fix Payload deser

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

@@ -183,7 +183,7 @@ runs:
       uses: actions/cache@v4
       with:
         path: ~/.cache/pypoetry/virtualenvs
-        key: v2-${{ runner.os }}-${{ runner.arch }}-python-deps-bookworm-${{ hashFiles('poetry.lock') }}
+        key: v2-${{ runner.os }}-${{ runner.arch }}-python-deps-${{ hashFiles('poetry.lock') }}
 
     - name: Store Allure test stat in the DB (new)
       if: ${{ !cancelled() && inputs.store-test-results-into-db == 'true' }}

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

@@ -88,7 +88,7 @@ runs:
       uses: actions/cache@v4
       with:
         path: ~/.cache/pypoetry/virtualenvs
-        key: v2-${{ runner.os }}-${{ runner.arch }}-python-deps-bookworm-${{ hashFiles('poetry.lock') }}
+        key: v2-${{ runner.os }}-${{ runner.arch }}-python-deps-${{ hashFiles('poetry.lock') }}
 
     - name: Install Python deps
       shell: bash -euxo pipefail {0}

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

@@ -124,28 +124,28 @@ jobs:
         uses: actions/cache@v4
         with:
           path: pg_install/v14
-          key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v14_rev.outputs.pg_rev }}-bookworm-${{ hashFiles('Makefile', 'Dockerfile.build-tools') }}
+          key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v14_rev.outputs.pg_rev }}-${{ hashFiles('Makefile', 'Dockerfile.build-tools') }}
 
       - name: Cache postgres v15 build
         id: cache_pg_15
         uses: actions/cache@v4
         with:
           path: pg_install/v15
-          key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v15_rev.outputs.pg_rev }}-bookworm-${{ hashFiles('Makefile', 'Dockerfile.build-tools') }}
+          key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v15_rev.outputs.pg_rev }}-${{ hashFiles('Makefile', 'Dockerfile.build-tools') }}
 
       - name: Cache postgres v16 build
         id: cache_pg_16
         uses: actions/cache@v4
         with:
           path: pg_install/v16
-          key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v16_rev.outputs.pg_rev }}-bookworm-${{ hashFiles('Makefile', 'Dockerfile.build-tools') }}
+          key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v16_rev.outputs.pg_rev }}-${{ hashFiles('Makefile', 'Dockerfile.build-tools') }}
 
       - name: Cache postgres v17 build
         id: cache_pg_17
         uses: actions/cache@v4
         with:
           path: pg_install/v17
-          key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v17_rev.outputs.pg_rev }}-bookworm-${{ hashFiles('Makefile', 'Dockerfile.build-tools') }}
+          key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v17_rev.outputs.pg_rev }}-${{ hashFiles('Makefile', 'Dockerfile.build-tools') }}
 
       - name: Build postgres v14
         if: steps.cache_pg_14.outputs.cache-hit != 'true'

.github/workflows/build-build-tools-image.yml

@@ -19,16 +19,9 @@ defaults:
   run:
     shell: bash -euo pipefail {0}
 
-# The initial idea was to prevent the waste of resources by not re-building the `build-tools` image
-# for the same tag in parallel workflow runs, and queue them to be skipped once we have
-# the first image pushed to Docker registry, but GitHub's concurrency mechanism is not working as expected.
-# GitHub can't have more than 1 job in a queue and removes the previous one, it causes failures if the dependent jobs.
-#
-# Ref https://github.com/orgs/community/discussions/41518
-#
-# concurrency:
-#   group: build-build-tools-image-${{ inputs.image-tag }}
-#   cancel-in-progress: false
+concurrency:
+  group: build-build-tools-image-${{ inputs.image-tag }}
+  cancel-in-progress: false
 
 # No permission for GITHUB_TOKEN by default; the **minimal required** set of permissions should be granted in each job.
 permissions: {}
@@ -43,7 +36,6 @@ jobs:
 
     strategy:
       matrix:
-        debian-version: [ bullseye, bookworm ]
         arch: [ x64, arm64 ]
 
     runs-on: ${{ fromJson(format('["self-hosted", "{0}"]', matrix.arch == 'arm64' && 'large-arm64' || 'large')) }}
@@ -82,22 +74,22 @@ jobs:
 
       - uses: docker/build-push-action@v6
         with:
-          file: Dockerfile.build-tools
           context: .
           provenance: false
           push: true
           pull: true
-          build-args: |
-            DEBIAN_VERSION=${{ matrix.debian-version }}
-          cache-from: type=registry,ref=cache.neon.build/build-tools:cache-${{ matrix.debian-version }}-${{ matrix.arch }}
-          cache-to: ${{ github.ref_name == 'main' && format('type=registry,ref=cache.neon.build/build-tools:cache-{0}-{1},mode=max', matrix.debian-version, matrix.arch) || '' }}
-          tags: |
-            neondatabase/build-tools:${{ inputs.image-tag }}-${{ matrix.debian-version }}-${{ matrix.arch }}
+          file: Dockerfile.build-tools
+          cache-from: type=registry,ref=cache.neon.build/build-tools:cache-${{ matrix.arch }}
+          cache-to: ${{ github.ref_name == 'main' && format('type=registry,ref=cache.neon.build/build-tools:cache-{0},mode=max', matrix.arch) || '' }}
+          tags: neondatabase/build-tools:${{ inputs.image-tag }}-${{ matrix.arch }}
 
   merge-images:
     needs: [ build-image ]
     runs-on: ubuntu-22.04
 
+    env:
+      IMAGE_TAG: ${{ inputs.image-tag }}
+
     steps:
       - uses: docker/login-action@v3
         with:
@@ -105,17 +97,7 @@ jobs:
           password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
 
       - name: Create multi-arch image
-        env:
-          DEFAULT_DEBIAN_VERSION: bullseye
-          IMAGE_TAG: ${{ inputs.image-tag }}
         run: |
-          for debian_version in bullseye bookworm; do
-            tags=("-t" "neondatabase/build-tools:${IMAGE_TAG}-${debian_version}")
-            if [ "${debian_version}" == "${DEFAULT_DEBIAN_VERSION}" ]; then
-              tags+=("-t" "neondatabase/build-tools:${IMAGE_TAG}")
-            fi
-
-            docker buildx imagetools create "${tags[@]}" \
-                                              neondatabase/build-tools:${IMAGE_TAG}-${debian_version}-x64 \
-                                              neondatabase/build-tools:${IMAGE_TAG}-${debian_version}-arm64
-          done
+          docker buildx imagetools create -t neondatabase/build-tools:${IMAGE_TAG} \
+                                             neondatabase/build-tools:${IMAGE_TAG}-x64 \
+                                             neondatabase/build-tools:${IMAGE_TAG}-arm64

.github/workflows/build_and_test.yml

@@ -92,7 +92,7 @@ jobs:
     needs: [ check-permissions, build-build-tools-image ]
     runs-on: [ self-hosted, small ]
     container:
-      image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
+      image: ${{ needs.build-build-tools-image.outputs.image }}
       credentials:
         username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
         password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
@@ -106,7 +106,7 @@ jobs:
         uses: actions/cache@v4
         with:
           path: ~/.cache/pypoetry/virtualenvs
-          key: v2-${{ runner.os }}-${{ runner.arch }}-python-deps-bookworm-${{ hashFiles('poetry.lock') }}
+          key: v2-${{ runner.os }}-${{ runner.arch }}-python-deps-${{ hashFiles('poetry.lock') }}
 
       - name: Install Python deps
         run: ./scripts/pysync
@@ -120,24 +120,6 @@ jobs:
       - name: Run mypy to check types
         run: poetry run mypy .
 
-  check-codestyle-jsonnet:
-    needs: [ check-permissions, build-build-tools-image ]
-    runs-on: [ self-hosted, small ]
-    container:
-      image: ${{ needs.build-build-tools-image.outputs.image }}
-      credentials:
-        username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
-        password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
-      options: --init
-
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-
-      - name: Check Jsonnet code formatting
-        run: |
-          make -C compute jsonnetfmt-test
-
   # Check that the vendor/postgres-* submodules point to the
   # corresponding REL_*_STABLE_neon branches.
   check-submodules:
@@ -199,7 +181,7 @@ jobs:
     runs-on: ${{ fromJson(format('["self-hosted", "{0}"]', matrix.arch == 'arm64' && 'small-arm64' || 'small')) }}
 
     container:
-      image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
+      image: ${{ needs.build-build-tools-image.outputs.image }}
       credentials:
         username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
         password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
@@ -279,7 +261,7 @@ jobs:
     uses: ./.github/workflows/_build-and-test-locally.yml
     with:
       arch: ${{ matrix.arch }}
-      build-tools-image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
+      build-tools-image: ${{ needs.build-build-tools-image.outputs.image }}
       build-tag: ${{ needs.tag.outputs.build-tag }}
       build-type: ${{ matrix.build-type }}
       # Run tests on all Postgres versions in release builds and only on the latest version in debug builds
@@ -294,7 +276,7 @@ jobs:
     needs: [ check-permissions, build-build-tools-image ]
     runs-on: [ self-hosted, small ]
     container:
-      image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
+      image: ${{ needs.build-build-tools-image.outputs.image }}
       credentials:
         username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
         password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
@@ -307,7 +289,7 @@ jobs:
         uses: actions/cache@v4
         with:
           path: ~/.cache/pypoetry/virtualenvs
-          key: v2-${{ runner.os }}-${{ runner.arch }}-python-deps-bookworm-${{ hashFiles('poetry.lock') }}
+          key: v1-${{ runner.os }}-${{ runner.arch }}-python-deps-${{ hashFiles('poetry.lock') }}
 
       - name: Install Python deps
         run: ./scripts/pysync
@@ -327,7 +309,7 @@ jobs:
     needs: [ check-permissions, build-and-test-locally, build-build-tools-image, get-benchmarks-durations ]
     runs-on: [ self-hosted, small ]
     container:
-      image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
+      image: ${{ needs.build-build-tools-image.outputs.image }}
       credentials:
         username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
         password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
@@ -385,7 +367,7 @@ jobs:
 
     runs-on: [ self-hosted, small ]
     container:
-      image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
+      image: ${{ needs.build-build-tools-image.outputs.image }}
       credentials:
         username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
         password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
@@ -433,7 +415,7 @@ jobs:
     needs: [ check-permissions, build-build-tools-image, build-and-test-locally ]
     runs-on: [ self-hosted, small ]
     container:
-      image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
+      image: ${{ needs.build-build-tools-image.outputs.image }}
       credentials:
         username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
         password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
@@ -577,16 +559,15 @@ jobs:
             ADDITIONAL_RUSTFLAGS=${{ matrix.arch == 'arm64' && '-Ctarget-feature=+lse -Ctarget-cpu=neoverse-n1' || '' }}
             GIT_VERSION=${{ github.event.pull_request.head.sha || github.sha }}
             BUILD_TAG=${{ needs.tag.outputs.build-tag }}
-            TAG=${{ needs.build-build-tools-image.outputs.image-tag }}-bookworm
-            DEBIAN_VERSION=bookworm
+            TAG=${{ needs.build-build-tools-image.outputs.image-tag }}
           provenance: false
           push: true
           pull: true
           file: Dockerfile
-          cache-from: type=registry,ref=cache.neon.build/neon:cache-bookworm-${{ matrix.arch }}
-          cache-to: ${{ github.ref_name == 'main' && format('type=registry,ref=cache.neon.build/neon:cache-{0}-{1},mode=max', 'bookworm', matrix.arch) || '' }}
+          cache-from: type=registry,ref=cache.neon.build/neon:cache-${{ matrix.arch }}
+          cache-to: ${{ github.ref_name == 'main' && format('type=registry,ref=cache.neon.build/neon:cache-{0},mode=max', matrix.arch) || '' }}
           tags: |
-            neondatabase/neon:${{ needs.tag.outputs.build-tag }}-bookworm-${{ matrix.arch }}
+            neondatabase/neon:${{ needs.tag.outputs.build-tag }}-${{ matrix.arch }}
 
   neon-image:
     needs: [ neon-image-arch, tag ]
@@ -601,9 +582,8 @@ jobs:
       - name: Create multi-arch image
         run: |
           docker buildx imagetools create -t neondatabase/neon:${{ needs.tag.outputs.build-tag }} \
-                                          -t neondatabase/neon:${{ needs.tag.outputs.build-tag }}-bookworm \
-                                             neondatabase/neon:${{ needs.tag.outputs.build-tag }}-bookworm-x64 \
-                                             neondatabase/neon:${{ needs.tag.outputs.build-tag }}-bookworm-arm64
+                                             neondatabase/neon:${{ needs.tag.outputs.build-tag }}-x64 \
+                                             neondatabase/neon:${{ needs.tag.outputs.build-tag }}-arm64
 
       - uses: docker/login-action@v3
         with:
@@ -624,16 +604,17 @@ jobs:
         version:
           # Much data was already generated on old PG versions with bullseye's
           # libraries, the locales of which can cause data incompatibilities.
-          # However, new PG versions should be build on newer images,
-          # as that reduces the support burden of old and ancient distros.
+          # However, new PG versions should check if they can be built on newer
+          # images, as that reduces the support burden of old and ancient
+          # distros.
           - pg: v14
-            debian: bullseye
+            debian: bullseye-slim
           - pg: v15
-            debian: bullseye
+            debian: bullseye-slim
           - pg: v16
-            debian: bullseye
+            debian: bullseye-slim
           - pg: v17
-            debian: bookworm
+            debian: bookworm-slim
         arch: [ x64, arm64 ]
 
     runs-on: ${{ fromJson(format('["self-hosted", "{0}"]', matrix.arch == 'arm64' && 'large-arm64' || 'large')) }}
@@ -678,16 +659,16 @@ jobs:
             GIT_VERSION=${{ github.event.pull_request.head.sha || github.sha }}
             PG_VERSION=${{ matrix.version.pg }}
             BUILD_TAG=${{ needs.tag.outputs.build-tag }}
-            TAG=${{ needs.build-build-tools-image.outputs.image-tag }}-${{ matrix.version.debian }}
-            DEBIAN_VERSION=${{ matrix.version.debian }}
+            TAG=${{ needs.build-build-tools-image.outputs.image-tag }}
+            DEBIAN_FLAVOR=${{ matrix.version.debian }}
           provenance: false
           push: true
           pull: true
           file: compute/Dockerfile.compute-node
-          cache-from: type=registry,ref=cache.neon.build/compute-node-${{ matrix.version.pg }}:cache-${{ matrix.version.debian }}-${{ matrix.arch }}
-          cache-to: ${{ github.ref_name == 'main' && format('type=registry,ref=cache.neon.build/compute-node-{0}:cache-{1}-{2},mode=max', matrix.version.pg, matrix.version.debian, matrix.arch) || '' }}
+          cache-from: type=registry,ref=cache.neon.build/compute-node-${{ matrix.version.pg }}:cache-${{ matrix.arch }}
+          cache-to: ${{ github.ref_name == 'main' && format('type=registry,ref=cache.neon.build/compute-node-{0}:cache-{1},mode=max', matrix.version.pg, matrix.arch) || '' }}
           tags: |
-            neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-${{ matrix.arch }}
+            neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}-${{ matrix.arch }}
 
       - name: Build neon extensions test image
         if: matrix.version.pg == 'v16'
@@ -698,17 +679,17 @@ jobs:
             GIT_VERSION=${{ github.event.pull_request.head.sha || github.sha }}
             PG_VERSION=${{ matrix.version.pg }}
             BUILD_TAG=${{ needs.tag.outputs.build-tag }}
-            TAG=${{ needs.build-build-tools-image.outputs.image-tag }}-${{ matrix.version.debian }}
-            DEBIAN_VERSION=${{ matrix.version.debian }}
+            TAG=${{ needs.build-build-tools-image.outputs.image-tag }}
+            DEBIAN_FLAVOR=${{ matrix.version.debian }}
           provenance: false
           push: true
           pull: true
           file: compute/Dockerfile.compute-node
           target: neon-pg-ext-test
-          cache-from: type=registry,ref=cache.neon.build/neon-test-extensions-${{ matrix.version.pg }}:cache-${{ matrix.version.debian }}-${{ matrix.arch }}
-          cache-to: ${{ github.ref_name == 'main' && format('type=registry,ref=cache.neon.build/neon-test-extensions-{0}:cache-{1}-{2},mode=max', matrix.version.pg, matrix.version.debian, matrix.arch) || '' }}
+          cache-from: type=registry,ref=cache.neon.build/neon-test-extensions-${{ matrix.version.pg }}:cache-${{ matrix.arch }}
+          cache-to: ${{ github.ref_name == 'main' && format('type=registry,ref=cache.neon.build/neon-test-extensions-{0}:cache-{1},mode=max', matrix.version.pg, matrix.arch) || '' }}
           tags: |
-            neondatabase/neon-test-extensions-${{ matrix.version.pg }}:${{needs.tag.outputs.build-tag}}-${{ matrix.version.debian }}-${{ matrix.arch }}
+            neondatabase/neon-test-extensions-${{ matrix.version.pg }}:${{needs.tag.outputs.build-tag}}-${{ matrix.arch }}
 
       - name: Build compute-tools image
         # compute-tools are Postgres independent, so build it only once
@@ -723,16 +704,14 @@ jobs:
           build-args: |
             GIT_VERSION=${{ github.event.pull_request.head.sha || github.sha }}
             BUILD_TAG=${{ needs.tag.outputs.build-tag }}
-            TAG=${{ needs.build-build-tools-image.outputs.image-tag }}-${{ matrix.version.debian }}
-            DEBIAN_VERSION=${{ matrix.version.debian }}
+            TAG=${{ needs.build-build-tools-image.outputs.image-tag }}
+            DEBIAN_FLAVOR=${{ matrix.version.debian }}
           provenance: false
           push: true
           pull: true
           file: compute/Dockerfile.compute-node
-          cache-from: type=registry,ref=cache.neon.build/neon-test-extensions-${{ matrix.version.pg }}:cache-${{ matrix.version.debian }}-${{ matrix.arch }}
-          cache-to: ${{ github.ref_name == 'main' && format('type=registry,ref=cache.neon.build/compute-tools-{0}:cache-{1}-{2},mode=max', matrix.version.pg, matrix.version.debian, matrix.arch) || '' }}
           tags: |
-            neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-${{ matrix.arch }}
+            neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}-${{ matrix.arch }}
 
   compute-node-image:
     needs: [ compute-node-image-arch, tag ]
@@ -740,16 +719,7 @@ jobs:
 
     strategy:
       matrix:
-        version:
-          # see the comment for `compute-node-image-arch` job
-          - pg: v14
-            debian: bullseye
-          - pg: v15
-            debian: bullseye
-          - pg: v16
-            debian: bullseye
-          - pg: v17
-            debian: bookworm
+        version: [ v14, v15, v16, v17 ]
 
     steps:
       - uses: docker/login-action@v3
@@ -759,26 +729,23 @@ jobs:
 
       - name: Create multi-arch compute-node image
         run: |
-          docker buildx imagetools create -t neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }} \
-                                          -t neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }} \
-                                             neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-x64 \
-                                             neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-arm64
+          docker buildx imagetools create -t neondatabase/compute-node-${{ matrix.version }}:${{ needs.tag.outputs.build-tag }} \
+                                             neondatabase/compute-node-${{ matrix.version }}:${{ needs.tag.outputs.build-tag }}-x64 \
+                                             neondatabase/compute-node-${{ matrix.version }}:${{ needs.tag.outputs.build-tag }}-arm64
 
       - name: Create multi-arch neon-test-extensions image
-        if: matrix.version.pg == 'v16'
+        if: matrix.version == 'v16'
         run: |
-          docker buildx imagetools create -t neondatabase/neon-test-extensions-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }} \
-                                          -t neondatabase/neon-test-extensions-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }} \
-                                             neondatabase/neon-test-extensions-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-x64 \
-                                             neondatabase/neon-test-extensions-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-arm64
+          docker buildx imagetools create -t neondatabase/neon-test-extensions-${{ matrix.version }}:${{ needs.tag.outputs.build-tag }} \
+                                             neondatabase/neon-test-extensions-${{ matrix.version }}:${{ needs.tag.outputs.build-tag }}-x64 \
+                                             neondatabase/neon-test-extensions-${{ matrix.version }}:${{ needs.tag.outputs.build-tag }}-arm64
 
       - name: Create multi-arch compute-tools image
-        if: matrix.version.pg == 'v16'
+        if: matrix.version == 'v17'
         run: |
           docker buildx imagetools create -t neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }} \
-                                          -t neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }} \
-                                             neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-x64 \
-                                             neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-arm64
+                                             neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}-x64 \
+                                             neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}-arm64
 
       - uses: docker/login-action@v3
         with:
@@ -786,13 +753,13 @@ jobs:
           username: ${{ secrets.AWS_ACCESS_KEY_DEV }}
           password: ${{ secrets.AWS_SECRET_KEY_DEV }}
 
-      - name: Push multi-arch compute-node-${{ matrix.version.pg }} image to ECR
+      - name: Push multi-arch compute-node-${{ matrix.version }} image to ECR
         run: |
-          docker buildx imagetools create -t 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }} \
-                                                                                neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}
+          docker buildx imagetools create -t 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-${{ matrix.version }}:${{ needs.tag.outputs.build-tag }} \
+                                                                                neondatabase/compute-node-${{ matrix.version }}:${{ needs.tag.outputs.build-tag }}
 
       - name: Push multi-arch compute-tools image to ECR
-        if: matrix.version.pg == 'v16'
+        if: matrix.version == 'v17'
         run: |
           docker buildx imagetools create -t 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-tools:${{ needs.tag.outputs.build-tag }} \
                                                                                 neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}
@@ -803,16 +770,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        version:
-          # see the comment for `compute-node-image-arch` job
-          - pg: v14
-            debian: bullseye
-          - pg: v15
-            debian: bullseye
-          - pg: v16
-            debian: bullseye
-          - pg: v17
-            debian: bookworm
+        version: [ v14, v15, v16, v17 ]
     env:
       VM_BUILDER_VERSION: v0.35.0
 
@@ -834,18 +792,18 @@ jobs:
       # it won't have the proper authentication (written at v0.6.0)
       - name: Pulling compute-node image
         run: |
-          docker pull neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}
+          docker pull neondatabase/compute-node-${{ matrix.version }}:${{ needs.tag.outputs.build-tag }}
 
       - name: Build vm image
         run: |
           ./vm-builder \
-            -spec=compute/vm-image-spec-${{ matrix.version.debian }}.yaml \
-            -src=neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }} \
-            -dst=neondatabase/vm-compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}
+            -spec=compute/vm-image-spec.yaml \
+            -src=neondatabase/compute-node-${{ matrix.version }}:${{ needs.tag.outputs.build-tag }} \
+            -dst=neondatabase/vm-compute-node-${{ matrix.version }}:${{ needs.tag.outputs.build-tag }}
 
       - name: Pushing vm-compute-node image
         run: |
-          docker push neondatabase/vm-compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}
+          docker push neondatabase/vm-compute-node-${{ matrix.version }}:${{ needs.tag.outputs.build-tag }}
 
   test-images:
     needs: [ check-permissions, tag, neon-image, compute-node-image ]

.github/workflows/neon_extra_builds.yml

@@ -155,7 +155,7 @@ jobs:
       github.ref_name == 'main'
     runs-on: [ self-hosted, large ]
     container:
-      image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
+      image: ${{ needs.build-build-tools-image.outputs.image }}
       credentials:
         username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
         password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}

.github/workflows/pg-clients.yml

@@ -55,7 +55,7 @@ jobs:
     runs-on: ubuntu-22.04
 
     container:
-      image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
+      image: ${{ needs.build-build-tools-image.outputs.image }}
       credentials:
         username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
         password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
@@ -150,7 +150,7 @@ jobs:
     runs-on: ubuntu-22.04
 
     container:
-      image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
+      image: ${{ needs.build-build-tools-image.outputs.image }}
       credentials:
         username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
         password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}

.github/workflows/pin-build-tools-image.yml

@@ -71,6 +71,7 @@ jobs:
 
     steps:
       - uses: docker/login-action@v3
+
         with:
           username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
           password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
@@ -93,22 +94,8 @@ jobs:
           az acr login --name=neoneastus2
 
       - name: Tag build-tools with `${{ env.TO_TAG }}` in Docker Hub, ECR, and ACR
-        env:
-          DEFAULT_DEBIAN_VERSION: bullseye
         run: |
-          for debian_version in bullseye bookworm; do
-            tags=()
-
-            tags+=("-t" "neondatabase/build-tools:${TO_TAG}-${debian_version}")
-            tags+=("-t" "369495373322.dkr.ecr.eu-central-1.amazonaws.com/build-tools:${TO_TAG}-${debian_version}")
-            tags+=("-t" "neoneastus2.azurecr.io/neondatabase/build-tools:${TO_TAG}-${debian_version}")
-
-            if [ "${debian_version}" == "${DEFAULT_DEBIAN_VERSION}" ]; then
-              tags+=("-t" "neondatabase/build-tools:${TO_TAG}")
-              tags+=("-t" "369495373322.dkr.ecr.eu-central-1.amazonaws.com/build-tools:${TO_TAG}")
-              tags+=("-t" "neoneastus2.azurecr.io/neondatabase/build-tools:${TO_TAG}")
-            fi
-
-            docker buildx imagetools create "${tags[@]}" \
-                                              neondatabase/build-tools:${FROM_TAG}-${debian_version}
-          done
+          docker buildx imagetools create -t 369495373322.dkr.ecr.eu-central-1.amazonaws.com/build-tools:${TO_TAG} \
+                                          -t neoneastus2.azurecr.io/neondatabase/build-tools:${TO_TAG} \
+                                          -t neondatabase/build-tools:${TO_TAG} \
+                                             neondatabase/build-tools:${FROM_TAG}

Cargo.lock

@@ -2695,7 +2695,6 @@ checksum = "ad227c3af19d4914570ad36d30409928b75967c298feb9ea1969db3a610bb14e"
 dependencies = [
  "equivalent",
  "hashbrown 0.14.5",
- "serde",
 ]
 
 [[package]]
@@ -2795,9 +2794,9 @@ dependencies = [
 
 [[package]]
 name = "itoa"
-version = "1.0.11"
+version = "1.0.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "49f1f14873335454500d59611f1cf4a4b0f786f9ac11f4312a78e4cf2566695b"
+checksum = "453ad9f582a441959e5f0d088b02ce04cfe8d51a8eaf077f12ac6d3e94164ca6"
 
 [[package]]
 name = "jobserver"
@@ -4297,7 +4296,6 @@ dependencies = [
  "indexmap 2.0.1",
  "ipnet",
  "itertools 0.10.5",
- "itoa",
  "jose-jwa",
  "jose-jwk",
  "lasso",
@@ -7309,7 +7307,6 @@ dependencies = [
  "hyper 1.4.1",
  "hyper-util",
  "indexmap 1.9.3",
- "indexmap 2.0.1",
  "itertools 0.12.1",
  "lazy_static",
  "libc",

Cargo.toml

@@ -107,7 +107,6 @@ indexmap = "2"
 indoc = "2"
 ipnet = "2.9.0"
 itertools = "0.10"
-itoa = "1.0.11"
 jsonwebtoken = "9"
 lasso = "0.7"
 libc = "0.2"

Dockerfile

@@ -7,8 +7,6 @@ ARG IMAGE=build-tools
 ARG TAG=pinned
 ARG DEFAULT_PG_VERSION=17
 ARG STABLE_PG_VERSION=16
-ARG DEBIAN_VERSION=bullseye
-ARG DEBIAN_FLAVOR=${DEBIAN_VERSION}-slim
 
 # Build Postgres
 FROM $REPOSITORY/$IMAGE:$TAG AS pg-build
@@ -59,7 +57,7 @@ RUN set -e \
 
 # Build final image
 #
-FROM debian:${DEBIAN_FLAVOR}
+FROM debian:bullseye-slim
 ARG DEFAULT_PG_VERSION
 WORKDIR /data
 

Dockerfile.build-tools

@@ -1,7 +1,12 @@
-ARG DEBIAN_VERSION=bullseye
+FROM debian:bullseye-slim
 
-FROM debian:${DEBIAN_VERSION}-slim
-ARG DEBIAN_VERSION
+# Use ARG as a build-time environment variable here to allow.
+# It's not supposed to be set outside.
+# Alternatively it can be obtained using the following command
+# ```
+# . /etc/os-release && echo "${VERSION_CODENAME}"
+# ```
+ARG DEBIAN_VERSION_CODENAME=bullseye
 
 # Add nonroot user
 RUN useradd -ms /bin/bash nonroot -b /home
@@ -27,7 +32,6 @@ RUN set -e \
         gnupg \
         gzip \
         jq \
-        jsonnet \
         libcurl4-openssl-dev \
         libbz2-dev \
         libffi-dev \
@@ -38,14 +42,14 @@ RUN set -e \
         libseccomp-dev \
         libsqlite3-dev \
         libssl-dev \
-        $([[ "${DEBIAN_VERSION}" = "bullseye" ]] && libstdc++-10-dev || libstdc++-11-dev) \
+        libstdc++-10-dev \
         libtool \
         libxml2-dev \
         libxmlsec1-dev \
         libxxhash-dev \
         lsof \
         make \
-        netcat-openbsd \
+        netcat \
         net-tools \
         openssh-client \
         parallel \
@@ -74,7 +78,7 @@ RUN curl -sL "https://github.com/peak/s5cmd/releases/download/v${S5CMD_VERSION}/
 # LLVM
 ENV LLVM_VERSION=18
 RUN curl -fsSL 'https://apt.llvm.org/llvm-snapshot.gpg.key' | apt-key add - \
-    && echo "deb http://apt.llvm.org/${DEBIAN_VERSION}/ llvm-toolchain-${DEBIAN_VERSION}-${LLVM_VERSION} main" > /etc/apt/sources.list.d/llvm.stable.list \
+    && echo "deb http://apt.llvm.org/${DEBIAN_VERSION_CODENAME}/ llvm-toolchain-${DEBIAN_VERSION_CODENAME}-${LLVM_VERSION} main" > /etc/apt/sources.list.d/llvm.stable.list \
     && apt update \
     && apt install -y clang-${LLVM_VERSION} llvm-${LLVM_VERSION} \
     && bash -c 'for f in /usr/bin/clang*-${LLVM_VERSION} /usr/bin/llvm*-${LLVM_VERSION}; do ln -s "${f}" "${f%-${LLVM_VERSION}}"; done' \
@@ -82,7 +86,7 @@ RUN curl -fsSL 'https://apt.llvm.org/llvm-snapshot.gpg.key' | apt-key add - \
 
 # Install docker
 RUN curl -fsSL https://download.docker.com/linux/ubuntu/gpg | gpg --dearmor -o /usr/share/keyrings/docker-archive-keyring.gpg \
-    && echo "deb [arch=$(dpkg --print-architecture) signed-by=/usr/share/keyrings/docker-archive-keyring.gpg] https://download.docker.com/linux/debian ${DEBIAN_VERSION} stable" > /etc/apt/sources.list.d/docker.list \
+    && echo "deb [arch=$(dpkg --print-architecture) signed-by=/usr/share/keyrings/docker-archive-keyring.gpg] https://download.docker.com/linux/debian ${DEBIAN_VERSION_CODENAME} stable" > /etc/apt/sources.list.d/docker.list \
     && apt update \
     && apt install -y docker-ce docker-ce-cli \
     && rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*

Makefile

@@ -291,7 +291,6 @@ postgres-check: \
 # This doesn't remove the effects of 'configure'.
 .PHONY: clean
 clean: postgres-clean neon-pg-clean-ext
-	$(MAKE) -C compute clean
 	$(CARGO_CMD_PREFIX) cargo clean
 
 # This removes everything

compute/.gitignore

@@ -1,5 +0,0 @@
-# sql_exporter config files generated from Jsonnet
-etc/neon_collector.yml
-etc/neon_collector_autoscaling.yml
-etc/sql_exporter.yml
-etc/sql_exporter_autoscaling.yml

compute/Dockerfile.compute-node

@@ -3,8 +3,7 @@ ARG REPOSITORY=neondatabase
 ARG IMAGE=build-tools
 ARG TAG=pinned
 ARG BUILD_TAG
-ARG DEBIAN_VERSION=bullseye
-ARG DEBIAN_FLAVOR=${DEBIAN_VERSION}-slim
+ARG DEBIAN_FLAVOR=bullseye-slim
 
 #########################################################################################
 #
@@ -12,23 +11,20 @@ ARG DEBIAN_FLAVOR=${DEBIAN_VERSION}-slim
 #
 #########################################################################################
 FROM debian:$DEBIAN_FLAVOR AS build-deps
-ARG DEBIAN_VERSION
+ARG DEBIAN_FLAVOR
 
-RUN case $DEBIAN_VERSION in \
+RUN case $DEBIAN_FLAVOR in \
       # Version-specific installs for Bullseye (PG14-PG16):
       # The h3_pg extension needs a cmake 3.20+, but Debian bullseye has 3.18.
       # Install newer version (3.25) from backports.
-      bullseye) \
+      bullseye*) \
         echo "deb http://deb.debian.org/debian bullseye-backports main" > /etc/apt/sources.list.d/bullseye-backports.list; \
         VERSION_INSTALLS="cmake/bullseye-backports cmake-data/bullseye-backports"; \
       ;; \
       # Version-specific installs for Bookworm (PG17):
-      bookworm) \
+      bookworm*) \
         VERSION_INSTALLS="cmake"; \
       ;; \
-      *) \
-        echo "Unknown Debian version ${DEBIAN_VERSION}" && exit 1 \
-      ;; \
     esac && \
     apt update &&  \
     apt install --no-install-recommends -y git autoconf automake libtool build-essential bison flex libreadline-dev \
@@ -349,7 +345,7 @@ ARG PG_VERSION
 COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
 
 # not version-specific
-# doesn't use releases, last commit f3d82fd - Mar 2, 2023
+# doesn't use releases, last commit f3d82fd - Mar 2, 2023 
 RUN wget https://github.com/michelp/pgjwt/archive/f3d82fd30151e754e19ce5d6a06c71c20689ce3d.tar.gz -O pgjwt.tar.gz && \
     echo "dae8ed99eebb7593b43013f6532d772b12dfecd55548d2673f2dfd0163f6d2b9 pgjwt.tar.gz" | sha256sum --check && \
     mkdir pgjwt-src && cd pgjwt-src && tar xzf ../pgjwt.tar.gz --strip-components=1 -C . && \
@@ -929,8 +925,8 @@ ARG PG_VERSION
 RUN case "${PG_VERSION}" in "v17") \
     echo "pg_session_jwt does not yet have a release that supports pg17" && exit 0;; \
     esac && \
-    wget https://github.com/neondatabase/pg_session_jwt/archive/5aee2625af38213650e1a07ae038fdc427250ee4.tar.gz -O pg_session_jwt.tar.gz && \
-    echo "5d91b10bc1347d36cffc456cb87bec25047935d6503dc652ca046f04760828e7 pg_session_jwt.tar.gz" | sha256sum --check && \
+    wget https://github.com/neondatabase/pg_session_jwt/archive/ff0a72440e8ff584dab24b3f9b7c00c56c660b8e.tar.gz -O pg_session_jwt.tar.gz && \
+    echo "1fbb2b5a339263bcf6daa847fad8bccbc0b451cea6a62e6d3bf232b0087f05cb pg_session_jwt.tar.gz" | sha256sum --check && \
     mkdir pg_session_jwt-src && cd pg_session_jwt-src && tar xzf ../pg_session_jwt.tar.gz --strip-components=1 -C . && \
     sed -i 's/pgrx = "=0.11.3"/pgrx = { version = "=0.11.3", features = [ "unsafe-postgres" ] }/g' Cargo.toml && \
     cargo pgrx install --release
@@ -1095,6 +1091,7 @@ RUN cd compute_tools && mold -run cargo build --locked --profile release-line-de
 #########################################################################################
 
 FROM debian:$DEBIAN_FLAVOR AS compute-tools-image
+ARG DEBIAN_FLAVOR
 
 COPY --from=compute-tools /home/nonroot/target/release-line-debug-size-lto/compute_ctl /usr/local/bin/compute_ctl
 
@@ -1105,6 +1102,7 @@ COPY --from=compute-tools /home/nonroot/target/release-line-debug-size-lto/compu
 #########################################################################################
 
 FROM debian:$DEBIAN_FLAVOR AS pgbouncer
+ARG DEBIAN_FLAVOR
 RUN set -e \
     && apt-get update \
     && apt-get install --no-install-recommends -y \
@@ -1169,18 +1167,6 @@ RUN rm -r /usr/local/pgsql/include
 # if they were to be used by other libraries.
 RUN rm /usr/local/pgsql/lib/lib*.a
 
-#########################################################################################
-#
-# Preprocess the sql_exporter configuration files
-#
-#########################################################################################
-FROM $REPOSITORY/$IMAGE:$TAG AS sql_exporter_preprocessor
-
-USER nonroot
-
-COPY --chown=nonroot compute compute
-
-RUN make -C compute
 
 #########################################################################################
 #
@@ -1271,7 +1257,7 @@ ENV PGDATABASE=postgres
 #
 #########################################################################################
 FROM debian:$DEBIAN_FLAVOR
-ARG DEBIAN_VERSION
+ARG DEBIAN_FLAVOR
 # Add user postgres
 RUN mkdir /var/db && useradd -m -d /var/db/postgres postgres && \
     echo "postgres:test_console_pass" | chpasswd && \
@@ -1299,10 +1285,10 @@ RUN mkdir -p /etc/local_proxy && chown postgres:postgres /etc/local_proxy
 COPY --from=postgres-exporter /bin/postgres_exporter /bin/postgres_exporter
 COPY --from=sql-exporter      /bin/sql_exporter      /bin/sql_exporter
 
-COPY --from=sql_exporter_preprocessor --chmod=0644 /home/nonroot/compute/etc/sql_exporter.yml               /etc/sql_exporter.yml
-COPY --from=sql_exporter_preprocessor --chmod=0644 /home/nonroot/compute/etc/neon_collector.yml             /etc/neon_collector.yml
-COPY --from=sql_exporter_preprocessor --chmod=0644 /home/nonroot/compute/etc/sql_exporter_autoscaling.yml   /etc/sql_exporter_autoscaling.yml
-COPY --from=sql_exporter_preprocessor --chmod=0644 /home/nonroot/compute/etc/neon_collector_autoscaling.yml /etc/neon_collector_autoscaling.yml
+COPY --chmod=0644 compute/etc/sql_exporter.yml               /etc/sql_exporter.yml
+COPY --chmod=0644 compute/etc/neon_collector.yml             /etc/neon_collector.yml
+COPY --chmod=0644 compute/etc/sql_exporter_autoscaling.yml   /etc/sql_exporter_autoscaling.yml
+COPY --chmod=0644 compute/etc/neon_collector_autoscaling.yml /etc/neon_collector_autoscaling.yml
 
 # Create remote extension download directory
 RUN mkdir /usr/local/download_extensions && chown -R postgres:postgres /usr/local/download_extensions
@@ -1319,22 +1305,19 @@ RUN mkdir /usr/local/download_extensions && chown -R postgres:postgres /usr/loca
 
 
 RUN apt update && \
-    case $DEBIAN_VERSION in \
+    case $DEBIAN_FLAVOR in \
       # Version-specific installs for Bullseye (PG14-PG16):
       # libicu67, locales for collations (including ICU and plpgsql_check)
       # libgdal28, libproj19 for PostGIS
-      bullseye) \
+      bullseye*) \
         VERSION_INSTALLS="libicu67 libgdal28 libproj19"; \
       ;; \
       # Version-specific installs for Bookworm (PG17):
       # libicu72, locales for collations (including ICU and plpgsql_check)
       # libgdal32, libproj25 for PostGIS
-      bookworm) \
+      bookworm*) \
         VERSION_INSTALLS="libicu72 libgdal32 libproj25"; \
       ;; \
-      *) \
-        echo "Unknown Debian version ${DEBIAN_VERSION}" && exit 1 \
-      ;; \
     esac && \
     apt install --no-install-recommends -y \
         gdb \

compute/Makefile

@@ -1,45 +0,0 @@
-jsonnet_files = $(wildcard \
-	etc/*.jsonnet \
-	etc/sql_exporter/*.libsonnet)
-
-.PHONY: all
-all: neon_collector.yml neon_collector_autoscaling.yml sql_exporter.yml sql_exporter_autoscaling.yml
-
-neon_collector.yml: $(jsonnet_files)
-	JSONNET_PATH=etc jsonnet \
-		--output-file etc/$@ \
-		etc/neon_collector.jsonnet
-
-neon_collector_autoscaling.yml: $(jsonnet_files)
-	JSONNET_PATH=etc jsonnet \
-		--output-file etc/$@ \
-		etc/neon_collector_autoscaling.jsonnet
-
-sql_exporter.yml: $(jsonnet_files)
-	JSONNET_PATH=etc jsonnet \
-		--output-file etc/$@ \
-		--tla-str collector_file=neon_collector.yml \
-		etc/sql_exporter.jsonnet
-
-sql_exporter_autoscaling.yml: $(jsonnet_files)
-	JSONNET_PATH=etc jsonnet \
-		--output-file etc/$@ \
-		--tla-str collector_file=neon_collector_autoscaling.yml \
-		--tla-str application_name=sql_exporter_autoscaling \
-		etc/sql_exporter.jsonnet
-
-.PHONY: clean
-clean:
-	rm --force \
-		etc/neon_collector.yml \
-		etc/neon_collector_autoscaling.yml \
-		etc/sql_exporter.yml \
-		etc/sql_exporter_autoscaling.yml
-
-.PHONY: jsonnetfmt-test
-jsonnetfmt-test:
-	jsonnetfmt --test $(jsonnet_files)
-
-.PHONY: jsonnetfmt-format
-jsonnetfmt-format:
-	jsonnetfmt --in-place $(jsonnet_files)

compute/etc/README.md

@@ -1,17 +0,0 @@
-# Compute Configuration
-
-These files are the configuration files for various other pieces of software
-that will be running in the compute alongside Postgres.
-
-## `sql_exporter`
-
-### Adding a `sql_exporter` Metric
-
-We use `sql_exporter` to export various metrics from Postgres. In order to add
-a metric, you will need to create two files: a `libsonnet` and a `sql` file. You
-will then import the `libsonnet` file in one of the collector files, and the
-`sql` file will be imported in the `libsonnet` file.
-
-In the event your statistic is an LSN, you may want to cast it to a `float8`
-because Prometheus only supports floats. It's probably fine because `float8` can
-store integers from `-2^53` to `+2^53` exactly.

compute/etc/neon_collector.jsonnet

@@ -1,51 +0,0 @@
-{
-  collector_name: 'neon_collector',
-  metrics: [
-    import 'sql_exporter/checkpoints_req.libsonnet',
-    import 'sql_exporter/checkpoints_timed.libsonnet',
-    import 'sql_exporter/compute_current_lsn.libsonnet',
-    import 'sql_exporter/compute_logical_snapshot_files.libsonnet',
-    import 'sql_exporter/compute_receive_lsn.libsonnet',
-    import 'sql_exporter/compute_subscriptions_count.libsonnet',
-    import 'sql_exporter/connection_counts.libsonnet',
-    import 'sql_exporter/db_total_size.libsonnet',
-    import 'sql_exporter/file_cache_read_wait_seconds_bucket.libsonnet',
-    import 'sql_exporter/file_cache_read_wait_seconds_count.libsonnet',
-    import 'sql_exporter/file_cache_read_wait_seconds_sum.libsonnet',
-    import 'sql_exporter/file_cache_write_wait_seconds_bucket.libsonnet',
-    import 'sql_exporter/file_cache_write_wait_seconds_count.libsonnet',
-    import 'sql_exporter/file_cache_write_wait_seconds_sum.libsonnet',
-    import 'sql_exporter/getpage_prefetch_discards_total.libsonnet',
-    import 'sql_exporter/getpage_prefetch_misses_total.libsonnet',
-    import 'sql_exporter/getpage_prefetch_requests_total.libsonnet',
-    import 'sql_exporter/getpage_prefetches_buffered.libsonnet',
-    import 'sql_exporter/getpage_sync_requests_total.libsonnet',
-    import 'sql_exporter/getpage_wait_seconds_bucket.libsonnet',
-    import 'sql_exporter/getpage_wait_seconds_count.libsonnet',
-    import 'sql_exporter/getpage_wait_seconds_sum.libsonnet',
-    import 'sql_exporter/lfc_approximate_working_set_size.libsonnet',
-    import 'sql_exporter/lfc_approximate_working_set_size_windows.libsonnet',
-    import 'sql_exporter/lfc_cache_size_limit.libsonnet',
-    import 'sql_exporter/lfc_hits.libsonnet',
-    import 'sql_exporter/lfc_misses.libsonnet',
-    import 'sql_exporter/lfc_used.libsonnet',
-    import 'sql_exporter/lfc_writes.libsonnet',
-    import 'sql_exporter/logical_slot_restart_lsn.libsonnet',
-    import 'sql_exporter/max_cluster_size.libsonnet',
-    import 'sql_exporter/pageserver_disconnects_total.libsonnet',
-    import 'sql_exporter/pageserver_requests_sent_total.libsonnet',
-    import 'sql_exporter/pageserver_send_flushes_total.libsonnet',
-    import 'sql_exporter/pageserver_open_requests.libsonnet',
-    import 'sql_exporter/pg_stats_userdb.libsonnet',
-    import 'sql_exporter/replication_delay_bytes.libsonnet',
-    import 'sql_exporter/replication_delay_seconds.libsonnet',
-    import 'sql_exporter/retained_wal.libsonnet',
-    import 'sql_exporter/wal_is_lost.libsonnet',
-  ],
-  queries: [
-    {
-      query_name: 'neon_perf_counters',
-      query: importstr 'sql_exporter/neon_perf_counters.sql',
-    },
-  ],
-}

compute/etc/neon_collector.yml

@@ -0,0 +1,331 @@
+collector_name: neon_collector
+metrics:
+- metric_name: lfc_misses
+  type: gauge
+  help: 'lfc_misses'
+  key_labels:
+  values: [lfc_misses]
+  query: |
+    select lfc_value as lfc_misses from neon.neon_lfc_stats where lfc_key='file_cache_misses';
+
+- metric_name: lfc_used
+  type: gauge
+  help: 'LFC chunks used (chunk = 1MB)'
+  key_labels:
+  values: [lfc_used]
+  query: |
+    select lfc_value as lfc_used from neon.neon_lfc_stats where lfc_key='file_cache_used';
+
+- metric_name: lfc_hits
+  type: gauge
+  help: 'lfc_hits'
+  key_labels:
+  values: [lfc_hits]
+  query: |
+    select lfc_value as lfc_hits from neon.neon_lfc_stats where lfc_key='file_cache_hits';
+
+- metric_name: lfc_writes
+  type: gauge
+  help: 'lfc_writes'
+  key_labels:
+  values: [lfc_writes]
+  query: |
+    select lfc_value as lfc_writes from neon.neon_lfc_stats where lfc_key='file_cache_writes';
+
+- metric_name: lfc_cache_size_limit
+  type: gauge
+  help: 'LFC cache size limit in bytes'
+  key_labels:
+  values: [lfc_cache_size_limit]
+  query: |
+    select pg_size_bytes(current_setting('neon.file_cache_size_limit')) as lfc_cache_size_limit;
+
+- metric_name: connection_counts
+  type: gauge
+  help: 'Connection counts'
+  key_labels:
+    - datname
+    - state
+  values: [count]
+  query: |
+    select datname, state, count(*) as count from pg_stat_activity where state <> '' group by datname, state;
+
+- metric_name: pg_stats_userdb
+  type: gauge
+  help: 'Stats for several oldest non-system dbs'
+  key_labels:
+    - datname
+  value_label: kind
+  values:
+    - db_size
+    - deadlocks
+    # Rows
+    - inserted
+    - updated
+    - deleted
+  # We export stats for 10 non-system database. Without this limit
+  # it is too easy to abuse the system by creating lots of databases.
+  query: |
+    select pg_database_size(datname) as db_size, deadlocks,
+       tup_inserted as inserted, tup_updated as updated, tup_deleted as deleted,
+       datname
+     from pg_stat_database
+     where datname IN (
+       select datname
+       from pg_database
+       where datname <> 'postgres' and not datistemplate
+       order by oid
+       limit 10
+     );
+
+- metric_name: max_cluster_size
+  type: gauge
+  help: 'neon.max_cluster_size setting'
+  key_labels:
+  values: [max_cluster_size]
+  query: |
+    select setting::int as max_cluster_size from pg_settings where name = 'neon.max_cluster_size';
+
+- metric_name: db_total_size
+  type: gauge
+  help: 'Size of all databases'
+  key_labels:
+  values: [total]
+  query: |
+    select sum(pg_database_size(datname)) as total from pg_database;
+
+- metric_name: getpage_wait_seconds_count
+  type: counter
+  help: 'Number of getpage requests'
+  values: [getpage_wait_seconds_count]
+  query_ref: neon_perf_counters
+
+- metric_name: getpage_wait_seconds_sum
+  type: counter
+  help: 'Time spent in getpage requests'
+  values: [getpage_wait_seconds_sum]
+  query_ref: neon_perf_counters
+
+- metric_name: getpage_prefetch_requests_total
+  type: counter
+  help: 'Number of getpage issued for prefetching'
+  values: [getpage_prefetch_requests_total]
+  query_ref: neon_perf_counters
+
+- metric_name: getpage_sync_requests_total
+  type: counter
+  help: 'Number of synchronous getpage issued'
+  values: [getpage_sync_requests_total]
+  query_ref: neon_perf_counters
+
+- metric_name: getpage_prefetch_misses_total
+  type: counter
+  help: 'Total number of readahead misses; consisting of either prefetches that don''t satisfy the LSN bounds once the prefetch got read by the backend, or cases where somehow no readahead was issued for the read'
+  values: [getpage_prefetch_misses_total]
+  query_ref: neon_perf_counters
+
+- metric_name: getpage_prefetch_discards_total
+  type: counter
+  help: 'Number of prefetch responses issued but not used'
+  values: [getpage_prefetch_discards_total]
+  query_ref: neon_perf_counters
+
+- metric_name: pageserver_requests_sent_total
+  type: counter
+  help: 'Number of all requests sent to the pageserver (not just GetPage requests)'
+  values: [pageserver_requests_sent_total]
+  query_ref: neon_perf_counters
+
+- metric_name: pageserver_disconnects_total
+  type: counter
+  help: 'Number of times that the connection to the pageserver was lost'
+  values: [pageserver_disconnects_total]
+  query_ref: neon_perf_counters
+
+- metric_name: pageserver_send_flushes_total
+  type: counter
+  help: 'Number of flushes to the pageserver connection'
+  values: [pageserver_send_flushes_total]
+  query_ref: neon_perf_counters
+
+- metric_name: getpage_wait_seconds_bucket
+  type: counter
+  help: 'Histogram buckets of getpage request latency'
+  key_labels:
+      - bucket_le
+  values: [value]
+  query_ref: getpage_wait_seconds_buckets
+
+# DEPRECATED
+- metric_name: lfc_approximate_working_set_size
+  type: gauge
+  help: 'Approximate working set size in pages of 8192 bytes'
+  key_labels:
+  values: [approximate_working_set_size]
+  query: |
+    select neon.approximate_working_set_size(false) as approximate_working_set_size;
+
+- metric_name: lfc_approximate_working_set_size_windows
+  type: gauge
+  help: 'Approximate working set size in pages of 8192 bytes'
+  key_labels: [duration]
+  values: [size]
+  # NOTE: This is the "public" / "human-readable" version. Here, we supply a small selection
+  # of durations in a pretty-printed form.
+  query: |
+    select
+      x as duration,
+      neon.approximate_working_set_size_seconds(extract('epoch' from x::interval)::int) as size
+    from
+      (values ('5m'),('15m'),('1h')) as t (x);
+
+- metric_name: compute_current_lsn
+  type: gauge
+  help: 'Current LSN of the database'
+  key_labels:
+  values: [lsn]
+  query: |
+    select
+      case
+        when pg_catalog.pg_is_in_recovery()
+        then (pg_last_wal_replay_lsn() - '0/0')::FLOAT8
+        else (pg_current_wal_lsn() - '0/0')::FLOAT8
+      end as lsn;
+
+- metric_name: compute_receive_lsn
+  type: gauge
+  help: 'Returns the last write-ahead log location that has been received and synced to disk by streaming replication'
+  key_labels:
+  values: [lsn]
+  query: |
+    SELECT
+      CASE
+        WHEN pg_catalog.pg_is_in_recovery()
+        THEN (pg_last_wal_receive_lsn() - '0/0')::FLOAT8
+        ELSE 0
+      END AS lsn;
+
+- metric_name: replication_delay_bytes
+  type: gauge
+  help: 'Bytes between received and replayed LSN'
+  key_labels:
+  values: [replication_delay_bytes]
+  # We use a GREATEST call here because this calculation can be negative.
+  # The calculation is not atomic, meaning after we've gotten the receive
+  # LSN, the replay LSN may have advanced past the receive LSN we
+  # are using for the calculation.
+  query: |
+    SELECT GREATEST(0, pg_wal_lsn_diff(pg_last_wal_receive_lsn(), pg_last_wal_replay_lsn())) AS replication_delay_bytes;
+
+- metric_name: replication_delay_seconds
+  type: gauge
+  help: 'Time since last LSN was replayed'
+  key_labels:
+  values: [replication_delay_seconds]
+  query: |
+    SELECT
+      CASE
+        WHEN pg_last_wal_receive_lsn() = pg_last_wal_replay_lsn() THEN 0
+        ELSE GREATEST (0, EXTRACT (EPOCH FROM now() - pg_last_xact_replay_timestamp()))
+     END AS replication_delay_seconds;
+
+- metric_name: checkpoints_req
+  type: gauge
+  help: 'Number of requested checkpoints'
+  key_labels:
+  values: [checkpoints_req]
+  query: |
+    SELECT checkpoints_req FROM pg_stat_bgwriter;
+
+- metric_name: checkpoints_timed
+  type: gauge
+  help: 'Number of scheduled checkpoints'
+  key_labels:
+  values: [checkpoints_timed]
+  query: |
+    SELECT checkpoints_timed FROM pg_stat_bgwriter;
+
+- metric_name: compute_logical_snapshot_files
+  type: gauge
+  help: 'Number of snapshot files in pg_logical/snapshot'
+  key_labels:
+    - timeline_id
+  values: [num_logical_snapshot_files]
+  query: |
+    SELECT
+      (SELECT setting FROM pg_settings WHERE name = 'neon.timeline_id') AS timeline_id,
+      -- Postgres creates temporary snapshot files of the form %X-%X.snap.%d.tmp. These
+      -- temporary snapshot files are renamed to the actual snapshot files after they are
+      -- completely built. We only WAL-log the completely built snapshot files.
+      (SELECT COUNT(*) FROM pg_ls_dir('pg_logical/snapshots') AS name WHERE name LIKE '%.snap') AS num_logical_snapshot_files;
+
+# In all the below metrics, we cast LSNs to floats because Prometheus only supports floats.
+# It's probably fine because float64 can store integers from -2^53 to +2^53 exactly.
+
+# Number of slots is limited by max_replication_slots, so collecting position for all of them shouldn't be bad.
+- metric_name: logical_slot_restart_lsn
+  type: gauge
+  help: 'restart_lsn of logical slots'
+  key_labels:
+    - slot_name
+  values: [restart_lsn]
+  query: |
+    select slot_name, (restart_lsn - '0/0')::FLOAT8 as restart_lsn
+    from pg_replication_slots
+    where slot_type = 'logical';
+
+- metric_name: compute_subscriptions_count
+  type: gauge
+  help: 'Number of logical replication subscriptions grouped by enabled/disabled'
+  key_labels:
+    - enabled
+  values: [subscriptions_count]
+  query: |
+    select subenabled::text as enabled, count(*) as subscriptions_count
+    from pg_subscription
+    group by subenabled;
+
+- metric_name: retained_wal
+  type: gauge
+  help: 'Retained WAL in inactive replication slots'
+  key_labels:
+    - slot_name
+  values: [retained_wal]
+  query: |
+    SELECT slot_name, pg_wal_lsn_diff(pg_current_wal_lsn(), restart_lsn)::FLOAT8 AS retained_wal
+    FROM pg_replication_slots
+    WHERE active = false;
+
+- metric_name: wal_is_lost
+  type: gauge
+  help: 'Whether or not the replication slot wal_status is lost'
+  key_labels:
+    - slot_name
+  values: [wal_is_lost]
+  query: |
+    SELECT slot_name,
+           CASE WHEN wal_status = 'lost' THEN 1 ELSE 0 END AS wal_is_lost
+    FROM pg_replication_slots;
+
+queries:
+  - query_name: neon_perf_counters
+    query: |
+      WITH c AS (
+        SELECT pg_catalog.jsonb_object_agg(metric, value) jb FROM neon.neon_perf_counters
+      )
+      SELECT d.*
+      FROM pg_catalog.jsonb_to_record((select jb from c)) as d(
+          getpage_wait_seconds_count numeric,
+          getpage_wait_seconds_sum numeric,
+          getpage_prefetch_requests_total numeric,
+          getpage_sync_requests_total numeric,
+          getpage_prefetch_misses_total numeric,
+          getpage_prefetch_discards_total numeric,
+          pageserver_requests_sent_total numeric,
+          pageserver_disconnects_total numeric,
+          pageserver_send_flushes_total numeric
+      );
+
+  - query_name: getpage_wait_seconds_buckets
+    query: |
+      SELECT bucket_le, value FROM neon.neon_perf_counters WHERE metric = 'getpage_wait_seconds_bucket';

compute/etc/neon_collector_autoscaling.jsonnet

@@ -1,11 +0,0 @@
-{
-  collector_name: 'neon_collector_autoscaling',
-  metrics: [
-    import 'sql_exporter/lfc_approximate_working_set_size_windows.autoscaling.libsonnet',
-    import 'sql_exporter/lfc_cache_size_limit.libsonnet',
-    import 'sql_exporter/lfc_hits.libsonnet',
-    import 'sql_exporter/lfc_misses.libsonnet',
-    import 'sql_exporter/lfc_used.libsonnet',
-    import 'sql_exporter/lfc_writes.libsonnet',
-  ],
-}

compute/etc/neon_collector_autoscaling.yml

@@ -0,0 +1,55 @@
+collector_name: neon_collector_autoscaling
+metrics:
+- metric_name: lfc_misses
+  type: gauge
+  help: 'lfc_misses'
+  key_labels:
+  values: [lfc_misses]
+  query: |
+    select lfc_value as lfc_misses from neon.neon_lfc_stats where lfc_key='file_cache_misses';
+
+- metric_name: lfc_used
+  type: gauge
+  help: 'LFC chunks used (chunk = 1MB)'
+  key_labels:
+  values: [lfc_used]
+  query: |
+    select lfc_value as lfc_used from neon.neon_lfc_stats where lfc_key='file_cache_used';
+
+- metric_name: lfc_hits
+  type: gauge
+  help: 'lfc_hits'
+  key_labels:
+  values: [lfc_hits]
+  query: |
+    select lfc_value as lfc_hits from neon.neon_lfc_stats where lfc_key='file_cache_hits';
+
+- metric_name: lfc_writes
+  type: gauge
+  help: 'lfc_writes'
+  key_labels:
+  values: [lfc_writes]
+  query: |
+    select lfc_value as lfc_writes from neon.neon_lfc_stats where lfc_key='file_cache_writes';
+
+- metric_name: lfc_cache_size_limit
+  type: gauge
+  help: 'LFC cache size limit in bytes'
+  key_labels:
+  values: [lfc_cache_size_limit]
+  query: |
+    select pg_size_bytes(current_setting('neon.file_cache_size_limit')) as lfc_cache_size_limit;
+
+- metric_name: lfc_approximate_working_set_size_windows
+  type: gauge
+  help: 'Approximate working set size in pages of 8192 bytes'
+  key_labels: [duration_seconds]
+  values: [size]
+  # NOTE: This is the "internal" / "machine-readable" version. This outputs the working set
+  # size looking back 1..60 minutes, labeled with the number of minutes.
+  query: |
+    select
+      x::text as duration_seconds,
+      neon.approximate_working_set_size_seconds(x) as size
+    from
+      (select generate_series * 60 as x from generate_series(1, 60)) as t (x);

compute/etc/sql_exporter.jsonnet

@@ -1,40 +0,0 @@
-function(collector_file, application_name='sql_exporter') {
-  // Configuration for sql_exporter for autoscaling-agent
-  // Global defaults.
-  global: {
-    // If scrape_timeout <= 0, no timeout is set unless Prometheus provides one. The default is 10s.
-    scrape_timeout: '10s',
-    // Subtracted from Prometheus' scrape_timeout to give us some headroom and prevent Prometheus from timing out first.
-    scrape_timeout_offset: '500ms',
-    // Minimum interval between collector runs: by default (0s) collectors are executed on every scrape.
-    min_interval: '0s',
-    // Maximum number of open connections to any one target. Metric queries will run concurrently on multiple connections,
-    // as will concurrent scrapes.
-    max_connections: 1,
-    // Maximum number of idle connections to any one target. Unless you use very long collection intervals, this should
-    // always be the same as max_connections.
-    max_idle_connections: 1,
-    // Maximum number of maximum amount of time a connection may be reused. Expired connections may be closed lazily before reuse.
-    // If 0, connections are not closed due to a connection's age.
-    max_connection_lifetime: '5m',
-  },
-
-  // The target to monitor and the collectors to execute on it.
-  target: {
-    // Data source name always has a URI schema that matches the driver name. In some cases (e.g. MySQL)
-    // the schema gets dropped or replaced to match the driver expected DSN format.
-    data_source_name: std.format('postgresql://cloud_admin@127.0.0.1:5432/postgres?sslmode=disable&application_name=%s', [application_name]),
-
-    // Collectors (referenced by name) to execute on the target.
-    // Glob patterns are supported (see <https://pkg.go.dev/path/filepath#Match> for syntax).
-    collectors: [
-      'neon_collector_autoscaling',
-    ],
-  },
-
-  // Collector files specifies a list of globs. One collector definition is read from each matching file.
-  // Glob patterns are supported (see <https://pkg.go.dev/path/filepath#Match> for syntax).
-  collector_files: [
-    collector_file,
-  ],
-}

compute/etc/sql_exporter.yml

@@ -0,0 +1,33 @@
+# Configuration for sql_exporter
+# Global defaults.
+global:
+  # If scrape_timeout <= 0, no timeout is set unless Prometheus provides one. The default is 10s.
+  scrape_timeout: 10s
+  # Subtracted from Prometheus' scrape_timeout to give us some headroom and prevent Prometheus from timing out first.
+  scrape_timeout_offset: 500ms
+  # Minimum interval between collector runs: by default (0s) collectors are executed on every scrape.
+  min_interval: 0s
+  # Maximum number of open connections to any one target. Metric queries will run concurrently on multiple connections,
+  # as will concurrent scrapes.
+  max_connections: 1
+  # Maximum number of idle connections to any one target. Unless you use very long collection intervals, this should
+  # always be the same as max_connections.
+  max_idle_connections: 1
+  # Maximum number of maximum amount of time a connection may be reused. Expired connections may be closed lazily before reuse.
+  # If 0, connections are not closed due to a connection's age.
+  max_connection_lifetime: 5m
+
+# The target to monitor and the collectors to execute on it.
+target:
+  # Data source name always has a URI schema that matches the driver name. In some cases (e.g. MySQL)
+  # the schema gets dropped or replaced to match the driver expected DSN format.
+  data_source_name: 'postgresql://cloud_admin@127.0.0.1:5432/postgres?sslmode=disable&application_name=sql_exporter'
+
+  # Collectors (referenced by name) to execute on the target.
+  # Glob patterns are supported (see <https://pkg.go.dev/path/filepath#Match> for syntax).
+  collectors: [neon_collector]
+
+# Collector files specifies a list of globs. One collector definition is read from each matching file.
+# Glob patterns are supported (see <https://pkg.go.dev/path/filepath#Match> for syntax).
+collector_files:
+  - "neon_collector.yml"

compute/etc/sql_exporter/checkpoints_req.libsonnet

@@ -1,10 +0,0 @@
-{
-  metric_name: 'checkpoints_req',
-  type: 'gauge',
-  help: 'Number of requested checkpoints',
-  key_labels: null,
-  values: [
-    'checkpoints_req',
-  ],
-  query: importstr 'sql_exporter/checkpoints_req.sql',
-}

compute/etc/sql_exporter/checkpoints_req.sql

@@ -1 +0,0 @@
-SELECT checkpoints_req FROM pg_stat_bgwriter;

compute/etc/sql_exporter/checkpoints_timed.libsonnet

@@ -1,10 +0,0 @@
-{
-  metric_name: 'checkpoints_timed',
-  type: 'gauge',
-  help: 'Number of scheduled checkpoints',
-  key_labels: null,
-  values: [
-    'checkpoints_timed',
-  ],
-  query: importstr 'sql_exporter/checkpoints_timed.sql',
-}

compute/etc/sql_exporter/checkpoints_timed.sql

@@ -1 +0,0 @@
-SELECT checkpoints_timed FROM pg_stat_bgwriter;

compute/etc/sql_exporter/compute_current_lsn.libsonnet

@@ -1,10 +0,0 @@
-{
-  metric_name: 'compute_current_lsn',
-  type: 'gauge',
-  help: 'Current LSN of the database',
-  key_labels: null,
-  values: [
-    'lsn',
-  ],
-  query: importstr 'sql_exporter/compute_current_lsn.sql',
-}

compute/etc/sql_exporter/compute_current_lsn.sql

@@ -1,4 +0,0 @@
-SELECT CASE
-  WHEN pg_catalog.pg_is_in_recovery() THEN (pg_last_wal_replay_lsn() - '0/0')::FLOAT8
-  ELSE (pg_current_wal_lsn() - '0/0')::FLOAT8
-END AS lsn;

compute/etc/sql_exporter/compute_logical_snapshot_files.libsonnet

@@ -1,12 +0,0 @@
-{
-  metric_name: 'compute_logical_snapshot_files',
-  type: 'gauge',
-  help: 'Number of snapshot files in pg_logical/snapshot',
-  key_labels: [
-    'timeline_id',
-  ],
-  values: [
-    'num_logical_snapshot_files',
-  ],
-  query: importstr 'sql_exporter/compute_logical_snapshot_files.sql',
-}

compute/etc/sql_exporter/compute_logical_snapshot_files.sql

@@ -1,7 +0,0 @@
-SELECT
-  (SELECT setting FROM pg_settings WHERE name = 'neon.timeline_id') AS timeline_id,
-  -- Postgres creates temporary snapshot files of the form %X-%X.snap.%d.tmp.
-  -- These temporary snapshot files are renamed to the actual snapshot files
-  -- after they are completely built. We only WAL-log the completely built
-  -- snapshot files
-  (SELECT COUNT(*) FROM pg_ls_dir('pg_logical/snapshots') AS name WHERE name LIKE '%.snap') AS num_logical_snapshot_files;

compute/etc/sql_exporter/compute_receive_lsn.libsonnet

@@ -1,10 +0,0 @@
-{
-  metric_name: 'compute_receive_lsn',
-  type: 'gauge',
-  help: 'Returns the last write-ahead log location that has been received and synced to disk by streaming replication',
-  key_labels: null,
-  values: [
-    'lsn',
-  ],
-  query: importstr 'sql_exporter/compute_receive_lsn.sql',
-}

compute/etc/sql_exporter/compute_receive_lsn.sql

@@ -1,4 +0,0 @@
-SELECT CASE
-  WHEN pg_catalog.pg_is_in_recovery() THEN (pg_last_wal_receive_lsn() - '0/0')::FLOAT8
-  ELSE 0
-END AS lsn;

compute/etc/sql_exporter/compute_subscriptions_count.libsonnet

@@ -1,12 +0,0 @@
-{
-  metric_name: 'compute_subscriptions_count',
-  type: 'gauge',
-  help: 'Number of logical replication subscriptions grouped by enabled/disabled',
-  key_labels: [
-    'enabled',
-  ],
-  values: [
-    'subscriptions_count',
-  ],
-  query: importstr 'sql_exporter/compute_subscriptions_count.sql',
-}

compute/etc/sql_exporter/compute_subscriptions_count.sql

@@ -1 +0,0 @@
-SELECT subenabled::text AS enabled, count(*) AS subscriptions_count FROM pg_subscription GROUP BY subenabled;

compute/etc/sql_exporter/connection_counts.libsonnet

@@ -1,13 +0,0 @@
-{
-  metric_name: 'connection_counts',
-  type: 'gauge',
-  help: 'Connection counts',
-  key_labels: [
-    'datname',
-    'state',
-  ],
-  values: [
-    'count',
-  ],
-  query: importstr 'sql_exporter/connection_counts.sql',
-}

compute/etc/sql_exporter/connection_counts.sql

@@ -1 +0,0 @@
-SELECT datname, state, count(*) AS count FROM pg_stat_activity WHERE state <> '' GROUP BY datname, state;

compute/etc/sql_exporter/db_total_size.libsonnet

@@ -1,10 +0,0 @@
-{
-  metric_name: 'db_total_size',
-  type: 'gauge',
-  help: 'Size of all databases',
-  key_labels: null,
-  values: [
-    'total',
-  ],
-  query: importstr 'sql_exporter/db_total_size.sql',
-}

compute/etc/sql_exporter/db_total_size.sql

@@ -1 +0,0 @@
-SELECT sum(pg_database_size(datname)) AS total FROM pg_database;

compute/etc/sql_exporter/file_cache_read_wait_seconds_bucket.libsonnet

@@ -1,12 +0,0 @@
-{
-  metric_name: 'file_cache_read_wait_seconds_bucket',
-  type: 'counter',
-  help: 'Histogram buckets of LFC read operation latencies',
-  key_labels: [
-    'bucket_le',
-  ],
-  values: [
-    'value',
-  ],
-  query: importstr 'sql_exporter/file_cache_read_wait_seconds_bucket.sql',
-}

compute/etc/sql_exporter/file_cache_read_wait_seconds_bucket.sql

@@ -1 +0,0 @@
-SELECT bucket_le, value FROM neon.neon_perf_counters WHERE metric = 'file_cache_read_wait_seconds_bucket';

compute/etc/sql_exporter/file_cache_read_wait_seconds_count.libsonnet

@@ -1,9 +0,0 @@
-{
-  metric_name: 'file_cache_read_wait_seconds_count',
-  type: 'counter',
-  help: 'Number of read operations in LFC',
-  values: [
-    'file_cache_read_wait_seconds_count',
-  ],
-  query_ref: 'neon_perf_counters',
-}

compute/etc/sql_exporter/file_cache_read_wait_seconds_sum.libsonnet

@@ -1,9 +0,0 @@
-{
-  metric_name: 'file_cache_read_wait_seconds_sum',
-  type: 'counter',
-  help: 'Time spent in LFC read operations',
-  values: [
-    'file_cache_read_wait_seconds_sum',
-  ],
-  query_ref: 'neon_perf_counters',
-}

compute/etc/sql_exporter/file_cache_write_wait_seconds_bucket.libsonnet

@@ -1,12 +0,0 @@
-{
-  metric_name: 'file_cache_write_wait_seconds_bucket',
-  type: 'counter',
-  help: 'Histogram buckets of LFC write operation latencies',
-  key_labels: [
-    'bucket_le',
-  ],
-  values: [
-    'value',
-  ],
-  query: importstr 'sql_exporter/file_cache_write_wait_seconds_bucket.sql',
-}

compute/etc/sql_exporter/file_cache_write_wait_seconds_bucket.sql

@@ -1 +0,0 @@
-SELECT bucket_le, value FROM neon.neon_perf_counters WHERE metric = 'file_cache_write_wait_seconds_bucket';

compute/etc/sql_exporter/file_cache_write_wait_seconds_count.libsonnet

@@ -1,9 +0,0 @@
-{
-  metric_name: 'file_cache_write_wait_seconds_count',
-  type: 'counter',
-  help: 'Number of write operations in LFC',
-  values: [
-    'file_cache_write_wait_seconds_count',
-  ],
-  query_ref: 'neon_perf_counters',
-}

compute/etc/sql_exporter/file_cache_write_wait_seconds_sum.libsonnet

@@ -1,9 +0,0 @@
-{
-  metric_name: 'file_cache_write_wait_seconds_sum',
-  type: 'counter',
-  help: 'Time spent in LFC write operations',
-  values: [
-    'file_cache_write_wait_seconds_sum',
-  ],
-  query_ref: 'neon_perf_counters',
-}

compute/etc/sql_exporter/getpage_prefetch_discards_total.libsonnet

@@ -1,9 +0,0 @@
-{
-  metric_name: 'getpage_prefetch_discards_total',
-  type: 'counter',
-  help: 'Number of prefetch responses issued but not used',
-  values: [
-    'getpage_prefetch_discards_total',
-  ],
-  query_ref: 'neon_perf_counters',
-}

compute/etc/sql_exporter/getpage_prefetch_misses_total.libsonnet

@@ -1,9 +0,0 @@
-{
-  metric_name: 'getpage_prefetch_misses_total',
-  type: 'counter',
-  help: "Total number of readahead misses; consisting of either prefetches that don't satisfy the LSN bounds once the prefetch got read by the backend, or cases where somehow no readahead was issued for the read",
-  values: [
-    'getpage_prefetch_misses_total',
-  ],
-  query_ref: 'neon_perf_counters',
-}

compute/etc/sql_exporter/getpage_prefetch_requests_total.libsonnet

@@ -1,9 +0,0 @@
-{
-  metric_name: 'getpage_prefetch_requests_total',
-  type: 'counter',
-  help: 'Number of getpage issued for prefetching',
-  values: [
-    'getpage_prefetch_requests_total',
-  ],
-  query_ref: 'neon_perf_counters',
-}

compute/etc/sql_exporter/getpage_prefetches_buffered.libsonnet

@@ -1,9 +0,0 @@
-{
-  metric_name: 'getpage_prefetches_buffered',
-  type: 'gauge',
-  help: 'Number of prefetched pages buffered in neon',
-  values: [
-    'getpage_prefetches_buffered',
-  ],
-  query_ref: 'neon_perf_counters',
-}

compute/etc/sql_exporter/getpage_sync_requests_total.libsonnet

@@ -1,9 +0,0 @@
-{
-  metric_name: 'getpage_sync_requests_total',
-  type: 'counter',
-  help: 'Number of synchronous getpage issued',
-  values: [
-    'getpage_sync_requests_total',
-  ],
-  query_ref: 'neon_perf_counters',
-}

compute/etc/sql_exporter/getpage_wait_seconds_bucket.libsonnet

@@ -1,12 +0,0 @@
-{
-  metric_name: 'getpage_wait_seconds_bucket',
-  type: 'counter',
-  help: 'Histogram buckets of getpage request latency',
-  key_labels: [
-    'bucket_le',
-  ],
-  values: [
-    'value',
-  ],
-  query: importstr 'sql_exporter/getpage_wait_seconds_bucket.sql',
-}

compute/etc/sql_exporter/getpage_wait_seconds_bucket.sql

@@ -1 +0,0 @@
-SELECT bucket_le, value FROM neon.neon_perf_counters WHERE metric = 'getpage_wait_seconds_bucket';

compute/etc/sql_exporter/getpage_wait_seconds_count.libsonnet

@@ -1,9 +0,0 @@
-{
-  metric_name: 'getpage_wait_seconds_count',
-  type: 'counter',
-  help: 'Number of getpage requests',
-  values: [
-    'getpage_wait_seconds_count',
-  ],
-  query_ref: 'neon_perf_counters',
-}

compute/etc/sql_exporter/getpage_wait_seconds_sum.libsonnet

@@ -1,9 +0,0 @@
-{
-  metric_name: 'getpage_wait_seconds_sum',
-  type: 'counter',
-  help: 'Time spent in getpage requests',
-  values: [
-    'getpage_wait_seconds_sum',
-  ],
-  query_ref: 'neon_perf_counters',
-}

compute/etc/sql_exporter/lfc_approximate_working_set_size.libsonnet

@@ -1,12 +0,0 @@
-// DEPRECATED
-
-{
-  metric_name: 'lfc_approximate_working_set_size',
-  type: 'gauge',
-  help: 'Approximate working set size in pages of 8192 bytes',
-  key_labels: null,
-  values: [
-    'approximate_working_set_size',
-  ],
-  query: importstr 'sql_exporter/lfc_approximate_working_set_size.sql',
-}

compute/etc/sql_exporter/lfc_approximate_working_set_size.sql

@@ -1 +0,0 @@
-SELECT neon.approximate_working_set_size(false) AS approximate_working_set_size;

compute/etc/sql_exporter/lfc_approximate_working_set_size_windows.autoscaling.libsonnet

@@ -1,12 +0,0 @@
-{
-  metric_name: 'lfc_approximate_working_set_size_windows',
-  type: 'gauge',
-  help: 'Approximate working set size in pages of 8192 bytes',
-  key_labels: [
-    'duration_seconds',
-  ],
-  values: [
-    'size',
-  ],
-  query: importstr 'sql_exporter/lfc_approximate_working_set_size_windows.autoscaling.sql',
-}

compute/etc/sql_exporter/lfc_approximate_working_set_size_windows.autoscaling.sql

@@ -1,8 +0,0 @@
--- NOTE: This is the "internal" / "machine-readable" version. This outputs the
--- working set size looking back 1..60 minutes, labeled with the number of
--- minutes.
-
-SELECT
-  x::text as duration_seconds,
-  neon.approximate_working_set_size_seconds(x) AS size
-FROM (SELECT generate_series * 60 AS x FROM generate_series(1, 60)) AS t (x);

compute/etc/sql_exporter/lfc_approximate_working_set_size_windows.libsonnet

@@ -1,12 +0,0 @@
-{
-  metric_name: 'lfc_approximate_working_set_size_windows',
-  type: 'gauge',
-  help: 'Approximate working set size in pages of 8192 bytes',
-  key_labels: [
-    'duration',
-  ],
-  values: [
-    'size',
-  ],
-  query: importstr 'sql_exporter/lfc_approximate_working_set_size_windows.sql',
-}

compute/etc/sql_exporter/lfc_approximate_working_set_size_windows.sql

@@ -1,8 +0,0 @@
--- NOTE: This is the "public" / "human-readable" version. Here, we supply a
--- small selection of durations in a pretty-printed form.
-
-SELECT
-  x AS duration,
-  neon.approximate_working_set_size_seconds(extract('epoch' FROM x::interval)::int) AS size FROM (
-    VALUES ('5m'), ('15m'), ('1h')
-  ) AS t (x);

compute/etc/sql_exporter/lfc_cache_size_limit.libsonnet

@@ -1,10 +0,0 @@
-{
-  metric_name: 'lfc_cache_size_limit',
-  type: 'gauge',
-  help: 'LFC cache size limit in bytes',
-  key_labels: null,
-  values: [
-    'lfc_cache_size_limit',
-  ],
-  query: importstr 'sql_exporter/lfc_cache_size_limit.sql',
-}

compute/etc/sql_exporter/lfc_cache_size_limit.sql

@@ -1 +0,0 @@
-SELECT pg_size_bytes(current_setting('neon.file_cache_size_limit')) AS lfc_cache_size_limit;

compute/etc/sql_exporter/lfc_hits.libsonnet

@@ -1,10 +0,0 @@
-{
-  metric_name: 'lfc_hits',
-  type: 'gauge',
-  help: 'lfc_hits',
-  key_labels: null,
-  values: [
-    'lfc_hits',
-  ],
-  query: importstr 'sql_exporter/lfc_hits.sql',
-}

compute/etc/sql_exporter/lfc_hits.sql

@@ -1 +0,0 @@
-SELECT lfc_value AS lfc_hits FROM neon.neon_lfc_stats WHERE lfc_key = 'file_cache_hits';

compute/etc/sql_exporter/lfc_misses.libsonnet

@@ -1,10 +0,0 @@
-{
-  metric_name: 'lfc_misses',
-  type: 'gauge',
-  help: 'lfc_misses',
-  key_labels: null,
-  values: [
-    'lfc_misses',
-  ],
-  query: importstr 'sql_exporter/lfc_misses.sql',
-}

compute/etc/sql_exporter/lfc_misses.sql

@@ -1 +0,0 @@
-SELECT lfc_value AS lfc_misses FROM neon.neon_lfc_stats WHERE lfc_key = 'file_cache_misses';

compute/etc/sql_exporter/lfc_used.libsonnet

@@ -1,10 +0,0 @@
-{
-  metric_name: 'lfc_used',
-  type: 'gauge',
-  help: 'LFC chunks used (chunk = 1MB)',
-  key_labels: null,
-  values: [
-    'lfc_used',
-  ],
-  query: importstr 'sql_exporter/lfc_used.sql',
-}

compute/etc/sql_exporter/lfc_used.sql

@@ -1 +0,0 @@
-SELECT lfc_value AS lfc_used FROM neon.neon_lfc_stats WHERE lfc_key = 'file_cache_used';

compute/etc/sql_exporter/lfc_writes.libsonnet

@@ -1,10 +0,0 @@
-{
-  metric_name: 'lfc_writes',
-  type: 'gauge',
-  help: 'lfc_writes',
-  key_labels: null,
-  values: [
-    'lfc_writes',
-  ],
-  query: importstr 'sql_exporter/lfc_writes.sql',
-}

compute/etc/sql_exporter/lfc_writes.sql

@@ -1 +0,0 @@
-SELECT lfc_value AS lfc_writes FROM neon.neon_lfc_stats WHERE lfc_key = 'file_cache_writes';

compute/etc/sql_exporter/logical_slot_restart_lsn.libsonnet

@@ -1,15 +0,0 @@
-// Number of slots is limited by max_replication_slots, so collecting position
-// for all of them shouldn't be bad.
-
-{
-  metric_name: 'logical_slot_restart_lsn',
-  type: 'gauge',
-  help: 'restart_lsn of logical slots',
-  key_labels: [
-    'slot_name',
-  ],
-  values: [
-    'restart_lsn',
-  ],
-  query: importstr 'sql_exporter/logical_slot_restart_lsn.sql',
-}

compute/etc/sql_exporter/logical_slot_restart_lsn.sql

@@ -1,3 +0,0 @@
-SELECT slot_name, (restart_lsn - '0/0')::FLOAT8 as restart_lsn
-FROM pg_replication_slots
-WHERE slot_type = 'logical';

compute/etc/sql_exporter/max_cluster_size.libsonnet

@@ -1,10 +0,0 @@
-{
-  metric_name: 'max_cluster_size',
-  type: 'gauge',
-  help: 'neon.max_cluster_size setting',
-  key_labels: null,
-  values: [
-    'max_cluster_size',
-  ],
-  query: importstr 'sql_exporter/max_cluster_size.sql',
-}

compute/etc/sql_exporter/max_cluster_size.sql

@@ -1 +0,0 @@
-SELECT setting::int AS max_cluster_size FROM pg_settings WHERE name = 'neon.max_cluster_size';

compute/etc/sql_exporter/neon_perf_counters.sql

@@ -1,19 +0,0 @@
-WITH c AS (SELECT pg_catalog.jsonb_object_agg(metric, value) jb FROM neon.neon_perf_counters)
-
-SELECT d.* FROM pg_catalog.jsonb_to_record((SELECT jb FROM c)) AS d(
-  file_cache_read_wait_seconds_count numeric,
-  file_cache_read_wait_seconds_sum numeric,
-  file_cache_write_wait_seconds_count numeric,
-  file_cache_write_wait_seconds_sum numeric,
-  getpage_wait_seconds_count numeric,
-  getpage_wait_seconds_sum numeric,
-  getpage_prefetch_requests_total numeric,
-  getpage_sync_requests_total numeric,
-  getpage_prefetch_misses_total numeric,
-  getpage_prefetch_discards_total numeric,
-  getpage_prefetches_buffered numeric,
-  pageserver_requests_sent_total numeric,
-  pageserver_disconnects_total numeric,
-  pageserver_send_flushes_total numeric,
-  pageserver_open_requests numeric
-);

compute/etc/sql_exporter/pageserver_disconnects_total.libsonnet

@@ -1,9 +0,0 @@
-{
-  metric_name: 'pageserver_disconnects_total',
-  type: 'counter',
-  help: 'Number of times that the connection to the pageserver was lost',
-  values: [
-    'pageserver_disconnects_total',
-  ],
-  query_ref: 'neon_perf_counters',
-}

compute/etc/sql_exporter/pageserver_open_requests.libsonnet

@@ -1,9 +0,0 @@
-{
-  metric_name: 'pageserver_open_requests',
-  type: 'gauge',
-  help: 'Number of open requests to PageServer',
-  values: [
-    'pageserver_open_requests',
-  ],
-  query_ref: 'neon_perf_counters',
-}

compute/etc/sql_exporter/pageserver_requests_sent_total.libsonnet

@@ -1,9 +0,0 @@
-{
-  metric_name: 'pageserver_requests_sent_total',
-  type: 'counter',
-  help: 'Number of all requests sent to the pageserver (not just GetPage requests)',
-  values: [
-    'pageserver_requests_sent_total',
-  ],
-  query_ref: 'neon_perf_counters',
-}

compute/etc/sql_exporter/pageserver_send_flushes_total.libsonnet

@@ -1,9 +0,0 @@
-{
-  metric_name: 'pageserver_send_flushes_total',
-  type: 'counter',
-  help: 'Number of flushes to the pageserver connection',
-  values: [
-    'pageserver_send_flushes_total',
-  ],
-  query_ref: 'neon_perf_counters',
-}

compute/etc/sql_exporter/pg_stats_userdb.libsonnet

@@ -1,18 +0,0 @@
-{
-  metric_name: 'pg_stats_userdb',
-  type: 'gauge',
-  help: 'Stats for several oldest non-system dbs',
-  key_labels: [
-    'datname',
-  ],
-  value_label: 'kind',
-  values: [
-    'db_size',
-    'deadlocks',
-    // Rows
-    'inserted',
-    'updated',
-    'deleted',
-  ],
-  query: importstr 'sql_exporter/pg_stats_userdb.sql',
-}

compute/etc/sql_exporter/pg_stats_userdb.sql

@@ -1,10 +0,0 @@
--- We export stats for 10 non-system databases. Without this limit it is too
--- easy to abuse the system by creating lots of databases.
-
-SELECT pg_database_size(datname) AS db_size, deadlocks, tup_inserted AS inserted,
-  tup_updated AS updated, tup_deleted AS deleted, datname
-FROM pg_stat_database
-WHERE datname IN (
-  SELECT datname FROM pg_database
-  WHERE datname <> 'postgres' AND NOT datistemplate ORDER BY oid LIMIT 10
-);

compute/etc/sql_exporter/replication_delay_bytes.libsonnet

@@ -1,10 +0,0 @@
-{
-  metric_name: 'replication_delay_bytes',
-  type: 'gauge',
-  help: 'Bytes between received and replayed LSN',
-  key_labels: null,
-  values: [
-    'replication_delay_bytes',
-  ],
-  query: importstr 'sql_exporter/replication_delay_bytes.sql',
-}

compute/etc/sql_exporter/replication_delay_bytes.sql

@@ -1,6 +0,0 @@
--- We use a GREATEST call here because this calculation can be negative. The
--- calculation is not atomic, meaning after we've gotten the receive LSN, the
--- replay LSN may have advanced past the receive LSN we are using for the
--- calculation.
-
-SELECT GREATEST(0, pg_wal_lsn_diff(pg_last_wal_receive_lsn(), pg_last_wal_replay_lsn())) AS replication_delay_bytes;

compute/etc/sql_exporter/replication_delay_seconds.libsonnet

@@ -1,10 +0,0 @@
-{
-  metric_name: 'replication_delay_seconds',
-  type: 'gauge',
-  help: 'Time since last LSN was replayed',
-  key_labels: null,
-  values: [
-    'replication_delay_seconds',
-  ],
-  query: importstr 'sql_exporter/replication_delay_seconds.sql',
-}

compute/etc/sql_exporter/replication_delay_seconds.sql

@@ -1,5 +0,0 @@
-SELECT
-  CASE
-    WHEN pg_last_wal_receive_lsn() = pg_last_wal_replay_lsn() THEN 0
-    ELSE GREATEST(0, EXTRACT (EPOCH FROM now() - pg_last_xact_replay_timestamp()))
-  END AS replication_delay_seconds;

compute/etc/sql_exporter/retained_wal.libsonnet

@@ -1,12 +0,0 @@
-{
-  metric_name: 'retained_wal',
-  type: 'gauge',
-  help: 'Retained WAL in inactive replication slots',
-  key_labels: [
-    'slot_name',
-  ],
-  values: [
-    'retained_wal',
-  ],
-  query: importstr 'sql_exporter/retained_wal.sql',
-}

compute/etc/sql_exporter/retained_wal.sql

@@ -1,5 +0,0 @@
-SELECT
-  slot_name,
-  pg_wal_lsn_diff(pg_current_wal_lsn(), restart_lsn)::FLOAT8 AS retained_wal
-FROM pg_replication_slots
-WHERE active = false;

compute/etc/sql_exporter/wal_is_lost.libsonnet

@@ -1,12 +0,0 @@
-{
-  metric_name: 'wal_is_lost',
-  type: 'gauge',
-  help: 'Whether or not the replication slot wal_status is lost',
-  key_labels: [
-    'slot_name',
-  ],
-  values: [
-    'wal_is_lost',
-  ],
-  query: importstr 'sql_exporter/wal_is_lost.sql',
-}

compute/etc/sql_exporter/wal_is_lost.sql

@@ -1,7 +0,0 @@
-SELECT
-  slot_name,
-  CASE
-    WHEN wal_status = 'lost' THEN 1
-    ELSE 0
-  END AS wal_is_lost
-FROM pg_replication_slots;

compute/etc/sql_exporter_autoscaling.yml

@@ -0,0 +1,33 @@
+# Configuration for sql_exporter for autoscaling-agent
+# Global defaults.
+global:
+  # If scrape_timeout <= 0, no timeout is set unless Prometheus provides one. The default is 10s.
+  scrape_timeout: 10s
+  # Subtracted from Prometheus' scrape_timeout to give us some headroom and prevent Prometheus from timing out first.
+  scrape_timeout_offset: 500ms
+  # Minimum interval between collector runs: by default (0s) collectors are executed on every scrape.
+  min_interval: 0s
+  # Maximum number of open connections to any one target. Metric queries will run concurrently on multiple connections,
+  # as will concurrent scrapes.
+  max_connections: 1
+  # Maximum number of idle connections to any one target. Unless you use very long collection intervals, this should
+  # always be the same as max_connections.
+  max_idle_connections: 1
+  # Maximum number of maximum amount of time a connection may be reused. Expired connections may be closed lazily before reuse.
+  # If 0, connections are not closed due to a connection's age.
+  max_connection_lifetime: 5m
+
+# The target to monitor and the collectors to execute on it.
+target:
+  # Data source name always has a URI schema that matches the driver name. In some cases (e.g. MySQL)
+  # the schema gets dropped or replaced to match the driver expected DSN format.
+  data_source_name: 'postgresql://cloud_admin@127.0.0.1:5432/postgres?sslmode=disable&application_name=sql_exporter_autoscaling'
+
+  # Collectors (referenced by name) to execute on the target.
+  # Glob patterns are supported (see <https://pkg.go.dev/path/filepath#Match> for syntax).
+  collectors: [neon_collector_autoscaling]
+
+# Collector files specifies a list of globs. One collector definition is read from each matching file.
+# Glob patterns are supported (see <https://pkg.go.dev/path/filepath#Match> for syntax).
+collector_files:
+  - "neon_collector_autoscaling.yml"

compute/vm-image-spec-bookworm.yaml

@@ -1,126 +0,0 @@
-# Supplemental file for neondatabase/autoscaling's vm-builder, for producing the VM compute image.
----
-commands:
-  - name: cgconfigparser
-    user: root
-    sysvInitAction: sysinit
-    shell: 'cgconfigparser -l /etc/cgconfig.conf -s 1664'
-  # restrict permissions on /neonvm/bin/resize-swap, because we grant access to compute_ctl for
-  # running it as root.
-  - name: chmod-resize-swap
-    user: root
-    sysvInitAction: sysinit
-    shell: 'chmod 711 /neonvm/bin/resize-swap'
-  - name: chmod-set-disk-quota
-    user: root
-    sysvInitAction: sysinit
-    shell: 'chmod 711 /neonvm/bin/set-disk-quota'
-  - name: pgbouncer
-    user: postgres
-    sysvInitAction: respawn
-    shell: '/usr/local/bin/pgbouncer /etc/pgbouncer.ini'
-  - name: local_proxy
-    user: postgres
-    sysvInitAction: respawn
-    shell: '/usr/local/bin/local_proxy --config-path /etc/local_proxy/config.json --pid-path /etc/local_proxy/pid --http 0.0.0.0:10432'
-  - name: postgres-exporter
-    user: nobody
-    sysvInitAction: respawn
-    shell: 'DATA_SOURCE_NAME="user=cloud_admin sslmode=disable dbname=postgres application_name=postgres-exporter" /bin/postgres_exporter'
-  - name: sql-exporter
-    user: nobody
-    sysvInitAction: respawn
-    shell: '/bin/sql_exporter -config.file=/etc/sql_exporter.yml -web.listen-address=:9399'
-  - name: sql-exporter-autoscaling
-    user: nobody
-    sysvInitAction: respawn
-    shell: '/bin/sql_exporter -config.file=/etc/sql_exporter_autoscaling.yml -web.listen-address=:9499'
-shutdownHook: |
-  su -p postgres --session-command '/usr/local/bin/pg_ctl stop -D /var/db/postgres/compute/pgdata -m fast --wait -t 10'
-files:
-  - filename: compute_ctl-sudoers
-    content: |
-      # Allow postgres user (which is what compute_ctl runs as) to run /neonvm/bin/resize-swap
-      # and /neonvm/bin/set-disk-quota as root without requiring entering a password (NOPASSWD),
-      # regardless of hostname (ALL)
-      postgres ALL=(root) NOPASSWD: /neonvm/bin/resize-swap, /neonvm/bin/set-disk-quota
-  - filename: cgconfig.conf
-    content: |
-      # Configuration for cgroups in VM compute nodes
-      group neon-postgres {
-          perm {
-              admin {
-                  uid = postgres;
-              }
-              task {
-                  gid = users;
-              }
-          }
-          memory {}
-      }
-build: |
-  # Build cgroup-tools
-  #
-  # At time of writing (2023-03-14), debian bullseye has a version of cgroup-tools (technically
-  # libcgroup) that doesn't support cgroup v2 (version 0.41-11). Unfortunately, the vm-monitor
-  # requires cgroup v2, so we'll build cgroup-tools ourselves.
-  #
-  # At time of migration to bookworm (2024-10-09), debian has a version of libcgroup/cgroup-tools 2.0.2,
-  # and it _probably_ can be used as-is. However, we'll build it ourselves to minimise the changeset
-  # for debian version migration.
-  #
-  FROM debian:bookworm-slim as libcgroup-builder
-  ENV LIBCGROUP_VERSION=v2.0.3
-
-  RUN set -exu \
-      && apt update \
-      && apt install --no-install-recommends -y \
-          git \
-          ca-certificates \
-          automake \
-          cmake \
-          make \
-          gcc \
-          byacc \
-          flex \
-          libtool \
-          libpam0g-dev \
-      && git clone --depth 1 -b $LIBCGROUP_VERSION https://github.com/libcgroup/libcgroup \
-      && INSTALL_DIR="/libcgroup-install" \
-      && mkdir -p "$INSTALL_DIR/bin" "$INSTALL_DIR/include" \
-      && cd libcgroup \
-      # extracted from bootstrap.sh, with modified flags:
-      && (test -d m4 || mkdir m4) \
-      && autoreconf -fi \
-      && rm -rf autom4te.cache \
-      && CFLAGS="-O3" ./configure --prefix="$INSTALL_DIR" --sysconfdir=/etc --localstatedir=/var --enable-opaque-hierarchy="name=systemd" \
-      # actually build the thing...
-      && make install
-merge: |
-  # tweak nofile limits
-  RUN set -e \
-      && echo 'fs.file-max = 1048576' >>/etc/sysctl.conf \
-      && test ! -e /etc/security || ( \
-         echo '*    - nofile 1048576' >>/etc/security/limits.conf \
-      && echo 'root - nofile 1048576' >>/etc/security/limits.conf \
-         )
-
-  # Allow postgres user (compute_ctl) to run swap resizer.
-  # Need to install sudo in order to allow this.
-  #
-  # Also, remove the 'read' permission from group/other on /neonvm/bin/resize-swap, just to be safe.
-  RUN set -e \
-      && apt update \
-      && apt install --no-install-recommends -y \
-             sudo \
-      && rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
-  COPY compute_ctl-sudoers /etc/sudoers.d/compute_ctl-sudoers
-
-  COPY cgconfig.conf /etc/cgconfig.conf
-
-  RUN set -e \
-      && chmod 0644 /etc/cgconfig.conf
-
-  COPY --from=libcgroup-builder /libcgroup-install/bin/*  /usr/bin/
-  COPY --from=libcgroup-builder /libcgroup-install/lib/*  /usr/lib/
-  COPY --from=libcgroup-builder /libcgroup-install/sbin/* /usr/sbin/

control_plane/src/endpoint.rs

@@ -97,21 +97,7 @@ impl ComputeControlPlane {
         for endpoint_dir in std::fs::read_dir(env.endpoints_path())
             .with_context(|| format!("failed to list {}", env.endpoints_path().display()))?
         {
-            let ep_res = Endpoint::from_dir_entry(endpoint_dir?, &env);
-            let ep = match ep_res {
-                Ok(ep) => ep,
-                Err(e) => match e.downcast::<std::io::Error>() {
-                    Ok(e) => {
-                        // A parallel task could delete an endpoint while we have just scanned the directory
-                        if e.kind() == std::io::ErrorKind::NotFound {
-                            continue;
-                        } else {
-                            Err(e)?
-                        }
-                    }
-                    Err(e) => Err(e)?,
-                },
-            };
+            let ep = Endpoint::from_dir_entry(endpoint_dir?, &env)?;
             endpoints.insert(ep.endpoint_id.clone(), Arc::new(ep));
         }
 

libs/utils/src/http/error.rs

@@ -28,9 +28,6 @@ pub enum ApiError {
     #[error("Resource temporarily unavailable: {0}")]
     ResourceUnavailable(Cow<'static, str>),
 
-    #[error("Too many requests: {0}")]
-    TooManyRequests(Cow<'static, str>),
-
     #[error("Shutting down")]
     ShuttingDown,
 
@@ -76,10 +73,6 @@ impl ApiError {
                 err.to_string(),
                 StatusCode::SERVICE_UNAVAILABLE,
             ),
-            ApiError::TooManyRequests(err) => HttpErrorBody::response_from_msg_and_status(
-                err.to_string(),
-                StatusCode::TOO_MANY_REQUESTS,
-            ),
             ApiError::Timeout(err) => HttpErrorBody::response_from_msg_and_status(
                 err.to_string(),
                 StatusCode::REQUEST_TIMEOUT,

pageserver/src/basebackup.rs

@@ -16,7 +16,7 @@ use fail::fail_point;
 use pageserver_api::key::Key;
 use postgres_ffi::pg_constants;
 use std::fmt::Write as FmtWrite;
-use std::time::{Instant, SystemTime};
+use std::time::SystemTime;
 use tokio::io;
 use tokio::io::AsyncWrite;
 use tracing::*;
@@ -352,25 +352,12 @@ where
             }
         }
 
-        let start_time = Instant::now();
-        let aux_files = self
+        for (path, content) in self
             .timeline
             .list_aux_files(self.lsn, self.ctx)
             .await
-            .map_err(|e| BasebackupError::Server(e.into()))?;
-        let aux_scan_time = start_time.elapsed();
-        let aux_estimated_size = aux_files
-            .values()
-            .map(|content| content.len())
-            .sum::<usize>();
-        info!(
-            "Scanned {} aux files in {}ms, aux file content size = {}",
-            aux_files.len(),
-            aux_scan_time.as_millis(),
-            aux_estimated_size
-        );
-
-        for (path, content) in aux_files {
+            .map_err(|e| BasebackupError::Server(e.into()))?
+        {
             if path.starts_with("pg_replslot") {
                 let offs = pg_constants::REPL_SLOT_ON_DISK_OFFSETOF_RESTART_LSN;
                 let restart_lsn = Lsn(u64::from_le_bytes(

pageserver/src/http/routes.rs

@@ -77,7 +77,6 @@ use crate::tenant::secondary::SecondaryController;
 use crate::tenant::size::ModelInputs;
 use crate::tenant::storage_layer::LayerAccessStatsReset;
 use crate::tenant::storage_layer::LayerName;
-use crate::tenant::timeline::offload::offload_timeline;
 use crate::tenant::timeline::CompactFlags;
 use crate::tenant::timeline::CompactionError;
 use crate::tenant::timeline::Timeline;
@@ -326,7 +325,6 @@ impl From<crate::tenant::TimelineArchivalError> for ApiError {
         match value {
             NotFound => ApiError::NotFound(anyhow::anyhow!("timeline not found").into()),
             Timeout => ApiError::Timeout("hit pageserver internal timeout".into()),
-            Cancelled => ApiError::ShuttingDown,
             e @ HasArchivedParent(_) => {
                 ApiError::PreconditionFailed(e.to_string().into_boxed_str())
             }
@@ -717,8 +715,6 @@ async fn timeline_archival_config_handler(
             .tenant_manager
             .get_attached_tenant_shard(tenant_shard_id)?;
 
-        tenant.wait_to_become_active(ACTIVE_TENANT_TIMEOUT).await?;
-
         tenant
             .apply_timeline_archival_config(timeline_id, request_data.state, ctx)
             .await?;
@@ -1787,49 +1783,6 @@ async fn timeline_compact_handler(
     .await
 }
 
-// Run offload immediately on given timeline.
-async fn timeline_offload_handler(
-    request: Request<Body>,
-    _cancel: CancellationToken,
-) -> Result<Response<Body>, ApiError> {
-    let tenant_shard_id: TenantShardId = parse_request_param(&request, "tenant_shard_id")?;
-    let timeline_id: TimelineId = parse_request_param(&request, "timeline_id")?;
-    check_permission(&request, Some(tenant_shard_id.tenant_id))?;
-
-    let state = get_state(&request);
-
-    async {
-        let tenant = state
-            .tenant_manager
-            .get_attached_tenant_shard(tenant_shard_id)?;
-
-        if tenant.get_offloaded_timeline(timeline_id).is_ok() {
-            return json_response(StatusCode::OK, ());
-        }
-        let timeline =
-            active_timeline_of_active_tenant(&state.tenant_manager, tenant_shard_id, timeline_id)
-                .await?;
-
-        if !tenant.timeline_has_no_attached_children(timeline_id) {
-            return Err(ApiError::PreconditionFailed(
-                "timeline has attached children".into(),
-            ));
-        }
-        if !timeline.can_offload() {
-            return Err(ApiError::PreconditionFailed(
-                "Timeline::can_offload() returned false".into(),
-            ));
-        }
-        offload_timeline(&tenant, &timeline)
-            .await
-            .map_err(ApiError::InternalServerError)?;
-
-        json_response(StatusCode::OK, ())
-    }
-    .instrument(info_span!("manual_timeline_offload", tenant_id = %tenant_shard_id.tenant_id, shard_id = %tenant_shard_id.shard_slug(), %timeline_id))
-    .await
-}
-
 // Run checkpoint immediately on given timeline.
 async fn timeline_checkpoint_handler(
     request: Request<Body>,
@@ -3053,10 +3006,6 @@ pub fn make_router(
             "/v1/tenant/:tenant_shard_id/timeline/:timeline_id/compact",
             |r| api_handler(r, timeline_compact_handler),
         )
-        .put(
-            "/v1/tenant/:tenant_shard_id/timeline/:timeline_id/offload",
-            |r| testing_api_handler("attempt timeline offload", r, timeline_offload_handler),
-        )
         .put(
             "/v1/tenant/:tenant_shard_id/timeline/:timeline_id/checkpoint",
             |r| testing_api_handler("run timeline checkpoint", r, timeline_checkpoint_handler),

pageserver/src/page_service.rs

@@ -26,8 +26,8 @@ use std::str::FromStr;
 use std::sync::Arc;
 use std::time::SystemTime;
 use std::time::{Duration, Instant};
+use tokio::io::AsyncWriteExt;
 use tokio::io::{AsyncRead, AsyncWrite};
-use tokio::io::{AsyncWriteExt, BufWriter};
 use tokio::task::JoinHandle;
 use tokio_util::sync::CancellationToken;
 use tracing::*;
@@ -1137,10 +1137,10 @@ impl PageServerHandler {
             .await
             .map_err(map_basebackup_error)?;
         } else {
-            let mut writer = BufWriter::new(pgb.copyout_writer());
+            let mut writer = pgb.copyout_writer();
             if gzip {
                 let mut encoder = GzipEncoder::with_quality(
-                    &mut writer,
+                    writer,
                     // NOTE using fast compression because it's on the critical path
                     //      for compute startup. For an empty database, we get
                     //      <100KB with this method. The Level::Best compression method
@@ -1175,10 +1175,6 @@ impl PageServerHandler {
                 .await
                 .map_err(map_basebackup_error)?;
             }
-            writer
-                .flush()
-                .await
-                .map_err(|e| map_basebackup_error(BasebackupError::Client(e)))?;
         }
 
         pgb.write_message_noflush(&BeMessage::CopyDone)

pageserver/src/pgdatadir_mapping.rs

@@ -1545,6 +1545,9 @@ impl<'a> DatadirModification<'a> {
             // Update relation size cache
             self.tline.set_cached_rel_size(rel, self.lsn, nblocks);
 
+            // Update relation size cache
+            self.tline.set_cached_rel_size(rel, self.lsn, nblocks);
+
             // Update logical database size.
             self.pending_nblocks -= old_size as i64 - nblocks as i64;
         }