Refactor WIP

.cargo/config.toml

@@ -11,6 +11,3 @@ opt-level = 3
 [profile.dev]
 # Turn on a small amount of optimization in Development mode.
 opt-level = 1
-
-[alias]
-build_testing = ["build", "--features", "testing"]

.dockerignore

@@ -1,22 +1,18 @@
-*
+**/.git/
+**/__pycache__
+**/.pytest_cache
 
-!rust-toolchain.toml
-!Cargo.toml
-!Cargo.lock
-!Makefile
+.git
+target
+tmp_check
+tmp_install
+tmp_check_cli
+test_output
+.vscode
+.neon
+integration_tests/.neon
+.mypy_cache
+
+Dockerfile
+.dockerignore
 
-!broker/
-!.cargo/
-!.config/
-!control_plane/
-!compute_tools/
-!libs/
-!pageserver/
-!pgxn/
-!proxy/
-!safekeeper/
-!vendor/postgres-v14/
-!vendor/postgres-v15/
-!workspace_hack/
-!neon_local/
-!scripts/ninstall.sh

.git-blame-ignore-revs

@@ -1 +0,0 @@
-4c2bb43775947775401cbb9d774823c5723a91f8

.github/ISSUE_TEMPLATE/bug-template.md

@@ -1,23 +0,0 @@
----
-name: Bug Template
-about: Used for describing bugs
-title: ''
-labels: t/bug
-assignees: ''
-
----
-
-## Steps to reproduce
-
-
-## Expected result
-
-
-## Actual result
-
-
-## Environment
-
-
-## Logs, links
-- 

.github/ISSUE_TEMPLATE/epic-template.md

@@ -1,25 +0,0 @@
----
-name: Epic Template
-about: A set of related tasks contributing towards specific outcome, comprising of
-  more than 1 week of work.
-title: 'Epic: '
-labels: t/Epic
-assignees: ''
-
----
-
-## Motivation
-
-
-## DoD
-
-
-## Implementation ideas
-
-
-## Tasks
-- [ ]
-
-
-## Other related tasks and Epics
-- 

.github/PULL_REQUEST_TEMPLATE/release-pr.md

@@ -1,20 +0,0 @@
-## Release 202Y-MM-DD
-
-**NB: this PR must be merged only by 'Create a merge commit'!**
-
-### Checklist when preparing for release
-- [ ] Read or refresh [the release flow guide](https://github.com/neondatabase/cloud/wiki/Release:-general-flow)
-- [ ] Ask in the [cloud Slack channel](https://neondb.slack.com/archives/C033A2WE6BZ) that you are going to rollout the release. Any blockers?
-- [ ] Does this release contain any db migrations? Destructive ones? What is the rollback plan?
-
-<!-- List everything that should be done **before** release, any issues / setting changes / etc -->
-
-### Checklist after release
-- [ ] Based on the merged commits write release notes and open a PR into `website` repo ([example](https://github.com/neondatabase/website/pull/219/files))
-- [ ] Check [#dev-production-stream](https://neondb.slack.com/archives/C03F5SM1N02) Slack channel
-- [ ] Check [stuck projects page](https://console.neon.tech/admin/projects?sort=last_active&order=desc&stuck=true)
-- [ ] Check [recent operation failures](https://console.neon.tech/admin/operations?action=create_timeline%2Cstart_compute%2Cstop_compute%2Csuspend_compute%2Capply_config%2Cdelete_timeline%2Cdelete_tenant%2Ccreate_branch%2Ccheck_availability&sort=updated_at&order=desc&had_retries=some)
-- [ ] Check [cloud SLO dashboard](https://observer.zenith.tech/d/_oWcBMJ7k/cloud-slos?orgId=1)
-- [ ] Check [compute startup metrics dashboard](https://observer.zenith.tech/d/5OkYJEmVz/compute-startup-time)
-
-<!-- List everything that should be done **after** release, any admin UI configuration / Grafana dashboard / alert changes / setting changes / etc -->

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

@@ -1,221 +0,0 @@
-name: 'Create Allure report'
-description: 'Create and publish Allure report'
-
-inputs:
-  action:
-    desctiption: 'generate or store'
-    required: true
-  build_type:
-    description: '`build_type` from run-python-test-set action'
-    required: true
-  test_selection:
-    description: '`test_selector` from run-python-test-set action'
-    required: false
-outputs:
-  report-url:
-    description: 'Allure report URL'
-    value: ${{ steps.generate-report.outputs.report-url }}
-
-runs:
-  using: "composite"
-  steps:
-    - name: Validate input parameters
-      shell: bash -euxo pipefail {0}
-      run: |
-        if [ "${{ inputs.action }}" != "store" ] && [ "${{ inputs.action }}" != "generate" ]; then
-          echo 2>&1 "Unknown inputs.action type '${{ inputs.action }}'; allowed 'generate' or 'store' only"
-          exit 1
-        fi
-
-        if [ -z "${{ inputs.test_selection }}" ] && [ "${{ inputs.action }}" == "store" ]; then
-          echo 2>&1 "inputs.test_selection must be set for 'store' action"
-          exit 2
-        fi
-
-    - name: Calculate key
-      id: calculate-key
-      shell: bash -euxo pipefail {0}
-      run: |
-        # TODO: for manually triggered workflows (via workflow_dispatch) we need to have a separate key
-
-        pr_number=$(jq --raw-output .pull_request.number "$GITHUB_EVENT_PATH" || true)
-        if [ "${pr_number}" != "null" ]; then
-          key=pr-${pr_number}
-        elif [ "${GITHUB_REF}" = "refs/heads/main" ]; then
-          # Shortcut for a special branch
-          key=main
-        else
-          key=branch-$(echo ${GITHUB_REF#refs/heads/} | tr -c "[:alnum:]._-" "-")
-        fi
-        echo "KEY=${key}" >> $GITHUB_OUTPUT
-
-    - uses: actions/setup-java@v3
-      if: ${{ inputs.action == 'generate' }}
-      with:
-        distribution: 'temurin'
-        java-version: '17'
-
-    - name: Install Allure
-      if: ${{ inputs.action == 'generate' }}
-      shell: bash -euxo pipefail {0}
-      run: |
-        if ! which allure; then
-          ALLURE_ZIP=allure-${ALLURE_VERSION}.zip
-          wget -q https://github.com/allure-framework/allure2/releases/download/${ALLURE_VERSION}/${ALLURE_ZIP}
-          echo "${ALLURE_ZIP_MD5}  ${ALLURE_ZIP}" | md5sum -c
-          unzip -q ${ALLURE_ZIP}
-          echo "$(pwd)/allure-${ALLURE_VERSION}/bin" >> $GITHUB_PATH
-          rm -f ${ALLURE_ZIP}
-        fi
-      env:
-        ALLURE_VERSION: 2.19.0
-        ALLURE_ZIP_MD5: ced21401a1a8b9dfb68cee9e4c210464
-
-    - name: Upload Allure results
-      if: ${{ inputs.action == 'store' }}
-      env:
-        REPORT_PREFIX: reports/${{ steps.calculate-key.outputs.KEY }}/${{ inputs.build_type }}
-        RAW_PREFIX: reports-raw/${{ steps.calculate-key.outputs.KEY }}/${{ inputs.build_type }}
-        TEST_OUTPUT: /tmp/test_output
-        BUCKET: neon-github-public-dev
-      shell: bash -euxo pipefail {0}
-      run: |
-        # Add metadata
-        cat <<EOF > $TEST_OUTPUT/allure/results/executor.json
-          {
-            "name": "GitHub Actions",
-            "type": "github",
-            "url": "https://${BUCKET}.s3.amazonaws.com/${REPORT_PREFIX}/latest/index.html",
-            "buildOrder": ${GITHUB_RUN_ID},
-            "buildName": "GitHub Actions Run #${{ github.run_number }}/${GITHUB_RUN_ATTEMPT}",
-            "buildUrl": "${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID}/attempts/${GITHUB_RUN_ATTEMPT}",
-            "reportUrl": "https://${BUCKET}.s3.amazonaws.com/${REPORT_PREFIX}/${GITHUB_RUN_ID}/index.html",
-            "reportName": "Allure Report"
-          }
-        EOF
-        cat <<EOF > $TEST_OUTPUT/allure/results/environment.properties
-          TEST_SELECTION=${{ inputs.test_selection }}
-          BUILD_TYPE=${{ inputs.build_type }}
-        EOF
-
-        ARCHIVE="${GITHUB_RUN_ID}-${{ inputs.test_selection }}-${GITHUB_RUN_ATTEMPT}-$(date +%s).tar.zst"
-        ZSTD_NBTHREADS=0
-
-        tar -C ${TEST_OUTPUT}/allure/results -cf ${ARCHIVE} --zstd .
-        aws s3 mv --only-show-errors ${ARCHIVE} "s3://${BUCKET}/${RAW_PREFIX}/${ARCHIVE}"
-
-    # Potentially we could have several running build for the same key (for example for the main branch),  so we use improvised lock for this
-    - name: Acquire Allure lock
-      if: ${{ inputs.action == 'generate' }}
-      shell: bash -euxo pipefail {0}
-      env:
-        LOCK_FILE: reports/${{ steps.calculate-key.outputs.KEY }}/lock.txt
-        BUCKET: neon-github-public-dev
-      run: |
-        LOCK_TIMEOUT=300 # seconds
-
-        for _ in $(seq 1 5); do
-          for i in $(seq 1 ${LOCK_TIMEOUT}); do
-            LOCK_ADDED=$(aws s3api head-object --bucket neon-github-public-dev --key ${LOCK_FILE} | jq --raw-output '.LastModified' || true)
-            # `date --date="..."` is supported only by gnu date (i.e. it doesn't work on BSD/macOS)
-            if [ -z "${LOCK_ADDED}" ] || [ "$(( $(date +%s) - $(date --date="${LOCK_ADDED}" +%s) ))" -gt "${LOCK_TIMEOUT}" ]; then
-              break
-            fi
-            sleep 1
-          done
-          echo "${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}-${{ inputs.test_selection }}" > lock.txt
-          aws s3 mv --only-show-errors lock.txt "s3://${BUCKET}/${LOCK_FILE}"
-
-          # A double-check that exactly WE have acquired the lock
-          aws s3 cp --only-show-errors "s3://${BUCKET}/${LOCK_FILE}" ./lock.txt
-          if [ "$(cat lock.txt)" = "${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}-${{ inputs.test_selection }}" ]; then
-            break
-          fi
-        done
-
-    - name: Generate and publish final Allure report
-      if: ${{ inputs.action == 'generate' }}
-      id: generate-report
-      env:
-        REPORT_PREFIX: reports/${{ steps.calculate-key.outputs.KEY }}/${{ inputs.build_type }}
-        RAW_PREFIX: reports-raw/${{ steps.calculate-key.outputs.KEY }}/${{ inputs.build_type }}
-        TEST_OUTPUT: /tmp/test_output
-        BUCKET: neon-github-public-dev
-      shell: bash -euxo pipefail {0}
-      run: |
-        # Get previously uploaded data for this run
-        ZSTD_NBTHREADS=0
-
-        s3_filepaths=$(aws s3api list-objects-v2 --bucket ${BUCKET} --prefix ${RAW_PREFIX}/${GITHUB_RUN_ID}- | jq --raw-output  '.Contents[].Key')
-        if [ -z "$s3_filepaths" ]; then
-          # There's no previously uploaded data for this run
-          exit 0
-        fi
-        for s3_filepath in ${s3_filepaths}; do
-          aws s3 cp --only-show-errors "s3://${BUCKET}/${s3_filepath}" "${TEST_OUTPUT}/allure/"
-
-          archive=${TEST_OUTPUT}/allure/$(basename $s3_filepath)
-          mkdir -p ${archive%.tar.zst}
-          tar -xf ${archive} -C ${archive%.tar.zst}
-          rm -f ${archive}
-        done
-
-        # Get history trend
-        aws s3 cp --recursive --only-show-errors "s3://${BUCKET}/${REPORT_PREFIX}/latest/history" "${TEST_OUTPUT}/allure/latest/history" || true
-
-        # Generate report
-        allure generate --clean --output $TEST_OUTPUT/allure/report $TEST_OUTPUT/allure/*
-
-        # Replace a logo link with a redirect to the latest version of the report
-        sed -i 's|<a href="." class=|<a href="https://'${BUCKET}'.s3.amazonaws.com/'${REPORT_PREFIX}'/latest/index.html" class=|g' $TEST_OUTPUT/allure/report/app.js
-
-        # Upload a history and the final report (in this particular order to not to have duplicated history in 2 places)
-        aws s3 mv --recursive --only-show-errors "${TEST_OUTPUT}/allure/report/history" "s3://${BUCKET}/${REPORT_PREFIX}/latest/history"
-        aws s3 mv --recursive --only-show-errors "${TEST_OUTPUT}/allure/report" "s3://${BUCKET}/${REPORT_PREFIX}/${GITHUB_RUN_ID}"
-
-        REPORT_URL=https://${BUCKET}.s3.amazonaws.com/${REPORT_PREFIX}/${GITHUB_RUN_ID}/index.html
-
-        # Generate redirect
-        cat <<EOF > ./index.html
-          <!DOCTYPE html>
-
-          <meta charset="utf-8">
-          <title>Redirecting to ${REPORT_URL}</title>
-          <meta http-equiv="refresh" content="0; URL=${REPORT_URL}">
-        EOF
-        aws s3 cp --only-show-errors ./index.html "s3://${BUCKET}/${REPORT_PREFIX}/latest/index.html"
-
-        echo "[Allure Report](${REPORT_URL})" >> ${GITHUB_STEP_SUMMARY}
-        echo "report-url=${REPORT_URL}" >> $GITHUB_OUTPUT
-
-    - name: Release Allure lock
-      if: ${{ inputs.action == 'generate' && always() }}
-      shell: bash -euxo pipefail {0}
-      env:
-        LOCK_FILE: reports/${{ steps.calculate-key.outputs.KEY }}/lock.txt
-        BUCKET: neon-github-public-dev
-      run: |
-        aws s3 cp --only-show-errors "s3://${BUCKET}/${LOCK_FILE}" ./lock.txt || exit 0
-
-        if [ "$(cat lock.txt)" = "${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}-${{ inputs.test_selection }}" ]; then
-          aws s3 rm "s3://${BUCKET}/${LOCK_FILE}"
-        fi
-
-    - uses: actions/github-script@v6
-      if: ${{ inputs.action == 'generate' && always() }}
-      env:
-        REPORT_URL: ${{ steps.generate-report.outputs.report-url }}
-        BUILD_TYPE: ${{ inputs.build_type }}
-        SHA: ${{ github.event.pull_request.head.sha || github.sha }}
-      with:
-        script: |
-          const { REPORT_URL, BUILD_TYPE, SHA } = process.env
-
-          await github.rest.repos.createCommitStatus({
-            owner: context.repo.owner,
-            repo: context.repo.repo,
-            sha: `${SHA}`,
-            state: 'success',
-            target_url: `${REPORT_URL}`,
-            context: `Allure report / ${BUILD_TYPE}`,
-          })

.github/actions/download/action.yml

@@ -1,59 +0,0 @@
-name: "Download an artifact"
-description: "Custom download action"
-inputs:
-  name:
-    description: "Artifact name"
-    required: true
-  path:
-    description: "A directory to put artifact into"
-    default: "."
-    required: false
-  skip-if-does-not-exist:
-    description: "Allow to skip if file doesn't exist, fail otherwise"
-    default: false
-    required: false
-  prefix:
-    description: "S3 prefix. Default is '${GITHUB_RUN_ID}/${GITHUB_RUN_ATTEMPT}'"
-    required: false
-
-runs:
-  using: "composite"
-  steps:
-    - name: Download artifact
-      id: download-artifact
-      shell: bash -euxo pipefail {0}
-      env:
-        TARGET: ${{ inputs.path }}
-        ARCHIVE: /tmp/downloads/${{ inputs.name }}.tar.zst
-        SKIP_IF_DOES_NOT_EXIST: ${{ inputs.skip-if-does-not-exist }}
-        PREFIX: artifacts/${{ inputs.prefix || format('{0}/{1}', github.run_id, github.run_attempt) }}
-      run: |
-        BUCKET=neon-github-public-dev
-        FILENAME=$(basename $ARCHIVE)
-
-        S3_KEY=$(aws s3api list-objects-v2 --bucket ${BUCKET} --prefix ${PREFIX%$GITHUB_RUN_ATTEMPT} | jq -r '.Contents[].Key' | grep ${FILENAME} | sort --version-sort | tail -1 || true)
-        if [ -z "${S3_KEY}" ]; then
-          if [ "${SKIP_IF_DOES_NOT_EXIST}" = "true" ]; then
-            echo 'SKIPPED=true' >> $GITHUB_OUTPUT
-            exit 0
-          else
-            echo 2>&1 "Neither s3://${BUCKET}/${PREFIX}/${FILENAME} nor its version from previous attempts exist"
-            exit 1
-          fi
-        fi
-
-        echo 'SKIPPED=false' >> $GITHUB_OUTPUT
-
-        mkdir -p $(dirname $ARCHIVE)
-        time aws s3 cp --only-show-errors s3://${BUCKET}/${S3_KEY} ${ARCHIVE}
-
-    - name: Extract artifact
-      if: ${{ steps.download-artifact.outputs.SKIPPED == 'false' }}
-      shell: bash -euxo pipefail {0}
-      env:
-        TARGET: ${{ inputs.path }}
-        ARCHIVE: /tmp/downloads/${{ inputs.name }}.tar.zst
-      run: |
-        mkdir -p ${TARGET}
-        time tar -xf ${ARCHIVE} -C ${TARGET}
-        rm -f ${ARCHIVE}

.github/actions/neon-project-create/action.yml

@@ -1,82 +0,0 @@
-name: 'Create Neon Project'
-description: 'Create Neon Project using API'
-
-inputs:
-  api_key:
-    desctiption: 'Neon API key'
-    required: true
-  environment:
-    desctiption: 'dev (aka captest) or stage'
-    required: true
-  region_id:
-    desctiption: 'Region ID, if not set the project will be created in the default region'
-    required: false
-outputs:
-  dsn:
-    description: 'Created Project DSN (for main database)'
-    value: ${{ steps.create-neon-project.outputs.dsn }}
-  project_id:
-    description: 'Created Project ID'
-    value: ${{ steps.create-neon-project.outputs.project_id }}
-
-runs:
-  using: "composite"
-  steps:
-    - name: Parse Input
-      id: parse-input
-      shell: bash -euxo pipefail {0}
-      run: |
-        case "${ENVIRONMENT}" in
-          dev)
-            API_HOST=console.dev.neon.tech
-            REGION_ID=${REGION_ID:-eu-west-1}
-            ;;
-          staging)
-            API_HOST=console.stage.neon.tech
-            REGION_ID=${REGION_ID:-us-east-1}
-            ;;
-          *)
-            echo 2>&1 "Unknown environment=${ENVIRONMENT}. Allowed 'dev' or 'staging' only"
-            exit 1
-            ;;
-        esac
-
-        echo "api_host=${API_HOST}" >> $GITHUB_OUTPUT
-        echo "region_id=${REGION_ID}" >> $GITHUB_OUTPUT
-      env:
-        ENVIRONMENT: ${{ inputs.environment }}
-        REGION_ID: ${{ inputs.region_id }}
-
-    - name: Create Neon Project
-      id: create-neon-project
-      # A shell without `set -x` to not to expose password/dsn in logs
-      shell: bash -euo pipefail {0}
-      run: |
-        project=$(curl \
-          "https://${API_HOST}/api/v1/projects" \
-          --fail \
-          --header "Accept: application/json" \
-          --header "Content-Type: application/json" \
-          --header "Authorization: Bearer ${API_KEY}" \
-          --data "{
-            \"project\": {
-              \"name\": \"Created by actions/neon-project-create; GITHUB_RUN_ID=${GITHUB_RUN_ID}\",
-              \"platform_id\": \"aws\",
-              \"region_id\": \"${REGION_ID}\",
-              \"settings\": { }
-            }
-          }")
-
-        # Mask password
-        echo "::add-mask::$(echo $project | jq --raw-output '.roles[] | select(.name != "web_access") | .password')"
-
-        dsn=$(echo $project | jq --raw-output '.roles[] | select(.name != "web_access") | .dsn')/main
-        echo "::add-mask::${dsn}"
-        echo "dsn=${dsn}" >> $GITHUB_OUTPUT
-
-        project_id=$(echo $project | jq --raw-output '.id')
-        echo "project_id=${project_id}" >> $GITHUB_OUTPUT
-      env:
-        API_KEY: ${{ inputs.api_key }}
-        API_HOST: ${{ steps.parse-input.outputs.api_host }}
-        REGION_ID: ${{ steps.parse-input.outputs.region_id }}

.github/actions/neon-project-delete/action.yml

@@ -1,54 +0,0 @@
-name: 'Delete Neon Project'
-description: 'Delete Neon Project using API'
-
-inputs:
-  api_key:
-    desctiption: 'Neon API key'
-    required: true
-  environment:
-    desctiption: 'dev (aka captest) or stage'
-    required: true
-  project_id:
-    desctiption: 'ID of the Project to delete'
-    required: true
-
-runs:
-  using: "composite"
-  steps:
-    - name: Parse Input
-      id: parse-input
-      shell: bash -euxo pipefail {0}
-      run: |
-        case "${ENVIRONMENT}" in
-          dev)
-            API_HOST=console.dev.neon.tech
-            ;;
-          staging)
-            API_HOST=console.stage.neon.tech
-            ;;
-          *)
-            echo 2>&1 "Unknown environment=${ENVIRONMENT}. Allowed 'dev' or 'staging' only"
-            exit 1
-            ;;
-        esac
-
-        echo "api_host=${API_HOST}" >> $GITHUB_OUTPUT
-      env:
-        ENVIRONMENT: ${{ inputs.environment }}
-
-    - name: Delete Neon Project
-      shell: bash -euxo pipefail {0}
-      run: |
-        # Allow PROJECT_ID to be empty/null for cases when .github/actions/neon-project-create failed
-        if [ -n "${PROJECT_ID}" ]; then
-          curl -X "POST" \
-            "https://${API_HOST}/api/v1/projects/${PROJECT_ID}/delete" \
-            --fail \
-            --header "Accept: application/json" \
-            --header "Content-Type: application/json" \
-            --header "Authorization: Bearer ${API_KEY}"
-        fi
-      env:
-        API_KEY: ${{ inputs.api_key }}
-        PROJECT_ID: ${{ inputs.project_id }}
-        API_HOST: ${{ steps.parse-input.outputs.api_host }}

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

@@ -3,7 +3,10 @@ description: 'Runs a Neon python test set, performing all the required preparati
 
 inputs:
   build_type:
-    description: 'Type of Rust (neon) and C (postgres) builds. Must be "release" or "debug", or "remote" for the remote cluster'
+    description: 'Type of Rust (neon) and C (postgres) builds. Must be "release" or "debug".'
+    required: true
+  rust_toolchain:
+    description: 'Rust toolchain version to fetch the caches'
     required: true
   test_selection:
     description: 'A python test suite to run'
@@ -21,55 +24,25 @@ inputs:
     required: false
     default: 'true'
   save_perf_report:
-    description: 'Whether to upload the performance report, if true PERF_TEST_RESULT_CONNSTR env variable should be set'
+    description: 'Whether to upload the performance report'
     required: false
     default: 'false'
-  run_with_real_s3:
-    description: 'Whether to pass real s3 credentials to the test suite'
-    required: false
-    default: 'false'
-  real_s3_bucket:
-    description: 'Bucket name for real s3 tests'
-    required: false
-    default: ''
-  real_s3_region:
-    description: 'Region name for real s3 tests'
-    required: false
-    default: ''
-  real_s3_access_key_id:
-    description: 'Access key id'
-    required: false
-    default: ''
-  real_s3_secret_access_key:
-    description: 'Secret access key'
-    required: false
-    default: ''
 
 runs:
   using: "composite"
   steps:
-    - name: Get Neon artifact
-      if: inputs.build_type != 'remote'
-      uses: ./.github/actions/download
+    - name: Get Neon artifact for restoration
+      uses: actions/download-artifact@v3
       with:
-        name: neon-${{ runner.os }}-${{ inputs.build_type }}-artifact
-        path: /tmp/neon
+        name: neon-${{ runner.os }}-${{ inputs.build_type }}-${{ inputs.rust_toolchain }}-artifact
+        path: ./neon-artifact/
 
-    - name: Download Neon binaries for the previous release
-      if: inputs.build_type != 'remote'
-      uses: ./.github/actions/download
-      with:
-        name: neon-${{ runner.os }}-${{ inputs.build_type }}-artifact
-        path: /tmp/neon-previous
-        prefix: latest
-
-    - name: Download compatibility snapshot for Postgres 14
-      if: inputs.build_type != 'remote'
-      uses: ./.github/actions/download
-      with:
-        name: compatibility-snapshot-${{ inputs.build_type }}-pg14
-        path: /tmp/compatibility_snapshot_pg14
-        prefix: latest
+    - name: Extract Neon artifact
+      shell: bash -ex {0}
+      run: |
+        mkdir -p /tmp/neon/
+        tar -xf ./neon-artifact/neon.tar.zst -C /tmp/neon/
+        rm -rf ./neon-artifact/
 
     - name: Checkout
       if: inputs.needs_postgres_source == 'true'
@@ -86,33 +59,19 @@ runs:
         key: v1-${{ runner.os }}-python-deps-${{ hashFiles('poetry.lock') }}
 
     - name: Install Python deps
-      shell: bash -euxo pipefail {0}
+      shell: bash -ex {0}
       run: ./scripts/pysync
 
     - name: Run pytest
       env:
         NEON_BIN: /tmp/neon/bin
-        COMPATIBILITY_NEON_BIN: /tmp/neon-previous/bin
-        COMPATIBILITY_POSTGRES_DISTRIB_DIR: /tmp/neon-previous/pg_install
+        POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
         TEST_OUTPUT: /tmp/test_output
-        BUILD_TYPE: ${{ inputs.build_type }}
-        AWS_ACCESS_KEY_ID: ${{ inputs.real_s3_access_key_id }}
-        AWS_SECRET_ACCESS_KEY: ${{ inputs.real_s3_secret_access_key }}
-        COMPATIBILITY_SNAPSHOT_DIR: /tmp/compatibility_snapshot_pg14
-        ALLOW_BACKWARD_COMPATIBILITY_BREAKAGE: contains(github.event.pull_request.labels.*.name, 'backward compatibility breakage')
-        ALLOW_FORWARD_COMPATIBILITY_BREAKAGE: contains(github.event.pull_request.labels.*.name, 'forward compatibility breakage')
-      shell: bash -euxo pipefail {0}
+        # this variable will be embedded in perf test report
+        # and is needed to distinguish different environments
+        PLATFORM: github-actions-selfhosted
+      shell: bash -ex {0}
       run: |
-        # PLATFORM will be embedded in the perf test report
-        # and it is needed to distinguish different environments
-        export PLATFORM=${PLATFORM:-github-actions-selfhosted}
-        export POSTGRES_DISTRIB_DIR=${POSTGRES_DISTRIB_DIR:-/tmp/neon/pg_install}
-        export DEFAULT_PG_VERSION=${DEFAULT_PG_VERSION:-14}
-
-        if [ "${BUILD_TYPE}" = "remote" ]; then
-          export REMOTE_ENV=1
-        fi
-
         PERF_REPORT_DIR="$(realpath test_runner/perf-report-local)"
         rm -rf $PERF_REPORT_DIR
 
@@ -123,37 +82,19 @@ runs:
           exit 1
         fi
         if [[ "${{ inputs.run_in_parallel }}" == "true" ]]; then
-          # -n4 uses four processes to run tests via pytest-xdist
           EXTRA_PARAMS="-n4 $EXTRA_PARAMS"
-
-          # --dist=loadgroup points tests marked with @pytest.mark.xdist_group
-          # to the same worker to make @pytest.mark.order work with xdist
-          EXTRA_PARAMS="--dist=loadgroup $EXTRA_PARAMS"
         fi
-
-        if [[ "${{ inputs.run_with_real_s3 }}" == "true" ]]; then
-          echo "REAL S3 ENABLED"
-          export ENABLE_REAL_S3_REMOTE_STORAGE=nonempty
-          export REMOTE_STORAGE_S3_BUCKET=${{ inputs.real_s3_bucket }}
-          export REMOTE_STORAGE_S3_REGION=${{ inputs.real_s3_region }}
-        fi
-
         if [[ "${{ inputs.save_perf_report }}" == "true" ]]; then
-          mkdir -p "$PERF_REPORT_DIR"
-          EXTRA_PARAMS="--out-dir $PERF_REPORT_DIR $EXTRA_PARAMS"
+          if [[ "$GITHUB_REF" == "refs/heads/main" ]]; then
+            mkdir -p "$PERF_REPORT_DIR"
+            EXTRA_PARAMS="--out-dir $PERF_REPORT_DIR $EXTRA_PARAMS"
+          fi
         fi
 
         if [[ "${{ inputs.build_type }}" == "debug" ]]; then
           cov_prefix=(scripts/coverage "--profraw-prefix=$GITHUB_JOB" --dir=/tmp/coverage run)
         elif [[ "${{ inputs.build_type }}" == "release" ]]; then
           cov_prefix=()
-        else
-          cov_prefix=()
-        fi
-
-        # Wake up the cluster if we use remote neon instance
-        if [ "${{ inputs.build_type }}" = "remote" ] && [ -n "${BENCHMARK_CONNSTR}" ]; then
-          ${POSTGRES_DISTRIB_DIR}/v${DEFAULT_PG_VERSION}/bin/psql ${BENCHMARK_CONNSTR} -c "SELECT version();"
         fi
 
         # Run the tests.
@@ -163,36 +104,37 @@ runs:
         # --verbose prints name of each test (helpful when there are
         # multiple tests in one file)
         # -rA prints summary in the end
+        # -n4 uses four processes to run tests via pytest-xdist
         # -s is not used to prevent pytest from capturing output, because tests are running
         # in parallel and logs are mixed between different tests
-        #
-        mkdir -p $TEST_OUTPUT/allure/results
         "${cov_prefix[@]}" ./scripts/pytest \
           --junitxml=$TEST_OUTPUT/junit.xml \
-          --alluredir=$TEST_OUTPUT/allure/results \
           --tb=short \
           --verbose \
+          -m "not remote_cluster" \
           -rA $TEST_SELECTION $EXTRA_PARAMS
 
         if [[ "${{ inputs.save_perf_report }}" == "true" ]]; then
-          export REPORT_FROM="$PERF_REPORT_DIR"
-          export REPORT_TO="$PLATFORM"
-          scripts/generate_and_push_perf_report.sh
+          if [[ "$GITHUB_REF" == "refs/heads/main" ]]; then
+            export REPORT_FROM="$PERF_REPORT_DIR"
+            export REPORT_TO=local
+            scripts/generate_and_push_perf_report.sh
+          fi
         fi
 
-    - name: Upload compatibility snapshot for Postgres 14
-      if: github.ref_name == 'release'
-      uses: ./.github/actions/upload
-      with:
-        name: compatibility-snapshot-${{ inputs.build_type }}-pg14-${{ github.run_id }}
-        # The path includes a test name (test_create_snapshot) and directory that the test creates (compatibility_snapshot_pg14), keep the path in sync with the test
-        path: /tmp/test_output/test_create_snapshot/compatibility_snapshot_pg14/
-        prefix: latest
+    - name: Delete all data but logs
+      shell: bash -ex {0}
+      if: always()
+      run: |
+        du -sh /tmp/test_output/*
+        find /tmp/test_output -type f ! -name "*.log" ! -name "regression.diffs" ! -name "junit.xml" ! -name "*.filediff" ! -name "*.stdout" ! -name "*.stderr" ! -name "flamegraph.svg" ! -name "*.metrics" -delete
+        du -sh /tmp/test_output/*
 
-    - name: Create Allure report
-      if: success() || failure()
-      uses: ./.github/actions/allure-report
+    - name: Upload python test logs
+      if: always()
+      uses: actions/upload-artifact@v3
       with:
-        action: store
-        build_type: ${{ inputs.build_type }}
-        test_selection: ${{ inputs.test_selection }}
+        retention-days: 7
+        if-no-files-found: error
+        name: python-test-${{ inputs.test_selection }}-${{ runner.os }}-${{ inputs.build_type }}-${{ inputs.rust_toolchain }}-logs
+        path: /tmp/test_output/

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

@@ -5,18 +5,13 @@ runs:
   using: "composite"
   steps:
     - name: Merge coverage data
-      shell: bash -euxo pipefail {0}
+      shell: bash -ex {0}
       run: scripts/coverage "--profraw-prefix=$GITHUB_JOB" --dir=/tmp/coverage merge
 
-    - name: Download previous coverage data into the same directory
-      uses: ./.github/actions/download
-      with:
-        name: coverage-data-artifact
-        path: /tmp/coverage
-        skip-if-does-not-exist: true # skip if there's no previous coverage to download
-
     - name: Upload coverage data
-      uses: ./.github/actions/upload
+      uses: actions/upload-artifact@v3
       with:
+        retention-days: 7
+        if-no-files-found: error
         name: coverage-data-artifact
-        path: /tmp/coverage
+        path: /tmp/coverage/

.github/actions/upload/action.yml

@@ -1,58 +0,0 @@
-name: "Upload an artifact"
-description: "Custom upload action"
-inputs:
-  name:
-    description: "Artifact name"
-    required: true
-  path:
-    description: "A directory or file to upload"
-    required: true
-  prefix:
-    description: "S3 prefix. Default is '${GITHUB_RUN_ID}/${GITHUB_RUN_ATTEMPT}'"
-    required: false
-
-runs:
-  using: "composite"
-  steps:
-    - name: Prepare artifact
-      shell: bash -euxo pipefail {0}
-      env:
-        SOURCE: ${{ inputs.path }}
-        ARCHIVE: /tmp/uploads/${{ inputs.name }}.tar.zst
-      run: |
-        mkdir -p $(dirname $ARCHIVE)
-
-        if [ -f ${ARCHIVE} ]; then
-          echo 2>&1 "File ${ARCHIVE} already exist. Something went wrong before"
-          exit 1
-        fi
-
-        ZSTD_NBTHREADS=0
-        if [ -d  ${SOURCE} ]; then
-          time tar -C ${SOURCE} -cf ${ARCHIVE} --zstd .
-        elif [ -f ${SOURCE} ]; then
-          time tar -cf ${ARCHIVE} --zstd ${SOURCE}
-        elif ! ls ${SOURCE} > /dev/null 2>&1; then
-          echo 2>&1 "${SOURCE} does not exist"
-          exit 2
-        else
-          echo 2>&1 "${SOURCE} is neither a directory nor a file, do not know how to handle it"
-          exit 3
-        fi
-
-    - name: Upload artifact
-      shell: bash -euxo pipefail {0}
-      env:
-        SOURCE: ${{ inputs.path }}
-        ARCHIVE: /tmp/uploads/${{ inputs.name }}.tar.zst
-        PREFIX: artifacts/${{ inputs.prefix || format('{0}/{1}', github.run_id, github.run_attempt) }}
-      run: |
-        BUCKET=neon-github-public-dev
-        FILENAME=$(basename $ARCHIVE)
-
-        FILESIZE=$(du -sh ${ARCHIVE} | cut -f1)
-
-        time aws s3 mv --only-show-errors ${ARCHIVE} s3://${BUCKET}/${PREFIX}/${FILENAME}
-
-        # Ref https://docs.github.com/en/actions/using-workflows/workflow-commands-for-github-actions#adding-a-job-summary
-        echo "[${FILENAME}](https://${BUCKET}.s3.amazonaws.com/${PREFIX}/${FILENAME}) ${FILESIZE}" >> ${GITHUB_STEP_SUMMARY}

.github/ansible/.gitignore

@@ -2,6 +2,3 @@ zenith_install.tar.gz
 .zenith_current_version
 neon_install.tar.gz
 .neon_current_version
-
-collections/*
-!collections/.keep

.github/ansible/ansible.cfg

@@ -3,7 +3,6 @@
 localhost_warning = False
 host_key_checking = False
 timeout = 30
-collections_paths = ./collections
 
 [ssh_connection]
 ssh_args   = -F ./ansible.ssh.cfg

.github/ansible/deploy.yaml

@@ -1,7 +1,7 @@
 - name: Upload Neon binaries
   hosts: storage
   gather_facts: False
-  remote_user: "{{ remote_user }}"
+  remote_user: admin
 
   tasks:
 
@@ -14,8 +14,7 @@
       - safekeeper
 
     - name: inform about versions
-      debug:
-        msg: "Version to deploy - {{ current_version }}"
+      debug: msg="Version to deploy - {{ current_version }}"
       tags:
       - pageserver
       - safekeeper
@@ -36,7 +35,7 @@
 - name: Deploy pageserver
   hosts: pageservers
   gather_facts: False
-  remote_user: "{{ remote_user }}"
+  remote_user: admin
 
   tasks:
 
@@ -59,34 +58,20 @@
         creates: "/storage/pageserver/data/tenants"
       environment:
         NEON_REPO_DIR: "/storage/pageserver/data"
-        LD_LIBRARY_PATH: "/usr/local/v14/lib"
+        LD_LIBRARY_PATH: "/usr/local/lib"
       become: true
       tags:
       - pageserver
 
-    - name: read the existing remote pageserver config
-      ansible.builtin.slurp:
-        src: /storage/pageserver/data/pageserver.toml
-      register: _remote_ps_config
-      tags:
-      - pageserver
-
-    - name: parse the existing pageserver configuration
-      ansible.builtin.set_fact:
-        _existing_ps_config: "{{ _remote_ps_config['content'] | b64decode | sivel.toiletwater.from_toml }}"
-      tags:
-      - pageserver
-
-    - name: construct the final pageserver configuration dict
-      ansible.builtin.set_fact:
-        pageserver_config: "{{ pageserver_config_stub | combine({'id': _existing_ps_config.id }) }}"
-      tags:
-      - pageserver
-
-    - name: template the pageserver config
-      template:
-        src: templates/pageserver.toml.j2
-        dest: /storage/pageserver/data/pageserver.toml
+    - name: update remote storage (s3) config
+      lineinfile:
+        path: /storage/pageserver/data/pageserver.toml
+        line: "{{ item }}"
+      loop:
+        - "[remote_storage]"
+        - "bucket_name = '{{ bucket_name }}'"
+        - "bucket_region = '{{ bucket_region }}'"
+        - "prefix_in_bucket = '{{ inventory_hostname }}'"
       become: true
       tags:
       - pageserver
@@ -124,7 +109,7 @@
 - name: Deploy safekeeper
   hosts: safekeepers
   gather_facts: False
-  remote_user: "{{ remote_user }}"
+  remote_user: admin
 
   tasks:
 
@@ -147,7 +132,7 @@
         creates: "/storage/safekeeper/data/safekeeper.id"
       environment:
         NEON_REPO_DIR: "/storage/safekeeper/data"
-        LD_LIBRARY_PATH: "/usr/local/v14/lib"
+        LD_LIBRARY_PATH: "/usr/local/lib"
       become: true
       tags:
       - safekeeper

.github/ansible/get_binaries.sh

@@ -2,14 +2,30 @@
 
 set -e
 
-if [ -n "${DOCKER_TAG}" ]; then
-  # Verson is DOCKER_TAG but without prefix
-  VERSION=$(echo $DOCKER_TAG | sed 's/^.*-//g')
+RELEASE=${RELEASE:-false}
+
+# look at docker hub for latest tag for neon docker image
+if [ "${RELEASE}" = "true" ]; then
+    echo "search latest release tag"
+    VERSION=$(curl -s https://registry.hub.docker.com/v1/repositories/neondatabase/neon/tags |jq -r -S '.[].name' | grep release | sed 's/release-//g' | grep -E '^[0-9]+$' | sort -n | tail -1)
+    if [ -z "${VERSION}" ]; then
+        echo "no any docker tags found, exiting..."
+        exit 1
+    else
+        TAG="release-${VERSION}"
+    fi
 else
-  echo "Please set DOCKER_TAG environment variable"
-  exit 1
+    echo "search latest dev tag"
+    VERSION=$(curl -s https://registry.hub.docker.com/v1/repositories/neondatabase/neon/tags |jq -r -S '.[].name' | grep -E '^[0-9]+$' | sort -n | tail -1)
+    if [ -z "${VERSION}" ]; then
+        echo "no any docker tags found, exiting..."
+        exit 1
+    else
+        TAG="${VERSION}"
+    fi
 fi
 
+echo "found ${VERSION}"
 
 # do initial cleanup
 rm -rf neon_install postgres_install.tar.gz neon_install.tar.gz .neon_current_version
@@ -17,20 +33,14 @@ mkdir neon_install
 
 # retrieve binaries from docker image
 echo "getting binaries from docker image"
-docker pull --quiet neondatabase/neon:${DOCKER_TAG}
-ID=$(docker create neondatabase/neon:${DOCKER_TAG})
+docker pull --quiet neondatabase/neon:${TAG}
+ID=$(docker create neondatabase/neon:${TAG})
 docker cp ${ID}:/data/postgres_install.tar.gz .
 tar -xzf postgres_install.tar.gz -C neon_install
-mkdir neon_install/bin/
 docker cp ${ID}:/usr/local/bin/pageserver neon_install/bin/
-docker cp ${ID}:/usr/local/bin/pageserver_binutils neon_install/bin/
 docker cp ${ID}:/usr/local/bin/safekeeper neon_install/bin/
-docker cp ${ID}:/usr/local/bin/neon_broker neon_install/bin/
 docker cp ${ID}:/usr/local/bin/proxy neon_install/bin/
-docker cp ${ID}:/usr/local/v14/bin/ neon_install/v14/bin/
-docker cp ${ID}:/usr/local/v15/bin/ neon_install/v15/bin/
-docker cp ${ID}:/usr/local/v14/lib/ neon_install/v14/lib/
-docker cp ${ID}:/usr/local/v15/lib/ neon_install/v15/lib/
+docker cp ${ID}:/usr/local/bin/postgres neon_install/bin/
 docker rm -vf ${ID}
 
 # store version to file (for ansible playbooks) and create binaries tarball

.github/ansible/neon-stress.hosts

@@ -0,0 +1,20 @@
+[pageservers]
+neon-stress-ps-1 console_region_id=1
+neon-stress-ps-2 console_region_id=1
+
+[safekeepers]
+neon-stress-sk-1 console_region_id=1
+neon-stress-sk-2 console_region_id=1
+neon-stress-sk-3 console_region_id=1
+
+[storage:children]
+pageservers
+safekeepers
+
+[storage:vars]
+env_name = neon-stress
+console_mgmt_base_url = http://neon-stress-console.local
+bucket_name           = neon-storage-ireland
+bucket_region         = eu-west-1
+etcd_endpoints        = etcd-stress.local:2379
+safekeeper_enable_s3_offload = false

.github/ansible/neon-stress.hosts.yaml

@@ -1,31 +0,0 @@
-storage:
-  vars:
-    bucket_name: neon-storage-ireland
-    bucket_region: eu-west-1
-    console_mgmt_base_url: http://neon-stress-console.local
-    etcd_endpoints: neon-stress-etcd.local:2379
-    safekeeper_enable_s3_offload: 'false'
-    pageserver_config_stub:
-      pg_distrib_dir: /usr/local
-      remote_storage:
-        bucket_name: "{{ bucket_name }}"
-        bucket_region: "{{ bucket_region }}"
-        prefix_in_bucket: "{{ inventory_hostname }}"
-    safekeeper_s3_prefix: neon-stress/wal
-    hostname_suffix: ".local"
-    remote_user: admin
-  children:
-    pageservers:
-      hosts:
-        neon-stress-ps-1:
-          console_region_id: aws-eu-west-1
-        neon-stress-ps-2:
-          console_region_id: aws-eu-west-1
-    safekeepers:
-      hosts:
-        neon-stress-sk-1:
-          console_region_id: aws-eu-west-1
-        neon-stress-sk-2:
-          console_region_id: aws-eu-west-1
-        neon-stress-sk-3:
-          console_region_id: aws-eu-west-1

.github/ansible/prod.ap-southeast-1.hosts.yaml

@@ -1,35 +0,0 @@
-storage:
-  vars:
-    bucket_name: neon-prod-storage-ap-southeast-1
-    bucket_region: ap-southeast-1
-    console_mgmt_base_url: http://console-release.local
-    etcd_endpoints: etcd-0.ap-southeast-1.aws.neon.tech:2379
-    pageserver_config_stub:
-      pg_distrib_dir: /usr/local
-      remote_storage:
-        bucket_name: "{{ bucket_name }}"
-        bucket_region: "{{ bucket_region }}"
-        prefix_in_bucket: "pageserver/v1"
-    safekeeper_s3_prefix: safekeeper/v1/wal
-    hostname_suffix: ""
-    remote_user: ssm-user
-    ansible_aws_ssm_region: ap-southeast-1
-    ansible_aws_ssm_bucket_name: neon-prod-storage-ap-southeast-1
-    console_region_id: aws-ap-southeast-1
-
-  children:
-    pageservers:
-      hosts:
-        pageserver-0.ap-southeast-1.aws.neon.tech:
-          ansible_host:  i-064de8ea28bdb495b
-        pageserver-1.ap-southeast-1.aws.neon.tech:
-          ansible_host:  i-0b180defcaeeb6b93
-
-    safekeepers:
-      hosts:
-        safekeeper-0.ap-southeast-1.aws.neon.tech:
-          ansible_host:  i-0d6f1dc5161eef894
-        safekeeper-1.ap-southeast-1.aws.neon.tech:
-          ansible_host:  i-0e338adda8eb2d19f
-        safekeeper-2.ap-southeast-1.aws.neon.tech:
-          ansible_host:  i-04fb63634e4679eb9

.github/ansible/prod.eu-central-1.hosts.yaml

@@ -1,35 +0,0 @@
-storage:
-  vars:
-    bucket_name: neon-prod-storage-eu-central-1
-    bucket_region: eu-central-1
-    console_mgmt_base_url: http://console-release.local
-    etcd_endpoints: etcd-0.eu-central-1.aws.neon.tech:2379
-    pageserver_config_stub:
-      pg_distrib_dir: /usr/local
-      remote_storage:
-        bucket_name: "{{ bucket_name }}"
-        bucket_region: "{{ bucket_region }}"
-        prefix_in_bucket: "pageserver/v1"
-    safekeeper_s3_prefix: safekeeper/v1/wal
-    hostname_suffix: ""
-    remote_user: ssm-user
-    ansible_aws_ssm_region: eu-central-1
-    ansible_aws_ssm_bucket_name: neon-prod-storage-eu-central-1
-    console_region_id: aws-eu-central-1
-
-  children:
-    pageservers:
-      hosts:
-        pageserver-0.eu-central-1.aws.neon.tech:
-          ansible_host:  i-0cd8d316ecbb715be
-        pageserver-1.eu-central-1.aws.neon.tech:
-          ansible_host:  i-090044ed3d383fef0
-
-    safekeepers:
-      hosts:
-        safekeeper-0.eu-central-1.aws.neon.tech:
-          ansible_host:  i-0b238612d2318a050
-        safekeeper-1.eu-central-1.aws.neon.tech:
-          ansible_host:  i-07b9c45e5c2637cd4
-        safekeeper-2.eu-central-1.aws.neon.tech:
-          ansible_host:  i-020257302c3c93d88

.github/ansible/prod.us-east-2.hosts.yaml

@@ -1,36 +0,0 @@
-storage:
-  vars:
-    bucket_name: neon-prod-storage-us-east-2
-    bucket_region: us-east-2
-    console_mgmt_base_url: http://console-release.local
-    etcd_endpoints: etcd-0.us-east-2.aws.neon.tech:2379
-    pageserver_config_stub:
-      pg_distrib_dir: /usr/local
-      remote_storage:
-        bucket_name: "{{ bucket_name }}"
-        bucket_region: "{{ bucket_region }}"
-        prefix_in_bucket: "pageserver/v1"
-    safekeeper_s3_prefix: safekeeper/v1/wal
-    hostname_suffix: ""
-    remote_user: ssm-user
-    ansible_aws_ssm_region: us-east-2
-    ansible_aws_ssm_bucket_name: neon-prod-storage-us-east-2
-    console_region_id: aws-us-east-2
-
-  children:
-    pageservers:
-      hosts:
-        pageserver-0.us-east-2.aws.neon.tech:
-          ansible_host:  i-062227ba7f119eb8c
-        pageserver-1.us-east-2.aws.neon.tech:
-          ansible_host:  i-0b3ec0afab5968938
-
-    safekeepers:
-      hosts:
-        safekeeper-0.us-east-2.aws.neon.tech:
-          ansible_host:  i-0e94224750c57d346
-        safekeeper-1.us-east-2.aws.neon.tech:
-          ansible_host:  i-06d113fb73bfddeb0
-        safekeeper-2.us-east-2.aws.neon.tech:
-          ansible_host:  i-09f66c8e04afff2e8
-          

.github/ansible/production.hosts

@@ -0,0 +1,20 @@
+[pageservers]
+#zenith-1-ps-1 console_region_id=1
+zenith-1-ps-2 console_region_id=1
+zenith-1-ps-3 console_region_id=1
+
+[safekeepers]
+zenith-1-sk-1 console_region_id=1
+zenith-1-sk-2 console_region_id=1
+zenith-1-sk-3 console_region_id=1
+
+[storage:children]
+pageservers
+safekeepers
+
+[storage:vars]
+env_name = prod-1
+console_mgmt_base_url = http://console-release.local
+bucket_name           = zenith-storage-oregon
+bucket_region         = us-west-2
+etcd_endpoints        = zenith-1-etcd.local:2379

.github/ansible/production.hosts.yaml

@@ -1,33 +0,0 @@
----
-storage:
-  vars:
-    console_mgmt_base_url: http://console-release.local
-    bucket_name: zenith-storage-oregon
-    bucket_region: us-west-2
-    etcd_endpoints: zenith-1-etcd.local:2379
-    pageserver_config_stub:
-      pg_distrib_dir: /usr/local
-      remote_storage:
-        bucket_name: "{{ bucket_name }}"
-        bucket_region: "{{ bucket_region }}"
-        prefix_in_bucket: "{{ inventory_hostname }}"
-    safekeeper_s3_prefix: prod-1/wal
-    hostname_suffix: ".local"
-    remote_user: admin
-
-  children:
-    pageservers:
-      hosts:
-        zenith-1-ps-2:
-          console_region_id: aws-us-west-2
-        zenith-1-ps-3:
-          console_region_id: aws-us-west-2
-
-    safekeepers:
-      hosts:
-        zenith-1-sk-1:
-          console_region_id: aws-us-west-2
-        zenith-1-sk-2:
-          console_region_id: aws-us-west-2
-        zenith-1-sk-3:
-          console_region_id: aws-us-west-2

.github/ansible/scripts/init_pageserver.sh

@@ -12,19 +12,18 @@ cat <<EOF | tee /tmp/payload
   "version": 1,
   "host": "${HOST}",
   "port": 6400,
-  "region_id": "{{ console_region_id }}",
+  "region_id": {{ console_region_id }},
   "instance_id": "${INSTANCE_ID}",
   "http_host": "${HOST}",
-  "http_port": 9898,
-  "active": false
+  "http_port": 9898
 }
 EOF
 
 # check if pageserver already registered or not
-if ! curl -sf -H "Authorization: Bearer {{ CONSOLE_API_TOKEN }}" {{ console_mgmt_base_url }}/management/api/v2/pageservers/${INSTANCE_ID} -o /dev/null; then
+if ! curl -sf -X PATCH -d '{}' {{ console_mgmt_base_url }}/api/v1/pageservers/${INSTANCE_ID} -o /dev/null; then
 
     # not registered, so register it now
-    ID=$(curl -sf -X POST -H "Authorization: Bearer {{ CONSOLE_API_TOKEN }}" {{ console_mgmt_base_url }}/management/api/v2/pageservers -d@/tmp/payload | jq -r '.id')
+    ID=$(curl -sf -X POST {{ console_mgmt_base_url }}/api/v1/pageservers -d@/tmp/payload | jq -r '.ID')
 
     # init pageserver
     sudo -u pageserver /usr/local/bin/pageserver -c "id=${ID}" -c "pg_distrib_dir='/usr/local'" --init -D /storage/pageserver/data

.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=$(hostname -f)
@@ -14,18 +13,17 @@ cat <<EOF | tee /tmp/payload
   "host": "${HOST}",
   "port": 6500,
   "http_port": 7676,
-  "region_id": "{{ console_region_id }}",
-  "instance_id": "${INSTANCE_ID}",
-  "availability_zone_id": "${AZ_ID}",
-  "active": false
+  "region_id": {{ console_region_id }},
+  "instance_id": "${INSTANCE_ID}"
 }
 EOF
 
 # check if safekeeper already registered or not
-if ! curl -sf -H "Authorization: Bearer {{ CONSOLE_API_TOKEN }}" {{ console_mgmt_base_url }}/management/api/v2/safekeepers/${INSTANCE_ID} -o /dev/null; then
+if ! curl -sf -X PATCH -d '{}' {{ console_mgmt_base_url }}/api/v1/safekeepers/${INSTANCE_ID} -o /dev/null; then
 
     # not registered, so register it now
-    ID=$(curl -sf -X POST -H "Authorization: Bearer {{ CONSOLE_API_TOKEN }}" {{ console_mgmt_base_url }}/management/api/v2/safekeepers -d@/tmp/payload | jq -r '.id')
+    ID=$(curl -sf -X POST {{ console_mgmt_base_url }}/api/v1/safekeepers -d@/tmp/payload | jq -r '.ID')
+
     # init safekeeper
     sudo -u safekeeper /usr/local/bin/safekeeper --id ${ID} --init -D /storage/safekeeper/data
 fi

.github/ansible/ssm_config

@@ -1,2 +0,0 @@
-ansible_connection: aws_ssm
-ansible_python_interpreter: /usr/bin/python3

.github/ansible/staging.hosts

@@ -0,0 +1,20 @@
+[pageservers]
+#zenith-us-stage-ps-1 console_region_id=27
+zenith-us-stage-ps-2 console_region_id=27
+zenith-us-stage-ps-3 console_region_id=27
+
+[safekeepers]
+zenith-us-stage-sk-4 console_region_id=27
+zenith-us-stage-sk-5 console_region_id=27
+zenith-us-stage-sk-6 console_region_id=27
+
+[storage:children]
+pageservers
+safekeepers
+
+[storage:vars]
+env_name = us-stage
+console_mgmt_base_url = http://console-staging.local
+bucket_name           = zenith-staging-storage-us-east-1
+bucket_region         = us-east-1
+etcd_endpoints        = zenith-us-stage-etcd.local:2379

.github/ansible/staging.hosts.yaml

@@ -1,34 +0,0 @@
-storage:
-  vars:
-    bucket_name: zenith-staging-storage-us-east-1
-    bucket_region: us-east-1
-    console_mgmt_base_url: http://console-staging.local
-    etcd_endpoints: zenith-us-stage-etcd.local:2379
-    pageserver_config_stub:
-      pg_distrib_dir: /usr/local
-      remote_storage:
-        bucket_name: "{{ bucket_name }}"
-        bucket_region: "{{ bucket_region }}"
-        prefix_in_bucket: "{{ inventory_hostname }}"
-    safekeeper_s3_prefix: us-stage/wal
-    hostname_suffix: ".local"
-    remote_user: admin
-
-  children:
-    pageservers:
-      hosts:
-        zenith-us-stage-ps-2:
-          console_region_id: aws-us-east-1
-        zenith-us-stage-ps-3:
-          console_region_id: aws-us-east-1
-        zenith-us-stage-ps-4:
-          console_region_id: aws-us-east-1
-
-    safekeepers:
-      hosts:
-        zenith-us-stage-sk-4:
-          console_region_id: aws-us-east-1
-        zenith-us-stage-sk-5:
-          console_region_id: aws-us-east-1
-        zenith-us-stage-sk-6:
-          console_region_id: aws-us-east-1

.github/ansible/staging.us-east-2.hosts.yaml

@@ -1,33 +0,0 @@
-storage:
-  vars:
-    bucket_name: neon-staging-storage-us-east-2
-    bucket_region: us-east-2
-    console_mgmt_base_url: http://console-staging.local
-    etcd_endpoints: etcd-0.us-east-2.aws.neon.build:2379
-    pageserver_config_stub:
-      pg_distrib_dir: /usr/local
-      remote_storage:
-        bucket_name: "{{ bucket_name }}"
-        bucket_region: "{{ bucket_region }}"
-        prefix_in_bucket: "pageserver/v1"
-    safekeeper_s3_prefix: safekeeper/v1/wal
-    hostname_suffix: ""
-    remote_user: ssm-user
-    ansible_aws_ssm_region: us-east-2
-    ansible_aws_ssm_bucket_name: neon-staging-storage-us-east-2
-    console_region_id: aws-us-east-2
-
-  children:
-    pageservers:
-      hosts:
-        pageserver-0.us-east-2.aws.neon.build:
-          ansible_host: i-0c3e70929edb5d691
-
-    safekeepers:
-      hosts:
-        safekeeper-0.us-east-2.aws.neon.build:
-          ansible_host: i-027662bd552bf5db0
-        safekeeper-1.us-east-2.aws.neon.build:
-          ansible_host: i-0171efc3604a7b907
-        safekeeper-2.us-east-2.aws.neon.build:
-          ansible_host: i-0de0b03a51676a6ce

.github/ansible/systemd/pageserver.service

@@ -1,11 +1,11 @@
 [Unit]
-Description=Neon pageserver
+Description=Zenith pageserver
 After=network.target auditd.service
 
 [Service]
 Type=simple
 User=pageserver
-Environment=RUST_BACKTRACE=1 NEON_REPO_DIR=/storage/pageserver LD_LIBRARY_PATH=/usr/local/v14/lib
+Environment=RUST_BACKTRACE=1 NEON_REPO_DIR=/storage/pageserver LD_LIBRARY_PATH=/usr/local/lib
 ExecStart=/usr/local/bin/pageserver -c "pg_distrib_dir='/usr/local'" -c "listen_pg_addr='0.0.0.0:6400'" -c "listen_http_addr='0.0.0.0:9898'" -c "broker_endpoints=['{{ etcd_endpoints }}']" -D /storage/pageserver/data
 ExecReload=/bin/kill -HUP $MAINPID
 KillMode=mixed

.github/ansible/systemd/safekeeper.service

@@ -1,12 +1,12 @@
 [Unit]
-Description=Neon safekeeper
+Description=Zenith safekeeper
 After=network.target auditd.service
 
 [Service]
 Type=simple
 User=safekeeper
-Environment=RUST_BACKTRACE=1 NEON_REPO_DIR=/storage/safekeeper/data LD_LIBRARY_PATH=/usr/local/v14/lib
-ExecStart=/usr/local/bin/safekeeper -l {{ inventory_hostname }}{{ hostname_suffix }}:6500 --listen-http {{ inventory_hostname }}{{ hostname_suffix }}:7676 -D /storage/safekeeper/data --broker-endpoints={{ etcd_endpoints }} --remote-storage='{bucket_name="{{bucket_name}}", bucket_region="{{bucket_region}}", prefix_in_bucket="{{ safekeeper_s3_prefix }}"}'
+Environment=RUST_BACKTRACE=1 NEON_REPO_DIR=/storage/safekeeper/data LD_LIBRARY_PATH=/usr/local/lib
+ExecStart=/usr/local/bin/safekeeper -l {{ inventory_hostname }}.local:6500 --listen-http {{ inventory_hostname }}.local:7676 -D /storage/safekeeper/data --broker-endpoints={{ etcd_endpoints }} --remote-storage='{bucket_name="{{bucket_name}}", bucket_region="{{bucket_region}}", prefix_in_bucket="{{ env_name }}/wal"}'
 ExecReload=/bin/kill -HUP $MAINPID
 KillMode=mixed
 KillSignal=SIGINT

.github/ansible/templates/pageserver.toml.j2

@@ -1 +0,0 @@
-{{ pageserver_config | sivel.toiletwater.to_toml }}

.github/helm-values/dev-us-east-2-beta.neon-proxy-scram.yaml

@@ -1,31 +0,0 @@
-# Helm chart values for neon-proxy-scram.
-# This is a YAML-formatted file.
-
-image:
-  repository: neondatabase/neon
-
-settings:
-  authBackend: "console"
-  authEndpoint: "http://console-staging.local/management/api/v2"
-  domain: "*.us-east-2.aws.neon.build"
-
-# -- Additional labels for neon-proxy pods
-podLabels:
-  zenith_service: proxy-scram
-  zenith_env: dev
-  zenith_region: us-east-2
-  zenith_region_slug: us-east-2
-
-exposedService:
-  annotations:
-    service.beta.kubernetes.io/aws-load-balancer-type: external
-    service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
-    service.beta.kubernetes.io/aws-load-balancer-scheme: internet-facing
-    external-dns.alpha.kubernetes.io/hostname: us-east-2.aws.neon.build
-
-#metrics:
-#  enabled: true
-#  serviceMonitor:
-#    enabled: true
-#    selector:
-#      release: kube-prometheus-stack

.github/helm-values/neon-stress.proxy.yaml

@@ -1,7 +1,6 @@
 fullnameOverride: "neon-stress-proxy"
 
 settings:
-  authBackend: "link"
   authEndpoint: "https://console.dev.neon.tech/authenticate_proxy_request/"
   uri: "https://console.dev.neon.tech/psql_session/"
 

.github/helm-values/prod-ap-southeast-1-epsilon.neon-proxy-scram.yaml

@@ -1,31 +0,0 @@
-# Helm chart values for neon-proxy-scram.
-# This is a YAML-formatted file.
-
-image:
-  repository: neondatabase/neon
-
-settings:
-  authBackend: "console"
-  authEndpoint: "http://console-release.local/management/api/v2"
-  domain: "*.ap-southeast-1.aws.neon.tech"
-
-# -- Additional labels for neon-proxy pods
-podLabels:
-  zenith_service: proxy-scram
-  zenith_env: prod
-  zenith_region: ap-southeast-1
-  zenith_region_slug: ap-southeast-1
-
-exposedService:
-  annotations:
-    service.beta.kubernetes.io/aws-load-balancer-type: external
-    service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
-    service.beta.kubernetes.io/aws-load-balancer-scheme: internet-facing
-    external-dns.alpha.kubernetes.io/hostname: ap-southeast-1.aws.neon.tech
-
-#metrics:
-#  enabled: true
-#  serviceMonitor:
-#    enabled: true
-#    selector:
-#      release: kube-prometheus-stack

.github/helm-values/prod-eu-central-1-gamma.neon-proxy-scram.yaml

@@ -1,31 +0,0 @@
-# Helm chart values for neon-proxy-scram.
-# This is a YAML-formatted file.
-
-image:
-  repository: neondatabase/neon
-
-settings:
-  authBackend: "console"
-  authEndpoint: "http://console-release.local/management/api/v2"
-  domain: "*.eu-central-1.aws.neon.tech"
-
-# -- Additional labels for neon-proxy pods
-podLabels:
-  zenith_service: proxy-scram
-  zenith_env: prod
-  zenith_region: eu-central-1
-  zenith_region_slug: eu-central-1
-
-exposedService:
-  annotations:
-    service.beta.kubernetes.io/aws-load-balancer-type: external
-    service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
-    service.beta.kubernetes.io/aws-load-balancer-scheme: internet-facing
-    external-dns.alpha.kubernetes.io/hostname: eu-central-1.aws.neon.tech
-
-#metrics:
-#  enabled: true
-#  serviceMonitor:
-#    enabled: true
-#    selector:
-#      release: kube-prometheus-stack

.github/helm-values/prod-us-east-2-delta.neon-proxy-scram.yaml

@@ -1,31 +0,0 @@
-# Helm chart values for neon-proxy-scram.
-# This is a YAML-formatted file.
-
-image:
-  repository: neondatabase/neon
-
-settings:
-  authBackend: "console"
-  authEndpoint: "http://console-release.local/management/api/v2"
-  domain: "*.us-east-2.aws.neon.tech"
-
-# -- Additional labels for neon-proxy pods
-podLabels:
-  zenith_service: proxy-scram
-  zenith_env: prod
-  zenith_region: us-east-2
-  zenith_region_slug: us-east-2
-
-exposedService:
-  annotations:
-    service.beta.kubernetes.io/aws-load-balancer-type: external
-    service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
-    service.beta.kubernetes.io/aws-load-balancer-scheme: internet-facing
-    external-dns.alpha.kubernetes.io/hostname: us-east-2.aws.neon.tech
-
-#metrics:
-#  enabled: true
-#  serviceMonitor:
-#    enabled: true
-#    selector:
-#      release: kube-prometheus-stack

.github/helm-values/production.proxy.yaml

@@ -1,5 +1,4 @@
 settings:
-  authBackend: "link"
   authEndpoint: "https://console.neon.tech/authenticate_proxy_request/"
   uri: "https://console.neon.tech/psql_session/"
 

.github/helm-values/staging.proxy.yaml

@@ -5,7 +5,6 @@ image:
   repository: neondatabase/neon
 
 settings:
-  authBackend: "link"
   authEndpoint: "https://console.stage.neon.tech/authenticate_proxy_request/"
   uri: "https://console.stage.neon.tech/psql_session/"
 

.github/workflows/benchmarking.yml

@@ -1,4 +1,4 @@
-name: Benchmarking
+name: benchmarking
 
 on:
   # uncomment to run on push for debugging your PR
@@ -11,29 +11,9 @@ on:
     #          │ │ ┌───────────── day of the month (1 - 31)
     #          │ │ │ ┌───────────── month (1 - 12 or JAN-DEC)
     #          │ │ │ │ ┌───────────── day of the week (0 - 6 or SUN-SAT)
-    - cron:  '0 3 * * *' # run once a day, timezone is utc
+    - cron:  '36 4 * * *' # run once a day, timezone is utc
 
   workflow_dispatch: # adds ability to run this manually
-    inputs:
-      environment:
-        description: 'Environment to run remote tests on (dev or staging)'
-        required: false
-      region_id:
-        description: 'Use a particular region. If not set the default region will be used'
-        required: false
-      save_perf_report:
-        type: boolean
-        description: 'Publish perf report or not. If not set, the report is published only for the main branch'
-        required: false
-
-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' }}
-  cancel-in-progress: true
 
 jobs:
   bench:
@@ -46,8 +26,7 @@ jobs:
     runs-on: [self-hosted, zenith-benchmarker]
 
     env:
-      POSTGRES_DISTRIB_DIR: /usr/pgsql
-      DEFAULT_PG_VERSION: 14
+      POSTGRES_DISTRIB_DIR: "/usr/pgsql-14"
 
     steps:
     - name: Checkout zenith repo
@@ -72,14 +51,22 @@ jobs:
         echo Poetry
         poetry --version
         echo Pgbench
-        ${POSTGRES_DISTRIB_DIR}/v${DEFAULT_PG_VERSION}/bin/pgbench --version
+        $POSTGRES_DISTRIB_DIR/bin/pgbench --version
 
-    - name: Create Neon Project
-      id: create-neon-project
-      uses: ./.github/actions/neon-project-create
-      with:
-        environment: ${{ github.event.inputs.environment || 'staging' }}
-        api_key: ${{ ( github.event.inputs.environment || 'staging' ) == 'staging' && secrets.NEON_STAGING_API_KEY  || secrets.NEON_CAPTEST_API_KEY }}
+    # FIXME cluster setup is skipped due to various changes in console API
+    # for now pre created cluster is used. When API gain some stability
+    # after massive changes dynamic cluster setup will be revived.
+    # So use pre created cluster. It needs to be started manually, but stop is automatic after 5 minutes of inactivity
+    - name: Setup cluster
+      env:
+        BENCHMARK_CONNSTR: "${{ secrets.BENCHMARK_STAGING_CONNSTR }}"
+      shell: bash
+      run: |
+        set -e
+
+        echo "Starting cluster"
+        # wake up the cluster
+        $POSTGRES_DISTRIB_DIR/bin/psql $BENCHMARK_CONNSTR -c "SELECT 1"
 
     - name: Run benchmark
       # pgbench is installed system wide from official repo
@@ -102,16 +89,14 @@ jobs:
         TEST_PG_BENCH_DURATIONS_MATRIX: "300"
         TEST_PG_BENCH_SCALES_MATRIX: "10,100"
         PLATFORM: "neon-staging"
-        BENCHMARK_CONNSTR: ${{ steps.create-neon-project.outputs.dsn }}
+        BENCHMARK_CONNSTR: "${{ secrets.BENCHMARK_STAGING_CONNSTR }}"
         REMOTE_ENV: "1" # indicate to test harness that we do not have zenith binaries locally
       run: |
         # just to be sure that no data was cached on self hosted runner
         # since it might generate duplicates when calling ingest_perf_test_result.py
         rm -rf perf-report-staging
         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 --out-dir perf-report-staging --timeout 5400
+        ./scripts/pytest test_runner/performance/ -v -m "remote_cluster" --skip-interfering-proc-check --out-dir perf-report-staging --timeout 3600
 
     - name: Submit result
       env:
@@ -120,14 +105,6 @@ jobs:
       run: |
         REPORT_FROM=$(realpath perf-report-staging) REPORT_TO=staging scripts/generate_and_push_perf_report.sh
 
-    - name: Delete Neon Project
-      if: ${{ always() }}
-      uses: ./.github/actions/neon-project-delete
-      with:
-        environment: staging
-        project_id: ${{ steps.create-neon-project.outputs.project_id }}
-        api_key: ${{ secrets.NEON_STAGING_API_KEY }}
-
     - name: Post to a Slack channel
       if: ${{ github.event.schedule && failure() }}
       uses: slackapi/slack-github-action@v1
@@ -136,154 +113,3 @@ jobs:
         slack-message: "Periodic perf testing: ${{ job.status }}\n${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}"
       env:
         SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
-
-  pgbench-compare:
-    strategy:
-      fail-fast: false
-      matrix:
-        # neon-captest-new: Run pgbench in a freshly created project
-        # neon-captest-reuse: Same, but reusing existing project
-        # neon-captest-prefetch: Same, with prefetching enabled (new project)
-        platform: [ neon-captest-new, neon-captest-reuse, neon-captest-prefetch ]
-        db_size: [ 10gb ]
-        include:
-          - platform: neon-captest-new
-            db_size: 50gb
-          - platform: neon-captest-prefetch
-            db_size: 50gb
-          - platform: rds-aurora
-            db_size: 50gb
-
-    env:
-      TEST_PG_BENCH_DURATIONS_MATRIX: "60m"
-      TEST_PG_BENCH_SCALES_MATRIX: ${{ matrix.db_size }}
-      POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
-      DEFAULT_PG_VERSION: 14
-      TEST_OUTPUT: /tmp/test_output
-      BUILD_TYPE: remote
-      SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref == 'refs/heads/main' ) }}
-      PLATFORM: ${{ matrix.platform }}
-
-    runs-on: dev
-    container:
-      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rustlegacy:pinned
-      options: --init
-
-    timeout-minutes: 360 # 6h
-
-    steps:
-    - uses: actions/checkout@v3
-
-    - name: Download Neon artifact
-      uses: ./.github/actions/download
-      with:
-        name: neon-${{ runner.os }}-release-artifact
-        path: /tmp/neon/
-        prefix: latest
-
-    - name: Add Postgres binaries to PATH
-      run: |
-        ${POSTGRES_DISTRIB_DIR}/v${DEFAULT_PG_VERSION}/bin/pgbench --version
-        echo "${POSTGRES_DISTRIB_DIR}/v${DEFAULT_PG_VERSION}/bin" >> $GITHUB_PATH
-
-    - name: Create Neon Project
-      if: contains(fromJson('["neon-captest-new", "neon-captest-prefetch"]'), matrix.platform)
-      id: create-neon-project
-      uses: ./.github/actions/neon-project-create
-      with:
-        environment: ${{ github.event.inputs.environment || 'dev' }}
-        api_key: ${{ ( github.event.inputs.environment || 'dev' ) == 'staging' && secrets.NEON_STAGING_API_KEY  || secrets.NEON_CAPTEST_API_KEY }}
-
-    - name: Set up Connection String
-      id: set-up-connstr
-      run: |
-        case "${PLATFORM}" in
-          neon-captest-reuse)
-            CONNSTR=${{ secrets.BENCHMARK_CAPTEST_CONNSTR }}
-            ;;
-          neon-captest-new | neon-captest-prefetch)
-            CONNSTR=${{ steps.create-neon-project.outputs.dsn }}
-            ;;
-          rds-aurora)
-            CONNSTR=${{ secrets.BENCHMARK_RDS_CONNSTR }}
-            ;;
-          *)
-            echo 2>&1 "Unknown PLATFORM=${PLATFORM}. Allowed only 'neon-captest-reuse', 'neon-captest-new', 'neon-captest-prefetch' or 'rds-aurora'"
-            exit 1
-            ;;
-        esac
-
-        echo "connstr=${CONNSTR}" >> $GITHUB_OUTPUT
-
-        psql ${CONNSTR} -c "SELECT version();"
-
-    - name: Set database options
-      if: matrix.platform == 'neon-captest-prefetch'
-      run: |
-        psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE main SET enable_seqscan_prefetch=on"
-        psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE main SET seqscan_prefetch_buffers=10"
-      env:
-        BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
-
-    - name: Benchmark init
-      uses: ./.github/actions/run-python-test-set
-      with:
-        build_type: ${{ env.BUILD_TYPE }}
-        test_selection: performance
-        run_in_parallel: false
-        save_perf_report: ${{ env.SAVE_PERF_REPORT }}
-        extra_params: -m remote_cluster --timeout 21600 -k test_pgbench_remote_init
-      env:
-        BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
-        VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
-        PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
-
-    - name: Benchmark simple-update
-      uses: ./.github/actions/run-python-test-set
-      with:
-        build_type: ${{ env.BUILD_TYPE }}
-        test_selection: performance
-        run_in_parallel: false
-        save_perf_report: ${{ env.SAVE_PERF_REPORT }}
-        extra_params: -m remote_cluster --timeout 21600 -k test_pgbench_remote_simple_update
-      env:
-        BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
-        VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
-        PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
-
-    - name: Benchmark select-only
-      uses: ./.github/actions/run-python-test-set
-      with:
-        build_type: ${{ env.BUILD_TYPE }}
-        test_selection: performance
-        run_in_parallel: false
-        save_perf_report: ${{ env.SAVE_PERF_REPORT }}
-        extra_params: -m remote_cluster --timeout 21600 -k test_pgbench_remote_select_only
-      env:
-        BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
-        VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
-        PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
-
-    - name: Create Allure report
-      if: success() || failure()
-      uses: ./.github/actions/allure-report
-      with:
-        action: generate
-        build_type: ${{ env.BUILD_TYPE }}
-
-    - name: Delete Neon Project
-      if: ${{ steps.create-neon-project.outputs.project_id && always() }}
-      uses: ./.github/actions/neon-project-delete
-      with:
-        environment: dev
-        project_id: ${{ steps.create-neon-project.outputs.project_id }}
-        api_key: ${{ secrets.NEON_CAPTEST_API_KEY }}
-
-    - name: Post to a Slack channel
-      if: ${{ github.event.schedule && failure() }}
-      uses: slackapi/slack-github-action@v1
-      with:
-        channel-id: "C033QLM5P7D" # dev-staging-stream
-        slack-message: "Periodic perf testing ${{ matrix.platform }}: ${{ job.status }}\n${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}"
-      env:
-        SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}

.github/workflows/codestyle.yml

@@ -8,7 +8,7 @@ on:
 
 defaults:
   run:
-    shell: bash -euxo pipefail {0}
+    shell: bash -ex {0}
 
 concurrency:
   # Allow only one workflow per any non-`main` branch.
@@ -17,30 +17,35 @@ concurrency:
 
 env:
   RUST_BACKTRACE: 1
-  COPT: '-Werror'
 
 jobs:
   check-codestyle-rust:
     strategy:
       fail-fast: false
       matrix:
-        # XXX: both OSes have rustup
-        #   * https://github.com/actions/runner-images/blob/main/images/macos/macos-12-Readme.md#rust-tools
-        #   * https://github.com/actions/runner-images/blob/main/images/linux/Ubuntu2204-Readme.md#rust-tools
-        # this is all we need to install our toolchain later via rust-toolchain.toml
-        # so don't install any toolchain explicitly.
+        # If we want to duplicate this job for different
+        # Rust toolchains (e.g. nightly or 1.37.0), add them here.
+        rust_toolchain: [1.58]
         os: [ubuntu-latest, macos-latest]
-    timeout-minutes: 90
-    name: check codestyle rust and postgres
+    timeout-minutes: 50
+    name: run regression test suite
     runs-on: ${{ matrix.os }}
 
     steps:
       - name: Checkout
-        uses: actions/checkout@v3
+        uses: actions/checkout@v2
         with:
           submodules: true
           fetch-depth: 2
 
+      - name: Install rust toolchain ${{ matrix.rust_toolchain }}
+        uses: actions-rs/toolchain@v1
+        with:
+          profile: minimal
+          toolchain: ${{ matrix.rust_toolchain }}
+          components: rustfmt, clippy
+          override: true
+
       - name: Check formatting
         run: cargo fmt --all -- --check
 
@@ -48,35 +53,23 @@ jobs:
         if: matrix.os == 'ubuntu-latest'
         run: |
           sudo apt update
-          sudo apt install build-essential libreadline-dev zlib1g-dev flex bison libseccomp-dev libssl-dev protobuf-compiler
+          sudo apt install build-essential libreadline-dev zlib1g-dev flex bison libseccomp-dev libssl-dev
 
       - name: Install macOS postgres dependencies
         if: matrix.os == 'macos-latest'
-        run: brew install flex bison openssl protobuf
+        run: brew install flex bison openssl
 
-      - name: Set pg 14 revision for caching
-        id: pg_v14_rev
-        run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v14) >> $GITHUB_OUTPUT
-        shell: bash -euxo pipefail {0}
+      - name: Set pg revision for caching
+        id: pg_ver
+        run: echo ::set-output name=pg_rev::$(git rev-parse HEAD:vendor/postgres)
 
-      - name: Set pg 15 revision for caching
-        id: pg_v15_rev
-        run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v15) >> $GITHUB_OUTPUT
-        shell: bash -euxo pipefail {0}
-
-      - name: Cache postgres v14 build
-        id: cache_pg_14
-        uses: actions/cache@v3
+      - name: Cache postgres build
+        id: cache_pg
+        uses: actions/cache@v2
         with:
-          path: pg_install/v14
-          key: v1-${{ runner.os }}-${{ matrix.build_type }}-pg-${{ steps.pg_v14_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
-
-      - name: Cache postgres v15 build
-        id: cache_pg_15
-        uses: actions/cache@v3
-        with:
-          path: pg_install/v15
-          key: v1-${{ runner.os }}-${{ matrix.build_type }}-pg-${{ steps.pg_v15_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
+          path: |
+            tmp_install/
+          key: ${{ runner.os }}-pg-${{ steps.pg_ver.outputs.pg_rev }}
 
       - name: Set extra env for macOS
         if: matrix.os == 'macos-latest'
@@ -84,55 +77,37 @@ jobs:
           echo 'LDFLAGS=-L/usr/local/opt/openssl@3/lib' >> $GITHUB_ENV
           echo 'CPPFLAGS=-I/usr/local/opt/openssl@3/include' >> $GITHUB_ENV
 
-      - name: Build postgres v14
-        if: steps.cache_pg_14.outputs.cache-hit != 'true'
-        run: make postgres-v14
-        shell: bash -euxo pipefail {0}
+      - name: Build postgres
+        if: steps.cache_pg.outputs.cache-hit != 'true'
+        run: make postgres
 
-      - name: Build postgres v15
-        if: steps.cache_pg_15.outputs.cache-hit != 'true'
-        run: make postgres-v15
-        shell: bash -euxo pipefail {0}
-
-      - name: Build neon extensions
-        run: make neon-pg-ext
+      # Plain configure output can contain weird errors like 'error: C compiler cannot create executables'
+      # and the real cause will be inside config.log
+      - name: Print configure logs in case of failure
+        if: failure()
+        continue-on-error: true
+        run: |
+          echo '' && echo '=== config.log ===' && echo ''
+          cat tmp_install/build/config.log
+          echo '' && echo '=== configure.log ===' && echo ''
+          cat tmp_install/build/configure.log
 
       - name: Cache cargo deps
         id: cache_cargo
-        uses: actions/cache@v3
+        uses: actions/cache@v2
         with:
           path: |
             ~/.cargo/registry
             !~/.cargo/registry/src
             ~/.cargo/git
             target
-          key: v6-${{ runner.os }}-cargo-${{ hashFiles('./Cargo.lock') }}-rust
+          key: v1-${{ runner.os }}-cargo-${{ hashFiles('./Cargo.lock') }}-rust-${{ matrix.rust_toolchain }}
 
       - name: Run cargo clippy
         run: ./run_clippy.sh
 
       - name: Ensure all project builds
-        run: cargo build --locked --all --all-targets
-
-  check-rust-dependencies:
-    runs-on: dev
-    container:
-      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
-      options: --init
-
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-        with:
-          submodules: false
-          fetch-depth: 1
-
-      # https://github.com/facebookincubator/cargo-guppy/tree/bec4e0eb29dcd1faac70b1b5360267fc02bf830e/tools/cargo-hakari#2-keep-the-workspace-hack-up-to-date-in-ci
-      - name: Check every project module is covered by Hakari
-        run: |
-          cargo hakari generate --diff  # workspace-hack Cargo.toml is up-to-date
-          cargo hakari manage-deps --dry-run  # all workspace crates depend on workspace-hack
-        shell: bash -euxo pipefail {0}
+        run: cargo build --all --all-targets
 
   check-codestyle-python:
     runs-on: [ self-hosted, Linux, k8s-runner ]
@@ -153,14 +128,8 @@ jobs:
       - name: Install Python deps
         run: ./scripts/pysync
 
-      - name: Run isort to ensure code format
-        run: poetry run isort --diff --check .
-
-      - name: Run black to ensure code format
-        run: poetry run black --diff --check .
-
-      - name: Run flake8 to ensure code format
-        run: poetry run flake8 .
+      - name: Run yapf to ensure code format
+        run: poetry run yapf --recursive --diff .
 
       - name: Run mypy to check types
         run: poetry run mypy .

.github/workflows/notifications.yml

@@ -0,0 +1,45 @@
+name: Send Notifications
+
+on:
+  push:
+    branches: [ main ]
+
+jobs:
+  send-notifications:
+    timeout-minutes: 30
+    name: send commit notifications
+    runs-on: ubuntu-latest
+
+    steps:
+
+      - name: Checkout
+        uses: actions/checkout@v2
+        with:
+          submodules: true
+          fetch-depth: 2
+
+      - name: Form variables for notification message
+        id: git_info_grab
+        run: |
+          git_stat=$(git show --stat=50)
+          git_stat="${git_stat//'%'/'%25'}"
+          git_stat="${git_stat//$'\n'/'%0A'}"
+          git_stat="${git_stat//$'\r'/'%0D'}"
+          git_stat="${git_stat// / }" # space -> 'Space En', as github tends to eat ordinary spaces
+          echo "::set-output name=git_stat::$git_stat"
+          echo "::set-output name=sha_short::$(git rev-parse --short HEAD)"
+          echo "##[set-output name=git_branch;]$(echo ${GITHUB_REF#refs/heads/})"
+
+      - name: Send notification
+        uses: appleboy/telegram-action@master
+        with:
+          to: ${{ secrets.TELEGRAM_TO }}
+          token: ${{ secrets.TELEGRAM_TOKEN }}
+          format: markdown
+          args: |
+            *@${{ github.actor }} pushed to* [${{ github.repository }}:${{steps.git_info_grab.outputs.git_branch}}](github.com/${{ github.repository }}/commit/${{steps.git_info_grab.outputs.sha_short }})
+
+            ```
+            ${{ steps.git_info_grab.outputs.git_stat }}
+            ```
+

.github/workflows/pg_clients.yml

@@ -19,12 +19,8 @@ concurrency:
 
 jobs:
   test-postgres-client-libs:
-    # TODO: switch to gen2 runner, requires docker
     runs-on: [ ubuntu-latest ]
 
-    env:
-      TEST_OUTPUT: /tmp/test_output
-
     steps:
     - name: Checkout
       uses: actions/checkout@v3
@@ -44,26 +40,20 @@ jobs:
         key: v1-${{ runner.os }}-python-deps-${{ hashFiles('poetry.lock') }}
 
     - name: Install Python deps
-      shell: bash -euxo pipefail {0}
+      shell: bash -ex {0}
       run: ./scripts/pysync
 
-    - name: Create Neon Project
-      id: create-neon-project
-      uses: ./.github/actions/neon-project-create
-      with:
-        environment: staging
-        api_key: ${{ secrets.NEON_STAGING_API_KEY }}
-
     - name: Run pytest
       env:
         REMOTE_ENV: 1
-        BENCHMARK_CONNSTR: ${{ steps.create-neon-project.outputs.dsn }}
+        BENCHMARK_CONNSTR: "${{ secrets.BENCHMARK_STAGING_CONNSTR }}"
+        TEST_OUTPUT: /tmp/test_output
         POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
-      shell: bash -euxo pipefail {0}
+      shell: bash -ex {0}
       run: |
         # Test framework expects we have psql binary;
         # but since we don't really need it in this test, let's mock it
-        mkdir -p "$POSTGRES_DISTRIB_DIR/v14/bin" && touch "$POSTGRES_DISTRIB_DIR/v14/bin/psql";
+        mkdir -p "$POSTGRES_DISTRIB_DIR/bin" && touch "$POSTGRES_DISTRIB_DIR/bin/psql";
         ./scripts/pytest \
           --junitxml=$TEST_OUTPUT/junit.xml \
           --tb=short \
@@ -71,26 +61,9 @@ jobs:
           -m "remote_cluster" \
           -rA "test_runner/pg_clients"
 
-    - name: Delete Neon Project
-      if: ${{ always() }}
-      uses: ./.github/actions/neon-project-delete
-      with:
-        environment: staging
-        project_id: ${{ steps.create-neon-project.outputs.project_id }}
-        api_key: ${{ secrets.NEON_STAGING_API_KEY }}
-
-    # We use GitHub's action upload-artifact because `ubuntu-latest` doesn't have configured AWS CLI.
-    # It will be fixed after switching to gen2 runner
-    - name: Upload python test logs
-      if: always()
-      uses: actions/upload-artifact@v3
-      with:
-        retention-days: 7
-        name: python-test-pg_clients-${{ runner.os }}-stage-logs
-        path: ${{ env.TEST_OUTPUT }}
-
     - name: Post to a Slack channel
-      if: ${{ github.event.schedule && failure() }}
+      if: failure()
+      id: slack
       uses: slackapi/slack-github-action@v1
       with:
         channel-id: "C033QLM5P7D" # dev-staging-stream

.gitignore

@@ -1,6 +1,6 @@
-/pg_install
 /target
 /tmp_check
+/tmp_install
 /tmp_check_cli
 __pycache__/
 test_output/
@@ -15,6 +15,3 @@ test_output/
 
 *.key
 *.crt
-*.o
-*.so
-*.Po

.gitmodules

@@ -1,8 +1,4 @@
-[submodule "vendor/postgres-v14"]
-	path = vendor/postgres-v14
-	url = https://github.com/neondatabase/postgres.git
-	branch = REL_14_STABLE_neon
-[submodule "vendor/postgres-v15"]
-	path = vendor/postgres-v15
-	url = https://github.com/neondatabase/postgres.git
-	branch = REL_15_STABLE_neon
+[submodule "vendor/postgres"]
+	path = vendor/postgres
+	url = https://github.com/zenithdb/postgres
+	branch = main

.yapfignore

@@ -0,0 +1,10 @@
+# This file is only read when `yapf` is run from this directory.
+# Hence we only top-level directories here to avoid confusion.
+# See source code for the exact file format: https://github.com/google/yapf/blob/c6077954245bc3add82dafd853a1c7305a6ebd20/yapf/yapflib/file_resources.py#L40-L43
+vendor/
+target/
+tmp_install/
+__pycache__/
+test_output/
+.neon/
+.git/

CODEOWNERS

@@ -1,10 +0,0 @@
-/compute_tools/ @neondatabase/control-plane
-/control_plane/ @neondatabase/compute @neondatabase/storage
-/libs/pageserver_api/ @neondatabase/compute @neondatabase/storage
-/libs/postgres_ffi/ @neondatabase/compute 
-/libs/remote_storage/ @neondatabase/storage 
-/libs/safekeeper_api/ @neondatabase/safekeepers  
-/pageserver/ @neondatabase/compute @neondatabase/storage 
-/pgxn/ @neondatabase/compute
-/proxy/ @neondatabase/control-plane 
-/safekeeper/ @neondatabase/safekeepers

CONTRIBUTING.md

@@ -11,15 +11,17 @@ than it was before.
 
 ## Submitting changes
 
-1. Get at least one +1 on your PR before you push.
+1. Make a PR for every change.
+
+   Even seemingly trivial patches can break things in surprising ways.
+Use of common sense is OK. If you're only fixing a typo in a comment,
+it's probably fine to just push it. But if in doubt, open a PR.
+
+2. Get at least one +1 on your PR before you push.
 
    For simple patches, it will only take a minute for someone to review
 it.
 
-2. Don't force push small changes after making the PR ready for review.
-Doing so will force readers to re-read your entire PR, which will delay
-the review process.
-
 3. Always keep the CI green.
 
    Do not push, if the CI failed on your PR. Even if you think it's not

Cargo.toml

@@ -1,23 +1,12 @@
-# 'named-profiles' feature was stabilized in cargo 1.57. This line makes the
-# build work with older cargo versions.
-#
-# We have this because as of this writing, the latest cargo Debian package
-# that's available is 1.56. (Confusingly, the Debian package version number
-# is 0.57, whereas 'cargo --version' says 1.56.)
-#
-# See https://tracker.debian.org/pkg/cargo for the current status of the
-# package. When that gets updated, we can remove this.
-cargo-features = ["named-profiles"]
-
 [workspace]
 members = [
-    "broker",
     "compute_tools",
     "control_plane",
     "pageserver",
     "proxy",
     "safekeeper",
     "workspace_hack",
+    "neon_local",
     "libs/*",
 ]
 
@@ -26,64 +15,7 @@ members = [
 # Besides, debug info should not affect the performance.
 debug = true
 
-# disable debug symbols for all packages except this one to decrease binaries size
-[profile.release.package."*"]
-debug = false
-
-[profile.release-line-debug]
-inherits = "release"
-debug = 1 # true = 2 = all symbols, 1 = line only
-[profile.release-line-debug-lto]
-inherits = "release"
-debug = 1 # true = 2 = all symbols, 1 = line only
-lto = true
-
-[profile.release-line-debug-size]
-inherits = "release"
-debug = 1 # true = 2 = all symbols, 1 = line only
-opt-level = "s"
-[profile.release-line-debug-zize]
-inherits = "release"
-debug = 1 # true = 2 = all symbols, 1 = line only
-opt-level = "z"
-[profile.release-line-debug-size-lto]
-inherits = "release"
-debug = 1 # true = 2 = all symbols, 1 = line only
-opt-level = "s"
-lto = true
-[profile.release-line-debug-zize-lto]
-inherits = "release"
-debug = 1 # true = 2 = all symbols, 1 = line only
-opt-level = "z"
-lto = true
-
-[profile.release-no-debug]
-inherits = "release"
-debug = false # true = 2 = all symbols, 1 = line only
-
-[profile.release-no-debug-size]
-inherits = "release"
-debug = false # true = 2 = all symbols, 1 = line only
-opt-level = "s"
-[profile.release-no-debug-zize]
-inherits = "release"
-debug = false # true = 2 = all symbols, 1 = line only
-opt-level = "z"
-
-[profile.release-no-debug-size-lto]
-inherits = "release"
-debug = false # true = 2 = all symbols, 1 = line only
-opt-level = "s"
-lto = true
-
-[profile.release-no-debug-zize-lto]
-inherits = "release"
-debug = false # true = 2 = all symbols, 1 = line only
-opt-level = "z"
-lto = true
-
-
 # This is only needed for proxy's tests.
 # TODO: we should probably fork `tokio-postgres-rustls` instead.
 [patch.crates-io]
-tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev="d052ee8b86fff9897c77b0fe89ea9daba0e1fa38" }
+tokio-postgres = { git = "https://github.com/zenithdb/rust-postgres.git", rev="d052ee8b86fff9897c77b0fe89ea9daba0e1fa38" }

Dockerfile

@@ -1,50 +1,37 @@
-### Creates a storage Docker image with postgres, pageserver, safekeeper and proxy binaries.
-### The image itself is mainly used as a container for the binaries and for starting e2e tests with custom parameters.
-### By default, the binaries inside the image have some mock parameters and can start, but are not intended to be used
-### inside this image in the real deployments.
-ARG REPOSITORY=369495373322.dkr.ecr.eu-central-1.amazonaws.com
-ARG IMAGE=rust
-ARG TAG=pinned
-
 # Build Postgres
-FROM $REPOSITORY/$IMAGE:$TAG AS pg-build
-WORKDIR /home/nonroot
+FROM neondatabase/rust:1.58 AS pg-build
+WORKDIR /pg
 
-COPY --chown=nonroot vendor/postgres-v14 vendor/postgres-v14
-COPY --chown=nonroot vendor/postgres-v15 vendor/postgres-v15
-COPY --chown=nonroot pgxn pgxn
-COPY --chown=nonroot Makefile Makefile
-COPY --chown=nonroot scripts/ninstall.sh scripts/ninstall.sh
+USER root
+
+COPY vendor/postgres vendor/postgres
+COPY Makefile Makefile
 
 ENV BUILD_TYPE release
 RUN set -e \
-    && mold -run make -j $(nproc) -s neon-pg-ext \
-    && rm -rf pg_install/build \
-    && tar -C pg_install -czf /home/nonroot/postgres_install.tar.gz .
+    && mold -run make -j $(nproc) -s postgres \
+    && rm -rf tmp_install/build \
+    && tar -C tmp_install -czf /postgres_install.tar.gz .
 
-# Build neon binaries
-FROM $REPOSITORY/$IMAGE:$TAG AS build
-WORKDIR /home/nonroot
+# Build zenith binaries
+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/pg_install/v14/include/postgresql/server pg_install/v14/include/postgresql/server
-COPY --from=pg-build /home/nonroot/pg_install/v15/include/postgresql/server pg_install/v15/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 --bin pageserver --bin pageserver_binutils --bin draw_timeline_dir --bin safekeeper --bin neon_broker --bin proxy --locked --release \
+    && sudo -E "PATH=$PATH" mold -run cargo build --release \
     && cachepot -s
 
 # Build final image
@@ -53,38 +40,27 @@ 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 \
         ca-certificates \
     && rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* \
-    && useradd -d /data neon \
-    && chown -R neon:neon /data
+    && useradd -d /data zenith \
+    && chown -R zenith:zenith /data
 
-COPY --from=build --chown=neon:neon /home/nonroot/target/release/pageserver          /usr/local/bin
-COPY --from=build --chown=neon:neon /home/nonroot/target/release/pageserver_binutils /usr/local/bin
-COPY --from=build --chown=neon:neon /home/nonroot/target/release/draw_timeline_dir   /usr/local/bin
-COPY --from=build --chown=neon:neon /home/nonroot/target/release/safekeeper          /usr/local/bin
-COPY --from=build --chown=neon:neon /home/nonroot/target/release/neon_broker         /usr/local/bin
-COPY --from=build --chown=neon:neon /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/pg_install/v14 /usr/local/v14/
-COPY --from=pg-build /home/nonroot/pg_install/v15 /usr/local/v15/
-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/
 
-# By default, pageserver uses `.neon/` working directory in WORKDIR, so create one and fill it with the dummy config.
-# Now, when `docker run ... pageserver` is run, it can start without errors, yet will have some default dummy values.
-RUN mkdir -p /data/.neon/ && chown -R neon:neon /data/.neon/ \
-    && /usr/local/bin/pageserver -D /data/.neon/ --init \
-       -c "id=1234" \
-       -c "broker_endpoints=['http://etcd:2379']" \
-       -c "pg_distrib_dir='/usr/local/'" \
-       -c "listen_pg_addr='0.0.0.0:6400'" \
-       -c "listen_http_addr='0.0.0.0:9898'"
+COPY docker-entrypoint.sh /docker-entrypoint.sh
 
 VOLUME ["/data"]
-USER neon
+USER zenith
 EXPOSE 6400
-EXPOSE 9898
+ENTRYPOINT ["/docker-entrypoint.sh"]
+CMD ["pageserver"]

Dockerfile.compute-node-v14

@@ -1,218 +0,0 @@
-#
-# This file is identical to the Dockerfile.compute-node-v15 file
-# except for the version of Postgres that is built.
-#
-
-ARG TAG=pinned
-
-#########################################################################################
-#
-# Layer "build-deps"
-#
-#########################################################################################
-FROM debian:bullseye-slim AS build-deps
-RUN apt update &&  \
-    apt install -y git autoconf automake libtool build-essential bison flex libreadline-dev \
-    zlib1g-dev libxml2-dev libcurl4-openssl-dev libossp-uuid-dev wget pkg-config libssl-dev
-
-#########################################################################################
-#
-# Layer "pg-build"
-# Build Postgres from the neon postgres repository.
-#
-#########################################################################################
-FROM build-deps AS pg-build
-COPY vendor/postgres-v14 postgres
-RUN cd postgres && \
-    ./configure CFLAGS='-O2 -g3' --enable-debug --with-openssl --with-uuid=ossp && \
-    make MAKELEVEL=0 -j $(getconf _NPROCESSORS_ONLN) -s install && \
-    make MAKELEVEL=0 -j $(getconf _NPROCESSORS_ONLN) -s -C contrib/ install && \
-    # Install headers
-    make MAKELEVEL=0 -j $(getconf _NPROCESSORS_ONLN) -s -C src/include install && \
-    make MAKELEVEL=0 -j $(getconf _NPROCESSORS_ONLN) -s -C src/interfaces/libpq install
-
-#########################################################################################
-#
-# Layer "postgis-build"
-# Build PostGIS from the upstream PostGIS mirror.
-#
-#########################################################################################
-FROM build-deps AS postgis-build
-COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
-RUN apt update && \
-    apt install -y gdal-bin libgdal-dev libprotobuf-c-dev protobuf-c-compiler xsltproc
-
-RUN wget https://download.osgeo.org/postgis/source/postgis-3.3.1.tar.gz && \
-    tar xvzf postgis-3.3.1.tar.gz && \
-    cd postgis-3.3.1 && \
-    ./autogen.sh && \
-    export PATH="/usr/local/pgsql/bin:$PATH" && \
-    ./configure && \
-    make -j $(getconf _NPROCESSORS_ONLN) install && \
-    cd extensions/postgis && \
-    make clean && \
-    make -j $(getconf _NPROCESSORS_ONLN) install && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_raster.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_tiger_geocoder.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_topology.control
-
-#########################################################################################
-#
-# Layer "plv8-build"
-# Build plv8
-#
-#########################################################################################
-FROM build-deps AS plv8-build
-COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
-RUN apt update && \
-    apt install -y ninja-build python3-dev libc++-dev libc++abi-dev libncurses5 binutils
-
-# https://github.com/plv8/plv8/issues/475:
-#   v8 uses gold for linking and sets `--thread-count=4` which breaks
-#   gold version <= 1.35 (https://sourceware.org/bugzilla/show_bug.cgi?id=23607)
-# Install newer gold version manually as debian-testing binutils version updates
-# libc version, which in turn breaks other extension built against non-testing libc.
-RUN wget https://ftp.gnu.org/gnu/binutils/binutils-2.38.tar.gz && \
-    tar xvzf binutils-2.38.tar.gz && \
-    cd binutils-2.38 && \
-    cd libiberty && ./configure && make -j $(getconf _NPROCESSORS_ONLN) && \
-    cd ../bfd && ./configure && make bfdver.h && \
-    cd ../gold && ./configure && make -j $(getconf _NPROCESSORS_ONLN) && make install && \
-    cp /usr/local/bin/ld.gold /usr/bin/gold
-
-# Sed is used to patch for https://github.com/plv8/plv8/issues/503
-RUN wget https://github.com/plv8/plv8/archive/refs/tags/v3.1.4.tar.gz && \
-    tar xvzf v3.1.4.tar.gz && \
-    cd plv8-3.1.4 && \
-    export PATH="/usr/local/pgsql/bin:$PATH" && \
-    sed -i 's/MemoryContextAlloc(/MemoryContextAllocZero(/' plv8.cc && \
-    make DOCKER=1 -j $(getconf _NPROCESSORS_ONLN) install && \
-    rm -rf /plv8-* && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/plv8.control
-
-#########################################################################################
-#
-# Layer "h3-pg-build"
-# Build h3_pg
-#
-#########################################################################################
-FROM build-deps AS h3-pg-build
-COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
-
-# packaged cmake is too old
-RUN wget https://github.com/Kitware/CMake/releases/download/v3.24.2/cmake-3.24.2-linux-x86_64.sh \
-      -q -O /tmp/cmake-install.sh \
-      && chmod u+x /tmp/cmake-install.sh \
-      && /tmp/cmake-install.sh --skip-license --prefix=/usr/local/ \
-      && rm /tmp/cmake-install.sh
-
-RUN wget https://github.com/uber/h3/archive/refs/tags/v4.0.1.tar.gz -O h3.tgz && \
-    tar xvzf h3.tgz  && \
-    cd h3-4.0.1 && \
-    mkdir build && \
-    cd build && \
-    cmake .. -DCMAKE_BUILD_TYPE=Release && \
-    make -j $(getconf _NPROCESSORS_ONLN) && \
-    DESTDIR=/h3 make install && \
-    cp -R /h3/usr / && \
-    rm -rf build
-
-RUN wget https://github.com/zachasme/h3-pg/archive/refs/tags/v4.0.1.tar.gz -O h3-pg.tgz && \
-    tar xvzf h3-pg.tgz && \
-    cd h3-pg-4.0.1 && \
-    export PATH="/usr/local/pgsql/bin:$PATH" && \
-    make -j $(getconf _NPROCESSORS_ONLN) && \
-    make -j $(getconf _NPROCESSORS_ONLN) install && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/h3.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/h3_postgis.control
-
-#########################################################################################
-#
-# Layer "neon-pg-ext-build"
-# compile neon extensions
-#
-#########################################################################################
-FROM build-deps AS neon-pg-ext-build
-COPY --from=postgis-build /usr/local/pgsql/ /usr/local/pgsql/
-COPY --from=plv8-build /usr/local/pgsql/ /usr/local/pgsql/
-COPY --from=h3-pg-build /usr/local/pgsql/ /usr/local/pgsql/
-COPY --from=h3-pg-build /h3/usr /
-COPY pgxn/ pgxn/
-
-RUN make -j $(getconf _NPROCESSORS_ONLN) \
-        PG_CONFIG=/usr/local/pgsql/bin/pg_config \
-        -C pgxn/neon \
-        -s install
-
-#########################################################################################
-#
-# Compile and run the Neon-specific `compute_ctl` binary
-#
-#########################################################################################
-FROM 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:$TAG AS compute-tools
-USER nonroot
-# Copy entire project to get Cargo.* files with proper dependencies for the whole project
-COPY --chown=nonroot . .
-RUN cd compute_tools && cargo build --locked --profile release-line-debug-size-lto
-
-#########################################################################################
-#
-# Clean up postgres folder before inclusion
-#
-#########################################################################################
-FROM neon-pg-ext-build AS postgres-cleanup-layer
-COPY --from=neon-pg-ext-build /usr/local/pgsql /usr/local/pgsql
-
-# Remove binaries from /bin/ that we won't use (or would manually copy & install otherwise)
-RUN cd /usr/local/pgsql/bin && rm ecpg raster2pgsql shp2pgsql pgtopo_export pgtopo_import pgsql2shp
-
-# Remove headers that we won't need anymore - we've completed installation of all extensions
-RUN rm -r /usr/local/pgsql/include
-
-# Remove now-useless PGXS src infrastructure
-RUN rm -r /usr/local/pgsql/lib/pgxs/src
-
-# Remove static postgresql libraries - all compilation is finished, so we
-# can now remove these files - they must be included in other binaries by now
-# if they were to be used by other libraries.
-RUN rm /usr/local/pgsql/lib/lib*.a
-
-#########################################################################################
-#
-# Final layer
-# Put it all together into the final image
-#
-#########################################################################################
-FROM debian:bullseye-slim
-# Add user postgres
-RUN mkdir /var/db && useradd -m -d /var/db/postgres postgres && \
-    echo "postgres:test_console_pass" | chpasswd && \
-    mkdir /var/db/postgres/compute && mkdir /var/db/postgres/specs && \
-    chown -R postgres:postgres /var/db/postgres && \
-    chmod 0750 /var/db/postgres/compute && \
-    echo '/usr/local/lib' >> /etc/ld.so.conf && /sbin/ldconfig
-
-COPY --from=postgres-cleanup-layer --chown=postgres /usr/local/pgsql /usr/local
-COPY --from=compute-tools --chown=postgres /home/nonroot/target/release-line-debug-size-lto/compute_ctl /usr/local/bin/compute_ctl
-
-# Install:
-# libreadline8 for psql
-# libossp-uuid16 for extension ossp-uuid
-# libgeos, libgdal, libproj and libprotobuf-c1 for PostGIS
-#
-# Lastly, link compute_ctl into zenith_ctl while we're at it,
-# so that we don't need to put this in another layer.
-RUN apt update &&  \
-    apt install --no-install-recommends -y \
-        libreadline8 \
-        libossp-uuid16 \
-        libgeos-c1v5 \
-        libgdal28 \
-        libproj19 \
-        libprotobuf-c1 && \
-    rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* && \
-    ln /usr/local/bin/compute_ctl /usr/local/bin/zenith_ctl
-
-USER postgres
-ENTRYPOINT ["/usr/local/bin/compute_ctl"]

Dockerfile.compute-node-v15

@@ -1,218 +0,0 @@
-#
-# This file is identical to the Dockerfile.compute-node-v14 file
-# except for the version of Postgres that is built.
-#
-
-ARG TAG=pinned
-
-#########################################################################################
-#
-# Layer "build-deps"
-#
-#########################################################################################
-FROM debian:bullseye-slim AS build-deps
-RUN apt update &&  \
-    apt install -y git autoconf automake libtool build-essential bison flex libreadline-dev \
-    zlib1g-dev libxml2-dev libcurl4-openssl-dev libossp-uuid-dev wget pkg-config libssl-dev
-
-#########################################################################################
-#
-# Layer "pg-build"
-# Build Postgres from the neon postgres repository.
-#
-#########################################################################################
-FROM build-deps AS pg-build
-COPY vendor/postgres-v15 postgres
-RUN cd postgres && \
-    ./configure CFLAGS='-O2 -g3' --enable-debug --with-openssl --with-uuid=ossp && \
-    make MAKELEVEL=0 -j $(getconf _NPROCESSORS_ONLN) -s install && \
-    make MAKELEVEL=0 -j $(getconf _NPROCESSORS_ONLN) -s -C contrib/ install && \
-    # Install headers
-    make MAKELEVEL=0 -j $(getconf _NPROCESSORS_ONLN) -s -C src/include install && \
-    make MAKELEVEL=0 -j $(getconf _NPROCESSORS_ONLN) -s -C src/interfaces/libpq install
-
-#########################################################################################
-#
-# Layer "postgis-build"
-# Build PostGIS from the upstream PostGIS mirror.
-#
-#########################################################################################
-FROM build-deps AS postgis-build
-COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
-RUN apt update && \
-    apt install -y gdal-bin libgdal-dev libprotobuf-c-dev protobuf-c-compiler xsltproc
-
-RUN wget https://download.osgeo.org/postgis/source/postgis-3.3.1.tar.gz && \
-    tar xvzf postgis-3.3.1.tar.gz && \
-    cd postgis-3.3.1 && \
-    ./autogen.sh && \
-    export PATH="/usr/local/pgsql/bin:$PATH" && \
-    ./configure && \
-    make -j $(getconf _NPROCESSORS_ONLN) install && \
-    cd extensions/postgis && \
-    make clean && \
-    make -j $(getconf _NPROCESSORS_ONLN) install && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_raster.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_tiger_geocoder.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_topology.control
-
-#########################################################################################
-#
-# Layer "plv8-build"
-# Build plv8
-#
-#########################################################################################
-FROM build-deps AS plv8-build
-COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
-RUN apt update && \
-    apt install -y ninja-build python3-dev libc++-dev libc++abi-dev libncurses5 binutils
-
-# https://github.com/plv8/plv8/issues/475:
-#   v8 uses gold for linking and sets `--thread-count=4` which breaks
-#   gold version <= 1.35 (https://sourceware.org/bugzilla/show_bug.cgi?id=23607)
-# Install newer gold version manually as debian-testing binutils version updates
-# libc version, which in turn breaks other extension built against non-testing libc.
-RUN wget https://ftp.gnu.org/gnu/binutils/binutils-2.38.tar.gz && \
-    tar xvzf binutils-2.38.tar.gz && \
-    cd binutils-2.38 && \
-    cd libiberty && ./configure && make -j $(getconf _NPROCESSORS_ONLN) && \
-    cd ../bfd && ./configure && make bfdver.h && \
-    cd ../gold && ./configure && make -j $(getconf _NPROCESSORS_ONLN) && make install && \
-    cp /usr/local/bin/ld.gold /usr/bin/gold
-
-# Sed is used to patch for https://github.com/plv8/plv8/issues/503
-RUN wget https://github.com/plv8/plv8/archive/refs/tags/v3.1.4.tar.gz && \
-    tar xvzf v3.1.4.tar.gz && \
-    cd plv8-3.1.4 && \
-    export PATH="/usr/local/pgsql/bin:$PATH" && \
-    sed -i 's/MemoryContextAlloc(/MemoryContextAllocZero(/' plv8.cc && \
-    make DOCKER=1 -j $(getconf _NPROCESSORS_ONLN) install && \
-    rm -rf /plv8-* && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/plv8.control
-
-#########################################################################################
-#
-# Layer "h3-pg-build"
-# Build h3_pg
-#
-#########################################################################################
-FROM build-deps AS h3-pg-build
-COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
-
-# packaged cmake is too old
-RUN wget https://github.com/Kitware/CMake/releases/download/v3.24.2/cmake-3.24.2-linux-x86_64.sh \
-      -q -O /tmp/cmake-install.sh \
-      && chmod u+x /tmp/cmake-install.sh \
-      && /tmp/cmake-install.sh --skip-license --prefix=/usr/local/ \
-      && rm /tmp/cmake-install.sh
-
-RUN wget https://github.com/uber/h3/archive/refs/tags/v4.0.1.tar.gz -O h3.tgz && \
-    tar xvzf h3.tgz  && \
-    cd h3-4.0.1 && \
-    mkdir build && \
-    cd build && \
-    cmake .. -DCMAKE_BUILD_TYPE=Release && \
-    make -j $(getconf _NPROCESSORS_ONLN) && \
-    DESTDIR=/h3 make install && \
-    cp -R /h3/usr / && \
-    rm -rf build
-
-RUN wget https://github.com/zachasme/h3-pg/archive/refs/tags/v4.0.1.tar.gz -O h3-pg.tgz && \
-    tar xvzf h3-pg.tgz && \
-    cd h3-pg-4.0.1 && \
-    export PATH="/usr/local/pgsql/bin:$PATH" && \
-    make -j $(getconf _NPROCESSORS_ONLN) && \
-    make -j $(getconf _NPROCESSORS_ONLN) install && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/h3.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/h3_postgis.control
-
-#########################################################################################
-#
-# Layer "neon-pg-ext-build"
-# compile neon extensions
-#
-#########################################################################################
-FROM build-deps AS neon-pg-ext-build
-COPY --from=postgis-build /usr/local/pgsql/ /usr/local/pgsql/
-COPY --from=plv8-build /usr/local/pgsql/ /usr/local/pgsql/
-COPY --from=h3-pg-build /usr/local/pgsql/ /usr/local/pgsql/
-COPY --from=h3-pg-build /h3/usr /
-COPY pgxn/ pgxn/
-
-RUN make -j $(getconf _NPROCESSORS_ONLN) \
-        PG_CONFIG=/usr/local/pgsql/bin/pg_config \
-        -C pgxn/neon \
-        -s install
-
-#########################################################################################
-#
-# Compile and run the Neon-specific `compute_ctl` binary
-#
-#########################################################################################
-FROM 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:$TAG AS compute-tools
-USER nonroot
-# Copy entire project to get Cargo.* files with proper dependencies for the whole project
-COPY --chown=nonroot . .
-RUN cd compute_tools && cargo build --locked --profile release-line-debug-size-lto
-
-#########################################################################################
-#
-# Clean up postgres folder before inclusion
-#
-#########################################################################################
-FROM neon-pg-ext-build AS postgres-cleanup-layer
-COPY --from=neon-pg-ext-build /usr/local/pgsql /usr/local/pgsql
-
-# Remove binaries from /bin/ that we won't use (or would manually copy & install otherwise)
-RUN cd /usr/local/pgsql/bin && rm ecpg raster2pgsql shp2pgsql pgtopo_export pgtopo_import pgsql2shp
-
-# Remove headers that we won't need anymore - we've completed installation of all extensions
-RUN rm -r /usr/local/pgsql/include
-
-# Remove now-useless PGXS src infrastructure
-RUN rm -r /usr/local/pgsql/lib/pgxs/src
-
-# Remove static postgresql libraries - all compilation is finished, so we
-# can now remove these files - they must be included in other binaries by now
-# if they were to be used by other libraries.
-RUN rm /usr/local/pgsql/lib/lib*.a
-
-#########################################################################################
-#
-# Final layer
-# Put it all together into the final image
-#
-#########################################################################################
-FROM debian:bullseye-slim
-# Add user postgres
-RUN mkdir /var/db && useradd -m -d /var/db/postgres postgres && \
-    echo "postgres:test_console_pass" | chpasswd && \
-    mkdir /var/db/postgres/compute && mkdir /var/db/postgres/specs && \
-    chown -R postgres:postgres /var/db/postgres && \
-    chmod 0750 /var/db/postgres/compute && \
-    echo '/usr/local/lib' >> /etc/ld.so.conf && /sbin/ldconfig
-
-COPY --from=postgres-cleanup-layer --chown=postgres /usr/local/pgsql /usr/local
-COPY --from=compute-tools --chown=postgres /home/nonroot/target/release-line-debug-size-lto/compute_ctl /usr/local/bin/compute_ctl
-
-# Install:
-# libreadline8 for psql
-# libossp-uuid16 for extension ossp-uuid
-# libgeos, libgdal, libproj and libprotobuf-c1 for PostGIS
-#
-# Lastly, link compute_ctl into zenith_ctl while we're at it,
-# so that we don't need to put this in another layer.
-RUN apt update &&  \
-    apt install --no-install-recommends -y \
-        libreadline8 \
-        libossp-uuid16 \
-        libgeos-c1v5 \
-        libgdal28 \
-        libproj19 \
-        libprotobuf-c1 && \
-    rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* && \
-    ln /usr/local/bin/compute_ctl /usr/local/bin/zenith_ctl
-
-USER postgres
-ENTRYPOINT ["/usr/local/bin/compute_ctl"]

Dockerfile.compute-tools

@@ -1,29 +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
-ARG REPOSITORY=369495373322.dkr.ecr.eu-central-1.amazonaws.com
-ARG IMAGE=rust
-ARG TAG=pinned
-
-FROM $REPOSITORY/$IMAGE:$TAG 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 --locked --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

Makefile

@@ -1,7 +1,15 @@
 ROOT_PROJECT_DIR := $(dir $(abspath $(lastword $(MAKEFILE_LIST))))
 
-# Where to install Postgres, default is ./pg_install, maybe useful for package managers
-POSTGRES_INSTALL_DIR ?= $(ROOT_PROJECT_DIR)/pg_install/
+# Where to install Postgres, default is ./tmp_install, maybe useful for package managers
+POSTGRES_INSTALL_DIR ?= $(ROOT_PROJECT_DIR)/tmp_install
+
+# Seccomp BPF is only available for Linux
+UNAME_S := $(shell uname -s)
+ifeq ($(UNAME_S),Linux)
+	SECCOMP = --with-libseccomp
+else
+	SECCOMP =
+endif
 
 #
 # We differentiate between release / debug build types using the BUILD_TYPE
@@ -20,12 +28,6 @@ else
 	$(error Bad build type '$(BUILD_TYPE)', see Makefile for options)
 endif
 
-# Seccomp BPF is only available for Linux
-UNAME_S := $(shell uname -s)
-ifeq ($(UNAME_S),Linux)
-	PG_CONFIGURE_OPTS += --with-libseccomp
-endif
-
 # macOS with brew-installed openssl requires explicit paths
 # It can be configured with OPENSSL_PREFIX variable
 UNAME_S := $(shell uname -s)
@@ -34,12 +36,6 @@ ifeq ($(UNAME_S),Darwin)
     PG_CONFIGURE_OPTS += --with-includes=$(OPENSSL_PREFIX)/include --with-libraries=$(OPENSSL_PREFIX)/lib
 endif
 
-# Use -C option so that when PostgreSQL "make install" installs the
-# headers, the mtime of the headers are not changed when there have
-# been no changes to the files. Changing the mtime triggers an
-# unnecessary rebuild of 'postgres_ffi'.
-PG_CONFIGURE_OPTS += INSTALL='$(ROOT_PROJECT_DIR)/scripts/ninstall.sh -C'
-
 # Choose whether we should be silent or verbose
 CARGO_BUILD_FLAGS += --$(if $(filter s,$(MAKEFLAGS)),quiet,verbose)
 # Fix for a corner case when make doesn't pass a jobserver
@@ -52,149 +48,64 @@ CARGO_CMD_PREFIX += $(if $(filter n,$(MAKEFLAGS)),,+)
 CARGO_CMD_PREFIX += CARGO_TERM_PROGRESS_WHEN=never CI=1
 
 #
-# Top level Makefile to build Neon and PostgreSQL
+# Top level Makefile to build Zenith and PostgreSQL
 #
 .PHONY: all
-all: neon postgres neon-pg-ext
+all: zenith postgres
 
-### Neon Rust bits
+### Zenith Rust bits
 #
 # The 'postgres_ffi' depends on the Postgres headers.
-.PHONY: neon
-neon: postgres-v14-headers postgres-v15-headers
-	+@echo "Compiling Neon"
+.PHONY: zenith
+zenith: postgres-headers
+	+@echo "Compiling Zenith"
 	$(CARGO_CMD_PREFIX) cargo build $(CARGO_BUILD_FLAGS)
 
 ### PostgreSQL parts
-# The rules are duplicated for Postgres v14 and 15. We may want to refactor
-# to avoid the duplication in the future, but it's tolerable for now.
-#
-$(POSTGRES_INSTALL_DIR)/build/v14/config.status:
-	+@echo "Configuring Postgres v14 build"
-	mkdir -p $(POSTGRES_INSTALL_DIR)/build/v14
-	(cd $(POSTGRES_INSTALL_DIR)/build/v14 && \
-	$(ROOT_PROJECT_DIR)/vendor/postgres-v14/configure CFLAGS='$(PG_CFLAGS)' \
+$(POSTGRES_INSTALL_DIR)/build/config.status:
+	+@echo "Configuring postgres build"
+	mkdir -p $(POSTGRES_INSTALL_DIR)/build
+	(cd $(POSTGRES_INSTALL_DIR)/build && \
+	$(ROOT_PROJECT_DIR)/vendor/postgres/configure CFLAGS='$(PG_CFLAGS)' \
 		$(PG_CONFIGURE_OPTS) \
-		--prefix=$(abspath $(POSTGRES_INSTALL_DIR))/v14 > configure.log)
+		$(SECCOMP) \
+		--prefix=$(abspath $(POSTGRES_INSTALL_DIR)) > configure.log)
 
-$(POSTGRES_INSTALL_DIR)/build/v15/config.status:
-	+@echo "Configuring Postgres v15 build"
-	mkdir -p $(POSTGRES_INSTALL_DIR)/build/v15
-	(cd $(POSTGRES_INSTALL_DIR)/build/v15 && \
-	$(ROOT_PROJECT_DIR)/vendor/postgres-v15/configure CFLAGS='$(PG_CFLAGS)' \
-		$(PG_CONFIGURE_OPTS) \
-		--prefix=$(abspath $(POSTGRES_INSTALL_DIR))/v15 > configure.log)
+# nicer alias for running 'configure'
+.PHONY: postgres-configure
+postgres-configure: $(POSTGRES_INSTALL_DIR)/build/config.status
 
-# nicer alias to run 'configure'
-.PHONY: postgres-v14-configure
-postgres-v14-configure: $(POSTGRES_INSTALL_DIR)/build/v14/config.status
+# Install the PostgreSQL header files into $(POSTGRES_INSTALL_DIR)/include
+.PHONY: postgres-headers
+postgres-headers: postgres-configure
+	+@echo "Installing PostgreSQL headers"
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/src/include MAKELEVEL=0 install
 
-.PHONY: postgres-v15-configure
-postgres-v15-configure: $(POSTGRES_INSTALL_DIR)/build/v15/config.status
+# Compile and install PostgreSQL and contrib/neon
+.PHONY: postgres
+postgres: postgres-configure \
+		  postgres-headers # to prevent `make install` conflicts with zenith's `postgres-headers`
+	+@echo "Compiling PostgreSQL"
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build MAKELEVEL=0 install
+	+@echo "Compiling contrib/neon"
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/contrib/neon install
+	+@echo "Compiling contrib/neon_test_utils"
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/contrib/neon_test_utils install
+	+@echo "Compiling pg_buffercache"
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/contrib/pg_buffercache install
+	+@echo "Compiling pageinspect"
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/contrib/pageinspect install
 
-# Install the PostgreSQL header files into $(POSTGRES_INSTALL_DIR)/<version>/include
-.PHONY: postgres-v14-headers
-postgres-v14-headers: postgres-v14-configure
-	+@echo "Installing PostgreSQL v14 headers"
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v14/src/include MAKELEVEL=0 install
 
-.PHONY: postgres-v15-headers
-postgres-v15-headers: postgres-v15-configure
-	+@echo "Installing PostgreSQL v15 headers"
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v15/src/include MAKELEVEL=0 install
-
-# Compile and install PostgreSQL
-.PHONY: postgres-v14
-postgres-v14: postgres-v14-configure \
-		  postgres-v14-headers # to prevent `make install` conflicts with neon's `postgres-headers`
-	+@echo "Compiling PostgreSQL v14"
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v14 MAKELEVEL=0 install
-	+@echo "Compiling libpq v14"
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v14/src/interfaces/libpq install
-	+@echo "Compiling pg_buffercache v14"
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v14/contrib/pg_buffercache install
-	+@echo "Compiling pageinspect v14"
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v14/contrib/pageinspect install
-
-.PHONY: postgres-v15
-postgres-v15: postgres-v15-configure \
-		  postgres-v15-headers # to prevent `make install` conflicts with neon's `postgres-headers`
-	+@echo "Compiling PostgreSQL v15"
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v15 MAKELEVEL=0 install
-	+@echo "Compiling libpq v15"
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v15/src/interfaces/libpq install
-	+@echo "Compiling pg_buffercache v15"
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v15/contrib/pg_buffercache install
-	+@echo "Compiling pageinspect v15"
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v15/contrib/pageinspect install
-
-# shorthand to build all Postgres versions
-postgres: postgres-v14 postgres-v15
-
-.PHONY: postgres-v14-clean
-postgres-v14-clean:
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v14 MAKELEVEL=0 clean
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v14/contrib/pg_buffercache clean
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v14/contrib/pageinspect clean
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v14/src/interfaces/libpq clean
-
-.PHONY: postgres-v15-clean
-postgres-v15-clean:
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v15 MAKELEVEL=0 clean
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v15/contrib/pg_buffercache clean
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v15/contrib/pageinspect clean
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v15/src/interfaces/libpq clean
-
-neon-pg-ext-v14: postgres-v14
-	+@echo "Compiling neon v14"
-	mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-v14
-	(cd $(POSTGRES_INSTALL_DIR)/build/neon-v14 && \
-	$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/v14/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
-		-f $(ROOT_PROJECT_DIR)/pgxn/neon/Makefile install)
-	+@echo "Compiling neon_walredo v14"
-	mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-walredo-v14
-	(cd $(POSTGRES_INSTALL_DIR)/build/neon-walredo-v14 && \
-	$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/v14/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
-		-f $(ROOT_PROJECT_DIR)/pgxn/neon_walredo/Makefile install)
-	+@echo "Compiling neon_test_utils" v14
-	mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-test-utils-v14
-	(cd $(POSTGRES_INSTALL_DIR)/build/neon-test-utils-v14 && \
-	$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/v14/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
-		-f $(ROOT_PROJECT_DIR)/pgxn/neon_test_utils/Makefile install)
-
-neon-pg-ext-v15: postgres-v15
-	+@echo "Compiling neon v15"
-	mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-v15
-	(cd $(POSTGRES_INSTALL_DIR)/build/neon-v15 && \
-	$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/v15/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
-		-f $(ROOT_PROJECT_DIR)/pgxn/neon/Makefile install)
-	+@echo "Compiling neon_walredo v15"
-	mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-walredo-v15
-	(cd $(POSTGRES_INSTALL_DIR)/build/neon-walredo-v15 && \
-	$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/v15/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
-		-f $(ROOT_PROJECT_DIR)/pgxn/neon_walredo/Makefile install)
-	+@echo "Compiling neon_test_utils" v15
-	mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-test-utils-v15
-	(cd $(POSTGRES_INSTALL_DIR)/build/neon-test-utils-v15 && \
-	$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/v15/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
-		-f $(ROOT_PROJECT_DIR)/pgxn/neon_test_utils/Makefile install)
-
-.PHONY: neon-pg-ext-clean
-	$(MAKE) -C $(ROOT_PROJECT_DIR)/pgxn/neon clean
-	$(MAKE) -C $(ROOT_PROJECT_DIR)/pgxn/neon_test_utils clean
-
-neon-pg-ext: neon-pg-ext-v14 neon-pg-ext-v15
-postgres-headers: postgres-v14-headers postgres-v15-headers
-postgres-clean: postgres-v14-clean postgres-v15-clean
+.PHONY: postgres-clean
+postgres-clean:
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build MAKELEVEL=0 clean
 
 # This doesn't remove the effects of 'configure'.
 .PHONY: clean
 clean:
-	cd $(POSTGRES_INSTALL_DIR)/build/v14 && $(MAKE) clean
-	cd $(POSTGRES_INSTALL_DIR)/build/v15 && $(MAKE) clean
+	cd $(POSTGRES_INSTALL_DIR)/build && $(MAKE) clean
 	$(CARGO_CMD_PREFIX) cargo clean
-	cd pgxn/neon && $(MAKE) clean
-	cd pgxn/neon_test_utils && $(MAKE) clean
 
 # This removes everything
 .PHONY: distclean

NOTICE

@@ -1,5 +1,5 @@
 Neon
 Copyright 2022 Neon Inc.
 
-The PostgreSQL submodules in vendor/postgres-v14 and vendor/postgres-v15 are licensed under the
-PostgreSQL license. See vendor/postgres-v14/COPYRIGHT and vendor/postgres-v15/COPYRIGHT.
+The PostgreSQL submodule in vendor/postgres is licensed under the
+PostgreSQL license. See vendor/postgres/COPYRIGHT.

README.md

@@ -25,7 +25,6 @@ Pageserver consists of:
 - WAL receiver - service that receives WAL from WAL service and stores it in the repository.
 - Page service - service that communicates with compute nodes and responds with pages from the repository.
 - WAL redo - service that builds pages from base images and WAL records on Page service request
-
 ## Running local installation
 
 
@@ -35,12 +34,12 @@ Pageserver consists of:
 * On Ubuntu or Debian, this set of packages should be sufficient to build the code:
 ```bash
 apt install build-essential libtool libreadline-dev zlib1g-dev flex bison libseccomp-dev \
-libssl-dev clang pkg-config libpq-dev etcd cmake postgresql-client protobuf-compiler
+libssl-dev clang pkg-config libpq-dev etcd cmake postgresql-client
 ```
 * On Fedora, these packages are needed:
 ```bash
 dnf install flex bison readline-devel zlib-devel openssl-devel \
-  libseccomp-devel perl clang cmake etcd postgresql postgresql-contrib protobuf-compiler
+  libseccomp-devel perl clang cmake etcd postgresql postgresql-contrib
 ```
 
 2. [Install Rust](https://www.rust-lang.org/tools/install)
@@ -69,17 +68,6 @@ brew install libpq
 brew link --force libpq
 ```
 
-#### Rustc version
-
-The project uses [rust toolchain file](./rust-toolchain.toml) to define the version it's built with in CI for testing and local builds.
-
-This file is automatically picked up by [`rustup`](https://rust-lang.github.io/rustup/overrides.html#the-toolchain-file) that installs (if absent) and uses the toolchain version pinned in the file.
-
-rustup users who want to build with another toolchain can use [`rustup override`](https://rust-lang.github.io/rustup/overrides.html#directory-overrides) command to set a specific toolchain for the project's directory.
-
-non-rustup users most probably are not getting the same toolchain automatically from the file, so are responsible to manually verify their toolchain matches the version in the file.
-Newer rustc versions most probably will work fine, yet older ones might not be supported due to some new features used by the project or the crates.
-
 #### Building on Linux
 
 1. Build neon and patched postgres
@@ -89,9 +77,9 @@ Newer rustc versions most probably will work fine, yet older ones might not be s
 git clone --recursive https://github.com/neondatabase/neon.git
 cd neon
 
-# The preferred and default is to make a debug build. This will create a
-# demonstrably slower build than a release build. For a release build,
-# use "BUILD_TYPE=release make -j`nproc`"
+# The preferred and default is to make a debug build. This will create a 
+# demonstrably slower build than a release build. If you want to use a release
+# build, utilize "BUILD_TYPE=release make -j`nproc`" 
 
 make -j`nproc`
 ```
@@ -105,15 +93,15 @@ make -j`nproc`
 git clone --recursive https://github.com/neondatabase/neon.git
 cd neon
 
-# The preferred and default is to make a debug build. This will create a
-# demonstrably slower build than a release build. For a release build,
-# use "BUILD_TYPE=release make -j`sysctl -n hw.logicalcpu`"
+# The preferred and default is to make a debug build. This will create a 
+# demonstrably slower build than a release build. If you want to use a release
+# build, utilize "BUILD_TYPE=release make -j`sysctl -n hw.logicalcpu`" 
 
 make -j`sysctl -n hw.logicalcpu`
 ```
 
 #### Dependency installation notes
-To run the `psql` client, install the `postgresql-client` package or modify `PATH` and `LD_LIBRARY_PATH` to include `pg_install/bin` and `pg_install/lib`, respectively.
+To run the `psql` client, install the `postgresql-client` package or modify `PATH` and `LD_LIBRARY_PATH` to include `tmp_install/bin` and `tmp_install/lib`, respectively.
 
 To run the integration tests or Python scripts (not required to use the code), install
 Python (3.9 or higher), and install python3 packages using `./scripts/pysync` (requires [poetry](https://python-poetry.org/)) in the project directory.
@@ -125,18 +113,16 @@ Python (3.9 or higher), and install python3 packages using `./scripts/pysync` (r
 # Create repository in .neon with proper paths to binaries and data
 # Later that would be responsibility of a package install script
 > ./target/debug/neon_local init
-Starting pageserver at '127.0.0.1:64000' in '.neon'
-
-Pageserver started
-Successfully initialized timeline 7dd0907914ac399ff3be45fb252bfdb7
-Stopping pageserver gracefully...done!
+initializing tenantid 9ef87a5bf0d92544f6fafeeb3239695c
+created initial timeline de200bd42b49cc1814412c7e592dd6e9 timeline.lsn 0/16B5A50
+initial timeline de200bd42b49cc1814412c7e592dd6e9 created
+pageserver init succeeded
 
 # start pageserver and safekeeper
 > ./target/debug/neon_local start
-Starting etcd broker using /usr/bin/etcd
 Starting pageserver at '127.0.0.1:64000' in '.neon'
-
 Pageserver started
+initializing for sk 1 for 7676
 Starting safekeeper at '127.0.0.1:5454' in '.neon/safekeepers/sk1'
 Safekeeper started
 
@@ -218,13 +204,9 @@ postgres=# select * from t;
 
 ## Running tests
 
-Ensure your dependencies are installed as described [here](https://github.com/neondatabase/neon#dependency-installation-notes).
-
 ```sh
 git clone --recursive https://github.com/neondatabase/neon.git
-
-CARGO_BUILD_FLAGS="--features=testing" make
-
+make # builds also postgres and installs it to ./tmp_install
 ./scripts/pytest
 ```
 

broker/Cargo.toml

@@ -1,42 +0,0 @@
-[package]
-name = "neon_broker"
-version = "0.1.0"
-edition = "2021"
-
-[features]
-bench = []
-# for exploring with tokio-console. Note that tokio_unstable cfg must be enabled, i.e.
-# RUSTFLAGS="--cfg tokio_unstable" cargo build -r -p neon_broker --features console
-console = ["dep:console-subscriber", "tokio/full", "tokio/tracing"]
-
-[[bin]]
-name = "neon_broker_bench"
-path = "src/bin/bench.rs"
-# build benchmarking binary only if explicitly requested with '--features bench'
-required-features = ["bench"]
-
-[dependencies]
-async-stream = "0.3"
-bytes = "1.0"
-clap = { version = "4.0", features = ["derive"] }
-futures-core = "0.3"
-futures-util = "0.3"
-git-version = "0.3.5"
-humantime = "2.1.0"
-hyper = {version = "0.14.14", features = ["full"]}
-once_cell = "1.13.0"
-parking_lot = "0.12"
-prost = "0.11"
-tonic = "0.8"
-tokio = { version = "1.0", features = ["macros", "rt-multi-thread"] }
-tokio-stream = "0.1"
-tracing = "0.1.27"
-
-console-subscriber = {version = "0.1.8", optional = true }
-
-metrics = { path = "../libs/metrics" }
-utils = { path = "../libs/utils" }
-workspace_hack = { version = "0.1", path = "../workspace_hack" }
-
-[build-dependencies]
-tonic-build = "0.8"

broker/build.rs

@@ -1,7 +0,0 @@
-fn main() -> Result<(), Box<dyn std::error::Error>> {
-    // Generate code to deterministic location to make finding it easier.
-    tonic_build::configure()
-        .out_dir("proto/") // put generated code to proto/
-        .compile(&["proto/broker.proto"], &["proto/"])?;
-    Ok(())
-}

broker/proto/.gitignore

@@ -1,2 +0,0 @@
-# protobuf generated code
-neon_broker.rs

broker/proto/broker.proto

@@ -1,44 +0,0 @@
-syntax = "proto3";
-
-import "google/protobuf/empty.proto";
-
-package neon_broker;
-
-service NeonBroker {
-    // Subscribe to safekeeper updates.
-    rpc SubscribeSafekeeperInfo(SubscribeSafekeeperInfoRequest) returns (stream SafekeeperTimelineInfo) {};
-
-    // Publish safekeeper updates.
-    rpc PublishSafekeeperInfo(stream SafekeeperTimelineInfo) returns (google.protobuf.Empty) {};
-}
-
-message SubscribeSafekeeperInfoRequest {
-    oneof subscription_key {
-        google.protobuf.Empty all = 1; // subscribe to everything
-        TenantTimelineId tenant_timeline_id = 2; // subscribe to specific timeline
-    }
-}
-
-message SafekeeperTimelineInfo {
-    uint64 safekeeper_id = 1;
-    TenantTimelineId tenant_timeline_id = 2;
-    // Term of the last entry.
-    uint64 last_log_term = 3;
-    // LSN of the last record.
-    uint64 flush_lsn = 4;
-    // Up to which LSN safekeeper regards its WAL as committed.
-    uint64 commit_lsn = 5;
-    // LSN up to which safekeeper has backed WAL.
-    uint64 backup_lsn = 6;
-    // LSN of last checkpoint uploaded by pageserver.
-    uint64 remote_consistent_lsn = 7;
-    uint64 peer_horizon_lsn = 8;
-    uint64 local_start_lsn = 9;
-    // A connection string to use for WAL receiving.
-    string safekeeper_connstr = 10;
-}
-
-message TenantTimelineId {
-    bytes tenant_id = 1;
-    bytes timeline_id = 2;
-}

broker/src/bin/bench.rs

@@ -1,174 +0,0 @@
-use std::sync::atomic::{AtomicU64, Ordering};
-use std::sync::Arc;
-use std::time::{Duration, Instant};
-
-use clap::Parser;
-use neon_broker::neon_broker_proto::subscribe_safekeeper_info_request::SubscriptionKey;
-use neon_broker::neon_broker_proto::TenantTimelineId as ProtoTenantTimelineId;
-use neon_broker::neon_broker_proto::{SafekeeperTimelineInfo, SubscribeSafekeeperInfoRequest};
-use neon_broker::NeonBrokerClientChannel;
-use neon_broker::DEFAULT_LISTEN_ADDR;
-use tokio::time::{self};
-
-use tonic::Request;
-
-const ABOUT: &str = r#"
-A simple benchmarking tool for neon_broker. Creates specified number of per
-timeline publishers and subscribers; each publisher continiously sends
-messages, subscribers read them. Each second the tool outputs number of
-messages summed across all subscribers and min number of messages
-recevied by single subscriber.
-
-For example,
-cargo build -r -p neon_broker --features bench && target/release/neon_broker
-target/release/neon_broker_bench -s 1 -p 1
-"#;
-
-#[derive(Parser, Debug)]
-#[clap(author, version, about = ABOUT)]
-struct Args {
-    /// Number of publishers
-    #[clap(short = 'p', long, value_parser, default_value_t = 1)]
-    num_pubs: u64,
-    /// Number of subscribers
-    #[clap(short = 's', long, value_parser, default_value_t = 1)]
-    num_subs: u64,
-}
-
-async fn progress_reporter(counters: Vec<Arc<AtomicU64>>) {
-    let mut interval = time::interval(Duration::from_millis(1000));
-    let mut c_old = counters.iter().map(|c| c.load(Ordering::Relaxed)).sum();
-    let mut c_min_old = counters
-        .iter()
-        .map(|c| c.load(Ordering::Relaxed))
-        .min()
-        .unwrap_or(0);
-    let mut started_at = None;
-    let mut skipped: u64 = 0;
-    loop {
-        interval.tick().await;
-        let c_new = counters.iter().map(|c| c.load(Ordering::Relaxed)).sum();
-        let c_min_new = counters
-            .iter()
-            .map(|c| c.load(Ordering::Relaxed))
-            .min()
-            .unwrap_or(0);
-        if c_new > 0 && started_at.is_none() {
-            started_at = Some(Instant::now());
-            skipped = c_new;
-        }
-        let avg_rps = started_at.map(|s| {
-            let dur = s.elapsed();
-            let dur_secs = dur.as_secs() as f64 + (dur.subsec_millis() as f64) / 1000.0;
-            let avg_rps = (c_new - skipped) as f64 / dur_secs;
-            (dur, avg_rps)
-        });
-        println!(
-            "sum rps {}, min rps {} total {}, total min {}, duration, avg sum rps {:?}",
-            c_new - c_old,
-            c_min_new - c_min_old,
-            c_new,
-            c_min_new,
-            avg_rps
-        );
-        c_old = c_new;
-        c_min_old = c_min_new;
-    }
-}
-
-fn tli_from_u64(i: u64) -> Vec<u8> {
-    let mut timeline_id = vec![0xFF; 8];
-    timeline_id.extend_from_slice(&i.to_be_bytes());
-    timeline_id
-}
-
-async fn subscribe(client: Option<NeonBrokerClientChannel>, counter: Arc<AtomicU64>, i: u64) {
-    let mut client = match client {
-        Some(c) => c,
-        None => NeonBrokerClientChannel::connect_lazy(format!("http://{}", DEFAULT_LISTEN_ADDR))
-            .await
-            .unwrap(),
-    };
-
-    // let key = SubscriptionKey::All(());
-    let key = SubscriptionKey::TenantTimelineId(ProtoTenantTimelineId {
-        tenant_id: vec![0xFF; 16],
-        timeline_id: tli_from_u64(i),
-    });
-    let request = SubscribeSafekeeperInfoRequest {
-        subscription_key: Some(key),
-    };
-    let mut stream = client
-        .subscribe_safekeeper_info(request)
-        .await
-        .unwrap()
-        .into_inner();
-
-    while let Some(_feature) = stream.message().await.unwrap() {
-        counter.fetch_add(1, Ordering::Relaxed);
-    }
-}
-
-async fn publish(client: Option<NeonBrokerClientChannel>, n_keys: u64) {
-    let mut client = match client {
-        Some(c) => c,
-        None => NeonBrokerClientChannel::connect_lazy(format!("http://{}", DEFAULT_LISTEN_ADDR))
-            .await
-            .unwrap(),
-    };
-    let mut counter: u64 = 0;
-
-    // create stream producing new values
-    let outbound = async_stream::stream! {
-        loop {
-            let info = SafekeeperTimelineInfo {
-                safekeeper_id: 1,
-                tenant_timeline_id: Some(ProtoTenantTimelineId {
-                    tenant_id: vec![0xFF; 16],
-                    timeline_id: tli_from_u64(counter % n_keys),
-                }),
-                last_log_term: 0,
-                flush_lsn: counter,
-                commit_lsn: 2,
-                backup_lsn: 3,
-                remote_consistent_lsn: 4,
-                peer_horizon_lsn: 5,
-                safekeeper_connstr: "zenith-1-sk-1.local:7676".to_owned(),
-                local_start_lsn: 0,
-            };
-            counter += 1;
-            yield info;
-        }
-    };
-    let response = client.publish_safekeeper_info(Request::new(outbound)).await;
-    println!("pub response is {:?}", response);
-}
-
-#[tokio::main]
-async fn main() -> Result<(), Box<dyn std::error::Error>> {
-    let args = Args::parse();
-
-    let mut counters = Vec::with_capacity(args.num_subs as usize);
-    for _ in 0..args.num_subs {
-        counters.push(Arc::new(AtomicU64::new(0)));
-    }
-    let h = tokio::spawn(progress_reporter(counters.clone()));
-
-    let c = NeonBrokerClientChannel::connect_lazy(format!("http://{}", DEFAULT_LISTEN_ADDR))
-        .await
-        .unwrap();
-
-    for i in 0..args.num_subs {
-        let c = Some(c.clone());
-        // let c = None;
-        tokio::spawn(subscribe(c, counters[i as usize].clone(), i));
-    }
-    for _i in 0..args.num_pubs {
-        // let c = Some(c.clone());
-        let c = None;
-        tokio::spawn(publish(c, args.num_subs as u64));
-    }
-
-    h.await?;
-    Ok(())
-}

broker/src/bin/neon_broker.rs

@@ -1,510 +0,0 @@
-//! Simple pub-sub based on grpc (tonic) and Tokio mpsc for storage nodes
-//! messaging. The main design goal is to avoid central synchronization during
-//! normal flow, resorting to it only when pub/sub change happens. Each
-//! subscriber holds mpsc for messages it sits on; tx end is sent to existing
-//! publishers and saved in shared state for new ones. Publishers maintain
-//! locally set of subscribers they stream messages to.
-//!
-//! Subscriptions to 1) single timeline 2) everything are possible. We could add
-//! subscription to set of timelines to save grpc streams, but testing shows
-//! many individual streams is also ok.
-//!
-//! Message is dropped if subscriber can't consume it, not affecting other
-//! subscribers.
-//!
-//! Only safekeeper message is supported, but it is not hard to add something
-//! else with generics.
-use clap::{command, Parser};
-use futures_core::Stream;
-use futures_util::StreamExt;
-use hyper::header::CONTENT_TYPE;
-use hyper::service::{make_service_fn, service_fn};
-use hyper::{Body, Method, StatusCode};
-use parking_lot::RwLock;
-use std::collections::HashMap;
-use std::convert::Infallible;
-use std::net::SocketAddr;
-use std::pin::Pin;
-use std::sync::Arc;
-use std::time::Duration;
-use tokio::sync::broadcast;
-use tokio::sync::broadcast::error::RecvError;
-use tonic::codegen::Service;
-use tonic::Code;
-use tonic::{Request, Response, Status};
-use tracing::*;
-
-use metrics::{Encoder, TextEncoder};
-use neon_broker::metrics::{NUM_PUBS, NUM_SUBS_ALL, NUM_SUBS_TIMELINE};
-use neon_broker::neon_broker_proto::neon_broker_server::{NeonBroker, NeonBrokerServer};
-use neon_broker::neon_broker_proto::subscribe_safekeeper_info_request::SubscriptionKey as ProtoSubscriptionKey;
-use neon_broker::neon_broker_proto::{SafekeeperTimelineInfo, SubscribeSafekeeperInfoRequest};
-use neon_broker::{parse_proto_ttid, EitherBody, DEFAULT_LISTEN_ADDR};
-use utils::id::TenantTimelineId;
-use utils::project_git_version;
-
-project_git_version!(GIT_VERSION);
-
-const DEFAULT_CHAN_SIZE: usize = 256;
-const DEFAULT_HTTP2_KEEPALIVE_INTERVAL: &str = "5000ms";
-
-#[derive(Parser, Debug)]
-#[command(version = GIT_VERSION, about = "Broker for neon storage nodes communication", long_about = None)]
-struct Args {
-    /// Endpoint to listen on.
-    #[arg(short, long, default_value = DEFAULT_LISTEN_ADDR)]
-    listen_addr: SocketAddr,
-    /// Size of the queue to the subscriber.
-    #[arg(long, default_value_t = DEFAULT_CHAN_SIZE)]
-    chan_size: usize,
-    /// HTTP/2 keepalive interval.
-    #[arg(long, value_parser= humantime::parse_duration, default_value = DEFAULT_HTTP2_KEEPALIVE_INTERVAL)]
-    http2_keepalive_interval: Duration,
-    /// Format for logging, either 'plain' or 'json'.
-    #[arg(long, default_value = "plain")]
-    log_format: String,
-}
-
-type PubId = u64; // id of publisher for registering in maps
-type SubId = u64; // id of subscriber for registering in maps
-
-#[derive(Copy, Clone)]
-enum SubscriptionKey {
-    All,
-    Timeline(TenantTimelineId),
-}
-
-impl SubscriptionKey {
-    // Parse protobuf subkey (protobuf doesn't have fixed size bytes, we get vectors).
-    pub fn from_proto_subscription_key(key: ProtoSubscriptionKey) -> Result<Self, Status> {
-        match key {
-            ProtoSubscriptionKey::All(_) => Ok(SubscriptionKey::All),
-            ProtoSubscriptionKey::TenantTimelineId(proto_ttid) => {
-                Ok(SubscriptionKey::Timeline(parse_proto_ttid(&proto_ttid)?))
-            }
-        }
-    }
-}
-
-// Channel to timeline subscribers.
-struct ChanToTimelineSub {
-    chan: broadcast::Sender<SafekeeperTimelineInfo>,
-    // Tracked separately to know when delete the shmem entry. receiver_count()
-    // is unhandy for that as unregistering and dropping the receiver side
-    // happens at different moments.
-    num_subscribers: u64,
-}
-
-struct SharedState {
-    next_pub_id: PubId,
-    num_pubs: i64,
-    next_sub_id: SubId,
-    num_subs_to_timelines: i64,
-    chans_to_timeline_subs: HashMap<TenantTimelineId, ChanToTimelineSub>,
-    num_subs_to_all: i64,
-    chan_to_all_subs: broadcast::Sender<SafekeeperTimelineInfo>,
-}
-
-impl SharedState {
-    pub fn new(chan_size: usize) -> Self {
-        SharedState {
-            next_pub_id: 0,
-            num_pubs: 0,
-            next_sub_id: 0,
-            num_subs_to_timelines: 0,
-            chans_to_timeline_subs: HashMap::new(),
-            num_subs_to_all: 0,
-            chan_to_all_subs: broadcast::channel(chan_size).0,
-        }
-    }
-
-    // Register new publisher.
-    pub fn register_publisher(&mut self, registry: Registry) -> Publisher {
-        let pub_id = self.next_pub_id;
-        self.next_pub_id += 1;
-        self.num_pubs += 1;
-        NUM_PUBS.set(self.num_pubs);
-        Publisher {
-            id: pub_id,
-            registry,
-        }
-    }
-
-    // Unregister publisher.
-    pub fn unregister_publisher(&mut self) {
-        self.num_pubs -= 1;
-        NUM_PUBS.set(self.num_pubs);
-    }
-
-    // Register new subscriber.
-    pub fn register_subscriber(
-        &mut self,
-        sub_key: SubscriptionKey,
-        registry: Registry,
-        chan_size: usize,
-    ) -> Subscriber {
-        let sub_id = self.next_sub_id;
-        self.next_sub_id += 1;
-        let sub_rx = match sub_key {
-            SubscriptionKey::All => {
-                self.num_subs_to_all += 1;
-                NUM_SUBS_ALL.set(self.num_subs_to_all);
-                self.chan_to_all_subs.subscribe()
-            }
-            SubscriptionKey::Timeline(ttid) => {
-                self.num_subs_to_timelines += 1;
-                NUM_SUBS_TIMELINE.set(self.num_subs_to_timelines);
-                // Create new broadcast channel for this key, or subscriber to
-                // the existing one.
-                let chan_to_timeline_sub =
-                    self.chans_to_timeline_subs
-                        .entry(ttid)
-                        .or_insert(ChanToTimelineSub {
-                            chan: broadcast::channel(chan_size).0,
-                            num_subscribers: 0,
-                        });
-                chan_to_timeline_sub.num_subscribers += 1;
-                chan_to_timeline_sub.chan.subscribe()
-            }
-        };
-        Subscriber {
-            id: sub_id,
-            key: sub_key,
-            sub_rx,
-            registry,
-        }
-    }
-
-    // Unregister the subscriber.
-    pub fn unregister_subscriber(&mut self, sub_key: SubscriptionKey) {
-        match sub_key {
-            SubscriptionKey::All => {
-                self.num_subs_to_all -= 1;
-                NUM_SUBS_ALL.set(self.num_subs_to_all);
-            }
-            SubscriptionKey::Timeline(ttid) => {
-                self.num_subs_to_timelines -= 1;
-                NUM_SUBS_TIMELINE.set(self.num_subs_to_timelines);
-
-                // Remove from the map, destroying the channel, if we are the
-                // last subscriber to this timeline.
-
-                // Missing entry is a bug; we must have registered.
-                let chan_to_timeline_sub = self.chans_to_timeline_subs.get_mut(&ttid).unwrap();
-                chan_to_timeline_sub.num_subscribers -= 1;
-                if chan_to_timeline_sub.num_subscribers == 0 {
-                    self.chans_to_timeline_subs.remove(&ttid);
-                }
-            }
-        }
-    }
-}
-
-// SharedState wrapper.
-#[derive(Clone)]
-struct Registry {
-    shared_state: Arc<RwLock<SharedState>>,
-    chan_size: usize,
-}
-
-impl Registry {
-    // Register new publisher in shared state.
-    pub fn register_publisher(&self) -> Publisher {
-        let publisher = self.shared_state.write().register_publisher(self.clone());
-        trace!("registered publisher {}", publisher.id);
-        publisher
-    }
-
-    pub fn unregister_publisher(&self, publisher: &Publisher) {
-        self.shared_state.write().unregister_publisher();
-        trace!("unregistered publisher {}", publisher.id);
-    }
-
-    // Register new subscriber in shared state.
-    pub fn register_subscriber(&self, sub_key: SubscriptionKey) -> Subscriber {
-        let subscriber =
-            self.shared_state
-                .write()
-                .register_subscriber(sub_key, self.clone(), self.chan_size);
-        trace!("registered subscriber {}", subscriber.id);
-        subscriber
-    }
-
-    // Unregister the subscriber
-    pub fn unregister_subscriber(&self, subscriber: &Subscriber) {
-        self.shared_state
-            .write()
-            .unregister_subscriber(subscriber.key);
-        trace!("unregistered subscriber {}", subscriber.id);
-    }
-}
-
-// Private subscriber state.
-struct Subscriber {
-    id: SubId,
-    key: SubscriptionKey,
-    // Subscriber receives messages from publishers here.
-    sub_rx: broadcast::Receiver<SafekeeperTimelineInfo>,
-    // to unregister itself from shared state in Drop
-    registry: Registry,
-}
-
-impl Drop for Subscriber {
-    fn drop(&mut self) {
-        self.registry.unregister_subscriber(self);
-    }
-}
-
-// Private publisher state
-struct Publisher {
-    id: PubId,
-    registry: Registry,
-}
-
-impl Publisher {
-    // Send msg to relevant subscribers.
-    pub fn send_msg(&mut self, msg: &SafekeeperTimelineInfo) -> Result<(), Status> {
-        // send message to subscribers for everything
-        let shared_state = self.registry.shared_state.read();
-        // Err means there is no subscribers, it is fine.
-        shared_state.chan_to_all_subs.send(msg.clone()).ok();
-
-        // send message to per timeline subscribers
-        let ttid =
-            parse_proto_ttid(msg.tenant_timeline_id.as_ref().ok_or_else(|| {
-                Status::new(Code::InvalidArgument, "missing tenant_timeline_id")
-            })?)?;
-        if let Some(subs) = shared_state.chans_to_timeline_subs.get(&ttid) {
-            // Err can't happen here, as rx is destroyed after removing from the
-            // map the last subscriber.
-            subs.chan.send(msg.clone()).unwrap();
-        }
-        Ok(())
-    }
-}
-
-impl Drop for Publisher {
-    fn drop(&mut self) {
-        self.registry.unregister_publisher(self);
-    }
-}
-
-struct NeonBrokerImpl {
-    registry: Registry,
-}
-
-#[tonic::async_trait]
-impl NeonBroker for NeonBrokerImpl {
-    async fn publish_safekeeper_info(
-        &self,
-        request: Request<tonic::Streaming<SafekeeperTimelineInfo>>,
-    ) -> Result<Response<()>, Status> {
-        let mut publisher = self.registry.register_publisher();
-
-        let mut stream = request.into_inner();
-
-        loop {
-            match stream.next().await {
-                Some(Ok(msg)) => publisher.send_msg(&msg)?,
-                Some(Err(e)) => return Err(e), // grpc error from the stream
-                None => break,                 // closed stream
-            }
-        }
-
-        Ok(Response::new(()))
-    }
-
-    type SubscribeSafekeeperInfoStream =
-        Pin<Box<dyn Stream<Item = Result<SafekeeperTimelineInfo, Status>> + Send + 'static>>;
-
-    async fn subscribe_safekeeper_info(
-        &self,
-        request: Request<SubscribeSafekeeperInfoRequest>,
-    ) -> Result<Response<Self::SubscribeSafekeeperInfoStream>, Status> {
-        let proto_key = request
-            .into_inner()
-            .subscription_key
-            .ok_or_else(|| Status::new(Code::InvalidArgument, "missing subscription key"))?;
-        let sub_key = SubscriptionKey::from_proto_subscription_key(proto_key)?;
-        let mut subscriber = self.registry.register_subscriber(sub_key);
-
-        // transform rx into stream with item = Result, as method result demands
-        let output = async_stream::try_stream! {
-            loop {
-                match subscriber.sub_rx.recv().await {
-                    Ok(info) => yield info,
-                    Err(RecvError::Lagged(_skipped_msg)) => {
-                        // warn!("dropped {} messages, channel is full", skipped_msg);
-                    }
-                    Err(RecvError::Closed) => {
-                        // can't happen, we never drop the channel while there is a subscriber
-                        Err(Status::new(Code::Internal, "channel unexpectantly closed"))?;
-                    }
-                }
-            }
-        };
-
-        Ok(Response::new(
-            Box::pin(output) as Self::SubscribeSafekeeperInfoStream
-        ))
-    }
-}
-
-// We serve only metrics through http1.
-async fn http1_handler(
-    req: hyper::Request<hyper::body::Body>,
-) -> Result<hyper::Response<Body>, Infallible> {
-    let resp = match (req.method(), req.uri().path()) {
-        (&Method::GET, "/metrics") => {
-            let mut buffer = vec![];
-            let metrics = metrics::gather();
-            let encoder = TextEncoder::new();
-            encoder.encode(&metrics, &mut buffer).unwrap();
-
-            hyper::Response::builder()
-                .status(StatusCode::OK)
-                .header(CONTENT_TYPE, encoder.format_type())
-                .body(Body::from(buffer))
-                .unwrap()
-        }
-        _ => hyper::Response::builder()
-            .status(StatusCode::NOT_FOUND)
-            .body(Body::empty())
-            .unwrap(),
-    };
-    Ok(resp)
-}
-
-#[tokio::main]
-async fn main() -> Result<(), Box<dyn std::error::Error>> {
-    let args = Args::parse();
-
-    #[cfg(not(feature = "console"))] // tokio-console inits tracing_subscriber on its own
-    utils::logging::init(utils::logging::LogFormat::from_config(&args.log_format)?)?;
-    info!("version: {GIT_VERSION}");
-
-    #[cfg(feature = "console")]
-    console_subscriber::init();
-
-    let registry = Registry {
-        shared_state: Arc::new(RwLock::new(SharedState::new(args.chan_size))),
-        chan_size: args.chan_size,
-    };
-    let neon_broker_impl = NeonBrokerImpl {
-        registry: registry.clone(),
-    };
-    let neon_broker_server = NeonBrokerServer::new(neon_broker_impl);
-
-    info!("listening on {}", &args.listen_addr);
-
-    // grpc is served along with http1 for metrics on a single port, hence we
-    // don't use tonic's Server.
-    hyper::Server::bind(&args.listen_addr)
-        .http2_keep_alive_interval(Some(args.http2_keepalive_interval))
-        .serve(make_service_fn(move |_| {
-            let neon_broker_server_cloned = neon_broker_server.clone();
-            async move {
-                Ok::<_, Infallible>(service_fn(move |req| {
-                    // Technically this second clone is not needed, but consume
-                    // by async block is apparently unavoidable. BTW, error
-                    // message is enigmatic, see
-                    // https://github.com/rust-lang/rust/issues/68119
-                    //
-                    // We could get away without async block at all, but then we
-                    // need to resort to futures::Either to merge the result,
-                    // which doesn't caress an eye as well.
-                    let mut neon_broker_server_svc = neon_broker_server_cloned.clone();
-                    async move {
-                        if req.headers().get("content-type").map(|x| x.as_bytes())
-                            == Some(b"application/grpc")
-                        {
-                            let res_resp = neon_broker_server_svc.call(req).await;
-                            // Grpc and http1 handlers have slightly different
-                            // Response types: it is UnsyncBoxBody for the
-                            // former one (not sure why) and plain hyper::Body
-                            // for the latter. Both implement HttpBody though,
-                            // and EitherBody is used to merge them.
-                            res_resp.map(|resp| resp.map(EitherBody::Left))
-                        } else {
-                            let res_resp = http1_handler(req).await;
-                            res_resp.map(|resp| resp.map(EitherBody::Right))
-                        }
-                    }
-                }))
-            }
-        }))
-        .await?;
-    Ok(())
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-    use neon_broker::neon_broker_proto::TenantTimelineId as ProtoTenantTimelineId;
-    use tokio::sync::broadcast::error::TryRecvError;
-    use utils::id::{TenantId, TimelineId};
-
-    fn msg(timeline_id: Vec<u8>) -> SafekeeperTimelineInfo {
-        SafekeeperTimelineInfo {
-            safekeeper_id: 1,
-            tenant_timeline_id: Some(ProtoTenantTimelineId {
-                tenant_id: vec![0x00; 16],
-                timeline_id,
-            }),
-            last_log_term: 0,
-            flush_lsn: 1,
-            commit_lsn: 2,
-            backup_lsn: 3,
-            remote_consistent_lsn: 4,
-            peer_horizon_lsn: 5,
-            safekeeper_connstr: "neon-1-sk-1.local:7676".to_owned(),
-            local_start_lsn: 0,
-        }
-    }
-
-    fn tli_from_u64(i: u64) -> Vec<u8> {
-        let mut timeline_id = vec![0xFF; 8];
-        timeline_id.extend_from_slice(&i.to_be_bytes());
-        timeline_id
-    }
-
-    #[tokio::test]
-    async fn test_registry() {
-        let registry = Registry {
-            shared_state: Arc::new(RwLock::new(SharedState::new(16))),
-            chan_size: 16,
-        };
-
-        // subscribe to timeline 2
-        let ttid_2 = TenantTimelineId {
-            tenant_id: TenantId::from_slice(&[0x00; 16]).unwrap(),
-            timeline_id: TimelineId::from_slice(&tli_from_u64(2)).unwrap(),
-        };
-        let sub_key_2 = SubscriptionKey::Timeline(ttid_2);
-        let mut subscriber_2 = registry.register_subscriber(sub_key_2);
-        let mut subscriber_all = registry.register_subscriber(SubscriptionKey::All);
-
-        // send two messages with different keys
-        let msg_1 = msg(tli_from_u64(1));
-        let msg_2 = msg(tli_from_u64(2));
-        let mut publisher = registry.register_publisher();
-        publisher.send_msg(&msg_1).expect("failed to send msg");
-        publisher.send_msg(&msg_2).expect("failed to send msg");
-
-        // msg with key 2 should arrive to subscriber_2
-        assert!(
-            matches!(subscriber_2.sub_rx.try_recv(), Ok(msg) if matches!(msg.tenant_timeline_id.as_ref(), Some(ttid) if parse_proto_ttid(ttid).unwrap() == ttid_2))
-        );
-        // but nothing more
-        assert!(
-            matches!(subscriber_2.sub_rx.try_recv(), Err(err) if matches!(err, TryRecvError::Empty))
-        );
-
-        // subscriber_all should receive both messages
-        assert!(matches!(subscriber_all.sub_rx.try_recv(), Ok(..)));
-        assert!(matches!(subscriber_all.sub_rx.try_recv(), Ok(..)));
-        assert!(
-            matches!(subscriber_all.sub_rx.try_recv(), Err(err) if matches!(err, TryRecvError::Empty))
-        );
-    }
-}

broker/src/lib.rs

@@ -1,108 +0,0 @@
-use hyper::body::HttpBody;
-use std::pin::Pin;
-use std::task::{Context, Poll};
-use tonic::codegen::StdError;
-use tonic::{transport::Channel, Code, Status};
-use utils::id::{TenantId, TenantTimelineId, TimelineId};
-
-use neon_broker_proto::{
-    neon_broker_client::NeonBrokerClient, TenantTimelineId as ProtoTenantTimelineId,
-};
-
-// Code generated by protobuf.
-pub mod neon_broker_proto {
-    include!("../proto/neon_broker.rs");
-}
-
-pub mod metrics;
-
-// Re-exports to avoid direct tonic dependency in user crates.
-pub use tonic::Request;
-pub use tonic::Streaming;
-
-pub const DEFAULT_LISTEN_ADDR: &str = "127.0.0.1:50051";
-
-// NeonBrokerClient charged with tonic provided Channel transport; helps to
-// avoid depending on tonic directly in user crates.
-pub type NeonBrokerClientChannel = NeonBrokerClient<Channel>;
-
-impl NeonBrokerClient<Channel> {
-    /// Create a new client to the given endpoint, but don't actually connect until the first request.
-    pub async fn connect_lazy<D>(dst: D) -> Result<Self, tonic::transport::Error>
-    where
-        D: std::convert::TryInto<tonic::transport::Endpoint>,
-        D::Error: Into<StdError>,
-    {
-        let conn = tonic::transport::Endpoint::new(dst)?.connect_lazy();
-        Ok(Self::new(conn))
-    }
-}
-
-// parse variable length bytes from protobuf
-pub fn parse_proto_ttid(proto_ttid: &ProtoTenantTimelineId) -> Result<TenantTimelineId, Status> {
-    let tenant_id = TenantId::from_slice(&proto_ttid.tenant_id)
-        .map_err(|e| Status::new(Code::InvalidArgument, format!("malformed tenant_id: {}", e)))?;
-    let timeline_id = TimelineId::from_slice(&proto_ttid.timeline_id).map_err(|e| {
-        Status::new(
-            Code::InvalidArgument,
-            format!("malformed timeline_id: {}", e),
-        )
-    })?;
-    Ok(TenantTimelineId {
-        tenant_id,
-        timeline_id,
-    })
-}
-
-// These several usages don't justify anyhow dependency, though it would work as
-// well.
-type AnyError = Box<dyn std::error::Error + Send + Sync + 'static>;
-
-// Provides impl HttpBody for two different types implementing it. Inspired by
-// https://github.com/hyperium/tonic/blob/master/examples/src/hyper_warp/server.rs
-pub enum EitherBody<A, B> {
-    Left(A),
-    Right(B),
-}
-
-impl<A, B> HttpBody for EitherBody<A, B>
-where
-    A: HttpBody + Send + Unpin,
-    B: HttpBody<Data = A::Data> + Send + Unpin,
-    A::Error: Into<AnyError>,
-    B::Error: Into<AnyError>,
-{
-    type Data = A::Data;
-    type Error = Box<dyn std::error::Error + Send + Sync + 'static>;
-
-    fn is_end_stream(&self) -> bool {
-        match self {
-            EitherBody::Left(b) => b.is_end_stream(),
-            EitherBody::Right(b) => b.is_end_stream(),
-        }
-    }
-
-    fn poll_data(
-        self: Pin<&mut Self>,
-        cx: &mut Context<'_>,
-    ) -> Poll<Option<Result<Self::Data, Self::Error>>> {
-        match self.get_mut() {
-            EitherBody::Left(b) => Pin::new(b).poll_data(cx).map(map_option_err),
-            EitherBody::Right(b) => Pin::new(b).poll_data(cx).map(map_option_err),
-        }
-    }
-
-    fn poll_trailers(
-        self: Pin<&mut Self>,
-        cx: &mut Context<'_>,
-    ) -> Poll<Result<Option<hyper::HeaderMap>, Self::Error>> {
-        match self.get_mut() {
-            EitherBody::Left(b) => Pin::new(b).poll_trailers(cx).map_err(Into::into),
-            EitherBody::Right(b) => Pin::new(b).poll_trailers(cx).map_err(Into::into),
-        }
-    }
-}
-
-fn map_option_err<T, U: Into<AnyError>>(err: Option<Result<T, U>>) -> Option<Result<T, AnyError>> {
-    err.map(|e| e.map_err(Into::into))
-}

broker/src/metrics.rs

@@ -1,25 +0,0 @@
-//! Broker metrics.
-
-use metrics::{register_int_gauge, IntGauge};
-use once_cell::sync::Lazy;
-
-pub static NUM_PUBS: Lazy<IntGauge> = Lazy::new(|| {
-    register_int_gauge!("broker_active_publishers", "Number of publications")
-        .expect("Failed to register metric")
-});
-
-pub static NUM_SUBS_TIMELINE: Lazy<IntGauge> = Lazy::new(|| {
-    register_int_gauge!(
-        "broker_per_timeline_active_subscribers",
-        "Number of subsciptions to particular tenant timeline id"
-    )
-    .expect("Failed to register metric")
-});
-
-pub static NUM_SUBS_ALL: Lazy<IntGauge> = Lazy::new(|| {
-    register_int_gauge!(
-        "broker_all_keys_active_subscribers",
-        "Number of subsciptions to all keys"
-    )
-    .expect("Failed to register metric")
-});

compute_tools/Cargo.toml

@@ -6,18 +6,16 @@ edition = "2021"
 [dependencies]
 anyhow = "1.0"
 chrono = "0.4"
-clap = "4.0"
+clap = "3.0"
 env_logger = "0.9"
-futures = "0.3.13"
 hyper = { version = "0.14", features = ["full"] }
 log = { version = "0.4", features = ["std", "serde"] }
-notify = "5.0.0"
-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev="d052ee8b86fff9897c77b0fe89ea9daba0e1fa38" }
+postgres = { git = "https://github.com/zenithdb/rust-postgres.git", rev="d052ee8b86fff9897c77b0fe89ea9daba0e1fa38" }
 regex = "1"
 serde = { version = "1.0", features = ["derive"] }
 serde_json = "1"
 tar = "0.4"
 tokio = { version = "1.17", features = ["macros", "rt", "rt-multi-thread"] }
-tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev="d052ee8b86fff9897c77b0fe89ea9daba0e1fa38" }
+tokio-postgres = { git = "https://github.com/zenithdb/rust-postgres.git", rev="d052ee8b86fff9897c77b0fe89ea9daba0e1fa38" }
 url = "2.2.2"
 workspace_hack = { version = "0.1", path = "../workspace_hack" }

compute_tools/src/bin/compute_ctl.rs

@@ -51,19 +51,53 @@ fn main() -> Result<()> {
     // TODO: re-use `utils::logging` later
     init_logger(DEFAULT_LOG_LEVEL)?;
 
-    let matches = cli().get_matches();
+    // Env variable is set by `cargo`
+    let version: Option<&str> = option_env!("CARGO_PKG_VERSION");
+    let matches = clap::App::new("compute_ctl")
+        .version(version.unwrap_or("unknown"))
+        .arg(
+            Arg::new("connstr")
+                .short('C')
+                .long("connstr")
+                .value_name("DATABASE_URL")
+                .required(true),
+        )
+        .arg(
+            Arg::new("pgdata")
+                .short('D')
+                .long("pgdata")
+                .value_name("DATADIR")
+                .required(true),
+        )
+        .arg(
+            Arg::new("pgbin")
+                .short('b')
+                .long("pgbin")
+                .value_name("POSTGRES_PATH"),
+        )
+        .arg(
+            Arg::new("spec")
+                .short('s')
+                .long("spec")
+                .value_name("SPEC_JSON"),
+        )
+        .arg(
+            Arg::new("spec-path")
+                .short('S')
+                .long("spec-path")
+                .value_name("SPEC_PATH"),
+        )
+        .get_matches();
 
-    let pgdata = matches
-        .get_one::<String>("pgdata")
-        .expect("PGDATA path is required");
+    let pgdata = matches.value_of("pgdata").expect("PGDATA path is required");
     let connstr = matches
-        .get_one::<String>("connstr")
+        .value_of("connstr")
         .expect("Postgres connection string is required");
-    let spec = matches.get_one::<String>("spec");
-    let spec_path = matches.get_one::<String>("spec-path");
+    let spec = matches.value_of("spec");
+    let spec_path = matches.value_of("spec-path");
 
     // Try to use just 'postgres' if no path is provided
-    let pgbin = matches.get_one::<String>("pgbin").unwrap();
+    let pgbin = matches.value_of("pgbin").unwrap_or("postgres");
 
     let spec: ComputeSpec = match spec {
         // First, try to get cluster spec from the cli argument
@@ -139,48 +173,3 @@ fn main() -> Result<()> {
         }
     }
 }
-
-fn cli() -> clap::Command {
-    // Env variable is set by `cargo`
-    let version = option_env!("CARGO_PKG_VERSION").unwrap_or("unknown");
-    clap::Command::new("compute_ctl")
-        .version(version)
-        .arg(
-            Arg::new("connstr")
-                .short('C')
-                .long("connstr")
-                .value_name("DATABASE_URL")
-                .required(true),
-        )
-        .arg(
-            Arg::new("pgdata")
-                .short('D')
-                .long("pgdata")
-                .value_name("DATADIR")
-                .required(true),
-        )
-        .arg(
-            Arg::new("pgbin")
-                .short('b')
-                .long("pgbin")
-                .default_value("postgres")
-                .value_name("POSTGRES_PATH"),
-        )
-        .arg(
-            Arg::new("spec")
-                .short('s')
-                .long("spec")
-                .value_name("SPEC_JSON"),
-        )
-        .arg(
-            Arg::new("spec-path")
-                .short('S')
-                .long("spec-path")
-                .value_name("SPEC_PATH"),
-        )
-}
-
-#[test]
-fn verify_cli() {
-    cli().debug_assert()
-}

compute_tools/src/compute.rs

@@ -187,13 +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: {}",
+                "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"),
             );
         }
 
@@ -257,7 +254,14 @@ impl ComputeNode {
             .spawn()
             .expect("cannot start postgres process");
 
-        wait_for_postgres(&mut pg, pgdata_path)?;
+        // Try default Postgres port if it is not provided
+        let port = self
+            .spec
+            .cluster
+            .settings
+            .find("port")
+            .unwrap_or_else(|| "5432".to_string());
+        wait_for_postgres(&mut pg, &port, pgdata_path)?;
 
         // If connection fails,
         // it may be the old node with `zenith_admin` superuser.

compute_tools/src/pg_helpers.rs

@@ -1,18 +1,18 @@
 use std::fmt::Write;
-use std::fs;
 use std::fs::File;
 use std::io::{BufRead, BufReader};
+use std::net::{SocketAddr, TcpStream};
 use std::os::unix::fs::PermissionsExt;
 use std::path::Path;
 use std::process::Child;
-use std::time::{Duration, Instant};
+use std::str::FromStr;
+use std::{fs, thread, time};
 
 use anyhow::{bail, Result};
-use notify::{RecursiveMode, Watcher};
 use postgres::{Client, Transaction};
 use serde::Deserialize;
 
-const POSTGRES_WAIT_TIMEOUT: Duration = Duration::from_millis(60 * 1000); // milliseconds
+const POSTGRES_WAIT_TIMEOUT: u64 = 60 * 1000; // milliseconds
 
 /// Rust representation of Postgres role info with only those fields
 /// that matter for us.
@@ -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_connection_timeout" => "neon.safekeeper_connection_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()
@@ -168,7 +161,7 @@ impl Database {
     /// it may require a proper quoting too.
     pub fn to_pg_options(&self) -> String {
         let mut params: String = self.options.as_pg_options();
-        write!(params, " OWNER {}", &self.owner.pg_quote())
+        write!(params, " OWNER {}", &self.owner.quote())
             .expect("String is documented to not to error during write operations");
 
         params
@@ -179,17 +172,18 @@ impl Database {
 /// intended to be used for DB / role names.
 pub type PgIdent = String;
 
-/// Generic trait used to provide quoting / encoding for strings used in the
-/// Postgres SQL queries and DATABASE_URL.
-pub trait Escaping {
-    fn pg_quote(&self) -> String;
+/// Generic trait used to provide quoting for strings used in the
+/// Postgres SQL queries. Currently used only to implement quoting
+/// of identifiers, but could be used for literals in the future.
+pub trait PgQuote {
+    fn quote(&self) -> String;
 }
 
-impl Escaping for PgIdent {
+impl PgQuote for PgIdent {
     /// This is intended to mimic Postgres quote_ident(), but for simplicity it
-    /// always quotes provided string with `""` and escapes every `"`.
-    /// **Not idempotent**, i.e. if string is already escaped it will be escaped again.
-    fn pg_quote(&self) -> String {
+    /// always quotes provided string with `""` and escapes every `"`. Not idempotent,
+    /// i.e. if string is already escaped it will be escaped again.
+    fn quote(&self) -> String {
         let result = format!("\"{}\"", self.replace('"', "\"\""));
         result
     }
@@ -229,112 +223,52 @@ pub fn get_existing_dbs(client: &mut Client) -> Result<Vec<Database>> {
     Ok(postgres_dbs)
 }
 
-/// Wait for Postgres to become ready to accept connections. It's ready to
-/// accept connections when the state-field in `pgdata/postmaster.pid` says
-/// 'ready'.
-pub fn wait_for_postgres(pg: &mut Child, pgdata: &Path) -> Result<()> {
+/// Wait for Postgres to become ready to accept connections:
+/// - state should be `ready` in the `pgdata/postmaster.pid`
+/// - and we should be able to connect to 127.0.0.1:5432
+pub fn wait_for_postgres(pg: &mut Child, port: &str, pgdata: &Path) -> Result<()> {
     let pid_path = pgdata.join("postmaster.pid");
+    let mut slept: u64 = 0; // ms
+    let pause = time::Duration::from_millis(100);
 
-    // PostgreSQL writes line "ready" to the postmaster.pid file, when it has
-    // completed initialization and is ready to accept connections. We want to
-    // react quickly and perform the rest of our initialization as soon as
-    // PostgreSQL starts accepting connections. Use 'notify' to be notified
-    // whenever the PID file is changed, and whenever it changes, read it to
-    // check if it's now "ready".
-    //
-    // You cannot actually watch a file before it exists, so we first watch the
-    // data directory, and once the postmaster.pid file appears, we switch to
-    // watch the file instead. We also wake up every 100 ms to poll, just in
-    // case we miss some events for some reason. Not strictly necessary, but
-    // better safe than sorry.
-    let (tx, rx) = std::sync::mpsc::channel();
-    let (mut watcher, rx): (Box<dyn Watcher>, _) = match notify::recommended_watcher(move |res| {
-        let _ = tx.send(res);
-    }) {
-        Ok(watcher) => (Box::new(watcher), rx),
-        Err(e) => {
-            match e.kind {
-                notify::ErrorKind::Io(os) if os.raw_os_error() == Some(38) => {
-                    // docker on m1 macs does not support recommended_watcher
-                    // but return "Function not implemented (os error 38)"
-                    // see https://github.com/notify-rs/notify/issues/423
-                    let (tx, rx) = std::sync::mpsc::channel();
+    let timeout = time::Duration::from_millis(10);
+    let addr = SocketAddr::from_str(&format!("127.0.0.1:{}", port)).unwrap();
 
-                    // let's poll it faster than what we check the results for (100ms)
-                    let config =
-                        notify::Config::default().with_poll_interval(Duration::from_millis(50));
-
-                    let watcher = notify::PollWatcher::new(
-                        move |res| {
-                            let _ = tx.send(res);
-                        },
-                        config,
-                    )?;
-
-                    (Box::new(watcher), rx)
-                }
-                _ => return Err(e.into()),
-            }
-        }
-    };
-
-    watcher.watch(pgdata, RecursiveMode::NonRecursive)?;
-
-    let started_at = Instant::now();
-    let mut postmaster_pid_seen = false;
     loop {
+        // Sleep POSTGRES_WAIT_TIMEOUT at max (a bit longer actually if consider a TCP timeout,
+        // but postgres starts listening almost immediately, even if it is not really
+        // ready to accept connections).
+        if slept >= POSTGRES_WAIT_TIMEOUT {
+            bail!("timed out while waiting for Postgres to start");
+        }
+
         if let Ok(Some(status)) = pg.try_wait() {
             // Postgres exited, that is not what we expected, bail out earlier.
             let code = status.code().unwrap_or(-1);
             bail!("Postgres exited unexpectedly with code {}", code);
         }
 
-        let res = rx.recv_timeout(Duration::from_millis(100));
-        log::debug!("woken up by notify: {res:?}");
-        // If there are multiple events in the channel already, we only need to be
-        // check once. Swallow the extra events before we go ahead to check the
-        // pid file.
-        while let Ok(res) = rx.try_recv() {
-            log::debug!("swallowing extra event: {res:?}");
-        }
-
         // Check that we can open pid file first.
         if let Ok(file) = File::open(&pid_path) {
-            if !postmaster_pid_seen {
-                log::debug!("postmaster.pid appeared");
-                watcher
-                    .unwatch(pgdata)
-                    .expect("Failed to remove pgdata dir watch");
-                watcher
-                    .watch(&pid_path, RecursiveMode::NonRecursive)
-                    .expect("Failed to add postmaster.pid file watch");
-                postmaster_pid_seen = true;
-            }
-
             let file = BufReader::new(file);
             let last_line = file.lines().last();
 
             // Pid file could be there and we could read it, but it could be empty, for example.
             if let Some(Ok(line)) = last_line {
                 let status = line.trim();
-                log::debug!("last line of postmaster.pid: {status:?}");
+                let can_connect = TcpStream::connect_timeout(&addr, timeout).is_ok();
 
                 // Now Postgres is ready to accept connections
-                if status == "ready" {
+                if status == "ready" && can_connect {
                     break;
                 }
             }
         }
 
-        // Give up after POSTGRES_WAIT_TIMEOUT.
-        let duration = started_at.elapsed();
-        if duration >= POSTGRES_WAIT_TIMEOUT {
-            bail!("timed out while waiting for Postgres to start");
-        }
+        thread::sleep(pause);
+        slept += 100;
     }
 
-    log::info!("PostgreSQL is now running, continuing to configure it");
-
     Ok(())
 }
 

compute_tools/src/spec.rs

@@ -1,9 +1,7 @@
 use std::path::Path;
-use std::str::FromStr;
 
 use anyhow::Result;
 use log::{info, log_enabled, warn, Level};
-use postgres::config::Config;
 use postgres::{Client, NoTls};
 use serde::Deserialize;
 
@@ -117,8 +115,8 @@ pub fn handle_roles(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
                     if existing_roles.iter().any(|r| r.name == op.name) {
                         let query: String = format!(
                             "ALTER ROLE {} RENAME TO {}",
-                            op.name.pg_quote(),
-                            new_name.pg_quote()
+                            op.name.quote(),
+                            new_name.quote()
                         );
 
                         warn!("renaming role '{}' to '{}'", op.name, new_name);
@@ -164,7 +162,7 @@ pub fn handle_roles(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
             }
 
             if update_role {
-                let mut query: String = format!("ALTER ROLE {} ", name.pg_quote());
+                let mut query: String = format!("ALTER ROLE {} ", name.quote());
                 info_print!(" -> update");
 
                 query.push_str(&role.to_pg_options());
@@ -172,7 +170,7 @@ pub fn handle_roles(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
             }
         } else {
             info!("role name: '{}'", &name);
-            let mut query: String = format!("CREATE ROLE {} ", name.pg_quote());
+            let mut query: String = format!("CREATE ROLE {} ", name.quote());
             info!("role create query: '{}'", &query);
             info_print!(" -> create");
 
@@ -181,7 +179,7 @@ pub fn handle_roles(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
 
             let grant_query = format!(
                 "GRANT pg_read_all_data, pg_write_all_data TO {}",
-                name.pg_quote()
+                name.quote()
             );
             xact.execute(grant_query.as_str(), &[])?;
             info!("role grant query: '{}'", &grant_query);
@@ -217,7 +215,7 @@ pub fn handle_role_deletions(node: &ComputeNode, client: &mut Client) -> Result<
             // We do not check either role exists or not,
             // Postgres will take care of it for us
             if op.action == "delete_role" {
-                let query: String = format!("DROP ROLE IF EXISTS {}", &op.name.pg_quote());
+                let query: String = format!("DROP ROLE IF EXISTS {}", &op.name.quote());
 
                 warn!("deleting role '{}'", &op.name);
                 xact.execute(query.as_str(), &[])?;
@@ -232,16 +230,17 @@ pub fn handle_role_deletions(node: &ComputeNode, client: &mut Client) -> Result<
 fn reassign_owned_objects(node: &ComputeNode, role_name: &PgIdent) -> Result<()> {
     for db in &node.spec.cluster.databases {
         if db.owner != *role_name {
-            let mut conf = Config::from_str(node.connstr.as_str())?;
-            conf.dbname(&db.name);
+            let mut connstr = node.connstr.clone();
+            // database name is always the last and the only component of the path
+            connstr.set_path(&db.name);
 
-            let mut client = conf.connect(NoTls)?;
+            let mut client = Client::connect(connstr.as_str(), NoTls)?;
 
             // This will reassign all dependent objects to the db owner
             let reassign_query = format!(
                 "REASSIGN OWNED BY {} TO {}",
-                role_name.pg_quote(),
-                db.owner.pg_quote()
+                role_name.quote(),
+                db.owner.quote()
             );
             info!(
                 "reassigning objects owned by '{}' in db '{}' to '{}'",
@@ -250,7 +249,7 @@ fn reassign_owned_objects(node: &ComputeNode, role_name: &PgIdent) -> Result<()>
             client.simple_query(&reassign_query)?;
 
             // This now will only drop privileges of the role
-            let drop_query = format!("DROP OWNED BY {}", role_name.pg_quote());
+            let drop_query = format!("DROP OWNED BY {}", role_name.quote());
             client.simple_query(&drop_query)?;
         }
     }
@@ -280,7 +279,7 @@ pub fn handle_databases(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
                 // We do not check either DB exists or not,
                 // Postgres will take care of it for us
                 "delete_db" => {
-                    let query: String = format!("DROP DATABASE IF EXISTS {}", &op.name.pg_quote());
+                    let query: String = format!("DROP DATABASE IF EXISTS {}", &op.name.quote());
 
                     warn!("deleting database '{}'", &op.name);
                     client.execute(query.as_str(), &[])?;
@@ -292,8 +291,8 @@ pub fn handle_databases(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
                     if existing_dbs.iter().any(|r| r.name == op.name) {
                         let query: String = format!(
                             "ALTER DATABASE {} RENAME TO {}",
-                            op.name.pg_quote(),
-                            new_name.pg_quote()
+                            op.name.quote(),
+                            new_name.quote()
                         );
 
                         warn!("renaming database '{}' to '{}'", op.name, new_name);
@@ -321,7 +320,7 @@ pub fn handle_databases(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
             // XXX: db owner name is returned as quoted string from Postgres,
             // when quoting is needed.
             let new_owner = if r.owner.starts_with('"') {
-                db.owner.pg_quote()
+                db.owner.quote()
             } else {
                 db.owner.clone()
             };
@@ -329,15 +328,15 @@ pub fn handle_databases(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
             if new_owner != r.owner {
                 let query: String = format!(
                     "ALTER DATABASE {} OWNER TO {}",
-                    name.pg_quote(),
-                    db.owner.pg_quote()
+                    name.quote(),
+                    db.owner.quote()
                 );
                 info_print!(" -> update");
 
                 client.execute(query.as_str(), &[])?;
             }
         } else {
-            let mut query: String = format!("CREATE DATABASE {} ", name.pg_quote());
+            let mut query: String = format!("CREATE DATABASE {} ", name.quote());
             info_print!(" -> create");
 
             query.push_str(&db.to_pg_options());
@@ -367,7 +366,7 @@ pub fn handle_grants(node: &ComputeNode, client: &mut Client) -> Result<()> {
         .cluster
         .roles
         .iter()
-        .map(|r| r.name.pg_quote())
+        .map(|r| r.name.quote())
         .collect::<Vec<_>>();
 
     for db in &spec.cluster.databases {
@@ -375,7 +374,7 @@ pub fn handle_grants(node: &ComputeNode, client: &mut Client) -> Result<()> {
 
         let query: String = format!(
             "GRANT CREATE ON DATABASE {} TO {}",
-            dbname.pg_quote(),
+            dbname.quote(),
             roles.join(", ")
         );
         info!("grant query {}", &query);
@@ -386,11 +385,12 @@ pub fn handle_grants(node: &ComputeNode, client: &mut Client) -> Result<()> {
     // Do some per-database access adjustments. We'd better do this at db creation time,
     // but CREATE DATABASE isn't transactional. So we cannot create db + do some grants
     // atomically.
+    let mut db_connstr = node.connstr.clone();
     for db in &node.spec.cluster.databases {
-        let mut conf = Config::from_str(node.connstr.as_str())?;
-        conf.dbname(&db.name);
+        // database name is always the last and the only component of the path
+        db_connstr.set_path(&db.name);
 
-        let mut db_client = conf.connect(NoTls)?;
+        let mut db_client = Client::connect(db_connstr.as_str(), NoTls)?;
 
         // This will only change ownership on the schema itself, not the objects
         // inside it. Without it owner of the `public` schema will be `cloud_admin`
@@ -419,36 +419,9 @@ pub fn handle_grants(node: &ComputeNode, client: &mut Client) -> Result<()> {
                     END IF;\n\
                 END\n\
             $$;",
-            db.owner.pg_quote()
+            db.owner.quote()
         );
         db_client.simple_query(&alter_query)?;
-
-        // Explicitly grant CREATE ON SCHEMA PUBLIC to the web_access user.
-        // This is needed because since postgres 15 this privilege is removed by default.
-        let grant_query = "DO $$\n\
-                BEGIN\n\
-                    IF EXISTS(\n\
-                        SELECT nspname\n\
-                        FROM pg_catalog.pg_namespace\n\
-                        WHERE nspname = 'public'\n\
-                    ) AND\n\
-                    current_setting('server_version_num')::int/10000 >= 15\n\
-                    THEN\n\
-                        IF EXISTS(\n\
-                            SELECT rolname\n\
-                            FROM pg_catalog.pg_roles\n\
-                            WHERE rolname = 'web_access'\n\
-                        )\n\
-                        THEN\n\
-                            GRANT CREATE ON SCHEMA public TO web_access;\n\
-                        END IF;\n\
-                    END IF;\n\
-                END\n\
-            $$;"
-        .to_string();
-
-        info!("grant query for db {} : {}", &db.name, &grant_query);
-        db_client.simple_query(&grant_query)?;
     }
 
     Ok(())

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",

compute_tools/tests/pg_helpers_tests.rs

@@ -28,14 +28,14 @@ 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'"
         );
     }
 
     #[test]
-    fn ident_pg_quote() {
+    fn quote_ident() {
         let ident: PgIdent = PgIdent::from("\"name\";\\n select 1;");
 
-        assert_eq!(ident.pg_quote(), "\"\"\"name\"\";\\n select 1;\"");
+        assert_eq!(ident.quote(), "\"\"\"name\"\";\\n select 1;\"");
     }
 }

control_plane/Cargo.toml

@@ -4,25 +4,19 @@ version = "0.1.0"
 edition = "2021"
 
 [dependencies]
-anyhow = "1.0"
-clap = "4.0"
-comfy-table = "6.1"
-git-version = "0.3.5"
-nix = "0.25"
-once_cell = "1.13.0"
-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev = "d052ee8b86fff9897c77b0fe89ea9daba0e1fa38" }
-regex = "1"
-reqwest = { version = "0.11", default-features = false, features = ["blocking", "json", "rustls-tls"] }
-serde = { version = "1.0", features = ["derive"] }
-serde_with = "2.0"
 tar = "0.4.38"
-thiserror = "1"
+postgres = { git = "https://github.com/zenithdb/rust-postgres.git", rev="d052ee8b86fff9897c77b0fe89ea9daba0e1fa38" }
+serde = { version = "1.0", features = ["derive"] }
+serde_with = "1.12.0"
 toml = "0.5"
-url = "2.2.2"
+lazy_static = "1.4"
+regex = "1"
+anyhow = "1.0"
+thiserror = "1"
+nix = "0.23"
+reqwest = { version = "0.11", default-features = false, features = ["blocking", "json", "rustls-tls"] }
 
-# Note: Do not directly depend on pageserver or safekeeper; use pageserver_api or safekeeper_api
-# instead, so that recompile times are better.
-pageserver_api = { path = "../libs/pageserver_api" }
-safekeeper_api = { path = "../libs/safekeeper_api" }
+pageserver = { path = "../pageserver" }
+safekeeper = { path = "../safekeeper" }
 utils = { path = "../libs/utils" }
 workspace_hack = { version = "0.1", path = "../workspace_hack" }

control_plane/simple.conf

@@ -1,4 +1,4 @@
-# Minimal neon environment with one safekeeper. This is equivalent to the built-in
+# Minimal zenith environment with one safekeeper. This is equivalent to the built-in
 # defaults that you get with no --config
 [pageserver]
 listen_pg_addr = '127.0.0.1:64000'

control_plane/src/background_process.rs

@@ -1,264 +0,0 @@
-//! Spawns and kills background processes that are needed by Neon CLI.
-//! Applies common set-up such as log and pid files (if needed) to every process.
-//!
-//! Neon CLI does not run in background, so it needs to store the information about
-//! spawned processes, which it does in this module.
-//! We do that by storing the pid of the process in the "${process_name}.pid" file.
-//! The pid file can be created by the process itself
-//! (Neon storage binaries do that and also ensure that a lock is taken onto that file)
-//! or we create such file after starting the process
-//! (non-Neon binaries don't necessarily follow our pidfile conventions).
-//! The pid stored in the file is later used to stop the service.
-//!
-//! See [`lock_file`] module for more info.
-
-use std::ffi::OsStr;
-use std::io::Write;
-use std::path::Path;
-use std::process::{Child, Command};
-use std::time::Duration;
-use std::{fs, io, thread};
-
-use anyhow::{anyhow, bail, Context, Result};
-use nix::errno::Errno;
-use nix::sys::signal::{kill, Signal};
-use nix::unistd::Pid;
-
-use utils::lock_file;
-
-const RETRIES: u32 = 15;
-const RETRY_TIMEOUT_MILLIS: u64 = 500;
-
-/// Argument to `start_process`, to indicate whether it should create pidfile or if the process creates
-/// it itself.
-pub enum InitialPidFile<'t> {
-    /// Create a pidfile, to allow future CLI invocations to manipulate the process.
-    Create(&'t Path),
-    /// The process will create the pidfile itself, need to wait for that event.
-    Expect(&'t Path),
-}
-
-/// Start a background child process using the parameters given.
-pub fn start_process<F, S: AsRef<OsStr>>(
-    process_name: &str,
-    datadir: &Path,
-    command: &Path,
-    args: &[S],
-    initial_pid_file: InitialPidFile,
-    process_status_check: F,
-) -> anyhow::Result<Child>
-where
-    F: Fn() -> anyhow::Result<bool>,
-{
-    let log_path = datadir.join(format!("{process_name}.log"));
-    let process_log_file = fs::OpenOptions::new()
-        .create(true)
-        .write(true)
-        .append(true)
-        .open(&log_path)
-        .with_context(|| {
-            format!("Could not open {process_name} log file {log_path:?} for writing")
-        })?;
-    let same_file_for_stderr = process_log_file.try_clone().with_context(|| {
-        format!("Could not reuse {process_name} log file {log_path:?} for writing stderr")
-    })?;
-
-    let mut command = Command::new(command);
-    let background_command = command
-        .stdout(process_log_file)
-        .stderr(same_file_for_stderr)
-        .args(args);
-    let filled_cmd = fill_aws_secrets_vars(fill_rust_env_vars(background_command));
-
-    let mut spawned_process = filled_cmd.spawn().with_context(|| {
-        format!("Could not spawn {process_name}, see console output and log files for details.")
-    })?;
-    let pid = spawned_process.id();
-    let pid = Pid::from_raw(
-        i32::try_from(pid)
-            .with_context(|| format!("Subprocess {process_name} has invalid pid {pid}"))?,
-    );
-
-    let pid_file_to_check = match initial_pid_file {
-        InitialPidFile::Create(target_pid_file_path) => {
-            match lock_file::create_lock_file(target_pid_file_path, pid.to_string()) {
-                lock_file::LockCreationResult::Created { .. } => {
-                    // We use "lock" file here only to create the pid file. The lock on the pidfile will be dropped as soon
-                    // as this CLI invocation exits, so it's a bit useless, but doesn't any harm either.
-                }
-                lock_file::LockCreationResult::AlreadyLocked { .. } => {
-                    anyhow::bail!("Cannot write pid file for {process_name} at path {target_pid_file_path:?}: file is already locked by another process")
-                }
-                lock_file::LockCreationResult::CreationFailed(e) => {
-                    return Err(e.context(format!(
-                    "Failed to create pid file for {process_name} at path {target_pid_file_path:?}"
-                )))
-                }
-            }
-            None
-        }
-        InitialPidFile::Expect(pid_file_path) => Some(pid_file_path),
-    };
-
-    for retries in 0..RETRIES {
-        match process_started(pid, pid_file_to_check, &process_status_check) {
-            Ok(true) => {
-                println!("\n{process_name} started, pid: {pid}");
-                return Ok(spawned_process);
-            }
-            Ok(false) => {
-                if retries < 5 {
-                    print!(".");
-                    io::stdout().flush().unwrap();
-                } else {
-                    if retries == 5 {
-                        println!() // put a line break after dots for second message
-                    }
-                    println!("{process_name} has not started yet, retrying ({retries})...");
-                }
-                thread::sleep(Duration::from_millis(RETRY_TIMEOUT_MILLIS));
-            }
-            Err(e) => {
-                println!("{process_name} failed to start: {e:#}");
-                if let Err(e) = spawned_process.kill() {
-                    println!("Could not stop {process_name} subprocess: {e:#}")
-                };
-                return Err(e);
-            }
-        }
-    }
-    anyhow::bail!("{process_name} could not start in {RETRIES} attempts");
-}
-
-/// Stops the process, using the pid file given. Returns Ok also if the process is already not running.
-pub fn stop_process(immediate: bool, process_name: &str, pid_file: &Path) -> anyhow::Result<()> {
-    if !pid_file.exists() {
-        println!("{process_name} is already stopped: no pid file {pid_file:?} is present");
-        return Ok(());
-    }
-    let pid = read_pidfile(pid_file)?;
-
-    let sig = if immediate {
-        print!("Stopping {process_name} with pid {pid} immediately..");
-        Signal::SIGQUIT
-    } else {
-        print!("Stopping {process_name} with pid {pid} gracefully..");
-        Signal::SIGTERM
-    };
-    io::stdout().flush().unwrap();
-    match kill(pid, sig) {
-        Ok(()) => (),
-        Err(Errno::ESRCH) => {
-            println!(
-                "{process_name} with pid {pid} does not exist, but a pid file {pid_file:?} was found"
-            );
-            return Ok(());
-        }
-        Err(e) => anyhow::bail!("Failed to send signal to {process_name} with pid {pid}: {e}"),
-    }
-
-    // Wait until process is gone
-    for _ in 0..RETRIES {
-        match process_has_stopped(pid) {
-            Ok(true) => {
-                println!("\n{process_name} stopped");
-                if let Err(e) = fs::remove_file(pid_file) {
-                    if e.kind() != io::ErrorKind::NotFound {
-                        eprintln!("Failed to remove pid file {pid_file:?} after stopping the process: {e:#}");
-                    }
-                }
-                return Ok(());
-            }
-            Ok(false) => {
-                print!(".");
-                io::stdout().flush().unwrap();
-                thread::sleep(Duration::from_secs(1))
-            }
-            Err(e) => {
-                println!("{process_name} with pid {pid} failed to stop: {e:#}");
-                return Err(e);
-            }
-        }
-    }
-
-    anyhow::bail!("{process_name} with pid {pid} failed to stop in {RETRIES} attempts");
-}
-
-fn fill_rust_env_vars(cmd: &mut Command) -> &mut Command {
-    let mut filled_cmd = cmd.env_clear().env("RUST_BACKTRACE", "1");
-
-    let var = "LLVM_PROFILE_FILE";
-    if let Some(val) = std::env::var_os(var) {
-        filled_cmd = filled_cmd.env(var, val);
-    }
-
-    const RUST_LOG_KEY: &str = "RUST_LOG";
-    if let Ok(rust_log_value) = std::env::var(RUST_LOG_KEY) {
-        filled_cmd.env(RUST_LOG_KEY, rust_log_value)
-    } else {
-        filled_cmd
-    }
-}
-
-fn fill_aws_secrets_vars(mut cmd: &mut Command) -> &mut Command {
-    for env_key in [
-        "AWS_ACCESS_KEY_ID",
-        "AWS_SECRET_ACCESS_KEY",
-        "AWS_SESSION_TOKEN",
-    ] {
-        if let Ok(value) = std::env::var(env_key) {
-            cmd = cmd.env(env_key, value);
-        }
-    }
-    cmd
-}
-
-fn process_started<F>(
-    pid: Pid,
-    pid_file_to_check: Option<&Path>,
-    status_check: &F,
-) -> anyhow::Result<bool>
-where
-    F: Fn() -> anyhow::Result<bool>,
-{
-    match status_check() {
-        Ok(true) => match pid_file_to_check {
-            Some(pid_file_path) => {
-                if pid_file_path.exists() {
-                    let pid_in_file = read_pidfile(pid_file_path)?;
-                    Ok(pid_in_file == pid)
-                } else {
-                    Ok(false)
-                }
-            }
-            None => Ok(true),
-        },
-        Ok(false) => Ok(false),
-        Err(e) => anyhow::bail!("process failed to start: {e}"),
-    }
-}
-
-/// Read a PID file
-///
-/// We expect a file that contains a single integer.
-fn read_pidfile(pidfile: &Path) -> Result<Pid> {
-    let pid_str = fs::read_to_string(pidfile)
-        .with_context(|| format!("failed to read pidfile {pidfile:?}"))?;
-    let pid: i32 = pid_str
-        .parse()
-        .map_err(|_| anyhow!("failed to parse pidfile {pidfile:?}"))?;
-    if pid < 1 {
-        bail!("pidfile {pidfile:?} contained bad value '{pid}'");
-    }
-    Ok(Pid::from_raw(pid))
-}
-
-fn process_has_stopped(pid: Pid) -> anyhow::Result<bool> {
-    match kill(pid, None) {
-        // Process exists, keep waiting
-        Ok(_) => Ok(false),
-        // Process not found, we're done
-        Err(Errno::ESRCH) => Ok(true),
-        Err(err) => anyhow::bail!("Failed to send signal to process with pid {pid}: {err}"),
-    }
-}

control_plane/src/compute.rs

@@ -12,14 +12,15 @@ use std::time::Duration;
 
 use anyhow::{Context, Result};
 use utils::{
-    id::{TenantId, TimelineId},
+    connstring::connection_host_port,
     lsn::Lsn,
     postgres_backend::AuthType,
+    zid::{ZTenantId, ZTimelineId},
 };
 
-use crate::local_env::{LocalEnv, DEFAULT_PG_VERSION};
-use crate::pageserver::PageServerNode;
+use crate::local_env::LocalEnv;
 use crate::postgresql_conf::PostgresConf;
+use crate::storage::PageServerNode;
 
 //
 // ComputeControlPlane
@@ -27,7 +28,7 @@ use crate::postgresql_conf::PostgresConf;
 pub struct ComputeControlPlane {
     base_port: u16,
     pageserver: Arc<PageServerNode>,
-    pub nodes: BTreeMap<(TenantId, String), Arc<PostgresNode>>,
+    pub nodes: BTreeMap<(ZTenantId, String), Arc<PostgresNode>>,
     env: LocalEnv,
 }
 
@@ -75,12 +76,11 @@ impl ComputeControlPlane {
 
     pub fn new_node(
         &mut self,
-        tenant_id: TenantId,
+        tenant_id: ZTenantId,
         name: &str,
-        timeline_id: TimelineId,
+        timeline_id: ZTimelineId,
         lsn: Option<Lsn>,
         port: Option<u16>,
-        pg_version: u32,
     ) -> Result<Arc<PostgresNode>> {
         let port = port.unwrap_or_else(|| self.get_port());
         let node = Arc::new(PostgresNode {
@@ -93,7 +93,6 @@ impl ComputeControlPlane {
             lsn,
             tenant_id,
             uses_wal_proposer: false,
-            pg_version,
         });
 
         node.create_pgdata()?;
@@ -115,11 +114,10 @@ pub struct PostgresNode {
     pub env: LocalEnv,
     pageserver: Arc<PageServerNode>,
     is_test: bool,
-    pub timeline_id: TimelineId,
+    pub timeline_id: ZTimelineId,
     pub lsn: Option<Lsn>, // if it's a read-only node. None for primary
-    pub tenant_id: TenantId,
+    pub tenant_id: ZTenantId,
     uses_wal_proposer: bool,
-    pg_version: u32,
 }
 
 impl PostgresNode {
@@ -150,17 +148,9 @@ impl PostgresNode {
         // Read a few options from the config file
         let context = format!("in config file {}", cfg_path_str);
         let port: u16 = conf.parse_field("port", &context)?;
-        let timeline_id: TimelineId = conf.parse_field("neon.timeline_id", &context)?;
-        let tenant_id: TenantId = conf.parse_field("neon.tenant_id", &context)?;
-        let uses_wal_proposer = conf.get("neon.safekeepers").is_some();
-
-        // Read postgres version from PG_VERSION file to determine which postgres version binary to use.
-        // If it doesn't exist, assume broken data directory and use default pg version.
-        let pg_version_path = entry.path().join("PG_VERSION");
-
-        let pg_version_str =
-            fs::read_to_string(pg_version_path).unwrap_or_else(|_| DEFAULT_PG_VERSION.to_string());
-        let pg_version = u32::from_str(&pg_version_str)?;
+        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("safekeepers").is_some();
 
         // parse recovery_target_lsn, if any
         let recovery_target_lsn: Option<Lsn> =
@@ -177,24 +167,17 @@ impl PostgresNode {
             lsn: recovery_target_lsn,
             tenant_id,
             uses_wal_proposer,
-            pg_version,
         })
     }
 
-    fn sync_safekeepers(&self, auth_token: &Option<String>, pg_version: u32) -> Result<Lsn> {
-        let pg_path = self.env.pg_bin_dir(pg_version)?.join("postgres");
+    fn sync_safekeepers(&self, auth_token: &Option<String>) -> Result<Lsn> {
+        let pg_path = self.env.pg_bin_dir().join("postgres");
         let mut cmd = Command::new(&pg_path);
 
         cmd.arg("--sync-safekeepers")
             .env_clear()
-            .env(
-                "LD_LIBRARY_PATH",
-                self.env.pg_lib_dir(pg_version)?.to_str().unwrap(),
-            )
-            .env(
-                "DYLD_LIBRARY_PATH",
-                self.env.pg_lib_dir(pg_version)?.to_str().unwrap(),
-            )
+            .env("LD_LIBRARY_PATH", self.env.pg_lib_dir().to_str().unwrap())
+            .env("DYLD_LIBRARY_PATH", self.env.pg_lib_dir().to_str().unwrap())
             .env("PGDATA", self.pgdata().to_str().unwrap())
             .stdout(Stdio::piped())
             // Comment this to avoid capturing stderr (useful if command hangs)
@@ -276,12 +259,14 @@ impl PostgresNode {
             })
     }
 
-    // Write postgresql.conf with default configuration
-    // and PG_VERSION file to the data directory of a new node.
+    // Connect to a page server, get base backup, and untar it to initialize a
+    // new data directory
     fn setup_pg_conf(&self, auth_type: AuthType) -> Result<()> {
         let mut conf = PostgresConf::new();
         conf.append("max_wal_senders", "10");
-        conf.append("wal_log_hints", "off");
+        // wal_log_hints is mandatory when running against pageserver (see gh issue#192)
+        // TODO: is it possible to check wal_log_hints at pageserver side via XLOG_PARAMETER_CHANGE?
+        conf.append("wal_log_hints", "on");
         conf.append("max_replication_slots", "10");
         conf.append("hot_standby", "on");
         conf.append("shared_buffers", "1MB");
@@ -299,8 +284,7 @@ impl PostgresNode {
 
         // Configure the node to fetch pages from pageserver
         let pageserver_connstr = {
-            let config = &self.pageserver.pg_connection_config;
-            let (host, port) = (config.host(), config.port());
+            let (host, port) = connection_host_port(&self.pageserver.pg_connection_config);
 
             // Set up authentication
             //
@@ -308,7 +292,7 @@ impl PostgresNode {
             // variable during compute pg startup. It is done this way because
             // otherwise user will be able to retrieve the value using SHOW
             // command or pg_settings
-            let password = if let AuthType::NeonJWT = auth_type {
+            let password = if let AuthType::ZenithJWT = auth_type {
                 "$ZENITH_AUTH_TOKEN"
             } else {
                 ""
@@ -317,7 +301,7 @@ impl PostgresNode {
             // Also note that not all parameters are supported here. Because in compute we substitute $ZENITH_AUTH_TOKEN
             // We parse this string and build it back with token from env var, and for simplicity rebuild
             // uses only needed variables namely host, port, user, password.
-            format!("postgresql://no_user:{password}@{host}:{port}")
+            format!("postgresql://no_user:{}@{}:{}", password, host, port)
         };
         conf.append("shared_preload_libraries", "neon");
         conf.append_line("");
@@ -357,7 +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,
@@ -373,9 +357,6 @@ impl PostgresNode {
         let mut file = File::create(self.pgdata().join("postgresql.conf"))?;
         file.write_all(conf.to_string().as_bytes())?;
 
-        let mut file = File::create(self.pgdata().join("PG_VERSION"))?;
-        file.write_all(self.pg_version.to_string().as_bytes())?;
-
         Ok(())
     }
 
@@ -387,7 +368,7 @@ impl PostgresNode {
             // latest data from the pageserver. That is a bit clumsy but whole bootstrap
             // procedure evolves quite actively right now, so let's think about it again
             // when things would be more stable (TODO).
-            let lsn = self.sync_safekeepers(auth_token, self.pg_version)?;
+            let lsn = self.sync_safekeepers(auth_token)?;
             if lsn == Lsn(0) {
                 None
             } else {
@@ -420,7 +401,7 @@ impl PostgresNode {
     }
 
     fn pg_ctl(&self, args: &[&str], auth_token: &Option<String>) -> Result<()> {
-        let pg_ctl_path = self.env.pg_bin_dir(self.pg_version)?.join("pg_ctl");
+        let pg_ctl_path = self.env.pg_bin_dir().join("pg_ctl");
         let mut cmd = Command::new(pg_ctl_path);
         cmd.args(
             [
@@ -436,14 +417,8 @@ impl PostgresNode {
             .concat(),
         )
         .env_clear()
-        .env(
-            "LD_LIBRARY_PATH",
-            self.env.pg_lib_dir(self.pg_version)?.to_str().unwrap(),
-        )
-        .env(
-            "DYLD_LIBRARY_PATH",
-            self.env.pg_lib_dir(self.pg_version)?.to_str().unwrap(),
-        );
+        .env("LD_LIBRARY_PATH", self.env.pg_lib_dir().to_str().unwrap())
+        .env("DYLD_LIBRARY_PATH", self.env.pg_lib_dir().to_str().unwrap());
         if let Some(token) = auth_token {
             cmd.env("ZENITH_AUTH_TOKEN", token);
         }

control_plane/src/connection.rs

@@ -1,57 +0,0 @@
-use url::Url;
-
-#[derive(Debug)]
-pub struct PgConnectionConfig {
-    url: Url,
-}
-
-impl PgConnectionConfig {
-    pub fn host(&self) -> &str {
-        self.url.host_str().expect("BUG: no host")
-    }
-
-    pub fn port(&self) -> u16 {
-        self.url.port().expect("BUG: no port")
-    }
-
-    /// Return a `<host>:<port>` string.
-    pub fn raw_address(&self) -> String {
-        format!("{}:{}", self.host(), self.port())
-    }
-
-    /// Connect using postgres protocol with TLS disabled.
-    pub fn connect_no_tls(&self) -> Result<postgres::Client, postgres::Error> {
-        postgres::Client::connect(self.url.as_str(), postgres::NoTls)
-    }
-}
-
-impl std::str::FromStr for PgConnectionConfig {
-    type Err = anyhow::Error;
-
-    fn from_str(s: &str) -> Result<Self, Self::Err> {
-        let mut url: Url = s.parse()?;
-
-        match url.scheme() {
-            "postgres" | "postgresql" => {}
-            other => anyhow::bail!("invalid scheme: {other}"),
-        }
-
-        // It's not a valid connection url if host is unavailable.
-        if url.host().is_none() {
-            anyhow::bail!(url::ParseError::EmptyHost);
-        }
-
-        // E.g. `postgres:bar`.
-        if url.cannot_be_a_base() {
-            anyhow::bail!("URL cannot be a base");
-        }
-
-        // Set the default PG port if it's missing.
-        if url.port().is_none() {
-            url.set_port(Some(5432))
-                .expect("BUG: couldn't set the default port");
-        }
-
-        Ok(Self { url })
-    }
-}

control_plane/src/etcd.rs

@@ -1,75 +1,95 @@
-use std::{fs, path::PathBuf};
+use std::{
+    fs,
+    path::PathBuf,
+    process::{Command, Stdio},
+};
 
 use anyhow::Context;
+use nix::{
+    sys::signal::{kill, Signal},
+    unistd::Pid,
+};
 
-use crate::{background_process, local_env};
+use crate::{local_env, read_pidfile};
 
 pub fn start_etcd_process(env: &local_env::LocalEnv) -> anyhow::Result<()> {
     let etcd_broker = &env.etcd_broker;
     println!(
-        "Starting etcd broker using {:?}",
-        etcd_broker.etcd_binary_path
+        "Starting etcd broker using {}",
+        etcd_broker.etcd_binary_path.display()
     );
 
     let etcd_data_dir = env.base_data_dir.join("etcd");
-    fs::create_dir_all(&etcd_data_dir)
-        .with_context(|| format!("Failed to create etcd data dir {etcd_data_dir:?}"))?;
+    fs::create_dir_all(&etcd_data_dir).with_context(|| {
+        format!(
+            "Failed to create etcd data dir: {}",
+            etcd_data_dir.display()
+        )
+    })?;
 
+    let etcd_stdout_file =
+        fs::File::create(etcd_data_dir.join("etcd.stdout.log")).with_context(|| {
+            format!(
+                "Failed to create ectd stout file in directory {}",
+                etcd_data_dir.display()
+            )
+        })?;
+    let etcd_stderr_file =
+        fs::File::create(etcd_data_dir.join("etcd.stderr.log")).with_context(|| {
+            format!(
+                "Failed to create ectd stderr file in directory {}",
+                etcd_data_dir.display()
+            )
+        })?;
     let client_urls = etcd_broker.comma_separated_endpoints();
-    let args = [
-        format!("--data-dir={}", etcd_data_dir.display()),
-        format!("--listen-client-urls={client_urls}"),
-        format!("--advertise-client-urls={client_urls}"),
-        // Set --quota-backend-bytes to keep the etcd virtual memory
-        // size smaller. Our test etcd clusters are very small.
-        // See https://github.com/etcd-io/etcd/issues/7910
-        "--quota-backend-bytes=100000000".to_string(),
-        // etcd doesn't compact (vacuum) with default settings,
-        // enable it to prevent space exhaustion.
-        "--auto-compaction-mode=revision".to_string(),
-        "--auto-compaction-retention=1".to_string(),
-    ];
 
-    let pid_file_path = etcd_pid_file_path(env);
+    let etcd_process = Command::new(&etcd_broker.etcd_binary_path)
+        .args(&[
+            format!("--data-dir={}", etcd_data_dir.display()),
+            format!("--listen-client-urls={client_urls}"),
+            format!("--advertise-client-urls={client_urls}"),
+            // Set --quota-backend-bytes to keep the etcd virtual memory
+            // size smaller. Our test etcd clusters are very small.
+            // See https://github.com/etcd-io/etcd/issues/7910
+            "--quota-backend-bytes=100000000".to_string(),
+        ])
+        .stdout(Stdio::from(etcd_stdout_file))
+        .stderr(Stdio::from(etcd_stderr_file))
+        .spawn()
+        .context("Failed to spawn etcd subprocess")?;
+    let pid = etcd_process.id();
 
-    let client = reqwest::blocking::Client::new();
-
-    background_process::start_process(
-        "etcd",
-        &etcd_data_dir,
-        &etcd_broker.etcd_binary_path,
-        &args,
-        background_process::InitialPidFile::Create(&pid_file_path),
-        || {
-            for broker_endpoint in &etcd_broker.broker_endpoints {
-                let request = broker_endpoint
-                    .join("health")
-                    .with_context(|| {
-                        format!(
-                            "Failed to append /health path to broker endopint {}",
-                            broker_endpoint
-                        )
-                    })
-                    .and_then(|url| {
-                        client.get(&url.to_string()).build().with_context(|| {
-                            format!("Failed to construct request to etcd endpoint {url}")
-                        })
-                    })?;
-                if client.execute(request).is_ok() {
-                    return Ok(true);
-                }
-            }
-
-            Ok(false)
-        },
-    )
-    .context("Failed to spawn etcd subprocess")?;
+    let etcd_pid_file_path = etcd_pid_file_path(env);
+    fs::write(&etcd_pid_file_path, pid.to_string()).with_context(|| {
+        format!(
+            "Failed to create etcd pid file at {}",
+            etcd_pid_file_path.display()
+        )
+    })?;
 
     Ok(())
 }
 
 pub fn stop_etcd_process(env: &local_env::LocalEnv) -> anyhow::Result<()> {
-    background_process::stop_process(true, "etcd", &etcd_pid_file_path(env))
+    let etcd_path = &env.etcd_broker.etcd_binary_path;
+    println!("Stopping etcd broker at {}", etcd_path.display());
+
+    let etcd_pid_file_path = etcd_pid_file_path(env);
+    let pid = Pid::from_raw(read_pidfile(&etcd_pid_file_path).with_context(|| {
+        format!(
+            "Failed to read etcd pid file at {}",
+            etcd_pid_file_path.display()
+        )
+    })?);
+
+    kill(pid, Signal::SIGTERM).with_context(|| {
+        format!(
+            "Failed to stop etcd with pid {pid} at {}",
+            etcd_pid_file_path.display()
+        )
+    })?;
+
+    Ok(())
 }
 
 fn etcd_pid_file_path(env: &local_env::LocalEnv) -> PathBuf {

control_plane/src/lib.rs

@@ -6,12 +6,55 @@
 // Intended to be used in integration tests and in CLI tools for
 // local installations.
 //
+use anyhow::{anyhow, bail, Context, Result};
+use std::fs;
+use std::path::Path;
+use std::process::Command;
 
-mod background_process;
 pub mod compute;
-pub mod connection;
 pub mod etcd;
 pub mod local_env;
-pub mod pageserver;
 pub mod postgresql_conf;
 pub mod safekeeper;
+pub mod storage;
+
+/// Read a PID file
+///
+/// We expect a file that contains a single integer.
+/// We return an i32 for compatibility with libc and nix.
+pub fn read_pidfile(pidfile: &Path) -> Result<i32> {
+    let pid_str = fs::read_to_string(pidfile)
+        .with_context(|| format!("failed to read pidfile {:?}", pidfile))?;
+    let pid: i32 = pid_str
+        .parse()
+        .map_err(|_| anyhow!("failed to parse pidfile {:?}", pidfile))?;
+    if pid < 1 {
+        bail!("pidfile {:?} contained bad value '{}'", pidfile, pid);
+    }
+    Ok(pid)
+}
+
+fn fill_rust_env_vars(cmd: &mut Command) -> &mut Command {
+    let cmd = cmd.env_clear().env("RUST_BACKTRACE", "1");
+
+    let var = "LLVM_PROFILE_FILE";
+    if let Some(val) = std::env::var_os(var) {
+        cmd.env(var, val);
+    }
+
+    const RUST_LOG_KEY: &str = "RUST_LOG";
+    if let Ok(rust_log_value) = std::env::var(RUST_LOG_KEY) {
+        cmd.env(RUST_LOG_KEY, rust_log_value)
+    } else {
+        cmd
+    }
+}
+
+fn fill_aws_secrets_vars(mut cmd: &mut Command) -> &mut Command {
+    for env_key in ["AWS_ACCESS_KEY_ID", "AWS_SECRET_ACCESS_KEY"] {
+        if let Ok(value) = std::env::var(env_key) {
+            cmd = cmd.env(env_key, value);
+        }
+    }
+    cmd
+}

control_plane/src/local_env.rs

@@ -14,19 +14,17 @@ use std::path::{Path, PathBuf};
 use std::process::{Command, Stdio};
 use utils::{
     auth::{encode_from_key_file, Claims, Scope},
-    id::{NodeId, TenantId, TenantTimelineId, TimelineId},
     postgres_backend::AuthType,
+    zid::{NodeId, ZTenantId, ZTenantTimelineId, ZTimelineId},
 };
 
 use crate::safekeeper::SafekeeperNode;
 
-pub const DEFAULT_PG_VERSION: u32 = 14;
-
 //
 // 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]
@@ -50,13 +48,13 @@ pub struct LocalEnv {
 
     // Path to pageserver binary.
     #[serde(default)]
-    pub neon_distrib_dir: PathBuf,
+    pub zenith_distrib_dir: PathBuf,
 
-    // Default tenant ID to use with the 'neon_local' command line utility, when
-    // --tenant_id is not explicitly specified.
+    // Default tenant ID to use with the 'zenith' command line utility, when
+    // --tenantid is not explicitly specified.
     #[serde(default)]
     #[serde_as(as = "Option<DisplayFromStr>")]
-    pub default_tenant_id: Option<TenantId>,
+    pub default_tenant_id: Option<ZTenantId>,
 
     // used to issue tokens during e.g pg start
     #[serde(default)]
@@ -71,11 +69,11 @@ pub struct LocalEnv {
 
     /// Keep human-readable aliases in memory (and persist them to config), to hide ZId hex strings from the user.
     #[serde(default)]
-    // A `HashMap<String, HashMap<TenantId, TimelineId>>` would be more appropriate here,
+    // A `HashMap<String, HashMap<ZTenantId, ZTimelineId>>` would be more appropriate here,
     // but deserialization into a generic toml object as `toml::Value::try_from` fails with an error.
     // https://toml.io/en/v1.0.0 does not contain a concept of "a table inside another table".
     #[serde_as(as = "HashMap<_, Vec<(DisplayFromStr, DisplayFromStr)>>")]
-    branch_name_mappings: HashMap<String, Vec<(TenantId, TimelineId)>>,
+    branch_name_mappings: HashMap<String, Vec<(ZTenantId, ZTimelineId)>>,
 }
 
 /// Etcd broker config for cluster internal communication.
@@ -197,50 +195,29 @@ impl Default for SafekeeperConf {
 }
 
 impl LocalEnv {
-    pub fn pg_distrib_dir_raw(&self) -> PathBuf {
-        self.pg_distrib_dir.clone()
+    // postgres installation paths
+    pub fn pg_bin_dir(&self) -> PathBuf {
+        self.pg_distrib_dir.join("bin")
+    }
+    pub fn pg_lib_dir(&self) -> PathBuf {
+        self.pg_distrib_dir.join("lib")
     }
 
-    pub fn pg_distrib_dir(&self, pg_version: u32) -> anyhow::Result<PathBuf> {
-        let path = self.pg_distrib_dir.clone();
-
-        match pg_version {
-            14 => Ok(path.join(format!("v{pg_version}"))),
-            15 => Ok(path.join(format!("v{pg_version}"))),
-            _ => bail!("Unsupported postgres version: {}", pg_version),
-        }
+    pub fn pageserver_bin(&self) -> anyhow::Result<PathBuf> {
+        Ok(self.zenith_distrib_dir.join("pageserver"))
     }
 
-    pub fn pg_bin_dir(&self, pg_version: u32) -> anyhow::Result<PathBuf> {
-        match pg_version {
-            14 => Ok(self.pg_distrib_dir(pg_version)?.join("bin")),
-            15 => Ok(self.pg_distrib_dir(pg_version)?.join("bin")),
-            _ => bail!("Unsupported postgres version: {}", pg_version),
-        }
-    }
-    pub fn pg_lib_dir(&self, pg_version: u32) -> anyhow::Result<PathBuf> {
-        match pg_version {
-            14 => Ok(self.pg_distrib_dir(pg_version)?.join("lib")),
-            15 => Ok(self.pg_distrib_dir(pg_version)?.join("lib")),
-            _ => bail!("Unsupported postgres version: {}", pg_version),
-        }
-    }
-
-    pub fn pageserver_bin(&self) -> PathBuf {
-        self.neon_distrib_dir.join("pageserver")
-    }
-
-    pub fn safekeeper_bin(&self) -> PathBuf {
-        self.neon_distrib_dir.join("safekeeper")
+    pub fn safekeeper_bin(&self) -> anyhow::Result<PathBuf> {
+        Ok(self.zenith_distrib_dir.join("safekeeper"))
     }
 
     pub fn pg_data_dirs_path(&self) -> PathBuf {
         self.base_data_dir.join("pgdatadirs").join("tenants")
     }
 
-    pub fn pg_data_dir(&self, tenant_id: &TenantId, branch_name: &str) -> PathBuf {
+    pub fn pg_data_dir(&self, tenantid: &ZTenantId, branch_name: &str) -> PathBuf {
         self.pg_data_dirs_path()
-            .join(tenant_id.to_string())
+            .join(tenantid.to_string())
             .join(branch_name)
     }
 
@@ -256,8 +233,8 @@ impl LocalEnv {
     pub fn register_branch_mapping(
         &mut self,
         branch_name: String,
-        tenant_id: TenantId,
-        timeline_id: TimelineId,
+        tenant_id: ZTenantId,
+        timeline_id: ZTimelineId,
     ) -> anyhow::Result<()> {
         let existing_values = self
             .branch_name_mappings
@@ -283,22 +260,22 @@ impl LocalEnv {
     pub fn get_branch_timeline_id(
         &self,
         branch_name: &str,
-        tenant_id: TenantId,
-    ) -> Option<TimelineId> {
+        tenant_id: ZTenantId,
+    ) -> Option<ZTimelineId> {
         self.branch_name_mappings
             .get(branch_name)?
             .iter()
             .find(|(mapped_tenant_id, _)| mapped_tenant_id == &tenant_id)
             .map(|&(_, timeline_id)| timeline_id)
-            .map(TimelineId::from)
+            .map(ZTimelineId::from)
     }
 
-    pub fn timeline_name_mappings(&self) -> HashMap<TenantTimelineId, String> {
+    pub fn timeline_name_mappings(&self) -> HashMap<ZTenantTimelineId, String> {
         self.branch_name_mappings
             .iter()
             .flat_map(|(name, tenant_timelines)| {
                 tenant_timelines.iter().map(|&(tenant_id, timeline_id)| {
-                    (TenantTimelineId::new(tenant_id, timeline_id), name.clone())
+                    (ZTenantTimelineId::new(tenant_id, timeline_id), name.clone())
                 })
             })
             .collect()
@@ -312,26 +289,24 @@ impl LocalEnv {
         let mut env: LocalEnv = toml::from_str(toml)?;
 
         // Find postgres binaries.
-        // Follow POSTGRES_DISTRIB_DIR if set, otherwise look in "pg_install".
-        // Note that later in the code we assume, that distrib dirs follow the same pattern
-        // for all postgres versions.
+        // Follow POSTGRES_DISTRIB_DIR if set, otherwise look in "tmp_install".
         if env.pg_distrib_dir == Path::new("") {
             if let Some(postgres_bin) = env::var_os("POSTGRES_DISTRIB_DIR") {
                 env.pg_distrib_dir = postgres_bin.into();
             } else {
                 let cwd = env::current_dir()?;
-                env.pg_distrib_dir = cwd.join("pg_install")
+                env.pg_distrib_dir = cwd.join("tmp_install")
             }
         }
 
-        // Find neon binaries.
-        if env.neon_distrib_dir == Path::new("") {
-            env.neon_distrib_dir = env::current_exe()?.parent().unwrap().to_owned();
+        // Find zenith binaries.
+        if env.zenith_distrib_dir == Path::new("") {
+            env.zenith_distrib_dir = env::current_exe()?.parent().unwrap().to_owned();
         }
 
         // If no initial tenant ID was given, generate it.
         if env.default_tenant_id.is_none() {
-            env.default_tenant_id = Some(TenantId::generate());
+            env.default_tenant_id = Some(ZTenantId::generate());
         }
 
         env.base_data_dir = base_path();
@@ -345,12 +320,12 @@ impl LocalEnv {
 
         if !repopath.exists() {
             bail!(
-                "Neon 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()
             );
         }
 
-        // TODO: check that it looks like a neon repository
+        // TODO: check that it looks like a zenith repository
 
         // load and parse file
         let config = fs::read_to_string(repopath.join("config"))?;
@@ -362,12 +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();
@@ -407,9 +382,9 @@ impl LocalEnv {
     }
 
     //
-    // Initialize a new Neon repository
+    // Initialize a new Zenith repository
     //
-    pub fn init(&mut self, pg_version: u32) -> anyhow::Result<()> {
+    pub fn init(&mut self) -> anyhow::Result<()> {
         // check if config already exists
         let base_path = &self.base_data_dir;
         ensure!(
@@ -422,17 +397,17 @@ impl LocalEnv {
             "directory '{}' already exists. Perhaps already initialized?",
             base_path.display()
         );
-        if !self.pg_bin_dir(pg_version)?.join("postgres").exists() {
+        if !self.pg_distrib_dir.join("bin/postgres").exists() {
             bail!(
                 "Can't find postgres binary at {}",
-                self.pg_bin_dir(pg_version)?.display()
+                self.pg_distrib_dir.display()
             );
         }
         for binary in ["pageserver", "safekeeper"] {
-            if !self.neon_distrib_dir.join(binary).exists() {
+            if !self.zenith_distrib_dir.join(binary).exists() {
                 bail!(
-                    "Can't find binary '{binary}' in neon distrib dir '{}'",
-                    self.neon_distrib_dir.display()
+                    "Can't find binary '{binary}' in zenith distrib dir '{}'",
+                    self.zenith_distrib_dir.display()
                 );
             }
         }

control_plane/src/pageserver.rs

@@ -1,539 +0,0 @@
-use std::collections::HashMap;
-use std::fs::{self, File};
-use std::io::{BufReader, Write};
-use std::num::NonZeroU64;
-use std::path::{Path, PathBuf};
-use std::process::Child;
-use std::{io, result};
-
-use crate::connection::PgConnectionConfig;
-use anyhow::{bail, Context};
-use pageserver_api::models::{
-    TenantConfigRequest, TenantCreateRequest, TenantInfo, TimelineCreateRequest, TimelineInfo,
-};
-use reqwest::blocking::{Client, RequestBuilder, Response};
-use reqwest::{IntoUrl, Method};
-use thiserror::Error;
-use utils::{
-    http::error::HttpErrorBody,
-    id::{TenantId, TimelineId},
-    lsn::Lsn,
-    postgres_backend::AuthType,
-};
-
-use crate::{background_process, local_env::LocalEnv};
-
-#[derive(Error, Debug)]
-pub enum PageserverHttpError {
-    #[error("Reqwest error: {0}")]
-    Transport(#[from] reqwest::Error),
-
-    #[error("Error: {0}")]
-    Response(String),
-}
-
-impl From<anyhow::Error> for PageserverHttpError {
-    fn from(e: anyhow::Error) -> Self {
-        Self::Response(e.to_string())
-    }
-}
-
-type Result<T> = result::Result<T, PageserverHttpError>;
-
-pub trait ResponseErrorMessageExt: Sized {
-    fn error_from_body(self) -> Result<Self>;
-}
-
-impl ResponseErrorMessageExt for Response {
-    fn error_from_body(self) -> Result<Self> {
-        let status = self.status();
-        if !(status.is_client_error() || status.is_server_error()) {
-            return Ok(self);
-        }
-
-        // reqwest does not export its error construction utility functions, so let's craft the message ourselves
-        let url = self.url().to_owned();
-        Err(PageserverHttpError::Response(
-            match self.json::<HttpErrorBody>() {
-                Ok(err_body) => format!("Error: {}", err_body.msg),
-                Err(_) => format!("Http error ({}) at {}.", status.as_u16(), url),
-            },
-        ))
-    }
-}
-
-//
-// Control routines for pageserver.
-//
-// Used in CLI and tests.
-//
-#[derive(Debug)]
-pub struct PageServerNode {
-    pub pg_connection_config: PgConnectionConfig,
-    pub env: LocalEnv,
-    pub http_client: Client,
-    pub http_base_url: String,
-}
-
-impl PageServerNode {
-    pub fn from_env(env: &LocalEnv) -> PageServerNode {
-        let password = if env.pageserver.auth_type == AuthType::NeonJWT {
-            &env.pageserver.auth_token
-        } else {
-            ""
-        };
-
-        Self {
-            pg_connection_config: Self::pageserver_connection_config(
-                password,
-                &env.pageserver.listen_pg_addr,
-            ),
-            env: env.clone(),
-            http_client: Client::new(),
-            http_base_url: format!("http://{}/v1", env.pageserver.listen_http_addr),
-        }
-    }
-
-    /// Construct libpq connection string for connecting to the pageserver.
-    fn pageserver_connection_config(password: &str, listen_addr: &str) -> PgConnectionConfig {
-        format!("postgresql://no_user:{password}@{listen_addr}/no_db")
-            .parse()
-            .unwrap()
-    }
-
-    pub fn initialize(
-        &self,
-        create_tenant: Option<TenantId>,
-        initial_timeline_id: Option<TimelineId>,
-        config_overrides: &[&str],
-        pg_version: u32,
-    ) -> anyhow::Result<TimelineId> {
-        let id = format!("id={}", self.env.pageserver.id);
-        // FIXME: the paths should be shell-escaped to handle paths with spaces, quotas etc.
-        let pg_distrib_dir_param = format!(
-            "pg_distrib_dir='{}'",
-            self.env.pg_distrib_dir_raw().display()
-        );
-
-        let authg_type_param = format!("auth_type='{}'", self.env.pageserver.auth_type);
-        let listen_http_addr_param = format!(
-            "listen_http_addr='{}'",
-            self.env.pageserver.listen_http_addr
-        );
-        let listen_pg_addr_param =
-            format!("listen_pg_addr='{}'", self.env.pageserver.listen_pg_addr);
-        let broker_endpoints_param = format!(
-            "broker_endpoints=[{}]",
-            self.env
-                .etcd_broker
-                .broker_endpoints
-                .iter()
-                .map(|url| format!("'{url}'"))
-                .collect::<Vec<_>>()
-                .join(",")
-        );
-        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);
-        }
-
-        if self.env.pageserver.auth_type != AuthType::Trust {
-            init_config_overrides.push("auth_validation_public_key_path='auth_public_key.pem'");
-        }
-
-        let mut pageserver_process = self
-            .start_node(&init_config_overrides, &self.env.base_data_dir, true)
-            .with_context(|| {
-                format!(
-                    "Failed to start a process for pageserver {}",
-                    self.env.pageserver.id,
-                )
-            })?;
-
-        let init_result = self
-            .try_init_timeline(create_tenant, initial_timeline_id, pg_version)
-            .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:#}"),
-        }
-        match pageserver_process.kill() {
-            Err(e) => {
-                eprintln!(
-                    "Failed to stop pageserver {} process with pid {}: {e:#}",
-                    self.env.pageserver.id,
-                    pageserver_process.id(),
-                )
-            }
-            Ok(()) => {
-                println!(
-                    "Stopped pageserver {} process with pid {}",
-                    self.env.pageserver.id,
-                    pageserver_process.id(),
-                );
-                // cleanup after pageserver startup, since we do not call regular `stop_process` during init
-                let pid_file = self.pid_file();
-                if let Err(e) = fs::remove_file(&pid_file) {
-                    if e.kind() != io::ErrorKind::NotFound {
-                        eprintln!("Failed to remove pid file {pid_file:?} after stopping the process: {e:#}");
-                    }
-                }
-            }
-        }
-        init_result
-    }
-
-    fn try_init_timeline(
-        &self,
-        new_tenant_id: Option<TenantId>,
-        new_timeline_id: Option<TimelineId>,
-        pg_version: u32,
-    ) -> anyhow::Result<TimelineId> {
-        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,
-            Some(pg_version),
-        )?;
-        Ok(initial_timeline_info.timeline_id)
-    }
-
-    pub fn repo_path(&self) -> PathBuf {
-        self.env.pageserver_data_dir()
-    }
-
-    /// The pid file is created by the pageserver process, with its pid stored inside.
-    /// Other pageservers cannot lock the same file and overwrite it for as long as the current
-    /// pageserver runs. (Unless someone removes the file manually; never do that!)
-    fn pid_file(&self) -> PathBuf {
-        self.repo_path().join("pageserver.pid")
-    }
-
-    pub fn start(&self, config_overrides: &[&str]) -> anyhow::Result<Child> {
-        self.start_node(config_overrides, &self.repo_path(), false)
-    }
-
-    fn start_node(
-        &self,
-        config_overrides: &[&str],
-        datadir: &Path,
-        update_config: bool,
-    ) -> anyhow::Result<Child> {
-        println!(
-            "Starting pageserver at '{}' in '{}'",
-            self.pg_connection_config.raw_address(),
-            datadir.display()
-        );
-        io::stdout().flush()?;
-
-        let mut args = vec![
-            "-D",
-            datadir.to_str().with_context(|| {
-                format!("Datadir path {datadir:?} cannot be represented as a unicode string")
-            })?,
-        ];
-
-        if update_config {
-            args.push("--update-config");
-        }
-
-        for config_override in config_overrides {
-            args.extend(["-c", config_override]);
-        }
-
-        background_process::start_process(
-            "pageserver",
-            datadir,
-            &self.env.pageserver_bin(),
-            &args,
-            background_process::InitialPidFile::Expect(&self.pid_file()),
-            || match self.check_status() {
-                Ok(()) => Ok(true),
-                Err(PageserverHttpError::Transport(_)) => Ok(false),
-                Err(e) => Err(anyhow::anyhow!("Failed to check node status: {e}")),
-            },
-        )
-    }
-
-    ///
-    /// Stop the server.
-    ///
-    /// If 'immediate' is true, we use SIGQUIT, killing the process immediately.
-    /// Otherwise we use SIGTERM, triggering a clean shutdown
-    ///
-    /// If the server is not running, returns success
-    ///
-    pub fn stop(&self, immediate: bool) -> anyhow::Result<()> {
-        background_process::stop_process(immediate, "pageserver", &self.pid_file())
-    }
-
-    pub fn page_server_psql(&self, sql: &str) -> Vec<postgres::SimpleQueryMessage> {
-        let mut client = self.pg_connection_config.connect_no_tls().unwrap();
-
-        println!("Pageserver query: '{sql}'");
-        client.simple_query(sql).unwrap()
-    }
-
-    pub fn page_server_psql_client(&self) -> result::Result<postgres::Client, postgres::Error> {
-        self.pg_connection_config.connect_no_tls()
-    }
-
-    fn http_request<U: IntoUrl>(&self, method: Method, url: U) -> RequestBuilder {
-        let mut builder = self.http_client.request(method, url);
-        if self.env.pageserver.auth_type == AuthType::NeonJWT {
-            builder = builder.bearer_auth(&self.env.pageserver.auth_token)
-        }
-        builder
-    }
-
-    pub fn check_status(&self) -> Result<()> {
-        self.http_request(Method::GET, format!("{}/status", self.http_base_url))
-            .send()?
-            .error_from_body()?;
-        Ok(())
-    }
-
-    pub fn tenant_list(&self) -> Result<Vec<TenantInfo>> {
-        Ok(self
-            .http_request(Method::GET, format!("{}/tenant", self.http_base_url))
-            .send()?
-            .error_from_body()?
-            .json()?)
-    }
-
-    pub fn tenant_create(
-        &self,
-        new_tenant_id: Option<TenantId>,
-        settings: HashMap<&str, &str>,
-    ) -> anyhow::Result<TenantId> {
-        let mut settings = settings.clone();
-        let request = TenantCreateRequest {
-            new_tenant_id,
-            checkpoint_distance: settings
-                .remove("checkpoint_distance")
-                .map(|x| x.parse::<u64>())
-                .transpose()?,
-            checkpoint_timeout: settings.remove("checkpoint_timeout").map(|x| x.to_string()),
-            compaction_target_size: settings
-                .remove("compaction_target_size")
-                .map(|x| x.parse::<u64>())
-                .transpose()?,
-            compaction_period: settings.remove("compaction_period").map(|x| x.to_string()),
-            compaction_threshold: settings
-                .remove("compaction_threshold")
-                .map(|x| x.parse::<usize>())
-                .transpose()?,
-            gc_horizon: settings
-                .remove("gc_horizon")
-                .map(|x| x.parse::<u64>())
-                .transpose()?,
-            gc_period: settings.remove("gc_period").map(|x| x.to_string()),
-            image_creation_threshold: settings
-                .remove("image_creation_threshold")
-                .map(|x| x.parse::<usize>())
-                .transpose()?,
-            pitr_interval: settings.remove("pitr_interval").map(|x| x.to_string()),
-            walreceiver_connect_timeout: settings
-                .remove("walreceiver_connect_timeout")
-                .map(|x| x.to_string()),
-            lagging_wal_timeout: settings
-                .remove("lagging_wal_timeout")
-                .map(|x| x.to_string()),
-            max_lsn_wal_lag: settings
-                .remove("max_lsn_wal_lag")
-                .map(|x| x.parse::<NonZeroU64>())
-                .transpose()
-                .context("Failed to parse 'max_lsn_wal_lag' as non zero integer")?,
-            trace_read_requests: settings
-                .remove("trace_read_requests")
-                .map(|x| x.parse::<bool>())
-                .transpose()
-                .context("Failed to parse 'trace_read_requests' as bool")?,
-        };
-        if !settings.is_empty() {
-            bail!("Unrecognized tenant settings: {settings:?}")
-        }
-        self.http_request(Method::POST, format!("{}/tenant", self.http_base_url))
-            .json(&request)
-            .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}'")
-                })
-            })
-    }
-
-    pub fn tenant_config(&self, tenant_id: TenantId, settings: HashMap<&str, &str>) -> Result<()> {
-        self.http_request(Method::PUT, format!("{}/tenant/config", self.http_base_url))
-            .json(&TenantConfigRequest {
-                tenant_id,
-                checkpoint_distance: settings
-                    .get("checkpoint_distance")
-                    .map(|x| x.parse::<u64>())
-                    .transpose()
-                    .context("Failed to parse 'checkpoint_distance' as an integer")?,
-                checkpoint_timeout: settings.get("checkpoint_timeout").map(|x| x.to_string()),
-                compaction_target_size: settings
-                    .get("compaction_target_size")
-                    .map(|x| x.parse::<u64>())
-                    .transpose()
-                    .context("Failed to parse 'compaction_target_size' as an integer")?,
-                compaction_period: settings.get("compaction_period").map(|x| x.to_string()),
-                compaction_threshold: settings
-                    .get("compaction_threshold")
-                    .map(|x| x.parse::<usize>())
-                    .transpose()
-                    .context("Failed to parse 'compaction_threshold' as an integer")?,
-                gc_horizon: settings
-                    .get("gc_horizon")
-                    .map(|x| x.parse::<u64>())
-                    .transpose()
-                    .context("Failed to parse 'gc_horizon' as an integer")?,
-                gc_period: settings.get("gc_period").map(|x| x.to_string()),
-                image_creation_threshold: settings
-                    .get("image_creation_threshold")
-                    .map(|x| x.parse::<usize>())
-                    .transpose()
-                    .context("Failed to parse 'image_creation_threshold' as non zero integer")?,
-                pitr_interval: settings.get("pitr_interval").map(|x| x.to_string()),
-                walreceiver_connect_timeout: settings
-                    .get("walreceiver_connect_timeout")
-                    .map(|x| x.to_string()),
-                lagging_wal_timeout: settings.get("lagging_wal_timeout").map(|x| x.to_string()),
-                max_lsn_wal_lag: settings
-                    .get("max_lsn_wal_lag")
-                    .map(|x| x.parse::<NonZeroU64>())
-                    .transpose()
-                    .context("Failed to parse 'max_lsn_wal_lag' as non zero integer")?,
-                trace_read_requests: settings
-                    .get("trace_read_requests")
-                    .map(|x| x.parse::<bool>())
-                    .transpose()
-                    .context("Failed to parse 'trace_read_requests' as bool")?,
-            })
-            .send()?
-            .error_from_body()?;
-
-        Ok(())
-    }
-
-    pub fn timeline_list(&self, tenant_id: &TenantId) -> anyhow::Result<Vec<TimelineInfo>> {
-        let timeline_infos: Vec<TimelineInfo> = self
-            .http_request(
-                Method::GET,
-                format!("{}/tenant/{}/timeline", self.http_base_url, tenant_id),
-            )
-            .send()?
-            .error_from_body()?
-            .json()?;
-
-        Ok(timeline_infos)
-    }
-
-    pub fn timeline_create(
-        &self,
-        tenant_id: TenantId,
-        new_timeline_id: Option<TimelineId>,
-        ancestor_start_lsn: Option<Lsn>,
-        ancestor_timeline_id: Option<TimelineId>,
-        pg_version: Option<u32>,
-    ) -> 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,
-            pg_version,
-        })
-        .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}"
-            )
-        })
-    }
-
-    /// Import a basebackup prepared using either:
-    /// a) `pg_basebackup -F tar`, or
-    /// b) The `fullbackup` pageserver endpoint
-    ///
-    /// # Arguments
-    /// * `tenant_id` - tenant to import into. Created if not exists
-    /// * `timeline_id` - id to assign to imported timeline
-    /// * `base` - (start lsn of basebackup, path to `base.tar` file)
-    /// * `pg_wal` - if there's any wal to import: (end lsn, path to `pg_wal.tar`)
-    pub fn timeline_import(
-        &self,
-        tenant_id: TenantId,
-        timeline_id: TimelineId,
-        base: (Lsn, PathBuf),
-        pg_wal: Option<(Lsn, PathBuf)>,
-        pg_version: u32,
-    ) -> anyhow::Result<()> {
-        let mut client = self.pg_connection_config.connect_no_tls().unwrap();
-
-        // Init base reader
-        let (start_lsn, base_tarfile_path) = base;
-        let base_tarfile = File::open(base_tarfile_path)?;
-        let mut base_reader = BufReader::new(base_tarfile);
-
-        // Init wal reader if necessary
-        let (end_lsn, wal_reader) = if let Some((end_lsn, wal_tarfile_path)) = pg_wal {
-            let wal_tarfile = File::open(wal_tarfile_path)?;
-            let wal_reader = BufReader::new(wal_tarfile);
-            (end_lsn, Some(wal_reader))
-        } else {
-            (start_lsn, None)
-        };
-
-        // Import base
-        let import_cmd = format!(
-            "import basebackup {tenant_id} {timeline_id} {start_lsn} {end_lsn} {pg_version}"
-        );
-        let mut writer = client.copy_in(&import_cmd)?;
-        io::copy(&mut base_reader, &mut writer)?;
-        writer.finish()?;
-
-        // Import wal if necessary
-        if let Some(mut wal_reader) = wal_reader {
-            let import_cmd = format!("import wal {tenant_id} {timeline_id} {start_lsn} {end_lsn}");
-            let mut writer = client.copy_in(&import_cmd)?;
-            io::copy(&mut wal_reader, &mut writer)?;
-            writer.finish()?;
-        }
-
-        Ok(())
-    }
-}

control_plane/src/postgresql_conf.rs

@@ -2,10 +2,10 @@
 /// Module for parsing postgresql.conf file.
 ///
 /// NOTE: This doesn't implement the full, correct postgresql.conf syntax. Just
-/// enough to extract a few settings we need in Neon, assuming you don't do
+/// enough to extract a few settings we need in Zenith, assuming you don't do
 /// funny stuff like include-directives or funny escaping.
 use anyhow::{bail, Context, Result};
-use once_cell::sync::Lazy;
+use lazy_static::lazy_static;
 use regex::Regex;
 use std::collections::HashMap;
 use std::fmt;
@@ -19,7 +19,9 @@ pub struct PostgresConf {
     hash: HashMap<String, String>,
 }
 
-static CONF_LINE_RE: Lazy<Regex> = Lazy::new(|| Regex::new(r"^((?:\w|\.)+)\s*=\s*(\S+)$").unwrap());
+lazy_static! {
+    static ref CONF_LINE_RE: Regex = Regex::new(r"^((?:\w|\.)+)\s*=\s*(\S+)$").unwrap();
+}
 
 impl PostgresConf {
     pub fn new() -> PostgresConf {
@@ -137,10 +139,10 @@ fn escape_str(s: &str) -> String {
     //
     // This regex is a bit more conservative than the rules in guc-file.l, so we quote some
     // strings that PostgreSQL would accept without quoting, but that's OK.
-
-    static UNQUOTED_RE: Lazy<Regex> =
-        Lazy::new(|| Regex::new(r"(^[-+]?[0-9]+[a-zA-Z]*$)|(^[a-zA-Z][a-zA-Z0-9]*$)").unwrap());
-
+    lazy_static! {
+        static ref UNQUOTED_RE: Regex =
+            Regex::new(r"(^[-+]?[0-9]+[a-zA-Z]*$)|(^[a-zA-Z][a-zA-Z0-9]*$)").unwrap();
+    }
     if UNQUOTED_RE.is_match(s) {
         s.to_string()
     } else {

control_plane/src/safekeeper.rs

@@ -1,22 +1,30 @@
 use std::io::Write;
+use std::net::TcpStream;
 use std::path::PathBuf;
-use std::process::Child;
+use std::process::Command;
 use std::sync::Arc;
-use std::{io, result};
+use std::time::Duration;
+use std::{io, result, thread};
 
-use anyhow::Context;
+use anyhow::bail;
+use nix::errno::Errno;
+use nix::sys::signal::{kill, Signal};
+use nix::unistd::Pid;
+use postgres::Config;
 use reqwest::blocking::{Client, RequestBuilder, Response};
 use reqwest::{IntoUrl, Method};
+use safekeeper::http::models::TimelineCreateRequest;
 use thiserror::Error;
-use utils::{http::error::HttpErrorBody, id::NodeId};
-
-use crate::connection::PgConnectionConfig;
-use crate::pageserver::PageServerNode;
-use crate::{
-    background_process,
-    local_env::{LocalEnv, SafekeeperConf},
+use utils::{
+    connstring::connection_address,
+    http::error::HttpErrorBody,
+    zid::{NodeId, ZTenantId, ZTimelineId},
 };
 
+use crate::local_env::{LocalEnv, SafekeeperConf};
+use crate::storage::PageServerNode;
+use crate::{fill_aws_secrets_vars, fill_rust_env_vars, read_pidfile};
+
 #[derive(Error, Debug)]
 pub enum SafekeeperHttpError {
     #[error("Reqwest error: {0}")]
@@ -39,12 +47,12 @@ impl ResponseErrorMessageExt for Response {
             return Ok(self);
         }
 
-        // reqwest does not export its error construction utility functions, so let's craft the message ourselves
+        // reqwest do not export it's error construction utility functions, so lets craft the message ourselves
         let url = self.url().to_owned();
         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()),
             },
         ))
     }
@@ -61,7 +69,7 @@ pub struct SafekeeperNode {
 
     pub conf: SafekeeperConf,
 
-    pub pg_connection_config: PgConnectionConfig,
+    pub pg_connection_config: Config,
     pub env: LocalEnv,
     pub http_client: Client,
     pub http_base_url: String,
@@ -85,15 +93,15 @@ impl SafekeeperNode {
     }
 
     /// Construct libpq connection string for connecting to this safekeeper.
-    fn safekeeper_connection_config(port: u16) -> PgConnectionConfig {
+    fn safekeeper_connection_config(port: u16) -> Config {
         // TODO safekeeper authentication not implemented yet
-        format!("postgresql://no_user@127.0.0.1:{port}/no_db")
+        format!("postgresql://no_user@127.0.0.1:{}/no_db", port)
             .parse()
             .unwrap()
     }
 
     pub fn datadir_path_by_id(env: &LocalEnv, sk_id: NodeId) -> PathBuf {
-        env.safekeeper_data_dir(&format!("sk{sk_id}"))
+        env.safekeeper_data_dir(format!("sk{}", sk_id).as_ref())
     }
 
     pub fn datadir_path(&self) -> PathBuf {
@@ -104,78 +112,92 @@ impl SafekeeperNode {
         self.datadir_path().join("safekeeper.pid")
     }
 
-    pub fn start(&self) -> anyhow::Result<Child> {
+    pub fn start(&self) -> anyhow::Result<()> {
         print!(
             "Starting safekeeper at '{}' in '{}'",
-            self.pg_connection_config.raw_address(),
+            connection_address(&self.pg_connection_config),
             self.datadir_path().display()
         );
         io::stdout().flush().unwrap();
 
         let listen_pg = format!("127.0.0.1:{}", self.conf.pg_port);
         let listen_http = format!("127.0.0.1:{}", self.conf.http_port);
-        let id = self.id;
-        let datadir = self.datadir_path();
 
-        let id_string = id.to_string();
-        let mut args = vec![
-            "-D",
-            datadir.to_str().with_context(|| {
-                format!("Datadir path {datadir:?} cannot be represented as a unicode string")
-            })?,
-            "--id",
-            &id_string,
-            "--listen-pg",
-            &listen_pg,
-            "--listen-http",
-            &listen_http,
-        ];
+        let mut cmd = Command::new(self.env.safekeeper_bin()?);
+        fill_rust_env_vars(
+            cmd.args(&["-D", self.datadir_path().to_str().unwrap()])
+                .args(&["--id", self.id.to_string().as_ref()])
+                .args(&["--listen-pg", &listen_pg])
+                .args(&["--listen-http", &listen_http])
+                .args(&["--recall", "1 second"])
+                .arg("--daemonize"),
+        );
         if !self.conf.sync {
-            args.push("--no-sync");
+            cmd.arg("--no-sync");
         }
 
         let comma_separated_endpoints = self.env.etcd_broker.comma_separated_endpoints();
         if !comma_separated_endpoints.is_empty() {
-            args.extend(["--broker-endpoints", &comma_separated_endpoints]);
+            cmd.args(&["--broker-endpoints", &comma_separated_endpoints]);
         }
         if let Some(prefix) = self.env.etcd_broker.broker_etcd_prefix.as_deref() {
-            args.extend(["--broker-etcd-prefix", prefix]);
+            cmd.args(&["--broker-etcd-prefix", prefix]);
         }
-
-        let mut backup_threads = String::new();
         if let Some(threads) = self.conf.backup_threads {
-            backup_threads = threads.to_string();
-            args.extend(["--backup-threads", &backup_threads]);
-        } else {
-            drop(backup_threads);
+            cmd.args(&["--backup-threads", threads.to_string().as_ref()]);
         }
-
         if let Some(ref remote_storage) = self.conf.remote_storage {
-            args.extend(["--remote-storage", remote_storage]);
+            cmd.args(&["--remote-storage", remote_storage]);
         }
-
-        let key_path = self.env.base_data_dir.join("auth_public_key.pem");
         if self.conf.auth_enabled {
-            args.extend([
-                "--auth-validation-public-key-path",
-                key_path.to_str().with_context(|| {
-                    format!("Key path {key_path:?} cannot be represented as a unicode string")
-                })?,
-            ]);
+            cmd.arg("--auth-validation-public-key-path");
+            // PathBuf is better be passed as is, not via `String`.
+            cmd.arg(self.env.base_data_dir.join("auth_public_key.pem"));
         }
 
-        background_process::start_process(
-            &format!("safekeeper {id}"),
-            &datadir,
-            &self.env.safekeeper_bin(),
-            &args,
-            background_process::InitialPidFile::Expect(&self.pid_file()),
-            || match self.check_status() {
-                Ok(()) => Ok(true),
-                Err(SafekeeperHttpError::Transport(_)) => Ok(false),
-                Err(e) => Err(anyhow::anyhow!("Failed to check node status: {e}")),
-            },
-        )
+        fill_aws_secrets_vars(&mut cmd);
+
+        if !cmd.status()?.success() {
+            bail!(
+                "Safekeeper failed to start. See '{}' for details.",
+                self.datadir_path().join("safekeeper.log").display()
+            );
+        }
+
+        // It takes a while for the safekeeper to start up. Wait until it is
+        // open for business.
+        const RETRIES: i8 = 15;
+        for retries in 1..RETRIES {
+            match self.check_status() {
+                Ok(_) => {
+                    println!("\nSafekeeper started");
+                    return Ok(());
+                }
+                Err(err) => {
+                    match err {
+                        SafekeeperHttpError::Transport(err) => {
+                            if err.is_connect() && retries < 5 {
+                                print!(".");
+                                io::stdout().flush().unwrap();
+                            } else {
+                                if retries == 5 {
+                                    println!() // put a line break after dots for second message
+                                }
+                                println!(
+                                    "Safekeeper not responding yet, err {} retrying ({})...",
+                                    err, retries
+                                );
+                            }
+                        }
+                        SafekeeperHttpError::Response(msg) => {
+                            bail!("safekeeper failed to start: {} ", msg)
+                        }
+                    }
+                    thread::sleep(Duration::from_secs(1));
+                }
+            }
+        }
+        bail!("safekeeper failed to start in {} seconds", RETRIES);
     }
 
     ///
@@ -187,16 +209,80 @@ impl SafekeeperNode {
     /// If the server is not running, returns success
     ///
     pub fn stop(&self, immediate: bool) -> anyhow::Result<()> {
-        background_process::stop_process(
-            immediate,
-            &format!("safekeeper {}", self.id),
-            &self.pid_file(),
-        )
+        let pid_file = self.pid_file();
+        if !pid_file.exists() {
+            println!("Safekeeper {} is already stopped", self.id);
+            return Ok(());
+        }
+        let pid = read_pidfile(&pid_file)?;
+        let pid = Pid::from_raw(pid);
+
+        let sig = if immediate {
+            print!("Stopping safekeeper {} immediately..", self.id);
+            Signal::SIGQUIT
+        } else {
+            print!("Stopping safekeeper {} gracefully..", self.id);
+            Signal::SIGTERM
+        };
+        io::stdout().flush().unwrap();
+        match kill(pid, sig) {
+            Ok(_) => (),
+            Err(Errno::ESRCH) => {
+                println!(
+                    "Safekeeper with pid {} does not exist, but a PID file was found",
+                    pid
+                );
+                return Ok(());
+            }
+            Err(err) => bail!(
+                "Failed to send signal to safekeeper 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 _ in 0..100 {
+            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
+                    }
+                }
+            }
+            print!(".");
+            io::stdout().flush().unwrap();
+            thread::sleep(Duration::from_secs(1));
+        }
+
+        bail!("Failed to stop safekeeper with pid {}", pid);
     }
 
     fn http_request<U: IntoUrl>(&self, method: Method, url: U) -> RequestBuilder {
         // TODO: authentication
-        //if self.env.auth_type == AuthType::NeonJWT {
+        //if self.env.auth_type == AuthType::ZenithJWT {
         //    builder = builder.bearer_auth(&self.env.safekeeper_auth_token)
         //}
         self.http_client.request(method, url)
@@ -208,4 +294,24 @@ impl SafekeeperNode {
             .error_from_body()?;
         Ok(())
     }
+
+    pub fn timeline_create(
+        &self,
+        tenant_id: ZTenantId,
+        timeline_id: ZTimelineId,
+        peer_ids: Vec<NodeId>,
+    ) -> Result<()> {
+        Ok(self
+            .http_request(
+                Method::POST,
+                format!("{}/tenant/{}/timeline", self.http_base_url, tenant_id),
+            )
+            .json(&TimelineCreateRequest {
+                timeline_id,
+                peer_ids,
+            })
+            .send()?
+            .error_from_body()?
+            .json()?)
+    }
 }

control_plane/src/storage.rs

@@ -0,0 +1,581 @@
+use std::collections::HashMap;
+use std::fs::File;
+use std::io::{BufReader, Write};
+use std::net::TcpStream;
+use std::num::NonZeroU64;
+use std::path::PathBuf;
+use std::process::Command;
+use std::time::Duration;
+use std::{io, result, thread};
+
+use anyhow::{bail, Context};
+use nix::errno::Errno;
+use nix::sys::signal::{kill, Signal};
+use nix::unistd::Pid;
+use pageserver::http::models::{
+    TenantConfigRequest, TenantCreateRequest, TenantInfo, TimelineCreateRequest, TimelineInfo,
+};
+use postgres::{Config, NoTls};
+use reqwest::blocking::{Client, RequestBuilder, Response};
+use reqwest::{IntoUrl, Method};
+use thiserror::Error;
+use utils::{
+    connstring::connection_address,
+    http::error::HttpErrorBody,
+    lsn::Lsn,
+    postgres_backend::AuthType,
+    zid::{ZTenantId, ZTimelineId},
+};
+
+use crate::local_env::LocalEnv;
+use crate::{fill_aws_secrets_vars, fill_rust_env_vars, read_pidfile};
+
+#[derive(Error, Debug)]
+pub enum PageserverHttpError {
+    #[error("Reqwest error: {0}")]
+    Transport(#[from] reqwest::Error),
+
+    #[error("Error: {0}")]
+    Response(String),
+}
+
+impl From<anyhow::Error> for PageserverHttpError {
+    fn from(e: anyhow::Error) -> Self {
+        Self::Response(e.to_string())
+    }
+}
+
+type Result<T> = result::Result<T, PageserverHttpError>;
+
+pub trait ResponseErrorMessageExt: Sized {
+    fn error_from_body(self) -> Result<Self>;
+}
+
+impl ResponseErrorMessageExt for Response {
+    fn error_from_body(self) -> Result<Self> {
+        let status = self.status();
+        if !(status.is_client_error() || status.is_server_error()) {
+            return Ok(self);
+        }
+
+        // reqwest do not export it's error construction utility functions, so lets craft the message ourselves
+        let url = self.url().to_owned();
+        Err(PageserverHttpError::Response(
+            match self.json::<HttpErrorBody>() {
+                Ok(err_body) => format!("Error: {}", err_body.msg),
+                Err(_) => format!("Http error ({}) at {}.", status.as_u16(), url),
+            },
+        ))
+    }
+}
+
+//
+// Control routines for pageserver.
+//
+// Used in CLI and tests.
+//
+#[derive(Debug)]
+pub struct PageServerNode {
+    pub pg_connection_config: Config,
+    pub env: LocalEnv,
+    pub http_client: Client,
+    pub http_base_url: String,
+}
+
+impl PageServerNode {
+    pub fn from_env(env: &LocalEnv) -> PageServerNode {
+        let password = if env.pageserver.auth_type == AuthType::ZenithJWT {
+            &env.pageserver.auth_token
+        } else {
+            ""
+        };
+
+        Self {
+            pg_connection_config: Self::pageserver_connection_config(
+                password,
+                &env.pageserver.listen_pg_addr,
+            ),
+            env: env.clone(),
+            http_client: Client::new(),
+            http_base_url: format!("http://{}/v1", env.pageserver.listen_http_addr),
+        }
+    }
+
+    /// Construct libpq connection string for connecting to the pageserver.
+    fn pageserver_connection_config(password: &str, listen_addr: &str) -> Config {
+        format!("postgresql://no_user:{}@{}/no_db", password, listen_addr)
+            .parse()
+            .unwrap()
+    }
+
+    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);
+        let listen_http_addr_param = format!(
+            "listen_http_addr='{}'",
+            self.env.pageserver.listen_http_addr
+        );
+        let listen_pg_addr_param =
+            format!("listen_pg_addr='{}'", self.env.pageserver.listen_pg_addr);
+        let broker_endpoints_param = format!(
+            "broker_endpoints=[{}]",
+            self.env
+                .etcd_broker
+                .broker_endpoints
+                .iter()
+                .map(|url| format!("'{url}'"))
+                .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}'"));
+        if let Some(broker_etcd_prefix_param) = broker_etcd_prefix_param.as_deref() {
+            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 {
+            args.extend([
+                "-c",
+                "auth_validation_public_key_path='auth_public_key.pem'",
+            ]);
+        }
+
+        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])
+        }
+
+        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 {
+        self.env.pageserver_data_dir()
+    }
+
+    pub fn pid_file(&self) -> PathBuf {
+        self.repo_path().join("pageserver.pid")
+    }
+
+    pub fn start(&self, config_overrides: &[&str]) -> anyhow::Result<()> {
+        print!(
+            "Starting pageserver at '{}' in '{}'",
+            connection_address(&self.pg_connection_config),
+            self.repo_path().display()
+        );
+        io::stdout().flush().unwrap();
+
+        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]);
+        }
+
+        let mut cmd = Command::new(self.env.pageserver_bin()?);
+        let mut filled_cmd = fill_rust_env_vars(cmd.args(&args).arg("--daemonize"));
+        filled_cmd = fill_aws_secrets_vars(filled_cmd);
+
+        if !filled_cmd.status()?.success() {
+            bail!(
+                "Pageserver failed to start. See '{}' for details.",
+                self.repo_path().join("pageserver.log").display()
+            );
+        }
+
+        // It takes a while for the page server to start up. Wait until it is
+        // open for business.
+        const RETRIES: i8 = 15;
+        for retries in 1..RETRIES {
+            match self.check_status() {
+                Ok(_) => {
+                    println!("\nPageserver started");
+                    return Ok(());
+                }
+                Err(err) => {
+                    match err {
+                        PageserverHttpError::Transport(err) => {
+                            if err.is_connect() && retries < 5 {
+                                print!(".");
+                                io::stdout().flush().unwrap();
+                            } else {
+                                if retries == 5 {
+                                    println!() // put a line break after dots for second message
+                                }
+                                println!(
+                                    "Pageserver not responding yet, err {} retrying ({})...",
+                                    err, retries
+                                );
+                            }
+                        }
+                        PageserverHttpError::Response(msg) => {
+                            bail!("pageserver failed to start: {} ", msg)
+                        }
+                    }
+                    thread::sleep(Duration::from_secs(1));
+                }
+            }
+        }
+        bail!("pageserver failed to start in {} seconds", RETRIES);
+    }
+
+    ///
+    /// Stop the server.
+    ///
+    /// If 'immediate' is true, we use SIGQUIT, killing the process immediately.
+    /// Otherwise we use SIGTERM, triggering a clean shutdown
+    ///
+    /// If the server is not running, returns success
+    ///
+    pub fn stop(&self, immediate: bool) -> anyhow::Result<()> {
+        let pid_file = self.pid_file();
+        if !pid_file.exists() {
+            println!("Pageserver is already stopped");
+            return Ok(());
+        }
+        let pid = Pid::from_raw(read_pidfile(&pid_file)?);
+
+        let sig = if immediate {
+            print!("Stopping pageserver immediately..");
+            Signal::SIGQUIT
+        } else {
+            print!("Stopping pageserver gracefully..");
+            Signal::SIGTERM
+        };
+        io::stdout().flush().unwrap();
+        match kill(pid, sig) {
+            Ok(_) => (),
+            Err(Errno::ESRCH) => {
+                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,
+                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 _ in 0..100 {
+            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
+                    }
+                }
+            }
+            print!(".");
+            io::stdout().flush().unwrap();
+            thread::sleep(Duration::from_secs(1));
+        }
+
+        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);
+        client.simple_query(sql).unwrap()
+    }
+
+    pub fn page_server_psql_client(&self) -> result::Result<postgres::Client, postgres::Error> {
+        self.pg_connection_config.connect(NoTls)
+    }
+
+    fn http_request<U: IntoUrl>(&self, method: Method, url: U) -> RequestBuilder {
+        let mut builder = self.http_client.request(method, url);
+        if self.env.pageserver.auth_type == AuthType::ZenithJWT {
+            builder = builder.bearer_auth(&self.env.pageserver.auth_token)
+        }
+        builder
+    }
+
+    pub fn check_status(&self) -> Result<()> {
+        self.http_request(Method::GET, format!("{}/status", self.http_base_url))
+            .send()?
+            .error_from_body()?;
+        Ok(())
+    }
+
+    pub fn tenant_list(&self) -> Result<Vec<TenantInfo>> {
+        Ok(self
+            .http_request(Method::GET, format!("{}/tenant", self.http_base_url))
+            .send()?
+            .error_from_body()?
+            .json()?)
+    }
+
+    pub fn tenant_create(
+        &self,
+        new_tenant_id: Option<ZTenantId>,
+        settings: HashMap<&str, &str>,
+    ) -> 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
+                    .get("checkpoint_distance")
+                    .map(|x| x.parse::<u64>())
+                    .transpose()?,
+                compaction_target_size: settings
+                    .get("compaction_target_size")
+                    .map(|x| x.parse::<u64>())
+                    .transpose()?,
+                compaction_period: settings.get("compaction_period").map(|x| x.to_string()),
+                compaction_threshold: settings
+                    .get("compaction_threshold")
+                    .map(|x| x.parse::<usize>())
+                    .transpose()?,
+                gc_horizon: settings
+                    .get("gc_horizon")
+                    .map(|x| x.parse::<u64>())
+                    .transpose()?,
+                gc_period: settings.get("gc_period").map(|x| x.to_string()),
+                image_creation_threshold: settings
+                    .get("image_creation_threshold")
+                    .map(|x| x.parse::<usize>())
+                    .transpose()?,
+                pitr_interval: settings.get("pitr_interval").map(|x| x.to_string()),
+                walreceiver_connect_timeout: settings
+                    .get("walreceiver_connect_timeout")
+                    .map(|x| x.to_string()),
+                lagging_wal_timeout: settings.get("lagging_wal_timeout").map(|x| x.to_string()),
+                max_lsn_wal_lag: settings
+                    .get("max_lsn_wal_lag")
+                    .map(|x| x.parse::<NonZeroU64>())
+                    .transpose()
+                    .context("Failed to parse 'max_lsn_wal_lag' as non zero integer")?,
+            })
+            .send()?
+            .error_from_body()?
+            .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<()> {
+        self.http_request(Method::PUT, format!("{}/tenant/config", self.http_base_url))
+            .json(&TenantConfigRequest {
+                tenant_id,
+                checkpoint_distance: settings
+                    .get("checkpoint_distance")
+                    .map(|x| x.parse::<u64>())
+                    .transpose()
+                    .context("Failed to parse 'checkpoint_distance' as an integer")?,
+                compaction_target_size: settings
+                    .get("compaction_target_size")
+                    .map(|x| x.parse::<u64>())
+                    .transpose()
+                    .context("Failed to parse 'compaction_target_size' as an integer")?,
+                compaction_period: settings.get("compaction_period").map(|x| x.to_string()),
+                compaction_threshold: settings
+                    .get("compaction_threshold")
+                    .map(|x| x.parse::<usize>())
+                    .transpose()
+                    .context("Failed to parse 'compaction_threshold' as an integer")?,
+                gc_horizon: settings
+                    .get("gc_horizon")
+                    .map(|x| x.parse::<u64>())
+                    .transpose()
+                    .context("Failed to parse 'gc_horizon' as an integer")?,
+                gc_period: settings.get("gc_period").map(|x| x.to_string()),
+                image_creation_threshold: settings
+                    .get("image_creation_threshold")
+                    .map(|x| x.parse::<usize>())
+                    .transpose()
+                    .context("Failed to parse 'image_creation_threshold' as non zero integer")?,
+                pitr_interval: settings.get("pitr_interval").map(|x| x.to_string()),
+                walreceiver_connect_timeout: settings
+                    .get("walreceiver_connect_timeout")
+                    .map(|x| x.to_string()),
+                lagging_wal_timeout: settings.get("lagging_wal_timeout").map(|x| x.to_string()),
+                max_lsn_wal_lag: settings
+                    .get("max_lsn_wal_lag")
+                    .map(|x| x.parse::<NonZeroU64>())
+                    .transpose()
+                    .context("Failed to parse 'max_lsn_wal_lag' as non zero integer")?,
+            })
+            .send()?
+            .error_from_body()?;
+
+        Ok(())
+    }
+
+    pub fn timeline_list(&self, tenant_id: &ZTenantId) -> anyhow::Result<Vec<TimelineInfo>> {
+        let timeline_infos: Vec<TimelineInfo> = self
+            .http_request(
+                Method::GET,
+                format!("{}/tenant/{}/timeline", self.http_base_url, tenant_id),
+            )
+            .send()?
+            .error_from_body()?
+            .json()?;
+
+        Ok(timeline_infos)
+    }
+
+    pub fn timeline_create(
+        &self,
+        tenant_id: ZTenantId,
+        new_timeline_id: Option<ZTimelineId>,
+        ancestor_start_lsn: Option<Lsn>,
+        ancestor_timeline_id: Option<ZTimelineId>,
+    ) -> 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) `pg_basebackup -F tar`, or
+    /// b) The `fullbackup` pageserver endpoint
+    ///
+    /// # Arguments
+    /// * `tenant_id` - tenant to import into. Created if not exists
+    /// * `timeline_id` - id to assign to imported timeline
+    /// * `base` - (start lsn of basebackup, path to `base.tar` file)
+    /// * `pg_wal` - if there's any wal to import: (end lsn, path to `pg_wal.tar`)
+    pub fn timeline_import(
+        &self,
+        tenant_id: ZTenantId,
+        timeline_id: ZTimelineId,
+        base: (Lsn, PathBuf),
+        pg_wal: Option<(Lsn, PathBuf)>,
+    ) -> anyhow::Result<()> {
+        let mut client = self.pg_connection_config.connect(NoTls).unwrap();
+
+        // Init base reader
+        let (start_lsn, base_tarfile_path) = base;
+        let base_tarfile = File::open(base_tarfile_path)?;
+        let mut base_reader = BufReader::new(base_tarfile);
+
+        // Init wal reader if necessary
+        let (end_lsn, wal_reader) = if let Some((end_lsn, wal_tarfile_path)) = pg_wal {
+            let wal_tarfile = File::open(wal_tarfile_path)?;
+            let wal_reader = BufReader::new(wal_tarfile);
+            (end_lsn, Some(wal_reader))
+        } else {
+            (start_lsn, None)
+        };
+
+        // Import base
+        let import_cmd =
+            format!("import basebackup {tenant_id} {timeline_id} {start_lsn} {end_lsn}");
+        let mut writer = client.copy_in(&import_cmd)?;
+        io::copy(&mut base_reader, &mut writer)?;
+        writer.finish()?;
+
+        // Import wal if necessary
+        if let Some(mut wal_reader) = wal_reader {
+            let import_cmd = format!("import wal {tenant_id} {timeline_id} {start_lsn} {end_lsn}");
+            let mut writer = client.copy_in(&import_cmd)?;
+            io::copy(&mut wal_reader, &mut writer)?;
+            writer.finish()?;
+        }
+
+        Ok(())
+    }
+}

docker-compose/compute_wrapper/Dockerfile

@@ -1,13 +0,0 @@
-ARG REPOSITORY=369495373322.dkr.ecr.eu-central-1.amazonaws.com
-ARG COMPUTE_IMAGE=compute-node-v14
-ARG TAG=latest
-
-FROM $REPOSITORY/${COMPUTE_IMAGE}:$TAG
-
-USER root
-RUN apt-get update &&       \
-    apt-get install -y curl \
-                       jq   \
-                       netcat
-
-USER postgres

docker-compose/compute_wrapper/shell/compute.sh

@@ -1,48 +0,0 @@
-#!/bin/bash
-set -eux
-
-PG_VERSION=${PG_VERSION:-14}
-
-SPEC_FILE_ORG=/var/db/postgres/specs/spec.json
-SPEC_FILE=/tmp/spec.json
-
-echo "Waiting pageserver become ready."
-while ! nc -z pageserver 6400; do
-     sleep 1;
-done
-echo "Page server is ready."
-
-echo "Create a tenant and timeline"
-PARAMS=(
-     -sb 
-     -X POST
-     -H "Content-Type: application/json"
-     -d "{}"
-     http://pageserver:9898/v1/tenant/
-)
-tenant_id=$(curl "${PARAMS[@]}" | sed 's/"//g')
-
-PARAMS=(
-     -sb 
-     -X POST
-     -H "Content-Type: application/json"
-     -d "{\"tenant_id\":\"${tenant_id}\", \"pg_version\": ${PG_VERSION}}"
-     "http://pageserver:9898/v1/tenant/${tenant_id}/timeline/"
-)
-result=$(curl "${PARAMS[@]}")
-echo $result | jq .
-
-echo "Overwrite tenant id and timeline id in spec file"
-tenant_id=$(echo ${result} | jq -r .tenant_id)
-timeline_id=$(echo ${result} | jq -r .timeline_id)
-
-sed "s/TENANT_ID/${tenant_id}/" ${SPEC_FILE_ORG} > ${SPEC_FILE}
-sed -i "s/TIMELINE_ID/${timeline_id}/" ${SPEC_FILE}
-
-cat ${SPEC_FILE}
-
-echo "Start compute node"
-/usr/local/bin/compute_ctl --pgdata /var/db/postgres/compute \
-     -C "postgresql://cloud_admin@localhost:55433/postgres"  \
-     -b /usr/local/bin/postgres                              \
-     -S ${SPEC_FILE}

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

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

docker-compose/docker-compose.yml

@@ -1,209 +0,0 @@
-version: '3'
-
-services:
-  etcd:
-    restart: always
-    image: quay.io/coreos/etcd:v3.5.4
-    ports:
-      - 2379:2379
-      - 2380:2380
-    environment:
-      # This signifficantly speeds up etcd and we anyway don't data persistency there.
-      ETCD_UNSAFE_NO_FSYNC: "1"
-    command:
-      - "etcd"
-      - "--auto-compaction-mode=revision"
-      - "--auto-compaction-retention=1"
-      - "--name=etcd-cluster"
-      - "--initial-cluster-state=new"
-      - "--initial-cluster-token=etcd-cluster-1"
-      - "--initial-cluster=etcd-cluster=http://etcd:2380"
-      - "--initial-advertise-peer-urls=http://etcd:2380"
-      - "--advertise-client-urls=http://etcd:2379"
-      - "--listen-client-urls=http://0.0.0.0:2379"
-      - "--listen-peer-urls=http://0.0.0.0:2380"
-      - "--quota-backend-bytes=134217728" # 128 MB
-
-  minio:
-    restart: always
-    image: quay.io/minio/minio:RELEASE.2022-10-20T00-55-09Z
-    ports:
-      - 9000:9000
-      - 9001:9001
-    environment:
-      - MINIO_ROOT_USER=minio
-      - MINIO_ROOT_PASSWORD=password
-    command: server /data --address :9000 --console-address ":9001"
-
-  minio_create_buckets:
-    image: minio/mc
-    environment:
-      - MINIO_ROOT_USER=minio
-      - MINIO_ROOT_PASSWORD=password
-    entrypoint:
-      - "/bin/sh"
-      - "-c"
-    command:
-      - "until (/usr/bin/mc alias set minio http://minio:9000 $$MINIO_ROOT_USER $$MINIO_ROOT_PASSWORD) do
-             echo 'Waiting to start minio...' && sleep 1;
-         done;
-         /usr/bin/mc mb minio/neon --region=eu-north-1;
-         exit 0;"
-    depends_on:
-      - minio
-
-  pageserver:
-    restart: always
-    image: ${REPOSITORY:-neondatabase}/neon:${TAG:-latest}
-    environment:
-      - BROKER_ENDPOINT='http://etcd:2379'
-      - AWS_ACCESS_KEY_ID=minio
-      - AWS_SECRET_ACCESS_KEY=password
-      #- RUST_BACKTRACE=1
-    ports:
-       #- 6400:6400  # pg protocol handler
-       - 9898:9898 # http endpoints
-    entrypoint:
-      - "/bin/sh"
-      - "-c"
-    command:
-      - "/usr/local/bin/pageserver -D /data/.neon/
-                                   -c \"broker_endpoints=[$$BROKER_ENDPOINT]\"
-                                   -c \"listen_pg_addr='0.0.0.0:6400'\"
-                                   -c \"listen_http_addr='0.0.0.0:9898'\"
-                                   -c \"remote_storage={endpoint='http://minio:9000',
-                                                        bucket_name='neon',
-                                                        bucket_region='eu-north-1',
-                                                        prefix_in_bucket='/pageserver/'}\""
-    depends_on:
-      - etcd
-      - minio_create_buckets
-
-  safekeeper1:
-    restart: always
-    image: ${REPOSITORY:-neondatabase}/neon:${TAG:-latest}
-    environment:
-      - SAFEKEEPER_ADVERTISE_URL=safekeeper1:5454
-      - SAFEKEEPER_ID=1
-      - BROKER_ENDPOINT=http://etcd:2379
-      - AWS_ACCESS_KEY_ID=minio
-      - AWS_SECRET_ACCESS_KEY=password
-      #- RUST_BACKTRACE=1
-    ports:
-      #- 5454:5454 # pg protocol handler
-      - 7676:7676 # http endpoints
-    entrypoint:
-      - "/bin/sh"
-      - "-c"
-    command:
-      - "safekeeper --listen-pg=$$SAFEKEEPER_ADVERTISE_URL
-                    --listen-http='0.0.0.0:7676'
-                    --id=$$SAFEKEEPER_ID
-                    --broker-endpoints=$$BROKER_ENDPOINT
-                    -D /data
-                    --remote-storage=\"{endpoint='http://minio:9000',
-                                        bucket_name='neon',
-                                        bucket_region='eu-north-1',
-                                        prefix_in_bucket='/safekeeper/'}\""
-    depends_on:
-      - etcd
-      - minio_create_buckets
-
-  safekeeper2:
-    restart: always
-    image: ${REPOSITORY:-neondatabase}/neon:${TAG:-latest}
-    environment:
-      - SAFEKEEPER_ADVERTISE_URL=safekeeper2:5454
-      - SAFEKEEPER_ID=2
-      - BROKER_ENDPOINT=http://etcd:2379
-      - AWS_ACCESS_KEY_ID=minio
-      - AWS_SECRET_ACCESS_KEY=password
-      #- RUST_BACKTRACE=1
-    ports:
-      #- 5454:5454 # pg protocol handler
-      - 7677:7676 # http endpoints
-    entrypoint:
-      - "/bin/sh"
-      - "-c"
-    command:
-      - "safekeeper --listen-pg=$$SAFEKEEPER_ADVERTISE_URL
-                    --listen-http='0.0.0.0:7676'
-                    --id=$$SAFEKEEPER_ID
-                    --broker-endpoints=$$BROKER_ENDPOINT
-                    -D /data
-                    --remote-storage=\"{endpoint='http://minio:9000',
-                                        bucket_name='neon',
-                                        bucket_region='eu-north-1',
-                                        prefix_in_bucket='/safekeeper/'}\""
-    depends_on:
-      - etcd
-      - minio_create_buckets
-
-  safekeeper3:
-    restart: always
-    image: ${REPOSITORY:-neondatabase}/neon:${TAG:-latest}
-    environment:
-      - SAFEKEEPER_ADVERTISE_URL=safekeeper3:5454
-      - SAFEKEEPER_ID=3
-      - BROKER_ENDPOINT=http://etcd:2379
-      - AWS_ACCESS_KEY_ID=minio
-      - AWS_SECRET_ACCESS_KEY=password
-      #- RUST_BACKTRACE=1
-    ports:
-      #- 5454:5454 # pg protocol handler
-      - 7678:7676 # http endpoints
-    entrypoint:
-      - "/bin/sh"
-      - "-c"
-    command:
-      - "safekeeper --listen-pg=$$SAFEKEEPER_ADVERTISE_URL
-                    --listen-http='0.0.0.0:7676'
-                    --id=$$SAFEKEEPER_ID
-                    --broker-endpoints=$$BROKER_ENDPOINT
-                    -D /data
-                    --remote-storage=\"{endpoint='http://minio:9000',
-                                        bucket_name='neon',
-                                        bucket_region='eu-north-1',
-                                        prefix_in_bucket='/safekeeper/'}\""
-    depends_on:
-      - etcd
-      - minio_create_buckets
-
-  compute:
-    restart: always
-    build:
-      context: ./compute_wrapper/
-      args:
-        - COMPUTE_IMAGE=compute-node-v${PG_VERSION:-14}
-        - TAG=${TAG:-latest}
-        - http_proxy=$http_proxy
-        - https_proxy=$https_proxy
-    environment:
-      - PG_VERSION=${PG_VERSION:-14}
-      #- RUST_BACKTRACE=1
-    # Mount the test files directly, for faster editing cycle.
-    volumes:
-      - ./compute_wrapper/var/db/postgres/specs/:/var/db/postgres/specs/
-      - ./compute_wrapper/shell/:/shell/
-    ports:
-      - 55433:55433 # pg protocol handler
-      - 3080:3080 # http endpoints
-    entrypoint:
-      - "/shell/compute.sh"
-    depends_on:
-      - safekeeper1
-      - safekeeper2
-      - safekeeper3
-      - pageserver
-
-  compute_is_ready:
-    image: postgres:latest
-    entrypoint:
-      - "/bin/bash"
-      - "-c"
-    command:
-      - "until pg_isready -h compute -p 55433 ; do
-            echo 'Waiting to start compute...' && sleep 1;
-         done"
-    depends_on:
-      - compute

docker-compose/docker_compose_test.sh

@@ -1,60 +0,0 @@
-#!/bin/bash
-
-# A basic test to ensure Docker images are built correctly.
-# Build a wrapper around the compute, start all services and runs a simple SQL query.
-# Repeats the process for all currenly supported Postgres versions.
-
-# Implicitly accepts `REPOSITORY` and `TAG` env vars that are passed into the compose file
-# Their defaults point at DockerHub `neondatabase/neon:latest` image.`,
-# to verify custom image builds (e.g pre-published ones).
-
-# XXX: Current does not work on M1 macs due to x86_64 Docker images compiled only, and no seccomp support in M1 Docker emulation layer.
-
-set -eux -o pipefail
-
-SCRIPT_DIR="$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )"
-COMPOSE_FILE=$SCRIPT_DIR/docker-compose.yml
-
-COMPUTE_CONTAINER_NAME=docker-compose-compute-1
-SQL="CREATE TABLE t(key int primary key, value text); insert into t values(1,1); select * from t;"
-PSQL_OPTION="-h localhost -U cloud_admin -p 55433 -c '$SQL' postgres"
-
-cleanup() {
-    echo "show container information"
-    docker ps
-    docker compose -f $COMPOSE_FILE logs
-    echo "stop containers..."
-    docker compose -f $COMPOSE_FILE down
-}
-
-echo "clean up containers if exists"
-cleanup
-
-for pg_version in 14 15; do
-    echo "start containers (pg_version=$pg_version)."
-    PG_VERSION=$pg_version docker compose -f $COMPOSE_FILE up --build -d
-
-    echo "wait until the compute is ready. timeout after 60s. "
-    cnt=0
-    while sleep 1; do
-        # check timeout
-        cnt=`expr $cnt + 1`
-        if [ $cnt -gt 60 ]; then
-            echo "timeout before the compute is ready."
-            cleanup
-            exit 1
-        fi
-
-        # check if the compute is ready
-        set +o pipefail
-        result=`docker compose -f $COMPOSE_FILE logs "compute_is_ready" | grep "accepting connections" | wc -l`
-        set -o pipefail
-        if [ $result -eq 1 ]; then
-            echo "OK. The compute is ready to connect."
-            echo "execute simple queries."
-            docker exec $COMPUTE_CONTAINER_NAME /bin/bash -c "psql $PSQL_OPTION"
-            cleanup
-            break
-        fi
-    done
-done

docker-entrypoint.sh

@@ -0,0 +1,20 @@
+#!/bin/sh
+set -eux
+
+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
+
+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=10" $broker_endpoints_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

docs/SUMMARY.md

@@ -52,8 +52,10 @@
 - [multitenancy.md](./multitenancy.md) — how multitenancy is organized in the pageserver and Zenith CLI.
 - [settings.md](./settings.md)
 #FIXME: move these under sourcetree.md
+#- [pageserver/README.md](/pageserver/README.md)
 #- [postgres_ffi/README.md](/libs/postgres_ffi/README.md)
 #- [test_runner/README.md](/test_runner/README.md)
+#- [safekeeper/README.md](/safekeeper/README.md)
 
 
 # RFCs
@@ -79,7 +81,4 @@
 - [014-storage-lsm](rfcs/014-storage-lsm.md)
 - [015-storage-messaging](rfcs/015-storage-messaging.md)
 - [016-connection-routing](rfcs/016-connection-routing.md)
-- [017-timeline-data-management](rfcs/017-timeline-data-management.md)
-- [018-storage-messaging-2](rfcs/018-storage-messaging-2.md)
-- [019-tenant-timeline-lifecycles](rfcs/019-tenant-timeline-lifecycles.md)
 - [cluster-size-limits](rfcs/cluster-size-limits.md)

docs/authentication.md

@@ -2,14 +2,14 @@
 
 ### Overview
 
-Current state of authentication includes usage of JWT tokens in communication between compute and pageserver and between CLI and pageserver. JWT token is signed using RSA keys. CLI generates a key pair during call to `neon_local init`. Using following openssl commands:
+Current state of authentication includes usage of JWT tokens in communication between compute and pageserver and between CLI and pageserver. JWT token is signed using RSA keys. CLI generates a key pair during call to `zenith init`. Using following openssl commands:
 
 ```bash
 openssl genrsa -out private_key.pem 2048
 openssl rsa -in private_key.pem -pubout -outform PEM -out public_key.pem
 ```
 
-CLI also generates signed token and saves it in the config for later access to pageserver. Now authentication is optional. Pageserver has two variables in config: `auth_validation_public_key_path` and `auth_type`, so when auth type present and set to `NeonJWT` pageserver will require authentication for connections. Actual JWT is passed in password field of connection string. There is a caveat for psql, it silently truncates passwords to 100 symbols, so to correctly pass JWT via psql you have to either use PGPASSWORD environment variable, or store password in psql config file.
+CLI also generates signed token and saves it in the config for later access to pageserver. Now authentication is optional. Pageserver has two variables in config: `auth_validation_public_key_path` and `auth_type`, so when auth type present and set to `ZenithJWT` pageserver will require authentication for connections. Actual JWT is passed in password field of connection string. There is a caveat for psql, it silently truncates passwords to 100 symbols, so to correctly pass JWT via psql you have to either use PGPASSWORD environment variable, or store password in psql config file.
 
 Currently there is no authentication between compute and safekeepers, because this communication layer is under heavy refactoring. After this refactoring support for authentication will be added there too. Now safekeeper supports "hardcoded" token passed via environment variable to be able to use callmemaybe command in pageserver.
 

docs/broker.md

@@ -1,25 +0,0 @@
-# Neon broker
-
-Neon storage broker targets two issues:
-- Allowing safekeepers and pageservers learn which nodes also hold their
-  timelines, and timeline statuses there.
-- Avoiding O(n^2) connections between storage nodes while doing so.
-
-This is used
-- By pageservers to determine the most advanced and alive safekeeper to pull WAL from.
-- By safekeepers to synchronize on the timeline: advance
-  `remote_consistent_lsn`, `backup_lsn`, choose who offloads WAL to s3.
-
-Technically, it is a simple stateless pub-sub message broker based on tonic
-(grpc) making multiplexing easy. Since it is stateless, fault tolerance can be
-provided by k8s; there is no built in replication support, though it is not hard
-to add.
-
-Currently, the only message is `SafekeeperTimelineInfo`. Each safekeeper, for
-each active timeline, once in a while pushes timeline status to the broker.
-Other nodes subscribe and receive this info, using it per above.
-
-grpcurl can be used to check which values are currently being pushed:
-```
-grpcurl -proto broker/proto/broker.proto -d '{"all":{}}' -plaintext localhost:50051 neon_broker.NeonBroker/SubscribeSafekeeperInfo
-```

docs/core_changes.md

@@ -148,6 +148,31 @@ relcache? (I think we do cache nblocks in relcache already, check why that's not
 Neon)
 
 
+## Misc change in vacuumlazy.c
+
+```
+index 8aab6e324e..c684c4fbee 100644
+--- a/src/backend/access/heap/vacuumlazy.c
++++ b/src/backend/access/heap/vacuumlazy.c
+@@ -1487,7 +1487,10 @@ lazy_scan_heap(LVRelState *vacrel, VacuumParams *params, bool aggressive)
+                else if (all_visible_according_to_vm && !PageIsAllVisible(page)
+                                 && VM_ALL_VISIBLE(vacrel->rel, blkno, &vmbuffer))
+                {
+-                       elog(WARNING, "page is not marked all-visible but visibility map bit is set in relation \"%s\" page %u",
++                       /* ZENITH-XXX: all visible hint is not wal-logged
++                        * FIXME: Replay visibilitymap changes in pageserver
++                        */
++                       elog(DEBUG1, "page is not marked all-visible but visibility map bit is set in relation \"%s\" page %u",
+                                 vacrel->relname, blkno);
+                        visibilitymap_clear(vacrel->rel, blkno, vmbuffer,
+                                                                VISIBILITYMAP_VALID_BITS);
+```
+
+
+Is this still needed? If that WARNING happens, it looks like potential corruption that we should
+fix!
+
+
 ## Use buffer manager when extending VM or FSM
 
 ```

docs/docker.md

@@ -18,67 +18,3 @@ We build all images after a successful `release` tests run and push automaticall
 1. `neondatabase/compute-tools` and `neondatabase/compute-node`
 
 2. `neondatabase/neon`
-
-## Docker Compose example
-
-You can see a [docker compose](https://docs.docker.com/compose/) example to create a neon cluster in [/docker-compose/docker-compose.yml](/docker-compose/docker-compose.yml). It creates the following conatainers.
-
-- etcd x 1
-- pageserver x 1
-- safekeeper x 3
-- compute x 1
-- MinIO x 1        # This is Amazon S3 compatible object storage
-
-### How to use
-
-1. create containers
-
-You can specify version of neon cluster using following environment values.
-- PG_VERSION: postgres version for compute (default is 14)
-- TAG: the tag version of [docker image](https://registry.hub.docker.com/r/neondatabase/neon/tags) (default is latest), which is tagged in [CI test](/.github/workflows/build_and_test.yml)
-```
-$ cd docker-compose/docker-compose.yml
-$ docker-compose down   # remove the conainers if exists
-$ PG_VERSION=15 TAG=2221 docker-compose up --build -d  # You can specify the postgres and image version
-Creating network "dockercompose_default" with the default driver
-Creating dockercompose_etcd3_1 ...
-(...omit...)
-```
-
-2. connect compute node
-```
-$ echo "localhost:55433:postgres:cloud_admin:cloud_admin" >> ~/.pgpass
-$ psql -h localhost -p 55433 -U cloud_admin
-postgres=# CREATE TABLE t(key int primary key, value text);
-CREATE TABLE
-postgres=# insert into t values(1,1);
-INSERT 0 1
-postgres=# select * from t;
- key | value
------+-------
-   1 | 1
-(1 row)
-```
-
-3. If you want to see the log, you can use `docker-compose logs` command.
-```
-# check the container name you want to see
-$ docker ps
-CONTAINER ID   IMAGE                                              COMMAND                  CREATED         STATUS         PORTS                                                                                                                                  NAMES
-d6968a5ae912   dockercompose_compute                              "/shell/compute.sh"      5 minutes ago   Up 5 minutes   0.0.0.0:3080->3080/tcp, 0.0.0.0:55433->55433/tcp                                                                                       dockercompose_compute_1
-(...omit...)
-
-$ docker logs -f dockercompose_compute_1
-2022-10-21 06:15:48.757 GMT [56] LOG:  connection authorized: user=cloud_admin database=postgres application_name=psql
-2022-10-21 06:17:00.307 GMT [56] LOG:  [NEON_SMGR] libpagestore: connected to 'host=pageserver port=6400'
-(...omit...)
-```
-
-4. If you want to see durable data in MinIO which is s3 compatible storage
-
-Access http://localhost:9001 and sign in.
-
-- Username: `minio`
-- Password: `password`
-
-You can see durable pages and WAL data in `neon` bucket.

docs/glossary.md

@@ -75,7 +75,7 @@ layer's Segment and range of LSNs.
 There are two kinds of layers, in-memory and on-disk layers. In-memory
 layers are used to ingest incoming WAL, and provide fast access
 to the recent page versions. On-disk layers are stored as files on disk, and
-are immutable. See [pageserver-storage.md](./pageserver-storage.md) for more.
+are immutable. See pageserver/src/layered_repository/README.md for more.
 
 ### Layer file (on-disk layer)
 
@@ -92,7 +92,6 @@ The layer map tracks what layers exist in a timeline.
 ### Layered repository
 
 Neon repository implementation that keeps data in layers.
-
 ### LSN
 
 The Log Sequence Number (LSN) is a unique identifier of the WAL record[] in the WAL log.
@@ -112,7 +111,7 @@ PostgreSQL LSNs and functions to monitor them:
 * `pg_last_wal_replay_lsn ()` - Returns the last write-ahead log location that has been replayed during recovery. If recovery is still in progress this will increase monotonically.
 [source PostgreSQL documentation](https://www.postgresql.org/docs/devel/functions-admin.html):
 
-Neon safekeeper LSNs. See [safekeeper protocol section](safekeeper-protocol.md) for more information.
+Neon safekeeper LSNs. For more check [safekeeper/README_PROTO.md](/safekeeper/README_PROTO.md)
 * `CommitLSN`: position in WAL confirmed by quorum safekeepers.
 * `RestartLSN`: position in WAL confirmed by all safekeepers.
 * `FlushLSN`: part of WAL persisted to the disk by safekeeper.
@@ -126,26 +125,6 @@ TODO: use this name consistently in remote storage code. Now `disk_consistent_ls
 * `ancestor_lsn` - LSN of the branch point (the LSN at which this branch was created)
 
 TODO: add table that describes mapping between PostgreSQL (compute), safekeeper and pageserver LSNs.
-
-### Logical size
-
-The pageserver tracks the "logical size" of a timeline. It is the
-total size of all relations in all Postgres databases on the
-timeline. It includes all user and system tables, including their FSM
-and VM forks. But it does not include SLRUs, twophase files or any
-other such data or metadata that lives outside relations.
-
-The logical size is calculated by the pageserver, and is sent to
-PostgreSQL via feedback messages to the safekeepers. PostgreSQL uses
-the logical size to enforce the size limit in the free tier. The
-logical size is also shown to users in the web console.
-
-The logical size is not affected by branches or the physical layout of
-layer files in the pageserver. If you have a database with 1 GB
-logical size and you create a branch of it, both branches will have 1
-GB logical size, even though the branch is copy-on-write and won't
-consume any extra physical disk space until you make changes to it.
-
 ### Page (block)
 
 The basic structure used to store relation data. All pages are of the same size.

docs/multitenancy.md

@@ -2,26 +2,26 @@
 
 ### Overview
 
-Neon supports multitenancy. One pageserver can serve multiple tenants at once. Tenants can be managed via neon_local CLI. During page server setup tenant can be created using ```neon_local init --create-tenant``` Also tenants can be added into the system on the fly without pageserver restart. This can be done using the following cli command: ```neon_local tenant create``` Tenants use random identifiers which can be represented as a 32 symbols hexadecimal string. So neon_local tenant create accepts desired tenant id as an optional argument. The concept of timelines/branches is working independently per tenant.
+Zenith supports multitenancy. One pageserver can serve multiple tenants at once. Tenants can be managed via zenith CLI. During page server setup tenant can be created using ```zenith init --create-tenant``` Also tenants can be added into the system on the fly without pageserver restart. This can be done using the following cli command: ```zenith tenant create``` Tenants use random identifiers which can be represented as a 32 symbols hexadecimal string. So zenith tenant create accepts desired tenant id as an optional argument. The concept of timelines/branches is working independently per tenant.
 
 ### Tenants in other commands
 
-By default during `neon_local init` new tenant is created on the pageserver. Newly created tenant's id is saved to cli config, so other commands can use it automatically if no direct argument `--tenant_id=<tenant_id>` is provided. So generally tenant_id more frequently appears in internal pageserver interface. Its commands take tenant_id argument to distinguish to which tenant operation should be applied. CLI support creation of new tenants.
+By default during `zenith init` new tenant is created on the pageserver. Newly created tenant's id is saved to cli config, so other commands can use it automatically if no direct argument `--tenantid=<tenantid>` is provided. So generally tenantid more frequently appears in internal pageserver interface. Its commands take tenantid argument to distinguish to which tenant operation should be applied. CLI support creation of new tenants.
 
 Examples for cli:
 
 ```sh
-neon_local tenant list
+zenith tenant list
 
-neon_local tenant create // generates new id
+zenith tenant create // generates new id
 
-neon_local tenant create ee6016ec31116c1b7c33dfdfca38892f
+zenith tenant create ee6016ec31116c1b7c33dfdfca38892f
 
-neon_local pg create main // default tenant from neon init
+zenith pg create main // default tenant from zenith init
 
-neon_local pg create main --tenant_id=ee6016ec31116c1b7c33dfdfca38892f
+zenith pg create main --tenantid=ee6016ec31116c1b7c33dfdfca38892f
 
-neon_local branch --tenant_id=ee6016ec31116c1b7c33dfdfca38892f
+zenith branch --tenantid=ee6016ec31116c1b7c33dfdfca38892f
 ```
 
 ### Data layout
@@ -56,4 +56,4 @@ Tenant id is passed to postgres via GUC the same way as the timeline. Tenant id
 
 ### Safety
 
-For now particular tenant can only appear on a particular pageserver. Set of safekeepers are also pinned to particular (tenant_id, timeline_id) pair so there can only be one writer for particular (tenant_id, timeline_id).
+For now particular tenant can only appear on a particular pageserver. Set of safekeepers are also pinned to particular (tenantid, timeline) pair so there can only be one writer for particular (tenantid, timeline).