Merge pull request #10320 from neondatabase/rc/release-proxy/2025-01-09

Proxy release 2025-01-09

.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:
@@ -26,9 +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
-  - SLACK_STORAGE_CHANNEL_ID
-  - NEON_DEV_AWS_ACCOUNT_ID
-  - NEON_PROD_AWS_ACCOUNT_ID
-  - AWS_ECR_REGION

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

@@ -17,38 +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 initiailly, but only when shard-split threshold is reached, specify true to explicitly shard-split initially'
-    required: false
-    default: 'false'
-  disable_sharding:
-    description: 'by default new projects use storage controller default policy to shard-split when shard-split threshold is reached, specify true to explicitly disable sharding'
-    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:
@@ -80,7 +48,7 @@ runs:
               \"provisioner\": \"k8s-neonvm\",
               \"autoscaling_limit_min_cu\": ${MIN_CU},
               \"autoscaling_limit_max_cu\": ${MAX_CU},
-              \"settings\": ${PROJECT_SETTINGS}
+              \"settings\": { }
             }
           }")
 
@@ -95,38 +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\": $STRIPE_SIZE}"
-        fi
-        if [ "${DISABLE_SHARDING}" = "true" ]; then
-          # determine tenant ID
-          TENANT_ID=`${PSQL} ${dsn} -t -A -c "SHOW neon.tenant_id"`
-
-          echo "Explicitly disabling shard-splitting for project ${project_id} with tenant_id ${TENANT_ID}"
-
-          echo "Sending PUT request to https://${API_HOST}/regions/${REGION_ID}/api/v1/admin/storage/proxy/control/v1/tenant/${TENANT_ID}/policy"
-          echo "with body {\"scheduling\": \"Essential\"}"
-
-          # 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}/policy" \
-            -H "Accept: application/json" -H "Content-Type: application/json" -H "Authorization: Bearer ${ADMIN_API_KEY}" \
-            -d "{\"scheduling\": \"Essential\"}"
-        fi
-
       env:
         API_HOST: ${{ inputs.api_host }}
         API_KEY: ${{ inputs.api_key }}
@@ -134,11 +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 }}
-        DISABLE_SHARDING: ${{ inputs.disable_sharding }}
-        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
@@ -348,18 +309,12 @@ jobs:
           rerun_failed: true
           pg_version: ${{ matrix.pg_version }}
           aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
-          # `--session-timeout` is equal to (timeout-minutes - 10 minutes) * 60 seconds.
-          # Attempt to stop tests gracefully to generate test reports
-          # until they are forcibly stopped by the stricter `timeout-minutes` limit.
-          extra_params: --session-timeout=${{ inputs.sanitizers != 'enabled' && 3000 || 10200 }}
         env:
           TEST_RESULT_CONNSTR: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}
           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/_push-to-acr.yml

@@ -0,0 +1,56 @@
+name: Push images to ACR
+on:
+  workflow_call:
+    inputs:
+      client_id:
+        description: Client ID of Azure managed identity or Entra app
+        required: true
+        type: string
+      image_tag:
+        description: Tag for the container image
+        required: true
+        type: string
+      images:
+        description: Images to push
+        required: true
+        type: string
+      registry_name:
+        description: Name of the container registry
+        required: true
+        type: string
+      subscription_id:
+        description: Azure subscription ID
+        required: true
+        type: string
+      tenant_id:
+        description: Azure tenant ID
+        required: true
+        type: string
+
+jobs:
+  push-to-acr:
+    runs-on: ubuntu-22.04
+    permissions:
+      contents: read  # This is required for actions/checkout
+      id-token: write # This is required for Azure Login to work.
+
+    steps:
+      - name: Azure login
+        uses: azure/login@6c251865b4e6290e7b78be643ea2d005bc51f69a  # @v2.1.1
+        with:
+          client-id: ${{ inputs.client_id }}
+          subscription-id: ${{ inputs.subscription_id }}
+          tenant-id: ${{ inputs.tenant_id }}
+
+      - name: Login to ACR
+        run: |
+          az acr login --name=${{ inputs.registry_name }}
+
+      - name: Copy docker images to ACR ${{ inputs.registry_name }}
+        run: |
+          images='${{ inputs.images }}'
+          for image in ${images}; do
+            docker buildx imagetools create \
+              -t ${{ inputs.registry_name }}.azurecr.io/neondatabase/${image}:${{ inputs.image_tag }} \
+                                                        neondatabase/${image}:${{ inputs.image_tag }}
+          done

.github/workflows/_push-to-container-registry.yml

@@ -1,101 +0,0 @@
-name: Push images to Container Registry
-on:
-  workflow_call:
-    inputs:
-      # Example: {"docker.io/neondatabase/neon:13196061314":["${{ vars.NEON_DEV_AWS_ACCOUNT_ID }}.dkr.ecr.${{ vars.AWS_ECR_REGION }}.amazonaws.com/neon:13196061314","neoneastus2.azurecr.io/neondatabase/neon:13196061314"]}
-      image-map:
-        description: JSON map of images, mapping from a source image to an array of target images that should be pushed.
-        required: true
-        type: string
-      aws-region:
-        description: AWS region to log in to. Required when pushing to ECR.
-        required: false
-        type: string
-      aws-account-ids:
-        description: Comma separated AWS account IDs to log in to for pushing to ECR. Required when pushing to ECR.
-        required: false
-        type: string
-      azure-client-id:
-        description: Client ID of Azure managed identity or Entra app. Required when pushing to ACR.
-        required: false
-        type: string
-      azure-subscription-id:
-        description: Azure subscription ID. Required when pushing to ACR.
-        required: false
-        type: string
-      azure-tenant-id:
-        description: Azure tenant ID. Required when pushing to ACR.
-        required: false
-        type: string
-      acr-registry-name:
-        description: ACR registry name. Required when pushing to ACR.
-        required: false
-        type: string
-    secrets:
-      docker-hub-username:
-        description: Docker Hub username. Required when pushing to Docker Hub.
-        required: false
-      docker-hub-password:
-        description: Docker Hub password. Required when pushing to Docker Hub.
-        required: false
-      aws-role-to-assume:
-        description: AWS role to assume. Required when pushing to ECR.
-        required: false
-
-permissions: {}
-
-defaults:
-  run:
-    shell: bash -euo pipefail {0}
-
-jobs:
-  push-to-container-registry:
-    runs-on: ubuntu-22.04
-    permissions:
-      id-token: write  # Required for aws/azure login
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          sparse-checkout: scripts/push_with_image_map.py
-          sparse-checkout-cone-mode: false
-
-      - name: Print image-map
-        run: echo '${{ inputs.image-map }}' | jq
-
-      - name: Configure AWS credentials
-        if: contains(inputs.image-map, 'amazonaws.com/')
-        uses: aws-actions/configure-aws-credentials@v4
-        with:
-          aws-region: "${{ inputs.aws-region }}"
-          role-to-assume: "${{ secrets.aws-role-to-assume }}"
-          role-duration-seconds: 3600
-
-      - name: Login to ECR
-        if: contains(inputs.image-map, 'amazonaws.com/')
-        uses: aws-actions/amazon-ecr-login@v2
-        with:
-          registries: "${{ inputs.aws-account-ids }}"
-
-      - name: Configure Azure credentials
-        if: contains(inputs.image-map, 'azurecr.io/')
-        uses: azure/login@6c251865b4e6290e7b78be643ea2d005bc51f69a  # @v2.1.1
-        with:
-          client-id: ${{ inputs.azure-client-id }}
-          subscription-id: ${{ inputs.azure-subscription-id }}
-          tenant-id: ${{ inputs.azure-tenant-id }}
-
-      - name: Login to ACR
-        if: contains(inputs.image-map, 'azurecr.io/')
-        run: |
-          az acr login --name=${{ inputs.acr-registry-name }}
-
-      - name: Log in to Docker Hub
-        uses: docker/login-action@v3
-        with:
-          username: ${{ secrets.docker-hub-username }}
-          password: ${{ secrets.docker-hub-password }}
-
-      - name: Copy docker images to target registries
-        run: python scripts/push_with_image_map.py
-        env:
-          IMAGE_MAP: ${{ inputs.image-map }}

.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

@@ -45,30 +45,10 @@ 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 ]
-    container: ${{ vars.NEON_DEV_AWS_ACCOUNT_ID }}.dkr.ecr.${{ vars.AWS_ECR_REGION }}.amazonaws.com/base:pinned
+    container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/base:pinned
     outputs:
       build-tag: ${{steps.build-tag.outputs.tag}}
 
@@ -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 ]
@@ -263,15 +301,14 @@ jobs:
           echo "json=$(jq --compact-output '.' /tmp/benchmark_durations.json)" >> $GITHUB_OUTPUT
 
   benchmarks:
-    # `!failure() && !cancelled()` is required because the workflow depends on the job that can be skipped: `deploy` in PRs
-    if: github.ref_name == 'main' || (contains(github.event.pull_request.labels.*.name, 'run-benchmarks') && !failure() && !cancelled())
-    needs: [ check-permissions, build-build-tools-image, get-benchmarks-durations, deploy ]
+    if: github.ref_name == 'main' || contains(github.event.pull_request.labels.*.name, 'run-benchmarks')
+    needs: [ check-permissions, build-and-test-locally, build-build-tools-image, get-benchmarks-durations ]
     permissions:
       id-token: write # aws-actions/configure-aws-credentials
       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:
@@ -309,22 +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 ]
@@ -498,7 +538,7 @@ jobs:
 
   trigger-e2e-tests:
     if: ${{ !github.event.pull_request.draft || contains( github.event.pull_request.labels.*.name, 'run-e2e-tests-in-draft') || github.ref_name == 'main' || github.ref_name == 'release' || github.ref_name == 'release-proxy' || github.ref_name == 'release-compute' }}
-    needs: [ check-permissions, push-neon-image-dev, push-compute-image-dev, tag ]
+    needs: [ check-permissions, promote-images-dev, tag ]
     uses: ./.github/workflows/trigger-e2e-tests.yml
     secrets: inherit
 
@@ -572,6 +612,21 @@ jobs:
                                              neondatabase/neon:${{ needs.tag.outputs.build-tag }}-bookworm-x64 \
                                              neondatabase/neon:${{ needs.tag.outputs.build-tag }}-bookworm-arm64
 
+      - name: Configure AWS credentials
+        uses: aws-actions/configure-aws-credentials@v4
+        with:
+          aws-region: eu-central-1
+          role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+          role-duration-seconds: 3600
+
+      - name: Login to Amazon Dev ECR
+        uses: aws-actions/amazon-ecr-login@v2
+
+      - name: Push multi-arch image to ECR
+        run: |
+          docker buildx imagetools create -t 369495373322.dkr.ecr.eu-central-1.amazonaws.com/neon:${{ needs.tag.outputs.build-tag }} \
+                                                                                neondatabase/neon:${{ needs.tag.outputs.build-tag }}
+
   compute-node-image-arch:
     needs: [ check-permissions, build-build-tools-image, tag ]
     permissions:
@@ -618,6 +673,16 @@ jobs:
           username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
           password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
 
+      - name: Configure AWS credentials
+        uses: aws-actions/configure-aws-credentials@v4
+        with:
+          aws-region: eu-central-1
+          role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+          role-duration-seconds: 3600
+
+      - name: Login to Amazon Dev ECR
+        uses: aws-actions/amazon-ecr-login@v2
+
       - uses: docker/login-action@v3
         with:
           registry: cache.neon.build
@@ -658,11 +723,35 @@ jobs:
           push: true
           pull: true
           file: compute/compute-node.Dockerfile
-          target: extension-tests
+          target: neon-pg-ext-test
           cache-from: type=registry,ref=cache.neon.build/compute-node-${{ 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 }}
 
+      - name: Build compute-tools image
+        # compute-tools are Postgres independent, so build it only once
+        # We pick 16, because that builds on debian 11 with older glibc (and is
+        # thus compatible with newer glibc), rather than 17 on Debian 12, as
+        # that isn't guaranteed to be compatible with Debian 11
+        if: matrix.version.pg == 'v16'
+        uses: docker/build-push-action@v6
+        with:
+          target: compute-tools-image
+          context: .
+          build-args: |
+            GIT_VERSION=${{ github.event.pull_request.head.sha || github.sha }}
+            BUILD_TAG=${{ needs.tag.outputs.build-tag }}
+            TAG=${{ needs.build-build-tools-image.outputs.image-tag }}-${{ matrix.version.debian }}
+            DEBIAN_VERSION=${{ matrix.version.debian }}
+          provenance: false
+          push: true
+          pull: true
+          file: compute/compute-node.Dockerfile
+          cache-from: type=registry,ref=cache.neon.build/compute-node-${{ matrix.version.pg }}:cache-${{ matrix.version.debian }}-${{ matrix.arch }}
+          cache-to: ${{ github.ref_name == 'main' && format('type=registry,ref=cache.neon.build/compute-tools-{0}:cache-{1}-{2},mode=max', matrix.version.pg, matrix.version.debian, matrix.arch) || '' }}
+          tags: |
+            neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-${{ matrix.arch }}
+
   compute-node-image:
     needs: [ compute-node-image-arch, tag ]
     permissions:
@@ -705,6 +794,35 @@ jobs:
                                              neondatabase/neon-test-extensions-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-x64 \
                                              neondatabase/neon-test-extensions-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-arm64
 
+      - name: Create multi-arch compute-tools image
+        if: matrix.version.pg == 'v16'
+        run: |
+          docker buildx imagetools create -t neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }} \
+                                          -t neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }} \
+                                             neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-x64 \
+                                             neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-arm64
+
+      - name: Configure AWS credentials
+        uses: aws-actions/configure-aws-credentials@v4
+        with:
+          aws-region: eu-central-1
+          role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+          role-duration-seconds: 3600
+
+      - name: Login to Amazon Dev ECR
+        uses: aws-actions/amazon-ecr-login@v2
+
+      - name: Push multi-arch compute-node-${{ matrix.version.pg }} image to ECR
+        run: |
+          docker buildx imagetools create -t 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }} \
+                                                                                neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}
+
+      - name: Push multi-arch compute-tools image to ECR
+        if: matrix.version.pg == 'v16'
+        run: |
+          docker buildx imagetools create -t 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-tools:${{ needs.tag.outputs.build-tag }} \
+                                                                                neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}
+
   vm-compute-node-image:
     needs: [ check-permissions, tag, compute-node-image ]
     runs-on: [ self-hosted, large ]
@@ -775,17 +893,6 @@ 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
@@ -817,132 +924,142 @@ 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
 
-  generate-image-maps:
-    needs: [ tag ]
+  promote-images-dev:
+    needs: [ check-permissions, tag, vm-compute-node-image ]
     runs-on: ubuntu-22.04
-    outputs:
-      neon-dev: ${{ steps.generate.outputs.neon-dev }}
-      neon-prod: ${{ steps.generate.outputs.neon-prod }}
-      compute-dev: ${{ steps.generate.outputs.compute-dev }}
-      compute-prod: ${{ steps.generate.outputs.compute-prod }}
+
+    permissions:
+      id-token: write # aws-actions/configure-aws-credentials
+      statuses: write
+      contents: read
+
+    env:
+      VERSIONS: v14 v15 v16 v17
+
     steps:
-      - uses: actions/checkout@v4
+      - uses: docker/login-action@v3
         with:
-          sparse-checkout: scripts/generate_image_maps.py
-          sparse-checkout-cone-mode: false
+          username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
+          password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
 
-      - name: Generate Image Maps
-        id: generate
-        run: python scripts/generate_image_maps.py
-        env:
-          BUILD_TAG: "${{ needs.tag.outputs.build-tag }}"
-          BRANCH: "${{ github.ref_name }}"
-          DEV_ACR: "${{ vars.AZURE_DEV_REGISTRY_NAME }}"
-          PROD_ACR: "${{ vars.AZURE_PROD_REGISTRY_NAME }}"
-          DEV_AWS: "${{ vars.NEON_DEV_AWS_ACCOUNT_ID }}"
-          PROD_AWS: "${{ vars.NEON_PROD_AWS_ACCOUNT_ID }}"
-          AWS_REGION: "${{ vars.AWS_ECR_REGION }}"
+      - 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: 3600
 
-  push-neon-image-dev:
-    needs: [ generate-image-maps, neon-image ]
-    uses: ./.github/workflows/_push-to-container-registry.yml
-    with:
-      image-map: '${{ needs.generate-image-maps.outputs.neon-dev }}'
-      aws-region: ${{ vars.AWS_ECR_REGION }}
-      aws-account-ids: "${{ vars.NEON_DEV_AWS_ACCOUNT_ID }}"
-      azure-client-id: ${{ vars.AZURE_DEV_CLIENT_ID }}
-      azure-subscription-id: ${{ vars.AZURE_DEV_SUBSCRIPTION_ID }}
-      azure-tenant-id: ${{ vars.AZURE_TENANT_ID }}
-      acr-registry-name: ${{ vars.AZURE_DEV_REGISTRY_NAME }}
-    secrets:
-      aws-role-to-assume: "${{ vars.DEV_AWS_OIDC_ROLE_ARN }}"
-      docker-hub-username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
-      docker-hub-password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
+      - name: Login to Amazon Dev ECR
+        uses: aws-actions/amazon-ecr-login@v2
 
-  push-compute-image-dev:
-    needs: [ generate-image-maps, vm-compute-node-image ]
-    uses: ./.github/workflows/_push-to-container-registry.yml
-    with:
-      image-map: '${{ needs.generate-image-maps.outputs.compute-dev }}'
-      aws-region: ${{ vars.AWS_ECR_REGION }}
-      aws-account-ids: "${{ vars.NEON_DEV_AWS_ACCOUNT_ID }}"
-      azure-client-id: ${{ vars.AZURE_DEV_CLIENT_ID }}
-      azure-subscription-id: ${{ vars.AZURE_DEV_SUBSCRIPTION_ID }}
-      azure-tenant-id: ${{ vars.AZURE_TENANT_ID }}
-      acr-registry-name: ${{ vars.AZURE_DEV_REGISTRY_NAME }}
-    secrets:
-      aws-role-to-assume: "${{ vars.DEV_AWS_OIDC_ROLE_ARN }}"
-      docker-hub-username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
-      docker-hub-password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
+      - name: Copy vm-compute-node images to ECR
+        run: |
+          for version in ${VERSIONS}; do
+            docker buildx imagetools create -t 369495373322.dkr.ecr.eu-central-1.amazonaws.com/vm-compute-node-${version}:${{ needs.tag.outputs.build-tag }} \
+                                               neondatabase/vm-compute-node-${version}:${{ needs.tag.outputs.build-tag }}
+          done
 
-  push-neon-image-prod:
-    if: github.ref_name == 'release' || github.ref_name == 'release-proxy' || github.ref_name == 'release-compute'
-    needs: [ generate-image-maps, neon-image, test-images ]
-    uses: ./.github/workflows/_push-to-container-registry.yml
-    with:
-      image-map: '${{ needs.generate-image-maps.outputs.neon-prod }}'
-      aws-region: ${{ vars.AWS_ECR_REGION }}
-      aws-account-ids: "${{ vars.NEON_PROD_AWS_ACCOUNT_ID }}"
-      azure-client-id: ${{ vars.AZURE_PROD_CLIENT_ID }}
-      azure-subscription-id: ${{ vars.AZURE_PROD_SUBSCRIPTION_ID }}
-      azure-tenant-id: ${{ vars.AZURE_TENANT_ID }}
-      acr-registry-name: ${{ vars.AZURE_PROD_REGISTRY_NAME }}
-    secrets:
-      aws-role-to-assume: "${{ secrets.PROD_GHA_OIDC_ROLE }}"
-      docker-hub-username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
-      docker-hub-password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
+  promote-images-prod:
+    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'
 
-  push-compute-image-prod:
-    if: github.ref_name == 'release' || github.ref_name == 'release-proxy' || github.ref_name == 'release-compute'
-    needs: [ generate-image-maps, vm-compute-node-image, test-images ]
-    uses: ./.github/workflows/_push-to-container-registry.yml
-    with:
-      image-map: '${{ needs.generate-image-maps.outputs.compute-prod }}'
-      aws-region: ${{ vars.AWS_ECR_REGION }}
-      aws-account-ids: "${{ vars.NEON_PROD_AWS_ACCOUNT_ID }}"
-      azure-client-id: ${{ vars.AZURE_PROD_CLIENT_ID }}
-      azure-subscription-id: ${{ vars.AZURE_PROD_SUBSCRIPTION_ID }}
-      azure-tenant-id: ${{ vars.AZURE_TENANT_ID }}
-      acr-registry-name: ${{ vars.AZURE_PROD_REGISTRY_NAME }}
-    secrets:
-      aws-role-to-assume: "${{ secrets.PROD_GHA_OIDC_ROLE }}"
-      docker-hub-username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
-      docker-hub-password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
+    permissions:
+      id-token: write # aws-actions/configure-aws-credentials
+      statuses: write
+      contents: read
 
-  # This is a bit of a special case so we're not using a generated image map.
-  add-latest-tag-to-neon-extensions-test-image:
+    env:
+      VERSIONS: v14 v15 v16 v17
+
+    steps:
+      - 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: 3600
+
+      - name: Login to Amazon Dev ECR
+        uses: aws-actions/amazon-ecr-login@v2
+
+      - uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
+          password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
+
+      - name: Add latest tag to images
+        if: github.ref_name == 'main'
+        run: |
+          for repo in neondatabase 369495373322.dkr.ecr.eu-central-1.amazonaws.com; do
+            docker buildx imagetools create -t $repo/neon:latest \
+                                               $repo/neon:${{ needs.tag.outputs.build-tag }}
+
+            docker buildx imagetools create -t $repo/compute-tools:latest \
+                                               $repo/compute-tools:${{ needs.tag.outputs.build-tag }}
+
+            for version in ${VERSIONS}; do
+              docker buildx imagetools create -t $repo/compute-node-${version}:latest \
+                                                 $repo/compute-node-${version}:${{ needs.tag.outputs.build-tag }}
+
+              docker buildx imagetools create -t $repo/vm-compute-node-${version}:latest \
+                                                 $repo/vm-compute-node-${version}:${{ needs.tag.outputs.build-tag }}
+            done
+          done
+          docker buildx imagetools create -t neondatabase/neon-test-extensions-v16:latest \
+                                              neondatabase/neon-test-extensions-v16:${{ needs.tag.outputs.build-tag }}
+
+      - name: Configure AWS-prod credentials
+        if: github.ref_name == 'release'|| github.ref_name == 'release-proxy' || github.ref_name == 'release-compute'
+        uses: aws-actions/configure-aws-credentials@v4
+        with:
+          aws-region: eu-central-1
+          mask-aws-account-id: true
+          role-to-assume: ${{ secrets.PROD_GHA_OIDC_ROLE }}
+
+      - name: Login to prod ECR
+        uses: docker/login-action@v3
+        if: github.ref_name == 'release'|| github.ref_name == 'release-proxy' || github.ref_name == 'release-compute'
+        with:
+          registry: 093970136003.dkr.ecr.eu-central-1.amazonaws.com
+
+      - name: Copy all images to prod ECR
+        if: github.ref_name == 'release' || github.ref_name == 'release-proxy' || github.ref_name == 'release-compute'
+        run: |
+          for image in neon compute-tools {vm-,}compute-node-{v14,v15,v16,v17}; do
+            docker buildx imagetools create -t 093970136003.dkr.ecr.eu-central-1.amazonaws.com/${image}:${{ needs.tag.outputs.build-tag }} \
+                                               369495373322.dkr.ecr.eu-central-1.amazonaws.com/${image}:${{ needs.tag.outputs.build-tag }}
+          done
+
+  push-to-acr-dev:
     if: github.ref_name == 'main'
-    needs: [ tag, compute-node-image ]
-    uses: ./.github/workflows/_push-to-container-registry.yml
+    needs: [ tag, promote-images-dev ]
+    uses: ./.github/workflows/_push-to-acr.yml
     with:
-      image-map: |
-        {
-          "docker.io/neondatabase/neon-test-extensions-v16:${{ needs.tag.outputs.build-tag }}": ["docker.io/neondatabase/neon-test-extensions-v16:latest"],
-          "docker.io/neondatabase/neon-test-extensions-v17:${{ needs.tag.outputs.build-tag }}": ["docker.io/neondatabase/neon-test-extensions-v17:latest"]
-        }
-    secrets:
-      docker-hub-username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
-      docker-hub-password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
+      client_id: ${{ vars.AZURE_DEV_CLIENT_ID }}
+      image_tag: ${{ needs.tag.outputs.build-tag }}
+      images: neon compute-tools vm-compute-node-v14 vm-compute-node-v15 vm-compute-node-v16 vm-compute-node-v17 compute-node-v14 compute-node-v15 compute-node-v16 compute-node-v17
+      registry_name: ${{ vars.AZURE_DEV_REGISTRY_NAME }}
+      subscription_id: ${{ vars.AZURE_DEV_SUBSCRIPTION_ID }}
+      tenant_id: ${{ vars.AZURE_TENANT_ID }}
+
+  push-to-acr-prod:
+    if: github.ref_name == 'release' || github.ref_name == 'release-proxy' || github.ref_name == 'release-compute'
+    needs: [ tag, promote-images-prod ]
+    uses: ./.github/workflows/_push-to-acr.yml
+    with:
+      client_id: ${{ vars.AZURE_PROD_CLIENT_ID }}
+      image_tag: ${{ needs.tag.outputs.build-tag }}
+      images: neon compute-tools vm-compute-node-v14 vm-compute-node-v15 vm-compute-node-v16 vm-compute-node-v17 compute-node-v14 compute-node-v15 compute-node-v16 compute-node-v17
+      registry_name: ${{ vars.AZURE_PROD_REGISTRY_NAME }}
+      subscription_id: ${{ vars.AZURE_PROD_SUBSCRIPTION_ID }}
+      tenant_id: ${{ vars.AZURE_TENANT_ID }}
 
   trigger-custom-extensions-build-and-wait:
     needs: [ check-permissions, tag ]
@@ -1024,7 +1141,7 @@ jobs:
           exit 1
 
   deploy:
-    needs: [ check-permissions, push-neon-image-prod, push-compute-image-prod, tag, build-and-test-locally, trigger-custom-extensions-build-and-wait ]
+    needs: [ check-permissions, promote-images-prod, tag, build-and-test-locally, trigger-custom-extensions-build-and-wait, push-to-acr-dev, push-to-acr-prod ]
     # `!failure() && !cancelled()` is required because the workflow depends on the job that can be skipped: `push-to-acr-dev` and `push-to-acr-prod`
     if: (github.ref_name == 'main' || github.ref_name == 'release' || github.ref_name == 'release-proxy' || github.ref_name == 'release-compute') && !failure() && !cancelled()
     permissions:
@@ -1032,7 +1149,7 @@ jobs:
       statuses: write
       contents: write
     runs-on: [ self-hosted, small ]
-    container: ${{ vars.NEON_DEV_AWS_ACCOUNT_ID }}.dkr.ecr.${{ vars.AWS_ECR_REGION }}.amazonaws.com/ansible:latest
+    container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/ansible:latest
     steps:
       - uses: actions/checkout@v4
 
@@ -1043,7 +1160,6 @@ jobs:
           retries: 5
           script: |
             const tag = "${{ needs.tag.outputs.build-tag }}";
-            const branch = "${{ github.ref_name }}";
 
             try {
               const existingRef = await github.rest.git.getRef({
@@ -1072,6 +1188,12 @@ 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,
@@ -1086,48 +1208,11 @@ 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.`);
             }
@@ -1181,22 +1266,6 @@ jobs:
             exit 1
           fi
 
-  notify-storage-release-deploy-failure:
-    needs: [ deploy ]
-    # We want this to run even if (transitive) dependencies are skipped, because deploy should really be successful on release branch workflow runs.
-    if: github.ref_name == 'release' && needs.deploy.result != 'success' && always()
-    runs-on: ubuntu-22.04
-    steps:
-      - name: Post release-deploy failure to team-storage slack channel
-        uses: slackapi/slack-github-action@v2
-        with:
-          method: chat.postMessage
-          token: ${{ secrets.SLACK_BOT_TOKEN }}
-          payload: |
-            channel: ${{ vars.SLACK_STORAGE_CHANNEL_ID }}
-            text: |
-              🔴 @oncall-storage: deploy job on release branch had unexpected status "${{ needs.deploy.result }}" <${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}|GitHub Run>.
-
   # The job runs on `release` branch and copies compatibility data and Neon artifact from the last *release PR* to the latest directory
   promote-compatibility-data:
     needs: [ deploy ]
@@ -1293,7 +1362,7 @@ jobs:
           done
 
   pin-build-tools-image:
-    needs: [ build-build-tools-image, test-images, build-and-test-locally ]
+    needs: [ build-build-tools-image, promote-images-prod, build-and-test-locally ]
     if: github.ref_name == 'main'
     uses: ./.github/workflows/pin-build-tools-image.yml
     with:
@@ -1316,10 +1385,7 @@ jobs:
       - build-and-test-locally
       - check-codestyle-python
       - check-codestyle-rust
-      - check-dependencies-rust
-      - files-changed
-      - push-compute-image-dev
-      - push-neon-image-dev
+      - promote-images-dev
       - test-images
       - trigger-custom-extensions-build-and-wait
     runs-on: ubuntu-22.04
@@ -1331,12 +1397,4 @@ 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.push-compute-image-dev.result == 'skipped'
-          || needs.push-neon-image-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: ${{ vars.NEON_DEV_AWS_ACCOUNT_ID }}.dkr.ecr.${{ vars.AWS_ECR_REGION }}.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/force-test-extensions-upgrade.yml

@@ -1,76 +0,0 @@
-name: Force Test Upgrading of Extension
-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:  '45 2 * * *' # run once a day, timezone is utc
-  workflow_dispatch: # adds ability to run this manually
-
-defaults:
-  run:
-    shell: bash -euxo pipefail {0}
-
-concurrency:
-  # Allow only one workflow
-  group: ${{ github.workflow }}
-  cancel-in-progress: true
-
-permissions:
-  id-token: write # aws-actions/configure-aws-credentials
-  statuses: write
-  contents: read
-
-jobs:
-  regress:
-    strategy:
-      fail-fast: false
-      matrix:
-        pg-version: [16, 17]
-
-    runs-on: small
-
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          submodules: false
-
-      - name: Get the last compute release tag
-        id: get-last-compute-release-tag
-        env:
-          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: |
-          tag=$(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}
-
-      - name: Test extension upgrade
-        timeout-minutes: 20
-        env:
-          NEWTAG: latest
-          OLDTAG: ${{ steps.get-last-compute-release-tag.outputs.tag }}
-          PG_VERSION: ${{ matrix.pg-version }}
-          FORCE_ALL_UPGRADE_TESTS: true
-        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
-
-      - name: Post to the Slack channel
-        if: ${{ github.event.schedule && failure() }}
-        uses: slackapi/slack-github-action@v1
-        with:
-          channel-id: ${{ vars.SLACK_ON_CALL_QA_STAGING_STREAM }}
-          slack-message: |
-            Test upgrading of extensions: ${{ job.status }}
-            <${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}|GitHub Run>
-        env:
-          SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}

.github/workflows/ingest_benchmark.yml

@@ -28,33 +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
-            disable_sharding: false
-          - 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
-            disable_sharding: false
-            postgres_version: 16
-          - target_project: new_empty_project
-            stripe_size: null # run with neon defaults which will shard split only when reaching the threshold
-            disable_sharding: false
-            postgres_version: 16
-          - target_project: new_empty_project
-            stripe_size: null # run with neon defaults which will shard split only when reaching the threshold
-            disable_sharding: false
-            postgres_version: 17
-          - target_project: large_existing_project
-            stripe_size: null # cannot re-shared or choose different stripe size for existing, already sharded project
-            disable_sharding: false
-            postgres_version: 16
-          - target_project: new_empty_project_unsharded
-            stripe_size: null # run with neon defaults which will shard split only when reaching the threshold
-            disable_sharding: true
-            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
@@ -93,22 +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 }}
-        disable_sharding: ${{ matrix.disable_sharding }} 
 
     - 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: ${{ steps.create-neon-project-ingest-target.outputs.project_id }}
@@ -161,7 +130,7 @@ jobs:
         test_selection: performance/test_perf_ingest_using_pgcopydb.py
         run_in_parallel: false
         extra_params: -s -m remote_cluster --timeout 86400 -k test_ingest_performance_using_pgcopydb
-        pg_version: v${{ matrix.postgres_version }}
+        pg_version: v16
         save_perf_report: true
         aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
       env:
@@ -177,7 +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/pin-build-tools-image.yml

@@ -33,6 +33,10 @@ concurrency:
 # No permission for GITHUB_TOKEN by default; the **minimal required** set of permissions should be granted in each job.
 permissions: {}
 
+env:
+  FROM_TAG: ${{ inputs.from-tag }}
+  TO_TAG: pinned
+
 jobs:
   check-manifests:
     runs-on: ubuntu-22.04
@@ -42,14 +46,11 @@ jobs:
     steps:
       - name: Check if we really need to pin the image
         id: check-manifests
-        env:
-          FROM_TAG: ${{ inputs.from-tag }}
-          TO_TAG: pinned
         run: |
-          docker manifest inspect "docker.io/neondatabase/build-tools:${FROM_TAG}" > "${FROM_TAG}.json"
-          docker manifest inspect "docker.io/neondatabase/build-tools:${TO_TAG}"   > "${TO_TAG}.json"
+          docker manifest inspect neondatabase/build-tools:${FROM_TAG} > ${FROM_TAG}.json
+          docker manifest inspect neondatabase/build-tools:${TO_TAG}   > ${TO_TAG}.json
 
-          if diff "${FROM_TAG}.json" "${TO_TAG}.json"; then
+          if diff ${FROM_TAG}.json ${TO_TAG}.json; then
             skip=true
           else
             skip=false
@@ -63,34 +64,55 @@ jobs:
     # use format(..) to catch both inputs.force = true AND inputs.force = 'true'
     if: needs.check-manifests.outputs.skip == 'false' || format('{0}', inputs.force) == 'true'
 
-    permissions:
-      id-token: write  # Required for aws/azure login
+    runs-on: ubuntu-22.04
 
-    uses: ./.github/workflows/_push-to-container-registry.yml
-    with:
-      image-map: |
-        {
-          "docker.io/neondatabase/build-tools:${{ inputs.from-tag }}-bullseye": [
-            "docker.io/neondatabase/build-tools:pinned-bullseye",
-            "${{ vars.NEON_DEV_AWS_ACCOUNT_ID }}.dkr.ecr.${{ vars.AWS_ECR_REGION }}.amazonaws.com/build-tools:pinned-bullseye",
-            "${{ vars.AZURE_DEV_REGISTRY_NAME }}.azurecr.io/neondatabase/build-tools:pinned-bullseye"
-          ],
-          "docker.io/neondatabase/build-tools:${{ inputs.from-tag }}-bookworm": [
-            "docker.io/neondatabase/build-tools:pinned-bookworm",
-            "docker.io/neondatabase/build-tools:pinned",
-            "${{ vars.NEON_DEV_AWS_ACCOUNT_ID }}.dkr.ecr.${{ vars.AWS_ECR_REGION }}.amazonaws.com/build-tools:pinned-bookworm",
-            "${{ vars.NEON_DEV_AWS_ACCOUNT_ID }}.dkr.ecr.${{ vars.AWS_ECR_REGION }}.amazonaws.com/build-tools:pinned",
-            "${{ vars.AZURE_DEV_REGISTRY_NAME }}.azurecr.io/neondatabase/build-tools:pinned-bookworm",
-            "${{ vars.AZURE_DEV_REGISTRY_NAME }}.azurecr.io/neondatabase/build-tools:pinned"
-          ]
-        }
-      aws-region: ${{ vars.AWS_ECR_REGION }}
-      aws-account-ids: "${{ vars.NEON_DEV_AWS_ACCOUNT_ID }}"
-      azure-client-id: ${{ vars.AZURE_DEV_CLIENT_ID }}
-      azure-subscription-id: ${{ vars.AZURE_DEV_SUBSCRIPTION_ID }}
-      azure-tenant-id: ${{ vars.AZURE_TENANT_ID }}
-      acr-registry-name: ${{ vars.AZURE_DEV_REGISTRY_NAME }}
-    secrets:
-      aws-role-to-assume: "${{ vars.DEV_AWS_OIDC_ROLE_ARN }}"
-      docker-hub-username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
-      docker-hub-password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
+    permissions:
+      id-token: write # for `azure/login` and aws auth
+
+    steps:
+      - uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
+          password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
+
+      - 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: 3600
+
+      - name: Login to Amazon Dev ECR
+        uses: aws-actions/amazon-ecr-login@v2
+
+      - name: Azure login
+        uses: azure/login@6c251865b4e6290e7b78be643ea2d005bc51f69a  # @v2.1.1
+        with:
+          client-id: ${{ secrets.AZURE_DEV_CLIENT_ID }}
+          tenant-id: ${{ secrets.AZURE_TENANT_ID }}
+          subscription-id: ${{ secrets.AZURE_DEV_SUBSCRIPTION_ID }}
+
+      - name: Login to ACR
+        run: |
+          az acr login --name=neoneastus2
+
+      - name: Tag build-tools with `${{ env.TO_TAG }}` in Docker Hub, ECR, and ACR
+        env:
+          DEFAULT_DEBIAN_VERSION: bookworm
+        run: |
+          for debian_version in bullseye bookworm; do
+            tags=()
+
+            tags+=("-t" "neondatabase/build-tools:${TO_TAG}-${debian_version}")
+            tags+=("-t" "369495373322.dkr.ecr.eu-central-1.amazonaws.com/build-tools:${TO_TAG}-${debian_version}")
+            tags+=("-t" "neoneastus2.azurecr.io/neondatabase/build-tools:${TO_TAG}-${debian_version}")
+
+            if [ "${debian_version}" == "${DEFAULT_DEBIAN_VERSION}" ]; then
+              tags+=("-t" "neondatabase/build-tools:${TO_TAG}")
+              tags+=("-t" "369495373322.dkr.ecr.eu-central-1.amazonaws.com/build-tools:${TO_TAG}")
+              tags+=("-t" "neoneastus2.azurecr.io/neondatabase/build-tools:${TO_TAG}")
+            fi
+
+            docker buildx imagetools create "${tags[@]}" \
+                                              neondatabase/build-tools:${FROM_TAG}-${debian_version}
+          done

.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/regenerate-pg-setting.yml

@@ -1,41 +0,0 @@
-name: Regenerate Postgres Settings
-
-on:
-  pull_request:
-    types:
-      - opened
-      - synchronize
-      - reopened
-    paths:
-      - pgxn/neon/**.c
-      - vendor/postgres-v*
-      - vendor/revisions.json
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.head_ref }}
-  cancel-in-progress: true
-
-permissions:
-  pull-requests: write
-
-jobs:
-  regenerate-pg-settings:
-    runs-on: ubuntu-22.04
-
-    steps:
-      - name: Add comment
-        uses: thollander/actions-comment-pull-request@v3
-        with:
-          comment-tag: ${{ github.job }}
-          pr-number: ${{ github.event.number }}
-          message: |
-            If this PR added a GUC in the Postgres fork or `neon` extension,
-            please regenerate the Postgres settings in the `cloud` repo:
-
-            ```
-            make NEON_WORKDIR=path/to/neon/checkout \
-              -C goapp/internal/shareddomain/postgres generate
-            ```
-
-            If you're an external contributor, a Neon employee will assist in
-            making sure this step is done.

.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

.github/workflows/trigger-e2e-tests.yml

@@ -15,14 +15,7 @@ env:
   E2E_CONCURRENCY_GROUP: ${{ github.repository }}-e2e-tests-${{ github.ref_name }}-${{ github.ref_name == 'main' && github.sha || 'anysha' }}
 
 jobs:
-  check-permissions:
-    if: ${{ !contains(github.event.pull_request.labels.*.name, 'run-no-ci') }}
-    uses: ./.github/workflows/check-permissions.yml
-    with:
-      github-event-name: ${{ github.event_name }}
-
   cancel-previous-e2e-tests:
-    needs: [ check-permissions ]
     if: github.event_name == 'pull_request'
     runs-on: ubuntu-22.04
 
@@ -36,7 +29,6 @@ jobs:
               --field concurrency_group="${{ env.E2E_CONCURRENCY_GROUP }}"
 
   tag:
-    needs: [ check-permissions ]
     runs-on: ubuntu-22.04
     outputs:
       build-tag: ${{ steps.build-tag.outputs.tag }}
@@ -76,7 +68,7 @@ jobs:
       GH_TOKEN: ${{ secrets.CI_ACCESS_TOKEN }}
       TAG: ${{ needs.tag.outputs.build-tag }}
     steps:
-      - name: Wait for `push-{neon,compute}-image-dev` job to finish
+      - name: Wait for `promote-images-dev` job to finish
         # It's important to have a timeout here, the script in the step can run infinitely
         timeout-minutes: 60
         run: |
@@ -87,20 +79,20 @@ jobs:
           # For PRs we use the run id as the tag
           BUILD_AND_TEST_RUN_ID=${TAG}
           while true; do
-            gh run --repo ${GITHUB_REPOSITORY} view ${BUILD_AND_TEST_RUN_ID} --json jobs --jq '[.jobs[] | select((.name | startswith("push-neon-image-dev")) or (.name | startswith("push-compute-image-dev"))) | {"name": .name, "conclusion": .conclusion, "url": .url}]' > jobs.json
-            if [ $(jq '[.[] | select(.conclusion == "success")] | length' jobs.json) -eq 2 ]; then
-              break
-            fi
-            jq -c '.[]' jobs.json | while read -r job; do
-              case $(echo $job | jq .conclusion) in
-                failure | cancelled | skipped)
-                  echo "The '$(echo $job | jq .name)' job didn't succeed: '$(echo $job | jq .conclusion)'. See log in '$(echo $job | jq .url)' Exiting..."
-                  exit 1
-                  ;;
-              esac
-            done
-            echo "The 'push-{neon,compute}-image-dev' jobs haven't succeeded yet. Waiting..."
-            sleep 60
+            conclusion=$(gh run --repo ${GITHUB_REPOSITORY} view ${BUILD_AND_TEST_RUN_ID} --json jobs --jq '.jobs[] | select(.name == "promote-images-dev") | .conclusion')
+            case "$conclusion" in
+              success)
+                break
+                ;;
+              failure | cancelled | skipped)
+                echo "The 'promote-images-dev' job didn't succeed: '${conclusion}'. Exiting..."
+                exit 1
+                ;;
+              *)
+                echo "The 'promote-images-dev' hasn't succeed yet. Waiting..."
+                sleep 60
+                ;;
+            esac
           done
 
       - name: Set e2e-platforms

Cargo.toml

@@ -18,7 +18,6 @@ members = [
     "storage_scrubber",
     "workspace_hack",
     "libs/compute_api",
-    "libs/http-utils",
     "libs/pageserver_api",
     "libs/postgres_ffi",
     "libs/safekeeper_api",
@@ -55,7 +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"] }
@@ -67,7 +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 = "0.7.5", features = ["ws"] }
 base64 = "0.13.0"
 bincode = "1.3"
 bindgen = "0.70"
@@ -79,10 +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"
@@ -112,7 +110,6 @@ hyper-util = "0.1"
 tokio-tungstenite = "0.21.0"
 indexmap = "2"
 indoc = "2"
-inferno = "0.12.0"
 ipnet = "2.10.0"
 itertools = "0.10"
 itoa = "1.0.11"
@@ -125,14 +122,14 @@ 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"
-opentelemetry = "0.27"
-opentelemetry_sdk = "0.27"
-opentelemetry-otlp = { version = "0.27", default-features = false, features = ["http-proto", "trace", "http", "reqwest-client"] }
-opentelemetry-semantic-conventions = "0.27"
+opentelemetry = "0.26"
+opentelemetry_sdk = "0.26"
+opentelemetry-otlp = { version = "0.26", default-features=false, features = ["http-proto", "trace", "http", "reqwest-client"] }
+opentelemetry-semantic-conventions = "0.26"
 parking_lot = "0.12"
 parquet = { version = "53", default-features = false, features = ["zstd"] }
 parquet_derive = "53"
@@ -146,7 +143,7 @@ rand = "0.8"
 redis = { version = "0.25.2", features = ["tokio-rustls-comp", "keep-alive"] }
 regex = "1.10.2"
 reqwest = { version = "0.12", default-features = false, features = ["rustls-tls"] }
-reqwest-tracing = { version = "0.5", features = ["opentelemetry_0_27"] }
+reqwest-tracing = { version = "0.5", features = ["opentelemetry_0_26"] }
 reqwest-middleware = "0.4"
 reqwest-retry = "0.7"
 routerify = "3"
@@ -179,7 +176,7 @@ 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"
@@ -189,15 +186,11 @@ 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"]}
-tower = { version = "0.5.2", default-features = false }
-tower-http = { version = "0.6.2", features = ["request-id", "trace"] }
-tower-service = "0.3.3"
+tonic = {version = "0.12.3", features = ["tls", "tls-roots"]}
+tower-service = "0.3.2"
 tracing = "0.1"
 tracing-error = "0.2"
-tracing-log = "0.2"
-tracing-opentelemetry = "0.28"
-tracing-serde = "0.2.0"
+tracing-opentelemetry = "0.27"
 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 }
@@ -210,7 +203,6 @@ rustls-native-certs = "0.8"
 x509-parser = "0.16"
 whoami = "1.5.1"
 zerocopy = { version = "0.7", features = ["derive"] }
-json-structural-diff = { version = "0.2.0" }
 
 ## TODO replace this with tracing
 env_logger = "0.10"
@@ -231,7 +223,6 @@ azure_storage_blobs = { git = "https://github.com/neondatabase/azure-sdk-for-rus
 ## Local libraries
 compute_api = { version = "0.1", path = "./libs/compute_api/" }
 consumption_metrics = { version = "0.1", path = "./libs/consumption_metrics/" }
-http-utils = { version = "0.1", path = "./libs/http-utils/" }
 metrics = { version = "0.1", path = "./libs/metrics/" }
 pageserver = { path = "./pageserver" }
 pageserver_api = { version = "0.1", path = "./libs/pageserver_api/" }

Dockerfile

@@ -10,28 +10,6 @@ ARG STABLE_PG_VERSION=16
 ARG DEBIAN_VERSION=bookworm
 ARG DEBIAN_FLAVOR=${DEBIAN_VERSION}-slim
 
-# Here are the INDEX DIGESTS for the images we use.
-# You can get them following next steps for now:
-# 1. Get an authentication token from DockerHub:
-#    TOKEN=$(curl -s "https://auth.docker.io/token?service=registry.docker.io&scope=repository:library/debian:pull" | jq -r .token)
-# 2. Using that token, query index for the given tag:
-#    curl -s -H "Authorization: Bearer $TOKEN" \
-#       -H "Accept: application/vnd.docker.distribution.manifest.list.v2+json" \
-#       "https://registry.hub.docker.com/v2/library/debian/manifests/bullseye-slim" \
-#       -I | grep -i docker-content-digest
-# 3. As a next step, TODO(fedordikarev): create script and schedule workflow to run these checks
-#    and updates on regular bases and in automated way.
-ARG BOOKWORM_SLIM_SHA=sha256:40b107342c492725bc7aacbe93a49945445191ae364184a6d24fedb28172f6f7
-ARG BULLSEYE_SLIM_SHA=sha256:e831d9a884d63734fe3dd9c491ed9a5a3d4c6a6d32c5b14f2067357c49b0b7e1
-
-# Here we use ${var/search/replace} syntax, to check
-# if base image is one of the images, we pin image index for.
-# If var will match one the known images, we will replace it with the known sha.
-# If no match, than value will be unaffected, and will process with no-pinned image.
-ARG BASE_IMAGE_SHA=debian:${DEBIAN_FLAVOR}
-ARG BASE_IMAGE_SHA=${BASE_IMAGE_SHA/debian:bookworm-slim/debian@$BOOKWORM_SLIM_SHA}
-ARG BASE_IMAGE_SHA=${BASE_IMAGE_SHA/debian:bullseye-slim/debian@$BULLSEYE_SLIM_SHA}
-
 # Build Postgres
 FROM $REPOSITORY/$IMAGE:$TAG AS pg-build
 WORKDIR /home/nonroot
@@ -50,14 +28,6 @@ RUN set -e \
     && rm -rf pg_install/build \
     && tar -C pg_install -czf /home/nonroot/postgres_install.tar.gz .
 
-# Prepare cargo-chef recipe
-FROM $REPOSITORY/$IMAGE:$TAG AS plan
-WORKDIR /home/nonroot
-
-COPY --chown=nonroot . .
-
-RUN cargo chef prepare --recipe-path recipe.json
-
 # Build neon binaries
 FROM $REPOSITORY/$IMAGE:$TAG AS build
 WORKDIR /home/nonroot
@@ -71,17 +41,11 @@ COPY --from=pg-build /home/nonroot/pg_install/v16/include/postgresql/server pg_i
 COPY --from=pg-build /home/nonroot/pg_install/v17/include/postgresql/server pg_install/v17/include/postgresql/server
 COPY --from=pg-build /home/nonroot/pg_install/v16/lib                       pg_install/v16/lib
 COPY --from=pg-build /home/nonroot/pg_install/v17/lib                       pg_install/v17/lib
-COPY --from=plan     /home/nonroot/recipe.json                              recipe.json
-
-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 chef cook --locked --release --recipe-path recipe.json
-
 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  \
@@ -95,12 +59,11 @@ RUN set -e \
 
 # Build final image
 #
-FROM $BASE_IMAGE_SHA
+FROM debian:${DEBIAN_FLAVOR}
 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 \
@@ -108,8 +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
@@ -142,9 +103,15 @@ RUN mkdir -p /data/.neon/ && \
   > /data/.neon/pageserver.toml && \
   chown -R neon:neon /data/.neon
 
+# When running a binary that links with libpq, default to using our most recent postgres version.  Binaries
+# that want a particular postgres version will select it explicitly: this is just a default.
+ENV LD_LIBRARY_PATH=/usr/local/v${DEFAULT_PG_VERSION}/lib
+
+
 VOLUME ["/data"]
 USER neon
 EXPOSE 6400
 EXPOSE 9898
 
 CMD ["/usr/local/bin/pageserver", "-D", "/data/.neon"]
+

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

@@ -1,42 +1,8 @@
 ARG DEBIAN_VERSION=bookworm
-ARG DEBIAN_FLAVOR=${DEBIAN_VERSION}-slim
 
-# Here are the INDEX DIGESTS for the images we use.
-# You can get them following next steps for now:
-# 1. Get an authentication token from DockerHub:
-#    TOKEN=$(curl -s "https://auth.docker.io/token?service=registry.docker.io&scope=repository:library/debian:pull" | jq -r .token)
-# 2. Using that token, query index for the given tag:
-#    curl -s -H "Authorization: Bearer $TOKEN" \
-#       -H "Accept: application/vnd.docker.distribution.manifest.list.v2+json" \
-#       "https://registry.hub.docker.com/v2/library/debian/manifests/bullseye-slim" \
-#       -I | grep -i docker-content-digest
-# 3. As a next step, TODO(fedordikarev): create script and schedule workflow to run these checks
-#    and updates on regular bases and in automated way.
-ARG BOOKWORM_SLIM_SHA=sha256:40b107342c492725bc7aacbe93a49945445191ae364184a6d24fedb28172f6f7
-ARG BULLSEYE_SLIM_SHA=sha256:e831d9a884d63734fe3dd9c491ed9a5a3d4c6a6d32c5b14f2067357c49b0b7e1
-
-# Here we use ${var/search/replace} syntax, to check
-# if base image is one of the images, we pin image index for.
-# If var will match one the known images, we will replace it with the known sha.
-# If no match, than value will be unaffected, and will process with no-pinned image.
-ARG BASE_IMAGE_SHA=debian:${DEBIAN_FLAVOR}
-ARG BASE_IMAGE_SHA=${BASE_IMAGE_SHA/debian:bookworm-slim/debian@$BOOKWORM_SLIM_SHA}
-ARG BASE_IMAGE_SHA=${BASE_IMAGE_SHA/debian:bullseye-slim/debian@$BULLSEYE_SLIM_SHA}
-
-FROM $BASE_IMAGE_SHA AS pgcopydb_builder
+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\nretry-on-host-error=on\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 [ "${DEBIAN_VERSION}" = "bookworm" ]; then \
         set -e && \
         apt update && \
@@ -69,7 +35,6 @@ RUN if [ "${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=$(find /lib /usr/lib -name "libpq.so.5" | head -n 1) && \
@@ -81,13 +46,12 @@ RUN if [ "${DEBIAN_VERSION}" = "bookworm" ]; then \
         mkdir -p mkdir -p /pgcopydb/lib && touch /pgcopydb/lib/libpq.so.5; \
     fi
 
-FROM $BASE_IMAGE_SHA AS build_tools
+FROM debian:${DEBIAN_VERSION}-slim AS build_tools
 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 && \
@@ -97,10 +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\nretry-on-host-error=on\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
@@ -155,14 +115,13 @@ 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 \
     && mkdir /tmp/sql_exporter \
     && tar xzvf sql_exporter.tar.gz -C /tmp/sql_exporter --strip-components=1 \
-    && mv /tmp/sql_exporter/sql_exporter /usr/local/bin/sql_exporter \
-    && rm sql_exporter.tar.gz
+    && mv /tmp/sql_exporter/sql_exporter /usr/local/bin/sql_exporter
 
 # protobuf-compiler (protoc)
 ENV PROTOC_VERSION=25.1
@@ -223,20 +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-${OPENSSL_VERSION}
+
 # Use the same version of libicu as the compute nodes so that
 # clusters created using inidb on pageserver can be used by computes.
 #
@@ -265,8 +233,6 @@ RUN wget -O /tmp/libicu-${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 \
@@ -292,7 +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=1.85.0
+ENV RUSTC_VERSION=1.83.0
 ENV RUSTUP_HOME="/home/nonroot/.rustup"
 ENV PATH="/home/nonroot/.cargo/bin:${PATH}"
 ARG RUSTFILT_VERSION=0.2.1
@@ -300,8 +266,6 @@ ARG CARGO_HAKARI_VERSION=0.9.33
 ARG CARGO_DENY_VERSION=0.16.2
 ARG CARGO_HACK_VERSION=0.6.33
 ARG CARGO_NEXTEST_VERSION=0.9.85
-ARG CARGO_CHEF_VERSION=0.1.71
-ARG CARGO_DIESEL_CLI_VERSION=2.2.6
 RUN curl -sSO https://static.rust-lang.org/rustup/dist/$(uname -m)-unknown-linux-gnu/rustup-init && whoami && \
 	chmod +x rustup-init && \
 	./rustup-init -y --default-toolchain ${RUSTC_VERSION} && \
@@ -315,9 +279,6 @@ RUN curl -sSO https://static.rust-lang.org/rustup/dist/$(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 cargo-chef --locked --version ${CARGO_CHEF_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_duckdb_v031.patch

@@ -1,11 +0,0 @@
-diff --git a/sql/pg_duckdb--0.2.0--0.3.0.sql b/sql/pg_duckdb--0.2.0--0.3.0.sql
-index d777d76..af60106 100644
---- a/sql/pg_duckdb--0.2.0--0.3.0.sql
-+++ b/sql/pg_duckdb--0.2.0--0.3.0.sql
-@@ -1056,3 +1056,6 @@ GRANT ALL ON FUNCTION duckdb.cache(TEXT, TEXT) TO PUBLIC;
- GRANT ALL ON FUNCTION duckdb.cache_info() TO PUBLIC;
- GRANT ALL ON FUNCTION duckdb.cache_delete(TEXT) TO PUBLIC;
- GRANT ALL ON PROCEDURE duckdb.recycle_ddb() TO PUBLIC;
-+GRANT ALL ON FUNCTION duckdb.install_extension(TEXT) TO neon_superuser;
-+GRANT ALL ON TABLE duckdb.extensions TO neon_superuser;
-+GRANT ALL ON SEQUENCE duckdb.extensions_table_seq TO neon_superuser;

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/pg_hint_plan_v16.patch

@@ -6,16 +6,16 @@ index da723b8..5328114 100644
  ----
  -- No.A-1-1-3
  CREATE EXTENSION pg_hint_plan;
-+LOG:  Sending request to compute_ctl: http://localhost:3081/extension_server/pg_hint_plan
++LOG:  Sending request to compute_ctl: http://localhost:3080/extension_server/pg_hint_plan
  -- No.A-1-2-3
  DROP EXTENSION pg_hint_plan;
  -- No.A-1-1-4
  CREATE SCHEMA other_schema;
  CREATE EXTENSION pg_hint_plan SCHEMA other_schema;
-+LOG:  Sending request to compute_ctl: http://localhost:3081/extension_server/pg_hint_plan
++LOG:  Sending request to compute_ctl: http://localhost:3080/extension_server/pg_hint_plan
  ERROR:  extension "pg_hint_plan" must be installed in schema "hint_plan"
  CREATE EXTENSION pg_hint_plan;
-+LOG:  Sending request to compute_ctl: http://localhost:3081/extension_server/pg_hint_plan
++LOG:  Sending request to compute_ctl: http://localhost:3080/extension_server/pg_hint_plan
  DROP SCHEMA other_schema;
  ----
  ---- No. A-5-1 comment pattern
@@ -35,7 +35,7 @@ index d372459..6282afe 100644
  SET client_min_messages TO LOG;
  SET pg_hint_plan.enable_hint TO on;
  CREATE EXTENSION file_fdw;
-+LOG:  Sending request to compute_ctl: http://localhost:3081/extension_server/file_fdw
++LOG:  Sending request to compute_ctl: http://localhost:3080/extension_server/file_fdw
  CREATE SERVER file_server FOREIGN DATA WRAPPER file_fdw;
  CREATE USER MAPPING FOR PUBLIC SERVER file_server;
  CREATE FOREIGN TABLE ft1 (id int, val int) SERVER file_server OPTIONS (format 'csv', filename :'filename');

compute/patches/pg_hint_plan_v17.patch

@@ -6,16 +6,16 @@ index e7d68a1..65a056c 100644
  ----
  -- No.A-1-1-3
  CREATE EXTENSION pg_hint_plan;
-+LOG:  Sending request to compute_ctl: http://localhost:3081/extension_server/pg_hint_plan
++LOG:  Sending request to compute_ctl: http://localhost:3080/extension_server/pg_hint_plan
  -- No.A-1-2-3
  DROP EXTENSION pg_hint_plan;
  -- No.A-1-1-4
  CREATE SCHEMA other_schema;
  CREATE EXTENSION pg_hint_plan SCHEMA other_schema;
-+LOG:  Sending request to compute_ctl: http://localhost:3081/extension_server/pg_hint_plan
++LOG:  Sending request to compute_ctl: http://localhost:3080/extension_server/pg_hint_plan
  ERROR:  extension "pg_hint_plan" must be installed in schema "hint_plan"
  CREATE EXTENSION pg_hint_plan;
-+LOG:  Sending request to compute_ctl: http://localhost:3081/extension_server/pg_hint_plan
++LOG:  Sending request to compute_ctl: http://localhost:3080/extension_server/pg_hint_plan
  DROP SCHEMA other_schema;
  ----
  ---- No. A-5-1 comment pattern
@@ -168,7 +168,7 @@ index 017fa4b..98d989b 100644
  SET client_min_messages TO LOG;
  SET pg_hint_plan.enable_hint TO on;
  CREATE EXTENSION file_fdw;
-+LOG:  Sending request to compute_ctl: http://localhost:3081/extension_server/file_fdw
++LOG:  Sending request to compute_ctl: http://localhost:3080/extension_server/file_fdw
  CREATE SERVER file_server FOREIGN DATA WRAPPER file_fdw;
  CREATE USER MAPPING FOR PUBLIC SERVER file_server;
  CREATE FOREIGN TABLE ft1 (id int, val int) SERVER file_server OPTIONS (format 'csv', filename :'filename');

compute/patches/pg_repack.patch

@@ -1,72 +0,0 @@
-diff --git a/regress/Makefile b/regress/Makefile
-index bf6edcb..89b4c7f 100644
---- a/regress/Makefile
-+++ b/regress/Makefile
-@@ -17,7 +17,7 @@ INTVERSION := $(shell echo $$(($$(echo $(VERSION).0 | sed 's/\([[:digit:]]\{1,\}
- # Test suite
- #
- 
--REGRESS := init-extension repack-setup repack-run error-on-invalid-idx no-error-on-invalid-idx after-schema repack-check nosuper tablespace get_order_by trigger
-+REGRESS := init-extension repack-setup repack-run error-on-invalid-idx no-error-on-invalid-idx after-schema repack-check nosuper get_order_by trigger
- 
- USE_PGXS = 1	# use pgxs if not in contrib directory
- PGXS := $(shell $(PG_CONFIG) --pgxs)
-diff --git a/regress/expected/nosuper.out b/regress/expected/nosuper.out
-index 8d0a94e..63b68bf 100644
---- a/regress/expected/nosuper.out
-+++ b/regress/expected/nosuper.out
-@@ -4,22 +4,22 @@
- SET client_min_messages = error;
- DROP ROLE IF EXISTS nosuper;
- SET client_min_messages = warning;
--CREATE ROLE nosuper WITH LOGIN;
-+CREATE ROLE nosuper WITH LOGIN PASSWORD 'NoSuPeRpAsSwOrD';
- -- => OK
- \! pg_repack --dbname=contrib_regression --table=tbl_cluster --no-superuser-check
- INFO: repacking table "public.tbl_cluster"
- -- => ERROR
--\! pg_repack --dbname=contrib_regression --table=tbl_cluster --username=nosuper
-+\! PGPASSWORD=NoSuPeRpAsSwOrD pg_repack --dbname=contrib_regression --table=tbl_cluster --username=nosuper
- ERROR: pg_repack failed with error: You must be a superuser to use pg_repack
- -- => ERROR
--\! pg_repack --dbname=contrib_regression --table=tbl_cluster --username=nosuper --no-superuser-check
-+\! PGPASSWORD=NoSuPeRpAsSwOrD pg_repack --dbname=contrib_regression --table=tbl_cluster --username=nosuper --no-superuser-check
- ERROR: pg_repack failed with error: ERROR:  permission denied for schema repack
- LINE 1: select repack.version(), repack.version_sql()
-                ^
- GRANT ALL ON ALL TABLES IN SCHEMA repack TO nosuper;
- GRANT USAGE ON SCHEMA repack TO nosuper;
- -- => ERROR
--\! pg_repack --dbname=contrib_regression --table=tbl_cluster --username=nosuper --no-superuser-check
-+\! PGPASSWORD=NoSuPeRpAsSwOrD pg_repack --dbname=contrib_regression --table=tbl_cluster --username=nosuper --no-superuser-check
- INFO: repacking table "public.tbl_cluster"
- ERROR: query failed: ERROR:  current transaction is aborted, commands ignored until end of transaction block
- DETAIL: query was: RESET lock_timeout
-diff --git a/regress/sql/nosuper.sql b/regress/sql/nosuper.sql
-index 072f0fa..dbe60f8 100644
---- a/regress/sql/nosuper.sql
-+++ b/regress/sql/nosuper.sql
-@@ -4,19 +4,19 @@
- SET client_min_messages = error;
- DROP ROLE IF EXISTS nosuper;
- SET client_min_messages = warning;
--CREATE ROLE nosuper WITH LOGIN;
-+CREATE ROLE nosuper WITH LOGIN PASSWORD 'NoSuPeRpAsSwOrD';
- -- => OK
- \! pg_repack --dbname=contrib_regression --table=tbl_cluster --no-superuser-check
- -- => ERROR
--\! pg_repack --dbname=contrib_regression --table=tbl_cluster --username=nosuper
-+\! PGPASSWORD=NoSuPeRpAsSwOrD pg_repack --dbname=contrib_regression --table=tbl_cluster --username=nosuper
- -- => ERROR
--\! pg_repack --dbname=contrib_regression --table=tbl_cluster --username=nosuper --no-superuser-check
-+\! PGPASSWORD=NoSuPeRpAsSwOrD pg_repack --dbname=contrib_regression --table=tbl_cluster --username=nosuper --no-superuser-check
- 
- GRANT ALL ON ALL TABLES IN SCHEMA repack TO nosuper;
- GRANT USAGE ON SCHEMA repack TO nosuper;
- 
- -- => ERROR
--\! pg_repack --dbname=contrib_regression --table=tbl_cluster --username=nosuper --no-superuser-check
-+\! PGPASSWORD=NoSuPeRpAsSwOrD pg_repack --dbname=contrib_regression --table=tbl_cluster --username=nosuper --no-superuser-check
- 
- REVOKE ALL ON ALL TABLES IN SCHEMA repack FROM nosuper;
- REVOKE USAGE ON SCHEMA repack FROM nosuper;

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
@@ -74,8 +68,8 @@ build: |
   # At time of migration to bookworm (2024-10-09), debian has a version of libcgroup/cgroup-tools 2.0.2,
   # and it _probably_ can be used as-is. However, we'll build it ourselves to minimise the changeset
   # for debian version migration.
-  ARG BOOKWORM_SLIM_SHA=sha256:40b107342c492725bc7aacbe93a49945445191ae364184a6d24fedb28172f6f7
-  FROM debian@$BOOKWORM_SLIM_SHA as libcgroup-builder
+  #
+  FROM debian:bookworm-slim as libcgroup-builder
   ENV LIBCGROUP_VERSION=v2.0.3
 
   RUN set -exu \

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
@@ -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
@@ -70,8 +64,7 @@ build: |
   # At time of writing (2023-03-14), debian bullseye has a version of cgroup-tools (technically
   # libcgroup) that doesn't support cgroup v2 (version 0.41-11). Unfortunately, the vm-monitor
   # requires cgroup v2, so we'll build cgroup-tools ourselves.
-  ARG BULLSEYE_SLIM_SHA=sha256:e831d9a884d63734fe3dd9c491ed9a5a3d4c6a6d32c5b14f2067357c49b0b7e1
-  FROM debian@$BULLSEYE_SLIM_SHA as libcgroup-builder
+  FROM debian:bullseye-slim as libcgroup-builder
   ENV LIBCGROUP_VERSION=v2.0.3
 
   RUN set -exu \

compute_tools/Cargo.toml

@@ -14,9 +14,7 @@ base64.workspace = true
 aws-config.workspace = true
 aws-sdk-s3.workspace = true
 aws-sdk-kms.workspace = true
-aws-smithy-types.workspace = true
 anyhow.workspace = true
-axum = { workspace = true, features = [] }
 camino.workspace = true
 chrono.workspace = true
 cfg-if.workspace = true
@@ -24,7 +22,7 @@ clap.workspace = true
 fail.workspace = true
 flate2.workspace = true
 futures.workspace = true
-http.workspace = true
+hyper0 = { workspace = true, features = ["full"] }
 metrics.workspace = true
 nix.workspace = true
 notify.workspace = true
@@ -39,20 +37,18 @@ serde_with.workspace = true
 serde_json.workspace = true
 signal-hook.workspace = true
 tar.workspace = true
-tower.workspace = true
-tower-http.workspace = true
 reqwest = { workspace = true, features = ["json"] }
 tokio = { workspace = true, features = ["rt", "rt-multi-thread"] }
 tokio-postgres.workspace = true
 tokio-util.workspace = true
 tokio-stream.workspace = true
 tracing.workspace = true
+tracing-opentelemetry.workspace = true
 tracing-subscriber.workspace = true
 tracing-utils.workspace = true
 thiserror.workspace = true
 url.workspace = true
-uuid.workspace = true
-walkdir.workspace = true
+prometheus.workspace = true
 
 postgres_initdb.workspace = true
 compute_api.workspace = true

compute_tools/src/bin/compute_ctl.rs

@@ -34,7 +34,6 @@
 //!             -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;
@@ -45,16 +44,15 @@ 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::http::server::Server;
 use compute_tools::lsn_lease::launch_lsn_lease_bg_task_for_static;
 use signal_hook::consts::{SIGQUIT, SIGTERM};
 use signal_hook::{consts::SIGINT, iterator::Signals};
 use tracing::{error, info, warn};
 use url::Url;
 
-use compute_api::responses::{ComputeCtlConfig, ComputeStatus};
+use compute_api::responses::ComputeStatus;
 use compute_api::spec::ComputeSpec;
 
 use compute_tools::compute::{
@@ -62,6 +60,7 @@ use compute_tools::compute::{
 };
 use compute_tools::configurator::launch_configurator;
 use compute_tools::extension_server::get_pg_version_string;
+use compute_tools::http::api::launch_http_server;
 use compute_tools::logger::*;
 use compute_tools::monitor::launch_monitor;
 use compute_tools::params::*;
@@ -74,94 +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())
-    }
-}
-
-#[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>,
-
-    /// The port to bind the external listening HTTP server to. Clients running
-    /// outside the compute will talk to the compute through this port. Keep
-    /// the previous name for this argument around for a smoother release
-    /// with the control plane.
-    #[arg(long, default_value_t = 3080)]
-    pub external_http_port: u16,
-
-    /// The port to bind the internal listening HTTP server to. Clients include
-    /// the neon extension (for installing remote extensions) and local_proxy.
-    #[arg(long, default_value_t = 3081)]
-    pub internal_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")]
-    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();
-
-    // For historical reasons, the main thread that processes the spec and launches postgres
-    // is synchronous, but we always have this tokio runtime available and we "enter" it so
-    // that you can use tokio::spawn() and tokio::runtime::Handle::current().block_on(...)
-    // from all parts of compute_ctl.
-    let runtime = tokio::runtime::Builder::new_multi_thread()
-        .enable_all()
-        .build()?;
-    let _rt_guard = runtime.enter();
-
-    let build_tag = runtime.block_on(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)?;
 
@@ -169,11 +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
     };
@@ -190,8 +108,13 @@ fn main() -> Result<()> {
     deinit_and_exit(wait_pg_result);
 }
 
-async fn init() -> Result<String> {
-    init_tracing_and_logging(DEFAULT_LOG_LEVEL).await?;
+fn init() -> Result<(String, clap::ArgMatches)> {
+    init_tracing_and_logging(DEFAULT_LOG_LEVEL)?;
+
+    opentelemetry::global::set_error_handler(|err| {
+        tracing::info!("OpenTelemetry error: {err}");
+    })
+    .expect("global error handler lock poisoned");
 
     let mut signals = Signals::new([SIGINT, SIGTERM, SIGQUIT])?;
     thread::spawn(move || {
@@ -205,7 +128,66 @@ async 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> {
@@ -258,35 +240,48 @@ 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)?),
-            compute_ctl_config: ComputeCtlConfig::default(),
             live_config_allowed: false,
         });
     }
 
     // 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)?),
-            compute_ctl_config: ComputeCtlConfig::default(),
             live_config_allowed: true,
         });
     }
 
-    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) {
-        Ok(resp) => Ok(CliSpecParams {
-            spec: resp.0,
-            compute_ctl_config: resp.1,
+    match get_spec_from_control_plane(control_plane_uri, compute_id) {
+        Ok(spec) => Ok(CliSpecParams {
+            spec,
             live_config_allowed: true,
         }),
         Err(e) => {
@@ -303,20 +298,26 @@ fn try_spec_from_cli(cli: &Cli) -> Result<CliSpecParams> {
 struct CliSpecParams {
     /// If a spec was provided via CLI or file, the [`ComputeSpec`]
     spec: Option<ComputeSpec>,
-    #[allow(dead_code)]
-    compute_ctl_config: ComputeCtlConfig,
     live_config_allowed: bool,
 }
 
 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,
-        compute_ctl_config: _,
     }: CliSpecParams,
-) -> Result<Arc<ComputeNode>> {
+) -> Result<WaitSpecResult> {
     let mut new_state = ComputeState::new();
     let spec_set;
 
@@ -328,25 +329,23 @@ 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),
-        external_http_port: cli.external_http_port,
-        internal_http_port: cli.internal_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,
     };
@@ -360,13 +359,10 @@ fn wait_spec(
         compute.prewarm_postgres()?;
     }
 
-    // Launch the external HTTP server first, so that we can serve control plane
-    // requests while configuration is still in progress.
-    Server::External(cli.external_http_port).launch(&compute);
-
-    // The internal HTTP server could be launched later, but there isn't much
-    // sense in waiting.
-    Server::Internal(cli.internal_http_port).launch(&compute);
+    // Launch http service first, so that we can serve control-plane requests
+    // while configuration is still in progress.
+    let _http_handle =
+        launch_http_server(http_port, &compute).expect("cannot launch http endpoint thread");
 
     if !spec_set {
         // No spec provided, hang waiting for it.
@@ -398,12 +394,27 @@ 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();
@@ -431,7 +442,7 @@ 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.
         //
@@ -458,9 +469,9 @@ 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");
@@ -482,10 +493,7 @@ fn start_postgres(
     let mut pg = None;
     if !prestartup_failed {
         pg = match compute.start_compute() {
-            Ok(pg) => {
-                info!(postmaster_pid = %pg.0.id(), "Postgres was started");
-                Some(pg)
-            }
+            Ok(pg) => Some(pg),
             Err(err) => {
                 error!("could not start the compute node: {:#}", err);
                 compute.set_failed_status(err);
@@ -503,6 +511,27 @@ 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.
+            let rt = if env::var_os("AUTOSCALING").is_some() {
+                Some(
+                    tokio::runtime::Builder::new_multi_thread()
+                        .worker_threads(4)
+                        .enable_all()
+                        .build()
+                        .expect("failed to create tokio runtime for monitor")
+                )
+            } else {
+                None
+            };
 
             // This token is used internally by the monitor to clean up all threads
             let token = CancellationToken::new();
@@ -511,22 +540,19 @@ 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 = if env::var_os("AUTOSCALING").is_some() {
-                let vm_monitor = tokio::spawn(vm_monitor::start(
+            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(),
-                ));
-                Some(vm_monitor)
-            } else {
-                None
-            };
+                ))
+            });
         }
     }
 
@@ -536,6 +562,8 @@ fn start_postgres(
             delay_exit,
             compute,
             #[cfg(target_os = "linux")]
+            rt,
+            #[cfg(target_os = "linux")]
             token,
             #[cfg(target_os = "linux")]
             vm_monitor,
@@ -543,13 +571,15 @@ fn start_postgres(
     ))
 }
 
-type PostgresHandle = (std::process::Child, tokio::task::JoinHandle<Result<()>>);
+type PostgresHandle = (std::process::Child, std::thread::JoinHandle<()>);
 
 struct StartPostgresResult {
     delay_exit: bool,
     // passed through from WaitSpecResult
     compute: Arc<ComputeNode>,
 
+    #[cfg(target_os = "linux")]
+    rt: Option<tokio::runtime::Runtime>,
     #[cfg(target_os = "linux")]
     token: tokio_util::sync::CancellationToken,
     #[cfg(target_os = "linux")]
@@ -561,17 +591,15 @@ fn wait_postgres(pg: Option<PostgresHandle>) -> Result<WaitPostgresResult> {
     // propagate to Postgres and it will be shut down as well.
     let mut exit_code = None;
     if let Some((mut pg, logs_handle)) = pg {
-        info!(postmaster_pid = %pg.id(), "Waiting for Postgres to exit");
-
         let ecode = pg
             .wait()
             .expect("failed to start waiting on Postgres process");
         PG_PID.store(0, Ordering::SeqCst);
 
-        // Process has exited. Wait for the log collecting task to finish.
-        let _ = tokio::runtime::Handle::current()
-            .block_on(logs_handle)
-            .map_err(|e| tracing::error!("log task panicked: {:?}", e));
+        // Process has exited, so we can join the logs thread.
+        let _ = logs_handle
+            .join()
+            .map_err(|e| tracing::error!("log thread panicked: {:?}", e));
 
         info!("Postgres exited with code {}, shutting down", ecode);
         exit_code = ecode.code()
@@ -592,6 +620,8 @@ fn cleanup_after_postgres_exit(
         vm_monitor,
         #[cfg(target_os = "linux")]
         token,
+        #[cfg(target_os = "linux")]
+        rt,
     }: StartPostgresResult,
 ) -> Result<bool> {
     // Terminate the vm_monitor so it releases the file watcher on
@@ -604,6 +634,10 @@ fn cleanup_after_postgres_exit(
                 token.cancel();
                 // Kills the actual task running the monitor
                 handle.abort();
+
+                // If handle is some, rt must have been used to produce it, and
+                // hence is also some
+                rt.unwrap().shutdown_timeout(Duration::from_secs(2));
             }
         }
     }
@@ -668,6 +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.
@@ -677,14 +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

@@ -17,7 +17,7 @@
 //!
 //! # Local Testing
 //!
-//! - Comment out most of the pgxns in compute-node.Dockerfile to speed up the build.
+//! - Comment out most of the pgxns in The Dockerfile.compute-tools to speed up the build.
 //! - Build the image with the following command:
 //!
 //! ```bash
@@ -25,13 +25,13 @@
 //! docker push localhost:3030/localregistry/compute-node-v14:latest
 //! ```
 
-use anyhow::{bail, Context};
+use anyhow::Context;
 use aws_config::BehaviorVersion;
 use camino::{Utf8Path, Utf8PathBuf};
-use clap::{Parser, Subcommand};
+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"]
@@ -41,62 +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(Subcommand, Debug)]
-enum Command {
-    /// Runs local postgres (neon binary), restores into it,
-    /// uploads pgdata to s3 to be consumed by pageservers
-    Pgdata {
-        /// Raw connection string to the source database. Used only in tests,
-        /// real scenario uses encrypted connection string in spec.json from s3.
-        #[clap(long)]
-        source_connection_string: Option<String>,
-        /// If specified, will not shut down the local postgres after the import. Used in local testing
-        #[clap(short, long)]
-        interactive: bool,
-        /// Port to run postgres on. Default is 5432.
-        #[clap(long, default_value_t = 5432)]
-        pg_port: u16, // port to run postgres on, 5432 is default
-
-        /// Number of CPUs in the system. This is used to configure # of
-        /// parallel worker processes, for index creation.
-        #[clap(long, env = "NEON_IMPORTER_NUM_CPUS")]
-        num_cpus: Option<usize>,
-
-        /// Amount of RAM in the system. This is used to configure shared_buffers
-        /// and maintenance_work_mem.
-        #[clap(long, env = "NEON_IMPORTER_MEMORY_MB")]
-        memory_mb: Option<usize>,
-    },
-
-    /// Runs pg_dump-pg_restore from source to destination without running local postgres.
-    DumpRestore {
-        /// Raw connection string to the source database. Used only in tests,
-        /// real scenario uses encrypted connection string in spec.json from s3.
-        #[clap(long)]
-        source_connection_string: Option<String>,
-        /// Raw connection string to the destination database. Used only in tests,
-        /// real scenario uses encrypted connection string in spec.json from s3.
-        #[clap(long)]
-        destination_connection_string: Option<String>,
-    },
-}
-
 #[derive(clap::Parser)]
 struct Args {
-    #[clap(long, env = "NEON_IMPORTER_WORKDIR")]
+    #[clap(long)]
     working_directory: Utf8PathBuf,
     #[clap(long, env = "NEON_IMPORTER_S3_PREFIX")]
-    s3_prefix: Option<s3_uri::S3Uri>,
-    #[clap(long, env = "NEON_IMPORTER_PG_BIN_DIR")]
+    s3_prefix: s3_uri::S3Uri,
+    #[clap(long)]
     pg_bin_dir: Utf8PathBuf,
-    #[clap(long, env = "NEON_IMPORTER_PG_LIB_DIR")]
+    #[clap(long)]
     pg_lib_dir: Utf8PathBuf,
-
-    #[clap(subcommand)]
-    command: Command,
 }
 
 #[serde_with::serde_as]
@@ -105,8 +59,6 @@ struct Spec {
     encryption_secret: EncryptionSecret,
     #[serde_as(as = "serde_with::base64::Base64")]
     source_connstring_ciphertext_base64: Vec<u8>,
-    #[serde_as(as = "Option<serde_with::base64::Base64>")]
-    destination_connstring_ciphertext_base64: Option<Vec<u8>>,
 }
 
 #[derive(serde::Deserialize)]
@@ -115,220 +67,164 @@ 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(
+        utils::logging::LogFormat::Plain,
+        utils::logging::TracingErrorLayerEnablement::EnableWithRustLogFilter,
+        utils::logging::Output::Stdout,
+    )?;
 
-async fn decode_connstring(
-    kms_client: &aws_sdk_kms::Client,
-    key_id: &String,
-    connstring_ciphertext_base64: Vec<u8>,
-) -> Result<String, anyhow::Error> {
-    let mut output = kms_client
-        .decrypt()
-        .key_id(key_id)
-        .ciphertext_blob(aws_sdk_s3::primitives::Blob::new(
-            connstring_ciphertext_base64,
-        ))
-        .send()
-        .await
-        .context("decrypt connection string")?;
+    info!("starting");
 
-    let plaintext = output
-        .plaintext
-        .take()
-        .context("get plaintext connection string")?;
+    let Args {
+        working_directory,
+        s3_prefix,
+        pg_bin_dir,
+        pg_lib_dir,
+    } = Args::parse();
 
-    String::from_utf8(plaintext.into_inner()).context("parse connection string as utf8")
-}
+    let aws_config = aws_config::load_defaults(BehaviorVersion::v2024_03_28()).await;
 
-struct PostgresProcess {
-    pgdata_dir: Utf8PathBuf,
-    pg_bin_dir: Utf8PathBuf,
-    pgbin: Utf8PathBuf,
-    pg_lib_dir: Utf8PathBuf,
-    postgres_proc: Option<tokio::process::Child>,
-}
+    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")?
+    };
 
-impl PostgresProcess {
-    fn new(pgdata_dir: Utf8PathBuf, pg_bin_dir: Utf8PathBuf, pg_lib_dir: Utf8PathBuf) -> Self {
-        Self {
-            pgdata_dir,
-            pgbin: pg_bin_dir.join("postgres"),
-            pg_bin_dir,
-            pg_lib_dir,
-            postgres_proc: None,
+    match tokio::fs::create_dir(&working_directory).await {
+        Ok(()) => {}
+        Err(e) if e.kind() == std::io::ErrorKind::AlreadyExists => {
+            if !is_directory_empty(&working_directory)
+                .await
+                .context("check if working directory is empty")?
+            {
+                anyhow::bail!("working directory is not empty");
+            } else {
+                // ok
+            }
         }
+        Err(e) => return Err(anyhow::Error::new(e).context("create working directory")),
     }
 
-    async fn prepare(&self, initdb_user: &str) -> Result<(), anyhow::Error> {
-        tokio::fs::create_dir(&self.pgdata_dir)
-            .await
-            .context("create pgdata directory")?;
-
-        let pg_version = match get_pg_version(self.pgbin.as_ref()) {
-            PostgresMajorVersion::V14 => 14,
-            PostgresMajorVersion::V15 => 15,
-            PostgresMajorVersion::V16 => 16,
-            PostgresMajorVersion::V17 => 17,
-        };
-        postgres_initdb::do_run_initdb(postgres_initdb::RunInitdbArgs {
-            superuser: initdb_user,
-            locale: DEFAULT_LOCALE, // XXX: this shouldn't be hard-coded,
-            pg_version,
-            initdb_bin: self.pg_bin_dir.join("initdb").as_ref(),
-            library_search_path: &self.pg_lib_dir, // TODO: is this right? Prob works in compute image, not sure about neon_local.
-            pgdata: &self.pgdata_dir,
-        })
+    let pgdata_dir = working_directory.join("pgdata");
+    tokio::fs::create_dir(&pgdata_dir)
         .await
-        .context("initdb")
-    }
+        .context("create pgdata directory")?;
 
-    async fn start(
-        &mut self,
-        initdb_user: &str,
-        port: u16,
-        nproc: usize,
-        memory_mb: usize,
-    ) -> Result<&tokio::process::Child, anyhow::Error> {
-        self.prepare(initdb_user).await?;
+    //
+    // Setup clients
+    //
+    let aws_config = aws_config::load_defaults(BehaviorVersion::v2024_03_28()).await;
+    let kms_client = aws_sdk_kms::Client::new(&aws_config);
 
-        // Somewhat arbitrarily, use 10 % of memory for shared buffer cache, 70% for
-        // maintenance_work_mem (i.e. for sorting during index creation), and leave the rest
-        // available for misc other stuff that PostgreSQL uses memory for.
-        let shared_buffers_mb = ((memory_mb as f32) * 0.10) as usize;
-        let maintenance_work_mem_mb = ((memory_mb as f32) * 0.70) as usize;
+    //
+    //  Initialize pgdata
+    //
+    let pgbin = pg_bin_dir.join("postgres");
+    let pg_version = match get_pg_version(pgbin.as_ref()) {
+        PostgresMajorVersion::V14 => 14,
+        PostgresMajorVersion::V15 => 15,
+        PostgresMajorVersion::V16 => 16,
+        PostgresMajorVersion::V17 => 17,
+    };
+    let superuser = "cloud_admin"; // XXX: this shouldn't be hard-coded
+    postgres_initdb::do_run_initdb(postgres_initdb::RunInitdbArgs {
+        superuser,
+        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.
+        pgdata: &pgdata_dir,
+    })
+    .await
+    .context("initdb")?;
 
-        //
-        // Launch postgres process
-        //
-        let mut proc = tokio::process::Command::new(&self.pgbin)
-            .arg("-D")
-            .arg(&self.pgdata_dir)
-            .args(["-p", &format!("{port}")])
-            .args(["-c", "wal_level=minimal"])
-            .args(["-c", &format!("shared_buffers={shared_buffers_mb}MB")])
-            .args(["-c", "max_wal_senders=0"])
-            .args(["-c", "fsync=off"])
-            .args(["-c", "full_page_writes=off"])
-            .args(["-c", "synchronous_commit=off"])
-            .args([
-                "-c",
-                &format!("maintenance_work_mem={maintenance_work_mem_mb}MB"),
-            ])
-            .args(["-c", &format!("max_parallel_maintenance_workers={nproc}")])
-            .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", "effective_io_concurrency=100"])
-            .env_clear()
-            .env("LD_LIBRARY_PATH", &self.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()
-            .context("spawn postgres")?;
+    let nproc = num_cpus::get();
 
-        info!("spawned postgres, waiting for it to become ready");
-        tokio::spawn(
-            child_stdio_to_log::relay_process_output(proc.stdout.take(), proc.stderr.take())
-                .instrument(info_span!("postgres")),
-        );
+    //
+    // Launch postgres process
+    //
+    let mut postgres_proc = tokio::process::Command::new(pgbin)
+        .arg("-D")
+        .arg(&pgdata_dir)
+        .args(["-c", "wal_level=minimal"])
+        .args(["-c", "shared_buffers=10GB"])
+        .args(["-c", "max_wal_senders=0"])
+        .args(["-c", "fsync=off"])
+        .args(["-c", "full_page_writes=off"])
+        .args(["-c", "synchronous_commit=off"])
+        .args(["-c", "maintenance_work_mem=8388608"])
+        .args(["-c", &format!("max_parallel_maintenance_workers={nproc}")])
+        .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", "effective_io_concurrency=100"])
+        .env_clear()
+        .stdout(std::process::Stdio::piped())
+        .stderr(std::process::Stdio::piped())
+        .spawn()
+        .context("spawn postgres")?;
 
-        self.postgres_proc = Some(proc);
-        Ok(self.postgres_proc.as_ref().unwrap())
-    }
-
-    async fn shutdown(&mut self) -> Result<(), anyhow::Error> {
-        let proc: &mut tokio::process::Child = self.postgres_proc.as_mut().unwrap();
-        info!("shutdown postgres");
-        nix::sys::signal::kill(
-            Pid::from_raw(i32::try_from(proc.id().unwrap()).expect("convert child pid to i32")),
-            nix::sys::signal::SIGTERM,
+    info!("spawned postgres, waiting for it to become ready");
+    tokio::spawn(
+        child_stdio_to_log::relay_process_output(
+            postgres_proc.stdout.take(),
+            postgres_proc.stderr.take(),
         )
-        .context("signal postgres to shut down")?;
-        proc.wait()
-            .await
-            .context("wait for postgres to shut down")
-            .map(|_| ())
-    }
-}
-
-async fn wait_until_ready(connstring: String, create_dbname: String) {
-    // Create neondb database in the running postgres
-    let start_time = std::time::Instant::now();
-
+        .instrument(info_span!("postgres")),
+    );
+    let restore_pg_connstring =
+        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(
-            &connstring.replace("dbname=neondb", "dbname=postgres"),
-            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(format!("CREATE DATABASE {create_dbname};").as_str())
-                    .await
-                {
-                    Ok(_) => {
-                        info!("created {} database", create_dbname);
-                        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;
         }
     }
-}
 
-async fn run_dump_restore(
-    workdir: Utf8PathBuf,
-    pg_bin_dir: Utf8PathBuf,
-    pg_lib_dir: Utf8PathBuf,
-    source_connstring: String,
-    destination_connstring: String,
-) -> Result<(), anyhow::Error> {
-    let dumpdir = workdir.join("dumpdir");
+    //
+    // 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");
 
     let common_args = [
         // schema mapping (prob suffices to specify them on one side)
@@ -357,18 +253,9 @@ async fn run_dump_restore(
             .arg("--no-sync")
             // POSITIONAL args
             // source db (db name included in connection string)
-            .arg(&source_connstring)
+            .arg(&source_connection_string)
             // how we run it
             .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(),
-            )
             .kill_on_drop(true)
             .stdout(std::process::Stdio::piped())
             .stderr(std::process::Stdio::piped())
@@ -385,31 +272,23 @@ async fn run_dump_restore(
         let st = pg_dump.wait().await.context("wait for pg_dump")?;
         info!(status=?st, "pg_dump exited");
         if !st.success() {
-            error!(status=%st, "pg_dump failed, restore will likely fail as well");
-            bail!("pg_dump failed");
+            warn!(status=%st, "pg_dump failed, restore will likely fail as well");
         }
     }
 
-    // TODO: maybe do it in a streaming way, plenty of internal research done on this already
+    // TODO: do it in a streaming way, plenty of internal research done on this already
     // TODO: do the unlogged table trick
+
+    info!("restore from working directory into vanilla postgres");
     {
         let mut pg_restore = tokio::process::Command::new(pg_bin_dir.join("pg_restore"))
             .args(&common_args)
             .arg("-d")
-            .arg(&destination_connstring)
+            .arg(&restore_pg_connstring)
             // POSITIONAL args
             .arg(&dumpdir)
             // how we run it
             .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(),
-            )
             .kill_on_drop(true)
             .stdout(std::process::Stdio::piped())
             .stderr(std::process::Stdio::piped())
@@ -427,260 +306,40 @@ async fn run_dump_restore(
         let st = pg_restore.wait().await.context("wait for pg_restore")?;
         info!(status=?st, "pg_restore exited");
         if !st.success() {
-            error!(status=%st, "pg_restore failed, restore will likely fail as well");
-            bail!("pg_restore failed");
+            warn!(status=%st, "pg_restore failed, restore will likely fail as well");
         }
     }
 
-    Ok(())
-}
-
-#[allow(clippy::too_many_arguments)]
-async fn cmd_pgdata(
-    s3_client: Option<aws_sdk_s3::Client>,
-    kms_client: Option<aws_sdk_kms::Client>,
-    maybe_s3_prefix: Option<s3_uri::S3Uri>,
-    maybe_spec: Option<Spec>,
-    source_connection_string: Option<String>,
-    interactive: bool,
-    pg_port: u16,
-    workdir: Utf8PathBuf,
-    pg_bin_dir: Utf8PathBuf,
-    pg_lib_dir: Utf8PathBuf,
-    num_cpus: Option<usize>,
-    memory_mb: Option<usize>,
-) -> Result<(), anyhow::Error> {
-    if maybe_spec.is_none() && source_connection_string.is_none() {
-        bail!("spec must be provided for pgdata command");
-    }
-    if maybe_spec.is_some() && source_connection_string.is_some() {
-        bail!("only one of spec or source_connection_string can be provided");
-    }
-
-    let source_connection_string = if let Some(spec) = maybe_spec {
-        match spec.encryption_secret {
-            EncryptionSecret::KMS { key_id } => {
-                decode_connstring(
-                    kms_client.as_ref().unwrap(),
-                    &key_id,
-                    spec.source_connstring_ciphertext_base64,
-                )
-                .await?
-            }
-        }
-    } else {
-        source_connection_string.unwrap()
-    };
-
-    let superuser = "cloud_admin";
-    let destination_connstring = format!(
-        "host=localhost port={} user={} dbname=neondb",
-        pg_port, superuser
-    );
-
-    let pgdata_dir = workdir.join("pgdata");
-    let mut proc = PostgresProcess::new(pgdata_dir.clone(), pg_bin_dir.clone(), pg_lib_dir.clone());
-    let nproc = num_cpus.unwrap_or_else(num_cpus::get);
-    let memory_mb = memory_mb.unwrap_or(256);
-    proc.start(superuser, pg_port, nproc, memory_mb).await?;
-    wait_until_ready(destination_connstring.clone(), "neondb".to_string()).await;
-
-    run_dump_restore(
-        workdir.clone(),
-        pg_bin_dir,
-        pg_lib_dir,
-        source_connection_string,
-        destination_connstring,
-    )
-    .await?;
-
-    // If interactive mode, wait for Ctrl+C
-    if interactive {
-        info!("Running in interactive mode. Press Ctrl+C to shut down.");
-        tokio::signal::ctrl_c().await.context("wait for ctrl-c")?;
-    }
-
-    proc.shutdown().await?;
-
-    // Only sync if s3_prefix was specified
-    if let Some(s3_prefix) = maybe_s3_prefix {
-        info!("upload pgdata");
-        aws_s3_sync::upload_dir_recursive(
-            s3_client.as_ref().unwrap(),
-            Utf8Path::new(&pgdata_dir),
-            &s3_prefix.append("/pgdata/"),
+    info!("shutdown postgres");
+    {
+        nix::sys::signal::kill(
+            Pid::from_raw(
+                i32::try_from(postgres_proc.id().unwrap()).expect("convert child pid to i32"),
+            ),
+            nix::sys::signal::SIGTERM,
         )
+        .context("signal postgres to shut down")?;
+        postgres_proc
+            .wait()
+            .await
+            .context("wait for postgres to shut down")?;
+    }
+
+    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 = workdir.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::upload_dir_recursive(
-                s3_client.as_ref().unwrap(),
-                &status_dir,
-                &s3_prefix.append("/status/"),
-            )
+    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(())
-}
-
-async fn cmd_dumprestore(
-    kms_client: Option<aws_sdk_kms::Client>,
-    maybe_spec: Option<Spec>,
-    source_connection_string: Option<String>,
-    destination_connection_string: Option<String>,
-    workdir: Utf8PathBuf,
-    pg_bin_dir: Utf8PathBuf,
-    pg_lib_dir: Utf8PathBuf,
-) -> Result<(), anyhow::Error> {
-    let (source_connstring, destination_connstring) = if let Some(spec) = maybe_spec {
-        match spec.encryption_secret {
-            EncryptionSecret::KMS { key_id } => {
-                let source = decode_connstring(
-                    kms_client.as_ref().unwrap(),
-                    &key_id,
-                    spec.source_connstring_ciphertext_base64,
-                )
-                .await?;
-
-                let dest = if let Some(dest_ciphertext) =
-                    spec.destination_connstring_ciphertext_base64
-                {
-                    decode_connstring(kms_client.as_ref().unwrap(), &key_id, dest_ciphertext)
-                        .await?
-                } else {
-                    bail!("destination connection string must be provided in spec for dump_restore command");
-                };
-
-                (source, dest)
-            }
-        }
-    } else {
-        (
-            source_connection_string.unwrap(),
-            if let Some(val) = destination_connection_string {
-                val
-            } else {
-                bail!("destination connection string must be provided for dump_restore command");
-            },
-        )
-    };
-
-    run_dump_restore(
-        workdir,
-        pg_bin_dir,
-        pg_lib_dir,
-        source_connstring,
-        destination_connstring,
-    )
-    .await
-}
-
-#[tokio::main]
-pub(crate) async fn main() -> anyhow::Result<()> {
-    utils::logging::init(
-        utils::logging::LogFormat::Json,
-        utils::logging::TracingErrorLayerEnablement::EnableWithRustLogFilter,
-        utils::logging::Output::Stdout,
-    )?;
-
-    info!("starting");
-
-    let args = Args::parse();
-
-    // Initialize AWS clients only if s3_prefix is specified
-    let (s3_client, kms_client) = if args.s3_prefix.is_some() {
-        let config = aws_config::load_defaults(BehaviorVersion::v2024_03_28()).await;
-        let s3_client = aws_sdk_s3::Client::new(&config);
-        let kms = aws_sdk_kms::Client::new(&config);
-        (Some(s3_client), Some(kms))
-    } else {
-        (None, None)
-    };
-
-    let spec: Option<Spec> = if let Some(s3_prefix) = &args.s3_prefix {
-        let spec_key = s3_prefix.append("/spec.json");
-        let object = s3_client
-            .as_ref()
-            .unwrap()
-            .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")?
-    } else {
-        None
-    };
-
-    match tokio::fs::create_dir(&args.working_directory).await {
-        Ok(()) => {}
-        Err(e) if e.kind() == std::io::ErrorKind::AlreadyExists => {
-            if !is_directory_empty(&args.working_directory)
-                .await
-                .context("check if working directory is empty")?
-            {
-                bail!("working directory is not empty");
-            } else {
-                // ok
-            }
-        }
-        Err(e) => return Err(anyhow::Error::new(e).context("create working directory")),
-    }
-
-    match args.command {
-        Command::Pgdata {
-            source_connection_string,
-            interactive,
-            pg_port,
-            num_cpus,
-            memory_mb,
-        } => {
-            cmd_pgdata(
-                s3_client,
-                kms_client,
-                args.s3_prefix,
-                spec,
-                source_connection_string,
-                interactive,
-                pg_port,
-                args.working_directory,
-                args.pg_bin_dir,
-                args.pg_lib_dir,
-                num_cpus,
-                memory_mb,
-            )
-            .await?;
-        }
-        Command::DumpRestore {
-            source_connection_string,
-            destination_connection_string,
-        } => {
-            cmd_dumprestore(
-                kms_client,
-                spec,
-                source_connection_string,
-                destination_connection_string,
-                args.working_directory,
-                args.pg_bin_dir,
-                args.pg_lib_dir,
-            )
-            .await?;
-        }
     }
 
     Ok(())

compute_tools/src/bin/fast_import/aws_s3_sync.rs

@@ -1,102 +1,24 @@
-use camino::{Utf8Path, Utf8PathBuf};
-use tokio::task::JoinSet;
-use walkdir::WalkDir;
+use anyhow::Context;
+use camino::Utf8Path;
 
 use super::s3_uri::S3Uri;
 
-use tracing::{info, warn};
-
-const MAX_PARALLEL_UPLOADS: usize = 10;
-
-/// Upload all files from 'local' to 'remote'
-pub(crate) async fn upload_dir_recursive(
-    s3_client: &aws_sdk_s3::Client,
-    local: &Utf8Path,
-    remote: &S3Uri,
-) -> anyhow::Result<()> {
-    // Recursively scan directory
-    let mut dirwalker = WalkDir::new(local)
-        .into_iter()
-        .map(|entry| {
-            let entry = entry?;
-            let file_type = entry.file_type();
-            let path = <&Utf8Path>::try_from(entry.path())?.to_path_buf();
-            Ok((file_type, path))
-        })
-        .filter_map(|e: anyhow::Result<(std::fs::FileType, Utf8PathBuf)>| {
-            match e {
-                Ok((file_type, path)) if file_type.is_file() => Some(Ok(path)),
-                Ok((file_type, _path)) if file_type.is_dir() => {
-                    // The WalkDir iterator will recurse into directories, but we don't want
-                    // to do anything with directories as such. There's no concept of uploading
-                    // an empty directory to S3.
-                    None
-                }
-                Ok((file_type, path)) if file_type.is_symlink() => {
-                    // huh, didn't expect a symlink. Can't upload that to S3. Warn and skip.
-                    warn!("cannot upload symlink ({})", path);
-                    None
-                }
-                Ok((_file_type, path)) => {
-                    // should not happen
-                    warn!("directory entry has unexpected type ({})", path);
-                    None
-                }
-                Err(e) => Some(Err(e)),
-            }
-        });
-
-    // Spawn upload tasks for each file, keeping MAX_PARALLEL_UPLOADS active in
-    // parallel.
-    let mut joinset = JoinSet::new();
-    loop {
-        // Could we upload more?
-        while joinset.len() < MAX_PARALLEL_UPLOADS {
-            if let Some(full_local_path) = dirwalker.next() {
-                let full_local_path = full_local_path?;
-                let relative_local_path = full_local_path
-                    .strip_prefix(local)
-                    .expect("all paths start from the walkdir root");
-                let remote_path = remote.append(relative_local_path.as_str());
-                info!(
-                    "starting upload of {} to {}",
-                    &full_local_path, &remote_path
-                );
-                let upload_task = upload_file(s3_client.clone(), full_local_path, remote_path);
-                joinset.spawn(upload_task);
-            } else {
-                info!("draining upload tasks");
-                break;
-            }
-        }
-
-        // Wait for an upload to complete
-        if let Some(res) = joinset.join_next().await {
-            let _ = res?;
-        } else {
-            // all done!
-            break;
-        }
+pub(crate) async fn sync(local: &Utf8Path, remote: &S3Uri) -> anyhow::Result<()> {
+    let mut builder = tokio::process::Command::new("aws");
+    builder
+        .arg("s3")
+        .arg("sync")
+        .arg(local.as_str())
+        .arg(remote.to_string());
+    let st = builder
+        .spawn()
+        .context("spawn aws s3 sync")?
+        .wait()
+        .await
+        .context("wait for aws s3 sync")?;
+    if st.success() {
+        Ok(())
+    } else {
+        Err(anyhow::anyhow!("aws s3 sync failed"))
     }
-    Ok(())
-}
-
-pub(crate) async fn upload_file(
-    s3_client: aws_sdk_s3::Client,
-    local_path: Utf8PathBuf,
-    remote: S3Uri,
-) -> anyhow::Result<()> {
-    use aws_smithy_types::byte_stream::ByteStream;
-    let stream = ByteStream::from_path(&local_path).await?;
-
-    let _result = s3_client
-        .put_object()
-        .bucket(remote.bucket)
-        .key(&remote.key)
-        .body(stream)
-        .send()
-        .await?;
-    info!("upload of {} to {} finished", &local_path, &remote.key);
-
-    Ok(())
 }

compute_tools/src/catalog.rs

@@ -36,11 +36,11 @@ pub async fn get_dbs_and_roles(compute: &Arc<ComputeNode>) -> anyhow::Result<Cat
 
 #[derive(Debug, thiserror::Error)]
 pub enum SchemaDumpError {
-    #[error("database does not exist")]
+    #[error("Database does not exist.")]
     DatabaseDoesNotExist,
-    #[error("failed to execute pg_dump")]
+    #[error("Failed to execute pg_dump.")]
     IO(#[from] std::io::Error),
-    #[error("unexpected I/O error")]
+    #[error("Unexpected error.")]
     Unexpected,
 }
 
@@ -140,34 +140,5 @@ pub async fn get_database_schema(
             warn!("pg_dump stderr: {}", line)
         }
     });
-
-    #[allow(dead_code)]
-    struct SchemaStream<S> {
-        // We keep a reference to the child process to ensure it stays alive
-        // while the stream is being consumed. When SchemaStream is dropped,
-        // cmd will be dropped, which triggers kill_on_drop and terminates pg_dump
-        cmd: tokio::process::Child,
-        stream: S,
-    }
-
-    impl<S> Stream for SchemaStream<S>
-    where
-        S: Stream<Item = Result<bytes::Bytes, std::io::Error>> + Unpin,
-    {
-        type Item = Result<bytes::Bytes, std::io::Error>;
-
-        fn poll_next(
-            mut self: std::pin::Pin<&mut Self>,
-            cx: &mut std::task::Context<'_>,
-        ) -> std::task::Poll<Option<Self::Item>> {
-            Stream::poll_next(std::pin::Pin::new(&mut self.stream), cx)
-        }
-    }
-
-    let schema_stream = SchemaStream {
-        cmd,
-        stream: initial_stream.chain(stdout_reader.map(|res| res.map(|b| b.freeze()))),
-    };
-
-    Ok(schema_stream)
+    Ok(initial_stream.chain(stdout_reader.map(|res| res.map(|b| b.freeze()))))
 }

compute_tools/src/compute.rs

@@ -9,6 +9,7 @@ use std::str::FromStr;
 use std::sync::atomic::AtomicU32;
 use std::sync::atomic::Ordering;
 use std::sync::{Arc, Condvar, Mutex, RwLock};
+use std::thread;
 use std::time::Duration;
 use std::time::Instant;
 
@@ -40,14 +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};
@@ -58,8 +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
@@ -82,10 +81,8 @@ pub struct ComputeNode {
     /// - we push spec and it does configuration
     /// - but then it is restarted without any spec again
     pub live_config_allowed: bool,
-    /// The port that the compute's external HTTP server listens on
-    pub external_http_port: u16,
-    /// The port that the compute's internal HTTP server listens on
-    pub internal_http_port: u16,
+    /// The port that the compute's HTTP server listens on
+    pub http_port: u16,
     /// Volatile part of the `ComputeNode`, which should be used under `Mutex`.
     /// To allow HTTP API server to serving status requests, while configuration
     /// is in progress, lock should be held only for short periods of time to do
@@ -343,15 +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)'.
@@ -549,7 +537,11 @@ impl ComputeNode {
     pub fn check_safekeepers_synced(&self, compute_state: &ComputeState) -> Result<Option<Lsn>> {
         let start_time = Utc::now();
 
-        let rt = tokio::runtime::Handle::current();
+        // Run actual work with new tokio runtime
+        let rt = tokio::runtime::Builder::new_current_thread()
+            .enable_all()
+            .build()
+            .expect("failed to create rt");
         let result = rt.block_on(self.check_safekeepers_synced_async(compute_state));
 
         // Record runtime
@@ -596,9 +588,9 @@ impl ComputeNode {
         SYNC_SAFEKEEPERS_PID.store(0, Ordering::SeqCst);
 
         // Process has exited, so we can join the logs thread.
-        let _ = tokio::runtime::Handle::current()
-            .block_on(logs_handle)
-            .map_err(|e| tracing::error!("log task panicked: {:?}", e));
+        let _ = logs_handle
+            .join()
+            .map_err(|e| tracing::error!("log thread panicked: {:?}", e));
 
         if !sync_output.status.success() {
             anyhow::bail!(
@@ -633,7 +625,7 @@ impl ComputeNode {
         config::write_postgres_conf(
             &pgdata_path.join("postgresql.conf"),
             &pspec.spec,
-            self.internal_http_port,
+            self.http_port,
         )?;
 
         // Syncing safekeepers is only safe with primary nodes: if a primary
@@ -783,7 +775,7 @@ impl ComputeNode {
     pub fn start_postgres(
         &self,
         storage_auth_token: Option<String>,
-    ) -> Result<(std::process::Child, tokio::task::JoinHandle<Result<()>>)> {
+    ) -> Result<(std::process::Child, std::thread::JoinHandle<()>)> {
         let pgdata_path = Path::new(&self.pgdata);
 
         // Run postgres as a child process.
@@ -799,7 +791,7 @@ impl ComputeNode {
             .expect("cannot start postgres process");
         PG_PID.store(pg.id(), Ordering::SeqCst);
 
-        // Start a task to collect logs from stderr.
+        // Start a thread to collect logs from stderr.
         let stderr = pg.stderr.take().expect("stderr should be captured");
         let logs_handle = handle_postgres_logs(stderr);
 
@@ -808,28 +800,20 @@ impl ComputeNode {
         Ok((pg, logs_handle))
     }
 
-    /// Do post configuration of the already started Postgres. This function spawns a background task to
+    /// Do post configuration of the already started Postgres. This function spawns a background thread to
     /// configure the database after applying the compute spec. Currently, it upgrades the neon extension
     /// version. In the future, it may upgrade all 3rd-party extensions.
     #[instrument(skip_all)]
     pub fn post_apply_config(&self) -> Result<()> {
-        let conf = self.get_tokio_conn_conf(Some("compute_ctl:post_apply_config"));
-        tokio::spawn(async move {
-            let res = async {
-                let (mut client, connection) = conf.connect(NoTls).await?;
-                tokio::spawn(async move {
-                    if let Err(e) = connection.await {
-                        eprintln!("connection error: {}", e);
-                    }
-                });
-
+        let conf = self.get_conn_conf(Some("compute_ctl:post_apply_config"));
+        thread::spawn(move || {
+            let func = || {
+                let mut client = conf.connect(NoTls)?;
                 handle_neon_extension_upgrade(&mut client)
-                    .await
                     .context("handle_neon_extension_upgrade")?;
                 Ok::<_, anyhow::Error>(())
-            }
-            .await;
-            if let Err(err) = res {
+            };
+            if let Err(err) = func() {
                 error!("error while post_apply_config: {err:#}");
             }
         });
@@ -926,10 +910,13 @@ impl ComputeNode {
         conf: Arc<tokio_postgres::Config>,
         concurrency: usize,
     ) -> Result<()> {
+        let rt = tokio::runtime::Builder::new_multi_thread()
+            .enable_all()
+            .build()?;
+
         info!("Applying config with max {} concurrency", concurrency);
         debug!("Config: {:?}", spec);
 
-        let rt = tokio::runtime::Handle::current();
         rt.block_on(async {
             // Proceed with post-startup configuration. Note, that order of operations is important.
             let client = Self::get_maintenance_client(&conf).await?;
@@ -942,48 +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
@@ -1051,7 +996,7 @@ impl ComputeNode {
                         jwks_roles.clone(),
                         concurrency_token.clone(),
                         db,
-                        [DropLogicalSubscriptions].to_vec(),
+                        [DropSubscriptionsForDeletedDatabases].to_vec(),
                     );
 
                     Ok(spawn(fut))
@@ -1079,7 +1024,6 @@ impl ComputeNode {
                 CreateAndAlterRoles,
                 RenameAndDeleteDatabases,
                 CreateAndAlterDatabases,
-                CreateSchemaNeon,
             ] {
                 info!("Applying phase {:?}", &phase);
                 apply_operations(
@@ -1120,17 +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,
@@ -1138,7 +1071,12 @@ impl ComputeNode {
                         jwks_roles.clone(),
                         concurrency_token.clone(),
                         db,
-                        phases,
+                        [
+                            DeleteDBRoleReferences,
+                            ChangeSchemaPerms,
+                            HandleAnonExtension,
+                        ]
+                        .to_vec(),
                     );
 
                     Ok(spawn(fut))
@@ -1150,20 +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(),
@@ -1323,18 +1253,14 @@ impl ComputeNode {
         }
 
         // Run migrations separately to not hold up cold starts
-        tokio::spawn(async move {
-            let mut conf = conf.as_ref().clone();
+        thread::spawn(move || {
+            let conf = conf.as_ref().clone();
+            let mut conf = postgres::config::Config::from(conf);
             conf.application_name("compute_ctl:migrations");
 
-            match conf.connect(NoTls).await {
-                Ok((mut client, connection)) => {
-                    tokio::spawn(async move {
-                        if let Err(e) = connection.await {
-                            eprintln!("connection error: {}", e);
-                        }
-                    });
-                    if let Err(e) = handle_migrations(&mut client).await {
+            match conf.connect(NoTls) {
+                Ok(mut client) => {
+                    if let Err(e) = handle_migrations(&mut client) {
                         error!("Failed to run migrations: {}", e);
                     }
                 }
@@ -1371,11 +1297,16 @@ impl ComputeNode {
         if let Some(ref pgbouncer_settings) = spec.pgbouncer_settings {
             info!("tuning pgbouncer");
 
-            // Spawn a background task to do the tuning,
+            let rt = tokio::runtime::Builder::new_current_thread()
+                .enable_all()
+                .build()
+                .expect("failed to create rt");
+
+            // Spawn a thread to do the tuning,
             // so that we don't block the main thread that starts Postgres.
             let pgbouncer_settings = pgbouncer_settings.clone();
-            tokio::spawn(async move {
-                let res = tune_pgbouncer(pgbouncer_settings).await;
+            let _handle = thread::spawn(move || {
+                let res = rt.block_on(tune_pgbouncer(pgbouncer_settings));
                 if let Err(err) = res {
                     error!("error while tuning pgbouncer: {err:?}");
                 }
@@ -1385,42 +1316,41 @@ impl ComputeNode {
         if let Some(ref local_proxy) = spec.local_proxy_config {
             info!("configuring local_proxy");
 
-            // Spawn a background task to do the configuration,
+            // Spawn a thread to do the configuration,
             // so that we don't block the main thread that starts Postgres.
             let local_proxy = local_proxy.clone();
-            tokio::spawn(async move {
+            let _handle = Some(thread::spawn(move || {
                 if let Err(err) = local_proxy::configure(&local_proxy) {
                     error!("error while configuring local_proxy: {err:?}");
                 }
-            });
+            }));
         }
 
         // Write new config
         let pgdata_path = Path::new(&self.pgdata);
         let postgresql_conf_path = pgdata_path.join("postgresql.conf");
-        config::write_postgres_conf(&postgresql_conf_path, &spec, self.internal_http_port)?;
+        config::write_postgres_conf(&postgresql_conf_path, &spec, self.http_port)?;
 
-        if !spec.skip_pg_catalog_updates {
-            let max_concurrent_connections = spec.reconfigure_concurrency;
-            // Temporarily reset max_cluster_size in config
-            // to avoid the possibility of hitting the limit, while we are reconfiguring:
-            // creating new extensions, roles, etc.
-            config::with_compute_ctl_tmp_override(pgdata_path, "neon.max_cluster_size=-1", || {
-                self.pg_reload_conf()?;
+        let max_concurrent_connections = spec.reconfigure_concurrency;
 
-                if spec.mode == ComputeMode::Primary {
-                    let mut conf = tokio_postgres::Config::from_str(self.connstr.as_str()).unwrap();
-                    conf.application_name("apply_config");
-                    let conf = Arc::new(conf);
+        // Temporarily reset max_cluster_size in config
+        // to avoid the possibility of hitting the limit, while we are reconfiguring:
+        // creating new extensions, roles, etc.
+        config::with_compute_ctl_tmp_override(pgdata_path, "neon.max_cluster_size=-1", || {
+            self.pg_reload_conf()?;
 
-                    let spec = Arc::new(spec.clone());
+            if spec.mode == ComputeMode::Primary {
+                let mut conf = tokio_postgres::Config::from_str(self.connstr.as_str()).unwrap();
+                conf.application_name("apply_config");
+                let conf = Arc::new(conf);
 
-                    self.apply_spec_sql(spec, conf, max_concurrent_connections)?;
-                }
+                let spec = Arc::new(spec.clone());
 
-                Ok(())
-            })?;
-        }
+                self.apply_spec_sql(spec, conf, max_concurrent_connections)?;
+            }
+
+            Ok(())
+        })?;
 
         self.pg_reload_conf()?;
 
@@ -1435,9 +1365,7 @@ impl ComputeNode {
     }
 
     #[instrument(skip_all)]
-    pub fn start_compute(
-        &self,
-    ) -> Result<(std::process::Child, tokio::task::JoinHandle<Result<()>>)> {
+    pub fn start_compute(&self) -> Result<(std::process::Child, std::thread::JoinHandle<()>)> {
         let compute_state = self.state.lock().unwrap().clone();
         let pspec = compute_state.pspec.as_ref().expect("spec must be set");
         info!(
@@ -1452,11 +1380,16 @@ impl ComputeNode {
         if let Some(pgbouncer_settings) = &pspec.spec.pgbouncer_settings {
             info!("tuning pgbouncer");
 
-            // Spawn a background task to do the tuning,
+            let rt = tokio::runtime::Builder::new_current_thread()
+                .enable_all()
+                .build()
+                .expect("failed to create rt");
+
+            // Spawn a thread to do the tuning,
             // so that we don't block the main thread that starts Postgres.
             let pgbouncer_settings = pgbouncer_settings.clone();
-            let _handle = tokio::spawn(async move {
-                let res = tune_pgbouncer(pgbouncer_settings).await;
+            let _handle = thread::spawn(move || {
+                let res = rt.block_on(tune_pgbouncer(pgbouncer_settings));
                 if let Err(err) = res {
                     error!("error while tuning pgbouncer: {err:?}");
                 }
@@ -1466,10 +1399,10 @@ impl ComputeNode {
         if let Some(local_proxy) = &pspec.spec.local_proxy_config {
             info!("configuring local_proxy");
 
-            // Spawn a background task to do the configuration,
+            // Spawn a thread to do the configuration,
             // so that we don't block the main thread that starts Postgres.
             let local_proxy = local_proxy.clone();
-            let _handle = tokio::spawn(async move {
+            let _handle = thread::spawn(move || {
                 if let Err(err) = local_proxy::configure(&local_proxy) {
                     error!("error while configuring local_proxy: {err:?}");
                 }
@@ -1488,8 +1421,7 @@ impl ComputeNode {
             extension_server::create_control_files(remote_extensions, &self.pgbin);
 
             let library_load_start_time = Utc::now();
-            let rt = tokio::runtime::Handle::current();
-            let remote_ext_metrics = rt.block_on(self.prepare_preload_libraries(&pspec.spec))?;
+            let remote_ext_metrics = self.prepare_preload_libraries(&pspec.spec)?;
 
             let library_load_time = Utc::now()
                 .signed_duration_since(library_load_start_time)
@@ -1531,20 +1463,12 @@ 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()?;
 
             let conf = self.get_conn_conf(None);
-            tokio::task::spawn_blocking(|| {
+            thread::spawn(move || {
                 let res = get_installed_extensions(conf);
                 match res {
                     Ok(extensions) => {
@@ -1893,6 +1817,7 @@ LIMIT 100",
         Ok(ext_version)
     }
 
+    #[tokio::main]
     pub async fn prepare_preload_libraries(
         &self,
         spec: &ComputeSpec,

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/configurator.rs

@@ -51,12 +51,9 @@ fn configurator_main_loop(compute: &Arc<ComputeNode>) {
 pub fn launch_configurator(compute: &Arc<ComputeNode>) -> thread::JoinHandle<()> {
     let compute = Arc::clone(compute);
 
-    let runtime = tokio::runtime::Handle::current();
-
     thread::Builder::new()
         .name("compute-configurator".into())
         .spawn(move || {
-            let _rt_guard = runtime.enter();
             configurator_main_loop(&compute);
             info!("configurator thread is exited");
         })

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/api.rs

@@ -0,0 +1,606 @@
+use std::convert::Infallible;
+use std::net::IpAddr;
+use std::net::Ipv6Addr;
+use std::net::SocketAddr;
+use std::sync::Arc;
+use std::thread;
+
+use crate::catalog::SchemaDumpError;
+use crate::catalog::{get_database_schema, get_dbs_and_roles};
+use crate::compute::forward_termination_signal;
+use crate::compute::{ComputeNode, ComputeState, ParsedSpec};
+use crate::installed_extensions;
+use compute_api::requests::{ConfigurationRequest, ExtensionInstallRequest, SetRoleGrantsRequest};
+use compute_api::responses::{
+    ComputeStatus, ComputeStatusResponse, ExtensionInstallResult, GenericAPIError,
+    SetRoleGrantsResponse,
+};
+
+use anyhow::Result;
+use hyper::header::CONTENT_TYPE;
+use hyper::service::{make_service_fn, service_fn};
+use hyper::{Body, Method, Request, Response, Server, StatusCode};
+use metrics::proto::MetricFamily;
+use metrics::Encoder;
+use metrics::TextEncoder;
+use tokio::task;
+use tokio_util::sync::CancellationToken;
+use tracing::{debug, error, info, warn};
+use tracing_utils::http::OtelName;
+use utils::failpoint_support::failpoints_handler;
+use utils::http::error::ApiError;
+use utils::http::request::must_get_query_param;
+
+fn status_response_from_state(state: &ComputeState) -> ComputeStatusResponse {
+    ComputeStatusResponse {
+        start_time: state.start_time,
+        tenant: state
+            .pspec
+            .as_ref()
+            .map(|pspec| pspec.tenant_id.to_string()),
+        timeline: state
+            .pspec
+            .as_ref()
+            .map(|pspec| pspec.timeline_id.to_string()),
+        status: state.status,
+        last_active: state.last_active,
+        error: state.error.clone(),
+    }
+}
+
+// Service function to handle all available routes.
+async fn routes(req: Request<Body>, compute: &Arc<ComputeNode>) -> Response<Body> {
+    //
+    // NOTE: The URI path is currently included in traces. That's OK because
+    // it doesn't contain any variable parts or sensitive information. But
+    // please keep that in mind if you change the routing here.
+    //
+    match (req.method(), req.uri().path()) {
+        // Serialized compute state.
+        (&Method::GET, "/status") => {
+            debug!("serving /status GET request");
+            let state = compute.state.lock().unwrap();
+            let status_response = status_response_from_state(&state);
+            Response::new(Body::from(serde_json::to_string(&status_response).unwrap()))
+        }
+
+        // Startup metrics in JSON format. Keep /metrics reserved for a possible
+        // future use for Prometheus metrics format.
+        (&Method::GET, "/metrics.json") => {
+            info!("serving /metrics.json GET request");
+            let metrics = compute.state.lock().unwrap().metrics.clone();
+            Response::new(Body::from(serde_json::to_string(&metrics).unwrap()))
+        }
+
+        // Prometheus metrics
+        (&Method::GET, "/metrics") => {
+            debug!("serving /metrics GET request");
+
+            // 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 = installed_extensions::collect()
+                .into_iter()
+                .filter(|m| !m.get_metric().is_empty())
+                .collect::<Vec<MetricFamily>>();
+
+            let encoder = TextEncoder::new();
+            let mut buffer = vec![];
+
+            if let Err(err) = encoder.encode(&metrics, &mut buffer) {
+                let msg = format!("error handling /metrics request: {err}");
+                error!(msg);
+                return render_json_error(&msg, StatusCode::INTERNAL_SERVER_ERROR);
+            }
+
+            match Response::builder()
+                .status(StatusCode::OK)
+                .header(CONTENT_TYPE, encoder.format_type())
+                .body(Body::from(buffer))
+            {
+                Ok(response) => response,
+                Err(err) => {
+                    let msg = format!("error handling /metrics request: {err}");
+                    error!(msg);
+                    render_json_error(&msg, StatusCode::INTERNAL_SERVER_ERROR)
+                }
+            }
+        }
+        // Collect Postgres current usage insights
+        (&Method::GET, "/insights") => {
+            info!("serving /insights GET request");
+            let status = compute.get_status();
+            if status != ComputeStatus::Running {
+                let msg = format!("compute is not running, current status: {:?}", status);
+                error!(msg);
+                return Response::new(Body::from(msg));
+            }
+
+            let insights = compute.collect_insights().await;
+            Response::new(Body::from(insights))
+        }
+
+        (&Method::POST, "/check_writability") => {
+            info!("serving /check_writability POST request");
+            let status = compute.get_status();
+            if status != ComputeStatus::Running {
+                let msg = format!(
+                    "invalid compute status for check_writability request: {:?}",
+                    status
+                );
+                error!(msg);
+                return Response::new(Body::from(msg));
+            }
+
+            let res = crate::checker::check_writability(compute).await;
+            match res {
+                Ok(_) => Response::new(Body::from("true")),
+                Err(e) => {
+                    error!("check_writability failed: {}", e);
+                    Response::new(Body::from(e.to_string()))
+                }
+            }
+        }
+
+        (&Method::POST, "/extensions") => {
+            info!("serving /extensions POST request");
+            let status = compute.get_status();
+            if status != ComputeStatus::Running {
+                let msg = format!(
+                    "invalid compute status for extensions request: {:?}",
+                    status
+                );
+                error!(msg);
+                return render_json_error(&msg, StatusCode::PRECONDITION_FAILED);
+            }
+
+            let request = hyper::body::to_bytes(req.into_body()).await.unwrap();
+            let request = serde_json::from_slice::<ExtensionInstallRequest>(&request).unwrap();
+            let res = compute
+                .install_extension(&request.extension, &request.database, request.version)
+                .await;
+            match res {
+                Ok(version) => render_json(Body::from(
+                    serde_json::to_string(&ExtensionInstallResult {
+                        extension: request.extension,
+                        version,
+                    })
+                    .unwrap(),
+                )),
+                Err(e) => {
+                    error!("install_extension failed: {}", e);
+                    render_json_error(&e.to_string(), StatusCode::INTERNAL_SERVER_ERROR)
+                }
+            }
+        }
+
+        (&Method::GET, "/info") => {
+            let num_cpus = num_cpus::get_physical();
+            info!("serving /info GET request. num_cpus: {}", num_cpus);
+            Response::new(Body::from(
+                serde_json::json!({
+                    "num_cpus": num_cpus,
+                })
+                .to_string(),
+            ))
+        }
+
+        // Accept spec in JSON format and request compute configuration. If
+        // anything goes wrong after we set the compute status to `ConfigurationPending`
+        // and update compute state with new spec, we basically leave compute
+        // in the potentially wrong state. That said, it's control-plane's
+        // responsibility to watch compute state after reconfiguration request
+        // and to clean restart in case of errors.
+        (&Method::POST, "/configure") => {
+            info!("serving /configure POST request");
+            match handle_configure_request(req, compute).await {
+                Ok(msg) => Response::new(Body::from(msg)),
+                Err((msg, code)) => {
+                    error!("error handling /configure request: {msg}");
+                    render_json_error(&msg, code)
+                }
+            }
+        }
+
+        (&Method::POST, "/terminate") => {
+            info!("serving /terminate POST request");
+            match handle_terminate_request(compute).await {
+                Ok(()) => Response::new(Body::empty()),
+                Err((msg, code)) => {
+                    error!("error handling /terminate request: {msg}");
+                    render_json_error(&msg, code)
+                }
+            }
+        }
+
+        (&Method::GET, "/dbs_and_roles") => {
+            info!("serving /dbs_and_roles GET request",);
+            match get_dbs_and_roles(compute).await {
+                Ok(res) => render_json(Body::from(serde_json::to_string(&res).unwrap())),
+                Err(_) => {
+                    render_json_error("can't get dbs and roles", StatusCode::INTERNAL_SERVER_ERROR)
+                }
+            }
+        }
+
+        (&Method::GET, "/database_schema") => {
+            let database = match must_get_query_param(&req, "database") {
+                Err(e) => return e.into_response(),
+                Ok(database) => database,
+            };
+            info!("serving /database_schema GET request with database: {database}",);
+            match get_database_schema(compute, &database).await {
+                Ok(res) => render_plain(Body::wrap_stream(res)),
+                Err(SchemaDumpError::DatabaseDoesNotExist) => {
+                    render_json_error("database does not exist", StatusCode::NOT_FOUND)
+                }
+                Err(e) => {
+                    error!("can't get schema dump: {}", e);
+                    render_json_error("can't get schema dump", StatusCode::INTERNAL_SERVER_ERROR)
+                }
+            }
+        }
+
+        (&Method::POST, "/grants") => {
+            info!("serving /grants POST request");
+            let status = compute.get_status();
+            if status != ComputeStatus::Running {
+                let msg = format!(
+                    "invalid compute status for set_role_grants request: {:?}",
+                    status
+                );
+                error!(msg);
+                return render_json_error(&msg, StatusCode::PRECONDITION_FAILED);
+            }
+
+            let request = hyper::body::to_bytes(req.into_body()).await.unwrap();
+            let request = serde_json::from_slice::<SetRoleGrantsRequest>(&request).unwrap();
+
+            let res = compute
+                .set_role_grants(
+                    &request.database,
+                    &request.schema,
+                    &request.privileges,
+                    &request.role,
+                )
+                .await;
+            match res {
+                Ok(()) => render_json(Body::from(
+                    serde_json::to_string(&SetRoleGrantsResponse {
+                        database: request.database,
+                        schema: request.schema,
+                        role: request.role,
+                        privileges: request.privileges,
+                    })
+                    .unwrap(),
+                )),
+                Err(e) => render_json_error(
+                    &format!("could not grant role privileges to the schema: {e}"),
+                    // TODO: can we filter on role/schema not found errors
+                    // and return appropriate error code?
+                    StatusCode::INTERNAL_SERVER_ERROR,
+                ),
+            }
+        }
+
+        // get the list of installed extensions
+        // currently only used in python tests
+        // TODO: call it from cplane
+        (&Method::GET, "/installed_extensions") => {
+            info!("serving /installed_extensions GET request");
+            let status = compute.get_status();
+            if status != ComputeStatus::Running {
+                let msg = format!(
+                    "invalid compute status for extensions request: {:?}",
+                    status
+                );
+                error!(msg);
+                return Response::new(Body::from(msg));
+            }
+
+            let conf = compute.get_conn_conf(None);
+            let res =
+                task::spawn_blocking(move || installed_extensions::get_installed_extensions(conf))
+                    .await
+                    .unwrap();
+
+            match res {
+                Ok(res) => render_json(Body::from(serde_json::to_string(&res).unwrap())),
+                Err(e) => render_json_error(
+                    &format!("could not get list of installed extensions: {}", e),
+                    StatusCode::INTERNAL_SERVER_ERROR,
+                ),
+            }
+        }
+
+        (&Method::POST, "/failpoints") if cfg!(feature = "testing") => {
+            match failpoints_handler(req, CancellationToken::new()).await {
+                Ok(r) => r,
+                Err(ApiError::BadRequest(e)) => {
+                    render_json_error(&e.to_string(), StatusCode::BAD_REQUEST)
+                }
+                Err(_) => {
+                    render_json_error("Internal server error", StatusCode::INTERNAL_SERVER_ERROR)
+                }
+            }
+        }
+
+        // download extension files from remote extension storage on demand
+        (&Method::POST, route) if route.starts_with("/extension_server/") => {
+            info!("serving {:?} POST request", route);
+            info!("req.uri {:?}", req.uri());
+
+            // don't even try to download extensions
+            // if no remote storage is configured
+            if compute.ext_remote_storage.is_none() {
+                info!("no extensions remote storage configured");
+                let mut resp = Response::new(Body::from("no remote storage configured"));
+                *resp.status_mut() = StatusCode::INTERNAL_SERVER_ERROR;
+                return resp;
+            }
+
+            let mut is_library = false;
+            if let Some(params) = req.uri().query() {
+                info!("serving {:?} POST request with params: {}", route, params);
+                if params == "is_library=true" {
+                    is_library = true;
+                } else {
+                    let mut resp = Response::new(Body::from("Wrong request parameters"));
+                    *resp.status_mut() = StatusCode::BAD_REQUEST;
+                    return resp;
+                }
+            }
+            let filename = route.split('/').last().unwrap().to_string();
+            info!("serving /extension_server POST request, filename: {filename:?} is_library: {is_library}");
+
+            // get ext_name and path from spec
+            // don't lock compute_state for too long
+            let ext = {
+                let compute_state = compute.state.lock().unwrap();
+                let pspec = compute_state.pspec.as_ref().expect("spec must be set");
+                let spec = &pspec.spec;
+
+                // debug only
+                info!("spec: {:?}", spec);
+
+                let remote_extensions = match spec.remote_extensions.as_ref() {
+                    Some(r) => r,
+                    None => {
+                        info!("no remote extensions spec was provided");
+                        let mut resp = Response::new(Body::from("no remote storage configured"));
+                        *resp.status_mut() = StatusCode::INTERNAL_SERVER_ERROR;
+                        return resp;
+                    }
+                };
+
+                remote_extensions.get_ext(
+                    &filename,
+                    is_library,
+                    &compute.build_tag,
+                    &compute.pgversion,
+                )
+            };
+
+            match ext {
+                Ok((ext_name, ext_path)) => {
+                    match compute.download_extension(ext_name, ext_path).await {
+                        Ok(_) => Response::new(Body::from("OK")),
+                        Err(e) => {
+                            error!("extension download failed: {}", e);
+                            let mut resp = Response::new(Body::from(e.to_string()));
+                            *resp.status_mut() = StatusCode::INTERNAL_SERVER_ERROR;
+                            resp
+                        }
+                    }
+                }
+                Err(e) => {
+                    warn!("extension download failed to find extension: {}", e);
+                    let mut resp = Response::new(Body::from("failed to find file"));
+                    *resp.status_mut() = StatusCode::INTERNAL_SERVER_ERROR;
+                    resp
+                }
+            }
+        }
+
+        // Return the `404 Not Found` for any other routes.
+        _ => {
+            let mut not_found = Response::new(Body::from("404 Not Found"));
+            *not_found.status_mut() = StatusCode::NOT_FOUND;
+            not_found
+        }
+    }
+}
+
+async fn handle_configure_request(
+    req: Request<Body>,
+    compute: &Arc<ComputeNode>,
+) -> Result<String, (String, StatusCode)> {
+    if !compute.live_config_allowed {
+        return Err((
+            "live configuration is not allowed for this compute node".to_string(),
+            StatusCode::PRECONDITION_FAILED,
+        ));
+    }
+
+    let body_bytes = hyper::body::to_bytes(req.into_body()).await.unwrap();
+    let spec_raw = String::from_utf8(body_bytes.to_vec()).unwrap();
+    if let Ok(request) = serde_json::from_str::<ConfigurationRequest>(&spec_raw) {
+        let spec = request.spec;
+
+        let parsed_spec = match ParsedSpec::try_from(spec) {
+            Ok(ps) => ps,
+            Err(msg) => return Err((msg, StatusCode::BAD_REQUEST)),
+        };
+
+        // XXX: wrap state update under lock in code blocks. Otherwise,
+        // we will try to `Send` `mut state` into the spawned thread
+        // bellow, which will cause error:
+        // ```
+        // error: future cannot be sent between threads safely
+        // ```
+        {
+            let mut state = compute.state.lock().unwrap();
+            if state.status != ComputeStatus::Empty && state.status != ComputeStatus::Running {
+                let msg = format!(
+                    "invalid compute status for configuration request: {:?}",
+                    state.status.clone()
+                );
+                return Err((msg, StatusCode::PRECONDITION_FAILED));
+            }
+            state.pspec = Some(parsed_spec);
+            state.set_status(ComputeStatus::ConfigurationPending, &compute.state_changed);
+            drop(state);
+            info!("set new spec and notified waiters");
+        }
+
+        // Spawn a blocking thread to wait for compute to become Running.
+        // This is needed to do not block the main pool of workers and
+        // be able to serve other requests while some particular request
+        // is waiting for compute to finish configuration.
+        let c = compute.clone();
+        task::spawn_blocking(move || {
+            let mut state = c.state.lock().unwrap();
+            while state.status != ComputeStatus::Running {
+                state = c.state_changed.wait(state).unwrap();
+                info!(
+                    "waiting for compute to become Running, current status: {:?}",
+                    state.status
+                );
+
+                if state.status == ComputeStatus::Failed {
+                    let err = state.error.as_ref().map_or("unknown error", |x| x);
+                    let msg = format!("compute configuration failed: {:?}", err);
+                    return Err((msg, StatusCode::INTERNAL_SERVER_ERROR));
+                }
+            }
+
+            Ok(())
+        })
+        .await
+        .unwrap()?;
+
+        // Return current compute state if everything went well.
+        let state = compute.state.lock().unwrap().clone();
+        let status_response = status_response_from_state(&state);
+        Ok(serde_json::to_string(&status_response).unwrap())
+    } else {
+        Err(("invalid spec".to_string(), StatusCode::BAD_REQUEST))
+    }
+}
+
+fn render_json_error(e: &str, status: StatusCode) -> Response<Body> {
+    let error = GenericAPIError {
+        error: e.to_string(),
+    };
+    Response::builder()
+        .status(status)
+        .header(CONTENT_TYPE, "application/json")
+        .body(Body::from(serde_json::to_string(&error).unwrap()))
+        .unwrap()
+}
+
+fn render_json(body: Body) -> Response<Body> {
+    Response::builder()
+        .header(CONTENT_TYPE, "application/json")
+        .body(body)
+        .unwrap()
+}
+
+fn render_plain(body: Body) -> Response<Body> {
+    Response::builder()
+        .header(CONTENT_TYPE, "text/plain")
+        .body(body)
+        .unwrap()
+}
+
+async fn handle_terminate_request(compute: &Arc<ComputeNode>) -> Result<(), (String, StatusCode)> {
+    {
+        let mut state = compute.state.lock().unwrap();
+        if state.status == ComputeStatus::Terminated {
+            return Ok(());
+        }
+        if state.status != ComputeStatus::Empty && state.status != ComputeStatus::Running {
+            let msg = format!(
+                "invalid compute status for termination request: {}",
+                state.status
+            );
+            return Err((msg, StatusCode::PRECONDITION_FAILED));
+        }
+        state.set_status(ComputeStatus::TerminationPending, &compute.state_changed);
+        drop(state);
+    }
+
+    forward_termination_signal();
+    info!("sent signal and notified waiters");
+
+    // Spawn a blocking thread to wait for compute to become Terminated.
+    // This is needed to do not block the main pool of workers and
+    // be able to serve other requests while some particular request
+    // is waiting for compute to finish configuration.
+    let c = compute.clone();
+    task::spawn_blocking(move || {
+        let mut state = c.state.lock().unwrap();
+        while state.status != ComputeStatus::Terminated {
+            state = c.state_changed.wait(state).unwrap();
+            info!(
+                "waiting for compute to become {}, current status: {:?}",
+                ComputeStatus::Terminated,
+                state.status
+            );
+        }
+
+        Ok(())
+    })
+    .await
+    .unwrap()?;
+    info!("terminated Postgres");
+    Ok(())
+}
+
+// Main Hyper HTTP server function that runs it and blocks waiting on it forever.
+#[tokio::main]
+async fn serve(port: u16, state: Arc<ComputeNode>) {
+    // this usually binds to both IPv4 and IPv6 on linux
+    // see e.g. https://github.com/rust-lang/rust/pull/34440
+    let addr = SocketAddr::new(IpAddr::from(Ipv6Addr::UNSPECIFIED), port);
+
+    let make_service = make_service_fn(move |_conn| {
+        let state = state.clone();
+        async move {
+            Ok::<_, Infallible>(service_fn(move |req: Request<Body>| {
+                let state = state.clone();
+                async move {
+                    Ok::<_, Infallible>(
+                        // NOTE: We include the URI path in the string. It
+                        // doesn't contain any variable parts or sensitive
+                        // information in this API.
+                        tracing_utils::http::tracing_handler(
+                            req,
+                            |req| routes(req, &state),
+                            OtelName::UriPath,
+                        )
+                        .await,
+                    )
+                }
+            }))
+        }
+    });
+
+    info!("starting HTTP server on {}", addr);
+
+    let server = Server::bind(&addr).serve(make_service);
+
+    // Run this server forever
+    if let Err(e) = server.await {
+        error!("server error: {}", e);
+    }
+}
+
+/// Launch a separate Hyper HTTP API server thread and return its `JoinHandle`.
+pub fn launch_http_server(port: u16, state: &Arc<ComputeNode>) -> Result<thread::JoinHandle<()>> {
+    let state = Arc::clone(state);
+
+    Ok(thread::Builder::new()
+        .name("http-endpoint".into())
+        .spawn(move || serve(port, state))?)
+}

compute_tools/src/http/extract/json.rs

@@ -1,44 +0,0 @@
-use std::ops::{Deref, DerefMut};
-
-use axum::extract::{rejection::JsonRejection, FromRequest, Request};
-use compute_api::responses::GenericAPIError;
-use http::StatusCode;
-
-/// Custom `Json` extractor, so that we can format errors into
-/// `JsonResponse<GenericAPIError>`.
-#[derive(Debug, Clone, Copy, Default)]
-pub(crate) struct Json<T>(pub T);
-
-impl<S, T> FromRequest<S> for Json<T>
-where
-    axum::Json<T>: FromRequest<S, Rejection = JsonRejection>,
-    S: Send + Sync,
-{
-    type Rejection = (StatusCode, axum::Json<GenericAPIError>);
-
-    async fn from_request(req: Request, state: &S) -> Result<Self, Self::Rejection> {
-        match axum::Json::<T>::from_request(req, state).await {
-            Ok(value) => Ok(Self(value.0)),
-            Err(rejection) => Err((
-                rejection.status(),
-                axum::Json(GenericAPIError {
-                    error: rejection.body_text().to_lowercase(),
-                }),
-            )),
-        }
-    }
-}
-
-impl<T> Deref for Json<T> {
-    type Target = T;
-
-    fn deref(&self) -> &Self::Target {
-        &self.0
-    }
-}
-
-impl<T> DerefMut for Json<T> {
-    fn deref_mut(&mut self) -> &mut Self::Target {
-        &mut self.0
-    }
-}

compute_tools/src/http/extract/mod.rs

@@ -1,7 +0,0 @@
-pub(crate) mod json;
-pub(crate) mod path;
-pub(crate) mod query;
-
-pub(crate) use json::Json;
-pub(crate) use path::Path;
-pub(crate) use query::Query;

compute_tools/src/http/extract/path.rs

@@ -1,44 +0,0 @@
-use std::ops::{Deref, DerefMut};
-
-use axum::extract::{rejection::PathRejection, FromRequestParts};
-use compute_api::responses::GenericAPIError;
-use http::{request::Parts, StatusCode};
-
-/// Custom `Path` extractor, so that we can format errors into
-/// `JsonResponse<GenericAPIError>`.
-#[derive(Debug, Clone, Copy, Default)]
-pub(crate) struct Path<T>(pub T);
-
-impl<S, T> FromRequestParts<S> for Path<T>
-where
-    axum::extract::Path<T>: FromRequestParts<S, Rejection = PathRejection>,
-    S: Send + Sync,
-{
-    type Rejection = (StatusCode, axum::Json<GenericAPIError>);
-
-    async fn from_request_parts(parts: &mut Parts, state: &S) -> Result<Self, Self::Rejection> {
-        match axum::extract::Path::<T>::from_request_parts(parts, state).await {
-            Ok(value) => Ok(Self(value.0)),
-            Err(rejection) => Err((
-                rejection.status(),
-                axum::Json(GenericAPIError {
-                    error: rejection.body_text().to_ascii_lowercase(),
-                }),
-            )),
-        }
-    }
-}
-
-impl<T> Deref for Path<T> {
-    type Target = T;
-
-    fn deref(&self) -> &Self::Target {
-        &self.0
-    }
-}
-
-impl<T> DerefMut for Path<T> {
-    fn deref_mut(&mut self) -> &mut Self::Target {
-        &mut self.0
-    }
-}

compute_tools/src/http/extract/query.rs

@@ -1,44 +0,0 @@
-use std::ops::{Deref, DerefMut};
-
-use axum::extract::{rejection::QueryRejection, FromRequestParts};
-use compute_api::responses::GenericAPIError;
-use http::{request::Parts, StatusCode};
-
-/// Custom `Query` extractor, so that we can format errors into
-/// `JsonResponse<GenericAPIError>`.
-#[derive(Debug, Clone, Copy, Default)]
-pub(crate) struct Query<T>(pub T);
-
-impl<S, T> FromRequestParts<S> for Query<T>
-where
-    axum::extract::Query<T>: FromRequestParts<S, Rejection = QueryRejection>,
-    S: Send + Sync,
-{
-    type Rejection = (StatusCode, axum::Json<GenericAPIError>);
-
-    async fn from_request_parts(parts: &mut Parts, state: &S) -> Result<Self, Self::Rejection> {
-        match axum::extract::Query::<T>::from_request_parts(parts, state).await {
-            Ok(value) => Ok(Self(value.0)),
-            Err(rejection) => Err((
-                rejection.status(),
-                axum::Json(GenericAPIError {
-                    error: rejection.body_text().to_ascii_lowercase(),
-                }),
-            )),
-        }
-    }
-}
-
-impl<T> Deref for Query<T> {
-    type Target = T;
-
-    fn deref(&self) -> &Self::Target {
-        &self.0
-    }
-}
-
-impl<T> DerefMut for Query<T> {
-    fn deref_mut(&mut self) -> &mut Self::Target {
-        &mut self.0
-    }
-}

compute_tools/src/http/mod.rs

@@ -1,54 +1 @@
-use axum::{body::Body, response::Response};
-use compute_api::responses::{ComputeStatus, GenericAPIError};
-use http::{header::CONTENT_TYPE, StatusCode};
-use serde::Serialize;
-use tracing::error;
-
-mod extract;
-mod routes;
-pub mod server;
-
-/// Convenience response builder for JSON responses
-struct JsonResponse;
-
-impl JsonResponse {
-    /// Helper for actually creating a response
-    fn create_response(code: StatusCode, body: impl Serialize) -> Response {
-        Response::builder()
-            .status(code)
-            .header(CONTENT_TYPE.as_str(), "application/json")
-            .body(Body::from(serde_json::to_string(&body).unwrap()))
-            .unwrap()
-    }
-
-    /// Create a successful error response
-    pub(self) fn success(code: StatusCode, body: impl Serialize) -> Response {
-        assert!({
-            let code = code.as_u16();
-
-            (200..300).contains(&code)
-        });
-
-        Self::create_response(code, body)
-    }
-
-    /// Create an error response
-    pub(self) fn error(code: StatusCode, error: impl ToString) -> Response {
-        assert!(code.as_u16() >= 400);
-
-        let message = error.to_string();
-        error!(message);
-
-        Self::create_response(code, &GenericAPIError { error: message })
-    }
-
-    /// Create an error response related to the compute being in an invalid state
-    pub(self) fn invalid_status(status: ComputeStatus) -> Response {
-        Self::create_response(
-            StatusCode::PRECONDITION_FAILED,
-            &GenericAPIError {
-                error: format!("invalid compute status: {status}"),
-            },
-        )
-    }
-}
+pub mod api;

compute_tools/src/http/openapi_spec.yaml

@@ -37,7 +37,7 @@ paths:
               schema:
                 $ref: "#/components/schemas/ComputeMetrics"
 
-  /metrics:
+  /metrics
     get:
       tags:
       - Info
@@ -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/check_writability.rs

@@ -1,20 +0,0 @@
-use std::sync::Arc;
-
-use axum::{extract::State, response::Response};
-use compute_api::responses::ComputeStatus;
-use http::StatusCode;
-
-use crate::{checker::check_writability, compute::ComputeNode, http::JsonResponse};
-
-/// Check that the compute is currently running.
-pub(in crate::http) async fn is_writable(State(compute): State<Arc<ComputeNode>>) -> Response {
-    let status = compute.get_status();
-    if status != ComputeStatus::Running {
-        return JsonResponse::invalid_status(status);
-    }
-
-    match check_writability(&compute).await {
-        Ok(_) => JsonResponse::success(StatusCode::OK, true),
-        Err(e) => JsonResponse::error(StatusCode::INTERNAL_SERVER_ERROR, e),
-    }
-}

compute_tools/src/http/routes/configure.rs

@@ -1,91 +0,0 @@
-use std::sync::Arc;
-
-use axum::{extract::State, response::Response};
-use compute_api::{
-    requests::ConfigurationRequest,
-    responses::{ComputeStatus, ComputeStatusResponse},
-};
-use http::StatusCode;
-use tokio::task;
-use tracing::info;
-
-use crate::{
-    compute::{ComputeNode, ParsedSpec},
-    http::{extract::Json, JsonResponse},
-};
-
-// Accept spec in JSON format and request compute configuration. If anything
-// goes wrong after we set the compute status to `ConfigurationPending` and
-// update compute state with new spec, we basically leave compute in the
-// potentially wrong state. That said, it's control-plane's responsibility to
-// watch compute state after reconfiguration request and to clean restart in
-// case of errors.
-pub(in crate::http) async fn configure(
-    State(compute): State<Arc<ComputeNode>>,
-    request: Json<ConfigurationRequest>,
-) -> Response {
-    if !compute.live_config_allowed {
-        return JsonResponse::error(
-            StatusCode::PRECONDITION_FAILED,
-            "live configuration is not allowed for this compute node".to_string(),
-        );
-    }
-
-    let pspec = match ParsedSpec::try_from(request.spec.clone()) {
-        Ok(p) => p,
-        Err(e) => return JsonResponse::error(StatusCode::BAD_REQUEST, e),
-    };
-
-    // XXX: wrap state update under lock in a code block. Otherwise, we will try
-    // to `Send` `mut state` into the spawned thread bellow, which will cause
-    // the following rustc error:
-    //
-    // error: future cannot be sent between threads safely
-    {
-        let mut state = compute.state.lock().unwrap();
-        if !matches!(state.status, ComputeStatus::Empty | ComputeStatus::Running) {
-            return JsonResponse::invalid_status(state.status);
-        }
-
-        state.pspec = Some(pspec);
-        state.set_status(ComputeStatus::ConfigurationPending, &compute.state_changed);
-        drop(state);
-    }
-
-    // Spawn a blocking thread to wait for compute to become Running. This is
-    // needed to do not block the main pool of workers and be able to serve
-    // other requests while some particular request is waiting for compute to
-    // finish configuration.
-    let c = compute.clone();
-    let completed = task::spawn_blocking(move || {
-        let mut state = c.state.lock().unwrap();
-        while state.status != ComputeStatus::Running {
-            state = c.state_changed.wait(state).unwrap();
-            info!(
-                "waiting for compute to become {}, current status: {}",
-                ComputeStatus::Running,
-                state.status
-            );
-
-            if state.status == ComputeStatus::Failed {
-                let err = state.error.as_ref().map_or("unknown error", |x| x);
-                let msg = format!("compute configuration failed: {:?}", err);
-                return Err(msg);
-            }
-        }
-
-        Ok(())
-    })
-    .await
-    .unwrap();
-
-    if let Err(e) = completed {
-        return JsonResponse::error(StatusCode::INTERNAL_SERVER_ERROR, e);
-    }
-
-    // Return current compute state if everything went well.
-    let state = compute.state.lock().unwrap().clone();
-    let body = ComputeStatusResponse::from(&state);
-
-    JsonResponse::success(StatusCode::OK, body)
-}

compute_tools/src/http/routes/database_schema.rs

@@ -1,34 +0,0 @@
-use std::sync::Arc;
-
-use axum::{body::Body, extract::State, response::Response};
-use http::{header::CONTENT_TYPE, StatusCode};
-use serde::Deserialize;
-
-use crate::{
-    catalog::{get_database_schema, SchemaDumpError},
-    compute::ComputeNode,
-    http::{extract::Query, JsonResponse},
-};
-
-#[derive(Debug, Clone, Deserialize)]
-pub(in crate::http) struct DatabaseSchemaParams {
-    database: String,
-}
-
-/// Get a schema dump of the requested database.
-pub(in crate::http) async fn get_schema_dump(
-    params: Query<DatabaseSchemaParams>,
-    State(compute): State<Arc<ComputeNode>>,
-) -> Response {
-    match get_database_schema(&compute, &params.database).await {
-        Ok(schema) => Response::builder()
-            .status(StatusCode::OK)
-            .header(CONTENT_TYPE.as_str(), "application/json")
-            .body(Body::from_stream(schema))
-            .unwrap(),
-        Err(SchemaDumpError::DatabaseDoesNotExist) => {
-            JsonResponse::error(StatusCode::NOT_FOUND, SchemaDumpError::DatabaseDoesNotExist)
-        }
-        Err(e) => JsonResponse::error(StatusCode::INTERNAL_SERVER_ERROR, e),
-    }
-}

compute_tools/src/http/routes/dbs_and_roles.rs

@@ -1,16 +0,0 @@
-use std::sync::Arc;
-
-use axum::{extract::State, response::Response};
-use http::StatusCode;
-
-use crate::{catalog::get_dbs_and_roles, compute::ComputeNode, http::JsonResponse};
-
-/// Get the databases and roles from the compute.
-pub(in crate::http) async fn get_catalog_objects(
-    State(compute): State<Arc<ComputeNode>>,
-) -> Response {
-    match get_dbs_and_roles(&compute).await {
-        Ok(catalog_objects) => JsonResponse::success(StatusCode::OK, catalog_objects),
-        Err(e) => JsonResponse::error(StatusCode::INTERNAL_SERVER_ERROR, e),
-    }
-}

compute_tools/src/http/routes/extension_server.rs

@@ -1,68 +0,0 @@
-use std::sync::Arc;
-
-use axum::{
-    extract::State,
-    response::{IntoResponse, Response},
-};
-use http::StatusCode;
-use serde::Deserialize;
-
-use crate::{
-    compute::ComputeNode,
-    http::{
-        extract::{Path, Query},
-        JsonResponse,
-    },
-};
-
-#[derive(Debug, Clone, Deserialize)]
-pub(in crate::http) struct ExtensionServerParams {
-    #[serde(default)]
-    is_library: bool,
-}
-
-/// Download a remote extension.
-pub(in crate::http) async fn download_extension(
-    Path(filename): Path<String>,
-    params: Query<ExtensionServerParams>,
-    State(compute): State<Arc<ComputeNode>>,
-) -> Response {
-    // Don't even try to download extensions if no remote storage is configured
-    if compute.ext_remote_storage.is_none() {
-        return JsonResponse::error(
-            StatusCode::PRECONDITION_FAILED,
-            "remote storage is not configured",
-        );
-    }
-
-    let ext = {
-        let state = compute.state.lock().unwrap();
-        let pspec = state.pspec.as_ref().unwrap();
-        let spec = &pspec.spec;
-
-        let remote_extensions = match spec.remote_extensions.as_ref() {
-            Some(r) => r,
-            None => {
-                return JsonResponse::error(
-                    StatusCode::CONFLICT,
-                    "information about remote extensions is unavailable",
-                );
-            }
-        };
-
-        remote_extensions.get_ext(
-            &filename,
-            params.is_library,
-            &compute.build_tag,
-            &compute.pgversion,
-        )
-    };
-
-    match ext {
-        Ok((ext_name, ext_path)) => match compute.download_extension(ext_name, ext_path).await {
-            Ok(_) => StatusCode::OK.into_response(),
-            Err(e) => JsonResponse::error(StatusCode::INTERNAL_SERVER_ERROR, e),
-        },
-        Err(e) => JsonResponse::error(StatusCode::NOT_FOUND, e),
-    }
-}

compute_tools/src/http/routes/extensions.rs

@@ -1,45 +0,0 @@
-use std::sync::Arc;
-
-use axum::{extract::State, response::Response};
-use compute_api::{
-    requests::ExtensionInstallRequest,
-    responses::{ComputeStatus, ExtensionInstallResponse},
-};
-use http::StatusCode;
-
-use crate::{
-    compute::ComputeNode,
-    http::{extract::Json, JsonResponse},
-};
-
-/// Install a extension.
-pub(in crate::http) async fn install_extension(
-    State(compute): State<Arc<ComputeNode>>,
-    request: Json<ExtensionInstallRequest>,
-) -> Response {
-    let status = compute.get_status();
-    if status != ComputeStatus::Running {
-        return JsonResponse::invalid_status(status);
-    }
-
-    match compute
-        .install_extension(
-            &request.extension,
-            &request.database,
-            request.version.to_string(),
-        )
-        .await
-    {
-        Ok(version) => JsonResponse::success(
-            StatusCode::CREATED,
-            Some(ExtensionInstallResponse {
-                extension: request.extension.clone(),
-                version,
-            }),
-        ),
-        Err(e) => JsonResponse::error(
-            StatusCode::INTERNAL_SERVER_ERROR,
-            format!("failed to install extension: {e}"),
-        ),
-    }
-}

compute_tools/src/http/routes/failpoints.rs

@@ -1,49 +0,0 @@
-use axum::response::{IntoResponse, Response};
-use http::StatusCode;
-use serde::{Deserialize, Serialize};
-use tracing::info;
-use utils::failpoint_support::apply_failpoint;
-
-pub type ConfigureFailpointsRequest = Vec<FailpointConfig>;
-
-/// Information for configuring a single fail point
-#[derive(Debug, Serialize, Deserialize)]
-pub struct FailpointConfig {
-    /// Name of the fail point
-    pub name: String,
-    /// List of actions to take, using the format described in `fail::cfg`
-    ///
-    /// We also support `actions = "exit"` to cause the fail point to immediately exit.
-    pub actions: String,
-}
-
-use crate::http::{extract::Json, JsonResponse};
-
-/// Configure failpoints for testing purposes.
-pub(in crate::http) async fn configure_failpoints(
-    failpoints: Json<ConfigureFailpointsRequest>,
-) -> Response {
-    if !fail::has_failpoints() {
-        return JsonResponse::error(
-            StatusCode::PRECONDITION_FAILED,
-            "Cannot manage failpoints because neon was compiled without failpoints support",
-        );
-    }
-
-    for fp in &*failpoints {
-        info!("cfg failpoint: {} {}", fp.name, fp.actions);
-
-        // We recognize one extra "action" that's not natively recognized
-        // by the failpoints crate: exit, to immediately kill the process
-        let cfg_result = apply_failpoint(&fp.name, &fp.actions);
-
-        if let Err(e) = cfg_result {
-            return JsonResponse::error(
-                StatusCode::BAD_REQUEST,
-                format!("failed to configure failpoints: {e}"),
-            );
-        }
-    }
-
-    StatusCode::OK.into_response()
-}

compute_tools/src/http/routes/grants.rs

@@ -1,48 +0,0 @@
-use std::sync::Arc;
-
-use axum::{extract::State, response::Response};
-use compute_api::{
-    requests::SetRoleGrantsRequest,
-    responses::{ComputeStatus, SetRoleGrantsResponse},
-};
-use http::StatusCode;
-
-use crate::{
-    compute::ComputeNode,
-    http::{extract::Json, JsonResponse},
-};
-
-/// Add grants for a role.
-pub(in crate::http) async fn add_grant(
-    State(compute): State<Arc<ComputeNode>>,
-    request: Json<SetRoleGrantsRequest>,
-) -> Response {
-    let status = compute.get_status();
-    if status != ComputeStatus::Running {
-        return JsonResponse::invalid_status(status);
-    }
-
-    match compute
-        .set_role_grants(
-            &request.database,
-            &request.schema,
-            &request.privileges,
-            &request.role,
-        )
-        .await
-    {
-        Ok(()) => JsonResponse::success(
-            StatusCode::CREATED,
-            Some(SetRoleGrantsResponse {
-                database: request.database.clone(),
-                schema: request.schema.clone(),
-                role: request.role.clone(),
-                privileges: request.privileges.clone(),
-            }),
-        ),
-        Err(e) => JsonResponse::error(
-            StatusCode::INTERNAL_SERVER_ERROR,
-            format!("failed to grant role privileges to the schema: {e}"),
-        ),
-    }
-}

compute_tools/src/http/routes/insights.rs

@@ -1,18 +0,0 @@
-use std::sync::Arc;
-
-use axum::{extract::State, response::Response};
-use compute_api::responses::ComputeStatus;
-use http::StatusCode;
-
-use crate::{compute::ComputeNode, http::JsonResponse};
-
-/// Collect current Postgres usage insights.
-pub(in crate::http) async fn get_insights(State(compute): State<Arc<ComputeNode>>) -> Response {
-    let status = compute.get_status();
-    if status != ComputeStatus::Running {
-        return JsonResponse::invalid_status(status);
-    }
-
-    let insights = compute.collect_insights().await;
-    JsonResponse::success(StatusCode::OK, insights)
-}

compute_tools/src/http/routes/metrics.rs

@@ -1,31 +0,0 @@
-use axum::{body::Body, response::Response};
-use http::header::CONTENT_TYPE;
-use http::StatusCode;
-use metrics::proto::MetricFamily;
-use metrics::{Encoder, TextEncoder};
-
-use crate::{http::JsonResponse, metrics::collect};
-
-/// 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()
-        .into_iter()
-        .filter(|m| !m.get_metric().is_empty())
-        .collect::<Vec<MetricFamily>>();
-
-    let encoder = TextEncoder::new();
-    let mut buffer = vec![];
-
-    if let Err(e) = encoder.encode(&metrics, &mut buffer) {
-        return JsonResponse::error(StatusCode::INTERNAL_SERVER_ERROR, e);
-    }
-
-    Response::builder()
-        .status(StatusCode::OK)
-        .header(CONTENT_TYPE, encoder.format_type())
-        .body(Body::from(buffer))
-        .unwrap()
-}

compute_tools/src/http/routes/metrics_json.rs

@@ -1,12 +0,0 @@
-use std::sync::Arc;
-
-use axum::{extract::State, response::Response};
-use http::StatusCode;
-
-use crate::{compute::ComputeNode, http::JsonResponse};
-
-/// Get startup metrics.
-pub(in crate::http) async fn get_metrics(State(compute): State<Arc<ComputeNode>>) -> Response {
-    let metrics = compute.state.lock().unwrap().metrics.clone();
-    JsonResponse::success(StatusCode::OK, metrics)
-}

compute_tools/src/http/routes/mod.rs

@@ -1,36 +0,0 @@
-use compute_api::responses::ComputeStatusResponse;
-
-use crate::compute::ComputeState;
-
-pub(in crate::http) mod check_writability;
-pub(in crate::http) mod configure;
-pub(in crate::http) mod database_schema;
-pub(in crate::http) mod dbs_and_roles;
-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 insights;
-pub(in crate::http) mod metrics;
-pub(in crate::http) mod metrics_json;
-pub(in crate::http) mod status;
-pub(in crate::http) mod terminate;
-
-impl From<&ComputeState> for ComputeStatusResponse {
-    fn from(state: &ComputeState) -> Self {
-        ComputeStatusResponse {
-            start_time: state.start_time,
-            tenant: state
-                .pspec
-                .as_ref()
-                .map(|pspec| pspec.tenant_id.to_string()),
-            timeline: state
-                .pspec
-                .as_ref()
-                .map(|pspec| pspec.timeline_id.to_string()),
-            status: state.status,
-            last_active: state.last_active,
-            error: state.error.clone(),
-        }
-    }
-}

compute_tools/src/http/routes/status.rs

@@ -1,14 +0,0 @@
-use std::{ops::Deref, sync::Arc};
-
-use axum::{extract::State, http::StatusCode, response::Response};
-use compute_api::responses::ComputeStatusResponse;
-
-use crate::{compute::ComputeNode, http::JsonResponse};
-
-/// Retrieve the state of the comute.
-pub(in crate::http) async fn get_status(State(compute): State<Arc<ComputeNode>>) -> Response {
-    let state = compute.state.lock().unwrap();
-    let body = ComputeStatusResponse::from(state.deref());
-
-    JsonResponse::success(StatusCode::OK, body)
-}

compute_tools/src/http/routes/terminate.rs

@@ -1,58 +0,0 @@
-use std::sync::Arc;
-
-use axum::{
-    extract::State,
-    response::{IntoResponse, Response},
-};
-use compute_api::responses::ComputeStatus;
-use http::StatusCode;
-use tokio::task;
-use tracing::info;
-
-use crate::{
-    compute::{forward_termination_signal, ComputeNode},
-    http::JsonResponse,
-};
-
-/// Terminate the compute.
-pub(in crate::http) async fn terminate(State(compute): State<Arc<ComputeNode>>) -> Response {
-    {
-        let mut state = compute.state.lock().unwrap();
-        if state.status == ComputeStatus::Terminated {
-            return StatusCode::CREATED.into_response();
-        }
-
-        if !matches!(state.status, ComputeStatus::Empty | ComputeStatus::Running) {
-            return JsonResponse::invalid_status(state.status);
-        }
-
-        state.set_status(ComputeStatus::TerminationPending, &compute.state_changed);
-        drop(state);
-    }
-
-    forward_termination_signal();
-    info!("sent signal and notified waiters");
-
-    // Spawn a blocking thread to wait for compute to become Terminated.
-    // This is needed to do not block the main pool of workers and
-    // be able to serve other requests while some particular request
-    // is waiting for compute to finish configuration.
-    let c = compute.clone();
-    task::spawn_blocking(move || {
-        let mut state = c.state.lock().unwrap();
-        while state.status != ComputeStatus::Terminated {
-            state = c.state_changed.wait(state).unwrap();
-            info!(
-                "waiting for compute to become {}, current status: {:?}",
-                ComputeStatus::Terminated,
-                state.status
-            );
-        }
-    })
-    .await
-    .unwrap();
-
-    info!("terminated Postgres");
-
-    StatusCode::OK.into_response()
-}

compute_tools/src/http/server.rs

@@ -1,211 +0,0 @@
-use std::{
-    fmt::Display,
-    net::{IpAddr, Ipv6Addr, SocketAddr},
-    sync::Arc,
-    time::Duration,
-};
-
-use anyhow::Result;
-use axum::{
-    extract::Request,
-    middleware::{self, Next},
-    response::{IntoResponse, Response},
-    routing::{get, post},
-    Router,
-};
-use http::StatusCode;
-use tokio::net::TcpListener;
-use tower::ServiceBuilder;
-use tower_http::{request_id::PropagateRequestIdLayer, 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,
-};
-use crate::compute::ComputeNode;
-
-const X_REQUEST_ID: &str = "x-request-id";
-
-/// `compute_ctl` has two servers: internal and external. The internal server
-/// binds to the loopback interface and handles communication from clients on
-/// the compute. The external server is what receives communication from the
-/// control plane, the metrics scraper, etc. We make the distinction because
-/// certain routes in `compute_ctl` only need to be exposed to local processes
-/// like Postgres via the neon extension and local_proxy.
-#[derive(Clone, Copy, Debug)]
-pub enum Server {
-    Internal(u16),
-    External(u16),
-}
-
-impl Display for Server {
-    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
-        match self {
-            Server::Internal(_) => f.write_str("internal"),
-            Server::External(_) => f.write_str("external"),
-        }
-    }
-}
-
-impl From<Server> for Router<Arc<ComputeNode>> {
-    fn from(server: Server) -> Self {
-        let mut router = Router::<Arc<ComputeNode>>::new();
-
-        router = match server {
-            Server::Internal(_) => {
-                router = router
-                    .route(
-                        "/extension_server/{*filename}",
-                        post(extension_server::download_extension),
-                    )
-                    .route("/extensions", post(extensions::install_extension))
-                    .route("/grants", post(grants::add_grant));
-
-                // Add in any testing support
-                if cfg!(feature = "testing") {
-                    use super::routes::failpoints;
-
-                    router = router.route("/failpoints", post(failpoints::configure_failpoints));
-                }
-
-                router
-            }
-            Server::External(_) => router
-                .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("/insights", get(insights::get_insights))
-                .route("/metrics", get(metrics::get_metrics))
-                .route("/metrics.json", get(metrics_json::get_metrics))
-                .route("/status", get(status::get_status))
-                .route("/terminate", post(terminate::terminate)),
-        };
-
-        router.fallback(Server::handle_404).method_not_allowed_fallback(Server::handle_405).layer(
-            ServiceBuilder::new()
-                // Add this middleware since we assume the request ID exists
-                .layer(middleware::from_fn(maybe_add_request_id_header))
-                .layer(
-                    TraceLayer::new_for_http()
-                        .on_request(|request: &http::Request<_>, _span: &Span| {
-                            let request_id = request
-                                .headers()
-                                .get(X_REQUEST_ID)
-                                .unwrap()
-                                .to_str()
-                                .unwrap();
-
-                            match request.uri().path() {
-                                "/metrics" => {
-                                    debug!(%request_id, "{} {}", request.method(), request.uri())
-                                }
-                                _ => info!(%request_id, "{} {}", request.method(), request.uri()),
-                            };
-                        })
-                        .on_response(
-                            |response: &http::Response<_>, latency: Duration, _span: &Span| {
-                                let request_id = response
-                                    .headers()
-                                    .get(X_REQUEST_ID)
-                                    .unwrap()
-                                    .to_str()
-                                    .unwrap();
-
-                                info!(
-                                    %request_id,
-                                    code = response.status().as_u16(),
-                                    latency = latency.as_millis()
-                                )
-                            },
-                        ),
-                )
-                .layer(PropagateRequestIdLayer::x_request_id()),
-        )
-    }
-}
-
-impl Server {
-    async fn handle_404() -> impl IntoResponse {
-        StatusCode::NOT_FOUND
-    }
-
-    async fn handle_405() -> impl IntoResponse {
-        StatusCode::METHOD_NOT_ALLOWED
-    }
-
-    async fn listener(&self) -> Result<TcpListener> {
-        let addr = SocketAddr::new(self.ip(), self.port());
-        let listener = TcpListener::bind(&addr).await?;
-
-        Ok(listener)
-    }
-
-    fn ip(&self) -> IpAddr {
-        match self {
-            // TODO: Change this to Ipv6Addr::LOCALHOST when the GitHub runners
-            // allow binding to localhost
-            Server::Internal(_) => IpAddr::from(Ipv6Addr::UNSPECIFIED),
-            Server::External(_) => IpAddr::from(Ipv6Addr::UNSPECIFIED),
-        }
-    }
-
-    fn port(self) -> u16 {
-        match self {
-            Server::Internal(port) => port,
-            Server::External(port) => port,
-        }
-    }
-
-    async fn serve(self, compute: Arc<ComputeNode>) {
-        let listener = self.listener().await.unwrap_or_else(|e| {
-            // If we can't bind, the compute cannot operate correctly
-            panic!(
-                "failed to bind the compute_ctl {} HTTP server to {}: {}",
-                self,
-                SocketAddr::new(self.ip(), self.port()),
-                e
-            );
-        });
-
-        if tracing::enabled!(tracing::Level::INFO) {
-            let local_addr = match listener.local_addr() {
-                Ok(local_addr) => local_addr,
-                Err(_) => SocketAddr::new(self.ip(), self.port()),
-            };
-
-            info!(
-                "compute_ctl {} HTTP server listening at {}",
-                self, local_addr
-            );
-        }
-
-        let router = Router::from(self).with_state(compute);
-
-        if let Err(e) = axum::serve(listener, router).await {
-            error!("compute_ctl {} HTTP server error: {}", self, e);
-        }
-    }
-
-    pub fn launch(self, compute: &Arc<ComputeNode>) {
-        let state = Arc::clone(compute);
-
-        info!("Launching the {} server", self);
-
-        tokio::spawn(self.serve(state));
-    }
-}
-
-/// 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();
-    if headers.get(X_REQUEST_ID).is_none() {
-        headers.append(X_REQUEST_ID, Uuid::new_v4().to_string().parse().unwrap());
-    }
-
-    next.run(request).await
-}

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

@@ -3,6 +3,8 @@
 #![deny(unsafe_code)]
 #![deny(clippy::undocumented_unsafe_blocks)]
 
+extern crate hyper0 as hyper;
+
 pub mod checker;
 pub mod config;
 pub mod configurator;
@@ -16,7 +18,6 @@ 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/logger.rs

@@ -11,7 +11,7 @@ use tracing_subscriber::prelude::*;
 /// set `OTEL_EXPORTER_OTLP_ENDPOINT=http://jaeger:4318`. See
 /// `tracing-utils` package description.
 ///
-pub async fn init_tracing_and_logging(default_log_level: &str) -> anyhow::Result<()> {
+pub fn init_tracing_and_logging(default_log_level: &str) -> anyhow::Result<()> {
     // Initialize Logging
     let env_filter = tracing_subscriber::EnvFilter::try_from_default_env()
         .unwrap_or_else(|_| tracing_subscriber::EnvFilter::new(default_log_level));
@@ -22,7 +22,7 @@ pub async fn init_tracing_and_logging(default_log_level: &str) -> anyhow::Result
         .with_writer(std::io::stderr);
 
     // Initialize OpenTelemetry
-    let otlp_layer = tracing_utils::init_tracing("compute_ctl").await;
+    let otlp_layer = tracing_utils::init_tracing_without_runtime("compute_ctl");
 
     // Put it all together
     tracing_subscriber::registry()

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 tokio_postgres::{Client, Transaction};
-use tracing::{error, info};
-
-use crate::metrics::DB_MIGRATION_FAILED;
+use postgres::Client;
+use tracing::info;
 
 /// Runs a series of migrations on a target database
 pub(crate) struct MigrationRunner<'m> {
@@ -21,11 +19,12 @@ impl<'m> MigrationRunner<'m> {
     }
 
     /// Get the current value neon_migration.migration_id
-    async fn get_migration_id(&mut self) -> Result<i64> {
+    fn get_migration_id(&mut self) -> Result<i64> {
+        let query = "SELECT id FROM neon_migration.migration_id";
         let row = self
             .client
-            .query_one("SELECT id FROM neon_migration.migration_id", &[])
-            .await?;
+            .query_one(query, &[])
+            .context("run_migrations get migration_id")?;
 
         Ok(row.get::<&str, i64>("id"))
     }
@@ -35,7 +34,7 @@ impl<'m> MigrationRunner<'m> {
     /// This function has a fail point called compute-migration, which can be
     /// used if you would like to fail the application of a series of migrations
     /// at some point.
-    async fn update_migration_id(txn: &mut Transaction<'_>, migration_id: i64) -> Result<()> {
+    fn update_migration_id(&mut self, migration_id: i64) -> Result<()> {
         // We use this fail point in order to check that failing in the
         // middle of applying a series of migrations fails in an expected
         // manner
@@ -56,92 +55,78 @@ impl<'m> MigrationRunner<'m> {
             }
         }
 
-        txn.query(
-            "UPDATE neon_migration.migration_id SET id = $1",
-            &[&migration_id],
-        )
-        .await
-        .with_context(|| format!("update neon_migration.migration_id to {migration_id}"))?;
+        self.client
+            .query(
+                "UPDATE neon_migration.migration_id SET id = $1",
+                &[&migration_id],
+            )
+            .context("run_migrations update id")?;
 
         Ok(())
     }
 
     /// Prepare the migrations the target database for handling migrations
-    async fn prepare_database(&mut self) -> Result<()> {
+    fn prepare_database(&mut self) -> Result<()> {
         self.client
-            .simple_query("CREATE SCHEMA IF NOT EXISTS neon_migration")
-            .await?;
-        self.client.simple_query("CREATE TABLE IF NOT EXISTS neon_migration.migration_id (key INT NOT NULL PRIMARY KEY, id bigint NOT NULL DEFAULT 0)").await?;
+            .simple_query("CREATE SCHEMA IF NOT EXISTS neon_migration")?;
+        self.client.simple_query("CREATE TABLE IF NOT EXISTS neon_migration.migration_id (key INT NOT NULL PRIMARY KEY, id bigint NOT NULL DEFAULT 0)")?;
+        self.client.simple_query(
+            "INSERT INTO neon_migration.migration_id VALUES (0, 0) ON CONFLICT DO NOTHING",
+        )?;
         self.client
-            .simple_query(
-                "INSERT INTO neon_migration.migration_id VALUES (0, 0) ON CONFLICT DO NOTHING",
-            )
-            .await?;
+            .simple_query("ALTER SCHEMA neon_migration OWNER TO cloud_admin")?;
         self.client
-            .simple_query("ALTER SCHEMA neon_migration OWNER TO cloud_admin")
-            .await?;
-        self.client
-            .simple_query("REVOKE ALL ON SCHEMA neon_migration FROM PUBLIC")
-            .await?;
+            .simple_query("REVOKE ALL ON SCHEMA neon_migration FROM PUBLIC")?;
 
         Ok(())
     }
 
-    /// Run an individual migration in a separate transaction block.
-    async fn run_migration(client: &mut Client, migration_id: i64, migration: &str) -> Result<()> {
-        let mut txn = client
-            .transaction()
-            .await
-            .with_context(|| format!("begin transaction for migration {migration_id}"))?;
+    /// Run the configrured set of migrations
+    pub fn run_migrations(mut self) -> Result<()> {
+        self.prepare_database()?;
 
-        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).await?;
-        } else {
-            info!("Running migration id={}:\n{}\n", migration_id, migration);
-
-            txn.simple_query(migration)
-                .await
-                .with_context(|| format!("apply migration {migration_id}"))?;
-
-            Self::update_migration_id(&mut txn, migration_id).await?;
-        }
-
-        txn.commit()
-            .await
-            .with_context(|| format!("commit transaction for migration {migration_id}"))?;
-
-        Ok(())
-    }
-
-    /// Run the configured set of migrations
-    pub async fn run_migrations(mut self) -> Result<()> {
-        self.prepare_database()
-            .await
-            .context("prepare database to handle migrations")?;
-
-        let mut current_migration = self.get_migration_id().await? as usize;
+        let mut current_migration = self.get_migration_id()? as usize;
         while current_migration < self.migrations.len() {
-            // 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;
+            macro_rules! migration_id {
+                ($cm:expr) => {
+                    ($cm + 1) as i64
+                };
+            }
+
             let migration = self.migrations[current_migration];
 
-            match Self::run_migration(self.client, migration_id, migration).await {
-                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);
-                }
+            if migration.starts_with("-- SKIP") {
+                info!("Skipping migration id={}", migration_id!(current_migration));
+
+                // 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(migration_id!(current_migration))?;
+            } else {
+                info!(
+                    "Running migration id={}:\n{}\n",
+                    migration_id!(current_migration),
+                    migration
+                );
+
+                self.client
+                    .simple_query("BEGIN")
+                    .context("begin migration")?;
+
+                self.client.simple_query(migration).with_context(|| {
+                    format!(
+                        "run_migrations migration id={}",
+                        migration_id!(current_migration)
+                    )
+                })?;
+
+                self.update_migration_id(migration_id!(current_migration))?;
+
+                self.client
+                    .simple_query("COMMIT")
+                    .context("commit migration")?;
+
+                info!("Finished migration id={}", migration_id!(current_migration));
             }
 
             current_migration += 1;

compute_tools/src/pg_helpers.rs

@@ -7,6 +7,7 @@ use std::os::unix::fs::PermissionsExt;
 use std::path::Path;
 use std::process::Child;
 use std::str::FromStr;
+use std::thread::JoinHandle;
 use std::time::{Duration, Instant};
 
 use anyhow::{bail, Result};
@@ -15,7 +16,6 @@ use ini::Ini;
 use notify::{RecursiveMode, Watcher};
 use postgres::config::Config;
 use tokio::io::AsyncBufReadExt;
-use tokio::task::JoinHandle;
 use tokio::time::timeout;
 use tokio_postgres;
 use tokio_postgres::NoTls;
@@ -477,13 +477,23 @@ pub async fn tune_pgbouncer(pgbouncer_config: HashMap<String, String>) -> Result
     Ok(())
 }
 
-/// Spawn a task that will read Postgres logs from `stderr`, join multiline logs
+/// Spawn a thread that will read Postgres logs from `stderr`, join multiline logs
 /// and send them to the logger. In the future we may also want to add context to
 /// these logs.
-pub fn handle_postgres_logs(stderr: std::process::ChildStderr) -> JoinHandle<Result<()>> {
-    tokio::spawn(async move {
-        let stderr = tokio::process::ChildStderr::from_std(stderr)?;
-        handle_postgres_logs_async(stderr).await
+pub fn handle_postgres_logs(stderr: std::process::ChildStderr) -> JoinHandle<()> {
+    std::thread::spawn(move || {
+        let runtime = tokio::runtime::Builder::new_current_thread()
+            .enable_all()
+            .build()
+            .expect("failed to build tokio runtime");
+
+        let res = runtime.block_on(async move {
+            let stderr = tokio::process::ChildStderr::from_std(stderr)?;
+            handle_postgres_logs_async(stderr).await
+        });
+        if let Err(e) = res {
+            tracing::error!("error while processing postgres logs: {}", e);
+        }
     })
 }
 

compute_tools/src/spec.rs

@@ -1,19 +1,16 @@
 use anyhow::{anyhow, bail, Result};
+use postgres::Client;
 use reqwest::StatusCode;
 use std::fs::File;
 use std::path::Path;
-use tokio_postgres::Client;
 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::{
-    ComputeCtlConfig, ControlPlaneComputeStatus, ControlPlaneSpecResponse,
-};
+use compute_api::responses::{ControlPlaneComputeStatus, ControlPlaneSpecResponse};
 use compute_api::spec::ComputeSpec;
 
 // Do control plane request and return response if any. In case of error it
@@ -22,7 +19,7 @@ use compute_api::spec::ComputeSpec;
 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))
@@ -30,42 +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()
+            ),
         )),
     }
 }
@@ -75,13 +65,14 @@ fn do_control_plane_request(
 pub fn get_spec_from_control_plane(
     base_uri: &str,
     compute_id: &str,
-) -> Result<(Option<ComputeSpec>, ComputeCtlConfig)> {
+) -> Result<Option<ComputeSpec>> {
     let cp_uri = format!("{base_uri}/compute/api/v2/computes/{compute_id}/spec");
     let jwt: String = match std::env::var("NEON_CONTROL_PLANE_TOKEN") {
         Ok(v) => v,
         Err(_) => "".to_string(),
     };
     let mut attempt = 1;
+    let mut spec: Result<Option<ComputeSpec>> = Ok(None);
 
     info!("getting spec from control plane: {}", cp_uri);
 
@@ -91,29 +82,18 @@ pub fn get_spec_from_control_plane(
     // - no spec for compute yet (Empty state) -> return Ok(None)
     // - got spec -> return Ok(Some(spec))
     while attempt < 4 {
-        let result = 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, spec_resp.compute_ctl_config)),
-                    ControlPlaneComputeStatus::Attached => {
-                        if let Some(spec) = spec_resp.spec {
-                            Ok((Some(spec), spec_resp.compute_ctl_config))
-                        } else {
-                            bail!("compute is attached, but spec is empty")
-                        }
+        spec = match do_control_plane_request(&cp_uri, &jwt) {
+            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 {
@@ -122,10 +102,10 @@ pub fn get_spec_from_control_plane(
             }
         };
 
-        if let Err(e) = &result {
+        if let Err(e) = &spec {
             error!("attempt {} to get spec failed with: {}", attempt, e);
         } else {
-            return result;
+            return spec;
         }
 
         attempt += 1;
@@ -133,9 +113,7 @@ pub fn get_spec_from_control_plane(
     }
 
     // All attempts failed, return error.
-    Err(anyhow::anyhow!(
-        "Exhausted all attempts to retrieve the spec from the control plane"
-    ))
+    spec
 }
 
 /// Check `pg_hba.conf` and update if needed to allow external connections.
@@ -169,17 +147,17 @@ pub fn add_standby_signal(pgdata_path: &Path) -> Result<()> {
 }
 
 #[instrument(skip_all)]
-pub async fn handle_neon_extension_upgrade(client: &mut Client) -> Result<()> {
+pub fn handle_neon_extension_upgrade(client: &mut Client) -> Result<()> {
     info!("handle neon extension upgrade");
     let query = "ALTER EXTENSION neon UPDATE";
     info!("update neon extension version with query: {}", query);
-    client.simple_query(query).await?;
+    client.simple_query(query)?;
 
     Ok(())
 }
 
 #[instrument(skip_all)]
-pub async fn handle_migrations(client: &mut Client) -> Result<()> {
+pub fn handle_migrations(client: &mut Client) -> Result<()> {
     info!("handle migrations");
 
     // !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
@@ -209,9 +187,7 @@ pub async fn handle_migrations(client: &mut Client) -> Result<()> {
         ),
     ];
 
-    MigrationRunner::new(client, &migrations)
-        .run_migrations()
-        .await?;
+    MigrationRunner::new(client, &migrations).run_migrations()?;
 
     Ok(())
 }
@@ -219,7 +195,7 @@ pub async fn handle_migrations(client: &mut Client) -> Result<()> {
 /// Connect to the database as superuser and pre-create anon extension
 /// if it is present in shared_preload_libraries
 #[instrument(skip_all)]
-pub async fn handle_extension_anon(
+pub fn handle_extension_anon(
     spec: &ComputeSpec,
     db_owner: &str,
     db_client: &mut Client,
@@ -232,7 +208,7 @@ pub async fn handle_extension_anon(
             if !grants_only {
                 // check if extension is already initialized using anon.is_initialized()
                 let query = "SELECT anon.is_initialized()";
-                match db_client.query(query, &[]).await {
+                match db_client.query(query, &[]) {
                     Ok(rows) => {
                         if !rows.is_empty() {
                             let is_initialized: bool = rows[0].get(0);
@@ -254,7 +230,7 @@ pub async fn handle_extension_anon(
                 // Users cannot create it themselves, because superuser is required.
                 let mut query = "CREATE EXTENSION IF NOT EXISTS anon CASCADE";
                 info!("creating anon extension with query: {}", query);
-                match db_client.query(query, &[]).await {
+                match db_client.query(query, &[]) {
                     Ok(_) => {}
                     Err(e) => {
                         error!("anon extension creation failed with error: {}", e);
@@ -264,7 +240,7 @@ pub async fn handle_extension_anon(
 
                 // check that extension is installed
                 query = "SELECT extname FROM pg_extension WHERE extname = 'anon'";
-                let rows = db_client.query(query, &[]).await?;
+                let rows = db_client.query(query, &[])?;
                 if rows.is_empty() {
                     error!("anon extension is not installed");
                     return Ok(());
@@ -273,7 +249,7 @@ pub async fn handle_extension_anon(
                 // Initialize anon extension
                 // This also requires superuser privileges, so users cannot do it themselves.
                 query = "SELECT anon.init()";
-                match db_client.query(query, &[]).await {
+                match db_client.query(query, &[]) {
                     Ok(_) => {}
                     Err(e) => {
                         error!("anon.init() failed with error: {}", e);
@@ -284,7 +260,7 @@ pub async fn handle_extension_anon(
 
             // check that extension is installed, if not bail early
             let query = "SELECT extname FROM pg_extension WHERE extname = 'anon'";
-            match db_client.query(query, &[]).await {
+            match db_client.query(query, &[]) {
                 Ok(rows) => {
                     if rows.is_empty() {
                         error!("anon extension is not installed");
@@ -299,12 +275,12 @@ pub async fn handle_extension_anon(
 
             let query = format!("GRANT ALL ON SCHEMA anon TO {}", db_owner);
             info!("granting anon extension permissions with query: {}", query);
-            db_client.simple_query(&query).await?;
+            db_client.simple_query(&query)?;
 
             // Grant permissions to db_owner to use anon extension functions
             let query = format!("GRANT ALL ON ALL FUNCTIONS IN SCHEMA anon TO {}", db_owner);
             info!("granting anon extension permissions with query: {}", query);
-            db_client.simple_query(&query).await?;
+            db_client.simple_query(&query)?;
 
             // This is needed, because some functions are defined as SECURITY DEFINER.
             // In Postgres SECURITY DEFINER functions are executed with the privileges
@@ -319,16 +295,16 @@ pub async fn handle_extension_anon(
                 where nsp.nspname = 'anon';", db_owner);
 
             info!("change anon extension functions owner to db owner");
-            db_client.simple_query(&query).await?;
+            db_client.simple_query(&query)?;
 
             //  affects views as well
             let query = format!("GRANT ALL ON ALL TABLES IN SCHEMA anon TO {}", db_owner);
             info!("granting anon extension permissions with query: {}", query);
-            db_client.simple_query(&query).await?;
+            db_client.simple_query(&query)?;
 
             let query = format!("GRANT ALL ON ALL SEQUENCES IN SCHEMA anon TO {}", db_owner);
             info!("granting anon extension permissions with query: {}", query);
-            db_client.simple_query(&query).await?;
+            db_client.simple_query(&query)?;
         }
     }
 

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 {
@@ -77,7 +75,7 @@ pub struct MutableApplyContext {
     pub dbs: HashMap<String, Database>,
 }
 
-/// Apply the operations that belong to the given spec apply phase.
+/// Appply the operations that belong to the given spec apply phase.
 ///
 /// Commands within a single phase are executed in order of Iterator yield.
 /// Commands of ApplySpecPhase::RunInEachDatabase will execute in the database
@@ -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),
                             );
 
@@ -506,19 +498,7 @@ async fn get_operations<'a>(
                                         ),
                                         comment: None,
                                     },
-                                    // Revoke some potentially blocking privileges (Neon-specific currently)
-                                    Operation {
-                                        query: format!(
-                                            include_str!("sql/pre_drop_role_revoke_privileges.sql"),
-                                            role_name = quoted,
-                                        ),
-                                        comment: None,
-                                    },
                                     // This now will only drop privileges of the role
-                                    // TODO: this is obviously not 100% true because of the above case,
-                                    // there could be still some privileges that are not revoked. Maybe this
-                                    // only drops privileges that were granted *by this* role, not *to this* role,
-                                    // but this has to be checked.
                                     Operation {
                                         query: format!("DROP OWNED BY {}", quoted),
                                         comment: None,
@@ -674,6 +654,10 @@ 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 +700,5 @@ 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/drop_subscription_for_drop_dbs.sql

@@ -2,7 +2,6 @@ DO $$
 DECLARE
     subname TEXT;
 BEGIN
-    LOCK TABLE pg_subscription IN ACCESS EXCLUSIVE MODE;
     FOR subname IN SELECT pg_subscription.subname FROM pg_subscription WHERE subdbid = (SELECT oid FROM pg_database WHERE datname = {datname_str}) LOOP
         EXECUTE format('ALTER SUBSCRIPTION %I DISABLE;', subname);
         EXECUTE format('ALTER SUBSCRIPTION %I SET (slot_name = NONE);', subname);

compute_tools/src/sql/finalize_drop_subscriptions.sql

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

compute_tools/src/sql/pre_drop_role_revoke_privileges.sql

@@ -1,28 +0,0 @@
-SET SESSION ROLE neon_superuser;
-
-DO $$
-DECLARE
-    schema TEXT;
-    revoke_query TEXT;
-BEGIN
-    FOR schema IN
-        SELECT schema_name
-        FROM information_schema.schemata
-        -- So far, we only had issues with 'public' schema. Probably, because we do some additional grants,
-        -- e.g., make DB owner the owner of 'public' schema automatically (when created via API).
-        -- See https://github.com/neondatabase/cloud/issues/13582 for the context.
-        -- Still, keep the loop because i) it efficiently handles the case when there is no 'public' schema,
-        -- ii) it's easy to add more schemas to the list if needed.
-        WHERE schema_name IN ('public')
-    LOOP
-        revoke_query := format(
-            'REVOKE ALL PRIVILEGES ON ALL TABLES IN SCHEMA %I FROM {role_name} GRANTED BY neon_superuser;',
-            schema
-        );
-
-        EXECUTE revoke_query;
-    END LOOP;
-END;
-$$;
-
-RESET ROLE;

control_plane/Cargo.toml

@@ -33,7 +33,6 @@ postgres_backend.workspace = true
 safekeeper_api.workspace = true
 postgres_connection.workspace = true
 storage_broker.workspace = true
-http-utils.workspace = true
 utils.workspace = true
 whoami.workspace = true
 

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

@@ -552,10 +552,8 @@ struct EndpointCreateCmdArgs {
     lsn: Option<Lsn>,
     #[clap(long)]
     pg_port: Option<u16>,
-    #[clap(long, alias = "http-port")]
-    external_http_port: Option<u16>,
     #[clap(long)]
-    internal_http_port: Option<u16>,
+    http_port: Option<u16>,
     #[clap(long = "pageserver-id")]
     endpoint_pageserver_id: Option<NodeId>,
 
@@ -1355,12 +1353,10 @@ async fn handle_endpoint(subcmd: &EndpointCmd, env: &local_env::LocalEnv) -> Res
                 tenant_id,
                 timeline_id,
                 args.pg_port,
-                args.external_http_port,
-                args.internal_http_port,
+                args.http_port,
                 args.pg_version,
                 mode,
                 !args.update_catalog,
-                false,
             )?;
         }
         EndpointCmd::Start(args) => {

control_plane/src/endpoint.rs

@@ -37,8 +37,6 @@
 //! ```
 //!
 use std::collections::BTreeMap;
-use std::net::IpAddr;
-use std::net::Ipv4Addr;
 use std::net::SocketAddr;
 use std::net::TcpStream;
 use std::path::PathBuf;
@@ -46,12 +44,8 @@ use std::process::Command;
 use std::str::FromStr;
 use std::sync::Arc;
 use std::time::Duration;
-use std::time::SystemTime;
-use std::time::UNIX_EPOCH;
 
 use anyhow::{anyhow, bail, Context, Result};
-use compute_api::requests::ConfigurationRequest;
-use compute_api::responses::ComputeCtlConfig;
 use compute_api::spec::Database;
 use compute_api::spec::PgIdent;
 use compute_api::spec::RemoteExtSpec;
@@ -61,7 +55,6 @@ use nix::sys::signal::Signal;
 use pageserver_api::shard::ShardStripeSize;
 use reqwest::header::CONTENT_TYPE;
 use serde::{Deserialize, Serialize};
-use tracing::debug;
 use url::Host;
 use utils::id::{NodeId, TenantId, TimelineId};
 
@@ -69,7 +62,7 @@ use crate::local_env::LocalEnv;
 use crate::postgresql_conf::PostgresConf;
 use crate::storage_controller::StorageController;
 
-use compute_api::responses::{ComputeStatus, ComputeStatusResponse};
+use compute_api::responses::{ComputeState, ComputeStatus};
 use compute_api::spec::{Cluster, ComputeFeature, ComputeMode, ComputeSpec};
 
 // contents of a endpoint.json file
@@ -80,14 +73,10 @@ pub struct EndpointConf {
     timeline_id: TimelineId,
     mode: ComputeMode,
     pg_port: u16,
-    external_http_port: u16,
-    internal_http_port: u16,
+    http_port: u16,
     pg_version: u32,
     skip_pg_catalog_updates: bool,
-    reconfigure_concurrency: usize,
-    drop_subscriptions_before_start: bool,
     features: Vec<ComputeFeature>,
-    cluster: Option<Cluster>,
 }
 
 //
@@ -138,7 +127,7 @@ impl ComputeControlPlane {
         1 + self
             .endpoints
             .values()
-            .map(|ep| std::cmp::max(ep.pg_address.port(), ep.external_http_address.port()))
+            .map(|ep| std::cmp::max(ep.pg_address.port(), ep.http_address.port()))
             .max()
             .unwrap_or(self.base_port)
     }
@@ -150,27 +139,17 @@ impl ComputeControlPlane {
         tenant_id: TenantId,
         timeline_id: TimelineId,
         pg_port: Option<u16>,
-        external_http_port: Option<u16>,
-        internal_http_port: Option<u16>,
+        http_port: Option<u16>,
         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 external_http_port = external_http_port.unwrap_or_else(|| self.get_port() + 1);
-        let internal_http_port = internal_http_port.unwrap_or_else(|| external_http_port + 1);
+        let http_port = http_port.unwrap_or_else(|| self.get_port() + 1);
         let ep = Arc::new(Endpoint {
             endpoint_id: endpoint_id.to_owned(),
-            pg_address: SocketAddr::new(IpAddr::from(Ipv4Addr::LOCALHOST), pg_port),
-            external_http_address: SocketAddr::new(
-                IpAddr::from(Ipv4Addr::UNSPECIFIED),
-                external_http_port,
-            ),
-            internal_http_address: SocketAddr::new(
-                IpAddr::from(Ipv4Addr::LOCALHOST),
-                internal_http_port,
-            ),
+            pg_address: SocketAddr::new("127.0.0.1".parse().unwrap(), pg_port),
+            http_address: SocketAddr::new("127.0.0.1".parse().unwrap(), http_port),
             env: self.env.clone(),
             timeline_id,
             mode,
@@ -183,10 +162,7 @@ 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,
-            reconfigure_concurrency: 1,
             features: vec![],
-            cluster: None,
         });
 
         ep.create_endpoint_dir()?;
@@ -197,15 +173,11 @@ impl ComputeControlPlane {
                 tenant_id,
                 timeline_id,
                 mode,
-                external_http_port,
-                internal_http_port,
+                http_port,
                 pg_port,
                 pg_version,
                 skip_pg_catalog_updates,
-                drop_subscriptions_before_start,
-                reconfigure_concurrency: 1,
                 features: vec![],
-                cluster: None,
             })?,
         )?;
         std::fs::write(
@@ -254,10 +226,9 @@ pub struct Endpoint {
     pub timeline_id: TimelineId,
     pub mode: ComputeMode,
 
-    // port and address of the Postgres server and `compute_ctl`'s HTTP APIs
+    // port and address of the Postgres server and `compute_ctl`'s HTTP API
     pub pg_address: SocketAddr,
-    pub external_http_address: SocketAddr,
-    pub internal_http_address: SocketAddr,
+    pub http_address: SocketAddr,
 
     // postgres major version in the format: 14, 15, etc.
     pg_version: u32,
@@ -269,12 +240,8 @@ pub struct Endpoint {
     // Optimizations
     skip_pg_catalog_updates: bool,
 
-    drop_subscriptions_before_start: bool,
-    reconfigure_concurrency: usize,
     // Feature flags
     features: Vec<ComputeFeature>,
-    // Cluster settings
-    cluster: Option<Cluster>,
 }
 
 #[derive(PartialEq, Eq)]
@@ -314,18 +281,9 @@ impl Endpoint {
         let conf: EndpointConf =
             serde_json::from_slice(&std::fs::read(entry.path().join("endpoint.json"))?)?;
 
-        debug!("serialized endpoint conf: {:?}", conf);
-
         Ok(Endpoint {
-            pg_address: SocketAddr::new(IpAddr::from(Ipv4Addr::LOCALHOST), conf.pg_port),
-            external_http_address: SocketAddr::new(
-                IpAddr::from(Ipv4Addr::UNSPECIFIED),
-                conf.external_http_port,
-            ),
-            internal_http_address: SocketAddr::new(
-                IpAddr::from(Ipv4Addr::LOCALHOST),
-                conf.internal_http_port,
-            ),
+            pg_address: SocketAddr::new("127.0.0.1".parse().unwrap(), conf.pg_port),
+            http_address: SocketAddr::new("127.0.0.1".parse().unwrap(), conf.http_port),
             endpoint_id,
             env: env.clone(),
             timeline_id: conf.timeline_id,
@@ -333,10 +291,7 @@ impl Endpoint {
             tenant_id: conf.tenant_id,
             pg_version: conf.pg_version,
             skip_pg_catalog_updates: conf.skip_pg_catalog_updates,
-            reconfigure_concurrency: conf.reconfigure_concurrency,
-            drop_subscriptions_before_start: conf.drop_subscriptions_before_start,
             features: conf.features,
-            cluster: conf.cluster,
         })
     }
 
@@ -623,7 +578,7 @@ impl Endpoint {
         };
 
         // Create spec file
-        let mut spec = ComputeSpec {
+        let spec = ComputeSpec {
             skip_pg_catalog_updates: self.skip_pg_catalog_updates,
             format_version: 1.0,
             operation_uuid: None,
@@ -656,7 +611,7 @@ impl Endpoint {
                     Vec::new()
                 },
                 settings: None,
-                postgresql_conf: Some(postgresql_conf.clone()),
+                postgresql_conf: Some(postgresql_conf),
             },
             delta_operations: None,
             tenant_id: Some(self.tenant_id),
@@ -669,35 +624,8 @@ impl Endpoint {
             pgbouncer_settings: None,
             shard_stripe_size: Some(shard_stripe_size),
             local_proxy_config: None,
-            reconfigure_concurrency: self.reconfigure_concurrency,
-            drop_subscriptions_before_start: self.drop_subscriptions_before_start,
+            reconfigure_concurrency: 1,
         };
-
-        // this strange code is needed to support respec() in tests
-        if self.cluster.is_some() {
-            debug!("Cluster is already set in the endpoint spec, using it");
-            spec.cluster = self.cluster.clone().unwrap();
-
-            debug!("spec.cluster {:?}", spec.cluster);
-
-            // fill missing fields again
-            if create_test_user {
-                spec.cluster.roles.push(Role {
-                    name: PgIdent::from_str("test").unwrap(),
-                    encrypted_password: None,
-                    options: None,
-                });
-                spec.cluster.databases.push(Database {
-                    name: PgIdent::from_str("neondb").unwrap(),
-                    owner: PgIdent::from_str("test").unwrap(),
-                    options: None,
-                    restrict_conn: false,
-                    invalid: false,
-                });
-            }
-            spec.cluster.postgresql_conf = Some(postgresql_conf);
-        }
-
         let spec_path = self.endpoint_path().join("spec.json");
         std::fs::write(spec_path, serde_json::to_string_pretty(&spec)?)?;
 
@@ -715,43 +643,24 @@ impl Endpoint {
             println!("Also at '{}'", conn_str);
         }
         let mut cmd = Command::new(self.env.neon_distrib_dir.join("compute_ctl"));
-        cmd.args([
-            "--external-http-port",
-            &self.external_http_address.port().to_string(),
-        ])
-        .args([
-            "--internal-http-port",
-            &self.internal_http_address.port().to_string(),
-        ])
-        .args(["--pgdata", self.pgdata().to_str().unwrap()])
-        .args(["--connstr", &conn_str])
-        .args([
-            "--spec-path",
-            self.endpoint_path().join("spec.json").to_str().unwrap(),
-        ])
-        .args([
-            "--pgbin",
-            self.env
-                .pg_bin_dir(self.pg_version)?
-                .join("postgres")
-                .to_str()
-                .unwrap(),
-        ])
-        // TODO: It would be nice if we generated compute IDs with the same
-        // algorithm as the real control plane.
-        .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);
+        cmd.args(["--http-port", &self.http_address.port().to_string()])
+            .args(["--pgdata", self.pgdata().to_str().unwrap()])
+            .args(["--connstr", &conn_str])
+            .args([
+                "--spec-path",
+                self.endpoint_path().join("spec.json").to_str().unwrap(),
+            ])
+            .args([
+                "--pgbin",
+                self.env
+                    .pg_bin_dir(self.pg_version)?
+                    .join("postgres")
+                    .to_str()
+                    .unwrap(),
+            ])
+            .stdin(std::process::Stdio::null())
+            .stderr(logfile.try_clone()?)
+            .stdout(logfile);
 
         if let Some(remote_ext_config) = remote_ext_config {
             cmd.args(["--remote-ext-config", remote_ext_config]);
@@ -830,7 +739,7 @@ impl Endpoint {
     }
 
     // Call the /status HTTP API
-    pub async fn get_status(&self) -> Result<ComputeStatusResponse> {
+    pub async fn get_status(&self) -> Result<ComputeState> {
         let client = reqwest::Client::new();
 
         let response = client
@@ -838,8 +747,8 @@ impl Endpoint {
                 reqwest::Method::GET,
                 format!(
                     "http://{}:{}/status",
-                    self.external_http_address.ip(),
-                    self.external_http_address.port()
+                    self.http_address.ip(),
+                    self.http_address.port()
                 ),
             )
             .send()
@@ -912,17 +821,14 @@ impl Endpoint {
         let response = client
             .post(format!(
                 "http://{}:{}/configure",
-                self.external_http_address.ip(),
-                self.external_http_address.port()
+                self.http_address.ip(),
+                self.http_address.port()
             ))
             .header(CONTENT_TYPE.as_str(), "application/json")
-            .body(
-                serde_json::to_string(&ConfigurationRequest {
-                    spec,
-                    compute_ctl_config: ComputeCtlConfig::default(),
-                })
-                .unwrap(),
-            )
+            .body(format!(
+                "{{\"spec\":{}}}",
+                serde_json::to_string_pretty(&spec)?
+            ))
             .send()
             .await?;
 

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

@@ -335,70 +335,29 @@ impl PageServerNode {
                 .map(|x| x.parse::<u64>())
                 .transpose()
                 .context("Failed to parse 'checkpoint_distance' as an integer")?,
-            checkpoint_timeout: settings
-                .remove("checkpoint_timeout")
-                .map(humantime::parse_duration)
-                .transpose()
-                .context("Failed to parse 'checkpoint_timeout' as duration")?,
+            checkpoint_timeout: settings.remove("checkpoint_timeout").map(|x| x.to_string()),
             compaction_target_size: settings
                 .remove("compaction_target_size")
                 .map(|x| x.parse::<u64>())
                 .transpose()
                 .context("Failed to parse 'compaction_target_size' as an integer")?,
-            compaction_period: settings
-                .remove("compaction_period")
-                .map(humantime::parse_duration)
-                .transpose()
-                .context("Failed to parse 'compaction_period' as duration")?,
+            compaction_period: settings.remove("compaction_period").map(|x| x.to_string()),
             compaction_threshold: settings
                 .remove("compaction_threshold")
                 .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")?,
-            compaction_l0_first: settings
-                .remove("compaction_l0_first")
-                .map(|x| x.parse::<bool>())
-                .transpose()
-                .context("Failed to parse 'compaction_l0_first' as a bool")?,
-            compaction_l0_semaphore: settings
-                .remove("compaction_l0_semaphore")
-                .map(|x| x.parse::<bool>())
-                .transpose()
-                .context("Failed to parse 'compaction_l0_semaphore' as a bool")?,
-            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>())
                 .transpose()
                 .context("Failed to parse 'gc_horizon' as an integer")?,
-            gc_period: settings.remove("gc_period")
-                .map(humantime::parse_duration)
-                .transpose()
-                .context("Failed to parse 'gc_period' as duration")?,
+            gc_period: settings.remove("gc_period").map(|x| x.to_string()),
             image_creation_threshold: settings
                 .remove("image_creation_threshold")
                 .map(|x| x.parse::<usize>())
@@ -409,25 +368,13 @@ 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(humantime::parse_duration)
-                .transpose()
-                .context("Failed to parse 'pitr_interval' as duration")?,
+            pitr_interval: settings.remove("pitr_interval").map(|x| x.to_string()),
             walreceiver_connect_timeout: settings
                 .remove("walreceiver_connect_timeout")
-                .map(humantime::parse_duration)
-                .transpose()
-                .context("Failed to parse 'walreceiver_connect_timeout' as duration")?,
+                .map(|x| x.to_string()),
             lagging_wal_timeout: settings
                 .remove("lagging_wal_timeout")
-                .map(humantime::parse_duration)
-                .transpose()
-                .context("Failed to parse 'lagging_wal_timeout' as duration")?,
+                .map(|x| x.to_string()),
             max_lsn_wal_lag: settings
                 .remove("max_lsn_wal_lag")
                 .map(|x| x.parse::<NonZeroU64>())
@@ -445,14 +392,8 @@ impl PageServerNode {
                 .context("Failed to parse 'min_resident_size_override' as integer")?,
             evictions_low_residence_duration_metric_threshold: settings
                 .remove("evictions_low_residence_duration_metric_threshold")
-                .map(humantime::parse_duration)
-                .transpose()
-                .context("Failed to parse 'evictions_low_residence_duration_metric_threshold' as duration")?,
-            heatmap_period: settings
-                .remove("heatmap_period")
-                .map(humantime::parse_duration)
-                .transpose()
-                .context("Failed to parse 'heatmap_period' as duration")?,
+                .map(|x| x.to_string()),
+            heatmap_period: settings.remove("heatmap_period").map(|x| x.to_string()),
             lazy_slru_download: settings
                 .remove("lazy_slru_download")
                 .map(|x| x.parse::<bool>())
@@ -463,15 +404,10 @@ impl PageServerNode {
                 .map(serde_json::from_str)
                 .transpose()
                 .context("parse `timeline_get_throttle` from json")?,
-            lsn_lease_length: settings.remove("lsn_lease_length")
-                .map(humantime::parse_duration)
-                .transpose()
-                .context("Failed to parse 'lsn_lease_length' as duration")?,
+            lsn_lease_length: settings.remove("lsn_lease_length").map(|x| x.to_string()),
             lsn_lease_length_for_ts: settings
                 .remove("lsn_lease_length_for_ts")
-                .map(humantime::parse_duration)
-                .transpose()
-                .context("Failed to parse 'lsn_lease_length_for_ts' as duration")?,
+                .map(|x| x.to_string()),
             timeline_offloading: settings
                 .remove("timeline_offloading")
                 .map(|x| x.parse::<bool>())
@@ -482,26 +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/safekeeper.rs

@@ -17,10 +17,8 @@ use camino::Utf8PathBuf;
 use postgres_connection::PgConnectionConfig;
 use reqwest::{IntoUrl, Method};
 use thiserror::Error;
-
-use http_utils::error::HttpErrorBody;
 use utils::auth::{Claims, Scope};
-use utils::id::NodeId;
+use utils::{http::error::HttpErrorBody, id::NodeId};
 
 use crate::{
     background_process,

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");
@@ -839,8 +823,8 @@ impl StorageController {
             Method::PUT,
             format!("control/v1/tenant/{tenant_shard_id}/migrate"),
             Some(TenantShardMigrateRequest {
+                tenant_shard_id,
                 node_id,
-                migration_config: None,
             }),
         )
         .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,
@@ -22,7 +17,7 @@ use pageserver_api::{
 };
 use pageserver_client::mgmt_api::{self};
 use reqwest::{Method, StatusCode, Url};
-use utils::id::{NodeId, TenantId, TimelineId};
+use utils::id::{NodeId, TenantId};
 
 use pageserver_api::controller_api::{
     NodeConfigureRequest, NodeRegisterRequest, NodeSchedulingPolicy, PlacementPolicy,
@@ -47,9 +42,6 @@ enum Command {
         listen_http_addr: String,
         #[arg(long)]
         listen_http_port: u16,
-        #[arg(long)]
-        listen_https_port: Option<u16>,
-
         #[arg(long)]
         availability_zone_id: String,
     },
@@ -120,13 +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)]
@@ -161,12 +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 {
@@ -235,26 +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,
-    },
-    /// Downloads any missing heatmap layers for all shard for a given timeline
-    DownloadHeatmapLayers {
-        /// Tenant ID or tenant shard ID. When an unsharded tenant ID is specified,
-        /// the operation is performed on all shards. When a sharded tenant ID is
-        /// specified, the operation is only performed on the specified shard.
-        #[arg(long)]
-        tenant_shard_id: TenantShardId,
-        #[arg(long)]
-        timeline_id: TimelineId,
-        /// Optional: Maximum download concurrency (default is 16)
-        #[arg(long)]
-        concurrency: Option<usize>,
-    },
 }
 
 #[derive(Parser)]
@@ -307,17 +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);
 
@@ -397,7 +345,6 @@ async fn main() -> anyhow::Result<()> {
             listen_pg_port,
             listen_http_addr,
             listen_http_port,
-            listen_https_port,
             availability_zone_id,
         } => {
             storcon_client
@@ -410,7 +357,6 @@ async fn main() -> anyhow::Result<()> {
                         listen_pg_port,
                         listen_http_addr,
                         listen_http_port,
-                        listen_https_port,
                         availability_zone_id: AvailabilityZone(availability_zone_id),
                     }),
                 )
@@ -449,12 +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),
                 ]);
@@ -514,65 +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}");
@@ -628,8 +541,8 @@ async fn main() -> anyhow::Result<()> {
             node,
         } => {
             let req = TenantShardMigrateRequest {
+                tenant_shard_id,
                 node_id: node,
-                migration_config: None,
             };
 
             storcon_client
@@ -640,23 +553,6 @@ async fn main() -> anyhow::Result<()> {
                 )
                 .await?;
         }
-        Command::TenantShardMigrateSecondary {
-            tenant_shard_id,
-            node,
-        } => {
-            let req = TenantShardMigrateRequest {
-                node_id: node,
-                migration_config: None,
-            };
-
-            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::<(), ()>(
@@ -700,19 +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)]);
@@ -721,14 +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
@@ -751,18 +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,
@@ -771,66 +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>(
@@ -959,7 +768,7 @@ async fn main() -> anyhow::Result<()> {
                                 threshold: threshold.into(),
                             },
                         )),
-                        heatmap_period: Some(Duration::from_secs(300)),
+                        heatmap_period: Some("300s".to_string()),
                         ..Default::default()
                     },
                 })
@@ -1107,8 +916,8 @@ async fn main() -> anyhow::Result<()> {
                                 Method::PUT,
                                 format!("control/v1/tenant/{}/migrate", mv.tenant_shard_id),
                                 Some(TenantShardMigrateRequest {
+                                    tenant_shard_id: mv.tenant_shard_id,
                                     node_id: mv.to,
-                                    migration_config: None,
                                 }),
                             )
                             .await
@@ -1226,15 +1035,7 @@ async fn main() -> anyhow::Result<()> {
             resp.sort_by(|a, b| a.id.cmp(&b.id));
 
             let mut table = comfy_table::Table::new();
-            table.set_header([
-                "Id",
-                "Version",
-                "Host",
-                "Port",
-                "Http Port",
-                "AZ Id",
-                "Scheduling",
-            ]);
+            table.set_header(["Id", "Version", "Host", "Port", "Http Port", "AZ Id"]);
             for sk in resp {
                 table.add_row([
                     format!("{}", sk.id),
@@ -1242,47 +1043,11 @@ async fn main() -> anyhow::Result<()> {
                     sk.host,
                     format!("{}", sk.port),
                     format!("{}", sk.http_port),
-                    sk.availability_zone_id.clone(),
-                    String::from(sk.scheduling_policy),
+                    sk.availability_zone_id.to_string(),
                 ]);
             }
             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)
-            );
-        }
-        Command::DownloadHeatmapLayers {
-            tenant_shard_id,
-            timeline_id,
-            concurrency,
-        } => {
-            let mut path = format!(
-                "/v1/tenant/{}/timeline/{}/download_heatmap_layers",
-                tenant_shard_id, timeline_id,
-            );
-
-            if let Some(c) = concurrency {
-                path = format!("{path}?concurrency={c}");
-            }
-
-            storcon_client
-                .dispatch::<(), ()>(Method::POST, path, None)
-                .await?;
-        }
     }
 
     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