Compare commits

..

3 Commits

Author SHA1 Message Date
Folke Behrens
c90b082222 Split handle_client and pass async callback for connect_once 2025-06-10 19:41:07 +02:00
Folke Behrens
0957c8ea69 Make a copy of connect_to_compute for pglb 2025-06-10 15:01:12 +02:00
Folke Behrens
6cea6560e9 Move task_main and handle_client to pglb 2025-06-10 14:59:12 +02:00
660 changed files with 11170 additions and 48004 deletions

View File

@@ -33,7 +33,6 @@ workspace-members = [
"compute_api",
"consumption_metrics",
"desim",
"json",
"metrics",
"pageserver_api",
"postgres_backend",

View File

@@ -4,7 +4,6 @@
!Cargo.lock
!Cargo.toml
!Makefile
!postgres.mk
!rust-toolchain.toml
!scripts/ninstall.sh
!docker-compose/run-tests.sh
@@ -27,4 +26,4 @@
!storage_controller/
!vendor/postgres-*/
!workspace_hack/
!build-tools/patches
!build_tools/patches

View File

@@ -7,7 +7,6 @@ self-hosted-runner:
- small-metal
- small-arm64
- unit-perf
- unit-perf-aws-arm
- us-east-2
config-variables:
- AWS_ECR_REGION
@@ -31,7 +30,6 @@ config-variables:
- NEON_PROD_AWS_ACCOUNT_ID
- PGREGRESS_PG16_PROJECT_ID
- PGREGRESS_PG17_PROJECT_ID
- PREWARM_PGBENCH_SIZE
- REMOTE_STORAGE_AZURE_CONTAINER
- REMOTE_STORAGE_AZURE_REGION
- SLACK_CICD_CHANNEL_ID

View File

@@ -176,13 +176,7 @@ runs:
fi
if [[ $BUILD_TYPE == "debug" && $RUNNER_ARCH == 'X64' ]]; then
# We don't use code coverage for regression tests (the step is disabled),
# so there's no need to collect it.
# Ref https://github.com/neondatabase/neon/issues/4540
# cov_prefix=(scripts/coverage "--profraw-prefix=$GITHUB_JOB" --dir=/tmp/coverage run)
cov_prefix=()
# Explicitly set LLVM_PROFILE_FILE to /dev/null to avoid writing *.profraw files
export LLVM_PROFILE_FILE=/dev/null
cov_prefix=(scripts/coverage "--profraw-prefix=$GITHUB_JOB" --dir=/tmp/coverage run)
else
cov_prefix=()
fi

View File

@@ -38,11 +38,6 @@ on:
required: false
default: 1
type: number
rerun-failed:
description: 'rerun failed tests to ignore flaky tests'
required: false
default: true
type: boolean
defaults:
run:
@@ -104,10 +99,11 @@ jobs:
# Set some environment variables used by all the steps.
#
# CARGO_FLAGS is extra options to pass to all "cargo" subcommands.
# CARGO_FLAGS is extra options to pass to "cargo build", "cargo test" etc.
# It also includes --features, if any
#
# CARGO_PROFILE is passed to "cargo build", "cargo test" etc, but not to
# "cargo metadata", because it doesn't accept --release or --debug options.
# CARGO_FEATURES is passed to "cargo metadata". It is separate from CARGO_FLAGS,
# because "cargo metadata" doesn't accept --release or --debug options
#
# We run tests with addtional features, that are turned off by default (e.g. in release builds), see
# corresponding Cargo.toml files for their descriptions.
@@ -116,16 +112,16 @@ jobs:
ARCH: ${{ inputs.arch }}
SANITIZERS: ${{ inputs.sanitizers }}
run: |
CARGO_FLAGS="--locked --features testing"
CARGO_FEATURES="--features testing"
if [[ $BUILD_TYPE == "debug" && $ARCH == 'x64' ]]; then
cov_prefix="scripts/coverage --profraw-prefix=$GITHUB_JOB --dir=/tmp/coverage run"
CARGO_PROFILE=""
CARGO_FLAGS="--locked"
elif [[ $BUILD_TYPE == "debug" ]]; then
cov_prefix=""
CARGO_PROFILE=""
CARGO_FLAGS="--locked"
elif [[ $BUILD_TYPE == "release" ]]; then
cov_prefix=""
CARGO_PROFILE="--release"
CARGO_FLAGS="--locked --release"
fi
if [[ $SANITIZERS == 'enabled' ]]; then
make_vars="WITH_SANITIZERS=yes"
@@ -135,8 +131,8 @@ jobs:
{
echo "cov_prefix=${cov_prefix}"
echo "make_vars=${make_vars}"
echo "CARGO_FEATURES=${CARGO_FEATURES}"
echo "CARGO_FLAGS=${CARGO_FLAGS}"
echo "CARGO_PROFILE=${CARGO_PROFILE}"
echo "CARGO_HOME=${GITHUB_WORKSPACE}/.cargo"
} >> $GITHUB_ENV
@@ -150,7 +146,7 @@ jobs:
secretKey: ${{ secrets.HETZNER_CACHE_SECRET_KEY }}
use-fallback: false
path: pg_install/v14
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v14_rev.outputs.pg_rev }}-bookworm-${{ hashFiles('Makefile', 'build-tools/Dockerfile') }}
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v14_rev.outputs.pg_rev }}-bookworm-${{ hashFiles('Makefile', 'build-tools.Dockerfile') }}
- name: Cache postgres v15 build
id: cache_pg_15
@@ -162,7 +158,7 @@ jobs:
secretKey: ${{ secrets.HETZNER_CACHE_SECRET_KEY }}
use-fallback: false
path: pg_install/v15
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v15_rev.outputs.pg_rev }}-bookworm-${{ hashFiles('Makefile', 'build-tools/Dockerfile') }}
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v15_rev.outputs.pg_rev }}-bookworm-${{ hashFiles('Makefile', 'build-tools.Dockerfile') }}
- name: Cache postgres v16 build
id: cache_pg_16
@@ -174,7 +170,7 @@ jobs:
secretKey: ${{ secrets.HETZNER_CACHE_SECRET_KEY }}
use-fallback: false
path: pg_install/v16
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v16_rev.outputs.pg_rev }}-bookworm-${{ hashFiles('Makefile', 'build-tools/Dockerfile') }}
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v16_rev.outputs.pg_rev }}-bookworm-${{ hashFiles('Makefile', 'build-tools.Dockerfile') }}
- name: Cache postgres v17 build
id: cache_pg_17
@@ -186,20 +182,36 @@ jobs:
secretKey: ${{ secrets.HETZNER_CACHE_SECRET_KEY }}
use-fallback: false
path: pg_install/v17
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v17_rev.outputs.pg_rev }}-bookworm-${{ hashFiles('Makefile', 'build-tools/Dockerfile') }}
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v17_rev.outputs.pg_rev }}-bookworm-${{ hashFiles('Makefile', 'build-tools.Dockerfile') }}
- name: Build all
# Note: the Makefile picks up BUILD_TYPE and CARGO_PROFILE from the env variables
run: mold -run make ${make_vars} all -j$(nproc) CARGO_BUILD_FLAGS="$CARGO_FLAGS"
- name: Build postgres v14
if: steps.cache_pg_14.outputs.cache-hit != 'true'
run: mold -run make ${make_vars} postgres-v14 -j$(nproc)
- name: Build postgres v15
if: steps.cache_pg_15.outputs.cache-hit != 'true'
run: mold -run make ${make_vars} postgres-v15 -j$(nproc)
- name: Build postgres v16
if: steps.cache_pg_16.outputs.cache-hit != 'true'
run: mold -run make ${make_vars} postgres-v16 -j$(nproc)
- name: Build postgres v17
if: steps.cache_pg_17.outputs.cache-hit != 'true'
run: mold -run make ${make_vars} postgres-v17 -j$(nproc)
- name: Build neon extensions
run: mold -run make ${make_vars} neon-pg-ext -j$(nproc)
- name: Build walproposer-lib
run: mold -run make ${make_vars} walproposer-lib -j$(nproc)
- name: Build unit tests
if: inputs.sanitizers != 'enabled'
- name: Run cargo build
env:
WITH_TESTS: ${{ inputs.sanitizers != 'enabled' && '--tests' || '' }}
run: |
export ASAN_OPTIONS=detect_leaks=0
${cov_prefix} mold -run cargo build $CARGO_FLAGS $CARGO_PROFILE --tests
${cov_prefix} mold -run cargo build $CARGO_FLAGS $CARGO_FEATURES --bins ${WITH_TESTS}
# Do install *before* running rust tests because they might recompile the
# binaries with different features/flags.
@@ -211,7 +223,7 @@ jobs:
# Install target binaries
mkdir -p /tmp/neon/bin/
binaries=$(
${cov_prefix} cargo metadata $CARGO_FLAGS --format-version=1 --no-deps |
${cov_prefix} cargo metadata $CARGO_FEATURES --format-version=1 --no-deps |
jq -r '.packages[].targets[] | select(.kind | index("bin")) | .name'
)
for bin in $binaries; do
@@ -228,7 +240,7 @@ jobs:
mkdir -p /tmp/neon/test_bin/
test_exe_paths=$(
${cov_prefix} cargo test $CARGO_FLAGS $CARGO_PROFILE --message-format=json --no-run |
${cov_prefix} cargo test $CARGO_FLAGS $CARGO_FEATURES --message-format=json --no-run |
jq -r '.executable | select(. != null)'
)
for bin in $test_exe_paths; do
@@ -262,10 +274,10 @@ jobs:
export LD_LIBRARY_PATH
#nextest does not yet support running doctests
${cov_prefix} cargo test --doc $CARGO_FLAGS $CARGO_PROFILE
${cov_prefix} cargo test --doc $CARGO_FLAGS $CARGO_FEATURES
# run all non-pageserver tests
${cov_prefix} cargo nextest run $CARGO_FLAGS $CARGO_PROFILE -E '!package(pageserver)'
${cov_prefix} cargo nextest run $CARGO_FLAGS $CARGO_FEATURES -E '!package(pageserver)'
# run pageserver tests
# (When developing new pageserver features gated by config fields, we commonly make the rust
@@ -274,13 +286,13 @@ jobs:
# pageserver tests from non-pageserver tests cuts down the time it takes for this CI step.)
NEON_PAGESERVER_UNIT_TEST_VIRTUAL_FILE_IOENGINE=tokio-epoll-uring \
${cov_prefix} \
cargo nextest run $CARGO_FLAGS $CARGO_PROFILE -E 'package(pageserver)'
cargo nextest run $CARGO_FLAGS $CARGO_FEATURES -E 'package(pageserver)'
# 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_PROFILE -E 'package(remote_storage)' -E 'test(test_real_s3)'
${cov_prefix} cargo nextest run $CARGO_FLAGS $CARGO_FEATURES -E 'package(remote_storage)' -E 'test(test_real_s3)'
# Run separate tests for real Azure Blob Storage
# XXX: replace region with `eu-central-1`-like region
@@ -289,17 +301,17 @@ jobs:
export AZURE_STORAGE_ACCESS_KEY="${{ 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_PROFILE -E 'package(remote_storage)' -E 'test(test_real_azure)'
${cov_prefix} cargo nextest run $CARGO_FLAGS $CARGO_FEATURES -E 'package(remote_storage)' -E 'test(test_real_azure)'
- name: Install postgres binaries
run: |
# Use tar to copy files matching the pattern, preserving the paths in the destionation
tar c \
pg_install/v* \
build/*/src/test/regress/*.so \
build/*/src/test/regress/pg_regress \
build/*/src/test/isolation/isolationtester \
build/*/src/test/isolation/pg_isolation_regress \
pg_install/build/*/src/test/regress/*.so \
pg_install/build/*/src/test/regress/pg_regress \
pg_install/build/*/src/test/isolation/isolationtester \
pg_install/build/*/src/test/isolation/pg_isolation_regress \
| tar x -C /tmp/neon
- name: Upload Neon artifact
@@ -367,7 +379,7 @@ jobs:
- name: Pytest regression tests
continue-on-error: ${{ matrix.lfc_state == 'with-lfc' && inputs.build-type == 'debug' }}
uses: ./.github/actions/run-python-test-set
timeout-minutes: ${{ (inputs.build-type == 'release' && inputs.sanitizers != 'enabled') && 75 || 180 }}
timeout-minutes: ${{ inputs.sanitizers != 'enabled' && 75 || 180 }}
with:
build_type: ${{ inputs.build-type }}
test_selection: regress
@@ -375,14 +387,14 @@ jobs:
run_with_real_s3: true
real_s3_bucket: neon-github-ci-tests
real_s3_region: eu-central-1
rerun_failed: ${{ inputs.rerun-failed }}
rerun_failed: ${{ inputs.test-run-count == 1 }}
pg_version: ${{ matrix.pg_version }}
sanitizers: ${{ inputs.sanitizers }}
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
# `--session-timeout` is equal to (timeout-minutes - 10 minutes) * 60 seconds.
# Attempt to stop tests gracefully to generate test reports
# until they are forcibly stopped by the stricter `timeout-minutes` limit.
extra_params: --session-timeout=${{ (inputs.build-type == 'release' && inputs.sanitizers != 'enabled') && 3000 || 10200 }} --count=${{ inputs.test-run-count }}
extra_params: --session-timeout=${{ inputs.sanitizers != 'enabled' && 3000 || 10200 }} --count=${{ inputs.test-run-count }}
${{ inputs.test-selection != '' && format('-k "{0}"', inputs.test-selection) || '' }}
env:
TEST_RESULT_CONNSTR: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}

View File

@@ -219,7 +219,6 @@ jobs:
--ignore test_runner/performance/test_cumulative_statistics_persistence.py
--ignore test_runner/performance/test_perf_many_relations.py
--ignore test_runner/performance/test_perf_oltp_large_tenant.py
--ignore test_runner/performance/test_lfc_prewarm.py
env:
BENCHMARK_CONNSTR: ${{ steps.create-neon-project.outputs.dsn }}
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
@@ -411,77 +410,6 @@ jobs:
env:
SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
prewarm-test:
if: ${{ github.event.inputs.run_only_pgvector_tests == 'false' || github.event.inputs.run_only_pgvector_tests == null }}
permissions:
contents: write
statuses: write
id-token: write # aws-actions/configure-aws-credentials
env:
PGBENCH_SIZE: ${{ vars.PREWARM_PGBENCH_SIZE }}
POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
DEFAULT_PG_VERSION: 17
TEST_OUTPUT: /tmp/test_output
BUILD_TYPE: remote
SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref_name == 'main' ) }}
PLATFORM: "neon-staging"
runs-on: [ self-hosted, us-east-2, x64 ]
container:
image: ghcr.io/neondatabase/build-tools:pinned-bookworm
credentials:
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
role-duration-seconds: 18000 # 5 hours
- name: Download Neon artifact
uses: ./.github/actions/download
with:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Run prewarm benchmark
uses: ./.github/actions/run-python-test-set
with:
build_type: ${{ env.BUILD_TYPE }}
test_selection: performance/test_lfc_prewarm.py
run_in_parallel: false
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 5400
pg_version: ${{ env.DEFAULT_PG_VERSION }}
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
NEON_API_KEY: ${{ secrets.NEON_STAGING_API_KEY }}
- name: Create Allure report
id: create-allure-report
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-generate
with:
store-test-results-into-db: true
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
REGRESS_TEST_RESULT_CONNSTR_NEW: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}
generate-matrices:
if: ${{ github.event.inputs.run_only_pgvector_tests == 'false' || github.event.inputs.run_only_pgvector_tests == null }}
# Create matrices for the benchmarking jobs, so we run benchmarks on rds only once a week (on Saturday)

View File

@@ -72,7 +72,7 @@ jobs:
ARCHS: ${{ inputs.archs || '["x64","arm64"]' }}
DEBIANS: ${{ inputs.debians || '["bullseye","bookworm"]' }}
IMAGE_TAG: |
${{ hashFiles('build-tools/Dockerfile',
${{ hashFiles('build-tools.Dockerfile',
'.github/workflows/build-build-tools-image.yml') }}
run: |
echo "archs=${ARCHS}" | tee -a ${GITHUB_OUTPUT}
@@ -144,7 +144,7 @@ jobs:
- uses: docker/build-push-action@471d1dc4e07e5cdedd4c2171150001c434f0b7a4 # v6.15.0
with:
file: build-tools/Dockerfile
file: build-tools.Dockerfile
context: .
provenance: false
push: true

View File

@@ -32,14 +32,161 @@ permissions:
contents: read
jobs:
make-all:
build-pgxn:
if: |
inputs.pg_versions != '[]' || inputs.rebuild_everything ||
contains(github.event.pull_request.labels.*.name, 'run-extra-build-macos') ||
contains(github.event.pull_request.labels.*.name, 'run-extra-build-*') ||
github.ref_name == 'main'
timeout-minutes: 30
runs-on: macos-15
strategy:
matrix:
postgres-version: ${{ inputs.rebuild_everything && fromJSON('["v14", "v15", "v16", "v17"]') || fromJSON(inputs.pg_versions) }}
env:
# Use release build only, to have less debug info around
# Hence keeping target/ (and general cache size) smaller
BUILD_TYPE: release
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Checkout main repo
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Set pg ${{ matrix.postgres-version }} for caching
id: pg_rev
run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-${{ matrix.postgres-version }}) | tee -a "${GITHUB_OUTPUT}"
- name: Cache postgres ${{ matrix.postgres-version }} build
id: cache_pg
uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
with:
path: pg_install/${{ matrix.postgres-version }}
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-${{ matrix.postgres-version }}-${{ steps.pg_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Checkout submodule vendor/postgres-${{ matrix.postgres-version }}
if: steps.cache_pg.outputs.cache-hit != 'true'
run: |
git submodule init vendor/postgres-${{ matrix.postgres-version }}
git submodule update --depth 1 --recursive
- name: Install build dependencies
if: steps.cache_pg.outputs.cache-hit != 'true'
run: |
brew install flex bison openssl protobuf icu4c
- name: Set extra env for macOS
if: steps.cache_pg.outputs.cache-hit != 'true'
run: |
echo 'LDFLAGS=-L/usr/local/opt/openssl@3/lib' >> $GITHUB_ENV
echo 'CPPFLAGS=-I/usr/local/opt/openssl@3/include' >> $GITHUB_ENV
- name: Build Postgres ${{ matrix.postgres-version }}
if: steps.cache_pg.outputs.cache-hit != 'true'
run: |
make postgres-${{ matrix.postgres-version }} -j$(sysctl -n hw.ncpu)
- name: Build Neon Pg Ext ${{ matrix.postgres-version }}
if: steps.cache_pg.outputs.cache-hit != 'true'
run: |
make "neon-pg-ext-${{ matrix.postgres-version }}" -j$(sysctl -n hw.ncpu)
- name: Get postgres headers ${{ matrix.postgres-version }}
if: steps.cache_pg.outputs.cache-hit != 'true'
run: |
make postgres-headers-${{ matrix.postgres-version }} -j$(sysctl -n hw.ncpu)
- name: Upload "pg_install/${{ matrix.postgres-version }}" artifact
uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
with:
name: pg_install--${{ matrix.postgres-version }}
path: pg_install/${{ matrix.postgres-version }}
# The artifact is supposed to be used by the next job in the same workflow,
# so theres no need to store it for too long.
retention-days: 1
build-walproposer-lib:
if: |
inputs.pg_versions != '[]' || inputs.rebuild_everything ||
contains(github.event.pull_request.labels.*.name, 'run-extra-build-macos') ||
contains(github.event.pull_request.labels.*.name, 'run-extra-build-*') ||
github.ref_name == 'main'
timeout-minutes: 30
runs-on: macos-15
needs: [build-pgxn]
env:
# Use release build only, to have less debug info around
# Hence keeping target/ (and general cache size) smaller
BUILD_TYPE: release
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Checkout main repo
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Set pg v17 for caching
id: pg_rev
run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v17) | tee -a "${GITHUB_OUTPUT}"
- name: Download "pg_install/v17" artifact
uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
with:
name: pg_install--v17
path: pg_install/v17
- name: Cache walproposer-lib
id: cache_walproposer_lib
uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
with:
path: pg_install/build/walproposer-lib
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-walproposer_lib-v17-${{ steps.pg_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Checkout submodule vendor/postgres-v17
if: steps.cache_walproposer_lib.outputs.cache-hit != 'true'
run: |
git submodule init vendor/postgres-v17
git submodule update --depth 1 --recursive
- name: Install build dependencies
if: steps.cache_walproposer_lib.outputs.cache-hit != 'true'
run: |
brew install flex bison openssl protobuf icu4c
- name: Set extra env for macOS
if: steps.cache_walproposer_lib.outputs.cache-hit != 'true'
run: |
echo 'LDFLAGS=-L/usr/local/opt/openssl@3/lib' >> $GITHUB_ENV
echo 'CPPFLAGS=-I/usr/local/opt/openssl@3/include' >> $GITHUB_ENV
- name: Build walproposer-lib (only for v17)
if: steps.cache_walproposer_lib.outputs.cache-hit != 'true'
run:
make walproposer-lib -j$(sysctl -n hw.ncpu)
- name: Upload "pg_install/build/walproposer-lib" artifact
uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
with:
name: pg_install--build--walproposer-lib
path: pg_install/build/walproposer-lib
# The artifact is supposed to be used by the next job in the same workflow,
# so theres no need to store it for too long.
retention-days: 1
cargo-build:
if: |
inputs.pg_versions != '[]' || inputs.rebuild_rust_code || inputs.rebuild_everything ||
contains(github.event.pull_request.labels.*.name, 'run-extra-build-macos') ||
contains(github.event.pull_request.labels.*.name, 'run-extra-build-*') ||
github.ref_name == 'main'
timeout-minutes: 60
timeout-minutes: 30
runs-on: macos-15
needs: [build-pgxn, build-walproposer-lib]
env:
# Use release build only, to have less debug info around
# Hence keeping target/ (and general cache size) smaller
@@ -55,53 +202,41 @@ jobs:
with:
submodules: true
- name: Install build dependencies
run: |
brew install flex bison openssl protobuf icu4c
- name: Set extra env for macOS
run: |
echo 'LDFLAGS=-L/usr/local/opt/openssl@3/lib' >> $GITHUB_ENV
echo 'CPPFLAGS=-I/usr/local/opt/openssl@3/include' >> $GITHUB_ENV
- name: Restore "pg_install/" cache
id: cache_pg
uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
- name: Download "pg_install/v14" artifact
uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
with:
path: pg_install
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-install-v14-${{ hashFiles('Makefile', 'postgres.mk', 'vendor/revisions.json') }}
name: pg_install--v14
path: pg_install/v14
- name: Checkout vendor/postgres submodules
if: steps.cache_pg.outputs.cache-hit != 'true'
run: |
git submodule init
git submodule update --depth 1 --recursive
- name: Download "pg_install/v15" artifact
uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
with:
name: pg_install--v15
path: pg_install/v15
- name: Build Postgres
if: steps.cache_pg.outputs.cache-hit != 'true'
run: |
make postgres -j$(sysctl -n hw.ncpu)
- name: Download "pg_install/v16" artifact
uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
with:
name: pg_install--v16
path: pg_install/v16
# This isn't strictly necessary, but it makes the cached and non-cached builds more similar,
# When pg_install is restored from cache, there is no 'build/' directory. By removing it
# in a non-cached build too, we enforce that the rest of the steps don't depend on it,
# so that we notice any build caching bugs earlier.
- name: Remove build artifacts
if: steps.cache_pg.outputs.cache-hit != 'true'
run: |
rm -rf build
- name: Download "pg_install/v17" artifact
uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
with:
name: pg_install--v17
path: pg_install/v17
# Explicitly update the rust toolchain before running 'make'. The parallel make build can
# invoke 'cargo build' more than once in parallel, for different crates. That's OK, 'cargo'
# does its own locking to prevent concurrent builds from stepping on each other's
# toes. However, it will first try to update the toolchain, and that step is not locked the
# same way. To avoid two toolchain updates running in parallel and stepping on each other's
# toes, ensure that the toolchain is up-to-date beforehand.
- name: Update rust toolchain
- name: Download "pg_install/build/walproposer-lib" artifact
uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
with:
name: pg_install--build--walproposer-lib
path: pg_install/build/walproposer-lib
# `actions/download-artifact` doesn't preserve permissions:
# https://github.com/actions/download-artifact?tab=readme-ov-file#permission-loss
- name: Make pg_install/v*/bin/* executable
run: |
rustup --version &&
rustup update &&
rustup show
chmod +x pg_install/v*/bin/*
- name: Cache cargo deps
uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
@@ -113,12 +248,17 @@ jobs:
target
key: v1-${{ runner.os }}-${{ runner.arch }}-cargo-${{ hashFiles('./Cargo.lock') }}-${{ hashFiles('./rust-toolchain.toml') }}-rust
# Build the neon-specific postgres extensions, and all the Rust bits.
#
# Pass PG_INSTALL_CACHED=1 because PostgreSQL was already built and cached
# separately.
- name: Build all
run: PG_INSTALL_CACHED=1 BUILD_TYPE=release make -j$(sysctl -n hw.ncpu) all
- name: Install build dependencies
run: |
brew install flex bison openssl protobuf icu4c
- name: Set extra env for macOS
run: |
echo 'LDFLAGS=-L/usr/local/opt/openssl@3/lib' >> $GITHUB_ENV
echo 'CPPFLAGS=-I/usr/local/opt/openssl@3/include' >> $GITHUB_ENV
- name: Run cargo build
run: cargo build --all --release -j$(sysctl -n hw.ncpu)
- name: Check that no warnings are produced
run: ./run_clippy.sh

View File

@@ -58,7 +58,6 @@ jobs:
test-cfg: ${{ inputs.pg-versions }}
test-selection: ${{ inputs.test-selection }}
test-run-count: ${{ fromJson(inputs.run-count) }}
rerun-failed: false
secrets: inherit
create-test-report:

View File

@@ -69,7 +69,7 @@ jobs:
submodules: true
- name: Check for file changes
uses: dorny/paths-filter@de90cc6fb38fc0963ad72b210f1f284cd68cea36 # v3.0.2
uses: step-security/paths-filter@v3
id: files-changed
with:
token: ${{ secrets.GITHUB_TOKEN }}
@@ -87,29 +87,6 @@ jobs:
uses: ./.github/workflows/build-build-tools-image.yml
secrets: inherit
lint-yamls:
needs: [ meta, check-permissions, build-build-tools-image ]
# We do need to run this in `.*-rc-pr` because of hotfixes.
if: ${{ contains(fromJSON('["pr", "push-main", "storage-rc-pr", "proxy-rc-pr", "compute-rc-pr"]'), needs.meta.outputs.run-kind) }}
runs-on: [ self-hosted, small ]
container:
image: ${{ needs.build-build-tools-image.outputs.image }}
credentials:
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- run: make -C compute manifest-schema-validation
- run: make lint-openapi-spec
check-codestyle-python:
needs: [ meta, check-permissions, build-build-tools-image ]
# No need to run on `main` because we this in the merge queue. We do need to run this in `.*-rc-pr` because of hotfixes.
@@ -307,14 +284,14 @@ jobs:
statuses: write
contents: write
pull-requests: write
runs-on: [ self-hosted, unit-perf-aws-arm ]
runs-on: [ self-hosted, unit-perf ]
container:
image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
credentials:
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
# for changed limits, see comments on `options:` earlier in this file
options: --init --shm-size=512mb --ulimit memlock=67108864:67108864 --ulimit nofile=65536:65536 --security-opt seccomp=unconfined
options: --init --shm-size=512mb --ulimit memlock=67108864:67108864
strategy:
fail-fast: false
matrix:
@@ -671,7 +648,7 @@ jobs:
ghcr.io/neondatabase/neon:${{ needs.meta.outputs.build-tag }}-bookworm-arm64
compute-node-image-arch:
needs: [ check-permissions, meta ]
needs: [ check-permissions, build-build-tools-image, meta ]
if: ${{ contains(fromJSON('["push-main", "pr", "compute-rc-pr"]'), needs.meta.outputs.run-kind) }}
permissions:
id-token: write # aws-actions/configure-aws-credentials
@@ -744,6 +721,7 @@ jobs:
GIT_VERSION=${{ github.event.pull_request.head.sha || github.sha }}
PG_VERSION=${{ matrix.version.pg }}
BUILD_TAG=${{ needs.meta.outputs.release-tag || needs.meta.outputs.build-tag }}
TAG=${{ needs.build-build-tools-image.outputs.image-tag }}-${{ matrix.version.debian }}
DEBIAN_VERSION=${{ matrix.version.debian }}
provenance: false
push: true
@@ -763,6 +741,7 @@ jobs:
GIT_VERSION=${{ github.event.pull_request.head.sha || github.sha }}
PG_VERSION=${{ matrix.version.pg }}
BUILD_TAG=${{ needs.meta.outputs.release-tag || needs.meta.outputs.build-tag }}
TAG=${{ needs.build-build-tools-image.outputs.image-tag }}-${{ matrix.version.debian }}
DEBIAN_VERSION=${{ matrix.version.debian }}
provenance: false
push: true
@@ -987,7 +966,6 @@ jobs:
- name: Verify docker-compose example and test extensions
timeout-minutes: 60
env:
PARALLEL_COMPUTES: 3
TAG: >-
${{
needs.meta.outputs.run-kind == 'compute-rc-pr'

View File

@@ -1,151 +0,0 @@
name: Build and Test Fully
on:
schedule:
# * is a special character in YAML so you have to quote this string
# ┌───────────── minute (0 - 59)
# │ ┌───────────── hour (0 - 23)
# │ │ ┌───────────── day of the month (1 - 31)
# │ │ │ ┌───────────── month (1 - 12 or JAN-DEC)
# │ │ │ │ ┌───────────── day of the week (0 - 6 or SUN-SAT)
- cron: '0 3 * * *' # run once a day, timezone is utc
workflow_dispatch:
defaults:
run:
shell: bash -euxo pipefail {0}
concurrency:
# Allow only one workflow per any non-`main` branch.
group: ${{ github.workflow }}-${{ github.ref_name }}-${{ github.ref_name == 'main' && github.sha || 'anysha' }}
cancel-in-progress: true
env:
RUST_BACKTRACE: 1
COPT: '-Werror'
jobs:
tag:
runs-on: [ self-hosted, small ]
container: ${{ vars.NEON_DEV_AWS_ACCOUNT_ID }}.dkr.ecr.${{ vars.AWS_ECR_REGION }}.amazonaws.com/base:pinned
outputs:
build-tag: ${{steps.build-tag.outputs.tag}}
steps:
# Need `fetch-depth: 0` to count the number of commits in the branch
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
fetch-depth: 0
- name: Get build tag
run: |
echo run:$GITHUB_RUN_ID
echo ref:$GITHUB_REF_NAME
echo rev:$(git rev-list --count HEAD)
if [[ "$GITHUB_REF_NAME" == "main" ]]; then
echo "tag=$(git rev-list --count HEAD)" >> $GITHUB_OUTPUT
elif [[ "$GITHUB_REF_NAME" == "release" ]]; then
echo "tag=release-$(git rev-list --count HEAD)" >> $GITHUB_OUTPUT
elif [[ "$GITHUB_REF_NAME" == "release-proxy" ]]; then
echo "tag=release-proxy-$(git rev-list --count HEAD)" >> $GITHUB_OUTPUT
elif [[ "$GITHUB_REF_NAME" == "release-compute" ]]; then
echo "tag=release-compute-$(git rev-list --count HEAD)" >> $GITHUB_OUTPUT
else
echo "GITHUB_REF_NAME (value '$GITHUB_REF_NAME') is not set to either 'main' or 'release', 'release-proxy', 'release-compute'"
echo "tag=$GITHUB_RUN_ID" >> $GITHUB_OUTPUT
fi
shell: bash
id: build-tag
build-build-tools-image:
uses: ./.github/workflows/build-build-tools-image.yml
secrets: inherit
build-and-test-locally:
needs: [ tag, build-build-tools-image ]
strategy:
fail-fast: false
matrix:
arch: [ x64, arm64 ]
build-type: [ debug, release ]
uses: ./.github/workflows/_build-and-test-locally.yml
with:
arch: ${{ matrix.arch }}
build-tools-image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
build-tag: ${{ needs.tag.outputs.build-tag }}
build-type: ${{ matrix.build-type }}
rerun-failed: false
test-cfg: '[{"pg_version":"v14", "lfc_state": "with-lfc"},
{"pg_version":"v15", "lfc_state": "with-lfc"},
{"pg_version":"v16", "lfc_state": "with-lfc"},
{"pg_version":"v17", "lfc_state": "with-lfc"},
{"pg_version":"v14", "lfc_state": "without-lfc"},
{"pg_version":"v15", "lfc_state": "without-lfc"},
{"pg_version":"v16", "lfc_state": "without-lfc"},
{"pg_version":"v17", "lfc_state": "withouts-lfc"}]'
secrets: inherit
create-test-report:
needs: [ build-and-test-locally, build-build-tools-image ]
if: ${{ !cancelled() }}
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: write
pull-requests: write
outputs:
report-url: ${{ steps.create-allure-report.outputs.report-url }}
runs-on: [ self-hosted, small ]
container:
image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
credentials:
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Create Allure report
if: ${{ !cancelled() }}
id: create-allure-report
uses: ./.github/actions/allure-report-generate
with:
store-test-results-into-db: true
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
REGRESS_TEST_RESULT_CONNSTR_NEW: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}
- uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
if: ${{ !cancelled() }}
with:
# Retry script for 5XX server errors: https://github.com/actions/github-script#retries
retries: 5
script: |
const report = {
reportUrl: "${{ steps.create-allure-report.outputs.report-url }}",
reportJsonUrl: "${{ steps.create-allure-report.outputs.report-json-url }}",
}
const coverage = {}
const script = require("./scripts/comment-test-report.js")
await script({
github,
context,
fetch,
report,
coverage,
})

View File

@@ -79,7 +79,6 @@ jobs:
build-tools-image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
build-tag: ${{ needs.tag.outputs.build-tag }}
build-type: ${{ matrix.build-type }}
rerun-failed: false
test-cfg: '[{"pg_version":"v17"}]'
sanitizers: enabled
secrets: inherit

View File

@@ -33,19 +33,11 @@ jobs:
fail-fast: false # allow other variants to continue even if one fails
matrix:
include:
# test only read-only custom scripts in new branch without database maintenance
- target: new_branch
custom_scripts: select_any_webhook_with_skew.sql@300 select_recent_webhook.sql@397 select_prefetch_webhook.sql@3
test_maintenance: false
# test all custom scripts in new branch with database maintenance
- target: new_branch
custom_scripts: insert_webhooks.sql@200 select_any_webhook_with_skew.sql@300 select_recent_webhook.sql@397 select_prefetch_webhook.sql@3 IUD_one_transaction.sql@100
test_maintenance: true
# test all custom scripts in reuse branch with database maintenance
- target: reuse_branch
custom_scripts: insert_webhooks.sql@200 select_any_webhook_with_skew.sql@300 select_recent_webhook.sql@397 select_prefetch_webhook.sql@3 IUD_one_transaction.sql@100
test_maintenance: true
max-parallel: 1 # we want to run each benchmark sequentially to not have noisy neighbors on shared storage (PS, SK)
max-parallel: 1 # we want to run each stripe size sequentially to be able to compare the results
permissions:
contents: write
statuses: write
@@ -153,7 +145,6 @@ jobs:
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
- name: Benchmark database maintenance
if: ${{ matrix.test_maintenance }}
uses: ./.github/actions/run-python-test-set
with:
build_type: ${{ env.BUILD_TYPE }}

View File

@@ -1,175 +0,0 @@
name: large oltp growth
# workflow to grow the reuse branch of large oltp benchmark continuously (about 16 GB per run)
on:
# uncomment to run on push for debugging your PR
# push:
# branches: [ bodobolero/increase_large_oltp_workload ]
schedule:
# * is a special character in YAML so you have to quote this string
# ┌───────────── minute (0 - 59)
# │ ┌───────────── hour (0 - 23)
# │ │ ┌───────────── day of the month (1 - 31)
# │ │ │ ┌───────────── month (1 - 12 or JAN-DEC)
# │ │ │ │ ┌───────────── day of the week (0 - 6 or SUN-SAT)
- cron: '0 6 * * *' # 06:00 UTC
- cron: '0 8 * * *' # 08:00 UTC
- cron: '0 10 * * *' # 10:00 UTC
- cron: '0 12 * * *' # 12:00 UTC
- cron: '0 14 * * *' # 14:00 UTC
- cron: '0 16 * * *' # 16:00 UTC
workflow_dispatch: # adds ability to run this manually
defaults:
run:
shell: bash -euxo pipefail {0}
concurrency:
# Allow only one workflow globally because we need dedicated resources which only exist once
group: large-oltp-growth
cancel-in-progress: true
permissions:
contents: read
jobs:
oltp:
strategy:
fail-fast: false # allow other variants to continue even if one fails
matrix:
include:
# for now only grow the reuse branch, not the other branches.
- target: reuse_branch
custom_scripts:
- grow_action_blocks.sql
- grow_action_kwargs.sql
- grow_device_fingerprint_event.sql
- grow_edges.sql
- grow_hotel_rate_mapping.sql
- grow_ocr_pipeline_results_version.sql
- grow_priceline_raw_response.sql
- grow_relabled_transactions.sql
- grow_state_values.sql
- grow_values.sql
- grow_vertices.sql
- update_accounting_coding_body_tracking_category_selection.sql
- update_action_blocks.sql
- update_action_kwargs.sql
- update_denormalized_approval_workflow.sql
- update_device_fingerprint_event.sql
- update_edges.sql
- update_heron_transaction_enriched_log.sql
- update_heron_transaction_enrichment_requests.sql
- update_hotel_rate_mapping.sql
- update_incoming_webhooks.sql
- update_manual_transaction.sql
- update_ml_receipt_matching_log.sql
- update_ocr_pipeine_results_version.sql
- update_orc_pipeline_step_results.sql
- update_orc_pipeline_step_results_version.sql
- update_priceline_raw_response.sql
- update_quickbooks_transactions.sql
- update_raw_finicity_transaction.sql
- update_relabeled_transactions.sql
- update_state_values.sql
- update_stripe_authorization_event_log.sql
- update_transaction.sql
- update_values.sql
- update_vertices.sql
max-parallel: 1 # we want to run each growth workload sequentially (for now there is just one)
permissions:
contents: write
statuses: write
id-token: write # aws-actions/configure-aws-credentials
env:
TEST_PG_BENCH_DURATIONS_MATRIX: "1h"
TEST_PGBENCH_CUSTOM_SCRIPTS: ${{ join(matrix.custom_scripts, ' ') }}
POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
PG_VERSION: 16 # pre-determined by pre-determined project
TEST_OUTPUT: /tmp/test_output
BUILD_TYPE: remote
PLATFORM: ${{ matrix.target }}
runs-on: [ self-hosted, us-east-2, x64 ]
container:
image: ghcr.io/neondatabase/build-tools:pinned-bookworm
credentials:
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Configure AWS credentials # necessary to download artefacts
uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
role-duration-seconds: 18000 # 5 hours is currently max associated with IAM role
- name: Download Neon artifact
uses: ./.github/actions/download
with:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Set up Connection String
id: set-up-connstr
run: |
case "${{ matrix.target }}" in
reuse_branch)
CONNSTR=${{ secrets.BENCHMARK_LARGE_OLTP_REUSE_CONNSTR }}
;;
*)
echo >&2 "Unknown target=${{ matrix.target }}"
exit 1
;;
esac
CONNSTR_WITHOUT_POOLER="${CONNSTR//-pooler/}"
echo "connstr=${CONNSTR}" >> $GITHUB_OUTPUT
echo "connstr_without_pooler=${CONNSTR_WITHOUT_POOLER}" >> $GITHUB_OUTPUT
- name: pgbench with custom-scripts
uses: ./.github/actions/run-python-test-set
with:
build_type: ${{ env.BUILD_TYPE }}
test_selection: performance
run_in_parallel: false
save_perf_report: true
extra_params: -m remote_cluster --timeout 7200 -k test_perf_oltp_large_tenant_growth
pg_version: ${{ env.PG_VERSION }}
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
- name: Create Allure report
id: create-allure-report
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-generate
with:
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
uses: slackapi/slack-github-action@fcfb566f8b0aab22203f066d80ca1d7e4b5d05b3 # v1.27.1
with:
channel-id: "C06KHQVQ7U3" # on-call-qa-staging-stream
slack-message: |
Periodic large oltp tenant growth increase: ${{ job.status }}
<${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}|GitHub Run>
<${{ steps.create-allure-report.outputs.report-url }}|Allure report>
env:
SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}

View File

@@ -53,7 +53,7 @@ jobs:
submodules: true
- name: Check for Postgres changes
uses: dorny/paths-filter@1441771bbfdd59dcd748680ee64ebd8faab1a242 #v3
uses: step-security/paths-filter@v3
id: files_changed
with:
token: ${{ github.token }}

View File

@@ -1,4 +1,4 @@
name: Periodic pagebench performance test on unit-perf-aws-arm runners
name: Periodic pagebench performance test on unit-perf hetzner runner
on:
schedule:
@@ -40,7 +40,7 @@ jobs:
statuses: write
contents: write
pull-requests: write
runs-on: [ self-hosted, unit-perf-aws-arm ]
runs-on: [ self-hosted, unit-perf ]
container:
image: ghcr.io/neondatabase/build-tools:pinned-bookworm
credentials:

View File

@@ -34,7 +34,7 @@ jobs:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
- uses: step-security/changed-files@3dbe17c78367e7d60f00d78ae6781a35be47b4a1 # v45.0.1
id: python-src
with:
files: |
@@ -45,7 +45,7 @@ jobs:
poetry.lock
pyproject.toml
- uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
- uses: step-security/changed-files@3dbe17c78367e7d60f00d78ae6781a35be47b4a1 # v45.0.1
id: rust-src
with:
files: |

View File

@@ -1,84 +0,0 @@
name: Periodic proxy performance test on unit-perf-aws-arm runners
on:
push: # TODO: remove after testing
branches:
- test-proxy-bench # Runs on pushes to branches starting with test-proxy-bench
# schedule:
# * is a special character in YAML so you have to quote this string
# ┌───────────── minute (0 - 59)
# │ ┌───────────── hour (0 - 23)
# │ │ ┌───────────── day of the month (1 - 31)
# │ │ │ ┌───────────── month (1 - 12 or JAN-DEC)
# │ │ │ │ ┌───────────── day of the week (0 - 6 or SUN-SAT)
# - cron: '0 5 * * *' # Runs at 5 UTC once a day
workflow_dispatch: # adds an ability to run this manually
defaults:
run:
shell: bash -euo pipefail {0}
concurrency:
group: ${{ github.workflow }}
cancel-in-progress: false
permissions:
contents: read
jobs:
run_periodic_proxybench_test:
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: write
pull-requests: write
runs-on: [self-hosted, unit-perf-aws-arm]
timeout-minutes: 60 # 1h timeout
container:
image: ghcr.io/neondatabase/build-tools:pinned-bookworm
credentials:
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
steps:
- name: Checkout proxy-bench Repo
uses: actions/checkout@v4
with:
repository: neondatabase/proxy-bench
path: proxy-bench
- name: Set up the environment which depends on $RUNNER_TEMP on nvme drive
id: set-env
shell: bash -euxo pipefail {0}
run: |
PROXY_BENCH_PATH=$(realpath ./proxy-bench)
{
echo "PROXY_BENCH_PATH=$PROXY_BENCH_PATH"
echo "NEON_DIR=${RUNNER_TEMP}/neon"
echo "TEST_OUTPUT=${PROXY_BENCH_PATH}/test_output"
echo ""
} >> "$GITHUB_ENV"
- name: Run proxy-bench
run: ${PROXY_BENCH_PATH}/run.sh
- name: Ingest Bench Results # neon repo script
if: always()
run: |
mkdir -p $TEST_OUTPUT
python $NEON_DIR/scripts/proxy_bench_results_ingest.py --out $TEST_OUTPUT
- name: Push Metrics to Proxy perf database
if: always()
env:
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PROXY_TEST_RESULT_CONNSTR }}"
REPORT_FROM: $TEST_OUTPUT
run: $NEON_DIR/scripts/generate_and_push_perf_report.sh
- name: Docker cleanup
if: always()
run: docker compose down
- name: Notify Failure
if: failure()
run: echo "Proxy bench job failed" && exit 1

7
.gitignore vendored
View File

@@ -1,12 +1,10 @@
/artifact_cache
/build
/pg_install
/target
/tmp_check
/tmp_check_cli
__pycache__/
test_output/
neon_previous/
.vscode
.idea
*.swp
@@ -15,8 +13,6 @@ neon.iml
/.neon
/integration_tests/.neon
compaction-suite-results.*
pgxn/neon/communicator/communicator_bindings.h
docker-compose/docker-compose-parallel.yml
# Coverage
*.profraw
@@ -30,6 +26,3 @@ docker-compose/docker-compose-parallel.yml
# pgindent typedef lists
*.list
# Node
**/node_modules/

8
.gitmodules vendored
View File

@@ -1,16 +1,16 @@
[submodule "vendor/postgres-v14"]
path = vendor/postgres-v14
url = ../postgres.git
url = https://github.com/neondatabase/postgres.git
branch = REL_14_STABLE_neon
[submodule "vendor/postgres-v15"]
path = vendor/postgres-v15
url = ../postgres.git
url = https://github.com/neondatabase/postgres.git
branch = REL_15_STABLE_neon
[submodule "vendor/postgres-v16"]
path = vendor/postgres-v16
url = ../postgres.git
url = https://github.com/neondatabase/postgres.git
branch = REL_16_STABLE_neon
[submodule "vendor/postgres-v17"]
path = vendor/postgres-v17
url = ../postgres.git
url = https://github.com/neondatabase/postgres.git
branch = REL_17_STABLE_neon

498
Cargo.lock generated

File diff suppressed because it is too large Load Diff

View File

@@ -8,7 +8,6 @@ members = [
"pageserver/compaction",
"pageserver/ctl",
"pageserver/client",
"pageserver/client_grpc",
"pageserver/pagebench",
"pageserver/page_api",
"proxy",
@@ -23,8 +22,6 @@ members = [
"libs/http-utils",
"libs/pageserver_api",
"libs/postgres_ffi",
"libs/postgres_ffi_types",
"libs/postgres_versioninfo",
"libs/safekeeper_api",
"libs/desim",
"libs/neon-shmem",
@@ -35,7 +32,6 @@ members = [
"libs/pq_proto",
"libs/tenant_size_model",
"libs/metrics",
"libs/neonart",
"libs/postgres_connection",
"libs/remote_storage",
"libs/tracing-utils",
@@ -44,12 +40,10 @@ members = [
"libs/walproposer",
"libs/wal_decoder",
"libs/postgres_initdb",
"libs/proxy/json",
"libs/proxy/postgres-protocol2",
"libs/proxy/postgres-types2",
"libs/proxy/tokio-postgres2",
"endpoint_storage",
"pgxn/neon/communicator",
]
[workspace.package]
@@ -77,8 +71,8 @@ aws-credential-types = "1.2.0"
aws-sigv4 = { version = "1.2", features = ["sign-http"] }
aws-types = "1.3"
axum = { version = "0.8.1", features = ["ws"] }
axum-extra = { version = "0.10.0", features = ["typed-header", "query"] }
base64 = "0.22"
axum-extra = { version = "0.10.0", features = ["typed-header"] }
base64 = "0.13.0"
bincode = "1.3"
bindgen = "0.71"
bit_field = "0.10.2"
@@ -93,7 +87,6 @@ clap = { version = "4.0", features = ["derive", "env"] }
clashmap = { version = "1.0", features = ["raw-api"] }
comfy-table = "7.1"
const_format = "0.2"
crossbeam-utils = "0.8.21"
crc32c = "0.6"
diatomic-waker = { version = "0.2.3" }
either = "1.8"
@@ -132,7 +125,6 @@ jemalloc_pprof = { version = "0.7", features = ["symbolize", "flamegraph"] }
jsonwebtoken = "9"
lasso = "0.7"
libc = "0.2"
lock_api = "0.4.13"
md5 = "0.7.0"
measured = { version = "0.0.22", features=["lasso"] }
measured-process = { version = "0.0.22" }
@@ -153,13 +145,11 @@ parquet = { version = "53", default-features = false, features = ["zstd"] }
parquet_derive = "53"
pbkdf2 = { version = "0.12.1", features = ["simple", "std"] }
pem = "3.0.3"
peekable = "0.3.0"
pin-project-lite = "0.2"
pprof = { version = "0.14", features = ["criterion", "flamegraph", "frame-pointer", "prost-codec"] }
procfs = "0.16"
prometheus = {version = "0.13", default-features=false, features = ["process"]} # removes protobuf dependency
prost = "0.13.5"
prost-types = "0.13.5"
rand = "0.8"
redis = { version = "0.29.2", features = ["tokio-rustls-comp", "keep-alive"] }
regex = "1.10.2"
@@ -169,7 +159,7 @@ reqwest-middleware = "0.4"
reqwest-retry = "0.7"
routerify = "3"
rpds = "0.13"
rustc-hash = "2.1.1"
rustc-hash = "1.1.0"
rustls = { version = "0.23.16", default-features = false }
rustls-pemfile = "2"
rustls-pki-types = "1.11"
@@ -181,16 +171,14 @@ sentry = { version = "0.37", default-features = false, features = ["backtrace",
serde = { version = "1.0", features = ["derive"] }
serde_json = "1"
serde_path_to_error = "0.1"
serde_with = { version = "3", features = [ "base64" ] }
serde_with = { version = "2.0", features = [ "base64" ] }
serde_assert = "0.5.0"
serde_repr = "0.1.20"
sha2 = "0.10.2"
signal-hook = "0.3"
smallvec = "1.11"
smol_str = { version = "0.2.0", features = ["serde"] }
socket2 = "0.5"
spki = "0.7.3"
spin = "0.9.8"
strum = "0.26"
strum_macros = "0.26"
"subtle" = "2.5.0"
@@ -202,15 +190,16 @@ thiserror = "1.0"
tikv-jemallocator = { version = "0.6", features = ["profiling", "stats", "unprefixed_malloc_on_supported_platforms"] }
tikv-jemalloc-ctl = { version = "0.6", features = ["stats"] }
tokio = { version = "1.43.1", features = ["macros"] }
tokio-epoll-uring = { git = "https://github.com/neondatabase/tokio-epoll-uring.git" , branch = "main" }
tokio-io-timeout = "1.2.0"
tokio-postgres-rustls = "0.12.0"
tokio-rustls = { version = "0.26.0", default-features = false, features = ["tls12", "ring"]}
tokio-stream = { version = "0.1", features = ["sync"] }
tokio-stream = "0.1"
tokio-tar = "0.3"
tokio-util = { version = "0.7.10", features = ["io", "io-util", "rt"] }
tokio-util = { version = "0.7.10", features = ["io", "rt"] }
toml = "0.8"
toml_edit = "0.22"
tonic = { version = "0.13.1", default-features = false, features = ["channel", "codegen", "gzip", "prost", "router", "server", "tls-ring", "tls-native-roots", "zstd"] }
tonic = { version = "0.13.1", default-features = false, features = ["channel", "codegen", "prost", "router", "server", "tls-ring", "tls-native-roots"] }
tonic-reflection = { version = "0.13.1", features = ["server"] }
tower = { version = "0.5.2", default-features = false }
tower-http = { version = "0.6.2", features = ["auth", "request-id", "trace"] }
@@ -243,9 +232,6 @@ x509-cert = { version = "0.2.5" }
env_logger = "0.11"
log = "0.4"
tokio-epoll-uring = { git = "https://github.com/neondatabase/tokio-epoll-uring.git" , branch = "main" }
uring-common = { git = "https://github.com/neondatabase/tokio-epoll-uring.git" , branch = "main" }
## Libraries from neondatabase/ git forks, ideally with changes to be upstreamed
postgres = { git = "https://github.com/neondatabase/rust-postgres.git", branch = "neon" }
postgres-protocol = { git = "https://github.com/neondatabase/rust-postgres.git", branch = "neon" }
@@ -265,18 +251,14 @@ desim = { version = "0.1", path = "./libs/desim" }
endpoint_storage = { version = "0.0.1", path = "./endpoint_storage/" }
http-utils = { version = "0.1", path = "./libs/http-utils/" }
metrics = { version = "0.1", path = "./libs/metrics/" }
neon-shmem = { version = "0.1", path = "./libs/neon-shmem/" }
pageserver = { path = "./pageserver" }
pageserver_api = { version = "0.1", path = "./libs/pageserver_api/" }
pageserver_client = { path = "./pageserver/client" }
pageserver_client_grpc = { path = "./pageserver/client_grpc" }
pageserver_compaction = { version = "0.1", path = "./pageserver/compaction/" }
pageserver_page_api = { path = "./pageserver/page_api" }
postgres_backend = { version = "0.1", path = "./libs/postgres_backend/" }
postgres_connection = { version = "0.1", path = "./libs/postgres_connection/" }
postgres_ffi = { version = "0.1", path = "./libs/postgres_ffi/" }
postgres_ffi_types = { version = "0.1", path = "./libs/postgres_ffi_types/" }
postgres_versioninfo = { version = "0.1", path = "./libs/postgres_versioninfo/" }
postgres_initdb = { path = "./libs/postgres_initdb" }
posthog_client_lite = { version = "0.1", path = "./libs/posthog_client_lite" }
pq_proto = { version = "0.1", path = "./libs/pq_proto/" }
@@ -296,7 +278,6 @@ walproposer = { version = "0.1", path = "./libs/walproposer/" }
workspace_hack = { version = "0.1", path = "./workspace_hack/" }
## Build dependencies
cbindgen = "0.29.0"
criterion = "0.5.1"
rcgen = "0.13"
rstest = "0.18"

View File

@@ -5,6 +5,8 @@
ARG REPOSITORY=ghcr.io/neondatabase
ARG IMAGE=build-tools
ARG TAG=pinned
ARG DEFAULT_PG_VERSION=17
ARG STABLE_PG_VERSION=16
ARG DEBIAN_VERSION=bookworm
ARG DEBIAN_FLAVOR=${DEBIAN_VERSION}-slim
@@ -30,18 +32,7 @@ ARG BASE_IMAGE_SHA=debian:${DEBIAN_FLAVOR}
ARG BASE_IMAGE_SHA=${BASE_IMAGE_SHA/debian:bookworm-slim/debian@$BOOKWORM_SLIM_SHA}
ARG BASE_IMAGE_SHA=${BASE_IMAGE_SHA/debian:bullseye-slim/debian@$BULLSEYE_SLIM_SHA}
# Naive way:
#
# 1. COPY . .
# 1. make neon-pg-ext
# 2. cargo build <storage binaries>
#
# But to enable docker to cache intermediate layers, we perform a few preparatory steps:
#
# - Build all postgres versions, depending on just the contents of vendor/
# - Use cargo chef to build all rust dependencies
# 1. Build all postgres versions
# Build Postgres
FROM $REPOSITORY/$IMAGE:$TAG AS pg-build
WORKDIR /home/nonroot
@@ -49,15 +40,17 @@ COPY --chown=nonroot vendor/postgres-v14 vendor/postgres-v14
COPY --chown=nonroot vendor/postgres-v15 vendor/postgres-v15
COPY --chown=nonroot vendor/postgres-v16 vendor/postgres-v16
COPY --chown=nonroot vendor/postgres-v17 vendor/postgres-v17
COPY --chown=nonroot pgxn pgxn
COPY --chown=nonroot Makefile Makefile
COPY --chown=nonroot postgres.mk postgres.mk
COPY --chown=nonroot scripts/ninstall.sh scripts/ninstall.sh
ENV BUILD_TYPE=release
RUN set -e \
&& mold -run make -j $(nproc) -s postgres
&& mold -run make -j $(nproc) -s neon-pg-ext \
&& rm -rf pg_install/build \
&& tar -C pg_install -czf /home/nonroot/postgres_install.tar.gz .
# 2. Prepare cargo-chef recipe
# Prepare cargo-chef recipe
FROM $REPOSITORY/$IMAGE:$TAG AS plan
WORKDIR /home/nonroot
@@ -65,22 +58,26 @@ COPY --chown=nonroot . .
RUN cargo chef prepare --recipe-path recipe.json
# Main build image
# Build neon binaries
FROM $REPOSITORY/$IMAGE:$TAG AS build
WORKDIR /home/nonroot
ARG GIT_VERSION=local
ARG BUILD_TAG
ARG STABLE_PG_VERSION
COPY --from=pg-build /home/nonroot/pg_install/v14/include/postgresql/server pg_install/v14/include/postgresql/server
COPY --from=pg-build /home/nonroot/pg_install/v15/include/postgresql/server pg_install/v15/include/postgresql/server
COPY --from=pg-build /home/nonroot/pg_install/v16/include/postgresql/server pg_install/v16/include/postgresql/server
COPY --from=pg-build /home/nonroot/pg_install/v17/include/postgresql/server pg_install/v17/include/postgresql/server
COPY --from=pg-build /home/nonroot/pg_install/v16/lib pg_install/v16/lib
COPY --from=pg-build /home/nonroot/pg_install/v17/lib pg_install/v17/lib
COPY --from=plan /home/nonroot/recipe.json recipe.json
ARG ADDITIONAL_RUSTFLAGS=""
# 3. Build cargo dependencies. Note that this step doesn't depend on anything else than
# `recipe.json`, so the layer can be reused as long as none of the dependencies change.
COPY --from=plan /home/nonroot/recipe.json recipe.json
RUN set -e \
&& RUSTFLAGS="-Clinker=clang -Clink-arg=-fuse-ld=mold -Clink-arg=-Wl,--no-rosegment -Cforce-frame-pointers=yes ${ADDITIONAL_RUSTFLAGS}" cargo chef cook --locked --release --recipe-path recipe.json
# Perform the main build. We reuse the Postgres build artifacts from the intermediate 'pg-build'
# layer, and the cargo dependencies built in the previous step.
COPY --chown=nonroot --from=pg-build /home/nonroot/pg_install/ pg_install
COPY --chown=nonroot . .
RUN set -e \
@@ -95,11 +92,12 @@ RUN set -e \
--bin endpoint_storage \
--bin neon_local \
--bin storage_scrubber \
--locked --release \
&& mold -run make -j $(nproc) -s neon-pg-ext
--locked --release
# Assemble the final image
# Build final image
#
FROM $BASE_IMAGE_SHA
ARG DEFAULT_PG_VERSION
WORKDIR /data
RUN set -e \
@@ -109,6 +107,8 @@ RUN set -e \
libreadline-dev \
libseccomp-dev \
ca-certificates \
# System postgres for use with client libraries (e.g. in storage controller)
postgresql-15 \
openssl \
unzip \
curl \
@@ -138,15 +138,12 @@ COPY --from=build --chown=neon:neon /home/nonroot/target/release/proxy
COPY --from=build --chown=neon:neon /home/nonroot/target/release/endpoint_storage /usr/local/bin
COPY --from=build --chown=neon:neon /home/nonroot/target/release/neon_local /usr/local/bin
COPY --from=build --chown=neon:neon /home/nonroot/target/release/storage_scrubber /usr/local/bin
COPY --from=build /home/nonroot/pg_install/v14 /usr/local/v14/
COPY --from=build /home/nonroot/pg_install/v15 /usr/local/v15/
COPY --from=build /home/nonroot/pg_install/v16 /usr/local/v16/
COPY --from=build /home/nonroot/pg_install/v17 /usr/local/v17/
# Deprecated: Old deployment scripts use this tarball which contains all the Postgres binaries.
# That's obsolete, since all the same files are also present under /usr/local/v*. But to keep the
# old scripts working for now, create the tarball.
RUN tar -C /usr/local -cvzf /data/postgres_install.tar.gz v14 v15 v16 v17
COPY --from=pg-build /home/nonroot/pg_install/v14 /usr/local/v14/
COPY --from=pg-build /home/nonroot/pg_install/v15 /usr/local/v15/
COPY --from=pg-build /home/nonroot/pg_install/v16 /usr/local/v16/
COPY --from=pg-build /home/nonroot/pg_install/v17 /usr/local/v17/
COPY --from=pg-build /home/nonroot/postgres_install.tar.gz /data/
# By default, pageserver uses `.neon/` working directory in WORKDIR, so create one and fill it with the dummy config.
# Now, when `docker run ... pageserver` is run, it can start without errors, yet will have some default dummy values.

273
Makefile
View File

@@ -1,20 +1,7 @@
ROOT_PROJECT_DIR := $(dir $(abspath $(lastword $(MAKEFILE_LIST))))
# Where to install Postgres, default is ./pg_install, maybe useful for package
# managers.
POSTGRES_INSTALL_DIR ?= $(ROOT_PROJECT_DIR)/pg_install
# Supported PostgreSQL versions
POSTGRES_VERSIONS = v17 v16 v15 v14
# CARGO_BUILD_FLAGS: Extra flags to pass to `cargo build`. `--locked`
# and `--features testing` are popular examples.
#
# CARGO_PROFILE: Set to override the cargo profile to use. By default,
# it is derived from BUILD_TYPE.
# All intermediate build artifacts are stored here.
BUILD_DIR := $(ROOT_PROJECT_DIR)/build
# Where to install Postgres, default is ./pg_install, maybe useful for package managers
POSTGRES_INSTALL_DIR ?= $(ROOT_PROJECT_DIR)/pg_install/
ICU_PREFIX_DIR := /usr/local/icu
@@ -29,19 +16,12 @@ ifeq ($(BUILD_TYPE),release)
PG_CONFIGURE_OPTS = --enable-debug --with-openssl
PG_CFLAGS += -O2 -g3 $(CFLAGS)
PG_LDFLAGS = $(LDFLAGS)
CARGO_PROFILE ?= --profile=release
# NEON_CARGO_ARTIFACT_TARGET_DIR is the directory where `cargo build` places
# the final build artifacts. There is unfortunately no easy way of changing
# it to a fully predictable path, nor to extract the path with a simple
# command. See https://github.com/rust-lang/cargo/issues/9661 and
# https://github.com/rust-lang/cargo/issues/6790.
NEON_CARGO_ARTIFACT_TARGET_DIR = $(ROOT_PROJECT_DIR)/target/release
# Unfortunately, `--profile=...` is a nightly feature
CARGO_BUILD_FLAGS += --release
else ifeq ($(BUILD_TYPE),debug)
PG_CONFIGURE_OPTS = --enable-debug --with-openssl --enable-cassert --enable-depend
PG_CFLAGS += -O0 -g3 $(CFLAGS)
PG_LDFLAGS = $(LDFLAGS)
CARGO_PROFILE ?= --profile=dev
NEON_CARGO_ARTIFACT_TARGET_DIR = $(ROOT_PROJECT_DIR)/target/debug
else
$(error Bad build type '$(BUILD_TYPE)', see Makefile for options)
endif
@@ -105,32 +85,141 @@ CACHEDIR_TAG_CONTENTS := "Signature: 8a477f597d28d172789f06886806bc55"
# Top level Makefile to build Neon and PostgreSQL
#
.PHONY: all
all: neon postgres-install neon-pg-ext
all: neon postgres neon-pg-ext
### Neon Rust bits
#
# The 'postgres_ffi' crate depends on the Postgres headers.
# The 'postgres_ffi' depends on the Postgres headers.
.PHONY: neon
neon: postgres-headers-install walproposer-lib cargo-target-dir
neon: postgres-headers walproposer-lib cargo-target-dir
+@echo "Compiling Neon"
$(CARGO_CMD_PREFIX) cargo build $(CARGO_BUILD_FLAGS) $(CARGO_PROFILE)
$(CARGO_CMD_PREFIX) cargo build $(CARGO_BUILD_FLAGS)
.PHONY: cargo-target-dir
cargo-target-dir:
# https://github.com/rust-lang/cargo/issues/14281
mkdir -p target
test -e target/CACHEDIR.TAG || echo "$(CACHEDIR_TAG_CONTENTS)" > target/CACHEDIR.TAG
### PostgreSQL parts
# Some rules are duplicated for Postgres v14 and 15. We may want to refactor
# to avoid the duplication in the future, but it's tolerable for now.
#
$(POSTGRES_INSTALL_DIR)/build/%/config.status:
mkdir -p $(POSTGRES_INSTALL_DIR)
test -e $(POSTGRES_INSTALL_DIR)/CACHEDIR.TAG || echo "$(CACHEDIR_TAG_CONTENTS)" > $(POSTGRES_INSTALL_DIR)/CACHEDIR.TAG
+@echo "Configuring Postgres $* build"
@test -s $(ROOT_PROJECT_DIR)/vendor/postgres-$*/configure || { \
echo "\nPostgres submodule not found in $(ROOT_PROJECT_DIR)/vendor/postgres-$*/, execute "; \
echo "'git submodule update --init --recursive --depth 2 --progress .' in project root.\n"; \
exit 1; }
mkdir -p $(POSTGRES_INSTALL_DIR)/build/$*
VERSION=$*; \
EXTRA_VERSION=$$(cd $(ROOT_PROJECT_DIR)/vendor/postgres-$$VERSION && git rev-parse HEAD); \
(cd $(POSTGRES_INSTALL_DIR)/build/$$VERSION && \
env PATH="$(EXTRA_PATH_OVERRIDES):$$PATH" $(ROOT_PROJECT_DIR)/vendor/postgres-$$VERSION/configure \
CFLAGS='$(PG_CFLAGS)' LDFLAGS='$(PG_LDFLAGS)' \
$(PG_CONFIGURE_OPTS) --with-extra-version=" ($$EXTRA_VERSION)" \
--prefix=$(abspath $(POSTGRES_INSTALL_DIR))/$$VERSION > configure.log)
# nicer alias to run 'configure'
# Note: I've been unable to use templates for this part of our configuration.
# I'm not sure why it wouldn't work, but this is the only place (apart from
# the "build-all-versions" entry points) where direct mention of PostgreSQL
# versions is used.
.PHONY: postgres-configure-v17
postgres-configure-v17: $(POSTGRES_INSTALL_DIR)/build/v17/config.status
.PHONY: postgres-configure-v16
postgres-configure-v16: $(POSTGRES_INSTALL_DIR)/build/v16/config.status
.PHONY: postgres-configure-v15
postgres-configure-v15: $(POSTGRES_INSTALL_DIR)/build/v15/config.status
.PHONY: postgres-configure-v14
postgres-configure-v14: $(POSTGRES_INSTALL_DIR)/build/v14/config.status
# Install the PostgreSQL header files into $(POSTGRES_INSTALL_DIR)/<version>/include
.PHONY: postgres-headers-%
postgres-headers-%: postgres-configure-%
+@echo "Installing PostgreSQL $* headers"
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/src/include MAKELEVEL=0 install
# Compile and install PostgreSQL
.PHONY: postgres-%
postgres-%: postgres-configure-% \
postgres-headers-% # to prevent `make install` conflicts with neon's `postgres-headers`
+@echo "Compiling PostgreSQL $*"
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$* MAKELEVEL=0 install
+@echo "Compiling libpq $*"
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/src/interfaces/libpq install
+@echo "Compiling pg_prewarm $*"
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pg_prewarm install
+@echo "Compiling pg_buffercache $*"
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pg_buffercache install
+@echo "Compiling pg_visibility $*"
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pg_visibility install
+@echo "Compiling pageinspect $*"
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pageinspect install
+@echo "Compiling pg_trgm $*"
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pg_trgm install
+@echo "Compiling amcheck $*"
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/amcheck install
+@echo "Compiling test_decoding $*"
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/test_decoding install
.PHONY: postgres-clean-%
postgres-clean-%:
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$* MAKELEVEL=0 clean
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pg_buffercache clean
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pageinspect clean
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/src/interfaces/libpq clean
.PHONY: postgres-check-%
postgres-check-%: postgres-%
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$* MAKELEVEL=0 check
.PHONY: neon-pg-ext-%
neon-pg-ext-%: postgres-install-% cargo-target-dir
+@echo "Compiling neon-specific Postgres extensions for $*"
mkdir -p $(BUILD_DIR)/pgxn-$*
$(MAKE) PG_CONFIG="$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config" COPT='$(COPT)' \
NEON_CARGO_ARTIFACT_TARGET_DIR="$(NEON_CARGO_ARTIFACT_TARGET_DIR)" \
CARGO_BUILD_FLAGS="$(CARGO_BUILD_FLAGS)" \
CARGO_PROFILE="$(CARGO_PROFILE)" \
-C $(BUILD_DIR)/pgxn-$*\
-f $(ROOT_PROJECT_DIR)/pgxn/Makefile install
neon-pg-ext-%: postgres-%
+@echo "Compiling neon $*"
mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-$*
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config COPT='$(COPT)' \
-C $(POSTGRES_INSTALL_DIR)/build/neon-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon/Makefile install
+@echo "Compiling neon_walredo $*"
mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-walredo-$*
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config COPT='$(COPT)' \
-C $(POSTGRES_INSTALL_DIR)/build/neon-walredo-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon_walredo/Makefile install
+@echo "Compiling neon_rmgr $*"
mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-rmgr-$*
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config COPT='$(COPT)' \
-C $(POSTGRES_INSTALL_DIR)/build/neon-rmgr-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon_rmgr/Makefile install
+@echo "Compiling neon_test_utils $*"
mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-test-utils-$*
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config COPT='$(COPT)' \
-C $(POSTGRES_INSTALL_DIR)/build/neon-test-utils-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon_test_utils/Makefile install
+@echo "Compiling neon_utils $*"
mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-utils-$*
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config COPT='$(COPT)' \
-C $(POSTGRES_INSTALL_DIR)/build/neon-utils-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon_utils/Makefile install
.PHONY: neon-pg-clean-ext-%
neon-pg-clean-ext-%:
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config \
-C $(POSTGRES_INSTALL_DIR)/build/neon-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon/Makefile clean
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config \
-C $(POSTGRES_INSTALL_DIR)/build/neon-walredo-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon_walredo/Makefile clean
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config \
-C $(POSTGRES_INSTALL_DIR)/build/neon-test-utils-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon_test_utils/Makefile clean
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config \
-C $(POSTGRES_INSTALL_DIR)/build/neon-utils-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon_utils/Makefile clean
# Build walproposer as a static library. walproposer source code is located
# in the pgxn/neon directory.
@@ -144,15 +233,15 @@ neon-pg-ext-%: postgres-install-% cargo-target-dir
.PHONY: walproposer-lib
walproposer-lib: neon-pg-ext-v17
+@echo "Compiling walproposer-lib"
mkdir -p $(BUILD_DIR)/walproposer-lib
mkdir -p $(POSTGRES_INSTALL_DIR)/build/walproposer-lib
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/v17/bin/pg_config COPT='$(COPT)' \
-C $(BUILD_DIR)/walproposer-lib \
-C $(POSTGRES_INSTALL_DIR)/build/walproposer-lib \
-f $(ROOT_PROJECT_DIR)/pgxn/neon/Makefile walproposer-lib
cp $(POSTGRES_INSTALL_DIR)/v17/lib/libpgport.a $(BUILD_DIR)/walproposer-lib
cp $(POSTGRES_INSTALL_DIR)/v17/lib/libpgcommon.a $(BUILD_DIR)/walproposer-lib
$(AR) d $(BUILD_DIR)/walproposer-lib/libpgport.a \
cp $(POSTGRES_INSTALL_DIR)/v17/lib/libpgport.a $(POSTGRES_INSTALL_DIR)/build/walproposer-lib
cp $(POSTGRES_INSTALL_DIR)/v17/lib/libpgcommon.a $(POSTGRES_INSTALL_DIR)/build/walproposer-lib
$(AR) d $(POSTGRES_INSTALL_DIR)/build/walproposer-lib/libpgport.a \
pg_strong_random.o
$(AR) d $(BUILD_DIR)/walproposer-lib/libpgcommon.a \
$(AR) d $(POSTGRES_INSTALL_DIR)/build/walproposer-lib/libpgcommon.a \
checksum_helper.o \
cryptohash_openssl.o \
hmac_openssl.o \
@@ -160,18 +249,69 @@ walproposer-lib: neon-pg-ext-v17
parse_manifest.o \
scram-common.o
ifeq ($(UNAME_S),Linux)
$(AR) d $(BUILD_DIR)/walproposer-lib/libpgcommon.a \
$(AR) d $(POSTGRES_INSTALL_DIR)/build/walproposer-lib/libpgcommon.a \
pg_crc32c.o
endif
# Shorthand to call neon-pg-ext-% target for all Postgres versions
.PHONY: walproposer-lib-clean
walproposer-lib-clean:
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/v17/bin/pg_config \
-C $(POSTGRES_INSTALL_DIR)/build/walproposer-lib \
-f $(ROOT_PROJECT_DIR)/pgxn/neon/Makefile clean
.PHONY: neon-pg-ext
neon-pg-ext: $(foreach pg_version,$(POSTGRES_VERSIONS),neon-pg-ext-$(pg_version))
neon-pg-ext: \
neon-pg-ext-v14 \
neon-pg-ext-v15 \
neon-pg-ext-v16 \
neon-pg-ext-v17
.PHONY: neon-pg-clean-ext
neon-pg-clean-ext: \
neon-pg-clean-ext-v14 \
neon-pg-clean-ext-v15 \
neon-pg-clean-ext-v16 \
neon-pg-clean-ext-v17
# shorthand to build all Postgres versions
.PHONY: postgres
postgres: \
postgres-v14 \
postgres-v15 \
postgres-v16 \
postgres-v17
.PHONY: postgres-headers
postgres-headers: \
postgres-headers-v14 \
postgres-headers-v15 \
postgres-headers-v16 \
postgres-headers-v17
.PHONY: postgres-clean
postgres-clean: \
postgres-clean-v14 \
postgres-clean-v15 \
postgres-clean-v16 \
postgres-clean-v17
.PHONY: postgres-check
postgres-check: \
postgres-check-v14 \
postgres-check-v15 \
postgres-check-v16 \
postgres-check-v17
# 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
.PHONY: distclean
distclean:
$(RM) -r $(POSTGRES_INSTALL_DIR) $(BUILD_DIR)
$(RM) -r $(POSTGRES_INSTALL_DIR)
$(CARGO_CMD_PREFIX) cargo clean
.PHONY: fmt
@@ -180,7 +320,7 @@ fmt:
postgres-%-pg-bsd-indent: postgres-%
+@echo "Compiling pg_bsd_indent"
$(MAKE) -C $(BUILD_DIR)/$*/src/tools/pg_bsd_indent/
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/src/tools/pg_bsd_indent/
# Create typedef list for the core. Note that generally it should be combined with
# buildfarm one to cover platform specific stuff.
@@ -199,7 +339,7 @@ postgres-%-pgindent: postgres-%-pg-bsd-indent postgres-%-typedefs.list
cat $(ROOT_PROJECT_DIR)/vendor/postgres-$*/src/tools/pgindent/typedefs.list |\
cat - postgres-$*-typedefs.list | sort | uniq > postgres-$*-typedefs-full.list
+@echo note: you might want to run it on selected files/dirs instead.
INDENT=$(BUILD_DIR)/$*/src/tools/pg_bsd_indent/pg_bsd_indent \
INDENT=$(POSTGRES_INSTALL_DIR)/build/$*/src/tools/pg_bsd_indent/pg_bsd_indent \
$(ROOT_PROJECT_DIR)/vendor/postgres-$*/src/tools/pgindent/pgindent --typedefs postgres-$*-typedefs-full.list \
$(ROOT_PROJECT_DIR)/vendor/postgres-$*/src/ \
--excludes $(ROOT_PROJECT_DIR)/vendor/postgres-$*/src/tools/pgindent/exclude_file_patterns
@@ -210,41 +350,12 @@ postgres-%-pgindent: postgres-%-pg-bsd-indent postgres-%-typedefs.list
neon-pgindent: postgres-v17-pg-bsd-indent neon-pg-ext-v17
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/v17/bin/pg_config COPT='$(COPT)' \
FIND_TYPEDEF=$(ROOT_PROJECT_DIR)/vendor/postgres-v17/src/tools/find_typedef \
INDENT=$(BUILD_DIR)/v17/src/tools/pg_bsd_indent/pg_bsd_indent \
INDENT=$(POSTGRES_INSTALL_DIR)/build/v17/src/tools/pg_bsd_indent/pg_bsd_indent \
PGINDENT_SCRIPT=$(ROOT_PROJECT_DIR)/vendor/postgres-v17/src/tools/pgindent/pgindent \
-C $(BUILD_DIR)/pgxn-v17/neon \
-C $(POSTGRES_INSTALL_DIR)/build/neon-v17 \
-f $(ROOT_PROJECT_DIR)/pgxn/neon/Makefile pgindent
.PHONY: setup-pre-commit-hook
setup-pre-commit-hook:
ln -s -f $(ROOT_PROJECT_DIR)/pre-commit.py .git/hooks/pre-commit
build-tools/node_modules: build-tools/package.json
cd build-tools && $(if $(CI),npm ci,npm install)
touch build-tools/node_modules
.PHONY: lint-openapi-spec
lint-openapi-spec: build-tools/node_modules
# operation-2xx-response: pageserver timeline delete returns 404 on success
find . -iname "openapi_spec.y*ml" -exec\
npx --prefix=build-tools/ redocly\
--skip-rule=operation-operationId --skip-rule=operation-summary --extends=minimal\
--skip-rule=no-server-example.com --skip-rule=operation-2xx-response\
lint {} \+
# Targets for building PostgreSQL are defined in postgres.mk.
#
# But if the caller has indicated that PostgreSQL is already
# installed, by setting the PG_INSTALL_CACHED variable, skip it.
ifdef PG_INSTALL_CACHED
postgres-install: skip-install
$(foreach pg_version,$(POSTGRES_VERSIONS),postgres-install-$(pg_version)): skip-install
postgres-headers-install:
+@echo "Skipping installation of PostgreSQL headers because PG_INSTALL_CACHED is set"
skip-install:
+@echo "Skipping PostgreSQL installation because PG_INSTALL_CACHED is set"
else
include postgres.mk
endif

View File

@@ -35,7 +35,7 @@ RUN echo 'Acquire::Retries "5";' > /etc/apt/apt.conf.d/80-retries && \
echo -e "retry_connrefused=on\ntimeout=15\ntries=5\nretry-on-host-error=on\n" > /root/.wgetrc && \
echo -e "--retry-connrefused\n--connect-timeout 15\n--retry 5\n--max-time 300\n" > /root/.curlrc
COPY build-tools/patches/pgcopydbv017.patch /pgcopydbv017.patch
COPY build_tools/patches/pgcopydbv017.patch /pgcopydbv017.patch
RUN if [ "${DEBIAN_VERSION}" = "bookworm" ]; then \
set -e && \
@@ -165,7 +165,6 @@ RUN curl -fsSL \
&& rm sql_exporter.tar.gz
# protobuf-compiler (protoc)
# Keep the version the same as in compute/compute-node.Dockerfile
ENV PROTOC_VERSION=25.1
RUN curl -fsSL "https://github.com/protocolbuffers/protobuf/releases/download/v${PROTOC_VERSION}/protoc-${PROTOC_VERSION}-linux-$(uname -m | sed 's/aarch64/aarch_64/g').zip" -o "protoc.zip" \
&& unzip -q protoc.zip -d protoc \
@@ -180,7 +179,7 @@ RUN curl -sL "https://github.com/peak/s5cmd/releases/download/v${S5CMD_VERSION}/
&& mv s5cmd /usr/local/bin/s5cmd
# LLVM
ENV LLVM_VERSION=20
ENV LLVM_VERSION=19
RUN curl -fsSL 'https://apt.llvm.org/llvm-snapshot.gpg.key' | apt-key add - \
&& echo "deb http://apt.llvm.org/${DEBIAN_VERSION}/ llvm-toolchain-${DEBIAN_VERSION}-${LLVM_VERSION} main" > /etc/apt/sources.list.d/llvm.stable.list \
&& apt update \
@@ -188,12 +187,6 @@ RUN curl -fsSL 'https://apt.llvm.org/llvm-snapshot.gpg.key' | apt-key add - \
&& bash -c 'for f in /usr/bin/clang*-${LLVM_VERSION} /usr/bin/llvm*-${LLVM_VERSION}; do ln -s "${f}" "${f%-${LLVM_VERSION}}"; done' \
&& rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
# Install node
ENV NODE_VERSION=24
RUN curl -fsSL https://deb.nodesource.com/setup_${NODE_VERSION}.x | bash - \
&& apt install -y nodejs \
&& rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
# 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 ${DEBIAN_VERSION} stable" > /etc/apt/sources.list.d/docker.list \
@@ -299,7 +292,7 @@ WORKDIR /home/nonroot
# Rust
# Please keep the version of llvm (installed above) in sync with rust llvm (`rustc --version --verbose | grep LLVM`)
ENV RUSTC_VERSION=1.88.0
ENV RUSTC_VERSION=1.87.0
ENV RUSTUP_HOME="/home/nonroot/.rustup"
ENV PATH="/home/nonroot/.cargo/bin:${PATH}"
ARG RUSTFILT_VERSION=0.2.1
@@ -317,14 +310,14 @@ RUN curl -sSO https://static.rust-lang.org/rustup/dist/$(uname -m)-unknown-linux
. "$HOME/.cargo/env" && \
cargo --version && rustup --version && \
rustup component add llvm-tools rustfmt clippy && \
cargo install rustfilt --locked --version ${RUSTFILT_VERSION} && \
cargo install cargo-hakari --locked --version ${CARGO_HAKARI_VERSION} && \
cargo install cargo-deny --locked --version ${CARGO_DENY_VERSION} && \
cargo install cargo-hack --locked --version ${CARGO_HACK_VERSION} && \
cargo install cargo-nextest --locked --version ${CARGO_NEXTEST_VERSION} && \
cargo install cargo-chef --locked --version ${CARGO_CHEF_VERSION} && \
cargo install diesel_cli --locked --version ${CARGO_DIESEL_CLI_VERSION} \
--features postgres-bundled --no-default-features && \
cargo install rustfilt --version ${RUSTFILT_VERSION} --locked && \
cargo install cargo-hakari --version ${CARGO_HAKARI_VERSION} --locked && \
cargo install cargo-deny --version ${CARGO_DENY_VERSION} --locked && \
cargo install cargo-hack --version ${CARGO_HACK_VERSION} --locked && \
cargo install cargo-nextest --version ${CARGO_NEXTEST_VERSION} --locked && \
cargo install cargo-chef --version ${CARGO_CHEF_VERSION} --locked && \
cargo install diesel_cli --version ${CARGO_DIESEL_CLI_VERSION} --locked \
--features postgres-bundled --no-default-features && \
rm -rf /home/nonroot/.cargo/registry && \
rm -rf /home/nonroot/.cargo/git

File diff suppressed because it is too large Load Diff

View File

@@ -1,8 +0,0 @@
{
"name": "build-tools",
"private": true,
"devDependencies": {
"@redocly/cli": "1.34.4",
"@sourcemeta/jsonschema": "10.0.0"
}
}

View File

@@ -1,12 +1,9 @@
disallowed-methods = [
"tokio::task::block_in_place",
# Allow this for now, to deny it later once we stop using Handle::block_on completely
# "tokio::runtime::Handle::block_on",
# tokio-epoll-uring:
# - allow-invalid because the method doesn't exist on macOS
{ path = "tokio_epoll_uring::thread_local_system", replacement = "tokio_epoll_uring_ext module inside pageserver crate", allow-invalid = true }
# use tokio_epoll_uring_ext instead
"tokio_epoll_uring::thread_local_system",
]
disallowed-macros = [

3
compute/.gitignore vendored
View File

@@ -3,6 +3,3 @@ etc/neon_collector.yml
etc/neon_collector_autoscaling.yml
etc/sql_exporter.yml
etc/sql_exporter_autoscaling.yml
# Node.js dependencies
node_modules/

View File

@@ -22,7 +22,7 @@ sql_exporter.yml: $(jsonnet_files)
--output-file etc/$@ \
--tla-str collector_name=neon_collector \
--tla-str collector_file=neon_collector.yml \
--tla-str 'connection_string=postgresql://cloud_admin@127.0.0.1:5432/postgres?sslmode=disable&application_name=sql_exporter&pgaudit.log=none' \
--tla-str 'connection_string=postgresql://cloud_admin@127.0.0.1:5432/postgres?sslmode=disable&application_name=sql_exporter' \
etc/sql_exporter.jsonnet
sql_exporter_autoscaling.yml: $(jsonnet_files)
@@ -30,7 +30,7 @@ sql_exporter_autoscaling.yml: $(jsonnet_files)
--output-file etc/$@ \
--tla-str collector_name=neon_collector_autoscaling \
--tla-str collector_file=neon_collector_autoscaling.yml \
--tla-str 'connection_string=postgresql://cloud_admin@127.0.0.1:5432/postgres?sslmode=disable&application_name=sql_exporter_autoscaling&pgaudit.log=none' \
--tla-str 'connection_string=postgresql://cloud_admin@127.0.0.1:5432/postgres?sslmode=disable&application_name=sql_exporter_autoscaling' \
etc/sql_exporter.jsonnet
.PHONY: clean
@@ -48,11 +48,3 @@ jsonnetfmt-test:
.PHONY: jsonnetfmt-format
jsonnetfmt-format:
jsonnetfmt --in-place $(jsonnet_files)
.PHONY: manifest-schema-validation
manifest-schema-validation: ../build-tools/node_modules
npx --prefix=../build-tools/ jsonschema validate -d https://json-schema.org/draft/2020-12/schema manifest.schema.json manifest.yaml
../build-tools/node_modules: ../build-tools/package.json
cd ../build-tools && $(if $(CI),npm ci,npm install)
touch ../build-tools/node_modules

View File

@@ -9,7 +9,7 @@
#
# build-tools: This contains Rust compiler toolchain and other tools needed at compile
# time. This is also used for the storage builds. This image is defined in
# build-tools/Dockerfile.
# build-tools.Dockerfile.
#
# build-deps: Contains C compiler, other build tools, and compile-time dependencies
# needed to compile PostgreSQL and most extensions. (Some extensions need
@@ -77,6 +77,9 @@
# build_and_test.yml github workflow for how that's done.
ARG PG_VERSION
ARG REPOSITORY=ghcr.io/neondatabase
ARG IMAGE=build-tools
ARG TAG=pinned
ARG BUILD_TAG
ARG DEBIAN_VERSION=bookworm
ARG DEBIAN_FLAVOR=${DEBIAN_VERSION}-slim
@@ -115,9 +118,6 @@ ARG EXTENSIONS=all
FROM $BASE_IMAGE_SHA AS build-deps
ARG DEBIAN_VERSION
# Keep in sync with build-tools/Dockerfile
ENV PROTOC_VERSION=25.1
# Use strict mode for bash to catch errors early
SHELL ["/bin/bash", "-euo", "pipefail", "-c"]
@@ -149,17 +149,8 @@ RUN case $DEBIAN_VERSION in \
ninja-build git autoconf automake libtool build-essential bison flex libreadline-dev \
zlib1g-dev libxml2-dev libcurl4-openssl-dev libossp-uuid-dev wget ca-certificates pkg-config libssl-dev \
libicu-dev libxslt1-dev liblz4-dev libzstd-dev zstd curl unzip g++ \
libclang-dev \
jsonnet \
$VERSION_INSTALLS \
&& apt clean && rm -rf /var/lib/apt/lists/* \
&& useradd -ms /bin/bash nonroot -b /home \
# Install protoc from binary release, since Debian's versions are too old.
&& curl -fsSL "https://github.com/protocolbuffers/protobuf/releases/download/v${PROTOC_VERSION}/protoc-${PROTOC_VERSION}-linux-$(uname -m | sed 's/aarch64/aarch_64/g').zip" -o "protoc.zip" \
&& unzip -q protoc.zip -d protoc \
&& mv protoc/bin/protoc /usr/local/bin/protoc \
&& mv protoc/include/google /usr/local/include/google \
&& rm -rf protoc.zip protoc
&& apt clean && rm -rf /var/lib/apt/lists/*
#########################################################################################
#
@@ -170,29 +161,7 @@ RUN case $DEBIAN_VERSION in \
FROM build-deps AS pg-build
ARG PG_VERSION
COPY vendor/postgres-${PG_VERSION:?} postgres
COPY compute/patches/postgres_fdw.patch .
COPY compute/patches/pg_stat_statements_pg14-16.patch .
COPY compute/patches/pg_stat_statements_pg17.patch .
RUN cd postgres && \
# Apply patches to some contrib extensions
# For example, we need to grant EXECUTE on pg_stat_statements_reset() to {privileged_role_name}.
# In vanilla Postgres this function is limited to Postgres role superuser.
# In Neon we have {privileged_role_name} role that is not a superuser but replaces superuser in some cases.
# We could add the additional grant statements to the Postgres repository but it would be hard to maintain,
# whenever we need to pick up a new Postgres version and we want to limit the changes in our Postgres fork,
# so we do it here.
case "${PG_VERSION}" in \
"v14" | "v15" | "v16") \
patch -p1 < /pg_stat_statements_pg14-16.patch; \
;; \
"v17") \
patch -p1 < /pg_stat_statements_pg17.patch; \
;; \
*) \
# To do not forget to migrate patches to the next major version
echo "No contrib patches for this PostgreSQL version" && exit 1;; \
esac && \
patch -p1 < /postgres_fdw.patch && \
export CONFIGURE_CMD="./configure CFLAGS='-O2 -g3 -fsigned-char' --enable-debug --with-openssl --with-uuid=ossp \
--with-icu --with-libxml --with-libxslt --with-lz4" && \
if [ "${PG_VERSION:?}" != "v14" ]; then \
@@ -202,10 +171,15 @@ RUN cd postgres && \
eval $CONFIGURE_CMD && \
make MAKELEVEL=0 -j $(getconf _NPROCESSORS_ONLN) -s install && \
make MAKELEVEL=0 -j $(getconf _NPROCESSORS_ONLN) -s -C contrib/ install && \
# Install headers
make MAKELEVEL=0 -j $(getconf _NPROCESSORS_ONLN) -s -C src/include install && \
make MAKELEVEL=0 -j $(getconf _NPROCESSORS_ONLN) -s -C src/interfaces/libpq install && \
# Enable some of contrib extensions
echo 'trusted = true' >> /usr/local/pgsql/share/extension/autoinc.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/dblink.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgres_fdw.control && \
file=/usr/local/pgsql/share/extension/postgres_fdw--1.0.sql && [ -e $file ] && \
echo 'GRANT USAGE ON FOREIGN DATA WRAPPER postgres_fdw TO neon_superuser;' >> $file && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/bloom.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/earthdistance.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/insert_username.control && \
@@ -215,7 +189,34 @@ RUN cd postgres && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/pgrowlocks.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/pgstattuple.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/refint.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/xml2.control
echo 'trusted = true' >> /usr/local/pgsql/share/extension/xml2.control && \
# We need to grant EXECUTE on pg_stat_statements_reset() to neon_superuser.
# In vanilla postgres this function is limited to Postgres role superuser.
# In neon we have neon_superuser role that is not a superuser but replaces superuser in some cases.
# We could add the additional grant statements to the postgres repository but it would be hard to maintain,
# whenever we need to pick up a new postgres version and we want to limit the changes in our postgres fork,
# so we do it here.
for file in /usr/local/pgsql/share/extension/pg_stat_statements--*.sql; do \
filename=$(basename "$file"); \
# Note that there are no downgrade scripts for pg_stat_statements, so we \
# don't have to modify any downgrade paths or (much) older versions: we only \
# have to make sure every creation of the pg_stat_statements_reset function \
# also adds execute permissions to the neon_superuser.
case $filename in \
pg_stat_statements--1.4.sql) \
# pg_stat_statements_reset is first created with 1.4
echo 'GRANT EXECUTE ON FUNCTION pg_stat_statements_reset() TO neon_superuser;' >> $file; \
;; \
pg_stat_statements--1.6--1.7.sql) \
# Then with the 1.6-1.7 migration it is re-created with a new signature, thus add the permissions back
echo 'GRANT EXECUTE ON FUNCTION pg_stat_statements_reset(Oid, Oid, bigint) TO neon_superuser;' >> $file; \
;; \
pg_stat_statements--1.10--1.11.sql) \
# Then with the 1.10-1.11 migration it is re-created with a new signature again, thus add the permissions back
echo 'GRANT EXECUTE ON FUNCTION pg_stat_statements_reset(Oid, Oid, bigint, boolean) TO neon_superuser;' >> $file; \
;; \
esac; \
done;
# Set PATH for all the subsequent build steps
ENV PATH="/usr/local/pgsql/bin:$PATH"
@@ -1056,10 +1057,17 @@ RUN make -j $(getconf _NPROCESSORS_ONLN) && \
#########################################################################################
#
# Layer "build-deps with Rust toolchain installed"
# Layer "pg build with nonroot user and cargo installed"
# This layer is base and common for layers with `pgrx`
#
#########################################################################################
FROM build-deps AS build-deps-with-cargo
FROM pg-build AS pg-build-nonroot-with-cargo
ARG PG_VERSION
RUN apt update && \
apt install --no-install-recommends --no-install-suggests -y curl libclang-dev && \
apt clean && rm -rf /var/lib/apt/lists/* && \
useradd -ms /bin/bash nonroot -b /home
ENV HOME=/home/nonroot
ENV PATH="/home/nonroot/.cargo/bin:$PATH"
@@ -1074,29 +1082,13 @@ RUN curl -sSO https://static.rust-lang.org/rustup/dist/$(uname -m)-unknown-linux
./rustup-init -y --no-modify-path --profile minimal --default-toolchain stable && \
rm rustup-init
#########################################################################################
#
# Layer "pg-build with Rust toolchain installed"
# This layer is base and common for layers with `pgrx`
#
#########################################################################################
FROM pg-build AS pg-build-with-cargo
ARG PG_VERSION
ENV HOME=/home/nonroot
ENV PATH="/home/nonroot/.cargo/bin:$PATH"
USER nonroot
WORKDIR /home/nonroot
COPY --from=build-deps-with-cargo /home/nonroot /home/nonroot
#########################################################################################
#
# Layer "rust extensions"
# This layer is used to build `pgrx` deps
#
#########################################################################################
FROM pg-build-with-cargo AS rust-extensions-build
FROM pg-build-nonroot-with-cargo AS rust-extensions-build
ARG PG_VERSION
RUN case "${PG_VERSION:?}" in \
@@ -1118,7 +1110,7 @@ USER root
# and eventually get merged with `rust-extensions-build`
#
#########################################################################################
FROM pg-build-with-cargo AS rust-extensions-build-pgrx12
FROM pg-build-nonroot-with-cargo AS rust-extensions-build-pgrx12
ARG PG_VERSION
RUN cargo install --locked --version 0.12.9 cargo-pgrx && \
@@ -1135,7 +1127,7 @@ USER root
# and eventually get merged with `rust-extensions-build`
#
#########################################################################################
FROM pg-build-with-cargo AS rust-extensions-build-pgrx14
FROM pg-build-nonroot-with-cargo AS rust-extensions-build-pgrx14
ARG PG_VERSION
RUN cargo install --locked --version 0.14.1 cargo-pgrx && \
@@ -1152,12 +1144,10 @@ USER root
FROM build-deps AS pgrag-src
ARG PG_VERSION
WORKDIR /ext-src
COPY compute/patches/onnxruntime.patch .
WORKDIR /ext-src
RUN wget https://github.com/microsoft/onnxruntime/archive/refs/tags/v1.18.1.tar.gz -O onnxruntime.tar.gz && \
mkdir onnxruntime-src && cd onnxruntime-src && tar xzf ../onnxruntime.tar.gz --strip-components=1 -C . && \
patch -p1 < /ext-src/onnxruntime.patch && \
echo "#nothing to test here" > neon-test.sh
RUN wget https://github.com/neondatabase-labs/pgrag/archive/refs/tags/v0.1.2.tar.gz -O pgrag.tar.gz && \
@@ -1172,7 +1162,7 @@ COPY --from=pgrag-src /ext-src/ /ext-src/
# Install it using virtual environment, because Python 3.11 (the default version on Debian 12 (Bookworm)) complains otherwise
WORKDIR /ext-src/onnxruntime-src
RUN apt update && apt install --no-install-recommends --no-install-suggests -y \
python3 python3-pip python3-venv && \
python3 python3-pip python3-venv protobuf-compiler && \
apt clean && rm -rf /var/lib/apt/lists/* && \
python3 -m venv venv && \
. venv/bin/activate && \
@@ -1517,7 +1507,7 @@ WORKDIR /ext-src
COPY compute/patches/pg_duckdb_v031.patch .
COPY compute/patches/duckdb_v120.patch .
# pg_duckdb build requires source dir to be a git repo to get submodules
# allow {privileged_role_name} to execute some functions that in pg_duckdb are available to superuser only:
# allow neon_superuser to execute some functions that in pg_duckdb are available to superuser only:
# - extension management function duckdb.install_extension()
# - access to duckdb.extensions table and its sequence
RUN git clone --depth 1 --branch v0.3.1 https://github.com/duckdb/pg_duckdb.git pg_duckdb-src && \
@@ -1565,31 +1555,29 @@ RUN make -j $(getconf _NPROCESSORS_ONLN) && \
FROM build-deps AS pgaudit-src
ARG PG_VERSION
WORKDIR /ext-src
COPY "compute/patches/pgaudit-parallel_workers-${PG_VERSION}.patch" .
RUN case "${PG_VERSION}" in \
"v14") \
export PGAUDIT_VERSION=1.6.3 \
export PGAUDIT_CHECKSUM=37a8f5a7cc8d9188e536d15cf0fdc457fcdab2547caedb54442c37f124110919 \
export PGAUDIT_VERSION=1.6.2 \
export PGAUDIT_CHECKSUM=1f350d70a0cbf488c0f2b485e3a5c9b11f78ad9e3cbb95ef6904afa1eb3187eb \
;; \
"v15") \
export PGAUDIT_VERSION=1.7.1 \
export PGAUDIT_CHECKSUM=e9c8e6e092d82b2f901d72555ce0fe7780552f35f8985573796cd7e64b09d4ec \
export PGAUDIT_VERSION=1.7.0 \
export PGAUDIT_CHECKSUM=8f4a73e451c88c567e516e6cba7dc1e23bc91686bb6f1f77f8f3126d428a8bd8 \
;; \
"v16") \
export PGAUDIT_VERSION=16.1 \
export PGAUDIT_CHECKSUM=3bae908ab70ba0c6f51224009dbcfff1a97bd6104c6273297a64292e1b921fee \
export PGAUDIT_VERSION=16.0 \
export PGAUDIT_CHECKSUM=d53ef985f2d0b15ba25c512c4ce967dce07b94fd4422c95bd04c4c1a055fe738 \
;; \
"v17") \
export PGAUDIT_VERSION=17.1 \
export PGAUDIT_CHECKSUM=9c5f37504d393486cc75d2ced83f75f5899be64fa85f689d6babb833b4361e6c \
export PGAUDIT_VERSION=17.0 \
export PGAUDIT_CHECKSUM=7d0d08d030275d525f36cd48b38c6455f1023da863385badff0cec44965bfd8c \
;; \
*) \
echo "pgaudit is not supported on this PostgreSQL version" && exit 1;; \
esac && \
wget https://github.com/pgaudit/pgaudit/archive/refs/tags/${PGAUDIT_VERSION}.tar.gz -O pgaudit.tar.gz && \
echo "${PGAUDIT_CHECKSUM} pgaudit.tar.gz" | sha256sum --check && \
mkdir pgaudit-src && cd pgaudit-src && tar xzf ../pgaudit.tar.gz --strip-components=1 -C . && \
patch -p1 < "/ext-src/pgaudit-parallel_workers-${PG_VERSION}.patch"
mkdir pgaudit-src && cd pgaudit-src && tar xzf ../pgaudit.tar.gz --strip-components=1 -C .
FROM pg-build AS pgaudit-build
COPY --from=pgaudit-src /ext-src/ /ext-src/
@@ -1629,14 +1617,22 @@ RUN make install USE_PGXS=1 -j $(getconf _NPROCESSORS_ONLN)
# compile neon extensions
#
#########################################################################################
FROM pg-build-with-cargo AS neon-ext-build
FROM pg-build AS neon-ext-build
ARG PG_VERSION
USER root
COPY . .
RUN make -j $(getconf _NPROCESSORS_ONLN) -C pgxn -s install-compute \
BUILD_TYPE=release CARGO_BUILD_FLAGS="--locked --release" NEON_CARGO_ARTIFACT_TARGET_DIR="$(pwd)/target/release"
COPY pgxn/ pgxn/
RUN make -j $(getconf _NPROCESSORS_ONLN) \
-C pgxn/neon \
-s install && \
make -j $(getconf _NPROCESSORS_ONLN) \
-C pgxn/neon_utils \
-s install && \
make -j $(getconf _NPROCESSORS_ONLN) \
-C pgxn/neon_test_utils \
-s install && \
make -j $(getconf _NPROCESSORS_ONLN) \
-C pgxn/neon_rmgr \
-s install
#########################################################################################
#
@@ -1726,7 +1722,7 @@ FROM extensions-${EXTENSIONS} AS neon-pg-ext-build
# Compile the Neon-specific `compute_ctl`, `fast_import`, and `local_proxy` binaries
#
#########################################################################################
FROM build-deps-with-cargo AS compute-tools
FROM $REPOSITORY/$IMAGE:$TAG AS compute-tools
ARG BUILD_TAG
ENV BUILD_TAG=$BUILD_TAG
@@ -1736,7 +1732,7 @@ COPY --chown=nonroot . .
RUN --mount=type=cache,uid=1000,target=/home/nonroot/.cargo/registry \
--mount=type=cache,uid=1000,target=/home/nonroot/.cargo/git \
--mount=type=cache,uid=1000,target=/home/nonroot/target \
cargo build --locked --profile release-line-debug-size-lto --bin compute_ctl --bin fast_import --bin local_proxy && \
mold -run cargo build --locked --profile release-line-debug-size-lto --bin compute_ctl --bin fast_import --bin local_proxy && \
mkdir target-bin && \
cp target/release-line-debug-size-lto/compute_ctl \
target/release-line-debug-size-lto/fast_import \
@@ -1783,7 +1779,7 @@ RUN set -e \
#########################################################################################
FROM build-deps AS exporters
ARG TARGETARCH
# Keep sql_exporter version same as in build-tools/Dockerfile and
# Keep sql_exporter version same as in build-tools.Dockerfile and
# test_runner/regress/test_compute_metrics.py
# See comment on the top of the file regading `echo`, `-e` and `\n`
RUN if [ "$TARGETARCH" = "amd64" ]; then\
@@ -1830,11 +1826,10 @@ RUN rm /usr/local/pgsql/lib/lib*.a
# Preprocess the sql_exporter configuration files
#
#########################################################################################
FROM build-deps AS sql_exporter_preprocessor
FROM $REPOSITORY/$IMAGE:$TAG AS sql_exporter_preprocessor
ARG PG_VERSION
USER nonroot
WORKDIR /home/nonroot
COPY --chown=nonroot compute compute
@@ -1908,10 +1903,10 @@ RUN cd /ext-src/pg_repack-src && patch -p1 </ext-src/pg_repack.patch && rm -f /e
COPY --chmod=755 docker-compose/run-tests.sh /run-tests.sh
RUN echo /usr/local/pgsql/lib > /etc/ld.so.conf.d/00-neon.conf && /sbin/ldconfig
RUN apt-get update && apt-get install -y libtap-parser-sourcehandler-pgtap-perl jq parallel \
RUN apt-get update && apt-get install -y libtap-parser-sourcehandler-pgtap-perl jq \
&& apt clean && rm -rf /ext-src/*.tar.gz /ext-src/*.patch /var/lib/apt/lists/*
ENV PATH=/usr/local/pgsql/bin:$PATH
ENV PGHOST=compute1
ENV PGHOST=compute
ENV PGPORT=55433
ENV PGUSER=cloud_admin
ENV PGDATABASE=postgres
@@ -1981,7 +1976,7 @@ RUN apt update && \
locales \
lsof \
procps \
rsyslog-gnutls \
rsyslog \
screen \
tcpdump \
$VERSION_INSTALLS && \

View File

@@ -8,8 +8,6 @@
import 'sql_exporter/compute_logical_snapshot_files.libsonnet',
import 'sql_exporter/compute_logical_snapshots_bytes.libsonnet',
import 'sql_exporter/compute_max_connections.libsonnet',
import 'sql_exporter/compute_pg_oldest_frozen_xid_age.libsonnet',
import 'sql_exporter/compute_pg_oldest_mxid_age.libsonnet',
import 'sql_exporter/compute_receive_lsn.libsonnet',
import 'sql_exporter/compute_subscriptions_count.libsonnet',
import 'sql_exporter/connection_counts.libsonnet',

View File

@@ -21,8 +21,6 @@ unix_socket_dir=/tmp/
unix_socket_mode=0777
; required for pgbouncer_exporter
ignore_startup_parameters=extra_float_digits
; pidfile for graceful termination
pidfile=/tmp/pgbouncer.pid
;; Disable connection logging. It produces a lot of logs that no one looks at,
;; and we can get similar log entries from the proxy too. We had incidents in

View File

@@ -1,13 +0,0 @@
{
metric_name: 'compute_pg_oldest_frozen_xid_age',
type: 'gauge',
help: 'Age of oldest XIDs that have not been frozen by VACUUM. An indicator of how long it has been since VACUUM last ran.',
key_labels: [
'database_name',
],
value_label: 'metric',
values: [
'frozen_xid_age',
],
query: importstr 'sql_exporter/compute_pg_oldest_frozen_xid_age.sql',
}

View File

@@ -1,4 +0,0 @@
SELECT datname database_name,
age(datfrozenxid) frozen_xid_age
FROM pg_database
ORDER BY frozen_xid_age DESC LIMIT 10;

View File

@@ -1,13 +0,0 @@
{
metric_name: 'compute_pg_oldest_mxid_age',
type: 'gauge',
help: 'Age of oldest MXIDs that have not been replaced by VACUUM. An indicator of how long it has been since VACUUM last ran.',
key_labels: [
'database_name',
],
value_label: 'metric',
values: [
'min_mxid_age',
],
query: importstr 'sql_exporter/compute_pg_oldest_mxid_age.sql',
}

View File

@@ -1,4 +0,0 @@
SELECT datname database_name,
mxid_age(datminmxid) min_mxid_age
FROM pg_database
ORDER BY min_mxid_age DESC LIMIT 10;

View File

@@ -1,209 +0,0 @@
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"title": "Neon Compute Manifest Schema",
"description": "Schema for Neon compute node configuration manifest",
"type": "object",
"properties": {
"pg_settings": {
"type": "object",
"properties": {
"common": {
"type": "object",
"properties": {
"client_connection_check_interval": {
"type": "string",
"description": "Check for client disconnection interval in milliseconds"
},
"effective_io_concurrency": {
"type": "string",
"description": "Effective IO concurrency setting"
},
"fsync": {
"type": "string",
"enum": ["on", "off"],
"description": "Whether to force fsync to disk"
},
"hot_standby": {
"type": "string",
"enum": ["on", "off"],
"description": "Whether hot standby is enabled"
},
"idle_in_transaction_session_timeout": {
"type": "string",
"description": "Timeout for idle transactions in milliseconds"
},
"listen_addresses": {
"type": "string",
"description": "Addresses to listen on"
},
"log_connections": {
"type": "string",
"enum": ["on", "off"],
"description": "Whether to log connections"
},
"log_disconnections": {
"type": "string",
"enum": ["on", "off"],
"description": "Whether to log disconnections"
},
"log_temp_files": {
"type": "string",
"description": "Size threshold for logging temporary files in KB"
},
"log_error_verbosity": {
"type": "string",
"enum": ["terse", "verbose", "default"],
"description": "Error logging verbosity level"
},
"log_min_error_statement": {
"type": "string",
"description": "Minimum error level for statement logging"
},
"maintenance_io_concurrency": {
"type": "string",
"description": "Maintenance IO concurrency setting"
},
"max_connections": {
"type": "string",
"description": "Maximum number of connections"
},
"max_replication_flush_lag": {
"type": "string",
"description": "Maximum replication flush lag"
},
"max_replication_slots": {
"type": "string",
"description": "Maximum number of replication slots"
},
"max_replication_write_lag": {
"type": "string",
"description": "Maximum replication write lag"
},
"max_wal_senders": {
"type": "string",
"description": "Maximum number of WAL senders"
},
"max_wal_size": {
"type": "string",
"description": "Maximum WAL size"
},
"neon.unstable_extensions": {
"type": "string",
"description": "List of unstable extensions"
},
"neon.protocol_version": {
"type": "string",
"description": "Neon protocol version"
},
"password_encryption": {
"type": "string",
"description": "Password encryption method"
},
"restart_after_crash": {
"type": "string",
"enum": ["on", "off"],
"description": "Whether to restart after crash"
},
"superuser_reserved_connections": {
"type": "string",
"description": "Number of reserved connections for superuser"
},
"synchronous_standby_names": {
"type": "string",
"description": "Names of synchronous standby servers"
},
"wal_keep_size": {
"type": "string",
"description": "WAL keep size"
},
"wal_level": {
"type": "string",
"description": "WAL level"
},
"wal_log_hints": {
"type": "string",
"enum": ["on", "off"],
"description": "Whether to log hints in WAL"
},
"wal_sender_timeout": {
"type": "string",
"description": "WAL sender timeout in milliseconds"
}
},
"required": [
"client_connection_check_interval",
"effective_io_concurrency",
"fsync",
"hot_standby",
"idle_in_transaction_session_timeout",
"listen_addresses",
"log_connections",
"log_disconnections",
"log_temp_files",
"log_error_verbosity",
"log_min_error_statement",
"maintenance_io_concurrency",
"max_connections",
"max_replication_flush_lag",
"max_replication_slots",
"max_replication_write_lag",
"max_wal_senders",
"max_wal_size",
"neon.unstable_extensions",
"neon.protocol_version",
"password_encryption",
"restart_after_crash",
"superuser_reserved_connections",
"synchronous_standby_names",
"wal_keep_size",
"wal_level",
"wal_log_hints",
"wal_sender_timeout"
]
},
"replica": {
"type": "object",
"properties": {
"hot_standby": {
"type": "string",
"enum": ["on", "off"],
"description": "Whether hot standby is enabled for replicas"
}
},
"required": ["hot_standby"]
},
"per_version": {
"type": "object",
"patternProperties": {
"^1[4-7]$": {
"type": "object",
"properties": {
"common": {
"type": "object",
"properties": {
"io_combine_limit": {
"type": "string",
"description": "IO combine limit"
}
}
},
"replica": {
"type": "object",
"properties": {
"recovery_prefetch": {
"type": "string",
"enum": ["on", "off"],
"description": "Whether to enable recovery prefetch for PostgreSQL replicas"
}
}
}
}
}
}
}
},
"required": ["common", "replica", "per_version"]
}
},
"required": ["pg_settings"]
}

View File

@@ -105,17 +105,17 @@ pg_settings:
# Neon hot standby ignores pages that are not in the shared_buffers
recovery_prefetch: "off"
16:
common: {}
common:
replica:
# prefetching of blocks referenced in WAL doesn't make sense for us
# Neon hot standby ignores pages that are not in the shared_buffers
recovery_prefetch: "off"
15:
common: {}
common:
replica:
# prefetching of blocks referenced in WAL doesn't make sense for us
# Neon hot standby ignores pages that are not in the shared_buffers
recovery_prefetch: "off"
14:
common: {}
replica: {}
common:
replica:

View File

@@ -1,37 +0,0 @@
{
"name": "neon-compute",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "neon-compute",
"dependencies": {
"@sourcemeta/jsonschema": "9.3.4"
}
},
"node_modules/@sourcemeta/jsonschema": {
"version": "9.3.4",
"resolved": "https://registry.npmjs.org/@sourcemeta/jsonschema/-/jsonschema-9.3.4.tgz",
"integrity": "sha512-hkujfkZAIGXUs4U//We9faZW8LZ4/H9LqagRYsFSulH/VLcKPNhZyCTGg7AhORuzm27zqENvKpnX4g2FzudYFw==",
"cpu": [
"x64",
"arm64"
],
"license": "AGPL-3.0",
"os": [
"darwin",
"linux",
"win32"
],
"bin": {
"jsonschema": "cli.js"
},
"engines": {
"node": ">=16"
},
"funding": {
"url": "https://github.com/sponsors/sourcemeta"
}
}
}
}

View File

@@ -1,27 +1,16 @@
diff --git a/sql/anon.sql b/sql/anon.sql
index 0cdc769..5eab1d6 100644
index 0cdc769..f6cc950 100644
--- a/sql/anon.sql
+++ b/sql/anon.sql
@@ -1141,3 +1141,19 @@ $$
@@ -1141,3 +1141,8 @@ $$
-- TODO : https://en.wikipedia.org/wiki/L-diversity
-- TODO : https://en.wikipedia.org/wiki/T-closeness
+
+-- NEON Patches
+
+DO $$
+DECLARE
+ privileged_role_name text;
+BEGIN
+ privileged_role_name := current_setting('neon.privileged_role_name');
+
+ EXECUTE format('GRANT ALL ON SCHEMA anon to %I', privileged_role_name);
+ EXECUTE format('GRANT ALL ON ALL TABLES IN SCHEMA anon TO %I', privileged_role_name);
+
+ IF current_setting('server_version_num')::int >= 150000 THEN
+ EXECUTE format('GRANT SET ON PARAMETER anon.transparent_dynamic_masking TO %I', privileged_role_name);
+ END IF;
+END $$;
+GRANT ALL ON SCHEMA anon to neon_superuser;
+GRANT ALL ON ALL TABLES IN SCHEMA anon TO neon_superuser;
diff --git a/sql/init.sql b/sql/init.sql
index 7da6553..9b6164b 100644
--- a/sql/init.sql

View File

@@ -1,15 +0,0 @@
diff --git a/cmake/deps.txt b/cmake/deps.txt
index d213b09034..229de2ebf0 100644
--- a/cmake/deps.txt
+++ b/cmake/deps.txt
@@ -22,7 +22,9 @@ dlpack;https://github.com/dmlc/dlpack/archive/refs/tags/v0.6.zip;4d565dd2e5b3132
# it contains changes on top of 3.4.0 which are required to fix build issues.
# Until the 3.4.1 release this is the best option we have.
# Issue link: https://gitlab.com/libeigen/eigen/-/issues/2744
-eigen;https://gitlab.com/libeigen/eigen/-/archive/e7248b26a1ed53fa030c5c459f7ea095dfd276ac/eigen-e7248b26a1ed53fa030c5c459f7ea095dfd276ac.zip;be8be39fdbc6e60e94fa7870b280707069b5b81a
+# Moved to github mirror to avoid gitlab issues.Add commentMore actions
+# Issue link: https://github.com/bazelbuild/bazel-central-registry/issues/4355
+eigen;https://github.com/eigen-mirror/eigen/archive/e7248b26a1ed53fa030c5c459f7ea095dfd276ac/eigen-e7248b26a1ed53fa030c5c459f7ea095dfd276ac.zip;61418a349000ba7744a3ad03cf5071f22ebf860a
flatbuffers;https://github.com/google/flatbuffers/archive/refs/tags/v23.5.26.zip;59422c3b5e573dd192fead2834d25951f1c1670c
fp16;https://github.com/Maratyszcza/FP16/archive/0a92994d729ff76a58f692d3028ca1b64b145d91.zip;b985f6985a05a1c03ff1bb71190f66d8f98a1494
fxdiv;https://github.com/Maratyszcza/FXdiv/archive/63058eff77e11aa15bf531df5dd34395ec3017c8.zip;a5658f4036402dbca7cebee32be57fb8149811e1

View File

@@ -21,21 +21,13 @@ index 3235cc8..6b892bc 100644
include Makefile.global
diff --git a/sql/pg_duckdb--0.2.0--0.3.0.sql b/sql/pg_duckdb--0.2.0--0.3.0.sql
index d777d76..3b54396 100644
index d777d76..af60106 100644
--- a/sql/pg_duckdb--0.2.0--0.3.0.sql
+++ b/sql/pg_duckdb--0.2.0--0.3.0.sql
@@ -1056,3 +1056,14 @@ GRANT ALL ON FUNCTION duckdb.cache(TEXT, TEXT) TO PUBLIC;
@@ -1056,3 +1056,6 @@ GRANT ALL ON FUNCTION duckdb.cache(TEXT, TEXT) TO PUBLIC;
GRANT ALL ON FUNCTION duckdb.cache_info() TO PUBLIC;
GRANT ALL ON FUNCTION duckdb.cache_delete(TEXT) TO PUBLIC;
GRANT ALL ON PROCEDURE duckdb.recycle_ddb() TO PUBLIC;
+
+DO $$
+DECLARE
+ privileged_role_name text;
+BEGIN
+ privileged_role_name := current_setting('neon.privileged_role_name');
+
+ EXECUTE format('GRANT ALL ON FUNCTION duckdb.install_extension(TEXT) TO %I', privileged_role_name);
+ EXECUTE format('GRANT ALL ON TABLE duckdb.extensions TO %I', privileged_role_name);
+ EXECUTE format('GRANT ALL ON SEQUENCE duckdb.extensions_table_seq TO %I', privileged_role_name);
+END $$;
+GRANT ALL ON FUNCTION duckdb.install_extension(TEXT) TO neon_superuser;
+GRANT ALL ON TABLE duckdb.extensions TO neon_superuser;
+GRANT ALL ON SEQUENCE duckdb.extensions_table_seq TO neon_superuser;

View File

@@ -1,34 +0,0 @@
diff --git a/contrib/pg_stat_statements/pg_stat_statements--1.4.sql b/contrib/pg_stat_statements/pg_stat_statements--1.4.sql
index 58cdf600fce..8be57a996f6 100644
--- a/contrib/pg_stat_statements/pg_stat_statements--1.4.sql
+++ b/contrib/pg_stat_statements/pg_stat_statements--1.4.sql
@@ -46,3 +46,12 @@ GRANT SELECT ON pg_stat_statements TO PUBLIC;
-- Don't want this to be available to non-superusers.
REVOKE ALL ON FUNCTION pg_stat_statements_reset() FROM PUBLIC;
+
+DO $$
+DECLARE
+ privileged_role_name text;
+BEGIN
+ privileged_role_name := current_setting('neon.privileged_role_name');
+
+ EXECUTE format('GRANT EXECUTE ON FUNCTION pg_stat_statements_reset() TO %I', privileged_role_name);
+END $$;
diff --git a/contrib/pg_stat_statements/pg_stat_statements--1.6--1.7.sql b/contrib/pg_stat_statements/pg_stat_statements--1.6--1.7.sql
index 6fc3fed4c93..256345a8f79 100644
--- a/contrib/pg_stat_statements/pg_stat_statements--1.6--1.7.sql
+++ b/contrib/pg_stat_statements/pg_stat_statements--1.6--1.7.sql
@@ -20,3 +20,12 @@ LANGUAGE C STRICT PARALLEL SAFE;
-- Don't want this to be available to non-superusers.
REVOKE ALL ON FUNCTION pg_stat_statements_reset(Oid, Oid, bigint) FROM PUBLIC;
+
+DO $$
+DECLARE
+ privileged_role_name text;
+BEGIN
+ privileged_role_name := current_setting('neon.privileged_role_name');
+
+ EXECUTE format('GRANT EXECUTE ON FUNCTION pg_stat_statements_reset(Oid, Oid, bigint) TO %I', privileged_role_name);
+END $$;

View File

@@ -1,52 +0,0 @@
diff --git a/contrib/pg_stat_statements/pg_stat_statements--1.10--1.11.sql b/contrib/pg_stat_statements/pg_stat_statements--1.10--1.11.sql
index 0bb2c397711..32764db1d8b 100644
--- a/contrib/pg_stat_statements/pg_stat_statements--1.10--1.11.sql
+++ b/contrib/pg_stat_statements/pg_stat_statements--1.10--1.11.sql
@@ -80,3 +80,12 @@ LANGUAGE C STRICT PARALLEL SAFE;
-- Don't want this to be available to non-superusers.
REVOKE ALL ON FUNCTION pg_stat_statements_reset(Oid, Oid, bigint, boolean) FROM PUBLIC;
+
+DO $$
+DECLARE
+ privileged_role_name text;
+BEGIN
+ privileged_role_name := current_setting('neon.privileged_role_name');
+
+ EXECUTE format('GRANT EXECUTE ON FUNCTION pg_stat_statements_reset(Oid, Oid, bigint, boolean) TO %I', privileged_role_name);
+END $$;
\ No newline at end of file
diff --git a/contrib/pg_stat_statements/pg_stat_statements--1.4.sql b/contrib/pg_stat_statements/pg_stat_statements--1.4.sql
index 58cdf600fce..8be57a996f6 100644
--- a/contrib/pg_stat_statements/pg_stat_statements--1.4.sql
+++ b/contrib/pg_stat_statements/pg_stat_statements--1.4.sql
@@ -46,3 +46,12 @@ GRANT SELECT ON pg_stat_statements TO PUBLIC;
-- Don't want this to be available to non-superusers.
REVOKE ALL ON FUNCTION pg_stat_statements_reset() FROM PUBLIC;
+
+DO $$
+DECLARE
+ privileged_role_name text;
+BEGIN
+ privileged_role_name := current_setting('neon.privileged_role_name');
+
+ EXECUTE format('GRANT EXECUTE ON FUNCTION pg_stat_statements_reset() TO %I', privileged_role_name);
+END $$;
diff --git a/contrib/pg_stat_statements/pg_stat_statements--1.6--1.7.sql b/contrib/pg_stat_statements/pg_stat_statements--1.6--1.7.sql
index 6fc3fed4c93..256345a8f79 100644
--- a/contrib/pg_stat_statements/pg_stat_statements--1.6--1.7.sql
+++ b/contrib/pg_stat_statements/pg_stat_statements--1.6--1.7.sql
@@ -20,3 +20,12 @@ LANGUAGE C STRICT PARALLEL SAFE;
-- Don't want this to be available to non-superusers.
REVOKE ALL ON FUNCTION pg_stat_statements_reset(Oid, Oid, bigint) FROM PUBLIC;
+
+DO $$
+DECLARE
+ privileged_role_name text;
+BEGIN
+ privileged_role_name := current_setting('neon.privileged_role_name');
+
+ EXECUTE format('GRANT EXECUTE ON FUNCTION pg_stat_statements_reset(Oid, Oid, bigint) TO %I', privileged_role_name);
+END $$;

View File

@@ -1,143 +0,0 @@
commit 7220bb3a3f23fa27207d77562dcc286f9a123313
Author: Tristan Partin <tristan.partin@databricks.com>
Date: 2025-06-23 02:09:31 +0000
Disable logging in parallel workers
When a query uses parallel workers, pgaudit will log the same query for
every parallel worker. This is undesireable since it can result in log
amplification for queries that use parallel workers.
Signed-off-by: Tristan Partin <tristan.partin@databricks.com>
diff --git a/expected/pgaudit.out b/expected/pgaudit.out
index baa8011..a601375 100644
--- a/expected/pgaudit.out
+++ b/expected/pgaudit.out
@@ -2563,6 +2563,37 @@ COMMIT;
NOTICE: AUDIT: SESSION,12,4,MISC,COMMIT,,,COMMIT;,<not logged>
DROP TABLE part_test;
NOTICE: AUDIT: SESSION,13,1,DDL,DROP TABLE,,,DROP TABLE part_test;,<not logged>
+--
+-- Test logging in parallel workers
+SET pgaudit.log = 'read';
+SET pgaudit.log_client = on;
+SET pgaudit.log_level = 'notice';
+-- Force parallel execution for testing
+SET max_parallel_workers_per_gather = 2;
+SET parallel_tuple_cost = 0;
+SET parallel_setup_cost = 0;
+SET min_parallel_table_scan_size = 0;
+SET min_parallel_index_scan_size = 0;
+-- Create table with enough data to trigger parallel execution
+CREATE TABLE parallel_test (id int, data text);
+INSERT INTO parallel_test SELECT generate_series(1, 1000), 'test data';
+SELECT count(*) FROM parallel_test;
+NOTICE: AUDIT: SESSION,14,1,READ,SELECT,,,SELECT count(*) FROM parallel_test;,<not logged>
+ count
+-------
+ 1000
+(1 row)
+
+-- Cleanup parallel test
+DROP TABLE parallel_test;
+RESET max_parallel_workers_per_gather;
+RESET parallel_tuple_cost;
+RESET parallel_setup_cost;
+RESET min_parallel_table_scan_size;
+RESET min_parallel_index_scan_size;
+RESET pgaudit.log;
+RESET pgaudit.log_client;
+RESET pgaudit.log_level;
-- Cleanup
-- Set client_min_messages up to warning to avoid noise
SET client_min_messages = 'warning';
diff --git a/pgaudit.c b/pgaudit.c
index 5e6fd38..ac9ded2 100644
--- a/pgaudit.c
+++ b/pgaudit.c
@@ -11,6 +11,7 @@
#include "postgres.h"
#include "access/htup_details.h"
+#include "access/parallel.h"
#include "access/sysattr.h"
#include "access/xact.h"
#include "access/relation.h"
@@ -1303,7 +1304,7 @@ pgaudit_ExecutorStart_hook(QueryDesc *queryDesc, int eflags)
{
AuditEventStackItem *stackItem = NULL;
- if (!internalStatement)
+ if (!internalStatement && !IsParallelWorker())
{
/* Push the audit even onto the stack */
stackItem = stack_push();
@@ -1384,7 +1385,7 @@ pgaudit_ExecutorCheckPerms_hook(List *rangeTabls, bool abort)
/* Log DML if the audit role is valid or session logging is enabled */
if ((auditOid != InvalidOid || auditLogBitmap != 0) &&
- !IsAbortedTransactionBlockState())
+ !IsAbortedTransactionBlockState() && !IsParallelWorker())
{
/* If auditLogRows is on, wait for rows processed to be set */
if (auditLogRows && auditEventStack != NULL)
@@ -1438,7 +1439,7 @@ pgaudit_ExecutorRun_hook(QueryDesc *queryDesc, ScanDirection direction, uint64 c
else
standard_ExecutorRun(queryDesc, direction, count, execute_once);
- if (auditLogRows && !internalStatement)
+ if (auditLogRows && !internalStatement && !IsParallelWorker())
{
/* Find an item from the stack by the query memory context */
stackItem = stack_find_context(queryDesc->estate->es_query_cxt);
@@ -1458,7 +1459,7 @@ pgaudit_ExecutorEnd_hook(QueryDesc *queryDesc)
AuditEventStackItem *stackItem = NULL;
AuditEventStackItem *auditEventStackFull = NULL;
- if (auditLogRows && !internalStatement)
+ if (auditLogRows && !internalStatement && !IsParallelWorker())
{
/* Find an item from the stack by the query memory context */
stackItem = stack_find_context(queryDesc->estate->es_query_cxt);
diff --git a/sql/pgaudit.sql b/sql/pgaudit.sql
index cc1374a..1870a60 100644
--- a/sql/pgaudit.sql
+++ b/sql/pgaudit.sql
@@ -1612,6 +1612,36 @@ COMMIT;
DROP TABLE part_test;
+--
+-- Test logging in parallel workers
+SET pgaudit.log = 'read';
+SET pgaudit.log_client = on;
+SET pgaudit.log_level = 'notice';
+
+-- Force parallel execution for testing
+SET max_parallel_workers_per_gather = 2;
+SET parallel_tuple_cost = 0;
+SET parallel_setup_cost = 0;
+SET min_parallel_table_scan_size = 0;
+SET min_parallel_index_scan_size = 0;
+
+-- Create table with enough data to trigger parallel execution
+CREATE TABLE parallel_test (id int, data text);
+INSERT INTO parallel_test SELECT generate_series(1, 1000), 'test data';
+
+SELECT count(*) FROM parallel_test;
+
+-- Cleanup parallel test
+DROP TABLE parallel_test;
+RESET max_parallel_workers_per_gather;
+RESET parallel_tuple_cost;
+RESET parallel_setup_cost;
+RESET min_parallel_table_scan_size;
+RESET min_parallel_index_scan_size;
+RESET pgaudit.log;
+RESET pgaudit.log_client;
+RESET pgaudit.log_level;
+
-- Cleanup
-- Set client_min_messages up to warning to avoid noise
SET client_min_messages = 'warning';

View File

@@ -1,143 +0,0 @@
commit 29dc2847f6255541992f18faf8a815dfab79631a
Author: Tristan Partin <tristan.partin@databricks.com>
Date: 2025-06-23 02:09:31 +0000
Disable logging in parallel workers
When a query uses parallel workers, pgaudit will log the same query for
every parallel worker. This is undesireable since it can result in log
amplification for queries that use parallel workers.
Signed-off-by: Tristan Partin <tristan.partin@databricks.com>
diff --git a/expected/pgaudit.out b/expected/pgaudit.out
index b22560b..73f0327 100644
--- a/expected/pgaudit.out
+++ b/expected/pgaudit.out
@@ -2563,6 +2563,37 @@ COMMIT;
NOTICE: AUDIT: SESSION,12,4,MISC,COMMIT,,,COMMIT;,<not logged>
DROP TABLE part_test;
NOTICE: AUDIT: SESSION,13,1,DDL,DROP TABLE,,,DROP TABLE part_test;,<not logged>
+--
+-- Test logging in parallel workers
+SET pgaudit.log = 'read';
+SET pgaudit.log_client = on;
+SET pgaudit.log_level = 'notice';
+-- Force parallel execution for testing
+SET max_parallel_workers_per_gather = 2;
+SET parallel_tuple_cost = 0;
+SET parallel_setup_cost = 0;
+SET min_parallel_table_scan_size = 0;
+SET min_parallel_index_scan_size = 0;
+-- Create table with enough data to trigger parallel execution
+CREATE TABLE parallel_test (id int, data text);
+INSERT INTO parallel_test SELECT generate_series(1, 1000), 'test data';
+SELECT count(*) FROM parallel_test;
+NOTICE: AUDIT: SESSION,14,1,READ,SELECT,,,SELECT count(*) FROM parallel_test;,<not logged>
+ count
+-------
+ 1000
+(1 row)
+
+-- Cleanup parallel test
+DROP TABLE parallel_test;
+RESET max_parallel_workers_per_gather;
+RESET parallel_tuple_cost;
+RESET parallel_setup_cost;
+RESET min_parallel_table_scan_size;
+RESET min_parallel_index_scan_size;
+RESET pgaudit.log;
+RESET pgaudit.log_client;
+RESET pgaudit.log_level;
-- Cleanup
-- Set client_min_messages up to warning to avoid noise
SET client_min_messages = 'warning';
diff --git a/pgaudit.c b/pgaudit.c
index 5e6fd38..ac9ded2 100644
--- a/pgaudit.c
+++ b/pgaudit.c
@@ -11,6 +11,7 @@
#include "postgres.h"
#include "access/htup_details.h"
+#include "access/parallel.h"
#include "access/sysattr.h"
#include "access/xact.h"
#include "access/relation.h"
@@ -1303,7 +1304,7 @@ pgaudit_ExecutorStart_hook(QueryDesc *queryDesc, int eflags)
{
AuditEventStackItem *stackItem = NULL;
- if (!internalStatement)
+ if (!internalStatement && !IsParallelWorker())
{
/* Push the audit even onto the stack */
stackItem = stack_push();
@@ -1384,7 +1385,7 @@ pgaudit_ExecutorCheckPerms_hook(List *rangeTabls, bool abort)
/* Log DML if the audit role is valid or session logging is enabled */
if ((auditOid != InvalidOid || auditLogBitmap != 0) &&
- !IsAbortedTransactionBlockState())
+ !IsAbortedTransactionBlockState() && !IsParallelWorker())
{
/* If auditLogRows is on, wait for rows processed to be set */
if (auditLogRows && auditEventStack != NULL)
@@ -1438,7 +1439,7 @@ pgaudit_ExecutorRun_hook(QueryDesc *queryDesc, ScanDirection direction, uint64 c
else
standard_ExecutorRun(queryDesc, direction, count, execute_once);
- if (auditLogRows && !internalStatement)
+ if (auditLogRows && !internalStatement && !IsParallelWorker())
{
/* Find an item from the stack by the query memory context */
stackItem = stack_find_context(queryDesc->estate->es_query_cxt);
@@ -1458,7 +1459,7 @@ pgaudit_ExecutorEnd_hook(QueryDesc *queryDesc)
AuditEventStackItem *stackItem = NULL;
AuditEventStackItem *auditEventStackFull = NULL;
- if (auditLogRows && !internalStatement)
+ if (auditLogRows && !internalStatement && !IsParallelWorker())
{
/* Find an item from the stack by the query memory context */
stackItem = stack_find_context(queryDesc->estate->es_query_cxt);
diff --git a/sql/pgaudit.sql b/sql/pgaudit.sql
index 8052426..7f0667b 100644
--- a/sql/pgaudit.sql
+++ b/sql/pgaudit.sql
@@ -1612,6 +1612,36 @@ COMMIT;
DROP TABLE part_test;
+--
+-- Test logging in parallel workers
+SET pgaudit.log = 'read';
+SET pgaudit.log_client = on;
+SET pgaudit.log_level = 'notice';
+
+-- Force parallel execution for testing
+SET max_parallel_workers_per_gather = 2;
+SET parallel_tuple_cost = 0;
+SET parallel_setup_cost = 0;
+SET min_parallel_table_scan_size = 0;
+SET min_parallel_index_scan_size = 0;
+
+-- Create table with enough data to trigger parallel execution
+CREATE TABLE parallel_test (id int, data text);
+INSERT INTO parallel_test SELECT generate_series(1, 1000), 'test data';
+
+SELECT count(*) FROM parallel_test;
+
+-- Cleanup parallel test
+DROP TABLE parallel_test;
+RESET max_parallel_workers_per_gather;
+RESET parallel_tuple_cost;
+RESET parallel_setup_cost;
+RESET min_parallel_table_scan_size;
+RESET min_parallel_index_scan_size;
+RESET pgaudit.log;
+RESET pgaudit.log_client;
+RESET pgaudit.log_level;
+
-- Cleanup
-- Set client_min_messages up to warning to avoid noise
SET client_min_messages = 'warning';

View File

@@ -1,143 +0,0 @@
commit cc708dde7ef2af2a8120d757102d2e34c0463a0f
Author: Tristan Partin <tristan.partin@databricks.com>
Date: 2025-06-23 02:09:31 +0000
Disable logging in parallel workers
When a query uses parallel workers, pgaudit will log the same query for
every parallel worker. This is undesireable since it can result in log
amplification for queries that use parallel workers.
Signed-off-by: Tristan Partin <tristan.partin@databricks.com>
diff --git a/expected/pgaudit.out b/expected/pgaudit.out
index 8772054..9b66ac6 100644
--- a/expected/pgaudit.out
+++ b/expected/pgaudit.out
@@ -2556,6 +2556,37 @@ DROP SERVER fdw_server;
NOTICE: AUDIT: SESSION,11,1,DDL,DROP SERVER,,,DROP SERVER fdw_server;,<not logged>
DROP EXTENSION postgres_fdw;
NOTICE: AUDIT: SESSION,12,1,DDL,DROP EXTENSION,,,DROP EXTENSION postgres_fdw;,<not logged>
+--
+-- Test logging in parallel workers
+SET pgaudit.log = 'read';
+SET pgaudit.log_client = on;
+SET pgaudit.log_level = 'notice';
+-- Force parallel execution for testing
+SET max_parallel_workers_per_gather = 2;
+SET parallel_tuple_cost = 0;
+SET parallel_setup_cost = 0;
+SET min_parallel_table_scan_size = 0;
+SET min_parallel_index_scan_size = 0;
+-- Create table with enough data to trigger parallel execution
+CREATE TABLE parallel_test (id int, data text);
+INSERT INTO parallel_test SELECT generate_series(1, 1000), 'test data';
+SELECT count(*) FROM parallel_test;
+NOTICE: AUDIT: SESSION,13,1,READ,SELECT,,,SELECT count(*) FROM parallel_test;,<not logged>
+ count
+-------
+ 1000
+(1 row)
+
+-- Cleanup parallel test
+DROP TABLE parallel_test;
+RESET max_parallel_workers_per_gather;
+RESET parallel_tuple_cost;
+RESET parallel_setup_cost;
+RESET min_parallel_table_scan_size;
+RESET min_parallel_index_scan_size;
+RESET pgaudit.log;
+RESET pgaudit.log_client;
+RESET pgaudit.log_level;
-- Cleanup
-- Set client_min_messages up to warning to avoid noise
SET client_min_messages = 'warning';
diff --git a/pgaudit.c b/pgaudit.c
index 004d1f9..f061164 100644
--- a/pgaudit.c
+++ b/pgaudit.c
@@ -11,6 +11,7 @@
#include "postgres.h"
#include "access/htup_details.h"
+#include "access/parallel.h"
#include "access/sysattr.h"
#include "access/xact.h"
#include "access/relation.h"
@@ -1339,7 +1340,7 @@ pgaudit_ExecutorStart_hook(QueryDesc *queryDesc, int eflags)
{
AuditEventStackItem *stackItem = NULL;
- if (!internalStatement)
+ if (!internalStatement && !IsParallelWorker())
{
/* Push the audit even onto the stack */
stackItem = stack_push();
@@ -1420,7 +1421,7 @@ pgaudit_ExecutorCheckPerms_hook(List *rangeTabls, List *permInfos, bool abort)
/* Log DML if the audit role is valid or session logging is enabled */
if ((auditOid != InvalidOid || auditLogBitmap != 0) &&
- !IsAbortedTransactionBlockState())
+ !IsAbortedTransactionBlockState() && !IsParallelWorker())
{
/* If auditLogRows is on, wait for rows processed to be set */
if (auditLogRows && auditEventStack != NULL)
@@ -1475,7 +1476,7 @@ pgaudit_ExecutorRun_hook(QueryDesc *queryDesc, ScanDirection direction, uint64 c
else
standard_ExecutorRun(queryDesc, direction, count, execute_once);
- if (auditLogRows && !internalStatement)
+ if (auditLogRows && !internalStatement && !IsParallelWorker())
{
/* Find an item from the stack by the query memory context */
stackItem = stack_find_context(queryDesc->estate->es_query_cxt);
@@ -1495,7 +1496,7 @@ pgaudit_ExecutorEnd_hook(QueryDesc *queryDesc)
AuditEventStackItem *stackItem = NULL;
AuditEventStackItem *auditEventStackFull = NULL;
- if (auditLogRows && !internalStatement)
+ if (auditLogRows && !internalStatement && !IsParallelWorker())
{
/* Find an item from the stack by the query memory context */
stackItem = stack_find_context(queryDesc->estate->es_query_cxt);
diff --git a/sql/pgaudit.sql b/sql/pgaudit.sql
index 6aae88b..de6d7fd 100644
--- a/sql/pgaudit.sql
+++ b/sql/pgaudit.sql
@@ -1631,6 +1631,36 @@ DROP USER MAPPING FOR regress_user1 SERVER fdw_server;
DROP SERVER fdw_server;
DROP EXTENSION postgres_fdw;
+--
+-- Test logging in parallel workers
+SET pgaudit.log = 'read';
+SET pgaudit.log_client = on;
+SET pgaudit.log_level = 'notice';
+
+-- Force parallel execution for testing
+SET max_parallel_workers_per_gather = 2;
+SET parallel_tuple_cost = 0;
+SET parallel_setup_cost = 0;
+SET min_parallel_table_scan_size = 0;
+SET min_parallel_index_scan_size = 0;
+
+-- Create table with enough data to trigger parallel execution
+CREATE TABLE parallel_test (id int, data text);
+INSERT INTO parallel_test SELECT generate_series(1, 1000), 'test data';
+
+SELECT count(*) FROM parallel_test;
+
+-- Cleanup parallel test
+DROP TABLE parallel_test;
+RESET max_parallel_workers_per_gather;
+RESET parallel_tuple_cost;
+RESET parallel_setup_cost;
+RESET min_parallel_table_scan_size;
+RESET min_parallel_index_scan_size;
+RESET pgaudit.log;
+RESET pgaudit.log_client;
+RESET pgaudit.log_level;
+
-- Cleanup
-- Set client_min_messages up to warning to avoid noise
SET client_min_messages = 'warning';

View File

@@ -1,143 +0,0 @@
commit 8d02e4c6c5e1e8676251b0717a46054267091cb4
Author: Tristan Partin <tristan.partin@databricks.com>
Date: 2025-06-23 02:09:31 +0000
Disable logging in parallel workers
When a query uses parallel workers, pgaudit will log the same query for
every parallel worker. This is undesireable since it can result in log
amplification for queries that use parallel workers.
Signed-off-by: Tristan Partin <tristan.partin@databricks.com>
diff --git a/expected/pgaudit.out b/expected/pgaudit.out
index d696287..4b1059a 100644
--- a/expected/pgaudit.out
+++ b/expected/pgaudit.out
@@ -2568,6 +2568,37 @@ DROP SERVER fdw_server;
NOTICE: AUDIT: SESSION,11,1,DDL,DROP SERVER,,,DROP SERVER fdw_server,<not logged>
DROP EXTENSION postgres_fdw;
NOTICE: AUDIT: SESSION,12,1,DDL,DROP EXTENSION,,,DROP EXTENSION postgres_fdw,<not logged>
+--
+-- Test logging in parallel workers
+SET pgaudit.log = 'read';
+SET pgaudit.log_client = on;
+SET pgaudit.log_level = 'notice';
+-- Force parallel execution for testing
+SET max_parallel_workers_per_gather = 2;
+SET parallel_tuple_cost = 0;
+SET parallel_setup_cost = 0;
+SET min_parallel_table_scan_size = 0;
+SET min_parallel_index_scan_size = 0;
+-- Create table with enough data to trigger parallel execution
+CREATE TABLE parallel_test (id int, data text);
+INSERT INTO parallel_test SELECT generate_series(1, 1000), 'test data';
+SELECT count(*) FROM parallel_test;
+NOTICE: AUDIT: SESSION,13,1,READ,SELECT,,,SELECT count(*) FROM parallel_test,<not logged>
+ count
+-------
+ 1000
+(1 row)
+
+-- Cleanup parallel test
+DROP TABLE parallel_test;
+RESET max_parallel_workers_per_gather;
+RESET parallel_tuple_cost;
+RESET parallel_setup_cost;
+RESET min_parallel_table_scan_size;
+RESET min_parallel_index_scan_size;
+RESET pgaudit.log;
+RESET pgaudit.log_client;
+RESET pgaudit.log_level;
-- Cleanup
-- Set client_min_messages up to warning to avoid noise
SET client_min_messages = 'warning';
diff --git a/pgaudit.c b/pgaudit.c
index 1764af1..0e48875 100644
--- a/pgaudit.c
+++ b/pgaudit.c
@@ -11,6 +11,7 @@
#include "postgres.h"
#include "access/htup_details.h"
+#include "access/parallel.h"
#include "access/sysattr.h"
#include "access/xact.h"
#include "access/relation.h"
@@ -1406,7 +1407,7 @@ pgaudit_ExecutorStart_hook(QueryDesc *queryDesc, int eflags)
{
AuditEventStackItem *stackItem = NULL;
- if (!internalStatement)
+ if (!internalStatement && !IsParallelWorker())
{
/* Push the audit event onto the stack */
stackItem = stack_push();
@@ -1489,7 +1490,7 @@ pgaudit_ExecutorCheckPerms_hook(List *rangeTabls, List *permInfos, bool abort)
/* Log DML if the audit role is valid or session logging is enabled */
if ((auditOid != InvalidOid || auditLogBitmap != 0) &&
- !IsAbortedTransactionBlockState())
+ !IsAbortedTransactionBlockState() && !IsParallelWorker())
{
/* If auditLogRows is on, wait for rows processed to be set */
if (auditLogRows && auditEventStack != NULL)
@@ -1544,7 +1545,7 @@ pgaudit_ExecutorRun_hook(QueryDesc *queryDesc, ScanDirection direction, uint64 c
else
standard_ExecutorRun(queryDesc, direction, count, execute_once);
- if (auditLogRows && !internalStatement)
+ if (auditLogRows && !internalStatement && !IsParallelWorker())
{
/* Find an item from the stack by the query memory context */
stackItem = stack_find_context(queryDesc->estate->es_query_cxt);
@@ -1564,7 +1565,7 @@ pgaudit_ExecutorEnd_hook(QueryDesc *queryDesc)
AuditEventStackItem *stackItem = NULL;
AuditEventStackItem *auditEventStackFull = NULL;
- if (auditLogRows && !internalStatement)
+ if (auditLogRows && !internalStatement && !IsParallelWorker())
{
/* Find an item from the stack by the query memory context */
stackItem = stack_find_context(queryDesc->estate->es_query_cxt);
diff --git a/sql/pgaudit.sql b/sql/pgaudit.sql
index e161f01..c873098 100644
--- a/sql/pgaudit.sql
+++ b/sql/pgaudit.sql
@@ -1637,6 +1637,36 @@ DROP USER MAPPING FOR regress_user1 SERVER fdw_server;
DROP SERVER fdw_server;
DROP EXTENSION postgres_fdw;
+--
+-- Test logging in parallel workers
+SET pgaudit.log = 'read';
+SET pgaudit.log_client = on;
+SET pgaudit.log_level = 'notice';
+
+-- Force parallel execution for testing
+SET max_parallel_workers_per_gather = 2;
+SET parallel_tuple_cost = 0;
+SET parallel_setup_cost = 0;
+SET min_parallel_table_scan_size = 0;
+SET min_parallel_index_scan_size = 0;
+
+-- Create table with enough data to trigger parallel execution
+CREATE TABLE parallel_test (id int, data text);
+INSERT INTO parallel_test SELECT generate_series(1, 1000), 'test data';
+
+SELECT count(*) FROM parallel_test;
+
+-- Cleanup parallel test
+DROP TABLE parallel_test;
+RESET max_parallel_workers_per_gather;
+RESET parallel_tuple_cost;
+RESET parallel_setup_cost;
+RESET min_parallel_table_scan_size;
+RESET min_parallel_index_scan_size;
+RESET pgaudit.log;
+RESET pgaudit.log_client;
+RESET pgaudit.log_level;
+
-- Cleanup
-- Set client_min_messages up to warning to avoid noise
SET client_min_messages = 'warning';

View File

@@ -1,17 +0,0 @@
diff --git a/contrib/postgres_fdw/postgres_fdw--1.0.sql b/contrib/postgres_fdw/postgres_fdw--1.0.sql
index a0f0fc1bf45..ee077f2eea6 100644
--- a/contrib/postgres_fdw/postgres_fdw--1.0.sql
+++ b/contrib/postgres_fdw/postgres_fdw--1.0.sql
@@ -16,3 +16,12 @@ LANGUAGE C STRICT;
CREATE FOREIGN DATA WRAPPER postgres_fdw
HANDLER postgres_fdw_handler
VALIDATOR postgres_fdw_validator;
+
+DO $$
+DECLARE
+ privileged_role_name text;
+BEGIN
+ privileged_role_name := current_setting('neon.privileged_role_name');
+
+ EXECUTE format('GRANT USAGE ON FOREIGN DATA WRAPPER postgres_fdw TO %I', privileged_role_name);
+END $$;

View File

@@ -26,7 +26,7 @@ commands:
- name: postgres-exporter
user: nobody
sysvInitAction: respawn
shell: 'DATA_SOURCE_NAME="user=cloud_admin sslmode=disable dbname=postgres application_name=postgres-exporter pgaudit.log=none" /bin/postgres_exporter --config.file=/etc/postgres_exporter.yml'
shell: 'DATA_SOURCE_NAME="user=cloud_admin sslmode=disable dbname=postgres application_name=postgres-exporter" /bin/postgres_exporter --config.file=/etc/postgres_exporter.yml'
- name: pgbouncer-exporter
user: postgres
sysvInitAction: respawn
@@ -59,7 +59,7 @@ files:
# the rules use ALL as the hostname. Avoid the pointless lookups and the "unable to
# resolve host" log messages that they generate.
Defaults !fqdn
# 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)

View File

@@ -26,7 +26,7 @@ commands:
- name: postgres-exporter
user: nobody
sysvInitAction: respawn
shell: 'DATA_SOURCE_NAME="user=cloud_admin sslmode=disable dbname=postgres application_name=postgres-exporter pgaudit.log=none" /bin/postgres_exporter --config.file=/etc/postgres_exporter.yml'
shell: 'DATA_SOURCE_NAME="user=cloud_admin sslmode=disable dbname=postgres application_name=postgres-exporter" /bin/postgres_exporter --config.file=/etc/postgres_exporter.yml'
- name: pgbouncer-exporter
user: postgres
sysvInitAction: respawn
@@ -59,7 +59,7 @@ files:
# the rules use ALL as the hostname. Avoid the pointless lookups and the "unable to
# resolve host" log messages that they generate.
Defaults !fqdn
# 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)

View File

@@ -27,7 +27,6 @@ fail.workspace = true
flate2.workspace = true
futures.workspace = true
http.workspace = true
hostname-validator = "1.1"
indexmap.workspace = true
itertools.workspace = true
jsonwebtoken.workspace = true
@@ -39,7 +38,6 @@ once_cell.workspace = true
opentelemetry.workspace = true
opentelemetry_sdk.workspace = true
p256 = { version = "0.13", features = ["pem"] }
pageserver_page_api.workspace = true
postgres.workspace = true
regex.workspace = true
reqwest = { workspace = true, features = ["json"] }
@@ -55,7 +53,6 @@ tokio = { workspace = true, features = ["rt", "rt-multi-thread"] }
tokio-postgres.workspace = true
tokio-util.workspace = true
tokio-stream.workspace = true
tonic.workspace = true
tower-otel.workspace = true
tracing.workspace = true
tracing-opentelemetry.workspace = true
@@ -66,8 +63,7 @@ url.workspace = true
uuid.workspace = true
walkdir.workspace = true
x509-cert.workspace = true
postgres-types.workspace = true
postgres_versioninfo.workspace = true
postgres_initdb.workspace = true
compute_api.workspace = true
utils.workspace = true

View File

@@ -46,14 +46,11 @@ stateDiagram-v2
Configuration --> Failed : Failed to configure the compute
Configuration --> Running : Compute has been configured
Empty --> Init : Compute spec is immediately available
Empty --> TerminationPendingFast : Requested termination
Empty --> TerminationPendingImmediate : Requested termination
Empty --> TerminationPending : Requested termination
Init --> Failed : Failed to start Postgres
Init --> Running : Started Postgres
Running --> TerminationPendingFast : Requested termination
Running --> TerminationPendingImmediate : Requested termination
TerminationPendingFast --> Terminated compute with 30s delay for cplane to inspect status
TerminationPendingImmediate --> Terminated : Terminated compute immediately
Running --> TerminationPending : Requested termination
TerminationPending --> Terminated : Terminated compute
Failed --> [*] : Compute exited
Terminated --> [*] : Compute exited
```

View File

@@ -36,8 +36,6 @@
use std::ffi::OsString;
use std::fs::File;
use std::process::exit;
use std::sync::Arc;
use std::sync::atomic::AtomicU64;
use std::sync::mpsc;
use std::thread;
use std::time::Duration;
@@ -87,14 +85,6 @@ struct Cli {
#[arg(short = 'C', long, value_name = "DATABASE_URL")]
pub connstr: String,
#[arg(
long,
default_value = "neon_superuser",
value_name = "PRIVILEGED_ROLE_NAME",
value_parser = Self::parse_privileged_role_name
)]
pub privileged_role_name: String,
#[cfg(target_os = "linux")]
#[arg(long, default_value = "neon-postgres")]
pub cgroup: String,
@@ -134,10 +124,6 @@ struct Cli {
/// Interval in seconds for collecting installed extensions statistics
#[arg(long, default_value = "3600")]
pub installed_extensions_collection_interval: u64,
/// Run in development mode, skipping VM-specific operations like process termination
#[arg(long, action = clap::ArgAction::SetTrue)]
pub dev: bool,
}
impl Cli {
@@ -157,21 +143,6 @@ impl Cli {
Ok(url)
}
/// For simplicity, we do not escape `privileged_role_name` anywhere in the code.
/// Since it's a system role, which we fully control, that's fine. Still, let's
/// validate it to avoid any surprises.
fn parse_privileged_role_name(value: &str) -> Result<String> {
use regex::Regex;
let pattern = Regex::new(r"^[a-z_]+$").unwrap();
if !pattern.is_match(value) {
bail!("--privileged-role-name can only contain lowercase letters and underscores")
}
Ok(value.to_string())
}
}
fn main() -> Result<()> {
@@ -188,7 +159,7 @@ fn main() -> Result<()> {
.build()?;
let _rt_guard = runtime.enter();
runtime.block_on(init(cli.dev))?;
runtime.block_on(init())?;
// enable core dumping for all child processes
setrlimit(Resource::CORE, rlimit::INFINITY, rlimit::INFINITY)?;
@@ -201,7 +172,6 @@ fn main() -> Result<()> {
ComputeNodeParams {
compute_id: cli.compute_id,
connstr,
privileged_role_name: cli.privileged_role_name.clone(),
pgdata: cli.pgdata.clone(),
pgbin: cli.pgbin.clone(),
pgversion: get_pg_version_string(&cli.pgbin),
@@ -216,9 +186,7 @@ fn main() -> Result<()> {
cgroup: cli.cgroup,
#[cfg(target_os = "linux")]
vm_monitor_addr: cli.vm_monitor_addr,
installed_extensions_collection_interval: Arc::new(AtomicU64::new(
cli.installed_extensions_collection_interval,
)),
installed_extensions_collection_interval: cli.installed_extensions_collection_interval,
},
config,
)?;
@@ -230,13 +198,13 @@ fn main() -> Result<()> {
deinit_and_exit(exit_code);
}
async fn init(dev_mode: bool) -> Result<()> {
async fn init() -> Result<()> {
init_tracing_and_logging(DEFAULT_LOG_LEVEL).await?;
let mut signals = Signals::new([SIGINT, SIGTERM, SIGQUIT])?;
thread::spawn(move || {
for sig in signals.forever() {
handle_exit_signal(sig, dev_mode);
handle_exit_signal(sig);
}
});
@@ -295,9 +263,9 @@ fn deinit_and_exit(exit_code: Option<i32>) -> ! {
/// When compute_ctl is killed, send also termination signal to sync-safekeepers
/// to prevent leakage. TODO: it is better to convert compute_ctl to async and
/// wait for termination which would be easy then.
fn handle_exit_signal(sig: i32, dev_mode: bool) {
fn handle_exit_signal(sig: i32) {
info!("received {sig} termination signal");
forward_termination_signal(dev_mode);
forward_termination_signal();
exit(1);
}
@@ -351,49 +319,4 @@ mod test {
])
.expect_err("URL parameters are not allowed");
}
#[test]
fn verify_privileged_role_name() {
// Valid name
let cli = Cli::parse_from([
"compute_ctl",
"--pgdata=test",
"--connstr=test",
"--compute-id=test",
"--privileged-role-name",
"my_superuser",
]);
assert_eq!(cli.privileged_role_name, "my_superuser");
// Invalid names
Cli::try_parse_from([
"compute_ctl",
"--pgdata=test",
"--connstr=test",
"--compute-id=test",
"--privileged-role-name",
"NeonSuperuser",
])
.expect_err("uppercase letters are not allowed");
Cli::try_parse_from([
"compute_ctl",
"--pgdata=test",
"--connstr=test",
"--compute-id=test",
"--privileged-role-name",
"$'neon_superuser",
])
.expect_err("special characters are not allowed");
Cli::try_parse_from([
"compute_ctl",
"--pgdata=test",
"--connstr=test",
"--compute-id=test",
"--privileged-role-name",
"",
])
.expect_err("empty name is not allowed");
}
}

View File

@@ -29,7 +29,7 @@ use anyhow::{Context, bail};
use aws_config::BehaviorVersion;
use camino::{Utf8Path, Utf8PathBuf};
use clap::{Parser, Subcommand};
use compute_tools::extension_server::get_pg_version;
use compute_tools::extension_server::{PostgresMajorVersion, get_pg_version};
use nix::unistd::Pid;
use std::ops::Not;
use tracing::{Instrument, error, info, info_span, warn};
@@ -179,8 +179,12 @@ impl PostgresProcess {
.await
.context("create pgdata directory")?;
let pg_version = get_pg_version(self.pgbin.as_ref());
let pg_version = match get_pg_version(self.pgbin.as_ref()) {
PostgresMajorVersion::V14 => 14,
PostgresMajorVersion::V15 => 15,
PostgresMajorVersion::V16 => 16,
PostgresMajorVersion::V17 => 17,
};
postgres_initdb::do_run_initdb(postgres_initdb::RunInitdbArgs {
superuser: initdb_user,
locale: DEFAULT_LOCALE, // XXX: this shouldn't be hard-coded,
@@ -482,8 +486,10 @@ async fn cmd_pgdata(
};
let superuser = "cloud_admin";
let destination_connstring =
format!("host=localhost port={pg_port} user={superuser} dbname=neondb");
let destination_connstring = format!(
"host=localhost port={} user={} dbname=neondb",
pg_port, superuser
);
let pgdata_dir = workdir.join("pgdata");
let mut proc = PostgresProcess::new(pgdata_dir.clone(), pg_bin_dir.clone(), pg_lib_dir.clone());

View File

@@ -69,7 +69,7 @@ impl clap::builder::TypedValueParser for S3Uri {
S3Uri::from_str(value_str).map_err(|e| {
clap::Error::raw(
clap::error::ErrorKind::InvalidValue,
format!("Failed to parse S3 URI: {e}"),
format!("Failed to parse S3 URI: {}", e),
)
})
}

View File

@@ -22,7 +22,7 @@ pub async fn get_dbs_and_roles(compute: &Arc<ComputeNode>) -> anyhow::Result<Cat
spawn(async move {
if let Err(e) = connection.await {
eprintln!("connection error: {e}");
eprintln!("connection error: {}", e);
}
});
@@ -119,7 +119,7 @@ pub async fn get_database_schema(
_ => {
let mut lines = stderr_reader.lines();
if let Some(line) = lines.next_line().await? {
if line.contains(&format!("FATAL: database \"{dbname}\" does not exist")) {
if line.contains(&format!("FATAL: database \"{}\" does not exist", dbname)) {
return Err(SchemaDumpError::DatabaseDoesNotExist);
}
warn!("pg_dump stderr: {}", line)

File diff suppressed because it is too large Load Diff

View File

@@ -5,7 +5,6 @@ use compute_api::responses::LfcOffloadState;
use compute_api::responses::LfcPrewarmState;
use http::StatusCode;
use reqwest::Client;
use std::mem::replace;
use std::sync::Arc;
use tokio::{io::AsyncReadExt, spawn};
use tracing::{error, info};
@@ -26,16 +25,11 @@ struct EndpointStoragePair {
}
const KEY: &str = "lfc_state";
impl EndpointStoragePair {
/// endpoint_id is set to None while prewarming from other endpoint, see replica promotion
/// If not None, takes precedence over pspec.spec.endpoint_id
fn from_spec_and_endpoint(
pspec: &crate::compute::ParsedSpec,
endpoint_id: Option<String>,
) -> Result<Self> {
let endpoint_id = endpoint_id.as_ref().or(pspec.spec.endpoint_id.as_ref());
let Some(ref endpoint_id) = endpoint_id else {
bail!("pspec.endpoint_id missing, other endpoint_id not provided")
impl TryFrom<&crate::compute::ParsedSpec> for EndpointStoragePair {
type Error = anyhow::Error;
fn try_from(pspec: &crate::compute::ParsedSpec) -> Result<Self, Self::Error> {
let Some(ref endpoint_id) = pspec.spec.endpoint_id else {
bail!("pspec.endpoint_id missing")
};
let Some(ref base_uri) = pspec.endpoint_storage_addr else {
bail!("pspec.endpoint_storage_addr missing")
@@ -70,7 +64,7 @@ impl ComputeNode {
}
};
let row = match client
.query_one("select * from neon.get_prewarm_info()", &[])
.query_one("select * from get_prewarm_info()", &[])
.await
{
Ok(row) => row,
@@ -89,62 +83,46 @@ impl ComputeNode {
self.state.lock().unwrap().lfc_offload_state.clone()
}
/// If there is a prewarm request ongoing, return `false`, `true` otherwise.
pub fn prewarm_lfc(self: &Arc<Self>, from_endpoint: Option<String>) -> bool {
/// Returns false if there is a prewarm request ongoing, true otherwise
pub fn prewarm_lfc(self: &Arc<Self>) -> bool {
crate::metrics::LFC_PREWARM_REQUESTS.inc();
{
let state = &mut self.state.lock().unwrap().lfc_prewarm_state;
if let LfcPrewarmState::Prewarming = replace(state, LfcPrewarmState::Prewarming) {
if let LfcPrewarmState::Prewarming =
std::mem::replace(state, LfcPrewarmState::Prewarming)
{
return false;
}
}
crate::metrics::LFC_PREWARMS.inc();
let cloned = self.clone();
spawn(async move {
let state = match cloned.prewarm_impl(from_endpoint).await {
Ok(true) => LfcPrewarmState::Completed,
Ok(false) => {
info!(
"skipping LFC prewarm because LFC state is not found in endpoint storage"
);
LfcPrewarmState::Skipped
}
Err(err) => {
crate::metrics::LFC_PREWARM_ERRORS.inc();
error!(%err, "could not prewarm LFC");
LfcPrewarmState::Failed {
error: err.to_string(),
}
}
let Err(err) = cloned.prewarm_impl().await else {
cloned.state.lock().unwrap().lfc_prewarm_state = LfcPrewarmState::Completed;
return;
};
error!(%err);
cloned.state.lock().unwrap().lfc_prewarm_state = LfcPrewarmState::Failed {
error: err.to_string(),
};
cloned.state.lock().unwrap().lfc_prewarm_state = state;
});
true
}
/// from_endpoint: None for endpoint managed by this compute_ctl
fn endpoint_storage_pair(&self, from_endpoint: Option<String>) -> Result<EndpointStoragePair> {
fn endpoint_storage_pair(&self) -> Result<EndpointStoragePair> {
let state = self.state.lock().unwrap();
EndpointStoragePair::from_spec_and_endpoint(state.pspec.as_ref().unwrap(), from_endpoint)
state.pspec.as_ref().unwrap().try_into()
}
/// Request LFC state from endpoint storage and load corresponding pages into Postgres.
/// Returns a result with `false` if the LFC state is not found in endpoint storage.
async fn prewarm_impl(&self, from_endpoint: Option<String>) -> Result<bool> {
let EndpointStoragePair { url, token } = self.endpoint_storage_pair(from_endpoint)?;
async fn prewarm_impl(&self) -> Result<()> {
let EndpointStoragePair { url, token } = self.endpoint_storage_pair()?;
info!(%url, "requesting LFC state from endpoint storage");
let request = Client::new().get(&url).bearer_auth(token);
let res = request.send().await.context("querying endpoint storage")?;
let status = res.status();
match status {
StatusCode::OK => (),
StatusCode::NOT_FOUND => {
return Ok(false);
}
_ => bail!("{status} querying endpoint storage"),
if status != StatusCode::OK {
bail!("{status} querying endpoint storage")
}
let mut uncompressed = Vec::new();
@@ -157,67 +135,52 @@ impl ComputeNode {
.await
.context("decoding LFC state")?;
let uncompressed_len = uncompressed.len();
info!(%url, "downloaded LFC state, uncompressed size {uncompressed_len}, loading into Postgres");
info!(%url, "downloaded LFC state, uncompressed size {uncompressed_len}, loading into postgres");
ComputeNode::get_maintenance_client(&self.tokio_conn_conf)
.await
.context("connecting to postgres")?
.query_one("select neon.prewarm_local_cache($1)", &[&uncompressed])
.query_one("select prewarm_local_cache($1)", &[&uncompressed])
.await
.context("loading LFC state into postgres")
.map(|_| ())?;
Ok(true)
.map(|_| ())
}
/// If offload request is ongoing, return false, true otherwise
/// Returns false if there is an offload request ongoing, true otherwise
pub fn offload_lfc(self: &Arc<Self>) -> bool {
crate::metrics::LFC_OFFLOAD_REQUESTS.inc();
{
let state = &mut self.state.lock().unwrap().lfc_offload_state;
if replace(state, LfcOffloadState::Offloading) == LfcOffloadState::Offloading {
if let LfcOffloadState::Offloading =
std::mem::replace(state, LfcOffloadState::Offloading)
{
return false;
}
}
let cloned = self.clone();
spawn(async move { cloned.offload_lfc_with_state_update().await });
spawn(async move {
let Err(err) = cloned.offload_lfc_impl().await else {
cloned.state.lock().unwrap().lfc_offload_state = LfcOffloadState::Completed;
return;
};
error!(%err);
cloned.state.lock().unwrap().lfc_offload_state = LfcOffloadState::Failed {
error: err.to_string(),
};
});
true
}
pub async fn offload_lfc_async(self: &Arc<Self>) {
{
let state = &mut self.state.lock().unwrap().lfc_offload_state;
if replace(state, LfcOffloadState::Offloading) == LfcOffloadState::Offloading {
return;
}
}
self.offload_lfc_with_state_update().await
}
async fn offload_lfc_with_state_update(&self) {
crate::metrics::LFC_OFFLOADS.inc();
let Err(err) = self.offload_lfc_impl().await else {
self.state.lock().unwrap().lfc_offload_state = LfcOffloadState::Completed;
return;
};
crate::metrics::LFC_OFFLOAD_ERRORS.inc();
error!(%err, "could not offload LFC state to endpoint storage");
self.state.lock().unwrap().lfc_offload_state = LfcOffloadState::Failed {
error: err.to_string(),
};
}
async fn offload_lfc_impl(&self) -> Result<()> {
let EndpointStoragePair { url, token } = self.endpoint_storage_pair(None)?;
info!(%url, "requesting LFC state from Postgres");
let EndpointStoragePair { url, token } = self.endpoint_storage_pair()?;
info!(%url, "requesting LFC state from postgres");
let mut compressed = Vec::new();
ComputeNode::get_maintenance_client(&self.tokio_conn_conf)
.await
.context("connecting to postgres")?
.query_one("select neon.get_local_cache_state()", &[])
.query_one("select get_local_cache_state()", &[])
.await
.context("querying LFC state")?
.try_get::<usize, &[u8]>(0)
@@ -226,17 +189,13 @@ impl ComputeNode {
.read_to_end(&mut compressed)
.await
.context("compressing LFC state")?;
let compressed_len = compressed.len();
info!(%url, "downloaded LFC state, compressed size {compressed_len}, writing to endpoint storage");
let request = Client::new().put(url).bearer_auth(token).body(compressed);
match request.send().await {
Ok(res) if res.status() == StatusCode::OK => Ok(()),
Ok(res) => bail!(
"Request to endpoint storage failed with status: {}",
res.status()
),
Ok(res) => bail!("Error writing to endpoint storage: {}", res.status()),
Err(err) => Err(err).context("writing to endpoint storage"),
}
}

View File

@@ -1,132 +0,0 @@
use crate::compute::ComputeNode;
use anyhow::{Context, Result, bail};
use compute_api::{
responses::{LfcPrewarmState, PromoteState, SafekeepersLsn},
spec::ComputeMode,
};
use std::{sync::Arc, time::Duration};
use tokio::time::sleep;
use utils::lsn::Lsn;
impl ComputeNode {
/// Returns only when promote fails or succeeds. If a network error occurs
/// and http client disconnects, this does not stop promotion, and subsequent
/// calls block until promote finishes.
/// Called by control plane on secondary after primary endpoint is terminated
pub async fn promote(self: &Arc<Self>, safekeepers_lsn: SafekeepersLsn) -> PromoteState {
let cloned = self.clone();
let start_promotion = || {
let (tx, rx) = tokio::sync::watch::channel(PromoteState::NotPromoted);
tokio::spawn(async move {
tx.send(match cloned.promote_impl(safekeepers_lsn).await {
Ok(_) => PromoteState::Completed,
Err(err) => {
tracing::error!(%err, "promoting");
PromoteState::Failed {
error: err.to_string(),
}
}
})
});
rx
};
let mut task;
// self.state is unlocked after block ends so we lock it in promote_impl
// and task.changed() is reached
{
task = self
.state
.lock()
.unwrap()
.promote_state
.get_or_insert_with(start_promotion)
.clone()
}
task.changed().await.expect("promote sender dropped");
task.borrow().clone()
}
// Why do we have to supply safekeepers?
// For secondary we use primary_connection_conninfo so safekeepers field is empty
async fn promote_impl(&self, safekeepers_lsn: SafekeepersLsn) -> Result<()> {
{
let state = self.state.lock().unwrap();
let mode = &state.pspec.as_ref().unwrap().spec.mode;
if *mode != ComputeMode::Replica {
bail!("{} is not replica", mode.to_type_str());
}
// we don't need to query Postgres so not self.lfc_prewarm_state()
match &state.lfc_prewarm_state {
LfcPrewarmState::NotPrewarmed | LfcPrewarmState::Prewarming => {
bail!("prewarm not requested or pending")
}
LfcPrewarmState::Failed { error } => {
tracing::warn!(%error, "replica prewarm failed")
}
_ => {}
}
}
let client = ComputeNode::get_maintenance_client(&self.tokio_conn_conf)
.await
.context("connecting to postgres")?;
let primary_lsn = safekeepers_lsn.wal_flush_lsn;
let mut last_wal_replay_lsn: Lsn = Lsn::INVALID;
const RETRIES: i32 = 20;
for i in 0..=RETRIES {
let row = client
.query_one("SELECT pg_last_wal_replay_lsn()", &[])
.await
.context("getting last replay lsn")?;
let lsn: u64 = row.get::<usize, postgres_types::PgLsn>(0).into();
last_wal_replay_lsn = lsn.into();
if last_wal_replay_lsn >= primary_lsn {
break;
}
tracing::info!("Try {i}, replica lsn {last_wal_replay_lsn}, primary lsn {primary_lsn}");
sleep(Duration::from_secs(1)).await;
}
if last_wal_replay_lsn < primary_lsn {
bail!("didn't catch up with primary in {RETRIES} retries");
}
// using $1 doesn't work with ALTER SYSTEM SET
let safekeepers_sql = format!(
"ALTER SYSTEM SET neon.safekeepers='{}'",
safekeepers_lsn.safekeepers
);
client
.query(&safekeepers_sql, &[])
.await
.context("setting safekeepers")?;
client
.query("SELECT pg_reload_conf()", &[])
.await
.context("reloading postgres config")?;
let row = client
.query_one("SELECT * FROM pg_promote()", &[])
.await
.context("pg_promote")?;
if !row.get::<usize, bool>(0) {
bail!("pg_promote() returned false");
}
let client = ComputeNode::get_maintenance_client(&self.tokio_conn_conf)
.await
.context("connecting to postgres")?;
let row = client
.query_one("SHOW transaction_read_only", &[])
.await
.context("getting transaction_read_only")?;
if row.get::<usize, &str>(0) == "on" {
bail!("replica in read only mode after promotion");
}
let mut state = self.state.lock().unwrap();
state.pspec.as_mut().unwrap().spec.mode = ComputeMode::Primary;
Ok(())
}
}

View File

@@ -9,14 +9,11 @@ use std::path::Path;
use compute_api::responses::TlsConfig;
use compute_api::spec::{ComputeAudit, ComputeMode, ComputeSpec, GenericOption};
use crate::compute::ComputeNodeParams;
use crate::pg_helpers::{
GenericOptionExt, GenericOptionsSearch, PgOptionsSerialize, escape_conf_value,
};
use crate::tls::{self, SERVER_CRT, SERVER_KEY};
use utils::shard::{ShardIndex, ShardNumber};
/// Check that `line` is inside a text file and put it there if it is not.
/// Create file if it doesn't exist.
pub fn line_in_file(path: &Path, line: &str) -> Result<bool> {
@@ -44,7 +41,6 @@ pub fn line_in_file(path: &Path, line: &str) -> Result<bool> {
/// Create or completely rewrite configuration file specified by `path`
pub fn write_postgres_conf(
pgdata_path: &Path,
params: &ComputeNodeParams,
spec: &ComputeSpec,
extension_server_port: u16,
tls_config: &Option<TlsConfig>,
@@ -55,104 +51,17 @@ pub fn write_postgres_conf(
// Write the postgresql.conf content from the spec file as is.
if let Some(conf) = &spec.cluster.postgresql_conf {
writeln!(file, "{conf}")?;
writeln!(file, "{}", conf)?;
}
// Add options for connecting to storage
writeln!(file, "# Neon storage settings")?;
writeln!(file)?;
if let Some(conninfo) = &spec.pageserver_connection_info {
// Stripe size GUC should be defined prior to connection string
if let Some(stripe_size) = conninfo.stripe_size {
writeln!(
file,
"# from compute spec's pageserver_conninfo.stripe_size field"
)?;
writeln!(file, "neon.stripe_size={stripe_size}")?;
}
let mut libpq_urls: Option<Vec<String>> = Some(Vec::new());
let mut grpc_urls: Option<Vec<String>> = Some(Vec::new());
let num_shards = if conninfo.shard_count.0 == 0 {
1 // unsharded, treat it as a single shard
} else {
conninfo.shard_count.0
};
for shard_number in 0..num_shards {
let shard_index = ShardIndex {
shard_number: ShardNumber(shard_number),
shard_count: conninfo.shard_count,
};
let info = conninfo.shards.get(&shard_index).ok_or_else(|| {
anyhow::anyhow!(
"shard {shard_index} missing from pageserver_connection_info shard map"
)
})?;
let first_pageserver = info
.pageservers
.first()
.expect("must have at least one pageserver");
// Add the libpq URL to the array, or if the URL is missing, reset the array
// forgetting any previous entries. All servers must have a libpq URL, or none
// at all.
if let Some(url) = &first_pageserver.libpq_url {
if let Some(ref mut urls) = libpq_urls {
urls.push(url.clone());
}
} else {
libpq_urls = None
}
// Similarly for gRPC URLs
if let Some(url) = &first_pageserver.grpc_url {
if let Some(ref mut urls) = grpc_urls {
urls.push(url.clone());
}
} else {
grpc_urls = None
}
}
if let Some(libpq_urls) = libpq_urls {
writeln!(
file,
"# derived from compute spec's pageserver_conninfo field"
)?;
writeln!(
file,
"neon.pageserver_connstring={}",
escape_conf_value(&libpq_urls.join(","))
)?;
} else {
writeln!(file, "# no neon.pageserver_connstring")?;
}
if let Some(grpc_urls) = grpc_urls {
writeln!(
file,
"# derived from compute spec's pageserver_conninfo field"
)?;
writeln!(
file,
"neon.pageserver_grpc_urls={}",
escape_conf_value(&grpc_urls.join(","))
)?;
} else {
writeln!(file, "# no neon.pageserver_grpc_urls")?;
}
} else {
// Stripe size GUC should be defined prior to connection string
if let Some(stripe_size) = spec.shard_stripe_size {
writeln!(file, "# from compute spec's shard_stripe_size field")?;
writeln!(file, "neon.stripe_size={stripe_size}")?;
}
if let Some(s) = &spec.pageserver_connstring {
writeln!(file, "# from compute spec's pageserver_connstring field")?;
writeln!(file, "neon.pageserver_connstring={}", escape_conf_value(s))?;
}
if let Some(s) = &spec.pageserver_connstring {
writeln!(file, "neon.pageserver_connstring={}", escape_conf_value(s))?;
}
if let Some(stripe_size) = spec.shard_stripe_size {
writeln!(file, "neon.stripe_size={stripe_size}")?;
}
if !spec.safekeeper_connstrings.is_empty() {
let mut neon_safekeepers_value = String::new();
tracing::info!(
@@ -161,7 +70,7 @@ pub fn write_postgres_conf(
);
// If generation is given, prepend sk list with g#number:
if let Some(generation) = spec.safekeepers_generation {
write!(neon_safekeepers_value, "g#{generation}:")?;
write!(neon_safekeepers_value, "g#{}:", generation)?;
}
neon_safekeepers_value.push_str(&spec.safekeeper_connstrings.join(","));
writeln!(
@@ -200,8 +109,8 @@ pub fn write_postgres_conf(
tls::update_key_path_blocking(pgdata_path, tls_config);
// these are the default, but good to be explicit.
writeln!(file, "ssl_cert_file = '{SERVER_CRT}'")?;
writeln!(file, "ssl_key_file = '{SERVER_KEY}'")?;
writeln!(file, "ssl_cert_file = '{}'", SERVER_CRT)?;
writeln!(file, "ssl_key_file = '{}'", SERVER_KEY)?;
}
// Locales
@@ -252,12 +161,6 @@ pub fn write_postgres_conf(
}
}
writeln!(
file,
"neon.privileged_role_name={}",
escape_conf_value(params.privileged_role_name.as_str())
)?;
// If there are any extra options in the 'settings' field, append those
if spec.cluster.settings.is_some() {
writeln!(file, "# Managed by compute_ctl: begin")?;
@@ -288,7 +191,8 @@ pub fn write_postgres_conf(
}
writeln!(
file,
"shared_preload_libraries='{libs}{extra_shared_preload_libraries}'"
"shared_preload_libraries='{}{}'",
libs, extra_shared_preload_libraries
)?;
} else {
// Typically, this should be unreacheable,
@@ -340,7 +244,8 @@ pub fn write_postgres_conf(
}
writeln!(
file,
"shared_preload_libraries='{libs}{extra_shared_preload_libraries}'"
"shared_preload_libraries='{}{}'",
libs, extra_shared_preload_libraries
)?;
} else {
// Typically, this should be unreacheable,
@@ -358,7 +263,7 @@ pub fn write_postgres_conf(
}
}
writeln!(file, "neon.extension_server_port={extension_server_port}")?;
writeln!(file, "neon.extension_server_port={}", extension_server_port)?;
if spec.drop_subscriptions_before_start {
writeln!(file, "neon.disable_logical_replication_subscribers=true")?;
@@ -386,7 +291,7 @@ where
{
let path = pgdata_path.join("compute_ctl_temp_override.conf");
let mut file = File::create(path)?;
write!(file, "{options}")?;
write!(file, "{}", options)?;
let res = exec();

View File

@@ -10,13 +10,7 @@ input(type="imfile" File="{log_directory}/*.log"
startmsg.regex="^[[:digit:]]{{4}}-[[:digit:]]{{2}}-[[:digit:]]{{2}} [[:digit:]]{{2}}:[[:digit:]]{{2}}:[[:digit:]]{{2}}.[[:digit:]]{{3}} GMT,")
# the directory to store rsyslog state files
global(
workDirectory="/var/log/rsyslog"
DefaultNetstreamDriverCAFile="/etc/ssl/certs/ca-certificates.crt"
)
# Whether the remote syslog receiver uses tls
set $.remote_syslog_tls = "{remote_syslog_tls}";
global(workDirectory="/var/log/rsyslog")
# Construct json, endpoint_id and project_id as additional metadata
set $.json_log!endpoint_id = "{endpoint_id}";
@@ -27,29 +21,5 @@ set $.json_log!msg = $msg;
template(name="PgAuditLog" type="string"
string="<%PRI%>1 %TIMESTAMP:::date-rfc3339% %HOSTNAME% - - - - %$.json_log%")
# Forward to remote syslog receiver (over TLS)
if ( $syslogtag == 'pgaudit_log' ) then {{
if ( $.remote_syslog_tls == 'true' ) then {{
action(type="omfwd" target="{remote_syslog_host}" port="{remote_syslog_port}" protocol="tcp"
template="PgAuditLog"
queue.type="linkedList"
queue.size="1000"
action.ResumeRetryCount="10"
StreamDriver="gtls"
StreamDriverMode="1"
StreamDriverAuthMode="x509/name"
StreamDriverPermittedPeers="{remote_syslog_host}"
StreamDriver.CheckExtendedKeyPurpose="on"
StreamDriver.PermitExpiredCerts="off"
)
stop
}} else {{
action(type="omfwd" target="{remote_syslog_host}" port="{remote_syslog_port}" protocol="tcp"
template="PgAuditLog"
queue.type="linkedList"
queue.size="1000"
action.ResumeRetryCount="10"
)
stop
}}
}}
# Forward to remote syslog receiver (@@<hostname>:<port>;format
local5.info @@{remote_endpoint};PgAuditLog

View File

@@ -74,11 +74,9 @@ More specifically, here is an example ext_index.json
use std::path::Path;
use std::str;
use crate::metrics::{REMOTE_EXT_REQUESTS_TOTAL, UNKNOWN_HTTP_STATUS};
use anyhow::{Context, Result, bail};
use bytes::Bytes;
use compute_api::spec::RemoteExtSpec;
use postgres_versioninfo::PgMajorVersion;
use regex::Regex;
use remote_storage::*;
use reqwest::StatusCode;
@@ -88,6 +86,8 @@ use tracing::log::warn;
use url::Url;
use zstd::stream::read::Decoder;
use crate::metrics::{REMOTE_EXT_REQUESTS_TOTAL, UNKNOWN_HTTP_STATUS};
fn get_pg_config(argument: &str, pgbin: &str) -> String {
// gives the result of `pg_config [argument]`
// where argument is a flag like `--version` or `--sharedir`
@@ -106,7 +106,7 @@ fn get_pg_config(argument: &str, pgbin: &str) -> String {
.to_string()
}
pub fn get_pg_version(pgbin: &str) -> PgMajorVersion {
pub fn get_pg_version(pgbin: &str) -> PostgresMajorVersion {
// pg_config --version returns a (platform specific) human readable string
// such as "PostgreSQL 15.4". We parse this to v14/v15/v16 etc.
let human_version = get_pg_config("--version", pgbin);
@@ -114,11 +114,25 @@ pub fn get_pg_version(pgbin: &str) -> PgMajorVersion {
}
pub fn get_pg_version_string(pgbin: &str) -> String {
get_pg_version(pgbin).v_str()
match get_pg_version(pgbin) {
PostgresMajorVersion::V14 => "v14",
PostgresMajorVersion::V15 => "v15",
PostgresMajorVersion::V16 => "v16",
PostgresMajorVersion::V17 => "v17",
}
.to_owned()
}
fn parse_pg_version(human_version: &str) -> PgMajorVersion {
use PgMajorVersion::*;
#[derive(Copy, Clone, Debug, PartialEq, Eq)]
pub enum PostgresMajorVersion {
V14,
V15,
V16,
V17,
}
fn parse_pg_version(human_version: &str) -> PostgresMajorVersion {
use PostgresMajorVersion::*;
// Normal releases have version strings like "PostgreSQL 15.4". But there
// are also pre-release versions like "PostgreSQL 17devel" or "PostgreSQL
// 16beta2" or "PostgreSQL 17rc1". And with the --with-extra-version
@@ -129,10 +143,10 @@ fn parse_pg_version(human_version: &str) -> PgMajorVersion {
.captures(human_version)
{
Some(captures) if captures.len() == 2 => match &captures["major"] {
"14" => return PG14,
"15" => return PG15,
"16" => return PG16,
"17" => return PG17,
"14" => return V14,
"15" => return V15,
"16" => return V16,
"17" => return V17,
_ => {}
},
_ => {}
@@ -296,7 +310,10 @@ async fn download_extension_tar(remote_ext_base_url: &Url, ext_path: &str) -> Re
async fn do_extension_server_request(uri: Url) -> Result<Bytes, (String, String)> {
let resp = reqwest::get(uri).await.map_err(|e| {
(
format!("could not perform remote extensions server request: {e:?}"),
format!(
"could not perform remote extensions server request: {:?}",
e
),
UNKNOWN_HTTP_STATUS.to_string(),
)
})?;
@@ -306,7 +323,7 @@ async fn do_extension_server_request(uri: Url) -> Result<Bytes, (String, String)
StatusCode::OK => match resp.bytes().await {
Ok(resp) => Ok(resp),
Err(e) => Err((
format!("could not read remote extensions server response: {e:?}"),
format!("could not read remote extensions server response: {:?}", e),
// It's fine to return and report error with status as 200 OK,
// because we still failed to read the response.
status.to_string(),
@@ -317,7 +334,10 @@ async fn do_extension_server_request(uri: Url) -> Result<Bytes, (String, String)
status.to_string(),
)),
_ => Err((
format!("unexpected remote extensions server response status code: {status}"),
format!(
"unexpected remote extensions server response status code: {}",
status
),
status.to_string(),
)),
}
@@ -329,25 +349,25 @@ mod tests {
#[test]
fn test_parse_pg_version() {
use postgres_versioninfo::PgMajorVersion::*;
assert_eq!(parse_pg_version("PostgreSQL 15.4"), PG15);
assert_eq!(parse_pg_version("PostgreSQL 15.14"), PG15);
use super::PostgresMajorVersion::*;
assert_eq!(parse_pg_version("PostgreSQL 15.4"), V15);
assert_eq!(parse_pg_version("PostgreSQL 15.14"), V15);
assert_eq!(
parse_pg_version("PostgreSQL 15.4 (Ubuntu 15.4-0ubuntu0.23.04.1)"),
PG15
V15
);
assert_eq!(parse_pg_version("PostgreSQL 14.15"), PG14);
assert_eq!(parse_pg_version("PostgreSQL 14.0"), PG14);
assert_eq!(parse_pg_version("PostgreSQL 14.15"), V14);
assert_eq!(parse_pg_version("PostgreSQL 14.0"), V14);
assert_eq!(
parse_pg_version("PostgreSQL 14.9 (Debian 14.9-1.pgdg120+1"),
PG14
V14
);
assert_eq!(parse_pg_version("PostgreSQL 16devel"), PG16);
assert_eq!(parse_pg_version("PostgreSQL 16beta1"), PG16);
assert_eq!(parse_pg_version("PostgreSQL 16rc2"), PG16);
assert_eq!(parse_pg_version("PostgreSQL 16extra"), PG16);
assert_eq!(parse_pg_version("PostgreSQL 16devel"), V16);
assert_eq!(parse_pg_version("PostgreSQL 16beta1"), V16);
assert_eq!(parse_pg_version("PostgreSQL 16rc2"), V16);
assert_eq!(parse_pg_version("PostgreSQL 16extra"), V16);
}
#[test]

View File

@@ -83,87 +83,6 @@ paths:
schema:
$ref: "#/components/schemas/DbsAndRoles"
/promote:
post:
tags:
- Promotion
summary: Promote secondary replica to primary
description: ""
operationId: promoteReplica
requestBody:
description: Promote requests data
required: true
content:
application/json:
schema:
$ref: "#/components/schemas/SafekeepersLsn"
responses:
200:
description: Promote succeeded or wasn't started
content:
application/json:
schema:
$ref: "#/components/schemas/PromoteState"
500:
description: Promote failed
content:
application/json:
schema:
$ref: "#/components/schemas/PromoteState"
/lfc/prewarm:
post:
summary: Request LFC Prewarm
parameters:
- name: from_endpoint
in: query
schema:
type: string
description: ""
operationId: lfcPrewarm
responses:
202:
description: LFC prewarm started
429:
description: LFC prewarm ongoing
get:
tags:
- Prewarm
summary: Get LFC prewarm state
description: ""
operationId: getLfcPrewarmState
responses:
200:
description: Prewarm state
content:
application/json:
schema:
$ref: "#/components/schemas/LfcPrewarmState"
/lfc/offload:
post:
summary: Request LFC offload
description: ""
operationId: lfcOffload
responses:
202:
description: LFC offload started
429:
description: LFC offload ongoing
get:
tags:
- Prewarm
summary: Get LFC offloading state
description: ""
operationId: getLfcOffloadState
responses:
200:
description: Offload state
content:
application/json:
schema:
$ref: "#/components/schemas/LfcOffloadState"
/database_schema:
get:
tags:
@@ -371,28 +290,9 @@ paths:
summary: Terminate Postgres and wait for it to exit
description: ""
operationId: terminate
parameters:
- name: mode
in: query
description: "Terminate mode: fast (wait 30s before returning) and immediate"
required: false
schema:
type: string
enum: ["fast", "immediate"]
default: fast
responses:
200:
description: Result
content:
application/json:
schema:
$ref: "#/components/schemas/TerminateResponse"
201:
description: Result if compute is already terminated
content:
application/json:
schema:
$ref: "#/components/schemas/TerminateResponse"
412:
description: "wrong state"
content:
@@ -435,6 +335,15 @@ components:
total_startup_ms:
type: integer
Info:
type: object
description: Information about VM/Pod.
required:
- num_cpus
properties:
num_cpus:
type: integer
DbsAndRoles:
type: object
description: Databases and Roles
@@ -549,14 +458,11 @@ components:
type: string
enum:
- empty
- configuration_pending
- init
- running
- configuration
- failed
- termination_pending_fast
- termination_pending_immediate
- terminated
- running
- configuration_pending
- configuration
example: running
ExtensionInstallRequest:
@@ -591,69 +497,25 @@ components:
type: string
example: "1.0.0"
SafekeepersLsn:
InstalledExtensions:
type: object
required:
- safekeepers
- wal_flush_lsn
properties:
safekeepers:
description: Primary replica safekeepers
type: string
wal_flush_lsn:
description: Primary last WAL flush LSN
type: string
LfcPrewarmState:
type: object
required:
- status
- total
- prewarmed
- skipped
properties:
status:
description: LFC prewarm status
enum: [not_prewarmed, prewarming, completed, failed, skipped]
type: string
error:
description: LFC prewarm error, if any
type: string
total:
description: Total pages processed
type: integer
prewarmed:
description: Total pages prewarmed
type: integer
skipped:
description: Pages processed but not prewarmed
type: integer
LfcOffloadState:
type: object
required:
- status
properties:
status:
description: LFC offload status
enum: [not_offloaded, offloading, completed, failed]
type: string
error:
description: LFC offload error, if any
type: string
PromoteState:
type: object
required:
- status
properties:
status:
description: Promote result
enum: [not_promoted, completed, failed]
type: string
error:
description: Promote error, if any
type: string
extensions:
description: Contains list of installed extensions.
type: array
items:
type: object
properties:
extname:
type: string
version:
type: string
items:
type: string
n_databases:
type: integer
owned_by_superuser:
type: integer
SetRoleGrantsRequest:
type: object
@@ -682,17 +544,6 @@ components:
description: Role name.
example: "neon"
TerminateResponse:
type: object
required:
- lsn
properties:
lsn:
type: string
nullable: true
description: "last WAL flush LSN"
example: "0/028F10D8"
SetRoleGrantsResponse:
type: object
required:

View File

@@ -65,7 +65,7 @@ pub(in crate::http) async fn configure(
if state.status == ComputeStatus::Failed {
let err = state.error.as_ref().map_or("unknown error", |x| x);
let msg = format!("compute configuration failed: {err:?}");
let msg = format!("compute configuration failed: {:?}", err);
return Err(msg);
}
}

View File

@@ -2,7 +2,6 @@ use crate::compute_prewarm::LfcPrewarmStateWithProgress;
use crate::http::JsonResponse;
use axum::response::{IntoResponse, Response};
use axum::{Json, http::StatusCode};
use axum_extra::extract::OptionalQuery;
use compute_api::responses::LfcOffloadState;
type Compute = axum::extract::State<std::sync::Arc<crate::compute::ComputeNode>>;
@@ -17,16 +16,8 @@ pub(in crate::http) async fn offload_state(compute: Compute) -> Json<LfcOffloadS
Json(compute.lfc_offload_state())
}
#[derive(serde::Deserialize)]
pub struct PrewarmQuery {
pub from_endpoint: String,
}
pub(in crate::http) async fn prewarm(
compute: Compute,
OptionalQuery(query): OptionalQuery<PrewarmQuery>,
) -> Response {
if compute.prewarm_lfc(query.map(|q| q.from_endpoint)) {
pub(in crate::http) async fn prewarm(compute: Compute) -> Response {
if compute.prewarm_lfc() {
StatusCode::ACCEPTED.into_response()
} else {
JsonResponse::error(

View File

@@ -14,7 +14,6 @@ pub(in crate::http) mod insights;
pub(in crate::http) mod lfc;
pub(in crate::http) mod metrics;
pub(in crate::http) mod metrics_json;
pub(in crate::http) mod promote;
pub(in crate::http) mod status;
pub(in crate::http) mod terminate;

View File

@@ -1,14 +0,0 @@
use crate::http::JsonResponse;
use axum::Form;
use http::StatusCode;
pub(in crate::http) async fn promote(
compute: axum::extract::State<std::sync::Arc<crate::compute::ComputeNode>>,
Form(safekeepers_lsn): Form<compute_api::responses::SafekeepersLsn>,
) -> axum::response::Response {
let state = compute.promote(safekeepers_lsn).await;
if let compute_api::responses::PromoteState::Failed { error } = state {
return JsonResponse::error(StatusCode::INTERNAL_SERVER_ERROR, error);
}
JsonResponse::success(StatusCode::OK, state)
}

View File

@@ -1,42 +1,32 @@
use crate::compute::{ComputeNode, forward_termination_signal};
use crate::http::JsonResponse;
use axum::extract::State;
use axum::response::Response;
use axum_extra::extract::OptionalQuery;
use compute_api::responses::{ComputeStatus, TerminateMode, TerminateResponse};
use http::StatusCode;
use serde::Deserialize;
use std::sync::Arc;
use axum::extract::State;
use axum::response::{IntoResponse, Response};
use compute_api::responses::ComputeStatus;
use http::StatusCode;
use tokio::task;
use tracing::info;
#[derive(Deserialize, Default)]
pub struct TerminateQuery {
mode: TerminateMode,
}
use crate::compute::{ComputeNode, forward_termination_signal};
use crate::http::JsonResponse;
/// Terminate the compute.
pub(in crate::http) async fn terminate(
State(compute): State<Arc<ComputeNode>>,
OptionalQuery(terminate): OptionalQuery<TerminateQuery>,
) -> Response {
let mode = terminate.unwrap_or_default().mode;
pub(in crate::http) async fn terminate(State(compute): State<Arc<ComputeNode>>) -> Response {
{
let mut state = compute.state.lock().unwrap();
if state.status == ComputeStatus::Terminated {
let response = TerminateResponse {
lsn: state.terminate_flush_lsn,
};
return JsonResponse::success(StatusCode::CREATED, response);
return StatusCode::CREATED.into_response();
}
if !matches!(state.status, ComputeStatus::Empty | ComputeStatus::Running) {
return JsonResponse::invalid_status(state.status);
}
state.set_status(mode.into(), &compute.state_changed);
state.set_status(ComputeStatus::TerminationPending, &compute.state_changed);
drop(state);
}
forward_termination_signal(false);
forward_termination_signal();
info!("sent signal and notified waiters");
// Spawn a blocking thread to wait for compute to become Terminated.
@@ -44,7 +34,7 @@ pub(in crate::http) async fn terminate(
// be able to serve other requests while some particular request
// is waiting for compute to finish configuration.
let c = compute.clone();
let lsn = task::spawn_blocking(move || {
task::spawn_blocking(move || {
let mut state = c.state.lock().unwrap();
while state.status != ComputeStatus::Terminated {
state = c.state_changed.wait(state).unwrap();
@@ -54,10 +44,11 @@ pub(in crate::http) async fn terminate(
state.status
);
}
state.terminate_flush_lsn
})
.await
.unwrap();
info!("terminated Postgres");
JsonResponse::success(StatusCode::OK, TerminateResponse { lsn })
StatusCode::OK.into_response()
}

View File

@@ -23,7 +23,7 @@ use super::{
middleware::authorize::Authorize,
routes::{
check_writability, configure, database_schema, dbs_and_roles, extension_server, extensions,
grants, insights, lfc, metrics, metrics_json, promote, status, terminate,
grants, insights, lfc, metrics, metrics_json, status, terminate,
},
};
use crate::compute::ComputeNode;
@@ -87,7 +87,6 @@ impl From<&Server> for Router<Arc<ComputeNode>> {
let authenticated_router = Router::<Arc<ComputeNode>>::new()
.route("/lfc/prewarm", get(lfc::prewarm_state).post(lfc::prewarm))
.route("/lfc/offload", get(lfc::offload_state).post(lfc::offload))
.route("/promote", post(promote::promote))
.route("/check_writability", post(check_writability::is_writable))
.route("/configure", post(configure::configure))
.route("/database_schema", get(database_schema::get_schema_dump))

View File

@@ -2,7 +2,6 @@ use std::collections::HashMap;
use anyhow::Result;
use compute_api::responses::{InstalledExtension, InstalledExtensions};
use tokio_postgres::error::Error as PostgresError;
use tokio_postgres::{Client, Config, NoTls};
use crate::metrics::INSTALLED_EXTENSIONS;
@@ -11,7 +10,7 @@ use crate::metrics::INSTALLED_EXTENSIONS;
/// and to make database listing query here more explicit.
///
/// Limit the number of databases to 500 to avoid excessive load.
async fn list_dbs(client: &mut Client) -> Result<Vec<String>, PostgresError> {
async fn list_dbs(client: &mut Client) -> Result<Vec<String>> {
// `pg_database.datconnlimit = -2` means that the database is in the
// invalid state
let databases = client
@@ -38,15 +37,13 @@ async fn list_dbs(client: &mut Client) -> Result<Vec<String>, PostgresError> {
/// Same extension can be installed in multiple databases with different versions,
/// so we report a separate metric (number of databases where it is installed)
/// for each extension version.
pub async fn get_installed_extensions(
mut conf: Config,
) -> Result<InstalledExtensions, PostgresError> {
pub async fn get_installed_extensions(mut conf: Config) -> Result<InstalledExtensions> {
conf.application_name("compute_ctl:get_installed_extensions");
let databases: Vec<String> = {
let (mut client, connection) = conf.connect(NoTls).await?;
tokio::spawn(async move {
if let Err(e) = connection.await {
eprintln!("connection error: {e}");
eprintln!("connection error: {}", e);
}
});
@@ -60,7 +57,7 @@ pub async fn get_installed_extensions(
let (client, connection) = conf.connect(NoTls).await?;
tokio::spawn(async move {
if let Err(e) = connection.await {
eprintln!("connection error: {e}");
eprintln!("connection error: {}", e);
}
});

View File

@@ -12,7 +12,6 @@ pub mod logger;
pub mod catalog;
pub mod compute;
pub mod compute_prewarm;
pub mod compute_promote;
pub mod disk_quota;
pub mod extension_server;
pub mod installed_extensions;
@@ -23,7 +22,6 @@ mod migration;
pub mod monitor;
pub mod params;
pub mod pg_helpers;
pub mod pgbouncer;
pub mod rsyslog;
pub mod spec;
mod spec_apply;

View File

@@ -4,13 +4,12 @@ use std::thread;
use std::time::{Duration, SystemTime};
use anyhow::{Result, bail};
use compute_api::spec::{ComputeMode, PageserverConnectionInfo, PageserverProtocol};
use pageserver_page_api as page_api;
use compute_api::spec::ComputeMode;
use postgres::{NoTls, SimpleQueryMessage};
use tracing::{info, warn};
use utils::id::{TenantId, TimelineId};
use utils::lsn::Lsn;
use utils::shard::TenantShardId;
use utils::shard::{ShardCount, ShardNumber, TenantShardId};
use crate::compute::ComputeNode;
@@ -77,16 +76,25 @@ fn acquire_lsn_lease_with_retry(
loop {
// Note: List of pageservers is dynamic, need to re-read configs before each attempt.
let (conninfo, auth) = {
let configs = {
let state = compute.state.lock().unwrap();
let spec = state.pspec.as_ref().expect("spec must be set");
(
spec.pageserver_conninfo.clone(),
spec.storage_auth_token.clone(),
)
let conn_strings = spec.pageserver_connstr.split(',');
conn_strings
.map(|connstr| {
let mut config = postgres::Config::from_str(connstr).expect("Invalid connstr");
if let Some(storage_auth_token) = &spec.storage_auth_token {
config.password(storage_auth_token.clone());
}
config
})
.collect::<Vec<_>>()
};
let result = try_acquire_lsn_lease(conninfo, auth.as_deref(), tenant_id, timeline_id, lsn);
let result = try_acquire_lsn_lease(tenant_id, timeline_id, lsn, &configs);
match result {
Ok(Some(res)) => {
return Ok(res);
@@ -108,113 +116,68 @@ fn acquire_lsn_lease_with_retry(
}
}
/// Tries to acquire LSN leases on all Pageserver shards.
/// Tries to acquire an LSN lease through PS page_service API.
fn try_acquire_lsn_lease(
conninfo: PageserverConnectionInfo,
auth: Option<&str>,
tenant_id: TenantId,
timeline_id: TimelineId,
lsn: Lsn,
configs: &[postgres::Config],
) -> Result<Option<SystemTime>> {
let mut leases = Vec::new();
for (shard_index, shard) in conninfo.shards.into_iter() {
let tenant_shard_id = TenantShardId {
tenant_id,
shard_number: shard_index.shard_number,
shard_count: shard_index.shard_count,
fn get_valid_until(
config: &postgres::Config,
tenant_shard_id: TenantShardId,
timeline_id: TimelineId,
lsn: Lsn,
) -> Result<Option<SystemTime>> {
let mut client = config.connect(NoTls)?;
let cmd = format!("lease lsn {} {} {} ", tenant_shard_id, timeline_id, lsn);
let res = client.simple_query(&cmd)?;
let msg = match res.first() {
Some(msg) => msg,
None => bail!("empty response"),
};
let row = match msg {
SimpleQueryMessage::Row(row) => row,
_ => bail!("error parsing lsn lease response"),
};
// XXX: If there are more than pageserver for the one shard, do we need to get a
// leas on all of them? Currently, that's what we assume, but this is hypothetical
// as of this writing, as we never pass the info for more than one pageserver per
// shard.
for pageserver in shard.pageservers {
let lease = match conninfo.prefer_protocol {
PageserverProtocol::Grpc => acquire_lsn_lease_grpc(
&pageserver.grpc_url.unwrap(),
auth,
tenant_shard_id,
timeline_id,
lsn,
)?,
PageserverProtocol::Libpq => acquire_lsn_lease_libpq(
&pageserver.libpq_url.unwrap(),
auth,
tenant_shard_id,
timeline_id,
lsn,
)?,
};
leases.push(lease);
}
// Note: this will be None if a lease is explicitly not granted.
let valid_until_str = row.get("valid_until");
let valid_until = valid_until_str.map(|s| {
SystemTime::UNIX_EPOCH
.checked_add(Duration::from_millis(u128::from_str(s).unwrap() as u64))
.expect("Time larger than max SystemTime could handle")
});
Ok(valid_until)
}
Ok(leases.into_iter().min().flatten())
}
let shard_count = configs.len();
/// Acquires an LSN lease on a single shard, using the libpq API. The connstring must use a
/// postgresql:// scheme.
fn acquire_lsn_lease_libpq(
connstring: &str,
auth: Option<&str>,
tenant_shard_id: TenantShardId,
timeline_id: TimelineId,
lsn: Lsn,
) -> Result<Option<SystemTime>> {
let mut config = postgres::Config::from_str(connstring)?;
if let Some(auth) = auth {
config.password(auth);
}
let mut client = config.connect(NoTls)?;
let cmd = format!("lease lsn {tenant_shard_id} {timeline_id} {lsn} ");
let res = client.simple_query(&cmd)?;
let msg = match res.first() {
Some(msg) => msg,
None => bail!("empty response"),
};
let row = match msg {
SimpleQueryMessage::Row(row) => row,
_ => bail!("error parsing lsn lease response"),
let valid_until = if shard_count > 1 {
configs
.iter()
.enumerate()
.map(|(shard_number, config)| {
let tenant_shard_id = TenantShardId {
tenant_id,
shard_count: ShardCount::new(shard_count as u8),
shard_number: ShardNumber(shard_number as u8),
};
get_valid_until(config, tenant_shard_id, timeline_id, lsn)
})
.collect::<Result<Vec<Option<SystemTime>>>>()?
.into_iter()
.min()
.unwrap()
} else {
get_valid_until(
&configs[0],
TenantShardId::unsharded(tenant_id),
timeline_id,
lsn,
)?
};
// Note: this will be None if a lease is explicitly not granted.
let valid_until_str = row.get("valid_until");
let valid_until = valid_until_str.map(|s| {
SystemTime::UNIX_EPOCH
.checked_add(Duration::from_millis(u128::from_str(s).unwrap() as u64))
.expect("Time larger than max SystemTime could handle")
});
Ok(valid_until)
}
/// Acquires an LSN lease on a single shard, using the gRPC API. The connstring must use a
/// grpc:// scheme.
fn acquire_lsn_lease_grpc(
connstring: &str,
auth: Option<&str>,
tenant_shard_id: TenantShardId,
timeline_id: TimelineId,
lsn: Lsn,
) -> Result<Option<SystemTime>> {
tokio::runtime::Handle::current().block_on(async move {
let mut client = page_api::Client::connect(
connstring.to_string(),
tenant_shard_id.tenant_id,
timeline_id,
tenant_shard_id.to_index(),
auth.map(String::from),
None,
)
.await?;
let req = page_api::LeaseLsnRequest { lsn };
match client.lease_lsn(req).await {
Ok(expires) => Ok(Some(expires)),
// Lease couldn't be acquired because the LSN has been garbage collected.
Err(err) if err.code() == tonic::Code::FailedPrecondition => Ok(None),
Err(err) => Err(err.into()),
}
})
}

View File

@@ -97,34 +97,20 @@ pub(crate) static PG_TOTAL_DOWNTIME_MS: Lazy<GenericCounter<AtomicU64>> = Lazy::
.expect("failed to define a metric")
});
pub(crate) static LFC_PREWARMS: Lazy<IntCounter> = Lazy::new(|| {
/// Needed as neon.file_cache_prewarm_batch == 0 doesn't mean we never tried to prewarm.
/// On the other hand, LFC_PREWARMED_PAGES is excessive as we can GET /lfc/prewarm
pub(crate) static LFC_PREWARM_REQUESTS: Lazy<IntCounter> = Lazy::new(|| {
register_int_counter!(
"compute_ctl_lfc_prewarms_total",
"Total number of LFC prewarms requested by compute_ctl or autoprewarm option",
"compute_ctl_lfc_prewarm_requests_total",
"Total number of LFC prewarm requests made by compute_ctl",
)
.expect("failed to define a metric")
});
pub(crate) static LFC_PREWARM_ERRORS: Lazy<IntCounter> = Lazy::new(|| {
pub(crate) static LFC_OFFLOAD_REQUESTS: Lazy<IntCounter> = Lazy::new(|| {
register_int_counter!(
"compute_ctl_lfc_prewarm_errors_total",
"Total number of LFC prewarm errors",
)
.expect("failed to define a metric")
});
pub(crate) static LFC_OFFLOADS: Lazy<IntCounter> = Lazy::new(|| {
register_int_counter!(
"compute_ctl_lfc_offloads_total",
"Total number of LFC offloads requested by compute_ctl or lfc_offload_period_seconds option",
)
.expect("failed to define a metric")
});
pub(crate) static LFC_OFFLOAD_ERRORS: Lazy<IntCounter> = Lazy::new(|| {
register_int_counter!(
"compute_ctl_lfc_offload_errors_total",
"Total number of LFC offload errors",
"compute_ctl_lfc_offload_requests_total",
"Total number of LFC offload requests made by compute_ctl",
)
.expect("failed to define a metric")
});
@@ -138,9 +124,7 @@ pub fn collect() -> Vec<MetricFamily> {
metrics.extend(AUDIT_LOG_DIR_SIZE.collect());
metrics.extend(PG_CURR_DOWNTIME_MS.collect());
metrics.extend(PG_TOTAL_DOWNTIME_MS.collect());
metrics.extend(LFC_PREWARMS.collect());
metrics.extend(LFC_PREWARM_ERRORS.collect());
metrics.extend(LFC_OFFLOADS.collect());
metrics.extend(LFC_OFFLOAD_ERRORS.collect());
metrics.extend(LFC_PREWARM_REQUESTS.collect());
metrics.extend(LFC_OFFLOAD_REQUESTS.collect());
metrics
}

View File

@@ -1 +0,0 @@
ALTER ROLE {privileged_role_name} BYPASSRLS;

View File

@@ -0,0 +1 @@
ALTER ROLE neon_superuser BYPASSRLS;

View File

@@ -1,21 +1,8 @@
-- On December 8th, 2023, an engineering escalation (INC-110) was opened after
-- it was found that BYPASSRLS was being applied to all roles.
--
-- PR that introduced the issue: https://github.com/neondatabase/neon/pull/5657
-- Subsequent commit on main: https://github.com/neondatabase/neon/commit/ad99fa5f0393e2679e5323df653c508ffa0ac072
--
-- NOBYPASSRLS and INHERIT are the defaults for a Postgres role, but because it
-- isn't easy to know if a Postgres cluster is affected by the issue, we need to
-- keep the migration around for a long time, if not indefinitely, so any
-- cluster can be fixed.
--
-- Branching is the gift that keeps on giving...
DO $$
DECLARE
role_name text;
BEGIN
FOR role_name IN SELECT rolname FROM pg_roles WHERE pg_has_role(rolname, '{privileged_role_name}', 'member')
FOR role_name IN SELECT rolname FROM pg_roles WHERE pg_has_role(rolname, 'neon_superuser', 'member')
LOOP
RAISE NOTICE 'EXECUTING ALTER ROLE % INHERIT', quote_ident(role_name);
EXECUTE 'ALTER ROLE ' || quote_ident(role_name) || ' INHERIT';
@@ -23,7 +10,7 @@ BEGIN
FOR role_name IN SELECT rolname FROM pg_roles
WHERE
NOT pg_has_role(rolname, '{privileged_role_name}', 'member') AND NOT starts_with(rolname, 'pg_')
NOT pg_has_role(rolname, 'neon_superuser', 'member') AND NOT starts_with(rolname, 'pg_')
LOOP
RAISE NOTICE 'EXECUTING ALTER ROLE % NOBYPASSRLS', quote_ident(role_name);
EXECUTE 'ALTER ROLE ' || quote_ident(role_name) || ' NOBYPASSRLS';

View File

@@ -1,6 +1,6 @@
DO $$
BEGIN
IF (SELECT setting::numeric >= 160000 FROM pg_settings WHERE name = 'server_version_num') THEN
EXECUTE 'GRANT pg_create_subscription TO {privileged_role_name}';
EXECUTE 'GRANT pg_create_subscription TO neon_superuser';
END IF;
END $$;

View File

@@ -0,0 +1 @@
GRANT pg_monitor TO neon_superuser WITH ADMIN OPTION;

View File

@@ -1 +0,0 @@
GRANT pg_monitor TO {privileged_role_name} WITH ADMIN OPTION;

View File

@@ -1,4 +1,4 @@
-- SKIP: Deemed insufficient for allowing relations created by extensions to be
-- interacted with by {privileged_role_name} without permission issues.
-- interacted with by neon_superuser without permission issues.
ALTER DEFAULT PRIVILEGES IN SCHEMA public GRANT ALL ON TABLES TO {privileged_role_name};
ALTER DEFAULT PRIVILEGES IN SCHEMA public GRANT ALL ON TABLES TO neon_superuser;

View File

@@ -1,4 +1,4 @@
-- SKIP: Deemed insufficient for allowing relations created by extensions to be
-- interacted with by {privileged_role_name} without permission issues.
-- interacted with by neon_superuser without permission issues.
ALTER DEFAULT PRIVILEGES IN SCHEMA public GRANT ALL ON SEQUENCES TO {privileged_role_name};
ALTER DEFAULT PRIVILEGES IN SCHEMA public GRANT ALL ON SEQUENCES TO neon_superuser;

View File

@@ -1,3 +1,3 @@
-- SKIP: Moved inline to the handle_grants() functions.
ALTER DEFAULT PRIVILEGES IN SCHEMA public GRANT ALL ON TABLES TO {privileged_role_name} WITH GRANT OPTION;
ALTER DEFAULT PRIVILEGES IN SCHEMA public GRANT ALL ON TABLES TO neon_superuser WITH GRANT OPTION;

View File

@@ -1,3 +1,3 @@
-- SKIP: Moved inline to the handle_grants() functions.
ALTER DEFAULT PRIVILEGES IN SCHEMA public GRANT ALL ON SEQUENCES TO {privileged_role_name} WITH GRANT OPTION;
ALTER DEFAULT PRIVILEGES IN SCHEMA public GRANT ALL ON SEQUENCES TO neon_superuser WITH GRANT OPTION;

View File

@@ -1,7 +1,7 @@
DO $$
BEGIN
IF (SELECT setting::numeric >= 160000 FROM pg_settings WHERE name = 'server_version_num') THEN
EXECUTE 'GRANT EXECUTE ON FUNCTION pg_export_snapshot TO {privileged_role_name}';
EXECUTE 'GRANT EXECUTE ON FUNCTION pg_log_standby_snapshot TO {privileged_role_name}';
EXECUTE 'GRANT EXECUTE ON FUNCTION pg_export_snapshot TO neon_superuser';
EXECUTE 'GRANT EXECUTE ON FUNCTION pg_log_standby_snapshot TO neon_superuser';
END IF;
END $$;

View File

@@ -0,0 +1 @@
GRANT EXECUTE ON FUNCTION pg_show_replication_origin_status TO neon_superuser;

View File

@@ -1 +0,0 @@
GRANT EXECUTE ON FUNCTION pg_show_replication_origin_status TO {privileged_role_name};

View File

@@ -1 +0,0 @@
GRANT pg_signal_backend TO {privileged_role_name} WITH ADMIN OPTION;

View File

@@ -7,17 +7,13 @@ BEGIN
INTO monitor
FROM pg_auth_members
WHERE roleid = 'pg_monitor'::regrole
AND member = 'neon_superuser'::regrole;
AND member = 'pg_monitor'::regrole;
IF monitor IS NULL THEN
RAISE EXCEPTION 'no entry in pg_auth_members for neon_superuser and pg_monitor';
END IF;
IF monitor.admin IS NULL OR NOT monitor.member THEN
IF NOT monitor.member THEN
RAISE EXCEPTION 'neon_superuser is not a member of pg_monitor';
END IF;
IF monitor.admin IS NULL OR NOT monitor.admin THEN
IF NOT monitor.admin THEN
RAISE EXCEPTION 'neon_superuser cannot grant pg_monitor';
END IF;
END $$;

View File

@@ -1,23 +0,0 @@
DO $$
DECLARE
signal_backend record;
BEGIN
SELECT pg_has_role('neon_superuser', 'pg_signal_backend', 'member') AS member,
admin_option AS admin
INTO signal_backend
FROM pg_auth_members
WHERE roleid = 'pg_signal_backend'::regrole
AND member = 'neon_superuser'::regrole;
IF signal_backend IS NULL THEN
RAISE EXCEPTION 'no entry in pg_auth_members for neon_superuser and pg_signal_backend';
END IF;
IF signal_backend.member IS NULL OR NOT signal_backend.member THEN
RAISE EXCEPTION 'neon_superuser is not a member of pg_signal_backend';
END IF;
IF signal_backend.admin IS NULL OR NOT signal_backend.admin THEN
RAISE EXCEPTION 'neon_superuser cannot grant pg_signal_backend';
END IF;
END $$;

Some files were not shown because too many files have changed in this diff Show More