Merge pull request #10288 from neondatabase/rc/release-compute/2025-01-07

Compute release 2025-01-07
2026-01-16 18:02:56 +00:00 · 2025-01-08 14:10:28 +02:00
parent 671889b0e9 31bd2dcdb4
commit 441517dd7c
249 changed files with 4288 additions and 2249 deletions
--- a/.cargo/config.toml
+++ b/.cargo/config.toml
@@ -3,6 +3,16 @@
 # 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"]
--- a/.github/actions/allure-report-generate/action.yml
+++ b/.github/actions/allure-report-generate/action.yml
@@ -7,10 +7,9 @@ inputs:
    type: boolean
    required: false
    default: false
-  aws_oicd_role_arn:
-    description: 'the OIDC role arn to (re-)acquire for allure report upload - if not set call must acquire OIDC role'
-    required: false
-    default: ''
+  aws-oicd-role-arn:
+    description: 'OIDC role arn to interract with S3'
+    required: true

 outputs:
  base-url:
@@ -84,12 +83,11 @@ runs:
        ALLURE_VERSION: 2.27.0
        ALLURE_ZIP_SHA256: b071858fb2fa542c65d8f152c5c40d26267b2dfb74df1f1608a589ecca38e777

-    - name: (Re-)configure AWS credentials # necessary to upload reports to S3 after a long-running test
-      if: ${{ !cancelled() && (inputs.aws_oicd_role_arn != '') }}
-      uses: aws-actions/configure-aws-credentials@v4
+    - uses: aws-actions/configure-aws-credentials@v4
+      if: ${{ !cancelled() }}
      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
--- a/.github/actions/allure-report-store/action.yml
+++ b/.github/actions/allure-report-store/action.yml
@@ -8,10 +8,9 @@ inputs:
  unique-key:
    description: 'string to distinguish different results in the same run'
    required: true
-  aws_oicd_role_arn:
-    description: 'the OIDC role arn to (re-)acquire for allure report upload - if not set call must acquire OIDC role'
-    required: false
-    default: ''
+  aws-oicd-role-arn:
+    description: 'OIDC role arn to interract with S3'
+    required: true

 runs:
  using: "composite"
@@ -36,12 +35,11 @@ runs:
      env:
        REPORT_DIR: ${{ inputs.report-dir }}

-    - name: (Re-)configure AWS credentials # necessary to upload reports to S3 after a long-running test
-      if: ${{ !cancelled() && (inputs.aws_oicd_role_arn != '') }}
-      uses: aws-actions/configure-aws-credentials@v4
+    - uses: aws-actions/configure-aws-credentials@v4
+      if: ${{ !cancelled() }}
      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
--- a/.github/actions/download/action.yml
+++ b/.github/actions/download/action.yml
@@ -15,19 +15,17 @@ inputs:
  prefix:
    description: "S3 prefix. Default is '${GITHUB_RUN_ID}/${GITHUB_RUN_ATTEMPT}'"
    required: false
-  aws_oicd_role_arn:
-    description: "the OIDC role arn for aws auth"
-    required: false
-    default: ""
+  aws-oicd-role-arn:
+    description: 'OIDC role arn to interract with S3'
+    required: true

 runs:
  using: "composite"
  steps:
-    - name: Configure AWS credentials
-      uses: aws-actions/configure-aws-credentials@v4
+    - 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

    - name: Download artifact
--- a/.github/actions/run-python-test-set/action.yml
+++ b/.github/actions/run-python-test-set/action.yml
@@ -48,10 +48,9 @@ inputs:
    description: 'benchmark durations JSON'
    required: false
    default: '{}'
-  aws_oicd_role_arn:
-    description: 'the OIDC role arn to (re-)acquire for allure report upload - if not set call must acquire OIDC role'
-    required: false
-    default: ''
+  aws-oicd-role-arn:
+    description: 'OIDC role arn to interract with S3'
+    required: true

 runs:
  using: "composite"
@@ -62,7 +61,7 @@ runs:
      with:
        name: neon-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build_type }}-artifact
        path: /tmp/neon
-        aws_oicd_role_arn: ${{ inputs.aws_oicd_role_arn }}
+        aws-oicd-role-arn: ${{ inputs.aws-oicd-role-arn }}

    - name: Download Neon binaries for the previous release
      if: inputs.build_type != 'remote'
@@ -71,7 +70,7 @@ 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 }}
+        aws-oicd-role-arn: ${{ inputs.aws-oicd-role-arn }}

    - name: Download compatibility snapshot
      if: inputs.build_type != 'remote'
@@ -83,7 +82,7 @@ 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 }}
+        aws-oicd-role-arn: ${{ inputs.aws-oicd-role-arn }}

    - name: Checkout
      if: inputs.needs_postgres_source == 'true'
@@ -221,19 +220,19 @@ 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 }}
+        aws-oicd-role-arn: ${{ inputs.aws-oicd-role-arn }}

-    - name: (Re-)configure AWS credentials # necessary to upload reports to S3 after a long-running test
-      if: ${{ !cancelled() && (inputs.aws_oicd_role_arn != '') }}
-      uses: aws-actions/configure-aws-credentials@v4
+    - uses: aws-actions/configure-aws-credentials@v4
+      if: ${{ !cancelled() }}
      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 }}
+        aws-oicd-role-arn: ${{ inputs.aws-oicd-role-arn }}
--- a/.github/actions/save-coverage-data/action.yml
+++ b/.github/actions/save-coverage-data/action.yml
@@ -14,11 +14,11 @@ 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 }}
+        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 }}
+        aws-oicd-role-arn: ${{ inputs.aws-oicd-role-arn }}
--- a/.github/actions/upload/action.yml
+++ b/.github/actions/upload/action.yml
@@ -14,7 +14,7 @@ inputs:
  prefix:
    description: "S3 prefix. Default is '${GITHUB_SHA}/${GITHUB_RUN_ID}/${GITHUB_RUN_ATTEMPT}'"
    required: false
-  aws_oicd_role_arn:
+  aws-oicd-role-arn:
    description: "the OIDC role arn for aws auth"
    required: false
    default: ""
@@ -61,7 +61,7 @@ runs:
      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

    - name: Upload artifact
--- a/.github/workflows/_benchmarking_preparation.yml
+++ b/.github/workflows/_benchmarking_preparation.yml
@@ -70,7 +70,7 @@ jobs:
        name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
        path: /tmp/neon/
        prefix: latest
-        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        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
--- a/.github/workflows/_build-and-test-locally.yml
+++ b/.github/workflows/_build-and-test-locally.yml
@@ -264,7 +264,7 @@ 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 }}
+          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
@@ -308,7 +308,7 @@ 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 }}
+          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
--- a/.github/workflows/actionlint.yml
+++ b/.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_on_error: true
+          fail_level: error
          filter_mode: nofilter
          level: error

--- a/.github/workflows/benchmarking.yml
+++ b/.github/workflows/benchmarking.yml
@@ -105,7 +105,7 @@ jobs:
        name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
        path: /tmp/neon/
        prefix: latest
-        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}

    - name: Create Neon Project
      id: create-neon-project
@@ -123,7 +123,7 @@ 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 +153,7 @@ 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: ${{ github.event.schedule && failure() }}
@@ -205,7 +205,7 @@ jobs:
        name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
        path: /tmp/neon/
        prefix: latest
-        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}

    - name: Run Logical Replication benchmarks
      uses: ./.github/actions/run-python-test-set
@@ -216,7 +216,7 @@ 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 +233,7 @@ 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 +245,7 @@ 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 }}

@@ -308,6 +308,7 @@ 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": '"$runner_azure"',   "image": "neondatabase/build-tools:pinned-bookworm" },
@@ -407,10 +408,10 @@ jobs:
        name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
        path: /tmp/neon/
        prefix: latest
-        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}

    - name: Create Neon Project
-      if: contains(fromJson('["neonvm-captest-new", "neonvm-captest-freetier", "neonvm-azure-captest-freetier", "neonvm-azure-captest-new"]'), matrix.platform)
+      if: contains(fromJson('["neonvm-captest-new", "neonvm-captest-new-many-tables", "neonvm-captest-freetier", "neonvm-azure-captest-freetier", "neonvm-azure-captest-new"]'), matrix.platform)
      id: create-neon-project
      uses: ./.github/actions/neon-project-create
      with:
@@ -429,7 +430,7 @@ jobs:
          neonvm-captest-sharding-reuse)
            CONNSTR=${{ secrets.BENCHMARK_CAPTEST_SHARDING_CONNSTR }}
            ;;
-          neonvm-captest-new | neonvm-captest-freetier | neonvm-azure-captest-new | neonvm-azure-captest-freetier)
+          neonvm-captest-new | neonvm-captest-new-many-tables | neonvm-captest-freetier | neonvm-azure-captest-new | neonvm-azure-captest-freetier)
            CONNSTR=${{ steps.create-neon-project.outputs.dsn }}
            ;;
          rds-aurora)
@@ -446,6 +447,26 @@ 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:
@@ -455,7 +476,7 @@ 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 }}"
@@ -470,7 +491,7 @@ 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 }}"
@@ -485,7 +506,7 @@ 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 }}"
@@ -503,7 +524,7 @@ 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() }}
@@ -614,7 +635,7 @@ 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 }}"
@@ -629,7 +650,7 @@ 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 }}"
@@ -640,7 +661,7 @@ 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: ${{ github.event.schedule && failure() }}
@@ -711,7 +732,7 @@ jobs:
        name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
        path: /tmp/neon/
        prefix: latest
-        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}

    - name: Set up Connection String
      id: set-up-connstr
@@ -743,7 +764,7 @@ 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 }}"
@@ -757,7 +778,7 @@ 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: ${{ github.event.schedule && failure() }}
@@ -822,7 +843,7 @@ jobs:
        name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
        path: /tmp/neon/
        prefix: latest
-        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}

    - name: Get Connstring Secret Name
      run: |
@@ -861,7 +882,7 @@ 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 }}"
@@ -873,7 +894,7 @@ 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: ${{ github.event.schedule && failure() }}
@@ -931,7 +952,7 @@ jobs:
        name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
        path: /tmp/neon/
        prefix: latest
-        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}

    - name: Set up Connection String
      id: set-up-connstr
@@ -963,7 +984,7 @@ 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 }}"
@@ -974,7 +995,7 @@ 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: ${{ github.event.schedule && failure() }}
--- a/.github/workflows/build_and_test.yml
+++ b/.github/workflows/build_and_test.yml
@@ -212,7 +212,7 @@ jobs:
          fi
          echo "CLIPPY_COMMON_ARGS=${CLIPPY_COMMON_ARGS}" >> $GITHUB_ENV
      - name: Run cargo clippy (debug)
-        run: cargo hack --feature-powerset clippy $CLIPPY_COMMON_ARGS
+        run: cargo hack --features default --ignore-unknown-features --feature-powerset clippy $CLIPPY_COMMON_ARGS

      - name: Check documentation generation
        run: cargo doc --workspace --no-deps --document-private-items
@@ -303,6 +303,11 @@ 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
@@ -331,6 +336,7 @@ 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 }}"
@@ -343,6 +349,11 @@ 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:
@@ -383,7 +394,7 @@ 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 }}

@@ -445,14 +456,14 @@ 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 }}
+          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 }}
+          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
@@ -527,7 +538,7 @@ jobs:

  trigger-e2e-tests:
    if: ${{ !github.event.pull_request.draft || contains( github.event.pull_request.labels.*.name, 'run-e2e-tests-in-draft') || github.ref_name == 'main' || github.ref_name == 'release' || github.ref_name == 'release-proxy' || github.ref_name == 'release-compute' }}
-    needs: [ check-permissions, promote-images, tag ]
+    needs: [ check-permissions, promote-images-dev, tag ]
    uses: ./.github/workflows/trigger-e2e-tests.yml
    secrets: inherit

@@ -919,8 +930,8 @@ jobs:
          docker compose -f ./docker-compose/docker-compose.yml logs || 0
          docker compose -f ./docker-compose/docker-compose.yml down

-  promote-images:
-    needs: [ check-permissions, tag, test-images, vm-compute-node-image ]
+  promote-images-dev:
+    needs: [ check-permissions, tag, vm-compute-node-image ]
    runs-on: ubuntu-22.04

    permissions:
@@ -954,6 +965,35 @@ 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: |
@@ -999,7 +1039,7 @@ jobs:

  push-to-acr-dev:
    if: github.ref_name == 'main'
-    needs: [ tag, promote-images ]
+    needs: [ tag, promote-images-dev ]
    uses: ./.github/workflows/_push-to-acr.yml
    with:
      client_id: ${{ vars.AZURE_DEV_CLIENT_ID }}
@@ -1011,7 +1051,7 @@ jobs:

  push-to-acr-prod:
    if: github.ref_name == 'release' || github.ref_name == 'release-proxy' || github.ref_name == 'release-compute'
-    needs: [ tag, promote-images ]
+    needs: [ tag, promote-images-prod ]
    uses: ./.github/workflows/_push-to-acr.yml
    with:
      client_id: ${{ vars.AZURE_PROD_CLIENT_ID }}
@@ -1024,6 +1064,11 @@ 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: |
@@ -1096,7 +1141,7 @@ jobs:
          exit 1

  deploy:
-    needs: [ check-permissions, promote-images, tag, build-and-test-locally, trigger-custom-extensions-build-and-wait, push-to-acr-dev, push-to-acr-prod ]
+    needs: [ check-permissions, promote-images-prod, tag, build-and-test-locally, trigger-custom-extensions-build-and-wait, push-to-acr-dev, push-to-acr-prod ]
    # `!failure() && !cancelled()` is required because the workflow depends on the job that can be skipped: `push-to-acr-dev` and `push-to-acr-prod`
    if: (github.ref_name == 'main' || github.ref_name == 'release' || github.ref_name == 'release-proxy' || github.ref_name == 'release-compute') && !failure() && !cancelled()
    permissions:
@@ -1264,6 +1309,12 @@ 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
@@ -1311,7 +1362,7 @@ jobs:
          done

  pin-build-tools-image:
-    needs: [ build-build-tools-image, promote-images, build-and-test-locally ]
+    needs: [ build-build-tools-image, promote-images-prod, build-and-test-locally ]
    if: github.ref_name == 'main'
    uses: ./.github/workflows/pin-build-tools-image.yml
    with:
@@ -1334,7 +1385,7 @@ jobs:
      - build-and-test-locally
      - check-codestyle-python
      - check-codestyle-rust
-      - promote-images
+      - promote-images-dev
      - test-images
      - trigger-custom-extensions-build-and-wait
    runs-on: ubuntu-22.04
--- a/.github/workflows/cloud-regress.yml
+++ b/.github/workflows/cloud-regress.yml
@@ -21,6 +21,8 @@ concurrency:

 permissions:
  id-token: write # aws-actions/configure-aws-credentials
+  statuses: write
+  contents: write

 jobs:
  regress:
@@ -79,7 +81,7 @@ jobs:
          name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
          path: /tmp/neon/
          prefix: latest
-          aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+          aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}

      - name: Create a new branch
        id: create-branch
@@ -95,10 +97,12 @@ jobs:
          test_selection: cloud_regress
          pg_version: ${{matrix.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}}

      - name: Delete branch
+        if: always()
        uses: ./.github/actions/neon-branch-delete
        with:
          api_key: ${{ secrets.NEON_STAGING_API_KEY }}
@@ -110,7 +114,7 @@ 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() }}
--- a/.github/workflows/ingest_benchmark.yml
+++ b/.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 +64,7 @@ jobs:
        name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
        path: /tmp/neon/
        prefix: latest
-        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}

    - name: Create Neon Project
      if: ${{ matrix.target_project == 'new_empty_project' }}
@@ -95,7 +95,7 @@ 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 +123,7 @@ 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 +132,7 @@ 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: ${{ matrix.target_project }}
@@ -144,7 +144,7 @@ jobs:
      run: |
        export LD_LIBRARY_PATH=${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
--- a/.github/workflows/periodic_pagebench.yml
+++ b/.github/workflows/periodic_pagebench.yml
@@ -21,15 +21,17 @@ defaults:
  run:
    shell: bash -euo pipefail {0}

-permissions:
-  id-token: write # aws-actions/configure-aws-credentials
-
 concurrency:
  group: ${{ github.workflow }}
  cancel-in-progress: false

 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
@@ -135,7 +137,7 @@ 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: ${{ github.event.schedule && failure() }}
--- a/.github/workflows/pg-clients.yml
+++ b/.github/workflows/pg-clients.yml
@@ -96,7 +96,7 @@ jobs:
          name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
          path: /tmp/neon/
          prefix: latest
-          aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+          aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}

      - name: Create Neon Project
        id: create-neon-project
@@ -113,6 +113,7 @@ 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 }}

@@ -129,7 +130,7 @@ 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 }}

@@ -163,7 +164,7 @@ jobs:
        name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
        path: /tmp/neon/
        prefix: latest
-        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}

    - name: Create Neon Project
      id: create-neon-project
@@ -180,6 +181,7 @@ 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 }}

@@ -196,7 +198,7 @@ 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 }}

--- a/.github/workflows/trigger-e2e-tests.yml
+++ b/.github/workflows/trigger-e2e-tests.yml
@@ -68,7 +68,7 @@ jobs:
      GH_TOKEN: ${{ secrets.CI_ACCESS_TOKEN }}
      TAG: ${{ needs.tag.outputs.build-tag }}
    steps:
-      - name: Wait for `promote-images` job to finish
+      - name: Wait for `promote-images-dev` job to finish
        # It's important to have a timeout here, the script in the step can run infinitely
        timeout-minutes: 60
        run: |
@@ -79,17 +79,17 @@ jobs:
          # For PRs we use the run id as the tag
          BUILD_AND_TEST_RUN_ID=${TAG}
          while true; do
-            conclusion=$(gh run --repo ${GITHUB_REPOSITORY} view ${BUILD_AND_TEST_RUN_ID} --json jobs --jq '.jobs[] | select(.name == "promote-images") | .conclusion')
+            conclusion=$(gh run --repo ${GITHUB_REPOSITORY} view ${BUILD_AND_TEST_RUN_ID} --json jobs --jq '.jobs[] | select(.name == "promote-images-dev") | .conclusion')
            case "$conclusion" in
              success)
                break
                ;;
              failure | cancelled | skipped)
-                echo "The 'promote-images' job didn't succeed: '${conclusion}'. Exiting..."
+                echo "The 'promote-images-dev' job didn't succeed: '${conclusion}'. Exiting..."
                exit 1
                ;;
              *)
-                echo "The 'promote-images' hasn't succeed yet. Waiting..."
+                echo "The 'promote-images-dev' hasn't succeed yet. Waiting..."
                sleep 60
                ;;
            esac
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -10,9 +10,9 @@ checksum = "8b5ace29ee3216de37c0546865ad08edef58b0f9e76838ed8959a84a990e58c5"

 [[package]]
 name = "addr2line"
-version = "0.21.0"
+version = "0.24.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8a30b2e23b9e17a9f90641c7ab1549cd9b44f296d3ccbf309d2863cfe398a0cb"
+checksum = "dfbe277e56a376000877090da837660b4427aad530e3028d44e0bffe4f89a1c1"
 dependencies = [
 "gimli",
 ]
@@ -23,6 +23,12 @@ version = "1.0.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f26201604c87b1e01bd3d98f8d5d9a8fcbb815e8cedb41ffccbeb4bf593a35fe"

+[[package]]
+name = "adler2"
+version = "2.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "512761e0bb2578dd7380c6baaa0f4ce03e84f95e960231d1dec8bf4d7d6e2627"
+
 [[package]]
 name = "ahash"
 version = "0.8.11"
@@ -871,17 +877,17 @@ dependencies = [

 [[package]]
 name = "backtrace"
-version = "0.3.69"
+version = "0.3.74"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2089b7e3f35b9dd2d0ed921ead4f6d318c27680d4a5bd167b3ee120edb105837"
+checksum = "8d82cb332cdfaed17ae235a638438ac4d4839913cc2af585c3c6746e8f8bee1a"
 dependencies = [
 "addr2line",
- "cc",
 "cfg-if",
 "libc",
- "miniz_oxide",
+ "miniz_oxide 0.8.0",
 "object",
 "rustc-demangle",
+ "windows-targets 0.52.6",
 ]

 [[package]]
@@ -1127,7 +1133,7 @@ dependencies = [
 "num-traits",
 "serde",
 "wasm-bindgen",
- "windows-targets 0.52.4",
+ "windows-targets 0.52.6",
 ]

 [[package]]
@@ -1268,6 +1274,7 @@ dependencies = [
 "chrono",
 "clap",
 "compute_api",
+ "fail",
 "flate2",
 "futures",
 "hyper 0.14.30",
@@ -1726,9 +1733,9 @@ checksum = "ab03c107fafeb3ee9f5925686dbb7a73bc76e3932abb0d2b365cb64b169cf04c"

 [[package]]
 name = "diesel"
-version = "2.2.3"
+version = "2.2.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "65e13bab2796f412722112327f3e575601a3e9cdcbe426f0d30dbf43f3f5dc71"
+checksum = "ccf1bedf64cdb9643204a36dd15b19a6ce8e7aa7f7b105868e9f1fad5ffa7d12"
 dependencies = [
 "bitflags 2.4.1",
 "byteorder",
@@ -2107,7 +2114,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "3b9429470923de8e8cbd4d2dc513535400b4b3fef0319fb5c4e1f520a7bef743"
 dependencies = [
 "crc32fast",
- "miniz_oxide",
+ "miniz_oxide 0.7.1",
 ]

 [[package]]
@@ -2308,9 +2315,9 @@ dependencies = [

 [[package]]
 name = "gimli"
-version = "0.28.1"
+version = "0.31.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4271d37baee1b8c7e4b708028c57d816cf9d2434acb33a549475f78c181f6253"
+checksum = "07e28edb80900c19c28f1072f2e8aeca7fa06b23cd4169cefe1af5aa3260783f"

 [[package]]
 name = "git-version"
@@ -3404,6 +3411,15 @@ dependencies = [
 "adler",
 ]

+[[package]]
+name = "miniz_oxide"
+version = "0.8.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e2d80299ef12ff69b16a84bb182e3b9df68b5a91574d3d4fa6e41b65deec4df1"
+dependencies = [
+ "adler2",
+]
+
 [[package]]
 name = "mio"
 version = "0.8.11"
@@ -3638,9 +3654,9 @@ dependencies = [

 [[package]]
 name = "object"
-version = "0.32.2"
+version = "0.36.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a6a622008b6e321afc04970976f62ee297fdbaa6f95318ca343e3eebb9648441"
+checksum = "aedf0a2d09c573ed1d8d85b30c119153926a2b36dce0ab28322c09a117a4683e"
 dependencies = [
 "memchr",
 ]
@@ -4401,11 +4417,13 @@ dependencies = [
 "bindgen",
 "bytes",
 "crc32c",
+ "criterion",
 "env_logger",
 "log",
 "memoffset 0.9.0",
 "once_cell",
 "postgres",
+ "pprof",
 "regex",
 "serde",
 "thiserror",
@@ -4476,9 +4494,9 @@ checksum = "5b40af805b3121feab8a3c29f04d8ad262fa8e0561883e7653e024ae4479e6de"

 [[package]]
 name = "pq-sys"
-version = "0.4.8"
+version = "0.6.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "31c0052426df997c0cbd30789eb44ca097e3541717a7b8fa36b1c464ee7edebd"
+checksum = "f6cc05d7ea95200187117196eee9edd0644424911821aeb28a18ce60ea0b8793"
 dependencies = [
 "vcpkg",
 ]
@@ -5062,6 +5080,7 @@ dependencies = [
 "once_cell",
 "pin-project-lite",
 "rand 0.8.5",
+ "reqwest",
 "scopeguard",
 "serde",
 "serde_json",
@@ -5320,9 +5339,9 @@ dependencies = [

 [[package]]
 name = "rustc-demangle"
-version = "0.1.23"
+version = "0.1.24"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d626bb9dae77e28219937af045c257c28bfd3f69333c512553507f5f9798cb76"
+checksum = "719b953e2095829ee67db738b3bfa9fa368c94900df327b3f07fe6e794d2fe1f"

 [[package]]
 name = "rustc-hash"
@@ -5535,6 +5554,7 @@ dependencies = [
 "remote_storage",
 "reqwest",
 "safekeeper_api",
+ "safekeeper_client",
 "scopeguard",
 "sd-notify",
 "serde",
@@ -5565,10 +5585,25 @@ name = "safekeeper_api"
 version = "0.1.0"
 dependencies = [
 "const_format",
+ "postgres_ffi",
+ "pq_proto",
 "serde",
+ "tokio",
 "utils",
 ]

+[[package]]
+name = "safekeeper_client"
+version = "0.1.0"
+dependencies = [
+ "reqwest",
+ "safekeeper_api",
+ "serde",
+ "thiserror",
+ "utils",
+ "workspace_hack",
+]
+
 [[package]]
 name = "same-file"
 version = "1.0.6"
@@ -7200,6 +7235,7 @@ dependencies = [
 "anyhow",
 "arc-swap",
 "async-compression",
+ "backtrace",
 "bincode",
 "byteorder",
 "bytes",
@@ -7210,12 +7246,14 @@ dependencies = [
 "criterion",
 "diatomic-waker",
 "fail",
+ "flate2",
 "futures",
 "git-version",
 "hex",
 "hex-literal",
 "humantime",
 "hyper 0.14.30",
+ "itertools 0.10.5",
 "jemalloc_pprof",
 "jsonwebtoken",
 "metrics",
@@ -7572,7 +7610,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e48a53791691ab099e5e2ad123536d0fff50652600abaf43bbf952894110d0be"
 dependencies = [
 "windows-core",
- "windows-targets 0.52.4",
+ "windows-targets 0.52.6",
 ]

 [[package]]
@@ -7581,7 +7619,7 @@ version = "0.52.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "33ab640c8d7e35bf8ba19b884ba838ceb4fba93a4e8c65a9059d08afcfc683d9"
 dependencies = [
- "windows-targets 0.52.4",
+ "windows-targets 0.52.6",
 ]

 [[package]]
@@ -7599,7 +7637,7 @@ version = "0.52.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "282be5f36a8ce781fad8c8ae18fa3f9beff57ec1b52cb3de0789201425d9a33d"
 dependencies = [
- "windows-targets 0.52.4",
+ "windows-targets 0.52.6",
 ]

 [[package]]
@@ -7619,17 +7657,18 @@ dependencies = [

 [[package]]
 name = "windows-targets"
-version = "0.52.4"
+version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7dd37b7e5ab9018759f893a1952c9420d060016fc19a472b4bb20d1bdd694d1b"
+checksum = "9b724f72796e036ab90c1021d4780d4d3d648aca59e491e6b98e725b84e99973"
 dependencies = [
- "windows_aarch64_gnullvm 0.52.4",
- "windows_aarch64_msvc 0.52.4",
- "windows_i686_gnu 0.52.4",
- "windows_i686_msvc 0.52.4",
- "windows_x86_64_gnu 0.52.4",
- "windows_x86_64_gnullvm 0.52.4",
- "windows_x86_64_msvc 0.52.4",
+ "windows_aarch64_gnullvm 0.52.6",
+ "windows_aarch64_msvc 0.52.6",
+ "windows_i686_gnu 0.52.6",
+ "windows_i686_gnullvm",
+ "windows_i686_msvc 0.52.6",
+ "windows_x86_64_gnu 0.52.6",
+ "windows_x86_64_gnullvm 0.52.6",
+ "windows_x86_64_msvc 0.52.6",
 ]

 [[package]]
@@ -7640,9 +7679,9 @@ checksum = "91ae572e1b79dba883e0d315474df7305d12f569b400fcf90581b06062f7e1bc"

 [[package]]
 name = "windows_aarch64_gnullvm"
-version = "0.52.4"
+version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bcf46cf4c365c6f2d1cc93ce535f2c8b244591df96ceee75d8e83deb70a9cac9"
+checksum = "32a4622180e7a0ec044bb555404c800bc9fd9ec262ec147edd5989ccd0c02cd3"

 [[package]]
 name = "windows_aarch64_msvc"
@@ -7652,9 +7691,9 @@ checksum = "b2ef27e0d7bdfcfc7b868b317c1d32c641a6fe4629c171b8928c7b08d98d7cf3"

 [[package]]
 name = "windows_aarch64_msvc"
-version = "0.52.4"
+version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "da9f259dd3bcf6990b55bffd094c4f7235817ba4ceebde8e6d11cd0c5633b675"
+checksum = "09ec2a7bb152e2252b53fa7803150007879548bc709c039df7627cabbd05d469"

 [[package]]
 name = "windows_i686_gnu"
@@ -7664,9 +7703,15 @@ checksum = "622a1962a7db830d6fd0a69683c80a18fda201879f0f447f065a3b7467daa241"

 [[package]]
 name = "windows_i686_gnu"
-version = "0.52.4"
+version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b474d8268f99e0995f25b9f095bc7434632601028cf86590aea5c8a5cb7801d3"
+checksum = "8e9b5ad5ab802e97eb8e295ac6720e509ee4c243f69d781394014ebfe8bbfa0b"
+
+[[package]]
+name = "windows_i686_gnullvm"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0eee52d38c090b3caa76c563b86c3a4bd71ef1a819287c19d586d7334ae8ed66"

 [[package]]
 name = "windows_i686_msvc"
@@ -7676,9 +7721,9 @@ checksum = "4542c6e364ce21bf45d69fdd2a8e455fa38d316158cfd43b3ac1c5b1b19f8e00"

 [[package]]
 name = "windows_i686_msvc"
-version = "0.52.4"
+version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1515e9a29e5bed743cb4415a9ecf5dfca648ce85ee42e15873c3cd8610ff8e02"
+checksum = "240948bc05c5e7c6dabba28bf89d89ffce3e303022809e73deaefe4f6ec56c66"

 [[package]]
 name = "windows_x86_64_gnu"
@@ -7688,9 +7733,9 @@ checksum = "ca2b8a661f7628cbd23440e50b05d705db3686f894fc9580820623656af974b1"

 [[package]]
 name = "windows_x86_64_gnu"
-version = "0.52.4"
+version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5eee091590e89cc02ad514ffe3ead9eb6b660aedca2183455434b93546371a03"
+checksum = "147a5c80aabfbf0c7d901cb5895d1de30ef2907eb21fbbab29ca94c5b08b1a78"

 [[package]]
 name = "windows_x86_64_gnullvm"
@@ -7700,9 +7745,9 @@ checksum = "7896dbc1f41e08872e9d5e8f8baa8fdd2677f29468c4e156210174edc7f7b953"

 [[package]]
 name = "windows_x86_64_gnullvm"
-version = "0.52.4"
+version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "77ca79f2451b49fa9e2af39f0747fe999fcda4f5e241b2898624dca97a1f2177"
+checksum = "24d5b23dc417412679681396f2b49f3de8c1473deb516bd34410872eff51ed0d"

 [[package]]
 name = "windows_x86_64_msvc"
@@ -7712,9 +7757,9 @@ checksum = "1a515f5799fe4961cb532f983ce2b23082366b898e52ffbce459c86f67c8378a"

 [[package]]
 name = "windows_x86_64_msvc"
-version = "0.52.4"
+version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "32b752e52a2da0ddfbdbcc6fceadfeede4c939ed16d13e648833a61dfb611ed8"
+checksum = "589f6da84c646204747d1270a2a5661ea66ed1cced2631d546fdfb155959f9ec"

 [[package]]
 name = "winnow"
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -11,6 +11,7 @@ members = [
    "pageserver/pagebench",
    "proxy",
    "safekeeper",
+    "safekeeper/client",
    "storage_broker",
    "storage_controller",
    "storage_controller/client",
@@ -51,6 +52,7 @@ 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"
 flate2 = "1.0.26"
 async-stream = "0.3"
 async-trait = "0.1"
@@ -133,7 +135,7 @@ 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", "protobuf", "protobuf-codec"] }
+pprof = { version = "0.14", features = ["criterion", "flamegraph", "frame-pointer", "protobuf", "protobuf-codec"] }
 procfs = "0.16"
 prometheus = {version = "0.13", default-features=false, features = ["process"]} # removes protobuf dependency
 prost = "0.13"
@@ -233,6 +235,7 @@ 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" }
@@ -263,6 +266,8 @@ 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
--- a/4
+++ b/4
@@ -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 ${ADDITIONAL_RUSTFLAGS}" cargo build \
+    && PQ_LIB_DIR=$(pwd)/pg_install/v${STABLE_PG_VERSION}/lib RUSTFLAGS="-Clinker=clang -Clink-arg=-fuse-ld=mold -Clink-arg=-Wl,--no-rosegment -Cforce-frame-pointers=yes ${ADDITIONAL_RUSTFLAGS}" cargo build \
      --bin pg_sni_router  \
      --bin pageserver  \
      --bin pagectl  \
@@ -69,6 +69,8 @@ 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
--- a/compute/compute-node.Dockerfile
+++ b/compute/compute-node.Dockerfile
@@ -35,10 +35,12 @@ RUN case $DEBIAN_VERSION in \
      ;; \
    esac && \
    apt update &&  \
-    apt install --no-install-recommends -y git autoconf automake libtool build-essential bison flex libreadline-dev \
+    apt install --no-install-recommends --no-install-suggests -y \
+    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/*

 #########################################################################################
 #
@@ -113,10 +115,12 @@ ARG DEBIAN_VERSION
 ARG PG_VERSION
 COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
 RUN apt update && \
-    apt install --no-install-recommends -y gdal-bin libboost-dev libboost-thread-dev libboost-filesystem-dev \
+    apt install --no-install-recommends --no-install-suggests -y \
+    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+
@@ -143,9 +147,9 @@ 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 . && make -j $(getconf _NPROCESSORS_ONLN) && \
-    DESTDIR=/sfcgal make install -j $(getconf _NPROCESSORS_ONLN) && \
-    make clean && cp -R /sfcgal/* /
+    cmake -DCMAKE_BUILD_TYPE=Release -GNinja . && ninja -j $(getconf _NPROCESSORS_ONLN) && \
+    DESTDIR=/sfcgal ninja install -j $(getconf _NPROCESSORS_ONLN) && \
+    ninja clean && cp -R /sfcgal/* /

 ENV PATH="/usr/local/pgsql/bin:$PATH"

@@ -213,9 +217,9 @@ 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 -DCMAKE_BUILD_TYPE=Release .. && \
-    make -j $(getconf _NPROCESSORS_ONLN) && \
-    make -j $(getconf _NPROCESSORS_ONLN) install && \
+    cmake -GNinja -DCMAKE_BUILD_TYPE=Release .. && \
+    ninja -j $(getconf _NPROCESSORS_ONLN) && \
+    ninja -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 && \
@@ -235,7 +239,9 @@ 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 -y ninja-build python3-dev libncurses5 binutils clang
+    apt install --no-install-recommends --no-install-suggests -y \
+    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
@@ -301,9 +307,10 @@ 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 .. -DCMAKE_BUILD_TYPE=Release && \
-    make -j $(getconf _NPROCESSORS_ONLN) && \
-    DESTDIR=/h3 make install && \
+    cmake .. -GNinja -DBUILD_BENCHMARKS=0 -DCMAKE_BUILD_TYPE=Release \
+        -DBUILD_FUZZERS=0 -DBUILD_FILTERS=0 -DBUILD_GENERATORS=0 -DBUILD_TESTING=0 \
+    && ninja -j $(getconf _NPROCESSORS_ONLN) && \
+    DESTDIR=/h3 ninja install && \
    cp -R /h3/usr / && \
    rm -rf build

@@ -650,14 +657,15 @@ FROM build-deps AS rdkit-pg-build
 ARG PG_VERSION
 COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/

-RUN apt-get update && \
-    apt-get install --no-install-recommends -y \
+RUN apt update && \
+    apt install --no-install-recommends --no-install-suggests -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
@@ -693,6 +701,8 @@ RUN case "${PG_VERSION}" in \
        -D RDK_BUILD_MOLINTERCHANGE_SUPPORT=OFF \
        -D RDK_BUILD_YAEHMOP_SUPPORT=OFF \
        -D RDK_BUILD_STRUCTCHECKER_SUPPORT=OFF \
+        -D RDK_TEST_MULTITHREADED=OFF \
+        -D RDK_BUILD_CPP_TESTS=OFF \
        -D RDK_USE_URF=OFF \
        -D RDK_BUILD_PGSQL=ON \
        -D RDK_PGSQL_STATIC=ON \
@@ -704,9 +714,10 @@ RUN case "${PG_VERSION}" in \
        -D RDK_INSTALL_COMIC_FONTS=OFF \
        -D RDK_BUILD_FREETYPE_SUPPORT=OFF \
        -D CMAKE_BUILD_TYPE=Release \
+        -GNinja \
        . && \
-    make -j $(getconf _NPROCESSORS_ONLN) && \
-    make -j $(getconf _NPROCESSORS_ONLN) install && \
+    ninja -j $(getconf _NPROCESSORS_ONLN) && \
+    ninja -j $(getconf _NPROCESSORS_ONLN) install && \
    echo 'trusted = true' >> /usr/local/pgsql/share/extension/rdkit.control

 #########################################################################################
@@ -849,8 +860,9 @@ FROM build-deps AS rust-extensions-build
 ARG PG_VERSION
 COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/

-RUN apt-get update && \
-    apt-get install --no-install-recommends -y curl libclang-dev && \
+RUN apt update && \
+    apt install --no-install-recommends --no-install-suggests -y curl libclang-dev && \
+    apt clean && rm -rf /var/lib/apt/lists/* && \
    useradd -ms /bin/bash nonroot -b /home

 ENV HOME=/home/nonroot
@@ -885,8 +897,9 @@ FROM build-deps AS rust-extensions-build-pgrx12
 ARG PG_VERSION
 COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/

-RUN apt-get update && \
-    apt-get install --no-install-recommends -y curl libclang-dev && \
+RUN apt update && \
+    apt install --no-install-recommends --no-install-suggests -y curl libclang-dev && \
+    apt clean && rm -rf /var/lib/apt/lists/* && \
    useradd -ms /bin/bash nonroot -b /home

 ENV HOME=/home/nonroot
@@ -914,18 +927,22 @@ 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-get update && apt-get install -y python3 python3-pip python3-venv && \
+RUN apt update && apt install --no-install-recommends --no-install-suggests -y \
+    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 --skip_submodule_sync --skip_tests --allow_running_as_root
+    ./build.sh --config Release --parallel --cmake_generator Ninja \
+    --skip_submodule_sync --skip_tests --allow_running_as_root


 FROM pg-onnx-build AS pgrag-pg-build

-RUN apt-get install -y protobuf-compiler && \
+RUN apt update && apt install --no-install-recommends --no-install-suggests -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 . && \
@@ -1168,6 +1185,25 @@ 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"
@@ -1213,6 +1249,7 @@ 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) \
@@ -1248,7 +1285,7 @@ RUN make -j $(getconf _NPROCESSORS_ONLN) \

 #########################################################################################
 #
-# Compile and run the Neon-specific `compute_ctl` and `fast_import` binaries
+# Compile the Neon-specific `compute_ctl`, `fast_import`, and `local_proxy` binaries
 #
 #########################################################################################
 FROM $REPOSITORY/$IMAGE:$TAG AS compute-tools
@@ -1258,7 +1295,7 @@ ENV BUILD_TAG=$BUILD_TAG
 USER nonroot
 # Copy entire project to get Cargo.* files with proper dependencies for the whole project
 COPY --chown=nonroot . .
-RUN cd compute_tools && mold -run cargo build --locked --profile release-line-debug-size-lto
+RUN mold -run cargo build --locked --profile release-line-debug-size-lto --bin compute_ctl --bin fast_import --bin local_proxy

 #########################################################################################
 #
@@ -1279,8 +1316,8 @@ COPY --from=compute-tools /home/nonroot/target/release-line-debug-size-lto/fast_

 FROM debian:$DEBIAN_FLAVOR AS pgbouncer
 RUN set -e \
-    && apt-get update \
-    && apt-get install --no-install-recommends -y \
+    && apt update \
+    && apt install --no-install-suggests --no-install-recommends -y \
        build-essential \
        git \
        ca-certificates \
@@ -1288,7 +1325,8 @@ 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
@@ -1300,20 +1338,6 @@ 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"
@@ -1453,7 +1477,7 @@ 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=local_proxy --chown=postgres /home/nonroot/target/release-line-debug-size-lto/local_proxy /usr/local/bin/local_proxy
+COPY --from=compute-tools --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
@@ -1518,28 +1542,30 @@ RUN apt update && \
        locales \
        procps \
        ca-certificates \
+        curl \
+        unzip \
        $VERSION_INSTALLS && \
-    rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* && \
+    apt clean && 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

-# s5cmd 2.2.2 from https://github.com/peak/s5cmd/releases/tag/v2.2.2
-# used by fast_import
+# aws cli is used by fast_import (curl and unzip above are at this time only used for this installation step)
 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 \
-        CHECKSUM="392c385320cd5ffa435759a95af77c215553d967e4b1c0fffe52e4f14c29cf85"; \
+        TARGETARCH_ALT="x86_64"; \
+        CHECKSUM="c9a9df3770a3ff9259cb469b6179e02829687a464e0824d5c32d378820b53a00"; \
    elif [ "${TARGETARCH}" = "arm64" ]; then \
-        CHECKSUM="939bee3cf4b5604ddb00e67f8c157b91d7c7a5b553d1fbb6890fad32894b7b46"; \
+        TARGETARCH_ALT="aarch64"; \
+        CHECKSUM="8181730be7891582b38b028112e81b4899ca817e8c616aad807c9e9d1289223a"; \
    else \
        echo "Unsupported architecture: ${TARGETARCH}"; exit 1; \
    fi; \
-    \
-    # Compute and validate the checksum
-    echo "${CHECKSUM}  /tmp/s5cmd.deb" | sha256sum -c -
-RUN dpkg -i /tmp/s5cmd.deb && rm /tmp/s5cmd.deb
+    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 -; \
+    unzip /tmp/awscliv2.zip -d /tmp/awscliv2; \
+    /tmp/awscliv2/aws/install; \
+    rm -rf /tmp/awscliv2.zip /tmp/awscliv2; \
+    true

 ENV LANG=en_US.utf8
 USER postgres
--- a/compute/etc/neon_collector.jsonnet
+++ b/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.libsonnet',
+    import 'sql_exporter/compute_backpressure_throttling_seconds_total.libsonnet',
    import 'sql_exporter/compute_current_lsn.libsonnet',
    import 'sql_exporter/compute_logical_snapshot_files.libsonnet',
    import 'sql_exporter/compute_logical_snapshots_bytes.libsonnet',
--- a/compute/etc/sql_exporter/compute_backpressure_throttling_seconds_total.libsonnet
+++ b/compute/etc/sql_exporter/compute_backpressure_throttling_seconds_total.libsonnet
@@ -1,10 +1,10 @@
 {
-  metric_name: 'compute_backpressure_throttling_seconds',
-  type: 'gauge',
+  metric_name: 'compute_backpressure_throttling_seconds_total',
+  type: 'counter',
  help: 'Time compute has spent throttled',
  key_labels: null,
  values: [
    'throttled',
  ],
-  query: importstr 'sql_exporter/compute_backpressure_throttling_seconds.sql',
+  query: importstr 'sql_exporter/compute_backpressure_throttling_seconds_total.sql',
 }
--- a/compute/etc/sql_exporter/compute_backpressure_throttling_seconds_total.sql
+++ b/compute/etc/sql_exporter/compute_backpressure_throttling_seconds_total.sql
--- a/compute/patches/cloud_regress_pg16.patch
+++ b/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..1afae5395f 100644
+index 8475231735..0653946337 100644
 --- a/src/test/regress/expected/password.out
 +++ b/src/test/regress/expected/password.out
@@ -12,11 +12,11 @@ SET password_encryption = 'md5'; -- ok
@@ -1006,65 +1006,63 @@ index 8475231735..1afae5395f 100644
 -----------------+---------------------------------------------------
 - regress_passwd1 | md5783277baca28003b33453252be4dbb34
 - regress_passwd2 | md54044304ba511dd062133eb5b4b84a2a3
-+ regress_passwd1 | NEON_MD5_PLACEHOLDER_regress_passwd1
-+ regress_passwd2 | NEON_MD5_PLACEHOLDER_regress_passwd2
+ regress_passwd1 | NEON_MD5_PLACEHOLDER:regress_passwd1
+ 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 +54,30 @@ ALTER ROLE regress_passwd2_new RENAME TO regress_passwd2;
+@@ -54,24 +54,16 @@ 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;
- -- already encrypted with MD5, use as it is
- CREATE ROLE regress_passwd5 PASSWORD 'md5e73a4b11df52a6068f8b39f90be36023';
-+ERROR:  Received HTTP code 400 from control plane: {"error":"Neon only supports being given plaintext passwords"}
- -- 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';
-+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"}
+-- Neon does not support encrypted passwords, use unencrypted instead
+CREATE ROLE regress_passwd5 PASSWORD NEON_PASSWORD_PLACEHOLDER;
+-- 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;
 CREATE ROLE regress_passwd9 PASSWORD 'alterediterationcount';
-@@ -81,63 +87,67 @@ SELECT rolname, regexp_replace(rolpassword, '(SCRAM-SHA-256)\$(\d+):([a-zA-Z0-9+
+@@ -81,11 +73,11 @@ 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_passwd2 | NEON_MD5_PLACEHOLDER_regress_passwd2
+ regress_passwd1 | NEON_MD5_PLACEHOLDER:regress_passwd1
+ 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_passwd6 | 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_passwd9 | SCRAM-SHA-256$1024:<salt>$<storedkey>:<serverkey>
-(9 rows)
-+(5 rows)
- 
+ regress_passwd5 | 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_passwd8 | SCRAM-SHA-256$4096:<salt>$<storedkey>:<serverkey>
+@@ -95,23 +87,20 @@ SELECT rolname, regexp_replace(rolpassword, '(SCRAM-SHA-256)\$(\d+):([a-zA-Z0-9+
 -- 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
@@ -1082,56 +1080,37 @@ index 8475231735..1afae5395f 100644
 -(1 row)
 +(0 rows)
 
- -- 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=';
-+ERROR:  Received HTTP code 400 from control plane: {"error":"Neon only supports being given plaintext passwords"}
- 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=';
-+ERROR:  Received HTTP code 400 from control plane: {"error":"Neon only supports being given plaintext passwords"}
+--- 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.
 SELECT rolname, rolpassword not like '%A6xHKoH/494E941doaPOYg==%' as is_rolpassword_rehashed
-     FROM pg_authid
-     WHERE rolname LIKE 'regress_passwd_sha_len%'
+@@ -120,7 +109,7 @@ SELECT rolname, rolpassword not like '%A6xHKoH/494E941doaPOYg==%' as is_rolpassw
     ORDER BY rolname;
-         rolname         | is_rolpassword_rehashed 
--------------------------+-------------------------
+          rolname         | is_rolpassword_rehashed 
+ -------------------------+-------------------------
 - regress_passwd_sha_len0 | f
- regress_passwd_sha_len1 | t
- regress_passwd_sha_len2 | t
-(3 rows)
-+ rolname | is_rolpassword_rehashed 
-+---------+-------------------------
-+(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
+ regress_passwd_sha_len0 | t
+  regress_passwd_sha_len1 | t
+  regress_passwd_sha_len2 | t
+ (3 rows)
+@@ -135,6 +124,7 @@ DROP ROLE regress_passwd7;
 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
@@ -3194,7 +3173,7 @@ 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..f07cf1ec54 100644
+index 53e86b0b6c..0303fdfe96 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
@@ -3213,23 +3192,59 @@ index 53e86b0b6c..f07cf1ec54 100644
 
 -- check list of created entries
 --
-@@ -42,14 +42,14 @@ ALTER ROLE regress_passwd2_new RENAME TO regress_passwd2;
+@@ -42,26 +42,18 @@ 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;
- -- already encrypted with MD5, use as it is
- CREATE ROLE regress_passwd5 PASSWORD 'md5e73a4b11df52a6068f8b39f90be36023';
+-- Neon does not support encrypted passwords, use unencrypted instead
+CREATE ROLE regress_passwd5 PASSWORD NEON_PASSWORD_PLACEHOLDER;
 
+--- 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
--- a/compute/patches/cloud_regress_pg17.patch
+++ b/compute/patches/cloud_regress_pg17.patch
@@ -1014,10 +1014,10 @@ 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 924d6e001d..5966531db6 100644
+index 924d6e001d..7fdda73439 100644
 --- a/src/test/regress/expected/password.out
 +++ b/src/test/regress/expected/password.out
-@@ -12,13 +12,13 @@ SET password_encryption = 'md5'; -- ok
+@@ -12,13 +12,11 @@ SET password_encryption = 'md5'; -- ok
 SET password_encryption = 'scram-sha-256'; -- ok
 -- consistency of password entries
 SET password_encryption = 'md5';
@@ -1026,9 +1026,7 @@ index 924d6e001d..5966531db6 100644
 -CREATE ROLE regress_passwd2;
 -ALTER ROLE regress_passwd2 PASSWORD 'role_pwd2';
 +CREATE ROLE regress_passwd1 PASSWORD NEON_PASSWORD_PLACEHOLDER;
-+ALTER ROLE regress_passwd1 PASSWORD NEON_PASSWORD_PLACEHOLDER;
 +CREATE ROLE regress_passwd2 PASSWORD NEON_PASSWORD_PLACEHOLDER;
-+ALTER ROLE regress_passwd2 PASSWORD NEON_PASSWORD_PLACEHOLDER;
 SET password_encryption = 'scram-sha-256';
 -CREATE ROLE regress_passwd3 PASSWORD 'role_pwd3';
 -CREATE ROLE regress_passwd4 PASSWORD NULL;
@@ -1037,71 +1035,69 @@ index 924d6e001d..5966531db6 100644
 -- check list of created entries
 --
 -- The scram secret will look something like:
-@@ -32,10 +32,10 @@ SELECT rolname, regexp_replace(rolpassword, '(SCRAM-SHA-256)\$(\d+):([a-zA-Z0-9+
+@@ -32,10 +30,10 @@ SELECT rolname, regexp_replace(rolpassword, '(SCRAM-SHA-256)\$(\d+):([a-zA-Z0-9+
     ORDER BY rolname, rolpassword;
      rolname     |                rolpassword_masked                 
 -----------------+---------------------------------------------------
 - regress_passwd1 | md5783277baca28003b33453252be4dbb34
 - regress_passwd2 | md54044304ba511dd062133eb5b4b84a2a3
-+ regress_passwd1 | NEON_MD5_PLACEHOLDER_regress_passwd1
-+ regress_passwd2 | NEON_MD5_PLACEHOLDER_regress_passwd2
+ regress_passwd1 | NEON_MD5_PLACEHOLDER:regress_passwd1
+ 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
-@@ -56,24 +56,30 @@ ALTER ROLE regress_passwd2_new RENAME TO regress_passwd2;
+@@ -56,24 +54,17 @@ 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';
 +ALTER ROLE  regress_passwd4 PASSWORD NEON_PASSWORD_PLACEHOLDER;
 -- already encrypted with MD5, use as it is
- CREATE ROLE regress_passwd5 PASSWORD 'md5e73a4b11df52a6068f8b39f90be36023';
-+ERROR:  Received HTTP code 400 from control plane: {"error":"Neon only supports being given plaintext passwords"}
- -- 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';
-+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"}
+-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_passwd5 PASSWORD NEON_PASSWORD_PLACEHOLDER;
+-- 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;
 CREATE ROLE regress_passwd9 PASSWORD 'alterediterationcount';
-@@ -83,63 +89,67 @@ SELECT rolname, regexp_replace(rolpassword, '(SCRAM-SHA-256)\$(\d+):([a-zA-Z0-9+
+@@ -83,11 +74,11 @@ 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_passwd2 | NEON_MD5_PLACEHOLDER_regress_passwd2
+ regress_passwd1 | NEON_MD5_PLACEHOLDER:regress_passwd1
+ 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_passwd6 | 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_passwd9 | SCRAM-SHA-256$1024:<salt>$<storedkey>:<serverkey>
-(9 rows)
-+(5 rows)
- 
+ regress_passwd5 | 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_passwd8 | SCRAM-SHA-256$4096:<salt>$<storedkey>:<serverkey>
+@@ -97,23 +88,20 @@ SELECT rolname, regexp_replace(rolpassword, '(SCRAM-SHA-256)\$(\d+):([a-zA-Z0-9+
 -- 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
@@ -1119,56 +1115,37 @@ index 924d6e001d..5966531db6 100644
 -(1 row)
 +(0 rows)
 
- -- 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=';
-+ERROR:  Received HTTP code 400 from control plane: {"error":"Neon only supports being given plaintext passwords"}
- 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=';
-+ERROR:  Received HTTP code 400 from control plane: {"error":"Neon only supports being given plaintext passwords"}
+--- 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.
 SELECT rolname, rolpassword not like '%A6xHKoH/494E941doaPOYg==%' as is_rolpassword_rehashed
-     FROM pg_authid
-     WHERE rolname LIKE 'regress_passwd_sha_len%'
+@@ -122,7 +110,7 @@ SELECT rolname, rolpassword not like '%A6xHKoH/494E941doaPOYg==%' as is_rolpassw
     ORDER BY rolname;
-         rolname         | is_rolpassword_rehashed 
--------------------------+-------------------------
+          rolname         | is_rolpassword_rehashed 
+ -------------------------+-------------------------
 - regress_passwd_sha_len0 | f
- regress_passwd_sha_len1 | t
- regress_passwd_sha_len2 | t
-(3 rows)
-+ rolname | is_rolpassword_rehashed 
-+---------+-------------------------
-+(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
+ regress_passwd_sha_len0 | t
+  regress_passwd_sha_len1 | t
+  regress_passwd_sha_len2 | t
+ (3 rows)
+@@ -137,6 +125,7 @@ DROP ROLE regress_passwd7;
 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 1296da0d57..f43fffa44c 100644
 --- a/src/test/regress/expected/privileges.out
@@ -3249,10 +3226,10 @@ 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 bb82aa4aa2..7424c91b10 100644
+index bb82aa4aa2..dd8a05e24d 100644
 --- a/src/test/regress/sql/password.sql
 +++ b/src/test/regress/sql/password.sql
-@@ -10,13 +10,13 @@ SET password_encryption = 'scram-sha-256'; -- ok
+@@ -10,13 +10,11 @@ SET password_encryption = 'scram-sha-256'; -- ok
 
 -- consistency of password entries
 SET password_encryption = 'md5';
@@ -3261,9 +3238,7 @@ index bb82aa4aa2..7424c91b10 100644
 -CREATE ROLE regress_passwd2;
 -ALTER ROLE regress_passwd2 PASSWORD 'role_pwd2';
 +CREATE ROLE regress_passwd1 PASSWORD NEON_PASSWORD_PLACEHOLDER;
-+ALTER ROLE regress_passwd1 PASSWORD NEON_PASSWORD_PLACEHOLDER;
 +CREATE ROLE regress_passwd2 PASSWORD NEON_PASSWORD_PLACEHOLDER;
-+ALTER ROLE regress_passwd2 PASSWORD NEON_PASSWORD_PLACEHOLDER;
 SET password_encryption = 'scram-sha-256';
 -CREATE ROLE regress_passwd3 PASSWORD 'role_pwd3';
 -CREATE ROLE regress_passwd4 PASSWORD NULL;
@@ -3272,23 +3247,59 @@ index bb82aa4aa2..7424c91b10 100644
 
 -- check list of created entries
 --
-@@ -44,14 +44,14 @@ ALTER ROLE regress_passwd2_new RENAME TO regress_passwd2;
+@@ -44,26 +42,19 @@ 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';
 +ALTER ROLE  regress_passwd4 PASSWORD NEON_PASSWORD_PLACEHOLDER;
 -- already encrypted with MD5, use as it is
- CREATE ROLE regress_passwd5 PASSWORD 'md5e73a4b11df52a6068f8b39f90be36023';
+-CREATE ROLE regress_passwd5 PASSWORD 'md5e73a4b11df52a6068f8b39f90be36023';
+-- Neon does not support encrypted passwords, use unencrypted instead
+CREATE ROLE regress_passwd5 PASSWORD NEON_PASSWORD_PLACEHOLDER;
 
+--- 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;
+@@ -80,13 +71,10 @@ 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 5880bc018d..27aa952b18 100644
 --- a/src/test/regress/sql/privileges.sql
--- a/compute_tools/Cargo.toml
+++ b/compute_tools/Cargo.toml
@@ -7,7 +7,7 @@ license.workspace = true
 [features]
 default = []
 # Enables test specific features.
-testing = []
+testing = ["fail/failpoints"]

 [dependencies]
 base64.workspace = true
@@ -19,6 +19,7 @@ camino.workspace = true
 chrono.workspace = true
 cfg-if.workspace = true
 clap.workspace = true
+fail.workspace = true
 flate2.workspace = true
 futures.workspace = true
 hyper0 = { workspace = true, features = ["full"] }
--- a/compute_tools/src/bin/compute_ctl.rs
+++ b/compute_tools/src/bin/compute_ctl.rs
@@ -67,12 +67,15 @@ 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
@@ -100,6 +103,8 @@ fn main() -> Result<()> {

    maybe_delay_exit(delay_exit);

+    scenario.teardown();
+
    deinit_and_exit(wait_pg_result);
 }

@@ -419,9 +424,14 @@ fn start_postgres(
        "running compute with features: {:?}",
        state.pspec.as_ref().unwrap().spec.features
    );
-    // before we release the mutex, fetch the swap size (if any) for later.
-    let swap_size_bytes = state.pspec.as_ref().unwrap().spec.swap_size_bytes;
-    let disk_quota_bytes = state.pspec.as_ref().unwrap().spec.disk_quota_bytes;
+    // before we release the mutex, fetch some parameters for later.
+    let &ComputeSpec {
+        swap_size_bytes,
+        disk_quota_bytes,
+        #[cfg(target_os = "linux")]
+        disable_lfc_resizing,
+        ..
+    } = &state.pspec.as_ref().unwrap().spec;
    drop(state);

    // Launch remaining service threads
@@ -526,11 +536,18 @@ 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: file_cache_connstr.cloned(),
+                        pgconnstr,
                        addr: vm_monitor_addr.clone(),
                    })),
                    token.clone(),
--- a/compute_tools/src/bin/fast_import.rs
+++ b/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");
-    s5cmd::sync(Utf8Path::new(&pgdata_dir), &s3_prefix.append("/"))
+    aws_s3_sync::sync(Utf8Path::new(&pgdata_dir), &s3_prefix.append("/pgdata/"))
        .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("status");
+        let status_file = status_dir.join("pgdata");
        std::fs::write(&status_file, serde_json::json!({"done": true}).to_string())
            .context("write status file")?;
-        s5cmd::sync(&status_file, &s3_prefix.append("/status/pgdata"))
+        aws_s3_sync::sync(&status_dir, &s3_prefix.append("/status/"))
            .await
            .context("sync status directory to destination")?;
    }
--- a/compute_tools/src/bin/fast_import/aws_s3_sync.rs
+++ b/compute_tools/src/bin/fast_import/aws_s3_sync.rs
@@ -4,24 +4,21 @@ 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("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);
-    }
+    let mut builder = tokio::process::Command::new("aws");
    builder
+        .arg("s3")
        .arg("sync")
        .arg(local.as_str())
        .arg(remote.to_string());
    let st = builder
        .spawn()
-        .context("spawn s5cmd")?
+        .context("spawn aws s3 sync")?
        .wait()
        .await
-        .context("wait for s5cmd")?;
+        .context("wait for aws s3 sync")?;
    if st.success() {
        Ok(())
    } else {
-        Err(anyhow::anyhow!("s5cmd failed"))
+        Err(anyhow::anyhow!("aws s3 sync failed"))
    }
 }
--- a/compute_tools/src/compute.rs
+++ b/compute_tools/src/compute.rs
@@ -1181,8 +1181,19 @@ impl ComputeNode {
            let mut conf = postgres::config::Config::from(conf);
            conf.application_name("compute_ctl:migrations");

-            let mut client = conf.connect(NoTls)?;
-            handle_migrations(&mut client).context("apply_config handle_migrations")
+            match conf.connect(NoTls) {
+                Ok(mut client) => {
+                    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>(())
--- a/compute_tools/src/http/api.rs
+++ b/compute_tools/src/http/api.rs
@@ -24,8 +24,11 @@ use metrics::proto::MetricFamily;
 use metrics::Encoder;
 use metrics::TextEncoder;
 use tokio::task;
+use tokio_util::sync::CancellationToken;
 use tracing::{debug, error, info, warn};
 use tracing_utils::http::OtelName;
+use utils::failpoint_support::failpoints_handler;
+use utils::http::error::ApiError;
 use utils::http::request::must_get_query_param;

 fn status_response_from_state(state: &ComputeState) -> ComputeStatusResponse {
@@ -310,6 +313,18 @@ async fn routes(req: Request<Body>, compute: &Arc<ComputeNode>) -> Response<Body
            }
        }

+        (&Method::POST, "/failpoints") if cfg!(feature = "testing") => {
+            match failpoints_handler(req, CancellationToken::new()).await {
+                Ok(r) => r,
+                Err(ApiError::BadRequest(e)) => {
+                    render_json_error(&e.to_string(), StatusCode::BAD_REQUEST)
+                }
+                Err(_) => {
+                    render_json_error("Internal server error", StatusCode::INTERNAL_SERVER_ERROR)
+                }
+            }
+        }
+
        // download extension files from remote extension storage on demand
        (&Method::POST, route) if route.starts_with("/extension_server/") => {
            info!("serving {:?} POST request", route);
--- a/compute_tools/src/migration.rs
+++ b/compute_tools/src/migration.rs
@@ -1,13 +1,16 @@
 use anyhow::{Context, Result};
+use fail::fail_point;
 use postgres::Client;
 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);
@@ -15,6 +18,7 @@ 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
@@ -25,37 +29,61 @@ impl<'m> MigrationRunner<'m> {
        Ok(row.get::<&str, i64>("id"))
    }

+    /// Update the neon_migration.migration_id value
+    ///
+    /// 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(&mut self, migration_id: i64) -> Result<()> {
-        let setval = format!("UPDATE neon_migration.migration_id SET id={}", migration_id);
+        // 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
+            })();
+
+            if fail {
+                return Err(anyhow::anyhow!(format!(
+                    "migration {} was configured to fail because of a failpoint",
+                    migration_id
+                )));
+            }
+        }

        self.client
-            .simple_query(&setval)
+            .query(
+                "UPDATE neon_migration.migration_id SET id = $1",
+                &[&migration_id],
+            )
            .context("run_migrations update id")?;

        Ok(())
    }

-    fn prepare_migrations(&mut self) -> Result<()> {
-        let query = "CREATE SCHEMA IF NOT EXISTS neon_migration";
-        self.client.simple_query(query)?;
-
-        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(query)?;
-
-        let query = "INSERT INTO neon_migration.migration_id VALUES (0, 0) ON CONFLICT DO NOTHING";
-        self.client.simple_query(query)?;
-
-        let query = "ALTER SCHEMA neon_migration OWNER TO cloud_admin";
-        self.client.simple_query(query)?;
-
-        let query = "REVOKE ALL ON SCHEMA neon_migration FROM PUBLIC";
-        self.client.simple_query(query)?;
+    /// Prepare the migrations the target database for handling migrations
+    fn prepare_database(&mut self) -> Result<()> {
+        self.client
+            .simple_query("CREATE SCHEMA IF NOT EXISTS neon_migration")?;
+        self.client.simple_query("CREATE TABLE IF NOT EXISTS neon_migration.migration_id (key INT NOT NULL PRIMARY KEY, id bigint NOT NULL DEFAULT 0)")?;
+        self.client.simple_query(
+            "INSERT INTO neon_migration.migration_id VALUES (0, 0) ON CONFLICT DO NOTHING",
+        )?;
+        self.client
+            .simple_query("ALTER SCHEMA neon_migration OWNER TO cloud_admin")?;
+        self.client
+            .simple_query("REVOKE ALL ON SCHEMA neon_migration FROM PUBLIC")?;

        Ok(())
    }

+    /// Run the configrured set of migrations
    pub fn run_migrations(mut self) -> Result<()> {
-        self.prepare_migrations()?;
+        self.prepare_database()?;

        let mut current_migration = self.get_migration_id()? as usize;
        while current_migration < self.migrations.len() {
@@ -69,6 +97,11 @@ impl<'m> MigrationRunner<'m> {

            if migration.starts_with("-- SKIP") {
                info!("Skipping migration id={}", migration_id!(current_migration));
+
+                // Even though we are skipping the migration, updating the
+                // migration ID should help keep logic easy to understand when
+                // trying to understand the state of a cluster.
+                self.update_migration_id(migration_id!(current_migration))?;
            } else {
                info!(
                    "Running migration id={}:\n{}\n",
@@ -87,7 +120,6 @@ impl<'m> MigrationRunner<'m> {
                    )
                })?;

-                // Migration IDs start at 1
                self.update_migration_id(migration_id!(current_migration))?;

                self.client
--- a/compute_tools/src/migrations/tests/0001-neon_superuser_bypass_rls.sql
+++ b/compute_tools/src/migrations/tests/0001-neon_superuser_bypass_rls.sql
@@ -0,0 +1,9 @@
+DO $$
+DECLARE
+    bypassrls boolean;
+BEGIN
+    SELECT rolbypassrls INTO bypassrls FROM pg_roles WHERE rolname = 'neon_superuser';
+    IF NOT bypassrls THEN
+        RAISE EXCEPTION 'neon_superuser cannot bypass RLS';
+    END IF;
+END $$;
--- a/compute_tools/src/migrations/tests/0002-alter_roles.sql
+++ b/compute_tools/src/migrations/tests/0002-alter_roles.sql
@@ -0,0 +1,25 @@
+DO $$
+DECLARE
+    role record;
+BEGIN
+    FOR role IN
+        SELECT rolname AS name, rolinherit AS inherit
+        FROM pg_roles
+        WHERE pg_has_role(rolname, 'neon_superuser', 'member')
+    LOOP
+        IF NOT role.inherit THEN
+            RAISE EXCEPTION '% cannot inherit', quote_ident(role.name);
+        END IF;
+    END LOOP;
+
+    FOR role IN
+        SELECT rolname AS name, rolbypassrls AS bypassrls
+        FROM pg_roles
+        WHERE NOT pg_has_role(rolname, 'neon_superuser', 'member')
+            AND NOT starts_with(rolname, 'pg_')
+    LOOP
+        IF role.bypassrls THEN
+            RAISE EXCEPTION  '% can bypass RLS', quote_ident(role.name);
+        END IF;
+    END LOOP;
+END $$;
--- a/compute_tools/src/migrations/tests/0003-grant_pg_create_subscription_to_neon_superuser.sql
+++ b/compute_tools/src/migrations/tests/0003-grant_pg_create_subscription_to_neon_superuser.sql
@@ -0,0 +1,10 @@
+DO $$
+BEGIN
+    IF (SELECT current_setting('server_version_num')::numeric < 160000) THEN
+        RETURN;
+    END IF;
+
+    IF NOT (SELECT pg_has_role('neon_superuser', 'pg_create_subscription', 'member')) THEN
+        RAISE EXCEPTION 'neon_superuser cannot execute pg_create_subscription';
+    END IF;
+END $$;
--- a/compute_tools/src/migrations/tests/0004-grant_pg_monitor_to_neon_superuser.sql
+++ b/compute_tools/src/migrations/tests/0004-grant_pg_monitor_to_neon_superuser.sql
@@ -0,0 +1,19 @@
+DO $$
+DECLARE
+    monitor record;
+BEGIN
+    SELECT pg_has_role('neon_superuser', 'pg_monitor', 'member') AS member,
+            admin_option AS admin
+        INTO monitor
+        FROM pg_auth_members
+        WHERE roleid = 'pg_monitor'::regrole
+            AND member = 'pg_monitor'::regrole;
+
+    IF NOT monitor.member THEN
+        RAISE EXCEPTION 'neon_superuser is not a member of pg_monitor';
+    END IF;
+
+    IF NOT monitor.admin THEN
+        RAISE EXCEPTION 'neon_superuser cannot grant pg_monitor';
+    END IF;
+END $$;
--- a/compute_tools/src/migrations/tests/0005-grant_all_on_tables_to_neon_superuser.sql
+++ b/compute_tools/src/migrations/tests/0005-grant_all_on_tables_to_neon_superuser.sql
@@ -0,0 +1,2 @@
+-- This test was never written becuase at the time migration tests were added
+-- the accompanying migration was already skipped.
--- a/compute_tools/src/migrations/tests/0006-grant_all_on_sequences_to_neon_superuser.sql
+++ b/compute_tools/src/migrations/tests/0006-grant_all_on_sequences_to_neon_superuser.sql
@@ -0,0 +1,2 @@
+-- This test was never written becuase at the time migration tests were added
+-- the accompanying migration was already skipped.
--- a/compute_tools/src/migrations/tests/0007-grant_all_on_tables_to_neon_superuser_with_grant_option.sql
+++ b/compute_tools/src/migrations/tests/0007-grant_all_on_tables_to_neon_superuser_with_grant_option.sql
@@ -0,0 +1,2 @@
+-- This test was never written becuase at the time migration tests were added
+-- the accompanying migration was already skipped.
--- a/compute_tools/src/migrations/tests/0008-grant_all_on_sequences_to_neon_superuser_with_grant_option.sql
+++ b/compute_tools/src/migrations/tests/0008-grant_all_on_sequences_to_neon_superuser_with_grant_option.sql
@@ -0,0 +1,2 @@
+-- This test was never written becuase at the time migration tests were added
+-- the accompanying migration was already skipped.
--- a/compute_tools/src/migrations/tests/0009-revoke_replication_for_previously_allowed_roles.sql
+++ b/compute_tools/src/migrations/tests/0009-revoke_replication_for_previously_allowed_roles.sql
@@ -0,0 +1,2 @@
+-- This test was never written becuase at the time migration tests were added
+-- the accompanying migration was already skipped.
--- a/compute_tools/src/migrations/tests/0010-grant_snapshot_synchronization_funcs_to_neon_superuser.sql
+++ b/compute_tools/src/migrations/tests/0010-grant_snapshot_synchronization_funcs_to_neon_superuser.sql
@@ -0,0 +1,13 @@
+DO $$
+DECLARE
+    can_execute boolean;
+BEGIN
+    SELECT bool_and(has_function_privilege('neon_superuser', oid, 'execute'))
+       INTO can_execute
+       FROM pg_proc
+       WHERE proname IN ('pg_export_snapshot', 'pg_log_standby_snapshot')
+           AND pronamespace = 'pg_catalog'::regnamespace;
+    IF NOT can_execute THEN
+        RAISE EXCEPTION 'neon_superuser cannot execute both pg_export_snapshot and pg_log_standby_snapshot';
+    END IF;
+END $$;
--- a/compute_tools/src/migrations/tests/0011-grant_pg_show_replication_origin_status_to_neon_superuser.sql
+++ b/compute_tools/src/migrations/tests/0011-grant_pg_show_replication_origin_status_to_neon_superuser.sql
@@ -0,0 +1,13 @@
+DO $$
+DECLARE
+    can_execute boolean;
+BEGIN
+    SELECT has_function_privilege('neon_superuser', oid, 'execute')
+       INTO can_execute
+       FROM pg_proc
+       WHERE proname = 'pg_show_replication_origin_status'
+           AND pronamespace = 'pg_catalog'::regnamespace;
+    IF NOT can_execute THEN
+        RAISE EXCEPTION 'neon_superuser cannot execute pg_show_replication_origin_status';
+    END IF;
+END $$;
--- a/control_plane/src/bin/neon_local.rs
+++ b/control_plane/src/bin/neon_local.rs
@@ -19,6 +19,7 @@ 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,
@@ -36,6 +37,8 @@ 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;
@@ -689,6 +692,21 @@ 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:
@@ -700,9 +718,14 @@ fn main() -> Result<()> {
    let cli = Cli::parse();

    // Check for 'neon init' command first.
-    let subcommand_result = if let NeonLocalCmd::Init(args) = cli.command {
-        handle_init(&args).map(|env| Some(Cow::Owned(env)))
+    let (subcommand_result, _lock) = if let NeonLocalCmd::Init(args) = cli.command {
+        (handle_init(&args).map(|env| Some(Cow::Owned(env))), None)
    } 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();
@@ -728,11 +751,12 @@ fn main() -> Result<()> {
            NeonLocalCmd::Mappings(subcmd) => handle_mappings(&subcmd, env),
        };

-        if &original_env != env {
+        let subcommand_result = if &original_env != env {
            subcommand_result.map(|()| Some(Cow::Borrowed(env)))
        } else {
            subcommand_result.map(|()| None)
-        }
+        };
+        (subcommand_result, Some(_repo_lock))
    };

    match subcommand_result {
@@ -922,7 +946,7 @@ 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(Some(DEFAULT_PAGESERVER_CONTROL_PLANE_API.parse().unwrap())),
+            control_plane_api: Some(DEFAULT_PAGESERVER_CONTROL_PLANE_API.parse().unwrap()),
            broker: NeonBroker {
                listen_addr: DEFAULT_BROKER_ADDR.parse().unwrap(),
            },
@@ -1718,18 +1742,15 @@ async fn handle_start_all_impl(
            broker::start_broker_process(env, &retry_timeout).await
        });

-        // Only start the storage controller if the pageserver is configured to need it
-        if env.control_plane_api.is_some() {
-            js.spawn(async move {
-                let storage_controller = StorageController::from_env(env);
-                storage_controller
-                    .start(NeonStorageControllerStartArgs::with_default_instance_id(
-                        retry_timeout,
-                    ))
-                    .await
-                    .map_err(|e| e.context("start storage_controller"))
-            });
-        }
+        js.spawn(async move {
+            let storage_controller = StorageController::from_env(env);
+            storage_controller
+                .start(NeonStorageControllerStartArgs::with_default_instance_id(
+                    retry_timeout,
+                ))
+                .await
+                .map_err(|e| e.context("start storage_controller"))
+        });

        for ps_conf in &env.pageservers {
            js.spawn(async move {
@@ -1774,10 +1795,6 @@ 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();
--- a/control_plane/src/endpoint.rs
+++ b/control_plane/src/endpoint.rs
@@ -316,6 +316,10 @@ 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");
@@ -581,6 +585,7 @@ 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
--- a/control_plane/src/local_env.rs
+++ b/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: Option<Url>,
+    pub control_plane_api: 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<Option<Url>>,
+    pub control_plane_api: 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(100);
+    const DEFAULT_HEARTBEAT_INTERVAL: std::time::Duration = std::time::Duration::from_millis(1000);
 }

 impl Default for NeonStorageControllerConf {
@@ -535,7 +535,7 @@ impl LocalEnv {
                storage_controller,
                pageservers,
                safekeepers,
-                control_plane_api,
+                control_plane_api: control_plane_api.unwrap(),
                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: self.control_plane_api.clone(),
+                control_plane_api: Some(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_or_default(),
+            control_plane_api: control_plane_api.unwrap(),
            control_plane_compute_hook_api: control_plane_compute_hook_api.unwrap_or_default(),
            branch_name_mappings: Default::default(),
        };
--- a/control_plane/src/pageserver.rs
+++ b/control_plane/src/pageserver.rs
@@ -95,21 +95,19 @@ impl PageServerNode {

        let mut overrides = vec![pg_distrib_dir_param, broker_endpoint_param];

-        if let Some(control_plane_api) = &self.env.control_plane_api {
-            overrides.push(format!(
-                "control_plane_api='{}'",
-                control_plane_api.as_str()
-            ));
+        overrides.push(format!(
+            "control_plane_api='{}'",
+            self.env.control_plane_api.as_str()
+        ));

-            // Storage controller uses the same auth as pageserver: if JWT is enabled
-            // for us, we will also need it to talk to them.
-            if matches!(conf.http_auth_type, AuthType::NeonJWT) {
-                let jwt_token = self
-                    .env
-                    .generate_auth_token(&Claims::new(None, Scope::GenerationsApi))
-                    .unwrap();
-                overrides.push(format!("control_plane_api_token='{}'", jwt_token));
-            }
+        // Storage controller uses the same auth as pageserver: if JWT is enabled
+        // for us, we will also need it to talk to them.
+        if matches!(conf.http_auth_type, AuthType::NeonJWT) {
+            let jwt_token = self
+                .env
+                .generate_auth_token(&Claims::new(None, Scope::GenerationsApi))
+                .unwrap();
+            overrides.push(format!("control_plane_api_token='{}'", jwt_token));
        }

        if !conf.other.contains_key("remote_storage") {
--- a/control_plane/src/storage_controller.rs
+++ b/control_plane/src/storage_controller.rs
@@ -338,7 +338,7 @@ impl StorageController {
                        .port(),
                )
            } else {
-                let listen_url = self.env.control_plane_api.clone().unwrap();
+                let listen_url = self.env.control_plane_api.clone();

                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().unwrap();
+            let listen_url = self.env.control_plane_api.clone();
            Url::from_str(&format!(
                "http://{}:{}/{path}",
                listen_url.host_str().unwrap(),
--- a/control_plane/storcon_cli/src/main.rs
+++ b/control_plane/storcon_cli/src/main.rs
@@ -5,7 +5,8 @@ use clap::{Parser, Subcommand};
 use pageserver_api::{
    controller_api::{
        AvailabilityZone, NodeAvailabilityWrapper, NodeDescribeResponse, NodeShardResponse,
-        ShardSchedulingPolicy, TenantCreateRequest, TenantDescribeResponse, TenantPolicyRequest,
+        SafekeeperDescribeResponse, ShardSchedulingPolicy, TenantCreateRequest,
+        TenantDescribeResponse, TenantPolicyRequest,
    },
    models::{
        EvictionPolicy, EvictionPolicyLayerAccessThreshold, LocationConfigSecondary,
@@ -211,6 +212,8 @@ enum Command {
        #[arg(long)]
        timeout: humantime::Duration,
    },
+    /// List safekeepers known to the storage controller
+    Safekeepers {},
 }

 #[derive(Parser)]
@@ -1020,6 +1023,31 @@ 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"]);
+            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.to_string(),
+                ]);
+            }
+            println!("{table}");
+        }
    }

    Ok(())
--- a/docker-compose/compute_wrapper/var/db/postgres/specs/spec.json
+++ b/docker-compose/compute_wrapper/var/db/postgres/specs/spec.json
@@ -132,11 +132,6 @@
                "name": "cron.database",
                "value": "postgres",
                "vartype": "string"
-            },
-            {
-                "name": "session_preload_libraries",
-                "value": "anon",
-                "vartype": "string"
            }
        ]
    },
--- a/docker-compose/docker_compose_test.sh
+++ b/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 remove the corresponding option
-    if [ $pg_version -eq 17 ]; then
+    # The support of pg_anon not yet added to PG17, so we have to add the corresponding option for other PG versions
+    if [ "${pg_version}" -ne 17 ]; then
      SPEC_PATH="compute_wrapper/var/db/postgres/specs"
      mv $SPEC_PATH/spec.json $SPEC_PATH/spec.bak
-      jq 'del(.cluster.settings[] | select (.name == "session_preload_libraries"))' $SPEC_PATH/spec.bak > $SPEC_PATH/spec.json
+      jq '.cluster.settings += [{"name": "session_preload_libraries","value": "anon","vartype": "string"}]' "${SPEC_PATH}/spec.bak" > "${SPEC_PATH}/spec.json"
    fi
    PG_VERSION=$pg_version PG_TEST_VERSION=$PG_TEST_VERSION docker compose --profile test-extensions -f $COMPOSE_FILE up --build -d

@@ -106,8 +106,8 @@ for pg_version in ${TEST_VERSION_ONLY-14 15 16 17}; do
        fi
    fi
    cleanup
-    # The support of pg_anon not yet added to PG17, so we have to remove the corresponding option
-    if [ $pg_version -eq 17 ]; then
-      mv $SPEC_PATH/spec.bak $SPEC_PATH/spec.json
+    # Restore the original spec.json
+    if [ "$pg_version" -ne 17 ]; then
+      mv "$SPEC_PATH/spec.bak" "$SPEC_PATH/spec.json"
    fi
 done
--- a/libs/compute_api/src/spec.rs
+++ b/libs/compute_api/src/spec.rs
@@ -67,6 +67,15 @@ 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>>,
--- a/libs/desim/src/time.rs
+++ b/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().map_or(false, |x| x.time <= self.now())
+        queue.peek().is_some_and(|x| x.time <= self.now())
    }

    /// Clear all pending events.
--- a/libs/pageserver_api/src/controller_api.rs
+++ b/libs/pageserver_api/src/controller_api.rs
@@ -372,6 +372,23 @@ 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,
+}
+
 #[cfg(test)]
 mod test {
    use super::*;
--- a/libs/pageserver_api/src/key.rs
+++ b/libs/pageserver_api/src/key.rs
@@ -565,6 +565,10 @@ 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)]
--- a/libs/pageserver_api/src/models.rs
+++ b/libs/pageserver_api/src/models.rs
@@ -6,6 +6,7 @@ pub mod utilization;
 use camino::Utf8PathBuf;
 pub use utilization::PageserverUtilization;

+use core::ops::Range;
 use std::{
    collections::HashMap,
    fmt::Display,
@@ -28,6 +29,7 @@ use utils::{
 };

 use crate::{
+    key::Key,
    reltag::RelTag,
    shard::{ShardCount, ShardStripeSize, TenantShardId},
 };
@@ -210,6 +212,68 @@ 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,
--- a/libs/pageserver_api/src/shard.rs
+++ b/libs/pageserver_api/src/shard.rs
@@ -173,7 +173,11 @@ 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() || key.is_slru_segment_size_key() || key.is_aux_file_key() {
+        if key.is_slru_block_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() {
--- a/libs/postgres_ffi/Cargo.toml
+++ b/libs/postgres_ffi/Cargo.toml
@@ -9,9 +9,11 @@ regex.workspace = true
 bytes.workspace = true
 anyhow.workspace = true
 crc32c.workspace = true
+criterion.workspace = true
 once_cell.workspace = true
 log.workspace = true
 memoffset.workspace = true
+pprof.workspace = true
 thiserror.workspace = true
 serde.workspace = true
 utils.workspace = true
@@ -24,3 +26,7 @@ postgres.workspace = true
 [build-dependencies]
 anyhow.workspace = true
 bindgen.workspace = true
+
+[[bench]]
+name = "waldecoder"
+harness = false
--- a/libs/postgres_ffi/benches/README.md
+++ b/libs/postgres_ffi/benches/README.md
@@ -0,0 +1,26 @@
+## Benchmarks
+
+To run benchmarks:
+
+```sh
+# All benchmarks.
+cargo bench --package postgres_ffi
+
+# Specific file.
+cargo bench --package postgres_ffi --bench waldecoder
+
+# Specific benchmark.
+cargo bench --package postgres_ffi --bench waldecoder complete_record/size=1024
+
+# List available benchmarks.
+cargo bench --package postgres_ffi --benches -- --list
+
+# Generate flamegraph profiles using pprof-rs, profiling for 10 seconds.
+# Output in target/criterion/*/profile/flamegraph.svg.
+cargo bench --package postgres_ffi --bench waldecoder complete_record/size=1024 -- --profile-time 10
+```
+
+Additional charts and statistics are available in `target/criterion/report/index.html`.
+
+Benchmarks are automatically compared against the previous run. To compare against other runs, see
+`--baseline` and `--save-baseline`.
--- a/libs/postgres_ffi/benches/waldecoder.rs
+++ b/libs/postgres_ffi/benches/waldecoder.rs
@@ -0,0 +1,49 @@
+use std::ffi::CStr;
+
+use criterion::{criterion_group, criterion_main, Bencher, Criterion};
+use postgres_ffi::v17::wal_generator::LogicalMessageGenerator;
+use postgres_ffi::v17::waldecoder_handler::WalStreamDecoderHandler;
+use postgres_ffi::waldecoder::WalStreamDecoder;
+use pprof::criterion::{Output, PProfProfiler};
+use utils::lsn::Lsn;
+
+const KB: usize = 1024;
+
+// Register benchmarks with Criterion.
+criterion_group!(
+    name = benches;
+    config = Criterion::default().with_profiler(PProfProfiler::new(100, Output::Flamegraph(None)));
+    targets = bench_complete_record,
+);
+criterion_main!(benches);
+
+/// Benchmarks WalStreamDecoder::complete_record() for a logical message of varying size.
+fn bench_complete_record(c: &mut Criterion) {
+    let mut g = c.benchmark_group("complete_record");
+    for size in [64, KB, 8 * KB, 128 * KB] {
+        // Kind of weird to change the group throughput per benchmark, but it's the only way
+        // to vary it per benchmark. It works.
+        g.throughput(criterion::Throughput::Bytes(size as u64));
+        g.bench_function(format!("size={size}"), |b| run_bench(b, size).unwrap());
+    }
+
+    fn run_bench(b: &mut Bencher, size: usize) -> anyhow::Result<()> {
+        const PREFIX: &CStr = c"";
+        let value_size = LogicalMessageGenerator::make_value_size(size, PREFIX);
+        let value = vec![1; value_size];
+
+        let mut decoder = WalStreamDecoder::new(Lsn(0), 170000);
+        let msg = LogicalMessageGenerator::new(PREFIX, &value)
+            .next()
+            .unwrap()
+            .encode(Lsn(0));
+        assert_eq!(msg.len(), size);
+
+        b.iter(|| {
+            let msg = msg.clone(); // Bytes::clone() is cheap
+            decoder.complete_record(msg).unwrap();
+        });
+
+        Ok(())
+    }
+}
--- a/libs/postgres_ffi/src/wal_generator.rs
+++ b/libs/postgres_ffi/src/wal_generator.rs
@@ -106,11 +106,11 @@ impl<R: RecordGenerator> WalGenerator<R> {
    const TIMELINE_ID: u32 = 1;

    /// Creates a new WAL generator with the given record generator.
-    pub fn new(record_generator: R) -> WalGenerator<R> {
+    pub fn new(record_generator: R, start_lsn: Lsn) -> WalGenerator<R> {
        Self {
            record_generator,
-            lsn: Lsn(0),
-            prev_lsn: Lsn(0),
+            lsn: start_lsn,
+            prev_lsn: start_lsn,
        }
    }

@@ -231,6 +231,22 @@ impl LogicalMessageGenerator {
        };
        [&header.encode(), prefix, message].concat().into()
    }
+
+    /// Computes how large a value must be to get a record of the given size. Convenience method to
+    /// construct records of pre-determined size. Panics if the record size is too small.
+    pub fn make_value_size(record_size: usize, prefix: &CStr) -> usize {
+        let xlog_header_size = XLOG_SIZE_OF_XLOG_RECORD;
+        let lm_header_size = size_of::<XlLogicalMessage>();
+        let prefix_size = prefix.to_bytes_with_nul().len();
+        let data_header_size = match record_size - xlog_header_size - 2 {
+            0..=255 => 2,
+            256..=258 => panic!("impossible record_size {record_size}"),
+            259.. => 5,
+        };
+        record_size
+            .checked_sub(xlog_header_size + lm_header_size + prefix_size + data_header_size)
+            .expect("record_size too small")
+    }
 }

 impl Iterator for LogicalMessageGenerator {
--- a/libs/postgres_ffi/wal_craft/src/xlog_utils_test.rs
+++ b/libs/postgres_ffi/wal_craft/src/xlog_utils_test.rs
@@ -81,7 +81,7 @@ fn test_end_of_wal<C: crate::Crafter>(test_name: &str) {
                continue;
            }
            let mut f = File::options().write(true).open(file.path()).unwrap();
-            const ZEROS: [u8; WAL_SEGMENT_SIZE] = [0u8; WAL_SEGMENT_SIZE];
+            static ZEROS: [u8; WAL_SEGMENT_SIZE] = [0u8; WAL_SEGMENT_SIZE];
            f.write_all(
                &ZEROS[0..min(
                    WAL_SEGMENT_SIZE,
--- a/libs/proxy/postgres-protocol2/Cargo.toml
+++ b/libs/proxy/postgres-protocol2/Cargo.toml
@@ -1,7 +1,7 @@
 [package]
 name = "postgres-protocol2"
 version = "0.1.0"
-edition = "2018"
+edition = "2021"
 license = "MIT/Apache-2.0"

 [dependencies]
--- a/libs/proxy/postgres-protocol2/src/lib.rs
+++ b/libs/proxy/postgres-protocol2/src/lib.rs
@@ -9,8 +9,7 @@
 //!
 //! This library assumes that the `client_encoding` backend parameter has been
 //! set to `UTF8`. It will most likely not behave properly if that is not the case.
-#![doc(html_root_url = "https://docs.rs/postgres-protocol/0.6")]
-#![warn(missing_docs, rust_2018_idioms, clippy::all)]
+#![warn(missing_docs, clippy::all)]

 use byteorder::{BigEndian, ByteOrder};
 use bytes::{BufMut, BytesMut};
--- a/libs/proxy/postgres-protocol2/src/message/frontend.rs
+++ b/libs/proxy/postgres-protocol2/src/message/frontend.rs
@@ -3,7 +3,6 @@

 use byteorder::{BigEndian, ByteOrder};
 use bytes::{Buf, BufMut, BytesMut};
-use std::convert::TryFrom;
 use std::error::Error;
 use std::io;
 use std::marker;
--- a/libs/proxy/postgres-types2/Cargo.toml
+++ b/libs/proxy/postgres-types2/Cargo.toml
@@ -1,7 +1,7 @@
 [package]
 name = "postgres-types2"
 version = "0.1.0"
-edition = "2018"
+edition = "2021"
 license = "MIT/Apache-2.0"

 [dependencies]
--- a/libs/proxy/postgres-types2/src/lib.rs
+++ b/libs/proxy/postgres-types2/src/lib.rs
@@ -2,8 +2,7 @@
 //!
 //! This crate is used by the `tokio-postgres` and `postgres` crates. You normally don't need to depend directly on it
 //! unless you want to define your own `ToSql` or `FromSql` definitions.
-#![doc(html_root_url = "https://docs.rs/postgres-types/0.2")]
-#![warn(clippy::all, rust_2018_idioms, missing_docs)]
+#![warn(clippy::all, missing_docs)]

 use fallible_iterator::FallibleIterator;
 use postgres_protocol2::types;
--- a/libs/proxy/tokio-postgres2/Cargo.toml
+++ b/libs/proxy/tokio-postgres2/Cargo.toml
@@ -1,7 +1,7 @@
 [package]
 name = "tokio-postgres2"
 version = "0.1.0"
-edition = "2018"
+edition = "2021"
 license = "MIT/Apache-2.0"

 [dependencies]
--- a/libs/proxy/tokio-postgres2/src/connection.rs
+++ b/libs/proxy/tokio-postgres2/src/connection.rs
@@ -33,10 +33,14 @@ pub struct Response {
 #[derive(PartialEq, Debug)]
 enum State {
    Active,
-    Terminating,
    Closing,
 }

+enum WriteReady {
+    Terminating,
+    WaitingOnRead,
+}
+
 /// A connection to a PostgreSQL database.
 ///
 /// This is one half of what is returned when a new connection is established. It performs the actual IO with the
@@ -51,7 +55,6 @@ pub struct Connection<S, T> {
    /// HACK: we need this in the Neon Proxy to forward params.
    pub parameters: HashMap<String, String>,
    receiver: mpsc::UnboundedReceiver<Request>,
-    pending_request: Option<RequestMessages>,
    pending_responses: VecDeque<BackendMessage>,
    responses: VecDeque<Response>,
    state: State,
@@ -72,7 +75,6 @@ where
            stream,
            parameters,
            receiver,
-            pending_request: None,
            pending_responses,
            responses: VecDeque::new(),
            state: State::Active,
@@ -93,26 +95,23 @@ where
            .map(|o| o.map(|r| r.map_err(Error::io)))
    }

-    fn poll_read(&mut self, cx: &mut Context<'_>) -> Result<Option<AsyncMessage>, Error> {
-        if self.state != State::Active {
-            trace!("poll_read: done");
-            return Ok(None);
-        }
-
+    /// Read and process messages from the connection to postgres.
+    /// client <- postgres
+    fn poll_read(&mut self, cx: &mut Context<'_>) -> Poll<Result<AsyncMessage, Error>> {
        loop {
            let message = match self.poll_response(cx)? {
                Poll::Ready(Some(message)) => message,
-                Poll::Ready(None) => return Err(Error::closed()),
+                Poll::Ready(None) => return Poll::Ready(Err(Error::closed())),
                Poll::Pending => {
                    trace!("poll_read: waiting on response");
-                    return Ok(None);
+                    return Poll::Pending;
                }
            };

            let (mut messages, request_complete) = match message {
                BackendMessage::Async(Message::NoticeResponse(body)) => {
                    let error = DbError::parse(&mut body.fields()).map_err(Error::parse)?;
-                    return Ok(Some(AsyncMessage::Notice(error)));
+                    return Poll::Ready(Ok(AsyncMessage::Notice(error)));
                }
                BackendMessage::Async(Message::NotificationResponse(body)) => {
                    let notification = Notification {
@@ -120,7 +119,7 @@ where
                        channel: body.channel().map_err(Error::parse)?.to_string(),
                        payload: body.message().map_err(Error::parse)?.to_string(),
                    };
-                    return Ok(Some(AsyncMessage::Notification(notification)));
+                    return Poll::Ready(Ok(AsyncMessage::Notification(notification)));
                }
                BackendMessage::Async(Message::ParameterStatus(body)) => {
                    self.parameters.insert(
@@ -139,8 +138,10 @@ where
            let mut response = match self.responses.pop_front() {
                Some(response) => response,
                None => match messages.next().map_err(Error::parse)? {
-                    Some(Message::ErrorResponse(error)) => return Err(Error::db(error)),
-                    _ => return Err(Error::unexpected_message()),
+                    Some(Message::ErrorResponse(error)) => {
+                        return Poll::Ready(Err(Error::db(error)))
+                    }
+                    _ => return Poll::Ready(Err(Error::unexpected_message())),
                },
            };

@@ -164,18 +165,14 @@ where
                        request_complete,
                    });
                    trace!("poll_read: waiting on sender");
-                    return Ok(None);
+                    return Poll::Pending;
                }
            }
        }
    }

+    /// Fetch the next client request and enqueue the response sender.
    fn poll_request(&mut self, cx: &mut Context<'_>) -> Poll<Option<RequestMessages>> {
-        if let Some(messages) = self.pending_request.take() {
-            trace!("retrying pending request");
-            return Poll::Ready(Some(messages));
-        }
-
        if self.receiver.is_closed() {
            return Poll::Ready(None);
        }
@@ -193,74 +190,80 @@ where
        }
    }

-    fn poll_write(&mut self, cx: &mut Context<'_>) -> Result<bool, Error> {
+    /// Process client requests and write them to the postgres connection, flushing if necessary.
+    /// client -> postgres
+    fn poll_write(&mut self, cx: &mut Context<'_>) -> Poll<Result<WriteReady, Error>> {
        loop {
-            if self.state == State::Closing {
-                trace!("poll_write: done");
-                return Ok(false);
-            }
-
            if Pin::new(&mut self.stream)
                .poll_ready(cx)
                .map_err(Error::io)?
                .is_pending()
            {
                trace!("poll_write: waiting on socket");
-                return Ok(false);
+
+                // poll_ready is self-flushing.
+                return Poll::Pending;
            }

-            let request = match self.poll_request(cx) {
-                Poll::Ready(Some(request)) => request,
-                Poll::Ready(None) if self.responses.is_empty() && self.state == State::Active => {
+            match self.poll_request(cx) {
+                // send the message to postgres
+                Poll::Ready(Some(RequestMessages::Single(request))) => {
+                    Pin::new(&mut self.stream)
+                        .start_send(request)
+                        .map_err(Error::io)?;
+                }
+                // No more messages from the client, and no more responses to wait for.
+                // Send a terminate message to postgres
+                Poll::Ready(None) if self.responses.is_empty() => {
                    trace!("poll_write: at eof, terminating");
-                    self.state = State::Terminating;
                    let mut request = BytesMut::new();
                    frontend::terminate(&mut request);
-                    RequestMessages::Single(FrontendMessage::Raw(request.freeze()))
+                    let request = FrontendMessage::Raw(request.freeze());
+
+                    Pin::new(&mut self.stream)
+                        .start_send(request)
+                        .map_err(Error::io)?;
+
+                    trace!("poll_write: sent eof, closing");
+                    trace!("poll_write: done");
+                    return Poll::Ready(Ok(WriteReady::Terminating));
                }
+                // No more messages from the client, but there are still some responses to wait for.
                Poll::Ready(None) => {
                    trace!(
                        "poll_write: at eof, pending responses {}",
                        self.responses.len()
                    );
-                    return Ok(true);
+                    ready!(self.poll_flush(cx))?;
+                    return Poll::Ready(Ok(WriteReady::WaitingOnRead));
                }
+                // Still waiting for a message from the client.
                Poll::Pending => {
                    trace!("poll_write: waiting on request");
-                    return Ok(true);
-                }
-            };
-
-            match request {
-                RequestMessages::Single(request) => {
-                    Pin::new(&mut self.stream)
-                        .start_send(request)
-                        .map_err(Error::io)?;
-                    if self.state == State::Terminating {
-                        trace!("poll_write: sent eof, closing");
-                        self.state = State::Closing;
-                    }
+                    ready!(self.poll_flush(cx))?;
+                    return Poll::Pending;
                }
            }
        }
    }

-    fn poll_flush(&mut self, cx: &mut Context<'_>) -> Result<(), Error> {
+    fn poll_flush(&mut self, cx: &mut Context<'_>) -> Poll<Result<(), Error>> {
        match Pin::new(&mut self.stream)
            .poll_flush(cx)
            .map_err(Error::io)?
        {
-            Poll::Ready(()) => trace!("poll_flush: flushed"),
-            Poll::Pending => trace!("poll_flush: waiting on socket"),
+            Poll::Ready(()) => {
+                trace!("poll_flush: flushed");
+                Poll::Ready(Ok(()))
+            }
+            Poll::Pending => {
+                trace!("poll_flush: waiting on socket");
+                Poll::Pending
+            }
        }
-        Ok(())
    }

    fn poll_shutdown(&mut self, cx: &mut Context<'_>) -> Poll<Result<(), Error>> {
-        if self.state != State::Closing {
-            return Poll::Pending;
-        }
-
        match Pin::new(&mut self.stream)
            .poll_close(cx)
            .map_err(Error::io)?
@@ -289,18 +292,30 @@ where
        &mut self,
        cx: &mut Context<'_>,
    ) -> Poll<Option<Result<AsyncMessage, Error>>> {
-        let message = self.poll_read(cx)?;
-        let want_flush = self.poll_write(cx)?;
-        if want_flush {
-            self.poll_flush(cx)?;
+        if self.state != State::Closing {
+            // if the state is still active, try read from and write to postgres.
+            let message = self.poll_read(cx)?;
+            let closing = self.poll_write(cx)?;
+            if let Poll::Ready(WriteReady::Terminating) = closing {
+                self.state = State::Closing;
+            }
+
+            if let Poll::Ready(message) = message {
+                return Poll::Ready(Some(Ok(message)));
+            }
+
+            // poll_read returned Pending.
+            // poll_write returned Pending or Ready(WriteReady::WaitingOnRead).
+            // if poll_write returned Ready(WriteReady::WaitingOnRead), then we are waiting to read more data from postgres.
+            if self.state != State::Closing {
+                return Poll::Pending;
+            }
        }
-        match message {
-            Some(message) => Poll::Ready(Some(Ok(message))),
-            None => match self.poll_shutdown(cx) {
-                Poll::Ready(Ok(())) => Poll::Ready(None),
-                Poll::Ready(Err(e)) => Poll::Ready(Some(Err(e))),
-                Poll::Pending => Poll::Pending,
-            },
+
+        match self.poll_shutdown(cx) {
+            Poll::Ready(Ok(())) => Poll::Ready(None),
+            Poll::Ready(Err(e)) => Poll::Ready(Some(Err(e))),
+            Poll::Pending => Poll::Pending,
        }
    }
 }
--- a/libs/proxy/tokio-postgres2/src/lib.rs
+++ b/libs/proxy/tokio-postgres2/src/lib.rs
@@ -1,5 +1,5 @@
 //! An asynchronous, pipelined, PostgreSQL client.
-#![warn(rust_2018_idioms, clippy::all)]
+#![warn(clippy::all)]

 pub use crate::cancel_token::CancelToken;
 pub use crate::client::{Client, SocketConfig};
--- a/libs/proxy/tokio-postgres2/src/to_statement.rs
+++ b/libs/proxy/tokio-postgres2/src/to_statement.rs
@@ -11,7 +11,7 @@ mod private {
        Query(&'a str),
    }

-    impl<'a> ToStatementType<'a> {
+    impl ToStatementType<'_> {
        pub async fn into_statement(self, client: &Client) -> Result<Statement, Error> {
            match self {
                ToStatementType::Statement(s) => Ok(s.clone()),
--- a/libs/remote_storage/Cargo.toml
+++ b/libs/remote_storage/Cargo.toml
@@ -18,6 +18,7 @@ camino = { workspace = true, features = ["serde1"] }
 humantime-serde.workspace = true
 hyper = { workspace = true, features = ["client"] }
 futures.workspace = true
+reqwest.workspace = true
 serde.workspace = true
 serde_json.workspace = true
 tokio = { workspace = true, features = ["sync", "fs", "io-util"] }
--- a/libs/remote_storage/src/azure_blob.rs
+++ b/libs/remote_storage/src/azure_blob.rs
@@ -8,6 +8,7 @@ use std::io;
 use std::num::NonZeroU32;
 use std::pin::Pin;
 use std::str::FromStr;
+use std::sync::Arc;
 use std::time::Duration;
 use std::time::SystemTime;

@@ -15,6 +16,8 @@ use super::REMOTE_STORAGE_PREFIX_SEPARATOR;
 use anyhow::Context;
 use anyhow::Result;
 use azure_core::request_options::{IfMatchCondition, MaxResults, Metadata, Range};
+use azure_core::HttpClient;
+use azure_core::TransportOptions;
 use azure_core::{Continuable, RetryOptions};
 use azure_storage::StorageCredentials;
 use azure_storage_blobs::blob::CopyStatus;
@@ -80,8 +83,13 @@ impl AzureBlobStorage {
            StorageCredentials::token_credential(token_credential)
        };

-        // we have an outer retry
-        let builder = ClientBuilder::new(account, credentials).retry(RetryOptions::none());
+        let builder = ClientBuilder::new(account, credentials)
+            // we have an outer retry
+            .retry(RetryOptions::none())
+            // Customize transport to configure conneciton pooling
+            .transport(TransportOptions::new(Self::reqwest_client(
+                azure_config.conn_pool_size,
+            )));

        let client = builder.container_client(azure_config.container_name.to_owned());

@@ -106,6 +114,14 @@ impl AzureBlobStorage {
        })
    }

+    fn reqwest_client(conn_pool_size: usize) -> Arc<dyn HttpClient> {
+        let client = reqwest::ClientBuilder::new()
+            .pool_max_idle_per_host(conn_pool_size)
+            .build()
+            .expect("failed to build `reqwest` client");
+        Arc::new(client)
+    }
+
    pub fn relative_path_to_name(&self, path: &RemotePath) -> String {
        assert_eq!(std::path::MAIN_SEPARATOR, REMOTE_STORAGE_PREFIX_SEPARATOR);
        let path_string = path.get_path().as_str();
@@ -544,9 +560,9 @@ impl RemoteStorage for AzureBlobStorage {
            .await
    }

-    async fn delete_objects<'a>(
+    async fn delete_objects(
        &self,
-        paths: &'a [RemotePath],
+        paths: &[RemotePath],
        cancel: &CancellationToken,
    ) -> anyhow::Result<()> {
        let kind = RequestKind::Delete;
--- a/libs/remote_storage/src/config.rs
+++ b/libs/remote_storage/src/config.rs
@@ -114,6 +114,16 @@ fn default_max_keys_per_list_response() -> Option<i32> {
    DEFAULT_MAX_KEYS_PER_LIST_RESPONSE
 }

+fn default_azure_conn_pool_size() -> usize {
+    // Conservative default: no connection pooling.  At time of writing this is the Azure
+    // SDK's default as well, due to historic reports of hard-to-reproduce issues
+    // (https://github.com/hyperium/hyper/issues/2312)
+    //
+    // However, using connection pooling is important to avoid exhausting client ports when
+    // doing huge numbers of requests (https://github.com/neondatabase/cloud/issues/20971)
+    0
+}
+
 impl Debug for S3Config {
    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
        f.debug_struct("S3Config")
@@ -146,6 +156,8 @@ pub struct AzureConfig {
    pub concurrency_limit: NonZeroUsize,
    #[serde(default = "default_max_keys_per_list_response")]
    pub max_keys_per_list_response: Option<i32>,
+    #[serde(default = "default_azure_conn_pool_size")]
+    pub conn_pool_size: usize,
 }

 fn default_remote_storage_azure_concurrency_limit() -> NonZeroUsize {
@@ -302,6 +314,7 @@ timeout = '5s'";
    container_region = 'westeurope'
    upload_storage_class = 'INTELLIGENT_TIERING'
    timeout = '7s'
+    conn_pool_size = 8
    ";

        let config = parse(toml).unwrap();
@@ -316,6 +329,7 @@ timeout = '5s'";
                    prefix_in_container: None,
                    concurrency_limit: default_remote_storage_azure_concurrency_limit(),
                    max_keys_per_list_response: DEFAULT_MAX_KEYS_PER_LIST_RESPONSE,
+                    conn_pool_size: 8,
                }),
                timeout: Duration::from_secs(7),
                small_timeout: RemoteStorageConfig::DEFAULT_SMALL_TIMEOUT
--- a/libs/remote_storage/src/lib.rs
+++ b/libs/remote_storage/src/lib.rs
@@ -341,9 +341,9 @@ pub trait RemoteStorage: Send + Sync + 'static {
    /// If the operation fails because of timeout or cancellation, the root cause of the error will be
    /// set to `TimeoutOrCancel`. In such situation it is unknown which deletions, if any, went
    /// through.
-    async fn delete_objects<'a>(
+    async fn delete_objects(
        &self,
-        paths: &'a [RemotePath],
+        paths: &[RemotePath],
        cancel: &CancellationToken,
    ) -> anyhow::Result<()>;

--- a/libs/remote_storage/src/local_fs.rs
+++ b/libs/remote_storage/src/local_fs.rs
@@ -562,9 +562,9 @@ impl RemoteStorage for LocalFs {
        }
    }

-    async fn delete_objects<'a>(
+    async fn delete_objects(
        &self,
-        paths: &'a [RemotePath],
+        paths: &[RemotePath],
        cancel: &CancellationToken,
    ) -> anyhow::Result<()> {
        for path in paths {
--- a/libs/remote_storage/src/s3_bucket.rs
+++ b/libs/remote_storage/src/s3_bucket.rs
@@ -813,9 +813,9 @@ impl RemoteStorage for S3Bucket {
        .await
    }

-    async fn delete_objects<'a>(
+    async fn delete_objects(
        &self,
-        paths: &'a [RemotePath],
+        paths: &[RemotePath],
        cancel: &CancellationToken,
    ) -> anyhow::Result<()> {
        let kind = RequestKind::Delete;
--- a/libs/remote_storage/src/simulate_failures.rs
+++ b/libs/remote_storage/src/simulate_failures.rs
@@ -181,9 +181,9 @@ impl RemoteStorage for UnreliableWrapper {
        self.delete_inner(path, true, cancel).await
    }

-    async fn delete_objects<'a>(
+    async fn delete_objects(
        &self,
-        paths: &'a [RemotePath],
+        paths: &[RemotePath],
        cancel: &CancellationToken,
    ) -> anyhow::Result<()> {
        self.attempt(RemoteOp::DeleteObjects(paths.to_vec()))?;
--- a/libs/remote_storage/tests/test_real_azure.rs
+++ b/libs/remote_storage/tests/test_real_azure.rs
@@ -218,6 +218,7 @@ async fn create_azure_client(
            prefix_in_container: Some(format!("test_{millis}_{random:08x}/")),
            concurrency_limit: NonZeroUsize::new(100).unwrap(),
            max_keys_per_list_response,
+            conn_pool_size: 8,
        }),
        timeout: RemoteStorageConfig::DEFAULT_TIMEOUT,
        small_timeout: RemoteStorageConfig::DEFAULT_SMALL_TIMEOUT,
--- a/libs/safekeeper_api/Cargo.toml
+++ b/libs/safekeeper_api/Cargo.toml
@@ -5,6 +5,9 @@ edition.workspace = true
 license.workspace = true

 [dependencies]
-serde.workspace = true
 const_format.workspace = true
+serde.workspace = true
+postgres_ffi.workspace = true
+pq_proto.workspace = true
+tokio.workspace = true
 utils.workspace = true
--- a/libs/safekeeper_api/src/lib.rs
+++ b/libs/safekeeper_api/src/lib.rs
@@ -1,10 +1,27 @@
 #![deny(unsafe_code)]
 #![deny(clippy::undocumented_unsafe_blocks)]
 use const_format::formatcp;
+use pq_proto::SystemId;
+use serde::{Deserialize, Serialize};

 /// Public API types
 pub mod models;

+/// Consensus logical timestamp. Note: it is a part of sk control file.
+pub type Term = u64;
+pub const INVALID_TERM: Term = 0;
+
+/// Information about Postgres. Safekeeper gets it once and then verifies all
+/// further connections from computes match. Note: it is a part of sk control
+/// file.
+#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
+pub struct ServerInfo {
+    /// Postgres server version
+    pub pg_version: u32,
+    pub system_id: SystemId,
+    pub wal_seg_size: u32,
+}
+
 pub const DEFAULT_PG_LISTEN_PORT: u16 = 5454;
 pub const DEFAULT_PG_LISTEN_ADDR: &str = formatcp!("127.0.0.1:{DEFAULT_PG_LISTEN_PORT}");

--- a/libs/safekeeper_api/src/models.rs
+++ b/libs/safekeeper_api/src/models.rs
@@ -1,10 +1,23 @@
+//! Types used in safekeeper http API. Many of them are also reused internally.
+
+use postgres_ffi::TimestampTz;
 use serde::{Deserialize, Serialize};
+use std::net::SocketAddr;
+use tokio::time::Instant;

 use utils::{
-    id::{NodeId, TenantId, TimelineId},
+    id::{NodeId, TenantId, TenantTimelineId, TimelineId},
    lsn::Lsn,
+    pageserver_feedback::PageserverFeedback,
 };

+use crate::{ServerInfo, Term};
+
+#[derive(Debug, Serialize)]
+pub struct SafekeeperStatus {
+    pub id: NodeId,
+}
+
 #[derive(Serialize, Deserialize)]
 pub struct TimelineCreateRequest {
    pub tenant_id: TenantId,
@@ -18,6 +31,161 @@ pub struct TimelineCreateRequest {
    pub local_start_lsn: Option<Lsn>,
 }

+/// Same as TermLsn, but serializes LSN using display serializer
+/// in Postgres format, i.e. 0/FFFFFFFF. Used only for the API response.
+#[derive(Debug, Clone, Copy, Serialize, Deserialize)]
+pub struct TermSwitchApiEntry {
+    pub term: Term,
+    pub lsn: Lsn,
+}
+
+/// Augment AcceptorState with last_log_term for convenience
+#[derive(Debug, Serialize, Deserialize)]
+pub struct AcceptorStateStatus {
+    pub term: Term,
+    pub epoch: Term, // aka last_log_term, old `epoch` name is left for compatibility
+    pub term_history: Vec<TermSwitchApiEntry>,
+}
+
+/// Things safekeeper should know about timeline state on peers.
+/// Used as both model and internally.
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct PeerInfo {
+    pub sk_id: NodeId,
+    pub term: Term,
+    /// Term of the last entry.
+    pub last_log_term: Term,
+    /// LSN of the last record.
+    pub flush_lsn: Lsn,
+    pub commit_lsn: Lsn,
+    /// Since which LSN safekeeper has WAL.
+    pub local_start_lsn: Lsn,
+    /// When info was received. Serde annotations are not very useful but make
+    /// the code compile -- we don't rely on this field externally.
+    #[serde(skip)]
+    #[serde(default = "Instant::now")]
+    pub ts: Instant,
+    pub pg_connstr: String,
+    pub http_connstr: String,
+}
+
+pub type FullTransactionId = u64;
+
+/// Hot standby feedback received from replica
+#[derive(Debug, Clone, Copy, Serialize, Deserialize)]
+pub struct HotStandbyFeedback {
+    pub ts: TimestampTz,
+    pub xmin: FullTransactionId,
+    pub catalog_xmin: FullTransactionId,
+}
+
+pub const INVALID_FULL_TRANSACTION_ID: FullTransactionId = 0;
+
+impl HotStandbyFeedback {
+    pub fn empty() -> HotStandbyFeedback {
+        HotStandbyFeedback {
+            ts: 0,
+            xmin: 0,
+            catalog_xmin: 0,
+        }
+    }
+}
+
+/// Standby status update
+#[derive(Debug, Clone, Copy, Serialize, Deserialize)]
+pub struct StandbyReply {
+    pub write_lsn: Lsn, // The location of the last WAL byte + 1 received and written to disk in the standby.
+    pub flush_lsn: Lsn, // The location of the last WAL byte + 1 flushed to disk in the standby.
+    pub apply_lsn: Lsn, // The location of the last WAL byte + 1 applied in the standby.
+    pub reply_ts: TimestampTz, // The client's system clock at the time of transmission, as microseconds since midnight on 2000-01-01.
+    pub reply_requested: bool,
+}
+
+impl StandbyReply {
+    pub fn empty() -> Self {
+        StandbyReply {
+            write_lsn: Lsn::INVALID,
+            flush_lsn: Lsn::INVALID,
+            apply_lsn: Lsn::INVALID,
+            reply_ts: 0,
+            reply_requested: false,
+        }
+    }
+}
+
+#[derive(Debug, Clone, Copy, Serialize, Deserialize)]
+pub struct StandbyFeedback {
+    pub reply: StandbyReply,
+    pub hs_feedback: HotStandbyFeedback,
+}
+
+impl StandbyFeedback {
+    pub fn empty() -> Self {
+        StandbyFeedback {
+            reply: StandbyReply::empty(),
+            hs_feedback: HotStandbyFeedback::empty(),
+        }
+    }
+}
+
+/// Receiver is either pageserver or regular standby, which have different
+/// feedbacks.
+/// Used as both model and internally.
+#[derive(Debug, Clone, Copy, Serialize, Deserialize)]
+pub enum ReplicationFeedback {
+    Pageserver(PageserverFeedback),
+    Standby(StandbyFeedback),
+}
+
+/// Uniquely identifies a WAL service connection. Logged in spans for
+/// observability.
+pub type ConnectionId = u32;
+
+/// Serialize is used only for json'ing in API response. Also used internally.
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct WalSenderState {
+    pub ttid: TenantTimelineId,
+    pub addr: SocketAddr,
+    pub conn_id: ConnectionId,
+    // postgres application_name
+    pub appname: Option<String>,
+    pub feedback: ReplicationFeedback,
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct WalReceiverState {
+    /// None means it is recovery initiated by us (this safekeeper).
+    pub conn_id: Option<ConnectionId>,
+    pub status: WalReceiverStatus,
+}
+
+/// Walreceiver status. Currently only whether it passed voting stage and
+/// started receiving the stream, but it is easy to add more if needed.
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub enum WalReceiverStatus {
+    Voting,
+    Streaming,
+}
+
+/// Info about timeline on safekeeper ready for reporting.
+#[derive(Debug, Serialize, Deserialize)]
+pub struct TimelineStatus {
+    pub tenant_id: TenantId,
+    pub timeline_id: TimelineId,
+    pub acceptor_state: AcceptorStateStatus,
+    pub pg_info: ServerInfo,
+    pub flush_lsn: Lsn,
+    pub timeline_start_lsn: Lsn,
+    pub local_start_lsn: Lsn,
+    pub commit_lsn: Lsn,
+    pub backup_lsn: Lsn,
+    pub peer_horizon_lsn: Lsn,
+    pub remote_consistent_lsn: Lsn,
+    pub peers: Vec<PeerInfo>,
+    pub walsenders: Vec<WalSenderState>,
+    pub walreceivers: Vec<WalReceiverState>,
+}
+
 fn lsn_invalid() -> Lsn {
    Lsn::INVALID
 }
--- a/libs/utils/Cargo.toml
+++ b/libs/utils/Cargo.toml
@@ -15,17 +15,20 @@ arc-swap.workspace = true
 sentry.workspace = true
 async-compression.workspace = true
 anyhow.workspace = true
+backtrace.workspace = true
 bincode.workspace = true
 bytes.workspace = true
 camino.workspace = true
 chrono.workspace = true
 diatomic-waker.workspace = true
+flate2.workspace = true
 git-version.workspace = true
 hex = { workspace = true, features = ["serde"] }
 humantime.workspace = true
 hyper0 = { workspace = true, features = ["full"] }
+itertools.workspace = true
 fail.workspace = true
-futures = { workspace = true}
+futures = { workspace = true }
 jemalloc_pprof.workspace = true
 jsonwebtoken.workspace = true
 nix.workspace = true
--- a/libs/utils/src/failpoint_support.rs
+++ b/libs/utils/src/failpoint_support.rs
@@ -9,7 +9,7 @@ use serde::{Deserialize, Serialize};
 use tokio_util::sync::CancellationToken;
 use tracing::*;

-/// Declare a failpoint that can use the `pause` failpoint action.
+/// Declare a failpoint that can use to `pause` failpoint action.
 /// We don't want to block the executor thread, hence, spawn_blocking + await.
 #[macro_export]
 macro_rules! pausable_failpoint {
@@ -181,7 +181,7 @@ pub async fn failpoints_handler(
 ) -> Result<Response<Body>, ApiError> {
    if !fail::has_failpoints() {
        return Err(ApiError::BadRequest(anyhow::anyhow!(
-            "Cannot manage failpoints because storage was compiled without failpoints support"
+            "Cannot manage failpoints because neon was compiled without failpoints support"
        )));
    }

--- a/libs/utils/src/http/endpoint.rs
+++ b/libs/utils/src/http/endpoint.rs
@@ -1,15 +1,22 @@
 use crate::auth::{AuthError, Claims, SwappableJwtAuth};
 use crate::http::error::{api_error_handler, route_error_handler, ApiError};
 use crate::http::request::{get_query_param, parse_query_param};
+use crate::pprof;
+use ::pprof::protos::Message as _;
+use ::pprof::ProfilerGuardBuilder;
 use anyhow::{anyhow, Context};
+use bytes::{Bytes, BytesMut};
 use hyper::header::{HeaderName, AUTHORIZATION, CONTENT_DISPOSITION};
 use hyper::http::HeaderValue;
 use hyper::Method;
 use hyper::{header::CONTENT_TYPE, Body, Request, Response};
 use metrics::{register_int_counter, Encoder, IntCounter, TextEncoder};
 use once_cell::sync::Lazy;
+use regex::Regex;
 use routerify::ext::RequestExt;
 use routerify::{Middleware, RequestInfo, Router, RouterBuilder};
+use tokio::sync::{mpsc, Mutex};
+use tokio_stream::wrappers::ReceiverStream;
 use tokio_util::io::ReaderStream;
 use tracing::{debug, info, info_span, warn, Instrument};

@@ -18,11 +25,6 @@ use std::io::Write as _;
 use std::str::FromStr;
 use std::time::Duration;

-use bytes::{Bytes, BytesMut};
-use pprof::protos::Message as _;
-use tokio::sync::{mpsc, Mutex};
-use tokio_stream::wrappers::ReceiverStream;
-
 static SERVE_METRICS_COUNT: Lazy<IntCounter> = Lazy::new(|| {
    register_int_counter!(
        "libmetrics_metric_handler_requests_total",
@@ -365,7 +367,7 @@ pub async fn profile_cpu_handler(req: Request<Body>) -> Result<Response<Body>, A

    // Take the profile.
    let report = tokio::task::spawn_blocking(move || {
-        let guard = pprof::ProfilerGuardBuilder::default()
+        let guard = ProfilerGuardBuilder::default()
            .frequency(frequency_hz)
            .blocklist(&["libc", "libgcc", "pthread", "vdso"])
            .build()?;
@@ -457,10 +459,34 @@ pub async fn profile_heap_handler(req: Request<Body>) -> Result<Response<Body>,
        }

        Format::Pprof => {
-            let data = tokio::task::spawn_blocking(move || prof_ctl.dump_pprof())
-                .await
-                .map_err(|join_err| ApiError::InternalServerError(join_err.into()))?
-                .map_err(ApiError::InternalServerError)?;
+            let data = tokio::task::spawn_blocking(move || {
+                let bytes = prof_ctl.dump_pprof()?;
+                // Symbolize the profile.
+                // TODO: consider moving this upstream to jemalloc_pprof and avoiding the
+                // serialization roundtrip.
+                static STRIP_FUNCTIONS: Lazy<Vec<(Regex, bool)>> = Lazy::new(|| {
+                    // Functions to strip from profiles. If true, also remove child frames.
+                    vec![
+                        (Regex::new("^__rust").unwrap(), false),
+                        (Regex::new("^_start$").unwrap(), false),
+                        (Regex::new("^irallocx_prof").unwrap(), true),
+                        (Regex::new("^prof_alloc_prep").unwrap(), true),
+                        (Regex::new("^std::rt::lang_start").unwrap(), false),
+                        (Regex::new("^std::sys::backtrace::__rust").unwrap(), false),
+                    ]
+                });
+                let profile = pprof::decode(&bytes)?;
+                let profile = pprof::symbolize(profile)?;
+                let profile = pprof::strip_locations(
+                    profile,
+                    &["libc", "libgcc", "pthread", "vdso"],
+                    &STRIP_FUNCTIONS,
+                );
+                pprof::encode(&profile)
+            })
+            .await
+            .map_err(|join_err| ApiError::InternalServerError(join_err.into()))?
+            .map_err(ApiError::InternalServerError)?;
            Response::builder()
                .status(200)
                .header(CONTENT_TYPE, "application/octet-stream")
--- a/libs/utils/src/lib.rs
+++ b/libs/utils/src/lib.rs
@@ -96,6 +96,8 @@ pub mod circuit_breaker;

 pub mod try_rcu;

+pub mod pprof;
+
 // Re-export used in macro. Avoids adding git-version as dep in target crates.
 #[doc(hidden)]
 pub use git_version;
--- a/libs/utils/src/pprof.rs
+++ b/libs/utils/src/pprof.rs
@@ -0,0 +1,190 @@
+use flate2::write::{GzDecoder, GzEncoder};
+use flate2::Compression;
+use itertools::Itertools as _;
+use once_cell::sync::Lazy;
+use pprof::protos::{Function, Line, Message as _, Profile};
+use regex::Regex;
+
+use std::borrow::Cow;
+use std::collections::{HashMap, HashSet};
+use std::ffi::c_void;
+use std::io::Write as _;
+
+/// Decodes a gzip-compressed Protobuf-encoded pprof profile.
+pub fn decode(bytes: &[u8]) -> anyhow::Result<Profile> {
+    let mut gz = GzDecoder::new(Vec::new());
+    gz.write_all(bytes)?;
+    Ok(Profile::parse_from_bytes(&gz.finish()?)?)
+}
+
+/// Encodes a pprof profile as gzip-compressed Protobuf.
+pub fn encode(profile: &Profile) -> anyhow::Result<Vec<u8>> {
+    let mut gz = GzEncoder::new(Vec::new(), Compression::default());
+    profile.write_to_writer(&mut gz)?;
+    Ok(gz.finish()?)
+}
+
+/// Symbolizes a pprof profile using the current binary.
+pub fn symbolize(mut profile: Profile) -> anyhow::Result<Profile> {
+    if !profile.function.is_empty() {
+        return Ok(profile); // already symbolized
+    }
+
+    // Collect function names.
+    let mut functions: HashMap<String, Function> = HashMap::new();
+    let mut strings: HashMap<String, i64> = profile
+        .string_table
+        .into_iter()
+        .enumerate()
+        .map(|(i, s)| (s, i as i64))
+        .collect();
+
+    // Helper to look up or register a string.
+    let mut string_id = |s: &str| -> i64 {
+        // Don't use .entry() to avoid unnecessary allocations.
+        if let Some(id) = strings.get(s) {
+            return *id;
+        }
+        let id = strings.len() as i64;
+        strings.insert(s.to_string(), id);
+        id
+    };
+
+    for loc in &mut profile.location {
+        if !loc.line.is_empty() {
+            continue;
+        }
+
+        // Resolve the line and function for each location.
+        backtrace::resolve(loc.address as *mut c_void, |symbol| {
+            let Some(symname) = symbol.name() else {
+                return;
+            };
+            let mut name = symname.to_string();
+
+            // Strip the Rust monomorphization suffix from the symbol name.
+            static SUFFIX_REGEX: Lazy<Regex> =
+                Lazy::new(|| Regex::new("::h[0-9a-f]{16}$").expect("invalid regex"));
+            if let Some(m) = SUFFIX_REGEX.find(&name) {
+                name.truncate(m.start());
+            }
+
+            let function_id = match functions.get(&name) {
+                Some(function) => function.id,
+                None => {
+                    let id = functions.len() as u64 + 1;
+                    let system_name = String::from_utf8_lossy(symname.as_bytes());
+                    let filename = symbol
+                        .filename()
+                        .map(|path| path.to_string_lossy())
+                        .unwrap_or(Cow::Borrowed(""));
+                    let function = Function {
+                        id,
+                        name: string_id(&name),
+                        system_name: string_id(&system_name),
+                        filename: string_id(&filename),
+                        ..Default::default()
+                    };
+                    functions.insert(name, function);
+                    id
+                }
+            };
+            loc.line.push(Line {
+                function_id,
+                line: symbol.lineno().unwrap_or(0) as i64,
+                ..Default::default()
+            });
+        });
+    }
+
+    // Store the resolved functions, and mark the mapping as resolved.
+    profile.function = functions.into_values().sorted_by_key(|f| f.id).collect();
+    profile.string_table = strings
+        .into_iter()
+        .sorted_by_key(|(_, i)| *i)
+        .map(|(s, _)| s)
+        .collect();
+
+    for mapping in &mut profile.mapping {
+        mapping.has_functions = true;
+        mapping.has_filenames = true;
+    }
+
+    Ok(profile)
+}
+
+/// Strips locations (stack frames) matching the given mappings (substring) or function names
+/// (regex). The function bool specifies whether child frames should be stripped as well.
+///
+/// The string definitions are left behind in the profile for simplicity, to avoid rewriting all
+/// string references.
+pub fn strip_locations(
+    mut profile: Profile,
+    mappings: &[&str],
+    functions: &[(Regex, bool)],
+) -> Profile {
+    // Strip mappings.
+    let mut strip_mappings: HashSet<u64> = HashSet::new();
+
+    profile.mapping.retain(|mapping| {
+        let Some(name) = profile.string_table.get(mapping.filename as usize) else {
+            return true;
+        };
+        if mappings.iter().any(|substr| name.contains(substr)) {
+            strip_mappings.insert(mapping.id);
+            return false;
+        }
+        true
+    });
+
+    // Strip functions.
+    let mut strip_functions: HashMap<u64, bool> = HashMap::new();
+
+    profile.function.retain(|function| {
+        let Some(name) = profile.string_table.get(function.name as usize) else {
+            return true;
+        };
+        for (regex, strip_children) in functions {
+            if regex.is_match(name) {
+                strip_functions.insert(function.id, *strip_children);
+                return false;
+            }
+        }
+        true
+    });
+
+    // Strip locations. The bool specifies whether child frames should be stripped too.
+    let mut strip_locations: HashMap<u64, bool> = HashMap::new();
+
+    profile.location.retain(|location| {
+        for line in &location.line {
+            if let Some(strip_children) = strip_functions.get(&line.function_id) {
+                strip_locations.insert(location.id, *strip_children);
+                return false;
+            }
+        }
+        if strip_mappings.contains(&location.mapping_id) {
+            strip_locations.insert(location.id, false);
+            return false;
+        }
+        true
+    });
+
+    // Strip sample locations.
+    for sample in &mut profile.sample {
+        // First, find the uppermost function with child removal and truncate the stack.
+        if let Some(truncate) = sample
+            .location_id
+            .iter()
+            .rposition(|id| strip_locations.get(id) == Some(&true))
+        {
+            sample.location_id.drain(..=truncate);
+        }
+        // Next, strip any individual frames without child removal.
+        sample
+            .location_id
+            .retain(|id| !strip_locations.contains_key(id));
+    }
+
+    profile
+}
--- a/pageserver/compaction/src/compact_tiered.rs
+++ b/pageserver/compaction/src/compact_tiered.rs
@@ -272,7 +272,7 @@ struct CompactionJob<E: CompactionJobExecutor> {
    completed: bool,
 }

-impl<'a, E> LevelCompactionState<'a, E>
+impl<E> LevelCompactionState<'_, E>
 where
    E: CompactionJobExecutor,
 {
--- a/pageserver/compaction/src/identify_levels.rs
+++ b/pageserver/compaction/src/identify_levels.rs
@@ -224,9 +224,8 @@ impl<L> Level<L> {
            }

            // recalculate depth if this was the last event at this point
-            let more_events_at_this_key = events_iter
-                .peek()
-                .map_or(false, |next_e| next_e.key == e.key);
+            let more_events_at_this_key =
+                events_iter.peek().is_some_and(|next_e| next_e.key == e.key);
            if !more_events_at_this_key {
                let mut active_depth = 0;
                for (_end_lsn, is_image, _idx) in active_set.iter().rev() {
--- a/pageserver/compaction/src/interface.rs
+++ b/pageserver/compaction/src/interface.rs
@@ -148,7 +148,7 @@ pub trait CompactionDeltaLayer<E: CompactionJobExecutor + ?Sized>: CompactionLay
        Self: 'a;

    /// Return all keys in this delta layer.
-    fn load_keys<'a>(
+    fn load_keys(
        &self,
        ctx: &E::RequestContext,
    ) -> impl Future<Output = anyhow::Result<Vec<Self::DeltaEntry<'_>>>> + Send;
--- a/pageserver/compaction/src/simulator.rs
+++ b/pageserver/compaction/src/simulator.rs
@@ -143,7 +143,7 @@ impl interface::CompactionLayer<Key> for Arc<MockDeltaLayer> {
 impl interface::CompactionDeltaLayer<MockTimeline> for Arc<MockDeltaLayer> {
    type DeltaEntry<'a> = MockRecord;

-    async fn load_keys<'a>(&self, _ctx: &MockRequestContext) -> anyhow::Result<Vec<MockRecord>> {
+    async fn load_keys(&self, _ctx: &MockRequestContext) -> anyhow::Result<Vec<MockRecord>> {
        Ok(self.records.clone())
    }
 }
--- a/pageserver/src/basebackup.rs
+++ b/pageserver/src/basebackup.rs
@@ -248,7 +248,7 @@ where
    }
 }

-impl<'a, W> Basebackup<'a, W>
+impl<W> Basebackup<'_, W>
 where
    W: AsyncWrite + Send + Sync + Unpin,
 {
--- a/pageserver/src/bin/pageserver.rs
+++ b/pageserver/src/bin/pageserver.rs
@@ -53,10 +53,12 @@ project_build_tag!(BUILD_TAG);
 #[global_allocator]
 static GLOBAL: tikv_jemallocator::Jemalloc = tikv_jemallocator::Jemalloc;

-/// Configure jemalloc to sample allocations for profiles every 1 MB (1 << 20).
-#[allow(non_upper_case_globals)]
-#[export_name = "malloc_conf"]
-pub static malloc_conf: &[u8] = b"prof:true,prof_active:true,lg_prof_sample:20\0";
+// Configure jemalloc to sample allocations for profiles every 1 MB (1 << 20).
+// TODO: disabled because concurrent CPU profiles cause seg faults. See:
+// https://github.com/neondatabase/neon/issues/10225.
+//#[allow(non_upper_case_globals)]
+//#[export_name = "malloc_conf"]
+//pub static malloc_conf: &[u8] = b"prof:true,prof_active:true,lg_prof_sample:20\0";

 const PID_FILE_NAME: &str = "pageserver.pid";

--- a/pageserver/src/http/routes.rs
+++ b/pageserver/src/http/routes.rs
@@ -97,8 +97,8 @@ use crate::tenant::{LogicalSizeCalculationCause, PageReconstructError};
 use crate::DEFAULT_PG_VERSION;
 use crate::{disk_usage_eviction_task, tenant};
 use pageserver_api::models::{
-    StatusResponse, TenantConfigRequest, TenantInfo, TimelineCreateRequest, TimelineGcRequest,
-    TimelineInfo,
+    CompactInfoResponse, StatusResponse, TenantConfigRequest, TenantInfo, TimelineCreateRequest,
+    TimelineGcRequest, TimelineInfo,
 };
 use utils::{
    auth::SwappableJwtAuth,
@@ -2039,6 +2039,34 @@ async fn timeline_cancel_compact_handler(
    .await
 }

+// Get compact info of a timeline
+async fn timeline_compact_info_handler(
+    request: Request<Body>,
+    _cancel: CancellationToken,
+) -> Result<Response<Body>, ApiError> {
+    let tenant_shard_id: TenantShardId = parse_request_param(&request, "tenant_shard_id")?;
+    let timeline_id: TimelineId = parse_request_param(&request, "timeline_id")?;
+    check_permission(&request, Some(tenant_shard_id.tenant_id))?;
+    let state = get_state(&request);
+    async {
+        let tenant = state
+            .tenant_manager
+            .get_attached_tenant_shard(tenant_shard_id)?;
+        let res = tenant.get_scheduled_compaction_tasks(timeline_id);
+        let mut resp = Vec::new();
+        for item in res {
+            resp.push(CompactInfoResponse {
+                compact_key_range: item.compact_key_range,
+                compact_lsn_range: item.compact_lsn_range,
+                sub_compaction: item.sub_compaction,
+            });
+        }
+        json_response(StatusCode::OK, resp)
+    }
+    .instrument(info_span!("timeline_compact_info", tenant_id = %tenant_shard_id.tenant_id, shard_id = %tenant_shard_id.shard_slug(), %timeline_id))
+    .await
+}
+
 // Run compaction immediately on given timeline.
 async fn timeline_compact_handler(
    mut request: Request<Body>,
@@ -3400,6 +3428,10 @@ pub fn make_router(
            "/v1/tenant/:tenant_shard_id/timeline/:timeline_id/do_gc",
            |r| api_handler(r, timeline_gc_handler),
        )
+        .get(
+            "/v1/tenant/:tenant_shard_id/timeline/:timeline_id/compact",
+            |r| api_handler(r, timeline_compact_info_handler),
+        )
        .put(
            "/v1/tenant/:tenant_shard_id/timeline/:timeline_id/compact",
            |r| api_handler(r, timeline_compact_handler),
--- a/pageserver/src/pgdatadir_mapping.rs
+++ b/pageserver/src/pgdatadir_mapping.rs
@@ -1242,7 +1242,7 @@ pub struct DatadirModification<'a> {
    pending_metadata_bytes: usize,
 }

-impl<'a> DatadirModification<'a> {
+impl DatadirModification<'_> {
    // When a DatadirModification is committed, we do a monolithic serialization of all its contents.  WAL records can
    // contain multiple pages, so the pageserver's record-based batch size isn't sufficient to bound this allocation: we
    // additionally specify a limit on how much payload a DatadirModification may contain before it should be committed.
@@ -1263,7 +1263,7 @@ impl<'a> DatadirModification<'a> {
    pub(crate) fn has_dirty_data(&self) -> bool {
        self.pending_data_batch
            .as_ref()
-            .map_or(false, |b| b.has_data())
+            .is_some_and(|b| b.has_data())
    }

    /// Set the current lsn
@@ -1319,18 +1319,23 @@ impl<'a> DatadirModification<'a> {

        let buf: Bytes = SlruSegmentDirectory::ser(&SlruSegmentDirectory::default())?.into();
        let empty_dir = Value::Image(buf);
-        self.put(slru_dir_to_key(SlruKind::Clog), empty_dir.clone());
-        self.pending_directory_entries
-            .push((DirectoryKind::SlruSegment(SlruKind::Clog), 0));
-        self.put(
-            slru_dir_to_key(SlruKind::MultiXactMembers),
-            empty_dir.clone(),
-        );
-        self.pending_directory_entries
-            .push((DirectoryKind::SlruSegment(SlruKind::Clog), 0));
-        self.put(slru_dir_to_key(SlruKind::MultiXactOffsets), empty_dir);
-        self.pending_directory_entries
-            .push((DirectoryKind::SlruSegment(SlruKind::MultiXactOffsets), 0));
+
+        // Initialize SLRUs on shard 0 only: creating these on other shards would be
+        // harmless but they'd just be dropped on later compaction.
+        if self.tline.tenant_shard_id.is_shard_zero() {
+            self.put(slru_dir_to_key(SlruKind::Clog), empty_dir.clone());
+            self.pending_directory_entries
+                .push((DirectoryKind::SlruSegment(SlruKind::Clog), 0));
+            self.put(
+                slru_dir_to_key(SlruKind::MultiXactMembers),
+                empty_dir.clone(),
+            );
+            self.pending_directory_entries
+                .push((DirectoryKind::SlruSegment(SlruKind::Clog), 0));
+            self.put(slru_dir_to_key(SlruKind::MultiXactOffsets), empty_dir);
+            self.pending_directory_entries
+                .push((DirectoryKind::SlruSegment(SlruKind::MultiXactOffsets), 0));
+        }

        Ok(())
    }
@@ -2225,7 +2230,7 @@ impl<'a> DatadirModification<'a> {
                assert!(!self
                    .pending_data_batch
                    .as_ref()
-                    .map_or(false, |b| b.updates_key(&key)));
+                    .is_some_and(|b| b.updates_key(&key)));
            }
        }

@@ -2294,7 +2299,7 @@ pub enum Version<'a> {
    Modified(&'a DatadirModification<'a>),
 }

-impl<'a> Version<'a> {
+impl Version<'_> {
    async fn get(
        &self,
        timeline: &Timeline,
--- a/pageserver/src/tenant.rs
+++ b/pageserver/src/tenant.rs
@@ -2604,9 +2604,15 @@ impl Tenant {
                WaitCompletionError::NotInitialized(
                    e, // If the queue is already stopped, it's a shutdown error.
                ) if e.is_stopping() => CreateTimelineError::ShuttingDown,
-                e => CreateTimelineError::Other(e.into()),
-            })
-            .context("wait for timeline initial uploads to complete")?;
+                WaitCompletionError::NotInitialized(_) => {
+                    // This is a bug: we should never try to wait for uploads before initializing the timeline
+                    debug_assert!(false);
+                    CreateTimelineError::Other(anyhow::anyhow!("timeline not initialized"))
+                }
+                WaitCompletionError::UploadQueueShutDownOrStopped => {
+                    CreateTimelineError::ShuttingDown
+                }
+            })?;

        // The creating task is responsible for activating the timeline.
        // We do this after `wait_completion()` so that we don't spin up tasks that start
@@ -3122,6 +3128,23 @@ impl Tenant {
        }
    }

+    pub(crate) fn get_scheduled_compaction_tasks(
+        &self,
+        timeline_id: TimelineId,
+    ) -> Vec<CompactOptions> {
+        use itertools::Itertools;
+        let guard = self.scheduled_compaction_tasks.lock().unwrap();
+        guard
+            .get(&timeline_id)
+            .map(|tline_pending_tasks| {
+                tline_pending_tasks
+                    .iter()
+                    .map(|x| x.options.clone())
+                    .collect_vec()
+            })
+            .unwrap_or_default()
+    }
+
    /// Schedule a compaction task for a timeline.
    pub(crate) async fn schedule_compaction(
        &self,
@@ -4465,13 +4488,17 @@ impl Tenant {
        let mut gc_cutoffs: HashMap<TimelineId, GcCutoffs> =
            HashMap::with_capacity(timelines.len());

+        // Ensures all timelines use the same start time when computing the time cutoff.
+        let now_ts_for_pitr_calc = SystemTime::now();
        for timeline in timelines.iter() {
            let cutoff = timeline
                .get_last_record_lsn()
                .checked_sub(horizon)
                .unwrap_or(Lsn(0));

-            let cutoffs = timeline.find_gc_cutoffs(cutoff, pitr, cancel, ctx).await?;
+            let cutoffs = timeline
+                .find_gc_cutoffs(now_ts_for_pitr_calc, cutoff, pitr, cancel, ctx)
+                .await?;
            let old = gc_cutoffs.insert(timeline.timeline_id, cutoffs);
            assert!(old.is_none());
        }
@@ -5759,13 +5786,13 @@ mod tests {
    use timeline::{CompactOptions, DeltaLayerTestDesc};
    use utils::id::TenantId;

+    #[cfg(feature = "testing")]
+    use models::CompactLsnRange;
    #[cfg(feature = "testing")]
    use pageserver_api::record::NeonWalRecord;
    #[cfg(feature = "testing")]
    use timeline::compaction::{KeyHistoryRetention, KeyLogAtLsn};
    #[cfg(feature = "testing")]
-    use timeline::CompactLsnRange;
-    #[cfg(feature = "testing")]
    use timeline::GcInfo;

    static TEST_KEY: Lazy<Key> =
@@ -9634,7 +9661,7 @@ mod tests {
    #[cfg(feature = "testing")]
    #[tokio::test]
    async fn test_simple_bottom_most_compaction_on_branch() -> anyhow::Result<()> {
-        use timeline::CompactLsnRange;
+        use models::CompactLsnRange;

        let harness = TenantHarness::create("test_simple_bottom_most_compaction_on_branch").await?;
        let (tenant, ctx) = harness.load().await;
--- a/pageserver/src/tenant/blob_io.rs
+++ b/pageserver/src/tenant/blob_io.rs
@@ -35,7 +35,7 @@ pub struct CompressionInfo {
    pub compressed_size: Option<usize>,
 }

-impl<'a> BlockCursor<'a> {
+impl BlockCursor<'_> {
    /// Read a blob into a new buffer.
    pub async fn read_blob(
        &self,
--- a/pageserver/src/tenant/block_io.rs
+++ b/pageserver/src/tenant/block_io.rs
@@ -89,7 +89,7 @@ pub(crate) enum BlockReaderRef<'a> {
    VirtualFile(&'a VirtualFile),
 }

-impl<'a> BlockReaderRef<'a> {
+impl BlockReaderRef<'_> {
    #[inline(always)]
    async fn read_blk(
        &self,
--- a/pageserver/src/tenant/checks.rs
+++ b/pageserver/src/tenant/checks.rs
@@ -1,12 +1,15 @@
 use std::collections::BTreeSet;

 use itertools::Itertools;
+use pageserver_compaction::helpers::overlaps_with;

 use super::storage_layer::LayerName;

 /// Checks whether a layer map is valid (i.e., is a valid result of the current compaction algorithm if nothing goes wrong).
 ///
-/// The function checks if we can split the LSN range of a delta layer only at the LSNs of the delta layers. For example,
+/// The function implements a fast path check and a slow path check.
+///
+/// The fast path checks if we can split the LSN range of a delta layer only at the LSNs of the delta layers. For example,
 ///
 /// ```plain
 /// |       |                 |       |
@@ -25,31 +28,47 @@ use super::storage_layer::LayerName;
 /// |       |    |   4   |    |       |
 ///
 /// If layer 2 and 4 contain the same single key, this is also a valid layer map.
+///
+/// However, if a partial compaction is still going on, it is possible that we get a layer map not satisfying the above condition.
+/// Therefore, we fallback to simply check if any of the two delta layers overlap. (See "A slow path...")
 pub fn check_valid_layermap(metadata: &[LayerName]) -> Option<String> {
    let mut lsn_split_point = BTreeSet::new(); // TODO: use a better data structure (range tree / range set?)
    let mut all_delta_layers = Vec::new();
    for name in metadata {
        if let LayerName::Delta(layer) = name {
-            if layer.key_range.start.next() != layer.key_range.end {
-                all_delta_layers.push(layer.clone());
-            }
+            all_delta_layers.push(layer.clone());
        }
    }
    for layer in &all_delta_layers {
-        let lsn_range = &layer.lsn_range;
-        lsn_split_point.insert(lsn_range.start);
-        lsn_split_point.insert(lsn_range.end);
+        if layer.key_range.start.next() != layer.key_range.end {
+            let lsn_range = &layer.lsn_range;
+            lsn_split_point.insert(lsn_range.start);
+            lsn_split_point.insert(lsn_range.end);
+        }
    }
-    for layer in &all_delta_layers {
+    for (idx, layer) in all_delta_layers.iter().enumerate() {
+        if layer.key_range.start.next() == layer.key_range.end {
+            continue;
+        }
        let lsn_range = layer.lsn_range.clone();
        let intersects = lsn_split_point.range(lsn_range).collect_vec();
        if intersects.len() > 1 {
-            let err = format!(
-                "layer violates the layer map LSN split assumption: layer {} intersects with LSN [{}]",
-                layer,
-                intersects.into_iter().map(|lsn| lsn.to_string()).join(", ")
-            );
-            return Some(err);
+            // A slow path to check if the layer intersects with any other delta layer.
+            for (other_idx, other_layer) in all_delta_layers.iter().enumerate() {
+                if other_idx == idx {
+                    // do not check self intersects with self
+                    continue;
+                }
+                if overlaps_with(&layer.lsn_range, &other_layer.lsn_range)
+                    && overlaps_with(&layer.key_range, &other_layer.key_range)
+                {
+                    let err = format!(
+                            "layer violates the layer map LSN split assumption: layer {} intersects with layer {}",
+                            layer, other_layer
+                        );
+                    return Some(err);
+                }
+            }
        }
    }
    None
--- a/Show More
+++ b/Show More