobs:
       run: |
         case "${PLATFORM}" in
           neonvm-captest-reuse)
-            case "${PG_VERSION}" in
-              16)
-                CONNSTR=${{ secrets.BENCHMARK_USER_EXAMPLE_CAPTEST_CONNSTR }}
-                ;;
-              17)
-                CONNSTR=${{ secrets.BENCHMARK_CAPTEST_USER_EXAMPLE_CONNSTR_PG17 }}
-                ;;
-              *)
-                echo >&2 "Unsupported PG_VERSION=${PG_VERSION} for PLATFORM=${PLATFORM}"
-                exit 1
-                ;;
-            esac
+            CONNSTR=${{ secrets.BENCHMARK_USER_EXAMPLE_CAPTEST_CONNSTR }}
             ;;
           rds-aurora)
             CONNSTR=${{ secrets.BENCHMARK_USER_EXAMPLE_RDS_AURORA_CONNSTR }}
@@ -1014,7 +983,7 @@ jobs:
         run_in_parallel: false
         save_perf_report: ${{ env.SAVE_PERF_REPORT }}
         extra_params: -m remote_cluster --timeout 21600 -k test_user_examples
-        pg_version: ${{ env.PG_VERSION }}
+        pg_version: ${{ env.DEFAULT_PG_VERSION }}
         aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
       env:
         VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"

.github/workflows/build-macos.yml

@@ -235,7 +235,7 @@ jobs:
           echo 'CPPFLAGS=-I/usr/local/opt/openssl@3/include' >> $GITHUB_ENV
 
       - name: Run cargo build (only for v17)
-        run: cargo build --all --release -j$(sysctl -n hw.ncpu)
+        run: PQ_LIB_DIR=$(pwd)/pg_install/v17/lib cargo build --all --release -j$(sysctl -n hw.ncpu)
 
       - name: Check that no warnings are produced (only for v17)
         run: ./run_clippy.sh

.github/workflows/build_and_test.yml

@@ -45,26 +45,6 @@ jobs:
             run cancel-previous-in-concurrency-group.yml \
               --field concurrency_group="${{ env.E2E_CONCURRENCY_GROUP }}"
 
-  files-changed:
-    needs: [ check-permissions ]
-    runs-on: [ self-hosted, small ]
-    timeout-minutes: 3
-    outputs:
-      check-rust-dependencies: ${{ steps.files-changed.outputs.rust_dependencies }}
-
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-        with:
-          submodules: true
-
-      - name: Check for file changes
-        uses: dorny/paths-filter@de90cc6fb38fc0963ad72b210f1f284cd68cea36  # v3.0.2
-        id: files-changed
-        with:
-          token: ${{ secrets.GITHUB_TOKEN }}
-          filters: .github/file-filters.yaml
-
   tag:
     needs: [ check-permissions ]
     runs-on: [ self-hosted, small ]
@@ -184,19 +164,77 @@ jobs:
 
   check-codestyle-rust:
     needs: [ check-permissions, build-build-tools-image ]
-    uses: ./.github/workflows/_check-codestyle-rust.yml
-    with:
-      build-tools-image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
-      archs: '["x64", "arm64"]'
-    secrets: inherit
+    strategy:
+      matrix:
+        arch: [ x64, arm64 ]
+    runs-on: ${{ fromJson(format('["self-hosted", "{0}"]', matrix.arch == 'arm64' && 'small-arm64' || 'small')) }}
 
-  check-dependencies-rust:
-    needs: [ files-changed, build-build-tools-image ]
-    if: ${{ needs.files-changed.outputs.check-rust-dependencies == 'true' }}
-    uses: ./.github/workflows/cargo-deny.yml
-    with:
-      build-tools-image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
-    secrets: inherit
+    container:
+      image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
+      credentials:
+        username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
+        password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
+      options: --init
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          submodules: true
+
+      - name: Cache cargo deps
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.cargo/registry
+            !~/.cargo/registry/src
+            ~/.cargo/git
+            target
+          key: v1-${{ runner.os }}-${{ runner.arch }}-cargo-${{ hashFiles('./Cargo.lock') }}-${{ hashFiles('./rust-toolchain.toml') }}-rust
+
+      # Some of our rust modules use FFI and need those to be checked
+      - name: Get postgres headers
+        run: make postgres-headers -j$(nproc)
+
+      # cargo hack runs the given cargo subcommand (clippy in this case) for all feature combinations.
+      # This will catch compiler & clippy warnings in all feature combinations.
+      # TODO: use cargo hack for build and test as well, but, that's quite expensive.
+      # NB: keep clippy args in sync with ./run_clippy.sh
+      #
+      # The only difference between "clippy --debug" and "clippy --release" is that in --release mode,
+      # #[cfg(debug_assertions)] blocks are not built. It's not worth building everything for second
+      # time just for that, so skip "clippy --release".
+      - run: |
+          CLIPPY_COMMON_ARGS="$( source .neon_clippy_args; echo "$CLIPPY_COMMON_ARGS")"
+          if [ "$CLIPPY_COMMON_ARGS" = "" ]; then
+            echo "No clippy args found in .neon_clippy_args"
+            exit 1
+          fi
+          echo "CLIPPY_COMMON_ARGS=${CLIPPY_COMMON_ARGS}" >> $GITHUB_ENV
+      - name: Run cargo clippy (debug)
+        run: cargo hack --features default --ignore-unknown-features --feature-powerset clippy $CLIPPY_COMMON_ARGS
+
+      - name: Check documentation generation
+        run: cargo doc --workspace --no-deps --document-private-items
+        env:
+            RUSTDOCFLAGS: "-Dwarnings -Arustdoc::private_intra_doc_links"
+
+      # Use `${{ !cancelled() }}` to run quck tests after the longer clippy run
+      - name: Check formatting
+        if: ${{ !cancelled() }}
+        run: cargo fmt --all -- --check
+
+      # https://github.com/facebookincubator/cargo-guppy/tree/bec4e0eb29dcd1faac70b1b5360267fc02bf830e/tools/cargo-hakari#2-keep-the-workspace-hack-up-to-date-in-ci
+      - name: Check rust dependencies
+        if: ${{ !cancelled() }}
+        run: |
+          cargo hakari generate --diff  # workspace-hack Cargo.toml is up-to-date
+          cargo hakari manage-deps --dry-run  # all workspace crates depend on workspace-hack
+
+      # https://github.com/EmbarkStudios/cargo-deny
+      - name: Check rust licenses/bans/advisories/sources
+        if: ${{ !cancelled() }}
+        run: cargo deny check --hide-inclusion-graph
 
   build-and-test-locally:
     needs: [ tag, build-build-tools-image ]
@@ -270,7 +308,7 @@ jobs:
       statuses: write
       contents: write
       pull-requests: write
-    runs-on: [ self-hosted, small-metal ]
+    runs-on: [ self-hosted, small ]
     container:
       image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
       credentials:
@@ -308,22 +346,25 @@ jobs:
       # XXX: no coverage data handling here, since benchmarks are run on release builds,
       # while coverage is currently collected for the debug ones
 
-  report-benchmarks-results-to-slack:
+  report-benchmarks-failures:
     needs: [ benchmarks, create-test-report ]
-    if: github.ref_name == 'main' && !cancelled() && contains(fromJSON('["success", "failure"]'), needs.benchmarks.result)
+    if: github.ref_name == 'main' && failure() && needs.benchmarks.result == 'failure'
+    permissions:
+      id-token: write # aws-actions/configure-aws-credentials
+      statuses: write
+      contents: write
+      pull-requests: write
     runs-on: ubuntu-22.04
 
     steps:
-    - uses: slackapi/slack-github-action@v2
+    - uses: slackapi/slack-github-action@v1
       with:
-        method: chat.postMessage
-        token: ${{ secrets.SLACK_BOT_TOKEN }}
-        payload: |
-          channel: "${{ vars.SLACK_ON_CALL_STORAGE_STAGING_STREAM }}"
-          text: |
-            Benchmarks on main: *${{ needs.benchmarks.result }}*
-            - <${{ needs.create-test-report.outputs.report-url }}|Allure report>
-            - <${{ github.event.head_commit.url }}|${{ github.sha }}>
+        channel-id: C060CNA47S9 # on-call-staging-storage-stream
+        slack-message: |
+          Benchmarks failed on main <${{ github.event.head_commit.url }}|${{ github.sha }}>
+          <${{ needs.create-test-report.outputs.report-url }}|Allure report>
+      env:
+        SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
 
   create-test-report:
     needs: [ check-permissions, build-and-test-locally, coverage-report, build-build-tools-image, benchmarks ]
@@ -682,7 +723,7 @@ jobs:
           push: true
           pull: true
           file: compute/compute-node.Dockerfile
-          target: extension-tests
+          target: neon-pg-ext-test
           cache-from: type=registry,ref=cache.neon.build/compute-node-${{ matrix.version.pg }}:cache-${{ matrix.version.debian }}-${{ matrix.arch }}
           tags: |
             neondatabase/neon-test-extensions-${{ matrix.version.pg }}:${{needs.tag.outputs.build-tag}}-${{ matrix.version.debian }}-${{ matrix.arch }}
@@ -814,17 +855,6 @@ jobs:
           username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
           password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
 
-      - name: Get the last compute release tag
-        id: get-last-compute-release-tag
-        env:
-          GH_TOKEN: ${{ secrets.CI_ACCESS_TOKEN }}
-        run: |
-          tag=$(gh api -q '[.[].tag_name | select(startswith("release-compute"))][0]'\
-            -H "Accept: application/vnd.github+json" \
-            -H "X-GitHub-Api-Version: 2022-11-28" \
-            "/repos/${{ github.repository }}/releases")
-          echo tag=${tag} >> ${GITHUB_OUTPUT}
-
       # `neondatabase/neon` contains multiple binaries, all of them use the same input for the version into the same version formatting library.
       # Pick pageserver as currently the only binary with extra "version" features printed in the string to verify.
       # Regular pageserver version string looks like
@@ -856,28 +886,14 @@ jobs:
           TEST_VERSION_ONLY: ${{ matrix.pg_version }}
         run: ./docker-compose/docker_compose_test.sh
 
-      - name: Print logs and clean up docker-compose test
-        if: always()
-        run: |
-          docker compose --profile test-extensions -f ./docker-compose/docker-compose.yml logs || true
-          docker compose --profile test-extensions -f ./docker-compose/docker-compose.yml down
-
-      - name: Test extension upgrade
-        timeout-minutes: 20
-        if: ${{ needs.tag.outputs.build-tag == github.run_id }}
-        env:
-          NEWTAG: ${{ needs.tag.outputs.build-tag }}
-          OLDTAG: ${{ steps.get-last-compute-release-tag.outputs.tag }}
-        run: ./docker-compose/test_extensions_upgrade.sh
-
       - name: Print logs and clean up
         if: always()
         run: |
-          docker compose --profile test-extensions -f ./docker-compose/docker-compose.yml logs || true
-          docker compose --profile test-extensions -f ./docker-compose/docker-compose.yml down
+          docker compose -f ./docker-compose/docker-compose.yml logs || 0
+          docker compose -f ./docker-compose/docker-compose.yml down
 
   promote-images-dev:
-    needs: [ check-permissions, tag, vm-compute-node-image, neon-image ]
+    needs: [ check-permissions, tag, vm-compute-node-image ]
     runs-on: ubuntu-22.04
 
     permissions:
@@ -912,7 +928,7 @@ jobs:
           done
 
   promote-images-prod:
-    needs: [ check-permissions, tag, test-images, promote-images-dev ]
+    needs: [ check-permissions, tag, test-images, vm-compute-node-image ]
     runs-on: ubuntu-22.04
     if: github.ref_name == 'main' || github.ref_name == 'release' || github.ref_name == 'release-proxy' || github.ref_name == 'release-compute'
 
@@ -1103,7 +1119,6 @@ jobs:
           retries: 5
           script: |
             const tag = "${{ needs.tag.outputs.build-tag }}";
-            const branch = "${{ github.ref_name }}";
 
             try {
               const existingRef = await github.rest.git.getRef({
@@ -1132,6 +1147,12 @@ jobs:
               console.log(`Tag ${tag} created successfully.`);
             }
 
+            // TODO: check how GitHub releases looks for proxy/compute releases and enable them if they're ok
+            if (context.ref !== 'refs/heads/release') {
+              console.log(`GitHub release skipped for ${context.ref}.`);
+              return;
+            }
+
             try {
               const existingRelease = await github.rest.repos.getReleaseByTag({
                 owner: context.repo.owner,
@@ -1146,48 +1167,11 @@ jobs:
               }
 
               console.log(`Release for tag ${tag} does not exist. Creating it...`);
-
-              // Find the PR number using the commit SHA
-              const pullRequests = await github.rest.pulls.list({
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                state: 'closed',
-                base: branch,
-              });
-
-              const pr = pullRequests.data.find(pr => pr.merge_commit_sha === context.sha);
-              const prNumber = pr ? pr.number : null;
-
-              // Find the previous release on the branch
-              const releases = await github.rest.repos.listReleases({
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                per_page: 100,
-              });
-
-              const branchReleases = releases.data
-                .filter((release) => {
-                  const regex = new RegExp(`^${branch}-\\d+$`);
-                  return regex.test(release.tag_name) && !release.draft && !release.prerelease;
-                })
-                .sort((a, b) => new Date(b.created_at) - new Date(a.created_at));
-
-              const previousTag = branchReleases.length > 0 ? branchReleases[0].tag_name : null;
-
-              const releaseNotes = [
-                prNumber
-                  ? `Release PR https://github.com/${context.repo.owner}/${context.repo.repo}/pull/${prNumber}.`
-                  : 'Release PR not found.',
-                previousTag
-                  ? `Diff with the previous release https://github.com/${context.repo.owner}/${context.repo.repo}/compare/${previousTag}...${tag}.`
-                  : `No previous release found on branch ${branch}.`,
-              ].join('\n\n');
-
               await github.rest.repos.createRelease({
                 owner: context.repo.owner,
                 repo: context.repo.repo,
                 tag_name: tag,
-                body: releaseNotes,
+                generate_release_notes: true,
               });
               console.log(`Release for tag ${tag} created successfully.`);
             }
@@ -1360,8 +1344,6 @@ jobs:
       - build-and-test-locally
       - check-codestyle-python
       - check-codestyle-rust
-      - check-dependencies-rust
-      - files-changed
       - promote-images-dev
       - test-images
       - trigger-custom-extensions-build-and-wait
@@ -1374,11 +1356,4 @@ jobs:
         if: |
           contains(needs.*.result, 'failure')
           || contains(needs.*.result, 'cancelled')
-          || (needs.check-dependencies-rust.result == 'skipped' && needs.files-changed.outputs.check-rust-dependencies == 'true')
-          || needs.build-and-test-locally.result == 'skipped'
-          || needs.check-codestyle-python.result == 'skipped'
-          || needs.check-codestyle-rust.result == 'skipped'
-          || needs.files-changed.result == 'skipped'
-          || needs.promote-images-dev.result == 'skipped'
-          || needs.test-images.result == 'skipped'
-          || needs.trigger-custom-extensions-build-and-wait.result == 'skipped'
+          || contains(needs.*.result, 'skipped')

.github/workflows/build_and_test_with_sanitizers.yml

@@ -1,134 +0,0 @@
-name: Build and Test with Sanitizers
-
-on:
-  schedule:
-    # * is a special character in YAML so you have to quote this string
-    #          ┌───────────── minute (0 - 59)
-    #          │ ┌───────────── hour (0 - 23)
-    #          │ │ ┌───────────── day of the month (1 - 31)
-    #          │ │ │ ┌───────────── month (1 - 12 or JAN-DEC)
-    #          │ │ │ │ ┌───────────── day of the week (0 - 6 or SUN-SAT)
-    - cron:   '0 1 * * *' # run once a day, timezone is utc
-  workflow_dispatch:
-
-defaults:
-  run:
-    shell: bash -euxo pipefail {0}
-
-concurrency:
-  # Allow only one workflow per any non-`main` branch.
-  group: ${{ github.workflow }}-${{ github.ref_name }}-${{ github.ref_name == 'main' && github.sha || 'anysha' }}
-  cancel-in-progress: true
-
-env:
-  RUST_BACKTRACE: 1
-  COPT: '-Werror'
-
-jobs:
-  tag:
-    runs-on: [ self-hosted, small ]
-    container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/base:pinned
-    outputs:
-      build-tag: ${{steps.build-tag.outputs.tag}}
-
-    steps:
-      # Need `fetch-depth: 0` to count the number of commits in the branch
-      - uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-
-      - name: Get build tag
-        run: |
-          echo run:$GITHUB_RUN_ID
-          echo ref:$GITHUB_REF_NAME
-          echo rev:$(git rev-list --count HEAD)
-          if [[ "$GITHUB_REF_NAME" == "main" ]]; then
-            echo "tag=$(git rev-list --count HEAD)" >> $GITHUB_OUTPUT
-          elif [[ "$GITHUB_REF_NAME" == "release" ]]; then
-            echo "tag=release-$(git rev-list --count HEAD)" >> $GITHUB_OUTPUT
-          elif [[ "$GITHUB_REF_NAME" == "release-proxy" ]]; then
-            echo "tag=release-proxy-$(git rev-list --count HEAD)" >> $GITHUB_OUTPUT
-          elif [[ "$GITHUB_REF_NAME" == "release-compute" ]]; then
-            echo "tag=release-compute-$(git rev-list --count HEAD)" >> $GITHUB_OUTPUT
-          else
-            echo "GITHUB_REF_NAME (value '$GITHUB_REF_NAME') is not set to either 'main' or 'release', 'release-proxy', 'release-compute'"
-            echo "tag=$GITHUB_RUN_ID" >> $GITHUB_OUTPUT
-          fi
-        shell: bash
-        id: build-tag
-
-  build-build-tools-image:
-    uses: ./.github/workflows/build-build-tools-image.yml
-    secrets: inherit
-
-  build-and-test-locally:
-    needs: [ tag, build-build-tools-image ]
-    strategy:
-      fail-fast: false
-      matrix:
-        arch: [ x64, arm64 ]
-        build-type: [ release ]
-    uses: ./.github/workflows/_build-and-test-locally.yml
-    with:
-      arch: ${{ matrix.arch }}
-      build-tools-image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
-      build-tag: ${{ needs.tag.outputs.build-tag }}
-      build-type: ${{ matrix.build-type }}
-      test-cfg: '[{"pg_version":"v17"}]'
-      sanitizers: enabled
-    secrets: inherit
-
-
-  create-test-report:
-    needs: [ build-and-test-locally, build-build-tools-image ]
-    if: ${{ !cancelled() }}
-    permissions:
-      id-token: write # aws-actions/configure-aws-credentials
-      statuses: write
-      contents: write
-      pull-requests: write
-    outputs:
-      report-url: ${{ steps.create-allure-report.outputs.report-url }}
-
-    runs-on: [ self-hosted, small ]
-    container:
-      image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
-      credentials:
-        username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
-        password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
-      options: --init
-
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Create Allure report
-        if: ${{ !cancelled() }}
-        id: create-allure-report
-        uses: ./.github/actions/allure-report-generate
-        with:
-          store-test-results-into-db: true
-          aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
-        env:
-          REGRESS_TEST_RESULT_CONNSTR_NEW: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}
-
-      - uses: actions/github-script@v7
-        if: ${{ !cancelled() }}
-        with:
-          # Retry script for 5XX server errors: https://github.com/actions/github-script#retries
-          retries: 5
-          script: |
-            const report = {
-              reportUrl:     "${{ steps.create-allure-report.outputs.report-url }}",
-              reportJsonUrl: "${{ steps.create-allure-report.outputs.report-json-url }}",
-            }
-
-            const coverage = {}
-
-            const script = require("./scripts/comment-test-report.js")
-            await script({
-              github,
-              context,
-              fetch,
-              report,
-              coverage,
-            })

.github/workflows/cargo-deny.yml

@@ -1,57 +0,0 @@
-name: cargo deny checks
-
-on:
-  workflow_call:
-    inputs:
-      build-tools-image:
-        required: false
-        type: string
-  schedule:
-    - cron: '0 0 * * *'
-
-jobs:
-  cargo-deny:
-    strategy:
-      matrix:
-        ref: >-
-          ${{
-            fromJSON(
-              github.event_name == 'schedule'
-                && '["main","release","release-proxy","release-compute"]'
-                || format('["{0}"]', github.sha)
-            )
-          }}
-
-    runs-on: [self-hosted, small]
-
-    container:
-      image: ${{ inputs.build-tools-image || 'neondatabase/build-tools:pinned' }}
-      credentials:
-        username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
-        password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
-      options: --init
-
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-        with:
-          ref: ${{ matrix.ref }}
-
-      - name: Check rust licenses/bans/advisories/sources
-        env:
-          CARGO_DENY_TARGET: >-
-            ${{ github.event_name == 'schedule' && 'advisories' || 'all' }}
-        run: cargo deny check --hide-inclusion-graph $CARGO_DENY_TARGET
-
-      - name: Post to a Slack channel
-        if: ${{ github.event_name == 'schedule' && failure() }}
-        uses: slackapi/slack-github-action@v2
-        with:
-          method: chat.postMessage
-          token: ${{ secrets.SLACK_BOT_TOKEN }}
-          payload: |
-            channel: ${{ vars.SLACK_CICD_CHANNEL_ID }}
-            text: |
-              Periodic cargo-deny on ${{ matrix.ref }}: ${{ job.status }}
-              <${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}|GitHub Run>
-              Pinging @oncall-devprod.

.github/workflows/ingest_benchmark.yml

@@ -28,24 +28,7 @@ jobs:
     strategy:
       fail-fast: false # allow other variants to continue even if one fails
       matrix:
-        include:
-          - target_project: new_empty_project_stripe_size_2048 
-            stripe_size: 2048 # 16 MiB
-            postgres_version: 16
-          - target_project: new_empty_project_stripe_size_32768
-            stripe_size: 32768 # 256 MiB # note that this is different from null because using null will shard_split the project only if it reaches the threshold
-                               # while here it is sharded from the beginning with a shard size of 256 MiB
-            postgres_version: 16
-          - target_project: new_empty_project
-            stripe_size: null # run with neon defaults which will shard split only when reaching the threshold
-            postgres_version: 16
-          - target_project: new_empty_project
-            stripe_size: null # run with neon defaults which will shard split only when reaching the threshold
-            postgres_version: 17
-          - target_project: large_existing_project
-            stripe_size: null # cannot re-shared or choose different stripe size for existing, already sharded project
-            postgres_version: 16
-      max-parallel: 1 # we want to run each stripe size sequentially to be able to compare the results
+        target_project: [new_empty_project, large_existing_project]
     permissions:
       contents: write
       statuses: write
@@ -84,21 +67,17 @@ jobs:
         aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
     - name: Create Neon Project
-      if: ${{ startsWith(matrix.target_project, 'new_empty_project') }}
+      if: ${{ matrix.target_project == 'new_empty_project' }}
       id: create-neon-project-ingest-target
       uses: ./.github/actions/neon-project-create
       with:
         region_id: aws-us-east-2
-        postgres_version: ${{ matrix.postgres_version }}
+        postgres_version: 16
         compute_units: '[7, 7]' # we want to test large compute here to avoid compute-side bottleneck
         api_key: ${{ secrets.NEON_STAGING_API_KEY }}
-        shard_split_project: ${{ matrix.stripe_size != null && 'true' || 'false' }}
-        admin_api_key: ${{ secrets.NEON_STAGING_ADMIN_API_KEY }} 
-        shard_count: 8
-        stripe_size: ${{ matrix.stripe_size }}
 
     - name: Initialize Neon project
-      if: ${{ startsWith(matrix.target_project, 'new_empty_project') }}
+      if: ${{ matrix.target_project == 'new_empty_project' }}
       env:
           BENCHMARK_INGEST_TARGET_CONNSTR: ${{ steps.create-neon-project-ingest-target.outputs.dsn }}
           NEW_PROJECT_ID: ${{ steps.create-neon-project-ingest-target.outputs.project_id }}
@@ -151,7 +130,7 @@ jobs:
         test_selection: performance/test_perf_ingest_using_pgcopydb.py
         run_in_parallel: false
         extra_params: -s -m remote_cluster --timeout 86400 -k test_ingest_performance_using_pgcopydb
-        pg_version: v${{ matrix.postgres_version }}
+        pg_version: v16
         save_perf_report: true
         aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
       env:
@@ -167,7 +146,7 @@ jobs:
         ${PSQL} "${BENCHMARK_INGEST_TARGET_CONNSTR}" -c "\dt+"
 
     - name: Delete Neon Project
-      if: ${{ always() && startsWith(matrix.target_project, 'new_empty_project') }}
+      if: ${{ always() && matrix.target_project == 'new_empty_project' }}
       uses: ./.github/actions/neon-project-delete
       with:
         project_id: ${{ steps.create-neon-project-ingest-target.outputs.project_id }}

.github/workflows/neon_extra_builds.yml

@@ -114,7 +114,7 @@ jobs:
         run: make walproposer-lib -j$(nproc)
 
       - name: Produce the build stats
-        run: cargo build --all --release --timings -j$(nproc)
+        run: PQ_LIB_DIR=$(pwd)/pg_install/v17/lib cargo build --all --release --timings -j$(nproc)
 
       - name: Configure AWS credentials
         uses: aws-actions/configure-aws-credentials@v4

.github/workflows/pg-clients.yml

@@ -12,8 +12,8 @@ on:
   pull_request:
     paths:
       - '.github/workflows/pg-clients.yml'
-      - 'test_runner/pg_clients/**/*.py'
-      - 'test_runner/logical_repl/**/*.py'
+      - 'test_runner/pg_clients/**'
+      - 'test_runner/logical_repl/**'
       - 'poetry.lock'
   workflow_dispatch:
 
@@ -104,8 +104,6 @@ jobs:
         with:
           api_key: ${{ secrets.NEON_STAGING_API_KEY }}
           postgres_version: ${{ env.DEFAULT_PG_VERSION }}
-          project_settings: >-
-            {"enable_logical_replication": true}
 
       - name: Run tests
         uses: ./.github/actions/run-python-test-set

.github/workflows/pre-merge-checks.yml

@@ -1,12 +1,6 @@
 name: Pre-merge checks
 
 on:
-  pull_request:
-    paths:
-      - .github/workflows/_check-codestyle-python.yml
-      - .github/workflows/_check-codestyle-rust.yml
-      - .github/workflows/build-build-tools-image.yml
-      - .github/workflows/pre-merge-checks.yml
   merge_group:
     branches:
       - main
@@ -23,10 +17,8 @@ jobs:
     runs-on: ubuntu-22.04
     outputs:
       python-changed: ${{ steps.python-src.outputs.any_changed }}
-      rust-changed: ${{ steps.rust-src.outputs.any_changed }}
     steps:
       - uses: actions/checkout@v4
-
       - uses: tj-actions/changed-files@4edd678ac3f81e2dc578756871e4d00c19191daf # v45.0.4
         id: python-src
         with:
@@ -38,31 +30,14 @@ jobs:
             poetry.lock
             pyproject.toml
 
-      - uses: tj-actions/changed-files@4edd678ac3f81e2dc578756871e4d00c19191daf # v45.0.4
-        id: rust-src
-        with:
-          files: |
-            .github/workflows/_check-codestyle-rust.yml
-            .github/workflows/build-build-tools-image.yml
-            .github/workflows/pre-merge-checks.yml
-            **/**.rs
-            **/Cargo.toml
-            Cargo.toml
-            Cargo.lock
-
       - name: PRINT ALL CHANGED FILES FOR DEBUG PURPOSES
         env:
           PYTHON_CHANGED_FILES: ${{ steps.python-src.outputs.all_changed_files }}
-          RUST_CHANGED_FILES: ${{ steps.rust-src.outputs.all_changed_files }}
         run: |
           echo "${PYTHON_CHANGED_FILES}"
-          echo "${RUST_CHANGED_FILES}"
 
   build-build-tools-image:
-    if: |
-      false
-      || needs.get-changed-files.outputs.python-changed == 'true'
-      || needs.get-changed-files.outputs.rust-changed == 'true'
+    if: needs.get-changed-files.outputs.python-changed == 'true'
     needs: [ get-changed-files ]
     uses: ./.github/workflows/build-build-tools-image.yml
     with:
@@ -80,30 +55,18 @@ jobs:
       build-tools-image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm-x64
     secrets: inherit
 
-  check-codestyle-rust:
-    if: needs.get-changed-files.outputs.rust-changed == 'true'
-    needs: [ get-changed-files, build-build-tools-image ]
-    uses: ./.github/workflows/_check-codestyle-rust.yml
-    with:
-      # `-bookworm-x64` suffix should match the combination in `build-build-tools-image`
-      build-tools-image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm-x64
-      archs: '["x64"]'
-    secrets: inherit
-
   # To get items from the merge queue merged into main we need to satisfy "Status checks that are required".
   # Currently we require 2 jobs (checks with exact name):
   # - conclusion
   # - neon-cloud-e2e
   conclusion:
-    # Do not run job on Pull Requests as it interferes with the `conclusion` job from the `build_and_test` workflow
-    if: always() && github.event_name == 'merge_group'
+    if: always()
     permissions:
       statuses: write # for `github.repos.createCommitStatus(...)`
       contents: write
     needs:
       - get-changed-files
       - check-codestyle-python
-      - check-codestyle-rust
     runs-on: ubuntu-22.04
     steps:
       - name: Create fake `neon-cloud-e2e` check
@@ -128,8 +91,6 @@ jobs:
       - name: Fail the job if any of the dependencies do not succeed or skipped
         run: exit 1
         if: |
-          false
-          || (needs.check-codestyle-python.result == 'skipped' && needs.get-changed-files.outputs.python-changed == 'true')
-          || (needs.check-codestyle-rust.result   == 'skipped' && needs.get-changed-files.outputs.rust-changed   == 'true')
+          (contains(needs.check-codestyle-python.result, 'skipped') && needs.get-changed-files.outputs.python-changed == 'true')
           || contains(needs.*.result, 'failure')
           || contains(needs.*.result, 'cancelled')

.github/workflows/release.yml

@@ -3,9 +3,8 @@ name: Create Release Branch
 on:
   schedule:
     # It should be kept in sync with if-condition in jobs
-    - cron: '0 6 * * THU' # Proxy release
     - cron: '0 6 * * FRI' # Storage release
-    - cron: '0 7 * * FRI' # Compute release
+    - cron: '0 6 * * THU' # Proxy release
   workflow_dispatch:
     inputs:
       create-storage-release-branch:
@@ -56,7 +55,7 @@ jobs:
       ci-access-token: ${{ secrets.CI_ACCESS_TOKEN }}
 
   create-compute-release-branch:
-    if: ${{ github.event.schedule == '0 7 * * FRI' || inputs.create-compute-release-branch }}
+    if: inputs.create-compute-release-branch
 
     permissions:
       contents: write

Cargo.toml

@@ -54,7 +54,6 @@ async-compression = { version = "0.4.0", features = ["tokio", "gzip", "zstd"] }
 atomic-take = "1.1.0"
 backtrace = "0.3.74"
 flate2 = "1.0.26"
-assert-json-diff = "2"
 async-stream = "0.3"
 async-trait = "0.1"
 aws-config = { version = "1.5", default-features = false, features=["rustls", "sso"] }
@@ -66,7 +65,7 @@ aws-smithy-types = "1.2"
 aws-credential-types = "1.2.0"
 aws-sigv4 = { version = "1.2", features = ["sign-http"] }
 aws-types = "1.3"
-axum = { version = "0.8.1", features = ["ws"] }
+axum = { version = "0.7.9", features = ["ws"] }
 base64 = "0.13.0"
 bincode = "1.3"
 bindgen = "0.70"
@@ -78,10 +77,10 @@ camino = "1.1.6"
 cfg-if = "1.0.0"
 chrono = { version = "0.4", default-features = false, features = ["clock"] }
 clap = { version = "4.0", features = ["derive", "env"] }
-clashmap = { version = "1.0", features = ["raw-api"] }
 comfy-table = "7.1"
 const_format = "0.2"
 crc32c = "0.6"
+dashmap = { version = "5.5.0", features = ["raw-api"] }
 diatomic-waker = { version = "0.2.3" }
 either = "1.8"
 enum-map = "2.4.2"
@@ -124,7 +123,7 @@ measured = { version = "0.0.22", features=["lasso"] }
 measured-process = { version = "0.0.22" }
 memoffset = "0.9"
 nix = { version = "0.27", features = ["dir", "fs", "process", "socket", "signal", "poll"] }
-notify = "8.0.0"
+notify = "6.0.0"
 num_cpus = "1.15"
 num-traits = "0.2.15"
 once_cell = "1.13"
@@ -178,7 +177,7 @@ test-context = "0.3"
 thiserror = "1.0"
 tikv-jemallocator = { version = "0.6", features = ["profiling", "stats", "unprefixed_malloc_on_supported_platforms"] }
 tikv-jemalloc-ctl = { version = "0.6", features = ["stats"] }
-tokio = { version = "1.41", features = ["macros"] }
+tokio = { version = "1.17", features = ["macros"] }
 tokio-epoll-uring = { git = "https://github.com/neondatabase/tokio-epoll-uring.git" , branch = "main" }
 tokio-io-timeout = "1.2.0"
 tokio-postgres-rustls = "0.12.0"
@@ -188,15 +187,13 @@ tokio-tar = "0.3"
 tokio-util = { version = "0.7.10", features = ["io", "rt"] }
 toml = "0.8"
 toml_edit = "0.22"
-tonic = {version = "0.12.3", default-features = false, features = ["channel", "tls", "tls-roots"]}
+tonic = {version = "0.12.3", features = ["tls", "tls-roots"]}
 tower = { version = "0.5.2", default-features = false }
 tower-http = { version = "0.6.2", features = ["request-id", "trace"] }
 tower-service = "0.3.3"
 tracing = "0.1"
 tracing-error = "0.2"
-tracing-log = "0.2"
 tracing-opentelemetry = "0.28"
-tracing-serde = "0.2.0"
 tracing-subscriber = { version = "0.3", default-features = false, features = ["smallvec", "fmt", "tracing-log", "std", "env-filter", "json"] }
 try-lock = "0.2.5"
 twox-hash = { version = "1.6.3", default-features = false }

Dockerfile

@@ -45,7 +45,7 @@ COPY --chown=nonroot . .
 
 ARG ADDITIONAL_RUSTFLAGS
 RUN set -e \
-    && RUSTFLAGS="-Clinker=clang -Clink-arg=-fuse-ld=mold -Clink-arg=-Wl,--no-rosegment -Cforce-frame-pointers=yes ${ADDITIONAL_RUSTFLAGS}" cargo build \
+    && PQ_LIB_DIR=$(pwd)/pg_install/v${STABLE_PG_VERSION}/lib RUSTFLAGS="-Clinker=clang -Clink-arg=-fuse-ld=mold -Clink-arg=-Wl,--no-rosegment -Cforce-frame-pointers=yes ${ADDITIONAL_RUSTFLAGS}" cargo build \
       --bin pg_sni_router  \
       --bin pageserver  \
       --bin pagectl  \
@@ -64,7 +64,6 @@ ARG DEFAULT_PG_VERSION
 WORKDIR /data
 
 RUN set -e \
-    && echo 'Acquire::Retries "5";' > /etc/apt/apt.conf.d/80-retries \
     && apt update \
     && apt install -y \
         libreadline-dev \
@@ -72,8 +71,6 @@ RUN set -e \
         ca-certificates \
 	# System postgres for use with client libraries (e.g. in storage controller)
         postgresql-15 \
-        openssl \
-    && rm -f /etc/apt/apt.conf.d/80-retries \
     && rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* \
     && useradd -d /data neon \
     && chown -R neon:neon /data

Makefile

@@ -3,6 +3,7 @@ ROOT_PROJECT_DIR := $(dir $(abspath $(lastword $(MAKEFILE_LIST))))
 # Where to install Postgres, default is ./pg_install, maybe useful for package managers
 POSTGRES_INSTALL_DIR ?= $(ROOT_PROJECT_DIR)/pg_install/
 
+OPENSSL_PREFIX_DIR := /usr/local/openssl
 ICU_PREFIX_DIR := /usr/local/icu
 
 #
@@ -10,43 +11,32 @@ ICU_PREFIX_DIR := /usr/local/icu
 # environment variable.
 #
 BUILD_TYPE ?= debug
-WITH_SANITIZERS ?= no
 ifeq ($(BUILD_TYPE),release)
 	PG_CONFIGURE_OPTS = --enable-debug --with-openssl
 	PG_CFLAGS = -O2 -g3 $(CFLAGS)
-	PG_LDFLAGS = $(LDFLAGS)
 	# Unfortunately, `--profile=...` is a nightly feature
 	CARGO_BUILD_FLAGS += --release
 else ifeq ($(BUILD_TYPE),debug)
 	PG_CONFIGURE_OPTS = --enable-debug --with-openssl --enable-cassert --enable-depend
 	PG_CFLAGS = -O0 -g3 $(CFLAGS)
-	PG_LDFLAGS = $(LDFLAGS)
 else
 	$(error Bad build type '$(BUILD_TYPE)', see Makefile for options)
 endif
 
-ifeq ($(WITH_SANITIZERS),yes)
-	PG_CFLAGS += -fsanitize=address -fsanitize=undefined -fno-sanitize-recover
-	COPT += -Wno-error # to avoid failing on warnings induced by sanitizers
-	PG_LDFLAGS = -fsanitize=address -fsanitize=undefined -static-libasan -static-libubsan $(LDFLAGS)
-	export CC := gcc
-	export ASAN_OPTIONS := detect_leaks=0
-endif
-
 ifeq ($(shell test -e /home/nonroot/.docker_build && echo -n yes),yes)
 	# Exclude static build openssl, icu for local build (MacOS, Linux)
 	# Only keep for build type release and debug
+	PG_CFLAGS += -I$(OPENSSL_PREFIX_DIR)/include
 	PG_CONFIGURE_OPTS += --with-icu
 	PG_CONFIGURE_OPTS += ICU_CFLAGS='-I/$(ICU_PREFIX_DIR)/include -DU_STATIC_IMPLEMENTATION'
 	PG_CONFIGURE_OPTS += ICU_LIBS='-L$(ICU_PREFIX_DIR)/lib -L$(ICU_PREFIX_DIR)/lib64 -licui18n -licuuc -licudata -lstdc++ -Wl,-Bdynamic -lm'
+	PG_CONFIGURE_OPTS += LDFLAGS='-L$(OPENSSL_PREFIX_DIR)/lib -L$(OPENSSL_PREFIX_DIR)/lib64 -L$(ICU_PREFIX_DIR)/lib -L$(ICU_PREFIX_DIR)/lib64 -Wl,-Bstatic -lssl -lcrypto -Wl,-Bdynamic -lrt -lm -ldl -lpthread'
 endif
 
 UNAME_S := $(shell uname -s)
 ifeq ($(UNAME_S),Linux)
 	# Seccomp BPF is only available for Linux
-	ifneq ($(WITH_SANITIZERS),yes)
-		PG_CONFIGURE_OPTS += --with-libseccomp
-	endif
+	PG_CONFIGURE_OPTS += --with-libseccomp
 else ifeq ($(UNAME_S),Darwin)
 	PG_CFLAGS += -DUSE_PREFETCH
 	ifndef DISABLE_HOMEBREW
@@ -77,6 +67,8 @@ CARGO_BUILD_FLAGS += $(filter -j1,$(MAKEFLAGS))
 CARGO_CMD_PREFIX += $(if $(filter n,$(MAKEFLAGS)),,+)
 # Force cargo not to print progress bar
 CARGO_CMD_PREFIX += CARGO_TERM_PROGRESS_WHEN=never CI=1
+# Set PQ_LIB_DIR to make sure `storage_controller` get linked with bundled libpq (through diesel)
+CARGO_CMD_PREFIX += PQ_LIB_DIR=$(POSTGRES_INSTALL_DIR)/v16/lib
 
 CACHEDIR_TAG_CONTENTS := "Signature: 8a477f597d28d172789f06886806bc55"
 
@@ -119,7 +111,7 @@ $(POSTGRES_INSTALL_DIR)/build/%/config.status:
 	EXTRA_VERSION=$$(cd $(ROOT_PROJECT_DIR)/vendor/postgres-$$VERSION && git rev-parse HEAD); \
 	(cd $(POSTGRES_INSTALL_DIR)/build/$$VERSION && \
 	env PATH="$(EXTRA_PATH_OVERRIDES):$$PATH" $(ROOT_PROJECT_DIR)/vendor/postgres-$$VERSION/configure \
-		CFLAGS='$(PG_CFLAGS)' LDFLAGS='$(PG_LDFLAGS)' \
+		CFLAGS='$(PG_CFLAGS)' \
 		$(PG_CONFIGURE_OPTS) --with-extra-version=" ($$EXTRA_VERSION)" \
 		--prefix=$(abspath $(POSTGRES_INSTALL_DIR))/$$VERSION > configure.log)
 

README.md

@@ -21,10 +21,8 @@ The Neon storage engine consists of two major components:
 
 See developer documentation in [SUMMARY.md](/docs/SUMMARY.md) for more information.
 
-## Running a local development environment
+## Running local installation
 
-Neon can be run on a workstation for small experiments and to test code changes, by
-following these instructions.
 
 #### Installing dependencies on Linux
 1. Install build dependencies and other applicable packages
@@ -240,7 +238,7 @@ postgres=# select * from t;
 > cargo neon stop
 ```
 
-More advanced usages can be found at [Local Development Control Plane (`neon_local`))](./control_plane/README.md).
+More advanced usages can be found at [Control Plane and Neon Local](./control_plane/README.md).
 
 #### Handling build failures
 

build-tools.Dockerfile

@@ -3,17 +3,6 @@ ARG DEBIAN_VERSION=bookworm
 FROM debian:bookworm-slim AS pgcopydb_builder
 ARG DEBIAN_VERSION
 
-# Use strict mode for bash to catch errors early
-SHELL ["/bin/bash", "-euo", "pipefail", "-c"]
-
-# By default, /bin/sh used in debian images will treat '\n' as eol,
-# but as we use bash as SHELL, and built-in echo in bash requires '-e' flag for that.
-RUN echo 'Acquire::Retries "5";' > /etc/apt/apt.conf.d/80-retries && \
-    echo -e "retry_connrefused = on\ntimeout=15\ntries=5\n" > /root/.wgetrc && \
-    echo -e "--retry-connrefused\n--connect-timeout 15\n--retry 5\n--max-time 300\n" > /root/.curlrc
-
-COPY build_tools/patches/pgcopydbv017.patch /pgcopydbv017.patch
-
 RUN if [ "${DEBIAN_VERSION}" = "bookworm" ]; then \
         set -e && \
         apt update && \
@@ -46,7 +35,6 @@ RUN if [ "${DEBIAN_VERSION}" = "bookworm" ]; then \
         mkdir /tmp/pgcopydb && \
         tar -xzf /tmp/pgcopydb.tar.gz -C /tmp/pgcopydb --strip-components=1 && \
         cd /tmp/pgcopydb && \
-        patch -p1 < /pgcopydbv017.patch && \
         make -s clean && \
         make -s -j12 install && \
         libpq_path=$(find /lib /usr/lib -name "libpq.so.5" | head -n 1) && \
@@ -63,8 +51,7 @@ ARG DEBIAN_VERSION
 
 # Add nonroot user
 RUN useradd -ms /bin/bash nonroot -b /home
-# Use strict mode for bash to catch errors early
-SHELL ["/bin/bash", "-euo", "pipefail", "-c"]
+SHELL ["/bin/bash", "-c"]
 
 RUN mkdir -p /pgcopydb/bin && \
     mkdir -p /pgcopydb/lib && \
@@ -74,10 +61,6 @@ RUN mkdir -p /pgcopydb/bin && \
 COPY --from=pgcopydb_builder /usr/lib/postgresql/16/bin/pgcopydb /pgcopydb/bin/pgcopydb
 COPY --from=pgcopydb_builder /pgcopydb/lib/libpq.so.5 /pgcopydb/lib/libpq.so.5
 
-RUN echo 'Acquire::Retries "5";' > /etc/apt/apt.conf.d/80-retries && \
-    echo -e "retry_connrefused = on\ntimeout=15\ntries=5\n" > /root/.wgetrc && \
-    echo -e "--retry-connrefused\n--connect-timeout 15\n--retry 5\n--max-time 300\n" > /root/.curlrc
-
 # System deps
 #
 # 'gdb' is included so that we get backtraces of core dumps produced in
@@ -132,7 +115,7 @@ RUN set -e \
 
 # Keep the version the same as in compute/compute-node.Dockerfile and
 # test_runner/regress/test_compute_metrics.py.
-ENV SQL_EXPORTER_VERSION=0.17.0
+ENV SQL_EXPORTER_VERSION=0.16.0
 RUN curl -fsSL \
     "https://github.com/burningalchemist/sql_exporter/releases/download/${SQL_EXPORTER_VERSION}/sql_exporter-${SQL_EXPORTER_VERSION}.linux-$(case "$(uname -m)" in x86_64) echo amd64;; aarch64) echo arm64;; esac).tar.gz" \
     --output sql_exporter.tar.gz \
@@ -199,20 +182,29 @@ RUN set -e \
 # It includes several bug fixes on top on v2.0 release (https://github.com/linux-test-project/lcov/compare/v2.0...master)
 # And patches from us:
 # - Generates json file with code coverage summary (https://github.com/neondatabase/lcov/commit/426e7e7a22f669da54278e9b55e6d8caabd00af0.tar.gz)
-RUN set +o pipefail && \
-	 for package in Capture::Tiny DateTime Devel::Cover Digest::MD5 File::Spec JSON::XS Memory::Process Time::HiRes JSON; do \
-		yes | perl -MCPAN -e "CPAN::Shell->notest('install', '$package')";\
-	 done && \
-	set -o pipefail
-# Split into separate step to debug flaky failures here
-RUN wget https://github.com/neondatabase/lcov/archive/426e7e7a22f669da54278e9b55e6d8caabd00af0.tar.gz -O lcov.tar.gz \
-    && ls -laht lcov.tar.gz && sha256sum lcov.tar.gz \
+RUN for package in Capture::Tiny DateTime Devel::Cover Digest::MD5 File::Spec JSON::XS Memory::Process Time::HiRes JSON; do yes | perl -MCPAN -e "CPAN::Shell->notest('install', '$package')"; done \
+    && wget https://github.com/neondatabase/lcov/archive/426e7e7a22f669da54278e9b55e6d8caabd00af0.tar.gz -O lcov.tar.gz \
     && echo "61a22a62e20908b8b9e27d890bd0ea31f567a7b9668065589266371dcbca0992  lcov.tar.gz" | sha256sum --check \
     && mkdir -p lcov && tar -xzf lcov.tar.gz -C lcov --strip-components=1 \
     && cd lcov \
     && make install \
     && rm -rf ../lcov.tar.gz
 
+# Compile and install the static OpenSSL library
+ENV OPENSSL_VERSION=1.1.1w
+ENV OPENSSL_PREFIX=/usr/local/openssl
+RUN wget -O /tmp/openssl-${OPENSSL_VERSION}.tar.gz https://www.openssl.org/source/openssl-${OPENSSL_VERSION}.tar.gz && \
+    echo "cf3098950cb4d853ad95c0841f1f9c6d3dc102dccfcacd521d93925208b76ac8 /tmp/openssl-${OPENSSL_VERSION}.tar.gz" | sha256sum --check && \
+    cd /tmp && \
+    tar xzvf /tmp/openssl-${OPENSSL_VERSION}.tar.gz && \
+    rm /tmp/openssl-${OPENSSL_VERSION}.tar.gz && \
+    cd /tmp/openssl-${OPENSSL_VERSION} && \
+    ./config --prefix=${OPENSSL_PREFIX}  -static --static no-shared -fPIC && \
+    make -j "$(nproc)" && \
+    make install && \
+    cd /tmp && \
+    rm -rf /tmp/openssl-${OPENSSL_VERSION}
+
 # Use the same version of libicu as the compute nodes so that
 # clusters created using inidb on pageserver can be used by computes.
 #
@@ -241,8 +233,6 @@ RUN wget -O /tmp/libicu-${ICU_VERSION}.tgz https://github.com/unicode-org/icu/re
 USER nonroot:nonroot
 WORKDIR /home/nonroot
 
-RUN echo -e "--retry-connrefused\n--connect-timeout 15\n--retry 5\n--max-time 300\n" > /home/nonroot/.curlrc
-
 # Python
 ENV PYTHON_VERSION=3.11.10 \
     PYENV_ROOT=/home/nonroot/.pyenv \
@@ -268,7 +258,7 @@ WORKDIR /home/nonroot
 
 # Rust
 # Please keep the version of llvm (installed above) in sync with rust llvm (`rustc --version --verbose | grep LLVM`)
-ENV RUSTC_VERSION=1.84.1
+ENV RUSTC_VERSION=1.84.0
 ENV RUSTUP_HOME="/home/nonroot/.rustup"
 ENV PATH="/home/nonroot/.cargo/bin:${PATH}"
 ARG RUSTFILT_VERSION=0.2.1
@@ -276,7 +266,6 @@ ARG CARGO_HAKARI_VERSION=0.9.33
 ARG CARGO_DENY_VERSION=0.16.2
 ARG CARGO_HACK_VERSION=0.6.33
 ARG CARGO_NEXTEST_VERSION=0.9.85
-ARG CARGO_DIESEL_CLI_VERSION=2.2.6
 RUN curl -sSO https://static.rust-lang.org/rustup/dist/$(uname -m)-unknown-linux-gnu/rustup-init && whoami && \
 	chmod +x rustup-init && \
 	./rustup-init -y --default-toolchain ${RUSTC_VERSION} && \
@@ -290,8 +279,6 @@ RUN curl -sSO https://static.rust-lang.org/rustup/dist/$(uname -m)-unknown-linux
     cargo install cargo-deny --locked --version ${CARGO_DENY_VERSION} && \
     cargo install cargo-hack          --version ${CARGO_HACK_VERSION} && \
     cargo install cargo-nextest       --version ${CARGO_NEXTEST_VERSION} && \
-    cargo install diesel_cli          --version ${CARGO_DIESEL_CLI_VERSION} \
-                                      --features postgres-bundled --no-default-features && \
     rm -rf /home/nonroot/.cargo/registry && \
     rm -rf /home/nonroot/.cargo/git
 

build_tools/patches/pgcopydbv017.patch

@@ -1,57 +0,0 @@
-diff --git a/src/bin/pgcopydb/copydb.c b/src/bin/pgcopydb/copydb.c
-index d730b03..69a9be9 100644
---- a/src/bin/pgcopydb/copydb.c
-+++ b/src/bin/pgcopydb/copydb.c
-@@ -44,6 +44,7 @@ GUC dstSettings[] = {
- 	{ "synchronous_commit", "'off'" },
- 	{ "statement_timeout", "0" },
- 	{ "lock_timeout", "0" },
-+	{ "idle_in_transaction_session_timeout", "0" },
- 	{ NULL, NULL },
- };
- 
-diff --git a/src/bin/pgcopydb/pgsql.c b/src/bin/pgcopydb/pgsql.c
-index 94f2f46..e051ba8 100644
---- a/src/bin/pgcopydb/pgsql.c
-+++ b/src/bin/pgcopydb/pgsql.c
-@@ -2319,6 +2319,11 @@ pgsql_execute_log_error(PGSQL *pgsql,
- 
- 	LinesBuffer lbuf = { 0 };
- 
-+	if (message != NULL){
-+		// make sure message is writable by splitLines
-+		message = strdup(message);
-+	}
-+
- 	if (!splitLines(&lbuf, message))
- 	{
- 		/* errors have already been logged */
-@@ -2332,6 +2337,7 @@ pgsql_execute_log_error(PGSQL *pgsql,
- 				  PQbackendPID(pgsql->connection),
- 				  lbuf.lines[lineNumber]);
- 	}
-+        free(message); // free copy of message we created above
- 
- 	if (pgsql->logSQL)
- 	{
-@@ -3174,11 +3180,18 @@ pgcopy_log_error(PGSQL *pgsql, PGresult *res, const char *context)
- 		/* errors have already been logged */
- 		return;
- 	}
--
- 	if (res != NULL)
- 	{
- 		char *sqlstate = PQresultErrorField(res, PG_DIAG_SQLSTATE);
--		strlcpy(pgsql->sqlstate, sqlstate, sizeof(pgsql->sqlstate));
-+		if (sqlstate == NULL)
-+		{
-+			// PQresultErrorField returned NULL!
-+			pgsql->sqlstate[0] = '\0';  // Set to an empty string to avoid segfault
-+		}
-+		else
-+		{
-+			strlcpy(pgsql->sqlstate, sqlstate, sizeof(pgsql->sqlstate));
-+		}
- 	}
- 
- 	char *endpoint =

compute/etc/pgbouncer.ini

@@ -19,8 +19,6 @@ max_prepared_statements=0
 admin_users=postgres
 unix_socket_dir=/tmp/
 unix_socket_mode=0777
-; required for pgbouncer_exporter
-ignore_startup_parameters=extra_float_digits
 
 ;; Disable connection logging. It produces a lot of logs that no one looks at,
 ;; and we can get similar log entries from the proxy too. We had incidents in

compute/patches/contrib_pg16.patch

@@ -1,242 +0,0 @@
-diff --git a/contrib/amcheck/expected/check_heap.out b/contrib/amcheck/expected/check_heap.out
-index 979e5e8..2375b45 100644
---- a/contrib/amcheck/expected/check_heap.out
-+++ b/contrib/amcheck/expected/check_heap.out
-@@ -80,12 +80,9 @@ INSERT INTO heaptest (a, b)
- -- same transaction.  The heaptest table is smaller than the default
- -- wal_skip_threshold, so a wal_level=minimal commit reads the table into
- -- shared_buffers.  A transaction delays that and excludes any autovacuum.
--SET allow_in_place_tablespaces = true;
--CREATE TABLESPACE regress_test_stats_tblspc LOCATION '';
- SELECT sum(reads) AS stats_bulkreads_before
-   FROM pg_stat_io WHERE context = 'bulkread' \gset
- BEGIN;
--ALTER TABLE heaptest SET TABLESPACE regress_test_stats_tblspc;
- -- Check that valid options are not rejected nor corruption reported
- -- for a non-empty table
- SELECT * FROM verify_heapam(relation := 'heaptest', skip := 'none');
-@@ -118,14 +115,6 @@ SELECT pg_stat_force_next_flush();
-  
- (1 row)
- 
--SELECT sum(reads) AS stats_bulkreads_after
--  FROM pg_stat_io WHERE context = 'bulkread' \gset
--SELECT :stats_bulkreads_after > :stats_bulkreads_before;
-- ?column? 
------------
-- t
--(1 row)
--
- CREATE ROLE regress_heaptest_role;
- -- verify permissions are checked (error due to function not callable)
- SET ROLE regress_heaptest_role;
-@@ -233,7 +222,6 @@ ERROR:  cannot check relation "test_foreign_table"
- DETAIL:  This operation is not supported for foreign tables.
- -- cleanup
- DROP TABLE heaptest;
--DROP TABLESPACE regress_test_stats_tblspc;
- DROP TABLE test_partition;
- DROP TABLE test_partitioned;
- DROP OWNED BY regress_heaptest_role; -- permissions
-diff --git a/contrib/amcheck/sql/check_heap.sql b/contrib/amcheck/sql/check_heap.sql
-index 1745bae..3b429c3 100644
---- a/contrib/amcheck/sql/check_heap.sql
-+++ b/contrib/amcheck/sql/check_heap.sql
-@@ -40,12 +40,9 @@ INSERT INTO heaptest (a, b)
- -- same transaction.  The heaptest table is smaller than the default
- -- wal_skip_threshold, so a wal_level=minimal commit reads the table into
- -- shared_buffers.  A transaction delays that and excludes any autovacuum.
--SET allow_in_place_tablespaces = true;
--CREATE TABLESPACE regress_test_stats_tblspc LOCATION '';
- SELECT sum(reads) AS stats_bulkreads_before
-   FROM pg_stat_io WHERE context = 'bulkread' \gset
- BEGIN;
--ALTER TABLE heaptest SET TABLESPACE regress_test_stats_tblspc;
- -- Check that valid options are not rejected nor corruption reported
- -- for a non-empty table
- SELECT * FROM verify_heapam(relation := 'heaptest', skip := 'none');
-@@ -58,9 +55,6 @@ COMMIT;
- --   ALTER TABLE ... SET TABLESPACE ...
- -- causing an additional bulkread, which should be reflected in pg_stat_io.
- SELECT pg_stat_force_next_flush();
--SELECT sum(reads) AS stats_bulkreads_after
--  FROM pg_stat_io WHERE context = 'bulkread' \gset
--SELECT :stats_bulkreads_after > :stats_bulkreads_before;
- 
- CREATE ROLE regress_heaptest_role;
- 
-@@ -140,7 +134,6 @@ SELECT * FROM verify_heapam('test_foreign_table',
- 
- -- cleanup
- DROP TABLE heaptest;
--DROP TABLESPACE regress_test_stats_tblspc;
- DROP TABLE test_partition;
- DROP TABLE test_partitioned;
- DROP OWNED BY regress_heaptest_role; -- permissions
-diff --git a/contrib/citext/expected/create_index_acl.out b/contrib/citext/expected/create_index_acl.out
-index 33be13a..70a406c 100644
---- a/contrib/citext/expected/create_index_acl.out
-+++ b/contrib/citext/expected/create_index_acl.out
-@@ -5,9 +5,6 @@
- -- owner having as few applicable privileges as possible.  (The privileges.sql
- -- regress_sro_user tests look for the opposite defect; they confirm that
- -- DefineIndex() uses the table owner userid where necessary.)
--SET allow_in_place_tablespaces = true;
--CREATE TABLESPACE regress_create_idx_tblspace LOCATION '';
--RESET allow_in_place_tablespaces;
- BEGIN;
- CREATE ROLE regress_minimal;
- CREATE SCHEMA s;
-@@ -49,11 +46,9 @@ ALTER TABLE s.x OWNER TO regress_minimal;
- -- Empty-table DefineIndex()
- CREATE UNIQUE INDEX u0rows ON s.x USING btree
-   ((s.index_this_expr(y, s.const())) COLLATE s.coll s.citext_pattern_ops)
--  TABLESPACE regress_create_idx_tblspace
-   WHERE s.index_row_if(y);
- ALTER TABLE s.x ADD CONSTRAINT e0rows EXCLUDE USING btree
-   ((s.index_this_expr(y, s.const())) COLLATE s.coll WITH s.=)
--  USING INDEX TABLESPACE regress_create_idx_tblspace
-   WHERE (s.index_row_if(y));
- -- Make the table nonempty.
- INSERT INTO s.x VALUES ('foo'), ('bar');
-@@ -66,11 +61,9 @@ RESET search_path;
- GRANT EXECUTE ON FUNCTION s.index_this_expr TO regress_minimal;
- CREATE UNIQUE INDEX u2rows ON s.x USING btree
-   ((s.index_this_expr(y, s.const())) COLLATE s.coll s.citext_pattern_ops)
--  TABLESPACE regress_create_idx_tblspace
-   WHERE s.index_row_if(y);
- ALTER TABLE s.x ADD CONSTRAINT e2rows EXCLUDE USING btree
-   ((s.index_this_expr(y, s.const())) COLLATE s.coll WITH s.=)
--  USING INDEX TABLESPACE regress_create_idx_tblspace
-   WHERE (s.index_row_if(y));
- -- Shall not find s.coll via search_path, despite the s.const->public.setter
- -- call having set search_path=s during expression planning.  Suppress the
-@@ -78,9 +71,7 @@ ALTER TABLE s.x ADD CONSTRAINT e2rows EXCLUDE USING btree
- \set VERBOSITY sqlstate
- ALTER TABLE s.x ADD CONSTRAINT underqualified EXCLUDE USING btree
-   ((s.index_this_expr(y, s.const())) COLLATE coll WITH s.=)
--  USING INDEX TABLESPACE regress_create_idx_tblspace
-   WHERE (s.index_row_if(y));
- ERROR:  42704
- \set VERBOSITY default
- ROLLBACK;
--DROP TABLESPACE regress_create_idx_tblspace;
-diff --git a/contrib/citext/sql/create_index_acl.sql b/contrib/citext/sql/create_index_acl.sql
-index 10b5225..ae442e1 100644
---- a/contrib/citext/sql/create_index_acl.sql
-+++ b/contrib/citext/sql/create_index_acl.sql
-@@ -6,10 +6,6 @@
- -- regress_sro_user tests look for the opposite defect; they confirm that
- -- DefineIndex() uses the table owner userid where necessary.)
- 
--SET allow_in_place_tablespaces = true;
--CREATE TABLESPACE regress_create_idx_tblspace LOCATION '';
--RESET allow_in_place_tablespaces;
--
- BEGIN;
- CREATE ROLE regress_minimal;
- CREATE SCHEMA s;
-@@ -51,11 +47,9 @@ ALTER TABLE s.x OWNER TO regress_minimal;
- -- Empty-table DefineIndex()
- CREATE UNIQUE INDEX u0rows ON s.x USING btree
-   ((s.index_this_expr(y, s.const())) COLLATE s.coll s.citext_pattern_ops)
--  TABLESPACE regress_create_idx_tblspace
-   WHERE s.index_row_if(y);
- ALTER TABLE s.x ADD CONSTRAINT e0rows EXCLUDE USING btree
-   ((s.index_this_expr(y, s.const())) COLLATE s.coll WITH s.=)
--  USING INDEX TABLESPACE regress_create_idx_tblspace
-   WHERE (s.index_row_if(y));
- -- Make the table nonempty.
- INSERT INTO s.x VALUES ('foo'), ('bar');
-@@ -68,11 +62,9 @@ RESET search_path;
- GRANT EXECUTE ON FUNCTION s.index_this_expr TO regress_minimal;
- CREATE UNIQUE INDEX u2rows ON s.x USING btree
-   ((s.index_this_expr(y, s.const())) COLLATE s.coll s.citext_pattern_ops)
--  TABLESPACE regress_create_idx_tblspace
-   WHERE s.index_row_if(y);
- ALTER TABLE s.x ADD CONSTRAINT e2rows EXCLUDE USING btree
-   ((s.index_this_expr(y, s.const())) COLLATE s.coll WITH s.=)
--  USING INDEX TABLESPACE regress_create_idx_tblspace
-   WHERE (s.index_row_if(y));
- -- Shall not find s.coll via search_path, despite the s.const->public.setter
- -- call having set search_path=s during expression planning.  Suppress the
-@@ -80,9 +72,7 @@ ALTER TABLE s.x ADD CONSTRAINT e2rows EXCLUDE USING btree
- \set VERBOSITY sqlstate
- ALTER TABLE s.x ADD CONSTRAINT underqualified EXCLUDE USING btree
-   ((s.index_this_expr(y, s.const())) COLLATE coll WITH s.=)
--  USING INDEX TABLESPACE regress_create_idx_tblspace
-   WHERE (s.index_row_if(y));
- \set VERBOSITY default
- ROLLBACK;
- 
--DROP TABLESPACE regress_create_idx_tblspace;
-diff --git a/contrib/file_fdw/expected/file_fdw.out b/contrib/file_fdw/expected/file_fdw.out
-index 72304e0..ebe131b 100644
---- a/contrib/file_fdw/expected/file_fdw.out
-+++ b/contrib/file_fdw/expected/file_fdw.out
-@@ -4,6 +4,7 @@
- -- directory paths are passed to us in environment variables
- \getenv abs_srcdir PG_ABS_SRCDIR
- -- Clean up in case a prior regression run failed
-+SET compute_query_id TO 'off';
- SET client_min_messages TO 'warning';
- DROP ROLE IF EXISTS regress_file_fdw_superuser, regress_file_fdw_user, regress_no_priv_user;
- RESET client_min_messages;
-diff --git a/contrib/file_fdw/sql/file_fdw.sql b/contrib/file_fdw/sql/file_fdw.sql
-index f0548e1..848a08c 100644
---- a/contrib/file_fdw/sql/file_fdw.sql
-+++ b/contrib/file_fdw/sql/file_fdw.sql
-@@ -6,6 +6,7 @@
- \getenv abs_srcdir PG_ABS_SRCDIR
- 
- -- Clean up in case a prior regression run failed
-+SET compute_query_id TO 'off';
- SET client_min_messages TO 'warning';
- DROP ROLE IF EXISTS regress_file_fdw_superuser, regress_file_fdw_user, regress_no_priv_user;
- RESET client_min_messages;
-diff --git a/contrib/pageinspect/expected/gist.out b/contrib/pageinspect/expected/gist.out
-index d1adbab..38b52ac 100644
---- a/contrib/pageinspect/expected/gist.out
-+++ b/contrib/pageinspect/expected/gist.out
-@@ -10,25 +10,6 @@ BEGIN;
- CREATE TABLE test_gist AS SELECT point(i,i) p, i::text t FROM
-     generate_series(1,1000) i;
- CREATE INDEX test_gist_idx ON test_gist USING gist (p);
---- Page 0 is the root, the rest are leaf pages
--SELECT * FROM gist_page_opaque_info(get_raw_page('test_gist_idx', 0));
-- lsn | nsn | rightlink  | flags 
-------+-----+------------+-------
-- 0/1 | 0/0 | 4294967295 | {}
--(1 row)
--
--SELECT * FROM gist_page_opaque_info(get_raw_page('test_gist_idx', 1));
-- lsn | nsn | rightlink  | flags  
-------+-----+------------+--------
-- 0/1 | 0/0 | 4294967295 | {leaf}
--(1 row)
--
--SELECT * FROM gist_page_opaque_info(get_raw_page('test_gist_idx', 2));
-- lsn | nsn | rightlink | flags  
-------+-----+-----------+--------
-- 0/1 | 0/0 |         1 | {leaf}
--(1 row)
--
- COMMIT;
- SELECT * FROM gist_page_items(get_raw_page('test_gist_idx', 0), 'test_gist_idx');
-  itemoffset |   ctid    | itemlen | dead |             keys              
-diff --git a/contrib/pageinspect/sql/gist.sql b/contrib/pageinspect/sql/gist.sql
-index d263542..607992f 100644
---- a/contrib/pageinspect/sql/gist.sql
-+++ b/contrib/pageinspect/sql/gist.sql
-@@ -12,11 +12,6 @@ CREATE TABLE test_gist AS SELECT point(i,i) p, i::text t FROM
-     generate_series(1,1000) i;
- CREATE INDEX test_gist_idx ON test_gist USING gist (p);
- 
---- Page 0 is the root, the rest are leaf pages
--SELECT * FROM gist_page_opaque_info(get_raw_page('test_gist_idx', 0));
--SELECT * FROM gist_page_opaque_info(get_raw_page('test_gist_idx', 1));
--SELECT * FROM gist_page_opaque_info(get_raw_page('test_gist_idx', 2));
--
- COMMIT;
- 
- SELECT * FROM gist_page_items(get_raw_page('test_gist_idx', 0), 'test_gist_idx');

compute/patches/contrib_pg17.patch

@@ -1,196 +0,0 @@
-diff --git a/contrib/amcheck/expected/check_heap.out b/contrib/amcheck/expected/check_heap.out
-index 979e5e8..2375b45 100644
---- a/contrib/amcheck/expected/check_heap.out
-+++ b/contrib/amcheck/expected/check_heap.out
-@@ -80,12 +80,9 @@ INSERT INTO heaptest (a, b)
- -- same transaction.  The heaptest table is smaller than the default
- -- wal_skip_threshold, so a wal_level=minimal commit reads the table into
- -- shared_buffers.  A transaction delays that and excludes any autovacuum.
--SET allow_in_place_tablespaces = true;
--CREATE TABLESPACE regress_test_stats_tblspc LOCATION '';
- SELECT sum(reads) AS stats_bulkreads_before
-   FROM pg_stat_io WHERE context = 'bulkread' \gset
- BEGIN;
--ALTER TABLE heaptest SET TABLESPACE regress_test_stats_tblspc;
- -- Check that valid options are not rejected nor corruption reported
- -- for a non-empty table
- SELECT * FROM verify_heapam(relation := 'heaptest', skip := 'none');
-@@ -118,14 +115,6 @@ SELECT pg_stat_force_next_flush();
-  
- (1 row)
- 
--SELECT sum(reads) AS stats_bulkreads_after
--  FROM pg_stat_io WHERE context = 'bulkread' \gset
--SELECT :stats_bulkreads_after > :stats_bulkreads_before;
-- ?column? 
------------
-- t
--(1 row)
--
- CREATE ROLE regress_heaptest_role;
- -- verify permissions are checked (error due to function not callable)
- SET ROLE regress_heaptest_role;
-@@ -233,7 +222,6 @@ ERROR:  cannot check relation "test_foreign_table"
- DETAIL:  This operation is not supported for foreign tables.
- -- cleanup
- DROP TABLE heaptest;
--DROP TABLESPACE regress_test_stats_tblspc;
- DROP TABLE test_partition;
- DROP TABLE test_partitioned;
- DROP OWNED BY regress_heaptest_role; -- permissions
-diff --git a/contrib/amcheck/sql/check_heap.sql b/contrib/amcheck/sql/check_heap.sql
-index 1745bae..3b429c3 100644
---- a/contrib/amcheck/sql/check_heap.sql
-+++ b/contrib/amcheck/sql/check_heap.sql
-@@ -40,12 +40,9 @@ INSERT INTO heaptest (a, b)
- -- same transaction.  The heaptest table is smaller than the default
- -- wal_skip_threshold, so a wal_level=minimal commit reads the table into
- -- shared_buffers.  A transaction delays that and excludes any autovacuum.
--SET allow_in_place_tablespaces = true;
--CREATE TABLESPACE regress_test_stats_tblspc LOCATION '';
- SELECT sum(reads) AS stats_bulkreads_before
-   FROM pg_stat_io WHERE context = 'bulkread' \gset
- BEGIN;
--ALTER TABLE heaptest SET TABLESPACE regress_test_stats_tblspc;
- -- Check that valid options are not rejected nor corruption reported
- -- for a non-empty table
- SELECT * FROM verify_heapam(relation := 'heaptest', skip := 'none');
-@@ -58,9 +55,6 @@ COMMIT;
- --   ALTER TABLE ... SET TABLESPACE ...
- -- causing an additional bulkread, which should be reflected in pg_stat_io.
- SELECT pg_stat_force_next_flush();
--SELECT sum(reads) AS stats_bulkreads_after
--  FROM pg_stat_io WHERE context = 'bulkread' \gset
--SELECT :stats_bulkreads_after > :stats_bulkreads_before;
- 
- CREATE ROLE regress_heaptest_role;
- 
-@@ -140,7 +134,6 @@ SELECT * FROM verify_heapam('test_foreign_table',
- 
- -- cleanup
- DROP TABLE heaptest;
--DROP TABLESPACE regress_test_stats_tblspc;
- DROP TABLE test_partition;
- DROP TABLE test_partitioned;
- DROP OWNED BY regress_heaptest_role; -- permissions
-diff --git a/contrib/citext/expected/create_index_acl.out b/contrib/citext/expected/create_index_acl.out
-index 33be13a..70a406c 100644
---- a/contrib/citext/expected/create_index_acl.out
-+++ b/contrib/citext/expected/create_index_acl.out
-@@ -5,9 +5,6 @@
- -- owner having as few applicable privileges as possible.  (The privileges.sql
- -- regress_sro_user tests look for the opposite defect; they confirm that
- -- DefineIndex() uses the table owner userid where necessary.)
--SET allow_in_place_tablespaces = true;
--CREATE TABLESPACE regress_create_idx_tblspace LOCATION '';
--RESET allow_in_place_tablespaces;
- BEGIN;
- CREATE ROLE regress_minimal;
- CREATE SCHEMA s;
-@@ -49,11 +46,9 @@ ALTER TABLE s.x OWNER TO regress_minimal;
- -- Empty-table DefineIndex()
- CREATE UNIQUE INDEX u0rows ON s.x USING btree
-   ((s.index_this_expr(y, s.const())) COLLATE s.coll s.citext_pattern_ops)
--  TABLESPACE regress_create_idx_tblspace
-   WHERE s.index_row_if(y);
- ALTER TABLE s.x ADD CONSTRAINT e0rows EXCLUDE USING btree
-   ((s.index_this_expr(y, s.const())) COLLATE s.coll WITH s.=)
--  USING INDEX TABLESPACE regress_create_idx_tblspace
-   WHERE (s.index_row_if(y));
- -- Make the table nonempty.
- INSERT INTO s.x VALUES ('foo'), ('bar');
-@@ -66,11 +61,9 @@ RESET search_path;
- GRANT EXECUTE ON FUNCTION s.index_this_expr TO regress_minimal;
- CREATE UNIQUE INDEX u2rows ON s.x USING btree
-   ((s.index_this_expr(y, s.const())) COLLATE s.coll s.citext_pattern_ops)
--  TABLESPACE regress_create_idx_tblspace
-   WHERE s.index_row_if(y);
- ALTER TABLE s.x ADD CONSTRAINT e2rows EXCLUDE USING btree
-   ((s.index_this_expr(y, s.const())) COLLATE s.coll WITH s.=)
--  USING INDEX TABLESPACE regress_create_idx_tblspace
-   WHERE (s.index_row_if(y));
- -- Shall not find s.coll via search_path, despite the s.const->public.setter
- -- call having set search_path=s during expression planning.  Suppress the
-@@ -78,9 +71,7 @@ ALTER TABLE s.x ADD CONSTRAINT e2rows EXCLUDE USING btree
- \set VERBOSITY sqlstate
- ALTER TABLE s.x ADD CONSTRAINT underqualified EXCLUDE USING btree
-   ((s.index_this_expr(y, s.const())) COLLATE coll WITH s.=)
--  USING INDEX TABLESPACE regress_create_idx_tblspace
-   WHERE (s.index_row_if(y));
- ERROR:  42704
- \set VERBOSITY default
- ROLLBACK;
--DROP TABLESPACE regress_create_idx_tblspace;
-diff --git a/contrib/citext/sql/create_index_acl.sql b/contrib/citext/sql/create_index_acl.sql
-index 10b5225..ae442e1 100644
---- a/contrib/citext/sql/create_index_acl.sql
-+++ b/contrib/citext/sql/create_index_acl.sql
-@@ -6,10 +6,6 @@
- -- regress_sro_user tests look for the opposite defect; they confirm that
- -- DefineIndex() uses the table owner userid where necessary.)
- 
--SET allow_in_place_tablespaces = true;
--CREATE TABLESPACE regress_create_idx_tblspace LOCATION '';
--RESET allow_in_place_tablespaces;
--
- BEGIN;
- CREATE ROLE regress_minimal;
- CREATE SCHEMA s;
-@@ -51,11 +47,9 @@ ALTER TABLE s.x OWNER TO regress_minimal;
- -- Empty-table DefineIndex()
- CREATE UNIQUE INDEX u0rows ON s.x USING btree
-   ((s.index_this_expr(y, s.const())) COLLATE s.coll s.citext_pattern_ops)
--  TABLESPACE regress_create_idx_tblspace
-   WHERE s.index_row_if(y);
- ALTER TABLE s.x ADD CONSTRAINT e0rows EXCLUDE USING btree
-   ((s.index_this_expr(y, s.const())) COLLATE s.coll WITH s.=)
--  USING INDEX TABLESPACE regress_create_idx_tblspace
-   WHERE (s.index_row_if(y));
- -- Make the table nonempty.
- INSERT INTO s.x VALUES ('foo'), ('bar');
-@@ -68,11 +62,9 @@ RESET search_path;
- GRANT EXECUTE ON FUNCTION s.index_this_expr TO regress_minimal;
- CREATE UNIQUE INDEX u2rows ON s.x USING btree
-   ((s.index_this_expr(y, s.const())) COLLATE s.coll s.citext_pattern_ops)
--  TABLESPACE regress_create_idx_tblspace
-   WHERE s.index_row_if(y);
- ALTER TABLE s.x ADD CONSTRAINT e2rows EXCLUDE USING btree
-   ((s.index_this_expr(y, s.const())) COLLATE s.coll WITH s.=)
--  USING INDEX TABLESPACE regress_create_idx_tblspace
-   WHERE (s.index_row_if(y));
- -- Shall not find s.coll via search_path, despite the s.const->public.setter
- -- call having set search_path=s during expression planning.  Suppress the
-@@ -80,9 +72,7 @@ ALTER TABLE s.x ADD CONSTRAINT e2rows EXCLUDE USING btree
- \set VERBOSITY sqlstate
- ALTER TABLE s.x ADD CONSTRAINT underqualified EXCLUDE USING btree
-   ((s.index_this_expr(y, s.const())) COLLATE coll WITH s.=)
--  USING INDEX TABLESPACE regress_create_idx_tblspace
-   WHERE (s.index_row_if(y));
- \set VERBOSITY default
- ROLLBACK;
- 
--DROP TABLESPACE regress_create_idx_tblspace;
-diff --git a/contrib/file_fdw/expected/file_fdw.out b/contrib/file_fdw/expected/file_fdw.out
-index 86c148a..81bdb2c 100644
---- a/contrib/file_fdw/expected/file_fdw.out
-+++ b/contrib/file_fdw/expected/file_fdw.out
-@@ -4,6 +4,7 @@
- -- directory paths are passed to us in environment variables
- \getenv abs_srcdir PG_ABS_SRCDIR
- -- Clean up in case a prior regression run failed
-+SET compute_query_id TO 'off';
- SET client_min_messages TO 'warning';
- DROP ROLE IF EXISTS regress_file_fdw_superuser, regress_file_fdw_user, regress_no_priv_user;
- RESET client_min_messages;
-diff --git a/contrib/file_fdw/sql/file_fdw.sql b/contrib/file_fdw/sql/file_fdw.sql
-index f0548e1..848a08c 100644
---- a/contrib/file_fdw/sql/file_fdw.sql
-+++ b/contrib/file_fdw/sql/file_fdw.sql
-@@ -6,6 +6,7 @@
- \getenv abs_srcdir PG_ABS_SRCDIR
- 
- -- Clean up in case a prior regression run failed
-+SET compute_query_id TO 'off';
- SET client_min_messages TO 'warning';
- DROP ROLE IF EXISTS regress_file_fdw_superuser, regress_file_fdw_user, regress_no_priv_user;
- RESET client_min_messages;

compute/patches/pg_graphql.patch

@@ -1,19 +0,0 @@
-commit ec6a491d126882966a696f9ad5d3698935361d55
-Author: Alexey Masterov <alexeymasterov@neon.tech>
-Date:   Tue Dec 17 10:25:00 2024 +0100
-
-    Changes required to run tests on Neon
-
-diff --git a/test/expected/permissions_functions.out b/test/expected/permissions_functions.out
-index 1e9fbc2..94cbe25 100644
---- a/test/expected/permissions_functions.out
-+++ b/test/expected/permissions_functions.out
-@@ -64,7 +64,7 @@ begin;
-     select current_user;
-  current_user 
- --------------
-- postgres
-+ cloud_admin
- (1 row)
- 
-     -- revoke default access from the public role for new functions

compute/patches/pgvector.patch

@@ -1,24 +1,8 @@
-diff --git a/Makefile b/Makefile
-index 7a4b88c..56678af 100644
---- a/Makefile
-+++ b/Makefile
-@@ -3,7 +3,10 @@ EXTVERSION = 0.8.0
- 
- MODULE_big = vector
- DATA = $(wildcard sql/*--*--*.sql)
--DATA_built = sql/$(EXTENSION)--$(EXTVERSION).sql
-+# This change is needed to install different per-version SQL files
-+# like pgvector--0.8.0.sql and pgvector--0.7.4.sql
-+# The corresponding file is downloaded during the Docker image build process
-+DATA_built = sql/$(EXTENSION)--$(EXTVERSION).sql sql/vector--0.7.4.sql
- OBJS = src/bitutils.o src/bitvec.o src/halfutils.o src/halfvec.o src/hnsw.o src/hnswbuild.o src/hnswinsert.o src/hnswscan.o src/hnswutils.o src/hnswvacuum.o src/ivfbuild.o src/ivfflat.o src/ivfinsert.o src/ivfkmeans.o src/ivfscan.o src/ivfutils.o src/ivfvacuum.o src/sparsevec.o src/vector.o
- HEADERS = src/halfvec.h src/sparsevec.h src/vector.h
- 
 diff --git a/src/hnswbuild.c b/src/hnswbuild.c
-index b667478..fc1897c 100644
+index dcfb2bd..d5189ee 100644
 --- a/src/hnswbuild.c
 +++ b/src/hnswbuild.c
-@@ -843,9 +843,17 @@ HnswParallelBuildMain(dsm_segment *seg, shm_toc *toc)
+@@ -860,9 +860,17 @@ HnswParallelBuildMain(dsm_segment *seg, shm_toc *toc)
  
  	hnswarea = shm_toc_lookup(toc, PARALLEL_KEY_HNSW_AREA, false);
  
@@ -36,7 +20,7 @@ index b667478..fc1897c 100644
  	/* Close relations within worker */
  	index_close(indexRel, indexLockmode);
  	table_close(heapRel, heapLockmode);
-@@ -1100,12 +1108,38 @@ BuildIndex(Relation heap, Relation index, IndexInfo *indexInfo,
+@@ -1117,12 +1125,38 @@ BuildIndex(Relation heap, Relation index, IndexInfo *indexInfo,
  	SeedRandom(42);
  #endif
  

compute/vm-image-spec-bookworm.yaml

@@ -27,10 +27,6 @@ commands:
     user: nobody
     sysvInitAction: respawn
     shell: 'DATA_SOURCE_NAME="user=cloud_admin sslmode=disable dbname=postgres application_name=postgres-exporter" /bin/postgres_exporter --config.file=/etc/postgres_exporter.yml'
-  - name: pgbouncer-exporter
-    user: postgres
-    sysvInitAction: respawn
-    shell: '/bin/pgbouncer_exporter --pgBouncer.connectionString="postgres:///pgbouncer?host=/tmp&port=6432&dbname=pgbouncer&user=pgbouncer"'
   - name: sql-exporter
     user: nobody
     sysvInitAction: respawn
@@ -47,9 +43,7 @@ files:
       # Allow postgres user (which is what compute_ctl runs as) to run /neonvm/bin/resize-swap
       # and /neonvm/bin/set-disk-quota as root without requiring entering a password (NOPASSWD),
       # regardless of hostname (ALL)
-      #
-      # Also allow it to shut down the VM. The fast_import job does that when it's finished.
-      postgres ALL=(root) NOPASSWD: /neonvm/bin/resize-swap, /neonvm/bin/set-disk-quota, /neonvm/bin/poweroff
+      postgres ALL=(root) NOPASSWD: /neonvm/bin/resize-swap, /neonvm/bin/set-disk-quota
   - filename: cgconfig.conf
     content: |
       # Configuration for cgroups in VM compute nodes

compute/vm-image-spec-bullseye.yaml

@@ -27,10 +27,6 @@ commands:
     user: nobody
     sysvInitAction: respawn
     shell: 'DATA_SOURCE_NAME="user=cloud_admin sslmode=disable dbname=postgres application_name=postgres-exporter" /bin/postgres_exporter --config.file=/etc/postgres_exporter.yml'
-  - name: pgbouncer-exporter
-    user: postgres
-    sysvInitAction: respawn
-    shell: '/bin/pgbouncer_exporter --pgBouncer.connectionString="postgres:///pgbouncer?host=/tmp&port=6432&dbname=pgbouncer&user=pgbouncer"'
   - name: sql-exporter
     user: nobody
     sysvInitAction: respawn

compute_tools/Cargo.toml

@@ -51,7 +51,6 @@ tracing-subscriber.workspace = true
 tracing-utils.workspace = true
 thiserror.workspace = true
 url.workspace = true
-uuid.workspace = true
 prometheus.workspace = true
 
 postgres_initdb.workspace = true

compute_tools/src/bin/compute_ctl.rs

@@ -34,19 +34,17 @@
 //!             -r http://pg-ext-s3-gateway \
 //! ```
 use std::collections::HashMap;
-use std::ffi::OsString;
 use std::fs::File;
 use std::path::Path;
 use std::process::exit;
 use std::str::FromStr;
 use std::sync::atomic::Ordering;
 use std::sync::{mpsc, Arc, Condvar, Mutex, RwLock};
-use std::time::SystemTime;
 use std::{thread, time::Duration};
 
 use anyhow::{Context, Result};
 use chrono::Utc;
-use clap::Parser;
+use clap::Arg;
 use compute_tools::disk_quota::set_disk_quota;
 use compute_tools::lsn_lease::launch_lsn_lease_bg_task_for_static;
 use signal_hook::consts::{SIGQUIT, SIGTERM};
@@ -75,89 +73,11 @@ use utils::failpoint_support;
 // in-case of not-set environment var
 const BUILD_TAG_DEFAULT: &str = "latest";
 
-// Compatibility hack: if the control plane specified any remote-ext-config
-// use the default value for extension storage proxy gateway.
-// Remove this once the control plane is updated to pass the gateway URL
-fn parse_remote_ext_config(arg: &str) -> Result<String> {
-    if arg.starts_with("http") {
-        Ok(arg.trim_end_matches('/').to_string())
-    } else {
-        Ok("http://pg-ext-s3-gateway".to_string())
-    }
-}
-
-/// Generate a compute ID if one is not supplied. This exists to keep forward
-/// compatibility tests working, but will be removed in a future iteration.
-fn generate_compute_id() -> String {
-    let now = SystemTime::now();
-
-    format!(
-        "compute-{}",
-        now.duration_since(SystemTime::UNIX_EPOCH)
-            .unwrap()
-            .as_secs()
-    )
-}
-
-#[derive(Parser)]
-#[command(rename_all = "kebab-case")]
-struct Cli {
-    #[arg(short = 'b', long, default_value = "postgres", env = "POSTGRES_PATH")]
-    pub pgbin: String,
-
-    #[arg(short = 'r', long, value_parser = parse_remote_ext_config)]
-    pub remote_ext_config: Option<String>,
-
-    #[arg(long, default_value_t = 3080)]
-    pub http_port: u16,
-
-    #[arg(short = 'D', long, value_name = "DATADIR")]
-    pub pgdata: String,
-
-    #[arg(short = 'C', long, value_name = "DATABASE_URL")]
-    pub connstr: String,
-
-    #[cfg(target_os = "linux")]
-    #[arg(long, default_value = "neon-postgres")]
-    pub cgroup: String,
-
-    #[cfg(target_os = "linux")]
-    #[arg(
-        long,
-        default_value = "host=localhost port=5432 dbname=postgres user=cloud_admin sslmode=disable application_name=vm-monitor"
-    )]
-    pub filecache_connstr: String,
-
-    #[cfg(target_os = "linux")]
-    #[arg(long, default_value = "0.0.0.0:10301")]
-    pub vm_monitor_addr: String,
-
-    #[arg(long, action = clap::ArgAction::SetTrue)]
-    pub resize_swap_on_bind: bool,
-
-    #[arg(long)]
-    pub set_disk_quota_for_fs: Option<String>,
-
-    #[arg(short = 's', long = "spec", group = "spec")]
-    pub spec_json: Option<String>,
-
-    #[arg(short = 'S', long, group = "spec-path")]
-    pub spec_path: Option<OsString>,
-
-    #[arg(short = 'i', long, group = "compute-id", default_value = generate_compute_id())]
-    pub compute_id: String,
-
-    #[arg(short = 'p', long, conflicts_with_all = ["spec", "spec-path"], value_name = "CONTROL_PLANE_API_BASE_URL")]
-    pub control_plane_uri: Option<String>,
-}
-
 fn main() -> Result<()> {
-    let cli = Cli::parse();
-
-    let build_tag = init()?;
-
     let scenario = failpoint_support::init();
 
+    let (build_tag, clap_args) = init()?;
+
     // enable core dumping for all child processes
     setrlimit(Resource::CORE, rlimit::INFINITY, rlimit::INFINITY)?;
 
@@ -165,11 +85,13 @@ fn main() -> Result<()> {
         // Enter startup tracing context
         let _startup_context_guard = startup_context_from_env();
 
-        let cli_spec = try_spec_from_cli(&cli)?;
+        let cli_args = process_cli(&clap_args)?;
 
-        let compute = wait_spec(build_tag, &cli, cli_spec)?;
+        let cli_spec = try_spec_from_cli(&clap_args, &cli_args)?;
 
-        start_postgres(&cli, compute)?
+        let wait_spec_result = wait_spec(build_tag, cli_args, cli_spec)?;
+
+        start_postgres(&clap_args, wait_spec_result)?
 
         // Startup is finished, exit the startup tracing span
     };
@@ -186,7 +108,7 @@ fn main() -> Result<()> {
     deinit_and_exit(wait_pg_result);
 }
 
-fn init() -> Result<String> {
+fn init() -> Result<(String, clap::ArgMatches)> {
     init_tracing_and_logging(DEFAULT_LOG_LEVEL)?;
 
     let mut signals = Signals::new([SIGINT, SIGTERM, SIGQUIT])?;
@@ -201,7 +123,66 @@ fn init() -> Result<String> {
         .to_string();
     info!("build_tag: {build_tag}");
 
-    Ok(build_tag)
+    Ok((build_tag, cli().get_matches()))
+}
+
+fn process_cli(matches: &clap::ArgMatches) -> Result<ProcessCliResult> {
+    let pgbin_default = "postgres";
+    let pgbin = matches
+        .get_one::<String>("pgbin")
+        .map(|s| s.as_str())
+        .unwrap_or(pgbin_default);
+
+    let ext_remote_storage = matches
+        .get_one::<String>("remote-ext-config")
+        // Compatibility hack: if the control plane specified any remote-ext-config
+        // use the default value for extension storage proxy gateway.
+        // Remove this once the control plane is updated to pass the gateway URL
+        .map(|conf| {
+            if conf.starts_with("http") {
+                conf.trim_end_matches('/')
+            } else {
+                "http://pg-ext-s3-gateway"
+            }
+        });
+
+    let http_port = *matches
+        .get_one::<u16>("http-port")
+        .expect("http-port is required");
+    let pgdata = matches
+        .get_one::<String>("pgdata")
+        .expect("PGDATA path is required");
+    let connstr = matches
+        .get_one::<String>("connstr")
+        .expect("Postgres connection string is required");
+    let spec_json = matches.get_one::<String>("spec");
+    let spec_path = matches.get_one::<String>("spec-path");
+    let resize_swap_on_bind = matches.get_flag("resize-swap-on-bind");
+    let set_disk_quota_for_fs = matches.get_one::<String>("set-disk-quota-for-fs");
+
+    Ok(ProcessCliResult {
+        connstr,
+        pgdata,
+        pgbin,
+        ext_remote_storage,
+        http_port,
+        spec_json,
+        spec_path,
+        resize_swap_on_bind,
+        set_disk_quota_for_fs,
+    })
+}
+
+struct ProcessCliResult<'clap> {
+    connstr: &'clap str,
+    pgdata: &'clap str,
+    pgbin: &'clap str,
+    ext_remote_storage: Option<&'clap str>,
+    http_port: u16,
+    spec_json: Option<&'clap String>,
+    spec_path: Option<&'clap String>,
+    resize_swap_on_bind: bool,
+    set_disk_quota_for_fs: Option<&'clap String>,
 }
 
 fn startup_context_from_env() -> Option<opentelemetry::ContextGuard> {
@@ -254,9 +235,19 @@ fn startup_context_from_env() -> Option<opentelemetry::ContextGuard> {
     }
 }
 
-fn try_spec_from_cli(cli: &Cli) -> Result<CliSpecParams> {
+fn try_spec_from_cli(
+    matches: &clap::ArgMatches,
+    ProcessCliResult {
+        spec_json,
+        spec_path,
+        ..
+    }: &ProcessCliResult,
+) -> Result<CliSpecParams> {
+    let compute_id = matches.get_one::<String>("compute-id");
+    let control_plane_uri = matches.get_one::<String>("control-plane-uri");
+
     // First, try to get cluster spec from the cli argument
-    if let Some(ref spec_json) = cli.spec_json {
+    if let Some(spec_json) = spec_json {
         info!("got spec from cli argument {}", spec_json);
         return Ok(CliSpecParams {
             spec: Some(serde_json::from_str(spec_json)?),
@@ -265,7 +256,7 @@ fn try_spec_from_cli(cli: &Cli) -> Result<CliSpecParams> {
     }
 
     // Second, try to read it from the file if path is provided
-    if let Some(ref spec_path) = cli.spec_path {
+    if let Some(spec_path) = spec_path {
         let file = File::open(Path::new(spec_path))?;
         return Ok(CliSpecParams {
             spec: Some(serde_json::from_reader(file)?),
@@ -273,11 +264,17 @@ fn try_spec_from_cli(cli: &Cli) -> Result<CliSpecParams> {
         });
     }
 
-    if cli.control_plane_uri.is_none() {
-        panic!("must specify --control-plane-uri");
+    let Some(compute_id) = compute_id else {
+        panic!(
+            "compute spec should be provided by one of the following ways: \
+                --spec OR --spec-path OR --control-plane-uri and --compute-id"
+        );
+    };
+    let Some(control_plane_uri) = control_plane_uri else {
+        panic!("must specify both --control-plane-uri and --compute-id or none");
     };
 
-    match get_spec_from_control_plane(cli.control_plane_uri.as_ref().unwrap(), &cli.compute_id) {
+    match get_spec_from_control_plane(control_plane_uri, compute_id) {
         Ok(spec) => Ok(CliSpecParams {
             spec,
             live_config_allowed: true,
@@ -301,12 +298,21 @@ struct CliSpecParams {
 
 fn wait_spec(
     build_tag: String,
-    cli: &Cli,
+    ProcessCliResult {
+        connstr,
+        pgdata,
+        pgbin,
+        ext_remote_storage,
+        resize_swap_on_bind,
+        set_disk_quota_for_fs,
+        http_port,
+        ..
+    }: ProcessCliResult,
     CliSpecParams {
         spec,
         live_config_allowed,
     }: CliSpecParams,
-) -> Result<Arc<ComputeNode>> {
+) -> Result<WaitSpecResult> {
     let mut new_state = ComputeState::new();
     let spec_set;
 
@@ -318,24 +324,23 @@ fn wait_spec(
     } else {
         spec_set = false;
     }
-    let connstr = Url::parse(&cli.connstr).context("cannot parse connstr as a URL")?;
+    let connstr = Url::parse(connstr).context("cannot parse connstr as a URL")?;
     let conn_conf = postgres::config::Config::from_str(connstr.as_str())
         .context("cannot build postgres config from connstr")?;
     let tokio_conn_conf = tokio_postgres::config::Config::from_str(connstr.as_str())
         .context("cannot build tokio postgres config from connstr")?;
     let compute_node = ComputeNode {
-        compute_id: cli.compute_id.clone(),
         connstr,
         conn_conf,
         tokio_conn_conf,
-        pgdata: cli.pgdata.clone(),
-        pgbin: cli.pgbin.clone(),
-        pgversion: get_pg_version_string(&cli.pgbin),
-        http_port: cli.http_port,
+        pgdata: pgdata.to_string(),
+        pgbin: pgbin.to_string(),
+        pgversion: get_pg_version_string(pgbin),
+        http_port,
         live_config_allowed,
         state: Mutex::new(new_state),
         state_changed: Condvar::new(),
-        ext_remote_storage: cli.remote_ext_config.clone(),
+        ext_remote_storage: ext_remote_storage.map(|s| s.to_string()),
         ext_download_progress: RwLock::new(HashMap::new()),
         build_tag,
     };
@@ -352,7 +357,7 @@ fn wait_spec(
     // Launch http service first, so that we can serve control-plane requests
     // while configuration is still in progress.
     let _http_handle =
-        launch_http_server(cli.http_port, &compute).expect("cannot launch http endpoint thread");
+        launch_http_server(http_port, &compute).expect("cannot launch http endpoint thread");
 
     if !spec_set {
         // No spec provided, hang waiting for it.
@@ -384,12 +389,27 @@ fn wait_spec(
 
     launch_lsn_lease_bg_task_for_static(&compute);
 
-    Ok(compute)
+    Ok(WaitSpecResult {
+        compute,
+        resize_swap_on_bind,
+        set_disk_quota_for_fs: set_disk_quota_for_fs.cloned(),
+    })
+}
+
+struct WaitSpecResult {
+    compute: Arc<ComputeNode>,
+    resize_swap_on_bind: bool,
+    set_disk_quota_for_fs: Option<String>,
 }
 
 fn start_postgres(
-    cli: &Cli,
-    compute: Arc<ComputeNode>,
+    // need to allow unused because `matches` is only used if target_os = "linux"
+    #[allow(unused_variables)] matches: &clap::ArgMatches,
+    WaitSpecResult {
+        compute,
+        resize_swap_on_bind,
+        set_disk_quota_for_fs,
+    }: WaitSpecResult,
 ) -> Result<(Option<PostgresHandle>, StartPostgresResult)> {
     // We got all we need, update the state.
     let mut state = compute.state.lock().unwrap();
@@ -417,7 +437,7 @@ fn start_postgres(
     let mut delay_exit = false;
 
     // Resize swap to the desired size if the compute spec says so
-    if let (Some(size_bytes), true) = (swap_size_bytes, cli.resize_swap_on_bind) {
+    if let (Some(size_bytes), true) = (swap_size_bytes, resize_swap_on_bind) {
         // To avoid 'swapoff' hitting postgres startup, we need to run resize-swap to completion
         // *before* starting postgres.
         //
@@ -444,9 +464,9 @@ fn start_postgres(
 
     // Set disk quota if the compute spec says so
     if let (Some(disk_quota_bytes), Some(disk_quota_fs_mountpoint)) =
-        (disk_quota_bytes, cli.set_disk_quota_for_fs.as_ref())
+        (disk_quota_bytes, set_disk_quota_for_fs)
     {
-        match set_disk_quota(disk_quota_bytes, disk_quota_fs_mountpoint) {
+        match set_disk_quota(disk_quota_bytes, &disk_quota_fs_mountpoint) {
             Ok(()) => {
                 let size_mib = disk_quota_bytes as f32 / (1 << 20) as f32; // just for more coherent display.
                 info!(%disk_quota_bytes, %size_mib, "set disk quota");
@@ -489,7 +509,13 @@ fn start_postgres(
         if #[cfg(target_os = "linux")] {
             use std::env;
             use tokio_util::sync::CancellationToken;
+            let vm_monitor_addr = matches
+                .get_one::<String>("vm-monitor-addr")
+                .expect("--vm-monitor-addr should always be set because it has a default arg");
+            let file_cache_connstr = matches.get_one::<String>("filecache-connstr");
+            let cgroup = matches.get_one::<String>("cgroup");
 
+            // Only make a runtime if we need to.
             // Note: it seems like you can make a runtime in an inner scope and
             // if you start a task in it it won't be dropped. However, make it
             // in the outermost scope just to be safe.
@@ -512,15 +538,15 @@ fn start_postgres(
             let pgconnstr = if disable_lfc_resizing.unwrap_or(false) {
                 None
             } else {
-                Some(cli.filecache_connstr.clone())
+                file_cache_connstr.cloned()
             };
 
             let vm_monitor = rt.as_ref().map(|rt| {
                 rt.spawn(vm_monitor::start(
                     Box::leak(Box::new(vm_monitor::Args {
-                        cgroup: Some(cli.cgroup.clone()),
+                        cgroup: cgroup.cloned(),
                         pgconnstr,
-                        addr: cli.vm_monitor_addr.clone(),
+                        addr: vm_monitor_addr.clone(),
                     })),
                     token.clone(),
                 ))
@@ -676,6 +702,105 @@ fn deinit_and_exit(WaitPostgresResult { exit_code }: WaitPostgresResult) -> ! {
     exit(exit_code.unwrap_or(1))
 }
 
+fn cli() -> clap::Command {
+    // Env variable is set by `cargo`
+    let version = option_env!("CARGO_PKG_VERSION").unwrap_or("unknown");
+    clap::Command::new("compute_ctl")
+        .version(version)
+        .arg(
+            Arg::new("http-port")
+                .long("http-port")
+                .value_name("HTTP_PORT")
+                .default_value("3080")
+                .value_parser(clap::value_parser!(u16))
+                .required(false),
+        )
+        .arg(
+            Arg::new("connstr")
+                .short('C')
+                .long("connstr")
+                .value_name("DATABASE_URL")
+                .required(true),
+        )
+        .arg(
+            Arg::new("pgdata")
+                .short('D')
+                .long("pgdata")
+                .value_name("DATADIR")
+                .required(true),
+        )
+        .arg(
+            Arg::new("pgbin")
+                .short('b')
+                .long("pgbin")
+                .default_value("postgres")
+                .value_name("POSTGRES_PATH"),
+        )
+        .arg(
+            Arg::new("spec")
+                .short('s')
+                .long("spec")
+                .value_name("SPEC_JSON"),
+        )
+        .arg(
+            Arg::new("spec-path")
+                .short('S')
+                .long("spec-path")
+                .value_name("SPEC_PATH"),
+        )
+        .arg(
+            Arg::new("compute-id")
+                .short('i')
+                .long("compute-id")
+                .value_name("COMPUTE_ID"),
+        )
+        .arg(
+            Arg::new("control-plane-uri")
+                .short('p')
+                .long("control-plane-uri")
+                .value_name("CONTROL_PLANE_API_BASE_URI"),
+        )
+        .arg(
+            Arg::new("remote-ext-config")
+                .short('r')
+                .long("remote-ext-config")
+                .value_name("REMOTE_EXT_CONFIG"),
+        )
+        // TODO(fprasx): we currently have default arguments because the cloud PR
+        // to pass them in hasn't been merged yet. We should get rid of them once
+        // the PR is merged.
+        .arg(
+            Arg::new("vm-monitor-addr")
+                .long("vm-monitor-addr")
+                .default_value("0.0.0.0:10301")
+                .value_name("VM_MONITOR_ADDR"),
+        )
+        .arg(
+            Arg::new("cgroup")
+                .long("cgroup")
+                .default_value("neon-postgres")
+                .value_name("CGROUP"),
+        )
+        .arg(
+            Arg::new("filecache-connstr")
+                .long("filecache-connstr")
+                .default_value(
+                    "host=localhost port=5432 dbname=postgres user=cloud_admin sslmode=disable application_name=vm-monitor",
+                )
+                .value_name("FILECACHE_CONNSTR"),
+        )
+        .arg(
+            Arg::new("resize-swap-on-bind")
+                .long("resize-swap-on-bind")
+                .action(clap::ArgAction::SetTrue),
+        )
+        .arg(
+            Arg::new("set-disk-quota-for-fs")
+                .long("set-disk-quota-for-fs")
+                .value_name("SET_DISK_QUOTA_FOR_FS")
+        )
+}
+
 /// When compute_ctl is killed, send also termination signal to sync-safekeepers
 /// to prevent leakage. TODO: it is better to convert compute_ctl to async and
 /// wait for termination which would be easy then.
@@ -685,14 +810,7 @@ fn handle_exit_signal(sig: i32) {
     exit(1);
 }
 
-#[cfg(test)]
-mod test {
-    use clap::CommandFactory;
-
-    use super::Cli;
-
-    #[test]
-    fn verify_cli() {
-        Cli::command().debug_assert()
-    }
+#[test]
+fn verify_cli() {
+    cli().debug_assert()
 }

compute_tools/src/bin/fast_import.rs

@@ -31,7 +31,7 @@ use camino::{Utf8Path, Utf8PathBuf};
 use clap::Parser;
 use compute_tools::extension_server::{get_pg_version, PostgresMajorVersion};
 use nix::unistd::Pid;
-use tracing::{error, info, info_span, warn, Instrument};
+use tracing::{info, info_span, warn, Instrument};
 use utils::fs_ext::is_directory_empty;
 
 #[path = "fast_import/aws_s3_sync.rs"]
@@ -41,25 +41,16 @@ mod child_stdio_to_log;
 #[path = "fast_import/s3_uri.rs"]
 mod s3_uri;
 
-const PG_WAIT_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(600);
-const PG_WAIT_RETRY_INTERVAL: std::time::Duration = std::time::Duration::from_millis(300);
-
 #[derive(clap::Parser)]
 struct Args {
     #[clap(long)]
     working_directory: Utf8PathBuf,
     #[clap(long, env = "NEON_IMPORTER_S3_PREFIX")]
-    s3_prefix: Option<s3_uri::S3Uri>,
-    #[clap(long)]
-    source_connection_string: Option<String>,
-    #[clap(short, long)]
-    interactive: bool,
+    s3_prefix: s3_uri::S3Uri,
     #[clap(long)]
     pg_bin_dir: Utf8PathBuf,
     #[clap(long)]
     pg_lib_dir: Utf8PathBuf,
-    #[clap(long)]
-    pg_port: Option<u16>, // port to run postgres on, 5432 is default
 }
 
 #[serde_with::serde_as]
@@ -76,13 +67,6 @@ enum EncryptionSecret {
     KMS { key_id: String },
 }
 
-// copied from pageserver_api::config::defaults::DEFAULT_LOCALE to avoid dependency just for a constant
-const DEFAULT_LOCALE: &str = if cfg!(target_os = "macos") {
-    "C"
-} else {
-    "C.UTF-8"
-};
-
 #[tokio::main]
 pub(crate) async fn main() -> anyhow::Result<()> {
     utils::logging::init(
@@ -93,74 +77,30 @@ pub(crate) async fn main() -> anyhow::Result<()> {
 
     info!("starting");
 
-    let args = Args::parse();
+    let Args {
+        working_directory,
+        s3_prefix,
+        pg_bin_dir,
+        pg_lib_dir,
+    } = Args::parse();
 
-    // Validate arguments
-    if args.s3_prefix.is_none() && args.source_connection_string.is_none() {
-        anyhow::bail!("either s3_prefix or source_connection_string must be specified");
-    }
-    if args.s3_prefix.is_some() && args.source_connection_string.is_some() {
-        anyhow::bail!("only one of s3_prefix or source_connection_string can be specified");
-    }
+    let aws_config = aws_config::load_defaults(BehaviorVersion::v2024_03_28()).await;
 
-    let working_directory = args.working_directory;
-    let pg_bin_dir = args.pg_bin_dir;
-    let pg_lib_dir = args.pg_lib_dir;
-    let pg_port = args.pg_port.unwrap_or_else(|| {
-        info!("pg_port not specified, using default 5432");
-        5432
-    });
-
-    // Initialize AWS clients only if s3_prefix is specified
-    let (aws_config, kms_client) = if args.s3_prefix.is_some() {
-        let config = aws_config::load_defaults(BehaviorVersion::v2024_03_28()).await;
-        let kms = aws_sdk_kms::Client::new(&config);
-        (Some(config), Some(kms))
-    } else {
-        (None, None)
-    };
-
-    // Get source connection string either from S3 spec or direct argument
-    let source_connection_string = if let Some(s3_prefix) = &args.s3_prefix {
-        let spec: Spec = {
-            let spec_key = s3_prefix.append("/spec.json");
-            let s3_client = aws_sdk_s3::Client::new(aws_config.as_ref().unwrap());
-            let object = s3_client
-                .get_object()
-                .bucket(&spec_key.bucket)
-                .key(spec_key.key)
-                .send()
-                .await
-                .context("get spec from s3")?
-                .body
-                .collect()
-                .await
-                .context("download spec body")?;
-            serde_json::from_slice(&object.into_bytes()).context("parse spec as json")?
-        };
-
-        match spec.encryption_secret {
-            EncryptionSecret::KMS { key_id } => {
-                let mut output = kms_client
-                    .unwrap()
-                    .decrypt()
-                    .key_id(key_id)
-                    .ciphertext_blob(aws_sdk_s3::primitives::Blob::new(
-                        spec.source_connstring_ciphertext_base64,
-                    ))
-                    .send()
-                    .await
-                    .context("decrypt source connection string")?;
-                let plaintext = output
-                    .plaintext
-                    .take()
-                    .context("get plaintext source connection string")?;
-                String::from_utf8(plaintext.into_inner())
-                    .context("parse source connection string as utf8")?
-            }
-        }
-    } else {
-        args.source_connection_string.unwrap()
+    let spec: Spec = {
+        let spec_key = s3_prefix.append("/spec.json");
+        let s3_client = aws_sdk_s3::Client::new(&aws_config);
+        let object = s3_client
+            .get_object()
+            .bucket(&spec_key.bucket)
+            .key(spec_key.key)
+            .send()
+            .await
+            .context("get spec from s3")?
+            .body
+            .collect()
+            .await
+            .context("download spec body")?;
+        serde_json::from_slice(&object.into_bytes()).context("parse spec as json")?
     };
 
     match tokio::fs::create_dir(&working_directory).await {
@@ -183,6 +123,15 @@ pub(crate) async fn main() -> anyhow::Result<()> {
         .await
         .context("create pgdata directory")?;
 
+    //
+    // Setup clients
+    //
+    let aws_config = aws_config::load_defaults(BehaviorVersion::v2024_03_28()).await;
+    let kms_client = aws_sdk_kms::Client::new(&aws_config);
+
+    //
+    //  Initialize pgdata
+    //
     let pgbin = pg_bin_dir.join("postgres");
     let pg_version = match get_pg_version(pgbin.as_ref()) {
         PostgresMajorVersion::V14 => 14,
@@ -193,7 +142,7 @@ pub(crate) async fn main() -> anyhow::Result<()> {
     let superuser = "cloud_admin"; // XXX: this shouldn't be hard-coded
     postgres_initdb::do_run_initdb(postgres_initdb::RunInitdbArgs {
         superuser,
-        locale: DEFAULT_LOCALE, // XXX: this shouldn't be hard-coded,
+        locale: "en_US.UTF-8", // XXX: this shouldn't be hard-coded,
         pg_version,
         initdb_bin: pg_bin_dir.join("initdb").as_ref(),
         library_search_path: &pg_lib_dir, // TODO: is this right? Prob works in compute image, not sure about neon_local.
@@ -210,7 +159,6 @@ pub(crate) async fn main() -> anyhow::Result<()> {
     let mut postgres_proc = tokio::process::Command::new(pgbin)
         .arg("-D")
         .arg(&pgdata_dir)
-        .args(["-p", &format!("{pg_port}")])
         .args(["-c", "wal_level=minimal"])
         .args(["-c", "shared_buffers=10GB"])
         .args(["-c", "max_wal_senders=0"])
@@ -222,23 +170,8 @@ pub(crate) async fn main() -> anyhow::Result<()> {
         .args(["-c", &format!("max_parallel_workers={nproc}")])
         .args(["-c", &format!("max_parallel_workers_per_gather={nproc}")])
         .args(["-c", &format!("max_worker_processes={nproc}")])
-        .args([
-            "-c",
-            &format!(
-                "effective_io_concurrency={}",
-                if cfg!(target_os = "macos") { 0 } else { 100 }
-            ),
-        ])
+        .args(["-c", "effective_io_concurrency=100"])
         .env_clear()
-        .env("LD_LIBRARY_PATH", &pg_lib_dir)
-        .env(
-            "ASAN_OPTIONS",
-            std::env::var("ASAN_OPTIONS").unwrap_or_default(),
-        )
-        .env(
-            "UBSAN_OPTIONS",
-            std::env::var("UBSAN_OPTIONS").unwrap_or_default(),
-        )
         .stdout(std::process::Stdio::piped())
         .stderr(std::process::Stdio::piped())
         .spawn()
@@ -252,58 +185,44 @@ pub(crate) async fn main() -> anyhow::Result<()> {
         )
         .instrument(info_span!("postgres")),
     );
-
-    // Create neondb database in the running postgres
     let restore_pg_connstring =
-        format!("host=localhost port={pg_port} user={superuser} dbname=postgres");
-
-    let start_time = std::time::Instant::now();
-
+        format!("host=localhost port=5432 user={superuser} dbname=postgres");
     loop {
-        if start_time.elapsed() > PG_WAIT_TIMEOUT {
-            error!(
-                "timeout exceeded: failed to poll postgres and create database within 10 minutes"
-            );
-            std::process::exit(1);
-        }
-
-        match tokio_postgres::connect(&restore_pg_connstring, tokio_postgres::NoTls).await {
-            Ok((client, connection)) => {
-                // Spawn the connection handling task to maintain the connection
-                tokio::spawn(async move {
-                    if let Err(e) = connection.await {
-                        warn!("connection error: {}", e);
-                    }
-                });
-
-                match client.simple_query("CREATE DATABASE neondb;").await {
-                    Ok(_) => {
-                        info!("created neondb database");
-                        break;
-                    }
-                    Err(e) => {
-                        warn!(
-                            "failed to create database: {}, retying in {}s",
-                            e,
-                            PG_WAIT_RETRY_INTERVAL.as_secs_f32()
-                        );
-                        tokio::time::sleep(PG_WAIT_RETRY_INTERVAL).await;
-                        continue;
-                    }
-                }
-            }
-            Err(_) => {
-                info!(
-                    "postgres not ready yet, retrying in {}s",
-                    PG_WAIT_RETRY_INTERVAL.as_secs_f32()
-                );
-                tokio::time::sleep(PG_WAIT_RETRY_INTERVAL).await;
-                continue;
-            }
+        let res = tokio_postgres::connect(&restore_pg_connstring, tokio_postgres::NoTls).await;
+        if res.is_ok() {
+            info!("postgres is ready, could connect to it");
+            break;
         }
     }
 
-    let restore_pg_connstring = restore_pg_connstring.replace("dbname=postgres", "dbname=neondb");
+    //
+    // Decrypt connection string
+    //
+    let source_connection_string = {
+        match spec.encryption_secret {
+            EncryptionSecret::KMS { key_id } => {
+                let mut output = kms_client
+                    .decrypt()
+                    .key_id(key_id)
+                    .ciphertext_blob(aws_sdk_s3::primitives::Blob::new(
+                        spec.source_connstring_ciphertext_base64,
+                    ))
+                    .send()
+                    .await
+                    .context("decrypt source connection string")?;
+                let plaintext = output
+                    .plaintext
+                    .take()
+                    .context("get plaintext source connection string")?;
+                String::from_utf8(plaintext.into_inner())
+                    .context("parse source connection string as utf8")?
+            }
+        }
+    };
+
+    //
+    // Start the work
+    //
 
     let dumpdir = working_directory.join("dumpdir");
 
@@ -337,7 +256,6 @@ pub(crate) async fn main() -> anyhow::Result<()> {
             .arg(&source_connection_string)
             // how we run it
             .env_clear()
-            .env("LD_LIBRARY_PATH", &pg_lib_dir)
             .kill_on_drop(true)
             .stdout(std::process::Stdio::piped())
             .stderr(std::process::Stdio::piped())
@@ -371,7 +289,6 @@ pub(crate) async fn main() -> anyhow::Result<()> {
             .arg(&dumpdir)
             // how we run it
             .env_clear()
-            .env("LD_LIBRARY_PATH", &pg_lib_dir)
             .kill_on_drop(true)
             .stdout(std::process::Stdio::piped())
             .stderr(std::process::Stdio::piped())
@@ -393,12 +310,6 @@ pub(crate) async fn main() -> anyhow::Result<()> {
         }
     }
 
-    // If interactive mode, wait for Ctrl+C
-    if args.interactive {
-        info!("Running in interactive mode. Press Ctrl+C to shut down.");
-        tokio::signal::ctrl_c().await.context("wait for ctrl-c")?;
-    }
-
     info!("shutdown postgres");
     {
         nix::sys::signal::kill(
@@ -414,24 +325,21 @@ pub(crate) async fn main() -> anyhow::Result<()> {
             .context("wait for postgres to shut down")?;
     }
 
-    // Only sync if s3_prefix was specified
-    if let Some(s3_prefix) = args.s3_prefix {
-        info!("upload pgdata");
-        aws_s3_sync::sync(Utf8Path::new(&pgdata_dir), &s3_prefix.append("/pgdata/"))
-            .await
-            .context("sync dump directory to destination")?;
+    info!("upload pgdata");
+    aws_s3_sync::sync(Utf8Path::new(&pgdata_dir), &s3_prefix.append("/pgdata/"))
+        .await
+        .context("sync dump directory to destination")?;
 
-        info!("write status");
-        {
-            let status_dir = working_directory.join("status");
-            std::fs::create_dir(&status_dir).context("create status directory")?;
-            let status_file = status_dir.join("pgdata");
-            std::fs::write(&status_file, serde_json::json!({"done": true}).to_string())
-                .context("write status file")?;
-            aws_s3_sync::sync(&status_dir, &s3_prefix.append("/status/"))
-                .await
-                .context("sync status directory to destination")?;
-        }
+    info!("write status");
+    {
+        let status_dir = working_directory.join("status");
+        std::fs::create_dir(&status_dir).context("create status directory")?;
+        let status_file = status_dir.join("pgdata");
+        std::fs::write(&status_file, serde_json::json!({"done": true}).to_string())
+            .context("write status file")?;
+        aws_s3_sync::sync(&status_dir, &s3_prefix.append("/status/"))
+            .await
+            .context("sync status directory to destination")?;
     }
 
     Ok(())

compute_tools/src/compute.rs

@@ -41,14 +41,14 @@ use crate::local_proxy;
 use crate::pg_helpers::*;
 use crate::spec::*;
 use crate::spec_apply::ApplySpecPhase::{
-    CreateAndAlterDatabases, CreateAndAlterRoles, CreateAvailabilityCheck, CreateSchemaNeon,
-    CreateSuperUser, DropInvalidDatabases, DropRoles, FinalizeDropLogicalSubscriptions,
-    HandleNeonExtension, HandleOtherExtensions, RenameAndDeleteDatabases, RenameRoles,
-    RunInEachDatabase,
+    CreateAndAlterDatabases, CreateAndAlterRoles, CreateAvailabilityCheck, CreateSuperUser,
+    DropInvalidDatabases, DropRoles, HandleNeonExtension, HandleOtherExtensions,
+    RenameAndDeleteDatabases, RenameRoles, RunInEachDatabase,
 };
 use crate::spec_apply::PerDatabasePhase;
 use crate::spec_apply::PerDatabasePhase::{
-    ChangeSchemaPerms, DeleteDBRoleReferences, DropLogicalSubscriptions, HandleAnonExtension,
+    ChangeSchemaPerms, DeleteDBRoleReferences, DropSubscriptionsForDeletedDatabases,
+    HandleAnonExtension,
 };
 use crate::spec_apply::{apply_operations, MutableApplyContext, DB};
 use crate::sync_sk::{check_if_synced, ping_safekeeper};
@@ -59,8 +59,6 @@ pub static PG_PID: AtomicU32 = AtomicU32::new(0);
 
 /// Compute node info shared across several `compute_ctl` threads.
 pub struct ComputeNode {
-    /// The ID of the compute
-    pub compute_id: String,
     // Url type maintains proper escaping
     pub connstr: url::Url,
     // We connect to Postgres from many different places, so build configs once
@@ -342,15 +340,6 @@ impl ComputeNode {
         self.state.lock().unwrap().status
     }
 
-    pub fn get_timeline_id(&self) -> Option<TimelineId> {
-        self.state
-            .lock()
-            .unwrap()
-            .pspec
-            .as_ref()
-            .map(|s| s.timeline_id)
-    }
-
     // Remove `pgdata` directory and create it again with right permissions.
     fn create_pgdata(&self) -> Result<()> {
         // Ignore removal error, likely it is a 'No such file or directory (os error 2)'.
@@ -940,48 +929,6 @@ impl ComputeNode {
                 .map(|role| (role.name.clone(), role))
                 .collect::<HashMap<String, Role>>();
 
-            // Check if we need to drop subscriptions before starting the endpoint.
-            //
-            // It is important to do this operation exactly once when endpoint starts on a new branch.
-            // Otherwise, we may drop not inherited, but newly created subscriptions.
-            //
-            // We cannot rely only on spec.drop_subscriptions_before_start flag,
-            // because if for some reason compute restarts inside VM,
-            // it will start again with the same spec and flag value.
-            //
-            // To handle this, we save the fact of the operation in the database
-            // in the neon.drop_subscriptions_done table.
-            // If the table does not exist, we assume that the operation was never performed, so we must do it.
-            // If table exists, we check if the operation was performed on the current timelilne.
-            //
-            let mut drop_subscriptions_done = false;
-
-            if spec.drop_subscriptions_before_start {
-                let timeline_id = self.get_timeline_id().context("timeline_id must be set")?;
-                let query = format!("select 1 from neon.drop_subscriptions_done where timeline_id = '{}'", timeline_id);
-
-                info!("Checking if drop subscription operation was already performed for timeline_id: {}", timeline_id);
-
-                drop_subscriptions_done =  match
-                    client.simple_query(&query).await {
-                    Ok(result) => {
-                        matches!(&result[0], postgres::SimpleQueryMessage::Row(_))
-                    },
-                    Err(e) =>
-                    {
-                        match e.code() {
-                            Some(&SqlState::UNDEFINED_TABLE) => false,
-                            _ => {
-                                // We don't expect any other error here, except for the schema/table not existing
-                                error!("Error checking if drop subscription operation was already performed: {}", e);
-                                return Err(e.into());
-                            }
-                        }
-                    }
-                }
-            };
-
-
             let jwks_roles = Arc::new(
                 spec.as_ref()
                     .local_proxy_config
@@ -1049,7 +996,7 @@ impl ComputeNode {
                         jwks_roles.clone(),
                         concurrency_token.clone(),
                         db,
-                        [DropLogicalSubscriptions].to_vec(),
+                        [DropSubscriptionsForDeletedDatabases].to_vec(),
                     );
 
                     Ok(spawn(fut))
@@ -1077,7 +1024,6 @@ impl ComputeNode {
                 CreateAndAlterRoles,
                 RenameAndDeleteDatabases,
                 CreateAndAlterDatabases,
-                CreateSchemaNeon,
             ] {
                 info!("Applying phase {:?}", &phase);
                 apply_operations(
@@ -1118,17 +1064,6 @@ impl ComputeNode {
                     }
 
                     let conf = Arc::new(conf);
-                    let mut phases = vec![
-                        DeleteDBRoleReferences,
-                        ChangeSchemaPerms,
-                        HandleAnonExtension,
-                    ];
-
-                    if spec.drop_subscriptions_before_start && !drop_subscriptions_done {
-                        info!("Adding DropLogicalSubscriptions phase because drop_subscriptions_before_start is set");
-                        phases.push(DropLogicalSubscriptions);
-                    }
-
                     let fut = Self::apply_spec_sql_db(
                         spec.clone(),
                         conf,
@@ -1136,7 +1071,12 @@ impl ComputeNode {
                         jwks_roles.clone(),
                         concurrency_token.clone(),
                         db,
-                        phases,
+                        [
+                            DeleteDBRoleReferences,
+                            ChangeSchemaPerms,
+                            HandleAnonExtension,
+                        ]
+                        .to_vec(),
                     );
 
                     Ok(spawn(fut))
@@ -1148,20 +1088,12 @@ impl ComputeNode {
                 handle.await??;
             }
 
-            let mut phases = vec![
+            for phase in vec![
                 HandleOtherExtensions,
-                HandleNeonExtension, // This step depends on CreateSchemaNeon
+                HandleNeonExtension,
                 CreateAvailabilityCheck,
                 DropRoles,
-            ];
-
-            // This step depends on CreateSchemaNeon
-            if spec.drop_subscriptions_before_start && !drop_subscriptions_done {
-                info!("Adding FinalizeDropLogicalSubscriptions phase because drop_subscriptions_before_start is set");
-                phases.push(FinalizeDropLogicalSubscriptions);
-            }
-
-            for phase in phases {
+            ] {
                 debug!("Applying phase {:?}", &phase);
                 apply_operations(
                     spec.clone(),
@@ -1531,14 +1463,6 @@ impl ComputeNode {
                         Ok(())
                     },
                 )?;
-
-                let postgresql_conf_path = pgdata_path.join("postgresql.conf");
-                if config::line_in_file(
-                    &postgresql_conf_path,
-                    "neon.disable_logical_replication_subscribers=false",
-                )? {
-                    info!("updated postgresql.conf to set neon.disable_logical_replication_subscribers=false");
-                }
                 self.pg_reload_conf()?;
             }
             self.post_apply_config()?;

compute_tools/src/config.rs

@@ -129,13 +129,6 @@ pub fn write_postgres_conf(
 
     writeln!(file, "neon.extension_server_port={}", extension_server_port)?;
 
-    if spec.drop_subscriptions_before_start {
-        writeln!(file, "neon.disable_logical_replication_subscribers=true")?;
-    } else {
-        // be explicit about the default value
-        writeln!(file, "neon.disable_logical_replication_subscribers=false")?;
-    }
-
     // This is essential to keep this line at the end of the file,
     // because it is intended to override any settings above.
     writeln!(file, "include_if_exists = 'compute_ctl_temp_override.conf'")?;

compute_tools/src/extension_server.rs

@@ -85,8 +85,6 @@ use tracing::info;
 use tracing::log::warn;
 use zstd::stream::read::Decoder;
 
-use crate::metrics::{REMOTE_EXT_REQUESTS_TOTAL, UNKNOWN_HTTP_STATUS};
-
 fn get_pg_config(argument: &str, pgbin: &str) -> String {
     // gives the result of `pg_config [argument]`
     // where argument is a flag like `--version` or `--sharedir`
@@ -258,60 +256,23 @@ pub fn create_control_files(remote_extensions: &RemoteExtSpec, pgbin: &str) {
 async fn download_extension_tar(ext_remote_storage: &str, ext_path: &str) -> Result<Bytes> {
     let uri = format!("{}/{}", ext_remote_storage, ext_path);
 
-    info!("Download extension {} from uri {}", ext_path, uri);
+    info!("Download extension {:?} from uri {:?}", ext_path, uri);
 
-    match do_extension_server_request(&uri).await {
-        Ok(resp) => {
-            info!("Successfully downloaded remote extension data {}", ext_path);
-            REMOTE_EXT_REQUESTS_TOTAL
-                .with_label_values(&[&StatusCode::OK.to_string()])
-                .inc();
-            Ok(resp)
-        }
-        Err((msg, status)) => {
-            REMOTE_EXT_REQUESTS_TOTAL
-                .with_label_values(&[&status])
-                .inc();
-            bail!(msg);
-        }
-    }
-}
+    let resp = reqwest::get(uri).await?;
 
-// Do a single remote extensions server request.
-// Return result or (error message + stringified status code) in case of any failures.
-async fn do_extension_server_request(uri: &str) -> Result<Bytes, (String, String)> {
-    let resp = reqwest::get(uri).await.map_err(|e| {
-        (
-            format!(
-                "could not perform remote extensions server request: {:?}",
-                e
-            ),
-            UNKNOWN_HTTP_STATUS.to_string(),
-        )
-    })?;
-    let status = resp.status();
-
-    match status {
+    match resp.status() {
         StatusCode::OK => match resp.bytes().await {
-            Ok(resp) => Ok(resp),
-            Err(e) => Err((
-                format!("could not read remote extensions server response: {:?}", e),
-                // It's fine to return and report error with status as 200 OK,
-                // because we still failed to read the response.
-                status.to_string(),
-            )),
+            Ok(resp) => {
+                info!("Download extension {:?} completed successfully", ext_path);
+                Ok(resp)
+            }
+            Err(e) => bail!("could not deserialize remote extension response: {}", e),
         },
-        StatusCode::SERVICE_UNAVAILABLE => Err((
-            "remote extensions server is temporarily unavailable".to_string(),
-            status.to_string(),
-        )),
-        _ => Err((
-            format!(
-                "unexpected remote extensions server response status code: {}",
-                status
-            ),
-            status.to_string(),
-        )),
+        StatusCode::SERVICE_UNAVAILABLE => bail!("remote extension is temporarily unavailable"),
+        _ => bail!(
+            "unexpected remote extension response status code: {}",
+            resp.status()
+        ),
     }
 }
 

compute_tools/src/http/extract/json.rs

@@ -1,6 +1,9 @@
 use std::ops::{Deref, DerefMut};
 
-use axum::extract::{rejection::JsonRejection, FromRequest, Request};
+use axum::{
+    async_trait,
+    extract::{rejection::JsonRejection, FromRequest, Request},
+};
 use compute_api::responses::GenericAPIError;
 use http::StatusCode;
 
@@ -9,6 +12,7 @@ use http::StatusCode;
 #[derive(Debug, Clone, Copy, Default)]
 pub(crate) struct Json<T>(pub T);
 
+#[async_trait]
 impl<S, T> FromRequest<S> for Json<T>
 where
     axum::Json<T>: FromRequest<S, Rejection = JsonRejection>,

compute_tools/src/http/extract/path.rs

@@ -1,6 +1,9 @@
 use std::ops::{Deref, DerefMut};
 
-use axum::extract::{rejection::PathRejection, FromRequestParts};
+use axum::{
+    async_trait,
+    extract::{rejection::PathRejection, FromRequestParts},
+};
 use compute_api::responses::GenericAPIError;
 use http::{request::Parts, StatusCode};
 
@@ -9,6 +12,7 @@ use http::{request::Parts, StatusCode};
 #[derive(Debug, Clone, Copy, Default)]
 pub(crate) struct Path<T>(pub T);
 
+#[async_trait]
 impl<S, T> FromRequestParts<S> for Path<T>
 where
     axum::extract::Path<T>: FromRequestParts<S, Rejection = PathRejection>,

compute_tools/src/http/extract/query.rs

@@ -1,6 +1,9 @@
 use std::ops::{Deref, DerefMut};
 
-use axum::extract::{rejection::QueryRejection, FromRequestParts};
+use axum::{
+    async_trait,
+    extract::{rejection::QueryRejection, FromRequestParts},
+};
 use compute_api::responses::GenericAPIError;
 use http::{request::Parts, StatusCode};
 
@@ -9,6 +12,7 @@ use http::{request::Parts, StatusCode};
 #[derive(Debug, Clone, Copy, Default)]
 pub(crate) struct Query<T>(pub T);
 
+#[async_trait]
 impl<S, T> FromRequestParts<S> for Query<T>
 where
     axum::extract::Query<T>: FromRequestParts<S, Rejection = QueryRejection>,

compute_tools/src/http/openapi_spec.yaml

@@ -68,6 +68,35 @@ paths:
               schema:
                 $ref: "#/components/schemas/ComputeInsights"
 
+  /installed_extensions:
+    get:
+      tags:
+      - Info
+      summary: Get installed extensions.
+      description: ""
+      operationId: getInstalledExtensions
+      responses:
+        200:
+          description: List of installed extensions
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/InstalledExtensions"
+  /info:
+    get:
+      tags:
+      - Info
+      summary: Get info about the compute pod / VM.
+      description: ""
+      operationId: getInfo
+      responses:
+        200:
+          description: Info
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/Info"
+
   /dbs_and_roles:
     get:
       tags:

compute_tools/src/http/routes/extension_server.rs

@@ -17,8 +17,7 @@ use crate::{
 
 #[derive(Debug, Clone, Deserialize)]
 pub(in crate::http) struct ExtensionServerParams {
-    #[serde(default)]
-    is_library: bool,
+    is_library: Option<bool>,
 }
 
 /// Download a remote extension.
@@ -52,7 +51,7 @@ pub(in crate::http) async fn download_extension(
 
         remote_extensions.get_ext(
             &filename,
-            params.is_library,
+            params.is_library.unwrap_or(false),
             &compute.build_tag,
             &compute.pgversion,
         )

compute_tools/src/http/routes/info.rs

@@ -0,0 +1,11 @@
+use axum::response::Response;
+use compute_api::responses::InfoResponse;
+use http::StatusCode;
+
+use crate::http::JsonResponse;
+
+/// Get information about the physical characteristics about the compute.
+pub(in crate::http) async fn get_info() -> Response {
+    let num_cpus = num_cpus::get_physical();
+    JsonResponse::success(StatusCode::OK, &InfoResponse { num_cpus })
+}

compute_tools/src/http/routes/installed_extensions.rs

@@ -0,0 +1,33 @@
+use std::sync::Arc;
+
+use axum::{extract::State, response::Response};
+use compute_api::responses::ComputeStatus;
+use http::StatusCode;
+use tokio::task;
+
+use crate::{compute::ComputeNode, http::JsonResponse, installed_extensions};
+
+/// Get a list of installed extensions.
+pub(in crate::http) async fn get_installed_extensions(
+    State(compute): State<Arc<ComputeNode>>,
+) -> Response {
+    let status = compute.get_status();
+    if status != ComputeStatus::Running {
+        return JsonResponse::invalid_status(status);
+    }
+
+    let conf = compute.get_conn_conf(None);
+    let res = task::spawn_blocking(move || installed_extensions::get_installed_extensions(conf))
+        .await
+        .unwrap();
+
+    match res {
+        Ok(installed_extensions) => {
+            JsonResponse::success(StatusCode::OK, Some(installed_extensions))
+        }
+        Err(e) => JsonResponse::error(
+            StatusCode::INTERNAL_SERVER_ERROR,
+            format!("failed to get list of installed extensions: {e}"),
+        ),
+    }
+}

compute_tools/src/http/routes/metrics.rs

@@ -2,16 +2,17 @@ use axum::{body::Body, response::Response};
 use http::header::CONTENT_TYPE;
 use http::StatusCode;
 use metrics::proto::MetricFamily;
-use metrics::{Encoder, TextEncoder};
+use metrics::Encoder;
+use metrics::TextEncoder;
 
-use crate::{http::JsonResponse, metrics::collect};
+use crate::{http::JsonResponse, installed_extensions};
 
 /// Expose Prometheus metrics.
 pub(in crate::http) async fn get_metrics() -> Response {
     // When we call TextEncoder::encode() below, it will immediately return an
     // error if a metric family has no metrics, so we need to preemptively
     // filter out metric families with no metrics.
-    let metrics = collect()
+    let metrics = installed_extensions::collect()
         .into_iter()
         .filter(|m| !m.get_metric().is_empty())
         .collect::<Vec<MetricFamily>>();

compute_tools/src/http/routes/mod.rs

@@ -10,7 +10,9 @@ pub(in crate::http) mod extension_server;
 pub(in crate::http) mod extensions;
 pub(in crate::http) mod failpoints;
 pub(in crate::http) mod grants;
+pub(in crate::http) mod info;
 pub(in crate::http) mod insights;
+pub(in crate::http) mod installed_extensions;
 pub(in crate::http) mod metrics;
 pub(in crate::http) mod metrics_json;
 pub(in crate::http) mod status;

compute_tools/src/http/server.rs

@@ -1,14 +1,15 @@
 use std::{
     net::{IpAddr, Ipv6Addr, SocketAddr},
-    sync::Arc,
+    sync::{
+        atomic::{AtomicU64, Ordering},
+        Arc,
+    },
     thread,
     time::Duration,
 };
 
 use anyhow::Result;
 use axum::{
-    extract::Request,
-    middleware::{self, Next},
     response::{IntoResponse, Response},
     routing::{get, post},
     Router,
@@ -16,13 +17,16 @@ use axum::{
 use http::StatusCode;
 use tokio::net::TcpListener;
 use tower::ServiceBuilder;
-use tower_http::{request_id::PropagateRequestIdLayer, trace::TraceLayer};
+use tower_http::{
+    request_id::{MakeRequestId, PropagateRequestIdLayer, RequestId, SetRequestIdLayer},
+    trace::TraceLayer,
+};
 use tracing::{debug, error, info, Span};
-use uuid::Uuid;
 
 use super::routes::{
     check_writability, configure, database_schema, dbs_and_roles, extension_server, extensions,
-    grants, insights, metrics, metrics_json, status, terminate,
+    grants, info as info_route, insights, installed_extensions, metrics, metrics_json, status,
+    terminate,
 };
 use crate::compute::ComputeNode;
 
@@ -30,36 +34,47 @@ async fn handle_404() -> Response {
     StatusCode::NOT_FOUND.into_response()
 }
 
-const X_REQUEST_ID: &str = "x-request-id";
+#[derive(Clone, Default)]
+struct ComputeMakeRequestId(Arc<AtomicU64>);
 
-/// This middleware function allows compute_ctl to generate its own request ID
-/// if one isn't supplied. The control plane will always send one as a UUID. The
-/// neon Postgres extension on the other hand does not send one.
-async fn maybe_add_request_id_header(mut request: Request, next: Next) -> Response {
-    let headers = request.headers_mut();
+impl MakeRequestId for ComputeMakeRequestId {
+    fn make_request_id<B>(
+        &mut self,
+        _request: &http::Request<B>,
+    ) -> Option<tower_http::request_id::RequestId> {
+        let request_id = self
+            .0
+            .fetch_add(1, Ordering::SeqCst)
+            .to_string()
+            .parse()
+            .unwrap();
 
-    if headers.get(X_REQUEST_ID).is_none() {
-        headers.append(X_REQUEST_ID, Uuid::new_v4().to_string().parse().unwrap());
+        Some(RequestId::new(request_id))
     }
-
-    next.run(request).await
 }
 
 /// Run the HTTP server and wait on it forever.
 #[tokio::main]
 async fn serve(port: u16, compute: Arc<ComputeNode>) {
+    const X_REQUEST_ID: &str = "x-request-id";
+
     let mut app = Router::new()
         .route("/check_writability", post(check_writability::is_writable))
         .route("/configure", post(configure::configure))
         .route("/database_schema", get(database_schema::get_schema_dump))
         .route("/dbs_and_roles", get(dbs_and_roles::get_catalog_objects))
         .route(
-            "/extension_server/{*filename}",
+            "/extension_server/*filename",
             post(extension_server::download_extension),
         )
         .route("/extensions", post(extensions::install_extension))
         .route("/grants", post(grants::add_grant))
+        .route("/info", get(info_route::get_info))
         .route("/insights", get(insights::get_insights))
+        .route(
+            "/installed_extensions",
+            get(installed_extensions::get_installed_extensions),
+        )
         .route("/metrics", get(metrics::get_metrics))
         .route("/metrics.json", get(metrics_json::get_metrics))
         .route("/status", get(status::get_status))
@@ -67,8 +82,9 @@ async fn serve(port: u16, compute: Arc<ComputeNode>) {
         .fallback(handle_404)
         .layer(
             ServiceBuilder::new()
-                // Add this middleware since we assume the request ID exists
-                .layer(middleware::from_fn(maybe_add_request_id_header))
+                .layer(SetRequestIdLayer::x_request_id(
+                    ComputeMakeRequestId::default(),
+                ))
                 .layer(
                     TraceLayer::new_for_http()
                         .on_request(|request: &http::Request<_>, _span: &Span| {

compute_tools/src/installed_extensions.rs

@@ -1,10 +1,13 @@
 use compute_api::responses::{InstalledExtension, InstalledExtensions};
+use metrics::proto::MetricFamily;
 use std::collections::HashMap;
 
 use anyhow::Result;
 use postgres::{Client, NoTls};
 
-use crate::metrics::INSTALLED_EXTENSIONS;
+use metrics::core::Collector;
+use metrics::{register_uint_gauge_vec, UIntGaugeVec};
+use once_cell::sync::Lazy;
 
 /// We don't reuse get_existing_dbs() just for code clarity
 /// and to make database listing query here more explicit.
@@ -99,3 +102,16 @@ pub fn get_installed_extensions(mut conf: postgres::config::Config) -> Result<In
         extensions: extensions_map.into_values().collect(),
     })
 }
+
+static INSTALLED_EXTENSIONS: Lazy<UIntGaugeVec> = Lazy::new(|| {
+    register_uint_gauge_vec!(
+        "compute_installed_extensions",
+        "Number of databases where the version of extension is installed",
+        &["extension_name", "version", "owned_by_superuser"]
+    )
+    .expect("failed to define a metric")
+});
+
+pub fn collect() -> Vec<MetricFamily> {
+    INSTALLED_EXTENSIONS.collect()
+}

compute_tools/src/lib.rs

@@ -16,7 +16,6 @@ pub mod extension_server;
 pub mod installed_extensions;
 pub mod local_proxy;
 pub mod lsn_lease;
-pub mod metrics;
 mod migration;
 pub mod monitor;
 pub mod params;

compute_tools/src/metrics.rs

@@ -1,70 +0,0 @@
-use metrics::core::Collector;
-use metrics::proto::MetricFamily;
-use metrics::{register_int_counter_vec, register_uint_gauge_vec, IntCounterVec, UIntGaugeVec};
-use once_cell::sync::Lazy;
-
-pub(crate) static INSTALLED_EXTENSIONS: Lazy<UIntGaugeVec> = Lazy::new(|| {
-    register_uint_gauge_vec!(
-        "compute_installed_extensions",
-        "Number of databases where the version of extension is installed",
-        &["extension_name", "version", "owned_by_superuser"]
-    )
-    .expect("failed to define a metric")
-});
-
-// Normally, any HTTP API request is described by METHOD (e.g. GET, POST, etc.) + PATH,
-// but for all our APIs we defined a 'slug'/method/operationId in the OpenAPI spec.
-// And it's fair to call it a 'RPC' (Remote Procedure Call).
-pub enum CPlaneRequestRPC {
-    GetSpec,
-}
-
-impl CPlaneRequestRPC {
-    pub fn as_str(&self) -> &str {
-        match self {
-            CPlaneRequestRPC::GetSpec => "GetSpec",
-        }
-    }
-}
-
-pub const UNKNOWN_HTTP_STATUS: &str = "unknown";
-
-pub(crate) static CPLANE_REQUESTS_TOTAL: Lazy<IntCounterVec> = Lazy::new(|| {
-    register_int_counter_vec!(
-        "compute_ctl_cplane_requests_total",
-        "Total number of control plane requests made by compute_ctl by status",
-        &["rpc", "http_status"]
-    )
-    .expect("failed to define a metric")
-});
-
-/// Total number of failed database migrations. Per-compute, this is actually a boolean metric,
-/// either empty or with a single value (1, migration_id) because we stop at the first failure.
-/// Yet, the sum over the fleet will provide the total number of failures.
-pub(crate) static DB_MIGRATION_FAILED: Lazy<IntCounterVec> = Lazy::new(|| {
-    register_int_counter_vec!(
-        "compute_ctl_db_migration_failed_total",
-        "Total number of failed database migrations",
-        &["migration_id"]
-    )
-    .expect("failed to define a metric")
-});
-
-pub(crate) static REMOTE_EXT_REQUESTS_TOTAL: Lazy<IntCounterVec> = Lazy::new(|| {
-    register_int_counter_vec!(
-        "compute_ctl_remote_ext_requests_total",
-        "Total number of requests made by compute_ctl to download extensions from S3 proxy by status",
-        // Do not use any labels like extension name yet.
-        // We can add them later if needed.
-        &["http_status"]
-    )
-    .expect("failed to define a metric")
-});
-
-pub fn collect() -> Vec<MetricFamily> {
-    let mut metrics = INSTALLED_EXTENSIONS.collect();
-    metrics.extend(CPLANE_REQUESTS_TOTAL.collect());
-    metrics.extend(REMOTE_EXT_REQUESTS_TOTAL.collect());
-    metrics.extend(DB_MIGRATION_FAILED.collect());
-    metrics
-}

compute_tools/src/migration.rs

@@ -1,9 +1,7 @@
 use anyhow::{Context, Result};
 use fail::fail_point;
 use postgres::{Client, Transaction};
-use tracing::{error, info};
-
-use crate::metrics::DB_MIGRATION_FAILED;
+use tracing::info;
 
 /// Runs a series of migrations on a target database
 pub(crate) struct MigrationRunner<'m> {
@@ -80,31 +78,24 @@ impl<'m> MigrationRunner<'m> {
         Ok(())
     }
 
-    /// Run an individual migration in a separate transaction block.
-    fn run_migration(client: &mut Client, migration_id: i64, migration: &str) -> Result<()> {
-        let mut txn = client
-            .transaction()
-            .with_context(|| format!("begin transaction for migration {migration_id}"))?;
-
+    /// Run an individual migration
+    fn run_migration(txn: &mut Transaction, migration_id: i64, migration: &str) -> Result<()> {
         if migration.starts_with("-- SKIP") {
             info!("Skipping migration id={}", migration_id);
 
             // Even though we are skipping the migration, updating the
             // migration ID should help keep logic easy to understand when
             // trying to understand the state of a cluster.
-            Self::update_migration_id(&mut txn, migration_id)?;
+            Self::update_migration_id(txn, migration_id)?;
         } else {
             info!("Running migration id={}:\n{}\n", migration_id, migration);
 
             txn.simple_query(migration)
                 .with_context(|| format!("apply migration {migration_id}"))?;
 
-            Self::update_migration_id(&mut txn, migration_id)?;
+            Self::update_migration_id(txn, migration_id)?;
         }
 
-        txn.commit()
-            .with_context(|| format!("commit transaction for migration {migration_id}"))?;
-
         Ok(())
     }
 
@@ -118,20 +109,19 @@ impl<'m> MigrationRunner<'m> {
             // The index lags the migration ID by 1, so the current migration
             // ID is also the next index
             let migration_id = (current_migration + 1) as i64;
-            let migration = self.migrations[current_migration];
 
-            match Self::run_migration(self.client, migration_id, migration) {
-                Ok(_) => {
-                    info!("Finished migration id={}", migration_id);
-                }
-                Err(e) => {
-                    error!("Failed to run migration id={}: {:?}", migration_id, e);
-                    DB_MIGRATION_FAILED
-                        .with_label_values(&[migration_id.to_string().as_str()])
-                        .inc();
-                    return Err(e);
-                }
-            }
+            let mut txn = self
+                .client
+                .transaction()
+                .with_context(|| format!("begin transaction for migration {migration_id}"))?;
+
+            Self::run_migration(&mut txn, migration_id, self.migrations[current_migration])
+                .with_context(|| format!("running migration {migration_id}"))?;
+
+            txn.commit()
+                .with_context(|| format!("commit transaction for migration {migration_id}"))?;
+
+            info!("Finished migration id={}", migration_id);
 
             current_migration += 1;
         }

compute_tools/src/spec.rs

@@ -1,44 +1,25 @@
 use anyhow::{anyhow, bail, Result};
 use postgres::Client;
 use reqwest::StatusCode;
-use serde::Deserialize;
 use std::fs::File;
 use std::path::Path;
 use tracing::{error, info, instrument, warn};
 
 use crate::config;
-use crate::metrics::{CPlaneRequestRPC, CPLANE_REQUESTS_TOTAL, UNKNOWN_HTTP_STATUS};
 use crate::migration::MigrationRunner;
 use crate::params::PG_HBA_ALL_MD5;
 use crate::pg_helpers::*;
 
+use compute_api::responses::{ControlPlaneComputeStatus, ControlPlaneSpecResponse};
 use compute_api::spec::ComputeSpec;
 
-/// Response of the `/computes/{compute_id}/spec` control-plane API.
-#[derive(Deserialize, Debug)]
-pub struct ControlPlaneSpecResponse {
-    pub spec: Option<ComputeSpec>,
-    pub status: ControlPlaneComputeStatus,
-}
-
-#[derive(Deserialize, Clone, Copy, Debug, PartialEq, Eq)]
-#[serde(rename_all = "snake_case")]
-pub enum ControlPlaneComputeStatus {
-    // Compute is known to control-plane, but it's not
-    // yet attached to any timeline / endpoint.
-    Empty,
-    // Compute is attached to some timeline / endpoint and
-    // should be able to start with provided spec.
-    Attached,
-}
-
 // Do control plane request and return response if any. In case of error it
 // returns a bool flag indicating whether it makes sense to retry the request
 // and a string with error message.
 fn do_control_plane_request(
     uri: &str,
     jwt: &str,
-) -> Result<ControlPlaneSpecResponse, (bool, String, String)> {
+) -> Result<ControlPlaneSpecResponse, (bool, String)> {
     let resp = reqwest::blocking::Client::new()
         .get(uri)
         .header("Authorization", format!("Bearer {}", jwt))
@@ -46,42 +27,35 @@ fn do_control_plane_request(
         .map_err(|e| {
             (
                 true,
-                format!("could not perform spec request to control plane: {:?}", e),
-                UNKNOWN_HTTP_STATUS.to_string(),
+                format!("could not perform spec request to control plane: {}", e),
             )
         })?;
 
-    let status = resp.status();
-    match status {
+    match resp.status() {
         StatusCode::OK => match resp.json::<ControlPlaneSpecResponse>() {
             Ok(spec_resp) => Ok(spec_resp),
             Err(e) => Err((
                 true,
-                format!("could not deserialize control plane response: {:?}", e),
-                status.to_string(),
+                format!("could not deserialize control plane response: {}", e),
             )),
         },
-        StatusCode::SERVICE_UNAVAILABLE => Err((
-            true,
-            "control plane is temporarily unavailable".to_string(),
-            status.to_string(),
-        )),
+        StatusCode::SERVICE_UNAVAILABLE => {
+            Err((true, "control plane is temporarily unavailable".to_string()))
+        }
         StatusCode::BAD_GATEWAY => {
             // We have a problem with intermittent 502 errors now
             // https://github.com/neondatabase/cloud/issues/2353
             // It's fine to retry GET request in this case.
-            Err((
-                true,
-                "control plane request failed with 502".to_string(),
-                status.to_string(),
-            ))
+            Err((true, "control plane request failed with 502".to_string()))
         }
         // Another code, likely 500 or 404, means that compute is unknown to the control plane
         // or some internal failure happened. Doesn't make much sense to retry in this case.
         _ => Err((
             false,
-            format!("unexpected control plane response status code: {}", status),
-            status.to_string(),
+            format!(
+                "unexpected control plane response status code: {}",
+                resp.status()
+            ),
         )),
     }
 }
@@ -109,28 +83,17 @@ pub fn get_spec_from_control_plane(
     // - got spec -> return Ok(Some(spec))
     while attempt < 4 {
         spec = match do_control_plane_request(&cp_uri, &jwt) {
-            Ok(spec_resp) => {
-                CPLANE_REQUESTS_TOTAL
-                    .with_label_values(&[
-                        CPlaneRequestRPC::GetSpec.as_str(),
-                        &StatusCode::OK.to_string(),
-                    ])
-                    .inc();
-                match spec_resp.status {
-                    ControlPlaneComputeStatus::Empty => Ok(None),
-                    ControlPlaneComputeStatus::Attached => {
-                        if let Some(spec) = spec_resp.spec {
-                            Ok(Some(spec))
-                        } else {
-                            bail!("compute is attached, but spec is empty")
-                        }
+            Ok(spec_resp) => match spec_resp.status {
+                ControlPlaneComputeStatus::Empty => Ok(None),
+                ControlPlaneComputeStatus::Attached => {
+                    if let Some(spec) = spec_resp.spec {
+                        Ok(Some(spec))
+                    } else {
+                        bail!("compute is attached, but spec is empty")
                     }
                 }
-            }
-            Err((retry, msg, status)) => {
-                CPLANE_REQUESTS_TOTAL
-                    .with_label_values(&[CPlaneRequestRPC::GetSpec.as_str(), &status])
-                    .inc();
+            },
+            Err((retry, msg)) => {
                 if retry {
                     Err(anyhow!(msg))
                 } else {

compute_tools/src/spec_apply.rs

@@ -47,7 +47,7 @@ pub enum PerDatabasePhase {
     DeleteDBRoleReferences,
     ChangeSchemaPerms,
     HandleAnonExtension,
-    DropLogicalSubscriptions,
+    DropSubscriptionsForDeletedDatabases,
 }
 
 #[derive(Clone, Debug)]
@@ -58,13 +58,11 @@ pub enum ApplySpecPhase {
     CreateAndAlterRoles,
     RenameAndDeleteDatabases,
     CreateAndAlterDatabases,
-    CreateSchemaNeon,
     RunInEachDatabase { db: DB, subphase: PerDatabasePhase },
     HandleOtherExtensions,
     HandleNeonExtension,
     CreateAvailabilityCheck,
     DropRoles,
-    FinalizeDropLogicalSubscriptions,
 }
 
 pub struct Operation {
@@ -333,7 +331,7 @@ async fn get_operations<'a>(
                             // NB: there could be other db states, which prevent us from dropping
                             // the database. For example, if db is used by any active subscription
                             // or replication slot.
-                            // Such cases are handled in the DropLogicalSubscriptions
+                            // Such cases are handled in the DropSubscriptionsForDeletedDatabases
                             // phase. We do all the cleanup before actually dropping the database.
                             let drop_db_query: String = format!(
                                 "DROP DATABASE IF EXISTS {} WITH (FORCE)",
@@ -444,19 +442,13 @@ async fn get_operations<'a>(
 
             Ok(Box::new(operations))
         }
-        ApplySpecPhase::CreateSchemaNeon => Ok(Box::new(once(Operation {
-            query: String::from("CREATE SCHEMA IF NOT EXISTS neon"),
-            comment: Some(String::from(
-                "create schema for neon extension and utils tables",
-            )),
-        }))),
         ApplySpecPhase::RunInEachDatabase { db, subphase } => {
             match subphase {
-                PerDatabasePhase::DropLogicalSubscriptions => {
+                PerDatabasePhase::DropSubscriptionsForDeletedDatabases => {
                     match &db {
                         DB::UserDB(db) => {
                             let drop_subscription_query: String = format!(
-                                include_str!("sql/drop_subscriptions.sql"),
+                                include_str!("sql/drop_subscription_for_drop_dbs.sql"),
                                 datname_str = escape_literal(&db.name),
                             );
 
@@ -674,6 +666,10 @@ async fn get_operations<'a>(
         }
         ApplySpecPhase::HandleNeonExtension => {
             let operations = vec![
+                Operation {
+                    query: String::from("CREATE SCHEMA IF NOT EXISTS neon"),
+                    comment: Some(String::from("init: add schema for extension")),
+                },
                 Operation {
                     query: String::from("CREATE EXTENSION IF NOT EXISTS neon WITH SCHEMA neon"),
                     comment: Some(String::from(
@@ -716,9 +712,5 @@ async fn get_operations<'a>(
 
             Ok(Box::new(operations))
         }
-        ApplySpecPhase::FinalizeDropLogicalSubscriptions => Ok(Box::new(once(Operation {
-            query: String::from(include_str!("sql/finalize_drop_subscriptions.sql")),
-            comment: None,
-        }))),
     }
 }

compute_tools/src/sql/finalize_drop_subscriptions.sql

@@ -1,21 +0,0 @@
-DO $$
-BEGIN
-    IF NOT EXISTS(
-        SELECT 1
-        FROM pg_catalog.pg_tables
-        WHERE tablename = 'drop_subscriptions_done'
-        AND schemaname = 'neon'
-    )
-    THEN
-        CREATE TABLE neon.drop_subscriptions_done
-        (id serial primary key, timeline_id text);
-    END IF;
-
-    -- preserve the timeline_id of the last drop_subscriptions run
-    -- to ensure that the cleanup of a timeline is executed only once.
-    -- use upsert to avoid the table bloat in case of cascade branching (branch of a branch)
-    INSERT INTO neon.drop_subscriptions_done VALUES (1, current_setting('neon.timeline_id'))
-    ON CONFLICT (id) DO UPDATE
-    SET timeline_id = current_setting('neon.timeline_id');
-END
-$$

control_plane/README.md

@@ -1,10 +1,6 @@
-# Local Development Control Plane (`neon_local`)
+# Control Plane and Neon Local
 
-This crate contains tools to start a Neon development environment locally. This utility can be used with the `cargo neon` command.  This is a convenience to invoke
-the `neon_local` binary.
-
-**Note**: this is a dev/test tool -- a minimal control plane suitable for testing
-code changes locally, but not suitable for running production systems.
+This crate contains tools to start a Neon development environment locally. This utility can be used with the `cargo neon` command.
 
 ## Example: Start with Postgres 16
 

control_plane/src/background_process.rs

@@ -261,13 +261,7 @@ fn fill_rust_env_vars(cmd: &mut Command) -> &mut Command {
     let mut filled_cmd = cmd.env_clear().env("RUST_BACKTRACE", backtrace_setting);
 
     // Pass through these environment variables to the command
-    for var in [
-        "LLVM_PROFILE_FILE",
-        "FAILPOINTS",
-        "RUST_LOG",
-        "ASAN_OPTIONS",
-        "UBSAN_OPTIONS",
-    ] {
+    for var in ["LLVM_PROFILE_FILE", "FAILPOINTS", "RUST_LOG"] {
         if let Some(val) = std::env::var_os(var) {
             filled_cmd = filled_cmd.env(var, val);
         }

control_plane/src/bin/neon_local.rs

@@ -1357,7 +1357,6 @@ async fn handle_endpoint(subcmd: &EndpointCmd, env: &local_env::LocalEnv) -> Res
                 args.pg_version,
                 mode,
                 !args.update_catalog,
-                false,
             )?;
         }
         EndpointCmd::Start(args) => {

control_plane/src/endpoint.rs

@@ -76,7 +76,6 @@ pub struct EndpointConf {
     http_port: u16,
     pg_version: u32,
     skip_pg_catalog_updates: bool,
-    drop_subscriptions_before_start: bool,
     features: Vec<ComputeFeature>,
 }
 
@@ -144,7 +143,6 @@ impl ComputeControlPlane {
         pg_version: u32,
         mode: ComputeMode,
         skip_pg_catalog_updates: bool,
-        drop_subscriptions_before_start: bool,
     ) -> Result<Arc<Endpoint>> {
         let pg_port = pg_port.unwrap_or_else(|| self.get_port());
         let http_port = http_port.unwrap_or_else(|| self.get_port() + 1);
@@ -164,7 +162,6 @@ impl ComputeControlPlane {
             // with this we basically test a case of waking up an idle compute, where
             // we also skip catalog updates in the cloud.
             skip_pg_catalog_updates,
-            drop_subscriptions_before_start,
             features: vec![],
         });
 
@@ -180,7 +177,6 @@ impl ComputeControlPlane {
                 pg_port,
                 pg_version,
                 skip_pg_catalog_updates,
-                drop_subscriptions_before_start,
                 features: vec![],
             })?,
         )?;
@@ -244,7 +240,6 @@ pub struct Endpoint {
     // Optimizations
     skip_pg_catalog_updates: bool,
 
-    drop_subscriptions_before_start: bool,
     // Feature flags
     features: Vec<ComputeFeature>,
 }
@@ -296,7 +291,6 @@ impl Endpoint {
             tenant_id: conf.tenant_id,
             pg_version: conf.pg_version,
             skip_pg_catalog_updates: conf.skip_pg_catalog_updates,
-            drop_subscriptions_before_start: conf.drop_subscriptions_before_start,
             features: conf.features,
         })
     }
@@ -631,7 +625,6 @@ impl Endpoint {
             shard_stripe_size: Some(shard_stripe_size),
             local_proxy_config: None,
             reconfigure_concurrency: 1,
-            drop_subscriptions_before_start: self.drop_subscriptions_before_start,
         };
         let spec_path = self.endpoint_path().join("spec.json");
         std::fs::write(spec_path, serde_json::to_string_pretty(&spec)?)?;
@@ -665,22 +658,6 @@ impl Endpoint {
                     .to_str()
                     .unwrap(),
             ])
-            // TODO: It would be nice if we generated compute IDs with the same
-            // algorithm as the real control plane.
-            //
-            // TODO: Add this back when
-            // https://github.com/neondatabase/neon/pull/10747 is merged.
-            //
-            //.args([
-            //    "--compute-id",
-            //    &format!(
-            //        "compute-{}",
-            //        SystemTime::now()
-            //            .duration_since(UNIX_EPOCH)
-            //            .unwrap()
-            //            .as_secs()
-            //    ),
-            //])
             .stdin(std::process::Stdio::null())
             .stderr(logfile.try_clone()?)
             .stdout(logfile);

control_plane/src/local_env.rs

@@ -483,6 +483,7 @@ impl LocalEnv {
             .iter()
             .find(|(mapped_tenant_id, _)| mapped_tenant_id == &tenant_id)
             .map(|&(_, timeline_id)| timeline_id)
+            .map(TimelineId::from)
     }
 
     pub fn timeline_name_mappings(&self) -> HashMap<TenantTimelineId, String> {

control_plane/src/pageserver.rs

@@ -347,31 +347,11 @@ impl PageServerNode {
                 .map(|x| x.parse::<usize>())
                 .transpose()
                 .context("Failed to parse 'compaction_threshold' as an integer")?,
-            compaction_upper_limit: settings
-                .remove("compaction_upper_limit")
-                .map(|x| x.parse::<usize>())
-                .transpose()
-                .context("Failed to parse 'compaction_upper_limit' as an integer")?,
             compaction_algorithm: settings
                 .remove("compaction_algorithm")
                 .map(serde_json::from_str)
                 .transpose()
                 .context("Failed to parse 'compaction_algorithm' json")?,
-            l0_flush_delay_threshold: settings
-                .remove("l0_flush_delay_threshold")
-                .map(|x| x.parse::<usize>())
-                .transpose()
-                .context("Failed to parse 'l0_flush_delay_threshold' as an integer")?,
-            l0_flush_wait_upload: settings
-                .remove("l0_flush_wait_upload")
-                .map(|x| x.parse::<bool>())
-                .transpose()
-                .context("Failed to parse 'l0_flush_wait_upload' as a boolean")?,
-            l0_flush_stall_threshold: settings
-                .remove("l0_flush_stall_threshold")
-                .map(|x| x.parse::<usize>())
-                .transpose()
-                .context("Failed to parse 'l0_flush_stall_threshold' as an integer")?,
             gc_horizon: settings
                 .remove("gc_horizon")
                 .map(|x| x.parse::<u64>())
@@ -388,11 +368,6 @@ impl PageServerNode {
                 .map(|x| x.parse::<u8>())
                 .transpose()
                 .context("Failed to parse 'image_creation_check_threshold' as integer")?,
-            image_creation_preempt_threshold: settings
-                .remove("image_creation_preempt_threshold")
-                .map(|x| x.parse::<usize>())
-                .transpose()
-                .context("Failed to parse 'image_creation_preempt_threshold' as integer")?,
             pitr_interval: settings.remove("pitr_interval").map(|x| x.to_string()),
             walreceiver_connect_timeout: settings
                 .remove("walreceiver_connect_timeout")
@@ -443,26 +418,6 @@ impl PageServerNode {
                 .map(serde_json::from_str)
                 .transpose()
                 .context("parse `wal_receiver_protocol_override` from json")?,
-            rel_size_v2_enabled: settings
-                .remove("rel_size_v2_enabled")
-                .map(|x| x.parse::<bool>())
-                .transpose()
-                .context("Failed to parse 'rel_size_v2_enabled' as bool")?,
-            gc_compaction_enabled: settings
-                .remove("gc_compaction_enabled")
-                .map(|x| x.parse::<bool>())
-                .transpose()
-                .context("Failed to parse 'gc_compaction_enabled' as bool")?,
-            gc_compaction_initial_threshold_kb: settings
-                .remove("gc_compaction_initial_threshold_kb")
-                .map(|x| x.parse::<u64>())
-                .transpose()
-                .context("Failed to parse 'gc_compaction_initial_threshold_kb' as integer")?,
-            gc_compaction_ratio_percent: settings
-                .remove("gc_compaction_ratio_percent")
-                .map(|x| x.parse::<u64>())
-                .transpose()
-                .context("Failed to parse 'gc_compaction_ratio_percent' as integer")?,
         };
         if !settings.is_empty() {
             bail!("Unrecognized tenant settings: {settings:?}")

control_plane/src/storage_controller.rs

@@ -221,17 +221,7 @@ impl StorageController {
             "-p",
             &format!("{}", postgres_port),
         ];
-        let pg_lib_dir = self.get_pg_lib_dir().await.unwrap();
-        let envs = [
-            ("LD_LIBRARY_PATH".to_owned(), pg_lib_dir.to_string()),
-            ("DYLD_LIBRARY_PATH".to_owned(), pg_lib_dir.to_string()),
-        ];
-        let exitcode = Command::new(bin_path)
-            .args(args)
-            .envs(envs)
-            .spawn()?
-            .wait()
-            .await?;
+        let exitcode = Command::new(bin_path).args(args).spawn()?.wait().await?;
 
         Ok(exitcode.success())
     }
@@ -252,11 +242,6 @@ impl StorageController {
 
         let pg_bin_dir = self.get_pg_bin_dir().await?;
         let createdb_path = pg_bin_dir.join("createdb");
-        let pg_lib_dir = self.get_pg_lib_dir().await.unwrap();
-        let envs = [
-            ("LD_LIBRARY_PATH".to_owned(), pg_lib_dir.to_string()),
-            ("DYLD_LIBRARY_PATH".to_owned(), pg_lib_dir.to_string()),
-        ];
         let output = Command::new(&createdb_path)
             .args([
                 "-h",
@@ -269,7 +254,6 @@ impl StorageController {
                 &username(),
                 DB_NAME,
             ])
-            .envs(envs)
             .output()
             .await
             .expect("Failed to spawn createdb");
@@ -838,7 +822,10 @@ impl StorageController {
         self.dispatch(
             Method::PUT,
             format!("control/v1/tenant/{tenant_shard_id}/migrate"),
-            Some(TenantShardMigrateRequest { node_id }),
+            Some(TenantShardMigrateRequest {
+                tenant_shard_id,
+                node_id,
+            }),
         )
         .await
     }

control_plane/storcon_cli/src/main.rs

@@ -1,17 +1,12 @@
 use futures::StreamExt;
-use std::{
-    collections::{HashMap, HashSet},
-    str::FromStr,
-    time::Duration,
-};
+use std::{str::FromStr, time::Duration};
 
 use clap::{Parser, Subcommand};
 use pageserver_api::{
     controller_api::{
         AvailabilityZone, NodeAvailabilityWrapper, NodeDescribeResponse, NodeShardResponse,
-        SafekeeperDescribeResponse, SafekeeperSchedulingPolicyRequest, ShardSchedulingPolicy,
-        ShardsPreferredAzsRequest, ShardsPreferredAzsResponse, SkSchedulingPolicy,
-        TenantCreateRequest, TenantDescribeResponse, TenantPolicyRequest,
+        SafekeeperDescribeResponse, ShardSchedulingPolicy, TenantCreateRequest,
+        TenantDescribeResponse, TenantPolicyRequest,
     },
     models::{
         EvictionPolicy, EvictionPolicyLayerAccessThreshold, LocationConfigSecondary,
@@ -117,13 +112,6 @@ enum Command {
         #[arg(long)]
         node: NodeId,
     },
-    /// Migrate the secondary location for a tenant shard to a specific pageserver.
-    TenantShardMigrateSecondary {
-        #[arg(long)]
-        tenant_shard_id: TenantShardId,
-        #[arg(long)]
-        node: NodeId,
-    },
     /// Cancel any ongoing reconciliation for this shard
     TenantShardCancelReconcile {
         #[arg(long)]
@@ -158,12 +146,6 @@ enum Command {
         #[arg(long)]
         tenant_id: TenantId,
     },
-    TenantSetPreferredAz {
-        #[arg(long)]
-        tenant_id: TenantId,
-        #[arg(long)]
-        preferred_az: Option<String>,
-    },
     /// Uncleanly drop a tenant from the storage controller: this doesn't delete anything from pageservers. Appropriate
     /// if you e.g. used `tenant-warmup` by mistake on a tenant ID that doesn't really exist, or is in some other region.
     TenantDrop {
@@ -232,13 +214,6 @@ enum Command {
     },
     /// List safekeepers known to the storage controller
     Safekeepers {},
-    /// Set the scheduling policy of the specified safekeeper
-    SafekeeperScheduling {
-        #[arg(long)]
-        node_id: NodeId,
-        #[arg(long)]
-        scheduling_policy: SkSchedulingPolicyArg,
-    },
 }
 
 #[derive(Parser)]
@@ -291,17 +266,6 @@ impl FromStr for PlacementPolicyArg {
     }
 }
 
-#[derive(Debug, Clone)]
-struct SkSchedulingPolicyArg(SkSchedulingPolicy);
-
-impl FromStr for SkSchedulingPolicyArg {
-    type Err = anyhow::Error;
-
-    fn from_str(s: &str) -> Result<Self, Self::Err> {
-        SkSchedulingPolicy::from_str(s).map(Self)
-    }
-}
-
 #[derive(Debug, Clone)]
 struct ShardSchedulingPolicyArg(ShardSchedulingPolicy);
 
@@ -431,12 +395,11 @@ async fn main() -> anyhow::Result<()> {
             resp.sort_by(|a, b| a.listen_http_addr.cmp(&b.listen_http_addr));
 
             let mut table = comfy_table::Table::new();
-            table.set_header(["Id", "Hostname", "AZ", "Scheduling", "Availability"]);
+            table.set_header(["Id", "Hostname", "Scheduling", "Availability"]);
             for node in resp {
                 table.add_row([
                     format!("{}", node.id),
                     node.listen_http_addr,
-                    node.availability_zone_id,
                     format!("{:?}", node.scheduling),
                     format!("{:?}", node.availability),
                 ]);
@@ -496,65 +459,33 @@ async fn main() -> anyhow::Result<()> {
             println!("{table}");
         }
         Command::Tenants { node_id: None } => {
-            // Set up output formatting
+            let mut resp = storcon_client
+                .dispatch::<(), Vec<TenantDescribeResponse>>(
+                    Method::GET,
+                    "control/v1/tenant".to_string(),
+                    None,
+                )
+                .await?;
+
+            resp.sort_by(|a, b| a.tenant_id.cmp(&b.tenant_id));
+
             let mut table = comfy_table::Table::new();
             table.set_header([
                 "TenantId",
-                "Preferred AZ",
                 "ShardCount",
                 "StripeSize",
                 "Placement",
                 "Scheduling",
             ]);
-
-            // Pagination loop over listing API
-            let mut start_after = None;
-            const LIMIT: usize = 1000;
-            loop {
-                let path = match start_after {
-                    None => format!("control/v1/tenant?limit={LIMIT}"),
-                    Some(start_after) => {
-                        format!("control/v1/tenant?limit={LIMIT}&start_after={start_after}")
-                    }
-                };
-
-                let resp = storcon_client
-                    .dispatch::<(), Vec<TenantDescribeResponse>>(Method::GET, path, None)
-                    .await?;
-
-                if resp.is_empty() {
-                    // End of data reached
-                    break;
-                }
-
-                // Give some visual feedback while we're building up the table (comfy_table doesn't have
-                // streaming output)
-                if resp.len() >= LIMIT {
-                    eprint!(".");
-                }
-
-                start_after = Some(resp.last().unwrap().tenant_id);
-
-                for tenant in resp {
-                    let shard_zero = tenant.shards.into_iter().next().unwrap();
-                    table.add_row([
-                        format!("{}", tenant.tenant_id),
-                        shard_zero
-                            .preferred_az_id
-                            .as_ref()
-                            .cloned()
-                            .unwrap_or("".to_string()),
-                        format!("{}", shard_zero.tenant_shard_id.shard_count.literal()),
-                        format!("{:?}", tenant.stripe_size),
-                        format!("{:?}", tenant.policy),
-                        format!("{:?}", shard_zero.scheduling_policy),
-                    ]);
-                }
-            }
-
-            // Terminate progress dots
-            if table.row_count() > LIMIT {
-                eprint!("");
+            for tenant in resp {
+                let shard_zero = tenant.shards.into_iter().next().unwrap();
+                table.add_row([
+                    format!("{}", tenant.tenant_id),
+                    format!("{}", shard_zero.tenant_shard_id.shard_count.literal()),
+                    format!("{:?}", tenant.stripe_size),
+                    format!("{:?}", tenant.policy),
+                    format!("{:?}", shard_zero.scheduling_policy),
+                ]);
             }
 
             println!("{table}");
@@ -609,7 +540,10 @@ async fn main() -> anyhow::Result<()> {
             tenant_shard_id,
             node,
         } => {
-            let req = TenantShardMigrateRequest { node_id: node };
+            let req = TenantShardMigrateRequest {
+                tenant_shard_id,
+                node_id: node,
+            };
 
             storcon_client
                 .dispatch::<TenantShardMigrateRequest, TenantShardMigrateResponse>(
@@ -619,20 +553,6 @@ async fn main() -> anyhow::Result<()> {
                 )
                 .await?;
         }
-        Command::TenantShardMigrateSecondary {
-            tenant_shard_id,
-            node,
-        } => {
-            let req = TenantShardMigrateRequest { node_id: node };
-
-            storcon_client
-                .dispatch::<TenantShardMigrateRequest, TenantShardMigrateResponse>(
-                    Method::PUT,
-                    format!("control/v1/tenant/{tenant_shard_id}/migrate_secondary"),
-                    Some(req),
-                )
-                .await?;
-        }
         Command::TenantShardCancelReconcile { tenant_shard_id } => {
             storcon_client
                 .dispatch::<(), ()>(
@@ -676,19 +596,6 @@ async fn main() -> anyhow::Result<()> {
                     None,
                 )
                 .await?;
-
-            let nodes = storcon_client
-                .dispatch::<(), Vec<NodeDescribeResponse>>(
-                    Method::GET,
-                    "control/v1/node".to_string(),
-                    None,
-                )
-                .await?;
-            let nodes = nodes
-                .into_iter()
-                .map(|n| (n.id, n))
-                .collect::<HashMap<_, _>>();
-
             println!("Tenant {tenant_id}");
             let mut table = comfy_table::Table::new();
             table.add_row(["Policy", &format!("{:?}", policy)]);
@@ -697,14 +604,7 @@ async fn main() -> anyhow::Result<()> {
             println!("{table}");
             println!("Shards:");
             let mut table = comfy_table::Table::new();
-            table.set_header([
-                "Shard",
-                "Attached",
-                "Attached AZ",
-                "Secondary",
-                "Last error",
-                "status",
-            ]);
+            table.set_header(["Shard", "Attached", "Secondary", "Last error", "status"]);
             for shard in shards {
                 let secondary = shard
                     .node_secondary
@@ -727,18 +627,11 @@ async fn main() -> anyhow::Result<()> {
                 }
                 let status = status_parts.join(",");
 
-                let attached_node = shard
-                    .node_attached
-                    .as_ref()
-                    .map(|id| nodes.get(id).expect("Shard references nonexistent node"));
-
                 table.add_row([
                     format!("{}", shard.tenant_shard_id),
-                    attached_node
-                        .map(|n| format!("{} ({})", n.listen_http_addr, n.id))
-                        .unwrap_or(String::new()),
-                    attached_node
-                        .map(|n| n.availability_zone_id.clone())
+                    shard
+                        .node_attached
+                        .map(|n| format!("{}", n))
                         .unwrap_or(String::new()),
                     secondary,
                     shard.last_error,
@@ -747,66 +640,6 @@ async fn main() -> anyhow::Result<()> {
             }
             println!("{table}");
         }
-        Command::TenantSetPreferredAz {
-            tenant_id,
-            preferred_az,
-        } => {
-            // First learn about the tenant's shards
-            let describe_response = storcon_client
-                .dispatch::<(), TenantDescribeResponse>(
-                    Method::GET,
-                    format!("control/v1/tenant/{tenant_id}"),
-                    None,
-                )
-                .await?;
-
-            // Learn about nodes to validate the AZ ID
-            let nodes = storcon_client
-                .dispatch::<(), Vec<NodeDescribeResponse>>(
-                    Method::GET,
-                    "control/v1/node".to_string(),
-                    None,
-                )
-                .await?;
-
-            if let Some(preferred_az) = &preferred_az {
-                let azs = nodes
-                    .into_iter()
-                    .map(|n| (n.availability_zone_id))
-                    .collect::<HashSet<_>>();
-                if !azs.contains(preferred_az) {
-                    anyhow::bail!(
-                        "AZ {} not found on any node: known AZs are: {:?}",
-                        preferred_az,
-                        azs
-                    );
-                }
-            } else {
-                // Make it obvious to the user that since they've omitted an AZ, we're clearing it
-                eprintln!("Clearing preferred AZ for tenant {}", tenant_id);
-            }
-
-            // Construct a request that modifies all the tenant's shards
-            let req = ShardsPreferredAzsRequest {
-                preferred_az_ids: describe_response
-                    .shards
-                    .into_iter()
-                    .map(|s| {
-                        (
-                            s.tenant_shard_id,
-                            preferred_az.clone().map(AvailabilityZone),
-                        )
-                    })
-                    .collect(),
-            };
-            storcon_client
-                .dispatch::<ShardsPreferredAzsRequest, ShardsPreferredAzsResponse>(
-                    Method::PUT,
-                    "control/v1/preferred_azs".to_string(),
-                    Some(req),
-                )
-                .await?;
-        }
         Command::TenantWarmup { tenant_id } => {
             let describe_response = storcon_client
                 .dispatch::<(), TenantDescribeResponse>(
@@ -1082,7 +915,10 @@ async fn main() -> anyhow::Result<()> {
                             .dispatch::<TenantShardMigrateRequest, TenantShardMigrateResponse>(
                                 Method::PUT,
                                 format!("control/v1/tenant/{}/migrate", mv.tenant_shard_id),
-                                Some(TenantShardMigrateRequest { node_id: mv.to }),
+                                Some(TenantShardMigrateRequest {
+                                    tenant_shard_id: mv.tenant_shard_id,
+                                    node_id: mv.to,
+                                }),
                             )
                             .await
                             .map_err(|e| (mv.tenant_shard_id, mv.from, mv.to, e))
@@ -1221,23 +1057,6 @@ async fn main() -> anyhow::Result<()> {
             }
             println!("{table}");
         }
-        Command::SafekeeperScheduling {
-            node_id,
-            scheduling_policy,
-        } => {
-            let scheduling_policy = scheduling_policy.0;
-            storcon_client
-                .dispatch::<SafekeeperSchedulingPolicyRequest, ()>(
-                    Method::POST,
-                    format!("control/v1/safekeeper/{node_id}/scheduling_policy"),
-                    Some(SafekeeperSchedulingPolicyRequest { scheduling_policy }),
-                )
-                .await?;
-            println!(
-                "Scheduling policy of {node_id} set to {}",
-                String::from(scheduling_policy)
-            );
-        }
     }
 
     Ok(())

deny.toml

@@ -32,7 +32,6 @@ reason = "the marvin attack only affects private key decryption, not public key
 # https://embarkstudios.github.io/cargo-deny/checks/licenses/cfg.html
 [licenses]
 allow = [
-    "0BSD",
     "Apache-2.0",
     "BSD-2-Clause",
     "BSD-3-Clause",
@@ -42,8 +41,8 @@ allow = [
     "MIT",
     "MPL-2.0",
     "OpenSSL",
+    "Unicode-DFS-2016",
     "Unicode-3.0",
-    "Zlib",
 ]
 confidence-threshold = 0.8
 exceptions = [

docker-compose/compute_wrapper/Dockerfile

@@ -7,12 +7,14 @@ FROM $REPOSITORY/${COMPUTE_IMAGE}:$TAG
 ARG COMPUTE_IMAGE
 
 USER root
-RUN echo 'Acquire::Retries "5";' > /etc/apt/apt.conf.d/80-retries && \
-    apt-get update &&       \
+RUN apt-get update &&       \
     apt-get install -y curl \
                        jq   \
+                       python3-pip \
                        netcat-openbsd
+#Faker is required for the pg_anon test
+RUN case $COMPUTE_IMAGE in compute-node-v17) OPT="--break-system-packages";; *) OPT= ;; esac && pip3 install $OPT Faker
 #This is required for the pg_hintplan test
-RUN mkdir -p /ext-src/pg_hint_plan-src /postgres/contrib/file_fdw && chown postgres /ext-src/pg_hint_plan-src /postgres/contrib/file_fdw
+RUN mkdir -p /ext-src/pg_hint_plan-src && chown postgres /ext-src/pg_hint_plan-src 
 
-USER postgres
+USER postgres

docker-compose/compute_wrapper/shell/compute.sh

@@ -20,55 +20,30 @@ while ! nc -z pageserver 6400; do
 done
 echo "Page server is ready."
 
-cp ${SPEC_FILE_ORG} ${SPEC_FILE}
+echo "Create a tenant and timeline"
+generate_id tenant_id
+PARAMS=(
+     -X PUT
+     -H "Content-Type: application/json"
+     -d "{\"mode\": \"AttachedSingle\", \"generation\": 1, \"tenant_conf\": {}}"
+     "http://pageserver:9898/v1/tenant/${tenant_id}/location_config"
+)
+result=$(curl "${PARAMS[@]}")
+echo $result | jq .
 
- if [ -n "${TENANT_ID:-}" ] && [ -n "${TIMELINE_ID:-}" ]; then
-   tenant_id=${TENANT_ID}
-   timeline_id=${TIMELINE_ID}
-else
-  echo "Check if a tenant present"
-  PARAMS=(
-       -X GET
-       -H "Content-Type: application/json"
-       "http://pageserver:9898/v1/tenant"
-  )
-  tenant_id=$(curl "${PARAMS[@]}" | jq -r .[0].id)
-  if [ -z "${tenant_id}" ] || [ "${tenant_id}" = null ]; then
-    echo "Create a tenant"
-    generate_id tenant_id
-    PARAMS=(
-         -X PUT
-         -H "Content-Type: application/json"
-         -d "{\"mode\": \"AttachedSingle\", \"generation\": 1, \"tenant_conf\": {}}"
-        "http://pageserver:9898/v1/tenant/${tenant_id}/location_config"
-    )
-    result=$(curl "${PARAMS[@]}")
-    echo $result | jq .
-  fi
-
-  echo "Check if a timeline present"
-  PARAMS=(
-       -X GET
-       -H "Content-Type: application/json"
-       "http://pageserver:9898/v1/tenant/${tenant_id}/timeline"
-  )
-  timeline_id=$(curl "${PARAMS[@]}" | jq -r .[0].timeline_id)
-  if [ -z "${timeline_id}" ] || [ "${timeline_id}" = null ]; then
-    generate_id timeline_id
-    PARAMS=(
-        -sbf
-        -X POST
-        -H "Content-Type: application/json"
-        -d "{\"new_timeline_id\": \"${timeline_id}\", \"pg_version\": ${PG_VERSION}}"
-        "http://pageserver:9898/v1/tenant/${tenant_id}/timeline/"
-    )
-    result=$(curl "${PARAMS[@]}")
-    echo $result | jq .
-  fi
-fi
+generate_id timeline_id
+PARAMS=(
+     -sbf
+     -X POST
+     -H "Content-Type: application/json"
+     -d "{\"new_timeline_id\": \"${timeline_id}\", \"pg_version\": ${PG_VERSION}}"
+     "http://pageserver:9898/v1/tenant/${tenant_id}/timeline/"
+)
+result=$(curl "${PARAMS[@]}")
+echo $result | jq .
 
 echo "Overwrite tenant id and timeline id in spec file"
-sed -i "s/TENANT_ID/${tenant_id}/" ${SPEC_FILE}
+sed "s/TENANT_ID/${tenant_id}/" ${SPEC_FILE_ORG} > ${SPEC_FILE}
 sed -i "s/TIMELINE_ID/${timeline_id}/" ${SPEC_FILE}
 
 cat ${SPEC_FILE}

docker-compose/docker-compose.yml

@@ -149,13 +149,11 @@ services:
       args:
         - REPOSITORY=${REPOSITORY:-neondatabase}
         - COMPUTE_IMAGE=compute-node-v${PG_VERSION:-16}
-        - TAG=${COMPUTE_TAG:-${TAG:-latest}}
-        - http_proxy=${http_proxy:-}
-        - https_proxy=${https_proxy:-}
+        - TAG=${TAG:-latest}
+        - http_proxy=$http_proxy
+        - https_proxy=$https_proxy
     environment:
       - PG_VERSION=${PG_VERSION:-16}
-      - TENANT_ID=${TENANT_ID:-}
-      - TIMELINE_ID=${TIMELINE_ID:-}
       #- RUST_BACKTRACE=1
     # Mount the test files directly, for faster editing cycle.
     volumes:
@@ -187,8 +185,6 @@ services:
   neon-test-extensions:
     profiles: ["test-extensions"]
     image: ${REPOSITORY:-neondatabase}/neon-test-extensions-v${PG_TEST_VERSION:-16}:${TAG:-latest}
-    environment:
-      - PGPASSWORD=cloud_admin
     entrypoint:
       - "/bin/bash"
       - "-c"

docker-compose/docker_compose_test.sh

@@ -18,10 +18,14 @@ cd $(dirname $0)
 COMPUTE_CONTAINER_NAME=docker-compose-compute-1
 TEST_CONTAINER_NAME=docker-compose-neon-test-extensions-1
 PSQL_OPTION="-h localhost -U cloud_admin -p 55433 -d postgres"
+: ${http_proxy:=}
+: ${https_proxy:=}
+export http_proxy https_proxy
 
 cleanup() {
     echo "show container information"
     docker ps
+    docker compose --profile test-extensions -f $COMPOSE_FILE logs
     echo "stop containers..."
     docker compose --profile test-extensions -f $COMPOSE_FILE down
 }
@@ -31,7 +35,13 @@ for pg_version in ${TEST_VERSION_ONLY-14 15 16 17}; do
     echo "clean up containers if exists"
     cleanup
     PG_TEST_VERSION=$((pg_version < 16 ? 16 : pg_version))
-    PG_VERSION=$pg_version PG_TEST_VERSION=$PG_TEST_VERSION docker compose --profile test-extensions -f $COMPOSE_FILE up --quiet-pull --build -d
+    # The support of pg_anon not yet added to PG17, so we have to add the corresponding option for other PG versions
+    if [ "${pg_version}" -ne 17 ]; then
+      SPEC_PATH="compute_wrapper/var/db/postgres/specs"
+      mv $SPEC_PATH/spec.json $SPEC_PATH/spec.bak
+      jq '.cluster.settings += [{"name": "session_preload_libraries","value": "anon","vartype": "string"}]' "${SPEC_PATH}/spec.bak" > "${SPEC_PATH}/spec.json"
+    fi
+    PG_VERSION=$pg_version PG_TEST_VERSION=$PG_TEST_VERSION docker compose --profile test-extensions -f $COMPOSE_FILE up --build -d
 
     echo "wait until the compute is ready. timeout after 60s. "
     cnt=0
@@ -40,6 +50,7 @@ for pg_version in ${TEST_VERSION_ONLY-14 15 16 17}; do
         cnt=`expr $cnt + 3`
         if [ $cnt -gt 60 ]; then
             echo "timeout before the compute is ready."
+            cleanup
             exit 1
         fi
         if docker compose --profile test-extensions -f $COMPOSE_FILE logs "compute_is_ready" | grep -q "accepting connections"; then
@@ -51,46 +62,52 @@ for pg_version in ${TEST_VERSION_ONLY-14 15 16 17}; do
     done
 
     if [ $pg_version -ge 16 ]; then
-        docker cp ext-src $TEST_CONTAINER_NAME:/
-        docker exec $TEST_CONTAINER_NAME bash -c "apt update && apt install -y libtap-parser-sourcehandler-pgtap-perl"
+        echo Enabling trust connection
+        docker exec $COMPUTE_CONTAINER_NAME bash -c "sed -i '\$d' /var/db/postgres/compute/pg_hba.conf && echo -e 'host\t all\t all\t all\t trust' >> /var/db/postgres/compute/pg_hba.conf && psql $PSQL_OPTION -c 'select pg_reload_conf()' "
+        echo Adding postgres role
+        docker exec $COMPUTE_CONTAINER_NAME psql $PSQL_OPTION -c "CREATE ROLE postgres SUPERUSER LOGIN"
         # This is required for the pg_hint_plan test, to prevent flaky log message causing the test to fail
         # It cannot be moved to Dockerfile now because the database directory is created after the start of the container
         echo Adding dummy config
         docker exec $COMPUTE_CONTAINER_NAME touch /var/db/postgres/compute/compute_ctl_temp_override.conf
-        # The following block copies the files for the pg_hintplan test to the compute node for the extension test in an isolated docker-compose environment
+        # This block is required for the pg_anon extension test.
+        # The test assumes that it is running on the same host with the postgres engine.
+        # In our case it's not true, that's why we are copying files to the compute node
         TMPDIR=$(mktemp -d)
+        # Add support for pg_anon for pg_v16
+        if [ $pg_version -ne 17 ]; then
+          docker cp $TEST_CONTAINER_NAME:/ext-src/pg_anon-src/data $TMPDIR/data
+          echo -e '1\t too \t many \t tabs' > $TMPDIR/data/bad.csv
+          docker cp $TMPDIR/data $COMPUTE_CONTAINER_NAME:/tmp/tmp_anon_alternate_data
+        rm -rf $TMPDIR
+        fi
+        TMPDIR=$(mktemp -d)
+        # The following block does the same for the pg_hintplan test
         docker cp $TEST_CONTAINER_NAME:/ext-src/pg_hint_plan-src/data $TMPDIR/data
         docker cp $TMPDIR/data $COMPUTE_CONTAINER_NAME:/ext-src/pg_hint_plan-src/
         rm -rf $TMPDIR
-        # The following block does the same for the contrib/file_fdw test
-        TMPDIR=$(mktemp -d)
-        docker cp $TEST_CONTAINER_NAME:/postgres/contrib/file_fdw/data $TMPDIR/data
-        docker cp $TMPDIR/data $COMPUTE_CONTAINER_NAME:/postgres/contrib/file_fdw/data
-        rm -rf $TMPDIR
-        # Apply patches
-        cat ../compute/patches/contrib_pg${pg_version}.patch | docker exec -i $TEST_CONTAINER_NAME bash -c "(cd /postgres && patch -p1)"
         # We are running tests now
-        rm -f testout.txt testout_contrib.txt
-        docker exec -e USE_PGXS=1 -e SKIP=timescaledb-src,rdkit-src,postgis-src,pgx_ulid-src,pgtap-src,pg_tiktoken-src,pg_jsonschema-src,kq_imcx-src,wal2json_2_5-src \
-        $TEST_CONTAINER_NAME /run-tests.sh /ext-src | tee testout.txt && EXT_SUCCESS=1 || EXT_SUCCESS=0
-        docker exec -e SKIP=start-scripts,postgres_fdw,ltree_plpython,jsonb_plpython,jsonb_plperl,hstore_plpython,hstore_plperl,dblink,bool_plperl \
-        $TEST_CONTAINER_NAME /run-tests.sh /postgres/contrib | tee testout_contrib.txt && CONTRIB_SUCCESS=1 || CONTRIB_SUCCESS=0
-        if [ $EXT_SUCCESS -eq 0 ] || [ $CONTRIB_SUCCESS -eq 0 ]; then
-            CONTRIB_FAILED=
-            FAILED=
-            [ $EXT_SUCCESS -eq 0 ] && FAILED=$(tail -1 testout.txt | awk '{for(i=1;i<=NF;i++){print "/ext-src/"$i;}}')
-            [ $CONTRIB_SUCCESS -eq 0 ] && CONTRIB_FAILED=$(tail -1 testout_contrib.txt | awk '{for(i=0;i<=NF;i++){print "/postgres/contrib/"$i;}}')
-            for d in $FAILED $CONTRIB_FAILED; do
-                dn="$(basename $d)"
-                rm -rf $dn
-                mkdir $dn
-                docker cp $TEST_CONTAINER_NAME:$d/regression.diffs $dn || [ $? -eq 1 ]
-                docker cp $TEST_CONTAINER_NAME:$d/regression.out $dn || [ $? -eq 1 ]
-                cat $dn/regression.out $dn/regression.diffs || true
-                rm -rf $dn
+        if docker exec -e SKIP=timescaledb-src,rdkit-src,postgis-src,pgx_ulid-src,pgtap-src,pg_tiktoken-src,pg_jsonschema-src,pg_graphql-src,kq_imcx-src,wal2json_2_5-src \
+            $TEST_CONTAINER_NAME /run-tests.sh | tee testout.txt
+        then
+            cleanup
+        else
+            FAILED=$(tail -1 testout.txt)
+            for d in $FAILED
+            do
+                mkdir $d
+                docker cp $TEST_CONTAINER_NAME:/ext-src/$d/regression.diffs $d || true
+                docker cp $TEST_CONTAINER_NAME:/ext-src/$d/regression.out $d || true
+                cat $d/regression.out $d/regression.diffs || true
             done
         rm -rf $FAILED
+        cleanup
         exit 1
         fi
     fi
+    cleanup
+    # Restore the original spec.json
+    if [ "$pg_version" -ne 17 ]; then
+      mv "$SPEC_PATH/spec.bak" "$SPEC_PATH/spec.json"
+    fi
 done

docker-compose/ext-src/hll-src/test-upgrade.sh

@@ -1,5 +0,0 @@
-#!/bin/sh
-set -ex
-cd "$(dirname ${0})"
-PG_REGRESS=$(dirname "$(pg_config --pgxs)")/../test/regress/pg_regress
-${PG_REGRESS} --use-existing --inputdir=./ --bindir='/usr/local/pgsql/bin'    --dbname=contrib_regression add_agg agg_oob auto_sparse card_op cast_shape copy_binary cumulative_add_cardinality_correction cumulative_add_comprehensive_promotion cumulative_add_sparse_edge cumulative_add_sparse_random cumulative_add_sparse_step cumulative_union_comprehensive cumulative_union_explicit_explicit cumulative_union_explicit_promotion cumulative_union_probabilistic_probabilistic cumulative_union_sparse_full_representation cumulative_union_sparse_promotion cumulative_union_sparse_sparse disable_hashagg equal explicit_thresh hash hash_any meta_func murmur_bigint murmur_bytea nosparse notequal scalar_oob storedproc transaction typmod typmod_insert union_op

docker-compose/ext-src/hypopg-src/test-upgrade.patch

@@ -1,27 +0,0 @@
-diff --git a/expected/hypopg.out b/expected/hypopg.out
-index 90121d0..859260b 100644
---- a/expected/hypopg.out
-+++ b/expected/hypopg.out
-@@ -11,7 +11,8 @@ BEGIN
- END;
- $_$
- LANGUAGE plpgsql;
--CREATE EXTENSION hypopg;
-+CREATE EXTENSION IF NOT EXISTS hypopg;
-+NOTICE:  extension "hypopg" already exists, skipping
- CREATE TABLE hypo (id integer, val text, "Id2" bigint);
- INSERT INTO hypo SELECT i, 'line ' || i
- FROM generate_series(1,100000) f(i);
-diff --git a/test/sql/hypopg.sql b/test/sql/hypopg.sql
-index 99722b0..8d6bacb 100644
---- a/test/sql/hypopg.sql
-+++ b/test/sql/hypopg.sql
-@@ -12,7 +12,7 @@ END;
- $_$
- LANGUAGE plpgsql;
-
--CREATE EXTENSION hypopg;
-+CREATE EXTENSION IF NOT EXISTS hypopg;
-
- CREATE TABLE hypo (id integer, val text, "Id2" bigint);
-

docker-compose/ext-src/hypopg-src/test-upgrade.sh

@@ -1,6 +0,0 @@
-#!/bin/sh
-set -ex
-cd "$(dirname ${0})"
-patch -p1 <test-upgrade.patch
-PG_REGRESS=$(dirname "$(pg_config --pgxs)")/../test/regress/pg_regress
-${PG_REGRESS} --inputdir=./ --bindir='/usr/local/pgsql/bin' --use-existing --inputdir=test --dbname=contrib_regression hypopg hypo_brin hypo_index_part hypo_include hypo_hash hypo_hide_index

docker-compose/ext-src/ip4r-src/test-upgrade.patch

@@ -1,23 +0,0 @@
-diff --git a/expected/ip4r.out b/expected/ip4r.out
-index 7527af3..b38ed29 100644
---- a/expected/ip4r.out
-+++ b/expected/ip4r.out
-@@ -1,6 +1,5 @@
- --
- /*CUT-HERE*/
--CREATE EXTENSION ip4r;
- -- Check whether any of our opclasses fail amvalidate
- DO $d$
-   DECLARE
-diff --git a/sql/ip4r.sql b/sql/ip4r.sql
-index 65c49ec..24ade09 100644
---- a/sql/ip4r.sql
-+++ b/sql/ip4r.sql
-@@ -1,7 +1,6 @@
- --
-
- /*CUT-HERE*/
--CREATE EXTENSION ip4r;
-
- -- Check whether any of our opclasses fail amvalidate
-

docker-compose/ext-src/ip4r-src/test-upgrade.sh

@@ -1,6 +0,0 @@
-#!/bin/sh
-set -ex
-cd "$(dirname ${0})"
-patch -p1 <test-upgrade.patch
-PG_REGRESS=$(dirname "$(pg_config --pgxs)")/../test/regress/pg_regress
-${PG_REGRESS} --use-existing --inputdir=./ --bindir='/usr/local/pgsql/bin'    --dbname=contrib_regression ip4r ip4r-softerr ip4r-v11

docker-compose/ext-src/pg_cron-src/test-upgrade.patch

@@ -1,75 +0,0 @@
-diff --git a/expected/pg_cron-test.out b/expected/pg_cron-test.out
-index d79d542..1663886 100644
---- a/expected/pg_cron-test.out
-+++ b/expected/pg_cron-test.out
-@@ -1,30 +1,3 @@
--CREATE EXTENSION pg_cron VERSION '1.0';
--SELECT extversion FROM pg_extension WHERE extname='pg_cron';
-- extversion 
--------------
-- 1.0
--(1 row)
--
---- Test binary compatibility with v1.4 function signature.
--ALTER EXTENSION pg_cron UPDATE TO '1.4';
--SELECT cron.unschedule(job_name := 'no_such_job');
--ERROR:  could not find valid entry for job 'no_such_job'
--SELECT cron.schedule('testjob', '* * * * *', 'SELECT 1');
-- schedule 
------------
--        1
--(1 row)
--
--SELECT cron.unschedule('testjob');
-- unschedule 
--------------
-- t
--(1 row)
--
---- Test cache invalidation
--DROP EXTENSION pg_cron;
--CREATE EXTENSION pg_cron VERSION '1.4';
--ALTER EXTENSION pg_cron UPDATE;
- -- Vacuum every day at 10:00am (GMT)
- SELECT cron.schedule('0 10 * * *', 'VACUUM');
-  schedule 
-@@ -300,8 +273,3 @@ SELECT jobid, jobname, schedule, command FROM cron.job ORDER BY jobid;
- SELECT cron.schedule('bad-last-dom-job1', '0 11 $foo * *', 'VACUUM FULL');
- ERROR:  invalid schedule: 0 11 $foo * *
- HINT:  Use cron format (e.g. 5 4 * * *), or interval format '[1-59] seconds'
---- cleaning
--DROP EXTENSION pg_cron;
--drop user pgcron_cront;
--drop database pgcron_dbno;
--drop database pgcron_dbyes;
-diff --git a/sql/pg_cron-test.sql b/sql/pg_cron-test.sql
-index 45f94d9..241cf73 100644
---- a/sql/pg_cron-test.sql
-+++ b/sql/pg_cron-test.sql
-@@ -1,17 +1,3 @@
--CREATE EXTENSION pg_cron VERSION '1.0';
--SELECT extversion FROM pg_extension WHERE extname='pg_cron';
---- Test binary compatibility with v1.4 function signature.
--ALTER EXTENSION pg_cron UPDATE TO '1.4';
--SELECT cron.unschedule(job_name := 'no_such_job');
--SELECT cron.schedule('testjob', '* * * * *', 'SELECT 1');
--SELECT cron.unschedule('testjob');
--
---- Test cache invalidation
--DROP EXTENSION pg_cron;
--CREATE EXTENSION pg_cron VERSION '1.4';
--
--ALTER EXTENSION pg_cron UPDATE;
--
- -- Vacuum every day at 10:00am (GMT)
- SELECT cron.schedule('0 10 * * *', 'VACUUM');
- 
-@@ -156,8 +142,3 @@ SELECT jobid, jobname, schedule, command FROM cron.job ORDER BY jobid;
- -- invalid last of day job
- SELECT cron.schedule('bad-last-dom-job1', '0 11 $foo * *', 'VACUUM FULL');
- 
---- cleaning
--DROP EXTENSION pg_cron;
--drop user pgcron_cront;
--drop database pgcron_dbno;
--drop database pgcron_dbyes;

docker-compose/ext-src/pg_cron-src/test-upgrade.sh

@@ -1,6 +0,0 @@
-#!/bin/sh
-set -ex
-cd "$(dirname ${0})"
-patch -p1 <test-upgrade.patch
-PG_REGRESS=$(dirname "$(pg_config --pgxs)")/../test/regress/pg_regress
-${PG_REGRESS} --use-existing --inputdir=./ --bindir='/usr/local/pgsql/bin'    --dbname=contrib_regression pg_cron-test

docker-compose/ext-src/pg_graphql-src/neon-test.sh

@@ -1,13 +0,0 @@
-#!/bin/bash
-set -ex
-cd "$(dirname "${0}")"
-dropdb --if-exists contrib_regression
-createdb contrib_regression
-PGXS="$(dirname "$(pg_config --pgxs)" )"
-REGRESS="${PGXS}/../test/regress/pg_regress"
-TESTDIR="test"
-TESTS=$(ls "${TESTDIR}/sql" | sort )
-TESTS=${TESTS//\.sql/}
-psql -v ON_ERROR_STOP=1 -f test/fixtures.sql -d contrib_regression
-${REGRESS} --use-existing --dbname=contrib_regression --inputdir=${TESTDIR} ${TESTS}
-

docker-compose/ext-src/pg_ivm-src/test-upgrade.patch

@@ -1,18 +0,0 @@
-diff --git a/expected/pg_ivm.out b/expected/pg_ivm.out
-index e8798ee..cca58d0 100644
---- a/expected/pg_ivm.out
-+++ b/expected/pg_ivm.out
-@@ -1,4 +1,3 @@
--CREATE EXTENSION pg_ivm;
- GRANT ALL ON SCHEMA public TO public;
- -- create a table to use as a basis for views and materialized views in various combinations
- CREATE TABLE mv_base_a (i int, j int);
-diff --git a/sql/pg_ivm.sql b/sql/pg_ivm.sql
-index d3c1a01..9382d7f 100644
---- a/sql/pg_ivm.sql
-+++ b/sql/pg_ivm.sql
-@@ -1,4 +1,3 @@
--CREATE EXTENSION pg_ivm;
- GRANT ALL ON SCHEMA public TO public;
- 
- -- create a table to use as a basis for views and materialized views in various combinations

docker-compose/ext-src/pg_ivm-src/test-upgrade.sh

@@ -1,6 +0,0 @@
-#!/bin/sh
-set -ex
-cd "$(dirname ${0})"
-patch -p1 <test-upgrade.patch
-PG_REGRESS=$(dirname "$(pg_config --pgxs)")/../test/regress/pg_regress
-${PG_REGRESS} --use-existing --inputdir=./ --bindir='/usr/local/pgsql/bin' --dbname=contrib_regression pg_ivm create_immv refresh_immv

docker-compose/ext-src/pg_roaringbitmap-src/test-upgrade.patch

@@ -1,25 +0,0 @@
-diff --git a/expected/roaringbitmap.out b/expected/roaringbitmap.out
-index de70531..a5f7c15 100644
---- a/expected/roaringbitmap.out
-+++ b/expected/roaringbitmap.out
-@@ -1,7 +1,6 @@
- --
- --  Test roaringbitmap extension
- --
--CREATE EXTENSION if not exists roaringbitmap;
- -- Test input and output
- set roaringbitmap.output_format='array';
- set extra_float_digits = 0;
-diff --git a/sql/roaringbitmap.sql b/sql/roaringbitmap.sql
-index a0e9c74..84bc966 100644
---- a/sql/roaringbitmap.sql
-+++ b/sql/roaringbitmap.sql
-@@ -2,8 +2,6 @@
- --  Test roaringbitmap extension
- --
- 
--CREATE EXTENSION if not exists roaringbitmap;
--
- -- Test input and output
- 
- set roaringbitmap.output_format='array';

docker-compose/ext-src/pg_roaringbitmap-src/test-upgrade.sh

@@ -1,6 +0,0 @@
-#!/bin/sh
-set -ex
-cd "$(dirname ${0})"
-patch -p1 <test-upgrade.patch
-PG_REGRESS=$(dirname "$(pg_config --pgxs)")/../test/regress/pg_regress
-${PG_REGRESS} --use-existing --inputdir=./ --bindir='/usr/local/pgsql/bin'    --dbname=contrib_regression roaringbitmap

docker-compose/ext-src/pg_semver-src/test-upgrade.patch

@@ -1,24 +0,0 @@
-diff --git a/test/sql/base.sql b/test/sql/base.sql
-index af599d8..2eed91b 100644
---- a/test/sql/base.sql
-+++ b/test/sql/base.sql
-@@ -2,7 +2,6 @@
- BEGIN;
- 
- \i test/pgtap-core.sql
--\i sql/semver.sql
- 
- SELECT plan(334);
- --SELECT * FROM no_plan();
-diff --git a/test/sql/corpus.sql b/test/sql/corpus.sql
-index 1f5f637..a519905 100644
---- a/test/sql/corpus.sql
-+++ b/test/sql/corpus.sql
-@@ -4,7 +4,6 @@ BEGIN;
- -- Test the SemVer corpus from https://regex101.com/r/Ly7O1x/3/.
- 
- \i test/pgtap-core.sql
--\i sql/semver.sql
- 
- SELECT plan(71);
- --SELECT * FROM no_plan();

docker-compose/ext-src/pg_semver-src/test-upgrade.sh

@@ -1,6 +0,0 @@
-#!/bin/sh
-set -ex
-cd "$(dirname ${0})"
-patch -p1 <test-upgrade.patch
-PG_REGRESS=$(dirname "$(pg_config --pgxs)")/../test/regress/pg_regress
-${PG_REGRESS} --use-existing --inputdir=./ --bindir='/usr/local/pgsql/bin'    --inputdir=test --dbname=contrib_regression base corpus

docker-compose/ext-src/pg_uuidv7-src/test-upgrade.sh

@@ -1,5 +0,0 @@
-#!/bin/sh
-set -ex
-cd "$(dirname ${0})"
-PG_REGRESS=$(dirname "$(pg_config --pgxs)")/../test/regress/pg_regress
-${PG_REGRESS} --use-existing --inputdir=./ --bindir='/usr/local/pgsql/bin'    --inputdir=test --dbname=contrib_regression  002_uuid_generate_v7 003_uuid_v7_to_timestamptz 004_uuid_timestamptz_to_v7 005_uuid_v7_to_timestamp 006_uuid_timestamp_to_v7

docker-compose/ext-src/pgjwt-src/neon-test.sh

@@ -1,4 +0,0 @@
-#!/bin/bash
-set -ex
-cd "$(dirname "${0}")"
-pg_prove test.sql

docker-compose/ext-src/pgjwt-src/test-upgrade.patch

@@ -1,15 +0,0 @@
-diff --git a/test.sql b/test.sql
-index d7a0ca8..f15bc76 100644
---- a/test.sql
-+++ b/test.sql
-@@ -9,9 +9,7 @@
- \set ON_ERROR_STOP true
- \set QUIET 1
- 
--CREATE EXTENSION pgcrypto;
--CREATE EXTENSION pgtap;
--CREATE EXTENSION pgjwt;
-+CREATE EXTENSION IF NOT EXISTS pgtap;
- 
- BEGIN;
- SELECT plan(23);

docker-compose/ext-src/pgjwt-src/test-upgrade.sh

@@ -1,5 +0,0 @@
-#!/bin/sh
-set -ex
-cd "$(dirname ${0})"
-patch -p1 <test-upgrade.patch
-pg_prove -d contrib_regression test.sql

docker-compose/ext-src/pgvector-src/test-upgrade.sh

@@ -1,5 +0,0 @@
-#!/bin/sh
-set -ex
-cd "$(dirname ${0})"
-PG_REGRESS=$(dirname "$(pg_config --pgxs)")/../test/regress/pg_regress
-${PG_REGRESS} --inputdir=./ --bindir='/usr/local/pgsql/bin' --inputdir=test --use-existing --dbname=contrib_regression bit btree cast copy halfvec hnsw_bit hnsw_halfvec hnsw_sparsevec hnsw_vector ivfflat_bit ivfflat_halfvec ivfflat_vector sparsevec vector_type

docker-compose/ext-src/plv8-src/test-upgrade.sh

@@ -1,5 +0,0 @@
-#!/bin/sh
-set -ex
-cd "$(dirname ${0})"
-PG_REGRESS=$(dirname "$(pg_config --pgxs)")/../test/regress/pg_regress
-${PG_REGRESS} --inputdir=./ --bindir='/usr/local/pgsql/bin'  --use-existing --dbname=contrib_regression plv8 plv8-errors scalar_args inline json startup_pre startup varparam json_conv jsonb_conv window guc es6 arraybuffer composites currentresource startup_perms bytea find_function_perms memory_limits reset show array_spread regression dialect bigint procedure

docker-compose/ext-src/postgresql-unit-src/test-upgrade.sh

@@ -1,5 +0,0 @@
-#!/bin/sh
-set -ex
-cd "$(dirname ${0})"
-PG_REGRESS=$(dirname "$(pg_config --pgxs)")/../test/regress/pg_regress
-${PG_REGRESS} --inputdir=./ --bindir='/usr/local/pgsql/bin' --use-existing --dbname=contrib_regression extension tables unit binary unicode prefix units time temperature functions language_functions round derived compare aggregate iec custom crosstab convert

docker-compose/ext-src/prefix-src/test-upgrade.sh

@@ -1,5 +0,0 @@
-#!/bin/sh
-set -ex
-cd "$(dirname ${0})"
-PG_REGRESS=$(dirname "$(pg_config --pgxs)")/../test/regress/pg_regress
-${PG_REGRESS} --use-existing --inputdir=./ --bindir='/usr/local/pgsql/bin'    --dbname=contrib_regression prefix falcon explain queries

docker-compose/ext-src/rum-src/test-upgrade.patch

@@ -1,19 +0,0 @@
-diff --git a/expected/rum.out b/expected/rum.out
-index 5966d19..8860b79 100644
---- a/expected/rum.out
-+++ b/expected/rum.out
-@@ -1,4 +1,3 @@
--CREATE EXTENSION rum;
- CREATE TABLE test_rum( t text, a tsvector );
- CREATE TRIGGER tsvectorupdate
- BEFORE UPDATE OR INSERT ON test_rum
-diff --git a/sql/rum.sql b/sql/rum.sql
-index 8414bb9..898e6ab 100644
---- a/sql/rum.sql
-+++ b/sql/rum.sql
-@@ -1,5 +1,3 @@
--CREATE EXTENSION rum;
--
- CREATE TABLE test_rum( t text, a tsvector );
-
- CREATE TRIGGER tsvectorupdate

docker-compose/ext-src/rum-src/test-upgrade.sh

@@ -1,6 +0,0 @@
-#!/bin/sh
-set -ex
-cd "$(dirname ${0})"
-patch -p1 <test-upgrade.patch
-PG_REGRESS=$(dirname "$(pg_config --pgxs)")/../test/regress/pg_regress
-${PG_REGRESS} --inputdir=./ --bindir='/usr/local/pgsql/bin' --use-existing --dbname=contrib_regression rum rum_validate rum_hash ruminv timestamp orderby orderby_hash altorder altorder_hash limits int2 int4 int8 float4 float8 money oid time timetz date interval macaddr inet cidr text varchar char bytea bit varbit numeric rum_weight expr array

docker-compose/run-tests.sh

@@ -1,22 +1,14 @@
 #!/bin/bash
 set -x
 
-extdir=${1}
-
-cd "${extdir}" || exit 2
+cd /ext-src || exit 2
 FAILED=
-LIST=$( (echo -e "${SKIP//","/"\n"}"; ls) | sort | uniq -u)
-for d in ${LIST}; do
-    [ -d "${d}" ] || continue
-    if ! psql -w -c "select 1" >/dev/null; then
-      FAILED="${d} ${FAILED}"
-      break
-    fi
-    if [ -f "${d}/neon-test.sh" ]; then
-       "${d}/neon-test.sh" || FAILED="${d} ${FAILED}"
-    else
+LIST=$( (echo -e "${SKIP//","/"\n"}"; ls -d -- *-src) | sort | uniq -u)
+for d in ${LIST}
+do
+       [ -d "${d}" ] || continue
+    psql -c "select 1" >/dev/null || break
        USE_PGXS=1 make -C "${d}" installcheck || FAILED="${d} ${FAILED}"
-    fi
 done
 [ -z "${FAILED}" ] && exit 0
 echo "${FAILED}"

docker-compose/test_extensions_upgrade.sh

@@ -1,94 +0,0 @@
-#!/bin/bash
-set -eux -o pipefail
-cd "$(dirname "${0}")"
-# Takes a variable name as argument. The result is stored in that variable.
-generate_id() {
-    local -n resvar=$1
-    printf -v resvar '%08x%08x%08x%08x' $SRANDOM $SRANDOM $SRANDOM $SRANDOM
-}
-if [ -z ${OLDTAG+x} ] || [ -z ${NEWTAG+x} ] || [ -z "${OLDTAG}" ] || [ -z "${NEWTAG}" ]; then
-  echo OLDTAG and NEWTAG must be defined
-  exit 1
-fi
-export PG_VERSION=${PG_VERSION:-16}
-function wait_for_ready {
-  TIME=0
-  while ! docker compose logs compute_is_ready | grep -q "accepting connections" && [ ${TIME} -le 300 ] ; do
-    ((TIME += 1 ))
-    sleep 1
-  done
-  if [ ${TIME} -gt 300 ]; then
-    echo Time is out.
-    exit 2
-  fi
-}
-function create_extensions() {
-  for ext in ${1}; do
-    docker compose exec neon-test-extensions psql -X -v ON_ERROR_STOP=1 -d contrib_regression -c "CREATE EXTENSION IF NOT EXISTS ${ext} CASCADE"
-  done
-}
-EXTENSIONS='[
-{"extname": "plv8", "extdir": "plv8-src"},
-{"extname": "vector", "extdir": "pgvector-src"},
-{"extname": "unit", "extdir": "postgresql-unit-src"},
-{"extname": "hypopg", "extdir": "hypopg-src"},
-{"extname": "rum", "extdir": "rum-src"},
-{"extname": "ip4r", "extdir": "ip4r-src"},
-{"extname": "prefix", "extdir": "prefix-src"},
-{"extname": "hll", "extdir": "hll-src"},
-{"extname": "pg_cron", "extdir": "pg_cron-src"},
-{"extname": "pg_uuidv7", "extdir": "pg_uuidv7-src"},
-{"extname": "roaringbitmap", "extdir": "pg_roaringbitmap-src"},
-{"extname": "semver", "extdir": "pg_semver-src"},
-{"extname": "pg_ivm", "extdir": "pg_ivm-src"},
-{"extname": "pgjwt", "extdir": "pgjwt-src"}
-]'
-EXTNAMES=$(echo ${EXTENSIONS} | jq -r '.[].extname' | paste -sd ' ' -)
-TAG=${NEWTAG} docker compose --profile test-extensions up --quiet-pull --build -d
-wait_for_ready
-docker compose exec neon-test-extensions psql -c "DROP DATABASE IF EXISTS contrib_regression"
-docker compose exec neon-test-extensions psql -c "CREATE DATABASE contrib_regression"
-create_extensions "${EXTNAMES}"
-query="select json_object_agg(extname,extversion) from pg_extension where extname in ('${EXTNAMES// /\',\'}')"
-new_vers=$(docker compose exec neon-test-extensions psql -Aqt -d contrib_regression -c "$query")
-docker compose --profile test-extensions down
-TAG=${OLDTAG} docker compose --profile test-extensions up --quiet-pull --build -d --force-recreate
-wait_for_ready
-docker compose cp  ext-src neon-test-extensions:/
-docker compose exec neon-test-extensions psql -c "DROP DATABASE IF EXISTS contrib_regression"
-docker compose exec neon-test-extensions psql -c "CREATE DATABASE contrib_regression"
-create_extensions "${EXTNAMES}"
-query="select pge.extname from pg_extension pge join (select key as extname, value as extversion from json_each_text('${new_vers}')) x on pge.extname=x.extname and pge.extversion <> x.extversion"
-exts=$(docker compose exec neon-test-extensions psql -Aqt -d contrib_regression -c "$query")
-if [ -z "${exts}" ]; then
-  echo "No extensions were upgraded"
-else
-  tenant_id=$(docker compose exec neon-test-extensions psql -Aqt -c "SHOW neon.tenant_id")
-  timeline_id=$(docker compose exec neon-test-extensions psql -Aqt -c "SHOW neon.timeline_id")
-  for ext in ${exts}; do
-    echo Testing ${ext}...
-    EXTDIR=$(echo ${EXTENSIONS} | jq -r '.[] | select(.extname=="'${ext}'") | .extdir')
-    generate_id new_timeline_id
-    PARAMS=(
-        -sbf
-        -X POST
-        -H "Content-Type: application/json"
-        -d "{\"new_timeline_id\": \"${new_timeline_id}\", \"pg_version\": ${PG_VERSION}, \"ancestor_timeline_id\": \"${timeline_id}\"}"
-        "http://127.0.0.1:9898/v1/tenant/${tenant_id}/timeline/"
-    )
-    result=$(curl "${PARAMS[@]}")
-    echo $result | jq .
-    TENANT_ID=${tenant_id} TIMELINE_ID=${new_timeline_id} TAG=${OLDTAG} docker compose down compute compute_is_ready
-    COMPUTE_TAG=${NEWTAG} TAG=${OLDTAG} TENANT_ID=${tenant_id} TIMELINE_ID=${new_timeline_id} docker compose up --quiet-pull -d --build compute compute_is_ready
-    wait_for_ready
-    TID=$(docker compose exec neon-test-extensions psql -Aqt -c "SHOW neon.timeline_id")
-    if [ ${TID} != ${new_timeline_id} ]; then
-      echo Timeline mismatch
-      exit 1
-    fi
-    docker compose exec neon-test-extensions psql -d contrib_regression -c "\dx ${ext}"
-    docker compose exec neon-test-extensions sh -c /ext-src/${EXTDIR}/test-upgrade.sh
-    docker compose exec neon-test-extensions psql -d contrib_regression -c "alter extension ${ext} update"
-    docker compose exec neon-test-extensions psql -d contrib_regression -c "\dx ${ext}"
-  done
-fi

docs/rfcs/035-safekeeper-dynamic-membership-change.md

@@ -81,7 +81,7 @@ configuration generation in them is less than its current one. Namely, it
 refuses to vote, to truncate WAL in `handle_elected` and to accept WAL. In
 response it sends its current configuration generation to let walproposer know.
 
-Safekeeper gets `PUT /v1/tenants/{tenant_id}/timelines/{timeline_id}/configuration`
+Safekeeper gets `PUT /v1/tenants/{tenant_id}/timelines/{timeline_id}/configuration` 
 accepting `Configuration`. Safekeeper switches to the given conf it is higher than its
 current one and ignores it otherwise. In any case it replies with
 ```
@@ -103,7 +103,7 @@ currently and tries to communicate with all of them. However, the list does not
 define consensus members. Instead, on start walproposer tracks highest
 configuration it receives from `AcceptorGreeting`s. Once it assembles greetings
 from majority of `sk_set` and majority of `new_sk_set` (if it is present), it
-establishes this configuration as its own and moves to voting.
+establishes this configuration as its own and moves to voting. 
 
 It should stop talking to safekeepers not listed in the configuration at this
 point, though it is not unsafe to continue doing so.
@@ -119,7 +119,7 @@ refusal to accept due to configuration change) it simply restarts.
 The following algorithm can be executed anywhere having access to configuration
 storage and safekeepers. It is safe to interrupt / restart it and run multiple
 instances of it concurrently, though likely one of them won't make
-progress then. It accepts `desired_set: Vec<NodeId>` as input.
+progress then. It accepts `desired_set: Vec<NodeId>` as input. 
 
 Algorithm will refuse to make the change if it encounters previous interrupted
 change attempt, but in this case it will try to finish it.
@@ -140,7 +140,7 @@ storage are reachable.
    safe. Failed CAS aborts the procedure.
 4) Call `PUT` `configuration` on safekeepers from the current set,
    delivering them `joint_conf`. Collecting responses from majority is required
-   to proceed. If any response returned generation higher than
+   to proceed. If any response returned generation higher than 
    `joint_conf.generation`, abort (another switch raced us). Otherwise, choose
    max `<last_log_term, flush_lsn>` among responses and establish it as
    (in memory) `sync_position`. Also choose max `term` and establish it as (in
@@ -149,49 +149,49 @@ storage are reachable.
    without ack from the new set. Similarly, we'll bump term on new majority
    to `sync_term` so that two computes with the same term are never elected.
 4) Initialize timeline on safekeeper(s) from `new_sk_set` where it
-   doesn't exist yet by doing `pull_timeline` from the majority of the
+   doesn't exist yet by doing `pull_timeline` from the majority of the 
    current set. Doing that on majority of `new_sk_set` is enough to
    proceed, but it is reasonable to ensure that all `new_sk_set` members
    are initialized -- if some of them are down why are we migrating there?
-5) Call `POST` `bump_term(sync_term)` on safekeepers from the new set.
+5) Call `POST` `bump_term(sync_term)` on safekeepers from the new set. 
    Success on majority is enough.
 6) Repeatedly call `PUT` `configuration` on safekeepers from the new set,
    delivering them `joint_conf` and collecting their positions. This will
-   switch them to the `joint_conf` which generally won't be needed
+   switch them to the `joint_conf` which generally won't be needed 
    because `pull_timeline` already includes it and plus additionally would be
    broadcast by compute. More importantly, we may proceed to the next step
-   only when `<last_log_term, flush_lsn>` on the majority of the new set reached
-   `sync_position`. Similarly, on the happy path no waiting is not needed because
+   only when `<last_log_term, flush_lsn>` on the majority of the new set reached 
+   `sync_position`. Similarly, on the happy path no waiting is not needed because 
    `pull_timeline` already includes it. However, we should double
     check to be safe. For example, timeline could have been created earlier e.g.
-    manually or after try-to-migrate, abort, try-to-migrate-again sequence.
-7) Create `new_conf: Configuration` incrementing `join_conf` generation and having new
-   safekeeper set as `sk_set` and None `new_sk_set`. Write it to configuration
+    manually or after try-to-migrate, abort, try-to-migrate-again sequence. 
+7) Create `new_conf: Configuration` incrementing `join_conf` generation and having new 
+   safekeeper set as `sk_set` and None `new_sk_set`. Write it to configuration 
    storage under one more CAS.
 8) Call `PUT` `configuration` on safekeepers from the new set,
-   delivering them `new_conf`. It is enough to deliver it to the majority
+   delivering them `new_conf`. It is enough to deliver it to the majority 
    of the new set; the rest can be updated by compute.
 
 I haven't put huge effort to make the description above very precise, because it
 is natural language prone to interpretations anyway. Instead I'd like to make TLA+
 spec of it.
 
-Description above focuses on safety. To make the flow practical and live, here a few more
+Description above focuses on safety. To make the flow practical and live, here a few more 
 considerations.
-1) It makes sense to ping new set to ensure it we are migrating to live node(s) before
+1) It makes sense to ping new set to ensure it we are migrating to live node(s) before 
   step 3.
-2) If e.g. accidentally wrong new sk set has been specified, before CAS in step `6` is completed
+2) If e.g. accidentally wrong new sk set has been specified, before CAS in step `6` is completed 
    it is safe to rollback to the old conf with one more CAS.
-3) On step 4 timeline might be already created on members of the new set for various reasons;
+3) On step 4 timeline might be already created on members of the new set for various reasons; 
    the simplest is the procedure restart. There are more complicated scenarious like mentioned
-   in step 5. Deleting and re-doing `pull_timeline` is generally unsafe without involving
-   generations, so seems simpler to treat existing timeline as success. However, this also
+   in step 5. Deleting and re-doing `pull_timeline` is generally unsafe without involving 
+   generations, so seems simpler to treat existing timeline as success. However, this also 
    has a disadvantage: you might imagine an surpassingly unlikely schedule where condition in
    the step 5 is never reached until compute is (re)awaken up to synchronize new member(s).
    I don't think we'll observe this in practice, but can add waking up compute if needed.
 4) In the end timeline should be locally deleted on the safekeeper(s) which are
    in the old set but not in the new one, unless they are unreachable. To be
-   safe this also should be done under generation number (deletion proceeds only if
+   safe this also should be done under generation number (deletion proceeds only if 
    current configuration is <= than one in request and safekeeper is not memeber of it).
 5) If current conf fetched on step 1 is already not joint and members equal to `desired_set`,
    jump to step 7, using it as `new_conf`.
@@ -202,93 +202,53 @@ The procedure ought to be driven from somewhere. Obvious candidates are control
 plane and storage_controller; and as each of them already has db we don't want
 yet another storage. I propose to manage safekeepers in storage_controller
 because 1) since it is in rust it simplifies simulation testing (more on this
-below) 2) it already manages pageservers.
+below) 2) it already manages pageservers. 
 
 This assumes that migration will be fully usable only after we migrate all
 tenants/timelines to storage_controller. It is discussible whether we want also
 to manage pageserver attachments for all of these, but likely we do.
 
-This requires us to define storcon <-> cplane interface and changes.
+This requires us to define storcon <-> cplane interface.
 
-### storage_controller <-> control plane interface and changes
+### storage_controller <-> control plane interface
 
 First of all, control plane should
 [change](https://neondb.slack.com/archives/C03438W3FLZ/p1719226543199829)
 storing safekeepers per timeline instead of per tenant because we can't migrate
-tenants atomically.
+tenants atomically. 
 
 The important question is how updated configuration is delivered from
 storage_controller to control plane to provide it to computes. As always, there
 are two options, pull and push. Let's do it the same push as with pageserver
 `/notify-attach` because 1) it keeps storage_controller out of critical compute
-start path 2) uniformity. It makes storage_controller responsible for retrying
-notifying control plane until it succeeds.
+start path 2) provides easier upgrade: there won't be such a thing as 'timeline
+managed by control plane / storcon', cplane just takes the value out of its db
+when needed 3) uniformity. It makes storage_controller responsible for retrying notifying
+control plane until it succeeds.
 
-It is not needed for the control plane to fully know the `Configuration`. It is
-enough for it to only to be aware of the list of safekeepers in the latest
-configuration to supply it to compute, plus associated generation number to
-protect from stale update requests and to also pass it to compute.
-
-So, cplane `/notify-safekeepers` for the timeline can accept JSON like
-```
-{
-   tenant_id: String,
-   timeline_id: String,
-   generation: u32,
-   safekeepers: Vec<SafekeeperId>,
-}
-```
-where `SafekeeperId` is
-```
-{
-   node_id: u64,
-   host: String
-}
-```
-In principle `host` is redundant, but may be useful for observability.
-
-The request updates list of safekeepers in the db if the provided conf
-generation is higher (the cplane db should also store generations for this).
-Similarly to
-[`/notify-attach`](https://www.notion.so/neondatabase/Storage-Controller-Control-Plane-interface-6de56dd310a043bfa5c2f5564fa98365),
-it should update db which makes the call successful, and then try to schedule
-`apply_config` if possible, it is ok if not. storage_controller should rate
-limit calling the endpoint, but likely this won't be needed, as migration
+So, cplane `/notify-safekeepers` for the timeline accepts `Configuration` and
+updates it in the db if the provided conf generation is higher (the cplane db
+should also store generations for this). Similarly to [`/notify-attach`](https://www.notion.so/neondatabase/Storage-Controller-Control-Plane-interface-6de56dd310a043bfa5c2f5564fa98365), it
+should update db which makes the call successful, and then try to schedule
+`apply_config` if possible, it is ok if not. storage_controller 
+should rate limit calling the endpoint, but likely this won't be needed, as migration
 throughput is limited by `pull_timeline`.
 
 Timeline (branch) creation in cplane should call storage_controller POST
 `tenant/:tenant_id/timeline` like it currently does for sharded tenants.
-Response should be augmented with `safekeepers_generation` and `safekeepers`
-fields like described in `/notify-safekeepers` above. Initially (currently)
-these fields may be absent; in this case cplane chooses safekeepers on its own
-like it currently does. The call should be retried until succeeds.
+Response should be augmented with `safekeeper_conf: Configuration`. The call
+should be retried until succeeds.
 
 Timeline deletion and tenant deletion in cplane should call appropriate
 storage_controller endpoints like it currently does for sharded tenants. The
 calls should be retried until they succeed.
 
-When compute receives safekeepers list from control plane it needs to know the
-generation to checked whether it should be updated (note that compute may get
-safekeeper list from either cplane or safekeepers). Currently `neon.safekeepers`
-GUC is just a comma separates list of `host:port`. Let's prefix it with
-`g#<generation>:` to this end, so it will look like
-```
-g#42:safekeeper-0.eu-central-1.aws.neon.tech:6401,safekeeper-2.eu-central-1.aws.neon.tech:6401,safekeeper-1.eu-central-1.aws.neon.tech:6401
-```
-
-To summarize, list of cplane changes:
-- per tenant -> per timeline safekeepers management and addition of int `safekeeper_generation` field.
-- `/notify-safekeepers` endpoint.
-- Branch creation call may return list of safekeepers and when it is
-  present cplane should adopt it instead of choosing on its own like it does currently.
-- `neon.safekeepers` GUC should be prefixed with `g#<generation>:`.
-
 ### storage_controller implementation
 
-If desired, we may continue using current 'load everything on startup and keep
-in memory' approach: single timeline shouldn't take more than 100 bytes (it's 16
-byte tenant_id, 16 byte timeline_id, int generation, vec of ~3 safekeeper ids
-plus some flags), so 10^6 of timelines shouldn't take more than 100MB.
+Current 'load everything on startup and keep in memory' easy design is fine.
+Single timeline shouldn't take more than 100 bytes (it's 16 byte tenant_id, 16
+byte timeline_id, int generation, vec of ~3 safekeeper ids plus some flags), so
+10^6 of timelines shouldn't take more than 100MB.
 
 Similar to pageserver attachment Intents storage_controller would have in-memory
 `MigrationRequest` (or its absense) for each timeline and pool of tasks trying
@@ -296,7 +256,7 @@ to make these request reality; this ensures one instance of storage_controller
 won't do several migrations on the same timeline concurrently. In the first
 version it is simpler to have more manual control and no retries, i.e. migration
 failure removes the request. Later we can build retries and automatic
-scheduling/migration around. `MigrationRequest` is
+scheduling/migration. `MigrationRequest` is
 ```
 enum MigrationRequest {
     To(Vec<NodeId>),
@@ -313,9 +273,9 @@ similarly, in the first version it is ok to trigger it manually).
 #### Schema
 
 `safekeepers` table mirroring current `nodes` should be added, except that for
-`scheduling_policy`: it is enough to have at least in the beginning only 3
-fields: 1) `active` 2) `paused` (initially means only not assign new tlis there
-3) `decomissioned` (node is removed).
+`scheduling_policy` field (seems like `status` is a better name for it): it is enough
+to have at least in the beginning only 3 fields: 1) `active` 2) `offline` 3)
+`decomissioned`.
 
 `timelines` table:
 ```
@@ -324,24 +284,18 @@ table! {
     timelines (tenant_id, timeline_id) {
         timeline_id -> Varchar,
         tenant_id -> Varchar,
-        start_lsn -> pg_lsn,
         generation -> Int4,
         sk_set -> Array<Int4>, // list of safekeeper ids
-        new_sk_set -> Nullable<Array<Int8>>, // list of safekeeper ids, null if not joint conf
+        new_sk_set -> Nullable<Array<Int4>>, // list of safekeeper ids, null if not joint conf
         cplane_notified_generation -> Int4,
-        deleted_at -> Nullable<Timestamptz>,
     }
 }
 ```
 
-`start_lsn` is needed to create timeline on safekeepers properly, see below. We
-might also want to add ancestor_timeline_id to preserve the hierarchy, but for
-this RFC it is not needed.
-
 #### API
 
 Node management is similar to pageserver:
-1) POST `/control/v1/safekeepers` inserts safekeeper.
+1) POST `/control/v1/safekeepers` upserts safekeeper.
 2) GET `/control/v1/safekeepers` lists safekeepers.
 3) GET `/control/v1/safekeepers/:node_id` gets safekeeper.
 4) PUT `/control/v1/safekepers/:node_id/status` changes status to e.g.
@@ -351,15 +305,25 @@ Node management is similar to pageserver:
 Safekeeper deploy scripts should register safekeeper at storage_contorller as
 they currently do with cplane, under the same id.
 
-Timeline creation/deletion will work through already existing POST and DELETE
-`tenant/:tenant_id/timeline`. Cplane is expected to retry both until they
-succeed. See next section on the implementation details.
+Timeline creation/deletion: already existing POST `tenant/:tenant_id/timeline`
+would 1) choose initial set of safekeepers; 2) write to the db initial
+`Configuration` with `INSERT ON CONFLICT DO NOTHING` returning existing row in
+case of conflict; 3) create timeline on the majority of safekeepers (already
+created is ok).
 
-We don't want to block timeline creation/deletion when one safekeeper is down.
-Currently this is crutched by compute implicitly creating timeline on any
-safekeeper it is connected to. This creates ugly timeline state on safekeeper
-when timeline is created, but start LSN is not defined yet. Next section
-describes dealing with this.
+We don't want to block timeline creation when one safekeeper is down. Currently
+this is solved by compute implicitly creating timeline on any safekeeper it is
+connected to. This creates ugly timeline state on safekeeper when timeline is
+created, but start LSN is not defined yet. It would be nice to remove this; to
+do that, controller can in the background retry to create timeline on
+safekeeper(s) which missed that during initial creation call. It can do that
+through `pull_timeline` from majority so it doesn't need to remember
+`parent_lsn` in its db.
+
+Timeline deletion removes the row from the db and forwards deletion to the
+current configuration members. Without additional actions deletions might leak,
+see below on this; initially let's ignore these, reporting to cplane success if
+at least one safekeeper deleted the timeline (this will remove s3 data).
 
 Tenant deletion repeats timeline deletion for all timelines.
 
@@ -391,6 +355,26 @@ Similar call should be added for the tenant.
 It would be great to have some way of subscribing to the results (apart from
 looking at logs/metrics).
 
+Migration is executed as described above. One subtlety is that (local) deletion on
+source safekeeper might fail, which is not a problem if we are going to
+decomission the node but leaves garbage otherwise. I'd propose in the first version
+1) Don't attempt deletion at all if node status is `offline`.
+2) If it failed, just issue warning.
+And add PUT `/control/v1/safekeepers/:node_id/scrub` endpoint which would find and 
+remove garbage timelines for manual use. It will 1) list all timelines on the 
+safekeeper 2) compare each one against configuration storage: if timeline 
+doesn't exist at all (had been deleted), it can be deleted. Otherwise, it can 
+be deleted under generation number if node is not member of current generation.
+
+Automating this is untrivial; we'd need to register all potential missing
+deletions <tenant_id, timeline_id, generation, node_id> in the same transaction
+which switches configurations. Similarly when timeline is fully deleted to
+prevent cplane operation from blocking when some safekeeper is not available
+deletion should be also registered.
+
+One more task pool should infinitely retry notifying control plane about changed
+safekeeper sets.
+
 3) GET `/control/v1/tenant/:tenant_id/timeline/:timeline_id/` should return
    current in memory state of the timeline and pending `MigrationRequest`,
    if any.
@@ -399,153 +383,12 @@ looking at logs/metrics).
    migration by switching configuration from the joint to the one with (previous) `sk_set` under CAS
    (incrementing generation as always).
 
-#### API implementation and reconciliation
-
-For timeline creation/deletion we want to preserve the basic assumption that
-unreachable minority (1 sk of 3) doesn't block their completion, but eventually
-we want to finish creation/deletion on nodes which missed it (unless they are
-removed). Similarly for migration; it may and should finish even though excluded
-members missed their exclusion. And of course e.g. such pending exclusion on
-node C after migration ABC -> ABD must not prevent next migration ABD -> ABE. As
-another example, if some node missed timeline creation it clearly must not block
-migration from it. Hence it is natural to have per safekeeper background
-reconciler which retries these ops until they succeed. There are 3 possible
-operation types, and the type is defined by timeline state (membership
-configuration and whether it is deleted) and safekeeper id: we may need to
-create timeline on sk (node added), locally delete it (node excluded, somewhat
-similar to detach) or globally delete it (timeline is deleted).
-
-Next, on storage controller restart in principle these pending operations can be
-figured out by comparing safekeepers state against storcon state. But it seems
-better to me to materialize them in the database; it is not expensive, avoids
-these startup scans which themselves can fail etc and makes it very easy to see
-outstanding work directly at the source of truth -- the db. So we can add table
-`safekeeper_timeline_pending_ops`
-```
-table! {
-    // timeline_id, sk_id is primary key
-    safekeeper_timeline_pending_ops (sk_id, tenant_id, timeline_id) {
-        sk_id -> int8,
-        tenant_id -> Varchar,
-        timeline_id -> Varchar,
-        generation -> Int4,
-        op_type -> Varchar,
-    }
-}
-```
-
-`op_type` can be `include` (seed from peers and ensure generation is up to
-date), `exclude` (remove locally) and `delete`. Field is actually not strictly
-needed as it can be computed from current configuration, but gives more explicit
-observability.
-
-`generation` is necessary there because after op is done reconciler must remove
-it and not remove another row with higher gen which in theory might appear.
-
-Any insert of row should overwrite (remove) all rows with the same sk and
-timeline id but lower `generation` as next op makes previous obsolete. Insertion
-of `op_type` `delete` overwrites all rows.
-
-About `exclude`: rather than adding explicit safekeeper http endpoint, it is
-reasonable to reuse membership switch endpoint: if safekeeper is not member
-of the configuration it locally removes the timeline on the switch. In this case
-404 should also be considered an 'ok' answer by the caller.
-
-So, main loop of per sk reconcile reads `safekeeper_timeline_pending_ops`
-joined with timeline configuration to get current conf (with generation `n`)
-for the safekeeper and does the jobs, infinitely retrying failures:
-1) If node is member (`include`):
-  - Check if timeline exists on it, if not, call pull_timeline on it from 
-     other members
-  - Call switch configuration to the current
-2) If node is not member (`exclude`):
-  - Call switch configuration to the current, 404 is ok.
-3) If timeline is deleted (`delete`), call delete.
-
-In cases 1 and 2 remove `safekeeper_timeline_pending_ops` for the sk and 
-timeline with generation <= `n` if `op_type` is not `delete`.
-In case 3 also remove `safekeeper_timeline_pending_ops` 
-entry + remove `timelines` entry if there is nothing left  in `safekeeper_timeline_pending_ops` for the timeline.
-
-Let's consider in details how APIs can be implemented from this angle.
-
-Timeline creation. It is assumed that cplane retries it until success, so all
-actions must be idempotent. Now, a tricky point here is timeline start LSN. For
-the initial (tenant creation) call cplane doesn't know it. However, setting
-start_lsn on safekeepers during creation is a good thing -- it provides a
-guarantee that walproposer can always find a common point in WAL histories of
-safekeeper and its own, and so absense of it would be a clear sign of
-corruption. The following sequence works:
-1) Create timeline (or observe that it exists) on pageserver,
-   figuring out last_record_lsn in response.
-2) Choose safekeepers and insert (ON CONFLICT DO NOTHING) timeline row into the
-   db. Note that last_record_lsn returned on the previous step is movable as it
-   changes once ingestion starts, insert must not overwrite it (as well as other
-   fields like membership conf). On the contrary, start_lsn used in the next
-   step must be set to the value in the db. cplane_notified_generation can be set
-   to 1 (initial generation) in insert to avoid notifying cplane about initial 
-   conf as cplane will receive it in timeline creation request anyway.
-3) Issue timeline creation calls to at least majority of safekeepers. Using
-   majority here is not necessary but handy because it guarantees that any live
-   majority will have at least one sk with created timeline and so
-   reconciliation task can use pull_timeline shared with migration instead of
-   create timeline special init case. OFC if timeline is already exists call is
-   ignored.
-4) For minority of safekeepers which could have missed creation insert
-   entries to `safekeeper_timeline_pending_ops`. We won't miss this insertion 
-   because response to cplane is sent only after it has happened, and cplane 
-   retries the call until 200 response.
-
-   There is a small question how request handler (timeline creation in this
-   case) would interact with per sk reconciler. As always I prefer to do the
-   simplest possible thing and here it seems to be just waking it up so it
-   re-reads the db for work to do. Passing work in memory is faster, but
-   that shouldn't matter, and path to scan db for work will exist anyway, 
-   simpler to reuse it.
-
-For pg version / wal segment size: while we may persist them in `timelines`
-table, it is not necessary as initial creation at step 3 can take them from
-pageserver or cplane creation call and later pull_timeline will carry them
-around.
-
-Timeline migration.
-1) CAS to the db to create joint conf, and in the same transaction create
-   `safekeeper_timeline_pending_ops` `include` entries to initialize new members
-   as well as deliver this conf to current ones; poke per sk reconcilers to work
-   on it. Also any conf change should also poke cplane notifier task(s).
-2) Once it becomes possible per alg description above, get out of joint conf
-   with another CAS. Task should get wakeups from per sk reconcilers because 
-   conf switch is required for advancement; however retries should be sleep
-   based as well as LSN advancement might be needed, though in happy path 
-   it isn't. To see whether further transition is possible on wakup migration
-   executor polls safekeepers per the algorithm. CAS creating new conf with only
-   new members should again insert entries to `safekeeper_timeline_pending_ops`
-   to switch them there, as well as `exclude` rows to remove timeline from 
-   old members.
-
-Timeline deletion: just set `deleted_at` on the timeline row and insert
-`safekeeper_timeline_pending_ops` entries in the same xact, the rest is done by
-per sk reconcilers.
-
-When node is removed (set to `decomissioned`), `safekeeper_timeline_pending_ops`
-for it must be cleared in the same transaction.
-
-One more task pool should infinitely retry notifying control plane about changed
-safekeeper sets (trying making `cplane_notified_generation` equal `generation`).
-
 #### Dealing with multiple instances of storage_controller
 
 Operations described above executed concurrently might create some errors but do
 not prevent progress, so while we normally don't want to run multiple instances
 of storage_controller it is fine to have it temporarily, e.g. during redeploy.
 
-To harden against some controller instance creating some work in
-`safekeeper_timeline_pending_ops` and then disappearing without anyone pickup up
-the job per sk reconcilers apart from explicit wakups should scan for work
-periodically. It is possible to remove that though if all db updates are
-protected with leadership token/term -- then such scans are needed only after
-leadership is acquired.
-
 Any interactions with db update in-memory controller state, e.g. if migration
 request failed because different one is in progress, controller remembers that
 and tries to finish it.
@@ -569,8 +412,8 @@ There should be following layers of tests:
 3) Since simulation testing injects at relatively high level points (not
    syscalls), it omits some code, in particular `pull_timeline`. Thus it is
    better to have basic tests covering whole system as well. Extended version of
-   `test_restarts_under_load` would do: start background load and do migration
-   under it, then restart endpoint and check that no reported commits
+   `test_restarts_under_load` would do: start background load and do migration 
+   under it, then restart endpoint and check that no reported commits 
    had been lost. I'd also add one more creating classic network split scenario, with
    one compute talking to AC and another to BD while migration from nodes ABC to ABD
    happens.
@@ -579,51 +422,35 @@ There should be following layers of tests:
 
 ## Order of implementation and rollout
 
-Note that
+Note that 
 - Control plane parts and integration with it is fully independent from everything else
   (tests would use simulation and neon_local).
-- It is reasonable to make compute <-> safekeepers protocol change
-  independent of enabling generations.
 - There is a lot of infra work making storage_controller aware of timelines and safekeepers
   and its impl/rollout should be separate from migration itself.
-- Initially walproposer can just stop working while it observes joint configuration.
+- Initially walproposer can just stop working while it observers joint configuration.
   Such window would be typically very short anyway.
-- Obviously we want to test the whole thing thoroughly on staging and only then
-  gradually enable in prod.
 
-Let's have the following implementation bits for gradual rollout:
-- compute gets `neon.safekeepers_proto_version` flag.
-  Initially both compute and safekeepers will be able to talk both
-  versions so that we can delay force restart of them and for
-  simplicity of rollback in case it is needed.
-- storcon gets `-set-safekeepers` config option disabled by
-  default. Timeline creation request chooses safekeepers
-  (and returns them in response to cplane) only when it is set to
-  true.
-- control_plane [see above](storage_controller-<->-control-plane interface-and-changes)
-  prefixes `neon.safekeepers` GUC with generation number. When it is 0
-  (or prefix not present at all), walproposer behaves as currently, committing on
-  the provided safekeeper list -- generations are disabled.
-  If it is non 0 it follows this RFC rules.
-- We provide a script for manual migration to storage controller.
-  It selects timeline(s) from control plane (specified or all of them) db
-  and calls special import endpoint on storage controller which is very
-  similar to timeline creation: it inserts into the db, sets
-  configuration to initial on the safekeepers, calls cplane
-  `notify-safekeepers`.
+To rollout smoothly, both walproposer and safekeeper should have flag
+`configurations_enabled`; when set to false, they would work as currently, i.e.
+walproposer is able to commit on whatever safekeeper set it is provided. Until
+all timelines are managed by storcon we'd need to use current script to migrate
+and update/drop entries in the storage_controller database if it has any.
 
-Then the rollout for a region would be:
-- Current situation: safekeepers are choosen by control_plane.
-- We manually migrate some timelines, test moving them around.
-- Then we enable `--set-safekeepers` so that all new timelines
-  are on storage controller.
-- Finally migrate all existing timelines using the script (no
-  compute should be speaking old proto version at this point).
+Safekeepers would need to be able to talk both current and new protocol version
+with compute to reduce number of computes restarted in prod once v2 protocol is
+deployed (though before completely switching we'd need to force this).
+
+Let's have the following rollout order:
+- storage_controller becomes aware of safekeepers;
+- storage_controller gets timeline creation for new timelines and deletion requests, but
+  doesn't manage all timelines yet. Migration can be tested on these new timelines.
+  To keep control plane and storage_controller databases in sync while control 
+  plane still chooses the safekeepers initially (until all timelines are imported
+  it can choose better), `TimelineCreateRequest` can get optional safekeepers
+  field with safekeepers chosen by cplane.
+- Then we can import all existing timelines from control plane to
+  storage_controller and gradually enable configurations region by region.
 
-Until all timelines are managed by storcon we'd need to use current ad hoc
-script to migrate if needed. To keep state clean, all storage controller managed
-timelines must be migrated before that, or controller db and configurations
-state of safekeepers dropped manually.
 
 Very rough implementation order:
 - Add concept of configurations to safekeepers (including control file),
@@ -631,10 +458,10 @@ Very rough implementation order:
 - Implement walproposer changes, including protocol.
 - Implement storconn part. Use it in neon_local (and pytest).
 - Make cplane store safekeepers per timeline instead of per tenant.
-- Implement cplane/storcon integration. Route branch creation/deletion
+- Implement cplane/storcon integration. Route branch creation/deletion 
   through storcon. Then we can test migration of new branches.
-- Finally import existing branches. Then we can drop cplane
-  safekeeper selection code. Gradually enable configurations at
+- Finally import existing branches. Then we can drop cplane 
+  safekeeper selection code. Gradually enable configurations at 
   computes and safekeepers. Before that, all computes must talk only
   v3 protocol version.
 
@@ -662,7 +489,7 @@ Aurora does this but similarly I don't think this is needed.
 
 We should use Compute <-> safekeeper protocol change to include other (long
 yearned) modifications:
-- send data in network order without putting whole structs to be arch independent
+- send data in network order to make arm work.
 - remove term_start_lsn from AppendRequest
 - add horizon to TermHistory
 - add to ProposerGreeting number of connection from this wp to sk