confused the files

# Conflicts:
#	.github/actions/neon-project-create/action.yml

.github/actions/allure-report-generate/action.yml

@@ -54,7 +54,7 @@ runs:
 
         LOCK_FILE=reports/${BRANCH_OR_PR}/lock.txt
 
-        WORKDIR=/__w/_temp/${BRANCH_OR_PR}-$(date +%s)
+        WORKDIR=/tmp/${BRANCH_OR_PR}-$(date +%s)
         mkdir -p ${WORKDIR}
 
         echo "BRANCH_OR_PR=${BRANCH_OR_PR}" >> $GITHUB_ENV
@@ -70,7 +70,7 @@ runs:
 
     - name: Install Allure
       shell: bash -euxo pipefail {0}
-      working-directory: /__w/_temp
+      working-directory: /tmp
       run: |
         if ! which allure; then
           ALLURE_ZIP=allure-${ALLURE_VERSION}.zip

.github/actions/download/action.yml

@@ -33,7 +33,7 @@ runs:
       shell: bash -euxo pipefail {0}
       env:
         TARGET: ${{ inputs.path }}
-        ARCHIVE: /__w/_temp/downloads/${{ inputs.name }}.tar.zst
+        ARCHIVE: /tmp/downloads/${{ inputs.name }}.tar.zst
         SKIP_IF_DOES_NOT_EXIST: ${{ inputs.skip-if-does-not-exist }}
         PREFIX: artifacts/${{ inputs.prefix || format('{0}/{1}/{2}', github.event.pull_request.head.sha || github.sha, github.run_id, github.run_attempt) }}
       run: |
@@ -61,7 +61,7 @@ runs:
       shell: bash -euxo pipefail {0}
       env:
         TARGET: ${{ inputs.path }}
-        ARCHIVE: /__w/_temp/downloads/${{ inputs.name }}.tar.zst
+        ARCHIVE: /tmp/downloads/${{ inputs.name }}.tar.zst
       run: |
         mkdir -p ${TARGET}
         time tar -xf ${ARCHIVE} -C ${TARGET}

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

@@ -40,15 +40,19 @@ inputs:
   psql_path:
     description: 'Path to psql binary - it is caller responsibility to provision the psql binary'
     required: false
-    default: '/__w/_temp/neon/pg_install/v16/bin/psql'
+    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: '/__w/_temp/neon/pg_install/v16/lib'
+    default: '/tmp/neon/pg_install/v16/lib'
   project_settings:
     description: 'A JSON object with project settings'
     required: false
     default: '{}'
+  default_endpoint_settings:
+    description: 'A JSON object with the default endpoint settings'
+    required: false
+    default: '{}'
 
 outputs:
   dsn:
@@ -83,7 +87,7 @@ runs:
               \"settings\": ${PROJECT_SETTINGS}
             }
           }")
-
+        
         code=${res: -3}
         if [[ ${code} -ge 400 ]]; then
           echo Request failed with error code ${code}
@@ -135,7 +139,22 @@ runs:
             -H "Accept: application/json" -H "Content-Type: application/json" -H "Authorization: Bearer ${ADMIN_API_KEY}" \
             -d "{\"scheduling\": \"Essential\"}"
         fi
-
+        # XXX
+        # This is a workaround for the default endpoint settings, which currently do not allow some settings in the public API.
+        # https://github.com/neondatabase/cloud/issues/27108
+        if [[ -n ${DEFAULT_ENDPOINT_SETTINGS} && ${DEFAULT_ENDPOINT_SETTINGS} != "{}" ]] ; then
+          PROJECT_DATA=$(curl -X GET \
+              "https://${API_HOST}/regions/${REGION_ID}/api/v1/admin/projects/${project_id}" \
+              -H "Accept: application/json" -H "Content-Type: application/json" -H "Authorization: Bearer ${ADMIN_API_KEY}" \
+              -d "{\"scheduling\": \"Essential\"}"
+          )
+          NEW_DEFAULT_ENDPOINT_SETTINGS=$(echo ${PROJECT_DATA} | jq -rc ".project.default_endpoint_settings + ${DEFAULT_ENDPOINT_SETTINGS}")
+          curl -X POST --fail \
+                "https://${API_HOST}/regions/${REGION_ID}/api/v1/admin/projects/${project_id}/default_endpoint_settings" \
+                -H "Accept: application/json" -H "Content-Type: application/json" -H "Authorization: Bearer ${ADMIN_API_KEY}" \
+                --data "${NEW_DEFAULT_ENDPOINT_SETTINGS}"
+        fi
+        
 
       env:
         API_HOST: ${{ inputs.api_host }}
@@ -152,3 +171,4 @@ runs:
         PSQL: ${{ inputs.psql_path }}
         LD_LIBRARY_PATH: ${{ inputs.libpq_lib_path }}
         PROJECT_SETTINGS: ${{ inputs.project_settings }}
+        DEFAULT_ENDPOINT_SETTINGS: ${{ inputs.default_endpoint_settings }}

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

@@ -65,7 +65,7 @@ runs:
       uses: ./.github/actions/download
       with:
         name: neon-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build_type }}${{ inputs.sanitizers == 'enabled' && '-sanitized' || '' }}-artifact
-        path: /__w/_temp/neon
+        path: /tmp/neon
         aws-oidc-role-arn: ${{ inputs.aws-oidc-role-arn }}
 
     - name: Download Neon binaries for the previous release
@@ -73,7 +73,7 @@ runs:
       uses: ./.github/actions/download
       with:
         name: neon-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build_type }}-artifact
-        path: /__w/_temp/neon-previous
+        path: /tmp/neon-previous
         prefix: latest
         aws-oidc-role-arn: ${{ inputs.aws-oidc-role-arn }}
 
@@ -82,7 +82,7 @@ runs:
       uses: ./.github/actions/download
       with:
         name: compatibility-snapshot-${{ runner.arch }}-${{ inputs.build_type }}-pg${{ inputs.pg_version }}
-        path: /__w/_temp/compatibility_snapshot_pg${{ inputs.pg_version }}
+        path: /tmp/compatibility_snapshot_pg${{ inputs.pg_version }}
         prefix: latest
         # The lack of compatibility snapshot (for example, for the new Postgres version)
         # shouldn't fail the whole job. Only relevant test should fail.
@@ -107,12 +107,12 @@ runs:
 
     - name: Run pytest
       env:
-        NEON_BIN: /__w/_temp/neon/bin
-        COMPATIBILITY_NEON_BIN: /__w/_temp/neon-previous/bin
-        COMPATIBILITY_POSTGRES_DISTRIB_DIR: /__w/_temp/neon-previous/pg_install
-        TEST_OUTPUT: /__w/_temp/test_output
+        NEON_BIN: /tmp/neon/bin
+        COMPATIBILITY_NEON_BIN: /tmp/neon-previous/bin
+        COMPATIBILITY_POSTGRES_DISTRIB_DIR: /tmp/neon-previous/pg_install
+        TEST_OUTPUT: /tmp/test_output
         BUILD_TYPE: ${{ inputs.build_type }}
-        COMPATIBILITY_SNAPSHOT_DIR: /__w/_temp/compatibility_snapshot_pg${{ inputs.pg_version }}
+        COMPATIBILITY_SNAPSHOT_DIR: /tmp/compatibility_snapshot_pg${{ inputs.pg_version }}
         RERUN_FAILED: ${{ inputs.rerun_failed }}
         PG_VERSION: ${{ inputs.pg_version }}
         SANITIZERS: ${{ inputs.sanitizers }}
@@ -121,7 +121,7 @@ runs:
         # PLATFORM will be embedded in the perf test report
         # and it is needed to distinguish different environments
         export PLATFORM=${PLATFORM:-github-actions-selfhosted}
-        export POSTGRES_DISTRIB_DIR=${POSTGRES_DISTRIB_DIR:-/__w/_temp/neon/pg_install}
+        export POSTGRES_DISTRIB_DIR=${POSTGRES_DISTRIB_DIR:-/tmp/neon/pg_install}
         export DEFAULT_PG_VERSION=${PG_VERSION#v}
         export LD_LIBRARY_PATH=${POSTGRES_DISTRIB_DIR}/v${DEFAULT_PG_VERSION}/lib
         export BENCHMARK_CONNSTR=${BENCHMARK_CONNSTR:-}
@@ -176,7 +176,7 @@ runs:
         fi
 
         if [[ $BUILD_TYPE == "debug" && $RUNNER_ARCH == 'X64' ]]; then
-          cov_prefix=(scripts/coverage "--profraw-prefix=$GITHUB_JOB" --dir=/__w/_temp/coverage run)
+          cov_prefix=(scripts/coverage "--profraw-prefix=$GITHUB_JOB" --dir=/tmp/coverage run)
         else
           cov_prefix=()
         fi
@@ -224,7 +224,7 @@ runs:
       with:
         name: compatibility-snapshot-${{ runner.arch }}-${{ inputs.build_type }}-pg${{ inputs.pg_version }}
         # Directory is created by test_compatibility.py::test_create_snapshot, keep the path in sync with the test
-        path: /__w/_temp/test_output/compatibility_snapshot_pg${{ inputs.pg_version }}/
+        path: /tmp/test_output/compatibility_snapshot_pg${{ inputs.pg_version }}/
         # The lack of compatibility snapshot shouldn't fail the job
         # (for example if we didn't run the test for non build-and-test workflow)
         skip-if-does-not-exist: true
@@ -241,6 +241,6 @@ runs:
       if: ${{ !cancelled() }}
       uses: ./.github/actions/allure-report-store
       with:
-        report-dir: /__w/_temp/test_output/allure/results
+        report-dir: /tmp/test_output/allure/results
         unique-key: ${{ inputs.build_type }}-${{ inputs.pg_version }}-${{ runner.arch }}
         aws-oidc-role-arn: ${{ inputs.aws-oidc-role-arn }}

.github/actions/save-coverage-data/action.yml

@@ -6,13 +6,13 @@ runs:
   steps:
     - name: Merge coverage data
       shell: bash -euxo pipefail {0}
-      run: scripts/coverage "--profraw-prefix=$GITHUB_JOB" --dir=/__w/_temp/coverage merge
+      run: scripts/coverage "--profraw-prefix=$GITHUB_JOB" --dir=/tmp/coverage merge
 
     - name: Download previous coverage data into the same directory
       uses: ./.github/actions/download
       with:
         name: coverage-data-artifact
-        path: /__w/_temp/coverage
+        path: /tmp/coverage
         skip-if-does-not-exist: true # skip if there's no previous coverage to download
         aws-oidc-role-arn: ${{ inputs.aws-oidc-role-arn }}
 
@@ -20,5 +20,5 @@ runs:
       uses: ./.github/actions/upload
       with:
         name: coverage-data-artifact
-        path: /__w/_temp/coverage
+        path: /tmp/coverage
         aws-oidc-role-arn: ${{ inputs.aws-oidc-role-arn }}

.github/actions/upload/action.yml

@@ -27,7 +27,7 @@ runs:
       shell: bash -euxo pipefail {0}
       env:
         SOURCE: ${{ inputs.path }}
-        ARCHIVE: /__w/_temp/uploads/${{ inputs.name }}.tar.zst
+        ARCHIVE: /tmp/uploads/${{ inputs.name }}.tar.zst
         SKIP_IF_DOES_NOT_EXIST: ${{ inputs.skip-if-does-not-exist }}
       run: |
         mkdir -p $(dirname $ARCHIVE)
@@ -69,7 +69,7 @@ runs:
       shell: bash -euxo pipefail {0}
       env:
         SOURCE: ${{ inputs.path }}
-        ARCHIVE: /__w/_temp/uploads/${{ inputs.name }}.tar.zst
+        ARCHIVE: /tmp/uploads/${{ inputs.name }}.tar.zst
         PREFIX: artifacts/${{ inputs.prefix || format('{0}/{1}/{2}', github.event.pull_request.head.sha || github.sha, github.run_id , github.run_attempt) }}
       run: |
         BUCKET=neon-github-public-dev

.github/workflows/_benchmarking_preparation.yml

@@ -24,9 +24,9 @@ jobs:
         database: [ clickbench, tpch, userexample ]
 
     env:
-      LD_LIBRARY_PATH: /__w/_temp/neon/pg_install/v16/lib
+      LD_LIBRARY_PATH: /tmp/neon/pg_install/v16/lib
       PLATFORM: ${{ matrix.platform }}
-      PG_BINARIES: /__w/_temp/neon/pg_install/v16/bin
+      PG_BINARIES: /tmp/neon/pg_install/v16/bin
 
     runs-on: [ self-hosted, us-east-2, x64 ]
     container:
@@ -79,7 +79,7 @@ jobs:
       uses: ./.github/actions/download
       with:
         name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
-        path: /__w/_temp/neon/
+        path: /tmp/neon/
         prefix: latest
         aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
@@ -127,13 +127,13 @@ jobs:
           echo "Database ${{ env.DATABASE_NAME }} already exists."
         fi
 
-    - name: Download dump from S3 to /__w/_temp/dumps
+    - name: Download dump from S3 to /tmp/dumps
       if: steps.check-restore-done.outputs.skip != 'true'
       env:
         DATABASE_NAME: ${{ matrix.database }}
       run: |
-        mkdir -p /__w/_temp/dumps
-        aws s3 cp s3://neon-github-dev/performance/pgdumps/$DATABASE_NAME/$DATABASE_NAME.pg_dump /__w/_temp/dumps/
+        mkdir -p /tmp/dumps
+        aws s3 cp s3://neon-github-dev/performance/pgdumps/$DATABASE_NAME/$DATABASE_NAME.pg_dump /tmp/dumps/
 
     - name: Replace database name in connection string
       if: steps.check-restore-done.outputs.skip != 'true'
@@ -166,7 +166,7 @@ jobs:
         # available in RDS, so we will always report an error, but we can ignore it
       run: |
         ${PG_BINARIES}/pg_restore --clean --if-exists --no-owner --jobs=4 \
-        -d "${DATABASE_CONNSTR}" /__w/_temp/dumps/${DATABASE_NAME}.pg_dump || true
+        -d "${DATABASE_CONNSTR}" /tmp/dumps/${DATABASE_NAME}.pg_dump || true
 
     - name: Update benchmark_restore_status table
       if: steps.check-restore-done.outputs.skip != 'true'

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

@@ -38,11 +38,6 @@ on:
         required: false
         default: 1
         type: number
-      rerun-failed:
-        description: 'rerun failed tests to ignore flaky tests'
-        required: false
-        default: true
-        type: boolean
 
 defaults:
   run:
@@ -104,10 +99,11 @@ jobs:
 
       # Set some environment variables used by all the steps.
       #
-      # CARGO_FLAGS is extra options to pass to all "cargo" subcommands.
+      # CARGO_FLAGS is extra options to pass to "cargo build", "cargo test" etc.
+      #   It also includes --features, if any
       #
-      # CARGO_PROFILE is passed to "cargo build", "cargo test" etc, but not to
-      #   "cargo metadata", because it doesn't accept --release or --debug options.
+      # CARGO_FEATURES is passed to "cargo metadata". It is separate from CARGO_FLAGS,
+      #   because "cargo metadata" doesn't accept --release or --debug options
       #
       # We run tests with addtional features, that are turned off by default (e.g. in release builds), see
       # corresponding Cargo.toml files for their descriptions.
@@ -116,16 +112,16 @@ jobs:
           ARCH: ${{ inputs.arch }}
           SANITIZERS: ${{ inputs.sanitizers }}
         run: |
-          CARGO_FLAGS="--locked --features testing"
+          CARGO_FEATURES="--features testing"
           if [[ $BUILD_TYPE == "debug" && $ARCH == 'x64' ]]; then
-            cov_prefix="scripts/coverage --profraw-prefix=$GITHUB_JOB --dir=/__w/_temp/coverage run"
-            CARGO_PROFILE=""
+            cov_prefix="scripts/coverage --profraw-prefix=$GITHUB_JOB --dir=/tmp/coverage run"
+            CARGO_FLAGS="--locked"
           elif [[ $BUILD_TYPE == "debug" ]]; then
             cov_prefix=""
-            CARGO_PROFILE=""
+            CARGO_FLAGS="--locked"
           elif [[ $BUILD_TYPE == "release" ]]; then
             cov_prefix=""
-            CARGO_PROFILE="--release"
+            CARGO_FLAGS="--locked --release"
           fi
           if [[ $SANITIZERS == 'enabled' ]]; then
             make_vars="WITH_SANITIZERS=yes"
@@ -135,8 +131,8 @@ jobs:
           {
             echo "cov_prefix=${cov_prefix}"
             echo "make_vars=${make_vars}"
+            echo "CARGO_FEATURES=${CARGO_FEATURES}"
             echo "CARGO_FLAGS=${CARGO_FLAGS}"
-            echo "CARGO_PROFILE=${CARGO_PROFILE}"
             echo "CARGO_HOME=${GITHUB_WORKSPACE}/.cargo"
           } >> $GITHUB_ENV
 
@@ -188,18 +184,34 @@ jobs:
           path: pg_install/v17
           key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v17_rev.outputs.pg_rev }}-bookworm-${{ hashFiles('Makefile', 'build-tools.Dockerfile') }}
 
-      - name: Build all
-        # Note: the Makefile picks up BUILD_TYPE and CARGO_PROFILE from the env variables
-        run: mold -run make ${make_vars} all -j$(nproc) CARGO_BUILD_FLAGS="$CARGO_FLAGS"
+      - name: Build postgres v14
+        if: steps.cache_pg_14.outputs.cache-hit != 'true'
+        run: mold -run make ${make_vars} postgres-v14 -j$(nproc)
+
+      - name: Build postgres v15
+        if: steps.cache_pg_15.outputs.cache-hit != 'true'
+        run: mold -run make ${make_vars} postgres-v15 -j$(nproc)
+
+      - name: Build postgres v16
+        if: steps.cache_pg_16.outputs.cache-hit != 'true'
+        run: mold -run make ${make_vars} postgres-v16 -j$(nproc)
+
+      - name: Build postgres v17
+        if: steps.cache_pg_17.outputs.cache-hit != 'true'
+        run: mold -run make ${make_vars} postgres-v17 -j$(nproc)
+
+      - name: Build neon extensions
+        run: mold -run make ${make_vars} neon-pg-ext -j$(nproc)
 
       - name: Build walproposer-lib
         run: mold -run make ${make_vars} walproposer-lib -j$(nproc)
 
-      - name: Build unit tests
-        if: inputs.sanitizers != 'enabled'
+      - 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_PROFILE --tests
+          ${cov_prefix} mold -run cargo build $CARGO_FLAGS $CARGO_FEATURES --bins ${WITH_TESTS}
 
       # Do install *before* running rust tests because they might recompile the
       # binaries with different features/flags.
@@ -209,40 +221,40 @@ jobs:
           SANITIZERS: ${{ inputs.sanitizers }}
         run: |
           # Install target binaries
-          mkdir -p /__w/_temp/neon/bin/
+          mkdir -p /tmp/neon/bin/
           binaries=$(
-            ${cov_prefix} cargo metadata $CARGO_FLAGS --format-version=1 --no-deps |
+            ${cov_prefix} cargo metadata $CARGO_FEATURES --format-version=1 --no-deps |
             jq -r '.packages[].targets[] | select(.kind | index("bin")) | .name'
           )
           for bin in $binaries; do
             SRC=target/$BUILD_TYPE/$bin
-            DST=/__w/_temp/neon/bin/$bin
+            DST=/tmp/neon/bin/$bin
             cp "$SRC" "$DST"
           done
 
           # Install test executables and write list of all binaries (for code coverage)
           if [[ $BUILD_TYPE == "debug" && $ARCH == 'x64' && $SANITIZERS != 'enabled' ]]; then
             # Keep bloated coverage data files away from the rest of the artifact
-            mkdir -p /__w/_temp/coverage/
+            mkdir -p /tmp/coverage/
 
-            mkdir -p /__w/_temp/neon/test_bin/
+            mkdir -p /tmp/neon/test_bin/
 
             test_exe_paths=$(
-              ${cov_prefix} cargo test $CARGO_FLAGS $CARGO_PROFILE --message-format=json --no-run |
+              ${cov_prefix} cargo test $CARGO_FLAGS $CARGO_FEATURES --message-format=json --no-run |
               jq -r '.executable | select(. != null)'
             )
             for bin in $test_exe_paths; do
               SRC=$bin
-              DST=/__w/_temp/neon/test_bin/$(basename $bin)
+              DST=/tmp/neon/test_bin/$(basename $bin)
 
               # We don't need debug symbols for code coverage, so strip them out to make
               # the artifact smaller.
               strip "$SRC" -o "$DST"
-              echo "$DST" >> /__w/_temp/coverage/binaries.list
+              echo "$DST" >> /tmp/coverage/binaries.list
             done
 
             for bin in $binaries; do
-              echo "/__w/_temp/neon/bin/$bin" >> /__w/_temp/coverage/binaries.list
+              echo "/tmp/neon/bin/$bin" >> /tmp/coverage/binaries.list
             done
           fi
 
@@ -262,25 +274,29 @@ jobs:
           export LD_LIBRARY_PATH
 
           #nextest does not yet support running doctests
-          ${cov_prefix} cargo test --doc $CARGO_FLAGS $CARGO_PROFILE
+          ${cov_prefix} cargo test --doc $CARGO_FLAGS $CARGO_FEATURES
 
           # run all non-pageserver tests
-          ${cov_prefix} cargo nextest run $CARGO_FLAGS $CARGO_PROFILE -E '!package(pageserver)'
+          ${cov_prefix} cargo nextest run $CARGO_FLAGS $CARGO_FEATURES -E '!package(pageserver)'
 
-          # run pageserver tests
-          # (When developing new pageserver features gated by config fields, we commonly make the rust
-          # unit tests sensitive to an environment variable NEON_PAGESERVER_UNIT_TEST_FEATURENAME.
-          # Then run the nextest invocation below for all relevant combinations. Singling out the
-          # pageserver tests from non-pageserver tests cuts down the time it takes for this CI step.)
-          NEON_PAGESERVER_UNIT_TEST_VIRTUAL_FILE_IOENGINE=tokio-epoll-uring  \
-          ${cov_prefix} \
-          cargo nextest run $CARGO_FLAGS $CARGO_PROFILE  -E 'package(pageserver)'
+          # run pageserver tests with different settings
+          for get_vectored_concurrent_io in sequential sidecar-task; do
+            for io_engine in std-fs tokio-epoll-uring ; do
+                for io_mode in buffered direct direct-rw ; do
+                  NEON_PAGESERVER_UNIT_TEST_GET_VECTORED_CONCURRENT_IO=$get_vectored_concurrent_io \
+                  NEON_PAGESERVER_UNIT_TEST_VIRTUAL_FILE_IOENGINE=$io_engine \
+                  NEON_PAGESERVER_UNIT_TEST_VIRTUAL_FILE_IO_MODE=$io_mode \
+                  ${cov_prefix} \
+                  cargo nextest run $CARGO_FLAGS $CARGO_FEATURES  -E 'package(pageserver)'
+              done
+            done
+          done
 
           # Run separate tests for real S3
           export ENABLE_REAL_S3_REMOTE_STORAGE=nonempty
           export REMOTE_STORAGE_S3_BUCKET=neon-github-ci-tests
           export REMOTE_STORAGE_S3_REGION=eu-central-1
-          ${cov_prefix} cargo nextest run $CARGO_FLAGS $CARGO_PROFILE -E 'package(remote_storage)' -E 'test(test_real_s3)'
+          ${cov_prefix} cargo nextest run $CARGO_FLAGS $CARGO_FEATURES -E 'package(remote_storage)' -E 'test(test_real_s3)'
 
           # Run separate tests for real Azure Blob Storage
           # XXX: replace region with `eu-central-1`-like region
@@ -289,35 +305,35 @@ jobs:
           export AZURE_STORAGE_ACCESS_KEY="${{ secrets.AZURE_STORAGE_ACCESS_KEY_DEV }}"
           export REMOTE_STORAGE_AZURE_CONTAINER="${{ vars.REMOTE_STORAGE_AZURE_CONTAINER }}"
           export REMOTE_STORAGE_AZURE_REGION="${{ vars.REMOTE_STORAGE_AZURE_REGION }}"
-          ${cov_prefix} cargo nextest run $CARGO_FLAGS $CARGO_PROFILE -E 'package(remote_storage)' -E 'test(test_real_azure)'
+          ${cov_prefix} cargo nextest run $CARGO_FLAGS $CARGO_FEATURES -E 'package(remote_storage)' -E 'test(test_real_azure)'
 
       - name: Install postgres binaries
         run: |
           # Use tar to copy files matching the pattern, preserving the paths in the destionation
           tar c \
             pg_install/v* \
-            build/*/src/test/regress/*.so \
-            build/*/src/test/regress/pg_regress \
-            build/*/src/test/isolation/isolationtester \
-            build/*/src/test/isolation/pg_isolation_regress \
-            | tar  x -C /__w/_temp/neon
+            pg_install/build/*/src/test/regress/*.so \
+            pg_install/build/*/src/test/regress/pg_regress \
+            pg_install/build/*/src/test/isolation/isolationtester \
+            pg_install/build/*/src/test/isolation/pg_isolation_regress \
+            | tar  x -C /tmp/neon
 
       - name: Upload Neon artifact
         uses: ./.github/actions/upload
         with:
           name: neon-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}${{ inputs.sanitizers == 'enabled' && '-sanitized' || '' }}-artifact
-          path: /__w/_temp/neon
+          path: /tmp/neon
           aws-oidc-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: /__w/_temp/neon/pg_install
+          POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
         run: |
           export ASAN_OPTIONS=detect_leaks=0
-          /__w/_temp/neon/bin/neon_local init
-          /__w/_temp/neon/bin/neon_local storage_controller start
+          /tmp/neon/bin/neon_local init
+          /tmp/neon/bin/neon_local storage_controller start
 
           diesel print-schema > storage_controller/src/schema.rs
 
@@ -328,7 +344,7 @@ jobs:
             exit 1
           fi
 
-          /__w/_temp/neon/bin/neon_local storage_controller stop
+          /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
@@ -367,7 +383,7 @@ 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.build-type == 'release' && inputs.sanitizers != 'enabled') && 75 || 180 }}
+        timeout-minutes: ${{ inputs.sanitizers != 'enabled' && 75 || 180 }}
         with:
           build_type: ${{ inputs.build-type }}
           test_selection: regress
@@ -375,20 +391,22 @@ jobs:
           run_with_real_s3: true
           real_s3_bucket: neon-github-ci-tests
           real_s3_region: eu-central-1
-          rerun_failed: ${{ inputs.rerun-failed }}
+          rerun_failed: ${{ inputs.test-run-count == 1 }}
           pg_version: ${{ matrix.pg_version }}
           sanitizers: ${{ inputs.sanitizers }}
           aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
           # `--session-timeout` is equal to (timeout-minutes - 10 minutes) * 60 seconds.
           # Attempt to stop tests gracefully to generate test reports
           # until they are forcibly stopped by the stricter `timeout-minutes` limit.
-          extra_params: --session-timeout=${{ (inputs.build-type == 'release' && inputs.sanitizers != 'enabled') && 3000 || 10200 }} --count=${{ inputs.test-run-count }}
+          extra_params: --session-timeout=${{ inputs.sanitizers != 'enabled' && 3000 || 10200 }} --count=${{ inputs.test-run-count }}
                         ${{ inputs.test-selection != '' && format('-k "{0}"', inputs.test-selection) || '' }}
         env:
           TEST_RESULT_CONNSTR: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}
           CHECK_ONDISK_DATA_COMPATIBILITY: nonempty
           BUILD_TAG: ${{ inputs.build-tag }}
           PAGESERVER_VIRTUAL_FILE_IO_ENGINE: tokio-epoll-uring
+          PAGESERVER_GET_VECTORED_CONCURRENT_IO: sidecar-task
+          PAGESERVER_VIRTUAL_FILE_IO_MODE: direct-rw
           USE_LFC: ${{ matrix.lfc_state == 'with-lfc' && 'true' || 'false' }}
 
       # Temporary disable this step until we figure out why it's so flaky

.github/workflows/benchmarking.yml

@@ -119,7 +119,7 @@ jobs:
             curl -s -X DELETE "$BASE_URL/projects/$project_id" \
               --header "Accept: application/json" \
               --header "Content-Type: application/json" \
-              --header "Authorization: Bearer ${API_KEY}"
+              --header "Authorization: Bearer ${API_KEY}" 
           done
         else
           echo "Dry run enabled — no projects were deleted."
@@ -149,9 +149,9 @@ jobs:
     env:
       TEST_PG_BENCH_DURATIONS_MATRIX: "300"
       TEST_PG_BENCH_SCALES_MATRIX: "10,100"
-      POSTGRES_DISTRIB_DIR: /__w/_temp/neon/pg_install
+      POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
       PG_VERSION: ${{ matrix.PG_VERSION }}
-      TEST_OUTPUT: /__w/_temp/test_output
+      TEST_OUTPUT: /tmp/test_output
       BUILD_TYPE: remote
       SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref_name == 'main' ) }}
       PLATFORM: ${{ matrix.PLATFORM }}
@@ -183,7 +183,7 @@ jobs:
       uses: ./.github/actions/download
       with:
         name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
-        path: /__w/_temp/neon/
+        path: /tmp/neon/
         prefix: latest
         aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
@@ -257,9 +257,9 @@ jobs:
       statuses: write
       id-token: write # aws-actions/configure-aws-credentials
     env:
-      POSTGRES_DISTRIB_DIR: /__w/_temp/neon/pg_install
+      POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
       DEFAULT_PG_VERSION: 17
-      TEST_OUTPUT: /__w/_temp/test_output
+      TEST_OUTPUT: /tmp/test_output
       BUILD_TYPE: remote
       SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref_name == 'main' ) }}
       PLATFORM: "neon-staging"
@@ -291,7 +291,7 @@ jobs:
       uses: ./.github/actions/download
       with:
         name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
-        path: /__w/_temp/neon/
+        path: /tmp/neon/
         prefix: latest
         aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
@@ -317,9 +317,9 @@ jobs:
       statuses: write
       id-token: write # aws-actions/configure-aws-credentials
     env:
-      POSTGRES_DISTRIB_DIR: /__w/_temp/neon/pg_install
+      POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
       DEFAULT_PG_VERSION: 16
-      TEST_OUTPUT: /__w/_temp/test_output
+      TEST_OUTPUT: /tmp/test_output
       BUILD_TYPE: remote
       SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref_name == 'main' ) }}
       PLATFORM: "neon-staging"
@@ -351,7 +351,7 @@ jobs:
       uses: ./.github/actions/download
       with:
         name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
-        path: /__w/_temp/neon/
+        path: /tmp/neon/
         prefix: latest
         aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
@@ -537,9 +537,9 @@ jobs:
     env:
       TEST_PG_BENCH_DURATIONS_MATRIX: "60m"
       TEST_PG_BENCH_SCALES_MATRIX: ${{ matrix.db_size }}
-      POSTGRES_DISTRIB_DIR: /__w/_temp/neon/pg_install
+      POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
       PG_VERSION: ${{ matrix.pg_version }}
-      TEST_OUTPUT: /__w/_temp/test_output
+      TEST_OUTPUT: /tmp/test_output
       BUILD_TYPE: remote
       SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref_name == 'main' ) }}
       PLATFORM: ${{ matrix.platform }}
@@ -574,7 +574,7 @@ jobs:
       uses: ./.github/actions/download
       with:
         name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
-        path: /__w/_temp/neon/
+        path: /tmp/neon/
         prefix: latest
         aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
@@ -728,9 +728,9 @@ jobs:
     env:
       TEST_PG_BENCH_DURATIONS_MATRIX: "15m"
       TEST_PG_BENCH_SCALES_MATRIX: "1"
-      POSTGRES_DISTRIB_DIR: /__w/_temp/neon/pg_install
+      POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
       PG_VERSION: ${{ matrix.postgres_version }}
-      TEST_OUTPUT: /__w/_temp/test_output
+      TEST_OUTPUT: /tmp/test_output
       BUILD_TYPE: remote
 
       SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref_name == 'main' ) }}
@@ -763,7 +763,7 @@ jobs:
       uses: ./.github/actions/download
       with:
         name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
-        path: /__w/_temp/neon/
+        path: /tmp/neon/
         prefix: latest
         aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
@@ -857,9 +857,9 @@ jobs:
       matrix: ${{ fromJSON(needs.generate-matrices.outputs.olap-compare-matrix) }}
 
     env:
-      POSTGRES_DISTRIB_DIR: /__w/_temp/neon/pg_install
+      POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
       PG_VERSION: ${{ matrix.pg_version }}
-      TEST_OUTPUT: /__w/_temp/test_output
+      TEST_OUTPUT: /tmp/test_output
       TEST_OLAP_COLLECT_EXPLAIN: ${{ github.event.inputs.collect_olap_explain }}
       TEST_OLAP_COLLECT_PG_STAT_STATEMENTS: ${{ github.event.inputs.collect_pg_stat_statements }}
       BUILD_TYPE: remote
@@ -897,7 +897,7 @@ jobs:
       uses: ./.github/actions/download
       with:
         name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
-        path: /__w/_temp/neon/
+        path: /tmp/neon/
         prefix: latest
         aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
@@ -989,9 +989,9 @@ jobs:
       matrix: ${{ fromJSON(needs.generate-matrices.outputs.tpch-compare-matrix) }}
 
     env:
-      POSTGRES_DISTRIB_DIR: /__w/_temp/neon/pg_install
+      POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
       PG_VERSION: ${{ matrix.pg_version }}
-      TEST_OUTPUT: /__w/_temp/test_output
+      TEST_OUTPUT: /tmp/test_output
       BUILD_TYPE: remote
       SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref_name == 'main' ) }}
       PLATFORM: ${{ matrix.platform }}
@@ -1023,7 +1023,7 @@ jobs:
       uses: ./.github/actions/download
       with:
         name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
-        path: /__w/_temp/neon/
+        path: /tmp/neon/
         prefix: latest
         aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
@@ -1113,9 +1113,9 @@ jobs:
       matrix: ${{ fromJSON(needs.generate-matrices.outputs.olap-compare-matrix) }}
 
     env:
-      POSTGRES_DISTRIB_DIR: /__w/_temp/neon/pg_install
+      POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
       PG_VERSION: ${{ matrix.pg_version }}
-      TEST_OUTPUT: /__w/_temp/test_output
+      TEST_OUTPUT: /tmp/test_output
       BUILD_TYPE: remote
       SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref_name == 'main' ) }}
       PLATFORM: ${{ matrix.platform }}
@@ -1147,7 +1147,7 @@ jobs:
       uses: ./.github/actions/download
       with:
         name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
-        path: /__w/_temp/neon/
+        path: /tmp/neon/
         prefix: latest
         aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 

.github/workflows/build-macos.yml

@@ -110,7 +110,7 @@ jobs:
 
   build-walproposer-lib:
     if: |
-      contains(inputs.pg_versions, 'v17') || inputs.rebuild_everything ||
+      inputs.pg_versions != '[]' || inputs.rebuild_everything ||
       contains(github.event.pull_request.labels.*.name, 'run-extra-build-macos')  ||
       contains(github.event.pull_request.labels.*.name, 'run-extra-build-*') ||
       github.ref_name == 'main'
@@ -144,7 +144,7 @@ jobs:
         id: cache_walproposer_lib
         uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
         with:
-          path: build/walproposer-lib
+          path: pg_install/build/walproposer-lib
           key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-walproposer_lib-v17-${{ steps.pg_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
 
       - name: Checkout submodule vendor/postgres-v17
@@ -169,11 +169,11 @@ jobs:
         run:
           make walproposer-lib -j$(sysctl -n hw.ncpu)
 
-      - name: Upload "build/walproposer-lib" artifact
+      - name: Upload "pg_install/build/walproposer-lib" artifact
         uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
         with:
-          name: build--walproposer-lib
-          path: build/walproposer-lib
+          name: pg_install--build--walproposer-lib
+          path: pg_install/build/walproposer-lib
           # The artifact is supposed to be used by the next job in the same workflow,
           # so there’s no need to store it for too long.
           retention-days: 1
@@ -226,11 +226,11 @@ jobs:
           name: pg_install--v17
           path: pg_install/v17
 
-      - name: Download "build/walproposer-lib" artifact
+      - name: Download "pg_install/build/walproposer-lib" artifact
         uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
         with:
-          name: build--walproposer-lib
-          path: build/walproposer-lib
+          name: pg_install--build--walproposer-lib
+          path: pg_install/build/walproposer-lib
 
       # `actions/download-artifact` doesn't preserve permissions:
       # https://github.com/actions/download-artifact?tab=readme-ov-file#permission-loss

.github/workflows/build_and_run_selected_test.yml

@@ -58,7 +58,6 @@ jobs:
       test-cfg: ${{ inputs.pg-versions }}
       test-selection: ${{ inputs.test-selection }}
       test-run-count: ${{ fromJson(inputs.run-count) }}
-      rerun-failed: false
     secrets: inherit
 
   create-test-report:

.github/workflows/build_and_test.yml

@@ -199,28 +199,6 @@ jobs:
       build-tools-image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
     secrets: inherit
 
-  validate-compute-manifest:
-    runs-on: ubuntu-22.04
-    needs: [ meta, check-permissions ]
-    # We do need to run this in `.*-rc-pr` because of hotfixes.
-    if: ${{ contains(fromJSON('["pr", "push-main", "storage-rc-pr", "proxy-rc-pr", "compute-rc-pr"]'), needs.meta.outputs.run-kind) }}
-    steps:
-      - name: Harden the runner (Audit all outbound calls)
-        uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
-        with:
-          egress-policy: audit
-
-      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
-
-      - name: Set up Node.js
-        uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4.4.0
-        with:
-          node-version: '24'
-
-      - name: Validate manifest against schema
-        run: |
-          make -C compute manifest-schema-validation
-
   build-and-test-locally:
     needs: [ meta, build-build-tools-image ]
     # We do need to run this in `.*-rc-pr` because of hotfixes.
@@ -294,8 +272,8 @@ jobs:
         run: |
           poetry run ./scripts/benchmark_durations.py "${TEST_RESULT_CONNSTR}" \
                                                       --days 10 \
-                                                      --output /__w/_temp/benchmark_durations.json
-          echo "json=$(jq --compact-output '.' /__w/_temp/benchmark_durations.json)" >> $GITHUB_OUTPUT
+                                                      --output /tmp/benchmark_durations.json
+          echo "json=$(jq --compact-output '.' /tmp/benchmark_durations.json)" >> $GITHUB_OUTPUT
 
   benchmarks:
     # `!failure() && !cancelled()` is required because the workflow depends on the job that can be skipped: `deploy` in PRs
@@ -336,8 +314,7 @@ jobs:
           test_selection: performance
           run_in_parallel: false
           save_perf_report: ${{ github.ref_name == 'main' }}
-          # test_pageserver_max_throughput_getpage_at_latest_lsn is run in separate workflow periodic_pagebench.yml because it needs snapshots
-          extra_params: --splits 5 --group ${{ matrix.pytest_split_group }} --ignore=test_runner/performance/pageserver/pagebench/test_pageserver_max_throughput_getpage_at_latest_lsn.py
+          extra_params: --splits 5 --group ${{ matrix.pytest_split_group }}
           benchmark_durations: ${{ needs.get-benchmarks-durations.outputs.json }}
           pg_version: v16
           aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
@@ -346,6 +323,8 @@ jobs:
           PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
           TEST_RESULT_CONNSTR: "${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}"
           PAGESERVER_VIRTUAL_FILE_IO_ENGINE: tokio-epoll-uring
+          PAGESERVER_GET_VECTORED_CONCURRENT_IO: sidecar-task
+          PAGESERVER_VIRTUAL_FILE_IO_MODE: direct-rw
           SYNC_BETWEEN_TESTS: true
       # XXX: no coverage data handling here, since benchmarks are run on release builds,
       # while coverage is currently collected for the debug ones
@@ -471,32 +450,32 @@ jobs:
         uses: ./.github/actions/download
         with:
           name: neon-${{ runner.os }}-${{ runner.arch }}-${{ matrix.build_type }}-artifact
-          path: /__w/_temp/neon
+          path: /tmp/neon
           aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
       - name: Get coverage artifact
         uses: ./.github/actions/download
         with:
           name: coverage-data-artifact
-          path: /__w/_temp/coverage
+          path: /tmp/coverage
           aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
       - name: Merge coverage data
-        run: scripts/coverage "--profraw-prefix=$GITHUB_JOB" --dir=/__w/_temp/coverage merge
+        run: scripts/coverage "--profraw-prefix=$GITHUB_JOB" --dir=/tmp/coverage merge
 
       - name: Build coverage report
         env:
           COMMIT_URL: ${{ github.server_url }}/${{ github.repository }}/commit/${{ github.event.pull_request.head.sha || github.sha }}
         run: |
-          scripts/coverage --dir=/__w/_temp/coverage \
+          scripts/coverage --dir=/tmp/coverage \
             report \
-            --input-objects=/__w/_temp/coverage/binaries.list \
+            --input-objects=/tmp/coverage/binaries.list \
             --commit-url=${COMMIT_URL} \
             --format=github
 
-          scripts/coverage --dir=/__w/_temp/coverage \
+          scripts/coverage --dir=/tmp/coverage \
             report \
-            --input-objects=/__w/_temp/coverage/binaries.list \
+            --input-objects=/tmp/coverage/binaries.list \
             --format=lcov
 
       - name: Build coverage report NEW
@@ -511,7 +490,7 @@ jobs:
           CURRENT="${COMMIT_SHA}"
           BASELINE="$(git merge-base $BASE_SHA $CURRENT)"
 
-          cp /__w/_temp/coverage/report/lcov.info ./${CURRENT}.info
+          cp /tmp/coverage/report/lcov.info ./${CURRENT}.info
 
           GENHTML_ARGS="--ignore-errors path,unmapped,empty --synthesize-missing --demangle-cpp rustfilt --output-directory lcov-html ${CURRENT}.info"
 
@@ -670,7 +649,7 @@ jobs:
                                              ghcr.io/neondatabase/neon:${{ needs.meta.outputs.build-tag }}-bookworm-arm64
 
   compute-node-image-arch:
-    needs: [ check-permissions, meta ]
+    needs: [ check-permissions, build-build-tools-image, meta ]
     if: ${{ contains(fromJSON('["push-main", "pr", "compute-rc-pr"]'), needs.meta.outputs.run-kind) }}
     permissions:
       id-token: write # aws-actions/configure-aws-credentials
@@ -743,6 +722,7 @@ jobs:
             GIT_VERSION=${{ github.event.pull_request.head.sha || github.sha }}
             PG_VERSION=${{ matrix.version.pg }}
             BUILD_TAG=${{ needs.meta.outputs.release-tag || needs.meta.outputs.build-tag }}
+            TAG=${{ needs.build-build-tools-image.outputs.image-tag }}-${{ matrix.version.debian }}
             DEBIAN_VERSION=${{ matrix.version.debian }}
           provenance: false
           push: true
@@ -762,6 +742,7 @@ jobs:
             GIT_VERSION=${{ github.event.pull_request.head.sha || github.sha }}
             PG_VERSION=${{ matrix.version.pg }}
             BUILD_TAG=${{ needs.meta.outputs.release-tag || needs.meta.outputs.build-tag }}
+            TAG=${{ needs.build-build-tools-image.outputs.image-tag }}-${{ matrix.version.debian }}
             DEBIAN_VERSION=${{ matrix.version.debian }}
           provenance: false
           push: true
@@ -984,7 +965,7 @@ jobs:
           fi
 
       - name: Verify docker-compose example and test extensions
-        timeout-minutes: 60
+        timeout-minutes: 40
         env:
           TAG: >-
             ${{

.github/workflows/build_and_test_fully.yml

@@ -1,151 +0,0 @@
-name: Build and Test Fully
-
-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 3 * * *' # run once a day, timezone is utc
-  workflow_dispatch:
-
-defaults:
-  run:
-    shell: bash -euxo pipefail {0}
-
-concurrency:
-  # Allow only one workflow per any non-`main` branch.
-  group: ${{ github.workflow }}-${{ github.ref_name }}-${{ github.ref_name == 'main' && github.sha || 'anysha' }}
-  cancel-in-progress: true
-
-env:
-  RUST_BACKTRACE: 1
-  COPT: '-Werror'
-
-jobs:
-  tag:
-    runs-on: [ self-hosted, small ]
-    container: ${{ vars.NEON_DEV_AWS_ACCOUNT_ID }}.dkr.ecr.${{ vars.AWS_ECR_REGION }}.amazonaws.com/base:pinned
-    outputs:
-      build-tag: ${{steps.build-tag.outputs.tag}}
-
-    steps:
-      # Need `fetch-depth: 0` to count the number of commits in the branch
-      - name: Harden the runner (Audit all outbound calls)
-        uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
-        with:
-          egress-policy: audit
-
-      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
-        with:
-          fetch-depth: 0
-
-      - name: Get build tag
-        run: |
-          echo run:$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: [ debug, 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 }}
-      rerun-failed: false
-      test-cfg: '[{"pg_version":"v14", "lfc_state": "with-lfc"},
-                  {"pg_version":"v15", "lfc_state": "with-lfc"},
-                  {"pg_version":"v16", "lfc_state": "with-lfc"},
-                  {"pg_version":"v17", "lfc_state": "with-lfc"},
-                  {"pg_version":"v14", "lfc_state": "without-lfc"},
-                  {"pg_version":"v15", "lfc_state": "without-lfc"},
-                  {"pg_version":"v16", "lfc_state": "without-lfc"},
-                  {"pg_version":"v17", "lfc_state": "withouts-lfc"}]'
-    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: ${{ github.actor }}
-        password: ${{ secrets.GITHUB_TOKEN }}
-      options: --init
-
-    steps:
-      - name: Harden the runner (Audit all outbound calls)
-        uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
-        with:
-          egress-policy: audit
-
-      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
-
-      - name: Create Allure report
-        if: ${{ !cancelled() }}
-        id: create-allure-report
-        uses: ./.github/actions/allure-report-generate
-        with:
-          store-test-results-into-db: true
-          aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
-        env:
-          REGRESS_TEST_RESULT_CONNSTR_NEW: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}
-
-      - uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
-        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/build_and_test_with_sanitizers.yml

@@ -79,7 +79,6 @@ jobs:
       build-tools-image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
       build-tag: ${{ needs.tag.outputs.build-tag }}
       build-type: ${{ matrix.build-type }}
-      rerun-failed: false
       test-cfg: '[{"pg_version":"v17"}]'
       sanitizers: enabled
     secrets: inherit

.github/workflows/cloud-extensions.yml

@@ -10,10 +10,10 @@ on:
     - cron:  '45 1 * * *' # run once a day, timezone is utc
   workflow_dispatch: # adds ability to run this manually
     inputs:
-      region_id:
+      project_id:
         description: 'Project region id. If not set, the default region will be used'
         required: false
-        default: 'aws-us-east-2'
+        default: 'raspy-voice-43157743'
 
 defaults:
   run:
@@ -27,18 +27,18 @@ permissions:
 jobs:
   regress:
     env:
-      POSTGRES_DISTRIB_DIR: /__w/_temp/neon/pg_install
-      TEST_OUTPUT: /__w/_temp/test_output
+      POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
+      TEST_OUTPUT: /tmp/test_output
       BUILD_TYPE: remote
     strategy:
       fail-fast: false
       matrix:
-        pg-version: [16, 17]
+        pg-version: [17]
 
     runs-on: us-east-2
     container:
       # We use the neon-test-extensions image here as it contains the source code for the extensions.
-      image: ghcr.io/neondatabase/neon-test-extensions-v${{ matrix.pg-version }}:latest
+      image: ghcr.io/neondatabase/neon-test-extensions-v${{ matrix.pg-version }}:14928114423
       credentials:
         username: ${{ github.actor }}
         password: ${{ secrets.GITHUB_TOKEN }}
@@ -61,23 +61,37 @@ jobs:
             ULID=pgx_ulid
           fi
           LIBS=timescaledb:rag_bge_small_en_v15,rag_jina_reranker_v1_tiny_en:$ULID
-          settings=$(jq -c -n --arg libs $LIBS '{preload_libraries:{use_defaults:false,enabled_libraries:($libs| split(":"))}}')
+          settings=$(jq -c -n --arg libs $LIBS '{preload_libraries:{use_defaults:false,enabled_libraries:($libs| split(":"))}, compute_flags:{target_architecture:"x64"}}')
           echo settings=$settings >> $GITHUB_OUTPUT
 
-      - name: Create Neon Project
-        id: create-neon-project
-        uses: ./.github/actions/neon-project-create
-        with:
-          region_id: ${{ inputs.region_id || 'aws-us-east-2' }}
-          postgres_version: ${{ matrix.pg-version }}
-          project_settings: ${{ steps.project-settings.outputs.settings }}
-          api_key: ${{ secrets.NEON_STAGING_API_KEY }}
-
+      - name: Get the connection URI
+        id: connect-uri
+        run: |
+          res=$(curl -w "%{http_code}" -X GET \
+                "https://console-stage.neon.build/api/v2/projects/${PROJECT_ID}/connection_uri?database_name=neondb&role_name=neondb_owner&pooled=false" \
+                -H 'accept: application/json' \
+                -H "Authorization: Bearer ${API_KEY}" 
+          )
+          code=${res: -3}
+          echo ${code}
+          if [[ ${code} -ge 400 ]]; then
+            echo ${res::-3}
+            exit 1
+          fi
+          URI=$(echo ${res::-3} | jq -r .uri)
+          sed +x
+          password=$(echo "$URI" | sed -n 's|.*://[^:]*:\([^@]*\)@.*|\1|p')
+          echo ::add-mask::$password
+          echo uri=${URI} >> ${GITHUB_OUTPUT}
+        env:
+          PROJECT_ID: ${{ inputs.project_id }}
+          API_KEY: ${{ secrets.NEON_STAGING_API_KEY }}
+          
       - name: Run the regression tests
         run: /run-tests.sh -r /ext-src
         env:
-          BENCHMARK_CONNSTR: ${{ steps.create-neon-project.outputs.dsn }}
-          SKIP: "pg_hint_plan-src,pg_repack-src,pg_cron-src,plpgsql_check-src"
+          BENCHMARK_CONNSTR: ${{ steps.connect-uri.outputs.uri }}
+          SKIP: "hll-src,hypopg-src,ip4r-src,pg_cron-src,pg_graphql-src,pg_hint_plan-src,pg_ivm-src,pg_jsonschema-src,pg_repack-src,pg_roaringbitmap-src,pg_semver-src,pg_session_jwt-src,pg_tiktoken-src,pg_uuidv7-src,pgjwt-src,pgrag-src,pgtap-src,pgvector-src,pgx_ulid-src,plv8-src,postgresql-unit-src,prefix-src,rag_bge_small_en_v15-src,rag_jina_reranker_v1_tiny_en-src,rum-src,plpgsql_check-src"
 
       - name: Delete Neon Project
         if: ${{ always() }}

.github/workflows/cloud-regress.yml

@@ -27,8 +27,8 @@ permissions:
 jobs:
   regress:
     env:
-      POSTGRES_DISTRIB_DIR: /__w/_temp/neon/pg_install
-      TEST_OUTPUT: /__w/_temp/test_output
+      POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
+      TEST_OUTPUT: /tmp/test_output
       BUILD_TYPE: remote
     strategy:
       fail-fast: false
@@ -87,7 +87,7 @@ jobs:
         uses: ./.github/actions/download
         with:
           name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
-          path: /__w/_temp/neon/
+          path: /tmp/neon/
           prefix: latest
           aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 

.github/workflows/ingest_benchmark.yml

@@ -63,9 +63,9 @@ jobs:
       statuses: write
       id-token: write # aws-actions/configure-aws-credentials
     env:
-      PG_CONFIG: /__w/_temp/neon/pg_install/v16/bin/pg_config
-      PSQL: /__w/_temp/neon/pg_install/v16/bin/psql
-      PG_16_LIB_PATH: /__w/_temp/neon/pg_install/v16/lib
+      PG_CONFIG: /tmp/neon/pg_install/v16/bin/pg_config
+      PSQL: /tmp/neon/pg_install/v16/bin/psql
+      PG_16_LIB_PATH: /tmp/neon/pg_install/v16/lib
       PGCOPYDB: /pgcopydb/bin/pgcopydb
       PGCOPYDB_LIB_PATH: /pgcopydb/lib
     runs-on: [ self-hosted, us-east-2, x64 ]
@@ -96,7 +96,7 @@ jobs:
       uses: ./.github/actions/download
       with:
         name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
-        path: /__w/_temp/neon/
+        path: /tmp/neon/
         prefix: latest
         aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 

.github/workflows/large_oltp_benchmark.yml

@@ -33,19 +33,11 @@ jobs:
       fail-fast: false # allow other variants to continue even if one fails
       matrix:
         include:
-          # test only read-only custom scripts in new branch without database maintenance
-          - target: new_branch
-            custom_scripts: select_any_webhook_with_skew.sql@300 select_recent_webhook.sql@397 select_prefetch_webhook.sql@3
-            test_maintenance: false
-          # test all custom scripts in new branch with database maintenance
           - target: new_branch
             custom_scripts: insert_webhooks.sql@200 select_any_webhook_with_skew.sql@300 select_recent_webhook.sql@397 select_prefetch_webhook.sql@3 IUD_one_transaction.sql@100
-            test_maintenance: true
-          # test all custom scripts in reuse branch with database maintenance
           - target: reuse_branch
             custom_scripts: insert_webhooks.sql@200 select_any_webhook_with_skew.sql@300 select_recent_webhook.sql@397 select_prefetch_webhook.sql@3 IUD_one_transaction.sql@100
-            test_maintenance: true
-      max-parallel: 1 # we want to run each benchmark sequentially to not have noisy neighbors on shared storage (PS, SK)
+      max-parallel: 1 # we want to run each stripe size sequentially to be able to compare the results
     permissions:
       contents: write
       statuses: write
@@ -53,9 +45,9 @@ jobs:
     env:
       TEST_PG_BENCH_DURATIONS_MATRIX: "1h" # todo update to > 1 h
       TEST_PGBENCH_CUSTOM_SCRIPTS: ${{ matrix.custom_scripts }}
-      POSTGRES_DISTRIB_DIR: /__w/_temp/neon/pg_install
+      POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
       PG_VERSION: 16 # pre-determined by pre-determined project
-      TEST_OUTPUT: /__w/_temp/test_output
+      TEST_OUTPUT: /tmp/test_output
       BUILD_TYPE: remote
       PLATFORM: ${{ matrix.target }}
 
@@ -91,7 +83,7 @@ jobs:
       uses: ./.github/actions/download
       with:
         name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
-        path: /__w/_temp/neon/
+        path: /tmp/neon/
         prefix: latest
         aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
@@ -128,9 +120,9 @@ jobs:
       if: ${{ matrix.target == 'reuse_branch' }}
       env:
           BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr_without_pooler }}
-          PG_CONFIG: /__w/_temp/neon/pg_install/v16/bin/pg_config
-          PSQL: /__w/_temp/neon/pg_install/v16/bin/psql
-          PG_16_LIB_PATH: /__w/_temp/neon/pg_install/v16/lib
+          PG_CONFIG: /tmp/neon/pg_install/v16/bin/pg_config
+          PSQL: /tmp/neon/pg_install/v16/bin/psql
+          PG_16_LIB_PATH: /tmp/neon/pg_install/v16/lib
       run: |
         echo "$(date '+%Y-%m-%d %H:%M:%S') - Deleting rows in table webhook.incoming_webhooks from prior runs"
         export LD_LIBRARY_PATH=${PG_16_LIB_PATH}
@@ -153,7 +145,6 @@ jobs:
         PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
 
     - name: Benchmark database maintenance
-      if: ${{ matrix.test_maintenance == 'true' }}
       uses: ./.github/actions/run-python-test-set
       with:
         build_type: ${{ env.BUILD_TYPE }}

.github/workflows/large_oltp_growth.yml

@@ -1,175 +0,0 @@
-name: large oltp growth
-# workflow to grow the reuse branch of large oltp benchmark continuously (about 16 GB per run)
-
-on:
-  # uncomment to run on push for debugging your PR
-  # push:
-  #  branches: [ bodobolero/increase_large_oltp_workload ]
-
-  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 6 * * *'   # 06:00 UTC
-    - cron: '0 8 * * *'   # 08:00 UTC
-    - cron: '0 10 * * *'  # 10:00 UTC
-    - cron: '0 12 * * *'  # 12:00 UTC
-    - cron: '0 14 * * *'  # 14:00 UTC
-    - cron: '0 16 * * *'  # 16:00 UTC
-  workflow_dispatch: # adds ability to run this manually
-
-defaults:
-  run:
-    shell: bash -euxo pipefail {0}
-
-concurrency:
-  # Allow only one workflow globally because we need dedicated resources which only exist once
-  group: large-oltp-growth
-  cancel-in-progress: true
-
-permissions:
-  contents: read
-
-jobs:
-  oltp:
-    strategy:
-      fail-fast: false # allow other variants to continue even if one fails
-      matrix:
-        include:
-          # for now only grow the reuse branch, not the other branches.
-          - target: reuse_branch
-            custom_scripts:
-            - grow_action_blocks.sql
-            - grow_action_kwargs.sql
-            - grow_device_fingerprint_event.sql
-            - grow_edges.sql
-            - grow_hotel_rate_mapping.sql
-            - grow_ocr_pipeline_results_version.sql
-            - grow_priceline_raw_response.sql
-            - grow_relabled_transactions.sql
-            - grow_state_values.sql
-            - grow_values.sql
-            - grow_vertices.sql
-            - update_accounting_coding_body_tracking_category_selection.sql
-            - update_action_blocks.sql
-            - update_action_kwargs.sql
-            - update_denormalized_approval_workflow.sql
-            - update_device_fingerprint_event.sql
-            - update_edges.sql
-            - update_heron_transaction_enriched_log.sql
-            - update_heron_transaction_enrichment_requests.sql
-            - update_hotel_rate_mapping.sql
-            - update_incoming_webhooks.sql
-            - update_manual_transaction.sql
-            - update_ml_receipt_matching_log.sql
-            - update_ocr_pipeine_results_version.sql
-            - update_orc_pipeline_step_results.sql
-            - update_orc_pipeline_step_results_version.sql
-            - update_priceline_raw_response.sql
-            - update_quickbooks_transactions.sql
-            - update_raw_finicity_transaction.sql
-            - update_relabeled_transactions.sql
-            - update_state_values.sql
-            - update_stripe_authorization_event_log.sql
-            - update_transaction.sql
-            - update_values.sql
-            - update_vertices.sql
-      max-parallel: 1 # we want to run each growth workload sequentially (for now there is just one)
-    permissions:
-      contents: write
-      statuses: write
-      id-token: write # aws-actions/configure-aws-credentials
-    env:
-      TEST_PG_BENCH_DURATIONS_MATRIX: "1h"
-      TEST_PGBENCH_CUSTOM_SCRIPTS: ${{ join(matrix.custom_scripts, ' ') }}
-      POSTGRES_DISTRIB_DIR: /__w/_temp/neon/pg_install
-      PG_VERSION: 16 # pre-determined by pre-determined project
-      TEST_OUTPUT: /__w/_temp/test_output
-      BUILD_TYPE: remote
-      PLATFORM: ${{ matrix.target }}
-
-    runs-on: [ self-hosted, us-east-2, x64 ]
-    container:
-      image: ghcr.io/neondatabase/build-tools:pinned-bookworm
-      credentials:
-        username: ${{ github.actor }}
-        password: ${{ secrets.GITHUB_TOKEN }}
-      options: --init
-
-    steps:
-    - name: Harden the runner (Audit all outbound calls)
-      uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
-      with:
-        egress-policy: audit
-
-    - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
-
-    - name: Configure AWS credentials # necessary to download artefacts
-      uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
-      with:
-        aws-region: eu-central-1
-        role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
-        role-duration-seconds: 18000 # 5 hours is currently max associated with IAM role
-
-    - name: Download Neon artifact
-      uses: ./.github/actions/download
-      with:
-        name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
-        path: /__w/_temp/neon/
-        prefix: latest
-        aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
-
-    - name: Set up Connection String
-      id: set-up-connstr
-      run: |
-        case "${{ matrix.target }}" in
-          reuse_branch)
-          CONNSTR=${{ secrets.BENCHMARK_LARGE_OLTP_REUSE_CONNSTR }}
-          ;;
-          *)
-          echo >&2 "Unknown target=${{ matrix.target }}"
-          exit 1
-          ;;
-        esac
-
-        CONNSTR_WITHOUT_POOLER="${CONNSTR//-pooler/}"
-
-        echo "connstr=${CONNSTR}" >> $GITHUB_OUTPUT
-        echo "connstr_without_pooler=${CONNSTR_WITHOUT_POOLER}" >> $GITHUB_OUTPUT
-
-    - name: pgbench with custom-scripts
-      uses: ./.github/actions/run-python-test-set
-      with:
-        build_type: ${{ env.BUILD_TYPE }}
-        test_selection: performance
-        run_in_parallel: false
-        save_perf_report: true
-        extra_params: -m remote_cluster --timeout 7200 -k test_perf_oltp_large_tenant_growth
-        pg_version: ${{ env.PG_VERSION }}
-        aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
-      env:
-        BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
-        VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
-        PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
-
-    - name: Create Allure report
-      id: create-allure-report
-      if: ${{ !cancelled() }}
-      uses: ./.github/actions/allure-report-generate
-      with:
-        aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
-
-    - name: Post to a Slack channel
-      if: ${{ github.event.schedule && failure() }}
-      uses: slackapi/slack-github-action@fcfb566f8b0aab22203f066d80ca1d7e4b5d05b3 # v1.27.1
-      with:
-        channel-id: "C06KHQVQ7U3" # on-call-qa-staging-stream
-        slack-message: |
-          Periodic large oltp tenant growth increase: ${{ job.status }}
-          <${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}|GitHub Run>
-          <${{ steps.create-allure-report.outputs.report-url }}|Allure report>
-      env:
-        SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}

.github/workflows/neon_extra_builds.yml

@@ -63,10 +63,8 @@ jobs:
 
       - name: Filter out only v-string for build matrix
         id: postgres_changes
-        env:
-          CHANGES: ${{ steps.files_changed.outputs.changes }}
         run: |
-          v_strings_only_as_json_array=$(echo ${CHANGES} | jq '.[]|select(test("v\\d+"))' | jq --slurp -c)
+          v_strings_only_as_json_array=$(echo ${{ steps.files_changed.outputs.chnages }} | jq '.[]|select(test("v\\d+"))' | jq --slurp -c)
           echo "changes=${v_strings_only_as_json_array}" | tee -a "${GITHUB_OUTPUT}"
 
   check-macos-build:

.github/workflows/periodic_pagebench.yml

@@ -1,4 +1,4 @@
-name: Periodic pagebench performance test on unit-perf hetzner runner
+name: Periodic pagebench performance test on dedicated EC2 machine in eu-central-1 region
 
 on:
   schedule:
@@ -8,7 +8,7 @@ on:
     #        │   │ ┌───────────── day of the month (1 - 31)
     #        │   │ │ ┌───────────── month (1 - 12 or JAN-DEC)
     #        │   │ │ │ ┌───────────── day of the week (0 - 6 or SUN-SAT)
-    - cron: '0 */4 * * *' # Runs every 4 hours
+    - cron: '0 */3 * * *' # Runs every 3 hours
   workflow_dispatch: # Allows manual triggering of the workflow
     inputs:
       commit_hash:
@@ -16,11 +16,6 @@ on:
         description: 'The long neon repo commit hash for the system under test (pageserver) to be tested.'
         required: false
         default: ''
-      recreate_snapshots:
-        type: boolean
-        description: 'Recreate snapshots - !!!WARNING!!! We should only recreate snapshots if the previous ones are no longer compatible. Otherwise benchmarking results are not comparable across runs.'
-        required: false
-        default: false
 
 defaults:
   run:
@@ -34,13 +29,13 @@ permissions:
   contents: read
 
 jobs:
-  run_periodic_pagebench_test:
+  trigger_bench_on_ec2_machine_in_eu_central_1:
     permissions:
       id-token: write # aws-actions/configure-aws-credentials
       statuses: write
       contents: write
       pull-requests: write
-    runs-on: [ self-hosted, unit-perf ]
+    runs-on: [ self-hosted, small ]
     container:
       image: ghcr.io/neondatabase/build-tools:pinned-bookworm
       credentials:
@@ -49,13 +44,10 @@ jobs:
       options: --init
     timeout-minutes: 360  # Set the timeout to 6 hours
     env:
+      API_KEY: ${{ secrets.PERIODIC_PAGEBENCH_EC2_RUNNER_API_KEY }}
       RUN_ID: ${{ github.run_id }}
-      DEFAULT_PG_VERSION: 16
-      BUILD_TYPE: release
-      RUST_BACKTRACE: 1
-      # NEON_ENV_BUILDER_USE_OVERLAYFS_FOR_SNAPSHOTS: 1 - doesn't work without root in container
-      S3_BUCKET: neon-github-public-dev
-      PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
+      AWS_DEFAULT_REGION : "eu-central-1"
+      AWS_INSTANCE_ID : "i-02a59a3bf86bc7e74"
     steps:
     # we don't need the neon source code because we run everything remotely
     # however we still need the local github actions to run the allure step below
@@ -64,194 +56,99 @@ jobs:
       with:
         egress-policy: audit
 
-    - name: Set up the environment which depends on $RUNNER_TEMP on nvme drive
-      id: set-env
-      shell: bash -euxo pipefail {0}
-      run: |
-        {
-          echo "NEON_DIR=${RUNNER_TEMP}/neon"
-          echo "NEON_BIN=${RUNNER_TEMP}/neon/bin"
-          echo "POSTGRES_DISTRIB_DIR=${RUNNER_TEMP}/neon/pg_install"
-          echo "LD_LIBRARY_PATH=${RUNNER_TEMP}/neon/pg_install/v${DEFAULT_PG_VERSION}/lib"
-          echo "BACKUP_DIR=${RUNNER_TEMP}/instance_store/saved_snapshots"
-          echo "TEST_OUTPUT=${RUNNER_TEMP}/neon/test_output"
-          echo "PERF_REPORT_DIR=${RUNNER_TEMP}/neon/test_output/perf-report-local"
-          echo "ALLURE_DIR=${RUNNER_TEMP}/neon/test_output/allure-results"
-          echo "ALLURE_RESULTS_DIR=${RUNNER_TEMP}/neon/test_output/allure-results/results"
-        } >> "$GITHUB_ENV"
+    - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
 
-        echo "allure_results_dir=${RUNNER_TEMP}/neon/test_output/allure-results/results" >> "$GITHUB_OUTPUT"
+    - name: Show my own (github runner) external IP address - usefull for IP allowlisting
+      run: curl https://ifconfig.me
 
-    - uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
+    - name: Assume AWS OIDC role that allows to manage (start/stop/describe... EC machine)
+      uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
       with:
         aws-region: eu-central-1
-        role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
-        role-duration-seconds: 18000 # max 5 hours (needed in case commit hash is still being built)
+        role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_MANAGE_BENCHMARK_EC2_VMS_ARN }}
+        role-duration-seconds: 3600
+
+    - name: Start EC2 instance and wait for the instance to boot up
+      run: |
+        aws ec2 start-instances --instance-ids $AWS_INSTANCE_ID
+        aws ec2 wait instance-running --instance-ids $AWS_INSTANCE_ID
+        sleep 60 # sleep some time to allow cloudinit and our API server to start up
+
+    - name: Determine public IP of the EC2 instance and set env variable EC2_MACHINE_URL_US
+      run: |
+        public_ip=$(aws ec2 describe-instances --instance-ids $AWS_INSTANCE_ID --query 'Reservations[*].Instances[*].PublicIpAddress' --output text)
+        echo "Public IP of the EC2 instance: $public_ip"
+        echo "EC2_MACHINE_URL_US=https://${public_ip}:8443" >> $GITHUB_ENV
+
     - name: Determine commit hash
-      id: commit_hash
-      shell: bash -euxo pipefail {0}
       env:
         INPUT_COMMIT_HASH: ${{ github.event.inputs.commit_hash }}
       run: |
-        if [[ -z "${INPUT_COMMIT_HASH}" ]]; then
-          COMMIT_HASH=$(curl -s https://api.github.com/repos/neondatabase/neon/commits/main | jq -r '.sha')
-          echo "COMMIT_HASH=$COMMIT_HASH" >> $GITHUB_ENV
-          echo "commit_hash=$COMMIT_HASH" >> "$GITHUB_OUTPUT"
+        if [ -z "$INPUT_COMMIT_HASH" ]; then
+          echo "COMMIT_HASH=$(curl -s https://api.github.com/repos/neondatabase/neon/commits/main | jq -r '.sha')" >> $GITHUB_ENV
           echo "COMMIT_HASH_TYPE=latest" >> $GITHUB_ENV
         else
-          COMMIT_HASH="${INPUT_COMMIT_HASH}"
-          echo "COMMIT_HASH=$COMMIT_HASH" >> $GITHUB_ENV
-          echo "commit_hash=$COMMIT_HASH" >> "$GITHUB_OUTPUT"
+          echo "COMMIT_HASH=$INPUT_COMMIT_HASH" >> $GITHUB_ENV
           echo "COMMIT_HASH_TYPE=manual" >> $GITHUB_ENV
         fi
-    - name: Checkout the neon repository at given commit hash
-      uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
-      with:
-        ref: ${{ steps.commit_hash.outputs.commit_hash }}
 
-    # does not reuse ./.github/actions/download because we need to download the artifact for the given commit hash
-    # example artifact
-    # s3://neon-github-public-dev/artifacts/48b870bc078bd2c450eb7b468e743b9c118549bf/15036827400/1/neon-Linux-X64-release-artifact.tar.zst /instance_store/artifacts/neon-Linux-release-artifact.tar.zst
-    - name: Determine artifact S3_KEY for given commit hash and download and extract artifact
-      id: artifact_prefix
-      shell: bash -euxo pipefail {0}
-      env:
-        ARCHIVE: ${{ runner.temp }}/downloads/neon-${{ runner.os }}-${{ runner.arch }}-release-artifact.tar.zst
-        COMMIT_HASH: ${{ env.COMMIT_HASH }}
-        COMMIT_HASH_TYPE: ${{ env.COMMIT_HASH_TYPE }}
+    - name: Start Bench with run_id
       run: |
-        attempt=0
-        max_attempts=24 # 5 minutes * 24 = 2 hours
+        curl -k -X 'POST' \
+        "${EC2_MACHINE_URL_US}/start_test/${GITHUB_RUN_ID}" \
+        -H 'accept: application/json' \
+        -H 'Content-Type: application/json' \
+        -H "Authorization: Bearer $API_KEY" \
+        -d "{\"neonRepoCommitHash\": \"${COMMIT_HASH}\", \"neonRepoCommitHashType\": \"${COMMIT_HASH_TYPE}\"}"
 
-        while [[ $attempt -lt $max_attempts ]]; do
-          # the following command will fail until the artifacts are available ...
-          S3_KEY=$(aws s3api list-objects-v2 --bucket "$S3_BUCKET" --prefix "artifacts/$COMMIT_HASH/" \
-            | jq -r '.Contents[]?.Key' \
-            | grep "neon-${{ runner.os }}-${{ runner.arch }}-release-artifact.tar.zst" \
-            | sort --version-sort \
-            | tail -1) || true # ... thus ignore errors from the command
-          if [[ -n "${S3_KEY}" ]]; then
-            echo "Artifact found: $S3_KEY"
-            echo "S3_KEY=$S3_KEY" >> $GITHUB_ENV
+    - name: Poll Test Status
+      id: poll_step
+      run: |
+        status=""
+        while [[ "$status" != "failure" && "$status" != "success" ]]; do
+          response=$(curl -k -X 'GET' \
+          "${EC2_MACHINE_URL_US}/test_status/${GITHUB_RUN_ID}" \
+          -H 'accept: application/json' \
+          -H "Authorization: Bearer $API_KEY")
+          echo "Response: $response"
+          set +x
+          status=$(echo $response | jq -r '.status')
+          echo "Test status: $status"
+          if [[ "$status" == "failure" ]]; then
+            echo "Test failed"
+            exit 1 # Fail the job step if status is failure
+          elif [[ "$status" == "success" || "$status" == "null" ]]; then
             break
+          elif [[ "$status" == "too_many_runs" ]]; then
+            echo "Too many runs already running"
+            echo "too_many_runs=true" >> "$GITHUB_OUTPUT"
+            exit 1
           fi
-          
-          # Increment attempt counter and sleep for 5 minutes
-          attempt=$((attempt + 1))
-          echo "Attempt $attempt of $max_attempts to find artifacts in S3 bucket s3://$S3_BUCKET/artifacts/$COMMIT_HASH failed. Retrying in 5 minutes..."
-          sleep 300 # Sleep for 5 minutes
+
+          sleep 60 # Poll every 60 seconds
         done
 
-        if [[ -z "${S3_KEY}" ]]; then
-          echo "Error: artifact not found in S3 bucket s3://$S3_BUCKET/artifacts/$COMMIT_HASH" after 2 hours
-        else
-          mkdir -p $(dirname $ARCHIVE)
-          time aws s3 cp --only-show-errors s3://$S3_BUCKET/${S3_KEY} ${ARCHIVE}
-          mkdir -p ${NEON_DIR}
-          time tar -xf ${ARCHIVE} -C ${NEON_DIR}
-          rm -f ${ARCHIVE}
-        fi
-
-    - name: Download snapshots from S3
-      if: ${{ github.event_name != 'workflow_dispatch' || github.event.inputs.recreate_snapshots == 'false' || github.event.inputs.recreate_snapshots == '' }}
-      id: download_snapshots
-      shell: bash -euxo pipefail {0}
+    - name: Retrieve Test Logs
+      if: always() && steps.poll_step.outputs.too_many_runs != 'true'
       run: |
-        # Download the snapshots from S3
-        mkdir -p ${TEST_OUTPUT}
-        mkdir -p $BACKUP_DIR
-        cd $BACKUP_DIR
-        mkdir parts
-        cd parts
-        PART=$(aws s3api list-objects-v2 --bucket $S3_BUCKET --prefix performance/pagebench/ \
-          | jq -r '.Contents[]?.Key' \
-          | grep -E 'shared-snapshots-[0-9]{4}-[0-9]{2}-[0-9]{2}' \
-          | sort \
-          | tail -1)
-        echo "Latest PART: $PART"
-        if [[ -z "$PART" ]]; then
-          echo "ERROR: No matching S3 key found" >&2
-          exit 1
-        fi
-        S3_KEY=$(dirname $PART)
-        time aws s3 cp --only-show-errors --recursive s3://${S3_BUCKET}/$S3_KEY/ .
-        cd $TEST_OUTPUT
-        time cat $BACKUP_DIR/parts/* | zstdcat | tar --extract --preserve-permissions
-        rm -rf ${BACKUP_DIR}
+        curl -k -X 'GET' \
+        "${EC2_MACHINE_URL_US}/test_log/${GITHUB_RUN_ID}" \
+        -H 'accept: application/gzip' \
+        -H "Authorization: Bearer $API_KEY" \
+        --output "test_log_${GITHUB_RUN_ID}.gz"
 
-    - name: Cache poetry deps
-      uses: actions/cache@v4
-      with:
-        path: ~/.cache/pypoetry/virtualenvs
-        key: v2-${{ runner.os }}-${{ runner.arch }}-python-deps-bookworm-${{ hashFiles('poetry.lock') }}
-
-    - name: Install Python deps
-      shell: bash -euxo pipefail {0}
-      run: ./scripts/pysync
-
-    # we need high number of open files for pagebench
-    - name: show ulimits
-      shell: bash -euxo pipefail {0}
+    - name: Unzip Test Log and Print it into this job's log
+      if: always() && steps.poll_step.outputs.too_many_runs != 'true'
       run: |
-        ulimit -a
-
-    - name: Run pagebench testcase
-      shell: bash -euxo pipefail {0}
-      env:
-        CI: false  # need to override this env variable set by github to enforce using snapshots
-      run: |
-        export PLATFORM=hetzner-unit-perf-${COMMIT_HASH_TYPE}
-        # report the commit hash of the neon repository in the revision of the test results
-        export GITHUB_SHA=${COMMIT_HASH}
-        rm -rf ${PERF_REPORT_DIR}
-        rm -rf ${ALLURE_RESULTS_DIR}
-        mkdir -p ${PERF_REPORT_DIR}
-        mkdir -p ${ALLURE_RESULTS_DIR}
-        PARAMS="--alluredir=${ALLURE_RESULTS_DIR} --tb=short --verbose -rA"
-        EXTRA_PARAMS="--out-dir ${PERF_REPORT_DIR} --durations-path $TEST_OUTPUT/benchmark_durations.json"
-        # run only two selected tests
-        # environment set by parent:
-        # RUST_BACKTRACE=1 DEFAULT_PG_VERSION=16 BUILD_TYPE=release
-        ./scripts/pytest ${PARAMS} test_runner/performance/pageserver/pagebench/test_pageserver_max_throughput_getpage_at_latest_lsn.py::test_pageserver_characterize_throughput_with_n_tenants ${EXTRA_PARAMS}
-        ./scripts/pytest ${PARAMS} test_runner/performance/pageserver/pagebench/test_pageserver_max_throughput_getpage_at_latest_lsn.py::test_pageserver_characterize_latencies_with_1_client_and_throughput_with_many_clients_one_tenant ${EXTRA_PARAMS}
-
-    - name: upload the performance metrics to the Neon performance database which is used by grafana dashboards to display the results
-      shell: bash -euxo pipefail {0}
-      run: |
-        export REPORT_FROM="$PERF_REPORT_DIR"
-        export GITHUB_SHA=${COMMIT_HASH}
-        time ./scripts/generate_and_push_perf_report.sh
-
-    - name: Upload test results
-      if: ${{ !cancelled() }}
-      uses: ./.github/actions/allure-report-store
-      with:
-        report-dir:  ${{ steps.set-env.outputs.allure_results_dir }}
-        unique-key: ${{ env.BUILD_TYPE }}-${{ env.DEFAULT_PG_VERSION }}-${{ runner.arch }}
-        aws-oidc-role-arn:  ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        gzip -d "test_log_${GITHUB_RUN_ID}.gz"
+        cat "test_log_${GITHUB_RUN_ID}"
 
     - name: Create Allure report
-      id: create-allure-report
       if: ${{ !cancelled() }}
       uses: ./.github/actions/allure-report-generate
       with:
         aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
-    - name: Upload snapshots
-      if: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.recreate_snapshots != 'false' && github.event.inputs.recreate_snapshots != '' }}
-      id: upload_snapshots
-      shell: bash -euxo pipefail {0}
-      run: |
-        mkdir -p $BACKUP_DIR
-        cd $TEST_OUTPUT
-        tar --create --preserve-permissions --file - shared-snapshots | zstd -o $BACKUP_DIR/shared_snapshots.tar.zst
-        cd $BACKUP_DIR
-        mkdir parts
-        split -b 1G shared_snapshots.tar.zst ./parts/shared_snapshots.tar.zst.part.
-        SNAPSHOT_DATE=$(date +%F)  # YYYY-MM-DD
-        cd parts
-        time aws s3 cp --recursive . s3://${S3_BUCKET}/performance/pagebench/shared-snapshots-${SNAPSHOT_DATE}/
-
     - name: Post to a Slack channel
       if: ${{ github.event.schedule && failure() }}
       uses: slackapi/slack-github-action@fcfb566f8b0aab22203f066d80ca1d7e4b5d05b3 # v1.27.1
@@ -260,22 +157,26 @@ jobs:
         slack-message: "Periodic pagebench testing on dedicated hardware: ${{ job.status }}\n${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}"
       env:
         SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
-        
+
     - name: Cleanup Test Resources
       if: always()
-      shell: bash -euxo pipefail {0}
-      env:
-        ARCHIVE: ${{ runner.temp }}/downloads/neon-${{ runner.os }}-${{ runner.arch }}-release-artifact.tar.zst
       run: |
-        # Cleanup the test resources
-        if [[ -d "${BACKUP_DIR}" ]]; then
-          rm -rf ${BACKUP_DIR}
-        fi
-        if [[ -d "${TEST_OUTPUT}" ]]; then
-          rm -rf ${TEST_OUTPUT}
-        fi
-        if [[ -d "${NEON_DIR}" ]]; then
-          rm -rf ${NEON_DIR}
-        fi
-        rm -rf $(dirname $ARCHIVE)
+        curl -k -X 'POST' \
+        "${EC2_MACHINE_URL_US}/cleanup_test/${GITHUB_RUN_ID}" \
+        -H 'accept: application/json' \
+        -H "Authorization: Bearer $API_KEY" \
+        -d ''
 
+    - name: Assume AWS OIDC role that allows to manage (start/stop/describe... EC machine)
+      if: always() && steps.poll_step.outputs.too_many_runs != 'true'
+      uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
+      with:
+        aws-region: eu-central-1
+        role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_MANAGE_BENCHMARK_EC2_VMS_ARN }}
+        role-duration-seconds: 3600
+
+    - name: Stop EC2 instance and wait for the instance to be stopped
+      if: always() && steps.poll_step.outputs.too_many_runs != 'true'
+      run: |
+        aws ec2 stop-instances --instance-ids $AWS_INSTANCE_ID
+        aws ec2 wait instance-stopped --instance-ids $AWS_INSTANCE_ID

.github/workflows/pg-clients.yml

@@ -101,7 +101,7 @@ jobs:
         uses: ./.github/actions/download
         with:
           name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
-          path: /__w/_temp/neon/
+          path: /tmp/neon/
           prefix: latest
           aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
@@ -176,7 +176,7 @@ jobs:
       uses: ./.github/actions/download
       with:
         name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
-        path: /__w/_temp/neon/
+        path: /tmp/neon/
         prefix: latest
         aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 

.github/workflows/random-ops-test.yml

@@ -35,7 +35,7 @@ env:
 jobs:
   run-random-rests:
     env:
-      POSTGRES_DISTRIB_DIR: /__w/_temp/neon/pg_install
+      POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
     runs-on: small
     permissions:
       id-token: write
@@ -64,7 +64,7 @@ jobs:
         uses: ./.github/actions/download
         with:
           name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
-          path: /__w/_temp/neon/
+          path: /tmp/neon/
           prefix: latest
           aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 

.gitignore

@@ -1,5 +1,4 @@
 /artifact_cache
-/build
 /pg_install
 /target
 /tmp_check

Cargo.lock

@@ -753,7 +753,6 @@ dependencies = [
  "axum",
  "axum-core",
  "bytes",
- "form_urlencoded",
  "futures-util",
  "headers",
  "http 1.1.0",
@@ -762,8 +761,6 @@ dependencies = [
  "mime",
  "pin-project-lite",
  "serde",
- "serde_html_form",
- "serde_path_to_error",
  "tower 0.5.2",
  "tower-layer",
  "tower-service",
@@ -903,6 +900,12 @@ version = "0.13.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9e1b586273c5702936fe7b7d6896644d8be71e6314cfe09d3167c95f712589e8"
 
+[[package]]
+name = "base64"
+version = "0.20.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0ea22880d78093b0cbe17c89f64a7d457941e65759157ec6cb31a31d652b05e5"
+
 [[package]]
 name = "base64"
 version = "0.21.7"
@@ -1109,12 +1112,6 @@ version = "1.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
 
-[[package]]
-name = "cfg_aliases"
-version = "0.2.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "613afe47fcd5fac7ccf1db93babcb082c5994d996f20b8b159f2ad1658eb5724"
-
 [[package]]
 name = "cgroups-rs"
 version = "0.3.3"
@@ -1273,7 +1270,7 @@ version = "0.1.0"
 dependencies = [
  "anyhow",
  "chrono",
- "indexmap 2.9.0",
+ "indexmap 2.0.1",
  "jsonwebtoken",
  "regex",
  "remote_storage",
@@ -1294,7 +1291,7 @@ dependencies = [
  "aws-smithy-types",
  "axum",
  "axum-extra",
- "base64 0.22.1",
+ "base64 0.13.1",
  "bytes",
  "camino",
  "cfg-if",
@@ -1305,11 +1302,10 @@ dependencies = [
  "flate2",
  "futures",
  "http 1.1.0",
- "indexmap 2.9.0",
- "itertools 0.10.5",
+ "indexmap 2.0.1",
  "jsonwebtoken",
  "metrics",
- "nix 0.30.1",
+ "nix 0.27.1",
  "notify",
  "num_cpus",
  "once_cell",
@@ -1420,7 +1416,7 @@ name = "control_plane"
 version = "0.1.0"
 dependencies = [
  "anyhow",
- "base64 0.22.1",
+ "base64 0.13.1",
  "camino",
  "clap",
  "comfy-table",
@@ -1432,7 +1428,7 @@ dependencies = [
  "humantime-serde",
  "hyper 0.14.30",
  "jsonwebtoken",
- "nix 0.30.1",
+ "nix 0.27.1",
  "once_cell",
  "pageserver_api",
  "pageserver_client",
@@ -1442,7 +1438,6 @@ dependencies = [
  "regex",
  "reqwest",
  "safekeeper_api",
- "safekeeper_client",
  "scopeguard",
  "serde",
  "serde_json",
@@ -2052,7 +2047,6 @@ dependencies = [
  "axum-extra",
  "camino",
  "camino-tempfile",
- "clap",
  "futures",
  "http-body-util",
  "itertools 0.10.5",
@@ -2596,7 +2590,7 @@ dependencies = [
  "futures-sink",
  "futures-util",
  "http 0.2.9",
- "indexmap 2.9.0",
+ "indexmap 2.0.1",
  "slab",
  "tokio",
  "tokio-util",
@@ -2615,7 +2609,7 @@ dependencies = [
  "futures-sink",
  "futures-util",
  "http 1.1.0",
- "indexmap 2.9.0",
+ "indexmap 2.0.1",
  "slab",
  "tokio",
  "tokio-util",
@@ -2862,14 +2856,14 @@ dependencies = [
  "pprof",
  "regex",
  "routerify",
- "rustls 0.23.27",
+ "rustls 0.23.18",
  "rustls-pemfile 2.1.1",
  "serde",
  "serde_json",
  "serde_path_to_error",
  "thiserror 1.0.69",
  "tokio",
- "tokio-rustls 0.26.2",
+ "tokio-rustls 0.26.0",
  "tokio-stream",
  "tokio-util",
  "tracing",
@@ -3199,12 +3193,12 @@ dependencies = [
 
 [[package]]
 name = "indexmap"
-version = "2.9.0"
+version = "2.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cea70ddb795996207ad57735b50c5982d8844f38ba9ee5f1aedcfb708a2aa11e"
+checksum = "ad227c3af19d4914570ad36d30409928b75967c298feb9ea1969db3a610bb14e"
 dependencies = [
  "equivalent",
- "hashbrown 0.15.2",
+ "hashbrown 0.14.5",
  "serde",
 ]
 
@@ -3227,7 +3221,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "232929e1d75fe899576a3d5c7416ad0d88dbfbb3c3d6aa00873a7408a50ddb88"
 dependencies = [
  "ahash",
- "indexmap 2.9.0",
+ "indexmap 2.0.1",
  "is-terminal",
  "itoa",
  "log",
@@ -3250,7 +3244,7 @@ dependencies = [
  "crossbeam-utils",
  "dashmap 6.1.0",
  "env_logger",
- "indexmap 2.9.0",
+ "indexmap 2.0.1",
  "itoa",
  "log",
  "num-format",
@@ -3517,9 +3511,9 @@ dependencies = [
 
 [[package]]
 name = "libc"
-version = "0.2.172"
+version = "0.2.169"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d750af042f7ef4f724306de029d18836c26c1765a54a6a3f094cbd23a7267ffa"
+checksum = "b5aba8db14291edd000dfcc4d620c7ebfb122c613afb886ca8803fa4e128a20a"
 
 [[package]]
 name = "libloading"
@@ -3793,16 +3787,6 @@ version = "0.8.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e5ce46fe64a9d73be07dcbe690a38ce1b293be448fd8ce1e6c1b8062c9f72c6a"
 
-[[package]]
-name = "neon-shmem"
-version = "0.1.0"
-dependencies = [
- "nix 0.30.1",
- "tempfile",
- "thiserror 1.0.69",
- "workspace_hack",
-]
-
 [[package]]
 name = "never-say-never"
 version = "6.6.666"
@@ -3836,13 +3820,12 @@ dependencies = [
 
 [[package]]
 name = "nix"
-version = "0.30.1"
+version = "0.27.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "74523f3a35e05aba87a1d978330aef40f67b0304ac79c1c00b294c9830543db6"
+checksum = "2eb04e9c688eff1c89d72b407f168cf79bb9e867a9d3323ed6c01519eb9cc053"
 dependencies = [
  "bitflags 2.8.0",
  "cfg-if",
- "cfg_aliases",
  "libc",
  "memoffset 0.9.0",
 ]
@@ -3897,16 +3880,6 @@ dependencies = [
  "winapi",
 ]
 
-[[package]]
-name = "nu-ansi-term"
-version = "0.46.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "77a8165726e8236064dbb45459242600304b42a5ea24ee2948e18e023bf7ba84"
-dependencies = [
- "overload",
- "winapi",
-]
-
 [[package]]
 name = "num"
 version = "0.4.1"
@@ -4111,7 +4084,7 @@ dependencies = [
  "opentelemetry-http",
  "opentelemetry-proto",
  "opentelemetry_sdk",
- "prost 0.13.5",
+ "prost 0.13.3",
  "reqwest",
  "thiserror 1.0.69",
 ]
@@ -4124,8 +4097,8 @@ checksum = "a6e05acbfada5ec79023c85368af14abd0b307c015e9064d249b2a950ef459a6"
 dependencies = [
  "opentelemetry",
  "opentelemetry_sdk",
- "prost 0.13.5",
- "tonic 0.12.3",
+ "prost 0.13.3",
+ "tonic",
 ]
 
 [[package]]
@@ -4191,12 +4164,6 @@ version = "0.5.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "4030760ffd992bef45b0ae3f10ce1aba99e33464c90d14dd7c039884963ddc7a"
 
-[[package]]
-name = "overload"
-version = "0.1.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b15813163c1d831bf4a13c3610c05c0d03b39feb07f7e09fa234dac9b15aaf39"
-
 [[package]]
 name = "p256"
 version = "0.11.1"
@@ -4235,8 +4202,6 @@ name = "pagebench"
 version = "0.1.0"
 dependencies = [
  "anyhow",
- "async-trait",
- "bytes",
  "camino",
  "clap",
  "futures",
@@ -4245,17 +4210,13 @@ dependencies = [
  "humantime-serde",
  "pageserver_api",
  "pageserver_client",
- "pageserver_page_api",
  "rand 0.8.5",
  "reqwest",
  "serde",
  "serde_json",
  "tokio",
- "tokio-stream",
  "tokio-util",
- "tonic 0.13.1",
  "tracing",
- "url",
  "utils",
  "workspace_hack",
 ]
@@ -4307,10 +4268,8 @@ dependencies = [
  "enumset",
  "fail",
  "futures",
- "hashlink",
  "hex",
  "hex-literal",
- "http 1.1.0",
  "http-utils",
  "humantime",
  "humantime-serde",
@@ -4320,14 +4279,13 @@ dependencies = [
  "jsonwebtoken",
  "md5",
  "metrics",
- "nix 0.30.1",
+ "nix 0.27.1",
  "num-traits",
  "num_cpus",
  "once_cell",
  "pageserver_api",
  "pageserver_client",
  "pageserver_compaction",
- "pageserver_page_api",
  "pem",
  "pin-project-lite",
  "postgres-protocol",
@@ -4335,9 +4293,7 @@ dependencies = [
  "postgres_backend",
  "postgres_connection",
  "postgres_ffi",
- "postgres_ffi_types",
  "postgres_initdb",
- "posthog_client_lite",
  "pprof",
  "pq_proto",
  "procfs",
@@ -4348,7 +4304,7 @@ dependencies = [
  "reqwest",
  "rpds",
  "rstest",
- "rustls 0.23.27",
+ "rustls 0.23.18",
  "scopeguard",
  "send-future",
  "serde",
@@ -4367,17 +4323,13 @@ dependencies = [
  "tokio-epoll-uring",
  "tokio-io-timeout",
  "tokio-postgres",
- "tokio-rustls 0.26.2",
+ "tokio-rustls 0.26.0",
  "tokio-stream",
  "tokio-tar",
  "tokio-util",
  "toml_edit",
- "tonic 0.13.1",
- "tonic-reflection",
- "tower 0.5.2",
  "tracing",
  "tracing-utils",
- "twox-hash",
  "url",
  "utils",
  "uuid",
@@ -4402,10 +4354,10 @@ dependencies = [
  "humantime",
  "humantime-serde",
  "itertools 0.10.5",
- "nix 0.30.1",
+ "nix 0.27.1",
  "once_cell",
  "postgres_backend",
- "postgres_ffi_types",
+ "postgres_ffi",
  "rand 0.8.5",
  "remote_storage",
  "reqwest",
@@ -4463,26 +4415,6 @@ dependencies = [
  "workspace_hack",
 ]
 
-[[package]]
-name = "pageserver_page_api"
-version = "0.1.0"
-dependencies = [
- "anyhow",
- "bytes",
- "futures",
- "pageserver_api",
- "postgres_ffi",
- "prost 0.13.5",
- "strum",
- "strum_macros",
- "thiserror 1.0.69",
- "tokio",
- "tonic 0.13.1",
- "tonic-build",
- "utils",
- "workspace_hack",
-]
-
 [[package]]
 name = "papaya"
 version = "0.2.1"
@@ -4819,7 +4751,7 @@ dependencies = [
 name = "postgres-protocol2"
 version = "0.1.0"
 dependencies = [
- "base64 0.22.1",
+ "base64 0.20.0",
  "byteorder",
  "bytes",
  "fallible-iterator",
@@ -4859,14 +4791,14 @@ dependencies = [
  "bytes",
  "once_cell",
  "pq_proto",
- "rustls 0.23.27",
+ "rustls 0.23.18",
  "rustls-pemfile 2.1.1",
  "serde",
  "thiserror 1.0.69",
  "tokio",
  "tokio-postgres",
  "tokio-postgres-rustls",
- "tokio-rustls 0.26.2",
+ "tokio-rustls 0.26.0",
  "tokio-util",
  "tracing",
 ]
@@ -4896,7 +4828,6 @@ dependencies = [
  "memoffset 0.9.0",
  "once_cell",
  "postgres",
- "postgres_ffi_types",
  "pprof",
  "regex",
  "serde",
@@ -4905,14 +4836,6 @@ dependencies = [
  "utils",
 ]
 
-[[package]]
-name = "postgres_ffi_types"
-version = "0.1.0"
-dependencies = [
- "thiserror 1.0.69",
- "workspace_hack",
-]
-
 [[package]]
 name = "postgres_initdb"
 version = "0.1.0"
@@ -4924,24 +4847,6 @@ dependencies = [
  "workspace_hack",
 ]
 
-[[package]]
-name = "posthog_client_lite"
-version = "0.1.0"
-dependencies = [
- "anyhow",
- "arc-swap",
- "reqwest",
- "serde",
- "serde_json",
- "sha2",
- "thiserror 1.0.69",
- "tokio",
- "tokio-util",
- "tracing",
- "tracing-utils",
- "workspace_hack",
-]
-
 [[package]]
 name = "powerfmt"
 version = "0.2.0"
@@ -4987,7 +4892,7 @@ dependencies = [
  "inferno 0.12.0",
  "num",
  "paste",
- "prost 0.13.5",
+ "prost 0.13.3",
 ]
 
 [[package]]
@@ -5092,12 +4997,12 @@ dependencies = [
 
 [[package]]
 name = "prost"
-version = "0.13.5"
+version = "0.13.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2796faa41db3ec313a31f7624d9286acf277b52de526150b7e69f3debf891ee5"
+checksum = "7b0487d90e047de87f984913713b85c601c05609aad5b0df4b4573fbf69aa13f"
 dependencies = [
  "bytes",
- "prost-derive 0.13.5",
+ "prost-derive 0.13.3",
 ]
 
 [[package]]
@@ -5135,7 +5040,7 @@ dependencies = [
  "once_cell",
  "petgraph",
  "prettyplease",
- "prost 0.13.5",
+ "prost 0.13.3",
  "prost-types 0.13.3",
  "regex",
  "syn 2.0.100",
@@ -5157,9 +5062,9 @@ dependencies = [
 
 [[package]]
 name = "prost-derive"
-version = "0.13.5"
+version = "0.13.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8a56d757972c98b346a9b766e3f02746cde6dd1cd1d1d563472929fdd74bec4d"
+checksum = "e9552f850d5f0964a4e4d0bf306459ac29323ddfbae05e35a7c0d35cb0803cc5"
 dependencies = [
  "anyhow",
  "itertools 0.12.1",
@@ -5183,7 +5088,7 @@ version = "0.13.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "4759aa0d3a6232fb8dbdb97b61de2c20047c68aca932c7ed76da9d788508d670"
 dependencies = [
- "prost 0.13.5",
+ "prost 0.13.3",
 ]
 
 [[package]]
@@ -5200,7 +5105,7 @@ dependencies = [
  "aws-config",
  "aws-sdk-iam",
  "aws-sigv4",
- "base64 0.22.1",
+ "base64 0.13.1",
  "bstr",
  "bytes",
  "camino",
@@ -5231,7 +5136,7 @@ dependencies = [
  "hyper 0.14.30",
  "hyper 1.4.1",
  "hyper-util",
- "indexmap 2.9.0",
+ "indexmap 2.0.1",
  "ipnet",
  "itertools 0.10.5",
  "itoa",
@@ -5265,7 +5170,7 @@ dependencies = [
  "rsa",
  "rstest",
  "rustc-hash 1.1.0",
- "rustls 0.23.27",
+ "rustls 0.23.18",
  "rustls-native-certs 0.8.0",
  "rustls-pemfile 2.1.1",
  "scopeguard",
@@ -5284,14 +5189,13 @@ dependencies = [
  "tokio",
  "tokio-postgres",
  "tokio-postgres2",
- "tokio-rustls 0.26.2",
+ "tokio-rustls 0.26.0",
  "tokio-tungstenite 0.21.0",
  "tokio-util",
  "tracing",
  "tracing-log",
  "tracing-opentelemetry",
  "tracing-subscriber",
- "tracing-test",
  "tracing-utils",
  "try-lock",
  "typed-json",
@@ -5508,13 +5412,13 @@ dependencies = [
  "num-bigint",
  "percent-encoding",
  "pin-project-lite",
- "rustls 0.23.27",
+ "rustls 0.23.18",
  "rustls-native-certs 0.8.0",
  "ryu",
  "sha1_smol",
  "socket2",
  "tokio",
- "tokio-rustls 0.26.2",
+ "tokio-rustls 0.26.0",
  "tokio-util",
  "url",
 ]
@@ -5962,15 +5866,15 @@ dependencies = [
 
 [[package]]
 name = "rustls"
-version = "0.23.27"
+version = "0.23.18"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "730944ca083c1c233a75c09f199e973ca499344a2b7ba9e755c457e86fb4a321"
+checksum = "9c9cc1d47e243d655ace55ed38201c19ae02c148ae56412ab8750e8f0166ab7f"
 dependencies = [
  "log",
  "once_cell",
  "ring",
  "rustls-pki-types",
- "rustls-webpki 0.103.3",
+ "rustls-webpki 0.102.8",
  "subtle",
  "zeroize",
 ]
@@ -6059,17 +5963,6 @@ dependencies = [
  "untrusted",
 ]
 
-[[package]]
-name = "rustls-webpki"
-version = "0.103.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e4a72fe2bcf7a6ac6fd7d0b9e5cb68aeb7d4c0a0271730218b3e92d43b4eb435"
-dependencies = [
- "ring",
- "rustls-pki-types",
- "untrusted",
-]
-
 [[package]]
 name = "rustversion"
 version = "1.0.12"
@@ -6121,7 +6014,7 @@ dependencies = [
  "regex",
  "remote_storage",
  "reqwest",
- "rustls 0.23.27",
+ "rustls 0.23.18",
  "safekeeper_api",
  "safekeeper_client",
  "scopeguard",
@@ -6138,7 +6031,7 @@ dependencies = [
  "tokio",
  "tokio-io-timeout",
  "tokio-postgres",
- "tokio-rustls 0.26.2",
+ "tokio-rustls 0.26.0",
  "tokio-stream",
  "tokio-tar",
  "tokio-util",
@@ -6310,7 +6203,7 @@ checksum = "255914a8e53822abd946e2ce8baa41d4cded6b8e938913b7f7b9da5b7ab44335"
 dependencies = [
  "httpdate",
  "reqwest",
- "rustls 0.23.27",
+ "rustls 0.23.18",
  "sentry-backtrace",
  "sentry-contexts",
  "sentry-core",
@@ -6435,19 +6328,6 @@ dependencies = [
  "syn 2.0.100",
 ]
 
-[[package]]
-name = "serde_html_form"
-version = "0.2.7"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9d2de91cf02bbc07cde38891769ccd5d4f073d22a40683aa4bc7a95781aaa2c4"
-dependencies = [
- "form_urlencoded",
- "indexmap 2.9.0",
- "itoa",
- "ryu",
- "serde",
-]
-
 [[package]]
 name = "serde_json"
 version = "1.0.125"
@@ -6504,17 +6384,15 @@ dependencies = [
 
 [[package]]
 name = "serde_with"
-version = "3.12.0"
+version = "2.3.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d6b6f7f2fcb69f747921f79f3926bd1e203fce4fef62c268dd3abfb6d86029aa"
+checksum = "07ff71d2c147a7b57362cead5e22f772cd52f6ab31cfcd9edcd7f6aeb2a0afbe"
 dependencies = [
- "base64 0.22.1",
+ "base64 0.13.1",
  "chrono",
  "hex",
  "indexmap 1.9.3",
- "indexmap 2.9.0",
  "serde",
- "serde_derive",
  "serde_json",
  "serde_with_macros",
  "time",
@@ -6522,9 +6400,9 @@ dependencies = [
 
 [[package]]
 name = "serde_with_macros"
-version = "3.12.0"
+version = "2.3.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8d00caa5193a3c8362ac2b73be6b9e768aa5a4b2f721d8f4b339600c3cb51f8e"
+checksum = "881b6f881b17d13214e5d494c939ebab463d01264ce1811e9d4ac3a882e7695f"
 dependencies = [
  "darling",
  "proc-macro2",
@@ -6754,11 +6632,11 @@ dependencies = [
  "metrics",
  "once_cell",
  "parking_lot 0.12.1",
- "prost 0.13.5",
- "rustls 0.23.27",
+ "prost 0.13.3",
+ "rustls 0.23.18",
  "tokio",
- "tokio-rustls 0.26.2",
- "tonic 0.13.1",
+ "tokio-rustls 0.26.0",
+ "tonic",
  "tonic-build",
  "tracing",
  "utils",
@@ -6800,7 +6678,7 @@ dependencies = [
  "regex",
  "reqwest",
  "routerify",
- "rustls 0.23.27",
+ "rustls 0.23.18",
  "rustls-native-certs 0.8.0",
  "safekeeper_api",
  "safekeeper_client",
@@ -6815,7 +6693,7 @@ dependencies = [
  "tokio",
  "tokio-postgres",
  "tokio-postgres-rustls",
- "tokio-rustls 0.26.2",
+ "tokio-rustls 0.26.0",
  "tokio-util",
  "tracing",
  "utils",
@@ -6853,7 +6731,7 @@ dependencies = [
  "postgres_ffi",
  "remote_storage",
  "reqwest",
- "rustls 0.23.27",
+ "rustls 0.23.18",
  "rustls-native-certs 0.8.0",
  "serde",
  "serde_json",
@@ -7387,10 +7265,10 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "04fb792ccd6bbcd4bba408eb8a292f70fc4a3589e5d793626f45190e6454b6ab"
 dependencies = [
  "ring",
- "rustls 0.23.27",
+ "rustls 0.23.18",
  "tokio",
  "tokio-postgres",
- "tokio-rustls 0.26.2",
+ "tokio-rustls 0.26.0",
  "x509-certificate",
 ]
 
@@ -7434,11 +7312,12 @@ dependencies = [
 
 [[package]]
 name = "tokio-rustls"
-version = "0.26.2"
+version = "0.26.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8e727b36a1a0e8b74c376ac2211e40c2c8af09fb4013c60d910495810f008e9b"
+checksum = "0c7bc40d0e5a97695bb96e27995cd3a08538541b0a846f65bba7a359f36700d4"
 dependencies = [
- "rustls 0.23.27",
+ "rustls 0.23.18",
+ "rustls-pki-types",
  "tokio",
 ]
 
@@ -7536,7 +7415,7 @@ version = "0.22.14"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f21c7aaf97f1bd9ca9d4f9e73b0a6c74bd5afef56f2bc931943a6e1c37e04e38"
 dependencies = [
- "indexmap 2.9.0",
+ "indexmap 2.0.1",
  "serde",
  "serde_spanned",
  "toml_datetime",
@@ -7555,53 +7434,28 @@ dependencies = [
  "http 1.1.0",
  "http-body 1.0.0",
  "http-body-util",
- "percent-encoding",
- "pin-project",
- "prost 0.13.5",
- "tokio-stream",
- "tower-layer",
- "tower-service",
- "tracing",
-]
-
-[[package]]
-name = "tonic"
-version = "0.13.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7e581ba15a835f4d9ea06c55ab1bd4dce26fc53752c69a04aac00703bfb49ba9"
-dependencies = [
- "async-trait",
- "axum",
- "base64 0.22.1",
- "bytes",
- "flate2",
- "h2 0.4.4",
- "http 1.1.0",
- "http-body 1.0.0",
- "http-body-util",
  "hyper 1.4.1",
  "hyper-timeout",
  "hyper-util",
  "percent-encoding",
  "pin-project",
- "prost 0.13.5",
+ "prost 0.13.3",
  "rustls-native-certs 0.8.0",
- "socket2",
+ "rustls-pemfile 2.1.1",
  "tokio",
- "tokio-rustls 0.26.2",
+ "tokio-rustls 0.26.0",
  "tokio-stream",
- "tower 0.5.2",
+ "tower 0.4.13",
  "tower-layer",
  "tower-service",
  "tracing",
- "zstd",
 ]
 
 [[package]]
 name = "tonic-build"
-version = "0.13.1"
+version = "0.12.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "eac6f67be712d12f0b41328db3137e0d0757645d8904b4cb7d51cd9c2279e847"
+checksum = "9557ce109ea773b399c9b9e5dca39294110b74f1f342cb347a80d1fce8c26a11"
 dependencies = [
  "prettyplease",
  "proc-macro2",
@@ -7611,19 +7465,6 @@ dependencies = [
  "syn 2.0.100",
 ]
 
-[[package]]
-name = "tonic-reflection"
-version = "0.13.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f9687bd5bfeafebdded2356950f278bba8226f0b32109537c4253406e09aafe1"
-dependencies = [
- "prost 0.13.5",
- "prost-types 0.13.3",
- "tokio",
- "tokio-stream",
- "tonic 0.13.1",
-]
-
 [[package]]
 name = "tower"
 version = "0.4.13"
@@ -7632,11 +7473,16 @@ checksum = "b8fa9be0de6cf49e536ce1851f987bd21a43b771b09473c3549a6c853db37c1c"
 dependencies = [
  "futures-core",
  "futures-util",
+ "indexmap 1.9.3",
  "pin-project",
  "pin-project-lite",
+ "rand 0.8.5",
+ "slab",
  "tokio",
+ "tokio-util",
  "tower-layer",
  "tower-service",
+ "tracing",
 ]
 
 [[package]]
@@ -7647,12 +7493,9 @@ checksum = "d039ad9159c98b70ecfd540b2573b97f7f52c3e8d9f8ad57a24b916a536975f9"
 dependencies = [
  "futures-core",
  "futures-util",
- "indexmap 2.9.0",
  "pin-project-lite",
- "slab",
  "sync_wrapper 1.0.1",
  "tokio",
- "tokio-util",
  "tower-layer",
  "tower-service",
  "tracing",
@@ -7803,7 +7646,6 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e8189decb5ac0fa7bc8b96b7cb9b2701d60d48805aca84a238004d665fcc4008"
 dependencies = [
  "matchers",
- "nu-ansi-term",
  "once_cell",
  "regex",
  "serde",
@@ -7817,27 +7659,6 @@ dependencies = [
  "tracing-serde",
 ]
 
-[[package]]
-name = "tracing-test"
-version = "0.2.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "557b891436fe0d5e0e363427fc7f217abf9ccd510d5136549847bdcbcd011d68"
-dependencies = [
- "tracing-core",
- "tracing-subscriber",
- "tracing-test-macro",
-]
-
-[[package]]
-name = "tracing-test-macro"
-version = "0.2.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "04659ddb06c87d233c566112c1c9c5b9e98256d9af50ec3bc9c8327f873a7568"
-dependencies = [
- "quote",
- "syn 2.0.100",
-]
-
 [[package]]
 name = "tracing-utils"
 version = "0.1.0"
@@ -7980,7 +7801,7 @@ dependencies = [
  "base64 0.22.1",
  "log",
  "once_cell",
- "rustls 0.23.27",
+ "rustls 0.23.18",
  "rustls-pki-types",
  "url",
  "webpki-roots",
@@ -8063,7 +7884,7 @@ dependencies = [
  "humantime",
  "jsonwebtoken",
  "metrics",
- "nix 0.30.1",
+ "nix 0.27.1",
  "once_cell",
  "pem",
  "pin-project-lite",
@@ -8174,9 +7995,8 @@ dependencies = [
  "futures",
  "pageserver_api",
  "postgres_ffi",
- "postgres_ffi_types",
  "pprof",
- "prost 0.13.5",
+ "prost 0.13.3",
  "remote_storage",
  "serde",
  "serde_json",
@@ -8596,8 +8416,7 @@ dependencies = [
  "ahash",
  "anstream",
  "anyhow",
- "axum",
- "axum-core",
+ "base64 0.13.1",
  "base64 0.21.7",
  "base64ct",
  "bytes",
@@ -8631,14 +8450,14 @@ dependencies = [
  "hyper 0.14.30",
  "hyper 1.4.1",
  "hyper-util",
- "indexmap 2.9.0",
+ "indexmap 1.9.3",
+ "indexmap 2.0.1",
  "itertools 0.12.1",
  "lazy_static",
  "libc",
  "log",
  "memchr",
  "nix 0.26.4",
- "nix 0.30.1",
  "nom",
  "num",
  "num-bigint",
@@ -8652,16 +8471,16 @@ dependencies = [
  "parquet",
  "prettyplease",
  "proc-macro2",
- "prost 0.13.5",
+ "prost 0.13.3",
  "quote",
  "rand 0.8.5",
  "regex",
  "regex-automata 0.4.3",
  "regex-syntax 0.8.2",
  "reqwest",
- "rustls 0.23.27",
+ "rustls 0.23.18",
  "rustls-pki-types",
- "rustls-webpki 0.103.3",
+ "rustls-webpki 0.102.8",
  "scopeguard",
  "sec1 0.7.3",
  "serde",
@@ -8679,15 +8498,15 @@ dependencies = [
  "time",
  "time-macros",
  "tokio",
- "tokio-rustls 0.26.2",
+ "tokio-rustls 0.26.0",
  "tokio-stream",
  "tokio-util",
  "toml_edit",
- "tower 0.5.2",
+ "tonic",
+ "tower 0.4.13",
  "tracing",
  "tracing-core",
  "tracing-log",
- "tracing-subscriber",
  "url",
  "uuid",
  "zeroize",

Cargo.toml

@@ -9,7 +9,6 @@ members = [
     "pageserver/ctl",
     "pageserver/client",
     "pageserver/pagebench",
-    "pageserver/page_api",
     "proxy",
     "safekeeper",
     "safekeeper/client",
@@ -22,14 +21,11 @@ members = [
     "libs/http-utils",
     "libs/pageserver_api",
     "libs/postgres_ffi",
-    "libs/postgres_ffi_types",
     "libs/safekeeper_api",
     "libs/desim",
-    "libs/neon-shmem",
     "libs/utils",
     "libs/consumption_metrics",
     "libs/postgres_backend",
-    "libs/posthog_client_lite",
     "libs/pq_proto",
     "libs/tenant_size_model",
     "libs/metrics",
@@ -72,8 +68,8 @@ 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-extra = { version = "0.10.0", features = ["typed-header", "query"] }
-base64 = "0.22"
+axum-extra = { version = "0.10.0", features = ["typed-header"] }
+base64 = "0.13.0"
 bincode = "1.3"
 bindgen = "0.71"
 bit_field = "0.10.2"
@@ -130,7 +126,7 @@ md5 = "0.7.0"
 measured = { version = "0.0.22", features=["lasso"] }
 measured-process = { version = "0.0.22" }
 memoffset = "0.9"
-nix = { version = "0.30.1", features = ["dir", "fs", "mman", "process", "socket", "signal", "poll"] }
+nix = { version = "0.27", features = ["dir", "fs", "process", "socket", "signal", "poll"] }
 # Do not update to >= 7.0.0, at least. The update will have a significant impact
 # on compute startup metrics (start_postgres_ms), >= 25% degradation.
 notify = "6.0.0"
@@ -150,7 +146,7 @@ pin-project-lite = "0.2"
 pprof = { version = "0.14", features = ["criterion", "flamegraph", "frame-pointer", "prost-codec"] }
 procfs = "0.16"
 prometheus = {version = "0.13", default-features=false, features = ["process"]} # removes protobuf dependency
-prost = "0.13.5"
+prost = "0.13"
 rand = "0.8"
 redis = { version = "0.29.2", features = ["tokio-rustls-comp", "keep-alive"] }
 regex = "1.10.2"
@@ -172,7 +168,7 @@ sentry = { version = "0.37", default-features = false, features = ["backtrace",
 serde = { version = "1.0", features = ["derive"] }
 serde_json = "1"
 serde_path_to_error = "0.1"
-serde_with = { version = "3", features = [ "base64" ] }
+serde_with = { version = "2.0", features = [ "base64" ] }
 serde_assert = "0.5.0"
 sha2 = "0.10.2"
 signal-hook = "0.3"
@@ -200,8 +196,7 @@ tokio-tar = "0.3"
 tokio-util = { version = "0.7.10", features = ["io", "rt"] }
 toml = "0.8"
 toml_edit = "0.22"
-tonic = { version = "0.13.1", default-features = false, features = ["channel", "codegen", "gzip", "prost", "router", "server", "tls-ring", "tls-native-roots", "zstd"] }
-tonic-reflection = { version = "0.13.1", features = ["server"] }
+tonic = {version = "0.12.3", default-features = false, features = ["channel", "tls", "tls-roots"]}
 tower = { version = "0.5.2", default-features = false }
 tower-http = { version = "0.6.2", features = ["auth", "request-id", "trace"] }
 
@@ -248,7 +243,6 @@ azure_storage_blobs = { git = "https://github.com/neondatabase/azure-sdk-for-rus
 ## Local libraries
 compute_api = { version = "0.1", path = "./libs/compute_api/" }
 consumption_metrics = { version = "0.1", path = "./libs/consumption_metrics/" }
-desim = { version = "0.1", path = "./libs/desim" }
 endpoint_storage = { version = "0.0.1", path = "./endpoint_storage/" }
 http-utils = { version = "0.1", path = "./libs/http-utils/" }
 metrics = { version = "0.1", path = "./libs/metrics/" }
@@ -256,25 +250,23 @@ pageserver = { path = "./pageserver" }
 pageserver_api = { version = "0.1", path = "./libs/pageserver_api/" }
 pageserver_client = { path = "./pageserver/client" }
 pageserver_compaction = { version = "0.1", path = "./pageserver/compaction/" }
-pageserver_page_api = { path = "./pageserver/page_api" }
 postgres_backend = { version = "0.1", path = "./libs/postgres_backend/" }
 postgres_connection = { version = "0.1", path = "./libs/postgres_connection/" }
 postgres_ffi = { version = "0.1", path = "./libs/postgres_ffi/" }
-postgres_ffi_types = { version = "0.1", path = "./libs/postgres_ffi_types/" }
 postgres_initdb = { path = "./libs/postgres_initdb" }
-posthog_client_lite = { version = "0.1", path = "./libs/posthog_client_lite" }
 pq_proto = { version = "0.1", path = "./libs/pq_proto/" }
 remote_storage = { version = "0.1", path = "./libs/remote_storage/" }
 safekeeper_api = { version = "0.1", path = "./libs/safekeeper_api" }
 safekeeper_client = { path = "./safekeeper/client" }
+desim = { version = "0.1", path = "./libs/desim" }
 storage_broker = { version = "0.1", path = "./storage_broker/" } # Note: main broker code is inside the binary crate, so linking with the library shouldn't be heavy.
 storage_controller_client = { path = "./storage_controller/client" }
 tenant_size_model = { version = "0.1", path = "./libs/tenant_size_model/" }
 tracing-utils = { version = "0.1", path = "./libs/tracing-utils/" }
 utils = { version = "0.1", path = "./libs/utils/" }
 vm_monitor = { version = "0.1", path = "./libs/vm_monitor/" }
-wal_decoder = { version = "0.1", path = "./libs/wal_decoder" }
 walproposer = { version = "0.1", path = "./libs/walproposer/" }
+wal_decoder = { version = "0.1", path = "./libs/wal_decoder" }
 
 ## Common library dependency
 workspace_hack = { version = "0.1", path = "./workspace_hack/" }
@@ -284,7 +276,7 @@ criterion = "0.5.1"
 rcgen = "0.13"
 rstest = "0.18"
 camino-tempfile = "1.0.2"
-tonic-build = "0.13.1"
+tonic-build = "0.12"
 
 [patch.crates-io]
 

Dockerfile

@@ -5,6 +5,8 @@
 ARG REPOSITORY=ghcr.io/neondatabase
 ARG IMAGE=build-tools
 ARG TAG=pinned
+ARG DEFAULT_PG_VERSION=17
+ARG STABLE_PG_VERSION=16
 ARG DEBIAN_VERSION=bookworm
 ARG DEBIAN_FLAVOR=${DEBIAN_VERSION}-slim
 
@@ -45,6 +47,7 @@ COPY --chown=nonroot scripts/ninstall.sh scripts/ninstall.sh
 ENV BUILD_TYPE=release
 RUN set -e \
     && mold -run make -j $(nproc) -s neon-pg-ext \
+    && rm -rf pg_install/build \
     && tar -C pg_install -czf /home/nonroot/postgres_install.tar.gz .
 
 # Prepare cargo-chef recipe
@@ -60,11 +63,14 @@ FROM $REPOSITORY/$IMAGE:$TAG AS build
 WORKDIR /home/nonroot
 ARG GIT_VERSION=local
 ARG BUILD_TAG
+ARG STABLE_PG_VERSION
 
 COPY --from=pg-build /home/nonroot/pg_install/v14/include/postgresql/server pg_install/v14/include/postgresql/server
 COPY --from=pg-build /home/nonroot/pg_install/v15/include/postgresql/server pg_install/v15/include/postgresql/server
 COPY --from=pg-build /home/nonroot/pg_install/v16/include/postgresql/server pg_install/v16/include/postgresql/server
 COPY --from=pg-build /home/nonroot/pg_install/v17/include/postgresql/server pg_install/v17/include/postgresql/server
+COPY --from=pg-build /home/nonroot/pg_install/v16/lib                       pg_install/v16/lib
+COPY --from=pg-build /home/nonroot/pg_install/v17/lib                       pg_install/v17/lib
 COPY --from=plan     /home/nonroot/recipe.json                              recipe.json
 
 ARG ADDITIONAL_RUSTFLAGS=""
@@ -91,6 +97,7 @@ RUN set -e \
 # Build final image
 #
 FROM $BASE_IMAGE_SHA
+ARG DEFAULT_PG_VERSION
 WORKDIR /data
 
 RUN set -e \
@@ -100,20 +107,9 @@ RUN set -e \
         libreadline-dev \
         libseccomp-dev \
         ca-certificates \
+	# System postgres for use with client libraries (e.g. in storage controller)
+        postgresql-15 \
         openssl \
-        unzip \
-        curl \
-    && ARCH=$(uname -m) \
-    && if [ "$ARCH" = "x86_64" ]; then \
-        curl "https://awscli.amazonaws.com/awscli-exe-linux-x86_64.zip" -o "awscliv2.zip"; \
-    elif [ "$ARCH" = "aarch64" ]; then \
-        curl "https://awscli.amazonaws.com/awscli-exe-linux-aarch64.zip" -o "awscliv2.zip"; \
-    else \
-        echo "Unsupported architecture: $ARCH" && exit 1; \
-    fi \
-    && unzip awscliv2.zip \
-    && ./aws/install \
-    && rm -rf aws awscliv2.zip \
     && rm -f /etc/apt/apt.conf.d/80-retries \
     && rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* \
     && useradd -d /data neon \

Makefile

@@ -1,18 +1,8 @@
 ROOT_PROJECT_DIR := $(dir $(abspath $(lastword $(MAKEFILE_LIST))))
 
-# Where to install Postgres, default is ./pg_install, maybe useful for package
-# managers.
+# Where to install Postgres, default is ./pg_install, maybe useful for package managers
 POSTGRES_INSTALL_DIR ?= $(ROOT_PROJECT_DIR)/pg_install/
 
-# CARGO_BUILD_FLAGS: Extra flags to pass to `cargo build`. `--locked`
-# and `--features testing` are popular examples.
-#
-# CARGO_PROFILE: You can also set to override the cargo profile to
-# use. By default, it is derived from BUILD_TYPE.
-
-# All intermediate build artifacts are stored here.
-BUILD_DIR := build
-
 ICU_PREFIX_DIR := /usr/local/icu
 
 #
@@ -26,12 +16,12 @@ ifeq ($(BUILD_TYPE),release)
 	PG_CONFIGURE_OPTS = --enable-debug --with-openssl
 	PG_CFLAGS += -O2 -g3 $(CFLAGS)
 	PG_LDFLAGS = $(LDFLAGS)
-	CARGO_PROFILE ?= --profile=release
+	# Unfortunately, `--profile=...` is a nightly feature
+	CARGO_BUILD_FLAGS += --release
 else ifeq ($(BUILD_TYPE),debug)
 	PG_CONFIGURE_OPTS = --enable-debug --with-openssl --enable-cassert --enable-depend
 	PG_CFLAGS += -O0 -g3 $(CFLAGS)
 	PG_LDFLAGS = $(LDFLAGS)
-	CARGO_PROFILE ?= --profile=dev
 else
 	$(error Bad build type '$(BUILD_TYPE)', see Makefile for options)
 endif
@@ -103,7 +93,7 @@ all: neon postgres neon-pg-ext
 .PHONY: neon
 neon: postgres-headers walproposer-lib cargo-target-dir
 	+@echo "Compiling Neon"
-	$(CARGO_CMD_PREFIX) cargo build $(CARGO_BUILD_FLAGS) $(CARGO_PROFILE)
+	$(CARGO_CMD_PREFIX) cargo build $(CARGO_BUILD_FLAGS)
 .PHONY: cargo-target-dir
 cargo-target-dir:
 	# https://github.com/rust-lang/cargo/issues/14281
@@ -114,20 +104,21 @@ cargo-target-dir:
 # Some rules are duplicated for Postgres v14 and 15. We may want to refactor
 # to avoid the duplication in the future, but it's tolerable for now.
 #
-$(BUILD_DIR)/%/config.status:
-	mkdir -p $(BUILD_DIR)
-	test -e $(BUILD_DIR)/CACHEDIR.TAG || echo "$(CACHEDIR_TAG_CONTENTS)" > $(BUILD_DIR)/CACHEDIR.TAG
+$(POSTGRES_INSTALL_DIR)/build/%/config.status:
+
+	mkdir -p $(POSTGRES_INSTALL_DIR)
+	test -e $(POSTGRES_INSTALL_DIR)/CACHEDIR.TAG || echo "$(CACHEDIR_TAG_CONTENTS)" > $(POSTGRES_INSTALL_DIR)/CACHEDIR.TAG
 
 	+@echo "Configuring Postgres $* build"
 	@test -s $(ROOT_PROJECT_DIR)/vendor/postgres-$*/configure || { \
 		echo "\nPostgres submodule not found in $(ROOT_PROJECT_DIR)/vendor/postgres-$*/, execute "; \
 		echo "'git submodule update --init --recursive --depth 2 --progress .' in project root.\n"; \
 		exit 1; }
-	mkdir -p $(BUILD_DIR)/$*
+	mkdir -p $(POSTGRES_INSTALL_DIR)/build/$*
 
 	VERSION=$*; \
 	EXTRA_VERSION=$$(cd $(ROOT_PROJECT_DIR)/vendor/postgres-$$VERSION && git rev-parse HEAD); \
-	(cd $(BUILD_DIR)/$$VERSION && \
+	(cd $(POSTGRES_INSTALL_DIR)/build/$$VERSION && \
 	env PATH="$(EXTRA_PATH_OVERRIDES):$$PATH" $(ROOT_PROJECT_DIR)/vendor/postgres-$$VERSION/configure \
 		CFLAGS='$(PG_CFLAGS)' LDFLAGS='$(PG_LDFLAGS)' \
 		$(PG_CONFIGURE_OPTS) --with-extra-version=" ($$EXTRA_VERSION)" \
@@ -139,54 +130,96 @@ $(BUILD_DIR)/%/config.status:
 # the "build-all-versions" entry points) where direct mention of PostgreSQL
 # versions is used.
 .PHONY: postgres-configure-v17
-postgres-configure-v17: $(BUILD_DIR)/v17/config.status
+postgres-configure-v17: $(POSTGRES_INSTALL_DIR)/build/v17/config.status
 .PHONY: postgres-configure-v16
-postgres-configure-v16: $(BUILD_DIR)/v16/config.status
+postgres-configure-v16: $(POSTGRES_INSTALL_DIR)/build/v16/config.status
 .PHONY: postgres-configure-v15
-postgres-configure-v15: $(BUILD_DIR)/v15/config.status
+postgres-configure-v15: $(POSTGRES_INSTALL_DIR)/build/v15/config.status
 .PHONY: postgres-configure-v14
-postgres-configure-v14: $(BUILD_DIR)/v14/config.status
+postgres-configure-v14: $(POSTGRES_INSTALL_DIR)/build/v14/config.status
 
 # Install the PostgreSQL header files into $(POSTGRES_INSTALL_DIR)/<version>/include
 .PHONY: postgres-headers-%
 postgres-headers-%: postgres-configure-%
 	+@echo "Installing PostgreSQL $* headers"
-	$(MAKE) -C $(BUILD_DIR)/$*/src/include MAKELEVEL=0 install
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/src/include MAKELEVEL=0 install
 
 # Compile and install PostgreSQL
 .PHONY: postgres-%
 postgres-%: postgres-configure-% \
 		  postgres-headers-% # to prevent `make install` conflicts with neon's `postgres-headers`
 	+@echo "Compiling PostgreSQL $*"
-	$(MAKE) -C $(BUILD_DIR)/$* MAKELEVEL=0 install
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$* MAKELEVEL=0 install
 	+@echo "Compiling libpq $*"
-	$(MAKE) -C $(BUILD_DIR)/$*/src/interfaces/libpq install
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/src/interfaces/libpq install
 	+@echo "Compiling pg_prewarm $*"
-	$(MAKE) -C $(BUILD_DIR)/$*/contrib/pg_prewarm install
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pg_prewarm install
 	+@echo "Compiling pg_buffercache $*"
-	$(MAKE) -C $(BUILD_DIR)/$*/contrib/pg_buffercache install
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pg_buffercache install
 	+@echo "Compiling pg_visibility $*"
-	$(MAKE) -C $(BUILD_DIR)/$*/contrib/pg_visibility install
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pg_visibility install
 	+@echo "Compiling pageinspect $*"
-	$(MAKE) -C $(BUILD_DIR)/$*/contrib/pageinspect install
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pageinspect install
 	+@echo "Compiling pg_trgm $*"
-	$(MAKE) -C $(BUILD_DIR)/$*/contrib/pg_trgm install
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pg_trgm install
 	+@echo "Compiling amcheck $*"
-	$(MAKE) -C $(BUILD_DIR)/$*/contrib/amcheck install
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/amcheck install
 	+@echo "Compiling test_decoding $*"
-	$(MAKE) -C $(BUILD_DIR)/$*/contrib/test_decoding install
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/test_decoding install
+
+.PHONY: postgres-clean-%
+postgres-clean-%:
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$* MAKELEVEL=0 clean
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pg_buffercache clean
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pageinspect clean
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/src/interfaces/libpq clean
 
 .PHONY: postgres-check-%
 postgres-check-%: postgres-%
-	$(MAKE) -C $(BUILD_DIR)/$* MAKELEVEL=0 check
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$* MAKELEVEL=0 check
 
 .PHONY: neon-pg-ext-%
 neon-pg-ext-%: postgres-%
-	+@echo "Compiling neon-specific Postgres extensions for $*"
-	mkdir -p $(BUILD_DIR)/pgxn-$*
+	+@echo "Compiling neon $*"
+	mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-$*
 	$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config COPT='$(COPT)' \
-		-C $(BUILD_DIR)/pgxn-$*\
-		-f $(ROOT_PROJECT_DIR)/pgxn/Makefile  install
+		-C $(POSTGRES_INSTALL_DIR)/build/neon-$* \
+		-f $(ROOT_PROJECT_DIR)/pgxn/neon/Makefile install
+	+@echo "Compiling neon_walredo $*"
+	mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-walredo-$*
+	$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config COPT='$(COPT)' \
+		-C $(POSTGRES_INSTALL_DIR)/build/neon-walredo-$* \
+		-f $(ROOT_PROJECT_DIR)/pgxn/neon_walredo/Makefile install
+	+@echo "Compiling neon_rmgr $*"
+	mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-rmgr-$*
+	$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config COPT='$(COPT)' \
+		-C $(POSTGRES_INSTALL_DIR)/build/neon-rmgr-$* \
+		-f $(ROOT_PROJECT_DIR)/pgxn/neon_rmgr/Makefile install
+	+@echo "Compiling neon_test_utils $*"
+	mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-test-utils-$*
+	$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config COPT='$(COPT)' \
+		-C $(POSTGRES_INSTALL_DIR)/build/neon-test-utils-$* \
+		-f $(ROOT_PROJECT_DIR)/pgxn/neon_test_utils/Makefile install
+	+@echo "Compiling neon_utils $*"
+	mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-utils-$*
+	$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config COPT='$(COPT)' \
+		-C $(POSTGRES_INSTALL_DIR)/build/neon-utils-$* \
+		-f $(ROOT_PROJECT_DIR)/pgxn/neon_utils/Makefile install
+
+.PHONY: neon-pg-clean-ext-%
+neon-pg-clean-ext-%:
+	$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config \
+	-C $(POSTGRES_INSTALL_DIR)/build/neon-$* \
+	-f $(ROOT_PROJECT_DIR)/pgxn/neon/Makefile clean
+	$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config \
+	-C $(POSTGRES_INSTALL_DIR)/build/neon-walredo-$* \
+	-f $(ROOT_PROJECT_DIR)/pgxn/neon_walredo/Makefile clean
+	$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config \
+	-C $(POSTGRES_INSTALL_DIR)/build/neon-test-utils-$* \
+	-f $(ROOT_PROJECT_DIR)/pgxn/neon_test_utils/Makefile clean
+	$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config \
+	-C $(POSTGRES_INSTALL_DIR)/build/neon-utils-$* \
+	-f $(ROOT_PROJECT_DIR)/pgxn/neon_utils/Makefile clean
 
 # Build walproposer as a static library. walproposer source code is located
 # in the pgxn/neon directory.
@@ -200,15 +233,15 @@ neon-pg-ext-%: postgres-%
 .PHONY: walproposer-lib
 walproposer-lib: neon-pg-ext-v17
 	+@echo "Compiling walproposer-lib"
-	mkdir -p $(BUILD_DIR)/walproposer-lib
+	mkdir -p $(POSTGRES_INSTALL_DIR)/build/walproposer-lib
 	$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/v17/bin/pg_config COPT='$(COPT)' \
-		-C $(BUILD_DIR)/walproposer-lib \
+		-C $(POSTGRES_INSTALL_DIR)/build/walproposer-lib \
 		-f $(ROOT_PROJECT_DIR)/pgxn/neon/Makefile walproposer-lib
-	cp $(POSTGRES_INSTALL_DIR)/v17/lib/libpgport.a $(BUILD_DIR)/walproposer-lib
-	cp $(POSTGRES_INSTALL_DIR)/v17/lib/libpgcommon.a $(BUILD_DIR)/walproposer-lib
-	$(AR) d $(BUILD_DIR)/walproposer-lib/libpgport.a \
+	cp $(POSTGRES_INSTALL_DIR)/v17/lib/libpgport.a $(POSTGRES_INSTALL_DIR)/build/walproposer-lib
+	cp $(POSTGRES_INSTALL_DIR)/v17/lib/libpgcommon.a $(POSTGRES_INSTALL_DIR)/build/walproposer-lib
+	$(AR) d $(POSTGRES_INSTALL_DIR)/build/walproposer-lib/libpgport.a \
 		pg_strong_random.o
-	$(AR) d $(BUILD_DIR)/walproposer-lib/libpgcommon.a \
+	$(AR) d $(POSTGRES_INSTALL_DIR)/build/walproposer-lib/libpgcommon.a \
 		checksum_helper.o \
 		cryptohash_openssl.o \
 		hmac_openssl.o \
@@ -216,10 +249,16 @@ walproposer-lib: neon-pg-ext-v17
 		parse_manifest.o \
 		scram-common.o
 ifeq ($(UNAME_S),Linux)
-	$(AR) d $(BUILD_DIR)/walproposer-lib/libpgcommon.a \
+	$(AR) d $(POSTGRES_INSTALL_DIR)/build/walproposer-lib/libpgcommon.a \
 		pg_crc32c.o
 endif
 
+.PHONY: walproposer-lib-clean
+walproposer-lib-clean:
+	$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/v17/bin/pg_config \
+		-C $(POSTGRES_INSTALL_DIR)/build/walproposer-lib \
+		-f $(ROOT_PROJECT_DIR)/pgxn/neon/Makefile clean
+
 .PHONY: neon-pg-ext
 neon-pg-ext: \
 	neon-pg-ext-v14 \
@@ -227,6 +266,13 @@ neon-pg-ext: \
 	neon-pg-ext-v16 \
 	neon-pg-ext-v17
 
+.PHONY: neon-pg-clean-ext
+neon-pg-clean-ext: \
+	neon-pg-clean-ext-v14 \
+	neon-pg-clean-ext-v15 \
+	neon-pg-clean-ext-v16 \
+	neon-pg-clean-ext-v17
+
 # shorthand to build all Postgres versions
 .PHONY: postgres
 postgres: \
@@ -242,6 +288,13 @@ postgres-headers: \
 	postgres-headers-v16 \
 	postgres-headers-v17
 
+.PHONY: postgres-clean
+postgres-clean: \
+	postgres-clean-v14 \
+	postgres-clean-v15 \
+	postgres-clean-v16 \
+	postgres-clean-v17
+
 .PHONY: postgres-check
 postgres-check: \
 	postgres-check-v14 \
@@ -249,6 +302,12 @@ postgres-check: \
 	postgres-check-v16 \
 	postgres-check-v17
 
+# This doesn't remove the effects of 'configure'.
+.PHONY: clean
+clean: postgres-clean neon-pg-clean-ext
+	$(MAKE) -C compute clean
+	$(CARGO_CMD_PREFIX) cargo clean
+
 # This removes everything
 .PHONY: distclean
 distclean:
@@ -261,7 +320,7 @@ fmt:
 
 postgres-%-pg-bsd-indent: postgres-%
 	+@echo "Compiling pg_bsd_indent"
-	$(MAKE) -C $(BUILD_DIR)/$*/src/tools/pg_bsd_indent/
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/src/tools/pg_bsd_indent/
 
 # Create typedef list for the core. Note that generally it should be combined with
 # buildfarm one to cover platform specific stuff.
@@ -280,7 +339,7 @@ postgres-%-pgindent: postgres-%-pg-bsd-indent postgres-%-typedefs.list
 	cat $(ROOT_PROJECT_DIR)/vendor/postgres-$*/src/tools/pgindent/typedefs.list |\
 		cat - postgres-$*-typedefs.list | sort | uniq > postgres-$*-typedefs-full.list
 	+@echo note: you might want to run it on selected files/dirs instead.
-	INDENT=$(BUILD_DIR)/$*/src/tools/pg_bsd_indent/pg_bsd_indent \
+	INDENT=$(POSTGRES_INSTALL_DIR)/build/$*/src/tools/pg_bsd_indent/pg_bsd_indent \
 		$(ROOT_PROJECT_DIR)/vendor/postgres-$*/src/tools/pgindent/pgindent --typedefs postgres-$*-typedefs-full.list \
 		$(ROOT_PROJECT_DIR)/vendor/postgres-$*/src/ \
 		--excludes $(ROOT_PROJECT_DIR)/vendor/postgres-$*/src/tools/pgindent/exclude_file_patterns
@@ -291,9 +350,9 @@ postgres-%-pgindent: postgres-%-pg-bsd-indent postgres-%-typedefs.list
 neon-pgindent: postgres-v17-pg-bsd-indent neon-pg-ext-v17
 	$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/v17/bin/pg_config COPT='$(COPT)' \
 		FIND_TYPEDEF=$(ROOT_PROJECT_DIR)/vendor/postgres-v17/src/tools/find_typedef \
-		INDENT=$(BUILD_DIR)/v17/src/tools/pg_bsd_indent/pg_bsd_indent \
+		INDENT=$(POSTGRES_INSTALL_DIR)/build/v17/src/tools/pg_bsd_indent/pg_bsd_indent \
 		PGINDENT_SCRIPT=$(ROOT_PROJECT_DIR)/vendor/postgres-v17/src/tools/pgindent/pgindent \
-		-C $(BUILD_DIR)/neon-v17 \
+		-C $(POSTGRES_INSTALL_DIR)/build/neon-v17 \
 		-f $(ROOT_PROJECT_DIR)/pgxn/neon/Makefile pgindent
 
 

build-tools.Dockerfile

@@ -155,7 +155,7 @@ RUN set -e \
 
 # Keep the version the same as in compute/compute-node.Dockerfile and
 # test_runner/regress/test_compute_metrics.py.
-ENV SQL_EXPORTER_VERSION=0.17.3
+ENV SQL_EXPORTER_VERSION=0.17.0
 RUN curl -fsSL \
     "https://github.com/burningalchemist/sql_exporter/releases/download/${SQL_EXPORTER_VERSION}/sql_exporter-${SQL_EXPORTER_VERSION}.linux-$(case "$(uname -m)" in x86_64) echo amd64;; aarch64) echo arm64;; esac).tar.gz" \
     --output sql_exporter.tar.gz \
@@ -292,7 +292,7 @@ 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=1.87.0
+ENV RUSTC_VERSION=1.86.0
 ENV RUSTUP_HOME="/home/nonroot/.rustup"
 ENV PATH="/home/nonroot/.cargo/bin:${PATH}"
 ARG RUSTFILT_VERSION=0.2.1
@@ -310,13 +310,13 @@ RUN curl -sSO https://static.rust-lang.org/rustup/dist/$(uname -m)-unknown-linux
     . "$HOME/.cargo/env" && \
     cargo --version && rustup --version && \
     rustup component add llvm-tools rustfmt clippy && \
-    cargo install rustfilt            --version ${RUSTFILT_VERSION} --locked && \
-    cargo install cargo-hakari        --version ${CARGO_HAKARI_VERSION} --locked && \
-    cargo install cargo-deny          --version ${CARGO_DENY_VERSION} --locked && \
-    cargo install cargo-hack          --version ${CARGO_HACK_VERSION} --locked && \
-    cargo install cargo-nextest       --version ${CARGO_NEXTEST_VERSION} --locked && \
-    cargo install cargo-chef          --version ${CARGO_CHEF_VERSION} --locked && \
-    cargo install diesel_cli          --version ${CARGO_DIESEL_CLI_VERSION} --locked \
+    cargo install rustfilt            --version ${RUSTFILT_VERSION} && \
+    cargo install cargo-hakari        --version ${CARGO_HAKARI_VERSION} && \
+    cargo install cargo-deny --locked --version ${CARGO_DENY_VERSION} && \
+    cargo install cargo-hack          --version ${CARGO_HACK_VERSION} && \
+    cargo install cargo-nextest       --version ${CARGO_NEXTEST_VERSION} && \
+    cargo install cargo-chef --locked --version ${CARGO_CHEF_VERSION} && \
+    cargo install diesel_cli          --version ${CARGO_DIESEL_CLI_VERSION} \
                                       --features postgres-bundled --no-default-features && \
     rm -rf /home/nonroot/.cargo/registry && \
     rm -rf /home/nonroot/.cargo/git

compute/.gitignore

@@ -3,6 +3,3 @@ etc/neon_collector.yml
 etc/neon_collector_autoscaling.yml
 etc/sql_exporter.yml
 etc/sql_exporter_autoscaling.yml
-
-# Node.js dependencies
-node_modules/

compute/Makefile

@@ -48,11 +48,3 @@ jsonnetfmt-test:
 .PHONY: jsonnetfmt-format
 jsonnetfmt-format:
 	jsonnetfmt --in-place $(jsonnet_files)
-
-.PHONY: manifest-schema-validation
-manifest-schema-validation: node_modules
-	node_modules/.bin/jsonschema validate -d https://json-schema.org/draft/2020-12/schema manifest.schema.json manifest.yaml
-
-node_modules: package.json
-	npm install
-	touch node_modules

compute/compute-node.Dockerfile

@@ -77,6 +77,9 @@
 # build_and_test.yml github workflow for how that's done.
 
 ARG PG_VERSION
+ARG REPOSITORY=ghcr.io/neondatabase
+ARG IMAGE=build-tools
+ARG TAG=pinned
 ARG BUILD_TAG
 ARG DEBIAN_VERSION=bookworm
 ARG DEBIAN_FLAVOR=${DEBIAN_VERSION}-slim
@@ -146,11 +149,8 @@ RUN case $DEBIAN_VERSION in \
     ninja-build git autoconf automake libtool build-essential bison flex libreadline-dev \
     zlib1g-dev libxml2-dev libcurl4-openssl-dev libossp-uuid-dev wget ca-certificates pkg-config libssl-dev \
     libicu-dev libxslt1-dev liblz4-dev libzstd-dev zstd curl unzip g++ \
-    libclang-dev \
-    jsonnet \
     $VERSION_INSTALLS \
-    && apt clean && rm -rf /var/lib/apt/lists/* && \
-    useradd -ms /bin/bash nonroot -b /home
+    && apt clean && rm -rf /var/lib/apt/lists/*
 
 #########################################################################################
 #
@@ -583,38 +583,6 @@ RUN make -j $(getconf _NPROCESSORS_ONLN) && \
     make -j $(getconf _NPROCESSORS_ONLN) install && \
     echo 'trusted = true' >> /usr/local/pgsql/share/extension/hypopg.control
 
-#########################################################################################
-#
-# Layer "online_advisor-build"
-# compile online_advisor extension
-#
-#########################################################################################
-FROM build-deps AS online_advisor-src
-ARG PG_VERSION
-
-# online_advisor supports all Postgres version starting from PG14, but prior to PG17 has to be included in preload_shared_libraries
-# last release 1.0 - May 15, 2025
-WORKDIR /ext-src
-RUN case "${PG_VERSION:?}" in \
-    "v17") \
-        ;; \
-    *) \
-        echo "skipping the version of online_advistor for $PG_VERSION" && exit 0 \
-        ;; \
-    esac && \
-	wget https://github.com/knizhnik/online_advisor/archive/refs/tags/1.0.tar.gz -O online_advisor.tar.gz && \
-    echo "37dcadf8f7cc8d6cc1f8831276ee245b44f1b0274f09e511e47a67738ba9ed0f online_advisor.tar.gz" | sha256sum --check && \
-    mkdir online_advisor-src && cd online_advisor-src && tar xzf ../online_advisor.tar.gz --strip-components=1 -C .
-
-FROM pg-build AS online_advisor-build
-COPY --from=online_advisor-src /ext-src/ /ext-src/
-WORKDIR /ext-src/
-RUN if [ -d online_advisor-src ]; then \
-	    cd online_advisor-src && \
-        make -j install && \
-        echo 'trusted = true' >> /usr/local/pgsql/share/extension/online_advisor.control; \
-    fi
-
 #########################################################################################
 #
 # Layer "pg_hashids-build"
@@ -1057,10 +1025,17 @@ RUN make -j $(getconf _NPROCESSORS_ONLN) && \
 
 #########################################################################################
 #
-# Layer "build-deps with Rust toolchain installed"
+# Layer "pg build with nonroot user and cargo installed"
+# This layer is base and common for layers with `pgrx`
 #
 #########################################################################################
-FROM build-deps AS build-deps-with-cargo
+FROM pg-build AS pg-build-nonroot-with-cargo
+ARG PG_VERSION
+
+RUN apt update && \
+    apt install --no-install-recommends --no-install-suggests -y curl libclang-dev && \
+    apt clean && rm -rf /var/lib/apt/lists/* && \
+    useradd -ms /bin/bash nonroot -b /home
 
 ENV HOME=/home/nonroot
 ENV PATH="/home/nonroot/.cargo/bin:$PATH"
@@ -1075,29 +1050,13 @@ RUN curl -sSO https://static.rust-lang.org/rustup/dist/$(uname -m)-unknown-linux
     ./rustup-init -y --no-modify-path --profile minimal --default-toolchain stable && \
     rm rustup-init
 
-#########################################################################################
-#
-# Layer "pg-build with Rust toolchain installed"
-# This layer is base and common for layers with `pgrx`
-#
-#########################################################################################
-FROM pg-build AS pg-build-with-cargo
-ARG PG_VERSION
-
-ENV HOME=/home/nonroot
-ENV PATH="/home/nonroot/.cargo/bin:$PATH"
-USER nonroot
-WORKDIR /home/nonroot
-
-COPY --from=build-deps-with-cargo /home/nonroot /home/nonroot
-
 #########################################################################################
 #
 # Layer "rust extensions"
 # This layer is used to build `pgrx` deps
 #
 #########################################################################################
-FROM pg-build-with-cargo AS rust-extensions-build
+FROM pg-build-nonroot-with-cargo AS rust-extensions-build
 ARG PG_VERSION
 
 RUN case "${PG_VERSION:?}" in \
@@ -1119,7 +1078,7 @@ USER root
 # and eventually get merged with `rust-extensions-build`
 #
 #########################################################################################
-FROM pg-build-with-cargo AS rust-extensions-build-pgrx12
+FROM pg-build-nonroot-with-cargo AS rust-extensions-build-pgrx12
 ARG PG_VERSION
 
 RUN cargo install --locked --version 0.12.9 cargo-pgrx && \
@@ -1136,7 +1095,7 @@ USER root
 # and eventually get merged with `rust-extensions-build`
 #
 #########################################################################################
-FROM pg-build-with-cargo AS rust-extensions-build-pgrx14
+FROM pg-build-nonroot-with-cargo AS rust-extensions-build-pgrx14
 ARG PG_VERSION
 
 RUN cargo install --locked --version 0.14.1 cargo-pgrx && \
@@ -1153,16 +1112,14 @@ USER root
 
 FROM build-deps AS pgrag-src
 ARG PG_VERSION
-WORKDIR /ext-src
-COPY compute/patches/onnxruntime.patch .
 
+WORKDIR /ext-src
 RUN wget https://github.com/microsoft/onnxruntime/archive/refs/tags/v1.18.1.tar.gz -O onnxruntime.tar.gz && \
     mkdir onnxruntime-src && cd onnxruntime-src && tar xzf ../onnxruntime.tar.gz --strip-components=1 -C . && \
-    patch -p1 < /ext-src/onnxruntime.patch && \
     echo "#nothing to test here" > neon-test.sh
 
-RUN wget https://github.com/neondatabase-labs/pgrag/archive/refs/tags/v0.1.2.tar.gz -O pgrag.tar.gz &&  \
-    echo "7361654ea24f08cbb9db13c2ee1c0fe008f6114076401bb871619690dafc5225 pgrag.tar.gz" | sha256sum --check && \
+RUN wget https://github.com/neondatabase-labs/pgrag/archive/refs/tags/v0.1.1.tar.gz -O pgrag.tar.gz &&  \
+    echo "087b2ecd11ba307dc968042ef2e9e43dc04d9ba60e8306e882c407bbe1350a50 pgrag.tar.gz" | sha256sum --check && \
     mkdir pgrag-src && cd pgrag-src && tar xzf ../pgrag.tar.gz --strip-components=1 -C .
 
 FROM rust-extensions-build-pgrx14 AS pgrag-build
@@ -1192,14 +1149,14 @@ RUN cd exts/rag && \
 RUN cd exts/rag_bge_small_en_v15 && \
     sed -i 's/pgrx = "0.14.1"/pgrx = { version = "0.14.1", features = [ "unsafe-postgres" ] }/g' Cargo.toml && \
     ORT_LIB_LOCATION=/ext-src/onnxruntime-src/build/Linux \
-        REMOTE_ONNX_URL=http://pg-ext-s3-gateway.pg-ext-s3-gateway.svc.cluster.local/pgrag-data/bge_small_en_v15.onnx \
+        REMOTE_ONNX_URL=http://pg-ext-s3-gateway/pgrag-data/bge_small_en_v15.onnx \
         cargo pgrx install --release --features remote_onnx && \
     echo "trusted = true" >> /usr/local/pgsql/share/extension/rag_bge_small_en_v15.control
 
 RUN cd exts/rag_jina_reranker_v1_tiny_en && \
     sed -i 's/pgrx = "0.14.1"/pgrx = { version = "0.14.1", features = [ "unsafe-postgres" ] }/g' Cargo.toml && \
     ORT_LIB_LOCATION=/ext-src/onnxruntime-src/build/Linux \
-        REMOTE_ONNX_URL=http://pg-ext-s3-gateway.pg-ext-s3-gateway.svc.cluster.local/pgrag-data/jina_reranker_v1_tiny_en.onnx \
+        REMOTE_ONNX_URL=http://pg-ext-s3-gateway/pgrag-data/jina_reranker_v1_tiny_en.onnx \
         cargo pgrx install --release --features remote_onnx && \
     echo "trusted = true" >> /usr/local/pgsql/share/extension/rag_jina_reranker_v1_tiny_en.control
 
@@ -1632,7 +1589,18 @@ FROM pg-build AS neon-ext-build
 ARG PG_VERSION
 
 COPY pgxn/ pgxn/
-RUN make -j $(getconf _NPROCESSORS_ONLN) -C pgxn -s install-compute
+RUN make -j $(getconf _NPROCESSORS_ONLN) \
+        -C pgxn/neon \
+        -s install && \
+    make -j $(getconf _NPROCESSORS_ONLN) \
+        -C pgxn/neon_utils \
+        -s install && \
+    make -j $(getconf _NPROCESSORS_ONLN) \
+        -C pgxn/neon_test_utils \
+        -s install && \
+    make -j $(getconf _NPROCESSORS_ONLN) \
+        -C pgxn/neon_rmgr \
+        -s install
 
 #########################################################################################
 #
@@ -1681,7 +1649,6 @@ COPY --from=pg_jsonschema-build /usr/local/pgsql/ /usr/local/pgsql/
 COPY --from=pg_graphql-build /usr/local/pgsql/ /usr/local/pgsql/
 COPY --from=pg_tiktoken-build /usr/local/pgsql/ /usr/local/pgsql/
 COPY --from=hypopg-build /usr/local/pgsql/ /usr/local/pgsql/
-COPY --from=online_advisor-build /usr/local/pgsql/ /usr/local/pgsql/
 COPY --from=pg_hashids-build /usr/local/pgsql/ /usr/local/pgsql/
 COPY --from=rum-build /usr/local/pgsql/ /usr/local/pgsql/
 COPY --from=pgtap-build /usr/local/pgsql/ /usr/local/pgsql/
@@ -1722,7 +1689,7 @@ FROM extensions-${EXTENSIONS} AS neon-pg-ext-build
 # Compile the Neon-specific `compute_ctl`, `fast_import`, and `local_proxy` binaries
 #
 #########################################################################################
-FROM build-deps-with-cargo AS compute-tools
+FROM $REPOSITORY/$IMAGE:$TAG AS compute-tools
 ARG BUILD_TAG
 ENV BUILD_TAG=$BUILD_TAG
 
@@ -1732,7 +1699,7 @@ COPY --chown=nonroot . .
 RUN --mount=type=cache,uid=1000,target=/home/nonroot/.cargo/registry \
     --mount=type=cache,uid=1000,target=/home/nonroot/.cargo/git \
     --mount=type=cache,uid=1000,target=/home/nonroot/target \
-    cargo build --locked --profile release-line-debug-size-lto --bin compute_ctl --bin fast_import --bin local_proxy && \
+    mold -run cargo build --locked --profile release-line-debug-size-lto --bin compute_ctl --bin fast_import --bin local_proxy && \
     mkdir target-bin && \
     cp target/release-line-debug-size-lto/compute_ctl \
        target/release-line-debug-size-lto/fast_import \
@@ -1785,17 +1752,17 @@ ARG TARGETARCH
 RUN if [ "$TARGETARCH" = "amd64" ]; then\
         postgres_exporter_sha256='59aa4a7bb0f7d361f5e05732f5ed8c03cc08f78449cef5856eadec33a627694b';\
         pgbouncer_exporter_sha256='c9f7cf8dcff44f0472057e9bf52613d93f3ffbc381ad7547a959daa63c5e84ac';\
-        sql_exporter_sha256='9a41127a493e8bfebfe692bf78c7ed2872a58a3f961ee534d1b0da9ae584aaab';\
+        sql_exporter_sha256='38e439732bbf6e28ca4a94d7bc3686d3fa1abdb0050773d5617a9efdb9e64d08';\
     else\
         postgres_exporter_sha256='d1dedea97f56c6d965837bfd1fbb3e35a3b4a4556f8cccee8bd513d8ee086124';\
         pgbouncer_exporter_sha256='217c4afd7e6492ae904055bc14fe603552cf9bac458c063407e991d68c519da3';\
-        sql_exporter_sha256='530e6afc77c043497ed965532c4c9dfa873bc2a4f0b3047fad367715c0081d6a';\
+        sql_exporter_sha256='11918b00be6e2c3a67564adfdb2414fdcbb15a5db76ea17d1d1a944237a893c6';\
     fi\
     && curl -sL https://github.com/prometheus-community/postgres_exporter/releases/download/v0.17.1/postgres_exporter-0.17.1.linux-${TARGETARCH}.tar.gz\
      | tar xzf - --strip-components=1 -C.\
     && curl -sL https://github.com/prometheus-community/pgbouncer_exporter/releases/download/v0.10.2/pgbouncer_exporter-0.10.2.linux-${TARGETARCH}.tar.gz\
      | tar xzf - --strip-components=1 -C.\
-    && curl -sL https://github.com/burningalchemist/sql_exporter/releases/download/0.17.3/sql_exporter-0.17.3.linux-${TARGETARCH}.tar.gz\
+    && curl -sL https://github.com/burningalchemist/sql_exporter/releases/download/0.17.0/sql_exporter-0.17.0.linux-${TARGETARCH}.tar.gz\
      | tar xzf - --strip-components=1 -C.\
     && echo "${postgres_exporter_sha256} postgres_exporter" | sha256sum -c -\
     && echo "${pgbouncer_exporter_sha256} pgbouncer_exporter" | sha256sum -c -\
@@ -1826,11 +1793,10 @@ RUN rm /usr/local/pgsql/lib/lib*.a
 # Preprocess the sql_exporter configuration files
 #
 #########################################################################################
-FROM build-deps AS sql_exporter_preprocessor
+FROM $REPOSITORY/$IMAGE:$TAG AS sql_exporter_preprocessor
 ARG PG_VERSION
 
 USER nonroot
-WORKDIR /home/nonroot
 
 COPY --chown=nonroot compute compute
 
@@ -1864,7 +1830,7 @@ COPY --from=postgis-build /usr/local/pgsql/ /usr/local/pgsql/
 COPY --from=postgis-build /ext-src/postgis-src /ext-src/postgis-src
 COPY --from=postgis-build /sfcgal/* /usr
 COPY --from=plv8-src /ext-src/ /ext-src/
-COPY --from=h3-pg-src /ext-src/h3-pg-src /ext-src/h3-pg-src
+#COPY --from=h3-pg-src /ext-src/ /ext-src/
 COPY --from=postgresql-unit-src /ext-src/ /ext-src/
 COPY --from=pgvector-src /ext-src/ /ext-src/
 COPY --from=pgjwt-src /ext-src/ /ext-src/
@@ -1873,7 +1839,6 @@ COPY --from=pgjwt-src /ext-src/ /ext-src/
 COPY --from=pg_graphql-src /ext-src/ /ext-src/
 #COPY --from=pg_tiktoken-src /ext-src/ /ext-src/
 COPY --from=hypopg-src /ext-src/ /ext-src/
-COPY --from=online_advisor-src /ext-src/ /ext-src/
 COPY --from=pg_hashids-src /ext-src/ /ext-src/
 COPY --from=rum-src /ext-src/ /ext-src/
 COPY --from=pgtap-src /ext-src/ /ext-src/
@@ -1903,7 +1868,6 @@ COPY compute/patches/pg_repack.patch /ext-src
 RUN cd /ext-src/pg_repack-src && patch -p1 </ext-src/pg_repack.patch && rm -f /ext-src/pg_repack.patch
 
 COPY --chmod=755 docker-compose/run-tests.sh /run-tests.sh
-RUN echo /usr/local/pgsql/lib > /etc/ld.so.conf.d/00-neon.conf && /sbin/ldconfig
 RUN apt-get update && apt-get install -y libtap-parser-sourcehandler-pgtap-perl jq \
    && apt clean && rm -rf /ext-src/*.tar.gz /ext-src/*.patch /var/lib/apt/lists/*
 ENV PATH=/usr/local/pgsql/bin:$PATH
@@ -2023,8 +1987,7 @@ COPY --from=sql_exporter_preprocessor --chmod=0644 /home/nonroot/compute/etc/sql
 COPY --from=sql_exporter_preprocessor --chmod=0644 /home/nonroot/compute/etc/neon_collector_autoscaling.yml /etc/neon_collector_autoscaling.yml
 
 # Make the libraries we built available
-COPY --chmod=0666 compute/etc/ld.so.conf.d/00-neon.conf /etc/ld.so.conf.d/00-neon.conf
-RUN /sbin/ldconfig
+RUN echo '/usr/local/lib' >> /etc/ld.so.conf && /sbin/ldconfig
 
 # rsyslog config permissions
 # directory for rsyslogd pid file

compute/etc/ld.so.conf.d/00-neon.conf

@@ -1 +0,0 @@
-/usr/local/lib

compute/etc/pgbouncer.ini

@@ -21,8 +21,6 @@ unix_socket_dir=/tmp/
 unix_socket_mode=0777
 ; required for pgbouncer_exporter
 ignore_startup_parameters=extra_float_digits
-; pidfile for graceful termination
-pidfile=/tmp/pgbouncer.pid
 
 ;; 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/manifest.schema.json

@@ -1,209 +0,0 @@
-{
-  "$schema": "https://json-schema.org/draft/2020-12/schema",
-  "title": "Neon Compute Manifest Schema",
-  "description": "Schema for Neon compute node configuration manifest",
-  "type": "object",
-  "properties": {
-    "pg_settings": {
-      "type": "object",
-      "properties": {
-        "common": {
-          "type": "object",
-          "properties": {
-            "client_connection_check_interval": {
-              "type": "string",
-              "description": "Check for client disconnection interval in milliseconds"
-            },
-            "effective_io_concurrency": {
-              "type": "string",
-              "description": "Effective IO concurrency setting"
-            },
-            "fsync": {
-              "type": "string",
-              "enum": ["on", "off"],
-              "description": "Whether to force fsync to disk"
-            },
-            "hot_standby": {
-              "type": "string",
-              "enum": ["on", "off"],
-              "description": "Whether hot standby is enabled"
-            },
-            "idle_in_transaction_session_timeout": {
-              "type": "string",
-              "description": "Timeout for idle transactions in milliseconds"
-            },
-            "listen_addresses": {
-              "type": "string",
-              "description": "Addresses to listen on"
-            },
-            "log_connections": {
-              "type": "string",
-              "enum": ["on", "off"],
-              "description": "Whether to log connections"
-            },
-            "log_disconnections": {
-              "type": "string",
-              "enum": ["on", "off"],
-              "description": "Whether to log disconnections"
-            },
-            "log_temp_files": {
-              "type": "string",
-              "description": "Size threshold for logging temporary files in KB"
-            },
-            "log_error_verbosity": {
-              "type": "string",
-              "enum": ["terse", "verbose", "default"],
-              "description": "Error logging verbosity level"
-            },
-            "log_min_error_statement": {
-              "type": "string",
-              "description": "Minimum error level for statement logging"
-            },
-            "maintenance_io_concurrency": {
-              "type": "string",
-              "description": "Maintenance IO concurrency setting"
-            },
-            "max_connections": {
-              "type": "string",
-              "description": "Maximum number of connections"
-            },
-            "max_replication_flush_lag": {
-              "type": "string",
-              "description": "Maximum replication flush lag"
-            },
-            "max_replication_slots": {
-              "type": "string",
-              "description": "Maximum number of replication slots"
-            },
-            "max_replication_write_lag": {
-              "type": "string",
-              "description": "Maximum replication write lag"
-            },
-            "max_wal_senders": {
-              "type": "string",
-              "description": "Maximum number of WAL senders"
-            },
-            "max_wal_size": {
-              "type": "string",
-              "description": "Maximum WAL size"
-            },
-            "neon.unstable_extensions": {
-              "type": "string",
-              "description": "List of unstable extensions"
-            },
-            "neon.protocol_version": {
-              "type": "string",
-              "description": "Neon protocol version"
-            },
-            "password_encryption": {
-              "type": "string",
-              "description": "Password encryption method"
-            },
-            "restart_after_crash": {
-              "type": "string",
-              "enum": ["on", "off"],
-              "description": "Whether to restart after crash"
-            },
-            "superuser_reserved_connections": {
-              "type": "string",
-              "description": "Number of reserved connections for superuser"
-            },
-            "synchronous_standby_names": {
-              "type": "string",
-              "description": "Names of synchronous standby servers"
-            },
-            "wal_keep_size": {
-              "type": "string",
-              "description": "WAL keep size"
-            },
-            "wal_level": {
-              "type": "string",
-              "description": "WAL level"
-            },
-            "wal_log_hints": {
-              "type": "string",
-              "enum": ["on", "off"],
-              "description": "Whether to log hints in WAL"
-            },
-            "wal_sender_timeout": {
-              "type": "string",
-              "description": "WAL sender timeout in milliseconds"
-            }
-          },
-          "required": [
-            "client_connection_check_interval",
-            "effective_io_concurrency",
-            "fsync",
-            "hot_standby",
-            "idle_in_transaction_session_timeout",
-            "listen_addresses",
-            "log_connections",
-            "log_disconnections",
-            "log_temp_files",
-            "log_error_verbosity",
-            "log_min_error_statement",
-            "maintenance_io_concurrency",
-            "max_connections",
-            "max_replication_flush_lag",
-            "max_replication_slots",
-            "max_replication_write_lag",
-            "max_wal_senders",
-            "max_wal_size",
-            "neon.unstable_extensions",
-            "neon.protocol_version",
-            "password_encryption",
-            "restart_after_crash",
-            "superuser_reserved_connections",
-            "synchronous_standby_names",
-            "wal_keep_size",
-            "wal_level",
-            "wal_log_hints",
-            "wal_sender_timeout"
-          ]
-        },
-        "replica": {
-          "type": "object",
-          "properties": {
-            "hot_standby": {
-              "type": "string",
-              "enum": ["on", "off"],
-              "description": "Whether hot standby is enabled for replicas"
-            }
-          },
-          "required": ["hot_standby"]
-        },
-        "per_version": {
-          "type": "object",
-          "patternProperties": {
-            "^1[4-7]$": {
-              "type": "object",
-              "properties": {
-                "common": {
-                  "type": "object",
-                  "properties": {
-                    "io_combine_limit": {
-                      "type": "string",
-                      "description": "IO combine limit"
-                    }
-                  }
-                },
-                "replica": {
-                  "type": "object",
-                  "properties": {
-                    "recovery_prefetch": {
-                      "type": "string",
-                      "enum": ["on", "off"],
-                      "description": "Whether to enable recovery prefetch for PostgreSQL replicas"
-                    }
-                  }
-                }
-              }
-            }
-          }
-        }
-      },
-      "required": ["common", "replica", "per_version"]
-    }
-  },
-  "required": ["pg_settings"]
-} 

compute/manifest.yaml

@@ -1,121 +0,0 @@
-pg_settings:
-  # Common settings for primaries and replicas of all versions.
-  common:
-    # Check for client disconnection every 1 minute. By default, Postgres will detect the
-    # loss of the connection only at the next interaction with the socket, when it waits
-    # for, receives or sends data, so it will likely waste resources till the end of the
-    # query execution. There should be no drawbacks in setting this for everyone, so enable
-    # it by default. If anyone will complain, we can allow editing it.
-    # https://www.postgresql.org/docs/16/runtime-config-connection.html#GUC-CLIENT-CONNECTION-CHECK-INTERVAL
-    client_connection_check_interval: "60000" # 1 minute
-    # ---- IO ---- 
-    effective_io_concurrency: "20"
-    maintenance_io_concurrency: "100"
-    fsync: "off"
-    hot_standby: "off"
-    # We allow users to change this if needed, but by default we
-    # just don't want to see long-lasting idle transactions, as they
-    # prevent activity monitor from suspending projects.
-    idle_in_transaction_session_timeout: "300000" # 5 minutes
-    listen_addresses: "*"
-    # --- LOGGING ---- helps investigations
-    log_connections: "on"
-    log_disconnections: "on"
-    # 1GB, unit is KB
-    log_temp_files: "1048576"
-    # Disable dumping customer data to logs, both to increase data privacy
-    # and to reduce the amount the logs.
-    log_error_verbosity: "terse"
-    log_min_error_statement: "panic"
-    max_connections: "100"
-    # --- WAL ---
-    # - flush lag is the max amount of WAL that has been generated but not yet stored
-    # to disk in the page server. A smaller value means less delay after a pageserver
-    # restart, but if you set it too small you might again need to slow down writes if the
-    # pageserver cannot flush incoming WAL to disk fast enough. This must be larger
-    # than the pageserver's checkpoint interval, currently 1 GB! Otherwise you get a
-    # a deadlock where the compute node refuses to generate more WAL before the
-    # old WAL has been uploaded to S3, but the pageserver is waiting for more WAL
-    # to be generated before it is uploaded to S3.
-    max_replication_flush_lag: "10GB"
-    max_replication_slots: "10"
-    # Backpressure configuration:
-    # - write lag is the max amount of WAL that has been generated by Postgres but not yet
-    # processed by the page server. Making this smaller reduces the worst case latency
-    # of a GetPage request, if you request a page that was recently modified. On the other
-    # hand, if this is too small, the compute node might need to wait on a write if there is a
-    # hiccup in the network or page server so that the page server has temporarily fallen
-    # behind.
-    #
-    # Previously it was set to 500 MB, but it caused compute being unresponsive under load
-    # https://github.com/neondatabase/neon/issues/2028
-    max_replication_write_lag: "500MB"
-    max_wal_senders: "10"
-    # A Postgres checkpoint is cheap in storage, as doesn't involve any significant amount
-    # of real I/O. Only the SLRU buffers and some other small files are flushed to disk.
-    # However, as long as we have full_page_writes=on, page updates after a checkpoint
-    # include full-page images which bloats the WAL. So may want to bump max_wal_size to
-    # reduce the WAL bloating, but at the same it will increase pg_wal directory size on
-    # compute and can lead to out of disk error on k8s nodes.
-    max_wal_size: "1024"
-    wal_keep_size: "0"
-    wal_level: "replica"
-    # Reduce amount of WAL generated by default.
-    wal_log_hints: "off"
-    # - without wal_sender_timeout set we don't get feedback messages,
-    # required for backpressure.
-    wal_sender_timeout: "10000"
-    # We have some experimental extensions, which we don't want users to install unconsciously.
-    # To install them, users would need to set the `neon.allow_unstable_extensions` setting.
-    # There are two of them currently:
-    # - `pgrag` - https://github.com/neondatabase-labs/pgrag - extension is actually called just `rag`,
-    #                                                          and two dependencies:
-    #                                                          - `rag_bge_small_en_v15`
-    #                                                          - `rag_jina_reranker_v1_tiny_en`
-    # - `pg_mooncake` - https://github.com/Mooncake-Labs/pg_mooncake/  
-    neon.unstable_extensions: "rag,rag_bge_small_en_v15,rag_jina_reranker_v1_tiny_en,pg_mooncake,anon"
-    neon.protocol_version: "3"
-    password_encryption: "scram-sha-256"
-    # This is important to prevent Postgres from trying to perform
-    # a local WAL redo after backend crash. It should exit and let
-    # the systemd or k8s to do a fresh startup with compute_ctl.
-    restart_after_crash: "off"
-    # By default 3. We have the following persistent connections in the VM:
-    # * compute_activity_monitor (from compute_ctl)
-    # * postgres-exporter (metrics collector; it has 2 connections)
-    # * sql_exporter (metrics collector; we have 2 instances [1 for us & users; 1 for autoscaling])
-    # * vm-monitor (to query & change file cache size)
-    # i.e. total of 6. Let's reserve 7, so there's still at least one left over.
-    superuser_reserved_connections: "7"
-    synchronous_standby_names: "walproposer"
-
-  replica:
-    hot_standby: "on"
-
-  per_version:
-    17:
-      common:
-        # PostgreSQL 17 has a new IO system called "read stream", which can combine IOs up to some
-        # size. It still has some issues with readahead, though, so we default to disabled/
-        # "no combining of IOs" to make sure we get the maximum prefetch depth.
-        # See also: https://github.com/neondatabase/neon/pull/9860
-        io_combine_limit: "1"
-      replica:
-        # prefetching of blocks referenced in WAL doesn't make sense for us
-        # Neon hot standby ignores pages that are not in the shared_buffers
-        recovery_prefetch: "off"
-    16:
-      common: {}
-      replica:
-        # prefetching of blocks referenced in WAL doesn't make sense for us
-        # Neon hot standby ignores pages that are not in the shared_buffers
-        recovery_prefetch: "off"
-    15:
-      common: {}
-      replica:
-        # prefetching of blocks referenced in WAL doesn't make sense for us
-        # Neon hot standby ignores pages that are not in the shared_buffers
-        recovery_prefetch: "off"
-    14:
-      common: {}
-      replica: {}

compute/package-lock.json

@@ -1,37 +0,0 @@
-{
-  "name": "neon-compute",
-  "lockfileVersion": 3,
-  "requires": true,
-  "packages": {
-    "": {
-      "name": "neon-compute",
-      "dependencies": {
-        "@sourcemeta/jsonschema": "9.3.4"
-      }
-    },
-    "node_modules/@sourcemeta/jsonschema": {
-      "version": "9.3.4",
-      "resolved": "https://registry.npmjs.org/@sourcemeta/jsonschema/-/jsonschema-9.3.4.tgz",
-      "integrity": "sha512-hkujfkZAIGXUs4U//We9faZW8LZ4/H9LqagRYsFSulH/VLcKPNhZyCTGg7AhORuzm27zqENvKpnX4g2FzudYFw==",
-      "cpu": [
-        "x64",
-        "arm64"
-      ],
-      "license": "AGPL-3.0",
-      "os": [
-        "darwin",
-        "linux",
-        "win32"
-      ],
-      "bin": {
-        "jsonschema": "cli.js"
-      },
-      "engines": {
-        "node": ">=16"
-      },
-      "funding": {
-        "url": "https://github.com/sponsors/sourcemeta"
-      }
-    }
-  }
-}

compute/package.json

@@ -1,7 +0,0 @@
-{
-  "name": "neon-compute",
-  "private": true,
-  "dependencies": {
-    "@sourcemeta/jsonschema": "9.3.4"
-  }
-} 

compute/patches/onnxruntime.patch

@@ -1,15 +0,0 @@
-diff --git a/cmake/deps.txt b/cmake/deps.txt
-index d213b09034..229de2ebf0 100644
---- a/cmake/deps.txt
-+++ b/cmake/deps.txt
-@@ -22,7 +22,9 @@ dlpack;https://github.com/dmlc/dlpack/archive/refs/tags/v0.6.zip;4d565dd2e5b3132
- # it contains changes on top of 3.4.0 which are required to fix build issues.
- # Until the 3.4.1 release this is the best option we have.
- # Issue link: https://gitlab.com/libeigen/eigen/-/issues/2744
--eigen;https://gitlab.com/libeigen/eigen/-/archive/e7248b26a1ed53fa030c5c459f7ea095dfd276ac/eigen-e7248b26a1ed53fa030c5c459f7ea095dfd276ac.zip;be8be39fdbc6e60e94fa7870b280707069b5b81a
-+# Moved to github mirror to avoid gitlab issues.Add commentMore actions
-+# Issue link: https://github.com/bazelbuild/bazel-central-registry/issues/4355
-+eigen;https://github.com/eigen-mirror/eigen/archive/e7248b26a1ed53fa030c5c459f7ea095dfd276ac/eigen-e7248b26a1ed53fa030c5c459f7ea095dfd276ac.zip;61418a349000ba7744a3ad03cf5071f22ebf860a
- flatbuffers;https://github.com/google/flatbuffers/archive/refs/tags/v23.5.26.zip;59422c3b5e573dd192fead2834d25951f1c1670c
- fp16;https://github.com/Maratyszcza/FP16/archive/0a92994d729ff76a58f692d3028ca1b64b145d91.zip;b985f6985a05a1c03ff1bb71190f66d8f98a1494
- fxdiv;https://github.com/Maratyszcza/FXdiv/archive/63058eff77e11aa15bf531df5dd34395ec3017c8.zip;a5658f4036402dbca7cebee32be57fb8149811e1

compute/patches/rum.patch

@@ -7,7 +7,7 @@ index 255e616..1c6edb7 100644
  			 RelationGetRelationName(index));
  
 +#ifdef NEON_SMGR
-+	smgr_start_unlogged_build(RelationGetSmgr(index));
++	smgr_start_unlogged_build(index->rd_smgr);
 +#endif
 +
  	initRumState(&buildstate.rumstate, index);
@@ -18,7 +18,7 @@ index 255e616..1c6edb7 100644
  	rumUpdateStats(index, &buildstate.buildStats, buildstate.rumstate.isBuild);
  
 +#ifdef NEON_SMGR
-+	smgr_finish_unlogged_build_phase_1(RelationGetSmgr(index));
++	smgr_finish_unlogged_build_phase_1(index->rd_smgr);
 +#endif
 +
  	/*
@@ -29,7 +29,7 @@ index 255e616..1c6edb7 100644
  	}
  
 +#ifdef NEON_SMGR
-+	smgr_end_unlogged_build(RelationGetSmgr(index));
++	smgr_end_unlogged_build(index->rd_smgr);
 +#endif
 +
  	/*

compute_tools/Cargo.toml

@@ -28,7 +28,6 @@ flate2.workspace = true
 futures.workspace = true
 http.workspace = true
 indexmap.workspace = true
-itertools.workspace = true
 jsonwebtoken.workspace = true
 metrics.workspace = true
 nix.workspace = true

compute_tools/src/bin/compute_ctl.rs

@@ -40,7 +40,7 @@ use std::sync::mpsc;
 use std::thread;
 use std::time::Duration;
 
-use anyhow::{Context, Result, bail};
+use anyhow::{Context, Result};
 use clap::Parser;
 use compute_api::responses::ComputeConfig;
 use compute_tools::compute::{
@@ -57,15 +57,31 @@ use tracing::{error, info};
 use url::Url;
 use utils::failpoint_support;
 
-#[derive(Debug, Parser)]
+// 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_base_url(arg: &str) -> Result<String> {
+    const FALLBACK_PG_EXT_GATEWAY_BASE_URL: &str =
+        "http://pg-ext-s3-gateway.pg-ext-s3-gateway.svc.cluster.local";
+
+    Ok(if arg.starts_with("http") {
+        arg
+    } else {
+        FALLBACK_PG_EXT_GATEWAY_BASE_URL
+    }
+    .to_owned())
+}
+
+#[derive(Parser)]
 #[command(rename_all = "kebab-case")]
 struct Cli {
     #[arg(short = 'b', long, default_value = "postgres", env = "POSTGRES_PATH")]
     pub pgbin: String,
 
     /// The base URL for the remote extension storage proxy gateway.
-    #[arg(short = 'r', long, value_parser = Self::parse_remote_ext_base_url)]
-    pub remote_ext_base_url: Option<Url>,
+    /// Should be in the form of `http(s)://<gateway-hostname>[:<port>]`.
+    #[arg(short = 'r', long, value_parser = parse_remote_ext_base_url, alias = "remote-ext-config")]
+    pub remote_ext_base_url: Option<String>,
 
     /// The port to bind the external listening HTTP server to. Clients running
     /// outside the compute will talk to the compute through this port. Keep
@@ -120,33 +136,6 @@ struct Cli {
         requires = "compute-id"
     )]
     pub control_plane_uri: Option<String>,
-
-    /// Interval in seconds for collecting installed extensions statistics
-    #[arg(long, default_value = "3600")]
-    pub installed_extensions_collection_interval: u64,
-
-    /// Run in development mode, skipping VM-specific operations like process termination
-    #[arg(long, action = clap::ArgAction::SetTrue)]
-    pub dev: bool,
-}
-
-impl Cli {
-    /// Parse a URL from an argument. By default, this isn't necessary, but we
-    /// want to do some sanity checking.
-    fn parse_remote_ext_base_url(value: &str) -> Result<Url> {
-        // Remove extra trailing slashes, and add one. We use Url::join() later
-        // when downloading remote extensions. If the base URL is something like
-        // http://example.com/pg-ext-s3-gateway, and join() is called with
-        // something like "xyz", the resulting URL is http://example.com/xyz.
-        let value = value.trim_end_matches('/').to_owned() + "/";
-        let url = Url::parse(&value)?;
-
-        if url.query_pairs().count() != 0 {
-            bail!("parameters detected in remote extensions base URL")
-        }
-
-        Ok(url)
-    }
 }
 
 fn main() -> Result<()> {
@@ -163,7 +152,7 @@ fn main() -> Result<()> {
         .build()?;
     let _rt_guard = runtime.enter();
 
-    runtime.block_on(init(cli.dev))?;
+    runtime.block_on(init())?;
 
     // enable core dumping for all child processes
     setrlimit(Resource::CORE, rlimit::INFINITY, rlimit::INFINITY)?;
@@ -190,7 +179,6 @@ fn main() -> Result<()> {
             cgroup: cli.cgroup,
             #[cfg(target_os = "linux")]
             vm_monitor_addr: cli.vm_monitor_addr,
-            installed_extensions_collection_interval: cli.installed_extensions_collection_interval,
         },
         config,
     )?;
@@ -202,13 +190,13 @@ fn main() -> Result<()> {
     deinit_and_exit(exit_code);
 }
 
-async fn init(dev_mode: bool) -> Result<()> {
+async fn init() -> Result<()> {
     init_tracing_and_logging(DEFAULT_LOG_LEVEL).await?;
 
     let mut signals = Signals::new([SIGINT, SIGTERM, SIGQUIT])?;
     thread::spawn(move || {
         for sig in signals.forever() {
-            handle_exit_signal(sig, dev_mode);
+            handle_exit_signal(sig);
         }
     });
 
@@ -267,16 +255,15 @@ fn deinit_and_exit(exit_code: Option<i32>) -> ! {
 /// 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.
-fn handle_exit_signal(sig: i32, dev_mode: bool) {
+fn handle_exit_signal(sig: i32) {
     info!("received {sig} termination signal");
-    forward_termination_signal(dev_mode);
+    forward_termination_signal();
     exit(1);
 }
 
 #[cfg(test)]
 mod test {
-    use clap::{CommandFactory, Parser};
-    use url::Url;
+    use clap::CommandFactory;
 
     use super::Cli;
 
@@ -286,41 +273,16 @@ mod test {
     }
 
     #[test]
-    fn verify_remote_ext_base_url() {
-        let cli = Cli::parse_from([
-            "compute_ctl",
-            "--pgdata=test",
-            "--connstr=test",
-            "--compute-id=test",
-            "--remote-ext-base-url",
-            "https://example.com/subpath",
-        ]);
-        assert_eq!(
-            cli.remote_ext_base_url.unwrap(),
-            Url::parse("https://example.com/subpath/").unwrap()
-        );
+    fn parse_pg_ext_gateway_base_url() {
+        let arg = "http://pg-ext-s3-gateway2";
+        let result = super::parse_remote_ext_base_url(arg).unwrap();
+        assert_eq!(result, arg);
 
-        let cli = Cli::parse_from([
-            "compute_ctl",
-            "--pgdata=test",
-            "--connstr=test",
-            "--compute-id=test",
-            "--remote-ext-base-url",
-            "https://example.com//",
-        ]);
+        let arg = "pg-ext-s3-gateway";
+        let result = super::parse_remote_ext_base_url(arg).unwrap();
         assert_eq!(
-            cli.remote_ext_base_url.unwrap(),
-            Url::parse("https://example.com").unwrap()
+            result,
+            "http://pg-ext-s3-gateway.pg-ext-s3-gateway.svc.cluster.local"
         );
-
-        Cli::try_parse_from([
-            "compute_ctl",
-            "--pgdata=test",
-            "--connstr=test",
-            "--compute-id=test",
-            "--remote-ext-base-url",
-            "https://example.com?hello=world",
-        ])
-        .expect_err("URL parameters are not allowed");
     }
 }

compute_tools/src/bin/fast_import.rs

@@ -339,8 +339,6 @@ async fn run_dump_restore(
     destination_connstring: String,
 ) -> Result<(), anyhow::Error> {
     let dumpdir = workdir.join("dumpdir");
-    let num_jobs = num_cpus::get().to_string();
-    info!("using {num_jobs} jobs for dump/restore");
 
     let common_args = [
         // schema mapping (prob suffices to specify them on one side)
@@ -356,7 +354,7 @@ async fn run_dump_restore(
         "directory".to_string(),
         // concurrency
         "--jobs".to_string(),
-        num_jobs,
+        num_cpus::get().to_string(),
         // progress updates
         "--verbose".to_string(),
     ];

compute_tools/src/compute.rs

@@ -3,7 +3,7 @@ use chrono::{DateTime, Utc};
 use compute_api::privilege::Privilege;
 use compute_api::responses::{
     ComputeConfig, ComputeCtlConfig, ComputeMetrics, ComputeStatus, LfcOffloadState,
-    LfcPrewarmState, TlsConfig,
+    LfcPrewarmState,
 };
 use compute_api::spec::{
     ComputeAudit, ComputeFeature, ComputeMode, ComputeSpec, ExtVersion, PgIdent,
@@ -11,7 +11,6 @@ use compute_api::spec::{
 use futures::StreamExt;
 use futures::future::join_all;
 use futures::stream::FuturesUnordered;
-use itertools::Itertools;
 use nix::sys::signal::{Signal, kill};
 use nix::unistd::Pid;
 use once_cell::sync::Lazy;
@@ -19,7 +18,7 @@ use postgres;
 use postgres::NoTls;
 use postgres::error::SqlState;
 use remote_storage::{DownloadError, RemotePath};
-use std::collections::{HashMap, HashSet};
+use std::collections::HashMap;
 use std::net::SocketAddr;
 use std::os::unix::fs::{PermissionsExt, symlink};
 use std::path::Path;
@@ -31,11 +30,9 @@ use std::time::{Duration, Instant};
 use std::{env, fs};
 use tokio::spawn;
 use tracing::{Instrument, debug, error, info, instrument, warn};
-use url::Url;
 use utils::id::{TenantId, TimelineId};
 use utils::lsn::Lsn;
 use utils::measured_stream::MeasuredReader;
-use utils::pid_file;
 
 use crate::configurator::launch_configurator;
 use crate::disk_quota::set_disk_quota;
@@ -45,7 +42,6 @@ use crate::lsn_lease::launch_lsn_lease_bg_task_for_static;
 use crate::metrics::COMPUTE_CTL_UP;
 use crate::monitor::launch_monitor;
 use crate::pg_helpers::*;
-use crate::pgbouncer::*;
 use crate::rsyslog::{
     PostgresLogsRsyslogConfig, configure_audit_rsyslog, configure_postgres_logs_export,
     launch_pgaudit_gc,
@@ -99,10 +95,7 @@ pub struct ComputeNodeParams {
     pub internal_http_port: u16,
 
     /// the address of extension storage proxy gateway
-    pub remote_ext_base_url: Option<Url>,
-
-    /// Interval for installed extensions collection
-    pub installed_extensions_collection_interval: u64,
+    pub remote_ext_base_url: Option<String>,
 }
 
 /// Compute node info shared across several `compute_ctl` threads.
@@ -163,10 +156,6 @@ pub struct ComputeState {
     pub lfc_prewarm_state: LfcPrewarmState,
     pub lfc_offload_state: LfcOffloadState,
 
-    /// WAL flush LSN that is set after terminating Postgres and syncing safekeepers if
-    /// mode == ComputeMode::Primary. None otherwise
-    pub terminate_flush_lsn: Option<Lsn>,
-
     pub metrics: ComputeMetrics,
 }
 
@@ -182,7 +171,6 @@ impl ComputeState {
             metrics: ComputeMetrics::default(),
             lfc_prewarm_state: LfcPrewarmState::default(),
             lfc_offload_state: LfcOffloadState::default(),
-            terminate_flush_lsn: None,
         }
     }
 
@@ -222,46 +210,6 @@ pub struct ParsedSpec {
     pub endpoint_storage_token: Option<String>,
 }
 
-impl ParsedSpec {
-    pub fn validate(&self) -> Result<(), String> {
-        // Only Primary nodes are using safekeeper_connstrings, and at the moment
-        // this method only validates that part of the specs.
-        if self.spec.mode != ComputeMode::Primary {
-            return Ok(());
-        }
-
-        // While it seems like a good idea to check for an odd number of entries in
-        // the safekeepers connection string, changes to the list of safekeepers might
-        // incur appending a new server to a list of 3, in which case a list of 4
-        // entries is okay in production.
-        //
-        // Still we want unique entries, and at least one entry in the vector
-        if self.safekeeper_connstrings.is_empty() {
-            return Err(String::from("safekeeper_connstrings is empty"));
-        }
-
-        // check for uniqueness of the connection strings in the set
-        let mut connstrings = self.safekeeper_connstrings.clone();
-
-        connstrings.sort();
-        let mut previous = &connstrings[0];
-
-        for current in connstrings.iter().skip(1) {
-            // duplicate entry?
-            if current == previous {
-                return Err(format!(
-                    "duplicate entry in safekeeper_connstrings: {}!",
-                    current,
-                ));
-            }
-
-            previous = current;
-        }
-
-        Ok(())
-    }
-}
-
 impl TryFrom<ComputeSpec> for ParsedSpec {
     type Error = String;
     fn try_from(spec: ComputeSpec) -> Result<Self, String> {
@@ -291,7 +239,6 @@ impl TryFrom<ComputeSpec> for ParsedSpec {
         } else {
             spec.safekeeper_connstrings.clone()
         };
-
         let storage_auth_token = spec.storage_auth_token.clone();
         let tenant_id: TenantId = if let Some(tenant_id) = spec.tenant_id {
             tenant_id
@@ -326,7 +273,7 @@ impl TryFrom<ComputeSpec> for ParsedSpec {
             .clone()
             .or_else(|| spec.cluster.settings.find("neon.endpoint_storage_token"));
 
-        let res = ParsedSpec {
+        Ok(ParsedSpec {
             spec,
             pageserver_connstr,
             safekeeper_connstrings,
@@ -335,11 +282,7 @@ impl TryFrom<ComputeSpec> for ParsedSpec {
             timeline_id,
             endpoint_storage_addr,
             endpoint_storage_token,
-        };
-
-        // Now check validity of the parsed specification
-        res.validate()?;
-        Ok(res)
+        })
     }
 }
 
@@ -406,11 +349,14 @@ impl ComputeNode {
         // that can affect `compute_ctl` and prevent it from properly configuring the database schema.
         // Unset them via connection string options before connecting to the database.
         // N.B. keep it in sync with `ZENITH_OPTIONS` in `get_maintenance_client()`.
+        //
+        // TODO(ololobus): we currently pass `-c default_transaction_read_only=off` from control plane
+        // as well. After rolling out this code, we can remove this parameter from control plane.
+        // In the meantime, double-passing is fine, the last value is applied.
+        // See: <https://github.com/neondatabase/cloud/blob/133dd8c4dbbba40edfbad475bf6a45073ca63faf/goapp/controlplane/internal/pkg/compute/provisioner/provisioner_common.go#L70>
         const EXTRA_OPTIONS: &str = "-c role=cloud_admin -c default_transaction_read_only=off -c search_path=public -c statement_timeout=0";
         let options = match conn_conf.get_options() {
-            // Allow the control plane to override any options set by the
-            // compute
-            Some(options) => format!("{} {}", EXTRA_OPTIONS, options),
+            Some(options) => format!("{} {}", options, EXTRA_OPTIONS),
             None => EXTRA_OPTIONS.to_string(),
         };
         conn_conf.options(&options);
@@ -445,7 +391,7 @@ impl ComputeNode {
         // because QEMU will already have its memory allocated from the host, and
         // the necessary binaries will already be cached.
         if cli_spec.is_none() {
-            this.prewarm_postgres_vm_memory()?;
+            this.prewarm_postgres()?;
         }
 
         // Set the up metric with Empty status before starting the HTTP server.
@@ -538,21 +484,12 @@ impl ComputeNode {
         // Reap the postgres process
         delay_exit |= this.cleanup_after_postgres_exit()?;
 
-        // /terminate returns LSN. If we don't sleep at all, connection will break and we
-        // won't get result. If we sleep too much, tests will take significantly longer
-        // and Github Action run will error out
-        let sleep_duration = if delay_exit {
-            Duration::from_secs(30)
-        } else {
-            Duration::from_millis(300)
-        };
-
         // If launch failed, keep serving HTTP requests for a while, so the cloud
         // control plane can get the actual error.
         if delay_exit {
             info!("giving control plane 30s to collect the error before shutdown");
+            std::thread::sleep(Duration::from_secs(30));
         }
-        std::thread::sleep(sleep_duration);
         Ok(exit_code)
     }
 
@@ -661,8 +598,6 @@ impl ComputeNode {
             });
         }
 
-        let tls_config = self.tls_config(&pspec.spec);
-
         // If there are any remote extensions in shared_preload_libraries, start downloading them
         if pspec.spec.remote_extensions.is_some() {
             let (this, spec) = (self.clone(), pspec.spec.clone());
@@ -719,7 +654,7 @@ impl ComputeNode {
             info!("tuning pgbouncer");
 
             let pgbouncer_settings = pgbouncer_settings.clone();
-            let tls_config = tls_config.clone();
+            let tls_config = self.compute_ctl_config.tls.clone();
 
             // Spawn a background task to do the tuning,
             // so that we don't block the main thread that starts Postgres.
@@ -738,10 +673,7 @@ impl ComputeNode {
 
             // Spawn a background task to do the configuration,
             // so that we don't block the main thread that starts Postgres.
-
-            let mut local_proxy = local_proxy.clone();
-            local_proxy.tls = tls_config.clone();
-
+            let local_proxy = local_proxy.clone();
             let _handle = tokio::spawn(async move {
                 if let Err(err) = local_proxy::configure(&local_proxy) {
                     error!("error while configuring local_proxy: {err:?}");
@@ -762,18 +694,25 @@ impl ComputeNode {
                 let log_directory_path = Path::new(&self.params.pgdata).join("log");
                 let log_directory_path = log_directory_path.to_string_lossy().to_string();
 
-                // Add project_id,endpoint_id to identify the logs.
+                // Add project_id,endpoint_id tag to identify the logs.
                 //
                 // These ids are passed from cplane,
-                let endpoint_id = pspec.spec.endpoint_id.as_deref().unwrap_or("");
-                let project_id = pspec.spec.project_id.as_deref().unwrap_or("");
+                // for backwards compatibility (old computes that don't have them),
+                // we set them to None.
+                // TODO: Clean up this code when all computes have them.
+                let tag: Option<String> = match (
+                    pspec.spec.project_id.as_deref(),
+                    pspec.spec.endpoint_id.as_deref(),
+                ) {
+                    (Some(project_id), Some(endpoint_id)) => {
+                        Some(format!("{project_id}/{endpoint_id}"))
+                    }
+                    (Some(project_id), None) => Some(format!("{project_id}/None")),
+                    (None, Some(endpoint_id)) => Some(format!("None,{endpoint_id}")),
+                    (None, None) => None,
+                };
 
-                configure_audit_rsyslog(
-                    log_directory_path.clone(),
-                    endpoint_id,
-                    project_id,
-                    &remote_endpoint,
-                )?;
+                configure_audit_rsyslog(log_directory_path.clone(), tag, &remote_endpoint)?;
 
                 // Launch a background task to clean up the audit logs
                 launch_pgaudit_gc(log_directory_path);
@@ -809,7 +748,17 @@ impl ComputeNode {
 
             let conf = self.get_tokio_conn_conf(None);
             tokio::task::spawn(async {
-                let _ = installed_extensions(conf).await;
+                let res = get_installed_extensions(conf).await;
+                match res {
+                    Ok(extensions) => {
+                        info!(
+                            "[NEON_EXT_STAT] {}",
+                            serde_json::to_string(&extensions)
+                                .expect("failed to serialize extensions list")
+                        );
+                    }
+                    Err(err) => error!("could not get installed extensions: {err:?}"),
+                }
             });
         }
 
@@ -839,11 +788,8 @@ impl ComputeNode {
         // Log metrics so that we can search for slow operations in logs
         info!(?metrics, postmaster_pid = %postmaster_pid, "compute start finished");
 
-        // Spawn the extension stats background task
-        self.spawn_extension_stats_task();
-
-        if pspec.spec.autoprewarm {
-            self.prewarm_lfc(None);
+        if pspec.spec.prewarm_lfc_on_startup {
+            self.prewarm_lfc();
         }
         Ok(())
     }
@@ -924,25 +870,20 @@ impl ComputeNode {
         // Maybe sync safekeepers again, to speed up next startup
         let compute_state = self.state.lock().unwrap().clone();
         let pspec = compute_state.pspec.as_ref().expect("spec must be set");
-        let lsn = if matches!(pspec.spec.mode, compute_api::spec::ComputeMode::Primary) {
+        if matches!(pspec.spec.mode, compute_api::spec::ComputeMode::Primary) {
             info!("syncing safekeepers on shutdown");
             let storage_auth_token = pspec.storage_auth_token.clone();
             let lsn = self.sync_safekeepers(storage_auth_token)?;
-            info!(%lsn, "synced safekeepers");
-            Some(lsn)
-        } else {
-            info!("not primary, not syncing safekeepers");
-            None
-        };
+            info!("synced safekeepers at lsn {lsn}");
+        }
 
         let mut delay_exit = false;
         let mut state = self.state.lock().unwrap();
-        state.terminate_flush_lsn = lsn;
-        if let ComputeStatus::TerminationPending { mode } = state.status {
+        if state.status == ComputeStatus::TerminationPending {
             state.status = ComputeStatus::Terminated;
             self.state_changed.notify_all();
             // we were asked to terminate gracefully, don't exit to avoid restart
-            delay_exit = mode == compute_api::responses::TerminateMode::Fast
+            delay_exit = true
         }
         drop(state);
 
@@ -1273,15 +1214,13 @@ impl ComputeNode {
         let spec = &pspec.spec;
         let pgdata_path = Path::new(&self.params.pgdata);
 
-        let tls_config = self.tls_config(&pspec.spec);
-
         // Remove/create an empty pgdata directory and put configuration there.
         self.create_pgdata()?;
         config::write_postgres_conf(
             pgdata_path,
             &pspec.spec,
             self.params.internal_http_port,
-            tls_config,
+            &self.compute_ctl_config.tls,
         )?;
 
         // Syncing safekeepers is only safe with primary nodes: if a primary
@@ -1377,8 +1316,8 @@ impl ComputeNode {
     }
 
     /// Start and stop a postgres process to warm up the VM for startup.
-    pub fn prewarm_postgres_vm_memory(&self) -> Result<()> {
-        info!("prewarming VM memory");
+    pub fn prewarm_postgres(&self) -> Result<()> {
+        info!("prewarming");
 
         // Create pgdata
         let pgdata = &format!("{}.warmup", self.params.pgdata);
@@ -1420,7 +1359,7 @@ impl ComputeNode {
         kill(pm_pid, Signal::SIGQUIT)?;
         info!("sent SIGQUIT signal");
         pg.wait()?;
-        info!("done prewarming vm memory");
+        info!("done prewarming");
 
         // clean up
         let _ok = fs::remove_dir_all(pgdata);
@@ -1606,22 +1545,14 @@ impl ComputeNode {
                 .clone(),
         );
 
-        let mut tls_config = None::<TlsConfig>;
-        if spec.features.contains(&ComputeFeature::TlsExperimental) {
-            tls_config = self.compute_ctl_config.tls.clone();
-        }
-
         let max_concurrent_connections = self.max_service_connections(compute_state, &spec);
 
         // Merge-apply spec & changes to PostgreSQL state.
         self.apply_spec_sql(spec.clone(), conf.clone(), max_concurrent_connections)?;
 
         if let Some(local_proxy) = &spec.clone().local_proxy_config {
-            let mut local_proxy = local_proxy.clone();
-            local_proxy.tls = tls_config.clone();
-
             info!("configuring local_proxy");
-            local_proxy::configure(&local_proxy).context("apply_config local_proxy")?;
+            local_proxy::configure(local_proxy).context("apply_config local_proxy")?;
         }
 
         // Run migrations separately to not hold up cold starts
@@ -1673,13 +1604,11 @@ impl ComputeNode {
     pub fn reconfigure(&self) -> Result<()> {
         let spec = self.state.lock().unwrap().pspec.clone().unwrap().spec;
 
-        let tls_config = self.tls_config(&spec);
-
         if let Some(ref pgbouncer_settings) = spec.pgbouncer_settings {
             info!("tuning pgbouncer");
 
             let pgbouncer_settings = pgbouncer_settings.clone();
-            let tls_config = tls_config.clone();
+            let tls_config = self.compute_ctl_config.tls.clone();
 
             // Spawn a background task to do the tuning,
             // so that we don't block the main thread that starts Postgres.
@@ -1697,7 +1626,7 @@ impl ComputeNode {
             // Spawn a background task to do the configuration,
             // so that we don't block the main thread that starts Postgres.
             let mut local_proxy = local_proxy.clone();
-            local_proxy.tls = tls_config.clone();
+            local_proxy.tls = self.compute_ctl_config.tls.clone();
             tokio::spawn(async move {
                 if let Err(err) = local_proxy::configure(&local_proxy) {
                     error!("error while configuring local_proxy: {err:?}");
@@ -1715,7 +1644,7 @@ impl ComputeNode {
             pgdata_path,
             &spec,
             self.params.internal_http_port,
-            tls_config,
+            &self.compute_ctl_config.tls,
         )?;
 
         if !spec.skip_pg_catalog_updates {
@@ -1813,7 +1742,7 @@ impl ComputeNode {
 
                             // exit loop
                             ComputeStatus::Failed
-                            | ComputeStatus::TerminationPending { .. }
+                            | ComputeStatus::TerminationPending
                             | ComputeStatus::Terminated => break 'cert_update,
 
                             // wait
@@ -1835,14 +1764,6 @@ impl ComputeNode {
         }
     }
 
-    pub fn tls_config(&self, spec: &ComputeSpec) -> &Option<TlsConfig> {
-        if spec.features.contains(&ComputeFeature::TlsExperimental) {
-            &self.compute_ctl_config.tls
-        } else {
-            &None::<TlsConfig>
-        }
-    }
-
     /// Update the `last_active` in the shared state, but ensure that it's a more recent one.
     pub fn update_last_active(&self, last_active: Option<DateTime<Utc>>) {
         let mut state = self.state.lock().unwrap();
@@ -2074,40 +1995,23 @@ LIMIT 100",
         tokio::spawn(conn);
 
         // TODO: support other types of grants apart from schemas?
-
-        // check the role grants first - to gracefully handle read-replicas.
-        let select = "SELECT privilege_type
-            FROM pg_namespace
-                JOIN LATERAL (SELECT * FROM aclexplode(nspacl) AS x) acl ON true
-                JOIN pg_user users ON acl.grantee = users.usesysid
-            WHERE users.usename = $1
-                AND nspname = $2";
-        let rows = db_client
-            .query(select, &[role_name, schema_name])
-            .await
-            .with_context(|| format!("Failed to execute query: {select}"))?;
-
-        let already_granted: HashSet<String> = rows.into_iter().map(|row| row.get(0)).collect();
-
-        let grants = privileges
-            .iter()
-            .filter(|p| !already_granted.contains(p.as_str()))
-            // should not be quoted as it's part of the command.
-            // is already sanitized so it's ok
-            .map(|p| p.as_str())
-            .join(", ");
-
-        if !grants.is_empty() {
+        let query = format!(
+            "GRANT {} ON SCHEMA {} TO {}",
+            privileges
+                .iter()
+                // should not be quoted as it's part of the command.
+                // is already sanitized so it's ok
+                .map(|p| p.as_str())
+                .collect::<Vec<&'static str>>()
+                .join(", "),
             // quote the schema and role name as identifiers to sanitize them.
-            let schema_name = schema_name.pg_quote();
-            let role_name = role_name.pg_quote();
-
-            let query = format!("GRANT {grants} ON SCHEMA {schema_name} TO {role_name}",);
-            db_client
-                .simple_query(&query)
-                .await
-                .with_context(|| format!("Failed to execute query: {}", query))?;
-        }
+            schema_name.pg_quote(),
+            role_name.pg_quote(),
+        );
+        db_client
+            .simple_query(&query)
+            .await
+            .with_context(|| format!("Failed to execute query: {}", query))?;
 
         Ok(())
     }
@@ -2277,105 +2181,14 @@ LIMIT 100",
             info!("Pageserver config changed");
         }
     }
-
-    pub fn spawn_extension_stats_task(&self) {
-        let conf = self.tokio_conn_conf.clone();
-        let installed_extensions_collection_interval =
-            self.params.installed_extensions_collection_interval;
-        tokio::spawn(async move {
-            // An initial sleep is added to ensure that two collections don't happen at the same time.
-            // The first collection happens during compute startup.
-            tokio::time::sleep(tokio::time::Duration::from_secs(
-                installed_extensions_collection_interval,
-            ))
-            .await;
-            let mut interval = tokio::time::interval(tokio::time::Duration::from_secs(
-                installed_extensions_collection_interval,
-            ));
-            loop {
-                interval.tick().await;
-                let _ = installed_extensions(conf.clone()).await;
-            }
-        });
-    }
 }
 
-pub async fn installed_extensions(conf: tokio_postgres::Config) -> Result<()> {
-    let res = get_installed_extensions(conf).await;
-    match res {
-        Ok(extensions) => {
-            info!(
-                "[NEON_EXT_STAT] {}",
-                serde_json::to_string(&extensions).expect("failed to serialize extensions list")
-            );
-        }
-        Err(err) => error!("could not get installed extensions: {err:?}"),
-    }
-    Ok(())
-}
-
-pub fn forward_termination_signal(dev_mode: bool) {
+pub fn forward_termination_signal() {
     let ss_pid = SYNC_SAFEKEEPERS_PID.load(Ordering::SeqCst);
     if ss_pid != 0 {
         let ss_pid = nix::unistd::Pid::from_raw(ss_pid as i32);
         kill(ss_pid, Signal::SIGTERM).ok();
     }
-
-    if !dev_mode {
-        //  Terminate pgbouncer with SIGKILL
-        match pid_file::read(PGBOUNCER_PIDFILE.into()) {
-            Ok(pid_file::PidFileRead::LockedByOtherProcess(pid)) => {
-                info!("sending SIGKILL to pgbouncer process pid: {}", pid);
-                if let Err(e) = kill(pid, Signal::SIGKILL) {
-                    error!("failed to terminate pgbouncer: {}", e);
-                }
-            }
-            // pgbouncer does not lock the pid file, so we read and kill the process directly
-            Ok(pid_file::PidFileRead::NotHeldByAnyProcess(_)) => {
-                if let Ok(pid_str) = std::fs::read_to_string(PGBOUNCER_PIDFILE) {
-                    if let Ok(pid) = pid_str.trim().parse::<i32>() {
-                        info!(
-                            "sending SIGKILL to pgbouncer process pid: {} (from unlocked pid file)",
-                            pid
-                        );
-                        if let Err(e) = kill(Pid::from_raw(pid), Signal::SIGKILL) {
-                            error!("failed to terminate pgbouncer: {}", e);
-                        }
-                    }
-                } else {
-                    info!("pgbouncer pid file exists but process not running");
-                }
-            }
-            Ok(pid_file::PidFileRead::NotExist) => {
-                info!("pgbouncer pid file not found, process may not be running");
-            }
-            Err(e) => {
-                error!("error reading pgbouncer pid file: {}", e);
-            }
-        }
-
-        // Terminate local_proxy
-        match pid_file::read("/etc/local_proxy/pid".into()) {
-            Ok(pid_file::PidFileRead::LockedByOtherProcess(pid)) => {
-                info!("sending SIGTERM to local_proxy process pid: {}", pid);
-                if let Err(e) = kill(pid, Signal::SIGTERM) {
-                    error!("failed to terminate local_proxy: {}", e);
-                }
-            }
-            Ok(pid_file::PidFileRead::NotHeldByAnyProcess(_)) => {
-                info!("local_proxy PID file exists but process not running");
-            }
-            Ok(pid_file::PidFileRead::NotExist) => {
-                info!("local_proxy PID file not found, process may not be running");
-            }
-            Err(e) => {
-                error!("error reading local_proxy PID file: {}", e);
-            }
-        }
-    } else {
-        info!("Skipping pgbouncer and local_proxy termination because in dev mode");
-    }
-
     let pg_pid = PG_PID.load(Ordering::SeqCst);
     if pg_pid != 0 {
         let pg_pid = nix::unistd::Pid::from_raw(pg_pid as i32);
@@ -2408,21 +2221,3 @@ impl<T: 'static> JoinSetExt<T> for tokio::task::JoinSet<T> {
         })
     }
 }
-
-#[cfg(test)]
-mod tests {
-    use std::fs::File;
-
-    use super::*;
-
-    #[test]
-    fn duplicate_safekeeper_connstring() {
-        let file = File::open("tests/cluster_spec.json").unwrap();
-        let spec: ComputeSpec = serde_json::from_reader(file).unwrap();
-
-        match ParsedSpec::try_from(spec.clone()) {
-            Ok(_p) => panic!("Failed to detect duplicate entry"),
-            Err(e) => assert!(e.starts_with("duplicate entry in safekeeper_connstrings:")),
-        };
-    }
-}

compute_tools/src/compute_prewarm.rs

@@ -25,16 +25,11 @@ struct EndpointStoragePair {
 }
 
 const KEY: &str = "lfc_state";
-impl EndpointStoragePair {
-    /// endpoint_id is set to None while prewarming from other endpoint, see replica promotion
-    /// If not None, takes precedence over pspec.spec.endpoint_id
-    fn from_spec_and_endpoint(
-        pspec: &crate::compute::ParsedSpec,
-        endpoint_id: Option<String>,
-    ) -> Result<Self> {
-        let endpoint_id = endpoint_id.as_ref().or(pspec.spec.endpoint_id.as_ref());
-        let Some(ref endpoint_id) = endpoint_id else {
-            bail!("pspec.endpoint_id missing, other endpoint_id not provided")
+impl TryFrom<&crate::compute::ParsedSpec> for EndpointStoragePair {
+    type Error = anyhow::Error;
+    fn try_from(pspec: &crate::compute::ParsedSpec) -> Result<Self, Self::Error> {
+        let Some(ref endpoint_id) = pspec.spec.endpoint_id else {
+            bail!("pspec.endpoint_id missing")
         };
         let Some(ref base_uri) = pspec.endpoint_storage_addr else {
             bail!("pspec.endpoint_storage_addr missing")
@@ -89,7 +84,7 @@ impl ComputeNode {
     }
 
     /// Returns false if there is a prewarm request ongoing, true otherwise
-    pub fn prewarm_lfc(self: &Arc<Self>, from_endpoint: Option<String>) -> bool {
+    pub fn prewarm_lfc(self: &Arc<Self>) -> bool {
         crate::metrics::LFC_PREWARM_REQUESTS.inc();
         {
             let state = &mut self.state.lock().unwrap().lfc_prewarm_state;
@@ -102,7 +97,7 @@ impl ComputeNode {
 
         let cloned = self.clone();
         spawn(async move {
-            let Err(err) = cloned.prewarm_impl(from_endpoint).await else {
+            let Err(err) = cloned.prewarm_impl().await else {
                 cloned.state.lock().unwrap().lfc_prewarm_state = LfcPrewarmState::Completed;
                 return;
             };
@@ -114,14 +109,13 @@ impl ComputeNode {
         true
     }
 
-    /// from_endpoint: None for endpoint managed by this compute_ctl
-    fn endpoint_storage_pair(&self, from_endpoint: Option<String>) -> Result<EndpointStoragePair> {
+    fn endpoint_storage_pair(&self) -> Result<EndpointStoragePair> {
         let state = self.state.lock().unwrap();
-        EndpointStoragePair::from_spec_and_endpoint(state.pspec.as_ref().unwrap(), from_endpoint)
+        state.pspec.as_ref().unwrap().try_into()
     }
 
-    async fn prewarm_impl(&self, from_endpoint: Option<String>) -> Result<()> {
-        let EndpointStoragePair { url, token } = self.endpoint_storage_pair(from_endpoint)?;
+    async fn prewarm_impl(&self) -> Result<()> {
+        let EndpointStoragePair { url, token } = self.endpoint_storage_pair()?;
         info!(%url, "requesting LFC state from endpoint storage");
 
         let request = Client::new().get(&url).bearer_auth(token);
@@ -179,7 +173,7 @@ impl ComputeNode {
     }
 
     async fn offload_lfc_impl(&self) -> Result<()> {
-        let EndpointStoragePair { url, token } = self.endpoint_storage_pair(None)?;
+        let EndpointStoragePair { url, token } = self.endpoint_storage_pair()?;
         info!(%url, "requesting LFC state from postgres");
 
         let mut compressed = Vec::new();

compute_tools/src/config.rs

@@ -224,10 +224,7 @@ pub fn write_postgres_conf(
             writeln!(file, "pgaudit.log_rotation_age=5")?;
 
             // Enable audit logs for pg_session_jwt extension
-            // TODO: Consider a good approach for shipping pg_session_jwt logs to the same sink as
-            // pgAudit - additional context in https://github.com/neondatabase/cloud/issues/28863
-            //
-            // writeln!(file, "pg_session_jwt.audit_log=on")?;
+            writeln!(file, "pg_session_jwt.audit_log=on")?;
 
             // Add audit shared_preload_libraries, if they are not present.
             //

compute_tools/src/config_template/compute_audit_rsyslog_template.conf

@@ -2,24 +2,10 @@
 module(load="imfile")
 
 # Input configuration for log files in the specified directory
-# The messages can be multiline. The start of the message is a timestamp
-# in "%Y-%m-%d %H:%M:%S.%3N GMT" (so timezone hardcoded).
-# Replace log_directory with the directory containing the log files
-input(type="imfile" File="{log_directory}/*.log"
-  Tag="pgaudit_log" Severity="info" Facility="local5"
-  startmsg.regex="^[[:digit:]]{{4}}-[[:digit:]]{{2}}-[[:digit:]]{{2}} [[:digit:]]{{2}}:[[:digit:]]{{2}}:[[:digit:]]{{2}}.[[:digit:]]{{3}} GMT,")
-
+# Replace {log_directory} with the directory containing the log files
+input(type="imfile" File="{log_directory}/*.log" Tag="{tag}" Severity="info" Facility="local0")
 # the directory to store rsyslog state files
 global(workDirectory="/var/log/rsyslog")
 
-# Construct json, endpoint_id and project_id as additional metadata
-set $.json_log!endpoint_id = "{endpoint_id}";
-set $.json_log!project_id = "{project_id}";
-set $.json_log!msg = $msg;
-
-# Template suitable for rfc5424 syslog format
-template(name="PgAuditLog" type="string"
-    string="<%PRI%>1 %TIMESTAMP:::date-rfc3339% %HOSTNAME% - - - - %$.json_log%")
-
-# Forward to remote syslog receiver (@@<hostname>:<port>;format
-local5.info @@{remote_endpoint};PgAuditLog
+# Forward logs to remote syslog server
+*.* @@{remote_endpoint}

compute_tools/src/extension_server.rs

@@ -83,7 +83,6 @@ use reqwest::StatusCode;
 use tar::Archive;
 use tracing::info;
 use tracing::log::warn;
-use url::Url;
 use zstd::stream::read::Decoder;
 
 use crate::metrics::{REMOTE_EXT_REQUESTS_TOTAL, UNKNOWN_HTTP_STATUS};
@@ -159,7 +158,7 @@ fn parse_pg_version(human_version: &str) -> PostgresMajorVersion {
 pub async fn download_extension(
     ext_name: &str,
     ext_path: &RemotePath,
-    remote_ext_base_url: &Url,
+    remote_ext_base_url: &str,
     pgbin: &str,
 ) -> Result<u64> {
     info!("Download extension {:?} from {:?}", ext_name, ext_path);
@@ -271,14 +270,10 @@ pub fn create_control_files(remote_extensions: &RemoteExtSpec, pgbin: &str) {
 }
 
 // Do request to extension storage proxy, e.g.,
-// curl http://pg-ext-s3-gateway.pg-ext-s3-gateway.svc.cluster.local/latest/v15/extensions/anon.tar.zst
+// curl http://pg-ext-s3-gateway/latest/v15/extensions/anon.tar.zst
 // using HTTP GET and return the response body as bytes.
-async fn download_extension_tar(remote_ext_base_url: &Url, ext_path: &str) -> Result<Bytes> {
-    let uri = remote_ext_base_url.join(ext_path).with_context(|| {
-        format!(
-            "failed to create the remote extension URI for {ext_path} using {remote_ext_base_url}"
-        )
-    })?;
+async fn download_extension_tar(remote_ext_base_url: &str, ext_path: &str) -> Result<Bytes> {
+    let uri = format!("{}/{}", remote_ext_base_url, ext_path);
     let filename = Path::new(ext_path)
         .file_name()
         .unwrap_or_else(|| std::ffi::OsStr::new("unknown"))
@@ -288,7 +283,7 @@ async fn download_extension_tar(remote_ext_base_url: &Url, ext_path: &str) -> Re
 
     info!("Downloading extension file '{}' from uri {}", filename, uri);
 
-    match do_extension_server_request(uri).await {
+    match do_extension_server_request(&uri).await {
         Ok(resp) => {
             info!("Successfully downloaded remote extension data {}", ext_path);
             REMOTE_EXT_REQUESTS_TOTAL
@@ -307,7 +302,7 @@ async fn download_extension_tar(remote_ext_base_url: &Url, ext_path: &str) -> Re
 
 // 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: Url) -> Result<Bytes, (String, String)> {
+async fn do_extension_server_request(uri: &str) -> Result<Bytes, (String, String)> {
     let resp = reqwest::get(uri).await.map_err(|e| {
         (
             format!(

compute_tools/src/http/mod.rs

@@ -48,9 +48,11 @@ impl JsonResponse {
 
     /// Create an error response related to the compute being in an invalid state
     pub(self) fn invalid_status(status: ComputeStatus) -> Response {
-        Self::error(
+        Self::create_response(
             StatusCode::PRECONDITION_FAILED,
-            format!("invalid compute status: {status}"),
+            &GenericAPIError {
+                error: format!("invalid compute status: {status}"),
+            },
         )
     }
 }

compute_tools/src/http/routes/configure.rs

@@ -22,7 +22,7 @@ pub(in crate::http) async fn configure(
     State(compute): State<Arc<ComputeNode>>,
     request: Json<ConfigurationRequest>,
 ) -> Response {
-    let pspec = match ParsedSpec::try_from(request.0.spec) {
+    let pspec = match ParsedSpec::try_from(request.spec.clone()) {
         Ok(p) => p,
         Err(e) => return JsonResponse::error(StatusCode::BAD_REQUEST, e),
     };

compute_tools/src/http/routes/lfc.rs

@@ -2,7 +2,6 @@ use crate::compute_prewarm::LfcPrewarmStateWithProgress;
 use crate::http::JsonResponse;
 use axum::response::{IntoResponse, Response};
 use axum::{Json, http::StatusCode};
-use axum_extra::extract::OptionalQuery;
 use compute_api::responses::LfcOffloadState;
 type Compute = axum::extract::State<std::sync::Arc<crate::compute::ComputeNode>>;
 
@@ -17,16 +16,8 @@ pub(in crate::http) async fn offload_state(compute: Compute) -> Json<LfcOffloadS
     Json(compute.lfc_offload_state())
 }
 
-#[derive(serde::Deserialize)]
-pub struct PrewarmQuery {
-    pub from_endpoint: String,
-}
-
-pub(in crate::http) async fn prewarm(
-    compute: Compute,
-    OptionalQuery(query): OptionalQuery<PrewarmQuery>,
-) -> Response {
-    if compute.prewarm_lfc(query.map(|q| q.from_endpoint)) {
+pub(in crate::http) async fn prewarm(compute: Compute) -> Response {
+    if compute.prewarm_lfc() {
         StatusCode::ACCEPTED.into_response()
     } else {
         JsonResponse::error(

compute_tools/src/http/routes/terminate.rs

@@ -1,42 +1,32 @@
-use crate::compute::{ComputeNode, forward_termination_signal};
-use crate::http::JsonResponse;
-use axum::extract::State;
-use axum::response::Response;
-use axum_extra::extract::OptionalQuery;
-use compute_api::responses::{ComputeStatus, TerminateResponse};
-use http::StatusCode;
-use serde::Deserialize;
 use std::sync::Arc;
+
+use axum::extract::State;
+use axum::response::{IntoResponse, Response};
+use compute_api::responses::ComputeStatus;
+use http::StatusCode;
 use tokio::task;
 use tracing::info;
 
-#[derive(Deserialize, Default)]
-pub struct TerminateQuery {
-    mode: compute_api::responses::TerminateMode,
-}
+use crate::compute::{ComputeNode, forward_termination_signal};
+use crate::http::JsonResponse;
 
 /// Terminate the compute.
-pub(in crate::http) async fn terminate(
-    State(compute): State<Arc<ComputeNode>>,
-    OptionalQuery(terminate): OptionalQuery<TerminateQuery>,
-) -> Response {
-    let mode = terminate.unwrap_or_default().mode;
+pub(in crate::http) async fn terminate(State(compute): State<Arc<ComputeNode>>) -> Response {
     {
         let mut state = compute.state.lock().unwrap();
         if state.status == ComputeStatus::Terminated {
-            return JsonResponse::success(StatusCode::CREATED, state.terminate_flush_lsn);
+            return StatusCode::CREATED.into_response();
         }
 
         if !matches!(state.status, ComputeStatus::Empty | ComputeStatus::Running) {
             return JsonResponse::invalid_status(state.status);
         }
-        state.set_status(
-            ComputeStatus::TerminationPending { mode },
-            &compute.state_changed,
-        );
+
+        state.set_status(ComputeStatus::TerminationPending, &compute.state_changed);
+        drop(state);
     }
 
-    forward_termination_signal(false);
+    forward_termination_signal();
     info!("sent signal and notified waiters");
 
     // Spawn a blocking thread to wait for compute to become Terminated.
@@ -44,7 +34,7 @@ pub(in crate::http) async fn terminate(
     // be able to serve other requests while some particular request
     // is waiting for compute to finish configuration.
     let c = compute.clone();
-    let lsn = task::spawn_blocking(move || {
+    task::spawn_blocking(move || {
         let mut state = c.state.lock().unwrap();
         while state.status != ComputeStatus::Terminated {
             state = c.state_changed.wait(state).unwrap();
@@ -54,10 +44,11 @@ pub(in crate::http) async fn terminate(
                 state.status
             );
         }
-        state.terminate_flush_lsn
     })
     .await
     .unwrap();
+
     info!("terminated Postgres");
-    JsonResponse::success(StatusCode::OK, TerminateResponse { lsn })
+
+    StatusCode::OK.into_response()
 }

compute_tools/src/lib.rs

@@ -22,7 +22,6 @@ mod migration;
 pub mod monitor;
 pub mod params;
 pub mod pg_helpers;
-pub mod pgbouncer;
 pub mod rsyslog;
 pub mod spec;
 mod spec_apply;

compute_tools/src/monitor.rs

@@ -13,12 +13,6 @@ use crate::metrics::{PG_CURR_DOWNTIME_MS, PG_TOTAL_DOWNTIME_MS};
 
 const MONITOR_CHECK_INTERVAL: Duration = Duration::from_millis(500);
 
-/// Struct to store runtime state of the compute monitor thread.
-/// In theory, this could be a part of `Compute`, but i)
-/// this state is expected to be accessed only by single thread,
-/// so we don't need to care about locking; ii) `Compute` is
-/// already quite big. Thus, it seems to be a good idea to keep
-/// all the activity/health monitoring parts here.
 struct ComputeMonitor {
     compute: Arc<ComputeNode>,
 
@@ -76,38 +70,12 @@ impl ComputeMonitor {
         )
     }
 
-    /// Check if compute is in some terminal or soon-to-be-terminal
-    /// state, then return `true`, signalling the caller that it
-    /// should exit gracefully. Otherwise, return `false`.
-    fn check_interrupts(&mut self) -> bool {
-        let compute_status = self.compute.get_status();
-        if matches!(
-            compute_status,
-            ComputeStatus::Terminated
-                | ComputeStatus::TerminationPending { .. }
-                | ComputeStatus::Failed
-        ) {
-            info!(
-                "compute is in {} status, stopping compute monitor",
-                compute_status
-            );
-            return true;
-        }
-
-        false
-    }
-
     /// Spin in a loop and figure out the last activity time in the Postgres.
-    /// Then update it in the shared state. This function currently never
-    /// errors out explicitly, but there is a graceful termination path.
-    /// Every time we receive an error trying to check Postgres, we use
-    /// [`ComputeMonitor::check_interrupts()`] because it could be that
-    /// compute is being terminated already, then we can exit gracefully
-    /// to not produce errors' noise in the log.
+    /// Then update it in the shared state. This function never errors out.
     /// NB: the only expected panic is at `Mutex` unwrap(), all other errors
     /// should be handled gracefully.
     #[instrument(skip_all)]
-    pub fn run(&mut self) -> anyhow::Result<()> {
+    pub fn run(&mut self) {
         // Suppose that `connstr` doesn't change
         let connstr = self.compute.params.connstr.clone();
         let conf = self
@@ -125,10 +93,6 @@ impl ComputeMonitor {
         info!("starting compute monitor for {}", connstr);
 
         loop {
-            if self.check_interrupts() {
-                break;
-            }
-
             match &mut client {
                 Ok(cli) => {
                     if cli.is_closed() {
@@ -136,10 +100,6 @@ impl ComputeMonitor {
                             downtime_info = self.downtime_info(),
                             "connection to Postgres is closed, trying to reconnect"
                         );
-                        if self.check_interrupts() {
-                            break;
-                        }
-
                         self.report_down();
 
                         // Connection is closed, reconnect and try again.
@@ -151,19 +111,15 @@ impl ComputeMonitor {
                                 self.compute.update_last_active(self.last_active);
                             }
                             Err(e) => {
-                                error!(
-                                    downtime_info = self.downtime_info(),
-                                    "could not check Postgres: {}", e
-                                );
-                                if self.check_interrupts() {
-                                    break;
-                                }
-
                                 // Although we have many places where we can return errors in `check()`,
                                 // normally it shouldn't happen. I.e., we will likely return error if
                                 // connection got broken, query timed out, Postgres returned invalid data, etc.
                                 // In all such cases it's suspicious, so let's report this as downtime.
                                 self.report_down();
+                                error!(
+                                    downtime_info = self.downtime_info(),
+                                    "could not check Postgres: {}", e
+                                );
 
                                 // Reconnect to Postgres just in case. During tests, I noticed
                                 // that queries in `check()` can fail with `connection closed`,
@@ -180,10 +136,6 @@ impl ComputeMonitor {
                         downtime_info = self.downtime_info(),
                         "could not connect to Postgres: {}, retrying", e
                     );
-                    if self.check_interrupts() {
-                        break;
-                    }
-
                     self.report_down();
 
                     // Establish a new connection and try again.
@@ -195,9 +147,6 @@ impl ComputeMonitor {
             self.last_checked = Utc::now();
             thread::sleep(MONITOR_CHECK_INTERVAL);
         }
-
-        // Graceful termination path
-        Ok(())
     }
 
     #[instrument(skip_all)]
@@ -480,10 +429,7 @@ pub fn launch_monitor(compute: &Arc<ComputeNode>) -> thread::JoinHandle<()> {
         .spawn(move || {
             let span = span!(Level::INFO, "compute_monitor");
             let _enter = span.enter();
-            match monitor.run() {
-                Ok(_) => info!("compute monitor thread terminated gracefully"),
-                Err(err) => error!("compute monitor thread terminated abnormally {:?}", err),
-            }
+            monitor.run();
         })
         .expect("cannot launch compute monitor thread")
 }

compute_tools/src/pg_helpers.rs

@@ -213,10 +213,8 @@ impl Escaping for PgIdent {
 
         // Find the first suitable tag that is not present in the string.
         // Postgres' max role/DB name length is 63 bytes, so even in the
-        // worst case it won't take long. Outer tag is always `tag + "x"`,
-        // so if `tag` is not present in the string, `outer_tag` is not
-        // present in the string either.
-        while self.contains(&tag.to_string()) {
+        // worst case it won't take long.
+        while self.contains(&format!("${tag}$")) || self.contains(&format!("${outer_tag}$")) {
             tag += "x";
             outer_tag = tag.clone() + "x";
         }

compute_tools/src/pgbouncer.rs

@@ -1 +0,0 @@
-pub const PGBOUNCER_PIDFILE: &str = "/tmp/pgbouncer.pid";

compute_tools/src/rsyslog.rs

@@ -27,40 +27,6 @@ fn get_rsyslog_pid() -> Option<String> {
     }
 }
 
-fn wait_for_rsyslog_pid() -> Result<String, anyhow::Error> {
-    const MAX_WAIT: Duration = Duration::from_secs(5);
-    const INITIAL_SLEEP: Duration = Duration::from_millis(2);
-
-    let mut sleep_duration = INITIAL_SLEEP;
-    let start = std::time::Instant::now();
-    let mut attempts = 1;
-
-    for attempt in 1.. {
-        attempts = attempt;
-        match get_rsyslog_pid() {
-            Some(pid) => return Ok(pid),
-            None => {
-                if start.elapsed() >= MAX_WAIT {
-                    break;
-                }
-                info!(
-                    "rsyslogd is not running, attempt {}. Sleeping for {} ms",
-                    attempt,
-                    sleep_duration.as_millis()
-                );
-                std::thread::sleep(sleep_duration);
-                sleep_duration *= 2;
-            }
-        }
-    }
-
-    Err(anyhow::anyhow!(
-        "rsyslogd is not running after waiting for {} seconds and {} attempts",
-        attempts,
-        start.elapsed().as_secs()
-    ))
-}
-
 // Restart rsyslogd to apply the new configuration.
 // This is necessary, because there is no other way to reload the rsyslog configuration.
 //
@@ -70,29 +36,27 @@ fn wait_for_rsyslog_pid() -> Result<String, anyhow::Error> {
 // TODO: test it properly
 //
 fn restart_rsyslog() -> Result<()> {
+    let old_pid = get_rsyslog_pid().context("rsyslogd is not running")?;
+    info!("rsyslogd is running with pid: {}, restart it", old_pid);
+
     // kill it to restart
     let _ = Command::new("pkill")
         .arg("rsyslogd")
         .output()
-        .context("Failed to restart rsyslogd")?;
-
-    // ensure rsyslogd is running
-    wait_for_rsyslog_pid()?;
+        .context("Failed to stop rsyslogd")?;
 
     Ok(())
 }
 
 pub fn configure_audit_rsyslog(
     log_directory: String,
-    endpoint_id: &str,
-    project_id: &str,
+    tag: Option<String>,
     remote_endpoint: &str,
 ) -> Result<()> {
     let config_content: String = format!(
         include_str!("config_template/compute_audit_rsyslog_template.conf"),
         log_directory = log_directory,
-        endpoint_id = endpoint_id,
-        project_id = project_id,
+        tag = tag.unwrap_or("".to_string()),
         remote_endpoint = remote_endpoint
     );
 
@@ -167,11 +131,15 @@ pub fn configure_postgres_logs_export(conf: PostgresLogsRsyslogConfig) -> Result
         return Ok(());
     }
 
-    // Nothing to configure
+    // When new config is empty we can simply remove the configuration file.
     if new_config.is_empty() {
-        // When the configuration is removed, PostgreSQL will stop sending data
-        // to the files watched by rsyslog, so restarting rsyslog is more effort
-        // than just ignoring this change.
+        info!("removing rsyslog config file: {}", POSTGRES_LOGS_CONF_PATH);
+        match std::fs::remove_file(POSTGRES_LOGS_CONF_PATH) {
+            Ok(_) => {}
+            Err(err) if err.kind() == ErrorKind::NotFound => {}
+            Err(err) => return Err(err.into()),
+        }
+        restart_rsyslog()?;
         return Ok(());
     }
 

compute_tools/tests/README.md

@@ -1,6 +0,0 @@
-### Test files
-
-The file `cluster_spec.json` has been copied over from libs/compute_api
-tests, with some edits:
-
-  - the neon.safekeepers setting contains a duplicate value

compute_tools/tests/cluster_spec.json

@@ -1,245 +0,0 @@
-{
-  "format_version": 1.0,
-
-  "timestamp": "2021-05-23T18:25:43.511Z",
-  "operation_uuid": "0f657b36-4b0f-4a2d-9c2e-1dcd615e7d8b",
-
-  "cluster": {
-    "cluster_id": "test-cluster-42",
-    "name": "Zenith Test",
-    "state": "restarted",
-    "roles": [
-      {
-        "name": "postgres",
-        "encrypted_password": "6b1d16b78004bbd51fa06af9eda75972",
-        "options": null
-      },
-      {
-        "name": "alexk",
-        "encrypted_password": null,
-        "options": null
-      },
-      {
-        "name": "zenith \"new\"",
-        "encrypted_password": "5b1d16b78004bbd51fa06af9eda75972",
-        "options": null
-      },
-      {
-        "name": "zen",
-        "encrypted_password": "9b1d16b78004bbd51fa06af9eda75972"
-      },
-      {
-        "name": "\"name\";\\n select 1;",
-        "encrypted_password": "5b1d16b78004bbd51fa06af9eda75972"
-      },
-      {
-        "name": "MyRole",
-        "encrypted_password": "5b1d16b78004bbd51fa06af9eda75972"
-      }
-    ],
-    "databases": [
-      {
-        "name": "DB2",
-        "owner": "alexk",
-        "options": [
-          {
-            "name": "LC_COLLATE",
-            "value": "C",
-            "vartype": "string"
-          },
-          {
-            "name": "LC_CTYPE",
-            "value": "C",
-            "vartype": "string"
-          },
-          {
-            "name": "TEMPLATE",
-            "value": "template0",
-            "vartype": "enum"
-          }
-        ]
-      },
-      {
-        "name": "zenith",
-        "owner": "MyRole"
-      },
-      {
-        "name": "zen",
-        "owner": "zen"
-      }
-    ],
-    "settings": [
-      {
-        "name": "fsync",
-        "value": "off",
-        "vartype": "bool"
-      },
-      {
-        "name": "wal_level",
-        "value": "logical",
-        "vartype": "enum"
-      },
-      {
-        "name": "hot_standby",
-        "value": "on",
-        "vartype": "bool"
-      },
-      {
-        "name": "prewarm_lfc_on_startup",
-        "value": "off",
-        "vartype": "bool"
-      },
-      {
-        "name": "neon.safekeepers",
-        "value": "127.0.0.1:6502,127.0.0.1:6503,127.0.0.1:6501,127.0.0.1:6502",
-        "vartype": "string"
-      },
-      {
-        "name": "wal_log_hints",
-        "value": "on",
-        "vartype": "bool"
-      },
-      {
-        "name": "log_connections",
-        "value": "on",
-        "vartype": "bool"
-      },
-      {
-        "name": "shared_buffers",
-        "value": "32768",
-        "vartype": "integer"
-      },
-      {
-        "name": "port",
-        "value": "55432",
-        "vartype": "integer"
-      },
-      {
-        "name": "max_connections",
-        "value": "100",
-        "vartype": "integer"
-      },
-      {
-        "name": "max_wal_senders",
-        "value": "10",
-        "vartype": "integer"
-      },
-      {
-        "name": "listen_addresses",
-        "value": "0.0.0.0",
-        "vartype": "string"
-      },
-      {
-        "name": "wal_sender_timeout",
-        "value": "0",
-        "vartype": "integer"
-      },
-      {
-        "name": "password_encryption",
-        "value": "md5",
-        "vartype": "enum"
-      },
-      {
-        "name": "maintenance_work_mem",
-        "value": "65536",
-        "vartype": "integer"
-      },
-      {
-        "name": "max_parallel_workers",
-        "value": "8",
-        "vartype": "integer"
-      },
-      {
-        "name": "max_worker_processes",
-        "value": "8",
-        "vartype": "integer"
-      },
-      {
-        "name": "neon.tenant_id",
-        "value": "b0554b632bd4d547a63b86c3630317e8",
-        "vartype": "string"
-      },
-      {
-        "name": "max_replication_slots",
-        "value": "10",
-        "vartype": "integer"
-      },
-      {
-        "name": "neon.timeline_id",
-        "value": "2414a61ffc94e428f14b5758fe308e13",
-        "vartype": "string"
-      },
-      {
-        "name": "shared_preload_libraries",
-        "value": "neon",
-        "vartype": "string"
-      },
-      {
-        "name": "synchronous_standby_names",
-        "value": "walproposer",
-        "vartype": "string"
-      },
-      {
-        "name": "neon.pageserver_connstring",
-        "value": "host=127.0.0.1 port=6400",
-        "vartype": "string"
-      },
-      {
-        "name": "test.escaping",
-        "value": "here's a backslash \\ and a quote ' and a double-quote \" hooray",
-        "vartype": "string"
-      }
-    ]
-  },
-  "delta_operations": [
-    {
-      "action": "delete_db",
-      "name": "zenith_test"
-    },
-    {
-      "action": "rename_db",
-      "name": "DB",
-      "new_name": "DB2"
-    },
-    {
-      "action": "delete_role",
-      "name": "zenith2"
-    },
-    {
-      "action": "rename_role",
-      "name": "zenith new",
-      "new_name": "zenith \"new\""
-    }
-  ],
-  "remote_extensions": {
-    "library_index": {
-      "postgis-3": "postgis",
-      "libpgrouting-3.4": "postgis",
-      "postgis_raster-3": "postgis",
-      "postgis_sfcgal-3": "postgis",
-      "postgis_topology-3": "postgis",
-      "address_standardizer-3": "postgis"
-    },
-    "extension_data": {
-      "postgis": {
-        "archive_path": "5834329303/v15/extensions/postgis.tar.zst",
-        "control_data": {
-          "postgis.control": "# postgis extension\ncomment = ''PostGIS geometry and geography spatial types and functions''\ndefault_version = ''3.3.2''\nmodule_pathname = ''$libdir/postgis-3''\nrelocatable = false\ntrusted = true\n",
-          "pgrouting.control": "# pgRouting Extension\ncomment = ''pgRouting Extension''\ndefault_version = ''3.4.2''\nmodule_pathname = ''$libdir/libpgrouting-3.4''\nrelocatable = true\nrequires = ''plpgsql''\nrequires = ''postgis''\ntrusted = true\n",
-          "postgis_raster.control": "# postgis_raster extension\ncomment = ''PostGIS raster types and functions''\ndefault_version = ''3.3.2''\nmodule_pathname = ''$libdir/postgis_raster-3''\nrelocatable = false\nrequires = postgis\ntrusted = true\n",
-          "postgis_sfcgal.control": "# postgis topology extension\ncomment = ''PostGIS SFCGAL functions''\ndefault_version = ''3.3.2''\nrelocatable = true\nrequires = postgis\ntrusted = true\n",
-          "postgis_topology.control": "# postgis topology extension\ncomment = ''PostGIS topology spatial types and functions''\ndefault_version = ''3.3.2''\nrelocatable = false\nschema = topology\nrequires = postgis\ntrusted = true\n",
-          "address_standardizer.control": "# address_standardizer extension\ncomment = ''Used to parse an address into constituent elements. Generally used to support geocoding address normalization step.''\ndefault_version = ''3.3.2''\nrelocatable = true\ntrusted = true\n",
-          "postgis_tiger_geocoder.control": "# postgis tiger geocoder extension\ncomment = ''PostGIS tiger geocoder and reverse geocoder''\ndefault_version = ''3.3.2''\nrelocatable = false\nschema = tiger\nrequires = ''postgis,fuzzystrmatch''\nsuperuser= false\ntrusted = true\n",
-          "address_standardizer_data_us.control": "# address standardizer us dataset\ncomment = ''Address Standardizer US dataset example''\ndefault_version = ''3.3.2''\nrelocatable = true\ntrusted = true\n"
-        }
-      }
-    },
-    "custom_extensions": [],
-    "public_extensions": ["postgis"]
-  },
-  "pgbouncer_settings": {
-    "default_pool_size": "42",
-    "pool_mode": "session"
-  }
-}

compute_tools/tests/pg_helpers_tests.rs

@@ -30,7 +30,7 @@ mod pg_helpers_tests {
             r#"fsync = off
 wal_level = logical
 hot_standby = on
-autoprewarm = off
+prewarm_lfc_on_startup = off
 neon.safekeepers = '127.0.0.1:6502,127.0.0.1:6503,127.0.0.1:6501'
 wal_log_hints = on
 log_connections = on
@@ -71,14 +71,6 @@ test.escaping = 'here''s a backslash \\ and a quote '' and a double-quote " hoor
             ("name$$$", ("$x$name$$$$x$", "xx")),
             ("name$$$$", ("$x$name$$$$$x$", "xx")),
             ("name$x$", ("$xx$name$x$$xx$", "xxx")),
-            ("x", ("$xx$x$xx$", "xxx")),
-            ("xx", ("$xxx$xx$xxx$", "xxxx")),
-            ("$x", ("$xx$$x$xx$", "xxx")),
-            ("x$", ("$xx$x$$xx$", "xxx")),
-            ("$x$", ("$xx$$x$$xx$", "xxx")),
-            ("xx$", ("$xxx$xx$$xxx$", "xxxx")),
-            ("$xx", ("$xxx$$xx$xxx$", "xxxx")),
-            ("$xx$", ("$xxx$$xx$$xxx$", "xxxx")),
         ];
 
         for (input, expected) in test_cases {

control_plane/Cargo.toml

@@ -36,7 +36,6 @@ pageserver_api.workspace = true
 pageserver_client.workspace = true
 postgres_backend.workspace = true
 safekeeper_api.workspace = true
-safekeeper_client.workspace = true
 postgres_connection.workspace = true
 storage_broker.workspace = true
 http-utils.workspace = true

control_plane/safekeepers.conf

@@ -2,10 +2,8 @@
 [pageserver]
 listen_pg_addr = '127.0.0.1:64000'
 listen_http_addr = '127.0.0.1:9898'
-listen_grpc_addr = '127.0.0.1:51051'
 pg_auth_type = 'Trust'
 http_auth_type = 'Trust'
-grpc_auth_type = 'Trust'
 
 [[safekeepers]]
 id = 1

control_plane/simple.conf

@@ -4,10 +4,8 @@
 id=1
 listen_pg_addr = '127.0.0.1:64000'
 listen_http_addr = '127.0.0.1:9898'
-listen_grpc_addr = '127.0.0.1:51051'
 pg_auth_type = 'Trust'
 http_auth_type = 'Trust'
-grpc_auth_type = 'Trust'
 
 [[safekeepers]]
 id = 1

control_plane/src/background_process.rs

@@ -14,7 +14,7 @@
 
 use std::ffi::OsStr;
 use std::io::Write;
-use std::os::fd::AsFd;
+use std::os::unix::prelude::AsRawFd;
 use std::os::unix::process::CommandExt;
 use std::path::Path;
 use std::process::Command;
@@ -356,7 +356,7 @@ where
             let file = pid_file::claim_for_current_process(&path).expect("claim pid file");
             // Remove the FD_CLOEXEC flag on the pidfile descriptor so that the pidfile
             // remains locked after exec.
-            nix::fcntl::fcntl(file.as_fd(), FcntlArg::F_SETFD(FdFlag::empty()))
+            nix::fcntl::fcntl(file.as_raw_fd(), FcntlArg::F_SETFD(FdFlag::empty()))
                 .expect("remove FD_CLOEXEC");
             // Don't run drop(file), it would close the file before we actually exec.
             std::mem::forget(file);

control_plane/src/bin/neon_local.rs

@@ -8,6 +8,7 @@
 use std::borrow::Cow;
 use std::collections::{BTreeSet, HashMap};
 use std::fs::File;
+use std::os::fd::AsRawFd;
 use std::path::PathBuf;
 use std::process::exit;
 use std::str::FromStr;
@@ -18,7 +19,7 @@ use clap::Parser;
 use compute_api::requests::ComputeClaimsScope;
 use compute_api::spec::ComputeMode;
 use control_plane::broker::StorageBroker;
-use control_plane::endpoint::{ComputeControlPlane, EndpointTerminateMode, PageserverProtocol};
+use control_plane::endpoint::ComputeControlPlane;
 use control_plane::endpoint_storage::{ENDPOINT_STORAGE_DEFAULT_ADDR, EndpointStorage};
 use control_plane::local_env;
 use control_plane::local_env::{
@@ -30,9 +31,8 @@ use control_plane::safekeeper::SafekeeperNode;
 use control_plane::storage_controller::{
     NeonStorageControllerStartArgs, NeonStorageControllerStopArgs, StorageController,
 };
-use nix::fcntl::{Flock, FlockArg};
+use nix::fcntl::{FlockArg, flock};
 use pageserver_api::config::{
-    DEFAULT_GRPC_LISTEN_PORT as DEFAULT_PAGESERVER_GRPC_PORT,
     DEFAULT_HTTP_LISTEN_PORT as DEFAULT_PAGESERVER_HTTP_PORT,
     DEFAULT_PG_LISTEN_PORT as DEFAULT_PAGESERVER_PG_PORT,
 };
@@ -45,7 +45,7 @@ use pageserver_api::models::{
 use pageserver_api::shard::{DEFAULT_STRIPE_SIZE, ShardCount, ShardStripeSize, TenantShardId};
 use postgres_backend::AuthType;
 use postgres_connection::parse_host_port;
-use safekeeper_api::membership::{SafekeeperGeneration, SafekeeperId};
+use safekeeper_api::membership::SafekeeperGeneration;
 use safekeeper_api::{
     DEFAULT_HTTP_LISTEN_PORT as DEFAULT_SAFEKEEPER_HTTP_PORT,
     DEFAULT_PG_LISTEN_PORT as DEFAULT_SAFEKEEPER_PG_PORT,
@@ -605,14 +605,6 @@ struct EndpointCreateCmdArgs {
     #[clap(long, help = "Postgres version")]
     pg_version: u32,
 
-    /// Use gRPC to communicate with Pageservers, by generating grpc:// connstrings.
-    ///
-    /// Specified on creation such that it's retained across reconfiguration and restarts.
-    ///
-    /// NB: not yet supported by computes.
-    #[clap(long)]
-    grpc: bool,
-
     #[clap(
         long,
         help = "If set, the node will be a hot replica on the specified timeline",
@@ -672,13 +664,6 @@ struct EndpointStartCmdArgs {
     #[clap(short = 't', long, value_parser= humantime::parse_duration, help = "timeout until we fail the command")]
     #[arg(default_value = "90s")]
     start_timeout: Duration,
-
-    #[clap(
-        long,
-        help = "Run in development mode, skipping VM-specific operations like process termination",
-        action = clap::ArgAction::SetTrue
-    )]
-    dev: bool,
 }
 
 #[derive(clap::Args)]
@@ -711,9 +696,10 @@ struct EndpointStopCmdArgs {
     )]
     destroy: bool,
 
-    #[clap(long, help = "Postgres shutdown mode")]
-    #[clap(default_value = "fast")]
-    mode: EndpointTerminateMode,
+    #[clap(long, help = "Postgres shutdown mode, passed to \"pg_ctl -m <mode>\"")]
+    #[arg(value_parser(["smart", "fast", "immediate"]))]
+    #[arg(default_value = "fast")]
+    mode: String,
 }
 
 #[derive(clap::Args)]
@@ -763,16 +749,16 @@ struct TimelineTreeEl {
 
 /// A flock-based guard over the neon_local repository directory
 struct RepoLock {
-    _file: Flock<File>,
+    _file: File,
 }
 
 impl RepoLock {
     fn new() -> Result<Self> {
         let repo_dir = File::open(local_env::base_path())?;
-        match Flock::lock(repo_dir, FlockArg::LockExclusive) {
-            Ok(f) => Ok(Self { _file: f }),
-            Err((_, e)) => Err(e).context("flock error"),
-        }
+        let repo_dir_fd = repo_dir.as_raw_fd();
+        flock(repo_dir_fd, FlockArg::LockExclusive)?;
+
+        Ok(Self { _file: repo_dir })
     }
 }
 
@@ -1022,16 +1008,13 @@ fn handle_init(args: &InitCmdArgs) -> anyhow::Result<LocalEnv> {
                     let pageserver_id = NodeId(DEFAULT_PAGESERVER_ID.0 + i as u64);
                     let pg_port = DEFAULT_PAGESERVER_PG_PORT + i;
                     let http_port = DEFAULT_PAGESERVER_HTTP_PORT + i;
-                    let grpc_port = DEFAULT_PAGESERVER_GRPC_PORT + i;
                     NeonLocalInitPageserverConf {
                         id: pageserver_id,
                         listen_pg_addr: format!("127.0.0.1:{pg_port}"),
                         listen_http_addr: format!("127.0.0.1:{http_port}"),
                         listen_https_addr: None,
-                        listen_grpc_addr: Some(format!("127.0.0.1:{grpc_port}")),
                         pg_auth_type: AuthType::Trust,
                         http_auth_type: AuthType::Trust,
-                        grpc_auth_type: AuthType::Trust,
                         other: Default::default(),
                         // Typical developer machines use disks with slow fsync, and we don't care
                         // about data integrity: disable disk syncs.
@@ -1269,45 +1252,6 @@ async fn handle_timeline(cmd: &TimelineCmd, env: &mut local_env::LocalEnv) -> Re
             pageserver
                 .timeline_import(tenant_id, timeline_id, base, pg_wal, args.pg_version)
                 .await?;
-            if env.storage_controller.timelines_onto_safekeepers {
-                println!("Creating timeline on safekeeper ...");
-                let timeline_info = pageserver
-                    .timeline_info(
-                        TenantShardId::unsharded(tenant_id),
-                        timeline_id,
-                        pageserver_client::mgmt_api::ForceAwaitLogicalSize::No,
-                    )
-                    .await?;
-                let default_sk = SafekeeperNode::from_env(env, env.safekeepers.first().unwrap());
-                let default_host = default_sk
-                    .conf
-                    .listen_addr
-                    .clone()
-                    .unwrap_or_else(|| "localhost".to_string());
-                let mconf = safekeeper_api::membership::Configuration {
-                    generation: SafekeeperGeneration::new(1),
-                    members: safekeeper_api::membership::MemberSet {
-                        m: vec![SafekeeperId {
-                            host: default_host,
-                            id: default_sk.conf.id,
-                            pg_port: default_sk.conf.pg_port,
-                        }],
-                    },
-                    new_members: None,
-                };
-                let pg_version = args.pg_version * 10000;
-                let req = safekeeper_api::models::TimelineCreateRequest {
-                    tenant_id,
-                    timeline_id,
-                    mconf,
-                    pg_version,
-                    system_id: None,
-                    wal_seg_size: None,
-                    start_lsn: timeline_info.last_record_lsn,
-                    commit_lsn: None,
-                };
-                default_sk.create_timeline(&req).await?;
-            }
             env.register_branch_mapping(branch_name.to_string(), tenant_id, timeline_id)?;
             println!("Done");
         }
@@ -1332,7 +1276,6 @@ async fn handle_timeline(cmd: &TimelineCmd, env: &mut local_env::LocalEnv) -> Re
                 mode: pageserver_api::models::TimelineCreateRequestMode::Branch {
                     ancestor_timeline_id,
                     ancestor_start_lsn: start_lsn,
-                    read_only: false,
                     pg_version: None,
                 },
             };
@@ -1465,7 +1408,6 @@ async fn handle_endpoint(subcmd: &EndpointCmd, env: &local_env::LocalEnv) -> Res
                 args.internal_http_port,
                 args.pg_version,
                 mode,
-                args.grpc,
                 !args.update_catalog,
                 false,
             )?;
@@ -1506,20 +1448,13 @@ async fn handle_endpoint(subcmd: &EndpointCmd, env: &local_env::LocalEnv) -> Res
 
             let (pageservers, stripe_size) = if let Some(pageserver_id) = pageserver_id {
                 let conf = env.get_pageserver_conf(pageserver_id).unwrap();
-                // Use gRPC if requested.
-                let pageserver = if endpoint.grpc {
-                    let grpc_addr = conf.listen_grpc_addr.as_ref().expect("bad config");
-                    let (host, port) = parse_host_port(grpc_addr)?;
-                    let port = port.unwrap_or(DEFAULT_PAGESERVER_GRPC_PORT);
-                    (PageserverProtocol::Grpc, host, port)
-                } else {
-                    let (host, port) = parse_host_port(&conf.listen_pg_addr)?;
-                    let port = port.unwrap_or(5432);
-                    (PageserverProtocol::Libpq, host, port)
-                };
-                // If caller is telling us what pageserver to use, this is not a tenant which is
-                // fully managed by storage controller, therefore not sharded.
-                (vec![pageserver], DEFAULT_STRIPE_SIZE)
+                let parsed = parse_host_port(&conf.listen_pg_addr).expect("Bad config");
+                (
+                    vec![(parsed.0, parsed.1.unwrap_or(5432))],
+                    // If caller is telling us what pageserver to use, this is not a tenant which is
+                    // full managed by storage controller, therefore not sharded.
+                    DEFAULT_STRIPE_SIZE,
+                )
             } else {
                 // Look up the currently attached location of the tenant, and its striping metadata,
                 // to pass these on to postgres.
@@ -1538,20 +1473,11 @@ async fn handle_endpoint(subcmd: &EndpointCmd, env: &local_env::LocalEnv) -> Res
                                 .await?;
                         }
 
-                        let pageserver = if endpoint.grpc {
-                            (
-                                PageserverProtocol::Grpc,
-                                Host::parse(&shard.listen_grpc_addr.expect("no gRPC address"))?,
-                                shard.listen_grpc_port.expect("no gRPC port"),
-                            )
-                        } else {
-                            (
-                                PageserverProtocol::Libpq,
-                                Host::parse(&shard.listen_pg_addr)?,
-                                shard.listen_pg_port,
-                            )
-                        };
-                        anyhow::Ok(pageserver)
+                        anyhow::Ok((
+                            Host::parse(&shard.listen_pg_addr)
+                                .expect("Storage controller reported bad hostname"),
+                            shard.listen_pg_port,
+                        ))
                     }),
                 )
                 .await?;
@@ -1596,7 +1522,6 @@ async fn handle_endpoint(subcmd: &EndpointCmd, env: &local_env::LocalEnv) -> Res
                     stripe_size.0 as usize,
                     args.create_test_user,
                     args.start_timeout,
-                    args.dev,
                 )
                 .await?;
         }
@@ -1607,19 +1532,11 @@ async fn handle_endpoint(subcmd: &EndpointCmd, env: &local_env::LocalEnv) -> Res
                 .get(endpoint_id.as_str())
                 .with_context(|| format!("postgres endpoint {endpoint_id} is not found"))?;
             let pageservers = if let Some(ps_id) = args.endpoint_pageserver_id {
-                let conf = env.get_pageserver_conf(ps_id)?;
-                // Use gRPC if requested.
-                let pageserver = if endpoint.grpc {
-                    let grpc_addr = conf.listen_grpc_addr.as_ref().expect("bad config");
-                    let (host, port) = parse_host_port(grpc_addr)?;
-                    let port = port.unwrap_or(DEFAULT_PAGESERVER_GRPC_PORT);
-                    (PageserverProtocol::Grpc, host, port)
-                } else {
-                    let (host, port) = parse_host_port(&conf.listen_pg_addr)?;
-                    let port = port.unwrap_or(5432);
-                    (PageserverProtocol::Libpq, host, port)
-                };
-                vec![pageserver]
+                let pageserver = PageServerNode::from_env(env, env.get_pageserver_conf(ps_id)?);
+                vec![(
+                    pageserver.pg_connection_config.host().clone(),
+                    pageserver.pg_connection_config.port(),
+                )]
             } else {
                 let storage_controller = StorageController::from_env(env);
                 storage_controller
@@ -1628,21 +1545,11 @@ async fn handle_endpoint(subcmd: &EndpointCmd, env: &local_env::LocalEnv) -> Res
                     .shards
                     .into_iter()
                     .map(|shard| {
-                        // Use gRPC if requested.
-                        if endpoint.grpc {
-                            (
-                                PageserverProtocol::Grpc,
-                                Host::parse(&shard.listen_grpc_addr.expect("no gRPC address"))
-                                    .expect("bad hostname"),
-                                shard.listen_grpc_port.expect("no gRPC port"),
-                            )
-                        } else {
-                            (
-                                PageserverProtocol::Libpq,
-                                Host::parse(&shard.listen_pg_addr).expect("bad hostname"),
-                                shard.listen_pg_port,
-                            )
-                        }
+                        (
+                            Host::parse(&shard.listen_pg_addr)
+                                .expect("Storage controller reported malformed host"),
+                            shard.listen_pg_port,
+                        )
                     })
                     .collect::<Vec<_>>()
             };
@@ -1657,10 +1564,7 @@ async fn handle_endpoint(subcmd: &EndpointCmd, env: &local_env::LocalEnv) -> Res
                 .endpoints
                 .get(endpoint_id)
                 .with_context(|| format!("postgres endpoint {endpoint_id} is not found"))?;
-            match endpoint.stop(args.mode, args.destroy).await?.lsn {
-                Some(lsn) => println!("{lsn}"),
-                None => println!("null"),
-            }
+            endpoint.stop(&args.mode, args.destroy)?;
         }
         EndpointCmd::GenerateJwt(args) => {
             let endpoint = {
@@ -2092,16 +1996,11 @@ async fn handle_stop_all(args: &StopCmdArgs, env: &local_env::LocalEnv) -> Resul
 }
 
 async fn try_stop_all(env: &local_env::LocalEnv, immediate: bool) {
-    let mode = if immediate {
-        EndpointTerminateMode::Immediate
-    } else {
-        EndpointTerminateMode::Fast
-    };
     // Stop all endpoints
     match ComputeControlPlane::load(env.clone()) {
         Ok(cplane) => {
             for (_k, node) in cplane.endpoints {
-                if let Err(e) = node.stop(mode, false).await {
+                if let Err(e) = node.stop(if immediate { "immediate" } else { "fast" }, false) {
                     eprintln!("postgres stop failed: {e:#}");
                 }
             }

control_plane/src/endpoint.rs

@@ -37,7 +37,6 @@
 //! ```
 //!
 use std::collections::BTreeMap;
-use std::fmt::Display;
 use std::net::{IpAddr, Ipv4Addr, SocketAddr, TcpStream};
 use std::path::PathBuf;
 use std::process::Command;
@@ -46,14 +45,11 @@ use std::sync::Arc;
 use std::time::{Duration, Instant};
 
 use anyhow::{Context, Result, anyhow, bail};
-use base64::Engine;
-use base64::prelude::BASE64_URL_SAFE_NO_PAD;
 use compute_api::requests::{
     COMPUTE_AUDIENCE, ComputeClaims, ComputeClaimsScope, ConfigurationRequest,
 };
 use compute_api::responses::{
-    ComputeConfig, ComputeCtlConfig, ComputeStatus, ComputeStatusResponse, TerminateResponse,
-    TlsConfig,
+    ComputeConfig, ComputeCtlConfig, ComputeStatus, ComputeStatusResponse, TlsConfig,
 };
 use compute_api::spec::{
     Cluster, ComputeAudit, ComputeFeature, ComputeMode, ComputeSpec, Database, PgIdent,
@@ -78,6 +74,7 @@ use utils::id::{NodeId, TenantId, TimelineId};
 
 use crate::local_env::LocalEnv;
 use crate::postgresql_conf::PostgresConf;
+use crate::storage_controller::StorageController;
 
 // contents of a endpoint.json file
 #[derive(Serialize, Deserialize, PartialEq, Eq, Clone, Debug)]
@@ -90,7 +87,6 @@ pub struct EndpointConf {
     external_http_port: u16,
     internal_http_port: u16,
     pg_version: u32,
-    grpc: bool,
     skip_pg_catalog_updates: bool,
     reconfigure_concurrency: usize,
     drop_subscriptions_before_start: bool,
@@ -168,7 +164,7 @@ impl ComputeControlPlane {
                     public_key_use: Some(PublicKeyUse::Signature),
                     key_operations: Some(vec![KeyOperations::Verify]),
                     key_algorithm: Some(KeyAlgorithm::EdDSA),
-                    key_id: Some(BASE64_URL_SAFE_NO_PAD.encode(key_hash)),
+                    key_id: Some(base64::encode_config(key_hash, base64::URL_SAFE_NO_PAD)),
                     x509_url: None::<String>,
                     x509_chain: None::<Vec<String>>,
                     x509_sha1_fingerprint: None::<String>,
@@ -177,7 +173,7 @@ impl ComputeControlPlane {
                 algorithm: AlgorithmParameters::OctetKeyPair(OctetKeyPairParameters {
                     key_type: OctetKeyPairType::OctetKeyPair,
                     curve: EllipticCurve::Ed25519,
-                    x: BASE64_URL_SAFE_NO_PAD.encode(public_key),
+                    x: base64::encode_config(public_key, base64::URL_SAFE_NO_PAD),
                 }),
             }],
         })
@@ -194,7 +190,6 @@ impl ComputeControlPlane {
         internal_http_port: Option<u16>,
         pg_version: u32,
         mode: ComputeMode,
-        grpc: bool,
         skip_pg_catalog_updates: bool,
         drop_subscriptions_before_start: bool,
     ) -> Result<Arc<Endpoint>> {
@@ -229,7 +224,6 @@ impl ComputeControlPlane {
             // we also skip catalog updates in the cloud.
             skip_pg_catalog_updates,
             drop_subscriptions_before_start,
-            grpc,
             reconfigure_concurrency: 1,
             features: vec![],
             cluster: None,
@@ -248,7 +242,6 @@ impl ComputeControlPlane {
                 internal_http_port,
                 pg_port,
                 pg_version,
-                grpc,
                 skip_pg_catalog_updates,
                 drop_subscriptions_before_start,
                 reconfigure_concurrency: 1,
@@ -303,8 +296,6 @@ pub struct Endpoint {
     pub tenant_id: TenantId,
     pub timeline_id: TimelineId,
     pub mode: ComputeMode,
-    /// If true, the endpoint should use gRPC to communicate with Pageservers.
-    pub grpc: bool,
 
     // port and address of the Postgres server and `compute_ctl`'s HTTP APIs
     pub pg_address: SocketAddr,
@@ -340,58 +331,15 @@ pub enum EndpointStatus {
     RunningNoPidfile,
 }
 
-impl Display for EndpointStatus {
+impl std::fmt::Display for EndpointStatus {
     fn fmt(&self, writer: &mut std::fmt::Formatter) -> std::fmt::Result {
-        writer.write_str(match self {
+        let s = match self {
             Self::Running => "running",
             Self::Stopped => "stopped",
             Self::Crashed => "crashed",
             Self::RunningNoPidfile => "running, no pidfile",
-        })
-    }
-}
-
-#[derive(Default, Clone, Copy, clap::ValueEnum)]
-pub enum EndpointTerminateMode {
-    #[default]
-    /// Use pg_ctl stop -m fast
-    Fast,
-    /// Use pg_ctl stop -m immediate
-    Immediate,
-    /// Use /terminate?mode=immediate
-    ImmediateTerminate,
-}
-
-impl std::fmt::Display for EndpointTerminateMode {
-    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
-        f.write_str(match &self {
-            EndpointTerminateMode::Fast => "fast",
-            EndpointTerminateMode::Immediate => "immediate",
-            EndpointTerminateMode::ImmediateTerminate => "immediate-terminate",
-        })
-    }
-}
-
-/// Protocol used to connect to a Pageserver.
-#[derive(Clone, Copy, Debug)]
-pub enum PageserverProtocol {
-    Libpq,
-    Grpc,
-}
-
-impl PageserverProtocol {
-    /// Returns the URL scheme for the protocol, used in connstrings.
-    pub fn scheme(&self) -> &'static str {
-        match self {
-            Self::Libpq => "postgresql",
-            Self::Grpc => "grpc",
-        }
-    }
-}
-
-impl Display for PageserverProtocol {
-    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
-        f.write_str(self.scheme())
+        };
+        write!(writer, "{}", s)
     }
 }
 
@@ -430,7 +378,6 @@ impl Endpoint {
             mode: conf.mode,
             tenant_id: conf.tenant_id,
             pg_version: conf.pg_version,
-            grpc: conf.grpc,
             skip_pg_catalog_updates: conf.skip_pg_catalog_updates,
             reconfigure_concurrency: conf.reconfigure_concurrency,
             drop_subscriptions_before_start: conf.drop_subscriptions_before_start,
@@ -659,10 +606,10 @@ impl Endpoint {
         }
     }
 
-    fn build_pageserver_connstr(pageservers: &[(PageserverProtocol, Host, u16)]) -> String {
+    fn build_pageserver_connstr(pageservers: &[(Host, u16)]) -> String {
         pageservers
             .iter()
-            .map(|(scheme, host, port)| format!("{scheme}://no_user@{host}:{port}"))
+            .map(|(host, port)| format!("postgresql://no_user@{host}:{port}"))
             .collect::<Vec<_>>()
             .join(",")
     }
@@ -707,12 +654,11 @@ impl Endpoint {
         endpoint_storage_addr: String,
         safekeepers_generation: Option<SafekeeperGeneration>,
         safekeepers: Vec<NodeId>,
-        pageservers: Vec<(PageserverProtocol, Host, u16)>,
+        pageservers: Vec<(Host, u16)>,
         remote_ext_base_url: Option<&String>,
         shard_stripe_size: usize,
         create_test_user: bool,
         start_timeout: Duration,
-        dev: bool,
     ) -> Result<()> {
         if self.status() == EndpointStatus::Running {
             anyhow::bail!("The endpoint is already running");
@@ -801,7 +747,7 @@ impl Endpoint {
                 logs_export_host: None::<String>,
                 endpoint_storage_addr: Some(endpoint_storage_addr),
                 endpoint_storage_token: Some(endpoint_storage_token),
-                autoprewarm: false,
+                prewarm_lfc_on_startup: false,
             };
 
             // this strange code is needed to support respec() in tests
@@ -883,10 +829,6 @@ impl Endpoint {
             cmd.args(["--remote-ext-base-url", remote_ext_base_url]);
         }
 
-        if dev {
-            cmd.arg("--dev");
-        }
-
         let child = cmd.spawn()?;
         // set up a scopeguard to kill & wait for the child in case we panic or bail below
         let child = scopeguard::guard(child, |mut child| {
@@ -939,7 +881,7 @@ impl Endpoint {
                         ComputeStatus::Empty
                         | ComputeStatus::ConfigurationPending
                         | ComputeStatus::Configuration
-                        | ComputeStatus::TerminationPending { .. }
+                        | ComputeStatus::TerminationPending
                         | ComputeStatus::Terminated => {
                             bail!("unexpected compute status: {:?}", state.status)
                         }
@@ -997,12 +939,10 @@ impl Endpoint {
 
     pub async fn reconfigure(
         &self,
-        pageservers: Vec<(PageserverProtocol, Host, u16)>,
+        mut pageservers: Vec<(Host, u16)>,
         stripe_size: Option<ShardStripeSize>,
         safekeepers: Option<Vec<NodeId>>,
     ) -> Result<()> {
-        anyhow::ensure!(!pageservers.is_empty(), "no pageservers provided");
-
         let (mut spec, compute_ctl_config) = {
             let config_path = self.endpoint_path().join("config.json");
             let file = std::fs::File::open(config_path)?;
@@ -1014,7 +954,25 @@ impl Endpoint {
         let postgresql_conf = self.read_postgresql_conf()?;
         spec.cluster.postgresql_conf = Some(postgresql_conf);
 
+        // If we weren't given explicit pageservers, query the storage controller
+        if pageservers.is_empty() {
+            let storage_controller = StorageController::from_env(&self.env);
+            let locate_result = storage_controller.tenant_locate(self.tenant_id).await?;
+            pageservers = locate_result
+                .shards
+                .into_iter()
+                .map(|shard| {
+                    (
+                        Host::parse(&shard.listen_pg_addr)
+                            .expect("Storage controller reported bad hostname"),
+                        shard.listen_pg_port,
+                    )
+                })
+                .collect::<Vec<_>>();
+        }
+
         let pageserver_connstr = Self::build_pageserver_connstr(&pageservers);
+        assert!(!pageserver_connstr.is_empty());
         spec.pageserver_connstring = Some(pageserver_connstr);
         if stripe_size.is_some() {
             spec.shard_stripe_size = stripe_size.map(|s| s.0 as usize);
@@ -1061,27 +1019,8 @@ impl Endpoint {
         }
     }
 
-    pub async fn stop(
-        &self,
-        mode: EndpointTerminateMode,
-        destroy: bool,
-    ) -> Result<TerminateResponse> {
-        // pg_ctl stop is fast but doesn't allow us to collect LSN. /terminate is
-        // slow, and test runs time out. Solution: special mode "immediate-terminate"
-        // which uses /terminate
-        let response = if let EndpointTerminateMode::ImmediateTerminate = mode {
-            let ip = self.external_http_address.ip();
-            let port = self.external_http_address.port();
-            let url = format!("http://{ip}:{port}/terminate?mode=immediate");
-            let token = self.generate_jwt(Some(ComputeClaimsScope::Admin))?;
-            let request = reqwest::Client::new().post(url).bearer_auth(token);
-            let response = request.send().await.context("/terminate")?;
-            let text = response.text().await.context("/terminate result")?;
-            serde_json::from_str(&text).with_context(|| format!("deserializing {text}"))?
-        } else {
-            self.pg_ctl(&["-m", &mode.to_string(), "stop"], &None)?;
-            TerminateResponse { lsn: None }
-        };
+    pub fn stop(&self, mode: &str, destroy: bool) -> Result<()> {
+        self.pg_ctl(&["-m", mode, "stop"], &None)?;
 
         // Also wait for the compute_ctl process to die. It might have some
         // cleanup work to do after postgres stops, like syncing safekeepers,
@@ -1091,7 +1030,7 @@ impl Endpoint {
         // waiting. Sometimes we do *not* want this cleanup: tests intentionally
         // do stop when majority of safekeepers is down, so sync-safekeepers
         // would hang otherwise. This could be a separate flag though.
-        let send_sigterm = destroy || !matches!(mode, EndpointTerminateMode::Fast);
+        let send_sigterm = destroy || mode == "immediate";
         self.wait_for_compute_ctl_to_exit(send_sigterm)?;
         if destroy {
             println!(
@@ -1100,7 +1039,7 @@ impl Endpoint {
             );
             std::fs::remove_dir_all(self.endpoint_path())?;
         }
-        Ok(response)
+        Ok(())
     }
 
     pub fn connstr(&self, user: &str, db_name: &str) -> String {

control_plane/src/local_env.rs

@@ -209,10 +209,6 @@ pub struct NeonStorageControllerConf {
     pub use_https_safekeeper_api: bool,
 
     pub use_local_compute_notifications: bool,
-
-    pub timeline_safekeeper_count: Option<i64>,
-
-    pub kick_secondary_downloads: Option<bool>,
 }
 
 impl NeonStorageControllerConf {
@@ -240,11 +236,9 @@ impl Default for NeonStorageControllerConf {
             heartbeat_interval: Self::DEFAULT_HEARTBEAT_INTERVAL,
             long_reconcile_threshold: None,
             use_https_pageserver_api: false,
-            timelines_onto_safekeepers: true,
+            timelines_onto_safekeepers: false,
             use_https_safekeeper_api: false,
             use_local_compute_notifications: true,
-            timeline_safekeeper_count: None,
-            kick_secondary_downloads: None,
         }
     }
 }
@@ -284,10 +278,8 @@ pub struct PageServerConf {
     pub listen_pg_addr: String,
     pub listen_http_addr: String,
     pub listen_https_addr: Option<String>,
-    pub listen_grpc_addr: Option<String>,
     pub pg_auth_type: AuthType,
     pub http_auth_type: AuthType,
-    pub grpc_auth_type: AuthType,
     pub no_sync: bool,
 }
 
@@ -298,10 +290,8 @@ impl Default for PageServerConf {
             listen_pg_addr: String::new(),
             listen_http_addr: String::new(),
             listen_https_addr: None,
-            listen_grpc_addr: None,
             pg_auth_type: AuthType::Trust,
             http_auth_type: AuthType::Trust,
-            grpc_auth_type: AuthType::Trust,
             no_sync: false,
         }
     }
@@ -316,10 +306,8 @@ pub struct NeonLocalInitPageserverConf {
     pub listen_pg_addr: String,
     pub listen_http_addr: String,
     pub listen_https_addr: Option<String>,
-    pub listen_grpc_addr: Option<String>,
     pub pg_auth_type: AuthType,
     pub http_auth_type: AuthType,
-    pub grpc_auth_type: AuthType,
     #[serde(default, skip_serializing_if = "std::ops::Not::not")]
     pub no_sync: bool,
     #[serde(flatten)]
@@ -333,10 +321,8 @@ impl From<&NeonLocalInitPageserverConf> for PageServerConf {
             listen_pg_addr,
             listen_http_addr,
             listen_https_addr,
-            listen_grpc_addr,
             pg_auth_type,
             http_auth_type,
-            grpc_auth_type,
             no_sync,
             other: _,
         } = conf;
@@ -345,9 +331,7 @@ impl From<&NeonLocalInitPageserverConf> for PageServerConf {
             listen_pg_addr: listen_pg_addr.clone(),
             listen_http_addr: listen_http_addr.clone(),
             listen_https_addr: listen_https_addr.clone(),
-            listen_grpc_addr: listen_grpc_addr.clone(),
             pg_auth_type: *pg_auth_type,
-            grpc_auth_type: *grpc_auth_type,
             http_auth_type: *http_auth_type,
             no_sync: *no_sync,
         }
@@ -723,10 +707,8 @@ impl LocalEnv {
                     listen_pg_addr: String,
                     listen_http_addr: String,
                     listen_https_addr: Option<String>,
-                    listen_grpc_addr: Option<String>,
                     pg_auth_type: AuthType,
                     http_auth_type: AuthType,
-                    grpc_auth_type: AuthType,
                     #[serde(default)]
                     no_sync: bool,
                 }
@@ -750,10 +732,8 @@ impl LocalEnv {
                     listen_pg_addr,
                     listen_http_addr,
                     listen_https_addr,
-                    listen_grpc_addr,
                     pg_auth_type,
                     http_auth_type,
-                    grpc_auth_type,
                     no_sync,
                 } = config_toml;
                 let IdentityTomlSubset {
@@ -770,10 +750,8 @@ impl LocalEnv {
                     listen_pg_addr,
                     listen_http_addr,
                     listen_https_addr,
-                    listen_grpc_addr,
                     pg_auth_type,
                     http_auth_type,
-                    grpc_auth_type,
                     no_sync,
                 };
                 pageservers.push(conf);

control_plane/src/pageserver.rs

@@ -16,7 +16,6 @@ use std::time::Duration;
 
 use anyhow::{Context, bail};
 use camino::Utf8PathBuf;
-use pageserver_api::config::{DEFAULT_GRPC_LISTEN_PORT, DEFAULT_HTTP_LISTEN_PORT};
 use pageserver_api::models::{self, TenantInfo, TimelineInfo};
 use pageserver_api::shard::TenantShardId;
 use pageserver_client::mgmt_api;
@@ -130,9 +129,7 @@ impl PageServerNode {
             ));
         }
 
-        if [conf.http_auth_type, conf.pg_auth_type, conf.grpc_auth_type]
-            .contains(&AuthType::NeonJWT)
-        {
+        if conf.http_auth_type != AuthType::Trust || conf.pg_auth_type != AuthType::Trust {
             // Keys are generated in the toplevel repo dir, pageservers' workdirs
             // are one level below that, so refer to keys with ../
             overrides.push("auth_validation_public_key_path='../auth_public_key.pem'".to_owned());
@@ -253,10 +250,9 @@ impl PageServerNode {
         // the storage controller
         let metadata_path = datadir.join("metadata.json");
 
-        let http_host = "localhost".to_string();
-        let (_, http_port) =
+        let (_http_host, http_port) =
             parse_host_port(&self.conf.listen_http_addr).expect("Unable to parse listen_http_addr");
-        let http_port = http_port.unwrap_or(DEFAULT_HTTP_LISTEN_PORT);
+        let http_port = http_port.unwrap_or(9898);
 
         let https_port = match self.conf.listen_https_addr.as_ref() {
             Some(https_addr) => {
@@ -267,13 +263,6 @@ impl PageServerNode {
             None => None,
         };
 
-        let (mut grpc_host, mut grpc_port) = (None, None);
-        if let Some(grpc_addr) = &self.conf.listen_grpc_addr {
-            let (_, port) = parse_host_port(grpc_addr).expect("Unable to parse listen_grpc_addr");
-            grpc_host = Some("localhost".to_string());
-            grpc_port = Some(port.unwrap_or(DEFAULT_GRPC_LISTEN_PORT));
-        }
-
         // Intentionally hand-craft JSON: this acts as an implicit format compat test
         // in case the pageserver-side structure is edited, and reflects the real life
         // situation: the metadata is written by some other script.
@@ -282,9 +271,7 @@ impl PageServerNode {
             serde_json::to_vec(&pageserver_api::config::NodeMetadata {
                 postgres_host: "localhost".to_string(),
                 postgres_port: self.pg_connection_config.port(),
-                grpc_host,
-                grpc_port,
-                http_host,
+                http_host: "localhost".to_string(),
                 http_port,
                 https_port,
                 other: HashMap::from([(
@@ -524,6 +511,11 @@ impl PageServerNode {
                 .map(|x| x.parse::<bool>())
                 .transpose()
                 .context("Failed to parse 'timeline_offloading' as bool")?,
+            wal_receiver_protocol_override: settings
+                .remove("wal_receiver_protocol_override")
+                .map(serde_json::from_str)
+                .transpose()
+                .context("parse `wal_receiver_protocol_override` from json")?,
             rel_size_v2_enabled: settings
                 .remove("rel_size_v2_enabled")
                 .map(|x| x.parse::<bool>())
@@ -554,16 +546,6 @@ impl PageServerNode {
                 .map(serde_json::from_str)
                 .transpose()
                 .context("Falied to parse 'sampling_ratio'")?,
-            relsize_snapshot_cache_capacity: settings
-                .remove("relsize snapshot cache capacity")
-                .map(|x| x.parse::<usize>())
-                .transpose()
-                .context("Falied to parse 'relsize_snapshot_cache_capacity' as integer")?,
-            basebackup_cache_enabled: settings
-                .remove("basebackup_cache_enabled")
-                .map(|x| x.parse::<bool>())
-                .transpose()
-                .context("Failed to parse 'basebackup_cache_enabled' as bool")?,
         };
         if !settings.is_empty() {
             bail!("Unrecognized tenant settings: {settings:?}")
@@ -646,16 +628,4 @@ impl PageServerNode {
 
         Ok(())
     }
-    pub async fn timeline_info(
-        &self,
-        tenant_shard_id: TenantShardId,
-        timeline_id: TimelineId,
-        force_await_logical_size: mgmt_api::ForceAwaitLogicalSize,
-    ) -> anyhow::Result<TimelineInfo> {
-        let timeline_info = self
-            .http_client
-            .timeline_info(tenant_shard_id, timeline_id, force_await_logical_size)
-            .await?;
-        Ok(timeline_info)
-    }
 }

control_plane/src/safekeeper.rs

@@ -6,6 +6,7 @@
 //!   .neon/safekeepers/<safekeeper id>
 //! ```
 use std::error::Error as _;
+use std::future::Future;
 use std::io::Write;
 use std::path::PathBuf;
 use std::time::Duration;
@@ -13,9 +14,9 @@ use std::{io, result};
 
 use anyhow::Context;
 use camino::Utf8PathBuf;
+use http_utils::error::HttpErrorBody;
 use postgres_connection::PgConnectionConfig;
-use safekeeper_api::models::TimelineCreateRequest;
-use safekeeper_client::mgmt_api;
+use reqwest::{IntoUrl, Method};
 use thiserror::Error;
 use utils::auth::{Claims, Scope};
 use utils::id::NodeId;
@@ -34,14 +35,25 @@ pub enum SafekeeperHttpError {
 
 type Result<T> = result::Result<T, SafekeeperHttpError>;
 
-fn err_from_client_err(err: mgmt_api::Error) -> SafekeeperHttpError {
-    use mgmt_api::Error::*;
-    match err {
-        ApiError(_, str) => SafekeeperHttpError::Response(str),
-        Cancelled => SafekeeperHttpError::Response("Cancelled".to_owned()),
-        ReceiveBody(err) => SafekeeperHttpError::Transport(err),
-        ReceiveErrorBody(err) => SafekeeperHttpError::Response(err),
-        Timeout(str) => SafekeeperHttpError::Response(format!("timeout: {str}")),
+pub(crate) trait ResponseErrorMessageExt: Sized {
+    fn error_from_body(self) -> impl Future<Output = Result<Self>> + Send;
+}
+
+impl ResponseErrorMessageExt for reqwest::Response {
+    async fn error_from_body(self) -> Result<Self> {
+        let status = self.status();
+        if !(status.is_client_error() || status.is_server_error()) {
+            return Ok(self);
+        }
+
+        // reqwest does not export its error construction utility functions, so let's craft the message ourselves
+        let url = self.url().to_owned();
+        Err(SafekeeperHttpError::Response(
+            match self.json::<HttpErrorBody>().await {
+                Ok(err_body) => format!("Error: {}", err_body.msg),
+                Err(_) => format!("Http error ({}) at {}.", status.as_u16(), url),
+            },
+        ))
     }
 }
 
@@ -58,8 +70,9 @@ pub struct SafekeeperNode {
 
     pub pg_connection_config: PgConnectionConfig,
     pub env: LocalEnv,
-    pub http_client: mgmt_api::Client,
+    pub http_client: reqwest::Client,
     pub listen_addr: String,
+    pub http_base_url: String,
 }
 
 impl SafekeeperNode {
@@ -69,14 +82,13 @@ impl SafekeeperNode {
         } else {
             "127.0.0.1".to_string()
         };
-        let jwt = None;
-        let http_base_url = format!("http://{}:{}", listen_addr, conf.http_port);
         SafekeeperNode {
             id: conf.id,
             conf: conf.clone(),
             pg_connection_config: Self::safekeeper_connection_config(&listen_addr, conf.pg_port),
             env: env.clone(),
-            http_client: mgmt_api::Client::new(env.create_http_client(), http_base_url, jwt),
+            http_client: env.create_http_client(),
+            http_base_url: format!("http://{}:{}/v1", listen_addr, conf.http_port),
             listen_addr,
         }
     }
@@ -266,19 +278,20 @@ impl SafekeeperNode {
         )
     }
 
-    pub async fn check_status(&self) -> Result<()> {
-        self.http_client
-            .status()
-            .await
-            .map_err(err_from_client_err)?;
-        Ok(())
+    fn http_request<U: IntoUrl>(&self, method: Method, url: U) -> reqwest::RequestBuilder {
+        // TODO: authentication
+        //if self.env.auth_type == AuthType::NeonJWT {
+        //    builder = builder.bearer_auth(&self.env.safekeeper_auth_token)
+        //}
+        self.http_client.request(method, url)
     }
 
-    pub async fn create_timeline(&self, req: &TimelineCreateRequest) -> Result<()> {
-        self.http_client
-            .create_timeline(req)
-            .await
-            .map_err(err_from_client_err)?;
+    pub async fn check_status(&self) -> Result<()> {
+        self.http_request(Method::GET, format!("{}/{}", self.http_base_url, "status"))
+            .send()
+            .await?
+            .error_from_body()
+            .await?;
         Ok(())
     }
 }

control_plane/src/storage_controller.rs

@@ -557,10 +557,6 @@ impl StorageController {
             args.push("--use-local-compute-notifications".to_string());
         }
 
-        if let Some(value) = self.config.kick_secondary_downloads {
-            args.push(format!("--kick-secondary-downloads={value}"));
-        }
-
         if let Some(ssl_ca_file) = self.env.ssl_ca_cert_path() {
             args.push(format!("--ssl-ca-file={}", ssl_ca_file.to_str().unwrap()));
         }
@@ -632,10 +628,6 @@ impl StorageController {
             args.push("--timelines-onto-safekeepers".to_string());
         }
 
-        if let Some(sk_cnt) = self.config.timeline_safekeeper_count {
-            args.push(format!("--timeline-safekeeper-count={sk_cnt}"));
-        }
-
         println!("Starting storage controller");
 
         background_process::start_process(

control_plane/storcon_cli/src/main.rs

@@ -36,10 +36,6 @@ enum Command {
         listen_pg_addr: String,
         #[arg(long)]
         listen_pg_port: u16,
-        #[arg(long)]
-        listen_grpc_addr: Option<String>,
-        #[arg(long)]
-        listen_grpc_port: Option<u16>,
 
         #[arg(long)]
         listen_http_addr: String,
@@ -65,16 +61,10 @@ enum Command {
         #[arg(long)]
         scheduling: Option<NodeSchedulingPolicy>,
     },
-    // Set a node status as deleted.
     NodeDelete {
         #[arg(long)]
         node_id: NodeId,
     },
-    /// Delete a tombstone of node from the storage controller.
-    NodeDeleteTombstone {
-        #[arg(long)]
-        node_id: NodeId,
-    },
     /// Modify a tenant's policies in the storage controller
     TenantPolicy {
         #[arg(long)]
@@ -92,8 +82,6 @@ enum Command {
     },
     /// List nodes known to the storage controller
     Nodes {},
-    /// List soft deleted nodes known to the storage controller
-    NodeTombstones {},
     /// List tenants known to the storage controller
     Tenants {
         /// If this field is set, it will list the tenants on a specific node
@@ -422,8 +410,6 @@ async fn main() -> anyhow::Result<()> {
             node_id,
             listen_pg_addr,
             listen_pg_port,
-            listen_grpc_addr,
-            listen_grpc_port,
             listen_http_addr,
             listen_http_port,
             listen_https_port,
@@ -437,8 +423,6 @@ async fn main() -> anyhow::Result<()> {
                         node_id,
                         listen_pg_addr,
                         listen_pg_port,
-                        listen_grpc_addr,
-                        listen_grpc_port,
                         listen_http_addr,
                         listen_http_port,
                         listen_https_port,
@@ -916,39 +900,6 @@ async fn main() -> anyhow::Result<()> {
                 .dispatch::<(), ()>(Method::DELETE, format!("control/v1/node/{node_id}"), None)
                 .await?;
         }
-        Command::NodeDeleteTombstone { node_id } => {
-            storcon_client
-                .dispatch::<(), ()>(
-                    Method::DELETE,
-                    format!("debug/v1/tombstone/{node_id}"),
-                    None,
-                )
-                .await?;
-        }
-        Command::NodeTombstones {} => {
-            let mut resp = storcon_client
-                .dispatch::<(), Vec<NodeDescribeResponse>>(
-                    Method::GET,
-                    "debug/v1/tombstone".to_string(),
-                    None,
-                )
-                .await?;
-
-            resp.sort_by(|a, b| a.listen_http_addr.cmp(&b.listen_http_addr));
-
-            let mut table = comfy_table::Table::new();
-            table.set_header(["Id", "Hostname", "AZ", "Scheduling", "Availability"]);
-            for node in resp {
-                table.add_row([
-                    format!("{}", node.id),
-                    node.listen_http_addr,
-                    node.availability_zone_id,
-                    format!("{:?}", node.scheduling),
-                    format!("{:?}", node.availability),
-                ]);
-            }
-            println!("{table}");
-        }
         Command::TenantSetTimeBasedEviction {
             tenant_id,
             period,

docker-compose/compute_wrapper/shell/compute.sh

@@ -1,36 +1,28 @@
-#!/usr/bin/env bash
+#!/bin/bash
 set -eux
 
 # Generate a random tenant or timeline ID
 #
 # 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}
+    local -n resvar=$1
+    printf -v resvar '%08x%08x%08x%08x' $SRANDOM $SRANDOM $SRANDOM $SRANDOM
 }
 
 PG_VERSION=${PG_VERSION:-14}
 
-readonly CONFIG_FILE_ORG=/var/db/postgres/configs/config.json
-readonly CONFIG_FILE=/tmp/config.json
-
-# Test that the first library path that the dynamic loader looks in is the path
-# that we use for custom compiled software
-first_path="$(ldconfig --verbose 2>/dev/null \
-    | grep --invert-match ^$'\t' \
-    | cut --delimiter=: --fields=1 \
-    | head --lines=1)"
-test "${first_path}" = '/usr/local/lib'
+CONFIG_FILE_ORG=/var/db/postgres/configs/config.json
+CONFIG_FILE=/tmp/config.json
 
 echo "Waiting pageserver become ready."
 while ! nc -z pageserver 6400; do
-     sleep 1
+     sleep 1;
 done
 echo "Page server is ready."
 
-cp "${CONFIG_FILE_ORG}" "${CONFIG_FILE}"
+cp ${CONFIG_FILE_ORG} ${CONFIG_FILE}
 
- if [[ -n "${TENANT_ID:-}" && -n "${TIMELINE_ID:-}" ]]; then
+ if [ -n "${TENANT_ID:-}" ] && [ -n "${TIMELINE_ID:-}" ]; then
    tenant_id=${TENANT_ID}
    timeline_id=${TIMELINE_ID}
 else
@@ -41,7 +33,7 @@ else
        "http://pageserver:9898/v1/tenant"
   )
   tenant_id=$(curl "${PARAMS[@]}" | jq -r .[0].id)
-  if [[ -z "${tenant_id}" || "${tenant_id}" = null ]]; then
+  if [ -z "${tenant_id}" ] || [ "${tenant_id}" = null ]; then
     echo "Create a tenant"
     generate_id tenant_id
     PARAMS=(
@@ -51,7 +43,7 @@ else
         "http://pageserver:9898/v1/tenant/${tenant_id}/location_config"
     )
     result=$(curl "${PARAMS[@]}")
-    printf '%s\n' "${result}" | jq .
+    echo $result | jq .
   fi
 
   echo "Check if a timeline present"
@@ -61,7 +53,7 @@ else
        "http://pageserver:9898/v1/tenant/${tenant_id}/timeline"
   )
   timeline_id=$(curl "${PARAMS[@]}" | jq -r .[0].timeline_id)
-  if [[ -z "${timeline_id}" || "${timeline_id}" = null ]]; then
+  if [ -z "${timeline_id}" ] || [ "${timeline_id}" = null ]; then
     generate_id timeline_id
     PARAMS=(
         -sbf
@@ -71,7 +63,7 @@ else
         "http://pageserver:9898/v1/tenant/${tenant_id}/timeline/"
     )
     result=$(curl "${PARAMS[@]}")
-    printf '%s\n' "${result}" | jq .
+    echo $result | jq .
   fi
 fi
 
@@ -82,10 +74,10 @@ else
 fi
 echo "Adding pgx_ulid"
 shared_libraries=$(jq -r '.spec.cluster.settings[] | select(.name=="shared_preload_libraries").value' ${CONFIG_FILE})
-sed -i "s|${shared_libraries}|${shared_libraries},${ulid_extension}|" ${CONFIG_FILE}
+sed -i "s/${shared_libraries}/${shared_libraries},${ulid_extension}/" ${CONFIG_FILE}
 echo "Overwrite tenant id and timeline id in spec file"
-sed -i "s|TENANT_ID|${tenant_id}|" ${CONFIG_FILE}
-sed -i "s|TIMELINE_ID|${timeline_id}|" ${CONFIG_FILE}
+sed -i "s/TENANT_ID/${tenant_id}/" ${CONFIG_FILE}
+sed -i "s/TIMELINE_ID/${timeline_id}/" ${CONFIG_FILE}
 
 cat ${CONFIG_FILE}
 
@@ -93,6 +85,5 @@ echo "Start compute node"
 /usr/local/bin/compute_ctl --pgdata /var/db/postgres/compute \
      -C "postgresql://cloud_admin@localhost:55433/postgres"  \
      -b /usr/local/bin/postgres                              \
-     --compute-id "compute-${RANDOM}"                          \
-     --config "${CONFIG_FILE}"
-     --dev
+     --compute-id "compute-$RANDOM"                          \
+     --config "$CONFIG_FILE"

docker-compose/docker-compose.yml

@@ -194,6 +194,6 @@ services:
       - "/bin/bash"
       - "-c"
     command:
-      - sleep 3600
+      - sleep 360000
     depends_on:
       - compute

docker-compose/ext-src/alter_db.sh

@@ -1,8 +0,0 @@
-#!/bin/bash
-# We need these settings to get the expected output results.
-# We cannot use the environment variables e.g. PGTZ due to
-# https://github.com/neondatabase/neon/issues/1287
-export DATABASE=${1:-contrib_regression}
-psql -c "ALTER DATABASE ${DATABASE} SET neon.allow_unstable_extensions='on'" \
-     -c "ALTER DATABASE ${DATABASE} SET DateStyle='Postgres,MDY'" \
-     -c "ALTER DATABASE ${DATABASE} SET TimeZone='America/Los_Angeles'" \

docker-compose/ext-src/h3-pg-src/neon-test.sh

@@ -1,16 +0,0 @@
-#!/usr/bin/env bash
-set -ex
-cd "$(dirname "${0}")"
-PG_REGRESS=$(dirname "$(pg_config --pgxs)")/../test/regress/pg_regress
-dropdb --if-exists contrib_regression
-createdb contrib_regression
-cd h3_postgis/test
-psql -d contrib_regression -c "CREATE EXTENSION postgis" -c "CREATE EXTENSION postgis_raster" -c "CREATE EXTENSION h3" -c "CREATE EXTENSION h3_postgis"
-TESTS=$(echo sql/* | sed 's|sql/||g; s|\.sql||g')
-${PG_REGRESS} --use-existing --dbname contrib_regression ${TESTS}
-cd ../../h3/test
-TESTS=$(echo sql/* | sed 's|sql/||g; s|\.sql||g')
-dropdb --if-exists contrib_regression
-createdb contrib_regression
-psql -d contrib_regression -c "CREATE EXTENSION h3"
-${PG_REGRESS} --use-existing --dbname contrib_regression ${TESTS}

docker-compose/ext-src/h3-pg-src/test-upgrade.sh

@@ -1,7 +0,0 @@
-#!/bin/sh
-set -ex
-cd "$(dirname ${0})"
-PG_REGRESS=$(dirname "$(pg_config --pgxs)")/../test/regress/pg_regress
-cd h3/test
-TESTS=$(echo sql/* | sed 's|sql/||g; s|\.sql||g')
-${PG_REGRESS} --use-existing --inputdir=./ --bindir='/usr/local/pgsql/bin'  --dbname=contrib_regression  ${TESTS}

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

@@ -1,6 +0,0 @@
-#!/bin/sh
-set -ex
-cd "$(dirname "${0}")"
-if [ -f Makefile ]; then
-  make installcheck
-fi

docker-compose/ext-src/online_advisor-src/regular-test.sh

@@ -1,9 +0,0 @@
-#!/bin/sh
-set -ex
-cd "$(dirname ${0})"
-[ -f Makefile ] || exit 0
-dropdb --if-exist contrib_regression
-createdb contrib_regression
-PG_REGRESS=$(dirname "$(pg_config --pgxs)")/../test/regress/pg_regress
-TESTS=$(echo sql/* | sed 's|sql/||g; s|\.sql||g')
-${PG_REGRESS} --use-existing --inputdir=./ --bindir='/usr/local/pgsql/bin' --dbname=contrib_regression ${TESTS}

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

@@ -18,7 +18,6 @@ TESTS=${TESTS/row_level_security/}
 TESTS=${TESTS/sqli_connection/}
 dropdb --if-exist contrib_regression
 createdb contrib_regression
-. ../alter_db.sh
 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/pgrag-src/regular-test.sh

@@ -3,7 +3,6 @@ set -ex
 cd "$(dirname "${0}")"
 dropdb --if-exist contrib_regression
 createdb contrib_regression
-. ../alter_db.sh
 psql -d contrib_regression -c "CREATE EXTENSION vector" -c "CREATE EXTENSION rag"
 PG_REGRESS=$(dirname "$(pg_config --pgxs)")/../test/regress/pg_regress
 ${PG_REGRESS} --inputdir=./ --bindir='/usr/local/pgsql/bin'    --use-existing --load-extension=vector --load-extension=rag --dbname=contrib_regression basic_functions text_processing api_keys chunking_functions document_processing embedding_api_functions voyageai_functions

docker-compose/ext-src/pgx_ulid-src/Makefile

@@ -20,6 +20,5 @@ installcheck: regression-test
 regression-test:
 	dropdb --if-exists contrib_regression
 	createdb contrib_regression
-	../alter_db.sh
 	psql -d contrib_regression -c "CREATE EXTENSION $(EXTNAME)"
 	$(PG_REGRESS) --inputdir=. --outputdir=. --use-existing --dbname=contrib_regression $(REGRESS)

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

@@ -3,7 +3,6 @@ set -ex
 cd "$(dirname ${0})"
 dropdb --if-exist contrib_regression
 createdb contrib_regression
-. ../alter_db.sh
 PG_REGRESS=$(dirname "$(pg_config --pgxs)")/../test/regress/pg_regress
 REGRESS="$(make -n installcheck | awk '{print substr($0,index($0,"init-extension"));}')"
 REGRESS="${REGRESS/startup_perms/}"

docker-compose/ext-src/postgis-src/README-Neon.md

@@ -1,70 +0,0 @@
-# PostGIS Testing in Neon
-
-This directory contains configuration files and patches for running PostGIS tests in the Neon database environment.
-
-## Overview
-
-PostGIS is a spatial database extension for PostgreSQL that adds support for geographic objects. Testing PostGIS compatibility ensures that Neon's modifications to PostgreSQL don't break compatibility with this critical extension.
-
-## PostGIS Versions
-
-- PostgreSQL v17: PostGIS 3.5.0
-- PostgreSQL v14/v15/v16: PostGIS 3.3.3
-
-## Test Configuration
-
-The test setup includes:
-
-- `postgis-no-upgrade-test.patch`: Disables upgrade tests by removing the upgrade test section from regress/runtest.mk
-- `postgis-regular-v16.patch`: Version-specific patch for PostgreSQL v16
-- `postgis-regular-v17.patch`: Version-specific patch for PostgreSQL v17
-- `regular-test.sh`: Script to run PostGIS tests as a regular user
-- `neon-test.sh`: Script to handle version-specific test configurations
-- `raster_outdb_template.sql`: Template for raster tests with explicit file paths
-
-## Excluded Tests
-
-**Important Note:** The test exclusions listed below are specifically for regular-user tests against staging instances. These exclusions are necessary because staging instances run with limited privileges and cannot perform operations requiring superuser access. Docker-compose based tests are not affected by these exclusions.
-
-### Tests Requiring Superuser Permissions
-
-These tests cannot be run as a regular user:
-- `estimatedextent`
-- `regress/core/legacy`
-- `regress/core/typmod`
-- `regress/loader/TestSkipANALYZE`
-- `regress/loader/TestANALYZE`
-
-### Tests Requiring Filesystem Access
-
-These tests need direct filesystem access that is only possible for superusers:
-- `loader/load_outdb`
-
-### Tests with Flaky Results
-
-These tests have assumptions that don't always hold true:
-- `regress/core/computed_columns` - Assumes computed columns always outperform alternatives, which is not consistently true
-
-### Tests Requiring Tunable Parameter Modifications
-
-These tests attempt to modify the `postgis.gdal_enabled_drivers` parameter, which is only accessible to superusers:
-- `raster/test/regress/rt_wkb`
-- `raster/test/regress/rt_addband`
-- `raster/test/regress/rt_setbandpath`
-- `raster/test/regress/rt_fromgdalraster`
-- `raster/test/regress/rt_asgdalraster`
-- `raster/test/regress/rt_astiff`
-- `raster/test/regress/rt_asjpeg`
-- `raster/test/regress/rt_aspng`
-- `raster/test/regress/permitted_gdal_drivers`
-- Loader tests: `BasicOutDB`, `Tiled10x10`, `Tiled10x10Copy`, `Tiled8x8`, `TiledAuto`, `TiledAutoSkipNoData`, `TiledAutoCopyn`
-
-### Topology Tests (v17 only)
-- `populate_topology_layer`
-- `renametopogeometrycolumn`
-
-## Other Modifications
-
-- Binary.sql tests are modified to use explicit file paths
-- Server-side SQL COPY commands (which require superuser privileges) are converted to client-side `\copy` commands
-- Upgrade tests are disabled

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

@@ -1,6 +1,9 @@
-#!/bin/sh
+#!/bin/bash
 set -ex
 cd "$(dirname "$0")"
-patch -p1 <"postgis-common-${PG_VERSION}.patch"
-trap 'echo Cleaning up; patch -R -p1 <postgis-common-${PG_VERSION}.patch' EXIT
+if [[ ${PG_VERSION} = v17 ]]; then
+  sed -i '/computed_columns/d' regress/core/tests.mk
+fi
+patch -p1 <postgis-no-upgrade-test.patch
+trap 'echo Cleaning up; patch -R -p1 <postgis-no-upgrade-test.patch' EXIT
 make installcheck-base

docker-compose/ext-src/postgis-src/postgis-common-v17.patch

@@ -1,35 +0,0 @@
-diff --git a/regress/core/tests.mk b/regress/core/tests.mk
-index 9e05244..90987df 100644
---- a/regress/core/tests.mk
-+++ b/regress/core/tests.mk
-@@ -143,8 +143,7 @@ TESTS += \
- 	$(top_srcdir)/regress/core/oriented_envelope \
- 	$(top_srcdir)/regress/core/point_coordinates \
- 	$(top_srcdir)/regress/core/out_geojson \
--  $(top_srcdir)/regress/core/wrapx \
--	$(top_srcdir)/regress/core/computed_columns
-+  $(top_srcdir)/regress/core/wrapx
- 
- # Slow slow tests
- TESTS_SLOW = \
-diff --git a/regress/runtest.mk b/regress/runtest.mk
-index 4b95b7e..449d5a2 100644
---- a/regress/runtest.mk
-+++ b/regress/runtest.mk
-@@ -24,16 +24,6 @@ check-regress:
- 
- 	@POSTGIS_TOP_BUILD_DIR=$(abs_top_builddir) $(PERL) $(top_srcdir)/regress/run_test.pl $(RUNTESTFLAGS) $(RUNTESTFLAGS_INTERNAL) $(TESTS)
- 
--	@if echo "$(RUNTESTFLAGS)" | grep -vq -- --upgrade; then \
--		echo "Running upgrade test as RUNTESTFLAGS did not contain that"; \
--		POSTGIS_TOP_BUILD_DIR=$(abs_top_builddir) $(PERL) $(top_srcdir)/regress/run_test.pl \
--      --upgrade \
--      $(RUNTESTFLAGS) \
--      $(RUNTESTFLAGS_INTERNAL) \
--      $(TESTS); \
--	else \
--		echo "Skipping upgrade test as RUNTESTFLAGS already requested upgrades"; \
--	fi
- 
- check-long:
- 	$(PERL) $(top_srcdir)/regress/run_test.pl $(RUNTESTFLAGS) $(TESTS) $(TESTS_SLOW)

docker-compose/ext-src/postgis-src/postgis-no-upgrade-test.patch

@@ -1,19 +1,3 @@
-diff --git a/regress/core/tests.mk b/regress/core/tests.mk
-index 3abd7bc..64a9254 100644
---- a/regress/core/tests.mk
-+++ b/regress/core/tests.mk
-@@ -144,11 +144,6 @@ TESTS_SLOW = \
- 	$(top_srcdir)/regress/core/concave_hull_hard \
- 	$(top_srcdir)/regress/core/knn_recheck
- 
--ifeq ($(shell expr "$(POSTGIS_PGSQL_VERSION)" ">=" 120),1)
--	TESTS += \
--		$(top_srcdir)/regress/core/computed_columns
--endif
--
- ifeq ($(shell expr "$(POSTGIS_GEOS_VERSION)" ">=" 30700),1)
- 	# GEOS-3.7 adds:
- 	# ST_FrechetDistance
 diff --git a/regress/runtest.mk b/regress/runtest.mk
 index c051f03..010e493 100644
 --- a/regress/runtest.mk

docker-compose/ext-src/postgis-src/postgis-regular-v16.patch

@@ -125,7 +125,7 @@ index 7a36b65..ad78fc7 100644
  DROP SCHEMA tm CASCADE;
 +
 diff --git a/regress/core/tests.mk b/regress/core/tests.mk
-index 64a9254..94903c3 100644
+index 3abd7bc..94903c3 100644
 --- a/regress/core/tests.mk
 +++ b/regress/core/tests.mk
 @@ -23,7 +23,6 @@ current_dir := $(dir $(abspath $(lastword $(MAKEFILE_LIST))))
@@ -160,6 +160,18 @@ index 64a9254..94903c3 100644
  	$(top_srcdir)/regress/core/wkb \
  	$(top_srcdir)/regress/core/wkt \
  	$(top_srcdir)/regress/core/wmsservers \
+@@ -144,11 +140,6 @@ TESTS_SLOW = \
+ 	$(top_srcdir)/regress/core/concave_hull_hard \
+ 	$(top_srcdir)/regress/core/knn_recheck
+ 
+-ifeq ($(shell expr "$(POSTGIS_PGSQL_VERSION)" ">=" 120),1)
+-	TESTS += \
+-		$(top_srcdir)/regress/core/computed_columns
+-endif
+-
+ ifeq ($(shell expr "$(POSTGIS_GEOS_VERSION)" ">=" 30700),1)
+ 	# GEOS-3.7 adds:
+ 	# ST_FrechetDistance
 diff --git a/regress/loader/tests.mk b/regress/loader/tests.mk
 index 1fc77ac..c3cb9de 100644
 --- a/regress/loader/tests.mk

docker-compose/ext-src/postgis-src/postgis-regular-v17.patch

@@ -125,7 +125,7 @@ index 7a36b65..ad78fc7 100644
  DROP SCHEMA tm CASCADE;
 +
 diff --git a/regress/core/tests.mk b/regress/core/tests.mk
-index 90987df..74fe3f1 100644
+index 9e05244..a63a3e1 100644
 --- a/regress/core/tests.mk
 +++ b/regress/core/tests.mk
 @@ -16,14 +16,13 @@ POSTGIS_PGSQL_VERSION=170
@@ -168,6 +168,16 @@ index 90987df..74fe3f1 100644
  	$(top_srcdir)/regress/core/wkb \
  	$(top_srcdir)/regress/core/wkt \
  	$(top_srcdir)/regress/core/wmsservers \
+@@ -143,8 +139,7 @@ TESTS += \
+ 	$(top_srcdir)/regress/core/oriented_envelope \
+ 	$(top_srcdir)/regress/core/point_coordinates \
+ 	$(top_srcdir)/regress/core/out_geojson \
+-  $(top_srcdir)/regress/core/wrapx \
+-	$(top_srcdir)/regress/core/computed_columns
++  $(top_srcdir)/regress/core/wrapx 
+ 
+ # Slow slow tests
+ TESTS_SLOW = \
 diff --git a/regress/loader/tests.mk b/regress/loader/tests.mk
 index ac4f8ad..4bad4fc 100644
 --- a/regress/loader/tests.mk

docker-compose/ext-src/postgis-src/regular-test.sh

@@ -10,8 +10,10 @@ psql -d contrib_regression -c "ALTER DATABASE contrib_regression SET TimeZone='U
      -c "CREATE EXTENSION postgis_tiger_geocoder CASCADE" \
      -c "CREATE EXTENSION postgis_raster SCHEMA public" \
      -c "CREATE EXTENSION postgis_sfcgal SCHEMA public"
-patch -p1 <"postgis-common-${PG_VERSION}.patch"
+patch -p1 <postgis-no-upgrade-test.patch
 patch -p1 <"postgis-regular-${PG_VERSION}.patch"
 psql -d contrib_regression -f raster_outdb_template.sql
-trap 'patch -R -p1 <postgis-regular-${PG_VERSION}.patch && patch -R -p1 <"postgis-common-${PG_VERSION}.patch"' EXIT
+trap 'patch -R -p1 <postgis-no-upgrade-test.patch && patch -R -p1 <"postgis-regular-${PG_VERSION}.patch"' EXIT
+#XXX remove after fix of using system libpq problem
+export LD_LIBRARY_PATH=/usr/local/pgsql/lib
 POSTGIS_REGRESS_DB=contrib_regression RUNTESTFLAGS=--nocreate make installcheck-base

docker-compose/ext-src/rag_bge_small_en_v15-src/Makefile

@@ -11,6 +11,5 @@ PG_REGRESS := $(dir $(PGXS))../../src/test/regress/pg_regress
 installcheck:
 	dropdb --if-exists contrib_regression
 	createdb contrib_regression
-	../alter_db.sh
 	psql -d contrib_regression -c "CREATE EXTENSION vector" -c "CREATE EXTENSION rag_bge_small_en_v15"
 	$(PG_REGRESS) --use-existing --dbname=contrib_regression $(REGRESS)

docker-compose/ext-src/rag_jina_reranker_v1_tiny_en-src/Makefile

@@ -11,6 +11,5 @@ PG_REGRESS := $(dir $(PGXS))../../src/test/regress/pg_regress
 installcheck:
 	dropdb --if-exists contrib_regression
 	createdb contrib_regression
-	../alter_db.sh
 	psql -d contrib_regression -c "CREATE EXTENSION vector" -c "CREATE EXTENSION rag_jina_reranker_v1_tiny_en"
 	$(PG_REGRESS) --use-existing --dbname=contrib_regression $(REGRESS)

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

@@ -3,6 +3,5 @@ set -ex
 cd "$(dirname ${0})"
 dropdb --if-exist contrib_regression
 createdb contrib_regression
-. ../alter_db.sh
 PG_REGRESS=$(dirname "$(pg_config --pgxs)")/../test/regress/pg_regress
 ${PG_REGRESS} --inputdir=./ --bindir='/usr/local/pgsql/bin' --use-existing --dbname=contrib_regression rum rum_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/pageserver_config/pageserver.toml

@@ -5,4 +5,3 @@ listen_http_addr='0.0.0.0:9898'
 remote_storage={ endpoint='http://minio:9000', bucket_name='neon', bucket_region='eu-north-1', prefix_in_bucket='/pageserver' }
 control_plane_api='http://0.0.0.0:6666' # No storage controller in docker compose, specify a junk address
 control_plane_emergency_mode=true
-virtual_file_io_mode="buffered" # the CI runners where we run the docker compose tests have slow disks

docker-compose/test_extensions_upgrade.sh

@@ -82,8 +82,7 @@ EXTENSIONS='[
 {"extname": "pg_ivm", "extdir": "pg_ivm-src"},
 {"extname": "pgjwt", "extdir": "pgjwt-src"},
 {"extname": "pgtap", "extdir": "pgtap-src"},
-{"extname": "pg_repack", "extdir": "pg_repack-src"},
-{"extname": "h3", "extdir": "h3-pg-src"}
+{"extname": "pg_repack", "extdir": "pg_repack-src"}
 ]'
 EXTNAMES=$(echo ${EXTENSIONS} | jq -r '.[].extname' | paste -sd ' ' -)
 COMPUTE_TAG=${NEW_COMPUTE_TAG} docker compose --profile test-extensions up --quiet-pull --build -d

docs/rfcs/030-vectored-timeline-get.md

@@ -7,8 +7,6 @@ Author: Christian Schwarz
 
 A brief RFC / GitHub Epic describing a vectored version of the `Timeline::get` method that is at the heart of Pageserver.
 
-**EDIT**: the implementation of this feature is described in [Vlad's (internal) tech talk](https://drive.google.com/file/d/1vfY24S869UP8lEUUDHRWKF1AJn8fpWoJ/view?usp=drive_link).
-
 # Motivation
 
 During basebackup, we issue many `Timeline::get` calls for SLRU pages that are *adjacent* in key space.

docs/rfcs/043-bottom-most-gc-compaction.md

@@ -1,194 +0,0 @@
-# Bottommost Garbage-Collection Compaction
-
-## Summary
-
-The goal of this doc is to propose a way to reliably collect garbages below the GC horizon. This process is called bottom-most garbage-collect-compaction, and is part of the broader legacy-enhanced compaction that we plan to implement in the future.
-
-## Motivation
-
-The current GC algorithm will wait until the covering via image layers before collecting the garbages of a key region. Relying on image layer generation to generate covering images is not reliable. There are prior arts to generate feedbacks from the GC algorithm to the image generation process to accelerate garbage collection, but it slows down the system and creates write amplification.
-
-# Basic Idea
-
-![](images/036-bottom-most-gc-compaction/01-basic-idea.svg)
-
-The idea of bottom-most compaction is simple: we rewrite all layers that are below or intersect with the GC horizon to produce a flat level of image layers at the GC horizon and deltas above the GC horizon. In this process,
-
-- All images and deltas ≤ GC horizon LSN will be dropped. This process collects garbages.
-- We produce images for all keys involved in the compaction process at the GC horizon.
-
-Therefore, it can precisely collect all garbages below the horizon, and reduce the space amplification, i.e., in the staircase pattern (test_gc_feedback).
-
-![The staircase pattern in test_gc_feedback in the original compaction algorithm. The goal is to collect garbage below the red horizontal line.](images/036-bottom-most-gc-compaction/12-staircase-test-gc-feedback.png)
-
-The staircase pattern in test_gc_feedback in the original compaction algorithm. The goal is to collect garbage below the red horizontal line.
-
-# Branches
-
-With branches, the bottom-most compaction should retain a snapshot of the keyspace at the `retain_lsn` so that the child branch can access data at the branch point. This requires some modifications to the basic bottom-most compaction algorithm that we sketched above. 
-
-![](images/036-bottom-most-gc-compaction/03-retain-lsn.svg)
-
-## Single Timeline w/ Snapshots: handle `retain_lsn`
-
-First let’s look into the case where we create branches over the main branch but don’t write any data to them (aka “snapshots”).
-
-The bottom-most compaction algorithm collects all deltas and images of a key and can make decisions on what data to retain. Given that we have a single key’s history as below:
-
-```
-LSN 0x10 -> A
-LSN 0x20 -> append B
-retain_lsn: 0x20
-LSN 0x30 -> append C
-LSN 0x40 -> append D
-retain_lsn: 0x40
-LSN 0x50 -> append E
-GC horizon: 0x50
-LSN 0x60 -> append F
-```
-
-The algorithm will produce:
-
-```
-LSN 0x20 -> AB
-(drop all history below the earliest retain_lsn)
-LSN 0x40 -> ABCD
-(assume the cost of replaying 2 deltas is higher than storing the full image, we generate an image here)
-LSN 0x50 -> append E
-(replay one delta is cheap)
-LSN 0x60 -> append F
-(keep everything as-is above the GC horizon)
-```
-
-![](images/036-bottom-most-gc-compaction/05-btmgc-parent.svg)
-
-What happens is that we balance the space taken by each retain_lsn and the cost of replaying deltas during the bottom-most compaction process. This is controlled by a threshold. If `count(deltas) < $threshold`, the deltas will be retained. Otherwise, an image will be generated and the deltas will be dropped.
-
-In the example above, the `$threshold` is 2.
-
-## Child Branches with data: pull + partial images
-
-In the previous section we have shown how bottom-most compaction respects `retain_lsn` so that all data that was readable at branch creation remains readable. But branches can have data on their own, and that data can fall out of the branch’s PITR window. So, this section explains how we deal with that.
-
-We will run the same bottom-most compaction for these branches, to ensure the space amplification on the child branch is reasonable. 
-
-```
-branch_lsn: 0x20
-LSN 0x30 -> append P
-LSN 0x40 -> append Q
-LSN 0x50 -> append R
-GC horizon: 0x50
-LSN 0x60 -> append S
-```
-
-Note that bottom-most compaction happens on a per-timeline basis. When it processes this key, it only reads the history from LSN 0x30 without a base image. Therefore, on child branches, the bottom-most compaction process will make image creation decisions based on the same `count(deltas) < $threshold` criteria, and if it decides to create an image, the base image will be retrieved from the ancestor branch.
-
-```
-branch_lsn: 0x20
-LSN 0x50 -> ABPQR
-(we pull the image at LSN 0x20 from the ancestor branch to get AB, and then apply append PQ to the page; we replace the record at 0x40 with an image and drop the delta)
-GC horizon: 0x50
-LSN 0x60 -> append S
-```
-
-![](images/036-bottom-most-gc-compaction/06-btmgc-child.svg)
-
-Note that for child branches, we do not create image layers for the images when bottom-most compaction runs. Instead, we drop the 0x30/0x40/0x50 delta records and directly place the image ABPQR@0x50 into the delta layer, which serves as a sparse image layer. For child branches, if we create image layers, we will need to put all keys in the range into the image layer. This causes space bloat and slow compactions. In this proposal, the compaction process will only compact and process keys modified inside the child branch.
-
-# Result
-
-Bottom-most compaction ensures all garbage under the GC horizon gets collected right away (compared with “eventually” in the current algorithm). Meanwhile, it generates images at each of the retain_lsn to ensure branch reads are fast. As we make per-key decisions on whether to generate an image or not, the theoretical lower bound of the storage space we need to retain for a branch is lower than before.
-
-Before: min(sum(logs for each key), sum(image for each key)), for each partition — we always generate image layers on a key range
-
-After: sum(min(logs for each key, image for each key))
-
-# Compaction Trigger
-
-The bottom-most compaction can be automatically triggered. The goal of the trigger is that it should ensure a constant factor for write amplification. Say that the user write 1GB of WAL into the system, we should write 1GB x C data to S3. The legacy compaction algorithm does not have such a constant factor C. The data we write to S3 is quadratic to the logical size of the database (see [A Theoretical View of Neon Storage](https://www.notion.so/A-Theoretical-View-of-Neon-Storage-8d7ad7555b0c41b2a3597fa780911194?pvs=21)).
-
-We propose the following compaction trigger that generates a constant write amplification factor. Write amplification >= total writes to S3 / total user writes. We only analyze the write amplification caused by the bottom-most GC-compaction process, ignoring the legacy create image layers amplification.
-
-Given that we have ***X*** bytes of the delta layers above the GC horizon, ***A*** bytes of the delta layers intersecting with the GC horizon, ***B*** bytes of the delta layers below the GC horizon, and ***C*** bytes of the image layers below the GC horizon.
-
-The legacy GC + compaction loop will always keep ***A*** unchanged, reduce ***B and C*** when there are image layers covering the key range. This yields 0 write amplification (only file deletions) and extra ***B*** bytes of space.
-
-![](images/036-bottom-most-gc-compaction/09-btmgc-analysis-2.svg)
-
-The bottom-most compaction proposed here will split ***A*** into deltas above the GC horizon and below the GC horizon. Everything below the GC horizon will be image layers after the compaction (not considering branches). Therefore, this yields ***A+C*** extra write traffic each iteration, plus 0 extra space.
-
-![](images/036-bottom-most-gc-compaction/07-btmgc-analysis-1.svg)
-
-Also considering read amplification (below the GC horizon). When a read request reaches the GC horizon, the read amplification will be (A+B+C)/C=1+(A+B)/C. Reducing ***A*** and ***B*** can help reduce the read amplification below the GC horizon.
-
-The metrics-based trigger will wait until a point that space amplification is not that large and write amplification is not that large before the compaction gets triggered. The trigger is defined as **(A+B)/C ≥ 1 (or some other ratio)**.
-
-To reason about this trigger, consider the two cases:
-
-**Data Ingestion**
-
-User keeps ingesting data into the database, which indicates that WAL size roughly equals to the database logical size. The compaction gets triggered only when the newly-written WAL roughly equals to the current bottom-most image size (=X). Therefore, it’s triggered when the database size gets doubled. This is a reasonable amount of work. Write amplification is 2X/X=1 for the X amount of data written.
-
-![](images/036-bottom-most-gc-compaction/10-btmgc-analysis-3.svg)
-
-**Updates/Deletion**
-
-In this case, WAL size will be larger than the database logical size ***D***. The compaction gets triggered for every ***D*** bytes of WAL written. Therefore, for every ***D*** bytes of WAL, we rewrite the bottom-most layer, which produces an extra ***D*** bytes of write amplification. This incurs exactly 2x write amplification (by the write of D), 1.5x write amplification (if we count from the start of the process) and no space amplification. 
-
-![](images/036-bottom-most-gc-compaction/11-btmgc-analysis-4.svg)
-
-Note that here I try to reason that write amplification is a constant (i.e., the data we write to S3 is proportional to the data the user write). The main problem with the current legacy compaction algorithm is that write amplification is proportional to the database size.
-
-The next step is to optimize the write amplification above the GC horizon (i.e., change the image creation criteria, top-most compaction, or introduce tiered compaction), to ensure the write amplification of the whole system is a constant factor.
-
-20GB layers → +20GB layers → delete 20GB, need 40GB temporary space
-
-# Sub-Compactions
-
-The gc-compaction algorithm may take a long time and we need to split the job into multiple sub-compaction jobs.
-
-![](images/036-bottom-most-gc-compaction/13-job-split.svg)
-
-As in the figure, the auto-trigger schedules a compaction job covering the full keyspace below a specific LSN. In such case that we cannot finish compacting it in one run in a reasonable amount of time, the algorithm will vertically split it into multiple jobs (in this case, 5).
-
-Each gc-compaction job will create one level of delta layers and one flat level of image layers for each LSN. Those layers will be automatically split based on size, which means that if the sub-compaction job produces 1GB of deltas, it will produce 4 * 256MB delta layers. For those layers that is not fully contained within the sub-compaction job rectangles, it will be rewritten to only contain the keys outside of the key range.
-
-# Implementation
-
-The main implementation of gc-compaction is in `compaction.rs`.
-
-* `compact_with_gc`: The main loop of gc-compaction. It takes a rectangle range of the layer map and compact that specific range. It selects layers intersecting with the rectangle, downloads the layers, creates the k-merge iterator to read those layers in the key-lsn order, and decide which keys to keep or insert a reconstructed page. The process is the basic unit of a gc-compaction and is not interruptable. If the process gets preempted by L0 compaction, it has to be restarted from scratch. For layers overlaps with the rectangle but not fully inside, the main loop will also rewrite them so that the new layer (or two layers if both left and right ends are outside of the rectangle) has the same LSN range as the original one but only contain the keys outside of the compaction range.
-* `gc_compaction_split_jobs`: Splits a big gc-compaction job into sub-compactions based on heuristics in the layer map. The function looks at the layer map and splits the compaction job based on the size of the layers so that each compaction job only pulls ~4GB of layer files.
-* `generate_key_retention` and `KeyHistoryRetention`: Implements the algorithm described in the "basic idea" and "branch" chapter of this RFC. It takes a vector of history of a key (key-lsn-value) and decides which LSNs of the key to retain. If there are too many deltas between two retain_lsns, it will reconstruct the page and insert an image into the compaction result. Also, we implement `KeyHistoryRetention::verify` to ensure the generated result is not corrupted -- all retain_lsns and all LSNs above the gc-horizon should be accessible.
-* `GcCompactionQueue`: the automatic trigger implementation for gc-compaction. `GcCompactionQueue::iteration` is called at the end of the tenant compaction loop. It will then call `trigger_auto_compaction` to decide whether to trigger a gc-compaction job for this tenant. If yes, the compaction-job will be added to the compaction queue, and the queue will be slowly drained once there are no other compaction jobs running. gc-compaction has the lowest priority. If a sub-compaction job is not successful or gets preempted by L0 compaction (see limitations for reasons why a compaction job would fail), it will _not_ be retried.
-* Changes to `index_part.json`: we added a `last_completed_lsn` field to the index part for the auto-trigger to decide when to trigger a compaction.
-* Changes to the read path: when gc-compaction updates the layer map, all reads need to wait. See `gc_compaction_layer_update_lock` and comments in the code path for more information.
-
-Gc-compaction can also be scheduled over the HTTP API. Example:
-
-```
-curl 'localhost:9898/v1/tenant/:tenant_id/timeline/:timeline_id/compact?enhanced_gc_bottom_most_compaction=true&dry_run=true' -X PUT -H "Content-Type: application/json" -d '{"scheduled": true, "compact_key_range": { "start": "000000067F0000A0000002A1CF0100000000", "end": "000000067F0000A0000002A1D70100000000" } }'
-```
-
-The `dry_run` mode can be specified in the query string so that the compaction will go through all layers to estimate how much space can be saved without writing the compaction result into the layer map.
-
-The auto-trigger is controlled by tenant-level flag `gc_compaction_enabled`. If this is set to false, no gc-compaction will be automatically scheduled on this tenant (but manual trigger still works).
-
-# Next Steps
-
-There are still some limitations of gc-compaction itself that needs to be resolved and tested,
-
-- gc-compaction is currently only automatically triggered on root branches. We have not tested gc-compaction on child branches in staging.
-- gc-compaction will skip aux key regions because of the possible conflict with the assumption of aux file tombstones.
-- gc-compaction does not consider keyspaces at retain_lsns and only look at keys in the layers. This also causes us giving up some sub-compaction jobs because a key might have part of its history available due to traditional GC removing part of the history.
-- We limit gc-compaction to run over shards <= 150GB to avoid gc-compaction taking too much time blocking other compaction jobs. The sub-compaction split algorithm needs to be improved to be able to split vertically and horizontally. Also, we need to move the download layer process out of the compaction loop so that we don't block other compaction jobs for too long.
-- The compaction trigger always schedules gc-compaction from the lowest LSN to the gc-horizon. Currently we do not schedule compaction jobs that only selects layers in the middle. Allowing this could potentially reduce the number of layers read/write throughout the process.
-- gc-compaction will give up if there are too many layers to rewrite or if there are not enough disk space for the compaction.
-- gc-compaction sometimes fails with "no key produced during compaction", which means that all existing keys within the compaction range can be collected; but we don't have a way to write this information back to the layer map -- we cannot generate an empty image layer.
-- We limit the maximum size of deltas for a single key to 512MB. If above this size, gc-compaction will give up. This can be resolved by changing `generate_key_retention` to be a stream instead of requiring to collect all the key history.
-
-In the future,
-
-- Top-most compaction: ensure we always have an image coverage for the latest data (or near the latest data), so that reads will be fast at the latest LSN.
-- Tiered compaction on deltas: ensure read from any LSN is fast.
-- Per-timeline compaction → tenant-wide compaction?

docs/rfcs/2025-04-30-direct-io-for-pageserver.md

@@ -1,362 +0,0 @@
-# Direct IO For Pageserver
-
-Date: Apr 30, 2025
-
-## Summary
-
-This document is a retroactive RFC. It
-- provides some background on what direct IO is,
-- motivates why Pageserver should be using it for its IO, and
-- describes how we changed Pageserver to use it.
-
-The [initial proposal](https://github.com/neondatabase/neon/pull/8240) that kicked off the work can be found in this closed GitHub PR.
-
-People primarily involved in this project were:
-- Yuchen Liang <yuchen@neon.tech>
-- Vlad Lazar <vlad@neon.tech>
-- Christian Schwarz <christian@neon.tech>
-
-## Timeline
-
-For posterity, here is the rough timeline of the development work that got us to where we are today.
-
-- Jan 2024: [integrate `tokio-epoll-uring`](https://github.com/neondatabase/neon/pull/5824) along with owned buffers API
-- March 2024: `tokio-epoll-uring` enabled in all regions in buffered IO mode
-- Feb 2024 to June 2024: PS PageCache Bypass For Data Blocks
-  - Feb 2024: [Vectored Get Implementation](https://github.com/neondatabase/neon/pull/6576) bypasses delta & image layer blocks for page requests
-  - Apr to June 2024: [Epic: bypass PageCache for use data blocks](https://github.com/neondatabase/neon/issues/7386) addresses remaining users
-- Aug to Nov 2024: direct IO: first code; preliminaries; read path coding; BufferedWriter; benchmarks show perf regressions too high, no-go.
-- Nov 2024 to Jan 2025: address perf regressions by developing page_service pipelining (aka batching) and concurrent IO ([Epic](https://github.com/neondatabase/neon/issues/9376))
-- Feb to March 2024: rollout batching, then concurrent+direct IO => read path and InMemoryLayer is now direct IO
-- Apr 2025: develop & roll out direct IO for the write path
-
-## Background: Terminology & Glossary
-
-**kernel page cache**: the Linux kernel's page cache is a write-back cache for filesystem contents.
-The cached unit is memory-page-sized & aligned chunks of the files that are being cached (typically 4k).
-The cache lives in kernel memory and is not directly accessible through userspace.
-
-**Buffered IO**: an application's read/write system calls go through the kernel page cache.
-For example, a 10 byte sized read or write to offset 5000 in a file will load the file contents
-at offset `[4096,8192)` into a free page in the kernel page cache. If necessary, it will evict
-a page to make room (cf eviction). Then, the kernel performs a memory-to-memory copy of 10 bytes
-from/to the offset `4` (`5000 = 4096 + 4`) within the cached page. If it's a write, the kernel keeps
-track of the fact that the page is now "dirty" in some ancillary structure.
-
-**Writeback**: a buffered read/write syscall returns after the memory-to-memory copy. The modifications
-made by e.g. write system calls are not even *issued* to disk, let alone durable. Instead, the kernel
-asynchronously writes back dirtied pages based on a variety of conditions. For us, the most relevant
-ones are a) explicit request by userspace (`fsync`) and b) memory pressure.
-
-**Memory pressure**: the kernel page cache is a best effort service and a user of spare memory capacity.
-If there is no free memory, the kernel page allocator will take pages used by page cache to satisfy allocations.
-Before reusing a page like that, the page has to be written back (writeback, see above).
-The far-reaching consequence of this is that **any allocation of anonymous memory can do IO** if the only
-way to get that memory is by eviction & re-using a dirty page cache page.
-Notably, this includes a simple `malloc` in userspace, because eventually that boils down to `mmap(..., MAP_ANON, ...)`.
-I refer to this effect as the "malloc latency backscatter" caused by buffered IO.
-
-**Direct IO** allows application's read/write system calls to bypass the kernel page cache. The filesystem
-is still involved because it is ultimately in charge of mapping the concept of files & offsets within them
-to sectors on block devices. Typically, the filesystem poses size and alignment requirements for memory buffers
-and file offsets (statx `Dio_mem_align` / `Dio_offset_align`), see [this gist](https://gist.github.com/problame/1c35cac41b7cd617779f8aae50f97155).
-The IO operations will fail at runtime with EINVAL if the alignment requirements are not met.
-
-**"buffered" vs "direct"**: the central distinction between buffered and direct IO is about who allocates and
-fills the IO buffers, and who controls when exactly the IOs are issued. In buffered IO, it's the syscall handlers,
-kernel page cache, and memory management subsystems (cf "writeback"). In direct IO, all of it is done by
-the application.
-It takes more effort by the application to program with direct instead of buffered IO.
-The return is precise control over and a clear distinction between consumption/modification of memory vs disk.
-
-**Pageserver PageCache**: Pageserver has an additional `PageCache` (referred to as PS PageCache from here on, as opposed to "kernel page cache").
-Its caching unit is 8KiB blocks of the layer files written by Pageserver.
-A miss in PageCache is filled by reading from the filesystem, through the `VirtualFile` abstraction layer.
-The default size is tiny (64MiB), very much like Postgres's `shared_buffers`.
-We ran production at 128MiB for a long time but gradually moved it up to 2GiB over the past ~year.
-
-**VirtualFile** is Pageserver's abstraction for file IO, very similar to the facility in Postgres that bears the same name.
-Its historical purpose appears to be working around open file descriptor limitations, which is practically irrelevant on Linux.
-However, the facility in Pageserver is useful as an intermediary layer for metrics and abstracts over the different kinds of
-IO engines that Pageserver supports (`std-fs` vs `tokio-epoll-uring`).
-
-## Background: History Of Caching In Pageserver
-
-For multiple years, Pageserver's `PageCache` was on the path of all read _and write_ IO.
-It performed write-back to the kernel using buffered IO.
-
-We converted it into a read-only cache of immutable data in [PR 4994](https://github.com/neondatabase/neon/pull/4994).
-
-The introduction of `tokio-epoll-uring` required converting the code base to used owned IO buffers.
-The `PageCache` pages are usable as owned IO buffers.
-
-We then started bypassing PageCache for user data blocks.
-Data blocks are the 8k blocks of data in layer files that hold the multiple `Value`s, as opposed to the disk btree index blocks that tell us which values exist in a file at what offsets.
-The disk btree embedded in delta & image layers remains `PageCache`'d.
-Epics for that work were:
-- Vectored `Timeline::get` (cf RFC 30) skipped delta and image layer data block `PageCache`ing outright.
-- Epic https://github.com/neondatabase/neon/issues/7386 took care of the remaining users for data blocks:
-  - Materialized page cache (cached materialized pages; shown to be ~0% hit rate in practice)
-  - InMemoryLayer
-  - Compaction
-
-The outcome of the above:
-1. All data blocks are always read through the `VirtualFile` APIs, hitting the kernel buffered read path (=> kernel page cache).
-2. Indirect blocks (=disk btree blocks) would be cached in the PS `PageCache`.
-
-In production we size the PS `PageCache` to be 2GiB.
-Thus drives hit rate up to ~99.95% and the eviction rate / replacement rates down to less than 200/second on a 1-minute average, on the busiest machines.
-High baseline replacement rates are treated as a signal of resource exhaustion (page cache insufficient to host working set of the PS).
-The response to this is to migrate tenants away, or increase PS `PageCache` size.
-It is currently manual but could be automated, e.g., in Storage Controller.
-
-In the future, we may eliminate the `PageCache` even for indirect blocks.
-For example with an LRU cache that has as unit the entire disk btree content
-instead of individual blocks.
-
-## High-Level Design
-
-So, before work on this project started, all data block reads and the entire write path of Pageserver were using kernel-buffered IO, i.e., the kernel page cache.
-We now want to get the kernel page cache out of the picture by using direct IO for all interaction with the filesystem.
-This achieves the following system properties:
-
-**Predictable VirtualFile latencies**
-* With buffered IO, reads are sometimes fast, sometimes slow, depending on kernel page cache hit/miss.
-* With buffered IO, appends when writing out new layer files during ingest or compaction are sometimes fast, sometimes slow because of write-back backpressure.
-* With buffered IO, the "malloc backscatter" phenomenon pointed out in the Glossary section is not something we actively observe.
-  But we do have occasional spikes in Dirty memory amount and Memory PSI graphs, so it may already be affecting to some degree.
-* By switching to direct IO, above operations will have the (predictable) device latency -- always.
-  Reads and appends always go to disk.
-  And malloc will not have to write back dirty data.
-
-**Explicitness & Tangibility of resource usage**
-* In a multi-tenant system, it is generally desirable and valuable to be *explicit* about the main resources we use for each tenant.
-* By using direct IO, we become explicit about the resources *disk IOPs*  and *memory capacity* in a way that was previously being conflated through the kernel page cache, outside our immediate control.
-* We will be able to build per-tenant observability of resource usage ("what tenant is causing the actual IOs that are sent to the disk?").
-* We will be able to build accounting & QoS by implementing an IO scheduler that is tenant aware. The kernel is not tenant-aware and can't do that.
-
-**CPU Efficiency**
-* The involvement of the kernel page cache means one additional memory-to-memory copy on read and write path.
-* Direct IO will eliminate that memory-to-memory copy, if we can make the userspace buffers used for the IO calls satisfy direct IO alignment requirements.
-
-The **trade-off** is that we no longer get the theoretical benefits of the kernel page cache. These are:
-- read latency improvements for repeat reads of the same data ("locality of reference")
-  - asterisk: only if that state is still cache-resident by time of next access
-- write throughput by having kernel page cache batch small VFS writes into bigger disk writes
-  - asterisk: only if memory pressure is low enough that the kernel can afford to delay writeback
-
-We are **happy to make this trade-off**:
-- Because of the advantages listed above.
-- Because we empirically have enough DRAM on Pageservers to serve metadata (=index blocks) from PS PageCache.
-  (At just 2GiB PS PageCache size, we average a 99.95% hit rate).
-  So, the latency of going to disk is only for data block reads, not the index traversal.
-- Because **the kernel page cache is ineffective** at high tenant density anyway (#tenants/pageserver instance).
-  And because dense packing of tenants will always be desirable to drive COGS down, we should design the system for it.
-  (See the appendix for a more detailed explanation why this is).
-- So, we accept that some reads that used to be fast by circumstance will have higher but **predictable** latency than before.
-
-### Desired End State
-
-The desired end state of the project is as follows, and with some asterisks, we have achieved it.
-
-All IOs of the Pageserver data path use direct IO, thereby bypassing the kernel page cache.
-
-In particular, the "data path" includes
-- the wal ingest path
-- compaction
-- anything on the `Timeline::get` / `Timeline::get_vectored` path.
-
-The production Pageserver config is tuned such that virtually all non-data blocks are cached in the PS PageCache.
-Hit rate target is 99.95%.
-
-There are no regressions to ingest latency.
-
-The total "wait-for-disk time" contribution to random getpage request latency is `O(1 read IOP latency)`.
-We accomplish that by having a near 100% PS PageCache hit rate so that layer index traversal effectively never needs not wait for IO.
-Thereby, it can issue all the data blocks as it traverses the index, and only wait at the end of it (concurrent IO).
-
-The amortized "wait-for-disk time" contribution of this direct IO proposal to a series of sequential getpage requests is `1/32 * read IOP latency` for each getpage request.
-We accomplish this by server-side batching of up to 32 reads into a single `Timeline::get_vectored` call.
-(This is an ideal world where our batches are full - that's not the case in prod today because of lack of queue depth).
-
-## Design & Implementation
-
-### Prerequisites
-
-A lot of prerequisite work had to happen to enable use of direct IO.
-
-To meet the "wait-for-disk time" requirements from the DoD, we implement for the read path:
-- page_service level server-side batching (config field `page_service_pipelining`)
-- concurrent IO (config field `get_vectored_concurrent_io`)
-The work for both of these these was tracked [in the epic](https://github.com/neondatabase/neon/issues/9376).
-Server-side batching will likely be obsoleted by the [#proj-compute-communicator](https://github.com/neondatabase/neon/pull/10799).
-The Concurrent IO work is described in retroactive RFC `2025-04-30-pageserver-concurrent-io-on-read-path.md`.
-The implementation is relatively brittle and needs further investment, see the `Future Work` section in that RFC.
-
-For the write path, and especially WAL ingest, we need to hide write latency.
-We accomplish this by implementing a (`BufferedWriter`) type that does double-buffering: flushes of the filled
-buffer happen in a sidecar tokio task while new writes fill a new buffer.
-We refactor InMemoryLayer as well as BlobWriter (=> delta and image layer writers) to use this new `BufferedWriter`.
-The most comprehensive write-up of this work is in [the PR description](https://github.com/neondatabase/neon/pull/11558).
-
-### Ensuring Adherence to Alignment Requirements
-
-Direct IO puts requirements on
-- memory buffer alignment
-- io size (=memory buffer size)
-- file offset alignment
-
-The requirements are specific to a combination of filesystem/block-device/architecture(hardware page size!).
-
-In Neon production environments we currently use ext4 with Linux 6.1.X on AWS and Azure storage-optimized instances (locally attached NVMe).
-Instead of dynamic discovery using `statx`, we statically hard-code 512 bytes as the buffer/offset alignment and size-multiple.
-We made this decision because:
-- a) it is compatible with all the environments we need to run in
-- b) our primary workload can be small-random-read-heavy (we do merge adjacent reads if possible, but the worst case is that all `Value`s that needs to be read are far apart)
-- c) 512-byte tail latency on the production instance types is much better than 4k (p99.9: 3x lower, p99.99 5x lower).
-- d) hard-coding at compile-time allows us to use the Rust type system to enforce the use of only aligned IO buffers, eliminating a source of runtime errors typically associated with direct IO.
-
-This was [discussed here](https://neondb.slack.com/archives/C07BZ38E6SD/p1725036790965549?thread_ts=1725026845.455259&cid=C07BZ38E6SD).
-
-The new `IoBufAligned` / `IoBufAlignedMut` marker traits indicate that a given buffer meets memory alignment requirements.
-All `VirtualFile` APIs and several software layers built on top of them only accept buffers that implement those traits.
-Implementors of the marker traits are:
-- `IoBuffer` / `IoBufferMut`: used for most reads and writes
-- `PageWriteGuardBuf`: for filling PS PageCache pages (index blocks!)
-
-The alignment requirement is infectious; it permeates bottom-up throughout the code base.
-We stop the infection at roughly the same layers in the code base where we stopped permeating the
-use of owned-buffers-style API for tokio-epoll-uring. The way the stopping works is by introducing
-a memory-to-memory copy from/to some unaligned memory location on the stack/current/heap.
-The places where we currently stop permeating are sort of arbitrary. For example, it would probably
-make sense to replace more usage of `Bytes` that we know holds 8k pages with 8k-sized `IoBuffer`s.
-
-The `IoBufAligned` / `IoBufAlignedMut` types do not protect us from the following types of runtime errors:
-- non-adherence to file offset alignment requirements
-- non-adherence to io size requirements
-
-The following higher-level constructs ensure we meet the requirements:
-- read path: the `ChunkedVectoredReadBuilder` and `mod vectored_dio_read` ensure reads happen at aligned offsets and in appropriate size multiples.
-- write path: `BufferedWriter` only writes in multiples of the capacity, at offsets that are `start_offset+N*capacity`; see its doc comment.
-
-Note that these types are used always, regardless of whether direct IO is enabled or not.
-There are some cases where this adds unnecessary overhead to buffered IO (e.g. all memcpy's inflated to multiples of 512).
-But we could not identify meaningful impact in practice when we shipped these changes while we were still using buffered IO.
-
-### Configuration / Feature Flagging
-
-In the previous section we described how all users of VirtualFile were changed to always adhere to direct IO alignment and size-multiple requirements.
-To actually enable direct IO, all we need to do is set the `O_DIRECT` flag in `open` syscalls / io_uring operations.
-
-We set `O_DIRECT` based on:
-- the VirtualFile API used to create/open the VirtualFile instance
-- the `virtual_file_io_mode` configuration flag
-- the OpenOptions `read` and/or `write` flags.
-
-The VirtualFile APIs suffixed with `_v2` are the only ones that _may_ open with `O_DIRECT` depending on the other two factors in above list.
-Other APIs never use `O_DIRECT`.
-(The name is bad and should really be `_maybe_direct_io`.)
-
-The reason for having new APIs is because all code used VirtualFile but implementation and rollout happened in consecutive phases (read path, InMemoryLayer, write path).
-At the VirtualFile level, context on whether an instance of VirtualFile is on read path, InMemoryLayer, or write path is not available.
-
-The `_v2` APIs then check make the decision to set `O_DIRECT` based on the `virtual_file_io_mode` flag and the OpenOptions `read`/`write` flags.
-The result is the following runtime behavior:
-
-|what|OpenOptions|`v_f_io_mode`<br/>=`buffered`|`v_f_io_mode`<br/>=`direct`|`v_f_io_mode`<br/>=`direct-rw`|
-|-|-|-|-|-|
-|`DeltaLayerInner`|read|()|O_DIRECT|O_DIRECT|
-|`ImageLayerInner`|read|()|O_DIRECT|O_DIRECT|
-|`InMemoryLayer`|read + write|()|()*|O_DIRECT|
-|`DeltaLayerWriter`| write | () | () |  O_DIRECT |
-|`ImageLayerWriter`| write | () | () |  O_DIRECT |
-|`download_layer_file`|write |()|()|O_DIRECT|
-
-The `InMemoryLayer` is marked with `*` because there was a period when it *did* use O_DIRECT under `=direct`.
-That period was when we implemented and shipped the first version of `BufferedWriter`.
-We used it in `InMemoryLayer` and `download_layer_file` but it was only sensitive to `v_f_io_mode` in `InMemoryLayer`.
-The introduction of `=direct-rw`, and the switch of the remaining write path to `BufferedWriter`, happened later,
-in https://github.com/neondatabase/neon/pull/11558.
-
-Note that this way of feature flagging inside VirtualFile makes it less and less a general purpose POSIX file access abstraction.
-For example, with `=direct-rw` enabled, it is no longer possible to open a `VirtualFile` without `O_DIRECT`. It'll always be set.
-
-## Correctness Validation
-
-The correctness risks with this project were:
-- Memory safety issues in the `IoBuffer` / `IoBufferMut` implementation.
-  These types expose an API that is largely identical to that of the `bytes` crate and/or Vec.
-- Runtime errors (=> downtime / unavailability) because of non-adherence to alignment/size-multiple requirements, resulting in EINVAL on the read path.
-
-We sadly do not have infrastructure to run pageserver under `cargo miri`.
-So for memory safety issues, we relied on careful peer review.
-
-We do assert the production-like alignment requirements in testing builds.
-However, these asserts were added retroactively.
-The actual validation before rollout happened in staging and pre-prod.
-We eventually enabled  `=direct`/`=direct-rw` for Rust unit tests and the regression test suite.
-I cannot recall a single instance of staging/pre-prod/production errors caused by non-adherence to alignment/size-multiple requirements.
-Evidently developer testing was good enough.
-
-## Performance Validation
-
-The read path went through a lot of iterations of benchmarking in staging and pre-prod.
-The benchmarks in those environments demonstrated performance regressions early in the implementation.
-It was actually this performance testing that made us implement batching and concurrent IO to avoid unacceptable regressions.
-
-The write path was much quicker to validate because `bench_ingest` covered all of the (less numerous) access patterns.
-
-## Future Work
-
-There is minor and major follow-up work that can be considered in the future.
-Check the (soon-to-be-closed) Epic https://github.com/neondatabase/neon/issues/8130's "Follow-Ups" section for a current list.
-
-Read Path:
-- PS PageCache hit rate is crucial to unlock concurrent IO and reasonable latency for random reads generally.
-  Instead of reactively sizing PS PageCache, we should estimate the required PS PageCache size
-  and potentially also use that to drive placement decisions of shards from StorageController
-  https://github.com/neondatabase/neon/issues/9288
-- ... unless we get rid of PS PageCache entirely and cache the index block in a more specialized cache.
-  But even then, an estimation of the working set would be helpful to figure out caching strategy.
-
-Write Path:
-- BlobWriter and its users could switch back to a borrowed API  https://github.com/neondatabase/neon/issues/10129
-- ... unless we want to implement bypass mode for large writes https://github.com/neondatabase/neon/issues/10101
-- The `TempVirtualFile` introduced as part of this project could internalize more of the common usage pattern: https://github.com/neondatabase/neon/issues/11692
-- Reduce conditional compilation around `virtual_file_io_mode`: https://github.com/neondatabase/neon/issues/11676
-
-Both:
-- A performance simulation mode that pads VirtualFile op latencies to typical NVMe latencies, even if the underlying storage is faster.
-  This would avoid misleadingly good performance on developer systems and in benchmarks on systems that are less busy than production hosts.
-  However, padding latencies at microsecond scale is non-trivial.
-
-Misc:
-- We should finish trimming VirtualFile's scope to be truly limited to core data path read & write.
-  Abstractions for reading & writing pageserver config, location config, heatmaps, etc, should use
-  APIs in a different package (`VirtualFile::crashsafe_overwrite` and `VirtualFile::read_to_string`
-  are good entrypoints for cleanup.) https://github.com/neondatabase/neon/issues/11809
-
-# Appendix
-
-## Why Kernel Page Cache Is Ineffective At Tenant High Density
-
-In the Motivation section, we stated:
-
-> - **The kernel page cache ineffective** at high tenant density anyways (#tenants/pageserver instance).
-
-The reason is that the  Pageserver workload sent from Computes is whatever is a Compute cache(s) miss.
-That's either sequential scans or random reads.
-A random read workload simply causes cache thrashing because a packed Pageserver NVMe drive (`im4gn.2xlarge`) has ~100x more capacity than DRAM available.
-It is complete waste to have the kernel page cache cache data blocks in this case.
-Sequential read workloads *can* benefit iff those pages have been updated recently (=no image layer yet) and together in time/LSN space.
-In such cases, the WAL records of those updates likely sit on the same delta layer block.
-When Compute does a sequential scan, it sends a series of single-page requests for these individual pages.
-When Pageserver processes the second request in such a series, it goes to the same delta layer block and have a kernel page cache hit.
-This dependence on kernel page cache for sequential scan performance is significant, but the solution is at a higher level than generic data block caching.
-We can either add a small per-connection LRU cache for such delta layer blocks.
-Or we can merge those sequential requests into a larger vectored get request, which is designed to never read a block twice.
-This amortizes the read latency for our delta layer block across the vectored get batch size (which currently is up to 32).
-
-There are Pageserver-internal workloads that do sequential access (compaction, image layer generation), but these
-1. are not latency-critical and can do batched access outside of the `page_service` protocol constraints (image layer generation)
-2. don't actually need to reconstruct images and therefore can use totally different access methods (=> compaction can use k-way merge iterators with their own internal buffering / prefetching).

docs/rfcs/2025-04-30-pageserver-concurrent-io-on-read-path.md

@@ -1,251 +0,0 @@
-# Concurrent IO for Pageserver Read Path
-
-Date: May 6, 2025
-
-## Summary
-
-This document is a retroactive RFC on the Pageserver Concurrent IO work that happened in late 2024 / early 2025.
-
-The gist of it is that Pageserver's `Timeline::get_vectored` now _issues_ the data block read operations against layer files
-_as it traverses the layer map_ and only _wait_ once, for all of them, after traversal is complete.
-
-Assuming a good PS PageCache hits on the index blocks during traversal, this drives down the "wait-for-disk" time
-contribution down from `random_read_io_latency * O(number_of_values)` to `random_read_io_latency * O(1 + traversal)`.
-
-The motivation for why this work had to happen when it happened was the switch of Pageserver to
-- not cache user data blocks in PS PageCache and
-- switch to use direct IO.
-More context on this are given in complimentary RFC `./rfcs/2025-04-30-direct-io-for-pageserver.md`.
-
-### Refs
-
-- Epic: https://github.com/neondatabase/neon/issues/9378
-- Prototyping happened during the Lisbon 2024 Offsite hackathon: https://github.com/neondatabase/neon/pull/9002
-- Main implementation PR with good description: https://github.com/neondatabase/neon/issues/9378
-
-Design and implementation by:
-- Vlad Lazar <vlad@neon.tech>
-- Christian Schwarz <christian@neon.tech>
-
-## Background & Motivation
-
-The Pageserver read path (`Timeline::get_vectored`) consists of two high-level steps:
-- Retrieve the delta and image `Value`s required to reconstruct the requested Page@LSN (`Timeline::get_values_reconstruct_data`).
-- Pass these values to walredo to reconstruct the page images.
-
-The read path used to be single-key but has been made multi-key some time ago.
-([Internal tech talk by Vlad](https://drive.google.com/file/d/1vfY24S869UP8lEUUDHRWKF1AJn8fpWoJ/view?usp=drive_link))
-However, for simplicity, most of this doc will explain things in terms of a single key being requested.
-
-The `Value` retrieval step above can be broken down into the following functions:
-- **Traversal** of the layer map to figure out which `Value`s from which layer files are required for the page reconstruction.
-- **Read IO Planning**: planning of the read IOs that need to be issued to the layer files / filesystem / disk.
-  The main job here is to coalesce the small value reads into larger filesystem-level read operations.
-  This layer also takes care of direct IO alignment and size-multiple requirements (cf the RFC for details.)
-  Check `struct VectoredReadPlanner` and `mod vectored_dio_read` for how it's done.
-- **Perform the read IO** using `tokio-epoll-uring`.
-
-Before this project, above functions were sequentially interleaved, meaning:
-1. we would advance traversal, ...
-2. discover, that we need to read a value, ...
-3. read it from disk using `tokio-epoll-uring`, ...
-4. goto 1 unless we're done.
-
-This meant that if N `Value`s need to be read to reconstruct a page,
-the time we spend waiting for disk will be we `random_read_io_latency * O(number_of_values)`.
-
-## Design
-
-The **traversal** and **read IO Planning** jobs still happen sequentially, layer by layer, as before.
-But instead of performing the read IOs inline, we submit the IOs to a concurrent tokio task for execution.
-After the last read from the last layer is submitted, we wait for the IOs to complete.
-
-Assuming the filesystem / disk is able to actually process the submitted IOs without queuing,
-we arrive at _time spent waiting for disk_ ~ `random_read_io_latency * O(1 + traversal)`.
-
-Note this whole RFC is concerned with the steady state where all layer files required for reconstruction are resident on local NVMe.
-Traversal will stall on on-demand layer download if a layer is not yet resident.
-It cannot proceed without the layer being resident beccause its next step depends on the contents of the layer index.
-
-### Avoiding Waiting For IO During Traversal
-
-The `traversal` component in above time-spent-waiting-for-disk estimation is dominant and needs to be minimized.
-
-Before this project, traversal needed to perform IOs for the following:
-1. The time we are waiting on PS PageCache to page in the visited layers' disk btree index blocks.
-2. When visiting a delta layer, reading the data block that contains a `Value` for a requested key,
-   to determine whether the `Value::will_init` the page and therefore traversal can stop for this key.
-
-The solution for (1) is to raise the PS PageCache size such that the hit rate is practically 100%.
-(Check out the `Background: History Of Caching In Pageserver` section in the RFC on Direct IO for more details.)
-
-The solution for (2) is source `will_init` from the disk btree index keys, which fortunately
-already encode this bit of information since the introduction of the current storage/layer format.
-
-### Concurrent IOs, Submission & Completion
-
-To separate IO submission from waiting for its completion,
-we introduce the notion of an `IoConcurrency` struct through which IOs are issued.
-
-An IO is an opaque future that
-- captures the `tx` side of a `oneshot` channel
-- performs the read IO by calling `VirtualFile::read_exact_at().await`
-- sending the result into the `tx`
-
-Issuing an IO means `Box`ing the future above and handing that `Box` over to the `IoConcurrency` struct.
-
-The traversal code that submits the IO stores the the corresponding `oneshot::Receiver`
-in the `VectoredValueReconstructState`, in the the place where we previously stored
-the sequentially read `img` and `records` fields.
-
-When we're done with traversal, we wait for all submitted IOs:
-for each key, there is a future that awaits all the `oneshot::Receiver`s
-for that key, and then calls into walredo to reconstruct the page image.
-Walredo is now invoked concurrently for each value instead of sequentially.
-Walredo itself remains unchanged.
-
-The spawned IO futures are driven to completion by a sidecar tokio task that
-is separate from the task that performs all the layer visiting and spawning of IOs.
-That tasks receives the IO futures via an unbounded mpsc channel and
-drives them to completion inside a `FuturedUnordered`.
-
-### Error handling, Panics, Cancellation-Safety
-
-There are two error classes during reconstruct data retrieval:
-* traversal errors: index lookup, move to next layer, and the like
-* value read IO errors
-
-A traversal error fails the entire `get_vectored` request, as before this PR.
-A value read error only fails reconstruction of that value.
-
-Panics and dropping of the `get_vectored` future before it completes
-leaves the sidecar task running and does not cancel submitted IOs
-(see next section for details on sidecar task lifecycle).
-All of this is safe, but, today's preference in the team is to close out
-all resource usage explicitly if possible, rather than cancelling + forgetting
-about it on drop. So, there is warning if we drop a
-`VectoredValueReconstructState`/`ValuesReconstructState` that still has uncompleted IOs.
-
-### Sidecar Task Lifecycle
-
-The sidecar tokio task is spawned as part of the `IoConcurrency::spawn_from_conf` struct.
-The `IoConcurrency` object acts as a handle through which IO futures are submitted.
-
-The spawned tokio task holds the `Timeline::gate` open.
-It is _not_ sensitive to `Timeline::cancel`, but instead to the `IoConcurrency` object being dropped.
-
-Once the `IoConcurrency` struct is dropped, no new IO futures can come in
-but already submitted IO futures will be driven to completion regardless.
-We _could_ safely stop polling these futures because `tokio-epoll-uring` op futures are cancel-safe.
-But the underlying kernel and hardware resources are not magically freed up by that.
-So, again, in the interest of closing out all outstanding resource usage, we make timeline shutdown wait for sidecar tasks and their IOs to complete.
-Under normal conditions, this should be in the low hundreds of microseconds.
-
-It is advisable to make the `IoConcurrency` as long-lived as possible to minimize the amount of
-tokio task churn (=> lower pressure on tokio). Generally this means creating it "high up" in the call stack.
-The pain with this is that the `IoConcurrency` reference needs to be propagated "down" to
-the (short-lived) functions/scope where we issue the IOs.
-We would like to use `RequestContext` for this propagation in the future (issue [here](https://github.com/neondatabase/neon/issues/10460)).
-For now, we just add another argument to the relevant code paths.
-
-### Feature Gating
-
-The `IoConcurrency` is an `enum` with two variants: `Sequential` and `SidecarTask`.
-
-The behavior from before this project is available through `IoConcurrency::Sequential`,
-which awaits the IO futures in place, without "spawning" or "submitting" them anywhere.
-
-The `get_vectored_concurrent_io` pageserver config variable determines the runtime value,
-**except** for the places that use `IoConcurrency::sequential` to get an `IoConcurrency` object.
-
-### Alternatives Explored & Caveats Encountered
-
-A few words on the rationale behind having a sidecar *task* and what
-alternatives were considered but abandoned.
-
-#### Why We Need A Sidecar *Task* / Why Just `FuturesUnordered` Doesn't Work
-
-We explored to not have a sidecar task, and instead have a `FuturesUnordered` per
-`Timeline::get_vectored`. We would queue all IO futures in it and poll it for the
-first time after traversal is complete (i.e., at `collect_pending_ios`).
-
-The obvious disadvantage, but not showstopper, is that we wouldn't be submitting
-IOs until traversal is complete.
-
-The showstopper however, is that deadlocks happen if we don't drive the
-IO futures to completion independently of the traversal task.
-The reason is that both the IO futures and the traversal task may hold _some_,
-_and_ try to acquire _more_, shared limited resources.
-For example, both the travseral task and IO future may try to acquire
-* a `VirtualFile` file descriptor cache slot async mutex (observed during impl)
-* a `tokio-epoll-uring` submission slot (observed during impl)
-* a `PageCache` slot (currently this is not the case but we may move more code into the IO futures in the future)
-
-#### Why We Don't Do `tokio::task`-per-IO-future
-
-Another option is to spawn a short-lived `tokio::task` for each IO future.
-We implemented and benchmarked it during development, but found little
-throughput improvement and moderate mean & tail latency degradation.
-Concerns about pressure on the tokio scheduler led us to abandon this variant.
-
-## Future Work
-
-In addition to what is listed here, also check the "Punted" list in the epic:
-https://github.com/neondatabase/neon/issues/9378
-
-### Enable `Timeline::get`
-
-The only major code path that still uses `IoConcurrency::sequential` is `Timeline::get`.
-The impact is that roughly the following parts of pageserver do not benefit yet:
-- parts of basebackup
-- reads performed by the ingest path
-- most internal operations that read metadata keys (e.g. `collect_keyspace`!)
-
-The solution is to propagate `IoConcurrency` via `RequestContext`:https://github.com/neondatabase/neon/issues/10460
-
-The tricky part is to figure out at which level of the code the `IoConcurrency` is spawned (and added to the RequestContext).
-
-Also, propagation via `RequestContext` makes makes it harder to tell during development whether a given
-piece of code uses concurrent vs sequential mode: one has to recurisvely walk up the call tree to find the
-place that puts the `IoConcurrency` into the `RequestContext`.
-We'd have to use `::Sequential` as the conservative default value in a fresh `RequestContext`, and add some
-observability to weed out places that fail to enrich with a properly spanwed `IoConcurrency::spawn_from_conf`.
-
-### Concurrent On-Demand Downloads enabled by Detached Indices
-
-As stated earlier, traversal stalls on on-demand download because its next step depends on the contents of the layer index.
-Once we have separated indices from data blocks (=> https://github.com/neondatabase/neon/issues/11695)
-we will only need to stall if the index is not resident. The download of the data blocks can happen concurrently or in the background. For example:
-- Move the `Layer::get_or_maybe_download().await` inside the IO futures.
-  This goes in the opposite direction of the next "future work" item below, but it's easy to do.
-- Serve the IO future directly from object storage and dispatch the layer download
-  to some other actor, e.g., an actor that is responsible for both downloads & eviction.
-
-### New `tokio-epoll-uring` API That Separates Submission & Wait-For-Completion
-
-Instead of `$op().await` style API, it would be useful to have a different `tokio-epoll-uring` API
-that separates enqueuing (without necessarily `io_uring_enter`ing the kernel each time), submission,
-and then wait for completion.
-
-The `$op().await` API is too opaque, so we _have_ to stuff it into a `FuturesUnordered`.
-
-A split API as sketched above would allow traversal to ensure an IO operation is enqueued to the kernel/disk (and get back-pressure iff the io_uring squeue is full).
-While avoiding spending of CPU cycles on processing of completions while we're still traversing.
-
-The idea gets muddied by the fact that we may self-deadlock if we submit too much without completing.
-So, the submission part of the split API needs to process completions if squeue is full.
-
-In any way, this split API is precondition for the bigger issue with the design presented here,
-which we dicsuss in the next section.
-
-### Opaque Futures Are Brittle
-
-The use of opaque futures to represent submitted IOs is a clever hack to minimize changes & allow for near-perfect feature-gating.
-However, we take on **brittleness** because callers must guarantee that the submitted futures are independent.
-By our experience, it is non-trivial to identify or rule out the interdependencies.
-See the lengthy doc comment on the `IoConcurrency::spawn_io` method for more details.
-
-The better interface and proper subsystem boundary is a _descriptive_ struct of what needs to be done ("read this range from this VirtualFile into this buffer")
-and get back a means to wait for completion.
-The subsystem can thereby reason by its own how operations may be related;
-unlike today, where the submitted opaque future can do just about anything.

docs/rfcs/images/036-bottom-most-gc-compaction/01-basic-idea.svg

@@ -1,135 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" standalone="no"?>
-<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
-<svg xmlns="http://www.w3.org/2000/svg" xmlns:xl="http://www.w3.org/1999/xlink" xmlns:dc="http://purl.org/dc/elements/1.1/" version="1.1" viewBox="82 284 863 375" width="863" height="375">
-  <defs/>
-  <g id="01-basic-idea" stroke-opacity="1" stroke-dasharray="none" stroke="none" fill="none" fill-opacity="1">
-    <title>01-basic-idea</title>
-    <rect fill="white" x="82" y="284" width="863" height="375"/>
-    <g id="01-basic-idea_Layer_1">
-      <title>Layer 1</title>
-      <g id="Graphic_2">
-        <rect x="234" y="379.5" width="203.5" height="17.5" fill="white"/>
-        <rect x="234" y="379.5" width="203.5" height="17.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_3">
-        <rect x="453.5" y="379.5" width="203.5" height="17.5" fill="white"/>
-        <rect x="453.5" y="379.5" width="203.5" height="17.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_4">
-        <rect x="672.5" y="379.5" width="203.5" height="17.5" fill="white"/>
-        <rect x="672.5" y="379.5" width="203.5" height="17.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_5">
-        <rect x="234" y="288.5" width="127" height="77.5" fill="white"/>
-        <rect x="234" y="288.5" width="127" height="77.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_6">
-        <rect x="375" y="288.5" width="127" height="77.5" fill="white"/>
-        <rect x="375" y="288.5" width="127" height="77.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_7">
-        <rect x="516" y="288.5" width="127" height="77.5" fill="white"/>
-        <rect x="516" y="288.5" width="127" height="77.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_8">
-        <rect x="657" y="288.5" width="127" height="77.5" fill="white"/>
-        <rect x="657" y="288.5" width="127" height="77.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_9">
-        <rect x="798" y="288.5" width="78" height="77.5" fill="white"/>
-        <rect x="798" y="288.5" width="78" height="77.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Line_11">
-        <line x1="185.5" y1="326.75" x2="943.7734" y2="326.75" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_12">
-        <text transform="translate(87 318.026)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="0" y="15" xml:space="preserve">GC Horizon</tspan>
-        </text>
-      </g>
-      <g id="Graphic_13">
-        <text transform="translate(106.41 372.886)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="8.39" y="15" xml:space="preserve">Images </tspan>
-          <tspan font-family="Helvetica Neue" font-size="10" fill="black" x="29132252e-19" y="28.447998" xml:space="preserve">at earlier LSN</tspan>
-        </text>
-      </g>
-      <g id="Graphic_14">
-        <text transform="translate(121.92 289.578)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="8739676e-19" y="15" xml:space="preserve">Deltas</tspan>
-        </text>
-      </g>
-      <g id="Graphic_15">
-        <path d="M 517.125 423.5 L 553.375 423.5 L 553.375 482 L 571.5 482 L 535.25 512 L 499 482 L 517.125 482 Z" fill="white"/>
-        <path d="M 517.125 423.5 L 553.375 423.5 L 553.375 482 L 571.5 482 L 535.25 512 L 499 482 L 517.125 482 Z" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_26">
-        <rect x="234" y="599.474" width="203.5" height="17.5" fill="white"/>
-        <rect x="234" y="599.474" width="203.5" height="17.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_25">
-        <rect x="453.5" y="599.474" width="203.5" height="17.5" fill="white"/>
-        <rect x="453.5" y="599.474" width="203.5" height="17.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_24">
-        <rect x="672.5" y="599.474" width="203.5" height="17.5" fill="white"/>
-        <rect x="672.5" y="599.474" width="203.5" height="17.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_23">
-        <rect x="234" y="533" width="127" height="52.974" fill="white"/>
-        <rect x="234" y="533" width="127" height="52.974" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_22">
-        <rect x="375" y="533" width="310.5" height="52.974" fill="white"/>
-        <rect x="375" y="533" width="310.5" height="52.974" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_21">
-        <rect x="702.5" y="533" width="173.5" height="52.974" fill="white"/>
-        <rect x="702.5" y="533" width="173.5" height="52.974" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Line_18">
-        <line x1="185.5" y1="607.724" x2="943.7734" y2="607.724" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_16">
-        <text transform="translate(121.92 538)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="8739676e-19" y="15" xml:space="preserve">Deltas</tspan>
-        </text>
-      </g>
-      <g id="Graphic_27">
-        <text transform="translate(114.8 592.86)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="3488765e-18" y="15" xml:space="preserve">Images </tspan>
-          <tspan font-family="Helvetica Neue" font-size="10" fill="black" x="4.01" y="28.447998" xml:space="preserve">at GC LSN</tspan>
-        </text>
-      </g>
-      <g id="Graphic_28">
-        <rect x="243.06836" y="300" width="624.3633" height="17.5" fill="#c0ffc0"/>
-        <text transform="translate(248.06836 301.068)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="13" fill="black" x="233.52364" y="12" xml:space="preserve">Deltas above GC Horizon</tspan>
-        </text>
-      </g>
-      <g id="Graphic_30">
-        <rect x="243.06836" y="335.5" width="624.3633" height="17.5" fill="#c0ffff"/>
-        <text transform="translate(248.06836 336.568)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="13" fill="black" x="233.89414" y="12" xml:space="preserve">Deltas below GC Horizon</tspan>
-        </text>
-      </g>
-      <g id="Graphic_32">
-        <rect x="243.06836" y="550.737" width="624.3633" height="17.5" fill="#c0ffc0"/>
-        <text transform="translate(248.06836 551.805)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="13" fill="black" x="233.52364" y="12" xml:space="preserve">Deltas above GC Horizon</tspan>
-        </text>
-      </g>
-      <g id="Graphic_33">
-        <rect x="304" y="630.474" width="485.5" height="28.447998" fill="#c0ffff"/>
-        <text transform="translate(309 637.016)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="13" fill="black" x="63.095" y="12" xml:space="preserve">Deltas and image below GC Horizon gets garbage-collected</tspan>
-        </text>
-      </g>
-      <g id="Graphic_34">
-        <text transform="translate(576.5 444.0325)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="12" fill="black" x="0" y="11" xml:space="preserve">WAL replay of deltas+image below GC Horizon</tspan>
-          <tspan font-family="Helvetica Neue" font-size="12" fill="black" x="0" y="25.336" xml:space="preserve">Reshuffle deltas</tspan>
-        </text>
-      </g>
-    </g>
-  </g>
-</svg>

docs/rfcs/images/036-bottom-most-gc-compaction/03-retain-lsn.svg

@@ -1,141 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" standalone="no"?>
-<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
-<svg xmlns="http://www.w3.org/2000/svg" xmlns:xl="http://www.w3.org/1999/xlink" xmlns:dc="http://purl.org/dc/elements/1.1/" version="1.1" viewBox="-104 215 863 335" width="863" height="335">
-  <defs>
-    <marker orient="auto" overflow="visible" markerUnits="strokeWidth" id="FilledArrow_Marker" stroke-linejoin="miter" stroke-miterlimit="10" viewBox="-1 -4 10 8" markerWidth="10" markerHeight="8" color="#7f8080">
-      <g>
-        <path d="M 8 0 L 0 -3 L 0 3 Z" fill="currentColor" stroke="currentColor" stroke-width="1"/>
-      </g>
-    </marker>
-  </defs>
-  <g id="03-retain-lsn" stroke-opacity="1" stroke-dasharray="none" stroke="none" fill="none" fill-opacity="1">
-    <title>03-retain-lsn</title>
-    <rect fill="white" x="-104" y="215" width="863" height="335"/>
-    <g id="03-retain-lsn_Layer_1">
-      <title>Layer 1</title>
-      <g id="Graphic_28">
-        <rect x="48" y="477" width="203.5" height="9.990005" fill="white"/>
-        <rect x="48" y="477" width="203.5" height="9.990005" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_27">
-        <rect x="267.5" y="477" width="203.5" height="9.990005" fill="white"/>
-        <rect x="267.5" y="477" width="203.5" height="9.990005" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_26">
-        <rect x="486.5" y="477" width="203.5" height="9.990005" fill="white"/>
-        <rect x="486.5" y="477" width="203.5" height="9.990005" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Line_20">
-        <line x1="-.5" y1="387.172" x2="757.7734" y2="387.172" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_19">
-        <text transform="translate(-99 378.448)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="0" y="15" xml:space="preserve">GC Horizon</tspan>
-        </text>
-      </g>
-      <g id="Graphic_31">
-        <rect x="48.25" y="410" width="203.5" height="9.990005" fill="white"/>
-        <rect x="48.25" y="410" width="203.5" height="9.990005" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_30">
-        <rect x="267.75" y="410" width="203.5" height="9.990005" fill="white"/>
-        <rect x="267.75" y="410" width="203.5" height="9.990005" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_29">
-        <rect x="486.75" y="410" width="203.5" height="9.990005" fill="white"/>
-        <rect x="486.75" y="410" width="203.5" height="9.990005" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_34">
-        <rect x="48.25" y="431.495" width="113.75" height="34" fill="white"/>
-        <rect x="48.25" y="431.495" width="113.75" height="34" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_33">
-        <rect x="172.5" y="431.495" width="203.5" height="34" fill="white"/>
-        <rect x="172.5" y="431.495" width="203.5" height="34" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_32">
-        <rect x="386.5" y="431.495" width="303.5" height="34" fill="white"/>
-        <rect x="386.5" y="431.495" width="303.5" height="34" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_37">
-        <rect x="48" y="498.495" width="203.5" height="9.990005" fill="white"/>
-        <rect x="48" y="498.495" width="203.5" height="9.990005" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_36">
-        <rect x="267.5" y="498.495" width="203.5" height="9.990005" fill="white"/>
-        <rect x="267.5" y="498.495" width="203.5" height="9.990005" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_35">
-        <rect x="486.5" y="498.495" width="203.5" height="9.990005" fill="white"/>
-        <rect x="486.5" y="498.495" width="203.5" height="9.990005" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Line_38">
-        <line x1="-10.48" y1="535.5395" x2="39.318294" y2="508.24794" marker-end="url(#FilledArrow_Marker)" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_39">
-        <text transform="translate(-96.984 526.3155)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="40500936e-20" y="15" xml:space="preserve">retain_lsn 1</tspan>
-        </text>
-      </g>
-      <g id="Line_41">
-        <line x1="-10.48" y1="507.0915" x2="38.90236" y2="485.8992" marker-end="url(#FilledArrow_Marker)" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_40">
-        <text transform="translate(-96.984 497.8675)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="40500936e-20" y="15" xml:space="preserve">retain_lsn 2</tspan>
-        </text>
-      </g>
-      <g id="Line_43">
-        <line x1="-10.48" y1="478.6435" x2="39.44267" y2="453.01616" marker-end="url(#FilledArrow_Marker)" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_42">
-        <text transform="translate(-96.984 469.4195)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="40500936e-20" y="15" xml:space="preserve">retain_lsn 3</tspan>
-        </text>
-      </g>
-      <g id="Line_45">
-        <line x1="-10.48" y1="448.495" x2="39.65061" y2="419.90015" marker-end="url(#FilledArrow_Marker)" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_44">
-        <text transform="translate(-96.984 439.271)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="40500936e-20" y="15" xml:space="preserve">retain_lsn 4</tspan>
-        </text>
-      </g>
-      <g id="Graphic_46">
-        <rect x="335.46477" y="215.5" width="353.4299" height="125.495" fill="white"/>
-        <rect x="335.46477" y="215.5" width="353.4299" height="125.495" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_48">
-        <text transform="translate(549.3766 317.547)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="6536993e-19" y="15" xml:space="preserve">Dependent Branch</tspan>
-        </text>
-      </g>
-      <g id="Graphic_50">
-        <text transform="translate(340.43824 317.547)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="40500936e-20" y="15" xml:space="preserve">retain_lsn 3</tspan>
-        </text>
-      </g>
-      <g id="Line_57">
-        <line x1="323.90685" y1="248.8045" x2="714.9232" y2="248.8045" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_56">
-        <text transform="translate(165.91346 240.0805)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="35811354e-19" y="15" xml:space="preserve">Branch GC Horizon</tspan>
-        </text>
-      </g>
-      <g id="Graphic_58">
-        <rect x="493.9232" y="301.6405" width="107.45294" height="9.990005" fill="white"/>
-        <rect x="493.9232" y="301.6405" width="107.45294" height="9.990005" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_59">
-        <text transform="translate(358.9232 277.276)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="0" y="15" xml:space="preserve">Partial Image Coverage</tspan>
-        </text>
-      </g>
-      <g id="Graphic_60">
-        <rect x="354.1732" y="301.6405" width="107.45294" height="9.990005" fill="white"/>
-        <rect x="354.1732" y="301.6405" width="107.45294" height="9.990005" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-    </g>
-  </g>
-</svg>