Clone less

This patch adds basic access statistics for historic layers
and exposes them in the management API's `LayerMapInfo`.

We record the accesses in the `{Delta,Image}Layer::load()` function
because it's the common path of
* page_service (`Timline::get_reconstruct_data()`)
* Compaction (`PersistentLayer::iter()` and `PersistentLayer::key_iter()`)

The stats survive residence status changes, and record these as well.

When scraping the layer map endpoint to record its evolution over time,
one must account for stat resets because they are in-memory only and
will reset on pageserver restart.
Use the launch timestamp header added by (#3527) to identify pageserver restarts.

This is PR https://github.com/neondatabase/neon/pull/3496

.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 = "3"
 
 # Setting workspace.resolver = "2" in the root Cargo.toml is HIGHLY recommended.
 # Hakari works much better with the new feature resolver.

.dockerignore

@@ -14,6 +14,8 @@
 !pgxn/
 !proxy/
 !safekeeper/
+!storage_broker/
+!trace/
 !vendor/postgres-v14/
 !vendor/postgres-v15/
 !workspace_hack/

.github/PULL_REQUEST_TEMPLATE/release-pr.md

@@ -10,11 +10,11 @@
 <!-- List everything that should be done **before** release, any issues / setting changes / etc -->
 
 ### Checklist after release
-- [ ] Based on the merged commits write release notes and open a PR into `website` repo ([example](https://github.com/neondatabase/website/pull/120/files))
+- [ ] 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

@@ -32,8 +32,8 @@ runs:
           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
@@ -41,13 +41,21 @@ 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 "${GITHUB_REF_NAME}" | tr -c "[:alnum:]._-" "-")
         fi
-        echo "::set-output name=KEY::${key}"
+        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' }}
@@ -74,10 +82,11 @@ runs:
     - 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
         BUCKET: neon-github-public-dev
+        TEST_SELECTION: ${{ steps.calculate-vars.outputs.TEST_SELECTION }}
       shell: bash -euxo pipefail {0}
       run: |
         # Add metadata
@@ -98,7 +107,7 @@ runs:
           BUILD_TYPE=${{ inputs.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 +118,9 @@ 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 +133,12 @@ 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
@@ -137,8 +147,8 @@ 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 }}/${{ inputs.build_type }}
         TEST_OUTPUT: /tmp/test_output
         BUCKET: neon-github-public-dev
       shell: bash -euxo pipefail {0}
@@ -186,18 +196,19 @@ runs:
         aws s3 cp --only-show-errors ./index.html "s3://${BUCKET}/${REPORT_PREFIX}/latest/index.html"
 
         echo "[Allure Report](${REPORT_URL})" >> ${GITHUB_STEP_SUMMARY}
-        echo "::set-output name=report-url::${REPORT_URL}"
+        echo "report-url=${REPORT_URL}" >> $GITHUB_OUTPUT
 
     - name: Release Allure lock
       if: ${{ inputs.action == 'generate' && always() }}
       shell: bash -euxo pipefail {0}
       env:
-        LOCK_FILE: reports/${{ steps.calculate-key.outputs.KEY }}/lock.txt
+        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
 

.github/actions/download/action.yml

@@ -34,7 +34,7 @@ runs:
         S3_KEY=$(aws s3api list-objects-v2 --bucket ${BUCKET} --prefix ${PREFIX%$GITHUB_RUN_ATTEMPT} | jq -r '.Contents[].Key' | grep ${FILENAME} | sort --version-sort | tail -1 || true)
         if [ -z "${S3_KEY}" ]; then
           if [ "${SKIP_IF_DOES_NOT_EXIST}" = "true" ]; then
-            echo '::set-output name=SKIPPED::true'
+            echo 'SKIPPED=true' >> $GITHUB_OUTPUT
             exit 0
           else
             echo 2>&1 "Neither s3://${BUCKET}/${PREFIX}/${FILENAME} nor its version from previous attempts exist"
@@ -42,7 +42,7 @@ runs:
           fi
         fi
 
-        echo '::set-output name=SKIPPED::false'
+        echo 'SKIPPED=false' >> $GITHUB_OUTPUT
 
         mkdir -p $(dirname $ARCHIVE)
         time aws s3 cp --only-show-errors s3://${BUCKET}/${S3_KEY} ${ARCHIVE}

.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>&1 "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>&1 "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>&1 "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 +5,16 @@ 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
+
 outputs:
   dsn:
     description: 'Created Project DSN (for main database)'
@@ -22,38 +26,13 @@ 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 "::set-output name=api_host::${API_HOST}"
-        echo "::set-output name=region_id::${REGION_ID}"
-      env:
-        ENVIRONMENT: ${{ inputs.environment }}
-        REGION_ID: ${{ inputs.region_id }}
-
     - name: Create Neon Project
       id: create-neon-project
       # A shell without `set -x` to not to expose password/dsn in logs
       shell: bash -euo pipefail {0}
       run: |
         project=$(curl \
-          "https://${API_HOST}/api/v1/projects" \
+          "https://${API_HOST}/api/v2/projects" \
           --fail \
           --header "Accept: application/json" \
           --header "Content-Type: application/json" \
@@ -61,7 +40,7 @@ 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}\",
               \"settings\": { }
             }
@@ -70,13 +49,16 @@ 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 "::set-output name=dsn::${dsn}"
+        echo "dsn=${dsn}" >> $GITHUB_OUTPUT
 
-        project_id=$(echo $project | jq --raw-output '.id')
+        project_id=$(echo $project | jq --raw-output '.project.id')
-        echo "::set-output name=project_id::${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 }}

.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 "::set-output name=api_host::${API_HOST}"
-      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" \
+          --fail \
-            "https://${API_HOST}/api/v1/projects/${PROJECT_ID}/delete" \
+          --request DELETE \
-            --fail \
+          --header "Accept: application/json" \
-            --header "Accept: application/json" \
+          --header "Content-Type: application/json" \
-            --header "Content-Type: application/json" \
+          --header "Authorization: Bearer ${API_KEY}"
-            --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

@@ -55,6 +55,22 @@ 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 +92,15 @@ 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: ${{ inputs.real_s3_secret_access_key }}
+        COMPATIBILITY_SNAPSHOT_DIR: /tmp/compatibility_snapshot_pg14
+        ALLOW_BACKWARD_COMPATIBILITY_BREAKAGE: contains(github.event.pull_request.labels.*.name, 'backward compatibility breakage')
+        ALLOW_FORWARD_COMPATIBILITY_BREAKAGE: contains(github.event.pull_request.labels.*.name, 'forward compatibility breakage')
       shell: bash -euxo pipefail {0}
       run: |
         # PLATFORM will be embedded in the perf test report
@@ -102,7 +123,12 @@ runs:
           exit 1
         fi
         if [[ "${{ 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
@@ -137,9 +163,9 @@ 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 +180,17 @@ 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: success() || failure()
       uses: ./.github/actions/allure-report
       with:
         action: store

.github/ansible/.gitignore

@@ -1,4 +1,5 @@
-zenith_install.tar.gz
-.zenith_current_version
 neon_install.tar.gz
 .neon_current_version
+
+collections/*
+!collections/.keep

.github/ansible/deploy.yaml

@@ -1,7 +1,7 @@
 - name: Upload Neon binaries
   hosts: storage
   gather_facts: False
-  remote_user: admin
+  remote_user: "{{ remote_user }}"
 
   tasks:
 
@@ -14,7 +14,8 @@
       - safekeeper
 
     - name: inform about versions
-      debug: msg="Version to deploy - {{ current_version }}"
+      debug:
+        msg: "Version to deploy - {{ current_version }}"
       tags:
       - pageserver
       - safekeeper
@@ -35,7 +36,7 @@
 - name: Deploy pageserver
   hosts: pageservers
   gather_facts: False
-  remote_user: admin
+  remote_user: "{{ remote_user }}"
 
   tasks:
 
@@ -63,15 +64,29 @@
       tags:
       - pageserver
 
-    - name: update remote storage (s3) config
+    - name: read the existing remote pageserver config
-      lineinfile:
+      ansible.builtin.slurp:
-        path: /storage/pageserver/data/pageserver.toml
+        src: /storage/pageserver/data/pageserver.toml
-        line: "{{ item }}"
+      register: _remote_ps_config
-      loop:
+      tags:
-        - "[remote_storage]"
+      - pageserver
-        - "bucket_name = '{{ bucket_name }}'"
+
-        - "bucket_region = '{{ bucket_region }}'"
+    - name: parse the existing pageserver configuration
-        - "prefix_in_bucket = '{{ inventory_hostname }}'"
+      ansible.builtin.set_fact:
+        _existing_ps_config: "{{ _remote_ps_config['content'] | b64decode | sivel.toiletwater.from_toml }}"
+      tags:
+      - pageserver
+
+    - name: construct the final pageserver configuration dict
+      ansible.builtin.set_fact:
+        pageserver_config: "{{ pageserver_config_stub | combine({'id': _existing_ps_config.id }) }}"
+      tags:
+      - pageserver
+
+    - name: template the pageserver config
+      template:
+        src: templates/pageserver.toml.j2
+        dest: /storage/pageserver/data/pageserver.toml
       become: true
       tags:
       - pageserver
@@ -102,14 +117,15 @@
       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 }}" -X POST -d@/tmp/new_version {{ console_mgmt_base_url }}/management/api/v2/pageservers
       tags:
       - pageserver
 
 - name: Deploy safekeeper
   hosts: safekeepers
   gather_facts: False
-  remote_user: admin
+  remote_user: "{{ remote_user }}"
 
   tasks:
 
@@ -171,6 +187,7 @@
       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 }}" -X POST -d@/tmp/new_version {{ console_mgmt_base_url }}/management/api/v2/safekeepers
       tags:
       - safekeeper

.github/ansible/get_binaries.sh

@@ -23,7 +23,9 @@ docker cp ${ID}:/data/postgres_install.tar.gz .
 tar -xzf postgres_install.tar.gz -C neon_install
 mkdir neon_install/bin/
 docker cp ${ID}:/usr/local/bin/pageserver neon_install/bin/
+docker cp ${ID}:/usr/local/bin/pageserver_binutils neon_install/bin/
 docker cp ${ID}:/usr/local/bin/safekeeper neon_install/bin/
+docker cp ${ID}:/usr/local/bin/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

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

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

@@ -0,0 +1,38 @@
+storage:
+  vars:
+    bucket_name: neon-prod-storage-ap-southeast-1
+    bucket_region: ap-southeast-1
+    console_mgmt_base_url: http://console-release.local
+    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://console-release.local/billing/api/v1/usage_events
+      metric_collection_interval: 10min
+      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-1.ap-southeast-1.aws.neon.tech:
+          ansible_host:  i-0e338adda8eb2d19f
+        safekeeper-2.ap-southeast-1.aws.neon.tech:
+          ansible_host:  i-04fb63634e4679eb9

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

@@ -0,0 +1,38 @@
+storage:
+  vars:
+    bucket_name: neon-prod-storage-eu-central-1
+    bucket_region: eu-central-1
+    console_mgmt_base_url: http://console-release.local
+    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://console-release.local/billing/api/v1/usage_events
+      metric_collection_interval: 10min
+      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
+
+    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 +1,39 @@
+storage:
+  vars:
+    bucket_name: neon-prod-storage-us-east-2
+    bucket_region: us-east-2
+    console_mgmt_base_url: http://console-release.local
+    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://console-release.local/billing/api/v1/usage_events
+      metric_collection_interval: 10min
+      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
+
+    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 +1,41 @@
+storage:
+  vars:
+    bucket_name: neon-prod-storage-us-west-2
+    bucket_region: us-west-2
+    console_mgmt_base_url: http://console-release.local
+    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://console-release.local/billing/api/v1/usage_events
+      metric_collection_interval: 10min
+      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
+
+    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

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

.github/ansible/production.hosts.yaml

@@ -0,0 +1,40 @@
+---
+storage:
+  vars:
+    console_mgmt_base_url: http://console-release.local
+    bucket_name: zenith-storage-oregon
+    bucket_region: us-west-2
+    broker_endpoint: http://storage-broker.prod.local:50051
+    pageserver_config_stub:
+      pg_distrib_dir: /usr/local
+      metric_collection_endpoint: http://console-release.local/billing/api/v1/usage_events
+      metric_collection_interval: 10min
+      remote_storage:
+        bucket_name: "{{ bucket_name }}"
+        bucket_region: "{{ bucket_region }}"
+        prefix_in_bucket: "{{ inventory_hostname }}"
+    safekeeper_s3_prefix: prod-1/wal
+    hostname_suffix: ".local"
+    remote_user: admin
+    sentry_environment: production
+
+  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
+        zenith-1-ps-4:
+          console_region_id: aws-us-west-2
+        zenith-1-ps-5:
+          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-4:
+          console_region_id: aws-us-west-2

.github/ansible/scripts/init_pageserver.sh

@@ -1,7 +1,8 @@
 #!/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)
 
 # store fqdn hostname in var
 HOST=$(hostname -f)
@@ -12,18 +13,20 @@ cat <<EOF | tee /tmp/payload
   "version": 1,
   "host": "${HOST}",
   "port": 6400,
-  "region_id": {{ console_region_id }},
+  "region_id": "{{ console_region_id }}",
   "instance_id": "${INSTANCE_ID}",
   "http_host": "${HOST}",
-  "http_port": 9898
+  "http_port": 9898,
+  "active": false,
+  "availability_zone_id": "${AZ_ID}"
 }
 EOF
 
 # check if pageserver already registered or not
-if ! curl -sf -X PATCH -d '{}' {{ console_mgmt_base_url }}/api/v1/pageservers/${INSTANCE_ID} -o /dev/null; then
+if ! curl -sf -H "Authorization: Bearer {{ CONSOLE_API_TOKEN }}" {{ console_mgmt_base_url }}/management/api/v2/pageservers/${INSTANCE_ID} -o /dev/null; then
 
     # not registered, so register it now
-    ID=$(curl -sf -X POST {{ console_mgmt_base_url }}/api/v1/pageservers -d@/tmp/payload | jq -r '.ID')
+    ID=$(curl -sf -X POST -H "Authorization: Bearer {{ CONSOLE_API_TOKEN }}" {{ console_mgmt_base_url }}/management/api/v2/pageservers -d@/tmp/payload | jq -r '.id')
 
     # 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

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

.github/ansible/ssm_config

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

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

@@ -0,0 +1,36 @@
+storage:
+  vars:
+    bucket_name: neon-dev-storage-eu-west-1
+    bucket_region: eu-west-1
+    console_mgmt_base_url: http://console-staging.local
+    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://console-staging.local/billing/api/v1/usage_events
+      metric_collection_interval: 10min
+      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

@@ -1,25 +0,0 @@
-[pageservers]
-#zenith-us-stage-ps-1 console_region_id=27
-zenith-us-stage-ps-2 console_region_id=27
-zenith-us-stage-ps-3 console_region_id=27
-zenith-us-stage-ps-4 console_region_id=27
-zenith-us-stage-test-ps-1 console_region_id=28
-
-[safekeepers]
-zenith-us-stage-sk-4 console_region_id=27
-zenith-us-stage-sk-5 console_region_id=27
-zenith-us-stage-sk-6 console_region_id=27
-zenith-us-stage-test-sk-1 console_region_id=28
-zenith-us-stage-test-sk-2 console_region_id=28
-zenith-us-stage-test-sk-3 console_region_id=28
-
-[storage:children]
-pageservers
-safekeepers
-
-[storage:vars]
-env_name = us-stage
-console_mgmt_base_url = http://console-staging.local
-bucket_name           = zenith-staging-storage-us-east-1
-bucket_region         = us-east-1
-etcd_endpoints        = zenith-us-stage-etcd.local:2379

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

@@ -0,0 +1,42 @@
+storage:
+  vars:
+    bucket_name: neon-staging-storage-us-east-2
+    bucket_region: us-east-2
+    console_mgmt_base_url: http://console-staging.local
+    broker_endpoint: http://storage-broker-lb.beta.us-east-2.internal.aws.neon.build:50051
+    pageserver_config_stub:
+      pg_distrib_dir: /usr/local
+      metric_collection_endpoint: http://console-staging.local/billing/api/v1/usage_events
+      metric_collection_interval: 10min
+      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
+
+    safekeepers:
+      hosts:
+        safekeeper-0.us-east-2.aws.neon.build:
+          ansible_host: i-027662bd552bf5db0
+        safekeeper-1.us-east-2.aws.neon.build:
+          ansible_host: i-0171efc3604a7b907
+        safekeeper-2.us-east-2.aws.neon.build:
+          ansible_host: i-0de0b03a51676a6ce

.github/ansible/systemd/pageserver.service

@@ -1,12 +1,12 @@
 [Unit]
-Description=Zenith pageserver
+Description=Neon pageserver
 After=network.target auditd.service
 
 [Service]
 Type=simple
 User=pageserver
-Environment=RUST_BACKTRACE=1 NEON_REPO_DIR=/storage/pageserver LD_LIBRARY_PATH=/usr/local/v14/lib
+Environment=RUST_BACKTRACE=1 NEON_REPO_DIR=/storage/pageserver LD_LIBRARY_PATH=/usr/local/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 }}'" -D /storage/pageserver/data
 ExecReload=/bin/kill -HUP $MAINPID
 KillMode=mixed
 KillSignal=SIGINT

.github/ansible/systemd/safekeeper.service

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

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

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

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

@@ -0,0 +1,61 @@
+# Helm chart values for neon-proxy-scram.
+# This is a YAML-formatted file.
+
+image:
+  repository: neondatabase/neon
+
+settings:
+  authBackend: "console"
+  authEndpoint: "http://console-staging.local/management/api/v2"
+  domain: "*.eu-west-1.aws.neon.build"
+  sentryEnvironment: "staging"
+  wssPort: 8443
+  metricCollectionEndpoint: "http://console-staging.local/billing/api/v1/usage_events"
+  metricCollectionInterval: "1min"
+
+# -- Additional labels for neon-proxy pods
+podLabels:
+  zenith_service: proxy-scram
+  zenith_env: dev
+  zenith_region: eu-west-1
+  zenith_region_slug: 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 +1,68 @@
+# 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://console-staging.local/billing/api/v1/usage_events"
+  metricCollectionInterval: "1min"
+
+# -- Additional labels for neon-proxy-link pods
+podLabels:
+  zenith_service: proxy
+  zenith_env: dev
+  zenith_region: us-east-2
+  zenith_region_slug: 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 +1,61 @@
+# Helm chart values for neon-proxy-scram.
+# This is a YAML-formatted file.
+
+image:
+  repository: neondatabase/neon
+
+settings:
+  authBackend: "console"
+  authEndpoint: "http://console-staging.local/management/api/v2"
+  domain: "*.cloud.stage.neon.tech"
+  sentryEnvironment: "staging"
+  wssPort: 8443
+  metricCollectionEndpoint: "http://console-staging.local/billing/api/v1/usage_events"
+  metricCollectionInterval: "1min"
+
+# -- Additional labels for neon-proxy pods
+podLabels:
+  zenith_service: proxy-scram-legacy
+  zenith_env: dev
+  zenith_region: us-east-2
+  zenith_region_slug: us-east-2
+
+exposedService:
+  annotations:
+    service.beta.kubernetes.io/aws-load-balancer-type: external
+    service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
+    service.beta.kubernetes.io/aws-load-balancer-scheme: internet-facing
+    external-dns.alpha.kubernetes.io/hostname: 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 +1,61 @@
+# Helm chart values for neon-proxy-scram.
+# This is a YAML-formatted file.
+
+image:
+  repository: neondatabase/neon
+
+settings:
+  authBackend: "console"
+  authEndpoint: "http://console-staging.local/management/api/v2"
+  domain: "*.us-east-2.aws.neon.build"
+  sentryEnvironment: "staging"
+  wssPort: 8443
+  metricCollectionEndpoint: "http://console-staging.local/billing/api/v1/usage_events"
+  metricCollectionInterval: "1min"
+
+# -- Additional labels for neon-proxy pods
+podLabels:
+  zenith_service: proxy-scram
+  zenith_env: dev
+  zenith_region: us-east-2
+  zenith_region_slug: us-east-2
+
+exposedService:
+  annotations:
+    service.beta.kubernetes.io/aws-load-balancer-type: external
+    service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
+    service.beta.kubernetes.io/aws-load-balancer-scheme: internet-facing
+    external-dns.alpha.kubernetes.io/hostname: us-east-2.aws.neon.build
+  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 +1,61 @@
+# Helm chart values for neon-proxy-scram.
+# This is a YAML-formatted file.
+
+image:
+  repository: neondatabase/neon
+
+settings:
+  authBackend: "console"
+  authEndpoint: "http://console-release.local/management/api/v2"
+  domain: "*.ap-southeast-1.aws.neon.tech"
+  sentryEnvironment: "production"
+  wssPort: 8443
+  metricCollectionEndpoint: "http://console-release.local/billing/api/v1/usage_events"
+  metricCollectionInterval: "10min"
+
+# -- Additional labels for neon-proxy pods
+podLabels:
+  zenith_service: proxy-scram
+  zenith_env: prod
+  zenith_region: ap-southeast-1
+  zenith_region_slug: ap-southeast-1
+
+exposedService:
+  annotations:
+    service.beta.kubernetes.io/aws-load-balancer-type: external
+    service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
+    service.beta.kubernetes.io/aws-load-balancer-scheme: internet-facing
+    external-dns.alpha.kubernetes.io/hostname: ap-southeast-1.aws.neon.tech
+  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 +1,61 @@
+# Helm chart values for neon-proxy-scram.
+# This is a YAML-formatted file.
+
+image:
+  repository: neondatabase/neon
+
+settings:
+  authBackend: "console"
+  authEndpoint: "http://console-release.local/management/api/v2"
+  domain: "*.eu-central-1.aws.neon.tech"
+  sentryEnvironment: "production"
+  wssPort: 8443
+  metricCollectionEndpoint: "http://console-release.local/billing/api/v1/usage_events"
+  metricCollectionInterval: "10min"
+
+# -- Additional labels for neon-proxy pods
+podLabels:
+  zenith_service: proxy-scram
+  zenith_env: prod
+  zenith_region: eu-central-1
+  zenith_region_slug: eu-central-1
+
+exposedService:
+  annotations:
+    service.beta.kubernetes.io/aws-load-balancer-type: external
+    service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
+    service.beta.kubernetes.io/aws-load-balancer-scheme: internet-facing
+    external-dns.alpha.kubernetes.io/hostname: eu-central-1.aws.neon.tech
+  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 +1,59 @@
+# 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:
+  zenith_service: proxy
+  zenith_env: production
+  zenith_region: us-east-2
+  zenith_region_slug: 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 +1,61 @@
+# Helm chart values for neon-proxy-scram.
+# This is a YAML-formatted file.
+
+image:
+  repository: neondatabase/neon
+
+settings:
+  authBackend: "console"
+  authEndpoint: "http://console-release.local/management/api/v2"
+  domain: "*.us-east-2.aws.neon.tech"
+  sentryEnvironment: "production"
+  wssPort: 8443
+  metricCollectionEndpoint: "http://console-release.local/billing/api/v1/usage_events"
+  metricCollectionInterval: "10min"
+
+# -- Additional labels for neon-proxy pods
+podLabels:
+  zenith_service: proxy-scram
+  zenith_env: prod
+  zenith_region: us-east-2
+  zenith_region_slug: us-east-2
+
+exposedService:
+  annotations:
+    service.beta.kubernetes.io/aws-load-balancer-type: external
+    service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
+    service.beta.kubernetes.io/aws-load-balancer-scheme: internet-facing
+    external-dns.alpha.kubernetes.io/hostname: us-east-2.aws.neon.tech
+  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 +1,61 @@
+# Helm chart values for neon-proxy-scram.
+# This is a YAML-formatted file.
+
+image:
+  repository: neondatabase/neon
+
+settings:
+  authBackend: "console"
+  authEndpoint: "http://console-release.local/management/api/v2"
+  domain: "*.cloud.neon.tech"
+  sentryEnvironment: "production"
+  wssPort: 8443
+  metricCollectionEndpoint: "http://console-release.local/billing/api/v1/usage_events"
+  metricCollectionInterval: "10min"
+
+# -- Additional labels for neon-proxy pods
+podLabels:
+  zenith_service: proxy-scram
+  zenith_env: prod
+  zenith_region: us-west-2
+  zenith_region_slug: 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 +1,61 @@
+# Helm chart values for neon-proxy-scram.
+# This is a YAML-formatted file.
+
+image:
+  repository: neondatabase/neon
+
+settings:
+  authBackend: "console"
+  authEndpoint: "http://console-release.local/management/api/v2"
+  domain: "*.us-west-2.aws.neon.tech"
+  sentryEnvironment: "production"
+  wssPort: 8443
+  metricCollectionEndpoint: "http://console-release.local/billing/api/v1/usage_events"
+  metricCollectionInterval: "10min"
+
+# -- Additional labels for neon-proxy pods
+podLabels:
+  zenith_service: proxy-scram
+  zenith_env: prod
+  zenith_region: us-west-2
+  zenith_region_slug: 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.neon-storage-broker.yaml

@@ -0,0 +1,56 @@
+# 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.prod.local
+  # service.type -- Service type
+  type: LoadBalancer
+  # service.port -- broker listen port
+  port: 50051
+
+ingress:
+  enabled: false
+
+metrics:
+  enabled: true
+  serviceMonitor:
+    enabled: true
+    selector:
+      release: kube-prometheus-stack
+
+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 +1,10 @@
+## 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.
+

.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'
@@ -37,97 +35,69 @@ concurrency:
 
 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: /tmp/pg_install
+      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 == 'refs/heads/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: success() || failure()
+      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
@@ -138,26 +108,38 @@ jobs:
         SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
 
   pgbench-compare:
-    env:
-      TEST_PG_BENCH_DURATIONS_MATRIX: "60m"
-      TEST_PG_BENCH_SCALES_MATRIX: "10gb"
-      POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
-      DEFAULT_PG_VERSION: 14
-      TEST_OUTPUT: /tmp/test_output
-      BUILD_TYPE: remote
-      SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref == 'refs/heads/main' ) }}
-
     strategy:
       fail-fast: false
       matrix:
         # neon-captest-new: Run pgbench in a freshly created project
         # neon-captest-reuse: Same, but reusing existing project
         # neon-captest-prefetch: Same, with prefetching enabled (new project)
-        platform: [ neon-captest-new, neon-captest-reuse, neon-captest-prefetch, rds-aurora ]
+        # 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
+        platform: [ neon-captest-reuse, neon-captest-prefetch, rds-postgres ]
+        db_size: [ 10gb ]
+        runner: [ us-east-2 ]
+        include:
+          - platform: neon-captest-prefetch
+            db_size: 50gb
+            runner: us-east-2
+          - platform: rds-aurora
+            db_size: 50gb
+            runner: us-east-2
 
-    runs-on: dev
+    env:
+      TEST_PG_BENCH_DURATIONS_MATRIX: "60m"
+      TEST_PG_BENCH_SCALES_MATRIX: ${{ matrix.db_size }}
+      POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
+      DEFAULT_PG_VERSION: 14
+      TEST_OUTPUT: /tmp/test_output
+      BUILD_TYPE: remote
+      SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref == 'refs/heads/main' ) }}
+      PLATFORM: ${{ matrix.platform }}
+
+    runs-on: [ self-hosted, "${{ matrix.runner }}", 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
@@ -178,12 +160,13 @@ jobs:
         echo "${POSTGRES_DISTRIB_DIR}/v${DEFAULT_PG_VERSION}/bin" >> $GITHUB_PATH
 
     - name: Create Neon Project
-      if: matrix.platform != 'neon-captest-reuse'
+      if: contains(fromJson('["neon-captest-new", "neon-captest-prefetch"]'), matrix.platform)
       id: create-neon-project
       uses: ./.github/actions/neon-project-create
       with:
-        environment: ${{ github.event.inputs.environment || 'dev' }}
+        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 }}
 
     - name: Set up Connection String
       id: set-up-connstr
@@ -196,25 +179,29 @@ jobs:
             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=${PLATFORM}. Allowed only 'neon-captest-reuse', 'neon-captest-new', 'neon-captest-prefetch' or 'rds-aurora'"
+            echo 2>&1 "Unknown PLATFORM=${PLATFORM}. Allowed only 'neon-captest-reuse', 'neon-captest-new', 'neon-captest-prefetch', 'rds-aurora', or 'rds-postgres'"
             exit 1
             ;;
         esac
 
-        echo "::set-output name=connstr::${CONNSTR}"
+        echo "connstr=${CONNSTR}" >> $GITHUB_OUTPUT
 
         psql ${CONNSTR} -c "SELECT version();"
-      env:
-        PLATFORM: ${{ matrix.platform }}
 
     - name: Set database options
       if: matrix.platform == 'neon-captest-prefetch'
       run: |
-        psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE main SET enable_seqscan_prefetch=on"
+        DB_NAME=$(psql ${BENCHMARK_CONNSTR} --no-align --quiet -t -c "SELECT current_database()")
-        psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE main SET seqscan_prefetch_buffers=10"
+
+        psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET enable_seqscan_prefetch=on"
+        psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET effective_io_concurrency=32"
+        psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET maintenance_io_concurrency=32"
       env:
         BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
 
@@ -227,7 +214,6 @@ jobs:
         save_perf_report: ${{ env.SAVE_PERF_REPORT }}
         extra_params: -m remote_cluster --timeout 21600 -k test_pgbench_remote_init
       env:
-        PLATFORM: ${{ matrix.platform }}
         BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
         VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
         PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
@@ -241,7 +227,6 @@ jobs:
         save_perf_report: ${{ env.SAVE_PERF_REPORT }}
         extra_params: -m remote_cluster --timeout 21600 -k test_pgbench_remote_simple_update
       env:
-        PLATFORM: ${{ matrix.platform }}
         BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
         VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
         PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
@@ -255,26 +240,24 @@ jobs:
         save_perf_report: ${{ env.SAVE_PERF_REPORT }}
         extra_params: -m remote_cluster --timeout 21600 -k test_pgbench_remote_select_only
       env:
-        PLATFORM: ${{ matrix.platform }}
         BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
         VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
         PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
 
+    - name: Delete Neon Project
+      if: ${{ steps.create-neon-project.outputs.project_id && always() }}
+      uses: ./.github/actions/neon-project-delete
+      with:
+        project_id: ${{ steps.create-neon-project.outputs.project_id }}
+        api_key: ${{ secrets.NEON_STAGING_API_KEY }}
+
     - name: Create Allure report
-      if: always()
+      if: success() || failure()
       uses: ./.github/actions/allure-report
       with:
         action: generate
         build_type: ${{ env.BUILD_TYPE }}
 
-    - name: Delete Neon Project
-      if: ${{ matrix.platform != 'neon-captest-reuse' && always() }}
-      uses: ./.github/actions/neon-project-delete
-      with:
-        environment: dev
-        project_id: ${{ steps.create-neon-project.outputs.project_id }}
-        api_key: ${{ secrets.NEON_CAPTEST_API_KEY }}
-
     - name: Post to a Slack channel
       if: ${{ github.event.schedule && failure() }}
       uses: slackapi/slack-github-action@v1
@@ -283,3 +266,331 @@ 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: success() || failure()
+    needs: [ pgbench-compare ]
+
+    strategy:
+      fail-fast: false
+      matrix:
+        # neon-captest-prefetch: We have pre-created projects with prefetch enabled
+        # 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
+        platform: [ neon-captest-prefetch, rds-postgres, rds-aurora ]
+
+    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 == 'refs/heads/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-prefetch)
+            CONNSTR=${{ secrets.BENCHMARK_CAPTEST_CLICKBENCH_10M_CONNSTR }}
+            ;;
+          rds-aurora)
+            CONNSTR=${{ secrets.BENCHMARK_RDS_AURORA_CLICKBENCH_10M_CONNSTR }}
+            ;;
+          rds-postgres)
+            CONNSTR=${{ secrets.BENCHMARK_RDS_POSTGRES_CLICKBENCH_10M_CONNSTR }}
+            ;;
+          *)
+            echo 2>&1 "Unknown PLATFORM=${PLATFORM}. Allowed only 'neon-captest-prefetch', 'rds-aurora', or 'rds-postgres'"
+            exit 1
+            ;;
+        esac
+
+        echo "connstr=${CONNSTR}" >> $GITHUB_OUTPUT
+
+        psql ${CONNSTR} -c "SELECT version();"
+
+    - name: Set database options
+      if: matrix.platform == 'neon-captest-prefetch'
+      run: |
+        DB_NAME=$(psql ${BENCHMARK_CONNSTR} --no-align --quiet -t -c "SELECT current_database()")
+
+        psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET enable_seqscan_prefetch=on"
+        psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET effective_io_concurrency=32"
+        psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET maintenance_io_concurrency=32"
+      env:
+        BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
+
+    - 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: success() || failure()
+      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: success() || failure()
+    needs: [ clickbench-compare ]
+
+    strategy:
+      fail-fast: false
+      matrix:
+        # neon-captest-prefetch: We have pre-created projects with prefetch enabled
+        # 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
+        platform: [ neon-captest-prefetch, rds-postgres, rds-aurora ]
+
+    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 == 'refs/heads/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-prefetch)
+            CONNSTR=${{ secrets.BENCHMARK_CAPTEST_TPCH_S10_CONNSTR }}
+            ;;
+          rds-aurora)
+            CONNSTR=${{ secrets.BENCHMARK_RDS_AURORA_TPCH_S10_CONNSTR }}
+            ;;
+          rds-postgres)
+            CONNSTR=${{ secrets.BENCHMARK_RDS_POSTGRES_TPCH_S10_CONNSTR }}
+            ;;
+          *)
+            echo 2>&1 "Unknown PLATFORM=${PLATFORM}. Allowed only 'neon-captest-prefetch', 'rds-aurora', or 'rds-postgres'"
+            exit 1
+            ;;
+        esac
+
+        echo "connstr=${CONNSTR}" >> $GITHUB_OUTPUT
+
+        psql ${CONNSTR} -c "SELECT version();"
+
+    - name: Set database options
+      if: matrix.platform == 'neon-captest-prefetch'
+      run: |
+        DB_NAME=$(psql ${BENCHMARK_CONNSTR} --no-align --quiet -t -c "SELECT current_database()")
+
+        psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET enable_seqscan_prefetch=on"
+        psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET effective_io_concurrency=32"
+        psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET maintenance_io_concurrency=32"
+      env:
+        BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
+
+    - 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: success() || failure()
+      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: success() || failure()
+    needs: [ tpch-compare ]
+
+    strategy:
+      fail-fast: false
+      matrix:
+        # neon-captest-prefetch: We have pre-created projects with prefetch enabled
+        # 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
+        platform: [ neon-captest-prefetch, rds-postgres, rds-aurora ]
+
+    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 == 'refs/heads/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-prefetch)
+            CONNSTR=${{ secrets.BENCHMARK_USER_EXAMPLE_CAPTEST_CONNSTR }}
+            ;;
+          rds-aurora)
+            CONNSTR=${{ secrets.BENCHMARK_USER_EXAMPLE_RDS_AURORA_CONNSTR }}
+            ;;
+          rds-postgres)
+            CONNSTR=${{ secrets.BENCHMARK_USER_EXAMPLE_RDS_POSTGRES_CONNSTR }}
+            ;;
+          *)
+            echo 2>&1 "Unknown PLATFORM=${PLATFORM}. Allowed only 'neon-captest-prefetch', 'rds-aurora', or 'rds-postgres'"
+            exit 1
+            ;;
+        esac
+
+        echo "connstr=${CONNSTR}" >> $GITHUB_OUTPUT
+
+        psql ${CONNSTR} -c "SELECT version();"
+
+    - name: Set database options
+      if: matrix.platform == 'neon-captest-prefetch'
+      run: |
+        DB_NAME=$(psql ${BENCHMARK_CONNSTR} --no-align --quiet -t -c "SELECT current_database()")
+
+        psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET enable_seqscan_prefetch=on"
+        psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET effective_io_concurrency=32"
+        psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET maintenance_io_concurrency=32"
+      env:
+        BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
+
+    - 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: success() || failure()
+      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/build_and_test.yml

@@ -1,4 +1,4 @@
-name: Test and Deploy
+name: Build and Test
 
 on:
   push:
@@ -7,6 +7,10 @@ on:
       - release
   pull_request:
 
+defaults:
+  run:
+    shell: bash -euxo pipefail {0}
+
 concurrency:
   # Allow only one workflow per any non-`main` branch.
   group: ${{ github.workflow }}-${{ github.ref }}-${{ github.ref == 'refs/heads/main' && github.sha || 'anysha' }}
@@ -15,11 +19,13 @@ concurrency:
 env:
   RUST_BACKTRACE: 1
   COPT: '-Werror'
+  AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_DEV }}
+  AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_KEY_DEV }}
 
 jobs:
   tag:
-    runs-on: dev
+    runs-on: [ self-hosted, gen3, small ]
-    container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/base:latest
+    container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/base:pinned
     outputs:
       build-tag: ${{steps.build-tag.outputs.tag}}
 
@@ -35,18 +41,101 @@ jobs:
           echo ref:$GITHUB_REF_NAME
           echo rev:$(git rev-list --count HEAD)
           if [[ "$GITHUB_REF_NAME" == "main" ]]; then
-            echo "::set-output name=tag::$(git rev-list --count HEAD)"
+            echo "tag=$(git rev-list --count HEAD)" >> $GITHUB_OUTPUT
           elif [[ "$GITHUB_REF_NAME" == "release" ]]; then
-            echo "::set-output name=tag::release-$(git rev-list --count HEAD)"
+            echo "tag=release-$(git rev-list --count HEAD)" >> $GITHUB_OUTPUT
           else
             echo "GITHUB_REF_NAME (value '$GITHUB_REF_NAME') is not set to either 'main' or 'release'"
-            echo "::set-output name=tag::$GITHUB_RUN_ID"
+            echo "tag=$GITHUB_RUN_ID" >> $GITHUB_OUTPUT
           fi
         shell: bash
         id: build-tag
 
+  check-codestyle-python:
+    runs-on: [ self-hosted, gen3, small ]
+    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
+
+      - name: Cache poetry deps
+        id: cache_poetry
+        uses: actions/cache@v3
+        with:
+          path: ~/.cache/pypoetry/virtualenvs
+          key: v1-codestyle-python-deps-${{ hashFiles('poetry.lock') }}
+
+      - name: Install Python deps
+        run: ./scripts/pysync
+
+      - name: Run isort to ensure code format
+        run: poetry run isort --diff --check .
+
+      - name: Run black to ensure code format
+        run: poetry run black --diff --check .
+
+      - name: Run flake8 to ensure code format
+        run: poetry run flake8 .
+
+      - name: Run mypy to check types
+        run: poetry run mypy .
+
+  check-codestyle-rust:
+    runs-on: [ self-hosted, gen3, large ]
+    container:
+      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
+      options: --init
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          submodules: true
+          fetch-depth: 1
+
+#      Disabled for now
+#      - name: Restore cargo deps cache
+#        id: cache_cargo
+#        uses: actions/cache@v3
+#        with:
+#          path: |
+#            !~/.cargo/registry/src
+#            ~/.cargo/git/
+#            target/
+#          key: v1-${{ runner.os }}-cargo-clippy-${{ hashFiles('rust-toolchain.toml') }}-${{ hashFiles('Cargo.lock') }}
+
+      # Some of our rust modules use FFI and need those to be checked
+      - name: Get postgres headers
+        run: make postgres-headers -j$(nproc)
+
+      - name: Run cargo clippy
+        run: ./run_clippy.sh
+
+      # Use `${{ !cancelled() }}` to run quck tests after the longer clippy run
+      - name: Check formatting
+        if: ${{ !cancelled() }}
+        run: cargo fmt --all -- --check
+
+      # https://github.com/facebookincubator/cargo-guppy/tree/bec4e0eb29dcd1faac70b1b5360267fc02bf830e/tools/cargo-hakari#2-keep-the-workspace-hack-up-to-date-in-ci
+      - name: Check rust dependencies
+        if: ${{ !cancelled() }}
+        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
+
+      # https://github.com/EmbarkStudios/cargo-deny
+      - name: Check rust licenses/bans/advisories/sources
+        if: ${{ !cancelled() }}
+        run: cargo deny check
+
   build-neon:
-    runs-on: dev
+    runs-on: [ self-hosted, gen3, large ]
     container:
       image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
       options: --init
@@ -54,7 +143,6 @@ jobs:
       fail-fast: false
       matrix:
         build_type: [ debug, release ]
-
     env:
       BUILD_TYPE: ${{ matrix.build_type }}
       GIT_VERSION: ${{ github.sha }}
@@ -78,13 +166,11 @@ jobs:
 
       - name: Set pg 14 revision for caching
         id: pg_v14_rev
-        run: echo ::set-output name=pg_rev::$(git rev-parse HEAD:vendor/postgres-v14)
+        run: echo pg_rev=$(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 ::set-output name=pg_rev::$(git rev-parse HEAD:vendor/postgres-v15)
+        run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v15) >> $GITHUB_OUTPUT
-        shell: bash -euxo pipefail {0}
 
       # Set some environment variables used by all the steps.
       #
@@ -98,37 +184,37 @@ jobs:
       # corresponding Cargo.toml files for their descriptions.
       - name: Set env variables
         run: |
+          CARGO_FEATURES="--features testing"
           if [[ $BUILD_TYPE == "debug" ]]; then
             cov_prefix="scripts/coverage --profraw-prefix=$GITHUB_JOB --dir=/tmp/coverage run"
-            CARGO_FEATURES="--features testing"
+            CARGO_FLAGS="--locked $CARGO_FEATURES"
-            CARGO_FLAGS="--locked --timings $CARGO_FEATURES"
           elif [[ $BUILD_TYPE == "release" ]]; then
             cov_prefix=""
-            CARGO_FEATURES="--features testing,profiling"
+            CARGO_FLAGS="--locked --release $CARGO_FEATURES"
-            CARGO_FLAGS="--locked --timings --release $CARGO_FEATURES"
           fi
           echo "cov_prefix=${cov_prefix}" >> $GITHUB_ENV
           echo "CARGO_FEATURES=${CARGO_FEATURES}" >> $GITHUB_ENV
           echo "CARGO_FLAGS=${CARGO_FLAGS}" >> $GITHUB_ENV
-        shell: bash -euxo pipefail {0}
+          echo "CARGO_HOME=${GITHUB_WORKSPACE}/.cargo" >> $GITHUB_ENV
 
+      # Disabled for now
       # Don't include the ~/.cargo/registry/src directory. It contains just
       # uncompressed versions of the crates in ~/.cargo/registry/cache
       # directory, and it's faster to let 'cargo' to rebuild it from the
       # compressed crates.
-      - name: Cache cargo deps
+#      - name: Cache cargo deps
-        id: cache_cargo
+#        id: cache_cargo
-        uses: actions/cache@v3
+#        uses: actions/cache@v3
-        with:
+#        with:
-          path: |
+#          path: |
-            ~/.cargo/registry/
+#            ~/.cargo/registry/
-            !~/.cargo/registry/src
+#            !~/.cargo/registry/src
-            ~/.cargo/git/
+#            ~/.cargo/git/
-            target/
+#            target/
-          # Fall back to older versions of the key, if no cache for current Cargo.lock was found
+#          # Fall back to older versions of the key, if no cache for current Cargo.lock was found
-          key: |
+#          key: |
-            v9-${{ runner.os }}-${{ matrix.build_type }}-cargo-${{ hashFiles('Cargo.lock') }}
+#            v1-${{ runner.os }}-${{ matrix.build_type }}-cargo-${{ hashFiles('rust-toolchain.toml') }}-${{ hashFiles('Cargo.lock') }}
-            v9-${{ runner.os }}-${{ matrix.build_type }}-cargo-
+#            v1-${{ runner.os }}-${{ matrix.build_type }}-cargo-${{ hashFiles('rust-toolchain.toml') }}-
 
       - name: Cache postgres v14 build
         id: cache_pg_14
@@ -147,26 +233,21 @@ jobs:
       - name: Build postgres v14
         if: steps.cache_pg_14.outputs.cache-hit != 'true'
         run: mold -run make postgres-v14 -j$(nproc)
-        shell: bash -euxo pipefail {0}
 
       - name: Build postgres v15
         if: steps.cache_pg_15.outputs.cache-hit != 'true'
         run: mold -run make postgres-v15 -j$(nproc)
-        shell: bash -euxo pipefail {0}
 
       - name: Build neon extensions
         run: mold -run make neon-pg-ext -j$(nproc)
-        shell: bash -euxo pipefail {0}
 
       - name: Run cargo build
         run: |
           ${cov_prefix} mold -run cargo build $CARGO_FLAGS --bins --tests
-        shell: bash -euxo pipefail {0}
 
       - name: Run cargo test
         run: |
           ${cov_prefix} cargo test $CARGO_FLAGS
-        shell: bash -euxo pipefail {0}
 
       - name: Install rust binaries
         run: |
@@ -207,11 +288,9 @@ jobs:
               echo "/tmp/neon/bin/$bin" >> /tmp/coverage/binaries.list
             done
           fi
-        shell: bash -euxo pipefail {0}
 
       - name: Install postgres binaries
         run: cp -a pg_install /tmp/neon/pg_install
-        shell: bash -euxo pipefail {0}
 
       - name: Upload Neon artifact
         uses: ./.github/actions/upload
@@ -219,24 +298,13 @@ jobs:
           name: neon-${{ runner.os }}-${{ matrix.build_type }}-artifact
           path: /tmp/neon
 
-      - name: Prepare cargo build timing stats for storing
-        run: |
-          mkdir -p "/tmp/neon/cargo-timings/$BUILD_TYPE/"
-          cp -r ./target/cargo-timings/* "/tmp/neon/cargo-timings/$BUILD_TYPE/"
-        shell: bash -euxo pipefail {0}
-      - name: Upload cargo build stats
-        uses: ./.github/actions/upload
-        with:
-          name: neon-${{ runner.os }}-${{ matrix.build_type }}-build-stats
-          path: /tmp/neon/cargo-timings/
-
       # XXX: keep this after the binaries.list is formed, so the coverage can properly work later
       - name: Merge and upload coverage data
         if: matrix.build_type == 'debug'
         uses: ./.github/actions/save-coverage-data
 
   regress-tests:
-    runs-on: dev
+    runs-on: [ self-hosted, gen3, large ]
     container:
       image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
       options: --init
@@ -250,7 +318,7 @@ jobs:
         uses: actions/checkout@v3
         with:
           submodules: true
-          fetch-depth: 2
+          fetch-depth: 1
 
       - name: Pytest regression tests
         uses: ./.github/actions/run-python-test-set
@@ -268,34 +336,8 @@ jobs:
         if: matrix.build_type == 'debug'
         uses: ./.github/actions/save-coverage-data
 
-  upload-latest-artifacts:
-    runs-on: dev
-    container:
-      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
-      options: --init
-    needs: [ regress-tests ]
-    if: github.ref_name == 'main'
-    steps:
-      - name: Copy Neon artifact to the latest directory
-        shell: bash -euxo pipefail {0}
-        env:
-          BUCKET: neon-github-public-dev
-          PREFIX: artifacts/${{ github.run_id }}
-        run: |
-          for build_type in debug release; do
-            FILENAME=neon-${{ runner.os }}-${build_type}-artifact.tar.zst
-
-            S3_KEY=$(aws s3api list-objects-v2 --bucket ${BUCKET} --prefix ${PREFIX} | jq -r '.Contents[].Key' | grep ${FILENAME} | sort --version-sort | tail -1 || true)
-            if [ -z "${S3_KEY}" ]; then
-              echo 2>&1 "Neither s3://${BUCKET}/${PREFIX}/${FILENAME} nor its version from previous attempts exist"
-              exit 1
-            fi
-
-            time aws s3 cp --only-show-errors s3://${BUCKET}/${S3_KEY} s3://${BUCKET}/artifacts/latest/${FILENAME}
-          done
-
   benchmarks:
-    runs-on: dev
+    runs-on: [ self-hosted, gen3, small ]
     container:
       image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
       options: --init
@@ -310,7 +352,7 @@ jobs:
         uses: actions/checkout@v3
         with:
           submodules: true
-          fetch-depth: 2
+          fetch-depth: 1
 
       - name: Pytest benchmarks
         uses: ./.github/actions/run-python-test-set
@@ -326,12 +368,12 @@ jobs:
       # while coverage is currently collected for the debug ones
 
   merge-allure-report:
-    runs-on: dev
+    runs-on: [ self-hosted, gen3, small ]
     container:
       image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
       options: --init
     needs: [ regress-tests, benchmarks ]
-    if: always()
+    if: ${{ !cancelled() }}
     strategy:
       fail-fast: false
       matrix:
@@ -356,7 +398,6 @@ jobs:
           SHA: ${{ github.event.pull_request.head.sha || github.sha }}
           REPORT_URL: ${{ steps.create-allure-report.outputs.report-url }}
           TEST_RESULT_CONNSTR: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR }}
-        shell: bash -euxo pipefail {0}
         run: |
           curl --fail --output suites.json ${REPORT_URL%/index.html}/data/suites.json
           ./scripts/pysync
@@ -364,7 +405,7 @@ jobs:
           DATABASE_URL="$TEST_RESULT_CONNSTR" poetry run python3 scripts/ingest_regress_test_result.py --revision ${SHA} --reference ${GITHUB_REF} --build-type ${BUILD_TYPE} --ingest suites.json
 
   coverage-report:
-    runs-on: dev
+    runs-on: [ self-hosted, gen3, small ]
     container:
       image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
       options: --init
@@ -380,16 +421,17 @@ jobs:
           submodules: true
           fetch-depth: 1
 
-      - name: Restore cargo deps cache
+#      Disabled for now
-        id: cache_cargo
+#      - name: Restore cargo deps cache
-        uses: actions/cache@v3
+#        id: cache_cargo
-        with:
+#        uses: actions/cache@v3
-          path: |
+#        with:
-            ~/.cargo/registry/
+#          path: |
-            !~/.cargo/registry/src
+#            ~/.cargo/registry/
-            ~/.cargo/git/
+#            !~/.cargo/registry/src
-            target/
+#            ~/.cargo/git/
-          key: v9-${{ runner.os }}-${{ matrix.build_type }}-cargo-${{ hashFiles('Cargo.lock') }}
+#            target/
+#          key: v1-${{ runner.os }}-${{ matrix.build_type }}-cargo-${{ hashFiles('rust-toolchain.toml') }}-${{ hashFiles('Cargo.lock') }}
 
       - name: Get Neon artifact
         uses: ./.github/actions/download
@@ -405,7 +447,6 @@ jobs:
 
       - name: Merge coverage data
         run: scripts/coverage "--profraw-prefix=$GITHUB_JOB" --dir=/tmp/coverage merge
-        shell: bash -euxo pipefail {0}
 
       - name: Build and upload coverage report
         run: |
@@ -438,18 +479,21 @@ jobs:
               \"description\": \"Coverage report is ready\",
               \"target_url\": \"$REPORT_URL\"
             }"
-        shell: bash -euxo pipefail {0}
 
   trigger-e2e-tests:
-    runs-on: dev
+    runs-on: [ self-hosted, gen3, small ]
     container:
       image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/base:pinned
       options: --init
-    needs: [ build-neon ]
+    needs: [ push-docker-hub, tag ]
     steps:
       - name: Set PR's status to pending and request a remote CI test
         run: |
+          # For pull requests, GH Actions set "github.sha" variable to point at a fake merge commit
+          # but we need to use a real sha of a latest commit in the PR's branch for the e2e job,
+          # to place a job run status update later.
           COMMIT_SHA=${{ github.event.pull_request.head.sha }}
+          # For non-PR kinds of runs, the above will produce an empty variable, pick the original sha value for those
           COMMIT_SHA=${COMMIT_SHA:-${{ github.sha }}}
 
           REMOTE_REPO="${{ github.repository_owner }}/cloud"
@@ -475,13 +519,20 @@ jobs:
               \"inputs\": {
                 \"ci_job_name\": \"neon-cloud-e2e\",
                 \"commit_hash\": \"$COMMIT_SHA\",
-                \"remote_repo\": \"${{ github.repository }}\"
+                \"remote_repo\": \"${{ github.repository }}\",
+                \"storage_image_tag\": \"${{ needs.tag.outputs.build-tag }}\",
+                \"compute_image_tag\": \"${{ needs.tag.outputs.build-tag }}\"
               }
             }"
 
   neon-image:
-    runs-on: dev
+    runs-on: [ self-hosted, gen3, large ]
-    container: gcr.io/kaniko-project/executor:v1.9.0-debug
+    needs: [ tag ]
+    # https://github.com/GoogleContainerTools/kaniko/issues/2005
+    container: gcr.io/kaniko-project/executor:v1.7.0-debug
+    defaults:
+      run:
+        shell: sh -eu {0}
 
     steps:
       - name: Checkout
@@ -494,11 +545,19 @@ jobs:
         run: echo "{\"credsStore\":\"ecr-login\"}" > /kaniko/.docker/config.json
 
       - name: Kaniko build neon
-        run: /kaniko/executor --snapshotMode=redo --cache=true --cache-repo 369495373322.dkr.ecr.eu-central-1.amazonaws.com/cache --snapshotMode=redo --context . --destination 369495373322.dkr.ecr.eu-central-1.amazonaws.com/neon:$GITHUB_RUN_ID
+        run: /kaniko/executor --reproducible --snapshotMode=redo --skip-unused-stages --cache=true --cache-repo 369495373322.dkr.ecr.eu-central-1.amazonaws.com/cache --context . --build-arg GIT_VERSION=${{ github.sha }} --destination 369495373322.dkr.ecr.eu-central-1.amazonaws.com/neon:${{needs.tag.outputs.build-tag}}
+
+      # Cleanup script fails otherwise - rm: cannot remove '/nvme/actions-runner/_work/_temp/_github_home/.ecr': Permission denied
+      - name: Cleanup ECR folder
+        run: rm -rf ~/.ecr
 
   compute-tools-image:
-    runs-on: dev
+    runs-on: [ self-hosted, gen3, large ]
-    container: gcr.io/kaniko-project/executor:v1.9.0-debug
+    needs: [ tag ]
+    container: gcr.io/kaniko-project/executor:v1.7.0-debug
+    defaults:
+      run:
+        shell: sh -eu {0}
 
     steps:
       - name: Checkout
@@ -508,80 +567,163 @@ jobs:
         run: echo "{\"credsStore\":\"ecr-login\"}" > /kaniko/.docker/config.json
 
       - name: Kaniko build compute tools
-        run: /kaniko/executor --snapshotMode=redo --cache=true --cache-repo 369495373322.dkr.ecr.eu-central-1.amazonaws.com/cache --snapshotMode=redo --context . --dockerfile Dockerfile.compute-tools --destination 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-tools:$GITHUB_RUN_ID
+        run: /kaniko/executor --reproducible --snapshotMode=redo --skip-unused-stages --cache=true --cache-repo 369495373322.dkr.ecr.eu-central-1.amazonaws.com/cache --context . --build-arg GIT_VERSION=${{ github.sha }} --dockerfile Dockerfile.compute-tools --destination 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-tools:${{needs.tag.outputs.build-tag}}
+
+      - name: Cleanup ECR folder
+        run: rm -rf ~/.ecr
 
   compute-node-image:
-    runs-on: dev
+    runs-on: [ self-hosted, gen3, large ]
-    container: gcr.io/kaniko-project/executor:v1.9.0-debug
+    container: gcr.io/kaniko-project/executor:v1.7.0-debug
-    steps:
+    needs: [ tag ]
-      - name: Checkout
-        uses: actions/checkout@v1 # v3 won't work with kaniko
-        with:
-          submodules: true
-          fetch-depth: 0
-
-      - name: Configure ECR login
-        run: echo "{\"credsStore\":\"ecr-login\"}" > /kaniko/.docker/config.json
-
-        # compute-node uses postgres 14, which is default now
-        # cloud repo depends on this image name, thus duplicating it
-        # remove compute-node when cloud repo is updated
-      - name: Kaniko build compute node with extensions v14 (compatibility)
-        run: /kaniko/executor --skip-unused-stages --snapshotMode=redo --cache=true --cache-repo 369495373322.dkr.ecr.eu-central-1.amazonaws.com/cache --snapshotMode=redo --context . --dockerfile Dockerfile.compute-node-v14 --destination 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node:$GITHUB_RUN_ID
-
-  compute-node-image-v14:
-    runs-on: dev
-    container: gcr.io/kaniko-project/executor:v1.9.0-debug
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v1 # v3 won't work with kaniko
-        with:
-          submodules: true
-          fetch-depth: 0
-
-      - name: Configure ECR login
-        run: echo "{\"credsStore\":\"ecr-login\"}" > /kaniko/.docker/config.json
-
-      - name: Kaniko build compute node with extensions v14
-        run: /kaniko/executor --skip-unused-stages  --snapshotMode=redo --cache=true --cache-repo 369495373322.dkr.ecr.eu-central-1.amazonaws.com/cache  --context . --dockerfile Dockerfile.compute-node-v14 --destination 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-v14:$GITHUB_RUN_ID
-
-
-  compute-node-image-v15:
-    runs-on: dev
-    container: gcr.io/kaniko-project/executor:v1.9.0-debug
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v1 # v3 won't work with kaniko
-        with:
-          submodules: true
-          fetch-depth: 0
-
-      - name: Configure ECR login
-        run: echo "{\"credsStore\":\"ecr-login\"}" > /kaniko/.docker/config.json
-
-      - name: Kaniko build compute node with extensions v15
-        run: /kaniko/executor --skip-unused-stages --snapshotMode=redo --cache=true --cache-repo 369495373322.dkr.ecr.eu-central-1.amazonaws.com/cache --context . --dockerfile Dockerfile.compute-node-v15 --destination 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-v15:$GITHUB_RUN_ID
-
-  promote-images:
-    runs-on: dev
-    needs: [ neon-image, compute-node-image, compute-node-image-v14, compute-tools-image ]
-    if: github.event_name != 'workflow_dispatch'
-    container: amazon/aws-cli
     strategy:
       fail-fast: false
       matrix:
-        # compute-node uses postgres 14, which is default now
+        version: [ v14, v15 ]
-        # cloud repo depends on this image name, thus duplicating it
+    defaults:
-        # remove compute-node when cloud repo is updated
+      run:
-        name: [ neon, compute-node, compute-node-v14, compute-tools ]
+        shell: sh -eu {0}
 
     steps:
-      - name: Promote image to latest
+      - name: Checkout
-        run:
+        uses: actions/checkout@v1 # v3 won't work with kaniko
-          MANIFEST=$(aws ecr batch-get-image --repository-name ${{ matrix.name }} --image-ids imageTag=$GITHUB_RUN_ID --query 'images[].imageManifest' --output text) && aws ecr put-image --repository-name ${{ matrix.name }} --image-tag latest --image-manifest "$MANIFEST"
+        with:
+          submodules: true
+          fetch-depth: 0
+
+      - name: Configure ECR login
+        run: echo "{\"credsStore\":\"ecr-login\"}" > /kaniko/.docker/config.json
+
+      - name: Kaniko build compute node with extensions
+        run: /kaniko/executor --reproducible --snapshotMode=redo --skip-unused-stages --cache=true --cache-repo 369495373322.dkr.ecr.eu-central-1.amazonaws.com/cache  --context . --build-arg GIT_VERSION=${{ github.sha }} --build-arg PG_VERSION=${{ matrix.version }} --dockerfile Dockerfile.compute-node --destination 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-${{ matrix.version }}:${{needs.tag.outputs.build-tag}}
+
+      - name: Cleanup ECR folder
+        run: rm -rf ~/.ecr
+
+  vm-compute-node-image:
+    runs-on: [ self-hosted, gen3, large ]
+    needs: [ tag, compute-node-image ]
+    strategy:
+      fail-fast: false
+      matrix:
+        version: [ v14, v15 ]
+    defaults:
+      run:
+        shell: sh -eu {0}
+    env:
+      VM_INFORMANT_VERSION: 0.1.1
+
+    steps:
+      - name: Downloading latest vm-builder
+        run: |
+          curl -L https://github.com/neondatabase/neonvm/releases/latest/download/vm-builder -o vm-builder
+          chmod +x vm-builder
+
+      - name: Pulling compute-node image
+        run: |
+          docker pull 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-${{ matrix.version }}:${{needs.tag.outputs.build-tag}}
+
+      - name: Downloading VM informant version ${{ env.VM_INFORMANT_VERSION }}
+        run: |
+          curl -fL https://github.com/neondatabase/autoscaling/releases/download/${{ env.VM_INFORMANT_VERSION }}/vm-informant -o vm-informant
+          chmod +x vm-informant
+
+      - name: Adding VM informant to compute-node image
+        run: |
+          ID=$(docker create 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-${{ matrix.version }}:${{needs.tag.outputs.build-tag}})
+          docker cp vm-informant $ID:/bin/vm-informant
+          docker commit $ID temp-vm-compute-node
+          docker rm -f $ID
+
+      - name: Build vm image
+        run: |
+          # note: as of 2023-01-12, vm-builder requires a trailing ":latest" for local images
+          ./vm-builder -src=temp-vm-compute-node:latest -dst=369495373322.dkr.ecr.eu-central-1.amazonaws.com/vm-compute-node-${{ matrix.version }}:${{needs.tag.outputs.build-tag}}
+
+      - name: Pushing vm-compute-node image
+        run: |
+          docker push 369495373322.dkr.ecr.eu-central-1.amazonaws.com/vm-compute-node-${{ matrix.version }}:${{needs.tag.outputs.build-tag}}
+
+  test-images:
+    needs: [ tag, neon-image, compute-node-image, compute-tools-image ]
+    runs-on: [ self-hosted, gen3, small ]
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      # `neondatabase/neon` contains multiple binaries, all of them use the same input for the version into the same version formatting library.
+      # Pick pageserver as currently the only binary with extra "version" features printed in the string to verify.
+      # Regular pageserver version string looks like
+      #   Neon page server git-env:32d14403bd6ab4f4520a94cbfd81a6acef7a526c failpoints: true, features: []
+      # Bad versions might loop like:
+      #   Neon page server git-env:local failpoints: true, features: ["testing"]
+      # Ensure that we don't have bad versions.
+      - name: Verify image versions
+        shell: bash # ensure no set -e for better error messages
+        run: |
+          pageserver_version=$(docker run --rm 369495373322.dkr.ecr.eu-central-1.amazonaws.com/neon:${{needs.tag.outputs.build-tag}} "/bin/sh" "-c" "/usr/local/bin/pageserver --version")
+
+          echo "Pageserver version string: $pageserver_version"
+
+          if ! echo "$pageserver_version" | grep -qv 'git-env:local' ; then
+            echo "Pageserver version should not be the default Dockerfile one"
+            exit 1
+          fi
+
+          if ! echo "$pageserver_version" | grep -qv '"testing"' ; then
+            echo "Pageserver version should have no testing feature enabled"
+            exit 1
+          fi
+
+      - name: Verify docker-compose example
+        run: env REPOSITORY=369495373322.dkr.ecr.eu-central-1.amazonaws.com TAG=${{needs.tag.outputs.build-tag}} ./docker-compose/docker_compose_test.sh
+
+      - name: Print logs and clean up
+        if: always()
+        run: |
+          docker compose -f ./docker-compose/docker-compose.yml logs || 0
+          docker compose -f ./docker-compose/docker-compose.yml down
+
+  promote-images:
+    runs-on: [ self-hosted, gen3, small ]
+    needs: [ tag, test-images, vm-compute-node-image ]
+    container: golang:1.19-bullseye
+    if: github.event_name != 'workflow_dispatch'
+
+    steps:
+      - name: Install Crane & ECR helper
+        if: |
+          (github.ref_name == 'main' || github.ref_name == 'release') &&
+          github.event_name != 'workflow_dispatch'
+        run: |
+          go install github.com/google/go-containerregistry/cmd/crane@31786c6cbb82d6ec4fb8eb79cd9387905130534e # v0.11.0
+          go install github.com/awslabs/amazon-ecr-credential-helper/ecr-login/cli/docker-credential-ecr-login@69c85dc22db6511932bbf119e1a0cc5c90c69a7f # v0.6.0
+
+      - name: Configure ECR login
+        run: |
+          mkdir /github/home/.docker/
+          echo "{\"credsStore\":\"ecr-login\"}" > /github/home/.docker/config.json
+
+      - name: Add latest tag to images
+        if: |
+          (github.ref_name == 'main' || github.ref_name == 'release') &&
+          github.event_name != 'workflow_dispatch'
+        run: |
+          crane tag 369495373322.dkr.ecr.eu-central-1.amazonaws.com/neon:${{needs.tag.outputs.build-tag}} latest
+          crane tag 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-tools:${{needs.tag.outputs.build-tag}} latest
+          crane tag 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-v14:${{needs.tag.outputs.build-tag}} latest
+          crane tag 369495373322.dkr.ecr.eu-central-1.amazonaws.com/vm-compute-node-v14:${{needs.tag.outputs.build-tag}} latest
+          crane tag 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-v15:${{needs.tag.outputs.build-tag}} latest
+          crane tag 369495373322.dkr.ecr.eu-central-1.amazonaws.com/vm-compute-node-v15:${{needs.tag.outputs.build-tag}} latest
+
+      - name: Cleanup ECR folder
+        run: rm -rf ~/.ecr
 
   push-docker-hub:
-    runs-on: dev
+    runs-on: [ self-hosted, dev, x64 ]
     needs: [ promote-images, tag ]
     container: golang:1.19-bullseye
 
@@ -597,16 +739,22 @@ jobs:
           echo "{\"credsStore\":\"ecr-login\"}" > /github/home/.docker/config.json
 
       - name: Pull neon image from ECR
-        run: crane pull 369495373322.dkr.ecr.eu-central-1.amazonaws.com/neon:latest neon
+        run: crane pull 369495373322.dkr.ecr.eu-central-1.amazonaws.com/neon:${{needs.tag.outputs.build-tag}} neon
 
       - name: Pull compute tools image from ECR
-        run: crane pull 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-tools:latest compute-tools
+        run: crane pull 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-tools:${{needs.tag.outputs.build-tag}} compute-tools
-
-      - name: Pull compute node image from ECR
-        run: crane pull 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node:latest compute-node
 
       - name: Pull compute node v14 image from ECR
-        run: crane pull 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-v14:latest compute-node-v14
+        run: crane pull 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-v14:${{needs.tag.outputs.build-tag}} compute-node-v14
+
+      - name: Pull vm compute node v14 image from ECR
+        run: crane pull 369495373322.dkr.ecr.eu-central-1.amazonaws.com/vm-compute-node-v14:${{needs.tag.outputs.build-tag}} vm-compute-node-v14
+
+      - name: Pull compute node v15 image from ECR
+        run: crane pull 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-v15:${{needs.tag.outputs.build-tag}} compute-node-v15
+
+      - name: Pull vm compute node v15 image from ECR
+        run: crane pull 369495373322.dkr.ecr.eu-central-1.amazonaws.com/vm-compute-node-v15:${{needs.tag.outputs.build-tag}} vm-compute-node-v15
 
       - name: Pull rust image from ECR
         run: crane pull 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned rust
@@ -616,9 +764,12 @@ jobs:
           (github.ref_name == 'main' || github.ref_name == 'release') &&
           github.event_name != 'workflow_dispatch'
         run: |
-          crane copy 369495373322.dkr.ecr.eu-central-1.amazonaws.com/neon:$GITHUB_RUN_ID 093970136003.dkr.ecr.us-east-2.amazonaws.com/neon:latest
+          crane copy 369495373322.dkr.ecr.eu-central-1.amazonaws.com/neon:${{needs.tag.outputs.build-tag}} 093970136003.dkr.ecr.eu-central-1.amazonaws.com/neon:latest
-          crane copy 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-tools:$GITHUB_RUN_ID 093970136003.dkr.ecr.us-east-2.amazonaws.com/compute-tools:latest
+          crane copy 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-tools:${{needs.tag.outputs.build-tag}} 093970136003.dkr.ecr.eu-central-1.amazonaws.com/compute-tools:latest
-          crane copy 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node:$GITHUB_RUN_ID 093970136003.dkr.ecr.us-east-2.amazonaws.com/compute-node:latest
+          crane copy 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-v14:${{needs.tag.outputs.build-tag}} 093970136003.dkr.ecr.eu-central-1.amazonaws.com/compute-node-v14:latest
+          crane copy 369495373322.dkr.ecr.eu-central-1.amazonaws.com/vm-compute-node-v14:${{needs.tag.outputs.build-tag}} 093970136003.dkr.ecr.eu-central-1.amazonaws.com/vm-compute-node-v14:latest
+          crane copy 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-v15:${{needs.tag.outputs.build-tag}} 093970136003.dkr.ecr.eu-central-1.amazonaws.com/compute-node-v15:latest
+          crane copy 369495373322.dkr.ecr.eu-central-1.amazonaws.com/vm-compute-node-v15:${{needs.tag.outputs.build-tag}} 093970136003.dkr.ecr.eu-central-1.amazonaws.com/vm-compute-node-v15:latest
 
       - name: Configure Docker Hub login
         run: |
@@ -632,12 +783,18 @@ jobs:
       - name: Push compute tools image to Docker Hub
         run: crane push compute-tools neondatabase/compute-tools:${{needs.tag.outputs.build-tag}}
 
-      - name: Push compute node image to Docker Hub
-        run: crane push compute-node neondatabase/compute-node:${{needs.tag.outputs.build-tag}}
-
       - name: Push compute node v14 image to Docker Hub
         run: crane push compute-node-v14 neondatabase/compute-node-v14:${{needs.tag.outputs.build-tag}}
 
+      - name: Push vm compute node v14 image to Docker Hub
+        run: crane push vm-compute-node-v14 neondatabase/vm-compute-node-v14:${{needs.tag.outputs.build-tag}}
+
+      - name: Push compute node v15 image to Docker Hub
+        run: crane push compute-node-v15 neondatabase/compute-node-v15:${{needs.tag.outputs.build-tag}}
+
+      - name: Push vm compute node v15 image to Docker Hub
+        run: crane push vm-compute-node-v15 neondatabase/vm-compute-node-v15:${{needs.tag.outputs.build-tag}}
+
       - name: Push rust image to Docker Hub
         run: crane push rust neondatabase/rust:pinned
 
@@ -648,46 +805,29 @@ jobs:
         run: |
           crane tag neondatabase/neon:${{needs.tag.outputs.build-tag}} latest
           crane tag neondatabase/compute-tools:${{needs.tag.outputs.build-tag}} latest
-          crane tag neondatabase/compute-node:${{needs.tag.outputs.build-tag}} latest
           crane tag neondatabase/compute-node-v14:${{needs.tag.outputs.build-tag}} latest
+          crane tag neondatabase/vm-compute-node-v14:${{needs.tag.outputs.build-tag}} latest
+          crane tag neondatabase/compute-node-v15:${{needs.tag.outputs.build-tag}} latest
+          crane tag neondatabase/vm-compute-node-v15:${{needs.tag.outputs.build-tag}} latest
 
-  calculate-deploy-targets:
+      - name: Cleanup ECR folder
-    runs-on: [ self-hosted, Linux, k8s-runner ]
+        run: rm -rf ~/.ecr
-    if: |
-      (github.ref_name == 'main' || github.ref_name == 'release') &&
-      github.event_name != 'workflow_dispatch'
-    outputs:
-      matrix-include: ${{ steps.set-matrix.outputs.include }}
-    steps:
-      - id: set-matrix
-        run: |
-          if [[ "$GITHUB_REF_NAME" == "main" ]]; then
-            STAGING='{"env_name": "staging", "proxy_job": "neon-proxy", "proxy_config": "staging.proxy", "kubeconfig_secret": "STAGING_KUBECONFIG_DATA"}'
-            NEON_STRESS='{"env_name": "neon-stress", "proxy_job": "neon-stress-proxy", "proxy_config": "neon-stress.proxy", "kubeconfig_secret": "NEON_STRESS_KUBECONFIG_DATA"}'
-            echo "::set-output name=include::[$STAGING, $NEON_STRESS]"
-          elif [[ "$GITHUB_REF_NAME" == "release" ]]; then
-            PRODUCTION='{"env_name": "production", "proxy_job": "neon-proxy", "proxy_config": "production.proxy", "kubeconfig_secret": "PRODUCTION_KUBECONFIG_DATA"}'
-            echo "::set-output name=include::[$PRODUCTION]"
-          else
-            echo "GITHUB_REF_NAME (value '$GITHUB_REF_NAME') is not set to either 'main' or 'release'"
-            exit 1
-          fi
 
-  deploy:
+  deploy-pr-test-new:
-    runs-on: [ self-hosted, Linux, k8s-runner ]
+    runs-on: [ self-hosted, gen3, small ]
-    #container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/base:latest
+    container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/ansible:pinned
     # We need both storage **and** compute images for deploy, because control plane picks the compute version based on the storage version.
     # If it notices a fresh storage it may bump the compute version. And if compute image failed to build it may break things badly
-    needs: [ push-docker-hub, calculate-deploy-targets, tag, regress-tests ]
+    needs: [ push-docker-hub, tag, regress-tests ]
     if: |
-      (github.ref_name == 'main' || github.ref_name == 'release') &&
+      contains(github.event.pull_request.labels.*.name, 'deploy-test-storage') &&
       github.event_name != 'workflow_dispatch'
     defaults:
       run:
         shell: bash
     strategy:
       matrix:
-        include: ${{fromJSON(needs.calculate-deploy-targets.outputs.matrix-include)}}
+        target_region: [ eu-west-1 ]
     steps:
       - name: Checkout
         uses: actions/checkout@v3
@@ -695,78 +835,76 @@ jobs:
           submodules: true
           fetch-depth: 0
 
-      - name: Setup python
-        uses: actions/setup-python@v4
-        with:
-          python-version: '3.10'
-
-      - name: Setup ansible
-        run: |
-          export PATH="/root/.local/bin:$PATH"
-          pip install --progress-bar off --user ansible boto3
-
       - name: Redeploy
         run: |
           export DOCKER_TAG=${{needs.tag.outputs.build-tag}}
           cd "$(pwd)/.github/ansible"
 
+          ./get_binaries.sh
+
+          ansible-galaxy collection install sivel.toiletwater
+          ansible-playbook 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:
+    runs-on: [ self-hosted, gen3, small ]
+    container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/ansible:latest
+    needs: [ push-docker-hub, tag, regress-tests ]
+    if: ( github.ref_name == 'main' || github.ref_name == 'release' ) && github.event_name != 'workflow_dispatch'
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          submodules: false
+          fetch-depth: 0
+
+      - name: Trigger deploy workflow
+        env:
+          GH_TOKEN: ${{ github.token }}
+        run: |
           if [[ "$GITHUB_REF_NAME" == "main" ]]; then
-            ./get_binaries.sh
+            gh workflow run deploy-dev.yml --ref main -f branch=${{ github.sha }} -f dockerTag=${{needs.tag.outputs.build-tag}}
           elif [[ "$GITHUB_REF_NAME" == "release" ]]; then
-            RELEASE=true ./get_binaries.sh
+            gh workflow run deploy-prod.yml --ref release -f branch=${{ github.sha }} -f dockerTag=${{needs.tag.outputs.build-tag}} -f disclamerAcknowledged=true
           else
             echo "GITHUB_REF_NAME (value '$GITHUB_REF_NAME') is not set to either 'main' or 'release'"
             exit 1
           fi
 
-          eval $(ssh-agent)
+  promote-compatibility-data:
-          echo "${{ secrets.TELEPORT_SSH_KEY }}"  | tr -d '\n'| base64 --decode >ssh-key
+    runs-on: [ self-hosted, gen3, small ]
-          echo "${{ secrets.TELEPORT_SSH_CERT }}" | tr -d '\n'| base64 --decode >ssh-key-cert.pub
+    container:
-          chmod 0600 ssh-key
+      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
-          ssh-add ssh-key
+      options: --init
-          rm -f ssh-key ssh-key-cert.pub
+    needs: [ push-docker-hub, tag, regress-tests ]
-
+    if: github.ref_name == 'release' && github.event_name != 'workflow_dispatch'
-          ansible-playbook deploy.yaml -i ${{ matrix.env_name }}.hosts
-          rm -f neon_install.tar.gz .neon_current_version
-
-  deploy-proxy:
-    runs-on: dev
-    container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/base:latest
-    # Compute image isn't strictly required for proxy deploy, but let's still wait for it to run all deploy jobs consistently.
-    needs: [ push-docker-hub, calculate-deploy-targets, tag, regress-tests ]
-    if: |
-      (github.ref_name == 'main' || github.ref_name == 'release') &&
-      github.event_name != 'workflow_dispatch'
-    defaults:
-      run:
-        shell: bash
-    strategy:
-      matrix:
-        include: ${{fromJSON(needs.calculate-deploy-targets.outputs.matrix-include)}}
-    env:
-      KUBECONFIG: .kubeconfig
     steps:
-      - name: Checkout
+      - name: Promote compatibility snapshot for the release
-        uses: actions/checkout@v3
+        env:
-        with:
+          BUCKET: neon-github-public-dev
-          submodules: true
+          PREFIX: artifacts/latest
-          fetch-depth: 0
-
-      - name: Add curl
-        run: apt update && apt install curl -y
-
-      - name: Store kubeconfig file
         run: |
-          echo "${{ secrets[matrix.kubeconfig_secret] }}" | base64 --decode > ${KUBECONFIG}
+          # Update compatibility snapshot for the release
-          chmod 0600 ${KUBECONFIG}
+          for build_type in debug release; do
+            OLD_FILENAME=compatibility-snapshot-${build_type}-pg14-${GITHUB_RUN_ID}.tar.zst
+            NEW_FILENAME=compatibility-snapshot-${build_type}-pg14.tar.zst
 
-      - name: Setup helm v3
+            time aws s3 mv --only-show-errors s3://${BUCKET}/${PREFIX}/${OLD_FILENAME} s3://${BUCKET}/${PREFIX}/${NEW_FILENAME}
-        run: |
+          done
-          curl -s https://raw.githubusercontent.com/helm/helm/main/scripts/get-helm-3 | bash
-          helm repo add neondatabase https://neondatabase.github.io/helm-charts
 
-      - name: Re-deploy proxy
+          # Update Neon artifact for the release (reuse already uploaded artifact)
-        run: |
+          for build_type in debug release; do
-          DOCKER_TAG=${{needs.tag.outputs.build-tag}}
+            OLD_PREFIX=artifacts/${GITHUB_RUN_ID}
-          helm upgrade ${{ matrix.proxy_job }}       neondatabase/neon-proxy --namespace default --install -f .github/helm-values/${{ matrix.proxy_config }}.yaml --set image.tag=${DOCKER_TAG} --wait --timeout 15m0s
+            FILENAME=neon-${{ runner.os }}-${build_type}-artifact.tar.zst
-          helm upgrade ${{ matrix.proxy_job }}-scram neondatabase/neon-proxy --namespace default --install -f .github/helm-values/${{ matrix.proxy_config }}-scram.yaml --set image.tag=${DOCKER_TAG} --wait --timeout 15m0s
+
+            S3_KEY=$(aws s3api list-objects-v2 --bucket ${BUCKET} --prefix ${OLD_PREFIX} | jq -r '.Contents[].Key' | grep ${FILENAME} | sort --version-sort | tail -1 || true)
+            if [ -z "${S3_KEY}" ]; then
+              echo 2>&1 "Neither s3://${BUCKET}/${OLD_PREFIX}/${FILENAME} nor its version from previous attempts exist"
+              exit 1
+            fi
+
+            time aws s3 cp --only-show-errors s3://${BUCKET}/${S3_KEY} s3://${BUCKET}/${PREFIX}/${FILENAME}
+          done

.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: ${{ matrix.os }}
-
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v2
-        with:
-          submodules: true
-          fetch-depth: 2
-
-      - name: Check formatting
-        run: cargo fmt --all -- --check
-
-      - name: Install Ubuntu postgres dependencies
-        if: matrix.os == 'ubuntu-latest'
-        run: |
-          sudo apt update
-          sudo apt install build-essential libreadline-dev zlib1g-dev flex bison libseccomp-dev libssl-dev
-
-      - name: Install macOS postgres dependencies
-        if: matrix.os == 'macos-latest'
-        run: brew install flex bison openssl
-
-      - name: Set pg 14 revision for caching
-        id: pg_v14_rev
-        run: echo ::set-output name=pg_rev::$(git rev-parse HEAD:vendor/postgres-v14)
-        shell: bash -euxo pipefail {0}
-
-      - name: Set pg 15 revision for caching
-        id: pg_v15_rev
-        run: echo ::set-output name=pg_rev::$(git rev-parse HEAD:vendor/postgres-v15)
-        shell: bash -euxo pipefail {0}
-
-      - name: Cache postgres v14 build
-        id: cache_pg_14
-        uses: actions/cache@v3
-        with:
-          path: pg_install/v14
-          key: v1-${{ 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 "$(pwd)/.github/ansible"
+
+          ./get_binaries.sh
+
+          ansible-galaxy collection install sivel.toiletwater
+          ansible-playbook deploy.yaml -i staging.${{ 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 +1,240 @@
+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: 093970136003.dkr.ecr.eu-central-1.amazonaws.com/ansible:latest
+    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 "$(pwd)/.github/ansible"
+
+          ./get_binaries.sh
+
+          ansible-galaxy collection install sivel.toiletwater
+          ansible-playbook deploy.yaml -i prod.${{ 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
+
+  # Deploy to old account below          
+
+  deploy:
+    runs-on: prod
+    container: 093970136003.dkr.ecr.eu-central-1.amazonaws.com/ansible:latest
+    if: inputs.deployStorage && inputs.disclamerAcknowledged
+    defaults:
+      run:
+        shell: bash
+    environment:
+      name: prod-old
+    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
+
+          eval $(ssh-agent)
+          echo "${{ secrets.TELEPORT_SSH_KEY }}"  | tr -d '\n'| base64 --decode >ssh-key
+          echo "${{ secrets.TELEPORT_SSH_CERT }}" | tr -d '\n'| base64 --decode >ssh-key-cert.pub
+          chmod 0600 ssh-key
+          ssh-add ssh-key
+          rm -f ssh-key ssh-key-cert.pub
+          ANSIBLE_CONFIG=./ansible.cfg ansible-galaxy collection install sivel.toiletwater
+          ANSIBLE_CONFIG=./ansible.cfg ansible-playbook deploy.yaml -i production.hosts.yaml -e CONSOLE_API_TOKEN=${{ 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
+
+      # Cleanup script fails otherwise - rm: cannot remove '/nvme/actions-runner/_work/_temp/_github_home/.ansible/collections': Permission denied
+      - name: Cleanup ansible folder
+        run: rm -rf ~/.ansible
+
+  deploy-storage-broker:
+    name: deploy storage broker on old staging and old prod
+    runs-on: [ self-hosted, gen3, small ]
+    container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/ansible:pinned
+    if: inputs.deployStorageBroker && inputs.disclamerAcknowledged
+    defaults:
+      run:
+        shell: bash
+    environment:
+      name: prod-old
+    env:
+      KUBECONFIG: .kubeconfig
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          submodules: true
+          fetch-depth: 0
+          ref: ${{ inputs.branch }}
+
+      - name: Store kubeconfig file
+        run: |
+          echo "${{ secrets.PRODUCTION_KUBECONFIG_DATA }}" | base64 --decode > ${KUBECONFIG}
+          chmod 0600 ${KUBECONFIG}
+
+      - name: Add neon helm chart
+        run: helm repo add neondatabase https://neondatabase.github.io/helm-charts
+
+      - name: Deploy storage-broker
+        run:
+          helm upgrade neon-storage-broker neondatabase/neon-storage-broker --namespace neon-storage-broker --create-namespace --install --atomic -f .github/helm-values/production.neon-storage-broker.yaml --set image.tag=${{ inputs.dockerTag }} --set settings.sentryUrl=${{ secrets.SENTRY_URL_BROKER }} --wait --timeout 5m0s
+
+      - name: Cleanup helm folder
+        run: rm -rf ~/.cache

.github/workflows/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 }}-${{ github.ref == 'refs/heads/main' && github.sha || 'anysha' }}
+  cancel-in-progress: true
+
+env:
+  RUST_BACKTRACE: 1
+  COPT: '-Werror'
+
+jobs:
+  check-macos-build:
+    if: github.ref_name == 'main' || contains(github.event.pull_request.labels.*.name, 'run-extra-build-macos')
+    timeout-minutes: 90
+    runs-on: macos-latest
+
+    env:
+      # Use release build only, to have less debug info around
+      # Hence keeping target/ (and general cache size) smaller
+      BUILD_TYPE: release
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          submodules: true
+          fetch-depth: 1
+
+      - name: Install macOS postgres dependencies
+        run: brew install flex bison openssl protobuf
+
+      - name: Set pg 14 revision for caching
+        id: pg_v14_rev
+        run: echo pg_rev=$(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 }}-${{ matrix.build_type }}-pg-${{ 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
+        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

@@ -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

@@ -5,15 +5,166 @@ 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 = "0.51.0"
+base64 = "0.13.0"
+bincode = "1.3"
+bindgen = "0.61"
+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"
+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 = "0.3"
+hmac = "0.12.1"
+hostname = "0.3.1"
+humantime = "2.1"
+humantime-serde = "1.1.1"
+hyper = "0.14"
+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-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"
+tracing-opentelemetry = "0.18.0"
+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"] }
+routerify = "3"
+rpds = "0.12.0"
+rustls = "0.20"
+rustls-pemfile = "1"
+rustls-split = "0.3"
+scopeguard = "1.1"
+sentry = { version = "0.29", 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 = "0.4.4"
+strum = "0.24"
+strum_macros = "0.24"
+svg_fmt = "0.4.1"
+tar = "0.4"
+thiserror = "1.0"
+tls-listener = { version = "0.6", features = ["rustls", "hyper-h1"] }
+tokio = { version = "1.17", features = ["macros"] }
+tokio-postgres-rustls = "0.9.0"
+tokio-rustls = "0.23"
+tokio-stream = "0.1"
+tokio-util = { version = "0.7", features = ["io"] }
+toml = "0.5"
+toml_edit = { version = "0.17", features = ["easy"] }
+tonic = {version = "0.8", features = ["tls", "tls-roots"]}
+tracing = "0.1"
+tracing-subscriber = { version = "0.3", features = ["env-filter"] }
+url = "2.2"
+uuid = { version = "1.2", features = ["v4", "serde"] }
+walkdir = "2.3.2"
+webpki-roots = "0.22.5"
+x509-parser = "0.14"
+
+## 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" }
+postgres-protocol = { git = "https://github.com/neondatabase/rust-postgres.git", rev="43e6db254a97fdecbce33d8bc0890accfd74495e" }
+postgres-types = { git = "https://github.com/neondatabase/rust-postgres.git", rev="43e6db254a97fdecbce33d8bc0890accfd74495e" }
+tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev="43e6db254a97fdecbce33d8bc0890accfd74495e" }
+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
+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_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 = "0.16"
+tempfile = "3.2"
+tonic-build = "0.8"
+
+# 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
@@ -65,9 +216,3 @@ 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

@@ -44,7 +44,7 @@ COPY . .
 # Show build caching stats to check if it was used in the end.
 # Has to be the part of the same RUN since cachepot daemon is killed in the end of this RUN, losing the compilation stats.
 RUN set -e \
-&& mold -run cargo build --bin pageserver --bin 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
@@ -63,9 +63,12 @@ RUN set -e \
     && useradd -d /data neon \
     && chown -R neon:neon /data
 
-COPY --from=build --chown=neon:neon /home/nonroot/target/release/pageserver /usr/local/bin
+COPY --from=build --chown=neon:neon /home/nonroot/target/release/pageserver          /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/pageserver_binutils /usr/local/bin
-COPY --from=build --chown=neon:neon /home/nonroot/target/release/proxy      /usr/local/bin
+COPY --from=build --chown=neon:neon /home/nonroot/target/release/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/
 COPY --from=pg-build /home/nonroot/pg_install/v15 /usr/local/v15/
@@ -76,7 +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'"
@@ -85,4 +88,3 @@ VOLUME ["/data"]
 USER neon
 EXPOSE 6400
 EXPOSE 9898
-CMD ["/bin/bash"]

Dockerfile.compute-node

@@ -0,0 +1,258 @@
+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
+
+#########################################################################################
+#
+# 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 && \
+    ./configure CFLAGS='-O2 -g3' --enable-debug --with-openssl --with-uuid=ossp --with-icu && \
+    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/bloom.control && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/pgrowlocks.control && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/intagg.control && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/pgstattuple.control && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/earthdistance.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
+
+RUN wget https://gitlab.com/Oslandia/SFCGAL/-/archive/v1.3.10/SFCGAL-v1.3.10.tar.gz && \
+    tar zxvf SFCGAL-v1.3.10.tar.gz && \
+    cd SFCGAL-v1.3.10 && cmake . && make -j $(getconf _NPROCESSORS_ONLN) && \
+    DESTDIR=/sfcgal make install -j $(getconf _NPROCESSORS_ONLN) && \
+    make clean && cp -R /sfcgal/* /
+
+RUN wget https://download.osgeo.org/postgis/source/postgis-3.3.1.tar.gz && \
+    tar xvzf postgis-3.3.1.tar.gz && \
+    cd postgis-3.3.1 && \
+    ./autogen.sh && \
+    export PATH="/usr/local/pgsql/bin:$PATH" && \
+    ./configure --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
+
+#########################################################################################
+#
+# Layer "plv8-build"
+# Build plv8
+#
+#########################################################################################
+FROM build-deps AS plv8-build
+COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
+RUN apt update && \
+    apt install -y ninja-build python3-dev libc++-dev libc++abi-dev libncurses5 binutils
+
+# https://github.com/plv8/plv8/issues/475:
+#   v8 uses gold for linking and sets `--thread-count=4` which breaks
+#   gold version <= 1.35 (https://sourceware.org/bugzilla/show_bug.cgi?id=23607)
+# Install newer gold version manually as debian-testing binutils version updates
+# libc version, which in turn breaks other extension built against non-testing libc.
+RUN wget https://ftp.gnu.org/gnu/binutils/binutils-2.38.tar.gz && \
+    tar xvzf binutils-2.38.tar.gz && \
+    cd binutils-2.38 && \
+    cd libiberty && ./configure && make -j $(getconf _NPROCESSORS_ONLN) && \
+    cd ../bfd && ./configure && make bfdver.h && \
+    cd ../gold && ./configure && make -j $(getconf _NPROCESSORS_ONLN) && make install && \
+    cp /usr/local/bin/ld.gold /usr/bin/gold
+
+# Sed is used to patch for https://github.com/plv8/plv8/issues/503
+RUN wget https://github.com/plv8/plv8/archive/refs/tags/v3.1.4.tar.gz && \
+    tar xvzf v3.1.4.tar.gz && \
+    cd plv8-3.1.4 && \
+    export PATH="/usr/local/pgsql/bin:$PATH" && \
+    sed -i 's/MemoryContextAlloc(/MemoryContextAllocZero(/' plv8.cc && \
+    make DOCKER=1 -j $(getconf _NPROCESSORS_ONLN) install && \
+    rm -rf /plv8-* && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/plv8.control
+
+#########################################################################################
+#
+# Layer "h3-pg-build"
+# Build h3_pg
+#
+#########################################################################################
+FROM build-deps AS h3-pg-build
+COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
+
+# packaged cmake is too old
+RUN wget https://github.com/Kitware/CMake/releases/download/v3.24.2/cmake-3.24.2-linux-x86_64.sh \
+      -q -O /tmp/cmake-install.sh \
+      && chmod u+x /tmp/cmake-install.sh \
+      && /tmp/cmake-install.sh --skip-license --prefix=/usr/local/ \
+      && rm /tmp/cmake-install.sh
+
+RUN wget https://github.com/uber/h3/archive/refs/tags/v4.0.1.tar.gz -O h3.tgz && \
+    tar xvzf h3.tgz  && \
+    cd h3-4.0.1 && \
+    mkdir build && \
+    cd build && \
+    cmake .. -DCMAKE_BUILD_TYPE=Release && \
+    make -j $(getconf _NPROCESSORS_ONLN) && \
+    DESTDIR=/h3 make install && \
+    cp -R /h3/usr / && \
+    rm -rf build
+
+RUN wget https://github.com/zachasme/h3-pg/archive/refs/tags/v4.0.1.tar.gz -O h3-pg.tgz && \
+    tar xvzf h3-pg.tgz && \
+    cd h3-pg-4.0.1 && \
+    export PATH="/usr/local/pgsql/bin:$PATH" && \
+    make -j $(getconf _NPROCESSORS_ONLN) && \
+    make -j $(getconf _NPROCESSORS_ONLN) install && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/h3.control && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/h3_postgis.control
+
+#########################################################################################
+#
+# Layer "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 && \
+    tar xvzf 7.7.tar.gz && \
+    cd postgresql-unit-7.7 && \
+    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 "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 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 $REPOSITORY/$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
+
+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)
+# libossp-uuid16 for extension ossp-uuid
+# libgeos, libgdal, libsfcgal1, libproj and libprotobuf-c1 for PostGIS
+RUN apt update &&  \
+    apt install --no-install-recommends -y \
+        locales \
+        libicu67 \
+        libreadline8 \
+        libossp-uuid16 \
+        libgeos-c1v5 \
+        libgdal28 \
+        libproj19 \
+        libprotobuf-c1 \
+        libsfcgal1 \
+        gdb && \
+    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

@@ -1,200 +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 $(getconf _NPROCESSORS_ONLN) install && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_raster.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_tiger_geocoder.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_topology.control
-
-#
-# Layer "plv8-build"
-# Build plv8
-#
-FROM build-deps AS plv8-build
-COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
-RUN apt update && \
-    apt install -y ninja-build python3-dev libc++-dev libc++abi-dev libncurses5
-
-# https://github.com/plv8/plv8/issues/475
-# Debian bullseye provides binutils 2.35 when >= 2.38 is necessary
-RUN apt update && \
-    apt install -y --no-install-recommends -t testing binutils
-
-RUN wget https://github.com/plv8/plv8/archive/refs/tags/v3.1.4.tar.gz && \
-    tar xvzf v3.1.4.tar.gz && \
-    cd plv8-3.1.4 && \
-    export PATH="/usr/local/pgsql/bin:$PATH" && \
-    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/
-# plv8 still sometimes crashes during the creation
-# 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

@@ -1,172 +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=3.3.0
-# ARG PLV8_VERSION=3.1.4
-# ARG PG_VERSION=v15
-
-#
-# 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
-
-#
-# 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 $(getconf _NPROCESSORS_ONLN) -s -C src/interfaces/libpq install
-
-#
-# Layer "postgis-build"
-# Build PostGIS from the upstream PostGIS mirror.
-#
-# PostGIS compiles against neon postgres sources without changes. Perhaps we
-# could even use the upstream binaries, compiled against vanilla Postgres, but
-# it would require some investigation to check that it works, and also keeps
-# working in the future. So for now, we compile our own binaries.
-FROM build-deps AS postgis-build
-COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
-RUN apt update && \
-    apt install -y gdal-bin libgdal-dev libprotobuf-c-dev protobuf-c-compiler xsltproc wget
-
-RUN wget https://download.osgeo.org/postgis/source/postgis-3.3.0.tar.gz && \
-    tar xvzf postgis-3.3.0.tar.gz && \
-    cd postgis-3.3.0 && \
-    ./autogen.sh && \
-    export PATH="/usr/local/pgsql/bin:$PATH" && \
-    ./configure && \
-    make -j $(getconf _NPROCESSORS_ONLN) install && \
-    cd extensions/postgis && \
-    make clean && \
-    make -j $(getconf _NPROCESSORS_ONLN) install && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_raster.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_tiger_geocoder.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_topology.control
-
-#
-# Layer "plv8-build"
-# Build plv8
-#
-FROM build-deps AS plv8-build
-COPY --from=postgis-build /usr/local/pgsql/ /usr/local/pgsql/
-RUN apt update && \
-    apt install -y git curl wget make ninja-build build-essential libncurses5 python3-dev pkg-config libc++-dev libc++abi-dev libglib2.0-dev
-
-# https://github.com/plv8/plv8/issues/475
-# Debian bullseye provides binutils 2.35 when >= 2.38 is necessary
-RUN echo "deb http://ftp.debian.org/debian testing main" >> /etc/apt/sources.list && \
-    echo "APT::Default-Release \"stable\";" > /etc/apt/apt.conf.d/default-release && \
-    apt update && \
-    apt install -y --no-install-recommends -t testing binutils
-
-RUN wget https://github.com/plv8/plv8/archive/refs/tags/v3.1.4.tar.gz && \
-    tar xvzf v3.1.4.tar.gz && \
-    cd plv8-3.1.4 && \
-    export PATH="/usr/local/pgsql/bin:$PATH" && \
-    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 "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 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
-
-# TODO: Check if we can make the extension setup more modular versus a linear build
-# currently plv8-build copies the output /usr/local/pgsql from postgis-build, etc#
-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"]

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
+	OPENSSL_PREFIX ?= $(shell brew --prefix openssl@3)
-UNAME_S := $(shell uname -s)
+	PG_CONFIGURE_OPTS += --with-includes=$(OPENSSL_PREFIX)/include --with-libraries=$(OPENSSL_PREFIX)/lib
-ifeq ($(UNAME_S),Darwin)
+	# macOS already has bison and flex in the system, but they are old and result in postgres-v14 target failure
-    OPENSSL_PREFIX ?= $(shell brew --prefix openssl@3)
+	# brew formulae are keg-only and not symlinked into HOMEBREW_PREFIX, force their usage
-    PG_CONFIGURE_OPTS += --with-includes=$(OPENSSL_PREFIX)/include --with-libraries=$(OPENSSL_PREFIX)/lib
+	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 +61,115 @@ 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
 
-.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) -C $(POSTGRES_INSTALL_DIR)/pgxn/neon-$* -f $(ROOT_PROJECT_DIR)/pgxn/neon/Makefile clean
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v14/contrib/pg_buffercache clean
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/pgxn/neon_walredo-$* -f $(ROOT_PROJECT_DIR)/pgxn/neon_walredo/Makefile clean
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v14/contrib/pageinspect clean
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/pgxn/neon_test_utils-$* -f $(ROOT_PROJECT_DIR)/pgxn/neon_test_utils/Makefile clean
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v14/src/interfaces/libpq 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
 
@@ -35,12 +26,13 @@ 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
 ```
 
 2. [Install Rust](https://www.rust-lang.org/tools/install)
@@ -53,7 +45,7 @@ curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
 1. Install XCode and dependencies
 ```
 xcode-select --install
-brew install protobuf etcd openssl
+brew install protobuf openssl flex bison
 ```
 
 2. [Install Rust](https://www.rust-lang.org/tools/install)
@@ -116,7 +108,7 @@ make -j`sysctl -n hw.logicalcpu`
 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
@@ -125,24 +117,26 @@ 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
-Starting new postgres main on timeline de200bd42b49cc1814412c7e592dd6e9 ...
+Starting new postgres (v14) main 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'
 
@@ -223,22 +217,27 @@ 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

@@ -1,21 +1,28 @@
 [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 = "3.0"
+clap.workspace = true
-env_logger = "0.9"
+futures.workspace = true
-hyper = { version = "0.14", features = ["full"] }
+hyper = { workspace = true, features = ["full"] }
-log = { version = "0.4", features = ["std", "serde"] }
+notify.workspace = true
-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev="d052ee8b86fff9897c77b0fe89ea9daba0e1fa38" }
+opentelemetry.workspace = true
-regex = "1"
+postgres.workspace = true
-serde = { version = "1.0", features = ["derive"] }
+regex.workspace = true
-serde_json = "1"
+serde.workspace = true
-tar = "0.4"
+serde_json.workspace = true
-tokio = { version = "1.17", features = ["macros", "rt", "rt-multi-thread"] }
+tar.workspace = true
-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
+
+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 \
@@ -36,10 +40,11 @@ use std::{thread, time::Duration};
 use anyhow::{Context, Result};
 use chrono::Utc;
 use clap::Arg;
-use log::{error, info};
+use tracing::{error, info};
 
 use compute_tools::compute::{ComputeMetrics, ComputeNode, ComputeState, ComputeStatus};
 use compute_tools::http::api::launch_http_server;
+use compute_tools::informant::spawn_vm_informant_if_present;
 use compute_tools::logger::*;
 use compute_tools::monitor::launch_monitor;
 use compute_tools::params::*;
@@ -48,56 +53,21 @@ 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)?;
 
-    // Env variable is set by `cargo`
+    let matches = cli().get_matches();
-    let version: Option<&str> = option_env!("CARGO_PKG_VERSION");
-    let matches = clap::App::new("compute_ctl")
-        .version(version.unwrap_or("unknown"))
-        .arg(
-            Arg::new("connstr")
-                .short('C')
-                .long("connstr")
-                .value_name("DATABASE_URL")
-                .required(true),
-        )
-        .arg(
-            Arg::new("pgdata")
-                .short('D')
-                .long("pgdata")
-                .value_name("DATADIR")
-                .required(true),
-        )
-        .arg(
-            Arg::new("pgbin")
-                .short('b')
-                .long("pgbin")
-                .value_name("POSTGRES_PATH"),
-        )
-        .arg(
-            Arg::new("spec")
-                .short('s')
-                .long("spec")
-                .value_name("SPEC_JSON"),
-        )
-        .arg(
-            Arg::new("spec-path")
-                .short('S')
-                .long("spec-path")
-                .value_name("SPEC_PATH"),
-        )
-        .get_matches();
 
-    let pgdata = matches.value_of("pgdata").expect("PGDATA path is required");
+    let pgdata = matches
+        .get_one::<String>("pgdata")
+        .expect("PGDATA path is required");
     let connstr = matches
-        .value_of("connstr")
+        .get_one::<String>("connstr")
         .expect("Postgres connection string is required");
-    let spec = matches.value_of("spec");
+    let spec = matches.get_one::<String>("spec");
-    let spec_path = matches.value_of("spec-path");
+    let spec_path = matches.get_one::<String>("spec-path");
 
     // Try to use just 'postgres' if no path is provided
-    let pgbin = matches.value_of("pgbin").unwrap_or("postgres");
+    let pgbin = matches.get_one::<String>("pgbin").unwrap();
 
     let spec: ComputeSpec = match spec {
         // First, try to get cluster spec from the cli argument
@@ -114,6 +84,29 @@ fn main() -> Result<()> {
         }
     };
 
+    // Extract OpenTelemetry context for the startup actions from the spec, and
+    // 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) = spec.startup_tracing_context {
+        use opentelemetry::propagation::TextMapPropagator;
+        use opentelemetry::sdk::propagation::TraceContextPropagator;
+        Some(TraceContextPropagator::new().extract(carrier).attach())
+    } else {
+        None
+    };
+
     let pageserver_connstr = spec
         .cluster
         .settings
@@ -139,7 +132,7 @@ fn main() -> Result<()> {
         tenant,
         timeline,
         pageserver_connstr,
-        metrics: ComputeMetrics::new(),
+        metrics: ComputeMetrics::default(),
         state: RwLock::new(ComputeState::new()),
     };
     let compute = Arc::new(compute_state);
@@ -148,28 +141,98 @@ fn main() -> Result<()> {
     // 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");
+    // Also spawn the thread responsible for handling the VM informant -- if it's present
+    let _vm_informant_handle = spawn_vm_informant_if_present().expect("cannot launch VM informant");
 
-    // Run compute (Postgres) and hang waiting on it.
+    // Start Postgres
-    match compute.prepare_and_run() {
+    let mut delay_exit = false;
-        Ok(ec) => {
+    let mut exit_code = None;
-            let code = ec.code().unwrap_or(1);
+    let pg = match compute.start_compute() {
-            info!("Postgres exited with code {}, shutting down", code);
+        Ok(pg) => Some(pg),
-            exit(code)
+        Err(err) => {
-        }
+            error!("could not start the compute node: {:?}", err);
-        Err(error) => {
-            error!("could not start the compute node: {:?}", error);
-
             let mut state = compute.state.write().unwrap();
-            state.error = Some(format!("{:?}", error));
+            state.error = Some(format!("{:?}", err));
             state.status = ComputeStatus::Failed;
             drop(state);
-
+            delay_exit = true;
-            // Keep serving HTTP requests, so the cloud control plane was able to
+            None
-            // get the actual error.
-            info!("giving control plane 30s to collect the error before shutdown");
-            thread::sleep(Duration::from_secs(30));
-            info!("shutting down");
-            Err(error)
         }
+    };
+
+    // 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));
+        info!("shutting down");
+    }
+
+    // Shutdown trace pipeline gracefully, so that it has a chance to send any
+    // pending traces before we exit.
+    tracing_utils::shutdown_tracing();
+
+    exit(exit_code.unwrap_or(1))
+}
+
+fn cli() -> clap::Command {
+    // Env variable is set by `cargo`
+    let version = option_env!("CARGO_PKG_VERSION").unwrap_or("unknown");
+    clap::Command::new("compute_ctl")
+        .version(version)
+        .arg(
+            Arg::new("connstr")
+                .short('C')
+                .long("connstr")
+                .value_name("DATABASE_URL")
+                .required(true),
+        )
+        .arg(
+            Arg::new("pgdata")
+                .short('D')
+                .long("pgdata")
+                .value_name("DATADIR")
+                .required(true),
+        )
+        .arg(
+            Arg::new("pgbin")
+                .short('b')
+                .long("pgbin")
+                .default_value("postgres")
+                .value_name("POSTGRES_PATH"),
+        )
+        .arg(
+            Arg::new("spec")
+                .short('s')
+                .long("spec")
+                .value_name("SPEC_JSON"),
+        )
+        .arg(
+            Arg::new("spec-path")
+                .short('S')
+                .long("spec-path")
+                .value_name("SPEC_PATH"),
+        )
+}
+
+#[test]
+fn verify_cli() {
+    cli().debug_assert()
 }

compute_tools/src/checker.rs

@@ -1,11 +1,12 @@
 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<()> {
+#[instrument(skip_all)]
+pub fn create_writability_check_data(client: &mut Client) -> Result<()> {
     let query = "
     CREATE TABLE IF NOT EXISTS health_check (
         id serial primary key,
@@ -21,6 +22,7 @@ pub fn create_writablity_check_data(client: &mut Client) -> Result<()> {
     Ok(())
 }
 
+#[instrument(skip_all)]
 pub async fn check_writability(compute: &ComputeNode) -> Result<()> {
     let (client, connection) = tokio_postgres::connect(compute.connstr.as_str(), NoTls).await?;
     if client.is_closed() {

compute_tools/src/compute.rs

@@ -17,17 +17,17 @@
 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::sync::RwLock;
 
 use anyhow::{Context, Result};
 use chrono::{DateTime, Utc};
-use log::info;
 use postgres::{Client, NoTls};
 use serde::{Serialize, Serializer};
+use tracing::{info, instrument, warn};
 
-use crate::checker::create_writablity_check_data;
+use crate::checker::create_writability_check_data;
 use crate::config;
 use crate::pg_helpers::*;
 use crate::spec::*;
@@ -91,7 +91,7 @@ pub enum ComputeStatus {
     Failed,
 }
 
-#[derive(Serialize)]
+#[derive(Default, Serialize)]
 pub struct ComputeMetrics {
     pub sync_safekeepers_ms: AtomicU64,
     pub basebackup_ms: AtomicU64,
@@ -99,23 +99,6 @@ pub struct ComputeMetrics {
     pub total_startup_ms: AtomicU64,
 }
 
-impl ComputeMetrics {
-    pub fn new() -> Self {
-        Self {
-            sync_safekeepers_ms: AtomicU64::new(0),
-            basebackup_ms: AtomicU64::new(0),
-            config_ms: AtomicU64::new(0),
-            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;
@@ -138,6 +121,7 @@ impl ComputeNode {
 
     // Get basebackup from the libpq connection to pageserver using `connstr` and
     // unarchive it to `pgdata` directory overriding all its previous content.
+    #[instrument(skip(self))]
     fn get_basebackup(&self, lsn: &str) -> Result<()> {
         let start_time = Utc::now();
 
@@ -171,14 +155,14 @@ impl ComputeNode {
 
     // Run `postgres` in a special mode with `--sync-safekeepers` argument
     // and return the reported LSN back to the caller.
+    #[instrument(skip(self))]
     fn sync_safekeepers(&self) -> Result<String> {
         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
             .stdout(Stdio::piped())
-            .stderr(Stdio::piped())
             .spawn()
             .expect("postgres --sync-safekeepers failed to start");
 
@@ -191,10 +175,10 @@ impl ComputeNode {
 
         if !sync_output.status.success() {
             anyhow::bail!(
-                "postgres --sync-safekeepers exited with non-zero status: {}. stdout: {}, stderr: {}",
+                "postgres --sync-safekeepers exited with non-zero status: {}. stdout: {}",
                 sync_output.status,
-                String::from_utf8(sync_output.stdout).expect("postgres --sync-safekeepers exited, and stdout is not utf-8"),
+                String::from_utf8(sync_output.stdout)
-                String::from_utf8(sync_output.stderr).expect("postgres --sync-safekeepers exited, and stderr is not utf-8"),
+                    .expect("postgres --sync-safekeepers exited, and stdout is not utf-8"),
             );
         }
 
@@ -214,6 +198,7 @@ impl ComputeNode {
 
     /// Do all the preparations like PGDATA directory creation, configuration,
     /// safekeepers sync, basebackup, etc.
+    #[instrument(skip(self))]
     pub fn prepare_pgdata(&self) -> Result<()> {
         let spec = &self.spec;
         let pgdata_path = Path::new(&self.pgdata);
@@ -247,30 +232,27 @@ 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) -> 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])
             .spawn()
             .expect("cannot start postgres process");
 
-        // Try default Postgres port if it is not provided
+        wait_for_postgres(&mut pg, pgdata_path)?;
-        let port = self
-            .spec
-            .cluster
-            .settings
-            .find("port")
-            .unwrap_or_else(|| "5432".to_string());
-        wait_for_postgres(&mut pg, &port, pgdata_path)?;
 
+        Ok(pg)
+    }
+
+    #[instrument(skip(self))]
+    pub fn apply_config(&self) -> 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) {
@@ -296,16 +278,43 @@ impl ComputeNode {
             Ok(client) => client,
         };
 
+        // Proceed with post-startup configuration. Note, that order of operations is important.
         handle_roles(&self.spec, &mut client)?;
         handle_databases(&self.spec, &mut client)?;
         handle_role_deletions(self, &mut client)?;
         handle_grants(self, &mut client)?;
-        create_writablity_check_data(&mut client)?;
+        create_writability_check_data(&mut client)?;
 
         // 'Close' connection
         drop(client);
-        let startup_end_time = Utc::now();
 
+        info!(
+            "finished configuration of compute for project {}",
+            self.spec.cluster.cluster_id
+        );
+
+        Ok(())
+    }
+
+    #[instrument(skip(self))]
+    pub fn start_compute(&self) -> Result<std::process::Child> {
+        info!(
+            "starting compute for project {}, operation {}, tenant {}, timeline {}",
+            self.spec.cluster.cluster_id,
+            self.spec.operation_uuid.as_ref().unwrap(),
+            self.tenant,
+            self.timeline,
+        );
+
+        self.prepare_pgdata()?;
+
+        let start_time = Utc::now();
+
+        let pg = self.start_postgres()?;
+
+        self.apply_config()?;
+
+        let startup_end_time = Utc::now();
         self.metrics.config_ms.store(
             startup_end_time
                 .signed_duration_since(start_time)
@@ -325,30 +334,70 @@ impl ComputeNode {
 
         self.set_status(ComputeStatus::Running);
 
-        info!(
+        Ok(pg)
-            "finished configuration of compute for project {}",
-            self.spec.cluster.cluster_id
-        );
-
-        // Wait for child Postgres process basically forever. In this state Ctrl+C
-        // 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> {
+    // Look for core dumps and collect backtraces.
-        info!(
+    //
-            "starting compute for project {}, operation {}, tenant {}, timeline {}",
+    // EKS worker nodes have following core dump settings:
-            self.spec.cluster.cluster_id,
+    //   /proc/sys/kernel/core_pattern -> core
-            self.spec.operation_uuid.as_ref().unwrap(),
+    //   /proc/sys/kernel/core_uses_pid -> 1
-            self.tenant,
+    //   ulimint -c -> unlimited
-            self.timeline,
+    // 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),
+        };
 
-        self.prepare_pgdata()?;
+        // Collect core dump paths if any
-        self.run()
+        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(())
     }
 }

compute_tools/src/http/api.rs

@@ -6,32 +6,20 @@ use std::thread;
 use anyhow::Result;
 use hyper::service::{make_service_fn, service_fn};
 use hyper::{Body, Method, Request, Response, Server, StatusCode};
-use log::{error, info};
 use serde_json;
+use tracing::{error, info};
+use tracing_utils::http::OtelName;
 
-use crate::compute::{ComputeNode, ComputeStatus};
+use crate::compute::ComputeNode;
 
 // 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");
@@ -46,19 +34,9 @@ async fn routes(req: Request<Body>, compute: Arc<ComputeNode>) -> Response<Body>
             Response::new(Body::from(serde_json::to_string(&compute.metrics).unwrap()))
         }
 
-        // DEPRECATED, use POST instead
-        (&Method::GET, "/check_writability") => {
-            info!("serving /check_writability GET request");
-            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())),
-            }
-        }
-
         (&Method::POST, "/check_writability") => {
             info!("serving /check_writability POST request");
-            let res = crate::checker::check_writability(&compute).await;
+            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())),
@@ -84,7 +62,19 @@ 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

@@ -37,58 +37,7 @@ paths:
               schema:
                 $ref: "#/components/schemas/ComputeMetrics"
 
-  /ready:
-    get:
-      deprecated: true
-      tags:
-      - "info"
-      summary: Check whether compute startup process finished successfully
-      description: ""
-      operationId: computeIsReady
-      responses:
-        "200":
-          description: Compute is ready ('true') or not ('false')
-          content:
-            text/plain:
-              schema:
-                type: string
-                example: "true"
-
-  /last_activity:
-    get:
-      deprecated: true
-      tags:
-      - "info"
-      summary: Get timestamp of the last compute activity
-      description: ""
-      operationId: getLastComputeActivityTS
-      responses:
-        "200":
-          description: Timestamp of the last compute activity
-          content:
-            text/plain:
-              schema:
-                type: string
-                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"

compute_tools/src/informant.rs

@@ -0,0 +1,50 @@
+use std::path::Path;
+use std::process;
+use std::thread;
+use std::time::Duration;
+use tracing::{info, warn};
+
+use anyhow::{Context, Result};
+
+const VM_INFORMANT_PATH: &str = "/bin/vm-informant";
+const RESTART_INFORMANT_AFTER_MILLIS: u64 = 5000;
+
+/// Launch a thread to start the VM informant if it's present (and restart, on failure)
+pub fn spawn_vm_informant_if_present() -> Result<Option<thread::JoinHandle<()>>> {
+    let exists = Path::new(VM_INFORMANT_PATH)
+        .try_exists()
+        .context("could not check if path exists")?;
+
+    if !exists {
+        return Ok(None);
+    }
+
+    Ok(Some(
+        thread::Builder::new()
+            .name("run-vm-informant".into())
+            .spawn(move || run_informant())?,
+    ))
+}
+
+fn run_informant() -> ! {
+    let restart_wait = Duration::from_millis(RESTART_INFORMANT_AFTER_MILLIS);
+
+    info!("starting VM informant");
+
+    loop {
+        let mut cmd = process::Command::new(VM_INFORMANT_PATH);
+        // Block on subprocess:
+        let result = cmd.status();
+
+        match result {
+            Err(e) => warn!("failed to run VM informant at {VM_INFORMANT_PATH:?}: {e}"),
+            Ok(status) if !status.success() => {
+                warn!("{VM_INFORMANT_PATH} exited with code {status:?}, retrying")
+            }
+            Ok(_) => info!("{VM_INFORMANT_PATH} ended gracefully (unexpectedly). Retrying"),
+        }
+
+        // Wait before retrying
+        thread::sleep(restart_wait);
+    }
+}

compute_tools/src/lib.rs

@@ -8,6 +8,7 @@ pub mod http;
 #[macro_use]
 pub mod logger;
 pub mod compute;
+pub mod informant;
 pub mod monitor;
 pub mod params;
 pub mod pg_helpers;

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;
 
@@ -52,10 +52,16 @@ fn watch_compute_activity(compute: &ComputeNode) {
                     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)),
@@ -74,10 +80,8 @@ 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;
                     }
                 }

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

@@ -1,18 +1,19 @@
 use std::fmt::Write;
+use std::fs;
 use std::fs::File;
 use std::io::{BufRead, BufReader};
-use std::net::{SocketAddr, TcpStream};
 use std::os::unix::fs::PermissionsExt;
 use std::path::Path;
 use std::process::Child;
-use std::str::FromStr;
+use std::time::{Duration, Instant};
-use std::{fs, thread, time};
 
 use anyhow::{bail, Result};
+use notify::{RecursiveMode, Watcher};
 use postgres::{Client, Transaction};
 use serde::Deserialize;
+use tracing::{debug, instrument};
 
-const POSTGRES_WAIT_TIMEOUT: u64 = 60 * 1000; // milliseconds
+const POSTGRES_WAIT_TIMEOUT: Duration = Duration::from_millis(60 * 1000); // milliseconds
 
 /// Rust representation of Postgres role info with only those fields
 /// that matter for us.
@@ -65,7 +66,7 @@ impl GenericOption {
             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",
+                "wal_acceptor_connection_timeout" => "neon.safekeeper_connection_timeout",
                 it => it,
             };
 
@@ -119,16 +120,9 @@ 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,
-        }
     }
 }
 
@@ -136,8 +130,8 @@ impl Role {
     /// Serialize a list of role parameters into a Postgres-acceptable
     /// string of arguments.
     pub 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();
 
@@ -161,6 +155,14 @@ impl Role {
 }
 
 impl Database {
+    pub fn new(name: PgIdent, owner: PgIdent) -> Self {
+        Self {
+            name,
+            owner,
+            options: None,
+        }
+    }
+
     /// 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
@@ -168,7 +170,7 @@ impl Database {
     /// it may require a proper quoting too.
     pub fn to_pg_options(&self) -> String {
         let mut params: String = self.options.as_pg_options();
-        write!(params, " OWNER {}", &self.owner.quote())
+        write!(params, " OWNER {}", &self.owner.pg_quote())
             .expect("String is documented to not to error during write operations");
 
         params
@@ -179,18 +181,17 @@ impl Database {
 /// intended to be used for DB / role names.
 pub type PgIdent = String;
 
-/// Generic trait used to provide quoting for strings used in the
+/// Generic trait used to provide quoting / encoding for strings used in the
-/// Postgres SQL queries. Currently used only to implement quoting
+/// Postgres SQL queries and DATABASE_URL.
-/// of identifiers, but could be used for literals in the future.
+pub trait Escaping {
-pub trait PgQuote {
+    fn pg_quote(&self) -> String;
-    fn quote(&self) -> String;
 }
 
-impl PgQuote for PgIdent {
+impl Escaping for PgIdent {
     /// This is intended to mimic Postgres quote_ident(), but for simplicity it
-    /// always quotes provided string with `""` and escapes every `"`. Not idempotent,
+    /// always quotes provided string with `""` and escapes every `"`.
-    /// i.e. if string is already escaped it will be escaped again.
+    /// **Not idempotent**, i.e. if string is already escaped it will be escaped again.
-    fn quote(&self) -> String {
+    fn pg_quote(&self) -> String {
         let result = format!("\"{}\"", self.replace('"', "\"\""));
         result
     }
@@ -220,62 +221,119 @@ pub fn get_existing_dbs(client: &mut Client) -> Result<Vec<Database>> {
             &[],
         )?
         .iter()
-        .map(|row| Database {
+        .map(|row| Database::new(row.get("datname"), row.get("owner")))
-            name: row.get("datname"),
-            owner: row.get("owner"),
-            options: None,
-        })
         .collect();
 
     Ok(postgres_dbs)
 }
 
-/// Wait for Postgres to become ready to accept connections:
+/// Wait for Postgres to become ready to accept connections. It's ready to
-/// - state should be `ready` in the `pgdata/postmaster.pid`
+/// accept connections when the state-field in `pgdata/postmaster.pid` says
-/// - and we should be able to connect to 127.0.0.1:5432
+/// 'ready'.
-pub fn wait_for_postgres(pg: &mut Child, port: &str, pgdata: &Path) -> Result<()> {
+#[instrument(skip(pg))]
+pub fn wait_for_postgres(pg: &mut Child, pgdata: &Path) -> Result<()> {
     let pid_path = pgdata.join("postmaster.pid");
-    let mut slept: u64 = 0; // ms
-    let pause = time::Duration::from_millis(100);
 
-    let timeout = time::Duration::from_millis(10);
+    // PostgreSQL writes line "ready" to the postmaster.pid file, when it has
-    let addr = SocketAddr::from_str(&format!("127.0.0.1:{}", port)).unwrap();
+    // completed initialization and is ready to accept connections. We want to
+    // react quickly and perform the rest of our initialization as soon as
+    // PostgreSQL starts accepting connections. Use 'notify' to be notified
+    // whenever the PID file is changed, and whenever it changes, read it to
+    // check if it's now "ready".
+    //
+    // You cannot actually watch a file before it exists, so we first watch the
+    // data directory, and once the postmaster.pid file appears, we switch to
+    // watch the file instead. We also wake up every 100 ms to poll, just in
+    // case we miss some events for some reason. Not strictly necessary, but
+    // better safe than sorry.
+    let (tx, rx) = std::sync::mpsc::channel();
+    let (mut watcher, rx): (Box<dyn Watcher>, _) = match notify::recommended_watcher(move |res| {
+        let _ = tx.send(res);
+    }) {
+        Ok(watcher) => (Box::new(watcher), rx),
+        Err(e) => {
+            match e.kind {
+                notify::ErrorKind::Io(os) if os.raw_os_error() == Some(38) => {
+                    // docker on m1 macs does not support recommended_watcher
+                    // but return "Function not implemented (os error 38)"
+                    // see https://github.com/notify-rs/notify/issues/423
+                    let (tx, rx) = std::sync::mpsc::channel();
 
-    loop {
+                    // let's poll it faster than what we check the results for (100ms)
-        // Sleep POSTGRES_WAIT_TIMEOUT at max (a bit longer actually if consider a TCP timeout,
+                    let config =
-        // but postgres starts listening almost immediately, even if it is not really
+                        notify::Config::default().with_poll_interval(Duration::from_millis(50));
-        // ready to accept connections).
+
-        if slept >= POSTGRES_WAIT_TIMEOUT {
+                    let watcher = notify::PollWatcher::new(
-            bail!("timed out while waiting for Postgres to start");
+                        move |res| {
+                            let _ = tx.send(res);
+                        },
+                        config,
+                    )?;
+
+                    (Box::new(watcher), rx)
+                }
+                _ => return Err(e.into()),
+            }
         }
+    };
 
+    watcher.watch(pgdata, RecursiveMode::NonRecursive)?;
+
+    let started_at = Instant::now();
+    let mut postmaster_pid_seen = false;
+    loop {
         if let Ok(Some(status)) = pg.try_wait() {
             // Postgres exited, that is not what we expected, bail out earlier.
             let code = status.code().unwrap_or(-1);
             bail!("Postgres exited unexpectedly with code {}", code);
         }
 
+        let res = rx.recv_timeout(Duration::from_millis(100));
+        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() {
+            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 {
+                debug!("postmaster.pid appeared");
+                watcher
+                    .unwatch(pgdata)
+                    .expect("Failed to remove pgdata dir watch");
+                watcher
+                    .watch(&pid_path, RecursiveMode::NonRecursive)
+                    .expect("Failed to add postmaster.pid file watch");
+                postmaster_pid_seen = true;
+            }
+
             let file = BufReader::new(file);
             let last_line = file.lines().last();
 
             // Pid file could be there and we could read it, but it could be empty, for example.
             if let Some(Ok(line)) = last_line {
                 let status = line.trim();
-                let can_connect = TcpStream::connect_timeout(&addr, timeout).is_ok();
+                debug!("last line of postmaster.pid: {status:?}");
 
                 // Now Postgres is ready to accept connections
-                if status == "ready" && can_connect {
+                if status == "ready" {
                     break;
                 }
             }
         }
 
-        thread::sleep(pause);
+        // Give up after POSTGRES_WAIT_TIMEOUT.
-        slept += 100;
+        let duration = started_at.elapsed();
+        if duration >= POSTGRES_WAIT_TIMEOUT {
+            bail!("timed out while waiting for Postgres to start");
+        }
     }
 
+    tracing::info!("PostgreSQL is now running, continuing to configure it");
+
     Ok(())
 }
 

compute_tools/src/spec.rs

@@ -1,9 +1,12 @@
+use std::collections::HashMap;
 use std::path::Path;
+use std::str::FromStr;
 
 use anyhow::Result;
-use log::{info, log_enabled, warn, Level};
+use postgres::config::Config;
 use postgres::{Client, NoTls};
 use serde::Deserialize;
+use tracing::{info, info_span, instrument, span_enabled, warn, Level};
 
 use crate::compute::ComputeNode;
 use crate::config;
@@ -20,6 +23,8 @@ pub struct ComputeSpec {
     /// Expected cluster state at the end of transition process.
     pub cluster: Cluster,
     pub delta_operations: Option<Vec<DeltaOp>>,
+
+    pub startup_tracing_context: Option<HashMap<String, String>>,
 }
 
 /// Cluster state seen from the perspective of the external tools
@@ -77,23 +82,25 @@ 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)
-    info!("postgres roles:");
+    if span_enabled!(Level::INFO) {
-    for r in &existing_roles {
+        info!("postgres roles:");
-        info_println!(
+        for r in &existing_roles {
-            "{} - {}:{}",
+            info!(
-            " ".repeat(27 + 5),
+                "    - {}:{}",
-            r.name,
+                r.name,
-            if r.encrypted_password.is_some() {
+                if r.encrypted_password.is_some() {
-                "[FILTERED]"
+                    "[FILTERED]"
-            } else {
+                } else {
-                "(null)"
+                    "(null)"
-            }
+                }
-        );
+            );
+        }
     }
 
     // Process delta operations first
@@ -115,8 +122,8 @@ pub fn handle_roles(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
                     if existing_roles.iter().any(|r| r.name == op.name) {
                         let query: String = format!(
                             "ALTER ROLE {} RENAME TO {}",
-                            op.name.quote(),
+                            op.name.pg_quote(),
-                            new_name.quote()
+                            new_name.pg_quote()
                         );
 
                         warn!("renaming role '{}' to '{}'", op.name, new_name);
@@ -134,58 +141,80 @@ 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 {
-                let mut query: String = format!("ALTER ROLE {} ", name.quote());
+            RoleAction::None => {}
-                info_print!(" -> update");
+            RoleAction::Update => {
-
+                let mut query: String = format!("ALTER ROLE {} ", name.pg_quote());
                 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());
-            let mut query: String = format!("CREATE ROLE {} ", name.quote());
+                info!("role create query: '{}'", &query);
-            info!("role create query: '{}'", &query);
+                query.push_str(&role.to_pg_options());
-            info_print!(" -> create");
+                xact.execute(query.as_str(), &[])?;
 
-            query.push_str(&role.to_pg_options());
+                let grant_query = format!(
-            xact.execute(query.as_str(), &[])?;
+                    "GRANT pg_read_all_data, pg_write_all_data TO {}",
-
+                    name.pg_quote()
-            let grant_query = format!(
+                );
-                "GRANT pg_read_all_data, pg_write_all_data TO {}",
+                xact.execute(grant_query.as_str(), &[])?;
-                name.quote()
+                info!("role grant query: '{}'", &grant_query);
-            );
+            }
-            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()?;
@@ -194,33 +223,43 @@ pub fn handle_roles(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
 }
 
 /// Reassign all dependent objects and delete requested roles.
+#[instrument(skip_all)]
 pub fn handle_role_deletions(node: &ComputeNode, client: &mut Client) -> Result<()> {
-    let spec = &node.spec;
+    if let Some(ops) = &node.spec.delta_operations {
-
+        // First, reassign all dependent objects to db owners.
-    // First, reassign all dependent objects to db owners.
-    if let Some(ops) = &spec.delta_operations {
         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
+            // 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(node, &op.name)?;
             }
         }
-    }
 
-    // Second, proceed with role deletions.
+        // 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
             if op.action == "delete_role" {
-                let query: String = format!("DROP ROLE IF EXISTS {}", &op.name.quote());
+                let query: String = format!("DROP ROLE IF EXISTS {}", &op.name.pg_quote());
 
                 warn!("deleting role '{}'", &op.name);
                 xact.execute(query.as_str(), &[])?;
             }
         }
+        xact.commit()?;
     }
 
     Ok(())
@@ -230,17 +269,16 @@ pub fn handle_role_deletions(node: &ComputeNode, client: &mut Client) -> Result<
 fn reassign_owned_objects(node: &ComputeNode, role_name: &PgIdent) -> Result<()> {
     for db in &node.spec.cluster.databases {
         if db.owner != *role_name {
-            let mut connstr = node.connstr.clone();
+            let mut conf = Config::from_str(node.connstr.as_str())?;
-            // database name is always the last and the only component of the path
+            conf.dbname(&db.name);
-            connstr.set_path(&db.name);
 
-            let mut client = Client::connect(connstr.as_str(), NoTls)?;
+            let mut client = conf.connect(NoTls)?;
 
             // This will reassign all dependent objects to the db owner
             let reassign_query = format!(
                 "REASSIGN OWNED BY {} TO {}",
-                role_name.quote(),
+                role_name.pg_quote(),
-                db.owner.quote()
+                db.owner.pg_quote()
             );
             info!(
                 "reassigning objects owned by '{}' in db '{}' to '{}'",
@@ -249,7 +287,7 @@ fn reassign_owned_objects(node: &ComputeNode, role_name: &PgIdent) -> Result<()>
             client.simple_query(&reassign_query)?;
 
             // This now will only drop privileges of the role
-            let drop_query = format!("DROP OWNED BY {}", role_name.quote());
+            let drop_query = format!("DROP OWNED BY {}", role_name.pg_quote());
             client.simple_query(&drop_query)?;
         }
     }
@@ -262,13 +300,16 @@ 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)
-    info!("postgres databases:");
+    if span_enabled!(Level::INFO) {
-    for r in &existing_dbs {
+        info!("postgres databases:");
-        info_println!("{} - {}:{}", " ".repeat(27 + 5), r.name, r.owner);
+        for r in &existing_dbs {
+            info!("    {}:{}", r.name, r.owner);
+        }
     }
 
     // Process delta operations first
@@ -279,7 +320,7 @@ pub fn handle_databases(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
                 // We do not check either DB exists or not,
                 // Postgres will take care of it for us
                 "delete_db" => {
-                    let query: String = format!("DROP DATABASE IF EXISTS {}", &op.name.quote());
+                    let query: String = format!("DROP DATABASE IF EXISTS {}", &op.name.pg_quote());
 
                     warn!("deleting database '{}'", &op.name);
                     client.execute(query.as_str(), &[])?;
@@ -291,8 +332,8 @@ pub fn handle_databases(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
                     if existing_dbs.iter().any(|r| r.name == op.name) {
                         let query: String = format!(
                             "ALTER DATABASE {} RENAME TO {}",
-                            op.name.quote(),
+                            op.name.pg_quote(),
-                            new_name.quote()
+                            new_name.pg_quote()
                         );
 
                         warn!("renaming database '{}' to '{}'", op.name, new_name);
@@ -311,39 +352,60 @@ 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('"') {
-                db.owner.quote()
+                db.owner.pg_quote()
             } else {
                 db.owner.clone()
             };
 
             if new_owner != r.owner {
-                let query: String = format!(
+                // Update the owner
-                    "ALTER DATABASE {} OWNER TO {}",
+                DatabaseAction::Update
-                    name.quote(),
+            } else {
-                    db.owner.quote()
+                DatabaseAction::None
-                );
-                info_print!(" -> update");
-
-                client.execute(query.as_str(), &[])?;
             }
         } else {
-            let mut query: String = format!("CREATE DATABASE {} ", name.quote());
+            DatabaseAction::Create
-            info_print!(" -> create");
+        };
 
-            query.push_str(&db.to_pg_options());
+        match action {
-            client.execute(query.as_str(), &[])?;
+            DatabaseAction::None => {}
+            DatabaseAction::Update => {
+                let query: String = format!(
+                    "ALTER DATABASE {} OWNER TO {}",
+                    name.pg_quote(),
+                    db.owner.pg_quote()
+                );
+                let _guard = info_span!("executing", query).entered();
+                client.execute(query.as_str(), &[])?;
+            }
+            DatabaseAction::Create => {
+                let mut query: String = format!("CREATE DATABASE {} ", name.pg_quote());
+                query.push_str(&db.to_pg_options());
+                let _guard = info_span!("executing", query).entered();
+                client.execute(query.as_str(), &[])?;
+            }
+        };
+
+        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);
         }
-
-        info_print!("\n");
     }
 
     Ok(())
@@ -351,6 +413,7 @@ 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.
+#[instrument(skip_all)]
 pub fn handle_grants(node: &ComputeNode, client: &mut Client) -> Result<()> {
     let spec = &node.spec;
 
@@ -366,7 +429,7 @@ pub fn handle_grants(node: &ComputeNode, client: &mut Client) -> Result<()> {
         .cluster
         .roles
         .iter()
-        .map(|r| r.name.quote())
+        .map(|r| r.name.pg_quote())
         .collect::<Vec<_>>();
 
     for db in &spec.cluster.databases {
@@ -374,7 +437,7 @@ pub fn handle_grants(node: &ComputeNode, client: &mut Client) -> Result<()> {
 
         let query: String = format!(
             "GRANT CREATE ON DATABASE {} TO {}",
-            dbname.quote(),
+            dbname.pg_quote(),
             roles.join(", ")
         );
         info!("grant query {}", &query);
@@ -385,12 +448,11 @@ pub fn handle_grants(node: &ComputeNode, client: &mut Client) -> Result<()> {
     // Do some per-database access adjustments. We'd better do this at db creation time,
     // but CREATE DATABASE isn't transactional. So we cannot create db + do some grants
     // atomically.
-    let mut db_connstr = node.connstr.clone();
     for db in &node.spec.cluster.databases {
-        // database name is always the last and the only component of the path
+        let mut conf = Config::from_str(node.connstr.as_str())?;
-        db_connstr.set_path(&db.name);
+        conf.dbname(&db.name);
 
-        let mut db_client = Client::connect(db_connstr.as_str(), NoTls)?;
+        let mut db_client = conf.connect(NoTls)?;
 
         // This will only change ownership on the schema itself, not the objects
         // inside it. Without it owner of the `public` schema will be `cloud_admin`
@@ -419,9 +481,36 @@ pub fn handle_grants(node: &ComputeNode, client: &mut Client) -> Result<()> {
                     END IF;\n\
                 END\n\
             $$;",
-            db.owner.quote()
+            db.owner.pg_quote()
         );
         db_client.simple_query(&alter_query)?;
+
+        // Explicitly grant CREATE ON SCHEMA PUBLIC to the web_access user.
+        // This is needed because since postgres 15 this privilege is removed by default.
+        let grant_query = "DO $$\n\
+                BEGIN\n\
+                    IF EXISTS(\n\
+                        SELECT nspname\n\
+                        FROM pg_catalog.pg_namespace\n\
+                        WHERE nspname = 'public'\n\
+                    ) AND\n\
+                    current_setting('server_version_num')::int/10000 >= 15\n\
+                    THEN\n\
+                        IF EXISTS(\n\
+                            SELECT rolname\n\
+                            FROM pg_catalog.pg_roles\n\
+                            WHERE rolname = 'web_access'\n\
+                        )\n\
+                        THEN\n\
+                            GRANT CREATE ON SCHEMA public TO web_access;\n\
+                        END IF;\n\
+                    END IF;\n\
+                END\n\
+            $$;"
+        .to_string();
+
+        info!("grant query for db {} : {}", &db.name, &grant_query);
+        db_client.simple_query(&grant_query)?;
     }
 
     Ok(())

compute_tools/tests/pg_helpers_tests.rs

@@ -33,9 +33,38 @@ mod pg_helpers_tests {
     }
 
     #[test]
-    fn quote_ident() {
+    fn ident_pg_quote() {
         let ident: PgIdent = PgIdent::from("\"name\";\\n select 1;");
 
-        assert_eq!(ident.quote(), "\"\"\"name\"\";\\n select 1;\"");
+        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

@@ -1,25 +1,31 @@
 [package]
 name = "control_plane"
 version = "0.1.0"
-edition = "2021"
+edition.workspace = true
+license.workspace = true
 
 [dependencies]
-clap = "3.0"
+anyhow.workspace = true
-comfy-table = "5.0.1"
+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 = "1.12.0"
+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_with.workspace = true
-thiserror = "1"
+tar.workspace = true
-nix = "0.23"
+thiserror.workspace = true
-reqwest = { version = "0.11", default-features = false, features = ["blocking", "json", "rustls-tls"] }
+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.workspace = true
+safekeeper_api.workspace = true
+postgres_connection.workspace = true
+storage_broker.workspace = true
+utils.workspace = true
 
-pageserver = { path = "../pageserver" }
+workspace_hack.workspace = true
-safekeeper = { path = "../safekeeper" }
-utils = { path = "../libs/utils" }
-workspace_hack = { version = "0.1", path = "../workspace_hack" }

control_plane/simple.conf

@@ -10,5 +10,5 @@ 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/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/compute.rs

@@ -12,15 +12,14 @@ 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
@@ -45,7 +44,7 @@ impl ComputeControlPlane {
         let mut nodes = BTreeMap::default();
         let pgdatadirspath = &env.pg_data_dirs_path();
 
-        for tenant_dir in fs::read_dir(&pgdatadirspath)
+        for tenant_dir in fs::read_dir(pgdatadirspath)
             .with_context(|| format!("failed to list {}", pgdatadirspath.display()))?
         {
             let tenant_dir = tenant_dir?;
@@ -68,8 +67,8 @@ impl ComputeControlPlane {
     fn get_port(&mut self) -> u16 {
         1 + self
             .nodes
-            .iter()
+            .values()
-            .map(|(_name, node)| node.address.port())
+            .map(|node| node.address.port())
             .max()
             .unwrap_or(self.base_port)
     }
@@ -183,18 +182,18 @@ impl PostgresNode {
     }
 
     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 +201,7 @@ 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 +261,7 @@ 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()
@@ -282,9 +281,7 @@ impl PostgresNode {
     fn setup_pg_conf(&self, auth_type: AuthType) -> 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");
@@ -302,21 +299,22 @@ impl PostgresNode {
 
         // Configure the node 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
             //
-            // $ZENITH_AUTH_TOKEN will be replaced with value from environment
+            // $NEON_AUTH_TOKEN will be replaced with value from environment
             // variable during compute pg startup. It is done this way because
             // otherwise user will be able to retrieve the value using SHOW
             // command or pg_settings
             let password = if let AuthType::NeonJWT = auth_type {
-                "$ZENITH_AUTH_TOKEN"
+                "$NEON_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
+            // Also note that not all parameters are supported here. Because in compute we substitute $NEON_AUTH_TOKEN
             // We parse this string and build it back with token from env var, and for simplicity rebuild
             // uses only needed variables namely host, port, user, password.
             format!("postgresql://no_user:{password}@{host}:{port}")
@@ -324,6 +322,9 @@ impl PostgresNode {
         conf.append("shared_preload_libraries", "neon");
         conf.append_line("");
         conf.append("neon.pageserver_connstring", &pageserver_connstr);
+        if let AuthType::NeonJWT = auth_type {
+            conf.append("neon.safekeeper_token_env", "$NEON_AUTH_TOKEN");
+        }
         conf.append("neon.tenant_id", &self.tenant_id.to_string());
         conf.append("neon.timeline_id", &self.timeline_id.to_string());
         if let Some(lsn) = self.lsn {
@@ -345,7 +346,7 @@ 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() {
@@ -422,7 +423,7 @@ impl PostgresNode {
     }
 
     fn pg_ctl(&self, args: &[&str], auth_token: &Option<String>) -> Result<()> {
-        let pg_ctl_path = self.env.pg_bin_dir(self.pg_version).join("pg_ctl");
+        let pg_ctl_path = self.env.pg_bin_dir(self.pg_version)?.join("pg_ctl");
         let mut cmd = Command::new(pg_ctl_path);
         cmd.args(
             [
@@ -440,14 +441,14 @@ 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(),
         );
         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")?;
@@ -477,7 +478,7 @@ 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
@@ -513,7 +514,7 @@ impl PostgresNode {
                 "Destroying postgres data directory '{}'",
                 self.pgdata().to_str().unwrap()
             );
-            fs::remove_dir_all(&self.pgdata())?;
+            fs::remove_dir_all(self.pgdata())?;
         } else {
             self.pg_ctl(&["stop"], &None)?;
         }

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

@@ -4,12 +4,16 @@
 //! script which will use local paths.
 
 use anyhow::{bail, ensure, Context};
+
 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::{
@@ -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
-            })
     }
 }
 
@@ -201,37 +164,41 @@ 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 storage_broker_bin(&self) -> PathBuf {
+        self.neon_distrib_dir.join("storage_broker")
     }
 
     pub fn pg_data_dirs_path(&self) -> PathBuf {
@@ -329,11 +296,6 @@ 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 +384,10 @@ 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"] {
@@ -437,7 +399,7 @@ impl LocalEnv {
             }
         }
 
-        fs::create_dir(&base_path)?;
+        fs::create_dir(base_path)?;
 
         // generate keys for jwt
         // openssl genrsa -out private_key.pem 2048
@@ -446,7 +408,7 @@ impl LocalEnv {
             private_key_path = base_path.join("auth_private_key.pem");
             let keygen_output = Command::new("openssl")
                 .arg("genrsa")
-                .args(&["-out", private_key_path.to_str().unwrap()])
+                .args(["-out", private_key_path.to_str().unwrap()])
                 .arg("2048")
                 .stdout(Stdio::null())
                 .output()
@@ -463,10 +425,10 @@ impl LocalEnv {
             // openssl rsa -in private_key.pem -pubout -outform PEM -out public_key.pem
             let keygen_output = Command::new("openssl")
                 .arg("rsa")
-                .args(&["-in", private_key_path.to_str().unwrap()])
+                .args(["-in", private_key_path.to_str().unwrap()])
                 .arg("-pubout")
-                .args(&["-outform", "PEM"])
+                .args(["-outform", "PEM"])
-                .args(&["-out", public_key_path.to_str().unwrap()])
+                .args(["-out", public_key_path.to_str().unwrap()])
                 .stdout(Stdio::null())
                 .output()
                 .context("failed to generate auth private key")?;
@@ -511,8 +473,8 @@ 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 pageserver_api::models::{
-use nix::sys::signal::{kill, Signal};
-use nix::unistd::Pid;
-use pageserver::http::models::{
     TenantConfigRequest, TenantCreateRequest, TenantInfo, TimelineCreateRequest, TimelineInfo,
 };
-use postgres::{Config, NoTls};
+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 +79,26 @@ pub struct PageServerNode {
 
 impl PageServerNode {
     pub fn from_env(env: &LocalEnv) -> PageServerNode {
+        let (host, port) = parse_host_port(&env.pageserver.listen_pg_addr)
+            .expect("Unable to parse listen_pg_addr");
+        let port = port.unwrap_or(5432);
         let password = if env.pageserver.auth_type == AuthType::NeonJWT {
-            &env.pageserver.auth_token
+            Some(env.pageserver.auth_token.clone())
         } else {
-            ""
+            None
         };
 
         Self {
-            pg_connection_config: Self::pageserver_connection_config(
+            pg_connection_config: PgConnectionConfig::new_host_port(host, port)
-                password,
+                .set_password(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!(
@@ -128,155 +113,149 @@ impl PageServerNode {
         );
         let listen_pg_addr_param =
             format!("listen_pg_addr='{}'", self.env.pageserver.listen_pg_addr);
-        let broker_endpoints_param = format!(
+        let broker_endpoint_param = format!("broker_endpoint='{}'", self.env.broker.client_url());
-            "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 mut overrides = vec![
-        init_config_overrides.push(&id);
+            id,
-        init_config_overrides.push(&pg_distrib_dir_param);
+            pg_distrib_dir_param,
-        init_config_overrides.push(&authg_type_param);
+            authg_type_param,
-        init_config_overrides.push(&listen_http_addr_param);
+            listen_http_addr_param,
-        init_config_overrides.push(&listen_pg_addr_param);
+            listen_pg_addr_param,
-        init_config_overrides.push(&broker_endpoints_param);
+            broker_endpoint_param,
-
+        ];
-        if let Some(broker_etcd_prefix_param) = broker_etcd_prefix_param.as_deref() {
-            init_config_overrides.push(broker_etcd_prefix_param);
-        }
 
         if self.env.pageserver.auth_type != AuthType::Trust {
-            init_config_overrides.push("auth_validation_public_key_path='auth_public_key.pem'");
+            overrides.push("auth_validation_public_key_path='auth_public_key.pem'".to_owned());
         }
-
+        overrides
-        self.start_node(&init_config_overrides, &self.env.base_data_dir, true)?;
-        let init_result = self
-            .try_init_timeline(create_tenant, initial_timeline_id, pg_version)
-            .context("Failed to create initial tenant and timeline for pageserver");
-        match &init_result {
-            Ok(initial_timeline_id) => {
-                println!("Successfully initialized timeline {initial_timeline_id}")
-            }
-            Err(e) => eprintln!("{e:#}"),
-        }
-        self.stop(false)?;
-        init_result
     }
 
-    fn try_init_timeline(
+    /// Initializes a pageserver node by creating its config with the overrides provided.
-        &self,
+    pub fn initialize(&self, config_overrides: &[&str]) -> anyhow::Result<()> {
-        new_tenant_id: Option<TenantId>,
+        // First, run `pageserver --init` and wait for it to write a config into FS and exit.
-        new_timeline_id: Option<TimelineId>,
+        self.pageserver_init(config_overrides).with_context(|| {
-        pg_version: u32,
+            format!(
-    ) -> anyhow::Result<TimelineId> {
+                "Failed to run init for pageserver node {}",
-        let initial_tenant_id = self.tenant_create(new_tenant_id, HashMap::new())?;
+                self.env.pageserver.id,
-        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()
-                )
-            })?,
-        ];
 
+        let init_output = Command::new(self.env.pageserver_bin())
+            .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}"))?;
+
+        anyhow::ensure!(
+            init_output.status.success(),
+            "Pageserver init for node {} did not finish successfully, stdout: {}, stderr: {}",
+            node_id,
+            String::from_utf8_lossy(&init_output.stdout),
+            String::from_utf8_lossy(&init_output.stderr),
+        );
+
+        Ok(())
+    }
+
+    fn start_node(&self, config_overrides: &[&str], update_config: bool) -> anyhow::Result<Child> {
+        let mut overrides = self.neon_local_overrides();
+        overrides.extend(config_overrides.iter().map(|&c| c.to_owned()));
+
+        let datadir = self.repo_path();
+        print!(
+            "Starting pageserver node {} at '{}' in {:?}",
+            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("--update-config");
+            args.push(Cow::Borrowed("--update-config"));
         }
 
-        for config_override in config_overrides {
+        background_process::start_process(
-            args.extend(["-c", config_override]);
+            "pageserver",
+            &datadir,
+            &self.env.pageserver_bin(),
+            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));
         }
 
-        let mut cmd = Command::new(self.env.pageserver_bin()?);
+        args
-        let mut filled_cmd = fill_rust_env_vars(cmd.args(&args).arg("--daemonize"));
+    }
-        filled_cmd = fill_aws_secrets_vars(filled_cmd);
 
-        if !filled_cmd.status()?.success() {
+    fn pageserver_env_variables(&self) -> anyhow::Result<Vec<(String, String)>> {
-            bail!(
+        Ok(if self.env.pageserver.auth_type != AuthType::Trust {
-                "Pageserver failed to start. See console output and '{}' for details.",
+            // Generate a token to connect from the pageserver to a safekeeper
-                datadir.join("pageserver.log").display()
+            let token = self
-            );
+                .env
-        }
+                .generate_auth_token(&Claims::new(None, Scope::SafekeeperData))?;
-
+            vec![("NEON_AUTH_TOKEN".to_owned(), token)]
-        // It takes a while for the page server to start up. Wait until it is
+        } else {
-        // open for business.
+            Vec::new()
-        const RETRIES: i8 = 15;
+        })
-        for retries in 1..RETRIES {
-            match self.check_status() {
-                Ok(()) => {
-                    println!("\nPageserver started");
-                    return Ok(());
-                }
-                Err(err) => {
-                    match err {
-                        PageserverHttpError::Transport(err) => {
-                            if err.is_connect() && retries < 5 {
-                                print!(".");
-                                io::stdout().flush().unwrap();
-                            } else {
-                                if retries == 5 {
-                                    println!() // put a line break after dots for second message
-                                }
-                                println!("Pageserver not responding yet, err {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");
     }
 
     ///
@@ -288,69 +267,18 @@ 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
-        for i in 0..600 {
-            let signal = None; // Send no signal, just get the error code
-            match kill(pid, signal) {
-                Ok(_) => (), // Process exists, keep waiting
-                Err(Errno::ESRCH) => {
-                    // Process not found, we're done
-                    println!("done!");
-                    return Ok(());
-                }
-                Err(err) => bail!(
-                    "Failed to send signal to pageserver with pid {}: {}",
-                    pid,
-                    err.desc()
-                ),
-            };
-
-            if i % 10 == 0 {
-                print!(".");
-                io::stdout().flush().unwrap();
-            }
-            thread::sleep(Duration::from_millis(100));
-        }
-
-        bail!("Failed to stop pageserver with pid {pid}");
     }
 
     pub fn page_server_psql(&self, sql: &str) -> Vec<postgres::SimpleQueryMessage> {
-        let mut client = self.pg_connection_config.connect(NoTls).unwrap();
+        let mut client = self.pg_connection_config.connect_no_tls().unwrap();
 
         println!("Pageserver query: '{sql}'");
         client.simple_query(sql).unwrap()
     }
 
     pub fn page_server_psql_client(&self) -> result::Result<postgres::Client, postgres::Error> {
-        self.pg_connection_config.connect(NoTls)
+        self.pg_connection_config.connect_no_tls()
     }
 
     fn http_request<U: IntoUrl>(&self, method: Method, url: U) -> RequestBuilder {
@@ -419,6 +347,11 @@ 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")?,
         };
         if !settings.is_empty() {
             bail!("Unrecognized tenant settings: {settings:?}")
@@ -481,6 +414,11 @@ 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")?,
             })
             .send()?
             .error_from_body()?;
@@ -549,7 +487,7 @@ 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.pg_connection_config.connect_no_tls().unwrap();
 
         // Init base reader
         let (start_lsn, base_tarfile_path) = base;

control_plane/src/safekeeper.rs

@@ -1,28 +1,21 @@
 use std::io::Write;
 use std::path::PathBuf;
-use std::process::Command;
+use std::process::Child;
 use std::sync::Arc;
-use std::time::Duration;
+use std::{io, result};
-use std::{io, result, thread};
 
-use anyhow::bail;
+use anyhow::Context;
-use nix::errno::Errno;
+use postgres_connection::PgConnectionConfig;
-use nix::sys::signal::{kill, Signal};
-use nix::unistd::Pid;
-use postgres::Config;
 use reqwest::blocking::{Client, RequestBuilder, Response};
 use reqwest::{IntoUrl, Method};
-use safekeeper::http::models::TimelineCreateRequest;
 use thiserror::Error;
-use utils::{
+use utils::{http::error::HttpErrorBody, id::NodeId};
-    connstring::connection_address,
-    http::error::HttpErrorBody,
-    id::{NodeId, TenantId, TimelineId},
-};
 
-use crate::local_env::{LocalEnv, SafekeeperConf};
+use crate::pageserver::PageServerNode;
-use crate::storage::PageServerNode;
+use crate::{
-use crate::{fill_aws_secrets_vars, fill_rust_env_vars, read_pidfile};
+    background_process,
+    local_env::{LocalEnv, SafekeeperConf},
+};
 
 #[derive(Error, Debug)]
 pub enum SafekeeperHttpError {
@@ -68,7 +61,7 @@ pub struct SafekeeperNode {
 
     pub conf: SafekeeperConf,
 
-    pub pg_connection_config: Config,
+    pub pg_connection_config: PgConnectionConfig,
     pub env: LocalEnv,
     pub http_client: Client,
     pub http_base_url: String,
@@ -92,15 +85,12 @@ impl SafekeeperNode {
     }
 
     /// Construct libpq connection string for connecting to this safekeeper.
-    fn safekeeper_connection_config(port: u16) -> Config {
+    fn safekeeper_connection_config(port: u16) -> PgConnectionConfig {
-        // TODO safekeeper authentication not implemented yet
+        PgConnectionConfig::new_host_port(url::Host::parse("127.0.0.1").unwrap(), port)
-        format!("postgresql://no_user@127.0.0.1:{}/no_db", port)
-            .parse()
-            .unwrap()
     }
 
     pub fn datadir_path_by_id(env: &LocalEnv, sk_id: NodeId) -> PathBuf {
-        env.safekeeper_data_dir(format!("sk{}", sk_id).as_ref())
+        env.safekeeper_data_dir(&format!("sk{sk_id}"))
     }
 
     pub fn datadir_path(&self) -> PathBuf {
@@ -111,92 +101,74 @@ impl SafekeeperNode {
         self.datadir_path().join("safekeeper.pid")
     }
 
-    pub fn start(&self) -> anyhow::Result<()> {
+    pub fn start(&self) -> anyhow::Result<Child> {
         print!(
             "Starting safekeeper at '{}' in '{}'",
-            connection_address(&self.pg_connection_config),
+            self.pg_connection_config.raw_address(),
             self.datadir_path().display()
         );
         io::stdout().flush().unwrap();
 
         let listen_pg = format!("127.0.0.1:{}", self.conf.pg_port);
         let listen_http = format!("127.0.0.1:{}", self.conf.http_port);
+        let id = self.id;
+        let datadir = self.datadir_path();
 
-        let mut cmd = Command::new(self.env.safekeeper_bin()?);
+        let id_string = id.to_string();
-        fill_rust_env_vars(
+        let mut args = vec![
-            cmd.args(&["-D", self.datadir_path().to_str().unwrap()])
+            "-D",
-                .args(&["--id", self.id.to_string().as_ref()])
+            datadir.to_str().with_context(|| {
-                .args(&["--listen-pg", &listen_pg])
+                format!("Datadir path {datadir:?} cannot be represented as a unicode string")
-                .args(&["--listen-http", &listen_http])
+            })?,
-                .args(&["--recall", "1 second"])
+            "--id",
-                .arg("--daemonize"),
+            &id_string,
-        );
+            "--listen-pg",
+            &listen_pg,
+            "--listen-http",
+            &listen_http,
+        ];
         if !self.conf.sync {
-            cmd.arg("--no-sync");
+            args.push("--no-sync");
         }
 
-        let comma_separated_endpoints = self.env.etcd_broker.comma_separated_endpoints();
+        let broker_endpoint = format!("{}", self.env.broker.client_url());
-        if !comma_separated_endpoints.is_empty() {
+        args.extend(["--broker-endpoint", &broker_endpoint]);
-            cmd.args(&["--broker-endpoints", &comma_separated_endpoints]);
+
-        }
+        let mut backup_threads = String::new();
-        if let Some(prefix) = self.env.etcd_broker.broker_etcd_prefix.as_deref() {
-            cmd.args(&["--broker-etcd-prefix", prefix]);
-        }
         if let Some(threads) = self.conf.backup_threads {
-            cmd.args(&["--backup-threads", threads.to_string().as_ref()]);
+            backup_threads = threads.to_string();
+            args.extend(["--backup-threads", &backup_threads]);
+        } else {
+            drop(backup_threads);
         }
+
         if let Some(ref remote_storage) = self.conf.remote_storage {
-            cmd.args(&["--remote-storage", remote_storage]);
+            args.extend(["--remote-storage", remote_storage]);
         }
+
+        let key_path = self.env.base_data_dir.join("auth_public_key.pem");
         if self.conf.auth_enabled {
-            cmd.arg("--auth-validation-public-key-path");
+            args.extend([
-            // PathBuf is better be passed as is, not via `String`.
+                "--auth-validation-public-key-path",
-            cmd.arg(self.env.base_data_dir.join("auth_public_key.pem"));
+                key_path.to_str().with_context(|| {
+                    format!("Key path {key_path:?} cannot be represented as a unicode string")
+                })?,
+            ]);
         }
 
-        fill_aws_secrets_vars(&mut cmd);
+        background_process::start_process(
-
+            &format!("safekeeper {id}"),
-        if !cmd.status()?.success() {
+            &datadir,
-            bail!(
+            &self.env.safekeeper_bin(),
-                "Safekeeper failed to start. See '{}' for details.",
+            &args,
-                self.datadir_path().join("safekeeper.log").display()
+            [],
-            );
+            background_process::InitialPidFile::Expect(&self.pid_file()),
-        }
+            || match self.check_status() {
-
+                Ok(()) => Ok(true),
-        // It takes a while for the safekeeper to start up. Wait until it is
+                Err(SafekeeperHttpError::Transport(_)) => Ok(false),
-        // open for business.
+                Err(e) => Err(anyhow::anyhow!("Failed to check node status: {e}")),
-        const RETRIES: i8 = 15;
+            },
-        for retries in 1..RETRIES {
+        )
-            match self.check_status() {
-                Ok(_) => {
-                    println!("\nSafekeeper started");
-                    return Ok(());
-                }
-                Err(err) => {
-                    match err {
-                        SafekeeperHttpError::Transport(err) => {
-                            if err.is_connect() && retries < 5 {
-                                print!(".");
-                                io::stdout().flush().unwrap();
-                            } else {
-                                if retries == 5 {
-                                    println!() // put a line break after dots for second message
-                                }
-                                println!(
-                                    "Safekeeper not responding yet, err {} retrying ({})...",
-                                    err, retries
-                                );
-                            }
-                        }
-                        SafekeeperHttpError::Response(msg) => {
-                            bail!("safekeeper failed to start: {} ", msg)
-                        }
-                    }
-                    thread::sleep(Duration::from_secs(1));
-                }
-            }
-        }
-        bail!("safekeeper failed to start in {} seconds", RETRIES);
     }
 
     ///
@@ -208,63 +180,11 @@ impl SafekeeperNode {
     /// 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(
-        if !pid_file.exists() {
+            immediate,
-            println!("Safekeeper {} is already stopped", self.id);
+            &format!("safekeeper {}", self.id),
-            return Ok(());
+            &self.pid_file(),
-        }
+        )
-        let pid = read_pidfile(&pid_file)?;
-        let pid = Pid::from_raw(pid);
-
-        let sig = if immediate {
-            print!("Stopping safekeeper {} immediately..", self.id);
-            Signal::SIGQUIT
-        } else {
-            print!("Stopping safekeeper {} gracefully..", self.id);
-            Signal::SIGTERM
-        };
-        io::stdout().flush().unwrap();
-        match kill(pid, sig) {
-            Ok(_) => (),
-            Err(Errno::ESRCH) => {
-                println!(
-                    "Safekeeper with pid {} does not exist, but a PID file was found",
-                    pid
-                );
-                return Ok(());
-            }
-            Err(err) => bail!(
-                "Failed to send signal to safekeeper with pid {}: {}",
-                pid,
-                err.desc()
-            ),
-        }
-
-        // Wait until process is gone
-        for i in 0..600 {
-            let signal = None; // Send no signal, just get the error code
-            match kill(pid, signal) {
-                Ok(_) => (), // Process exists, keep waiting
-                Err(Errno::ESRCH) => {
-                    // Process not found, we're done
-                    println!("done!");
-                    return Ok(());
-                }
-                Err(err) => bail!(
-                    "Failed to send signal to pageserver with pid {}: {}",
-                    pid,
-                    err.desc()
-                ),
-            };
-
-            if i % 10 == 0 {
-                print!(".");
-                io::stdout().flush().unwrap();
-            }
-            thread::sleep(Duration::from_millis(100));
-        }
-
-        bail!("Failed to stop safekeeper with pid {}", pid);
     }
 
     fn http_request<U: IntoUrl>(&self, method: Method, url: U) -> RequestBuilder {
@@ -281,24 +201,4 @@ impl SafekeeperNode {
             .error_from_body()?;
         Ok(())
     }
-
-    pub fn timeline_create(
-        &self,
-        tenant_id: TenantId,
-        timeline_id: TimelineId,
-        peer_ids: Vec<NodeId>,
-    ) -> Result<()> {
-        Ok(self
-            .http_request(
-                Method::POST,
-                format!("{}/tenant/{}/timeline", self.http_base_url, tenant_id),
-            )
-            .json(&TimelineCreateRequest {
-                timeline_id,
-                peer_ids,
-            })
-            .send()?
-            .error_from_body()?
-            .json()?)
-    }
 }