docker compose with compute-node build commands

## Problem

close https://github.com/neondatabase/neon/issues/10208
part of #9114 

## Summary of changes

* Ensure remote `latest_gc_cutoff` is up-to-date before removing any
files for gc-compaction.

Signed-off-by: Alex Chi Z <chi@neon.tech>

.github/actionlint.yml

@@ -23,3 +23,5 @@ config-variables:
   - BENCHMARK_INGEST_TARGET_PROJECTID
   - PGREGRESS_PG16_PROJECT_ID
   - PGREGRESS_PG17_PROJECT_ID
+  - SLACK_ON_CALL_QA_STAGING_STREAM
+  - DEV_AWS_OIDC_ROLE_MANAGE_BENCHMARK_EC2_VMS_ARN

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

@@ -7,10 +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

.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

.github/actions/download/action.yml

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

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

@@ -48,10 +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"
@@ -62,6 +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 }}
 
     - name: Download Neon binaries for the previous release
       if: inputs.build_type != 'remote'
@@ -70,6 +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 }}
 
     - name: Download compatibility snapshot
       if: inputs.build_type != 'remote'
@@ -81,6 +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 }}
 
     - name: Checkout
       if: inputs.needs_postgres_source == 'true'
@@ -218,17 +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 }}
 
-    - 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 }}

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

@@ -14,9 +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 }}
 
     - name: Upload coverage data
       uses: ./.github/actions/upload
       with:
         name: coverage-data-artifact
         path: /tmp/coverage
+        aws-oicd-role-arn: ${{ inputs.aws-oicd-role-arn }}

.github/actions/upload/action.yml

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

.github/workflows/_benchmarking_preparation.yml

@@ -70,6 +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 }}
 
     # we create a table that has one row for each database that we want to restore with the status whether the restore is done
     - name: Create benchmark_restore_status table if it does not exist

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

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

.github/workflows/benchmarking.yml

@@ -105,6 +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 }}
 
     - name: Create Neon Project
       id: create-neon-project
@@ -122,7 +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
@@ -152,7 +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: ${{ github.event.schedule && failure() }}
@@ -204,6 +205,7 @@ jobs:
         name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
         path: /tmp/neon/
         prefix: latest
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
     - name: Run Logical Replication benchmarks
       uses: ./.github/actions/run-python-test-set
@@ -214,7 +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 }}"
@@ -231,7 +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 }}"
@@ -243,7 +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 }}
 
@@ -306,6 +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": '"$runner_azure"',   "image": "neondatabase/build-tools:pinned-bookworm" },
@@ -405,9 +408,10 @@ jobs:
         name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
         path: /tmp/neon/
         prefix: latest
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
     - 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:
@@ -426,7 +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)
@@ -443,6 +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:
@@ -452,7 +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 }}"
@@ -467,7 +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 }}"
@@ -482,7 +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 }}"
@@ -500,7 +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() }}
@@ -611,7 +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 }}"
@@ -626,7 +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 }}"
@@ -637,7 +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: ${{ github.event.schedule && failure() }}
@@ -708,6 +732,7 @@ jobs:
         name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
         path: /tmp/neon/
         prefix: latest
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
     - name: Set up Connection String
       id: set-up-connstr
@@ -739,7 +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 }}"
@@ -753,7 +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: ${{ github.event.schedule && failure() }}
@@ -818,6 +843,7 @@ jobs:
         name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
         path: /tmp/neon/
         prefix: latest
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
     - name: Get Connstring Secret Name
       run: |
@@ -856,7 +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 }}"
@@ -868,7 +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: ${{ github.event.schedule && failure() }}
@@ -926,6 +952,7 @@ jobs:
         name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
         path: /tmp/neon/
         prefix: latest
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
     - name: Set up Connection String
       id: set-up-connstr
@@ -957,7 +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 }}"
@@ -968,7 +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() }}

.github/workflows/build_and_test.yml

@@ -21,8 +21,6 @@ concurrency:
 env:
   RUST_BACKTRACE: 1
   COPT: '-Werror'
-  AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_DEV }}
-  AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_KEY_DEV }}
   # A concurrency group that we use for e2e-tests runs, matches `concurrency.group` above with `github.repository` as a prefix
   E2E_CONCURRENCY_GROUP: ${{ github.repository }}-e2e-tests-${{ github.ref_name }}-${{ github.ref_name == 'main' && github.sha || 'anysha' }}
 
@@ -255,15 +253,15 @@ jobs:
       build-tools-image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
       build-tag: ${{ needs.tag.outputs.build-tag }}
       build-type: ${{ matrix.build-type }}
-      # Run tests on all Postgres versions in release builds and only on the latest version in debug builds
-      # run without LFC on v17 release only
+      # Run tests on all Postgres versions in release builds and only on the latest version in debug builds.
+      # Run without LFC on v17 release and debug builds only. For all the other cases LFC is enabled.
       test-cfg: |
-        ${{ matrix.build-type == 'release' && '[{"pg_version":"v14", "lfc_state": "without-lfc"},
-                                                {"pg_version":"v15", "lfc_state": "without-lfc"},
-                                                {"pg_version":"v16", "lfc_state": "without-lfc"},
-                                                {"pg_version":"v17", "lfc_state": "without-lfc"},
-                                                {"pg_version":"v17", "lfc_state": "with-lfc"}]'
-                                           || '[{"pg_version":"v17", "lfc_state": "without-lfc"}]' }}
+        ${{ matrix.build-type == 'release' && '[{"pg_version":"v14", "lfc_state": "with-lfc"},
+                                                {"pg_version":"v15", "lfc_state": "with-lfc"},
+                                                {"pg_version":"v16", "lfc_state": "with-lfc"},
+                                                {"pg_version":"v17", "lfc_state": "with-lfc"},
+                                                {"pg_version":"v17", "lfc_state": "without-lfc"}]'
+                                           || '[{"pg_version":"v17", "lfc_state": "without-lfc" }]' }}
     secrets: inherit
 
   # Keep `benchmarks` job outside of `build-and-test-locally` workflow to make job failures non-blocking
@@ -305,6 +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
@@ -333,6 +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 }}"
@@ -345,6 +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:
@@ -360,6 +369,11 @@ jobs:
   create-test-report:
     needs: [ check-permissions, build-and-test-locally, coverage-report, build-build-tools-image, benchmarks ]
     if: ${{ !cancelled() && contains(fromJSON('["skipped", "success"]'), needs.check-permissions.result) }}
+    permissions:
+      id-token: write # aws-actions/configure-aws-credentials
+      statuses: write
+      contents: write
+      pull-requests: write
     outputs:
       report-url: ${{ steps.create-allure-report.outputs.report-url }}
 
@@ -380,6 +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 }}
         env:
           REGRESS_TEST_RESULT_CONNSTR_NEW: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}
 
@@ -411,6 +426,10 @@ jobs:
   coverage-report:
     if: ${{ !startsWith(github.ref_name, 'release') }}
     needs: [ check-permissions, build-build-tools-image, build-and-test-locally ]
+    permissions:
+      id-token: write # aws-actions/configure-aws-credentials
+      statuses: write
+      contents: write
     runs-on: [ self-hosted, small ]
     container:
       image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
@@ -437,12 +456,14 @@ jobs:
         with:
           name: neon-${{ runner.os }}-${{ runner.arch }}-${{ matrix.build_type }}-artifact
           path: /tmp/neon
+          aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
       - name: Get coverage artifact
         uses: ./.github/actions/download
         with:
           name: coverage-data-artifact
           path: /tmp/coverage
+          aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
       - name: Merge coverage data
         run: scripts/coverage "--profraw-prefix=$GITHUB_JOB" --dir=/tmp/coverage merge
@@ -573,6 +594,10 @@ jobs:
   neon-image:
     needs: [ neon-image-arch, tag ]
     runs-on: ubuntu-22.04
+    permissions:
+      id-token: write # aws-actions/configure-aws-credentials
+      statuses: write
+      contents: read
 
     steps:
       - uses: docker/login-action@v3
@@ -587,11 +612,15 @@ jobs:
                                              neondatabase/neon:${{ needs.tag.outputs.build-tag }}-bookworm-x64 \
                                              neondatabase/neon:${{ needs.tag.outputs.build-tag }}-bookworm-arm64
 
-      - uses: docker/login-action@v3
+      - name: Configure AWS credentials
+        uses: aws-actions/configure-aws-credentials@v4
         with:
-          registry: 369495373322.dkr.ecr.eu-central-1.amazonaws.com
-          username: ${{ secrets.AWS_ACCESS_KEY_DEV }}
-          password: ${{ secrets.AWS_SECRET_KEY_DEV }}
+          aws-region: eu-central-1
+          role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+          role-duration-seconds: 3600
+
+      - name: Login to Amazon Dev ECR
+        uses: aws-actions/amazon-ecr-login@v2
 
       - name: Push multi-arch image to ECR
         run: |
@@ -600,6 +629,10 @@ jobs:
 
   compute-node-image-arch:
     needs: [ check-permissions, build-build-tools-image, tag ]
+    permissions:
+      id-token: write # aws-actions/configure-aws-credentials
+      statuses: write
+      contents: read
     strategy:
       fail-fast: false
       matrix:
@@ -640,11 +673,15 @@ jobs:
           username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
           password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
 
-      - uses: docker/login-action@v3
+      - name: Configure AWS credentials
+        uses: aws-actions/configure-aws-credentials@v4
         with:
-          registry: 369495373322.dkr.ecr.eu-central-1.amazonaws.com
-          username: ${{ secrets.AWS_ACCESS_KEY_DEV }}
-          password: ${{ secrets.AWS_SECRET_KEY_DEV }}
+          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:
@@ -717,6 +754,10 @@ jobs:
 
   compute-node-image:
     needs: [ compute-node-image-arch, tag ]
+    permissions:
+      id-token: write # aws-actions/configure-aws-credentials
+      statuses: write
+      contents: read
     runs-on: ubuntu-22.04
 
     strategy:
@@ -761,11 +802,15 @@ jobs:
                                              neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-x64 \
                                              neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-arm64
 
-      - uses: docker/login-action@v3
+      - name: Configure AWS credentials
+        uses: aws-actions/configure-aws-credentials@v4
         with:
-          registry: 369495373322.dkr.ecr.eu-central-1.amazonaws.com
-          username: ${{ secrets.AWS_ACCESS_KEY_DEV }}
-          password: ${{ secrets.AWS_SECRET_KEY_DEV }}
+          aws-region: eu-central-1
+          role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+          role-duration-seconds: 3600
+
+      - name: Login to Amazon Dev ECR
+        uses: aws-actions/amazon-ecr-login@v2
 
       - name: Push multi-arch compute-node-${{ matrix.version.pg }} image to ECR
         run: |
@@ -795,7 +840,7 @@ jobs:
           - pg: v17
             debian: bookworm
     env:
-      VM_BUILDER_VERSION: v0.35.0
+      VM_BUILDER_VERSION: v0.37.1
 
     steps:
       - uses: actions/checkout@v4
@@ -890,7 +935,9 @@ jobs:
     runs-on: ubuntu-22.04
 
     permissions:
-      id-token: write # for `aws-actions/configure-aws-credentials`
+      id-token: write # aws-actions/configure-aws-credentials
+      statuses: write
+      contents: read
 
     env:
       VERSIONS: v14 v15 v16 v17
@@ -901,12 +948,15 @@ jobs:
           username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
           password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
 
-      - name: Login to dev ECR
-        uses: docker/login-action@v3
+      - name: Configure AWS credentials
+        uses: aws-actions/configure-aws-credentials@v4
         with:
-          registry: 369495373322.dkr.ecr.eu-central-1.amazonaws.com
-          username: ${{ secrets.AWS_ACCESS_KEY_DEV }}
-          password: ${{ secrets.AWS_SECRET_KEY_DEV }}
+          aws-region: eu-central-1
+          role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+          role-duration-seconds: 3600
+
+      - name: Login to Amazon Dev ECR
+        uses: aws-actions/amazon-ecr-login@v2
 
       - name: Copy vm-compute-node images to ECR
         run: |
@@ -985,6 +1035,11 @@ 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: |
@@ -1060,12 +1115,79 @@ jobs:
     needs: [ check-permissions, promote-images, tag, build-and-test-locally, trigger-custom-extensions-build-and-wait, push-to-acr-dev, push-to-acr-prod ]
     # `!failure() && !cancelled()` is required because the workflow depends on the job that can be skipped: `push-to-acr-dev` and `push-to-acr-prod`
     if: (github.ref_name == 'main' || github.ref_name == 'release' || github.ref_name == 'release-proxy' || github.ref_name == 'release-compute') && !failure() && !cancelled()
-
+    permissions:
+      id-token: write # aws-actions/configure-aws-credentials
+      statuses: write
+      contents: write
     runs-on: [ self-hosted, small ]
     container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/ansible:latest
     steps:
       - uses: actions/checkout@v4
 
+      - name: Create git tag and GitHub release
+        if: github.ref_name == 'release' || github.ref_name == 'release-proxy' || github.ref_name == 'release-compute'
+        uses: actions/github-script@v7
+        with:
+          retries: 5
+          script: |
+            const tag = "${{ needs.tag.outputs.build-tag }}";
+
+            try {
+              const existingRef = await github.rest.git.getRef({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                ref: `tags/${tag}`,
+              });
+
+              if (existingRef.data.object.sha !== context.sha) {
+                throw new Error(`Tag ${tag} already exists but points to a different commit (expected: ${context.sha}, actual: ${existingRef.data.object.sha}).`);
+              }
+
+              console.log(`Tag ${tag} already exists and points to ${context.sha} as expected.`);
+            } catch (error) {
+              if (error.status !== 404) {
+                throw error;
+              }
+
+              console.log(`Tag ${tag} does not exist. Creating it...`);
+              await github.rest.git.createRef({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                ref: `refs/tags/${tag}`,
+                sha: context.sha,
+              });
+              console.log(`Tag ${tag} created successfully.`);
+            }
+
+            // TODO: check how GitHub releases looks for proxy/compute releases and enable them if they're ok
+            if (context.ref !== 'refs/heads/release') {
+              console.log(`GitHub release skipped for ${context.ref}.`);
+              return;
+            }
+
+            try {
+              const existingRelease = await github.rest.repos.getReleaseByTag({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                tag: tag,
+              });
+
+              console.log(`Release for tag ${tag} already exists (ID: ${existingRelease.data.id}).`);
+            } catch (error) {
+              if (error.status !== 404) {
+                throw error;
+              }
+
+              console.log(`Release for tag ${tag} does not exist. Creating it...`);
+              await github.rest.repos.createRelease({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                tag_name: tag,
+                generate_release_notes: true,
+              });
+              console.log(`Release for tag ${tag} created successfully.`);
+            }
+
       - name: Trigger deploy workflow
         env:
           GH_TOKEN: ${{ secrets.CI_ACCESS_TOKEN }}
@@ -1115,38 +1237,13 @@ jobs:
             exit 1
           fi
 
-      - name: Create git tag
-        if: github.ref_name == 'release' || github.ref_name == 'release-proxy' || github.ref_name == 'release-compute'
-        uses: actions/github-script@v7
-        with:
-          # Retry script for 5XX server errors: https://github.com/actions/github-script#retries
-          retries: 5
-          script: |
-            await github.rest.git.createRef({
-              owner: context.repo.owner,
-              repo: context.repo.repo,
-              ref: "refs/tags/${{ needs.tag.outputs.build-tag }}",
-              sha: context.sha,
-            })
-
-      # TODO: check how GitHub releases looks for proxy releases and enable it if it's ok
-      - name: Create GitHub release
-        if: github.ref_name == 'release'
-        uses: actions/github-script@v7
-        with:
-          # Retry script for 5XX server errors: https://github.com/actions/github-script#retries
-          retries: 5
-          script: |
-            await github.rest.repos.createRelease({
-              owner: context.repo.owner,
-              repo: context.repo.repo,
-              tag_name: "${{ needs.tag.outputs.build-tag }}",
-              generate_release_notes: true,
-            })
-
   # The job runs on `release` branch and copies compatibility data and Neon artifact from the last *release PR* to the latest directory
   promote-compatibility-data:
     needs: [ deploy ]
+    permissions:
+      id-token: write # aws-actions/configure-aws-credentials
+      statuses: write
+      contents: read
     # `!failure() && !cancelled()` is required because the workflow transitively depends on the job that can be skipped: `push-to-acr-dev` and `push-to-acr-prod`
     if: github.ref_name == 'release' && !failure() && !cancelled()
 
@@ -1183,6 +1280,12 @@ 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

.github/workflows/cloud-regress.yml

@@ -19,14 +19,17 @@ concurrency:
   group: ${{ github.workflow }}
   cancel-in-progress: true
 
+permissions:
+  id-token: write # aws-actions/configure-aws-credentials
+  statuses: write
+  contents: write
+
 jobs:
   regress:
     env:
       POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
       TEST_OUTPUT: /tmp/test_output
       BUILD_TYPE: remote
-      AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_DEV }}
-      AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_KEY_DEV }}
     strategy:
       fail-fast: false
       matrix:
@@ -78,6 +81,7 @@ jobs:
           name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
           path: /tmp/neon/
           prefix: latest
+          aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
       - name: Create a new branch
         id: create-branch
@@ -93,10 +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 }}
@@ -107,12 +113,14 @@ jobs:
         id: create-allure-report
         if: ${{ !cancelled() }}
         uses: ./.github/actions/allure-report-generate
+        with:
+          aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
       - name: Post to a Slack channel
         if: ${{ github.event.schedule && failure() }}
         uses: slackapi/slack-github-action@v1
         with:
-          channel-id: "C033QLM5P7D" # on-call-staging-stream
+          channel-id: ${{ vars.SLACK_ON_CALL_QA_STAGING_STREAM }}
           slack-message: |
             Periodic pg_regress on staging: ${{ job.status }}
             <${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}|GitHub Run>

.github/workflows/ingest_benchmark.yml

@@ -13,7 +13,7 @@ on:
     #          │ │ │ │ ┌───────────── day of the week (0 - 6 or SUN-SAT)
     - cron:   '0 9 * * *' # run once a day, timezone is utc
   workflow_dispatch: # adds ability to run this manually
-    
+
 defaults:
   run:
     shell: bash -euxo pipefail {0}
@@ -28,7 +28,7 @@ jobs:
     strategy:
       fail-fast: false # allow other variants to continue even if one fails
       matrix:
-        target_project: [new_empty_project, large_existing_project]  
+        target_project: [new_empty_project, large_existing_project]
     permissions:
       contents: write
       statuses: write
@@ -56,7 +56,7 @@ jobs:
       with:
         aws-region: eu-central-1
         role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
-        role-duration-seconds: 18000 # 5 hours is currently max associated with IAM role 
+        role-duration-seconds: 18000 # 5 hours is currently max associated with IAM role
 
     - name: Download Neon artifact
       uses: ./.github/actions/download
@@ -64,6 +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 }}
 
     - name: Create Neon Project
       if: ${{ matrix.target_project == 'new_empty_project' }}
@@ -94,7 +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 }}
@@ -122,7 +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
@@ -131,7 +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: ${{ matrix.target_project }}
@@ -143,7 +144,7 @@ jobs:
       run: |
         export LD_LIBRARY_PATH=${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

.github/workflows/neon_extra_builds.yml

@@ -143,6 +143,10 @@ jobs:
 
   gather-rust-build-stats:
     needs: [ check-permissions, build-build-tools-image ]
+    permissions:
+      id-token: write # aws-actions/configure-aws-credentials
+      statuses: write
+      contents: write
     if: |
       contains(github.event.pull_request.labels.*.name, 'run-extra-build-stats') ||
       contains(github.event.pull_request.labels.*.name, 'run-extra-build-*') ||
@@ -177,13 +181,18 @@ jobs:
       - name: Produce the build stats
         run: PQ_LIB_DIR=$(pwd)/pg_install/v17/lib cargo build --all --release --timings -j$(nproc)
 
+      - name: Configure AWS credentials
+        uses: aws-actions/configure-aws-credentials@v4
+        with:
+          aws-region: eu-central-1
+          role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+          role-duration-seconds: 3600
+
       - name: Upload the build stats
         id: upload-stats
         env:
           BUCKET: neon-github-public-dev
           SHA: ${{ github.event.pull_request.head.sha || github.sha }}
-          AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_DEV }}
-          AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_KEY_DEV }}
         run: |
           REPORT_URL=https://${BUCKET}.s3.amazonaws.com/build-stats/${SHA}/${GITHUB_RUN_ID}/cargo-timing.html
           aws s3 cp --only-show-errors ./target/cargo-timings/cargo-timing.html "s3://${BUCKET}/build-stats/${SHA}/${GITHUB_RUN_ID}/"

.github/workflows/periodic_pagebench.yml

@@ -27,6 +27,11 @@ concurrency:
 
 jobs:
   trigger_bench_on_ec2_machine_in_eu_central_1:
+    permissions:
+      id-token: write # aws-actions/configure-aws-credentials
+      statuses: write
+      contents: write
+      pull-requests: write
     runs-on: [ self-hosted, small ]
     container:
       image: neondatabase/build-tools:pinned-bookworm
@@ -38,8 +43,6 @@ jobs:
     env:
       API_KEY: ${{ secrets.PERIODIC_PAGEBENCH_EC2_RUNNER_API_KEY }}
       RUN_ID: ${{ github.run_id }}
-      AWS_ACCESS_KEY_ID: ${{ secrets.AWS_EC2_US_TEST_RUNNER_ACCESS_KEY_ID }}
-      AWS_SECRET_ACCESS_KEY : ${{ secrets.AWS_EC2_US_TEST_RUNNER_ACCESS_KEY_SECRET }}
       AWS_DEFAULT_REGION : "eu-central-1"
       AWS_INSTANCE_ID : "i-02a59a3bf86bc7e74"
     steps:
@@ -50,6 +53,13 @@ jobs:
     - name: Show my own (github runner) external IP address - usefull for IP allowlisting
       run: curl https://ifconfig.me
 
+    - name: Assume AWS OIDC role that allows to manage (start/stop/describe... EC machine)
+      uses: aws-actions/configure-aws-credentials@v4
+      with:
+        aws-region: eu-central-1
+        role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_MANAGE_BENCHMARK_EC2_VMS_ARN }}
+        role-duration-seconds: 3600
+
     - name: Start EC2 instance and wait for the instance to boot up
       run: |
         aws ec2 start-instances --instance-ids $AWS_INSTANCE_ID
@@ -124,11 +134,10 @@ jobs:
         cat "test_log_${GITHUB_RUN_ID}"
 
     - name: Create Allure report
-      env:
-        AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_DEV }}
-        AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_KEY_DEV }}
       if: ${{ !cancelled() }}
       uses: ./.github/actions/allure-report-generate
+      with:
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
     - name: Post to a Slack channel
       if: ${{ github.event.schedule && failure() }}
@@ -148,6 +157,14 @@ jobs:
         -H "Authorization: Bearer $API_KEY" \
         -d ''
 
+    - name: Assume AWS OIDC role that allows to manage (start/stop/describe... EC machine)
+      if: always() && steps.poll_step.outputs.too_many_runs != 'true'
+      uses: aws-actions/configure-aws-credentials@v4
+      with:
+        aws-region: eu-central-1
+        role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_MANAGE_BENCHMARK_EC2_VMS_ARN }}
+        role-duration-seconds: 3600
+
     - name: Stop EC2 instance and wait for the instance to be stopped
       if: always() && steps.poll_step.outputs.too_many_runs != 'true'
       run: |

.github/workflows/pg-clients.yml

@@ -25,11 +25,13 @@ defaults:
   run:
     shell: bash -euxo pipefail {0}
 
+permissions:
+  id-token: write # aws-actions/configure-aws-credentials
+  statuses: write # require for posting a status update
+
 env:
   DEFAULT_PG_VERSION: 16
   PLATFORM: neon-captest-new
-  AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_DEV }}
-  AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_KEY_DEV }}
   AWS_DEFAULT_REGION: eu-central-1
 
 jobs:
@@ -94,6 +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 }}
 
       - name: Create Neon Project
         id: create-neon-project
@@ -110,6 +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 }}
 
@@ -126,6 +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 }}
         env:
           REGRESS_TEST_RESULT_CONNSTR_NEW: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}
 
@@ -159,6 +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 }}
 
     - name: Create Neon Project
       id: create-neon-project
@@ -175,6 +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 }}
 
@@ -191,6 +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 }}
       env:
         REGRESS_TEST_RESULT_CONNSTR_NEW: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}
 

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

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

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

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

.github/workflows/release.yml

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

.gitignore

@@ -25,3 +25,5 @@ compaction-suite-results.*
 
 # pgindent typedef lists
 *.list
+
+venv/

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]]
@@ -2107,7 +2113,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "3b9429470923de8e8cbd4d2dc513535400b4b3fef0319fb5c4e1f520a7bef743"
 dependencies = [
  "crc32fast",
- "miniz_oxide",
+ "miniz_oxide 0.7.1",
 ]
 
 [[package]]
@@ -2308,9 +2314,9 @@ 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 +3410,15 @@ 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 +3653,9 @@ 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 +4416,13 @@ dependencies = [
  "bindgen",
  "bytes",
  "crc32c",
+ "criterion",
  "env_logger",
  "log",
  "memoffset 0.9.0",
  "once_cell",
  "postgres",
+ "pprof",
  "regex",
  "serde",
  "thiserror",
@@ -5062,6 +5079,7 @@ dependencies = [
  "once_cell",
  "pin-project-lite",
  "rand 0.8.5",
+ "reqwest",
  "scopeguard",
  "serde",
  "serde_json",
@@ -5320,9 +5338,9 @@ 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 +5553,7 @@ dependencies = [
  "remote_storage",
  "reqwest",
  "safekeeper_api",
+ "safekeeper_client",
  "scopeguard",
  "sd-notify",
  "serde",
@@ -5565,10 +5584,25 @@ 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 +7234,7 @@ dependencies = [
  "anyhow",
  "arc-swap",
  "async-compression",
+ "backtrace",
  "bincode",
  "byteorder",
  "bytes",
@@ -7210,12 +7245,14 @@ 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 +7609,7 @@ 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 +7618,7 @@ 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 +7636,7 @@ 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 +7656,18 @@ 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 +7678,9 @@ 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 +7690,9 @@ 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 +7702,15 @@ 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 +7720,9 @@ 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 +7732,9 @@ 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 +7744,9 @@ 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 +7756,9 @@ 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"

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"
@@ -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" }

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) \
@@ -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
@@ -1518,28 +1556,30 @@ 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

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',

compute/etc/pgbouncer.ini

@@ -19,3 +19,10 @@ max_prepared_statements=0
 admin_users=postgres
 unix_socket_dir=/tmp/
 unix_socket_mode=0777
+
+;; Disable connection logging. It produces a lot of logs that no one looks at,
+;; and we can get similar log entries from the proxy too. We had incidents in
+;; the past where the logging significantly stressed the log device or pgbouncer
+;; itself.
+log_connections=0
+log_disconnections=0

compute/etc/sql_exporter/compute_backpressure_throttling_seconds_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',
 }

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

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

compute_tools/src/bin/compute_ctl.rs

@@ -246,47 +246,48 @@ fn try_spec_from_cli(
     let compute_id = matches.get_one::<String>("compute-id");
     let control_plane_uri = matches.get_one::<String>("control-plane-uri");
 
-    let spec;
-    let mut live_config_allowed = false;
-    match spec_json {
-        // First, try to get cluster spec from the cli argument
-        Some(json) => {
-            info!("got spec from cli argument {}", json);
-            spec = Some(serde_json::from_str(json)?);
-        }
-        None => {
-            // Second, try to read it from the file if path is provided
-            if let Some(sp) = spec_path {
-                let path = Path::new(sp);
-                let file = File::open(path)?;
-                spec = Some(serde_json::from_reader(file)?);
-                live_config_allowed = true;
-            } else if let Some(id) = compute_id {
-                if let Some(cp_base) = control_plane_uri {
-                    live_config_allowed = true;
-                    spec = match get_spec_from_control_plane(cp_base, id) {
-                        Ok(s) => s,
-                        Err(e) => {
-                            error!("cannot get response from control plane: {}", e);
-                            panic!("neither spec nor confirmation that compute is in the Empty state was received");
-                        }
-                    };
-                } else {
-                    panic!("must specify both --control-plane-uri and --compute-id or none");
-                }
-            } else {
-                panic!(
-                    "compute spec should be provided by one of the following ways: \
-                    --spec OR --spec-path OR --control-plane-uri and --compute-id"
-                );
-            }
-        }
+    // First, try to get cluster spec from the cli argument
+    if let Some(spec_json) = spec_json {
+        info!("got spec from cli argument {}", spec_json);
+        return Ok(CliSpecParams {
+            spec: Some(serde_json::from_str(spec_json)?),
+            live_config_allowed: false,
+        });
+    }
+
+    // Second, try to read it from the file if path is provided
+    if let Some(spec_path) = spec_path {
+        let file = File::open(Path::new(spec_path))?;
+        return Ok(CliSpecParams {
+            spec: Some(serde_json::from_reader(file)?),
+            live_config_allowed: true,
+        });
+    }
+
+    let Some(compute_id) = compute_id else {
+        panic!(
+            "compute spec should be provided by one of the following ways: \
+                --spec OR --spec-path OR --control-plane-uri and --compute-id"
+        );
+    };
+    let Some(control_plane_uri) = control_plane_uri else {
+        panic!("must specify both --control-plane-uri and --compute-id or none");
     };
 
-    Ok(CliSpecParams {
-        spec,
-        live_config_allowed,
-    })
+    match get_spec_from_control_plane(control_plane_uri, compute_id) {
+        Ok(spec) => Ok(CliSpecParams {
+            spec,
+            live_config_allowed: true,
+        }),
+        Err(e) => {
+            error!(
+                "cannot get response from control plane: {}\n\
+                neither spec nor confirmation that compute is in the Empty state was received",
+                e
+            );
+            Err(e)
+        }
+    }
 }
 
 struct CliSpecParams {

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")?;
     }

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"))
     }
 }

compute_tools/src/http/openapi_spec.yaml

@@ -537,12 +537,14 @@ components:
             properties:
               extname:
                 type: string
-              versions:
-                type: array
+              version:
+                type: string
                 items:
                   type: string
               n_databases:
                 type: integer
+              owned_by_superuser:
+                type: integer
 
     SetRoleGrantsRequest:
       type: object

compute_tools/src/installed_extensions.rs

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

control_plane/src/background_process.rs

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

control_plane/src/bin/neon_local.rs

@@ -19,6 +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();

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");
@@ -810,7 +814,7 @@ impl Endpoint {
         }
 
         let client = reqwest::Client::builder()
-            .timeout(Duration::from_secs(30))
+            .timeout(Duration::from_secs(120))
             .build()
             .unwrap();
         let response = client

control_plane/src/local_env.rs

@@ -76,7 +76,7 @@ pub struct LocalEnv {
 
     // Control plane upcall API for pageserver: if None, we will not run storage_controller  If set, this will
     // be propagated into each pageserver's configuration.
-    pub control_plane_api: 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(),
         };

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") {
@@ -435,7 +433,7 @@ impl PageServerNode {
     ) -> anyhow::Result<()> {
         let config = Self::parse_config(settings)?;
         self.http_client
-            .tenant_config(&models::TenantConfigRequest { tenant_id, config })
+            .set_tenant_config(&models::TenantConfigRequest { tenant_id, config })
             .await?;
 
         Ok(())

control_plane/src/storage_controller.rs

@@ -338,7 +338,7 @@ impl StorageController {
                         .port(),
                 )
             } else {
-                let listen_url = self.env.control_plane_api.clone().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(),

control_plane/storcon_cli/src/main.rs

@@ -5,12 +5,13 @@ 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,
-        ShardParameters, TenantConfig, TenantConfigRequest, TenantShardSplitRequest,
-        TenantShardSplitResponse,
+        ShardParameters, TenantConfig, TenantConfigPatchRequest, TenantConfigRequest,
+        TenantShardSplitRequest, TenantShardSplitResponse,
     },
     shard::{ShardStripeSize, TenantShardId},
 };
@@ -116,9 +117,19 @@ enum Command {
         #[arg(long)]
         tenant_shard_id: TenantShardId,
     },
-    /// Modify the pageserver tenant configuration of a tenant: this is the configuration structure
+    /// Set the pageserver tenant configuration of a tenant: this is the configuration structure
     /// that is passed through to pageservers, and does not affect storage controller behavior.
-    TenantConfig {
+    /// Any previous tenant configs are overwritten.
+    SetTenantConfig {
+        #[arg(long)]
+        tenant_id: TenantId,
+        #[arg(long)]
+        config: String,
+    },
+    /// Patch the pageserver tenant configuration of a tenant. Any fields with null values in the
+    /// provided JSON are unset from the tenant config and all fields with non-null values are set.
+    /// Unspecified fields are not changed.
+    PatchTenantConfig {
         #[arg(long)]
         tenant_id: TenantId,
         #[arg(long)]
@@ -201,6 +212,8 @@ enum Command {
         #[arg(long)]
         timeout: humantime::Duration,
     },
+    /// List safekeepers known to the storage controller
+    Safekeepers {},
 }
 
 #[derive(Parser)]
@@ -549,11 +562,21 @@ async fn main() -> anyhow::Result<()> {
                 )
                 .await?;
         }
-        Command::TenantConfig { tenant_id, config } => {
+        Command::SetTenantConfig { tenant_id, config } => {
             let tenant_conf = serde_json::from_str(&config)?;
 
             vps_client
-                .tenant_config(&TenantConfigRequest {
+                .set_tenant_config(&TenantConfigRequest {
+                    tenant_id,
+                    config: tenant_conf,
+                })
+                .await?;
+        }
+        Command::PatchTenantConfig { tenant_id, config } => {
+            let tenant_conf = serde_json::from_str(&config)?;
+
+            vps_client
+                .patch_tenant_config(&TenantConfigPatchRequest {
                     tenant_id,
                     config: tenant_conf,
                 })
@@ -736,7 +759,7 @@ async fn main() -> anyhow::Result<()> {
             threshold,
         } => {
             vps_client
-                .tenant_config(&TenantConfigRequest {
+                .set_tenant_config(&TenantConfigRequest {
                     tenant_id,
                     config: TenantConfig {
                         eviction_policy: Some(EvictionPolicy::LayerAccessThreshold(
@@ -1000,6 +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(())

docker-compose.yaml

@@ -0,0 +1,96 @@
+version: '3.8'
+
+x-build-args-bullseye: &build-args-bullseye
+  DEBIAN_VERSION: bullseye
+  GIT_VERSION: local # seems to be not used in compute node though
+  BUILD_TAG: ${BUILD_TAG:-local}
+
+x-build-args-bookworm: &build-args-bookworm
+  DEBIAN_VERSION: bookworm
+  GIT_VERSION: local # seems to be not used in compute node though
+  BUILD_TAG: ${BUILD_TAG:-local}
+
+services:
+  compute-node-v14: &compute-node-v14-base
+    image: neondatabase/compute-node-v14:${IMAGE_TAG:-local}
+    build:
+      context: .
+      dockerfile: compute/compute-node.Dockerfile
+      args:
+        <<: *build-args-bullseye
+        PG_VERSION: v14
+      cache_from:
+        - neondatabase/compute-node-v14:${CACHE_FROM_TAG:-latest}
+
+  compute-node-v14-amd64:
+    <<: *compute-node-v14-base
+    platform: linux/amd64
+    image: neondatabase/compute-node-v14:${IMAGE_TAG:-local}-amd64
+
+  compute-node-v14-arm64:
+    <<: *compute-node-v14-base
+    platform: linux/arm64
+    image: neondatabase/compute-node-v14:${IMAGE_TAG:-local}-arm64
+
+  compute-node-v15: &compute-node-v15-base
+    image: neondatabase/compute-node-v15:${IMAGE_TAG:-local}
+    build:
+      context: .
+      dockerfile: compute/compute-node.Dockerfile
+      args:
+        <<: *build-args-bullseye
+        PG_VERSION: v15
+      cache_from:
+        - neondatabase/compute-node-v15:${CACHE_FROM_TAG:-latest}
+
+  compute-node-v15-amd64:
+    <<: *compute-node-v15-base
+    platform: linux/amd64
+    image: neondatabase/compute-node-v15:${IMAGE_TAG:-local}-amd64
+
+  compute-node-v15-arm64:
+    <<: *compute-node-v15-base
+    platform: linux/arm64
+    image: neondatabase/compute-node-v15:${IMAGE_TAG:-local}-arm64
+
+  compute-node-v16: &compute-node-v16-base
+    image: neondatabase/compute-node-v16:${IMAGE_TAG:-local}
+    build:
+      context: .
+      dockerfile: compute/compute-node.Dockerfile
+      args:
+        <<: *build-args-bullseye
+        PG_VERSION: v16
+      cache_from:
+        - neondatabase/compute-node-v16:${CACHE_FROM_TAG:-latest}
+
+  compute-node-v16-amd64:
+    <<: *compute-node-v16-base
+    platform: linux/amd64
+    image: neondatabase/compute-node-v16:${IMAGE_TAG:-local}-amd64
+
+  compute-node-v16-arm64:
+    <<: *compute-node-v16-base
+    platform: linux/arm64
+    image: neondatabase/compute-node-v16:${IMAGE_TAG:-local}-arm64
+
+  compute-node-v17: &compute-node-v17-base
+    image: neondatabase/compute-node-v17:${IMAGE_TAG:-local}
+    build:
+      context: .
+      dockerfile: compute/compute-node.Dockerfile
+      args:
+        <<: *build-args-bookworm
+        PG_VERSION: v17
+      cache_from:
+        - neondatabase/compute-node-v17:${CACHE_FROM_TAG:-latest}
+
+  compute-node-v17-amd64:
+    <<: *compute-node-v17-base
+    platform: linux/amd64
+    image: neondatabase/compute-node-v17:${IMAGE_TAG:-local}-amd64
+
+  compute-node-v17-arm64:
+    <<: *compute-node-v17-base
+    platform: linux/arm64
+    image: neondatabase/compute-node-v17:${IMAGE_TAG:-local}-arm64

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"
             }
         ]
     },

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

libs/compute_api/src/responses.rs

@@ -1,6 +1,5 @@
 //! Structs representing the JSON formats used in the compute_ctl's HTTP API.
 
-use std::collections::HashSet;
 use std::fmt::Display;
 
 use chrono::{DateTime, Utc};
@@ -163,8 +162,9 @@ pub enum ControlPlaneComputeStatus {
 #[derive(Clone, Debug, Default, Serialize)]
 pub struct InstalledExtension {
     pub extname: String,
-    pub versions: HashSet<String>,
+    pub version: String,
     pub n_databases: u32, // Number of databases using this extension
+    pub owned_by_superuser: String,
 }
 
 #[derive(Clone, Debug, Default, Serialize)]

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.

libs/pageserver_api/src/controller_api.rs

@@ -75,7 +75,7 @@ pub struct TenantPolicyRequest {
     pub scheduling: Option<ShardSchedulingPolicy>,
 }
 
-#[derive(Clone, Serialize, Deserialize, PartialEq, Eq, Hash, Debug)]
+#[derive(Clone, Serialize, Deserialize, PartialEq, Eq, Hash, Debug, PartialOrd, Ord)]
 pub struct AvailabilityZone(pub String);
 
 impl Display for AvailabilityZone {
@@ -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::*;

libs/pageserver_api/src/key.rs

@@ -24,7 +24,7 @@ pub struct Key {
 
 /// When working with large numbers of Keys in-memory, it is more efficient to handle them as i128 than as
 /// a struct of fields.
-#[derive(Clone, Copy, Hash, PartialEq, Eq, Ord, PartialOrd, Serialize, Deserialize)]
+#[derive(Clone, Copy, Hash, PartialEq, Eq, Ord, PartialOrd, Serialize, Deserialize, Debug)]
 pub struct CompactKey(i128);
 
 /// The storage key size.
@@ -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)]

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,
@@ -17,7 +18,7 @@ use std::{
 
 use byteorder::{BigEndian, ReadBytesExt};
 use postgres_ffi::BLCKSZ;
-use serde::{Deserialize, Serialize};
+use serde::{Deserialize, Deserializer, Serialize, Serializer};
 use serde_with::serde_as;
 use utils::{
     completion,
@@ -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,
@@ -325,6 +389,115 @@ impl Default for ShardParameters {
     }
 }
 
+#[derive(Debug, Default, Clone, Eq, PartialEq)]
+pub enum FieldPatch<T> {
+    Upsert(T),
+    Remove,
+    #[default]
+    Noop,
+}
+
+impl<T> FieldPatch<T> {
+    fn is_noop(&self) -> bool {
+        matches!(self, FieldPatch::Noop)
+    }
+
+    pub fn apply(self, target: &mut Option<T>) {
+        match self {
+            Self::Upsert(v) => *target = Some(v),
+            Self::Remove => *target = None,
+            Self::Noop => {}
+        }
+    }
+
+    pub fn map<U, E, F: FnOnce(T) -> Result<U, E>>(self, map: F) -> Result<FieldPatch<U>, E> {
+        match self {
+            Self::Upsert(v) => Ok(FieldPatch::<U>::Upsert(map(v)?)),
+            Self::Remove => Ok(FieldPatch::<U>::Remove),
+            Self::Noop => Ok(FieldPatch::<U>::Noop),
+        }
+    }
+}
+
+impl<'de, T: Deserialize<'de>> Deserialize<'de> for FieldPatch<T> {
+    fn deserialize<D>(deserializer: D) -> Result<Self, D::Error>
+    where
+        D: Deserializer<'de>,
+    {
+        Option::deserialize(deserializer).map(|opt| match opt {
+            None => FieldPatch::Remove,
+            Some(val) => FieldPatch::Upsert(val),
+        })
+    }
+}
+
+impl<T: Serialize> Serialize for FieldPatch<T> {
+    fn serialize<S>(&self, serializer: S) -> Result<S::Ok, S::Error>
+    where
+        S: Serializer,
+    {
+        match self {
+            FieldPatch::Upsert(val) => serializer.serialize_some(val),
+            FieldPatch::Remove => serializer.serialize_none(),
+            FieldPatch::Noop => unreachable!(),
+        }
+    }
+}
+
+#[derive(Serialize, Deserialize, Debug, Default, Clone, Eq, PartialEq)]
+#[serde(default)]
+pub struct TenantConfigPatch {
+    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
+    pub checkpoint_distance: FieldPatch<u64>,
+    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
+    pub checkpoint_timeout: FieldPatch<String>,
+    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
+    pub compaction_target_size: FieldPatch<u64>,
+    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
+    pub compaction_period: FieldPatch<String>,
+    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
+    pub compaction_threshold: FieldPatch<usize>,
+    // defer parsing compaction_algorithm, like eviction_policy
+    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
+    pub compaction_algorithm: FieldPatch<CompactionAlgorithmSettings>,
+    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
+    pub gc_horizon: FieldPatch<u64>,
+    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
+    pub gc_period: FieldPatch<String>,
+    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
+    pub image_creation_threshold: FieldPatch<usize>,
+    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
+    pub pitr_interval: FieldPatch<String>,
+    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
+    pub walreceiver_connect_timeout: FieldPatch<String>,
+    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
+    pub lagging_wal_timeout: FieldPatch<String>,
+    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
+    pub max_lsn_wal_lag: FieldPatch<NonZeroU64>,
+    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
+    pub eviction_policy: FieldPatch<EvictionPolicy>,
+    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
+    pub min_resident_size_override: FieldPatch<u64>,
+    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
+    pub evictions_low_residence_duration_metric_threshold: FieldPatch<String>,
+    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
+    pub heatmap_period: FieldPatch<String>,
+    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
+    pub lazy_slru_download: FieldPatch<bool>,
+    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
+    pub timeline_get_throttle: FieldPatch<ThrottleConfig>,
+    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
+    pub image_layer_creation_check_threshold: FieldPatch<u8>,
+    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
+    pub lsn_lease_length: FieldPatch<String>,
+    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
+    pub lsn_lease_length_for_ts: FieldPatch<String>,
+    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
+    pub timeline_offloading: FieldPatch<bool>,
+    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
+    pub wal_receiver_protocol_override: FieldPatch<PostgresClientProtocol>,
+}
+
 /// An alternative representation of `pageserver::tenant::TenantConf` with
 /// simpler types.
 #[derive(Serialize, Deserialize, Debug, Default, Clone, Eq, PartialEq)]
@@ -356,6 +529,107 @@ pub struct TenantConfig {
     pub wal_receiver_protocol_override: Option<PostgresClientProtocol>,
 }
 
+impl TenantConfig {
+    pub fn apply_patch(self, patch: TenantConfigPatch) -> TenantConfig {
+        let Self {
+            mut checkpoint_distance,
+            mut checkpoint_timeout,
+            mut compaction_target_size,
+            mut compaction_period,
+            mut compaction_threshold,
+            mut compaction_algorithm,
+            mut gc_horizon,
+            mut gc_period,
+            mut image_creation_threshold,
+            mut pitr_interval,
+            mut walreceiver_connect_timeout,
+            mut lagging_wal_timeout,
+            mut max_lsn_wal_lag,
+            mut eviction_policy,
+            mut min_resident_size_override,
+            mut evictions_low_residence_duration_metric_threshold,
+            mut heatmap_period,
+            mut lazy_slru_download,
+            mut timeline_get_throttle,
+            mut image_layer_creation_check_threshold,
+            mut lsn_lease_length,
+            mut lsn_lease_length_for_ts,
+            mut timeline_offloading,
+            mut wal_receiver_protocol_override,
+        } = self;
+
+        patch.checkpoint_distance.apply(&mut checkpoint_distance);
+        patch.checkpoint_timeout.apply(&mut checkpoint_timeout);
+        patch
+            .compaction_target_size
+            .apply(&mut compaction_target_size);
+        patch.compaction_period.apply(&mut compaction_period);
+        patch.compaction_threshold.apply(&mut compaction_threshold);
+        patch.compaction_algorithm.apply(&mut compaction_algorithm);
+        patch.gc_horizon.apply(&mut gc_horizon);
+        patch.gc_period.apply(&mut gc_period);
+        patch
+            .image_creation_threshold
+            .apply(&mut image_creation_threshold);
+        patch.pitr_interval.apply(&mut pitr_interval);
+        patch
+            .walreceiver_connect_timeout
+            .apply(&mut walreceiver_connect_timeout);
+        patch.lagging_wal_timeout.apply(&mut lagging_wal_timeout);
+        patch.max_lsn_wal_lag.apply(&mut max_lsn_wal_lag);
+        patch.eviction_policy.apply(&mut eviction_policy);
+        patch
+            .min_resident_size_override
+            .apply(&mut min_resident_size_override);
+        patch
+            .evictions_low_residence_duration_metric_threshold
+            .apply(&mut evictions_low_residence_duration_metric_threshold);
+        patch.heatmap_period.apply(&mut heatmap_period);
+        patch.lazy_slru_download.apply(&mut lazy_slru_download);
+        patch
+            .timeline_get_throttle
+            .apply(&mut timeline_get_throttle);
+        patch
+            .image_layer_creation_check_threshold
+            .apply(&mut image_layer_creation_check_threshold);
+        patch.lsn_lease_length.apply(&mut lsn_lease_length);
+        patch
+            .lsn_lease_length_for_ts
+            .apply(&mut lsn_lease_length_for_ts);
+        patch.timeline_offloading.apply(&mut timeline_offloading);
+        patch
+            .wal_receiver_protocol_override
+            .apply(&mut wal_receiver_protocol_override);
+
+        Self {
+            checkpoint_distance,
+            checkpoint_timeout,
+            compaction_target_size,
+            compaction_period,
+            compaction_threshold,
+            compaction_algorithm,
+            gc_horizon,
+            gc_period,
+            image_creation_threshold,
+            pitr_interval,
+            walreceiver_connect_timeout,
+            lagging_wal_timeout,
+            max_lsn_wal_lag,
+            eviction_policy,
+            min_resident_size_override,
+            evictions_low_residence_duration_metric_threshold,
+            heatmap_period,
+            lazy_slru_download,
+            timeline_get_throttle,
+            image_layer_creation_check_threshold,
+            lsn_lease_length,
+            lsn_lease_length_for_ts,
+            timeline_offloading,
+            wal_receiver_protocol_override,
+        }
+    }
+}
+
 /// The policy for the aux file storage.
 ///
 /// It can be switched through `switch_aux_file_policy` tenant config.
@@ -686,6 +960,14 @@ impl TenantConfigRequest {
     }
 }
 
+#[derive(Serialize, Deserialize, Debug)]
+#[serde(deny_unknown_fields)]
+pub struct TenantConfigPatchRequest {
+    pub tenant_id: TenantId,
+    #[serde(flatten)]
+    pub config: TenantConfigPatch, // as we have a flattened field, we should reject all unknown fields in it
+}
+
 /// See [`TenantState::attachment_status`] and the OpenAPI docs for context.
 #[derive(Serialize, Deserialize, Clone)]
 #[serde(tag = "slug", content = "data", rename_all = "snake_case")]
@@ -1699,4 +1981,45 @@ mod tests {
             );
         }
     }
+
+    #[test]
+    fn test_tenant_config_patch_request_serde() {
+        let patch_request = TenantConfigPatchRequest {
+            tenant_id: TenantId::from_str("17c6d121946a61e5ab0fe5a2fd4d8215").unwrap(),
+            config: TenantConfigPatch {
+                checkpoint_distance: FieldPatch::Upsert(42),
+                gc_horizon: FieldPatch::Remove,
+                compaction_threshold: FieldPatch::Noop,
+                ..TenantConfigPatch::default()
+            },
+        };
+
+        let json = serde_json::to_string(&patch_request).unwrap();
+
+        let expected = r#"{"tenant_id":"17c6d121946a61e5ab0fe5a2fd4d8215","checkpoint_distance":42,"gc_horizon":null}"#;
+        assert_eq!(json, expected);
+
+        let decoded: TenantConfigPatchRequest = serde_json::from_str(&json).unwrap();
+        assert_eq!(decoded.tenant_id, patch_request.tenant_id);
+        assert_eq!(decoded.config, patch_request.config);
+
+        // Now apply the patch to a config to demonstrate semantics
+
+        let base = TenantConfig {
+            checkpoint_distance: Some(28),
+            gc_horizon: Some(100),
+            compaction_target_size: Some(1024),
+            ..Default::default()
+        };
+
+        let expected = TenantConfig {
+            checkpoint_distance: Some(42),
+            gc_horizon: None,
+            ..base.clone()
+        };
+
+        let patched = base.apply_patch(decoded.config);
+
+        assert_eq!(patched, expected);
+    }
 }

libs/pageserver_api/src/shard.rs

@@ -173,7 +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() {

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

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`.

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(())
+    }
+}

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 {

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,

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]

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};

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;

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]

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;

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]

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};

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()),

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"] }

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;

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

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<()>;
 

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 {

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;

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()))?;

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,

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

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}");
 

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
 }

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

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")

libs/utils/src/lib.rs

@@ -94,6 +94,10 @@ pub mod toml_edit_ext;
 
 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;

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
+}

libs/utils/src/try_rcu.rs

@@ -0,0 +1,77 @@
+//! Try RCU extension lifted from <https://github.com/vorner/arc-swap/issues/94#issuecomment-1987154023>
+
+pub trait ArcSwapExt<T> {
+    /// [`ArcSwap::rcu`](arc_swap::ArcSwap::rcu), but with Result that short-circuits on error.
+    fn try_rcu<R, F, E>(&self, f: F) -> Result<T, E>
+    where
+        F: FnMut(&T) -> Result<R, E>,
+        R: Into<T>;
+}
+
+impl<T, S> ArcSwapExt<T> for arc_swap::ArcSwapAny<T, S>
+where
+    T: arc_swap::RefCnt,
+    S: arc_swap::strategy::CaS<T>,
+{
+    fn try_rcu<R, F, E>(&self, mut f: F) -> Result<T, E>
+    where
+        F: FnMut(&T) -> Result<R, E>,
+        R: Into<T>,
+    {
+        fn ptr_eq<Base, A, B>(a: A, b: B) -> bool
+        where
+            A: arc_swap::AsRaw<Base>,
+            B: arc_swap::AsRaw<Base>,
+        {
+            let a = a.as_raw();
+            let b = b.as_raw();
+            std::ptr::eq(a, b)
+        }
+
+        let mut cur = self.load();
+        loop {
+            let new = f(&cur)?.into();
+            let prev = self.compare_and_swap(&*cur, new);
+            let swapped = ptr_eq(&*cur, &*prev);
+            if swapped {
+                return Ok(arc_swap::Guard::into_inner(prev));
+            } else {
+                cur = prev;
+            }
+        }
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use arc_swap::ArcSwap;
+    use std::sync::Arc;
+
+    #[test]
+    fn test_try_rcu_success() {
+        let swap = ArcSwap::from(Arc::new(42));
+
+        let result = swap.try_rcu(|value| -> Result<_, String> { Ok(**value + 1) });
+
+        assert!(result.is_ok());
+        assert_eq!(**swap.load(), 43);
+    }
+
+    #[test]
+    fn test_try_rcu_error() {
+        let swap = ArcSwap::from(Arc::new(42));
+
+        let result = swap.try_rcu(|value| -> Result<i32, _> {
+            if **value == 42 {
+                Err("err")
+            } else {
+                Ok(**value + 1)
+            }
+        });
+
+        assert!(result.is_err());
+        assert_eq!(result.unwrap_err(), "err");
+        assert_eq!(**swap.load(), 42);
+    }
+}

libs/wal_decoder/proto/interpreted_wal.proto

@@ -37,7 +37,7 @@ message ValueMeta {
 }
 
 message CompactKey {
-  int64 high = 1;
-  int64 low = 2;
+  uint64 high = 1;
+  uint64 low = 2;
 }
 

libs/wal_decoder/src/wire_format.rs

@@ -236,8 +236,8 @@ impl From<ValueMeta> for proto::ValueMeta {
 impl From<CompactKey> for proto::CompactKey {
     fn from(value: CompactKey) -> Self {
         proto::CompactKey {
-            high: (value.raw() >> 64) as i64,
-            low: value.raw() as i64,
+            high: (value.raw() >> 64) as u64,
+            low: value.raw() as u64,
         }
     }
 }
@@ -354,3 +354,64 @@ impl From<proto::CompactKey> for CompactKey {
         (((value.high as i128) << 64) | (value.low as i128)).into()
     }
 }
+
+#[test]
+fn test_compact_key_with_large_relnode() {
+    use pageserver_api::key::Key;
+
+    let inputs = vec![
+        Key {
+            field1: 0,
+            field2: 0x100,
+            field3: 0x200,
+            field4: 0,
+            field5: 0x10,
+            field6: 0x5,
+        },
+        Key {
+            field1: 0,
+            field2: 0x100,
+            field3: 0x200,
+            field4: 0x007FFFFF,
+            field5: 0x10,
+            field6: 0x5,
+        },
+        Key {
+            field1: 0,
+            field2: 0x100,
+            field3: 0x200,
+            field4: 0x00800000,
+            field5: 0x10,
+            field6: 0x5,
+        },
+        Key {
+            field1: 0,
+            field2: 0x100,
+            field3: 0x200,
+            field4: 0x00800001,
+            field5: 0x10,
+            field6: 0x5,
+        },
+        Key {
+            field1: 0,
+            field2: 0xFFFFFFFF,
+            field3: 0xFFFFFFFF,
+            field4: 0xFFFFFFFF,
+            field5: 0x0,
+            field6: 0x0,
+        },
+    ];
+
+    for input in inputs {
+        assert!(input.is_valid_key_on_write_path());
+        let compact = input.to_compact();
+        let proto: proto::CompactKey = compact.into();
+        let from_proto: CompactKey = proto.into();
+
+        assert_eq!(
+            compact, from_proto,
+            "Round trip failed for key with relnode={:#x}",
+            input.field4
+        );
+    }
+}

libs/walproposer/build.rs

@@ -30,9 +30,9 @@ fn main() -> anyhow::Result<()> {
     let pgxn_neon = std::fs::canonicalize(pgxn_neon)?;
     let pgxn_neon = pgxn_neon.to_str().ok_or(anyhow!("Bad non-UTF path"))?;
 
+    println!("cargo:rustc-link-lib=static=walproposer");
     println!("cargo:rustc-link-lib=static=pgport");
     println!("cargo:rustc-link-lib=static=pgcommon");
-    println!("cargo:rustc-link-lib=static=walproposer");
     println!("cargo:rustc-link-search={walproposer_lib_search_str}");
 
     // Rebuild crate when libwalproposer.a changes

pageserver/client/src/mgmt_api.rs

@@ -270,12 +270,18 @@ impl Client {
         Ok(body)
     }
 
-    pub async fn tenant_config(&self, req: &TenantConfigRequest) -> Result<()> {
+    pub async fn set_tenant_config(&self, req: &TenantConfigRequest) -> Result<()> {
         let uri = format!("{}/v1/tenant/config", self.mgmt_api_endpoint);
         self.request(Method::PUT, &uri, req).await?;
         Ok(())
     }
 
+    pub async fn patch_tenant_config(&self, req: &TenantConfigPatchRequest) -> Result<()> {
+        let uri = format!("{}/v1/tenant/config", self.mgmt_api_endpoint);
+        self.request(Method::PATCH, &uri, req).await?;
+        Ok(())
+    }
+
     pub async fn tenant_secondary_download(
         &self,
         tenant_id: TenantShardId,

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,
 {

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() {

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;

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())
     }
 }

pageserver/pagebench/src/cmd/aux_files.rs

@@ -64,7 +64,7 @@ async fn main_impl(args: Args) -> anyhow::Result<()> {
     println!("operating on timeline {}", timeline);
 
     mgmt_api_client
-        .tenant_config(&TenantConfigRequest {
+        .set_tenant_config(&TenantConfigRequest {
             tenant_id: timeline.tenant_id,
             config: TenantConfig::default(),
         })

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,
 {

pageserver/src/http/openapi_spec.yml

@@ -767,7 +767,27 @@ paths:
   /v1/tenant/config:
     put:
       description: |
-        Update tenant's config.
+        Update tenant's config by setting it to the provided value
+
+        Invalid fields in the tenant config will cause the request to be rejected with status 400.
+      requestBody:
+        content:
+          application/json:
+            schema:
+              $ref: "#/components/schemas/TenantConfigRequest"
+      responses:
+        "200":
+          description: OK
+          content:
+            application/json:
+              schema:
+                type: array
+                items:
+                  $ref: "#/components/schemas/TenantInfo"
+    patch:
+      description: |
+        Update tenant's config additively by patching the updated fields provided.
+        Null values unset the field and non-null values upsert it.
 
         Invalid fields in the tenant config will cause the request to be rejected with status 400.
       requestBody:

pageserver/src/http/routes.rs

@@ -28,6 +28,7 @@ use pageserver_api::models::LsnLease;
 use pageserver_api::models::LsnLeaseRequest;
 use pageserver_api::models::OffloadedTimelineInfo;
 use pageserver_api::models::ShardParameters;
+use pageserver_api::models::TenantConfigPatchRequest;
 use pageserver_api::models::TenantDetails;
 use pageserver_api::models::TenantLocationConfigRequest;
 use pageserver_api::models::TenantLocationConfigResponse;
@@ -96,8 +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,
@@ -1695,7 +1696,47 @@ async fn update_tenant_config_handler(
     crate::tenant::Tenant::persist_tenant_config(state.conf, &tenant_shard_id, &location_conf)
         .await
         .map_err(|e| ApiError::InternalServerError(anyhow::anyhow!(e)))?;
-    tenant.set_new_tenant_config(new_tenant_conf);
+
+    let _ = tenant
+        .update_tenant_config(|_crnt| Ok(new_tenant_conf.clone()))
+        .expect("Closure returns Ok()");
+
+    json_response(StatusCode::OK, ())
+}
+
+async fn patch_tenant_config_handler(
+    mut request: Request<Body>,
+    _cancel: CancellationToken,
+) -> Result<Response<Body>, ApiError> {
+    let request_data: TenantConfigPatchRequest = json_request(&mut request).await?;
+    let tenant_id = request_data.tenant_id;
+    check_permission(&request, Some(tenant_id))?;
+
+    let state = get_state(&request);
+
+    let tenant_shard_id = TenantShardId::unsharded(tenant_id);
+
+    let tenant = state
+        .tenant_manager
+        .get_attached_tenant_shard(tenant_shard_id)?;
+    tenant.wait_to_become_active(ACTIVE_TENANT_TIMEOUT).await?;
+
+    let updated = tenant
+        .update_tenant_config(|crnt| crnt.apply_patch(request_data.config.clone()))
+        .map_err(ApiError::BadRequest)?;
+
+    // This is a legacy API that only operates on attached tenants: the preferred
+    // API to use is the location_config/ endpoint, which lets the caller provide
+    // the full LocationConf.
+    let location_conf = LocationConf::attached_single(
+        updated,
+        tenant.get_generation(),
+        &ShardParameters::default(),
+    );
+
+    crate::tenant::Tenant::persist_tenant_config(state.conf, &tenant_shard_id, &location_conf)
+        .await
+        .map_err(|e| ApiError::InternalServerError(anyhow::anyhow!(e)))?;
 
     json_response(StatusCode::OK, ())
 }
@@ -1998,6 +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>,
@@ -2040,13 +2109,20 @@ async fn timeline_compact_handler(
         .as_ref()
         .map(|r| r.sub_compaction)
         .unwrap_or(false);
+    let sub_compaction_max_job_size_mb = compact_request
+        .as_ref()
+        .and_then(|r| r.sub_compaction_max_job_size_mb);
+
     let options = CompactOptions {
-        compact_range: compact_request
+        compact_key_range: compact_request
             .as_ref()
-            .and_then(|r| r.compact_range.clone()),
-        compact_below_lsn: compact_request.as_ref().and_then(|r| r.compact_below_lsn),
+            .and_then(|r| r.compact_key_range.clone()),
+        compact_lsn_range: compact_request
+            .as_ref()
+            .and_then(|r| r.compact_lsn_range.clone()),
         flags,
         sub_compaction,
+        sub_compaction_max_job_size_mb,
     };
 
     let scheduled = compact_request
@@ -3288,6 +3364,9 @@ pub fn make_router(
         .get("/v1/tenant/:tenant_shard_id/synthetic_size", |r| {
             api_handler(r, tenant_size_handler)
         })
+        .patch("/v1/tenant/config", |r| {
+            api_handler(r, patch_tenant_config_handler)
+        })
         .put("/v1/tenant/config", |r| {
             api_handler(r, update_tenant_config_handler)
         })
@@ -3349,6 +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),

pageserver/src/metrics.rs

@@ -3,7 +3,7 @@ use metrics::{
     register_counter_vec, register_gauge_vec, register_histogram, register_histogram_vec,
     register_int_counter, register_int_counter_pair_vec, register_int_counter_vec,
     register_int_gauge, register_int_gauge_vec, register_uint_gauge, register_uint_gauge_vec,
-    Counter, CounterVec, Gauge, GaugeVec, Histogram, HistogramVec, IntCounter, IntCounterPair,
+    Counter, CounterVec, GaugeVec, Histogram, HistogramVec, IntCounter, IntCounterPair,
     IntCounterPairVec, IntCounterVec, IntGauge, IntGaugeVec, UIntGauge, UIntGaugeVec,
 };
 use once_cell::sync::Lazy;
@@ -16,7 +16,6 @@ use postgres_backend::{is_expected_io_error, QueryError};
 use pq_proto::framed::ConnectionError;
 use strum::{EnumCount, VariantNames};
 use strum_macros::{IntoStaticStr, VariantNames};
-use tracing::warn;
 use utils::id::TimelineId;
 
 /// Prometheus histogram buckets (in seconds) for operations in the critical
@@ -446,15 +445,6 @@ pub(crate) static WAIT_LSN_TIME: Lazy<Histogram> = Lazy::new(|| {
     .expect("failed to define a metric")
 });
 
-static FLUSH_WAIT_UPLOAD_TIME: Lazy<GaugeVec> = Lazy::new(|| {
-    register_gauge_vec!(
-        "pageserver_flush_wait_upload_seconds",
-        "Time spent waiting for preceding uploads during layer flush",
-        &["tenant_id", "shard_id", "timeline_id"]
-    )
-    .expect("failed to define a metric")
-});
-
 static LAST_RECORD_LSN: Lazy<IntGaugeVec> = Lazy::new(|| {
     register_int_gauge_vec!(
         "pageserver_last_record_lsn",
@@ -1225,32 +1215,58 @@ pub(crate) mod virtual_file_io_engine {
 
 pub(crate) struct SmgrOpTimer(Option<SmgrOpTimerInner>);
 pub(crate) struct SmgrOpTimerInner {
-    global_latency_histo: Histogram,
+    global_execution_latency_histo: Histogram,
+    per_timeline_execution_latency_histo: Option<Histogram>,
 
-    // Optional because not all op types are tracked per-timeline
-    per_timeline_latency_histo: Option<Histogram>,
+    global_batch_wait_time: Histogram,
+    per_timeline_batch_wait_time: Histogram,
 
     global_flush_in_progress_micros: IntCounter,
     per_timeline_flush_in_progress_micros: IntCounter,
 
-    start: Instant,
-    throttled: Duration,
-    op: SmgrQueryType,
+    timings: SmgrOpTimerState,
+}
+
+#[derive(Debug)]
+enum SmgrOpTimerState {
+    Received {
+        received_at: Instant,
+    },
+    ThrottleDoneExecutionStarting {
+        received_at: Instant,
+        throttle_started_at: Instant,
+        started_execution_at: Instant,
+    },
 }
 
 pub(crate) struct SmgrOpFlushInProgress {
-    base: Instant,
+    flush_started_at: Instant,
     global_micros: IntCounter,
     per_timeline_micros: IntCounter,
 }
 
 impl SmgrOpTimer {
-    pub(crate) fn deduct_throttle(&mut self, throttle: &Option<Duration>) {
-        let Some(throttle) = throttle else {
-            return;
-        };
+    pub(crate) fn observe_throttle_done_execution_starting(&mut self, throttle: &ThrottleResult) {
         let inner = self.0.as_mut().expect("other public methods consume self");
-        inner.throttled += *throttle;
+        match (&mut inner.timings, throttle) {
+            (SmgrOpTimerState::Received { received_at }, throttle) => match throttle {
+                ThrottleResult::NotThrottled { start } => {
+                    inner.timings = SmgrOpTimerState::ThrottleDoneExecutionStarting {
+                        received_at: *received_at,
+                        throttle_started_at: *start,
+                        started_execution_at: *start,
+                    };
+                }
+                ThrottleResult::Throttled { start, end } => {
+                    inner.timings = SmgrOpTimerState::ThrottleDoneExecutionStarting {
+                        received_at: *start,
+                        throttle_started_at: *start,
+                        started_execution_at: *end,
+                    };
+                }
+            },
+            (x, _) => panic!("called in unexpected state: {x:?}"),
+        }
     }
 
     pub(crate) fn observe_smgr_op_completion_and_start_flushing(mut self) -> SmgrOpFlushInProgress {
@@ -1263,7 +1279,7 @@ impl SmgrOpTimer {
             ..
         } = inner;
         SmgrOpFlushInProgress {
-            base: flush_start,
+            flush_started_at: flush_start,
             global_micros: global_flush_in_progress_micros,
             per_timeline_micros: per_timeline_flush_in_progress_micros,
         }
@@ -1274,32 +1290,42 @@ impl SmgrOpTimer {
         let inner = self.0.take()?;
 
         let now = Instant::now();
-        let elapsed = now - inner.start;
 
-        let elapsed = match elapsed.checked_sub(inner.throttled) {
-            Some(elapsed) => elapsed,
-            None => {
-                use utils::rate_limit::RateLimit;
-                static LOGGED: Lazy<Mutex<enum_map::EnumMap<SmgrQueryType, RateLimit>>> =
-                    Lazy::new(|| {
-                        Mutex::new(enum_map::EnumMap::from_array(std::array::from_fn(|_| {
-                            RateLimit::new(Duration::from_secs(10))
-                        })))
-                    });
-                let mut guard = LOGGED.lock().unwrap();
-                let rate_limit = &mut guard[inner.op];
-                rate_limit.call(|| {
-                    warn!(op=?inner.op, ?elapsed, ?inner.throttled, "implementation error: time spent throttled exceeds total request wall clock time");
-                });
-                elapsed // un-throttled time, more info than just saturating to 0
+        let batch;
+        let execution;
+        let throttle;
+        match inner.timings {
+            SmgrOpTimerState::Received { received_at } => {
+                batch = (now - received_at).as_secs_f64();
+                // TODO: use label for dropped requests.
+                // This is quite rare in practice, only during tenant/pageservers shutdown.
+                throttle = Duration::ZERO;
+                execution = Duration::ZERO.as_secs_f64();
             }
-        };
+            SmgrOpTimerState::ThrottleDoneExecutionStarting {
+                received_at,
+                throttle_started_at,
+                started_execution_at,
+            } => {
+                batch = (throttle_started_at - received_at).as_secs_f64();
+                throttle = started_execution_at - throttle_started_at;
+                execution = (now - started_execution_at).as_secs_f64();
+            }
+        }
 
-        let elapsed = elapsed.as_secs_f64();
+        // update time spent in batching
+        inner.global_batch_wait_time.observe(batch);
+        inner.per_timeline_batch_wait_time.observe(batch);
 
-        inner.global_latency_histo.observe(elapsed);
-        if let Some(per_timeline_getpage_histo) = &inner.per_timeline_latency_histo {
-            per_timeline_getpage_histo.observe(elapsed);
+        // time spent in throttle metric is updated by throttle impl
+        let _ = throttle;
+
+        // update metrics for execution latency
+        inner.global_execution_latency_histo.observe(execution);
+        if let Some(per_timeline_execution_latency_histo) =
+            &inner.per_timeline_execution_latency_histo
+        {
+            per_timeline_execution_latency_histo.observe(execution);
         }
 
         Some((now, inner))
@@ -1325,12 +1351,12 @@ impl SmgrOpFlushInProgress {
         // Last call is tracked in `now`.
         let mut observe_guard = scopeguard::guard(
             || {
-                let elapsed = now - self.base;
+                let elapsed = now - self.flush_started_at;
                 self.global_micros
                     .inc_by(u64::try_from(elapsed.as_micros()).unwrap());
                 self.per_timeline_micros
                     .inc_by(u64::try_from(elapsed.as_micros()).unwrap());
-                self.base = now;
+                self.flush_started_at = now;
             },
             |mut observe| {
                 observe();
@@ -1377,6 +1403,8 @@ pub(crate) struct SmgrQueryTimePerTimeline {
     per_timeline_batch_size: Histogram,
     global_flush_in_progress_micros: IntCounter,
     per_timeline_flush_in_progress_micros: IntCounter,
+    global_batch_wait_time: Histogram,
+    per_timeline_batch_wait_time: Histogram,
 }
 
 static SMGR_QUERY_STARTED_GLOBAL: Lazy<IntCounterVec> = Lazy::new(|| {
@@ -1399,12 +1427,15 @@ static SMGR_QUERY_STARTED_PER_TENANT_TIMELINE: Lazy<IntCounterVec> = Lazy::new(|
     .expect("failed to define a metric")
 });
 
+// Alias so all histograms recording per-timeline smgr timings use the same buckets.
+static SMGR_QUERY_TIME_PER_TENANT_TIMELINE_BUCKETS: &[f64] = CRITICAL_OP_BUCKETS;
+
 static SMGR_QUERY_TIME_PER_TENANT_TIMELINE: Lazy<HistogramVec> = Lazy::new(|| {
     register_histogram_vec!(
         "pageserver_smgr_query_seconds",
-        "Time spent on smgr query handling, aggegated by query type and tenant/timeline.",
+        "Time spent _executing_ smgr query handling, excluding batch and throttle delays.",
         &["smgr_query_type", "tenant_id", "shard_id", "timeline_id"],
-        CRITICAL_OP_BUCKETS.into(),
+        SMGR_QUERY_TIME_PER_TENANT_TIMELINE_BUCKETS.into(),
     )
     .expect("failed to define a metric")
 });
@@ -1462,7 +1493,7 @@ static SMGR_QUERY_TIME_GLOBAL_BUCKETS: Lazy<Vec<f64>> = Lazy::new(|| {
 static SMGR_QUERY_TIME_GLOBAL: Lazy<HistogramVec> = Lazy::new(|| {
     register_histogram_vec!(
         "pageserver_smgr_query_seconds_global",
-        "Time spent on smgr query handling, aggregated by query type.",
+        "Like pageserver_smgr_query_seconds, but aggregated to instance level.",
         &["smgr_query_type"],
         SMGR_QUERY_TIME_GLOBAL_BUCKETS.clone(),
     )
@@ -1559,6 +1590,25 @@ static PAGE_SERVICE_SMGR_FLUSH_INPROGRESS_MICROS_GLOBAL: Lazy<IntCounter> = Lazy
     .expect("failed to define a metric")
 });
 
+static PAGE_SERVICE_SMGR_BATCH_WAIT_TIME: Lazy<HistogramVec> = Lazy::new(|| {
+    register_histogram_vec!(
+        "pageserver_page_service_pagestream_batch_wait_time_seconds",
+        "Time a request spent waiting in its batch until the batch moved to throttle&execution.",
+        &["tenant_id", "shard_id", "timeline_id"],
+        SMGR_QUERY_TIME_PER_TENANT_TIMELINE_BUCKETS.into(),
+    )
+    .expect("failed to define a metric")
+});
+
+static PAGE_SERVICE_SMGR_BATCH_WAIT_TIME_GLOBAL: Lazy<Histogram> = Lazy::new(|| {
+    register_histogram!(
+        "pageserver_page_service_pagestream_batch_wait_time_seconds_global",
+        "Like pageserver_page_service_pagestream_batch_wait_time_seconds, but aggregated to instance level.",
+        SMGR_QUERY_TIME_GLOBAL_BUCKETS.to_vec(),
+    )
+    .expect("failed to define a metric")
+});
+
 impl SmgrQueryTimePerTimeline {
     pub(crate) fn new(tenant_shard_id: &TenantShardId, timeline_id: &TimelineId) -> Self {
         let tenant_id = tenant_shard_id.tenant_id.to_string();
@@ -1599,6 +1649,11 @@ impl SmgrQueryTimePerTimeline {
             .get_metric_with_label_values(&[&tenant_id, &shard_slug, &timeline_id])
             .unwrap();
 
+        let global_batch_wait_time = PAGE_SERVICE_SMGR_BATCH_WAIT_TIME_GLOBAL.clone();
+        let per_timeline_batch_wait_time = PAGE_SERVICE_SMGR_BATCH_WAIT_TIME
+            .get_metric_with_label_values(&[&tenant_id, &shard_slug, &timeline_id])
+            .unwrap();
+
         let global_flush_in_progress_micros =
             PAGE_SERVICE_SMGR_FLUSH_INPROGRESS_MICROS_GLOBAL.clone();
         let per_timeline_flush_in_progress_micros = PAGE_SERVICE_SMGR_FLUSH_INPROGRESS_MICROS
@@ -1614,9 +1669,11 @@ impl SmgrQueryTimePerTimeline {
             per_timeline_batch_size,
             global_flush_in_progress_micros,
             per_timeline_flush_in_progress_micros,
+            global_batch_wait_time,
+            per_timeline_batch_wait_time,
         }
     }
-    pub(crate) fn start_smgr_op(&self, op: SmgrQueryType, started_at: Instant) -> SmgrOpTimer {
+    pub(crate) fn start_smgr_op(&self, op: SmgrQueryType, received_at: Instant) -> SmgrOpTimer {
         self.global_started[op as usize].inc();
 
         let per_timeline_latency_histo = if matches!(op, SmgrQueryType::GetPageAtLsn) {
@@ -1627,15 +1684,15 @@ impl SmgrQueryTimePerTimeline {
         };
 
         SmgrOpTimer(Some(SmgrOpTimerInner {
-            global_latency_histo: self.global_latency[op as usize].clone(),
-            per_timeline_latency_histo,
-            start: started_at,
-            op,
-            throttled: Duration::ZERO,
+            global_execution_latency_histo: self.global_latency[op as usize].clone(),
+            per_timeline_execution_latency_histo: per_timeline_latency_histo,
+            timings: SmgrOpTimerState::Received { received_at },
             global_flush_in_progress_micros: self.global_flush_in_progress_micros.clone(),
             per_timeline_flush_in_progress_micros: self
                 .per_timeline_flush_in_progress_micros
                 .clone(),
+            global_batch_wait_time: self.global_batch_wait_time.clone(),
+            per_timeline_batch_wait_time: self.per_timeline_batch_wait_time.clone(),
         }))
     }
 
@@ -2520,7 +2577,6 @@ pub(crate) struct TimelineMetrics {
     shard_id: String,
     timeline_id: String,
     pub flush_time_histo: StorageTimeMetrics,
-    pub flush_wait_upload_time_gauge: Gauge,
     pub compact_time_histo: StorageTimeMetrics,
     pub create_images_time_histo: StorageTimeMetrics,
     pub logical_size_histo: StorageTimeMetrics,
@@ -2566,9 +2622,6 @@ impl TimelineMetrics {
             &shard_id,
             &timeline_id,
         );
-        let flush_wait_upload_time_gauge = FLUSH_WAIT_UPLOAD_TIME
-            .get_metric_with_label_values(&[&tenant_id, &shard_id, &timeline_id])
-            .unwrap();
         let compact_time_histo = StorageTimeMetrics::new(
             StorageTimeOperation::Compact,
             &tenant_id,
@@ -2714,7 +2767,6 @@ impl TimelineMetrics {
             shard_id,
             timeline_id,
             flush_time_histo,
-            flush_wait_upload_time_gauge,
             compact_time_histo,
             create_images_time_histo,
             logical_size_histo,
@@ -2764,14 +2816,6 @@ impl TimelineMetrics {
         self.resident_physical_size_gauge.get()
     }
 
-    pub(crate) fn flush_wait_upload_time_gauge_add(&self, duration: f64) {
-        self.flush_wait_upload_time_gauge.add(duration);
-        crate::metrics::FLUSH_WAIT_UPLOAD_TIME
-            .get_metric_with_label_values(&[&self.tenant_id, &self.shard_id, &self.timeline_id])
-            .unwrap()
-            .add(duration);
-    }
-
     pub(crate) fn shutdown(&self) {
         let was_shutdown = self
             .shutdown
@@ -2789,7 +2833,6 @@ impl TimelineMetrics {
         let shard_id = &self.shard_id;
         let _ = LAST_RECORD_LSN.remove_label_values(&[tenant_id, shard_id, timeline_id]);
         let _ = DISK_CONSISTENT_LSN.remove_label_values(&[tenant_id, shard_id, timeline_id]);
-        let _ = FLUSH_WAIT_UPLOAD_TIME.remove_label_values(&[tenant_id, shard_id, timeline_id]);
         let _ = STANDBY_HORIZON.remove_label_values(&[tenant_id, shard_id, timeline_id]);
         {
             RESIDENT_PHYSICAL_SIZE_GLOBAL.sub(self.resident_physical_size_get());
@@ -2889,6 +2932,11 @@ impl TimelineMetrics {
             shard_id,
             timeline_id,
         ]);
+        let _ = PAGE_SERVICE_SMGR_BATCH_WAIT_TIME.remove_label_values(&[
+            tenant_id,
+            shard_id,
+            timeline_id,
+        ]);
     }
 }
 
@@ -2919,6 +2967,7 @@ use crate::context::{PageContentKind, RequestContext};
 use crate::task_mgr::TaskKind;
 use crate::tenant::mgr::TenantSlot;
 use crate::tenant::tasks::BackgroundLoopKind;
+use crate::tenant::throttle::ThrottleResult;
 use crate::tenant::Timeline;
 
 /// Maintain a per timeline gauge in addition to the global gauge.
@@ -3773,6 +3822,7 @@ pub fn preinitialize_metrics(conf: &'static PageServerConf) {
         &REMOTE_ONDEMAND_DOWNLOADED_BYTES,
         &CIRCUIT_BREAKERS_BROKEN,
         &CIRCUIT_BREAKERS_UNBROKEN,
+        &PAGE_SERVICE_SMGR_FLUSH_INPROGRESS_MICROS_GLOBAL,
     ]
     .into_iter()
     .for_each(|c| {
@@ -3820,6 +3870,7 @@ pub fn preinitialize_metrics(conf: &'static PageServerConf) {
         &WAL_REDO_BYTES_HISTOGRAM,
         &WAL_REDO_PROCESS_LAUNCH_DURATION_HISTOGRAM,
         &PAGE_SERVICE_BATCH_SIZE_GLOBAL,
+        &PAGE_SERVICE_SMGR_BATCH_WAIT_TIME_GLOBAL,
     ]
     .into_iter()
     .for_each(|h| {

pageserver/src/page_service.rs

@@ -575,7 +575,10 @@ enum BatchedFeMessage {
 }
 
 impl BatchedFeMessage {
-    async fn throttle(&mut self, cancel: &CancellationToken) -> Result<(), QueryError> {
+    async fn throttle_and_record_start_processing(
+        &mut self,
+        cancel: &CancellationToken,
+    ) -> Result<(), QueryError> {
         let (shard, tokens, timers) = match self {
             BatchedFeMessage::Exists { shard, timer, .. }
             | BatchedFeMessage::Nblocks { shard, timer, .. }
@@ -603,7 +606,7 @@ impl BatchedFeMessage {
             }
         };
         for timer in timers {
-            timer.deduct_throttle(&throttled);
+            timer.observe_throttle_done_execution_starting(&throttled);
         }
         Ok(())
     }
@@ -1230,7 +1233,7 @@ impl PageServerHandler {
                 }
             };
 
-            if let Err(cancelled) = msg.throttle(&self.cancel).await {
+            if let Err(cancelled) = msg.throttle_and_record_start_processing(&self.cancel).await {
                 break cancelled;
             }
 
@@ -1397,7 +1400,9 @@ impl PageServerHandler {
                             return Err(e);
                         }
                     };
-                    batch.throttle(&self.cancel).await?;
+                    batch
+                        .throttle_and_record_start_processing(&self.cancel)
+                        .await?;
                     self.pagesteam_handle_batched_message(pgb_writer, batch, &cancel, &ctx)
                         .await?;
                 }

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,

pageserver/src/tenant.rs

@@ -44,6 +44,7 @@ use std::sync::atomic::AtomicBool;
 use std::sync::Weak;
 use std::time::SystemTime;
 use storage_broker::BrokerClientChannel;
+use timeline::compaction::GcCompactJob;
 use timeline::compaction::ScheduledCompactionTask;
 use timeline::import_pgdata;
 use timeline::offload::offload_timeline;
@@ -68,6 +69,7 @@ use utils::sync::gate::Gate;
 use utils::sync::gate::GateGuard;
 use utils::timeout::timeout_cancellable;
 use utils::timeout::TimeoutCancellableError;
+use utils::try_rcu::ArcSwapExt;
 use utils::zstd::create_zst_tarball;
 use utils::zstd::extract_zst_tarball;
 
@@ -3016,8 +3018,15 @@ impl Tenant {
                             warn!("ignoring scheduled compaction task: scheduled task must be gc compaction: {:?}", next_scheduled_compaction_task.options);
                         } else if next_scheduled_compaction_task.options.sub_compaction {
                             info!("running scheduled enhanced gc bottom-most compaction with sub-compaction, splitting compaction jobs");
-                            let jobs = timeline
-                                .gc_compaction_split_jobs(next_scheduled_compaction_task.options)
+                            let jobs: Vec<GcCompactJob> = timeline
+                                .gc_compaction_split_jobs(
+                                    GcCompactJob::from_compact_options(
+                                        next_scheduled_compaction_task.options.clone(),
+                                    ),
+                                    next_scheduled_compaction_task
+                                        .options
+                                        .sub_compaction_max_job_size_mb,
+                                )
                                 .await
                                 .map_err(CompactionError::Other)?;
                             if jobs.is_empty() {
@@ -3028,9 +3037,23 @@ impl Tenant {
                                 let mut guard = self.scheduled_compaction_tasks.lock().unwrap();
                                 let tline_pending_tasks = guard.entry(*timeline_id).or_default();
                                 for (idx, job) in jobs.into_iter().enumerate() {
+                                    // Unfortunately we need to convert the `GcCompactJob` back to `CompactionOptions`
+                                    // until we do further refactors to allow directly call `compact_with_gc`.
+                                    let mut flags: EnumSet<CompactFlags> = EnumSet::default();
+                                    flags |= CompactFlags::EnhancedGcBottomMostCompaction;
+                                    if job.dry_run {
+                                        flags |= CompactFlags::DryRun;
+                                    }
+                                    let options = CompactOptions {
+                                        flags,
+                                        sub_compaction: false,
+                                        compact_key_range: Some(job.compact_key_range.into()),
+                                        compact_lsn_range: Some(job.compact_lsn_range.into()),
+                                        sub_compaction_max_job_size_mb: None,
+                                    };
                                     tline_pending_tasks.push_back(if idx == jobs_len - 1 {
                                         ScheduledCompactionTask {
-                                            options: job,
+                                            options,
                                             // The last job in the queue sends the signal and releases the gc guard
                                             result_tx: next_scheduled_compaction_task
                                                 .result_tx
@@ -3041,7 +3064,7 @@ impl Tenant {
                                         }
                                     } else {
                                         ScheduledCompactionTask {
-                                            options: job,
+                                            options,
                                             result_tx: None,
                                             gc_block: None,
                                         }
@@ -3099,6 +3122,23 @@ 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,
@@ -3921,25 +3961,28 @@ impl Tenant {
         }
     }
 
-    pub fn set_new_tenant_config(&self, new_tenant_conf: TenantConfOpt) {
+    pub fn update_tenant_config<F: Fn(TenantConfOpt) -> anyhow::Result<TenantConfOpt>>(
+        &self,
+        update: F,
+    ) -> anyhow::Result<TenantConfOpt> {
         // Use read-copy-update in order to avoid overwriting the location config
         // state if this races with [`Tenant::set_new_location_config`]. Note that
         // this race is not possible if both request types come from the storage
         // controller (as they should!) because an exclusive op lock is required
         // on the storage controller side.
 
-        self.tenant_conf.rcu(|inner| {
-            Arc::new(AttachedTenantConf {
-                tenant_conf: new_tenant_conf.clone(),
-                location: inner.location,
-                // Attached location is not changed, no need to update lsn lease deadline.
-                lsn_lease_deadline: inner.lsn_lease_deadline,
-            })
-        });
+        self.tenant_conf
+            .try_rcu(|attached_conf| -> Result<_, anyhow::Error> {
+                Ok(Arc::new(AttachedTenantConf {
+                    tenant_conf: update(attached_conf.tenant_conf.clone())?,
+                    location: attached_conf.location,
+                    lsn_lease_deadline: attached_conf.lsn_lease_deadline,
+                }))
+            })?;
 
-        let updated = self.tenant_conf.load().clone();
+        let updated = self.tenant_conf.load();
 
-        self.tenant_conf_updated(&new_tenant_conf);
+        self.tenant_conf_updated(&updated.tenant_conf);
         // Don't hold self.timelines.lock() during the notifies.
         // There's no risk of deadlock right now, but there could be if we consolidate
         // mutexes in struct Timeline in the future.
@@ -3947,6 +3990,8 @@ impl Tenant {
         for timeline in timelines {
             timeline.tenant_conf_updated(&updated);
         }
+
+        Ok(updated.tenant_conf.clone())
     }
 
     pub(crate) fn set_new_location_config(&self, new_conf: AttachedTenantConf) {
@@ -4506,7 +4551,12 @@ impl Tenant {
                 // - this timeline was created while we were finding cutoffs
                 // - lsn for timestamp search fails for this timeline repeatedly
                 if let Some(cutoffs) = gc_cutoffs.get(&timeline.timeline_id) {
-                    target.cutoffs = cutoffs.clone();
+                    let original_cutoffs = target.cutoffs.clone();
+                    // GC cutoffs should never go back
+                    target.cutoffs = GcCutoffs {
+                        space: Lsn(cutoffs.space.0.max(original_cutoffs.space.0)),
+                        time: Lsn(cutoffs.time.0.max(original_cutoffs.time.0)),
+                    }
                 }
             }
 
@@ -5726,6 +5776,8 @@ 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")]
@@ -9322,7 +9374,6 @@ mod tests {
                 &cancel,
                 CompactOptions {
                     flags: dryrun_flags,
-                    compact_range: None,
                     ..Default::default()
                 },
                 &ctx,
@@ -9571,7 +9622,6 @@ mod tests {
                 &cancel,
                 CompactOptions {
                     flags: dryrun_flags,
-                    compact_range: None,
                     ..Default::default()
                 },
                 &ctx,
@@ -9601,6 +9651,8 @@ mod tests {
     #[cfg(feature = "testing")]
     #[tokio::test]
     async fn test_simple_bottom_most_compaction_on_branch() -> anyhow::Result<()> {
+        use models::CompactLsnRange;
+
         let harness = TenantHarness::create("test_simple_bottom_most_compaction_on_branch").await?;
         let (tenant, ctx) = harness.load().await;
 
@@ -9793,6 +9845,22 @@ mod tests {
 
         verify_result().await;
 
+        // Piggyback a compaction with above_lsn. Ensure it works correctly when the specified LSN intersects with the layer files.
+        // Now we already have a single large delta layer, so the compaction min_layer_lsn should be the same as ancestor LSN (0x18).
+        branch_tline
+            .compact_with_gc(
+                &cancel,
+                CompactOptions {
+                    compact_lsn_range: Some(CompactLsnRange::above(Lsn(0x40))),
+                    ..Default::default()
+                },
+                &ctx,
+            )
+            .await
+            .unwrap();
+
+        verify_result().await;
+
         Ok(())
     }
 
@@ -10081,7 +10149,7 @@ mod tests {
                 &cancel,
                 CompactOptions {
                     flags: EnumSet::new(),
-                    compact_range: Some((get_key(0)..get_key(2)).into()),
+                    compact_key_range: Some((get_key(0)..get_key(2)).into()),
                     ..Default::default()
                 },
                 &ctx,
@@ -10128,7 +10196,7 @@ mod tests {
                 &cancel,
                 CompactOptions {
                     flags: EnumSet::new(),
-                    compact_range: Some((get_key(2)..get_key(4)).into()),
+                    compact_key_range: Some((get_key(2)..get_key(4)).into()),
                     ..Default::default()
                 },
                 &ctx,
@@ -10180,7 +10248,7 @@ mod tests {
                 &cancel,
                 CompactOptions {
                     flags: EnumSet::new(),
-                    compact_range: Some((get_key(4)..get_key(9)).into()),
+                    compact_key_range: Some((get_key(4)..get_key(9)).into()),
                     ..Default::default()
                 },
                 &ctx,
@@ -10231,7 +10299,7 @@ mod tests {
                 &cancel,
                 CompactOptions {
                     flags: EnumSet::new(),
-                    compact_range: Some((get_key(9)..get_key(10)).into()),
+                    compact_key_range: Some((get_key(9)..get_key(10)).into()),
                     ..Default::default()
                 },
                 &ctx,
@@ -10287,7 +10355,7 @@ mod tests {
                 &cancel,
                 CompactOptions {
                     flags: EnumSet::new(),
-                    compact_range: Some((get_key(0)..get_key(10)).into()),
+                    compact_key_range: Some((get_key(0)..get_key(10)).into()),
                     ..Default::default()
                 },
                 &ctx,
@@ -10316,7 +10384,6 @@ mod tests {
                 },
             ],
         );
-
         Ok(())
     }
 
@@ -10369,4 +10436,602 @@ mod tests {
 
         Ok(())
     }
+
+    #[cfg(feature = "testing")]
+    #[tokio::test]
+    async fn test_simple_bottom_most_compaction_above_lsn() -> anyhow::Result<()> {
+        let harness = TenantHarness::create("test_simple_bottom_most_compaction_above_lsn").await?;
+        let (tenant, ctx) = harness.load().await;
+
+        fn get_key(id: u32) -> Key {
+            // using aux key here b/c they are guaranteed to be inside `collect_keyspace`.
+            let mut key = Key::from_hex("620000000033333333444444445500000000").unwrap();
+            key.field6 = id;
+            key
+        }
+
+        let img_layer = (0..10)
+            .map(|id| (get_key(id), Bytes::from(format!("value {id}@0x10"))))
+            .collect_vec();
+
+        let delta1 = vec![(
+            get_key(1),
+            Lsn(0x20),
+            Value::WalRecord(NeonWalRecord::wal_append("@0x20")),
+        )];
+        let delta4 = vec![(
+            get_key(1),
+            Lsn(0x28),
+            Value::WalRecord(NeonWalRecord::wal_append("@0x28")),
+        )];
+        let delta2 = vec![
+            (
+                get_key(1),
+                Lsn(0x30),
+                Value::WalRecord(NeonWalRecord::wal_append("@0x30")),
+            ),
+            (
+                get_key(1),
+                Lsn(0x38),
+                Value::WalRecord(NeonWalRecord::wal_append("@0x38")),
+            ),
+        ];
+        let delta3 = vec![
+            (
+                get_key(8),
+                Lsn(0x48),
+                Value::WalRecord(NeonWalRecord::wal_append("@0x48")),
+            ),
+            (
+                get_key(9),
+                Lsn(0x48),
+                Value::WalRecord(NeonWalRecord::wal_append("@0x48")),
+            ),
+        ];
+
+        let tline = tenant
+            .create_test_timeline_with_layers(
+                TIMELINE_ID,
+                Lsn(0x10),
+                DEFAULT_PG_VERSION,
+                &ctx,
+                vec![
+                    // delta1/2/4 only contain a single key but multiple updates
+                    DeltaLayerTestDesc::new_with_inferred_key_range(Lsn(0x20)..Lsn(0x28), delta1),
+                    DeltaLayerTestDesc::new_with_inferred_key_range(Lsn(0x30)..Lsn(0x50), delta2),
+                    DeltaLayerTestDesc::new_with_inferred_key_range(Lsn(0x28)..Lsn(0x30), delta4),
+                    DeltaLayerTestDesc::new_with_inferred_key_range(Lsn(0x30)..Lsn(0x50), delta3),
+                ], // delta layers
+                vec![(Lsn(0x10), img_layer)], // image layers
+                Lsn(0x50),
+            )
+            .await?;
+        {
+            tline
+                .latest_gc_cutoff_lsn
+                .lock_for_write()
+                .store_and_unlock(Lsn(0x30))
+                .wait()
+                .await;
+            // Update GC info
+            let mut guard = tline.gc_info.write().unwrap();
+            *guard = GcInfo {
+                retain_lsns: vec![
+                    (Lsn(0x10), tline.timeline_id, MaybeOffloaded::No),
+                    (Lsn(0x20), tline.timeline_id, MaybeOffloaded::No),
+                ],
+                cutoffs: GcCutoffs {
+                    time: Lsn(0x30),
+                    space: Lsn(0x30),
+                },
+                leases: Default::default(),
+                within_ancestor_pitr: false,
+            };
+        }
+
+        let expected_result = [
+            Bytes::from_static(b"value 0@0x10"),
+            Bytes::from_static(b"value 1@0x10@0x20@0x28@0x30@0x38"),
+            Bytes::from_static(b"value 2@0x10"),
+            Bytes::from_static(b"value 3@0x10"),
+            Bytes::from_static(b"value 4@0x10"),
+            Bytes::from_static(b"value 5@0x10"),
+            Bytes::from_static(b"value 6@0x10"),
+            Bytes::from_static(b"value 7@0x10"),
+            Bytes::from_static(b"value 8@0x10@0x48"),
+            Bytes::from_static(b"value 9@0x10@0x48"),
+        ];
+
+        let expected_result_at_gc_horizon = [
+            Bytes::from_static(b"value 0@0x10"),
+            Bytes::from_static(b"value 1@0x10@0x20@0x28@0x30"),
+            Bytes::from_static(b"value 2@0x10"),
+            Bytes::from_static(b"value 3@0x10"),
+            Bytes::from_static(b"value 4@0x10"),
+            Bytes::from_static(b"value 5@0x10"),
+            Bytes::from_static(b"value 6@0x10"),
+            Bytes::from_static(b"value 7@0x10"),
+            Bytes::from_static(b"value 8@0x10"),
+            Bytes::from_static(b"value 9@0x10"),
+        ];
+
+        let expected_result_at_lsn_20 = [
+            Bytes::from_static(b"value 0@0x10"),
+            Bytes::from_static(b"value 1@0x10@0x20"),
+            Bytes::from_static(b"value 2@0x10"),
+            Bytes::from_static(b"value 3@0x10"),
+            Bytes::from_static(b"value 4@0x10"),
+            Bytes::from_static(b"value 5@0x10"),
+            Bytes::from_static(b"value 6@0x10"),
+            Bytes::from_static(b"value 7@0x10"),
+            Bytes::from_static(b"value 8@0x10"),
+            Bytes::from_static(b"value 9@0x10"),
+        ];
+
+        let expected_result_at_lsn_10 = [
+            Bytes::from_static(b"value 0@0x10"),
+            Bytes::from_static(b"value 1@0x10"),
+            Bytes::from_static(b"value 2@0x10"),
+            Bytes::from_static(b"value 3@0x10"),
+            Bytes::from_static(b"value 4@0x10"),
+            Bytes::from_static(b"value 5@0x10"),
+            Bytes::from_static(b"value 6@0x10"),
+            Bytes::from_static(b"value 7@0x10"),
+            Bytes::from_static(b"value 8@0x10"),
+            Bytes::from_static(b"value 9@0x10"),
+        ];
+
+        let verify_result = || async {
+            let gc_horizon = {
+                let gc_info = tline.gc_info.read().unwrap();
+                gc_info.cutoffs.time
+            };
+            for idx in 0..10 {
+                assert_eq!(
+                    tline
+                        .get(get_key(idx as u32), Lsn(0x50), &ctx)
+                        .await
+                        .unwrap(),
+                    &expected_result[idx]
+                );
+                assert_eq!(
+                    tline
+                        .get(get_key(idx as u32), gc_horizon, &ctx)
+                        .await
+                        .unwrap(),
+                    &expected_result_at_gc_horizon[idx]
+                );
+                assert_eq!(
+                    tline
+                        .get(get_key(idx as u32), Lsn(0x20), &ctx)
+                        .await
+                        .unwrap(),
+                    &expected_result_at_lsn_20[idx]
+                );
+                assert_eq!(
+                    tline
+                        .get(get_key(idx as u32), Lsn(0x10), &ctx)
+                        .await
+                        .unwrap(),
+                    &expected_result_at_lsn_10[idx]
+                );
+            }
+        };
+
+        verify_result().await;
+
+        let cancel = CancellationToken::new();
+        tline
+            .compact_with_gc(
+                &cancel,
+                CompactOptions {
+                    compact_lsn_range: Some(CompactLsnRange::above(Lsn(0x28))),
+                    ..Default::default()
+                },
+                &ctx,
+            )
+            .await
+            .unwrap();
+        verify_result().await;
+
+        let all_layers = inspect_and_sort(&tline, Some(get_key(0)..get_key(10))).await;
+        check_layer_map_key_eq(
+            all_layers,
+            vec![
+                // The original image layer, not compacted
+                PersistentLayerKey {
+                    key_range: get_key(0)..get_key(10),
+                    lsn_range: Lsn(0x10)..Lsn(0x11),
+                    is_delta: false,
+                },
+                // Delta layer below the specified above_lsn not compacted
+                PersistentLayerKey {
+                    key_range: get_key(1)..get_key(2),
+                    lsn_range: Lsn(0x20)..Lsn(0x28),
+                    is_delta: true,
+                },
+                // Delta layer compacted above the LSN
+                PersistentLayerKey {
+                    key_range: get_key(1)..get_key(10),
+                    lsn_range: Lsn(0x28)..Lsn(0x50),
+                    is_delta: true,
+                },
+            ],
+        );
+
+        // compact again
+        tline
+            .compact_with_gc(&cancel, CompactOptions::default(), &ctx)
+            .await
+            .unwrap();
+        verify_result().await;
+
+        let all_layers = inspect_and_sort(&tline, Some(get_key(0)..get_key(10))).await;
+        check_layer_map_key_eq(
+            all_layers,
+            vec![
+                // The compacted image layer (full key range)
+                PersistentLayerKey {
+                    key_range: Key::MIN..Key::MAX,
+                    lsn_range: Lsn(0x10)..Lsn(0x11),
+                    is_delta: false,
+                },
+                // All other data in the delta layer
+                PersistentLayerKey {
+                    key_range: get_key(1)..get_key(10),
+                    lsn_range: Lsn(0x10)..Lsn(0x50),
+                    is_delta: true,
+                },
+            ],
+        );
+
+        Ok(())
+    }
+
+    #[cfg(feature = "testing")]
+    #[tokio::test]
+    async fn test_simple_bottom_most_compaction_rectangle() -> anyhow::Result<()> {
+        let harness = TenantHarness::create("test_simple_bottom_most_compaction_rectangle").await?;
+        let (tenant, ctx) = harness.load().await;
+
+        fn get_key(id: u32) -> Key {
+            // using aux key here b/c they are guaranteed to be inside `collect_keyspace`.
+            let mut key = Key::from_hex("620000000033333333444444445500000000").unwrap();
+            key.field6 = id;
+            key
+        }
+
+        let img_layer = (0..10)
+            .map(|id| (get_key(id), Bytes::from(format!("value {id}@0x10"))))
+            .collect_vec();
+
+        let delta1 = vec![(
+            get_key(1),
+            Lsn(0x20),
+            Value::WalRecord(NeonWalRecord::wal_append("@0x20")),
+        )];
+        let delta4 = vec![(
+            get_key(1),
+            Lsn(0x28),
+            Value::WalRecord(NeonWalRecord::wal_append("@0x28")),
+        )];
+        let delta2 = vec![
+            (
+                get_key(1),
+                Lsn(0x30),
+                Value::WalRecord(NeonWalRecord::wal_append("@0x30")),
+            ),
+            (
+                get_key(1),
+                Lsn(0x38),
+                Value::WalRecord(NeonWalRecord::wal_append("@0x38")),
+            ),
+        ];
+        let delta3 = vec![
+            (
+                get_key(8),
+                Lsn(0x48),
+                Value::WalRecord(NeonWalRecord::wal_append("@0x48")),
+            ),
+            (
+                get_key(9),
+                Lsn(0x48),
+                Value::WalRecord(NeonWalRecord::wal_append("@0x48")),
+            ),
+        ];
+
+        let tline = tenant
+            .create_test_timeline_with_layers(
+                TIMELINE_ID,
+                Lsn(0x10),
+                DEFAULT_PG_VERSION,
+                &ctx,
+                vec![
+                    // delta1/2/4 only contain a single key but multiple updates
+                    DeltaLayerTestDesc::new_with_inferred_key_range(Lsn(0x20)..Lsn(0x28), delta1),
+                    DeltaLayerTestDesc::new_with_inferred_key_range(Lsn(0x30)..Lsn(0x50), delta2),
+                    DeltaLayerTestDesc::new_with_inferred_key_range(Lsn(0x28)..Lsn(0x30), delta4),
+                    DeltaLayerTestDesc::new_with_inferred_key_range(Lsn(0x30)..Lsn(0x50), delta3),
+                ], // delta layers
+                vec![(Lsn(0x10), img_layer)], // image layers
+                Lsn(0x50),
+            )
+            .await?;
+        {
+            tline
+                .latest_gc_cutoff_lsn
+                .lock_for_write()
+                .store_and_unlock(Lsn(0x30))
+                .wait()
+                .await;
+            // Update GC info
+            let mut guard = tline.gc_info.write().unwrap();
+            *guard = GcInfo {
+                retain_lsns: vec![
+                    (Lsn(0x10), tline.timeline_id, MaybeOffloaded::No),
+                    (Lsn(0x20), tline.timeline_id, MaybeOffloaded::No),
+                ],
+                cutoffs: GcCutoffs {
+                    time: Lsn(0x30),
+                    space: Lsn(0x30),
+                },
+                leases: Default::default(),
+                within_ancestor_pitr: false,
+            };
+        }
+
+        let expected_result = [
+            Bytes::from_static(b"value 0@0x10"),
+            Bytes::from_static(b"value 1@0x10@0x20@0x28@0x30@0x38"),
+            Bytes::from_static(b"value 2@0x10"),
+            Bytes::from_static(b"value 3@0x10"),
+            Bytes::from_static(b"value 4@0x10"),
+            Bytes::from_static(b"value 5@0x10"),
+            Bytes::from_static(b"value 6@0x10"),
+            Bytes::from_static(b"value 7@0x10"),
+            Bytes::from_static(b"value 8@0x10@0x48"),
+            Bytes::from_static(b"value 9@0x10@0x48"),
+        ];
+
+        let expected_result_at_gc_horizon = [
+            Bytes::from_static(b"value 0@0x10"),
+            Bytes::from_static(b"value 1@0x10@0x20@0x28@0x30"),
+            Bytes::from_static(b"value 2@0x10"),
+            Bytes::from_static(b"value 3@0x10"),
+            Bytes::from_static(b"value 4@0x10"),
+            Bytes::from_static(b"value 5@0x10"),
+            Bytes::from_static(b"value 6@0x10"),
+            Bytes::from_static(b"value 7@0x10"),
+            Bytes::from_static(b"value 8@0x10"),
+            Bytes::from_static(b"value 9@0x10"),
+        ];
+
+        let expected_result_at_lsn_20 = [
+            Bytes::from_static(b"value 0@0x10"),
+            Bytes::from_static(b"value 1@0x10@0x20"),
+            Bytes::from_static(b"value 2@0x10"),
+            Bytes::from_static(b"value 3@0x10"),
+            Bytes::from_static(b"value 4@0x10"),
+            Bytes::from_static(b"value 5@0x10"),
+            Bytes::from_static(b"value 6@0x10"),
+            Bytes::from_static(b"value 7@0x10"),
+            Bytes::from_static(b"value 8@0x10"),
+            Bytes::from_static(b"value 9@0x10"),
+        ];
+
+        let expected_result_at_lsn_10 = [
+            Bytes::from_static(b"value 0@0x10"),
+            Bytes::from_static(b"value 1@0x10"),
+            Bytes::from_static(b"value 2@0x10"),
+            Bytes::from_static(b"value 3@0x10"),
+            Bytes::from_static(b"value 4@0x10"),
+            Bytes::from_static(b"value 5@0x10"),
+            Bytes::from_static(b"value 6@0x10"),
+            Bytes::from_static(b"value 7@0x10"),
+            Bytes::from_static(b"value 8@0x10"),
+            Bytes::from_static(b"value 9@0x10"),
+        ];
+
+        let verify_result = || async {
+            let gc_horizon = {
+                let gc_info = tline.gc_info.read().unwrap();
+                gc_info.cutoffs.time
+            };
+            for idx in 0..10 {
+                assert_eq!(
+                    tline
+                        .get(get_key(idx as u32), Lsn(0x50), &ctx)
+                        .await
+                        .unwrap(),
+                    &expected_result[idx]
+                );
+                assert_eq!(
+                    tline
+                        .get(get_key(idx as u32), gc_horizon, &ctx)
+                        .await
+                        .unwrap(),
+                    &expected_result_at_gc_horizon[idx]
+                );
+                assert_eq!(
+                    tline
+                        .get(get_key(idx as u32), Lsn(0x20), &ctx)
+                        .await
+                        .unwrap(),
+                    &expected_result_at_lsn_20[idx]
+                );
+                assert_eq!(
+                    tline
+                        .get(get_key(idx as u32), Lsn(0x10), &ctx)
+                        .await
+                        .unwrap(),
+                    &expected_result_at_lsn_10[idx]
+                );
+            }
+        };
+
+        verify_result().await;
+
+        let cancel = CancellationToken::new();
+
+        tline
+            .compact_with_gc(
+                &cancel,
+                CompactOptions {
+                    compact_key_range: Some((get_key(0)..get_key(2)).into()),
+                    compact_lsn_range: Some((Lsn(0x20)..Lsn(0x28)).into()),
+                    ..Default::default()
+                },
+                &ctx,
+            )
+            .await
+            .unwrap();
+        verify_result().await;
+
+        let all_layers = inspect_and_sort(&tline, Some(get_key(0)..get_key(10))).await;
+        check_layer_map_key_eq(
+            all_layers,
+            vec![
+                // The original image layer, not compacted
+                PersistentLayerKey {
+                    key_range: get_key(0)..get_key(10),
+                    lsn_range: Lsn(0x10)..Lsn(0x11),
+                    is_delta: false,
+                },
+                // According the selection logic, we select all layers with start key <= 0x28, so we would merge the layer 0x20-0x28 and
+                // the layer 0x28-0x30 into one.
+                PersistentLayerKey {
+                    key_range: get_key(1)..get_key(2),
+                    lsn_range: Lsn(0x20)..Lsn(0x30),
+                    is_delta: true,
+                },
+                // Above the upper bound and untouched
+                PersistentLayerKey {
+                    key_range: get_key(1)..get_key(2),
+                    lsn_range: Lsn(0x30)..Lsn(0x50),
+                    is_delta: true,
+                },
+                // This layer is untouched
+                PersistentLayerKey {
+                    key_range: get_key(8)..get_key(10),
+                    lsn_range: Lsn(0x30)..Lsn(0x50),
+                    is_delta: true,
+                },
+            ],
+        );
+
+        tline
+            .compact_with_gc(
+                &cancel,
+                CompactOptions {
+                    compact_key_range: Some((get_key(3)..get_key(8)).into()),
+                    compact_lsn_range: Some((Lsn(0x28)..Lsn(0x40)).into()),
+                    ..Default::default()
+                },
+                &ctx,
+            )
+            .await
+            .unwrap();
+        verify_result().await;
+
+        let all_layers = inspect_and_sort(&tline, Some(get_key(0)..get_key(10))).await;
+        check_layer_map_key_eq(
+            all_layers,
+            vec![
+                // The original image layer, not compacted
+                PersistentLayerKey {
+                    key_range: get_key(0)..get_key(10),
+                    lsn_range: Lsn(0x10)..Lsn(0x11),
+                    is_delta: false,
+                },
+                // Not in the compaction key range, uncompacted
+                PersistentLayerKey {
+                    key_range: get_key(1)..get_key(2),
+                    lsn_range: Lsn(0x20)..Lsn(0x30),
+                    is_delta: true,
+                },
+                // Not in the compaction key range, uncompacted but need rewrite because the delta layer overlaps with the range
+                PersistentLayerKey {
+                    key_range: get_key(1)..get_key(2),
+                    lsn_range: Lsn(0x30)..Lsn(0x50),
+                    is_delta: true,
+                },
+                // Note that when we specify the LSN upper bound to be 0x40, the compaction algorithm will not try to cut the layer
+                // horizontally in half. Instead, it will include all LSNs that overlap with 0x40. So the real max_lsn of the compaction
+                // becomes 0x50.
+                PersistentLayerKey {
+                    key_range: get_key(8)..get_key(10),
+                    lsn_range: Lsn(0x30)..Lsn(0x50),
+                    is_delta: true,
+                },
+            ],
+        );
+
+        // compact again
+        tline
+            .compact_with_gc(
+                &cancel,
+                CompactOptions {
+                    compact_key_range: Some((get_key(0)..get_key(5)).into()),
+                    compact_lsn_range: Some((Lsn(0x20)..Lsn(0x50)).into()),
+                    ..Default::default()
+                },
+                &ctx,
+            )
+            .await
+            .unwrap();
+        verify_result().await;
+
+        let all_layers = inspect_and_sort(&tline, Some(get_key(0)..get_key(10))).await;
+        check_layer_map_key_eq(
+            all_layers,
+            vec![
+                // The original image layer, not compacted
+                PersistentLayerKey {
+                    key_range: get_key(0)..get_key(10),
+                    lsn_range: Lsn(0x10)..Lsn(0x11),
+                    is_delta: false,
+                },
+                // The range gets compacted
+                PersistentLayerKey {
+                    key_range: get_key(1)..get_key(2),
+                    lsn_range: Lsn(0x20)..Lsn(0x50),
+                    is_delta: true,
+                },
+                // Not touched during this iteration of compaction
+                PersistentLayerKey {
+                    key_range: get_key(8)..get_key(10),
+                    lsn_range: Lsn(0x30)..Lsn(0x50),
+                    is_delta: true,
+                },
+            ],
+        );
+
+        // final full compaction
+        tline
+            .compact_with_gc(&cancel, CompactOptions::default(), &ctx)
+            .await
+            .unwrap();
+        verify_result().await;
+
+        let all_layers = inspect_and_sort(&tline, Some(get_key(0)..get_key(10))).await;
+        check_layer_map_key_eq(
+            all_layers,
+            vec![
+                // The compacted image layer (full key range)
+                PersistentLayerKey {
+                    key_range: Key::MIN..Key::MAX,
+                    lsn_range: Lsn(0x10)..Lsn(0x11),
+                    is_delta: false,
+                },
+                // All other data in the delta layer
+                PersistentLayerKey {
+                    key_range: get_key(1)..get_key(10),
+                    lsn_range: Lsn(0x10)..Lsn(0x50),
+                    is_delta: true,
+                },
+            ],
+        );
+
+        Ok(())
+    }
 }

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,

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,

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

pageserver/src/tenant/config.rs

@@ -11,7 +11,7 @@
 pub(crate) use pageserver_api::config::TenantConfigToml as TenantConf;
 use pageserver_api::models::CompactionAlgorithmSettings;
 use pageserver_api::models::EvictionPolicy;
-use pageserver_api::models::{self, ThrottleConfig};
+use pageserver_api::models::{self, TenantConfigPatch, ThrottleConfig};
 use pageserver_api::shard::{ShardCount, ShardIdentity, ShardNumber, ShardStripeSize};
 use serde::de::IntoDeserializer;
 use serde::{Deserialize, Serialize};
@@ -427,6 +427,129 @@ impl TenantConfOpt {
                 .or(global_conf.wal_receiver_protocol_override),
         }
     }
+
+    pub fn apply_patch(self, patch: TenantConfigPatch) -> anyhow::Result<TenantConfOpt> {
+        let Self {
+            mut checkpoint_distance,
+            mut checkpoint_timeout,
+            mut compaction_target_size,
+            mut compaction_period,
+            mut compaction_threshold,
+            mut compaction_algorithm,
+            mut gc_horizon,
+            mut gc_period,
+            mut image_creation_threshold,
+            mut pitr_interval,
+            mut walreceiver_connect_timeout,
+            mut lagging_wal_timeout,
+            mut max_lsn_wal_lag,
+            mut eviction_policy,
+            mut min_resident_size_override,
+            mut evictions_low_residence_duration_metric_threshold,
+            mut heatmap_period,
+            mut lazy_slru_download,
+            mut timeline_get_throttle,
+            mut image_layer_creation_check_threshold,
+            mut lsn_lease_length,
+            mut lsn_lease_length_for_ts,
+            mut timeline_offloading,
+            mut wal_receiver_protocol_override,
+        } = self;
+
+        patch.checkpoint_distance.apply(&mut checkpoint_distance);
+        patch
+            .checkpoint_timeout
+            .map(|v| humantime::parse_duration(&v))?
+            .apply(&mut checkpoint_timeout);
+        patch
+            .compaction_target_size
+            .apply(&mut compaction_target_size);
+        patch
+            .compaction_period
+            .map(|v| humantime::parse_duration(&v))?
+            .apply(&mut compaction_period);
+        patch.compaction_threshold.apply(&mut compaction_threshold);
+        patch.compaction_algorithm.apply(&mut compaction_algorithm);
+        patch.gc_horizon.apply(&mut gc_horizon);
+        patch
+            .gc_period
+            .map(|v| humantime::parse_duration(&v))?
+            .apply(&mut gc_period);
+        patch
+            .image_creation_threshold
+            .apply(&mut image_creation_threshold);
+        patch
+            .pitr_interval
+            .map(|v| humantime::parse_duration(&v))?
+            .apply(&mut pitr_interval);
+        patch
+            .walreceiver_connect_timeout
+            .map(|v| humantime::parse_duration(&v))?
+            .apply(&mut walreceiver_connect_timeout);
+        patch
+            .lagging_wal_timeout
+            .map(|v| humantime::parse_duration(&v))?
+            .apply(&mut lagging_wal_timeout);
+        patch.max_lsn_wal_lag.apply(&mut max_lsn_wal_lag);
+        patch.eviction_policy.apply(&mut eviction_policy);
+        patch
+            .min_resident_size_override
+            .apply(&mut min_resident_size_override);
+        patch
+            .evictions_low_residence_duration_metric_threshold
+            .map(|v| humantime::parse_duration(&v))?
+            .apply(&mut evictions_low_residence_duration_metric_threshold);
+        patch
+            .heatmap_period
+            .map(|v| humantime::parse_duration(&v))?
+            .apply(&mut heatmap_period);
+        patch.lazy_slru_download.apply(&mut lazy_slru_download);
+        patch
+            .timeline_get_throttle
+            .apply(&mut timeline_get_throttle);
+        patch
+            .image_layer_creation_check_threshold
+            .apply(&mut image_layer_creation_check_threshold);
+        patch
+            .lsn_lease_length
+            .map(|v| humantime::parse_duration(&v))?
+            .apply(&mut lsn_lease_length);
+        patch
+            .lsn_lease_length_for_ts
+            .map(|v| humantime::parse_duration(&v))?
+            .apply(&mut lsn_lease_length_for_ts);
+        patch.timeline_offloading.apply(&mut timeline_offloading);
+        patch
+            .wal_receiver_protocol_override
+            .apply(&mut wal_receiver_protocol_override);
+
+        Ok(Self {
+            checkpoint_distance,
+            checkpoint_timeout,
+            compaction_target_size,
+            compaction_period,
+            compaction_threshold,
+            compaction_algorithm,
+            gc_horizon,
+            gc_period,
+            image_creation_threshold,
+            pitr_interval,
+            walreceiver_connect_timeout,
+            lagging_wal_timeout,
+            max_lsn_wal_lag,
+            eviction_policy,
+            min_resident_size_override,
+            evictions_low_residence_duration_metric_threshold,
+            heatmap_period,
+            lazy_slru_download,
+            timeline_get_throttle,
+            image_layer_creation_check_threshold,
+            lsn_lease_length,
+            lsn_lease_length_for_ts,
+            timeline_offloading,
+            wal_receiver_protocol_override,
+        })
+    }
 }
 
 impl TryFrom<&'_ models::TenantConfig> for TenantConfOpt {

pageserver/src/tenant/disk_btree.rs

@@ -532,7 +532,7 @@ pub struct DiskBtreeIterator<'a> {
     >,
 }
 
-impl<'a> DiskBtreeIterator<'a> {
+impl DiskBtreeIterator<'_> {
     pub async fn next(&mut self) -> Option<std::result::Result<(Vec<u8>, u64), DiskBtreeError>> {
         self.stream.next().await
     }