pageserver: fix tenant::storage_layer::layer tests

## 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/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

@@ -15,19 +15,17 @@ inputs:
   prefix:
     description: "S3 prefix. Default is '${GITHUB_RUN_ID}/${GITHUB_RUN_ATTEMPT}'"
     required: false
-  aws_oicd_role_arn:
-    description: "the OIDC role arn for aws auth"
-    required: false
-    default: ""
+  aws-oicd-role-arn:
+    description: 'OIDC role arn to interract with S3'
+    required: true
 
 runs:
   using: "composite"
   steps:
-    - name: Configure AWS credentials
-      uses: aws-actions/configure-aws-credentials@v4
+    - uses: aws-actions/configure-aws-credentials@v4
       with:
         aws-region: eu-central-1
-        role-to-assume: ${{ inputs.aws_oicd_role_arn }}
+        role-to-assume: ${{ inputs.aws-oicd-role-arn }}
         role-duration-seconds: 3600
 
     - name: Download artifact

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

@@ -48,10 +48,9 @@ inputs:
     description: 'benchmark durations JSON'
     required: false
     default: '{}'
-  aws_oicd_role_arn:
-    description: 'the OIDC role arn to (re-)acquire for allure report upload - if not set call must acquire OIDC role'
-    required: false
-    default: ''
+  aws-oicd-role-arn:
+    description: 'OIDC role arn to interract with S3'
+    required: true
 
 runs:
   using: "composite"
@@ -62,7 +61,7 @@ runs:
       with:
         name: neon-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build_type }}-artifact
         path: /tmp/neon
-        aws_oicd_role_arn: ${{ inputs.aws_oicd_role_arn }}
+        aws-oicd-role-arn: ${{ inputs.aws-oicd-role-arn }}
 
     - name: Download Neon binaries for the previous release
       if: inputs.build_type != 'remote'
@@ -71,7 +70,7 @@ runs:
         name: neon-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build_type }}-artifact
         path: /tmp/neon-previous
         prefix: latest
-        aws_oicd_role_arn: ${{ inputs.aws_oicd_role_arn }}
+        aws-oicd-role-arn: ${{ inputs.aws-oicd-role-arn }}
 
     - name: Download compatibility snapshot
       if: inputs.build_type != 'remote'
@@ -83,7 +82,7 @@ runs:
         # The lack of compatibility snapshot (for example, for the new Postgres version)
         # shouldn't fail the whole job. Only relevant test should fail.
         skip-if-does-not-exist: true
-        aws_oicd_role_arn: ${{ inputs.aws_oicd_role_arn }}
+        aws-oicd-role-arn: ${{ inputs.aws-oicd-role-arn }}
 
     - name: Checkout
       if: inputs.needs_postgres_source == 'true'
@@ -221,19 +220,19 @@ runs:
         # The lack of compatibility snapshot shouldn't fail the job
         # (for example if we didn't run the test for non build-and-test workflow)
         skip-if-does-not-exist: true
-        aws_oicd_role_arn: ${{ inputs.aws_oicd_role_arn }}
+        aws-oicd-role-arn: ${{ inputs.aws-oicd-role-arn }}
 
-    - name: (Re-)configure AWS credentials # necessary to upload reports to S3 after a long-running test
-      if: ${{ !cancelled() && (inputs.aws_oicd_role_arn != '') }}
-      uses: aws-actions/configure-aws-credentials@v4
+    - uses: aws-actions/configure-aws-credentials@v4
+      if: ${{ !cancelled() }}
       with:
         aws-region: eu-central-1
-        role-to-assume: ${{ inputs.aws_oicd_role_arn }}
+        role-to-assume: ${{ inputs.aws-oicd-role-arn }}
         role-duration-seconds: 3600 # 1 hour should be more than enough to upload report
+
     - name: Upload test results
       if: ${{ !cancelled() }}
       uses: ./.github/actions/allure-report-store
       with:
         report-dir: /tmp/test_output/allure/results
         unique-key: ${{ inputs.build_type }}-${{ inputs.pg_version }}
-        aws_oicd_role_arn: ${{ inputs.aws_oicd_role_arn }}
+        aws-oicd-role-arn: ${{ inputs.aws-oicd-role-arn }}

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

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

.github/actions/upload/action.yml

@@ -14,7 +14,7 @@ inputs:
   prefix:
     description: "S3 prefix. Default is '${GITHUB_SHA}/${GITHUB_RUN_ID}/${GITHUB_RUN_ATTEMPT}'"
     required: false
-  aws_oicd_role_arn:
+  aws-oicd-role-arn:
     description: "the OIDC role arn for aws auth"
     required: false
     default: ""
@@ -61,7 +61,7 @@ runs:
       uses: aws-actions/configure-aws-credentials@v4
       with:
         aws-region: eu-central-1
-        role-to-assume: ${{ inputs.aws_oicd_role_arn }}
+        role-to-assume: ${{ inputs.aws-oicd-role-arn }}
         role-duration-seconds: 3600
 
     - name: Upload artifact

.github/workflows/_benchmarking_preparation.yml

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

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

@@ -264,7 +264,7 @@ jobs:
         with:
           name: neon-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-artifact
           path: /tmp/neon
-          aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+          aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
       # XXX: keep this after the binaries.list is formed, so the coverage can properly work later
       - name: Merge and upload coverage data
@@ -308,7 +308,7 @@ jobs:
           real_s3_region: eu-central-1
           rerun_failed: true
           pg_version: ${{ matrix.pg_version }}
-          aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+          aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
         env:
           TEST_RESULT_CONNSTR: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}
           CHECK_ONDISK_DATA_COMPATIBILITY: nonempty

.github/workflows/benchmarking.yml

@@ -105,7 +105,7 @@ jobs:
         name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
         path: /tmp/neon/
         prefix: latest
-        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
     - name: Create Neon Project
       id: create-neon-project
@@ -123,7 +123,7 @@ jobs:
         run_in_parallel: false
         save_perf_report: ${{ env.SAVE_PERF_REPORT }}
         pg_version: ${{ env.DEFAULT_PG_VERSION }}
-        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
         # Set --sparse-ordering option of pytest-order plugin
         # to ensure tests are running in order of appears in the file.
         # It's important for test_perf_pgbench.py::test_pgbench_remote_* tests
@@ -153,7 +153,7 @@ jobs:
       if: ${{ !cancelled() }}
       uses: ./.github/actions/allure-report-generate
       with:
-        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
     - name: Post to a Slack channel
       if: ${{ github.event.schedule && failure() }}
@@ -205,7 +205,7 @@ jobs:
         name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
         path: /tmp/neon/
         prefix: latest
-        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
     - name: Run Logical Replication benchmarks
       uses: ./.github/actions/run-python-test-set
@@ -216,7 +216,7 @@ jobs:
         save_perf_report: ${{ env.SAVE_PERF_REPORT }}
         extra_params: -m remote_cluster --timeout 5400
         pg_version: ${{ env.DEFAULT_PG_VERSION }}
-        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
       env:
         VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
         PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
@@ -233,7 +233,7 @@ jobs:
         save_perf_report: ${{ env.SAVE_PERF_REPORT }}
         extra_params: -m remote_cluster --timeout 5400
         pg_version: ${{ env.DEFAULT_PG_VERSION }}
-        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
       env:
         VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
         PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
@@ -245,7 +245,7 @@ jobs:
       uses: ./.github/actions/allure-report-generate
       with:
         store-test-results-into-db: true
-        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
       env:
         REGRESS_TEST_RESULT_CONNSTR_NEW: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}
 
@@ -308,6 +308,7 @@ jobs:
           "image": [ "'"$image_default"'" ],
           "include": [{ "pg_version": 16, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-freetier",       "db_size": "3gb" ,"runner": '"$runner_default"', "image": "'"$image_default"'" },
                       { "pg_version": 16, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-new",            "db_size": "10gb","runner": '"$runner_default"', "image": "'"$image_default"'" },
+                      { "pg_version": 16, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-new-many-tables","db_size": "10gb","runner": '"$runner_default"', "image": "'"$image_default"'" },
                       { "pg_version": 16, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-new",            "db_size": "50gb","runner": '"$runner_default"', "image": "'"$image_default"'" },
                       { "pg_version": 16, "region_id": "azure-eastus2",          "platform": "neonvm-azure-captest-freetier", "db_size": "3gb" ,"runner": '"$runner_azure"',   "image": "neondatabase/build-tools:pinned-bookworm" },
                       { "pg_version": 16, "region_id": "azure-eastus2",          "platform": "neonvm-azure-captest-new",      "db_size": "10gb","runner": '"$runner_azure"',   "image": "neondatabase/build-tools:pinned-bookworm" },
@@ -407,10 +408,10 @@ jobs:
         name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
         path: /tmp/neon/
         prefix: latest
-        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
     - name: Create Neon Project
-      if: contains(fromJson('["neonvm-captest-new", "neonvm-captest-freetier", "neonvm-azure-captest-freetier", "neonvm-azure-captest-new"]'), matrix.platform)
+      if: contains(fromJson('["neonvm-captest-new", "neonvm-captest-new-many-tables", "neonvm-captest-freetier", "neonvm-azure-captest-freetier", "neonvm-azure-captest-new"]'), matrix.platform)
       id: create-neon-project
       uses: ./.github/actions/neon-project-create
       with:
@@ -429,7 +430,7 @@ jobs:
           neonvm-captest-sharding-reuse)
             CONNSTR=${{ secrets.BENCHMARK_CAPTEST_SHARDING_CONNSTR }}
             ;;
-          neonvm-captest-new | neonvm-captest-freetier | neonvm-azure-captest-new | neonvm-azure-captest-freetier)
+          neonvm-captest-new | neonvm-captest-new-many-tables | neonvm-captest-freetier | neonvm-azure-captest-new | neonvm-azure-captest-freetier)
             CONNSTR=${{ steps.create-neon-project.outputs.dsn }}
             ;;
           rds-aurora)
@@ -446,6 +447,26 @@ jobs:
 
         echo "connstr=${CONNSTR}" >> $GITHUB_OUTPUT
 
+    # we want to compare Neon project OLTP throughput and latency at scale factor 10 GB 
+    # without (neonvm-captest-new)
+    # and with (neonvm-captest-new-many-tables) many relations in the database
+    - name: Create many relations before the run
+      if: contains(fromJson('["neonvm-captest-new-many-tables"]'), matrix.platform)
+      uses: ./.github/actions/run-python-test-set
+      with:
+        build_type: ${{ env.BUILD_TYPE }}
+        test_selection: performance
+        run_in_parallel: false
+        save_perf_report: ${{ env.SAVE_PERF_REPORT }}
+        extra_params: -m remote_cluster --timeout 21600 -k test_perf_many_relations
+        pg_version: ${{ env.DEFAULT_PG_VERSION }}
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+      env:
+        BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
+        VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
+        PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
+        TEST_NUM_RELATIONS: 10000
+
     - name: Benchmark init
       uses: ./.github/actions/run-python-test-set
       with:
@@ -455,7 +476,7 @@ jobs:
         save_perf_report: ${{ env.SAVE_PERF_REPORT }}
         extra_params: -m remote_cluster --timeout 21600 -k test_pgbench_remote_init
         pg_version: ${{ env.DEFAULT_PG_VERSION }}
-        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
       env:
         BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
         VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
@@ -470,7 +491,7 @@ jobs:
         save_perf_report: ${{ env.SAVE_PERF_REPORT }}
         extra_params: -m remote_cluster --timeout 21600 -k test_pgbench_remote_simple_update
         pg_version: ${{ env.DEFAULT_PG_VERSION }}
-        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
       env:
         BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
         VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
@@ -485,7 +506,7 @@ jobs:
         save_perf_report: ${{ env.SAVE_PERF_REPORT }}
         extra_params: -m remote_cluster --timeout 21600 -k test_pgbench_remote_select_only
         pg_version: ${{ env.DEFAULT_PG_VERSION }}
-        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
       env:
         BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
         VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
@@ -503,7 +524,7 @@ jobs:
       if: ${{ !cancelled() }}
       uses: ./.github/actions/allure-report-generate
       with:
-        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
     - name: Post to a Slack channel
       if: ${{ github.event.schedule && failure() }}
@@ -614,7 +635,7 @@ jobs:
         save_perf_report: ${{ env.SAVE_PERF_REPORT }}
         extra_params: -m remote_cluster --timeout 21600 -k test_pgvector_indexing
         pg_version: ${{ env.DEFAULT_PG_VERSION }}
-        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
       env:
         VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
         PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
@@ -629,7 +650,7 @@ jobs:
         save_perf_report: ${{ env.SAVE_PERF_REPORT }}
         extra_params: -m remote_cluster --timeout 21600
         pg_version: ${{ env.DEFAULT_PG_VERSION }}
-        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
       env:
         BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
         VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
@@ -640,7 +661,7 @@ jobs:
       if: ${{ !cancelled() }}
       uses: ./.github/actions/allure-report-generate
       with:
-        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
     - name: Post to a Slack channel
       if: ${{ github.event.schedule && failure() }}
@@ -711,7 +732,7 @@ jobs:
         name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
         path: /tmp/neon/
         prefix: latest
-        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
     - name: Set up Connection String
       id: set-up-connstr
@@ -743,7 +764,7 @@ jobs:
         save_perf_report: ${{ env.SAVE_PERF_REPORT }}
         extra_params: -m remote_cluster --timeout 43200 -k test_clickbench
         pg_version: ${{ env.DEFAULT_PG_VERSION }}
-        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
       env:
         VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
         PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
@@ -757,7 +778,7 @@ jobs:
       if: ${{ !cancelled() }}
       uses: ./.github/actions/allure-report-generate
       with:
-        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
     - name: Post to a Slack channel
       if: ${{ github.event.schedule && failure() }}
@@ -822,7 +843,7 @@ jobs:
         name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
         path: /tmp/neon/
         prefix: latest
-        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
     - name: Get Connstring Secret Name
       run: |
@@ -861,7 +882,7 @@ jobs:
         save_perf_report: ${{ env.SAVE_PERF_REPORT }}
         extra_params: -m remote_cluster --timeout 21600 -k test_tpch
         pg_version: ${{ env.DEFAULT_PG_VERSION }}
-        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
       env:
         VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
         PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
@@ -873,7 +894,7 @@ jobs:
       if: ${{ !cancelled() }}
       uses: ./.github/actions/allure-report-generate
       with:
-        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
     - name: Post to a Slack channel
       if: ${{ github.event.schedule && failure() }}
@@ -931,7 +952,7 @@ jobs:
         name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
         path: /tmp/neon/
         prefix: latest
-        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
     - name: Set up Connection String
       id: set-up-connstr
@@ -963,7 +984,7 @@ jobs:
         save_perf_report: ${{ env.SAVE_PERF_REPORT }}
         extra_params: -m remote_cluster --timeout 21600 -k test_user_examples
         pg_version: ${{ env.DEFAULT_PG_VERSION }}
-        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
       env:
         VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
         PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
@@ -974,7 +995,7 @@ jobs:
       if: ${{ !cancelled() }}
       uses: ./.github/actions/allure-report-generate
       with:
-        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
     - name: Post to a Slack channel
       if: ${{ github.event.schedule && failure() }}

.github/workflows/build_and_test.yml

@@ -254,16 +254,14 @@ jobs:
       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 and debug builds only. For all the other cases LFC is enabled. Failure on the
-      # debug build with LFC enabled doesn't block merging.
+      # 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": "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"},
-                                                {"pg_version":"v17", "lfc_state": "with-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:
@@ -385,7 +394,7 @@ jobs:
         uses: ./.github/actions/allure-report-generate
         with:
           store-test-results-into-db: true
-          aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+          aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
         env:
           REGRESS_TEST_RESULT_CONNSTR_NEW: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}
 
@@ -447,14 +456,14 @@ jobs:
         with:
           name: neon-${{ runner.os }}-${{ runner.arch }}-${{ matrix.build_type }}-artifact
           path: /tmp/neon
-          aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+          aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
       - name: Get coverage artifact
         uses: ./.github/actions/download
         with:
           name: coverage-data-artifact
           path: /tmp/coverage
-          aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+          aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
       - name: Merge coverage data
         run: scripts/coverage "--profraw-prefix=$GITHUB_JOB" --dir=/tmp/coverage merge
@@ -1026,6 +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: |
@@ -1145,7 +1159,7 @@ jobs:
               console.log(`Tag ${tag} created successfully.`);
             }
 
-            # TODO: check how GitHub releases looks for proxy/compute releases and enable them if they're ok
+            // 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 ${context.ref}.`);
               return;
@@ -1266,6 +1280,12 @@ jobs:
           echo "run-id=${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

@@ -21,6 +21,8 @@ concurrency:
 
 permissions:
   id-token: write # aws-actions/configure-aws-credentials
+  statuses: write
+  contents: write
 
 jobs:
   regress:
@@ -79,7 +81,7 @@ jobs:
           name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
           path: /tmp/neon/
           prefix: latest
-          aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+          aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
       - name: Create a new branch
         id: create-branch
@@ -95,10 +97,12 @@ jobs:
           test_selection: cloud_regress
           pg_version: ${{matrix.pg-version}}
           extra_params: -m remote_cluster
+          aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
         env:
           BENCHMARK_CONNSTR: ${{steps.create-branch.outputs.dsn}}
 
       - name: Delete branch
+        if: always()
         uses: ./.github/actions/neon-branch-delete
         with:
           api_key: ${{ secrets.NEON_STAGING_API_KEY }}
@@ -110,7 +114,7 @@ jobs:
         if: ${{ !cancelled() }}
         uses: ./.github/actions/allure-report-generate
         with:
-          aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+          aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
       - name: Post to a Slack channel
         if: ${{ github.event.schedule && failure() }}

.github/workflows/ingest_benchmark.yml

@@ -13,7 +13,7 @@ on:
     #          │ │ │ │ ┌───────────── day of the week (0 - 6 or SUN-SAT)
     - cron:   '0 9 * * *' # run once a day, timezone is utc
   workflow_dispatch: # adds ability to run this manually
-    
+
 defaults:
   run:
     shell: bash -euxo pipefail {0}
@@ -28,7 +28,7 @@ jobs:
     strategy:
       fail-fast: false # allow other variants to continue even if one fails
       matrix:
-        target_project: [new_empty_project, large_existing_project]  
+        target_project: [new_empty_project, large_existing_project]
     permissions:
       contents: write
       statuses: write
@@ -56,7 +56,7 @@ jobs:
       with:
         aws-region: eu-central-1
         role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
-        role-duration-seconds: 18000 # 5 hours is currently max associated with IAM role 
+        role-duration-seconds: 18000 # 5 hours is currently max associated with IAM role
 
     - name: Download Neon artifact
       uses: ./.github/actions/download
@@ -64,7 +64,7 @@ jobs:
         name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
         path: /tmp/neon/
         prefix: latest
-        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
     - name: Create Neon Project
       if: ${{ matrix.target_project == 'new_empty_project' }}
@@ -95,7 +95,7 @@ jobs:
         project_id: ${{ vars.BENCHMARK_INGEST_TARGET_PROJECTID }}
         api_key: ${{ secrets.NEON_STAGING_API_KEY }}
 
-    - name: Initialize Neon project 
+    - name: Initialize Neon project
       if: ${{ matrix.target_project == 'large_existing_project' }}
       env:
           BENCHMARK_INGEST_TARGET_CONNSTR: ${{ steps.create-neon-branch-ingest-target.outputs.dsn }}
@@ -123,7 +123,7 @@ jobs:
         ${PSQL} "${BENCHMARK_INGEST_TARGET_CONNSTR}" -c "CREATE EXTENSION IF NOT EXISTS neon; CREATE EXTENSION IF NOT EXISTS neon_utils;"
         echo "BENCHMARK_INGEST_TARGET_CONNSTR=${BENCHMARK_INGEST_TARGET_CONNSTR}" >> $GITHUB_ENV
 
-    - name: Invoke pgcopydb  
+    - name: Invoke pgcopydb
       uses: ./.github/actions/run-python-test-set
       with:
         build_type: remote
@@ -132,7 +132,7 @@ jobs:
         extra_params: -s -m remote_cluster --timeout 86400 -k test_ingest_performance_using_pgcopydb
         pg_version: v16
         save_perf_report: true
-        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
       env:
         BENCHMARK_INGEST_SOURCE_CONNSTR: ${{ secrets.BENCHMARK_INGEST_SOURCE_CONNSTR }}
         TARGET_PROJECT_TYPE: ${{ matrix.target_project }}
@@ -144,7 +144,7 @@ jobs:
       run: |
         export LD_LIBRARY_PATH=${PG_16_LIB_PATH}
         ${PSQL} "${BENCHMARK_INGEST_TARGET_CONNSTR}" -c "\dt+"
-      
+
     - name: Delete Neon Project
       if: ${{ always() && matrix.target_project == 'new_empty_project' }}
       uses: ./.github/actions/neon-project-delete

.github/workflows/periodic_pagebench.yml

@@ -21,15 +21,17 @@ defaults:
   run:
     shell: bash -euo pipefail {0}
 
-permissions:
-  id-token: write # aws-actions/configure-aws-credentials
-
 concurrency:
   group: ${{ github.workflow }}
   cancel-in-progress: false
 
 jobs:
   trigger_bench_on_ec2_machine_in_eu_central_1:
+    permissions:
+      id-token: write # aws-actions/configure-aws-credentials
+      statuses: write
+      contents: write
+      pull-requests: write
     runs-on: [ self-hosted, small ]
     container:
       image: neondatabase/build-tools:pinned-bookworm
@@ -135,7 +137,7 @@ jobs:
       if: ${{ !cancelled() }}
       uses: ./.github/actions/allure-report-generate
       with:
-        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
     - name: Post to a Slack channel
       if: ${{ github.event.schedule && failure() }}

.github/workflows/pg-clients.yml

@@ -96,7 +96,7 @@ jobs:
           name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
           path: /tmp/neon/
           prefix: latest
-          aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+          aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
       - name: Create Neon Project
         id: create-neon-project
@@ -113,6 +113,7 @@ jobs:
           run_in_parallel: false
           extra_params: -m remote_cluster
           pg_version: ${{ env.DEFAULT_PG_VERSION }}
+          aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
         env:
           BENCHMARK_CONNSTR: ${{ steps.create-neon-project.outputs.dsn }}
 
@@ -129,7 +130,7 @@ jobs:
         uses: ./.github/actions/allure-report-generate
         with:
           store-test-results-into-db: true
-          aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+          aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
         env:
           REGRESS_TEST_RESULT_CONNSTR_NEW: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}
 
@@ -163,7 +164,7 @@ jobs:
         name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
         path: /tmp/neon/
         prefix: latest
-        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
     - name: Create Neon Project
       id: create-neon-project
@@ -180,6 +181,7 @@ jobs:
         run_in_parallel: false
         extra_params: -m remote_cluster
         pg_version: ${{ env.DEFAULT_PG_VERSION }}
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
       env:
         BENCHMARK_CONNSTR: ${{ steps.create-neon-project.outputs.dsn }}
 
@@ -196,7 +198,7 @@ jobs:
       uses: ./.github/actions/allure-report-generate
       with:
         store-test-results-into-db: true
-        aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
       env:
         REGRESS_TEST_RESULT_CONNSTR_NEW: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}
 

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",
 ]
@@ -3930,6 +3945,7 @@ dependencies = [
  "serde_json",
  "serde_path_to_error",
  "serde_with",
+ "serial_test",
  "smallvec",
  "storage_broker",
  "strum",
@@ -4401,11 +4417,13 @@ dependencies = [
  "bindgen",
  "bytes",
  "crc32c",
+ "criterion",
  "env_logger",
  "log",
  "memoffset 0.9.0",
  "once_cell",
  "postgres",
+ "pprof",
  "regex",
  "serde",
  "thiserror",
@@ -5062,6 +5080,7 @@ dependencies = [
  "once_cell",
  "pin-project-lite",
  "rand 0.8.5",
+ "reqwest",
  "scopeguard",
  "serde",
  "serde_json",
@@ -5320,9 +5339,9 @@ dependencies = [
 
 [[package]]
 name = "rustc-demangle"
-version = "0.1.23"
+version = "0.1.24"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d626bb9dae77e28219937af045c257c28bfd3f69333c512553507f5f9798cb76"
+checksum = "719b953e2095829ee67db738b3bfa9fa368c94900df327b3f07fe6e794d2fe1f"
 
 [[package]]
 name = "rustc-hash"
@@ -5535,6 +5554,7 @@ dependencies = [
  "remote_storage",
  "reqwest",
  "safekeeper_api",
+ "safekeeper_client",
  "scopeguard",
  "sd-notify",
  "serde",
@@ -5565,10 +5585,25 @@ name = "safekeeper_api"
 version = "0.1.0"
 dependencies = [
  "const_format",
+ "postgres_ffi",
+ "pq_proto",
  "serde",
+ "tokio",
  "utils",
 ]
 
+[[package]]
+name = "safekeeper_client"
+version = "0.1.0"
+dependencies = [
+ "reqwest",
+ "safekeeper_api",
+ "serde",
+ "thiserror",
+ "utils",
+ "workspace_hack",
+]
+
 [[package]]
 name = "same-file"
 version = "1.0.6"
@@ -5578,6 +5613,15 @@ dependencies = [
  "winapi-util",
 ]
 
+[[package]]
+name = "scc"
+version = "2.2.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "94b13f8ea6177672c49d12ed964cca44836f59621981b04a3e26b87e675181de"
+dependencies = [
+ "sdd",
+]
+
 [[package]]
 name = "schannel"
 version = "0.1.23"
@@ -5618,6 +5662,12 @@ version = "0.4.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "621e3680f3e07db4c9c2c3fb07c6223ab2fab2e54bd3c04c3ae037990f428c32"
 
+[[package]]
+name = "sdd"
+version = "3.0.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "478f121bb72bbf63c52c93011ea1791dca40140dfe13f8336c4c5ac952c33aa9"
+
 [[package]]
 name = "sec1"
 version = "0.3.0"
@@ -5907,6 +5957,31 @@ dependencies = [
  "serde",
 ]
 
+[[package]]
+name = "serial_test"
+version = "3.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1b258109f244e1d6891bf1053a55d63a5cd4f8f4c30cf9a1280989f80e7a1fa9"
+dependencies = [
+ "futures",
+ "log",
+ "once_cell",
+ "parking_lot 0.12.1",
+ "scc",
+ "serial_test_derive",
+]
+
+[[package]]
+name = "serial_test_derive"
+version = "3.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5d69265a08751de7844521fd15003ae0a888e035773ba05695c5c759a6f89eef"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.90",
+]
+
 [[package]]
 name = "sha1"
 version = "0.10.5"
@@ -7200,6 +7275,7 @@ dependencies = [
  "anyhow",
  "arc-swap",
  "async-compression",
+ "backtrace",
  "bincode",
  "byteorder",
  "bytes",
@@ -7210,12 +7286,14 @@ 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 +7650,7 @@ 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 +7659,7 @@ 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 +7677,7 @@ 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 +7697,18 @@ 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 +7719,9 @@ 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 +7731,9 @@ 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 +7743,15 @@ 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 +7761,9 @@ 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 +7773,9 @@ 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 +7785,9 @@ 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 +7797,9 @@ 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"
@@ -159,6 +161,7 @@ serde_json = "1"
 serde_path_to_error = "0.1"
 serde_with = { version = "2.0", features = [ "base64" ] }
 serde_assert = "0.5.0"
+serial_test = "3.2.0"
 sha2 = "0.10.2"
 signal-hook = "0.3"
 smallvec = "1.11"
@@ -233,6 +236,7 @@ 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/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/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"))
     }
 }

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");

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") {

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

@@ -5,7 +5,8 @@ use clap::{Parser, Subcommand};
 use pageserver_api::{
     controller_api::{
         AvailabilityZone, NodeAvailabilityWrapper, NodeDescribeResponse, NodeShardResponse,
-        ShardSchedulingPolicy, TenantCreateRequest, TenantDescribeResponse, TenantPolicyRequest,
+        SafekeeperDescribeResponse, ShardSchedulingPolicy, TenantCreateRequest,
+        TenantDescribeResponse, TenantPolicyRequest,
     },
     models::{
         EvictionPolicy, EvictionPolicyLayerAccessThreshold, LocationConfigSecondary,
@@ -211,6 +212,8 @@ enum Command {
         #[arg(long)]
         timeout: humantime::Duration,
     },
+    /// List safekeepers known to the storage controller
+    Safekeepers {},
 }
 
 #[derive(Parser)]
@@ -1020,6 +1023,31 @@ async fn main() -> anyhow::Result<()> {
                 "Fill was cancelled for node {node_id}. Schedulling policy is now {final_policy:?}"
             );
         }
+        Command::Safekeepers {} => {
+            let mut resp = storcon_client
+                .dispatch::<(), Vec<SafekeeperDescribeResponse>>(
+                    Method::GET,
+                    "control/v1/safekeeper".to_string(),
+                    None,
+                )
+                .await?;
+
+            resp.sort_by(|a, b| a.id.cmp(&b.id));
+
+            let mut table = comfy_table::Table::new();
+            table.set_header(["Id", "Version", "Host", "Port", "Http Port", "AZ Id"]);
+            for sk in resp {
+                table.add_row([
+                    format!("{}", sk.id),
+                    format!("{}", sk.version),
+                    sk.host,
+                    format!("{}", sk.port),
+                    format!("{}", sk.http_port),
+                    sk.availability_zone_id.to_string(),
+                ]);
+            }
+            println!("{table}");
+        }
     }
 
     Ok(())

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/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

@@ -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

@@ -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,
@@ -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,

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

@@ -96,6 +96,8 @@ pub mod circuit_breaker;
 
 pub mod try_rcu;
 
+pub mod pprof;
+
 // Re-export used in macro. Avoids adding git-version as dep in target crates.
 #[doc(hidden)]
 pub use git_version;

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
+}

pageserver/Cargo.toml

@@ -94,6 +94,7 @@ procfs.workspace = true
 [dev-dependencies]
 criterion.workspace = true
 hex-literal.workspace = true
+serial_test.workspace = true
 tokio = { workspace = true, features = ["process", "sync", "fs", "rt", "io-util", "time", "test-util"] }
 indoc.workspace = true
 

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/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/routes.rs

@@ -97,8 +97,8 @@ use crate::tenant::{LogicalSizeCalculationCause, PageReconstructError};
 use crate::DEFAULT_PG_VERSION;
 use crate::{disk_usage_eviction_task, tenant};
 use pageserver_api::models::{
-    StatusResponse, TenantConfigRequest, TenantInfo, TimelineCreateRequest, TimelineGcRequest,
-    TimelineInfo,
+    CompactInfoResponse, StatusResponse, TenantConfigRequest, TenantInfo, TimelineCreateRequest,
+    TimelineGcRequest, TimelineInfo,
 };
 use utils::{
     auth::SwappableJwtAuth,
@@ -2039,6 +2039,34 @@ async fn timeline_cancel_compact_handler(
     .await
 }
 
+// Get compact info of a timeline
+async fn timeline_compact_info_handler(
+    request: Request<Body>,
+    _cancel: CancellationToken,
+) -> Result<Response<Body>, ApiError> {
+    let tenant_shard_id: TenantShardId = parse_request_param(&request, "tenant_shard_id")?;
+    let timeline_id: TimelineId = parse_request_param(&request, "timeline_id")?;
+    check_permission(&request, Some(tenant_shard_id.tenant_id))?;
+    let state = get_state(&request);
+    async {
+        let tenant = state
+            .tenant_manager
+            .get_attached_tenant_shard(tenant_shard_id)?;
+        let res = tenant.get_scheduled_compaction_tasks(timeline_id);
+        let mut resp = Vec::new();
+        for item in res {
+            resp.push(CompactInfoResponse {
+                compact_key_range: item.compact_key_range,
+                compact_lsn_range: item.compact_lsn_range,
+                sub_compaction: item.sub_compaction,
+            });
+        }
+        json_response(StatusCode::OK, resp)
+    }
+    .instrument(info_span!("timeline_compact_info", tenant_id = %tenant_shard_id.tenant_id, shard_id = %tenant_shard_id.shard_slug(), %timeline_id))
+    .await
+}
+
 // Run compaction immediately on given timeline.
 async fn timeline_compact_handler(
     mut request: Request<Body>,
@@ -3400,6 +3428,10 @@ pub fn make_router(
             "/v1/tenant/:tenant_shard_id/timeline/:timeline_id/do_gc",
             |r| api_handler(r, timeline_gc_handler),
         )
+        .get(
+            "/v1/tenant/:tenant_shard_id/timeline/:timeline_id/compact",
+            |r| api_handler(r, timeline_compact_info_handler),
+        )
         .put(
             "/v1/tenant/:tenant_shard_id/timeline/:timeline_id/compact",
             |r| api_handler(r, timeline_compact_handler),

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;
@@ -445,15 +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",
@@ -2586,7 +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,
@@ -2632,9 +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,
@@ -2780,7 +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,
@@ -2830,14 +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
@@ -2855,7 +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());

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

@@ -3122,6 +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,
@@ -5759,13 +5776,13 @@ mod tests {
     use timeline::{CompactOptions, DeltaLayerTestDesc};
     use utils::id::TenantId;
 
+    #[cfg(feature = "testing")]
+    use models::CompactLsnRange;
     #[cfg(feature = "testing")]
     use pageserver_api::record::NeonWalRecord;
     #[cfg(feature = "testing")]
     use timeline::compaction::{KeyHistoryRetention, KeyLogAtLsn};
     #[cfg(feature = "testing")]
-    use timeline::CompactLsnRange;
-    #[cfg(feature = "testing")]
     use timeline::GcInfo;
 
     static TEST_KEY: Lazy<Key> =
@@ -9634,7 +9651,7 @@ mod tests {
     #[cfg(feature = "testing")]
     #[tokio::test]
     async fn test_simple_bottom_most_compaction_on_branch() -> anyhow::Result<()> {
-        use timeline::CompactLsnRange;
+        use models::CompactLsnRange;
 
         let harness = TenantHarness::create("test_simple_bottom_most_compaction_on_branch").await?;
         let (tenant, ctx) = harness.load().await;

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/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
     }

pageserver/src/tenant/ephemeral_file.rs

@@ -174,11 +174,11 @@ impl EphemeralFile {
 }
 
 impl super::storage_layer::inmemory_layer::vectored_dio_read::File for EphemeralFile {
-    async fn read_exact_at_eof_ok<'a, 'b, B: IoBufAlignedMut + Send>(
-        &'b self,
+    async fn read_exact_at_eof_ok<B: IoBufAlignedMut + Send>(
+        &self,
         start: u64,
         dst: tokio_epoll_uring::Slice<B>,
-        ctx: &'a RequestContext,
+        ctx: &RequestContext,
     ) -> std::io::Result<(tokio_epoll_uring::Slice<B>, usize)> {
         let submitted_offset = self.buffered_writer.bytes_submitted();
 

pageserver/src/tenant/layer_map.rs

@@ -392,8 +392,8 @@ impl LayerMap {
         image_layer: Option<Arc<PersistentLayerDesc>>,
         end_lsn: Lsn,
     ) -> Option<SearchResult> {
-        assert!(delta_layer.as_ref().map_or(true, |l| l.is_delta()));
-        assert!(image_layer.as_ref().map_or(true, |l| !l.is_delta()));
+        assert!(delta_layer.as_ref().is_none_or(|l| l.is_delta()));
+        assert!(image_layer.as_ref().is_none_or(|l| !l.is_delta()));
 
         match (delta_layer, image_layer) {
             (None, None) => None,

pageserver/src/tenant/remote_timeline_client.rs

@@ -749,7 +749,7 @@ impl RemoteTimelineClient {
         // ahead of what's _actually_ on the remote during index upload.
         upload_queue.dirty.metadata = metadata.clone();
 
-        self.schedule_index_upload(upload_queue)?;
+        self.schedule_index_upload(upload_queue);
 
         Ok(())
     }
@@ -770,7 +770,7 @@ impl RemoteTimelineClient {
 
         upload_queue.dirty.metadata.apply(update);
 
-        self.schedule_index_upload(upload_queue)?;
+        self.schedule_index_upload(upload_queue);
 
         Ok(())
     }
@@ -809,7 +809,7 @@ impl RemoteTimelineClient {
         if let Some(archived_at_set) = need_upload_scheduled {
             let intended_archived_at = archived_at_set.then(|| Utc::now().naive_utc());
             upload_queue.dirty.archived_at = intended_archived_at;
-            self.schedule_index_upload(upload_queue)?;
+            self.schedule_index_upload(upload_queue);
         }
 
         let need_wait = need_change(&upload_queue.clean.0.archived_at, state).is_some();
@@ -824,7 +824,7 @@ impl RemoteTimelineClient {
         let mut guard = self.upload_queue.lock().unwrap();
         let upload_queue = guard.initialized_mut()?;
         upload_queue.dirty.import_pgdata = state;
-        self.schedule_index_upload(upload_queue)?;
+        self.schedule_index_upload(upload_queue);
         Ok(())
     }
 
@@ -843,17 +843,14 @@ impl RemoteTimelineClient {
         let upload_queue = guard.initialized_mut()?;
 
         if upload_queue.latest_files_changes_since_metadata_upload_scheduled > 0 {
-            self.schedule_index_upload(upload_queue)?;
+            self.schedule_index_upload(upload_queue);
         }
 
         Ok(())
     }
 
     /// Launch an index-file upload operation in the background (internal function)
-    fn schedule_index_upload(
-        self: &Arc<Self>,
-        upload_queue: &mut UploadQueueInitialized,
-    ) -> Result<(), NotInitialized> {
+    fn schedule_index_upload(self: &Arc<Self>, upload_queue: &mut UploadQueueInitialized) {
         let disk_consistent_lsn = upload_queue.dirty.metadata.disk_consistent_lsn();
         // fix up the duplicated field
         upload_queue.dirty.disk_consistent_lsn = disk_consistent_lsn;
@@ -880,7 +877,6 @@ impl RemoteTimelineClient {
 
         // Launch the task immediately, if possible
         self.launch_queued_tasks(upload_queue);
-        Ok(())
     }
 
     /// Reparent this timeline to a new parent.
@@ -909,7 +905,7 @@ impl RemoteTimelineClient {
                 upload_queue.dirty.metadata.reparent(new_parent);
                 upload_queue.dirty.lineage.record_previous_ancestor(&prev);
 
-                self.schedule_index_upload(upload_queue)?;
+                self.schedule_index_upload(upload_queue);
 
                 Some(self.schedule_barrier0(upload_queue))
             }
@@ -948,7 +944,7 @@ impl RemoteTimelineClient {
                     assert!(prev.is_none(), "copied layer existed already {layer}");
                 }
 
-                self.schedule_index_upload(upload_queue)?;
+                self.schedule_index_upload(upload_queue);
 
                 Some(self.schedule_barrier0(upload_queue))
             }
@@ -1004,7 +1000,7 @@ impl RemoteTimelineClient {
                     upload_queue.dirty.gc_blocking = current
                         .map(|x| x.with_reason(reason))
                         .or_else(|| Some(index::GcBlocking::started_now_for(reason)));
-                    self.schedule_index_upload(upload_queue)?;
+                    self.schedule_index_upload(upload_queue);
                     Some(self.schedule_barrier0(upload_queue))
                 }
             }
@@ -1057,8 +1053,7 @@ impl RemoteTimelineClient {
                     upload_queue.dirty.gc_blocking =
                         current.as_ref().and_then(|x| x.without_reason(reason));
                     assert!(wanted(upload_queue.dirty.gc_blocking.as_ref()));
-                    // FIXME: bogus ?
-                    self.schedule_index_upload(upload_queue)?;
+                    self.schedule_index_upload(upload_queue);
                     Some(self.schedule_barrier0(upload_queue))
                 }
             }
@@ -1125,8 +1120,8 @@ impl RemoteTimelineClient {
         let mut guard = self.upload_queue.lock().unwrap();
         let upload_queue = guard.initialized_mut()?;
 
-        let with_metadata = self
-            .schedule_unlinking_of_layers_from_index_part0(upload_queue, names.iter().cloned())?;
+        let with_metadata =
+            self.schedule_unlinking_of_layers_from_index_part0(upload_queue, names.iter().cloned());
 
         self.schedule_deletion_of_unlinked0(upload_queue, with_metadata);
 
@@ -1153,7 +1148,7 @@ impl RemoteTimelineClient {
 
         let names = gc_layers.iter().map(|x| x.layer_desc().layer_name());
 
-        self.schedule_unlinking_of_layers_from_index_part0(upload_queue, names)?;
+        self.schedule_unlinking_of_layers_from_index_part0(upload_queue, names);
 
         self.launch_queued_tasks(upload_queue);
 
@@ -1166,7 +1161,7 @@ impl RemoteTimelineClient {
         self: &Arc<Self>,
         upload_queue: &mut UploadQueueInitialized,
         names: I,
-    ) -> Result<Vec<(LayerName, LayerFileMetadata)>, NotInitialized>
+    ) -> Vec<(LayerName, LayerFileMetadata)>
     where
         I: IntoIterator<Item = LayerName>,
     {
@@ -1208,10 +1203,10 @@ impl RemoteTimelineClient {
         // index_part update, because that needs to be uploaded before we can actually delete the
         // files.
         if upload_queue.latest_files_changes_since_metadata_upload_scheduled > 0 {
-            self.schedule_index_upload(upload_queue)?;
+            self.schedule_index_upload(upload_queue);
         }
 
-        Ok(with_metadata)
+        with_metadata
     }
 
     /// Schedules deletion for layer files which have previously been unlinked from the
@@ -1302,7 +1297,7 @@ impl RemoteTimelineClient {
 
         let names = compacted_from.iter().map(|x| x.layer_desc().layer_name());
 
-        self.schedule_unlinking_of_layers_from_index_part0(upload_queue, names)?;
+        self.schedule_unlinking_of_layers_from_index_part0(upload_queue, names);
         self.launch_queued_tasks(upload_queue);
 
         Ok(())

pageserver/src/tenant/remote_timeline_client/download.rs

@@ -145,8 +145,8 @@ pub async fn download_layer_file<'a>(
 ///
 /// If Err() is returned, there was some error. The file at `dst_path` has been unlinked.
 /// The unlinking has _not_ been made durable.
-async fn download_object<'a>(
-    storage: &'a GenericRemoteStorage,
+async fn download_object(
+    storage: &GenericRemoteStorage,
     src_path: &RemotePath,
     dst_path: &Utf8PathBuf,
     #[cfg_attr(target_os = "macos", allow(unused_variables))] gate: &utils::sync::gate::Gate,

pageserver/src/tenant/remote_timeline_client/upload.rs

@@ -25,8 +25,8 @@ use utils::id::{TenantId, TimelineId};
 use tracing::info;
 
 /// Serializes and uploads the given index part data to the remote storage.
-pub(crate) async fn upload_index_part<'a>(
-    storage: &'a GenericRemoteStorage,
+pub(crate) async fn upload_index_part(
+    storage: &GenericRemoteStorage,
     tenant_shard_id: &TenantShardId,
     timeline_id: &TimelineId,
     generation: Generation,

pageserver/src/tenant/storage_layer.rs

@@ -345,10 +345,7 @@ impl LayerFringe {
     }
 
     pub(crate) fn next_layer(&mut self) -> Option<(ReadableLayer, KeySpace, Range<Lsn>)> {
-        let read_desc = match self.planned_visits_by_lsn.pop() {
-            Some(desc) => desc,
-            None => return None,
-        };
+        let read_desc = self.planned_visits_by_lsn.pop()?;
 
         let removed = self.visit_reads.remove_entry(&read_desc.layer_to_visit_id);
 

pageserver/src/tenant/storage_layer/delta_layer.rs

@@ -1486,7 +1486,7 @@ pub struct ValueRef<'a> {
     layer: &'a DeltaLayerInner,
 }
 
-impl<'a> ValueRef<'a> {
+impl ValueRef<'_> {
     /// Loads the value from disk
     pub async fn load(&self, ctx: &RequestContext) -> Result<Value> {
         let buf = self.load_raw(ctx).await?;
@@ -1543,7 +1543,7 @@ pub struct DeltaLayerIterator<'a> {
     is_end: bool,
 }
 
-impl<'a> DeltaLayerIterator<'a> {
+impl DeltaLayerIterator<'_> {
     pub(crate) fn layer_dbg_info(&self) -> String {
         self.delta_layer.layer_dbg_info()
     }

pageserver/src/tenant/storage_layer/image_layer.rs

@@ -1052,7 +1052,7 @@ pub struct ImageLayerIterator<'a> {
     is_end: bool,
 }
 
-impl<'a> ImageLayerIterator<'a> {
+impl ImageLayerIterator<'_> {
     pub(crate) fn layer_dbg_info(&self) -> String {
         self.image_layer.layer_dbg_info()
     }

pageserver/src/tenant/storage_layer/inmemory_layer/vectored_dio_read.rs

@@ -25,11 +25,11 @@ pub trait File: Send {
     /// [`std::io::ErrorKind::UnexpectedEof`] error if the file is shorter than `start+dst.len()`.
     ///
     /// No guarantees are made about the remaining bytes in `dst` in case of a short read.
-    async fn read_exact_at_eof_ok<'a, 'b, B: IoBufAlignedMut + Send>(
-        &'b self,
+    async fn read_exact_at_eof_ok<B: IoBufAlignedMut + Send>(
+        &self,
         start: u64,
         dst: Slice<B>,
-        ctx: &'a RequestContext,
+        ctx: &RequestContext,
     ) -> std::io::Result<(Slice<B>, usize)>;
 }
 
@@ -479,11 +479,11 @@ mod tests {
     }
 
     impl File for InMemoryFile {
-        async fn read_exact_at_eof_ok<'a, 'b, B: IoBufMut + Send>(
-            &'b self,
+        async fn read_exact_at_eof_ok<B: IoBufMut + Send>(
+            &self,
             start: u64,
             mut dst: Slice<B>,
-            _ctx: &'a RequestContext,
+            _ctx: &RequestContext,
         ) -> std::io::Result<(Slice<B>, usize)> {
             let dst_slice: &mut [u8] = dst.as_mut_rust_slice_full_zeroed();
             let nread = {
@@ -609,12 +609,12 @@ mod tests {
         }
     }
 
-    impl<'x> File for RecorderFile<'x> {
-        async fn read_exact_at_eof_ok<'a, 'b, B: IoBufAlignedMut + Send>(
-            &'b self,
+    impl File for RecorderFile<'_> {
+        async fn read_exact_at_eof_ok<B: IoBufAlignedMut + Send>(
+            &self,
             start: u64,
             dst: Slice<B>,
-            ctx: &'a RequestContext,
+            ctx: &RequestContext,
         ) -> std::io::Result<(Slice<B>, usize)> {
             let (dst, nread) = self.file.read_exact_at_eof_ok(start, dst, ctx).await?;
             self.recorded.borrow_mut().push(RecordedRead {
@@ -740,11 +740,11 @@ mod tests {
     }
 
     impl File for MockFile {
-        async fn read_exact_at_eof_ok<'a, 'b, B: IoBufMut + Send>(
-            &'b self,
+        async fn read_exact_at_eof_ok<B: IoBufMut + Send>(
+            &self,
             start: u64,
             mut dst: Slice<B>,
-            _ctx: &'a RequestContext,
+            _ctx: &RequestContext,
         ) -> std::io::Result<(Slice<B>, usize)> {
             let ExpectedRead {
                 expect_pos,

pageserver/src/tenant/storage_layer/layer.rs

@@ -1,5 +1,6 @@
 use anyhow::Context;
 use camino::{Utf8Path, Utf8PathBuf};
+use once_cell::sync::Lazy;
 use pageserver_api::keyspace::KeySpace;
 use pageserver_api::models::HistoricLayerInfo;
 use pageserver_api::shard::{ShardIdentity, ShardIndex, TenantShardId};
@@ -2096,6 +2097,36 @@ impl Default for LayerImplMetrics {
 }
 
 impl LayerImplMetrics {
+    /// Resets the layer metrics to 0, for use in tests. Since this is a global static, metrics will
+    /// be shared across tests, and must be reset in each test case.
+    #[cfg(test)]
+    fn reset(&self) {
+        // Destructure to error on new fields.
+        let LayerImplMetrics {
+            started_evictions,
+            completed_evictions,
+            cancelled_evictions,
+            started_deletes,
+            completed_deletes,
+            failed_deletes,
+            rare_counters,
+            inits_cancelled,
+            redownload_after,
+            time_to_evict,
+        } = self;
+
+        started_evictions.reset();
+        completed_evictions.reset();
+        cancelled_evictions.values().for_each(|c| c.reset());
+        started_deletes.reset();
+        completed_deletes.reset();
+        failed_deletes.values().for_each(|c| c.reset());
+        rare_counters.values().for_each(|c| c.reset());
+        inits_cancelled.reset();
+        redownload_after.local().clear();
+        time_to_evict.local().clear();
+    }
+
     fn inc_started_evictions(&self) {
         self.started_evictions.inc();
     }
@@ -2247,5 +2278,4 @@ impl RareEvent {
     }
 }
 
-pub(crate) static LAYER_IMPL_METRICS: once_cell::sync::Lazy<LayerImplMetrics> =
-    once_cell::sync::Lazy::new(LayerImplMetrics::default);
+pub(crate) static LAYER_IMPL_METRICS: Lazy<LayerImplMetrics> = Lazy::new(LayerImplMetrics::default);

pageserver/src/tenant/storage_layer/layer/tests.rs

@@ -1,6 +1,7 @@
 use std::time::UNIX_EPOCH;
 
 use pageserver_api::key::CONTROLFILE_KEY;
+use serial_test::serial;
 use tokio::task::JoinSet;
 use utils::{
     completion::{self, Completion},
@@ -21,7 +22,10 @@ const FOREVER: std::time::Duration = std::time::Duration::from_secs(ADVANCE.as_s
 
 /// Demonstrate the API and resident -> evicted -> resident -> deleted transitions.
 #[tokio::test]
+#[serial]
 async fn smoke_test() {
+    LAYER_IMPL_METRICS.reset();
+
     let handle = tokio::runtime::Handle::current();
 
     let h = TenantHarness::create("smoke_test").await.unwrap();
@@ -198,7 +202,10 @@ async fn smoke_test() {
 /// This test demonstrates a previous hang when a eviction and deletion were requested at the same
 /// time. Now both of them complete per Arc drop semantics.
 #[tokio::test(start_paused = true)]
+#[serial]
 async fn evict_and_wait_on_wanted_deleted() {
+    LAYER_IMPL_METRICS.reset();
+
     // this is the runtime on which Layer spawns the blocking tasks on
     let handle = tokio::runtime::Handle::current();
 
@@ -275,7 +282,10 @@ async fn evict_and_wait_on_wanted_deleted() {
 /// This test ensures we are able to read the layer while the layer eviction has been
 /// started but not completed.
 #[test]
+#[serial]
 fn read_wins_pending_eviction() {
+    LAYER_IMPL_METRICS.reset();
+
     let rt = tokio::runtime::Builder::new_current_thread()
         .max_blocking_threads(1)
         .enable_all()
@@ -395,6 +405,7 @@ fn read_wins_pending_eviction() {
 
 /// Use failpoint to delay an eviction starting to get a VersionCheckFailed.
 #[test]
+#[serial]
 fn multiple_pending_evictions_in_order() {
     let name = "multiple_pending_evictions_in_order";
     let in_order = true;
@@ -403,6 +414,7 @@ fn multiple_pending_evictions_in_order() {
 
 /// Use failpoint to reorder later eviction before first to get a UnexpectedEvictedState.
 #[test]
+#[serial]
 fn multiple_pending_evictions_out_of_order() {
     let name = "multiple_pending_evictions_out_of_order";
     let in_order = false;
@@ -410,6 +422,8 @@ fn multiple_pending_evictions_out_of_order() {
 }
 
 fn multiple_pending_evictions_scenario(name: &'static str, in_order: bool) {
+    LAYER_IMPL_METRICS.reset();
+
     let rt = tokio::runtime::Builder::new_current_thread()
         .max_blocking_threads(1)
         .enable_all()
@@ -587,7 +601,10 @@ fn multiple_pending_evictions_scenario(name: &'static str, in_order: bool) {
 /// disk but the layer internal state says it has not been initialized. Futhermore, it allows us to
 /// have non-repairing `Layer::is_likely_resident`.
 #[tokio::test(start_paused = true)]
+#[serial]
 async fn cancelled_get_or_maybe_download_does_not_cancel_eviction() {
+    LAYER_IMPL_METRICS.reset();
+
     let handle = tokio::runtime::Handle::current();
     let h = TenantHarness::create("cancelled_get_or_maybe_download_does_not_cancel_eviction")
         .await
@@ -665,8 +682,8 @@ async fn cancelled_get_or_maybe_download_does_not_cancel_eviction() {
 }
 
 #[tokio::test(start_paused = true)]
+#[serial]
 async fn evict_and_wait_does_not_wait_for_download() {
-    // let handle = tokio::runtime::Handle::current();
     let h = TenantHarness::create("evict_and_wait_does_not_wait_for_download")
         .await
         .unwrap();
@@ -759,10 +776,13 @@ async fn evict_and_wait_does_not_wait_for_download() {
 ///
 /// Also checks that the same does not happen on a non-evicted layer (regression test).
 #[tokio::test(start_paused = true)]
+#[serial]
 async fn eviction_cancellation_on_drop() {
     use bytes::Bytes;
     use pageserver_api::value::Value;
 
+    LAYER_IMPL_METRICS.reset();
+
     // this is the runtime on which Layer spawns the blocking tasks on
     let handle = tokio::runtime::Handle::current();
 

pageserver/src/tenant/timeline.rs

@@ -31,9 +31,9 @@ use pageserver_api::{
     },
     keyspace::{KeySpaceAccum, KeySpaceRandomAccum, SparseKeyPartitioning},
     models::{
-        CompactionAlgorithm, CompactionAlgorithmSettings, DownloadRemoteLayersTaskInfo,
-        DownloadRemoteLayersTaskSpawnRequest, EvictionPolicy, InMemoryLayerInfo, LayerMapInfo,
-        LsnLease, TimelineState,
+        CompactKeyRange, CompactLsnRange, CompactionAlgorithm, CompactionAlgorithmSettings,
+        DownloadRemoteLayersTaskInfo, DownloadRemoteLayersTaskSpawnRequest, EvictionPolicy,
+        InMemoryLayerInfo, LayerMapInfo, LsnLease, TimelineState,
     },
     reltag::BlockNumber,
     shard::{ShardIdentity, ShardNumber, TenantShardId},
@@ -144,19 +144,15 @@ use self::layer_manager::LayerManager;
 use self::logical_size::LogicalSize;
 use self::walreceiver::{WalReceiver, WalReceiverConf};
 
+use super::config::TenantConf;
+use super::remote_timeline_client::index::IndexPart;
+use super::remote_timeline_client::RemoteTimelineClient;
+use super::secondary::heatmap::{HeatMapLayer, HeatMapTimeline};
+use super::storage_layer::{LayerFringe, LayerVisibilityHint, ReadableLayer};
+use super::upload_queue::NotInitialized;
+use super::GcError;
 use super::{
-    config::TenantConf, storage_layer::LayerVisibilityHint, upload_queue::NotInitialized,
-    MaybeOffloaded,
-};
-use super::{debug_assert_current_span_has_tenant_and_timeline_id, AttachedTenantConf};
-use super::{remote_timeline_client::index::IndexPart, storage_layer::LayerFringe};
-use super::{
-    remote_timeline_client::RemoteTimelineClient, remote_timeline_client::WaitCompletionError,
-    storage_layer::ReadableLayer,
-};
-use super::{
-    secondary::heatmap::{HeatMapLayer, HeatMapTimeline},
-    GcError,
+    debug_assert_current_span_has_tenant_and_timeline_id, AttachedTenantConf, MaybeOffloaded,
 };
 
 #[cfg(test)]
@@ -792,63 +788,6 @@ pub(crate) struct CompactRequest {
     pub sub_compaction_max_job_size_mb: Option<u64>,
 }
 
-#[serde_with::serde_as]
-#[derive(Debug, Clone, serde::Deserialize)]
-pub(crate) struct CompactLsnRange {
-    pub start: Lsn,
-    pub end: Lsn,
-}
-
-#[serde_with::serde_as]
-#[derive(Debug, Clone, serde::Deserialize)]
-pub(crate) 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 {
-    #[cfg(test)]
-    #[cfg(feature = "testing")]
-    pub fn above(lsn: Lsn) -> Self {
-        Self {
-            start: lsn,
-            end: Lsn::MAX,
-        }
-    }
-}
-
 #[derive(Debug, Clone, Default)]
 pub(crate) struct CompactOptions {
     pub flags: EnumSet<CompactFlags>,
@@ -3897,24 +3836,6 @@ impl Timeline {
             // release lock on 'layers'
         };
 
-        // Backpressure mechanism: wait with continuation of the flush loop until we have uploaded all layer files.
-        // This makes us refuse ingest until the new layers have been persisted to the remote
-        let start = Instant::now();
-        self.remote_client
-            .wait_completion()
-            .await
-            .map_err(|e| match e {
-                WaitCompletionError::UploadQueueShutDownOrStopped
-                | WaitCompletionError::NotInitialized(
-                    NotInitialized::ShuttingDown | NotInitialized::Stopped,
-                ) => FlushLayerError::Cancelled,
-                WaitCompletionError::NotInitialized(NotInitialized::Uninitialized) => {
-                    FlushLayerError::Other(anyhow!(e).into())
-                }
-            })?;
-        let duration = start.elapsed().as_secs_f64();
-        self.metrics.flush_wait_upload_time_gauge_add(duration);
-
         // FIXME: between create_delta_layer and the scheduling of the upload in `update_metadata_file`,
         // a compaction can delete the file and then it won't be available for uploads any more.
         // We still schedule the upload, resulting in an error, but ideally we'd somehow avoid this
@@ -4064,8 +3985,11 @@ impl Timeline {
             // NB: there are two callers, one is the compaction task, of which there is only one per struct Tenant and hence Timeline.
             // The other is the initdb optimization in flush_frozen_layer, used by `boostrap_timeline`, which runs before `.activate()`
             // and hence before the compaction task starts.
+            // Note that there are a third "caller" that will take the `partitioning` lock. It is `gc_compaction_split_jobs` for
+            // gc-compaction where it uses the repartition data to determine the split jobs. In the future, it might use its own
+            // heuristics, but for now, we should allow concurrent access to it and let the caller retry compaction.
             return Err(CompactionError::Other(anyhow!(
-                "repartition() called concurrently, this should not happen"
+                "repartition() called concurrently, this is rare and a retry should be fine"
             )));
         };
         let ((dense_partition, sparse_partition), partition_lsn) = &*partitioning_guard;
@@ -5861,7 +5785,7 @@ enum OpenLayerAction {
     None,
 }
 
-impl<'a> TimelineWriter<'a> {
+impl TimelineWriter<'_> {
     async fn handle_open_layer_action(
         &mut self,
         at: Lsn,

pageserver/src/tenant/timeline/compaction.rs

@@ -29,6 +29,7 @@ use utils::id::TimelineId;
 use crate::context::{AccessStatsBehavior, RequestContext, RequestContextBuilder};
 use crate::page_cache;
 use crate::statvfs::Statvfs;
+use crate::tenant::checks::check_valid_layermap;
 use crate::tenant::remote_timeline_client::WaitCompletionError;
 use crate::tenant::storage_layer::batch_split_writer::{
     BatchWriterResult, SplitDeltaLayerWriter, SplitImageLayerWriter,
@@ -1110,7 +1111,7 @@ impl Timeline {
                 return Err(CompactionError::ShuttingDown);
             }
 
-            let same_key = prev_key.map_or(false, |prev_key| prev_key == key);
+            let same_key = prev_key == Some(key);
             // We need to check key boundaries once we reach next key or end of layer with the same key
             if !same_key || lsn == dup_end_lsn {
                 let mut next_key_size = 0u64;
@@ -1821,10 +1822,12 @@ impl Timeline {
         let mut compact_jobs = Vec::new();
         // For now, we simply use the key partitioning information; we should do a more fine-grained partitioning
         // by estimating the amount of files read for a compaction job. We should also partition on LSN.
-        let Ok(partition) = self.partitioning.try_lock() else {
-            bail!("failed to acquire partition lock");
+        let ((dense_ks, sparse_ks), _) = {
+            let Ok(partition) = self.partitioning.try_lock() else {
+                bail!("failed to acquire partition lock during gc-compaction");
+            };
+            partition.clone()
         };
-        let ((dense_ks, sparse_ks), _) = &*partition;
         // Truncate the key range to be within user specified compaction range.
         fn truncate_to(
             source_start: &Key,
@@ -2154,15 +2157,14 @@ impl Timeline {
 
         // Step 1: construct a k-merge iterator over all layers.
         // Also, verify if the layer map can be split by drawing a horizontal line at every LSN start/end split point.
-        // disable the check for now because we need to adjust the check for partial compactions, will enable later.
-        // let layer_names = job_desc
-        //     .selected_layers
-        //     .iter()
-        //     .map(|layer| layer.layer_desc().layer_name())
-        //     .collect_vec();
-        // if let Some(err) = check_valid_layermap(&layer_names) {
-        //     warn!("gc-compaction layer map check failed because {}, this is normal if partial compaction is not finished yet", err);
-        // }
+        let layer_names = job_desc
+            .selected_layers
+            .iter()
+            .map(|layer| layer.layer_desc().layer_name())
+            .collect_vec();
+        if let Some(err) = check_valid_layermap(&layer_names) {
+            bail!("gc-compaction layer map check failed because {}, cannot proceed with compaction due to potential data loss", err);
+        }
         // The maximum LSN we are processing in this compaction loop
         let end_lsn = job_desc
             .selected_layers
@@ -2544,13 +2546,48 @@ impl Timeline {
         );
 
         // Step 3: Place back to the layer map.
+
+        // First, do a sanity check to ensure the newly-created layer map does not contain overlaps.
+        let all_layers = {
+            let guard = self.layers.read().await;
+            let layer_map = guard.layer_map()?;
+            layer_map.iter_historic_layers().collect_vec()
+        };
+
+        let mut final_layers = all_layers
+            .iter()
+            .map(|layer| layer.layer_name())
+            .collect::<HashSet<_>>();
+        for layer in &layer_selection {
+            final_layers.remove(&layer.layer_desc().layer_name());
+        }
+        for layer in &compact_to {
+            final_layers.insert(layer.layer_desc().layer_name());
+        }
+        let final_layers = final_layers.into_iter().collect_vec();
+
+        // TODO: move this check before we call `finish` on image layer writers. However, this will require us to get the layer name before we finish
+        // the writer, so potentially, we will need a function like `ImageLayerBatchWriter::get_all_pending_layer_keys` to get all the keys that are
+        // in the writer before finalizing the persistent layers. Now we would leave some dangling layers on the disk if the check fails.
+        if let Some(err) = check_valid_layermap(&final_layers) {
+            bail!("gc-compaction layer map check failed after compaction because {}, compaction result not applied to the layer map due to potential data loss", err);
+        }
+
+        // Between the sanity check and this compaction update, there could be new layers being flushed, but it should be fine because we only
+        // operate on L1 layers.
         {
-            // TODO: sanity check if the layer map is valid (i.e., should not have overlaps)
             let mut guard = self.layers.write().await;
             guard
                 .open_mut()?
                 .finish_gc_compaction(&layer_selection, &compact_to, &self.metrics)
         };
+
+        // Schedule an index-only upload to update the `latest_gc_cutoff` in the index_part.json.
+        // Otherwise, after restart, the index_part only contains the old `latest_gc_cutoff` and
+        // find_gc_cutoffs will try accessing things below the cutoff. TODO: ideally, this should
+        // be batched into `schedule_compaction_update`.
+        let disk_consistent_lsn = self.disk_consistent_lsn.load();
+        self.schedule_uploads(disk_consistent_lsn, None)?;
         self.remote_client
             .schedule_compaction_update(&layer_selection, &compact_to)?;
 
@@ -2902,7 +2939,7 @@ impl CompactionLayer<Key> for ResidentDeltaLayer {
 impl CompactionDeltaLayer<TimelineAdaptor> for ResidentDeltaLayer {
     type DeltaEntry<'a> = DeltaEntry<'a>;
 
-    async fn load_keys<'a>(&self, ctx: &RequestContext) -> anyhow::Result<Vec<DeltaEntry<'_>>> {
+    async fn load_keys(&self, ctx: &RequestContext) -> anyhow::Result<Vec<DeltaEntry<'_>>> {
         self.0.get_as_delta(ctx).await?.index_entries(ctx).await
     }
 }

pgxn/neon/control_plane_connector.c

@@ -428,6 +428,8 @@ MergeTable()
 		hash_seq_init(&status, old_table->role_table);
 		while ((entry = hash_seq_search(&status)) != NULL)
 		{
+			RoleEntry * old;
+			bool found_old = false;
 			RoleEntry  *to_write = hash_search(
 											   CurrentDdlTable->role_table,
 											   entry->name,
@@ -435,30 +437,23 @@ MergeTable()
 											   NULL);
 
 			to_write->type = entry->type;
-			if (entry->password)
-				to_write->password = entry->password;
+			to_write->password = entry->password;
 			strlcpy(to_write->old_name, entry->old_name, NAMEDATALEN);
-			if (entry->old_name[0] != '\0')
-			{
-				bool		found_old = false;
-				RoleEntry  *old = hash_search(
-											  CurrentDdlTable->role_table,
-											  entry->old_name,
-											  HASH_FIND,
-											  &found_old);
+			if (entry->old_name[0] == '\0')
+				continue;
 
-				if (found_old)
-				{
-					if (old->old_name[0] != '\0')
-						strlcpy(to_write->old_name, old->old_name, NAMEDATALEN);
-					else
-						strlcpy(to_write->old_name, entry->old_name, NAMEDATALEN);
-					hash_search(CurrentDdlTable->role_table,
-								entry->old_name,
-								HASH_REMOVE,
-								NULL);
-				}
-			}
+			old = hash_search(
+							  CurrentDdlTable->role_table,
+							  entry->old_name,
+							  HASH_FIND,
+							  &found_old);
+			if (!found_old)
+				continue;
+			strlcpy(to_write->old_name, old->old_name, NAMEDATALEN);
+			hash_search(CurrentDdlTable->role_table,
+						entry->old_name,
+						HASH_REMOVE,
+						NULL);
 		}
 		hash_destroy(old_table->role_table);
 	}

pgxn/neon/file_cache.c

@@ -365,6 +365,10 @@ lfc_change_limit_hook(int newval, void *extra)
 			neon_log(LOG, "Failed to punch hole in file: %m");
 #endif
 		/* We remove the old entry, and re-enter a hole to the hash table */
+		for (int i = 0; i < BLOCKS_PER_CHUNK; i++)
+		{
+			lfc_ctl->used_pages -= (victim->bitmap[i >> 5] >> (i & 31)) & 1;
+		}
 		hash_search_with_hash_value(lfc_hash, &victim->key, victim->hash, HASH_REMOVE, NULL);
 
 		memset(&holetag, 0, sizeof(holetag));

pgxn/neon/libpagestore.c

@@ -827,7 +827,6 @@ pageserver_send(shardno_t shard_no, NeonRequest *request)
 	{
 		while (!pageserver_connect(shard_no, shard->n_reconnect_attempts < max_reconnect_attempts ? LOG : ERROR))
 		{
-			HandleMainLoopInterrupts();
 			shard->n_reconnect_attempts += 1;
 		}
 		shard->n_reconnect_attempts = 0;

pgxn/neon/logical_replication_monitor.c

@@ -131,8 +131,8 @@ get_snapshots_cutoff_lsn(void)
 	{
 		cutoff = snapshot_descriptors[logical_replication_max_snap_files - 1].lsn;
 		elog(LOG,
-			"ls_monitor: dropping logical slots with restart_lsn lower %X/%X, found %zu snapshot files, limit is %d",
-			LSN_FORMAT_ARGS(cutoff), snapshot_index, logical_replication_max_snap_files);
+			"ls_monitor: number of snapshot files, %zu, is larger than limit of %d",
+			snapshot_index, logical_replication_max_snap_files);
 	}
 
 	/* Is the size of the logical snapshots directory larger than specified?
@@ -162,8 +162,8 @@ get_snapshots_cutoff_lsn(void)
 		}
 
 		if (cutoff != original)
-			elog(LOG, "ls_monitor: dropping logical slots with restart_lsn lower than %X/%X, " SNAPDIR " is larger than %d KB",
-					LSN_FORMAT_ARGS(cutoff), logical_replication_max_logicalsnapdir_size);
+			elog(LOG, "ls_monitor: " SNAPDIR " is larger than %d KB",
+				 logical_replication_max_logicalsnapdir_size);
 	}
 
 	pfree(snapshot_descriptors);
@@ -214,9 +214,13 @@ InitLogicalReplicationMonitor(void)
 }
 
 /*
- * Unused logical replication slots pins WAL and prevents deletion of snapshots.
+ * Unused logical replication slots pins WAL and prevent deletion of snapshots.
  * WAL bloat is guarded by max_slot_wal_keep_size; this bgw removes slots which
- * need too many .snap files.
+ * need too many .snap files. These files are stored as AUX files, which are a
+ * pageserver mechanism for storing non-relation data. AUX files are shipped in
+ * in the basebackup which is requested by compute_ctl before Postgres starts.
+ * The larger the time to retrieve the basebackup, the more likely it is the
+ * compute will be killed by the control plane due to a timeout.
  */
 void
 LogicalSlotsMonitorMain(Datum main_arg)
@@ -239,10 +243,7 @@ LogicalSlotsMonitorMain(Datum main_arg)
 			ProcessConfigFile(PGC_SIGHUP);
 		}
 
-		/*
-		 * If there are too many .snap files, just drop all logical slots to
-		 * prevent aux files bloat.
-		 */
+		/* Get the cutoff LSN */
 		cutoff_lsn = get_snapshots_cutoff_lsn();
 		if (cutoff_lsn > 0)
 		{
@@ -252,31 +253,37 @@ LogicalSlotsMonitorMain(Datum main_arg)
 				ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i];
 				XLogRecPtr	restart_lsn;
 
-				/* find the name */
 				LWLockAcquire(ReplicationSlotControlLock, LW_SHARED);
-				/* Consider only logical repliction slots */
+
+				/* Consider only active logical repliction slots */
 				if (!s->in_use || !SlotIsLogical(s))
 				{
 					LWLockRelease(ReplicationSlotControlLock);
 					continue;
 				}
 
-				/* do we need to drop it? */
+				/*
+				 * Retrieve the restart LSN to determine if we need to drop the
+				 * slot
+				 */
 				SpinLockAcquire(&s->mutex);
 				restart_lsn = s->data.restart_lsn;
 				SpinLockRelease(&s->mutex);
+
+				strlcpy(slot_name, s->data.name.data, sizeof(slot_name));
+				LWLockRelease(ReplicationSlotControlLock);
+
 				if (restart_lsn >= cutoff_lsn)
 				{
-					LWLockRelease(ReplicationSlotControlLock);
+					elog(LOG, "ls_monitor: not dropping replication slot %s because restart LSN %X/%X is greater than cutoff LSN %X/%X",
+						 slot_name, LSN_FORMAT_ARGS(restart_lsn), LSN_FORMAT_ARGS(cutoff_lsn));
 					continue;
 				}
 
-				strlcpy(slot_name, s->data.name.data, NAMEDATALEN);
-				elog(LOG, "ls_monitor: dropping slot %s with restart_lsn %X/%X below horizon %X/%X",
+				elog(LOG, "ls_monitor: dropping replication slot %s because restart LSN %X/%X lower than cutoff LSN %X/%X",
 					 slot_name, LSN_FORMAT_ARGS(restart_lsn), LSN_FORMAT_ARGS(cutoff_lsn));
-				LWLockRelease(ReplicationSlotControlLock);
 
-				/* now try to drop it, killing owner before if any */
+				/* now try to drop it, killing owner before, if any */
 				for (;;)
 				{
 					pid_t		active_pid;
@@ -288,9 +295,9 @@ LogicalSlotsMonitorMain(Datum main_arg)
 					if (active_pid == 0)
 					{
 						/*
-						 * Slot is releasted, try to drop it. Though of course
+						 * Slot is released, try to drop it. Though of course,
 						 * it could have been reacquired, so drop can ERROR
-						 * out. Similarly it could have been dropped in the
+						 * out. Similarly, it could have been dropped in the
 						 * meanwhile.
 						 *
 						 * In principle we could remove pg_try/pg_catch, that
@@ -300,14 +307,14 @@ LogicalSlotsMonitorMain(Datum main_arg)
 						PG_TRY();
 						{
 							ReplicationSlotDrop(slot_name, true);
-							elog(LOG, "ls_monitor: slot %s dropped", slot_name);
+							elog(LOG, "ls_monitor: replication slot %s dropped", slot_name);
 						}
 						PG_CATCH();
 						{
 							/* log ERROR and reset elog stack */
 							EmitErrorReport();
 							FlushErrorState();
-							elog(LOG, "ls_monitor: failed to drop slot %s", slot_name);
+							elog(LOG, "ls_monitor: failed to drop replication slot %s", slot_name);
 						}
 						PG_END_TRY();
 						break;
@@ -315,7 +322,7 @@ LogicalSlotsMonitorMain(Datum main_arg)
 					else
 					{
 						/* kill the owner and wait for release */
-						elog(LOG, "ls_monitor: killing slot %s owner %d", slot_name, active_pid);
+						elog(LOG, "ls_monitor: killing replication slot %s owner %d", slot_name, active_pid);
 						(void) kill(active_pid, SIGTERM);
 						/* We shouldn't get stuck, but to be safe add timeout. */
 						ConditionVariableTimedSleep(&s->active_cv, 1000, WAIT_EVENT_REPLICATION_SLOT_DROP);

proxy/src/auth/backend/console_redirect.rs

@@ -187,7 +187,6 @@ async fn authenticate(
         NodeInfo {
             config,
             aux: db_info.aux,
-            allow_self_signed_compute: false, // caller may override
         },
         db_info.allowed_ips,
     ))

proxy/src/auth/backend/jwt.rs

@@ -776,6 +776,7 @@ impl From<&jose_jwk::Key> for KeyType {
 }
 
 #[cfg(test)]
+#[expect(clippy::unwrap_used)]
 mod tests {
     use std::future::IntoFuture;
     use std::net::SocketAddr;

proxy/src/auth/backend/local.rs

@@ -37,7 +37,6 @@ impl LocalBackend {
                     branch_id: BranchIdTag::get_interner().get_or_intern("local"),
                     cold_start_info: ColdStartInfo::WarmCached,
                 },
-                allow_self_signed_compute: false,
             },
         }
     }

proxy/src/auth/backend/mod.rs

@@ -463,6 +463,8 @@ impl ComputeConnectBackend for Backend<'_, ComputeCredentials> {
 
 #[cfg(test)]
 mod tests {
+    #![allow(clippy::unimplemented, clippy::unwrap_used)]
+
     use std::net::IpAddr;
     use std::sync::Arc;
     use std::time::Duration;
@@ -676,6 +678,9 @@ mod tests {
         .await
         .unwrap();
 
+        // flush the final server message
+        stream.flush().await.unwrap();
+
         handle.await.unwrap();
     }