Dead-end websocket experiments

SELECT 1.0 is still not working

.config/hakari.toml

@@ -4,7 +4,7 @@
 hakari-package = "workspace_hack"
 
 # Format for `workspace-hack = ...` lines in other Cargo.tomls. Requires cargo-hakari 0.9.8 or above.
-dep-format-version = "2"
+dep-format-version = "4"
 
 # Setting workspace.resolver = "2" in the root Cargo.toml is HIGHLY recommended.
 # Hakari works much better with the new feature resolver.

.dockerignore

@@ -14,8 +14,11 @@
 !pgxn/
 !proxy/
 !safekeeper/
+!storage_broker/
+!trace/
 !vendor/postgres-v14/
 !vendor/postgres-v15/
 !workspace_hack/
 !neon_local/
 !scripts/ninstall.sh
+!vm-cgconfig.conf

.github/PULL_REQUEST_TEMPLATE/release-pr.md

@@ -10,11 +10,12 @@
 <!-- List everything that should be done **before** release, any issues / setting changes / etc -->
 
 ### Checklist after release
+- [ ] Make sure instructions from PRs included in this release and labeled `manual_release_instructions` are executed (either by you or by people who wrote them).
 - [ ] 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 [cloud SLO dashboard](https://neonprod.grafana.net/d/_oWcBMJ7k/cloud-slos?orgId=1)
-- [ ] Check [compute startup metrics dashboard](https://observer.zenith.tech/d/5OkYJEmVz/compute-startup-time)
+- [ ] Check [compute startup metrics dashboard](https://neonprod.grafana.net/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

@@ -15,25 +15,47 @@ outputs:
   report-url:
     description: 'Allure report URL'
     value: ${{ steps.generate-report.outputs.report-url }}
+  report-json-url:
+    description: 'Allure report JSON URL'
+    value: ${{ steps.generate-report.outputs.report-json-url }}
 
 runs:
   using: "composite"
+
   steps:
+    # We're using some of env variables quite offen, so let's set them once.
+    #
+    # It would be nice to have them set in common runs.env[0] section, but it doesn't work[1]
+    #
+    # - [0] https://docs.github.com/en/actions/creating-actions/metadata-syntax-for-github-actions#runsenv
+    # - [1] https://github.com/neondatabase/neon/pull/3907#discussion_r1154703456
+    #
+    - name: Set common environment variables
+      shell: bash -euxo pipefail {0}
+      run: |
+        echo "BUILD_TYPE=${BUILD_TYPE}"   >> $GITHUB_ENV
+        echo "BUCKET=${BUCKET}"           >> $GITHUB_ENV
+        echo "TEST_OUTPUT=${TEST_OUTPUT}" >> $GITHUB_ENV
+      env:
+        BUILD_TYPE: ${{ inputs.build_type }}
+        BUCKET: neon-github-public-dev
+        TEST_OUTPUT: /tmp/test_output
+
     - name: Validate input parameters
       shell: bash -euxo pipefail {0}
       run: |
         if [ "${{ inputs.action }}" != "store" ] && [ "${{ inputs.action }}" != "generate" ]; then
-          echo 2>&1 "Unknown inputs.action type '${{ inputs.action }}'; allowed 'generate' or 'store' only"
+          echo >&2 "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"
+          echo >&2 "inputs.test_selection must be set for 'store' action"
           exit 2
         fi
 
-    - name: Calculate key
+    - name: Calculate variables
-      id: calculate-key
+      id: calculate-vars
       shell: bash -euxo pipefail {0}
       run: |
         # TODO: for manually triggered workflows (via workflow_dispatch) we need to have a separate key
@@ -41,14 +63,22 @@ runs:
         pr_number=$(jq --raw-output .pull_request.number "$GITHUB_EVENT_PATH" || true)
         if [ "${pr_number}" != "null" ]; then
           key=pr-${pr_number}
-        elif [ "${GITHUB_REF}" = "refs/heads/main" ]; then
+        elif [ "${GITHUB_REF_NAME}" = "main" ]; then
           # Shortcut for a special branch
           key=main
+        elif [ "${GITHUB_REF_NAME}" = "release" ]; then
+          # Shortcut for a special branch
+          key=release
         else
-          key=branch-$(echo ${GITHUB_REF#refs/heads/} | tr -c "[:alnum:]._-" "-")
+          key=branch-$(printf "${GITHUB_REF_NAME}" | tr -c "[:alnum:]._-" "-")
         fi
         echo "KEY=${key}" >> $GITHUB_OUTPUT
 
+        # Sanitize test selection to remove `/` and any other special characters
+        # Use printf instead of echo to avoid having `\n` at the end of the string
+        test_selection=$(printf "${{ inputs.test_selection }}" | tr -c "[:alnum:]._-" "-" )
+        echo "TEST_SELECTION=${test_selection}" >> $GITHUB_OUTPUT
+
     - uses: actions/setup-java@v3
       if: ${{ inputs.action == 'generate' }}
       with:
@@ -68,16 +98,15 @@ runs:
           rm -f ${ALLURE_ZIP}
         fi
       env:
-        ALLURE_VERSION: 2.19.0
+        ALLURE_VERSION: 2.21.0
-        ALLURE_ZIP_MD5: ced21401a1a8b9dfb68cee9e4c210464
+        ALLURE_ZIP_MD5: c8db4dd8e2a7882583d569ed2c82879c
 
     - name: Upload Allure results
       if: ${{ inputs.action == 'store' }}
       env:
-        REPORT_PREFIX: reports/${{ steps.calculate-key.outputs.KEY }}/${{ inputs.build_type }}
+        REPORT_PREFIX: reports/${{ steps.calculate-vars.outputs.KEY }}/${{ inputs.build_type }}
-        RAW_PREFIX: reports-raw/${{ steps.calculate-key.outputs.KEY }}/${{ inputs.build_type }}
+        RAW_PREFIX: reports-raw/${{ steps.calculate-vars.outputs.KEY }}/${{ inputs.build_type }}
-        TEST_OUTPUT: /tmp/test_output
+        TEST_SELECTION: ${{ steps.calculate-vars.outputs.TEST_SELECTION }}
-        BUCKET: neon-github-public-dev
       shell: bash -euxo pipefail {0}
       run: |
         # Add metadata
@@ -95,10 +124,10 @@ runs:
         EOF
         cat <<EOF > $TEST_OUTPUT/allure/results/environment.properties
           TEST_SELECTION=${{ inputs.test_selection }}
-          BUILD_TYPE=${{ inputs.build_type }}
+          BUILD_TYPE=${BUILD_TYPE}
         EOF
 
-        ARCHIVE="${GITHUB_RUN_ID}-${{ inputs.test_selection }}-${GITHUB_RUN_ATTEMPT}-$(date +%s).tar.zst"
+        ARCHIVE="${GITHUB_RUN_ID}-${TEST_SELECTION}-${GITHUB_RUN_ATTEMPT}-$(date +%s).tar.zst"
         ZSTD_NBTHREADS=0
 
         tar -C ${TEST_OUTPUT}/allure/results -cf ${ARCHIVE} --zstd .
@@ -109,8 +138,8 @@ runs:
       if: ${{ inputs.action == 'generate' }}
       shell: bash -euxo pipefail {0}
       env:
-        LOCK_FILE: reports/${{ steps.calculate-key.outputs.KEY }}/lock.txt
+        LOCK_FILE: reports/${{ steps.calculate-vars.outputs.KEY }}/lock.txt
-        BUCKET: neon-github-public-dev
+        TEST_SELECTION: ${{ steps.calculate-vars.outputs.TEST_SELECTION }}
       run: |
         LOCK_TIMEOUT=300 # seconds
 
@@ -123,12 +152,12 @@ runs:
             fi
             sleep 1
           done
-          echo "${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}-${{ inputs.test_selection }}" > lock.txt
+          echo "${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}-${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
+          if [ "$(cat lock.txt)" = "${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}-${TEST_SELECTION}" ]; then
             break
           fi
         done
@@ -137,10 +166,8 @@ runs:
       if: ${{ inputs.action == 'generate' }}
       id: generate-report
       env:
-        REPORT_PREFIX: reports/${{ steps.calculate-key.outputs.KEY }}/${{ inputs.build_type }}
+        REPORT_PREFIX: reports/${{ steps.calculate-vars.outputs.KEY }}/${{ inputs.build_type }}
-        RAW_PREFIX: reports-raw/${{ steps.calculate-key.outputs.KEY }}/${{ inputs.build_type }}
+        RAW_PREFIX: reports-raw/${{ steps.calculate-vars.outputs.KEY }}/${{ inputs.build_type }}
-        TEST_OUTPUT: /tmp/test_output
-        BUCKET: neon-github-public-dev
       shell: bash -euxo pipefail {0}
       run: |
         # Get previously uploaded data for this run
@@ -176,36 +203,42 @@ runs:
         REPORT_URL=https://${BUCKET}.s3.amazonaws.com/${REPORT_PREFIX}/${GITHUB_RUN_ID}/index.html
 
         # Generate redirect
-        cat <<EOF > ./index.html
+        cat <<EOF > ${TEST_OUTPUT}/allure/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"
+        aws s3 cp --only-show-errors ${TEST_OUTPUT}/allure/index.html "s3://${BUCKET}/${REPORT_PREFIX}/latest/index.html"
 
         echo "[Allure Report](${REPORT_URL})" >> ${GITHUB_STEP_SUMMARY}
         echo "report-url=${REPORT_URL}" >> $GITHUB_OUTPUT
+        echo "report-json-url=${REPORT_URL%/index.html}/data/suites.json" >> $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
+        LOCK_FILE: reports/${{ steps.calculate-vars.outputs.KEY }}/lock.txt
-        BUCKET: neon-github-public-dev
+        TEST_SELECTION: ${{ steps.calculate-vars.outputs.TEST_SELECTION }}
       run: |
         aws s3 cp --only-show-errors "s3://${BUCKET}/${LOCK_FILE}" ./lock.txt || exit 0
 
-        if [ "$(cat lock.txt)" = "${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}-${{ inputs.test_selection }}" ]; then
+        if [ "$(cat lock.txt)" = "${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}-${TEST_SELECTION}" ]; then
           aws s3 rm "s3://${BUCKET}/${LOCK_FILE}"
         fi
 
+    - name: Cleanup
+      if: always()
+      shell: bash -euxo pipefail {0}
+      run: |
+        rm -rf ${TEST_OUTPUT}/allure
+
     - 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: |

.github/actions/download/action.yml

@@ -37,7 +37,7 @@ runs:
             echo 'SKIPPED=true' >> $GITHUB_OUTPUT
             exit 0
           else
-            echo 2>&1 "Neither s3://${BUCKET}/${PREFIX}/${FILENAME} nor its version from previous attempts exist"
+            echo >&2 "Neither s3://${BUCKET}/${PREFIX}/${FILENAME} nor its version from previous attempts exist"
             exit 1
           fi
         fi

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

@@ -0,0 +1,138 @@
+name: 'Create Branch'
+description: 'Create Branch using API'
+
+inputs:
+  api_key:
+    desctiption: 'Neon API key'
+    required: true
+  project_id:
+    desctiption: 'ID of the Project to create Branch in'
+    required: true
+  api_host:
+    desctiption: 'Neon API host'
+    default: console.stage.neon.tech
+outputs:
+  dsn:
+    description: 'Created Branch DSN (for main database)'
+    value: ${{ steps.change-password.outputs.dsn }}
+  branch_id:
+    description: 'Created Branch ID'
+    value: ${{ steps.create-branch.outputs.branch_id }}
+
+runs:
+  using: "composite"
+  steps:
+    - name: Create New Branch
+      id: create-branch
+      shell: bash -euxo pipefail {0}
+      run: |
+        for i in $(seq 1 10); do
+         branch=$(curl \
+            "https://${API_HOST}/api/v2/projects/${PROJECT_ID}/branches" \
+            --header "Accept: application/json" \
+            --header "Content-Type: application/json" \
+            --header "Authorization: Bearer ${API_KEY}" \
+            --data "{
+              \"branch\": {
+                \"name\": \"Created by actions/neon-branch-create; GITHUB_RUN_ID=${GITHUB_RUN_ID} at $(date +%s)\"
+              },
+              \"endpoints\": [
+                {
+                  \"type\": \"read_write\"
+                }
+              ]
+            }")
+
+          if [ -z "${branch}" ]; then
+            sleep 1
+            continue
+          fi
+
+          branch_id=$(echo $branch | jq --raw-output '.branch.id')
+          if [ "${branch_id}" == "null" ]; then
+            sleep 1
+            continue
+          fi
+
+          break
+        done
+
+        if [ -z "${branch_id}" ] || [ "${branch_id}" == "null" ]; then
+          echo >&2 "Failed to create branch after 10 attempts, the latest response was: ${branch}"
+          exit 1
+        fi
+
+        branch_id=$(echo $branch | jq --raw-output '.branch.id')
+        echo "branch_id=${branch_id}" >> $GITHUB_OUTPUT
+
+        host=$(echo $branch | jq --raw-output '.endpoints[0].host')
+        echo "host=${host}" >> $GITHUB_OUTPUT
+      env:
+        API_HOST: ${{ inputs.api_host }}
+        API_KEY: ${{ inputs.api_key }}
+        PROJECT_ID: ${{ inputs.project_id }}
+
+    - name: Get Role name
+      id: role-name
+      shell: bash -euxo pipefail {0}
+      run: |
+        roles=$(curl \
+          "https://${API_HOST}/api/v2/projects/${PROJECT_ID}/branches/${BRANCH_ID}/roles" \
+          --fail \
+          --header "Accept: application/json" \
+          --header "Content-Type: application/json" \
+          --header "Authorization: Bearer ${API_KEY}"
+          )
+
+        role_name=$(echo $roles | jq --raw-output '.roles[] | select(.protected == false) | .name')
+        echo "role_name=${role_name}" >> $GITHUB_OUTPUT
+      env:
+        API_HOST: ${{ inputs.api_host }}
+        API_KEY: ${{ inputs.api_key }}
+        PROJECT_ID: ${{ inputs.project_id }}
+        BRANCH_ID: ${{ steps.create-branch.outputs.branch_id }}
+
+    - name: Change Password
+      id: change-password
+      # A shell without `set -x` to not to expose password/dsn in logs
+      shell: bash -euo pipefail {0}
+      run: |
+        for i in $(seq 1 10); do
+          reset_password=$(curl \
+            "https://${API_HOST}/api/v2/projects/${PROJECT_ID}/branches/${BRANCH_ID}/roles/${ROLE_NAME}/reset_password" \
+            --request POST \
+            --header "Accept: application/json" \
+            --header "Content-Type: application/json" \
+            --header "Authorization: Bearer ${API_KEY}"
+            )
+
+          if [ -z "${reset_password}" ]; then
+            sleep 1
+            continue
+          fi
+
+          password=$(echo $reset_password | jq --raw-output '.role.password')
+          if [ "${password}" == "null" ]; then
+            sleep 1
+            continue
+          fi
+
+          echo "::add-mask::${password}"
+          break
+        done
+
+        if [ -z "${password}" ] || [ "${password}" == "null" ]; then
+          echo >&2 "Failed to reset password after 10 attempts, the latest response was: ${reset_password}"
+          exit 1
+        fi
+
+        dsn="postgres://${ROLE_NAME}:${password}@${HOST}/neondb"
+        echo "::add-mask::${dsn}"
+        echo "dsn=${dsn}" >> $GITHUB_OUTPUT
+      env:
+        API_HOST: ${{ inputs.api_host }}
+        API_KEY: ${{ inputs.api_key }}
+        PROJECT_ID: ${{ inputs.project_id }}
+        BRANCH_ID: ${{ steps.create-branch.outputs.branch_id }}
+        ROLE_NAME: ${{ steps.role-name.outputs.role_name }}
+        HOST: ${{ steps.create-branch.outputs.host }}

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

@@ -0,0 +1,58 @@
+name: 'Delete Branch'
+description: 'Delete Branch using API'
+
+inputs:
+  api_key:
+    desctiption: 'Neon API key'
+    required: true
+  project_id:
+    desctiption: 'ID of the Project which should be deleted'
+    required: true
+  branch_id:
+    desctiption: 'ID of the branch to delete'
+    required: true
+  api_host:
+    desctiption: 'Neon API host'
+    default: console.stage.neon.tech
+
+runs:
+  using: "composite"
+  steps:
+    - name: Delete Branch
+      # Do not try to delete a branch if .github/actions/neon-project-create
+      # or .github/actions/neon-branch-create failed before
+      if: ${{ inputs.project_id != '' && inputs.branch_id != '' }}
+      shell: bash -euxo pipefail {0}
+      run: |
+        for i in $(seq 1 10); do
+          deleted_branch=$(curl \
+            "https://${API_HOST}/api/v2/projects/${PROJECT_ID}/branches/${BRANCH_ID}" \
+            --request DELETE \
+            --header "Accept: application/json" \
+            --header "Content-Type: application/json" \
+            --header "Authorization: Bearer ${API_KEY}"
+            )
+
+          if [ -z "${deleted_branch}" ]; then
+            sleep 1
+            continue
+          fi
+
+          branch_id=$(echo $deleted_branch | jq --raw-output '.branch.id')
+          if [ "${branch_id}" == "null" ]; then
+            sleep 1
+            continue
+          fi
+
+          break
+        done
+
+        if [ -z "${branch_id}" ] || [ "${branch_id}" == "null" ]; then
+          echo >&2 "Failed to delete branch after 10 attempts, the latest response was: ${deleted_branch}"
+          exit 1
+        fi
+      env:
+        API_HOST: ${{ inputs.api_host }}
+        API_KEY: ${{ inputs.api_key }}
+        PROJECT_ID: ${{ inputs.project_id }}
+        BRANCH_ID: ${{ inputs.branch_id }}

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

@@ -5,12 +5,22 @@ 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
+    default: aws-us-east-2
+  postgres_version:
+    desctiption: 'Postgres version; default is 15'
+    default: 15
+  api_host:
+    desctiption: 'Neon API host'
+    default: console.stage.neon.tech
+  provisioner:
+    desctiption: 'k8s-pod or k8s-neonvm'
+    default: 'k8s-pod'
+  compute_units:
+    desctiption: '[Min, Max] compute units; Min and Max are used for k8s-neonvm with autoscaling, for k8s-pod values Min and Max should be equal'
+    default: '[1, 1]'
+
 outputs:
   dsn:
     description: 'Created Project DSN (for main database)'
@@ -22,38 +32,17 @@ outputs:
 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: ${{ inputs.region_id }}
-
     - name: Create Neon Project
       id: create-neon-project
       # A shell without `set -x` to not to expose password/dsn in logs
       shell: bash -euo pipefail {0}
       run: |
+        if [ "${PROVISIONER}" == "k8s-pod" ] && [ "${MIN_CU}" != "${MAX_CU}" ]; then
+          echo >&2 "For k8s-pod provisioner MIN_CU should be equal to MAX_CU"
+        fi
+
         project=$(curl \
-          "https://${API_HOST}/api/v1/projects" \
+          "https://${API_HOST}/api/v2/projects" \
           --fail \
           --header "Accept: application/json" \
           --header "Content-Type: application/json" \
@@ -61,8 +50,11 @@ runs:
           --data "{
             \"project\": {
               \"name\": \"Created by actions/neon-project-create; GITHUB_RUN_ID=${GITHUB_RUN_ID}\",
-              \"platform_id\": \"aws\",
+              \"pg_version\": ${POSTGRES_VERSION},
               \"region_id\": \"${REGION_ID}\",
+              \"provisioner\": \"${PROVISIONER}\",
+              \"autoscaling_limit_min_cu\": ${MIN_CU},
+              \"autoscaling_limit_max_cu\": ${MAX_CU},
               \"settings\": { }
             }
           }")
@@ -70,13 +62,19 @@ runs:
         # Mask password
         echo "::add-mask::$(echo $project | jq --raw-output '.roles[] | select(.name != "web_access") | .password')"
 
-        dsn=$(echo $project | jq --raw-output '.roles[] | select(.name != "web_access") | .dsn')/main
+        dsn=$(echo $project | jq --raw-output '.connection_uris[0].connection_uri')
         echo "::add-mask::${dsn}"
         echo "dsn=${dsn}" >> $GITHUB_OUTPUT
 
-        project_id=$(echo $project | jq --raw-output '.id')
+        project_id=$(echo $project | jq --raw-output '.project.id')
         echo "project_id=${project_id}" >> $GITHUB_OUTPUT
+
+        echo "Project ${project_id} has been created"
       env:
+        API_HOST: ${{ inputs.api_host }}
         API_KEY: ${{ inputs.api_key }}
-        API_HOST: ${{ steps.parse-input.outputs.api_host }}
+        REGION_ID: ${{ inputs.region_id }}
-        REGION_ID: ${{ steps.parse-input.outputs.region_id }}
+        POSTGRES_VERSION: ${{ inputs.postgres_version }}
+        PROVISIONER: ${{ inputs.provisioner }}
+        MIN_CU: ${{ fromJSON(inputs.compute_units)[0] }}
+        MAX_CU: ${{ fromJSON(inputs.compute_units)[1] }}

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

@@ -5,50 +5,31 @@ 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
+  api_host:
+    desctiption: 'Neon API host'
+    default: console.stage.neon.tech
 
 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
+      # Do not try to delete a project if .github/actions/neon-project-create failed before
+      if: ${{ inputs.project_id != '' }}
       shell: bash -euxo pipefail {0}
       run: |
-        # Allow PROJECT_ID to be empty/null for cases when .github/actions/neon-project-create failed
+        curl \
-        if [ -n "${PROJECT_ID}" ]; then
+          "https://${API_HOST}/api/v2/projects/${PROJECT_ID}" \
-          curl -X "POST" \
-            "https://${API_HOST}/api/v1/projects/${PROJECT_ID}/delete" \
           --fail \
+          --request DELETE \
           --header "Accept: application/json" \
           --header "Content-Type: application/json" \
           --header "Authorization: Bearer ${API_KEY}"
-        fi
+
+        echo "Project ${PROJECT_ID} has been deleted"
       env:
+        API_HOST: ${{ inputs.api_host }}
         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

@@ -44,6 +44,10 @@ inputs:
     description: 'Secret access key'
     required: false
     default: ''
+  rerun_flaky:
+    description: 'Whether to rerun flaky tests'
+    required: false
+    default: 'false'
 
 runs:
   using: "composite"
@@ -55,6 +59,22 @@ runs:
         name: neon-${{ runner.os }}-${{ inputs.build_type }}-artifact
         path: /tmp/neon
 
+    - 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: Checkout
       if: inputs.needs_postgres_source == 'true'
       uses: actions/checkout@v3
@@ -76,10 +96,16 @@ runs:
     - 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
         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')
+        RERUN_FLAKY: ${{ inputs.rerun_flaky }}
       shell: bash -euxo pipefail {0}
       run: |
         # PLATFORM will be embedded in the perf test report
@@ -102,7 +128,12 @@ runs:
           exit 1
         fi
         if [[ "${{ inputs.run_in_parallel }}" == "true" ]]; then
-          EXTRA_PARAMS="-n4 $EXTRA_PARAMS"
+          # -n16 uses sixteen processes to run tests via pytest-xdist
+          EXTRA_PARAMS="-n16 $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
@@ -117,6 +148,13 @@ runs:
           EXTRA_PARAMS="--out-dir $PERF_REPORT_DIR $EXTRA_PARAMS"
         fi
 
+        if [ "${RERUN_FLAKY}" == "true" ]; then
+          mkdir -p $TEST_OUTPUT
+          poetry run ./scripts/flaky_tests.py "${TEST_RESULT_CONNSTR}" --days 10 --output "$TEST_OUTPUT/flaky.json"
+
+          EXTRA_PARAMS="--flaky-tests-json $TEST_OUTPUT/flaky.json $EXTRA_PARAMS"
+        fi
+
         if [[ "${{ inputs.build_type }}" == "debug" ]]; then
           cov_prefix=(scripts/coverage "--profraw-prefix=$GITHUB_JOB" --dir=/tmp/coverage run)
         elif [[ "${{ inputs.build_type }}" == "release" ]]; then
@@ -137,9 +175,9 @@ 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 \
@@ -154,8 +192,17 @@ runs:
           scripts/generate_and_push_perf_report.sh
         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: Create Allure report
-      if: always()
+      if: ${{ !cancelled() }}
       uses: ./.github/actions/allure-report
       with:
         action: store

.github/actions/upload/action.yml

@@ -23,7 +23,7 @@ runs:
         mkdir -p $(dirname $ARCHIVE)
 
         if [ -f ${ARCHIVE} ]; then
-          echo 2>&1 "File ${ARCHIVE} already exist. Something went wrong before"
+          echo >&2 "File ${ARCHIVE} already exist. Something went wrong before"
           exit 1
         fi
 
@@ -33,10 +33,10 @@ runs:
         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"
+          echo >&2 "${SOURCE} does not exist"
           exit 2
         else
-          echo 2>&1 "${SOURCE} is neither a directory nor a file, do not know how to handle it"
+          echo >&2 "${SOURCE} is neither a directory nor a file, do not know how to handle it"
           exit 3
         fi
 

.github/ansible/.gitignore

@@ -1,5 +1,3 @@
-zenith_install.tar.gz
-.zenith_current_version
 neon_install.tar.gz
 .neon_current_version
 

.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

@@ -91,6 +91,15 @@
       tags:
       - pageserver
 
+    # used in `pageserver.service` template
+    - name: learn current availability_zone
+      shell:
+        cmd: "curl -s http://169.254.169.254/latest/meta-data/placement/availability-zone"
+      register: ec2_availability_zone
+
+    - set_fact: 
+        ec2_availability_zone={{ ec2_availability_zone.stdout }}
+
     - name: upload systemd service definition
       ansible.builtin.template:
         src: systemd/pageserver.service
@@ -117,7 +126,8 @@
       shell:
         cmd: |
           INSTANCE_ID=$(curl -s http://169.254.169.254/latest/meta-data/instance-id)
-          curl -sfS -d '{"version": {{ current_version }} }' -X PATCH {{ console_mgmt_base_url }}/api/v1/pageservers/$INSTANCE_ID
+          curl -sfS -H "Authorization: Bearer {{ CONSOLE_API_TOKEN }}" {{ console_mgmt_base_url }}/management/api/v2/pageservers/$INSTANCE_ID | jq '.version = {{ current_version }}' > /tmp/new_version
+          curl -sfS -H "Authorization: Bearer {{ CONSOLE_API_TOKEN }}" -H "Content-Type: application/json" -X POST -d@/tmp/new_version {{ console_mgmt_base_url }}/management/api/v2/pageservers
       tags:
       - pageserver
 
@@ -152,6 +162,15 @@
       tags:
       - safekeeper
 
+    # used in `safekeeper.service` template
+    - name: learn current availability_zone
+      shell:
+        cmd: "curl -s http://169.254.169.254/latest/meta-data/placement/availability-zone"
+      register: ec2_availability_zone
+
+    - set_fact: 
+        ec2_availability_zone={{ ec2_availability_zone.stdout }}
+
     # in the future safekeepers should discover pageservers byself
     # but currently use first pageserver that was discovered
     - name: set first pageserver var for safekeepers
@@ -186,6 +205,7 @@
       shell:
         cmd: |
           INSTANCE_ID=$(curl -s http://169.254.169.254/latest/meta-data/instance-id)
-          curl -sfS -d '{"version": {{ current_version }} }' -X PATCH {{ console_mgmt_base_url }}/api/v1/safekeepers/$INSTANCE_ID
+          curl -sfS -H "Authorization: Bearer {{ CONSOLE_API_TOKEN }}" {{ console_mgmt_base_url }}/management/api/v2/safekeepers/$INSTANCE_ID | jq '.version = {{ current_version }}' > /tmp/new_version
+          curl -sfS -H "Authorization: Bearer {{ CONSOLE_API_TOKEN }}" -H "Content-Type: application/json" -X POST -d@/tmp/new_version {{ console_mgmt_base_url }}/management/api/v2/safekeepers
       tags:
       - safekeeper

.github/ansible/get_binaries.sh

@@ -25,6 +25,7 @@ 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/storage_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/

.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
-    env_name: neon-stress
-    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 }}"
-    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

@@ -0,0 +1,48 @@
+storage:
+  vars:
+    bucket_name: neon-prod-storage-ap-southeast-1
+    bucket_region: ap-southeast-1
+    console_mgmt_base_url: http://neon-internal-api.aws.neon.tech
+    broker_endpoint: http://storage-broker-lb.epsilon.ap-southeast-1.internal.aws.neon.tech:50051
+    pageserver_config_stub:
+      pg_distrib_dir: /usr/local
+      metric_collection_endpoint: http://neon-internal-api.aws.neon.tech/billing/api/v1/usage_events
+      metric_collection_interval: 10min
+      disk_usage_based_eviction:
+        max_usage_pct: 85 # TODO: decrease to 80 after all pageservers are below 80
+        min_avail_bytes: 0
+        period: "10s"
+      tenant_config:
+        eviction_policy:
+          kind: "LayerAccessThreshold"
+          period: "10m"
+          threshold: &default_eviction_threshold "24h"
+        evictions_low_residence_duration_metric_threshold: *default_eviction_threshold
+      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
+    sentry_environment: production
+
+  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-2.ap-southeast-1.aws.neon.tech:
+          ansible_host:  i-04fb63634e4679eb9
+        safekeeper-3.ap-southeast-1.aws.neon.tech:
+          ansible_host:  i-05481f3bc88cfc2d4

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

@@ -0,0 +1,50 @@
+storage:
+  vars:
+    bucket_name: neon-prod-storage-eu-central-1
+    bucket_region: eu-central-1
+    console_mgmt_base_url: http://neon-internal-api.aws.neon.tech
+    broker_endpoint: http://storage-broker-lb.gamma.eu-central-1.internal.aws.neon.tech:50051
+    pageserver_config_stub:
+      pg_distrib_dir: /usr/local
+      metric_collection_endpoint: http://neon-internal-api.aws.neon.tech/billing/api/v1/usage_events
+      metric_collection_interval: 10min
+      disk_usage_based_eviction:
+        max_usage_pct: 85 # TODO: decrease to 80 after all pageservers are below 80
+        min_avail_bytes: 0
+        period: "10s"
+      tenant_config:
+        eviction_policy:
+          kind: "LayerAccessThreshold"
+          period: "10m"
+          threshold: &default_eviction_threshold "24h"
+        evictions_low_residence_duration_metric_threshold: *default_eviction_threshold
+      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
+    sentry_environment: production
+
+  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
+        pageserver-2.eu-central-1.aws.neon.tech:
+          ansible_host:  i-033584edf3f4b6742
+
+    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

@@ -0,0 +1,51 @@
+storage:
+  vars:
+    bucket_name: neon-prod-storage-us-east-2
+    bucket_region: us-east-2
+    console_mgmt_base_url: http://neon-internal-api.aws.neon.tech
+    broker_endpoint: http://storage-broker-lb.delta.us-east-2.internal.aws.neon.tech:50051
+    pageserver_config_stub:
+      pg_distrib_dir: /usr/local
+      metric_collection_endpoint: http://neon-internal-api.aws.neon.tech/billing/api/v1/usage_events
+      metric_collection_interval: 10min
+      disk_usage_based_eviction:
+        max_usage_pct: 85 # TODO: decrease to 80 after all pageservers are below 80
+        min_avail_bytes: 0
+        period: "10s"
+      tenant_config:
+        eviction_policy:
+          kind: "LayerAccessThreshold"
+          period: "10m"
+          threshold: &default_eviction_threshold "24h"
+        evictions_low_residence_duration_metric_threshold: *default_eviction_threshold
+      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
+    sentry_environment: production
+
+  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
+        pageserver-2.us-east-2.aws.neon.tech:
+          ansible_host:  i-0d7a1c4325e71421d
+
+    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/prod.us-west-2.hosts.yaml

@@ -0,0 +1,53 @@
+storage:
+  vars:
+    bucket_name: neon-prod-storage-us-west-2
+    bucket_region: us-west-2
+    console_mgmt_base_url: http://neon-internal-api.aws.neon.tech
+    broker_endpoint: http://storage-broker-lb.eta.us-west-2.internal.aws.neon.tech:50051
+    pageserver_config_stub:
+      pg_distrib_dir: /usr/local
+      metric_collection_endpoint: http://neon-internal-api.aws.neon.tech/billing/api/v1/usage_events
+      metric_collection_interval: 10min
+      disk_usage_based_eviction:
+        max_usage_pct: 85 # TODO: decrease to 80 after all pageservers are below 80
+        min_avail_bytes: 0
+        period: "10s"
+      tenant_config:
+        eviction_policy:
+          kind: "LayerAccessThreshold"
+          period: "10m"
+          threshold: &default_eviction_threshold "24h"
+        evictions_low_residence_duration_metric_threshold: *default_eviction_threshold
+      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-west-2
+    ansible_aws_ssm_bucket_name: neon-prod-storage-us-west-2
+    console_region_id: aws-us-west-2-new
+    sentry_environment: production
+
+  children:
+    pageservers:
+      hosts:
+        pageserver-0.us-west-2.aws.neon.tech:
+          ansible_host: i-0d9f6dfae0e1c780d
+        pageserver-1.us-west-2.aws.neon.tech:
+          ansible_host: i-0c834be1dddba8b3f
+        pageserver-2.us-west-2.aws.neon.tech:
+          ansible_host: i-051642d372c0a4f32
+        pageserver-3.us-west-2.aws.neon.tech:
+          ansible_host: i-00c3844beb9ad1c6b
+
+    safekeepers:
+      hosts:
+        safekeeper-0.us-west-2.aws.neon.tech:
+          ansible_host: i-00719d8a74986fda6
+        safekeeper-1.us-west-2.aws.neon.tech:
+          ansible_host: i-074682f9d3c712e7c
+        safekeeper-2.us-west-2.aws.neon.tech:
+          ansible_host: i-042b7efb1729d7966
+

.github/ansible/production.hosts.yaml

@@ -1,33 +0,0 @@
----
-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
-    pageserver_config_stub:
-      pg_distrib_dir: /usr/local
-      remote_storage:
-        bucket_name: "{{ bucket_name }}"
-        bucket_region: "{{ bucket_region }}"
-        prefix_in_bucket: "{{ inventory_hostname }}"
-    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

@@ -1,7 +1,10 @@
 #!/bin/sh
 
-# get instance id from meta-data service
+# fetch params 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)
+INSTANCE_TYPE=$(curl -s http://169.254.169.254/latest/meta-data/instance-type)
+DISK_SIZE=$(df -B1 /storage | tail -1 | awk '{print $2}')
 
 # store fqdn hostname in var
 HOST=$(hostname -f)
@@ -16,7 +19,10 @@ cat <<EOF | tee /tmp/payload
   "instance_id": "${INSTANCE_ID}",
   "http_host": "${HOST}",
   "http_port": 9898,
-  "active": false
+  "active": false,
+  "availability_zone_id": "${AZ_ID}",
+  "disk_size": ${DISK_SIZE},
+  "instance_type": "${INSTANCE_TYPE}"
 }
 EOF
 
@@ -24,7 +30,7 @@ EOF
 if ! curl -sf -H "Authorization: Bearer {{ CONSOLE_API_TOKEN }}" {{ console_mgmt_base_url }}/management/api/v2/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 -H "Authorization: Bearer {{ CONSOLE_API_TOKEN }}" -H "Content-Type: application/json" {{ console_mgmt_base_url }}/management/api/v2/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

@@ -25,7 +25,7 @@ EOF
 if ! curl -sf -H "Authorization: Bearer {{ CONSOLE_API_TOKEN }}" {{ console_mgmt_base_url }}/management/api/v2/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 -H "Authorization: Bearer {{ CONSOLE_API_TOKEN }}" -H "Content-Type: application/json" {{ console_mgmt_base_url }}/management/api/v2/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

@@ -1,3 +1,2 @@
 ansible_connection: aws_ssm
-ansible_aws_ssm_bucket_name: neon-dev-bucket
 ansible_python_interpreter: /usr/bin/python3

.github/ansible/staging.eu-west-1.hosts.yaml

@@ -0,0 +1,46 @@
+storage:
+  vars:
+    bucket_name: neon-dev-storage-eu-west-1
+    bucket_region: eu-west-1
+    console_mgmt_base_url: http://neon-internal-api.aws.neon.build
+    broker_endpoint: http://storage-broker-lb.zeta.eu-west-1.internal.aws.neon.build:50051
+    pageserver_config_stub:
+      pg_distrib_dir: /usr/local
+      metric_collection_endpoint: http://neon-internal-api.aws.neon.build/billing/api/v1/usage_events
+      metric_collection_interval: 10min
+      disk_usage_based_eviction:
+        max_usage_pct: 80
+        min_avail_bytes: 0
+        period: "10s"
+      tenant_config:
+        eviction_policy:
+          kind: "LayerAccessThreshold"
+          period: "20m"
+          threshold: &default_eviction_threshold "20m"
+        evictions_low_residence_duration_metric_threshold: *default_eviction_threshold
+      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-west-1
+    ansible_aws_ssm_bucket_name: neon-dev-storage-eu-west-1
+    console_region_id: aws-eu-west-1
+    sentry_environment: staging
+
+  children:
+    pageservers:
+      hosts:
+        pageserver-0.eu-west-1.aws.neon.build:
+          ansible_host: i-01d496c5041c7f34c
+
+    safekeepers:
+      hosts:
+        safekeeper-0.eu-west-1.aws.neon.build:
+          ansible_host: i-05226ef85722831bf
+        safekeeper-1.eu-west-1.aws.neon.build:
+          ansible_host: i-06969ee1bf2958bfc
+        safekeeper-2.eu-west-1.aws.neon.build:
+          ansible_host: i-087892e9625984a0b

.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
-    env_name: us-stage
-    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 }}"
-    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

@@ -2,25 +2,47 @@ storage:
   vars:
     bucket_name: neon-staging-storage-us-east-2
     bucket_region: us-east-2
-    console_mgmt_base_url: http://console-staging.local
+    console_mgmt_base_url: http://neon-internal-api.aws.neon.build
-    env_name: us-stage
+    broker_endpoint: http://storage-broker-lb.beta.us-east-2.internal.aws.neon.build:50051
-    etcd_endpoints: etcd-0.us-east-2.aws.neon.build:2379
     pageserver_config_stub:
       pg_distrib_dir: /usr/local
+      metric_collection_endpoint: http://neon-internal-api.aws.neon.build/billing/api/v1/usage_events
+      metric_collection_interval: 10min
+      disk_usage_based_eviction:
+        max_usage_pct: 80
+        min_avail_bytes: 0
+        period: "10s"
+      tenant_config:
+        eviction_policy:
+          kind: "LayerAccessThreshold"
+          period: "20m"
+          threshold: &default_eviction_threshold "20m"
+        evictions_low_residence_duration_metric_threshold: *default_eviction_threshold
       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
+    sentry_environment: staging
 
   children:
     pageservers:
       hosts:
         pageserver-0.us-east-2.aws.neon.build:
           ansible_host: i-0c3e70929edb5d691
+        pageserver-1.us-east-2.aws.neon.build:
+          ansible_host: i-0565a8b4008aa3f40
+        pageserver-2.us-east-2.aws.neon.build:
+          ansible_host: i-01e31cdf7e970586a
+        pageserver-3.us-east-2.aws.neon.build:
+          ansible_host: i-0602a0291365ef7cc
+        pageserver-99.us-east-2.aws.neon.build:
+          ansible_host: i-0c39491109bb88824
 
     safekeepers:
       hosts:
@@ -30,3 +52,5 @@ storage:
           ansible_host: i-0171efc3604a7b907
         safekeeper-2.us-east-2.aws.neon.build:
           ansible_host: i-0de0b03a51676a6ce
+        safekeeper-99.us-east-2.aws.neon.build:
+          ansible_host: i-0d61b6a2ea32028d5

.github/ansible/systemd/pageserver.service

@@ -5,8 +5,8 @@ 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/v14/lib SENTRY_DSN={{ SENTRY_URL_PAGESERVER }} SENTRY_ENVIRONMENT={{ sentry_environment }}
-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
+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_endpoint='{{ broker_endpoint }}'" -c "availability_zone='{{ ec2_availability_zone }}'" -D /storage/pageserver/data
 ExecReload=/bin/kill -HUP $MAINPID
 KillMode=mixed
 KillSignal=SIGINT

.github/ansible/systemd/safekeeper.service

@@ -5,8 +5,8 @@ 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
+Environment=RUST_BACKTRACE=1 NEON_REPO_DIR=/storage/safekeeper/data LD_LIBRARY_PATH=/usr/local/v14/lib SENTRY_DSN={{ SENTRY_URL_SAFEKEEPER }} SENTRY_ENVIRONMENT={{ sentry_environment }}
-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="{{ env_name }}/wal"}'
+ExecStart=/usr/local/bin/safekeeper -l {{ inventory_hostname }}{{ hostname_suffix }}:6500 --listen-http {{ inventory_hostname }}{{ hostname_suffix }}:7676 -D /storage/safekeeper/data --broker-endpoint={{ broker_endpoint }} --remote-storage='{bucket_name="{{bucket_name}}", bucket_region="{{bucket_region}}", prefix_in_bucket="{{ safekeeper_s3_prefix }}"}' --availability-zone={{ ec2_availability_zone }}
 ExecReload=/bin/kill -HUP $MAINPID
 KillMode=mixed
 KillSignal=SIGINT

.github/helm-values/dev-eu-west-1-zeta.neon-proxy-scram.yaml

@@ -0,0 +1,75 @@
+# Helm chart values for neon-proxy-scram.
+# This is a YAML-formatted file.
+
+deploymentStrategy:
+  type: RollingUpdate
+  rollingUpdate:
+    maxSurge: 100%
+    maxUnavailable: 50%
+
+# Delay the kill signal by 5 minutes (5 * 60)
+# The pod(s) will stay in Terminating, keeps the existing connections
+# but doesn't receive new ones
+containerLifecycle:
+  preStop:
+    exec:
+      command: ["/bin/sh", "-c", "sleep 300"]
+terminationGracePeriodSeconds: 604800
+
+image:
+  repository: neondatabase/neon
+
+settings:
+  authBackend: "console"
+  authEndpoint: "http://neon-internal-api.aws.neon.build/management/api/v2"
+  domain: "*.eu-west-1.aws.neon.build"
+  sentryEnvironment: "staging"
+  wssPort: 8443
+  metricCollectionEndpoint: "http://neon-internal-api.aws.neon.build/billing/api/v1/usage_events"
+  metricCollectionInterval: "1min"
+
+# -- Additional labels for neon-proxy pods
+podLabels:
+  neon_service: proxy-scram
+  neon_env: dev
+  neon_region: eu-west-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-west-1.aws.neon.build
+  httpsPort: 443
+
+#metrics:
+#  enabled: true
+#  serviceMonitor:
+#    enabled: true
+#    selector:
+#      release: kube-prometheus-stack
+
+extraManifests:
+  - apiVersion: operator.victoriametrics.com/v1beta1
+    kind: VMServiceScrape
+    metadata:
+      name: "{{ include \"neon-proxy.fullname\" . }}"
+      labels:
+        helm.sh/chart: neon-proxy-{{ .Chart.Version }}
+        app.kubernetes.io/name: neon-proxy
+        app.kubernetes.io/instance: "{{ include \"neon-proxy.fullname\" . }}"
+        app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
+        app.kubernetes.io/managed-by: Helm
+      namespace: "{{ .Release.Namespace }}"
+    spec:
+      selector:
+        matchLabels:
+          app.kubernetes.io/name: "neon-proxy"
+      endpoints:
+        - port: http
+          path: /metrics
+          interval: 10s
+          scrapeTimeout: 10s
+      namespaceSelector:
+        matchNames:
+          - "{{ .Release.Namespace }}"

.github/helm-values/dev-eu-west-1-zeta.neon-storage-broker.yaml

@@ -0,0 +1,52 @@
+# Helm chart values for neon-storage-broker
+podLabels:
+  neon_env: staging
+  neon_service: storage-broker
+
+# Use L4 LB
+service:
+  # service.annotations -- Annotations to add to the service
+  annotations:
+    service.beta.kubernetes.io/aws-load-balancer-type: external  # use newer AWS Load Balancer Controller
+    service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
+    service.beta.kubernetes.io/aws-load-balancer-scheme: internal  # deploy LB to private subnet
+    # assign service to this name at external-dns
+    external-dns.alpha.kubernetes.io/hostname: storage-broker-lb.zeta.eu-west-1.internal.aws.neon.build
+  # service.type -- Service type
+  type: LoadBalancer
+  # service.port -- broker listen port
+  port: 50051
+
+ingress:
+  enabled: false
+
+metrics:
+  enabled: false
+
+extraManifests:
+  - apiVersion: operator.victoriametrics.com/v1beta1
+    kind: VMServiceScrape
+    metadata:
+      name: "{{ include \"neon-storage-broker.fullname\" . }}"
+      labels:
+        helm.sh/chart: neon-storage-broker-{{ .Chart.Version }}
+        app.kubernetes.io/name: neon-storage-broker
+        app.kubernetes.io/instance: neon-storage-broker
+        app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
+        app.kubernetes.io/managed-by: Helm
+      namespace: "{{ .Release.Namespace }}"
+    spec:
+      selector:
+        matchLabels:
+          app.kubernetes.io/name: "neon-storage-broker"
+      endpoints:
+        - port: broker
+          path: /metrics
+          interval: 10s
+          scrapeTimeout: 10s
+      namespaceSelector:
+        matchNames:
+          - "{{ .Release.Namespace }}"
+
+settings:
+  sentryEnvironment: "staging"

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

@@ -0,0 +1,67 @@
+# Helm chart values for neon-proxy-link.
+# This is a YAML-formatted file.
+
+image:
+  repository: neondatabase/neon
+
+settings:
+  authBackend: "link"
+  authEndpoint: "https://console.stage.neon.tech/authenticate_proxy_request/"
+  uri: "https://console.stage.neon.tech/psql_session/"
+  domain: "pg.neon.build"
+  sentryEnvironment: "staging"
+  metricCollectionEndpoint: "http://neon-internal-api.aws.neon.build/billing/api/v1/usage_events"
+  metricCollectionInterval: "1min"
+
+# -- Additional labels for neon-proxy-link pods
+podLabels:
+  neon_service: proxy
+  neon_env: dev
+  neon_region: us-east-2
+
+service:
+  type: LoadBalancer
+  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: internal
+    external-dns.alpha.kubernetes.io/hostname: neon-proxy-link-mgmt.beta.us-east-2.aws.neon.build
+
+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: neon-proxy-link.beta.us-east-2.aws.neon.build
+
+#metrics:
+#  enabled: true
+#  serviceMonitor:
+#    enabled: true
+#    selector:
+#      release: kube-prometheus-stack
+
+extraManifests:
+  - apiVersion: operator.victoriametrics.com/v1beta1
+    kind: VMServiceScrape
+    metadata:
+      name: "{{ include \"neon-proxy.fullname\" . }}"
+      labels:
+        helm.sh/chart: neon-proxy-{{ .Chart.Version }}
+        app.kubernetes.io/name: neon-proxy
+        app.kubernetes.io/instance: "{{ include \"neon-proxy.fullname\" . }}"
+        app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
+        app.kubernetes.io/managed-by: Helm
+      namespace: "{{ .Release.Namespace }}"
+    spec:
+      selector:
+        matchLabels:
+          app.kubernetes.io/name: "neon-proxy"
+      endpoints:
+        - port: http
+          path: /metrics
+          interval: 10s
+          scrapeTimeout: 10s
+      namespaceSelector:
+        matchNames:
+          - "{{ .Release.Namespace }}"

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

@@ -0,0 +1,76 @@
+# Helm chart values for neon-proxy-scram.
+# This is a YAML-formatted file.
+
+deploymentStrategy:
+  type: RollingUpdate
+  rollingUpdate:
+    maxSurge: 100%
+    maxUnavailable: 50%
+
+# Delay the kill signal by 5 minutes (5 * 60)
+# The pod(s) will stay in Terminating, keeps the existing connections
+# but doesn't receive new ones
+containerLifecycle:
+  preStop:
+    exec:
+      command: ["/bin/sh", "-c", "sleep 300"]
+terminationGracePeriodSeconds: 604800
+
+
+image:
+  repository: neondatabase/neon
+
+settings:
+  authBackend: "console"
+  authEndpoint: "http://neon-internal-api.aws.neon.build/management/api/v2"
+  domain: "*.cloud.stage.neon.tech"
+  sentryEnvironment: "staging"
+  wssPort: 8443
+  metricCollectionEndpoint: "http://neon-internal-api.aws.neon.build/billing/api/v1/usage_events"
+  metricCollectionInterval: "1min"
+
+# -- Additional labels for neon-proxy pods
+podLabels:
+  neon_service: proxy-scram-legacy
+  neon_env: dev
+  neon_region: 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: neon-proxy-scram-legacy.beta.us-east-2.aws.neon.build
+  httpsPort: 443
+
+#metrics:
+#  enabled: true
+#  serviceMonitor:
+#    enabled: true
+#    selector:
+#      release: kube-prometheus-stack
+
+extraManifests:
+  - apiVersion: operator.victoriametrics.com/v1beta1
+    kind: VMServiceScrape
+    metadata:
+      name: "{{ include \"neon-proxy.fullname\" . }}"
+      labels:
+        helm.sh/chart: neon-proxy-{{ .Chart.Version }}
+        app.kubernetes.io/name: neon-proxy
+        app.kubernetes.io/instance: "{{ include \"neon-proxy.fullname\" . }}"
+        app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
+        app.kubernetes.io/managed-by: Helm
+      namespace: "{{ .Release.Namespace }}"
+    spec:
+      selector:
+        matchLabels:
+          app.kubernetes.io/name: "neon-proxy"
+      endpoints:
+        - port: http
+          path: /metrics
+          interval: 10s
+          scrapeTimeout: 10s
+      namespaceSelector:
+        matchNames:
+          - "{{ .Release.Namespace }}"

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

@@ -0,0 +1,77 @@
+# Helm chart values for neon-proxy-scram.
+# This is a YAML-formatted file.
+
+deploymentStrategy:
+  type: RollingUpdate
+  rollingUpdate:
+    maxSurge: 100%
+    maxUnavailable: 50%
+
+# Delay the kill signal by 5 minutes (5 * 60)
+# The pod(s) will stay in Terminating, keeps the existing connections
+# but doesn't receive new ones
+containerLifecycle:
+  preStop:
+    exec:
+      command: ["/bin/sh", "-c", "sleep 300"]
+terminationGracePeriodSeconds: 604800
+
+
+image:
+  repository: neondatabase/neon
+
+settings:
+  authBackend: "console"
+  authEndpoint: "http://neon-internal-api.aws.neon.build/management/api/v2"
+  domain: "*.us-east-2.aws.neon.build"
+  extraDomains: ["*.us-east-2.postgres.zenith.tech", "*.us-east-2.retooldb-staging.com"]
+  sentryEnvironment: "staging"
+  wssPort: 8443
+  metricCollectionEndpoint: "http://neon-internal-api.aws.neon.build/billing/api/v1/usage_events"
+  metricCollectionInterval: "1min"
+
+# -- Additional labels for neon-proxy pods
+podLabels:
+  neon_service: proxy-scram
+  neon_env: dev
+  neon_region: 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
+  httpsPort: 443
+
+#metrics:
+#  enabled: true
+#  serviceMonitor:
+#    enabled: true
+#    selector:
+#      release: kube-prometheus-stack
+
+extraManifests:
+  - apiVersion: operator.victoriametrics.com/v1beta1
+    kind: VMServiceScrape
+    metadata:
+      name: "{{ include \"neon-proxy.fullname\" . }}"
+      labels:
+        helm.sh/chart: neon-proxy-{{ .Chart.Version }}
+        app.kubernetes.io/name: neon-proxy
+        app.kubernetes.io/instance: "{{ include \"neon-proxy.fullname\" . }}"
+        app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
+        app.kubernetes.io/managed-by: Helm
+      namespace: "{{ .Release.Namespace }}"
+    spec:
+      selector:
+        matchLabels:
+          app.kubernetes.io/name: "neon-proxy"
+      endpoints:
+        - port: http
+          path: /metrics
+          interval: 10s
+          scrapeTimeout: 10s
+      namespaceSelector:
+        matchNames:
+          - "{{ .Release.Namespace }}"

.github/helm-values/dev-us-east-2-beta.neon-storage-broker.yaml

@@ -0,0 +1,52 @@
+# Helm chart values for neon-storage-broker
+podLabels:
+  neon_env: staging
+  neon_service: storage-broker
+
+# Use L4 LB
+service:
+  # service.annotations -- Annotations to add to the service
+  annotations:
+    service.beta.kubernetes.io/aws-load-balancer-type: external  # use newer AWS Load Balancer Controller
+    service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
+    service.beta.kubernetes.io/aws-load-balancer-scheme: internal  # deploy LB to private subnet
+    # assign service to this name at external-dns
+    external-dns.alpha.kubernetes.io/hostname: storage-broker-lb.beta.us-east-2.internal.aws.neon.build
+  # service.type -- Service type
+  type: LoadBalancer
+  # service.port -- broker listen port
+  port: 50051
+
+ingress:
+  enabled: false
+
+metrics:
+  enabled: false
+
+extraManifests:
+  - apiVersion: operator.victoriametrics.com/v1beta1
+    kind: VMServiceScrape
+    metadata:
+      name: "{{ include \"neon-storage-broker.fullname\" . }}"
+      labels:
+        helm.sh/chart: neon-storage-broker-{{ .Chart.Version }}
+        app.kubernetes.io/name: neon-storage-broker
+        app.kubernetes.io/instance: neon-storage-broker
+        app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
+        app.kubernetes.io/managed-by: Helm
+      namespace: "{{ .Release.Namespace }}"
+    spec:
+      selector:
+        matchLabels:
+          app.kubernetes.io/name: "neon-storage-broker"
+      endpoints:
+        - port: broker
+          path: /metrics
+          interval: 10s
+          scrapeTimeout: 10s
+      namespaceSelector:
+        matchNames:
+          - "{{ .Release.Namespace }}"
+
+settings:
+  sentryEnvironment: "staging"

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

@@ -1,26 +0,0 @@
-fullnameOverride: "neon-stress-proxy-scram"
-
-settings:
-  authBackend: "console"
-  authEndpoint: "http://neon-stress-console.local/management/api/v2"
-  domain: "*.stress.neon.tech"
-
-podLabels:
-  zenith_service: proxy-scram
-  zenith_env: staging
-  zenith_region: eu-west-1
-  zenith_region_slug: ireland
-
-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: '*.stress.neon.tech'
-
-metrics:
-  enabled: true
-  serviceMonitor:
-    enabled: true
-    selector:
-      release: kube-prometheus-stack

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

@@ -1,35 +0,0 @@
-fullnameOverride: "neon-stress-proxy"
-
-settings:
-  authBackend: "link"
-  authEndpoint: "https://console.dev.neon.tech/authenticate_proxy_request/"
-  uri: "https://console.dev.neon.tech/psql_session/"
-
-# -- Additional labels for zenith-proxy pods
-podLabels:
-  zenith_service: proxy
-  zenith_env: staging
-  zenith_region: eu-west-1
-  zenith_region_slug: ireland
-
-service:
-  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: internal
-    external-dns.alpha.kubernetes.io/hostname: neon-stress-proxy.local
-  type: LoadBalancer
-
-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: connect.dev.neon.tech
-
-metrics:
-  enabled: true
-  serviceMonitor:
-    enabled: true
-    selector:
-      release: kube-prometheus-stack

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

@@ -0,0 +1,77 @@
+# Helm chart values for neon-proxy-scram.
+# This is a YAML-formatted file.
+
+deploymentStrategy:
+  type: RollingUpdate
+  rollingUpdate:
+    maxSurge: 100%
+    maxUnavailable: 50%
+
+# Delay the kill signal by 5 minutes (5 * 60)
+# The pod(s) will stay in Terminating, keeps the existing connections
+# but doesn't receive new ones
+containerLifecycle:
+  preStop:
+    exec:
+      command: ["/bin/sh", "-c", "sleep 300"]
+terminationGracePeriodSeconds: 604800
+
+
+image:
+  repository: neondatabase/neon
+
+settings:
+  authBackend: "console"
+  authEndpoint: "http://neon-internal-api.aws.neon.tech/management/api/v2"
+  domain: "*.ap-southeast-1.aws.neon.tech"
+  extraDomains: ["*.ap-southeast-1.retooldb.com", "*.ap-southeast-1.postgres.vercel-storage.com"]
+  sentryEnvironment: "production"
+  wssPort: 8443
+  metricCollectionEndpoint: "http://neon-internal-api.aws.neon.tech/billing/api/v1/usage_events"
+  metricCollectionInterval: "10min"
+
+# -- Additional labels for neon-proxy pods
+podLabels:
+  neon_service: proxy-scram
+  neon_env: prod
+  neon_region: 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
+  httpsPort: 443
+
+#metrics:
+#  enabled: true
+#  serviceMonitor:
+#    enabled: true
+#    selector:
+#      release: kube-prometheus-stack
+
+extraManifests:
+  - apiVersion: operator.victoriametrics.com/v1beta1
+    kind: VMServiceScrape
+    metadata:
+      name: "{{ include \"neon-proxy.fullname\" . }}"
+      labels:
+        helm.sh/chart: neon-proxy-{{ .Chart.Version }}
+        app.kubernetes.io/name: neon-proxy
+        app.kubernetes.io/instance: "{{ include \"neon-proxy.fullname\" . }}"
+        app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
+        app.kubernetes.io/managed-by: Helm
+      namespace: "{{ .Release.Namespace }}"
+    spec:
+      selector:
+        matchLabels:
+          app.kubernetes.io/name: "neon-proxy"
+      endpoints:
+        - port: http
+          path: /metrics
+          interval: 10s
+          scrapeTimeout: 10s
+      namespaceSelector:
+        matchNames:
+          - "{{ .Release.Namespace }}"

.github/helm-values/prod-ap-southeast-1-epsilon.neon-storage-broker.yaml

@@ -0,0 +1,52 @@
+# Helm chart values for neon-storage-broker
+podLabels:
+  neon_env: production
+  neon_service: storage-broker
+
+# Use L4 LB
+service:
+  # service.annotations -- Annotations to add to the service
+  annotations:
+    service.beta.kubernetes.io/aws-load-balancer-type: external  # use newer AWS Load Balancer Controller
+    service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
+    service.beta.kubernetes.io/aws-load-balancer-scheme: internal  # deploy LB to private subnet
+    # assign service to this name at external-dns
+    external-dns.alpha.kubernetes.io/hostname: storage-broker-lb.epsilon.ap-southeast-1.internal.aws.neon.tech
+  # service.type -- Service type
+  type: LoadBalancer
+  # service.port -- broker listen port
+  port: 50051
+
+ingress:
+  enabled: false
+
+metrics:
+  enabled: false
+
+extraManifests:
+  - apiVersion: operator.victoriametrics.com/v1beta1
+    kind: VMServiceScrape
+    metadata:
+      name: "{{ include \"neon-storage-broker.fullname\" . }}"
+      labels:
+        helm.sh/chart: neon-storage-broker-{{ .Chart.Version }}
+        app.kubernetes.io/name: neon-storage-broker
+        app.kubernetes.io/instance: neon-storage-broker
+        app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
+        app.kubernetes.io/managed-by: Helm
+      namespace: "{{ .Release.Namespace }}"
+    spec:
+      selector:
+        matchLabels:
+          app.kubernetes.io/name: "neon-storage-broker"
+      endpoints:
+        - port: broker
+          path: /metrics
+          interval: 10s
+          scrapeTimeout: 10s
+      namespaceSelector:
+        matchNames:
+          - "{{ .Release.Namespace }}"
+
+settings:
+  sentryEnvironment: "production"

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

@@ -0,0 +1,77 @@
+# Helm chart values for neon-proxy-scram.
+# This is a YAML-formatted file.
+
+deploymentStrategy:
+  type: RollingUpdate
+  rollingUpdate:
+    maxSurge: 100%
+    maxUnavailable: 50%
+
+# Delay the kill signal by 5 minutes (5 * 60)
+# The pod(s) will stay in Terminating, keeps the existing connections
+# but doesn't receive new ones
+containerLifecycle:
+  preStop:
+    exec:
+      command: ["/bin/sh", "-c", "sleep 300"]
+terminationGracePeriodSeconds: 604800
+
+
+image:
+  repository: neondatabase/neon
+
+settings:
+  authBackend: "console"
+  authEndpoint: "http://neon-internal-api.aws.neon.tech/management/api/v2"
+  domain: "*.eu-central-1.aws.neon.tech"
+  extraDomains: ["*.eu-central-1.retooldb.com", "*.eu-central-1.postgres.vercel-storage.com"]
+  sentryEnvironment: "production"
+  wssPort: 8443
+  metricCollectionEndpoint: "http://neon-internal-api.aws.neon.tech/billing/api/v1/usage_events"
+  metricCollectionInterval: "10min"
+
+# -- Additional labels for neon-proxy pods
+podLabels:
+  neon_service: proxy-scram
+  neon_env: prod
+  neon_region: 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
+  httpsPort: 443
+
+#metrics:
+#  enabled: true
+#  serviceMonitor:
+#    enabled: true
+#    selector:
+#      release: kube-prometheus-stack
+
+extraManifests:
+  - apiVersion: operator.victoriametrics.com/v1beta1
+    kind: VMServiceScrape
+    metadata:
+      name: "{{ include \"neon-proxy.fullname\" . }}"
+      labels:
+        helm.sh/chart: neon-proxy-{{ .Chart.Version }}
+        app.kubernetes.io/name: neon-proxy
+        app.kubernetes.io/instance: "{{ include \"neon-proxy.fullname\" . }}"
+        app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
+        app.kubernetes.io/managed-by: Helm
+      namespace: "{{ .Release.Namespace }}"
+    spec:
+      selector:
+        matchLabels:
+          app.kubernetes.io/name: "neon-proxy"
+      endpoints:
+        - port: http
+          path: /metrics
+          interval: 10s
+          scrapeTimeout: 10s
+      namespaceSelector:
+        matchNames:
+          - "{{ .Release.Namespace }}"

.github/helm-values/prod-eu-central-1-gamma.neon-storage-broker.yaml

@@ -0,0 +1,52 @@
+# Helm chart values for neon-storage-broker
+podLabels:
+  neon_env: production
+  neon_service: storage-broker
+
+# Use L4 LB
+service:
+  # service.annotations -- Annotations to add to the service
+  annotations:
+    service.beta.kubernetes.io/aws-load-balancer-type: external  # use newer AWS Load Balancer Controller
+    service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
+    service.beta.kubernetes.io/aws-load-balancer-scheme: internal  # deploy LB to private subnet
+    # assign service to this name at external-dns
+    external-dns.alpha.kubernetes.io/hostname: storage-broker-lb.gamma.eu-central-1.internal.aws.neon.tech
+  # service.type -- Service type
+  type: LoadBalancer
+  # service.port -- broker listen port
+  port: 50051
+
+ingress:
+  enabled: false
+
+metrics:
+  enabled: false
+
+extraManifests:
+  - apiVersion: operator.victoriametrics.com/v1beta1
+    kind: VMServiceScrape
+    metadata:
+      name: "{{ include \"neon-storage-broker.fullname\" . }}"
+      labels:
+        helm.sh/chart: neon-storage-broker-{{ .Chart.Version }}
+        app.kubernetes.io/name: neon-storage-broker
+        app.kubernetes.io/instance: neon-storage-broker
+        app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
+        app.kubernetes.io/managed-by: Helm
+      namespace: "{{ .Release.Namespace }}"
+    spec:
+      selector:
+        matchLabels:
+          app.kubernetes.io/name: "neon-storage-broker"
+      endpoints:
+        - port: broker
+          path: /metrics
+          interval: 10s
+          scrapeTimeout: 10s
+      namespaceSelector:
+        matchNames:
+          - "{{ .Release.Namespace }}"
+
+settings:
+  sentryEnvironment: "production"

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

@@ -0,0 +1,58 @@
+# Helm chart values for neon-proxy-link.
+# This is a YAML-formatted file.
+
+image:
+  repository: neondatabase/neon
+
+settings:
+  authBackend: "link"
+  authEndpoint: "https://console.neon.tech/authenticate_proxy_request/"
+  uri: "https://console.neon.tech/psql_session/"
+  domain: "pg.neon.tech"
+  sentryEnvironment: "production"
+
+# -- Additional labels for zenith-proxy pods
+podLabels:
+  neon_service: proxy
+  neon_env: production
+  neon_region: us-east-2
+
+service:
+  type: LoadBalancer
+  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: internal
+    external-dns.alpha.kubernetes.io/hostname: neon-proxy-link-mgmt.delta.us-east-2.aws.neon.tech
+
+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: neon-proxy-link.delta.us-east-2.aws.neon.tech
+
+extraManifests:
+  - apiVersion: operator.victoriametrics.com/v1beta1
+    kind: VMServiceScrape
+    metadata:
+      name: "{{ include \"neon-proxy.fullname\" . }}"
+      labels:
+        helm.sh/chart: neon-proxy-{{ .Chart.Version }}
+        app.kubernetes.io/name: neon-proxy
+        app.kubernetes.io/instance: "{{ include \"neon-proxy.fullname\" . }}"
+        app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
+        app.kubernetes.io/managed-by: Helm
+      namespace: "{{ .Release.Namespace }}"
+    spec:
+      selector:
+        matchLabels:
+          app.kubernetes.io/name: "neon-proxy"
+      endpoints:
+        - port: http
+          path: /metrics
+          interval: 10s
+          scrapeTimeout: 10s
+      namespaceSelector:
+        matchNames:
+          - "{{ .Release.Namespace }}"

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

@@ -0,0 +1,77 @@
+# Helm chart values for neon-proxy-scram.
+# This is a YAML-formatted file.
+
+deploymentStrategy:
+  type: RollingUpdate
+  rollingUpdate:
+    maxSurge: 100%
+    maxUnavailable: 50%
+
+# Delay the kill signal by 5 minutes (5 * 60)
+# The pod(s) will stay in Terminating, keeps the existing connections
+# but doesn't receive new ones
+containerLifecycle:
+  preStop:
+    exec:
+      command: ["/bin/sh", "-c", "sleep 300"]
+terminationGracePeriodSeconds: 604800
+
+
+image:
+  repository: neondatabase/neon
+
+settings:
+  authBackend: "console"
+  authEndpoint: "http://neon-internal-api.aws.neon.tech/management/api/v2"
+  domain: "*.us-east-2.aws.neon.tech"
+  extraDomains: ["*.us-east-2.retooldb.com", "*.us-east-2.postgres.vercel-storage.com"]
+  sentryEnvironment: "production"
+  wssPort: 8443
+  metricCollectionEndpoint: "http://neon-internal-api.aws.neon.tech/billing/api/v1/usage_events"
+  metricCollectionInterval: "10min"
+
+# -- Additional labels for neon-proxy pods
+podLabels:
+  neon_service: proxy-scram
+  neon_env: prod
+  neon_region: 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
+  httpsPort: 443
+
+#metrics:
+#  enabled: true
+#  serviceMonitor:
+#    enabled: true
+#    selector:
+#      release: kube-prometheus-stack
+
+extraManifests:
+  - apiVersion: operator.victoriametrics.com/v1beta1
+    kind: VMServiceScrape
+    metadata:
+      name: "{{ include \"neon-proxy.fullname\" . }}"
+      labels:
+        helm.sh/chart: neon-proxy-{{ .Chart.Version }}
+        app.kubernetes.io/name: neon-proxy
+        app.kubernetes.io/instance: "{{ include \"neon-proxy.fullname\" . }}"
+        app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
+        app.kubernetes.io/managed-by: Helm
+      namespace: "{{ .Release.Namespace }}"
+    spec:
+      selector:
+        matchLabels:
+          app.kubernetes.io/name: "neon-proxy"
+      endpoints:
+        - port: http
+          path: /metrics
+          interval: 10s
+          scrapeTimeout: 10s
+      namespaceSelector:
+        matchNames:
+          - "{{ .Release.Namespace }}"

.github/helm-values/prod-us-east-2-delta.neon-storage-broker.yaml

@@ -0,0 +1,52 @@
+# Helm chart values for neon-storage-broker
+podLabels:
+  neon_env: production
+  neon_service: storage-broker
+
+# Use L4 LB
+service:
+  # service.annotations -- Annotations to add to the service
+  annotations:
+    service.beta.kubernetes.io/aws-load-balancer-type: external  # use newer AWS Load Balancer Controller
+    service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
+    service.beta.kubernetes.io/aws-load-balancer-scheme: internal  # deploy LB to private subnet
+    # assign service to this name at external-dns
+    external-dns.alpha.kubernetes.io/hostname: storage-broker-lb.delta.us-east-2.internal.aws.neon.tech
+  # service.type -- Service type
+  type: LoadBalancer
+  # service.port -- broker listen port
+  port: 50051
+
+ingress:
+  enabled: false
+
+metrics:
+  enabled: false
+
+extraManifests:
+  - apiVersion: operator.victoriametrics.com/v1beta1
+    kind: VMServiceScrape
+    metadata:
+      name: "{{ include \"neon-storage-broker.fullname\" . }}"
+      labels:
+        helm.sh/chart: neon-storage-broker-{{ .Chart.Version }}
+        app.kubernetes.io/name: neon-storage-broker
+        app.kubernetes.io/instance: neon-storage-broker
+        app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
+        app.kubernetes.io/managed-by: Helm
+      namespace: "{{ .Release.Namespace }}"
+    spec:
+      selector:
+        matchLabels:
+          app.kubernetes.io/name: "neon-storage-broker"
+      endpoints:
+        - port: broker
+          path: /metrics
+          interval: 10s
+          scrapeTimeout: 10s
+      namespaceSelector:
+        matchNames:
+          - "{{ .Release.Namespace }}"
+
+settings:
+  sentryEnvironment: "production"

.github/helm-values/prod-us-west-2-eta.neon-proxy-scram-legacy.yaml

@@ -0,0 +1,76 @@
+# Helm chart values for neon-proxy-scram.
+# This is a YAML-formatted file.
+
+deploymentStrategy:
+  type: RollingUpdate
+  rollingUpdate:
+    maxSurge: 100%
+    maxUnavailable: 50%
+
+# Delay the kill signal by 5 minutes (5 * 60)
+# The pod(s) will stay in Terminating, keeps the existing connections
+# but doesn't receive new ones
+containerLifecycle:
+  preStop:
+    exec:
+      command: ["/bin/sh", "-c", "sleep 300"]
+terminationGracePeriodSeconds: 604800
+
+
+image:
+  repository: neondatabase/neon
+
+settings:
+  authBackend: "console"
+  authEndpoint: "http://neon-internal-api.aws.neon.tech/management/api/v2"
+  domain: "*.cloud.neon.tech"
+  sentryEnvironment: "production"
+  wssPort: 8443
+  metricCollectionEndpoint: "http://neon-internal-api.aws.neon.tech/billing/api/v1/usage_events"
+  metricCollectionInterval: "10min"
+
+# -- Additional labels for neon-proxy pods
+podLabels:
+  neon_service: proxy-scram
+  neon_env: prod
+  neon_region: us-west-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: neon-proxy-scram-legacy.eta.us-west-2.aws.neon.tech
+  httpsPort: 443
+
+#metrics:
+#  enabled: true
+#  serviceMonitor:
+#    enabled: true
+#    selector:
+#      release: kube-prometheus-stack
+
+extraManifests:
+  - apiVersion: operator.victoriametrics.com/v1beta1
+    kind: VMServiceScrape
+    metadata:
+      name: "{{ include \"neon-proxy.fullname\" . }}"
+      labels:
+        helm.sh/chart: neon-proxy-{{ .Chart.Version }}
+        app.kubernetes.io/name: neon-proxy
+        app.kubernetes.io/instance: "{{ include \"neon-proxy.fullname\" . }}"
+        app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
+        app.kubernetes.io/managed-by: Helm
+      namespace: "{{ .Release.Namespace }}"
+    spec:
+      selector:
+        matchLabels:
+          app.kubernetes.io/name: "neon-proxy"
+      endpoints:
+        - port: http
+          path: /metrics
+          interval: 10s
+          scrapeTimeout: 10s
+      namespaceSelector:
+        matchNames:
+          - "{{ .Release.Namespace }}"

.github/helm-values/prod-us-west-2-eta.neon-proxy-scram.yaml

@@ -0,0 +1,77 @@
+# Helm chart values for neon-proxy-scram.
+# This is a YAML-formatted file.
+
+deploymentStrategy:
+  type: RollingUpdate
+  rollingUpdate:
+    maxSurge: 100%
+    maxUnavailable: 50%
+
+# Delay the kill signal by 5 minutes (5 * 60)
+# The pod(s) will stay in Terminating, keeps the existing connections
+# but doesn't receive new ones
+containerLifecycle:
+  preStop:
+    exec:
+      command: ["/bin/sh", "-c", "sleep 300"]
+terminationGracePeriodSeconds: 604800
+
+
+image:
+  repository: neondatabase/neon
+
+settings:
+  authBackend: "console"
+  authEndpoint: "http://neon-internal-api.aws.neon.tech/management/api/v2"
+  domain: "*.us-west-2.aws.neon.tech"
+  extraDomains: ["*.us-west-2.retooldb.com", "*.us-west-2.postgres.vercel-storage.com"]
+  sentryEnvironment: "production"
+  wssPort: 8443
+  metricCollectionEndpoint: "http://neon-internal-api.aws.neon.tech/billing/api/v1/usage_events"
+  metricCollectionInterval: "10min"
+
+# -- Additional labels for neon-proxy pods
+podLabels:
+  neon_service: proxy-scram
+  neon_env: prod
+  neon_region: us-west-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-west-2.aws.neon.tech
+  httpsPort: 443
+
+#metrics:
+#  enabled: true
+#  serviceMonitor:
+#    enabled: true
+#    selector:
+#      release: kube-prometheus-stack
+
+extraManifests:
+  - apiVersion: operator.victoriametrics.com/v1beta1
+    kind: VMServiceScrape
+    metadata:
+      name: "{{ include \"neon-proxy.fullname\" . }}"
+      labels:
+        helm.sh/chart: neon-proxy-{{ .Chart.Version }}
+        app.kubernetes.io/name: neon-proxy
+        app.kubernetes.io/instance: "{{ include \"neon-proxy.fullname\" . }}"
+        app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
+        app.kubernetes.io/managed-by: Helm
+      namespace: "{{ .Release.Namespace }}"
+    spec:
+      selector:
+        matchLabels:
+          app.kubernetes.io/name: "neon-proxy"
+      endpoints:
+        - port: http
+          path: /metrics
+          interval: 10s
+          scrapeTimeout: 10s
+      namespaceSelector:
+        matchNames:
+          - "{{ .Release.Namespace }}"

.github/helm-values/prod-us-west-2-eta.neon-storage-broker.yaml

@@ -0,0 +1,52 @@
+# Helm chart values for neon-storage-broker
+podLabels:
+  neon_env: production
+  neon_service: storage-broker
+
+# Use L4 LB
+service:
+  # service.annotations -- Annotations to add to the service
+  annotations:
+    service.beta.kubernetes.io/aws-load-balancer-type: external  # use newer AWS Load Balancer Controller
+    service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
+    service.beta.kubernetes.io/aws-load-balancer-scheme: internal  # deploy LB to private subnet
+    # assign service to this name at external-dns
+    external-dns.alpha.kubernetes.io/hostname: storage-broker-lb.eta.us-west-2.internal.aws.neon.tech
+  # service.type -- Service type
+  type: LoadBalancer
+  # service.port -- broker listen port
+  port: 50051
+
+ingress:
+  enabled: false
+
+metrics:
+  enabled: false
+
+extraManifests:
+  - apiVersion: operator.victoriametrics.com/v1beta1
+    kind: VMServiceScrape
+    metadata:
+      name: "{{ include \"neon-storage-broker.fullname\" . }}"
+      labels:
+        helm.sh/chart: neon-storage-broker-{{ .Chart.Version }}
+        app.kubernetes.io/name: neon-storage-broker
+        app.kubernetes.io/instance: neon-storage-broker
+        app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
+        app.kubernetes.io/managed-by: Helm
+      namespace: "{{ .Release.Namespace }}"
+    spec:
+      selector:
+        matchLabels:
+          app.kubernetes.io/name: "neon-storage-broker"
+      endpoints:
+        - port: broker
+          path: /metrics
+          interval: 10s
+          scrapeTimeout: 10s
+      namespaceSelector:
+        matchNames:
+          - "{{ .Release.Namespace }}"
+
+settings:
+  sentryEnvironment: "production"

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

@@ -1,24 +0,0 @@
-settings:
-  authBackend: "console"
-  authEndpoint: "http://console-release.local/management/api/v2"
-  domain: "*.cloud.neon.tech"
-
-podLabels:
-  zenith_service: proxy-scram
-  zenith_env: production
-  zenith_region: us-west-2
-  zenith_region_slug: oregon
-
-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: '*.cloud.neon.tech'
-
-metrics:
-  enabled: true
-  serviceMonitor:
-    enabled: true
-    selector:
-      release: kube-prometheus-stack

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

@@ -1,33 +0,0 @@
-settings:
-  authBackend: "link"
-  authEndpoint: "https://console.neon.tech/authenticate_proxy_request/"
-  uri: "https://console.neon.tech/psql_session/"
-
-# -- Additional labels for zenith-proxy pods
-podLabels:
-  zenith_service: proxy
-  zenith_env: production
-  zenith_region: us-west-2
-  zenith_region_slug: oregon
-
-service:
-  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: internal
-    external-dns.alpha.kubernetes.io/hostname: proxy-release.local
-  type: LoadBalancer
-
-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: connect.neon.tech,pg.neon.tech
-
-metrics:
-  enabled: true
-  serviceMonitor:
-    enabled: true
-    selector:
-      release: kube-prometheus-stack

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

@@ -1,31 +0,0 @@
-# Helm chart values for zenith-proxy.
-# This is a YAML-formatted file.
-
-image:
-  repository: neondatabase/neon
-
-settings:
-  authBackend: "console"
-  authEndpoint: "http://console-staging.local/management/api/v2"
-  domain: "*.cloud.stage.neon.tech"
-
-# -- Additional labels for zenith-proxy pods
-podLabels:
-  zenith_service: proxy-scram
-  zenith_env: staging
-  zenith_region: us-east-1
-  zenith_region_slug: virginia
-
-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: cloud.stage.neon.tech
-
-metrics:
-  enabled: true
-  serviceMonitor:
-    enabled: true
-    selector:
-      release: kube-prometheus-stack

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

@@ -1,31 +0,0 @@
-# Helm chart values for zenith-proxy.
-# This is a YAML-formatted file.
-
-image:
-  repository: neondatabase/neon
-
-settings:
-  authBackend: "link"
-  authEndpoint: "https://console.stage.neon.tech/authenticate_proxy_request/"
-  uri: "https://console.stage.neon.tech/psql_session/"
-
-# -- Additional labels for zenith-proxy pods
-podLabels:
-  zenith_service: proxy
-  zenith_env: staging
-  zenith_region: us-east-1
-  zenith_region_slug: virginia
-
-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: connect.stage.neon.tech
-
-metrics:
-  enabled: true
-  serviceMonitor:
-    enabled: true
-    selector:
-      release: kube-prometheus-stack

.github/pull_request_template.md

@@ -0,0 +1,14 @@
+## Describe your changes
+
+## Issue ticket number and link
+
+## Checklist before requesting a review
+
+- [ ] I have performed a self-review of my code.
+- [ ] If it is a core feature, I have added thorough tests.
+- [ ] Do we need to implement analytics? if so did you add the relevant metrics to the dashboard?
+- [ ] If this PR requires public announcement, mark it with /release-notes label and add several sentences in this section.
+
+## Checklist before merging
+
+- [ ] Do not forget to reformat commit message to not include the above checklist

.github/workflows/benchmarking.yml

@@ -15,12 +15,10 @@ on:
 
   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
+        default: 'aws-us-east-2'
       save_perf_report:
         type: boolean
         description: 'Publish perf report or not. If not set, the report is published only for the main branch'
@@ -32,102 +30,74 @@ defaults:
 
 concurrency:
   # Allow only one workflow per any non-`main` branch.
-  group: ${{ github.workflow }}-${{ github.ref }}-${{ github.ref == 'refs/heads/main' && github.sha || 'anysha' }}
+  group: ${{ github.workflow }}-${{ github.ref_name }}-${{ github.ref_name == 'main' && github.sha || 'anysha' }}
   cancel-in-progress: true
 
 jobs:
   bench:
-    # this workflow runs on self hosteed runner
-    # it's environment is quite different from usual guthub runner
-    # probably the most important difference is that it doesn't start from clean workspace each time
-    # e g if you install system packages they are not cleaned up since you install them directly in host machine
-    # not a container or something
-    # See documentation for more info: https://docs.github.com/en/actions/hosting-your-own-runners/about-self-hosted-runners
-    runs-on: [self-hosted, zenith-benchmarker]
-
     env:
-      POSTGRES_DISTRIB_DIR: /usr/pgsql
+      TEST_PG_BENCH_DURATIONS_MATRIX: "300"
+      TEST_PG_BENCH_SCALES_MATRIX: "10,100"
+      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_name == 'main' ) }}
+      PLATFORM: "neon-staging"
+
+    runs-on: [ self-hosted, us-east-2, x64 ]
+    container:
+      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
+      options: --init
 
     steps:
-    - name: Checkout zenith repo
+    - uses: actions/checkout@v3
-      uses: actions/checkout@v3
 
-    # actions/setup-python@v2 is not working correctly on self-hosted runners
+    - name: Download Neon artifact
-    # see https://github.com/actions/setup-python/issues/162
+      uses: ./.github/actions/download
-    # and probably https://github.com/actions/setup-python/issues/162#issuecomment-865387976 in particular
+      with:
-    # so the simplest solution to me is to use already installed system python and spin virtualenvs for job runs.
+        name: neon-${{ runner.os }}-release-artifact
-    # there is Python 3.7.10 already installed on the machine so use it to install poetry and then use poetry's virtuealenvs
+        path: /tmp/neon/
-    - name: Install poetry & deps
+        prefix: latest
-      run: |
-        python3 -m pip install --upgrade poetry wheel
-        # since pip/poetry caches are reused there shouldn't be any troubles with install every time
-        ./scripts/pysync
-
-    - name: Show versions
-      run: |
-        echo Python
-        python3 --version
-        poetry run python3 --version
-        echo Poetry
-        poetry --version
-        echo Pgbench
-        ${POSTGRES_DISTRIB_DIR}/v${DEFAULT_PG_VERSION}/bin/pgbench --version
 
     - name: Create Neon Project
       id: create-neon-project
       uses: ./.github/actions/neon-project-create
       with:
-        environment: ${{ github.event.inputs.environment || 'staging' }}
+        region_id: ${{ github.event.inputs.region_id || 'aws-us-east-2' }}
-        api_key: ${{ ( github.event.inputs.environment || 'staging' ) == 'staging' && secrets.NEON_STAGING_API_KEY  || secrets.NEON_CAPTEST_API_KEY }}
+        postgres_version: ${{ env.DEFAULT_PG_VERSION }}
+        api_key: ${{ secrets.NEON_STAGING_API_KEY }}
 
     - name: Run benchmark
-      # pgbench is installed system wide from official repo
+      uses: ./.github/actions/run-python-test-set
-      # https://download.postgresql.org/pub/repos/yum/13/redhat/rhel-7-x86_64/
+      with:
-      # via
+        build_type: ${{ env.BUILD_TYPE }}
-      # sudo tee /etc/yum.repos.d/pgdg.repo<<EOF
+        test_selection: performance
-      # [pgdg13]
+        run_in_parallel: false
-      # name=PostgreSQL 13 for RHEL/CentOS 7 - x86_64
+        save_perf_report: ${{ env.SAVE_PERF_REPORT }}
-      # baseurl=https://download.postgresql.org/pub/repos/yum/13/redhat/rhel-7-x86_64/
+        # Set --sparse-ordering option of pytest-order plugin
-      # enabled=1
+        # to ensure tests are running in order of appears in the file.
-      # gpgcheck=0
+        # It's important for test_perf_pgbench.py::test_pgbench_remote_* tests
-      # EOF
+        extra_params: -m remote_cluster --sparse-ordering --timeout 5400 --ignore test_runner/performance/test_perf_olap.py
-      # sudo yum makecache
-      # sudo yum install postgresql13-contrib
-      # actual binaries are located in /usr/pgsql-13/bin/
       env:
-        # The pgbench test runs two tests of given duration against each scale.
-        # So the total runtime with these parameters is 2 * 2 * 300 = 1200, or 20 minutes.
-        # Plus time needed to initialize the test databases.
-        TEST_PG_BENCH_DURATIONS_MATRIX: "300"
-        TEST_PG_BENCH_SCALES_MATRIX: "10,100"
-        PLATFORM: "neon-staging"
         BENCHMARK_CONNSTR: ${{ steps.create-neon-project.outputs.dsn }}
-        REMOTE_ENV: "1" # indicate to test harness that we do not have zenith binaries locally
-      run: |
-        # just to be sure that no data was cached on self hosted runner
-        # since it might generate duplicates when calling ingest_perf_test_result.py
-        rm -rf perf-report-staging
-        mkdir -p perf-report-staging
-        # Set --sparse-ordering option of pytest-order plugin to ensure tests are running in order of appears in the file,
-        # it's important for test_perf_pgbench.py::test_pgbench_remote_* tests
-        ./scripts/pytest test_runner/performance/ -v -m "remote_cluster" --sparse-ordering --out-dir perf-report-staging --timeout 5400
-
-    - name: Submit result
-      env:
         VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
         PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
-      run: |
-        REPORT_FROM=$(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: Create Allure report
+      if: ${{ !cancelled() }}
+      uses: ./.github/actions/allure-report
+      with:
+        action: generate
+        build_type: ${{ env.BUILD_TYPE }}
+
     - name: Post to a Slack channel
       if: ${{ github.event.schedule && failure() }}
       uses: slackapi/slack-github-action@v1
@@ -137,22 +107,65 @@ jobs:
       env:
         SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
 
+  generate-matrices:
+    # Create matrices for the benchmarking jobs, so we run benchmarks on rds only once a week (on Saturday)
+    #
+    # Available platforms:
+    # - neon-captest-new: Freshly created project (1 CU)
+    # - neon-captest-freetier: Use freetier-sized compute (0.25 CU)
+    # - neon-captest-reuse: Reusing existing project
+    # - rds-aurora: Aurora Postgres Serverless v2 with autoscaling from 0.5 to 2 ACUs
+    # - rds-postgres: RDS Postgres db.m5.large instance (2 vCPU, 8 GiB) with gp3 EBS storage
+    runs-on: ubuntu-latest
+    outputs:
+      pgbench-compare-matrix: ${{ steps.pgbench-compare-matrix.outputs.matrix }}
+      olap-compare-matrix: ${{ steps.olap-compare-matrix.outputs.matrix }}
+
+    steps:
+    - name: Generate matrix for pgbench benchmark
+      id: pgbench-compare-matrix
+      run: |
+        matrix='{
+          "platform": [
+            "neon-captest-new",
+            "neon-captest-reuse"
+          ],
+          "db_size": [ "10gb" ],
+          "include": [
+            { "platform": "neon-captest-freetier", "db_size": "3gb"  },
+            { "platform": "neon-captest-new",      "db_size": "50gb" }
+          ]
+        }'
+
+        if [ "$(date +%A)" = "Saturday" ]; then
+          matrix=$(echo $matrix | jq '.include += [{ "platform": "rds-postgres", "db_size": "10gb"},
+                                                   { "platform": "rds-aurora",   "db_size": "50gb"}]')
+        fi
+
+        echo "matrix=$(echo $matrix | jq --compact-output '.')" >> $GITHUB_OUTPUT
+
+    - name: Generate matrix for OLAP benchmarks
+      id: olap-compare-matrix
+      run: |
+        matrix='{
+          "platform": [
+            "neon-captest-reuse"
+          ]
+        }'
+
+        if [ "$(date +%A)" = "Saturday" ]; then
+          matrix=$(echo $matrix | jq '.include += [{ "platform": "rds-postgres" },
+                                                   { "platform": "rds-aurora"   }]')
+        fi
+
+        echo "matrix=$(echo $matrix | jq --compact-output '.')" >> $GITHUB_OUTPUT
+
   pgbench-compare:
+    needs: [ generate-matrices ]
+
     strategy:
       fail-fast: false
-      matrix:
+      matrix: ${{fromJson(needs.generate-matrices.outputs.pgbench-compare-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"
@@ -161,12 +174,12 @@ jobs:
       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' ) }}
+      SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref_name == 'main' ) }}
       PLATFORM: ${{ matrix.platform }}
 
-    runs-on: dev
+    runs-on: [ self-hosted, us-east-2, x64 ]
     container:
-      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rustlegacy:pinned
+      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
       options: --init
 
     timeout-minutes: 360 # 6h
@@ -187,12 +200,14 @@ jobs:
         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)
+      if: contains(fromJson('["neon-captest-new", "neon-captest-freetier"]'), matrix.platform)
       id: create-neon-project
       uses: ./.github/actions/neon-project-create
       with:
-        environment: ${{ github.event.inputs.environment || 'dev' }}
+        region_id: ${{ github.event.inputs.region_id || 'aws-us-east-2' }}
-        api_key: ${{ ( github.event.inputs.environment || 'dev' ) == 'staging' && secrets.NEON_STAGING_API_KEY  || secrets.NEON_CAPTEST_API_KEY }}
+        postgres_version: ${{ env.DEFAULT_PG_VERSION }}
+        api_key: ${{ secrets.NEON_STAGING_API_KEY }}
+        compute_units: ${{ (matrix.platform == 'neon-captest-freetier' && '[0.25, 0.25]') || '[1, 1]' }}
 
     - name: Set up Connection String
       id: set-up-connstr
@@ -201,14 +216,17 @@ jobs:
           neon-captest-reuse)
             CONNSTR=${{ secrets.BENCHMARK_CAPTEST_CONNSTR }}
             ;;
-          neon-captest-new | neon-captest-prefetch)
+          neon-captest-new | neon-captest-freetier)
             CONNSTR=${{ steps.create-neon-project.outputs.dsn }}
             ;;
           rds-aurora)
-            CONNSTR=${{ secrets.BENCHMARK_RDS_CONNSTR }}
+            CONNSTR=${{ secrets.BENCHMARK_RDS_AURORA_CONNSTR }}
+            ;;
+          rds-postgres)
+            CONNSTR=${{ secrets.BENCHMARK_RDS_POSTGRES_CONNSTR }}
             ;;
           *)
-            echo 2>&1 "Unknown PLATFORM=${PLATFORM}. Allowed only 'neon-captest-reuse', 'neon-captest-new', 'neon-captest-prefetch' or 'rds-aurora'"
+            echo >&2 "Unknown PLATFORM=${PLATFORM}. Allowed only 'neon-captest-reuse', 'neon-captest-new', 'neon-captest-freetier', 'rds-aurora', or 'rds-postgres'"
             exit 1
             ;;
         esac
@@ -217,14 +235,6 @@ jobs:
 
         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: ${{ steps.set-up-connstr.outputs.connstr }}
-
     - name: Benchmark init
       uses: ./.github/actions/run-python-test-set
       with:
@@ -264,20 +274,19 @@ jobs:
         VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
         PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
 
-    - name: Create Allure report
-      if: always()
-      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 }}
+        api_key: ${{ secrets.NEON_STAGING_API_KEY }}
+
+    - name: Create Allure report
+      if: ${{ !cancelled() }}
+      uses: ./.github/actions/allure-report
+      with:
+        action: generate
+        build_type: ${{ env.BUILD_TYPE }}
 
     - name: Post to a Slack channel
       if: ${{ github.event.schedule && failure() }}
@@ -287,3 +296,286 @@ jobs:
         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 }}
+
+  clickbench-compare:
+    # ClichBench DB for rds-aurora and rds-Postgres deployed to the same clusters
+    # we use for performance testing in pgbench-compare.
+    # Run this job only when pgbench-compare is finished to avoid the intersection.
+    # We might change it after https://github.com/neondatabase/neon/issues/2900.
+    #
+    # *_CLICKBENCH_CONNSTR: Genuine ClickBench DB with ~100M rows
+    # *_CLICKBENCH_10M_CONNSTR: DB with the first 10M rows of ClickBench DB
+    if: ${{ !cancelled() }}
+    needs: [ generate-matrices, pgbench-compare ]
+
+    strategy:
+      fail-fast: false
+      matrix: ${{ fromJson(needs.generate-matrices.outputs.olap-compare-matrix) }}
+
+    env:
+      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_name == 'main' ) }}
+      PLATFORM: ${{ matrix.platform }}
+
+    runs-on: [ self-hosted, us-east-2, x64 ]
+    container:
+      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
+      options: --init
+
+    timeout-minutes: 360 # 6h
+
+    steps:
+    - uses: actions/checkout@v3
+
+    - name: Download Neon artifact
+      uses: ./.github/actions/download
+      with:
+        name: neon-${{ 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" >> $GITHUB_PATH
+
+    - name: Set up Connection String
+      id: set-up-connstr
+      run: |
+        case "${PLATFORM}" in
+          neon-captest-reuse)
+            CONNSTR=${{ secrets.BENCHMARK_CAPTEST_CLICKBENCH_10M_CONNSTR }}
+            ;;
+          rds-aurora)
+            CONNSTR=${{ secrets.BENCHMARK_RDS_AURORA_CLICKBENCH_10M_CONNSTR }}
+            ;;
+          rds-postgres)
+            CONNSTR=${{ secrets.BENCHMARK_RDS_POSTGRES_CLICKBENCH_10M_CONNSTR }}
+            ;;
+          *)
+            echo >&2 "Unknown PLATFORM=${PLATFORM}. Allowed only 'neon-captest-reuse', 'rds-aurora', or 'rds-postgres'"
+            exit 1
+            ;;
+        esac
+
+        echo "connstr=${CONNSTR}" >> $GITHUB_OUTPUT
+
+        psql ${CONNSTR} -c "SELECT version();"
+
+    - name: ClickBench benchmark
+      uses: ./.github/actions/run-python-test-set
+      with:
+        build_type: ${{ env.BUILD_TYPE }}
+        test_selection: performance/test_perf_olap.py
+        run_in_parallel: false
+        save_perf_report: ${{ env.SAVE_PERF_REPORT }}
+        extra_params: -m remote_cluster --timeout 21600 -k test_clickbench
+      env:
+        VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
+        PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
+        BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
+
+    - name: Create Allure report
+      if: ${{ !cancelled() }}
+      uses: ./.github/actions/allure-report
+      with:
+        action: generate
+        build_type: ${{ env.BUILD_TYPE }}
+
+    - 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 OLAP 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 }}
+
+  tpch-compare:
+    # TCP-H DB for rds-aurora and rds-Postgres deployed to the same clusters
+    # we use for performance testing in pgbench-compare & clickbench-compare.
+    # Run this job only when clickbench-compare is finished to avoid the intersection.
+    # We might change it after https://github.com/neondatabase/neon/issues/2900.
+    #
+    # *_TPCH_S10_CONNSTR: DB generated with scale factor 10 (~10 GB)
+    if: ${{ !cancelled() }}
+    needs: [ generate-matrices, clickbench-compare ]
+
+    strategy:
+      fail-fast: false
+      matrix: ${{ fromJson(needs.generate-matrices.outputs.olap-compare-matrix) }}
+
+    env:
+      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_name == 'main' ) }}
+      PLATFORM: ${{ matrix.platform }}
+
+    runs-on: [ self-hosted, us-east-2, x64 ]
+    container:
+      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
+      options: --init
+
+    timeout-minutes: 360 # 6h
+
+    steps:
+    - uses: actions/checkout@v3
+
+    - name: Download Neon artifact
+      uses: ./.github/actions/download
+      with:
+        name: neon-${{ 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" >> $GITHUB_PATH
+
+    - name: Set up Connection String
+      id: set-up-connstr
+      run: |
+        case "${PLATFORM}" in
+          neon-captest-reuse)
+            CONNSTR=${{ secrets.BENCHMARK_CAPTEST_TPCH_S10_CONNSTR }}
+            ;;
+          rds-aurora)
+            CONNSTR=${{ secrets.BENCHMARK_RDS_AURORA_TPCH_S10_CONNSTR }}
+            ;;
+          rds-postgres)
+            CONNSTR=${{ secrets.BENCHMARK_RDS_POSTGRES_TPCH_S10_CONNSTR }}
+            ;;
+          *)
+            echo >&2 "Unknown PLATFORM=${PLATFORM}. Allowed only 'neon-captest-reuse', 'rds-aurora', or 'rds-postgres'"
+            exit 1
+            ;;
+        esac
+
+        echo "connstr=${CONNSTR}" >> $GITHUB_OUTPUT
+
+        psql ${CONNSTR} -c "SELECT version();"
+
+    - name: Run TPC-H benchmark
+      uses: ./.github/actions/run-python-test-set
+      with:
+        build_type: ${{ env.BUILD_TYPE }}
+        test_selection: performance/test_perf_olap.py
+        run_in_parallel: false
+        save_perf_report: ${{ env.SAVE_PERF_REPORT }}
+        extra_params: -m remote_cluster --timeout 21600 -k test_tpch
+      env:
+        VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
+        PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
+        BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
+
+    - name: Create Allure report
+      if: ${{ !cancelled() }}
+      uses: ./.github/actions/allure-report
+      with:
+        action: generate
+        build_type: ${{ env.BUILD_TYPE }}
+
+    - 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 TPC-H 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 }}
+
+  user-examples-compare:
+    if: ${{ !cancelled() }}
+    needs: [ generate-matrices, tpch-compare ]
+
+    strategy:
+      fail-fast: false
+      matrix: ${{ fromJson(needs.generate-matrices.outputs.olap-compare-matrix) }}
+
+    env:
+      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_name == 'main' ) }}
+      PLATFORM: ${{ matrix.platform }}
+
+    runs-on: [ self-hosted, us-east-2, x64 ]
+    container:
+      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
+      options: --init
+
+    timeout-minutes: 360 # 6h
+
+    steps:
+    - uses: actions/checkout@v3
+
+    - name: Download Neon artifact
+      uses: ./.github/actions/download
+      with:
+        name: neon-${{ 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" >> $GITHUB_PATH
+
+    - name: Set up Connection String
+      id: set-up-connstr
+      run: |
+        case "${PLATFORM}" in
+          neon-captest-reuse)
+            CONNSTR=${{ secrets.BENCHMARK_USER_EXAMPLE_CAPTEST_CONNSTR }}
+            ;;
+          rds-aurora)
+            CONNSTR=${{ secrets.BENCHMARK_USER_EXAMPLE_RDS_AURORA_CONNSTR }}
+            ;;
+          rds-postgres)
+            CONNSTR=${{ secrets.BENCHMARK_USER_EXAMPLE_RDS_POSTGRES_CONNSTR }}
+            ;;
+          *)
+            echo >&2 "Unknown PLATFORM=${PLATFORM}. Allowed only 'neon-captest-reuse', 'rds-aurora', or 'rds-postgres'"
+            exit 1
+            ;;
+        esac
+
+        echo "connstr=${CONNSTR}" >> $GITHUB_OUTPUT
+
+        psql ${CONNSTR} -c "SELECT version();"
+
+    - name: Run user examples
+      uses: ./.github/actions/run-python-test-set
+      with:
+        build_type: ${{ env.BUILD_TYPE }}
+        test_selection: performance/test_perf_olap.py
+        run_in_parallel: false
+        save_perf_report: ${{ env.SAVE_PERF_REPORT }}
+        extra_params: -m remote_cluster --timeout 21600 -k test_user_examples
+      env:
+        VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
+        PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
+        BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
+
+    - name: Create Allure report
+      if: ${{ !cancelled() }}
+      uses: ./.github/actions/allure-report
+      with:
+        action: generate
+        build_type: ${{ env.BUILD_TYPE }}
+
+    - 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 TPC-H 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

@@ -1,166 +0,0 @@
-name: Check code style and build
-
-on:
-  push:
-    branches:
-    - main
-  pull_request:
-
-defaults:
-  run:
-    shell: bash -euxo pipefail {0}
-
-concurrency:
-  # Allow only one workflow per any non-`main` branch.
-  group: ${{ github.workflow }}-${{ github.ref }}-${{ github.ref == 'refs/heads/main' && github.sha || 'anysha' }}
-  cancel-in-progress: true
-
-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.
-        os: [ubuntu-latest, macos-latest]
-    timeout-minutes: 90
-    name: check codestyle rust and postgres
-    runs-on: ${{ matrix.os }}
-
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-        with:
-          submodules: true
-          fetch-depth: 2
-
-      - name: Check formatting
-        run: cargo fmt --all -- --check
-
-      - name: Install Ubuntu postgres dependencies
-        if: matrix.os == 'ubuntu-latest'
-        run: |
-          sudo apt update
-          sudo apt install build-essential libreadline-dev zlib1g-dev flex bison libseccomp-dev libssl-dev
-
-      - name: Install macOS postgres dependencies
-        if: matrix.os == 'macos-latest'
-        run: brew install flex bison openssl
-
-      - name: Set pg 14 revision for caching
-        id: pg_v14_rev
-        run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v14) >> $GITHUB_OUTPUT
-        shell: bash -euxo pipefail {0}
-
-      - name: Set pg 15 revision for caching
-        id: pg_v15_rev
-        run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v15) >> $GITHUB_OUTPUT
-        shell: bash -euxo pipefail {0}
-
-      - name: Cache postgres v14 build
-        id: cache_pg_14
-        uses: actions/cache@v3
-        with:
-          path: pg_install/v14
-          key: v1-${{ 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') }}
-
-      - name: Set extra env for macOS
-        if: matrix.os == 'macos-latest'
-        run: |
-          echo 'LDFLAGS=-L/usr/local/opt/openssl@3/lib' >> $GITHUB_ENV
-          echo 'CPPFLAGS=-I/usr/local/opt/openssl@3/include' >> $GITHUB_ENV
-
-      - name: Build postgres v14
-        if: steps.cache_pg_14.outputs.cache-hit != 'true'
-        run: make postgres-v14
-        shell: bash -euxo pipefail {0}
-
-      - name: Build postgres v15
-        if: steps.cache_pg_15.outputs.cache-hit != 'true'
-        run: make postgres-v15
-        shell: bash -euxo pipefail {0}
-
-      - name: Build neon extensions
-        run: make neon-pg-ext
-
-      - name: Cache cargo deps
-        id: cache_cargo
-        uses: actions/cache@v3
-        with:
-          path: |
-            ~/.cargo/registry
-            !~/.cargo/registry/src
-            ~/.cargo/git
-            target
-          key: v5-${{ runner.os }}-cargo-${{ hashFiles('./Cargo.lock') }}-rust
-
-      - name: Run cargo clippy
-        run: ./run_clippy.sh
-
-      - name: Ensure all project builds
-        run: cargo build --locked --all --all-targets
-
-  check-rust-dependencies:
-    runs-on: dev
-    container:
-      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
-      options: --init
-
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-        with:
-          submodules: false
-          fetch-depth: 1
-
-      # https://github.com/facebookincubator/cargo-guppy/tree/bec4e0eb29dcd1faac70b1b5360267fc02bf830e/tools/cargo-hakari#2-keep-the-workspace-hack-up-to-date-in-ci
-      - name: Check every project module is covered by Hakari
-        run: |
-          cargo hakari generate --diff  # workspace-hack Cargo.toml is up-to-date
-          cargo hakari manage-deps --dry-run  # all workspace crates depend on workspace-hack
-        shell: bash -euxo pipefail {0}
-
-  check-codestyle-python:
-    runs-on: [ self-hosted, Linux, k8s-runner ]
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-        with:
-          submodules: false
-          fetch-depth: 1
-
-      - name: Cache poetry deps
-        id: cache_poetry
-        uses: actions/cache@v3
-        with:
-          path: ~/.cache/pypoetry/virtualenvs
-          key: v1-codestyle-python-deps-${{ hashFiles('poetry.lock') }}
-
-      - 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 mypy to check types
-        run: poetry run mypy .

.github/workflows/deploy-dev.yml

@@ -0,0 +1,179 @@
+name: Neon Deploy dev
+
+on:
+  workflow_dispatch:
+    inputs:
+      dockerTag:
+        description: 'Docker tag to deploy'
+        required: true
+        type: string
+      branch:
+        description: 'Branch or commit used for deploy scripts and configs'
+        required: true
+        type: string
+        default: 'main'
+      deployStorage:
+        description: 'Deploy storage'
+        required: true
+        type: boolean
+        default: true
+      deployProxy:
+        description: 'Deploy proxy'
+        required: true
+        type: boolean
+        default: true
+      deployStorageBroker:
+        description: 'Deploy storage-broker'
+        required: true
+        type: boolean
+        default: true
+
+env:
+  AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_DEV }}
+  AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_KEY_DEV }}
+
+concurrency:
+  group: deploy-dev
+  cancel-in-progress: false
+
+jobs:
+  deploy-storage-new:
+    runs-on: [ self-hosted, gen3, small ]
+    container:
+      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/ansible:pinned
+      options: --user root --privileged
+    if: inputs.deployStorage
+    defaults:
+      run:
+        shell: bash
+    strategy:
+      matrix:
+        target_region: [ eu-west-1, us-east-2 ]
+    environment:
+      name: dev-${{ matrix.target_region }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          submodules: true
+          fetch-depth: 0
+          ref: ${{ inputs.branch }}
+
+      - name: Redeploy
+        run: |
+          export DOCKER_TAG=${{ inputs.dockerTag }}
+          cd "$(pwd)/.github/ansible"
+
+          ./get_binaries.sh
+
+          ansible-galaxy collection install sivel.toiletwater
+          ansible-playbook -v deploy.yaml -i staging.${{ matrix.target_region }}.hosts.yaml -e @ssm_config -e CONSOLE_API_TOKEN=${{ secrets.NEON_STAGING_API_KEY }} -e SENTRY_URL_PAGESERVER=${{ secrets.SENTRY_URL_PAGESERVER }} -e SENTRY_URL_SAFEKEEPER=${{ secrets.SENTRY_URL_SAFEKEEPER }}
+          rm -f neon_install.tar.gz .neon_current_version
+
+      - name: Cleanup ansible folder
+        run: rm -rf ~/.ansible
+
+  deploy-proxy-new:
+    runs-on: [ self-hosted, gen3, small ]
+    container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/ansible:pinned
+    if: inputs.deployProxy
+    defaults:
+      run:
+        shell: bash
+    strategy:
+      matrix:
+        include:
+          - target_region:  us-east-2
+            target_cluster: dev-us-east-2-beta
+            deploy_link_proxy: true
+            deploy_legacy_scram_proxy: true
+          - target_region:  eu-west-1
+            target_cluster: dev-eu-west-1-zeta
+            deploy_link_proxy: false
+            deploy_legacy_scram_proxy: false
+    environment:
+      name: dev-${{ matrix.target_region }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          submodules: true
+          fetch-depth: 0
+          ref: ${{ inputs.branch }}
+  
+      - name: Configure AWS Credentials
+        uses: aws-actions/configure-aws-credentials@v1-node16
+        with:
+          role-to-assume: arn:aws:iam::369495373322:role/github-runner
+          aws-region: eu-central-1
+          role-skip-session-tagging: true
+          role-duration-seconds: 1800
+  
+      - name: Configure environment
+        run: |
+          helm repo add neondatabase https://neondatabase.github.io/helm-charts
+          aws --region ${{ matrix.target_region }} eks update-kubeconfig --name  ${{ matrix.target_cluster }}
+  
+      - name: Re-deploy scram proxy
+        run: |
+          DOCKER_TAG=${{ inputs.dockerTag }}
+          helm upgrade neon-proxy-scram neondatabase/neon-proxy --namespace neon-proxy --create-namespace --install --atomic -f .github/helm-values/${{ matrix.target_cluster }}.neon-proxy-scram.yaml --set image.tag=${DOCKER_TAG} --set settings.sentryUrl=${{ secrets.SENTRY_URL_PROXY }} --wait --timeout 15m0s
+  
+      - name: Re-deploy link proxy
+        if: matrix.deploy_link_proxy
+        run: |
+          DOCKER_TAG=${{ inputs.dockerTag }}
+          helm upgrade neon-proxy-link neondatabase/neon-proxy --namespace neon-proxy --create-namespace --install --atomic -f .github/helm-values/${{ matrix.target_cluster }}.neon-proxy-link.yaml --set image.tag=${DOCKER_TAG} --set settings.sentryUrl=${{ secrets.SENTRY_URL_PROXY }} --wait --timeout 15m0s
+  
+      - name: Re-deploy legacy scram proxy
+        if: matrix.deploy_legacy_scram_proxy
+        run: |
+          DOCKER_TAG=${{ inputs.dockerTag }}
+          helm upgrade neon-proxy-scram-legacy neondatabase/neon-proxy --namespace neon-proxy --create-namespace --install --atomic -f .github/helm-values/${{ matrix.target_cluster }}.neon-proxy-scram-legacy.yaml --set image.tag=${DOCKER_TAG} --set settings.sentryUrl=${{ secrets.SENTRY_URL_PROXY }} --wait --timeout 15m0s
+  
+      - name: Cleanup helm folder
+        run: rm -rf ~/.cache
+  
+  deploy-storage-broker-new:
+    runs-on: [ self-hosted, gen3, small ]
+    container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/ansible:pinned
+    if: inputs.deployStorageBroker
+    defaults:
+      run:
+        shell: bash
+    strategy:
+      matrix:
+        include:
+          - target_region:  us-east-2
+            target_cluster: dev-us-east-2-beta
+          - target_region:  eu-west-1
+            target_cluster: dev-eu-west-1-zeta
+    environment:
+      name: dev-${{ matrix.target_region }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          submodules: true
+          fetch-depth: 0
+          ref: ${{ inputs.branch }}
+  
+      - name: Configure AWS Credentials
+        uses: aws-actions/configure-aws-credentials@v1-node16
+        with:
+          role-to-assume: arn:aws:iam::369495373322:role/github-runner
+          aws-region: eu-central-1
+          role-skip-session-tagging: true
+          role-duration-seconds: 1800
+  
+      - name: Configure environment
+        run: |
+          helm repo add neondatabase https://neondatabase.github.io/helm-charts
+          aws --region ${{ matrix.target_region }} eks update-kubeconfig --name  ${{ matrix.target_cluster }}
+  
+      - name: Deploy storage-broker
+        run:
+          helm upgrade neon-storage-broker-lb neondatabase/neon-storage-broker --namespace neon-storage-broker-lb --create-namespace --install --atomic -f .github/helm-values/${{ matrix.target_cluster }}.neon-storage-broker.yaml --set image.tag=${{ inputs.dockerTag }} --set settings.sentryUrl=${{ secrets.SENTRY_URL_BROKER }} --wait --timeout 5m0s
+  
+      - name: Cleanup helm folder
+        run: rm -rf ~/.cache

.github/workflows/deploy-prod.yml

@@ -0,0 +1,167 @@
+name: Neon Deploy prod
+
+on:
+  workflow_dispatch:
+    inputs:
+      dockerTag:
+        description: 'Docker tag to deploy'
+        required: true
+        type: string
+      branch:
+        description: 'Branch or commit used for deploy scripts and configs'
+        required: true
+        type: string
+        default: 'release'
+      deployStorage:
+        description: 'Deploy storage'
+        required: true
+        type: boolean
+        default: true
+      deployProxy:
+        description: 'Deploy proxy'
+        required: true
+        type: boolean
+        default: true
+      deployStorageBroker:
+        description: 'Deploy storage-broker'
+        required: true
+        type: boolean
+        default: true
+      disclamerAcknowledged:
+        description: 'I confirm that there is an emergency and I can not use regular release workflow'
+        required: true
+        type: boolean
+        default: false
+
+concurrency:
+  group: deploy-prod
+  cancel-in-progress: false
+
+jobs:
+  deploy-prod-new:
+    runs-on: prod
+    container:
+      image: 093970136003.dkr.ecr.eu-central-1.amazonaws.com/ansible:latest
+      options: --user root --privileged
+    if: inputs.deployStorage && inputs.disclamerAcknowledged
+    defaults:
+      run:
+        shell: bash
+    strategy:
+      matrix:
+        target_region: [ us-east-2, us-west-2, eu-central-1, ap-southeast-1 ]
+    environment:
+      name: prod-${{ matrix.target_region }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          submodules: true
+          fetch-depth: 0
+          ref: ${{ inputs.branch }}
+
+      - name: Redeploy
+        run: |
+          export DOCKER_TAG=${{ inputs.dockerTag }}
+          cd "$(pwd)/.github/ansible"
+
+          ./get_binaries.sh
+
+          ansible-galaxy collection install sivel.toiletwater
+          ansible-playbook -v deploy.yaml -i prod.${{ matrix.target_region }}.hosts.yaml -e @ssm_config -e CONSOLE_API_TOKEN=${{ secrets.NEON_PRODUCTION_API_KEY }} -e SENTRY_URL_PAGESERVER=${{ secrets.SENTRY_URL_PAGESERVER }} -e SENTRY_URL_SAFEKEEPER=${{ secrets.SENTRY_URL_SAFEKEEPER }}
+          rm -f neon_install.tar.gz .neon_current_version
+
+  deploy-proxy-prod-new:
+    runs-on: prod
+    container: 093970136003.dkr.ecr.eu-central-1.amazonaws.com/ansible:latest
+    if: inputs.deployProxy && inputs.disclamerAcknowledged
+    defaults:
+      run:
+        shell: bash
+    strategy:
+      matrix:
+        include:
+          - target_region:  us-east-2
+            target_cluster: prod-us-east-2-delta
+            deploy_link_proxy: true
+            deploy_legacy_scram_proxy: false
+          - target_region:  us-west-2
+            target_cluster: prod-us-west-2-eta
+            deploy_link_proxy: false
+            deploy_legacy_scram_proxy: true
+          - target_region: eu-central-1
+            target_cluster: prod-eu-central-1-gamma
+            deploy_link_proxy: false
+            deploy_legacy_scram_proxy: false
+          - target_region: ap-southeast-1
+            target_cluster: prod-ap-southeast-1-epsilon
+            deploy_link_proxy: false
+            deploy_legacy_scram_proxy: false
+    environment:
+      name: prod-${{ matrix.target_region }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          submodules: true
+          fetch-depth: 0
+          ref: ${{ inputs.branch }}
+
+      - name: Configure environment
+        run: |
+          helm repo add neondatabase https://neondatabase.github.io/helm-charts
+          aws --region ${{ matrix.target_region }} eks update-kubeconfig --name  ${{ matrix.target_cluster }}
+
+      - name: Re-deploy scram proxy
+        run: |
+          DOCKER_TAG=${{ inputs.dockerTag }}
+          helm upgrade neon-proxy-scram neondatabase/neon-proxy --namespace neon-proxy --create-namespace --install --atomic -f .github/helm-values/${{ matrix.target_cluster }}.neon-proxy-scram.yaml --set image.tag=${DOCKER_TAG} --set settings.sentryUrl=${{ secrets.SENTRY_URL_PROXY }} --wait --timeout 15m0s
+
+      - name: Re-deploy link proxy
+        if: matrix.deploy_link_proxy
+        run: |
+          DOCKER_TAG=${{ inputs.dockerTag }}
+          helm upgrade neon-proxy-link neondatabase/neon-proxy --namespace neon-proxy --create-namespace --install --atomic -f .github/helm-values/${{ matrix.target_cluster }}.neon-proxy-link.yaml --set image.tag=${DOCKER_TAG} --set settings.sentryUrl=${{ secrets.SENTRY_URL_PROXY }} --wait --timeout 15m0s
+
+      - name: Re-deploy legacy scram proxy
+        if: matrix.deploy_legacy_scram_proxy
+        run: |
+          DOCKER_TAG=${{ inputs.dockerTag }}
+          helm upgrade neon-proxy-scram-legacy neondatabase/neon-proxy --namespace neon-proxy --create-namespace --install --atomic -f .github/helm-values/${{ matrix.target_cluster }}.neon-proxy-scram-legacy.yaml --set image.tag=${DOCKER_TAG} --set settings.sentryUrl=${{ secrets.SENTRY_URL_PROXY }} --wait --timeout 15m0s
+
+  deploy-storage-broker-prod-new:
+    runs-on: prod
+    container: 093970136003.dkr.ecr.eu-central-1.amazonaws.com/ansible:latest
+    if: inputs.deployStorageBroker && inputs.disclamerAcknowledged
+    defaults:
+      run:
+        shell: bash
+    strategy:
+      matrix:
+        include:
+          - target_region:  us-east-2
+            target_cluster: prod-us-east-2-delta
+          - target_region:  us-west-2
+            target_cluster: prod-us-west-2-eta
+          - target_region: eu-central-1
+            target_cluster: prod-eu-central-1-gamma
+          - target_region: ap-southeast-1
+            target_cluster: prod-ap-southeast-1-epsilon
+    environment:
+      name: prod-${{ matrix.target_region }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          submodules: true
+          fetch-depth: 0
+          ref: ${{ inputs.branch }}
+
+      - name: Configure environment
+        run: |
+          helm repo add neondatabase https://neondatabase.github.io/helm-charts
+          aws --region ${{ matrix.target_region }} eks update-kubeconfig --name  ${{ matrix.target_cluster }}
+
+      - name: Deploy storage-broker
+        run:
+          helm upgrade neon-storage-broker-lb neondatabase/neon-storage-broker --namespace neon-storage-broker-lb --create-namespace --install --atomic -f .github/helm-values/${{ matrix.target_cluster }}.neon-storage-broker.yaml --set image.tag=${{ inputs.dockerTag }} --set settings.sentryUrl=${{ secrets.SENTRY_URL_BROKER }} --wait --timeout 5m0s

.github/workflows/neon_extra_builds.yml

@@ -0,0 +1,154 @@
+name: Check neon with extra platform builds
+
+on:
+  push:
+    branches:
+    - main
+  pull_request:
+
+defaults:
+  run:
+    shell: bash -euxo pipefail {0}
+
+concurrency:
+  # Allow only one workflow per any non-`main` branch.
+  group: ${{ github.workflow }}-${{ github.ref_name }}-${{ github.ref_name == 'main' && github.sha || 'anysha' }}
+  cancel-in-progress: true
+
+env:
+  RUST_BACKTRACE: 1
+  COPT: '-Werror'
+
+jobs:
+  check-macos-build:
+    if: github.ref_name == 'main' || contains(github.event.pull_request.labels.*.name, 'run-extra-build-macos')
+    timeout-minutes: 90
+    runs-on: macos-latest
+
+    env:
+      # Use release build only, to have less debug info around
+      # Hence keeping target/ (and general cache size) smaller
+      BUILD_TYPE: release
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          submodules: true
+          fetch-depth: 1
+
+      - name: Install macOS postgres dependencies
+        run: brew install flex bison openssl protobuf
+
+      - name: Set pg 14 revision for caching
+        id: pg_v14_rev
+        run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v14) >> $GITHUB_OUTPUT
+
+      - name: Set pg 15 revision for caching
+        id: pg_v15_rev
+        run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v15) >> $GITHUB_OUTPUT
+
+      - name: Cache postgres v14 build
+        id: cache_pg_14
+        uses: actions/cache@v3
+        with:
+          path: pg_install/v14
+          key: v1-${{ runner.os }}-${{ env.BUILD_TYPE }}-pg-${{ 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 }}-${{ env.BUILD_TYPE }}-pg-${{ steps.pg_v15_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
+
+      - name: Set extra env for macOS
+        run: |
+          echo 'LDFLAGS=-L/usr/local/opt/openssl@3/lib' >> $GITHUB_ENV
+          echo 'CPPFLAGS=-I/usr/local/opt/openssl@3/include' >> $GITHUB_ENV
+
+      - name: Cache cargo deps
+        uses: actions/cache@v3
+        with:
+          path: |
+            ~/.cargo/registry
+            !~/.cargo/registry/src
+            ~/.cargo/git
+            target
+          key: v1-${{ runner.os }}-cargo-${{ hashFiles('./Cargo.lock') }}-${{ hashFiles('./rust-toolchain.toml') }}-rust
+
+      - name: Build postgres v14
+        if: steps.cache_pg_14.outputs.cache-hit != 'true'
+        run: make postgres-v14 -j$(nproc)
+
+      - name: Build postgres v15
+        if: steps.cache_pg_15.outputs.cache-hit != 'true'
+        run: make postgres-v15 -j$(nproc)
+
+      - name: Build neon extensions
+        run: make neon-pg-ext -j$(nproc)
+
+      - name: Run cargo build
+        run: cargo build --all --release
+
+      - name: Check that no warnings are produced
+        run: ./run_clippy.sh
+
+  gather-rust-build-stats:
+    if: github.ref_name == 'main' || contains(github.event.pull_request.labels.*.name, 'run-extra-build-stats')
+    runs-on: [ self-hosted, gen3, large ]
+    container:
+      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
+      options: --init
+
+    env:
+      BUILD_TYPE: release
+      # remove the cachepot wrapper and build without crate caches
+      RUSTC_WRAPPER: ""
+      # build with incremental compilation produce partial results
+      # so do not attempt to cache this build, also disable the incremental compilation
+      CARGO_INCREMENTAL: 0
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          submodules: true
+          fetch-depth: 1
+
+      # Some of our rust modules use FFI and need those to be checked
+      - name: Get postgres headers
+        run: make postgres-headers -j$(nproc)
+
+      - name: Produce the build stats
+        run: cargo build --all --release --timings
+
+      - name: Upload the build stats
+        id: upload-stats
+        env:
+          BUCKET: neon-github-public-dev
+          SHA: ${{ github.event.pull_request.head.sha || github.sha }}
+          AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_DEV }}
+          AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_KEY_DEV }}
+        run: |
+          REPORT_URL=https://${BUCKET}.s3.amazonaws.com/build-stats/${SHA}/${GITHUB_RUN_ID}/cargo-timing.html
+          aws s3 cp --only-show-errors ./target/cargo-timings/cargo-timing.html "s3://${BUCKET}/build-stats/${SHA}/${GITHUB_RUN_ID}/"
+          echo "report-url=${REPORT_URL}" >> $GITHUB_OUTPUT
+
+      - name: Publish build stats report
+        uses: actions/github-script@v6
+        env:
+          REPORT_URL: ${{ steps.upload-stats.outputs.report-url }}
+          SHA: ${{ github.event.pull_request.head.sha || github.sha }}
+        with:
+          script: |
+            const { REPORT_URL, SHA } = process.env
+
+            await github.rest.repos.createCommitStatus({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              sha: `${SHA}`,
+              state: 'success',
+              target_url: `${REPORT_URL}`,
+              context: `Build stats (release)`,
+            })

.github/workflows/pg_clients.yml

@@ -14,7 +14,7 @@ on:
 
 concurrency:
   # Allow only one workflow per any non-`main` branch.
-  group: ${{ github.workflow }}-${{ github.ref }}-${{ github.ref == 'refs/heads/main' && github.sha || 'anysha' }}
+  group: ${{ github.workflow }}-${{ github.ref_name }}-${{ github.ref_name == 'main' && github.sha || 'anysha' }}
   cancel-in-progress: true
 
 jobs:
@@ -23,6 +23,7 @@ jobs:
     runs-on: [ ubuntu-latest ]
 
     env:
+      DEFAULT_PG_VERSION: 14
       TEST_OUTPUT: /tmp/test_output
 
     steps:
@@ -51,8 +52,8 @@ jobs:
       id: create-neon-project
       uses: ./.github/actions/neon-project-create
       with:
-        environment: staging
         api_key: ${{ secrets.NEON_STAGING_API_KEY }}
+        postgres_version: ${{ env.DEFAULT_PG_VERSION }}
 
     - name: Run pytest
       env:
@@ -63,7 +64,7 @@ jobs:
       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 "$POSTGRES_DISTRIB_DIR/v${DEFAULT_PG_VERSION}/bin" && touch "$POSTGRES_DISTRIB_DIR/v${DEFAULT_PG_VERSION}/bin/psql";
         ./scripts/pytest \
           --junitxml=$TEST_OUTPUT/junit.xml \
           --tb=short \
@@ -75,7 +76,6 @@ jobs:
       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 }}
 

.github/workflows/release.yml

@@ -0,0 +1,33 @@
+name: Create Release Branch
+
+on:
+  schedule:
+    - cron: '0 10 * * 2'
+
+jobs:
+  create_release_branch:
+    runs-on: [ubuntu-latest]
+
+    steps:
+    - name: Check out code
+      uses: actions/checkout@v3
+      with:
+        ref: main
+
+    - name: Get current date
+      id: date
+      run: echo "date=$(date +'%Y-%m-%d')" >> $GITHUB_OUTPUT
+
+    - name: Create release branch
+      run: git checkout -b releases/${{ steps.date.outputs.date }}
+
+    - name: Push new branch
+      run: git push origin releases/${{ steps.date.outputs.date }}
+
+    - name: Create pull request into release
+      uses: thomaseizinger/create-pull-request@e3972219c86a56550fb70708d96800d8e24ba862 # 1.3.0
+      with:
+        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        head: releases/${{ steps.date.outputs.date }}
+        base: release
+        title: Release ${{ steps.date.outputs.date }}

.gitmodules

@@ -1,7 +1,7 @@
 [submodule "vendor/postgres-v14"]
 	path = vendor/postgres-v14
 	url = https://github.com/neondatabase/postgres.git
-	branch = main
+	branch = REL_14_STABLE_neon
 [submodule "vendor/postgres-v15"]
 	path = vendor/postgres-v15
 	url = https://github.com/neondatabase/postgres.git

CODEOWNERS

@@ -0,0 +1,11 @@
+/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
+/vendor/ @neondatabase/compute

Cargo.toml

@@ -1,14 +1,3 @@
-# '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 = [
     "compute_tools",
@@ -16,15 +5,176 @@ members = [
     "pageserver",
     "proxy",
     "safekeeper",
+    "storage_broker",
     "workspace_hack",
+    "trace",
     "libs/*",
 ]
 
+[workspace.package]
+edition = "2021"
+license = "Apache-2.0"
+
+## All dependency versions, used in the project
+[workspace.dependencies]
+anyhow = { version = "1.0", features = ["backtrace"] }
+async-stream = "0.3"
+async-trait = "0.1"
+atty = "0.2.14"
+aws-config = { version = "0.51.0", default-features = false, features=["rustls"] }
+aws-sdk-s3 = "0.21.0"
+aws-smithy-http = "0.51.0"
+aws-types = "0.55"
+base64 = "0.13.0"
+bincode = "1.3"
+bindgen = "0.65"
+bstr = "1.0"
+byteorder = "1.4"
+bytes = "1.0"
+chrono = { version = "0.4", default-features = false, features = ["clock"] }
+clap = { version = "4.0", features = ["derive"] }
+close_fds = "0.3.2"
+comfy-table = "6.1"
+const_format = "0.2"
+crc32c = "0.6"
+crossbeam-utils = "0.8.5"
+either = "1.8"
+enum-map = "2.4.2"
+enumset = "1.0.12"
+fail = "0.5.0"
+fs2 = "0.4.3"
+futures = "0.3"
+futures-core = "0.3"
+futures-util = "0.3"
+git-version = "0.3"
+hashbrown = "0.13"
+hashlink = "0.8.1"
+hex = "0.4"
+hex-literal = "0.4"
+hmac = "0.12.1"
+hostname = "0.3.1"
+humantime = "2.1"
+humantime-serde = "1.1.1"
+hyper = { version = "0.14",  features = ["http2", "tcp", "runtime", "http1"]}
+hyper-tungstenite = "0.9"
+itertools = "0.10"
+jsonwebtoken = "8"
+libc = "0.2"
+md5 = "0.7.0"
+memoffset = "0.8"
+nix = "0.26"
+notify = "5.0.0"
+num_cpus = "1.15"
+num-traits = "0.2.15"
+once_cell = "1.13"
+opentelemetry = "0.18.0"
+opentelemetry-otlp = { version = "0.11.0", default_features=false, features = ["http-proto", "trace", "http", "reqwest-client"] }
+opentelemetry-semantic-conventions = "0.10.0"
+parking_lot = "0.12"
+pin-project-lite = "0.2"
+prometheus = {version = "0.13", default_features=false, features = ["process"]} # removes protobuf dependency
+prost = "0.11"
+rand = "0.8"
+regex = "1.4"
+reqwest = { version = "0.11", default-features = false, features = ["rustls-tls"] }
+reqwest-tracing = { version = "0.4.0", features = ["opentelemetry_0_18"] }
+reqwest-middleware = "0.2.0"
+routerify = "3"
+rpds = "0.13"
+rustls = "0.20"
+rustls-pemfile = "1"
+rustls-split = "0.3"
+scopeguard = "1.1"
+sentry = { version = "0.30", default-features = false, features = ["backtrace", "contexts", "panic", "rustls", "reqwest" ] }
+serde = { version = "1.0", features = ["derive"] }
+serde_json = "1"
+serde_with = "2.0"
+sha2 = "0.10.2"
+signal-hook = "0.3"
+socket2 = "0.5"
+strum = "0.24"
+strum_macros = "0.24"
+svg_fmt = "0.4.1"
+sync_wrapper = "0.1.2"
+tar = "0.4"
+test-context = "0.1"
+thiserror = "1.0"
+tls-listener = { version = "0.6", features = ["rustls", "hyper-h1"] }
+tokio = { version = "1.17", features = ["macros"] }
+tokio-io-timeout = "1.2.0"
+tokio-postgres-rustls = "0.9.0"
+tokio-rustls = "0.23"
+tokio-stream = "0.1"
+tokio-util = { version = "0.7", features = ["io"] }
+toml = "0.7"
+toml_edit = "0.19"
+tonic = {version = "0.9", features = ["tls", "tls-roots"]}
+tracing = "0.1"
+tracing-opentelemetry = "0.18.0"
+tracing-subscriber = { version = "0.3", features = ["env-filter"] }
+url = "2.2"
+uuid = { version = "1.2", features = ["v4", "serde"] }
+walkdir = "2.3.2"
+webpki-roots = "0.23"
+x509-parser = "0.15"
+percent-encoding = "1.0"
+
+## TODO replace this with tracing
+env_logger = "0.10"
+log = "0.4"
+
+## Libraries from neondatabase/ git forks, ideally with changes to be upstreamed
+postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev="43e6db254a97fdecbce33d8bc0890accfd74495e", features = ["with-chrono-0_4", "array-impls"] }
+postgres-protocol = { git = "https://github.com/neondatabase/rust-postgres.git", rev="43e6db254a97fdecbce33d8bc0890accfd74495e" }
+postgres-types = { git = "https://github.com/neondatabase/rust-postgres.git", rev="43e6db254a97fdecbce33d8bc0890accfd74495e", features = ["array-impls"] }
+tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev="43e6db254a97fdecbce33d8bc0890accfd74495e", features = ["array-impls"] }
+tokio-tar = { git = "https://github.com/neondatabase/tokio-tar.git", rev="404df61437de0feef49ba2ccdbdd94eb8ad6e142" }
+
+## Other git libraries
+heapless = { default-features=false, features=[], git = "https://github.com/japaric/heapless.git", rev = "644653bf3b831c6bb4963be2de24804acf5e5001" } # upstream release pending
+
+## Local libraries
+compute_api = { version = "0.1", path = "./libs/compute_api/" }
+consumption_metrics = { version = "0.1", path = "./libs/consumption_metrics/" }
+metrics = { version = "0.1", path = "./libs/metrics/" }
+pageserver_api = { version = "0.1", path = "./libs/pageserver_api/" }
+postgres_backend = { version = "0.1", path = "./libs/postgres_backend/" }
+postgres_connection = { version = "0.1", path = "./libs/postgres_connection/" }
+postgres_ffi = { version = "0.1", path = "./libs/postgres_ffi/" }
+pq_proto = { version = "0.1", path = "./libs/pq_proto/" }
+remote_storage = { version = "0.1", path = "./libs/remote_storage/" }
+safekeeper_api = { version = "0.1", path = "./libs/safekeeper_api" }
+storage_broker = { version = "0.1", path = "./storage_broker/" } # Note: main broker code is inside the binary crate, so linking with the library shouldn't be heavy.
+tenant_size_model = { version = "0.1", path = "./libs/tenant_size_model/" }
+tracing-utils = { version = "0.1", path = "./libs/tracing-utils/" }
+utils = { version = "0.1", path = "./libs/utils/" }
+
+## Common library dependency
+workspace_hack = { version = "0.1", path = "./workspace_hack/" }
+
+## Build dependencies
+criterion = "0.4"
+rcgen = "0.10"
+rstest = "0.17"
+tempfile = "3.4"
+tonic-build = "0.9"
+
+# 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="43e6db254a97fdecbce33d8bc0890accfd74495e" }
+
+################# Binary contents sections
+
 [profile.release]
 # This is useful for profiling and, to some extent, debug.
 # 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
@@ -76,9 +226,3 @@ 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" }

Dockerfile

@@ -39,12 +39,12 @@ ARG CACHEPOT_BUCKET=neon-github-dev
 
 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 . .
+COPY --chown=nonroot . .
 
 # 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 safekeeper --bin proxy --locked --release \
+&& mold -run cargo build --bin pageserver --bin pageserver_binutils --bin draw_timeline_dir --bin safekeeper --bin storage_broker --bin proxy --locked --release \
     && cachepot -s
 
 # Build final image
@@ -65,7 +65,9 @@ RUN set -e \
 
 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/storage_broker         /usr/local/bin
 COPY --from=build --chown=neon:neon /home/nonroot/target/release/proxy               /usr/local/bin
 
 COPY --from=pg-build /home/nonroot/pg_install/v14 /usr/local/v14/
@@ -77,7 +79,7 @@ COPY --from=pg-build /home/nonroot/postgres_install.tar.gz /data/
 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 "broker_endpoint='http://storage_broker:50051'" \
        -c "pg_distrib_dir='/usr/local/'" \
        -c "listen_pg_addr='0.0.0.0:6400'" \
        -c "listen_http_addr='0.0.0.0:9898'"

Dockerfile.compute-node

@@ -0,0 +1,600 @@
+ARG PG_VERSION
+ARG REPOSITORY=369495373322.dkr.ecr.eu-central-1.amazonaws.com
+ARG IMAGE=rust
+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 \
+    libicu-dev libxslt1-dev liblz4-dev libzstd-dev
+
+#########################################################################################
+#
+# Layer "pg-build"
+# Build Postgres from the neon postgres repository.
+#
+#########################################################################################
+FROM build-deps AS pg-build
+ARG PG_VERSION
+COPY vendor/postgres-${PG_VERSION} postgres
+RUN cd postgres && \
+    export CONFIGURE_CMD="./configure CFLAGS='-O2 -g3' --enable-debug --with-openssl --with-uuid=ossp \
+    --with-icu --with-libxml --with-libxslt --with-lz4" && \
+    if [ "${PG_VERSION}" != "v14" ]; then \
+        # zstd is available only from PG15
+        export CONFIGURE_CMD="${CONFIGURE_CMD} --with-zstd"; \
+    fi && \
+    eval $CONFIGURE_CMD && \
+    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 && \
+    # Enable some of contrib extensions
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/autoinc.control && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/bloom.control && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/earthdistance.control && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/insert_username.control && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/intagg.control && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/moddatetime.control && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/pg_stat_statements.control && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/pgrowlocks.control && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/pgstattuple.control && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/refint.control && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/xml2.control
+
+#########################################################################################
+#
+# 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 cmake gdal-bin libboost-dev libboost-thread-dev libboost-filesystem-dev \
+    libboost-system-dev libboost-iostreams-dev libboost-program-options-dev libboost-timer-dev \
+    libcgal-dev libgdal-dev libgmp-dev libmpfr-dev libopenscenegraph-dev libprotobuf-c-dev \
+    protobuf-c-compiler xsltproc
+
+# SFCGAL > 1.3 requires CGAL > 5.2, Bullseye's libcgal-dev is 5.2
+RUN wget https://gitlab.com/Oslandia/SFCGAL/-/archive/v1.3.10/SFCGAL-v1.3.10.tar.gz -O SFCGAL.tar.gz && \
+    echo "4e39b3b2adada6254a7bdba6d297bb28e1a9835a9f879b74f37e2dab70203232 SFCGAL.tar.gz" | sha256sum --check && \
+    mkdir sfcgal-src && cd sfcgal-src && tar xvzf ../SFCGAL.tar.gz --strip-components=1 -C . && \
+    cmake . && make -j $(getconf _NPROCESSORS_ONLN) && \
+    DESTDIR=/sfcgal make install -j $(getconf _NPROCESSORS_ONLN) && \
+    make clean && cp -R /sfcgal/* /
+
+ENV PATH "/usr/local/pgsql/bin:$PATH"
+
+RUN wget https://download.osgeo.org/postgis/source/postgis-3.3.2.tar.gz -O postgis.tar.gz && \
+    echo "9a2a219da005a1730a39d1959a1c7cec619b1efb009b65be80ffc25bad299068 postgis.tar.gz" | sha256sum --check && \
+    mkdir postgis-src && cd postgis-src && tar xvzf ../postgis.tar.gz --strip-components=1 -C . && \
+    ./autogen.sh && \
+    ./configure --with-sfcgal=/usr/local/bin/sfcgal-config && \
+    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_sfcgal.control && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_tiger_geocoder.control && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_topology.control && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/address_standardizer.control && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/address_standardizer_data_us.control
+
+RUN wget https://github.com/pgRouting/pgrouting/archive/v3.4.2.tar.gz -O pgrouting.tar.gz && \
+    echo "cac297c07d34460887c4f3b522b35c470138760fe358e351ad1db4edb6ee306e pgrouting.tar.gz" | sha256sum --check && \
+    mkdir pgrouting-src && cd pgrouting-src && tar xvzf ../pgrouting.tar.gz --strip-components=1 -C . && \
+    mkdir build && \
+    cd build && \
+    cmake .. && \
+    make -j $(getconf _NPROCESSORS_ONLN) && \
+    make -j $(getconf _NPROCESSORS_ONLN) install && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/pgrouting.control
+
+#########################################################################################
+#
+# Layer "plv8-build"
+# Build plv8
+#
+#########################################################################################
+FROM build-deps AS plv8-build
+COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
+RUN apt update && \
+    apt install -y ninja-build python3-dev libncurses5 binutils clang
+
+RUN wget https://github.com/plv8/plv8/archive/refs/tags/v3.1.5.tar.gz -O plv8.tar.gz && \
+    echo "1e108d5df639e4c189e1c5bdfa2432a521c126ca89e7e5a969d46899ca7bf106 plv8.tar.gz" | sha256sum --check && \
+    mkdir plv8-src && cd plv8-src && tar xvzf ../plv8.tar.gz --strip-components=1 -C . && \
+    export PATH="/usr/local/pgsql/bin:$PATH" && \
+    make DOCKER=1 -j $(getconf _NPROCESSORS_ONLN) install && \
+    rm -rf /plv8-* && \
+    find /usr/local/pgsql/ -name "plv8-*.so" | xargs strip && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/plv8.control && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/plcoffee.control && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/plls.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 \
+      && echo "739d372726cb23129d57a539ce1432453448816e345e1545f6127296926b6754 /tmp/cmake-install.sh" | sha256sum --check \
+      && 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/v4.1.0.tar.gz -O h3.tar.gz && \
+    echo "ec99f1f5974846bde64f4513cf8d2ea1b8d172d2218ab41803bf6a63532272bc h3.tar.gz" | sha256sum --check && \
+    mkdir h3-src && cd h3-src && tar xvzf ../h3.tar.gz --strip-components=1 -C . && \
+    mkdir build && cd build && \
+    cmake .. -DCMAKE_BUILD_TYPE=Release && \
+    make -j $(getconf _NPROCESSORS_ONLN) && \
+    DESTDIR=/h3 make install && \
+    cp -R /h3/usr / && \
+    rm -rf build
+
+RUN wget https://github.com/zachasme/h3-pg/archive/refs/tags/v4.1.2.tar.gz -O h3-pg.tar.gz && \
+    echo "c135aa45999b2ad1326d2537c1cadef96d52660838e4ca371706c08fdea1a956 h3-pg.tar.gz" | sha256sum --check && \
+    mkdir h3-pg-src && cd h3-pg-src && tar xvzf ../h3-pg.tar.gz --strip-components=1 -C . && \
+    export PATH="/usr/local/pgsql/bin:$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 "unit-pg-build"
+# compile unit extension
+#
+#########################################################################################
+FROM build-deps AS unit-pg-build
+COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
+
+RUN wget https://github.com/df7cb/postgresql-unit/archive/refs/tags/7.7.tar.gz -O postgresql-unit.tar.gz && \
+    echo "411d05beeb97e5a4abf17572bfcfbb5a68d98d1018918feff995f6ee3bb03e79 postgresql-unit.tar.gz" | sha256sum --check && \
+    mkdir postgresql-unit-src && cd postgresql-unit-src && tar xvzf ../postgresql-unit.tar.gz --strip-components=1 -C . && \
+    make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
+    make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
+    # unit extension's "create extension" script relies on absolute install path to fill some reference tables.
+    # We move the extension from '/usr/local/pgsql/' to '/usr/local/'  after it is build. So we need to adjust the path.
+    # This one-liner removes pgsql/ part of the path.
+    # NOTE: Other extensions that rely on MODULEDIR variable after building phase will need the same fix.
+    find /usr/local/pgsql/share/extension/ -name "unit*.sql" -print0 | xargs -0 sed -i "s|pgsql/||g" && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/unit.control
+
+#########################################################################################
+#
+# Layer "vector-pg-build"
+# compile pgvector extension
+#
+#########################################################################################
+FROM build-deps AS vector-pg-build
+COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
+
+RUN wget https://github.com/pgvector/pgvector/archive/refs/tags/v0.4.0.tar.gz -O pgvector.tar.gz && \
+    echo "b76cf84ddad452cc880a6c8c661d137ddd8679c000a16332f4f03ecf6e10bcc8 pgvector.tar.gz" | sha256sum --check && \
+    mkdir pgvector-src && cd pgvector-src && tar xvzf ../pgvector.tar.gz --strip-components=1 -C . && \
+    make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
+    make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/vector.control
+
+#########################################################################################
+#
+# Layer "pgjwt-pg-build"
+# compile pgjwt extension
+#
+#########################################################################################
+FROM build-deps AS pgjwt-pg-build
+COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
+
+# 9742dab1b2f297ad3811120db7b21451bca2d3c9 made on 13/11/2021
+RUN wget https://github.com/michelp/pgjwt/archive/9742dab1b2f297ad3811120db7b21451bca2d3c9.tar.gz -O pgjwt.tar.gz && \
+    echo "cfdefb15007286f67d3d45510f04a6a7a495004be5b3aecb12cda667e774203f pgjwt.tar.gz" | sha256sum --check && \
+    mkdir pgjwt-src && cd pgjwt-src && tar xvzf ../pgjwt.tar.gz --strip-components=1 -C . && \
+    make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/pgjwt.control
+
+#########################################################################################
+#
+# Layer "hypopg-pg-build"
+# compile hypopg extension
+#
+#########################################################################################
+FROM build-deps AS hypopg-pg-build
+COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
+
+RUN wget https://github.com/HypoPG/hypopg/archive/refs/tags/1.3.1.tar.gz -O hypopg.tar.gz && \
+    echo "e7f01ee0259dc1713f318a108f987663d60f3041948c2ada57a94b469565ca8e hypopg.tar.gz" | sha256sum --check && \
+    mkdir hypopg-src && cd hypopg-src && tar xvzf ../hypopg.tar.gz --strip-components=1 -C . && \
+    make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
+    make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/hypopg.control
+
+#########################################################################################
+#
+# Layer "pg-hashids-pg-build"
+# compile pg_hashids extension
+#
+#########################################################################################
+FROM build-deps AS pg-hashids-pg-build
+COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
+
+RUN wget https://github.com/iCyberon/pg_hashids/archive/refs/tags/v1.2.1.tar.gz -O pg_hashids.tar.gz && \
+    echo "74576b992d9277c92196dd8d816baa2cc2d8046fe102f3dcd7f3c3febed6822a pg_hashids.tar.gz" | sha256sum --check && \
+    mkdir pg_hashids-src && cd pg_hashids-src && tar xvzf ../pg_hashids.tar.gz --strip-components=1 -C . && \
+    make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config USE_PGXS=1 && \
+    make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config USE_PGXS=1 && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/pg_hashids.control
+
+#########################################################################################
+#
+# Layer "rum-pg-build"
+# compile rum extension
+#
+#########################################################################################
+FROM build-deps AS rum-pg-build
+COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
+
+RUN wget https://github.com/postgrespro/rum/archive/refs/tags/1.3.13.tar.gz -O rum.tar.gz && \
+    echo "6ab370532c965568df6210bd844ac6ba649f53055e48243525b0b7e5c4d69a7d rum.tar.gz" | sha256sum --check && \
+    mkdir rum-src && cd rum-src && tar xvzf ../rum.tar.gz --strip-components=1 -C . && \
+    make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config USE_PGXS=1 && \
+    make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config USE_PGXS=1 && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/rum.control
+
+#########################################################################################
+#
+# Layer "pgtap-pg-build"
+# compile pgTAP extension
+#
+#########################################################################################
+FROM build-deps AS pgtap-pg-build
+COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
+
+RUN wget https://github.com/theory/pgtap/archive/refs/tags/v1.2.0.tar.gz -O pgtap.tar.gz && \
+    echo "9c7c3de67ea41638e14f06da5da57bac6f5bd03fea05c165a0ec862205a5c052 pgtap.tar.gz" | sha256sum --check && \
+    mkdir pgtap-src && cd pgtap-src && tar xvzf ../pgtap.tar.gz --strip-components=1 -C . && \
+    make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
+    make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/pgtap.control
+
+#########################################################################################
+#
+# Layer "ip4r-pg-build"
+# compile ip4r extension
+#
+#########################################################################################
+FROM build-deps AS ip4r-pg-build
+COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
+
+RUN wget https://github.com/RhodiumToad/ip4r/archive/refs/tags/2.4.1.tar.gz -O ip4r.tar.gz && \
+    echo "78b9f0c1ae45c22182768fe892a32d533c82281035e10914111400bf6301c726 ip4r.tar.gz" | sha256sum --check && \
+    mkdir ip4r-src && cd ip4r-src && tar xvzf ../ip4r.tar.gz --strip-components=1 -C . && \
+    make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
+    make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/ip4r.control
+
+#########################################################################################
+#
+# Layer "prefix-pg-build"
+# compile Prefix extension
+#
+#########################################################################################
+FROM build-deps AS prefix-pg-build
+COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
+
+RUN wget https://github.com/dimitri/prefix/archive/refs/tags/v1.2.9.tar.gz -O prefix.tar.gz && \
+    echo "38d30a08d0241a8bbb8e1eb8f0152b385051665a8e621c8899e7c5068f8b511e prefix.tar.gz" | sha256sum --check && \
+    mkdir prefix-src && cd prefix-src && tar xvzf ../prefix.tar.gz --strip-components=1 -C . && \
+    make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
+    make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/prefix.control
+
+#########################################################################################
+#
+# Layer "hll-pg-build"
+# compile hll extension
+#
+#########################################################################################
+FROM build-deps AS hll-pg-build
+COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
+
+RUN wget https://github.com/citusdata/postgresql-hll/archive/refs/tags/v2.17.tar.gz -O hll.tar.gz && \
+    echo "9a18288e884f197196b0d29b9f178ba595b0dfc21fbf7a8699380e77fa04c1e9 hll.tar.gz" | sha256sum --check && \
+    mkdir hll-src && cd hll-src && tar xvzf ../hll.tar.gz --strip-components=1 -C . && \
+    make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
+    make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/hll.control
+
+#########################################################################################
+#
+# Layer "plpgsql-check-pg-build"
+# compile plpgsql_check extension
+#
+#########################################################################################
+FROM build-deps AS plpgsql-check-pg-build
+COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
+
+RUN wget https://github.com/okbob/plpgsql_check/archive/refs/tags/v2.3.2.tar.gz -O plpgsql_check.tar.gz && \
+    echo "9d81167c4bbeb74eebf7d60147b21961506161addc2aee537f95ad8efeae427b plpgsql_check.tar.gz" | sha256sum --check && \
+    mkdir plpgsql_check-src && cd plpgsql_check-src && tar xvzf ../plpgsql_check.tar.gz --strip-components=1 -C . && \
+    make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config USE_PGXS=1 && \
+    make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config USE_PGXS=1 && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/plpgsql_check.control
+
+#########################################################################################
+#
+# Layer "timescaledb-pg-build"
+# compile timescaledb extension
+#
+#########################################################################################
+FROM build-deps AS timescaledb-pg-build
+COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
+
+ENV PATH "/usr/local/pgsql/bin:$PATH"
+
+RUN apt-get update && \
+    apt-get install -y cmake && \
+    wget https://github.com/timescale/timescaledb/archive/refs/tags/2.10.1.tar.gz -O timescaledb.tar.gz && \
+    echo "6fca72a6ed0f6d32d2b3523951ede73dc5f9b0077b38450a029a5f411fdb8c73 timescaledb.tar.gz" | sha256sum --check && \
+    mkdir timescaledb-src && cd timescaledb-src && tar xvzf ../timescaledb.tar.gz --strip-components=1 -C . && \
+    ./bootstrap -DSEND_TELEMETRY_DEFAULT:BOOL=OFF -DUSE_TELEMETRY:BOOL=OFF -DAPACHE_ONLY:BOOL=ON && \
+    cd build && \
+    make -j $(getconf _NPROCESSORS_ONLN) && \
+    make install -j $(getconf _NPROCESSORS_ONLN) && \
+    echo "trusted = true" >> /usr/local/pgsql/share/extension/timescaledb.control
+
+#########################################################################################
+#
+# Layer "pg-hint-plan-pg-build"
+# compile pg_hint_plan extension
+#
+#########################################################################################
+FROM build-deps AS pg-hint-plan-pg-build
+COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
+
+ARG PG_VERSION
+ENV PATH "/usr/local/pgsql/bin:$PATH"
+
+RUN case "${PG_VERSION}" in \
+      "v14") \
+        export PG_HINT_PLAN_VERSION=14_1_4_1 \
+        export PG_HINT_PLAN_CHECKSUM=c3501becf70ead27f70626bce80ea401ceac6a77e2083ee5f3ff1f1444ec1ad1 \
+        ;; \
+      "v15") \
+        export PG_HINT_PLAN_VERSION=15_1_5_0 \
+        export PG_HINT_PLAN_CHECKSUM=564cbbf4820973ffece63fbf76e3c0af62c4ab23543142c7caaa682bc48918be \
+        ;; \
+      *) \
+        echo "Export the valid PG_HINT_PLAN_VERSION variable" && exit 1 \
+        ;; \
+    esac && \
+    wget https://github.com/ossc-db/pg_hint_plan/archive/refs/tags/REL${PG_HINT_PLAN_VERSION}.tar.gz -O pg_hint_plan.tar.gz && \
+    echo "${PG_HINT_PLAN_CHECKSUM} pg_hint_plan.tar.gz" | sha256sum --check && \
+    mkdir pg_hint_plan-src && cd pg_hint_plan-src && tar xvzf ../pg_hint_plan.tar.gz --strip-components=1 -C . && \
+    make -j $(getconf _NPROCESSORS_ONLN) && \
+    make install -j $(getconf _NPROCESSORS_ONLN) && \
+    echo "trusted = true" >> /usr/local/pgsql/share/extension/pg_hint_plan.control
+
+#########################################################################################
+#
+# Layer "rust extensions"
+# This layer is used to build `pgx` deps
+#
+#########################################################################################
+FROM build-deps AS rust-extensions-build
+COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
+
+RUN apt-get update && \
+    apt-get install -y curl libclang-dev cmake && \
+    useradd -ms /bin/bash nonroot -b /home
+
+ENV HOME=/home/nonroot
+ENV PATH="/home/nonroot/.cargo/bin:/usr/local/pgsql/bin/:$PATH"
+USER nonroot
+WORKDIR /home/nonroot
+ARG PG_VERSION
+
+RUN curl -sSO https://static.rust-lang.org/rustup/dist/$(uname -m)-unknown-linux-gnu/rustup-init && \
+    chmod +x rustup-init && \
+    ./rustup-init -y --no-modify-path --profile minimal --default-toolchain stable && \
+    rm rustup-init && \
+    cargo install --locked --version 0.7.3 cargo-pgx && \
+    /bin/bash -c 'cargo pgx init --pg${PG_VERSION:1}=/usr/local/pgsql/bin/pg_config'
+
+USER root
+
+#########################################################################################
+#
+# Layer "pg-jsonschema-pg-build"
+# Compile "pg_jsonschema" extension
+#
+#########################################################################################
+
+FROM rust-extensions-build AS pg-jsonschema-pg-build
+
+# caeab60d70b2fd3ae421ec66466a3abbb37b7ee6 made on 06/03/2023
+# there is no release tag yet, but we need it due to the superuser fix in the control file, switch to git tag after release >= 0.1.5
+RUN wget https://github.com/supabase/pg_jsonschema/archive/caeab60d70b2fd3ae421ec66466a3abbb37b7ee6.tar.gz -O pg_jsonschema.tar.gz && \
+    echo "54129ce2e7ee7a585648dbb4cef6d73f795d94fe72f248ac01119992518469a4 pg_jsonschema.tar.gz" | sha256sum --check && \
+    mkdir pg_jsonschema-src && cd pg_jsonschema-src && tar xvzf ../pg_jsonschema.tar.gz --strip-components=1 -C . && \
+    sed -i 's/pgx = "0.7.1"/pgx = { version = "0.7.3", features = [ "unsafe-postgres" ] }/g' Cargo.toml && \
+    cargo pgx install --release && \
+    echo "trusted = true" >> /usr/local/pgsql/share/extension/pg_jsonschema.control
+
+#########################################################################################
+#
+# Layer "pg-graphql-pg-build"
+# Compile "pg_graphql" extension
+#
+#########################################################################################
+
+FROM rust-extensions-build AS pg-graphql-pg-build
+
+# b4988843647450a153439be367168ed09971af85 made on 22/02/2023 (from remove-pgx-contrib-spiext branch)
+# Currently pgx version bump to >= 0.7.2  causes "call to unsafe function" compliation errors in
+# pgx-contrib-spiext. There is a branch that removes that dependency, so use it. It is on the
+# same 1.1 version we've used before.
+RUN wget https://github.com/yrashk/pg_graphql/archive/b4988843647450a153439be367168ed09971af85.tar.gz -O pg_graphql.tar.gz && \
+    echo "0c7b0e746441b2ec24187d0e03555faf935c2159e2839bddd14df6dafbc8c9bd pg_graphql.tar.gz" | sha256sum --check && \
+    mkdir pg_graphql-src && cd pg_graphql-src && tar xvzf ../pg_graphql.tar.gz --strip-components=1 -C . && \
+    sed -i 's/pgx = "~0.7.1"/pgx = { version = "0.7.3", features = [ "unsafe-postgres" ] }/g' Cargo.toml && \
+    sed -i 's/pgx-tests = "~0.7.1"/pgx-tests = "0.7.3"/g' Cargo.toml && \
+    cargo pgx install --release && \
+    # it's needed to enable extension because it uses untrusted C language
+    sed -i 's/superuser = false/superuser = true/g' /usr/local/pgsql/share/extension/pg_graphql.control && \
+    echo "trusted = true" >> /usr/local/pgsql/share/extension/pg_graphql.control
+
+#########################################################################################
+#
+# Layer "pg-tiktoken-build"
+# Compile "pg_tiktoken" extension
+#
+#########################################################################################
+
+FROM rust-extensions-build AS pg-tiktoken-pg-build
+
+# 801f84f08c6881c8aa30f405fafbf00eec386a72 made on 10/03/2023
+RUN wget https://github.com/kelvich/pg_tiktoken/archive/801f84f08c6881c8aa30f405fafbf00eec386a72.tar.gz -O pg_tiktoken.tar.gz && \
+    echo "52f60ac800993a49aa8c609961842b611b6b1949717b69ce2ec9117117e16e4a pg_tiktoken.tar.gz" | sha256sum --check && \
+    mkdir pg_tiktoken-src && cd pg_tiktoken-src && tar xvzf ../pg_tiktoken.tar.gz --strip-components=1 -C . && \
+    cargo pgx install --release && \
+    echo "trusted = true" >> /usr/local/pgsql/share/extension/pg_tiktoken.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=postgis-build /sfcgal/* /
+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 --from=unit-pg-build /usr/local/pgsql/ /usr/local/pgsql/
+COPY --from=vector-pg-build /usr/local/pgsql/ /usr/local/pgsql/
+COPY --from=pgjwt-pg-build /usr/local/pgsql/ /usr/local/pgsql/
+COPY --from=pg-jsonschema-pg-build /usr/local/pgsql/ /usr/local/pgsql/
+COPY --from=pg-graphql-pg-build /usr/local/pgsql/ /usr/local/pgsql/
+COPY --from=pg-tiktoken-pg-build /usr/local/pgsql/ /usr/local/pgsql/
+COPY --from=hypopg-pg-build /usr/local/pgsql/ /usr/local/pgsql/
+COPY --from=pg-hashids-pg-build /usr/local/pgsql/ /usr/local/pgsql/
+COPY --from=rum-pg-build /usr/local/pgsql/ /usr/local/pgsql/
+COPY --from=pgtap-pg-build /usr/local/pgsql/ /usr/local/pgsql/
+COPY --from=ip4r-pg-build /usr/local/pgsql/ /usr/local/pgsql/
+COPY --from=prefix-pg-build /usr/local/pgsql/ /usr/local/pgsql/
+COPY --from=hll-pg-build /usr/local/pgsql/ /usr/local/pgsql/
+COPY --from=plpgsql-check-pg-build /usr/local/pgsql/ /usr/local/pgsql/
+COPY --from=timescaledb-pg-build /usr/local/pgsql/ /usr/local/pgsql/
+COPY --from=pg-hint-plan-pg-build /usr/local/pgsql/ /usr/local/pgsql/
+COPY pgxn/ pgxn/
+
+RUN make -j $(getconf _NPROCESSORS_ONLN) \
+        PG_CONFIG=/usr/local/pgsql/bin/pg_config \
+        -C pgxn/neon \
+        -s install && \
+    make -j $(getconf _NPROCESSORS_ONLN) \
+        PG_CONFIG=/usr/local/pgsql/bin/pg_config \
+        -C pgxn/neon_utils \
+        -s install
+
+#########################################################################################
+#
+# Compile and run the Neon-specific `compute_ctl` binary
+#
+#########################################################################################
+FROM $REPOSITORY/$IMAGE:$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 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 && \
+    # create folder for file cache
+    mkdir -p -m 777 /neon/cache
+
+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
+# libicu67, locales for collations (including ICU and plpgsql_check)
+# liblz4-1 for lz4
+# libossp-uuid16 for extension ossp-uuid
+# libgeos, libgdal, libsfcgal1, libproj and libprotobuf-c1 for PostGIS
+# libxml2, libxslt1.1 for xml2
+# libzstd1 for zstd
+RUN apt update &&  \
+    apt install --no-install-recommends -y \
+        gdb \
+        locales \
+        libicu67 \
+        liblz4-1 \
+        libreadline8 \
+        libossp-uuid16 \
+        libgeos-c1v5 \
+        libgdal28 \
+        libproj19 \
+        libprotobuf-c1 \
+        libsfcgal1 \
+        libxml2 \
+        libxslt1.1 \
+        libzstd1 \
+        procps && \
+    rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* && \
+    localedef -i en_US -c -f UTF-8 -A /usr/share/locale/locale.alias en_US.UTF-8
+
+ENV LANG en_US.utf8
+USER postgres
+ENTRYPOINT ["/usr/local/bin/compute_ctl"]

Dockerfile.compute-node-v14

@@ -1,201 +0,0 @@
-ARG TAG=pinned
-# apparently, ARGs don't get replaced in RUN commands in kaniko
-# ARG POSTGIS_VERSION=3.3.0
-# ARG PLV8_VERSION=3.1.4
-# ARG PG_VERSION=v14
-
-#
-# Layer "build-deps"
-#
-FROM debian:bullseye-slim AS build-deps
-RUN echo "deb http://ftp.debian.org/debian testing main" >> /etc/apt/sources.list && \
-    echo "APT::Default-Release \"stable\";" > /etc/apt/apt.conf.d/default-release && \
-    apt update
-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 libglib2.0-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-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 $(getconf _NPROCESSORS_ONLN) -s -C src/interfaces/libpq install
-
-#
-# Layer "postgis-build"
-# Build PostGIS from the upstream PostGIS mirror.
-#
-# PostGIS compiles against neon postgres sources without changes. Perhaps we
-# could even use the upstream binaries, compiled against vanilla Postgres, but
-# it would require some investigation to check that it works, and also keeps
-# working in the future. So for now, we compile our own binaries.
-FROM build-deps AS postgis-build
-COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
-RUN apt update && \
-    apt install -y gdal-bin libgdal-dev libprotobuf-c-dev protobuf-c-compiler xsltproc
-
-RUN wget https://download.osgeo.org/postgis/source/postgis-3.3.0.tar.gz && \
-    tar xvzf postgis-3.3.0.tar.gz && \
-    cd postgis-3.3.0 && \
-    ./autogen.sh && \
-    export PATH="/usr/local/pgsql/bin:$PATH" && \
-    ./configure && \
-    make -j $(getconf _NPROCESSORS_ONLN) install && \
-    cd extensions/postgis && \
-    make clean && \
-    make -j $(getconf _NPROCESSORS_ONLN) install && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_raster.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_tiger_geocoder.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_topology.control
-
-#
-# Layer "plv8-build"
-# Build plv8
-#
-FROM build-deps AS plv8-build
-COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
-RUN apt update && \
-    apt install -y ninja-build python3-dev libc++-dev libc++abi-dev libncurses5
-
-# https://github.com/plv8/plv8/issues/475
-# Debian bullseye provides binutils 2.35 when >= 2.38 is necessary
-RUN apt update && \
-    apt install -y --no-install-recommends -t testing binutils
-
-# Sed is used to patch for https://github.com/plv8/plv8/issues/503
-RUN wget https://github.com/plv8/plv8/archive/refs/tags/v3.1.4.tar.gz && \
-    tar xvzf v3.1.4.tar.gz && \
-    cd plv8-3.1.4 && \
-    export PATH="/usr/local/pgsql/bin:$PATH" && \
-    sed -i 's/MemoryContextAlloc(/MemoryContextAllocZero(/' plv8.cc && \
-    make -j $(getconf _NPROCESSORS_ONLN) && \
-    make -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 apt update && \
-    apt install -y --no-install-recommends -t testing cmake
-
-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
-
-#
-# 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
-# GLIBC 2.34 for plv8.
-#     Debian bullseye provides GLIBC 2.31, so we install the library from testing
-#
-# 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/* && \
-    echo "Installing GLIBC 2.34" && \
-    echo "deb http://ftp.debian.org/debian testing main" >> /etc/apt/sources.list && \
-    echo "APT::Default-Release \"stable\";" > /etc/apt/apt.conf.d/default-release && \
-    apt update && \
-    apt install -y --no-install-recommends -t testing libc6 && \
-    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

@@ -1,206 +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
-# apparently, ARGs don't get replaced in RUN commands in kaniko
-# ARG POSTGIS_VERSION=3.3.1
-# ARG PLV8_VERSION=3.1.4
-# ARG PG_VERSION=v15
-
-#
-# Layer "build-deps"
-#
-FROM debian:bullseye-slim AS build-deps
-RUN echo "deb http://ftp.debian.org/debian testing main" >> /etc/apt/sources.list && \
-    echo "APT::Default-Release \"stable\";" > /etc/apt/apt.conf.d/default-release && \
-    apt update
-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 libglib2.0-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-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 $(getconf _NPROCESSORS_ONLN) -s -C src/interfaces/libpq install
-
-#
-# Layer "postgis-build"
-# Build PostGIS from the upstream PostGIS mirror.
-#
-# PostGIS compiles against neon postgres sources without changes. Perhaps we
-# could even use the upstream binaries, compiled against vanilla Postgres, but
-# it would require some investigation to check that it works, and also keeps
-# working in the future. So for now, we compile our own binaries.
-FROM build-deps AS postgis-build
-COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
-RUN apt update && \
-    apt install -y gdal-bin libgdal-dev libprotobuf-c-dev protobuf-c-compiler xsltproc
-
-RUN wget https://download.osgeo.org/postgis/source/postgis-3.3.1.tar.gz && \
-    tar xvzf postgis-3.3.1.tar.gz && \
-    cd postgis-3.3.1 && \
-    ./autogen.sh && \
-    export PATH="/usr/local/pgsql/bin:$PATH" && \
-    ./configure && \
-    make -j $(getconf _NPROCESSORS_ONLN) install && \
-    cd extensions/postgis && \
-    make clean && \
-    make -j $(getconf _NPROCESSORS_ONLN) install && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_raster.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_tiger_geocoder.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_topology.control
-
-#
-# Layer "plv8-build"
-# Build plv8
-#
-FROM build-deps AS plv8-build
-COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
-RUN apt update && \
-    apt install -y ninja-build python3-dev libc++-dev libc++abi-dev libncurses5
-
-# https://github.com/plv8/plv8/issues/475
-# Debian bullseye provides binutils 2.35 when >= 2.38 is necessary
-RUN apt update && \
-    apt install -y --no-install-recommends -t testing binutils
-
-# Sed is used to patch for https://github.com/plv8/plv8/issues/503
-RUN wget https://github.com/plv8/plv8/archive/refs/tags/v3.1.4.tar.gz && \
-    tar xvzf v3.1.4.tar.gz && \
-    cd plv8-3.1.4 && \
-    export PATH="/usr/local/pgsql/bin:$PATH" && \
-    sed -i 's/MemoryContextAlloc(/MemoryContextAllocZero(/' plv8.cc && \
-    make -j $(getconf _NPROCESSORS_ONLN) && \
-    make -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 apt update && \
-    apt install -y --no-install-recommends -t testing cmake
-
-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
-
-#
-# 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
-# GLIBC 2.34 for plv8.
-#     Debian bullseye provides GLIBC 2.31, so we install the library from testing
-#
-# 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/* && \
-    echo "Installing GLIBC 2.34" && \
-    echo "deb http://ftp.debian.org/debian testing main" >> /etc/apt/sources.list && \
-    echo "APT::Default-Release \"stable\";" > /etc/apt/apt.conf.d/default-release && \
-    apt update && \
-    apt install -y --no-install-recommends -t testing libc6 && \
-    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.legacy

@@ -1,88 +0,0 @@
-#
-# Legacy version of the Dockerfile for the compute node.
-# Used by e2e CI. Building Dockerfile.compute-node will take
-# unreasonable ammount of time without v2 runners.
-#
-# TODO: remove once cloud repo CI is moved to v2 runners.
-#
-
-
-# Allow specifiyng different compute-tools tag and image repo, so we are
-# able to use different images
-ARG REPOSITORY=369495373322.dkr.ecr.eu-central-1.amazonaws.com
-ARG IMAGE=compute-tools
-ARG TAG=latest
-
-#
-# Image with pre-built tools
-#
-FROM $REPOSITORY/$IMAGE:$TAG AS compute-deps
-# Only to get ready compute_ctl binary as deppendency
-
-#
-# Image with Postgres build deps
-#
-FROM debian:bullseye-slim AS build-deps
-
-RUN apt-get update && apt-get -yq install automake libtool build-essential bison flex libreadline-dev zlib1g-dev libxml2-dev \
-                                          libcurl4-openssl-dev libossp-uuid-dev
-
-#
-# Image with built Postgres
-#
-FROM build-deps AS pg-build
-
-# Add user postgres
-RUN adduser postgres
-RUN mkdir /pg && chown postgres:postgres /pg
-
-# Copy source files
-# version 14 is default for now
-COPY ./vendor/postgres-v14 /pg/
-COPY ./pgxn /pg/
-
-# Build and install Postgres locally
-RUN mkdir /pg/compute_build && cd /pg/compute_build && \
-    ../configure CFLAGS='-O2 -g3' --prefix=$(pwd)/postgres_bin --enable-debug --with-uuid=ossp && \
-    # Install main binaries and contribs
-    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
-
-# Install neon contrib
-RUN make MAKELEVEL=0 PG_CONFIG=/pg/compute_build/postgres_bin/bin/pg_config -j $(getconf _NPROCESSORS_ONLN) -C /pg/neon install
-
-USER postgres
-WORKDIR /pg
-
-#
-# Final compute node image to be exported
-#
-FROM debian:bullseye-slim
-
-# libreadline-dev is required to run psql
-RUN apt-get update && apt-get -yq install libreadline-dev libossp-uuid-dev
-
-# 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
-
-# Copy ready Postgres binaries
-COPY --from=pg-build /pg/compute_build/postgres_bin /usr/local
-
-# Copy binaries from compute-tools
-COPY --from=compute-deps /usr/local/bin/compute_ctl /usr/local/bin/compute_ctl
-
-# XXX: temporary symlink for compatibility with old control-plane
-RUN ln -s /usr/local/bin/compute_ctl /usr/local/bin/zenith_ctl
-
-# Add postgres shared objects to the search path
-RUN echo '/usr/local/lib' >> /etc/ld.so.conf && /sbin/ldconfig
-
-USER postgres
-
-ENTRYPOINT ["/usr/local/bin/compute_ctl"]

Dockerfile.vm-compute-node

@@ -0,0 +1,70 @@
+# Note: this file *mostly* just builds on Dockerfile.compute-node
+
+ARG SRC_IMAGE
+ARG VM_INFORMANT_VERSION=v0.1.14
+# on libcgroup update, make sure to check bootstrap.sh for changes
+ARG LIBCGROUP_VERSION=v2.0.3
+
+# Pull VM informant, to copy from later
+FROM neondatabase/vm-informant:$VM_INFORMANT_VERSION as informant
+
+# Build cgroup-tools
+#
+# At time of writing (2023-03-14), debian bullseye has a version of cgroup-tools (technically
+# libcgroup) that doesn't support cgroup v2 (version 0.41-11). Unfortunately, the vm-informant
+# requires cgroup v2, so we'll build cgroup-tools ourselves.
+FROM debian:bullseye-slim as libcgroup-builder
+ARG LIBCGROUP_VERSION
+
+RUN set -exu \
+	&& apt update \
+	&& apt install --no-install-recommends -y \
+		git \
+		ca-certificates \
+		automake \
+		cmake \
+		make \
+		gcc \
+		byacc \
+		flex \
+		libtool \
+		libpam0g-dev \
+	&& git clone --depth 1 -b $LIBCGROUP_VERSION https://github.com/libcgroup/libcgroup \
+	&& INSTALL_DIR="/libcgroup-install" \
+	&& mkdir -p "$INSTALL_DIR/bin" "$INSTALL_DIR/include" \
+	&& cd libcgroup \
+	# extracted from bootstrap.sh, with modified flags:
+	&& (test -d m4 || mkdir m4) \
+	&& autoreconf -fi \
+	&& rm -rf autom4te.cache \
+	&& CFLAGS="-O3" ./configure --prefix="$INSTALL_DIR" --sysconfdir=/etc --localstatedir=/var --enable-opaque-hierarchy="name=systemd" \
+	# actually build the thing...
+	&& make install
+
+# Combine, starting from non-VM compute node image.
+FROM $SRC_IMAGE as base
+
+# Temporarily set user back to root so we can run adduser, set inittab
+USER root
+RUN adduser vm-informant --disabled-password --no-create-home
+
+RUN set -e \
+	&& rm -f /etc/inittab \
+	&& touch /etc/inittab
+
+RUN set -e \
+	&& echo "::sysinit:cgconfigparser -l /etc/cgconfig.conf -s 1664" >> /etc/inittab \
+	&& CONNSTR="dbname=neondb user=cloud_admin sslmode=disable" \
+	&& ARGS="--auto-restart --cgroup=neon-postgres --pgconnstr=\"$CONNSTR\"" \
+	&& echo "::respawn:su vm-informant -c '/usr/local/bin/vm-informant $ARGS'" >> /etc/inittab
+
+USER postgres
+
+ADD vm-cgconfig.conf /etc/cgconfig.conf
+COPY --from=informant /usr/bin/vm-informant /usr/local/bin/vm-informant
+
+COPY --from=libcgroup-builder /libcgroup-install/bin/* /usr/bin/
+COPY --from=libcgroup-builder /libcgroup-install/lib/* /usr/lib/
+COPY --from=libcgroup-builder /libcgroup-install/sbin/* /usr/sbin/
+
+ENTRYPOINT ["/usr/sbin/cgexec", "-g", "*:neon-postgres", "/usr/local/bin/compute_ctl"]

Makefile

@@ -20,18 +20,18 @@ 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)
+	# Seccomp BPF is only available for Linux
 	PG_CONFIGURE_OPTS += --with-libseccomp
-endif
+else ifeq ($(UNAME_S),Darwin)
-
+	# macOS with brew-installed openssl requires explicit paths
-# macOS with brew-installed openssl requires explicit paths
+	# It can be configured with OPENSSL_PREFIX variable
-# It can be configured with OPENSSL_PREFIX variable
-UNAME_S := $(shell uname -s)
-ifeq ($(UNAME_S),Darwin)
 	OPENSSL_PREFIX ?= $(shell brew --prefix openssl@3)
 	PG_CONFIGURE_OPTS += --with-includes=$(OPENSSL_PREFIX)/include --with-libraries=$(OPENSSL_PREFIX)/lib
+	# macOS already has bison and flex in the system, but they are old and result in postgres-v14 target failure
+	# brew formulae are keg-only and not symlinked into HOMEBREW_PREFIX, force their usage
+	EXTRA_PATH_OVERRIDES += $(shell brew --prefix bison)/bin/:$(shell brew --prefix flex)/bin/:
 endif
 
 # Use -C option so that when PostgreSQL "make install" installs the
@@ -61,130 +61,129 @@ all: neon postgres neon-pg-ext
 #
 # The 'postgres_ffi' depends on the Postgres headers.
 .PHONY: neon
-neon: postgres-v14-headers postgres-v15-headers
+neon: postgres-headers
 	+@echo "Compiling Neon"
 	$(CARGO_CMD_PREFIX) cargo build $(CARGO_BUILD_FLAGS)
 
 ### PostgreSQL parts
-# The rules are duplicated for Postgres v14 and 15. We may want to refactor
+# Some 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.
 #
-$(POSTGRES_INSTALL_DIR)/build/v14/config.status:
+$(POSTGRES_INSTALL_DIR)/build/%/config.status:
-	+@echo "Configuring Postgres v14 build"
+	+@echo "Configuring Postgres $* build"
-	mkdir -p $(POSTGRES_INSTALL_DIR)/build/v14
+	mkdir -p $(POSTGRES_INSTALL_DIR)/build/$*
-	(cd $(POSTGRES_INSTALL_DIR)/build/v14 && \
+	(cd $(POSTGRES_INSTALL_DIR)/build/$* && \
-	$(ROOT_PROJECT_DIR)/vendor/postgres-v14/configure CFLAGS='$(PG_CFLAGS)' \
+	env PATH="$(EXTRA_PATH_OVERRIDES):$$PATH" $(ROOT_PROJECT_DIR)/vendor/postgres-$*/configure \
+		CFLAGS='$(PG_CFLAGS)' \
 		$(PG_CONFIGURE_OPTS) \
-		--prefix=$(abspath $(POSTGRES_INSTALL_DIR))/v14 > configure.log)
+		--prefix=$(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 to run 'configure'
-.PHONY: postgres-v14-configure
+# Note: I've been unable to use templates for this part of our configuration.
-postgres-v14-configure: $(POSTGRES_INSTALL_DIR)/build/v14/config.status
+# I'm not sure why it wouldn't work, but this is the only place (apart from
-
+# the "build-all-versions" entry points) where direct mention of PostgreSQL
-.PHONY: postgres-v15-configure
+# versions is used.
-postgres-v15-configure: $(POSTGRES_INSTALL_DIR)/build/v15/config.status
+.PHONY: postgres-configure-v15
+postgres-configure-v15: $(POSTGRES_INSTALL_DIR)/build/v15/config.status
+.PHONY: postgres-configure-v14
+postgres-configure-v14: $(POSTGRES_INSTALL_DIR)/build/v14/config.status
 
 # Install the PostgreSQL header files into $(POSTGRES_INSTALL_DIR)/<version>/include
-.PHONY: postgres-v14-headers
+.PHONY: postgres-headers-%
-postgres-v14-headers: postgres-v14-configure
+postgres-headers-%: postgres-configure-%
-	+@echo "Installing PostgreSQL v14 headers"
+	+@echo "Installing PostgreSQL $* headers"
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v14/src/include MAKELEVEL=0 install
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/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
+.PHONY: postgres-%
-postgres-v14: postgres-v14-configure \
+postgres-%: postgres-configure-% \
-		  postgres-v14-headers # to prevent `make install` conflicts with neon's `postgres-headers`
+		  postgres-headers-% # to prevent `make install` conflicts with neon's `postgres-headers`
-	+@echo "Compiling PostgreSQL v14"
+	+@echo "Compiling PostgreSQL $*"
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v14 MAKELEVEL=0 install
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$* MAKELEVEL=0 install
-	+@echo "Compiling libpq v14"
+	+@echo "Compiling libpq $*"
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v14/src/interfaces/libpq install
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/src/interfaces/libpq install
-	+@echo "Compiling pg_buffercache v14"
+	+@echo "Compiling pg_prewarm $*"
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v14/contrib/pg_buffercache install
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pg_prewarm install
-	+@echo "Compiling pageinspect v14"
+	+@echo "Compiling pg_buffercache $*"
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v14/contrib/pageinspect install
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pg_buffercache install
+	+@echo "Compiling pageinspect $*"
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pageinspect install
 
-.PHONY: postgres-v15
+.PHONY: postgres-clean-%
-postgres-v15: postgres-v15-configure \
+postgres-clean-%:
-		  postgres-v15-headers # to prevent `make install` conflicts with neon's `postgres-headers`
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$* MAKELEVEL=0 clean
-	+@echo "Compiling PostgreSQL v15"
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pg_buffercache clean
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v15 MAKELEVEL=0 install
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pageinspect clean
-	+@echo "Compiling libpq v15"
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/src/interfaces/libpq clean
-	$(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
+.PHONY: neon-pg-ext-%
-postgres: postgres-v14 postgres-v15
+neon-pg-ext-%: postgres-%
+	+@echo "Compiling neon $*"
+	mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-$*
+	$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
+		-C $(POSTGRES_INSTALL_DIR)/build/neon-$* \
+		-f $(ROOT_PROJECT_DIR)/pgxn/neon/Makefile install
+	+@echo "Compiling neon_walredo $*"
+	mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-walredo-$*
+	$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
+		-C $(POSTGRES_INSTALL_DIR)/build/neon-walredo-$* \
+		-f $(ROOT_PROJECT_DIR)/pgxn/neon_walredo/Makefile install
+	+@echo "Compiling neon_test_utils $*"
+	mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-test-utils-$*
+	$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
+		-C $(POSTGRES_INSTALL_DIR)/build/neon-test-utils-$* \
+		-f $(ROOT_PROJECT_DIR)/pgxn/neon_test_utils/Makefile install
+	+@echo "Compiling neon_utils $*"
+	mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-utils-$*
+	$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
+		-C $(POSTGRES_INSTALL_DIR)/build/neon-utils-$* \
+		-f $(ROOT_PROJECT_DIR)/pgxn/neon_utils/Makefile install
 
-.PHONY: postgres-v14-clean
+.PHONY: neon-pg-ext-clean-%
-postgres-v14-clean:
+neon-pg-ext-clean-%:
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v14 MAKELEVEL=0 clean
+	$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config \
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v14/contrib/pg_buffercache clean
+	-C $(POSTGRES_INSTALL_DIR)/build/neon-$* \
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v14/contrib/pageinspect clean
+	-f $(ROOT_PROJECT_DIR)/pgxn/neon/Makefile clean
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v14/src/interfaces/libpq clean
+	$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config \
+	-C $(POSTGRES_INSTALL_DIR)/build/neon-walredo-$* \
+	-f $(ROOT_PROJECT_DIR)/pgxn/neon_walredo/Makefile clean
+	$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config \
+	-C $(POSTGRES_INSTALL_DIR)/build/neon-test-utils-$* \
+	-f $(ROOT_PROJECT_DIR)/pgxn/neon_test_utils/Makefile clean
+	$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config \
+	-C $(POSTGRES_INSTALL_DIR)/build/neon-utils-$* \
+	-f $(ROOT_PROJECT_DIR)/pgxn/neon_utils/Makefile clean
 
-.PHONY: postgres-v15-clean
+.PHONY: neon-pg-ext
-postgres-v15-clean:
+neon-pg-ext: \
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v15 MAKELEVEL=0 clean
+	neon-pg-ext-v14 \
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v15/contrib/pg_buffercache clean
+	neon-pg-ext-v15
-	$(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_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_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
+neon-pg-ext-clean: \
-	$(MAKE) -C $(ROOT_PROJECT_DIR)/pgxn/neon_test_utils clean
+	neon-pg-ext-clean-v14 \
+	neon-pg-ext-clean-v15
 
-neon-pg-ext: neon-pg-ext-v14 neon-pg-ext-v15
+# shorthand to build all Postgres versions
-postgres-headers: postgres-v14-headers postgres-v15-headers
+.PHONY: postgres
-postgres-clean: postgres-v14-clean postgres-v15-clean
+postgres: \
+	postgres-v14 \
+	postgres-v15
+
+.PHONY: postgres-headers
+postgres-headers: \
+	postgres-headers-v14 \
+	postgres-headers-v15
+
+.PHONY: postgres-clean
+postgres-clean: \
+	postgres-clean-v14 \
+	postgres-clean-v15
 
 # This doesn't remove the effects of 'configure'.
 .PHONY: clean
-clean:
+clean: postgres-clean neon-pg-ext-clean
-	cd $(POSTGRES_INSTALL_DIR)/build/v14 && $(MAKE) clean
-	cd $(POSTGRES_INSTALL_DIR)/build/v15 && $(MAKE) clean
 	$(CARGO_CMD_PREFIX) cargo clean
-	cd pgxn/neon && $(MAKE) clean
-	cd pgxn/neon_test_utils && $(MAKE) clean
 
 # This removes everything
 .PHONY: distclean

README.md

@@ -2,29 +2,20 @@
 
 Neon is a serverless open-source alternative to AWS Aurora Postgres. It separates storage and compute and substitutes the PostgreSQL storage layer by redistributing data across a cluster of nodes.
 
-The project used to be called "Zenith". Many of the commands and code comments
-still refer to "zenith", but we are in the process of renaming things.
-
 ## Quick start
-[Join the waitlist](https://neon.tech/) for our free tier to receive your serverless postgres instance. Then connect to it with your preferred postgres client (psql, dbeaver, etc) or use the online SQL editor.
+Try the [Neon Free Tier](https://neon.tech/docs/introduction/technical-preview-free-tier/) to create a serverless Postgres instance. Then connect to it with your preferred Postgres client (psql, dbeaver, etc) or use the online [SQL Editor](https://neon.tech/docs/get-started-with-neon/query-with-neon-sql-editor/). See [Connect from any application](https://neon.tech/docs/connect/connect-from-any-app/) for connection instructions.
 
 Alternatively, compile and run the project [locally](#running-local-installation).
 
 ## Architecture overview
 
-A Neon installation consists of compute nodes and a Neon storage engine.
+A Neon installation consists of compute nodes and the Neon storage engine. Compute nodes are stateless PostgreSQL nodes backed by the Neon storage engine.
-
-Compute nodes are stateless PostgreSQL nodes backed by the Neon storage engine.
 
 The Neon storage engine consists of two major components:
 - Pageserver. Scalable storage backend for the compute nodes.
-- WAL service. The service receives WAL from the compute node and ensures that it is stored durably.
+- Safekeepers. The safekeepers form a redundant WAL service that received WAL from the compute node, and stores it durably until it has been processed by the pageserver and uploaded to cloud storage.
 
-Pageserver consists of:
+See developer documentation in [/docs/SUMMARY.md](/docs/SUMMARY.md) for more information.
-- Repository - Neon storage implementation.
-- 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
 
@@ -35,13 +26,21 @@ 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
+libssl-dev clang pkg-config libpq-dev cmake postgresql-client protobuf-compiler
 ```
 * 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
+  libseccomp-devel perl clang cmake postgresql postgresql-contrib protobuf-compiler \
+  protobuf-devel
 ```
+* On Arch based systems, these packages are needed:
+```bash
+pacman -S base-devel readline zlib libseccomp openssl clang \
+postgresql-libs cmake postgresql protobuf
+```
+
+Building Neon requires 3.15+ version of `protoc` (protobuf-compiler). If your distribution provides an older version, you can install a newer version from [here](https://github.com/protocolbuffers/protobuf/releases).
 
 2. [Install Rust](https://www.rust-lang.org/tools/install)
 ```
@@ -49,11 +48,14 @@ dnf install flex bison readline-devel zlib-devel openssl-devel \
 curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
 ```
 
-#### Installing dependencies on OSX (12.3.1)
+#### Installing dependencies on macOS (12.3.1)
 1. Install XCode and dependencies
 ```
 xcode-select --install
-brew install protobuf etcd openssl
+brew install protobuf openssl flex bison
+
+# add openssl to PATH, required for ed25519 keys generation in neon_local
+echo 'export PATH="$(brew --prefix openssl)/bin:$PATH"' >> ~/.zshrc
 ```
 
 2. [Install Rust](https://www.rust-lang.org/tools/install)
@@ -91,9 +93,10 @@ 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`"
+# use "BUILD_TYPE=release make -j`nproc` -s"
+# Remove -s for the verbose build log
 
-make -j`nproc`
+make -j`nproc` -s
 ```
 
 #### Building on OSX
@@ -107,16 +110,17 @@ 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`"
+# use "BUILD_TYPE=release make -j`sysctl -n hw.logicalcpu` -s"
+# Remove -s for the verbose build log
 
-make -j`sysctl -n hw.logicalcpu`
+make -j`sysctl -n hw.logicalcpu` -s
 ```
 
 #### 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 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.
+Python (3.9 or higher), and install python3 packages using `./scripts/pysync` (requires [poetry>=1.3](https://python-poetry.org/)) in the project directory.
 
 
 #### Running neon database
@@ -125,30 +129,32 @@ 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'
+Starting pageserver at '127.0.0.1:64000' in '.neon'.
 
-Pageserver started
+# start pageserver, safekeeper, and broker for their intercommunication
-Successfully initialized timeline 7dd0907914ac399ff3be45fb252bfdb7
-Stopping pageserver gracefully...done!
-
-# start pageserver and safekeeper
 > ./target/debug/neon_local start
-Starting etcd broker using /usr/bin/etcd
+Starting neon broker at 127.0.0.1:50051
-Starting pageserver at '127.0.0.1:64000' in '.neon'
+storage_broker started, pid: 2918372
+Starting pageserver at '127.0.0.1:64000' in '.neon'.
+pageserver started, pid: 2918386
+Starting safekeeper at '127.0.0.1:5454' in '.neon/safekeepers/sk1'.
+safekeeper 1 started, pid: 2918437
 
-Pageserver started
+# create initial tenant and use it as a default for every future neon_local invocation
-Starting safekeeper at '127.0.0.1:5454' in '.neon/safekeepers/sk1'
+> ./target/debug/neon_local tenant create --set-default
-Safekeeper started
+tenant 9ef87a5bf0d92544f6fafeeb3239695c successfully created on the pageserver
+Created an initial timeline 'de200bd42b49cc1814412c7e592dd6e9' at Lsn 0/16B5A50 for tenant: 9ef87a5bf0d92544f6fafeeb3239695c
+Setting tenant 9ef87a5bf0d92544f6fafeeb3239695c as a default one
 
 # start postgres compute node
-> ./target/debug/neon_local pg start main
+> ./target/debug/neon_local endpoint start main
-Starting new postgres main on timeline de200bd42b49cc1814412c7e592dd6e9 ...
+Starting new endpoint main (PostgreSQL v14) on timeline de200bd42b49cc1814412c7e592dd6e9 ...
 Extracting base backup to create postgres instance: path=.neon/pgdatadirs/tenants/9ef87a5bf0d92544f6fafeeb3239695c/main port=55432
-Starting postgres node at 'host=127.0.0.1 port=55432 user=cloud_admin dbname=postgres'
+Starting postgres at 'host=127.0.0.1 port=55432 user=cloud_admin dbname=postgres'
 
 # check list of running postgres instances
-> ./target/debug/neon_local pg list
+> ./target/debug/neon_local endpoint list
- NODE  ADDRESS          TIMELINE                          BRANCH NAME  LSN        STATUS
+ ENDPOINT  ADDRESS          TIMELINE                          BRANCH NAME  LSN        STATUS
  main      127.0.0.1:55432  de200bd42b49cc1814412c7e592dd6e9  main         0/16B5BA8  running
 ```
 
@@ -178,14 +184,14 @@ Created timeline 'b3b863fa45fa9e57e615f9f2d944e601' at Lsn 0/16F9A00 for tenant:
 (L) ┗━ @0/16F9A00: migration_check [b3b863fa45fa9e57e615f9f2d944e601]
 
 # start postgres on that branch
-> ./target/debug/neon_local pg start migration_check --branch-name migration_check
+> ./target/debug/neon_local endpoint start migration_check --branch-name migration_check
-Starting new postgres migration_check on timeline b3b863fa45fa9e57e615f9f2d944e601 ...
+Starting new endpoint migration_check (PostgreSQL v14) on timeline b3b863fa45fa9e57e615f9f2d944e601 ...
 Extracting base backup to create postgres instance: path=.neon/pgdatadirs/tenants/9ef87a5bf0d92544f6fafeeb3239695c/migration_check port=55433
-Starting postgres node at 'host=127.0.0.1 port=55433 user=cloud_admin dbname=postgres'
+Starting postgres at 'host=127.0.0.1 port=55433 user=cloud_admin dbname=postgres'
 
 # check the new list of running postgres instances
-> ./target/debug/neon_local pg list
+> ./target/debug/neon_local endpoint list
- NODE             ADDRESS          TIMELINE                          BRANCH NAME      LSN        STATUS
+ ENDPOINT         ADDRESS          TIMELINE                          BRANCH NAME      LSN        STATUS
  main             127.0.0.1:55432  de200bd42b49cc1814412c7e592dd6e9  main             0/16F9A38  running
  migration_check  127.0.0.1:55433  b3b863fa45fa9e57e615f9f2d944e601  migration_check  0/16F9A70  running
 
@@ -223,22 +229,27 @@ Ensure your dependencies are installed as described [here](https://github.com/ne
 ```sh
 git clone --recursive https://github.com/neondatabase/neon.git
 
-# either:
 CARGO_BUILD_FLAGS="--features=testing" make
-# or:
-make debug
 
 ./scripts/pytest
 ```
 
 ## Documentation
 
-Now we use README files to cover design ideas and overall architecture for each module and `rustdoc` style documentation comments. See also [/docs/](/docs/) a top-level overview of all available markdown documentation.
+[/docs/](/docs/) Contains a top-level overview of all available markdown documentation.
 
 - [/docs/sourcetree.md](/docs/sourcetree.md) contains overview of source tree layout.
 
 To view your `rustdoc` documentation in a browser, try running `cargo doc --no-deps --open`
 
+See also README files in some source directories, and `rustdoc` style documentation comments.
+
+Other resources:
+
+- [SELECT 'Hello, World'](https://neon.tech/blog/hello-world/): Blog post by Nikita Shamgunov on the high level architecture
+- [Architecture decisions in Neon](https://neon.tech/blog/architecture-decisions-in-neon/): Blog post by Heikki Linnakangas
+- [Neon: Serverless PostgreSQL!](https://www.youtube.com/watch?v=rES0yzeERns): Presentation on storage system by Heikki Linnakangas in the CMU Database Group seminar series
+
 ### Postgres-specific terms
 
 Due to Neon's very close relation with PostgreSQL internals, numerous specific terms are used.

cli-v2-story.md

@@ -1,188 +0,0 @@
-Create a new Zenith repository in the current directory:
-
-    ~/git-sandbox/zenith (cli-v2)$ ./target/debug/cli init
-    The files belonging to this database system will be owned by user "heikki".
-    This user must also own the server process.
-    
-    The database cluster will be initialized with locale "en_GB.UTF-8".
-    The default database encoding has accordingly been set to "UTF8".
-    The default text search configuration will be set to "english".
-    
-    Data page checksums are disabled.
-    
-    creating directory tmp ... ok
-    creating subdirectories ... ok
-    selecting dynamic shared memory implementation ... posix
-    selecting default max_connections ... 100
-    selecting default shared_buffers ... 128MB
-    selecting default time zone ... Europe/Helsinki
-    creating configuration files ... ok
-    running bootstrap script ... ok
-    performing post-bootstrap initialization ... ok
-    syncing data to disk ... ok
-    
-    initdb: warning: enabling "trust" authentication for local connections
-    You can change this by editing pg_hba.conf or using the option -A, or
-    --auth-local and --auth-host, the next time you run initdb.
-    new zenith repository was created in .zenith
-
-Initially, there is only one branch:
-
-    ~/git-sandbox/zenith (cli-v2)$ ./target/debug/cli branch
-      main
-
-Start a local Postgres instance on the branch:
-
-    ~/git-sandbox/zenith (cli-v2)$ ./target/debug/cli start main
-    Creating data directory from snapshot at 0/15FFB08...
-    waiting for server to start....2021-04-13 09:27:43.919 EEST [984664] LOG:  starting PostgreSQL 14devel on x86_64-pc-linux-gnu, compiled by gcc (Debian 10.2.1-6) 10.2.1 20210110, 64-bit
-    2021-04-13 09:27:43.920 EEST [984664] LOG:  listening on IPv6 address "::1", port 5432
-    2021-04-13 09:27:43.920 EEST [984664] LOG:  listening on IPv4 address "127.0.0.1", port 5432
-    2021-04-13 09:27:43.927 EEST [984664] LOG:  listening on Unix socket "/tmp/.s.PGSQL.5432"
-    2021-04-13 09:27:43.939 EEST [984665] LOG:  database system was interrupted; last known up at 2021-04-13 09:27:33 EEST
-    2021-04-13 09:27:43.939 EEST [984665] LOG:  creating missing WAL directory "pg_wal/archive_status"
-    2021-04-13 09:27:44.189 EEST [984665] LOG:  database system was not properly shut down; automatic recovery in progress
-    2021-04-13 09:27:44.195 EEST [984665] LOG:  invalid record length at 0/15FFB80: wanted 24, got 0
-    2021-04-13 09:27:44.195 EEST [984665] LOG:  redo is not required
-    2021-04-13 09:27:44.225 EEST [984664] LOG:  database system is ready to accept connections
-     done
-    server started
-
-Run some commands against it:
-
-    ~/git-sandbox/zenith (cli-v2)$ psql postgres -c "create table foo (t text);" 
-    CREATE TABLE
-    ~/git-sandbox/zenith (cli-v2)$ psql postgres -c "insert into foo values ('inserted on the main branch');" 
-    INSERT 0 1
-    ~/git-sandbox/zenith (cli-v2)$ psql postgres -c "select * from foo" 
-                  t              
-    -----------------------------
-     inserted on the main branch
-    (1 row)
-
-Create a new branch called 'experimental'. We create it from the
-current end of the 'main' branch, but you could specify a different
-LSN as the start point instead.
-
-    ~/git-sandbox/zenith (cli-v2)$ ./target/debug/cli branch experimental main
-    branching at end of WAL: 0/161F478
-    
-    ~/git-sandbox/zenith (cli-v2)$ ./target/debug/cli branch 
-      experimental
-      main
-
-Start another Postgres instance off the 'experimental' branch:
-
-    ~/git-sandbox/zenith (cli-v2)$ ./target/debug/cli start experimental -- -o -p5433
-    Creating data directory from snapshot at 0/15FFB08...
-    waiting for server to start....2021-04-13 09:28:41.874 EEST [984766] LOG:  starting PostgreSQL 14devel on x86_64-pc-linux-gnu, compiled by gcc (Debian 10.2.1-6) 10.2.1 20210110, 64-bit
-    2021-04-13 09:28:41.875 EEST [984766] LOG:  listening on IPv6 address "::1", port 5433
-    2021-04-13 09:28:41.875 EEST [984766] LOG:  listening on IPv4 address "127.0.0.1", port 5433
-    2021-04-13 09:28:41.883 EEST [984766] LOG:  listening on Unix socket "/tmp/.s.PGSQL.5433"
-    2021-04-13 09:28:41.896 EEST [984767] LOG:  database system was interrupted; last known up at 2021-04-13 09:27:33 EEST
-    2021-04-13 09:28:42.265 EEST [984767] LOG:  database system was not properly shut down; automatic recovery in progress
-    2021-04-13 09:28:42.269 EEST [984767] LOG:  redo starts at 0/15FFB80
-    2021-04-13 09:28:42.272 EEST [984767] LOG:  invalid record length at 0/161F4B0: wanted 24, got 0
-    2021-04-13 09:28:42.272 EEST [984767] LOG:  redo done at 0/161F478 system usage: CPU: user: 0.00 s, system: 0.00 s, elapsed: 0.00 s
-    2021-04-13 09:28:42.321 EEST [984766] LOG:  database system is ready to accept connections
-     done
-    server started
-
-Insert some a row on the 'experimental' branch:
-
-    ~/git-sandbox/zenith (cli-v2)$ psql postgres -p5433 -c "select * from foo" 
-                  t              
-    -----------------------------
-     inserted on the main branch
-    (1 row)
-    
-    ~/git-sandbox/zenith (cli-v2)$ psql postgres -p5433 -c "insert into foo values ('inserted on experimental')" 
-    INSERT 0 1
-    ~/git-sandbox/zenith (cli-v2)$ psql postgres -p5433 -c "select * from foo" 
-                  t              
-    -----------------------------
-     inserted on the main branch
-     inserted on experimental
-    (2 rows)
-    
-See that the other Postgres instance is still running on 'main' branch on port 5432:
-
-
-    ~/git-sandbox/zenith (cli-v2)$ psql postgres -p5432 -c "select * from foo" 
-                  t              
-    -----------------------------
-     inserted on the main branch
-    (1 row)
-
-
-
-
-Everything is stored in the .zenith directory:
-
-    ~/git-sandbox/zenith (cli-v2)$ ls -l .zenith/
-    total 12
-    drwxr-xr-x 4 heikki heikki 4096 Apr 13 09:28 datadirs
-    drwxr-xr-x 4 heikki heikki 4096 Apr 13 09:27 refs
-    drwxr-xr-x 4 heikki heikki 4096 Apr 13 09:28 timelines
-
-The 'datadirs' directory contains the datadirs of the running instances:
-
-    ~/git-sandbox/zenith (cli-v2)$ ls -l .zenith/datadirs/
-    total 8
-    drwx------ 18 heikki heikki 4096 Apr 13 09:27 3c0c634c1674079b2c6d4edf7c91523e
-    drwx------ 18 heikki heikki 4096 Apr 13 09:28 697e3c103d4b1763cd6e82e4ff361d76
-    ~/git-sandbox/zenith (cli-v2)$ ls -l .zenith/datadirs/3c0c634c1674079b2c6d4edf7c91523e/
-    total 124
-    drwxr-xr-x 5 heikki heikki  4096 Apr 13 09:27 base
-    drwxr-xr-x 2 heikki heikki  4096 Apr 13 09:27 global
-    drwxr-xr-x 2 heikki heikki  4096 Apr 13 09:27 pg_commit_ts
-    drwxr-xr-x 2 heikki heikki  4096 Apr 13 09:27 pg_dynshmem
-    -rw------- 1 heikki heikki  4760 Apr 13 09:27 pg_hba.conf
-    -rw------- 1 heikki heikki  1636 Apr 13 09:27 pg_ident.conf
-    drwxr-xr-x 4 heikki heikki  4096 Apr 13 09:32 pg_logical
-    drwxr-xr-x 4 heikki heikki  4096 Apr 13 09:27 pg_multixact
-    drwxr-xr-x 2 heikki heikki  4096 Apr 13 09:27 pg_notify
-    drwxr-xr-x 2 heikki heikki  4096 Apr 13 09:27 pg_replslot
-    drwxr-xr-x 2 heikki heikki  4096 Apr 13 09:27 pg_serial
-    drwxr-xr-x 2 heikki heikki  4096 Apr 13 09:27 pg_snapshots
-    drwxr-xr-x 2 heikki heikki  4096 Apr 13 09:27 pg_stat
-    drwxr-xr-x 2 heikki heikki  4096 Apr 13 09:34 pg_stat_tmp
-    drwxr-xr-x 2 heikki heikki  4096 Apr 13 09:27 pg_subtrans
-    drwxr-xr-x 2 heikki heikki  4096 Apr 13 09:27 pg_tblspc
-    drwxr-xr-x 2 heikki heikki  4096 Apr 13 09:27 pg_twophase
-    -rw------- 1 heikki heikki     3 Apr 13 09:27 PG_VERSION
-    lrwxrwxrwx 1 heikki heikki    52 Apr 13 09:27 pg_wal -> ../../timelines/3c0c634c1674079b2c6d4edf7c91523e/wal
-    drwxr-xr-x 2 heikki heikki  4096 Apr 13 09:27 pg_xact
-    -rw------- 1 heikki heikki    88 Apr 13 09:27 postgresql.auto.conf
-    -rw------- 1 heikki heikki 28688 Apr 13 09:27 postgresql.conf
-    -rw------- 1 heikki heikki    96 Apr 13 09:27 postmaster.opts
-    -rw------- 1 heikki heikki   149 Apr 13 09:27 postmaster.pid
-
-Note how 'pg_wal' is just a symlink to the 'timelines' directory. The
-datadir is ephemeral, you can delete it at any time, and it can be reconstructed
-from the snapshots and WAL stored in the 'timelines' directory. So if you push/pull
-the repository, the 'datadirs' are not included. (They are like git working trees)
-
-    ~/git-sandbox/zenith (cli-v2)$ killall -9 postgres
-    ~/git-sandbox/zenith (cli-v2)$ rm -rf .zenith/datadirs/*
-    ~/git-sandbox/zenith (cli-v2)$ ./target/debug/cli start experimental -- -o -p5433
-    Creating data directory from snapshot at 0/15FFB08...
-    waiting for server to start....2021-04-13 09:37:05.476 EEST [985340] LOG:  starting PostgreSQL 14devel on x86_64-pc-linux-gnu, compiled by gcc (Debian 10.2.1-6) 10.2.1 20210110, 64-bit
-    2021-04-13 09:37:05.477 EEST [985340] LOG:  listening on IPv6 address "::1", port 5433
-    2021-04-13 09:37:05.477 EEST [985340] LOG:  listening on IPv4 address "127.0.0.1", port 5433
-    2021-04-13 09:37:05.487 EEST [985340] LOG:  listening on Unix socket "/tmp/.s.PGSQL.5433"
-    2021-04-13 09:37:05.498 EEST [985341] LOG:  database system was interrupted; last known up at 2021-04-13 09:27:33 EEST
-    2021-04-13 09:37:05.808 EEST [985341] LOG:  database system was not properly shut down; automatic recovery in progress
-    2021-04-13 09:37:05.813 EEST [985341] LOG:  redo starts at 0/15FFB80
-    2021-04-13 09:37:05.815 EEST [985341] LOG:  invalid record length at 0/161F770: wanted 24, got 0
-    2021-04-13 09:37:05.815 EEST [985341] LOG:  redo done at 0/161F738 system usage: CPU: user: 0.00 s, system: 0.00 s, elapsed: 0.00 s
-    2021-04-13 09:37:05.866 EEST [985340] LOG:  database system is ready to accept connections
-     done
-    server started
-    ~/git-sandbox/zenith (cli-v2)$ psql postgres -p5433 -c "select * from foo" 
-                  t              
-    -----------------------------
-     inserted on the main branch
-     inserted on experimental
-    (2 rows)
-

compute_tools/Cargo.toml

@@ -1,23 +1,32 @@
 [package]
 name = "compute_tools"
 version = "0.1.0"
-edition = "2021"
+edition.workspace = true
+license.workspace = true
 
 [dependencies]
-anyhow = "1.0"
+anyhow.workspace = true
-chrono = "0.4"
+chrono.workspace = true
-clap = "4.0"
+clap.workspace = true
-env_logger = "0.9"
+futures.workspace = true
-futures = "0.3.13"
+hyper = { workspace = true, features = ["full"] }
-hyper = { version = "0.14", features = ["full"] }
+notify.workspace = true
-log = { version = "0.4", features = ["std", "serde"] }
+num_cpus.workspace = true
-notify = "5.0.0"
+opentelemetry.workspace = true
-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev="d052ee8b86fff9897c77b0fe89ea9daba0e1fa38" }
+postgres.workspace = true
-regex = "1"
+regex.workspace = true
-serde = { version = "1.0", features = ["derive"] }
+serde.workspace = true
-serde_json = "1"
+serde_json.workspace = true
-tar = "0.4"
+tar.workspace = true
-tokio = { version = "1.17", features = ["macros", "rt", "rt-multi-thread"] }
+reqwest = { workspace = true, features = ["json"] }
-tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev="d052ee8b86fff9897c77b0fe89ea9daba0e1fa38" }
+tokio = { workspace = true, features = ["rt", "rt-multi-thread"] }
-url = "2.2.2"
+tokio-postgres.workspace = true
-workspace_hack = { version = "0.1", path = "../workspace_hack" }
+tracing.workspace = true
+tracing-opentelemetry.workspace = true
+tracing-subscriber.workspace = true
+tracing-utils.workspace = true
+url.workspace = true
+
+compute_api.workspace = true
+utils.workspace = true
+workspace_hack.workspace = true

compute_tools/README.md

@@ -19,6 +19,10 @@ Also `compute_ctl` spawns two separate service threads:
 - `http-endpoint` runs a Hyper HTTP API server, which serves readiness and the
   last activity requests.
 
+If the `vm-informant` binary is present at `/bin/vm-informant`, it will also be started. For VM
+compute nodes, `vm-informant` communicates with the VM autoscaling system. It coordinates
+downscaling and (eventually) will request immediate upscaling under resource pressure.
+
 Usage example:
 ```sh
 compute_ctl -D /var/db/postgres/compute \

compute_tools/src/bin/compute_ctl.rs

@@ -18,6 +18,10 @@
 //! - `http-endpoint` runs a Hyper HTTP API server, which serves readiness and the
 //!   last activity requests.
 //!
+//! If the `vm-informant` binary is present at `/bin/vm-informant`, it will also be started. For VM
+//! compute nodes, `vm-informant` communicates with the VM autoscaling system. It coordinates
+//! downscaling and (eventually) will request immediate upscaling under resource pressure.
+//!
 //! Usage example:
 //! ```sh
 //! compute_ctl -D /var/db/postgres/compute \
@@ -30,26 +34,27 @@ use std::fs::File;
 use std::panic;
 use std::path::Path;
 use std::process::exit;
-use std::sync::{Arc, RwLock};
+use std::sync::{mpsc, Arc, Condvar, Mutex};
 use std::{thread, time::Duration};
 
 use anyhow::{Context, Result};
 use chrono::Utc;
 use clap::Arg;
-use log::{error, info};
+use tracing::{error, info};
+use url::Url;
 
-use compute_tools::compute::{ComputeMetrics, ComputeNode, ComputeState, ComputeStatus};
+use compute_api::responses::ComputeStatus;
+
+use compute_tools::compute::{ComputeNode, ComputeState, ParsedSpec};
+use compute_tools::configurator::launch_configurator;
 use compute_tools::http::api::launch_http_server;
 use compute_tools::logger::*;
 use compute_tools::monitor::launch_monitor;
 use compute_tools::params::*;
-use compute_tools::pg_helpers::*;
 use compute_tools::spec::*;
-use url::Url;
 
 fn main() -> Result<()> {
-    // TODO: re-use `utils::logging` later
+    init_tracing_and_logging(DEFAULT_LOG_LEVEL)?;
-    init_logger(DEFAULT_LOG_LEVEL)?;
 
     let matches = cli().get_matches();
 
@@ -59,85 +64,183 @@ fn main() -> Result<()> {
     let connstr = matches
         .get_one::<String>("connstr")
         .expect("Postgres connection string is required");
-    let spec = matches.get_one::<String>("spec");
+    let spec_json = matches.get_one::<String>("spec");
     let spec_path = matches.get_one::<String>("spec-path");
 
+    let compute_id = matches.get_one::<String>("compute-id");
+    let control_plane_uri = matches.get_one::<String>("control-plane-uri");
+
     // Try to use just 'postgres' if no path is provided
     let pgbin = matches.get_one::<String>("pgbin").unwrap();
 
-    let spec: ComputeSpec = match spec {
+    let mut spec = None;
+    let mut live_config_allowed = false;
+    match spec_json {
         // First, try to get cluster spec from the cli argument
-        Some(json) => serde_json::from_str(json)?,
+        Some(json) => {
+            spec = Some(serde_json::from_str(json)?);
+        }
         None => {
             // Second, try to read it from the file if path is provided
             if let Some(sp) = spec_path {
                 let path = Path::new(sp);
                 let file = File::open(path)?;
-                serde_json::from_reader(file)?
+                spec = Some(serde_json::from_reader(file)?);
+            } else if let Some(id) = compute_id {
+                if let Some(cp_base) = control_plane_uri {
+                    live_config_allowed = true;
+                    if let Ok(s) = get_spec_from_control_plane(cp_base, id) {
+                        spec = Some(s);
+                    }
                 } else {
-                panic!("cluster spec should be provided via --spec or --spec-path argument");
+                    panic!("must specify both --control-plane-uri and --compute-id or none");
+                }
+            } else {
+                panic!(
+                    "compute spec should be provided by one of the following ways: \
+                    --spec OR --spec-path OR --control-plane-uri and --compute-id"
+                );
             }
         }
     };
 
-    let pageserver_connstr = spec
+    let mut new_state = ComputeState::new();
-        .cluster
+    let spec_set;
-        .settings
+    if let Some(spec) = spec {
-        .find("neon.pageserver_connstring")
+        let pspec = ParsedSpec::try_from(spec).map_err(|msg| anyhow::anyhow!(msg))?;
-        .expect("pageserver connstr should be provided");
+        new_state.pspec = Some(pspec);
-    let tenant = spec
+        spec_set = true;
-        .cluster
+    } else {
-        .settings
+        spec_set = false;
-        .find("neon.tenant_id")
+    }
-        .expect("tenant id should be provided");
+    let compute_node = ComputeNode {
-    let timeline = spec
-        .cluster
-        .settings
-        .find("neon.timeline_id")
-        .expect("tenant id should be provided");
-
-    let compute_state = ComputeNode {
         start_time: Utc::now(),
         connstr: Url::parse(connstr).context("cannot parse connstr as a URL")?,
         pgdata: pgdata.to_string(),
         pgbin: pgbin.to_string(),
-        spec,
+        live_config_allowed,
-        tenant,
+        state: Mutex::new(new_state),
-        timeline,
+        state_changed: Condvar::new(),
-        pageserver_connstr,
-        metrics: ComputeMetrics::new(),
-        state: RwLock::new(ComputeState::new()),
     };
-    let compute = Arc::new(compute_state);
+    let compute = Arc::new(compute_node);
 
-    // Launch service threads first, so we were able to serve availability
+    // Launch http service first, so we were able to serve control-plane
     // requests, while configuration is still in progress.
     let _http_handle = launch_http_server(&compute).expect("cannot launch http endpoint thread");
-    let _monitor_handle = launch_monitor(&compute).expect("cannot launch compute monitor thread");
 
-    // Run compute (Postgres) and hang waiting on it.
+    if !spec_set {
-    match compute.prepare_and_run() {
+        // No spec provided, hang waiting for it.
-        Ok(ec) => {
+        info!("no compute spec provided, waiting");
-            let code = ec.code().unwrap_or(1);
+        let mut state = compute.state.lock().unwrap();
-            info!("Postgres exited with code {}, shutting down", code);
+        while state.status != ComputeStatus::ConfigurationPending {
-            exit(code)
+            state = compute.state_changed.wait(state).unwrap();
+
+            if state.status == ComputeStatus::ConfigurationPending {
+                info!("got spec, continue configuration");
+                // Spec is already set by the http server handler.
+                break;
+            }
+        }
     }
-        Err(error) => {
-            error!("could not start the compute node: {:?}", error);
 
-            let mut state = compute.state.write().unwrap();
+    // We got all we need, update the state.
-            state.error = Some(format!("{:?}", error));
+    let mut state = compute.state.lock().unwrap();
-            state.status = ComputeStatus::Failed;
+    let pspec = state.pspec.as_ref().expect("spec must be set");
+    let startup_tracing_context = pspec.spec.startup_tracing_context.clone();
+    state.status = ComputeStatus::Init;
+    compute.state_changed.notify_all();
     drop(state);
 
-            // Keep serving HTTP requests, so the cloud control plane was able to
+    // Extract OpenTelemetry context for the startup actions from the spec, and
-            // get the actual error.
+    // attach it to the current tracing context.
+    //
+    // This is used to propagate the context for the 'start_compute' operation
+    // from the neon control plane. This allows linking together the wider
+    // 'start_compute' operation that creates the compute container, with the
+    // startup actions here within the container.
+    //
+    // Switch to the startup context here, and exit it once the startup has
+    // completed and Postgres is up and running.
+    //
+    // NOTE: This is supposed to only cover the *startup* actions. Once
+    // postgres is configured and up-and-running, we exit this span. Any other
+    // actions that are performed on incoming HTTP requests, for example, are
+    // performed in separate spans.
+    let startup_context_guard = if let Some(ref carrier) = startup_tracing_context {
+        use opentelemetry::propagation::TextMapPropagator;
+        use opentelemetry::sdk::propagation::TraceContextPropagator;
+        Some(TraceContextPropagator::new().extract(carrier).attach())
+    } else {
+        None
+    };
+
+    // Launch remaining service threads
+    let _monitor_handle = launch_monitor(&compute).expect("cannot launch compute monitor thread");
+    let _configurator_handle =
+        launch_configurator(&compute).expect("cannot launch configurator thread");
+
+    // Start Postgres
+    let mut delay_exit = false;
+    let mut exit_code = None;
+    let pg = match compute.start_compute() {
+        Ok(pg) => Some(pg),
+        Err(err) => {
+            error!("could not start the compute node: {:?}", err);
+            let mut state = compute.state.lock().unwrap();
+            state.error = Some(format!("{:?}", err));
+            state.status = ComputeStatus::Failed;
+            drop(state);
+            delay_exit = true;
+            None
+        }
+    };
+
+    // Wait for the child Postgres process forever. In this state Ctrl+C will
+    // propagate to Postgres and it will be shut down as well.
+    if let Some(mut pg) = pg {
+        // Startup is finished, exit the startup tracing span
+        drop(startup_context_guard);
+
+        let ecode = pg
+            .wait()
+            .expect("failed to start waiting on Postgres process");
+        info!("Postgres exited with code {}, shutting down", ecode);
+        exit_code = ecode.code()
+    }
+
+    if let Err(err) = compute.check_for_core_dumps() {
+        error!("error while checking for core dumps: {err:?}");
+    }
+
+    // If launch failed, keep serving HTTP requests for a while, so the cloud
+    // control plane can get the actual error.
+    if delay_exit {
         info!("giving control plane 30s to collect the error before shutdown");
         thread::sleep(Duration::from_secs(30));
+    }
+
+    // Shutdown trace pipeline gracefully, so that it has a chance to send any
+    // pending traces before we exit. Shutting down OTEL tracing provider may
+    // hang for quite some time, see, for example:
+    // - https://github.com/open-telemetry/opentelemetry-rust/issues/868
+    // - and our problems with staging https://github.com/neondatabase/cloud/issues/3707#issuecomment-1493983636
+    //
+    // Yet, we want computes to shut down fast enough, as we may need a new one
+    // for the same timeline ASAP. So wait no longer than 2s for the shutdown to
+    // complete, then just error out and exit the main thread.
+    info!("shutting down tracing");
+    let (sender, receiver) = mpsc::channel();
+    let _ = thread::spawn(move || {
+        tracing_utils::shutdown_tracing();
+        sender.send(()).ok()
+    });
+    let shutdown_res = receiver.recv_timeout(Duration::from_millis(2000));
+    if shutdown_res.is_err() {
+        error!("timed out while shutting down tracing, exiting anyway");
+    }
+
     info!("shutting down");
-            Err(error)
+    exit(exit_code.unwrap_or(1))
-        }
-    }
 }
 
 fn cli() -> clap::Command {
@@ -178,6 +281,18 @@ fn cli() -> clap::Command {
                 .long("spec-path")
                 .value_name("SPEC_PATH"),
         )
+        .arg(
+            Arg::new("compute-id")
+                .short('i')
+                .long("compute-id")
+                .value_name("COMPUTE_ID"),
+        )
+        .arg(
+            Arg::new("control-plane-uri")
+                .short('p')
+                .long("control-plane-uri")
+                .value_name("CONTROL_PLANE_API_BASE_URI"),
+        )
 }
 
 #[test]

compute_tools/src/checker.rs

@@ -1,11 +1,28 @@
 use anyhow::{anyhow, Result};
-use log::error;
-use postgres::Client;
 use tokio_postgres::NoTls;
+use tracing::{error, instrument};
 
 use crate::compute::ComputeNode;
 
-pub fn create_writablity_check_data(client: &mut Client) -> Result<()> {
+/// Update timestamp in a row in a special service table to check
+/// that we can actually write some data in this particular timeline.
+/// Create table if it's missing.
+#[instrument(skip_all)]
+pub async fn check_writability(compute: &ComputeNode) -> Result<()> {
+    // Connect to the database.
+    let (client, connection) = tokio_postgres::connect(compute.connstr.as_str(), NoTls).await?;
+    if client.is_closed() {
+        return Err(anyhow!("connection to postgres closed"));
+    }
+
+    // The connection object performs the actual communication with the database,
+    // so spawn it off to run on its own.
+    tokio::spawn(async move {
+        if let Err(e) = connection.await {
+            error!("connection error: {}", e);
+        }
+    });
+
     let query = "
     CREATE TABLE IF NOT EXISTS health_check (
         id serial primary key,
@@ -14,30 +31,15 @@ pub fn create_writablity_check_data(client: &mut Client) -> Result<()> {
     INSERT INTO health_check VALUES (1, now())
         ON CONFLICT (id) DO UPDATE
          SET updated_at = now();";
-    let result = client.simple_query(query)?;
+
-    if result.len() < 2 {
+    let result = client.simple_query(query).await?;
-        return Err(anyhow::format_err!("executed  {} queries", result.len()));
+
-    }
+    if result.len() != 2 {
-    Ok(())
+        return Err(anyhow::format_err!(
-}
+            "expected 2 query results, but got {}",
-
+            result.len()
-pub async fn check_writability(compute: &ComputeNode) -> Result<()> {
+        ));
-    let (client, connection) = tokio_postgres::connect(compute.connstr.as_str(), NoTls).await?;
-    if client.is_closed() {
-        return Err(anyhow!("connection to postgres closed"));
-    }
-    tokio::spawn(async move {
-        if let Err(e) = connection.await {
-            error!("connection error: {}", e);
-        }
-    });
-
-    let result = client
-        .simple_query("UPDATE health_check SET updated_at = now() WHERE id = 1;")
-        .await?;
-
-    if result.len() != 1 {
-        return Err(anyhow!("statement can't be executed"));
     }
+
     Ok(())
 }

compute_tools/src/compute.rs

@@ -17,17 +17,21 @@
 use std::fs;
 use std::os::unix::fs::PermissionsExt;
 use std::path::Path;
-use std::process::{Command, ExitStatus, Stdio};
+use std::process::{Command, Stdio};
-use std::sync::atomic::{AtomicU64, Ordering};
+use std::str::FromStr;
-use std::sync::RwLock;
+use std::sync::{Condvar, Mutex};
 
 use anyhow::{Context, Result};
 use chrono::{DateTime, Utc};
-use log::info;
 use postgres::{Client, NoTls};
-use serde::{Serialize, Serializer};
+use tokio_postgres;
+use tracing::{info, instrument, warn};
+use utils::id::{TenantId, TimelineId};
+use utils::lsn::Lsn;
+
+use compute_api::responses::{ComputeMetrics, ComputeStatus};
+use compute_api::spec::ComputeSpec;
 
-use crate::checker::create_writablity_check_data;
 use crate::config;
 use crate::pg_helpers::*;
 use crate::spec::*;
@@ -39,40 +43,45 @@ pub struct ComputeNode {
     pub connstr: url::Url,
     pub pgdata: String,
     pub pgbin: String,
-    pub spec: ComputeSpec,
+    /// We should only allow live re- / configuration of the compute node if
-    pub tenant: String,
+    /// it uses 'pull model', i.e. it can go to control-plane and fetch
-    pub timeline: String,
+    /// the latest configuration. Otherwise, there could be a case:
-    pub pageserver_connstr: String,
+    /// - we start compute with some spec provided as argument
-    pub metrics: ComputeMetrics,
+    /// - we push new spec and it does reconfiguration
-    /// Volatile part of the `ComputeNode` so should be used under `RwLock`
+    /// - but then something happens and compute pod / VM is destroyed,
-    /// to allow HTTP API server to serve status requests, while configuration
+    ///   so k8s controller starts it again with the **old** spec
-    /// is in progress.
+    /// and the same for empty computes:
-    pub state: RwLock<ComputeState>,
+    /// - we started compute without any spec
+    /// - we push spec and it does configuration
+    /// - but then it is restarted without any spec again
+    pub live_config_allowed: bool,
+    /// Volatile part of the `ComputeNode`, which should be used under `Mutex`.
+    /// To allow HTTP API server to serving status requests, while configuration
+    /// is in progress, lock should be held only for short periods of time to do
+    /// read/write, not the whole configuration process.
+    pub state: Mutex<ComputeState>,
+    /// `Condvar` to allow notifying waiters about state changes.
+    pub state_changed: Condvar,
 }
 
-fn rfc3339_serialize<S>(x: &DateTime<Utc>, s: S) -> Result<S::Ok, S::Error>
+#[derive(Clone, Debug)]
-where
-    S: Serializer,
-{
-    x.to_rfc3339().serialize(s)
-}
-
-#[derive(Serialize)]
-#[serde(rename_all = "snake_case")]
 pub struct ComputeState {
     pub status: ComputeStatus,
     /// Timestamp of the last Postgres activity
-    #[serde(serialize_with = "rfc3339_serialize")]
     pub last_active: DateTime<Utc>,
     pub error: Option<String>,
+    pub pspec: Option<ParsedSpec>,
+    pub metrics: ComputeMetrics,
 }
 
 impl ComputeState {
     pub fn new() -> Self {
         Self {
-            status: ComputeStatus::Init,
+            status: ComputeStatus::Empty,
             last_active: Utc::now(),
             error: None,
+            pspec: None,
+            metrics: ComputeMetrics::default(),
         }
     }
 }
@@ -83,46 +92,58 @@ impl Default for ComputeState {
     }
 }
 
-#[derive(Serialize, Clone, Copy, PartialEq, Eq)]
+#[derive(Clone, Debug)]
-#[serde(rename_all = "snake_case")]
+pub struct ParsedSpec {
-pub enum ComputeStatus {
+    pub spec: ComputeSpec,
-    Init,
+    pub tenant_id: TenantId,
-    Running,
+    pub timeline_id: TimelineId,
-    Failed,
+    pub pageserver_connstr: String,
+    pub storage_auth_token: Option<String>,
 }
 
-#[derive(Serialize)]
+impl TryFrom<ComputeSpec> for ParsedSpec {
-pub struct ComputeMetrics {
+    type Error = String;
-    pub sync_safekeepers_ms: AtomicU64,
+    fn try_from(spec: ComputeSpec) -> Result<Self, String> {
-    pub basebackup_ms: AtomicU64,
+        let pageserver_connstr = spec
-    pub config_ms: AtomicU64,
+            .cluster
-    pub total_startup_ms: AtomicU64,
+            .settings
-}
+            .find("neon.pageserver_connstring")
+            .ok_or("pageserver connstr should be provided")?;
+        let storage_auth_token = spec.storage_auth_token.clone();
+        let tenant_id: TenantId = spec
+            .cluster
+            .settings
+            .find("neon.tenant_id")
+            .ok_or("tenant id should be provided")
+            .map(|s| TenantId::from_str(&s))?
+            .or(Err("invalid tenant id"))?;
+        let timeline_id: TimelineId = spec
+            .cluster
+            .settings
+            .find("neon.timeline_id")
+            .ok_or("timeline id should be provided")
+            .map(|s| TimelineId::from_str(&s))?
+            .or(Err("invalid timeline id"))?;
 
-impl ComputeMetrics {
+        Ok(ParsedSpec {
-    pub fn new() -> Self {
+            spec,
-        Self {
+            pageserver_connstr,
-            sync_safekeepers_ms: AtomicU64::new(0),
+            storage_auth_token,
-            basebackup_ms: AtomicU64::new(0),
+            tenant_id,
-            config_ms: AtomicU64::new(0),
+            timeline_id,
-            total_startup_ms: AtomicU64::new(0),
+        })
-        }
-    }
-}
-
-impl Default for ComputeMetrics {
-    fn default() -> Self {
-        Self::new()
     }
 }
 
 impl ComputeNode {
     pub fn set_status(&self, status: ComputeStatus) {
-        self.state.write().unwrap().status = status;
+        let mut state = self.state.lock().unwrap();
+        state.status = status;
+        self.state_changed.notify_all();
     }
 
     pub fn get_status(&self) -> ComputeStatus {
-        self.state.read().unwrap().status
+        self.state.lock().unwrap().status
     }
 
     // Remove `pgdata` directory and create it again with right permissions.
@@ -138,13 +159,26 @@ impl ComputeNode {
 
     // Get basebackup from the libpq connection to pageserver using `connstr` and
     // unarchive it to `pgdata` directory overriding all its previous content.
-    fn get_basebackup(&self, lsn: &str) -> Result<()> {
+    #[instrument(skip(self, compute_state))]
+    fn get_basebackup(&self, compute_state: &ComputeState, lsn: Lsn) -> Result<()> {
+        let spec = compute_state.pspec.as_ref().expect("spec must be set");
         let start_time = Utc::now();
 
-        let mut client = Client::connect(&self.pageserver_connstr, NoTls)?;
+        let mut config = postgres::Config::from_str(&spec.pageserver_connstr)?;
+
+        // Use the storage auth token from the config file, if given.
+        // Note: this overrides any password set in the connection string.
+        if let Some(storage_auth_token) = &spec.storage_auth_token {
+            info!("Got storage auth token from spec file");
+            config.password(storage_auth_token);
+        } else {
+            info!("Storage auth token not set");
+        }
+
+        let mut client = config.connect(NoTls)?;
         let basebackup_cmd = match lsn {
-            "0/0" => format!("basebackup {} {}", &self.tenant, &self.timeline), // First start of the compute
+            Lsn(0) => format!("basebackup {} {}", spec.tenant_id, spec.timeline_id), // First start of the compute
-            _ => format!("basebackup {} {} {}", &self.tenant, &self.timeline, lsn),
+            _ => format!("basebackup {} {} {}", spec.tenant_id, spec.timeline_id, lsn),
         };
         let copyreader = client.copy_out(basebackup_cmd.as_str())?;
 
@@ -157,26 +191,28 @@ impl ComputeNode {
         ar.set_ignore_zeros(true);
         ar.unpack(&self.pgdata)?;
 
-        self.metrics.basebackup_ms.store(
+        self.state.lock().unwrap().metrics.basebackup_ms = Utc::now()
-            Utc::now()
             .signed_duration_since(start_time)
             .to_std()
             .unwrap()
-                .as_millis() as u64,
+            .as_millis() as u64;
-            Ordering::Relaxed,
-        );
-
         Ok(())
     }
 
     // Run `postgres` in a special mode with `--sync-safekeepers` argument
     // and return the reported LSN back to the caller.
-    fn sync_safekeepers(&self) -> Result<String> {
+    #[instrument(skip(self, storage_auth_token))]
+    fn sync_safekeepers(&self, storage_auth_token: Option<String>) -> Result<Lsn> {
         let start_time = Utc::now();
 
         let sync_handle = Command::new(&self.pgbin)
-            .args(&["--sync-safekeepers"])
+            .args(["--sync-safekeepers"])
             .env("PGDATA", &self.pgdata) // we cannot use -D in this mode
+            .envs(if let Some(storage_auth_token) = &storage_auth_token {
+                vec![("NEON_AUTH_TOKEN", storage_auth_token)]
+            } else {
+                vec![]
+            })
             .stdout(Stdio::piped())
             .spawn()
             .expect("postgres --sync-safekeepers failed to start");
@@ -197,44 +233,42 @@ impl ComputeNode {
             );
         }
 
-        self.metrics.sync_safekeepers_ms.store(
+        self.state.lock().unwrap().metrics.sync_safekeepers_ms = Utc::now()
-            Utc::now()
             .signed_duration_since(start_time)
             .to_std()
             .unwrap()
-                .as_millis() as u64,
+            .as_millis() as u64;
-            Ordering::Relaxed,
-        );
 
-        let lsn = String::from(String::from_utf8(sync_output.stdout)?.trim());
+        let lsn = Lsn::from_str(String::from_utf8(sync_output.stdout)?.trim())?;
 
         Ok(lsn)
     }
 
     /// Do all the preparations like PGDATA directory creation, configuration,
     /// safekeepers sync, basebackup, etc.
-    pub fn prepare_pgdata(&self) -> Result<()> {
+    #[instrument(skip(self, compute_state))]
-        let spec = &self.spec;
+    pub fn prepare_pgdata(&self, compute_state: &ComputeState) -> Result<()> {
+        let pspec = compute_state.pspec.as_ref().expect("spec must be set");
         let pgdata_path = Path::new(&self.pgdata);
 
         // Remove/create an empty pgdata directory and put configuration there.
         self.create_pgdata()?;
-        config::write_postgres_conf(&pgdata_path.join("postgresql.conf"), spec)?;
+        config::write_postgres_conf(&pgdata_path.join("postgresql.conf"), &pspec.spec)?;
 
         info!("starting safekeepers syncing");
         let lsn = self
-            .sync_safekeepers()
+            .sync_safekeepers(pspec.storage_auth_token.clone())
             .with_context(|| "failed to sync safekeepers")?;
         info!("safekeepers synced at LSN {}", lsn);
 
         info!(
             "getting basebackup@{} from pageserver {}",
-            lsn, &self.pageserver_connstr
+            lsn, &pspec.pageserver_connstr
         );
-        self.get_basebackup(&lsn).with_context(|| {
+        self.get_basebackup(compute_state, lsn).with_context(|| {
             format!(
                 "failed to get basebackup@{} from pageserver {}",
-                lsn, &self.pageserver_connstr
+                lsn, &pspec.pageserver_connstr
             )
         })?;
 
@@ -246,23 +280,36 @@ impl ComputeNode {
 
     /// Start Postgres as a child process and manage DBs/roles.
     /// After that this will hang waiting on the postmaster process to exit.
-    pub fn run(&self) -> Result<ExitStatus> {
+    #[instrument(skip(self))]
-        let start_time = Utc::now();
+    pub fn start_postgres(
-
+        &self,
+        storage_auth_token: Option<String>,
+    ) -> Result<std::process::Child> {
         let pgdata_path = Path::new(&self.pgdata);
 
         // Run postgres as a child process.
         let mut pg = Command::new(&self.pgbin)
-            .args(&["-D", &self.pgdata])
+            .args(["-D", &self.pgdata])
+            .envs(if let Some(storage_auth_token) = &storage_auth_token {
+                vec![("NEON_AUTH_TOKEN", storage_auth_token)]
+            } else {
+                vec![]
+            })
             .spawn()
             .expect("cannot start postgres process");
 
         wait_for_postgres(&mut pg, pgdata_path)?;
 
+        Ok(pg)
+    }
+
+    /// Do initial configuration of the already started Postgres.
+    #[instrument(skip(self, compute_state))]
+    pub fn apply_config(&self, compute_state: &ComputeState) -> Result<()> {
         // If connection fails,
         // it may be the old node with `zenith_admin` superuser.
         //
-        // In this case we need to connect with old `zenith_admin`name
+        // In this case we need to connect with old `zenith_admin` name
         // and create new user. We cannot simply rename connected user,
         // but we can create a new one and grant it all privileges.
         let mut client = match Client::connect(self.connstr.as_str(), NoTls) {
@@ -288,59 +335,206 @@ impl ComputeNode {
             Ok(client) => client,
         };
 
-        handle_roles(&self.spec, &mut client)?;
+        // Proceed with post-startup configuration. Note, that order of operations is important.
-        handle_databases(&self.spec, &mut client)?;
+        let spec = &compute_state.pspec.as_ref().expect("spec must be set").spec;
-        handle_role_deletions(self, &mut client)?;
+        handle_roles(spec, &mut client)?;
-        handle_grants(self, &mut client)?;
+        handle_databases(spec, &mut client)?;
-        create_writablity_check_data(&mut client)?;
+        handle_role_deletions(spec, self.connstr.as_str(), &mut client)?;
+        handle_grants(spec, self.connstr.as_str(), &mut client)?;
+        handle_extensions(spec, &mut client)?;
 
         // 'Close' connection
         drop(client);
-        let startup_end_time = Utc::now();
-
-        self.metrics.config_ms.store(
-            startup_end_time
-                .signed_duration_since(start_time)
-                .to_std()
-                .unwrap()
-                .as_millis() as u64,
-            Ordering::Relaxed,
-        );
-        self.metrics.total_startup_ms.store(
-            startup_end_time
-                .signed_duration_since(self.start_time)
-                .to_std()
-                .unwrap()
-                .as_millis() as u64,
-            Ordering::Relaxed,
-        );
-
-        self.set_status(ComputeStatus::Running);
 
         info!(
             "finished configuration of compute for project {}",
-            self.spec.cluster.cluster_id
+            spec.cluster.cluster_id
         );
 
-        // Wait for child Postgres process basically forever. In this state Ctrl+C
+        Ok(())
-        // will propagate to Postgres and it will be shut down as well.
-        let ecode = pg
-            .wait()
-            .expect("failed to start waiting on Postgres process");
-
-        Ok(ecode)
     }
 
-    pub fn prepare_and_run(&self) -> Result<ExitStatus> {
+    // We could've wrapped this around `pg_ctl reload`, but right now we don't use
+    // `pg_ctl` for start / stop, so this just seems much easier to do as we already
+    // have opened connection to Postgres and superuser access.
+    #[instrument(skip(self, client))]
+    fn pg_reload_conf(&self, client: &mut Client) -> Result<()> {
+        client.simple_query("SELECT pg_reload_conf()")?;
+        Ok(())
+    }
+
+    /// Similar to `apply_config()`, but does a bit different sequence of operations,
+    /// as it's used to reconfigure a previously started and configured Postgres node.
+    #[instrument(skip(self))]
+    pub fn reconfigure(&self) -> Result<()> {
+        let spec = self.state.lock().unwrap().pspec.clone().unwrap().spec;
+
+        // Write new config
+        let pgdata_path = Path::new(&self.pgdata);
+        config::write_postgres_conf(&pgdata_path.join("postgresql.conf"), &spec)?;
+
+        let mut client = Client::connect(self.connstr.as_str(), NoTls)?;
+        self.pg_reload_conf(&mut client)?;
+
+        // Proceed with post-startup configuration. Note, that order of operations is important.
+        handle_roles(&spec, &mut client)?;
+        handle_databases(&spec, &mut client)?;
+        handle_role_deletions(&spec, self.connstr.as_str(), &mut client)?;
+        handle_grants(&spec, self.connstr.as_str(), &mut client)?;
+        handle_extensions(&spec, &mut client)?;
+
+        // 'Close' connection
+        drop(client);
+
+        let unknown_op = "unknown".to_string();
+        let op_id = spec.operation_uuid.as_ref().unwrap_or(&unknown_op);
+        info!(
+            "finished reconfiguration of compute node for operation {}",
+            op_id
+        );
+
+        Ok(())
+    }
+
+    #[instrument(skip(self))]
+    pub fn start_compute(&self) -> Result<std::process::Child> {
+        let compute_state = self.state.lock().unwrap().clone();
+        let spec = compute_state.pspec.as_ref().expect("spec must be set");
         info!(
             "starting compute for project {}, operation {}, tenant {}, timeline {}",
-            self.spec.cluster.cluster_id,
+            spec.spec.cluster.cluster_id,
-            self.spec.operation_uuid.as_ref().unwrap(),
+            spec.spec.operation_uuid.as_deref().unwrap_or("None"),
-            self.tenant,
+            spec.tenant_id,
-            self.timeline,
+            spec.timeline_id,
         );
 
-        self.prepare_pgdata()?;
+        self.prepare_pgdata(&compute_state)?;
-        self.run()
+
+        let start_time = Utc::now();
+
+        let pg = self.start_postgres(spec.storage_auth_token.clone())?;
+
+        self.apply_config(&compute_state)?;
+
+        let startup_end_time = Utc::now();
+        {
+            let mut state = self.state.lock().unwrap();
+            state.metrics.config_ms = startup_end_time
+                .signed_duration_since(start_time)
+                .to_std()
+                .unwrap()
+                .as_millis() as u64;
+            state.metrics.total_startup_ms = startup_end_time
+                .signed_duration_since(self.start_time)
+                .to_std()
+                .unwrap()
+                .as_millis() as u64;
+        }
+        self.set_status(ComputeStatus::Running);
+
+        Ok(pg)
+    }
+
+    // Look for core dumps and collect backtraces.
+    //
+    // EKS worker nodes have following core dump settings:
+    //   /proc/sys/kernel/core_pattern -> core
+    //   /proc/sys/kernel/core_uses_pid -> 1
+    //   ulimint -c -> unlimited
+    // which results in core dumps being written to postgres data directory as core.<pid>.
+    //
+    // Use that as a default location and pattern, except macos where core dumps are written
+    // to /cores/ directory by default.
+    pub fn check_for_core_dumps(&self) -> Result<()> {
+        let core_dump_dir = match std::env::consts::OS {
+            "macos" => Path::new("/cores/"),
+            _ => Path::new(&self.pgdata),
+        };
+
+        // Collect core dump paths if any
+        info!("checking for core dumps in {}", core_dump_dir.display());
+        let files = fs::read_dir(core_dump_dir)?;
+        let cores = files.filter_map(|entry| {
+            let entry = entry.ok()?;
+            let _ = entry.file_name().to_str()?.strip_prefix("core.")?;
+            Some(entry.path())
+        });
+
+        // Print backtrace for each core dump
+        for core_path in cores {
+            warn!(
+                "core dump found: {}, collecting backtrace",
+                core_path.display()
+            );
+
+            // Try first with gdb
+            let backtrace = Command::new("gdb")
+                .args(["--batch", "-q", "-ex", "bt", &self.pgbin])
+                .arg(&core_path)
+                .output();
+
+            // Try lldb if no gdb is found -- that is handy for local testing on macOS
+            let backtrace = match backtrace {
+                Err(ref e) if e.kind() == std::io::ErrorKind::NotFound => {
+                    warn!("cannot find gdb, trying lldb");
+                    Command::new("lldb")
+                        .arg("-c")
+                        .arg(&core_path)
+                        .args(["--batch", "-o", "bt all", "-o", "quit"])
+                        .output()
+                }
+                _ => backtrace,
+            }?;
+
+            warn!(
+                "core dump backtrace: {}",
+                String::from_utf8_lossy(&backtrace.stdout)
+            );
+            warn!(
+                "debugger stderr: {}",
+                String::from_utf8_lossy(&backtrace.stderr)
+            );
+        }
+
+        Ok(())
+    }
+
+    /// Select `pg_stat_statements` data and return it as a stringified JSON
+    pub async fn collect_insights(&self) -> String {
+        let mut result_rows: Vec<String> = Vec::new();
+        let connect_result = tokio_postgres::connect(self.connstr.as_str(), NoTls).await;
+        let (client, connection) = connect_result.unwrap();
+        tokio::spawn(async move {
+            if let Err(e) = connection.await {
+                eprintln!("connection error: {}", e);
+            }
+        });
+        let result = client
+            .simple_query(
+                "SELECT
+    row_to_json(pg_stat_statements)
+FROM
+    pg_stat_statements
+WHERE
+    userid != 'cloud_admin'::regrole::oid
+ORDER BY
+    (mean_exec_time + mean_plan_time) DESC
+LIMIT 100",
+            )
+            .await;
+
+        if let Ok(raw_rows) = result {
+            for message in raw_rows.iter() {
+                if let postgres::SimpleQueryMessage::Row(row) = message {
+                    if let Some(json) = row.get(0) {
+                        result_rows.push(json.to_string());
+                    }
+                }
+            }
+
+            format!("{{\"pg_stat_statements\": [{}]}}", result_rows.join(","))
+        } else {
+            "{{\"pg_stat_statements\": []}}".to_string()
+        }
     }
 }

compute_tools/src/config.rs

@@ -6,7 +6,7 @@ use std::path::Path;
 use anyhow::Result;
 
 use crate::pg_helpers::PgOptionsSerialize;
-use crate::spec::ComputeSpec;
+use compute_api::spec::ComputeSpec;
 
 /// Check that `line` is inside a text file and put it there if it is not.
 /// Create file if it doesn't exist.

compute_tools/src/configurator.rs

@@ -0,0 +1,54 @@
+use std::sync::Arc;
+use std::thread;
+
+use anyhow::Result;
+use tracing::{error, info, instrument};
+
+use compute_api::responses::ComputeStatus;
+
+use crate::compute::ComputeNode;
+
+#[instrument(skip(compute))]
+fn configurator_main_loop(compute: &Arc<ComputeNode>) {
+    info!("waiting for reconfiguration requests");
+    loop {
+        let state = compute.state.lock().unwrap();
+        let mut state = compute.state_changed.wait(state).unwrap();
+
+        if state.status == ComputeStatus::ConfigurationPending {
+            info!("got configuration request");
+            state.status = ComputeStatus::Configuration;
+            compute.state_changed.notify_all();
+            drop(state);
+
+            let mut new_status = ComputeStatus::Failed;
+            if let Err(e) = compute.reconfigure() {
+                error!("could not configure compute node: {}", e);
+            } else {
+                new_status = ComputeStatus::Running;
+                info!("compute node configured");
+            }
+
+            // XXX: used to test that API is blocking
+            // std::thread::sleep(std::time::Duration::from_millis(10000));
+
+            compute.set_status(new_status);
+        } else if state.status == ComputeStatus::Failed {
+            info!("compute node is now in Failed state, exiting");
+            break;
+        } else {
+            info!("woken up for compute status: {:?}, sleeping", state.status);
+        }
+    }
+}
+
+pub fn launch_configurator(compute: &Arc<ComputeNode>) -> Result<thread::JoinHandle<()>> {
+    let compute = Arc::clone(compute);
+
+    Ok(thread::Builder::new()
+        .name("compute-configurator".into())
+        .spawn(move || {
+            configurator_main_loop(&compute);
+            info!("configurator thread is exited");
+        })?)
+}

compute_tools/src/http/api.rs

@@ -3,65 +3,120 @@ use std::net::SocketAddr;
 use std::sync::Arc;
 use std::thread;
 
+use crate::compute::{ComputeNode, ComputeState, ParsedSpec};
+use compute_api::requests::ConfigurationRequest;
+use compute_api::responses::{ComputeStatus, ComputeStatusResponse, GenericAPIError};
+
 use anyhow::Result;
 use hyper::service::{make_service_fn, service_fn};
 use hyper::{Body, Method, Request, Response, Server, StatusCode};
-use log::{error, info};
+use num_cpus;
 use serde_json;
+use tokio::task;
+use tracing::{error, info};
+use tracing_utils::http::OtelName;
 
-use crate::compute::{ComputeNode, ComputeStatus};
+fn status_response_from_state(state: &ComputeState) -> ComputeStatusResponse {
+    ComputeStatusResponse {
+        tenant: state
+            .pspec
+            .as_ref()
+            .map(|pspec| pspec.tenant_id.to_string()),
+        timeline: state
+            .pspec
+            .as_ref()
+            .map(|pspec| pspec.timeline_id.to_string()),
+        status: state.status,
+        last_active: state.last_active,
+        error: state.error.clone(),
+    }
+}
 
 // Service function to handle all available routes.
-async fn routes(req: Request<Body>, compute: Arc<ComputeNode>) -> Response<Body> {
+async fn routes(req: Request<Body>, compute: &Arc<ComputeNode>) -> Response<Body> {
+    //
+    // NOTE: The URI path is currently included in traces. That's OK because
+    // it doesn't contain any variable parts or sensitive information. But
+    // please keep that in mind if you change the routing here.
+    //
     match (req.method(), req.uri().path()) {
-        // Timestamp of the last Postgres activity in the plain text.
-        // DEPRECATED in favour of /status
-        (&Method::GET, "/last_activity") => {
-            info!("serving /last_active GET request");
-            let state = compute.state.read().unwrap();
-
-            // Use RFC3339 format for consistency.
-            Response::new(Body::from(state.last_active.to_rfc3339()))
-        }
-
-        // Has compute setup process finished? -> true/false.
-        // DEPRECATED in favour of /status
-        (&Method::GET, "/ready") => {
-            info!("serving /ready GET request");
-            let status = compute.get_status();
-            Response::new(Body::from(format!("{}", status == ComputeStatus::Running)))
-        }
-
         // Serialized compute state.
         (&Method::GET, "/status") => {
             info!("serving /status GET request");
-            let state = compute.state.read().unwrap();
+            let state = compute.state.lock().unwrap();
-            Response::new(Body::from(serde_json::to_string(&*state).unwrap()))
+            let status_response = status_response_from_state(&state);
+            Response::new(Body::from(serde_json::to_string(&status_response).unwrap()))
         }
 
         // Startup metrics in JSON format. Keep /metrics reserved for a possible
         // future use for Prometheus metrics format.
         (&Method::GET, "/metrics.json") => {
             info!("serving /metrics.json GET request");
-            Response::new(Body::from(serde_json::to_string(&compute.metrics).unwrap()))
+            let metrics = compute.state.lock().unwrap().metrics.clone();
+            Response::new(Body::from(serde_json::to_string(&metrics).unwrap()))
         }
 
-        // DEPRECATED, use POST instead
+        // Collect Postgres current usage insights
-        (&Method::GET, "/check_writability") => {
+        (&Method::GET, "/insights") => {
-            info!("serving /check_writability GET request");
+            info!("serving /insights GET request");
-            let res = crate::checker::check_writability(&compute).await;
+            let status = compute.get_status();
-            match res {
+            if status != ComputeStatus::Running {
-                Ok(_) => Response::new(Body::from("true")),
+                let msg = format!("compute is not running, current status: {:?}", status);
-                Err(e) => Response::new(Body::from(e.to_string())),
+                error!(msg);
+                return Response::new(Body::from(msg));
             }
+
+            let insights = compute.collect_insights().await;
+            Response::new(Body::from(insights))
         }
 
         (&Method::POST, "/check_writability") => {
             info!("serving /check_writability POST request");
-            let res = crate::checker::check_writability(&compute).await;
+            let status = compute.get_status();
+            if status != ComputeStatus::Running {
+                let msg = format!(
+                    "invalid compute status for check_writability request: {:?}",
+                    status
+                );
+                error!(msg);
+                return Response::new(Body::from(msg));
+            }
+
+            let res = crate::checker::check_writability(compute).await;
             match res {
                 Ok(_) => Response::new(Body::from("true")),
-                Err(e) => Response::new(Body::from(e.to_string())),
+                Err(e) => {
+                    error!("check_writability failed: {}", e);
+                    Response::new(Body::from(e.to_string()))
+                }
+            }
+        }
+
+        (&Method::GET, "/info") => {
+            let num_cpus = num_cpus::get_physical();
+            info!("serving /info GET request. num_cpus: {}", num_cpus);
+            Response::new(Body::from(
+                serde_json::json!({
+                    "num_cpus": num_cpus,
+                })
+                .to_string(),
+            ))
+        }
+
+        // Accept spec in JSON format and request compute configuration. If
+        // anything goes wrong after we set the compute status to `ConfigurationPending`
+        // and update compute state with new spec, we basically leave compute
+        // in the potentially wrong state. That said, it's control-plane's
+        // responsibility to watch compute state after reconfiguration request
+        // and to clean restart in case of errors.
+        (&Method::POST, "/configure") => {
+            info!("serving /configure POST request");
+            match handle_configure_request(req, compute).await {
+                Ok(msg) => Response::new(Body::from(msg)),
+                Err((msg, code)) => {
+                    error!("error handling /configure request: {msg}");
+                    render_json_error(&msg, code)
+                }
             }
         }
 
@@ -74,6 +129,94 @@ async fn routes(req: Request<Body>, compute: Arc<ComputeNode>) -> Response<Body>
     }
 }
 
+async fn handle_configure_request(
+    req: Request<Body>,
+    compute: &Arc<ComputeNode>,
+) -> Result<String, (String, StatusCode)> {
+    if !compute.live_config_allowed {
+        return Err((
+            "live configuration is not allowed for this compute node".to_string(),
+            StatusCode::PRECONDITION_FAILED,
+        ));
+    }
+
+    let body_bytes = hyper::body::to_bytes(req.into_body()).await.unwrap();
+    let spec_raw = String::from_utf8(body_bytes.to_vec()).unwrap();
+    if let Ok(request) = serde_json::from_str::<ConfigurationRequest>(&spec_raw) {
+        let spec = request.spec;
+
+        let parsed_spec = match ParsedSpec::try_from(spec) {
+            Ok(ps) => ps,
+            Err(msg) => return Err((msg, StatusCode::PRECONDITION_FAILED)),
+        };
+
+        // XXX: wrap state update under lock in code blocks. Otherwise,
+        // we will try to `Send` `mut state` into the spawned thread
+        // bellow, which will cause error:
+        // ```
+        // error: future cannot be sent between threads safely
+        // ```
+        {
+            let mut state = compute.state.lock().unwrap();
+            if state.status != ComputeStatus::Empty && state.status != ComputeStatus::Running {
+                let msg = format!(
+                    "invalid compute status for configuration request: {:?}",
+                    state.status.clone()
+                );
+                return Err((msg, StatusCode::PRECONDITION_FAILED));
+            }
+            state.pspec = Some(parsed_spec);
+            state.status = ComputeStatus::ConfigurationPending;
+            compute.state_changed.notify_all();
+            drop(state);
+            info!("set new spec and notified waiters");
+        }
+
+        // Spawn a blocking thread to wait for compute to become Running.
+        // This is needed to do not block the main pool of workers and
+        // be able to serve other requests while some particular request
+        // is waiting for compute to finish configuration.
+        let c = compute.clone();
+        task::spawn_blocking(move || {
+            let mut state = c.state.lock().unwrap();
+            while state.status != ComputeStatus::Running {
+                state = c.state_changed.wait(state).unwrap();
+                info!(
+                    "waiting for compute to become Running, current status: {:?}",
+                    state.status
+                );
+
+                if state.status == ComputeStatus::Failed {
+                    let err = state.error.as_ref().map_or("unknown error", |x| x);
+                    let msg = format!("compute configuration failed: {:?}", err);
+                    return Err((msg, StatusCode::INTERNAL_SERVER_ERROR));
+                }
+            }
+
+            Ok(())
+        })
+        .await
+        .unwrap()?;
+
+        // Return current compute state if everything went well.
+        let state = compute.state.lock().unwrap().clone();
+        let status_response = status_response_from_state(&state);
+        Ok(serde_json::to_string(&status_response).unwrap())
+    } else {
+        Err(("invalid spec".to_string(), StatusCode::BAD_REQUEST))
+    }
+}
+
+fn render_json_error(e: &str, status: StatusCode) -> Response<Body> {
+    let error = GenericAPIError {
+        error: e.to_string(),
+    };
+    Response::builder()
+        .status(status)
+        .body(Body::from(serde_json::to_string(&error).unwrap()))
+        .unwrap()
+}
+
 // Main Hyper HTTP server function that runs it and blocks waiting on it forever.
 #[tokio::main]
 async fn serve(state: Arc<ComputeNode>) {
@@ -84,7 +227,19 @@ async fn serve(state: Arc<ComputeNode>) {
         async move {
             Ok::<_, Infallible>(service_fn(move |req: Request<Body>| {
                 let state = state.clone();
-                async move { Ok::<_, Infallible>(routes(req, state).await) }
+                async move {
+                    Ok::<_, Infallible>(
+                        // NOTE: We include the URI path in the string. It
+                        // doesn't contain any variable parts or sensitive
+                        // information in this API.
+                        tracing_utils::http::tracing_handler(
+                            req,
+                            |req| routes(req, &state),
+                            OtelName::UriPath,
+                        )
+                        .await,
+                    )
+                }
             }))
         }
     });

compute_tools/src/http/openapi_spec.yaml

@@ -10,12 +10,12 @@ paths:
   /status:
     get:
       tags:
-      - "info"
+      - Info
-      summary: Get compute node internal status
+      summary: Get compute node internal status.
       description: ""
       operationId: getComputeStatus
       responses:
-        "200":
+        200:
           description: ComputeState
           content:
             application/json:
@@ -25,86 +25,121 @@ paths:
   /metrics.json:
     get:
       tags:
-      - "info"
+      - Info
-      summary: Get compute node startup metrics in JSON format
+      summary: Get compute node startup metrics in JSON format.
       description: ""
       operationId: getComputeMetricsJSON
       responses:
-        "200":
+        200:
           description: ComputeMetrics
           content:
             application/json:
               schema:
                 $ref: "#/components/schemas/ComputeMetrics"
 
-  /ready:
+  /insights:
     get:
-      deprecated: true
       tags:
-      - "info"
+      - Info
-      summary: Check whether compute startup process finished successfully
+      summary: Get current compute insights in JSON format.
-      description: ""
+      description: |
-      operationId: computeIsReady
+        Note, that this doesn't include any historical data.
+      operationId: getComputeInsights
       responses:
-        "200":
+        200:
-          description: Compute is ready ('true') or not ('false')
+          description: Compute insights
           content:
-            text/plain:
+            application/json:
               schema:
-                type: string
+                $ref: "#/components/schemas/ComputeInsights"
-                example: "true"
 
-  /last_activity:
+  /info:
     get:
-      deprecated: true
       tags:
-      - "info"
+      - Info
-      summary: Get timestamp of the last compute activity
+      summary: Get info about the compute pod / VM.
       description: ""
-      operationId: getLastComputeActivityTS
+      operationId: getInfo
       responses:
-        "200":
+        200:
-          description: Timestamp of the last compute activity
+          description: Info
           content:
-            text/plain:
+            application/json:
               schema:
-                type: string
+                $ref: "#/components/schemas/Info"
-                example: "2022-10-12T07:20:50.52Z"
 
   /check_writability:
-    get:
-      deprecated: true
-      tags:
-      - "check"
-      summary: Check that we can write new data on this compute
-      description: ""
-      operationId: checkComputeWritabilityDeprecated
-      responses:
-        "200":
-          description: Check result
-          content:
-            text/plain:
-              schema:
-                type: string
-                description: Error text or 'true' if check passed
-                example: "true"
-
     post:
       tags:
-      - "check"
+      - Check
-      summary: Check that we can write new data on this compute
+      summary: Check that we can write new data on this compute.
       description: ""
       operationId: checkComputeWritability
       responses:
-        "200":
+        200:
           description: Check result
           content:
             text/plain:
               schema:
                 type: string
-                description: Error text or 'true' if check passed
+                description: Error text or 'true' if check passed.
                 example: "true"
 
+  /configure:
+    post:
+      tags:
+      - Configure
+      summary: Perform compute node configuration.
+      description: |
+        This is a blocking API endpoint, i.e. it blocks waiting until
+        compute is finished configuration and is in `Running` state.
+        Optional non-blocking mode could be added later.
+      operationId: configureCompute
+      requestBody:
+        description: Configuration request.
+        required: true
+        content:
+          application/json:
+            schema:
+              type: object
+              required:
+                - spec
+              properties:
+                spec:
+                  # XXX: I don't want to explain current spec in the OpenAPI format,
+                  # as it could be changed really soon. Consider doing it later.
+                  type: object
+      responses:
+        200:
+          description: Compute configuration finished.
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/ComputeState"
+        400:
+          description: Provided spec is invalid.
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/GenericError"
+        412:
+          description: |
+            It's not possible to do live-configuration of the compute.
+            It's either in the wrong state, or compute doesn't use pull
+            mode of configuration.
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/GenericError"
+        500:
+          description: |
+            Compute configuration request was processed, but error
+            occurred. Compute will likely shutdown soon.
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/GenericError"
+
 components:
   securitySchemes:
     JWT:
@@ -115,7 +150,7 @@ components:
   schemas:
     ComputeMetrics:
       type: object
-      description: Compute startup metrics
+      description: Compute startup metrics.
       required:
         - sync_safekeepers_ms
         - basebackup_ms
@@ -131,6 +166,15 @@ components:
         total_startup_ms:
           type: integer
 
+    Info:
+      type: object
+      description: Information about VM/Pod.
+      required:
+        - num_cpus
+      properties:
+        num_cpus:
+          type: integer
+
     ComputeState:
       type: object
       required:
@@ -141,11 +185,29 @@ components:
           $ref: '#/components/schemas/ComputeStatus'
         last_active:
           type: string
-          description: The last detected compute activity timestamp in UTC and RFC3339 format
+          description: The last detected compute activity timestamp in UTC and RFC3339 format.
           example: "2022-10-12T07:20:50.52Z"
         error:
           type: string
-          description: Text of the error during compute startup, if any
+          description: Text of the error during compute startup, if any.
+          example: ""
+        tenant:
+          type: string
+          description: Identifier of the current tenant served by compute node, if any.
+          example: c9269c359e9a199fad1ea0981246a78f
+        timeline:
+          type: string
+          description: Identifier of the current timeline served by compute node, if any.
+          example: ece7de74d4b8cbe5433a68ce4d1b97b4
+
+    ComputeInsights:
+      type: object
+      properties:
+        pg_stat_statements:
+          description: Contains raw output from pg_stat_statements in JSON format.
+          type: array
+          items:
+            type: object
 
     ComputeStatus:
       type: string
@@ -153,6 +215,19 @@ components:
         - init
         - failed
         - running
+      example: running
+
+    #
+    # Errors
+    #
+
+    GenericError:
+      type: object
+      required:
+        - error
+      properties:
+        error:
+          type: string
 
 security:
   - JWT: []

compute_tools/src/lib.rs

@@ -4,6 +4,7 @@
 //!
 pub mod checker;
 pub mod config;
+pub mod configurator;
 pub mod http;
 #[macro_use]
 pub mod logger;

compute_tools/src/logger.rs

@@ -1,43 +1,37 @@
-use std::io::Write;
+use tracing_opentelemetry::OpenTelemetryLayer;
+use tracing_subscriber::layer::SubscriberExt;
+use tracing_subscriber::prelude::*;
 
-use anyhow::Result;
+/// Initialize logging to stderr, and OpenTelemetry tracing and exporter.
-use chrono::Utc;
+///
-use env_logger::{Builder, Env};
+/// Logging is configured using either `default_log_level` or
-
-macro_rules! info_println {
-    ($($tts:tt)*) => {
-        if log_enabled!(Level::Info) {
-            println!($($tts)*);
-        }
-    }
-}
-
-macro_rules! info_print {
-    ($($tts:tt)*) => {
-        if log_enabled!(Level::Info) {
-            print!($($tts)*);
-        }
-    }
-}
-
-/// Initialize `env_logger` using either `default_level` or
 /// `RUST_LOG` environment variable as default log level.
-pub fn init_logger(default_level: &str) -> Result<()> {
+///
-    let env = Env::default().filter_or("RUST_LOG", default_level);
+/// OpenTelemetry is configured with OTLP/HTTP exporter. It picks up
+/// configuration from environment variables. For example, to change the destination,
+/// set `OTEL_EXPORTER_OTLP_ENDPOINT=http://jaeger:4318`. See
+/// `tracing-utils` package description.
+///
+pub fn init_tracing_and_logging(default_log_level: &str) -> anyhow::Result<()> {
+    // Initialize Logging
+    let env_filter = tracing_subscriber::EnvFilter::try_from_default_env()
+        .unwrap_or_else(|_| tracing_subscriber::EnvFilter::new(default_log_level));
 
-    Builder::from_env(env)
+    let fmt_layer = tracing_subscriber::fmt::layer()
-        .format(|buf, record| {
+        .with_target(false)
-            let thread_handle = std::thread::current();
+        .with_writer(std::io::stderr);
-            writeln!(
+
-                buf,
+    // Initialize OpenTelemetry
-                "{} [{}] {}: {}",
+    let otlp_layer =
-                Utc::now().format("%Y-%m-%d %H:%M:%S%.3f %Z"),
+        tracing_utils::init_tracing_without_runtime("compute_ctl").map(OpenTelemetryLayer::new);
-                thread_handle.name().unwrap_or("main"),
+
-                record.level(),
+    // Put it all together
-                record.args()
+    tracing_subscriber::registry()
-            )
+        .with(env_filter)
-        })
+        .with(otlp_layer)
+        .with(fmt_layer)
         .init();
+    tracing::info!("logging and tracing started");
 
     Ok(())
 }

compute_tools/src/monitor.rs

@@ -3,8 +3,8 @@ use std::{thread, time};
 
 use anyhow::Result;
 use chrono::{DateTime, Utc};
-use log::{debug, info};
 use postgres::{Client, NoTls};
+use tracing::{debug, info};
 
 use crate::compute::ComputeNode;
 
@@ -46,16 +46,22 @@ fn watch_compute_activity(compute: &ComputeNode) {
                             AND usename != 'cloud_admin';", // XXX: find a better way to filter other monitors?
                         &[],
                     );
-                let mut last_active = compute.state.read().unwrap().last_active;
+                let mut last_active = compute.state.lock().unwrap().last_active;
 
                 if let Ok(backs) = backends {
                     let mut idle_backs: Vec<DateTime<Utc>> = vec![];
 
                     for b in backs.into_iter() {
-                        let state: String = b.get("state");
+                        let state: String = match b.try_get("state") {
-                        let change: String = b.get("state_change");
+                            Ok(state) => state,
+                            Err(_) => continue,
+                        };
 
                         if state == "idle" {
+                            let change: String = match b.try_get("state_change") {
+                                Ok(state_change) => state_change,
+                                Err(_) => continue,
+                            };
                             let change = DateTime::parse_from_rfc3339(&change);
                             match change {
                                 Ok(t) => idle_backs.push(t.with_timezone(&Utc)),
@@ -74,16 +80,14 @@ fn watch_compute_activity(compute: &ComputeNode) {
                         }
                     }
 
-                    // Sort idle backend `state_change` timestamps. The last one corresponds
+                    // Get idle backend `state_change` with the max timestamp.
-                    // to the last activity.
+                    if let Some(last) = idle_backs.iter().max() {
-                    idle_backs.sort();
-                    if let Some(last) = idle_backs.last() {
                         last_active = *last;
                     }
                 }
 
                 // Update the last activity in the shared state if we got a more recent one.
-                let mut state = compute.state.write().unwrap();
+                let mut state = compute.state.lock().unwrap();
                 if last_active > state.last_active {
                     state.last_active = last_active;
                     debug!("set the last compute activity time to: {}", last_active);

compute_tools/src/params.rs

@@ -1,3 +1,9 @@
 pub const DEFAULT_LOG_LEVEL: &str = "info";
-pub const DEFAULT_CONNSTRING: &str = "host=localhost user=postgres";
+// From Postgres docs:
+//   To ease transition from the md5 method to the newer SCRAM method, if md5 is specified
+//   as a method in pg_hba.conf but the user's password on the server is encrypted for SCRAM
+//   (see below), then SCRAM-based authentication will automatically be chosen instead.
+//   https://www.postgresql.org/docs/15/auth-password.html
+//
+// So it's safe to set md5 here, as `control-plane` anyway uses SCRAM for all roles.
 pub const PG_HBA_ALL_MD5: &str = "host\tall\t\tall\t\t0.0.0.0/0\t\tmd5";

compute_tools/src/pg_helpers.rs

@@ -10,48 +10,34 @@ use std::time::{Duration, Instant};
 use anyhow::{bail, Result};
 use notify::{RecursiveMode, Watcher};
 use postgres::{Client, Transaction};
-use serde::Deserialize;
+use tracing::{debug, instrument};
+
+use compute_api::spec::{Database, GenericOption, GenericOptions, PgIdent, Role};
 
 const POSTGRES_WAIT_TIMEOUT: Duration = Duration::from_millis(60 * 1000); // milliseconds
 
-/// Rust representation of Postgres role info with only those fields
+/// Escape a string for including it in a SQL literal
-/// that matter for us.
+fn escape_literal(s: &str) -> String {
-#[derive(Clone, Deserialize)]
+    s.replace('\'', "''").replace('\\', "\\\\")
-pub struct Role {
-    pub name: PgIdent,
-    pub encrypted_password: Option<String>,
-    pub options: GenericOptions,
 }
 
-/// Rust representation of Postgres database info with only those fields
+/// Escape a string so that it can be used in postgresql.conf.
-/// that matter for us.
+/// Same as escape_literal, currently.
-#[derive(Clone, Deserialize)]
+fn escape_conf_value(s: &str) -> String {
-pub struct Database {
+    s.replace('\'', "''").replace('\\', "\\\\")
-    pub name: PgIdent,
-    pub owner: PgIdent,
-    pub options: GenericOptions,
 }
 
-/// Common type representing both SQL statement params with or without value,
+trait GenericOptionExt {
-/// like `LOGIN` or `OWNER username` in the `CREATE/ALTER ROLE`, and config
+    fn to_pg_option(&self) -> String;
-/// options like `wal_level = logical`.
+    fn to_pg_setting(&self) -> String;
-#[derive(Clone, Deserialize)]
-pub struct GenericOption {
-    pub name: String,
-    pub value: Option<String>,
-    pub vartype: String,
 }
 
-/// Optional collection of `GenericOption`'s. Type alias allows us to
+impl GenericOptionExt for GenericOption {
-/// declare a `trait` on it.
-pub type GenericOptions = Option<Vec<GenericOption>>;
-
-impl GenericOption {
     /// Represent `GenericOption` as SQL statement parameter.
-    pub fn to_pg_option(&self) -> String {
+    fn to_pg_option(&self) -> String {
         if let Some(val) = &self.value {
             match self.vartype.as_ref() {
-                "string" => format!("{} '{}'", self.name, val),
+                "string" => format!("{} '{}'", self.name, escape_literal(val)),
                 _ => format!("{} {}", self.name, val),
             }
         } else {
@@ -60,18 +46,11 @@ impl GenericOption {
     }
 
     /// Represent `GenericOption` as configuration option.
-    pub fn to_pg_setting(&self) -> String {
+    fn to_pg_setting(&self) -> String {
         if let Some(val) = &self.value {
-            let name = match self.name.as_str() {
-                "safekeepers" => "neon.safekeepers",
-                "wal_acceptor_reconnect" => "neon.safekeeper_reconnect_timeout",
-                "wal_acceptor_connect_timeout" => "neon.safekeeper_connect_timeout",
-                it => it,
-            };
-
             match self.vartype.as_ref() {
-                "string" => format!("{} = '{}'", name, val),
+                "string" => format!("{} = '{}'", self.name, escape_conf_value(val)),
-                _ => format!("{} = {}", name, val),
+                _ => format!("{} = {}", self.name, val),
             }
         } else {
             self.name.to_owned()
@@ -106,6 +85,7 @@ impl PgOptionsSerialize for GenericOptions {
                 .map(|op| op.to_pg_setting())
                 .collect::<Vec<String>>()
                 .join("\n")
+                + "\n" // newline after last setting
         } else {
             "".to_string()
         }
@@ -119,25 +99,22 @@ pub trait GenericOptionsSearch {
 impl GenericOptionsSearch for GenericOptions {
     /// Lookup option by name
     fn find(&self, name: &str) -> Option<String> {
-        match &self {
+        let ops = self.as_ref()?;
-            Some(ops) => {
+        let op = ops.iter().find(|s| s.name == name)?;
-                let op = ops.iter().find(|s| s.name == name);
+        op.value.clone()
-                match op {
-                    Some(op) => op.value.clone(),
-                    None => None,
-                }
-            }
-            None => None,
-        }
     }
 }
 
-impl Role {
+pub trait RoleExt {
+    fn to_pg_options(&self) -> String;
+}
+
+impl RoleExt for Role {
     /// Serialize a list of role parameters into a Postgres-acceptable
     /// string of arguments.
-    pub fn to_pg_options(&self) -> String {
+    fn to_pg_options(&self) -> String {
-        // XXX: consider putting LOGIN as a default option somewhere higher, e.g. in Rails.
+        // XXX: consider putting LOGIN as a default option somewhere higher, e.g. in control-plane.
-        // For now we do not use generic `options` for roles. Once used, add
+        // For now, we do not use generic `options` for roles. Once used, add
         // `self.options.as_pg_options()` somewhere here.
         let mut params: String = "LOGIN".to_string();
 
@@ -160,13 +137,17 @@ impl Role {
     }
 }
 
-impl Database {
+pub trait DatabaseExt {
+    fn to_pg_options(&self) -> String;
+}
+
+impl DatabaseExt for Database {
     /// Serialize a list of database parameters into a Postgres-acceptable
     /// string of arguments.
     /// NB: `TEMPLATE` is actually also an identifier, but so far we only need
     /// to use `template0` and `template1`, so it is not a problem. Yet in the future
     /// it may require a proper quoting too.
-    pub fn to_pg_options(&self) -> String {
+    fn to_pg_options(&self) -> String {
         let mut params: String = self.options.as_pg_options();
         write!(params, " OWNER {}", &self.owner.pg_quote())
             .expect("String is documented to not to error during write operations");
@@ -175,10 +156,6 @@ impl Database {
     }
 }
 
-/// String type alias representing Postgres identifier and
-/// 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 {
@@ -232,6 +209,7 @@ pub fn get_existing_dbs(client: &mut Client) -> Result<Vec<Database>> {
 /// 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'.
+#[instrument(skip(pg))]
 pub fn wait_for_postgres(pg: &mut Child, pgdata: &Path) -> Result<()> {
     let pid_path = pgdata.join("postmaster.pid");
 
@@ -290,18 +268,18 @@ pub fn wait_for_postgres(pg: &mut Child, pgdata: &Path) -> Result<()> {
         }
 
         let res = rx.recv_timeout(Duration::from_millis(100));
-        log::debug!("woken up by notify: {res:?}");
+        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:?}");
+            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");
+                debug!("postmaster.pid appeared");
                 watcher
                     .unwatch(pgdata)
                     .expect("Failed to remove pgdata dir watch");
@@ -317,7 +295,7 @@ pub fn wait_for_postgres(pg: &mut Child, pgdata: &Path) -> Result<()> {
             // 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:?}");
+                debug!("last line of postmaster.pid: {status:?}");
 
                 // Now Postgres is ready to accept connections
                 if status == "ready" {
@@ -333,7 +311,7 @@ pub fn wait_for_postgres(pg: &mut Child, pgdata: &Path) -> Result<()> {
         }
     }
 
-    log::info!("PostgreSQL is now running, continuing to configure it");
+    tracing::info!("PostgreSQL is now running, continuing to configure it");
 
     Ok(())
 }

compute_tools/src/spec.rs

@@ -1,52 +1,45 @@
 use std::path::Path;
 use std::str::FromStr;
 
-use anyhow::Result;
+use anyhow::{anyhow, bail, Result};
-use log::{info, log_enabled, warn, Level};
 use postgres::config::Config;
 use postgres::{Client, NoTls};
-use serde::Deserialize;
+use tracing::{info, info_span, instrument, span_enabled, warn, Level};
 
-use crate::compute::ComputeNode;
 use crate::config;
 use crate::params::PG_HBA_ALL_MD5;
 use crate::pg_helpers::*;
 
-/// Cluster spec or configuration represented as an optional number of
+use compute_api::responses::ControlPlaneSpecResponse;
-/// delta operations + final cluster state description.
+use compute_api::spec::{ComputeSpec, Database, PgIdent, Role};
-#[derive(Clone, Deserialize)]
-pub struct ComputeSpec {
-    pub format_version: f32,
-    pub timestamp: String,
-    pub operation_uuid: Option<String>,
-    /// Expected cluster state at the end of transition process.
-    pub cluster: Cluster,
-    pub delta_operations: Option<Vec<DeltaOp>>,
-}
 
-/// Cluster state seen from the perspective of the external tools
+/// Request spec from the control-plane by compute_id. If `NEON_CONSOLE_JWT`
-/// like Rails web console.
+/// env variable is set, it will be used for authorization.
-#[derive(Clone, Deserialize)]
+pub fn get_spec_from_control_plane(base_uri: &str, compute_id: &str) -> Result<ComputeSpec> {
-pub struct Cluster {
+    let cp_uri = format!("{base_uri}/management/api/v2/computes/{compute_id}/spec");
-    pub cluster_id: String,
+    let jwt: String = match std::env::var("NEON_CONSOLE_JWT") {
-    pub name: String,
+        Ok(v) => v,
-    pub state: Option<String>,
+        Err(_) => "".to_string(),
-    pub roles: Vec<Role>,
+    };
-    pub databases: Vec<Database>,
+    info!("getting spec from control plane: {}", cp_uri);
-    pub settings: GenericOptions,
-}
 
-/// Single cluster state changing operation that could not be represented as
+    // TODO: check the response. We should distinguish cases when it's
-/// a static `Cluster` structure. For example:
+    // - network error, then retry
-/// - DROP DATABASE
+    // - no spec for compute yet, then wait
-/// - DROP ROLE
+    // - compute id is unknown or any other error, then bail out
-/// - ALTER ROLE name RENAME TO new_name
+    let resp: ControlPlaneSpecResponse = reqwest::blocking::Client::new()
-/// - ALTER DATABASE name RENAME TO new_name
+        .get(cp_uri)
-#[derive(Clone, Deserialize)]
+        .header("Authorization", jwt)
-pub struct DeltaOp {
+        .send()
-    pub action: String,
+        .map_err(|e| anyhow!("could not send spec request to control plane: {}", e))?
-    pub name: PgIdent,
+        .json()
-    pub new_name: Option<PgIdent>,
+        .map_err(|e| anyhow!("could not get compute spec from control plane: {}", e))?;
+
+    if let Some(spec) = resp.spec {
+        Ok(spec)
+    } else {
+        bail!("could not get compute spec from control plane")
+    }
 }
 
 /// It takes cluster specification and does the following:
@@ -79,16 +72,17 @@ pub fn update_pg_hba(pgdata_path: &Path) -> Result<()> {
 
 /// Given a cluster spec json and open transaction it handles roles creation,
 /// deletion and update.
+#[instrument(skip_all)]
 pub fn handle_roles(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
     let mut xact = client.transaction()?;
     let existing_roles: Vec<Role> = get_existing_roles(&mut xact)?;
 
     // Print a list of existing Postgres roles (only in debug mode)
+    if span_enabled!(Level::INFO) {
         info!("postgres roles:");
         for r in &existing_roles {
-        info_println!(
+            info!(
-            "{} - {}:{}",
+                "    - {}:{}",
-            " ".repeat(27 + 5),
                 r.name,
                 if r.encrypted_password.is_some() {
                     "[FILTERED]"
@@ -97,6 +91,7 @@ pub fn handle_roles(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
                 }
             );
         }
+    }
 
     // Process delta operations first
     if let Some(ops) = &spec.delta_operations {
@@ -136,46 +131,55 @@ pub fn handle_roles(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
     info!("cluster spec roles:");
     for role in &spec.cluster.roles {
         let name = &role.name;
-
-        info_print!(
-            "{} - {}:{}",
-            " ".repeat(27 + 5),
-            name,
-            if role.encrypted_password.is_some() {
-                "[FILTERED]"
-            } else {
-                "(null)"
-            }
-        );
-
         // XXX: with a limited number of roles it is fine, but consider making it a HashMap
         let pg_role = existing_roles.iter().find(|r| r.name == *name);
 
-        if let Some(r) = pg_role {
+        enum RoleAction {
-            let mut update_role = false;
+            None,
-
+            Update,
+            Create,
+        }
+        let action = if let Some(r) = pg_role {
             if (r.encrypted_password.is_none() && role.encrypted_password.is_some())
                 || (r.encrypted_password.is_some() && role.encrypted_password.is_none())
             {
-                update_role = true;
+                RoleAction::Update
             } else if let Some(pg_pwd) = &r.encrypted_password {
-                // Check whether password changed or not (trim 'md5:' prefix first)
+                // Check whether password changed or not (trim 'md5' prefix first if any)
-                update_role = pg_pwd[3..] != *role.encrypted_password.as_ref().unwrap();
+                //
+                // This is a backward compatibility hack, which comes from the times when we were using
+                // md5 for everyone and hashes were stored in the console db without md5 prefix. So when
+                // role comes from the control-plane (json spec) `Role.encrypted_password` doesn't have md5 prefix,
+                // but when role comes from Postgres (`get_existing_roles` / `existing_roles`) it has this prefix.
+                // Here is the only place so far where we compare hashes, so it seems to be the best candidate
+                // to place this compatibility layer.
+                let pg_pwd = if let Some(stripped) = pg_pwd.strip_prefix("md5") {
+                    stripped
+                } else {
+                    pg_pwd
+                };
+                if pg_pwd != *role.encrypted_password.as_ref().unwrap() {
+                    RoleAction::Update
+                } else {
+                    RoleAction::None
                 }
+            } else {
+                RoleAction::None
+            }
+        } else {
+            RoleAction::Create
+        };
 
-            if update_role {
+        match action {
+            RoleAction::None => {}
+            RoleAction::Update => {
                 let mut query: String = format!("ALTER ROLE {} ", name.pg_quote());
-                info_print!(" -> update");
-
                 query.push_str(&role.to_pg_options());
                 xact.execute(query.as_str(), &[])?;
             }
-        } else {
+            RoleAction::Create => {
-            info!("role name: '{}'", &name);
                 let mut query: String = format!("CREATE ROLE {} ", name.pg_quote());
                 info!("role create query: '{}'", &query);
-            info_print!(" -> create");
-
                 query.push_str(&role.to_pg_options());
                 xact.execute(query.as_str(), &[])?;
 
@@ -186,8 +190,21 @@ pub fn handle_roles(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
                 xact.execute(grant_query.as_str(), &[])?;
                 info!("role grant query: '{}'", &grant_query);
             }
+        }
 
-        info_print!("\n");
+        if span_enabled!(Level::INFO) {
+            let pwd = if role.encrypted_password.is_some() {
+                "[FILTERED]"
+            } else {
+                "(null)"
+            };
+            let action_str = match action {
+                RoleAction::None => "",
+                RoleAction::Create => " -> create",
+                RoleAction::Update => " -> update",
+            };
+            info!("   - {}:{}{}", name, pwd, action_str);
+        }
     }
 
     xact.commit()?;
@@ -196,23 +213,32 @@ pub fn handle_roles(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
 }
 
 /// Reassign all dependent objects and delete requested roles.
-pub fn handle_role_deletions(node: &ComputeNode, client: &mut Client) -> Result<()> {
+#[instrument(skip_all)]
-    let spec = &node.spec;
+pub fn handle_role_deletions(spec: &ComputeSpec, connstr: &str, client: &mut Client) -> Result<()> {
-
-    // First, reassign all dependent objects to db owners.
     if let Some(ops) = &spec.delta_operations {
+        // First, reassign all dependent objects to db owners.
         info!("reassigning dependent objects of to-be-deleted roles");
+
+        // Fetch existing roles. We could've exported and used `existing_roles` from
+        // `handle_roles()`, but we only make this list there before creating new roles.
+        // Which is probably fine as we never create to-be-deleted roles, but that'd
+        // just look a bit untidy. Anyway, the entire `pg_roles` should be in shared
+        // buffers already, so this shouldn't be a big deal.
+        let mut xact = client.transaction()?;
+        let existing_roles: Vec<Role> = get_existing_roles(&mut xact)?;
+        xact.commit()?;
+
         for op in ops {
-            if op.action == "delete_role" {
+            // Check that role is still present in Postgres, as this could be a
-                reassign_owned_objects(node, &op.name)?;
+            // restart with the same spec after role deletion.
-            }
+            if op.action == "delete_role" && existing_roles.iter().any(|r| r.name == op.name) {
+                reassign_owned_objects(spec, connstr, &op.name)?;
             }
         }
 
         // Second, proceed with role deletions.
-    let mut xact = client.transaction()?;
-    if let Some(ops) = &spec.delta_operations {
         info!("processing role deletions");
+        let mut xact = client.transaction()?;
         for op in ops {
             // We do not check either role exists or not,
             // Postgres will take care of it for us
@@ -223,16 +249,17 @@ pub fn handle_role_deletions(node: &ComputeNode, client: &mut Client) -> Result<
                 xact.execute(query.as_str(), &[])?;
             }
         }
+        xact.commit()?;
     }
 
     Ok(())
 }
 
 // Reassign all owned objects in all databases to the owner of the database.
-fn reassign_owned_objects(node: &ComputeNode, role_name: &PgIdent) -> Result<()> {
+fn reassign_owned_objects(spec: &ComputeSpec, connstr: &str, role_name: &PgIdent) -> Result<()> {
-    for db in &node.spec.cluster.databases {
+    for db in &spec.cluster.databases {
         if db.owner != *role_name {
-            let mut conf = Config::from_str(node.connstr.as_str())?;
+            let mut conf = Config::from_str(connstr)?;
             conf.dbname(&db.name);
 
             let mut client = conf.connect(NoTls)?;
@@ -263,13 +290,16 @@ fn reassign_owned_objects(node: &ComputeNode, role_name: &PgIdent) -> Result<()>
 /// like `CREATE DATABASE` and `DROP DATABASE` do not support it. Statement-level
 /// atomicity should be enough here due to the order of operations and various checks,
 /// which together provide us idempotency.
+#[instrument(skip_all)]
 pub fn handle_databases(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
     let existing_dbs: Vec<Database> = get_existing_dbs(client)?;
 
     // Print a list of existing Postgres databases (only in debug mode)
+    if span_enabled!(Level::INFO) {
         info!("postgres databases:");
         for r in &existing_dbs {
-        info_println!("{} - {}:{}", " ".repeat(27 + 5), r.name, r.owner);
+            info!("    {}:{}", r.name, r.owner);
+        }
     }
 
     // Process delta operations first
@@ -312,12 +342,15 @@ pub fn handle_databases(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
     for db in &spec.cluster.databases {
         let name = &db.name;
 
-        info_print!("{} - {}:{}", " ".repeat(27 + 5), db.name, db.owner);
-
         // XXX: with a limited number of databases it is fine, but consider making it a HashMap
         let pg_db = existing_dbs.iter().find(|r| r.name == *name);
 
-        if let Some(r) = pg_db {
+        enum DatabaseAction {
+            None,
+            Update,
+            Create,
+        }
+        let action = if let Some(r) = pg_db {
             // XXX: db owner name is returned as quoted string from Postgres,
             // when quoting is needed.
             let new_owner = if r.owner.starts_with('"') {
@@ -327,24 +360,42 @@ pub fn handle_databases(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
             };
 
             if new_owner != r.owner {
+                // Update the owner
+                DatabaseAction::Update
+            } else {
+                DatabaseAction::None
+            }
+        } else {
+            DatabaseAction::Create
+        };
+
+        match action {
+            DatabaseAction::None => {}
+            DatabaseAction::Update => {
                 let query: String = format!(
                     "ALTER DATABASE {} OWNER TO {}",
                     name.pg_quote(),
                     db.owner.pg_quote()
                 );
-                info_print!(" -> update");
+                let _guard = info_span!("executing", query).entered();
-
                 client.execute(query.as_str(), &[])?;
             }
-        } else {
+            DatabaseAction::Create => {
                 let mut query: String = format!("CREATE DATABASE {} ", name.pg_quote());
-            info_print!(" -> create");
-
                 query.push_str(&db.to_pg_options());
+                let _guard = info_span!("executing", query).entered();
                 client.execute(query.as_str(), &[])?;
             }
+        };
 
-        info_print!("\n");
+        if span_enabled!(Level::INFO) {
+            let action_str = match action {
+                DatabaseAction::None => "",
+                DatabaseAction::Create => " -> create",
+                DatabaseAction::Update => " -> update",
+            };
+            info!("   - {}:{}{}", db.name, db.owner, action_str);
+        }
     }
 
     Ok(())
@@ -352,9 +403,8 @@ pub fn handle_databases(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
 
 /// Grant CREATE ON DATABASE to the database owner and do some other alters and grants
 /// to allow users creating trusted extensions and re-creating `public` schema, for example.
-pub fn handle_grants(node: &ComputeNode, client: &mut Client) -> Result<()> {
+#[instrument(skip_all)]
-    let spec = &node.spec;
+pub fn handle_grants(spec: &ComputeSpec, connstr: &str, client: &mut Client) -> Result<()> {
-
     info!("cluster spec grants:");
 
     // We now have a separate `web_access` role to connect to the database
@@ -386,8 +436,8 @@ 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.
-    for db in &node.spec.cluster.databases {
+    for db in &spec.cluster.databases {
-        let mut conf = Config::from_str(node.connstr.as_str())?;
+        let mut conf = Config::from_str(connstr)?;
         conf.dbname(&db.name);
 
         let mut db_client = conf.connect(NoTls)?;
@@ -424,11 +474,47 @@ pub fn handle_grants(node: &ComputeNode, client: &mut Client) -> Result<()> {
         db_client.simple_query(&alter_query)?;
 
         // Explicitly grant CREATE ON SCHEMA PUBLIC to the web_access user.
-        // This is needed since postgres 15, where this privilege is removed by default.
+        // This is needed because since postgres 15 this privilege is removed by default.
-        let grant_query: String = "GRANT CREATE ON SCHEMA public TO web_access".to_string();
+        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(())
 }
+
+/// Create required system extensions
+#[instrument(skip_all)]
+pub fn handle_extensions(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
+    if let Some(libs) = spec.cluster.settings.find("shared_preload_libraries") {
+        if libs.contains("pg_stat_statements") {
+            // Create extension only if this compute really needs it
+            let query = "CREATE EXTENSION IF NOT EXISTS pg_stat_statements";
+            info!("creating system extensions with query: {}", query);
+            client.simple_query(query)?;
+        }
+    }
+
+    Ok(())
+}

compute_tools/tests/pg_helpers_tests.rs

@@ -1,14 +1,13 @@
 #[cfg(test)]
 mod pg_helpers_tests {
-
     use std::fs::File;
 
+    use compute_api::spec::{ComputeSpec, GenericOption, GenericOptions, PgIdent};
     use compute_tools::pg_helpers::*;
-    use compute_tools::spec::ComputeSpec;
 
     #[test]
     fn params_serialize() {
-        let file = File::open("tests/cluster_spec.json").unwrap();
+        let file = File::open("../libs/compute_api/tests/cluster_spec.json").unwrap();
         let spec: ComputeSpec = serde_json::from_reader(file).unwrap();
 
         assert_eq!(
@@ -23,12 +22,35 @@ mod pg_helpers_tests {
 
     #[test]
     fn settings_serialize() {
-        let file = File::open("tests/cluster_spec.json").unwrap();
+        let file = File::open("../libs/compute_api/tests/cluster_spec.json").unwrap();
         let spec: ComputeSpec = serde_json::from_reader(file).unwrap();
 
         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'"
+            r#"fsync = off
+wal_level = replica
+hot_standby = on
+neon.safekeepers = '127.0.0.1:6502,127.0.0.1:6503,127.0.0.1:6501'
+wal_log_hints = on
+log_connections = on
+shared_buffers = 32768
+port = 55432
+max_connections = 100
+max_wal_senders = 10
+listen_addresses = '0.0.0.0'
+wal_sender_timeout = 0
+password_encryption = md5
+maintenance_work_mem = 65536
+max_parallel_workers = 8
+max_worker_processes = 8
+neon.tenant_id = 'b0554b632bd4d547a63b86c3630317e8'
+max_replication_slots = 10
+neon.timeline_id = '2414a61ffc94e428f14b5758fe308e13'
+shared_preload_libraries = 'neon'
+synchronous_standby_names = 'walproposer'
+neon.pageserver_connstring = 'host=127.0.0.1 port=6400'
+test.escaping = 'here''s a backslash \\ and a quote '' and a double-quote " hooray'
+"#
         );
     }
 
@@ -38,4 +60,33 @@ mod pg_helpers_tests {
 
         assert_eq!(ident.pg_quote(), "\"\"\"name\"\";\\n select 1;\"");
     }
+
+    #[test]
+    fn generic_options_search() {
+        let generic_options: GenericOptions = Some(vec![
+            GenericOption {
+                name: "present_value".into(),
+                value: Some("value".into()),
+                vartype: "string".into(),
+            },
+            GenericOption {
+                name: "missed_value".into(),
+                value: None,
+                vartype: "int".into(),
+            },
+        ]);
+        assert_eq!(generic_options.find("present_value"), Some("value".into()));
+        assert_eq!(generic_options.find("missed_value"), None);
+        assert_eq!(generic_options.find("invalid_value"), None);
+
+        let empty_generic_options: GenericOptions = Some(vec![]);
+        assert_eq!(empty_generic_options.find("present_value"), None);
+        assert_eq!(empty_generic_options.find("missed_value"), None);
+        assert_eq!(empty_generic_options.find("invalid_value"), None);
+
+        let none_generic_options: GenericOptions = None;
+        assert_eq!(none_generic_options.find("present_value"), None);
+        assert_eq!(none_generic_options.find("missed_value"), None);
+        assert_eq!(none_generic_options.find("invalid_value"), None);
+    }
 }

control_plane/Cargo.toml

@@ -1,27 +1,33 @@
 [package]
 name = "control_plane"
 version = "0.1.0"
-edition = "2021"
+edition.workspace = true
+license.workspace = true
 
 [dependencies]
-clap = "4.0"
+anyhow.workspace = true
-comfy-table = "6.1"
+clap.workspace = true
-git-version = "0.3.5"
+comfy-table.workspace = true
-tar = "0.4.38"
+git-version.workspace = true
-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev = "d052ee8b86fff9897c77b0fe89ea9daba0e1fa38" }
+nix.workspace = true
-serde = { version = "1.0", features = ["derive"] }
+once_cell.workspace = true
-serde_with = "2.0"
+postgres.workspace = true
-toml = "0.5"
+regex.workspace = true
-once_cell = "1.13.0"
+reqwest = { workspace = true, features = ["blocking", "json"] }
-regex = "1"
+serde.workspace = true
-anyhow = "1.0"
+serde_json.workspace = true
-thiserror = "1"
+serde_with.workspace = true
-nix = "0.25"
+tar.workspace = true
-reqwest = { version = "0.11", default-features = false, features = ["blocking", "json", "rustls-tls"] }
+thiserror.workspace = true
-
+toml.workspace = true
+url.workspace = true
 # 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" }
+pageserver_api.workspace = true
-safekeeper_api = { path = "../libs/safekeeper_api" }
+postgres_backend.workspace = true
-utils = { path = "../libs/utils" }
+safekeeper_api.workspace = true
-workspace_hack = { version = "0.1", path = "../workspace_hack" }
+postgres_connection.workspace = true
+storage_broker.workspace = true
+utils.workspace = true
+
+workspace_hack.workspace = true

control_plane/safekeepers.conf

@@ -2,7 +2,8 @@
 [pageserver]
 listen_pg_addr = '127.0.0.1:64000'
 listen_http_addr = '127.0.0.1:9898'
-auth_type = 'Trust'
+pg_auth_type = 'Trust'
+http_auth_type = 'Trust'
 
 [[safekeepers]]
 id = 1

control_plane/simple.conf

@@ -3,12 +3,13 @@
 [pageserver]
 listen_pg_addr = '127.0.0.1:64000'
 listen_http_addr = '127.0.0.1:9898'
-auth_type = 'Trust'
+pg_auth_type = 'Trust'
+http_auth_type = 'Trust'
 
 [[safekeepers]]
 id = 1
 pg_port = 5454
 http_port = 7676
 
-[etcd_broker]
+[broker]
-broker_endpoints = ['http://127.0.0.1:2379']
+listen_addr = '127.0.0.1:50051'

control_plane/src/background_process.rs

@@ -0,0 +1,337 @@
+//! 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::os::unix::prelude::AsRawFd;
+use std::os::unix::process::CommandExt;
+use std::path::{Path, PathBuf};
+use std::process::{Child, Command};
+use std::time::Duration;
+use std::{fs, io, thread};
+
+use anyhow::Context;
+use nix::errno::Errno;
+use nix::fcntl::{FcntlArg, FdFlag};
+use nix::sys::signal::{kill, Signal};
+use nix::unistd::Pid;
+use utils::pid_file::{self, PidFileRead};
+
+// These constants control the loop used to poll for process start / stop.
+//
+// The loop waits for at most 10 seconds, polling every 100 ms.
+// Once a second, it prints a dot ("."), to give the user an indication that
+// it's waiting. If the process hasn't started/stopped after 5 seconds,
+// it prints a notice that it's taking long, but keeps waiting.
+//
+const RETRY_UNTIL_SECS: u64 = 10;
+const RETRIES: u64 = (RETRY_UNTIL_SECS * 1000) / RETRY_INTERVAL_MILLIS;
+const RETRY_INTERVAL_MILLIS: u64 = 100;
+const DOT_EVERY_RETRIES: u64 = 10;
+const NOTICE_AFTER_RETRIES: u64 = 50;
+
+/// 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, AI, A, EI>(
+    process_name: &str,
+    datadir: &Path,
+    command: &Path,
+    args: AI,
+    envs: EI,
+    initial_pid_file: InitialPidFile,
+    process_status_check: F,
+) -> anyhow::Result<Child>
+where
+    F: Fn() -> anyhow::Result<bool>,
+    AI: IntoIterator<Item = A>,
+    A: AsRef<OsStr>,
+    // Not generic AsRef<OsStr>, otherwise empty `envs` prevents type inference
+    EI: IntoIterator<Item = (String, String)>,
+{
+    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));
+    filled_cmd.envs(envs);
+
+    let pid_file_to_check = match initial_pid_file {
+        InitialPidFile::Create(path) => {
+            pre_exec_create_pidfile(filled_cmd, path);
+            path
+        }
+        InitialPidFile::Expect(path) => path,
+    };
+
+    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}"))?,
+    );
+
+    for retries in 0..RETRIES {
+        match process_started(pid, Some(pid_file_to_check), &process_status_check) {
+            Ok(true) => {
+                println!("\n{process_name} started, pid: {pid}");
+                return Ok(spawned_process);
+            }
+            Ok(false) => {
+                if retries == NOTICE_AFTER_RETRIES {
+                    // The process is taking a long time to start up. Keep waiting, but
+                    // print a message
+                    print!("\n{process_name} has not started yet, continuing to wait");
+                }
+                if retries % DOT_EVERY_RETRIES == 0 {
+                    print!(".");
+                    io::stdout().flush().unwrap();
+                }
+                thread::sleep(Duration::from_millis(RETRY_INTERVAL_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);
+            }
+        }
+    }
+    println!();
+    anyhow::bail!("{process_name} did not start in {RETRY_UNTIL_SECS} seconds");
+}
+
+/// 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<()> {
+    let pid = match pid_file::read(pid_file)
+        .with_context(|| format!("read pid_file {pid_file:?}"))?
+    {
+        PidFileRead::NotExist => {
+            println!("{process_name} is already stopped: no pid file present at {pid_file:?}");
+            return Ok(());
+        }
+        PidFileRead::NotHeldByAnyProcess(_) => {
+            // Don't try to kill according to file contents beacuse the pid might have been re-used by another process.
+            // Don't delete the file either, it can race with new pid file creation.
+            // Read `pid_file` module comment for details.
+            println!(
+                "No process is holding the pidfile. The process must have already exited. Leave in place to avoid race conditions: {pid_file:?}"
+            );
+            return Ok(());
+        }
+        PidFileRead::LockedByOtherProcess(pid) => pid,
+    };
+    // XXX the pid could become invalid (and recycled) at any time before the kill() below.
+
+    // send signal
+    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) => {
+            // Again, don't delete the pid file. The unlink can race with a new pid file being created.
+            println!(
+                "{process_name} with pid {pid} does not exist, but a pid file {pid_file:?} was found. Likely the pid got recycled. Lucky we didn't harm anyone."
+            );
+            return Ok(());
+        }
+        Err(e) => anyhow::bail!("Failed to send signal to {process_name} with pid {pid}: {e}"),
+    }
+
+    // Wait until process is gone
+    for retries in 0..RETRIES {
+        match process_has_stopped(pid) {
+            Ok(true) => {
+                println!("\n{process_name} stopped");
+                return Ok(());
+            }
+            Ok(false) => {
+                if retries == NOTICE_AFTER_RETRIES {
+                    // The process is taking a long time to start up. Keep waiting, but
+                    // print a message
+                    print!("\n{process_name} has not stopped yet, continuing to wait");
+                }
+                if retries % DOT_EVERY_RETRIES == 0 {
+                    print!(".");
+                    io::stdout().flush().unwrap();
+                }
+                thread::sleep(Duration::from_millis(RETRY_INTERVAL_MILLIS));
+            }
+            Err(e) => {
+                println!("{process_name} with pid {pid} failed to stop: {e:#}");
+                return Err(e);
+            }
+        }
+    }
+    println!();
+    anyhow::bail!("{process_name} with pid {pid} did not stop in {RETRY_UNTIL_SECS} seconds");
+}
+
+fn fill_rust_env_vars(cmd: &mut Command) -> &mut Command {
+    // If RUST_BACKTRACE is set, pass it through. But if it's not set, default
+    // to RUST_BACKTRACE=1.
+    let backtrace_setting = std::env::var_os("RUST_BACKTRACE");
+    let backtrace_setting = backtrace_setting
+        .as_deref()
+        .unwrap_or_else(|| OsStr::new("1"));
+
+    let mut filled_cmd = cmd.env_clear().env("RUST_BACKTRACE", backtrace_setting);
+
+    // Pass through these environment variables to the command
+    for var in ["LLVM_PROFILE_FILE", "FAILPOINTS", "RUST_LOG"] {
+        if let Some(val) = std::env::var_os(var) {
+            filled_cmd = filled_cmd.env(var, val);
+        }
+    }
+
+    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
+}
+
+/// Add a `pre_exec` to the cmd that, inbetween fork() and exec(),
+/// 1. Claims a pidfile with a fcntl lock on it and
+/// 2. Sets up the pidfile's file descriptor so that it (and the lock)
+///    will remain held until the cmd exits.
+fn pre_exec_create_pidfile<P>(cmd: &mut Command, path: P) -> &mut Command
+where
+    P: Into<PathBuf>,
+{
+    let path: PathBuf = path.into();
+    // SAFETY
+    // pre_exec is marked unsafe because it runs between fork and exec.
+    // Why is that dangerous in various ways?
+    // Long answer:  https://github.com/rust-lang/rust/issues/39575
+    // Short answer: in a multi-threaded program, other threads may have
+    // been inside of critical sections at the time of fork. In the
+    // original process, that was allright, assuming they protected
+    // the critical sections appropriately, e.g., through locks.
+    // Fork adds another process to the mix that
+    //   1. Has a single thread T
+    //   2. In an exact copy of the address space at the time of fork.
+    // A variety of problems scan occur now:
+    //   1. T tries to grab a lock that was locked at the time of fork.
+    //      It will wait forever since in its address space, the lock
+    //      is in state 'taken' but the thread that would unlock it is
+    //      not there.
+    //   2. A rust object that represented some external resource in the
+    //      parent now got implicitly copied by the the fork, even though
+    //      the object's type is not `Copy`. The parent program may use
+    //      non-copyability as way to enforce unique ownership of an
+    //      external resource in the typesystem. The fork breaks that
+    //      assumption, as now both parent and child process have an
+    //      owned instance of the object that represents the same
+    //      underlying resource.
+    // While these seem like niche problems, (1) in particular is
+    // highly relevant. For example, `malloc()` may grab a mutex internally,
+    // and so, if we forked while another thread was mallocing' and our
+    // pre_exec closure allocates as well, it will block on the malloc
+    // mutex forever
+    //
+    // The proper solution is to only use C library functions that are marked
+    // "async-signal-safe": https://man7.org/linux/man-pages/man7/signal-safety.7.html
+    //
+    // With this specific pre_exec() closure, the non-error path doesn't allocate.
+    // The error path uses `anyhow`, and hence does allocate.
+    // We take our chances there, hoping that any potential disaster is constrained
+    // to the child process (e.g., malloc has no state ourside of the child process).
+    // Last, `expect` prints to stderr, and stdio is not async-signal-safe.
+    // Again, we take our chances, making the same assumptions as for malloc.
+    unsafe {
+        cmd.pre_exec(move || {
+            let file = pid_file::claim_for_current_process(&path).expect("claim pid file");
+            // Remove the FD_CLOEXEC flag on the pidfile descriptor so that the pidfile
+            // remains locked after exec.
+            nix::fcntl::fcntl(file.as_raw_fd(), FcntlArg::F_SETFD(FdFlag::empty()))
+                .expect("remove FD_CLOEXEC");
+            // Don't run drop(file), it would close the file before we actually exec.
+            std::mem::forget(file);
+            Ok(())
+        });
+    }
+    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) => match pid_file::read(pid_file_path)? {
+                PidFileRead::NotExist => Ok(false),
+                PidFileRead::LockedByOtherProcess(pid_in_file) => Ok(pid_in_file == pid),
+                PidFileRead::NotHeldByAnyProcess(_) => Ok(false),
+            },
+            None => Ok(true),
+        },
+        Ok(false) => Ok(false),
+        Err(e) => anyhow::bail!("process failed to start: {e}"),
+    }
+}
+
+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/bin/neon_local.rs

@@ -7,29 +7,30 @@
 //!
 use anyhow::{anyhow, bail, Context, Result};
 use clap::{value_parser, Arg, ArgAction, ArgMatches, Command};
-use control_plane::compute::ComputeControlPlane;
+use control_plane::endpoint::ComputeControlPlane;
-use control_plane::local_env::{EtcdBroker, LocalEnv};
+use control_plane::local_env::LocalEnv;
+use control_plane::pageserver::PageServerNode;
 use control_plane::safekeeper::SafekeeperNode;
-use control_plane::storage::PageServerNode;
+use control_plane::{broker, local_env};
-use control_plane::{etcd, local_env};
 use pageserver_api::models::TimelineInfo;
 use pageserver_api::{
     DEFAULT_HTTP_LISTEN_ADDR as DEFAULT_PAGESERVER_HTTP_ADDR,
     DEFAULT_PG_LISTEN_ADDR as DEFAULT_PAGESERVER_PG_ADDR,
 };
+use postgres_backend::AuthType;
 use safekeeper_api::{
     DEFAULT_HTTP_LISTEN_PORT as DEFAULT_SAFEKEEPER_HTTP_PORT,
     DEFAULT_PG_LISTEN_PORT as DEFAULT_SAFEKEEPER_PG_PORT,
 };
 use std::collections::{BTreeSet, HashMap};
-use std::path::{Path, PathBuf};
+use std::path::PathBuf;
 use std::process::exit;
 use std::str::FromStr;
+use storage_broker::DEFAULT_LISTEN_ADDR as DEFAULT_BROKER_ADDR;
 use utils::{
     auth::{Claims, Scope},
     id::{NodeId, TenantId, TenantTimelineId, TimelineId},
     lsn::Lsn,
-    postgres_backend::AuthType,
     project_git_version,
 };
 
@@ -41,27 +42,26 @@ project_git_version!(GIT_VERSION);
 
 const DEFAULT_PG_VERSION: &str = "14";
 
-fn default_conf(etcd_binary_path: &Path) -> String {
+fn default_conf() -> String {
     format!(
         r#"
 # Default built-in configuration, defined in main.rs
-[etcd_broker]
+[broker]
-broker_endpoints = ['http://localhost:2379']
+listen_addr = '{DEFAULT_BROKER_ADDR}'
-etcd_binary_path = '{etcd_binary_path}'
 
 [pageserver]
 id = {DEFAULT_PAGESERVER_ID}
 listen_pg_addr = '{DEFAULT_PAGESERVER_PG_ADDR}'
 listen_http_addr = '{DEFAULT_PAGESERVER_HTTP_ADDR}'
-auth_type = '{pageserver_auth_type}'
+pg_auth_type = '{trust_auth}'
+http_auth_type = '{trust_auth}'
 
 [[safekeepers]]
 id = {DEFAULT_SAFEKEEPER_ID}
 pg_port = {DEFAULT_SAFEKEEPER_PG_PORT}
 http_port = {DEFAULT_SAFEKEEPER_HTTP_PORT}
 "#,
-        etcd_binary_path = etcd_binary_path.display(),
+        trust_auth = AuthType::Trust,
-        pageserver_auth_type = AuthType::Trust,
     )
 }
 
@@ -106,8 +106,9 @@ fn main() -> Result<()> {
             "start" => handle_start_all(sub_args, &env),
             "stop" => handle_stop_all(sub_args, &env),
             "pageserver" => handle_pageserver(sub_args, &env),
-            "pg" => handle_pg(sub_args, &env),
             "safekeeper" => handle_safekeeper(sub_args, &env),
+            "endpoint" => handle_endpoint(sub_args, &env),
+            "pg" => bail!("'pg' subcommand has been renamed to 'endpoint'"),
             _ => bail!("unexpected subcommand {sub_name}"),
         };
 
@@ -264,7 +265,7 @@ fn get_tenant_id(sub_match: &ArgMatches, env: &local_env::LocalEnv) -> anyhow::R
     } else if let Some(default_id) = env.default_tenant_id {
         Ok(default_id)
     } else {
-        bail!("No tenant id. Use --tenant-id, or set 'default_tenant_id' in the config file");
+        anyhow::bail!("No tenant id. Use --tenant-id, or set a default tenant");
     }
 }
 
@@ -285,8 +286,6 @@ fn parse_timeline_id(sub_match: &ArgMatches) -> anyhow::Result<Option<TimelineId
 }
 
 fn handle_init(init_match: &ArgMatches) -> anyhow::Result<LocalEnv> {
-    let initial_timeline_id_arg = parse_timeline_id(init_match)?;
-
     // Create config file
     let toml_file: String = if let Some(config_path) = init_match.get_one::<PathBuf>("config") {
         // load and parse the file
@@ -298,7 +297,7 @@ fn handle_init(init_match: &ArgMatches) -> anyhow::Result<LocalEnv> {
         })?
     } else {
         // Built-in default config
-        default_conf(&EtcdBroker::locate_etcd()?)
+        default_conf()
     };
 
     let pg_version = init_match
@@ -310,30 +309,16 @@ fn handle_init(init_match: &ArgMatches) -> anyhow::Result<LocalEnv> {
         LocalEnv::parse_config(&toml_file).context("Failed to create neon configuration")?;
     env.init(pg_version)
         .context("Failed to initialize neon repository")?;
-    let initial_tenant_id = env
-        .default_tenant_id
-        .expect("default_tenant_id should be generated by the `env.init()` call above");
 
     // Initialize pageserver, create initial tenant and timeline.
     let pageserver = PageServerNode::from_env(&env);
-    let initial_timeline_id = pageserver
+    pageserver
-        .initialize(
+        .initialize(&pageserver_config_overrides(init_match))
-            Some(initial_tenant_id),
-            initial_timeline_id_arg,
-            &pageserver_config_overrides(init_match),
-            pg_version,
-        )
         .unwrap_or_else(|e| {
-            eprintln!("pageserver init failed: {e}");
+            eprintln!("pageserver init failed: {e:?}");
             exit(1);
         });
 
-    env.register_branch_mapping(
-        DEFAULT_BRANCH_NAME.to_owned(),
-        initial_tenant_id,
-        initial_timeline_id,
-    )?;
-
     Ok(env)
 }
 
@@ -342,7 +327,7 @@ fn pageserver_config_overrides(init_match: &ArgMatches) -> Vec<&str> {
         .get_many::<String>("pageserver-config-override")
         .into_iter()
         .flatten()
-        .map(|s| s.as_str())
+        .map(String::as_str)
         .collect()
 }
 
@@ -389,6 +374,17 @@ fn handle_tenant(tenant_match: &ArgMatches, env: &mut local_env::LocalEnv) -> an
             println!(
                 "Created an initial timeline '{new_timeline_id}' at Lsn {last_record_lsn} for tenant: {new_tenant_id}",
             );
+
+            if create_match.get_flag("set-default") {
+                println!("Setting tenant {new_tenant_id} as a default one");
+                env.default_tenant_id = Some(new_tenant_id);
+            }
+        }
+        Some(("set-default", set_default_match)) => {
+            let tenant_id =
+                parse_tenant_id(set_default_match)?.context("No tenant id specified")?;
+            println!("Setting tenant {tenant_id} as a default one");
+            env.default_tenant_id = Some(tenant_id);
         }
         Some(("config", create_match)) => {
             let tenant_id = get_tenant_id(create_match, env)?;
@@ -475,10 +471,10 @@ fn handle_timeline(timeline_match: &ArgMatches, env: &mut local_env::LocalEnv) -
             let mut cplane = ComputeControlPlane::load(env.clone())?;
             println!("Importing timeline into pageserver ...");
             pageserver.timeline_import(tenant_id, timeline_id, base, pg_wal, pg_version)?;
-            println!("Creating node for imported timeline ...");
             env.register_branch_mapping(name.to_string(), tenant_id, timeline_id)?;
 
-            cplane.new_node(tenant_id, name, timeline_id, None, None, pg_version)?;
+            println!("Creating endpoint for imported timeline ...");
+            cplane.new_endpoint(tenant_id, name, timeline_id, None, None, pg_version)?;
             println!("Done");
         }
         Some(("branch", branch_match)) => {
@@ -526,10 +522,10 @@ fn handle_timeline(timeline_match: &ArgMatches, env: &mut local_env::LocalEnv) -
     Ok(())
 }
 
-fn handle_pg(pg_match: &ArgMatches, env: &local_env::LocalEnv) -> Result<()> {
+fn handle_endpoint(ep_match: &ArgMatches, env: &local_env::LocalEnv) -> Result<()> {
-    let (sub_name, sub_args) = match pg_match.subcommand() {
+    let (sub_name, sub_args) = match ep_match.subcommand() {
-        Some(pg_subcommand_data) => pg_subcommand_data,
+        Some(ep_subcommand_data) => ep_subcommand_data,
-        None => bail!("no pg subcommand provided"),
+        None => bail!("no endpoint subcommand provided"),
     };
 
     let mut cplane = ComputeControlPlane::load(env.clone())?;
@@ -550,8 +546,8 @@ fn handle_pg(pg_match: &ArgMatches, env: &local_env::LocalEnv) -> Result<()> {
 
             table.load_preset(comfy_table::presets::NOTHING);
 
-            table.set_header(&[
+            table.set_header([
-                "NODE",
+                "ENDPOINT",
                 "ADDRESS",
                 "TIMELINE",
                 "BRANCH NAME",
@@ -559,39 +555,39 @@ fn handle_pg(pg_match: &ArgMatches, env: &local_env::LocalEnv) -> Result<()> {
                 "STATUS",
             ]);
 
-            for ((_, node_name), node) in cplane
+            for (endpoint_id, endpoint) in cplane
-                .nodes
+                .endpoints
                 .iter()
-                .filter(|((node_tenant_id, _), _)| node_tenant_id == &tenant_id)
+                .filter(|(_, endpoint)| endpoint.tenant_id == tenant_id)
             {
-                let lsn_str = match node.lsn {
+                let lsn_str = match endpoint.lsn {
                     None => {
-                        // -> primary node
+                        // -> primary endpoint
                         // Use the LSN at the end of the timeline.
                         timeline_infos
-                            .get(&node.timeline_id)
+                            .get(&endpoint.timeline_id)
                             .map(|bi| bi.last_record_lsn.to_string())
                             .unwrap_or_else(|| "?".to_string())
                     }
                     Some(lsn) => {
-                        // -> read-only node
+                        // -> read-only endpoint
-                        // Use the node's LSN.
+                        // Use the endpoint's LSN.
                         lsn.to_string()
                     }
                 };
 
                 let branch_name = timeline_name_mappings
-                    .get(&TenantTimelineId::new(tenant_id, node.timeline_id))
+                    .get(&TenantTimelineId::new(tenant_id, endpoint.timeline_id))
                     .map(|name| name.as_str())
                     .unwrap_or("?");
 
-                table.add_row(&[
+                table.add_row([
-                    node_name.as_str(),
+                    endpoint_id.as_str(),
-                    &node.address.to_string(),
+                    &endpoint.address.to_string(),
-                    &node.timeline_id.to_string(),
+                    &endpoint.timeline_id.to_string(),
                     branch_name,
                     lsn_str.as_str(),
-                    node.status(),
+                    endpoint.status(),
                 ]);
             }
 
@@ -602,10 +598,10 @@ fn handle_pg(pg_match: &ArgMatches, env: &local_env::LocalEnv) -> Result<()> {
                 .get_one::<String>("branch-name")
                 .map(|s| s.as_str())
                 .unwrap_or(DEFAULT_BRANCH_NAME);
-            let node_name = sub_args
+            let endpoint_id = sub_args
-                .get_one::<String>("node")
+                .get_one::<String>("endpoint_id")
-                .map(|node_name| node_name.to_string())
+                .map(String::to_string)
-                .unwrap_or_else(|| format!("{branch_name}_node"));
+                .unwrap_or_else(|| format!("ep-{branch_name}"));
 
             let lsn = sub_args
                 .get_one::<String>("lsn")
@@ -623,17 +619,17 @@ fn handle_pg(pg_match: &ArgMatches, env: &local_env::LocalEnv) -> Result<()> {
                 .copied()
                 .context("Failed to parse postgres version from the argument string")?;
 
-            cplane.new_node(tenant_id, &node_name, timeline_id, lsn, port, pg_version)?;
+            cplane.new_endpoint(tenant_id, &endpoint_id, timeline_id, lsn, port, pg_version)?;
         }
         "start" => {
             let port: Option<u16> = sub_args.get_one::<u16>("port").copied();
-            let node_name = sub_args
+            let endpoint_id = sub_args
-                .get_one::<String>("node")
+                .get_one::<String>("endpoint_id")
-                .ok_or_else(|| anyhow!("No node name was provided to start"))?;
+                .ok_or_else(|| anyhow!("No endpoint ID was provided to start"))?;
 
-            let node = cplane.nodes.get(&(tenant_id, node_name.to_string()));
+            let endpoint = cplane.endpoints.get(endpoint_id.as_str());
 
-            let auth_token = if matches!(env.pageserver.auth_type, AuthType::NeonJWT) {
+            let auth_token = if matches!(env.pageserver.pg_auth_type, AuthType::NeonJWT) {
                 let claims = Claims::new(Some(tenant_id), Scope::Tenant);
 
                 Some(env.generate_auth_token(&claims)?)
@@ -641,9 +637,9 @@ fn handle_pg(pg_match: &ArgMatches, env: &local_env::LocalEnv) -> Result<()> {
                 None
             };
 
-            if let Some(node) = node {
+            if let Some(endpoint) = endpoint {
-                println!("Starting existing postgres {node_name}...");
+                println!("Starting existing endpoint {endpoint_id}...");
-                node.start(&auth_token)?;
+                endpoint.start(&auth_token)?;
             } else {
                 let branch_name = sub_args
                     .get_one::<String>("branch-name")
@@ -668,27 +664,33 @@ fn handle_pg(pg_match: &ArgMatches, env: &local_env::LocalEnv) -> Result<()> {
                 // start --port X
                 // stop
                 // start <-- will also use port X even without explicit port argument
-                println!("Starting new postgres (v{pg_version}) {node_name} on timeline {timeline_id} ...");
+                println!("Starting new endpoint {endpoint_id} (PostgreSQL v{pg_version}) on timeline {timeline_id} ...");
 
-                let node =
+                let ep = cplane.new_endpoint(
-                    cplane.new_node(tenant_id, node_name, timeline_id, lsn, port, pg_version)?;
+                    tenant_id,
-                node.start(&auth_token)?;
+                    endpoint_id,
+                    timeline_id,
+                    lsn,
+                    port,
+                    pg_version,
+                )?;
+                ep.start(&auth_token)?;
             }
         }
         "stop" => {
-            let node_name = sub_args
+            let endpoint_id = sub_args
-                .get_one::<String>("node")
+                .get_one::<String>("endpoint_id")
-                .ok_or_else(|| anyhow!("No node name was provided to stop"))?;
+                .ok_or_else(|| anyhow!("No endpoint ID was provided to stop"))?;
             let destroy = sub_args.get_flag("destroy");
 
-            let node = cplane
+            let endpoint = cplane
-                .nodes
+                .endpoints
-                .get(&(tenant_id, node_name.to_string()))
+                .get(endpoint_id.as_str())
-                .with_context(|| format!("postgres {node_name} is not found"))?;
+                .with_context(|| format!("postgres endpoint {endpoint_id} is not found"))?;
-            node.stop(destroy)?;
+            endpoint.stop(destroy)?;
         }
 
-        _ => bail!("Unexpected pg subcommand '{sub_name}'"),
+        _ => bail!("Unexpected endpoint subcommand '{sub_name}'"),
     }
 
     Ok(())
@@ -748,7 +750,7 @@ fn get_safekeeper(env: &local_env::LocalEnv, id: NodeId) -> Result<SafekeeperNod
     if let Some(node) = env.safekeepers.iter().find(|node| node.id == id) {
         Ok(SafekeeperNode::from_env(env, node))
     } else {
-        bail!("could not find safekeeper '{}'", id)
+        bail!("could not find safekeeper {id}")
     }
 }
 
@@ -807,22 +809,22 @@ fn handle_safekeeper(sub_match: &ArgMatches, env: &local_env::LocalEnv) -> Resul
 }
 
 fn handle_start_all(sub_match: &ArgMatches, env: &local_env::LocalEnv) -> anyhow::Result<()> {
-    etcd::start_etcd_process(env)?;
+    // Endpoints are not started automatically
+
+    broker::start_broker_process(env)?;
+
     let pageserver = PageServerNode::from_env(env);
-
-    // Postgres nodes are not started automatically
-
     if let Err(e) = pageserver.start(&pageserver_config_overrides(sub_match)) {
-        eprintln!("pageserver start failed: {e}");
+        eprintln!("pageserver {} start failed: {:#}", env.pageserver.id, e);
-        try_stop_etcd_process(env);
+        try_stop_all(env, true);
         exit(1);
     }
 
     for node in env.safekeepers.iter() {
         let safekeeper = SafekeeperNode::from_env(env, node);
         if let Err(e) = safekeeper.start() {
-            eprintln!("safekeeper '{}' start failed: {e}", safekeeper.id);
+            eprintln!("safekeeper {} start failed: {:#}", safekeeper.id, e);
-            try_stop_etcd_process(env);
+            try_stop_all(env, false);
             exit(1);
         }
     }
@@ -833,35 +835,41 @@ fn handle_stop_all(sub_match: &ArgMatches, env: &local_env::LocalEnv) -> Result<
     let immediate =
         sub_match.get_one::<String>("stop-mode").map(|s| s.as_str()) == Some("immediate");
 
+    try_stop_all(env, immediate);
+
+    Ok(())
+}
+
+fn try_stop_all(env: &local_env::LocalEnv, immediate: bool) {
     let pageserver = PageServerNode::from_env(env);
 
-    // Stop all compute nodes
+    // Stop all endpoints
-    let cplane = ComputeControlPlane::load(env.clone())?;
+    match ComputeControlPlane::load(env.clone()) {
-    for (_k, node) in cplane.nodes {
+        Ok(cplane) => {
+            for (_k, node) in cplane.endpoints {
                 if let Err(e) = node.stop(false) {
-            eprintln!("postgres stop failed: {}", e);
+                    eprintln!("postgres stop failed: {e:#}");
+                }
+            }
+        }
+        Err(e) => {
+            eprintln!("postgres stop failed, could not restore control plane data from env: {e:#}")
         }
     }
 
     if let Err(e) = pageserver.stop(immediate) {
-        eprintln!("pageserver stop failed: {}", e);
+        eprintln!("pageserver {} stop failed: {:#}", env.pageserver.id, e);
     }
 
     for node in env.safekeepers.iter() {
         let safekeeper = SafekeeperNode::from_env(env, node);
         if let Err(e) = safekeeper.stop(immediate) {
-            eprintln!("safekeeper '{}' stop failed: {}", safekeeper.id, e);
+            eprintln!("safekeeper {} stop failed: {:#}", safekeeper.id, e);
         }
     }
 
-    try_stop_etcd_process(env);
+    if let Err(e) = broker::stop_broker_process(env) {
-
+        eprintln!("neon broker stop failed: {e:#}");
-    Ok(())
-}
-
-fn try_stop_etcd_process(env: &local_env::LocalEnv) {
-    if let Err(e) = etcd::stop_etcd_process(env) {
-        eprintln!("etcd stop failed: {e}");
     }
 }
 
@@ -871,7 +879,9 @@ fn cli() -> Command {
         .help("Name of the branch to be created or used as an alias for other services")
         .required(false);
 
-    let pg_node_arg = Arg::new("node").help("Postgres node name").required(false);
+    let endpoint_id_arg = Arg::new("endpoint_id")
+        .help("Postgres endpoint id")
+        .required(false);
 
     let safekeeper_id_arg = Arg::new("id").help("safekeeper id").required(false);
 
@@ -901,6 +911,7 @@ fn cli() -> Command {
     let stop_mode_arg = Arg::new("stop-mode")
         .short('m')
         .value_parser(["fast", "immediate"])
+        .default_value("fast")
         .help("If 'immediate', don't flush repository data at shutdown")
         .required(false)
         .value_name("stop-mode");
@@ -922,9 +933,8 @@ fn cli() -> Command {
         .version(GIT_VERSION)
         .subcommand(
             Command::new("init")
-                .about("Initialize a new Neon repository")
+                .about("Initialize a new Neon repository, preparing configs for services to start with")
                 .arg(pageserver_config_args.clone())
-                .arg(timeline_id_arg.clone().help("Use a specific timeline id when creating a tenant and its initial timeline"))
                 .arg(
                     Arg::new("config")
                         .long("config")
@@ -986,11 +996,14 @@ fn cli() -> Command {
                 .arg(timeline_id_arg.clone().help("Use a specific timeline id when creating a tenant and its initial timeline"))
                 .arg(Arg::new("config").short('c').num_args(1).action(ArgAction::Append).required(false))
                 .arg(pg_version_arg.clone())
+                .arg(Arg::new("set-default").long("set-default").action(ArgAction::SetTrue).required(false)
+                    .help("Use this tenant in future CLI commands where tenant_id is needed, but not specified"))
                 )
+            .subcommand(Command::new("set-default").arg(tenant_id_arg.clone().required(true))
+                .about("Set a particular tenant as default in future CLI commands where tenant_id is needed, but not specified"))
             .subcommand(Command::new("config")
                 .arg(tenant_id_arg.clone())
-                .arg(Arg::new("config").short('c').num_args(1).action(ArgAction::Append).required(false))
+                .arg(Arg::new("config").short('c').num_args(1).action(ArgAction::Append).required(false)))
-                )
         )
         .subcommand(
             Command::new("pageserver")
@@ -1022,27 +1035,27 @@ fn cli() -> Command {
                 )
         )
         .subcommand(
-            Command::new("pg")
+            Command::new("endpoint")
                 .arg_required_else_help(true)
                 .about("Manage postgres instances")
                 .subcommand(Command::new("list").arg(tenant_id_arg.clone()))
                 .subcommand(Command::new("create")
-                    .about("Create a postgres compute node")
+                    .about("Create a compute endpoint")
-                    .arg(pg_node_arg.clone())
+                    .arg(endpoint_id_arg.clone())
                     .arg(branch_name_arg.clone())
                     .arg(tenant_id_arg.clone())
                     .arg(lsn_arg.clone())
                     .arg(port_arg.clone())
                     .arg(
                         Arg::new("config-only")
-                            .help("Don't do basebackup, create compute node with only config files")
+                            .help("Don't do basebackup, create endpoint directory with only config files")
                             .long("config-only")
                             .required(false))
                     .arg(pg_version_arg.clone())
                 )
                 .subcommand(Command::new("start")
-                    .about("Start a postgres compute node.\n This command actually creates new node from scratch, but preserves existing config files")
+                    .about("Start postgres.\n If the endpoint doesn't exist yet, it is created.")
-                    .arg(pg_node_arg.clone())
+                    .arg(endpoint_id_arg.clone())
                     .arg(tenant_id_arg.clone())
                     .arg(branch_name_arg)
                     .arg(timeline_id_arg)
@@ -1052,7 +1065,7 @@ fn cli() -> Command {
                 )
                 .subcommand(
                     Command::new("stop")
-                    .arg(pg_node_arg)
+                    .arg(endpoint_id_arg)
                     .arg(tenant_id_arg)
                     .arg(
                         Arg::new("destroy")
@@ -1064,6 +1077,13 @@ fn cli() -> Command {
                 )
 
         )
+        // Obsolete old name for 'endpoint'. We now just print an error if it's used.
+        .subcommand(
+            Command::new("pg")
+                .hide(true)
+                .arg(Arg::new("ignore-rest").allow_hyphen_values(true).num_args(0..).required(false))
+                .trailing_var_arg(true)
+        )
         .subcommand(
             Command::new("start")
                 .about("Start page server and safekeepers")

control_plane/src/broker.rs

@@ -0,0 +1,48 @@
+use anyhow::Context;
+
+use std::path::PathBuf;
+
+use crate::{background_process, local_env};
+
+pub fn start_broker_process(env: &local_env::LocalEnv) -> anyhow::Result<()> {
+    let broker = &env.broker;
+    let listen_addr = &broker.listen_addr;
+
+    print!("Starting neon broker at {}", listen_addr);
+
+    let args = [format!("--listen-addr={listen_addr}")];
+
+    let client = reqwest::blocking::Client::new();
+    background_process::start_process(
+        "storage_broker",
+        &env.base_data_dir,
+        &env.storage_broker_bin(),
+        args,
+        [],
+        background_process::InitialPidFile::Create(&storage_broker_pid_file_path(env)),
+        || {
+            let url = broker.client_url();
+            let status_url = url.join("status").with_context(|| {
+                format!("Failed to append /status path to broker endpoint {url}",)
+            })?;
+            let request = client
+                .get(status_url)
+                .build()
+                .with_context(|| format!("Failed to construct request to broker endpoint {url}"))?;
+            match client.execute(request) {
+                Ok(resp) => Ok(resp.status().is_success()),
+                Err(_) => Ok(false),
+            }
+        },
+    )
+    .context("Failed to spawn storage_broker subprocess")?;
+    Ok(())
+}
+
+pub fn stop_broker_process(env: &local_env::LocalEnv) -> anyhow::Result<()> {
+    background_process::stop_process(true, "storage_broker", &storage_broker_pid_file_path(env))
+}
+
+fn storage_broker_pid_file_path(env: &local_env::LocalEnv) -> PathBuf {
+    env.base_data_dir.join("storage_broker.pid")
+}

control_plane/src/endpoint.rs

@@ -12,69 +12,58 @@ use std::time::Duration;
 
 use anyhow::{Context, Result};
 use utils::{
-    connstring::connection_host_port,
     id::{TenantId, TimelineId},
     lsn::Lsn,
-    postgres_backend::AuthType,
 };
 
 use crate::local_env::{LocalEnv, DEFAULT_PG_VERSION};
+use crate::pageserver::PageServerNode;
 use crate::postgresql_conf::PostgresConf;
-use crate::storage::PageServerNode;
 
 //
 // ComputeControlPlane
 //
 pub struct ComputeControlPlane {
     base_port: u16,
-    pageserver: Arc<PageServerNode>,
+
-    pub nodes: BTreeMap<(TenantId, String), Arc<PostgresNode>>,
+    // endpoint ID is the key
+    pub endpoints: BTreeMap<String, Arc<Endpoint>>,
+
     env: LocalEnv,
+    pageserver: Arc<PageServerNode>,
 }
 
 impl ComputeControlPlane {
-    // Load current nodes with ports from data directories on disk
+    // Load current endpoints from the endpoints/ subdirectories
-    // Directory structure has the following layout:
-    // pgdatadirs
-    // |- tenants
-    // |  |- <tenant_id>
-    // |  |   |- <node name>
     pub fn load(env: LocalEnv) -> Result<ComputeControlPlane> {
         let pageserver = Arc::new(PageServerNode::from_env(&env));
 
-        let mut nodes = BTreeMap::default();
+        let mut endpoints = BTreeMap::default();
-        let pgdatadirspath = &env.pg_data_dirs_path();
+        for endpoint_dir in fs::read_dir(env.endpoints_path())
-
+            .with_context(|| format!("failed to list {}", env.endpoints_path().display()))?
-        for tenant_dir in fs::read_dir(&pgdatadirspath)
-            .with_context(|| format!("failed to list {}", pgdatadirspath.display()))?
         {
-            let tenant_dir = tenant_dir?;
+            let ep = Endpoint::from_dir_entry(endpoint_dir?, &env, &pageserver)?;
-            for timeline_dir in fs::read_dir(tenant_dir.path())
+            endpoints.insert(ep.name.clone(), Arc::new(ep));
-                .with_context(|| format!("failed to list {}", tenant_dir.path().display()))?
-            {
-                let node = PostgresNode::from_dir_entry(timeline_dir?, &env, &pageserver)?;
-                nodes.insert((node.tenant_id, node.name.clone()), Arc::new(node));
-            }
         }
 
         Ok(ComputeControlPlane {
             base_port: 55431,
-            pageserver,
+            endpoints,
-            nodes,
             env,
+            pageserver,
         })
     }
 
     fn get_port(&mut self) -> u16 {
         1 + self
-            .nodes
+            .endpoints
-            .iter()
+            .values()
-            .map(|(_name, node)| node.address.port())
+            .map(|ep| ep.address.port())
             .max()
             .unwrap_or(self.base_port)
     }
 
-    pub fn new_node(
+    pub fn new_endpoint(
         &mut self,
         tenant_id: TenantId,
         name: &str,
@@ -82,56 +71,58 @@ impl ComputeControlPlane {
         lsn: Option<Lsn>,
         port: Option<u16>,
         pg_version: u32,
-    ) -> Result<Arc<PostgresNode>> {
+    ) -> Result<Arc<Endpoint>> {
         let port = port.unwrap_or_else(|| self.get_port());
-        let node = Arc::new(PostgresNode {
+        let ep = Arc::new(Endpoint {
             name: name.to_owned(),
             address: SocketAddr::new("127.0.0.1".parse().unwrap(), port),
             env: self.env.clone(),
             pageserver: Arc::clone(&self.pageserver),
-            is_test: false,
             timeline_id,
             lsn,
             tenant_id,
-            uses_wal_proposer: false,
             pg_version,
         });
 
-        node.create_pgdata()?;
+        ep.create_pgdata()?;
-        node.setup_pg_conf(self.env.pageserver.auth_type)?;
+        ep.setup_pg_conf()?;
 
-        self.nodes
+        self.endpoints.insert(ep.name.clone(), Arc::clone(&ep));
-            .insert((tenant_id, node.name.clone()), Arc::clone(&node));
 
-        Ok(node)
+        Ok(ep)
     }
 }
 
 ///////////////////////////////////////////////////////////////////////////////
 
 #[derive(Debug)]
-pub struct PostgresNode {
+pub struct Endpoint {
-    pub address: SocketAddr,
+    /// used as the directory name
     name: String,
+    pub tenant_id: TenantId,
+    pub timeline_id: TimelineId,
+    // Some(lsn) if this is a read-only endpoint anchored at 'lsn'. None for the primary.
+    pub lsn: Option<Lsn>,
+
+    // port and address of the Postgres server
+    pub address: SocketAddr,
+    pg_version: u32,
+
+    // These are not part of the endpoint as such, but the environment
+    // the endpoint runs in.
     pub env: LocalEnv,
     pageserver: Arc<PageServerNode>,
-    is_test: bool,
-    pub timeline_id: TimelineId,
-    pub lsn: Option<Lsn>, // if it's a read-only node. None for primary
-    pub tenant_id: TenantId,
-    uses_wal_proposer: bool,
-    pg_version: u32,
 }
 
-impl PostgresNode {
+impl Endpoint {
     fn from_dir_entry(
         entry: std::fs::DirEntry,
         env: &LocalEnv,
         pageserver: &Arc<PageServerNode>,
-    ) -> Result<PostgresNode> {
+    ) -> Result<Endpoint> {
         if !entry.file_type()?.is_dir() {
             anyhow::bail!(
-                "PostgresNode::from_dir_entry failed: '{}' is not a directory",
+                "Endpoint::from_dir_entry failed: '{}' is not a directory",
                 entry.path().display()
             );
         }
@@ -141,7 +132,7 @@ impl PostgresNode {
         let name = fname.to_str().unwrap().to_string();
 
         // Read config file into memory
-        let cfg_path = entry.path().join("postgresql.conf");
+        let cfg_path = entry.path().join("pgdata").join("postgresql.conf");
         let cfg_path_str = cfg_path.to_string_lossy();
         let mut conf_file = File::open(&cfg_path)
             .with_context(|| format!("failed to open config file in {}", cfg_path_str))?;
@@ -153,7 +144,6 @@ impl PostgresNode {
         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.
@@ -168,33 +158,31 @@ impl PostgresNode {
             conf.parse_field_optional("recovery_target_lsn", &context)?;
 
         // ok now
-        Ok(PostgresNode {
+        Ok(Endpoint {
             address: SocketAddr::new("127.0.0.1".parse().unwrap(), port),
             name,
             env: env.clone(),
             pageserver: Arc::clone(pageserver),
-            is_test: false,
             timeline_id,
             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");
+        let pg_path = self.env.pg_bin_dir(pg_version)?.join("postgres");
-        let mut cmd = Command::new(&pg_path);
+        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(),
+                self.env.pg_lib_dir(pg_version)?.to_str().unwrap(),
             )
             .env(
                 "DYLD_LIBRARY_PATH",
-                self.env.pg_lib_dir(pg_version).to_str().unwrap(),
+                self.env.pg_lib_dir(pg_version)?.to_str().unwrap(),
             )
             .env("PGDATA", self.pgdata().to_str().unwrap())
             .stdout(Stdio::piped())
@@ -202,7 +190,7 @@ impl PostgresNode {
             .stderr(Stdio::piped());
 
         if let Some(token) = auth_token {
-            cmd.env("ZENITH_AUTH_TOKEN", token);
+            cmd.env("NEON_AUTH_TOKEN", token);
         }
 
         let sync_handle = cmd
@@ -262,7 +250,7 @@ impl PostgresNode {
     }
 
     fn create_pgdata(&self) -> Result<()> {
-        fs::create_dir_all(&self.pgdata()).with_context(|| {
+        fs::create_dir_all(self.pgdata()).with_context(|| {
             format!(
                 "could not create data directory {}",
                 self.pgdata().display()
@@ -278,13 +266,11 @@ impl PostgresNode {
     }
 
     // Write postgresql.conf with default configuration
-    // and PG_VERSION file to the data directory of a new node.
+    // and PG_VERSION file to the data directory of a new endpoint.
-    fn setup_pg_conf(&self, auth_type: AuthType) -> Result<()> {
+    fn setup_pg_conf(&self) -> Result<()> {
         let mut conf = PostgresConf::new();
         conf.append("max_wal_senders", "10");
-        // wal_log_hints is mandatory when running against pageserver (see gh issue#192)
+        conf.append("wal_log_hints", "off");
-        // 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");
@@ -300,26 +286,13 @@ impl PostgresNode {
         // walproposer panics when basebackup is invalid, it is pointless to restart in this case.
         conf.append("restart_after_crash", "off");
 
-        // Configure the node to fetch pages from pageserver
+        // Configure the Neon Postgres extension to fetch pages from pageserver
         let pageserver_connstr = {
-            let (host, port) = connection_host_port(&self.pageserver.pg_connection_config);
+            let config = &self.pageserver.pg_connection_config;
+            let (host, port) = (config.host(), config.port());
 
-            // Set up authentication
+            // NOTE: avoid spaces in connection string, because it is less error prone if we forward it somewhere.
-            //
+            format!("postgresql://no_user@{host}:{port}")
-            // $ZENITH_AUTH_TOKEN will be replaced with value from environment
-            // variable during compute pg startup. It is done this way because
-            // otherwise user will be able to retrieve the value using SHOW
-            // command or pg_settings
-            let password = if let AuthType::NeonJWT = auth_type {
-                "$ZENITH_AUTH_TOKEN"
-            } else {
-                ""
-            };
-            // NOTE avoiding spaces in connection string, because it is less error prone if we forward it somewhere.
-            // 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}")
         };
         conf.append("shared_preload_libraries", "neon");
         conf.append_line("");
@@ -345,11 +318,11 @@ impl PostgresNode {
         //   To be able to restore database in case of pageserver node crash, safekeeper should not
         //   remove WAL beyond this point. Too large lag can cause space exhaustion in safekeepers
         //   (if they are not able to upload WAL to S3).
-        conf.append("max_replication_write_lag", "500MB");
+        conf.append("max_replication_write_lag", "15MB");
         conf.append("max_replication_flush_lag", "10GB");
 
         if !self.env.safekeepers.is_empty() {
-            // Configure the node to connect to the safekeepers
+            // Configure Postgres to connect to the safekeepers
             conf.append("synchronous_standby_names", "walproposer");
 
             let safekeepers = self
@@ -384,7 +357,7 @@ impl PostgresNode {
     fn load_basebackup(&self, auth_token: &Option<String>) -> Result<()> {
         let backup_lsn = if let Some(lsn) = self.lsn {
             Some(lsn)
-        } else if self.uses_wal_proposer {
+        } else if !self.env.safekeepers.is_empty() {
             // LSN 0 means that it is bootstrap and we need to download just
             // 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
@@ -404,8 +377,12 @@ impl PostgresNode {
         Ok(())
     }
 
+    pub fn endpoint_path(&self) -> PathBuf {
+        self.env.endpoints_path().join(&self.name)
+    }
+
     pub fn pgdata(&self) -> PathBuf {
-        self.env.pg_data_dir(&self.tenant_id, &self.name)
+        self.endpoint_path().join("pgdata")
     }
 
     pub fn status(&self) -> &str {
@@ -422,8 +399,8 @@ 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(self.pg_version)?.join("pg_ctl");
-        let mut cmd = Command::new(pg_ctl_path);
+        let mut cmd = Command::new(&pg_ctl_path);
         cmd.args(
             [
                 &[
@@ -440,17 +417,21 @@ impl PostgresNode {
         .env_clear()
         .env(
             "LD_LIBRARY_PATH",
-            self.env.pg_lib_dir(self.pg_version).to_str().unwrap(),
+            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(),
+            self.env.pg_lib_dir(self.pg_version)?.to_str().unwrap(),
         );
+
+        // Pass authentication token used for the connections to pageserver and safekeepers
         if let Some(token) = auth_token {
-            cmd.env("ZENITH_AUTH_TOKEN", token);
+            cmd.env("NEON_AUTH_TOKEN", token);
         }
 
-        let pg_ctl = cmd.output().context("pg_ctl failed")?;
+        let pg_ctl = cmd
+            .output()
+            .context(format!("{} failed", pg_ctl_path.display()))?;
         if !pg_ctl.status.success() {
             anyhow::bail!(
                 "pg_ctl failed, exit code: {}, stdout: {}, stderr: {}",
@@ -463,12 +444,11 @@ impl PostgresNode {
     }
 
     pub fn start(&self, auth_token: &Option<String>) -> Result<()> {
-        // Bail if the node already running.
         if self.status() == "running" {
-            anyhow::bail!("The node is already running");
+            anyhow::bail!("The endpoint is already running");
         }
 
-        // 1. We always start compute node from scratch, so
+        // 1. We always start Postgres from scratch, so
         // if old dir exists, preserve 'postgresql.conf' and drop the directory
         let postgresql_conf_path = self.pgdata().join("postgresql.conf");
         let postgresql_conf = fs::read(&postgresql_conf_path).with_context(|| {
@@ -477,7 +457,7 @@ impl PostgresNode {
                 postgresql_conf_path.to_str().unwrap()
             )
         })?;
-        fs::remove_dir_all(&self.pgdata())?;
+        fs::remove_dir_all(self.pgdata())?;
         self.create_pgdata()?;
 
         // 2. Bring back config files
@@ -490,21 +470,17 @@ impl PostgresNode {
             File::create(self.pgdata().join("standby.signal"))?;
         }
 
-        // 4. Finally start the compute node postgres
+        // 4. Finally start postgres
-        println!("Starting postgres node at '{}'", self.connstr());
+        println!("Starting postgres at '{}'", self.connstr());
         self.pg_ctl(&["start"], auth_token)
     }
 
-    pub fn restart(&self, auth_token: &Option<String>) -> Result<()> {
-        self.pg_ctl(&["restart"], auth_token)
-    }
-
     pub fn stop(&self, destroy: bool) -> Result<()> {
         // If we are going to destroy data directory,
         // use immediate shutdown mode, otherwise,
         // shutdown gracefully to leave the data directory sane.
         //
-        // Compute node always starts from scratch, so stop
+        // Postgres is always started from scratch, so stop
         // without destroy only used for testing and debugging.
         //
         if destroy {
@@ -513,7 +489,7 @@ impl PostgresNode {
                 "Destroying postgres data directory '{}'",
                 self.pgdata().to_str().unwrap()
             );
-            fs::remove_dir_all(&self.pgdata())?;
+            fs::remove_dir_all(self.endpoint_path())?;
         } else {
             self.pg_ctl(&["stop"], &None)?;
         }
@@ -529,26 +505,4 @@ impl PostgresNode {
             "postgres"
         )
     }
-
-    // XXX: cache that in control plane
-    pub fn whoami(&self) -> String {
-        let output = Command::new("whoami")
-            .output()
-            .expect("failed to execute whoami");
-
-        assert!(output.status.success(), "whoami failed");
-
-        String::from_utf8(output.stdout).unwrap().trim().to_string()
-    }
-}
-
-impl Drop for PostgresNode {
-    // destructor to clean up state after test is done
-    // XXX: we may detect failed test by setting some flag in catch_unwind()
-    // and checking it here. But let just clean datadirs on start.
-    fn drop(&mut self) {
-        if self.is_test {
-            let _ = self.stop(true);
-        }
-    }
 }

control_plane/src/etcd.rs

@@ -1,97 +0,0 @@
-use std::{
-    fs,
-    path::PathBuf,
-    process::{Command, Stdio},
-};
-
-use anyhow::Context;
-use nix::{
-    sys::signal::{kill, Signal},
-    unistd::Pid,
-};
-
-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.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.display()
-        )
-    })?;
-
-    let etcd_stdout_file =
-        fs::File::create(etcd_data_dir.join("etcd.stdout.log")).with_context(|| {
-            format!(
-                "Failed to create etcd 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 etcd stderr file in directory {}",
-                etcd_data_dir.display()
-            )
-        })?;
-    let client_urls = etcd_broker.comma_separated_endpoints();
-
-    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 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<()> {
-    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 {
-    env.base_data_dir.join("etcd.pid")
-}

control_plane/src/lib.rs

@@ -6,59 +6,11 @@
 // 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;
 
-pub mod compute;
+mod background_process;
-pub mod etcd;
+pub mod broker;
+pub mod endpoint;
 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",
-        "AWS_SESSION_TOKEN",
-    ] {
-        if let Ok(value) = std::env::var(env_key) {
-            cmd = cmd.env(env_key, value);
-        }
-    }
-    cmd
-}

control_plane/src/local_env.rs

@@ -4,18 +4,22 @@
 //! script which will use local paths.
 
 use anyhow::{bail, ensure, Context};
+
+use postgres_backend::AuthType;
 use reqwest::Url;
 use serde::{Deserialize, Serialize};
 use serde_with::{serde_as, DisplayFromStr};
 use std::collections::HashMap;
 use std::env;
 use std::fs;
+use std::net::IpAddr;
+use std::net::Ipv4Addr;
+use std::net::SocketAddr;
 use std::path::{Path, PathBuf};
 use std::process::{Command, Stdio};
 use utils::{
-    auth::{encode_from_key_file, Claims, Scope},
+    auth::{encode_from_key_file, Claims},
     id::{NodeId, TenantId, TenantTimelineId, TimelineId},
-    postgres_backend::AuthType,
 };
 
 use crate::safekeeper::SafekeeperNode;
@@ -62,7 +66,7 @@ pub struct LocalEnv {
     #[serde(default)]
     pub private_key_path: PathBuf,
 
-    pub etcd_broker: EtcdBroker,
+    pub broker: NeonBroker,
 
     pub pageserver: PageServerConf,
 
@@ -78,67 +82,26 @@ pub struct LocalEnv {
     branch_name_mappings: HashMap<String, Vec<(TenantId, TimelineId)>>,
 }
 
-/// Etcd broker config for cluster internal communication.
+/// Broker config for cluster internal communication.
-#[serde_as]
 #[derive(Serialize, Deserialize, PartialEq, Eq, Clone, Debug)]
-pub struct EtcdBroker {
+#[serde(default)]
-    /// A prefix to all to any key when pushing/polling etcd from a node.
+pub struct NeonBroker {
-    #[serde(default)]
+    /// Broker listen address for storage nodes coordination, e.g. '127.0.0.1:50051'.
-    pub broker_etcd_prefix: Option<String>,
+    pub listen_addr: SocketAddr,
-
-    /// Broker (etcd) endpoints for storage nodes coordination, e.g. 'http://127.0.0.1:2379'.
-    #[serde(default)]
-    #[serde_as(as = "Vec<DisplayFromStr>")]
-    pub broker_endpoints: Vec<Url>,
-
-    /// Etcd binary path to use.
-    #[serde(default)]
-    pub etcd_binary_path: PathBuf,
 }
 
-impl EtcdBroker {
+// Dummy Default impl to satisfy Deserialize derive.
-    pub fn locate_etcd() -> anyhow::Result<PathBuf> {
+impl Default for NeonBroker {
-        let which_output = Command::new("which")
+    fn default() -> Self {
-            .arg("etcd")
+        NeonBroker {
-            .output()
+            listen_addr: SocketAddr::new(IpAddr::V4(Ipv4Addr::new(0, 0, 0, 0)), 0),
-            .context("Failed to run 'which etcd' command")?;
-        let stdout = String::from_utf8_lossy(&which_output.stdout);
-        ensure!(
-            which_output.status.success(),
-            "'which etcd' invocation failed. Status: {}, stdout: {stdout}, stderr: {}",
-            which_output.status,
-            String::from_utf8_lossy(&which_output.stderr)
-        );
-
-        let etcd_path = PathBuf::from(stdout.trim());
-        ensure!(
-            etcd_path.is_file(),
-            "'which etcd' invocation was successful, but the path it returned is not a file or does not exist: {}",
-            etcd_path.display()
-        );
-
-        Ok(etcd_path)
         }
+    }
+}
 
-    pub fn comma_separated_endpoints(&self) -> String {
+impl NeonBroker {
-        self.broker_endpoints
+    pub fn client_url(&self) -> Url {
-            .iter()
+        Url::parse(&format!("http://{}", self.listen_addr)).expect("failed to construct url")
-            .map(|url| {
-                // URL by default adds a '/' path at the end, which is not what etcd CLI wants.
-                let url_string = url.as_str();
-                if url_string.ends_with('/') {
-                    &url_string[0..url_string.len() - 1]
-                } else {
-                    url_string
-                }
-            })
-            .fold(String::new(), |mut comma_separated_urls, url| {
-                if !comma_separated_urls.is_empty() {
-                    comma_separated_urls.push(',');
-                }
-                comma_separated_urls.push_str(url);
-                comma_separated_urls
-            })
     }
 }
 
@@ -147,15 +110,14 @@ impl EtcdBroker {
 pub struct PageServerConf {
     // node id
     pub id: NodeId,
+
     // Pageserver connection settings
     pub listen_pg_addr: String,
     pub listen_http_addr: String,
 
-    // used to determine which auth type is used
+    // auth type used for the PG and HTTP ports
-    pub auth_type: AuthType,
+    pub pg_auth_type: AuthType,
-
+    pub http_auth_type: AuthType,
-    // jwt auth token used for communication with pageserver
-    pub auth_token: String,
 }
 
 impl Default for PageServerConf {
@@ -164,8 +126,8 @@ impl Default for PageServerConf {
             id: NodeId(0),
             listen_pg_addr: String::new(),
             listen_http_addr: String::new(),
-            auth_type: AuthType::Trust,
+            pg_auth_type: AuthType::Trust,
-            auth_token: String::new(),
+            http_auth_type: AuthType::Trust,
         }
     }
 }
@@ -201,47 +163,45 @@ impl LocalEnv {
         self.pg_distrib_dir.clone()
     }
 
-    pub fn pg_distrib_dir(&self, pg_version: u32) -> PathBuf {
+    pub fn pg_distrib_dir(&self, pg_version: u32) -> anyhow::Result<PathBuf> {
         let path = self.pg_distrib_dir.clone();
 
         match pg_version {
-            14 => path.join(format!("v{pg_version}")),
+            14 => Ok(path.join(format!("v{pg_version}"))),
-            15 => path.join(format!("v{pg_version}")),
+            15 => Ok(path.join(format!("v{pg_version}"))),
-            _ => panic!("Unsupported postgres version: {}", pg_version),
+            _ => bail!("Unsupported postgres version: {}", pg_version),
         }
     }
 
-    pub fn pg_bin_dir(&self, pg_version: u32) -> PathBuf {
+    pub fn pg_bin_dir(&self, pg_version: u32) -> anyhow::Result<PathBuf> {
         match pg_version {
-            14 => self.pg_distrib_dir(pg_version).join("bin"),
+            14 => Ok(self.pg_distrib_dir(pg_version)?.join("bin")),
-            15 => self.pg_distrib_dir(pg_version).join("bin"),
+            15 => Ok(self.pg_distrib_dir(pg_version)?.join("bin")),
-            _ => panic!("Unsupported postgres version: {}", pg_version),
+            _ => bail!("Unsupported postgres version: {}", pg_version),
         }
     }
-    pub fn pg_lib_dir(&self, pg_version: u32) -> PathBuf {
+    pub fn pg_lib_dir(&self, pg_version: u32) -> anyhow::Result<PathBuf> {
         match pg_version {
-            14 => self.pg_distrib_dir(pg_version).join("lib"),
+            14 => Ok(self.pg_distrib_dir(pg_version)?.join("lib")),
-            15 => self.pg_distrib_dir(pg_version).join("lib"),
+            15 => Ok(self.pg_distrib_dir(pg_version)?.join("lib")),
-            _ => panic!("Unsupported postgres version: {}", pg_version),
+            _ => bail!("Unsupported postgres version: {}", pg_version),
         }
     }
 
-    pub fn pageserver_bin(&self) -> anyhow::Result<PathBuf> {
+    pub fn pageserver_bin(&self) -> PathBuf {
-        Ok(self.neon_distrib_dir.join("pageserver"))
+        self.neon_distrib_dir.join("pageserver")
     }
 
-    pub fn safekeeper_bin(&self) -> anyhow::Result<PathBuf> {
+    pub fn safekeeper_bin(&self) -> PathBuf {
-        Ok(self.neon_distrib_dir.join("safekeeper"))
+        self.neon_distrib_dir.join("safekeeper")
     }
 
-    pub fn pg_data_dirs_path(&self) -> PathBuf {
+    pub fn storage_broker_bin(&self) -> PathBuf {
-        self.base_data_dir.join("pgdatadirs").join("tenants")
+        self.neon_distrib_dir.join("storage_broker")
     }
 
-    pub fn pg_data_dir(&self, tenant_id: &TenantId, branch_name: &str) -> PathBuf {
+    pub fn endpoints_path(&self) -> PathBuf {
-        self.pg_data_dirs_path()
+        self.base_data_dir.join("endpoints")
-            .join(tenant_id.to_string())
-            .join(branch_name)
     }
 
     // TODO: move pageserver files into ./pageserver
@@ -329,11 +289,6 @@ impl LocalEnv {
             env.neon_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.base_data_dir = base_path();
 
         Ok(env)
@@ -422,10 +377,10 @@ impl LocalEnv {
             "directory '{}' already exists. Perhaps already initialized?",
             base_path.display()
         );
-        if !self.pg_bin_dir(pg_version).join("postgres").exists() {
+        if !self.pg_bin_dir(pg_version)?.join("postgres").exists() {
             bail!(
                 "Can't find postgres binary at {}",
-                self.pg_bin_dir(pg_version).display()
+                self.pg_bin_dir(pg_version)?.display()
             );
         }
         for binary in ["pageserver", "safekeeper"] {
@@ -437,51 +392,36 @@ impl LocalEnv {
             }
         }
 
-        fs::create_dir(&base_path)?;
+        fs::create_dir(base_path)?;
 
-        // generate keys for jwt
+        // Generate keypair for JWT.
-        // openssl genrsa -out private_key.pem 2048
+        //
-        let private_key_path;
+        // The keypair is only needed if authentication is enabled in any of the
+        // components. For convenience, we generate the keypair even if authentication
+        // is not enabled, so that you can easily enable it after the initialization
+        // step. However, if the key generation fails, we treat it as non-fatal if
+        // authentication was not enabled.
         if self.private_key_path == PathBuf::new() {
-            private_key_path = base_path.join("auth_private_key.pem");
+            match generate_auth_keys(
-            let keygen_output = Command::new("openssl")
+                base_path.join("auth_private_key.pem").as_path(),
-                .arg("genrsa")
+                base_path.join("auth_public_key.pem").as_path(),
-                .args(&["-out", private_key_path.to_str().unwrap()])
+            ) {
-                .arg("2048")
+                Ok(()) => {
-                .stdout(Stdio::null())
-                .output()
-                .context("failed to generate auth private key")?;
-            if !keygen_output.status.success() {
-                bail!(
-                    "openssl failed: '{}'",
-                    String::from_utf8_lossy(&keygen_output.stderr)
-                );
-            }
                     self.private_key_path = PathBuf::from("auth_private_key.pem");
-
+                }
-            let public_key_path = base_path.join("auth_public_key.pem");
+                Err(e) => {
-            // openssl rsa -in private_key.pem -pubout -outform PEM -out public_key.pem
+                    if !self.auth_keys_needed() {
-            let keygen_output = Command::new("openssl")
+                        eprintln!("Could not generate keypair for JWT authentication: {e}");
-                .arg("rsa")
+                        eprintln!("Continuing anyway because authentication was not enabled");
-                .args(&["-in", private_key_path.to_str().unwrap()])
+                        self.private_key_path = PathBuf::from("auth_private_key.pem");
-                .arg("-pubout")
+                    } else {
-                .args(&["-outform", "PEM"])
+                        return Err(e);
-                .args(&["-out", public_key_path.to_str().unwrap()])
+                    }
-                .stdout(Stdio::null())
+                }
-                .output()
-                .context("failed to generate auth private key")?;
-            if !keygen_output.status.success() {
-                bail!(
-                    "openssl failed: '{}'",
-                    String::from_utf8_lossy(&keygen_output.stderr)
-                );
             }
         }
 
-        self.pageserver.auth_token =
+        fs::create_dir_all(self.endpoints_path())?;
-            self.generate_auth_token(&Claims::new(None, Scope::PageServerApi))?;
-
-        fs::create_dir_all(self.pg_data_dirs_path())?;
 
         for safekeeper in &self.safekeepers {
             fs::create_dir_all(SafekeeperNode::datadir_path_by_id(self, safekeeper.id))?;
@@ -489,6 +429,12 @@ impl LocalEnv {
 
         self.persist_config(base_path)
     }
+
+    fn auth_keys_needed(&self) -> bool {
+        self.pageserver.pg_auth_type == AuthType::NeonJWT
+            || self.pageserver.http_auth_type == AuthType::NeonJWT
+            || self.safekeepers.iter().any(|sk| sk.auth_enabled)
+    }
 }
 
 fn base_path() -> PathBuf {
@@ -498,6 +444,43 @@ fn base_path() -> PathBuf {
     }
 }
 
+/// Generate a public/private key pair for JWT authentication
+fn generate_auth_keys(private_key_path: &Path, public_key_path: &Path) -> anyhow::Result<()> {
+    // Generate the key pair
+    //
+    // openssl genpkey -algorithm ed25519 -out auth_private_key.pem
+    let keygen_output = Command::new("openssl")
+        .arg("genpkey")
+        .args(["-algorithm", "ed25519"])
+        .args(["-out", private_key_path.to_str().unwrap()])
+        .stdout(Stdio::null())
+        .output()
+        .context("failed to generate auth private key")?;
+    if !keygen_output.status.success() {
+        bail!(
+            "openssl failed: '{}'",
+            String::from_utf8_lossy(&keygen_output.stderr)
+        );
+    }
+    // Extract the public key from the private key file
+    //
+    // openssl pkey -in auth_private_key.pem -pubout -out auth_public_key.pem
+    let keygen_output = Command::new("openssl")
+        .arg("pkey")
+        .args(["-in", private_key_path.to_str().unwrap()])
+        .arg("-pubout")
+        .args(["-out", public_key_path.to_str().unwrap()])
+        .output()
+        .context("failed to extract public key from private key")?;
+    if !keygen_output.status.success() {
+        bail!(
+            "openssl failed: '{}'",
+            String::from_utf8_lossy(&keygen_output.stderr)
+        );
+    }
+    Ok(())
+}
+
 #[cfg(test)]
 mod tests {
     use super::*;
@@ -511,8 +494,8 @@ mod tests {
             "failed to parse simple config {simple_conf_toml}, reason: {simple_conf_parse_result:?}"
         );
 
-        let string_to_replace = "broker_endpoints = ['http://127.0.0.1:2379']";
+        let string_to_replace = "listen_addr = '127.0.0.1:50051'";
-        let spoiled_url_str = "broker_endpoints = ['!@$XOXO%^&']";
+        let spoiled_url_str = "listen_addr = '!@$XOXO%^&'";
         let spoiled_url_toml = simple_conf_toml.replace(string_to_replace, spoiled_url_str);
         assert!(
             spoiled_url_toml.contains(spoiled_url_str),

control_plane/src/pageserver.rs

@@ -1,33 +1,29 @@
+use std::borrow::Cow;
 use std::collections::HashMap;
 use std::fs::File;
 use std::io::{BufReader, Write};
 use std::num::NonZeroU64;
-use std::path::{Path, PathBuf};
+use std::path::PathBuf;
-use std::process::Command;
+use std::process::{Child, Command};
-use std::time::Duration;
+use std::{io, result};
-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_api::models::{
     TenantConfigRequest, TenantCreateRequest, TenantInfo, TimelineCreateRequest, TimelineInfo,
 };
-use postgres::{Config, NoTls};
+use postgres_backend::AuthType;
+use postgres_connection::{parse_host_port, PgConnectionConfig};
 use reqwest::blocking::{Client, RequestBuilder, Response};
 use reqwest::{IntoUrl, Method};
 use thiserror::Error;
+use utils::auth::{Claims, Scope};
 use utils::{
-    connstring::connection_address,
     http::error::HttpErrorBody,
     id::{TenantId, TimelineId},
     lsn::Lsn,
-    postgres_backend::AuthType,
 };
 
-use crate::local_env::LocalEnv;
+use crate::{background_process, local_env::LocalEnv};
-use crate::{fill_aws_secrets_vars, fill_rust_env_vars, read_pidfile};
 
 #[derive(Error, Debug)]
 pub enum PageserverHttpError {
@@ -75,7 +71,7 @@ impl ResponseErrorMessageExt for Response {
 //
 #[derive(Debug)]
 pub struct PageServerNode {
-    pub pg_connection_config: Config,
+    pub pg_connection_config: PgConnectionConfig,
     pub env: LocalEnv,
     pub http_client: Client,
     pub http_base_url: String,
@@ -83,37 +79,19 @@ pub struct PageServerNode {
 
 impl PageServerNode {
     pub fn from_env(env: &LocalEnv) -> PageServerNode {
-        let password = if env.pageserver.auth_type == AuthType::NeonJWT {
+        let (host, port) = parse_host_port(&env.pageserver.listen_pg_addr)
-            &env.pageserver.auth_token
+            .expect("Unable to parse listen_pg_addr");
-        } else {
+        let port = port.unwrap_or(5432);
-            ""
-        };
-
         Self {
-            pg_connection_config: Self::pageserver_connection_config(
+            pg_connection_config: PgConnectionConfig::new_host_port(host, port),
-                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.
+    // pageserver conf overrides defined by neon_local configuration.
-    fn pageserver_connection_config(password: &str, listen_addr: &str) -> Config {
+    fn neon_local_overrides(&self) -> Vec<String> {
-        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!(
@@ -121,162 +99,166 @@ impl PageServerNode {
             self.env.pg_distrib_dir_raw().display()
         );
 
-        let authg_type_param = format!("auth_type='{}'", self.env.pageserver.auth_type);
+        let http_auth_type_param =
+            format!("http_auth_type='{}'", self.env.pageserver.http_auth_type);
         let listen_http_addr_param = format!(
             "listen_http_addr='{}'",
             self.env.pageserver.listen_http_addr
         );
+
+        let pg_auth_type_param = format!("pg_auth_type='{}'", self.env.pageserver.pg_auth_type);
         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();
+        let broker_endpoint_param = format!("broker_endpoint='{}'", self.env.broker.client_url());
-        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() {
+        let mut overrides = vec![
-            init_config_overrides.push(broker_etcd_prefix_param);
+            id,
+            pg_distrib_dir_param,
+            http_auth_type_param,
+            pg_auth_type_param,
+            listen_http_addr_param,
+            listen_pg_addr_param,
+            broker_endpoint_param,
+        ];
+
+        if self.env.pageserver.http_auth_type != AuthType::Trust
+            || self.env.pageserver.pg_auth_type != AuthType::Trust
+        {
+            overrides.push("auth_validation_public_key_path='auth_public_key.pem'".to_owned());
+        }
+        overrides
     }
 
-        if self.env.pageserver.auth_type != AuthType::Trust {
+    /// Initializes a pageserver node by creating its config with the overrides provided.
-            init_config_overrides.push("auth_validation_public_key_path='auth_public_key.pem'");
+    pub fn initialize(&self, config_overrides: &[&str]) -> anyhow::Result<()> {
-        }
+        // First, run `pageserver --init` and wait for it to write a config into FS and exit.
-
+        self.pageserver_init(config_overrides).with_context(|| {
-        self.start_node(&init_config_overrides, &self.env.base_data_dir, true)?;
+            format!(
-        let init_result = self
+                "Failed to run init for pageserver node {}",
-            .try_init_timeline(create_tenant, initial_timeline_id, pg_version)
+                self.env.pageserver.id,
-            .context("Failed to create initial tenant and timeline for pageserver");
+            )
-        match &init_result {
+        })
-            Ok(initial_timeline_id) => {
-                println!("Successfully initialized timeline {initial_timeline_id}")
-            }
-            Err(e) => eprintln!("{e:#}"),
-        }
-        self.stop(false)?;
-        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()
     }
 
-    pub fn pid_file(&self) -> PathBuf {
+    /// 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<()> {
+    pub fn start(&self, config_overrides: &[&str]) -> anyhow::Result<Child> {
-        self.start_node(config_overrides, &self.repo_path(), false)
+        self.start_node(config_overrides, false)
     }
 
-    fn start_node(
+    fn pageserver_init(&self, config_overrides: &[&str]) -> anyhow::Result<()> {
-        &self,
+        let datadir = self.repo_path();
-        config_overrides: &[&str],
+        let node_id = self.env.pageserver.id;
-        datadir: &Path,
-        update_config: bool,
-    ) -> anyhow::Result<()> {
         println!(
-            "Starting pageserver at '{}' in '{}'",
+            "Initializing pageserver node {} at '{}' in {:?}",
-            connection_address(&self.pg_connection_config),
+            node_id,
-            datadir.display()
+            self.pg_connection_config.raw_address(),
+            datadir
         );
         io::stdout().flush()?;
 
-        let mut args = vec![
+        let datadir_path_str = datadir.to_str().with_context(|| {
-            "-D",
+            format!("Cannot start pageserver node {node_id} in path that has no string representation: {datadir:?}")
-            datadir.to_str().with_context(|| {
+        })?;
-                format!(
+        let mut args = self.pageserver_basic_args(config_overrides, datadir_path_str);
-                    "Datadir path '{}' cannot be represented as a unicode string",
+        args.push(Cow::Borrowed("--init"));
-                    datadir.display()
-                )
-            })?,
-        ];
 
-        if update_config {
+        let init_output = Command::new(self.env.pageserver_bin())
-            args.push("--update-config");
+            .args(args.iter().map(Cow::as_ref))
-        }
+            .envs(self.pageserver_env_variables()?)
+            .output()
+            .with_context(|| format!("Failed to run pageserver init for node {node_id}"))?;
 
-        for config_override in config_overrides {
+        anyhow::ensure!(
-            args.extend(["-c", config_override]);
+            init_output.status.success(),
-        }
+            "Pageserver init for node {} did not finish successfully, stdout: {}, stderr: {}",
-
+            node_id,
-        let mut cmd = Command::new(self.env.pageserver_bin()?);
+            String::from_utf8_lossy(&init_output.stdout),
-        let mut filled_cmd = fill_rust_env_vars(cmd.args(&args).arg("--daemonize"));
+            String::from_utf8_lossy(&init_output.stderr),
-        filled_cmd = fill_aws_secrets_vars(filled_cmd);
-
-        if !filled_cmd.status()?.success() {
-            bail!(
-                "Pageserver failed to start. See console output and '{}' for details.",
-                datadir.join("pageserver.log").display()
         );
+
+        Ok(())
     }
 
-        // It takes a while for the page server to start up. Wait until it is
+    fn start_node(&self, config_overrides: &[&str], update_config: bool) -> anyhow::Result<Child> {
-        // open for business.
+        let mut overrides = self.neon_local_overrides();
-        const RETRIES: i8 = 15;
+        overrides.extend(config_overrides.iter().map(|&c| c.to_owned()));
-        for retries in 1..RETRIES {
+
-            match self.check_status() {
+        let datadir = self.repo_path();
-                Ok(()) => {
+        print!(
-                    println!("\nPageserver started");
+            "Starting pageserver node {} at '{}' in {:?}",
-                    return Ok(());
+            self.env.pageserver.id,
+            self.pg_connection_config.raw_address(),
+            datadir
+        );
+        io::stdout().flush()?;
+
+        let datadir_path_str = datadir.to_str().with_context(|| {
+            format!(
+                "Cannot start pageserver node {} in path that has no string representation: {:?}",
+                self.env.pageserver.id, datadir,
+            )
+        })?;
+        let mut args = self.pageserver_basic_args(config_overrides, datadir_path_str);
+        if update_config {
+            args.push(Cow::Borrowed("--update-config"));
         }
-                Err(err) => {
+
-                    match err {
+        background_process::start_process(
-                        PageserverHttpError::Transport(err) => {
+            "pageserver",
-                            if err.is_connect() && retries < 5 {
+            &datadir,
-                                print!(".");
+            &self.env.pageserver_bin(),
-                                io::stdout().flush().unwrap();
+            args.iter().map(Cow::as_ref),
+            self.pageserver_env_variables()?,
+            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}")),
+            },
+        )
+    }
+
+    fn pageserver_basic_args<'a>(
+        &self,
+        config_overrides: &'a [&'a str],
+        datadir_path_str: &'a str,
+    ) -> Vec<Cow<'a, str>> {
+        let mut args = vec![Cow::Borrowed("-D"), Cow::Borrowed(datadir_path_str)];
+
+        let mut overrides = self.neon_local_overrides();
+        overrides.extend(config_overrides.iter().map(|&c| c.to_owned()));
+        for config_override in overrides {
+            args.push(Cow::Borrowed("-c"));
+            args.push(Cow::Owned(config_override));
+        }
+
+        args
+    }
+
+    fn pageserver_env_variables(&self) -> anyhow::Result<Vec<(String, String)>> {
+        // FIXME: why is this tied to pageserver's auth type? Whether or not the safekeeper
+        // needs a token, and how to generate that token, seems independent to whether
+        // the pageserver requires a token in incoming requests.
+        Ok(if self.env.pageserver.http_auth_type != AuthType::Trust {
+            // Generate a token to connect from the pageserver to a safekeeper
+            let token = self
+                .env
+                .generate_auth_token(&Claims::new(None, Scope::SafekeeperData))?;
+            vec![("NEON_AUTH_TOKEN".to_owned(), token)]
         } else {
-                                if retries == 5 {
+            Vec::new()
-                                    println!() // put a line break after dots for second message
+        })
-                                }
-                                println!("Pageserver not responding yet, err {err} retrying ({retries})...");
-                            }
-                        }
-                        PageserverHttpError::Response(msg) => {
-                            bail!("pageserver failed to start: {msg} ")
-                        }
-                    }
-                    thread::sleep(Duration::from_secs(1));
-                }
-            }
-        }
-        bail!("pageserver failed to start in {RETRIES} seconds");
     }
 
     ///
@@ -288,81 +270,33 @@ impl PageServerNode {
     /// If the server is not running, returns success
     ///
     pub fn stop(&self, immediate: bool) -> anyhow::Result<()> {
-        let pid_file = self.pid_file();
+        background_process::stop_process(immediate, "pageserver", &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 {pid} does not exist, but a PID file was found");
-                return Ok(());
-            }
-            Err(err) => bail!(
-                "Failed to send signal to pageserver with pid {pid}: {}",
-                err.desc()
-            ),
     }
 
-        // Wait until process is gone
+    pub fn page_server_psql_client(&self) -> anyhow::Result<postgres::Client> {
-        for i in 0..600 {
+        let mut config = self.pg_connection_config.clone();
-            let signal = None; // Send no signal, just get the error code
+        if self.env.pageserver.pg_auth_type == AuthType::NeonJWT {
-            match kill(pid, signal) {
+            let token = self
-                Ok(_) => (), // Process exists, keep waiting
+                .env
-                Err(Errno::ESRCH) => {
+                .generate_auth_token(&Claims::new(None, Scope::PageServerApi))?;
-                    // Process not found, we're done
+            config = config.set_password(Some(token));
-                    println!("done!");
-                    return Ok(());
         }
-                Err(err) => bail!(
+        Ok(config.connect_no_tls()?)
-                    "Failed to send signal to pageserver with pid {}: {}",
-                    pid,
-                    err.desc()
-                ),
-            };
-
-            if i % 10 == 0 {
-                print!(".");
-                io::stdout().flush().unwrap();
-            }
-            thread::sleep(Duration::from_millis(100));
     }
 
-        bail!("Failed to stop pageserver with pid {pid}");
+    fn http_request<U: IntoUrl>(&self, method: Method, url: U) -> anyhow::Result<RequestBuilder> {
-    }
-
-    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::NeonJWT {
+        if self.env.pageserver.http_auth_type == AuthType::NeonJWT {
-            builder = builder.bearer_auth(&self.env.pageserver.auth_token)
+            let token = self
+                .env
+                .generate_auth_token(&Claims::new(None, Scope::PageServerApi))?;
+            builder = builder.bearer_auth(token)
         }
-        builder
+        Ok(builder)
     }
 
     pub fn check_status(&self) -> Result<()> {
-        self.http_request(Method::GET, format!("{}/status", self.http_base_url))
+        self.http_request(Method::GET, format!("{}/status", self.http_base_url))?
             .send()?
             .error_from_body()?;
         Ok(())
@@ -370,7 +304,7 @@ impl PageServerNode {
 
     pub fn tenant_list(&self) -> Result<Vec<TenantInfo>> {
         Ok(self
-            .http_request(Method::GET, format!("{}/tenant", self.http_base_url))
+            .http_request(Method::GET, format!("{}/tenant", self.http_base_url))?
             .send()?
             .error_from_body()?
             .json()?)
@@ -419,11 +353,29 @@ impl PageServerNode {
                 .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")?,
+            eviction_policy: settings
+                .get("eviction_policy")
+                .map(|x| serde_json::from_str(x))
+                .transpose()
+                .context("Failed to parse 'eviction_policy' json")?,
+            min_resident_size_override: settings
+                .remove("min_resident_size_override")
+                .map(|x| x.parse::<u64>())
+                .transpose()
+                .context("Failed to parse 'min_resident_size_override' as integer")?,
+            evictions_low_residence_duration_metric_threshold: settings
+                .remove("evictions_low_residence_duration_metric_threshold")
+                .map(|x| x.to_string()),
         };
         if !settings.is_empty() {
             bail!("Unrecognized tenant settings: {settings:?}")
         }
-        self.http_request(Method::POST, format!("{}/tenant", self.http_base_url))
+        self.http_request(Method::POST, format!("{}/tenant", self.http_base_url))?
             .json(&request)
             .send()?
             .error_from_body()?
@@ -440,7 +392,7 @@ impl PageServerNode {
     }
 
     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))
+        self.http_request(Method::PUT, format!("{}/tenant/config", self.http_base_url))?
             .json(&TenantConfigRequest {
                 tenant_id,
                 checkpoint_distance: settings
@@ -481,6 +433,24 @@ impl PageServerNode {
                     .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")?,
+                eviction_policy: settings
+                    .get("eviction_policy")
+                    .map(|x| serde_json::from_str(x))
+                    .transpose()
+                    .context("Failed to parse 'eviction_policy' json")?,
+                min_resident_size_override: settings
+                    .get("min_resident_size_override")
+                    .map(|x| x.parse::<u64>())
+                    .transpose()
+                    .context("Failed to parse 'min_resident_size_override' as an integer")?,
+                evictions_low_residence_duration_metric_threshold: settings
+                    .get("evictions_low_residence_duration_metric_threshold")
+                    .map(|x| x.to_string()),
             })
             .send()?
             .error_from_body()?;
@@ -493,7 +463,7 @@ impl PageServerNode {
             .http_request(
                 Method::GET,
                 format!("{}/tenant/{}/timeline", self.http_base_url, tenant_id),
-            )
+            )?
             .send()?
             .error_from_body()?
             .json()?;
@@ -512,7 +482,7 @@ impl PageServerNode {
         self.http_request(
             Method::POST,
             format!("{}/tenant/{}/timeline", self.http_base_url, tenant_id),
-        )
+        )?
         .json(&TimelineCreateRequest {
             new_timeline_id,
             ancestor_start_lsn,
@@ -549,7 +519,7 @@ impl PageServerNode {
         pg_wal: Option<(Lsn, PathBuf)>,
         pg_version: u32,
     ) -> anyhow::Result<()> {
-        let mut client = self.pg_connection_config.connect(NoTls).unwrap();
+        let mut client = self.page_server_psql_client()?;
 
         // Init base reader
         let (start_lsn, base_tarfile_path) = base;