fix accidental recursion

.cargo/config.toml

@@ -3,16 +3,6 @@
 # by the RUSTDOCFLAGS env var in CI.
 rustdocflags = ["-Arustdoc::private_intra_doc_links"]
 
-# Enable frame pointers. This may have a minor performance overhead, but makes it easier and more
-# efficient to obtain stack traces (and thus CPU/heap profiles). It may also avoid seg faults that
-# we've seen with libunwind-based profiling. See also:
-#
-# * <https://www.brendangregg.com/blog/2024-03-17/the-return-of-the-frame-pointers.html>
-# * <https://github.com/rust-lang/rust/pull/122646>
-#
-# NB: the RUSTFLAGS envvar will replace this. Make sure to update e.g. Dockerfile as well.
-rustflags = ["-Cforce-frame-pointers=yes"]
-
 [alias]
 build_testing = ["build", "--features", "testing"]
 neon = ["run", "--bin", "neon_local"]

.github/actionlint.yml

@@ -21,7 +21,3 @@ config-variables:
   - SLACK_UPCOMING_RELEASE_CHANNEL_ID
   - DEV_AWS_OIDC_ROLE_ARN
   - BENCHMARK_INGEST_TARGET_PROJECTID
-  - PGREGRESS_PG16_PROJECT_ID
-  - PGREGRESS_PG17_PROJECT_ID
-  - SLACK_ON_CALL_QA_STAGING_STREAM
-  - DEV_AWS_OIDC_ROLE_MANAGE_BENCHMARK_EC2_VMS_ARN

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

@@ -7,9 +7,10 @@ inputs:
     type: boolean
     required: false
     default: false
-  aws-oicd-role-arn:
+  aws_oicd_role_arn:
-    description: 'OIDC role arn to interract with S3'
+    description: 'the OIDC role arn to (re-)acquire for allure report upload - if not set call must acquire OIDC role'
-    required: true
+    required: false
+    default: ''
 
 outputs:
   base-url:
@@ -83,11 +84,12 @@ runs:
         ALLURE_VERSION: 2.27.0
         ALLURE_ZIP_SHA256: b071858fb2fa542c65d8f152c5c40d26267b2dfb74df1f1608a589ecca38e777
 
-    - uses: aws-actions/configure-aws-credentials@v4
+    - name: (Re-)configure AWS credentials # necessary to upload reports to S3 after a long-running test
-      if: ${{ !cancelled() }}
+      if: ${{ !cancelled() && (inputs.aws_oicd_role_arn != '') }}
+      uses: aws-actions/configure-aws-credentials@v4
       with:
         aws-region: eu-central-1
-        role-to-assume: ${{ inputs.aws-oicd-role-arn }}
+        role-to-assume: ${{ inputs.aws_oicd_role_arn }}
         role-duration-seconds: 3600 # 1 hour should be more than enough to upload report
 
     # Potentially we could have several running build for the same key (for example, for the main branch), so we use improvised lock for this

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

@@ -8,9 +8,10 @@ inputs:
   unique-key:
     description: 'string to distinguish different results in the same run'
     required: true
-  aws-oicd-role-arn:
+  aws_oicd_role_arn:
-    description: 'OIDC role arn to interract with S3'
+    description: 'the OIDC role arn to (re-)acquire for allure report upload - if not set call must acquire OIDC role'
-    required: true
+    required: false
+    default: ''
 
 runs:
   using: "composite"
@@ -35,11 +36,12 @@ runs:
       env:
         REPORT_DIR: ${{ inputs.report-dir }}
 
-    - uses: aws-actions/configure-aws-credentials@v4
+    - name: (Re-)configure AWS credentials # necessary to upload reports to S3 after a long-running test
-      if: ${{ !cancelled() }}
+      if: ${{ !cancelled() && (inputs.aws_oicd_role_arn != '') }}
+      uses: aws-actions/configure-aws-credentials@v4
       with:
         aws-region: eu-central-1
-        role-to-assume: ${{ inputs.aws-oicd-role-arn }}
+        role-to-assume: ${{ inputs.aws_oicd_role_arn }}
         role-duration-seconds: 3600 # 1 hour should be more than enough to upload report
 
     - name: Upload test results

.github/actions/download/action.yml

@@ -15,19 +15,10 @@ inputs:
   prefix:
     description: "S3 prefix. Default is '${GITHUB_RUN_ID}/${GITHUB_RUN_ATTEMPT}'"
     required: false
-  aws-oicd-role-arn:
-    description: 'OIDC role arn to interract with S3'
-    required: true
 
 runs:
   using: "composite"
   steps:
-    - uses: aws-actions/configure-aws-credentials@v4
-      with:
-        aws-region: eu-central-1
-        role-to-assume: ${{ inputs.aws-oicd-role-arn }}
-        role-duration-seconds: 3600
-
     - name: Download artifact
       id: download-artifact
       shell: bash -euxo pipefail {0}

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

@@ -48,9 +48,10 @@ inputs:
     description: 'benchmark durations JSON'
     required: false
     default: '{}'
-  aws-oicd-role-arn:
+  aws_oicd_role_arn:
-    description: 'OIDC role arn to interract with S3'
+    description: 'the OIDC role arn to (re-)acquire for allure report upload - if not set call must acquire OIDC role'
-    required: true
+    required: false
+    default: ''
 
 runs:
   using: "composite"
@@ -61,7 +62,6 @@ runs:
       with:
         name: neon-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build_type }}-artifact
         path: /tmp/neon
-        aws-oicd-role-arn: ${{ inputs.aws-oicd-role-arn }}
 
     - name: Download Neon binaries for the previous release
       if: inputs.build_type != 'remote'
@@ -70,7 +70,6 @@ runs:
         name: neon-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build_type }}-artifact
         path: /tmp/neon-previous
         prefix: latest
-        aws-oicd-role-arn: ${{ inputs.aws-oicd-role-arn }}
 
     - name: Download compatibility snapshot
       if: inputs.build_type != 'remote'
@@ -82,7 +81,6 @@ runs:
         # The lack of compatibility snapshot (for example, for the new Postgres version)
         # shouldn't fail the whole job. Only relevant test should fail.
         skip-if-does-not-exist: true
-        aws-oicd-role-arn: ${{ inputs.aws-oicd-role-arn }}
 
     - name: Checkout
       if: inputs.needs_postgres_source == 'true'
@@ -220,19 +218,17 @@ runs:
         # 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
-        aws-oicd-role-arn: ${{ inputs.aws-oicd-role-arn }}
 
-    - uses: aws-actions/configure-aws-credentials@v4
+    - name: (Re-)configure AWS credentials # necessary to upload reports to S3 after a long-running test
-      if: ${{ !cancelled() }}
+      if: ${{ !cancelled() && (inputs.aws_oicd_role_arn != '') }}
+      uses: aws-actions/configure-aws-credentials@v4
       with:
         aws-region: eu-central-1
-        role-to-assume: ${{ inputs.aws-oicd-role-arn }}
+        role-to-assume: ${{ inputs.aws_oicd_role_arn }}
         role-duration-seconds: 3600 # 1 hour should be more than enough to upload report
-
     - name: Upload test results
       if: ${{ !cancelled() }}
       uses: ./.github/actions/allure-report-store
       with:
         report-dir: /tmp/test_output/allure/results
         unique-key: ${{ inputs.build_type }}-${{ inputs.pg_version }}
-        aws-oicd-role-arn: ${{ inputs.aws-oicd-role-arn }}

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

@@ -14,11 +14,9 @@ runs:
         name: coverage-data-artifact
         path: /tmp/coverage
         skip-if-does-not-exist: true # skip if there's no previous coverage to download
-        aws-oicd-role-arn: ${{ inputs.aws-oicd-role-arn }}
 
     - name: Upload coverage data
       uses: ./.github/actions/upload
       with:
         name: coverage-data-artifact
         path: /tmp/coverage
-        aws-oicd-role-arn: ${{ inputs.aws-oicd-role-arn }}

.github/actions/upload/action.yml

@@ -14,10 +14,6 @@ inputs:
   prefix:
     description: "S3 prefix. Default is '${GITHUB_SHA}/${GITHUB_RUN_ID}/${GITHUB_RUN_ATTEMPT}'"
     required: false
-  aws-oicd-role-arn:
-    description: "the OIDC role arn for aws auth"
-    required: false
-    default: ""
 
 runs:
   using: "composite"
@@ -57,13 +53,6 @@ runs:
 
         echo 'SKIPPED=false' >> $GITHUB_OUTPUT
 
-    - name: Configure AWS credentials
-      uses: aws-actions/configure-aws-credentials@v4
-      with:
-        aws-region: eu-central-1
-        role-to-assume: ${{ inputs.aws-oicd-role-arn }}
-        role-duration-seconds: 3600
-
     - name: Upload artifact
       if: ${{ steps.prepare-artifact.outputs.SKIPPED == 'false' }}
       shell: bash -euxo pipefail {0}

.github/file-filters.yaml

@@ -1,12 +0,0 @@
-rust_code: ['**/*.rs', '**/Cargo.toml', '**/Cargo.lock']
-
-v14: ['vendor/postgres-v14/**', 'Makefile', 'pgxn/**']
-v15: ['vendor/postgres-v15/**', 'Makefile', 'pgxn/**']
-v16: ['vendor/postgres-v16/**', 'Makefile', 'pgxn/**']
-v17: ['vendor/postgres-v17/**', 'Makefile', 'pgxn/**']
-
-rebuild_neon_extra:
-    - .github/workflows/neon_extra_builds.yml
-
-rebuild_macos:
-    - .github/workflows/build-macos.yml

.github/workflows/_benchmarking_preparation.yml

@@ -70,7 +70,6 @@ jobs:
         name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
         path: /tmp/neon/
         prefix: latest
-        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
     # we create a table that has one row for each database that we want to restore with the status whether the restore is done
     - name: Create benchmark_restore_status table if it does not exist

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

@@ -31,13 +31,12 @@ defaults:
 env:
   RUST_BACKTRACE: 1
   COPT: '-Werror'
+  AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_DEV }}
+  AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_KEY_DEV }}
 
 jobs:
   build-neon:
     runs-on: ${{ fromJson(format('["self-hosted", "{0}"]', inputs.arch == 'arm64' && 'large-arm64' || 'large')) }}
-    permissions:
-      id-token: write # aws-actions/configure-aws-credentials
-      contents: read
     container:
       image: ${{ inputs.build-tools-image }}
       credentials:
@@ -206,13 +205,6 @@ jobs:
             done
           fi
 
-      - name: Configure AWS credentials
-        uses: aws-actions/configure-aws-credentials@v4
-        with:
-          aws-region: eu-central-1
-          role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
-          role-duration-seconds: 18000 # 5 hours
-
       - name: Run rust tests
         env:
           NEXTEST_RETRIES: 3
@@ -264,7 +256,6 @@ jobs:
         with:
           name: neon-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-artifact
           path: /tmp/neon
-          aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
       # XXX: keep this after the binaries.list is formed, so the coverage can properly work later
       - name: Merge and upload coverage data
@@ -274,10 +265,6 @@ jobs:
   regress-tests:
     # Don't run regression tests on debug arm64 builds
     if: inputs.build-type != 'debug' || inputs.arch != 'arm64'
-    permissions:
-      id-token: write # aws-actions/configure-aws-credentials
-      contents: read
-      statuses: write
     needs: [ build-neon ]
     runs-on: ${{ fromJson(format('["self-hosted", "{0}"]', inputs.arch == 'arm64' && 'large-arm64' || 'large')) }}
     container:
@@ -296,7 +283,7 @@ jobs:
           submodules: true
 
       - name: Pytest regression tests
-        continue-on-error: ${{ matrix.lfc_state == 'with-lfc' && inputs.build-type == 'debug' }}
+        continue-on-error: ${{ matrix.lfc_state == 'with-lfc' }}
         uses: ./.github/actions/run-python-test-set
         timeout-minutes: 60
         with:
@@ -308,7 +295,6 @@ jobs:
           real_s3_region: eu-central-1
           rerun_failed: true
           pg_version: ${{ matrix.pg_version }}
-          aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
         env:
           TEST_RESULT_CONNSTR: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}
           CHECK_ONDISK_DATA_COMPATIBILITY: nonempty

.github/workflows/actionlint.yml

@@ -33,7 +33,7 @@ jobs:
           # SC2086 - Double quote to prevent globbing and word splitting. - https://www.shellcheck.net/wiki/SC2086
           SHELLCHECK_OPTS: --exclude=SC2046,SC2086
         with:
-          fail_level: error
+          fail_on_error: true
           filter_mode: nofilter
           level: error
 

.github/workflows/benchmarking.yml

@@ -105,7 +105,6 @@ jobs:
         name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
         path: /tmp/neon/
         prefix: latest
-        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
     - name: Create Neon Project
       id: create-neon-project
@@ -123,7 +122,7 @@ jobs:
         run_in_parallel: false
         save_perf_report: ${{ env.SAVE_PERF_REPORT }}
         pg_version: ${{ env.DEFAULT_PG_VERSION }}
-        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
         # Set --sparse-ordering option of pytest-order plugin
         # to ensure tests are running in order of appears in the file.
         # It's important for test_perf_pgbench.py::test_pgbench_remote_* tests
@@ -153,7 +152,7 @@ jobs:
       if: ${{ !cancelled() }}
       uses: ./.github/actions/allure-report-generate
       with:
-        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
     - name: Post to a Slack channel
       if: ${{ github.event.schedule && failure() }}
@@ -205,7 +204,6 @@ jobs:
         name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
         path: /tmp/neon/
         prefix: latest
-        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
     - name: Run Logical Replication benchmarks
       uses: ./.github/actions/run-python-test-set
@@ -216,7 +214,7 @@ jobs:
         save_perf_report: ${{ env.SAVE_PERF_REPORT }}
         extra_params: -m remote_cluster --timeout 5400
         pg_version: ${{ env.DEFAULT_PG_VERSION }}
-        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
       env:
         VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
         PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
@@ -233,7 +231,7 @@ jobs:
         save_perf_report: ${{ env.SAVE_PERF_REPORT }}
         extra_params: -m remote_cluster --timeout 5400
         pg_version: ${{ env.DEFAULT_PG_VERSION }}
-        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
       env:
         VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
         PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
@@ -245,7 +243,7 @@ jobs:
       uses: ./.github/actions/allure-report-generate
       with:
         store-test-results-into-db: true
-        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
       env:
         REGRESS_TEST_RESULT_CONNSTR_NEW: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}
 
@@ -308,7 +306,6 @@ jobs:
           "image": [ "'"$image_default"'" ],
           "include": [{ "pg_version": 16, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-freetier",       "db_size": "3gb" ,"runner": '"$runner_default"', "image": "'"$image_default"'" },
                       { "pg_version": 16, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-new",            "db_size": "10gb","runner": '"$runner_default"', "image": "'"$image_default"'" },
-                      { "pg_version": 16, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-new-many-tables","db_size": "10gb","runner": '"$runner_default"', "image": "'"$image_default"'" },
                       { "pg_version": 16, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-new",            "db_size": "50gb","runner": '"$runner_default"', "image": "'"$image_default"'" },
                       { "pg_version": 16, "region_id": "azure-eastus2",          "platform": "neonvm-azure-captest-freetier", "db_size": "3gb" ,"runner": '"$runner_azure"',   "image": "neondatabase/build-tools:pinned-bookworm" },
                       { "pg_version": 16, "region_id": "azure-eastus2",          "platform": "neonvm-azure-captest-new",      "db_size": "10gb","runner": '"$runner_azure"',   "image": "neondatabase/build-tools:pinned-bookworm" },
@@ -408,10 +405,9 @@ jobs:
         name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
         path: /tmp/neon/
         prefix: latest
-        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
     - name: Create Neon Project
-      if: contains(fromJson('["neonvm-captest-new", "neonvm-captest-new-many-tables", "neonvm-captest-freetier", "neonvm-azure-captest-freetier", "neonvm-azure-captest-new"]'), matrix.platform)
+      if: contains(fromJson('["neonvm-captest-new", "neonvm-captest-freetier", "neonvm-azure-captest-freetier", "neonvm-azure-captest-new"]'), matrix.platform)
       id: create-neon-project
       uses: ./.github/actions/neon-project-create
       with:
@@ -430,7 +426,7 @@ jobs:
           neonvm-captest-sharding-reuse)
             CONNSTR=${{ secrets.BENCHMARK_CAPTEST_SHARDING_CONNSTR }}
             ;;
-          neonvm-captest-new | neonvm-captest-new-many-tables | neonvm-captest-freetier | neonvm-azure-captest-new | neonvm-azure-captest-freetier)
+          neonvm-captest-new | neonvm-captest-freetier | neonvm-azure-captest-new | neonvm-azure-captest-freetier)
             CONNSTR=${{ steps.create-neon-project.outputs.dsn }}
             ;;
           rds-aurora)
@@ -447,26 +443,6 @@ jobs:
 
         echo "connstr=${CONNSTR}" >> $GITHUB_OUTPUT
 
-    # we want to compare Neon project OLTP throughput and latency at scale factor 10 GB 
-    # without (neonvm-captest-new)
-    # and with (neonvm-captest-new-many-tables) many relations in the database
-    - name: Create many relations before the run
-      if: contains(fromJson('["neonvm-captest-new-many-tables"]'), matrix.platform)
-      uses: ./.github/actions/run-python-test-set
-      with:
-        build_type: ${{ env.BUILD_TYPE }}
-        test_selection: performance
-        run_in_parallel: false
-        save_perf_report: ${{ env.SAVE_PERF_REPORT }}
-        extra_params: -m remote_cluster --timeout 21600 -k test_perf_many_relations
-        pg_version: ${{ env.DEFAULT_PG_VERSION }}
-        aws-oicd-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 }}"
-        TEST_NUM_RELATIONS: 10000
-
     - name: Benchmark init
       uses: ./.github/actions/run-python-test-set
       with:
@@ -476,7 +452,7 @@ jobs:
         save_perf_report: ${{ env.SAVE_PERF_REPORT }}
         extra_params: -m remote_cluster --timeout 21600 -k test_pgbench_remote_init
         pg_version: ${{ env.DEFAULT_PG_VERSION }}
-        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws_oicd_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 }}"
@@ -491,7 +467,7 @@ jobs:
         save_perf_report: ${{ env.SAVE_PERF_REPORT }}
         extra_params: -m remote_cluster --timeout 21600 -k test_pgbench_remote_simple_update
         pg_version: ${{ env.DEFAULT_PG_VERSION }}
-        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws_oicd_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 }}"
@@ -506,7 +482,7 @@ jobs:
         save_perf_report: ${{ env.SAVE_PERF_REPORT }}
         extra_params: -m remote_cluster --timeout 21600 -k test_pgbench_remote_select_only
         pg_version: ${{ env.DEFAULT_PG_VERSION }}
-        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws_oicd_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 }}"
@@ -524,7 +500,7 @@ jobs:
       if: ${{ !cancelled() }}
       uses: ./.github/actions/allure-report-generate
       with:
-        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
     - name: Post to a Slack channel
       if: ${{ github.event.schedule && failure() }}
@@ -635,7 +611,7 @@ jobs:
         save_perf_report: ${{ env.SAVE_PERF_REPORT }}
         extra_params: -m remote_cluster --timeout 21600 -k test_pgvector_indexing
         pg_version: ${{ env.DEFAULT_PG_VERSION }}
-        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
       env:
         VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
         PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
@@ -650,7 +626,7 @@ jobs:
         save_perf_report: ${{ env.SAVE_PERF_REPORT }}
         extra_params: -m remote_cluster --timeout 21600
         pg_version: ${{ env.DEFAULT_PG_VERSION }}
-        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws_oicd_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 }}"
@@ -661,7 +637,7 @@ jobs:
       if: ${{ !cancelled() }}
       uses: ./.github/actions/allure-report-generate
       with:
-        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
     - name: Post to a Slack channel
       if: ${{ github.event.schedule && failure() }}
@@ -732,7 +708,6 @@ jobs:
         name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
         path: /tmp/neon/
         prefix: latest
-        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
     - name: Set up Connection String
       id: set-up-connstr
@@ -764,7 +739,7 @@ jobs:
         save_perf_report: ${{ env.SAVE_PERF_REPORT }}
         extra_params: -m remote_cluster --timeout 43200 -k test_clickbench
         pg_version: ${{ env.DEFAULT_PG_VERSION }}
-        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
       env:
         VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
         PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
@@ -778,7 +753,7 @@ jobs:
       if: ${{ !cancelled() }}
       uses: ./.github/actions/allure-report-generate
       with:
-        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
     - name: Post to a Slack channel
       if: ${{ github.event.schedule && failure() }}
@@ -843,7 +818,6 @@ jobs:
         name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
         path: /tmp/neon/
         prefix: latest
-        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
     - name: Get Connstring Secret Name
       run: |
@@ -882,7 +856,7 @@ jobs:
         save_perf_report: ${{ env.SAVE_PERF_REPORT }}
         extra_params: -m remote_cluster --timeout 21600 -k test_tpch
         pg_version: ${{ env.DEFAULT_PG_VERSION }}
-        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
       env:
         VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
         PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
@@ -894,7 +868,7 @@ jobs:
       if: ${{ !cancelled() }}
       uses: ./.github/actions/allure-report-generate
       with:
-        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
     - name: Post to a Slack channel
       if: ${{ github.event.schedule && failure() }}
@@ -952,7 +926,6 @@ jobs:
         name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
         path: /tmp/neon/
         prefix: latest
-        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
     - name: Set up Connection String
       id: set-up-connstr
@@ -984,7 +957,7 @@ jobs:
         save_perf_report: ${{ env.SAVE_PERF_REPORT }}
         extra_params: -m remote_cluster --timeout 21600 -k test_user_examples
         pg_version: ${{ env.DEFAULT_PG_VERSION }}
-        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
       env:
         VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
         PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
@@ -995,7 +968,7 @@ jobs:
       if: ${{ !cancelled() }}
       uses: ./.github/actions/allure-report-generate
       with:
-        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
     - name: Post to a Slack channel
       if: ${{ github.event.schedule && failure() }}

.github/workflows/build-macos.yml

@@ -1,241 +0,0 @@
-name: Check neon with MacOS builds
-
-on:
-  workflow_call:
-    inputs:
-      pg_versions:
-        description: "Array of the pg versions to build for, for example: ['v14', 'v17']"
-        type: string
-        default: '[]'
-        required: false
-      rebuild_rust_code:
-        description: "Rebuild Rust code"
-        type: boolean
-        default: false
-        required: false
-      rebuild_everything:
-        description: "If true, rebuild for all versions"
-        type: boolean
-        default: false
-        required: false
-
-env:
-  RUST_BACKTRACE: 1
-  COPT: '-Werror'
-
-# TODO: move `check-*` and `files-changed` jobs to the "Caller" Workflow
-# We should care about that as Github has limitations:
-# - You can connect up to four levels of workflows
-# - You can call a maximum of 20 unique reusable workflows from a single workflow file.
-# https://docs.github.com/en/actions/sharing-automations/reusing-workflows#limitations
-jobs:
-  build-pgxn:
-    if: |
-      (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'
-      )
-    timeout-minutes: 30
-    runs-on: macos-15
-    strategy:
-      matrix:
-        postgres-version: ${{ inputs.rebuild_everything && fromJson('["v14", "v15", "v16", "v17"]') || fromJSON(inputs.pg_versions) }}
-    env:
-      # Use release build only, to have less debug info around
-      # Hence keeping target/ (and general cache size) smaller
-      BUILD_TYPE: release
-    steps:
-      - name: Checkout main repo
-        uses: actions/checkout@v4
-
-      - name: Set pg ${{ matrix.postgres-version }} for caching
-        id: pg_rev
-        run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-${{ matrix.postgres-version }}) | tee -a "${GITHUB_OUTPUT}"
-
-      - name: Cache postgres ${{ matrix.postgres-version }} build
-        id: cache_pg
-        uses: actions/cache@v4
-        with:
-          path: pg_install/${{ matrix.postgres-version }}
-          key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-${{ matrix.postgres-version }}-${{ steps.pg_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
-
-      - name: Checkout submodule vendor/postgres-${{ matrix.postgres-version }}
-        if: steps.cache_pg.outputs.cache-hit != 'true'
-        run: |
-          git submodule init vendor/postgres-${{ matrix.postgres-version }}
-          git submodule update --depth 1 --recursive
-
-      - name: Install build dependencies
-        if: steps.cache_pg.outputs.cache-hit != 'true'
-        run: |
-          brew install flex bison openssl protobuf icu4c
-
-      - name: Set extra env for macOS
-        if: steps.cache_pg.outputs.cache-hit != 'true'
-        run: |
-          echo 'LDFLAGS=-L/usr/local/opt/openssl@3/lib' >> $GITHUB_ENV
-          echo 'CPPFLAGS=-I/usr/local/opt/openssl@3/include' >> $GITHUB_ENV
-
-      - name: Build Postgres ${{ matrix.postgres-version }}
-        if: steps.cache_pg.outputs.cache-hit != 'true'
-        run: |
-          make postgres-${{ matrix.postgres-version }} -j$(sysctl -n hw.ncpu)
-
-      - name: Build Neon Pg Ext ${{ matrix.postgres-version }}
-        if: steps.cache_pg.outputs.cache-hit != 'true'
-        run: |
-          make "neon-pg-ext-${{ matrix.postgres-version }}" -j$(sysctl -n hw.ncpu)
-
-      - name: Get postgres headers ${{ matrix.postgres-version }}
-        if: steps.cache_pg.outputs.cache-hit != 'true'
-        run: |
-          make postgres-headers-${{ matrix.postgres-version }} -j$(sysctl -n hw.ncpu)
-
-  build-walproposer-lib:
-    if: |
-      (inputs.pg_versions != '[]' || inputs.rebuild_everything) && (
-        contains(github.event.pull_request.labels.*.name, 'run-extra-build-macos')  ||
-        contains(github.event.pull_request.labels.*.name, 'run-extra-build-*') ||
-        github.ref_name == 'main'
-      )
-    timeout-minutes: 30
-    runs-on: macos-15
-    needs: [build-pgxn]
-    env:
-      # Use release build only, to have less debug info around
-      # Hence keeping target/ (and general cache size) smaller
-      BUILD_TYPE: release
-    steps:
-      - name: Checkout main repo
-        uses: actions/checkout@v4
-
-      - name: Set pg v17 for caching
-        id: pg_rev
-        run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v17) | tee -a "${GITHUB_OUTPUT}"
-
-      - name: Cache postgres v17 build
-        id: cache_pg
-        uses: actions/cache@v4
-        with:
-          path: pg_install/v17
-          key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-v17-${{ steps.pg_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
-
-      - name: Cache walproposer-lib
-        id: cache_walproposer_lib
-        uses: actions/cache@v4
-        with:
-          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
-        if: steps.cache_walproposer_lib.outputs.cache-hit != 'true'
-        run: |
-          git submodule init vendor/postgres-v17
-          git submodule update --depth 1 --recursive
-
-      - name: Install build dependencies
-        if: steps.cache_walproposer_lib.outputs.cache-hit != 'true'
-        run: |
-          brew install flex bison openssl protobuf icu4c
-
-      - name: Set extra env for macOS
-        if: steps.cache_walproposer_lib.outputs.cache-hit != 'true'
-        run: |
-          echo 'LDFLAGS=-L/usr/local/opt/openssl@3/lib' >> $GITHUB_ENV
-          echo 'CPPFLAGS=-I/usr/local/opt/openssl@3/include' >> $GITHUB_ENV
-
-      - name: Build walproposer-lib (only for v17)
-        if: steps.cache_walproposer_lib.outputs.cache-hit != 'true'
-        run:
-          make walproposer-lib -j$(sysctl -n hw.ncpu)
-
-  cargo-build:
-    if: |
-      (inputs.pg_versions != '[]' || inputs.rebuild_rust_code || 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'
-      )
-    timeout-minutes: 30
-    runs-on: macos-15
-    needs: [build-pgxn, build-walproposer-lib]
-    env:
-      # Use release build only, to have less debug info around
-      # Hence keeping target/ (and general cache size) smaller
-      BUILD_TYPE: release
-    steps:
-      - name: Checkout main repo
-        uses: actions/checkout@v4
-        with:
-          submodules: true
-
-      - name: Set pg v14 for caching
-        id: pg_rev_v14
-        run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v14) | tee -a "${GITHUB_OUTPUT}"
-      - name: Set pg v15 for caching
-        id: pg_rev_v15
-        run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v15) | tee -a "${GITHUB_OUTPUT}"
-      - name: Set pg v16 for caching
-        id: pg_rev_v16
-        run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v16) | tee -a "${GITHUB_OUTPUT}"
-      - name: Set pg v17 for caching
-        id: pg_rev_v17
-        run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v17) | tee -a "${GITHUB_OUTPUT}"
-
-      - name: Cache postgres v14 build
-        id: cache_pg
-        uses: actions/cache@v4
-        with:
-          path: pg_install/v14
-          key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-v14-${{ steps.pg_rev_v14.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
-      - name: Cache postgres v15 build
-        id: cache_pg_v15
-        uses: actions/cache@v4
-        with:
-          path: pg_install/v15
-          key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-v15-${{ steps.pg_rev_v15.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
-      - name: Cache postgres v16 build
-        id: cache_pg_v16
-        uses: actions/cache@v4
-        with:
-          path: pg_install/v16
-          key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-v16-${{ steps.pg_rev_v16.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
-      - name: Cache postgres v17 build
-        id: cache_pg_v17
-        uses: actions/cache@v4
-        with:
-          path: pg_install/v17
-          key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-v17-${{ steps.pg_rev_v17.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
-
-      - name: Cache cargo deps (only for v17)
-        uses: actions/cache@v4
-        with:
-          path: |
-            ~/.cargo/registry
-            !~/.cargo/registry/src
-            ~/.cargo/git
-            target
-          key: v1-${{ runner.os }}-${{ runner.arch }}-cargo-${{ hashFiles('./Cargo.lock') }}-${{ hashFiles('./rust-toolchain.toml') }}-rust
-
-      - name: Cache walproposer-lib
-        id: cache_walproposer_lib
-        uses: actions/cache@v4
-        with:
-          path: pg_install/build/walproposer-lib
-          key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-walproposer_lib-v17-${{ steps.pg_rev_v17.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
-
-      - name: Install build dependencies
-        run: |
-          brew install flex bison openssl protobuf icu4c
-
-      - name: Set extra env for macOS
-        run: |
-          echo 'LDFLAGS=-L/usr/local/opt/openssl@3/lib' >> $GITHUB_ENV
-          echo 'CPPFLAGS=-I/usr/local/opt/openssl@3/include' >> $GITHUB_ENV
-
-      - name: Run cargo build (only for v17)
-        run: PQ_LIB_DIR=$(pwd)/pg_install/v17/lib cargo build --all --release -j$(sysctl -n hw.ncpu)
-
-      - name: Check that no warnings are produced (only for v17)
-        run: ./run_clippy.sh

.github/workflows/build_and_test.yml

@@ -21,6 +21,8 @@ concurrency:
 env:
   RUST_BACKTRACE: 1
   COPT: '-Werror'
+  AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_DEV }}
+  AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_KEY_DEV }}
   # A concurrency group that we use for e2e-tests runs, matches `concurrency.group` above with `github.repository` as a prefix
   E2E_CONCURRENCY_GROUP: ${{ github.repository }}-e2e-tests-${{ github.ref_name }}-${{ github.ref_name == 'main' && github.sha || 'anysha' }}
 
@@ -212,7 +214,7 @@ jobs:
           fi
           echo "CLIPPY_COMMON_ARGS=${CLIPPY_COMMON_ARGS}" >> $GITHUB_ENV
       - name: Run cargo clippy (debug)
-        run: cargo hack --features default --ignore-unknown-features --feature-powerset clippy $CLIPPY_COMMON_ARGS
+        run: cargo hack --feature-powerset clippy $CLIPPY_COMMON_ARGS
 
       - name: Check documentation generation
         run: cargo doc --workspace --no-deps --document-private-items
@@ -253,15 +255,15 @@ jobs:
       build-tools-image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
       build-tag: ${{ needs.tag.outputs.build-tag }}
       build-type: ${{ matrix.build-type }}
-      # Run tests on all Postgres versions in release builds and only on the latest version in debug builds.
+      # Run tests on all Postgres versions in release builds and only on the latest version in debug builds
-      # Run without LFC on v17 release and debug builds only. For all the other cases LFC is enabled.
+      # run without LFC on v17 release only
       test-cfg: |
-        ${{ matrix.build-type == 'release' && '[{"pg_version":"v14", "lfc_state": "with-lfc"},
+        ${{ matrix.build-type == 'release' && '[{"pg_version":"v14", "lfc_state": "without-lfc"},
-                                                {"pg_version":"v15", "lfc_state": "with-lfc"},
+                                                {"pg_version":"v15", "lfc_state": "without-lfc"},
-                                                {"pg_version":"v16", "lfc_state": "with-lfc"},
+                                                {"pg_version":"v16", "lfc_state": "without-lfc"},
-                                                {"pg_version":"v17", "lfc_state": "with-lfc"},
+                                                {"pg_version":"v17", "lfc_state": "without-lfc"},
-                                                {"pg_version":"v17", "lfc_state": "without-lfc"}]'
+                                                {"pg_version":"v17", "lfc_state": "with-lfc"}]'
-                                           || '[{"pg_version":"v17", "lfc_state": "without-lfc" }]' }}
+                                           || '[{"pg_version":"v17", "lfc_state": "without-lfc"}]' }}
     secrets: inherit
 
   # Keep `benchmarks` job outside of `build-and-test-locally` workflow to make job failures non-blocking
@@ -303,11 +305,6 @@ jobs:
   benchmarks:
     if: github.ref_name == 'main' || contains(github.event.pull_request.labels.*.name, 'run-benchmarks')
     needs: [ check-permissions, build-and-test-locally, build-build-tools-image, get-benchmarks-durations ]
-    permissions:
-      id-token: write # aws-actions/configure-aws-credentials
-      statuses: write
-      contents: write
-      pull-requests: write
     runs-on: [ self-hosted, small ]
     container:
       image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
@@ -336,7 +333,6 @@ jobs:
           extra_params: --splits 5 --group ${{ matrix.pytest_split_group }}
           benchmark_durations: ${{ needs.get-benchmarks-durations.outputs.json }}
           pg_version: v16
-          aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
         env:
           VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
           PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
@@ -349,11 +345,6 @@ jobs:
   report-benchmarks-failures:
     needs: [ benchmarks, create-test-report ]
     if: github.ref_name == 'main' && failure() && needs.benchmarks.result == 'failure'
-    permissions:
-      id-token: write # aws-actions/configure-aws-credentials
-      statuses: write
-      contents: write
-      pull-requests: write
     runs-on: ubuntu-22.04
 
     steps:
@@ -369,11 +360,6 @@ jobs:
   create-test-report:
     needs: [ check-permissions, build-and-test-locally, coverage-report, build-build-tools-image, benchmarks ]
     if: ${{ !cancelled() && contains(fromJSON('["skipped", "success"]'), needs.check-permissions.result) }}
-    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 }}
 
@@ -394,7 +380,6 @@ jobs:
         uses: ./.github/actions/allure-report-generate
         with:
           store-test-results-into-db: true
-          aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
         env:
           REGRESS_TEST_RESULT_CONNSTR_NEW: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}
 
@@ -426,10 +411,6 @@ jobs:
   coverage-report:
     if: ${{ !startsWith(github.ref_name, 'release') }}
     needs: [ check-permissions, build-build-tools-image, build-and-test-locally ]
-    permissions:
-      id-token: write # aws-actions/configure-aws-credentials
-      statuses: write
-      contents: write
     runs-on: [ self-hosted, small ]
     container:
       image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
@@ -456,14 +437,12 @@ jobs:
         with:
           name: neon-${{ runner.os }}-${{ runner.arch }}-${{ matrix.build_type }}-artifact
           path: /tmp/neon
-          aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
       - name: Get coverage artifact
         uses: ./.github/actions/download
         with:
           name: coverage-data-artifact
           path: /tmp/coverage
-          aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
       - name: Merge coverage data
         run: scripts/coverage "--profraw-prefix=$GITHUB_JOB" --dir=/tmp/coverage merge
@@ -538,7 +517,7 @@ jobs:
 
   trigger-e2e-tests:
     if: ${{ !github.event.pull_request.draft || contains( github.event.pull_request.labels.*.name, 'run-e2e-tests-in-draft') || github.ref_name == 'main' || github.ref_name == 'release' || github.ref_name == 'release-proxy' || github.ref_name == 'release-compute' }}
-    needs: [ check-permissions, promote-images-dev, tag ]
+    needs: [ check-permissions, promote-images, tag ]
     uses: ./.github/workflows/trigger-e2e-tests.yml
     secrets: inherit
 
@@ -594,10 +573,6 @@ jobs:
   neon-image:
     needs: [ neon-image-arch, tag ]
     runs-on: ubuntu-22.04
-    permissions:
-      id-token: write # aws-actions/configure-aws-credentials
-      statuses: write
-      contents: read
 
     steps:
       - uses: docker/login-action@v3
@@ -612,15 +587,11 @@ jobs:
                                              neondatabase/neon:${{ needs.tag.outputs.build-tag }}-bookworm-x64 \
                                              neondatabase/neon:${{ needs.tag.outputs.build-tag }}-bookworm-arm64
 
-      - name: Configure AWS credentials
+      - uses: docker/login-action@v3
-        uses: aws-actions/configure-aws-credentials@v4
         with:
-          aws-region: eu-central-1
+          registry: 369495373322.dkr.ecr.eu-central-1.amazonaws.com
-          role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+          username: ${{ secrets.AWS_ACCESS_KEY_DEV }}
-          role-duration-seconds: 3600
+          password: ${{ secrets.AWS_SECRET_KEY_DEV }}
-
-      - name: Login to Amazon Dev ECR
-        uses: aws-actions/amazon-ecr-login@v2
 
       - name: Push multi-arch image to ECR
         run: |
@@ -629,10 +600,6 @@ jobs:
 
   compute-node-image-arch:
     needs: [ check-permissions, build-build-tools-image, tag ]
-    permissions:
-      id-token: write # aws-actions/configure-aws-credentials
-      statuses: write
-      contents: read
     strategy:
       fail-fast: false
       matrix:
@@ -673,15 +640,11 @@ jobs:
           username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
           password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
 
-      - name: Configure AWS credentials
+      - uses: docker/login-action@v3
-        uses: aws-actions/configure-aws-credentials@v4
         with:
-          aws-region: eu-central-1
+          registry: 369495373322.dkr.ecr.eu-central-1.amazonaws.com
-          role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+          username: ${{ secrets.AWS_ACCESS_KEY_DEV }}
-          role-duration-seconds: 3600
+          password: ${{ secrets.AWS_SECRET_KEY_DEV }}
-
-      - name: Login to Amazon Dev ECR
-        uses: aws-actions/amazon-ecr-login@v2
 
       - uses: docker/login-action@v3
         with:
@@ -754,10 +717,6 @@ jobs:
 
   compute-node-image:
     needs: [ compute-node-image-arch, tag ]
-    permissions:
-      id-token: write # aws-actions/configure-aws-credentials
-      statuses: write
-      contents: read
     runs-on: ubuntu-22.04
 
     strategy:
@@ -802,15 +761,11 @@ jobs:
                                              neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-x64 \
                                              neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-arm64
 
-      - name: Configure AWS credentials
+      - uses: docker/login-action@v3
-        uses: aws-actions/configure-aws-credentials@v4
         with:
-          aws-region: eu-central-1
+          registry: 369495373322.dkr.ecr.eu-central-1.amazonaws.com
-          role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+          username: ${{ secrets.AWS_ACCESS_KEY_DEV }}
-          role-duration-seconds: 3600
+          password: ${{ secrets.AWS_SECRET_KEY_DEV }}
-
-      - name: Login to Amazon Dev ECR
-        uses: aws-actions/amazon-ecr-login@v2
 
       - name: Push multi-arch compute-node-${{ matrix.version.pg }} image to ECR
         run: |
@@ -840,7 +795,7 @@ jobs:
           - pg: v17
             debian: bookworm
     env:
-      VM_BUILDER_VERSION: v0.37.1
+      VM_BUILDER_VERSION: v0.35.0
 
     steps:
       - uses: actions/checkout@v4
@@ -930,14 +885,12 @@ jobs:
           docker compose -f ./docker-compose/docker-compose.yml logs || 0
           docker compose -f ./docker-compose/docker-compose.yml down
 
-  promote-images-dev:
+  promote-images:
-    needs: [ check-permissions, tag, vm-compute-node-image ]
+    needs: [ check-permissions, tag, test-images, vm-compute-node-image ]
     runs-on: ubuntu-22.04
 
     permissions:
-      id-token: write # aws-actions/configure-aws-credentials
+      id-token: write # for `aws-actions/configure-aws-credentials`
-      statuses: write
-      contents: read
 
     env:
       VERSIONS: v14 v15 v16 v17
@@ -948,15 +901,12 @@ jobs:
           username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
           password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
 
-      - name: Configure AWS credentials
+      - name: Login to dev ECR
-        uses: aws-actions/configure-aws-credentials@v4
+        uses: docker/login-action@v3
         with:
-          aws-region: eu-central-1
+          registry: 369495373322.dkr.ecr.eu-central-1.amazonaws.com
-          role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+          username: ${{ secrets.AWS_ACCESS_KEY_DEV }}
-          role-duration-seconds: 3600
+          password: ${{ secrets.AWS_SECRET_KEY_DEV }}
-
-      - name: Login to Amazon Dev ECR
-        uses: aws-actions/amazon-ecr-login@v2
 
       - name: Copy vm-compute-node images to ECR
         run: |
@@ -965,35 +915,6 @@ jobs:
                                                neondatabase/vm-compute-node-${version}:${{ needs.tag.outputs.build-tag }}
           done
 
-  promote-images-prod:
-    needs: [ check-permissions, tag, test-images, vm-compute-node-image ]
-    runs-on: ubuntu-22.04
-    if: github.ref_name == 'main' || github.ref_name == 'release' || github.ref_name == 'release-proxy' || github.ref_name == 'release-compute'
-
-    permissions:
-      id-token: write # aws-actions/configure-aws-credentials
-      statuses: write
-      contents: read
-
-    env:
-      VERSIONS: v14 v15 v16 v17
-
-    steps:
-      - name: Configure AWS credentials
-        uses: aws-actions/configure-aws-credentials@v4
-        with:
-          aws-region: eu-central-1
-          role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
-          role-duration-seconds: 3600
-
-      - name: Login to Amazon Dev ECR
-        uses: aws-actions/amazon-ecr-login@v2
-
-      - uses: docker/login-action@v3
-        with:
-          username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
-          password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
-
       - name: Add latest tag to images
         if: github.ref_name == 'main'
         run: |
@@ -1039,7 +960,7 @@ jobs:
 
   push-to-acr-dev:
     if: github.ref_name == 'main'
-    needs: [ tag, promote-images-dev ]
+    needs: [ tag, promote-images ]
     uses: ./.github/workflows/_push-to-acr.yml
     with:
       client_id: ${{ vars.AZURE_DEV_CLIENT_ID }}
@@ -1051,7 +972,7 @@ jobs:
 
   push-to-acr-prod:
     if: github.ref_name == 'release' || github.ref_name == 'release-proxy' || github.ref_name == 'release-compute'
-    needs: [ tag, promote-images-prod ]
+    needs: [ tag, promote-images ]
     uses: ./.github/workflows/_push-to-acr.yml
     with:
       client_id: ${{ vars.AZURE_PROD_CLIENT_ID }}
@@ -1064,11 +985,6 @@ jobs:
   trigger-custom-extensions-build-and-wait:
     needs: [ check-permissions, tag ]
     runs-on: ubuntu-22.04
-    permissions:
-      id-token: write # aws-actions/configure-aws-credentials
-      statuses: write
-      contents: write
-      pull-requests: write
     steps:
       - name: Set PR's status to pending and request a remote CI test
         run: |
@@ -1141,82 +1057,15 @@ jobs:
           exit 1
 
   deploy:
-    needs: [ check-permissions, promote-images-prod, tag, build-and-test-locally, trigger-custom-extensions-build-and-wait, push-to-acr-dev, push-to-acr-prod ]
+    needs: [ check-permissions, promote-images, tag, build-and-test-locally, trigger-custom-extensions-build-and-wait, push-to-acr-dev, push-to-acr-prod ]
     # `!failure() && !cancelled()` is required because the workflow depends on the job that can be skipped: `push-to-acr-dev` and `push-to-acr-prod`
     if: (github.ref_name == 'main' || github.ref_name == 'release' || github.ref_name == 'release-proxy' || github.ref_name == 'release-compute') && !failure() && !cancelled()
-    permissions:
+
-      id-token: write # aws-actions/configure-aws-credentials
-      statuses: write
-      contents: write
     runs-on: [ self-hosted, small ]
     container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/ansible:latest
     steps:
       - uses: actions/checkout@v4
 
-      - name: Create git tag and GitHub release
-        if: github.ref_name == 'release' || github.ref_name == 'release-proxy' || github.ref_name == 'release-compute'
-        uses: actions/github-script@v7
-        with:
-          retries: 5
-          script: |
-            const tag = "${{ needs.tag.outputs.build-tag }}";
-
-            try {
-              const existingRef = await github.rest.git.getRef({
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                ref: `tags/${tag}`,
-              });
-
-              if (existingRef.data.object.sha !== context.sha) {
-                throw new Error(`Tag ${tag} already exists but points to a different commit (expected: ${context.sha}, actual: ${existingRef.data.object.sha}).`);
-              }
-
-              console.log(`Tag ${tag} already exists and points to ${context.sha} as expected.`);
-            } catch (error) {
-              if (error.status !== 404) {
-                throw error;
-              }
-
-              console.log(`Tag ${tag} does not exist. Creating it...`);
-              await github.rest.git.createRef({
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                ref: `refs/tags/${tag}`,
-                sha: context.sha,
-              });
-              console.log(`Tag ${tag} created successfully.`);
-            }
-
-            // TODO: check how GitHub releases looks for proxy/compute releases and enable them if they're ok
-            if (context.ref !== 'refs/heads/release') {
-              console.log(`GitHub release skipped for ${context.ref}.`);
-              return;
-            }
-
-            try {
-              const existingRelease = await github.rest.repos.getReleaseByTag({
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                tag: tag,
-              });
-
-              console.log(`Release for tag ${tag} already exists (ID: ${existingRelease.data.id}).`);
-            } catch (error) {
-              if (error.status !== 404) {
-                throw error;
-              }
-
-              console.log(`Release for tag ${tag} does not exist. Creating it...`);
-              await github.rest.repos.createRelease({
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                tag_name: tag,
-                generate_release_notes: true,
-              });
-              console.log(`Release for tag ${tag} created successfully.`);
-            }
-
       - name: Trigger deploy workflow
         env:
           GH_TOKEN: ${{ secrets.CI_ACCESS_TOKEN }}
@@ -1266,13 +1115,38 @@ jobs:
             exit 1
           fi
 
+      - name: Create git tag
+        if: github.ref_name == 'release' || github.ref_name == 'release-proxy' || github.ref_name == 'release-compute'
+        uses: actions/github-script@v7
+        with:
+          # Retry script for 5XX server errors: https://github.com/actions/github-script#retries
+          retries: 5
+          script: |
+            await github.rest.git.createRef({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              ref: "refs/tags/${{ needs.tag.outputs.build-tag }}",
+              sha: context.sha,
+            })
+
+      # TODO: check how GitHub releases looks for proxy releases and enable it if it's ok
+      - name: Create GitHub release
+        if: github.ref_name == 'release'
+        uses: actions/github-script@v7
+        with:
+          # Retry script for 5XX server errors: https://github.com/actions/github-script#retries
+          retries: 5
+          script: |
+            await github.rest.repos.createRelease({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              tag_name: "${{ needs.tag.outputs.build-tag }}",
+              generate_release_notes: true,
+            })
+
   # The job runs on `release` branch and copies compatibility data and Neon artifact from the last *release PR* to the latest directory
   promote-compatibility-data:
     needs: [ deploy ]
-    permissions:
-      id-token: write # aws-actions/configure-aws-credentials
-      statuses: write
-      contents: read
     # `!failure() && !cancelled()` is required because the workflow transitively depends on the job that can be skipped: `push-to-acr-dev` and `push-to-acr-prod`
     if: github.ref_name == 'release' && !failure() && !cancelled()
 
@@ -1309,12 +1183,6 @@ jobs:
           echo "run-id=${run_id}" | tee -a ${GITHUB_OUTPUT}
           echo "commit-sha=${last_commit_sha}" | tee -a ${GITHUB_OUTPUT}
 
-      - uses: aws-actions/configure-aws-credentials@v4
-        with:
-          aws-region: eu-central-1
-          role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
-          role-duration-seconds: 3600
-
       - name: Promote compatibility snapshot and Neon artifact
         env:
           BUCKET: neon-github-public-dev
@@ -1362,7 +1230,7 @@ jobs:
           done
 
   pin-build-tools-image:
-    needs: [ build-build-tools-image, promote-images-prod, build-and-test-locally ]
+    needs: [ build-build-tools-image, promote-images, build-and-test-locally ]
     if: github.ref_name == 'main'
     uses: ./.github/workflows/pin-build-tools-image.yml
     with:
@@ -1385,7 +1253,7 @@ jobs:
       - build-and-test-locally
       - check-codestyle-python
       - check-codestyle-rust
-      - promote-images-dev
+      - promote-images
       - test-images
       - trigger-custom-extensions-build-and-wait
     runs-on: ubuntu-22.04

.github/workflows/cloud-regress.yml

@@ -19,21 +19,15 @@ concurrency:
   group: ${{ github.workflow }}
   cancel-in-progress: true
 
-permissions:
-  id-token: write # aws-actions/configure-aws-credentials
-  statuses: write
-  contents: write
-
 jobs:
   regress:
     env:
       POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
+      DEFAULT_PG_VERSION: 16
       TEST_OUTPUT: /tmp/test_output
       BUILD_TYPE: remote
-    strategy:
+      AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_DEV }}
-      fail-fast: false
+      AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_KEY_DEV }}
-      matrix:
-        pg-version: [16, 17]
 
     runs-on: us-east-2
     container:
@@ -46,11 +40,9 @@ jobs:
           submodules: true
 
       - name: Patch the test
-        env:
-          PG_VERSION: ${{matrix.pg-version}}
         run: |
-          cd "vendor/postgres-v${PG_VERSION}"
+          cd "vendor/postgres-v${DEFAULT_PG_VERSION}"
-          patch -p1 < "../../compute/patches/cloud_regress_pg${PG_VERSION}.patch"
+          patch -p1 < "../../compute/patches/cloud_regress_pg${DEFAULT_PG_VERSION}.patch"
 
       - name: Generate a random password
         id: pwgen
@@ -63,9 +55,8 @@ jobs:
       - name: Change tests according to the generated password
         env:
           DBPASS: ${{ steps.pwgen.outputs.DBPASS }}
-          PG_VERSION: ${{matrix.pg-version}}
         run: |
-          cd vendor/postgres-v"${PG_VERSION}"/src/test/regress
+          cd vendor/postgres-v"${DEFAULT_PG_VERSION}"/src/test/regress
           for fname in sql/*.sql expected/*.out; do
             sed -i.bak s/NEON_PASSWORD_PLACEHOLDER/"'${DBPASS}'"/ "${fname}"
           done
@@ -81,46 +72,27 @@ jobs:
           name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
           path: /tmp/neon/
           prefix: latest
-          aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
-
-      - name: Create a new branch
-        id: create-branch
-        uses: ./.github/actions/neon-branch-create
-        with:
-          api_key: ${{ secrets.NEON_STAGING_API_KEY }}
-          project_id: ${{ vars[format('PGREGRESS_PG{0}_PROJECT_ID', matrix.pg-version)] }}
 
       - name: Run the regression tests
         uses: ./.github/actions/run-python-test-set
         with:
           build_type: ${{ env.BUILD_TYPE }}
           test_selection: cloud_regress
-          pg_version: ${{matrix.pg-version}}
+          pg_version: ${{ env.DEFAULT_PG_VERSION }}
           extra_params: -m remote_cluster
-          aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
         env:
-          BENCHMARK_CONNSTR: ${{steps.create-branch.outputs.dsn}}
+          BENCHMARK_CONNSTR: ${{ secrets.PG_REGRESS_CONNSTR }}
-
-      - name: Delete branch
-        if: always()
-        uses: ./.github/actions/neon-branch-delete
-        with:
-          api_key: ${{ secrets.NEON_STAGING_API_KEY }}
-          project_id: ${{ vars[format('PGREGRESS_PG{0}_PROJECT_ID', matrix.pg-version)] }}
-          branch_id: ${{steps.create-branch.outputs.branch_id}}
 
       - name: Create Allure report
         id: create-allure-report
         if: ${{ !cancelled() }}
         uses: ./.github/actions/allure-report-generate
-        with:
-          aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
       - name: Post to a Slack channel
         if: ${{ github.event.schedule && failure() }}
         uses: slackapi/slack-github-action@v1
         with:
-          channel-id: ${{ vars.SLACK_ON_CALL_QA_STAGING_STREAM }}
+          channel-id: "C033QLM5P7D" # on-call-staging-stream
           slack-message: |
             Periodic pg_regress on staging: ${{ job.status }}
             <${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}|GitHub Run>

.github/workflows/ingest_benchmark.yml

@@ -13,7 +13,7 @@ on:
     #          │ │ │ │ ┌───────────── day of the week (0 - 6 or SUN-SAT)
     - cron:   '0 9 * * *' # run once a day, timezone is utc
   workflow_dispatch: # adds ability to run this manually
-
+    
 defaults:
   run:
     shell: bash -euxo pipefail {0}
@@ -28,7 +28,7 @@ jobs:
     strategy:
       fail-fast: false # allow other variants to continue even if one fails
       matrix:
-        target_project: [new_empty_project, large_existing_project]
+        target_project: [new_empty_project, large_existing_project]  
     permissions:
       contents: write
       statuses: write
@@ -56,7 +56,7 @@ jobs:
       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
+        role-duration-seconds: 18000 # 5 hours is currently max associated with IAM role 
 
     - name: Download Neon artifact
       uses: ./.github/actions/download
@@ -64,7 +64,6 @@ jobs:
         name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
         path: /tmp/neon/
         prefix: latest
-        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
     - name: Create Neon Project
       if: ${{ matrix.target_project == 'new_empty_project' }}
@@ -95,7 +94,7 @@ jobs:
         project_id: ${{ vars.BENCHMARK_INGEST_TARGET_PROJECTID }}
         api_key: ${{ secrets.NEON_STAGING_API_KEY }}
 
-    - name: Initialize Neon project
+    - name: Initialize Neon project 
       if: ${{ matrix.target_project == 'large_existing_project' }}
       env:
           BENCHMARK_INGEST_TARGET_CONNSTR: ${{ steps.create-neon-branch-ingest-target.outputs.dsn }}
@@ -123,7 +122,7 @@ jobs:
         ${PSQL} "${BENCHMARK_INGEST_TARGET_CONNSTR}" -c "CREATE EXTENSION IF NOT EXISTS neon; CREATE EXTENSION IF NOT EXISTS neon_utils;"
         echo "BENCHMARK_INGEST_TARGET_CONNSTR=${BENCHMARK_INGEST_TARGET_CONNSTR}" >> $GITHUB_ENV
 
-    - name: Invoke pgcopydb
+    - name: Invoke pgcopydb  
       uses: ./.github/actions/run-python-test-set
       with:
         build_type: remote
@@ -132,7 +131,7 @@ jobs:
         extra_params: -s -m remote_cluster --timeout 86400 -k test_ingest_performance_using_pgcopydb
         pg_version: v16
         save_perf_report: true
-        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
       env:
         BENCHMARK_INGEST_SOURCE_CONNSTR: ${{ secrets.BENCHMARK_INGEST_SOURCE_CONNSTR }}
         TARGET_PROJECT_TYPE: ${{ matrix.target_project }}
@@ -144,7 +143,7 @@ jobs:
       run: |
         export LD_LIBRARY_PATH=${PG_16_LIB_PATH}
         ${PSQL} "${BENCHMARK_INGEST_TARGET_CONNSTR}" -c "\dt+"
-
+      
     - name: Delete Neon Project
       if: ${{ always() && matrix.target_project == 'new_empty_project' }}
       uses: ./.github/actions/neon-project-delete

.github/workflows/neon_extra_builds.yml

@@ -31,15 +31,19 @@ jobs:
     uses: ./.github/workflows/build-build-tools-image.yml
     secrets: inherit
 
-  files-changed:
+  check-macos-build:
-    name: Detect what files changed
+    needs: [ check-permissions ]
-    runs-on: ubuntu-22.04
+    if: |
-    timeout-minutes: 3
+      contains(github.event.pull_request.labels.*.name, 'run-extra-build-macos')  ||
-    outputs:
+      contains(github.event.pull_request.labels.*.name, 'run-extra-build-*') ||
-      v17: ${{ steps.files_changed.outputs.v17 }}
+      github.ref_name == 'main'
-      postgres_changes: ${{ steps.postgres_changes.outputs.changes }}
+    timeout-minutes: 90
-      rebuild_rust_code: ${{ steps.files_changed.outputs.rust_code }}
+    runs-on: macos-15
-      rebuild_everything: ${{ steps.files_changed.outputs.rebuild_neon_extra || steps.files_changed.outputs.rebuild_macos }}
+
+    env:
+      # Use release build only, to have less debug info around
+      # Hence keeping target/ (and general cache size) smaller
+      BUILD_TYPE: release
 
     steps:
       - name: Checkout
@@ -47,45 +51,102 @@ jobs:
         with:
           submodules: true
 
-      - name: Check for Postgres changes
+      - name: Install macOS postgres dependencies
-        uses: dorny/paths-filter@1441771bbfdd59dcd748680ee64ebd8faab1a242  #v3
+        run: brew install flex bison openssl protobuf icu4c
-        id: files_changed
+
+      - name: Set pg 14 revision for caching
+        id: pg_v14_rev
+        run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v14) >> $GITHUB_OUTPUT
+
+      - name: Set pg 15 revision for caching
+        id: pg_v15_rev
+        run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v15) >> $GITHUB_OUTPUT
+
+      - name: Set pg 16 revision for caching
+        id: pg_v16_rev
+        run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v16) >> $GITHUB_OUTPUT
+
+      - name: Set pg 17 revision for caching
+        id: pg_v17_rev
+        run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v17) >> $GITHUB_OUTPUT
+
+      - name: Cache postgres v14 build
+        id: cache_pg_14
+        uses: actions/cache@v4
         with:
-          token: ${{ github.token }}
+          path: pg_install/v14
-          filters: .github/file-filters.yaml
+          key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-${{ steps.pg_v14_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
-          base: ${{ github.event_name != 'pull_request' && (github.event.merge_group.base_ref || github.ref_name) || '' }}
-          ref: ${{ github.event_name != 'pull_request' && (github.event.merge_group.head_ref || github.ref) || '' }}
 
-      - name: Filter out only v-string for build matrix
+      - name: Cache postgres v15 build
-        id: postgres_changes
+        id: cache_pg_15
+        uses: actions/cache@v4
+        with:
+          path: pg_install/v15
+          key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-${{ steps.pg_v15_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
+
+      - name: Cache postgres v16 build
+        id: cache_pg_16
+        uses: actions/cache@v4
+        with:
+          path: pg_install/v16
+          key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-${{ steps.pg_v16_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
+
+      - name: Cache postgres v17 build
+        id: cache_pg_17
+        uses: actions/cache@v4
+        with:
+          path: pg_install/v17
+          key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-${{ steps.pg_v17_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
+
+      - name: Set extra env for macOS
         run: |
-          v_strings_only_as_json_array=$(echo ${{ steps.files_changed.outputs.chnages }} | jq '.[]|select(test("v\\d+"))' | jq --slurp -c)
+          echo 'LDFLAGS=-L/usr/local/opt/openssl@3/lib' >> $GITHUB_ENV
-          echo "changes=${v_strings_only_as_json_array}" | tee -a "${GITHUB_OUTPUT}"
+          echo 'CPPFLAGS=-I/usr/local/opt/openssl@3/include' >> $GITHUB_ENV
 
-  check-macos-build:
+      - name: Cache cargo deps
-    needs: [ check-permissions, files-changed ]
+        uses: actions/cache@v4
-    if: |
+        with:
-      contains(github.event.pull_request.labels.*.name, 'run-extra-build-macos')  ||
+          path: |
-      contains(github.event.pull_request.labels.*.name, 'run-extra-build-*') ||
+            ~/.cargo/registry
-      github.ref_name == 'main'
+            !~/.cargo/registry/src
-    uses: ./.github/workflows/build-macos.yml
+            ~/.cargo/git
-    with:
+            target
-      pg_versions: ${{ needs.files-changed.outputs.postgres_changes }}
+          key: v1-${{ runner.os }}-${{ runner.arch }}-cargo-${{ hashFiles('./Cargo.lock') }}-${{ hashFiles('./rust-toolchain.toml') }}-rust
-      rebuild_rust_code: ${{ needs.files-changed.outputs.rebuild_rust_code }}
+
-      rebuild_everything: ${{ fromJson(needs.files-changed.outputs.rebuild_everything) }}
+      - name: Build postgres v14
+        if: steps.cache_pg_14.outputs.cache-hit != 'true'
+        run: make postgres-v14 -j$(sysctl -n hw.ncpu)
+
+      - name: Build postgres v15
+        if: steps.cache_pg_15.outputs.cache-hit != 'true'
+        run: make postgres-v15 -j$(sysctl -n hw.ncpu)
+
+      - name: Build postgres v16
+        if: steps.cache_pg_16.outputs.cache-hit != 'true'
+        run: make postgres-v16 -j$(sysctl -n hw.ncpu)
+
+      - name: Build postgres v17
+        if: steps.cache_pg_17.outputs.cache-hit != 'true'
+        run: make postgres-v17 -j$(sysctl -n hw.ncpu)
+
+      - name: Build neon extensions
+        run: make neon-pg-ext -j$(sysctl -n hw.ncpu)
+
+      - name: Build walproposer-lib
+        run: make walproposer-lib -j$(sysctl -n hw.ncpu)
+
+      - name: Run cargo build
+        run: PQ_LIB_DIR=$(pwd)/pg_install/v16/lib cargo build --all --release
+
+      - name: Check that no warnings are produced
+        run: ./run_clippy.sh
 
   gather-rust-build-stats:
-    needs: [ check-permissions, build-build-tools-image, files-changed ]
+    needs: [ check-permissions, build-build-tools-image ]
-    permissions:
-      id-token: write # aws-actions/configure-aws-credentials
-      statuses: write
-      contents: write
     if: |
-      (needs.files-changed.outputs.v17 == 'true' || needs.files-changed.outputs.rebuild_everything == 'true') && (
+      contains(github.event.pull_request.labels.*.name, 'run-extra-build-stats') ||
-        contains(github.event.pull_request.labels.*.name, 'run-extra-build-stats') ||
+      contains(github.event.pull_request.labels.*.name, 'run-extra-build-*') ||
-        contains(github.event.pull_request.labels.*.name, 'run-extra-build-*') ||
+      github.ref_name == 'main'
-        github.ref_name == 'main'
-      )
     runs-on: [ self-hosted, large ]
     container:
       image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
@@ -116,18 +177,13 @@ jobs:
       - name: Produce the build stats
         run: PQ_LIB_DIR=$(pwd)/pg_install/v17/lib cargo build --all --release --timings -j$(nproc)
 
-      - name: Configure AWS credentials
-        uses: aws-actions/configure-aws-credentials@v4
-        with:
-          aws-region: eu-central-1
-          role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
-          role-duration-seconds: 3600
-
       - name: Upload the build stats
         id: upload-stats
         env:
           BUCKET: neon-github-public-dev
           SHA: ${{ github.event.pull_request.head.sha || github.sha }}
+          AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_DEV }}
+          AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_KEY_DEV }}
         run: |
           REPORT_URL=https://${BUCKET}.s3.amazonaws.com/build-stats/${SHA}/${GITHUB_RUN_ID}/cargo-timing.html
           aws s3 cp --only-show-errors ./target/cargo-timings/cargo-timing.html "s3://${BUCKET}/build-stats/${SHA}/${GITHUB_RUN_ID}/"

.github/workflows/periodic_pagebench.yml

@@ -27,11 +27,6 @@ concurrency:
 
 jobs:
   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, small ]
     container:
       image: neondatabase/build-tools:pinned-bookworm
@@ -43,6 +38,8 @@ jobs:
     env:
       API_KEY: ${{ secrets.PERIODIC_PAGEBENCH_EC2_RUNNER_API_KEY }}
       RUN_ID: ${{ github.run_id }}
+      AWS_ACCESS_KEY_ID: ${{ secrets.AWS_EC2_US_TEST_RUNNER_ACCESS_KEY_ID }}
+      AWS_SECRET_ACCESS_KEY : ${{ secrets.AWS_EC2_US_TEST_RUNNER_ACCESS_KEY_SECRET }}
       AWS_DEFAULT_REGION : "eu-central-1"
       AWS_INSTANCE_ID : "i-02a59a3bf86bc7e74"
     steps:
@@ -53,13 +50,6 @@ jobs:
     - name: Show my own (github runner) external IP address - usefull for IP allowlisting
       run: curl https://ifconfig.me
 
-    - name: Assume AWS OIDC role that allows to manage (start/stop/describe... EC machine)
-      uses: aws-actions/configure-aws-credentials@v4
-      with:
-        aws-region: eu-central-1
-        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 $AWS_INSTANCE_ID
@@ -134,10 +124,11 @@ jobs:
         cat "test_log_${GITHUB_RUN_ID}"
 
     - name: Create Allure report
+      env:
+        AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_DEV }}
+        AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_KEY_DEV }}
       if: ${{ !cancelled() }}
       uses: ./.github/actions/allure-report-generate
-      with:
-        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
     - name: Post to a Slack channel
       if: ${{ github.event.schedule && failure() }}
@@ -157,14 +148,6 @@ jobs:
         -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@v4
-      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: |

.github/workflows/pg-clients.yml

@@ -25,13 +25,11 @@ defaults:
   run:
     shell: bash -euxo pipefail {0}
 
-permissions:
-  id-token: write # aws-actions/configure-aws-credentials
-  statuses: write # require for posting a status update
-
 env:
   DEFAULT_PG_VERSION: 16
   PLATFORM: neon-captest-new
+  AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_DEV }}
+  AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_KEY_DEV }}
   AWS_DEFAULT_REGION: eu-central-1
 
 jobs:
@@ -96,7 +94,6 @@ jobs:
           name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
           path: /tmp/neon/
           prefix: latest
-          aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
       - name: Create Neon Project
         id: create-neon-project
@@ -113,7 +110,6 @@ jobs:
           run_in_parallel: false
           extra_params: -m remote_cluster
           pg_version: ${{ env.DEFAULT_PG_VERSION }}
-          aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
         env:
           BENCHMARK_CONNSTR: ${{ steps.create-neon-project.outputs.dsn }}
 
@@ -130,7 +126,6 @@ jobs:
         uses: ./.github/actions/allure-report-generate
         with:
           store-test-results-into-db: true
-          aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
         env:
           REGRESS_TEST_RESULT_CONNSTR_NEW: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}
 
@@ -164,7 +159,6 @@ jobs:
         name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
         path: /tmp/neon/
         prefix: latest
-        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
     - name: Create Neon Project
       id: create-neon-project
@@ -181,7 +175,6 @@ jobs:
         run_in_parallel: false
         extra_params: -m remote_cluster
         pg_version: ${{ env.DEFAULT_PG_VERSION }}
-        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
       env:
         BENCHMARK_CONNSTR: ${{ steps.create-neon-project.outputs.dsn }}
 
@@ -198,7 +191,6 @@ jobs:
       uses: ./.github/actions/allure-report-generate
       with:
         store-test-results-into-db: true
-        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
       env:
         REGRESS_TEST_RESULT_CONNSTR_NEW: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}
 

.github/workflows/pin-build-tools-image.yml

@@ -67,7 +67,7 @@ jobs:
     runs-on: ubuntu-22.04
 
     permissions:
-      id-token: write # for `azure/login` and aws auth
+      id-token: write # for `azure/login`
 
     steps:
       - uses: docker/login-action@v3
@@ -75,15 +75,11 @@ jobs:
           username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
           password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
 
-      - name: Configure AWS credentials
+      - uses: docker/login-action@v3
-        uses: aws-actions/configure-aws-credentials@v4
         with:
-          aws-region: eu-central-1
+          registry: 369495373322.dkr.ecr.eu-central-1.amazonaws.com
-          role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+          username: ${{ secrets.AWS_ACCESS_KEY_DEV }}
-          role-duration-seconds: 3600
+          password: ${{ secrets.AWS_SECRET_KEY_DEV }}
-
-      - name: Login to Amazon Dev ECR
-        uses: aws-actions/amazon-ecr-login@v2
 
       - name: Azure login
         uses: azure/login@6c251865b4e6290e7b78be643ea2d005bc51f69a  # @v2.1.1

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

@@ -63,7 +63,6 @@ jobs:
     if: always()
     permissions:
       statuses: write # for `github.repos.createCommitStatus(...)`
-      contents: write
     needs:
       - get-changed-files
       - check-codestyle-python

.github/workflows/release.yml

@@ -3,7 +3,7 @@ name: Create Release Branch
 on:
   schedule:
     # It should be kept in sync with if-condition in jobs
-    - cron: '0 6 * * FRI' # Storage release
+    - cron: '0 6 * * MON' # Storage release
     - cron: '0 6 * * THU' # Proxy release
   workflow_dispatch:
     inputs:
@@ -29,7 +29,7 @@ defaults:
 
 jobs:
   create-storage-release-branch:
-    if: ${{ github.event.schedule == '0 6 * * FRI' || inputs.create-storage-release-branch }}
+    if: ${{ github.event.schedule == '0 6 * * MON' || inputs.create-storage-release-branch }}
 
     permissions:
       contents: write

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

@@ -68,7 +68,7 @@ jobs:
       GH_TOKEN: ${{ secrets.CI_ACCESS_TOKEN }}
       TAG: ${{ needs.tag.outputs.build-tag }}
     steps:
-      - name: Wait for `promote-images-dev` job to finish
+      - name: Wait for `promote-images` job to finish
         # It's important to have a timeout here, the script in the step can run infinitely
         timeout-minutes: 60
         run: |
@@ -79,17 +79,17 @@ jobs:
           # For PRs we use the run id as the tag
           BUILD_AND_TEST_RUN_ID=${TAG}
           while true; do
-            conclusion=$(gh run --repo ${GITHUB_REPOSITORY} view ${BUILD_AND_TEST_RUN_ID} --json jobs --jq '.jobs[] | select(.name == "promote-images-dev") | .conclusion')
+            conclusion=$(gh run --repo ${GITHUB_REPOSITORY} view ${BUILD_AND_TEST_RUN_ID} --json jobs --jq '.jobs[] | select(.name == "promote-images") | .conclusion')
             case "$conclusion" in
               success)
                 break
                 ;;
               failure | cancelled | skipped)
-                echo "The 'promote-images-dev' job didn't succeed: '${conclusion}'. Exiting..."
+                echo "The 'promote-images' job didn't succeed: '${conclusion}'. Exiting..."
                 exit 1
                 ;;
               *)
-                echo "The 'promote-images-dev' hasn't succeed yet. Waiting..."
+                echo "The 'promote-images' hasn't succeed yet. Waiting..."
                 sleep 60
                 ;;
             esac

CODEOWNERS

@@ -1,29 +1,16 @@
-# Autoscaling
-/libs/vm_monitor/ @neondatabase/autoscaling
-
-# DevProd
 /.github/ @neondatabase/developer-productivity
-
+/compute_tools/ @neondatabase/control-plane @neondatabase/compute
-# Compute
+/libs/pageserver_api/ @neondatabase/storage
-/pgxn/ @neondatabase/compute
+/libs/postgres_ffi/ @neondatabase/compute @neondatabase/storage
-/vendor/ @neondatabase/compute
-/compute/ @neondatabase/compute
-/compute_tools/ @neondatabase/compute
-
-# Proxy
 /libs/proxy/ @neondatabase/proxy
-/proxy/ @neondatabase/proxy
+/libs/remote_storage/ @neondatabase/storage
-
+/libs/safekeeper_api/ @neondatabase/storage
-# Storage
+/libs/vm_monitor/ @neondatabase/autoscaling
 /pageserver/ @neondatabase/storage
+/pgxn/ @neondatabase/compute
+/pgxn/neon/ @neondatabase/compute @neondatabase/storage
+/proxy/ @neondatabase/proxy
 /safekeeper/ @neondatabase/storage
 /storage_controller @neondatabase/storage
 /storage_scrubber @neondatabase/storage
-/libs/pageserver_api/ @neondatabase/storage
+/vendor/ @neondatabase/compute
-/libs/remote_storage/ @neondatabase/storage
-/libs/safekeeper_api/ @neondatabase/storage
-
-# Shared
-/pgxn/neon/ @neondatabase/compute @neondatabase/storage
-/libs/compute_api/ @neondatabase/compute @neondatabase/control-plane
-/libs/postgres_ffi/ @neondatabase/compute @neondatabase/storage

Cargo.toml

@@ -11,7 +11,6 @@ members = [
     "pageserver/pagebench",
     "proxy",
     "safekeeper",
-    "safekeeper/client",
     "storage_broker",
     "storage_controller",
     "storage_controller/client",
@@ -52,7 +51,10 @@ anyhow = { version = "1.0", features = ["backtrace"] }
 arc-swap = "1.6"
 async-compression = { version = "0.4.0", features = ["tokio", "gzip", "zstd"] }
 atomic-take = "1.1.0"
-backtrace = "0.3.74"
+azure_core = { version = "0.19", default-features = false, features = ["enable_reqwest_rustls", "hmac_rust"] }
+azure_identity = { version = "0.19", default-features = false, features = ["enable_reqwest_rustls"] }
+azure_storage = { version = "0.19", default-features = false, features = ["enable_reqwest_rustls"] }
+azure_storage_blobs = { version = "0.19", default-features = false, features = ["enable_reqwest_rustls"] }
 flate2 = "1.0.26"
 async-stream = "0.3"
 async-trait = "0.1"
@@ -65,7 +67,7 @@ aws-smithy-types = "1.2"
 aws-credential-types = "1.2.0"
 aws-sigv4 = { version = "1.2", features = ["sign-http"] }
 aws-types = "1.3"
-axum = { version = "0.7.9", features = ["ws"] }
+axum = { version = "0.7.5", features = ["ws"] }
 base64 = "0.13.0"
 bincode = "1.3"
 bindgen = "0.70"
@@ -135,7 +137,7 @@ parquet = { version = "53", default-features = false, features = ["zstd"] }
 parquet_derive = "53"
 pbkdf2 = { version = "0.12.1", features = ["simple", "std"] }
 pin-project-lite = "0.2"
-pprof = { version = "0.14", features = ["criterion", "flamegraph", "frame-pointer", "protobuf", "protobuf-codec"] }
+pprof = { version = "0.14", features = ["criterion", "flamegraph", "protobuf", "protobuf-codec"] }
 procfs = "0.16"
 prometheus = {version = "0.13", default-features=false, features = ["process"]} # removes protobuf dependency
 prost = "0.13"
@@ -187,9 +189,7 @@ tokio-util = { version = "0.7.10", features = ["io", "rt"] }
 toml = "0.8"
 toml_edit = "0.22"
 tonic = {version = "0.12.3", features = ["tls", "tls-roots"]}
-tower = { version = "0.5.2", default-features = false }
+tower-service = "0.3.2"
-tower-http = { version = "0.6.2", features = ["request-id", "trace"] }
-tower-service = "0.3.3"
 tracing = "0.1"
 tracing-error = "0.2"
 tracing-opentelemetry = "0.27"
@@ -216,12 +216,6 @@ postgres-protocol = { git = "https://github.com/neondatabase/rust-postgres.git",
 postgres-types = { git = "https://github.com/neondatabase/rust-postgres.git", branch = "neon" }
 tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", branch = "neon" }
 
-## Azure SDK crates
-azure_core = { git = "https://github.com/neondatabase/azure-sdk-for-rust.git", branch = "neon", default-features = false, features = ["enable_reqwest_rustls", "hmac_rust"] }
-azure_identity = { git = "https://github.com/neondatabase/azure-sdk-for-rust.git", branch = "neon", default-features = false, features = ["enable_reqwest_rustls"] }
-azure_storage = { git = "https://github.com/neondatabase/azure-sdk-for-rust.git", branch = "neon", default-features = false, features = ["enable_reqwest_rustls"] }
-azure_storage_blobs = { git = "https://github.com/neondatabase/azure-sdk-for-rust.git", branch = "neon", default-features = false, features = ["enable_reqwest_rustls"] }
-
 ## Local libraries
 compute_api = { version = "0.1", path = "./libs/compute_api/" }
 consumption_metrics = { version = "0.1", path = "./libs/consumption_metrics/" }
@@ -237,7 +231,6 @@ postgres_initdb = { path = "./libs/postgres_initdb" }
 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" }
@@ -268,8 +261,6 @@ tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", br
 [profile.release]
 # This is useful for profiling and, to some extent, debug.
 # Besides, debug info should not affect the performance.
-#
-# NB: we also enable frame pointers for improved profiling, see .cargo/config.toml.
 debug = true
 
 # disable debug symbols for all packages except this one to decrease binaries size

Dockerfile

@@ -45,7 +45,7 @@ COPY --chown=nonroot . .
 
 ARG ADDITIONAL_RUSTFLAGS
 RUN set -e \
-    && PQ_LIB_DIR=$(pwd)/pg_install/v${STABLE_PG_VERSION}/lib RUSTFLAGS="-Clinker=clang -Clink-arg=-fuse-ld=mold -Clink-arg=-Wl,--no-rosegment -Cforce-frame-pointers=yes ${ADDITIONAL_RUSTFLAGS}" cargo build \
+    && PQ_LIB_DIR=$(pwd)/pg_install/v${STABLE_PG_VERSION}/lib RUSTFLAGS="-Clinker=clang -Clink-arg=-fuse-ld=mold -Clink-arg=-Wl,--no-rosegment ${ADDITIONAL_RUSTFLAGS}" cargo build \
       --bin pg_sni_router  \
       --bin pageserver  \
       --bin pagectl  \
@@ -69,8 +69,6 @@ RUN set -e \
         libreadline-dev \
         libseccomp-dev \
         ca-certificates \
-	# System postgres for use with client libraries (e.g. in storage controller)
-        postgresql-15 \
     && rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* \
     && useradd -d /data neon \
     && chown -R neon:neon /data
@@ -103,6 +101,11 @@ RUN mkdir -p /data/.neon/ && \
   > /data/.neon/pageserver.toml && \
   chown -R neon:neon /data/.neon
 
+# When running a binary that links with libpq, default to using our most recent postgres version.  Binaries
+# that want a particular postgres version will select it explicitly: this is just a default.
+ENV LD_LIBRARY_PATH=/usr/local/v${DEFAULT_PG_VERSION}/lib
+
+
 VOLUME ["/data"]
 USER neon
 EXPOSE 6400

build-tools.Dockerfile

@@ -115,7 +115,7 @@ RUN set -e \
 
 # Keep the version the same as in compute/compute-node.Dockerfile and
 # test_runner/regress/test_compute_metrics.py.
-ENV SQL_EXPORTER_VERSION=0.16.0
+ENV SQL_EXPORTER_VERSION=0.13.1
 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 \
@@ -258,7 +258,7 @@ WORKDIR /home/nonroot
 
 # Rust
 # Please keep the version of llvm (installed above) in sync with rust llvm (`rustc --version --verbose | grep LLVM`)
-ENV RUSTC_VERSION=1.84.0
+ENV RUSTC_VERSION=1.83.0
 ENV RUSTUP_HOME="/home/nonroot/.rustup"
 ENV PATH="/home/nonroot/.cargo/bin:${PATH}"
 ARG RUSTFILT_VERSION=0.2.1

compute/compute-node.Dockerfile

@@ -35,12 +35,10 @@ RUN case $DEBIAN_VERSION in \
       ;; \
     esac && \
     apt update &&  \
-    apt install --no-install-recommends --no-install-suggests -y \
+    apt install --no-install-recommends -y git autoconf automake libtool build-essential bison flex libreadline-dev \
-    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 \
-    $VERSION_INSTALLS \
+    $VERSION_INSTALLS
-    && apt clean && rm -rf /var/lib/apt/lists/*
 
 #########################################################################################
 #
@@ -115,12 +113,10 @@ ARG DEBIAN_VERSION
 ARG PG_VERSION
 COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
 RUN apt update && \
-    apt install --no-install-recommends --no-install-suggests -y \
+    apt install --no-install-recommends -y gdal-bin libboost-dev libboost-thread-dev libboost-filesystem-dev \
-    gdal-bin libboost-dev libboost-thread-dev libboost-filesystem-dev \
     libboost-system-dev libboost-iostreams-dev libboost-program-options-dev libboost-timer-dev \
     libcgal-dev libgdal-dev libgmp-dev libmpfr-dev libopenscenegraph-dev libprotobuf-c-dev \
-    protobuf-c-compiler xsltproc \
+    protobuf-c-compiler xsltproc
-    && apt clean && rm -rf /var/lib/apt/lists/*
 
 
 # Postgis 3.5.0 requires SFCGAL 1.4+
@@ -147,9 +143,9 @@ RUN case "${DEBIAN_VERSION}" in \
     wget https://gitlab.com/sfcgal/SFCGAL/-/archive/v${SFCGAL_VERSION}/SFCGAL-v${SFCGAL_VERSION}.tar.gz -O SFCGAL.tar.gz && \
     echo "${SFCGAL_CHECKSUM} SFCGAL.tar.gz" | sha256sum --check && \
     mkdir sfcgal-src && cd sfcgal-src && tar xzf ../SFCGAL.tar.gz --strip-components=1 -C . && \
-    cmake -DCMAKE_BUILD_TYPE=Release -GNinja . && ninja -j $(getconf _NPROCESSORS_ONLN) && \
+    cmake -DCMAKE_BUILD_TYPE=Release . && make -j $(getconf _NPROCESSORS_ONLN) && \
-    DESTDIR=/sfcgal ninja install -j $(getconf _NPROCESSORS_ONLN) && \
+    DESTDIR=/sfcgal make install -j $(getconf _NPROCESSORS_ONLN) && \
-    ninja clean && cp -R /sfcgal/* /
+    make clean && cp -R /sfcgal/* /
 
 ENV PATH="/usr/local/pgsql/bin:$PATH"
 
@@ -217,9 +213,9 @@ RUN case "${PG_VERSION}" in \
     echo "${PGROUTING_CHECKSUM} pgrouting.tar.gz" | sha256sum --check && \
     mkdir pgrouting-src && cd pgrouting-src && tar xzf ../pgrouting.tar.gz --strip-components=1 -C . && \
     mkdir build && cd build && \
-    cmake -GNinja -DCMAKE_BUILD_TYPE=Release .. && \
+    cmake -DCMAKE_BUILD_TYPE=Release .. && \
-    ninja -j $(getconf _NPROCESSORS_ONLN) && \
+    make -j $(getconf _NPROCESSORS_ONLN) && \
-    ninja -j $(getconf _NPROCESSORS_ONLN) install && \
+    make -j $(getconf _NPROCESSORS_ONLN) install && \
     echo 'trusted = true' >> /usr/local/pgsql/share/extension/pgrouting.control && \
     find /usr/local/pgsql -type f | sed 's|^/usr/local/pgsql/||' > /after.txt &&\
     cp /usr/local/pgsql/share/extension/pgrouting.control /extensions/postgis && \
@@ -239,9 +235,7 @@ COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
 COPY compute/patches/plv8-3.1.10.patch /plv8-3.1.10.patch
 
 RUN apt update && \
-    apt install --no-install-recommends --no-install-suggests -y \
+    apt install --no-install-recommends -y ninja-build python3-dev libncurses5 binutils clang
-    ninja-build python3-dev libncurses5 binutils clang \
-    && apt clean && rm -rf /var/lib/apt/lists/*
 
 # plv8 3.2.3 supports v17
 # last release v3.2.3 - Sep 7, 2024
@@ -307,10 +301,9 @@ RUN mkdir -p /h3/usr/ && \
     echo "ec99f1f5974846bde64f4513cf8d2ea1b8d172d2218ab41803bf6a63532272bc h3.tar.gz" | sha256sum --check && \
     mkdir h3-src && cd h3-src && tar xzf ../h3.tar.gz --strip-components=1 -C . && \
     mkdir build && cd build && \
-    cmake .. -GNinja -DBUILD_BENCHMARKS=0 -DCMAKE_BUILD_TYPE=Release \
+    cmake .. -DCMAKE_BUILD_TYPE=Release && \
-        -DBUILD_FUZZERS=0 -DBUILD_FILTERS=0 -DBUILD_GENERATORS=0 -DBUILD_TESTING=0 \
+    make -j $(getconf _NPROCESSORS_ONLN) && \
-    && ninja -j $(getconf _NPROCESSORS_ONLN) && \
+    DESTDIR=/h3 make install && \
-    DESTDIR=/h3 ninja install && \
     cp -R /h3/usr / && \
     rm -rf build
 
@@ -657,15 +650,14 @@ FROM build-deps AS rdkit-pg-build
 ARG PG_VERSION
 COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
 
-RUN apt update && \
+RUN apt-get update && \
-    apt install --no-install-recommends --no-install-suggests -y \
+    apt-get install --no-install-recommends -y \
         libboost-iostreams1.74-dev \
         libboost-regex1.74-dev \
         libboost-serialization1.74-dev \
         libboost-system1.74-dev \
         libeigen3-dev \
-        libboost-all-dev \
+        libboost-all-dev
-    && apt clean && rm -rf /var/lib/apt/lists/*
 
 # rdkit Release_2024_09_1 supports v17
 # last release Release_2024_09_1 - Sep 27, 2024
@@ -701,8 +693,6 @@ RUN case "${PG_VERSION}" in \
         -D RDK_BUILD_MOLINTERCHANGE_SUPPORT=OFF \
         -D RDK_BUILD_YAEHMOP_SUPPORT=OFF \
         -D RDK_BUILD_STRUCTCHECKER_SUPPORT=OFF \
-        -D RDK_TEST_MULTITHREADED=OFF \
-        -D RDK_BUILD_CPP_TESTS=OFF \
         -D RDK_USE_URF=OFF \
         -D RDK_BUILD_PGSQL=ON \
         -D RDK_PGSQL_STATIC=ON \
@@ -714,10 +704,9 @@ RUN case "${PG_VERSION}" in \
         -D RDK_INSTALL_COMIC_FONTS=OFF \
         -D RDK_BUILD_FREETYPE_SUPPORT=OFF \
         -D CMAKE_BUILD_TYPE=Release \
-        -GNinja \
         . && \
-    ninja -j $(getconf _NPROCESSORS_ONLN) && \
+    make -j $(getconf _NPROCESSORS_ONLN) && \
-    ninja -j $(getconf _NPROCESSORS_ONLN) install && \
+    make -j $(getconf _NPROCESSORS_ONLN) install && \
     echo 'trusted = true' >> /usr/local/pgsql/share/extension/rdkit.control
 
 #########################################################################################
@@ -860,9 +849,8 @@ FROM build-deps AS rust-extensions-build
 ARG PG_VERSION
 COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
 
-RUN apt update && \
+RUN apt-get update && \
-    apt install --no-install-recommends --no-install-suggests -y curl libclang-dev && \
+    apt-get install --no-install-recommends -y curl libclang-dev && \
-    apt clean && rm -rf /var/lib/apt/lists/* && \
     useradd -ms /bin/bash nonroot -b /home
 
 ENV HOME=/home/nonroot
@@ -897,9 +885,8 @@ FROM build-deps AS rust-extensions-build-pgrx12
 ARG PG_VERSION
 COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
 
-RUN apt update && \
+RUN apt-get update && \
-    apt install --no-install-recommends --no-install-suggests -y curl libclang-dev && \
+    apt-get install --no-install-recommends -y curl libclang-dev && \
-    apt clean && rm -rf /var/lib/apt/lists/* && \
     useradd -ms /bin/bash nonroot -b /home
 
 ENV HOME=/home/nonroot
@@ -927,22 +914,18 @@ FROM rust-extensions-build-pgrx12 AS pg-onnx-build
 
 # cmake 3.26 or higher is required, so installing it using pip (bullseye-backports has cmake 3.25).
 # Install it using virtual environment, because Python 3.11 (the default version on Debian 12 (Bookworm)) complains otherwise
-RUN apt update && apt install --no-install-recommends --no-install-suggests -y \
+RUN apt-get update && apt-get install -y python3 python3-pip python3-venv && \
-    python3 python3-pip python3-venv && \
-    apt clean && rm -rf /var/lib/apt/lists/* && \
     python3 -m venv venv && \
     . venv/bin/activate && \
     python3 -m pip install cmake==3.30.5 && \
     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 . && \
-    ./build.sh --config Release --parallel --cmake_generator Ninja \
+    ./build.sh --config Release --parallel --skip_submodule_sync --skip_tests --allow_running_as_root
-    --skip_submodule_sync --skip_tests --allow_running_as_root
 
 
 FROM pg-onnx-build AS pgrag-pg-build
 
-RUN apt update && apt install --no-install-recommends --no-install-suggests -y protobuf-compiler \
+RUN apt-get install -y protobuf-compiler && \
-    && apt clean && rm -rf /var/lib/apt/lists/* && \
     wget https://github.com/neondatabase-labs/pgrag/archive/refs/tags/v0.0.0.tar.gz -O pgrag.tar.gz &&  \
     echo "2cbe394c1e74fc8bcad9b52d5fbbfb783aef834ca3ce44626cfd770573700bb4 pgrag.tar.gz" | sha256sum --check && \
     mkdir pgrag-src && cd pgrag-src && tar xzf ../pgrag.tar.gz --strip-components=1 -C . && \
@@ -1185,25 +1168,6 @@ RUN case "${PG_VERSION}" in \
     make BUILD_TYPE=release -j $(getconf _NPROCESSORS_ONLN) install && \
     echo 'trusted = true' >> /usr/local/pgsql/share/extension/pg_mooncake.control
 
-#########################################################################################
-#
-# Layer "pg_repack"
-# compile pg_repack extension
-#
-#########################################################################################
-
-FROM build-deps AS pg-repack-build
-ARG PG_VERSION
-COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
-
-ENV PATH="/usr/local/pgsql/bin/:$PATH"
-
-RUN wget https://github.com/reorg/pg_repack/archive/refs/tags/ver_1.5.2.tar.gz -O pg_repack.tar.gz && \
-    echo '4516cad42251ed3ad53ff619733004db47d5755acac83f75924cd94d1c4fb681 pg_repack.tar.gz' | sha256sum --check && \
-    mkdir pg_repack-src && cd pg_repack-src && tar xzf ../pg_repack.tar.gz --strip-components=1 -C . && \
-    make -j $(getconf _NPROCESSORS_ONLN) && \
-    make -j $(getconf _NPROCESSORS_ONLN) install
-
 #########################################################################################
 #
 # Layer "neon-pg-ext-build"
@@ -1249,7 +1213,6 @@ COPY --from=pg-anon-pg-build /usr/local/pgsql/ /usr/local/pgsql/
 COPY --from=pg-ivm-build /usr/local/pgsql/ /usr/local/pgsql/
 COPY --from=pg-partman-build /usr/local/pgsql/ /usr/local/pgsql/
 COPY --from=pg-mooncake-build /usr/local/pgsql/ /usr/local/pgsql/
-COPY --from=pg-repack-build /usr/local/pgsql/ /usr/local/pgsql/
 COPY pgxn/ pgxn/
 
 RUN make -j $(getconf _NPROCESSORS_ONLN) \
@@ -1285,7 +1248,7 @@ RUN make -j $(getconf _NPROCESSORS_ONLN) \
 
 #########################################################################################
 #
-# Compile the Neon-specific `compute_ctl`, `fast_import`, and `local_proxy` binaries
+# Compile and run the Neon-specific `compute_ctl` and `fast_import` binaries
 #
 #########################################################################################
 FROM $REPOSITORY/$IMAGE:$TAG AS compute-tools
@@ -1295,7 +1258,7 @@ ENV BUILD_TAG=$BUILD_TAG
 USER nonroot
 # Copy entire project to get Cargo.* files with proper dependencies for the whole project
 COPY --chown=nonroot . .
-RUN mold -run cargo build --locked --profile release-line-debug-size-lto --bin compute_ctl --bin fast_import --bin local_proxy
+RUN cd compute_tools && mold -run cargo build --locked --profile release-line-debug-size-lto
 
 #########################################################################################
 #
@@ -1316,8 +1279,8 @@ COPY --from=compute-tools /home/nonroot/target/release-line-debug-size-lto/fast_
 
 FROM debian:$DEBIAN_FLAVOR AS pgbouncer
 RUN set -e \
-    && apt update \
+    && apt-get update \
-    && apt install --no-install-suggests --no-install-recommends -y \
+    && apt-get install --no-install-recommends -y \
         build-essential \
         git \
         ca-certificates \
@@ -1325,8 +1288,7 @@ RUN set -e \
         automake \
         libevent-dev \
         libtool \
-        pkg-config \
+        pkg-config
-    && apt clean && rm -rf /var/lib/apt/lists/*
 
 # Use `dist_man_MANS=` to skip manpage generation (which requires python3/pandoc)
 ENV PGBOUNCER_TAG=pgbouncer_1_22_1
@@ -1338,6 +1300,20 @@ RUN set -e \
     && make -j $(nproc) dist_man_MANS= \
     && make install dist_man_MANS=
 
+#########################################################################################
+#
+# Compile the Neon-specific `local_proxy` binary
+#
+#########################################################################################
+FROM $REPOSITORY/$IMAGE:$TAG AS local_proxy
+ARG BUILD_TAG
+ENV BUILD_TAG=$BUILD_TAG
+
+USER nonroot
+# Copy entire project to get Cargo.* files with proper dependencies for the whole project
+COPY --chown=nonroot . .
+RUN mold -run cargo build --locked --profile release-line-debug-size-lto --bin local_proxy
+
 #########################################################################################
 #
 # Layers "postgres-exporter" and "sql-exporter"
@@ -1348,7 +1324,7 @@ FROM quay.io/prometheuscommunity/postgres-exporter:v0.12.1 AS postgres-exporter
 
 # Keep the version the same as in build-tools.Dockerfile and
 # test_runner/regress/test_compute_metrics.py.
-FROM burningalchemist/sql_exporter:0.16.0 AS sql-exporter
+FROM burningalchemist/sql_exporter:0.13.1 AS sql-exporter
 
 #########################################################################################
 #
@@ -1477,7 +1453,7 @@ COPY --from=pgbouncer         /usr/local/pgbouncer/bin/pgbouncer /usr/local/bin/
 COPY --chmod=0666 --chown=postgres compute/etc/pgbouncer.ini /etc/pgbouncer.ini
 
 # local_proxy and its config
-COPY --from=compute-tools --chown=postgres /home/nonroot/target/release-line-debug-size-lto/local_proxy /usr/local/bin/local_proxy
+COPY --from=local_proxy --chown=postgres /home/nonroot/target/release-line-debug-size-lto/local_proxy /usr/local/bin/local_proxy
 RUN mkdir -p /etc/local_proxy && chown postgres:postgres /etc/local_proxy
 
 # Metrics exporter binaries and  configuration files
@@ -1542,30 +1518,28 @@ RUN apt update && \
         locales \
         procps \
         ca-certificates \
-        curl \
-        unzip \
         $VERSION_INSTALLS && \
-    apt clean && rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* && \
+    rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* && \
     localedef -i en_US -c -f UTF-8 -A /usr/share/locale/locale.alias en_US.UTF-8
 
-# aws cli is used by fast_import (curl and unzip above are at this time only used for this installation step)
+# s5cmd 2.2.2 from https://github.com/peak/s5cmd/releases/tag/v2.2.2
+# used by fast_import
 ARG TARGETARCH
+ADD https://github.com/peak/s5cmd/releases/download/v2.2.2/s5cmd_2.2.2_linux_$TARGETARCH.deb /tmp/s5cmd.deb
 RUN set -ex; \
+    \
+    # Determine the expected checksum based on TARGETARCH
     if [ "${TARGETARCH}" = "amd64" ]; then \
-        TARGETARCH_ALT="x86_64"; \
+        CHECKSUM="392c385320cd5ffa435759a95af77c215553d967e4b1c0fffe52e4f14c29cf85"; \
-        CHECKSUM="c9a9df3770a3ff9259cb469b6179e02829687a464e0824d5c32d378820b53a00"; \
     elif [ "${TARGETARCH}" = "arm64" ]; then \
-        TARGETARCH_ALT="aarch64"; \
+        CHECKSUM="939bee3cf4b5604ddb00e67f8c157b91d7c7a5b553d1fbb6890fad32894b7b46"; \
-        CHECKSUM="8181730be7891582b38b028112e81b4899ca817e8c616aad807c9e9d1289223a"; \
     else \
         echo "Unsupported architecture: ${TARGETARCH}"; exit 1; \
     fi; \
-    curl -L "https://awscli.amazonaws.com/awscli-exe-linux-${TARGETARCH_ALT}-2.17.5.zip" -o /tmp/awscliv2.zip; \
+    \
-    echo "${CHECKSUM}  /tmp/awscliv2.zip" | sha256sum -c -; \
+    # Compute and validate the checksum
-    unzip /tmp/awscliv2.zip -d /tmp/awscliv2; \
+    echo "${CHECKSUM}  /tmp/s5cmd.deb" | sha256sum -c -
-    /tmp/awscliv2/aws/install; \
+RUN dpkg -i /tmp/s5cmd.deb && rm /tmp/s5cmd.deb
-    rm -rf /tmp/awscliv2.zip /tmp/awscliv2; \
-    true
 
 ENV LANG=en_US.utf8
 USER postgres

compute/etc/neon_collector.jsonnet

@@ -3,7 +3,7 @@
   metrics: [
     import 'sql_exporter/checkpoints_req.libsonnet',
     import 'sql_exporter/checkpoints_timed.libsonnet',
-    import 'sql_exporter/compute_backpressure_throttling_seconds_total.libsonnet',
+    import 'sql_exporter/compute_backpressure_throttling_seconds.libsonnet',
     import 'sql_exporter/compute_current_lsn.libsonnet',
     import 'sql_exporter/compute_logical_snapshot_files.libsonnet',
     import 'sql_exporter/compute_logical_snapshots_bytes.libsonnet',

compute/etc/pgbouncer.ini

@@ -19,10 +19,3 @@ max_prepared_statements=0
 admin_users=postgres
 unix_socket_dir=/tmp/
 unix_socket_mode=0777
-
-;; 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
-;; the past where the logging significantly stressed the log device or pgbouncer
-;; itself.
-log_connections=0
-log_disconnections=0

compute/etc/sql_exporter/compute_backpressure_throttling_seconds.libsonnet

@@ -1,10 +1,10 @@
 {
-  metric_name: 'compute_backpressure_throttling_seconds_total',
+  metric_name: 'compute_backpressure_throttling_seconds',
-  type: 'counter',
+  type: 'gauge',
   help: 'Time compute has spent throttled',
   key_labels: null,
   values: [
     'throttled',
   ],
-  query: importstr 'sql_exporter/compute_backpressure_throttling_seconds_total.sql',
+  query: importstr 'sql_exporter/compute_backpressure_throttling_seconds.sql',
 }

compute/patches/cloud_regress_pg16.patch

@@ -981,7 +981,7 @@ index fc42d418bf..e38f517574 100644
  CREATE SCHEMA addr_nsp;
  SET search_path TO 'addr_nsp';
 diff --git a/src/test/regress/expected/password.out b/src/test/regress/expected/password.out
-index 8475231735..0653946337 100644
+index 8475231735..1afae5395f 100644
 --- a/src/test/regress/expected/password.out
 +++ b/src/test/regress/expected/password.out
 @@ -12,11 +12,11 @@ SET password_encryption = 'md5'; -- ok
@@ -1006,63 +1006,65 @@ index 8475231735..0653946337 100644
  -----------------+---------------------------------------------------
 - regress_passwd1 | md5783277baca28003b33453252be4dbb34
 - regress_passwd2 | md54044304ba511dd062133eb5b4b84a2a3
-+ regress_passwd1 | NEON_MD5_PLACEHOLDER:regress_passwd1
++ regress_passwd1 | NEON_MD5_PLACEHOLDER_regress_passwd1
-+ regress_passwd2 | NEON_MD5_PLACEHOLDER:regress_passwd2
++ regress_passwd2 | NEON_MD5_PLACEHOLDER_regress_passwd2
   regress_passwd3 | SCRAM-SHA-256$4096:<salt>$<storedkey>:<serverkey>
 - regress_passwd4 | 
 + regress_passwd4 | SCRAM-SHA-256$4096:<salt>$<storedkey>:<serverkey>
  (4 rows)
  
  -- Rename a role
-@@ -54,24 +54,16 @@ ALTER ROLE regress_passwd2_new RENAME TO regress_passwd2;
+@@ -54,24 +54,30 @@ ALTER ROLE regress_passwd2_new RENAME TO regress_passwd2;
  -- passwords.
  SET password_encryption = 'md5';
  -- encrypt with MD5
 -ALTER ROLE regress_passwd2 PASSWORD 'foo';
---- already encrypted, use as they are
--ALTER ROLE regress_passwd1 PASSWORD 'md5cd3578025fe2c3d7ed1b9a9b26238b70';
--ALTER ROLE regress_passwd3 PASSWORD 'SCRAM-SHA-256$4096:VLK4RMaQLCvNtQ==$6YtlR4t69SguDiwFvbVgVZtuz6gpJQQqUMZ7IQJK5yI=:ps75jrHeYU4lXCcXI4O8oIdJ3eO8o2jirjruw9phBTo=';
 +ALTER ROLE regress_passwd2 PASSWORD NEON_PASSWORD_PLACEHOLDER;
+ -- already encrypted, use as they are
+ ALTER ROLE regress_passwd1 PASSWORD 'md5cd3578025fe2c3d7ed1b9a9b26238b70';
++ERROR:  Received HTTP code 400 from control plane: {"error":"Neon only supports being given plaintext passwords"}
+ ALTER ROLE regress_passwd3 PASSWORD 'SCRAM-SHA-256$4096:VLK4RMaQLCvNtQ==$6YtlR4t69SguDiwFvbVgVZtuz6gpJQQqUMZ7IQJK5yI=:ps75jrHeYU4lXCcXI4O8oIdJ3eO8o2jirjruw9phBTo=';
++ERROR:  Received HTTP code 400 from control plane: {"error":"Neon only supports being given plaintext passwords"}
  SET password_encryption = 'scram-sha-256';
  -- create SCRAM secret
 -ALTER ROLE  regress_passwd4 PASSWORD 'foo';
---- already encrypted with MD5, use as it is
--CREATE ROLE regress_passwd5 PASSWORD 'md5e73a4b11df52a6068f8b39f90be36023';
---- This looks like a valid SCRAM-SHA-256 secret, but it is not
---- so it should be hashed with SCRAM-SHA-256.
--CREATE ROLE regress_passwd6 PASSWORD 'SCRAM-SHA-256$1234';
---- These may look like valid MD5 secrets, but they are not, so they
---- should be hashed with SCRAM-SHA-256.
---- trailing garbage at the end
--CREATE ROLE regress_passwd7 PASSWORD 'md5012345678901234567890123456789zz';
---- invalid length
--CREATE ROLE regress_passwd8 PASSWORD 'md501234567890123456789012345678901zz';
 +ALTER ROLE  regress_passwd4 PASSWORD NEON_PASSWORD_PLACEHOLDER;
-+-- Neon does not support encrypted passwords, use unencrypted instead
+ -- already encrypted with MD5, use as it is
-+CREATE ROLE regress_passwd5 PASSWORD NEON_PASSWORD_PLACEHOLDER;
+ CREATE ROLE regress_passwd5 PASSWORD 'md5e73a4b11df52a6068f8b39f90be36023';
-+-- Neon does not support encrypted passwords, use unencrypted instead
++ERROR:  Received HTTP code 400 from control plane: {"error":"Neon only supports being given plaintext passwords"}
-+CREATE ROLE regress_passwd6 PASSWORD NEON_PASSWORD_PLACEHOLDER;
+ -- This looks like a valid SCRAM-SHA-256 secret, but it is not
-+CREATE ROLE regress_passwd7 PASSWORD NEON_PASSWORD_PLACEHOLDER;
+ -- so it should be hashed with SCRAM-SHA-256.
-+CREATE ROLE regress_passwd8 PASSWORD NEON_PASSWORD_PLACEHOLDER;
+ CREATE ROLE regress_passwd6 PASSWORD 'SCRAM-SHA-256$1234';
++ERROR:  Received HTTP code 400 from control plane: {"error":"Neon only supports being given plaintext passwords"}
+ -- These may look like valid MD5 secrets, but they are not, so they
+ -- should be hashed with SCRAM-SHA-256.
+ -- trailing garbage at the end
+ CREATE ROLE regress_passwd7 PASSWORD 'md5012345678901234567890123456789zz';
++ERROR:  Received HTTP code 400 from control plane: {"error":"Neon only supports being given plaintext passwords"}
+ -- invalid length
+ CREATE ROLE regress_passwd8 PASSWORD 'md501234567890123456789012345678901zz';
++ERROR:  Received HTTP code 400 from control plane: {"error":"Neon only supports being given plaintext passwords"}
  -- Changing the SCRAM iteration count
  SET scram_iterations = 1024;
  CREATE ROLE regress_passwd9 PASSWORD 'alterediterationcount';
-@@ -81,11 +73,11 @@ SELECT rolname, regexp_replace(rolpassword, '(SCRAM-SHA-256)\$(\d+):([a-zA-Z0-9+
+@@ -81,63 +87,67 @@ SELECT rolname, regexp_replace(rolpassword, '(SCRAM-SHA-256)\$(\d+):([a-zA-Z0-9+
      ORDER BY rolname, rolpassword;
       rolname     |                rolpassword_masked                 
  -----------------+---------------------------------------------------
 - regress_passwd1 | md5cd3578025fe2c3d7ed1b9a9b26238b70
 - regress_passwd2 | md5dfa155cadd5f4ad57860162f3fab9cdb
-+ regress_passwd1 | NEON_MD5_PLACEHOLDER:regress_passwd1
++ regress_passwd1 | NEON_MD5_PLACEHOLDER_regress_passwd1
-+ regress_passwd2 | NEON_MD5_PLACEHOLDER:regress_passwd2
++ regress_passwd2 | NEON_MD5_PLACEHOLDER_regress_passwd2
   regress_passwd3 | SCRAM-SHA-256$4096:<salt>$<storedkey>:<serverkey>
   regress_passwd4 | SCRAM-SHA-256$4096:<salt>$<storedkey>:<serverkey>
 - regress_passwd5 | md5e73a4b11df52a6068f8b39f90be36023
-+ regress_passwd5 | SCRAM-SHA-256$4096:<salt>$<storedkey>:<serverkey>
+- regress_passwd6 | SCRAM-SHA-256$4096:<salt>$<storedkey>:<serverkey>
-  regress_passwd6 | SCRAM-SHA-256$4096:<salt>$<storedkey>:<serverkey>
+- regress_passwd7 | SCRAM-SHA-256$4096:<salt>$<storedkey>:<serverkey>
-  regress_passwd7 | SCRAM-SHA-256$4096:<salt>$<storedkey>:<serverkey>
+- regress_passwd8 | SCRAM-SHA-256$4096:<salt>$<storedkey>:<serverkey>
-  regress_passwd8 | SCRAM-SHA-256$4096:<salt>$<storedkey>:<serverkey>
+  regress_passwd9 | SCRAM-SHA-256$1024:<salt>$<storedkey>:<serverkey>
-@@ -95,23 +87,20 @@ SELECT rolname, regexp_replace(rolpassword, '(SCRAM-SHA-256)\$(\d+):([a-zA-Z0-9+
+-(9 rows)
++(5 rows)
+ 
  -- An empty password is not allowed, in any form
  CREATE ROLE regress_passwd_empty PASSWORD '';
  NOTICE:  empty string is not a valid password, clearing password
@@ -1080,37 +1082,56 @@ index 8475231735..0653946337 100644
 -(1 row)
 +(0 rows)
  
---- Test with invalid stored and server keys.
+ -- Test with invalid stored and server keys.
----
+ --
---- The first is valid, to act as a control. The others have too long
+ -- The first is valid, to act as a control. The others have too long
---- stored/server keys. They will be re-hashed.
+ -- stored/server keys. They will be re-hashed.
--CREATE ROLE regress_passwd_sha_len0 PASSWORD 'SCRAM-SHA-256$4096:A6xHKoH/494E941doaPOYg==$Ky+A30sewHIH3VHQLRN9vYsuzlgNyGNKCh37dy96Rqw=:COPdlNiIkrsacU5QoxydEuOH6e/KfiipeETb/bPw8ZI=';
+ CREATE ROLE regress_passwd_sha_len0 PASSWORD 'SCRAM-SHA-256$4096:A6xHKoH/494E941doaPOYg==$Ky+A30sewHIH3VHQLRN9vYsuzlgNyGNKCh37dy96Rqw=:COPdlNiIkrsacU5QoxydEuOH6e/KfiipeETb/bPw8ZI=';
--CREATE ROLE regress_passwd_sha_len1 PASSWORD 'SCRAM-SHA-256$4096:A6xHKoH/494E941doaPOYg==$Ky+A30sewHIH3VHQLRN9vYsuzlgNyGNKCh37dy96RqwAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA=:COPdlNiIkrsacU5QoxydEuOH6e/KfiipeETb/bPw8ZI=';
++ERROR:  Received HTTP code 400 from control plane: {"error":"Neon only supports being given plaintext passwords"}
--CREATE ROLE regress_passwd_sha_len2 PASSWORD 'SCRAM-SHA-256$4096:A6xHKoH/494E941doaPOYg==$Ky+A30sewHIH3VHQLRN9vYsuzlgNyGNKCh37dy96Rqw=:COPdlNiIkrsacU5QoxydEuOH6e/KfiipeETb/bPw8ZIAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA=';
+ CREATE ROLE regress_passwd_sha_len1 PASSWORD 'SCRAM-SHA-256$4096:A6xHKoH/494E941doaPOYg==$Ky+A30sewHIH3VHQLRN9vYsuzlgNyGNKCh37dy96RqwAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA=:COPdlNiIkrsacU5QoxydEuOH6e/KfiipeETb/bPw8ZI=';
-+-- Neon does not support encrypted passwords, use unencrypted instead
++ERROR:  Received HTTP code 400 from control plane: {"error":"Neon only supports being given plaintext passwords"}
-+CREATE ROLE regress_passwd_sha_len0 PASSWORD NEON_PASSWORD_PLACEHOLDER;
+ CREATE ROLE regress_passwd_sha_len2 PASSWORD 'SCRAM-SHA-256$4096:A6xHKoH/494E941doaPOYg==$Ky+A30sewHIH3VHQLRN9vYsuzlgNyGNKCh37dy96Rqw=:COPdlNiIkrsacU5QoxydEuOH6e/KfiipeETb/bPw8ZIAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA=';
-+CREATE ROLE regress_passwd_sha_len1 PASSWORD NEON_PASSWORD_PLACEHOLDER;
++ERROR:  Received HTTP code 400 from control plane: {"error":"Neon only supports being given plaintext passwords"}
-+CREATE ROLE regress_passwd_sha_len2 PASSWORD NEON_PASSWORD_PLACEHOLDER;
  -- Check that the invalid secrets were re-hashed. A re-hashed secret
  -- should not contain the original salt.
  SELECT rolname, rolpassword not like '%A6xHKoH/494E941doaPOYg==%' as is_rolpassword_rehashed
-@@ -120,7 +109,7 @@ SELECT rolname, rolpassword not like '%A6xHKoH/494E941doaPOYg==%' as is_rolpassw
+     FROM pg_authid
+     WHERE rolname LIKE 'regress_passwd_sha_len%'
      ORDER BY rolname;
-          rolname         | is_rolpassword_rehashed 
+-         rolname         | is_rolpassword_rehashed 
- -------------------------+-------------------------
+--------------------------+-------------------------
 - regress_passwd_sha_len0 | f
-+ regress_passwd_sha_len0 | t
+- regress_passwd_sha_len1 | t
-  regress_passwd_sha_len1 | t
+- regress_passwd_sha_len2 | t
-  regress_passwd_sha_len2 | t
+-(3 rows)
- (3 rows)
++ rolname | is_rolpassword_rehashed 
-@@ -135,6 +124,7 @@ DROP ROLE regress_passwd7;
++---------+-------------------------
++(0 rows)
+ 
+ DROP ROLE regress_passwd1;
+ DROP ROLE regress_passwd2;
+ DROP ROLE regress_passwd3;
+ DROP ROLE regress_passwd4;
+ DROP ROLE regress_passwd5;
++ERROR:  role "regress_passwd5" does not exist
+ DROP ROLE regress_passwd6;
++ERROR:  role "regress_passwd6" does not exist
+ DROP ROLE regress_passwd7;
++ERROR:  role "regress_passwd7" does not exist
  DROP ROLE regress_passwd8;
++ERROR:  role "regress_passwd8" does not exist
  DROP ROLE regress_passwd9;
  DROP ROLE regress_passwd_empty;
 +ERROR:  role "regress_passwd_empty" does not exist
  DROP ROLE regress_passwd_sha_len0;
++ERROR:  role "regress_passwd_sha_len0" does not exist
  DROP ROLE regress_passwd_sha_len1;
++ERROR:  role "regress_passwd_sha_len1" does not exist
  DROP ROLE regress_passwd_sha_len2;
++ERROR:  role "regress_passwd_sha_len2" does not exist
+ -- all entries should have been removed
+ SELECT rolname, rolpassword
+     FROM pg_authid
 diff --git a/src/test/regress/expected/privileges.out b/src/test/regress/expected/privileges.out
 index 5b9dba7b32..cc408dad42 100644
 --- a/src/test/regress/expected/privileges.out
@@ -3173,7 +3194,7 @@ index 1a6c61f49d..1c31ac6a53 100644
  -- Test generic object addressing/identification functions
  CREATE SCHEMA addr_nsp;
 diff --git a/src/test/regress/sql/password.sql b/src/test/regress/sql/password.sql
-index 53e86b0b6c..0303fdfe96 100644
+index 53e86b0b6c..f07cf1ec54 100644
 --- a/src/test/regress/sql/password.sql
 +++ b/src/test/regress/sql/password.sql
 @@ -10,11 +10,11 @@ SET password_encryption = 'scram-sha-256'; -- ok
@@ -3192,59 +3213,23 @@ index 53e86b0b6c..0303fdfe96 100644
  
  -- check list of created entries
  --
-@@ -42,26 +42,18 @@ ALTER ROLE regress_passwd2_new RENAME TO regress_passwd2;
+@@ -42,14 +42,14 @@ ALTER ROLE regress_passwd2_new RENAME TO regress_passwd2;
  SET password_encryption = 'md5';
  
  -- encrypt with MD5
 -ALTER ROLE regress_passwd2 PASSWORD 'foo';
---- already encrypted, use as they are
--ALTER ROLE regress_passwd1 PASSWORD 'md5cd3578025fe2c3d7ed1b9a9b26238b70';
--ALTER ROLE regress_passwd3 PASSWORD 'SCRAM-SHA-256$4096:VLK4RMaQLCvNtQ==$6YtlR4t69SguDiwFvbVgVZtuz6gpJQQqUMZ7IQJK5yI=:ps75jrHeYU4lXCcXI4O8oIdJ3eO8o2jirjruw9phBTo=';
 +ALTER ROLE regress_passwd2 PASSWORD NEON_PASSWORD_PLACEHOLDER;
+ -- already encrypted, use as they are
+ ALTER ROLE regress_passwd1 PASSWORD 'md5cd3578025fe2c3d7ed1b9a9b26238b70';
+ ALTER ROLE regress_passwd3 PASSWORD 'SCRAM-SHA-256$4096:VLK4RMaQLCvNtQ==$6YtlR4t69SguDiwFvbVgVZtuz6gpJQQqUMZ7IQJK5yI=:ps75jrHeYU4lXCcXI4O8oIdJ3eO8o2jirjruw9phBTo=';
  
  SET password_encryption = 'scram-sha-256';
  -- create SCRAM secret
 -ALTER ROLE  regress_passwd4 PASSWORD 'foo';
---- already encrypted with MD5, use as it is
--CREATE ROLE regress_passwd5 PASSWORD 'md5e73a4b11df52a6068f8b39f90be36023';
 +ALTER ROLE  regress_passwd4 PASSWORD NEON_PASSWORD_PLACEHOLDER;
-+-- Neon does not support encrypted passwords, use unencrypted instead
+ -- already encrypted with MD5, use as it is
-+CREATE ROLE regress_passwd5 PASSWORD NEON_PASSWORD_PLACEHOLDER;
+ CREATE ROLE regress_passwd5 PASSWORD 'md5e73a4b11df52a6068f8b39f90be36023';
  
---- This looks like a valid SCRAM-SHA-256 secret, but it is not
---- so it should be hashed with SCRAM-SHA-256.
--CREATE ROLE regress_passwd6 PASSWORD 'SCRAM-SHA-256$1234';
---- These may look like valid MD5 secrets, but they are not, so they
---- should be hashed with SCRAM-SHA-256.
---- trailing garbage at the end
--CREATE ROLE regress_passwd7 PASSWORD 'md5012345678901234567890123456789zz';
---- invalid length
--CREATE ROLE regress_passwd8 PASSWORD 'md501234567890123456789012345678901zz';
-+-- Neon does not support encrypted passwords, use unencrypted instead
-+CREATE ROLE regress_passwd6 PASSWORD NEON_PASSWORD_PLACEHOLDER;
-+CREATE ROLE regress_passwd7 PASSWORD NEON_PASSWORD_PLACEHOLDER;
-+CREATE ROLE regress_passwd8 PASSWORD NEON_PASSWORD_PLACEHOLDER;
- 
- -- Changing the SCRAM iteration count
- SET scram_iterations = 1024;
-@@ -78,13 +70,10 @@ ALTER ROLE regress_passwd_empty PASSWORD 'md585939a5ce845f1a1b620742e3c659e0a';
- ALTER ROLE regress_passwd_empty PASSWORD 'SCRAM-SHA-256$4096:hpFyHTUsSWcR7O9P$LgZFIt6Oqdo27ZFKbZ2nV+vtnYM995pDh9ca6WSi120=:qVV5NeluNfUPkwm7Vqat25RjSPLkGeoZBQs6wVv+um4=';
- SELECT rolpassword FROM pg_authid WHERE rolname='regress_passwd_empty';
- 
---- Test with invalid stored and server keys.
----
---- The first is valid, to act as a control. The others have too long
---- stored/server keys. They will be re-hashed.
--CREATE ROLE regress_passwd_sha_len0 PASSWORD 'SCRAM-SHA-256$4096:A6xHKoH/494E941doaPOYg==$Ky+A30sewHIH3VHQLRN9vYsuzlgNyGNKCh37dy96Rqw=:COPdlNiIkrsacU5QoxydEuOH6e/KfiipeETb/bPw8ZI=';
--CREATE ROLE regress_passwd_sha_len1 PASSWORD 'SCRAM-SHA-256$4096:A6xHKoH/494E941doaPOYg==$Ky+A30sewHIH3VHQLRN9vYsuzlgNyGNKCh37dy96RqwAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA=:COPdlNiIkrsacU5QoxydEuOH6e/KfiipeETb/bPw8ZI=';
--CREATE ROLE regress_passwd_sha_len2 PASSWORD 'SCRAM-SHA-256$4096:A6xHKoH/494E941doaPOYg==$Ky+A30sewHIH3VHQLRN9vYsuzlgNyGNKCh37dy96Rqw=:COPdlNiIkrsacU5QoxydEuOH6e/KfiipeETb/bPw8ZIAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA=';
-+-- Neon does not support encrypted passwords, use unencrypted instead
-+CREATE ROLE regress_passwd_sha_len0 PASSWORD NEON_PASSWORD_PLACEHOLDER;
-+CREATE ROLE regress_passwd_sha_len1 PASSWORD NEON_PASSWORD_PLACEHOLDER;
-+CREATE ROLE regress_passwd_sha_len2 PASSWORD NEON_PASSWORD_PLACEHOLDER;
- 
- -- Check that the invalid secrets were re-hashed. A re-hashed secret
- -- should not contain the original salt.
 diff --git a/src/test/regress/sql/privileges.sql b/src/test/regress/sql/privileges.sql
 index 249df17a58..b258e7f26a 100644
 --- a/src/test/regress/sql/privileges.sql

compute_tools/Cargo.toml

@@ -7,7 +7,7 @@ license.workspace = true
 [features]
 default = []
 # Enables test specific features.
-testing = ["fail/failpoints"]
+testing = []
 
 [dependencies]
 base64.workspace = true
@@ -15,15 +15,13 @@ aws-config.workspace = true
 aws-sdk-s3.workspace = true
 aws-sdk-kms.workspace = true
 anyhow.workspace = true
-axum = { workspace = true, features = [] }
 camino.workspace = true
 chrono.workspace = true
 cfg-if.workspace = true
 clap.workspace = true
-fail.workspace = true
 flate2.workspace = true
 futures.workspace = true
-http.workspace = true
+hyper0 = { workspace = true, features = ["full"] }
 metrics.workspace = true
 nix.workspace = true
 notify.workspace = true
@@ -38,8 +36,6 @@ serde_with.workspace = true
 serde_json.workspace = true
 signal-hook.workspace = true
 tar.workspace = true
-tower.workspace = true
-tower-http.workspace = true
 reqwest = { workspace = true, features = ["json"] }
 tokio = { workspace = true, features = ["rt", "rt-multi-thread"] }
 tokio-postgres.workspace = true

compute_tools/src/bin/compute_ctl.rs

@@ -60,22 +60,19 @@ use compute_tools::compute::{
 };
 use compute_tools::configurator::launch_configurator;
 use compute_tools::extension_server::get_pg_version_string;
-use compute_tools::http::launch_http_server;
+use compute_tools::http::api::launch_http_server;
 use compute_tools::logger::*;
 use compute_tools::monitor::launch_monitor;
 use compute_tools::params::*;
 use compute_tools::spec::*;
 use compute_tools::swap::resize_swap;
 use rlimit::{setrlimit, Resource};
-use utils::failpoint_support;
 
 // this is an arbitrary build tag. Fine as a default / for testing purposes
 // in-case of not-set environment var
 const BUILD_TAG_DEFAULT: &str = "latest";
 
 fn main() -> Result<()> {
-    let scenario = failpoint_support::init();
-
     let (build_tag, clap_args) = init()?;
 
     // enable core dumping for all child processes
@@ -103,8 +100,6 @@ fn main() -> Result<()> {
 
     maybe_delay_exit(delay_exit);
 
-    scenario.teardown();
-
     deinit_and_exit(wait_pg_result);
 }
 
@@ -251,48 +246,47 @@ fn try_spec_from_cli(
     let compute_id = matches.get_one::<String>("compute-id");
     let control_plane_uri = matches.get_one::<String>("control-plane-uri");
 
-    // First, try to get cluster spec from the cli argument
+    let spec;
-    if let Some(spec_json) = spec_json {
+    let mut live_config_allowed = false;
-        info!("got spec from cli argument {}", spec_json);
+    match spec_json {
-        return Ok(CliSpecParams {
+        // First, try to get cluster spec from the cli argument
-            spec: Some(serde_json::from_str(spec_json)?),
+        Some(json) => {
-            live_config_allowed: false,
+            info!("got spec from cli argument {}", json);
-        });
+            spec = Some(serde_json::from_str(json)?);
-    }
-
-    // Second, try to read it from the file if path is provided
-    if let Some(spec_path) = spec_path {
-        let file = File::open(Path::new(spec_path))?;
-        return Ok(CliSpecParams {
-            spec: Some(serde_json::from_reader(file)?),
-            live_config_allowed: true,
-        });
-    }
-
-    let Some(compute_id) = compute_id else {
-        panic!(
-            "compute spec should be provided by one of the following ways: \
-                --spec OR --spec-path OR --control-plane-uri and --compute-id"
-        );
-    };
-    let Some(control_plane_uri) = control_plane_uri else {
-        panic!("must specify both --control-plane-uri and --compute-id or none");
-    };
-
-    match get_spec_from_control_plane(control_plane_uri, compute_id) {
-        Ok(spec) => Ok(CliSpecParams {
-            spec,
-            live_config_allowed: true,
-        }),
-        Err(e) => {
-            error!(
-                "cannot get response from control plane: {}\n\
-                neither spec nor confirmation that compute is in the Empty state was received",
-                e
-            );
-            Err(e)
         }
-    }
+        None => {
+            // Second, try to read it from the file if path is provided
+            if let Some(sp) = spec_path {
+                let path = Path::new(sp);
+                let file = File::open(path)?;
+                spec = Some(serde_json::from_reader(file)?);
+                live_config_allowed = true;
+            } else if let Some(id) = compute_id {
+                if let Some(cp_base) = control_plane_uri {
+                    live_config_allowed = true;
+                    spec = match get_spec_from_control_plane(cp_base, id) {
+                        Ok(s) => s,
+                        Err(e) => {
+                            error!("cannot get response from control plane: {}", e);
+                            panic!("neither spec nor confirmation that compute is in the Empty state was received");
+                        }
+                    };
+                } else {
+                    panic!("must specify both --control-plane-uri and --compute-id or none");
+                }
+            } else {
+                panic!(
+                    "compute spec should be provided by one of the following ways: \
+                    --spec OR --spec-path OR --control-plane-uri and --compute-id"
+                );
+            }
+        }
+    };
+
+    Ok(CliSpecParams {
+        spec,
+        live_config_allowed,
+    })
 }
 
 struct CliSpecParams {
@@ -424,14 +418,9 @@ fn start_postgres(
         "running compute with features: {:?}",
         state.pspec.as_ref().unwrap().spec.features
     );
-    // before we release the mutex, fetch some parameters for later.
+    // before we release the mutex, fetch the swap size (if any) for later.
-    let &ComputeSpec {
+    let swap_size_bytes = state.pspec.as_ref().unwrap().spec.swap_size_bytes;
-        swap_size_bytes,
+    let disk_quota_bytes = state.pspec.as_ref().unwrap().spec.disk_quota_bytes;
-        disk_quota_bytes,
-        #[cfg(target_os = "linux")]
-        disable_lfc_resizing,
-        ..
-    } = &state.pspec.as_ref().unwrap().spec;
     drop(state);
 
     // Launch remaining service threads
@@ -493,10 +482,7 @@ fn start_postgres(
     let mut pg = None;
     if !prestartup_failed {
         pg = match compute.start_compute() {
-            Ok(pg) => {
+            Ok(pg) => Some(pg),
-                info!(postmaster_pid = %pg.0.id(), "Postgres was started");
-                Some(pg)
-            }
             Err(err) => {
                 error!("could not start the compute node: {:#}", err);
                 compute.set_failed_status(err);
@@ -539,18 +525,11 @@ fn start_postgres(
             // This token is used internally by the monitor to clean up all threads
             let token = CancellationToken::new();
 
-            // don't pass postgres connection string to vm-monitor if we don't want it to resize LFC
-            let pgconnstr = if disable_lfc_resizing.unwrap_or(false) {
-                None
-            } else {
-                file_cache_connstr.cloned()
-            };
-
             let vm_monitor = rt.as_ref().map(|rt| {
                 rt.spawn(vm_monitor::start(
                     Box::leak(Box::new(vm_monitor::Args {
                         cgroup: cgroup.cloned(),
-                        pgconnstr,
+                        pgconnstr: file_cache_connstr.cloned(),
                         addr: vm_monitor_addr.clone(),
                     })),
                     token.clone(),
@@ -594,8 +573,6 @@ fn wait_postgres(pg: Option<PostgresHandle>) -> Result<WaitPostgresResult> {
     // propagate to Postgres and it will be shut down as well.
     let mut exit_code = None;
     if let Some((mut pg, logs_handle)) = pg {
-        info!(postmaster_pid = %pg.id(), "Waiting for Postgres to exit");
-
         let ecode = pg
             .wait()
             .expect("failed to start waiting on Postgres process");

compute_tools/src/bin/fast_import.rs

@@ -34,12 +34,12 @@ use nix::unistd::Pid;
 use tracing::{info, info_span, warn, Instrument};
 use utils::fs_ext::is_directory_empty;
 
-#[path = "fast_import/aws_s3_sync.rs"]
-mod aws_s3_sync;
 #[path = "fast_import/child_stdio_to_log.rs"]
 mod child_stdio_to_log;
 #[path = "fast_import/s3_uri.rs"]
 mod s3_uri;
+#[path = "fast_import/s5cmd.rs"]
+mod s5cmd;
 
 #[derive(clap::Parser)]
 struct Args {
@@ -326,7 +326,7 @@ pub(crate) async fn main() -> anyhow::Result<()> {
     }
 
     info!("upload pgdata");
-    aws_s3_sync::sync(Utf8Path::new(&pgdata_dir), &s3_prefix.append("/pgdata/"))
+    s5cmd::sync(Utf8Path::new(&pgdata_dir), &s3_prefix.append("/"))
         .await
         .context("sync dump directory to destination")?;
 
@@ -334,10 +334,10 @@ pub(crate) async fn main() -> anyhow::Result<()> {
     {
         let status_dir = working_directory.join("status");
         std::fs::create_dir(&status_dir).context("create status directory")?;
-        let status_file = status_dir.join("pgdata");
+        let status_file = status_dir.join("status");
         std::fs::write(&status_file, serde_json::json!({"done": true}).to_string())
             .context("write status file")?;
-        aws_s3_sync::sync(&status_dir, &s3_prefix.append("/status/"))
+        s5cmd::sync(&status_file, &s3_prefix.append("/status/pgdata"))
             .await
             .context("sync status directory to destination")?;
     }

compute_tools/src/bin/fast_import/s5cmd.rs

@@ -4,21 +4,24 @@ use camino::Utf8Path;
 use super::s3_uri::S3Uri;
 
 pub(crate) async fn sync(local: &Utf8Path, remote: &S3Uri) -> anyhow::Result<()> {
-    let mut builder = tokio::process::Command::new("aws");
+    let mut builder = tokio::process::Command::new("s5cmd");
+    // s5cmd uses aws-sdk-go v1, hence doesn't support AWS_ENDPOINT_URL
+    if let Some(val) = std::env::var_os("AWS_ENDPOINT_URL") {
+        builder.arg("--endpoint-url").arg(val);
+    }
     builder
-        .arg("s3")
         .arg("sync")
         .arg(local.as_str())
         .arg(remote.to_string());
     let st = builder
         .spawn()
-        .context("spawn aws s3 sync")?
+        .context("spawn s5cmd")?
         .wait()
         .await
-        .context("wait for aws s3 sync")?;
+        .context("wait for s5cmd")?;
     if st.success() {
         Ok(())
     } else {
-        Err(anyhow::anyhow!("aws s3 sync failed"))
+        Err(anyhow::anyhow!("s5cmd failed"))
     }
 }

compute_tools/src/catalog.rs

@@ -36,11 +36,11 @@ pub async fn get_dbs_and_roles(compute: &Arc<ComputeNode>) -> anyhow::Result<Cat
 
 #[derive(Debug, thiserror::Error)]
 pub enum SchemaDumpError {
-    #[error("database does not exist")]
+    #[error("Database does not exist.")]
     DatabaseDoesNotExist,
-    #[error("failed to execute pg_dump")]
+    #[error("Failed to execute pg_dump.")]
     IO(#[from] std::io::Error),
-    #[error("unexpected I/O error")]
+    #[error("Unexpected error.")]
     Unexpected,
 }
 

compute_tools/src/compute.rs

@@ -15,7 +15,7 @@ use std::time::Instant;
 
 use anyhow::{Context, Result};
 use chrono::{DateTime, Utc};
-use compute_api::spec::{Database, PgIdent, Role};
+use compute_api::spec::{PgIdent, Role};
 use futures::future::join_all;
 use futures::stream::FuturesUnordered;
 use futures::StreamExt;
@@ -45,10 +45,8 @@ use crate::spec_apply::ApplySpecPhase::{
     DropInvalidDatabases, DropRoles, HandleNeonExtension, HandleOtherExtensions,
     RenameAndDeleteDatabases, RenameRoles, RunInEachDatabase,
 };
-use crate::spec_apply::PerDatabasePhase;
 use crate::spec_apply::PerDatabasePhase::{
-    ChangeSchemaPerms, DeleteDBRoleReferences, DropSubscriptionsForDeletedDatabases,
+    ChangeSchemaPerms, DeleteDBRoleReferences, HandleAnonExtension,
-    HandleAnonExtension,
 };
 use crate::spec_apply::{apply_operations, MutableApplyContext, DB};
 use crate::sync_sk::{check_if_synced, ping_safekeeper};
@@ -836,7 +834,7 @@ impl ComputeNode {
         conf
     }
 
-    pub async fn get_maintenance_client(
+    async fn get_maintenance_client(
         conf: &tokio_postgres::Config,
     ) -> Result<tokio_postgres::Client> {
         let mut conf = conf.clone();
@@ -945,78 +943,6 @@ impl ComputeNode {
                 dbs: databases,
             }));
 
-            // Apply special pre drop database phase.
-            // NOTE: we use the code of RunInEachDatabase phase for parallelism
-            // and connection management, but we don't really run it in *each* database,
-            // only in databases, we're about to drop.
-            info!("Applying PerDatabase (pre-dropdb) phase");
-            let concurrency_token = Arc::new(tokio::sync::Semaphore::new(concurrency));
-
-            // Run the phase for each database that we're about to drop.
-            let db_processes = spec
-                .delta_operations
-                .iter()
-                .flatten()
-                .filter_map(move |op| {
-                    if op.action.as_str() == "delete_db" {
-                        Some(op.name.clone())
-                    } else {
-                        None
-                    }
-                })
-                .map(|dbname| {
-                    let spec = spec.clone();
-                    let ctx = ctx.clone();
-                    let jwks_roles = jwks_roles.clone();
-                    let mut conf = conf.as_ref().clone();
-                    let concurrency_token = concurrency_token.clone();
-                    // We only need dbname field for this phase, so set other fields to dummy values
-                    let db = DB::UserDB(Database {
-                        name: dbname.clone(),
-                        owner: "cloud_admin".to_string(),
-                        options: None,
-                        restrict_conn: false,
-                        invalid: false,
-                    });
-
-                    debug!("Applying per-database phases for Database {:?}", &db);
-
-                    match &db {
-                        DB::SystemDB => {}
-                        DB::UserDB(db) => {
-                            conf.dbname(db.name.as_str());
-                        }
-                    }
-
-                    let conf = Arc::new(conf);
-                    let fut = Self::apply_spec_sql_db(
-                        spec.clone(),
-                        conf,
-                        ctx.clone(),
-                        jwks_roles.clone(),
-                        concurrency_token.clone(),
-                        db,
-                        [DropSubscriptionsForDeletedDatabases].to_vec(),
-                    );
-
-                    Ok(spawn(fut))
-                })
-                .collect::<Vec<Result<_, anyhow::Error>>>();
-
-            for process in db_processes.into_iter() {
-                let handle = process?;
-                if let Err(e) = handle.await? {
-                    // Handle the error case where the database does not exist
-                    // We do not check whether the DB exists or not in the deletion phase,
-                    // so we shouldn't be strict about it in pre-deletion cleanup as well.
-                    if e.to_string().contains("does not exist") {
-                        warn!("Error dropping subscription: {}", e);
-                    } else {
-                        return Err(e);
-                    }
-                };
-            }
-
             for phase in [
                 CreateSuperUser,
                 DropInvalidDatabases,
@@ -1036,7 +962,7 @@ impl ComputeNode {
                 .await?;
             }
 
-            info!("Applying RunInEachDatabase2 phase");
+            info!("Applying RunInEachDatabase phase");
             let concurrency_token = Arc::new(tokio::sync::Semaphore::new(concurrency));
 
             let db_processes = spec
@@ -1071,12 +997,6 @@ impl ComputeNode {
                         jwks_roles.clone(),
                         concurrency_token.clone(),
                         db,
-                        [
-                            DeleteDBRoleReferences,
-                            ChangeSchemaPerms,
-                            HandleAnonExtension,
-                        ]
-                        .to_vec(),
                     );
 
                     Ok(spawn(fut))
@@ -1123,13 +1043,16 @@ impl ComputeNode {
         jwks_roles: Arc<HashSet<String>>,
         concurrency_token: Arc<tokio::sync::Semaphore>,
         db: DB,
-        subphases: Vec<PerDatabasePhase>,
     ) -> Result<()> {
         let _permit = concurrency_token.acquire().await?;
 
         let mut client_conn = None;
 
-        for subphase in subphases {
+        for subphase in [
+            DeleteDBRoleReferences,
+            ChangeSchemaPerms,
+            HandleAnonExtension,
+        ] {
             apply_operations(
                 spec.clone(),
                 ctx.clone(),
@@ -1258,19 +1181,8 @@ impl ComputeNode {
             let mut conf = postgres::config::Config::from(conf);
             conf.application_name("compute_ctl:migrations");
 
-            match conf.connect(NoTls) {
+            let mut client = conf.connect(NoTls)?;
-                Ok(mut client) => {
+            handle_migrations(&mut client).context("apply_config handle_migrations")
-                    if let Err(e) = handle_migrations(&mut client) {
-                        error!("Failed to run migrations: {}", e);
-                    }
-                }
-                Err(e) => {
-                    error!(
-                        "Failed to connect to the compute for running migrations: {}",
-                        e
-                    );
-                }
-            };
         });
 
         Ok::<(), anyhow::Error>(())

compute_tools/src/http/api.rs

@@ -0,0 +1,591 @@
+use std::convert::Infallible;
+use std::net::IpAddr;
+use std::net::Ipv6Addr;
+use std::net::SocketAddr;
+use std::sync::Arc;
+use std::thread;
+
+use crate::catalog::SchemaDumpError;
+use crate::catalog::{get_database_schema, get_dbs_and_roles};
+use crate::compute::forward_termination_signal;
+use crate::compute::{ComputeNode, ComputeState, ParsedSpec};
+use crate::installed_extensions;
+use compute_api::requests::{ConfigurationRequest, ExtensionInstallRequest, SetRoleGrantsRequest};
+use compute_api::responses::{
+    ComputeStatus, ComputeStatusResponse, ExtensionInstallResult, GenericAPIError,
+    SetRoleGrantsResponse,
+};
+
+use anyhow::Result;
+use hyper::header::CONTENT_TYPE;
+use hyper::service::{make_service_fn, service_fn};
+use hyper::{Body, Method, Request, Response, Server, StatusCode};
+use metrics::proto::MetricFamily;
+use metrics::Encoder;
+use metrics::TextEncoder;
+use tokio::task;
+use tracing::{debug, error, info, warn};
+use tracing_utils::http::OtelName;
+use utils::http::request::must_get_query_param;
+
+fn status_response_from_state(state: &ComputeState) -> ComputeStatusResponse {
+    ComputeStatusResponse {
+        start_time: state.start_time,
+        tenant: state
+            .pspec
+            .as_ref()
+            .map(|pspec| pspec.tenant_id.to_string()),
+        timeline: state
+            .pspec
+            .as_ref()
+            .map(|pspec| pspec.timeline_id.to_string()),
+        status: state.status,
+        last_active: state.last_active,
+        error: state.error.clone(),
+    }
+}
+
+// Service function to handle all available routes.
+async fn routes(req: Request<Body>, compute: &Arc<ComputeNode>) -> Response<Body> {
+    //
+    // NOTE: The URI path is currently included in traces. That's OK because
+    // it doesn't contain any variable parts or sensitive information. But
+    // please keep that in mind if you change the routing here.
+    //
+    match (req.method(), req.uri().path()) {
+        // Serialized compute state.
+        (&Method::GET, "/status") => {
+            debug!("serving /status GET request");
+            let state = compute.state.lock().unwrap();
+            let status_response = status_response_from_state(&state);
+            Response::new(Body::from(serde_json::to_string(&status_response).unwrap()))
+        }
+
+        // Startup metrics in JSON format. Keep /metrics reserved for a possible
+        // future use for Prometheus metrics format.
+        (&Method::GET, "/metrics.json") => {
+            info!("serving /metrics.json GET request");
+            let metrics = compute.state.lock().unwrap().metrics.clone();
+            Response::new(Body::from(serde_json::to_string(&metrics).unwrap()))
+        }
+
+        // Prometheus metrics
+        (&Method::GET, "/metrics") => {
+            debug!("serving /metrics GET request");
+
+            // When we call TextEncoder::encode() below, it will immediately
+            // return an error if a metric family has no metrics, so we need to
+            // preemptively filter out metric families with no metrics.
+            let metrics = installed_extensions::collect()
+                .into_iter()
+                .filter(|m| !m.get_metric().is_empty())
+                .collect::<Vec<MetricFamily>>();
+
+            let encoder = TextEncoder::new();
+            let mut buffer = vec![];
+
+            if let Err(err) = encoder.encode(&metrics, &mut buffer) {
+                let msg = format!("error handling /metrics request: {err}");
+                error!(msg);
+                return render_json_error(&msg, StatusCode::INTERNAL_SERVER_ERROR);
+            }
+
+            match Response::builder()
+                .status(StatusCode::OK)
+                .header(CONTENT_TYPE, encoder.format_type())
+                .body(Body::from(buffer))
+            {
+                Ok(response) => response,
+                Err(err) => {
+                    let msg = format!("error handling /metrics request: {err}");
+                    error!(msg);
+                    render_json_error(&msg, StatusCode::INTERNAL_SERVER_ERROR)
+                }
+            }
+        }
+        // Collect Postgres current usage insights
+        (&Method::GET, "/insights") => {
+            info!("serving /insights GET request");
+            let status = compute.get_status();
+            if status != ComputeStatus::Running {
+                let msg = format!("compute is not running, current status: {:?}", status);
+                error!(msg);
+                return Response::new(Body::from(msg));
+            }
+
+            let insights = compute.collect_insights().await;
+            Response::new(Body::from(insights))
+        }
+
+        (&Method::POST, "/check_writability") => {
+            info!("serving /check_writability POST request");
+            let status = compute.get_status();
+            if status != ComputeStatus::Running {
+                let msg = format!(
+                    "invalid compute status for check_writability request: {:?}",
+                    status
+                );
+                error!(msg);
+                return Response::new(Body::from(msg));
+            }
+
+            let res = crate::checker::check_writability(compute).await;
+            match res {
+                Ok(_) => Response::new(Body::from("true")),
+                Err(e) => {
+                    error!("check_writability failed: {}", e);
+                    Response::new(Body::from(e.to_string()))
+                }
+            }
+        }
+
+        (&Method::POST, "/extensions") => {
+            info!("serving /extensions POST request");
+            let status = compute.get_status();
+            if status != ComputeStatus::Running {
+                let msg = format!(
+                    "invalid compute status for extensions request: {:?}",
+                    status
+                );
+                error!(msg);
+                return render_json_error(&msg, StatusCode::PRECONDITION_FAILED);
+            }
+
+            let request = hyper::body::to_bytes(req.into_body()).await.unwrap();
+            let request = serde_json::from_slice::<ExtensionInstallRequest>(&request).unwrap();
+            let res = compute
+                .install_extension(&request.extension, &request.database, request.version)
+                .await;
+            match res {
+                Ok(version) => render_json(Body::from(
+                    serde_json::to_string(&ExtensionInstallResult {
+                        extension: request.extension,
+                        version,
+                    })
+                    .unwrap(),
+                )),
+                Err(e) => {
+                    error!("install_extension failed: {}", e);
+                    render_json_error(&e.to_string(), StatusCode::INTERNAL_SERVER_ERROR)
+                }
+            }
+        }
+
+        (&Method::GET, "/info") => {
+            let num_cpus = num_cpus::get_physical();
+            info!("serving /info GET request. num_cpus: {}", num_cpus);
+            Response::new(Body::from(
+                serde_json::json!({
+                    "num_cpus": num_cpus,
+                })
+                .to_string(),
+            ))
+        }
+
+        // Accept spec in JSON format and request compute configuration. If
+        // anything goes wrong after we set the compute status to `ConfigurationPending`
+        // and update compute state with new spec, we basically leave compute
+        // in the potentially wrong state. That said, it's control-plane's
+        // responsibility to watch compute state after reconfiguration request
+        // and to clean restart in case of errors.
+        (&Method::POST, "/configure") => {
+            info!("serving /configure POST request");
+            match handle_configure_request(req, compute).await {
+                Ok(msg) => Response::new(Body::from(msg)),
+                Err((msg, code)) => {
+                    error!("error handling /configure request: {msg}");
+                    render_json_error(&msg, code)
+                }
+            }
+        }
+
+        (&Method::POST, "/terminate") => {
+            info!("serving /terminate POST request");
+            match handle_terminate_request(compute).await {
+                Ok(()) => Response::new(Body::empty()),
+                Err((msg, code)) => {
+                    error!("error handling /terminate request: {msg}");
+                    render_json_error(&msg, code)
+                }
+            }
+        }
+
+        (&Method::GET, "/dbs_and_roles") => {
+            info!("serving /dbs_and_roles GET request",);
+            match get_dbs_and_roles(compute).await {
+                Ok(res) => render_json(Body::from(serde_json::to_string(&res).unwrap())),
+                Err(_) => {
+                    render_json_error("can't get dbs and roles", StatusCode::INTERNAL_SERVER_ERROR)
+                }
+            }
+        }
+
+        (&Method::GET, "/database_schema") => {
+            let database = match must_get_query_param(&req, "database") {
+                Err(e) => return e.into_response(),
+                Ok(database) => database,
+            };
+            info!("serving /database_schema GET request with database: {database}",);
+            match get_database_schema(compute, &database).await {
+                Ok(res) => render_plain(Body::wrap_stream(res)),
+                Err(SchemaDumpError::DatabaseDoesNotExist) => {
+                    render_json_error("database does not exist", StatusCode::NOT_FOUND)
+                }
+                Err(e) => {
+                    error!("can't get schema dump: {}", e);
+                    render_json_error("can't get schema dump", StatusCode::INTERNAL_SERVER_ERROR)
+                }
+            }
+        }
+
+        (&Method::POST, "/grants") => {
+            info!("serving /grants POST request");
+            let status = compute.get_status();
+            if status != ComputeStatus::Running {
+                let msg = format!(
+                    "invalid compute status for set_role_grants request: {:?}",
+                    status
+                );
+                error!(msg);
+                return render_json_error(&msg, StatusCode::PRECONDITION_FAILED);
+            }
+
+            let request = hyper::body::to_bytes(req.into_body()).await.unwrap();
+            let request = serde_json::from_slice::<SetRoleGrantsRequest>(&request).unwrap();
+
+            let res = compute
+                .set_role_grants(
+                    &request.database,
+                    &request.schema,
+                    &request.privileges,
+                    &request.role,
+                )
+                .await;
+            match res {
+                Ok(()) => render_json(Body::from(
+                    serde_json::to_string(&SetRoleGrantsResponse {
+                        database: request.database,
+                        schema: request.schema,
+                        role: request.role,
+                        privileges: request.privileges,
+                    })
+                    .unwrap(),
+                )),
+                Err(e) => render_json_error(
+                    &format!("could not grant role privileges to the schema: {e}"),
+                    // TODO: can we filter on role/schema not found errors
+                    // and return appropriate error code?
+                    StatusCode::INTERNAL_SERVER_ERROR,
+                ),
+            }
+        }
+
+        // get the list of installed extensions
+        // currently only used in python tests
+        // TODO: call it from cplane
+        (&Method::GET, "/installed_extensions") => {
+            info!("serving /installed_extensions GET request");
+            let status = compute.get_status();
+            if status != ComputeStatus::Running {
+                let msg = format!(
+                    "invalid compute status for extensions request: {:?}",
+                    status
+                );
+                error!(msg);
+                return Response::new(Body::from(msg));
+            }
+
+            let conf = compute.get_conn_conf(None);
+            let res =
+                task::spawn_blocking(move || installed_extensions::get_installed_extensions(conf))
+                    .await
+                    .unwrap();
+
+            match res {
+                Ok(res) => render_json(Body::from(serde_json::to_string(&res).unwrap())),
+                Err(e) => render_json_error(
+                    &format!("could not get list of installed extensions: {}", e),
+                    StatusCode::INTERNAL_SERVER_ERROR,
+                ),
+            }
+        }
+
+        // download extension files from remote extension storage on demand
+        (&Method::POST, route) if route.starts_with("/extension_server/") => {
+            info!("serving {:?} POST request", route);
+            info!("req.uri {:?}", req.uri());
+
+            // don't even try to download extensions
+            // if no remote storage is configured
+            if compute.ext_remote_storage.is_none() {
+                info!("no extensions remote storage configured");
+                let mut resp = Response::new(Body::from("no remote storage configured"));
+                *resp.status_mut() = StatusCode::INTERNAL_SERVER_ERROR;
+                return resp;
+            }
+
+            let mut is_library = false;
+            if let Some(params) = req.uri().query() {
+                info!("serving {:?} POST request with params: {}", route, params);
+                if params == "is_library=true" {
+                    is_library = true;
+                } else {
+                    let mut resp = Response::new(Body::from("Wrong request parameters"));
+                    *resp.status_mut() = StatusCode::BAD_REQUEST;
+                    return resp;
+                }
+            }
+            let filename = route.split('/').last().unwrap().to_string();
+            info!("serving /extension_server POST request, filename: {filename:?} is_library: {is_library}");
+
+            // get ext_name and path from spec
+            // don't lock compute_state for too long
+            let ext = {
+                let compute_state = compute.state.lock().unwrap();
+                let pspec = compute_state.pspec.as_ref().expect("spec must be set");
+                let spec = &pspec.spec;
+
+                // debug only
+                info!("spec: {:?}", spec);
+
+                let remote_extensions = match spec.remote_extensions.as_ref() {
+                    Some(r) => r,
+                    None => {
+                        info!("no remote extensions spec was provided");
+                        let mut resp = Response::new(Body::from("no remote storage configured"));
+                        *resp.status_mut() = StatusCode::INTERNAL_SERVER_ERROR;
+                        return resp;
+                    }
+                };
+
+                remote_extensions.get_ext(
+                    &filename,
+                    is_library,
+                    &compute.build_tag,
+                    &compute.pgversion,
+                )
+            };
+
+            match ext {
+                Ok((ext_name, ext_path)) => {
+                    match compute.download_extension(ext_name, ext_path).await {
+                        Ok(_) => Response::new(Body::from("OK")),
+                        Err(e) => {
+                            error!("extension download failed: {}", e);
+                            let mut resp = Response::new(Body::from(e.to_string()));
+                            *resp.status_mut() = StatusCode::INTERNAL_SERVER_ERROR;
+                            resp
+                        }
+                    }
+                }
+                Err(e) => {
+                    warn!("extension download failed to find extension: {}", e);
+                    let mut resp = Response::new(Body::from("failed to find file"));
+                    *resp.status_mut() = StatusCode::INTERNAL_SERVER_ERROR;
+                    resp
+                }
+            }
+        }
+
+        // Return the `404 Not Found` for any other routes.
+        _ => {
+            let mut not_found = Response::new(Body::from("404 Not Found"));
+            *not_found.status_mut() = StatusCode::NOT_FOUND;
+            not_found
+        }
+    }
+}
+
+async fn handle_configure_request(
+    req: Request<Body>,
+    compute: &Arc<ComputeNode>,
+) -> Result<String, (String, StatusCode)> {
+    if !compute.live_config_allowed {
+        return Err((
+            "live configuration is not allowed for this compute node".to_string(),
+            StatusCode::PRECONDITION_FAILED,
+        ));
+    }
+
+    let body_bytes = hyper::body::to_bytes(req.into_body()).await.unwrap();
+    let spec_raw = String::from_utf8(body_bytes.to_vec()).unwrap();
+    if let Ok(request) = serde_json::from_str::<ConfigurationRequest>(&spec_raw) {
+        let spec = request.spec;
+
+        let parsed_spec = match ParsedSpec::try_from(spec) {
+            Ok(ps) => ps,
+            Err(msg) => return Err((msg, StatusCode::BAD_REQUEST)),
+        };
+
+        // XXX: wrap state update under lock in code blocks. Otherwise,
+        // we will try to `Send` `mut state` into the spawned thread
+        // bellow, which will cause error:
+        // ```
+        // error: future cannot be sent between threads safely
+        // ```
+        {
+            let mut state = compute.state.lock().unwrap();
+            if state.status != ComputeStatus::Empty && state.status != ComputeStatus::Running {
+                let msg = format!(
+                    "invalid compute status for configuration request: {:?}",
+                    state.status.clone()
+                );
+                return Err((msg, StatusCode::PRECONDITION_FAILED));
+            }
+            state.pspec = Some(parsed_spec);
+            state.set_status(ComputeStatus::ConfigurationPending, &compute.state_changed);
+            drop(state);
+            info!("set new spec and notified waiters");
+        }
+
+        // Spawn a blocking thread to wait for compute to become Running.
+        // This is needed to do not block the main pool of workers and
+        // be able to serve other requests while some particular request
+        // is waiting for compute to finish configuration.
+        let c = compute.clone();
+        task::spawn_blocking(move || {
+            let mut state = c.state.lock().unwrap();
+            while state.status != ComputeStatus::Running {
+                state = c.state_changed.wait(state).unwrap();
+                info!(
+                    "waiting for compute to become Running, current status: {:?}",
+                    state.status
+                );
+
+                if state.status == ComputeStatus::Failed {
+                    let err = state.error.as_ref().map_or("unknown error", |x| x);
+                    let msg = format!("compute configuration failed: {:?}", err);
+                    return Err((msg, StatusCode::INTERNAL_SERVER_ERROR));
+                }
+            }
+
+            Ok(())
+        })
+        .await
+        .unwrap()?;
+
+        // Return current compute state if everything went well.
+        let state = compute.state.lock().unwrap().clone();
+        let status_response = status_response_from_state(&state);
+        Ok(serde_json::to_string(&status_response).unwrap())
+    } else {
+        Err(("invalid spec".to_string(), StatusCode::BAD_REQUEST))
+    }
+}
+
+fn render_json_error(e: &str, status: StatusCode) -> Response<Body> {
+    let error = GenericAPIError {
+        error: e.to_string(),
+    };
+    Response::builder()
+        .status(status)
+        .header(CONTENT_TYPE, "application/json")
+        .body(Body::from(serde_json::to_string(&error).unwrap()))
+        .unwrap()
+}
+
+fn render_json(body: Body) -> Response<Body> {
+    Response::builder()
+        .header(CONTENT_TYPE, "application/json")
+        .body(body)
+        .unwrap()
+}
+
+fn render_plain(body: Body) -> Response<Body> {
+    Response::builder()
+        .header(CONTENT_TYPE, "text/plain")
+        .body(body)
+        .unwrap()
+}
+
+async fn handle_terminate_request(compute: &Arc<ComputeNode>) -> Result<(), (String, StatusCode)> {
+    {
+        let mut state = compute.state.lock().unwrap();
+        if state.status == ComputeStatus::Terminated {
+            return Ok(());
+        }
+        if state.status != ComputeStatus::Empty && state.status != ComputeStatus::Running {
+            let msg = format!(
+                "invalid compute status for termination request: {}",
+                state.status
+            );
+            return Err((msg, StatusCode::PRECONDITION_FAILED));
+        }
+        state.set_status(ComputeStatus::TerminationPending, &compute.state_changed);
+        drop(state);
+    }
+
+    forward_termination_signal();
+    info!("sent signal and notified waiters");
+
+    // Spawn a blocking thread to wait for compute to become Terminated.
+    // This is needed to do not block the main pool of workers and
+    // be able to serve other requests while some particular request
+    // is waiting for compute to finish configuration.
+    let c = compute.clone();
+    task::spawn_blocking(move || {
+        let mut state = c.state.lock().unwrap();
+        while state.status != ComputeStatus::Terminated {
+            state = c.state_changed.wait(state).unwrap();
+            info!(
+                "waiting for compute to become {}, current status: {:?}",
+                ComputeStatus::Terminated,
+                state.status
+            );
+        }
+
+        Ok(())
+    })
+    .await
+    .unwrap()?;
+    info!("terminated Postgres");
+    Ok(())
+}
+
+// Main Hyper HTTP server function that runs it and blocks waiting on it forever.
+#[tokio::main]
+async fn serve(port: u16, state: Arc<ComputeNode>) {
+    // this usually binds to both IPv4 and IPv6 on linux
+    // see e.g. https://github.com/rust-lang/rust/pull/34440
+    let addr = SocketAddr::new(IpAddr::from(Ipv6Addr::UNSPECIFIED), port);
+
+    let make_service = make_service_fn(move |_conn| {
+        let state = state.clone();
+        async move {
+            Ok::<_, Infallible>(service_fn(move |req: Request<Body>| {
+                let state = state.clone();
+                async move {
+                    Ok::<_, Infallible>(
+                        // NOTE: We include the URI path in the string. It
+                        // doesn't contain any variable parts or sensitive
+                        // information in this API.
+                        tracing_utils::http::tracing_handler(
+                            req,
+                            |req| routes(req, &state),
+                            OtelName::UriPath,
+                        )
+                        .await,
+                    )
+                }
+            }))
+        }
+    });
+
+    info!("starting HTTP server on {}", addr);
+
+    let server = Server::bind(&addr).serve(make_service);
+
+    // Run this server forever
+    if let Err(e) = server.await {
+        error!("server error: {}", e);
+    }
+}
+
+/// Launch a separate Hyper HTTP API server thread and return its `JoinHandle`.
+pub fn launch_http_server(port: u16, state: &Arc<ComputeNode>) -> Result<thread::JoinHandle<()>> {
+    let state = Arc::clone(state);
+
+    Ok(thread::Builder::new()
+        .name("http-endpoint".into())
+        .spawn(move || serve(port, state))?)
+}

compute_tools/src/http/extract/json.rs

@@ -1,48 +0,0 @@
-use std::ops::{Deref, DerefMut};
-
-use axum::{
-    async_trait,
-    extract::{rejection::JsonRejection, FromRequest, Request},
-};
-use compute_api::responses::GenericAPIError;
-use http::StatusCode;
-
-/// Custom `Json` extractor, so that we can format errors into
-/// `JsonResponse<GenericAPIError>`.
-#[derive(Debug, Clone, Copy, Default)]
-pub(crate) struct Json<T>(pub T);
-
-#[async_trait]
-impl<S, T> FromRequest<S> for Json<T>
-where
-    axum::Json<T>: FromRequest<S, Rejection = JsonRejection>,
-    S: Send + Sync,
-{
-    type Rejection = (StatusCode, axum::Json<GenericAPIError>);
-
-    async fn from_request(req: Request, state: &S) -> Result<Self, Self::Rejection> {
-        match axum::Json::<T>::from_request(req, state).await {
-            Ok(value) => Ok(Self(value.0)),
-            Err(rejection) => Err((
-                rejection.status(),
-                axum::Json(GenericAPIError {
-                    error: rejection.body_text().to_lowercase(),
-                }),
-            )),
-        }
-    }
-}
-
-impl<T> Deref for Json<T> {
-    type Target = T;
-
-    fn deref(&self) -> &Self::Target {
-        &self.0
-    }
-}
-
-impl<T> DerefMut for Json<T> {
-    fn deref_mut(&mut self) -> &mut Self::Target {
-        &mut self.0
-    }
-}

compute_tools/src/http/extract/mod.rs

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

compute_tools/src/http/extract/path.rs

@@ -1,48 +0,0 @@
-use std::ops::{Deref, DerefMut};
-
-use axum::{
-    async_trait,
-    extract::{rejection::PathRejection, FromRequestParts},
-};
-use compute_api::responses::GenericAPIError;
-use http::{request::Parts, StatusCode};
-
-/// Custom `Path` extractor, so that we can format errors into
-/// `JsonResponse<GenericAPIError>`.
-#[derive(Debug, Clone, Copy, Default)]
-pub(crate) struct Path<T>(pub T);
-
-#[async_trait]
-impl<S, T> FromRequestParts<S> for Path<T>
-where
-    axum::extract::Path<T>: FromRequestParts<S, Rejection = PathRejection>,
-    S: Send + Sync,
-{
-    type Rejection = (StatusCode, axum::Json<GenericAPIError>);
-
-    async fn from_request_parts(parts: &mut Parts, state: &S) -> Result<Self, Self::Rejection> {
-        match axum::extract::Path::<T>::from_request_parts(parts, state).await {
-            Ok(value) => Ok(Self(value.0)),
-            Err(rejection) => Err((
-                rejection.status(),
-                axum::Json(GenericAPIError {
-                    error: rejection.body_text().to_ascii_lowercase(),
-                }),
-            )),
-        }
-    }
-}
-
-impl<T> Deref for Path<T> {
-    type Target = T;
-
-    fn deref(&self) -> &Self::Target {
-        &self.0
-    }
-}
-
-impl<T> DerefMut for Path<T> {
-    fn deref_mut(&mut self) -> &mut Self::Target {
-        &mut self.0
-    }
-}

compute_tools/src/http/extract/query.rs

@@ -1,48 +0,0 @@
-use std::ops::{Deref, DerefMut};
-
-use axum::{
-    async_trait,
-    extract::{rejection::QueryRejection, FromRequestParts},
-};
-use compute_api::responses::GenericAPIError;
-use http::{request::Parts, StatusCode};
-
-/// Custom `Query` extractor, so that we can format errors into
-/// `JsonResponse<GenericAPIError>`.
-#[derive(Debug, Clone, Copy, Default)]
-pub(crate) struct Query<T>(pub T);
-
-#[async_trait]
-impl<S, T> FromRequestParts<S> for Query<T>
-where
-    axum::extract::Query<T>: FromRequestParts<S, Rejection = QueryRejection>,
-    S: Send + Sync,
-{
-    type Rejection = (StatusCode, axum::Json<GenericAPIError>);
-
-    async fn from_request_parts(parts: &mut Parts, state: &S) -> Result<Self, Self::Rejection> {
-        match axum::extract::Query::<T>::from_request_parts(parts, state).await {
-            Ok(value) => Ok(Self(value.0)),
-            Err(rejection) => Err((
-                rejection.status(),
-                axum::Json(GenericAPIError {
-                    error: rejection.body_text().to_ascii_lowercase(),
-                }),
-            )),
-        }
-    }
-}
-
-impl<T> Deref for Query<T> {
-    type Target = T;
-
-    fn deref(&self) -> &Self::Target {
-        &self.0
-    }
-}
-
-impl<T> DerefMut for Query<T> {
-    fn deref_mut(&mut self) -> &mut Self::Target {
-        &mut self.0
-    }
-}

compute_tools/src/http/mod.rs

@@ -1,56 +1 @@
-use axum::{body::Body, response::Response};
+pub mod api;
-use compute_api::responses::{ComputeStatus, GenericAPIError};
-use http::{header::CONTENT_TYPE, StatusCode};
-use serde::Serialize;
-use tracing::error;
-
-pub use server::launch_http_server;
-
-mod extract;
-mod routes;
-mod server;
-
-/// Convenience response builder for JSON responses
-struct JsonResponse;
-
-impl JsonResponse {
-    /// Helper for actually creating a response
-    fn create_response(code: StatusCode, body: impl Serialize) -> Response {
-        Response::builder()
-            .status(code)
-            .header(CONTENT_TYPE.as_str(), "application/json")
-            .body(Body::from(serde_json::to_string(&body).unwrap()))
-            .unwrap()
-    }
-
-    /// Create a successful error response
-    pub(self) fn success(code: StatusCode, body: impl Serialize) -> Response {
-        assert!({
-            let code = code.as_u16();
-
-            (200..300).contains(&code)
-        });
-
-        Self::create_response(code, body)
-    }
-
-    /// Create an error response
-    pub(self) fn error(code: StatusCode, error: impl ToString) -> Response {
-        assert!(code.as_u16() >= 400);
-
-        let message = error.to_string();
-        error!(message);
-
-        Self::create_response(code, &GenericAPIError { error: message })
-    }
-
-    /// Create an error response related to the compute being in an invalid state
-    pub(self) fn invalid_status(status: ComputeStatus) -> Response {
-        Self::create_response(
-            StatusCode::PRECONDITION_FAILED,
-            &GenericAPIError {
-                error: format!("invalid compute status: {status}"),
-            },
-        )
-    }
-}

compute_tools/src/http/openapi_spec.yaml

@@ -37,7 +37,7 @@ paths:
               schema:
                 $ref: "#/components/schemas/ComputeMetrics"
 
-  /metrics:
+  /metrics
     get:
       tags:
       - Info
@@ -537,14 +537,12 @@ components:
             properties:
               extname:
                 type: string
-              version:
+              versions:
-                type: string
+                type: array
                 items:
                   type: string
               n_databases:
                 type: integer
-              owned_by_superuser:
-                type: integer
 
     SetRoleGrantsRequest:
       type: object

compute_tools/src/http/routes/check_writability.rs

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

compute_tools/src/http/routes/configure.rs

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

compute_tools/src/http/routes/database_schema.rs

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

compute_tools/src/http/routes/dbs_and_roles.rs

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

compute_tools/src/http/routes/extension_server.rs

@@ -1,67 +0,0 @@
-use std::sync::Arc;
-
-use axum::{
-    extract::State,
-    response::{IntoResponse, Response},
-};
-use http::StatusCode;
-use serde::Deserialize;
-
-use crate::{
-    compute::ComputeNode,
-    http::{
-        extract::{Path, Query},
-        JsonResponse,
-    },
-};
-
-#[derive(Debug, Clone, Deserialize)]
-pub(in crate::http) struct ExtensionServerParams {
-    is_library: Option<bool>,
-}
-
-/// Download a remote extension.
-pub(in crate::http) async fn download_extension(
-    Path(filename): Path<String>,
-    params: Query<ExtensionServerParams>,
-    State(compute): State<Arc<ComputeNode>>,
-) -> Response {
-    // Don't even try to download extensions if no remote storage is configured
-    if compute.ext_remote_storage.is_none() {
-        return JsonResponse::error(
-            StatusCode::PRECONDITION_FAILED,
-            "remote storage is not configured",
-        );
-    }
-
-    let ext = {
-        let state = compute.state.lock().unwrap();
-        let pspec = state.pspec.as_ref().unwrap();
-        let spec = &pspec.spec;
-
-        let remote_extensions = match spec.remote_extensions.as_ref() {
-            Some(r) => r,
-            None => {
-                return JsonResponse::error(
-                    StatusCode::CONFLICT,
-                    "information about remote extensions is unavailable",
-                );
-            }
-        };
-
-        remote_extensions.get_ext(
-            &filename,
-            params.is_library.unwrap_or(false),
-            &compute.build_tag,
-            &compute.pgversion,
-        )
-    };
-
-    match ext {
-        Ok((ext_name, ext_path)) => match compute.download_extension(ext_name, ext_path).await {
-            Ok(_) => StatusCode::OK.into_response(),
-            Err(e) => JsonResponse::error(StatusCode::INTERNAL_SERVER_ERROR, e),
-        },
-        Err(e) => JsonResponse::error(StatusCode::NOT_FOUND, e),
-    }
-}

compute_tools/src/http/routes/extensions.rs

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

compute_tools/src/http/routes/failpoints.rs

@@ -1,35 +0,0 @@
-use axum::response::{IntoResponse, Response};
-use http::StatusCode;
-use tracing::info;
-use utils::failpoint_support::{apply_failpoint, ConfigureFailpointsRequest};
-
-use crate::http::{extract::Json, JsonResponse};
-
-/// Configure failpoints for testing purposes.
-pub(in crate::http) async fn configure_failpoints(
-    failpoints: Json<ConfigureFailpointsRequest>,
-) -> Response {
-    if !fail::has_failpoints() {
-        return JsonResponse::error(
-            StatusCode::PRECONDITION_FAILED,
-            "Cannot manage failpoints because neon was compiled without failpoints support",
-        );
-    }
-
-    for fp in &*failpoints {
-        info!("cfg failpoint: {} {}", fp.name, fp.actions);
-
-        // We recognize one extra "action" that's not natively recognized
-        // by the failpoints crate: exit, to immediately kill the process
-        let cfg_result = apply_failpoint(&fp.name, &fp.actions);
-
-        if let Err(e) = cfg_result {
-            return JsonResponse::error(
-                StatusCode::BAD_REQUEST,
-                format!("failed to configure failpoints: {e}"),
-            );
-        }
-    }
-
-    StatusCode::OK.into_response()
-}

compute_tools/src/http/routes/grants.rs

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

compute_tools/src/http/routes/info.rs

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

compute_tools/src/http/routes/insights.rs

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

compute_tools/src/http/routes/installed_extensions.rs

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

compute_tools/src/http/routes/metrics.rs

@@ -1,32 +0,0 @@
-use axum::{body::Body, response::Response};
-use http::header::CONTENT_TYPE;
-use http::StatusCode;
-use metrics::proto::MetricFamily;
-use metrics::Encoder;
-use metrics::TextEncoder;
-
-use crate::{http::JsonResponse, installed_extensions};
-
-/// Expose Prometheus metrics.
-pub(in crate::http) async fn get_metrics() -> Response {
-    // When we call TextEncoder::encode() below, it will immediately return an
-    // error if a metric family has no metrics, so we need to preemptively
-    // filter out metric families with no metrics.
-    let metrics = installed_extensions::collect()
-        .into_iter()
-        .filter(|m| !m.get_metric().is_empty())
-        .collect::<Vec<MetricFamily>>();
-
-    let encoder = TextEncoder::new();
-    let mut buffer = vec![];
-
-    if let Err(e) = encoder.encode(&metrics, &mut buffer) {
-        return JsonResponse::error(StatusCode::INTERNAL_SERVER_ERROR, e);
-    }
-
-    Response::builder()
-        .status(StatusCode::OK)
-        .header(CONTENT_TYPE, encoder.format_type())
-        .body(Body::from(buffer))
-        .unwrap()
-}

compute_tools/src/http/routes/metrics_json.rs

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

compute_tools/src/http/routes/mod.rs

@@ -1,38 +0,0 @@
-use compute_api::responses::ComputeStatusResponse;
-
-use crate::compute::ComputeState;
-
-pub(in crate::http) mod check_writability;
-pub(in crate::http) mod configure;
-pub(in crate::http) mod database_schema;
-pub(in crate::http) mod dbs_and_roles;
-pub(in crate::http) mod extension_server;
-pub(in crate::http) mod extensions;
-pub(in crate::http) mod failpoints;
-pub(in crate::http) mod grants;
-pub(in crate::http) mod info;
-pub(in crate::http) mod insights;
-pub(in crate::http) mod installed_extensions;
-pub(in crate::http) mod metrics;
-pub(in crate::http) mod metrics_json;
-pub(in crate::http) mod status;
-pub(in crate::http) mod terminate;
-
-impl From<&ComputeState> for ComputeStatusResponse {
-    fn from(state: &ComputeState) -> Self {
-        ComputeStatusResponse {
-            start_time: state.start_time,
-            tenant: state
-                .pspec
-                .as_ref()
-                .map(|pspec| pspec.tenant_id.to_string()),
-            timeline: state
-                .pspec
-                .as_ref()
-                .map(|pspec| pspec.timeline_id.to_string()),
-            status: state.status,
-            last_active: state.last_active,
-            error: state.error.clone(),
-        }
-    }
-}

compute_tools/src/http/routes/status.rs

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

compute_tools/src/http/routes/terminate.rs

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

compute_tools/src/http/server.rs

@@ -1,165 +0,0 @@
-use std::{
-    net::{IpAddr, Ipv6Addr, SocketAddr},
-    sync::{
-        atomic::{AtomicU64, Ordering},
-        Arc,
-    },
-    thread,
-    time::Duration,
-};
-
-use anyhow::Result;
-use axum::{
-    response::{IntoResponse, Response},
-    routing::{get, post},
-    Router,
-};
-use http::StatusCode;
-use tokio::net::TcpListener;
-use tower::ServiceBuilder;
-use tower_http::{
-    request_id::{MakeRequestId, PropagateRequestIdLayer, RequestId, SetRequestIdLayer},
-    trace::TraceLayer,
-};
-use tracing::{debug, error, info, Span};
-
-use super::routes::{
-    check_writability, configure, database_schema, dbs_and_roles, extension_server, extensions,
-    grants, info as info_route, insights, installed_extensions, metrics, metrics_json, status,
-    terminate,
-};
-use crate::compute::ComputeNode;
-
-async fn handle_404() -> Response {
-    StatusCode::NOT_FOUND.into_response()
-}
-
-#[derive(Clone, Default)]
-struct ComputeMakeRequestId(Arc<AtomicU64>);
-
-impl MakeRequestId for ComputeMakeRequestId {
-    fn make_request_id<B>(
-        &mut self,
-        _request: &http::Request<B>,
-    ) -> Option<tower_http::request_id::RequestId> {
-        let request_id = self
-            .0
-            .fetch_add(1, Ordering::SeqCst)
-            .to_string()
-            .parse()
-            .unwrap();
-
-        Some(RequestId::new(request_id))
-    }
-}
-
-/// Run the HTTP server and wait on it forever.
-#[tokio::main]
-async fn serve(port: u16, compute: Arc<ComputeNode>) {
-    const X_REQUEST_ID: &str = "x-request-id";
-
-    let mut app = Router::new()
-        .route("/check_writability", post(check_writability::is_writable))
-        .route("/configure", post(configure::configure))
-        .route("/database_schema", get(database_schema::get_schema_dump))
-        .route("/dbs_and_roles", get(dbs_and_roles::get_catalog_objects))
-        .route(
-            "/extension_server/*filename",
-            post(extension_server::download_extension),
-        )
-        .route("/extensions", post(extensions::install_extension))
-        .route("/grants", post(grants::add_grant))
-        .route("/info", get(info_route::get_info))
-        .route("/insights", get(insights::get_insights))
-        .route(
-            "/installed_extensions",
-            get(installed_extensions::get_installed_extensions),
-        )
-        .route("/metrics", get(metrics::get_metrics))
-        .route("/metrics.json", get(metrics_json::get_metrics))
-        .route("/status", get(status::get_status))
-        .route("/terminate", post(terminate::terminate))
-        .fallback(handle_404)
-        .layer(
-            ServiceBuilder::new()
-                .layer(SetRequestIdLayer::x_request_id(
-                    ComputeMakeRequestId::default(),
-                ))
-                .layer(
-                    TraceLayer::new_for_http()
-                        .on_request(|request: &http::Request<_>, _span: &Span| {
-                            let request_id = request
-                                .headers()
-                                .get(X_REQUEST_ID)
-                                .unwrap()
-                                .to_str()
-                                .unwrap();
-
-                            match request.uri().path() {
-                                "/metrics" => {
-                                    debug!(%request_id, "{} {}", request.method(), request.uri())
-                                }
-                                _ => info!(%request_id, "{} {}", request.method(), request.uri()),
-                            };
-                        })
-                        .on_response(
-                            |response: &http::Response<_>, latency: Duration, _span: &Span| {
-                                let request_id = response
-                                    .headers()
-                                    .get(X_REQUEST_ID)
-                                    .unwrap()
-                                    .to_str()
-                                    .unwrap();
-
-                                info!(
-                                    %request_id,
-                                    code = response.status().as_u16(),
-                                    latency = latency.as_millis()
-                                )
-                            },
-                        ),
-                )
-                .layer(PropagateRequestIdLayer::x_request_id()),
-        )
-        .with_state(compute);
-
-    // Add in any testing support
-    if cfg!(feature = "testing") {
-        use super::routes::failpoints;
-
-        app = app.route("/failpoints", post(failpoints::configure_failpoints))
-    }
-
-    // This usually binds to both IPv4 and IPv6 on Linux, see
-    // https://github.com/rust-lang/rust/pull/34440 for more information
-    let addr = SocketAddr::new(IpAddr::from(Ipv6Addr::UNSPECIFIED), port);
-    let listener = match TcpListener::bind(&addr).await {
-        Ok(listener) => listener,
-        Err(e) => {
-            error!(
-                "failed to bind the compute_ctl HTTP server to port {}: {}",
-                port, e
-            );
-            return;
-        }
-    };
-
-    if let Ok(local_addr) = listener.local_addr() {
-        info!("compute_ctl HTTP server listening on {}", local_addr);
-    } else {
-        info!("compute_ctl HTTP server listening on port {}", port);
-    }
-
-    if let Err(e) = axum::serve(listener, app).await {
-        error!("compute_ctl HTTP server error: {}", e);
-    }
-}
-
-/// Launch a separate HTTP server thread and return its `JoinHandle`.
-pub fn launch_http_server(port: u16, state: &Arc<ComputeNode>) -> Result<thread::JoinHandle<()>> {
-    let state = Arc::clone(state);
-
-    Ok(thread::Builder::new()
-        .name("http-server".into())
-        .spawn(move || serve(port, state))?)
-}

compute_tools/src/installed_extensions.rs

@@ -1,6 +1,7 @@
 use compute_api::responses::{InstalledExtension, InstalledExtensions};
 use metrics::proto::MetricFamily;
 use std::collections::HashMap;
+use std::collections::HashSet;
 
 use anyhow::Result;
 use postgres::{Client, NoTls};
@@ -37,77 +38,61 @@ fn list_dbs(client: &mut Client) -> Result<Vec<String>> {
 /// Connect to every database (see list_dbs above) and get the list of installed extensions.
 ///
 /// Same extension can be installed in multiple databases with different versions,
-/// so we report a separate metric (number of databases where it is installed)
+/// we only keep the highest and lowest version across all databases.
-/// for each extension version.
 pub fn get_installed_extensions(mut conf: postgres::config::Config) -> Result<InstalledExtensions> {
     conf.application_name("compute_ctl:get_installed_extensions");
     let mut client = conf.connect(NoTls)?;
+
     let databases: Vec<String> = list_dbs(&mut client)?;
 
-    let mut extensions_map: HashMap<(String, String, String), InstalledExtension> = HashMap::new();
+    let mut extensions_map: HashMap<String, InstalledExtension> = HashMap::new();
     for db in databases.iter() {
         conf.dbname(db);
         let mut db_client = conf.connect(NoTls)?;
-        let extensions: Vec<(String, String, i32)> = db_client
+        let extensions: Vec<(String, String)> = db_client
             .query(
-                "SELECT extname, extversion, extowner::integer FROM pg_catalog.pg_extension",
+                "SELECT extname, extversion FROM pg_catalog.pg_extension;",
                 &[],
             )?
             .iter()
-            .map(|row| {
+            .map(|row| (row.get("extname"), row.get("extversion")))
-                (
-                    row.get("extname"),
-                    row.get("extversion"),
-                    row.get("extowner"),
-                )
-            })
             .collect();
 
-        for (extname, v, extowner) in extensions.iter() {
+        for (extname, v) in extensions.iter() {
             let version = v.to_string();
 
-            // check if the extension is owned by superuser
+            // increment the number of databases where the version of extension is installed
-            // 10 is the oid of superuser
+            INSTALLED_EXTENSIONS
-            let owned_by_superuser = if *extowner == 10 { "1" } else { "0" };
+                .with_label_values(&[extname, &version])
+                .inc();
 
             extensions_map
-                .entry((
+                .entry(extname.to_string())
-                    extname.to_string(),
-                    version.clone(),
-                    owned_by_superuser.to_string(),
-                ))
                 .and_modify(|e| {
+                    e.versions.insert(version.clone());
                     // count the number of databases where the extension is installed
                     e.n_databases += 1;
                 })
                 .or_insert(InstalledExtension {
                     extname: extname.to_string(),
-                    version: version.clone(),
+                    versions: HashSet::from([version.clone()]),
                     n_databases: 1,
-                    owned_by_superuser: owned_by_superuser.to_string(),
                 });
         }
     }
 
-    for (key, ext) in extensions_map.iter() {
+    let res = InstalledExtensions {
-        let (extname, version, owned_by_superuser) = key;
-        let n_databases = ext.n_databases as u64;
-
-        INSTALLED_EXTENSIONS
-            .with_label_values(&[extname, version, owned_by_superuser])
-            .set(n_databases);
-    }
-
-    Ok(InstalledExtensions {
         extensions: extensions_map.into_values().collect(),
-    })
+    };
+
+    Ok(res)
 }
 
 static INSTALLED_EXTENSIONS: Lazy<UIntGaugeVec> = Lazy::new(|| {
     register_uint_gauge_vec!(
         "compute_installed_extensions",
         "Number of databases where the version of extension is installed",
-        &["extension_name", "version", "owned_by_superuser"]
+        &["extension_name", "version"]
     )
     .expect("failed to define a metric")
 });

compute_tools/src/lib.rs

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

compute_tools/src/migration.rs

@@ -1,16 +1,13 @@
 use anyhow::{Context, Result};
-use fail::fail_point;
+use postgres::Client;
-use postgres::{Client, Transaction};
 use tracing::info;
 
-/// Runs a series of migrations on a target database
 pub(crate) struct MigrationRunner<'m> {
     client: &'m mut Client,
     migrations: &'m [&'m str],
 }
 
 impl<'m> MigrationRunner<'m> {
-    /// Create a new migration runner
     pub fn new(client: &'m mut Client, migrations: &'m [&'m str]) -> Self {
         // The neon_migration.migration_id::id column is a bigint, which is equivalent to an i64
         assert!(migrations.len() + 1 < i64::MAX as usize);
@@ -18,110 +15,87 @@ impl<'m> MigrationRunner<'m> {
         Self { client, migrations }
     }
 
-    /// Get the current value neon_migration.migration_id
     fn get_migration_id(&mut self) -> Result<i64> {
+        let query = "SELECT id FROM neon_migration.migration_id";
         let row = self
             .client
-            .query_one("SELECT id FROM neon_migration.migration_id", &[])?;
+            .query_one(query, &[])
+            .context("run_migrations get migration_id")?;
 
         Ok(row.get::<&str, i64>("id"))
     }
 
-    /// Update the neon_migration.migration_id value
+    fn update_migration_id(&mut self, migration_id: i64) -> Result<()> {
-    ///
+        let setval = format!("UPDATE neon_migration.migration_id SET id={}", migration_id);
-    /// This function has a fail point called compute-migration, which can be
-    /// used if you would like to fail the application of a series of migrations
-    /// at some point.
-    fn update_migration_id(txn: &mut Transaction, migration_id: i64) -> Result<()> {
-        // We use this fail point in order to check that failing in the
-        // middle of applying a series of migrations fails in an expected
-        // manner
-        if cfg!(feature = "testing") {
-            let fail = (|| {
-                fail_point!("compute-migration", |fail_migration_id| {
-                    migration_id == fail_migration_id.unwrap().parse::<i64>().unwrap()
-                });
 
-                false
+        self.client
-            })();
+            .simple_query(&setval)
-
+            .context("run_migrations update id")?;
-            if fail {
-                return Err(anyhow::anyhow!(format!(
-                    "migration {} was configured to fail because of a failpoint",
-                    migration_id
-                )));
-            }
-        }
-
-        txn.query(
-            "UPDATE neon_migration.migration_id SET id = $1",
-            &[&migration_id],
-        )
-        .with_context(|| format!("update neon_migration.migration_id to {migration_id}"))?;
 
         Ok(())
     }
 
-    /// Prepare the migrations the target database for handling migrations
+    fn prepare_migrations(&mut self) -> Result<()> {
-    fn prepare_database(&mut self) -> Result<()> {
+        let query = "CREATE SCHEMA IF NOT EXISTS neon_migration";
-        self.client
+        self.client.simple_query(query)?;
-            .simple_query("CREATE SCHEMA IF NOT EXISTS neon_migration")?;
+
-        self.client.simple_query("CREATE TABLE IF NOT EXISTS neon_migration.migration_id (key INT NOT NULL PRIMARY KEY, id bigint NOT NULL DEFAULT 0)")?;
+        let query = "CREATE TABLE IF NOT EXISTS neon_migration.migration_id (key INT NOT NULL PRIMARY KEY, id bigint NOT NULL DEFAULT 0)";
-        self.client.simple_query(
+        self.client.simple_query(query)?;
-            "INSERT INTO neon_migration.migration_id VALUES (0, 0) ON CONFLICT DO NOTHING",
+
-        )?;
+        let query = "INSERT INTO neon_migration.migration_id VALUES (0, 0) ON CONFLICT DO NOTHING";
-        self.client
+        self.client.simple_query(query)?;
-            .simple_query("ALTER SCHEMA neon_migration OWNER TO cloud_admin")?;
+
-        self.client
+        let query = "ALTER SCHEMA neon_migration OWNER TO cloud_admin";
-            .simple_query("REVOKE ALL ON SCHEMA neon_migration FROM PUBLIC")?;
+        self.client.simple_query(query)?;
+
+        let query = "REVOKE ALL ON SCHEMA neon_migration FROM PUBLIC";
+        self.client.simple_query(query)?;
 
         Ok(())
     }
 
-    /// Run an individual migration
-    fn run_migration(txn: &mut Transaction, migration_id: i64, migration: &str) -> Result<()> {
-        if migration.starts_with("-- SKIP") {
-            info!("Skipping migration id={}", migration_id);
-
-            // Even though we are skipping the migration, updating the
-            // migration ID should help keep logic easy to understand when
-            // trying to understand the state of a cluster.
-            Self::update_migration_id(txn, migration_id)?;
-        } else {
-            info!("Running migration id={}:\n{}\n", migration_id, migration);
-
-            txn.simple_query(migration)
-                .with_context(|| format!("apply migration {migration_id}"))?;
-
-            Self::update_migration_id(txn, migration_id)?;
-        }
-
-        Ok(())
-    }
-
-    /// Run the configured set of migrations
     pub fn run_migrations(mut self) -> Result<()> {
-        self.prepare_database()
+        self.prepare_migrations()?;
-            .context("prepare database to handle migrations")?;
 
         let mut current_migration = self.get_migration_id()? as usize;
         while current_migration < self.migrations.len() {
-            // The index lags the migration ID by 1, so the current migration
+            macro_rules! migration_id {
-            // ID is also the next index
+                ($cm:expr) => {
-            let migration_id = (current_migration + 1) as i64;
+                    ($cm + 1) as i64
+                };
+            }
 
-            let mut txn = self
+            let migration = self.migrations[current_migration];
-                .client
-                .transaction()
-                .with_context(|| format!("begin transaction for migration {migration_id}"))?;
 
-            Self::run_migration(&mut txn, migration_id, self.migrations[current_migration])
+            if migration.starts_with("-- SKIP") {
-                .with_context(|| format!("running migration {migration_id}"))?;
+                info!("Skipping migration id={}", migration_id!(current_migration));
+            } else {
+                info!(
+                    "Running migration id={}:\n{}\n",
+                    migration_id!(current_migration),
+                    migration
+                );
 
-            txn.commit()
+                self.client
-                .with_context(|| format!("commit transaction for migration {migration_id}"))?;
+                    .simple_query("BEGIN")
+                    .context("begin migration")?;
 
-            info!("Finished migration id={}", migration_id);
+                self.client.simple_query(migration).with_context(|| {
+                    format!(
+                        "run_migrations migration id={}",
+                        migration_id!(current_migration)
+                    )
+                })?;
+
+                // Migration IDs start at 1
+                self.update_migration_id(migration_id!(current_migration))?;
+
+                self.client
+                    .simple_query("COMMIT")
+                    .context("commit migration")?;
+
+                info!("Finished migration id={}", migration_id!(current_migration));
+            }
 
             current_migration += 1;
         }

compute_tools/src/migrations/tests/0001-neon_superuser_bypass_rls.sql

@@ -1,9 +0,0 @@
-DO $$
-DECLARE
-    bypassrls boolean;
-BEGIN
-    SELECT rolbypassrls INTO bypassrls FROM pg_roles WHERE rolname = 'neon_superuser';
-    IF NOT bypassrls THEN
-        RAISE EXCEPTION 'neon_superuser cannot bypass RLS';
-    END IF;
-END $$;

compute_tools/src/migrations/tests/0002-alter_roles.sql

@@ -1,25 +0,0 @@
-DO $$
-DECLARE
-    role record;
-BEGIN
-    FOR role IN
-        SELECT rolname AS name, rolinherit AS inherit
-        FROM pg_roles
-        WHERE pg_has_role(rolname, 'neon_superuser', 'member')
-    LOOP
-        IF NOT role.inherit THEN
-            RAISE EXCEPTION '% cannot inherit', quote_ident(role.name);
-        END IF;
-    END LOOP;
-
-    FOR role IN
-        SELECT rolname AS name, rolbypassrls AS bypassrls
-        FROM pg_roles
-        WHERE NOT pg_has_role(rolname, 'neon_superuser', 'member')
-            AND NOT starts_with(rolname, 'pg_')
-    LOOP
-        IF role.bypassrls THEN
-            RAISE EXCEPTION  '% can bypass RLS', quote_ident(role.name);
-        END IF;
-    END LOOP;
-END $$;

compute_tools/src/migrations/tests/0003-grant_pg_create_subscription_to_neon_superuser.sql

@@ -1,10 +0,0 @@
-DO $$
-BEGIN
-    IF (SELECT current_setting('server_version_num')::numeric < 160000) THEN
-        RETURN;
-    END IF;
-
-    IF NOT (SELECT pg_has_role('neon_superuser', 'pg_create_subscription', 'member')) THEN
-        RAISE EXCEPTION 'neon_superuser cannot execute pg_create_subscription';
-    END IF;
-END $$;

compute_tools/src/migrations/tests/0004-grant_pg_monitor_to_neon_superuser.sql

@@ -1,19 +0,0 @@
-DO $$
-DECLARE
-    monitor record;
-BEGIN
-    SELECT pg_has_role('neon_superuser', 'pg_monitor', 'member') AS member,
-            admin_option AS admin
-        INTO monitor
-        FROM pg_auth_members
-        WHERE roleid = 'pg_monitor'::regrole
-            AND member = 'pg_monitor'::regrole;
-
-    IF NOT monitor.member THEN
-        RAISE EXCEPTION 'neon_superuser is not a member of pg_monitor';
-    END IF;
-
-    IF NOT monitor.admin THEN
-        RAISE EXCEPTION 'neon_superuser cannot grant pg_monitor';
-    END IF;
-END $$;

compute_tools/src/migrations/tests/0005-grant_all_on_tables_to_neon_superuser.sql

@@ -1,2 +0,0 @@
--- This test was never written becuase at the time migration tests were added
--- the accompanying migration was already skipped.

compute_tools/src/migrations/tests/0006-grant_all_on_sequences_to_neon_superuser.sql

@@ -1,2 +0,0 @@
--- This test was never written becuase at the time migration tests were added
--- the accompanying migration was already skipped.

compute_tools/src/migrations/tests/0007-grant_all_on_tables_to_neon_superuser_with_grant_option.sql

@@ -1,2 +0,0 @@
--- This test was never written becuase at the time migration tests were added
--- the accompanying migration was already skipped.

compute_tools/src/migrations/tests/0008-grant_all_on_sequences_to_neon_superuser_with_grant_option.sql

@@ -1,2 +0,0 @@
--- This test was never written becuase at the time migration tests were added
--- the accompanying migration was already skipped.

compute_tools/src/migrations/tests/0009-revoke_replication_for_previously_allowed_roles.sql

@@ -1,2 +0,0 @@
--- This test was never written becuase at the time migration tests were added
--- the accompanying migration was already skipped.

compute_tools/src/migrations/tests/0010-grant_snapshot_synchronization_funcs_to_neon_superuser.sql

@@ -1,13 +0,0 @@
-DO $$
-DECLARE
-    can_execute boolean;
-BEGIN
-    SELECT bool_and(has_function_privilege('neon_superuser', oid, 'execute'))
-       INTO can_execute
-       FROM pg_proc
-       WHERE proname IN ('pg_export_snapshot', 'pg_log_standby_snapshot')
-           AND pronamespace = 'pg_catalog'::regnamespace;
-    IF NOT can_execute THEN
-        RAISE EXCEPTION 'neon_superuser cannot execute both pg_export_snapshot and pg_log_standby_snapshot';
-    END IF;
-END $$;

compute_tools/src/migrations/tests/0011-grant_pg_show_replication_origin_status_to_neon_superuser.sql

@@ -1,13 +0,0 @@
-DO $$
-DECLARE
-    can_execute boolean;
-BEGIN
-    SELECT has_function_privilege('neon_superuser', oid, 'execute')
-       INTO can_execute
-       FROM pg_proc
-       WHERE proname = 'pg_show_replication_origin_status'
-           AND pronamespace = 'pg_catalog'::regnamespace;
-    IF NOT can_execute THEN
-        RAISE EXCEPTION 'neon_superuser cannot execute pg_show_replication_origin_status';
-    END IF;
-END $$;

compute_tools/src/spec_apply.rs

@@ -47,7 +47,6 @@ pub enum PerDatabasePhase {
     DeleteDBRoleReferences,
     ChangeSchemaPerms,
     HandleAnonExtension,
-    DropSubscriptionsForDeletedDatabases,
 }
 
 #[derive(Clone, Debug)]
@@ -75,7 +74,7 @@ pub struct MutableApplyContext {
     pub dbs: HashMap<String, Database>,
 }
 
-/// Apply the operations that belong to the given spec apply phase.
+/// Appply the operations that belong to the given spec apply phase.
 ///
 /// Commands within a single phase are executed in order of Iterator yield.
 /// Commands of ApplySpecPhase::RunInEachDatabase will execute in the database
@@ -327,12 +326,13 @@ async fn get_operations<'a>(
 
                             // Use FORCE to drop database even if there are active connections.
                             // We run this from `cloud_admin`, so it should have enough privileges.
-                            //
                             // NB: there could be other db states, which prevent us from dropping
                             // the database. For example, if db is used by any active subscription
                             // or replication slot.
-                            // Such cases are handled in the DropSubscriptionsForDeletedDatabases
+                            // TODO: deal with it once we allow logical replication. Proper fix should
-                            // phase. We do all the cleanup before actually dropping the database.
+                            // involve returning an error code to the control plane, so it could
+                            // figure out that this is a non-retryable error, return it to the user
+                            // and fail operation permanently.
                             let drop_db_query: String = format!(
                                 "DROP DATABASE IF EXISTS {} WITH (FORCE)",
                                 &op.name.pg_quote()
@@ -444,30 +444,6 @@ async fn get_operations<'a>(
         }
         ApplySpecPhase::RunInEachDatabase { db, subphase } => {
             match subphase {
-                PerDatabasePhase::DropSubscriptionsForDeletedDatabases => {
-                    match &db {
-                        DB::UserDB(db) => {
-                            let drop_subscription_query: String = format!(
-                                include_str!("sql/drop_subscription_for_drop_dbs.sql"),
-                                datname_str = escape_literal(&db.name),
-                            );
-
-                            let operations = vec![Operation {
-                                query: drop_subscription_query,
-                                comment: Some(format!(
-                                    "optionally dropping subscriptions for DB {}",
-                                    db.name,
-                                )),
-                            }]
-                            .into_iter();
-
-                            Ok(Box::new(operations))
-                        }
-                        // skip this cleanup for the system databases
-                        // because users can't drop them
-                        DB::SystemDB => Ok(Box::new(empty())),
-                    }
-                }
                 PerDatabasePhase::DeleteDBRoleReferences => {
                     let ctx = ctx.read().await;
 
@@ -498,19 +474,7 @@ async fn get_operations<'a>(
                                         ),
                                         comment: None,
                                     },
-                                    // Revoke some potentially blocking privileges (Neon-specific currently)
-                                    Operation {
-                                        query: format!(
-                                            include_str!("sql/pre_drop_role_revoke_privileges.sql"),
-                                            role_name = quoted,
-                                        ),
-                                        comment: None,
-                                    },
                                     // This now will only drop privileges of the role
-                                    // TODO: this is obviously not 100% true because of the above case,
-                                    // there could be still some privileges that are not revoked. Maybe this
-                                    // only drops privileges that were granted *by this* role, not *to this* role,
-                                    // but this has to be checked.
                                     Operation {
                                         query: format!("DROP OWNED BY {}", quoted),
                                         comment: None,

compute_tools/src/sql/drop_subscription_for_drop_dbs.sql

@@ -1,11 +0,0 @@
-DO $$
-DECLARE
-    subname TEXT;
-BEGIN
-    FOR subname IN SELECT pg_subscription.subname FROM pg_subscription WHERE subdbid = (SELECT oid FROM pg_database WHERE datname = {datname_str}) LOOP
-        EXECUTE format('ALTER SUBSCRIPTION %I DISABLE;', subname);
-        EXECUTE format('ALTER SUBSCRIPTION %I SET (slot_name = NONE);', subname);
-        EXECUTE format('DROP SUBSCRIPTION %I;', subname);
-    END LOOP;
-END;
-$$;

compute_tools/src/sql/pre_drop_role_revoke_privileges.sql

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

control_plane/src/background_process.rs

@@ -274,7 +274,6 @@ fn fill_remote_storage_secrets_vars(mut cmd: &mut Command) -> &mut Command {
     for env_key in [
         "AWS_ACCESS_KEY_ID",
         "AWS_SECRET_ACCESS_KEY",
-        "AWS_SESSION_TOKEN",
         "AWS_PROFILE",
         // HOME is needed in combination with `AWS_PROFILE` to pick up the SSO sessions.
         "HOME",

control_plane/src/bin/neon_local.rs

@@ -19,7 +19,6 @@ use control_plane::storage_controller::{
     NeonStorageControllerStartArgs, NeonStorageControllerStopArgs, StorageController,
 };
 use control_plane::{broker, local_env};
-use nix::fcntl::{flock, FlockArg};
 use pageserver_api::config::{
     DEFAULT_HTTP_LISTEN_PORT as DEFAULT_PAGESERVER_HTTP_PORT,
     DEFAULT_PG_LISTEN_PORT as DEFAULT_PAGESERVER_PG_PORT,
@@ -37,8 +36,6 @@ use safekeeper_api::{
 };
 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;
@@ -692,21 +689,6 @@ struct TimelineTreeEl {
     pub children: BTreeSet<TimelineId>,
 }
 
-/// A flock-based guard over the neon_local repository directory
-struct RepoLock {
-    _file: File,
-}
-
-impl RepoLock {
-    fn new() -> Result<Self> {
-        let repo_dir = File::open(local_env::base_path())?;
-        let repo_dir_fd = repo_dir.as_raw_fd();
-        flock(repo_dir_fd, FlockArg::LockExclusive)?;
-
-        Ok(Self { _file: repo_dir })
-    }
-}
-
 // Main entry point for the 'neon_local' CLI utility
 //
 // This utility helps to manage neon installation. That includes following:
@@ -718,14 +700,9 @@ fn main() -> Result<()> {
     let cli = Cli::parse();
 
     // Check for 'neon init' command first.
-    let (subcommand_result, _lock) = if let NeonLocalCmd::Init(args) = cli.command {
+    let subcommand_result = if let NeonLocalCmd::Init(args) = cli.command {
-        (handle_init(&args).map(|env| Some(Cow::Owned(env))), None)
+        handle_init(&args).map(|env| Some(Cow::Owned(env)))
     } else {
-        // This tool uses a collection of simple files to store its state, and consequently
-        // it is not generally safe to run multiple commands concurrently.  Rather than expect
-        // all callers to know this, use a lock file to protect against concurrent execution.
-        let _repo_lock = RepoLock::new().unwrap();
-
         // all other commands need an existing config
         let env = LocalEnv::load_config(&local_env::base_path()).context("Error loading config")?;
         let original_env = env.clone();
@@ -751,12 +728,11 @@ fn main() -> Result<()> {
             NeonLocalCmd::Mappings(subcmd) => handle_mappings(&subcmd, env),
         };
 
-        let subcommand_result = if &original_env != env {
+        if &original_env != env {
             subcommand_result.map(|()| Some(Cow::Borrowed(env)))
         } else {
             subcommand_result.map(|()| None)
-        };
+        }
-        (subcommand_result, Some(_repo_lock))
     };
 
     match subcommand_result {
@@ -946,7 +922,7 @@ fn handle_init(args: &InitCmdArgs) -> anyhow::Result<LocalEnv> {
     } else {
         // User (likely interactive) did not provide a description of the environment, give them the default
         NeonLocalInitConf {
-            control_plane_api: Some(DEFAULT_PAGESERVER_CONTROL_PLANE_API.parse().unwrap()),
+            control_plane_api: Some(Some(DEFAULT_PAGESERVER_CONTROL_PLANE_API.parse().unwrap())),
             broker: NeonBroker {
                 listen_addr: DEFAULT_BROKER_ADDR.parse().unwrap(),
             },
@@ -1742,15 +1718,18 @@ async fn handle_start_all_impl(
             broker::start_broker_process(env, &retry_timeout).await
         });
 
-        js.spawn(async move {
+        // Only start the storage controller if the pageserver is configured to need it
-            let storage_controller = StorageController::from_env(env);
+        if env.control_plane_api.is_some() {
-            storage_controller
+            js.spawn(async move {
-                .start(NeonStorageControllerStartArgs::with_default_instance_id(
+                let storage_controller = StorageController::from_env(env);
-                    retry_timeout,
+                storage_controller
-                ))
+                    .start(NeonStorageControllerStartArgs::with_default_instance_id(
-                .await
+                        retry_timeout,
-                .map_err(|e| e.context("start storage_controller"))
+                    ))
-        });
+                    .await
+                    .map_err(|e| e.context("start storage_controller"))
+            });
+        }
 
         for ps_conf in &env.pageservers {
             js.spawn(async move {
@@ -1795,6 +1774,10 @@ async fn neon_start_status_check(
     const RETRY_INTERVAL: Duration = Duration::from_millis(100);
     const NOTICE_AFTER_RETRIES: Duration = Duration::from_secs(5);
 
+    if env.control_plane_api.is_none() {
+        return Ok(());
+    }
+
     let storcon = StorageController::from_env(env);
 
     let retries = retry_timeout.as_millis() / RETRY_INTERVAL.as_millis();

control_plane/src/endpoint.rs

@@ -62,7 +62,7 @@ use crate::local_env::LocalEnv;
 use crate::postgresql_conf::PostgresConf;
 use crate::storage_controller::StorageController;
 
-use compute_api::responses::{ComputeStatus, ComputeStatusResponse};
+use compute_api::responses::{ComputeState, ComputeStatus};
 use compute_api::spec::{Cluster, ComputeFeature, ComputeMode, ComputeSpec};
 
 // contents of a endpoint.json file
@@ -316,10 +316,6 @@ impl Endpoint {
         // and can cause errors like 'no unpinned buffers available', see
         // <https://github.com/neondatabase/neon/issues/9956>
         conf.append("shared_buffers", "1MB");
-        // Postgres defaults to effective_io_concurrency=1, which does not exercise the pageserver's
-        // batching logic.  Set this to 2 so that we exercise the code a bit without letting
-        // individual tests do a lot of concurrent work on underpowered test machines
-        conf.append("effective_io_concurrency", "2");
         conf.append("fsync", "off");
         conf.append("max_connections", "100");
         conf.append("wal_level", "logical");
@@ -585,7 +581,6 @@ impl Endpoint {
             features: self.features.clone(),
             swap_size_bytes: None,
             disk_quota_bytes: None,
-            disable_lfc_resizing: None,
             cluster: Cluster {
                 cluster_id: None, // project ID: not used
                 name: None,       // project name: not used
@@ -739,7 +734,7 @@ impl Endpoint {
     }
 
     // Call the /status HTTP API
-    pub async fn get_status(&self) -> Result<ComputeStatusResponse> {
+    pub async fn get_status(&self) -> Result<ComputeState> {
         let client = reqwest::Client::new();
 
         let response = client
@@ -815,7 +810,7 @@ impl Endpoint {
         }
 
         let client = reqwest::Client::builder()
-            .timeout(Duration::from_secs(120))
+            .timeout(Duration::from_secs(30))
             .build()
             .unwrap();
         let response = client

control_plane/src/local_env.rs

@@ -76,7 +76,7 @@ pub struct LocalEnv {
 
     // Control plane upcall API for pageserver: if None, we will not run storage_controller  If set, this will
     // be propagated into each pageserver's configuration.
-    pub control_plane_api: Url,
+    pub control_plane_api: Option<Url>,
 
     // Control plane upcall API for storage controller.  If set, this will be propagated into the
     // storage controller's configuration.
@@ -133,7 +133,7 @@ pub struct NeonLocalInitConf {
     pub storage_controller: Option<NeonStorageControllerConf>,
     pub pageservers: Vec<NeonLocalInitPageserverConf>,
     pub safekeepers: Vec<SafekeeperConf>,
-    pub control_plane_api: Option<Url>,
+    pub control_plane_api: Option<Option<Url>>,
     pub control_plane_compute_hook_api: Option<Option<Url>>,
 }
 
@@ -180,7 +180,7 @@ impl NeonStorageControllerConf {
     const DEFAULT_MAX_WARMING_UP_INTERVAL: std::time::Duration = std::time::Duration::from_secs(30);
 
     // Very tight heartbeat interval to speed up tests
-    const DEFAULT_HEARTBEAT_INTERVAL: std::time::Duration = std::time::Duration::from_millis(1000);
+    const DEFAULT_HEARTBEAT_INTERVAL: std::time::Duration = std::time::Duration::from_millis(100);
 }
 
 impl Default for NeonStorageControllerConf {
@@ -535,7 +535,7 @@ impl LocalEnv {
                 storage_controller,
                 pageservers,
                 safekeepers,
-                control_plane_api: control_plane_api.unwrap(),
+                control_plane_api,
                 control_plane_compute_hook_api,
                 branch_name_mappings,
             }
@@ -638,7 +638,7 @@ impl LocalEnv {
                 storage_controller: self.storage_controller.clone(),
                 pageservers: vec![], // it's skip_serializing anyway
                 safekeepers: self.safekeepers.clone(),
-                control_plane_api: Some(self.control_plane_api.clone()),
+                control_plane_api: self.control_plane_api.clone(),
                 control_plane_compute_hook_api: self.control_plane_compute_hook_api.clone(),
                 branch_name_mappings: self.branch_name_mappings.clone(),
             },
@@ -768,7 +768,7 @@ impl LocalEnv {
             storage_controller: storage_controller.unwrap_or_default(),
             pageservers: pageservers.iter().map(Into::into).collect(),
             safekeepers,
-            control_plane_api: control_plane_api.unwrap(),
+            control_plane_api: control_plane_api.unwrap_or_default(),
             control_plane_compute_hook_api: control_plane_compute_hook_api.unwrap_or_default(),
             branch_name_mappings: Default::default(),
         };

control_plane/src/pageserver.rs

@@ -95,19 +95,21 @@ impl PageServerNode {
 
         let mut overrides = vec![pg_distrib_dir_param, broker_endpoint_param];
 
-        overrides.push(format!(
+        if let Some(control_plane_api) = &self.env.control_plane_api {
-            "control_plane_api='{}'",
+            overrides.push(format!(
-            self.env.control_plane_api.as_str()
+                "control_plane_api='{}'",
-        ));
+                control_plane_api.as_str()
+            ));
 
-        // Storage controller uses the same auth as pageserver: if JWT is enabled
+            // Storage controller uses the same auth as pageserver: if JWT is enabled
-        // for us, we will also need it to talk to them.
+            // for us, we will also need it to talk to them.
-        if matches!(conf.http_auth_type, AuthType::NeonJWT) {
+            if matches!(conf.http_auth_type, AuthType::NeonJWT) {
-            let jwt_token = self
+                let jwt_token = self
-                .env
+                    .env
-                .generate_auth_token(&Claims::new(None, Scope::GenerationsApi))
+                    .generate_auth_token(&Claims::new(None, Scope::GenerationsApi))
-                .unwrap();
+                    .unwrap();
-            overrides.push(format!("control_plane_api_token='{}'", jwt_token));
+                overrides.push(format!("control_plane_api_token='{}'", jwt_token));
+            }
         }
 
         if !conf.other.contains_key("remote_storage") {
@@ -433,7 +435,7 @@ impl PageServerNode {
     ) -> anyhow::Result<()> {
         let config = Self::parse_config(settings)?;
         self.http_client
-            .set_tenant_config(&models::TenantConfigRequest { tenant_id, config })
+            .tenant_config(&models::TenantConfigRequest { tenant_id, config })
             .await?;
 
         Ok(())

control_plane/src/storage_controller.rs

@@ -338,7 +338,7 @@ impl StorageController {
                         .port(),
                 )
             } else {
-                let listen_url = self.env.control_plane_api.clone();
+                let listen_url = self.env.control_plane_api.clone().unwrap();
 
                 let listen = format!(
                     "{}:{}",
@@ -708,7 +708,7 @@ impl StorageController {
         } else {
             // The configured URL has the /upcall path prefix for pageservers to use: we will strip that out
             // for general purpose API access.
-            let listen_url = self.env.control_plane_api.clone();
+            let listen_url = self.env.control_plane_api.clone().unwrap();
             Url::from_str(&format!(
                 "http://{}:{}/{path}",
                 listen_url.host_str().unwrap(),

control_plane/storcon_cli/src/main.rs

@@ -5,13 +5,12 @@ use clap::{Parser, Subcommand};
 use pageserver_api::{
     controller_api::{
         AvailabilityZone, NodeAvailabilityWrapper, NodeDescribeResponse, NodeShardResponse,
-        SafekeeperDescribeResponse, ShardSchedulingPolicy, TenantCreateRequest,
+        ShardSchedulingPolicy, TenantCreateRequest, TenantDescribeResponse, TenantPolicyRequest,
-        TenantDescribeResponse, TenantPolicyRequest,
     },
     models::{
         EvictionPolicy, EvictionPolicyLayerAccessThreshold, LocationConfigSecondary,
-        ShardParameters, TenantConfig, TenantConfigPatchRequest, TenantConfigRequest,
+        ShardParameters, TenantConfig, TenantConfigRequest, TenantShardSplitRequest,
-        TenantShardSplitRequest, TenantShardSplitResponse,
+        TenantShardSplitResponse,
     },
     shard::{ShardStripeSize, TenantShardId},
 };
@@ -117,19 +116,9 @@ enum Command {
         #[arg(long)]
         tenant_shard_id: TenantShardId,
     },
-    /// Set the pageserver tenant configuration of a tenant: this is the configuration structure
+    /// Modify the pageserver tenant configuration of a tenant: this is the configuration structure
     /// that is passed through to pageservers, and does not affect storage controller behavior.
-    /// Any previous tenant configs are overwritten.
+    TenantConfig {
-    SetTenantConfig {
-        #[arg(long)]
-        tenant_id: TenantId,
-        #[arg(long)]
-        config: String,
-    },
-    /// Patch the pageserver tenant configuration of a tenant. Any fields with null values in the
-    /// provided JSON are unset from the tenant config and all fields with non-null values are set.
-    /// Unspecified fields are not changed.
-    PatchTenantConfig {
         #[arg(long)]
         tenant_id: TenantId,
         #[arg(long)]
@@ -212,8 +201,6 @@ enum Command {
         #[arg(long)]
         timeout: humantime::Duration,
     },
-    /// List safekeepers known to the storage controller
-    Safekeepers {},
 }
 
 #[derive(Parser)]
@@ -562,21 +549,11 @@ async fn main() -> anyhow::Result<()> {
                 )
                 .await?;
         }
-        Command::SetTenantConfig { tenant_id, config } => {
+        Command::TenantConfig { tenant_id, config } => {
             let tenant_conf = serde_json::from_str(&config)?;
 
             vps_client
-                .set_tenant_config(&TenantConfigRequest {
+                .tenant_config(&TenantConfigRequest {
-                    tenant_id,
-                    config: tenant_conf,
-                })
-                .await?;
-        }
-        Command::PatchTenantConfig { tenant_id, config } => {
-            let tenant_conf = serde_json::from_str(&config)?;
-
-            vps_client
-                .patch_tenant_config(&TenantConfigPatchRequest {
                     tenant_id,
                     config: tenant_conf,
                 })
@@ -759,7 +736,7 @@ async fn main() -> anyhow::Result<()> {
             threshold,
         } => {
             vps_client
-                .set_tenant_config(&TenantConfigRequest {
+                .tenant_config(&TenantConfigRequest {
                     tenant_id,
                     config: TenantConfig {
                         eviction_policy: Some(EvictionPolicy::LayerAccessThreshold(
@@ -1023,40 +1000,6 @@ async fn main() -> anyhow::Result<()> {
                 "Fill was cancelled for node {node_id}. Schedulling policy is now {final_policy:?}"
             );
         }
-        Command::Safekeepers {} => {
-            let mut resp = storcon_client
-                .dispatch::<(), Vec<SafekeeperDescribeResponse>>(
-                    Method::GET,
-                    "control/v1/safekeeper".to_string(),
-                    None,
-                )
-                .await?;
-
-            resp.sort_by(|a, b| a.id.cmp(&b.id));
-
-            let mut table = comfy_table::Table::new();
-            table.set_header([
-                "Id",
-                "Version",
-                "Host",
-                "Port",
-                "Http Port",
-                "AZ Id",
-                "Scheduling",
-            ]);
-            for sk in resp {
-                table.add_row([
-                    format!("{}", sk.id),
-                    format!("{}", sk.version),
-                    sk.host,
-                    format!("{}", sk.port),
-                    format!("{}", sk.http_port),
-                    sk.availability_zone_id.clone(),
-                    String::from(sk.scheduling_policy),
-                ]);
-            }
-            println!("{table}");
-        }
     }
 
     Ok(())

deny.toml

@@ -42,7 +42,6 @@ allow = [
     "MPL-2.0",
     "OpenSSL",
     "Unicode-DFS-2016",
-    "Unicode-3.0",
 ]
 confidence-threshold = 0.8
 exceptions = [

docker-compose/compute_wrapper/var/db/postgres/specs/spec.json

@@ -132,6 +132,11 @@
                 "name": "cron.database",
                 "value": "postgres",
                 "vartype": "string"
+            },
+            {
+                "name": "session_preload_libraries",
+                "value": "anon",
+                "vartype": "string"
             }
         ]
     },

docker-compose/docker_compose_test.sh

@@ -35,11 +35,11 @@ for pg_version in ${TEST_VERSION_ONLY-14 15 16 17}; do
     echo "clean up containers if exists"
     cleanup
     PG_TEST_VERSION=$((pg_version < 16 ? 16 : pg_version))
-    # The support of pg_anon not yet added to PG17, so we have to add the corresponding option for other PG versions
+    # The support of pg_anon not yet added to PG17, so we have to remove the corresponding option
-    if [ "${pg_version}" -ne 17 ]; then
+    if [ $pg_version -eq 17 ]; then
       SPEC_PATH="compute_wrapper/var/db/postgres/specs"
       mv $SPEC_PATH/spec.json $SPEC_PATH/spec.bak
-      jq '.cluster.settings += [{"name": "session_preload_libraries","value": "anon","vartype": "string"}]' "${SPEC_PATH}/spec.bak" > "${SPEC_PATH}/spec.json"
+      jq 'del(.cluster.settings[] | select (.name == "session_preload_libraries"))' $SPEC_PATH/spec.bak > $SPEC_PATH/spec.json
     fi
     PG_VERSION=$pg_version PG_TEST_VERSION=$PG_TEST_VERSION docker compose --profile test-extensions -f $COMPOSE_FILE up --build -d
 
@@ -106,8 +106,8 @@ for pg_version in ${TEST_VERSION_ONLY-14 15 16 17}; do
         fi
     fi
     cleanup
-    # Restore the original spec.json
+    # The support of pg_anon not yet added to PG17, so we have to remove the corresponding option
-    if [ "$pg_version" -ne 17 ]; then
+    if [ $pg_version -eq 17 ]; then
-      mv "$SPEC_PATH/spec.bak" "$SPEC_PATH/spec.json"
+      mv $SPEC_PATH/spec.bak $SPEC_PATH/spec.json
     fi
 done

libs/compute_api/src/responses.rs

@@ -1,5 +1,6 @@
 //! Structs representing the JSON formats used in the compute_ctl's HTTP API.
 
+use std::collections::HashSet;
 use std::fmt::Display;
 
 use chrono::{DateTime, Utc};
@@ -15,17 +16,6 @@ pub struct GenericAPIError {
     pub error: String,
 }
 
-#[derive(Debug, Clone, Serialize)]
-pub struct InfoResponse {
-    pub num_cpus: usize,
-}
-
-#[derive(Debug, Clone, Serialize)]
-pub struct ExtensionInstallResponse {
-    pub extension: PgIdent,
-    pub version: ExtVersion,
-}
-
 /// Response of the /status API
 #[derive(Serialize, Debug, Deserialize)]
 #[serde(rename_all = "snake_case")]
@@ -39,6 +29,16 @@ pub struct ComputeStatusResponse {
     pub error: Option<String>,
 }
 
+#[derive(Deserialize, Serialize)]
+#[serde(rename_all = "snake_case")]
+pub struct ComputeState {
+    pub status: ComputeStatus,
+    /// Timestamp of the last Postgres activity
+    #[serde(serialize_with = "rfc3339_serialize")]
+    pub last_active: Option<DateTime<Utc>>,
+    pub error: Option<String>,
+}
+
 #[derive(Serialize, Clone, Copy, Debug, Deserialize, PartialEq, Eq)]
 #[serde(rename_all = "snake_case")]
 pub enum ComputeStatus {
@@ -79,7 +79,7 @@ impl Display for ComputeStatus {
     }
 }
 
-pub fn rfc3339_serialize<S>(x: &Option<DateTime<Utc>>, s: S) -> Result<S::Ok, S::Error>
+fn rfc3339_serialize<S>(x: &Option<DateTime<Utc>>, s: S) -> Result<S::Ok, S::Error>
 where
     S: Serializer,
 {
@@ -163,9 +163,8 @@ pub enum ControlPlaneComputeStatus {
 #[derive(Clone, Debug, Default, Serialize)]
 pub struct InstalledExtension {
     pub extname: String,
-    pub version: String,
+    pub versions: HashSet<String>,
     pub n_databases: u32, // Number of databases using this extension
-    pub owned_by_superuser: String,
 }
 
 #[derive(Clone, Debug, Default, Serialize)]

libs/compute_api/src/spec.rs

@@ -67,15 +67,6 @@ pub struct ComputeSpec {
     #[serde(default)]
     pub disk_quota_bytes: Option<u64>,
 
-    /// Disables the vm-monitor behavior that resizes LFC on upscale/downscale, instead relying on
-    /// the initial size of LFC.
-    ///
-    /// This is intended for use when the LFC size is being overridden from the default but
-    /// autoscaling is still enabled, and we don't want the vm-monitor to interfere with the custom
-    /// LFC sizing.
-    #[serde(default)]
-    pub disable_lfc_resizing: Option<bool>,
-
     /// Expected cluster state at the end of transition process.
     pub cluster: Cluster,
     pub delta_operations: Option<Vec<DeltaOp>>,

libs/desim/src/time.rs

@@ -91,7 +91,7 @@ impl Timing {
 
     /// Return true if there is a ready event.
     fn is_event_ready(&self, queue: &mut BinaryHeap<Pending>) -> bool {
-        queue.peek().is_some_and(|x| x.time <= self.now())
+        queue.peek().map_or(false, |x| x.time <= self.now())
     }
 
     /// Clear all pending events.

libs/pageserver_api/src/controller_api.rs

@@ -75,7 +75,7 @@ pub struct TenantPolicyRequest {
     pub scheduling: Option<ShardSchedulingPolicy>,
 }
 
-#[derive(Clone, Serialize, Deserialize, PartialEq, Eq, Hash, Debug, PartialOrd, Ord)]
+#[derive(Clone, Serialize, Deserialize, PartialEq, Eq, Hash, Debug)]
 pub struct AvailabilityZone(pub String);
 
 impl Display for AvailabilityZone {
@@ -245,17 +245,6 @@ impl From<NodeAvailability> for NodeAvailabilityWrapper {
     }
 }
 
-/// Scheduling policy enables us to selectively disable some automatic actions that the
-/// controller performs on a tenant shard. This is only set to a non-default value by
-/// human intervention, and it is reset to the default value (Active) when the tenant's
-/// placement policy is modified away from Attached.
-///
-/// The typical use of a non-Active scheduling policy is one of:
-/// - Pinnning a shard to a node (i.e. migrating it there & setting a non-Active scheduling policy)
-/// - Working around a bug (e.g. if something is flapping and we need to stop it until the bug is fixed)
-///
-/// If you're not sure which policy to use to pin a shard to its current location, you probably
-/// want Pause.
 #[derive(Serialize, Deserialize, Clone, Copy, Eq, PartialEq, Debug)]
 pub enum ShardSchedulingPolicy {
     // Normal mode: the tenant's scheduled locations may be updated at will, including
@@ -320,38 +309,6 @@ impl From<NodeSchedulingPolicy> for String {
     }
 }
 
-#[derive(Serialize, Deserialize, Clone, Copy, Eq, PartialEq, Debug)]
-pub enum SkSchedulingPolicy {
-    Active,
-    Disabled,
-    Decomissioned,
-}
-
-impl FromStr for SkSchedulingPolicy {
-    type Err = anyhow::Error;
-
-    fn from_str(s: &str) -> Result<Self, Self::Err> {
-        Ok(match s {
-            "active" => Self::Active,
-            "disabled" => Self::Disabled,
-            "decomissioned" => Self::Decomissioned,
-            _ => return Err(anyhow::anyhow!("Unknown scheduling state '{s}'")),
-        })
-    }
-}
-
-impl From<SkSchedulingPolicy> for String {
-    fn from(value: SkSchedulingPolicy) -> String {
-        use SkSchedulingPolicy::*;
-        match value {
-            Active => "active",
-            Disabled => "disabled",
-            Decomissioned => "decomissioned",
-        }
-        .to_string()
-    }
-}
-
 /// Controls how tenant shards are mapped to locations on pageservers, e.g. whether
 /// to create secondary locations.
 #[derive(Clone, Serialize, Deserialize, Debug, PartialEq, Eq)]
@@ -404,24 +361,6 @@ pub struct MetadataHealthListOutdatedResponse {
     pub health_records: Vec<MetadataHealthRecord>,
 }
 
-/// Publicly exposed safekeeper description
-///
-/// The `active` flag which we have in the DB is not included on purpose: it is deprecated.
-#[derive(Serialize, Deserialize, Clone)]
-pub struct SafekeeperDescribeResponse {
-    pub id: NodeId,
-    pub region_id: String,
-    /// 1 is special, it means just created (not currently posted to storcon).
-    /// Zero or negative is not really expected.
-    /// Otherwise the number from `release-$(number_of_commits_on_branch)` tag.
-    pub version: i64,
-    pub host: String,
-    pub port: i32,
-    pub http_port: i32,
-    pub availability_zone_id: String,
-    pub scheduling_policy: SkSchedulingPolicy,
-}
-
 #[cfg(test)]
 mod test {
     use super::*;

libs/pageserver_api/src/key.rs

@@ -24,7 +24,7 @@ pub struct Key {
 
 /// When working with large numbers of Keys in-memory, it is more efficient to handle them as i128 than as
 /// a struct of fields.
-#[derive(Clone, Copy, Hash, PartialEq, Eq, Ord, PartialOrd, Serialize, Deserialize, Debug)]
+#[derive(Clone, Copy, Hash, PartialEq, Eq, Ord, PartialOrd, Serialize, Deserialize)]
 pub struct CompactKey(i128);
 
 /// The storage key size.
@@ -565,10 +565,6 @@ impl Key {
             && self.field5 == 0
             && self.field6 == u32::MAX
     }
-
-    pub fn is_slru_dir_key(&self) -> bool {
-        slru_dir_kind(self).is_some()
-    }
 }
 
 #[inline(always)]

libs/pageserver_api/src/models.rs

@@ -6,7 +6,6 @@ pub mod utilization;
 use camino::Utf8PathBuf;
 pub use utilization::PageserverUtilization;
 
-use core::ops::Range;
 use std::{
     collections::HashMap,
     fmt::Display,
@@ -18,7 +17,7 @@ use std::{
 
 use byteorder::{BigEndian, ReadBytesExt};
 use postgres_ffi::BLCKSZ;
-use serde::{Deserialize, Deserializer, Serialize, Serializer};
+use serde::{Deserialize, Serialize};
 use serde_with::serde_as;
 use utils::{
     completion,
@@ -29,7 +28,6 @@ use utils::{
 };
 
 use crate::{
-    key::Key,
     reltag::RelTag,
     shard::{ShardCount, ShardStripeSize, TenantShardId},
 };
@@ -212,68 +210,6 @@ pub enum TimelineState {
     Broken { reason: String, backtrace: String },
 }
 
-#[serde_with::serde_as]
-#[derive(Debug, Clone, serde::Deserialize, serde::Serialize)]
-pub struct CompactLsnRange {
-    pub start: Lsn,
-    pub end: Lsn,
-}
-
-#[serde_with::serde_as]
-#[derive(Debug, Clone, serde::Deserialize, serde::Serialize)]
-pub struct CompactKeyRange {
-    #[serde_as(as = "serde_with::DisplayFromStr")]
-    pub start: Key,
-    #[serde_as(as = "serde_with::DisplayFromStr")]
-    pub end: Key,
-}
-
-impl From<Range<Lsn>> for CompactLsnRange {
-    fn from(range: Range<Lsn>) -> Self {
-        Self {
-            start: range.start,
-            end: range.end,
-        }
-    }
-}
-
-impl From<Range<Key>> for CompactKeyRange {
-    fn from(range: Range<Key>) -> Self {
-        Self {
-            start: range.start,
-            end: range.end,
-        }
-    }
-}
-
-impl From<CompactLsnRange> for Range<Lsn> {
-    fn from(range: CompactLsnRange) -> Self {
-        range.start..range.end
-    }
-}
-
-impl From<CompactKeyRange> for Range<Key> {
-    fn from(range: CompactKeyRange) -> Self {
-        range.start..range.end
-    }
-}
-
-impl CompactLsnRange {
-    pub fn above(lsn: Lsn) -> Self {
-        Self {
-            start: lsn,
-            end: Lsn::MAX,
-        }
-    }
-}
-
-#[derive(Debug, Clone, Serialize)]
-pub struct CompactInfoResponse {
-    pub compact_key_range: Option<CompactKeyRange>,
-    pub compact_lsn_range: Option<CompactLsnRange>,
-    pub sub_compaction: bool,
-}
-
 #[derive(Serialize, Deserialize, Clone)]
 pub struct TimelineCreateRequest {
     pub new_timeline_id: TimelineId,
@@ -389,115 +325,6 @@ impl Default for ShardParameters {
     }
 }
 
-#[derive(Debug, Default, Clone, Eq, PartialEq)]
-pub enum FieldPatch<T> {
-    Upsert(T),
-    Remove,
-    #[default]
-    Noop,
-}
-
-impl<T> FieldPatch<T> {
-    fn is_noop(&self) -> bool {
-        matches!(self, FieldPatch::Noop)
-    }
-
-    pub fn apply(self, target: &mut Option<T>) {
-        match self {
-            Self::Upsert(v) => *target = Some(v),
-            Self::Remove => *target = None,
-            Self::Noop => {}
-        }
-    }
-
-    pub fn map<U, E, F: FnOnce(T) -> Result<U, E>>(self, map: F) -> Result<FieldPatch<U>, E> {
-        match self {
-            Self::Upsert(v) => Ok(FieldPatch::<U>::Upsert(map(v)?)),
-            Self::Remove => Ok(FieldPatch::<U>::Remove),
-            Self::Noop => Ok(FieldPatch::<U>::Noop),
-        }
-    }
-}
-
-impl<'de, T: Deserialize<'de>> Deserialize<'de> for FieldPatch<T> {
-    fn deserialize<D>(deserializer: D) -> Result<Self, D::Error>
-    where
-        D: Deserializer<'de>,
-    {
-        Option::deserialize(deserializer).map(|opt| match opt {
-            None => FieldPatch::Remove,
-            Some(val) => FieldPatch::Upsert(val),
-        })
-    }
-}
-
-impl<T: Serialize> Serialize for FieldPatch<T> {
-    fn serialize<S>(&self, serializer: S) -> Result<S::Ok, S::Error>
-    where
-        S: Serializer,
-    {
-        match self {
-            FieldPatch::Upsert(val) => serializer.serialize_some(val),
-            FieldPatch::Remove => serializer.serialize_none(),
-            FieldPatch::Noop => unreachable!(),
-        }
-    }
-}
-
-#[derive(Serialize, Deserialize, Debug, Default, Clone, Eq, PartialEq)]
-#[serde(default)]
-pub struct TenantConfigPatch {
-    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
-    pub checkpoint_distance: FieldPatch<u64>,
-    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
-    pub checkpoint_timeout: FieldPatch<String>,
-    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
-    pub compaction_target_size: FieldPatch<u64>,
-    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
-    pub compaction_period: FieldPatch<String>,
-    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
-    pub compaction_threshold: FieldPatch<usize>,
-    // defer parsing compaction_algorithm, like eviction_policy
-    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
-    pub compaction_algorithm: FieldPatch<CompactionAlgorithmSettings>,
-    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
-    pub gc_horizon: FieldPatch<u64>,
-    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
-    pub gc_period: FieldPatch<String>,
-    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
-    pub image_creation_threshold: FieldPatch<usize>,
-    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
-    pub pitr_interval: FieldPatch<String>,
-    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
-    pub walreceiver_connect_timeout: FieldPatch<String>,
-    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
-    pub lagging_wal_timeout: FieldPatch<String>,
-    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
-    pub max_lsn_wal_lag: FieldPatch<NonZeroU64>,
-    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
-    pub eviction_policy: FieldPatch<EvictionPolicy>,
-    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
-    pub min_resident_size_override: FieldPatch<u64>,
-    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
-    pub evictions_low_residence_duration_metric_threshold: FieldPatch<String>,
-    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
-    pub heatmap_period: FieldPatch<String>,
-    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
-    pub lazy_slru_download: FieldPatch<bool>,
-    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
-    pub timeline_get_throttle: FieldPatch<ThrottleConfig>,
-    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
-    pub image_layer_creation_check_threshold: FieldPatch<u8>,
-    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
-    pub lsn_lease_length: FieldPatch<String>,
-    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
-    pub lsn_lease_length_for_ts: FieldPatch<String>,
-    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
-    pub timeline_offloading: FieldPatch<bool>,
-    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
-    pub wal_receiver_protocol_override: FieldPatch<PostgresClientProtocol>,
-}
-
 /// An alternative representation of `pageserver::tenant::TenantConf` with
 /// simpler types.
 #[derive(Serialize, Deserialize, Debug, Default, Clone, Eq, PartialEq)]
@@ -529,107 +356,6 @@ pub struct TenantConfig {
     pub wal_receiver_protocol_override: Option<PostgresClientProtocol>,
 }
 
-impl TenantConfig {
-    pub fn apply_patch(self, patch: TenantConfigPatch) -> TenantConfig {
-        let Self {
-            mut checkpoint_distance,
-            mut checkpoint_timeout,
-            mut compaction_target_size,
-            mut compaction_period,
-            mut compaction_threshold,
-            mut compaction_algorithm,
-            mut gc_horizon,
-            mut gc_period,
-            mut image_creation_threshold,
-            mut pitr_interval,
-            mut walreceiver_connect_timeout,
-            mut lagging_wal_timeout,
-            mut max_lsn_wal_lag,
-            mut eviction_policy,
-            mut min_resident_size_override,
-            mut evictions_low_residence_duration_metric_threshold,
-            mut heatmap_period,
-            mut lazy_slru_download,
-            mut timeline_get_throttle,
-            mut image_layer_creation_check_threshold,
-            mut lsn_lease_length,
-            mut lsn_lease_length_for_ts,
-            mut timeline_offloading,
-            mut wal_receiver_protocol_override,
-        } = self;
-
-        patch.checkpoint_distance.apply(&mut checkpoint_distance);
-        patch.checkpoint_timeout.apply(&mut checkpoint_timeout);
-        patch
-            .compaction_target_size
-            .apply(&mut compaction_target_size);
-        patch.compaction_period.apply(&mut compaction_period);
-        patch.compaction_threshold.apply(&mut compaction_threshold);
-        patch.compaction_algorithm.apply(&mut compaction_algorithm);
-        patch.gc_horizon.apply(&mut gc_horizon);
-        patch.gc_period.apply(&mut gc_period);
-        patch
-            .image_creation_threshold
-            .apply(&mut image_creation_threshold);
-        patch.pitr_interval.apply(&mut pitr_interval);
-        patch
-            .walreceiver_connect_timeout
-            .apply(&mut walreceiver_connect_timeout);
-        patch.lagging_wal_timeout.apply(&mut lagging_wal_timeout);
-        patch.max_lsn_wal_lag.apply(&mut max_lsn_wal_lag);
-        patch.eviction_policy.apply(&mut eviction_policy);
-        patch
-            .min_resident_size_override
-            .apply(&mut min_resident_size_override);
-        patch
-            .evictions_low_residence_duration_metric_threshold
-            .apply(&mut evictions_low_residence_duration_metric_threshold);
-        patch.heatmap_period.apply(&mut heatmap_period);
-        patch.lazy_slru_download.apply(&mut lazy_slru_download);
-        patch
-            .timeline_get_throttle
-            .apply(&mut timeline_get_throttle);
-        patch
-            .image_layer_creation_check_threshold
-            .apply(&mut image_layer_creation_check_threshold);
-        patch.lsn_lease_length.apply(&mut lsn_lease_length);
-        patch
-            .lsn_lease_length_for_ts
-            .apply(&mut lsn_lease_length_for_ts);
-        patch.timeline_offloading.apply(&mut timeline_offloading);
-        patch
-            .wal_receiver_protocol_override
-            .apply(&mut wal_receiver_protocol_override);
-
-        Self {
-            checkpoint_distance,
-            checkpoint_timeout,
-            compaction_target_size,
-            compaction_period,
-            compaction_threshold,
-            compaction_algorithm,
-            gc_horizon,
-            gc_period,
-            image_creation_threshold,
-            pitr_interval,
-            walreceiver_connect_timeout,
-            lagging_wal_timeout,
-            max_lsn_wal_lag,
-            eviction_policy,
-            min_resident_size_override,
-            evictions_low_residence_duration_metric_threshold,
-            heatmap_period,
-            lazy_slru_download,
-            timeline_get_throttle,
-            image_layer_creation_check_threshold,
-            lsn_lease_length,
-            lsn_lease_length_for_ts,
-            timeline_offloading,
-            wal_receiver_protocol_override,
-        }
-    }
-}
-
 /// The policy for the aux file storage.
 ///
 /// It can be switched through `switch_aux_file_policy` tenant config.
@@ -960,14 +686,6 @@ impl TenantConfigRequest {
     }
 }
 
-#[derive(Serialize, Deserialize, Debug)]
-#[serde(deny_unknown_fields)]
-pub struct TenantConfigPatchRequest {
-    pub tenant_id: TenantId,
-    #[serde(flatten)]
-    pub config: TenantConfigPatch, // as we have a flattened field, we should reject all unknown fields in it
-}
-
 /// See [`TenantState::attachment_status`] and the OpenAPI docs for context.
 #[derive(Serialize, Deserialize, Clone)]
 #[serde(tag = "slug", content = "data", rename_all = "snake_case")]
@@ -1460,91 +1178,75 @@ impl TryFrom<u8> for PagestreamBeMessageTag {
 // interface allows sending both LSNs, and let the pageserver do the right thing. There was no
 // difference in the responses between V1 and V2.
 //
-// V3 version of protocol adds request ID to all requests. This request ID is also included in response
+#[derive(Clone, Copy)]
-// as well as other fields from requests, which allows to verify that we receive response for our request.
-// We copy fields from request to response to make checking more reliable: request ID is formed from process ID
-// and local counter, so in principle there can be duplicated requests IDs if process PID is reused.
-//
-#[derive(Debug, PartialEq, Eq, Clone, Copy)]
 pub enum PagestreamProtocolVersion {
     V2,
-    V3,
 }
 
-pub type RequestId = u64;
+#[derive(Debug, PartialEq, Eq)]
-
+pub struct PagestreamExistsRequest {
-#[derive(Debug, PartialEq, Eq, Clone, Copy)]
-pub struct PagestreamRequest {
-    pub reqid: RequestId,
     pub request_lsn: Lsn,
     pub not_modified_since: Lsn,
-}
-
-#[derive(Debug, PartialEq, Eq, Clone, Copy)]
-pub struct PagestreamExistsRequest {
-    pub hdr: PagestreamRequest,
     pub rel: RelTag,
 }
 
-#[derive(Debug, PartialEq, Eq, Clone, Copy)]
+#[derive(Debug, PartialEq, Eq)]
 pub struct PagestreamNblocksRequest {
-    pub hdr: PagestreamRequest,
+    pub request_lsn: Lsn,
+    pub not_modified_since: Lsn,
     pub rel: RelTag,
 }
 
-#[derive(Debug, PartialEq, Eq, Clone, Copy)]
+#[derive(Debug, PartialEq, Eq)]
 pub struct PagestreamGetPageRequest {
-    pub hdr: PagestreamRequest,
+    pub request_lsn: Lsn,
+    pub not_modified_since: Lsn,
     pub rel: RelTag,
     pub blkno: u32,
 }
 
-#[derive(Debug, PartialEq, Eq, Clone, Copy)]
+#[derive(Debug, PartialEq, Eq)]
 pub struct PagestreamDbSizeRequest {
-    pub hdr: PagestreamRequest,
+    pub request_lsn: Lsn,
+    pub not_modified_since: Lsn,
     pub dbnode: u32,
 }
 
-#[derive(Debug, PartialEq, Eq, Clone, Copy)]
+#[derive(Debug, PartialEq, Eq)]
 pub struct PagestreamGetSlruSegmentRequest {
-    pub hdr: PagestreamRequest,
+    pub request_lsn: Lsn,
+    pub not_modified_since: Lsn,
     pub kind: u8,
     pub segno: u32,
 }
 
 #[derive(Debug)]
 pub struct PagestreamExistsResponse {
-    pub req: PagestreamExistsRequest,
     pub exists: bool,
 }
 
 #[derive(Debug)]
 pub struct PagestreamNblocksResponse {
-    pub req: PagestreamNblocksRequest,
     pub n_blocks: u32,
 }
 
 #[derive(Debug)]
 pub struct PagestreamGetPageResponse {
-    pub req: PagestreamGetPageRequest,
     pub page: Bytes,
 }
 
 #[derive(Debug)]
 pub struct PagestreamGetSlruSegmentResponse {
-    pub req: PagestreamGetSlruSegmentRequest,
     pub segment: Bytes,
 }
 
 #[derive(Debug)]
 pub struct PagestreamErrorResponse {
-    pub req: PagestreamRequest,
     pub message: String,
 }
 
 #[derive(Debug)]
 pub struct PagestreamDbSizeResponse {
-    pub req: PagestreamDbSizeRequest,
     pub db_size: i64,
 }
 
@@ -1561,16 +1263,15 @@ pub struct TenantHistorySize {
 
 impl PagestreamFeMessage {
     /// Serialize a compute -> pageserver message. This is currently only used in testing
-    /// tools. Always uses protocol version 3.
+    /// tools. Always uses protocol version 2.
     pub fn serialize(&self) -> Bytes {
         let mut bytes = BytesMut::new();
 
         match self {
             Self::Exists(req) => {
                 bytes.put_u8(0);
-                bytes.put_u64(req.hdr.reqid);
+                bytes.put_u64(req.request_lsn.0);
-                bytes.put_u64(req.hdr.request_lsn.0);
+                bytes.put_u64(req.not_modified_since.0);
-                bytes.put_u64(req.hdr.not_modified_since.0);
                 bytes.put_u32(req.rel.spcnode);
                 bytes.put_u32(req.rel.dbnode);
                 bytes.put_u32(req.rel.relnode);
@@ -1579,9 +1280,8 @@ impl PagestreamFeMessage {
 
             Self::Nblocks(req) => {
                 bytes.put_u8(1);
-                bytes.put_u64(req.hdr.reqid);
+                bytes.put_u64(req.request_lsn.0);
-                bytes.put_u64(req.hdr.request_lsn.0);
+                bytes.put_u64(req.not_modified_since.0);
-                bytes.put_u64(req.hdr.not_modified_since.0);
                 bytes.put_u32(req.rel.spcnode);
                 bytes.put_u32(req.rel.dbnode);
                 bytes.put_u32(req.rel.relnode);
@@ -1590,9 +1290,8 @@ impl PagestreamFeMessage {
 
             Self::GetPage(req) => {
                 bytes.put_u8(2);
-                bytes.put_u64(req.hdr.reqid);
+                bytes.put_u64(req.request_lsn.0);
-                bytes.put_u64(req.hdr.request_lsn.0);
+                bytes.put_u64(req.not_modified_since.0);
-                bytes.put_u64(req.hdr.not_modified_since.0);
                 bytes.put_u32(req.rel.spcnode);
                 bytes.put_u32(req.rel.dbnode);
                 bytes.put_u32(req.rel.relnode);
@@ -1602,17 +1301,15 @@ impl PagestreamFeMessage {
 
             Self::DbSize(req) => {
                 bytes.put_u8(3);
-                bytes.put_u64(req.hdr.reqid);
+                bytes.put_u64(req.request_lsn.0);
-                bytes.put_u64(req.hdr.request_lsn.0);
+                bytes.put_u64(req.not_modified_since.0);
-                bytes.put_u64(req.hdr.not_modified_since.0);
                 bytes.put_u32(req.dbnode);
             }
 
             Self::GetSlruSegment(req) => {
                 bytes.put_u8(4);
-                bytes.put_u64(req.hdr.reqid);
+                bytes.put_u64(req.request_lsn.0);
-                bytes.put_u64(req.hdr.request_lsn.0);
+                bytes.put_u64(req.not_modified_since.0);
-                bytes.put_u64(req.hdr.not_modified_since.0);
                 bytes.put_u8(req.kind);
                 bytes.put_u32(req.segno);
             }
@@ -1621,35 +1318,21 @@ impl PagestreamFeMessage {
         bytes.into()
     }
 
-    pub fn parse<R: std::io::Read>(
+    pub fn parse<R: std::io::Read>(body: &mut R) -> anyhow::Result<PagestreamFeMessage> {
-        body: &mut R,
-        protocol_version: PagestreamProtocolVersion,
-    ) -> anyhow::Result<PagestreamFeMessage> {
         // these correspond to the NeonMessageTag enum in pagestore_client.h
         //
         // TODO: consider using protobuf or serde bincode for less error prone
         // serialization.
         let msg_tag = body.read_u8()?;
-        let (reqid, request_lsn, not_modified_since) = match protocol_version {
+
-            PagestreamProtocolVersion::V2 => (
+        // these two fields are the same for every request type
-                0,
+        let request_lsn = Lsn::from(body.read_u64::<BigEndian>()?);
-                Lsn::from(body.read_u64::<BigEndian>()?),
+        let not_modified_since = Lsn::from(body.read_u64::<BigEndian>()?);
-                Lsn::from(body.read_u64::<BigEndian>()?),
-            ),
-            PagestreamProtocolVersion::V3 => (
-                body.read_u64::<BigEndian>()?,
-                Lsn::from(body.read_u64::<BigEndian>()?),
-                Lsn::from(body.read_u64::<BigEndian>()?),
-            ),
-        };
 
         match msg_tag {
             0 => Ok(PagestreamFeMessage::Exists(PagestreamExistsRequest {
-                hdr: PagestreamRequest {
+                request_lsn,
-                    reqid,
+                not_modified_since,
-                    request_lsn,
-                    not_modified_since,
-                },
                 rel: RelTag {
                     spcnode: body.read_u32::<BigEndian>()?,
                     dbnode: body.read_u32::<BigEndian>()?,
@@ -1658,11 +1341,8 @@ impl PagestreamFeMessage {
                 },
             })),
             1 => Ok(PagestreamFeMessage::Nblocks(PagestreamNblocksRequest {
-                hdr: PagestreamRequest {
+                request_lsn,
-                    reqid,
+                not_modified_since,
-                    request_lsn,
-                    not_modified_since,
-                },
                 rel: RelTag {
                     spcnode: body.read_u32::<BigEndian>()?,
                     dbnode: body.read_u32::<BigEndian>()?,
@@ -1671,11 +1351,8 @@ impl PagestreamFeMessage {
                 },
             })),
             2 => Ok(PagestreamFeMessage::GetPage(PagestreamGetPageRequest {
-                hdr: PagestreamRequest {
+                request_lsn,
-                    reqid,
+                not_modified_since,
-                    request_lsn,
-                    not_modified_since,
-                },
                 rel: RelTag {
                     spcnode: body.read_u32::<BigEndian>()?,
                     dbnode: body.read_u32::<BigEndian>()?,
@@ -1685,20 +1362,14 @@ impl PagestreamFeMessage {
                 blkno: body.read_u32::<BigEndian>()?,
             })),
             3 => Ok(PagestreamFeMessage::DbSize(PagestreamDbSizeRequest {
-                hdr: PagestreamRequest {
+                request_lsn,
-                    reqid,
+                not_modified_since,
-                    request_lsn,
-                    not_modified_since,
-                },
                 dbnode: body.read_u32::<BigEndian>()?,
             })),
             4 => Ok(PagestreamFeMessage::GetSlruSegment(
                 PagestreamGetSlruSegmentRequest {
-                    hdr: PagestreamRequest {
+                    request_lsn,
-                        reqid,
+                    not_modified_since,
-                        request_lsn,
-                        not_modified_since,
-                    },
                     kind: body.read_u8()?,
                     segno: body.read_u32::<BigEndian>()?,
                 },
@@ -1709,114 +1380,43 @@ impl PagestreamFeMessage {
 }
 
 impl PagestreamBeMessage {
-    pub fn serialize(&self, protocol_version: PagestreamProtocolVersion) -> Bytes {
+    pub fn serialize(&self) -> Bytes {
         let mut bytes = BytesMut::new();
 
         use PagestreamBeMessageTag as Tag;
-        match protocol_version {
+        match self {
-            PagestreamProtocolVersion::V2 => {
+            Self::Exists(resp) => {
-                match self {
+                bytes.put_u8(Tag::Exists as u8);
-                    Self::Exists(resp) => {
+                bytes.put_u8(resp.exists as u8);
-                        bytes.put_u8(Tag::Exists as u8);
-                        bytes.put_u8(resp.exists as u8);
-                    }
-
-                    Self::Nblocks(resp) => {
-                        bytes.put_u8(Tag::Nblocks as u8);
-                        bytes.put_u32(resp.n_blocks);
-                    }
-
-                    Self::GetPage(resp) => {
-                        bytes.put_u8(Tag::GetPage as u8);
-                        bytes.put(&resp.page[..])
-                    }
-
-                    Self::Error(resp) => {
-                        bytes.put_u8(Tag::Error as u8);
-                        bytes.put(resp.message.as_bytes());
-                        bytes.put_u8(0); // null terminator
-                    }
-                    Self::DbSize(resp) => {
-                        bytes.put_u8(Tag::DbSize as u8);
-                        bytes.put_i64(resp.db_size);
-                    }
-
-                    Self::GetSlruSegment(resp) => {
-                        bytes.put_u8(Tag::GetSlruSegment as u8);
-                        bytes.put_u32((resp.segment.len() / BLCKSZ as usize) as u32);
-                        bytes.put(&resp.segment[..]);
-                    }
-                }
             }
-            PagestreamProtocolVersion::V3 => {
-                match self {
-                    Self::Exists(resp) => {
-                        bytes.put_u8(Tag::Exists as u8);
-                        bytes.put_u64(resp.req.hdr.reqid);
-                        bytes.put_u64(resp.req.hdr.request_lsn.0);
-                        bytes.put_u64(resp.req.hdr.not_modified_since.0);
-                        bytes.put_u32(resp.req.rel.spcnode);
-                        bytes.put_u32(resp.req.rel.dbnode);
-                        bytes.put_u32(resp.req.rel.relnode);
-                        bytes.put_u8(resp.req.rel.forknum);
-                        bytes.put_u8(resp.exists as u8);
-                    }
 
-                    Self::Nblocks(resp) => {
+            Self::Nblocks(resp) => {
-                        bytes.put_u8(Tag::Nblocks as u8);
+                bytes.put_u8(Tag::Nblocks as u8);
-                        bytes.put_u64(resp.req.hdr.reqid);
+                bytes.put_u32(resp.n_blocks);
-                        bytes.put_u64(resp.req.hdr.request_lsn.0);
+            }
-                        bytes.put_u64(resp.req.hdr.not_modified_since.0);
-                        bytes.put_u32(resp.req.rel.spcnode);
-                        bytes.put_u32(resp.req.rel.dbnode);
-                        bytes.put_u32(resp.req.rel.relnode);
-                        bytes.put_u8(resp.req.rel.forknum);
-                        bytes.put_u32(resp.n_blocks);
-                    }
 
-                    Self::GetPage(resp) => {
+            Self::GetPage(resp) => {
-                        bytes.put_u8(Tag::GetPage as u8);
+                bytes.put_u8(Tag::GetPage as u8);
-                        bytes.put_u64(resp.req.hdr.reqid);
+                bytes.put(&resp.page[..]);
-                        bytes.put_u64(resp.req.hdr.request_lsn.0);
+            }
-                        bytes.put_u64(resp.req.hdr.not_modified_since.0);
-                        bytes.put_u32(resp.req.rel.spcnode);
-                        bytes.put_u32(resp.req.rel.dbnode);
-                        bytes.put_u32(resp.req.rel.relnode);
-                        bytes.put_u8(resp.req.rel.forknum);
-                        bytes.put_u32(resp.req.blkno);
-                        bytes.put(&resp.page[..])
-                    }
 
-                    Self::Error(resp) => {
+            Self::Error(resp) => {
-                        bytes.put_u8(Tag::Error as u8);
+                bytes.put_u8(Tag::Error as u8);
-                        bytes.put_u64(resp.req.reqid);
+                bytes.put(resp.message.as_bytes());
-                        bytes.put_u64(resp.req.request_lsn.0);
+                bytes.put_u8(0); // null terminator
-                        bytes.put_u64(resp.req.not_modified_since.0);
+            }
-                        bytes.put(resp.message.as_bytes());
+            Self::DbSize(resp) => {
-                        bytes.put_u8(0); // null terminator
+                bytes.put_u8(Tag::DbSize as u8);
-                    }
+                bytes.put_i64(resp.db_size);
-                    Self::DbSize(resp) => {
+            }
-                        bytes.put_u8(Tag::DbSize as u8);
-                        bytes.put_u64(resp.req.hdr.reqid);
-                        bytes.put_u64(resp.req.hdr.request_lsn.0);
-                        bytes.put_u64(resp.req.hdr.not_modified_since.0);
-                        bytes.put_u32(resp.req.dbnode);
-                        bytes.put_i64(resp.db_size);
-                    }
 
-                    Self::GetSlruSegment(resp) => {
+            Self::GetSlruSegment(resp) => {
-                        bytes.put_u8(Tag::GetSlruSegment as u8);
+                bytes.put_u8(Tag::GetSlruSegment as u8);
-                        bytes.put_u64(resp.req.hdr.reqid);
+                bytes.put_u32((resp.segment.len() / BLCKSZ as usize) as u32);
-                        bytes.put_u64(resp.req.hdr.request_lsn.0);
+                bytes.put(&resp.segment[..]);
-                        bytes.put_u64(resp.req.hdr.not_modified_since.0);
-                        bytes.put_u8(resp.req.kind);
-                        bytes.put_u32(resp.req.segno);
-                        bytes.put_u32((resp.segment.len() / BLCKSZ as usize) as u32);
-                        bytes.put(&resp.segment[..]);
-                    }
-                }
             }
         }
+
         bytes.into()
     }
 
@@ -1828,131 +1428,38 @@ impl PagestreamBeMessage {
         let ok =
             match Tag::try_from(msg_tag).map_err(|tag: u8| anyhow::anyhow!("invalid tag {tag}"))? {
                 Tag::Exists => {
-                    let reqid = buf.read_u64::<BigEndian>()?;
+                    let exists = buf.read_u8()?;
-                    let request_lsn = Lsn(buf.read_u64::<BigEndian>()?);
-                    let not_modified_since = Lsn(buf.read_u64::<BigEndian>()?);
-                    let rel = RelTag {
-                        spcnode: buf.read_u32::<BigEndian>()?,
-                        dbnode: buf.read_u32::<BigEndian>()?,
-                        relnode: buf.read_u32::<BigEndian>()?,
-                        forknum: buf.read_u8()?,
-                    };
-                    let exists = buf.read_u8()? != 0;
                     Self::Exists(PagestreamExistsResponse {
-                        req: PagestreamExistsRequest {
+                        exists: exists != 0,
-                            hdr: PagestreamRequest {
-                                reqid,
-                                request_lsn,
-                                not_modified_since,
-                            },
-                            rel,
-                        },
-                        exists,
                     })
                 }
                 Tag::Nblocks => {
-                    let reqid = buf.read_u64::<BigEndian>()?;
-                    let request_lsn = Lsn(buf.read_u64::<BigEndian>()?);
-                    let not_modified_since = Lsn(buf.read_u64::<BigEndian>()?);
-                    let rel = RelTag {
-                        spcnode: buf.read_u32::<BigEndian>()?,
-                        dbnode: buf.read_u32::<BigEndian>()?,
-                        relnode: buf.read_u32::<BigEndian>()?,
-                        forknum: buf.read_u8()?,
-                    };
                     let n_blocks = buf.read_u32::<BigEndian>()?;
-                    Self::Nblocks(PagestreamNblocksResponse {
+                    Self::Nblocks(PagestreamNblocksResponse { n_blocks })
-                        req: PagestreamNblocksRequest {
-                            hdr: PagestreamRequest {
-                                reqid,
-                                request_lsn,
-                                not_modified_since,
-                            },
-                            rel,
-                        },
-                        n_blocks,
-                    })
                 }
                 Tag::GetPage => {
-                    let reqid = buf.read_u64::<BigEndian>()?;
-                    let request_lsn = Lsn(buf.read_u64::<BigEndian>()?);
-                    let not_modified_since = Lsn(buf.read_u64::<BigEndian>()?);
-                    let rel = RelTag {
-                        spcnode: buf.read_u32::<BigEndian>()?,
-                        dbnode: buf.read_u32::<BigEndian>()?,
-                        relnode: buf.read_u32::<BigEndian>()?,
-                        forknum: buf.read_u8()?,
-                    };
-                    let blkno = buf.read_u32::<BigEndian>()?;
                     let mut page = vec![0; 8192]; // TODO: use MaybeUninit
                     buf.read_exact(&mut page)?;
-                    Self::GetPage(PagestreamGetPageResponse {
+                    PagestreamBeMessage::GetPage(PagestreamGetPageResponse { page: page.into() })
-                        req: PagestreamGetPageRequest {
-                            hdr: PagestreamRequest {
-                                reqid,
-                                request_lsn,
-                                not_modified_since,
-                            },
-                            rel,
-                            blkno,
-                        },
-                        page: page.into(),
-                    })
                 }
                 Tag::Error => {
-                    let reqid = buf.read_u64::<BigEndian>()?;
-                    let request_lsn = Lsn(buf.read_u64::<BigEndian>()?);
-                    let not_modified_since = Lsn(buf.read_u64::<BigEndian>()?);
                     let mut msg = Vec::new();
                     buf.read_until(0, &mut msg)?;
                     let cstring = std::ffi::CString::from_vec_with_nul(msg)?;
                     let rust_str = cstring.to_str()?;
-                    Self::Error(PagestreamErrorResponse {
+                    PagestreamBeMessage::Error(PagestreamErrorResponse {
-                        req: PagestreamRequest {
-                            reqid,
-                            request_lsn,
-                            not_modified_since,
-                        },
                         message: rust_str.to_owned(),
                     })
                 }
                 Tag::DbSize => {
-                    let reqid = buf.read_u64::<BigEndian>()?;
-                    let request_lsn = Lsn(buf.read_u64::<BigEndian>()?);
-                    let not_modified_since = Lsn(buf.read_u64::<BigEndian>()?);
-                    let dbnode = buf.read_u32::<BigEndian>()?;
                     let db_size = buf.read_i64::<BigEndian>()?;
-                    Self::DbSize(PagestreamDbSizeResponse {
+                    Self::DbSize(PagestreamDbSizeResponse { db_size })
-                        req: PagestreamDbSizeRequest {
-                            hdr: PagestreamRequest {
-                                reqid,
-                                request_lsn,
-                                not_modified_since,
-                            },
-                            dbnode,
-                        },
-                        db_size,
-                    })
                 }
                 Tag::GetSlruSegment => {
-                    let reqid = buf.read_u64::<BigEndian>()?;
-                    let request_lsn = Lsn(buf.read_u64::<BigEndian>()?);
-                    let not_modified_since = Lsn(buf.read_u64::<BigEndian>()?);
-                    let kind = buf.read_u8()?;
-                    let segno = buf.read_u32::<BigEndian>()?;
                     let n_blocks = buf.read_u32::<BigEndian>()?;
                     let mut segment = vec![0; n_blocks as usize * BLCKSZ as usize];
                     buf.read_exact(&mut segment)?;
                     Self::GetSlruSegment(PagestreamGetSlruSegmentResponse {
-                        req: PagestreamGetSlruSegmentRequest {
-                            hdr: PagestreamRequest {
-                                reqid,
-                                request_lsn,
-                                not_modified_since,
-                            },
-                            kind,
-                            segno,
-                        },
                         segment: segment.into(),
                     })
                 }
@@ -1991,11 +1498,8 @@ mod tests {
         // Test serialization/deserialization of PagestreamFeMessage
         let messages = vec![
             PagestreamFeMessage::Exists(PagestreamExistsRequest {
-                hdr: PagestreamRequest {
+                request_lsn: Lsn(4),
-                    reqid: 0,
+                not_modified_since: Lsn(3),
-                    request_lsn: Lsn(4),
-                    not_modified_since: Lsn(3),
-                },
                 rel: RelTag {
                     forknum: 1,
                     spcnode: 2,
@@ -2004,11 +1508,8 @@ mod tests {
                 },
             }),
             PagestreamFeMessage::Nblocks(PagestreamNblocksRequest {
-                hdr: PagestreamRequest {
+                request_lsn: Lsn(4),
-                    reqid: 0,
+                not_modified_since: Lsn(4),
-                    request_lsn: Lsn(4),
-                    not_modified_since: Lsn(4),
-                },
                 rel: RelTag {
                     forknum: 1,
                     spcnode: 2,
@@ -2017,11 +1518,8 @@ mod tests {
                 },
             }),
             PagestreamFeMessage::GetPage(PagestreamGetPageRequest {
-                hdr: PagestreamRequest {
+                request_lsn: Lsn(4),
-                    reqid: 0,
+                not_modified_since: Lsn(3),
-                    request_lsn: Lsn(4),
-                    not_modified_since: Lsn(3),
-                },
                 rel: RelTag {
                     forknum: 1,
                     spcnode: 2,
@@ -2031,19 +1529,14 @@ mod tests {
                 blkno: 7,
             }),
             PagestreamFeMessage::DbSize(PagestreamDbSizeRequest {
-                hdr: PagestreamRequest {
+                request_lsn: Lsn(4),
-                    reqid: 0,
+                not_modified_since: Lsn(3),
-                    request_lsn: Lsn(4),
-                    not_modified_since: Lsn(3),
-                },
                 dbnode: 7,
             }),
         ];
         for msg in messages {
             let bytes = msg.serialize();
-            let reconstructed =
+            let reconstructed = PagestreamFeMessage::parse(&mut bytes.reader()).unwrap();
-                PagestreamFeMessage::parse(&mut bytes.reader(), PagestreamProtocolVersion::V3)
-                    .unwrap();
             assert!(msg == reconstructed);
         }
     }
@@ -2206,45 +1699,4 @@ mod tests {
             );
         }
     }
-
-    #[test]
-    fn test_tenant_config_patch_request_serde() {
-        let patch_request = TenantConfigPatchRequest {
-            tenant_id: TenantId::from_str("17c6d121946a61e5ab0fe5a2fd4d8215").unwrap(),
-            config: TenantConfigPatch {
-                checkpoint_distance: FieldPatch::Upsert(42),
-                gc_horizon: FieldPatch::Remove,
-                compaction_threshold: FieldPatch::Noop,
-                ..TenantConfigPatch::default()
-            },
-        };
-
-        let json = serde_json::to_string(&patch_request).unwrap();
-
-        let expected = r#"{"tenant_id":"17c6d121946a61e5ab0fe5a2fd4d8215","checkpoint_distance":42,"gc_horizon":null}"#;
-        assert_eq!(json, expected);
-
-        let decoded: TenantConfigPatchRequest = serde_json::from_str(&json).unwrap();
-        assert_eq!(decoded.tenant_id, patch_request.tenant_id);
-        assert_eq!(decoded.config, patch_request.config);
-
-        // Now apply the patch to a config to demonstrate semantics
-
-        let base = TenantConfig {
-            checkpoint_distance: Some(28),
-            gc_horizon: Some(100),
-            compaction_target_size: Some(1024),
-            ..Default::default()
-        };
-
-        let expected = TenantConfig {
-            checkpoint_distance: Some(42),
-            gc_horizon: None,
-            ..base.clone()
-        };
-
-        let patched = base.apply_patch(decoded.config);
-
-        assert_eq!(patched, expected);
-    }
 }

libs/pageserver_api/src/shard.rs

@@ -173,11 +173,7 @@ impl ShardIdentity {
 
     /// Return true if the key should be stored on all shards, not just one.
     pub fn is_key_global(&self, key: &Key) -> bool {
-        if key.is_slru_block_key()
+        if key.is_slru_block_key() || key.is_slru_segment_size_key() || key.is_aux_file_key() {
-            || key.is_slru_segment_size_key()
-            || key.is_aux_file_key()
-            || key.is_slru_dir_key()
-        {
             // Special keys that are only stored on shard 0
             false
         } else if key.is_rel_block_key() {