Disable XLP_FIRST_IS_CONTRECORD check

2026-06-03 05:20:38 +00:00 · 2022-08-15 19:38:12 +00:00
78 changed files with 1232 additions and 1457 deletions
--- a/.github/ansible/scripts/init_safekeeper.sh
+++ b/.github/ansible/scripts/init_safekeeper.sh
@@ -1,8 +1,7 @@
 #!/bin/sh

-# fetch params from meta-data service
+# get instance id from meta-data service
 INSTANCE_ID=$(curl -s http://169.254.169.254/latest/meta-data/instance-id)
-AZ_ID=$(curl -s http://169.254.169.254/latest/meta-data/placement/availability-zone)

 # store fqdn hostname in var
 HOST=$(hostname -f)
@@ -15,8 +14,7 @@ cat <<EOF | tee /tmp/payload
  "port": 6500,
  "http_port": 7676,
  "region_id": {{ console_region_id }},
-  "instance_id": "${INSTANCE_ID}",
-  "availability_zone_id": "${AZ_ID}"
+  "instance_id": "${INSTANCE_ID}"
 }
 EOF

--- a/.github/workflows/benchmarking.yml
+++ b/.github/workflows/benchmarking.yml
@@ -106,7 +106,7 @@ jobs:
        mkdir -p perf-report-staging
        # Set --sparse-ordering option of pytest-order plugin to ensure tests are running in order of appears in the file,
        # it's important for test_perf_pgbench.py::test_pgbench_remote_* tests
-        ./scripts/pytest test_runner/performance/ -v -m "remote_cluster" --sparse-ordering --skip-interfering-proc-check --out-dir perf-report-staging --timeout 5400
+        ./scripts/pytest test_runner/performance/ -v -m "remote_cluster" --sparse-ordering --skip-interfering-proc-check --out-dir perf-report-staging --timeout 3600

    - name: Submit result
      env:
--- a/.github/workflows/build_and_test.yml
+++ b/.github/workflows/build_and_test.yml
@@ -7,6 +7,10 @@ on:
      - release
  pull_request:

+defaults:
+  run:
+    shell: bash -euxo pipefail {0}
+
 concurrency:
  # Allow only one workflow per any non-`main` branch.
  group: ${{ github.workflow }}-${{ github.ref }}-${{ github.ref == 'refs/heads/main' && github.sha || 'anysha' }}
@@ -17,39 +21,9 @@ env:
  COPT: '-Werror'

 jobs:
-  tag:
-    runs-on: dev
-    container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/base:latest
-    outputs:
-      build-tag: ${{steps.build-tag.outputs.tag}}
-
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 0
-
-      - name: Get build tag
-        run: |
-          echo run:$GITHUB_RUN_ID
-          echo ref:$GITHUB_REF_NAME
-          echo rev:$(git rev-list --count HEAD)
-          if [[ "$GITHUB_REF_NAME" == "main" ]]; then
-            echo "::set-output name=tag::$(git rev-list --count HEAD)"
-          elif [[ "$GITHUB_REF_NAME" == "release" ]]; then
-            echo "::set-output name=tag::release-$(git rev-list --count HEAD)"
-          else
-            echo "GITHUB_REF_NAME (value '$GITHUB_REF_NAME') is not set to either 'main' or 'release'"
-            echo "::set-output name=tag::$GITHUB_RUN_ID"
-          fi
-        shell: bash
-        id: build-tag
-
  build-neon:
    runs-on: dev
-    container:
-      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
-      options: --init
+    container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rustlegacy:2746987948
    strategy:
      fail-fast: false
      matrix:
@@ -61,7 +35,7 @@ jobs:
      GIT_VERSION: ${{ github.sha }}

    steps:
-      - name: Fix git ownership
+      - name: Fix git ownerwhip
        run: |
          # Workaround for `fatal: detected dubious ownership in repository at ...`
          #
@@ -80,7 +54,6 @@ jobs:
      - name: Set pg revision for caching
        id: pg_ver
        run: echo ::set-output name=pg_rev::$(git rev-parse HEAD:vendor/postgres)
-        shell: bash -euxo pipefail {0}

      # Set some environment variables used by all the steps.
      #
@@ -104,7 +77,6 @@ jobs:
          echo "cov_prefix=${cov_prefix}" >> $GITHUB_ENV
          echo "CARGO_FEATURES=${CARGO_FEATURES}" >> $GITHUB_ENV
          echo "CARGO_FLAGS=${CARGO_FLAGS}" >> $GITHUB_ENV
-        shell: bash -euxo pipefail {0}

      # Don't include the ~/.cargo/registry/src directory. It contains just
      # uncompressed versions of the crates in ~/.cargo/registry/cache
@@ -121,8 +93,8 @@ jobs:
            target/
          # Fall back to older versions of the key, if no cache for current Cargo.lock was found
          key: |
-            v6-${{ runner.os }}-${{ matrix.build_type }}-cargo-${{ matrix.rust_toolchain }}-${{ hashFiles('Cargo.lock') }}
-            v6-${{ runner.os }}-${{ matrix.build_type }}-cargo-${{ matrix.rust_toolchain }}-
+            v3-${{ runner.os }}-${{ matrix.build_type }}-cargo-${{ matrix.rust_toolchain }}-${{ hashFiles('Cargo.lock') }}
+            v3-${{ runner.os }}-${{ matrix.build_type }}-cargo-${{ matrix.rust_toolchain }}-

      - name: Cache postgres build
        id: cache_pg
@@ -134,17 +106,14 @@ jobs:
      - name: Build postgres
        if: steps.cache_pg.outputs.cache-hit != 'true'
        run: mold -run make postgres -j$(nproc)
-        shell: bash -euxo pipefail {0}

      - name: Run cargo build
        run: |
          ${cov_prefix} mold -run cargo build $CARGO_FLAGS --features failpoints --bins --tests
-        shell: bash -euxo pipefail {0}

      - name: Run cargo test
        run: |
          ${cov_prefix} cargo test $CARGO_FLAGS
-        shell: bash -euxo pipefail {0}

      - name: Install rust binaries
        run: |
@@ -185,11 +154,9 @@ jobs:
              echo "/tmp/neon/bin/$bin" >> /tmp/coverage/binaries.list
            done
          fi
-        shell: bash -euxo pipefail {0}

      - name: Install postgres binaries
        run: cp -a tmp_install /tmp/neon/pg_install
-        shell: bash -euxo pipefail {0}

      - name: Upload Neon artifact
        uses: ./.github/actions/upload
@@ -204,9 +171,7 @@ jobs:

  pg_regress-tests:
    runs-on: dev
-    container:
-      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
-      options: --init
+    container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rustlegacy:2746987948
    needs: [ build-neon ]
    strategy:
      fail-fast: false
@@ -234,9 +199,7 @@ jobs:

  other-tests:
    runs-on: dev
-    container:
-      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
-      options: --init
+    container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rustlegacy:2746987948
    needs: [ build-neon ]
    strategy:
      fail-fast: false
@@ -267,9 +230,7 @@ jobs:

  benchmarks:
    runs-on: dev
-    container:
-      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
-      options: --init
+    container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rustlegacy:2746987948
    needs: [ build-neon ]
    if: github.ref_name == 'main' || contains(github.event.pull_request.labels.*.name, 'run-benchmarks')
    strategy:
@@ -300,9 +261,7 @@ jobs:

  coverage-report:
    runs-on: dev
-    container:
-      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
-      options: --init
+    container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rustlegacy:2746987948
    needs: [ other-tests, pg_regress-tests ]
    strategy:
      fail-fast: false
@@ -325,7 +284,7 @@ jobs:
            !~/.cargo/registry/src
            ~/.cargo/git/
            target/
-          key: v5-${{ runner.os }}-${{ matrix.build_type }}-cargo-${{ matrix.rust_toolchain }}-${{ hashFiles('Cargo.lock') }}
+          key: v3-${{ runner.os }}-${{ matrix.build_type }}-cargo-${{ matrix.rust_toolchain }}-${{ hashFiles('Cargo.lock') }}

      - name: Get Neon artifact
        uses: ./.github/actions/download
@@ -341,7 +300,6 @@ jobs:

      - name: Merge coverage data
        run: scripts/coverage "--profraw-prefix=$GITHUB_JOB" --dir=/tmp/coverage merge
-        shell: bash -euxo pipefail {0}

      - name: Build and upload coverage report
        run: |
@@ -374,13 +332,9 @@ jobs:
              \"description\": \"Coverage report is ready\",
              \"target_url\": \"$REPORT_URL\"
            }"
-        shell: bash -euxo pipefail {0}

  trigger-e2e-tests:
-    runs-on: dev
-    container:
-      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
-      options: --init
+    runs-on: [ self-hosted, Linux, k8s-runner ]
    needs: [ build-neon ]
    steps:
      - name: Set PR's status to pending and request a remote CI test
@@ -415,150 +369,150 @@ jobs:
              }
            }"

-  neon-image:
-    runs-on: dev
-    container: gcr.io/kaniko-project/executor:v1.9.0-debug
-
+  docker-image:
+    runs-on: [ self-hosted, Linux, k8s-runner ]
+    needs: [ pg_regress-tests, other-tests ]
+    if: |
+      (github.ref_name == 'main' || github.ref_name == 'release') &&
+      github.event_name != 'workflow_dispatch'
+    outputs:
+      build-tag: ${{steps.build-tag.outputs.tag}}
    steps:
      - name: Checkout
-        uses: actions/checkout@v1 # v3 won't work with kaniko
+        uses: actions/checkout@v3
        with:
          submodules: true
          fetch-depth: 0

-      - name: Configure ECR login
-        run: echo "{\"credsStore\":\"ecr-login\"}" > /kaniko/.docker/config.json
+      - name: Login to DockerHub
+        uses: docker/login-action@v1
+        with:
+          username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
+          password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}

-      - name: Kaniko build neon
-        run: /kaniko/executor --snapshotMode=redo --cache=true --cache-repo 369495373322.dkr.ecr.eu-central-1.amazonaws.com/cache --snapshotMode=redo --context . --destination 369495373322.dkr.ecr.eu-central-1.amazonaws.com/neon:$GITHUB_RUN_ID
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v1
+        with:
+          driver: docker

-  compute-tools-image:
-    runs-on: dev
-    container: gcr.io/kaniko-project/executor:v1.9.0-debug
+      - name: Get build tag
+        run: |
+          if [[ "$GITHUB_REF_NAME" == "main" ]]; then
+            echo "::set-output name=tag::$(git rev-list --count HEAD)"
+          elif [[ "$GITHUB_REF_NAME" == "release" ]]; then
+            echo "::set-output name=tag::release-$(git rev-list --count HEAD)"
+          else
+            echo "GITHUB_REF_NAME (value '$GITHUB_REF_NAME') is not set to either 'main' or 'release'"
+            exit 1
+          fi
+        id: build-tag

+      - name: Get legacy build tag
+        run: |
+          if [[ "$GITHUB_REF_NAME" == "main" ]]; then
+            echo "::set-output name=tag::latest"
+          elif [[ "$GITHUB_REF_NAME" == "release" ]]; then
+            echo "::set-output name=tag::release"
+          else
+            echo "GITHUB_REF_NAME (value '$GITHUB_REF_NAME') is not set to either 'main' or 'release'"
+            exit 1
+          fi
+        id: legacy-build-tag
+
+      - name: Build neon Docker image
+        uses: docker/build-push-action@v2
+        with:
+          context: .
+          build-args: |
+            GIT_VERSION="${{github.sha}}"
+            AWS_ACCESS_KEY_ID="${{secrets.CACHEPOT_AWS_ACCESS_KEY_ID}}"
+            AWS_SECRET_ACCESS_KEY="${{secrets.CACHEPOT_AWS_SECRET_ACCESS_KEY}}"
+          pull: true
+          push: true
+          tags: neondatabase/neon:${{steps.legacy-build-tag.outputs.tag}}, neondatabase/neon:${{steps.build-tag.outputs.tag}}
+
+  docker-image-compute:
+    runs-on: [ self-hosted, Linux, k8s-runner ]
+    needs: [ pg_regress-tests, other-tests ]
+    if: |
+      (github.ref_name == 'main' || github.ref_name == 'release') &&
+      github.event_name != 'workflow_dispatch'
+    outputs:
+      build-tag: ${{steps.build-tag.outputs.tag}}
    steps:
      - name: Checkout
-        uses: actions/checkout@v1 # v3 won't work with kaniko
-
-      - name: Configure ECR login
-        run: echo "{\"credsStore\":\"ecr-login\"}" > /kaniko/.docker/config.json
-
-      - name: Kaniko build compute tools
-        run: /kaniko/executor --snapshotMode=redo --cache=true --cache-repo 369495373322.dkr.ecr.eu-central-1.amazonaws.com/cache --snapshotMode=redo --context . --dockerfile Dockerfile.compute-tools --destination 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-tools:$GITHUB_RUN_ID
-
-  promote-image-compute-tools:
-    runs-on: dev
-    needs: [ compute-tools-image ]
-    if: github.event_name != 'workflow_dispatch'
-    container: amazon/aws-cli
-    strategy:
-      fail-fast: false
-      matrix:
-        name: [ compute-tools ]
-
-    steps:
-      - name: Promote image to latest
-        run:
-          MANIFEST=$(aws ecr batch-get-image --repository-name ${{ matrix.name }} --image-ids imageTag=$GITHUB_RUN_ID --query 'images[].imageManifest' --output text) && aws ecr put-image --repository-name ${{ matrix.name }} --image-tag latest --image-manifest "$MANIFEST"
-
-  compute-node-image:
-    runs-on: dev
-    container: gcr.io/kaniko-project/executor:v1.9.0-debug
-    # note: This image depends on neondatabase/compute-tools:latest (or :thisversion),
-    # which isn't available until after the image is promoted.
-    # Ergo, we must explicitly build and promote compute-tools separately.
-    needs:
-      - promote-image-compute-tools
-
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v1 # v3 won't work with kaniko
+        uses: actions/checkout@v3
        with:
          submodules: true
          fetch-depth: 0

-      - name: Configure ECR login
-        run: echo "{\"credsStore\":\"ecr-login\"}" > /kaniko/.docker/config.json
+      - name: Login to DockerHub
+        uses: docker/login-action@v1
+        with:
+          username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
+          password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}

-      - name: Kaniko build compute node
-        working-directory: ./vendor/postgres/
-        run: /kaniko/executor --snapshotMode=redo --cache=true --cache-repo 369495373322.dkr.ecr.eu-central-1.amazonaws.com/cache --snapshotMode=redo --context . --build-arg=COMPUTE_TOOLS_TAG=$GITHUB_RUN_ID --destination 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node:$GITHUB_RUN_ID
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v1
+        with:
+          driver: docker

-  promote-images:
-    runs-on: dev
-    needs: [ neon-image, compute-node-image ]
-    if: github.event_name != 'workflow_dispatch'
-    container: amazon/aws-cli
-    strategy:
-      fail-fast: false
-      matrix:
-        name: [ neon, compute-node ]
-
-    steps:
-      - name: Promote image to latest
-        run:
-          MANIFEST=$(aws ecr batch-get-image --repository-name ${{ matrix.name }} --image-ids imageTag=$GITHUB_RUN_ID --query 'images[].imageManifest' --output text) && aws ecr put-image --repository-name ${{ matrix.name }} --image-tag latest --image-manifest "$MANIFEST"
-
-  push-docker-hub:
-    runs-on: dev
-    needs: [ promote-images, tag ]
-    container: golang:1.19-bullseye
-
-    steps:
-      - name: Install Crane & ECR helper
+      - name: Get build tag
        run: |
-          go install github.com/google/go-containerregistry/cmd/crane@31786c6cbb82d6ec4fb8eb79cd9387905130534e # v0.11.0
-          go install github.com/awslabs/amazon-ecr-credential-helper/ecr-login/cli/docker-credential-ecr-login@69c85dc22db6511932bbf119e1a0cc5c90c69a7f # v0.6.0
-          
-#      - name: Get build tag
-#        run: |
-#          if [[ "$GITHUB_REF_NAME" == "main" ]]; then
-#            echo "::set-output name=tag::$(git rev-list --count HEAD)"
-#          elif [[ "$GITHUB_REF_NAME" == "release" ]]; then
-#            echo "::set-output name=tag::release-$(git rev-list --count HEAD)"
-#          else
-#            echo "GITHUB_REF_NAME (value '$GITHUB_REF_NAME') is not set to either 'main' or 'release' "
-#            echo "::set-output name=tag::$GITHUB_RUN_ID"
-#          fi
-#        id: build-tag
+          if [[ "$GITHUB_REF_NAME" == "main" ]]; then
+            echo "::set-output name=tag::$(git rev-list --count HEAD)"
+          elif [[ "$GITHUB_REF_NAME" == "release" ]]; then
+            echo "::set-output name=tag::release-$(git rev-list --count HEAD)"
+          else
+            echo "GITHUB_REF_NAME (value '$GITHUB_REF_NAME') is not set to either 'main' or 'release'"
+            exit 1
+          fi
+        id: build-tag

-      - name: Configure ECR login
+      - name: Get legacy build tag
        run: |
-          mkdir /github/home/.docker/
-          echo "{\"credsStore\":\"ecr-login\"}" > /github/home/.docker/config.json
+          if [[ "$GITHUB_REF_NAME" == "main" ]]; then
+            echo "::set-output name=tag::latest"
+          elif [[ "$GITHUB_REF_NAME" == "release" ]]; then
+            echo "::set-output name=tag::release"
+          else
+            echo "GITHUB_REF_NAME (value '$GITHUB_REF_NAME') is not set to either 'main' or 'release'"
+            exit 1
+          fi
+        id: legacy-build-tag

-      - name: Pull neon image from ECR
-        run: crane pull 369495373322.dkr.ecr.eu-central-1.amazonaws.com/neon:latest neon
+      - name: Build compute-tools Docker image
+        uses: docker/build-push-action@v2
+        with:
+          context: .
+          build-args: |
+            GIT_VERSION="${{github.sha}}"
+            AWS_ACCESS_KEY_ID="${{secrets.CACHEPOT_AWS_ACCESS_KEY_ID}}"
+            AWS_SECRET_ACCESS_KEY="${{secrets.CACHEPOT_AWS_SECRET_ACCESS_KEY}}"
+          push: false
+          file: Dockerfile.compute-tools
+          tags: neondatabase/compute-tools:local

-      - name: Pull compute tools image from ECR
-        run: crane pull 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-tools:latest compute-tools
+      - name: Push compute-tools Docker image
+        uses: docker/build-push-action@v2
+        with:
+          context: .
+          build-args: |
+            GIT_VERSION="${{github.sha}}"
+            AWS_ACCESS_KEY_ID="${{secrets.CACHEPOT_AWS_ACCESS_KEY_ID}}"
+            AWS_SECRET_ACCESS_KEY="${{secrets.CACHEPOT_AWS_SECRET_ACCESS_KEY}}"
+          push: true
+          file: Dockerfile.compute-tools
+          tags: neondatabase/compute-tools:${{steps.legacy-build-tag.outputs.tag}}

-      - name: Pull compute node image from ECR
-        run: crane pull 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node:latest compute-node
-
-      - name: Configure docker login
-        run: |
-          # ECR Credential Helper & Docker Hub don't work together in config, hence reset
-          echo "" > /github/home/.docker/config.json
-          crane auth login -u ${{ secrets.NEON_DOCKERHUB_USERNAME }} -p ${{ secrets.NEON_DOCKERHUB_PASSWORD }} index.docker.io
-
-      - name: Push neon image to Docker Hub
-        run: crane push neon neondatabase/neon:${{needs.tag.outputs.build-tag}}
-
-      - name: Push compute tools image to Docker Hub
-        run: crane push compute-tools neondatabase/compute-tools:${{needs.tag.outputs.build-tag}}
-
-      - name: Push compute node image to Docker Hub
-        run: crane push compute-node neondatabase/compute-node:${{needs.tag.outputs.build-tag}}
-
-      - name: Add latest tag to images
-        if: |
-          (github.ref_name == 'main' || github.ref_name == 'release') &&
-          github.event_name != 'workflow_dispatch'
-        run: |
-          crane tag neondatabase/neon:${{needs.tag.outputs.build-tag}} latest
-          crane tag neondatabase/compute-tools:${{needs.tag.outputs.build-tag}} latest
-          crane tag neondatabase/compute-node:${{needs.tag.outputs.build-tag}} latest
+      - name: Build compute-node Docker image
+        uses: docker/build-push-action@v2
+        with:
+          context: ./vendor/postgres/
+          build-args:
+            COMPUTE_TOOLS_TAG=local
+          push: true
+          tags: neondatabase/compute-node:${{steps.legacy-build-tag.outputs.tag}}, neondatabase/compute-node:${{steps.build-tag.outputs.tag}}

  calculate-deploy-targets:
    runs-on: [ self-hosted, Linux, k8s-runner ]
@@ -584,16 +538,14 @@ jobs:

  deploy:
    runs-on: [ self-hosted, Linux, k8s-runner ]
-    #container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/base:latest
-    # We need both storage **and** compute images for deploy, because control plane picks the compute version based on the storage version.
-    # If it notices a fresh storage it may bump the compute version. And if compute image failed to build it may break things badly
-    needs: [ push-docker-hub, calculate-deploy-targets, tag, other-tests, pg_regress-tests ]
+    # We need both storage **and** compute images for deploy, because control plane
+    # picks the compute version based on the storage version. If it notices a fresh
+    # storage it may bump the compute version. And if compute image failed to build
+    # it may break things badly.
+    needs: [ docker-image, docker-image-compute, calculate-deploy-targets ]
    if: |
      (github.ref_name == 'main' || github.ref_name == 'release') &&
      github.event_name != 'workflow_dispatch'
-    defaults:
-      run:
-        shell: bash
    strategy:
      matrix:
        include: ${{fromJSON(needs.calculate-deploy-targets.outputs.matrix-include)}}
@@ -604,19 +556,13 @@ jobs:
          submodules: true
          fetch-depth: 0

-      - name: Setup python
-        uses: actions/setup-python@v4
-        with:
-          python-version: '3.10'
-
      - name: Setup ansible
        run: |
-          export PATH="/root/.local/bin:$PATH"
          pip install --progress-bar off --user ansible boto3

      - name: Redeploy
        run: |
-          export DOCKER_TAG=${{needs.tag.outputs.build-tag}}
+          export DOCKER_TAG=${{needs.docker-image.outputs.build-tag}}
          cd "$(pwd)/.github/ansible"

          if [[ "$GITHUB_REF_NAME" == "main" ]]; then
@@ -639,16 +585,13 @@ jobs:
          rm -f neon_install.tar.gz .neon_current_version

  deploy-proxy:
-    runs-on: dev
-    container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/base:latest
-    # Compute image isn't strictly required for proxy deploy, but let's still wait for it to run all deploy jobs consistently.
-    needs: [ push-docker-hub, calculate-deploy-targets, tag, other-tests, pg_regress-tests ]
+    runs-on: [ self-hosted, Linux, k8s-runner ]
+    # Compute image isn't strictly required for proxy deploy, but let's still wait for it
+    # to run all deploy jobs consistently.
+    needs: [ docker-image, docker-image-compute, calculate-deploy-targets ]
    if: |
      (github.ref_name == 'main' || github.ref_name == 'release') &&
      github.event_name != 'workflow_dispatch'
-    defaults:
-      run:
-        shell: bash
    strategy:
      matrix:
        include: ${{fromJSON(needs.calculate-deploy-targets.outputs.matrix-include)}}
@@ -661,9 +604,6 @@ jobs:
          submodules: true
          fetch-depth: 0

-      - name: Add curl
-        run: apt update && apt install curl -y
-
      - name: Store kubeconfig file
        run: |
          echo "${{ secrets[matrix.kubeconfig_secret] }}" | base64 --decode > ${KUBECONFIG}
@@ -676,6 +616,6 @@ jobs:

      - name: Re-deploy proxy
        run: |
-          DOCKER_TAG=${{needs.tag.outputs.build-tag}}
+          DOCKER_TAG=${{needs.docker-image.outputs.build-tag}}
          helm upgrade ${{ matrix.proxy_job }}       neondatabase/neon-proxy --namespace default --install -f .github/helm-values/${{ matrix.proxy_config }}.yaml --set image.tag=${DOCKER_TAG} --wait --timeout 15m0s
          helm upgrade ${{ matrix.proxy_job }}-scram neondatabase/neon-proxy --namespace default --install -f .github/helm-values/${{ matrix.proxy_config }}-scram.yaml --set image.tag=${DOCKER_TAG} --wait --timeout 15m0s
--- a/.github/workflows/codestyle.yml
+++ b/.github/workflows/codestyle.yml
@@ -101,7 +101,7 @@ jobs:
            !~/.cargo/registry/src
            ~/.cargo/git
            target
-          key: v2-${{ runner.os }}-cargo-${{ hashFiles('./Cargo.lock') }}-rust-${{ matrix.rust_toolchain }}
+          key: v1-${{ runner.os }}-cargo-${{ hashFiles('./Cargo.lock') }}-rust-${{ matrix.rust_toolchain }}

      - name: Run cargo clippy
        run: ./run_clippy.sh
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -48,9 +48,9 @@ dependencies = [

 [[package]]
 name = "anyhow"
-version = "1.0.59"
+version = "1.0.58"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c91f1f46651137be86f3a2b9a8359f9ab421d04d941c62b5982e1ca21113adf9"
+checksum = "bb07d2053ccdbe10e2af2995a2f116c1330396493dc1269f6a91d0ae82e19704"
 dependencies = [
 "backtrace",
 ]
@@ -77,7 +77,7 @@ dependencies = [
 "num-traits",
 "rusticata-macros",
 "thiserror",
- "time 0.3.12",
+ "time 0.3.11",
 ]

 [[package]]
@@ -126,9 +126,9 @@ dependencies = [

 [[package]]
 name = "async-trait"
-version = "0.1.57"
+version = "0.1.56"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "76464446b8bc32758d7e88ee1a804d9914cd9b1cb264c029899680b0be29826f"
+checksum = "96cf8829f67d2eab0b2dfa42c5d0ef737e0724e4a82b01b3e292456202b19716"
 dependencies = [
 "proc-macro2",
 "quote",
@@ -166,7 +166,7 @@ dependencies = [
 "http",
 "http-body",
 "hyper",
- "itoa 1.0.3",
+ "itoa 1.0.2",
 "matchit",
 "memchr",
 "mime",
@@ -298,9 +298,9 @@ checksum = "37ccbd214614c6783386c1af30caf03192f17891059cecc394b4fb119e363de3"

 [[package]]
 name = "bytemuck"
-version = "1.11.0"
+version = "1.10.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a5377c8865e74a160d21f29c2d40669f53286db6eab59b88540cbb12ffc8b835"
+checksum = "c53dfa917ec274df8ed3c572698f381a24eef2efba9492d797301b72b6db408a"

 [[package]]
 name = "byteorder"
@@ -310,9 +310,9 @@ checksum = "14c189c53d098945499cdfa7ecc63567cf3886b3332b312a5b4585d8d3a6a610"

 [[package]]
 name = "bytes"
-version = "1.2.1"
+version = "1.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ec8a7b6a70fde80372154c65702f00a0f56f3e1c36abbc6c440484be248856db"
+checksum = "c4872d67bab6358e59559027aa3b9157c53d9358c51423c17554809a8858e0f8"
 dependencies = [
 "serde",
 ]
@@ -386,9 +386,9 @@ dependencies = [

 [[package]]
 name = "clap"
-version = "3.2.16"
+version = "3.2.12"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a3dbbb6653e7c55cc8595ad3e1f7be8f32aba4eb7ff7f0fd1163d4f3d137c0a9"
+checksum = "ab8b79fe3946ceb4a0b1c080b4018992b8d27e9ff363644c1c9b6387c854614d"
 dependencies = [
 "atty",
 "bitflags",
@@ -455,7 +455,7 @@ version = "0.1.0"
 dependencies = [
 "anyhow",
 "chrono",
- "clap 3.2.16",
+ "clap 3.2.12",
 "env_logger",
 "hyper",
 "log",
@@ -601,9 +601,9 @@ dependencies = [

 [[package]]
 name = "crossbeam-channel"
-version = "0.5.6"
+version = "0.5.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c2dd04ddaf88237dc3b8d8f9a3c1004b506b54b3313403944054d23c0870c521"
+checksum = "4c02a4d71819009c192cf4872265391563fd6a84c81ff2c0f2a7026ca4c1d85c"
 dependencies = [
 "cfg-if",
 "crossbeam-utils",
@@ -611,9 +611,9 @@ dependencies = [

 [[package]]
 name = "crossbeam-deque"
-version = "0.8.2"
+version = "0.8.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "715e8152b692bba2d374b53d4875445368fdf21a94751410af607a5ac677d1fc"
+checksum = "6455c0ca19f0d2fbf751b908d5c55c1f5cbc65e03c4225427254b46890bdde1e"
 dependencies = [
 "cfg-if",
 "crossbeam-epoch",
@@ -622,9 +622,9 @@ dependencies = [

 [[package]]
 name = "crossbeam-epoch"
-version = "0.9.10"
+version = "0.9.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "045ebe27666471bb549370b4b0b3e51b07f56325befa4284db65fc89c02511b1"
+checksum = "07db9d94cbd326813772c968ccd25999e5f8ae22f4f8d1b11effa37ef6ce281d"
 dependencies = [
 "autocfg",
 "cfg-if",
@@ -636,9 +636,9 @@ dependencies = [

 [[package]]
 name = "crossbeam-utils"
-version = "0.8.11"
+version = "0.8.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "51887d4adc7b564537b15adcfb307936f8075dfcd5f00dde9a9f1d29383682bc"
+checksum = "7d82ee10ce34d7bc12c2122495e7593a9c41347ecdd64185af4ecf72cb1a7f83"
 dependencies = [
 "cfg-if",
 "once_cell",
@@ -917,9 +917,9 @@ checksum = "4443176a9f2c162692bd3d352d745ef9413eec5782a80d8fd6f8a1ac692a07f7"

 [[package]]
 name = "fastrand"
-version = "1.8.0"
+version = "1.7.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a7a407cfaa3385c4ae6b23e84623d48c2798d06e3e6a1878f7f59f17b3f86499"
+checksum = "c3fcf0cee53519c866c09b5de1f6c56ff9d647101f81c1964fa632e148896cdf"
 dependencies = [
 "instant",
 ]
@@ -1086,9 +1086,9 @@ dependencies = [

 [[package]]
 name = "generic-array"
-version = "0.14.6"
+version = "0.14.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bff49e947297f3312447abdca79f45f4738097cc82b06e72054d2223f601f1b9"
+checksum = "fd48d33ec7f05fbfa152300fdad764757cbded343c1aa1cff2fbaf4134851803"
 dependencies = [
 "typenum",
 "version_check",
@@ -1245,7 +1245,7 @@ checksum = "75f43d41e26995c17e71ee126451dd3941010b0514a81a9d11f3b341debc2399"
 dependencies = [
 "bytes",
 "fnv",
- "itoa 1.0.3",
+ "itoa 1.0.2",
 ]

 [[package]]
@@ -1308,7 +1308,7 @@ dependencies = [
 "http-body",
 "httparse",
 "httpdate",
- "itoa 1.0.3",
+ "itoa 1.0.2",
 "pin-project-lite",
 "socket2",
 "tokio",
@@ -1391,7 +1391,7 @@ dependencies = [
 "ahash",
 "atty",
 "indexmap",
- "itoa 1.0.3",
+ "itoa 1.0.2",
 "lazy_static",
 "log",
 "num-format",
@@ -1432,15 +1432,15 @@ checksum = "b71991ff56294aa922b450139ee08b3bfc70982c6b2c7562771375cf73542dd4"

 [[package]]
 name = "itoa"
-version = "1.0.3"
+version = "1.0.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6c8af84674fe1f223a982c933a0ee1086ac4d4052aa0fb8060c12c6ad838e754"
+checksum = "112c678d4050afce233f4f2852bb2eb519230b3cf12f33585275537d7e41578d"

 [[package]]
 name = "js-sys"
-version = "0.3.59"
+version = "0.3.58"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "258451ab10b34f8af53416d1fdab72c22e805f0c92a1136d59470ec0b11138b2"
+checksum = "c3fac17f7123a73ca62df411b1bf727ccc805daa070338fda671c86dac1bdc27"
 dependencies = [
 "wasm-bindgen",
 ]
@@ -1482,9 +1482,9 @@ checksum = "830d08ce1d1d941e6b30645f1a0eb5643013d835ce3779a5fc208261dbe10f55"

 [[package]]
 name = "libc"
-version = "0.2.127"
+version = "0.2.126"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "505e71a4706fa491e9b1b55f51b95d4037d0821ee40131190475f692b35b009b"
+checksum = "349d5a591cd28b49e1d1037471617a32ddcda5731b99419008085f72d5a53836"

 [[package]]
 name = "libloading"
@@ -1659,7 +1659,7 @@ name = "neon_local"
 version = "0.1.0"
 dependencies = [
 "anyhow",
- "clap 3.2.16",
+ "clap 3.2.12",
 "comfy-table",
 "control_plane",
 "git-version",
@@ -1854,7 +1854,7 @@ dependencies = [
 "byteorder",
 "bytes",
 "chrono",
- "clap 3.2.16",
+ "clap 3.2.12",
 "close_fds",
 "const_format",
 "crc32c",
@@ -2155,9 +2155,9 @@ checksum = "eb9f9e6e233e5c4a35559a617bf40a4ec447db2e84c20b55a6f83167b7e57872"

 [[package]]
 name = "prettyplease"
-version = "0.1.18"
+version = "0.1.16"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "697ae720ee02011f439e0701db107ffe2916d83f718342d65d7f8bf7b8a5fee9"
+checksum = "da6ffbe862780245013cb1c0a48c4e44b7d665548088f91f6b90876d0625e4c2"
 dependencies = [
 "proc-macro2",
 "syn",
@@ -2171,9 +2171,9 @@ checksum = "dbf0c48bc1d91375ae5c3cd81e3722dff1abcf81a30960240640d223f59fe0e5"

 [[package]]
 name = "proc-macro2"
-version = "1.0.43"
+version = "1.0.40"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0a2ca2c61bc9f3d74d2886294ab7b9853abd9c1ad903a3ac7815c58989bb7bab"
+checksum = "dd96a1e8ed2596c337f8eae5f24924ec83f5ad5ab21ea8e455d3566c69fbcaf7"
 dependencies = [
 "unicode-ident",
 ]
@@ -2271,7 +2271,7 @@ dependencies = [
 "base64",
 "bstr",
 "bytes",
- "clap 3.2.16",
+ "clap 3.2.12",
 "futures",
 "git-version",
 "hashbrown 0.11.2",
@@ -2326,9 +2326,9 @@ dependencies = [

 [[package]]
 name = "quote"
-version = "1.0.21"
+version = "1.0.20"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bbe448f377a7d6961e30f5955f9b8d106c3f5e449d493ee1b125c1d43c2b5179"
+checksum = "3bcdf212e9776fbcb2d23ab029360416bb1706b1aea2d1a5ba002727cbcab804"
 dependencies = [
 "proc-macro2",
 ]
@@ -2411,9 +2411,9 @@ dependencies = [

 [[package]]
 name = "redox_syscall"
-version = "0.2.16"
+version = "0.2.13"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fb5a58c1855b4b6819d59012155603f0b22ad30cad752600aadfcb695265519a"
+checksum = "62f25bc4c7e55e0b0b7a1d43fb893f4fa1361d0abe38b9ce4f323c2adfe6ef42"
 dependencies = [
 "bitflags",
 ]
@@ -2508,7 +2508,7 @@ dependencies = [
 "percent-encoding",
 "pin-project-lite",
 "rustls",
- "rustls-pemfile 1.0.1",
+ "rustls-pemfile 1.0.0",
 "serde",
 "serde_json",
 "serde_urlencoded",
@@ -2708,9 +2708,9 @@ dependencies = [

 [[package]]
 name = "rustls-pemfile"
-version = "1.0.1"
+version = "1.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0864aeff53f8c05aa08d86e5ef839d3dfcf07aeba2db32f12db0ef716e87bd55"
+checksum = "e7522c9de787ff061458fe9a829dc790a3f5b22dc571694fc5883f448b94d9a9"
 dependencies = [
 "base64",
 ]
@@ -2726,15 +2726,15 @@ dependencies = [

 [[package]]
 name = "rustversion"
-version = "1.0.9"
+version = "1.0.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "97477e48b4cf8603ad5f7aaf897467cf42ab4218a38ef76fb14c2d6773a6d6a8"
+checksum = "24c8ad4f0c00e1eb5bc7614d236a7f1300e3dbd76b68cac8e06fb00b015ad8d8"

 [[package]]
 name = "ryu"
-version = "1.0.11"
+version = "1.0.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4501abdff3ae82a1c1b477a17252eb69cee9e66eb915c1abaa4f44d873df9f09"
+checksum = "f3f6f92acf49d1b98f7a81226834412ada05458b7364277387724a237f062695"

 [[package]]
 name = "safekeeper"
@@ -2744,7 +2744,7 @@ dependencies = [
 "async-trait",
 "byteorder",
 "bytes",
- "clap 3.2.16",
+ "clap 3.2.12",
 "const_format",
 "crc32c",
 "daemonize",
@@ -2835,15 +2835,15 @@ dependencies = [

 [[package]]
 name = "semver"
-version = "1.0.13"
+version = "1.0.12"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "93f6841e709003d68bb2deee8c343572bf446003ec20a583e76f7b15cebf3711"
+checksum = "a2333e6df6d6598f2b1974829f853c2b4c5f4a6e503c10af918081aa6f8564e1"

 [[package]]
 name = "serde"
-version = "1.0.142"
+version = "1.0.139"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e590c437916fb6b221e1d00df6e3294f3fccd70ca7e92541c475d6ed6ef5fee2"
+checksum = "0171ebb889e45aa68b44aee0859b3eede84c6f5f5c228e6f140c0b2a0a46cad6"
 dependencies = [
 "serde_derive",
 ]
@@ -2860,9 +2860,9 @@ dependencies = [

 [[package]]
 name = "serde_derive"
-version = "1.0.142"
+version = "1.0.139"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "34b5b8d809babe02f538c2cfec6f2c1ed10804c0e5a6a041a049a4f5588ccc2e"
+checksum = "dc1d3230c1de7932af58ad8ffbe1d784bd55efd5a9d84ac24f69c72d83543dfb"
 dependencies = [
 "proc-macro2",
 "quote",
@@ -2871,11 +2871,11 @@ dependencies = [

 [[package]]
 name = "serde_json"
-version = "1.0.83"
+version = "1.0.82"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "38dd04e3c8279e75b31ef29dbdceebfe5ad89f4d0937213c53f7d49d01b3d5a7"
+checksum = "82c2c1fdcd807d1098552c5b9a36e425e42e9fbd7c6a37a8425f390f781f7fa7"
 dependencies = [
- "itoa 1.0.3",
+ "itoa 1.0.2",
 "ryu",
 "serde",
 ]
@@ -2887,7 +2887,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d3491c14715ca2294c4d6a88f15e84739788c1d030eed8c110436aafdaa2f3fd"
 dependencies = [
 "form_urlencoded",
- "itoa 1.0.3",
+ "itoa 1.0.2",
 "ryu",
 "serde",
 ]
@@ -2992,7 +2992,7 @@ dependencies = [
 "num-bigint",
 "num-traits",
 "thiserror",
- "time 0.3.12",
+ "time 0.3.11",
 ]

 [[package]]
@@ -3003,12 +3003,9 @@ checksum = "7bd3e3206899af3f8b12af284fafc038cc1dc2b41d1b89dd17297221c5d225de"

 [[package]]
 name = "slab"
-version = "0.4.7"
+version = "0.4.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4614a76b2a8be0058caa9dbbaf66d988527d86d003c11a94fbd335d7661edcef"
-dependencies = [
- "autocfg",
-]
+checksum = "eb703cfe953bccee95685111adeedb76fabe4e97549a58d16f03ea7b9367bb32"

 [[package]]
 name = "smallvec"
@@ -3116,9 +3113,9 @@ dependencies = [

 [[package]]
 name = "syn"
-version = "1.0.99"
+version = "1.0.98"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "58dbef6ec655055e20b86b15a8cc6d439cca19b667537ac6a1369572d151ab13"
+checksum = "c50aef8a904de4c23c788f104b7dddc7d6f79c647c7c8ce4cc8f73eb0ca773dd"
 dependencies = [
 "proc-macro2",
 "quote",
@@ -3194,18 +3191,18 @@ checksum = "b1141d4d61095b28419e22cb0bbf02755f5e54e0526f97f1e3d1d160e60885fb"

 [[package]]
 name = "thiserror"
-version = "1.0.32"
+version = "1.0.31"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f5f6586b7f764adc0231f4c79be7b920e766bb2f3e51b3661cdb263828f19994"
+checksum = "bd829fe32373d27f76265620b5309d0340cb8550f523c1dda251d6298069069a"
 dependencies = [
 "thiserror-impl",
 ]

 [[package]]
 name = "thiserror-impl"
-version = "1.0.32"
+version = "1.0.31"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "12bafc5b54507e0149cdf1b145a5d80ab80a90bcd9275df43d4fff68460f6c21"
+checksum = "0396bc89e626244658bef819e22d0cc459e795a5ebe878e6ec336d1674a8d79a"
 dependencies = [
 "proc-macro2",
 "quote",
@@ -3234,12 +3231,11 @@ dependencies = [

 [[package]]
 name = "time"
-version = "0.3.12"
+version = "0.3.11"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "74b7cc93fc23ba97fde84f7eea56c55d1ba183f495c6715defdfc7b9cb8c870f"
+checksum = "72c91f41dcb2f096c05f0873d667dceec1087ce5bcf984ec8ffb19acddbb3217"
 dependencies = [
- "itoa 1.0.3",
- "js-sys",
+ "itoa 1.0.2",
 "libc",
 "num_threads",
 "quickcheck",
@@ -3279,9 +3275,9 @@ checksum = "cda74da7e1a664f795bb1f8a87ec406fb89a02522cf6e50620d016add6dbbf5c"

 [[package]]
 name = "tokio"
-version = "1.20.1"
+version = "1.20.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7a8325f63a7d4774dd041e363b2409ed1c5cbbd0f867795e661df066b2b0a581"
+checksum = "57aec3cfa4c296db7255446efb4928a6be304b431a806216105542a67b6ca82e"
 dependencies = [
 "autocfg",
 "bytes",
@@ -3611,9 +3607,9 @@ checksum = "099b7128301d285f79ddd55b9a83d5e6b9e97c92e0ea0daebee7263e932de992"

 [[package]]
 name = "unicode-ident"
-version = "1.0.3"
+version = "1.0.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c4f5b37a154999a8f3f98cc23a628d850e154479cd94decf3414696e12e31aaf"
+checksum = "15c61ba63f9235225a22310255a29b806b907c9b8c964bcbd0a2c70f3f2deea7"

 [[package]]
 name = "unicode-normalization"
@@ -3732,7 +3728,7 @@ name = "wal_craft"
 version = "0.1.0"
 dependencies = [
 "anyhow",
- "clap 3.2.16",
+ "clap 3.2.12",
 "env_logger",
 "log",
 "once_cell",
@@ -3776,9 +3772,9 @@ checksum = "9c8d87e72b64a3b4db28d11ce29237c246188f4f51057d65a7eab63b7987e423"

 [[package]]
 name = "wasm-bindgen"
-version = "0.2.82"
+version = "0.2.81"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fc7652e3f6c4706c8d9cd54832c4a4ccb9b5336e2c3bd154d5cccfbf1c1f5f7d"
+checksum = "7c53b543413a17a202f4be280a7e5c62a1c69345f5de525ee64f8cfdbc954994"
 dependencies = [
 "cfg-if",
 "wasm-bindgen-macro",
@@ -3786,13 +3782,13 @@ dependencies = [

 [[package]]
 name = "wasm-bindgen-backend"
-version = "0.2.82"
+version = "0.2.81"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "662cd44805586bd52971b9586b1df85cdbbd9112e4ef4d8f41559c334dc6ac3f"
+checksum = "5491a68ab4500fa6b4d726bd67408630c3dbe9c4fe7bda16d5c82a1fd8c7340a"
 dependencies = [
 "bumpalo",
+ "lazy_static",
 "log",
- "once_cell",
 "proc-macro2",
 "quote",
 "syn",
@@ -3801,9 +3797,9 @@ dependencies = [

 [[package]]
 name = "wasm-bindgen-futures"
-version = "0.4.32"
+version = "0.4.31"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fa76fb221a1f8acddf5b54ace85912606980ad661ac7a503b4570ffd3a624dad"
+checksum = "de9a9cec1733468a8c657e57fa2413d2ae2c0129b95e87c5b72b8ace4d13f31f"
 dependencies = [
 "cfg-if",
 "js-sys",
@@ -3813,9 +3809,9 @@ dependencies = [

 [[package]]
 name = "wasm-bindgen-macro"
-version = "0.2.82"
+version = "0.2.81"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b260f13d3012071dfb1512849c033b1925038373aea48ced3012c09df952c602"
+checksum = "c441e177922bc58f1e12c022624b6216378e5febc2f0533e41ba443d505b80aa"
 dependencies = [
 "quote",
 "wasm-bindgen-macro-support",
@@ -3823,9 +3819,9 @@ dependencies = [

 [[package]]
 name = "wasm-bindgen-macro-support"
-version = "0.2.82"
+version = "0.2.81"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5be8e654bdd9b79216c2929ab90721aa82faf65c48cdf08bdc4e7f51357b80da"
+checksum = "7d94ac45fcf608c1f45ef53e748d35660f168490c10b23704c7779ab8f5c3048"
 dependencies = [
 "proc-macro2",
 "quote",
@@ -3836,15 +3832,15 @@ dependencies = [

 [[package]]
 name = "wasm-bindgen-shared"
-version = "0.2.82"
+version = "0.2.81"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6598dd0bd3c7d51095ff6531a5b23e02acdc81804e30d8f07afb77b7215a140a"
+checksum = "6a89911bd99e5f3659ec4acf9c4d93b0a90fe4a2a11f15328472058edc5261be"

 [[package]]
 name = "web-sys"
-version = "0.3.59"
+version = "0.3.58"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ed055ab27f941423197eb86b2035720b1a3ce40504df082cac2ecc6ed73335a1"
+checksum = "2fed94beee57daf8dd7d51f2b15dc2bcde92d7a72304cdf662a4371008b71b90"
 dependencies = [
 "js-sys",
 "wasm-bindgen",
@@ -3997,7 +3993,7 @@ dependencies = [
 "scopeguard",
 "serde",
 "syn",
- "time 0.3.12",
+ "time 0.3.11",
 "tokio",
 "tokio-util",
 "tracing",
@@ -4019,7 +4015,7 @@ dependencies = [
 "oid-registry",
 "rusticata-macros",
 "thiserror",
- "time 0.3.12",
+ "time 0.3.11",
 ]

 [[package]]
@@ -4048,6 +4044,6 @@ dependencies = [

 [[package]]
 name = "zeroize"
-version = "1.5.7"
+version = "1.5.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c394b5bd0c6f669e7275d9c20aa90ae064cb22e75a1cad54e1b34088034b149f"
+checksum = "20b578acffd8516a6c3f2a1bdefc1ec37e547bb4e0fb8b6b01a4cafc886b4442"
--- a/42
+++ b/42
@@ -1,6 +1,8 @@
 # Build Postgres
-FROM 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned AS pg-build
-WORKDIR /home/nonroot
+FROM neondatabase/rust:1.58 AS pg-build
+WORKDIR /pg
+
+USER root

 COPY vendor/postgres vendor/postgres
 COPY Makefile Makefile
@@ -9,30 +11,27 @@ ENV BUILD_TYPE release
 RUN set -e \
    && mold -run make -j $(nproc) -s postgres \
    && rm -rf tmp_install/build \
-    && tar -C tmp_install -czf /home/nonroot/postgres_install.tar.gz .
+    && tar -C tmp_install -czf /postgres_install.tar.gz .

 # Build zenith binaries
-FROM 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned AS build
-WORKDIR /home/nonroot
+FROM neondatabase/rust:1.58 AS build
 ARG GIT_VERSION=local

 # Enable https://github.com/paritytech/cachepot to cache Rust crates' compilation results in Docker builds.
 # Set up cachepot to use an AWS S3 bucket for cache results, to reuse it between `docker build` invocations.
-# cachepot falls back to local filesystem if S3 is misconfigured, not failing the build
+# cachepot falls back to local filesystem if S3 is misconfigured, not failing the build.
 ARG RUSTC_WRAPPER=cachepot
-ENV AWS_REGION=eu-central-1
-ENV CACHEPOT_S3_KEY_PREFIX=cachepot
-ARG CACHEPOT_BUCKET=neon-github-dev
-#ARG AWS_ACCESS_KEY_ID
-#ARG AWS_SECRET_ACCESS_KEY
+ARG CACHEPOT_BUCKET=zenith-rust-cachepot
+ARG AWS_ACCESS_KEY_ID
+ARG AWS_SECRET_ACCESS_KEY

-COPY --from=pg-build /home/nonroot/tmp_install/include/postgresql/server tmp_install/include/postgresql/server
+COPY --from=pg-build /pg/tmp_install/include/postgresql/server tmp_install/include/postgresql/server
 COPY . .

 # Show build caching stats to check if it was used in the end.
 # Has to be the part of the same RUN since cachepot daemon is killed in the end of this RUN, losing the compilation stats.
 RUN set -e \
-    && mold -run cargo build --release \
+    && sudo -E "PATH=$PATH" mold -run cargo build --release \
    && cachepot -s

 # Build final image
@@ -41,8 +40,8 @@ FROM debian:bullseye-slim
 WORKDIR /data

 RUN set -e \
-    && apt update \
-    && apt install -y \
+    && apt-get update \
+    && apt-get install -y \
        libreadline-dev \
        libseccomp-dev \
        openssl \
@@ -51,14 +50,17 @@ RUN set -e \
    && useradd -d /data zenith \
    && chown -R zenith:zenith /data

-COPY --from=build --chown=zenith:zenith /home/nonroot/target/release/pageserver /usr/local/bin
-COPY --from=build --chown=zenith:zenith /home/nonroot/target/release/safekeeper /usr/local/bin
-COPY --from=build --chown=zenith:zenith /home/nonroot/target/release/proxy      /usr/local/bin
+COPY --from=build --chown=zenith:zenith /home/runner/target/release/pageserver /usr/local/bin
+COPY --from=build --chown=zenith:zenith /home/runner/target/release/safekeeper /usr/local/bin
+COPY --from=build --chown=zenith:zenith /home/runner/target/release/proxy      /usr/local/bin

-COPY --from=pg-build /home/nonroot/tmp_install/ /usr/local/
-COPY --from=pg-build /home/nonroot/postgres_install.tar.gz /data/
+COPY --from=pg-build /pg/tmp_install/         /usr/local/
+COPY --from=pg-build /postgres_install.tar.gz /data/
+
+COPY docker-entrypoint.sh /docker-entrypoint.sh

 VOLUME ["/data"]
 USER zenith
 EXPOSE 6400
+ENTRYPOINT ["/docker-entrypoint.sh"]
 CMD ["pageserver"]
--- a/Dockerfile.compute-tools
+++ b/Dockerfile.compute-tools
@@ -1,25 +1,22 @@
 # First transient image to build compute_tools binaries
 # NB: keep in sync with rust image version in .github/workflows/build_and_test.yml
-FROM 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned AS rust-build
-WORKDIR /home/nonroot
+FROM neondatabase/rust:1.58 AS rust-build

 # Enable https://github.com/paritytech/cachepot to cache Rust crates' compilation results in Docker builds.
 # Set up cachepot to use an AWS S3 bucket for cache results, to reuse it between `docker build` invocations.
 # cachepot falls back to local filesystem if S3 is misconfigured, not failing the build.
 ARG RUSTC_WRAPPER=cachepot
-ENV AWS_REGION=eu-central-1
-ENV CACHEPOT_S3_KEY_PREFIX=cachepot
-ARG CACHEPOT_BUCKET=neon-github-dev
-#ARG AWS_ACCESS_KEY_ID
-#ARG AWS_SECRET_ACCESS_KEY
+ARG CACHEPOT_BUCKET=zenith-rust-cachepot
+ARG AWS_ACCESS_KEY_ID
+ARG AWS_SECRET_ACCESS_KEY

 COPY . .

 RUN set -e \
-    && mold -run cargo build -p compute_tools --release \
+    && sudo -E "PATH=$PATH" mold -run cargo build -p compute_tools --release \
    && cachepot -s

 # Final image that only has one binary
-FROM debian:bullseye-slim
+FROM debian:buster-slim

-COPY --from=rust-build /home/nonroot/target/release/compute_ctl /usr/local/bin/compute_ctl
+COPY --from=rust-build /home/runner/target/release/compute_ctl /usr/local/bin/compute_ctl
--- a/compute_tools/src/compute.rs
+++ b/compute_tools/src/compute.rs
@@ -178,7 +178,6 @@ impl ComputeNode {
            .args(&["--sync-safekeepers"])
            .env("PGDATA", &self.pgdata) // we cannot use -D in this mode
            .stdout(Stdio::piped())
-            .stderr(Stdio::piped())
            .spawn()
            .expect("postgres --sync-safekeepers failed to start");

@@ -188,13 +187,10 @@ impl ComputeNode {
        let sync_output = sync_handle
            .wait_with_output()
            .expect("postgres --sync-safekeepers failed");
-
        if !sync_output.status.success() {
            anyhow::bail!(
-                "postgres --sync-safekeepers exited with non-zero status: {}. stdout: {}, stderr: {}",
+                "postgres --sync-safekeepers exited with non-zero status: {}",
                sync_output.status,
-                String::from_utf8(sync_output.stdout).expect("postgres --sync-safekeepers exited, and stdout is not utf-8"),
-                String::from_utf8(sync_output.stderr).expect("postgres --sync-safekeepers exited, and stderr is not utf-8"),
            );
        }

--- a/compute_tools/src/pg_helpers.rs
+++ b/compute_tools/src/pg_helpers.rs
@@ -62,16 +62,9 @@ impl GenericOption {
    /// Represent `GenericOption` as configuration option.
    pub fn to_pg_setting(&self) -> String {
        if let Some(val) = &self.value {
-            let name = match self.name.as_str() {
-                "safekeepers" => "neon.safekeepers",
-                "wal_acceptor_reconnect" => "neon.safekeeper_reconnect_timeout",
-                "wal_acceptor_connect_timeout" => "neon.safekeeper_connect_timeout",
-                it => it,
-            };
-
            match self.vartype.as_ref() {
-                "string" => format!("{} = '{}'", name, val),
-                _ => format!("{} = {}", name, val),
+                "string" => format!("{} = '{}'", self.name, val),
+                _ => format!("{} = {}", self.name, val),
            }
        } else {
            self.name.to_owned()
--- a/compute_tools/tests/cluster_spec.json
+++ b/compute_tools/tests/cluster_spec.json
@@ -85,7 +85,7 @@
                "vartype": "bool"
            },
            {
-                "name": "neon.safekeepers",
+                "name": "safekeepers",
                "value": "127.0.0.1:6502,127.0.0.1:6503,127.0.0.1:6501",
                "vartype": "string"
            },
@@ -181,6 +181,7 @@
            }
        ]
    },
+
    "delta_operations": [
        {
            "action": "delete_db",
--- a/compute_tools/tests/pg_helpers_tests.rs
+++ b/compute_tools/tests/pg_helpers_tests.rs
@@ -28,7 +28,7 @@ mod pg_helpers_tests {

        assert_eq!(
            spec.cluster.settings.as_pg_settings(),
-            "fsync = off\nwal_level = replica\nhot_standby = on\nneon.safekeepers = '127.0.0.1:6502,127.0.0.1:6503,127.0.0.1:6501'\nwal_log_hints = on\nlog_connections = on\nshared_buffers = 32768\nport = 55432\nmax_connections = 100\nmax_wal_senders = 10\nlisten_addresses = '0.0.0.0'\nwal_sender_timeout = 0\npassword_encryption = md5\nmaintenance_work_mem = 65536\nmax_parallel_workers = 8\nmax_worker_processes = 8\nneon.tenant_id = 'b0554b632bd4d547a63b86c3630317e8'\nmax_replication_slots = 10\nneon.timeline_id = '2414a61ffc94e428f14b5758fe308e13'\nshared_preload_libraries = 'neon'\nsynchronous_standby_names = 'walproposer'\nneon.pageserver_connstring = 'host=127.0.0.1 port=6400'"
+            "fsync = off\nwal_level = replica\nhot_standby = on\nsafekeepers = '127.0.0.1:6502,127.0.0.1:6503,127.0.0.1:6501'\nwal_log_hints = on\nlog_connections = on\nshared_buffers = 32768\nport = 55432\nmax_connections = 100\nmax_wal_senders = 10\nlisten_addresses = '0.0.0.0'\nwal_sender_timeout = 0\npassword_encryption = md5\nmaintenance_work_mem = 65536\nmax_parallel_workers = 8\nmax_worker_processes = 8\nneon.tenant_id = 'b0554b632bd4d547a63b86c3630317e8'\nmax_replication_slots = 10\nneon.timeline_id = '2414a61ffc94e428f14b5758fe308e13'\nshared_preload_libraries = 'neon'\nsynchronous_standby_names = 'walproposer'\nneon.pageserver_connstring = 'host=127.0.0.1 port=6400'"
        );
    }

--- a/control_plane/src/compute.rs
+++ b/control_plane/src/compute.rs
@@ -150,7 +150,7 @@ impl PostgresNode {
        let port: u16 = conf.parse_field("port", &context)?;
        let timeline_id: ZTimelineId = conf.parse_field("neon.timeline_id", &context)?;
        let tenant_id: ZTenantId = conf.parse_field("neon.tenant_id", &context)?;
-        let uses_wal_proposer = conf.get("neon.safekeepers").is_some();
+        let uses_wal_proposer = conf.get("safekeepers").is_some();

        // parse recovery_target_lsn, if any
        let recovery_target_lsn: Option<Lsn> =
@@ -341,7 +341,7 @@ impl PostgresNode {
                .map(|sk| format!("localhost:{}", sk.pg_port))
                .collect::<Vec<String>>()
                .join(",");
-            conf.append("neon.safekeepers", &safekeepers);
+            conf.append("safekeepers", &safekeepers);
        } else {
            // We only use setup without safekeepers for tests,
            // and don't care about data durability on pageserver,
--- a/control_plane/src/local_env.rs
+++ b/control_plane/src/local_env.rs
@@ -24,7 +24,7 @@ use crate::safekeeper::SafekeeperNode;
 // This data structures represents neon_local CLI config
 //
 // It is deserialized from the .neon/config file, or the config file passed
-// to 'neon_local init --config=<path>' option. See control_plane/simple.conf for
+// to 'zenith init --config=<path>' option. See control_plane/simple.conf for
 // an example.
 //
 #[serde_as]
@@ -320,7 +320,7 @@ impl LocalEnv {

        if !repopath.exists() {
            bail!(
-                "Zenith config is not found in {}. You need to run 'neon_local init' first",
+                "Zenith config is not found in {}. You need to run 'zenith init' first",
                repopath.to_str().unwrap()
            );
        }
@@ -337,12 +337,12 @@ impl LocalEnv {
    }

    pub fn persist_config(&self, base_path: &Path) -> anyhow::Result<()> {
-        // Currently, the user first passes a config file with 'neon_local init --config=<path>'
+        // Currently, the user first passes a config file with 'zenith init --config=<path>'
        // We read that in, in `create_config`, and fill any missing defaults. Then it's saved
        // to .neon/config. TODO: We lose any formatting and comments along the way, which is
        // a bit sad.
        let mut conf_content = r#"# This file describes a locale deployment of the page server
-# and safekeeeper node. It is read by the 'neon_local' command-line
+# and safekeeeper node. It is read by the 'zenith' command-line
 # utility.
 "#
        .to_string();
@@ -382,7 +382,7 @@ impl LocalEnv {
    }

    //
-    // Initialize a new Neon repository
+    // Initialize a new Zenith repository
    //
    pub fn init(&mut self) -> anyhow::Result<()> {
        // check if config already exists
--- a/control_plane/src/safekeeper.rs
+++ b/control_plane/src/safekeeper.rs
@@ -1,4 +1,5 @@
 use std::io::Write;
+use std::net::TcpStream;
 use std::path::PathBuf;
 use std::process::Command;
 use std::sync::Arc;
@@ -51,7 +52,7 @@ impl ResponseErrorMessageExt for Response {
        Err(SafekeeperHttpError::Response(
            match self.json::<HttpErrorBody>() {
                Ok(err_body) => format!("Error: {}", err_body.msg),
-                Err(_) => format!("Http error ({}) at {}.", status.as_u16(), url),
+                Err(_) => format!("Http error ({}) at {url}.", status.as_u16()),
            },
        ))
    }
@@ -240,23 +241,37 @@ impl SafekeeperNode {
            ),
        }

-        // Wait until process is gone
-        for i in 0..600 {
-            let signal = None; // Send no signal, just get the error code
-            match kill(pid, signal) {
-                Ok(_) => (), // Process exists, keep waiting
-                Err(Errno::ESRCH) => {
-                    // Process not found, we're done
-                    println!("done!");
-                    return Ok(());
-                }
-                Err(err) => bail!(
-                    "Failed to send signal to pageserver with pid {}: {}",
-                    pid,
-                    err.desc()
-                ),
-            };
+        let address = connection_address(&self.pg_connection_config);

+        // TODO Remove this "timeout" and handle it on caller side instead.
+        // Shutting down may take a long time,
+        // if safekeeper flushes a lot of data
+        let mut tcp_stopped = false;
+        for i in 0..600 {
+            if !tcp_stopped {
+                if let Err(err) = TcpStream::connect(&address) {
+                    tcp_stopped = true;
+                    if err.kind() != io::ErrorKind::ConnectionRefused {
+                        eprintln!("\nSafekeeper connection failed with error: {err}");
+                    }
+                }
+            }
+            if tcp_stopped {
+                // Also check status on the HTTP port
+                match self.check_status() {
+                    Err(SafekeeperHttpError::Transport(err)) if err.is_connect() => {
+                        println!("done!");
+                        return Ok(());
+                    }
+                    Err(err) => {
+                        eprintln!("\nSafekeeper status check failed with error: {err}");
+                        return Ok(());
+                    }
+                    Ok(()) => {
+                        // keep waiting
+                    }
+                }
+            }
            if i % 10 == 0 {
                print!(".");
                io::stdout().flush().unwrap();
--- a/control_plane/src/storage.rs
+++ b/control_plane/src/storage.rs
@@ -1,8 +1,9 @@
 use std::collections::HashMap;
 use std::fs::File;
 use std::io::{BufReader, Write};
+use std::net::TcpStream;
 use std::num::NonZeroU64;
-use std::path::{Path, PathBuf};
+use std::path::PathBuf;
 use std::process::Command;
 use std::time::Duration;
 use std::{io, result, thread};
@@ -102,19 +103,23 @@ impl PageServerNode {

    /// Construct libpq connection string for connecting to the pageserver.
    fn pageserver_connection_config(password: &str, listen_addr: &str) -> Config {
-        format!("postgresql://no_user:{password}@{listen_addr}/no_db")
+        format!("postgresql://no_user:{}@{}/no_db", password, listen_addr)
            .parse()
            .unwrap()
    }

-    pub fn initialize(
+    pub fn init(
        &self,
        create_tenant: Option<ZTenantId>,
        initial_timeline_id: Option<ZTimelineId>,
        config_overrides: &[&str],
    ) -> anyhow::Result<ZTimelineId> {
+        let mut cmd = Command::new(self.env.pageserver_bin()?);
+
        let id = format!("id={}", self.env.pageserver.id);
+
        // FIXME: the paths should be shell-escaped to handle paths with spaces, quotas etc.
+        let base_data_dir_param = self.env.base_data_dir.display().to_string();
        let pg_distrib_dir_param =
            format!("pg_distrib_dir='{}'", self.env.pg_distrib_dir.display());
        let authg_type_param = format!("auth_type='{}'", self.env.pageserver.auth_type);
@@ -134,52 +139,67 @@ impl PageServerNode {
                .collect::<Vec<_>>()
                .join(",")
        );
+        let mut args = Vec::with_capacity(20);
+
+        args.push("--init");
+        args.extend(["-D", &base_data_dir_param]);
+        args.extend(["-c", &pg_distrib_dir_param]);
+        args.extend(["-c", &authg_type_param]);
+        args.extend(["-c", &listen_http_addr_param]);
+        args.extend(["-c", &listen_pg_addr_param]);
+        args.extend(["-c", &broker_endpoints_param]);
+        args.extend(["-c", &id]);
+
        let broker_etcd_prefix_param = self
            .env
            .etcd_broker
            .broker_etcd_prefix
            .as_ref()
            .map(|prefix| format!("broker_etcd_prefix='{prefix}'"));
-
-        let mut init_config_overrides = config_overrides.to_vec();
-        init_config_overrides.push(&id);
-        init_config_overrides.push(&pg_distrib_dir_param);
-        init_config_overrides.push(&authg_type_param);
-        init_config_overrides.push(&listen_http_addr_param);
-        init_config_overrides.push(&listen_pg_addr_param);
-        init_config_overrides.push(&broker_endpoints_param);
-
        if let Some(broker_etcd_prefix_param) = broker_etcd_prefix_param.as_deref() {
-            init_config_overrides.push(broker_etcd_prefix_param);
+            args.extend(["-c", broker_etcd_prefix_param]);
+        }
+
+        for config_override in config_overrides {
+            args.extend(["-c", config_override]);
        }

        if self.env.pageserver.auth_type != AuthType::Trust {
-            init_config_overrides.push("auth_validation_public_key_path='auth_public_key.pem'");
+            args.extend([
+                "-c",
+                "auth_validation_public_key_path='auth_public_key.pem'",
+            ]);
        }

-        self.start_node(&init_config_overrides, &self.env.base_data_dir, true)?;
-        let init_result = self
-            .try_init_timeline(create_tenant, initial_timeline_id)
-            .context("Failed to create initial tenant and timeline for pageserver");
-        match &init_result {
-            Ok(initial_timeline_id) => {
-                println!("Successfully initialized timeline {initial_timeline_id}")
-            }
-            Err(e) => eprintln!("{e:#}"),
+        let create_tenant = create_tenant.map(|id| id.to_string());
+        if let Some(tenant_id) = create_tenant.as_deref() {
+            args.extend(["--create-tenant", tenant_id])
        }
-        self.stop(false)?;
-        init_result
-    }

-    fn try_init_timeline(
-        &self,
-        new_tenant_id: Option<ZTenantId>,
-        new_timeline_id: Option<ZTimelineId>,
-    ) -> anyhow::Result<ZTimelineId> {
-        let initial_tenant_id = self.tenant_create(new_tenant_id, HashMap::new())?;
-        let initial_timeline_info =
-            self.timeline_create(initial_tenant_id, new_timeline_id, None, None)?;
-        Ok(initial_timeline_info.timeline_id)
+        let initial_timeline_id = initial_timeline_id.unwrap_or_else(ZTimelineId::generate);
+        let initial_timeline_id_string = initial_timeline_id.to_string();
+        args.extend(["--initial-timeline-id", &initial_timeline_id_string]);
+
+        let cmd_with_args = cmd.args(args);
+        let init_output = fill_rust_env_vars(cmd_with_args)
+            .output()
+            .with_context(|| {
+                format!("failed to init pageserver with command {:?}", cmd_with_args)
+            })?;
+
+        if !init_output.status.success() {
+            bail!(
+                "init invocation failed, {}\nStdout: {}\nStderr: {}",
+                init_output.status,
+                String::from_utf8_lossy(&init_output.stdout),
+                String::from_utf8_lossy(&init_output.stderr)
+            );
+        }
+
+        // echo the captured output of the init command
+        println!("{}", String::from_utf8_lossy(&init_output.stdout));
+
+        Ok(initial_timeline_id)
    }

    pub fn repo_path(&self) -> PathBuf {
@@ -191,35 +211,15 @@ impl PageServerNode {
    }

    pub fn start(&self, config_overrides: &[&str]) -> anyhow::Result<()> {
-        self.start_node(config_overrides, &self.repo_path(), false)
-    }
-
-    fn start_node(
-        &self,
-        config_overrides: &[&str],
-        datadir: &Path,
-        update_config: bool,
-    ) -> anyhow::Result<()> {
-        println!(
+        print!(
            "Starting pageserver at '{}' in '{}'",
            connection_address(&self.pg_connection_config),
-            datadir.display()
+            self.repo_path().display()
        );
-        io::stdout().flush()?;
+        io::stdout().flush().unwrap();

-        let mut args = vec![
-            "-D",
-            datadir.to_str().with_context(|| {
-                format!(
-                    "Datadir path '{}' cannot be represented as a unicode string",
-                    datadir.display()
-                )
-            })?,
-        ];
-
-        if update_config {
-            args.push("--update-config");
-        }
+        let repo_path = self.repo_path();
+        let mut args = vec!["-D", repo_path.to_str().unwrap()];

        for config_override in config_overrides {
            args.extend(["-c", config_override]);
@@ -231,8 +231,8 @@ impl PageServerNode {

        if !filled_cmd.status()?.success() {
            bail!(
-                "Pageserver failed to start. See console output and '{}' for details.",
-                datadir.join("pageserver.log").display()
+                "Pageserver failed to start. See '{}' for details.",
+                self.repo_path().join("pageserver.log").display()
            );
        }

@@ -241,7 +241,7 @@ impl PageServerNode {
        const RETRIES: i8 = 15;
        for retries in 1..RETRIES {
            match self.check_status() {
-                Ok(()) => {
+                Ok(_) => {
                    println!("\nPageserver started");
                    return Ok(());
                }
@@ -255,18 +255,21 @@ impl PageServerNode {
                                if retries == 5 {
                                    println!() // put a line break after dots for second message
                                }
-                                println!("Pageserver not responding yet, err {err} retrying ({retries})...");
+                                println!(
+                                    "Pageserver not responding yet, err {} retrying ({})...",
+                                    err, retries
+                                );
                            }
                        }
                        PageserverHttpError::Response(msg) => {
-                            bail!("pageserver failed to start: {msg} ")
+                            bail!("pageserver failed to start: {} ", msg)
                        }
                    }
                    thread::sleep(Duration::from_secs(1));
                }
            }
        }
-        bail!("pageserver failed to start in {RETRIES} seconds");
+        bail!("pageserver failed to start in {} seconds", RETRIES);
    }

    ///
@@ -296,32 +299,51 @@ impl PageServerNode {
        match kill(pid, sig) {
            Ok(_) => (),
            Err(Errno::ESRCH) => {
-                println!("Pageserver with pid {pid} does not exist, but a PID file was found");
+                println!(
+                    "Pageserver with pid {} does not exist, but a PID file was found",
+                    pid
+                );
                return Ok(());
            }
            Err(err) => bail!(
-                "Failed to send signal to pageserver with pid {pid}: {}",
+                "Failed to send signal to pageserver with pid {}: {}",
+                pid,
                err.desc()
            ),
        }

-        // Wait until process is gone
-        for i in 0..600 {
-            let signal = None; // Send no signal, just get the error code
-            match kill(pid, signal) {
-                Ok(_) => (), // Process exists, keep waiting
-                Err(Errno::ESRCH) => {
-                    // Process not found, we're done
-                    println!("done!");
-                    return Ok(());
-                }
-                Err(err) => bail!(
-                    "Failed to send signal to pageserver with pid {}: {}",
-                    pid,
-                    err.desc()
-                ),
-            };
+        let address = connection_address(&self.pg_connection_config);

+        // TODO Remove this "timeout" and handle it on caller side instead.
+        // Shutting down may take a long time,
+        // if pageserver checkpoints a lot of data
+        let mut tcp_stopped = false;
+        for i in 0..600 {
+            if !tcp_stopped {
+                if let Err(err) = TcpStream::connect(&address) {
+                    tcp_stopped = true;
+                    if err.kind() != io::ErrorKind::ConnectionRefused {
+                        eprintln!("\nPageserver connection failed with error: {err}");
+                    }
+                }
+            }
+            if tcp_stopped {
+                // Also check status on the HTTP port
+
+                match self.check_status() {
+                    Err(PageserverHttpError::Transport(err)) if err.is_connect() => {
+                        println!("done!");
+                        return Ok(());
+                    }
+                    Err(err) => {
+                        eprintln!("\nPageserver status check failed with error: {err}");
+                        return Ok(());
+                    }
+                    Ok(()) => {
+                        // keep waiting
+                    }
+                }
+            }
            if i % 10 == 0 {
                print!(".");
                io::stdout().flush().unwrap();
@@ -329,13 +351,13 @@ impl PageServerNode {
            thread::sleep(Duration::from_millis(100));
        }

-        bail!("Failed to stop pageserver with pid {pid}");
+        bail!("Failed to stop pageserver with pid {}", pid);
    }

    pub fn page_server_psql(&self, sql: &str) -> Vec<postgres::SimpleQueryMessage> {
        let mut client = self.pg_connection_config.connect(NoTls).unwrap();

-        println!("Pageserver query: '{sql}'");
+        println!("Pageserver query: '{}'", sql);
        client.simple_query(sql).unwrap()
    }

@@ -370,8 +392,9 @@ impl PageServerNode {
        &self,
        new_tenant_id: Option<ZTenantId>,
        settings: HashMap<&str, &str>,
-    ) -> anyhow::Result<ZTenantId> {
-        self.http_request(Method::POST, format!("{}/tenant", self.http_base_url))
+    ) -> anyhow::Result<Option<ZTenantId>> {
+        let tenant_id_string = self
+            .http_request(Method::POST, format!("{}/tenant", self.http_base_url))
            .json(&TenantCreateRequest {
                new_tenant_id,
                checkpoint_distance: settings
@@ -410,16 +433,18 @@ impl PageServerNode {
            })
            .send()?
            .error_from_body()?
-            .json::<Option<String>>()
-            .with_context(|| {
-                format!("Failed to parse tenant creation response for tenant id: {new_tenant_id:?}")
-            })?
-            .context("No tenant id was found in the tenant creation response")
-            .and_then(|tenant_id_string| {
-                tenant_id_string.parse().with_context(|| {
-                    format!("Failed to parse response string as tenant id: '{tenant_id_string}'")
+            .json::<Option<String>>()?;
+
+        tenant_id_string
+            .map(|id| {
+                id.parse().with_context(|| {
+                    format!(
+                        "Failed to parse tennat creation response as tenant id: {}",
+                        id
+                    )
                })
            })
+            .transpose()
    }

    pub fn tenant_config(&self, tenant_id: ZTenantId, settings: HashMap<&str, &str>) -> Result<()> {
@@ -490,27 +515,22 @@ impl PageServerNode {
        new_timeline_id: Option<ZTimelineId>,
        ancestor_start_lsn: Option<Lsn>,
        ancestor_timeline_id: Option<ZTimelineId>,
-    ) -> anyhow::Result<TimelineInfo> {
-        self.http_request(
-            Method::POST,
-            format!("{}/tenant/{}/timeline", self.http_base_url, tenant_id),
-        )
-        .json(&TimelineCreateRequest {
-            new_timeline_id,
-            ancestor_start_lsn,
-            ancestor_timeline_id,
-        })
-        .send()?
-        .error_from_body()?
-        .json::<Option<TimelineInfo>>()
-        .with_context(|| {
-            format!("Failed to parse timeline creation response for tenant id: {tenant_id}")
-        })?
-        .with_context(|| {
-            format!(
-                "No timeline id was found in the timeline creation response for tenant {tenant_id}"
+    ) -> anyhow::Result<Option<TimelineInfo>> {
+        let timeline_info_response = self
+            .http_request(
+                Method::POST,
+                format!("{}/tenant/{}/timeline", self.http_base_url, tenant_id),
            )
-        })
+            .json(&TimelineCreateRequest {
+                new_timeline_id,
+                ancestor_start_lsn,
+                ancestor_timeline_id,
+            })
+            .send()?
+            .error_from_body()?
+            .json::<Option<TimelineInfo>>()?;
+
+        Ok(timeline_info_response)
    }

    /// Import a basebackup prepared using either:
--- a/docker-entrypoint.sh
+++ b/docker-entrypoint.sh
@@ -0,0 +1,24 @@
+#!/bin/sh
+set -eux
+
+pageserver_id_param="${NODE_ID:-10}"
+
+broker_endpoints_param="${BROKER_ENDPOINT:-absent}"
+if [ "$broker_endpoints_param" != "absent" ]; then
+    broker_endpoints_param="-c broker_endpoints=['$broker_endpoints_param']"
+else
+    broker_endpoints_param=''
+fi
+
+remote_storage_param="${REMOTE_STORAGE:-}"
+
+if [ "$1" = 'pageserver' ]; then
+    if [ ! -d "/data/tenants" ]; then
+        echo "Initializing pageserver data directory"
+        pageserver --init -D /data -c "pg_distrib_dir='/usr/local'" -c "id=${pageserver_id_param}" $broker_endpoints_param $remote_storage_param
+    fi
+    echo "Staring pageserver at 0.0.0.0:6400"
+    pageserver -c "listen_pg_addr='0.0.0.0:6400'" -c "listen_http_addr='0.0.0.0:9898'" $broker_endpoints_param -D /data
+else
+    "$@"
+fi
--- a/libs/postgres_ffi/build.rs
+++ b/libs/postgres_ffi/build.rs
@@ -44,7 +44,7 @@ impl ParseCallbacks for PostgresFfiCallbacks {

 fn main() {
    // Tell cargo to invalidate the built crate whenever the wrapper changes
-    println!("cargo:rerun-if-changed=bindgen_deps.h");
+    println!("cargo:rerun-if-changed=pg_control_ffi.h");

    // Finding the location of C headers for the Postgres server:
    // - if POSTGRES_INSTALL_DIR is set look into it, otherwise look into `<project_root>/tmp_install`
@@ -88,9 +88,9 @@ fn main() {
    // the resulting bindings.
    let bindings = bindgen::Builder::default()
        //
-        // All the needed PostgreSQL headers are included from 'bindgen_deps.h'
+        // All the needed PostgreSQL headers are included from 'pg_control_ffi.h'
        //
-        .header("bindgen_deps.h")
+        .header("pg_control_ffi.h")
        //
        // Tell cargo to invalidate the built crate whenever any of the
        // included header files changed.
--- a/libs/postgres_ffi/pg_control_ffi.h
+++ b/libs/postgres_ffi/pg_control_ffi.h
--- a/libs/postgres_ffi/src/controlfile_utils.rs
+++ b/libs/postgres_ffi/src/controlfile_utils.rs
@@ -23,7 +23,7 @@
 //! information. You can use PostgreSQL's pg_controldata utility to view its
 //! contents.
 //!
-use super::bindings::{ControlFileData, PG_CONTROL_FILE_SIZE};
+use crate::{ControlFileData, PG_CONTROL_FILE_SIZE};

 use anyhow::{bail, Result};
 use bytes::{Bytes, BytesMut};
--- a/libs/postgres_ffi/src/lib.rs
+++ b/libs/postgres_ffi/src/lib.rs
@@ -7,62 +7,21 @@
 // https://github.com/rust-lang/rust-bindgen/issues/1651
 #![allow(deref_nullptr)]

+use serde::{Deserialize, Serialize};
 use utils::lsn::Lsn;

-macro_rules! postgres_ffi {
-    ($version:ident) => {
-        #[path = "."]
-        pub mod $version {
-            // fixme: does this have to be 'pub'?
-            pub mod bindings {
-                // bindgen generates bindings for a lot of stuff we don't need
-                #![allow(dead_code)]
+include!(concat!(env!("OUT_DIR"), "/bindings.rs"));

-                use serde::{Deserialize, Serialize};
-                include!(concat!(env!("OUT_DIR"), "/bindings.rs"));
-            }
-            pub mod controlfile_utils;
-            pub mod nonrelfile_utils;
-            pub mod pg_constants;
-            pub mod relfile_utils;
-            pub mod waldecoder;
-            pub mod xlog_utils;
-
-            // Re-export some symbols from bindings
-            pub use bindings::DBState_DB_SHUTDOWNED;
-            pub use bindings::{CheckPoint, ControlFileData, XLogRecord};
-        }
-    };
-}
-
-postgres_ffi!(v14);
-
-// Export some widely used datatypes that are unlikely to change across Postgres versions
-pub use v14::bindings::{uint32, uint64, Oid};
-pub use v14::bindings::{BlockNumber, OffsetNumber};
-pub use v14::bindings::{MultiXactId, TransactionId};
-
-// Likewise for these, although the assumption that these don't change is a little more iffy.
-pub use v14::bindings::{MultiXactOffset, MultiXactStatus};
-
-// from pg_config.h. These can be changed with configure options --with-blocksize=BLOCKSIZE and
-// --with-segsize=SEGSIZE, but assume the defaults for now.
-pub const BLCKSZ: u16 = 8192;
-pub const RELSEG_SIZE: u32 = 1024 * 1024 * 1024 / (BLCKSZ as u32);
-pub const XLOG_BLCKSZ: usize = 8192;
-
-// PG timeline is always 1, changing it doesn't have any useful meaning in Neon.
-//
-// NOTE: this is not to be confused with Neon timelines; different concept!
-//
-// It's a shaky assumption, that it's always 1. We might import a
-// PostgreSQL data directory that has gone through timeline bumps,
-// for example. FIXME later.
-pub const PG_TLI: u32 = 1;
+pub mod controlfile_utils;
+pub mod nonrelfile_utils;
+pub mod pg_constants;
+pub mod relfile_utils;
+pub mod waldecoder;
+pub mod xlog_utils;

 //  See TransactionIdIsNormal in transam.h
 pub const fn transaction_id_is_normal(id: TransactionId) -> bool {
-    id > v14::pg_constants::FIRST_NORMAL_TRANSACTION_ID
+    id > pg_constants::FIRST_NORMAL_TRANSACTION_ID
 }

 // See TransactionIdPrecedes in transam.c
--- a/libs/postgres_ffi/src/nonrelfile_utils.rs
+++ b/libs/postgres_ffi/src/nonrelfile_utils.rs
@@ -1,12 +1,11 @@
 //!
 //! Common utilities for dealing with PostgreSQL non-relation files.
 //!
-use crate::transaction_id_precedes;
-use super::pg_constants;
+use crate::{pg_constants, transaction_id_precedes};
 use bytes::BytesMut;
 use log::*;

-use super::bindings::MultiXactId;
+use crate::MultiXactId;

 pub fn transaction_id_set_status(xid: u32, status: u8, page: &mut BytesMut) {
    trace!(
--- a/libs/postgres_ffi/src/pg_constants.rs
+++ b/libs/postgres_ffi/src/pg_constants.rs
@@ -7,8 +7,7 @@
 //! comments on them.
 //!

-use super::bindings::PageHeaderData;
-use crate::BLCKSZ;
+use crate::PageHeaderData;

 //
 // From pg_tablespace_d.h
@@ -32,6 +31,11 @@ pub const SMGR_TRUNCATE_HEAP: u32 = 0x0001;
 pub const SMGR_TRUNCATE_VM: u32 = 0x0002;
 pub const SMGR_TRUNCATE_FSM: u32 = 0x0004;

+// from pg_config.h. These can be changed with configure options --with-blocksize=BLOCKSIZE and
+// --with-segsize=SEGSIZE, but assume the defaults for now.
+pub const BLCKSZ: u16 = 8192;
+pub const RELSEG_SIZE: u32 = 1024 * 1024 * 1024 / (BLCKSZ as u32);
+
 //
 // From bufpage.h
 //
@@ -209,6 +213,7 @@ pub const FIRST_NORMAL_OBJECT_ID: u32 = 16384;
 /* FIXME: pageserver should request wal_seg_size from compute node */
 pub const WAL_SEGMENT_SIZE: usize = 16 * 1024 * 1024;

+pub const XLOG_BLCKSZ: usize = 8192;
 pub const XLOG_CHECKPOINT_SHUTDOWN: u8 = 0x00;
 pub const XLOG_CHECKPOINT_ONLINE: u8 = 0x10;
 pub const XLP_LONG_HEADER: u16 = 0x0002;
--- a/libs/postgres_ffi/src/relfile_utils.rs
+++ b/libs/postgres_ffi/src/relfile_utils.rs
@@ -1,11 +1,11 @@
 //!
 //! Common utilities for dealing with PostgreSQL relation files.
 //!
-use super::pg_constants;
+use crate::pg_constants;
 use once_cell::sync::OnceCell;
 use regex::Regex;

-#[derive(Debug, Clone, thiserror::Error, PartialEq, Eq)]
+#[derive(Debug, Clone, thiserror::Error, PartialEq)]
 pub enum FilePathError {
    #[error("invalid relation fork name")]
    InvalidForkName,
--- a/libs/postgres_ffi/src/waldecoder.rs
+++ b/libs/postgres_ffi/src/waldecoder.rs
@@ -10,7 +10,10 @@
 //!
 use super::pg_constants;
 use super::xlog_utils::*;
-use super::bindings::{XLogLongPageHeaderData, XLogPageHeaderData, XLogRecord, XLOG_PAGE_MAGIC};
+use super::XLogLongPageHeaderData;
+use super::XLogPageHeaderData;
+use super::XLogRecord;
+use super::XLOG_PAGE_MAGIC;
 use bytes::{Buf, BufMut, Bytes, BytesMut};
 use crc32c::*;
 use log::*;
@@ -81,11 +84,11 @@ impl WalStreamDecoder {
            }
            match self.state {
                State::WaitingForRecord => {
-                    if hdr.xlp_info & XLP_FIRST_IS_CONTRECORD != 0 {
-                        return Err(
-                            "invalid xlog page header: unexpected XLP_FIRST_IS_CONTRECORD".into(),
-                        );
-                    }
+                    // if hdr.xlp_info & XLP_FIRST_IS_CONTRECORD != 0 {
+                    //     return Err(
+                    //         "invalid xlog page header: unexpected XLP_FIRST_IS_CONTRECORD".into(),
+                    //     );
+                    // }
                    if hdr.xlp_rem_len != 0 {
                        return Err(format!(
                            "invalid xlog page header: xlp_rem_len={}, but it's not a contrecord",
--- a/libs/postgres_ffi/src/xlog_utils.rs
+++ b/libs/postgres_ffi/src/xlog_utils.rs
@@ -7,24 +7,22 @@
 // have been named the same as the corresponding PostgreSQL functions instead.
 //

-use crc32c::crc32c_append;
+use crate::pg_constants;
+use crate::CheckPoint;
+use crate::FullTransactionId;
+use crate::XLogLongPageHeaderData;
+use crate::XLogPageHeaderData;
+use crate::XLogRecord;
+use crate::XLOG_PAGE_MAGIC;

-use super::bindings::{
-    CheckPoint, FullTransactionId, XLogLongPageHeaderData, XLogPageHeaderData, XLogRecord,
-    XLOG_PAGE_MAGIC,
-};
-use super::pg_constants;
-use super::pg_constants::WAL_SEGMENT_SIZE;
-use crate::v14::waldecoder::WalStreamDecoder;
-use crate::PG_TLI;
-use crate::{uint32, uint64, Oid};
+use crate::pg_constants::WAL_SEGMENT_SIZE;
+use crate::waldecoder::WalStreamDecoder;

 use bytes::BytesMut;
 use bytes::{Buf, Bytes};

 use log::*;

-use serde::Serialize;
 use std::fs::File;
 use std::io::prelude::*;
 use std::io::ErrorKind;
@@ -49,6 +47,9 @@ pub const XLOG_SIZE_OF_XLOG_RECORD: usize = std::mem::size_of::<XLogRecord>();
 #[allow(clippy::identity_op)]
 pub const SIZE_OF_XLOG_RECORD_DATA_HEADER_SHORT: usize = 1 * 2;

+// PG timeline is always 1, changing it doesn't have useful meaning in Zenith.
+pub const PG_TLI: u32 = 1;
+
 pub type XLogRecPtr = u64;
 pub type TimeLineID = u32;
 pub type TimestampTz = i64;
@@ -79,12 +80,12 @@ pub fn XLogSegNoOffsetToRecPtr(

 #[allow(non_snake_case)]
 pub fn XLogFileName(tli: TimeLineID, logSegNo: XLogSegNo, wal_segsz_bytes: usize) -> String {
-    format!(
+    return format!(
        "{:>08X}{:>08X}{:>08X}",
        tli,
        logSegNo / XLogSegmentsPerXLogId(wal_segsz_bytes),
        logSegNo % XLogSegmentsPerXLogId(wal_segsz_bytes)
-    )
+    );
 }

 #[allow(non_snake_case)]
@@ -345,85 +346,6 @@ pub fn generate_wal_segment(segno: u64, system_id: u64) -> Result<Bytes, Seriali
    Ok(seg_buf.freeze())
 }

-#[repr(C)]
-#[derive(Serialize)]
-struct XlLogicalMessage {
-    db_id: Oid,
-    transactional: uint32, // bool, takes 4 bytes due to alignment in C structures
-    prefix_size: uint64,
-    message_size: uint64,
-}
-
-impl XlLogicalMessage {
-    pub fn encode(&self) -> Bytes {
-        use utils::bin_ser::LeSer;
-        self.ser().unwrap().into()
-    }
-}
-
-/// Create new WAL record for non-transactional logical message.
-/// Used for creating artificial WAL for tests, as LogicalMessage
-/// record is basically no-op.
-///
-/// NOTE: This leaves the xl_prev field zero. The safekeeper and
-/// pageserver tolerate that, but PostgreSQL does not.
-pub fn encode_logical_message(prefix: &str, message: &str) -> Vec<u8> {
-    let mut prefix_bytes: Vec<u8> = Vec::with_capacity(prefix.len() + 1);
-    prefix_bytes.write_all(prefix.as_bytes()).unwrap();
-    prefix_bytes.push(0);
-
-    let message_bytes = message.as_bytes();
-
-    let logical_message = XlLogicalMessage {
-        db_id: 0,
-        transactional: 0,
-        prefix_size: prefix_bytes.len() as u64,
-        message_size: message_bytes.len() as u64,
-    };
-
-    let mainrdata = logical_message.encode();
-    let mainrdata_len: usize = mainrdata.len() + prefix_bytes.len() + message_bytes.len();
-    // only short mainrdata is supported for now
-    assert!(mainrdata_len <= 255);
-    let mainrdata_len = mainrdata_len as u8;
-
-    let mut data: Vec<u8> = vec![pg_constants::XLR_BLOCK_ID_DATA_SHORT, mainrdata_len];
-    data.extend_from_slice(&mainrdata);
-    data.extend_from_slice(&prefix_bytes);
-    data.extend_from_slice(message_bytes);
-
-    let total_len = XLOG_SIZE_OF_XLOG_RECORD + data.len();
-
-    let mut header = XLogRecord {
-        xl_tot_len: total_len as u32,
-        xl_xid: 0,
-        xl_prev: 0,
-        xl_info: 0,
-        xl_rmid: 21,
-        __bindgen_padding_0: [0u8; 2usize],
-        xl_crc: 0, // crc will be calculated later
-    };
-
-    let header_bytes = header.encode().expect("failed to encode header");
-    let crc = crc32c_append(0, &data);
-    let crc = crc32c_append(crc, &header_bytes[0..XLOG_RECORD_CRC_OFFS]);
-    header.xl_crc = crc;
-
-    let mut wal: Vec<u8> = Vec::new();
-    wal.extend_from_slice(&header.encode().expect("failed to encode header"));
-    wal.extend_from_slice(&data);
-
-    // WAL start position must be aligned at 8 bytes,
-    // this will add padding for the next WAL record.
-    const PADDING: usize = 8;
-    let padding_rem = wal.len() % PADDING;
-    if padding_rem != 0 {
-        wal.resize(wal.len() + PADDING - padding_rem, 0);
-    }
-
-    wal
-}
-
 #[cfg(test)]
 mod tests {
    use super::*;
@@ -625,15 +547,4 @@ mod tests {
        checkpoint.update_next_xid(1024);
        assert_eq!(checkpoint.nextXid.value, 2048);
    }
-
-    #[test]
-    pub fn test_encode_logical_message() {
-        let expected = [
-            64, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 21, 0, 0, 170, 34, 166, 227, 255,
-            38, 0, 0, 0, 0, 0, 0, 0, 0, 7, 0, 0, 0, 0, 0, 0, 0, 7, 0, 0, 0, 0, 0, 0, 0, 112, 114,
-            101, 102, 105, 120, 0, 109, 101, 115, 115, 97, 103, 101,
-        ];
-        let actual = encode_logical_message("prefix", "message");
-        assert_eq!(expected, actual[..]);
-    }
 }
--- a/libs/postgres_ffi/wal_craft/src/lib.rs
+++ b/libs/postgres_ffi/wal_craft/src/lib.rs
@@ -4,8 +4,8 @@ use log::*;
 use once_cell::sync::Lazy;
 use postgres::types::PgLsn;
 use postgres::Client;
-use postgres_ffi::v14::pg_constants::WAL_SEGMENT_SIZE;
-use postgres_ffi::v14::xlog_utils::{
+use postgres_ffi::pg_constants::WAL_SEGMENT_SIZE;
+use postgres_ffi::xlog_utils::{
    XLOG_BLCKSZ, XLOG_SIZE_OF_XLOG_RECORD, XLOG_SIZE_OF_XLOG_SHORT_PHD,
 };
 use std::cmp::Ordering;
--- a/libs/utils/src/bin_ser.rs
+++ b/libs/utils/src/bin_ser.rs
@@ -265,7 +265,7 @@ mod tests {
    use serde::{Deserialize, Serialize};
    use std::io::Cursor;

-    #[derive(Debug, PartialEq, Eq, Serialize, Deserialize)]
+    #[derive(Debug, PartialEq, Serialize, Deserialize)]
    pub struct ShortStruct {
        a: u8,
        b: u32,
@@ -286,7 +286,7 @@ mod tests {
    const SHORT2_ENC_LE: &[u8] = &[8, 0, 0, 3, 7];
    const SHORT2_ENC_LE_TRAILING: &[u8] = &[8, 0, 0, 3, 7, 0xff, 0xff, 0xff];

-    #[derive(Debug, PartialEq, Eq, Serialize, Deserialize)]
+    #[derive(Debug, PartialEq, Serialize, Deserialize)]
    pub struct LongMsg {
        pub tag: u8,
        pub blockpos: u32,
--- a/libs/utils/src/http/request.rs
+++ b/libs/utils/src/http/request.rs
@@ -10,10 +10,12 @@ pub fn get_request_param<'a>(
 ) -> Result<&'a str, ApiError> {
    match request.param(param_name) {
        Some(arg) => Ok(arg),
-        None => Err(ApiError::BadRequest(format!(
-            "no {} specified in path param",
-            param_name
-        ))),
+        None => {
+            return Err(ApiError::BadRequest(format!(
+                "no {} specified in path param",
+                param_name
+            )))
+        }
    }
 }

--- a/libs/utils/src/lsn.rs
+++ b/libs/utils/src/lsn.rs
@@ -18,7 +18,7 @@ pub const XLOG_BLCKSZ: u32 = 8192;
 pub struct Lsn(pub u64);

 /// We tried to parse an LSN from a string, but failed
-#[derive(Debug, PartialEq, Eq, thiserror::Error)]
+#[derive(Debug, PartialEq, thiserror::Error)]
 #[error("LsnParseError")]
 pub struct LsnParseError;

--- a/libs/utils/src/postgres_backend.rs
+++ b/libs/utils/src/postgres_backend.rs
@@ -50,7 +50,7 @@ pub trait Handler {

 /// PostgresBackend protocol state.
 /// XXX: The order of the constructors matters.
-#[derive(Clone, Copy, PartialEq, Eq, PartialOrd)]
+#[derive(Clone, Copy, PartialEq, PartialOrd)]
 pub enum ProtoState {
    Initialization,
    Encrypted,
--- a/libs/utils/src/pq_proto.rs
+++ b/libs/utils/src/pq_proto.rs
@@ -930,7 +930,7 @@ impl<'a> BeMessage<'a> {

 // Neon extension of postgres replication protocol
 // See NEON_STATUS_UPDATE_TAG_BYTE
-#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
+#[derive(Debug, Clone, Copy, PartialEq, Serialize, Deserialize)]
 pub struct ReplicationFeedback {
    // Last known size of the timeline. Used to enforce timeline size limit.
    pub current_timeline_size: u64,
--- a/libs/utils/src/seqwait.rs
+++ b/libs/utils/src/seqwait.rs
@@ -9,7 +9,7 @@ use std::sync::Mutex;
 use std::time::Duration;

 /// An error happened while waiting for a number
-#[derive(Debug, PartialEq, Eq, thiserror::Error)]
+#[derive(Debug, PartialEq, thiserror::Error)]
 #[error("SeqWaitError")]
 pub enum SeqWaitError {
    /// The wait timeout was reached
--- a/libs/utils/tests/bin_ser_test.rs
+++ b/libs/utils/tests/bin_ser_test.rs
@@ -4,7 +4,7 @@ use serde::Deserialize;
 use std::io::Read;
 use utils::bin_ser::LeSer;

-#[derive(Debug, PartialEq, Eq, Deserialize)]
+#[derive(Debug, PartialEq, Deserialize)]
 pub struct HeaderData {
    magic: u16,
    info: u16,
--- a/libs/utils/tests/ssl_test.rs
+++ b/libs/utils/tests/ssl_test.rs
@@ -30,9 +30,6 @@ static CERT: Lazy<rustls::Certificate> = Lazy::new(|| {
 });

 #[test]
-// [false-positive](https://github.com/rust-lang/rust-clippy/issues/9274),
-// we resize the vector so doing some modifications after all
-#[allow(clippy::read_zero_byte_vec)]
 fn ssl() {
    let (mut client_sock, server_sock) = make_tcp_pair();

--- a/neon_local/src/main.rs
+++ b/neon_local/src/main.rs
@@ -501,10 +501,10 @@ fn handle_init(init_match: &ArgMatches) -> anyhow::Result<LocalEnv> {
    // default_tenantid was generated by the `env.init()` call above
    let initial_tenant_id = env.default_tenant_id.unwrap();

-    // Initialize pageserver, create initial tenant and timeline.
+    // Call 'pageserver init'.
    let pageserver = PageServerNode::from_env(&env);
    let initial_timeline_id = pageserver
-        .initialize(
+        .init(
            Some(initial_tenant_id),
            initial_timeline_id_arg,
            &pageserver_config_overrides(init_match),
@@ -551,15 +551,25 @@ fn handle_tenant(tenant_match: &ArgMatches, env: &mut local_env::LocalEnv) -> an
                .values_of("config")
                .map(|vals| vals.flat_map(|c| c.split_once(':')).collect())
                .unwrap_or_default();
-            let new_tenant_id = pageserver.tenant_create(initial_tenant_id, tenant_conf)?;
-            println!("tenant {new_tenant_id} successfully created on the pageserver");
+            let new_tenant_id = pageserver
+                .tenant_create(initial_tenant_id, tenant_conf)?
+                .ok_or_else(|| {
+                    anyhow!("Tenant with id {:?} was already created", initial_tenant_id)
+                })?;
+            println!(
+                "tenant {} successfully created on the pageserver",
+                new_tenant_id
+            );

            // Create an initial timeline for the new tenant
            let new_timeline_id = parse_timeline_id(create_match)?;
-            let timeline_info =
-                pageserver.timeline_create(new_tenant_id, new_timeline_id, None, None)?;
-            let new_timeline_id = timeline_info.timeline_id;
-            let last_record_lsn = timeline_info
+            let timeline = pageserver
+                .timeline_create(new_tenant_id, new_timeline_id, None, None)?
+                .context(format!(
+                    "Failed to create initial timeline for tenant {new_tenant_id}"
+                ))?;
+            let new_timeline_id = timeline.timeline_id;
+            let last_record_lsn = timeline
                .local
                .context(format!("Failed to get last record LSN: no local timeline info for timeline {new_timeline_id}"))?
                .last_record_lsn;
@@ -606,18 +616,20 @@ fn handle_timeline(timeline_match: &ArgMatches, env: &mut local_env::LocalEnv) -
            let new_branch_name = create_match
                .value_of("branch-name")
                .ok_or_else(|| anyhow!("No branch name provided"))?;
-            let timeline_info = pageserver.timeline_create(tenant_id, None, None, None)?;
-            let new_timeline_id = timeline_info.timeline_id;
+            let timeline = pageserver
+                .timeline_create(tenant_id, None, None, None)?
+                .ok_or_else(|| anyhow!("Failed to create new timeline for tenant {}", tenant_id))?;
+            let new_timeline_id = timeline.timeline_id;

-            let last_record_lsn = timeline_info
+            let last_record_lsn = timeline
                .local
                .expect("no local timeline info")
                .last_record_lsn;
            env.register_branch_mapping(new_branch_name.to_string(), tenant_id, new_timeline_id)?;

            println!(
-                "Created timeline '{}' at Lsn {last_record_lsn} for tenant: {tenant_id}",
-                timeline_info.timeline_id
+                "Created timeline '{}' at Lsn {} for tenant: {}",
+                timeline.timeline_id, last_record_lsn, tenant_id,
            );
        }
        Some(("import", import_match)) => {
@@ -668,7 +680,10 @@ fn handle_timeline(timeline_match: &ArgMatches, env: &mut local_env::LocalEnv) -
            let ancestor_timeline_id = env
                .get_branch_timeline_id(ancestor_branch_name, tenant_id)
                .ok_or_else(|| {
-                    anyhow!("Found no timeline id for branch name '{ancestor_branch_name}'")
+                    anyhow!(
+                        "Found no timeline id for branch name '{}'",
+                        ancestor_branch_name
+                    )
                })?;

            let start_lsn = branch_match
@@ -676,15 +691,12 @@ fn handle_timeline(timeline_match: &ArgMatches, env: &mut local_env::LocalEnv) -
                .map(Lsn::from_str)
                .transpose()
                .context("Failed to parse ancestor start Lsn from the request")?;
-            let timeline_info = pageserver.timeline_create(
-                tenant_id,
-                None,
-                start_lsn,
-                Some(ancestor_timeline_id),
-            )?;
-            let new_timeline_id = timeline_info.timeline_id;
+            let timeline = pageserver
+                .timeline_create(tenant_id, None, start_lsn, Some(ancestor_timeline_id))?
+                .ok_or_else(|| anyhow!("Failed to create new timeline for tenant {}", tenant_id))?;
+            let new_timeline_id = timeline.timeline_id;

-            let last_record_lsn = timeline_info
+            let last_record_lsn = timeline
                .local
                .expect("no local timeline info")
                .last_record_lsn;
@@ -692,11 +704,11 @@ fn handle_timeline(timeline_match: &ArgMatches, env: &mut local_env::LocalEnv) -
            env.register_branch_mapping(new_branch_name.to_string(), tenant_id, new_timeline_id)?;

            println!(
-                "Created timeline '{}' at Lsn {last_record_lsn} for tenant: {tenant_id}. Ancestor timeline: '{ancestor_branch_name}'",
-                timeline_info.timeline_id
+                "Created timeline '{}' at Lsn {} for tenant: {}. Ancestor timeline: '{}'",
+                timeline.timeline_id, last_record_lsn, tenant_id, ancestor_branch_name,
            );
        }
-        Some((sub_name, _)) => bail!("Unexpected tenant subcommand '{sub_name}'"),
+        Some((sub_name, _)) => bail!("Unexpected tenant subcommand '{}'", sub_name),
        None => bail!("no tenant subcommand provided"),
    }

--- a/pageserver/src/basebackup.rs
+++ b/pageserver/src/basebackup.rs
@@ -24,13 +24,8 @@ use tracing::*;

 use crate::reltag::{RelTag, SlruKind};
 use crate::DatadirTimeline;
-
-use postgres_ffi::v14::pg_constants;
-use postgres_ffi::v14::xlog_utils::{generate_wal_segment, normalize_lsn, XLogFileName};
-use postgres_ffi::v14::{CheckPoint, ControlFileData};
-use postgres_ffi::TransactionId;
-use postgres_ffi::PG_TLI;
-use postgres_ffi::{BLCKSZ, RELSEG_SIZE};
+use postgres_ffi::xlog_utils::*;
+use postgres_ffi::*;
 use utils::lsn::Lsn;

 /// This is short-living object only for the time of tarball creation,
@@ -205,7 +200,7 @@ where
        }

        // Add a file for each chunk of blocks (aka segment)
-        let chunks = (0..nblocks).chunks(RELSEG_SIZE as usize);
+        let chunks = (0..nblocks).chunks(pg_constants::RELSEG_SIZE as usize);
        for (seg, blocks) in chunks.into_iter().enumerate() {
            let mut segment_data: Vec<u8> = vec![];
            for blknum in blocks {
@@ -225,19 +220,23 @@ where
    fn add_slru_segment(&mut self, slru: SlruKind, segno: u32) -> anyhow::Result<()> {
        let nblocks = self.timeline.get_slru_segment_size(slru, segno, self.lsn)?;

-        let mut slru_buf: Vec<u8> = Vec::with_capacity(nblocks as usize * BLCKSZ as usize);
+        let mut slru_buf: Vec<u8> =
+            Vec::with_capacity(nblocks as usize * pg_constants::BLCKSZ as usize);
        for blknum in 0..nblocks {
            let img = self
                .timeline
                .get_slru_page_at_lsn(slru, segno, blknum, self.lsn)?;

            if slru == SlruKind::Clog {
-                ensure!(img.len() == BLCKSZ as usize || img.len() == BLCKSZ as usize + 8);
+                ensure!(
+                    img.len() == pg_constants::BLCKSZ as usize
+                        || img.len() == pg_constants::BLCKSZ as usize + 8
+                );
            } else {
-                ensure!(img.len() == BLCKSZ as usize);
+                ensure!(img.len() == pg_constants::BLCKSZ as usize);
            }

-            slru_buf.extend_from_slice(&img[..BLCKSZ as usize]);
+            slru_buf.extend_from_slice(&img[..pg_constants::BLCKSZ as usize]);
        }

        let segname = format!("{}/{:>04X}", slru.to_str(), segno);
--- a/pageserver/src/bin/pageserver.rs
+++ b/pageserver/src/bin/pageserver.rs
@@ -1,6 +1,6 @@
 //! Main entry point for the Page Server executable.

-use std::{env, ops::ControlFlow, path::Path, str::FromStr};
+use std::{env, path::Path, str::FromStr};
 use tracing::*;

 use anyhow::{bail, Context, Result};
@@ -13,7 +13,7 @@ use pageserver::{
    config::{defaults::*, PageServerConf},
    http, page_cache, page_service, profiling, tenant_mgr, thread_mgr,
    thread_mgr::ThreadKind,
-    virtual_file, LOG_FILE_NAME,
+    timelines, virtual_file, LOG_FILE_NAME,
 };
 use utils::{
    auth::JwtAuth,
@@ -24,6 +24,7 @@ use utils::{
    shutdown::exit_now,
    signals::{self, Signal},
    tcp_listener,
+    zid::{ZTenantId, ZTimelineId},
 };

 project_git_version!(GIT_VERSION);
@@ -41,7 +42,6 @@ fn main() -> anyhow::Result<()> {
        .about("Materializes WAL stream to pages and serves them to the postgres")
        .version(&*version())
        .arg(
-
            Arg::new("daemonize")
                .short('d')
                .long("daemonize")
@@ -52,7 +52,7 @@ fn main() -> anyhow::Result<()> {
            Arg::new("init")
                .long("init")
                .takes_value(false)
-                .help("Initialize pageserver with all given config overrides"),
+                .help("Initialize pageserver service: creates an initial config, tenant and timeline, if specified"),
        )
        .arg(
            Arg::new("workdir")
@@ -61,6 +61,20 @@ fn main() -> anyhow::Result<()> {
                .takes_value(true)
                .help("Working directory for the pageserver"),
        )
+        .arg(
+            Arg::new("create-tenant")
+                .long("create-tenant")
+                .takes_value(true)
+                .help("Create tenant during init")
+                .requires("init"),
+        )
+        .arg(
+            Arg::new("initial-timeline-id")
+                .long("initial-timeline-id")
+                .takes_value(true)
+                .help("Use a specific timeline id during init and tenant creation")
+                .requires("create-tenant"),
+        )
        // See `settings.md` for more details on the extra configuration patameters pageserver can process
        .arg(
            Arg::new("config-override")
@@ -71,9 +85,6 @@ fn main() -> anyhow::Result<()> {
                .help("Additional configuration overrides of the ones from the toml config file (or new ones to add there).
                Any option has to be a valid toml document, example: `-c=\"foo='hey'\"` `-c=\"foo={value=1}\"`"),
        )
-        .arg(Arg::new("update-config").long("update-config").takes_value(false).help(
-            "Update the config file when started",
-        ))
        .arg(
            Arg::new("enabled-features")
                .long("enabled-features")
@@ -99,6 +110,18 @@ fn main() -> anyhow::Result<()> {
        .with_context(|| format!("Error opening workdir '{}'", workdir.display()))?;
    let cfg_file_path = workdir.join("pageserver.toml");

+    let init = arg_matches.is_present("init");
+    let create_tenant = arg_matches
+        .value_of("create-tenant")
+        .map(ZTenantId::from_str)
+        .transpose()
+        .context("Failed to parse tenant id from the arguments")?;
+    let initial_timeline_id = arg_matches
+        .value_of("initial-timeline-id")
+        .map(ZTimelineId::from_str)
+        .transpose()
+        .context("Failed to parse timeline id from the arguments")?;
+
    // Set CWD to workdir for non-daemon modes
    env::set_current_dir(&workdir).with_context(|| {
        format!(
@@ -108,86 +131,30 @@ fn main() -> anyhow::Result<()> {
    })?;

    let daemonize = arg_matches.is_present("daemonize");
-
-    let conf = match initialize_config(&cfg_file_path, arg_matches, &workdir)? {
-        ControlFlow::Continue(conf) => conf,
-        ControlFlow::Break(()) => {
-            info!("Pageserver config init successful");
-            return Ok(());
-        }
-    };
-
-    let tenants_path = conf.tenants_path();
-    if !tenants_path.exists() {
-        utils::crashsafe_dir::create_dir_all(conf.tenants_path()).with_context(|| {
-            format!(
-                "Failed to create tenants root dir at '{}'",
-                tenants_path.display()
-            )
-        })?;
+    if init && daemonize {
+        bail!("--daemonize cannot be used with --init")
    }

-    // Initialize up failpoints support
-    let scenario = FailScenario::setup();
-
-    // Basic initialization of things that don't change after startup
-    virtual_file::init(conf.max_file_descriptors);
-    page_cache::init(conf.page_cache_size);
-
-    start_pageserver(conf, daemonize).context("Failed to start pageserver")?;
-
-    scenario.teardown();
-    Ok(())
-}
-
-fn initialize_config(
-    cfg_file_path: &Path,
-    arg_matches: clap::ArgMatches,
-    workdir: &Path,
-) -> anyhow::Result<ControlFlow<(), &'static PageServerConf>> {
-    let init = arg_matches.is_present("init");
-    let update_config = init || arg_matches.is_present("update-config");
-
-    let (mut toml, config_file_exists) = if cfg_file_path.is_file() {
-        if init {
-            anyhow::bail!(
-                "Config file '{}' already exists, cannot init it, use --update-config to update it",
-                cfg_file_path.display()
-            );
-        }
-        // Supplement the CLI arguments with the config file
-        let cfg_file_contents = std::fs::read_to_string(&cfg_file_path).with_context(|| {
-            format!(
-                "Failed to read pageserver config at '{}'",
-                cfg_file_path.display()
-            )
-        })?;
-        (
-            cfg_file_contents
-                .parse::<toml_edit::Document>()
-                .with_context(|| {
-                    format!(
-                        "Failed to parse '{}' as pageserver config",
-                        cfg_file_path.display()
-                    )
-                })?,
-            true,
-        )
-    } else if cfg_file_path.exists() {
-        anyhow::bail!(
-            "Config file '{}' exists but is not a regular file",
-            cfg_file_path.display()
-        );
-    } else {
+    let mut toml = if init {
        // We're initializing the repo, so there's no config file yet
-        (
-            DEFAULT_CONFIG_FILE
-                .parse::<toml_edit::Document>()
-                .context("could not parse built-in config file")?,
-            false,
-        )
+        DEFAULT_CONFIG_FILE
+            .parse::<toml_edit::Document>()
+            .context("could not parse built-in config file")?
+    } else {
+        // Supplement the CLI arguments with the config file
+        let cfg_file_contents = std::fs::read_to_string(&cfg_file_path)
+            .with_context(|| format!("No pageserver config at '{}'", cfg_file_path.display()))?;
+        cfg_file_contents
+            .parse::<toml_edit::Document>()
+            .with_context(|| {
+                format!(
+                    "Failed to read '{}' as pageserver config",
+                    cfg_file_path.display()
+                )
+            })?
    };

+    // Process any extra options given with -c
    if let Some(values) = arg_matches.values_of("config-override") {
        for option_line in values {
            let doc = toml_edit::Document::from_str(option_line).with_context(|| {
@@ -198,38 +165,49 @@ fn initialize_config(
            })?;

            for (key, item) in doc.iter() {
-                if config_file_exists && update_config && key == "id" && toml.contains_key(key) {
-                    anyhow::bail!("Pageserver config file exists at '{}' and has node id already, it cannot be overridden", cfg_file_path.display());
+                if key == "id" {
+                    anyhow::ensure!(
+                        init,
+                        "node id can only be set during pageserver init and cannot be overridden"
+                    );
                }
                toml.insert(key, item.clone());
            }
        }
    }
-
-    debug!("Resulting toml: {toml}");
-    let conf = PageServerConf::parse_and_validate(&toml, workdir)
+    trace!("Resulting toml: {}", toml);
+    let conf = PageServerConf::parse_and_validate(&toml, &workdir)
        .context("Failed to parse pageserver configuration")?;

-    if update_config {
-        info!("Writing pageserver config to '{}'", cfg_file_path.display());
+    // The configuration is all set up now. Turn it into a 'static
+    // that can be freely stored in structs and passed across threads
+    // as a ref.
+    let conf: &'static PageServerConf = Box::leak(Box::new(conf));

+    // Initialize up failpoints support
+    let scenario = FailScenario::setup();
+
+    // Basic initialization of things that don't change after startup
+    virtual_file::init(conf.max_file_descriptors);
+    page_cache::init(conf.page_cache_size);
+
+    // Create repo and exit if init was requested
+    if init {
+        timelines::init_pageserver(conf, create_tenant, initial_timeline_id)
+            .context("Failed to init pageserver")?;
+        // write the config file
        std::fs::write(&cfg_file_path, toml.to_string()).with_context(|| {
            format!(
-                "Failed to write pageserver config to '{}'",
+                "Failed to initialize pageserver config at '{}'",
                cfg_file_path.display()
            )
        })?;
-        info!(
-            "Config successfully written to '{}'",
-            cfg_file_path.display()
-        )
+    } else {
+        start_pageserver(conf, daemonize).context("Failed to start pageserver")?;
    }

-    Ok(if init {
-        ControlFlow::Break(())
-    } else {
-        ControlFlow::Continue(Box::leak(Box::new(conf)))
-    })
+    scenario.teardown();
+    Ok(())
 }

 fn start_pageserver(conf: &'static PageServerConf, daemonize: bool) -> Result<()> {
--- a/pageserver/src/http/routes.rs
+++ b/pageserver/src/http/routes.rs
@@ -11,13 +11,14 @@ use super::models::{
    StatusResponse, TenantConfigRequest, TenantCreateRequest, TenantCreateResponse, TenantInfo,
    TimelineCreateRequest,
 };
-use crate::layered_repository::{metadata::TimelineMetadata, LayeredTimeline};
+use crate::layered_repository::metadata::TimelineMetadata;
 use crate::pgdatadir_mapping::DatadirTimeline;
 use crate::repository::{LocalTimelineState, RepositoryTimeline};
 use crate::repository::{Repository, Timeline};
 use crate::storage_sync;
 use crate::storage_sync::index::{RemoteIndex, RemoteTimeline};
 use crate::tenant_config::TenantConfOpt;
+use crate::TimelineImpl;
 use crate::{config::PageServerConf, tenant_mgr, timelines};
 use utils::{
    auth::JwtAuth,
@@ -85,7 +86,7 @@ fn get_config(request: &Request<Body>) -> &'static PageServerConf {
 // Helper functions to construct a LocalTimelineInfo struct for a timeline

 fn local_timeline_info_from_loaded_timeline(
-    timeline: &LayeredTimeline,
+    timeline: &TimelineImpl,
    include_non_incremental_logical_size: bool,
    include_non_incremental_physical_size: bool,
 ) -> anyhow::Result<LocalTimelineInfo> {
@@ -160,13 +161,13 @@ fn local_timeline_info_from_unloaded_timeline(metadata: &TimelineMetadata) -> Lo
 }

 fn local_timeline_info_from_repo_timeline(
-    repo_timeline: &RepositoryTimeline<LayeredTimeline>,
+    repo_timeline: &RepositoryTimeline<TimelineImpl>,
    include_non_incremental_logical_size: bool,
    include_non_incremental_physical_size: bool,
 ) -> anyhow::Result<LocalTimelineInfo> {
    match repo_timeline {
        RepositoryTimeline::Loaded(timeline) => local_timeline_info_from_loaded_timeline(
-            timeline,
+            &*timeline,
            include_non_incremental_logical_size,
            include_non_incremental_physical_size,
        ),
--- a/pageserver/src/import_datadir.rs
+++ b/pageserver/src/import_datadir.rs
@@ -15,24 +15,13 @@ use crate::pgdatadir_mapping::*;
 use crate::reltag::{RelTag, SlruKind};
 use crate::walingest::WalIngest;
 use crate::walrecord::DecodedWALRecord;
-use postgres_ffi::v14::relfile_utils::*;
-use postgres_ffi::v14::waldecoder::*;
-use postgres_ffi::v14::xlog_utils::*;
-use postgres_ffi::v14::{pg_constants, ControlFileData, DBState_DB_SHUTDOWNED};
+use postgres_ffi::relfile_utils::*;
+use postgres_ffi::waldecoder::*;
+use postgres_ffi::xlog_utils::*;
 use postgres_ffi::Oid;
-use postgres_ffi::BLCKSZ;
+use postgres_ffi::{pg_constants, ControlFileData, DBState_DB_SHUTDOWNED};
 use utils::lsn::Lsn;

-// Returns checkpoint LSN from controlfile
-pub fn get_lsn_from_controlfile(path: &Path) -> Result<Lsn> {
-    // Read control file to extract the LSN
-    let controlfile_path = path.join("global").join("pg_control");
-    let controlfile = ControlFileData::decode(&std::fs::read(controlfile_path)?)?;
-    let lsn = controlfile.checkPoint;
-
-    Ok(Lsn(lsn))
-}
-
 ///
 /// Import all relation data pages from local disk into the repository.
 ///
@@ -121,8 +110,8 @@ fn import_rel<T: DatadirTimeline, Reader: Read>(

    let mut buf: [u8; 8192] = [0u8; 8192];

-    ensure!(len % BLCKSZ as usize == 0);
-    let nblocks = len / BLCKSZ as usize;
+    ensure!(len % pg_constants::BLCKSZ as usize == 0);
+    let nblocks = len / pg_constants::BLCKSZ as usize;

    let rel = RelTag {
        spcnode: spcoid,
@@ -131,7 +120,7 @@ fn import_rel<T: DatadirTimeline, Reader: Read>(
        forknum,
    };

-    let mut blknum: u32 = segno * (1024 * 1024 * 1024 / BLCKSZ as u32);
+    let mut blknum: u32 = segno * (1024 * 1024 * 1024 / pg_constants::BLCKSZ as u32);

    // Call put_rel_creation for every segment of the relation,
    // because there is no guarantee about the order in which we are processing segments.
@@ -155,7 +144,8 @@ fn import_rel<T: DatadirTimeline, Reader: Read>(
            Err(err) => match err.kind() {
                std::io::ErrorKind::UnexpectedEof => {
                    // reached EOF. That's expected.
-                    let relative_blknum = blknum - segno * (1024 * 1024 * 1024 / BLCKSZ as u32);
+                    let relative_blknum =
+                        blknum - segno * (1024 * 1024 * 1024 / pg_constants::BLCKSZ as u32);
                    ensure!(relative_blknum == nblocks as u32, "unexpected EOF");
                    break;
                }
@@ -194,8 +184,8 @@ fn import_slru<T: DatadirTimeline, Reader: Read>(
        .to_string_lossy();
    let segno = u32::from_str_radix(filename, 16)?;

-    ensure!(len % BLCKSZ as usize == 0); // we assume SLRU block size is the same as BLCKSZ
-    let nblocks = len / BLCKSZ as usize;
+    ensure!(len % pg_constants::BLCKSZ as usize == 0); // we assume SLRU block size is the same as BLCKSZ
+    let nblocks = len / pg_constants::BLCKSZ as usize;

    ensure!(nblocks <= pg_constants::SLRU_PAGES_PER_SEGMENT as usize);

--- a/pageserver/src/keyspace.rs
+++ b/pageserver/src/keyspace.rs
@@ -1,5 +1,5 @@
 use crate::repository::{key_range_size, singleton_range, Key};
-use postgres_ffi::BLCKSZ;
+use postgres_ffi::pg_constants;
 use std::ops::Range;

 ///
@@ -19,7 +19,7 @@ impl KeySpace {
    ///
    pub fn partition(&self, target_size: u64) -> KeyPartitioning {
        // Assume that each value is 8k in size.
-        let target_nblocks = (target_size / BLCKSZ as u64) as usize;
+        let target_nblocks = (target_size / pg_constants::BLCKSZ as u64) as usize;

        let mut parts = Vec::new();
        let mut current_part = Vec::new();
--- a/pageserver/src/layered_repository.rs
+++ b/pageserver/src/layered_repository.rs
@@ -59,9 +59,7 @@ mod storage_layer;
 mod timeline;

 use storage_layer::Layer;
-use timeline::LayeredTimelineEntry;
-
-pub use timeline::LayeredTimeline;
+use timeline::{LayeredTimeline, LayeredTimelineEntry};

 // re-export this function so that page_cache.rs can use it.
 pub use crate::layered_repository::ephemeral_file::writeback as writeback_ephemeral_file;
--- a/pageserver/src/layered_repository/block_io.rs
+++ b/pageserver/src/layered_repository/block_io.rs
@@ -157,14 +157,7 @@ where
        // Look up the right page
        let cache = page_cache::get();
        loop {
-            match cache
-                .read_immutable_buf(self.file_id, blknum)
-                .map_err(|e| {
-                    std::io::Error::new(
-                        std::io::ErrorKind::Other,
-                        format!("Failed to read immutable buf: {e:#}"),
-                    )
-                })? {
+            match cache.read_immutable_buf(self.file_id, blknum) {
                ReadBufResult::Found(guard) => break Ok(guard),
                ReadBufResult::NotFound(mut write_guard) => {
                    // Read the page from disk into the buffer
--- a/pageserver/src/layered_repository/disk_btree.rs
+++ b/pageserver/src/layered_repository/disk_btree.rs
@@ -209,7 +209,7 @@ where
    reader: R,
 }

-#[derive(Clone, Copy, Debug, PartialEq, Eq)]
+#[derive(Clone, Copy, Debug, PartialEq)]
 pub enum VisitDirection {
    Forwards,
    Backwards,
--- a/pageserver/src/layered_repository/ephemeral_file.rs
+++ b/pageserver/src/layered_repository/ephemeral_file.rs
@@ -12,7 +12,7 @@ use once_cell::sync::Lazy;
 use std::cmp::min;
 use std::collections::HashMap;
 use std::fs::OpenOptions;
-use std::io::{self, ErrorKind};
+use std::io::{Error, ErrorKind};
 use std::ops::DerefMut;
 use std::path::PathBuf;
 use std::sync::{Arc, RwLock};
@@ -51,7 +51,7 @@ impl EphemeralFile {
        conf: &PageServerConf,
        tenantid: ZTenantId,
        timelineid: ZTimelineId,
-    ) -> Result<EphemeralFile, io::Error> {
+    ) -> Result<EphemeralFile, std::io::Error> {
        let mut l = EPHEMERAL_FILES.write().unwrap();
        let file_id = l.next_file_id;
        l.next_file_id += 1;
@@ -76,7 +76,7 @@ impl EphemeralFile {
        })
    }

-    fn fill_buffer(&self, buf: &mut [u8], blkno: u32) -> Result<(), io::Error> {
+    fn fill_buffer(&self, buf: &mut [u8], blkno: u32) -> Result<(), Error> {
        let mut off = 0;
        while off < PAGE_SZ {
            let n = self
@@ -96,13 +96,10 @@ impl EphemeralFile {
        Ok(())
    }

-    fn get_buf_for_write(&self, blkno: u32) -> Result<page_cache::PageWriteGuard, io::Error> {
+    fn get_buf_for_write(&self, blkno: u32) -> Result<page_cache::PageWriteGuard, Error> {
        // Look up the right page
        let cache = page_cache::get();
-        let mut write_guard = match cache
-            .write_ephemeral_buf(self.file_id, blkno)
-            .map_err(|e| to_io_error(e, "Failed to write ephemeral buf"))?
-        {
+        let mut write_guard = match cache.write_ephemeral_buf(self.file_id, blkno) {
            WriteBufResult::Found(guard) => guard,
            WriteBufResult::NotFound(mut guard) => {
                // Read the page from disk into the buffer
@@ -130,7 +127,7 @@ pub fn is_ephemeral_file(filename: &str) -> bool {
 }

 impl FileExt for EphemeralFile {
-    fn read_at(&self, dstbuf: &mut [u8], offset: u64) -> Result<usize, io::Error> {
+    fn read_at(&self, dstbuf: &mut [u8], offset: u64) -> Result<usize, Error> {
        // Look up the right page
        let blkno = (offset / PAGE_SZ as u64) as u32;
        let off = offset as usize % PAGE_SZ;
@@ -140,10 +137,7 @@ impl FileExt for EphemeralFile {
        let mut write_guard;

        let cache = page_cache::get();
-        let buf = match cache
-            .read_ephemeral_buf(self.file_id, blkno)
-            .map_err(|e| to_io_error(e, "Failed to read ephemeral buf"))?
-        {
+        let buf = match cache.read_ephemeral_buf(self.file_id, blkno) {
            ReadBufResult::Found(guard) => {
                read_guard = guard;
                read_guard.as_ref()
@@ -164,7 +158,7 @@ impl FileExt for EphemeralFile {
        Ok(len)
    }

-    fn write_at(&self, srcbuf: &[u8], offset: u64) -> Result<usize, io::Error> {
+    fn write_at(&self, srcbuf: &[u8], offset: u64) -> Result<usize, Error> {
        // Look up the right page
        let blkno = (offset / PAGE_SZ as u64) as u32;
        let off = offset as usize % PAGE_SZ;
@@ -172,10 +166,7 @@ impl FileExt for EphemeralFile {

        let mut write_guard;
        let cache = page_cache::get();
-        let buf = match cache
-            .write_ephemeral_buf(self.file_id, blkno)
-            .map_err(|e| to_io_error(e, "Failed to write ephemeral buf"))?
-        {
+        let buf = match cache.write_ephemeral_buf(self.file_id, blkno) {
            WriteBufResult::Found(guard) => {
                write_guard = guard;
                write_guard.deref_mut()
@@ -199,7 +190,7 @@ impl FileExt for EphemeralFile {
 }

 impl BlobWriter for EphemeralFile {
-    fn write_blob(&mut self, srcbuf: &[u8]) -> Result<u64, io::Error> {
+    fn write_blob(&mut self, srcbuf: &[u8]) -> Result<u64, Error> {
        let pos = self.size;

        let mut blknum = (self.size / PAGE_SZ as u64) as u32;
@@ -277,11 +268,11 @@ impl Drop for EphemeralFile {
    }
 }

-pub fn writeback(file_id: u64, blkno: u32, buf: &[u8]) -> Result<(), io::Error> {
+pub fn writeback(file_id: u64, blkno: u32, buf: &[u8]) -> Result<(), std::io::Error> {
    if let Some(file) = EPHEMERAL_FILES.read().unwrap().files.get(&file_id) {
        match file.write_all_at(buf, blkno as u64 * PAGE_SZ as u64) {
            Ok(_) => Ok(()),
-            Err(e) => Err(io::Error::new(
+            Err(e) => Err(std::io::Error::new(
                ErrorKind::Other,
                format!(
                    "failed to write back to ephemeral file at {} error: {}",
@@ -291,7 +282,7 @@ pub fn writeback(file_id: u64, blkno: u32, buf: &[u8]) -> Result<(), io::Error>
            )),
        }
    } else {
-        Err(io::Error::new(
+        Err(std::io::Error::new(
            ErrorKind::Other,
            "could not write back page, not found in ephemeral files hash",
        ))
@@ -301,14 +292,11 @@ pub fn writeback(file_id: u64, blkno: u32, buf: &[u8]) -> Result<(), io::Error>
 impl BlockReader for EphemeralFile {
    type BlockLease = page_cache::PageReadGuard<'static>;

-    fn read_blk(&self, blknum: u32) -> Result<Self::BlockLease, io::Error> {
+    fn read_blk(&self, blknum: u32) -> Result<Self::BlockLease, std::io::Error> {
        // Look up the right page
        let cache = page_cache::get();
        loop {
-            match cache
-                .read_ephemeral_buf(self.file_id, blknum)
-                .map_err(|e| to_io_error(e, "Failed to read ephemeral buf"))?
-            {
+            match cache.read_ephemeral_buf(self.file_id, blknum) {
                ReadBufResult::Found(guard) => return Ok(guard),
                ReadBufResult::NotFound(mut write_guard) => {
                    // Read the page from disk into the buffer
@@ -323,10 +311,6 @@ impl BlockReader for EphemeralFile {
    }
 }

-fn to_io_error(e: anyhow::Error, context: &str) -> io::Error {
-    io::Error::new(ErrorKind::Other, format!("{context}: {e:#}"))
-}
-
 #[cfg(test)]
 mod tests {
    use super::*;
@@ -338,7 +322,7 @@ mod tests {

    fn repo_harness(
        test_name: &str,
-    ) -> Result<(&'static PageServerConf, ZTenantId, ZTimelineId), io::Error> {
+    ) -> Result<(&'static PageServerConf, ZTenantId, ZTimelineId), Error> {
        let repo_dir = PageServerConf::test_repo_dir(test_name);
        let _ = fs::remove_dir_all(&repo_dir);
        let conf = PageServerConf::dummy_conf(repo_dir);
@@ -355,7 +339,7 @@ mod tests {

    // Helper function to slurp contents of a file, starting at the current position,
    // into a string
-    fn read_string(efile: &EphemeralFile, offset: u64, len: usize) -> Result<String, io::Error> {
+    fn read_string(efile: &EphemeralFile, offset: u64, len: usize) -> Result<String, Error> {
        let mut buf = Vec::new();
        buf.resize(len, 0u8);

@@ -367,7 +351,7 @@ mod tests {
    }

    #[test]
-    fn test_ephemeral_files() -> Result<(), io::Error> {
+    fn test_ephemeral_files() -> Result<(), Error> {
        let (conf, tenantid, timelineid) = repo_harness("ephemeral_files")?;

        let file_a = EphemeralFile::create(conf, tenantid, timelineid)?;
@@ -398,7 +382,7 @@ mod tests {
    }

    #[test]
-    fn test_ephemeral_blobs() -> Result<(), io::Error> {
+    fn test_ephemeral_blobs() -> Result<(), Error> {
        let (conf, tenantid, timelineid) = repo_harness("ephemeral_blobs")?;

        let mut file = EphemeralFile::create(conf, tenantid, timelineid)?;
--- a/pageserver/src/layered_repository/timeline.rs
+++ b/pageserver/src/layered_repository/timeline.rs
@@ -4,7 +4,6 @@ use anyhow::{anyhow, bail, ensure, Context, Result};
 use bytes::Bytes;
 use fail::fail_point;
 use itertools::Itertools;
-use metrics::core::{AtomicU64, GenericCounter};
 use once_cell::sync::Lazy;
 use tracing::*;

@@ -45,7 +44,7 @@ use crate::reltag::RelTag;
 use crate::tenant_config::TenantConfOpt;
 use crate::DatadirTimeline;

-use postgres_ffi::v14::xlog_utils::to_pg_timestamp;
+use postgres_ffi::xlog_utils::to_pg_timestamp;
 use utils::{
    lsn::{AtomicLsn, Lsn, RecordLsn},
    seqwait::SeqWait,
@@ -224,70 +223,6 @@ impl From<LayeredTimelineEntry> for RepositoryTimeline<LayeredTimeline> {
    }
 }

-struct TimelineMetrics {
-    pub reconstruct_time_histo: Histogram,
-    pub materialized_page_cache_hit_counter: GenericCounter<AtomicU64>,
-    pub flush_time_histo: Histogram,
-    pub compact_time_histo: Histogram,
-    pub create_images_time_histo: Histogram,
-    pub init_logical_size_histo: Histogram,
-    pub load_layer_map_histo: Histogram,
-    pub last_record_gauge: IntGauge,
-    pub wait_lsn_time_histo: Histogram,
-    pub current_physical_size_gauge: UIntGauge,
-}
-
-impl TimelineMetrics {
-    fn new(tenant_id: &ZTenantId, timeline_id: &ZTimelineId) -> Self {
-        let tenant_id = tenant_id.to_string();
-        let timeline_id = timeline_id.to_string();
-
-        let reconstruct_time_histo = RECONSTRUCT_TIME
-            .get_metric_with_label_values(&[&tenant_id, &timeline_id])
-            .unwrap();
-        let materialized_page_cache_hit_counter = MATERIALIZED_PAGE_CACHE_HIT
-            .get_metric_with_label_values(&[&tenant_id, &timeline_id])
-            .unwrap();
-        let flush_time_histo = STORAGE_TIME
-            .get_metric_with_label_values(&["layer flush", &tenant_id, &timeline_id])
-            .unwrap();
-        let compact_time_histo = STORAGE_TIME
-            .get_metric_with_label_values(&["compact", &tenant_id, &timeline_id])
-            .unwrap();
-        let create_images_time_histo = STORAGE_TIME
-            .get_metric_with_label_values(&["create images", &tenant_id, &timeline_id])
-            .unwrap();
-        let init_logical_size_histo = STORAGE_TIME
-            .get_metric_with_label_values(&["init logical size", &tenant_id, &timeline_id])
-            .unwrap();
-        let load_layer_map_histo = STORAGE_TIME
-            .get_metric_with_label_values(&["load layer map", &tenant_id, &timeline_id])
-            .unwrap();
-        let last_record_gauge = LAST_RECORD_LSN
-            .get_metric_with_label_values(&[&tenant_id, &timeline_id])
-            .unwrap();
-        let wait_lsn_time_histo = WAIT_LSN_TIME
-            .get_metric_with_label_values(&[&tenant_id, &timeline_id])
-            .unwrap();
-        let current_physical_size_gauge = CURRENT_PHYSICAL_SIZE
-            .get_metric_with_label_values(&[&tenant_id, &timeline_id])
-            .unwrap();
-
-        TimelineMetrics {
-            reconstruct_time_histo,
-            materialized_page_cache_hit_counter,
-            flush_time_histo,
-            compact_time_histo,
-            create_images_time_histo,
-            init_logical_size_histo,
-            load_layer_map_histo,
-            last_record_gauge,
-            wait_lsn_time_histo,
-            current_physical_size_gauge,
-        }
-    }
-}
-
 pub struct LayeredTimeline {
    conf: &'static PageServerConf,
    tenant_conf: Arc<RwLock<TenantConfOpt>>,
@@ -334,7 +269,14 @@ pub struct LayeredTimeline {
    ancestor_lsn: Lsn,

    // Metrics
-    metrics: TimelineMetrics,
+    reconstruct_time_histo: Histogram,
+    materialized_page_cache_hit_counter: IntCounter,
+    flush_time_histo: Histogram,
+    compact_time_histo: Histogram,
+    create_images_time_histo: Histogram,
+    last_record_gauge: IntGauge,
+    wait_lsn_time_histo: Histogram,
+    current_physical_size_gauge: UIntGauge,

    /// If `true`, will backup its files that appear after each checkpointing to the remote storage.
    upload_layers: AtomicBool,
@@ -484,7 +426,7 @@ impl Timeline for LayeredTimeline {
            "wait_lsn called by WAL receiver thread"
        );

-        self.metrics.wait_lsn_time_histo.observe_closure_duration(
+        self.wait_lsn_time_histo.observe_closure_duration(
            || self.last_record_lsn
                .wait_for_timeout(lsn, self.conf.wait_lsn_timeout)
                .with_context(|| {
@@ -526,8 +468,7 @@ impl Timeline for LayeredTimeline {

        self.get_reconstruct_data(key, lsn, &mut reconstruct_state)?;

-        self.metrics
-            .reconstruct_time_histo
+        self.reconstruct_time_histo
            .observe_closure_duration(|| self.reconstruct_value(key, lsn, reconstruct_state))
    }

@@ -589,7 +530,7 @@ impl Timeline for LayeredTimeline {
    }

    fn get_physical_size(&self) -> u64 {
-        self.metrics.current_physical_size_gauge.get()
+        self.current_physical_size_gauge.get()
    }

    fn get_physical_size_non_incremental(&self) -> anyhow::Result<u64> {
@@ -663,6 +604,43 @@ impl LayeredTimeline {
        walredo_mgr: Arc<dyn WalRedoManager + Send + Sync>,
        upload_layers: bool,
    ) -> LayeredTimeline {
+        let reconstruct_time_histo = RECONSTRUCT_TIME
+            .get_metric_with_label_values(&[&tenant_id.to_string(), &timeline_id.to_string()])
+            .unwrap();
+        let materialized_page_cache_hit_counter = MATERIALIZED_PAGE_CACHE_HIT
+            .get_metric_with_label_values(&[&tenant_id.to_string(), &timeline_id.to_string()])
+            .unwrap();
+        let flush_time_histo = STORAGE_TIME
+            .get_metric_with_label_values(&[
+                "layer flush",
+                &tenant_id.to_string(),
+                &timeline_id.to_string(),
+            ])
+            .unwrap();
+        let compact_time_histo = STORAGE_TIME
+            .get_metric_with_label_values(&[
+                "compact",
+                &tenant_id.to_string(),
+                &timeline_id.to_string(),
+            ])
+            .unwrap();
+        let create_images_time_histo = STORAGE_TIME
+            .get_metric_with_label_values(&[
+                "create images",
+                &tenant_id.to_string(),
+                &timeline_id.to_string(),
+            ])
+            .unwrap();
+        let last_record_gauge = LAST_RECORD_LSN
+            .get_metric_with_label_values(&[&tenant_id.to_string(), &timeline_id.to_string()])
+            .unwrap();
+        let wait_lsn_time_histo = WAIT_LSN_TIME
+            .get_metric_with_label_values(&[&tenant_id.to_string(), &timeline_id.to_string()])
+            .unwrap();
+        let current_physical_size_gauge = CURRENT_PHYSICAL_SIZE
+            .get_metric_with_label_values(&[&tenant_id.to_string(), &timeline_id.to_string()])
+            .unwrap();
+
        let mut result = LayeredTimeline {
            conf,
            tenant_conf,
@@ -685,7 +663,14 @@ impl LayeredTimeline {
            ancestor_timeline: ancestor,
            ancestor_lsn: metadata.ancestor_lsn(),

-            metrics: TimelineMetrics::new(&tenant_id, &timeline_id),
+            reconstruct_time_histo,
+            materialized_page_cache_hit_counter,
+            flush_time_histo,
+            compact_time_histo,
+            create_images_time_histo,
+            last_record_gauge,
+            wait_lsn_time_histo,
+            current_physical_size_gauge,

            upload_layers: AtomicBool::new(upload_layers),

@@ -721,8 +706,6 @@ impl LayeredTimeline {
        let mut layers = self.layers.write().unwrap();
        let mut num_layers = 0;

-        let timer = self.metrics.load_layer_map_histo.start_timer();
-
        // Scan timeline directory and create ImageFileName and DeltaFilename
        // structs representing all files on disk
        let timeline_path = self.conf.timeline_path(&self.timeline_id, &self.tenant_id);
@@ -794,11 +777,7 @@ impl LayeredTimeline {
            "loaded layer map with {} layers at {}, total physical size: {}",
            num_layers, disk_consistent_lsn, total_physical_size
        );
-        self.metrics
-            .current_physical_size_gauge
-            .set(total_physical_size);
-
-        timer.stop_and_record();
+        self.current_physical_size_gauge.set(total_physical_size);

        Ok(())
    }
@@ -829,16 +808,12 @@ impl LayeredTimeline {
            }
        }

-        let timer = self.metrics.init_logical_size_histo.start_timer();
-
        // Have to calculate it the hard way
        let last_lsn = self.get_last_record_lsn();
        let logical_size = self.get_current_logical_size_non_incremental(last_lsn)?;
        self.current_logical_size
            .store(logical_size as isize, AtomicOrdering::SeqCst);
        debug!("calculated logical size the hard way: {}", logical_size);
-
-        timer.stop_and_record();
        Ok(())
    }

@@ -903,7 +878,7 @@ impl LayeredTimeline {
                ValueReconstructResult::Continue => {
                    // If we reached an earlier cached page image, we're done.
                    if cont_lsn == cached_lsn + 1 {
-                        self.metrics.materialized_page_cache_hit_counter.inc_by(1);
+                        self.materialized_page_cache_hit_counter.inc_by(1);
                        return Ok(());
                    }
                    if prev_lsn <= cont_lsn {
@@ -1099,7 +1074,7 @@ impl LayeredTimeline {
    fn finish_write(&self, new_lsn: Lsn) {
        assert!(new_lsn.is_aligned());

-        self.metrics.last_record_gauge.set(new_lsn.0 as i64);
+        self.last_record_gauge.set(new_lsn.0 as i64);
        self.last_record_lsn.advance(new_lsn);
    }

@@ -1203,7 +1178,7 @@ impl LayeredTimeline {
            }
        };

-        let timer = self.metrics.flush_time_histo.start_timer();
+        let timer = self.flush_time_histo.start_timer();

        loop {
            let layers = self.layers.read().unwrap();
@@ -1374,7 +1349,7 @@ impl LayeredTimeline {

        // update the timeline's physical size
        let sz = new_delta_path.metadata()?.len();
-        self.metrics.current_physical_size_gauge.add(sz);
+        self.current_physical_size_gauge.add(sz);
        // update metrics
        NUM_PERSISTENT_FILES_CREATED.inc_by(1);
        PERSISTENT_BYTES_WRITTEN.inc_by(sz);
@@ -1443,7 +1418,7 @@ impl LayeredTimeline {
                }

                // 3. Compact
-                let timer = self.metrics.compact_time_histo.start_timer();
+                let timer = self.compact_time_histo.start_timer();
                self.compact_level0(target_file_size)?;
                timer.stop_and_record();
            }
@@ -1519,7 +1494,7 @@ impl LayeredTimeline {
        lsn: Lsn,
        force: bool,
    ) -> Result<HashSet<PathBuf>> {
-        let timer = self.metrics.create_images_time_histo.start_timer();
+        let timer = self.create_images_time_histo.start_timer();
        let mut image_layers: Vec<ImageLayer> = Vec::new();
        let mut layer_paths_to_upload = HashSet::new();
        for partition in partitioning.parts.iter() {
@@ -1563,8 +1538,7 @@ impl LayeredTimeline {

        let mut layers = self.layers.write().unwrap();
        for l in image_layers {
-            self.metrics
-                .current_physical_size_gauge
+            self.current_physical_size_gauge
                .add(l.path().metadata()?.len());
            layers.insert_historic(Arc::new(l));
        }
@@ -1814,8 +1788,7 @@ impl LayeredTimeline {
            let new_delta_path = l.path();

            // update the timeline's physical size
-            self.metrics
-                .current_physical_size_gauge
+            self.current_physical_size_gauge
                .add(new_delta_path.metadata()?.len());

            new_layer_paths.insert(new_delta_path);
@@ -1828,9 +1801,7 @@ impl LayeredTimeline {
        drop(all_keys_iter);
        for l in deltas_to_compact {
            if let Some(path) = l.local_path() {
-                self.metrics
-                    .current_physical_size_gauge
-                    .sub(path.metadata()?.len());
+                self.current_physical_size_gauge.sub(path.metadata()?.len());
                layer_paths_do_delete.insert(path);
            }
            l.delete()?;
@@ -2087,9 +2058,7 @@ impl LayeredTimeline {
        let mut layer_paths_to_delete = HashSet::with_capacity(layers_to_remove.len());
        for doomed_layer in layers_to_remove {
            if let Some(path) = doomed_layer.local_path() {
-                self.metrics
-                    .current_physical_size_gauge
-                    .sub(path.metadata()?.len());
+                self.current_physical_size_gauge.sub(path.metadata()?.len());
                layer_paths_to_delete.insert(path);
            }
            doomed_layer.delete()?;
@@ -2117,7 +2086,7 @@ impl LayeredTimeline {
        key: Key,
        request_lsn: Lsn,
        mut data: ValueReconstructState,
-    ) -> anyhow::Result<Bytes> {
+    ) -> Result<Bytes> {
        // Perform WAL redo if needed
        data.records.reverse();

@@ -2167,15 +2136,13 @@ impl LayeredTimeline {

                if img.len() == page_cache::PAGE_SZ {
                    let cache = page_cache::get();
-                    cache
-                        .memorize_materialized_page(
-                            self.tenant_id,
-                            self.timeline_id,
-                            key,
-                            last_rec_lsn,
-                            &img,
-                        )
-                        .context("Materialized page memoization failed")?;
+                    cache.memorize_materialized_page(
+                        self.tenant_id,
+                        self.timeline_id,
+                        key,
+                        last_rec_lsn,
+                        &img,
+                    );
                }

                Ok(img)
--- a/pageserver/src/lib.rs
+++ b/pageserver/src/lib.rs
@@ -28,6 +28,7 @@ use tracing::info;
 use crate::thread_mgr::ThreadKind;
 use metrics::{register_int_gauge_vec, IntGaugeVec};

+use layered_repository::LayeredRepository;
 use pgdatadir_mapping::DatadirTimeline;

 /// Current storage format version
@@ -61,6 +62,9 @@ pub enum CheckpointConfig {
    Forced,
 }

+pub type RepositoryImpl = LayeredRepository;
+pub type TimelineImpl = <LayeredRepository as repository::Repository>::Timeline;
+
 pub fn shutdown_pageserver(exit_code: i32) {
    // Shut down the libpq endpoint thread. This prevents new connections from
    // being accepted.
--- a/pageserver/src/page_cache.rs
+++ b/pageserver/src/page_cache.rs
@@ -45,7 +45,6 @@ use std::{
    },
 };

-use anyhow::Context;
 use once_cell::sync::OnceCell;
 use tracing::error;
 use utils::{
@@ -84,7 +83,7 @@ pub fn get() -> &'static PageCache {
    }
 }

-pub const PAGE_SZ: usize = postgres_ffi::BLCKSZ as usize;
+pub const PAGE_SZ: usize = postgres_ffi::pg_constants::BLCKSZ as usize;
 const MAX_USAGE_COUNT: u8 = 5;

 ///
@@ -343,7 +342,7 @@ impl PageCache {
        key: Key,
        lsn: Lsn,
        img: &[u8],
-    ) -> anyhow::Result<()> {
+    ) {
        let cache_key = CacheKey::MaterializedPage {
            hash_key: MaterializedPageHashKey {
                tenant_id,
@@ -353,7 +352,7 @@ impl PageCache {
            lsn,
        };

-        match self.lock_for_write(&cache_key)? {
+        match self.lock_for_write(&cache_key) {
            WriteBufResult::Found(write_guard) => {
                // We already had it in cache. Another thread must've put it there
                // concurrently. Check that it had the same contents that we
@@ -365,19 +364,17 @@ impl PageCache {
                write_guard.mark_valid();
            }
        }
-
-        Ok(())
    }

    // Section 1.2: Public interface functions for working with Ephemeral pages.

-    pub fn read_ephemeral_buf(&self, file_id: u64, blkno: u32) -> anyhow::Result<ReadBufResult> {
+    pub fn read_ephemeral_buf(&self, file_id: u64, blkno: u32) -> ReadBufResult {
        let mut cache_key = CacheKey::EphemeralPage { file_id, blkno };

        self.lock_for_read(&mut cache_key)
    }

-    pub fn write_ephemeral_buf(&self, file_id: u64, blkno: u32) -> anyhow::Result<WriteBufResult> {
+    pub fn write_ephemeral_buf(&self, file_id: u64, blkno: u32) -> WriteBufResult {
        let cache_key = CacheKey::EphemeralPage { file_id, blkno };

        self.lock_for_write(&cache_key)
@@ -405,7 +402,7 @@ impl PageCache {

    // Section 1.3: Public interface functions for working with immutable file pages.

-    pub fn read_immutable_buf(&self, file_id: u64, blkno: u32) -> anyhow::Result<ReadBufResult> {
+    pub fn read_immutable_buf(&self, file_id: u64, blkno: u32) -> ReadBufResult {
        let mut cache_key = CacheKey::ImmutableFilePage { file_id, blkno };

        self.lock_for_read(&mut cache_key)
@@ -498,16 +495,15 @@ impl PageCache {
    /// }
    /// ```
    ///
-    fn lock_for_read(&self, cache_key: &mut CacheKey) -> anyhow::Result<ReadBufResult> {
+    fn lock_for_read(&self, cache_key: &mut CacheKey) -> ReadBufResult {
        loop {
            // First check if the key already exists in the cache.
            if let Some(read_guard) = self.try_lock_for_read(cache_key) {
-                return Ok(ReadBufResult::Found(read_guard));
+                return ReadBufResult::Found(read_guard);
            }

            // Not found. Find a victim buffer
-            let (slot_idx, mut inner) =
-                self.find_victim().context("Failed to find evict victim")?;
+            let (slot_idx, mut inner) = self.find_victim();

            // Insert mapping for this. At this point, we may find that another
            // thread did the same thing concurrently. In that case, we evicted
@@ -530,10 +526,10 @@ impl PageCache {
            inner.dirty = false;
            slot.usage_count.store(1, Ordering::Relaxed);

-            return Ok(ReadBufResult::NotFound(PageWriteGuard {
+            return ReadBufResult::NotFound(PageWriteGuard {
                inner,
                valid: false,
-            }));
+            });
        }
    }

@@ -560,16 +556,15 @@ impl PageCache {
    ///
    /// Similar to lock_for_read(), but the returned buffer is write-locked and
    /// may be modified by the caller even if it's already found in the cache.
-    fn lock_for_write(&self, cache_key: &CacheKey) -> anyhow::Result<WriteBufResult> {
+    fn lock_for_write(&self, cache_key: &CacheKey) -> WriteBufResult {
        loop {
            // First check if the key already exists in the cache.
            if let Some(write_guard) = self.try_lock_for_write(cache_key) {
-                return Ok(WriteBufResult::Found(write_guard));
+                return WriteBufResult::Found(write_guard);
            }

            // Not found. Find a victim buffer
-            let (slot_idx, mut inner) =
-                self.find_victim().context("Failed to find evict victim")?;
+            let (slot_idx, mut inner) = self.find_victim();

            // Insert mapping for this. At this point, we may find that another
            // thread did the same thing concurrently. In that case, we evicted
@@ -592,10 +587,10 @@ impl PageCache {
            inner.dirty = false;
            slot.usage_count.store(1, Ordering::Relaxed);

-            return Ok(WriteBufResult::NotFound(PageWriteGuard {
+            return WriteBufResult::NotFound(PageWriteGuard {
                inner,
                valid: false,
-            }));
+            });
        }
    }

@@ -759,7 +754,7 @@ impl PageCache {
    /// Find a slot to evict.
    ///
    /// On return, the slot is empty and write-locked.
-    fn find_victim(&self) -> anyhow::Result<(usize, RwLockWriteGuard<SlotInner>)> {
+    fn find_victim(&self) -> (usize, RwLockWriteGuard<SlotInner>) {
        let iter_limit = self.slots.len() * 10;
        let mut iters = 0;
        loop {
@@ -772,7 +767,7 @@ impl PageCache {
                let mut inner = match slot.inner.try_write() {
                    Ok(inner) => inner,
                    Err(TryLockError::Poisoned(err)) => {
-                        anyhow::bail!("buffer lock was poisoned: {err:?}")
+                        panic!("buffer lock was poisoned: {:?}", err)
                    }
                    Err(TryLockError::WouldBlock) => {
                        // If we have looped through the whole buffer pool 10 times
@@ -782,7 +777,7 @@ impl PageCache {
                        // there are buffers in the pool. In practice, with a reasonably
                        // large buffer pool it really shouldn't happen.
                        if iters > iter_limit {
-                            anyhow::bail!("exceeded evict iter limit");
+                            panic!("could not find a victim buffer to evict");
                        }
                        continue;
                    }
@@ -809,7 +804,7 @@ impl PageCache {
                    inner.dirty = false;
                    inner.key = None;
                }
-                return Ok((slot_idx, inner));
+                return (slot_idx, inner);
            }
        }
    }
--- a/pageserver/src/page_service.rs
+++ b/pageserver/src/page_service.rs
@@ -40,10 +40,9 @@ use crate::thread_mgr;
 use crate::thread_mgr::ThreadKind;
 use crate::CheckpointConfig;
 use metrics::{register_histogram_vec, HistogramVec};
-use postgres_ffi::v14::xlog_utils::to_pg_timestamp;
+use postgres_ffi::xlog_utils::to_pg_timestamp;

-use postgres_ffi::v14::pg_constants::DEFAULTTABLESPACE_OID;
-use postgres_ffi::BLCKSZ;
+use postgres_ffi::pg_constants;

 // Wrapped in libpq CopyData
 enum PagestreamFeMessage {
@@ -726,9 +725,10 @@ impl PageServerHandler {
        let latest_gc_cutoff_lsn = timeline.get_latest_gc_cutoff_lsn();
        let lsn = Self::wait_or_get_last_lsn(timeline, req.lsn, req.latest, &latest_gc_cutoff_lsn)?;

-        let total_blocks = timeline.get_db_size(DEFAULTTABLESPACE_OID, req.dbnode, lsn)?;
+        let total_blocks =
+            timeline.get_db_size(pg_constants::DEFAULTTABLESPACE_OID, req.dbnode, lsn)?;

-        let db_size = total_blocks as i64 * BLCKSZ as i64;
+        let db_size = total_blocks as i64 * pg_constants::BLCKSZ as i64;

        Ok(PagestreamBeMessage::DbSize(PagestreamDbSizeResponse {
            db_size,
--- a/pageserver/src/pgdatadir_mapping.rs
+++ b/pageserver/src/pgdatadir_mapping.rs
@@ -13,10 +13,8 @@ use crate::repository::*;
 use crate::walrecord::ZenithWalRecord;
 use anyhow::{bail, ensure, Result};
 use bytes::{Buf, Bytes};
-use postgres_ffi::v14::pg_constants;
-use postgres_ffi::v14::xlog_utils::TimestampTz;
-use postgres_ffi::BLCKSZ;
-use postgres_ffi::{Oid, TransactionId};
+use postgres_ffi::xlog_utils::TimestampTz;
+use postgres_ffi::{pg_constants, Oid, TransactionId};
 use serde::{Deserialize, Serialize};
 use std::collections::{HashMap, HashSet};
 use std::ops::Range;
@@ -299,9 +297,9 @@ pub trait DatadirTimeline: Timeline {
                let clog_page =
                    self.get_slru_page_at_lsn(SlruKind::Clog, segno, blknum, probe_lsn)?;

-                if clog_page.len() == BLCKSZ as usize + 8 {
+                if clog_page.len() == pg_constants::BLCKSZ as usize + 8 {
                    let mut timestamp_bytes = [0u8; 8];
-                    timestamp_bytes.copy_from_slice(&clog_page[BLCKSZ as usize..]);
+                    timestamp_bytes.copy_from_slice(&clog_page[pg_constants::BLCKSZ as usize..]);
                    let timestamp = TimestampTz::from_be_bytes(timestamp_bytes);

                    if timestamp >= search_timestamp {
@@ -384,7 +382,7 @@ pub trait DatadirTimeline: Timeline {
                total_size += relsize as usize;
            }
        }
-        Ok(total_size * BLCKSZ as usize)
+        Ok(total_size * pg_constants::BLCKSZ as usize)
    }

    ///
@@ -914,7 +912,7 @@ impl<'a, T: DatadirTimeline> DatadirModification<'a, T> {
        result?;

        if pending_nblocks != 0 {
-            writer.update_current_logical_size(pending_nblocks * BLCKSZ as isize);
+            writer.update_current_logical_size(pending_nblocks * pg_constants::BLCKSZ as isize);
            self.pending_nblocks = 0;
        }

@@ -942,7 +940,7 @@ impl<'a, T: DatadirTimeline> DatadirModification<'a, T> {
        writer.finish_write(lsn);

        if pending_nblocks != 0 {
-            writer.update_current_logical_size(pending_nblocks * BLCKSZ as isize);
+            writer.update_current_logical_size(pending_nblocks * pg_constants::BLCKSZ as isize);
        }

        Ok(())
@@ -1016,7 +1014,7 @@ struct SlruSegmentDirectory {
    segments: HashSet<u32>,
 }

-static ZERO_PAGE: Bytes = Bytes::from_static(&[0u8; BLCKSZ as usize]);
+static ZERO_PAGE: Bytes = Bytes::from_static(&[0u8; pg_constants::BLCKSZ as usize]);

 // Layout of the Key address space
 //
--- a/pageserver/src/reltag.rs
+++ b/pageserver/src/reltag.rs
@@ -2,9 +2,8 @@ use serde::{Deserialize, Serialize};
 use std::cmp::Ordering;
 use std::fmt;

-use postgres_ffi::v14::pg_constants;
-use postgres_ffi::v14::relfile_utils::forknumber_to_name;
-use postgres_ffi::Oid;
+use postgres_ffi::relfile_utils::forknumber_to_name;
+use postgres_ffi::{pg_constants, Oid};

 ///
 /// Relation data file segment id throughout the Postgres cluster.
--- a/pageserver/src/repository.rs
+++ b/pageserver/src/repository.rs
@@ -412,6 +412,7 @@ pub mod repo_harness {
    use std::sync::{Arc, RwLock, RwLockReadGuard, RwLockWriteGuard};
    use std::{fs, path::PathBuf};

+    use crate::RepositoryImpl;
    use crate::{
        config::PageServerConf,
        layered_repository::LayeredRepository,
@@ -507,11 +508,11 @@ pub mod repo_harness {
            })
        }

-        pub fn load(&self) -> LayeredRepository {
+        pub fn load(&self) -> RepositoryImpl {
            self.try_load().expect("failed to load test repo")
        }

-        pub fn try_load(&self) -> Result<LayeredRepository> {
+        pub fn try_load(&self) -> Result<RepositoryImpl> {
            let walredo_mgr = Arc::new(TestRedoManager);

            let repo = LayeredRepository::new(
--- a/pageserver/src/tenant_mgr.rs
+++ b/pageserver/src/tenant_mgr.rs
@@ -3,14 +3,16 @@

 use crate::config::PageServerConf;
 use crate::http::models::TenantInfo;
-use crate::layered_repository::{load_metadata, LayeredRepository, LayeredTimeline};
+use crate::layered_repository::{load_metadata, LayeredRepository};
 use crate::repository::Repository;
 use crate::storage_sync::index::{RemoteIndex, RemoteTimelineIndex};
 use crate::storage_sync::{self, LocalTimelineInitStatus, SyncStartupData};
 use crate::tenant_config::TenantConfOpt;
 use crate::thread_mgr::ThreadKind;
+use crate::timelines::CreateRepo;
 use crate::walredo::PostgresRedoManager;
 use crate::{thread_mgr, timelines, walreceiver};
+use crate::{RepositoryImpl, TimelineImpl};
 use anyhow::Context;
 use serde::{Deserialize, Serialize};
 use std::collections::hash_map::Entry;
@@ -94,13 +96,13 @@ mod tenants_state {
 struct Tenant {
    state: TenantState,
    /// Contains in-memory state, including the timeline that might not yet flushed on disk or loaded form disk.
-    repo: Arc<LayeredRepository>,
+    repo: Arc<RepositoryImpl>,
    /// Timelines, located locally in the pageserver's datadir.
    /// Timelines can entirely be removed entirely by the `detach` operation only.
    ///
    /// Local timelines have more metadata that's loaded into memory,
    /// that is located in the `repo.timelines` field, [`crate::layered_repository::LayeredTimelineEntry`].
-    local_timelines: HashMap<ZTimelineId, Arc<LayeredTimeline>>,
+    local_timelines: HashMap<ZTimelineId, Arc<<RepositoryImpl as Repository>::Timeline>>,
 }

 #[derive(Debug, Serialize, Deserialize, Clone, Copy, PartialEq, Eq)]
@@ -177,7 +179,7 @@ pub enum LocalTimelineUpdate {
    },
    Attach {
        id: ZTenantTimelineId,
-        datadir: Arc<LayeredTimeline>,
+        datadir: Arc<<RepositoryImpl as Repository>::Timeline>,
    },
 }

@@ -283,8 +285,10 @@ pub fn create_tenant_repository(
                conf,
                tenant_conf,
                tenant_id,
-                wal_redo_manager,
-                remote_index,
+                CreateRepo::Real {
+                    wal_redo_manager,
+                    remote_index,
+                },
            )?;
            v.insert(Tenant {
                state: TenantState::Idle,
@@ -365,7 +369,7 @@ pub fn set_tenant_state(tenant_id: ZTenantId, new_state: TenantState) -> anyhow:
    Ok(())
 }

-pub fn get_repository_for_tenant(tenant_id: ZTenantId) -> anyhow::Result<Arc<LayeredRepository>> {
+pub fn get_repository_for_tenant(tenant_id: ZTenantId) -> anyhow::Result<Arc<RepositoryImpl>> {
    let m = tenants_state::read_tenants();
    let tenant = m
        .get(&tenant_id)
@@ -379,7 +383,7 @@ pub fn get_repository_for_tenant(tenant_id: ZTenantId) -> anyhow::Result<Arc<Lay
 pub fn get_local_timeline_with_load(
    tenant_id: ZTenantId,
    timeline_id: ZTimelineId,
-) -> anyhow::Result<Arc<LayeredTimeline>> {
+) -> anyhow::Result<Arc<TimelineImpl>> {
    let mut m = tenants_state::write_tenants();
    let tenant = m
        .get_mut(&tenant_id)
@@ -484,9 +488,9 @@ pub fn detach_tenant(conf: &'static PageServerConf, tenant_id: ZTenantId) -> any
 }

 fn load_local_timeline(
-    repo: &LayeredRepository,
+    repo: &RepositoryImpl,
    timeline_id: ZTimelineId,
-) -> anyhow::Result<Arc<LayeredTimeline>> {
+) -> anyhow::Result<Arc<TimelineImpl>> {
    let inmem_timeline = repo.get_timeline_load(timeline_id).with_context(|| {
        format!("Inmem timeline {timeline_id} not found in tenant's repository")
    })?;
@@ -630,7 +634,7 @@ fn load_local_repo(
    conf: &'static PageServerConf,
    tenant_id: ZTenantId,
    remote_index: &RemoteIndex,
-) -> anyhow::Result<Arc<LayeredRepository>> {
+) -> anyhow::Result<Arc<RepositoryImpl>> {
    let mut m = tenants_state::write_tenants();
    let tenant = m.entry(tenant_id).or_insert_with(|| {
        // Set up a WAL redo manager, for applying WAL records.
--- a/pageserver/src/timelines.rs
+++ b/pageserver/src/timelines.rs
@@ -3,7 +3,7 @@
 //

 use anyhow::{bail, ensure, Context, Result};
-
+use postgres_ffi::ControlFileData;
 use std::{
    fs,
    path::Path,
@@ -13,21 +13,18 @@ use std::{
 use tracing::*;

 use utils::{
-    crashsafe_dir,
+    crashsafe_dir, logging,
    lsn::Lsn,
    zid::{ZTenantId, ZTimelineId},
 };

-use crate::import_datadir;
 use crate::tenant_mgr;
 use crate::{
    config::PageServerConf, repository::Repository, storage_sync::index::RemoteIndex,
-    tenant_config::TenantConfOpt,
-};
-use crate::{
-    layered_repository::{LayeredRepository, LayeredTimeline},
-    walredo::WalRedoManager,
+    tenant_config::TenantConfOpt, RepositoryImpl, TimelineImpl,
 };
+use crate::{import_datadir, LOG_FILE_NAME};
+use crate::{layered_repository::LayeredRepository, walredo::WalRedoManager};
 use crate::{repository::Timeline, CheckpointConfig};

 #[derive(Debug, Clone, Copy)]
@@ -36,13 +33,69 @@ pub struct PointInTime {
    pub lsn: Lsn,
 }

+pub fn init_pageserver(
+    conf: &'static PageServerConf,
+    create_tenant: Option<ZTenantId>,
+    initial_timeline_id: Option<ZTimelineId>,
+) -> anyhow::Result<()> {
+    // Initialize logger
+    // use true as daemonize parameter because otherwise we pollute zenith cli output with a few pages long output of info messages
+    let _log_file = logging::init(LOG_FILE_NAME, true)?;
+
+    crashsafe_dir::create_dir_all(conf.tenants_path())?;
+
+    if let Some(tenant_id) = create_tenant {
+        println!("initializing tenantid {}", tenant_id);
+        let repo = create_repo(conf, TenantConfOpt::default(), tenant_id, CreateRepo::Dummy)
+            .context("failed to create repo")?;
+        let new_timeline_id = initial_timeline_id.unwrap_or_else(ZTimelineId::generate);
+        bootstrap_timeline(conf, tenant_id, new_timeline_id, repo.as_ref())
+            .context("failed to create initial timeline")?;
+        println!("initial timeline {} created", new_timeline_id)
+    } else if initial_timeline_id.is_some() {
+        println!("Ignoring initial timeline parameter, due to no tenant id to create given");
+    }
+
+    println!("pageserver init succeeded");
+    Ok(())
+}
+
+pub enum CreateRepo {
+    Real {
+        wal_redo_manager: Arc<dyn WalRedoManager + Send + Sync>,
+        remote_index: RemoteIndex,
+    },
+    Dummy,
+}
+
 pub fn create_repo(
    conf: &'static PageServerConf,
    tenant_conf: TenantConfOpt,
    tenant_id: ZTenantId,
-    wal_redo_manager: Arc<dyn WalRedoManager + Send + Sync>,
-    remote_index: RemoteIndex,
-) -> Result<Arc<LayeredRepository>> {
+    create_repo: CreateRepo,
+) -> Result<Arc<RepositoryImpl>> {
+    let (wal_redo_manager, remote_index) = match create_repo {
+        CreateRepo::Real {
+            wal_redo_manager,
+            remote_index,
+        } => (wal_redo_manager, remote_index),
+        CreateRepo::Dummy => {
+            // We don't use the real WAL redo manager, because we don't want to spawn the WAL redo
+            // process during repository initialization.
+            //
+            // FIXME: That caused trouble, because the WAL redo manager spawned a thread that launched
+            // initdb in the background, and it kept running even after the "zenith init" had exited.
+            // In tests, we started the  page server immediately after that, so that initdb was still
+            // running in the background, and we failed to run initdb again in the same directory. This
+            // has been solved for the rapid init+start case now, but the general race condition remains
+            // if you restart the server quickly. The WAL redo manager doesn't use a separate thread
+            // anymore, but I think that could still happen.
+            let wal_redo_manager = Arc::new(crate::walredo::DummyRedoManager {});
+
+            (wal_redo_manager as _, RemoteIndex::default())
+        }
+    };
+
    let repo_dir = conf.tenant_path(&tenant_id);
    ensure!(
        !repo_dir.exists(),
@@ -69,6 +122,16 @@ pub fn create_repo(
    )))
 }

+// Returns checkpoint LSN from controlfile
+fn get_lsn_from_controlfile(path: &Path) -> Result<Lsn> {
+    // Read control file to extract the LSN
+    let controlfile_path = path.join("global").join("pg_control");
+    let controlfile = ControlFileData::decode(&fs::read(controlfile_path)?)?;
+    let lsn = controlfile.checkPoint;
+
+    Ok(Lsn(lsn))
+}
+
 // Create the cluster temporarily in 'initdbpath' directory inside the repository
 // to get bootstrap data for timeline initialization.
 //
@@ -118,7 +181,7 @@ fn bootstrap_timeline<R: Repository>(
    run_initdb(conf, &initdb_path)?;
    let pgdata_path = initdb_path;

-    let lsn = import_datadir::get_lsn_from_controlfile(&pgdata_path)?.align();
+    let lsn = get_lsn_from_controlfile(&pgdata_path)?.align();

    // Import the contents of the data directory at the initial checkpoint
    // LSN, and any WAL after that.
@@ -160,7 +223,7 @@ pub(crate) fn create_timeline(
    new_timeline_id: Option<ZTimelineId>,
    ancestor_timeline_id: Option<ZTimelineId>,
    mut ancestor_start_lsn: Option<Lsn>,
-) -> Result<Option<(ZTimelineId, Arc<LayeredTimeline>)>> {
+) -> Result<Option<(ZTimelineId, Arc<TimelineImpl>)>> {
    let new_timeline_id = new_timeline_id.unwrap_or_else(ZTimelineId::generate);
    let repo = tenant_mgr::get_repository_for_tenant(tenant_id)?;

--- a/pageserver/src/walingest.rs
+++ b/pageserver/src/walingest.rs
@@ -22,8 +22,8 @@
 //! bespoken Rust code.

 use anyhow::Context;
-use postgres_ffi::v14::nonrelfile_utils::clogpage_precedes;
-use postgres_ffi::v14::nonrelfile_utils::slru_may_delete_clogsegment;
+use postgres_ffi::nonrelfile_utils::clogpage_precedes;
+use postgres_ffi::nonrelfile_utils::slru_may_delete_clogsegment;
 use postgres_ffi::{page_is_new, page_set_lsn};

 use anyhow::Result;
@@ -33,12 +33,10 @@ use tracing::*;
 use crate::pgdatadir_mapping::*;
 use crate::reltag::{RelTag, SlruKind};
 use crate::walrecord::*;
-use postgres_ffi::v14::nonrelfile_utils::mx_offset_to_member_segment;
-use postgres_ffi::v14::pg_constants;
-use postgres_ffi::v14::xlog_utils::*;
-use postgres_ffi::v14::CheckPoint;
+use postgres_ffi::nonrelfile_utils::mx_offset_to_member_segment;
+use postgres_ffi::xlog_utils::*;
 use postgres_ffi::TransactionId;
-use postgres_ffi::BLCKSZ;
+use postgres_ffi::{pg_constants, CheckPoint};
 use utils::lsn::Lsn;

 static ZERO_PAGE: Bytes = Bytes::from_static(&[0u8; 8192]);
@@ -295,7 +293,7 @@ impl<'a, T: DatadirTimeline> WalIngest<'a, T> {
            // Extract page image from FPI record
            let img_len = blk.bimg_len as usize;
            let img_offs = blk.bimg_offset as usize;
-            let mut image = BytesMut::with_capacity(BLCKSZ as usize);
+            let mut image = BytesMut::with_capacity(pg_constants::BLCKSZ as usize);
            image.extend_from_slice(&decoded.record[img_offs..img_offs + img_len]);

            if blk.hole_length != 0 {
@@ -311,7 +309,7 @@ impl<'a, T: DatadirTimeline> WalIngest<'a, T> {
            if !page_is_new(&image) {
                page_set_lsn(&mut image, lsn)
            }
-            assert_eq!(image.len(), BLCKSZ as usize);
+            assert_eq!(image.len(), pg_constants::BLCKSZ as usize);
            self.put_rel_page_image(modification, rel, blk.blkno, image.freeze())?;
        } else {
            let rec = ZenithWalRecord::Postgres {
@@ -1035,8 +1033,7 @@ mod tests {
    use crate::pgdatadir_mapping::create_test_timeline;
    use crate::repository::repo_harness::*;
    use crate::repository::Timeline;
-    use postgres_ffi::v14::xlog_utils::SIZEOF_CHECKPOINT;
-    use postgres_ffi::RELSEG_SIZE;
+    use postgres_ffi::pg_constants;

    /// Arbitrary relation tag, for testing.
    const TESTREL_A: RelTag = RelTag {
@@ -1325,7 +1322,7 @@ mod tests {
        let mut walingest = init_walingest_test(&*tline)?;

        let mut lsn = 0x10;
-        for blknum in 0..RELSEG_SIZE + 1 {
+        for blknum in 0..pg_constants::RELSEG_SIZE + 1 {
            lsn += 0x10;
            let mut m = tline.begin_modification(Lsn(lsn));
            let img = TEST_IMG(&format!("foo blk {} at {}", blknum, Lsn(lsn)));
@@ -1335,22 +1332,31 @@ mod tests {

        assert_current_logical_size(&*tline, Lsn(lsn));

-        assert_eq!(tline.get_rel_size(TESTREL_A, Lsn(lsn))?, RELSEG_SIZE + 1);
+        assert_eq!(
+            tline.get_rel_size(TESTREL_A, Lsn(lsn))?,
+            pg_constants::RELSEG_SIZE + 1
+        );

        // Truncate one block
        lsn += 0x10;
        let mut m = tline.begin_modification(Lsn(lsn));
-        walingest.put_rel_truncation(&mut m, TESTREL_A, RELSEG_SIZE)?;
+        walingest.put_rel_truncation(&mut m, TESTREL_A, pg_constants::RELSEG_SIZE)?;
        m.commit()?;
-        assert_eq!(tline.get_rel_size(TESTREL_A, Lsn(lsn))?, RELSEG_SIZE);
+        assert_eq!(
+            tline.get_rel_size(TESTREL_A, Lsn(lsn))?,
+            pg_constants::RELSEG_SIZE
+        );
        assert_current_logical_size(&*tline, Lsn(lsn));

        // Truncate another block
        lsn += 0x10;
        let mut m = tline.begin_modification(Lsn(lsn));
-        walingest.put_rel_truncation(&mut m, TESTREL_A, RELSEG_SIZE - 1)?;
+        walingest.put_rel_truncation(&mut m, TESTREL_A, pg_constants::RELSEG_SIZE - 1)?;
        m.commit()?;
-        assert_eq!(tline.get_rel_size(TESTREL_A, Lsn(lsn))?, RELSEG_SIZE - 1);
+        assert_eq!(
+            tline.get_rel_size(TESTREL_A, Lsn(lsn))?,
+            pg_constants::RELSEG_SIZE - 1
+        );
        assert_current_logical_size(&*tline, Lsn(lsn));

        // Truncate to 1500, and then truncate all the way down to 0, one block at a time
--- a/pageserver/src/walreceiver/connection_manager.rs
+++ b/pageserver/src/walreceiver/connection_manager.rs
@@ -16,7 +16,6 @@ use std::{
    time::Duration,
 };

-use crate::{layered_repository::LayeredTimeline, repository::Timeline};
 use anyhow::Context;
 use chrono::{NaiveDateTime, Utc};
 use etcd_broker::{
@@ -26,7 +25,12 @@ use etcd_broker::{
 use tokio::select;
 use tracing::*;

-use crate::{exponential_backoff, DEFAULT_BASE_BACKOFF_SECONDS, DEFAULT_MAX_BACKOFF_SECONDS};
+use crate::{
+    exponential_backoff,
+    repository::{Repository, Timeline},
+    DEFAULT_BASE_BACKOFF_SECONDS, DEFAULT_MAX_BACKOFF_SECONDS,
+};
+use crate::{RepositoryImpl, TimelineImpl};
 use utils::{
    lsn::Lsn,
    zid::{NodeId, ZTenantTimelineId},
@@ -39,7 +43,7 @@ pub(super) fn spawn_connection_manager_task(
    id: ZTenantTimelineId,
    broker_loop_prefix: String,
    mut client: Client,
-    local_timeline: Arc<LayeredTimeline>,
+    local_timeline: Arc<TimelineImpl>,
    wal_connect_timeout: Duration,
    lagging_wal_timeout: Duration,
    max_lsn_wal_lag: NonZeroU64,
@@ -96,8 +100,6 @@ async fn connection_manager_loop_step(
    info!("Subscribed for etcd timeline changes, waiting for new etcd data");

    loop {
-        let time_until_next_retry = walreceiver_state.time_until_next_retry();
-
        select! {
            broker_connection_result = &mut broker_subscription.watcher_handle => {
                cleanup_broker_connection(broker_connection_result, walreceiver_state);
@@ -112,23 +114,27 @@ async fn connection_manager_loop_step(
            } => {
                let wal_connection = walreceiver_state.wal_connection.as_mut().expect("Should have a connection, as checked by the corresponding select! guard");
                match wal_connection_update {
-                    TaskEvent::Started => {},
+                    TaskEvent::Started => {
+                        *walreceiver_state.wal_connection_attempts.entry(wal_connection.sk_id).or_insert(0) += 1;
+                    },
                    TaskEvent::NewEvent(status) => {
-                        if status.has_processed_wal {
-                            // We have advanced last_record_lsn by processing the WAL received
-                            // from this safekeeper. This is good enough to clean unsuccessful
-                            // retries history and allow reconnecting to this safekeeper without
-                            // sleeping for a long time.
-                            walreceiver_state.wal_connection_retries.remove(&wal_connection.sk_id);
+                        if status.has_received_wal {
+                            // Reset connection attempts here only, we know that safekeeper is healthy
+                            // because it can send us a WAL update.
+                            walreceiver_state.wal_connection_attempts.remove(&wal_connection.sk_id);
                        }
                        wal_connection.status = status;
                    },
                    TaskEvent::End(end_result) => {
                        match end_result {
                            Ok(()) => debug!("WAL receiving task finished"),
-                            Err(e) => warn!("WAL receiving task failed: {e}"),
+                            Err(e) => {
+                                warn!("WAL receiving task failed: {e}");
+                                // If the task failed, set the connection attempts to at least 1, to try other safekeepers.
+                                let _ = *walreceiver_state.wal_connection_attempts.entry(wal_connection.sk_id).or_insert(1);
+                            }
                        };
-                        walreceiver_state.drop_old_connection(false).await;
+                        walreceiver_state.wal_connection = None;
                    },
                }
            },
@@ -152,8 +158,6 @@ async fn connection_manager_loop_step(
                    }
                }
            },
-
-            _ = async { tokio::time::sleep(time_until_next_retry.unwrap()).await }, if time_until_next_retry.is_some() => {}
        }

        // Fetch more etcd timeline updates, but limit ourselves since they may arrive quickly.
@@ -234,15 +238,11 @@ async fn subscribe_for_timeline_updates(
    }
 }

-const WALCONNECTION_RETRY_MIN_BACKOFF_SECONDS: f64 = 0.1;
-const WALCONNECTION_RETRY_MAX_BACKOFF_SECONDS: f64 = 15.0;
-const WALCONNECTION_RETRY_BACKOFF_MULTIPLIER: f64 = 1.5;
-
 /// All data that's needed to run endless broker loop and keep the WAL streaming connection alive, if possible.
 struct WalreceiverState {
    id: ZTenantTimelineId,
    /// Use pageserver data about the timeline to filter out some of the safekeepers.
-    local_timeline: Arc<LayeredTimeline>,
+    local_timeline: Arc<TimelineImpl>,
    /// The timeout on the connection to safekeeper for WAL streaming.
    wal_connect_timeout: Duration,
    /// The timeout to use to determine when the current connection is "stale" and reconnect to the other one.
@@ -251,8 +251,7 @@ struct WalreceiverState {
    max_lsn_wal_lag: NonZeroU64,
    /// Current connection to safekeeper for WAL streaming.
    wal_connection: Option<WalConnection>,
-    /// Info about retries and unsuccessful attempts to connect to safekeepers.
-    wal_connection_retries: HashMap<NodeId, RetryInfo>,
+    wal_connection_attempts: HashMap<NodeId, u32>,
    /// Data about all timelines, available for connection, fetched from etcd, grouped by their corresponding safekeeper node id.
    wal_stream_candidates: HashMap<NodeId, EtcdSkTimeline>,
 }
@@ -260,8 +259,6 @@ struct WalreceiverState {
 /// Current connection data.
 #[derive(Debug)]
 struct WalConnection {
-    /// Time when the connection was initiated.
-    started_at: NaiveDateTime,
    /// Current safekeeper pageserver is connected to for WAL streaming.
    sk_id: NodeId,
    /// Status of the connection.
@@ -281,12 +278,6 @@ struct NewCommittedWAL {
    discovered_at: NaiveDateTime,
 }

-#[derive(Debug)]
-struct RetryInfo {
-    next_retry_at: Option<NaiveDateTime>,
-    retry_duration_seconds: f64,
-}
-
 /// Data about the timeline to connect to, received from etcd.
 #[derive(Debug)]
 struct EtcdSkTimeline {
@@ -300,7 +291,7 @@ struct EtcdSkTimeline {
 impl WalreceiverState {
    fn new(
        id: ZTenantTimelineId,
-        local_timeline: Arc<LayeredTimeline>,
+        local_timeline: Arc<<RepositoryImpl as Repository>::Timeline>,
        wal_connect_timeout: Duration,
        lagging_wal_timeout: Duration,
        max_lsn_wal_lag: NonZeroU64,
@@ -313,18 +304,31 @@ impl WalreceiverState {
            max_lsn_wal_lag,
            wal_connection: None,
            wal_stream_candidates: HashMap::new(),
-            wal_connection_retries: HashMap::new(),
+            wal_connection_attempts: HashMap::new(),
        }
    }

    /// Shuts down the current connection (if any) and immediately starts another one with the given connection string.
    async fn change_connection(&mut self, new_sk_id: NodeId, new_wal_source_connstr: String) {
-        self.drop_old_connection(true).await;
+        if let Some(old_connection) = self.wal_connection.take() {
+            old_connection.connection_task.shutdown().await
+        }

        let id = self.id;
        let connect_timeout = self.wal_connect_timeout;
+        let connection_attempt = self
+            .wal_connection_attempts
+            .get(&new_sk_id)
+            .copied()
+            .unwrap_or(0);
        let connection_handle = TaskHandle::spawn(move |events_sender, cancellation| {
            async move {
+                exponential_backoff(
+                    connection_attempt,
+                    DEFAULT_BASE_BACKOFF_SECONDS,
+                    DEFAULT_MAX_BACKOFF_SECONDS,
+                )
+                .await;
                super::walreceiver_connection::handle_walreceiver_connection(
                    id,
                    &new_wal_source_connstr,
@@ -340,11 +344,10 @@ impl WalreceiverState {

        let now = Utc::now().naive_utc();
        self.wal_connection = Some(WalConnection {
-            started_at: now,
            sk_id: new_sk_id,
            status: WalConnectionStatus {
                is_connected: false,
-                has_processed_wal: false,
+                has_received_wal: false,
                latest_connection_update: now,
                latest_wal_update: now,
                streaming_lsn: None,
@@ -355,71 +358,6 @@ impl WalreceiverState {
        });
    }

-    /// Drops the current connection (if any) and updates retry timeout for the next
-    /// connection attempt to the same safekeeper.
-    async fn drop_old_connection(&mut self, needs_shutdown: bool) {
-        let wal_connection = match self.wal_connection.take() {
-            Some(wal_connection) => wal_connection,
-            None => return,
-        };
-
-        if needs_shutdown {
-            wal_connection.connection_task.shutdown().await;
-        }
-
-        let retry = self
-            .wal_connection_retries
-            .entry(wal_connection.sk_id)
-            .or_insert(RetryInfo {
-                next_retry_at: None,
-                retry_duration_seconds: WALCONNECTION_RETRY_MIN_BACKOFF_SECONDS,
-            });
-
-        let now = Utc::now().naive_utc();
-
-        // Schedule the next retry attempt. We want to have exponential backoff for connection attempts,
-        // and we add backoff to the time when we started the connection attempt. If the connection
-        // was active for a long time, then next_retry_at will be in the past.
-        retry.next_retry_at =
-            wal_connection
-                .started_at
-                .checked_add_signed(chrono::Duration::milliseconds(
-                    (retry.retry_duration_seconds * 1000.0) as i64,
-                ));
-
-        if let Some(next) = &retry.next_retry_at {
-            if next > &now {
-                info!(
-                    "Next connection retry to {:?} is at {}",
-                    wal_connection.sk_id, next
-                );
-            }
-        }
-
-        let next_retry_duration =
-            retry.retry_duration_seconds * WALCONNECTION_RETRY_BACKOFF_MULTIPLIER;
-        // Clamp the next retry duration to the maximum allowed.
-        let next_retry_duration = next_retry_duration.min(WALCONNECTION_RETRY_MAX_BACKOFF_SECONDS);
-        // Clamp the next retry duration to the minimum allowed.
-        let next_retry_duration = next_retry_duration.max(WALCONNECTION_RETRY_MIN_BACKOFF_SECONDS);
-
-        retry.retry_duration_seconds = next_retry_duration;
-    }
-
-    /// Returns time needed to wait to have a new candidate for WAL streaming.
-    fn time_until_next_retry(&self) -> Option<Duration> {
-        let now = Utc::now().naive_utc();
-
-        let next_retry_at = self
-            .wal_connection_retries
-            .values()
-            .filter_map(|retry| retry.next_retry_at)
-            .filter(|next_retry_at| next_retry_at > &now)
-            .min();
-
-        next_retry_at.and_then(|next_retry_at| (next_retry_at - now).to_std().ok())
-    }
-
    /// Adds another etcd timeline into the state, if its more recent than the one already added there for the same key.
    fn register_timeline_update(&mut self, timeline_update: BrokerUpdate<SkTimelineInfo>) {
        match self
@@ -613,37 +551,52 @@ impl WalreceiverState {
    /// Optionally, omits the given node, to support gracefully switching from a healthy safekeeper to another.
    ///
    /// The candidate that is chosen:
-    /// * has no pending retry cooldown
-    /// * has greatest commit_lsn among the ones that are left
+    /// * has fewest connection attempts from pageserver to safekeeper node (reset every time we receive a WAL message from the node)
+    /// * has greatest data Lsn among the ones that are left
+    ///
+    /// NOTE:
+    /// We evict timeline data received from etcd based on time passed since it was registered, along with its connection attempts values, but
+    /// otherwise to reset the connection attempts, a successful connection to that node is needed.
+    /// That won't happen now, before all nodes with less connection attempts are connected to first, which might leave the sk node with more advanced state to be ignored.
    fn select_connection_candidate(
        &self,
        node_to_omit: Option<NodeId>,
    ) -> Option<(NodeId, &SkTimelineInfo, String)> {
-        self.applicable_connection_candidates()
+        let all_candidates = self
+            .applicable_connection_candidates()
            .filter(|&(sk_id, _, _)| Some(sk_id) != node_to_omit)
+            .collect::<Vec<_>>();
+
+        let smallest_attempts_allowed = all_candidates
+            .iter()
+            .map(|(sk_id, _, _)| {
+                self.wal_connection_attempts
+                    .get(sk_id)
+                    .copied()
+                    .unwrap_or(0)
+            })
+            .min()?;
+
+        all_candidates
+            .into_iter()
+            .filter(|(sk_id, _, _)| {
+                smallest_attempts_allowed
+                    >= self
+                        .wal_connection_attempts
+                        .get(sk_id)
+                        .copied()
+                        .unwrap_or(0)
+            })
            .max_by_key(|(_, info, _)| info.commit_lsn)
    }

    /// Returns a list of safekeepers that have valid info and ready for connection.
-    /// Some safekeepers are filtered by the retry cooldown.
    fn applicable_connection_candidates(
        &self,
    ) -> impl Iterator<Item = (NodeId, &SkTimelineInfo, String)> {
-        let now = Utc::now().naive_utc();
-
        self.wal_stream_candidates
            .iter()
            .filter(|(_, info)| info.timeline.commit_lsn.is_some())
-            .filter(move |(sk_id, _)| {
-                let next_retry_at = self
-                    .wal_connection_retries
-                    .get(sk_id)
-                    .and_then(|retry_info| {
-                        retry_info.next_retry_at
-                    });
-
-                next_retry_at.is_none() || next_retry_at.unwrap() <= now
-            })
            .filter_map(|(sk_id, etcd_info)| {
                let info = &etcd_info.timeline;
                match wal_stream_connection_string(
@@ -678,7 +631,7 @@ impl WalreceiverState {
        });

        for node_id in node_ids_to_remove {
-            self.wal_connection_retries.remove(&node_id);
+            self.wal_connection_attempts.remove(&node_id);
        }
    }
 }
@@ -735,6 +688,7 @@ fn wal_stream_connection_string(

 #[cfg(test)]
 mod tests {
+
    use crate::repository::{
        repo_harness::{RepoHarness, TIMELINE_ID},
        Repository,
@@ -839,7 +793,7 @@ mod tests {

        let connection_status = WalConnectionStatus {
            is_connected: true,
-            has_processed_wal: true,
+            has_received_wal: true,
            latest_connection_update: now,
            latest_wal_update: now,
            commit_lsn: Some(Lsn(current_lsn)),
@@ -848,7 +802,6 @@ mod tests {

        state.max_lsn_wal_lag = NonZeroU64::new(100).unwrap();
        state.wal_connection = Some(WalConnection {
-            started_at: now,
            sk_id: connected_sk_id,
            status: connection_status.clone(),
            connection_task: TaskHandle::spawn(move |sender, _| async move {
@@ -1068,13 +1021,7 @@ mod tests {
                },
            ),
        ]);
-        state.wal_connection_retries = HashMap::from([(
-            NodeId(0),
-            RetryInfo {
-                next_retry_at: now.checked_add_signed(chrono::Duration::hours(1)),
-                retry_duration_seconds: WALCONNECTION_RETRY_MAX_BACKOFF_SECONDS,
-            },
-        )]);
+        state.wal_connection_attempts = HashMap::from([(NodeId(0), 1), (NodeId(1), 0)]);

        let candidate_with_less_errors = state
            .next_connection_candidate()
@@ -1082,7 +1029,7 @@ mod tests {
        assert_eq!(
            candidate_with_less_errors.safekeeper_id,
            NodeId(1),
-            "Should select the node with no pending retry cooldown"
+            "Should select the node with less connection errors"
        );

        Ok(())
@@ -1100,7 +1047,7 @@ mod tests {

        let connection_status = WalConnectionStatus {
            is_connected: true,
-            has_processed_wal: true,
+            has_received_wal: true,
            latest_connection_update: now,
            latest_wal_update: now,
            commit_lsn: Some(current_lsn),
@@ -1108,7 +1055,6 @@ mod tests {
        };

        state.wal_connection = Some(WalConnection {
-            started_at: now,
            sk_id: connected_sk_id,
            status: connection_status.clone(),
            connection_task: TaskHandle::spawn(move |sender, _| async move {
@@ -1188,7 +1134,7 @@ mod tests {

        let connection_status = WalConnectionStatus {
            is_connected: true,
-            has_processed_wal: true,
+            has_received_wal: true,
            latest_connection_update: time_over_threshold,
            latest_wal_update: time_over_threshold,
            commit_lsn: Some(current_lsn),
@@ -1196,7 +1142,6 @@ mod tests {
        };

        state.wal_connection = Some(WalConnection {
-            started_at: now,
            sk_id: NodeId(1),
            status: connection_status.clone(),
            connection_task: TaskHandle::spawn(move |sender, _| async move {
@@ -1261,7 +1206,7 @@ mod tests {

        let connection_status = WalConnectionStatus {
            is_connected: true,
-            has_processed_wal: true,
+            has_received_wal: true,
            latest_connection_update: now,
            latest_wal_update: time_over_threshold,
            commit_lsn: Some(current_lsn),
@@ -1269,7 +1214,6 @@ mod tests {
        };

        state.wal_connection = Some(WalConnection {
-            started_at: now,
            sk_id: NodeId(1),
            status: connection_status,
            connection_task: TaskHandle::spawn(move |_, _| async move { Ok(()) }),
@@ -1341,7 +1285,7 @@ mod tests {
            max_lsn_wal_lag: NonZeroU64::new(1024 * 1024).unwrap(),
            wal_connection: None,
            wal_stream_candidates: HashMap::new(),
-            wal_connection_retries: HashMap::new(),
+            wal_connection_attempts: HashMap::new(),
        }
    }
 }
--- a/pageserver/src/walreceiver/walreceiver_connection.rs
+++ b/pageserver/src/walreceiver/walreceiver_connection.rs
@@ -27,7 +27,7 @@ use crate::{
    walingest::WalIngest,
    walrecord::DecodedWALRecord,
 };
-use postgres_ffi::v14::waldecoder::WalStreamDecoder;
+use postgres_ffi::waldecoder::WalStreamDecoder;
 use utils::{lsn::Lsn, pq_proto::ReplicationFeedback, zid::ZTenantTimelineId};

 /// Status of the connection.
@@ -35,9 +35,8 @@ use utils::{lsn::Lsn, pq_proto::ReplicationFeedback, zid::ZTenantTimelineId};
 pub struct WalConnectionStatus {
    /// If we were able to initiate a postgres connection, this means that safekeeper process is at least running.
    pub is_connected: bool,
-    /// Defines a healthy connection as one on which pageserver received WAL from safekeeper
-    /// and is able to process it in walingest without errors.
-    pub has_processed_wal: bool,
+    /// Defines a healthy connection as one on which we have received at least some WAL bytes.
+    pub has_received_wal: bool,
    /// Connection establishment time or the timestamp of a latest connection message received.
    pub latest_connection_update: NaiveDateTime,
    /// Time of the latest WAL message received.
@@ -72,7 +71,7 @@ pub async fn handle_walreceiver_connection(
    info!("connected!");
    let mut connection_status = WalConnectionStatus {
        is_connected: true,
-        has_processed_wal: false,
+        has_received_wal: false,
        latest_connection_update: Utc::now().naive_utc(),
        latest_wal_update: Utc::now().naive_utc(),
        streaming_lsn: None,
@@ -118,6 +117,13 @@ pub async fn handle_walreceiver_connection(
    let identify = identify_system(&mut replication_client).await?;
    info!("{identify:?}");

+    connection_status.latest_connection_update = Utc::now().naive_utc();
+    if let Err(e) = events_sender.send(TaskEvent::NewEvent(connection_status.clone())) {
+        warn!("Wal connection event listener dropped after IDENTIFY_SYSTEM, aborting the connection: {e}");
+        return Ok(());
+    }
+
+    // NB: this is a flush_lsn, not a commit_lsn.
    let end_of_wal = Lsn::from(u64::from(identify.xlogpos));
    let mut caught_up = false;
    let ZTenantTimelineId {
@@ -125,14 +131,6 @@ pub async fn handle_walreceiver_connection(
        timeline_id,
    } = id;

-    connection_status.latest_connection_update = Utc::now().naive_utc();
-    connection_status.latest_wal_update = Utc::now().naive_utc();
-    connection_status.commit_lsn = Some(end_of_wal);
-    if let Err(e) = events_sender.send(TaskEvent::NewEvent(connection_status.clone())) {
-        warn!("Wal connection event listener dropped after IDENTIFY_SYSTEM, aborting the connection: {e}");
-        return Ok(());
-    }
-
    let (repo, timeline) = tokio::task::spawn_blocking(move || {
        let repo = tenant_mgr::get_repository_for_tenant(tenant_id)
            .with_context(|| format!("no repository found for tenant {tenant_id}"))?;
@@ -183,7 +181,6 @@ pub async fn handle_walreceiver_connection(
    } {
        let replication_message = replication_message?;
        let now = Utc::now().naive_utc();
-        let last_rec_lsn_before_msg = last_rec_lsn;

        // Update the connection status before processing the message. If the message processing
        // fails (e.g. in walingest), we still want to know latests LSNs from the safekeeper.
@@ -196,6 +193,7 @@ pub async fn handle_walreceiver_connection(
                ));
                if !xlog_data.data().is_empty() {
                    connection_status.latest_wal_update = now;
+                    connection_status.has_received_wal = true;
                }
            }
            ReplicationMessage::PrimaryKeepAlive(keepalive) => {
@@ -267,15 +265,6 @@ pub async fn handle_walreceiver_connection(
            _ => None,
        };

-        if !connection_status.has_processed_wal && last_rec_lsn > last_rec_lsn_before_msg {
-            // We have successfully processed at least one WAL record.
-            connection_status.has_processed_wal = true;
-            if let Err(e) = events_sender.send(TaskEvent::NewEvent(connection_status.clone())) {
-                warn!("Wal connection event listener dropped, aborting the connection: {e}");
-                return Ok(());
-            }
-        }
-
        let timeline_to_check = Arc::clone(&timeline);
        tokio::task::spawn_blocking(move || timeline_to_check.check_checkpoint_distance())
            .await
--- a/pageserver/src/walrecord.rs
+++ b/pageserver/src/walrecord.rs
@@ -3,10 +3,9 @@
 //!
 use anyhow::Result;
 use bytes::{Buf, Bytes};
-use postgres_ffi::v14::pg_constants;
-use postgres_ffi::v14::xlog_utils::{TimestampTz, XLOG_SIZE_OF_XLOG_RECORD};
-use postgres_ffi::v14::XLogRecord;
-use postgres_ffi::BLCKSZ;
+use postgres_ffi::pg_constants;
+use postgres_ffi::xlog_utils::{TimestampTz, XLOG_SIZE_OF_XLOG_RECORD};
+use postgres_ffi::XLogRecord;
 use postgres_ffi::{BlockNumber, OffsetNumber};
 use postgres_ffi::{MultiXactId, MultiXactOffset, MultiXactStatus, Oid, TransactionId};
 use serde::{Deserialize, Serialize};
@@ -619,7 +618,7 @@ pub fn decode_wal_record(
                            blk.hole_length = 0;
                        }
                    } else {
-                        blk.hole_length = BLCKSZ - blk.bimg_len;
+                        blk.hole_length = pg_constants::BLCKSZ - blk.bimg_len;
                    }
                    datatotal += blk.bimg_len as u32;
                    blocks_total_len += blk.bimg_len as u32;
@@ -629,7 +628,9 @@ pub fn decode_wal_record(
                     * bimg_len < BLCKSZ if the HAS_HOLE flag is set.
                     */
                    if blk.bimg_info & pg_constants::BKPIMAGE_HAS_HOLE != 0
-                        && (blk.hole_offset == 0 || blk.hole_length == 0 || blk.bimg_len == BLCKSZ)
+                        && (blk.hole_offset == 0
+                            || blk.hole_length == 0
+                            || blk.bimg_len == pg_constants::BLCKSZ)
                    {
                        // TODO
                        /*
@@ -666,7 +667,7 @@ pub fn decode_wal_record(
                     * flag is set.
                     */
                    if (blk.bimg_info & pg_constants::BKPIMAGE_IS_COMPRESSED == 0)
-                        && blk.bimg_len == BLCKSZ
+                        && blk.bimg_len == pg_constants::BLCKSZ
                    {
                        // TODO
                        /*
@@ -684,7 +685,7 @@ pub fn decode_wal_record(
                     */
                    if blk.bimg_info & pg_constants::BKPIMAGE_HAS_HOLE == 0
                        && blk.bimg_info & pg_constants::BKPIMAGE_IS_COMPRESSED == 0
-                        && blk.bimg_len != BLCKSZ
+                        && blk.bimg_len != pg_constants::BLCKSZ
                    {
                        // TODO
                        /*
--- a/pageserver/src/walredo.rs
+++ b/pageserver/src/walredo.rs
@@ -44,12 +44,11 @@ use crate::reltag::{RelTag, SlruKind};
 use crate::repository::Key;
 use crate::walrecord::ZenithWalRecord;
 use metrics::{register_histogram, register_int_counter, Histogram, IntCounter};
-use postgres_ffi::v14::nonrelfile_utils::{
-    mx_offset_to_flags_bitshift, mx_offset_to_flags_offset, mx_offset_to_member_offset,
-    transaction_id_set_status,
-};
-use postgres_ffi::v14::pg_constants;
-use postgres_ffi::BLCKSZ;
+use postgres_ffi::nonrelfile_utils::mx_offset_to_flags_bitshift;
+use postgres_ffi::nonrelfile_utils::mx_offset_to_flags_offset;
+use postgres_ffi::nonrelfile_utils::mx_offset_to_member_offset;
+use postgres_ffi::nonrelfile_utils::transaction_id_set_status;
+use postgres_ffi::pg_constants;

 ///
 /// `RelTag` + block number (`blknum`) gives us a unique id of the page in the cluster.
@@ -83,6 +82,24 @@ pub trait WalRedoManager: Send + Sync {
    ) -> Result<Bytes, WalRedoError>;
 }

+///
+/// A dummy WAL Redo Manager implementation that doesn't allow replaying
+/// anything. Currently used during bootstrapping (zenith init), to create
+/// a Repository object without launching the real WAL redo process.
+///
+pub struct DummyRedoManager {}
+impl crate::walredo::WalRedoManager for DummyRedoManager {
+    fn request_redo(
+        &self,
+        _key: Key,
+        _lsn: Lsn,
+        _base_img: Option<Bytes>,
+        _records: Vec<(Lsn, ZenithWalRecord)>,
+    ) -> Result<Bytes, WalRedoError> {
+        Err(WalRedoError::InvalidState)
+    }
+}
+
 // Metrics collected on WAL redo operations
 //
 // We collect the time spent in actual WAL redo ('redo'), and time waiting
@@ -418,10 +435,10 @@ impl PostgresRedoManager {
                }

                // Append the timestamp
-                if page.len() == BLCKSZ as usize + 8 {
-                    page.truncate(BLCKSZ as usize);
+                if page.len() == pg_constants::BLCKSZ as usize + 8 {
+                    page.truncate(pg_constants::BLCKSZ as usize);
                }
-                if page.len() == BLCKSZ as usize {
+                if page.len() == pg_constants::BLCKSZ as usize {
                    page.extend_from_slice(&timestamp.to_be_bytes());
                } else {
                    warn!(
@@ -742,7 +759,7 @@ impl PostgresRedoProcess {

        // We expect the WAL redo process to respond with an 8k page image. We read it
        // into this buffer.
-        let mut resultbuf = vec![0; BLCKSZ.into()];
+        let mut resultbuf = vec![0; pg_constants::BLCKSZ.into()];
        let mut nresult: usize = 0; // # of bytes read into 'resultbuf' so far

        // Prepare for calling poll()
@@ -755,7 +772,7 @@ impl PostgresRedoProcess {
        // We do three things simultaneously: send the old base image and WAL records to
        // the child process's stdin, read the result from child's stdout, and forward any logging
        // information that the child writes to its stderr to the page server's log.
-        while nresult < BLCKSZ.into() {
+        while nresult < pg_constants::BLCKSZ.into() {
            // If we have more data to write, wake up if 'stdin' becomes writeable or
            // we have data to read. Otherwise only wake up if there's data to read.
            let nfds = if nwrite < writebuf.len() { 3 } else { 2 };
--- a/proxy/src/auth/backend.rs
+++ b/proxy/src/auth/backend.rs
@@ -86,7 +86,7 @@ impl From<DatabaseInfo> for tokio_postgres::Config {
 /// * However, when we substitute `T` with [`ClientCredentials`],
 ///   this helps us provide the credentials only to those auth
 ///   backends which require them for the authentication process.
-#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+#[derive(Debug, Clone, Copy, PartialEq)]
 pub enum BackendType<T> {
    /// Legacy Cloud API (V1) + link auth.
    LegacyConsole(T),
--- a/proxy/src/compute.rs
+++ b/proxy/src/compute.rs
@@ -65,17 +65,8 @@ impl NodeInfo {
        // require for our business.
        let mut connection_error = None;
        let ports = self.config.get_ports();
-        let hosts = self.config.get_hosts();
-        // the ports array is supposed to have 0 entries, 1 entry, or as many entries as in the hosts array
-        if ports.len() > 1 && ports.len() != hosts.len() {
-            return Err(io::Error::new(
-                io::ErrorKind::Other,
-                format!("couldn't connect: bad compute config, ports and hosts entries' count does not match: {:?}", self.config),
-            ));
-        }
-
-        for (i, host) in hosts.iter().enumerate() {
-            let port = ports.get(i).or_else(|| ports.first()).unwrap_or(&5432);
+        for (i, host) in self.config.get_hosts().iter().enumerate() {
+            let port = ports.get(i).or_else(|| ports.get(0)).unwrap_or(&5432);
            let host = match host {
                Host::Tcp(host) => host.as_str(),
                Host::Unix(_) => continue, // unix sockets are not welcome here
--- a/proxy/src/scram/messages.rs
+++ b/proxy/src/scram/messages.rs
@@ -14,7 +14,7 @@ pub const SCRAM_RAW_NONCE_LEN: usize = 18;
 fn validate_sasl_extensions<'a>(parts: impl Iterator<Item = &'a str>) -> Option<()> {
    for mut chars in parts.map(|s| s.chars()) {
        let attr = chars.next()?;
-        if !('a'..='z').contains(&attr) && !('A'..='Z').contains(&attr) {
+        if !('a'..'z').contains(&attr) && !('A'..'Z').contains(&attr) {
            return None;
        }
        let eq = chars.next()?;
--- a/safekeeper/src/control_file_upgrade.rs
+++ b/safekeeper/src/control_file_upgrade.rs
@@ -40,7 +40,7 @@ struct SafeKeeperStateV1 {
    wal_start_lsn: Lsn,
 }

-#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
+#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
 pub struct ServerInfoV2 {
    /// Postgres server version
    pub pg_version: u32,
@@ -70,7 +70,7 @@ pub struct SafeKeeperStateV2 {
    pub wal_start_lsn: Lsn,
 }

-#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
+#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
 pub struct ServerInfoV3 {
    /// Postgres server version
    pub pg_version: u32,
--- a/safekeeper/src/handler.rs
+++ b/safekeeper/src/handler.rs
@@ -9,7 +9,7 @@ use crate::timeline::{Timeline, TimelineTools};
 use crate::SafeKeeperConf;
 use anyhow::{bail, Context, Result};

-use postgres_ffi::PG_TLI;
+use postgres_ffi::xlog_utils::PG_TLI;
 use regex::Regex;
 use std::str::FromStr;
 use std::sync::Arc;
@@ -90,10 +90,7 @@ impl postgres_backend::Handler for SafekeeperPostgresHandler {
    fn process_query(&mut self, pgb: &mut PostgresBackend, query_string: &str) -> Result<()> {
        let cmd = parse_cmd(query_string)?;

-        info!(
-            "got query {:?} in timeline {:?}",
-            query_string, self.ztimelineid
-        );
+        info!("got query {:?}", query_string);

        let create = !(matches!(cmd, SafekeeperPostgresCommand::StartReplication { .. })
            || matches!(cmd, SafekeeperPostgresCommand::IdentifySystem));
@@ -109,17 +106,23 @@ impl postgres_backend::Handler for SafekeeperPostgresHandler {
        }

        match cmd {
-            SafekeeperPostgresCommand::StartWalPush => ReceiveWalConn::new(pgb)
-                .run(self)
-                .context("failed to run ReceiveWalConn"),
-            SafekeeperPostgresCommand::StartReplication { start_lsn } => ReplicationConn::new(pgb)
-                .run(self, pgb, start_lsn)
-                .context("failed to run ReplicationConn"),
-            SafekeeperPostgresCommand::IdentifySystem => self.handle_identify_system(pgb),
-            SafekeeperPostgresCommand::JSONCtrl { ref cmd } => handle_json_ctrl(self, pgb, cmd),
+            SafekeeperPostgresCommand::StartWalPush => {
+                ReceiveWalConn::new(pgb)
+                    .run(self)
+                    .context("failed to run ReceiveWalConn")?;
+            }
+            SafekeeperPostgresCommand::StartReplication { start_lsn } => {
+                ReplicationConn::new(pgb)
+                    .run(self, pgb, start_lsn)
+                    .context("failed to run ReplicationConn")?;
+            }
+            SafekeeperPostgresCommand::IdentifySystem => {
+                self.handle_identify_system(pgb)?;
+            }
+            SafekeeperPostgresCommand::JSONCtrl { ref cmd } => {
+                handle_json_ctrl(self, pgb, cmd)?;
+            }
        }
-        .context(format!("timeline {timelineid}"))?;
-
        Ok(())
    }
 }
@@ -150,15 +153,8 @@ impl SafekeeperPostgresHandler {
    /// Handle IDENTIFY_SYSTEM replication command
    ///
    fn handle_identify_system(&mut self, pgb: &mut PostgresBackend) -> Result<()> {
-        let lsn = if self.is_walproposer_recovery() {
-            // walproposer should get all local WAL until flush_lsn
-            self.timeline.get().get_end_of_wal()
-        } else {
-            // other clients shouldn't get any uncommitted WAL
-            self.timeline.get().get_state().0.commit_lsn
-        }
-        .to_string();
-
+        let start_pos = self.timeline.get().get_end_of_wal();
+        let lsn = start_pos.to_string();
        let sysid = self
            .timeline
            .get()
@@ -207,11 +203,4 @@ impl SafekeeperPostgresHandler {
        .write_message(&BeMessage::CommandComplete(b"IDENTIFY_SYSTEM"))?;
        Ok(())
    }
-
-    /// Returns true if current connection is a replication connection, originating
-    /// from a walproposer recovery function. This connection gets a special handling:
-    /// safekeeper must stream all local WAL till the flush_lsn, whether committed or not.
-    pub fn is_walproposer_recovery(&self) -> bool {
-        self.appname == Some("wal_proposer_recovery".to_string())
-    }
 }
--- a/safekeeper/src/json_ctrl.rs
+++ b/safekeeper/src/json_ctrl.rs
@@ -7,7 +7,8 @@
 //!

 use anyhow::Result;
-use bytes::Bytes;
+use bytes::{BufMut, Bytes, BytesMut};
+use crc32c::crc32c_append;
 use serde::{Deserialize, Serialize};
 use tracing::*;

@@ -18,8 +19,9 @@ use crate::safekeeper::{
 };
 use crate::safekeeper::{SafeKeeperState, Term, TermHistory, TermSwitchEntry};
 use crate::timeline::TimelineTools;
-use postgres_ffi::v14::pg_constants;
-use postgres_ffi::v14::xlog_utils;
+use postgres_ffi::pg_constants;
+use postgres_ffi::xlog_utils;
+use postgres_ffi::{uint32, uint64, Oid, XLogRecord};
 use utils::{
    lsn::Lsn,
    postgres_backend::PostgresBackend,
@@ -142,7 +144,7 @@ fn append_logical_message(
    spg: &mut SafekeeperPostgresHandler,
    msg: &AppendLogicalMessage,
 ) -> Result<InsertedWAL> {
-    let wal_data = xlog_utils::encode_logical_message(&msg.lm_prefix, &msg.lm_message);
+    let wal_data = encode_logical_message(&msg.lm_prefix, &msg.lm_message);
    let sk_state = spg.timeline.get().get_state().1;

    let begin_lsn = msg.begin_lsn;
@@ -180,3 +182,90 @@ fn append_logical_message(
        append_response,
    })
 }
+
+#[repr(C)]
+#[derive(Debug, Clone, Default, Serialize, Deserialize)]
+struct XlLogicalMessage {
+    db_id: Oid,
+    transactional: uint32, // bool, takes 4 bytes due to alignment in C structures
+    prefix_size: uint64,
+    message_size: uint64,
+}
+
+impl XlLogicalMessage {
+    pub fn encode(&self) -> Bytes {
+        use utils::bin_ser::LeSer;
+        self.ser().unwrap().into()
+    }
+}
+
+/// Create new WAL record for non-transactional logical message.
+/// Used for creating artificial WAL for tests, as LogicalMessage
+/// record is basically no-op.
+fn encode_logical_message(prefix: &str, message: &str) -> Vec<u8> {
+    let mut prefix_bytes = BytesMut::with_capacity(prefix.len() + 1);
+    prefix_bytes.put(prefix.as_bytes());
+    prefix_bytes.put_u8(0);
+
+    let message_bytes = message.as_bytes();
+
+    let logical_message = XlLogicalMessage {
+        db_id: 0,
+        transactional: 0,
+        prefix_size: prefix_bytes.len() as u64,
+        message_size: message_bytes.len() as u64,
+    };
+
+    let mainrdata = logical_message.encode();
+    let mainrdata_len: usize = mainrdata.len() + prefix_bytes.len() + message_bytes.len();
+    // only short mainrdata is supported for now
+    assert!(mainrdata_len <= 255);
+    let mainrdata_len = mainrdata_len as u8;
+
+    let mut data: Vec<u8> = vec![pg_constants::XLR_BLOCK_ID_DATA_SHORT, mainrdata_len];
+    data.extend_from_slice(&mainrdata);
+    data.extend_from_slice(&prefix_bytes);
+    data.extend_from_slice(message_bytes);
+
+    let total_len = xlog_utils::XLOG_SIZE_OF_XLOG_RECORD + data.len();
+
+    let mut header = XLogRecord {
+        xl_tot_len: total_len as u32,
+        xl_xid: 0,
+        xl_prev: 0,
+        xl_info: 0,
+        xl_rmid: 21,
+        __bindgen_padding_0: [0u8; 2usize],
+        xl_crc: 0, // crc will be calculated later
+    };
+
+    let header_bytes = header.encode().expect("failed to encode header");
+    let crc = crc32c_append(0, &data);
+    let crc = crc32c_append(crc, &header_bytes[0..xlog_utils::XLOG_RECORD_CRC_OFFS]);
+    header.xl_crc = crc;
+
+    let mut wal: Vec<u8> = Vec::new();
+    wal.extend_from_slice(&header.encode().expect("failed to encode header"));
+    wal.extend_from_slice(&data);
+
+    // WAL start position must be aligned at 8 bytes,
+    // this will add padding for the next WAL record.
+    const PADDING: usize = 8;
+    let padding_rem = wal.len() % PADDING;
+    if padding_rem != 0 {
+        wal.resize(wal.len() + PADDING - padding_rem, 0);
+    }
+
+    wal
+}
+
+#[test]
+fn test_encode_logical_message() {
+    let expected = [
+        64, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 21, 0, 0, 170, 34, 166, 227, 255, 38,
+        0, 0, 0, 0, 0, 0, 0, 0, 7, 0, 0, 0, 0, 0, 0, 0, 7, 0, 0, 0, 0, 0, 0, 0, 112, 114, 101, 102,
+        105, 120, 0, 109, 101, 115, 115, 97, 103, 101,
+    ];
+    let actual = encode_logical_message("prefix", "message");
+    assert_eq!(expected, actual[..]);
+}
--- a/safekeeper/src/metrics.rs
+++ b/safekeeper/src/metrics.rs
@@ -7,7 +7,7 @@ use metrics::{
    proto::MetricFamily,
    Gauge, IntGaugeVec,
 };
-use postgres_ffi::v14::xlog_utils::XLogSegNo;
+use postgres_ffi::xlog_utils::XLogSegNo;
 use utils::{lsn::Lsn, zid::ZTenantTimelineId};

 use crate::{
--- a/safekeeper/src/safekeeper.rs
+++ b/safekeeper/src/safekeeper.rs
@@ -5,7 +5,9 @@ use byteorder::{LittleEndian, ReadBytesExt};
 use bytes::{Buf, BufMut, Bytes, BytesMut};

 use etcd_broker::subscription_value::SkTimelineInfo;
-use postgres_ffi::v14::xlog_utils::{TimeLineID, XLogSegNo, MAX_SEND_SIZE};
+use postgres_ffi::xlog_utils::TimeLineID;
+
+use postgres_ffi::xlog_utils::XLogSegNo;
 use serde::{Deserialize, Serialize};
 use std::cmp::max;
 use std::cmp::min;
@@ -17,6 +19,7 @@ use crate::control_file;
 use crate::send_wal::HotStandbyFeedback;

 use crate::wal_storage;
+use postgres_ffi::xlog_utils::MAX_SEND_SIZE;
 use utils::{
    bin_ser::LeSer,
    lsn::Lsn,
@@ -124,7 +127,7 @@ impl AcceptorState {

 /// Information about Postgres. Safekeeper gets it once and then verifies
 /// all further connections from computes match.
-#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
+#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
 pub struct ServerInfo {
    /// Postgres server version
    pub pg_version: u32,
--- a/safekeeper/src/send_wal.rs
+++ b/safekeeper/src/send_wal.rs
@@ -6,7 +6,7 @@ use crate::timeline::{ReplicaState, Timeline, TimelineTools};
 use crate::wal_storage::WalReader;
 use anyhow::{bail, Context, Result};

-use postgres_ffi::v14::xlog_utils::{get_current_timestamp, TimestampTz, MAX_SEND_SIZE};
+use postgres_ffi::xlog_utils::{get_current_timestamp, TimestampTz, MAX_SEND_SIZE};

 use bytes::Bytes;
 use serde::{Deserialize, Serialize};
@@ -36,7 +36,7 @@ const NEON_STATUS_UPDATE_TAG_BYTE: u8 = b'z';
 type FullTransactionId = u64;

 /// Hot standby feedback received from replica
-#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
+#[derive(Debug, Clone, Copy, PartialEq, Serialize, Deserialize)]
 pub struct HotStandbyFeedback {
    pub ts: TimestampTz,
    pub xmin: FullTransactionId,
@@ -170,7 +170,6 @@ impl ReplicationConn {
        // spawn the background thread which receives HotStandbyFeedback messages.
        let bg_timeline = Arc::clone(spg.timeline.get());
        let bg_stream_in = self.stream_in.take().unwrap();
-        let bg_timeline_id = spg.ztimelineid.unwrap();

        let state = ReplicaState::new();
        // This replica_id is used below to check if it's time to stop replication.
@@ -189,8 +188,6 @@ impl ReplicationConn {
        let _ = thread::Builder::new()
            .name("HotStandbyFeedback thread".into())
            .spawn(move || {
-                let _enter =
-                    info_span!("HotStandbyFeedback thread", timeline = %bg_timeline_id).entered();
                if let Err(err) = Self::background_thread(bg_stream_in, bg_replica_guard) {
                    error!("Replication background thread failed: {}", err);
                }
@@ -201,12 +198,13 @@ impl ReplicationConn {
            .build()?;

        runtime.block_on(async move {
-            let (inmem_state, persisted_state) = spg.timeline.get().get_state();
+            let (_, persisted_state) = spg.timeline.get().get_state();
            // add persisted_state.timeline_start_lsn == Lsn(0) check
            if persisted_state.server.wal_seg_size == 0 {
                bail!("Cannot start replication before connecting to walproposer");
            }

+            let wal_end = spg.timeline.get().get_end_of_wal();
            // Walproposer gets special handling: safekeeper must give proposer all
            // local WAL till the end, whether committed or not (walproposer will
            // hang otherwise). That's because walproposer runs the consensus and
@@ -216,8 +214,8 @@ impl ReplicationConn {
            // another compute rises which collects majority and starts fixing log
            // on this safekeeper itself. That's ok as (old) proposer will never be
            // able to commit such WAL.
-            let stop_pos: Option<Lsn> = if spg.is_walproposer_recovery() {
-                let wal_end = spg.timeline.get().get_end_of_wal();
+            let stop_pos: Option<Lsn> = if spg.appname == Some("wal_proposer_recovery".to_string())
+            {
                Some(wal_end)
            } else {
                None
@@ -228,7 +226,7 @@ impl ReplicationConn {
            // switch to copy
            pgb.write_message(&BeMessage::CopyBothResponse)?;

-            let mut end_pos = stop_pos.unwrap_or(inmem_state.commit_lsn);
+            let mut end_pos = Lsn(0);

            let mut wal_reader = WalReader::new(
                spg.conf.timeline_dir(&spg.timeline.get().zttid),
--- a/safekeeper/src/timeline.rs
+++ b/safekeeper/src/timeline.rs
@@ -4,9 +4,8 @@
 use anyhow::{bail, Context, Result};

 use etcd_broker::subscription_value::SkTimelineInfo;
-
 use once_cell::sync::Lazy;
-use postgres_ffi::v14::xlog_utils::XLogSegNo;
+use postgres_ffi::xlog_utils::XLogSegNo;

 use serde::Serialize;
 use tokio::sync::watch;
--- a/safekeeper/src/wal_backup.rs
+++ b/safekeeper/src/wal_backup.rs
@@ -11,8 +11,7 @@ use std::pin::Pin;
 use std::sync::Arc;
 use std::time::Duration;

-use postgres_ffi::v14::xlog_utils::{XLogFileName, XLogSegNo, XLogSegNoOffsetToRecPtr};
-use postgres_ffi::PG_TLI;
+use postgres_ffi::xlog_utils::{XLogFileName, XLogSegNo, XLogSegNoOffsetToRecPtr, PG_TLI};
 use remote_storage::{GenericRemoteStorage, RemoteStorage};
 use tokio::fs::File;
 use tokio::runtime::Builder;
--- a/safekeeper/src/wal_storage.rs
+++ b/safekeeper/src/wal_storage.rs
@@ -13,10 +13,9 @@ use std::pin::Pin;
 use tokio::io::AsyncRead;

 use once_cell::sync::Lazy;
-use postgres_ffi::v14::xlog_utils::{
-    find_end_of_wal, IsPartialXLogFileName, IsXLogFileName, XLogFromFileName, XLogSegNo,
+use postgres_ffi::xlog_utils::{
+    find_end_of_wal, IsPartialXLogFileName, IsXLogFileName, XLogFromFileName, XLogSegNo, PG_TLI,
 };
-use postgres_ffi::PG_TLI;
 use std::cmp::min;

 use std::fs::{self, remove_file, File, OpenOptions};
@@ -31,10 +30,9 @@ use crate::safekeeper::SafeKeeperState;

 use crate::wal_backup::read_object;
 use crate::SafeKeeperConf;
-use postgres_ffi::v14::xlog_utils::XLogFileName;
-use postgres_ffi::XLOG_BLCKSZ;
+use postgres_ffi::xlog_utils::{XLogFileName, XLOG_BLCKSZ};

-use postgres_ffi::v14::waldecoder::WalStreamDecoder;
+use postgres_ffi::waldecoder::WalStreamDecoder;

 use metrics::{register_histogram_vec, Histogram, HistogramVec, DISK_WRITE_SECONDS_BUCKETS};

--- a/setup.cfg
+++ b/setup.cfg
@@ -18,10 +18,6 @@ exclude = ^vendor/
 # some tests don't typecheck when this flag is set
 check_untyped_defs = false

-# Help mypy find imports when running against list of individual files.
-# Without this line it would behave differently when executed on the entire project.
-mypy_path = $MYPY_CONFIG_FILE_DIR:$MYPY_CONFIG_FILE_DIR/test_runner
-
 disallow_incomplete_defs = false
 disallow_untyped_calls = false
 disallow_untyped_decorators = false
--- a/test_runner/batch_others/test_pageserver_api.py
+++ b/test_runner/batch_others/test_pageserver_api.py
@@ -1,11 +1,7 @@
 from typing import Optional
 from uuid import uuid4, UUID
 import pytest
-import pathlib
-import os
-import subprocess
 from fixtures.utils import lsn_from_hex
-from fixtures.log_helper import log
 from fixtures.neon_fixtures import (
    DEFAULT_BRANCH_NAME,
    NeonEnv,
@@ -13,43 +9,16 @@ from fixtures.neon_fixtures import (
    NeonPageserverHttpClient,
    NeonPageserverApiException,
    wait_until,
-    neon_binpath,
-    pg_distrib_dir,
 )


-# test that we cannot override node id after init
-def test_pageserver_init_node_id(neon_simple_env: NeonEnv):
-    repo_dir = neon_simple_env.repo_dir
-    pageserver_config = repo_dir / 'pageserver.toml'
-    pageserver_bin = pathlib.Path(neon_binpath) / 'pageserver'
-    run_pageserver = lambda args: subprocess.run([str(pageserver_bin), '-D', str(repo_dir), *args],
-                                                 check=False,
-                                                 universal_newlines=True,
-                                                 stdout=subprocess.PIPE,
-                                                 stderr=subprocess.PIPE)
-
-    # remove initial config
-    pageserver_config.unlink()
-
-    bad_init = run_pageserver(['--init', '-c', f'pg_distrib_dir="{pg_distrib_dir}"'])
-    assert bad_init.returncode == 1, 'pageserver should not be able to init new config without the node id'
-    assert "missing id" in bad_init.stderr
-    assert not pageserver_config.exists(), 'config file should not be created after init error'
-
-    completed_init = run_pageserver(
-        ['--init', '-c', 'id = 12345', '-c', f'pg_distrib_dir="{pg_distrib_dir}"'])
-    assert completed_init.returncode == 0, 'pageserver should be able to create a new config with the node id given'
-    assert pageserver_config.exists(), 'config file should be created successfully'
-
-    bad_reinit = run_pageserver(
-        ['--init', '-c', 'id = 12345', '-c', f'pg_distrib_dir="{pg_distrib_dir}"'])
-    assert bad_reinit.returncode == 1, 'pageserver should not be able to init new config without the node id'
-    assert "already exists, cannot init it" in bad_reinit.stderr
-
-    bad_update = run_pageserver(['--update-config', '-c', 'id = 3'])
-    assert bad_update.returncode == 1, 'pageserver should not allow updating node id'
-    assert "has node id already, it cannot be overridden" in bad_update.stderr
+# test that we cannot override node id
+def test_pageserver_init_node_id(neon_env_builder: NeonEnvBuilder):
+    env = neon_env_builder.init()
+    with pytest.raises(
+            Exception,
+            match="node id can only be set during pageserver init and cannot be overridden"):
+        env.pageserver.start(overrides=['--pageserver-config-override=id=10'])


 def check_client(client: NeonPageserverHttpClient, initial_tenant: UUID):
--- a/test_runner/batch_others/test_readonly_node.py
+++ b/test_runner/batch_others/test_readonly_node.py
@@ -1,9 +1,7 @@
 import pytest
 from fixtures.log_helper import log
-from fixtures.neon_fixtures import NeonEnv, wait_for_last_record_lsn, wait_for_upload
-from fixtures.utils import lsn_from_hex, lsn_to_hex, query_scalar
-import time
-from uuid import UUID
+from fixtures.neon_fixtures import NeonEnv
+from fixtures.utils import query_scalar


 #
@@ -92,49 +90,3 @@ def test_readonly_node(neon_simple_env: NeonEnv):
        env.postgres.create_start(branch_name='test_readonly_node',
                                  node_name='test_readonly_node_preinitdb',
                                  lsn='0/42')
-
-# Similar test, but with more data, and we force checkpoints
-def test_timetravel(neon_simple_env: NeonEnv):
-    env = neon_simple_env
-    env.neon_cli.create_branch('test_timetravel', 'empty')
-    pg = env.postgres.create_start('test_timetravel')
-
-    client = env.pageserver.http_client()
-
-    tenant_id = pg.safe_psql("show neon.tenant_id")[0][0]
-    timeline_id = pg.safe_psql("show neon.timeline_id")[0][0]
-
-    lsns = []
-
-    with pg.cursor() as cur:
-        cur.execute(f"""
-        CREATE TABLE testtab(id serial primary key, iteration int, data text);
-        INSERT INTO testtab (iteration, data) SELECT 0, 'data' FROM generate_series(1, 100000);
-        """)
-        current_lsn = lsn_from_hex(query_scalar(cur, "SELECT pg_current_wal_flush_lsn()"))
-    lsns.append((0, current_lsn))
-
-    for i in range(1, 5):
-        with pg.cursor() as cur:
-            cur.execute(f'UPDATE testtab SET iteration = {i}')
-            current_lsn = lsn_from_hex(query_scalar(cur, "SELECT pg_current_wal_flush_lsn()"))
-        lsns.append((i, current_lsn))
-
-        # wait until pageserver receives that data
-        wait_for_last_record_lsn(client, UUID(tenant_id), UUID(timeline_id), current_lsn)
-
-        # run checkpoint manually to force a new layer file
-        env.pageserver.safe_psql(f"checkpoint {tenant_id} {timeline_id}")
-
-    ##### Restart pageserver
-    env.postgres.stop_all()
-    env.pageserver.stop()
-    env.pageserver.start()
-
-    for (i, lsn) in lsns:
-        pg_old = env.postgres.create_start(branch_name='test_timetravel',
-                                           node_name=f'test_old_lsn_{i}',
-                                           lsn=lsn_to_hex(lsn))
-        with pg_old.cursor() as cur:
-            assert query_scalar(cur, f"select count(*) from testtab where iteration={i}") == 100000
-            assert query_scalar(cur, f"select count(*) from testtab where iteration<>{i}") == 0
--- a/test_runner/batch_others/test_setup.py
+++ b/test_runner/batch_others/test_setup.py
@@ -1,17 +0,0 @@
-"""Tests for the code in test fixtures"""
-
-from fixtures.neon_fixtures import NeonEnvBuilder
-
-
-# Test that pageserver and safekeeper can restart quickly.
-# This is a regression test, see https://github.com/neondatabase/neon/issues/2247
-def test_fixture_restart(neon_env_builder: NeonEnvBuilder):
-    env = neon_env_builder.init_start()
-
-    for i in range(3):
-        env.pageserver.stop()
-        env.pageserver.start()
-
-    for i in range(3):
-        env.safekeepers[0].stop()
-        env.safekeepers[0].start()
--- a/test_runner/batch_others/test_tenant_relocation.py
+++ b/test_runner/batch_others/test_tenant_relocation.py
@@ -44,22 +44,30 @@ def new_pageserver_helper(new_pageserver_dir: pathlib.Path,
    cannot use NeonPageserver yet because it depends on neon cli
    which currently lacks support for multiple pageservers
    """
-    # actually run new pageserver
    cmd = [
        str(pageserver_bin),
+        '--init',
        '--workdir',
        str(new_pageserver_dir),
-        '--daemonize',
-        '--update-config',
        f"-c listen_pg_addr='localhost:{pg_port}'",
        f"-c listen_http_addr='localhost:{http_port}'",
        f"-c pg_distrib_dir='{pg_distrib_dir}'",
        f"-c id=2",
        f"-c remote_storage={{local_path='{remote_storage_mock_path}'}}",
    ]
+
    if broker is not None:
        cmd.append(f"-c broker_endpoints=['{broker.client_url()}']", )

+    subprocess.check_output(cmd, text=True)
+
+    # actually run new pageserver
+    cmd = [
+        str(pageserver_bin),
+        '--workdir',
+        str(new_pageserver_dir),
+        '--daemonize',
+    ]
    log.info("starting new pageserver %s", cmd)
    out = subprocess.check_output(cmd, text=True)
    log.info("started new pageserver %s", out)
--- a/test_runner/batch_others/test_wal_acceptor.py
+++ b/test_runner/batch_others/test_wal_acceptor.py
@@ -569,7 +569,7 @@ class ProposerPostgres(PgProtocol):
                f"neon.timeline_id = '{self.timeline_id.hex}'\n",
                f"neon.tenant_id = '{self.tenant_id.hex}'\n",
                f"neon.pageserver_connstring = ''\n",
-                f"neon.safekeepers = '{safekeepers}'\n",
+                f"safekeepers = '{safekeepers}'\n",
                f"listen_addresses = '{self.listen_addr}'\n",
                f"port = '{self.port}'\n",
            ]
--- a/test_runner/fixtures/neon_fixtures.py
+++ b/test_runner/fixtures/neon_fixtures.py
@@ -1855,11 +1855,11 @@ class Postgres(PgProtocol):
                # walproposer uses different application_name
                if ("synchronous_standby_names" in cfg_line or
                        # don't repeat safekeepers/wal_acceptors multiple times
-                        "neon.safekeepers" in cfg_line):
+                        "safekeepers" in cfg_line):
                    continue
                f.write(cfg_line)
            f.write("synchronous_standby_names = 'walproposer'\n")
-            f.write("neon.safekeepers = '{}'\n".format(safekeepers))
+            f.write("safekeepers = '{}'\n".format(safekeepers))
        return self

    def config(self, lines: List[str]) -> 'Postgres':
--- a/vendor/postgres
+++ b/vendor/postgres