Revert "revert the cancellation sensitivity change for the flush task, doesn't work because flush task can't disambiguate orderly shutdown"

This reverts commit 42922cebe0.

.dockerignore

@@ -19,7 +19,7 @@
 !pageserver/
 !pgxn/
 !proxy/
-!endpoint_storage/
+!object_storage/
 !storage_scrubber/
 !safekeeper/
 !storage_broker/

.github/actionlint.yml

@@ -6,7 +6,6 @@ self-hosted-runner:
     - small
     - small-metal
     - small-arm64
-    - unit-perf
     - us-east-2
 config-variables:
   - AWS_ECR_REGION

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

@@ -70,7 +70,6 @@ runs:
 
     - name: Install Allure
       shell: bash -euxo pipefail {0}
-      working-directory: /tmp
       run: |
         if ! which allure; then
           ALLURE_ZIP=allure-${ALLURE_VERSION}.zip

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

@@ -113,6 +113,8 @@ runs:
         TEST_OUTPUT: /tmp/test_output
         BUILD_TYPE: ${{ inputs.build_type }}
         COMPATIBILITY_SNAPSHOT_DIR: /tmp/compatibility_snapshot_pg${{ inputs.pg_version }}
+        ALLOW_BACKWARD_COMPATIBILITY_BREAKAGE: contains(github.event.pull_request.labels.*.name, 'backward compatibility breakage')
+        ALLOW_FORWARD_COMPATIBILITY_BREAKAGE: contains(github.event.pull_request.labels.*.name, 'forward compatibility breakage')
         RERUN_FAILED: ${{ inputs.rerun_failed }}
         PG_VERSION: ${{ inputs.pg_version }}
         SANITIZERS: ${{ inputs.sanitizers }}
@@ -133,7 +135,6 @@ runs:
         fi
 
         PERF_REPORT_DIR="$(realpath test_runner/perf-report-local)"
-        echo "PERF_REPORT_DIR=${PERF_REPORT_DIR}" >> ${GITHUB_ENV}
         rm -rf $PERF_REPORT_DIR
 
         TEST_SELECTION="test_runner/${{ inputs.test_selection }}"
@@ -210,12 +211,11 @@ runs:
           --verbose \
           -rA $TEST_SELECTION $EXTRA_PARAMS
 
-    - name: Upload performance report
-      if: ${{ !cancelled() && inputs.save_perf_report == 'true' }}
-      shell: bash -euxo pipefail {0}
-      run: |
-        export REPORT_FROM="${PERF_REPORT_DIR}"
-        scripts/generate_and_push_perf_report.sh
+        if [[ "${{ inputs.save_perf_report }}" == "true" ]]; then
+          export REPORT_FROM="$PERF_REPORT_DIR"
+          export REPORT_TO="$PLATFORM"
+          scripts/generate_and_push_perf_report.sh
+        fi
 
     - name: Upload compatibility snapshot
       # Note, that we use `github.base_ref` which is a target branch for a PR

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

@@ -272,13 +272,10 @@ jobs:
           # run pageserver tests with different settings
           for get_vectored_concurrent_io in sequential sidecar-task; do
             for io_engine in std-fs tokio-epoll-uring ; do
-                for io_mode in buffered direct direct-rw ; do
-                  NEON_PAGESERVER_UNIT_TEST_GET_VECTORED_CONCURRENT_IO=$get_vectored_concurrent_io \
-                  NEON_PAGESERVER_UNIT_TEST_VIRTUAL_FILE_IOENGINE=$io_engine \
-                  NEON_PAGESERVER_UNIT_TEST_VIRTUAL_FILE_IO_MODE=$io_mode \
-                  ${cov_prefix} \
-                  cargo nextest run $CARGO_FLAGS $CARGO_FEATURES  -E 'package(pageserver)'
-              done
+              NEON_PAGESERVER_UNIT_TEST_GET_VECTORED_CONCURRENT_IO=$get_vectored_concurrent_io \
+                NEON_PAGESERVER_UNIT_TEST_VIRTUAL_FILE_IOENGINE=$io_engine \
+                ${cov_prefix} \
+                cargo nextest run $CARGO_FLAGS $CARGO_FEATURES  -E 'package(pageserver)'
             done
           done
 
@@ -349,7 +346,7 @@ jobs:
       contents: read
       statuses: write
     needs: [ build-neon ]
-    runs-on: ${{ fromJSON(format('["self-hosted", "{0}"]', inputs.arch == 'arm64' && 'large-arm64' || 'large-metal')) }}
+    runs-on: ${{ fromJSON(format('["self-hosted", "{0}"]', inputs.arch == 'arm64' && 'large-arm64' || 'large')) }}
     container:
       image: ${{ inputs.build-tools-image }}
       credentials:
@@ -395,7 +392,6 @@ jobs:
           BUILD_TAG: ${{ inputs.build-tag }}
           PAGESERVER_VIRTUAL_FILE_IO_ENGINE: tokio-epoll-uring
           PAGESERVER_GET_VECTORED_CONCURRENT_IO: sidecar-task
-          PAGESERVER_VIRTUAL_FILE_IO_MODE: direct-rw
           USE_LFC: ${{ matrix.lfc_state == 'with-lfc' && 'true' || 'false' }}
 
       # Temporary disable this step until we figure out why it's so flaky

.github/workflows/_create-release-pr.yml

@@ -53,13 +53,10 @@ jobs:
             || inputs.component-name == 'Compute' && 'release-compute'
           }}
       run: |
-        now_date=$(date -u +'%Y-%m-%d')
-        now_time=$(date -u +'%H-%M-%Z')
-        {
-          echo "title=${COMPONENT_NAME} release ${now_date}"
-          echo "rc-branch=rc/${RELEASE_BRANCH}/${now_date}_${now_time}"
-          echo "release-branch=${RELEASE_BRANCH}"
-        } | tee -a ${GITHUB_OUTPUT}
+        today=$(date +'%Y-%m-%d')
+        echo "title=${COMPONENT_NAME} release ${today}" | tee -a ${GITHUB_OUTPUT}
+        echo "rc-branch=rc/${RELEASE_BRANCH}/${today}"  | tee -a ${GITHUB_OUTPUT}
+        echo "release-branch=${RELEASE_BRANCH}"         | tee -a ${GITHUB_OUTPUT}
 
     - name: Configure git
       run: |

.github/workflows/_meta.yml

@@ -165,5 +165,5 @@ jobs:
           GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           CURRENT_SHA: ${{ github.sha }}
         run: |
-          RELEASE_PR_RUN_ID=$(gh api "/repos/${GITHUB_REPOSITORY}/actions/runs?head_sha=$CURRENT_SHA" | jq '[.workflow_runs[] | select(.name == "Build and Test") | select(.head_branch | test("^rc/release.*$"; "s"))] | first | .id // ("Failed to find Build and Test run from  RC PR!" | halt_error(1))')
+          RELEASE_PR_RUN_ID=$(gh api "/repos/${GITHUB_REPOSITORY}/actions/runs?head_sha=$CURRENT_SHA" | jq '[.workflow_runs[] | select(.name == "Build and Test") | select(.head_branch | test("^rc/release(-(proxy|compute))?/[0-9]{4}-[0-9]{2}-[0-9]{2}$"; "s"))] | first | .id // ("Failed to find Build and Test run from  RC PR!" | halt_error(1))')
           echo "release-pr-run-id=$RELEASE_PR_RUN_ID" | tee -a $GITHUB_OUTPUT

.github/workflows/build-macos.yml

@@ -63,8 +63,13 @@ jobs:
 
       - name: Cache postgres ${{ matrix.postgres-version }} build
         id: cache_pg
-        uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
+        uses: tespkg/actions-cache@b7bf5fcc2f98a52ac6080eb0fd282c2f752074b1  # v1.8.0
         with:
+          endpoint: ${{ vars.HETZNER_CACHE_REGION }}.${{ vars.HETZNER_CACHE_ENDPOINT }}
+          bucket: ${{ vars.HETZNER_CACHE_BUCKET }}
+          accessKey: ${{ secrets.HETZNER_CACHE_ACCESS_KEY }}
+          secretKey: ${{ secrets.HETZNER_CACHE_SECRET_KEY }}
+          use-fallback: false
           path: pg_install/${{ matrix.postgres-version }}
           key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-${{ matrix.postgres-version }}-${{ steps.pg_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
 
@@ -129,15 +134,25 @@ jobs:
 
       - name: Cache postgres v17 build
         id: cache_pg
-        uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
+        uses: tespkg/actions-cache@b7bf5fcc2f98a52ac6080eb0fd282c2f752074b1  # v1.8.0
         with:
+          endpoint: ${{ vars.HETZNER_CACHE_REGION }}.${{ vars.HETZNER_CACHE_ENDPOINT }}
+          bucket: ${{ vars.HETZNER_CACHE_BUCKET }}
+          accessKey: ${{ secrets.HETZNER_CACHE_ACCESS_KEY }}
+          secretKey: ${{ secrets.HETZNER_CACHE_SECRET_KEY }}
+          use-fallback: false
           path: pg_install/v17
           key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-v17-${{ steps.pg_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
 
       - name: Cache walproposer-lib
         id: cache_walproposer_lib
-        uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
+        uses: tespkg/actions-cache@b7bf5fcc2f98a52ac6080eb0fd282c2f752074b1  # v1.8.0
         with:
+          endpoint: ${{ vars.HETZNER_CACHE_REGION }}.${{ vars.HETZNER_CACHE_ENDPOINT }}
+          bucket: ${{ vars.HETZNER_CACHE_BUCKET }}
+          accessKey: ${{ secrets.HETZNER_CACHE_ACCESS_KEY }}
+          secretKey: ${{ secrets.HETZNER_CACHE_SECRET_KEY }}
+          use-fallback: false
           path: pg_install/build/walproposer-lib
           key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-walproposer_lib-v17-${{ steps.pg_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
 
@@ -203,32 +218,57 @@ jobs:
 
       - name: Cache postgres v14 build
         id: cache_pg
-        uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
+        uses: tespkg/actions-cache@b7bf5fcc2f98a52ac6080eb0fd282c2f752074b1  # v1.8.0
         with:
+          endpoint: ${{ vars.HETZNER_CACHE_REGION }}.${{ vars.HETZNER_CACHE_ENDPOINT }}
+          bucket: ${{ vars.HETZNER_CACHE_BUCKET }}
+          accessKey: ${{ secrets.HETZNER_CACHE_ACCESS_KEY }}
+          secretKey: ${{ secrets.HETZNER_CACHE_SECRET_KEY }}
+          use-fallback: false
           path: pg_install/v14
           key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-v14-${{ steps.pg_rev_v14.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
       - name: Cache postgres v15 build
         id: cache_pg_v15
-        uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
+        uses: tespkg/actions-cache@b7bf5fcc2f98a52ac6080eb0fd282c2f752074b1  # v1.8.0
         with:
+          endpoint: ${{ vars.HETZNER_CACHE_REGION }}.${{ vars.HETZNER_CACHE_ENDPOINT }}
+          bucket: ${{ vars.HETZNER_CACHE_BUCKET }}
+          accessKey: ${{ secrets.HETZNER_CACHE_ACCESS_KEY }}
+          secretKey: ${{ secrets.HETZNER_CACHE_SECRET_KEY }}
+          use-fallback: false
           path: pg_install/v15
           key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-v15-${{ steps.pg_rev_v15.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
       - name: Cache postgres v16 build
         id: cache_pg_v16
-        uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
+        uses: tespkg/actions-cache@b7bf5fcc2f98a52ac6080eb0fd282c2f752074b1  # v1.8.0
         with:
+          endpoint: ${{ vars.HETZNER_CACHE_REGION }}.${{ vars.HETZNER_CACHE_ENDPOINT }}
+          bucket: ${{ vars.HETZNER_CACHE_BUCKET }}
+          accessKey: ${{ secrets.HETZNER_CACHE_ACCESS_KEY }}
+          secretKey: ${{ secrets.HETZNER_CACHE_SECRET_KEY }}
+          use-fallback: false
           path: pg_install/v16
           key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-v16-${{ steps.pg_rev_v16.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
       - name: Cache postgres v17 build
         id: cache_pg_v17
-        uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
+        uses: tespkg/actions-cache@b7bf5fcc2f98a52ac6080eb0fd282c2f752074b1  # v1.8.0
         with:
+          endpoint: ${{ vars.HETZNER_CACHE_REGION }}.${{ vars.HETZNER_CACHE_ENDPOINT }}
+          bucket: ${{ vars.HETZNER_CACHE_BUCKET }}
+          accessKey: ${{ secrets.HETZNER_CACHE_ACCESS_KEY }}
+          secretKey: ${{ secrets.HETZNER_CACHE_SECRET_KEY }}
+          use-fallback: false
           path: pg_install/v17
           key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-v17-${{ steps.pg_rev_v17.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
 
       - name: Cache cargo deps (only for v17)
-        uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
+        uses: tespkg/actions-cache@b7bf5fcc2f98a52ac6080eb0fd282c2f752074b1  # v1.8.0
         with:
+          endpoint: ${{ vars.HETZNER_CACHE_REGION }}.${{ vars.HETZNER_CACHE_ENDPOINT }}
+          bucket: ${{ vars.HETZNER_CACHE_BUCKET }}
+          accessKey: ${{ secrets.HETZNER_CACHE_ACCESS_KEY }}
+          secretKey: ${{ secrets.HETZNER_CACHE_SECRET_KEY }}
+          use-fallback: false
           path: |
             ~/.cargo/registry
             !~/.cargo/registry/src
@@ -238,8 +278,13 @@ jobs:
 
       - name: Cache walproposer-lib
         id: cache_walproposer_lib
-        uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
+        uses: tespkg/actions-cache@b7bf5fcc2f98a52ac6080eb0fd282c2f752074b1  # v1.8.0
         with:
+          endpoint: ${{ vars.HETZNER_CACHE_REGION }}.${{ vars.HETZNER_CACHE_ENDPOINT }}
+          bucket: ${{ vars.HETZNER_CACHE_BUCKET }}
+          accessKey: ${{ secrets.HETZNER_CACHE_ACCESS_KEY }}
+          secretKey: ${{ secrets.HETZNER_CACHE_SECRET_KEY }}
+          use-fallback: false
           path: pg_install/build/walproposer-lib
           key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-walproposer_lib-v17-${{ steps.pg_rev_v17.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
 

.github/workflows/build_and_test.yml

@@ -284,7 +284,7 @@ jobs:
       statuses: write
       contents: write
       pull-requests: write
-    runs-on: [ self-hosted, unit-perf ]
+    runs-on: [ self-hosted, small-metal ]
     container:
       image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
       credentials:
@@ -323,8 +323,6 @@ jobs:
           PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
           TEST_RESULT_CONNSTR: "${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}"
           PAGESERVER_VIRTUAL_FILE_IO_ENGINE: tokio-epoll-uring
-          PAGESERVER_GET_VECTORED_CONCURRENT_IO: sidecar-task
-          PAGESERVER_VIRTUAL_FILE_IO_MODE: direct-rw
           SYNC_BETWEEN_TESTS: true
       # XXX: no coverage data handling here, since benchmarks are run on release builds,
       # while coverage is currently collected for the debug ones
@@ -1238,7 +1236,7 @@ jobs:
         env:
           GH_TOKEN: ${{ secrets.CI_ACCESS_TOKEN }}
         run: |
-          TIMEOUT=5400 # 90 minutes, usually it takes ~2-3 minutes, but if runners are busy, it might take longer
+          TIMEOUT=1800 # 30 minutes, usually it takes ~2-3 minutes, but if runners are busy, it might take longer
           INTERVAL=15 # try each N seconds
 
           last_status="" # a variable to carry the last status of the "build-and-upload-extensions" context
@@ -1273,7 +1271,7 @@ jobs:
           exit 1
 
   deploy:
-    needs: [ check-permissions, push-neon-image-dev, push-compute-image-dev, push-neon-image-prod, push-compute-image-prod, meta, trigger-custom-extensions-build-and-wait ]
+    needs: [ check-permissions, push-neon-image-dev, push-compute-image-dev, push-neon-image-prod, push-compute-image-prod, meta, build-and-test-locally, trigger-custom-extensions-build-and-wait ]
     # `!failure() && !cancelled()` is required because the workflow depends on the job that can be skipped: `push-neon-image-prod` and `push-compute-image-prod`
     if: ${{ contains(fromJSON('["push-main", "storage-release", "proxy-release", "compute-release"]'), needs.meta.outputs.run-kind) && !failure() && !cancelled() }}
     permissions:

.github/workflows/fast-forward.yml

@@ -27,17 +27,15 @@ jobs:
       - name: Fast forwarding
         uses: sequoia-pgp/fast-forward@ea7628bedcb0b0b96e94383ada458d812fca4979
         # See https://docs.github.com/en/graphql/reference/enums#mergestatestatus
-        if: ${{ contains(fromJSON('["clean", "unstable"]'), github.event.pull_request.mergeable_state) }}
+        if: ${{ github.event.pull_request.mergeable_state  == 'clean' }}
         with:
           merge: true
           comment: on-error
           github_token: ${{ secrets.CI_ACCESS_TOKEN }}
 
       - name: Comment if mergeable_state is not clean
-        if: ${{ !contains(fromJSON('["clean", "unstable"]'), github.event.pull_request.mergeable_state) }}
-        env:
-          GH_TOKEN: ${{ secrets.CI_ACCESS_TOKEN }}
+        if: ${{ github.event.pull_request.mergeable_state  != 'clean' }}
         run: |
           gh pr comment ${{ github.event.pull_request.number }} \
             --repo "${GITHUB_REPOSITORY}" \
-            --body "Not trying to forward pull-request, because \`mergeable_state\` is \`${{ github.event.pull_request.mergeable_state }}\`, not \`clean\` or \`unstable\`."
+            --body "Not trying to forward pull-request, because \`mergeable_state\` is \`${{ github.event.pull_request.mergeable_state }}\`, not \`clean\`."

.github/workflows/pg-clients.yml

@@ -30,7 +30,7 @@ permissions:
   statuses: write # require for posting a status update
 
 env:
-  DEFAULT_PG_VERSION: 17
+  DEFAULT_PG_VERSION: 16
   PLATFORM: neon-captest-new
   AWS_DEFAULT_REGION: eu-central-1
 
@@ -42,8 +42,6 @@ jobs:
       github-event-name: ${{ github.event_name }}
 
   build-build-tools-image:
-    permissions:
-      packages: write
     needs: [ check-permissions ]
     uses: ./.github/workflows/build-build-tools-image.yml
     secrets: inherit

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

@@ -1,93 +0,0 @@
-name: Random Operations Test
-
-on:
-  schedule:
-    # * is a special character in YAML so you have to quote this string
-    #          ┌───────────── minute (0 - 59)
-    #          │  ┌───────────── hour (0 - 23)
-    #          │  │  ┌───────────── day of the month (1 - 31)
-    #          │  │  │ ┌───────────── month (1 - 12 or JAN-DEC)
-    #          │  │  │ │ ┌───────────── day of the week (0 - 6 or SUN-SAT)
-    - cron:  '23 */2 * * *' # runs every 2 hours
-  workflow_dispatch:
-    inputs:
-      random_seed:
-        type: number
-        description: 'The random seed'
-        required: false
-        default: 0
-      num_operations:
-        type: number
-        description: "The number of operations to test"
-        default: 250
-
-defaults:
-  run:
-    shell: bash -euxo pipefail {0}
-
-permissions: {}
-
-env:
-  DEFAULT_PG_VERSION: 16
-  PLATFORM: neon-captest-new
-  AWS_DEFAULT_REGION: eu-central-1
-
-jobs:
-  run-random-rests:
-    env:
-      POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
-    runs-on: small
-    permissions:
-      id-token: write
-      statuses: write
-
-    strategy:
-      fail-fast: false
-      matrix:
-        pg-version: [16, 17]
-
-    container:
-      image: ghcr.io/neondatabase/build-tools:pinned-bookworm
-      credentials:
-        username: ${{ github.actor }}
-        password: ${{ secrets.GITHUB_TOKEN }}
-      options: --init
-    steps:
-      - name: Harden the runner (Audit all outbound calls)
-        uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
-        with:
-          egress-policy: audit
-
-      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
-
-      - name: Download Neon artifact
-        uses: ./.github/actions/download
-        with:
-          name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
-          path: /tmp/neon/
-          prefix: latest
-          aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
-
-      - name: Run tests
-        uses: ./.github/actions/run-python-test-set
-        with:
-          build_type: remote
-          test_selection: random_ops
-          run_in_parallel: false
-          extra_params: -m remote_cluster
-          pg_version: ${{ matrix.pg-version }}
-          aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
-        env:
-          NEON_API_KEY: ${{ secrets.NEON_STAGING_API_KEY }}
-          RANDOM_SEED: ${{ inputs.random_seed }}
-          NUM_OPERATIONS: ${{ inputs.num_operations }}
-
-      - name: Create Allure report
-        if: ${{ !cancelled() }}
-        id: create-allure-report
-        uses: ./.github/actions/allure-report-generate
-        with:
-          store-test-results-into-db: true
-          aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
-        env:
-          REGRESS_TEST_RESULT_CONNSTR_NEW: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}

Cargo.lock

@@ -40,7 +40,7 @@ dependencies = [
  "getrandom 0.2.11",
  "once_cell",
  "version_check",
- "zerocopy 0.7.31",
+ "zerocopy",
 ]
 
 [[package]]
@@ -1323,6 +1323,7 @@ dependencies = [
  "serde_json",
  "serde_with",
  "signal-hook",
+ "spki 0.7.3",
  "tar",
  "thiserror 1.0.69",
  "tokio",
@@ -1415,7 +1416,6 @@ name = "control_plane"
 version = "0.1.0"
 dependencies = [
  "anyhow",
- "base64 0.13.1",
  "camino",
  "clap",
  "comfy-table",
@@ -1425,12 +1425,10 @@ dependencies = [
  "humantime",
  "humantime-serde",
  "hyper 0.14.30",
- "jsonwebtoken",
  "nix 0.27.1",
  "once_cell",
  "pageserver_api",
  "pageserver_client",
- "pem",
  "postgres_backend",
  "postgres_connection",
  "regex",
@@ -1439,8 +1437,6 @@ dependencies = [
  "scopeguard",
  "serde",
  "serde_json",
- "sha2",
- "spki 0.7.3",
  "storage_broker",
  "thiserror 1.0.69",
  "tokio",
@@ -2036,33 +2032,6 @@ dependencies = [
  "zeroize",
 ]
 
-[[package]]
-name = "endpoint_storage"
-version = "0.0.1"
-dependencies = [
- "anyhow",
- "axum",
- "axum-extra",
- "camino",
- "camino-tempfile",
- "futures",
- "http-body-util",
- "itertools 0.10.5",
- "jsonwebtoken",
- "prometheus",
- "rand 0.8.5",
- "remote_storage",
- "serde",
- "serde_json",
- "test-log",
- "tokio",
- "tokio-util",
- "tower 0.5.2",
- "tracing",
- "utils",
- "workspace_hack",
-]
-
 [[package]]
 name = "enum-map"
 version = "2.5.0"
@@ -2848,7 +2817,6 @@ dependencies = [
  "hyper 0.14.30",
  "itertools 0.10.5",
  "jemalloc_pprof",
- "jsonwebtoken",
  "metrics",
  "once_cell",
  "pprof",
@@ -4024,6 +3992,33 @@ dependencies = [
  "memchr",
 ]
 
+[[package]]
+name = "object_storage"
+version = "0.0.1"
+dependencies = [
+ "anyhow",
+ "axum",
+ "axum-extra",
+ "camino",
+ "camino-tempfile",
+ "futures",
+ "http-body-util",
+ "itertools 0.10.5",
+ "jsonwebtoken",
+ "prometheus",
+ "rand 0.8.5",
+ "remote_storage",
+ "serde",
+ "serde_json",
+ "test-log",
+ "tokio",
+ "tokio-util",
+ "tower 0.5.2",
+ "tracing",
+ "utils",
+ "workspace_hack",
+]
+
 [[package]]
 name = "once_cell"
 version = "1.20.2"
@@ -4274,7 +4269,6 @@ dependencies = [
  "hyper 0.14.30",
  "indoc",
  "itertools 0.10.5",
- "jsonwebtoken",
  "md5",
  "metrics",
  "nix 0.27.1",
@@ -4284,7 +4278,6 @@ dependencies = [
  "pageserver_api",
  "pageserver_client",
  "pageserver_compaction",
- "pem",
  "pin-project-lite",
  "postgres-protocol",
  "postgres-types",
@@ -4301,7 +4294,6 @@ dependencies = [
  "remote_storage",
  "reqwest",
  "rpds",
- "rstest",
  "rustls 0.23.18",
  "scopeguard",
  "send-future",
@@ -4353,7 +4345,6 @@ dependencies = [
  "humantime-serde",
  "itertools 0.10.5",
  "nix 0.27.1",
- "once_cell",
  "postgres_backend",
  "postgres_ffi",
  "rand 0.8.5",
@@ -4415,9 +4406,9 @@ dependencies = [
 
 [[package]]
 name = "papaya"
-version = "0.2.1"
+version = "0.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6827e3fc394523c21d4464d02c0bb1c19966ea4a58a9844ad6d746214179d2bc"
+checksum = "aab21828b6b5952fdadd6c377728ffae53ec3a21b2febc47319ab65741f7e2fd"
 dependencies = [
  "equivalent",
  "seize",
@@ -5204,7 +5195,7 @@ dependencies = [
  "walkdir",
  "workspace_hack",
  "x509-cert",
- "zerocopy 0.8.24",
+ "zerocopy",
 ]
 
 [[package]]
@@ -5594,7 +5585,7 @@ dependencies = [
  "wasm-bindgen-futures",
  "wasm-streams",
  "web-sys",
- "webpki-roots",
+ "webpki-roots 0.26.1",
  "winreg",
 ]
 
@@ -5694,9 +5685,9 @@ dependencies = [
 
 [[package]]
 name = "ring"
-version = "0.17.14"
+version = "0.17.13"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a4689e6c2294d81e88dc6261c768b63bc4fcdb852be6d1352498b114f61383b7"
+checksum = "70ac5d832aa16abd7d1def883a8545280c20a60f523a370aa3a9617c2b8550ee"
 dependencies = [
  "cc",
  "cfg-if",
@@ -5997,12 +5988,10 @@ dependencies = [
  "humantime",
  "hyper 0.14.30",
  "itertools 0.10.5",
- "jsonwebtoken",
  "metrics",
  "once_cell",
  "pageserver_api",
  "parking_lot 0.12.1",
- "pem",
  "postgres-protocol",
  "postgres_backend",
  "postgres_ffi",
@@ -6195,13 +6184,13 @@ checksum = "224e328af6e080cddbab3c770b1cf50f0351ba0577091ef2410c3951d835ff87"
 
 [[package]]
 name = "sentry"
-version = "0.37.0"
+version = "0.32.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "255914a8e53822abd946e2ce8baa41d4cded6b8e938913b7f7b9da5b7ab44335"
+checksum = "00421ed8fa0c995f07cde48ba6c89e80f2b312f74ff637326f392fbfd23abe02"
 dependencies = [
  "httpdate",
  "reqwest",
- "rustls 0.23.18",
+ "rustls 0.21.12",
  "sentry-backtrace",
  "sentry-contexts",
  "sentry-core",
@@ -6209,14 +6198,14 @@ dependencies = [
  "sentry-tracing",
  "tokio",
  "ureq",
- "webpki-roots",
+ "webpki-roots 0.25.2",
 ]
 
 [[package]]
 name = "sentry-backtrace"
-version = "0.37.0"
+version = "0.32.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "00293cd332a859961f24fd69258f7e92af736feaeb91020cff84dac4188a4302"
+checksum = "a79194074f34b0cbe5dd33896e5928bbc6ab63a889bd9df2264af5acb186921e"
 dependencies = [
  "backtrace",
  "once_cell",
@@ -6226,9 +6215,9 @@ dependencies = [
 
 [[package]]
 name = "sentry-contexts"
-version = "0.37.0"
+version = "0.32.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "961990f9caa76476c481de130ada05614cd7f5aa70fb57c2142f0e09ad3fb2aa"
+checksum = "eba8870c5dba2bfd9db25c75574a11429f6b95957b0a78ac02e2970dd7a5249a"
 dependencies = [
  "hostname",
  "libc",
@@ -6240,9 +6229,9 @@ dependencies = [
 
 [[package]]
 name = "sentry-core"
-version = "0.37.0"
+version = "0.32.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1a6409d845707d82415c800290a5d63be5e3df3c2e417b0997c60531dfbd35ef"
+checksum = "46a75011ea1c0d5c46e9e57df03ce81f5c7f0a9e199086334a1f9c0a541e0826"
 dependencies = [
  "once_cell",
  "rand 0.8.5",
@@ -6253,9 +6242,9 @@ dependencies = [
 
 [[package]]
 name = "sentry-panic"
-version = "0.37.0"
+version = "0.32.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "609b1a12340495ce17baeec9e08ff8ed423c337c1a84dffae36a178c783623f3"
+checksum = "2eaa3ecfa3c8750c78dcfd4637cfa2598b95b52897ed184b4dc77fcf7d95060d"
 dependencies = [
  "sentry-backtrace",
  "sentry-core",
@@ -6263,9 +6252,9 @@ dependencies = [
 
 [[package]]
 name = "sentry-tracing"
-version = "0.37.0"
+version = "0.32.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "49f4e86402d5c50239dc7d8fd3f6d5e048221d5fcb4e026d8d50ab57fe4644cb"
+checksum = "f715932bf369a61b7256687c6f0554141b7ce097287e30e3f7ed6e9de82498fe"
 dependencies = [
  "sentry-backtrace",
  "sentry-core",
@@ -6275,9 +6264,9 @@ dependencies = [
 
 [[package]]
 name = "sentry-types"
-version = "0.37.0"
+version = "0.32.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3d3f117b8755dbede8260952de2aeb029e20f432e72634e8969af34324591631"
+checksum = "4519c900ce734f7a0eb7aba0869dfb225a7af8820634a7dd51449e3b093cfb7c"
 dependencies = [
  "debugid",
  "hex",
@@ -6711,6 +6700,8 @@ version = "0.1.0"
 dependencies = [
  "anyhow",
  "async-stream",
+ "aws-config",
+ "aws-sdk-s3",
  "camino",
  "chrono",
  "clap",
@@ -7799,7 +7790,7 @@ dependencies = [
  "rustls 0.23.18",
  "rustls-pki-types",
  "url",
- "webpki-roots",
+ "webpki-roots 0.26.1",
 ]
 
 [[package]]
@@ -7881,7 +7872,6 @@ dependencies = [
  "metrics",
  "nix 0.27.1",
  "once_cell",
- "pem",
  "pin-project-lite",
  "postgres_connection",
  "pprof",
@@ -8167,6 +8157,12 @@ dependencies = [
  "wasm-bindgen",
 ]
 
+[[package]]
+name = "webpki-roots"
+version = "0.25.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "14247bb57be4f377dfb94c72830b8ce8fc6beac03cf4bf7b9732eadd414123fc"
+
 [[package]]
 name = "webpki-roots"
 version = "0.26.1"
@@ -8474,8 +8470,6 @@ dependencies = [
  "regex-syntax 0.8.2",
  "reqwest",
  "rustls 0.23.18",
- "rustls-pki-types",
- "rustls-webpki 0.102.8",
  "scopeguard",
  "sec1 0.7.3",
  "serde",
@@ -8504,6 +8498,7 @@ dependencies = [
  "tracing-log",
  "url",
  "uuid",
+ "zerocopy",
  "zeroize",
  "zstd",
  "zstd-safe",
@@ -8607,16 +8602,8 @@ version = "0.7.31"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1c4061bedbb353041c12f413700357bec76df2c7e2ca8e4df8bac24c6bf68e3d"
 dependencies = [
- "zerocopy-derive 0.7.31",
-]
-
-[[package]]
-name = "zerocopy"
-version = "0.8.24"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2586fea28e186957ef732a5f8b3be2da217d65c5969d4b1e17f973ebbe876879"
-dependencies = [
- "zerocopy-derive 0.8.24",
+ "byteorder",
+ "zerocopy-derive",
 ]
 
 [[package]]
@@ -8630,17 +8617,6 @@ dependencies = [
  "syn 2.0.100",
 ]
 
-[[package]]
-name = "zerocopy-derive"
-version = "0.8.24"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a996a8f63c5c4448cd959ac1bab0aaa3306ccfd060472f85943ee0750f0169be"
-dependencies = [
- "proc-macro2",
- "quote",
- "syn 2.0.100",
-]
-
 [[package]]
 name = "zerofrom"
 version = "0.1.5"

Cargo.toml

@@ -40,7 +40,7 @@ members = [
     "libs/proxy/postgres-protocol2",
     "libs/proxy/postgres-types2",
     "libs/proxy/tokio-postgres2",
-    "endpoint_storage",
+    "object_storage",
 ]
 
 [workspace.package]
@@ -141,7 +141,6 @@ parking_lot = "0.12"
 parquet = { version = "53", default-features = false, features = ["zstd"] }
 parquet_derive = "53"
 pbkdf2 = { version = "0.12.1", features = ["simple", "std"] }
-pem = "3.0.3"
 pin-project-lite = "0.2"
 pprof = { version = "0.14", features = ["criterion", "flamegraph", "frame-pointer", "prost-codec"] }
 procfs = "0.16"
@@ -164,7 +163,7 @@ scopeguard = "1.1"
 sysinfo = "0.29.2"
 sd-notify = "0.4.1"
 send-future = "0.1.0"
-sentry = { version = "0.37", default-features = false, features = ["backtrace", "contexts", "panic", "rustls", "reqwest" ] }
+sentry = { version = "0.32", default-features = false, features = ["backtrace", "contexts", "panic", "rustls", "reqwest" ] }
 serde = { version = "1.0", features = ["derive"] }
 serde_json = "1"
 serde_path_to_error = "0.1"
@@ -175,7 +174,6 @@ signal-hook = "0.3"
 smallvec = "1.11"
 smol_str = { version = "0.2.0", features = ["serde"] }
 socket2 = "0.5"
-spki = "0.7.3"
 strum = "0.26"
 strum_macros = "0.26"
 "subtle"  = "2.5.0"
@@ -220,7 +218,7 @@ uuid = { version = "1.6.1", features = ["v4", "v7", "serde"] }
 walkdir = "2.3.2"
 rustls-native-certs = "0.8"
 whoami = "1.5.1"
-zerocopy = { version = "0.8", features = ["derive", "simd"] }
+zerocopy = { version = "0.7", features = ["derive"] }
 json-structural-diff = { version = "0.2.0" }
 x509-cert = { version = "0.2.5" }
 

Dockerfile

@@ -89,7 +89,7 @@ RUN set -e \
       --bin storage_broker  \
       --bin storage_controller  \
       --bin proxy  \
-      --bin endpoint_storage \
+      --bin object_storage \
       --bin neon_local \
       --bin storage_scrubber \
       --locked --release
@@ -122,7 +122,7 @@ COPY --from=build --chown=neon:neon /home/nonroot/target/release/safekeeper
 COPY --from=build --chown=neon:neon /home/nonroot/target/release/storage_broker      /usr/local/bin
 COPY --from=build --chown=neon:neon /home/nonroot/target/release/storage_controller  /usr/local/bin
 COPY --from=build --chown=neon:neon /home/nonroot/target/release/proxy               /usr/local/bin
-COPY --from=build --chown=neon:neon /home/nonroot/target/release/endpoint_storage    /usr/local/bin
+COPY --from=build --chown=neon:neon /home/nonroot/target/release/object_storage      /usr/local/bin
 COPY --from=build --chown=neon:neon /home/nonroot/target/release/neon_local          /usr/local/bin
 COPY --from=build --chown=neon:neon /home/nonroot/target/release/storage_scrubber    /usr/local/bin
 

README.md

@@ -270,7 +270,7 @@ By default, this runs both debug and release modes, and all supported postgres v
 testing locally, it is convenient to run just one set of permutations, like this:
 
 ```sh
-DEFAULT_PG_VERSION=17 BUILD_TYPE=release ./scripts/pytest
+DEFAULT_PG_VERSION=16 BUILD_TYPE=release ./scripts/pytest
 ```
 
 ## Flamegraphs

build-tools.Dockerfile

@@ -173,7 +173,7 @@ RUN curl -fsSL "https://github.com/protocolbuffers/protobuf/releases/download/v$
     && rm -rf protoc.zip protoc
 
 # s5cmd
-ENV S5CMD_VERSION=2.3.0
+ENV S5CMD_VERSION=2.2.2
 RUN curl -sL "https://github.com/peak/s5cmd/releases/download/v${S5CMD_VERSION}/s5cmd_${S5CMD_VERSION}_Linux-$(uname -m | sed 's/x86_64/64bit/g' | sed 's/aarch64/arm64/g').tar.gz" | tar zxvf - s5cmd \
     && chmod +x s5cmd \
     && mv s5cmd /usr/local/bin/s5cmd
@@ -206,7 +206,7 @@ RUN curl "https://awscli.amazonaws.com/awscli-exe-linux-$(uname -m).zip" -o "aws
     && rm awscliv2.zip
 
 # Mold: A Modern Linker
-ENV MOLD_VERSION=v2.37.1
+ENV MOLD_VERSION=v2.34.1
 RUN set -e \
     && git clone https://github.com/rui314/mold.git \
     && mkdir mold/build \
@@ -268,7 +268,7 @@ WORKDIR /home/nonroot
 RUN echo -e "--retry-connrefused\n--connect-timeout 15\n--retry 5\n--max-time 300\n" > /home/nonroot/.curlrc
 
 # Python
-ENV PYTHON_VERSION=3.11.12 \
+ENV PYTHON_VERSION=3.11.10 \
     PYENV_ROOT=/home/nonroot/.pyenv \
     PATH=/home/nonroot/.pyenv/shims:/home/nonroot/.pyenv/bin:/home/nonroot/.poetry/bin:$PATH
 RUN set -e \
@@ -296,12 +296,12 @@ ENV RUSTC_VERSION=1.86.0
 ENV RUSTUP_HOME="/home/nonroot/.rustup"
 ENV PATH="/home/nonroot/.cargo/bin:${PATH}"
 ARG RUSTFILT_VERSION=0.2.1
-ARG CARGO_HAKARI_VERSION=0.9.36
-ARG CARGO_DENY_VERSION=0.18.2
-ARG CARGO_HACK_VERSION=0.6.36
-ARG CARGO_NEXTEST_VERSION=0.9.94
+ARG CARGO_HAKARI_VERSION=0.9.33
+ARG CARGO_DENY_VERSION=0.16.2
+ARG CARGO_HACK_VERSION=0.6.33
+ARG CARGO_NEXTEST_VERSION=0.9.85
 ARG CARGO_CHEF_VERSION=0.1.71
-ARG CARGO_DIESEL_CLI_VERSION=2.2.9
+ARG CARGO_DIESEL_CLI_VERSION=2.2.6
 RUN curl -sSO https://static.rust-lang.org/rustup/dist/$(uname -m)-unknown-linux-gnu/rustup-init && whoami && \
 	chmod +x rustup-init && \
 	./rustup-init -y --default-toolchain ${RUSTC_VERSION} && \

clippy.toml

@@ -12,5 +12,3 @@ disallowed-macros = [
     # cannot disallow this, because clippy finds used from tokio macros
     #"tokio::pin",
 ]
-
-allow-unwrap-in-tests = true

compute/compute-node.Dockerfile

@@ -1677,7 +1677,7 @@ RUN set -e \
     && 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_24_1
+ENV PGBOUNCER_TAG=pgbouncer_1_22_1
 RUN set -e \
     && git clone --recurse-submodules --depth 1 --branch ${PGBOUNCER_TAG} https://github.com/pgbouncer/pgbouncer.git pgbouncer \
     && cd pgbouncer \

compute/patches/pg_anon.patch

@@ -0,0 +1,265 @@
+commit 00aa659afc9c7336ab81036edec3017168aabf40
+Author: Heikki Linnakangas <heikki@neon.tech>
+Date:   Tue Nov 12 16:59:19 2024 +0200
+
+    Temporarily disable test that depends on timezone
+
+diff --git a/tests/expected/generalization.out b/tests/expected/generalization.out
+index 23ef5fa..9e60deb 100644
+--- a/ext-src/pg_anon-src/tests/expected/generalization.out
++++ b/ext-src/pg_anon-src/tests/expected/generalization.out
+@@ -284,12 +284,9 @@ SELECT anon.generalize_tstzrange('19041107','century');
+  ["Tue Jan 01 00:00:00 1901 PST","Mon Jan 01 00:00:00 2001 PST")
+ (1 row)
+ 
+-SELECT anon.generalize_tstzrange('19041107','millennium');
+-                      generalize_tstzrange                       
+------------------------------------------------------------------
+- ["Thu Jan 01 00:00:00 1001 PST","Mon Jan 01 00:00:00 2001 PST")
+-(1 row)
+-
++-- temporarily disabled, see:
++-- https://gitlab.com/dalibo/postgresql_anonymizer/-/commit/199f0a392b37c59d92ae441fb8f037e094a11a52#note_2148017485
++--SELECT anon.generalize_tstzrange('19041107','millennium');
+ -- generalize_daterange
+ SELECT anon.generalize_daterange('19041107');
+   generalize_daterange   
+diff --git a/tests/sql/generalization.sql b/tests/sql/generalization.sql
+index b868344..b4fc977 100644
+--- a/ext-src/pg_anon-src/tests/sql/generalization.sql
++++ b/ext-src/pg_anon-src/tests/sql/generalization.sql
+@@ -61,7 +61,9 @@ SELECT anon.generalize_tstzrange('19041107','month');
+ SELECT anon.generalize_tstzrange('19041107','year');
+ SELECT anon.generalize_tstzrange('19041107','decade');
+ SELECT anon.generalize_tstzrange('19041107','century');
+-SELECT anon.generalize_tstzrange('19041107','millennium');
++-- temporarily disabled, see:
++-- https://gitlab.com/dalibo/postgresql_anonymizer/-/commit/199f0a392b37c59d92ae441fb8f037e094a11a52#note_2148017485
++--SELECT anon.generalize_tstzrange('19041107','millennium');
+ 
+ -- generalize_daterange
+ SELECT anon.generalize_daterange('19041107');
+
+commit 7dd414ee75f2875cffb1d6ba474df1f135a6fc6f
+Author: Alexey Masterov <alexeymasterov@neon.tech>
+Date:   Fri May 31 06:34:26 2024 +0000
+
+    These alternative expected files were added to consider the neon features
+
+diff --git a/ext-src/pg_anon-src/tests/expected/permissions_masked_role_1.out b/ext-src/pg_anon-src/tests/expected/permissions_masked_role_1.out
+new file mode 100644
+index 0000000..2539cfd
+--- /dev/null
++++ b/ext-src/pg_anon-src/tests/expected/permissions_masked_role_1.out
+@@ -0,0 +1,101 @@
++BEGIN;
++CREATE EXTENSION anon CASCADE;
++NOTICE:  installing required extension "pgcrypto"
++SELECT anon.init();
++ init 
++------
++ t
++(1 row)
++
++CREATE ROLE mallory_the_masked_user;
++SECURITY LABEL FOR anon ON ROLE mallory_the_masked_user IS 'MASKED';
++CREATE TABLE t1(i INT);
++ALTER TABLE t1 ADD COLUMN t TEXT;
++SECURITY LABEL FOR anon ON COLUMN t1.t
++IS 'MASKED WITH VALUE NULL';
++INSERT INTO t1 VALUES (1,'test');
++--
++-- We're checking the owner's permissions
++--
++-- see
++-- https://postgresql-anonymizer.readthedocs.io/en/latest/SECURITY/#permissions
++--
++SET ROLE mallory_the_masked_user;
++SELECT anon.pseudo_first_name(0) IS NOT NULL;
++ ?column? 
++----------
++ t
++(1 row)
++
++-- SHOULD FAIL
++DO $$
++BEGIN
++  PERFORM anon.init();
++  EXCEPTION WHEN insufficient_privilege
++  THEN RAISE NOTICE 'insufficient_privilege';
++END$$;
++NOTICE:  insufficient_privilege
++-- SHOULD FAIL
++DO $$
++BEGIN
++  PERFORM anon.anonymize_table('t1');
++  EXCEPTION WHEN insufficient_privilege
++  THEN RAISE NOTICE 'insufficient_privilege';
++END$$;
++NOTICE:  insufficient_privilege
++-- SHOULD FAIL
++SAVEPOINT fail_start_engine;
++SELECT anon.start_dynamic_masking();
++ERROR:  Only supersusers can start the dynamic masking engine.
++CONTEXT:  PL/pgSQL function anon.start_dynamic_masking(boolean) line 18 at RAISE
++ROLLBACK TO fail_start_engine;
++RESET ROLE;
++SELECT anon.start_dynamic_masking();
++ start_dynamic_masking 
++-----------------------
++ t
++(1 row)
++
++SET ROLE mallory_the_masked_user;
++SELECT * FROM mask.t1;
++ i | t 
++---+---
++ 1 | 
++(1 row)
++
++-- SHOULD FAIL
++DO $$
++BEGIN
++  SELECT * FROM public.t1;
++  EXCEPTION WHEN insufficient_privilege
++  THEN RAISE NOTICE 'insufficient_privilege';
++END$$;
++NOTICE:  insufficient_privilege
++-- SHOULD FAIL
++SAVEPOINT fail_stop_engine;
++SELECT anon.stop_dynamic_masking();
++ERROR:  Only supersusers can stop the dynamic masking engine.
++CONTEXT:  PL/pgSQL function anon.stop_dynamic_masking() line 18 at RAISE
++ROLLBACK TO fail_stop_engine;
++RESET ROLE;
++SELECT anon.stop_dynamic_masking();
++NOTICE:  The previous priviledges of 'mallory_the_masked_user' are not restored. You need to grant them manually.
++ stop_dynamic_masking 
++----------------------
++ t
++(1 row)
++
++SET ROLE mallory_the_masked_user;
++SELECT COUNT(*)=1 FROM anon.pg_masking_rules;
++ ?column? 
++----------
++ t
++(1 row)
++
++-- SHOULD FAIL
++SAVEPOINT fail_seclabel_on_role;
++SECURITY LABEL FOR anon ON ROLE mallory_the_masked_user IS NULL;
++ERROR:  permission denied
++DETAIL:  The current user must have the CREATEROLE attribute.
++ROLLBACK TO fail_seclabel_on_role;
++ROLLBACK;
+diff --git a/ext-src/pg_anon-src/tests/expected/permissions_owner_1.out b/ext-src/pg_anon-src/tests/expected/permissions_owner_1.out
+new file mode 100644
+index 0000000..8b090fe
+--- /dev/null
++++ b/ext-src/pg_anon-src/tests/expected/permissions_owner_1.out
+@@ -0,0 +1,104 @@
++BEGIN;
++CREATE EXTENSION anon CASCADE;
++NOTICE:  installing required extension "pgcrypto"
++SELECT anon.init();
++ init 
++------
++ t
++(1 row)
++
++CREATE ROLE oscar_the_owner;
++ALTER DATABASE :DBNAME OWNER TO oscar_the_owner;
++CREATE ROLE mallory_the_masked_user;
++SECURITY LABEL FOR anon ON ROLE mallory_the_masked_user IS 'MASKED';
++--
++-- We're checking the owner's permissions
++--
++-- see
++-- https://postgresql-anonymizer.readthedocs.io/en/latest/SECURITY/#permissions
++--
++SET ROLE oscar_the_owner;
++SELECT anon.pseudo_first_name(0) IS NOT NULL;
++ ?column? 
++----------
++ t
++(1 row)
++
++-- SHOULD FAIL
++DO $$
++BEGIN
++  PERFORM anon.init();
++  EXCEPTION WHEN insufficient_privilege
++  THEN RAISE NOTICE 'insufficient_privilege';
++END$$;
++NOTICE:  insufficient_privilege
++CREATE TABLE t1(i INT);
++ALTER TABLE t1 ADD COLUMN t TEXT;
++SECURITY LABEL FOR anon ON COLUMN t1.t
++IS 'MASKED WITH VALUE NULL';
++INSERT INTO t1 VALUES (1,'test');
++SELECT anon.anonymize_table('t1');
++ anonymize_table 
++-----------------
++ t
++(1 row)
++
++SELECT * FROM t1;
++ i | t 
++---+---
++ 1 | 
++(1 row)
++
++UPDATE t1 SET t='test' WHERE i=1;
++-- SHOULD FAIL
++SAVEPOINT fail_start_engine;
++SELECT anon.start_dynamic_masking();
++ start_dynamic_masking 
++-----------------------
++ t
++(1 row)
++
++ROLLBACK TO fail_start_engine;
++RESET ROLE;
++SELECT anon.start_dynamic_masking();
++ start_dynamic_masking 
++-----------------------
++ t
++(1 row)
++
++SET ROLE oscar_the_owner;
++SELECT * FROM t1;
++ i |  t   
++---+------
++ 1 | test
++(1 row)
++
++--SELECT * FROM mask.t1;
++-- SHOULD FAIL
++SAVEPOINT fail_stop_engine;
++SELECT anon.stop_dynamic_masking();
++ERROR:  permission denied for schema mask
++CONTEXT:  SQL statement "DROP VIEW mask.t1;"
++PL/pgSQL function anon.mask_drop_view(oid) line 3 at EXECUTE
++SQL statement "SELECT anon.mask_drop_view(oid)
++  FROM pg_catalog.pg_class
++  WHERE relnamespace=quote_ident(pg_catalog.current_setting('anon.sourceschema'))::REGNAMESPACE
++  AND relkind IN ('r','p','f')"
++PL/pgSQL function anon.stop_dynamic_masking() line 22 at PERFORM
++ROLLBACK TO fail_stop_engine;
++RESET ROLE;
++SELECT anon.stop_dynamic_masking();
++NOTICE:  The previous priviledges of 'mallory_the_masked_user' are not restored. You need to grant them manually.
++ stop_dynamic_masking 
++----------------------
++ t
++(1 row)
++
++SET ROLE oscar_the_owner;
++-- SHOULD FAIL
++SAVEPOINT fail_seclabel_on_role;
++SECURITY LABEL FOR anon ON ROLE mallory_the_masked_user IS NULL;
++ERROR:  permission denied
++DETAIL:  The current user must have the CREATEROLE attribute.
++ROLLBACK TO fail_seclabel_on_role;
++ROLLBACK;

compute/patches/pg_repack.patch

@@ -11,14 +11,6 @@ index bf6edcb..89b4c7f 100644
  
  USE_PGXS = 1	# use pgxs if not in contrib directory
  PGXS := $(shell $(PG_CONFIG) --pgxs)
-diff --git a/regress/expected/init-extension.out b/regress/expected/init-extension.out
-index 9f2e171..f6e4f8d 100644
---- a/regress/expected/init-extension.out
-+++ b/regress/expected/init-extension.out
-@@ -1,3 +1,2 @@
- SET client_min_messages = warning;
- CREATE EXTENSION pg_repack;
--RESET client_min_messages;
 diff --git a/regress/expected/nosuper.out b/regress/expected/nosuper.out
 index 8d0a94e..63b68bf 100644
 --- a/regress/expected/nosuper.out
@@ -50,14 +42,6 @@ index 8d0a94e..63b68bf 100644
  INFO: repacking table "public.tbl_cluster"
  ERROR: query failed: ERROR:  current transaction is aborted, commands ignored until end of transaction block
  DETAIL: query was: RESET lock_timeout
-diff --git a/regress/sql/init-extension.sql b/regress/sql/init-extension.sql
-index 9f2e171..f6e4f8d 100644
---- a/regress/sql/init-extension.sql
-+++ b/regress/sql/init-extension.sql
-@@ -1,3 +1,2 @@
- SET client_min_messages = warning;
- CREATE EXTENSION pg_repack;
--RESET client_min_messages;
 diff --git a/regress/sql/nosuper.sql b/regress/sql/nosuper.sql
 index 072f0fa..dbe60f8 100644
 --- a/regress/sql/nosuper.sql

compute/patches/pgvector.patch

@@ -15,7 +15,7 @@ index 7a4b88c..56678af 100644
  HEADERS = src/halfvec.h src/sparsevec.h src/vector.h
  
 diff --git a/src/hnswbuild.c b/src/hnswbuild.c
-index b667478..1298aa1 100644
+index b667478..dc95d89 100644
 --- a/src/hnswbuild.c
 +++ b/src/hnswbuild.c
 @@ -843,9 +843,17 @@ HnswParallelBuildMain(dsm_segment *seg, shm_toc *toc)
@@ -36,7 +36,7 @@ index b667478..1298aa1 100644
  	/* Close relations within worker */
  	index_close(indexRel, indexLockmode);
  	table_close(heapRel, heapLockmode);
-@@ -1100,13 +1108,25 @@ BuildIndex(Relation heap, Relation index, IndexInfo *indexInfo,
+@@ -1100,12 +1108,39 @@ BuildIndex(Relation heap, Relation index, IndexInfo *indexInfo,
  	SeedRandom(42);
  #endif
  
@@ -48,17 +48,32 @@ index b667478..1298aa1 100644
  
  	BuildGraph(buildstate, forkNum);
  
+-	if (RelationNeedsWAL(index) || forkNum == INIT_FORKNUM)
 +#ifdef NEON_SMGR
 +	smgr_finish_unlogged_build_phase_1(RelationGetSmgr(index));
 +#endif
 +
- 	if (RelationNeedsWAL(index) || forkNum == INIT_FORKNUM)
++	if (RelationNeedsWAL(index) || forkNum == INIT_FORKNUM) {
  		log_newpage_range(index, forkNum, 0, RelationGetNumberOfBlocksInFork(index, forkNum), true);
- 
++#ifdef NEON_SMGR
++		{
++#if PG_VERSION_NUM >= 160000
++			RelFileLocator rlocator = RelationGetSmgr(index)->smgr_rlocator.locator;
++#else
++			RelFileNode rlocator = RelationGetSmgr(index)->smgr_rnode.node;
++#endif
++			if (set_lwlsn_block_range_hook)
++				set_lwlsn_block_range_hook(XactLastRecEnd, rlocator,
++										   MAIN_FORKNUM, 0, RelationGetNumberOfBlocks(index));
++			if (set_lwlsn_relation_hook)
++				set_lwlsn_relation_hook(XactLastRecEnd, rlocator, MAIN_FORKNUM);
++		}
++#endif
++	}
++
 +#ifdef NEON_SMGR
 +	smgr_end_unlogged_build(RelationGetSmgr(index));
 +#endif
-+
+ 
  	FreeBuildState(buildstate);
  }
- 

compute/patches/rum.patch

@@ -1,5 +1,5 @@
 diff --git a/src/ruminsert.c b/src/ruminsert.c
-index 255e616..1c6edb7 100644
+index 255e616..7a2240f 100644
 --- a/src/ruminsert.c
 +++ b/src/ruminsert.c
 @@ -628,6 +628,10 @@ rumbuild(Relation heap, Relation index, struct IndexInfo *indexInfo)
@@ -24,12 +24,24 @@ index 255e616..1c6edb7 100644
  	/*
  	 * Write index to xlog
  	 */
-@@ -713,6 +721,10 @@ rumbuild(Relation heap, Relation index, struct IndexInfo *indexInfo)
+@@ -713,6 +721,22 @@ rumbuild(Relation heap, Relation index, struct IndexInfo *indexInfo)
  		UnlockReleaseBuffer(buffer);
  	}
  
 +#ifdef NEON_SMGR
-+	smgr_end_unlogged_build(index->rd_smgr);
++	{
++#if PG_VERSION_NUM >= 160000
++		RelFileLocator rlocator = RelationGetSmgr(index)->smgr_rlocator.locator;
++#else
++		RelFileNode rlocator = RelationGetSmgr(index)->smgr_rnode.node;
++#endif
++		if (set_lwlsn_block_range_hook)
++			set_lwlsn_block_range_hook(XactLastRecEnd, rlocator, MAIN_FORKNUM, 0, RelationGetNumberOfBlocks(index));
++		if (set_lwlsn_relation_hook)
++			set_lwlsn_relation_hook(XactLastRecEnd, rlocator, MAIN_FORKNUM);
++
++		smgr_end_unlogged_build(index->rd_smgr);
++	}
 +#endif
 +
  	/*

compute/vm-image-spec-bookworm.yaml

@@ -22,7 +22,7 @@ commands:
   - name: local_proxy
     user: postgres
     sysvInitAction: respawn
-    shell: 'RUST_LOG="info,proxy::serverless::sql_over_http=warn" /usr/local/bin/local_proxy --config-path /etc/local_proxy/config.json --pid-path /etc/local_proxy/pid --http 0.0.0.0:10432'
+    shell: '/usr/local/bin/local_proxy --config-path /etc/local_proxy/config.json --pid-path /etc/local_proxy/pid --http 0.0.0.0:10432'
   - name: postgres-exporter
     user: nobody
     sysvInitAction: respawn

compute/vm-image-spec-bullseye.yaml

@@ -22,7 +22,7 @@ commands:
   - name: local_proxy
     user: postgres
     sysvInitAction: respawn
-    shell: 'RUST_LOG="info,proxy::serverless::sql_over_http=warn" /usr/local/bin/local_proxy --config-path /etc/local_proxy/config.json --pid-path /etc/local_proxy/pid --http 0.0.0.0:10432'
+    shell: '/usr/local/bin/local_proxy --config-path /etc/local_proxy/config.json --pid-path /etc/local_proxy/pid --http 0.0.0.0:10432'
   - name: postgres-exporter
     user: nobody
     sysvInitAction: respawn

compute_tools/Cargo.toml

@@ -44,6 +44,7 @@ serde.workspace = true
 serde_with.workspace = true
 serde_json.workspace = true
 signal-hook.workspace = true
+spki = { version = "0.7.3", features = ["std"] }
 tar.workspace = true
 tower.workspace = true
 tower-http.workspace = true

compute_tools/src/bin/compute_ctl.rs

@@ -29,12 +29,13 @@
 //! ```sh
 //! compute_ctl -D /var/db/postgres/compute \
 //!             -C 'postgresql://cloud_admin@localhost/postgres' \
-//!             -c /var/db/postgres/configs/config.json \
+//!             -S /var/db/postgres/specs/current.json \
 //!             -b /usr/local/bin/postgres \
 //!             -r http://pg-ext-s3-gateway \
 //! ```
 use std::ffi::OsString;
 use std::fs::File;
+use std::path::Path;
 use std::process::exit;
 use std::sync::mpsc;
 use std::thread;
@@ -42,7 +43,8 @@ use std::time::Duration;
 
 use anyhow::{Context, Result};
 use clap::Parser;
-use compute_api::responses::ComputeConfig;
+use compute_api::responses::ComputeCtlConfig;
+use compute_api::spec::ComputeSpec;
 use compute_tools::compute::{
     BUILD_TAG, ComputeNode, ComputeNodeParams, forward_termination_signal,
 };
@@ -116,8 +118,8 @@ struct Cli {
     #[arg(long)]
     pub set_disk_quota_for_fs: Option<String>,
 
-    #[arg(short = 'c', long)]
-    pub config: Option<OsString>,
+    #[arg(short = 'S', long, group = "spec-path")]
+    pub spec_path: Option<OsString>,
 
     #[arg(short = 'i', long, group = "compute-id")]
     pub compute_id: String,
@@ -125,9 +127,8 @@ struct Cli {
     #[arg(
         short = 'p',
         long,
-        conflicts_with = "config",
-        value_name = "CONTROL_PLANE_API_BASE_URL",
-        requires = "compute-id"
+        conflicts_with = "spec-path",
+        value_name = "CONTROL_PLANE_API_BASE_URL"
     )]
     pub control_plane_uri: Option<String>,
 }
@@ -137,7 +138,7 @@ fn main() -> Result<()> {
 
     let scenario = failpoint_support::init();
 
-    // For historical reasons, the main thread that processes the config and launches postgres
+    // For historical reasons, the main thread that processes the spec and launches postgres
     // is synchronous, but we always have this tokio runtime available and we "enter" it so
     // that you can use tokio::spawn() and tokio::runtime::Handle::current().block_on(...)
     // from all parts of compute_ctl.
@@ -153,7 +154,7 @@ fn main() -> Result<()> {
 
     let connstr = Url::parse(&cli.connstr).context("cannot parse connstr as a URL")?;
 
-    let config = get_config(&cli)?;
+    let cli_spec = try_spec_from_cli(&cli)?;
 
     let compute_node = ComputeNode::new(
         ComputeNodeParams {
@@ -174,7 +175,8 @@ fn main() -> Result<()> {
             #[cfg(target_os = "linux")]
             vm_monitor_addr: cli.vm_monitor_addr,
         },
-        config,
+        cli_spec.spec,
+        cli_spec.compute_ctl_config,
     )?;
 
     let exit_code = compute_node.run()?;
@@ -199,17 +201,27 @@ async fn init() -> Result<()> {
     Ok(())
 }
 
-fn get_config(cli: &Cli) -> Result<ComputeConfig> {
-    // First, read the config from the path if provided
-    if let Some(ref config) = cli.config {
-        let file = File::open(config)?;
-        return Ok(serde_json::from_reader(&file)?);
+fn try_spec_from_cli(cli: &Cli) -> Result<CliSpecParams> {
+    // First, read spec from the path if provided
+    if let Some(ref spec_path) = cli.spec_path {
+        let file = File::open(Path::new(spec_path))?;
+        return Ok(CliSpecParams {
+            spec: Some(serde_json::from_reader(file)?),
+            compute_ctl_config: ComputeCtlConfig::default(),
+        });
     }
 
-    // If the config wasn't provided in the CLI arguments, then retrieve it from
+    if cli.control_plane_uri.is_none() {
+        panic!("must specify --control-plane-uri");
+    };
+
+    // If the spec wasn't provided in the CLI arguments, then retrieve it from
     // the control plane
-    match get_config_from_control_plane(cli.control_plane_uri.as_ref().unwrap(), &cli.compute_id) {
-        Ok(config) => Ok(config),
+    match get_spec_from_control_plane(cli.control_plane_uri.as_ref().unwrap(), &cli.compute_id) {
+        Ok(resp) => Ok(CliSpecParams {
+            spec: resp.0,
+            compute_ctl_config: resp.1,
+        }),
         Err(e) => {
             error!(
                 "cannot get response from control plane: {}\n\
@@ -221,6 +233,13 @@ fn get_config(cli: &Cli) -> Result<ComputeConfig> {
     }
 }
 
+struct CliSpecParams {
+    /// If a spec was provided via CLI or file, the [`ComputeSpec`]
+    spec: Option<ComputeSpec>,
+    #[allow(dead_code)]
+    compute_ctl_config: ComputeCtlConfig,
+}
+
 fn deinit_and_exit(exit_code: Option<i32>) -> ! {
     // Shutdown trace pipeline gracefully, so that it has a chance to send any
     // pending traces before we exit. Shutting down OTEL tracing provider may

compute_tools/src/compute.rs

@@ -11,7 +11,7 @@ use std::{env, fs};
 use anyhow::{Context, Result};
 use chrono::{DateTime, Utc};
 use compute_api::privilege::Privilege;
-use compute_api::responses::{ComputeConfig, ComputeCtlConfig, ComputeMetrics, ComputeStatus};
+use compute_api::responses::{ComputeCtlConfig, ComputeMetrics, ComputeStatus};
 use compute_api::spec::{
     ComputeAudit, ComputeFeature, ComputeMode, ComputeSpec, ExtVersion, PgIdent,
 };
@@ -303,7 +303,11 @@ struct StartVmMonitorResult {
 }
 
 impl ComputeNode {
-    pub fn new(params: ComputeNodeParams, config: ComputeConfig) -> Result<Self> {
+    pub fn new(
+        params: ComputeNodeParams,
+        cli_spec: Option<ComputeSpec>,
+        compute_ctl_config: ComputeCtlConfig,
+    ) -> Result<Self> {
         let connstr = params.connstr.as_str();
         let conn_conf = postgres::config::Config::from_str(connstr)
             .context("cannot build postgres config from connstr")?;
@@ -311,8 +315,8 @@ impl ComputeNode {
             .context("cannot build tokio postgres config from connstr")?;
 
         let mut new_state = ComputeState::new();
-        if let Some(spec) = config.spec {
-            let pspec = ParsedSpec::try_from(spec).map_err(|msg| anyhow::anyhow!(msg))?;
+        if let Some(cli_spec) = cli_spec {
+            let pspec = ParsedSpec::try_from(cli_spec).map_err(|msg| anyhow::anyhow!(msg))?;
             new_state.pspec = Some(pspec);
         }
 
@@ -323,7 +327,7 @@ impl ComputeNode {
             state: Mutex::new(new_state),
             state_changed: Condvar::new(),
             ext_download_progress: RwLock::new(HashMap::new()),
-            compute_ctl_config: config.compute_ctl_config,
+            compute_ctl_config,
         })
     }
 
@@ -641,26 +645,7 @@ impl ComputeNode {
 
                 let log_directory_path = Path::new(&self.params.pgdata).join("log");
                 let log_directory_path = log_directory_path.to_string_lossy().to_string();
-
-                // Add project_id,endpoint_id tag to identify the logs.
-                //
-                // These ids are passed from cplane,
-                // for backwards compatibility (old computes that don't have them),
-                // we set them to None.
-                // TODO: Clean up this code when all computes have them.
-                let tag: Option<String> = match (
-                    pspec.spec.project_id.as_deref(),
-                    pspec.spec.endpoint_id.as_deref(),
-                ) {
-                    (Some(project_id), Some(endpoint_id)) => {
-                        Some(format!("{project_id}/{endpoint_id}"))
-                    }
-                    (Some(project_id), None) => Some(format!("{project_id}/None")),
-                    (None, Some(endpoint_id)) => Some(format!("None,{endpoint_id}")),
-                    (None, None) => None,
-                };
-
-                configure_audit_rsyslog(log_directory_path.clone(), tag, &remote_endpoint)?;
+                configure_audit_rsyslog(log_directory_path.clone(), "hipaa", &remote_endpoint)?;
 
                 // Launch a background task to clean up the audit logs
                 launch_pgaudit_gc(log_directory_path);

compute_tools/src/http/extract/mod.rs

@@ -6,5 +6,4 @@ pub(crate) mod request_id;
 pub(crate) use json::Json;
 pub(crate) use path::Path;
 pub(crate) use query::Query;
-#[allow(unused)]
 pub(crate) use request_id::RequestId;

compute_tools/src/http/middleware/authorize.rs

@@ -1,7 +1,7 @@
-use std::collections::HashSet;
+use std::{collections::HashSet, net::SocketAddr};
 
 use anyhow::{Result, anyhow};
-use axum::{RequestExt, body::Body};
+use axum::{RequestExt, body::Body, extract::ConnectInfo};
 use axum_extra::{
     TypedHeader,
     headers::{Authorization, authorization::Bearer},
@@ -11,9 +11,9 @@ use futures::future::BoxFuture;
 use http::{Request, Response, StatusCode};
 use jsonwebtoken::{Algorithm, DecodingKey, TokenData, Validation, jwk::JwkSet};
 use tower_http::auth::AsyncAuthorizeRequest;
-use tracing::{debug, warn};
+use tracing::warn;
 
-use crate::http::JsonResponse;
+use crate::http::{JsonResponse, extract::RequestId};
 
 #[derive(Clone, Debug)]
 pub(in crate::http) struct Authorize {
@@ -52,6 +52,31 @@ impl AsyncAuthorizeRequest<Body> for Authorize {
         let validation = self.validation.clone();
 
         Box::pin(async move {
+            let request_id = request.extract_parts::<RequestId>().await.unwrap();
+
+            // TODO: Remove this stanza after teaching neon_local and the
+            // regression tests to use a JWT + JWKS.
+            //
+            // https://github.com/neondatabase/neon/issues/11316
+            if cfg!(feature = "testing") {
+                warn!(%request_id, "Skipping compute_ctl authorization check");
+
+                return Ok(request);
+            }
+
+            let connect_info = request
+                .extract_parts::<ConnectInfo<SocketAddr>>()
+                .await
+                .unwrap();
+
+            // In the event the request is coming from the loopback interface,
+            // allow all requests
+            if connect_info.ip().is_loopback() {
+                warn!(%request_id, "Bypassed authorization because request is coming from the loopback interface");
+
+                return Ok(request);
+            }
+
             let TypedHeader(Authorization(bearer)) = request
                 .extract_parts::<TypedHeader<Authorization<Bearer>>>()
                 .await
@@ -67,7 +92,7 @@ impl AsyncAuthorizeRequest<Body> for Authorize {
             if data.claims.compute_id != compute_id {
                 return Err(JsonResponse::error(
                     StatusCode::UNAUTHORIZED,
-                    "invalid compute ID in authorization token claims",
+                    "invalid claims in authorization token",
                 ));
             }
 
@@ -87,16 +112,12 @@ impl Authorize {
         token: &str,
         validation: &Validation,
     ) -> Result<TokenData<ComputeClaims>> {
-        debug_assert!(!jwks.keys.is_empty());
-
-        debug!("verifying token {}", token);
-
         for jwk in jwks.keys.iter() {
             let decoding_key = match DecodingKey::from_jwk(jwk) {
                 Ok(key) => key,
                 Err(e) => {
                     warn!(
-                        "failed to construct decoding key from {}: {}",
+                        "Failed to construct decoding key from {}: {}",
                         jwk.common.key_id.as_ref().unwrap(),
                         e
                     );
@@ -109,7 +130,7 @@ impl Authorize {
                 Ok(data) => return Ok(data),
                 Err(e) => {
                     warn!(
-                        "failed to decode authorization token using {}: {}",
+                        "Failed to decode authorization token using {}: {}",
                         jwk.common.key_id.as_ref().unwrap(),
                         e
                     );
@@ -119,6 +140,6 @@ impl Authorize {
             }
         }
 
-        Err(anyhow!("failed to verify authorization token"))
+        Err(anyhow!("Failed to verify authorization token"))
     }
 }

compute_tools/src/metrics.rs

@@ -1,8 +1,8 @@
-use metrics::core::{AtomicF64, AtomicU64, Collector, GenericCounter, GenericGauge};
+use metrics::core::{AtomicF64, Collector, GenericGauge};
 use metrics::proto::MetricFamily;
 use metrics::{
-    IntCounterVec, IntGaugeVec, UIntGaugeVec, register_gauge, register_int_counter,
-    register_int_counter_vec, register_int_gauge_vec, register_uint_gauge_vec,
+    IntCounterVec, IntGaugeVec, UIntGaugeVec, register_gauge, register_int_counter_vec,
+    register_int_gauge_vec, register_uint_gauge_vec,
 };
 use once_cell::sync::Lazy;
 
@@ -19,13 +19,13 @@ pub(crate) static INSTALLED_EXTENSIONS: Lazy<UIntGaugeVec> = Lazy::new(|| {
 // but for all our APIs we defined a 'slug'/method/operationId in the OpenAPI spec.
 // And it's fair to call it a 'RPC' (Remote Procedure Call).
 pub enum CPlaneRequestRPC {
-    GetConfig,
+    GetSpec,
 }
 
 impl CPlaneRequestRPC {
     pub fn as_str(&self) -> &str {
         match self {
-            CPlaneRequestRPC::GetConfig => "GetConfig",
+            CPlaneRequestRPC::GetSpec => "GetSpec",
         }
     }
 }
@@ -81,22 +81,6 @@ pub(crate) static COMPUTE_CTL_UP: Lazy<IntGaugeVec> = Lazy::new(|| {
     .expect("failed to define a metric")
 });
 
-pub(crate) static PG_CURR_DOWNTIME_MS: Lazy<GenericGauge<AtomicF64>> = Lazy::new(|| {
-    register_gauge!(
-        "compute_pg_current_downtime_ms",
-        "Non-cumulative duration of Postgres downtime in ms; resets after successful check",
-    )
-    .expect("failed to define a metric")
-});
-
-pub(crate) static PG_TOTAL_DOWNTIME_MS: Lazy<GenericCounter<AtomicU64>> = Lazy::new(|| {
-    register_int_counter!(
-        "compute_pg_downtime_ms_total",
-        "Cumulative duration of Postgres downtime in ms",
-    )
-    .expect("failed to define a metric")
-});
-
 pub fn collect() -> Vec<MetricFamily> {
     let mut metrics = COMPUTE_CTL_UP.collect();
     metrics.extend(INSTALLED_EXTENSIONS.collect());
@@ -104,7 +88,5 @@ pub fn collect() -> Vec<MetricFamily> {
     metrics.extend(REMOTE_EXT_REQUESTS_TOTAL.collect());
     metrics.extend(DB_MIGRATION_FAILED.collect());
     metrics.extend(AUDIT_LOG_DIR_SIZE.collect());
-    metrics.extend(PG_CURR_DOWNTIME_MS.collect());
-    metrics.extend(PG_TOTAL_DOWNTIME_MS.collect());
     metrics
 }

compute_tools/src/monitor.rs

@@ -6,294 +6,197 @@ use chrono::{DateTime, Utc};
 use compute_api::responses::ComputeStatus;
 use compute_api::spec::ComputeFeature;
 use postgres::{Client, NoTls};
-use tracing::{Level, error, info, instrument, span};
+use tracing::{debug, error, info, warn};
 
 use crate::compute::ComputeNode;
-use crate::metrics::{PG_CURR_DOWNTIME_MS, PG_TOTAL_DOWNTIME_MS};
 
 const MONITOR_CHECK_INTERVAL: Duration = Duration::from_millis(500);
 
-struct ComputeMonitor {
-    compute: Arc<ComputeNode>,
+// Spin in a loop and figure out the last activity time in the Postgres.
+// Then update it in the shared state. This function never errors out.
+// NB: the only expected panic is at `Mutex` unwrap(), all other errors
+// should be handled gracefully.
+fn watch_compute_activity(compute: &ComputeNode) {
+    // Suppose that `connstr` doesn't change
+    let connstr = compute.params.connstr.clone();
+    let conf = compute.get_conn_conf(Some("compute_ctl:activity_monitor"));
 
-    /// The moment when Postgres had some activity,
-    /// that should prevent compute from being suspended.
-    last_active: Option<DateTime<Utc>>,
+    // During startup and configuration we connect to every Postgres database,
+    // but we don't want to count this as some user activity. So wait until
+    // the compute fully started before monitoring activity.
+    wait_for_postgres_start(compute);
 
-    /// The moment when we last tried to check Postgres.
-    last_checked: DateTime<Utc>,
-    /// The last moment we did a successful Postgres check.
-    last_up: DateTime<Utc>,
+    // Define `client` outside of the loop to reuse existing connection if it's active.
+    let mut client = conf.connect(NoTls);
 
-    /// Only used for internal statistics change tracking
-    /// between monitor runs and can be outdated.
-    active_time: Option<f64>,
-    /// Only used for internal statistics change tracking
-    /// between monitor runs and can be outdated.
-    sessions: Option<i64>,
+    let mut sleep = false;
+    let mut prev_active_time: Option<f64> = None;
+    let mut prev_sessions: Option<i64> = None;
 
-    /// Use experimental statistics-based activity monitor. It's no longer
-    /// 'experimental' per se, as it's enabled for everyone, but we still
-    /// keep the flag as an option to turn it off in some cases if it will
-    /// misbehave.
-    experimental: bool,
-}
-
-impl ComputeMonitor {
-    fn report_down(&self) {
-        let now = Utc::now();
-
-        // Calculate and report current downtime
-        // (since the last time Postgres was up)
-        let downtime = now.signed_duration_since(self.last_up);
-        PG_CURR_DOWNTIME_MS.set(downtime.num_milliseconds() as f64);
-
-        // Calculate and update total downtime
-        // (cumulative duration of Postgres downtime in ms)
-        let inc = now
-            .signed_duration_since(self.last_checked)
-            .num_milliseconds();
-        PG_TOTAL_DOWNTIME_MS.inc_by(inc as u64);
+    if compute.has_feature(ComputeFeature::ActivityMonitorExperimental) {
+        info!("starting experimental activity monitor for {}", connstr);
+    } else {
+        info!("starting activity monitor for {}", connstr);
     }
 
-    fn report_up(&mut self) {
-        self.last_up = Utc::now();
-        PG_CURR_DOWNTIME_MS.set(0.0);
-    }
-
-    fn downtime_info(&self) -> String {
-        format!(
-            "total_ms: {}, current_ms: {}, last_up: {}",
-            PG_TOTAL_DOWNTIME_MS.get(),
-            PG_CURR_DOWNTIME_MS.get(),
-            self.last_up
-        )
-    }
-
-    /// Spin in a loop and figure out the last activity time in the Postgres.
-    /// Then update it in the shared state. This function never errors out.
-    /// NB: the only expected panic is at `Mutex` unwrap(), all other errors
-    /// should be handled gracefully.
-    #[instrument(skip_all)]
-    pub fn run(&mut self) {
-        // Suppose that `connstr` doesn't change
-        let connstr = self.compute.params.connstr.clone();
-        let conf = self
-            .compute
-            .get_conn_conf(Some("compute_ctl:compute_monitor"));
-
-        // During startup and configuration we connect to every Postgres database,
-        // but we don't want to count this as some user activity. So wait until
-        // the compute fully started before monitoring activity.
-        wait_for_postgres_start(&self.compute);
-
-        // Define `client` outside of the loop to reuse existing connection if it's active.
-        let mut client = conf.connect(NoTls);
-
-        info!("starting compute monitor for {}", connstr);
-
-        loop {
-            match &mut client {
-                Ok(cli) => {
-                    if cli.is_closed() {
-                        info!(
-                            downtime_info = self.downtime_info(),
-                            "connection to Postgres is closed, trying to reconnect"
-                        );
-                        self.report_down();
-
-                        // Connection is closed, reconnect and try again.
-                        client = conf.connect(NoTls);
-                    } else {
-                        match self.check(cli) {
-                            Ok(_) => {
-                                self.report_up();
-                                self.compute.update_last_active(self.last_active);
-                            }
-                            Err(e) => {
-                                // Although we have many places where we can return errors in `check()`,
-                                // normally it shouldn't happen. I.e., we will likely return error if
-                                // connection got broken, query timed out, Postgres returned invalid data, etc.
-                                // In all such cases it's suspicious, so let's report this as downtime.
-                                self.report_down();
-                                error!(
-                                    downtime_info = self.downtime_info(),
-                                    "could not check Postgres: {}", e
-                                );
-
-                                // Reconnect to Postgres just in case. During tests, I noticed
-                                // that queries in `check()` can fail with `connection closed`,
-                                // but `cli.is_closed()` above doesn't detect it. Even if old
-                                // connection is still alive, it will be dropped when we reassign
-                                // `client` to a new connection.
-                                client = conf.connect(NoTls);
-                            }
-                        }
-                    }
-                }
-                Err(e) => {
-                    info!(
-                        downtime_info = self.downtime_info(),
-                        "could not connect to Postgres: {}, retrying", e
-                    );
-                    self.report_down();
-
-                    // Establish a new connection and try again.
-                    client = conf.connect(NoTls);
-                }
-            }
-
-            // Reset the `last_checked` timestamp and sleep before the next iteration.
-            self.last_checked = Utc::now();
+    loop {
+        // We use `continue` a lot, so it's more convenient to sleep at the top of the loop.
+        // But skip the first sleep, so we can connect to Postgres immediately.
+        if sleep {
+            // Should be outside of the mutex lock to allow others to read while we sleep.
             thread::sleep(MONITOR_CHECK_INTERVAL);
+        } else {
+            sleep = true;
         }
-    }
 
-    #[instrument(skip_all)]
-    fn check(&mut self, cli: &mut Client) -> anyhow::Result<()> {
-        // This is new logic, only enable if the feature flag is set.
-        // TODO: remove this once we are sure that it works OR drop it altogether.
-        if self.experimental {
-            // Check if the total active time or sessions across all databases has changed.
-            // If it did, it means that user executed some queries. In theory, it can even go down if
-            // some databases were dropped, but it's still user activity.
-            match get_database_stats(cli) {
-                Ok((active_time, sessions)) => {
-                    let mut detected_activity = false;
+        match &mut client {
+            Ok(cli) => {
+                if cli.is_closed() {
+                    info!("connection to Postgres is closed, trying to reconnect");
 
-                    if let Some(prev_active_time) = self.active_time {
-                        if active_time != prev_active_time {
-                            detected_activity = true;
+                    // Connection is closed, reconnect and try again.
+                    client = conf.connect(NoTls);
+                    continue;
+                }
+
+                // This is a new logic, only enable if the feature flag is set.
+                // TODO: remove this once we are sure that it works OR drop it altogether.
+                if compute.has_feature(ComputeFeature::ActivityMonitorExperimental) {
+                    // First, check if the total active time or sessions across all databases has changed.
+                    // If it did, it means that user executed some queries. In theory, it can even go down if
+                    // some databases were dropped, but it's still a user activity.
+                    match get_database_stats(cli) {
+                        Ok((active_time, sessions)) => {
+                            let mut detected_activity = false;
+
+                            prev_active_time = match prev_active_time {
+                                Some(prev_active_time) => {
+                                    if active_time != prev_active_time {
+                                        detected_activity = true;
+                                    }
+                                    Some(active_time)
+                                }
+                                None => Some(active_time),
+                            };
+                            prev_sessions = match prev_sessions {
+                                Some(prev_sessions) => {
+                                    if sessions != prev_sessions {
+                                        detected_activity = true;
+                                    }
+                                    Some(sessions)
+                                }
+                                None => Some(sessions),
+                            };
+
+                            if detected_activity {
+                                // Update the last active time and continue, we don't need to
+                                // check backends state change.
+                                compute.update_last_active(Some(Utc::now()));
+                                continue;
+                            }
+                        }
+                        Err(e) => {
+                            error!("could not get database statistics: {}", e);
+                            continue;
                         }
                     }
-                    self.active_time = Some(active_time);
+                }
 
-                    if let Some(prev_sessions) = self.sessions {
-                        if sessions != prev_sessions {
-                            detected_activity = true;
+                // Second, if database statistics is the same, check all backends state change,
+                // maybe there is some with more recent activity. `get_backends_state_change()`
+                // can return None or stale timestamp, so it's `compute.update_last_active()`
+                // responsibility to check if the new timestamp is more recent than the current one.
+                // This helps us to discover new sessions, that did nothing yet.
+                match get_backends_state_change(cli) {
+                    Ok(last_active) => {
+                        compute.update_last_active(last_active);
+                    }
+                    Err(e) => {
+                        error!("could not get backends state change: {}", e);
+                    }
+                }
+
+                // Finally, if there are existing (logical) walsenders, do not suspend.
+                //
+                // walproposer doesn't currently show up in pg_stat_replication,
+                // but protect if it will be
+                let ws_count_query = "select count(*) from pg_stat_replication where application_name != 'walproposer';";
+                match cli.query_one(ws_count_query, &[]) {
+                    Ok(r) => match r.try_get::<&str, i64>("count") {
+                        Ok(num_ws) => {
+                            if num_ws > 0 {
+                                compute.update_last_active(Some(Utc::now()));
+                                continue;
+                            }
                         }
-                    }
-                    self.sessions = Some(sessions);
-
-                    if detected_activity {
-                        // Update the last active time and continue, we don't need to
-                        // check backends state change.
-                        self.last_active = Some(Utc::now());
-                        return Ok(());
+                        Err(e) => {
+                            warn!("failed to parse walsenders count: {:?}", e);
+                            continue;
+                        }
+                    },
+                    Err(e) => {
+                        warn!("failed to get list of walsenders: {:?}", e);
+                        continue;
                     }
                 }
-                Err(e) => {
-                    return Err(anyhow::anyhow!("could not get database statistics: {}", e));
+                //
+                // Don't suspend compute if there is an active logical replication subscription
+                //
+                // `where pid is not null` – to filter out read only computes and subscription on branches
+                //
+                let logical_subscriptions_query =
+                    "select count(*) from pg_stat_subscription where pid is not null;";
+                match cli.query_one(logical_subscriptions_query, &[]) {
+                    Ok(row) => match row.try_get::<&str, i64>("count") {
+                        Ok(num_subscribers) => {
+                            if num_subscribers > 0 {
+                                compute.update_last_active(Some(Utc::now()));
+                                continue;
+                            }
+                        }
+                        Err(e) => {
+                            warn!("failed to parse `pg_stat_subscription` count: {:?}", e);
+                            continue;
+                        }
+                    },
+                    Err(e) => {
+                        warn!(
+                            "failed to get list of active logical replication subscriptions: {:?}",
+                            e
+                        );
+                        continue;
+                    }
+                }
+                //
+                // Do not suspend compute if autovacuum is running
+                //
+                let autovacuum_count_query = "select count(*) from pg_stat_activity where backend_type = 'autovacuum worker'";
+                match cli.query_one(autovacuum_count_query, &[]) {
+                    Ok(r) => match r.try_get::<&str, i64>("count") {
+                        Ok(num_workers) => {
+                            if num_workers > 0 {
+                                compute.update_last_active(Some(Utc::now()));
+                                continue;
+                            }
+                        }
+                        Err(e) => {
+                            warn!("failed to parse autovacuum workers count: {:?}", e);
+                            continue;
+                        }
+                    },
+                    Err(e) => {
+                        warn!("failed to get list of autovacuum workers: {:?}", e);
+                        continue;
+                    }
                 }
             }
-        }
-
-        // If database statistics are the same, check all backends for state changes.
-        // Maybe there are some with more recent activity. `get_backends_state_change()`
-        // can return None or stale timestamp, so it's `compute.update_last_active()`
-        // responsibility to check if the new timestamp is more recent than the current one.
-        // This helps us to discover new sessions that have not done anything yet.
-        match get_backends_state_change(cli) {
-            Ok(last_active) => match (last_active, self.last_active) {
-                (Some(last_active), Some(prev_last_active)) => {
-                    if last_active > prev_last_active {
-                        self.last_active = Some(last_active);
-                        return Ok(());
-                    }
-                }
-                (Some(last_active), None) => {
-                    self.last_active = Some(last_active);
-                    return Ok(());
-                }
-                _ => {}
-            },
             Err(e) => {
-                return Err(anyhow::anyhow!(
-                    "could not get backends state change: {}",
-                    e
-                ));
+                debug!("could not connect to Postgres: {}, retrying", e);
+
+                // Establish a new connection and try again.
+                client = conf.connect(NoTls);
             }
         }
-
-        // If there are existing (logical) walsenders, do not suspend.
-        //
-        // N.B. walproposer doesn't currently show up in pg_stat_replication,
-        // but protect if it will.
-        const WS_COUNT_QUERY: &str =
-            "select count(*) from pg_stat_replication where application_name != 'walproposer';";
-        match cli.query_one(WS_COUNT_QUERY, &[]) {
-            Ok(r) => match r.try_get::<&str, i64>("count") {
-                Ok(num_ws) => {
-                    if num_ws > 0 {
-                        self.last_active = Some(Utc::now());
-                        return Ok(());
-                    }
-                }
-                Err(e) => {
-                    let err: anyhow::Error = e.into();
-                    return Err(err.context("failed to parse walsenders count"));
-                }
-            },
-            Err(e) => {
-                return Err(anyhow::anyhow!("failed to get list of walsenders: {}", e));
-            }
-        }
-
-        // Don't suspend compute if there is an active logical replication subscription
-        //
-        // `where pid is not null` – to filter out read only computes and subscription on branches
-        const LOGICAL_SUBSCRIPTIONS_QUERY: &str =
-            "select count(*) from pg_stat_subscription where pid is not null;";
-        match cli.query_one(LOGICAL_SUBSCRIPTIONS_QUERY, &[]) {
-            Ok(row) => match row.try_get::<&str, i64>("count") {
-                Ok(num_subscribers) => {
-                    if num_subscribers > 0 {
-                        self.last_active = Some(Utc::now());
-                        return Ok(());
-                    }
-                }
-                Err(e) => {
-                    return Err(anyhow::anyhow!(
-                        "failed to parse 'pg_stat_subscription' count: {}",
-                        e
-                    ));
-                }
-            },
-            Err(e) => {
-                return Err(anyhow::anyhow!(
-                    "failed to get list of active logical replication subscriptions: {}",
-                    e
-                ));
-            }
-        }
-
-        // Do not suspend compute if autovacuum is running
-        const AUTOVACUUM_COUNT_QUERY: &str =
-            "select count(*) from pg_stat_activity where backend_type = 'autovacuum worker'";
-        match cli.query_one(AUTOVACUUM_COUNT_QUERY, &[]) {
-            Ok(r) => match r.try_get::<&str, i64>("count") {
-                Ok(num_workers) => {
-                    if num_workers > 0 {
-                        self.last_active = Some(Utc::now());
-                        return Ok(());
-                    };
-                }
-                Err(e) => {
-                    return Err(anyhow::anyhow!(
-                        "failed to parse autovacuum workers count: {}",
-                        e
-                    ));
-                }
-            },
-            Err(e) => {
-                return Err(anyhow::anyhow!(
-                    "failed to get list of autovacuum workers: {}",
-                    e
-                ));
-            }
-        }
-
-        Ok(())
     }
 }
 
@@ -412,24 +315,9 @@ fn get_backends_state_change(cli: &mut Client) -> anyhow::Result<Option<DateTime
 /// Launch a separate compute monitor thread and return its `JoinHandle`.
 pub fn launch_monitor(compute: &Arc<ComputeNode>) -> thread::JoinHandle<()> {
     let compute = Arc::clone(compute);
-    let experimental = compute.has_feature(ComputeFeature::ActivityMonitorExperimental);
-    let now = Utc::now();
-    let mut monitor = ComputeMonitor {
-        compute,
-        last_active: None,
-        last_checked: now,
-        last_up: now,
-        active_time: None,
-        sessions: None,
-        experimental,
-    };
 
-    let span = span!(Level::INFO, "compute_monitor");
     thread::Builder::new()
         .name("compute-monitor".into())
-        .spawn(move || {
-            let _enter = span.enter();
-            monitor.run();
-        })
+        .spawn(move || watch_compute_activity(&compute))
         .expect("cannot launch compute monitor thread")
 }

compute_tools/src/rsyslog.rs

@@ -50,13 +50,13 @@ fn restart_rsyslog() -> Result<()> {
 
 pub fn configure_audit_rsyslog(
     log_directory: String,
-    tag: Option<String>,
+    tag: &str,
     remote_endpoint: &str,
 ) -> Result<()> {
     let config_content: String = format!(
         include_str!("config_template/compute_audit_rsyslog_template.conf"),
         log_directory = log_directory,
-        tag = tag.unwrap_or("".to_string()),
+        tag = tag,
         remote_endpoint = remote_endpoint
     );
 

compute_tools/src/spec.rs

@@ -3,8 +3,9 @@ use std::path::Path;
 
 use anyhow::{Result, anyhow, bail};
 use compute_api::responses::{
-    ComputeConfig, ControlPlaneComputeStatus, ControlPlaneConfigResponse,
+    ComputeCtlConfig, ControlPlaneComputeStatus, ControlPlaneSpecResponse,
 };
+use compute_api::spec::ComputeSpec;
 use reqwest::StatusCode;
 use tokio_postgres::Client;
 use tracing::{error, info, instrument};
@@ -20,7 +21,7 @@ use crate::params::PG_HBA_ALL_MD5;
 fn do_control_plane_request(
     uri: &str,
     jwt: &str,
-) -> Result<ControlPlaneConfigResponse, (bool, String, String)> {
+) -> Result<ControlPlaneSpecResponse, (bool, String, String)> {
     let resp = reqwest::blocking::Client::new()
         .get(uri)
         .header("Authorization", format!("Bearer {}", jwt))
@@ -28,14 +29,14 @@ fn do_control_plane_request(
         .map_err(|e| {
             (
                 true,
-                format!("could not perform request to control plane: {:?}", e),
+                format!("could not perform spec request to control plane: {:?}", e),
                 UNKNOWN_HTTP_STATUS.to_string(),
             )
         })?;
 
     let status = resp.status();
     match status {
-        StatusCode::OK => match resp.json::<ControlPlaneConfigResponse>() {
+        StatusCode::OK => match resp.json::<ControlPlaneSpecResponse>() {
             Ok(spec_resp) => Ok(spec_resp),
             Err(e) => Err((
                 true,
@@ -68,35 +69,40 @@ fn do_control_plane_request(
     }
 }
 
-/// Request config from the control-plane by compute_id. If
-/// `NEON_CONTROL_PLANE_TOKEN` env variable is set, it will be used for
-/// authorization.
-pub fn get_config_from_control_plane(base_uri: &str, compute_id: &str) -> Result<ComputeConfig> {
+/// Request spec from the control-plane by compute_id. If `NEON_CONTROL_PLANE_TOKEN`
+/// env variable is set, it will be used for authorization.
+pub fn get_spec_from_control_plane(
+    base_uri: &str,
+    compute_id: &str,
+) -> Result<(Option<ComputeSpec>, ComputeCtlConfig)> {
     let cp_uri = format!("{base_uri}/compute/api/v2/computes/{compute_id}/spec");
-    let jwt: String = std::env::var("NEON_CONTROL_PLANE_TOKEN").unwrap_or_default();
+    let jwt: String = match std::env::var("NEON_CONTROL_PLANE_TOKEN") {
+        Ok(v) => v,
+        Err(_) => "".to_string(),
+    };
     let mut attempt = 1;
 
-    info!("getting config from control plane: {}", cp_uri);
+    info!("getting spec from control plane: {}", cp_uri);
 
     // Do 3 attempts to get spec from the control plane using the following logic:
     // - network error -> then retry
     // - compute id is unknown or any other error -> bail out
     // - no spec for compute yet (Empty state) -> return Ok(None)
-    // - got config -> return Ok(Some(config))
+    // - got spec -> return Ok(Some(spec))
     while attempt < 4 {
         let result = match do_control_plane_request(&cp_uri, &jwt) {
-            Ok(config_resp) => {
+            Ok(spec_resp) => {
                 CPLANE_REQUESTS_TOTAL
                     .with_label_values(&[
-                        CPlaneRequestRPC::GetConfig.as_str(),
+                        CPlaneRequestRPC::GetSpec.as_str(),
                         &StatusCode::OK.to_string(),
                     ])
                     .inc();
-                match config_resp.status {
-                    ControlPlaneComputeStatus::Empty => Ok(config_resp.into()),
+                match spec_resp.status {
+                    ControlPlaneComputeStatus::Empty => Ok((None, spec_resp.compute_ctl_config)),
                     ControlPlaneComputeStatus::Attached => {
-                        if config_resp.spec.is_some() {
-                            Ok(config_resp.into())
+                        if let Some(spec) = spec_resp.spec {
+                            Ok((Some(spec), spec_resp.compute_ctl_config))
                         } else {
                             bail!("compute is attached, but spec is empty")
                         }
@@ -105,7 +111,7 @@ pub fn get_config_from_control_plane(base_uri: &str, compute_id: &str) -> Result
             }
             Err((retry, msg, status)) => {
                 CPLANE_REQUESTS_TOTAL
-                    .with_label_values(&[CPlaneRequestRPC::GetConfig.as_str(), &status])
+                    .with_label_values(&[CPlaneRequestRPC::GetSpec.as_str(), &status])
                     .inc();
                 if retry {
                     Err(anyhow!(msg))
@@ -116,7 +122,7 @@ pub fn get_config_from_control_plane(base_uri: &str, compute_id: &str) -> Result
         };
 
         if let Err(e) = &result {
-            error!("attempt {} to get config failed with: {}", attempt, e);
+            error!("attempt {} to get spec failed with: {}", attempt, e);
         } else {
             return result;
         }
@@ -127,13 +133,13 @@ pub fn get_config_from_control_plane(base_uri: &str, compute_id: &str) -> Result
 
     // All attempts failed, return error.
     Err(anyhow::anyhow!(
-        "Exhausted all attempts to retrieve the config from the control plane"
+        "Exhausted all attempts to retrieve the spec from the control plane"
     ))
 }
 
 /// Check `pg_hba.conf` and update if needed to allow external connections.
 pub fn update_pg_hba(pgdata_path: &Path) -> Result<()> {
-    // XXX: consider making it a part of config.json
+    // XXX: consider making it a part of spec.json
     let pghba_path = pgdata_path.join("pg_hba.conf");
 
     if config::line_in_file(&pghba_path, PG_HBA_ALL_MD5)? {
@@ -147,7 +153,7 @@ pub fn update_pg_hba(pgdata_path: &Path) -> Result<()> {
 
 /// Create a standby.signal file
 pub fn add_standby_signal(pgdata_path: &Path) -> Result<()> {
-    // XXX: consider making it a part of config.json
+    // XXX: consider making it a part of spec.json
     let signalfile = pgdata_path.join("standby.signal");
 
     if !signalfile.exists() {

compute_tools/src/tls.rs

@@ -3,6 +3,7 @@ use std::{io::Write, os::unix::fs::OpenOptionsExt, path::Path, time::Duration};
 use anyhow::{Context, Result, bail};
 use compute_api::responses::TlsConfig;
 use ring::digest;
+use spki::der::{Decode, PemReader};
 use x509_cert::Certificate;
 
 #[derive(Clone, Copy)]
@@ -51,7 +52,7 @@ pub fn update_key_path_blocking(pg_data: &Path, tls_config: &TlsConfig) {
         match try_update_key_path_blocking(pg_data, tls_config) {
             Ok(()) => break,
             Err(e) => {
-                tracing::error!(error = ?e, "could not create key file");
+                tracing::error!("could not create key file {e:?}");
                 std::thread::sleep(Duration::from_secs(1))
             }
         }
@@ -91,14 +92,8 @@ fn try_update_key_path_blocking(pg_data: &Path, tls_config: &TlsConfig) -> Resul
 fn verify_key_cert(key: &str, cert: &str) -> Result<()> {
     use x509_cert::der::oid::db::rfc5912::ECDSA_WITH_SHA_256;
 
-    let certs = Certificate::load_pem_chain(cert.as_bytes())
-        .context("decoding PEM encoded certificates")?;
-
-    // First certificate is our server-cert,
-    // all the rest of the certs are the CA cert chain.
-    let Some(cert) = certs.first() else {
-        bail!("no certificates found");
-    };
+    let cert = Certificate::decode(&mut PemReader::new(cert.as_bytes()).context("pem reader")?)
+        .context("decode cert")?;
 
     match cert.signature_algorithm.oid {
         ECDSA_WITH_SHA_256 => {
@@ -120,82 +115,3 @@ fn verify_key_cert(key: &str, cert: &str) -> Result<()> {
 
     Ok(())
 }
-
-#[cfg(test)]
-mod tests {
-    use super::verify_key_cert;
-
-    /// Real certificate chain file, generated by cert-manager in dev.
-    /// The server auth certificate has expired since 2025-04-24T15:41:35Z.
-    const CERT: &str = "
------BEGIN CERTIFICATE-----
-MIICCDCCAa+gAwIBAgIQKhLomFcNULbZA/bPdGzaSzAKBggqhkjOPQQDAjBEMQsw
-CQYDVQQGEwJVUzESMBAGA1UEChMJTmVvbiBJbmMuMSEwHwYDVQQDExhOZW9uIEs4
-cyBJbnRlcm1lZGlhdGUgQ0EwHhcNMjUwNDIzMTU0MTM1WhcNMjUwNDI0MTU0MTM1
-WjBBMT8wPQYDVQQDEzZjb21wdXRlLXdpc3B5LWdyYXNzLXcwY21laWp3LmRlZmF1
-bHQuc3ZjLmNsdXN0ZXIubG9jYWwwWTATBgcqhkjOPQIBBggqhkjOPQMBBwNCAATF
-QCcG2m/EVHAiZtSsYgVnHgoTjUL/Jtwfdrpvz2t0bVRZmBmSKhlo53uPV9Y5eKFG
-AmR54p9/gT2eO3xU7vAgo4GFMIGCMA4GA1UdDwEB/wQEAwIFoDAMBgNVHRMBAf8E
-AjAAMB8GA1UdIwQYMBaAFFR2JAhXkeiNQNEixTvAYIwxUu3QMEEGA1UdEQQ6MDiC
-NmNvbXB1dGUtd2lzcHktZ3Jhc3MtdzBjbWVpancuZGVmYXVsdC5zdmMuY2x1c3Rl
-ci5sb2NhbDAKBggqhkjOPQQDAgNHADBEAiBLG22wKG8XS9e9RxBT+kmUx/kIThcP
-DIpp7jx0PrFcdQIgEMTdnXpx5Cv/Z0NIEDxtMHUD7G0vuRPfztki36JuakM=
------END CERTIFICATE-----
------BEGIN CERTIFICATE-----
-MIICFzCCAb6gAwIBAgIUbbX98N2Ip6lWAONRk8dU9hSz+YIwCgYIKoZIzj0EAwIw
-RDELMAkGA1UEBhMCVVMxEjAQBgNVBAoTCU5lb24gSW5jLjEhMB8GA1UEAxMYTmVv
-biBBV1MgSW50ZXJtZWRpYXRlIENBMB4XDTI1MDQyMjE1MTAxMFoXDTI1MDcyMTE1
-MTAxMFowRDELMAkGA1UEBhMCVVMxEjAQBgNVBAoTCU5lb24gSW5jLjEhMB8GA1UE
-AxMYTmVvbiBLOHMgSW50ZXJtZWRpYXRlIENBMFkwEwYHKoZIzj0CAQYIKoZIzj0D
-AQcDQgAE5++m5owqNI4BPMTVNIUQH0qvU7pYhdpHGVGhdj/Lgars6ROvE6uSNQV4
-SAmJN5HBzj5/6kLQaTPWpXW7EHXjK6OBjTCBijAOBgNVHQ8BAf8EBAMCAQYwEgYD
-VR0TAQH/BAgwBgEB/wIBADAdBgNVHQ4EFgQUVHYkCFeR6I1A0SLFO8BgjDFS7dAw
-HwYDVR0jBBgwFoAUgHfNXfyKtHO0V9qoLOWCjkNiaI8wJAYDVR0eAQH/BBowGKAW
-MBSCEi5zdmMuY2x1c3Rlci5sb2NhbDAKBggqhkjOPQQDAgNHADBEAiBObVFFdXaL
-QpOXmN60dYUNnQRwjKreFduEkQgOdOlssgIgVAdJJQFgvlrvEOBhY8j5WyeKRwUN
-k/ALs6KpgaFBCGY=
------END CERTIFICATE-----
------BEGIN CERTIFICATE-----
-MIIB4jCCAYegAwIBAgIUFlxWFn/11yoGdmD+6gf+yQMToS0wCgYIKoZIzj0EAwIw
-ODELMAkGA1UEBhMCVVMxEjAQBgNVBAoTCU5lb24gSW5jLjEVMBMGA1UEAxMMTmVv
-biBSb290IENBMB4XDTI1MDQwMzA3MTUyMloXDTI2MDQwMzA3MTUyMlowRDELMAkG
-A1UEBhMCVVMxEjAQBgNVBAoTCU5lb24gSW5jLjEhMB8GA1UEAxMYTmVvbiBBV1Mg
-SW50ZXJtZWRpYXRlIENBMFkwEwYHKoZIzj0CAQYIKoZIzj0DAQcDQgAEqonG/IQ6
-ZxtEtOUTkkoNopPieXDO5CBKUkNFTGeJEB7OxRlSpYJgsBpaYIaD6Vc4sVk3thIF
-p+pLw52idQOIN6NjMGEwDgYDVR0PAQH/BAQDAgEGMA8GA1UdEwEB/wQFMAMBAf8w
-HQYDVR0OBBYEFIB3zV38irRztFfaqCzlgo5DYmiPMB8GA1UdIwQYMBaAFKh7M4/G
-FHvr/ORDQZt4bMLlJvHCMAoGCCqGSM49BAMCA0kAMEYCIQCbS4x7QPslONzBYbjC
-UQaQ0QLDW4CJHvQ4u4gbWFG87wIhAJMsHQHjP9qTT27Q65zQCR7O8QeLAfha1jrH
-Ag/LsxSr
------END CERTIFICATE-----
-";
-
-    /// The key corresponding to [`CERT`]
-    const KEY: &str = "
------BEGIN EC PRIVATE KEY-----
-MHcCAQEEIDnAnrqmIJjndCLWP1iIO5X3X63Aia48TGpGuMXwvm6IoAoGCCqGSM49
-AwEHoUQDQgAExUAnBtpvxFRwImbUrGIFZx4KE41C/ybcH3a6b89rdG1UWZgZkioZ
-aOd7j1fWOXihRgJkeeKff4E9njt8VO7wIA==
------END EC PRIVATE KEY-----
-";
-
-    /// An incorrect key.
-    const INCORRECT_KEY: &str = "
------BEGIN EC PRIVATE KEY-----
-MHcCAQEEIL6WqqBDyvM0HWz7Ir5M5+jhFWB7IzOClGn26OPrzHCXoAoGCCqGSM49
-AwEHoUQDQgAE7XVvdOy5lfwtNKb+gJEUtnG+DrnnXLY5LsHDeGQKV9PTRcEMeCrG
-YZzHyML4P6Sr4yi2ts+4B9i47uvAG8+XwQ==
------END EC PRIVATE KEY-----
-";
-
-    #[test]
-    fn certificate_verification() {
-        verify_key_cert(KEY, CERT).unwrap();
-    }
-
-    #[test]
-    #[should_panic(expected = "private key file does not match certificate")]
-    fn certificate_verification_fail() {
-        verify_key_cert(INCORRECT_KEY, CERT).unwrap();
-    }
-}

control_plane/Cargo.toml

@@ -6,16 +6,13 @@ license.workspace = true
 
 [dependencies]
 anyhow.workspace = true
-base64.workspace = true
 camino.workspace = true
 clap.workspace = true
 comfy-table.workspace = true
 futures.workspace = true
 humantime.workspace = true
-jsonwebtoken.workspace = true
 nix.workspace = true
 once_cell.workspace = true
-pem.workspace = true
 humantime-serde.workspace = true
 hyper0.workspace = true
 regex.workspace = true
@@ -23,8 +20,6 @@ reqwest = { workspace = true, features = ["blocking", "json"] }
 scopeguard.workspace = true
 serde.workspace = true
 serde_json.workspace = true
-sha2.workspace = true
-spki.workspace = true
 thiserror.workspace = true
 toml.workspace = true
 toml_edit.workspace = true

control_plane/src/bin/neon_local.rs

@@ -18,11 +18,12 @@ use anyhow::{Context, Result, anyhow, bail};
 use clap::Parser;
 use compute_api::spec::ComputeMode;
 use control_plane::endpoint::ComputeControlPlane;
-use control_plane::endpoint_storage::{ENDPOINT_STORAGE_DEFAULT_PORT, EndpointStorage};
 use control_plane::local_env::{
-    EndpointStorageConf, InitForceMode, LocalEnv, NeonBroker, NeonLocalInitConf,
-    NeonLocalInitPageserverConf, SafekeeperConf,
+    InitForceMode, LocalEnv, NeonBroker, NeonLocalInitConf, NeonLocalInitPageserverConf,
+    ObjectStorageConf, SafekeeperConf,
 };
+use control_plane::object_storage::OBJECT_STORAGE_DEFAULT_PORT;
+use control_plane::object_storage::ObjectStorage;
 use control_plane::pageserver::PageServerNode;
 use control_plane::safekeeper::SafekeeperNode;
 use control_plane::storage_controller::{
@@ -62,7 +63,7 @@ const DEFAULT_PAGESERVER_ID: NodeId = NodeId(1);
 const DEFAULT_BRANCH_NAME: &str = "main";
 project_git_version!(GIT_VERSION);
 
-const DEFAULT_PG_VERSION: u32 = 17;
+const DEFAULT_PG_VERSION: u32 = 16;
 
 const DEFAULT_PAGESERVER_CONTROL_PLANE_API: &str = "http://127.0.0.1:1234/upcall/v1/";
 
@@ -92,7 +93,7 @@ enum NeonLocalCmd {
     #[command(subcommand)]
     Safekeeper(SafekeeperCmd),
     #[command(subcommand)]
-    EndpointStorage(EndpointStorageCmd),
+    ObjectStorage(ObjectStorageCmd),
     #[command(subcommand)]
     Endpoint(EndpointCmd),
     #[command(subcommand)]
@@ -459,14 +460,14 @@ enum SafekeeperCmd {
 
 #[derive(clap::Subcommand)]
 #[clap(about = "Manage object storage")]
-enum EndpointStorageCmd {
-    Start(EndpointStorageStartCmd),
-    Stop(EndpointStorageStopCmd),
+enum ObjectStorageCmd {
+    Start(ObjectStorageStartCmd),
+    Stop(ObjectStorageStopCmd),
 }
 
 #[derive(clap::Args)]
 #[clap(about = "Start object storage")]
-struct EndpointStorageStartCmd {
+struct ObjectStorageStartCmd {
     #[clap(short = 't', long, help = "timeout until we fail the command")]
     #[arg(default_value = "10s")]
     start_timeout: humantime::Duration,
@@ -474,7 +475,7 @@ struct EndpointStorageStartCmd {
 
 #[derive(clap::Args)]
 #[clap(about = "Stop object storage")]
-struct EndpointStorageStopCmd {
+struct ObjectStorageStopCmd {
     #[arg(value_enum, default_value = "fast")]
     #[clap(
         short = 'm',
@@ -551,7 +552,6 @@ enum EndpointCmd {
     Start(EndpointStartCmdArgs),
     Reconfigure(EndpointReconfigureCmdArgs),
     Stop(EndpointStopCmdArgs),
-    GenerateJwt(EndpointGenerateJwtCmdArgs),
 }
 
 #[derive(clap::Args)]
@@ -699,13 +699,6 @@ struct EndpointStopCmdArgs {
     mode: String,
 }
 
-#[derive(clap::Args)]
-#[clap(about = "Generate a JWT for an endpoint")]
-struct EndpointGenerateJwtCmdArgs {
-    #[clap(help = "Postgres endpoint id")]
-    endpoint_id: String,
-}
-
 #[derive(clap::Subcommand)]
 #[clap(about = "Manage neon_local branch name mappings")]
 enum MappingsCmd {
@@ -796,9 +789,7 @@ fn main() -> Result<()> {
             }
             NeonLocalCmd::StorageBroker(subcmd) => rt.block_on(handle_storage_broker(&subcmd, env)),
             NeonLocalCmd::Safekeeper(subcmd) => rt.block_on(handle_safekeeper(&subcmd, env)),
-            NeonLocalCmd::EndpointStorage(subcmd) => {
-                rt.block_on(handle_endpoint_storage(&subcmd, env))
-            }
+            NeonLocalCmd::ObjectStorage(subcmd) => rt.block_on(handle_object_storage(&subcmd, env)),
             NeonLocalCmd::Endpoint(subcmd) => rt.block_on(handle_endpoint(&subcmd, env)),
             NeonLocalCmd::Mappings(subcmd) => handle_mappings(&subcmd, env),
         };
@@ -1015,8 +1006,8 @@ fn handle_init(args: &InitCmdArgs) -> anyhow::Result<LocalEnv> {
                     }
                 })
                 .collect(),
-            endpoint_storage: EndpointStorageConf {
-                port: ENDPOINT_STORAGE_DEFAULT_PORT,
+            object_storage: ObjectStorageConf {
+                port: OBJECT_STORAGE_DEFAULT_PORT,
             },
             pg_distrib_dir: None,
             neon_distrib_dir: None,
@@ -1537,16 +1528,6 @@ async fn handle_endpoint(subcmd: &EndpointCmd, env: &local_env::LocalEnv) -> Res
                 .with_context(|| format!("postgres endpoint {endpoint_id} is not found"))?;
             endpoint.stop(&args.mode, args.destroy)?;
         }
-        EndpointCmd::GenerateJwt(args) => {
-            let endpoint_id = &args.endpoint_id;
-            let endpoint = cplane
-                .endpoints
-                .get(endpoint_id)
-                .with_context(|| format!("postgres endpoint {endpoint_id} is not found"))?;
-            let jwt = endpoint.generate_jwt()?;
-
-            print!("{jwt}");
-        }
     }
 
     Ok(())
@@ -1736,15 +1717,12 @@ async fn handle_safekeeper(subcmd: &SafekeeperCmd, env: &local_env::LocalEnv) ->
     Ok(())
 }
 
-async fn handle_endpoint_storage(
-    subcmd: &EndpointStorageCmd,
-    env: &local_env::LocalEnv,
-) -> Result<()> {
-    use EndpointStorageCmd::*;
-    let storage = EndpointStorage::from_env(env);
+async fn handle_object_storage(subcmd: &ObjectStorageCmd, env: &local_env::LocalEnv) -> Result<()> {
+    use ObjectStorageCmd::*;
+    let storage = ObjectStorage::from_env(env);
 
     // In tests like test_forward_compatibility or test_graceful_cluster_restart
-    // old neon binaries (without endpoint_storage) are present
+    // old neon binaries (without object_storage) are present
     if !storage.bin.exists() {
         eprintln!(
             "{} binary not found. Ignore if this is a compatibility test",
@@ -1754,13 +1732,13 @@ async fn handle_endpoint_storage(
     }
 
     match subcmd {
-        Start(EndpointStorageStartCmd { start_timeout }) => {
+        Start(ObjectStorageStartCmd { start_timeout }) => {
             if let Err(e) = storage.start(start_timeout).await {
-                eprintln!("endpoint_storage start failed: {e}");
+                eprintln!("object_storage start failed: {e}");
                 exit(1);
             }
         }
-        Stop(EndpointStorageStopCmd { stop_mode }) => {
+        Stop(ObjectStorageStopCmd { stop_mode }) => {
             let immediate = match stop_mode {
                 StopMode::Fast => false,
                 StopMode::Immediate => true,
@@ -1870,10 +1848,10 @@ async fn handle_start_all_impl(
         }
 
         js.spawn(async move {
-            EndpointStorage::from_env(env)
+            ObjectStorage::from_env(env)
                 .start(&retry_timeout)
                 .await
-                .map_err(|e| e.context("start endpoint_storage"))
+                .map_err(|e| e.context("start object_storage"))
         });
     })();
 
@@ -1972,9 +1950,9 @@ async fn try_stop_all(env: &local_env::LocalEnv, immediate: bool) {
         }
     }
 
-    let storage = EndpointStorage::from_env(env);
+    let storage = ObjectStorage::from_env(env);
     if let Err(e) = storage.stop(immediate) {
-        eprintln!("endpoint_storage stop failed: {:#}", e);
+        eprintln!("object_storage stop failed: {:#}", e);
     }
 
     for ps_conf in &env.pageservers {

control_plane/src/endpoint.rs

@@ -29,7 +29,7 @@
 //!     compute.log               - log output of `compute_ctl` and `postgres`
 //!     endpoint.json             - serialized `EndpointConf` struct
 //!     postgresql.conf           - postgresql settings
-//!     config.json                 - passed to `compute_ctl`
+//!     spec.json                 - passed to `compute_ctl`
 //!     pgdata/
 //!         postgresql.conf       - copy of postgresql.conf created by `compute_ctl`
 //!         zenith.signal
@@ -42,30 +42,20 @@ use std::path::PathBuf;
 use std::process::Command;
 use std::str::FromStr;
 use std::sync::Arc;
-use std::time::{Duration, Instant};
+use std::time::{Duration, Instant, SystemTime, UNIX_EPOCH};
 
 use anyhow::{Context, Result, anyhow, bail};
-use compute_api::requests::{ComputeClaims, ConfigurationRequest};
-use compute_api::responses::{
-    ComputeConfig, ComputeCtlConfig, ComputeStatus, ComputeStatusResponse, TlsConfig,
-};
+use compute_api::requests::ConfigurationRequest;
+use compute_api::responses::{ComputeCtlConfig, ComputeStatus, ComputeStatusResponse};
 use compute_api::spec::{
     Cluster, ComputeAudit, ComputeFeature, ComputeMode, ComputeSpec, Database, PgIdent,
     RemoteExtSpec, Role,
 };
-use jsonwebtoken::jwk::{
-    AlgorithmParameters, CommonParameters, EllipticCurve, Jwk, JwkSet, KeyAlgorithm, KeyOperations,
-    OctetKeyPairParameters, OctetKeyPairType, PublicKeyUse,
-};
 use nix::sys::signal::{Signal, kill};
 use pageserver_api::shard::ShardStripeSize;
-use pem::Pem;
 use reqwest::header::CONTENT_TYPE;
 use safekeeper_api::membership::SafekeeperGeneration;
 use serde::{Deserialize, Serialize};
-use sha2::{Digest, Sha256};
-use spki::der::Decode;
-use spki::{SubjectPublicKeyInfo, SubjectPublicKeyInfoRef};
 use tracing::debug;
 use url::Host;
 use utils::id::{NodeId, TenantId, TimelineId};
@@ -90,7 +80,6 @@ pub struct EndpointConf {
     drop_subscriptions_before_start: bool,
     features: Vec<ComputeFeature>,
     cluster: Option<Cluster>,
-    compute_ctl_config: ComputeCtlConfig,
 }
 
 //
@@ -146,37 +135,6 @@ impl ComputeControlPlane {
             .unwrap_or(self.base_port)
     }
 
-    /// Create a JSON Web Key Set. This ideally matches the way we create a JWKS
-    /// from the production control plane.
-    fn create_jwks_from_pem(pem: &Pem) -> Result<JwkSet> {
-        let spki: SubjectPublicKeyInfoRef = SubjectPublicKeyInfo::from_der(pem.contents())?;
-        let public_key = spki.subject_public_key.raw_bytes();
-
-        let mut hasher = Sha256::new();
-        hasher.update(public_key);
-        let key_hash = hasher.finalize();
-
-        Ok(JwkSet {
-            keys: vec![Jwk {
-                common: CommonParameters {
-                    public_key_use: Some(PublicKeyUse::Signature),
-                    key_operations: Some(vec![KeyOperations::Verify]),
-                    key_algorithm: Some(KeyAlgorithm::EdDSA),
-                    key_id: Some(base64::encode_config(key_hash, base64::URL_SAFE_NO_PAD)),
-                    x509_url: None::<String>,
-                    x509_chain: None::<Vec<String>>,
-                    x509_sha1_fingerprint: None::<String>,
-                    x509_sha256_fingerprint: None::<String>,
-                },
-                algorithm: AlgorithmParameters::OctetKeyPair(OctetKeyPairParameters {
-                    key_type: OctetKeyPairType::OctetKeyPair,
-                    curve: EllipticCurve::Ed25519,
-                    x: base64::encode_config(public_key, base64::URL_SAFE_NO_PAD),
-                }),
-            }],
-        })
-    }
-
     #[allow(clippy::too_many_arguments)]
     pub fn new_endpoint(
         &mut self,
@@ -194,10 +152,6 @@ impl ComputeControlPlane {
         let pg_port = pg_port.unwrap_or_else(|| self.get_port());
         let external_http_port = external_http_port.unwrap_or_else(|| self.get_port() + 1);
         let internal_http_port = internal_http_port.unwrap_or_else(|| external_http_port + 1);
-        let compute_ctl_config = ComputeCtlConfig {
-            jwks: Self::create_jwks_from_pem(&self.env.read_public_key()?)?,
-            tls: None::<TlsConfig>,
-        };
         let ep = Arc::new(Endpoint {
             endpoint_id: endpoint_id.to_owned(),
             pg_address: SocketAddr::new(IpAddr::from(Ipv4Addr::LOCALHOST), pg_port),
@@ -225,7 +179,6 @@ impl ComputeControlPlane {
             reconfigure_concurrency: 1,
             features: vec![],
             cluster: None,
-            compute_ctl_config: compute_ctl_config.clone(),
         });
 
         ep.create_endpoint_dir()?;
@@ -245,7 +198,6 @@ impl ComputeControlPlane {
                 reconfigure_concurrency: 1,
                 features: vec![],
                 cluster: None,
-                compute_ctl_config,
             })?,
         )?;
         std::fs::write(
@@ -288,6 +240,7 @@ impl ComputeControlPlane {
 
 ///////////////////////////////////////////////////////////////////////////////
 
+#[derive(Debug)]
 pub struct Endpoint {
     /// used as the directory name
     endpoint_id: String,
@@ -316,9 +269,6 @@ pub struct Endpoint {
     features: Vec<ComputeFeature>,
     // Cluster settings
     cluster: Option<Cluster>,
-
-    /// The compute_ctl config for the endpoint's compute.
-    compute_ctl_config: ComputeCtlConfig,
 }
 
 #[derive(PartialEq, Eq)]
@@ -381,7 +331,6 @@ impl Endpoint {
             drop_subscriptions_before_start: conf.drop_subscriptions_before_start,
             features: conf.features,
             cluster: conf.cluster,
-            compute_ctl_config: conf.compute_ctl_config,
         })
     }
 
@@ -629,13 +578,6 @@ impl Endpoint {
         Ok(safekeeper_connstrings)
     }
 
-    /// Generate a JWT with the correct claims.
-    pub fn generate_jwt(&self) -> Result<String> {
-        self.env.generate_auth_token(&ComputeClaims {
-            compute_id: self.endpoint_id.clone(),
-        })
-    }
-
     #[allow(clippy::too_many_arguments)]
     pub async fn start(
         &self,
@@ -677,97 +619,90 @@ impl Endpoint {
             remote_extensions = None;
         };
 
-        // Create config file
-        let config = {
-            let mut spec = ComputeSpec {
-                skip_pg_catalog_updates: self.skip_pg_catalog_updates,
-                format_version: 1.0,
-                operation_uuid: None,
-                features: self.features.clone(),
-                swap_size_bytes: None,
-                disk_quota_bytes: None,
-                disable_lfc_resizing: None,
-                cluster: Cluster {
-                    cluster_id: None, // project ID: not used
-                    name: None,       // project name: not used
-                    state: None,
-                    roles: if create_test_user {
-                        vec![Role {
-                            name: PgIdent::from_str("test").unwrap(),
-                            encrypted_password: None,
-                            options: None,
-                        }]
-                    } else {
-                        Vec::new()
-                    },
-                    databases: if create_test_user {
-                        vec![Database {
-                            name: PgIdent::from_str("neondb").unwrap(),
-                            owner: PgIdent::from_str("test").unwrap(),
-                            options: None,
-                            restrict_conn: false,
-                            invalid: false,
-                        }]
-                    } else {
-                        Vec::new()
-                    },
-                    settings: None,
-                    postgresql_conf: Some(postgresql_conf.clone()),
-                },
-                delta_operations: None,
-                tenant_id: Some(self.tenant_id),
-                timeline_id: Some(self.timeline_id),
-                project_id: None,
-                branch_id: None,
-                endpoint_id: Some(self.endpoint_id.clone()),
-                mode: self.mode,
-                pageserver_connstring: Some(pageserver_connstring),
-                safekeepers_generation: safekeepers_generation.map(|g| g.into_inner()),
-                safekeeper_connstrings,
-                storage_auth_token: auth_token.clone(),
-                remote_extensions,
-                pgbouncer_settings: None,
-                shard_stripe_size: Some(shard_stripe_size),
-                local_proxy_config: None,
-                reconfigure_concurrency: self.reconfigure_concurrency,
-                drop_subscriptions_before_start: self.drop_subscriptions_before_start,
-                audit_log_level: ComputeAudit::Disabled,
-                logs_export_host: None::<String>,
-            };
-
-            // this strange code is needed to support respec() in tests
-            if self.cluster.is_some() {
-                debug!("Cluster is already set in the endpoint spec, using it");
-                spec.cluster = self.cluster.clone().unwrap();
-
-                debug!("spec.cluster {:?}", spec.cluster);
-
-                // fill missing fields again
-                if create_test_user {
-                    spec.cluster.roles.push(Role {
+        // Create spec file
+        let mut spec = ComputeSpec {
+            skip_pg_catalog_updates: self.skip_pg_catalog_updates,
+            format_version: 1.0,
+            operation_uuid: None,
+            features: self.features.clone(),
+            swap_size_bytes: None,
+            disk_quota_bytes: None,
+            disable_lfc_resizing: None,
+            cluster: Cluster {
+                cluster_id: None, // project ID: not used
+                name: None,       // project name: not used
+                state: None,
+                roles: if create_test_user {
+                    vec![Role {
                         name: PgIdent::from_str("test").unwrap(),
                         encrypted_password: None,
                         options: None,
-                    });
-                    spec.cluster.databases.push(Database {
+                    }]
+                } else {
+                    Vec::new()
+                },
+                databases: if create_test_user {
+                    vec![Database {
                         name: PgIdent::from_str("neondb").unwrap(),
                         owner: PgIdent::from_str("test").unwrap(),
                         options: None,
                         restrict_conn: false,
                         invalid: false,
-                    });
-                }
-                spec.cluster.postgresql_conf = Some(postgresql_conf);
-            }
-
-            ComputeConfig {
-                spec: Some(spec),
-                compute_ctl_config: self.compute_ctl_config.clone(),
-            }
+                    }]
+                } else {
+                    Vec::new()
+                },
+                settings: None,
+                postgresql_conf: Some(postgresql_conf.clone()),
+            },
+            delta_operations: None,
+            tenant_id: Some(self.tenant_id),
+            timeline_id: Some(self.timeline_id),
+            project_id: None,
+            branch_id: None,
+            endpoint_id: Some(self.endpoint_id.clone()),
+            mode: self.mode,
+            pageserver_connstring: Some(pageserver_connstring),
+            safekeepers_generation: safekeepers_generation.map(|g| g.into_inner()),
+            safekeeper_connstrings,
+            storage_auth_token: auth_token.clone(),
+            remote_extensions,
+            pgbouncer_settings: None,
+            shard_stripe_size: Some(shard_stripe_size),
+            local_proxy_config: None,
+            reconfigure_concurrency: self.reconfigure_concurrency,
+            drop_subscriptions_before_start: self.drop_subscriptions_before_start,
+            audit_log_level: ComputeAudit::Disabled,
+            logs_export_host: None::<String>,
         };
 
-        let config_path = self.endpoint_path().join("config.json");
-        std::fs::write(config_path, serde_json::to_string_pretty(&config)?)?;
+        // this strange code is needed to support respec() in tests
+        if self.cluster.is_some() {
+            debug!("Cluster is already set in the endpoint spec, using it");
+            spec.cluster = self.cluster.clone().unwrap();
+
+            debug!("spec.cluster {:?}", spec.cluster);
+
+            // fill missing fields again
+            if create_test_user {
+                spec.cluster.roles.push(Role {
+                    name: PgIdent::from_str("test").unwrap(),
+                    encrypted_password: None,
+                    options: None,
+                });
+                spec.cluster.databases.push(Database {
+                    name: PgIdent::from_str("neondb").unwrap(),
+                    owner: PgIdent::from_str("test").unwrap(),
+                    options: None,
+                    restrict_conn: false,
+                    invalid: false,
+                });
+            }
+            spec.cluster.postgresql_conf = Some(postgresql_conf);
+        }
+
+        let spec_path = self.endpoint_path().join("spec.json");
+        std::fs::write(spec_path, serde_json::to_string_pretty(&spec)?)?;
 
         // Open log file. We'll redirect the stdout and stderr of `compute_ctl` to it.
         let logfile = std::fs::OpenOptions::new()
@@ -793,8 +728,10 @@ impl Endpoint {
         ])
         .args(["--pgdata", self.pgdata().to_str().unwrap()])
         .args(["--connstr", &conn_str])
-        .arg("--config")
-        .arg(self.endpoint_path().join("config.json").as_os_str())
+        .args([
+            "--spec-path",
+            self.endpoint_path().join("spec.json").to_str().unwrap(),
+        ])
         .args([
             "--pgbin",
             self.env
@@ -805,7 +742,16 @@ impl Endpoint {
         ])
         // TODO: It would be nice if we generated compute IDs with the same
         // algorithm as the real control plane.
-        .args(["--compute-id", &self.endpoint_id])
+        .args([
+            "--compute-id",
+            &format!(
+                "compute-{}",
+                SystemTime::now()
+                    .duration_since(UNIX_EPOCH)
+                    .unwrap()
+                    .as_secs()
+            ),
+        ])
         .stdin(std::process::Stdio::null())
         .stderr(logfile.try_clone()?)
         .stdout(logfile);
@@ -903,7 +849,6 @@ impl Endpoint {
                     self.external_http_address.port()
                 ),
             )
-            .bearer_auth(self.generate_jwt()?)
             .send()
             .await?;
 
@@ -928,12 +873,10 @@ impl Endpoint {
         stripe_size: Option<ShardStripeSize>,
         safekeepers: Option<Vec<NodeId>>,
     ) -> Result<()> {
-        let (mut spec, compute_ctl_config) = {
-            let config_path = self.endpoint_path().join("config.json");
-            let file = std::fs::File::open(config_path)?;
-            let config: ComputeConfig = serde_json::from_reader(file)?;
-
-            (config.spec.unwrap(), config.compute_ctl_config)
+        let mut spec: ComputeSpec = {
+            let spec_path = self.endpoint_path().join("spec.json");
+            let file = std::fs::File::open(spec_path)?;
+            serde_json::from_reader(file)?
         };
 
         let postgresql_conf = self.read_postgresql_conf()?;
@@ -980,11 +923,10 @@ impl Endpoint {
                 self.external_http_address.port()
             ))
             .header(CONTENT_TYPE.as_str(), "application/json")
-            .bearer_auth(self.generate_jwt()?)
             .body(
                 serde_json::to_string(&ConfigurationRequest {
                     spec,
-                    compute_ctl_config,
+                    compute_ctl_config: ComputeCtlConfig::default(),
                 })
                 .unwrap(),
             )

control_plane/src/lib.rs

@@ -9,8 +9,8 @@
 mod background_process;
 pub mod broker;
 pub mod endpoint;
-pub mod endpoint_storage;
 pub mod local_env;
+pub mod object_storage;
 pub mod pageserver;
 pub mod postgresql_conf;
 pub mod safekeeper;

control_plane/src/local_env.rs

@@ -12,18 +12,17 @@ use std::{env, fs};
 
 use anyhow::{Context, bail};
 use clap::ValueEnum;
-use pem::Pem;
 use postgres_backend::AuthType;
 use reqwest::Url;
 use serde::{Deserialize, Serialize};
 use utils::auth::encode_from_key_file;
 use utils::id::{NodeId, TenantId, TenantTimelineId, TimelineId};
 
-use crate::endpoint_storage::{ENDPOINT_STORAGE_REMOTE_STORAGE_DIR, EndpointStorage};
+use crate::object_storage::{OBJECT_STORAGE_REMOTE_STORAGE_DIR, ObjectStorage};
 use crate::pageserver::{PAGESERVER_REMOTE_STORAGE_DIR, PageServerNode};
 use crate::safekeeper::SafekeeperNode;
 
-pub const DEFAULT_PG_VERSION: u32 = 17;
+pub const DEFAULT_PG_VERSION: u32 = 16;
 
 //
 // This data structures represents neon_local CLI config
@@ -57,7 +56,6 @@ pub struct LocalEnv {
 
     // used to issue tokens during e.g pg start
     pub private_key_path: PathBuf,
-    /// Path to environment's public key
     pub public_key_path: PathBuf,
 
     pub broker: NeonBroker,
@@ -72,7 +70,7 @@ pub struct LocalEnv {
 
     pub safekeepers: Vec<SafekeeperConf>,
 
-    pub endpoint_storage: EndpointStorageConf,
+    pub object_storage: ObjectStorageConf,
 
     // 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.
@@ -110,7 +108,7 @@ pub struct OnDiskConfig {
     )]
     pub pageservers: Vec<PageServerConf>,
     pub safekeepers: Vec<SafekeeperConf>,
-    pub endpoint_storage: EndpointStorageConf,
+    pub object_storage: ObjectStorageConf,
     pub control_plane_api: Option<Url>,
     pub control_plane_hooks_api: Option<Url>,
     pub control_plane_compute_hook_api: Option<Url>,
@@ -144,7 +142,7 @@ pub struct NeonLocalInitConf {
     pub storage_controller: Option<NeonStorageControllerConf>,
     pub pageservers: Vec<NeonLocalInitPageserverConf>,
     pub safekeepers: Vec<SafekeeperConf>,
-    pub endpoint_storage: EndpointStorageConf,
+    pub object_storage: ObjectStorageConf,
     pub control_plane_api: Option<Url>,
     pub control_plane_hooks_api: Option<Url>,
     pub generate_local_ssl_certs: bool,
@@ -152,7 +150,7 @@ pub struct NeonLocalInitConf {
 
 #[derive(Serialize, Default, Deserialize, PartialEq, Eq, Clone, Debug)]
 #[serde(default)]
-pub struct EndpointStorageConf {
+pub struct ObjectStorageConf {
     pub port: u16,
 }
 
@@ -413,8 +411,8 @@ impl LocalEnv {
         self.pg_dir(pg_version, "lib")
     }
 
-    pub fn endpoint_storage_bin(&self) -> PathBuf {
-        self.neon_distrib_dir.join("endpoint_storage")
+    pub fn object_storage_bin(&self) -> PathBuf {
+        self.neon_distrib_dir.join("object_storage")
     }
 
     pub fn pageserver_bin(&self) -> PathBuf {
@@ -450,8 +448,8 @@ impl LocalEnv {
         self.base_data_dir.join("safekeepers").join(data_dir_name)
     }
 
-    pub fn endpoint_storage_data_dir(&self) -> PathBuf {
-        self.base_data_dir.join("endpoint_storage")
+    pub fn object_storage_data_dir(&self) -> PathBuf {
+        self.base_data_dir.join("object_storage")
     }
 
     pub fn get_pageserver_conf(&self, id: NodeId) -> anyhow::Result<&PageServerConf> {
@@ -615,7 +613,7 @@ impl LocalEnv {
                 control_plane_compute_hook_api: _,
                 branch_name_mappings,
                 generate_local_ssl_certs,
-                endpoint_storage,
+                object_storage,
             } = on_disk_config;
             LocalEnv {
                 base_data_dir: repopath.to_owned(),
@@ -632,7 +630,7 @@ impl LocalEnv {
                 control_plane_hooks_api,
                 branch_name_mappings,
                 generate_local_ssl_certs,
-                endpoint_storage,
+                object_storage,
             }
         };
 
@@ -742,7 +740,7 @@ impl LocalEnv {
                 control_plane_compute_hook_api: None,
                 branch_name_mappings: self.branch_name_mappings.clone(),
                 generate_local_ssl_certs: self.generate_local_ssl_certs,
-                endpoint_storage: self.endpoint_storage.clone(),
+                object_storage: self.object_storage.clone(),
             },
         )
     }
@@ -760,11 +758,11 @@ impl LocalEnv {
 
     // this function is used only for testing purposes in CLI e g generate tokens during init
     pub fn generate_auth_token<S: Serialize>(&self, claims: &S) -> anyhow::Result<String> {
-        let key = self.read_private_key()?;
-        encode_from_key_file(claims, &key)
+        let private_key_path = self.get_private_key_path();
+        let key_data = fs::read(private_key_path)?;
+        encode_from_key_file(claims, &key_data)
     }
 
-    /// Get the path to the private key.
     pub fn get_private_key_path(&self) -> PathBuf {
         if self.private_key_path.is_absolute() {
             self.private_key_path.to_path_buf()
@@ -773,29 +771,6 @@ impl LocalEnv {
         }
     }
 
-    /// Get the path to the public key.
-    pub fn get_public_key_path(&self) -> PathBuf {
-        if self.public_key_path.is_absolute() {
-            self.public_key_path.to_path_buf()
-        } else {
-            self.base_data_dir.join(&self.public_key_path)
-        }
-    }
-
-    /// Read the contents of the private key file.
-    pub fn read_private_key(&self) -> anyhow::Result<Pem> {
-        let private_key_path = self.get_private_key_path();
-        let pem = pem::parse(fs::read(private_key_path)?)?;
-        Ok(pem)
-    }
-
-    /// Read the contents of the public key file.
-    pub fn read_public_key(&self) -> anyhow::Result<Pem> {
-        let public_key_path = self.get_public_key_path();
-        let pem = pem::parse(fs::read(public_key_path)?)?;
-        Ok(pem)
-    }
-
     /// Materialize the [`NeonLocalInitConf`] to disk. Called during [`neon_local init`].
     pub fn init(conf: NeonLocalInitConf, force: &InitForceMode) -> anyhow::Result<()> {
         let base_path = base_path();
@@ -849,7 +824,7 @@ impl LocalEnv {
             control_plane_api,
             generate_local_ssl_certs,
             control_plane_hooks_api,
-            endpoint_storage,
+            object_storage,
         } = conf;
 
         // Find postgres binaries.
@@ -901,7 +876,7 @@ impl LocalEnv {
             control_plane_hooks_api,
             branch_name_mappings: Default::default(),
             generate_local_ssl_certs,
-            endpoint_storage,
+            object_storage,
         };
 
         if generate_local_ssl_certs {
@@ -929,13 +904,13 @@ impl LocalEnv {
                 .context("pageserver init failed")?;
         }
 
-        EndpointStorage::from_env(&env)
+        ObjectStorage::from_env(&env)
             .init()
             .context("object storage init failed")?;
 
         // setup remote remote location for default LocalFs remote storage
         std::fs::create_dir_all(env.base_data_dir.join(PAGESERVER_REMOTE_STORAGE_DIR))?;
-        std::fs::create_dir_all(env.base_data_dir.join(ENDPOINT_STORAGE_REMOTE_STORAGE_DIR))?;
+        std::fs::create_dir_all(env.base_data_dir.join(OBJECT_STORAGE_REMOTE_STORAGE_DIR))?;
 
         env.persist_config()
     }
@@ -981,7 +956,6 @@ fn generate_auth_keys(private_key_path: &Path, public_key_path: &Path) -> anyhow
             String::from_utf8_lossy(&keygen_output.stderr)
         );
     }
-
     // Extract the public key from the private key file
     //
     // openssl pkey -in auth_private_key.pem -pubout -out auth_public_key.pem
@@ -998,7 +972,6 @@ fn generate_auth_keys(private_key_path: &Path, public_key_path: &Path) -> anyhow
             String::from_utf8_lossy(&keygen_output.stderr)
         );
     }
-
     Ok(())
 }
 
@@ -1007,7 +980,7 @@ fn generate_ssl_ca_cert(cert_path: &Path, key_path: &Path) -> anyhow::Result<()>
     // -out rootCA.crt -keyout rootCA.key
     let keygen_output = Command::new("openssl")
         .args([
-            "req", "-x509", "-newkey", "ed25519", "-nodes", "-days", "36500",
+            "req", "-x509", "-newkey", "rsa:2048", "-nodes", "-days", "36500",
         ])
         .args(["-subj", "/CN=Neon Local CA"])
         .args(["-out", cert_path.to_str().unwrap()])
@@ -1037,7 +1010,7 @@ fn generate_ssl_cert(
     // -subj "/CN=localhost" -addext "subjectAltName=DNS:localhost,IP:127.0.0.1"
     let keygen_output = Command::new("openssl")
         .args(["req", "-new", "-nodes"])
-        .args(["-newkey", "ed25519"])
+        .args(["-newkey", "rsa:2048"])
         .args(["-subj", "/CN=localhost"])
         .args(["-addext", "subjectAltName=DNS:localhost,IP:127.0.0.1"])
         .args(["-keyout", key_path.to_str().unwrap()])

control_plane/src/object_storage.rs

@@ -1,33 +1,34 @@
 use crate::background_process::{self, start_process, stop_process};
 use crate::local_env::LocalEnv;
+use anyhow::anyhow;
 use anyhow::{Context, Result};
 use camino::Utf8PathBuf;
 use std::io::Write;
 use std::time::Duration;
 
 /// Directory within .neon which will be used by default for LocalFs remote storage.
-pub const ENDPOINT_STORAGE_REMOTE_STORAGE_DIR: &str = "local_fs_remote_storage/endpoint_storage";
-pub const ENDPOINT_STORAGE_DEFAULT_PORT: u16 = 9993;
+pub const OBJECT_STORAGE_REMOTE_STORAGE_DIR: &str = "local_fs_remote_storage/object_storage";
+pub const OBJECT_STORAGE_DEFAULT_PORT: u16 = 9993;
 
-pub struct EndpointStorage {
+pub struct ObjectStorage {
     pub bin: Utf8PathBuf,
     pub data_dir: Utf8PathBuf,
     pub pemfile: Utf8PathBuf,
     pub port: u16,
 }
 
-impl EndpointStorage {
-    pub fn from_env(env: &LocalEnv) -> EndpointStorage {
-        EndpointStorage {
-            bin: Utf8PathBuf::from_path_buf(env.endpoint_storage_bin()).unwrap(),
-            data_dir: Utf8PathBuf::from_path_buf(env.endpoint_storage_data_dir()).unwrap(),
+impl ObjectStorage {
+    pub fn from_env(env: &LocalEnv) -> ObjectStorage {
+        ObjectStorage {
+            bin: Utf8PathBuf::from_path_buf(env.object_storage_bin()).unwrap(),
+            data_dir: Utf8PathBuf::from_path_buf(env.object_storage_data_dir()).unwrap(),
             pemfile: Utf8PathBuf::from_path_buf(env.public_key_path.clone()).unwrap(),
-            port: env.endpoint_storage.port,
+            port: env.object_storage.port,
         }
     }
 
     fn config_path(&self) -> Utf8PathBuf {
-        self.data_dir.join("endpoint_storage.json")
+        self.data_dir.join("object_storage.json")
     }
 
     fn listen_addr(&self) -> Utf8PathBuf {
@@ -48,7 +49,7 @@ impl EndpointStorage {
         let cfg = Cfg {
             listen: self.listen_addr(),
             pemfile: parent.join(self.pemfile.clone()),
-            local_path: parent.join(ENDPOINT_STORAGE_REMOTE_STORAGE_DIR),
+            local_path: parent.join(OBJECT_STORAGE_REMOTE_STORAGE_DIR),
             r#type: "LocalFs".to_string(),
         };
         std::fs::create_dir_all(self.config_path().parent().unwrap())?;
@@ -58,19 +59,24 @@ impl EndpointStorage {
     }
 
     pub async fn start(&self, retry_timeout: &Duration) -> Result<()> {
-        println!("Starting endpoint_storage at {}", self.listen_addr());
+        println!("Starting s3 proxy at {}", self.listen_addr());
         std::io::stdout().flush().context("flush stdout")?;
 
         let process_status_check = || async {
-            let res = reqwest::Client::new().get(format!("http://{}/metrics", self.listen_addr()));
-            match res.send().await {
-                Ok(res) => Ok(res.status().is_success()),
-                Err(_) => Ok(false),
+            tokio::time::sleep(Duration::from_millis(500)).await;
+            let res = reqwest::Client::new()
+                .get(format!("http://{}/metrics", self.listen_addr()))
+                .send()
+                .await;
+            match res {
+                Ok(response) if response.status().is_success() => Ok(true),
+                Ok(_) => Err(anyhow!("Failed to query /metrics")),
+                Err(e) => Err(anyhow!("Failed to check node status: {e}")),
             }
         };
 
         let res = start_process(
-            "endpoint_storage",
+            "object_storage",
             &self.data_dir.clone().into_std_path_buf(),
             &self.bin.clone().into_std_path_buf(),
             vec![self.config_path().to_string()],
@@ -88,14 +94,14 @@ impl EndpointStorage {
     }
 
     pub fn stop(&self, immediate: bool) -> anyhow::Result<()> {
-        stop_process(immediate, "endpoint_storage", &self.pid_file())
+        stop_process(immediate, "object_storage", &self.pid_file())
     }
 
     fn log_file(&self) -> Utf8PathBuf {
-        self.data_dir.join("endpoint_storage.log")
+        self.data_dir.join("object_storage.log")
     }
 
     fn pid_file(&self) -> Utf8PathBuf {
-        self.data_dir.join("endpoint_storage.pid")
+        self.data_dir.join("object_storage.pid")
     }
 }

control_plane/src/pageserver.rs

@@ -413,11 +413,6 @@ impl PageServerNode {
                 .map(serde_json::from_str)
                 .transpose()
                 .context("Failed to parse 'compaction_algorithm' json")?,
-            compaction_shard_ancestor: settings
-                .remove("compaction_shard_ancestor")
-                .map(|x| x.parse::<bool>())
-                .transpose()
-                .context("Failed to parse 'compaction_shard_ancestor' as a bool")?,
             compaction_l0_first: settings
                 .remove("compaction_l0_first")
                 .map(|x| x.parse::<bool>())
@@ -540,11 +535,6 @@ impl PageServerNode {
                 .map(|x| x.parse::<bool>())
                 .transpose()
                 .context("Failed to parse 'gc_compaction_enabled' as bool")?,
-            gc_compaction_verification: settings
-                .remove("gc_compaction_verification")
-                .map(|x| x.parse::<bool>())
-                .transpose()
-                .context("Failed to parse 'gc_compaction_verification' as bool")?,
             gc_compaction_initial_threshold_kb: settings
                 .remove("gc_compaction_initial_threshold_kb")
                 .map(|x| x.parse::<u64>())

control_plane/src/storage_controller.rs

@@ -18,7 +18,6 @@ use pageserver_api::models::{
 };
 use pageserver_api::shard::TenantShardId;
 use pageserver_client::mgmt_api::ResponseErrorMessageExt;
-use pem::Pem;
 use postgres_backend::AuthType;
 use reqwest::{Certificate, Method};
 use serde::de::DeserializeOwned;
@@ -35,8 +34,8 @@ use crate::local_env::{LocalEnv, NeonStorageControllerConf};
 
 pub struct StorageController {
     env: LocalEnv,
-    private_key: Option<Pem>,
-    public_key: Option<Pem>,
+    private_key: Option<Vec<u8>>,
+    public_key: Option<String>,
     client: reqwest::Client,
     config: NeonStorageControllerConf,
 
@@ -117,9 +116,7 @@ impl StorageController {
             AuthType::Trust => (None, None),
             AuthType::NeonJWT => {
                 let private_key_path = env.get_private_key_path();
-                let private_key =
-                    pem::parse(fs::read(private_key_path).expect("failed to read private key"))
-                        .expect("failed to parse PEM file");
+                let private_key = fs::read(private_key_path).expect("failed to read private key");
 
                 // If pageserver auth is enabled, this implicitly enables auth for this service,
                 // using the same credentials.
@@ -141,13 +138,9 @@ impl StorageController {
                         .expect("Empty key dir")
                         .expect("Error reading key dir");
 
-                    pem::parse(std::fs::read_to_string(dent.path()).expect("Can't read public key"))
-                        .expect("Failed to parse PEM file")
+                    std::fs::read_to_string(dent.path()).expect("Can't read public key")
                 } else {
-                    pem::parse(
-                        std::fs::read_to_string(&public_key_path).expect("Can't read public key"),
-                    )
-                    .expect("Failed to parse PEM file")
+                    std::fs::read_to_string(&public_key_path).expect("Can't read public key")
                 };
                 (Some(private_key), Some(public_key))
             }

deny.toml

@@ -45,7 +45,9 @@ allow = [
     "ISC",
     "MIT",
     "MPL-2.0",
+    "OpenSSL",
     "Unicode-3.0",
+    "Zlib",
 ]
 confidence-threshold = 0.8
 exceptions = [
@@ -54,6 +56,14 @@ exceptions = [
     { allow = ["Zlib"], name = "const_format", version = "*" },
 ]
 
+[[licenses.clarify]]
+name = "ring"
+version = "*"
+expression = "MIT AND ISC AND OpenSSL"
+license-files = [
+    { path = "LICENSE", hash = 0xbd0eed23 }
+]
+
 [licenses.private]
 ignore = true
 registries = []
@@ -106,11 +116,7 @@ name = "openssl"
 unknown-registry = "warn"
 unknown-git = "warn"
 allow-registry = ["https://github.com/rust-lang/crates.io-index"]
-allow-git = [
-    # Crate pinned to commit in origin repo due to opentelemetry version.
-    # TODO: Remove this once crate is fetched from crates.io again.
-    "https://github.com/mattiapenati/tower-otel",
-]
+allow-git = []
 
 [sources.allow-org]
 github = [

docker-compose/README.md

@@ -1,3 +1,4 @@
+
 # Example docker compose configuration
 
 The configuration in this directory is used for testing Neon docker images: it is
@@ -7,13 +8,3 @@ you can experiment with a miniature Neon system, use `cargo neon` rather than co
 This configuration does not start the storage controller, because the controller
 needs a way to reconfigure running computes, and no such thing exists in this setup.
 
-## Generating the JWKS for a compute
-
-```shell
-openssl genpkey -algorithm Ed25519 -out private-key.pem
-openssl pkey -in private-key.pem -pubout -out public-key.pem
-openssl pkey -pubin -inform pem -in public-key.pem -pubout -outform der -out public-key.der
-key="$(xxd -plain -cols 32 -s -32 public-key.der)"
-key_id="$(printf '%s' "$key" | sha256sum | awk '{ print $1 }' | basenc --base64url --wrap=0)"
-x="$(printf '%s' "$key" | basenc --base64url --wrap=0)"
-```

docker-compose/compute_wrapper/private-key.pem

@@ -1,3 +0,0 @@
------BEGIN PRIVATE KEY-----
-MC4CAQAwBQYDK2VwBCIEIOmnRbzt2AJ0d+S3aU1hiYOl/tXpvz1FmWBfwHYBgOma
------END PRIVATE KEY-----

docker-compose/compute_wrapper/public-key.pem

@@ -1,3 +0,0 @@
------BEGIN PUBLIC KEY-----
-MCowBQYDK2VwAyEADY0al/U0bgB3+9fUGk+3PKWnsck9OyxN5DjHIN6Xep0=
------END PUBLIC KEY-----

docker-compose/compute_wrapper/shell/compute.sh

@@ -11,8 +11,8 @@ generate_id() {
 
 PG_VERSION=${PG_VERSION:-14}
 
-CONFIG_FILE_ORG=/var/db/postgres/configs/config.json
-CONFIG_FILE=/tmp/config.json
+SPEC_FILE_ORG=/var/db/postgres/specs/spec.json
+SPEC_FILE=/tmp/spec.json
 
 echo "Waiting pageserver become ready."
 while ! nc -z pageserver 6400; do
@@ -20,7 +20,7 @@ while ! nc -z pageserver 6400; do
 done
 echo "Page server is ready."
 
-cp ${CONFIG_FILE_ORG} ${CONFIG_FILE}
+cp ${SPEC_FILE_ORG} ${SPEC_FILE}
 
  if [ -n "${TENANT_ID:-}" ] && [ -n "${TIMELINE_ID:-}" ]; then
    tenant_id=${TENANT_ID}
@@ -73,17 +73,17 @@ else
   ulid_extension=ulid
 fi
 echo "Adding pgx_ulid"
-shared_libraries=$(jq -r '.spec.cluster.settings[] | select(.name=="shared_preload_libraries").value' ${CONFIG_FILE})
-sed -i "s/${shared_libraries}/${shared_libraries},${ulid_extension}/" ${CONFIG_FILE}
+shared_libraries=$(jq -r '.cluster.settings[] | select(.name=="shared_preload_libraries").value' ${SPEC_FILE})
+sed -i "s/${shared_libraries}/${shared_libraries},${ulid_extension}/" ${SPEC_FILE}
 echo "Overwrite tenant id and timeline id in spec file"
-sed -i "s/TENANT_ID/${tenant_id}/" ${CONFIG_FILE}
-sed -i "s/TIMELINE_ID/${timeline_id}/" ${CONFIG_FILE}
+sed -i "s/TENANT_ID/${tenant_id}/" ${SPEC_FILE}
+sed -i "s/TIMELINE_ID/${timeline_id}/" ${SPEC_FILE}
 
-cat ${CONFIG_FILE}
+cat ${SPEC_FILE}
 
 echo "Start compute node"
 /usr/local/bin/compute_ctl --pgdata /var/db/postgres/compute \
      -C "postgresql://cloud_admin@localhost:55433/postgres"  \
      -b /usr/local/bin/postgres                              \
      --compute-id "compute-$RANDOM"                          \
-     --config "$CONFIG_FILE"
+     -S ${SPEC_FILE}

docker-compose/compute_wrapper/var/db/postgres/configs/config.json

@@ -1,160 +0,0 @@
-{
-    "spec": {
-        "format_version": 1.0,
-
-        "timestamp": "2022-10-12T18:00:00.000Z",
-        "operation_uuid": "0f657b36-4b0f-4a2d-9c2e-1dcd615e7d8c",
-
-        "cluster": {
-            "cluster_id": "docker_compose",
-            "name": "docker_compose_test",
-            "state": "restarted",
-            "roles": [
-                {
-                    "name": "cloud_admin",
-                    "encrypted_password": "b093c0d3b281ba6da1eacc608620abd8",
-                    "options": null
-                }
-            ],
-            "databases": [
-            ],
-            "settings": [
-                {
-                    "name": "fsync",
-                    "value": "off",
-                    "vartype": "bool"
-                },
-                {
-                    "name": "wal_level",
-                    "value": "logical",
-                    "vartype": "enum"
-                },
-                {
-                    "name": "wal_log_hints",
-                    "value": "on",
-                    "vartype": "bool"
-                },
-                {
-                    "name": "log_connections",
-                    "value": "on",
-                    "vartype": "bool"
-                },
-                {
-                    "name": "port",
-                    "value": "55433",
-                    "vartype": "integer"
-                },
-                {
-                    "name": "shared_buffers",
-                    "value": "1MB",
-                    "vartype": "string"
-                },
-                {
-                    "name": "max_connections",
-                    "value": "100",
-                    "vartype": "integer"
-                },
-                {
-                    "name": "listen_addresses",
-                    "value": "0.0.0.0",
-                    "vartype": "string"
-                },
-                {
-                    "name": "max_wal_senders",
-                    "value": "10",
-                    "vartype": "integer"
-                },
-                {
-                    "name": "max_replication_slots",
-                    "value": "10",
-                    "vartype": "integer"
-                },
-                {
-                    "name": "wal_sender_timeout",
-                    "value": "5s",
-                    "vartype": "string"
-                },
-                {
-                    "name": "wal_keep_size",
-                    "value": "0",
-                    "vartype": "integer"
-                },
-                {
-                    "name": "password_encryption",
-                    "value": "md5",
-                    "vartype": "enum"
-                },
-                {
-                    "name": "restart_after_crash",
-                    "value": "off",
-                    "vartype": "bool"
-                },
-                {
-                    "name": "synchronous_standby_names",
-                    "value": "walproposer",
-                    "vartype": "string"
-                },
-                {
-                    "name": "shared_preload_libraries",
-                    "value": "neon,pg_cron,timescaledb,pg_stat_statements",
-                    "vartype": "string"
-                },
-                {
-                    "name": "neon.safekeepers",
-                    "value": "safekeeper1:5454,safekeeper2:5454,safekeeper3:5454",
-                    "vartype": "string"
-                },
-                {
-                    "name": "neon.timeline_id",
-                    "value": "TIMELINE_ID",
-                    "vartype": "string"
-                },
-                {
-                    "name": "neon.tenant_id",
-                    "value": "TENANT_ID",
-                    "vartype": "string"
-                },
-                {
-                    "name": "neon.pageserver_connstring",
-                    "value": "host=pageserver port=6400",
-                    "vartype": "string"
-                },
-                {
-                    "name": "max_replication_write_lag",
-                    "value": "500MB",
-                    "vartype": "string"
-                },
-                {
-                    "name": "max_replication_flush_lag",
-                    "value": "10GB",
-                    "vartype": "string"
-                },
-                {
-                    "name": "cron.database",
-                    "value": "postgres",
-                    "vartype": "string"
-                }
-            ]
-        },
-
-        "delta_operations": [
-        ]
-    },
-    "compute_ctl_config": {
-        "jwks": {
-            "keys": [
-                {
-                    "use": "sig",
-                    "key_ops": [
-                        "verify"
-                    ],
-                    "alg": "EdDSA",
-                    "kid": "ZGIxMzAzOGY0YWQwODk2ODU1MTk1NzMxMDFkYmUyOWU2NzZkOWNjNjMyMGRkZGJjOWY0MjdjYWVmNzE1MjUyOAo=",
-                    "kty": "OKP",
-                    "crv": "Ed25519",
-                    "x": "MGQ4ZDFhOTdmNTM0NmUwMDc3ZmJkN2Q0MWE0ZmI3M2NhNWE3YjFjOTNkM2IyYzRkZTQzOGM3MjBkZTk3N2E5ZAo="
-                }
-            ]
-        }
-    }
-}

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

@@ -0,0 +1,141 @@
+{
+    "format_version": 1.0,
+
+    "timestamp": "2022-10-12T18:00:00.000Z",
+    "operation_uuid": "0f657b36-4b0f-4a2d-9c2e-1dcd615e7d8c",
+
+    "cluster": {
+        "cluster_id": "docker_compose",
+        "name": "docker_compose_test",
+        "state": "restarted",
+        "roles": [
+            {
+                "name": "cloud_admin",
+                "encrypted_password": "b093c0d3b281ba6da1eacc608620abd8",
+                "options": null
+            }
+        ],
+        "databases": [
+        ],
+        "settings": [
+            {
+                "name": "fsync",
+                "value": "off",
+                "vartype": "bool"
+            },
+            {
+                "name": "wal_level",
+                "value": "logical",
+                "vartype": "enum"
+            },
+            {
+                "name": "wal_log_hints",
+                "value": "on",
+                "vartype": "bool"
+            },
+            {
+                "name": "log_connections",
+                "value": "on",
+                "vartype": "bool"
+            },
+            {
+                "name": "port",
+                "value": "55433",
+                "vartype": "integer"
+            },
+            {
+                "name": "shared_buffers",
+                "value": "1MB",
+                "vartype": "string"
+            },
+            {
+                "name": "max_connections",
+                "value": "100",
+                "vartype": "integer"
+            },
+            {
+                "name": "listen_addresses",
+                "value": "0.0.0.0",
+                "vartype": "string"
+            },
+            {
+                "name": "max_wal_senders",
+                "value": "10",
+                "vartype": "integer"
+            },
+            {
+                "name": "max_replication_slots",
+                "value": "10",
+                "vartype": "integer"
+            },
+            {
+                "name": "wal_sender_timeout",
+                "value": "5s",
+                "vartype": "string"
+            },
+            {
+                "name": "wal_keep_size",
+                "value": "0",
+                "vartype": "integer"
+            },
+            {
+                "name": "password_encryption",
+                "value": "md5",
+                "vartype": "enum"
+            },
+            {
+                "name": "restart_after_crash",
+                "value": "off",
+                "vartype": "bool"
+            },
+            {
+                "name": "synchronous_standby_names",
+                "value": "walproposer",
+                "vartype": "string"
+            },
+            {
+                "name": "shared_preload_libraries",
+                "value": "neon,pg_cron,timescaledb,pg_stat_statements",
+                "vartype": "string"
+            },
+            {
+                "name": "neon.safekeepers",
+                "value": "safekeeper1:5454,safekeeper2:5454,safekeeper3:5454",
+                "vartype": "string"
+            },
+            {
+                "name": "neon.timeline_id",
+                "value": "TIMELINE_ID",
+                "vartype": "string"
+            },
+            {
+                "name": "neon.tenant_id",
+                "value": "TENANT_ID",
+                "vartype": "string"
+            },
+            {
+                "name": "neon.pageserver_connstring",
+                "value": "host=pageserver port=6400",
+                "vartype": "string"
+            },
+            {
+                "name": "max_replication_write_lag",
+                "value": "500MB",
+                "vartype": "string"
+            },
+            {
+                "name": "max_replication_flush_lag",
+                "value": "10GB",
+                "vartype": "string"
+            },
+            {
+                "name": "cron.database",
+                "value": "postgres",
+                "vartype": "string"
+            }
+        ]
+    },
+
+    "delta_operations": [
+    ]
+}

docker-compose/docker-compose.yml

@@ -159,7 +159,7 @@ services:
       #- RUST_BACKTRACE=1
     # Mount the test files directly, for faster editing cycle.
     volumes:
-      - ./compute_wrapper/var/db/postgres/configs/:/var/db/postgres/configs/
+      - ./compute_wrapper/var/db/postgres/specs/:/var/db/postgres/specs/
       - ./compute_wrapper/shell/:/shell/
     ports:
       - 55433:55433 # pg protocol handler

docker-compose/docker_compose_test.sh

@@ -9,20 +9,21 @@
 # to verify custom image builds (e.g pre-published ones).
 #
 # A test script for postgres extensions
-# Currently supports only v16+
+# Currently supports only v16
 #
 set -eux -o pipefail
 
-export COMPOSE_FILE='docker-compose.yml'
-export COMPOSE_PROFILES=test-extensions
-cd "$(dirname "${0}")"
+COMPOSE_FILE='docker-compose.yml'
+cd $(dirname $0)
+COMPUTE_CONTAINER_NAME=docker-compose-compute-1
+TEST_CONTAINER_NAME=docker-compose-neon-test-extensions-1
 PSQL_OPTION="-h localhost -U cloud_admin -p 55433 -d postgres"
 
-function cleanup() {
+cleanup() {
     echo "show container information"
     docker ps
     echo "stop containers..."
-    docker compose down
+    docker compose --profile test-extensions -f $COMPOSE_FILE down
 }
 
 for pg_version in ${TEST_VERSION_ONLY-14 15 16 17}; do
@@ -30,55 +31,55 @@ 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))
-    PG_VERSION=${pg_version} PG_TEST_VERSION=${PG_TEST_VERSION} docker compose up --quiet-pull --build -d
+    PG_VERSION=$pg_version PG_TEST_VERSION=$PG_TEST_VERSION docker compose --profile test-extensions -f $COMPOSE_FILE up --quiet-pull --build -d
 
     echo "wait until the compute is ready. timeout after 60s. "
     cnt=0
     while sleep 3; do
         # check timeout
-        (( cnt += 3 ))
-        if [[ ${cnt} -gt 60 ]]; then
+        cnt=`expr $cnt + 3`
+        if [ $cnt -gt 60 ]; then
             echo "timeout before the compute is ready."
             exit 1
         fi
-        if docker compose logs "compute_is_ready" | grep -q "accepting connections"; then
+        if docker compose --profile test-extensions -f $COMPOSE_FILE logs "compute_is_ready" | grep -q "accepting connections"; then
             echo "OK. The compute is ready to connect."
             echo "execute simple queries."
-            docker compose exec compute /bin/bash -c "psql ${PSQL_OPTION} -c 'SELECT 1'"
+            docker exec $COMPUTE_CONTAINER_NAME /bin/bash -c "psql $PSQL_OPTION"
             break
         fi
     done
 
-    if [[ ${pg_version} -ge 16 ]]; then
+    if [ $pg_version -ge 16 ]; then
         # This is required for the pg_hint_plan test, to prevent flaky log message causing the test to fail
         # It cannot be moved to Dockerfile now because the database directory is created after the start of the container
         echo Adding dummy config
-        docker compose exec compute touch /var/db/postgres/compute/compute_ctl_temp_override.conf
+        docker exec $COMPUTE_CONTAINER_NAME touch /var/db/postgres/compute/compute_ctl_temp_override.conf
         # The following block copies the files for the pg_hintplan test to the compute node for the extension test in an isolated docker-compose environment
         TMPDIR=$(mktemp -d)
-        docker compose cp neon-test-extensions:/ext-src/pg_hint_plan-src/data "${TMPDIR}/data"
-        docker compose cp "${TMPDIR}/data" compute:/ext-src/pg_hint_plan-src/
-        rm -rf "${TMPDIR}"
+        docker cp $TEST_CONTAINER_NAME:/ext-src/pg_hint_plan-src/data $TMPDIR/data
+        docker cp $TMPDIR/data $COMPUTE_CONTAINER_NAME:/ext-src/pg_hint_plan-src/
+        rm -rf $TMPDIR
         # The following block does the same for the contrib/file_fdw test
         TMPDIR=$(mktemp -d)
-        docker compose cp neon-test-extensions:/postgres/contrib/file_fdw/data "${TMPDIR}/data"
-        docker compose cp "${TMPDIR}/data" compute:/postgres/contrib/file_fdw/data
-        rm -rf "${TMPDIR}"
+        docker cp $TEST_CONTAINER_NAME:/postgres/contrib/file_fdw/data $TMPDIR/data
+        docker cp $TMPDIR/data $COMPUTE_CONTAINER_NAME:/postgres/contrib/file_fdw/data
+        rm -rf $TMPDIR
         # Apply patches
-        docker compose exec -i neon-test-extensions bash -c "(cd /postgres && patch -p1)" <"../compute/patches/contrib_pg${pg_version}.patch"
+        cat ../compute/patches/contrib_pg${pg_version}.patch | docker exec -i $TEST_CONTAINER_NAME bash -c "(cd /postgres && patch -p1)"
         # We are running tests now
         rm -f testout.txt testout_contrib.txt
-        docker compose exec -e USE_PGXS=1 -e SKIP=timescaledb-src,rdkit-src,postgis-src,pg_jsonschema-src,kq_imcx-src,wal2json_2_5-src,rag_jina_reranker_v1_tiny_en-src,rag_bge_small_en_v15-src \
-        neon-test-extensions /run-tests.sh /ext-src | tee testout.txt && EXT_SUCCESS=1 || EXT_SUCCESS=0
-        docker compose exec -e SKIP=start-scripts,postgres_fdw,ltree_plpython,jsonb_plpython,jsonb_plperl,hstore_plpython,hstore_plperl,dblink,bool_plperl \
-        neon-test-extensions /run-tests.sh /postgres/contrib | tee testout_contrib.txt && CONTRIB_SUCCESS=1 || CONTRIB_SUCCESS=0
-        if [[ ${EXT_SUCCESS} -eq 0 || ${CONTRIB_SUCCESS} -eq 0 ]]; then
+        docker exec -e USE_PGXS=1 -e SKIP=timescaledb-src,rdkit-src,postgis-src,pg_jsonschema-src,kq_imcx-src,wal2json_2_5-src,rag_jina_reranker_v1_tiny_en-src,rag_bge_small_en_v15-src \
+        $TEST_CONTAINER_NAME /run-tests.sh /ext-src | tee testout.txt && EXT_SUCCESS=1 || EXT_SUCCESS=0
+        docker exec -e SKIP=start-scripts,postgres_fdw,ltree_plpython,jsonb_plpython,jsonb_plperl,hstore_plpython,hstore_plperl,dblink,bool_plperl \
+        $TEST_CONTAINER_NAME /run-tests.sh /postgres/contrib | tee testout_contrib.txt && CONTRIB_SUCCESS=1 || CONTRIB_SUCCESS=0
+        if [ $EXT_SUCCESS -eq 0 ] || [ $CONTRIB_SUCCESS -eq 0 ]; then
             CONTRIB_FAILED=
             FAILED=
-            [[ ${EXT_SUCCESS} -eq 0 ]] && FAILED=$(tail -1 testout.txt | awk '{for(i=1;i<=NF;i++){print "/ext-src/"$i;}}')
-            [[ ${CONTRIB_SUCCESS} -eq 0 ]] && CONTRIB_FAILED=$(tail -1 testout_contrib.txt | awk '{for(i=0;i<=NF;i++){print "/postgres/contrib/"$i;}}')
-            for d in ${FAILED} ${CONTRIB_FAILED}; do
-                docker compose exec neon-test-extensions bash -c 'for file in $(find '"${d}"' -name regression.diffs -o -name regression.out); do cat ${file}; done' || [[ ${?} -eq 1 ]]
+            [ $EXT_SUCCESS -eq 0 ] && FAILED=$(tail -1 testout.txt | awk '{for(i=1;i<=NF;i++){print "/ext-src/"$i;}}')
+            [ $CONTRIB_SUCCESS -eq 0 ] && CONTRIB_FAILED=$(tail -1 testout_contrib.txt | awk '{for(i=0;i<=NF;i++){print "/postgres/contrib/"$i;}}')
+            for d in $FAILED $CONTRIB_FAILED; do
+                docker exec $TEST_CONTAINER_NAME bash -c 'for file in $(find '"$d"' -name regression.diffs -o -name regression.out); do cat $file; done' || [ $? -eq 1 ]
             done
         exit 1
         fi

docker-compose/ext-src/pg_jsonschema-src/Makefile

@@ -1,8 +0,0 @@
-EXTENSION = pg_jsonschema
-DATA = pg_jsonschema--1.0.sql
-REGRESS = jsonschema_valid_api  jsonschema_edge_cases
-REGRESS_OPTS = --load-extension=pg_jsonschema
-
-PG_CONFIG ?= pg_config
-PGXS := $(shell $(PG_CONFIG) --pgxs)
-include $(PGXS)

docker-compose/ext-src/pg_jsonschema-src/expected/jsonschema_edge_cases.out

@@ -1,87 +0,0 @@
--- Schema with enums, nulls, extra properties disallowed
-SELECT jsonschema_is_valid('{
-  "type": "object",
-  "properties": {
-    "status": { "type": "string", "enum": ["active", "inactive", "pending"] },
-    "email": { "type": ["string", "null"], "format": "email" }
-  },
-  "required": ["status"],
-  "additionalProperties": false
-}'::json);
- jsonschema_is_valid 
----------------------
- t
-(1 row)
-
--- Valid enum and null email
-SELECT jsonschema_validation_errors(
-  '{
-    "type": "object",
-    "properties": {
-      "status": { "type": "string", "enum": ["active", "inactive", "pending"] },
-      "email": { "type": ["string", "null"], "format": "email" }
-    },
-    "required": ["status"],
-    "additionalProperties": false
-  }'::json,
-  '{"status": "active", "email": null}'::json
-);
- jsonschema_validation_errors 
-------------------------------
- {}
-(1 row)
-
--- Invalid enum value
-SELECT jsonschema_validation_errors(
-  '{
-    "type": "object",
-    "properties": {
-      "status": { "type": "string", "enum": ["active", "inactive", "pending"] },
-      "email": { "type": ["string", "null"], "format": "email" }
-    },
-    "required": ["status"],
-    "additionalProperties": false
-  }'::json,
-  '{"status": "disabled", "email": null}'::json
-);
-                     jsonschema_validation_errors                     
-----------------------------------------------------------------------
- {"\"disabled\" is not one of [\"active\",\"inactive\",\"pending\"]"}
-(1 row)
-
--- Invalid email format (assuming format is validated)
-SELECT jsonschema_validation_errors(
-  '{
-    "type": "object",
-    "properties": {
-      "status": { "type": "string", "enum": ["active", "inactive", "pending"] },
-      "email": { "type": ["string", "null"], "format": "email" }
-    },
-    "required": ["status"],
-    "additionalProperties": false
-  }'::json,
-  '{"status": "active", "email": "not-an-email"}'::json
-);
-      jsonschema_validation_errors       
------------------------------------------
- {"\"not-an-email\" is not a \"email\""}
-(1 row)
-
--- Extra property not allowed
-SELECT jsonschema_validation_errors(
-  '{
-    "type": "object",
-    "properties": {
-      "status": { "type": "string", "enum": ["active", "inactive", "pending"] },
-      "email": { "type": ["string", "null"], "format": "email" }
-    },
-    "required": ["status"],
-    "additionalProperties": false
-  }'::json,
-  '{"status": "active", "extra": "should not be here"}'::json
-);
-                    jsonschema_validation_errors                    
---------------------------------------------------------------------
- {"Additional properties are not allowed ('extra' was unexpected)"}
-(1 row)
-

docker-compose/ext-src/pg_jsonschema-src/expected/jsonschema_valid_api.out

@@ -1,65 +0,0 @@
--- Define schema
-SELECT jsonschema_is_valid('{
-  "type": "object",
-  "properties": {
-    "username": { "type": "string" },
-    "age": { "type": "integer" }
-  },
-  "required": ["username"]
-}'::json);
- jsonschema_is_valid 
----------------------
- t
-(1 row)
-
--- Valid instance
-SELECT jsonschema_validation_errors(
-  '{
-    "type": "object",
-    "properties": {
-      "username": { "type": "string" },
-      "age": { "type": "integer" }
-    },
-    "required": ["username"]
-  }'::json,
-  '{"username": "alice", "age": 25}'::json
-);
- jsonschema_validation_errors 
-------------------------------
- {}
-(1 row)
-
--- Invalid instance: missing required "username"
-SELECT jsonschema_validation_errors(
-  '{
-    "type": "object",
-    "properties": {
-      "username": { "type": "string" },
-      "age": { "type": "integer" }
-    },
-    "required": ["username"]
-  }'::json,
-  '{"age": 25}'::json
-);
-      jsonschema_validation_errors       
------------------------------------------
- {"\"username\" is a required property"}
-(1 row)
-
--- Invalid instance: wrong type for "age"
-SELECT jsonschema_validation_errors(
-  '{
-    "type": "object",
-    "properties": {
-      "username": { "type": "string" },
-      "age": { "type": "integer" }
-    },
-    "required": ["username"]
-  }'::json,
-  '{"username": "bob", "age": "twenty"}'::json
-);
-       jsonschema_validation_errors        
--------------------------------------------
- {"\"twenty\" is not of type \"integer\""}
-(1 row)
-

docker-compose/ext-src/pg_jsonschema-src/sql/jsonschema_edge_cases.sql

@@ -1,66 +0,0 @@
--- Schema with enums, nulls, extra properties disallowed
-SELECT jsonschema_is_valid('{
-  "type": "object",
-  "properties": {
-    "status": { "type": "string", "enum": ["active", "inactive", "pending"] },
-    "email": { "type": ["string", "null"], "format": "email" }
-  },
-  "required": ["status"],
-  "additionalProperties": false
-}'::json);
-
--- Valid enum and null email
-SELECT jsonschema_validation_errors(
-  '{
-    "type": "object",
-    "properties": {
-      "status": { "type": "string", "enum": ["active", "inactive", "pending"] },
-      "email": { "type": ["string", "null"], "format": "email" }
-    },
-    "required": ["status"],
-    "additionalProperties": false
-  }'::json,
-  '{"status": "active", "email": null}'::json
-);
-
--- Invalid enum value
-SELECT jsonschema_validation_errors(
-  '{
-    "type": "object",
-    "properties": {
-      "status": { "type": "string", "enum": ["active", "inactive", "pending"] },
-      "email": { "type": ["string", "null"], "format": "email" }
-    },
-    "required": ["status"],
-    "additionalProperties": false
-  }'::json,
-  '{"status": "disabled", "email": null}'::json
-);
-
--- Invalid email format (assuming format is validated)
-SELECT jsonschema_validation_errors(
-  '{
-    "type": "object",
-    "properties": {
-      "status": { "type": "string", "enum": ["active", "inactive", "pending"] },
-      "email": { "type": ["string", "null"], "format": "email" }
-    },
-    "required": ["status"],
-    "additionalProperties": false
-  }'::json,
-  '{"status": "active", "email": "not-an-email"}'::json
-);
-
--- Extra property not allowed
-SELECT jsonschema_validation_errors(
-  '{
-    "type": "object",
-    "properties": {
-      "status": { "type": "string", "enum": ["active", "inactive", "pending"] },
-      "email": { "type": ["string", "null"], "format": "email" }
-    },
-    "required": ["status"],
-    "additionalProperties": false
-  }'::json,
-  '{"status": "active", "extra": "should not be here"}'::json
-);

docker-compose/ext-src/pg_jsonschema-src/sql/jsonschema_valid_api.sql

@@ -1,48 +0,0 @@
--- Define schema
-SELECT jsonschema_is_valid('{
-  "type": "object",
-  "properties": {
-    "username": { "type": "string" },
-    "age": { "type": "integer" }
-  },
-  "required": ["username"]
-}'::json);
-
--- Valid instance
-SELECT jsonschema_validation_errors(
-  '{
-    "type": "object",
-    "properties": {
-      "username": { "type": "string" },
-      "age": { "type": "integer" }
-    },
-    "required": ["username"]
-  }'::json,
-  '{"username": "alice", "age": 25}'::json
-);
-
--- Invalid instance: missing required "username"
-SELECT jsonschema_validation_errors(
-  '{
-    "type": "object",
-    "properties": {
-      "username": { "type": "string" },
-      "age": { "type": "integer" }
-    },
-    "required": ["username"]
-  }'::json,
-  '{"age": 25}'::json
-);
-
--- Invalid instance: wrong type for "age"
-SELECT jsonschema_validation_errors(
-  '{
-    "type": "object",
-    "properties": {
-      "username": { "type": "string" },
-      "age": { "type": "integer" }
-    },
-    "required": ["username"]
-  }'::json,
-  '{"username": "bob", "age": "twenty"}'::json
-);

docker-compose/ext-src/pg_session_jwt-src/Makefile

@@ -1,9 +0,0 @@
-EXTENSION = pg_session_jwt
-
-REGRESS = basic_functions
-REGRESS_OPTS = --load-extension=$(EXTENSION)
-export PGOPTIONS = -c pg_session_jwt.jwk={"crv":"Ed25519","kty":"OKP","x":"R_Abz-63zJ00l-IraL5fQhwkhGVZCSooQFV5ntC3C7M"}
-
-PG_CONFIG ?= pg_config
-PGXS := $(shell $(PG_CONFIG) --pgxs)
-include $(PGXS)

docker-compose/ext-src/pg_session_jwt-src/expected/basic_functions.out

@@ -1,35 +0,0 @@
--- Basic functionality tests for pg_session_jwt
--- Test auth.init() function
-SELECT auth.init();
- init 
-------
- 
-(1 row)
-
--- Test an invalid JWT
-SELECT auth.jwt_session_init('INVALID-JWT');
-ERROR:  invalid JWT encoding
--- Test creating a session with an expired JWT
-SELECT auth.jwt_session_init('eyJhbGciOiJFZERTQSJ9.eyJleHAiOjE3NDI1NjQ0MzIsImlhdCI6MTc0MjU2NDI1MiwianRpIjo0MjQyNDIsInN1YiI6InVzZXIxMjMifQ.A6FwKuaSduHB9O7Gz37g0uoD_U9qVS0JNtT7YABGVgB7HUD1AMFc9DeyhNntWBqncg8k5brv-hrNTuUh5JYMAw');
-ERROR:  Token used after it has expired
--- Test creating a session with a valid JWT
-SELECT auth.jwt_session_init('eyJhbGciOiJFZERTQSJ9.eyJleHAiOjQ4OTYxNjQyNTIsImlhdCI6MTc0MjU2NDI1MiwianRpIjo0MzQzNDMsInN1YiI6InVzZXIxMjMifQ.2TXVgjb6JSUq6_adlvp-m_SdOxZSyGS30RS9TLB0xu2N83dMSs2NybwE1NMU8Fb0tcAZR_ET7M2rSxbTrphfCg');
- jwt_session_init 
-------------------
- 
-(1 row)
-
--- Test auth.session() function
-SELECT auth.session();
-                                 session                                 
--------------------------------------------------------------------------
- {"exp": 4896164252, "iat": 1742564252, "jti": 434343, "sub": "user123"}
-(1 row)
-
--- Test auth.user_id() function
-SELECT auth.user_id() AS user_id;
- user_id 
----------
- user123
-(1 row)
-

docker-compose/ext-src/pg_session_jwt-src/sql/basic_functions.sql

@@ -1,19 +0,0 @@
--- Basic functionality tests for pg_session_jwt
-
--- Test auth.init() function
-SELECT auth.init();
-
--- Test an invalid JWT
-SELECT auth.jwt_session_init('INVALID-JWT');
-
--- Test creating a session with an expired JWT
-SELECT auth.jwt_session_init('eyJhbGciOiJFZERTQSJ9.eyJleHAiOjE3NDI1NjQ0MzIsImlhdCI6MTc0MjU2NDI1MiwianRpIjo0MjQyNDIsInN1YiI6InVzZXIxMjMifQ.A6FwKuaSduHB9O7Gz37g0uoD_U9qVS0JNtT7YABGVgB7HUD1AMFc9DeyhNntWBqncg8k5brv-hrNTuUh5JYMAw');
-
--- Test creating a session with a valid JWT
-SELECT auth.jwt_session_init('eyJhbGciOiJFZERTQSJ9.eyJleHAiOjQ4OTYxNjQyNTIsImlhdCI6MTc0MjU2NDI1MiwianRpIjo0MzQzNDMsInN1YiI6InVzZXIxMjMifQ.2TXVgjb6JSUq6_adlvp-m_SdOxZSyGS30RS9TLB0xu2N83dMSs2NybwE1NMU8Fb0tcAZR_ET7M2rSxbTrphfCg');
-
--- Test auth.session() function
-SELECT auth.session();
-
--- Test auth.user_id() function
-SELECT auth.user_id() AS user_id;

libs/compute_api/src/responses.rs

@@ -14,32 +14,6 @@ pub struct GenericAPIError {
     pub error: String,
 }
 
-/// All configuration parameters necessary for a compute. When
-/// [`ComputeConfig::spec`] is provided, it means that the compute is attached
-/// to a tenant. [`ComputeConfig::compute_ctl_config`] will always be provided
-/// and contains parameters necessary for operating `compute_ctl` independently
-/// of whether a tenant is attached to the compute or not.
-///
-/// This also happens to be the body of `compute_ctl`'s /configure request.
-#[derive(Debug, Deserialize, Serialize)]
-pub struct ComputeConfig {
-    /// The compute spec
-    pub spec: Option<ComputeSpec>,
-
-    /// The compute_ctl configuration
-    #[allow(dead_code)]
-    pub compute_ctl_config: ComputeCtlConfig,
-}
-
-impl From<ControlPlaneConfigResponse> for ComputeConfig {
-    fn from(value: ControlPlaneConfigResponse) -> Self {
-        Self {
-            spec: value.spec,
-            compute_ctl_config: value.compute_ctl_config,
-        }
-    }
-}
-
 #[derive(Debug, Clone, Serialize)]
 pub struct ExtensionInstallResponse {
     pub extension: PgIdent,
@@ -160,7 +134,7 @@ pub struct CatalogObjects {
     pub databases: Vec<Database>,
 }
 
-#[derive(Clone, Debug, Deserialize, Eq, PartialEq, Serialize)]
+#[derive(Clone, Debug, Deserialize, Serialize)]
 pub struct ComputeCtlConfig {
     /// Set of JSON web keys that the compute can use to authenticate
     /// communication from the control plane.
@@ -179,7 +153,7 @@ impl Default for ComputeCtlConfig {
     }
 }
 
-#[derive(Clone, Debug, Deserialize, Eq, PartialEq, Serialize)]
+#[derive(Clone, Debug, Deserialize, Serialize)]
 pub struct TlsConfig {
     pub key_path: String,
     pub cert_path: String,
@@ -187,7 +161,7 @@ pub struct TlsConfig {
 
 /// Response of the `/computes/{compute_id}/spec` control-plane API.
 #[derive(Deserialize, Debug)]
-pub struct ControlPlaneConfigResponse {
+pub struct ControlPlaneSpecResponse {
     pub spec: Option<ComputeSpec>,
     pub status: ControlPlaneComputeStatus,
     pub compute_ctl_config: ComputeCtlConfig,

libs/compute_api/src/spec.rs

@@ -1,8 +1,8 @@
-//! The ComputeSpec contains all the information needed to start up
-//! the right version of PostgreSQL, and connect it to the storage nodes.
-//! It can be passed as part of the `config.json`, or the control plane can
-//! provide it by calling the compute_ctl's `/compute_ctl` endpoint, or
-//! compute_ctl can fetch it by calling the control plane's API.
+//! `ComputeSpec` represents the contents of the spec.json file.
+//!
+//! The spec.json file is used to pass information to 'compute_ctl'. It contains
+//! all the information needed to start up the right version of PostgreSQL,
+//! and connect it to the storage nodes.
 use std::collections::HashMap;
 
 use indexmap::IndexMap;
@@ -242,22 +242,13 @@ impl RemoteExtSpec {
 
         match self.extension_data.get(real_ext_name) {
             Some(_ext_data) => {
-                // We have decided to use the Go naming convention due to Kubernetes.
-
-                let arch = match std::env::consts::ARCH {
-                    "x86_64" => "amd64",
-                    "aarch64" => "arm64",
-                    arch => arch,
-                };
-
                 // Construct the path to the extension archive
                 // BUILD_TAG/PG_MAJOR_VERSION/extensions/EXTENSION_NAME.tar.zst
                 //
                 // Keep it in sync with path generation in
                 // https://github.com/neondatabase/build-custom-extensions/tree/main
-                let archive_path_str = format!(
-                    "{build_tag}/{arch}/{pg_major_version}/extensions/{real_ext_name}.tar.zst"
-                );
+                let archive_path_str =
+                    format!("{build_tag}/{pg_major_version}/extensions/{real_ext_name}.tar.zst");
                 Ok((
                     real_ext_name.to_string(),
                     RemotePath::from_string(&archive_path_str)?,

libs/http-utils/Cargo.toml

@@ -14,7 +14,6 @@ futures.workspace = true
 hyper0.workspace = true
 itertools.workspace = true
 jemalloc_pprof.workspace = true
-jsonwebtoken.workspace = true
 once_cell.workspace = true
 pprof.workspace = true
 regex.workspace = true

libs/http-utils/src/endpoint.rs

@@ -8,7 +8,6 @@ use bytes::{Bytes, BytesMut};
 use hyper::header::{AUTHORIZATION, CONTENT_DISPOSITION, CONTENT_TYPE, HeaderName};
 use hyper::http::HeaderValue;
 use hyper::{Body, Method, Request, Response};
-use jsonwebtoken::TokenData;
 use metrics::{Encoder, IntCounter, TextEncoder, register_int_counter};
 use once_cell::sync::Lazy;
 use pprof::ProfilerGuardBuilder;
@@ -619,7 +618,7 @@ pub fn auth_middleware<B: hyper::body::HttpBody + Send + Sync + 'static>(
                     })?;
                     let token = parse_token(header_value)?;
 
-                    let data: TokenData<Claims> = auth.decode(token).map_err(|err| {
+                    let data = auth.decode(token).map_err(|err| {
                         warn!("Authentication error: {err}");
                         // Rely on From<AuthError> for ApiError impl
                         err

libs/pageserver_api/Cargo.toml

@@ -35,7 +35,6 @@ nix = {workspace = true, optional = true}
 reqwest.workspace = true
 rand.workspace = true
 tracing-utils.workspace = true
-once_cell.workspace = true
 
 [dev-dependencies]
 bincode.workspace = true

libs/pageserver_api/src/config.rs

@@ -181,7 +181,6 @@ pub struct ConfigToml {
     pub generate_unarchival_heatmap: Option<bool>,
     pub tracing: Option<Tracing>,
     pub enable_tls_page_service_api: bool,
-    pub dev_mode: bool,
 }
 
 #[derive(Debug, Clone, PartialEq, Eq, serde::Serialize, serde::Deserialize)]
@@ -208,10 +207,6 @@ pub struct PageServicePipeliningConfigPipelined {
     /// Causes runtime errors if larger than max get_vectored batch size.
     pub max_batch_size: NonZeroUsize,
     pub execution: PageServiceProtocolPipelinedExecutionStrategy,
-    // The default below is such that new versions of the software can start
-    // with the old configuration.
-    #[serde(default)]
-    pub batching: PageServiceProtocolPipelinedBatchingStrategy,
 }
 
 #[derive(Debug, Clone, Copy, PartialEq, Eq, serde::Serialize, serde::Deserialize)]
@@ -221,19 +216,6 @@ pub enum PageServiceProtocolPipelinedExecutionStrategy {
     Tasks,
 }
 
-#[derive(Default, Debug, Clone, Copy, PartialEq, Eq, serde::Serialize, serde::Deserialize)]
-#[serde(rename_all = "kebab-case")]
-pub enum PageServiceProtocolPipelinedBatchingStrategy {
-    /// All get page requests in a batch will be at the same LSN
-    #[default]
-    UniformLsn,
-    /// Get page requests in a batch may be at different LSN
-    ///
-    /// One key cannot be present more than once at different LSNs in
-    /// the same batch.
-    ScatteredLsn,
-}
-
 #[derive(Debug, Clone, PartialEq, Eq, serde::Serialize, serde::Deserialize)]
 #[serde(tag = "mode", rename_all = "kebab-case")]
 pub enum GetVectoredConcurrentIo {
@@ -380,8 +362,6 @@ pub struct TenantConfigToml {
     /// size exceeds `compaction_upper_limit * checkpoint_distance`.
     pub compaction_upper_limit: usize,
     pub compaction_algorithm: crate::models::CompactionAlgorithmSettings,
-    /// If true, enable shard ancestor compaction (enabled by default).
-    pub compaction_shard_ancestor: bool,
     /// If true, compact down L0 across all tenant timelines before doing regular compaction. L0
     /// compaction must be responsive to avoid read amp during heavy ingestion. Defaults to true.
     pub compaction_l0_first: bool,
@@ -472,8 +452,6 @@ pub struct TenantConfigToml {
     // gc-compaction related configs
     /// Enable automatic gc-compaction trigger on this tenant.
     pub gc_compaction_enabled: bool,
-    /// Enable verification of gc-compaction results.
-    pub gc_compaction_verification: bool,
     /// The initial threshold for gc-compaction in KB. Once the total size of layers below the gc-horizon is above this threshold,
     /// gc-compaction will be triggered.
     pub gc_compaction_initial_threshold_kb: u64,
@@ -635,12 +613,9 @@ impl Default for ConfigToml {
             page_service_pipelining: if !cfg!(test) {
                 PageServicePipeliningConfig::Serial
             } else {
-                // Do not turn this into the default until scattered reads have been
-                // validated and rolled-out fully.
                 PageServicePipeliningConfig::Pipelined(PageServicePipeliningConfigPipelined {
                     max_batch_size: NonZeroUsize::new(32).unwrap(),
                     execution: PageServiceProtocolPipelinedExecutionStrategy::ConcurrentFutures,
-                    batching: PageServiceProtocolPipelinedBatchingStrategy::ScatteredLsn,
                 })
             },
             get_vectored_concurrent_io: if !cfg!(test) {
@@ -658,7 +633,6 @@ impl Default for ConfigToml {
             generate_unarchival_heatmap: None,
             tracing: None,
             enable_tls_page_service_api: false,
-            dev_mode: false,
         }
     }
 }
@@ -681,13 +655,12 @@ pub mod tenant_conf_defaults {
 
     pub const DEFAULT_COMPACTION_PERIOD: &str = "20 s";
     pub const DEFAULT_COMPACTION_THRESHOLD: usize = 10;
-    pub const DEFAULT_COMPACTION_SHARD_ANCESTOR: bool = true;
 
     // This value needs to be tuned to avoid OOM. We have 3/4*CPUs threads for L0 compaction, that's
-    // 3/4*8=6 on most of our pageservers. Compacting 10 layers requires a maximum of
-    // DEFAULT_CHECKPOINT_DISTANCE*10 memory, that's 2560MB. So with this config, we can get a maximum peak
-    // compaction usage of 15360MB.
-    pub const DEFAULT_COMPACTION_UPPER_LIMIT: usize = 10;
+    // 3/4*16=9 on most of our pageservers. Compacting 20 layers requires about 1 GB memory (could
+    // be reduced later by optimizing L0 hole calculation to avoid loading all keys into memory). So
+    // with this config, we can get a maximum peak compaction usage of 9 GB.
+    pub const DEFAULT_COMPACTION_UPPER_LIMIT: usize = 20;
     // Enable L0 compaction pass and semaphore by default. L0 compaction must be responsive to avoid
     // read amp.
     pub const DEFAULT_COMPACTION_L0_FIRST: bool = true;
@@ -704,11 +677,8 @@ pub mod tenant_conf_defaults {
     // Relevant: https://github.com/neondatabase/neon/issues/3394
     pub const DEFAULT_GC_PERIOD: &str = "1 hr";
     pub const DEFAULT_IMAGE_CREATION_THRESHOLD: usize = 3;
-    // Currently, any value other than 0 will trigger image layer creation preemption immediately with L0 backpressure
-    // without looking at the exact number of L0 layers.
-    // It was expected to have the following behavior:
-    // > If there are more than threshold * compaction_threshold (that is 3 * 10 in the default config) L0 layers, image
-    // > layer creation will end immediately. Set to 0 to disable.
+    // If there are more than threshold * compaction_threshold (that is 3 * 10 in the default config) L0 layers, image
+    // layer creation will end immediately. Set to 0 to disable.
     pub const DEFAULT_IMAGE_CREATION_PREEMPT_THRESHOLD: usize = 3;
     pub const DEFAULT_PITR_INTERVAL: &str = "7 days";
     pub const DEFAULT_WALRECEIVER_CONNECT_TIMEOUT: &str = "10 seconds";
@@ -722,7 +692,6 @@ pub mod tenant_conf_defaults {
     // image layers should be created.
     pub const DEFAULT_IMAGE_LAYER_CREATION_CHECK_THRESHOLD: u8 = 2;
     pub const DEFAULT_GC_COMPACTION_ENABLED: bool = false;
-    pub const DEFAULT_GC_COMPACTION_VERIFICATION: bool = true;
     pub const DEFAULT_GC_COMPACTION_INITIAL_THRESHOLD_KB: u64 = 5 * 1024 * 1024; // 5GB
     pub const DEFAULT_GC_COMPACTION_RATIO_PERCENT: u64 = 100;
 }
@@ -742,7 +711,6 @@ impl Default for TenantConfigToml {
             compaction_algorithm: crate::models::CompactionAlgorithmSettings {
                 kind: DEFAULT_COMPACTION_ALGORITHM,
             },
-            compaction_shard_ancestor: DEFAULT_COMPACTION_SHARD_ANCESTOR,
             compaction_l0_first: DEFAULT_COMPACTION_L0_FIRST,
             compaction_l0_semaphore: DEFAULT_COMPACTION_L0_SEMAPHORE,
             l0_flush_delay_threshold: None,
@@ -778,7 +746,6 @@ impl Default for TenantConfigToml {
             wal_receiver_protocol_override: None,
             rel_size_v2_enabled: false,
             gc_compaction_enabled: DEFAULT_GC_COMPACTION_ENABLED,
-            gc_compaction_verification: DEFAULT_GC_COMPACTION_VERIFICATION,
             gc_compaction_initial_threshold_kb: DEFAULT_GC_COMPACTION_INITIAL_THRESHOLD_KB,
             gc_compaction_ratio_percent: DEFAULT_GC_COMPACTION_RATIO_PERCENT,
             sampling_ratio: None,

libs/pageserver_api/src/models.rs

@@ -320,35 +320,6 @@ pub struct TimelineCreateRequest {
     pub mode: TimelineCreateRequestMode,
 }
 
-impl TimelineCreateRequest {
-    pub fn mode_tag(&self) -> &'static str {
-        match &self.mode {
-            TimelineCreateRequestMode::Branch { .. } => "branch",
-            TimelineCreateRequestMode::ImportPgdata { .. } => "import",
-            TimelineCreateRequestMode::Bootstrap { .. } => "bootstrap",
-        }
-    }
-
-    pub fn is_import(&self) -> bool {
-        matches!(self.mode, TimelineCreateRequestMode::ImportPgdata { .. })
-    }
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Eq)]
-pub enum ShardImportStatus {
-    InProgress,
-    Done,
-    Error(String),
-}
-impl ShardImportStatus {
-    pub fn is_terminal(&self) -> bool {
-        match self {
-            ShardImportStatus::InProgress => false,
-            ShardImportStatus::Done | ShardImportStatus::Error(_) => true,
-        }
-    }
-}
-
 /// Storage controller specific extensions to [`TimelineInfo`].
 #[derive(Serialize, Deserialize, Clone)]
 pub struct TimelineCreateResponseStorcon {
@@ -555,8 +526,6 @@ pub struct TenantConfigPatch {
     #[serde(skip_serializing_if = "FieldPatch::is_noop")]
     pub compaction_algorithm: FieldPatch<CompactionAlgorithmSettings>,
     #[serde(skip_serializing_if = "FieldPatch::is_noop")]
-    pub compaction_shard_ancestor: FieldPatch<bool>,
-    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
     pub compaction_l0_first: FieldPatch<bool>,
     #[serde(skip_serializing_if = "FieldPatch::is_noop")]
     pub compaction_l0_semaphore: FieldPatch<bool>,
@@ -607,8 +576,6 @@ pub struct TenantConfigPatch {
     #[serde(skip_serializing_if = "FieldPatch::is_noop")]
     pub gc_compaction_enabled: FieldPatch<bool>,
     #[serde(skip_serializing_if = "FieldPatch::is_noop")]
-    pub gc_compaction_verification: FieldPatch<bool>,
-    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
     pub gc_compaction_initial_threshold_kb: FieldPatch<u64>,
     #[serde(skip_serializing_if = "FieldPatch::is_noop")]
     pub gc_compaction_ratio_percent: FieldPatch<u64>,
@@ -646,9 +613,6 @@ pub struct TenantConfig {
     #[serde(skip_serializing_if = "Option::is_none")]
     pub compaction_algorithm: Option<CompactionAlgorithmSettings>,
 
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub compaction_shard_ancestor: Option<bool>,
-
     #[serde(skip_serializing_if = "Option::is_none")]
     pub compaction_l0_first: Option<bool>,
 
@@ -732,9 +696,6 @@ pub struct TenantConfig {
     #[serde(skip_serializing_if = "Option::is_none")]
     pub gc_compaction_enabled: Option<bool>,
 
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub gc_compaction_verification: Option<bool>,
-
     #[serde(skip_serializing_if = "Option::is_none")]
     pub gc_compaction_initial_threshold_kb: Option<u64>,
 
@@ -758,7 +719,6 @@ impl TenantConfig {
             mut compaction_threshold,
             mut compaction_upper_limit,
             mut compaction_algorithm,
-            mut compaction_shard_ancestor,
             mut compaction_l0_first,
             mut compaction_l0_semaphore,
             mut l0_flush_delay_threshold,
@@ -784,7 +744,6 @@ impl TenantConfig {
             mut wal_receiver_protocol_override,
             mut rel_size_v2_enabled,
             mut gc_compaction_enabled,
-            mut gc_compaction_verification,
             mut gc_compaction_initial_threshold_kb,
             mut gc_compaction_ratio_percent,
             mut sampling_ratio,
@@ -807,9 +766,6 @@ impl TenantConfig {
             .compaction_upper_limit
             .apply(&mut compaction_upper_limit);
         patch.compaction_algorithm.apply(&mut compaction_algorithm);
-        patch
-            .compaction_shard_ancestor
-            .apply(&mut compaction_shard_ancestor);
         patch.compaction_l0_first.apply(&mut compaction_l0_first);
         patch
             .compaction_l0_semaphore
@@ -879,9 +835,6 @@ impl TenantConfig {
         patch
             .gc_compaction_enabled
             .apply(&mut gc_compaction_enabled);
-        patch
-            .gc_compaction_verification
-            .apply(&mut gc_compaction_verification);
         patch
             .gc_compaction_initial_threshold_kb
             .apply(&mut gc_compaction_initial_threshold_kb);
@@ -898,7 +851,6 @@ impl TenantConfig {
             compaction_threshold,
             compaction_upper_limit,
             compaction_algorithm,
-            compaction_shard_ancestor,
             compaction_l0_first,
             compaction_l0_semaphore,
             l0_flush_delay_threshold,
@@ -924,7 +876,6 @@ impl TenantConfig {
             wal_receiver_protocol_override,
             rel_size_v2_enabled,
             gc_compaction_enabled,
-            gc_compaction_verification,
             gc_compaction_initial_threshold_kb,
             gc_compaction_ratio_percent,
             sampling_ratio,
@@ -959,9 +910,6 @@ impl TenantConfig {
                 .as_ref()
                 .unwrap_or(&global_conf.compaction_algorithm)
                 .clone(),
-            compaction_shard_ancestor: self
-                .compaction_shard_ancestor
-                .unwrap_or(global_conf.compaction_shard_ancestor),
             compaction_l0_first: self
                 .compaction_l0_first
                 .unwrap_or(global_conf.compaction_l0_first),
@@ -1026,9 +974,6 @@ impl TenantConfig {
             gc_compaction_enabled: self
                 .gc_compaction_enabled
                 .unwrap_or(global_conf.gc_compaction_enabled),
-            gc_compaction_verification: self
-                .gc_compaction_verification
-                .unwrap_or(global_conf.gc_compaction_verification),
             gc_compaction_initial_threshold_kb: self
                 .gc_compaction_initial_threshold_kb
                 .unwrap_or(global_conf.gc_compaction_initial_threshold_kb),
@@ -1803,8 +1748,6 @@ pub struct TopTenantShardsResponse {
 }
 
 pub mod virtual_file {
-    use std::sync::LazyLock;
-
     #[derive(
         Copy,
         Clone,
@@ -1842,38 +1785,14 @@ pub mod virtual_file {
     pub enum IoMode {
         /// Uses buffered IO.
         Buffered,
-        /// Uses direct IO for reads only.
+        /// Uses direct IO, error out if the operation fails.
         #[cfg(target_os = "linux")]
         Direct,
-        /// Use direct IO for reads and writes.
-        #[cfg(target_os = "linux")]
-        DirectRw,
     }
 
     impl IoMode {
-        pub fn preferred() -> Self {
-            // The default behavior when running Rust unit tests without any further
-            // flags is to use the newest behavior (DirectRw).
-            // The CI uses the following environment variable to unit tests for all
-            // different modes.
-            // NB: the Python regression & perf tests have their own defaults management
-            // that writes pageserver.toml; they do not use this variable.
-            if cfg!(test) {
-                static CACHED: LazyLock<IoMode> = LazyLock::new(|| {
-                    utils::env::var_serde_json_string(
-                        "NEON_PAGESERVER_UNIT_TEST_VIRTUAL_FILE_IO_MODE",
-                    )
-                    .unwrap_or(
-                        #[cfg(target_os = "linux")]
-                        IoMode::DirectRw,
-                        #[cfg(not(target_os = "linux"))]
-                        IoMode::Buffered,
-                    )
-                });
-                *CACHED
-            } else {
-                IoMode::Buffered
-            }
+        pub const fn preferred() -> Self {
+            Self::Buffered
         }
     }
 
@@ -1885,8 +1804,6 @@ pub mod virtual_file {
                 v if v == (IoMode::Buffered as u8) => IoMode::Buffered,
                 #[cfg(target_os = "linux")]
                 v if v == (IoMode::Direct as u8) => IoMode::Direct,
-                #[cfg(target_os = "linux")]
-                v if v == (IoMode::DirectRw as u8) => IoMode::DirectRw,
                 x => return Err(x),
             })
         }

libs/pageserver_api/src/upcall_api.rs

@@ -4,10 +4,10 @@
 //! See docs/rfcs/025-generation-numbers.md
 
 use serde::{Deserialize, Serialize};
-use utils::id::{NodeId, TimelineId};
+use utils::id::NodeId;
 
 use crate::controller_api::NodeRegisterRequest;
-use crate::models::{LocationConfigMode, ShardImportStatus};
+use crate::models::LocationConfigMode;
 use crate::shard::TenantShardId;
 
 /// Upcall message sent by the pageserver to the configured `control_plane_api` on
@@ -62,10 +62,3 @@ pub struct ValidateResponseTenant {
     pub id: TenantShardId,
     pub valid: bool,
 }
-
-#[derive(Serialize, Deserialize)]
-pub struct PutTimelineImportStatusRequest {
-    pub tenant_shard_id: TenantShardId,
-    pub timeline_id: TimelineId,
-    pub status: ShardImportStatus,
-}

libs/remote_storage/src/azure_blob.rs

@@ -14,9 +14,8 @@ use anyhow::{Context, Result};
 use azure_core::request_options::{IfMatchCondition, MaxResults, Metadata, Range};
 use azure_core::{Continuable, HttpClient, RetryOptions, TransportOptions};
 use azure_storage::StorageCredentials;
+use azure_storage_blobs::blob::CopyStatus;
 use azure_storage_blobs::blob::operations::GetBlobBuilder;
-use azure_storage_blobs::blob::{Blob, CopyStatus};
-use azure_storage_blobs::container::operations::ListBlobsBuilder;
 use azure_storage_blobs::prelude::{ClientBuilder, ContainerClient};
 use bytes::Bytes;
 use futures::FutureExt;
@@ -254,15 +253,53 @@ impl AzureBlobStorage {
         download
     }
 
-    fn list_streaming_for_fn<T: Default + ListingCollector>(
+    async fn permit(
+        &self,
+        kind: RequestKind,
+        cancel: &CancellationToken,
+    ) -> Result<tokio::sync::SemaphorePermit<'_>, Cancelled> {
+        let acquire = self.concurrency_limiter.acquire(kind);
+
+        tokio::select! {
+            permit = acquire => Ok(permit.expect("never closed")),
+            _ = cancel.cancelled() => Err(Cancelled),
+        }
+    }
+
+    pub fn container_name(&self) -> &str {
+        &self.container_name
+    }
+}
+
+fn to_azure_metadata(metadata: StorageMetadata) -> Metadata {
+    let mut res = Metadata::new();
+    for (k, v) in metadata.0.into_iter() {
+        res.insert(k, v);
+    }
+    res
+}
+
+fn to_download_error(error: azure_core::Error) -> DownloadError {
+    if let Some(http_err) = error.as_http_error() {
+        match http_err.status() {
+            StatusCode::NotFound => DownloadError::NotFound,
+            StatusCode::NotModified => DownloadError::Unmodified,
+            StatusCode::BadRequest => DownloadError::BadInput(anyhow::Error::new(error)),
+            _ => DownloadError::Other(anyhow::Error::new(error)),
+        }
+    } else {
+        DownloadError::Other(error.into())
+    }
+}
+
+impl RemoteStorage for AzureBlobStorage {
+    fn list_streaming(
         &self,
         prefix: Option<&RemotePath>,
         mode: ListingMode,
         max_keys: Option<NonZeroU32>,
         cancel: &CancellationToken,
-        request_kind: RequestKind,
-        customize_builder: impl Fn(ListBlobsBuilder) -> ListBlobsBuilder,
-    ) -> impl Stream<Item = Result<T, DownloadError>> {
+    ) -> impl Stream<Item = Result<Listing, DownloadError>> {
         // get the passed prefix or if it is not set use prefix_in_bucket value
         let list_prefix = prefix.map(|p| self.relative_path_to_name(p)).or_else(|| {
             self.prefix_in_container.clone().map(|mut s| {
@@ -274,7 +311,7 @@ impl AzureBlobStorage {
         });
 
         async_stream::stream! {
-            let _permit = self.permit(request_kind, cancel).await?;
+            let _permit = self.permit(RequestKind::List, cancel).await?;
 
             let mut builder = self.client.list_blobs();
 
@@ -290,8 +327,6 @@ impl AzureBlobStorage {
                 builder = builder.max_results(MaxResults::new(limit));
             }
 
-            builder = customize_builder(builder);
-
             let mut next_marker = None;
 
             let mut timeout_try_cnt = 1;
@@ -347,20 +382,26 @@ impl AzureBlobStorage {
                     break;
                 };
 
-                let mut res = T::default();
+                let mut res = Listing::default();
                 next_marker = entry.continuation();
                 let prefix_iter = entry
                     .blobs
                     .prefixes()
                     .map(|prefix| self.name_to_relative_path(&prefix.name));
-                res.add_prefixes(self, prefix_iter);
+                res.prefixes.extend(prefix_iter);
 
                 let blob_iter = entry
                     .blobs
-                    .blobs();
+                    .blobs()
+                    .map(|k| ListingObject{
+                        key: self.name_to_relative_path(&k.name),
+                        last_modified: k.properties.last_modified.into(),
+                        size: k.properties.content_length,
+                    }
+                );
 
                 for key in blob_iter {
-                    res.add_blob(self, key);
+                    res.keys.push(key);
 
                     if let Some(mut mk) = max_keys {
                         assert!(mk > 0);
@@ -382,128 +423,6 @@ impl AzureBlobStorage {
         }
     }
 
-    async fn permit(
-        &self,
-        kind: RequestKind,
-        cancel: &CancellationToken,
-    ) -> Result<tokio::sync::SemaphorePermit<'_>, Cancelled> {
-        let acquire = self.concurrency_limiter.acquire(kind);
-
-        tokio::select! {
-            permit = acquire => Ok(permit.expect("never closed")),
-            _ = cancel.cancelled() => Err(Cancelled),
-        }
-    }
-
-    pub fn container_name(&self) -> &str {
-        &self.container_name
-    }
-}
-
-trait ListingCollector {
-    fn add_prefixes(&mut self, abs: &AzureBlobStorage, prefix_it: impl Iterator<Item = RemotePath>);
-    fn add_blob(&mut self, abs: &AzureBlobStorage, blob: &Blob);
-}
-
-impl ListingCollector for Listing {
-    fn add_prefixes(
-        &mut self,
-        _abs: &AzureBlobStorage,
-        prefix_it: impl Iterator<Item = RemotePath>,
-    ) {
-        self.prefixes.extend(prefix_it);
-    }
-    fn add_blob(&mut self, abs: &AzureBlobStorage, blob: &Blob) {
-        self.keys.push(ListingObject {
-            key: abs.name_to_relative_path(&blob.name),
-            last_modified: blob.properties.last_modified.into(),
-            size: blob.properties.content_length,
-        });
-    }
-}
-
-impl ListingCollector for crate::VersionListing {
-    fn add_prefixes(
-        &mut self,
-        _abs: &AzureBlobStorage,
-        _prefix_it: impl Iterator<Item = RemotePath>,
-    ) {
-        // nothing
-    }
-    fn add_blob(&mut self, abs: &AzureBlobStorage, blob: &Blob) {
-        let id = crate::VersionId(blob.version_id.clone().expect("didn't find version ID"));
-        self.versions.push(crate::Version {
-            key: abs.name_to_relative_path(&blob.name),
-            last_modified: blob.properties.last_modified.into(),
-            kind: crate::VersionKind::Version(id),
-        });
-    }
-}
-
-fn to_azure_metadata(metadata: StorageMetadata) -> Metadata {
-    let mut res = Metadata::new();
-    for (k, v) in metadata.0.into_iter() {
-        res.insert(k, v);
-    }
-    res
-}
-
-fn to_download_error(error: azure_core::Error) -> DownloadError {
-    if let Some(http_err) = error.as_http_error() {
-        match http_err.status() {
-            StatusCode::NotFound => DownloadError::NotFound,
-            StatusCode::NotModified => DownloadError::Unmodified,
-            StatusCode::BadRequest => DownloadError::BadInput(anyhow::Error::new(error)),
-            _ => DownloadError::Other(anyhow::Error::new(error)),
-        }
-    } else {
-        DownloadError::Other(error.into())
-    }
-}
-
-impl RemoteStorage for AzureBlobStorage {
-    fn list_streaming(
-        &self,
-        prefix: Option<&RemotePath>,
-        mode: ListingMode,
-        max_keys: Option<NonZeroU32>,
-        cancel: &CancellationToken,
-    ) -> impl Stream<Item = Result<Listing, DownloadError>> {
-        let customize_builder = |builder| builder;
-        let kind = RequestKind::ListVersions;
-        self.list_streaming_for_fn(prefix, mode, max_keys, cancel, kind, customize_builder)
-    }
-
-    async fn list_versions(
-        &self,
-        prefix: Option<&RemotePath>,
-        mode: ListingMode,
-        max_keys: Option<NonZeroU32>,
-        cancel: &CancellationToken,
-    ) -> std::result::Result<crate::VersionListing, DownloadError> {
-        let customize_builder = |mut builder: ListBlobsBuilder| {
-            builder = builder.include_versions(true);
-            builder
-        };
-        let kind = RequestKind::ListVersions;
-
-        let mut stream = std::pin::pin!(self.list_streaming_for_fn(
-            prefix,
-            mode,
-            max_keys,
-            cancel,
-            kind,
-            customize_builder
-        ));
-        let mut combined: crate::VersionListing =
-            stream.next().await.expect("At least one item required")?;
-        while let Some(list) = stream.next().await {
-            let list = list?;
-            combined.versions.extend(list.versions.into_iter());
-        }
-        Ok(combined)
-    }
-
     async fn head_object(
         &self,
         key: &RemotePath,
@@ -613,12 +532,7 @@ impl RemoteStorage for AzureBlobStorage {
         let mut builder = blob_client.get();
 
         if let Some(ref etag) = opts.etag {
-            builder = builder.if_match(IfMatchCondition::NotMatch(etag.to_string()));
-        }
-
-        if let Some(ref version_id) = opts.version_id {
-            let version_id = azure_storage_blobs::prelude::VersionId::new(version_id.0.clone());
-            builder = builder.blob_versioning(version_id);
+            builder = builder.if_match(IfMatchCondition::NotMatch(etag.to_string()))
         }
 
         if let Some((start, end)) = opts.byte_range() {

libs/remote_storage/src/lib.rs

@@ -176,32 +176,6 @@ pub struct Listing {
     pub keys: Vec<ListingObject>,
 }
 
-#[derive(Default)]
-pub struct VersionListing {
-    pub versions: Vec<Version>,
-}
-
-pub struct Version {
-    pub key: RemotePath,
-    pub last_modified: SystemTime,
-    pub kind: VersionKind,
-}
-
-impl Version {
-    pub fn version_id(&self) -> Option<&VersionId> {
-        match &self.kind {
-            VersionKind::Version(id) => Some(id),
-            VersionKind::DeletionMarker => None,
-        }
-    }
-}
-
-#[derive(Debug)]
-pub enum VersionKind {
-    DeletionMarker,
-    Version(VersionId),
-}
-
 /// Options for downloads. The default value is a plain GET.
 pub struct DownloadOpts {
     /// If given, returns [`DownloadError::Unmodified`] if the object still has
@@ -212,8 +186,6 @@ pub struct DownloadOpts {
     /// The end of the byte range to download, or unbounded. Must be after the
     /// start bound.
     pub byte_end: Bound<u64>,
-    /// Optionally request a specific version of a key
-    pub version_id: Option<VersionId>,
     /// Indicate whether we're downloading something small or large: this indirectly controls
     /// timeouts: for something like an index/manifest/heatmap, we should time out faster than
     /// for layer files
@@ -225,16 +197,12 @@ pub enum DownloadKind {
     Small,
 }
 
-#[derive(Debug, Clone)]
-pub struct VersionId(pub String);
-
 impl Default for DownloadOpts {
     fn default() -> Self {
         Self {
             etag: Default::default(),
             byte_start: Bound::Unbounded,
             byte_end: Bound::Unbounded,
-            version_id: None,
             kind: DownloadKind::Large,
         }
     }
@@ -327,14 +295,6 @@ pub trait RemoteStorage: Send + Sync + 'static {
         Ok(combined)
     }
 
-    async fn list_versions(
-        &self,
-        prefix: Option<&RemotePath>,
-        mode: ListingMode,
-        max_keys: Option<NonZeroU32>,
-        cancel: &CancellationToken,
-    ) -> Result<VersionListing, DownloadError>;
-
     /// Obtain metadata information about an object.
     async fn head_object(
         &self,
@@ -515,22 +475,6 @@ impl<Other: RemoteStorage> GenericRemoteStorage<Arc<Other>> {
         }
     }
 
-    // See [`RemoteStorage::list_versions`].
-    pub async fn list_versions<'a>(
-        &'a self,
-        prefix: Option<&'a RemotePath>,
-        mode: ListingMode,
-        max_keys: Option<NonZeroU32>,
-        cancel: &'a CancellationToken,
-    ) -> Result<VersionListing, DownloadError> {
-        match self {
-            Self::LocalFs(s) => s.list_versions(prefix, mode, max_keys, cancel).await,
-            Self::AwsS3(s) => s.list_versions(prefix, mode, max_keys, cancel).await,
-            Self::AzureBlob(s) => s.list_versions(prefix, mode, max_keys, cancel).await,
-            Self::Unreliable(s) => s.list_versions(prefix, mode, max_keys, cancel).await,
-        }
-    }
-
     // See [`RemoteStorage::head_object`].
     pub async fn head_object(
         &self,
@@ -783,7 +727,6 @@ impl ConcurrencyLimiter {
             RequestKind::Copy => &self.write,
             RequestKind::TimeTravel => &self.write,
             RequestKind::Head => &self.read,
-            RequestKind::ListVersions => &self.read,
         }
     }
 

libs/remote_storage/src/local_fs.rs

@@ -445,16 +445,6 @@ impl RemoteStorage for LocalFs {
         }
     }
 
-    async fn list_versions(
-        &self,
-        _prefix: Option<&RemotePath>,
-        _mode: ListingMode,
-        _max_keys: Option<NonZeroU32>,
-        _cancel: &CancellationToken,
-    ) -> Result<crate::VersionListing, DownloadError> {
-        unimplemented!()
-    }
-
     async fn head_object(
         &self,
         key: &RemotePath,

libs/remote_storage/src/metrics.rs

@@ -14,7 +14,6 @@ pub(crate) enum RequestKind {
     Copy = 4,
     TimeTravel = 5,
     Head = 6,
-    ListVersions = 7,
 }
 
 use RequestKind::*;
@@ -30,7 +29,6 @@ impl RequestKind {
             Copy => "copy_object",
             TimeTravel => "time_travel_recover",
             Head => "head_object",
-            ListVersions => "list_versions",
         }
     }
     const fn as_index(&self) -> usize {
@@ -38,10 +36,7 @@ impl RequestKind {
     }
 }
 
-const REQUEST_KIND_LIST: &[RequestKind] =
-    &[Get, Put, Delete, List, Copy, TimeTravel, Head, ListVersions];
-
-const REQUEST_KIND_COUNT: usize = REQUEST_KIND_LIST.len();
+const REQUEST_KIND_COUNT: usize = 7;
 pub(crate) struct RequestTyped<C>([C; REQUEST_KIND_COUNT]);
 
 impl<C> RequestTyped<C> {
@@ -50,11 +45,12 @@ impl<C> RequestTyped<C> {
     }
 
     fn build_with(mut f: impl FnMut(RequestKind) -> C) -> Self {
-        let mut it = REQUEST_KIND_LIST.iter();
+        use RequestKind::*;
+        let mut it = [Get, Put, Delete, List, Copy, TimeTravel, Head].into_iter();
         let arr = std::array::from_fn::<C, REQUEST_KIND_COUNT, _>(|index| {
             let next = it.next().unwrap();
             assert_eq!(index, next.as_index());
-            f(*next)
+            f(next)
         });
 
         if let Some(next) = it.next() {

libs/remote_storage/src/s3_bucket.rs

@@ -21,8 +21,9 @@ use aws_sdk_s3::config::{AsyncSleep, IdentityCache, Region, SharedAsyncSleep};
 use aws_sdk_s3::error::SdkError;
 use aws_sdk_s3::operation::get_object::GetObjectError;
 use aws_sdk_s3::operation::head_object::HeadObjectError;
-use aws_sdk_s3::types::{Delete, ObjectIdentifier, StorageClass};
+use aws_sdk_s3::types::{Delete, DeleteMarkerEntry, ObjectIdentifier, ObjectVersion, StorageClass};
 use aws_smithy_async::rt::sleep::TokioSleep;
+use aws_smithy_types::DateTime;
 use aws_smithy_types::body::SdkBody;
 use aws_smithy_types::byte_stream::ByteStream;
 use aws_smithy_types::date_time::ConversionError;
@@ -45,7 +46,7 @@ use crate::support::PermitCarrying;
 use crate::{
     ConcurrencyLimiter, Download, DownloadError, DownloadOpts, Listing, ListingMode, ListingObject,
     MAX_KEYS_PER_DELETE_S3, REMOTE_STORAGE_PREFIX_SEPARATOR, RemotePath, RemoteStorage,
-    TimeTravelError, TimeoutOrCancel, Version, VersionId, VersionKind, VersionListing,
+    TimeTravelError, TimeoutOrCancel,
 };
 
 /// AWS S3 storage.
@@ -65,7 +66,6 @@ struct GetObjectRequest {
     key: String,
     etag: Option<String>,
     range: Option<String>,
-    version_id: Option<String>,
 }
 impl S3Bucket {
     /// Creates the S3 storage, errors if incorrect AWS S3 configuration provided.
@@ -251,7 +251,6 @@ impl S3Bucket {
             .get_object()
             .bucket(request.bucket)
             .key(request.key)
-            .set_version_id(request.version_id)
             .set_range(request.range);
 
         if let Some(etag) = request.etag {
@@ -406,124 +405,6 @@ impl S3Bucket {
         Ok(())
     }
 
-    async fn list_versions_with_permit(
-        &self,
-        _permit: &tokio::sync::SemaphorePermit<'_>,
-        prefix: Option<&RemotePath>,
-        mode: ListingMode,
-        max_keys: Option<NonZeroU32>,
-        cancel: &CancellationToken,
-    ) -> Result<crate::VersionListing, DownloadError> {
-        // get the passed prefix or if it is not set use prefix_in_bucket value
-        let prefix = prefix
-            .map(|p| self.relative_path_to_s3_object(p))
-            .or_else(|| self.prefix_in_bucket.clone());
-
-        let warn_threshold = 3;
-        let max_retries = 10;
-        let is_permanent = |e: &_| matches!(e, DownloadError::Cancelled);
-
-        let mut key_marker = None;
-        let mut version_id_marker = None;
-        let mut versions_and_deletes = Vec::new();
-
-        loop {
-            let response = backoff::retry(
-                || async {
-                    let mut request = self
-                        .client
-                        .list_object_versions()
-                        .bucket(self.bucket_name.clone())
-                        .set_prefix(prefix.clone())
-                        .set_key_marker(key_marker.clone())
-                        .set_version_id_marker(version_id_marker.clone());
-
-                    if let ListingMode::WithDelimiter = mode {
-                        request = request.delimiter(REMOTE_STORAGE_PREFIX_SEPARATOR.to_string());
-                    }
-
-                    let op = request.send();
-
-                    tokio::select! {
-                        res = op => res.map_err(|e| DownloadError::Other(e.into())),
-                        _ = cancel.cancelled() => Err(DownloadError::Cancelled),
-                    }
-                },
-                is_permanent,
-                warn_threshold,
-                max_retries,
-                "listing object versions",
-                cancel,
-            )
-            .await
-            .ok_or_else(|| DownloadError::Cancelled)
-            .and_then(|x| x)?;
-
-            tracing::trace!(
-                "  Got List response version_id_marker={:?}, key_marker={:?}",
-                response.version_id_marker,
-                response.key_marker
-            );
-            let versions = response
-                .versions
-                .unwrap_or_default()
-                .into_iter()
-                .map(|version| {
-                    let key = version.key.expect("response does not contain a key");
-                    let key = self.s3_object_to_relative_path(&key);
-                    let version_id = VersionId(version.version_id.expect("needing version id"));
-                    let last_modified =
-                        SystemTime::try_from(version.last_modified.expect("no last_modified"))?;
-                    Ok(Version {
-                        key,
-                        last_modified,
-                        kind: crate::VersionKind::Version(version_id),
-                    })
-                });
-            let deletes = response
-                .delete_markers
-                .unwrap_or_default()
-                .into_iter()
-                .map(|version| {
-                    let key = version.key.expect("response does not contain a key");
-                    let key = self.s3_object_to_relative_path(&key);
-                    let last_modified =
-                        SystemTime::try_from(version.last_modified.expect("no last_modified"))?;
-                    Ok(Version {
-                        key,
-                        last_modified,
-                        kind: crate::VersionKind::DeletionMarker,
-                    })
-                });
-            itertools::process_results(versions.chain(deletes), |n_vds| {
-                versions_and_deletes.extend(n_vds)
-            })
-            .map_err(DownloadError::Other)?;
-            fn none_if_empty(v: Option<String>) -> Option<String> {
-                v.filter(|v| !v.is_empty())
-            }
-            version_id_marker = none_if_empty(response.next_version_id_marker);
-            key_marker = none_if_empty(response.next_key_marker);
-            if version_id_marker.is_none() {
-                // The final response is not supposed to be truncated
-                if response.is_truncated.unwrap_or_default() {
-                    return Err(DownloadError::Other(anyhow::anyhow!(
-                        "Received truncated ListObjectVersions response for prefix={prefix:?}"
-                    )));
-                }
-                break;
-            }
-            if let Some(max_keys) = max_keys {
-                if versions_and_deletes.len() >= max_keys.get().try_into().unwrap() {
-                    return Err(DownloadError::Other(anyhow::anyhow!("too many versions")));
-                }
-            }
-        }
-        Ok(VersionListing {
-            versions: versions_and_deletes,
-        })
-    }
-
     pub fn bucket_name(&self) -> &str {
         &self.bucket_name
     }
@@ -740,19 +621,6 @@ impl RemoteStorage for S3Bucket {
         }
     }
 
-    async fn list_versions(
-        &self,
-        prefix: Option<&RemotePath>,
-        mode: ListingMode,
-        max_keys: Option<NonZeroU32>,
-        cancel: &CancellationToken,
-    ) -> Result<crate::VersionListing, DownloadError> {
-        let kind = RequestKind::ListVersions;
-        let permit = self.permit(kind, cancel).await?;
-        self.list_versions_with_permit(&permit, prefix, mode, max_keys, cancel)
-            .await
-    }
-
     async fn head_object(
         &self,
         key: &RemotePath,
@@ -933,7 +801,6 @@ impl RemoteStorage for S3Bucket {
                 key: self.relative_path_to_s3_object(from),
                 etag: opts.etag.as_ref().map(|e| e.to_string()),
                 range: opts.byte_range_header(),
-                version_id: opts.version_id.as_ref().map(|v| v.0.to_owned()),
             },
             cancel,
         )
@@ -978,25 +845,94 @@ impl RemoteStorage for S3Bucket {
         let kind = RequestKind::TimeTravel;
         let permit = self.permit(kind, cancel).await?;
 
+        let timestamp = DateTime::from(timestamp);
+        let done_if_after = DateTime::from(done_if_after);
+
         tracing::trace!("Target time: {timestamp:?}, done_if_after {done_if_after:?}");
 
-        // Limit the number of versions deletions, mostly so that we don't
-        // keep requesting forever if the list is too long, as we'd put the
-        // list in RAM.
-        // Building a list of 100k entries that reaches the limit roughly takes
-        // 40 seconds, and roughly corresponds to tenants of 2 TiB physical size.
-        const COMPLEXITY_LIMIT: Option<NonZeroU32> = NonZeroU32::new(100_000);
+        // get the passed prefix or if it is not set use prefix_in_bucket value
+        let prefix = prefix
+            .map(|p| self.relative_path_to_s3_object(p))
+            .or_else(|| self.prefix_in_bucket.clone());
 
-        let mode = ListingMode::NoDelimiter;
-        let version_listing = self
-            .list_versions_with_permit(&permit, prefix, mode, COMPLEXITY_LIMIT, cancel)
+        let warn_threshold = 3;
+        let max_retries = 10;
+        let is_permanent = |e: &_| matches!(e, TimeTravelError::Cancelled);
+
+        let mut key_marker = None;
+        let mut version_id_marker = None;
+        let mut versions_and_deletes = Vec::new();
+
+        loop {
+            let response = backoff::retry(
+                || async {
+                    let op = self
+                        .client
+                        .list_object_versions()
+                        .bucket(self.bucket_name.clone())
+                        .set_prefix(prefix.clone())
+                        .set_key_marker(key_marker.clone())
+                        .set_version_id_marker(version_id_marker.clone())
+                        .send();
+
+                    tokio::select! {
+                        res = op => res.map_err(|e| TimeTravelError::Other(e.into())),
+                        _ = cancel.cancelled() => Err(TimeTravelError::Cancelled),
+                    }
+                },
+                is_permanent,
+                warn_threshold,
+                max_retries,
+                "listing object versions for time_travel_recover",
+                cancel,
+            )
             .await
-            .map_err(|err| match err {
-                DownloadError::Other(e) => TimeTravelError::Other(e),
-                DownloadError::Cancelled => TimeTravelError::Cancelled,
-                other => TimeTravelError::Other(other.into()),
-            })?;
-        let versions_and_deletes = version_listing.versions;
+            .ok_or_else(|| TimeTravelError::Cancelled)
+            .and_then(|x| x)?;
+
+            tracing::trace!(
+                "  Got List response version_id_marker={:?}, key_marker={:?}",
+                response.version_id_marker,
+                response.key_marker
+            );
+            let versions = response
+                .versions
+                .unwrap_or_default()
+                .into_iter()
+                .map(VerOrDelete::from_version);
+            let deletes = response
+                .delete_markers
+                .unwrap_or_default()
+                .into_iter()
+                .map(VerOrDelete::from_delete_marker);
+            itertools::process_results(versions.chain(deletes), |n_vds| {
+                versions_and_deletes.extend(n_vds)
+            })
+            .map_err(TimeTravelError::Other)?;
+            fn none_if_empty(v: Option<String>) -> Option<String> {
+                v.filter(|v| !v.is_empty())
+            }
+            version_id_marker = none_if_empty(response.next_version_id_marker);
+            key_marker = none_if_empty(response.next_key_marker);
+            if version_id_marker.is_none() {
+                // The final response is not supposed to be truncated
+                if response.is_truncated.unwrap_or_default() {
+                    return Err(TimeTravelError::Other(anyhow::anyhow!(
+                        "Received truncated ListObjectVersions response for prefix={prefix:?}"
+                    )));
+                }
+                break;
+            }
+            // Limit the number of versions deletions, mostly so that we don't
+            // keep requesting forever if the list is too long, as we'd put the
+            // list in RAM.
+            // Building a list of 100k entries that reaches the limit roughly takes
+            // 40 seconds, and roughly corresponds to tenants of 2 TiB physical size.
+            const COMPLEXITY_LIMIT: usize = 100_000;
+            if versions_and_deletes.len() >= COMPLEXITY_LIMIT {
+                return Err(TimeTravelError::TooManyVersions);
+            }
+        }
 
         tracing::info!(
             "Built list for time travel with {} versions and deletions",
@@ -1012,26 +948,24 @@ impl RemoteStorage for S3Bucket {
         let mut vds_for_key = HashMap::<_, Vec<_>>::new();
 
         for vd in &versions_and_deletes {
-            let Version { key, .. } = &vd;
-            let version_id = vd.version_id().map(|v| v.0.as_str());
-            if version_id == Some("null") {
+            let VerOrDelete {
+                version_id, key, ..
+            } = &vd;
+            if version_id == "null" {
                 return Err(TimeTravelError::Other(anyhow!(
                     "Received ListVersions response for key={key} with version_id='null', \
                     indicating either disabled versioning, or legacy objects with null version id values"
                 )));
             }
-            tracing::trace!("Parsing version key={key} kind={:?}", vd.kind);
+            tracing::trace!(
+                "Parsing version key={key} version_id={version_id} kind={:?}",
+                vd.kind
+            );
 
             vds_for_key.entry(key).or_default().push(vd);
         }
-
-        let warn_threshold = 3;
-        let max_retries = 10;
-        let is_permanent = |e: &_| matches!(e, TimeTravelError::Cancelled);
-
         for (key, versions) in vds_for_key {
             let last_vd = versions.last().unwrap();
-            let key = self.relative_path_to_s3_object(key);
             if last_vd.last_modified > done_if_after {
                 tracing::trace!("Key {key} has version later than done_if_after, skipping");
                 continue;
@@ -1056,11 +990,11 @@ impl RemoteStorage for S3Bucket {
                 do_delete = true;
             } else {
                 match &versions[version_to_restore_to - 1] {
-                    Version {
-                        kind: VersionKind::Version(version_id),
+                    VerOrDelete {
+                        kind: VerOrDeleteKind::Version,
+                        version_id,
                         ..
                     } => {
-                        let version_id = &version_id.0;
                         tracing::trace!("Copying old version {version_id} for {key}...");
                         // Restore the state to the last version by copying
                         let source_id =
@@ -1072,7 +1006,7 @@ impl RemoteStorage for S3Bucket {
                                     .client
                                     .copy_object()
                                     .bucket(self.bucket_name.clone())
-                                    .key(&key)
+                                    .key(key)
                                     .set_storage_class(self.upload_storage_class.clone())
                                     .copy_source(&source_id)
                                     .send();
@@ -1093,8 +1027,8 @@ impl RemoteStorage for S3Bucket {
                         .and_then(|x| x)?;
                         tracing::info!(%version_id, %key, "Copied old version in S3");
                     }
-                    Version {
-                        kind: VersionKind::DeletionMarker,
+                    VerOrDelete {
+                        kind: VerOrDeleteKind::DeleteMarker,
                         ..
                     } => {
                         do_delete = true;
@@ -1102,7 +1036,7 @@ impl RemoteStorage for S3Bucket {
                 }
             };
             if do_delete {
-                if matches!(last_vd.kind, VersionKind::DeletionMarker) {
+                if matches!(last_vd.kind, VerOrDeleteKind::DeleteMarker) {
                     // Key has since been deleted (but there was some history), no need to do anything
                     tracing::trace!("Key {key} already deleted, skipping.");
                 } else {
@@ -1130,6 +1064,62 @@ impl RemoteStorage for S3Bucket {
     }
 }
 
+// Save RAM and only store the needed data instead of the entire ObjectVersion/DeleteMarkerEntry
+struct VerOrDelete {
+    kind: VerOrDeleteKind,
+    last_modified: DateTime,
+    version_id: String,
+    key: String,
+}
+
+#[derive(Debug)]
+enum VerOrDeleteKind {
+    Version,
+    DeleteMarker,
+}
+
+impl VerOrDelete {
+    fn with_kind(
+        kind: VerOrDeleteKind,
+        last_modified: Option<DateTime>,
+        version_id: Option<String>,
+        key: Option<String>,
+    ) -> anyhow::Result<Self> {
+        let lvk = (last_modified, version_id, key);
+        let (Some(last_modified), Some(version_id), Some(key)) = lvk else {
+            anyhow::bail!(
+                "One (or more) of last_modified, key, and id is None. \
+            Is versioning enabled in the bucket? last_modified={:?}, version_id={:?}, key={:?}",
+                lvk.0,
+                lvk.1,
+                lvk.2,
+            );
+        };
+        Ok(Self {
+            kind,
+            last_modified,
+            version_id,
+            key,
+        })
+    }
+    fn from_version(v: ObjectVersion) -> anyhow::Result<Self> {
+        Self::with_kind(
+            VerOrDeleteKind::Version,
+            v.last_modified,
+            v.version_id,
+            v.key,
+        )
+    }
+    fn from_delete_marker(v: DeleteMarkerEntry) -> anyhow::Result<Self> {
+        Self::with_kind(
+            VerOrDeleteKind::DeleteMarker,
+            v.last_modified,
+            v.version_id,
+            v.key,
+        )
+    }
+}
+
 #[cfg(test)]
 mod tests {
     use std::num::NonZeroUsize;

libs/remote_storage/src/simulate_failures.rs

@@ -139,20 +139,6 @@ impl RemoteStorage for UnreliableWrapper {
         self.inner.list(prefix, mode, max_keys, cancel).await
     }
 
-    async fn list_versions(
-        &self,
-        prefix: Option<&RemotePath>,
-        mode: ListingMode,
-        max_keys: Option<NonZeroU32>,
-        cancel: &CancellationToken,
-    ) -> Result<crate::VersionListing, DownloadError> {
-        self.attempt(RemoteOp::ListPrefixes(prefix.cloned()))
-            .map_err(DownloadError::Other)?;
-        self.inner
-            .list_versions(prefix, mode, max_keys, cancel)
-            .await
-    }
-
     async fn head_object(
         &self,
         key: &RemotePath,

libs/utils/Cargo.toml

@@ -29,7 +29,6 @@ futures = { workspace = true }
 jsonwebtoken.workspace = true
 nix = { workspace = true, features = ["ioctl"] }
 once_cell.workspace = true
-pem.workspace = true
 pin-project-lite.workspace = true
 regex.workspace = true
 serde.workspace = true

libs/utils/src/auth.rs

@@ -11,8 +11,7 @@ use camino::Utf8Path;
 use jsonwebtoken::{
     Algorithm, DecodingKey, EncodingKey, Header, TokenData, Validation, decode, encode,
 };
-use pem::Pem;
-use serde::{Deserialize, Serialize, de::DeserializeOwned};
+use serde::{Deserialize, Serialize};
 
 use crate::id::TenantId;
 
@@ -74,10 +73,7 @@ impl SwappableJwtAuth {
     pub fn swap(&self, jwt_auth: JwtAuth) {
         self.0.swap(Arc::new(jwt_auth));
     }
-    pub fn decode<D: DeserializeOwned>(
-        &self,
-        token: &str,
-    ) -> std::result::Result<TokenData<D>, AuthError> {
+    pub fn decode(&self, token: &str) -> std::result::Result<TokenData<Claims>, AuthError> {
         self.0.load().decode(token)
     }
 }
@@ -152,10 +148,7 @@ impl JwtAuth {
     /// The function tries the stored decoding keys in succession,
     /// and returns the first yielding a successful result.
     /// If there is no working decoding key, it returns the last error.
-    pub fn decode<D: DeserializeOwned>(
-        &self,
-        token: &str,
-    ) -> std::result::Result<TokenData<D>, AuthError> {
+    pub fn decode(&self, token: &str) -> std::result::Result<TokenData<Claims>, AuthError> {
         let mut res = None;
         for decoding_key in &self.decoding_keys {
             res = Some(decode(token, decoding_key, &self.validation));
@@ -180,8 +173,8 @@ impl std::fmt::Debug for JwtAuth {
 }
 
 // this function is used only for testing purposes in CLI e g generate tokens during init
-pub fn encode_from_key_file<S: Serialize>(claims: &S, pem: &Pem) -> Result<String> {
-    let key = EncodingKey::from_ed_der(pem.contents());
+pub fn encode_from_key_file<S: Serialize>(claims: &S, key_data: &[u8]) -> Result<String> {
+    let key = EncodingKey::from_ed_pem(key_data)?;
     Ok(encode(&Header::new(STORAGE_TOKEN_ALGORITHM), claims, &key)?)
 }
 
@@ -195,13 +188,13 @@ mod tests {
     //
     // openssl genpkey -algorithm ed25519 -out ed25519-priv.pem
     // openssl pkey -in ed25519-priv.pem -pubout -out ed25519-pub.pem
-    const TEST_PUB_KEY_ED25519: &str = r#"
+    const TEST_PUB_KEY_ED25519: &[u8] = br#"
 -----BEGIN PUBLIC KEY-----
 MCowBQYDK2VwAyEARYwaNBayR+eGI0iXB4s3QxE3Nl2g1iWbr6KtLWeVD/w=
 -----END PUBLIC KEY-----
 "#;
 
-    const TEST_PRIV_KEY_ED25519: &str = r#"
+    const TEST_PRIV_KEY_ED25519: &[u8] = br#"
 -----BEGIN PRIVATE KEY-----
 MC4CAQAwBQYDK2VwBCIEID/Drmc1AA6U/znNRWpF3zEGegOATQxfkdWxitcOMsIH
 -----END PRIVATE KEY-----
@@ -229,9 +222,9 @@ MC4CAQAwBQYDK2VwBCIEID/Drmc1AA6U/znNRWpF3zEGegOATQxfkdWxitcOMsIH
 
         // Check it can be validated with the public key
         let auth = JwtAuth::new(vec![
-            DecodingKey::from_ed_pem(TEST_PUB_KEY_ED25519.as_bytes()).unwrap(),
+            DecodingKey::from_ed_pem(TEST_PUB_KEY_ED25519).unwrap(),
         ]);
-        let claims_from_token: Claims = auth.decode(encoded_eddsa).unwrap().claims;
+        let claims_from_token = auth.decode(encoded_eddsa).unwrap().claims;
         assert_eq!(claims_from_token, expected_claims);
     }
 
@@ -242,14 +235,13 @@ MC4CAQAwBQYDK2VwBCIEID/Drmc1AA6U/znNRWpF3zEGegOATQxfkdWxitcOMsIH
             scope: Scope::Tenant,
         };
 
-        let pem = pem::parse(TEST_PRIV_KEY_ED25519).unwrap();
-        let encoded = encode_from_key_file(&claims, &pem).unwrap();
+        let encoded = encode_from_key_file(&claims, TEST_PRIV_KEY_ED25519).unwrap();
 
         // decode it back
         let auth = JwtAuth::new(vec![
-            DecodingKey::from_ed_pem(TEST_PUB_KEY_ED25519.as_bytes()).unwrap(),
+            DecodingKey::from_ed_pem(TEST_PUB_KEY_ED25519).unwrap(),
         ]);
-        let decoded: TokenData<Claims> = auth.decode(&encoded).unwrap();
+        let decoded = auth.decode(&encoded).unwrap();
 
         assert_eq!(decoded.claims, claims);
     }

object_storage/Cargo.toml

@@ -1,5 +1,5 @@
 [package]
-name = "endpoint_storage"
+name = "object_storage"
 version = "0.0.1"
 edition.workspace = true
 license.workspace = true

object_storage/src/app.rs

@@ -2,7 +2,7 @@ use anyhow::anyhow;
 use axum::body::{Body, Bytes};
 use axum::response::{IntoResponse, Response};
 use axum::{Router, http::StatusCode};
-use endpoint_storage::{PrefixS3Path, S3Path, Storage, bad_request, internal_error, not_found, ok};
+use object_storage::{PrefixS3Path, S3Path, Storage, bad_request, internal_error, not_found, ok};
 use remote_storage::TimeoutOrCancel;
 use remote_storage::{DownloadError, DownloadOpts, GenericRemoteStorage, RemotePath};
 use std::{sync::Arc, time::SystemTime, time::UNIX_EPOCH};
@@ -46,12 +46,12 @@ async fn metrics() -> Result {
 
 async fn get(S3Path { path }: S3Path, state: State) -> Result {
     info!(%path, "downloading");
-    let download_err = |err| {
-        if let DownloadError::NotFound = err {
-            info!(%path, %err, "downloading"); // 404 is not an issue of _this_ service
+    let download_err = |e| {
+        if let DownloadError::NotFound = e {
+            info!(%path, %e, "downloading"); // 404 is not an issue of _this_ service
             return not_found(&path);
         }
-        internal_error(err, &path, "downloading")
+        internal_error(e, &path, "downloading")
     };
     let cancel = state.cancel.clone();
     let opts = &DownloadOpts::default();
@@ -249,7 +249,7 @@ mod tests {
         };
 
         let proxy = Storage {
-            auth: endpoint_storage::JwtAuth::new(TEST_PUB_KEY_ED25519).unwrap(),
+            auth: object_storage::JwtAuth::new(TEST_PUB_KEY_ED25519).unwrap(),
             storage,
             cancel: cancel.clone(),
             max_upload_file_limit: usize::MAX,
@@ -343,14 +343,14 @@ MC4CAQAwBQYDK2VwBCIEID/Drmc1AA6U/znNRWpF3zEGegOATQxfkdWxitcOMsIH
         TimelineId::from_array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 1, 2, 3, 4, 5, 7]);
     const ENDPOINT_ID: &str = "ep-winter-frost-a662z3vg";
     fn token() -> String {
-        let claims = endpoint_storage::Claims {
+        let claims = object_storage::Claims {
             tenant_id: TENANT_ID,
             timeline_id: TIMELINE_ID,
             endpoint_id: ENDPOINT_ID.into(),
             exp: u64::MAX,
         };
         let key = jsonwebtoken::EncodingKey::from_ed_pem(TEST_PRIV_KEY_ED25519).unwrap();
-        let header = jsonwebtoken::Header::new(endpoint_storage::VALIDATION_ALGO);
+        let header = jsonwebtoken::Header::new(object_storage::VALIDATION_ALGO);
         jsonwebtoken::encode(&header, &claims, &key).unwrap()
     }
 
@@ -364,10 +364,7 @@ MC4CAQAwBQYDK2VwBCIEID/Drmc1AA6U/znNRWpF3zEGegOATQxfkdWxitcOMsIH
             vec![TIMELINE_ID.to_string(), TimelineId::generate().to_string()],
             vec![ENDPOINT_ID, "ep-ololo"]
         )
-        // first one is fully valid path, second path is valid for GET as
-        // read paths may have different endpoint if tenant and timeline matches
-        // (needed for prewarming RO->RW replica)
-        .skip(2);
+        .skip(1);
 
         for ((uri, method), (tenant, timeline, endpoint)) in iproduct!(routes(), args) {
             info!(%uri, %method, %tenant, %timeline, %endpoint);
@@ -478,16 +475,6 @@ MC4CAQAwBQYDK2VwBCIEID/Drmc1AA6U/znNRWpF3zEGegOATQxfkdWxitcOMsIH
         requests_chain(chain.into_iter(), |_| token()).await;
     }
 
-    #[testlog(tokio::test)]
-    async fn read_other_endpoint_data() {
-        let uri = format!("/{TENANT_ID}/{TIMELINE_ID}/other_endpoint/key");
-        let chain = vec![
-            (uri.clone(), "GET", "", StatusCode::NOT_FOUND, false),
-            (uri.clone(), "PUT", "", StatusCode::UNAUTHORIZED, false),
-        ];
-        requests_chain(chain.into_iter(), |_| token()).await;
-    }
-
     fn delete_prefix_token(uri: &str) -> String {
         use serde::Serialize;
         let parts = uri.split("/").collect::<Vec<&str>>();
@@ -495,7 +482,7 @@ MC4CAQAwBQYDK2VwBCIEID/Drmc1AA6U/znNRWpF3zEGegOATQxfkdWxitcOMsIH
         struct PrefixClaims {
             tenant_id: TenantId,
             timeline_id: Option<TimelineId>,
-            endpoint_id: Option<endpoint_storage::EndpointId>,
+            endpoint_id: Option<object_storage::EndpointId>,
             exp: u64,
         }
         let claims = PrefixClaims {
@@ -505,7 +492,7 @@ MC4CAQAwBQYDK2VwBCIEID/Drmc1AA6U/znNRWpF3zEGegOATQxfkdWxitcOMsIH
             exp: u64::MAX,
         };
         let key = jsonwebtoken::EncodingKey::from_ed_pem(TEST_PRIV_KEY_ED25519).unwrap();
-        let header = jsonwebtoken::Header::new(endpoint_storage::VALIDATION_ALGO);
+        let header = jsonwebtoken::Header::new(object_storage::VALIDATION_ALGO);
         jsonwebtoken::encode(&header, &claims, &key).unwrap()
     }
 

object_storage/src/lib.rs

@@ -169,19 +169,10 @@ impl FromRequestParts<Arc<Storage>> for S3Path {
             .auth
             .decode(bearer.token())
             .map_err(|e| bad_request(e, "decoding token"))?;
-
-        // Read paths may have different endpoint ids. For readonly -> readwrite replica
-        // prewarming, endpoint must read other endpoint's data.
-        let endpoint_id = if parts.method == axum::http::Method::GET {
-            claims.endpoint_id.clone()
-        } else {
-            path.endpoint_id.clone()
-        };
-
         let route = Claims {
             tenant_id: path.tenant_id,
             timeline_id: path.timeline_id,
-            endpoint_id,
+            endpoint_id: path.endpoint_id.clone(),
             exp: claims.exp,
         };
         if route != claims {

object_storage/src/main.rs

@@ -1,4 +1,4 @@
-//! `endpoint_storage` is a service which provides API for uploading and downloading
+//! `object_storage` is a service which provides API for uploading and downloading
 //! files. It is used by compute and control plane for accessing LFC prewarm data.
 //! This service is deployed either as a separate component or as part of compute image
 //! for large computes.
@@ -33,7 +33,7 @@ async fn main() -> anyhow::Result<()> {
 
     let config: String = std::env::args().skip(1).take(1).collect();
     if config.is_empty() {
-        anyhow::bail!("Usage: endpoint_storage config.json")
+        anyhow::bail!("Usage: object_storage config.json")
     }
     info!("Reading config from {config}");
     let config = std::fs::read_to_string(config.clone())?;
@@ -41,7 +41,7 @@ async fn main() -> anyhow::Result<()> {
     info!("Reading pemfile from {}", config.pemfile.clone());
     let pemfile = std::fs::read(config.pemfile.clone())?;
     info!("Loading public key from {}", config.pemfile.clone());
-    let auth = endpoint_storage::JwtAuth::new(&pemfile)?;
+    let auth = object_storage::JwtAuth::new(&pemfile)?;
 
     let listener = tokio::net::TcpListener::bind(config.listen).await.unwrap();
     info!("listening on {}", listener.local_addr().unwrap());
@@ -50,7 +50,7 @@ async fn main() -> anyhow::Result<()> {
     let cancel = tokio_util::sync::CancellationToken::new();
     app::check_storage_permissions(&storage, cancel.clone()).await?;
 
-    let proxy = std::sync::Arc::new(endpoint_storage::Storage {
+    let proxy = std::sync::Arc::new(object_storage::Storage {
         auth,
         storage,
         cancel: cancel.clone(),

pageserver/Cargo.toml

@@ -10,8 +10,6 @@ default = []
 # which adds some runtime cost to run tests on outage conditions
 testing = ["fail/failpoints", "pageserver_api/testing", "wal_decoder/testing", "pageserver_client/testing"]
 
-fuzz-read-path = ["testing"]
-
 [dependencies]
 anyhow.workspace = true
 arc-swap.workspace = true
@@ -35,7 +33,6 @@ humantime.workspace = true
 humantime-serde.workspace = true
 hyper0.workspace = true
 itertools.workspace = true
-jsonwebtoken.workspace = true
 md5.workspace = true
 nix.workspace = true
 # hack to get the number of worker threads tokio uses
@@ -78,7 +75,6 @@ metrics.workspace = true
 pageserver_api.workspace = true
 pageserver_client.workspace = true # for ResponseErrorMessageExt TOOD refactor that
 pageserver_compaction.workspace = true
-pem.workspace = true
 postgres_connection.workspace = true
 postgres_ffi.workspace = true
 pq_proto.workspace = true
@@ -106,7 +102,6 @@ hex-literal.workspace = true
 tokio = { workspace = true, features = ["process", "sync", "fs", "rt", "io-util", "time", "test-util"] }
 indoc.workspace = true
 uuid.workspace = true
-rstest.workspace = true
 
 [[bench]]
 name = "bench_layer_map"

pageserver/benches/bench_ingest.rs

@@ -11,7 +11,6 @@ use pageserver::task_mgr::TaskKind;
 use pageserver::tenant::storage_layer::InMemoryLayer;
 use pageserver::{page_cache, virtual_file};
 use pageserver_api::key::Key;
-use pageserver_api::models::virtual_file::IoMode;
 use pageserver_api::shard::TenantShardId;
 use pageserver_api::value::Value;
 use tokio_util::sync::CancellationToken;
@@ -29,7 +28,6 @@ fn murmurhash32(mut h: u32) -> u32 {
     h
 }
 
-#[derive(serde::Serialize, Clone, Copy, Debug)]
 enum KeyLayout {
     /// Sequential unique keys
     Sequential,
@@ -39,7 +37,6 @@ enum KeyLayout {
     RandomReuse(u32),
 }
 
-#[derive(serde::Serialize, Clone, Copy, Debug)]
 enum WriteDelta {
     Yes,
     No,
@@ -141,15 +138,12 @@ async fn ingest(
 /// Wrapper to instantiate a tokio runtime
 fn ingest_main(
     conf: &'static PageServerConf,
-    io_mode: IoMode,
     put_size: usize,
     put_count: usize,
     key_layout: KeyLayout,
     write_delta: WriteDelta,
 ) {
-    pageserver::virtual_file::set_io_mode(io_mode);
-
-    let runtime = tokio::runtime::Builder::new_multi_thread()
+    let runtime = tokio::runtime::Builder::new_current_thread()
         .enable_all()
         .build()
         .unwrap();
@@ -180,245 +174,93 @@ fn criterion_benchmark(c: &mut Criterion) {
     virtual_file::init(
         16384,
         virtual_file::io_engine_for_bench(),
-        // immaterial, each `ingest_main` invocation below overrides this
         conf.virtual_file_io_mode,
-        // without actually doing syncs, buffered writes have an unfair advantage over direct IO writes
         virtual_file::SyncMode::Sync,
     );
     page_cache::init(conf.page_cache_size);
 
-    #[derive(serde::Serialize)]
-    struct ExplodedParameters {
-        io_mode: IoMode,
-        volume_mib: usize,
-        key_size: usize,
-        key_layout: KeyLayout,
-        write_delta: WriteDelta,
-    }
-    #[derive(Clone)]
-    struct HandPickedParameters {
-        volume_mib: usize,
-        key_size: usize,
-        key_layout: KeyLayout,
-        write_delta: WriteDelta,
-    }
-    let expect = vec![
-        // Small values (100b) tests
-        HandPickedParameters {
-            volume_mib: 128,
-            key_size: 100,
-            key_layout: KeyLayout::Sequential,
-            write_delta: WriteDelta::Yes,
-        },
-        HandPickedParameters {
-            volume_mib: 128,
-            key_size: 100,
-            key_layout: KeyLayout::Random,
-            write_delta: WriteDelta::Yes,
-        },
-        HandPickedParameters {
-            volume_mib: 128,
-            key_size: 100,
-            key_layout: KeyLayout::RandomReuse(0x3ff),
-            write_delta: WriteDelta::Yes,
-        },
-        HandPickedParameters {
-            volume_mib: 128,
-            key_size: 100,
-            key_layout: KeyLayout::Sequential,
-            write_delta: WriteDelta::No,
-        },
-        // Large values (8k) tests
-        HandPickedParameters {
-            volume_mib: 128,
-            key_size: 8192,
-            key_layout: KeyLayout::Sequential,
-            write_delta: WriteDelta::Yes,
-        },
-        HandPickedParameters {
-            volume_mib: 128,
-            key_size: 8192,
-            key_layout: KeyLayout::Sequential,
-            write_delta: WriteDelta::No,
-        },
-    ];
-    let exploded_parameters = {
-        let mut out = Vec::new();
-        for io_mode in [
-            IoMode::Buffered,
-            #[cfg(target_os = "linux")]
-            IoMode::Direct,
-            #[cfg(target_os = "linux")]
-            IoMode::DirectRw,
-        ] {
-            for param in expect.clone() {
-                let HandPickedParameters {
-                    volume_mib,
-                    key_size,
-                    key_layout,
-                    write_delta,
-                } = param;
-                out.push(ExplodedParameters {
-                    io_mode,
-                    volume_mib,
-                    key_size,
-                    key_layout,
-                    write_delta,
-                });
-            }
-        }
-        out
-    };
-    impl ExplodedParameters {
-        fn benchmark_id(&self) -> String {
-            let ExplodedParameters {
-                io_mode,
-                volume_mib,
-                key_size,
-                key_layout,
-                write_delta,
-            } = self;
-            format!(
-                "io_mode={io_mode:?} volume_mib={volume_mib:?} key_size_bytes={key_size:?} key_layout={key_layout:?} write_delta={write_delta:?}"
-            )
-        }
-    }
-    let mut group = c.benchmark_group("ingest");
-    for params in exploded_parameters {
-        let id = params.benchmark_id();
-        let ExplodedParameters {
-            io_mode,
-            volume_mib,
-            key_size,
-            key_layout,
-            write_delta,
-        } = params;
-        let put_count = volume_mib * 1024 * 1024 / key_size;
-        group.throughput(criterion::Throughput::Bytes((key_size * put_count) as u64));
+    {
+        let mut group = c.benchmark_group("ingest-small-values");
+        let put_size = 100usize;
+        let put_count = 128 * 1024 * 1024 / put_size;
+        group.throughput(criterion::Throughput::Bytes((put_size * put_count) as u64));
         group.sample_size(10);
-        group.bench_function(id, |b| {
-            b.iter(|| ingest_main(conf, io_mode, key_size, put_count, key_layout, write_delta))
+        group.bench_function("ingest 128MB/100b seq", |b| {
+            b.iter(|| {
+                ingest_main(
+                    conf,
+                    put_size,
+                    put_count,
+                    KeyLayout::Sequential,
+                    WriteDelta::Yes,
+                )
+            })
+        });
+        group.bench_function("ingest 128MB/100b rand", |b| {
+            b.iter(|| {
+                ingest_main(
+                    conf,
+                    put_size,
+                    put_count,
+                    KeyLayout::Random,
+                    WriteDelta::Yes,
+                )
+            })
+        });
+        group.bench_function("ingest 128MB/100b rand-1024keys", |b| {
+            b.iter(|| {
+                ingest_main(
+                    conf,
+                    put_size,
+                    put_count,
+                    KeyLayout::RandomReuse(0x3ff),
+                    WriteDelta::Yes,
+                )
+            })
+        });
+        group.bench_function("ingest 128MB/100b seq, no delta", |b| {
+            b.iter(|| {
+                ingest_main(
+                    conf,
+                    put_size,
+                    put_count,
+                    KeyLayout::Sequential,
+                    WriteDelta::No,
+                )
+            })
+        });
+    }
+
+    {
+        let mut group = c.benchmark_group("ingest-big-values");
+        let put_size = 8192usize;
+        let put_count = 128 * 1024 * 1024 / put_size;
+        group.throughput(criterion::Throughput::Bytes((put_size * put_count) as u64));
+        group.sample_size(10);
+        group.bench_function("ingest 128MB/8k seq", |b| {
+            b.iter(|| {
+                ingest_main(
+                    conf,
+                    put_size,
+                    put_count,
+                    KeyLayout::Sequential,
+                    WriteDelta::Yes,
+                )
+            })
+        });
+        group.bench_function("ingest 128MB/8k seq, no delta", |b| {
+            b.iter(|| {
+                ingest_main(
+                    conf,
+                    put_size,
+                    put_count,
+                    KeyLayout::Sequential,
+                    WriteDelta::No,
+                )
+            })
         });
     }
 }
 
 criterion_group!(benches, criterion_benchmark);
 criterion_main!(benches);
-
-/*
-cargo bench --bench bench_ingest
-
-im4gn.2xlarge:
-
-ingest/io_mode=Buffered volume_mib=128 key_size_bytes=100 key_layout=Sequential write_delta=Yes
-                        time:   [1.2901 s 1.2943 s 1.2991 s]
-                        thrpt:  [98.533 MiB/s 98.892 MiB/s 99.220 MiB/s]
-ingest/io_mode=Buffered volume_mib=128 key_size_bytes=100 key_layout=Random write_delta=Yes
-                        time:   [2.1387 s 2.1623 s 2.1845 s]
-                        thrpt:  [58.595 MiB/s 59.197 MiB/s 59.851 MiB/s]
-ingest/io_mode=Buffered volume_mib=128 key_size_bytes=100 key_layout=RandomReuse(1023) write_delta=Y...
-                        time:   [1.2036 s 1.2074 s 1.2122 s]
-                        thrpt:  [105.60 MiB/s 106.01 MiB/s 106.35 MiB/s]
-ingest/io_mode=Buffered volume_mib=128 key_size_bytes=100 key_layout=Sequential write_delta=No
-                        time:   [520.55 ms 521.46 ms 522.57 ms]
-                        thrpt:  [244.94 MiB/s 245.47 MiB/s 245.89 MiB/s]
-ingest/io_mode=Buffered volume_mib=128 key_size_bytes=8192 key_layout=Sequential write_delta=Yes
-                        time:   [440.33 ms 442.24 ms 444.10 ms]
-                        thrpt:  [288.22 MiB/s 289.43 MiB/s 290.69 MiB/s]
-ingest/io_mode=Buffered volume_mib=128 key_size_bytes=8192 key_layout=Sequential write_delta=No
-                        time:   [168.78 ms 169.42 ms 170.18 ms]
-                        thrpt:  [752.16 MiB/s 755.52 MiB/s 758.40 MiB/s]
-ingest/io_mode=Direct volume_mib=128 key_size_bytes=100 key_layout=Sequential write_delta=Yes
-                        time:   [1.2978 s 1.3094 s 1.3227 s]
-                        thrpt:  [96.775 MiB/s 97.758 MiB/s 98.632 MiB/s]
-ingest/io_mode=Direct volume_mib=128 key_size_bytes=100 key_layout=Random write_delta=Yes
-                        time:   [2.1976 s 2.2067 s 2.2154 s]
-                        thrpt:  [57.777 MiB/s 58.006 MiB/s 58.245 MiB/s]
-ingest/io_mode=Direct volume_mib=128 key_size_bytes=100 key_layout=RandomReuse(1023) write_delta=Yes
-                        time:   [1.2103 s 1.2160 s 1.2233 s]
-                        thrpt:  [104.64 MiB/s 105.26 MiB/s 105.76 MiB/s]
-ingest/io_mode=Direct volume_mib=128 key_size_bytes=100 key_layout=Sequential write_delta=No
-                        time:   [525.05 ms 526.37 ms 527.79 ms]
-                        thrpt:  [242.52 MiB/s 243.17 MiB/s 243.79 MiB/s]
-ingest/io_mode=Direct volume_mib=128 key_size_bytes=8192 key_layout=Sequential write_delta=Yes
-                        time:   [443.06 ms 444.88 ms 447.15 ms]
-                        thrpt:  [286.26 MiB/s 287.72 MiB/s 288.90 MiB/s]
-ingest/io_mode=Direct volume_mib=128 key_size_bytes=8192 key_layout=Sequential write_delta=No
-                        time:   [169.40 ms 169.80 ms 170.17 ms]
-                        thrpt:  [752.21 MiB/s 753.81 MiB/s 755.60 MiB/s]
-ingest/io_mode=DirectRw volume_mib=128 key_size_bytes=100 key_layout=Sequential write_delta=Yes
-                        time:   [1.2844 s 1.2915 s 1.2990 s]
-                        thrpt:  [98.536 MiB/s 99.112 MiB/s 99.657 MiB/s]
-ingest/io_mode=DirectRw volume_mib=128 key_size_bytes=100 key_layout=Random write_delta=Yes
-                        time:   [2.1431 s 2.1663 s 2.1900 s]
-                        thrpt:  [58.446 MiB/s 59.087 MiB/s 59.726 MiB/s]
-ingest/io_mode=DirectRw volume_mib=128 key_size_bytes=100 key_layout=RandomReuse(1023) write_delta=Y...
-                        time:   [1.1906 s 1.1926 s 1.1947 s]
-                        thrpt:  [107.14 MiB/s 107.33 MiB/s 107.51 MiB/s]
-ingest/io_mode=DirectRw volume_mib=128 key_size_bytes=100 key_layout=Sequential write_delta=No
-                        time:   [516.86 ms 518.25 ms 519.47 ms]
-                        thrpt:  [246.40 MiB/s 246.98 MiB/s 247.65 MiB/s]
-ingest/io_mode=DirectRw volume_mib=128 key_size_bytes=8192 key_layout=Sequential write_delta=Yes
-                        time:   [536.50 ms 536.53 ms 536.60 ms]
-                        thrpt:  [238.54 MiB/s 238.57 MiB/s 238.59 MiB/s]
-ingest/io_mode=DirectRw volume_mib=128 key_size_bytes=8192 key_layout=Sequential write_delta=No
-                        time:   [267.77 ms 267.90 ms 268.04 ms]
-                        thrpt:  [477.53 MiB/s 477.79 MiB/s 478.02 MiB/s]
-
-Hetzner AX102:
-
-ingest/io_mode=Buffered volume_mib=128 key_size_bytes=100 key_layout=Sequential write_delta=Yes
-                        time:   [836.58 ms 861.93 ms 886.57 ms]
-                        thrpt:  [144.38 MiB/s 148.50 MiB/s 153.00 MiB/s]
-ingest/io_mode=Buffered volume_mib=128 key_size_bytes=100 key_layout=Random write_delta=Yes
-                        time:   [1.2782 s 1.3191 s 1.3665 s]
-                        thrpt:  [93.668 MiB/s 97.037 MiB/s 100.14 MiB/s]
-ingest/io_mode=Buffered volume_mib=128 key_size_bytes=100 key_layout=RandomReuse(1023) write_delta=Y...
-                        time:   [791.27 ms 807.08 ms 822.95 ms]
-                        thrpt:  [155.54 MiB/s 158.60 MiB/s 161.77 MiB/s]
-ingest/io_mode=Buffered volume_mib=128 key_size_bytes=100 key_layout=Sequential write_delta=No
-                        time:   [310.78 ms 314.66 ms 318.47 ms]
-                        thrpt:  [401.92 MiB/s 406.79 MiB/s 411.87 MiB/s]
-ingest/io_mode=Buffered volume_mib=128 key_size_bytes=8192 key_layout=Sequential write_delta=Yes
-                        time:   [377.11 ms 387.77 ms 399.21 ms]
-                        thrpt:  [320.63 MiB/s 330.10 MiB/s 339.42 MiB/s]
-ingest/io_mode=Buffered volume_mib=128 key_size_bytes=8192 key_layout=Sequential write_delta=No
-                        time:   [128.37 ms 132.96 ms 138.55 ms]
-                        thrpt:  [923.83 MiB/s 962.69 MiB/s 997.11 MiB/s]
-ingest/io_mode=Direct volume_mib=128 key_size_bytes=100 key_layout=Sequential write_delta=Yes
-                        time:   [900.38 ms 914.88 ms 928.86 ms]
-                        thrpt:  [137.80 MiB/s 139.91 MiB/s 142.16 MiB/s]
-ingest/io_mode=Direct volume_mib=128 key_size_bytes=100 key_layout=Random write_delta=Yes
-                        time:   [1.2538 s 1.2936 s 1.3313 s]
-                        thrpt:  [96.149 MiB/s 98.946 MiB/s 102.09 MiB/s]
-ingest/io_mode=Direct volume_mib=128 key_size_bytes=100 key_layout=RandomReuse(1023) write_delta=Yes
-                        time:   [787.17 ms 803.89 ms 820.63 ms]
-                        thrpt:  [155.98 MiB/s 159.23 MiB/s 162.61 MiB/s]
-ingest/io_mode=Direct volume_mib=128 key_size_bytes=100 key_layout=Sequential write_delta=No
-                        time:   [318.78 ms 321.89 ms 324.74 ms]
-                        thrpt:  [394.16 MiB/s 397.65 MiB/s 401.53 MiB/s]
-ingest/io_mode=Direct volume_mib=128 key_size_bytes=8192 key_layout=Sequential write_delta=Yes
-                        time:   [374.01 ms 383.45 ms 393.20 ms]
-                        thrpt:  [325.53 MiB/s 333.81 MiB/s 342.24 MiB/s]
-ingest/io_mode=Direct volume_mib=128 key_size_bytes=8192 key_layout=Sequential write_delta=No
-                        time:   [137.98 ms 141.31 ms 143.57 ms]
-                        thrpt:  [891.58 MiB/s 905.79 MiB/s 927.66 MiB/s]
-ingest/io_mode=DirectRw volume_mib=128 key_size_bytes=100 key_layout=Sequential write_delta=Yes
-                        time:   [613.69 ms 622.48 ms 630.97 ms]
-                        thrpt:  [202.86 MiB/s 205.63 MiB/s 208.57 MiB/s]
-ingest/io_mode=DirectRw volume_mib=128 key_size_bytes=100 key_layout=Random write_delta=Yes
-                        time:   [1.0299 s 1.0766 s 1.1273 s]
-                        thrpt:  [113.55 MiB/s 118.90 MiB/s 124.29 MiB/s]
-ingest/io_mode=DirectRw volume_mib=128 key_size_bytes=100 key_layout=RandomReuse(1023) write_delta=Y...
-                        time:   [637.80 ms 647.78 ms 658.01 ms]
-                        thrpt:  [194.53 MiB/s 197.60 MiB/s 200.69 MiB/s]
-ingest/io_mode=DirectRw volume_mib=128 key_size_bytes=100 key_layout=Sequential write_delta=No
-                        time:   [266.09 ms 267.20 ms 268.31 ms]
-                        thrpt:  [477.06 MiB/s 479.04 MiB/s 481.04 MiB/s]
-ingest/io_mode=DirectRw volume_mib=128 key_size_bytes=8192 key_layout=Sequential write_delta=Yes
-                        time:   [269.34 ms 273.27 ms 277.69 ms]
-                        thrpt:  [460.95 MiB/s 468.40 MiB/s 475.24 MiB/s]
-ingest/io_mode=DirectRw volume_mib=128 key_size_bytes=8192 key_layout=Sequential write_delta=No
-                        time:   [123.18 ms 124.24 ms 125.15 ms]
-                        thrpt:  [1022.8 MiB/s 1.0061 GiB/s 1.0148 GiB/s]
-*/

pageserver/client/src/mgmt_api.rs

@@ -419,23 +419,6 @@ impl Client {
         }
     }
 
-    pub async fn timeline_detail(
-        &self,
-        tenant_shard_id: TenantShardId,
-        timeline_id: TimelineId,
-    ) -> Result<TimelineInfo> {
-        let uri = format!(
-            "{}/v1/tenant/{tenant_shard_id}/timeline/{timeline_id}",
-            self.mgmt_api_endpoint
-        );
-
-        self.request(Method::GET, &uri, ())
-            .await?
-            .json()
-            .await
-            .map_err(Error::ReceiveBody)
-    }
-
     pub async fn timeline_archival_config(
         &self,
         tenant_shard_id: TenantShardId,

pageserver/pagebench/src/cmd/getpage_latest_lsn.rs

@@ -68,13 +68,6 @@ pub(crate) struct Args {
     targets: Option<Vec<TenantTimelineId>>,
 }
 
-/// State shared by all clients
-#[derive(Debug)]
-struct SharedState {
-    start_work_barrier: tokio::sync::Barrier,
-    live_stats: LiveStats,
-}
-
 #[derive(Debug, Default)]
 struct LiveStats {
     completed_requests: AtomicU64,
@@ -247,26 +240,24 @@ async fn main_impl(
         all_ranges
     };
 
+    let live_stats = Arc::new(LiveStats::default());
+
     let num_live_stats_dump = 1;
     let num_work_sender_tasks = args.num_clients.get() * timelines.len();
     let num_main_impl = 1;
 
-    let shared_state = Arc::new(SharedState {
-        start_work_barrier: tokio::sync::Barrier::new(
-            num_live_stats_dump + num_work_sender_tasks + num_main_impl,
-        ),
-        live_stats: LiveStats::default(),
-    });
-    let cancel = CancellationToken::new();
+    let start_work_barrier = Arc::new(tokio::sync::Barrier::new(
+        num_live_stats_dump + num_work_sender_tasks + num_main_impl,
+    ));
 
-    let ss = shared_state.clone();
     tokio::spawn({
+        let stats = Arc::clone(&live_stats);
+        let start_work_barrier = Arc::clone(&start_work_barrier);
         async move {
-            ss.start_work_barrier.wait().await;
+            start_work_barrier.wait().await;
             loop {
                 let start = std::time::Instant::now();
                 tokio::time::sleep(std::time::Duration::from_secs(1)).await;
-                let stats = &ss.live_stats;
                 let completed_requests = stats.completed_requests.swap(0, Ordering::Relaxed);
                 let missed = stats.missed.swap(0, Ordering::Relaxed);
                 let elapsed = start.elapsed();
@@ -279,12 +270,14 @@ async fn main_impl(
         }
     });
 
+    let cancel = CancellationToken::new();
+
     let rps_period = args
         .per_client_rate
         .map(|rps_limit| Duration::from_secs_f64(1.0 / (rps_limit as f64)));
     let make_worker: &dyn Fn(WorkerId) -> Pin<Box<dyn Send + Future<Output = ()>>> = &|worker_id| {
-        let ss = shared_state.clone();
-        let cancel = cancel.clone();
+        let live_stats = live_stats.clone();
+        let start_work_barrier = start_work_barrier.clone();
         let ranges: Vec<KeyRange> = all_ranges
             .iter()
             .filter(|r| r.timeline == worker_id.timeline)
@@ -294,8 +287,85 @@ async fn main_impl(
             rand::distributions::weighted::WeightedIndex::new(ranges.iter().map(|v| v.len()))
                 .unwrap();
 
+        let cancel = cancel.clone();
         Box::pin(async move {
-            client_libpq(args, worker_id, ss, cancel, rps_period, ranges, weights).await
+            let client =
+                pageserver_client::page_service::Client::new(args.page_service_connstring.clone())
+                    .await
+                    .unwrap();
+            let mut client = client
+                .pagestream(worker_id.timeline.tenant_id, worker_id.timeline.timeline_id)
+                .await
+                .unwrap();
+
+            start_work_barrier.wait().await;
+            let client_start = Instant::now();
+            let mut ticks_processed = 0;
+            let mut inflight = VecDeque::new();
+            while !cancel.is_cancelled() {
+                // Detect if a request took longer than the RPS rate
+                if let Some(period) = &rps_period {
+                    let periods_passed_until_now =
+                        usize::try_from(client_start.elapsed().as_micros() / period.as_micros())
+                            .unwrap();
+
+                    if periods_passed_until_now > ticks_processed {
+                        live_stats.missed((periods_passed_until_now - ticks_processed) as u64);
+                    }
+                    ticks_processed = periods_passed_until_now;
+                }
+
+                while inflight.len() < args.queue_depth.get() {
+                    let start = Instant::now();
+                    let req = {
+                        let mut rng = rand::thread_rng();
+                        let r = &ranges[weights.sample(&mut rng)];
+                        let key: i128 = rng.gen_range(r.start..r.end);
+                        let key = Key::from_i128(key);
+                        assert!(key.is_rel_block_key());
+                        let (rel_tag, block_no) = key
+                            .to_rel_block()
+                            .expect("we filter non-rel-block keys out above");
+                        PagestreamGetPageRequest {
+                            hdr: PagestreamRequest {
+                                reqid: 0,
+                                request_lsn: if rng.gen_bool(args.req_latest_probability) {
+                                    Lsn::MAX
+                                } else {
+                                    r.timeline_lsn
+                                },
+                                not_modified_since: r.timeline_lsn,
+                            },
+                            rel: rel_tag,
+                            blkno: block_no,
+                        }
+                    };
+                    client.getpage_send(req).await.unwrap();
+                    inflight.push_back(start);
+                }
+
+                let start = inflight.pop_front().unwrap();
+                client.getpage_recv().await.unwrap();
+                let end = Instant::now();
+                live_stats.request_done();
+                ticks_processed += 1;
+                STATS.with(|stats| {
+                    stats
+                        .borrow()
+                        .lock()
+                        .unwrap()
+                        .observe(end.duration_since(start))
+                        .unwrap();
+                });
+
+                if let Some(period) = &rps_period {
+                    let next_at = client_start
+                        + Duration::from_micros(
+                            (ticks_processed) as u64 * u64::try_from(period.as_micros()).unwrap(),
+                        );
+                    tokio::time::sleep_until(next_at.into()).await;
+                }
+            }
         })
     };
 
@@ -317,7 +387,7 @@ async fn main_impl(
     };
 
     info!("waiting for everything to become ready");
-    shared_state.start_work_barrier.wait().await;
+    start_work_barrier.wait().await;
     info!("work started");
     if let Some(runtime) = args.runtime {
         tokio::time::sleep(runtime.into()).await;
@@ -346,91 +416,3 @@ async fn main_impl(
 
     anyhow::Ok(())
 }
-
-async fn client_libpq(
-    args: &Args,
-    worker_id: WorkerId,
-    shared_state: Arc<SharedState>,
-    cancel: CancellationToken,
-    rps_period: Option<Duration>,
-    ranges: Vec<KeyRange>,
-    weights: rand::distributions::weighted::WeightedIndex<i128>,
-) {
-    let client = pageserver_client::page_service::Client::new(args.page_service_connstring.clone())
-        .await
-        .unwrap();
-    let mut client = client
-        .pagestream(worker_id.timeline.tenant_id, worker_id.timeline.timeline_id)
-        .await
-        .unwrap();
-
-    shared_state.start_work_barrier.wait().await;
-    let client_start = Instant::now();
-    let mut ticks_processed = 0;
-    let mut inflight = VecDeque::new();
-    while !cancel.is_cancelled() {
-        // Detect if a request took longer than the RPS rate
-        if let Some(period) = &rps_period {
-            let periods_passed_until_now =
-                usize::try_from(client_start.elapsed().as_micros() / period.as_micros()).unwrap();
-
-            if periods_passed_until_now > ticks_processed {
-                shared_state
-                    .live_stats
-                    .missed((periods_passed_until_now - ticks_processed) as u64);
-            }
-            ticks_processed = periods_passed_until_now;
-        }
-
-        while inflight.len() < args.queue_depth.get() {
-            let start = Instant::now();
-            let req = {
-                let mut rng = rand::thread_rng();
-                let r = &ranges[weights.sample(&mut rng)];
-                let key: i128 = rng.gen_range(r.start..r.end);
-                let key = Key::from_i128(key);
-                assert!(key.is_rel_block_key());
-                let (rel_tag, block_no) = key
-                    .to_rel_block()
-                    .expect("we filter non-rel-block keys out above");
-                PagestreamGetPageRequest {
-                    hdr: PagestreamRequest {
-                        reqid: 0,
-                        request_lsn: if rng.gen_bool(args.req_latest_probability) {
-                            Lsn::MAX
-                        } else {
-                            r.timeline_lsn
-                        },
-                        not_modified_since: r.timeline_lsn,
-                    },
-                    rel: rel_tag,
-                    blkno: block_no,
-                }
-            };
-            client.getpage_send(req).await.unwrap();
-            inflight.push_back(start);
-        }
-
-        let start = inflight.pop_front().unwrap();
-        client.getpage_recv().await.unwrap();
-        let end = Instant::now();
-        shared_state.live_stats.request_done();
-        ticks_processed += 1;
-        STATS.with(|stats| {
-            stats
-                .borrow()
-                .lock()
-                .unwrap()
-                .observe(end.duration_since(start))
-                .unwrap();
-        });
-
-        if let Some(period) = &rps_period {
-            let next_at = client_start
-                + Duration::from_micros(
-                    (ticks_processed) as u64 * u64::try_from(period.as_micros()).unwrap(),
-                );
-            tokio::time::sleep_until(next_at.into()).await;
-        }
-    }
-}

pageserver/src/basebackup.rs

@@ -34,7 +34,7 @@ use utils::lsn::Lsn;
 use crate::context::RequestContext;
 use crate::pgdatadir_mapping::Version;
 use crate::tenant::storage_layer::IoConcurrency;
-use crate::tenant::timeline::{GetVectoredError, VersionedKeySpaceQuery};
+use crate::tenant::timeline::GetVectoredError;
 use crate::tenant::{PageReconstructError, Timeline};
 
 #[derive(Debug, thiserror::Error)]
@@ -353,10 +353,9 @@ where
             let mut slru_builder = SlruSegmentsBuilder::new(&mut self.ar);
 
             for part in slru_partitions.parts {
-                let query = VersionedKeySpaceQuery::uniform(part, self.lsn);
                 let blocks = self
                     .timeline
-                    .get_vectored(query, self.io_concurrency.clone(), self.ctx)
+                    .get_vectored(part, self.lsn, self.io_concurrency.clone(), self.ctx)
                     .await?;
 
                 for (key, block) in blocks {

pageserver/src/bin/pageserver.rs

@@ -416,18 +416,8 @@ fn start_pageserver(
     // The storage_broker::connect call needs to happen inside a tokio runtime thread.
     let broker_client = WALRECEIVER_RUNTIME
         .block_on(async {
-            let tls_config = storage_broker::ClientTlsConfig::new().ca_certificates(
-                conf.ssl_ca_certs
-                    .iter()
-                    .map(pem::encode)
-                    .map(storage_broker::Certificate::from_pem),
-            );
             // Note: we do not attempt connecting here (but validate endpoints sanity).
-            storage_broker::connect(
-                conf.broker_endpoint.clone(),
-                conf.broker_keepalive_interval,
-                tls_config,
-            )
+            storage_broker::connect(conf.broker_endpoint.clone(), conf.broker_keepalive_interval)
         })
         .with_context(|| {
             format!(

pageserver/src/config.rs

@@ -17,10 +17,9 @@ use once_cell::sync::OnceCell;
 use pageserver_api::config::{DiskUsageEvictionTaskConfig, MaxVectoredReadBytes};
 use pageserver_api::models::ImageCompressionAlgorithm;
 use pageserver_api::shard::TenantShardId;
-use pem::Pem;
 use postgres_backend::AuthType;
 use remote_storage::{RemotePath, RemoteStorageConfig};
-use reqwest::Url;
+use reqwest::{Certificate, Url};
 use storage_broker::Uri;
 use utils::id::{NodeId, TimelineId};
 use utils::logging::{LogFormat, SecretString};
@@ -68,8 +67,8 @@ pub struct PageServerConf {
     /// Period to reload certificate and private key from files.
     /// Default: 60s.
     pub ssl_cert_reload_period: Duration,
-    /// Trusted root CA certificates to use in https APIs in PEM format.
-    pub ssl_ca_certs: Vec<Pem>,
+    /// Trusted root CA certificates to use in https APIs.
+    pub ssl_ca_certs: Vec<Certificate>,
 
     /// Current availability zone. Used for traffic metrics.
     pub availability_zone: Option<String>,
@@ -119,13 +118,13 @@ pub struct PageServerConf {
     /// A lower value implicitly deprioritizes loading such tenants, vs. other work in the system.
     pub concurrent_tenant_warmup: ConfigurableSemaphore,
 
-    /// Number of concurrent [`TenantShard::gather_size_inputs`](crate::tenant::TenantShard::gather_size_inputs) allowed.
+    /// Number of concurrent [`Tenant::gather_size_inputs`](crate::tenant::Tenant::gather_size_inputs) allowed.
     pub concurrent_tenant_size_logical_size_queries: ConfigurableSemaphore,
-    /// Limit of concurrent [`TenantShard::gather_size_inputs`] issued by module `eviction_task`.
+    /// Limit of concurrent [`Tenant::gather_size_inputs`] issued by module `eviction_task`.
     /// The number of permits is the same as `concurrent_tenant_size_logical_size_queries`.
     /// See the comment in `eviction_task` for details.
     ///
-    /// [`TenantShard::gather_size_inputs`]: crate::tenant::TenantShard::gather_size_inputs
+    /// [`Tenant::gather_size_inputs`]: crate::tenant::Tenant::gather_size_inputs
     pub eviction_task_immitated_concurrent_logical_size_queries: ConfigurableSemaphore,
 
     // How often to collect metrics and send them to the metrics endpoint.
@@ -225,11 +224,6 @@ pub struct PageServerConf {
     /// Does not force TLS: the client negotiates TLS usage during the handshake.
     /// Uses key and certificate from ssl_key_file/ssl_cert_file.
     pub enable_tls_page_service_api: bool,
-
-    /// Run in development mode, which disables certain safety checks
-    /// such as authentication requirements for HTTP and PostgreSQL APIs.
-    /// This is insecure and should only be used in development environments.
-    pub dev_mode: bool,
 }
 
 /// Token for authentication to safekeepers
@@ -403,7 +397,6 @@ impl PageServerConf {
             generate_unarchival_heatmap,
             tracing,
             enable_tls_page_service_api,
-            dev_mode,
         } = config_toml;
 
         let mut conf = PageServerConf {
@@ -455,7 +448,6 @@ impl PageServerConf {
             get_vectored_concurrent_io,
             tracing,
             enable_tls_page_service_api,
-            dev_mode,
 
             // ------------------------------------------------------------
             // fields that require additional validation or custom handling
@@ -505,10 +497,7 @@ impl PageServerConf {
             ssl_ca_certs: match ssl_ca_file {
                 Some(ssl_ca_file) => {
                     let buf = std::fs::read(ssl_ca_file)?;
-                    pem::parse_many(&buf)?
-                        .into_iter()
-                        .filter(|pem| pem.tag() == "CERTIFICATE")
-                        .collect()
+                    Certificate::from_pem_bundle(&buf)?
                 }
                 None => Vec::new(),
             },
@@ -599,10 +588,10 @@ impl ConfigurableSemaphore {
     /// Initializse using a non-zero amount of permits.
     ///
     /// Require a non-zero initial permits, because using permits == 0 is a crude way to disable a
-    /// feature such as [`TenantShard::gather_size_inputs`]. Otherwise any semaphore using future will
+    /// feature such as [`Tenant::gather_size_inputs`]. Otherwise any semaphore using future will
     /// behave like [`futures::future::pending`], just waiting until new permits are added.
     ///
-    /// [`TenantShard::gather_size_inputs`]: crate::tenant::TenantShard::gather_size_inputs
+    /// [`Tenant::gather_size_inputs`]: crate::tenant::Tenant::gather_size_inputs
     pub fn new(initial_permits: NonZeroUsize) -> Self {
         ConfigurableSemaphore {
             initial_permits,

pageserver/src/consumption_metrics.rs

@@ -24,7 +24,7 @@ use crate::task_mgr::{self, BACKGROUND_RUNTIME, TaskKind};
 use crate::tenant::mgr::TenantManager;
 use crate::tenant::size::CalculateSyntheticSizeError;
 use crate::tenant::tasks::BackgroundLoopKind;
-use crate::tenant::{LogicalSizeCalculationCause, TenantShard};
+use crate::tenant::{LogicalSizeCalculationCause, Tenant};
 
 mod disk_cache;
 mod metrics;
@@ -428,7 +428,7 @@ async fn calculate_synthetic_size_worker(
     }
 }
 
-async fn calculate_and_log(tenant: &TenantShard, cancel: &CancellationToken, ctx: &RequestContext) {
+async fn calculate_and_log(tenant: &Tenant, cancel: &CancellationToken, ctx: &RequestContext) {
     const CAUSE: LogicalSizeCalculationCause =
         LogicalSizeCalculationCause::ConsumptionMetricsSyntheticSize;
 

pageserver/src/consumption_metrics/metrics.rs

@@ -175,9 +175,9 @@ impl MetricsKey {
         .absolute_values()
     }
 
-    /// [`TenantShard::remote_size`]
+    /// [`Tenant::remote_size`]
     ///
-    /// [`TenantShard::remote_size`]: crate::tenant::TenantShard::remote_size
+    /// [`Tenant::remote_size`]: crate::tenant::Tenant::remote_size
     const fn remote_storage_size(tenant_id: TenantId) -> AbsoluteValueFactory {
         MetricsKey {
             tenant_id,
@@ -199,9 +199,9 @@ impl MetricsKey {
         .absolute_values()
     }
 
-    /// [`TenantShard::cached_synthetic_size`] as refreshed by [`calculate_synthetic_size_worker`].
+    /// [`Tenant::cached_synthetic_size`] as refreshed by [`calculate_synthetic_size_worker`].
     ///
-    /// [`TenantShard::cached_synthetic_size`]: crate::tenant::TenantShard::cached_synthetic_size
+    /// [`Tenant::cached_synthetic_size`]: crate::tenant::Tenant::cached_synthetic_size
     /// [`calculate_synthetic_size_worker`]: super::calculate_synthetic_size_worker
     const fn synthetic_size(tenant_id: TenantId) -> AbsoluteValueFactory {
         MetricsKey {
@@ -254,7 +254,7 @@ pub(super) async fn collect_all_metrics(
 
 async fn collect<S>(tenants: S, cache: &Cache, ctx: &RequestContext) -> Vec<NewRawMetric>
 where
-    S: futures::stream::Stream<Item = (TenantId, Arc<crate::tenant::TenantShard>)>,
+    S: futures::stream::Stream<Item = (TenantId, Arc<crate::tenant::Tenant>)>,
 {
     let mut current_metrics: Vec<NewRawMetric> = Vec::new();
 
@@ -263,9 +263,7 @@ where
     while let Some((tenant_id, tenant)) = tenants.next().await {
         let mut tenant_resident_size = 0;
 
-        let timelines = tenant.list_timelines();
-        let timelines_len = timelines.len();
-        for timeline in timelines {
+        for timeline in tenant.list_timelines() {
             let timeline_id = timeline.timeline_id;
 
             match TimelineSnapshot::collect(&timeline, ctx) {
@@ -291,11 +289,6 @@ where
             tenant_resident_size += timeline.resident_physical_size();
         }
 
-        if timelines_len == 0 {
-            // Force set it to 1 byte to avoid not being reported -- all timelines are offloaded.
-            tenant_resident_size = 1;
-        }
-
         let snap = TenantSnapshot::collect(&tenant, tenant_resident_size);
         snap.to_metrics(tenant_id, Utc::now(), cache, &mut current_metrics);
     }
@@ -315,7 +308,7 @@ impl TenantSnapshot {
     ///
     /// `resident_size` is calculated of the timelines we had access to for other metrics, so we
     /// cannot just list timelines here.
-    fn collect(t: &Arc<crate::tenant::TenantShard>, resident_size: u64) -> Self {
+    fn collect(t: &Arc<crate::tenant::Tenant>, resident_size: u64) -> Self {
         TenantSnapshot {
             resident_size,
             remote_size: t.remote_size(),

pageserver/src/controller_upcall_client.rs

@@ -3,19 +3,17 @@ use std::collections::HashMap;
 use futures::Future;
 use pageserver_api::config::NodeMetadata;
 use pageserver_api::controller_api::{AvailabilityZone, NodeRegisterRequest};
-use pageserver_api::models::ShardImportStatus;
 use pageserver_api::shard::TenantShardId;
 use pageserver_api::upcall_api::{
-    PutTimelineImportStatusRequest, ReAttachRequest, ReAttachResponse, ReAttachResponseTenant,
-    ValidateRequest, ValidateRequestTenant, ValidateResponse,
+    ReAttachRequest, ReAttachResponse, ReAttachResponseTenant, ValidateRequest,
+    ValidateRequestTenant, ValidateResponse,
 };
-use reqwest::Certificate;
 use serde::Serialize;
 use serde::de::DeserializeOwned;
 use tokio_util::sync::CancellationToken;
 use url::Url;
 use utils::generation::Generation;
-use utils::id::{NodeId, TimelineId};
+use utils::id::NodeId;
 use utils::{backoff, failpoint_support};
 
 use crate::config::PageServerConf;
@@ -47,12 +45,6 @@ pub trait StorageControllerUpcallApi {
         &self,
         tenants: Vec<(TenantShardId, Generation)>,
     ) -> impl Future<Output = Result<HashMap<TenantShardId, bool>, RetryForeverError>> + Send;
-    fn put_timeline_import_status(
-        &self,
-        tenant_shard_id: TenantShardId,
-        timeline_id: TimelineId,
-        status: ShardImportStatus,
-    ) -> impl Future<Output = Result<(), RetryForeverError>> + Send;
 }
 
 impl StorageControllerUpcallClient {
@@ -84,8 +76,8 @@ impl StorageControllerUpcallClient {
             client = client.default_headers(headers);
         }
 
-        for cert in &conf.ssl_ca_certs {
-            client = client.add_root_certificate(Certificate::from_der(cert.contents())?);
+        for ssl_ca_cert in &conf.ssl_ca_certs {
+            client = client.add_root_certificate(ssl_ca_cert.clone());
         }
 
         Ok(Some(Self {
@@ -280,30 +272,4 @@ impl StorageControllerUpcallApi for StorageControllerUpcallClient {
 
         Ok(result.into_iter().collect())
     }
-
-    /// Send a shard import status to the storage controller
-    ///
-    /// The implementation must have at-least-once delivery semantics.
-    /// To this end, we retry the request until it succeeds. If the pageserver
-    /// restarts or crashes, the shard import will start again from the beggining.
-    #[tracing::instrument(skip_all)] // so that warning logs from retry_http_forever have context
-    async fn put_timeline_import_status(
-        &self,
-        tenant_shard_id: TenantShardId,
-        timeline_id: TimelineId,
-        status: ShardImportStatus,
-    ) -> Result<(), RetryForeverError> {
-        let url = self
-            .base_url
-            .join("timeline_import_status")
-            .expect("Failed to build path");
-
-        let request = PutTimelineImportStatusRequest {
-            tenant_shard_id,
-            timeline_id,
-            status,
-        };
-
-        self.retry_http_forever(&url, request).await
-    }
 }

pageserver/src/deletion_queue.rs

@@ -787,15 +787,6 @@ mod test {
 
             Ok(result)
         }
-
-        async fn put_timeline_import_status(
-            &self,
-            _tenant_shard_id: TenantShardId,
-            _timeline_id: TimelineId,
-            _status: pageserver_api::models::ShardImportStatus,
-        ) -> Result<(), RetryForeverError> {
-            unimplemented!()
-        }
     }
 
     async fn setup(test_name: &str) -> anyhow::Result<TestSetup> {

pageserver/src/http/routes.rs

@@ -1873,7 +1873,7 @@ async fn update_tenant_config_handler(
         &ShardParameters::default(),
     );
 
-    crate::tenant::TenantShard::persist_tenant_config(state.conf, &tenant_shard_id, &location_conf)
+    crate::tenant::Tenant::persist_tenant_config(state.conf, &tenant_shard_id, &location_conf)
         .await
         .map_err(|e| ApiError::InternalServerError(anyhow::anyhow!(e)))?;
 
@@ -1917,7 +1917,7 @@ async fn patch_tenant_config_handler(
         &ShardParameters::default(),
     );
 
-    crate::tenant::TenantShard::persist_tenant_config(state.conf, &tenant_shard_id, &location_conf)
+    crate::tenant::Tenant::persist_tenant_config(state.conf, &tenant_shard_id, &location_conf)
         .await
         .map_err(|e| ApiError::InternalServerError(anyhow::anyhow!(e)))?;
 

pageserver/src/lib.rs

@@ -49,7 +49,7 @@ use tracing::{info, info_span};
 /// backwards-compatible changes to the metadata format.
 pub const STORAGE_FORMAT_VERSION: u16 = 3;
 
-pub const DEFAULT_PG_VERSION: u32 = 17;
+pub const DEFAULT_PG_VERSION: u32 = 16;
 
 // Magic constants used to identify different kinds of files
 pub const IMAGE_FILE_MAGIC: u16 = 0x5A60;

pageserver/src/metrics.rs

@@ -17,7 +17,7 @@ use metrics::{
 use once_cell::sync::Lazy;
 use pageserver_api::config::{
     PageServicePipeliningConfig, PageServicePipeliningConfigPipelined,
-    PageServiceProtocolPipelinedBatchingStrategy, PageServiceProtocolPipelinedExecutionStrategy,
+    PageServiceProtocolPipelinedExecutionStrategy,
 };
 use pageserver_api::models::InMemoryLayerInfo;
 use pageserver_api::shard::TenantShardId;
@@ -1086,7 +1086,7 @@ pub(crate) static TIMELINE_EPHEMERAL_BYTES: Lazy<UIntGauge> = Lazy::new(|| {
     .expect("Failed to register metric")
 });
 
-/// Metrics related to the lifecycle of a [`crate::tenant::TenantShard`] object: things
+/// Metrics related to the lifecycle of a [`crate::tenant::Tenant`] object: things
 /// like how long it took to load.
 ///
 /// Note that these are process-global metrics, _not_ per-tenant metrics.  Per-tenant
@@ -1289,7 +1289,6 @@ pub(crate) enum StorageIoOperation {
     Seek,
     Fsync,
     Metadata,
-    SetLen,
 }
 
 impl StorageIoOperation {
@@ -1304,7 +1303,6 @@ impl StorageIoOperation {
             StorageIoOperation::Seek => "seek",
             StorageIoOperation::Fsync => "fsync",
             StorageIoOperation::Metadata => "metadata",
-            StorageIoOperation::SetLen => "set_len",
         }
     }
 }
@@ -1716,28 +1714,6 @@ pub enum SmgrQueryType {
     Test,
 }
 
-#[derive(
-    Debug,
-    Clone,
-    Copy,
-    IntoStaticStr,
-    strum_macros::EnumCount,
-    strum_macros::EnumIter,
-    strum_macros::FromRepr,
-    enum_map::Enum,
-)]
-#[strum(serialize_all = "snake_case")]
-pub enum GetPageBatchBreakReason {
-    BatchFull,
-    NonBatchableRequest,
-    NonUniformLsn,
-    SamePageAtDifferentLsn,
-    NonUniformTimeline,
-    ExecutorSteal,
-    #[cfg(feature = "testing")]
-    NonUniformKey,
-}
-
 pub(crate) struct SmgrQueryTimePerTimeline {
     global_started: [IntCounter; SmgrQueryType::COUNT],
     global_latency: [Histogram; SmgrQueryType::COUNT],
@@ -1749,8 +1725,6 @@ pub(crate) struct SmgrQueryTimePerTimeline {
     per_timeline_flush_in_progress_micros: IntCounter,
     global_batch_wait_time: Histogram,
     per_timeline_batch_wait_time: Histogram,
-    global_batch_break_reason: [IntCounter; GetPageBatchBreakReason::COUNT],
-    per_timeline_batch_break_reason: GetPageBatchBreakReasonTimelineMetrics,
     throttling: Arc<tenant_throttling::Pagestream>,
 }
 
@@ -1884,55 +1858,12 @@ static PAGE_SERVICE_BATCH_SIZE_PER_TENANT_TIMELINE: Lazy<HistogramVec> = Lazy::n
     .expect("failed to define a metric")
 });
 
-static PAGE_SERVICE_BATCH_BREAK_REASON_GLOBAL: Lazy<IntCounterVec> = Lazy::new(|| {
-    register_int_counter_vec!(
-        // it's a counter, but, name is prepared to extend it to a histogram of queue depth
-        "pageserver_page_service_batch_break_reason_global",
-        "Reason for breaking batches of get page requests",
-        &["reason"],
-    )
-    .expect("failed to define a metric")
-});
-
-struct GetPageBatchBreakReasonTimelineMetrics {
-    map: EnumMap<GetPageBatchBreakReason, IntCounter>,
-}
-
-impl GetPageBatchBreakReasonTimelineMetrics {
-    fn new(tenant_id: &str, shard_slug: &str, timeline_id: &str) -> Self {
-        GetPageBatchBreakReasonTimelineMetrics {
-            map: EnumMap::from_array(std::array::from_fn(|reason_idx| {
-                let reason = GetPageBatchBreakReason::from_usize(reason_idx);
-                PAGE_SERVICE_BATCH_BREAK_REASON_PER_TENANT_TIMELINE.with_label_values(&[
-                    tenant_id,
-                    shard_slug,
-                    timeline_id,
-                    reason.into(),
-                ])
-            })),
-        }
-    }
-
-    fn inc(&self, reason: GetPageBatchBreakReason) {
-        self.map[reason].inc()
-    }
-}
-
-static PAGE_SERVICE_BATCH_BREAK_REASON_PER_TENANT_TIMELINE: Lazy<IntCounterVec> = Lazy::new(|| {
-    register_int_counter_vec!(
-        "pageserver_page_service_batch_break_reason",
-        "Reason for breaking batches of get page requests",
-        &["tenant_id", "shard_id", "timeline_id", "reason"],
-    )
-    .expect("failed to define a metric")
-});
-
 pub(crate) static PAGE_SERVICE_CONFIG_MAX_BATCH_SIZE: Lazy<IntGaugeVec> = Lazy::new(|| {
     register_int_gauge_vec!(
         "pageserver_page_service_config_max_batch_size",
         "Configured maximum batch size for the server-side batching functionality of page_service. \
          Labels expose more of the configuration parameters.",
-        &["mode", "execution", "batching"]
+        &["mode", "execution"]
     )
     .expect("failed to define a metric")
 });
@@ -1940,11 +1871,10 @@ pub(crate) static PAGE_SERVICE_CONFIG_MAX_BATCH_SIZE: Lazy<IntGaugeVec> = Lazy::
 fn set_page_service_config_max_batch_size(conf: &PageServicePipeliningConfig) {
     PAGE_SERVICE_CONFIG_MAX_BATCH_SIZE.reset();
     let (label_values, value) = match conf {
-        PageServicePipeliningConfig::Serial => (["serial", "-", "-"], 1),
+        PageServicePipeliningConfig::Serial => (["serial", "-"], 1),
         PageServicePipeliningConfig::Pipelined(PageServicePipeliningConfigPipelined {
             max_batch_size,
             execution,
-            batching,
         }) => {
             let mode = "pipelined";
             let execution = match execution {
@@ -1953,12 +1883,7 @@ fn set_page_service_config_max_batch_size(conf: &PageServicePipeliningConfig) {
                 }
                 PageServiceProtocolPipelinedExecutionStrategy::Tasks => "tasks",
             };
-            let batching = match batching {
-                PageServiceProtocolPipelinedBatchingStrategy::UniformLsn => "uniform-lsn",
-                PageServiceProtocolPipelinedBatchingStrategy::ScatteredLsn => "scattered-lsn",
-            };
-
-            ([mode, execution, batching], max_batch_size.get())
+            ([mode, execution], max_batch_size.get())
         }
     };
     PAGE_SERVICE_CONFIG_MAX_BATCH_SIZE
@@ -2054,15 +1979,6 @@ impl SmgrQueryTimePerTimeline {
             .get_metric_with_label_values(&[&tenant_id, &shard_slug, &timeline_id])
             .unwrap();
 
-        let global_batch_break_reason = std::array::from_fn(|i| {
-            let reason = GetPageBatchBreakReason::from_usize(i);
-            PAGE_SERVICE_BATCH_BREAK_REASON_GLOBAL
-                .get_metric_with_label_values(&[reason.into()])
-                .unwrap()
-        });
-        let per_timeline_batch_break_reason =
-            GetPageBatchBreakReasonTimelineMetrics::new(&tenant_id, &shard_slug, &timeline_id);
-
         let global_flush_in_progress_micros =
             PAGE_SERVICE_SMGR_FLUSH_INPROGRESS_MICROS_GLOBAL.clone();
         let per_timeline_flush_in_progress_micros = PAGE_SERVICE_SMGR_FLUSH_INPROGRESS_MICROS
@@ -2080,8 +1996,6 @@ impl SmgrQueryTimePerTimeline {
             per_timeline_flush_in_progress_micros,
             global_batch_wait_time,
             per_timeline_batch_wait_time,
-            global_batch_break_reason,
-            per_timeline_batch_break_reason,
             throttling: pagestream_throttle_metrics,
         }
     }
@@ -2110,16 +2024,9 @@ impl SmgrQueryTimePerTimeline {
     }
 
     /// TODO: do something about this? seems odd, we have a similar call on SmgrOpTimer
-    pub(crate) fn observe_getpage_batch_start(
-        &self,
-        batch_size: usize,
-        break_reason: GetPageBatchBreakReason,
-    ) {
+    pub(crate) fn observe_getpage_batch_start(&self, batch_size: usize) {
         self.global_batch_size.observe(batch_size as f64);
         self.per_timeline_batch_size.observe(batch_size as f64);
-
-        self.global_batch_break_reason[break_reason.into_usize()].inc();
-        self.per_timeline_batch_break_reason.inc(break_reason);
     }
 }
 
@@ -3485,15 +3392,6 @@ impl TimelineMetrics {
             shard_id,
             timeline_id,
         ]);
-
-        for reason in GetPageBatchBreakReason::iter() {
-            let _ = PAGE_SERVICE_BATCH_BREAK_REASON_PER_TENANT_TIMELINE.remove_label_values(&[
-                tenant_id,
-                shard_id,
-                timeline_id,
-                reason.into(),
-            ]);
-        }
     }
 }
 
@@ -4372,7 +4270,6 @@ pub fn preinitialize_metrics(
     [
         &BACKGROUND_LOOP_PERIOD_OVERRUN_COUNT,
         &SMGR_QUERY_STARTED_GLOBAL,
-        &PAGE_SERVICE_BATCH_BREAK_REASON_GLOBAL,
     ]
     .into_iter()
     .for_each(|c| {

pageserver/src/page_service.rs

@@ -15,11 +15,10 @@ use async_compression::tokio::write::GzipEncoder;
 use bytes::Buf;
 use futures::FutureExt;
 use itertools::Itertools;
-use jsonwebtoken::TokenData;
 use once_cell::sync::OnceCell;
 use pageserver_api::config::{
     PageServicePipeliningConfig, PageServicePipeliningConfigPipelined,
-    PageServiceProtocolPipelinedBatchingStrategy, PageServiceProtocolPipelinedExecutionStrategy,
+    PageServiceProtocolPipelinedExecutionStrategy,
 };
 use pageserver_api::key::rel_block_to_key;
 use pageserver_api::models::{
@@ -59,8 +58,8 @@ use crate::context::{
     DownloadBehavior, PerfInstrumentFutureExt, RequestContext, RequestContextBuilder,
 };
 use crate::metrics::{
-    self, COMPUTE_COMMANDS_COUNTERS, ComputeCommandKind, GetPageBatchBreakReason, LIVE_CONNECTIONS,
-    SmgrOpTimer, TimelineMetrics,
+    self, COMPUTE_COMMANDS_COUNTERS, ComputeCommandKind, LIVE_CONNECTIONS, SmgrOpTimer,
+    TimelineMetrics,
 };
 use crate::pgdatadir_mapping::Version;
 use crate::span::{
@@ -76,7 +75,7 @@ use crate::tenant::timeline::{self, WaitLsnError};
 use crate::tenant::{GetTimelineError, PageReconstructError, Timeline};
 use crate::{basebackup, timed_after_cancellation};
 
-/// How long we may wait for a [`crate::tenant::mgr::TenantSlot::InProgress`]` and/or a [`crate::tenant::TenantShard`] which
+/// How long we may wait for a [`crate::tenant::mgr::TenantSlot::InProgress`]` and/or a [`crate::tenant::Tenant`] which
 /// is not yet in state [`TenantState::Active`].
 ///
 /// NB: this is a different value than [`crate::http::routes::ACTIVE_TENANT_TIMEOUT`].
@@ -642,7 +641,6 @@ impl std::fmt::Display for BatchedPageStreamError {
 struct BatchedGetPageRequest {
     req: PagestreamGetPageRequest,
     timer: SmgrOpTimer,
-    effective_request_lsn: Lsn,
     ctx: RequestContext,
 }
 
@@ -672,8 +670,8 @@ enum BatchedFeMessage {
     GetPage {
         span: Span,
         shard: timeline::handle::WeakHandle<TenantManagerTypes>,
+        effective_request_lsn: Lsn,
         pages: smallvec::SmallVec<[BatchedGetPageRequest; 1]>,
-        batch_break_reason: GetPageBatchBreakReason,
     },
     DbSize {
         span: Span,
@@ -726,119 +724,6 @@ impl BatchedFeMessage {
             BatchedFeMessage::RespondError { .. } => {}
         }
     }
-
-    fn should_break_batch(
-        &self,
-        other: &BatchedFeMessage,
-        max_batch_size: NonZeroUsize,
-        batching_strategy: PageServiceProtocolPipelinedBatchingStrategy,
-    ) -> Option<GetPageBatchBreakReason> {
-        match (self, other) {
-            (
-                BatchedFeMessage::GetPage {
-                    shard: accum_shard,
-                    pages: accum_pages,
-                    ..
-                },
-                BatchedFeMessage::GetPage {
-                    shard: this_shard,
-                    pages: this_pages,
-                    ..
-                },
-            ) => {
-                assert_eq!(this_pages.len(), 1);
-                if accum_pages.len() >= max_batch_size.get() {
-                    trace!(%max_batch_size, "stopping batching because of batch size");
-                    assert_eq!(accum_pages.len(), max_batch_size.get());
-
-                    return Some(GetPageBatchBreakReason::BatchFull);
-                }
-                if !accum_shard.is_same_handle_as(this_shard) {
-                    trace!("stopping batching because timeline object mismatch");
-                    // TODO: we _could_ batch & execute each shard seperately (and in parallel).
-                    // But the current logic for keeping responses in order does not support that.
-
-                    return Some(GetPageBatchBreakReason::NonUniformTimeline);
-                }
-
-                match batching_strategy {
-                    PageServiceProtocolPipelinedBatchingStrategy::UniformLsn => {
-                        if let Some(last_in_batch) = accum_pages.last() {
-                            if last_in_batch.effective_request_lsn
-                                != this_pages[0].effective_request_lsn
-                            {
-                                trace!(
-                                    accum_lsn = %last_in_batch.effective_request_lsn,
-                                    this_lsn = %this_pages[0].effective_request_lsn,
-                                    "stopping batching because LSN changed"
-                                );
-
-                                return Some(GetPageBatchBreakReason::NonUniformLsn);
-                            }
-                        }
-                    }
-                    PageServiceProtocolPipelinedBatchingStrategy::ScatteredLsn => {
-                        // The read path doesn't curently support serving the same page at different LSNs.
-                        // While technically possible, it's uncertain if the complexity is worth it.
-                        // Break the batch if such a case is encountered.
-                        let same_page_different_lsn = accum_pages.iter().any(|batched| {
-                            batched.req.rel == this_pages[0].req.rel
-                                && batched.req.blkno == this_pages[0].req.blkno
-                                && batched.effective_request_lsn
-                                    != this_pages[0].effective_request_lsn
-                        });
-
-                        if same_page_different_lsn {
-                            trace!(
-                                rel=%this_pages[0].req.rel,
-                                blkno=%this_pages[0].req.blkno,
-                                lsn=%this_pages[0].effective_request_lsn,
-                                "stopping batching because same page was requested at different LSNs"
-                            );
-
-                            return Some(GetPageBatchBreakReason::SamePageAtDifferentLsn);
-                        }
-                    }
-                }
-
-                None
-            }
-            #[cfg(feature = "testing")]
-            (
-                BatchedFeMessage::Test {
-                    shard: accum_shard,
-                    requests: accum_requests,
-                    ..
-                },
-                BatchedFeMessage::Test {
-                    shard: this_shard,
-                    requests: this_requests,
-                    ..
-                },
-            ) => {
-                assert!(this_requests.len() == 1);
-                if accum_requests.len() >= max_batch_size.get() {
-                    trace!(%max_batch_size, "stopping batching because of batch size");
-                    assert_eq!(accum_requests.len(), max_batch_size.get());
-                    return Some(GetPageBatchBreakReason::BatchFull);
-                }
-                if !accum_shard.is_same_handle_as(this_shard) {
-                    trace!("stopping batching because timeline object mismatch");
-                    // TODO: we _could_ batch & execute each shard seperately (and in parallel).
-                    // But the current logic for keeping responses in order does not support that.
-                    return Some(GetPageBatchBreakReason::NonUniformTimeline);
-                }
-                let this_batch_key = this_requests[0].req.batch_key;
-                let accum_batch_key = accum_requests[0].req.batch_key;
-                if this_requests[0].req.batch_key != accum_requests[0].req.batch_key {
-                    trace!(%accum_batch_key, %this_batch_key, "stopping batching because batch key changed");
-                    return Some(GetPageBatchBreakReason::NonUniformKey);
-                }
-                None
-            }
-            (_, _) => Some(GetPageBatchBreakReason::NonBatchableRequest),
-        }
-    }
 }
 
 impl PageServerHandler {
@@ -1140,32 +1025,34 @@ impl PageServerHandler {
                 .await?;
 
                 // We're holding the Handle
-                let effective_request_lsn = match Self::effective_request_lsn(
+                // TODO: if we actually need to wait for lsn here, it delays the entire batch which doesn't need to wait
+                let res = Self::wait_or_get_last_lsn(
                     &shard,
-                    shard.get_last_record_lsn(),
                     req.hdr.request_lsn,
                     req.hdr.not_modified_since,
                     &shard.get_applied_gc_cutoff_lsn(),
-                ) {
+                    &ctx,
+                )
+                .maybe_perf_instrument(&ctx, |current_perf_span| {
+                    info_span!(
+                        target: PERF_TRACE_TARGET,
+                        parent: current_perf_span,
+                        "WAIT_LSN",
+                    )
+                })
+                .await;
+
+                let effective_request_lsn = match res {
                     Ok(lsn) => lsn,
                     Err(e) => {
                         return respond_error!(span, e);
                     }
                 };
-
                 BatchedFeMessage::GetPage {
                     span,
                     shard: shard.downgrade(),
-                    pages: smallvec::smallvec![BatchedGetPageRequest {
-                        req,
-                        timer,
-                        effective_request_lsn,
-                        ctx,
-                    }],
-                    // The executor grabs the batch when it becomes idle.
-                    // Hence, [`GetPageBatchBreakReason::ExecutorSteal`] is the
-                    // default reason for breaking the batch.
-                    batch_break_reason: GetPageBatchBreakReason::ExecutorSteal,
+                    effective_request_lsn,
+                    pages: smallvec::smallvec![BatchedGetPageRequest { req, timer, ctx }],
                 }
             }
             #[cfg(feature = "testing")]
@@ -1191,7 +1078,6 @@ impl PageServerHandler {
     #[instrument(skip_all, level = tracing::Level::TRACE)]
     #[allow(clippy::boxed_local)]
     fn pagestream_do_batch(
-        batching_strategy: PageServiceProtocolPipelinedBatchingStrategy,
         max_batch_size: NonZeroUsize,
         batch: &mut Result<BatchedFeMessage, QueryError>,
         this_msg: Result<BatchedFeMessage, QueryError>,
@@ -1203,58 +1089,89 @@ impl PageServerHandler {
             Err(e) => return Err(Err(e)),
         };
 
-        let eligible_batch = match batch {
-            Ok(b) => b,
-            Err(_) => {
-                return Err(Ok(this_msg));
-            }
-        };
-
-        let batch_break =
-            eligible_batch.should_break_batch(&this_msg, max_batch_size, batching_strategy);
-
-        match batch_break {
-            Some(reason) => {
-                if let BatchedFeMessage::GetPage {
-                    batch_break_reason, ..
-                } = eligible_batch
-                {
-                    *batch_break_reason = reason;
+        match (&mut *batch, this_msg) {
+            // something batched already, let's see if we can add this message to the batch
+            (
+                Ok(BatchedFeMessage::GetPage {
+                    span: _,
+                    shard: accum_shard,
+                    pages: accum_pages,
+                    effective_request_lsn: accum_lsn,
+                }),
+                BatchedFeMessage::GetPage {
+                    span: _,
+                    shard: this_shard,
+                    pages: this_pages,
+                    effective_request_lsn: this_lsn,
+                },
+            ) if (|| {
+                assert_eq!(this_pages.len(), 1);
+                if accum_pages.len() >= max_batch_size.get() {
+                    trace!(%accum_lsn, %this_lsn, %max_batch_size, "stopping batching because of batch size");
+                    assert_eq!(accum_pages.len(), max_batch_size.get());
+                    return false;
                 }
-
-                Err(Ok(this_msg))
-            }
-            None => {
+                if !accum_shard.is_same_handle_as(&this_shard) {
+                    trace!(%accum_lsn, %this_lsn, "stopping batching because timeline object mismatch");
+                    // TODO: we _could_ batch & execute each shard seperately (and in parallel).
+                    // But the current logic for keeping responses in order does not support that.
+                    return false;
+                }
+                // the vectored get currently only supports a single LSN, so, bounce as soon
+                // as the effective request_lsn changes
+                if *accum_lsn != this_lsn {
+                    trace!(%accum_lsn, %this_lsn, "stopping batching because LSN changed");
+                    return false;
+                }
+                true
+            })() =>
+            {
                 // ok to batch
-                match (eligible_batch, this_msg) {
-                    (
-                        BatchedFeMessage::GetPage {
-                            pages: accum_pages, ..
-                        },
-                        BatchedFeMessage::GetPage {
-                            pages: this_pages, ..
-                        },
-                    ) => {
-                        accum_pages.extend(this_pages);
-                        Ok(())
-                    }
-                    #[cfg(feature = "testing")]
-                    (
-                        BatchedFeMessage::Test {
-                            requests: accum_requests,
-                            ..
-                        },
-                        BatchedFeMessage::Test {
-                            requests: this_requests,
-                            ..
-                        },
-                    ) => {
-                        accum_requests.extend(this_requests);
-                        Ok(())
-                    }
-                    // Shape guaranteed by [`BatchedFeMessage::should_break_batch`]
-                    _ => unreachable!(),
+                accum_pages.extend(this_pages);
+                Ok(())
+            }
+            #[cfg(feature = "testing")]
+            (
+                Ok(BatchedFeMessage::Test {
+                    shard: accum_shard,
+                    requests: accum_requests,
+                    ..
+                }),
+                BatchedFeMessage::Test {
+                    shard: this_shard,
+                    requests: this_requests,
+                    ..
+                },
+            ) if (|| {
+                assert!(this_requests.len() == 1);
+                if accum_requests.len() >= max_batch_size.get() {
+                    trace!(%max_batch_size, "stopping batching because of batch size");
+                    assert_eq!(accum_requests.len(), max_batch_size.get());
+                    return false;
                 }
+                if !accum_shard.is_same_handle_as(&this_shard) {
+                    trace!("stopping batching because timeline object mismatch");
+                    // TODO: we _could_ batch & execute each shard seperately (and in parallel).
+                    // But the current logic for keeping responses in order does not support that.
+                    return false;
+                }
+                let this_batch_key = this_requests[0].req.batch_key;
+                let accum_batch_key = accum_requests[0].req.batch_key;
+                if this_requests[0].req.batch_key != accum_requests[0].req.batch_key {
+                    trace!(%accum_batch_key, %this_batch_key, "stopping batching because batch key changed");
+                    return false;
+                }
+                true
+            })() =>
+            {
+                // ok to batch
+                accum_requests.extend(this_requests);
+                Ok(())
+            }
+            // something batched already but this message is unbatchable
+            (_, this_msg) => {
+                // by default, don't continue batching
+                Err(Ok(this_msg))
             }
         }
     }
@@ -1476,8 +1393,8 @@ impl PageServerHandler {
             BatchedFeMessage::GetPage {
                 span,
                 shard,
+                effective_request_lsn,
                 pages,
-                batch_break_reason,
             } => {
                 fail::fail_point!("ps::handle-pagerequest-message::getpage");
                 let (shard, ctx) = upgrade_handle_and_set_context!(shard);
@@ -1488,9 +1405,9 @@ impl PageServerHandler {
                         let res = self
                             .handle_get_page_at_lsn_request_batched(
                                 &shard,
+                                effective_request_lsn,
                                 pages,
                                 io_concurrency,
-                                batch_break_reason,
                                 &ctx,
                             )
                             .instrument(span.clone())
@@ -1807,7 +1724,6 @@ impl PageServerHandler {
         let PageServicePipeliningConfigPipelined {
             max_batch_size,
             execution,
-            batching: batching_strategy,
         } = pipelining_config;
 
         // Macro to _define_ a pipeline stage.
@@ -1859,7 +1775,7 @@ impl PageServerHandler {
                     exit |= read_res.is_err();
                     let could_send = batch_tx
                         .send(read_res, |batch, res| {
-                            Self::pagestream_do_batch(batching_strategy, max_batch_size, batch, res)
+                            Self::pagestream_do_batch(max_batch_size, batch, res)
                         })
                         .await;
                     exit |= could_send.is_err();
@@ -1955,39 +1871,7 @@ impl PageServerHandler {
         ctx: &RequestContext,
     ) -> Result<Lsn, PageStreamError> {
         let last_record_lsn = timeline.get_last_record_lsn();
-        let effective_request_lsn = Self::effective_request_lsn(
-            timeline,
-            last_record_lsn,
-            request_lsn,
-            not_modified_since,
-            latest_gc_cutoff_lsn,
-        )?;
 
-        if effective_request_lsn > last_record_lsn {
-            timeline
-                .wait_lsn(
-                    not_modified_since,
-                    crate::tenant::timeline::WaitLsnWaiter::PageService,
-                    timeline::WaitLsnTimeout::Default,
-                    ctx,
-                )
-                .await?;
-
-            // Since we waited for 'effective_request_lsn' to arrive, that is now the last
-            // record LSN. (Or close enough for our purposes; the last-record LSN can
-            // advance immediately after we return anyway)
-        }
-
-        Ok(effective_request_lsn)
-    }
-
-    fn effective_request_lsn(
-        timeline: &Timeline,
-        last_record_lsn: Lsn,
-        request_lsn: Lsn,
-        not_modified_since: Lsn,
-        latest_gc_cutoff_lsn: &RcuReadGuard<Lsn>,
-    ) -> Result<Lsn, PageStreamError> {
         // Sanity check the request
         if request_lsn < not_modified_since {
             return Err(PageStreamError::BadRequest(
@@ -2022,7 +1906,19 @@ impl PageServerHandler {
             }
         }
 
+        // Wait for WAL up to 'not_modified_since' to arrive, if necessary
         if not_modified_since > last_record_lsn {
+            timeline
+                .wait_lsn(
+                    not_modified_since,
+                    crate::tenant::timeline::WaitLsnWaiter::PageService,
+                    timeline::WaitLsnTimeout::Default,
+                    ctx,
+                )
+                .await?;
+            // Since we waited for 'not_modified_since' to arrive, that is now the last
+            // record LSN. (Or close enough for our purposes; the last-record LSN can
+            // advance immediately after we return anyway)
             Ok(not_modified_since)
         } else {
             // It might be better to use max(not_modified_since, latest_gc_cutoff_lsn)
@@ -2177,16 +2073,16 @@ impl PageServerHandler {
     async fn handle_get_page_at_lsn_request_batched(
         &mut self,
         timeline: &Timeline,
+        effective_lsn: Lsn,
         requests: smallvec::SmallVec<[BatchedGetPageRequest; 1]>,
         io_concurrency: IoConcurrency,
-        batch_break_reason: GetPageBatchBreakReason,
         ctx: &RequestContext,
     ) -> Vec<Result<(PagestreamBeMessage, SmgrOpTimer), BatchedPageStreamError>> {
         debug_assert_current_span_has_tenant_and_timeline_id();
 
         timeline
             .query_metrics
-            .observe_getpage_batch_start(requests.len(), batch_break_reason);
+            .observe_getpage_batch_start(requests.len());
 
         // If a page trace is running, submit an event for this request.
         if let Some(page_trace) = timeline.page_trace.load().as_ref() {
@@ -2196,81 +2092,20 @@ impl PageServerHandler {
                 // Ignore error (trace buffer may be full or tracer may have disconnected).
                 _ = page_trace.try_send(PageTraceEvent {
                     key,
-                    effective_lsn: batch.effective_request_lsn,
+                    effective_lsn,
                     time,
                 });
             }
         }
 
-        // If any request in the batch needs to wait for LSN, then do so now.
-        let mut perf_instrument = false;
-        let max_effective_lsn = requests
-            .iter()
-            .map(|req| {
-                if req.ctx.has_perf_span() {
-                    perf_instrument = true;
-                }
-
-                req.effective_request_lsn
-            })
-            .max()
-            .expect("batch is never empty");
-
-        let ctx = match perf_instrument {
-            true => RequestContextBuilder::from(ctx)
-                .root_perf_span(|| {
-                    info_span!(
-                        target: PERF_TRACE_TARGET,
-                        "GET_VECTORED",
-                        tenant_id = %timeline.tenant_shard_id.tenant_id,
-                        timeline_id = %timeline.timeline_id,
-                        shard = %timeline.tenant_shard_id.shard_slug(),
-                        %max_effective_lsn
-                    )
-                })
-                .attached_child(),
-            false => ctx.attached_child(),
-        };
-
-        let last_record_lsn = timeline.get_last_record_lsn();
-        if max_effective_lsn > last_record_lsn {
-            if let Err(e) = timeline
-                .wait_lsn(
-                    max_effective_lsn,
-                    crate::tenant::timeline::WaitLsnWaiter::PageService,
-                    timeline::WaitLsnTimeout::Default,
-                    &ctx,
-                )
-                .maybe_perf_instrument(&ctx, |current_perf_span| {
-                    info_span!(
-                        target: PERF_TRACE_TARGET,
-                        parent: current_perf_span,
-                        "WAIT_LSN",
-                    )
-                })
-                .await
-            {
-                return Vec::from_iter(requests.into_iter().map(|req| {
-                    Err(BatchedPageStreamError {
-                        err: PageStreamError::from(e.clone()),
-                        req: req.req.hdr,
-                    })
-                }));
-            }
-        }
-
         let results = timeline
             .get_rel_page_at_lsn_batched(
-                requests.iter().map(|p| {
-                    (
-                        &p.req.rel,
-                        &p.req.blkno,
-                        p.effective_request_lsn,
-                        p.ctx.attached_child(),
-                    )
-                }),
+                requests
+                    .iter()
+                    .map(|p| (&p.req.rel, &p.req.blkno, p.ctx.attached_child())),
+                effective_lsn,
                 io_concurrency,
-                &ctx,
+                ctx,
             )
             .await;
         assert_eq!(results.len(), requests.len());
@@ -2838,7 +2673,7 @@ where
     ) -> Result<(), QueryError> {
         // this unwrap is never triggered, because check_auth_jwt only called when auth_type is NeonJWT
         // which requires auth to be present
-        let data: TokenData<Claims> = self
+        let data = self
             .auth
             .as_ref()
             .unwrap()

pageserver/src/pgdatadir_mapping.rs

@@ -6,7 +6,7 @@
 //! walingest.rs handles a few things like implicit relation creation and extension.
 //! Clarify that)
 //!
-use std::collections::{HashMap, HashSet, hash_map};
+use std::collections::{BTreeMap, HashMap, HashSet, hash_map};
 use std::ops::{ControlFlow, Range};
 
 use crate::walingest::{WalIngestError, WalIngestErrorKind};
@@ -14,6 +14,7 @@ use crate::{PERF_TRACE_TARGET, ensure_walingest};
 use anyhow::Context;
 use bytes::{Buf, Bytes, BytesMut};
 use enum_map::Enum;
+use itertools::Itertools;
 use pageserver_api::key::{
     AUX_FILES_KEY, CHECKPOINT_KEY, CONTROLFILE_KEY, CompactKey, DBDIR_KEY, Key, RelDirExists,
     TWOPHASEDIR_KEY, dbdir_key_range, rel_block_to_key, rel_dir_to_key, rel_key_range,
@@ -21,7 +22,7 @@ use pageserver_api::key::{
     repl_origin_key, repl_origin_key_range, slru_block_to_key, slru_dir_to_key,
     slru_segment_key_range, slru_segment_size_to_key, twophase_file_key, twophase_key_range,
 };
-use pageserver_api::keyspace::{KeySpaceRandomAccum, SparseKeySpace};
+use pageserver_api::keyspace::SparseKeySpace;
 use pageserver_api::models::RelSizeMigration;
 use pageserver_api::record::NeonWalRecord;
 use pageserver_api::reltag::{BlockNumber, RelTag, SlruKind};
@@ -40,7 +41,7 @@ use wal_decoder::serialized_batch::{SerializedValueBatch, ValueMeta};
 
 use super::tenant::{PageReconstructError, Timeline};
 use crate::aux_file;
-use crate::context::{PerfInstrumentFutureExt, RequestContext};
+use crate::context::{PerfInstrumentFutureExt, RequestContext, RequestContextBuilder};
 use crate::keyspace::{KeySpace, KeySpaceAccum};
 use crate::metrics::{
     RELSIZE_CACHE_ENTRIES, RELSIZE_CACHE_HITS, RELSIZE_CACHE_MISSES, RELSIZE_CACHE_MISSES_OLD,
@@ -50,7 +51,7 @@ use crate::span::{
     debug_assert_current_span_has_tenant_and_timeline_id_no_shard_id,
 };
 use crate::tenant::storage_layer::IoConcurrency;
-use crate::tenant::timeline::{GetVectoredError, VersionedKeySpaceQuery};
+use crate::tenant::timeline::GetVectoredError;
 
 /// Max delta records appended to the AUX_FILES_KEY (for aux v1). The write path will write a full image once this threshold is reached.
 pub const MAX_AUX_FILE_DELTAS: usize = 1024;
@@ -206,9 +207,10 @@ impl Timeline {
                 let pages: smallvec::SmallVec<[_; 1]> = smallvec::smallvec![(tag, blknum)];
                 let res = self
                     .get_rel_page_at_lsn_batched(
-                        pages.iter().map(|(tag, blknum)| {
-                            (tag, blknum, effective_lsn, ctx.attached_child())
-                        }),
+                        pages
+                            .iter()
+                            .map(|(tag, blknum)| (tag, blknum, ctx.attached_child())),
+                        effective_lsn,
                         io_concurrency.clone(),
                         ctx,
                     )
@@ -246,7 +248,8 @@ impl Timeline {
     /// The ordering of the returned vec corresponds to the ordering of `pages`.
     pub(crate) async fn get_rel_page_at_lsn_batched(
         &self,
-        pages: impl ExactSizeIterator<Item = (&RelTag, &BlockNumber, Lsn, RequestContext)>,
+        pages: impl ExactSizeIterator<Item = (&RelTag, &BlockNumber, RequestContext)>,
+        effective_lsn: Lsn,
         io_concurrency: IoConcurrency,
         ctx: &RequestContext,
     ) -> Vec<Result<Bytes, PageReconstructError>> {
@@ -259,13 +262,11 @@ impl Timeline {
         let mut result = Vec::with_capacity(pages.len());
         let result_slots = result.spare_capacity_mut();
 
-        let mut keys_slots: HashMap<Key, smallvec::SmallVec<[(usize, RequestContext); 1]>> =
-            HashMap::with_capacity(pages.len());
+        let mut keys_slots: BTreeMap<Key, smallvec::SmallVec<[(usize, RequestContext); 1]>> =
+            BTreeMap::default();
 
-        let mut req_keyspaces: HashMap<Lsn, KeySpaceRandomAccum> =
-            HashMap::with_capacity(pages.len());
-
-        for (response_slot_idx, (tag, blknum, lsn, ctx)) in pages.enumerate() {
+        let mut perf_instrument = false;
+        for (response_slot_idx, (tag, blknum, ctx)) in pages.enumerate() {
             if tag.relnode == 0 {
                 result_slots[response_slot_idx].write(Err(PageReconstructError::Other(
                     RelationError::InvalidRelnode.into(),
@@ -276,14 +277,14 @@ impl Timeline {
             }
 
             let nblocks = match self
-                .get_rel_size(*tag, Version::Lsn(lsn), &ctx)
+                .get_rel_size(*tag, Version::Lsn(effective_lsn), &ctx)
                 .maybe_perf_instrument(&ctx, |crnt_perf_span| {
                     info_span!(
                         target: PERF_TRACE_TARGET,
                         parent: crnt_perf_span,
                         "GET_REL_SIZE",
                         reltag=%tag,
-                        lsn=%lsn,
+                        lsn=%effective_lsn,
                     )
                 })
                 .await
@@ -299,7 +300,7 @@ impl Timeline {
             if *blknum >= nblocks {
                 debug!(
                     "read beyond EOF at {} blk {} at {}, size is {}: returning all-zeros page",
-                    tag, blknum, lsn, nblocks
+                    tag, blknum, effective_lsn, nblocks
                 );
                 result_slots[response_slot_idx].write(Ok(ZERO_PAGE.clone()));
                 slots_filled += 1;
@@ -308,29 +309,46 @@ impl Timeline {
 
             let key = rel_block_to_key(*tag, *blknum);
 
+            if ctx.has_perf_span() {
+                perf_instrument = true;
+            }
+
             let key_slots = keys_slots.entry(key).or_default();
             key_slots.push((response_slot_idx, ctx));
-
-            let acc = req_keyspaces.entry(lsn).or_default();
-            acc.add_key(key);
         }
 
-        let query: Vec<(Lsn, KeySpace)> = req_keyspaces
-            .into_iter()
-            .map(|(lsn, acc)| (lsn, acc.to_keyspace()))
-            .collect();
+        let keyspace = {
+            // add_key requires monotonicity
+            let mut acc = KeySpaceAccum::new();
+            for key in keys_slots
+                .keys()
+                // in fact it requires strong monotonicity
+                .dedup()
+            {
+                acc.add_key(*key);
+            }
+            acc.to_keyspace()
+        };
+
+        let ctx = match perf_instrument {
+            true => RequestContextBuilder::from(ctx)
+                .root_perf_span(|| {
+                    info_span!(
+                        target: PERF_TRACE_TARGET,
+                        "GET_VECTORED",
+                        tenant_id = %self.tenant_shard_id.tenant_id,
+                        timeline_id = %self.timeline_id,
+                        lsn = %effective_lsn,
+                        shard = %self.tenant_shard_id.shard_slug(),
+                    )
+                })
+                .attached_child(),
+            false => ctx.attached_child(),
+        };
 
-        let query = VersionedKeySpaceQuery::scattered(query);
         let res = self
-            .get_vectored(query, io_concurrency, ctx)
-            .maybe_perf_instrument(ctx, |current_perf_span| {
-                info_span!(
-                    target: PERF_TRACE_TARGET,
-                    parent: current_perf_span,
-                    "GET_BATCH",
-                    batch_size = %page_count,
-                )
-            })
+            .get_vectored(keyspace, effective_lsn, io_concurrency, &ctx)
+            .maybe_perf_instrument(&ctx, |current_perf_span| current_perf_span.clone())
             .await;
 
         match res {
@@ -360,12 +378,12 @@ impl Timeline {
                         // There is no standardized way to express that the batched span followed from N request spans.
                         // So, abuse the system and mark the request contexts as follows_from the batch span, so we get
                         // some linkage in our trace viewer. It allows us to answer: which GET_VECTORED did this GET_PAGE wait for.
-                        req_ctx.perf_follows_from(ctx);
+                        req_ctx.perf_follows_from(&ctx);
                         slots_filled += 1;
                     }
 
                     result_slots[first_slot].write(res);
-                    first_req_ctx.perf_follows_from(ctx);
+                    first_req_ctx.perf_follows_from(&ctx);
                     slots_filled += 1;
                 }
             }
@@ -404,7 +422,7 @@ impl Timeline {
                         }
                     };
 
-                    req_ctx.perf_follows_from(ctx);
+                    req_ctx.perf_follows_from(&ctx);
                     result_slots[*slot].write(err);
                 }
 
@@ -643,9 +661,8 @@ impl Timeline {
 
         let mut segment = BytesMut::with_capacity(n_blocks as usize * BLCKSZ as usize);
         for batch in batches.parts {
-            let query = VersionedKeySpaceQuery::uniform(batch, lsn);
             let blocks = self
-                .get_vectored(query, io_concurrency.clone(), ctx)
+                .get_vectored(batch, lsn, io_concurrency.clone(), ctx)
                 .await?;
 
             for (_key, block) in blocks {
@@ -882,9 +899,8 @@ impl Timeline {
             );
 
             for batch in batches.parts.into_iter().rev() {
-                let query = VersionedKeySpaceQuery::uniform(batch, probe_lsn);
                 let blocks = self
-                    .get_vectored(query, io_concurrency.clone(), ctx)
+                    .get_vectored(batch, probe_lsn, io_concurrency.clone(), ctx)
                     .await?;
 
                 for (_key, clog_page) in blocks.into_iter().rev() {
@@ -1084,17 +1100,8 @@ impl Timeline {
         let mut result = HashMap::new();
         for (k, v) in kv {
             let v = v?;
-            if v.is_empty() {
-                // This is a tombstone -- we can skip it.
-                // Originally, the replorigin code uses `Lsn::INVALID` to represent a tombstone. However, as it part of
-                // the sparse keyspace and the sparse keyspace uses an empty image to universally represent a tombstone,
-                // we also need to consider that. Such tombstones might be written on the detach ancestor code path to
-                // avoid the value going into the child branch. (See [`crate::tenant::timeline::detach_ancestor::generate_tombstone_image_layer`] for more details.)
-                continue;
-            }
             let origin_id = k.field6 as RepOriginId;
-            let origin_lsn = Lsn::des(&v)
-                .with_context(|| format!("decode replorigin value for {}: {v:?}", origin_id))?;
+            let origin_lsn = Lsn::des(&v).unwrap();
             if origin_lsn != Lsn::INVALID {
                 result.insert(origin_id, origin_lsn);
             }
@@ -2587,11 +2594,6 @@ impl DatadirModification<'_> {
         }
     }
 
-    #[cfg(test)]
-    pub fn put_for_unit_test(&mut self, key: Key, val: Value) {
-        self.put(key, val);
-    }
-
     fn put(&mut self, key: Key, val: Value) {
         if Self::is_data_key(&key) {
             self.put_data(key.to_compact(), val)

pageserver/src/tenant/blob_io.rs

@@ -15,23 +15,21 @@
 //! len >= 128: 1CCCXXXX XXXXXXXX XXXXXXXX XXXXXXXX
 //!
 use std::cmp::min;
+use std::io::Error;
 
-use anyhow::Context;
 use async_compression::Level;
 use bytes::{BufMut, BytesMut};
 use pageserver_api::models::ImageCompressionAlgorithm;
 use tokio::io::AsyncWriteExt;
-use tokio_epoll_uring::IoBuf;
+use tokio_epoll_uring::{BoundedBuf, IoBuf, Slice};
 use tokio_util::sync::CancellationToken;
 use tracing::warn;
 
 use crate::context::RequestContext;
 use crate::page_cache::PAGE_SZ;
 use crate::tenant::block_io::BlockCursor;
-use crate::virtual_file::IoBufferMut;
+use crate::virtual_file::VirtualFile;
 use crate::virtual_file::owned_buffers_io::io_buf_ext::{FullSlice, IoBufExt};
-use crate::virtual_file::owned_buffers_io::write::{BufferedWriter, FlushTaskError};
-use crate::virtual_file::owned_buffers_io::write::{BufferedWriterShutdownMode, OwnedAsyncWriter};
 
 #[derive(Copy, Clone, Debug)]
 pub struct CompressionInfo {
@@ -39,67 +37,6 @@ pub struct CompressionInfo {
     pub compressed_size: Option<usize>,
 }
 
-/// A blob header, with header+data length and compression info.
-///
-/// TODO: use this more widely, and add an encode() method too.
-/// TODO: document the header format.
-#[derive(Clone, Copy, Default)]
-pub struct Header {
-    pub header_len: usize,
-    pub data_len: usize,
-    pub compression_bits: u8,
-}
-
-impl Header {
-    /// Decodes a header from a byte slice.
-    pub fn decode(bytes: &[u8]) -> anyhow::Result<Self> {
-        let Some(&first_header_byte) = bytes.first() else {
-            anyhow::bail!("zero-length blob header");
-        };
-
-        // If the first bit is 0, this is just a 1-byte length prefix up to 128 bytes.
-        if first_header_byte < 0x80 {
-            return Ok(Self {
-                header_len: 1, // by definition
-                data_len: first_header_byte as usize,
-                compression_bits: BYTE_UNCOMPRESSED,
-            });
-        }
-
-        // Otherwise, this is a 4-byte header containing compression information and length.
-        const HEADER_LEN: usize = 4;
-        let mut header_buf: [u8; HEADER_LEN] = bytes[0..HEADER_LEN]
-            .try_into()
-            .map_err(|_| anyhow::anyhow!("blob header too short: {bytes:?}"))?;
-
-        // TODO: verify the compression bits and convert to an enum.
-        let compression_bits = header_buf[0] & LEN_COMPRESSION_BIT_MASK;
-        header_buf[0] &= !LEN_COMPRESSION_BIT_MASK;
-        let data_len = u32::from_be_bytes(header_buf) as usize;
-
-        Ok(Self {
-            header_len: HEADER_LEN,
-            data_len,
-            compression_bits,
-        })
-    }
-
-    /// Returns the total header+data length.
-    pub fn total_len(&self) -> usize {
-        self.header_len + self.data_len
-    }
-}
-
-#[derive(Debug, thiserror::Error)]
-pub enum WriteBlobError {
-    #[error(transparent)]
-    Flush(FlushTaskError),
-    #[error("blob too large ({len} bytes)")]
-    BlobTooLarge { len: usize },
-    #[error(transparent)]
-    WriteBlobRaw(anyhow::Error),
-}
-
 impl BlockCursor<'_> {
     /// Read a blob into a new buffer.
     pub async fn read_blob(
@@ -219,64 +156,143 @@ pub(super) const BYTE_UNCOMPRESSED: u8 = 0x80;
 pub(super) const BYTE_ZSTD: u8 = BYTE_UNCOMPRESSED | 0x10;
 
 /// A wrapper of `VirtualFile` that allows users to write blobs.
-pub struct BlobWriter<W> {
+///
+/// If a `BlobWriter` is dropped, the internal buffer will be
+/// discarded. You need to call [`flush_buffer`](Self::flush_buffer)
+/// manually before dropping.
+pub struct BlobWriter<const BUFFERED: bool> {
+    inner: VirtualFile,
+    offset: u64,
+    /// A buffer to save on write calls, only used if BUFFERED=true
+    buf: Vec<u8>,
     /// We do tiny writes for the length headers; they need to be in an owned buffer;
     io_buf: Option<BytesMut>,
-    writer: BufferedWriter<IoBufferMut, W>,
-    offset: u64,
 }
 
-impl<W> BlobWriter<W>
-where
-    W: OwnedAsyncWriter + std::fmt::Debug + Send + Sync + 'static,
-{
-    /// See [`BufferedWriter`] struct-level doc comment for semantics of `start_offset`.
+impl<const BUFFERED: bool> BlobWriter<BUFFERED> {
     pub fn new(
-        file: W,
+        inner: VirtualFile,
         start_offset: u64,
-        gate: &utils::sync::gate::Gate,
-        cancel: CancellationToken,
-        ctx: &RequestContext,
-        flush_task_span: tracing::Span,
-    ) -> anyhow::Result<Self> {
-        Ok(Self {
-            io_buf: Some(BytesMut::new()),
-            writer: BufferedWriter::new(
-                file,
-                start_offset,
-                || IoBufferMut::with_capacity(Self::CAPACITY),
-                gate.enter()?,
-                cancel,
-                ctx,
-                flush_task_span,
-            ),
+        _gate: &utils::sync::gate::Gate,
+        _cancel: CancellationToken,
+        _ctx: &RequestContext,
+    ) -> Self {
+        Self {
+            inner,
             offset: start_offset,
-        })
+            buf: Vec::with_capacity(Self::CAPACITY),
+            io_buf: Some(BytesMut::new()),
+        }
     }
 
     pub fn size(&self) -> u64 {
         self.offset
     }
 
-    const CAPACITY: usize = 64 * 1024;
+    const CAPACITY: usize = if BUFFERED { 64 * 1024 } else { 0 };
 
-    /// Writes `src_buf` to the file at the current offset.
+    /// Writes the given buffer directly to the underlying `VirtualFile`.
+    /// You need to make sure that the internal buffer is empty, otherwise
+    /// data will be written in wrong order.
+    #[inline(always)]
+    async fn write_all_unbuffered<Buf: IoBuf + Send>(
+        &mut self,
+        src_buf: FullSlice<Buf>,
+        ctx: &RequestContext,
+    ) -> (FullSlice<Buf>, Result<(), Error>) {
+        let (src_buf, res) = self.inner.write_all(src_buf, ctx).await;
+        let nbytes = match res {
+            Ok(nbytes) => nbytes,
+            Err(e) => return (src_buf, Err(e)),
+        };
+        self.offset += nbytes as u64;
+        (src_buf, Ok(()))
+    }
+
+    #[inline(always)]
+    /// Flushes the internal buffer to the underlying `VirtualFile`.
+    pub async fn flush_buffer(&mut self, ctx: &RequestContext) -> Result<(), Error> {
+        let buf = std::mem::take(&mut self.buf);
+        let (slice, res) = self.inner.write_all(buf.slice_len(), ctx).await;
+        res?;
+        let mut buf = slice.into_raw_slice().into_inner();
+        buf.clear();
+        self.buf = buf;
+        Ok(())
+    }
+
+    #[inline(always)]
+    /// Writes as much of `src_buf` into the internal buffer as it fits
+    fn write_into_buffer(&mut self, src_buf: &[u8]) -> usize {
+        let remaining = Self::CAPACITY - self.buf.len();
+        let to_copy = src_buf.len().min(remaining);
+        self.buf.extend_from_slice(&src_buf[..to_copy]);
+        self.offset += to_copy as u64;
+        to_copy
+    }
+
+    /// Internal, possibly buffered, write function
     async fn write_all<Buf: IoBuf + Send>(
         &mut self,
         src_buf: FullSlice<Buf>,
         ctx: &RequestContext,
-    ) -> (FullSlice<Buf>, Result<(), FlushTaskError>) {
-        let res = self
-            .writer
-            // TODO: why are we taking a FullSlice if we're going to pass a borrow downstack?
-            // Can remove all the complexity around owned buffers upstack
-            .write_buffered_borrowed(&src_buf, ctx)
-            .await
-            .map(|len| {
-                self.offset += len as u64;
-            });
+    ) -> (FullSlice<Buf>, Result<(), Error>) {
+        let src_buf = src_buf.into_raw_slice();
+        let src_buf_bounds = src_buf.bounds();
+        let restore = move |src_buf_slice: Slice<_>| {
+            FullSlice::must_new(Slice::from_buf_bounds(
+                src_buf_slice.into_inner(),
+                src_buf_bounds,
+            ))
+        };
 
-        (src_buf, res)
+        if !BUFFERED {
+            assert!(self.buf.is_empty());
+            return self
+                .write_all_unbuffered(FullSlice::must_new(src_buf), ctx)
+                .await;
+        }
+        let remaining = Self::CAPACITY - self.buf.len();
+        let src_buf_len = src_buf.bytes_init();
+        if src_buf_len == 0 {
+            return (restore(src_buf), Ok(()));
+        }
+        let mut src_buf = src_buf.slice(0..src_buf_len);
+        // First try to copy as much as we can into the buffer
+        if remaining > 0 {
+            let copied = self.write_into_buffer(&src_buf);
+            src_buf = src_buf.slice(copied..);
+        }
+        // Then, if the buffer is full, flush it out
+        if self.buf.len() == Self::CAPACITY {
+            if let Err(e) = self.flush_buffer(ctx).await {
+                return (restore(src_buf), Err(e));
+            }
+        }
+        // Finally, write the tail of src_buf:
+        // If it wholly fits into the buffer without
+        // completely filling it, then put it there.
+        // If not, write it out directly.
+        let src_buf = if !src_buf.is_empty() {
+            assert_eq!(self.buf.len(), 0);
+            if src_buf.len() < Self::CAPACITY {
+                let copied = self.write_into_buffer(&src_buf);
+                // We just verified above that src_buf fits into our internal buffer.
+                assert_eq!(copied, src_buf.len());
+                restore(src_buf)
+            } else {
+                let (src_buf, res) = self
+                    .write_all_unbuffered(FullSlice::must_new(src_buf), ctx)
+                    .await;
+                if let Err(e) = res {
+                    return (src_buf, Err(e));
+                }
+                src_buf
+            }
+        } else {
+            restore(src_buf)
+        };
+        (src_buf, Ok(()))
     }
 
     /// Write a blob of data. Returns the offset that it was written to,
@@ -285,7 +301,7 @@ where
         &mut self,
         srcbuf: FullSlice<Buf>,
         ctx: &RequestContext,
-    ) -> (FullSlice<Buf>, Result<u64, WriteBlobError>) {
+    ) -> (FullSlice<Buf>, Result<u64, Error>) {
         let (buf, res) = self
             .write_blob_maybe_compressed(srcbuf, ctx, ImageCompressionAlgorithm::Disabled)
             .await;
@@ -299,10 +315,7 @@ where
         srcbuf: FullSlice<Buf>,
         ctx: &RequestContext,
         algorithm: ImageCompressionAlgorithm,
-    ) -> (
-        FullSlice<Buf>,
-        Result<(u64, CompressionInfo), WriteBlobError>,
-    ) {
+    ) -> (FullSlice<Buf>, Result<(u64, CompressionInfo), Error>) {
         let offset = self.offset;
         let mut compression_info = CompressionInfo {
             written_compressed: false,
@@ -318,16 +331,14 @@ where
             if len < 128 {
                 // Short blob. Write a 1-byte length header
                 io_buf.put_u8(len as u8);
-                let (slice, res) = self.write_all(io_buf.slice_len(), ctx).await;
-                let res = res.map_err(WriteBlobError::Flush);
-                ((slice, res), srcbuf)
+                (self.write_all(io_buf.slice_len(), ctx).await, srcbuf)
             } else {
                 // Write a 4-byte length header
                 if len > MAX_SUPPORTED_BLOB_LEN {
                     return (
                         (
                             io_buf.slice_len(),
-                            Err(WriteBlobError::BlobTooLarge { len }),
+                            Err(Error::other(format!("blob too large ({len} bytes)"))),
                         ),
                         srcbuf,
                     );
@@ -361,9 +372,7 @@ where
                 assert_eq!(len_buf[0] & 0xf0, 0);
                 len_buf[0] |= high_bit_mask;
                 io_buf.extend_from_slice(&len_buf[..]);
-                let (slice, res) = self.write_all(io_buf.slice_len(), ctx).await;
-                let res = res.map_err(WriteBlobError::Flush);
-                ((slice, res), srcbuf)
+                (self.write_all(io_buf.slice_len(), ctx).await, srcbuf)
             }
         }
         .await;
@@ -378,49 +387,33 @@ where
         } else {
             self.write_all(srcbuf, ctx).await
         };
-        let res = res.map_err(WriteBlobError::Flush);
         (srcbuf, res.map(|_| (offset, compression_info)))
     }
+}
 
-    /// Writes a raw blob containing both header and data, returning its offset.
-    pub(crate) async fn write_blob_raw<Buf: IoBuf + Send>(
-        &mut self,
-        raw_with_header: FullSlice<Buf>,
-        ctx: &RequestContext,
-    ) -> (FullSlice<Buf>, Result<u64, WriteBlobError>) {
-        // Verify the header, to ensure we don't write invalid/corrupt data.
-        let header = match Header::decode(&raw_with_header)
-            .context("decoding blob header")
-            .map_err(WriteBlobError::WriteBlobRaw)
-        {
-            Ok(header) => header,
-            Err(err) => return (raw_with_header, Err(err)),
-        };
-        if raw_with_header.len() != header.total_len() {
-            let header_total_len = header.total_len();
-            let raw_len = raw_with_header.len();
-            return (
-                raw_with_header,
-                Err(WriteBlobError::WriteBlobRaw(anyhow::anyhow!(
-                    "header length mismatch: {header_total_len} != {raw_len}"
-                ))),
-            );
-        }
-
-        let offset = self.offset;
-        let (raw_with_header, result) = self.write_all(raw_with_header, ctx).await;
-        let result = result.map_err(WriteBlobError::Flush);
-        (raw_with_header, result.map(|_| offset))
+impl BlobWriter<true> {
+    /// Access the underlying `VirtualFile`.
+    ///
+    /// This function flushes the internal buffer before giving access
+    /// to the underlying `VirtualFile`.
+    pub async fn into_inner(mut self, ctx: &RequestContext) -> Result<VirtualFile, Error> {
+        self.flush_buffer(ctx).await?;
+        Ok(self.inner)
     }
 
-    /// Finish this blob writer and return the underlying `W`.
-    pub async fn shutdown(
-        self,
-        mode: BufferedWriterShutdownMode,
-        ctx: &RequestContext,
-    ) -> Result<W, FlushTaskError> {
-        let (_, file) = self.writer.shutdown(mode, ctx).await?;
-        Ok(file)
+    /// Access the underlying `VirtualFile`.
+    ///
+    /// Unlike [`into_inner`](Self::into_inner), this doesn't flush
+    /// the internal buffer before giving access.
+    pub fn into_inner_no_flush(self) -> VirtualFile {
+        self.inner
+    }
+}
+
+impl BlobWriter<false> {
+    /// Access the underlying `VirtualFile`.
+    pub fn into_inner(self) -> VirtualFile {
+        self.inner
     }
 }
 
@@ -429,25 +422,21 @@ pub(crate) mod tests {
     use camino::Utf8PathBuf;
     use camino_tempfile::Utf8TempDir;
     use rand::{Rng, SeedableRng};
-    use tracing::info_span;
 
     use super::*;
     use crate::context::DownloadBehavior;
     use crate::task_mgr::TaskKind;
     use crate::tenant::block_io::BlockReaderRef;
-    use crate::virtual_file;
-    use crate::virtual_file::TempVirtualFile;
-    use crate::virtual_file::VirtualFile;
 
-    async fn round_trip_test(blobs: &[Vec<u8>]) -> anyhow::Result<()> {
-        round_trip_test_compressed(blobs, false).await
+    async fn round_trip_test<const BUFFERED: bool>(blobs: &[Vec<u8>]) -> Result<(), Error> {
+        round_trip_test_compressed::<BUFFERED>(blobs, false).await
     }
 
-    pub(crate) async fn write_maybe_compressed(
+    pub(crate) async fn write_maybe_compressed<const BUFFERED: bool>(
         blobs: &[Vec<u8>],
         compression: bool,
         ctx: &RequestContext,
-    ) -> anyhow::Result<(Utf8TempDir, Utf8PathBuf, Vec<u64>)> {
+    ) -> Result<(Utf8TempDir, Utf8PathBuf, Vec<u64>), Error> {
         let temp_dir = camino_tempfile::tempdir()?;
         let pathbuf = temp_dir.path().join("file");
         let gate = utils::sync::gate::Gate::default();
@@ -456,19 +445,8 @@ pub(crate) mod tests {
         // Write part (in block to drop the file)
         let mut offsets = Vec::new();
         {
-            let file = TempVirtualFile::new(
-                VirtualFile::open_with_options_v2(
-                    pathbuf.as_path(),
-                    virtual_file::OpenOptions::new()
-                        .create_new(true)
-                        .write(true),
-                    ctx,
-                )
-                .await?,
-                gate.enter()?,
-            );
-            let mut wtr =
-                BlobWriter::new(file, 0, &gate, cancel.clone(), ctx, info_span!("test")).unwrap();
+            let file = VirtualFile::create(pathbuf.as_path(), ctx).await?;
+            let mut wtr = BlobWriter::<BUFFERED>::new(file, 0, &gate, cancel.clone(), ctx);
             for blob in blobs.iter() {
                 let (_, res) = if compression {
                     let res = wtr
@@ -485,28 +463,26 @@ pub(crate) mod tests {
                 let offs = res?;
                 offsets.push(offs);
             }
-            let file = wtr
-                .shutdown(
-                    BufferedWriterShutdownMode::ZeroPadToNextMultiple(PAGE_SZ),
-                    ctx,
-                )
-                .await?;
-            file.disarm_into_inner()
-        };
+            // Write out one page worth of zeros so that we can
+            // read again with read_blk
+            let (_, res) = wtr.write_blob(vec![0; PAGE_SZ].slice_len(), ctx).await;
+            let offs = res?;
+            println!("Writing final blob at offs={offs}");
+            wtr.flush_buffer(ctx).await?;
+        }
         Ok((temp_dir, pathbuf, offsets))
     }
 
-    async fn round_trip_test_compressed(
+    async fn round_trip_test_compressed<const BUFFERED: bool>(
         blobs: &[Vec<u8>],
         compression: bool,
-    ) -> anyhow::Result<()> {
+    ) -> Result<(), Error> {
         let ctx =
             RequestContext::new(TaskKind::UnitTest, DownloadBehavior::Error).with_scope_unit_test();
         let (_temp_dir, pathbuf, offsets) =
-            write_maybe_compressed(blobs, compression, &ctx).await?;
+            write_maybe_compressed::<BUFFERED>(blobs, compression, &ctx).await?;
 
-        println!("Done writing!");
-        let file = VirtualFile::open_v2(pathbuf, &ctx).await?;
+        let file = VirtualFile::open(pathbuf, &ctx).await?;
         let rdr = BlockReaderRef::VirtualFile(&file);
         let rdr = BlockCursor::new_with_compression(rdr, compression);
         for (idx, (blob, offset)) in blobs.iter().zip(offsets.iter()).enumerate() {
@@ -525,27 +501,30 @@ pub(crate) mod tests {
     }
 
     #[tokio::test]
-    async fn test_one() -> anyhow::Result<()> {
+    async fn test_one() -> Result<(), Error> {
         let blobs = &[vec![12, 21, 22]];
-        round_trip_test(blobs).await?;
+        round_trip_test::<false>(blobs).await?;
+        round_trip_test::<true>(blobs).await?;
         Ok(())
     }
 
     #[tokio::test]
-    async fn test_hello_simple() -> anyhow::Result<()> {
+    async fn test_hello_simple() -> Result<(), Error> {
         let blobs = &[
             vec![0, 1, 2, 3],
             b"Hello, World!".to_vec(),
             Vec::new(),
             b"foobar".to_vec(),
         ];
-        round_trip_test(blobs).await?;
-        round_trip_test_compressed(blobs, true).await?;
+        round_trip_test::<false>(blobs).await?;
+        round_trip_test::<true>(blobs).await?;
+        round_trip_test_compressed::<false>(blobs, true).await?;
+        round_trip_test_compressed::<true>(blobs, true).await?;
         Ok(())
     }
 
     #[tokio::test]
-    async fn test_really_big_array() -> anyhow::Result<()> {
+    async fn test_really_big_array() -> Result<(), Error> {
         let blobs = &[
             b"test".to_vec(),
             random_array(10 * PAGE_SZ),
@@ -554,22 +533,25 @@ pub(crate) mod tests {
             vec![0xf3; 24 * PAGE_SZ],
             b"foobar".to_vec(),
         ];
-        round_trip_test(blobs).await?;
-        round_trip_test_compressed(blobs, true).await?;
+        round_trip_test::<false>(blobs).await?;
+        round_trip_test::<true>(blobs).await?;
+        round_trip_test_compressed::<false>(blobs, true).await?;
+        round_trip_test_compressed::<true>(blobs, true).await?;
         Ok(())
     }
 
     #[tokio::test]
-    async fn test_arrays_inc() -> anyhow::Result<()> {
+    async fn test_arrays_inc() -> Result<(), Error> {
         let blobs = (0..PAGE_SZ / 8)
             .map(|v| random_array(v * 16))
             .collect::<Vec<_>>();
-        round_trip_test(&blobs).await?;
+        round_trip_test::<false>(&blobs).await?;
+        round_trip_test::<true>(&blobs).await?;
         Ok(())
     }
 
     #[tokio::test]
-    async fn test_arrays_random_size() -> anyhow::Result<()> {
+    async fn test_arrays_random_size() -> Result<(), Error> {
         let mut rng = rand::rngs::StdRng::seed_from_u64(42);
         let blobs = (0..1024)
             .map(|_| {
@@ -581,18 +563,20 @@ pub(crate) mod tests {
                 random_array(sz.into())
             })
             .collect::<Vec<_>>();
-        round_trip_test(&blobs).await?;
+        round_trip_test::<false>(&blobs).await?;
+        round_trip_test::<true>(&blobs).await?;
         Ok(())
     }
 
     #[tokio::test]
-    async fn test_arrays_page_boundary() -> anyhow::Result<()> {
+    async fn test_arrays_page_boundary() -> Result<(), Error> {
         let blobs = &[
             random_array(PAGE_SZ - 4),
             random_array(PAGE_SZ - 4),
             random_array(PAGE_SZ - 4),
         ];
-        round_trip_test(blobs).await?;
+        round_trip_test::<false>(blobs).await?;
+        round_trip_test::<true>(blobs).await?;
         Ok(())
     }
 }

pageserver/src/tenant/block_io.rs

@@ -4,12 +4,14 @@
 
 use std::ops::Deref;
 
+use bytes::Bytes;
+
 use super::storage_layer::delta_layer::{Adapter, DeltaLayerInner};
 use crate::context::RequestContext;
 use crate::page_cache::{self, FileId, PAGE_SZ, PageReadGuard, PageWriteGuard, ReadBufResult};
 #[cfg(test)]
 use crate::virtual_file::IoBufferMut;
-use crate::virtual_file::{IoBuffer, VirtualFile};
+use crate::virtual_file::VirtualFile;
 
 /// This is implemented by anything that can read 8 kB (PAGE_SZ)
 /// blocks, using the page cache
@@ -245,17 +247,17 @@ pub trait BlockWriter {
     /// 'buf' must be of size PAGE_SZ. Returns the block number the page was
     /// written to.
     ///
-    fn write_blk(&mut self, buf: IoBuffer) -> Result<u32, std::io::Error>;
+    fn write_blk(&mut self, buf: Bytes) -> Result<u32, std::io::Error>;
 }
 
 ///
 /// A simple in-memory buffer of blocks.
 ///
 pub struct BlockBuf {
-    pub blocks: Vec<IoBuffer>,
+    pub blocks: Vec<Bytes>,
 }
 impl BlockWriter for BlockBuf {
-    fn write_blk(&mut self, buf: IoBuffer) -> Result<u32, std::io::Error> {
+    fn write_blk(&mut self, buf: Bytes) -> Result<u32, std::io::Error> {
         assert!(buf.len() == PAGE_SZ);
         let blknum = self.blocks.len();
         self.blocks.push(buf);