pageserver: trace slow requests when compact_l0

Signed-off-by: Alex Chi Z <chi@neon.tech>
Co-authored-by: Christian Schwarz <christian@neon.tech>

.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:
@@ -27,4 +26,3 @@ config-variables:
   - SLACK_ON_CALL_QA_STAGING_STREAM
   - DEV_AWS_OIDC_ROLE_MANAGE_BENCHMARK_EC2_VMS_ARN
   - SLACK_ON_CALL_STORAGE_STAGING_STREAM
-  - SLACK_CICD_CHANNEL_ID

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

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

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

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

.github/file-filters.yaml

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

.github/workflows/_benchmarking_preparation.yml

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

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

@@ -23,11 +23,6 @@ on:
         description: 'a json object of postgres versions and lfc states to run regression tests on'
         required: true
         type: string
-      sanitizers:
-        description: 'enabled or disabled'
-        required: false
-        default: 'disabled'
-        type: string
 
 defaults:
   run:
@@ -92,7 +87,6 @@ jobs:
       - name: Set env variables
         env:
           ARCH: ${{ inputs.arch }}
-          SANITIZERS: ${{ inputs.sanitizers }}
         run: |
           CARGO_FEATURES="--features testing"
           if [[ $BUILD_TYPE == "debug" && $ARCH == 'x64' ]]; then
@@ -105,14 +99,8 @@ jobs:
             cov_prefix=""
             CARGO_FLAGS="--locked --release"
           fi
-          if [[ $SANITIZERS == 'enabled' ]]; then
-            make_vars="WITH_SANITIZERS=yes"
-          else
-            make_vars=""
-          fi
           {
             echo "cov_prefix=${cov_prefix}"
-            echo "make_vars=${make_vars}"
             echo "CARGO_FEATURES=${CARGO_FEATURES}"
             echo "CARGO_FLAGS=${CARGO_FLAGS}"
             echo "CARGO_HOME=${GITHUB_WORKSPACE}/.cargo"
@@ -148,39 +136,37 @@ jobs:
 
       - name: Build postgres v14
         if: steps.cache_pg_14.outputs.cache-hit != 'true'
-        run: mold -run make ${make_vars} postgres-v14 -j$(nproc)
+        run: mold -run make postgres-v14 -j$(nproc)
 
       - name: Build postgres v15
         if: steps.cache_pg_15.outputs.cache-hit != 'true'
-        run: mold -run make ${make_vars} postgres-v15 -j$(nproc)
+        run: mold -run make postgres-v15 -j$(nproc)
 
       - name: Build postgres v16
         if: steps.cache_pg_16.outputs.cache-hit != 'true'
-        run: mold -run make ${make_vars} postgres-v16 -j$(nproc)
+        run: mold -run make postgres-v16 -j$(nproc)
 
       - name: Build postgres v17
         if: steps.cache_pg_17.outputs.cache-hit != 'true'
-        run: mold -run make ${make_vars} postgres-v17 -j$(nproc)
+        run: mold -run make postgres-v17 -j$(nproc)
 
       - name: Build neon extensions
-        run: mold -run make ${make_vars} neon-pg-ext -j$(nproc)
+        run: mold -run make neon-pg-ext -j$(nproc)
 
       - name: Build walproposer-lib
-        run: mold -run make ${make_vars} walproposer-lib -j$(nproc)
+        run: mold -run make walproposer-lib -j$(nproc)
 
       - name: Run cargo build
-        env:
-          WITH_TESTS: ${{ inputs.sanitizers != 'enabled' && '--tests' || '' }}
         run: |
-          export ASAN_OPTIONS=detect_leaks=0
-          ${cov_prefix} mold -run cargo build $CARGO_FLAGS $CARGO_FEATURES --bins ${WITH_TESTS}
+          PQ_LIB_DIR=$(pwd)/pg_install/v16/lib
+          export PQ_LIB_DIR
+          ${cov_prefix} mold -run cargo build $CARGO_FLAGS $CARGO_FEATURES --bins --tests
 
       # Do install *before* running rust tests because they might recompile the
       # binaries with different features/flags.
       - name: Install rust binaries
         env:
           ARCH: ${{ inputs.arch }}
-          SANITIZERS: ${{ inputs.sanitizers }}
         run: |
           # Install target binaries
           mkdir -p /tmp/neon/bin/
@@ -195,7 +181,7 @@ jobs:
           done
 
           # Install test executables and write list of all binaries (for code coverage)
-          if [[ $BUILD_TYPE == "debug" && $ARCH == 'x64' && $SANITIZERS != 'enabled' ]]; then
+          if [[ $BUILD_TYPE == "debug" && $ARCH == 'x64' ]]; then
             # Keep bloated coverage data files away from the rest of the artifact
             mkdir -p /tmp/coverage/
 
@@ -228,10 +214,11 @@ jobs:
           role-duration-seconds: 18000 # 5 hours
 
       - name: Run rust tests
-        if: ${{ inputs.sanitizers != 'enabled' }}
         env:
           NEXTEST_RETRIES: 3
         run: |
+          PQ_LIB_DIR=$(pwd)/pg_install/v16/lib
+          export PQ_LIB_DIR
           LD_LIBRARY_PATH=$(pwd)/pg_install/v17/lib
           export LD_LIBRARY_PATH
 
@@ -284,27 +271,6 @@ 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 +303,7 @@ 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
@@ -355,7 +321,6 @@ jobs:
           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

@@ -16,9 +16,6 @@ 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:
@@ -87,3 +84,8 @@ jobs:
         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

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

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

.github/workflows/benchmarking.yml

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

.github/workflows/build-macos.yml

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

.github/workflows/build_and_test.yml

@@ -45,26 +45,6 @@ jobs:
             run cancel-previous-in-concurrency-group.yml \
               --field concurrency_group="${{ env.E2E_CONCURRENCY_GROUP }}"
 
-  files-changed:
-    needs: [ check-permissions ]
-    runs-on: [ self-hosted, small ]
-    timeout-minutes: 3
-    outputs:
-      check-rust-dependencies: ${{ steps.files-changed.outputs.rust_dependencies }}
-
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-        with:
-          submodules: true
-
-      - name: Check for file changes
-        uses: dorny/paths-filter@de90cc6fb38fc0963ad72b210f1f284cd68cea36  # v3.0.2
-        id: files-changed
-        with:
-          token: ${{ secrets.GITHUB_TOKEN }}
-          filters: .github/file-filters.yaml
-
   tag:
     needs: [ check-permissions ]
     runs-on: [ self-hosted, small ]
@@ -190,14 +170,6 @@ jobs:
       archs: '["x64", "arm64"]'
     secrets: inherit
 
-  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
-
   build-and-test-locally:
     needs: [ tag, build-build-tools-image ]
     strategy:
@@ -270,7 +242,7 @@ jobs:
       statuses: write
       contents: write
       pull-requests: write
-    runs-on: [ self-hosted, small-metal ]
+    runs-on: [ self-hosted, small ]
     container:
       image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
       credentials:
@@ -682,7 +654,7 @@ jobs:
           push: true
           pull: true
           file: compute/compute-node.Dockerfile
-          target: extension-tests
+          target: neon-pg-ext-test
           cache-from: type=registry,ref=cache.neon.build/compute-node-${{ matrix.version.pg }}:cache-${{ matrix.version.debian }}-${{ matrix.arch }}
           tags: |
             neondatabase/neon-test-extensions-${{ matrix.version.pg }}:${{needs.tag.outputs.build-tag}}-${{ matrix.version.debian }}-${{ matrix.arch }}
@@ -814,17 +786,6 @@ jobs:
           username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
           password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
 
-      - name: Get the last compute release tag
-        id: get-last-compute-release-tag
-        env:
-          GH_TOKEN: ${{ secrets.CI_ACCESS_TOKEN }}
-        run: |
-          tag=$(gh api -q '[.[].tag_name | select(startswith("release-compute"))][0]'\
-            -H "Accept: application/vnd.github+json" \
-            -H "X-GitHub-Api-Version: 2022-11-28" \
-            "/repos/${{ github.repository }}/releases")
-          echo tag=${tag} >> ${GITHUB_OUTPUT}
-
       # `neondatabase/neon` contains multiple binaries, all of them use the same input for the version into the same version formatting library.
       # Pick pageserver as currently the only binary with extra "version" features printed in the string to verify.
       # Regular pageserver version string looks like
@@ -856,20 +817,6 @@ 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: ${{ steps.get-last-compute-release-tag.outputs.tag }}
-        run: ./docker-compose/test_extensions_upgrade.sh
-
       - name: Print logs and clean up
         if: always()
         run: |
@@ -1103,7 +1050,6 @@ jobs:
           retries: 5
           script: |
             const tag = "${{ needs.tag.outputs.build-tag }}";
-            const branch = "${{ github.ref_name }}";
 
             try {
               const existingRef = await github.rest.git.getRef({
@@ -1146,48 +1092,12 @@ 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,
+                // TODO: Automate release notes properly
+                generate_release_notes: false,
               });
               console.log(`Release for tag ${tag} created successfully.`);
             }
@@ -1360,8 +1270,6 @@ jobs:
       - build-and-test-locally
       - check-codestyle-python
       - check-codestyle-rust
-      - check-dependencies-rust
-      - files-changed
       - promote-images-dev
       - test-images
       - trigger-custom-extensions-build-and-wait
@@ -1374,11 +1282,4 @@ jobs:
         if: |
           contains(needs.*.result, 'failure')
           || contains(needs.*.result, 'cancelled')
-          || (needs.check-dependencies-rust.result == 'skipped' && needs.files-changed.outputs.check-rust-dependencies == 'true')
-          || needs.build-and-test-locally.result == 'skipped'
-          || needs.check-codestyle-python.result == 'skipped'
-          || needs.check-codestyle-rust.result == 'skipped'
-          || needs.files-changed.result == 'skipped'
-          || needs.promote-images-dev.result == 'skipped'
-          || needs.test-images.result == 'skipped'
-          || needs.trigger-custom-extensions-build-and-wait.result == 'skipped'
+          || contains(needs.*.result, 'skipped')

.github/workflows/build_and_test_with_sanitizers.yml

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

.github/workflows/cargo-deny.yml

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

.github/workflows/ingest_benchmark.yml

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

.github/workflows/neon_extra_builds.yml

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

.github/workflows/pg-clients.yml

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

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

@@ -59,10 +59,7 @@ jobs:
           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:
@@ -95,8 +92,7 @@ jobs:
   # - 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
@@ -128,8 +124,6 @@ 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')

Cargo.toml

@@ -54,7 +54,6 @@ async-compression = { version = "0.4.0", features = ["tokio", "gzip", "zstd"] }
 atomic-take = "1.1.0"
 backtrace = "0.3.74"
 flate2 = "1.0.26"
-assert-json-diff = "2"
 async-stream = "0.3"
 async-trait = "0.1"
 aws-config = { version = "1.5", default-features = false, features=["rustls", "sso"] }
@@ -66,7 +65,7 @@ aws-smithy-types = "1.2"
 aws-credential-types = "1.2.0"
 aws-sigv4 = { version = "1.2", features = ["sign-http"] }
 aws-types = "1.3"
-axum = { version = "0.8.1", features = ["ws"] }
+axum = { version = "0.7.9", features = ["ws"] }
 base64 = "0.13.0"
 bincode = "1.3"
 bindgen = "0.70"
@@ -78,10 +77,10 @@ camino = "1.1.6"
 cfg-if = "1.0.0"
 chrono = { version = "0.4", default-features = false, features = ["clock"] }
 clap = { version = "4.0", features = ["derive", "env"] }
-clashmap = { version = "1.0", features = ["raw-api"] }
 comfy-table = "7.1"
 const_format = "0.2"
 crc32c = "0.6"
+dashmap = { version = "5.5.0", features = ["raw-api"] }
 diatomic-waker = { version = "0.2.3" }
 either = "1.8"
 enum-map = "2.4.2"
@@ -124,7 +123,7 @@ measured = { version = "0.0.22", features=["lasso"] }
 measured-process = { version = "0.0.22" }
 memoffset = "0.9"
 nix = { version = "0.27", features = ["dir", "fs", "process", "socket", "signal", "poll"] }
-notify = "8.0.0"
+notify = "6.0.0"
 num_cpus = "1.15"
 num-traits = "0.2.15"
 once_cell = "1.13"
@@ -178,7 +177,7 @@ test-context = "0.3"
 thiserror = "1.0"
 tikv-jemallocator = { version = "0.6", features = ["profiling", "stats", "unprefixed_malloc_on_supported_platforms"] }
 tikv-jemalloc-ctl = { version = "0.6", features = ["stats"] }
-tokio = { version = "1.41", features = ["macros"] }
+tokio = { version = "1.17", features = ["macros"] }
 tokio-epoll-uring = { git = "https://github.com/neondatabase/tokio-epoll-uring.git" , branch = "main" }
 tokio-io-timeout = "1.2.0"
 tokio-postgres-rustls = "0.12.0"
@@ -194,9 +193,7 @@ tower-http = { version = "0.6.2", features = ["request-id", "trace"] }
 tower-service = "0.3.3"
 tracing = "0.1"
 tracing-error = "0.2"
-tracing-log = "0.2"
 tracing-opentelemetry = "0.28"
-tracing-serde = "0.2.0"
 tracing-subscriber = { version = "0.3", default-features = false, features = ["smallvec", "fmt", "tracing-log", "std", "env-filter", "json"] }
 try-lock = "0.2.5"
 twox-hash = { version = "1.6.3", default-features = false }

Dockerfile

@@ -45,7 +45,7 @@ COPY --chown=nonroot . .
 
 ARG ADDITIONAL_RUSTFLAGS
 RUN set -e \
-    && RUSTFLAGS="-Clinker=clang -Clink-arg=-fuse-ld=mold -Clink-arg=-Wl,--no-rosegment -Cforce-frame-pointers=yes ${ADDITIONAL_RUSTFLAGS}" cargo build \
+    && PQ_LIB_DIR=$(pwd)/pg_install/v${STABLE_PG_VERSION}/lib RUSTFLAGS="-Clinker=clang -Clink-arg=-fuse-ld=mold -Clink-arg=-Wl,--no-rosegment -Cforce-frame-pointers=yes ${ADDITIONAL_RUSTFLAGS}" cargo build \
       --bin pg_sni_router  \
       --bin pageserver  \
       --bin pagectl  \
@@ -64,7 +64,6 @@ ARG DEFAULT_PG_VERSION
 WORKDIR /data
 
 RUN set -e \
-    && echo 'Acquire::Retries "5";' > /etc/apt/apt.conf.d/80-retries \
     && apt update \
     && apt install -y \
         libreadline-dev \
@@ -73,7 +72,6 @@ RUN set -e \
 	# System postgres for use with client libraries (e.g. in storage controller)
         postgresql-15 \
         openssl \
-    && rm -f /etc/apt/apt.conf.d/80-retries \
     && rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* \
     && useradd -d /data neon \
     && chown -R neon:neon /data

Makefile

@@ -10,29 +10,18 @@ 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
@@ -44,9 +33,7 @@ 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 +64,8 @@ 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 +108,7 @@ $(POSTGRES_INSTALL_DIR)/build/%/config.status:
 	EXTRA_VERSION=$$(cd $(ROOT_PROJECT_DIR)/vendor/postgres-$$VERSION && git rev-parse HEAD); \
 	(cd $(POSTGRES_INSTALL_DIR)/build/$$VERSION && \
 	env PATH="$(EXTRA_PATH_OVERRIDES):$$PATH" $(ROOT_PROJECT_DIR)/vendor/postgres-$$VERSION/configure \
-		CFLAGS='$(PG_CFLAGS)' LDFLAGS='$(PG_LDFLAGS)' \
+		CFLAGS='$(PG_CFLAGS)' \
 		$(PG_CONFIGURE_OPTS) --with-extra-version=" ($$EXTRA_VERSION)" \
 		--prefix=$(abspath $(POSTGRES_INSTALL_DIR))/$$VERSION > configure.log)
 

README.md

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

build-tools.Dockerfile

@@ -3,17 +3,6 @@ ARG DEBIAN_VERSION=bookworm
 FROM debian:bookworm-slim AS pgcopydb_builder
 ARG DEBIAN_VERSION
 
-# Use strict mode for bash to catch errors early
-SHELL ["/bin/bash", "-euo", "pipefail", "-c"]
-
-# By default, /bin/sh used in debian images will treat '\n' as eol,
-# but as we use bash as SHELL, and built-in echo in bash requires '-e' flag for that.
-RUN echo 'Acquire::Retries "5";' > /etc/apt/apt.conf.d/80-retries && \
-    echo -e "retry_connrefused = on\ntimeout=15\ntries=5\n" > /root/.wgetrc && \
-    echo -e "--retry-connrefused\n--connect-timeout 15\n--retry 5\n--max-time 300\n" > /root/.curlrc
-
-COPY build_tools/patches/pgcopydbv017.patch /pgcopydbv017.patch
-
 RUN if [ "${DEBIAN_VERSION}" = "bookworm" ]; then \
         set -e && \
         apt update && \
@@ -46,7 +35,6 @@ RUN if [ "${DEBIAN_VERSION}" = "bookworm" ]; then \
         mkdir /tmp/pgcopydb && \
         tar -xzf /tmp/pgcopydb.tar.gz -C /tmp/pgcopydb --strip-components=1 && \
         cd /tmp/pgcopydb && \
-        patch -p1 < /pgcopydbv017.patch && \
         make -s clean && \
         make -s -j12 install && \
         libpq_path=$(find /lib /usr/lib -name "libpq.so.5" | head -n 1) && \
@@ -63,8 +51,7 @@ ARG DEBIAN_VERSION
 
 # Add nonroot user
 RUN useradd -ms /bin/bash nonroot -b /home
-# Use strict mode for bash to catch errors early
-SHELL ["/bin/bash", "-euo", "pipefail", "-c"]
+SHELL ["/bin/bash", "-c"]
 
 RUN mkdir -p /pgcopydb/bin && \
     mkdir -p /pgcopydb/lib && \
@@ -74,10 +61,6 @@ RUN mkdir -p /pgcopydb/bin && \
 COPY --from=pgcopydb_builder /usr/lib/postgresql/16/bin/pgcopydb /pgcopydb/bin/pgcopydb
 COPY --from=pgcopydb_builder /pgcopydb/lib/libpq.so.5 /pgcopydb/lib/libpq.so.5
 
-RUN echo 'Acquire::Retries "5";' > /etc/apt/apt.conf.d/80-retries && \
-    echo -e "retry_connrefused = on\ntimeout=15\ntries=5\n" > /root/.wgetrc && \
-    echo -e "--retry-connrefused\n--connect-timeout 15\n--retry 5\n--max-time 300\n" > /root/.curlrc
-
 # System deps
 #
 # 'gdb' is included so that we get backtraces of core dumps produced in
@@ -199,14 +182,8 @@ 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 \
@@ -241,8 +218,6 @@ RUN wget -O /tmp/libicu-${ICU_VERSION}.tgz https://github.com/unicode-org/icu/re
 USER nonroot:nonroot
 WORKDIR /home/nonroot
 
-RUN echo -e "--retry-connrefused\n--connect-timeout 15\n--retry 5\n--max-time 300\n" > /home/nonroot/.curlrc
-
 # Python
 ENV PYTHON_VERSION=3.11.10 \
     PYENV_ROOT=/home/nonroot/.pyenv \
@@ -268,7 +243,7 @@ WORKDIR /home/nonroot
 
 # Rust
 # Please keep the version of llvm (installed above) in sync with rust llvm (`rustc --version --verbose | grep LLVM`)
-ENV RUSTC_VERSION=1.84.1
+ENV RUSTC_VERSION=1.84.0
 ENV RUSTUP_HOME="/home/nonroot/.rustup"
 ENV PATH="/home/nonroot/.cargo/bin:${PATH}"
 ARG RUSTFILT_VERSION=0.2.1
@@ -276,7 +251,6 @@ ARG CARGO_HAKARI_VERSION=0.9.33
 ARG CARGO_DENY_VERSION=0.16.2
 ARG CARGO_HACK_VERSION=0.6.33
 ARG CARGO_NEXTEST_VERSION=0.9.85
-ARG CARGO_DIESEL_CLI_VERSION=2.2.6
 RUN curl -sSO https://static.rust-lang.org/rustup/dist/$(uname -m)-unknown-linux-gnu/rustup-init && whoami && \
 	chmod +x rustup-init && \
 	./rustup-init -y --default-toolchain ${RUSTC_VERSION} && \
@@ -290,8 +264,6 @@ RUN curl -sSO https://static.rust-lang.org/rustup/dist/$(uname -m)-unknown-linux
     cargo install cargo-deny --locked --version ${CARGO_DENY_VERSION} && \
     cargo install cargo-hack          --version ${CARGO_HACK_VERSION} && \
     cargo install cargo-nextest       --version ${CARGO_NEXTEST_VERSION} && \
-    cargo install diesel_cli          --version ${CARGO_DIESEL_CLI_VERSION} \
-                                      --features postgres-bundled --no-default-features && \
     rm -rf /home/nonroot/.cargo/registry && \
     rm -rf /home/nonroot/.cargo/git
 

build_tools/patches/pgcopydbv017.patch

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

compute/etc/pgbouncer.ini

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

compute/patches/contrib_pg16.patch

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

compute/patches/contrib_pg17.patch

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

compute/patches/pg_graphql.patch

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

compute/vm-image-spec-bookworm.yaml

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

compute/vm-image-spec-bullseye.yaml

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

compute_tools/src/bin/compute_ctl.rs

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

compute_tools/src/bin/fast_import.rs

@@ -231,14 +231,6 @@ pub(crate) async fn main() -> anyhow::Result<()> {
         ])
         .env_clear()
         .env("LD_LIBRARY_PATH", &pg_lib_dir)
-        .env(
-            "ASAN_OPTIONS",
-            std::env::var("ASAN_OPTIONS").unwrap_or_default(),
-        )
-        .env(
-            "UBSAN_OPTIONS",
-            std::env::var("UBSAN_OPTIONS").unwrap_or_default(),
-        )
         .stdout(std::process::Stdio::piped())
         .stderr(std::process::Stdio::piped())
         .spawn()

compute_tools/src/compute.rs

@@ -59,8 +59,6 @@ pub static PG_PID: AtomicU32 = AtomicU32::new(0);
 
 /// Compute node info shared across several `compute_ctl` threads.
 pub struct ComputeNode {
-    /// The ID of the compute
-    pub compute_id: String,
     // Url type maintains proper escaping
     pub connstr: url::Url,
     // We connect to Postgres from many different places, so build configs once

compute_tools/src/extension_server.rs

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

compute_tools/src/http/extract/json.rs

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

compute_tools/src/http/extract/path.rs

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

compute_tools/src/http/extract/query.rs

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

compute_tools/src/http/openapi_spec.yaml

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

compute_tools/src/http/routes/info.rs

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

compute_tools/src/http/routes/installed_extensions.rs

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

compute_tools/src/http/routes/metrics.rs

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

compute_tools/src/http/routes/mod.rs

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

compute_tools/src/http/server.rs

@@ -22,7 +22,8 @@ use uuid::Uuid;
 
 use super::routes::{
     check_writability, configure, database_schema, dbs_and_roles, extension_server, extensions,
-    grants, insights, metrics, metrics_json, status, terminate,
+    grants, info as info_route, insights, installed_extensions, metrics, metrics_json, status,
+    terminate,
 };
 use crate::compute::ComputeNode;
 
@@ -54,12 +55,17 @@ async fn serve(port: u16, compute: Arc<ComputeNode>) {
         .route("/database_schema", get(database_schema::get_schema_dump))
         .route("/dbs_and_roles", get(dbs_and_roles::get_catalog_objects))
         .route(
-            "/extension_server/{*filename}",
+            "/extension_server/*filename",
             post(extension_server::download_extension),
         )
         .route("/extensions", post(extensions::install_extension))
         .route("/grants", post(grants::add_grant))
+        .route("/info", get(info_route::get_info))
         .route("/insights", get(insights::get_insights))
+        .route(
+            "/installed_extensions",
+            get(installed_extensions::get_installed_extensions),
+        )
         .route("/metrics", get(metrics::get_metrics))
         .route("/metrics.json", get(metrics_json::get_metrics))
         .route("/status", get(status::get_status))

compute_tools/src/installed_extensions.rs

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

compute_tools/src/lib.rs

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

compute_tools/src/metrics.rs

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

compute_tools/src/migration.rs

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

compute_tools/src/spec.rs

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

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/endpoint.rs

@@ -665,22 +665,6 @@ impl Endpoint {
                     .to_str()
                     .unwrap(),
             ])
-            // TODO: It would be nice if we generated compute IDs with the same
-            // algorithm as the real control plane.
-            //
-            // TODO: Add this back when
-            // https://github.com/neondatabase/neon/pull/10747 is merged.
-            //
-            //.args([
-            //    "--compute-id",
-            //    &format!(
-            //        "compute-{}",
-            //        SystemTime::now()
-            //            .duration_since(UNIX_EPOCH)
-            //            .unwrap()
-            //            .as_secs()
-            //    ),
-            //])
             .stdin(std::process::Stdio::null())
             .stderr(logfile.try_clone()?)
             .stdout(logfile);

control_plane/src/pageserver.rs

@@ -347,11 +347,6 @@ impl PageServerNode {
                 .map(|x| x.parse::<usize>())
                 .transpose()
                 .context("Failed to parse 'compaction_threshold' as an integer")?,
-            compaction_upper_limit: settings
-                .remove("compaction_upper_limit")
-                .map(|x| x.parse::<usize>())
-                .transpose()
-                .context("Failed to parse 'compaction_upper_limit' as an integer")?,
             compaction_algorithm: settings
                 .remove("compaction_algorithm")
                 .map(serde_json::from_str)
@@ -362,11 +357,6 @@ impl PageServerNode {
                 .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>())
@@ -388,11 +378,6 @@ impl PageServerNode {
                 .map(|x| x.parse::<u8>())
                 .transpose()
                 .context("Failed to parse 'image_creation_check_threshold' as integer")?,
-            image_creation_preempt_threshold: settings
-                .remove("image_creation_preempt_threshold")
-                .map(|x| x.parse::<usize>())
-                .transpose()
-                .context("Failed to parse 'image_creation_preempt_threshold' as integer")?,
             pitr_interval: settings.remove("pitr_interval").map(|x| x.to_string()),
             walreceiver_connect_timeout: settings
                 .remove("walreceiver_connect_timeout")

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");

control_plane/storcon_cli/src/main.rs

@@ -10,8 +10,8 @@ use pageserver_api::{
     controller_api::{
         AvailabilityZone, NodeAvailabilityWrapper, NodeDescribeResponse, NodeShardResponse,
         SafekeeperDescribeResponse, SafekeeperSchedulingPolicyRequest, ShardSchedulingPolicy,
-        ShardsPreferredAzsRequest, ShardsPreferredAzsResponse, SkSchedulingPolicy,
-        TenantCreateRequest, TenantDescribeResponse, TenantPolicyRequest,
+        ShardsPreferredAzsRequest, SkSchedulingPolicy, TenantCreateRequest, TenantDescribeResponse,
+        TenantPolicyRequest,
     },
     models::{
         EvictionPolicy, EvictionPolicyLayerAccessThreshold, LocationConfigSecondary,
@@ -800,7 +800,7 @@ async fn main() -> anyhow::Result<()> {
                     .collect(),
             };
             storcon_client
-                .dispatch::<ShardsPreferredAzsRequest, ShardsPreferredAzsResponse>(
+                .dispatch::<ShardsPreferredAzsRequest, ()>(
                     Method::PUT,
                     "control/v1/preferred_azs".to_string(),
                     Some(req),

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 +7,11 @@ 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   \
                        netcat-openbsd
 #This is required for the pg_hintplan test
-RUN mkdir -p /ext-src/pg_hint_plan-src /postgres/contrib/file_fdw && chown postgres /ext-src/pg_hint_plan-src /postgres/contrib/file_fdw
+RUN mkdir -p /ext-src/pg_hint_plan-src && chown postgres /ext-src/pg_hint_plan-src 
 
-USER postgres
+USER postgres

docker-compose/compute_wrapper/shell/compute.sh

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

docker-compose/docker-compose.yml

@@ -149,13 +149,11 @@ services:
       args:
         - REPOSITORY=${REPOSITORY:-neondatabase}
         - COMPUTE_IMAGE=compute-node-v${PG_VERSION:-16}
-        - TAG=${COMPUTE_TAG:-${TAG:-latest}}
+        - TAG=${TAG:-latest}
         - http_proxy=${http_proxy:-}
         - https_proxy=${https_proxy:-}
     environment:
       - PG_VERSION=${PG_VERSION:-16}
-      - TENANT_ID=${TENANT_ID:-}
-      - TIMELINE_ID=${TIMELINE_ID:-}
       #- RUST_BACKTRACE=1
     # Mount the test files directly, for faster editing cycle.
     volumes:

docker-compose/docker_compose_test.sh

@@ -31,7 +31,7 @@ for pg_version in ${TEST_VERSION_ONLY-14 15 16 17}; do
     echo "clean up containers if exists"
     cleanup
     PG_TEST_VERSION=$((pg_version < 16 ? 16 : pg_version))
-    PG_VERSION=$pg_version PG_TEST_VERSION=$PG_TEST_VERSION docker compose --profile test-extensions -f $COMPOSE_FILE up --quiet-pull --build -d
+    PG_VERSION=$pg_version PG_TEST_VERSION=$PG_TEST_VERSION docker compose --profile test-extensions -f $COMPOSE_FILE up --build -d
 
     echo "wait until the compute is ready. timeout after 60s. "
     cnt=0
@@ -51,8 +51,6 @@ for pg_version in ${TEST_VERSION_ONLY-14 15 16 17}; do
     done
 
     if [ $pg_version -ge 16 ]; then
-        docker cp ext-src $TEST_CONTAINER_NAME:/
-        docker exec $TEST_CONTAINER_NAME bash -c "apt update && apt install -y libtap-parser-sourcehandler-pgtap-perl"
         # This is required for the pg_hint_plan test, to prevent flaky log message causing the test to fail
         # It cannot be moved to Dockerfile now because the database directory is created after the start of the container
         echo Adding dummy config
@@ -62,32 +60,17 @@ for pg_version in ${TEST_VERSION_ONLY-14 15 16 17}; do
         docker cp $TEST_CONTAINER_NAME:/ext-src/pg_hint_plan-src/data $TMPDIR/data
         docker cp $TMPDIR/data $COMPUTE_CONTAINER_NAME:/ext-src/pg_hint_plan-src/
         rm -rf $TMPDIR
-        # The following block does the same for the contrib/file_fdw test
-        TMPDIR=$(mktemp -d)
-        docker cp $TEST_CONTAINER_NAME:/postgres/contrib/file_fdw/data $TMPDIR/data
-        docker cp $TMPDIR/data $COMPUTE_CONTAINER_NAME:/postgres/contrib/file_fdw/data
-        rm -rf $TMPDIR
-        # Apply patches
-        cat ../compute/patches/contrib_pg${pg_version}.patch | docker exec -i $TEST_CONTAINER_NAME bash -c "(cd /postgres && patch -p1)"
         # We are running tests now
-        rm -f testout.txt testout_contrib.txt
-        docker exec -e USE_PGXS=1 -e SKIP=timescaledb-src,rdkit-src,postgis-src,pgx_ulid-src,pgtap-src,pg_tiktoken-src,pg_jsonschema-src,kq_imcx-src,wal2json_2_5-src \
-        $TEST_CONTAINER_NAME /run-tests.sh /ext-src | tee testout.txt && EXT_SUCCESS=1 || EXT_SUCCESS=0
-        docker exec -e SKIP=start-scripts,postgres_fdw,ltree_plpython,jsonb_plpython,jsonb_plperl,hstore_plpython,hstore_plperl,dblink,bool_plperl \
-        $TEST_CONTAINER_NAME /run-tests.sh /postgres/contrib | tee testout_contrib.txt && CONTRIB_SUCCESS=1 || CONTRIB_SUCCESS=0
-        if [ $EXT_SUCCESS -eq 0 ] || [ $CONTRIB_SUCCESS -eq 0 ]; then
-            CONTRIB_FAILED=
-            FAILED=
-            [ $EXT_SUCCESS -eq 0 ] && FAILED=$(tail -1 testout.txt | awk '{for(i=1;i<=NF;i++){print "/ext-src/"$i;}}')
-            [ $CONTRIB_SUCCESS -eq 0 ] && CONTRIB_FAILED=$(tail -1 testout_contrib.txt | awk '{for(i=0;i<=NF;i++){print "/postgres/contrib/"$i;}}')
-            for d in $FAILED $CONTRIB_FAILED; do
-                dn="$(basename $d)"
-                rm -rf $dn
-                mkdir $dn
-                docker cp $TEST_CONTAINER_NAME:$d/regression.diffs $dn || [ $? -eq 1 ]
-                docker cp $TEST_CONTAINER_NAME:$d/regression.out $dn || [ $? -eq 1 ]
-                cat $dn/regression.out $dn/regression.diffs || true
-                rm -rf $dn
+        if ! docker exec -e SKIP=timescaledb-src,rdkit-src,postgis-src,pgx_ulid-src,pgtap-src,pg_tiktoken-src,pg_jsonschema-src,pg_graphql-src,kq_imcx-src,wal2json_2_5-src \
+            $TEST_CONTAINER_NAME /run-tests.sh | tee testout.txt
+        then
+            FAILED=$(tail -1 testout.txt)
+            for d in $FAILED
+            do
+                mkdir $d
+                docker cp $TEST_CONTAINER_NAME:/ext-src/$d/regression.diffs $d || true
+                docker cp $TEST_CONTAINER_NAME:/ext-src/$d/regression.out $d || true
+                cat $d/regression.out $d/regression.diffs || true
             done
         rm -rf $FAILED
         exit 1

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

docker-compose/run-tests.sh

@@ -1,22 +1,17 @@
 #!/bin/bash
 set -x
 
-extdir=${1}
-
-cd "${extdir}" || exit 2
+cd /ext-src || exit 2
 FAILED=
-LIST=$( (echo -e "${SKIP//","/"\n"}"; ls) | sort | uniq -u)
-for d in ${LIST}; do
-    [ -d "${d}" ] || continue
-    if ! psql -w -c "select 1" >/dev/null; then
-      FAILED="${d} ${FAILED}"
-      break
-    fi
-    if [ -f "${d}/neon-test.sh" ]; then
-       "${d}/neon-test.sh" || FAILED="${d} ${FAILED}"
-    else
+LIST=$( (echo -e "${SKIP//","/"\n"}"; ls -d -- *-src) | sort | uniq -u)
+for d in ${LIST}
+do
+       [ -d "${d}" ] || continue
+       if ! psql -w -c "select 1" >/dev/null; then
+          FAILED="${d} ${FAILED}"
+          break
+       fi
        USE_PGXS=1 make -C "${d}" installcheck || FAILED="${d} ${FAILED}"
-    fi
 done
 [ -z "${FAILED}" ] && exit 0
 echo "${FAILED}"

docker-compose/test_extensions_upgrade.sh

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

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

@@ -285,10 +285,10 @@ To summarize, list of cplane changes:
 
 ### storage_controller implementation
 
-If desired, we may continue using current 'load everything on startup and keep
-in memory' approach: single timeline shouldn't take more than 100 bytes (it's 16
-byte tenant_id, 16 byte timeline_id, int generation, vec of ~3 safekeeper ids
-plus some flags), so 10^6 of timelines shouldn't take more than 100MB.
+Current 'load everything on startup and keep in memory' easy design is fine.
+Single timeline shouldn't take more than 100 bytes (it's 16 byte tenant_id, 16
+byte timeline_id, int generation, vec of ~3 safekeeper ids plus some flags), so
+10^6 of timelines shouldn't take more than 100MB.
 
 Similar to pageserver attachment Intents storage_controller would have in-memory
 `MigrationRequest` (or its absense) for each timeline and pool of tasks trying
@@ -296,7 +296,7 @@ to make these request reality; this ensures one instance of storage_controller
 won't do several migrations on the same timeline concurrently. In the first
 version it is simpler to have more manual control and no retries, i.e. migration
 failure removes the request. Later we can build retries and automatic
-scheduling/migration around. `MigrationRequest` is
+scheduling/migration. `MigrationRequest` is
 ```
 enum MigrationRequest {
     To(Vec<NodeId>),
@@ -313,9 +313,9 @@ similarly, in the first version it is ok to trigger it manually).
 #### Schema
 
 `safekeepers` table mirroring current `nodes` should be added, except that for
-`scheduling_policy`: it is enough to have at least in the beginning only 3
-fields: 1) `active` 2) `paused` (initially means only not assign new tlis there
-3) `decomissioned` (node is removed).
+`scheduling_policy` field (seems like `status` is a better name for it): it is enough
+to have at least in the beginning only 3 fields: 1) `active` 2) `offline` 3)
+`decomissioned`.
 
 `timelines` table:
 ```
@@ -324,24 +324,18 @@ table! {
     timelines (tenant_id, timeline_id) {
         timeline_id -> Varchar,
         tenant_id -> Varchar,
-        start_lsn -> pg_lsn,
         generation -> Int4,
         sk_set -> Array<Int4>, // list of safekeeper ids
-        new_sk_set -> Nullable<Array<Int8>>, // list of safekeeper ids, null if not joint conf
+        new_sk_set -> Nullable<Array<Int4>>, // list of safekeeper ids, null if not joint conf
         cplane_notified_generation -> Int4,
-        deleted_at -> Nullable<Timestamptz>,
     }
 }
 ```
 
-`start_lsn` is needed to create timeline on safekeepers properly, see below. We
-might also want to add ancestor_timeline_id to preserve the hierarchy, but for
-this RFC it is not needed.
-
 #### API
 
 Node management is similar to pageserver:
-1) POST `/control/v1/safekeepers` inserts safekeeper.
+1) POST `/control/v1/safekeepers` upserts safekeeper.
 2) GET `/control/v1/safekeepers` lists safekeepers.
 3) GET `/control/v1/safekeepers/:node_id` gets safekeeper.
 4) PUT `/control/v1/safekepers/:node_id/status` changes status to e.g.
@@ -351,15 +345,25 @@ Node management is similar to pageserver:
 Safekeeper deploy scripts should register safekeeper at storage_contorller as
 they currently do with cplane, under the same id.
 
-Timeline creation/deletion will work through already existing POST and DELETE
-`tenant/:tenant_id/timeline`. Cplane is expected to retry both until they
-succeed. See next section on the implementation details.
+Timeline creation/deletion: already existing POST `tenant/:tenant_id/timeline`
+would 1) choose initial set of safekeepers; 2) write to the db initial
+`Configuration` with `INSERT ON CONFLICT DO NOTHING` returning existing row in
+case of conflict; 3) create timeline on the majority of safekeepers (already
+created is ok).
 
-We don't want to block timeline creation/deletion when one safekeeper is down.
-Currently this is crutched by compute implicitly creating timeline on any
-safekeeper it is connected to. This creates ugly timeline state on safekeeper
-when timeline is created, but start LSN is not defined yet. Next section
-describes dealing with this.
+We don't want to block timeline creation when one safekeeper is down. Currently
+this is solved by compute implicitly creating timeline on any safekeeper it is
+connected to. This creates ugly timeline state on safekeeper when timeline is
+created, but start LSN is not defined yet. It would be nice to remove this; to
+do that, controller can in the background retry to create timeline on
+safekeeper(s) which missed that during initial creation call. It can do that
+through `pull_timeline` from majority so it doesn't need to remember
+`parent_lsn` in its db.
+
+Timeline deletion removes the row from the db and forwards deletion to the
+current configuration members. Without additional actions deletions might leak,
+see below on this; initially let's ignore these, reporting to cplane success if
+at least one safekeeper deleted the timeline (this will remove s3 data).
 
 Tenant deletion repeats timeline deletion for all timelines.
 
@@ -391,6 +395,26 @@ Similar call should be added for the tenant.
 It would be great to have some way of subscribing to the results (apart from
 looking at logs/metrics).
 
+Migration is executed as described above. One subtlety is that (local) deletion on
+source safekeeper might fail, which is not a problem if we are going to
+decomission the node but leaves garbage otherwise. I'd propose in the first version
+1) Don't attempt deletion at all if node status is `offline`.
+2) If it failed, just issue warning.
+And add PUT `/control/v1/safekeepers/:node_id/scrub` endpoint which would find and
+remove garbage timelines for manual use. It will 1) list all timelines on the
+safekeeper 2) compare each one against configuration storage: if timeline
+doesn't exist at all (had been deleted), it can be deleted. Otherwise, it can
+be deleted under generation number if node is not member of current generation.
+
+Automating this is untrivial; we'd need to register all potential missing
+deletions <tenant_id, timeline_id, generation, node_id> in the same transaction
+which switches configurations. Similarly when timeline is fully deleted to
+prevent cplane operation from blocking when some safekeeper is not available
+deletion should be also registered.
+
+One more task pool should infinitely retry notifying control plane about changed
+safekeeper sets.
+
 3) GET `/control/v1/tenant/:tenant_id/timeline/:timeline_id/` should return
    current in memory state of the timeline and pending `MigrationRequest`,
    if any.
@@ -399,153 +423,12 @@ looking at logs/metrics).
    migration by switching configuration from the joint to the one with (previous) `sk_set` under CAS
    (incrementing generation as always).
 
-#### API implementation and reconciliation
-
-For timeline creation/deletion we want to preserve the basic assumption that
-unreachable minority (1 sk of 3) doesn't block their completion, but eventually
-we want to finish creation/deletion on nodes which missed it (unless they are
-removed). Similarly for migration; it may and should finish even though excluded
-members missed their exclusion. And of course e.g. such pending exclusion on
-node C after migration ABC -> ABD must not prevent next migration ABD -> ABE. As
-another example, if some node missed timeline creation it clearly must not block
-migration from it. Hence it is natural to have per safekeeper background
-reconciler which retries these ops until they succeed. There are 3 possible
-operation types, and the type is defined by timeline state (membership
-configuration and whether it is deleted) and safekeeper id: we may need to
-create timeline on sk (node added), locally delete it (node excluded, somewhat
-similar to detach) or globally delete it (timeline is deleted).
-
-Next, on storage controller restart in principle these pending operations can be
-figured out by comparing safekeepers state against storcon state. But it seems
-better to me to materialize them in the database; it is not expensive, avoids
-these startup scans which themselves can fail etc and makes it very easy to see
-outstanding work directly at the source of truth -- the db. So we can add table
-`safekeeper_timeline_pending_ops`
-```
-table! {
-    // timeline_id, sk_id is primary key
-    safekeeper_timeline_pending_ops (sk_id, tenant_id, timeline_id) {
-        sk_id -> int8,
-        tenant_id -> Varchar,
-        timeline_id -> Varchar,
-        generation -> Int4,
-        op_type -> Varchar,
-    }
-}
-```
-
-`op_type` can be `include` (seed from peers and ensure generation is up to
-date), `exclude` (remove locally) and `delete`. Field is actually not strictly
-needed as it can be computed from current configuration, but gives more explicit
-observability.
-
-`generation` is necessary there because after op is done reconciler must remove
-it and not remove another row with higher gen which in theory might appear.
-
-Any insert of row should overwrite (remove) all rows with the same sk and
-timeline id but lower `generation` as next op makes previous obsolete. Insertion
-of `op_type` `delete` overwrites all rows.
-
-About `exclude`: rather than adding explicit safekeeper http endpoint, it is
-reasonable to reuse membership switch endpoint: if safekeeper is not member
-of the configuration it locally removes the timeline on the switch. In this case
-404 should also be considered an 'ok' answer by the caller.
-
-So, main loop of per sk reconcile reads `safekeeper_timeline_pending_ops`
-joined with timeline configuration to get current conf (with generation `n`)
-for the safekeeper and does the jobs, infinitely retrying failures:
-1) If node is member (`include`):
-  - Check if timeline exists on it, if not, call pull_timeline on it from 
-     other members
-  - Call switch configuration to the current
-2) If node is not member (`exclude`):
-  - Call switch configuration to the current, 404 is ok.
-3) If timeline is deleted (`delete`), call delete.
-
-In cases 1 and 2 remove `safekeeper_timeline_pending_ops` for the sk and 
-timeline with generation <= `n` if `op_type` is not `delete`.
-In case 3 also remove `safekeeper_timeline_pending_ops` 
-entry + remove `timelines` entry if there is nothing left  in `safekeeper_timeline_pending_ops` for the timeline.
-
-Let's consider in details how APIs can be implemented from this angle.
-
-Timeline creation. It is assumed that cplane retries it until success, so all
-actions must be idempotent. Now, a tricky point here is timeline start LSN. For
-the initial (tenant creation) call cplane doesn't know it. However, setting
-start_lsn on safekeepers during creation is a good thing -- it provides a
-guarantee that walproposer can always find a common point in WAL histories of
-safekeeper and its own, and so absense of it would be a clear sign of
-corruption. The following sequence works:
-1) Create timeline (or observe that it exists) on pageserver,
-   figuring out last_record_lsn in response.
-2) Choose safekeepers and insert (ON CONFLICT DO NOTHING) timeline row into the
-   db. Note that last_record_lsn returned on the previous step is movable as it
-   changes once ingestion starts, insert must not overwrite it (as well as other
-   fields like membership conf). On the contrary, start_lsn used in the next
-   step must be set to the value in the db. cplane_notified_generation can be set
-   to 1 (initial generation) in insert to avoid notifying cplane about initial 
-   conf as cplane will receive it in timeline creation request anyway.
-3) Issue timeline creation calls to at least majority of safekeepers. Using
-   majority here is not necessary but handy because it guarantees that any live
-   majority will have at least one sk with created timeline and so
-   reconciliation task can use pull_timeline shared with migration instead of
-   create timeline special init case. OFC if timeline is already exists call is
-   ignored.
-4) For minority of safekeepers which could have missed creation insert
-   entries to `safekeeper_timeline_pending_ops`. We won't miss this insertion 
-   because response to cplane is sent only after it has happened, and cplane 
-   retries the call until 200 response.
-
-   There is a small question how request handler (timeline creation in this
-   case) would interact with per sk reconciler. As always I prefer to do the
-   simplest possible thing and here it seems to be just waking it up so it
-   re-reads the db for work to do. Passing work in memory is faster, but
-   that shouldn't matter, and path to scan db for work will exist anyway, 
-   simpler to reuse it.
-
-For pg version / wal segment size: while we may persist them in `timelines`
-table, it is not necessary as initial creation at step 3 can take them from
-pageserver or cplane creation call and later pull_timeline will carry them
-around.
-
-Timeline migration.
-1) CAS to the db to create joint conf, and in the same transaction create
-   `safekeeper_timeline_pending_ops` `include` entries to initialize new members
-   as well as deliver this conf to current ones; poke per sk reconcilers to work
-   on it. Also any conf change should also poke cplane notifier task(s).
-2) Once it becomes possible per alg description above, get out of joint conf
-   with another CAS. Task should get wakeups from per sk reconcilers because 
-   conf switch is required for advancement; however retries should be sleep
-   based as well as LSN advancement might be needed, though in happy path 
-   it isn't. To see whether further transition is possible on wakup migration
-   executor polls safekeepers per the algorithm. CAS creating new conf with only
-   new members should again insert entries to `safekeeper_timeline_pending_ops`
-   to switch them there, as well as `exclude` rows to remove timeline from 
-   old members.
-
-Timeline deletion: just set `deleted_at` on the timeline row and insert
-`safekeeper_timeline_pending_ops` entries in the same xact, the rest is done by
-per sk reconcilers.
-
-When node is removed (set to `decomissioned`), `safekeeper_timeline_pending_ops`
-for it must be cleared in the same transaction.
-
-One more task pool should infinitely retry notifying control plane about changed
-safekeeper sets (trying making `cplane_notified_generation` equal `generation`).
-
 #### Dealing with multiple instances of storage_controller
 
 Operations described above executed concurrently might create some errors but do
 not prevent progress, so while we normally don't want to run multiple instances
 of storage_controller it is fine to have it temporarily, e.g. during redeploy.
 
-To harden against some controller instance creating some work in
-`safekeeper_timeline_pending_ops` and then disappearing without anyone pickup up
-the job per sk reconcilers apart from explicit wakups should scan for work
-periodically. It is possible to remove that though if all db updates are
-protected with leadership token/term -- then such scans are needed only after
-leadership is acquired.
-
 Any interactions with db update in-memory controller state, e.g. if migration
 request failed because different one is in progress, controller remembers that
 and tries to finish it.
@@ -662,7 +545,7 @@ Aurora does this but similarly I don't think this is needed.
 
 We should use Compute <-> safekeeper protocol change to include other (long
 yearned) modifications:
-- send data in network order without putting whole structs to be arch independent
+- send data in network order to make arm work.
 - remove term_start_lsn from AppendRequest
 - add horizon to TermHistory
 - add to ProposerGreeting number of connection from this wp to sk

libs/compute_api/src/responses.rs

@@ -7,7 +7,7 @@ use serde::{Deserialize, Serialize, Serializer};
 
 use crate::{
     privilege::Privilege,
-    spec::{Database, ExtVersion, PgIdent, Role},
+    spec::{ComputeSpec, Database, ExtVersion, PgIdent, Role},
 };
 
 #[derive(Serialize, Debug, Deserialize)]
@@ -15,6 +15,11 @@ pub struct GenericAPIError {
     pub error: String,
 }
 
+#[derive(Debug, Clone, Serialize)]
+pub struct InfoResponse {
+    pub num_cpus: usize,
+}
+
 #[derive(Debug, Clone, Serialize)]
 pub struct ExtensionInstallResponse {
     pub extension: PgIdent,
@@ -135,6 +140,26 @@ pub struct CatalogObjects {
     pub databases: Vec<Database>,
 }
 
+/// Response of the `/computes/{compute_id}/spec` control-plane API.
+/// This is not actually a compute API response, so consider moving
+/// to a different place.
+#[derive(Deserialize, Debug)]
+pub struct ControlPlaneSpecResponse {
+    pub spec: Option<ComputeSpec>,
+    pub status: ControlPlaneComputeStatus,
+}
+
+#[derive(Deserialize, Clone, Copy, Debug, PartialEq, Eq)]
+#[serde(rename_all = "snake_case")]
+pub enum ControlPlaneComputeStatus {
+    // Compute is known to control-plane, but it's not
+    // yet attached to any timeline / endpoint.
+    Empty,
+    // Compute is attached to some timeline / endpoint and
+    // should be able to start with provided spec.
+    Attached,
+}
+
 #[derive(Clone, Debug, Default, Serialize)]
 pub struct InstalledExtension {
     pub extname: String,

libs/compute_api/src/spec.rs

@@ -204,16 +204,14 @@ impl RemoteExtSpec {
 
         // Check if extension is present in public or custom.
         // If not, then it is not allowed to be used by this compute.
-        if !self
-            .public_extensions
-            .as_ref()
-            .is_some_and(|exts| exts.iter().any(|e| e == real_ext_name))
-            && !self
-                .custom_extensions
-                .as_ref()
-                .is_some_and(|exts| exts.iter().any(|e| e == real_ext_name))
-        {
-            return Err(anyhow::anyhow!("extension {} is not found", real_ext_name));
+        if let Some(public_extensions) = &self.public_extensions {
+            if !public_extensions.contains(&real_ext_name.to_string()) {
+                if let Some(custom_extensions) = &self.custom_extensions {
+                    if !custom_extensions.contains(&real_ext_name.to_string()) {
+                        return Err(anyhow::anyhow!("extension {} is not found", real_ext_name));
+                    }
+                }
+            }
         }
 
         match self.extension_data.get(real_ext_name) {
@@ -342,102 +340,6 @@ mod tests {
     use super::*;
     use std::fs::File;
 
-    #[test]
-    fn allow_installing_remote_extensions() {
-        let rspec: RemoteExtSpec = serde_json::from_value(serde_json::json!({
-            "public_extensions": null,
-            "custom_extensions": null,
-            "library_index": {},
-            "extension_data": {},
-        }))
-        .unwrap();
-
-        rspec
-            .get_ext("ext", false, "latest", "v17")
-            .expect_err("Extension should not be found");
-
-        let rspec: RemoteExtSpec = serde_json::from_value(serde_json::json!({
-            "public_extensions": [],
-            "custom_extensions": null,
-            "library_index": {},
-            "extension_data": {},
-        }))
-        .unwrap();
-
-        rspec
-            .get_ext("ext", false, "latest", "v17")
-            .expect_err("Extension should not be found");
-
-        let rspec: RemoteExtSpec = serde_json::from_value(serde_json::json!({
-            "public_extensions": [],
-            "custom_extensions": [],
-            "library_index": {
-                "ext": "ext"
-            },
-            "extension_data": {
-                "ext": {
-                    "control_data": {
-                        "ext.control": ""
-                    },
-                    "archive_path": ""
-                }
-            },
-        }))
-        .unwrap();
-
-        rspec
-            .get_ext("ext", false, "latest", "v17")
-            .expect_err("Extension should not be found");
-
-        let rspec: RemoteExtSpec = serde_json::from_value(serde_json::json!({
-            "public_extensions": [],
-            "custom_extensions": ["ext"],
-            "library_index": {
-                "ext": "ext"
-            },
-            "extension_data": {
-                "ext": {
-                    "control_data": {
-                        "ext.control": ""
-                    },
-                    "archive_path": ""
-                }
-            },
-        }))
-        .unwrap();
-
-        rspec
-            .get_ext("ext", false, "latest", "v17")
-            .expect("Extension should be found");
-
-        let rspec: RemoteExtSpec = serde_json::from_value(serde_json::json!({
-            "public_extensions": ["ext"],
-            "custom_extensions": [],
-            "library_index": {
-                "extlib": "ext",
-            },
-            "extension_data": {
-                "ext": {
-                    "control_data": {
-                        "ext.control": ""
-                    },
-                    "archive_path": ""
-                }
-            },
-        }))
-        .unwrap();
-
-        rspec
-            .get_ext("ext", false, "latest", "v17")
-            .expect("Extension should be found");
-
-        // test library index for the case when library name
-        // doesn't match the extension name
-        rspec
-            .get_ext("extlib", true, "latest", "v17")
-            .expect("Library should be found");
-    }
-
     #[test]
     fn parse_spec_file() {
         let file = File::open("tests/cluster_spec.json").unwrap();

libs/pageserver_api/src/config.rs

@@ -94,7 +94,6 @@ pub struct ConfigToml {
     pub ondemand_download_behavior_treat_error_as_warn: bool,
     #[serde(with = "humantime_serde")]
     pub background_task_maximum_delay: Duration,
-    pub use_compaction_semaphore: bool,
     pub control_plane_api: Option<reqwest::Url>,
     pub control_plane_api_token: Option<String>,
     pub control_plane_emergency_mode: bool,
@@ -122,7 +121,6 @@ pub struct ConfigToml {
     pub wal_receiver_protocol: PostgresClientProtocol,
     pub page_service_pipelining: PageServicePipeliningConfig,
     pub get_vectored_concurrent_io: GetVectoredConcurrentIo,
-    pub enable_read_path_debugging: Option<bool>,
 }
 
 #[derive(Debug, Clone, PartialEq, Eq, serde::Serialize, serde::Deserialize)]
@@ -258,24 +256,16 @@ pub struct TenantConfigToml {
     pub compaction_period: Duration,
     /// Level0 delta layer threshold for compaction.
     pub compaction_threshold: usize,
-    /// Controls the amount of L0 included in a single compaction iteration.
-    /// The unit is `checkpoint_distance`, i.e., a size.
-    /// We add L0s to the set of layers to compact until their cumulative
-    /// size exceeds `compaction_upper_limit * checkpoint_distance`.
-    pub compaction_upper_limit: usize,
     pub compaction_algorithm: crate::models::CompactionAlgorithmSettings,
     /// Level0 delta layer threshold at which to delay layer flushes for compaction backpressure,
     /// such that they take 2x as long, and start waiting for layer flushes during ephemeral layer
     /// rolls. This helps compaction keep up with WAL ingestion, and avoids read amplification
-    /// blowing up. Should be >compaction_threshold. 0 to disable. Disabled by default.
+    /// blowing up. Should be >compaction_threshold. If None, defaults to 2 * compaction_threshold.
+    /// 0 to disable.
     pub l0_flush_delay_threshold: Option<usize>,
-    /// Level0 delta layer threshold at which to stall layer flushes. Must be >compaction_threshold
-    /// to avoid deadlock. 0 to disable. Disabled by default.
+    /// Level0 delta layer threshold at which to stall layer flushes. 0 to disable. If None,
+    /// defaults to 4 * compaction_threshold. Must be >compaction_threshold to avoid deadlock.
     pub l0_flush_stall_threshold: Option<usize>,
-    /// If true, Level0 delta layer flushes will wait for S3 upload before flushing the next
-    /// layer. This is a temporary backpressure mechanism which should be removed once
-    /// l0_flush_{delay,stall}_threshold is fully enabled.
-    pub l0_flush_wait_upload: bool,
     // Determines how much history is retained, to allow
     // branching and read replicas at an older point in time.
     // The unit is #of bytes of WAL.
@@ -325,10 +315,6 @@ pub struct TenantConfigToml {
     // Expresed in multiples of checkpoint distance.
     pub image_layer_creation_check_threshold: u8,
 
-    // How many multiples of L0 `compaction_threshold` will preempt image layer creation and do L0 compaction.
-    // Set to 0 to disable preemption.
-    pub image_creation_preempt_threshold: usize,
-
     /// The length for an explicit LSN lease request.
     /// Layers needed to reconstruct pages at LSN will not be GC-ed during this interval.
     #[serde(with = "humantime_serde")]
@@ -472,7 +458,6 @@ impl Default for ConfigToml {
                 DEFAULT_BACKGROUND_TASK_MAXIMUM_DELAY,
             )
             .unwrap()),
-            use_compaction_semaphore: false,
 
             control_plane_api: (None),
             control_plane_api_token: (None),
@@ -513,11 +498,6 @@ impl Default for ConfigToml {
             } else {
                 GetVectoredConcurrentIo::SidecarTask
             },
-            enable_read_path_debugging: if cfg!(test) || cfg!(feature = "testing") {
-                Some(true)
-            } else {
-                None
-            },
         }
     }
 }
@@ -540,17 +520,9 @@ pub mod tenant_conf_defaults {
 
     pub const DEFAULT_COMPACTION_PERIOD: &str = "20 s";
     pub const DEFAULT_COMPACTION_THRESHOLD: usize = 10;
-
-    // This value needs to be tuned to avoid OOM. We have 3/4 of the total CPU threads to do background works, that's 16*3/4=9 on
-    // most of our pageservers. Compaction ~50 layers requires about 2GB memory (could be reduced later by optimizing L0 hole
-    // calculation to avoid loading all keys into the memory). So with this config, we can get a maximum peak compaction usage of 18GB.
-    pub const DEFAULT_COMPACTION_UPPER_LIMIT: usize = 50;
-
     pub const DEFAULT_COMPACTION_ALGORITHM: crate::models::CompactionAlgorithm =
         crate::models::CompactionAlgorithm::Legacy;
 
-    pub const DEFAULT_L0_FLUSH_WAIT_UPLOAD: bool = true;
-
     pub const DEFAULT_GC_HORIZON: u64 = 64 * 1024 * 1024;
 
     // Large DEFAULT_GC_PERIOD is fine as long as PITR_INTERVAL is larger.
@@ -559,10 +531,6 @@ pub mod tenant_conf_defaults {
     // Relevant: https://github.com/neondatabase/neon/issues/3394
     pub const DEFAULT_GC_PERIOD: &str = "1 hr";
     pub const DEFAULT_IMAGE_CREATION_THRESHOLD: usize = 3;
-    // If there are more than threshold * compaction_threshold (that is 3 * 10 in the default config) L0 layers, image
-    // layer creation will end immediately. Set to 0 to disable. The target default will be 3 once we
-    // want to enable this feature.
-    pub const DEFAULT_IMAGE_CREATION_PREEMPT_THRESHOLD: usize = 0;
     pub const DEFAULT_PITR_INTERVAL: &str = "7 days";
     pub const DEFAULT_WALRECEIVER_CONNECT_TIMEOUT: &str = "10 seconds";
     pub const DEFAULT_WALRECEIVER_LAGGING_WAL_TIMEOUT: &str = "10 seconds";
@@ -590,13 +558,11 @@ impl Default for TenantConfigToml {
             compaction_period: humantime::parse_duration(DEFAULT_COMPACTION_PERIOD)
                 .expect("cannot parse default compaction period"),
             compaction_threshold: DEFAULT_COMPACTION_THRESHOLD,
-            compaction_upper_limit: DEFAULT_COMPACTION_UPPER_LIMIT,
             compaction_algorithm: crate::models::CompactionAlgorithmSettings {
                 kind: DEFAULT_COMPACTION_ALGORITHM,
             },
             l0_flush_delay_threshold: None,
             l0_flush_stall_threshold: None,
-            l0_flush_wait_upload: DEFAULT_L0_FLUSH_WAIT_UPLOAD,
             gc_horizon: DEFAULT_GC_HORIZON,
             gc_period: humantime::parse_duration(DEFAULT_GC_PERIOD)
                 .expect("cannot parse default gc period"),
@@ -621,7 +587,6 @@ impl Default for TenantConfigToml {
             lazy_slru_download: false,
             timeline_get_throttle: crate::models::ThrottleConfig::disabled(),
             image_layer_creation_check_threshold: DEFAULT_IMAGE_LAYER_CREATION_CHECK_THRESHOLD,
-            image_creation_preempt_threshold: DEFAULT_IMAGE_CREATION_PREEMPT_THRESHOLD,
             lsn_lease_length: LsnLease::DEFAULT_LENGTH,
             lsn_lease_length_for_ts: LsnLease::DEFAULT_LENGTH_FOR_TS,
             timeline_offloading: false,

libs/pageserver_api/src/models.rs

@@ -458,8 +458,6 @@ pub struct TenantConfigPatch {
     pub compaction_period: FieldPatch<String>,
     #[serde(skip_serializing_if = "FieldPatch::is_noop")]
     pub compaction_threshold: FieldPatch<usize>,
-    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
-    pub compaction_upper_limit: FieldPatch<usize>,
     // defer parsing compaction_algorithm, like eviction_policy
     #[serde(skip_serializing_if = "FieldPatch::is_noop")]
     pub compaction_algorithm: FieldPatch<CompactionAlgorithmSettings>,
@@ -468,8 +466,6 @@ pub struct TenantConfigPatch {
     #[serde(skip_serializing_if = "FieldPatch::is_noop")]
     pub l0_flush_stall_threshold: FieldPatch<usize>,
     #[serde(skip_serializing_if = "FieldPatch::is_noop")]
-    pub l0_flush_wait_upload: FieldPatch<bool>,
-    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
     pub gc_horizon: FieldPatch<u64>,
     #[serde(skip_serializing_if = "FieldPatch::is_noop")]
     pub gc_period: FieldPatch<String>,
@@ -498,8 +494,6 @@ pub struct TenantConfigPatch {
     #[serde(skip_serializing_if = "FieldPatch::is_noop")]
     pub image_layer_creation_check_threshold: FieldPatch<u8>,
     #[serde(skip_serializing_if = "FieldPatch::is_noop")]
-    pub image_creation_preempt_threshold: FieldPatch<usize>,
-    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
     pub lsn_lease_length: FieldPatch<String>,
     #[serde(skip_serializing_if = "FieldPatch::is_noop")]
     pub lsn_lease_length_for_ts: FieldPatch<String>,
@@ -526,12 +520,10 @@ pub struct TenantConfig {
     pub compaction_target_size: Option<u64>,
     pub compaction_period: Option<String>,
     pub compaction_threshold: Option<usize>,
-    pub compaction_upper_limit: Option<usize>,
     // defer parsing compaction_algorithm, like eviction_policy
     pub compaction_algorithm: Option<CompactionAlgorithmSettings>,
     pub l0_flush_delay_threshold: Option<usize>,
     pub l0_flush_stall_threshold: Option<usize>,
-    pub l0_flush_wait_upload: Option<bool>,
     pub gc_horizon: Option<u64>,
     pub gc_period: Option<String>,
     pub image_creation_threshold: Option<usize>,
@@ -546,7 +538,6 @@ pub struct TenantConfig {
     pub lazy_slru_download: Option<bool>,
     pub timeline_get_throttle: Option<ThrottleConfig>,
     pub image_layer_creation_check_threshold: Option<u8>,
-    pub image_creation_preempt_threshold: Option<usize>,
     pub lsn_lease_length: Option<String>,
     pub lsn_lease_length_for_ts: Option<String>,
     pub timeline_offloading: Option<bool>,
@@ -565,11 +556,9 @@ impl TenantConfig {
             mut compaction_target_size,
             mut compaction_period,
             mut compaction_threshold,
-            mut compaction_upper_limit,
             mut compaction_algorithm,
             mut l0_flush_delay_threshold,
             mut l0_flush_stall_threshold,
-            mut l0_flush_wait_upload,
             mut gc_horizon,
             mut gc_period,
             mut image_creation_threshold,
@@ -584,7 +573,6 @@ impl TenantConfig {
             mut lazy_slru_download,
             mut timeline_get_throttle,
             mut image_layer_creation_check_threshold,
-            mut image_creation_preempt_threshold,
             mut lsn_lease_length,
             mut lsn_lease_length_for_ts,
             mut timeline_offloading,
@@ -602,9 +590,6 @@ impl TenantConfig {
             .apply(&mut compaction_target_size);
         patch.compaction_period.apply(&mut compaction_period);
         patch.compaction_threshold.apply(&mut compaction_threshold);
-        patch
-            .compaction_upper_limit
-            .apply(&mut compaction_upper_limit);
         patch.compaction_algorithm.apply(&mut compaction_algorithm);
         patch
             .l0_flush_delay_threshold
@@ -612,7 +597,6 @@ impl TenantConfig {
         patch
             .l0_flush_stall_threshold
             .apply(&mut l0_flush_stall_threshold);
-        patch.l0_flush_wait_upload.apply(&mut l0_flush_wait_upload);
         patch.gc_horizon.apply(&mut gc_horizon);
         patch.gc_period.apply(&mut gc_period);
         patch
@@ -639,9 +623,6 @@ impl TenantConfig {
         patch
             .image_layer_creation_check_threshold
             .apply(&mut image_layer_creation_check_threshold);
-        patch
-            .image_creation_preempt_threshold
-            .apply(&mut image_creation_preempt_threshold);
         patch.lsn_lease_length.apply(&mut lsn_lease_length);
         patch
             .lsn_lease_length_for_ts
@@ -667,11 +648,9 @@ impl TenantConfig {
             compaction_target_size,
             compaction_period,
             compaction_threshold,
-            compaction_upper_limit,
             compaction_algorithm,
             l0_flush_delay_threshold,
             l0_flush_stall_threshold,
-            l0_flush_wait_upload,
             gc_horizon,
             gc_period,
             image_creation_threshold,
@@ -686,7 +665,6 @@ impl TenantConfig {
             lazy_slru_download,
             timeline_get_throttle,
             image_layer_creation_check_threshold,
-            image_creation_preempt_threshold,
             lsn_lease_length,
             lsn_lease_length_for_ts,
             timeline_offloading,
@@ -1037,13 +1015,6 @@ pub struct TenantConfigPatchRequest {
     pub config: TenantConfigPatch, // as we have a flattened field, we should reject all unknown fields in it
 }
 
-#[derive(Serialize, Deserialize, Debug)]
-pub struct TenantWaitLsnRequest {
-    #[serde(flatten)]
-    pub timelines: HashMap<TimelineId, Lsn>,
-    pub timeout: Duration,
-}
-
 /// See [`TenantState::attachment_status`] and the OpenAPI docs for context.
 #[derive(Serialize, Deserialize, Clone)]
 #[serde(tag = "slug", content = "data", rename_all = "snake_case")]

libs/postgres_ffi/wal_craft/src/lib.rs

@@ -76,15 +76,7 @@ impl Conf {
         let mut cmd = Command::new(path);
         cmd.env_clear()
             .env("LD_LIBRARY_PATH", self.pg_lib_dir()?)
-            .env("DYLD_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(),
-            );
+            .env("DYLD_LIBRARY_PATH", self.pg_lib_dir()?);
         Ok(cmd)
     }
 

libs/postgres_initdb/src/lib.rs

@@ -64,14 +64,6 @@ pub async fn do_run_initdb(args: RunInitdbArgs<'_>) -> Result<(), Error> {
         .env_clear()
         .env("LD_LIBRARY_PATH", library_search_path)
         .env("DYLD_LIBRARY_PATH", library_search_path)
-        .env(
-            "ASAN_OPTIONS",
-            std::env::var("ASAN_OPTIONS").unwrap_or_default(),
-        )
-        .env(
-            "UBSAN_OPTIONS",
-            std::env::var("UBSAN_OPTIONS").unwrap_or_default(),
-        )
         .stdin(std::process::Stdio::null())
         // stdout invocation produces the same output every time, we don't need it
         .stdout(std::process::Stdio::null())

libs/pq_proto/src/lib.rs

@@ -182,13 +182,6 @@ pub struct CancelKeyData {
     pub cancel_key: i32,
 }
 
-pub fn id_to_cancel_key(id: u64) -> CancelKeyData {
-    CancelKeyData {
-        backend_pid: (id >> 32) as i32,
-        cancel_key: (id & 0xffffffff) as i32,
-    }
-}
-
 impl fmt::Display for CancelKeyData {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
         let hi = (self.backend_pid as u64) << 32;

libs/proxy/tokio-postgres2/Cargo.toml

@@ -19,4 +19,3 @@ postgres-protocol2 = { path = "../postgres-protocol2" }
 postgres-types2 = { path = "../postgres-types2" }
 tokio = { workspace = true, features = ["io-util", "time", "net"] }
 tokio-util = { workspace = true, features = ["codec"] }
-serde = { workspace = true, features = ["derive"] }

libs/proxy/tokio-postgres2/src/cancel_token.rs

@@ -3,13 +3,12 @@ use crate::tls::TlsConnect;
 
 use crate::{cancel_query, client::SocketConfig, tls::MakeTlsConnect};
 use crate::{cancel_query_raw, Error};
-use serde::{Deserialize, Serialize};
 use tokio::io::{AsyncRead, AsyncWrite};
 use tokio::net::TcpStream;
 
 /// The capability to request cancellation of in-progress queries on a
 /// connection.
-#[derive(Clone, Serialize, Deserialize)]
+#[derive(Clone)]
 pub struct CancelToken {
     pub socket_config: Option<SocketConfig>,
     pub ssl_mode: SslMode,

libs/proxy/tokio-postgres2/src/client.rs

@@ -18,7 +18,6 @@ use fallible_iterator::FallibleIterator;
 use futures_util::{future, ready, TryStreamExt};
 use parking_lot::Mutex;
 use postgres_protocol2::message::{backend::Message, frontend};
-use serde::{Deserialize, Serialize};
 use std::collections::HashMap;
 use std::fmt;
 use std::sync::Arc;
@@ -138,7 +137,7 @@ impl InnerClient {
     }
 }
 
-#[derive(Clone, Serialize, Deserialize)]
+#[derive(Clone)]
 pub struct SocketConfig {
     pub host: Host,
     pub port: u16,