Merge remote-tracking branch 'upstream/main' into jcsp/always-detach-…

…before-delete
neondatabase · Jun 21, 2024 · 3ce9b55 · 3ce9b55
2 parents f27d24a + 59f949b
commit 3ce9b55
Show file tree

Hide file tree

Showing 105 changed files with 3,045 additions and 2,036 deletions.
diff --git a/.github/actions/run-python-test-set/action.yml b/.github/actions/run-python-test-set/action.yml
@@ -183,8 +183,7 @@ runs:
 
         # Run the tests.
         #
-        # The junit.xml file allows CI tools to display more fine-grained test information
-        # in its "Tests" tab in the results page.
+        # --alluredir saves test results in Allure format (in a specified directory)
         # --verbose prints name of each test (helpful when there are
         # multiple tests in one file)
         # -rA prints summary in the end
@@ -193,7 +192,6 @@ runs:
         #
         mkdir -p $TEST_OUTPUT/allure/results
         "${cov_prefix[@]}" ./scripts/pytest \
-          --junitxml=$TEST_OUTPUT/junit.xml \
           --alluredir=$TEST_OUTPUT/allure/results \
           --tb=short \
           --verbose \

diff --git a/.github/workflows/actionlint.yml b/.github/workflows/actionlint.yml
@@ -36,15 +36,16 @@ jobs:
           fail_on_error: true
           filter_mode: nofilter
           level: error
-      - run: |
+
+      - name: Disallow 'ubuntu-latest' runners
+        run: |
           PAT='^\s*runs-on:.*-latest'
-          if grep -ERq $PAT .github/workflows
-          then
+          if grep -ERq $PAT .github/workflows; then
             grep -ERl $PAT .github/workflows |\
             while read -r f
             do
               l=$(grep -nE $PAT .github/workflows/release.yml | awk -F: '{print $1}' | head -1)
-              echo "::error file=$f,line=$l::Please, do not use ubuntu-latest images to run on, use LTS instead."
+              echo "::error file=$f,line=$l::Please use 'ubuntu-22.04' instead of 'ubuntu-latest'"
             done
             exit 1
           fi
diff --git a/.github/workflows/benchmarking.yml b/.github/workflows/benchmarking.yml
@@ -99,7 +99,7 @@ jobs:
         # Set --sparse-ordering option of pytest-order plugin
         # to ensure tests are running in order of appears in the file.
         # It's important for test_perf_pgbench.py::test_pgbench_remote_* tests
-        extra_params: -m remote_cluster --sparse-ordering --timeout 5400 --ignore test_runner/performance/test_perf_olap.py
+        extra_params: -m remote_cluster --sparse-ordering --timeout 5400 --ignore test_runner/performance/test_perf_olap.py --ignore test_runner/performance/test_perf_pgvector_queries.py
       env:
         BENCHMARK_CONNSTR: ${{ steps.create-neon-project.outputs.dsn }}
         VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
@@ -410,14 +410,14 @@ jobs:
         PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
         BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
 
-    - name: Benchmark pgvector hnsw queries
+    - name: Benchmark pgvector queries
       uses: ./.github/actions/run-python-test-set
       with:
         build_type: ${{ env.BUILD_TYPE }}
-        test_selection: performance
+        test_selection: performance/test_perf_pgvector_queries.py
         run_in_parallel: false
         save_perf_report: ${{ env.SAVE_PERF_REPORT }}
-        extra_params: -m remote_cluster --timeout 21600 -k test_pgbench_remote_pgvector
+        extra_params: -m remote_cluster --timeout 21600 
       env:
         BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
         VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"

diff --git a/.github/workflows/build-build-tools-image.yml b/.github/workflows/build-build-tools-image.yml
@@ -30,7 +30,6 @@ jobs:
   check-image:
     uses: ./.github/workflows/check-build-tools-image.yml
 
-  # This job uses older version of GitHub Actions because it's run on gen2 runners, which don't support node 20 (for newer versions)
   build-image:
     needs: [ check-image ]
     if: needs.check-image.outputs.found == 'false'

diff --git a/.github/workflows/build_and_test.yml b/.github/workflows/build_and_test.yml
@@ -299,21 +299,21 @@ jobs:
         uses: actions/cache@v4
         with:
           path: pg_install/v14
-          key: v1-${{ runner.os }}-${{ matrix.build_type }}-pg-${{ steps.pg_v14_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
+          key: v1-${{ runner.os }}-${{ matrix.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-${{ runner.os }}-${{ matrix.build_type }}-pg-${{ steps.pg_v15_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
+          key: v1-${{ runner.os }}-${{ matrix.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-${{ runner.os }}-${{ matrix.build_type }}-pg-${{ steps.pg_v16_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
+          key: v1-${{ runner.os }}-${{ matrix.build_type }}-pg-${{ steps.pg_v16_rev.outputs.pg_rev }}-${{ hashFiles('Makefile', 'Dockerfile.build-tools') }}
 
       - name: Build postgres v14
         if: steps.cache_pg_14.outputs.cache-hit != 'true'
@@ -337,34 +337,8 @@ jobs:
         run: |
           ${cov_prefix} mold -run cargo build $CARGO_FLAGS $CARGO_FEATURES --bins --tests
 
-      - name: Run rust tests
-        env:
-          NEXTEST_RETRIES: 3
-        run: |
-          #nextest does not yet support running doctests
-          cargo test --doc $CARGO_FLAGS $CARGO_FEATURES
-
-          for io_engine in std-fs tokio-epoll-uring ; do
-            NEON_PAGESERVER_UNIT_TEST_VIRTUAL_FILE_IOENGINE=$io_engine ${cov_prefix} cargo nextest run $CARGO_FLAGS $CARGO_FEATURES
-          done
-
-          # Run separate tests for real S3
-          export ENABLE_REAL_S3_REMOTE_STORAGE=nonempty
-          export REMOTE_STORAGE_S3_BUCKET=neon-github-ci-tests
-          export REMOTE_STORAGE_S3_REGION=eu-central-1
-          # Avoid `$CARGO_FEATURES` since there's no `testing` feature in the e2e tests now
-          ${cov_prefix} cargo nextest run $CARGO_FLAGS -E 'package(remote_storage)' -E 'test(test_real_s3)'
-
-          # Run separate tests for real Azure Blob Storage
-          # XXX: replace region with `eu-central-1`-like region
-          export ENABLE_REAL_AZURE_REMOTE_STORAGE=y
-          export AZURE_STORAGE_ACCOUNT="${{ secrets.AZURE_STORAGE_ACCOUNT_DEV }}"
-          export AZURE_STORAGE_ACCESS_KEY="${{ secrets.AZURE_STORAGE_ACCESS_KEY_DEV }}"
-          export REMOTE_STORAGE_AZURE_CONTAINER="${{ vars.REMOTE_STORAGE_AZURE_CONTAINER }}"
-          export REMOTE_STORAGE_AZURE_REGION="${{ vars.REMOTE_STORAGE_AZURE_REGION }}"
-          # Avoid `$CARGO_FEATURES` since there's no `testing` feature in the e2e tests now
-          ${cov_prefix} cargo nextest run $CARGO_FLAGS -E 'package(remote_storage)' -E 'test(test_real_azure)'
-
+      # Do install *before* running rust tests because they might recompile the
+      # binaries with different features/flags.
       - name: Install rust binaries
         run: |
           # Install target binaries
@@ -405,6 +379,32 @@ jobs:
             done
           fi
 
+      - name: Run rust tests
+        env:
+          NEXTEST_RETRIES: 3
+        run: |
+          #nextest does not yet support running doctests
+          cargo test --doc $CARGO_FLAGS $CARGO_FEATURES
+
+          for io_engine in std-fs tokio-epoll-uring ; do
+            NEON_PAGESERVER_UNIT_TEST_VIRTUAL_FILE_IOENGINE=$io_engine ${cov_prefix} cargo nextest run $CARGO_FLAGS $CARGO_FEATURES
+          done
+
+          # Run separate tests for real S3
+          export ENABLE_REAL_S3_REMOTE_STORAGE=nonempty
+          export REMOTE_STORAGE_S3_BUCKET=neon-github-ci-tests
+          export REMOTE_STORAGE_S3_REGION=eu-central-1
+          ${cov_prefix} cargo nextest run $CARGO_FLAGS $CARGO_FEATURES -E 'package(remote_storage)' -E 'test(test_real_s3)'
+
+          # Run separate tests for real Azure Blob Storage
+          # XXX: replace region with `eu-central-1`-like region
+          export ENABLE_REAL_AZURE_REMOTE_STORAGE=y
+          export AZURE_STORAGE_ACCOUNT="${{ secrets.AZURE_STORAGE_ACCOUNT_DEV }}"
+          export AZURE_STORAGE_ACCESS_KEY="${{ secrets.AZURE_STORAGE_ACCESS_KEY_DEV }}"
+          export REMOTE_STORAGE_AZURE_CONTAINER="${{ vars.REMOTE_STORAGE_AZURE_CONTAINER }}"
+          export REMOTE_STORAGE_AZURE_REGION="${{ vars.REMOTE_STORAGE_AZURE_REGION }}"
+          ${cov_prefix} cargo nextest run $CARGO_FLAGS $CARGO_FEATURES -E 'package(remote_storage)' -E 'test(test_real_azure)'
+
       - name: Install postgres binaries
         run: cp -a pg_install /tmp/neon/pg_install
 
@@ -1023,6 +1023,18 @@ jobs:
         with:
           fetch-depth: 0
 
+      # Use custom DOCKER_CONFIG directory to avoid conflicts with default settings
+      # The default value is ~/.docker
+      - name: Set custom docker config directory
+        run: |
+          mkdir -p .docker-custom
+          echo DOCKER_CONFIG=$(pwd)/.docker-custom >> $GITHUB_ENV
+
+      - uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
+          password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
+
       # `neondatabase/neon` contains multiple binaries, all of them use the same input for the version into the same version formatting library.
       # Pick pageserver as currently the only binary with extra "version" features printed in the string to verify.
       # Regular pageserver version string looks like
@@ -1057,6 +1069,11 @@ jobs:
           docker compose -f ./docker-compose/docker-compose.yml logs || 0
           docker compose -f ./docker-compose/docker-compose.yml down
 
+      - name: Remove custom docker config directory
+        if: always()
+        run: |
+          rm -rf .docker-custom
+
   promote-images:
     needs: [ check-permissions, tag, test-images, vm-compute-node-image ]
     runs-on: ubuntu-22.04
@@ -1070,7 +1087,8 @@ jobs:
           username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
           password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
 
-      - uses: docker/login-action@v3
+      - name: Login to dev ECR
+        uses: docker/login-action@v3
         with:
           registry: 369495373322.dkr.ecr.eu-central-1.amazonaws.com
           username: ${{ secrets.AWS_ACCESS_KEY_DEV }}
@@ -1104,6 +1122,22 @@ jobs:
           docker buildx imagetools create -t neondatabase/neon-test-extensions-v16:latest \
                                              neondatabase/neon-test-extensions-v16:${{ needs.tag.outputs.build-tag }}
 
+      - name: Login to prod ECR
+        uses: docker/login-action@v3
+        if: github.ref_name == 'release'|| github.ref_name == 'release-proxy'
+        with:
+          registry: 093970136003.dkr.ecr.eu-central-1.amazonaws.com
+          username: ${{ secrets.PROD_GHA_RUNNER_LIMITED_AWS_ACCESS_KEY_ID }}
+          password: ${{ secrets.PROD_GHA_RUNNER_LIMITED_AWS_SECRET_ACCESS_KEY }}
+
+      - name: Copy all images to prod ECR
+        if: github.ref_name == 'release'|| github.ref_name == 'release-proxy'
+        run: |
+          for image in neon compute-tools {vm-,}compute-node-{v14,v15,v16}; do
+            docker buildx imagetools create -t 093970136003.dkr.ecr.eu-central-1.amazonaws.com/${image}:${{ needs.tag.outputs.build-tag }} \
+                                               369495373322.dkr.ecr.eu-central-1.amazonaws.com/${image}:${{ needs.tag.outputs.build-tag }}
+          done
+
   trigger-custom-extensions-build-and-wait:
     needs: [ check-permissions, tag ]
     runs-on: ubuntu-22.04

diff --git a/.github/workflows/check-build-tools-image.yml b/.github/workflows/check-build-tools-image.yml
@@ -25,26 +25,17 @@ jobs:
       found: ${{ steps.check-image.outputs.found }}
 
     steps:
+      - uses: actions/checkout@v4
+
       - name: Get build-tools image tag for the current commit
         id: get-build-tools-tag
         env:
-          # Usually, for COMMIT_SHA, we use `github.event.pull_request.head.sha || github.sha`, but here, even for PRs,
-          # we want to use `github.sha` i.e. point to a phantom merge commit to determine the image tag correctly.
-          COMMIT_SHA: ${{ github.sha }}
-          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          IMAGE_TAG: |
+            ${{ hashFiles('Dockerfile.build-tools',
+                          '.github/workflows/check-build-tools-image.yml',
+                          '.github/workflows/build-build-tools-image.yml') }}
         run: |
-          LAST_BUILD_TOOLS_SHA=$(
-            gh api \
-              -H "Accept: application/vnd.github+json" \
-              -H "X-GitHub-Api-Version: 2022-11-28" \
-              --method GET \
-              --field path=Dockerfile.build-tools \
-              --field sha=${COMMIT_SHA} \
-              --field per_page=1 \
-              --jq ".[0].sha" \
-              "/repos/${GITHUB_REPOSITORY}/commits"
-          )
-          echo "image-tag=${LAST_BUILD_TOOLS_SHA}" | tee -a $GITHUB_OUTPUT
+          echo "image-tag=${IMAGE_TAG}" | tee -a $GITHUB_OUTPUT
 
       - name: Check if such tag found in the registry
         id: check-image

diff --git a/.github/workflows/release.yml b/.github/workflows/release.yml
@@ -52,13 +52,15 @@ jobs:
       env:
         GH_TOKEN: ${{ secrets.CI_ACCESS_TOKEN }}
       run: |
+        TITLE="Storage & Compute release ${RELEASE_DATE}"
+
         cat << EOF > body.md
-          ## Storage & Compute release ${RELEASE_DATE}
+          ## ${TITLE}
 
           **Please merge this Pull Request using 'Create a merge commit' button**
         EOF
 
-        gh pr create --title "Release ${RELEASE_DATE}" \
+        gh pr create --title "${TITLE}" \
                      --body-file "body.md" \
                      --head "${RELEASE_BRANCH}" \
                      --base "release"
@@ -91,13 +93,15 @@ jobs:
       env:
         GH_TOKEN: ${{ secrets.CI_ACCESS_TOKEN }}
       run: |
+        TITLE="Proxy release ${RELEASE_DATE}"
+
         cat << EOF > body.md
-          ## Proxy release ${RELEASE_DATE}
+          ## ${TITLE}
 
           **Please merge this Pull Request using 'Create a merge commit' button**
         EOF
 
-        gh pr create --title "Proxy release ${RELEASE_DATE}" \
+        gh pr create --title "${TITLE}" \
                      --body-file "body.md" \
                      --head "${RELEASE_BRANCH}" \
                      --base "release-proxy"
diff --git a/Cargo.lock b/Cargo.lock
diff --git a/Dockerfile b/Dockerfile
@@ -69,8 +69,6 @@ RUN set -e \
     && apt install -y \
         libreadline-dev \
         libseccomp-dev \
-        libicu67 \
-        openssl \
         ca-certificates \
     && rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* \
     && useradd -d /data neon \

diff --git a/Dockerfile.build-tools b/Dockerfile.build-tools
@@ -112,6 +112,45 @@ RUN for package in Capture::Tiny DateTime Devel::Cover Digest::MD5 File::Spec JS
     && make install \
     && rm -rf ../lcov.tar.gz
 
+# Compile and install the static OpenSSL library
+ENV OPENSSL_VERSION=3.2.2
+ENV OPENSSL_PREFIX=/usr/local/openssl
+RUN wget -O /tmp/openssl-${OPENSSL_VERSION}.tar.gz https://www.openssl.org/source/openssl-${OPENSSL_VERSION}.tar.gz && \
+    echo "197149c18d9e9f292c43f0400acaba12e5f52cacfe050f3d199277ea738ec2e7 /tmp/openssl-${OPENSSL_VERSION}.tar.gz" | sha256sum --check && \
+    cd /tmp && \
+    tar xzvf /tmp/openssl-${OPENSSL_VERSION}.tar.gz && \
+    rm /tmp/openssl-${OPENSSL_VERSION}.tar.gz && \
+    cd /tmp/openssl-${OPENSSL_VERSION} && \
+    ./config --prefix=${OPENSSL_PREFIX}  -static --static no-shared -fPIC && \
+    make -j "$(nproc)" && \
+    make install && \
+    cd /tmp && \
+    rm -rf /tmp/openssl-${OPENSSL_VERSION}
+
+# Use the same version of libicu as the compute nodes so that
+# clusters created using inidb on pageserver can be used by computes.
+#
+# TODO: at this time, Dockerfile.compute-node uses the debian bullseye libicu
+# package, which is 67.1. We're duplicating that knowledge here, and also, technically,
+# Debian has a few patches on top of 67.1 that we're not adding here.
+ENV ICU_VERSION=67.1
+ENV ICU_PREFIX=/usr/local/icu
+
+# Download and build static ICU
+RUN wget -O /tmp/libicu-${ICU_VERSION}.tgz https://github.com/unicode-org/icu/releases/download/release-${ICU_VERSION//./-}/icu4c-${ICU_VERSION//./_}-src.tgz && \
+    echo "94a80cd6f251a53bd2a997f6f1b5ac6653fe791dfab66e1eb0227740fb86d5dc /tmp/libicu-${ICU_VERSION}.tgz" | sha256sum --check && \
+    mkdir /tmp/icu && \
+    pushd /tmp/icu && \
+    tar -xzf /tmp/libicu-${ICU_VERSION}.tgz && \
+    pushd icu/source && \
+    ./configure --prefix=${ICU_PREFIX}  --enable-static --enable-shared=no CXXFLAGS="-fPIC" CFLAGS="-fPIC" && \
+    make -j "$(nproc)" && \
+    make install && \
+    popd && \
+    rm -rf icu && \
+    rm -f /tmp/libicu-${ICU_VERSION}.tgz && \
+    popd
+
 # Switch to nonroot user
 USER nonroot:nonroot
 WORKDIR /home/nonroot
@@ -170,3 +209,6 @@ RUN whoami \
     && rustup --version --verbose \
     && rustc --version --verbose \
     && clang --version
+
+# Set following flag to check in Makefile if its running in Docker
+RUN touch /home/nonroot/.docker_build